diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/log.txt b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..42380ce3ecf8edebf088c2d5b1c05e89e228786d --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,961 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 22:56:30 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:55 lr: nan time: 3.7392 data: 3.1189 max mem: 21740 +train: [0] [ 20/400] eta: 0:04:00 lr: 0.000003 loss: 3.1832 (3.1836) grad: 0.0656 (0.0658) time: 0.4766 data: 0.0028 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:16 lr: 0.000006 loss: 3.1826 (3.1819) grad: 0.0628 (0.0629) time: 0.4565 data: 0.0049 max mem: 22448 +train: [0] [ 60/400] eta: 0:02:54 lr: 0.000009 loss: 3.1702 (3.1756) grad: 0.0585 (0.0611) time: 0.4441 data: 0.0044 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:39 lr: 0.000012 loss: 3.1592 (3.1711) grad: 0.0600 (0.0619) time: 0.4536 data: 0.0049 max mem: 22448 +train: [0] [100/400] eta: 0:02:26 lr: 0.000015 loss: 3.1544 (3.1684) grad: 0.0620 (0.0620) time: 0.4503 data: 0.0047 max mem: 22448 +train: [0] [120/400] eta: 0:02:15 lr: 0.000018 loss: 3.1576 (3.1672) grad: 0.0605 (0.0619) time: 0.4580 data: 0.0046 max mem: 22448 +train: [0] [140/400] eta: 0:02:04 lr: 0.000021 loss: 3.1577 (3.1662) grad: 0.0584 (0.0614) time: 0.4571 data: 0.0046 max mem: 22448 +train: [0] [160/400] eta: 0:01:54 lr: 0.000024 loss: 3.1545 (3.1645) grad: 0.0589 (0.0615) time: 0.4588 data: 0.0046 max mem: 22448 +train: [0] [180/400] eta: 0:01:44 lr: 0.000027 loss: 3.1545 (3.1635) grad: 0.0584 (0.0614) time: 0.4646 data: 0.0048 max mem: 22448 +train: [0] [200/400] eta: 0:01:34 lr: 0.000030 loss: 3.1546 (3.1622) grad: 0.0571 (0.0610) time: 0.4618 data: 0.0049 max mem: 22448 +train: [0] [220/400] eta: 0:01:25 lr: 0.000033 loss: 3.1326 (3.1588) grad: 0.0602 (0.0615) time: 0.4582 data: 0.0047 max mem: 22448 +train: [0] [240/400] eta: 0:01:15 lr: 0.000036 loss: 3.1312 (3.1562) grad: 0.0665 (0.0619) time: 0.4478 data: 0.0048 max mem: 22448 +train: [0] [260/400] eta: 0:01:05 lr: 0.000039 loss: 3.1334 (3.1538) grad: 0.0672 (0.0625) time: 0.4589 data: 0.0048 max mem: 22448 +train: [0] [280/400] eta: 0:00:56 lr: 0.000042 loss: 3.1168 (3.1511) grad: 0.0700 (0.0631) time: 0.4450 data: 0.0045 max mem: 22448 +train: [0] [300/400] eta: 0:00:46 lr: 0.000045 loss: 3.1093 (3.1473) grad: 0.0741 (0.0642) time: 0.4558 data: 0.0049 max mem: 22448 +train: [0] [320/400] eta: 0:00:37 lr: 0.000048 loss: 3.0842 (3.1431) grad: 0.0807 (0.0651) time: 0.4593 data: 0.0047 max mem: 22448 +train: [0] [340/400] eta: 0:00:27 lr: 0.000051 loss: 3.0729 (3.1389) grad: 0.0807 (0.0660) time: 0.4520 data: 0.0045 max mem: 22448 +train: [0] [360/400] eta: 0:00:18 lr: 0.000054 loss: 3.0650 (3.1339) grad: 0.0853 (0.0673) time: 0.4535 data: 0.0044 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0628 (3.1300) grad: 0.0916 (0.0686) time: 0.4671 data: 0.0047 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0485 (3.1249) grad: 0.0957 (0.0701) time: 0.4557 data: 0.0048 max mem: 22448 +train: [0] Total time: 0:03:06 (0.4656 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0485 (3.1249) grad: 0.0957 (0.0701) +eval (validation): [0] [ 0/85] eta: 0:04:34 time: 3.2325 data: 2.9472 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:33 time: 0.3834 data: 0.0063 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:19 time: 0.3266 data: 0.0035 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3336 data: 0.0040 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3260 data: 0.0041 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3193 data: 0.0041 max mem: 22448 +eval (validation): [0] Total time: 0:00:32 (0.3777 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.541 acc: 0.237 f1: 0.159 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:24 lr: nan time: 3.3621 data: 2.9400 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:53 lr: 0.000063 loss: 3.0199 (3.0311) grad: 0.0985 (0.0994) time: 0.4784 data: 0.0029 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:12 lr: 0.000066 loss: 3.0101 (3.0162) grad: 0.0985 (0.0975) time: 0.4517 data: 0.0048 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:52 lr: 0.000069 loss: 3.0071 (3.0169) grad: 0.0924 (0.0960) time: 0.4458 data: 0.0048 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:38 lr: 0.000072 loss: 3.0141 (3.0173) grad: 0.0931 (0.0962) time: 0.4588 data: 0.0049 max mem: 22448 +train: [1] [100/400] eta: 0:02:26 lr: 0.000075 loss: 2.9947 (3.0068) grad: 0.0965 (0.0967) time: 0.4564 data: 0.0047 max mem: 22448 +train: [1] [120/400] eta: 0:02:15 lr: 0.000078 loss: 2.9657 (3.0015) grad: 0.1062 (0.0999) time: 0.4593 data: 0.0048 max mem: 22448 +train: [1] [140/400] eta: 0:02:04 lr: 0.000081 loss: 2.9748 (2.9973) grad: 0.1029 (0.0993) time: 0.4554 data: 0.0047 max mem: 22448 +train: [1] [160/400] eta: 0:01:54 lr: 0.000084 loss: 2.9728 (2.9922) grad: 0.0999 (0.1004) time: 0.4562 data: 0.0049 max mem: 22448 +train: [1] [180/400] eta: 0:01:44 lr: 0.000087 loss: 2.9694 (2.9877) grad: 0.1066 (0.1013) time: 0.4577 data: 0.0047 max mem: 22448 +train: [1] [200/400] eta: 0:01:34 lr: 0.000090 loss: 2.9567 (2.9838) grad: 0.1066 (0.1016) time: 0.4596 data: 0.0047 max mem: 22448 +train: [1] [220/400] eta: 0:01:25 lr: 0.000093 loss: 2.9334 (2.9796) grad: 0.1072 (0.1026) time: 0.4718 data: 0.0047 max mem: 22448 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 2.9427 (2.9765) grad: 0.1162 (0.1038) time: 0.4508 data: 0.0047 max mem: 22448 +train: [1] [260/400] eta: 0:01:05 lr: 0.000099 loss: 2.9250 (2.9718) grad: 0.1162 (0.1046) time: 0.4531 data: 0.0048 max mem: 22448 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 2.8963 (2.9668) grad: 0.1146 (0.1055) time: 0.4612 data: 0.0046 max mem: 22448 +train: [1] [300/400] eta: 0:00:46 lr: 0.000105 loss: 2.9149 (2.9639) grad: 0.1115 (0.1059) time: 0.4579 data: 0.0046 max mem: 22448 +train: [1] [320/400] eta: 0:00:37 lr: 0.000108 loss: 2.9239 (2.9611) grad: 0.1120 (0.1068) time: 0.4726 data: 0.0049 max mem: 22448 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 2.8879 (2.9562) grad: 0.1230 (0.1078) time: 0.4618 data: 0.0048 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.8760 (2.9528) grad: 0.1195 (0.1085) time: 0.4631 data: 0.0048 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.8755 (2.9500) grad: 0.1187 (0.1092) time: 0.4601 data: 0.0048 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.8940 (2.9479) grad: 0.1224 (0.1099) time: 0.4708 data: 0.0048 max mem: 22448 +train: [1] Total time: 0:03:07 (0.4679 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.8940 (2.9479) grad: 0.1224 (0.1099) +eval (validation): [1] [ 0/85] eta: 0:04:32 time: 3.2008 data: 2.9220 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:32 time: 0.3654 data: 0.0049 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3245 data: 0.0040 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3496 data: 0.0040 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3447 data: 0.0043 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3389 data: 0.0042 max mem: 22448 +eval (validation): [1] Total time: 0:00:32 (0.3823 s / it) +cv: [1] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 2.490 acc: 0.254 f1: 0.183 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:34 lr: nan time: 3.3865 data: 2.9748 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:46 lr: 0.000123 loss: 2.8588 (2.8603) grad: 0.1228 (0.1260) time: 0.4567 data: 0.0038 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:10 lr: 0.000126 loss: 2.8441 (2.8389) grad: 0.1259 (0.1291) time: 0.4601 data: 0.0048 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:51 lr: 0.000129 loss: 2.8232 (2.8379) grad: 0.1322 (0.1310) time: 0.4550 data: 0.0051 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:37 lr: 0.000132 loss: 2.8416 (2.8483) grad: 0.1330 (0.1317) time: 0.4554 data: 0.0048 max mem: 22448 +train: [2] [100/400] eta: 0:02:25 lr: 0.000135 loss: 2.8670 (2.8513) grad: 0.1382 (0.1352) time: 0.4562 data: 0.0047 max mem: 22448 +train: [2] [120/400] eta: 0:02:14 lr: 0.000138 loss: 2.8486 (2.8485) grad: 0.1388 (0.1358) time: 0.4620 data: 0.0049 max mem: 22448 +train: [2] [140/400] eta: 0:02:04 lr: 0.000141 loss: 2.8444 (2.8490) grad: 0.1379 (0.1371) time: 0.4662 data: 0.0049 max mem: 22448 +train: [2] [160/400] eta: 0:01:54 lr: 0.000144 loss: 2.8340 (2.8465) grad: 0.1486 (0.1390) time: 0.4594 data: 0.0046 max mem: 22448 +train: [2] [180/400] eta: 0:01:44 lr: 0.000147 loss: 2.8234 (2.8443) grad: 0.1532 (0.1412) time: 0.4768 data: 0.0048 max mem: 22448 +train: [2] [200/400] eta: 0:01:35 lr: 0.000150 loss: 2.8362 (2.8474) grad: 0.1556 (0.1428) time: 0.4615 data: 0.0048 max mem: 22448 +train: [2] [220/400] eta: 0:01:25 lr: 0.000153 loss: 2.8389 (2.8454) grad: 0.1490 (0.1432) time: 0.4593 data: 0.0048 max mem: 22448 +train: [2] [240/400] eta: 0:01:15 lr: 0.000156 loss: 2.8300 (2.8418) grad: 0.1446 (0.1432) time: 0.4589 data: 0.0046 max mem: 22448 +train: [2] [260/400] eta: 0:01:06 lr: 0.000159 loss: 2.7906 (2.8373) grad: 0.1416 (0.1432) time: 0.4612 data: 0.0047 max mem: 22448 +train: [2] [280/400] eta: 0:00:56 lr: 0.000162 loss: 2.7605 (2.8346) grad: 0.1420 (0.1432) time: 0.4633 data: 0.0045 max mem: 22448 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 2.8248 (2.8359) grad: 0.1464 (0.1437) time: 0.4593 data: 0.0047 max mem: 22448 +train: [2] [320/400] eta: 0:00:37 lr: 0.000168 loss: 2.8130 (2.8322) grad: 0.1442 (0.1436) time: 0.4607 data: 0.0047 max mem: 22448 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 2.7704 (2.8296) grad: 0.1409 (0.1438) time: 0.4582 data: 0.0047 max mem: 22448 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 2.7586 (2.8267) grad: 0.1418 (0.1441) time: 0.4606 data: 0.0048 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.7900 (2.8255) grad: 0.1483 (0.1444) time: 0.4683 data: 0.0046 max mem: 22448 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.7997 (2.8243) grad: 0.1486 (0.1446) time: 0.4559 data: 0.0050 max mem: 22448 +train: [2] Total time: 0:03:07 (0.4686 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.7997 (2.8243) grad: 0.1486 (0.1446) +eval (validation): [2] [ 0/85] eta: 0:04:31 time: 3.1920 data: 2.9057 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:31 time: 0.3483 data: 0.0048 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3473 data: 0.0039 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3511 data: 0.0044 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3253 data: 0.0039 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3169 data: 0.0039 max mem: 22448 +eval (validation): [2] Total time: 0:00:32 (0.3783 s / it) +cv: [2] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 2.473 acc: 0.250 f1: 0.176 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [3] [ 0/400] eta: 0:21:53 lr: nan time: 3.2826 data: 2.8723 max mem: 22448 +train: [3] [ 20/400] eta: 0:03:44 lr: 0.000183 loss: 2.7278 (2.7504) grad: 0.1505 (0.1579) time: 0.4562 data: 0.0048 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:09 lr: 0.000186 loss: 2.7490 (2.7629) grad: 0.1670 (0.1661) time: 0.4593 data: 0.0045 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:51 lr: 0.000189 loss: 2.7355 (2.7536) grad: 0.1647 (0.1630) time: 0.4575 data: 0.0049 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:36 lr: 0.000192 loss: 2.7086 (2.7445) grad: 0.1600 (0.1651) time: 0.4476 data: 0.0051 max mem: 22448 +train: [3] [100/400] eta: 0:02:24 lr: 0.000195 loss: 2.7523 (2.7530) grad: 0.1733 (0.1699) time: 0.4541 data: 0.0049 max mem: 22448 +train: [3] [120/400] eta: 0:02:14 lr: 0.000198 loss: 2.8161 (2.7771) grad: 0.2253 (0.2089) time: 0.4609 data: 0.0048 max mem: 22448 +WARNING: classifier 48 (50, 1.0) diverged (loss=84.15 > 63.56) at step 665. Freezing. +train: [3] [140/400] eta: 0:02:03 lr: 0.000201 loss: 2.8529 (2.8387) grad: 0.3532 (0.2663) time: 0.4558 data: 0.0048 max mem: 22448 +train: [3] [160/400] eta: 0:01:53 lr: 0.000204 loss: 2.8340 (2.8302) grad: 0.1568 (0.2522) time: 0.4510 data: 0.0047 max mem: 22448 +train: [3] [180/400] eta: 0:01:43 lr: 0.000207 loss: 2.7693 (2.8247) grad: 0.1559 (0.2417) time: 0.4491 data: 0.0048 max mem: 22448 +train: [3] [200/400] eta: 0:01:33 lr: 0.000210 loss: 2.8063 (2.8236) grad: 0.1562 (0.2337) time: 0.4580 data: 0.0052 max mem: 22448 +train: [3] [220/400] eta: 0:01:24 lr: 0.000213 loss: 2.7817 (2.8158) grad: 0.1620 (0.2275) time: 0.4598 data: 0.0048 max mem: 22448 +train: [3] [240/400] eta: 0:01:14 lr: 0.000216 loss: 2.7265 (2.8076) grad: 0.1628 (0.2219) time: 0.4469 data: 0.0048 max mem: 22448 +train: [3] [260/400] eta: 0:01:05 lr: 0.000219 loss: 2.7440 (2.8039) grad: 0.1629 (0.2174) time: 0.4526 data: 0.0048 max mem: 22448 +train: [3] [280/400] eta: 0:00:55 lr: 0.000222 loss: 2.7631 (2.8002) grad: 0.1622 (0.2138) time: 0.4554 data: 0.0049 max mem: 22448 +train: [3] [300/400] eta: 0:00:46 lr: 0.000225 loss: 2.7559 (2.7964) grad: 0.1599 (0.2103) time: 0.4531 data: 0.0046 max mem: 22448 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 2.7241 (2.7925) grad: 0.1599 (0.2073) time: 0.4531 data: 0.0045 max mem: 22448 +train: [3] [340/400] eta: 0:00:27 lr: 0.000231 loss: 2.7235 (2.7876) grad: 0.1627 (0.2050) time: 0.4658 data: 0.0048 max mem: 22448 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 2.7110 (2.7840) grad: 0.1561 (0.2022) time: 0.4575 data: 0.0049 max mem: 22448 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 2.7266 (2.7815) grad: 0.1561 (0.2001) time: 0.4767 data: 0.0052 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.7305 (2.7776) grad: 0.1711 (0.1991) time: 0.4610 data: 0.0051 max mem: 22448 +train: [3] Total time: 0:03:05 (0.4642 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.7305 (2.7776) grad: 0.1711 (0.1991) +eval (validation): [3] [ 0/85] eta: 0:04:20 time: 3.0661 data: 2.8188 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:32 time: 0.3652 data: 0.0230 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:19 time: 0.3613 data: 0.0043 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:10 time: 0.3598 data: 0.0043 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3231 data: 0.0041 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3165 data: 0.0041 max mem: 22448 +eval (validation): [3] Total time: 0:00:32 (0.3852 s / it) +cv: [3] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 2.433 acc: 0.267 f1: 0.194 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:20:18 lr: nan time: 3.0474 data: 2.7182 max mem: 22448 +train: [4] [ 20/400] eta: 0:03:31 lr: 0.000243 loss: 2.6835 (2.7030) grad: 0.1792 (0.1822) time: 0.4313 data: 0.0051 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:01 lr: 0.000246 loss: 2.6855 (2.7080) grad: 0.1792 (0.1798) time: 0.4523 data: 0.0048 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:46 lr: 0.000249 loss: 2.7212 (2.7087) grad: 0.1809 (0.1789) time: 0.4590 data: 0.0049 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:33 lr: 0.000252 loss: 2.6987 (2.7019) grad: 0.1732 (0.1773) time: 0.4502 data: 0.0050 max mem: 22448 +train: [4] [100/400] eta: 0:02:22 lr: 0.000255 loss: 2.6568 (2.6969) grad: 0.1832 (0.1833) time: 0.4568 data: 0.0049 max mem: 22448 +train: [4] [120/400] eta: 0:02:12 lr: 0.000258 loss: 2.7616 (2.7478) grad: 0.2340 (0.2602) time: 0.4553 data: 0.0048 max mem: 22448 +WARNING: classifier 47 (43, 1.0) diverged (loss=63.92 > 63.56) at step 863. Freezing. +train: [4] [140/400] eta: 0:02:01 lr: 0.000261 loss: 2.8308 (2.8031) grad: 0.3600 (0.2988) time: 0.4474 data: 0.0048 max mem: 22448 +train: [4] [160/400] eta: 0:01:52 lr: 0.000264 loss: 2.8825 (2.8260) grad: 0.3292 (0.3436) time: 0.4552 data: 0.0049 max mem: 22448 +WARNING: classifier 46 (36, 1.0) diverged (loss=121.06 > 63.56) at step 886. Freezing. +train: [4] [180/400] eta: 0:01:42 lr: 0.000267 loss: 2.9433 (2.8849) grad: 0.5791 (0.4251) time: 0.4468 data: 0.0047 max mem: 22448 +train: [4] [200/400] eta: 0:01:32 lr: 0.000270 loss: 2.7390 (2.8664) grad: 0.1689 (0.3999) time: 0.4481 data: 0.0047 max mem: 22448 +train: [4] [220/400] eta: 0:01:22 lr: 0.000273 loss: 2.6810 (2.8513) grad: 0.1689 (0.3791) time: 0.4389 data: 0.0047 max mem: 22448 +train: [4] [240/400] eta: 0:01:13 lr: 0.000276 loss: 2.6943 (2.8404) grad: 0.1702 (0.3618) time: 0.4485 data: 0.0048 max mem: 22448 +train: [4] [260/400] eta: 0:01:04 lr: 0.000279 loss: 2.6938 (2.8285) grad: 0.1679 (0.3472) time: 0.4477 data: 0.0048 max mem: 22448 +train: [4] [280/400] eta: 0:00:54 lr: 0.000282 loss: 2.6569 (2.8163) grad: 0.1699 (0.3346) time: 0.4448 data: 0.0047 max mem: 22448 +train: [4] [300/400] eta: 0:00:45 lr: 0.000285 loss: 2.6634 (2.8088) grad: 0.1675 (0.3235) time: 0.4414 data: 0.0047 max mem: 22448 +train: [4] [320/400] eta: 0:00:36 lr: 0.000288 loss: 2.6876 (2.8027) grad: 0.1659 (0.3138) time: 0.4524 data: 0.0047 max mem: 22448 +train: [4] [340/400] eta: 0:00:27 lr: 0.000291 loss: 2.6703 (2.7945) grad: 0.1638 (0.3048) time: 0.4479 data: 0.0047 max mem: 22448 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 2.6777 (2.7903) grad: 0.1638 (0.2975) time: 0.4672 data: 0.0050 max mem: 22448 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.7067 (2.7872) grad: 0.1694 (0.2907) time: 0.4608 data: 0.0048 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.7062 (2.7821) grad: 0.1653 (0.2844) time: 0.4412 data: 0.0046 max mem: 22448 +train: [4] Total time: 0:03:02 (0.4567 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.7062 (2.7821) grad: 0.1653 (0.2844) +eval (validation): [4] [ 0/85] eta: 0:04:40 time: 3.3032 data: 3.0073 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3560 data: 0.0055 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:19 time: 0.3456 data: 0.0038 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3594 data: 0.0046 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3143 data: 0.0043 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3087 data: 0.0042 max mem: 22448 +eval (validation): [4] Total time: 0:00:32 (0.3805 s / it) +cv: [4] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.390 acc: 0.293 f1: 0.215 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:20:16 lr: nan time: 3.0404 data: 2.6629 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:35 lr: 0.000300 loss: 2.6227 (2.6423) grad: 0.1650 (0.1733) time: 0.4442 data: 0.0052 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:02 lr: 0.000300 loss: 2.6351 (2.6429) grad: 0.1665 (0.1694) time: 0.4420 data: 0.0041 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:45 lr: 0.000300 loss: 2.6386 (2.6503) grad: 0.1676 (0.1704) time: 0.4472 data: 0.0050 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:32 lr: 0.000300 loss: 2.6047 (2.6370) grad: 0.1668 (0.1684) time: 0.4470 data: 0.0050 max mem: 22448 +train: [5] [100/400] eta: 0:02:21 lr: 0.000300 loss: 2.6441 (2.6487) grad: 0.1668 (0.1691) time: 0.4542 data: 0.0048 max mem: 22448 +train: [5] [120/400] eta: 0:02:10 lr: 0.000300 loss: 2.6440 (2.6401) grad: 0.1774 (0.1729) time: 0.4412 data: 0.0048 max mem: 22448 +train: [5] [140/400] eta: 0:02:00 lr: 0.000300 loss: 2.6157 (2.6468) grad: 0.1951 (0.1762) time: 0.4506 data: 0.0046 max mem: 22448 +train: [5] [160/400] eta: 0:01:51 lr: 0.000299 loss: 2.6991 (2.6586) grad: 0.1953 (0.1787) time: 0.4507 data: 0.0048 max mem: 22448 +train: [5] [180/400] eta: 0:01:41 lr: 0.000299 loss: 2.6098 (2.6516) grad: 0.1866 (0.1786) time: 0.4561 data: 0.0050 max mem: 22448 +train: [5] [200/400] eta: 0:01:32 lr: 0.000299 loss: 2.6098 (2.6523) grad: 0.1767 (0.1790) time: 0.4460 data: 0.0048 max mem: 22448 +train: [5] [220/400] eta: 0:01:22 lr: 0.000299 loss: 2.6210 (2.6483) grad: 0.1786 (0.1792) time: 0.4391 data: 0.0047 max mem: 22448 +train: [5] [240/400] eta: 0:01:13 lr: 0.000299 loss: 2.6375 (2.6532) grad: 0.1775 (0.1796) time: 0.4534 data: 0.0049 max mem: 22448 +train: [5] [260/400] eta: 0:01:03 lr: 0.000299 loss: 2.6665 (2.6538) grad: 0.1785 (0.1809) time: 0.4415 data: 0.0048 max mem: 22448 +train: [5] [280/400] eta: 0:00:54 lr: 0.000298 loss: 2.6591 (2.6546) grad: 0.2080 (0.1838) time: 0.4480 data: 0.0049 max mem: 22448 +train: [5] [300/400] eta: 0:00:45 lr: 0.000298 loss: 2.7308 (2.6673) grad: 0.2485 (0.2010) time: 0.4538 data: 0.0051 max mem: 22448 +train: [5] [320/400] eta: 0:00:36 lr: 0.000298 loss: 2.9922 (2.7073) grad: 0.8482 (0.2627) time: 0.4526 data: 0.0051 max mem: 22448 +WARNING: classifier 44 (26, 1.0) diverged (loss=84.31 > 63.56) at step 1161. Freezing. +train: [5] [340/400] eta: 0:00:27 lr: 0.000298 loss: 2.9380 (2.7124) grad: 0.8607 (0.2677) time: 0.4617 data: 0.0049 max mem: 22448 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 2.5744 (2.7036) grad: 0.1693 (0.2620) time: 0.4459 data: 0.0050 max mem: 22448 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.5953 (2.6988) grad: 0.1696 (0.2572) time: 0.4522 data: 0.0050 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.6457 (2.6974) grad: 0.1714 (0.2530) time: 0.4411 data: 0.0046 max mem: 22448 +train: [5] Total time: 0:03:02 (0.4554 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.6457 (2.6974) grad: 0.1714 (0.2530) +eval (validation): [5] [ 0/85] eta: 0:04:34 time: 3.2257 data: 2.9213 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:33 time: 0.3779 data: 0.0061 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3275 data: 0.0033 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3436 data: 0.0040 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3310 data: 0.0039 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3252 data: 0.0037 max mem: 22448 +eval (validation): [5] Total time: 0:00:32 (0.3809 s / it) +cv: [5] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.385 acc: 0.287 f1: 0.221 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:20:52 lr: nan time: 3.1321 data: 2.7438 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:38 lr: 0.000296 loss: 2.5801 (2.6110) grad: 0.1612 (0.1624) time: 0.4481 data: 0.0042 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:03 lr: 0.000296 loss: 2.5941 (2.6121) grad: 0.1580 (0.1614) time: 0.4397 data: 0.0040 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:46 lr: 0.000296 loss: 2.5889 (2.6021) grad: 0.1607 (0.1627) time: 0.4469 data: 0.0051 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:32 lr: 0.000295 loss: 2.5691 (2.5969) grad: 0.1688 (0.1653) time: 0.4429 data: 0.0042 max mem: 22448 +train: [6] [100/400] eta: 0:02:22 lr: 0.000295 loss: 2.5517 (2.5895) grad: 0.1722 (0.1671) time: 0.4577 data: 0.0048 max mem: 22448 +train: [6] [120/400] eta: 0:02:11 lr: 0.000295 loss: 2.5508 (2.5870) grad: 0.1734 (0.1683) time: 0.4478 data: 0.0050 max mem: 22448 +train: [6] [140/400] eta: 0:02:01 lr: 0.000294 loss: 2.5508 (2.5842) grad: 0.1712 (0.1690) time: 0.4449 data: 0.0047 max mem: 22448 +train: [6] [160/400] eta: 0:01:51 lr: 0.000294 loss: 2.5511 (2.5810) grad: 0.1706 (0.1687) time: 0.4478 data: 0.0048 max mem: 22448 +train: [6] [180/400] eta: 0:01:41 lr: 0.000293 loss: 2.5347 (2.5771) grad: 0.1708 (0.1687) time: 0.4518 data: 0.0050 max mem: 22448 +train: [6] [200/400] eta: 0:01:32 lr: 0.000293 loss: 2.5536 (2.5771) grad: 0.1708 (0.1690) time: 0.4505 data: 0.0049 max mem: 22448 +train: [6] [220/400] eta: 0:01:22 lr: 0.000292 loss: 2.5536 (2.5739) grad: 0.1664 (0.1689) time: 0.4369 data: 0.0048 max mem: 22448 +train: [6] [240/400] eta: 0:01:13 lr: 0.000292 loss: 2.5488 (2.5727) grad: 0.1664 (0.1689) time: 0.4439 data: 0.0049 max mem: 22448 +train: [6] [260/400] eta: 0:01:03 lr: 0.000291 loss: 2.6025 (2.5766) grad: 0.1753 (0.1701) time: 0.4495 data: 0.0047 max mem: 22448 +train: [6] [280/400] eta: 0:00:54 lr: 0.000291 loss: 2.6025 (2.5774) grad: 0.1790 (0.1707) time: 0.4515 data: 0.0048 max mem: 22448 +train: [6] [300/400] eta: 0:00:45 lr: 0.000290 loss: 2.5403 (2.5750) grad: 0.1787 (0.1712) time: 0.4446 data: 0.0047 max mem: 22448 +train: [6] [320/400] eta: 0:00:36 lr: 0.000290 loss: 2.5288 (2.5719) grad: 0.1770 (0.1717) time: 0.4497 data: 0.0047 max mem: 22448 +train: [6] [340/400] eta: 0:00:27 lr: 0.000289 loss: 2.5457 (2.5710) grad: 0.1732 (0.1716) time: 0.4458 data: 0.0046 max mem: 22448 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 2.5423 (2.5691) grad: 0.1699 (0.1716) time: 0.4594 data: 0.0048 max mem: 22448 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 2.5170 (2.5695) grad: 0.1739 (0.1718) time: 0.4513 data: 0.0049 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.5154 (2.5676) grad: 0.1789 (0.1722) time: 0.4487 data: 0.0047 max mem: 22448 +train: [6] Total time: 0:03:02 (0.4552 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.5154 (2.5676) grad: 0.1789 (0.1722) +eval (validation): [6] [ 0/85] eta: 0:04:39 time: 3.2910 data: 3.0137 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:33 time: 0.3838 data: 0.0057 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:19 time: 0.3293 data: 0.0034 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3350 data: 0.0040 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3317 data: 0.0039 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3220 data: 0.0037 max mem: 22448 +eval (validation): [6] Total time: 0:00:32 (0.3809 s / it) +cv: [6] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.393 acc: 0.281 f1: 0.209 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:20:57 lr: nan time: 3.1439 data: 2.8093 max mem: 22448 +train: [7] [ 20/400] eta: 0:03:39 lr: 0.000286 loss: 2.4979 (2.5160) grad: 0.1839 (0.1817) time: 0.4500 data: 0.0044 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:04 lr: 0.000286 loss: 2.5119 (2.5207) grad: 0.1845 (0.1821) time: 0.4436 data: 0.0045 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:46 lr: 0.000285 loss: 2.5484 (2.5311) grad: 0.1834 (0.1813) time: 0.4425 data: 0.0044 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:33 lr: 0.000284 loss: 2.5347 (2.5196) grad: 0.1775 (0.1787) time: 0.4446 data: 0.0046 max mem: 22448 +train: [7] [100/400] eta: 0:02:21 lr: 0.000284 loss: 2.5050 (2.5266) grad: 0.1723 (0.1781) time: 0.4524 data: 0.0047 max mem: 22448 +train: [7] [120/400] eta: 0:02:11 lr: 0.000283 loss: 2.5189 (2.5255) grad: 0.1723 (0.1774) time: 0.4491 data: 0.0050 max mem: 22448 +train: [7] [140/400] eta: 0:02:01 lr: 0.000282 loss: 2.4987 (2.5228) grad: 0.1766 (0.1774) time: 0.4490 data: 0.0048 max mem: 22448 +train: [7] [160/400] eta: 0:01:50 lr: 0.000282 loss: 2.5224 (2.5271) grad: 0.1710 (0.1765) time: 0.4341 data: 0.0046 max mem: 22448 +train: [7] [180/400] eta: 0:01:41 lr: 0.000281 loss: 2.5617 (2.5299) grad: 0.1713 (0.1767) time: 0.4488 data: 0.0046 max mem: 22448 +train: [7] [200/400] eta: 0:01:31 lr: 0.000280 loss: 2.5282 (2.5282) grad: 0.1744 (0.1768) time: 0.4492 data: 0.0045 max mem: 22448 +train: [7] [220/400] eta: 0:01:22 lr: 0.000279 loss: 2.5315 (2.5329) grad: 0.1750 (0.1769) time: 0.4369 data: 0.0045 max mem: 22448 +train: [7] [240/400] eta: 0:01:13 lr: 0.000278 loss: 2.5273 (2.5313) grad: 0.1721 (0.1767) time: 0.4495 data: 0.0048 max mem: 22448 +train: [7] [260/400] eta: 0:01:03 lr: 0.000278 loss: 2.5236 (2.5353) grad: 0.1709 (0.1768) time: 0.4412 data: 0.0045 max mem: 22448 +train: [7] [280/400] eta: 0:00:54 lr: 0.000277 loss: 2.5236 (2.5334) grad: 0.1725 (0.1764) time: 0.4347 data: 0.0047 max mem: 22448 +train: [7] [300/400] eta: 0:00:45 lr: 0.000276 loss: 2.4931 (2.5299) grad: 0.1725 (0.1766) time: 0.4484 data: 0.0049 max mem: 22448 +train: [7] [320/400] eta: 0:00:36 lr: 0.000275 loss: 2.4472 (2.5258) grad: 0.1755 (0.1768) time: 0.4438 data: 0.0047 max mem: 22448 +train: [7] [340/400] eta: 0:00:27 lr: 0.000274 loss: 2.4987 (2.5254) grad: 0.1743 (0.1768) time: 0.4510 data: 0.0049 max mem: 22448 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 2.4953 (2.5212) grad: 0.1756 (0.1771) time: 0.4498 data: 0.0049 max mem: 22448 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 2.4953 (2.5211) grad: 0.1756 (0.1772) time: 0.4523 data: 0.0049 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.5028 (2.5214) grad: 0.1786 (0.1774) time: 0.4613 data: 0.0048 max mem: 22448 +train: [7] Total time: 0:03:01 (0.4539 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.5028 (2.5214) grad: 0.1786 (0.1774) +eval (validation): [7] [ 0/85] eta: 0:04:42 time: 3.3205 data: 3.0543 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:33 time: 0.3774 data: 0.0038 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3612 data: 0.0038 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3315 data: 0.0040 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3302 data: 0.0043 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3262 data: 0.0042 max mem: 22448 +eval (validation): [7] Total time: 0:00:32 (0.3877 s / it) +cv: [7] best hparam: (0.72, 1.0) (022) ('022_lr7.2e-01_wd1.0e+00') loss: 2.358 acc: 0.292 f1: 0.221 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:21:03 lr: nan time: 3.1580 data: 2.7863 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:44 lr: 0.000270 loss: 2.4076 (2.4419) grad: 0.1663 (0.1701) time: 0.4627 data: 0.0038 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:04 lr: 0.000270 loss: 2.4472 (2.4576) grad: 0.1696 (0.1722) time: 0.4312 data: 0.0048 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:47 lr: 0.000269 loss: 2.4815 (2.4668) grad: 0.1753 (0.1731) time: 0.4518 data: 0.0049 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:33 lr: 0.000268 loss: 2.4815 (2.4729) grad: 0.1788 (0.1761) time: 0.4438 data: 0.0047 max mem: 22448 +train: [8] [100/400] eta: 0:02:22 lr: 0.000267 loss: 2.4938 (2.4853) grad: 0.1818 (0.1768) time: 0.4439 data: 0.0048 max mem: 22448 +train: [8] [120/400] eta: 0:02:11 lr: 0.000266 loss: 2.4625 (2.4723) grad: 0.1737 (0.1759) time: 0.4475 data: 0.0050 max mem: 22448 +train: [8] [140/400] eta: 0:02:01 lr: 0.000265 loss: 2.4240 (2.4659) grad: 0.1760 (0.1773) time: 0.4456 data: 0.0048 max mem: 22448 +train: [8] [160/400] eta: 0:01:50 lr: 0.000264 loss: 2.4165 (2.4647) grad: 0.1862 (0.1788) time: 0.4379 data: 0.0049 max mem: 22448 +train: [8] [180/400] eta: 0:01:41 lr: 0.000263 loss: 2.3907 (2.4569) grad: 0.1835 (0.1791) time: 0.4347 data: 0.0047 max mem: 22448 +train: [8] [200/400] eta: 0:01:31 lr: 0.000262 loss: 2.4180 (2.4593) grad: 0.1815 (0.1800) time: 0.4313 data: 0.0049 max mem: 22448 +train: [8] [220/400] eta: 0:01:21 lr: 0.000260 loss: 2.4712 (2.4588) grad: 0.1815 (0.1798) time: 0.4360 data: 0.0048 max mem: 22448 +train: [8] [240/400] eta: 0:01:12 lr: 0.000259 loss: 2.4520 (2.4584) grad: 0.1831 (0.1809) time: 0.4338 data: 0.0047 max mem: 22448 +train: [8] [260/400] eta: 0:01:03 lr: 0.000258 loss: 2.4694 (2.4611) grad: 0.1876 (0.1813) time: 0.4360 data: 0.0047 max mem: 22448 +train: [8] [280/400] eta: 0:00:54 lr: 0.000257 loss: 2.5119 (2.4641) grad: 0.1849 (0.1813) time: 0.4367 data: 0.0049 max mem: 22448 +train: [8] [300/400] eta: 0:00:45 lr: 0.000256 loss: 2.5070 (2.4677) grad: 0.1856 (0.1819) time: 0.4442 data: 0.0046 max mem: 22448 +train: [8] [320/400] eta: 0:00:35 lr: 0.000255 loss: 2.5047 (2.4679) grad: 0.1858 (0.1822) time: 0.4275 data: 0.0049 max mem: 22448 +train: [8] [340/400] eta: 0:00:26 lr: 0.000254 loss: 2.5040 (2.4687) grad: 0.1858 (0.1823) time: 0.4333 data: 0.0047 max mem: 22448 +train: [8] [360/400] eta: 0:00:17 lr: 0.000253 loss: 2.5040 (2.4695) grad: 0.1818 (0.1823) time: 0.4355 data: 0.0047 max mem: 22448 +train: [8] [380/400] eta: 0:00:08 lr: 0.000252 loss: 2.4632 (2.4677) grad: 0.1842 (0.1824) time: 0.4372 data: 0.0048 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.4368 (2.4689) grad: 0.1842 (0.1828) time: 0.4390 data: 0.0048 max mem: 22448 +train: [8] Total time: 0:02:58 (0.4469 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.4368 (2.4689) grad: 0.1842 (0.1828) +eval (validation): [8] [ 0/85] eta: 0:04:57 time: 3.5030 data: 3.2275 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:32 time: 0.3491 data: 0.0032 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:19 time: 0.3429 data: 0.0039 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3387 data: 0.0043 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3141 data: 0.0040 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3091 data: 0.0038 max mem: 22448 +eval (validation): [8] Total time: 0:00:31 (0.3743 s / it) +cv: [8] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.433 acc: 0.289 f1: 0.215 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:20:56 lr: nan time: 3.1406 data: 2.7704 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:33 lr: 0.000249 loss: 2.4165 (2.4408) grad: 0.1789 (0.1807) time: 0.4324 data: 0.0043 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:00 lr: 0.000248 loss: 2.4165 (2.4186) grad: 0.1794 (0.1861) time: 0.4395 data: 0.0049 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:44 lr: 0.000247 loss: 2.4212 (2.4367) grad: 0.1839 (0.1867) time: 0.4489 data: 0.0049 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:31 lr: 0.000246 loss: 2.4322 (2.4241) grad: 0.1839 (0.1855) time: 0.4417 data: 0.0046 max mem: 22448 +train: [9] [100/400] eta: 0:02:20 lr: 0.000244 loss: 2.3675 (2.4138) grad: 0.1824 (0.1863) time: 0.4451 data: 0.0048 max mem: 22448 +train: [9] [120/400] eta: 0:02:10 lr: 0.000243 loss: 2.3614 (2.4113) grad: 0.1823 (0.1858) time: 0.4603 data: 0.0050 max mem: 22448 +train: [9] [140/400] eta: 0:02:00 lr: 0.000242 loss: 2.3982 (2.4146) grad: 0.1839 (0.1865) time: 0.4474 data: 0.0049 max mem: 22448 +train: [9] [160/400] eta: 0:01:50 lr: 0.000241 loss: 2.4057 (2.4156) grad: 0.1852 (0.1867) time: 0.4442 data: 0.0046 max mem: 22448 +train: [9] [180/400] eta: 0:01:41 lr: 0.000240 loss: 2.3722 (2.4196) grad: 0.1829 (0.1858) time: 0.4409 data: 0.0046 max mem: 22448 +train: [9] [200/400] eta: 0:01:31 lr: 0.000238 loss: 2.4353 (2.4233) grad: 0.1809 (0.1854) time: 0.4496 data: 0.0049 max mem: 22448 +train: [9] [220/400] eta: 0:01:22 lr: 0.000237 loss: 2.4089 (2.4164) grad: 0.1812 (0.1853) time: 0.4495 data: 0.0048 max mem: 22448 +train: [9] [240/400] eta: 0:01:13 lr: 0.000236 loss: 2.3601 (2.4143) grad: 0.1830 (0.1854) time: 0.4423 data: 0.0048 max mem: 22448 +train: [9] [260/400] eta: 0:01:03 lr: 0.000234 loss: 2.4051 (2.4164) grad: 0.1810 (0.1849) time: 0.4454 data: 0.0047 max mem: 22448 +train: [9] [280/400] eta: 0:00:54 lr: 0.000233 loss: 2.4371 (2.4223) grad: 0.1827 (0.1856) time: 0.4460 data: 0.0051 max mem: 22448 +train: [9] [300/400] eta: 0:00:45 lr: 0.000232 loss: 2.4332 (2.4219) grad: 0.1905 (0.1858) time: 0.4496 data: 0.0047 max mem: 22448 +train: [9] [320/400] eta: 0:00:36 lr: 0.000230 loss: 2.4122 (2.4225) grad: 0.1893 (0.1863) time: 0.4578 data: 0.0047 max mem: 22448 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 2.4122 (2.4210) grad: 0.1882 (0.1864) time: 0.4515 data: 0.0049 max mem: 22448 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 2.4077 (2.4229) grad: 0.1961 (0.1871) time: 0.4542 data: 0.0048 max mem: 22448 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 2.4246 (2.4243) grad: 0.1963 (0.1874) time: 0.4520 data: 0.0049 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.3966 (2.4236) grad: 0.1854 (0.1872) time: 0.4539 data: 0.0049 max mem: 22448 +train: [9] Total time: 0:03:01 (0.4549 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.3966 (2.4236) grad: 0.1854 (0.1872) +eval (validation): [9] [ 0/85] eta: 0:05:34 time: 3.9300 data: 3.6460 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:34 time: 0.3668 data: 0.0027 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:19 time: 0.3257 data: 0.0042 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:10 time: 0.3350 data: 0.0044 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3221 data: 0.0042 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3120 data: 0.0040 max mem: 22448 +eval (validation): [9] Total time: 0:00:32 (0.3813 s / it) +cv: [9] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.369 acc: 0.286 f1: 0.216 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:25:43 lr: nan time: 3.8576 data: 3.5163 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:44 lr: 0.000224 loss: 2.3208 (2.3385) grad: 0.1738 (0.1763) time: 0.4286 data: 0.0029 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:06 lr: 0.000222 loss: 2.3534 (2.3696) grad: 0.1792 (0.1843) time: 0.4394 data: 0.0046 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:48 lr: 0.000221 loss: 2.3466 (2.3644) grad: 0.1892 (0.1853) time: 0.4462 data: 0.0048 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:33 lr: 0.000220 loss: 2.3667 (2.3755) grad: 0.1807 (0.1849) time: 0.4314 data: 0.0045 max mem: 22448 +train: [10] [100/400] eta: 0:02:21 lr: 0.000218 loss: 2.3816 (2.3755) grad: 0.1863 (0.1856) time: 0.4448 data: 0.0049 max mem: 22448 +train: [10] [120/400] eta: 0:02:11 lr: 0.000217 loss: 2.3511 (2.3765) grad: 0.1885 (0.1865) time: 0.4516 data: 0.0048 max mem: 22448 +train: [10] [140/400] eta: 0:02:01 lr: 0.000215 loss: 2.3344 (2.3716) grad: 0.1859 (0.1866) time: 0.4477 data: 0.0048 max mem: 22448 +train: [10] [160/400] eta: 0:01:50 lr: 0.000214 loss: 2.3403 (2.3715) grad: 0.1770 (0.1855) time: 0.4363 data: 0.0044 max mem: 22448 +train: [10] [180/400] eta: 0:01:41 lr: 0.000213 loss: 2.3660 (2.3690) grad: 0.1753 (0.1853) time: 0.4513 data: 0.0048 max mem: 22448 +train: [10] [200/400] eta: 0:01:31 lr: 0.000211 loss: 2.3221 (2.3626) grad: 0.1805 (0.1850) time: 0.4464 data: 0.0050 max mem: 22448 +train: [10] [220/400] eta: 0:01:22 lr: 0.000210 loss: 2.3091 (2.3598) grad: 0.1847 (0.1856) time: 0.4551 data: 0.0049 max mem: 22448 +train: [10] [240/400] eta: 0:01:13 lr: 0.000208 loss: 2.3479 (2.3589) grad: 0.1862 (0.1855) time: 0.4432 data: 0.0046 max mem: 22448 +train: [10] [260/400] eta: 0:01:04 lr: 0.000207 loss: 2.3924 (2.3645) grad: 0.1832 (0.1850) time: 0.4530 data: 0.0049 max mem: 22448 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 2.4086 (2.3687) grad: 0.1832 (0.1853) time: 0.4454 data: 0.0049 max mem: 22448 +train: [10] [300/400] eta: 0:00:45 lr: 0.000204 loss: 2.4216 (2.3696) grad: 0.1894 (0.1863) time: 0.4498 data: 0.0048 max mem: 22448 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.4147 (2.3723) grad: 0.2011 (0.1872) time: 0.4451 data: 0.0048 max mem: 22448 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.4067 (2.3722) grad: 0.1997 (0.1874) time: 0.4452 data: 0.0048 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.3912 (2.3746) grad: 0.1893 (0.1879) time: 0.4487 data: 0.0047 max mem: 22448 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 2.3861 (2.3735) grad: 0.1977 (0.1885) time: 0.4530 data: 0.0047 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.3861 (2.3750) grad: 0.1942 (0.1888) time: 0.4663 data: 0.0047 max mem: 22448 +train: [10] Total time: 0:03:02 (0.4555 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.3861 (2.3750) grad: 0.1942 (0.1888) +eval (validation): [10] [ 0/85] eta: 0:04:28 time: 3.1595 data: 2.9120 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:32 time: 0.3598 data: 0.0054 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3407 data: 0.0033 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3345 data: 0.0040 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3390 data: 0.0040 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3303 data: 0.0039 max mem: 22448 +eval (validation): [10] Total time: 0:00:32 (0.3792 s / it) +cv: [10] best hparam: (0.61, 1.0) (021) ('021_lr6.1e-01_wd1.0e+00') loss: 2.367 acc: 0.290 f1: 0.223 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:20:36 lr: nan time: 3.0912 data: 2.7608 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:41 lr: 0.000195 loss: 2.3424 (2.3481) grad: 0.1948 (0.1991) time: 0.4573 data: 0.0047 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:07 lr: 0.000193 loss: 2.3147 (2.3202) grad: 0.1924 (0.1943) time: 0.4545 data: 0.0046 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:49 lr: 0.000192 loss: 2.2893 (2.3198) grad: 0.1870 (0.1907) time: 0.4531 data: 0.0049 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:34 lr: 0.000190 loss: 2.3331 (2.3325) grad: 0.1877 (0.1922) time: 0.4357 data: 0.0048 max mem: 22448 +train: [11] [100/400] eta: 0:02:23 lr: 0.000189 loss: 2.3190 (2.3241) grad: 0.1894 (0.1905) time: 0.4586 data: 0.0050 max mem: 22448 +train: [11] [120/400] eta: 0:02:12 lr: 0.000187 loss: 2.3053 (2.3247) grad: 0.1876 (0.1894) time: 0.4570 data: 0.0050 max mem: 22448 +train: [11] [140/400] eta: 0:02:03 lr: 0.000186 loss: 2.3324 (2.3280) grad: 0.1876 (0.1896) time: 0.4720 data: 0.0050 max mem: 22448 +train: [11] [160/400] eta: 0:01:53 lr: 0.000184 loss: 2.3298 (2.3258) grad: 0.1864 (0.1891) time: 0.4497 data: 0.0047 max mem: 22448 +train: [11] [180/400] eta: 0:01:43 lr: 0.000183 loss: 2.2959 (2.3272) grad: 0.1828 (0.1894) time: 0.4581 data: 0.0051 max mem: 22448 +train: [11] [200/400] eta: 0:01:33 lr: 0.000181 loss: 2.3219 (2.3296) grad: 0.1841 (0.1897) time: 0.4584 data: 0.0049 max mem: 22448 +train: [11] [220/400] eta: 0:01:23 lr: 0.000180 loss: 2.3294 (2.3308) grad: 0.1909 (0.1901) time: 0.4438 data: 0.0048 max mem: 22448 +train: [11] [240/400] eta: 0:01:14 lr: 0.000178 loss: 2.3559 (2.3335) grad: 0.1961 (0.1911) time: 0.4507 data: 0.0048 max mem: 22448 +train: [11] [260/400] eta: 0:01:05 lr: 0.000177 loss: 2.3315 (2.3356) grad: 0.1992 (0.1915) time: 0.4885 data: 0.0050 max mem: 22448 +train: [11] [280/400] eta: 0:00:55 lr: 0.000175 loss: 2.2970 (2.3331) grad: 0.1930 (0.1911) time: 0.4436 data: 0.0046 max mem: 22448 +train: [11] [300/400] eta: 0:00:46 lr: 0.000174 loss: 2.3326 (2.3341) grad: 0.1811 (0.1908) time: 0.4647 data: 0.0051 max mem: 22448 +train: [11] [320/400] eta: 0:00:37 lr: 0.000172 loss: 2.3326 (2.3346) grad: 0.1868 (0.1909) time: 0.4396 data: 0.0045 max mem: 22448 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 2.3040 (2.3330) grad: 0.1947 (0.1911) time: 0.4343 data: 0.0043 max mem: 22448 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 2.3288 (2.3329) grad: 0.1976 (0.1915) time: 0.4472 data: 0.0044 max mem: 22448 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 2.3405 (2.3347) grad: 0.1910 (0.1912) time: 0.4450 data: 0.0048 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.3179 (2.3330) grad: 0.1885 (0.1913) time: 0.4310 data: 0.0046 max mem: 22448 +train: [11] Total time: 0:03:03 (0.4593 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.3179 (2.3330) grad: 0.1885 (0.1913) +eval (validation): [11] [ 0/85] eta: 0:04:13 time: 2.9825 data: 2.7078 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:30 time: 0.3494 data: 0.0042 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:18 time: 0.3238 data: 0.0038 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3328 data: 0.0040 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3220 data: 0.0042 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3147 data: 0.0040 max mem: 22448 +eval (validation): [11] Total time: 0:00:30 (0.3646 s / it) +cv: [11] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.358 acc: 0.295 f1: 0.224 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:20:45 lr: nan time: 3.1144 data: 2.7874 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:31 lr: 0.000164 loss: 2.2653 (2.2877) grad: 0.1840 (0.1881) time: 0.4276 data: 0.0031 max mem: 22448 +train: [12] [ 40/400] eta: 0:02:59 lr: 0.000163 loss: 2.2653 (2.2825) grad: 0.1827 (0.1886) time: 0.4366 data: 0.0041 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:45 lr: 0.000161 loss: 2.2963 (2.2954) grad: 0.1842 (0.1888) time: 0.4612 data: 0.0050 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:32 lr: 0.000160 loss: 2.2942 (2.2809) grad: 0.1923 (0.1900) time: 0.4534 data: 0.0050 max mem: 22448 +train: [12] [100/400] eta: 0:02:20 lr: 0.000158 loss: 2.2405 (2.2787) grad: 0.1933 (0.1914) time: 0.4387 data: 0.0048 max mem: 22448 +train: [12] [120/400] eta: 0:02:10 lr: 0.000156 loss: 2.2875 (2.2853) grad: 0.1927 (0.1914) time: 0.4501 data: 0.0048 max mem: 22448 +train: [12] [140/400] eta: 0:02:00 lr: 0.000155 loss: 2.3368 (2.2941) grad: 0.1927 (0.1918) time: 0.4553 data: 0.0049 max mem: 22448 +train: [12] [160/400] eta: 0:01:51 lr: 0.000153 loss: 2.3152 (2.2958) grad: 0.1918 (0.1922) time: 0.4468 data: 0.0050 max mem: 22448 +train: [12] [180/400] eta: 0:01:41 lr: 0.000152 loss: 2.2634 (2.2903) grad: 0.1934 (0.1923) time: 0.4524 data: 0.0051 max mem: 22448 +train: [12] [200/400] eta: 0:01:32 lr: 0.000150 loss: 2.2329 (2.2938) grad: 0.1866 (0.1922) time: 0.4683 data: 0.0050 max mem: 22448 +train: [12] [220/400] eta: 0:01:23 lr: 0.000149 loss: 2.3382 (2.2949) grad: 0.1905 (0.1927) time: 0.4617 data: 0.0048 max mem: 22448 +train: [12] [240/400] eta: 0:01:13 lr: 0.000147 loss: 2.2869 (2.2920) grad: 0.1929 (0.1925) time: 0.4502 data: 0.0047 max mem: 22448 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 2.2787 (2.2900) grad: 0.1903 (0.1925) time: 0.4356 data: 0.0048 max mem: 22448 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 2.2787 (2.2930) grad: 0.1903 (0.1924) time: 0.4296 data: 0.0047 max mem: 22448 +train: [12] [300/400] eta: 0:00:45 lr: 0.000142 loss: 2.2994 (2.2942) grad: 0.1872 (0.1919) time: 0.4404 data: 0.0048 max mem: 22448 +train: [12] [320/400] eta: 0:00:36 lr: 0.000141 loss: 2.3048 (2.2974) grad: 0.1898 (0.1924) time: 0.4374 data: 0.0048 max mem: 22448 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 2.3203 (2.2979) grad: 0.1984 (0.1925) time: 0.4341 data: 0.0049 max mem: 22448 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 2.2919 (2.2961) grad: 0.1911 (0.1925) time: 0.4312 data: 0.0047 max mem: 22448 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 2.2744 (2.2970) grad: 0.1911 (0.1927) time: 0.4500 data: 0.0045 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.3195 (2.2996) grad: 0.1926 (0.1928) time: 0.4469 data: 0.0048 max mem: 22448 +train: [12] Total time: 0:03:01 (0.4526 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.3195 (2.2996) grad: 0.1926 (0.1928) +eval (validation): [12] [ 0/85] eta: 0:04:11 time: 2.9554 data: 2.6765 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:31 time: 0.3532 data: 0.0048 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:18 time: 0.3309 data: 0.0033 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3346 data: 0.0041 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3202 data: 0.0038 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3152 data: 0.0038 max mem: 22448 +eval (validation): [12] Total time: 0:00:31 (0.3672 s / it) +cv: [12] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.367 acc: 0.293 f1: 0.226 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:23:20 lr: nan time: 3.5016 data: 3.0952 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:51 lr: 0.000133 loss: 2.2357 (2.2953) grad: 0.1766 (0.1875) time: 0.4639 data: 0.0040 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:12 lr: 0.000131 loss: 2.2303 (2.2481) grad: 0.1795 (0.1860) time: 0.4585 data: 0.0045 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:51 lr: 0.000130 loss: 2.1989 (2.2420) grad: 0.1865 (0.1867) time: 0.4407 data: 0.0046 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:37 lr: 0.000128 loss: 2.2437 (2.2479) grad: 0.1906 (0.1883) time: 0.4501 data: 0.0049 max mem: 22448 +train: [13] [100/400] eta: 0:02:25 lr: 0.000127 loss: 2.2666 (2.2544) grad: 0.1874 (0.1881) time: 0.4606 data: 0.0048 max mem: 22448 +train: [13] [120/400] eta: 0:02:14 lr: 0.000125 loss: 2.2666 (2.2507) grad: 0.1892 (0.1895) time: 0.4624 data: 0.0049 max mem: 22448 +train: [13] [140/400] eta: 0:02:04 lr: 0.000124 loss: 2.2360 (2.2491) grad: 0.1934 (0.1903) time: 0.4684 data: 0.0048 max mem: 22448 +train: [13] [160/400] eta: 0:01:54 lr: 0.000122 loss: 2.2360 (2.2516) grad: 0.1927 (0.1908) time: 0.4595 data: 0.0052 max mem: 22448 +train: [13] [180/400] eta: 0:01:44 lr: 0.000120 loss: 2.2988 (2.2592) grad: 0.1917 (0.1912) time: 0.4547 data: 0.0049 max mem: 22448 +train: [13] [200/400] eta: 0:01:34 lr: 0.000119 loss: 2.2969 (2.2585) grad: 0.1877 (0.1917) time: 0.4637 data: 0.0048 max mem: 22448 +train: [13] [220/400] eta: 0:01:24 lr: 0.000117 loss: 2.2675 (2.2580) grad: 0.1864 (0.1913) time: 0.4538 data: 0.0047 max mem: 22448 +train: [13] [240/400] eta: 0:01:15 lr: 0.000116 loss: 2.2446 (2.2594) grad: 0.1897 (0.1917) time: 0.4566 data: 0.0048 max mem: 22448 +train: [13] [260/400] eta: 0:01:05 lr: 0.000114 loss: 2.2808 (2.2620) grad: 0.1893 (0.1909) time: 0.4552 data: 0.0047 max mem: 22448 +train: [13] [280/400] eta: 0:00:56 lr: 0.000113 loss: 2.2808 (2.2614) grad: 0.1861 (0.1910) time: 0.4596 data: 0.0048 max mem: 22448 +train: [13] [300/400] eta: 0:00:46 lr: 0.000111 loss: 2.2311 (2.2564) grad: 0.1885 (0.1909) time: 0.4483 data: 0.0049 max mem: 22448 +train: [13] [320/400] eta: 0:00:37 lr: 0.000110 loss: 2.2442 (2.2564) grad: 0.1907 (0.1913) time: 0.4304 data: 0.0047 max mem: 22448 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 2.2550 (2.2568) grad: 0.1992 (0.1920) time: 0.4462 data: 0.0044 max mem: 22448 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 2.2501 (2.2554) grad: 0.1977 (0.1918) time: 0.4406 data: 0.0047 max mem: 22448 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 2.2398 (2.2538) grad: 0.1874 (0.1919) time: 0.4324 data: 0.0047 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.2627 (2.2566) grad: 0.1881 (0.1917) time: 0.4460 data: 0.0047 max mem: 22448 +train: [13] Total time: 0:03:04 (0.4608 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.2627 (2.2566) grad: 0.1881 (0.1917) +eval (validation): [13] [ 0/85] eta: 0:04:12 time: 2.9714 data: 2.7326 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:29 time: 0.3354 data: 0.0040 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:17 time: 0.3326 data: 0.0038 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3128 data: 0.0040 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3227 data: 0.0040 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3141 data: 0.0039 max mem: 22448 +eval (validation): [13] Total time: 0:00:30 (0.3593 s / it) +cv: [13] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.358 acc: 0.294 f1: 0.228 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:20:02 lr: nan time: 3.0069 data: 2.6903 max mem: 22448 +train: [14] [ 20/400] eta: 0:03:31 lr: 0.000102 loss: 2.1862 (2.1856) grad: 0.1793 (0.1847) time: 0.4341 data: 0.0047 max mem: 22448 +train: [14] [ 40/400] eta: 0:02:59 lr: 0.000101 loss: 2.2392 (2.2231) grad: 0.1902 (0.1884) time: 0.4365 data: 0.0045 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:42 lr: 0.000099 loss: 2.2392 (2.2211) grad: 0.1907 (0.1894) time: 0.4329 data: 0.0047 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:29 lr: 0.000098 loss: 2.2134 (2.2242) grad: 0.1957 (0.1913) time: 0.4391 data: 0.0048 max mem: 22448 +train: [14] [100/400] eta: 0:02:19 lr: 0.000096 loss: 2.2278 (2.2274) grad: 0.1893 (0.1910) time: 0.4583 data: 0.0049 max mem: 22448 +train: [14] [120/400] eta: 0:02:10 lr: 0.000095 loss: 2.1896 (2.2185) grad: 0.1867 (0.1902) time: 0.4608 data: 0.0047 max mem: 22448 +train: [14] [140/400] eta: 0:02:00 lr: 0.000093 loss: 2.1691 (2.2135) grad: 0.1883 (0.1914) time: 0.4579 data: 0.0048 max mem: 22448 +train: [14] [160/400] eta: 0:01:51 lr: 0.000092 loss: 2.2178 (2.2141) grad: 0.1928 (0.1914) time: 0.4593 data: 0.0048 max mem: 22448 +train: [14] [180/400] eta: 0:01:41 lr: 0.000090 loss: 2.1901 (2.2107) grad: 0.1879 (0.1916) time: 0.4595 data: 0.0048 max mem: 22448 +train: [14] [200/400] eta: 0:01:32 lr: 0.000089 loss: 2.1879 (2.2080) grad: 0.1929 (0.1914) time: 0.4631 data: 0.0049 max mem: 22448 +train: [14] [220/400] eta: 0:01:23 lr: 0.000088 loss: 2.2003 (2.2116) grad: 0.1883 (0.1910) time: 0.4626 data: 0.0049 max mem: 22448 +train: [14] [240/400] eta: 0:01:13 lr: 0.000086 loss: 2.2433 (2.2120) grad: 0.1883 (0.1909) time: 0.4558 data: 0.0048 max mem: 22448 +train: [14] [260/400] eta: 0:01:04 lr: 0.000085 loss: 2.1416 (2.2074) grad: 0.1858 (0.1906) time: 0.4640 data: 0.0051 max mem: 22448 +train: [14] [280/400] eta: 0:00:55 lr: 0.000083 loss: 2.1954 (2.2087) grad: 0.1897 (0.1909) time: 0.4413 data: 0.0048 max mem: 22448 +train: [14] [300/400] eta: 0:00:45 lr: 0.000082 loss: 2.2419 (2.2085) grad: 0.1926 (0.1910) time: 0.4347 data: 0.0049 max mem: 22448 +train: [14] [320/400] eta: 0:00:36 lr: 0.000081 loss: 2.2578 (2.2121) grad: 0.2020 (0.1918) time: 0.4719 data: 0.0051 max mem: 22448 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 2.2246 (2.2119) grad: 0.1998 (0.1921) time: 0.4613 data: 0.0049 max mem: 22448 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 2.1906 (2.2105) grad: 0.1938 (0.1921) time: 0.4609 data: 0.0052 max mem: 22448 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 2.1906 (2.2129) grad: 0.1870 (0.1920) time: 0.4614 data: 0.0050 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.2398 (2.2143) grad: 0.1864 (0.1919) time: 0.4583 data: 0.0046 max mem: 22448 +train: [14] Total time: 0:03:04 (0.4607 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.2398 (2.2143) grad: 0.1864 (0.1919) +eval (validation): [14] [ 0/85] eta: 0:04:59 time: 3.5247 data: 3.1948 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:34 time: 0.3833 data: 0.0042 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:20 time: 0.3516 data: 0.0041 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3311 data: 0.0036 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3253 data: 0.0039 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3208 data: 0.0038 max mem: 22448 +eval (validation): [14] Total time: 0:00:32 (0.3864 s / it) +cv: [14] best hparam: (0.38, 1.0) (018) ('018_lr3.8e-01_wd1.0e+00') loss: 2.357 acc: 0.296 f1: 0.225 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [15] [ 0/400] eta: 0:23:22 lr: nan time: 3.5071 data: 3.1495 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:52 lr: 0.000074 loss: 2.1619 (2.1872) grad: 0.1829 (0.1823) time: 0.4670 data: 0.0051 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:09 lr: 0.000072 loss: 2.1825 (2.1897) grad: 0.1870 (0.1863) time: 0.4382 data: 0.0042 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:50 lr: 0.000071 loss: 2.1808 (2.1840) grad: 0.1883 (0.1859) time: 0.4446 data: 0.0049 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:36 lr: 0.000070 loss: 2.1808 (2.1955) grad: 0.1837 (0.1878) time: 0.4550 data: 0.0050 max mem: 22448 +train: [15] [100/400] eta: 0:02:25 lr: 0.000068 loss: 2.1727 (2.1916) grad: 0.1906 (0.1890) time: 0.4630 data: 0.0050 max mem: 22448 +train: [15] [120/400] eta: 0:02:14 lr: 0.000067 loss: 2.1618 (2.1891) grad: 0.1926 (0.1896) time: 0.4576 data: 0.0048 max mem: 22448 +train: [15] [140/400] eta: 0:02:03 lr: 0.000066 loss: 2.1681 (2.1889) grad: 0.1896 (0.1896) time: 0.4497 data: 0.0048 max mem: 22448 +train: [15] [160/400] eta: 0:01:53 lr: 0.000064 loss: 2.1956 (2.1911) grad: 0.1953 (0.1904) time: 0.4462 data: 0.0046 max mem: 22448 +train: [15] [180/400] eta: 0:01:43 lr: 0.000063 loss: 2.1956 (2.1888) grad: 0.1960 (0.1909) time: 0.4406 data: 0.0049 max mem: 22448 +train: [15] [200/400] eta: 0:01:33 lr: 0.000062 loss: 2.1694 (2.1883) grad: 0.1945 (0.1905) time: 0.4455 data: 0.0049 max mem: 22448 +train: [15] [220/400] eta: 0:01:23 lr: 0.000061 loss: 2.1703 (2.1926) grad: 0.1945 (0.1906) time: 0.4581 data: 0.0051 max mem: 22448 +train: [15] [240/400] eta: 0:01:14 lr: 0.000059 loss: 2.1671 (2.1892) grad: 0.1919 (0.1905) time: 0.4586 data: 0.0051 max mem: 22448 +train: [15] [260/400] eta: 0:01:05 lr: 0.000058 loss: 2.1554 (2.1918) grad: 0.1905 (0.1907) time: 0.4648 data: 0.0050 max mem: 22448 +train: [15] [280/400] eta: 0:00:55 lr: 0.000057 loss: 2.2009 (2.1936) grad: 0.1950 (0.1910) time: 0.4621 data: 0.0051 max mem: 22448 +train: [15] [300/400] eta: 0:00:46 lr: 0.000056 loss: 2.2070 (2.1931) grad: 0.1875 (0.1907) time: 0.4577 data: 0.0048 max mem: 22448 +train: [15] [320/400] eta: 0:00:37 lr: 0.000054 loss: 2.2070 (2.1945) grad: 0.1898 (0.1909) time: 0.4825 data: 0.0049 max mem: 22448 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 2.1873 (2.1964) grad: 0.1950 (0.1914) time: 0.4732 data: 0.0051 max mem: 22448 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 2.1913 (2.1980) grad: 0.1927 (0.1912) time: 0.4604 data: 0.0051 max mem: 22448 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.2187 (2.1979) grad: 0.1896 (0.1912) time: 0.4466 data: 0.0046 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.1508 (2.1942) grad: 0.1877 (0.1910) time: 0.4689 data: 0.0049 max mem: 22448 +train: [15] Total time: 0:03:06 (0.4652 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.1508 (2.1942) grad: 0.1877 (0.1910) +eval (validation): [15] [ 0/85] eta: 0:04:53 time: 3.4518 data: 3.1409 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:32 time: 0.3481 data: 0.0040 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3498 data: 0.0040 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3802 data: 0.0045 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3504 data: 0.0041 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3423 data: 0.0041 max mem: 22448 +eval (validation): [15] Total time: 0:00:33 (0.3961 s / it) +cv: [15] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.375 acc: 0.293 f1: 0.227 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:23:12 lr: nan time: 3.4818 data: 3.1196 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:55 lr: 0.000048 loss: 2.1542 (2.1401) grad: 0.1951 (0.1908) time: 0.4759 data: 0.0033 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:14 lr: 0.000047 loss: 2.1626 (2.1613) grad: 0.1978 (0.1939) time: 0.4563 data: 0.0045 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:54 lr: 0.000046 loss: 2.1520 (2.1592) grad: 0.1924 (0.1912) time: 0.4619 data: 0.0051 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:40 lr: 0.000045 loss: 2.1457 (2.1549) grad: 0.1850 (0.1911) time: 0.4623 data: 0.0050 max mem: 22448 +train: [16] [100/400] eta: 0:02:26 lr: 0.000044 loss: 2.1583 (2.1537) grad: 0.1850 (0.1895) time: 0.4397 data: 0.0049 max mem: 22448 +train: [16] [120/400] eta: 0:02:15 lr: 0.000043 loss: 2.1550 (2.1534) grad: 0.1863 (0.1906) time: 0.4664 data: 0.0049 max mem: 22448 +train: [16] [140/400] eta: 0:02:05 lr: 0.000042 loss: 2.1319 (2.1532) grad: 0.1920 (0.1903) time: 0.4699 data: 0.0051 max mem: 22448 +train: [16] [160/400] eta: 0:01:55 lr: 0.000041 loss: 2.1266 (2.1512) grad: 0.1825 (0.1891) time: 0.4593 data: 0.0050 max mem: 22448 +train: [16] [180/400] eta: 0:01:45 lr: 0.000040 loss: 2.1111 (2.1493) grad: 0.1814 (0.1886) time: 0.4660 data: 0.0050 max mem: 22448 +train: [16] [200/400] eta: 0:01:35 lr: 0.000039 loss: 2.1483 (2.1501) grad: 0.1856 (0.1884) time: 0.4825 data: 0.0049 max mem: 22448 +train: [16] [220/400] eta: 0:01:26 lr: 0.000038 loss: 2.1361 (2.1508) grad: 0.1855 (0.1882) time: 0.4720 data: 0.0049 max mem: 22448 +train: [16] [240/400] eta: 0:01:16 lr: 0.000036 loss: 2.1568 (2.1557) grad: 0.1855 (0.1881) time: 0.4626 data: 0.0051 max mem: 22448 +train: [16] [260/400] eta: 0:01:06 lr: 0.000035 loss: 2.1613 (2.1540) grad: 0.1882 (0.1882) time: 0.4622 data: 0.0050 max mem: 22448 +train: [16] [280/400] eta: 0:00:56 lr: 0.000034 loss: 2.1641 (2.1573) grad: 0.1885 (0.1883) time: 0.4483 data: 0.0048 max mem: 22448 +train: [16] [300/400] eta: 0:00:47 lr: 0.000033 loss: 2.1641 (2.1545) grad: 0.1943 (0.1887) time: 0.4466 data: 0.0049 max mem: 22448 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 2.1333 (2.1557) grad: 0.1867 (0.1888) time: 0.4580 data: 0.0050 max mem: 22448 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 2.1853 (2.1594) grad: 0.1817 (0.1885) time: 0.4456 data: 0.0046 max mem: 22448 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 2.1966 (2.1605) grad: 0.1861 (0.1885) time: 0.4551 data: 0.0050 max mem: 22448 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 2.1648 (2.1589) grad: 0.1873 (0.1884) time: 0.4723 data: 0.0049 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.1512 (2.1581) grad: 0.1828 (0.1883) time: 0.4642 data: 0.0049 max mem: 22448 +train: [16] Total time: 0:03:07 (0.4695 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.1512 (2.1581) grad: 0.1828 (0.1883) +eval (validation): [16] [ 0/85] eta: 0:04:25 time: 3.1214 data: 2.8234 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:31 time: 0.3577 data: 0.0056 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:19 time: 0.3664 data: 0.0036 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:10 time: 0.3561 data: 0.0042 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3373 data: 0.0039 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3260 data: 0.0037 max mem: 22448 +eval (validation): [16] Total time: 0:00:33 (0.3883 s / it) +cv: [16] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.372 acc: 0.295 f1: 0.228 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:20:58 lr: nan time: 3.1460 data: 2.7746 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:42 lr: 0.000028 loss: 2.0478 (2.0527) grad: 0.1863 (0.1850) time: 0.4563 data: 0.0041 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:07 lr: 0.000027 loss: 2.0896 (2.1009) grad: 0.1901 (0.1872) time: 0.4567 data: 0.0049 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:51 lr: 0.000026 loss: 2.1421 (2.1204) grad: 0.1901 (0.1869) time: 0.4650 data: 0.0050 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:37 lr: 0.000025 loss: 2.1357 (2.1191) grad: 0.1877 (0.1871) time: 0.4562 data: 0.0048 max mem: 22448 +train: [17] [100/400] eta: 0:02:26 lr: 0.000024 loss: 2.0951 (2.1226) grad: 0.1845 (0.1865) time: 0.4698 data: 0.0049 max mem: 22448 +train: [17] [120/400] eta: 0:02:15 lr: 0.000023 loss: 2.1286 (2.1219) grad: 0.1807 (0.1854) time: 0.4648 data: 0.0050 max mem: 22448 +train: [17] [140/400] eta: 0:02:05 lr: 0.000023 loss: 2.1373 (2.1296) grad: 0.1829 (0.1861) time: 0.4636 data: 0.0051 max mem: 22448 +train: [17] [160/400] eta: 0:01:54 lr: 0.000022 loss: 2.1455 (2.1319) grad: 0.1907 (0.1860) time: 0.4626 data: 0.0050 max mem: 22448 +train: [17] [180/400] eta: 0:01:44 lr: 0.000021 loss: 2.1439 (2.1376) grad: 0.1851 (0.1857) time: 0.4654 data: 0.0049 max mem: 22448 +train: [17] [200/400] eta: 0:01:34 lr: 0.000020 loss: 2.1439 (2.1378) grad: 0.1857 (0.1856) time: 0.4529 data: 0.0053 max mem: 22448 +train: [17] [220/400] eta: 0:01:24 lr: 0.000019 loss: 2.1171 (2.1366) grad: 0.1882 (0.1858) time: 0.4370 data: 0.0049 max mem: 22448 +train: [17] [240/400] eta: 0:01:15 lr: 0.000019 loss: 2.1134 (2.1361) grad: 0.1878 (0.1862) time: 0.4489 data: 0.0049 max mem: 22448 +train: [17] [260/400] eta: 0:01:05 lr: 0.000018 loss: 2.1180 (2.1343) grad: 0.1854 (0.1861) time: 0.4595 data: 0.0050 max mem: 22448 +train: [17] [280/400] eta: 0:00:56 lr: 0.000017 loss: 2.1037 (2.1327) grad: 0.1804 (0.1859) time: 0.4687 data: 0.0050 max mem: 22448 +train: [17] [300/400] eta: 0:00:46 lr: 0.000016 loss: 2.1037 (2.1336) grad: 0.1812 (0.1860) time: 0.4652 data: 0.0049 max mem: 22448 +train: [17] [320/400] eta: 0:00:37 lr: 0.000016 loss: 2.1296 (2.1331) grad: 0.1812 (0.1856) time: 0.4747 data: 0.0048 max mem: 22448 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 2.1347 (2.1354) grad: 0.1813 (0.1856) time: 0.4512 data: 0.0048 max mem: 22448 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 2.1347 (2.1349) grad: 0.1813 (0.1852) time: 0.4782 data: 0.0052 max mem: 22448 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 2.1149 (2.1344) grad: 0.1771 (0.1852) time: 0.4659 data: 0.0048 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.1435 (2.1349) grad: 0.1836 (0.1851) time: 0.4479 data: 0.0045 max mem: 22448 +train: [17] Total time: 0:03:07 (0.4679 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.1435 (2.1349) grad: 0.1836 (0.1851) +eval (validation): [17] [ 0/85] eta: 0:04:19 time: 3.0487 data: 2.8214 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:31 time: 0.3568 data: 0.0041 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3490 data: 0.0036 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3495 data: 0.0037 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3459 data: 0.0042 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3353 data: 0.0040 max mem: 22448 +eval (validation): [17] Total time: 0:00:32 (0.3839 s / it) +cv: [17] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.371 acc: 0.292 f1: 0.226 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:23:05 lr: nan time: 3.4632 data: 3.0970 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:54 lr: 0.000012 loss: 2.1493 (2.1543) grad: 0.1835 (0.1837) time: 0.4758 data: 0.0037 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:16 lr: 0.000012 loss: 2.1385 (2.1405) grad: 0.1846 (0.1841) time: 0.4693 data: 0.0043 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:56 lr: 0.000011 loss: 2.1299 (2.1428) grad: 0.1838 (0.1840) time: 0.4631 data: 0.0050 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:41 lr: 0.000011 loss: 2.1303 (2.1374) grad: 0.1833 (0.1841) time: 0.4582 data: 0.0050 max mem: 22448 +train: [18] [100/400] eta: 0:02:28 lr: 0.000010 loss: 2.1303 (2.1320) grad: 0.1769 (0.1822) time: 0.4558 data: 0.0050 max mem: 22448 +train: [18] [120/400] eta: 0:02:16 lr: 0.000009 loss: 2.1193 (2.1267) grad: 0.1766 (0.1810) time: 0.4501 data: 0.0050 max mem: 22448 +train: [18] [140/400] eta: 0:02:04 lr: 0.000009 loss: 2.1057 (2.1197) grad: 0.1809 (0.1817) time: 0.4381 data: 0.0049 max mem: 22448 +train: [18] [160/400] eta: 0:01:54 lr: 0.000008 loss: 2.1057 (2.1204) grad: 0.1826 (0.1823) time: 0.4480 data: 0.0051 max mem: 22448 +train: [18] [180/400] eta: 0:01:44 lr: 0.000008 loss: 2.1195 (2.1255) grad: 0.1826 (0.1823) time: 0.4600 data: 0.0051 max mem: 22448 +train: [18] [200/400] eta: 0:01:34 lr: 0.000007 loss: 2.0736 (2.1187) grad: 0.1780 (0.1817) time: 0.4649 data: 0.0048 max mem: 22448 +train: [18] [220/400] eta: 0:01:25 lr: 0.000007 loss: 2.0559 (2.1138) grad: 0.1743 (0.1811) time: 0.4724 data: 0.0049 max mem: 22448 +train: [18] [240/400] eta: 0:01:15 lr: 0.000006 loss: 2.0600 (2.1123) grad: 0.1759 (0.1810) time: 0.4541 data: 0.0049 max mem: 22448 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 2.0975 (2.1123) grad: 0.1793 (0.1812) time: 0.4559 data: 0.0050 max mem: 22448 +train: [18] [280/400] eta: 0:00:56 lr: 0.000006 loss: 2.1267 (2.1133) grad: 0.1800 (0.1816) time: 0.4651 data: 0.0050 max mem: 22448 +train: [18] [300/400] eta: 0:00:46 lr: 0.000005 loss: 2.1042 (2.1125) grad: 0.1816 (0.1816) time: 0.4615 data: 0.0050 max mem: 22448 +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 2.0736 (2.1101) grad: 0.1816 (0.1816) time: 0.4553 data: 0.0048 max mem: 22448 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 2.0888 (2.1103) grad: 0.1839 (0.1818) time: 0.4627 data: 0.0048 max mem: 22448 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 2.0926 (2.1089) grad: 0.1800 (0.1815) time: 0.4596 data: 0.0050 max mem: 22448 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 2.1050 (2.1105) grad: 0.1768 (0.1812) time: 0.4880 data: 0.0049 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.1188 (2.1090) grad: 0.1786 (0.1814) time: 0.4925 data: 0.0050 max mem: 22448 +train: [18] Total time: 0:03:08 (0.4707 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.1188 (2.1090) grad: 0.1786 (0.1814) +eval (validation): [18] [ 0/85] eta: 0:04:45 time: 3.3553 data: 3.0856 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:34 time: 0.3834 data: 0.0047 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:20 time: 0.3779 data: 0.0041 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:10 time: 0.3665 data: 0.0046 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:02 time: 0.3675 data: 0.0044 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3603 data: 0.0045 max mem: 22448 +eval (validation): [18] Total time: 0:00:34 (0.4097 s / it) +cv: [18] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.368 acc: 0.295 f1: 0.228 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:07 lr: nan time: 3.4691 data: 3.0582 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:55 lr: 0.000003 loss: 2.0923 (2.0941) grad: 0.1806 (0.1819) time: 0.4764 data: 0.0046 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:11 lr: 0.000003 loss: 2.0923 (2.1013) grad: 0.1813 (0.1818) time: 0.4431 data: 0.0044 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:51 lr: 0.000002 loss: 2.1057 (2.1048) grad: 0.1813 (0.1821) time: 0.4446 data: 0.0050 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:38 lr: 0.000002 loss: 2.1133 (2.1023) grad: 0.1824 (0.1829) time: 0.4633 data: 0.0048 max mem: 22448 +train: [19] [100/400] eta: 0:02:26 lr: 0.000002 loss: 2.1280 (2.1021) grad: 0.1822 (0.1827) time: 0.4698 data: 0.0053 max mem: 22448 +train: [19] [120/400] eta: 0:02:15 lr: 0.000002 loss: 2.1146 (2.1130) grad: 0.1816 (0.1827) time: 0.4668 data: 0.0049 max mem: 22448 +train: [19] [140/400] eta: 0:02:05 lr: 0.000001 loss: 2.0972 (2.1115) grad: 0.1833 (0.1834) time: 0.4536 data: 0.0048 max mem: 22448 +train: [19] [160/400] eta: 0:01:54 lr: 0.000001 loss: 2.0938 (2.1114) grad: 0.1833 (0.1832) time: 0.4541 data: 0.0051 max mem: 22448 +train: [19] [180/400] eta: 0:01:44 lr: 0.000001 loss: 2.1294 (2.1164) grad: 0.1825 (0.1825) time: 0.4714 data: 0.0049 max mem: 22448 +train: [19] [200/400] eta: 0:01:35 lr: 0.000001 loss: 2.0929 (2.1092) grad: 0.1789 (0.1827) time: 0.4683 data: 0.0051 max mem: 22448 +train: [19] [220/400] eta: 0:01:25 lr: 0.000001 loss: 2.0640 (2.1077) grad: 0.1857 (0.1834) time: 0.4460 data: 0.0048 max mem: 22448 +train: [19] [240/400] eta: 0:01:15 lr: 0.000001 loss: 2.1480 (2.1142) grad: 0.1886 (0.1833) time: 0.4531 data: 0.0049 max mem: 22448 +train: [19] [260/400] eta: 0:01:06 lr: 0.000000 loss: 2.1490 (2.1125) grad: 0.1843 (0.1833) time: 0.4774 data: 0.0051 max mem: 22448 +train: [19] [280/400] eta: 0:00:56 lr: 0.000000 loss: 2.1101 (2.1127) grad: 0.1771 (0.1827) time: 0.4804 data: 0.0050 max mem: 22448 +train: [19] [300/400] eta: 0:00:47 lr: 0.000000 loss: 2.1000 (2.1120) grad: 0.1767 (0.1828) time: 0.4618 data: 0.0050 max mem: 22448 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 2.0767 (2.1104) grad: 0.1767 (0.1825) time: 0.4604 data: 0.0048 max mem: 22448 +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 2.0527 (2.1064) grad: 0.1756 (0.1820) time: 0.4697 data: 0.0050 max mem: 22448 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.0797 (2.1090) grad: 0.1842 (0.1823) time: 0.4678 data: 0.0048 max mem: 22448 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 2.1346 (2.1088) grad: 0.1850 (0.1824) time: 0.4605 data: 0.0050 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.0873 (2.1092) grad: 0.1737 (0.1822) time: 0.4630 data: 0.0051 max mem: 22448 +train: [19] Total time: 0:03:08 (0.4707 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.0873 (2.1092) grad: 0.1737 (0.1822) +eval (validation): [19] [ 0/85] eta: 0:04:41 time: 3.3092 data: 2.9864 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:32 time: 0.3639 data: 0.0052 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3450 data: 0.0036 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3302 data: 0.0041 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3372 data: 0.0044 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3318 data: 0.0044 max mem: 22448 +eval (validation): [19] Total time: 0:00:32 (0.3811 s / it) +cv: [19] best hparam: (0.52, 1.0) (020) ('020_lr5.2e-01_wd1.0e+00') loss: 2.367 acc: 0.295 f1: 0.228 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.29494278331487633, "hparam": [0.52, 1.0], "hparam_id": 20, "epoch": 19, "is_best": false, "best_score": 0.2956810631229236} +eval (train): [20] [ 0/509] eta: 0:27:27 time: 3.2374 data: 2.9738 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:01 time: 0.3562 data: 0.0032 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:16 time: 0.3425 data: 0.0054 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:02:56 time: 0.3367 data: 0.0034 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:44 time: 0.3525 data: 0.0038 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:35 time: 0.3702 data: 0.0044 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:26 time: 0.3513 data: 0.0042 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:17 time: 0.3490 data: 0.0041 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:08 time: 0.3474 data: 0.0037 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:01 time: 0.3644 data: 0.0042 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:53 time: 0.3631 data: 0.0043 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:45 time: 0.3574 data: 0.0042 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:38 time: 0.3780 data: 0.0042 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:31 time: 0.3632 data: 0.0040 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3631 data: 0.0043 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3599 data: 0.0044 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3652 data: 0.0044 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3575 data: 0.0042 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3616 data: 0.0041 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3588 data: 0.0044 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3571 data: 0.0042 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3672 data: 0.0039 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3587 data: 0.0041 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3261 data: 0.0037 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3671 data: 0.0045 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3450 data: 0.0041 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3321 data: 0.0039 max mem: 22448 +eval (train): [20] Total time: 0:03:05 (0.3635 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:41 time: 3.3093 data: 2.9952 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3728 data: 0.0046 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3434 data: 0.0038 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3994 data: 0.0049 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3509 data: 0.0041 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3407 data: 0.0040 max mem: 22448 +eval (validation): [20] Total time: 0:00:34 (0.4025 s / it) +eval (test): [20] [ 0/85] eta: 0:04:25 time: 3.1229 data: 2.8156 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:33 time: 0.3881 data: 0.0044 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3426 data: 0.0042 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3973 data: 0.0047 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:02 time: 0.3470 data: 0.0043 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3327 data: 0.0040 max mem: 22448 +eval (test): [20] Total time: 0:00:34 (0.4006 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:23 time: 3.2187 data: 2.9194 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:31 time: 0.3692 data: 0.0043 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.3789 data: 0.0038 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3637 data: 0.0043 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3534 data: 0.0044 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3378 data: 0.0042 max mem: 22448 +eval (testid): [20] Total time: 0:00:32 (0.4019 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.2956810631229236, "hparam": [0.38, 1.0], "hparam_id": 18, "epoch": 14, "is_best": true, "best_score": 0.2956810631229236} +eval (train): [20] [ 0/509] eta: 0:27:24 time: 3.2308 data: 2.9194 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:22 time: 0.4021 data: 0.0054 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:26 time: 0.3374 data: 0.0034 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:08 time: 0.3768 data: 0.0046 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:03:00 time: 0.4227 data: 0.0046 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:48 time: 0.3821 data: 0.0045 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:37 time: 0.3659 data: 0.0040 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:25 time: 0.3394 data: 0.0038 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:16 time: 0.3503 data: 0.0043 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:07 time: 0.3771 data: 0.0044 max mem: 22448 +eval (train): [20] [200/509] eta: 0:02:00 time: 0.4001 data: 0.0049 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:51 time: 0.3516 data: 0.0040 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:43 time: 0.3504 data: 0.0042 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:34 time: 0.3530 data: 0.0041 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:27 time: 0.3858 data: 0.0045 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:19 time: 0.3875 data: 0.0042 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:11 time: 0.3360 data: 0.0038 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:03 time: 0.3544 data: 0.0041 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:56 time: 0.3801 data: 0.0042 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:48 time: 0.3632 data: 0.0041 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:41 time: 0.3653 data: 0.0038 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:33 time: 0.3440 data: 0.0040 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3795 data: 0.0046 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3762 data: 0.0046 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3748 data: 0.0044 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3619 data: 0.0042 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3412 data: 0.0040 max mem: 22448 +eval (train): [20] Total time: 0:03:10 (0.3752 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:12 time: 2.9657 data: 2.6766 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:34 time: 0.4097 data: 0.0056 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:20 time: 0.3932 data: 0.0043 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3662 data: 0.0043 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3644 data: 0.0042 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3471 data: 0.0040 max mem: 22448 +eval (validation): [20] Total time: 0:00:35 (0.4137 s / it) +eval (test): [20] [ 0/85] eta: 0:04:08 time: 2.9203 data: 2.6670 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:29 time: 0.3364 data: 0.0050 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3723 data: 0.0034 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3841 data: 0.0044 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3405 data: 0.0041 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3263 data: 0.0039 max mem: 22448 +eval (test): [20] Total time: 0:00:33 (0.3885 s / it) +eval (testid): [20] [ 0/82] eta: 0:03:55 time: 2.8663 data: 2.5948 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:33 time: 0.4178 data: 0.0046 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.3569 data: 0.0043 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3728 data: 0.0048 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3323 data: 0.0040 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3202 data: 0.0040 max mem: 22448 +eval (testid): [20] Total time: 0:00:32 (0.4006 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|---------:|-----:|------------:|:------------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 14 | 0.000114 | 0.05 | 18 | [0.38, 1.0] | train | 2.1286 | 0.35831 | 0.0023368 | 0.29595 | 0.0023133 | +| flat_mae | patch | attn | nsd_cococlip | best | 14 | 0.000114 | 0.05 | 18 | [0.38, 1.0] | validation | 2.3574 | 0.29568 | 0.0052654 | 0.2247 | 0.0049165 | +| flat_mae | patch | attn | nsd_cococlip | best | 14 | 0.000114 | 0.05 | 18 | [0.38, 1.0] | test | 2.2639 | 0.3128 | 0.00559 | 0.24265 | 0.0055982 | +| flat_mae | patch | attn | nsd_cococlip | best | 14 | 0.000114 | 0.05 | 18 | [0.38, 1.0] | testid | 2.2681 | 0.31001 | 0.0056353 | 0.24743 | 0.0053609 | + + +done! total time: 1:24:59 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/train_log.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..229836fdb8952636691e15179ae92f803f254fb7 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1248835158348083, "train/grad": 0.07007952475920319, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.180445556640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.18013916015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.179659423828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.179176025390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.178736572265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1780224609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.177298583984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.176478271484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.175418701171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.174324951171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.17330322265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.17182861328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.170296630859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.16832763671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.166456298828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.164796142578125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.16277099609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.16054931640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.158402099609375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.15647705078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.154415283203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.152587890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1507177734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.14902099609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.147506103515625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1458740234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.144735107421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.143714599609375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.14259033203125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.141519775390625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1405712890625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.13991943359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.139071044921875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.138330078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.137596435546875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.136697998046875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.13553466796875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1334735107421876, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.126741943359375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.107404327392578, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.084527587890625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.061809387207031, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0330140686035154, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0102087020874024, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9861255264282227, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9587260627746583, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.934400634765625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.910984115600586, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.8985690021514894, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008944672890938818, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008935868076514452, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008921657148748636, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008907548440620304, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008893882220145316, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008875341229140759, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00885500811971724, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008833057982847094, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0088052071724087, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008776724652852863, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008750139996409416, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008712534594815224, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008678193315863609, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008632796045858412, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008594371387735009, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008561539745423943, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008524888944812119, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00848946720827371, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008459121822379529, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008438757110852749, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008422992269042879, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008414900894276798, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008413549959659577, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008417078088968992, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008423746994230897, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00843326379545033, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008443259375635535, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008452063088770955, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008462959623429925, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008475630001630634, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008485810125712305, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00849505384452641, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008504164342302828, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008510811440646648, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008516177854035049, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008519950152840466, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00853274084161967, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008588513487484305, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008848256622441113, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009662951403297483, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01032432672334835, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011038883219007402, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01182648700196296, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01242305874126032, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.013180894090328365, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014204691457562148, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014873666006606072, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01593510259874165, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01714307953370735, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1769917011260986, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.176023483276367, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1744399070739746, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.172914743423462, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.171412229537964, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1693830490112305, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.167166233062744, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.164783000946045, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.161742687225342, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.158689498901367, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.155839443206787, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.151855707168579, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1482796669006348, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.143671751022339, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1398158073425293, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.136627197265625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1332716941833496, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1302173137664795, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.127821445465088, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1263344287872314, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1252923011779785, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124804973602295, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1246395111083984, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1246466636657715, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1247360706329346, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.124826669692993, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.124790906906128, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.124664068222046, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1243107318878174, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.123669385910034, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1229708194732666, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1222422122955322, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.121107339859009, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1198313236236572, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1174817085266113, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1130599975585938, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.101339817047119, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0640764236450195, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9626243114471436, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8879098892211914, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.805483102798462, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.788156747817993, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7085001468658447, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6518306732177734, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6197497844696045, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.59751558303833, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.601372241973877, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.5887374877929688, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.540508508682251, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05795496493170912, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.067921742340347, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06921373200442968, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0753045404208195, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09376153562200074, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.11941675895164268, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.14857881136950904, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17072720561092655, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.17238833517903285, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18844592100406055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20007382798080472, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.21428571428571427, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22259136212624583, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22609819121447028, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23034330011074197, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.23735695828719083, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009703928178780033, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009337049896094901, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008829060714149455, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008999933589174116, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009082281729144518, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007880356616606162, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007550344396909703, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006815456157896849, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007291873506235918, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00793819839753476, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007543558323421813, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008138618318976262, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008607155160278789, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009360438927847587, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009837065102605817, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009854913893280309, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010047812010630488, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.009294576926382558, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.006120965310983575, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.004958246346555324, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00496410790783837, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005166579679888658, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005373149991198495, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0059078312369337796, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.006614459706238587, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.007479290964732872, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.008320060094532003, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.009356210599578411, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.009595889621720092, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.009838283219578184, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.010064328918883638, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.013649832384044915, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.033779913790692014, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04280766116627437, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06409261087344015, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.09139498904313374, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.10149404854047435, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.11975271934670899, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13267490849371474, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.14252223455419202, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14400925786448954, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15404718968337197, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.16111489018953054, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15917272226751836, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.8985690021514894, "validation/loss_best": 2.540508508682251, "validation/acc_best": 0.23735695828719083, "validation/f1_best": 0.15917272226751836} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.9479333782196044, "train/grad": 0.1098721645027399, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.168983154296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.167386474609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.164771728515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.162193603515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.160037841796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.157093505859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.154068603515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.151004638671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.147607421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.144482421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.141893310546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.138809814453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.136412353515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.133822021484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.132218017578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.13093505859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1298486328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.128922119140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12812744140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.127725830078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.127125244140625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12674560546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126318359375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.125582275390625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.124864501953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.12365234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.122374267578125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.120557861328125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.114609375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0886355590820314, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0442404174804687, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9959698486328126, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.928113021850586, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.867975158691406, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7983620452880857, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7333919906616213, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.67655912399292, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.619244918823242, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.570370788574219, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5291984128952025, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.508294019699097, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.496354646682739, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4870556592941284, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4826718521118165, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.493271646499634, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.496278922557831, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.508367727994919, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.5386735928058624, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.567534511089325, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008460081787779928, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008416372949723154, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008349925219081343, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008291224769782274, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008238890152424573, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008176094342488796, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008116953924763947, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008063854596111924, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008011819054372609, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007974760897923261, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007953931109514088, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007943037536460907, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007949739028699696, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007975426693446934, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008007004156243057, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008038855222985149, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008078362236265093, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008118809617590159, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008155636424198746, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008182917174417525, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008206729833036662, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008222434637136757, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008232146175578237, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008235627948306502, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008233682047575712, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008224535949993879, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008215398853644728, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008213956784456968, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00831985850352794, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009165795058943332, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010506300136912615, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.011703579830937087, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013188081507105381, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014677935717627407, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01637071239296347, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.018031098865903913, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.019487637793645263, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02109977768268436, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.022227275180630387, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02311406773980707, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02393754694610834, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02465682562440634, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.025544868186116218, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.026195426732301713, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.026419379776343704, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.027458277838304637, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.028559863604605197, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.030225580176338553, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0315478634275496, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1603775024414062, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1576502323150635, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1535160541534424, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1498169898986816, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1465306282043457, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1425371170043945, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.138718843460083, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1352479457855225, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.131754159927368, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.129058361053467, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.127183437347412, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125399112701416, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124363660812378, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1235198974609375, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1230671405792236, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122817277908325, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1225426197052, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1222214698791504, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1218297481536865, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1214096546173096, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1207830905914307, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1200313568115234, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.119018793106079, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.117750644683838, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.116077184677124, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1132419109344482, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1087305545806885, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.098949432373047, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.041088819503784, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.843008041381836, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7303273677825928, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6502749919891357, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5856006145477295, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.536198139190674, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.514448881149292, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5089733600616455, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.517587184906006, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5088727474212646, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.490257501602173, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.478254556655884, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.472428321838379, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.497380018234253, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5406253337860107, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5651915073394775, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7506513595581055, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.632540225982666, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.558123826980591, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.5889346599578857, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.651395320892334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07419712070874862, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.11092654115909929, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.162421557770395, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.18512366186784793, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2041343669250646, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21391657438169065, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23052787006275377, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24953857511997046, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25249169435215946, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24381690660760427, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2351421188630491, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2026578073089701, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21908453303802142, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2249907715023994, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.21428571428571427, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006753270736239301, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007402717826998681, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007625340768622043, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0082305385103049, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008674344871684118, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009279661177576613, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00966557391024494, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009867812368158061, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009939811850803528, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010250184878782032, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009903233753058573, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009433116672834937, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009195588559941006, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009374139679315198, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010114235206024258, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010448897510364789, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010224976420145776, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01000534188034188, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.010872511000699095, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01220404011523906, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.015018917129098414, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.015213900853666447, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013888117812053714, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013593971258232203, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.015585920860684548, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.021823697657855152, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.027175354815271325, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03277148930716633, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.046742735257941204, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08087763380318562, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.10243276734108268, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12067152122178942, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1351425944716078, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15729041639485283, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16020771689306923, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16602890484339825, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16802563682070104, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1756404739547608, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18339785120160765, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1818087974450174, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18537432408215845, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17286394195486446, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.164685071682228, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16271027403301327, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1350465440572901, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14236868974092937, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15300559920853787, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15269835715578858, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.14706374508648687, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 2.570370788574219, "validation/loss_best": 2.490257501602173, "validation/acc_best": 0.2541528239202658, "validation/f1_best": 0.18339785120160765} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.824316794872284, "train/grad": 0.14456998962908985, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15188720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.149158935546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.145142822265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.141773681640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.139111328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.136195068359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.133692626953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1316943359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13004150390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1288916015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.128223876953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127509765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.126549072265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126181640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12563232421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125137939453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12442626953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1235986328125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.122684326171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121358642578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.119576416015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11612060546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.104578857421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0608309936523437, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.974397888183594, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8867298126220704, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8032114410400393, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.697690658569336, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5974740600585937, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.535293598175049, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.491798439025879, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.445956802368164, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4169014167785643, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3887232875823976, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.366203799247742, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3558904409408568, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3393797099590303, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.337088522911072, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3467179322242737, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3625067234039308, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3768949127197265, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3910294508934022, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4126967144012452, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.45884471654892, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4928554093837736, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5272151398658753, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.5841547298431395, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6348404228687285, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008275243467651308, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008226147096138448, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008165750049520283, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008127917619422078, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00810729391174391, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008100698455236852, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008114929622970522, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008146335566416384, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008197935111820698, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008253012772183866, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00830116524361074, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008359212356153875, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008398911599069834, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008435564374085516, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008455313520971685, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008466130020096899, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008473613548558205, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008476957681123167, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008475251249037682, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00847073741722852, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008460832424461842, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008448549646418542, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008457125679124147, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008711837364826351, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010004005995579063, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01245530383195728, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.014786413684487344, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.016788806419353933, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0192462222231552, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.021374129578471183, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02252264292910695, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.023243218436837198, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02433457775041461, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.025173114668577908, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.026290910299867392, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02689780465327203, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027217317475005984, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02786822719499469, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.028474078448489308, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02952340153977275, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029751710267737506, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.030405735280364752, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.031219402430579066, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0321528928168118, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.032645150171592835, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03455795624293387, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.035720468945801255, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03781108469702303, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04001011135056615, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1420936584472656, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1387815475463867, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1343932151794434, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1311376094818115, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.128739595413208, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.126443386077881, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1248326301574707, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1237637996673584, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1230313777923584, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122624397277832, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1224260330200195, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.122227191925049, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1220803260803223, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.121896505355835, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.12170147895813, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1214709281921387, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1210830211639404, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1205084323883057, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1196255683898926, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.118495464324951, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.116335391998291, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.111988067626953, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0973715782165527, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.012049436569214, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8198916912078857, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.7013485431671143, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6384775638580322, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5942859649658203, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5501413345336914, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5207507610321045, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5118393898010254, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5124998092651367, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5043253898620605, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4976892471313477, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.49676775932312, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.524092197418213, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5412073135375977, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5145485401153564, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.488074779510498, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4728264808654785, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5013389587402344, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5456647872924805, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6170706748962402, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.691542625427246, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7867839336395264, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.686929941177368, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.740020990371704, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7076077461242676, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.8934519290924072, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08416389811738649, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1153562200073828, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.15873015873015872, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1788482834994463, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.19564414913252123, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.21040974529346623, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2216685123661868, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24953857511997046, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2441860465116279, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24086378737541528, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21779254337393872, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21520856404577335, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.20339608711701734, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21705426356589147, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22831303063861202, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20191952750092285, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009232161938493052, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00972332742297122, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009943900246651866, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010102707516196808, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010075304424302572, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008612809028046436, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006116071428571428, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00557362889548776, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004972744142890281, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00496410790783837, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00496410790783837, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.004964970181228649, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005179723755871183, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005180734639404797, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005181771846187326, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005185412745483022, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005374473539644754, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.006205336502611643, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0076361858142643705, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.00959600751908373, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01295476572048087, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02394713560072599, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.045426068753451315, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.07635403484824604, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09228533196095744, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10870043791120372, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1274054401940596, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.14086778668184977, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.15984575395836598, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.16211458842251633, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.16062101751406208, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.16218411110315167, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16330478481510433, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16660978381922162, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16693361703743068, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16619794644519195, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.16924335276995314, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17120068746970718, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17645232190757362, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16586002637629485, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16905501031705192, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15802488712964902, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16719647566544635, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1408479941538893, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14703314819784916, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1542536313208478, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15772721179627727, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.12924881398312413, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 2.3467179322242737, "validation/loss_best": 2.4728264808654785, "validation/acc_best": 0.24953857511997046, "validation/f1_best": 0.17645232190757362} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.7775627899169923, "train/grad": 0.1990815170109272, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1367041015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13410400390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.130972900390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128924560546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127581787109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126490478515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125623779296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1249462890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12446533203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.123936767578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12343994140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1228125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122193603515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1211669921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1202001953125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11910400390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.117613525390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11544921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.111834716796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.10394287109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0660284423828124, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9813807678222655, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8644789123535155, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.7390290832519533, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.63715576171875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.550411319732666, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4918586158752443, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.446469717025757, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3998681259155275, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.360622773170471, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.33022292137146, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3050538635253908, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2844020771980285, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2715510296821595, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2616622257232666, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.260985107421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2691971266269686, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.271485948562622, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.289418716430664, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3042830848693847, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3250530314445497, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3464513742923736, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.37143439412117, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4108950448036195, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.4816027653217314, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.544563410282135, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5689022266864776, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7024303174018858, "train/loss_048_lr5.0e+01_wd1.0e+00": 4.5021740293502805, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00813445935724303, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00812523962231353, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008140208711847664, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008176073986105621, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008219776807818562, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008278990390244871, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008336762664839625, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008385815827641635, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008427705396898091, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00845366741763428, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008467916387598962, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008478393342811615, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008481887844391167, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008483273808378726, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008480399393010884, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008476634295657277, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008469270523637534, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008459029833320529, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008460968693252652, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00857612700900063, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00963344970252365, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01215687145711854, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.015585620461497456, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.018791454527527094, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02078660940285772, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.022167454697191714, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.023113126773387192, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02401639093644917, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.025147532364353537, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02602986928075552, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02679136867634952, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02739518877118826, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.027795969638973475, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02816756007261574, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.028843544451519848, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02989219835028052, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03044690176844597, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03127156444825232, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03193875478580594, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.032681321166455744, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.032609557742252944, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.033375746104866266, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03366338174790144, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03532712523825467, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03627882798202336, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03931821031495929, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04020979294553399, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04398343743756414, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06038681732490659, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1295292377471924, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1273958683013916, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1251096725463867, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1238229274749756, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12312912940979, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1225850582122803, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122199058532715, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121948719024658, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1217153072357178, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1214942932128906, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1213202476501465, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121039390563965, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1207706928253174, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.120317220687866, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1198222637176514, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1191587448120117, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1179330348968506, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.115168333053589, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.106757164001465, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0722622871398926, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8956921100616455, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.733466863632202, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.637834310531616, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5621466636657715, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5022530555725098, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.473288059234619, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4642820358276367, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4670541286468506, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4870445728302, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.500854969024658, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4985530376434326, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.494114398956299, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4699504375457764, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.435837745666504, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4330081939697266, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.45530366897583, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4574949741363525, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.448598623275757, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4432265758514404, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.556095600128174, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.569014072418213, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.657466411590576, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7118895053863525, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7672765254974365, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.997426748275757, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.90903902053833, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8904144763946533, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.181511878967285, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.08600959763750461, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.14857881136950904, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.18696936138796605, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2102251753414544, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23181985972683647, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.266703580657069, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25046142488002954, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25249169435215946, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23181985972683647, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21908453303802142, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2087486157253599, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20062753783684018, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1878922111480251, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009762755564026728, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01029909403567946, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010273942449442922, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009767104718759608, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00904081023103343, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008839522608130474, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008195805795368378, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0081258348649653, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007925608791307095, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007443172678897938, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007268066735038485, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0063463232910841, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005874546609174122, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005357233533084188, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005372012259193437, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005373110646605545, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005214153774337594, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00565900511757268, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007984796907816541, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03107491944686094, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.06604683381891409, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.09962585800681617, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.12240357051494906, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14474883561233545, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16556618711647997, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.17994117775921134, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18473404531444837, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.18338963645109044, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1806380312380598, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17951346134781665, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18164198120732977, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18125377970757317, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18532877729174702, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18804197054369487, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19415277461524635, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20182325545962018, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.195882544496676, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19871671561189563, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1983699946560078, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1773983607701558, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17851587674584157, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15921198597265443, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15012700050747765, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14113127230025452, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13004697371530352, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1320274822748333, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.14172528935137033, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1226096907334746, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 2.2616622257232666, "validation/loss_best": 2.4330081939697266, "validation/acc_best": 0.266703580657069, "validation/f1_best": 0.19415277461524635} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.782145323753357, "train/grad": 0.2844285161048174, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1329248046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.131912841796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1308349609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130267333984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1299462890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129525146484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129093017578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1286279296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.128011474609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12723388671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12660888671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12548828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.124354248046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.122403564453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.120250244140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.117198486328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1095654296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0733737182617187, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.963242492675781, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.8361941528320314, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.695586929321289, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.601012763977051, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.526720447540283, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4623760032653808, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.409965648651123, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.358201723098755, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.322946090698242, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2956776142120363, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2631177139282226, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2334558534622193, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2143514728546143, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2021748065948485, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2008750772476198, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.203313331604004, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2053236150741578, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2130769324302673, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.222176730632782, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2285967755317686, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2556805288791657, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.289820659160614, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3127744793891907, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3465904700756073, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4180631744861603, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.440356894135475, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5409179127216337, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5984857058525086, "train/loss_046_lr3.6e+01_wd1.0e+00": 5.445423300266266, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.6291286301612855, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008163776341825723, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00821672728518024, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008299600121099503, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00836348073091358, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008409360412042589, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008450486569199712, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008476450620219112, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008491821228526533, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008500988406594842, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008505105443764477, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00850666914600879, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008506620309781283, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008505355091765523, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008501764645334333, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008497916751075536, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008503999197855591, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008609168790280819, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009651714081410318, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012811627793125809, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01634590537752956, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019832136309705675, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.021797948670573532, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.022851233198307456, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02368272085674107, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02454038307070732, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.025747685050591825, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.026617108322679998, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02730508130043745, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02819350579753518, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028740969514474274, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029501166101545094, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030039106607437135, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030334670804440977, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030870437165722252, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03167844532988966, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03249417843297124, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03279956963844597, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0332449403218925, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.034244248867034914, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.035312308743596074, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03537791491486132, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03545587765984237, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.038562375213950874, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03822474137879908, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04086307696998119, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04348006844520569, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.10615860068239272, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06389793811365962, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1246466636657715, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1237518787384033, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1229305267333984, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122490167617798, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1221675872802734, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121861696243286, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121492862701416, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1211156845092773, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1206095218658447, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1200335025787354, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.119446277618408, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.118464231491089, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1173324584960938, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115234851837158, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.111943006515503, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.105686902999878, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.078108310699463, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9133379459381104, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7194817066192627, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6217026710510254, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5400919914245605, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4741828441619873, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.434159755706787, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.410122871398926, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3951773643493652, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3920071125030518, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.389941453933716, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.39216947555542, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4039294719696045, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4240217208862305, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4119789600372314, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.3753082752227783, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.3627257347106934, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.3762624263763428, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.3843488693237305, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.411966323852539, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4492557048797607, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4814693927764893, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4907314777374268, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.477119207382202, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4582407474517822, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5140748023986816, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.447706460952759, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.568291425704956, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6195242404937744, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6060914993286133, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07899593946105574, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10003691399040236, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14987080103359174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19158361018826134, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21853082318198597, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23403469915097821, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2528608342561831, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2663344407530454, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27445551864156514, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2807308970099668, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2871908453303802, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.29309708379475824, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2884828349944629, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2833148763381321, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.28294573643410853, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.29051310446659284, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2929125138427464, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2929125138427464, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.29051310446659284, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2827611664820967, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.262827611664821, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.26005906238464377, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26947212993724623, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2587670727205611, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2766703580657069, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23661867847914358, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2397563676633444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21631598375784422, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00851958909579782, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0072347608757813665, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00625296156474352, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005927680927680927, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006098992398662556, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006065781982218719, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006508175559380378, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006920586984352926, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008085238717320814, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008410936875873375, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0089709340678314, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010279596564199023, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010675791231763111, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012770149993965389, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.017104626457024347, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.021700583900055085, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.04103373515159666, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07580188930442099, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11414708925162598, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13586708842761833, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.15139051817151264, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17438964771746632, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18934292022101298, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1986364995319507, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2040473739937045, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20870364529927454, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21531058912707532, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21467506267302938, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21107264249624866, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20954370999503583, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2143981115809157, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21724497740312473, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21919520120242508, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.22266840495087256, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.22291062371616702, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2063824125929334, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21131858190312006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21125996954222157, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19628044083753285, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21593813824815486, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2132328760564157, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20310512920412707, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21253738354020527, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19422204905431248, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1839855894991235, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17100398186780616, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.322946090698242, "validation/loss_best": 2.389941453933716, "validation/acc_best": 0.29309708379475824, "validation/f1_best": 0.21531058912707532} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.6974352264404295, "train/grad": 0.25302656173706056, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129283447265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12873046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12810302734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127615966796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127135009765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126358642578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12554443359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.124588623046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12344482421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12213623046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.120743408203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11850830078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.115928955078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.110333251953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0967376708984373, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0467449951171877, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.9119488525390627, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.750917282104492, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.634664421081543, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.559446029663086, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4818896675109863, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.421709909439087, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.371429738998413, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3266625928878786, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2849748659133913, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2487870693206786, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2244721984863283, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.204755344390869, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.1793476343154907, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1614788937568665, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.149821339845657, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.140501855611801, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1470998787879942, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1471011435985563, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1536348062753676, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.148177044391632, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.164278173446655, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.185097415447235, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2204086768627165, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2510856020450594, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2908508479595184, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3343713271617887, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3651560127735136, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4395738899707795, "train/loss_044_lr2.6e+01_wd1.0e+00": 5.300596140623092, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.586528031826019, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008333299316000194, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008379472808446736, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008431268355343491, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008460939622018486, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0084782512485981, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008490865046624094, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008497737352736295, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008501144160982221, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008502239845693111, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008501627668738364, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008499550146516412, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008494610404595733, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008489666958339512, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008510779377538712, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008762764791026712, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010185313988476991, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.014086729260161518, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01857271430082619, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0211321337800473, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.022262418689206243, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.023458042945712805, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.024403134537860752, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02524968173354864, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02608123651705682, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027182815680280328, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028040070002898574, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02870020652189851, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02924756403081119, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030263319155201317, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03089898464269936, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031560718044638635, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03222788388840854, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03254977393895388, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03281590790487826, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03332080505788326, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03379219367168844, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03417319274507463, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03521168948151171, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03605840474367142, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.035892759440466764, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03616169330663979, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.037646798714995384, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.037037287754938, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04032414638437331, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.12628914575092495, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04574347901158035, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122908353805542, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1225194931030273, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1221182346343994, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121797800064087, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121483087539673, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121044397354126, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1205382347106934, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.119943380355835, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1190948486328125, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.118086814880371, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.116950273513794, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.114816188812256, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1117751598358154, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1020052433013916, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0590734481811523, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.9047751426696777, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.727888822555542, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6238903999328613, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5519187450408936, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4983983039855957, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4519264698028564, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4247961044311523, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.410384178161621, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4014008045196533, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.384153366088867, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.378257989883423, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.3848557472229004, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4062652587890625, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4502789974212646, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4392223358154297, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.470116138458252, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.508915901184082, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5039007663726807, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.547154426574707, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.565995693206787, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.524641275405884, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4932897090911865, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5062267780303955, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4683034420013428, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.485934257507324, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.596444606781006, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6250529289245605, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6008808612823486, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6034128665924072, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6822757720947266, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08010335917312661, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.10852713178294573, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.14857881136950904, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18420081210778885, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2087486157253599, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22388335179032853, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24234034699150978, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2567368032484312, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.262827611664821, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.28036175710594313, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28645256552233295, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2870062753783684, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27906976744186046, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2727943890734588, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2652270210409745, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24049464747139165, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23255813953488372, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2321889996308601, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008024708429166456, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007758620689655173, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00812230419913913, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00880221323525958, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009705386243067882, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009798173413011613, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009977883360405011, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010416636993357925, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010740842576645876, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011304690103218223, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011327269595421526, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01256456400039444, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013629983458521669, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.018696982327284974, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.045429640664386206, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06910999047568717, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10384264558403904, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.128282955521066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1435452658136838, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1638816983324499, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.18310855486050417, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1911579707022387, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19675663827613699, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20757816043081925, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21467690317974797, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2190078143128312, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2206039539655803, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21592372423176667, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20753385781009026, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21118405855254083, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20292783936804018, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20080811891027553, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19842264063210632, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19587251223464527, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19643319570135911, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19372407018708038, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1988506153803793, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1793888221768943, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19904733488073778, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19687682838389564, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17719812451806238, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16353843369686394, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1938611846416519, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19797235337180039, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17145708227757486, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.2244721984863283, "validation/loss_best": 2.3848557472229004, "validation/acc_best": 0.2870062753783684, "validation/f1_best": 0.2206039539655803} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.567630029916763, "train/grad": 0.1721582194417715, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123707275390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1232861328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.122620849609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121998291015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1213232421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.120382080078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1193798828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11812744140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.116541748046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.114603271484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.112469482421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.108143310546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.100653076171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0580450439453126, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9212864685058593, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7718248748779297, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6463934326171876, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5520591735839844, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.472347640991211, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4122684669494627, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3530719566345213, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.3032806396484373, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2531059074401854, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.2076344156265257, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1653834056854246, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.129427409172058, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1039515995979308, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0836366629600525, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.059617569446564, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0443767166137694, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0362605583667754, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.030132795572281, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0331773281097414, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0312802243232726, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.038000464439392, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.044290673136711, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.057612345814705, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.08027784883976, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1115610939264298, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.148970695734024, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.183460122346878, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2202098679542543, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2798858422040937, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.326061750650406, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.444245045185089, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008419242578092963, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0084507413697429, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008481665675062686, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0084970220644027, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008505488133523613, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008512029086705297, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008515796402934938, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008518202225677668, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00851971650728956, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008519070791080594, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008519023738335818, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00852598129073158, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008592852442525327, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009602900736499578, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013490382968448102, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01764115024358034, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020617197495885194, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02216629155911505, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.023314897110685705, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024210819937288762, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.025059557603672147, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026002581268548965, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026862278264015913, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02736690152436495, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02810795824043453, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028532119523733853, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028787604682147503, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029004283687099813, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029907085299491883, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03043176761828363, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031055042576044797, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03158199181780219, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03184797773137689, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03219509458169341, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0326320580393076, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.033364826077595354, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03365772983990609, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03488092567771673, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03530854072421789, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03559689951129258, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03510964383371174, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03520195602439344, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.037063859887421134, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03747923068702221, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04061929876916111, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1220180988311768, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1216676235198975, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121171712875366, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1206893920898438, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.120190382003784, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.11950945854187, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1187033653259277, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1177825927734375, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1164517402648926, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1147634983062744, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1126320362091064, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.107279062271118, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0939230918884277, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9809463024139404, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.776285171508789, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6624221801757812, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5779623985290527, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.506620168685913, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4539268016815186, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4256842136383057, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.40262770652771, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.393372058868408, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3934173583984375, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4031589031219482, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4008429050445557, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.415349006652832, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.427467107772827, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4445955753326416, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.464153528213501, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4730653762817383, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4760162830352783, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.479994058609009, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5206611156463623, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5622565746307373, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.583658456802368, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5773675441741943, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.658405065536499, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7007057666778564, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7000653743743896, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7414345741271973, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.675306558609009, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5855374336242676, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.595258951187134, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6283018589019775, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6245179176330566, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.08324104835732743, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.13732004429678848, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1805094130675526, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.20339608711701734, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.22388335179032853, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2397563676633444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2622739018087855, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27002583979328165, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.27408637873754155, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2781469176818014, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28146917681801403, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27611664820967147, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2798080472499077, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2777777777777778, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27759320782576596, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2676264304171281, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2441860465116279, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24640088593576967, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2602436323366556, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25544481358434845, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23421926910299004, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006463740107227538, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006316403331328705, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006819968170450485, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007332238970875068, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007369007803790412, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007650908489491984, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008111086297942988, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008108435040217667, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008298587245974048, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009204801392056275, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00956316076980094, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013529685767050501, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02584400795765387, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06661545764614299, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.09897575200724773, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1234944266522251, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.14409566666811227, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.16126268110118885, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.18603599437856044, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19562952761289143, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1992093161700166, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2058792216943688, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20947479352228204, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20846468399551732, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21346343069906637, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21264793385108346, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21642419166299623, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21656706940682846, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20806771810119087, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20732521375172885, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20248270029602988, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20444551154844914, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1938972763579786, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19103135684450137, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1879012242250422, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19707649981865605, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18315212015345048, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17107209794290645, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1741823242157332, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.16844129544094247, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1729820886338919, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18428098951629276, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18326874686187336, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18391737760147978, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.18103797944665537, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.2531059074401854, "validation/loss_best": 2.3934173583984375, "validation/acc_best": 0.28146917681801403, "validation/f1_best": 0.20947479352228204} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.5214220559597016, "train/grad": 0.17744392201304435, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125528564453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1250146484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1242529296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.123466796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.122645263671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.121568603515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.120245361328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.118629150390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11637939453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.113626708984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11003662109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0993701171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0604888916015627, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8788493347167967, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7205384826660155, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6267777252197266, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.541995391845703, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.462890281677246, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3976430320739746, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.347345008850098, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2924294090270996, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.243852252960205, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1932310676574707, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.150162410736084, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.10882306098938, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0757537198066713, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.051059947013855, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.033522665500641, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.005891559123993, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.990986214876175, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.979186989068985, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9666162997484207, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9670559358596802, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9681678467988968, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9769398635625839, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9823836338520051, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0008645087480543, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.0236759865283966, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.058137288093567, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1003864508867265, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1404302948713303, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.186248025894165, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2348526692390442, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2833093893527985, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.390923911333084, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00834273810731247, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008360516005195677, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008374535799957812, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00838023009710014, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008382181676570327, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008381880614906549, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008379953950643539, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00837656817631796, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008371112900786102, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008368009021505713, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008374859432224184, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008498012179043144, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00946345086907968, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014525952585972845, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01875876435544342, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020909402212128045, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02253666948527098, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023868575068190692, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.024756289338693022, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.025496309576556086, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026459712544456126, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027255491679534317, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027920823674649, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028314000377431512, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028968926724046468, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029543866254389286, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030221281442791223, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030770907076075674, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03186654058285057, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.032493776753544805, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03289836282841861, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03321373456157744, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03318726062774658, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03366626837290823, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.033795700250193475, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03463392524048686, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03446461428888142, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03502922429703176, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.035412446931004524, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03607644799165428, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.035112085621804, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03573735075071454, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03582340215332806, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.036496582860127094, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.037740683080628515, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.121049404144287, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1206438541412354, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1200082302093506, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1193928718566895, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.118777275085449, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1179416179656982, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1169536113739014, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1157968044281006, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1140284538269043, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.111440896987915, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.107224941253662, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.089418649673462, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.000373125076294, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7636632919311523, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.641242265701294, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.569694995880127, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.501216173171997, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.449387311935425, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.421189785003662, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.403012752532959, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3852782249450684, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3686037063598633, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.358151435852051, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3675713539123535, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3825457096099854, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.415008068084717, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.458921432495117, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4978084564208984, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5270485877990723, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4961421489715576, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4836277961730957, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5131418704986572, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5441644191741943, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.580268383026123, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.563188076019287, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.558468818664551, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5660784244537354, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5391604900360107, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.575627565383911, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6307761669158936, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.635652780532837, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5956037044525146, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5379459857940674, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5376245975494385, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.647298812866211, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.073827980804725, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08250276854928018, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.12624584717607973, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17755629383536362, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.20967146548541898, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2249907715023994, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24769287559985234, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2742709486895533, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27870062753783686, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2812846068660022, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28608342561830935, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2918050941306755, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28959025470653377, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2857142857142857, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2823920265780731, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.27648578811369506, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27722406792174237, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2427094868955334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24455518641565152, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24529346622369877, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23255813953488372, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008116832388276892, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008448029111979836, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009180577838375262, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009117253884332691, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008999750658361947, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010045360080682015, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010898339530129477, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011493225694438239, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012416098408812649, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01526024527023024, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.017343371017772013, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.026561611624863406, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06010957022808202, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.10052067694131565, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.12917662662122045, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1460575678748052, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.16975193322161178, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19293705662361235, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20049989916712144, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2079621709116857, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2116731869183628, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2147471174159056, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22131416466144893, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22289869402979923, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22097865337298983, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.217719546706445, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21249486352506933, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2125861210746358, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20358131092178935, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22446662821885513, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2297323750719307, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22037717271207366, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.22283535443317226, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21255498316693475, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21795103214309872, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2236773838755557, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21888212855395675, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.22149208790706645, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2169752296232992, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21518649135004406, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19657332471627245, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19776894536653536, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20292070760707703, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2057278147259556, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.16945767517635069, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 22, "lr_best": 0.00021599999999999996, "wd_best": 0.05, "train/loss_best": 2.1932310676574707, "validation/loss_best": 2.358151435852051, "validation/acc_best": 0.2918050941306755, "validation/f1_best": 0.22131416466144893} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.468872233629227, "train/grad": 0.18278034679591657, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.124874267578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124356689453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123370361328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12234130859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.121387939453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1199755859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11834228515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.116251220703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.113167724609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10852294921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.100301513671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.05623779296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.90947998046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.708879852294922, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.602453842163086, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.529059715270996, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.452686557769775, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.386540746688843, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3276042461395265, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.279114537239075, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.224328055381775, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1742527294158935, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.12448082447052, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.082533121109009, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.0433952951431276, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0114323043823243, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.984622540473938, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9679445385932923, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.938874101638794, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9162399768829346, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9030465364456177, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8926976716518402, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.898078252673149, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8948723429441452, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9097236597537994, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.922377614378929, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9400612914562225, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9614530813694, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9892683440446854, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0248900765180586, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0741947442293167, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.118049119114876, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.166798505783081, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2307799637317656, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.3478985023498535, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008376077632419765, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008383711855858565, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008389106262475252, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008389815476257355, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008389760174322873, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00838889529928565, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008388203002978116, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008387813847512006, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008389882636256516, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008408135080244392, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008499487047083676, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009552307932171971, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013523668125271797, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.018926305091008545, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.021266350019723178, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.022618022076785566, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02408694751560688, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.024940888723358513, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.025869028056040407, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026684367647394538, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0276118129491806, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.028394657103344798, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02906043382361531, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02949406358413398, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03015231657773256, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030694189323112367, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031443465314805505, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03190352804027498, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03279999762773514, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03320518190041184, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.033535585794597866, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.033693865416571496, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.033696171725168825, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.034016956239938737, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03459756691940129, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.035811373554170134, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03583241562359035, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03587749062106013, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03579623161815107, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03541814659722149, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.035159427290782336, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.035497991498559714, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0355872212164104, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0377320097386837, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03903693202883005, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1210289001464844, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1206445693969727, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1199676990509033, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1193103790283203, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1185786724090576, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1175811290740967, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.116332769393921, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.114746332168579, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1119561195373535, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.106976270675659, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0956413745880127, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0133931636810303, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8266377449035645, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.657727003097534, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5697100162506104, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.507369041442871, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4507596492767334, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.4183614253997803, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3944132328033447, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.381443738937378, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.380858898162842, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3880441188812256, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4018282890319824, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.419915199279785, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.417903184890747, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4300150871276855, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.432920455932617, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4415245056152344, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.436041831970215, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4139795303344727, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.426321506500244, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.443708658218384, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4602158069610596, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4786312580108643, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.495088815689087, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.51119327545166, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5472586154937744, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.530271530151367, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5455265045166016, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5071656703948975, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.479922294616699, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.4735803604125977, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.4834632873535156, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5295603275299072, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.56168794631958, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11590992986341823, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.16223698781838317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.20505721668512367, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2279438907345884, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.24621631598375784, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2617201919527501, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2713178294573643, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27556293835363604, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2792543373938723, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2840531561461794, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2840531561461794, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2857142857142857, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2823920265780731, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2842377260981912, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2838685861941676, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.28922111480251017, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.28552971576227393, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.28165374677002586, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2877445551864157, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.28608342561830935, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.28017718715393136, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.284422296050203, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.27906976744186046, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.27888519748984864, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.28054632705795496, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2702104097452935, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2619047619047619, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2733480989294943, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.27150239940937615, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2753783684016242, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.26541159099298633, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2526762643041713, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006098992398662556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005905897841363581, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006143763357432511, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007099745021725517, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007467636325364464, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00753686479759087, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00808656125707792, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009011868677013273, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010203952500108525, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011827898313887085, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01652937096100725, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05122445553193918, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08064589144134572, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.12012359123675946, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.14153684597493857, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.159101063057519, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.18154451641156122, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19457506932569382, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.20325627244457792, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.20810997046123833, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21586463428246472, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2166987967485198, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2171579067551164, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2113169090724404, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21302563792733628, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20964805839626977, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21515440591764468, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21307703342120202, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21261482775985777, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22678839967363906, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22890253213773085, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22650758758830958, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.22353864085014954, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21563007166277262, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.22052062234930872, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22344141155943006, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2117474061656519, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2126737069695547, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20954411796222436, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20684070134785407, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2180103388412092, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21516670140782757, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2232451065556247, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21758267559166145, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19089021667983222, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 1.984622540473938, "validation/loss_best": 2.432920455932617, "validation/acc_best": 0.28922111480251017, "validation/f1_best": 0.21515440591764468} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.4235833609104156, "train/grad": 0.18722217857837678, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12252197265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12187255859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12073974609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.119583740234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.118436279296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.116795654296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.114864501953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11233154296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.107918701171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0997412109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0784765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.94882568359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7773980712890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6260262298583985, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.536550407409668, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.466931266784668, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3997862243652346, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3386667919158937, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2796439647674562, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2321763706207274, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1779494190216067, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1290416145324706, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0792768239974975, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.03579391002655, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9945780587196351, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.9611407613754273, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9310888075828552, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9118063342571259, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8836582112312317, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.859081039428711, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8468145745992661, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.834270731806755, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.835112406015396, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8318335157632828, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.842660523056984, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.852138679623604, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.874510200023651, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8835252290964126, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9118624866008758, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9551982527971268, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0165807366371156, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0542180651426314, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.112411198616028, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.1556608164310456, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.2585875606536865, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008448315688874573, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008454473586753011, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008459667752031236, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008462419270072132, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00846388045931235, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008464882785920053, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008465348852332681, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008467061009723694, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008478719007689506, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008557246215641499, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008984265280887485, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01249026037286967, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.017229209118522704, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021045788363553582, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.022704230956733226, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.024001089027151465, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02508352539502084, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02591473264619708, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02701345824636519, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02778637023642659, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028464403348043562, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.029111313140019773, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029705292349681257, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.030195424938574432, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.030953593822196125, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03158634528517723, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.032256853403523564, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03270765693858266, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03380786932073534, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.034402174660936, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03495433021336794, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03509348233230412, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0350852919742465, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.035432395404204724, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03581577022559941, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.036352707091718915, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.036413413351401684, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03624178568832576, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.036390606639906765, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.036579953664913775, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03620319277048111, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03563345946371555, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03628979140892625, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03620081963017583, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03611693002283573, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1207520961761475, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.120345115661621, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1195898056030273, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1188321113586426, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1180260181427, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.116823673248291, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1152408123016357, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1130361557006836, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1085386276245117, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0980288982391357, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.063544750213623, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.8803818225860596, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.720332145690918, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5966031551361084, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.524780750274658, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4730916023254395, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.435746908187866, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.411736011505127, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3911802768707275, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.378577709197998, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.368727207183838, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.365539073944092, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.369819164276123, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.390216588973999, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.401841402053833, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.412818193435669, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4273297786712646, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4617509841918945, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.500617265701294, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.500091075897217, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.482621192932129, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.502683401107788, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5152573585510254, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.530958890914917, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5984103679656982, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.539156436920166, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5593643188476562, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.544947624206543, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.541121006011963, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.558107376098633, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5348522663116455, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5151872634887695, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5529375076293945, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.565014123916626, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5424792766571045, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07825765965300849, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09856035437430787, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.15319306016980436, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18807678110003692, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22369878183831673, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.23864894795127353, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2587670727205611, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2681801402731635, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.27999261720191954, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2862679955703212, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28497600590623845, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28552971576227393, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28165374677002586, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2827611664820967, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28165374677002586, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2838685861941676, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2796234772978959, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.27445551864156514, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2753783684016242, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.27648578811369506, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2709486895533407, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26688815060908083, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2737172388335179, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.27703949796973054, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2633813215208564, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25802879291251385, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2604282022886674, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2631967515688446, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007224882565747388, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007761135206889885, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0075659214073182796, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008381415036099498, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008166167195185538, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008713342170063787, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009579629499496546, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011019741189981965, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.015103327874172562, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02014969256003685, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.037891107523179195, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07276743983934883, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10816378986409786, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1390846262184254, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.15394784128257794, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1769118318233297, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19248979675117073, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.19402716530930722, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.203122480077745, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2096074703711035, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21610306062619541, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.21631771878171993, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21903415917892424, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.21885098469712064, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22091555287066603, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21855615212229154, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22555361030315313, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21720161116804512, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21377466365653364, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2224069448709695, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2322148838239193, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22801050427752143, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.22682437830164096, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.22801798661417083, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21715464465025136, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22827552283128363, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.22320143109630478, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2183340563386973, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21546765001887677, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.22379304063775732, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21879903200569584, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2013444256846512, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18918876952364297, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19815329822184394, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19289497886308457, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.1779494190216067, "validation/loss_best": 2.368727207183838, "validation/acc_best": 0.2862679955703212, "validation/f1_best": 0.21610306062619541} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.3750453114509584, "train/grad": 0.18881547920405864, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12372314453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122969970703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12160400390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.120313720703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.118941650390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.116976318359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.114478759765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11121826171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1047265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.08847412109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.031826171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.837841033935547, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6942909240722654, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5704071807861326, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4870097732543943, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.423347396850586, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3618850898742676, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2983558273315428, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2369057750701904, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1871387481689455, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1301670551300047, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0793195295333864, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0276757287979126, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9815330481529236, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9370209503173828, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8993761217594147, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8653766101598739, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8449498581886292, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.809008942246437, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.785986332297325, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.770372132062912, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.7583535194396973, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.7595706814527512, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.752923658490181, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.755053043961525, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7599624091386794, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.77654680788517, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8004486930370331, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8342612999677659, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8764668452739715, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9290934920310974, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9713713997602462, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0378305715322496, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0813697671890257, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.1932497906684874, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008330517350696027, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008334971498697996, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008338461257517337, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008339825607836247, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008340958710759879, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008342220564372838, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008344113701023162, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008350730400998145, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008392164984252303, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008648169205989688, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010038943467661739, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.015180148603394627, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01903961616102606, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.021877110823988914, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.023466968862339854, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.024575025886297227, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025438004536554218, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02644794770516455, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.027606744803488254, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.028201820757240058, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.028731555826961994, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.029328697295859456, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.029961584582924843, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.030466054435819387, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.031154559440910817, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.031612304029986264, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03228583017364144, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03284907903522253, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03406671700067818, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03502057478763163, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03545970943756402, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.035731501886621116, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03573485555127263, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03606268684379756, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0362305495608598, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.036534274248406294, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03632561851292849, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.037117614233866336, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03689861332066357, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.036755728628486396, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03557845270261169, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.035242174938321116, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03586088486015797, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03572394189424813, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03540592532604933, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.120493173599243, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1199939250946045, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.119180202484131, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.118309259414673, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.117401599884033, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1159870624542236, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1140520572662354, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1111209392547607, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.104192018508911, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0825870037078857, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9982380867004395, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7866320610046387, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6592516899108887, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.550689220428467, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4790847301483154, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4342899322509766, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4021904468536377, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.375911235809326, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3623664379119873, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3611412048339844, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.362171173095703, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3670568466186523, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3791544437408447, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.405118703842163, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4291574954986572, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4456751346588135, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4644601345062256, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5038063526153564, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5171127319335938, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.521000862121582, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.548466920852661, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.583263635635376, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5531117916107178, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5717830657958984, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6491410732269287, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6436212062835693, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6968636512756348, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.696117877960205, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6731467247009277, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.629683017730713, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.59312105178833, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.609452247619629, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.581766366958618, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5351486206054688, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.517249822616577, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08157991878922112, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.11923218899963087, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17257290513104467, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2100406053894426, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23385012919896642, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2604282022886674, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27150239940937615, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2751937984496124, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28036175710594313, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28903654485049834, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28903654485049834, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28959025470653377, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.287375415282392, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28183831672203763, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2798080472499077, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2822074566260613, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27888519748984864, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.268733850129199, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26375046142488, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24640088593576967, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2497231450719823, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23440383905500184, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25452196382428943, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2558139534883721, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2526762643041713, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005898142613623786, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006192038216408481, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00631616239780011, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006460868888823689, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006579556203355926, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006851204247798251, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007122060820443887, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009592310260938227, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01237433941764385, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.019112514009452, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.046624967527828354, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09362542073229889, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12892176189854593, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.15257537431211832, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.17895325559207667, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19425940047608062, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2006424333497745, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20627322027085102, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21764867793607304, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2199713857657483, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22175724480949158, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22282098868985598, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22284744357501474, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2212522392512728, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22097680675900566, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22397084791811325, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22511434898391477, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21633636848403406, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21575453025081157, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22388891374377717, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22127285618325412, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21864666328975604, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2232697689955098, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.22433146664874512, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2206534505154696, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22139106365894393, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20823854741128608, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21349979202100644, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21312528698832978, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20912511651941412, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21497632733794714, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20745847398775438, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2135607607719248, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21671452802683425, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.20617457699632732, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 21, "lr_best": 0.00018299999999999998, "wd_best": 0.05, "train/loss_best": 2.0793195295333864, "validation/loss_best": 2.3670568466186523, "validation/acc_best": 0.2897748246585456, "validation/f1_best": 0.22282098868985598} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.333031951189041, "train/grad": 0.19128529697656632, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.121800537109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120906982421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.119464111328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11810302734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.116700439453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114364013671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.111575927734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.107425537109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.09783935546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0663812255859373, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9604296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7609381103515624, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.640760498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5305412673950194, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.451173267364502, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3931453895568846, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.33312611579895, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.26602650642395, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.202720866203308, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1531409311294554, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0972046709060668, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0457439970970155, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9918308460712433, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9446908807754517, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8971667736768723, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8576129651069642, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.820837315917015, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7923875343799591, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.746231455206871, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7188363516330718, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.6962079584598542, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6780643701553344, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6803284984827043, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.6750697201490403, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.676567969918251, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6683672189712524, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.695765728354454, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7216232025623321, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7611096048355102, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8091321861743928, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8697050458192825, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9174245816469193, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.961586812734604, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0110935765504836, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.1099148952960967, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00850819309707731, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008509523766115308, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008509899054188282, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008509218711405992, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0085076943365857, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008506751221138984, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008508657852653414, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00852137632202357, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00861783483531326, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00927895322907716, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01203088297508657, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01743954308796674, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.020655311299487947, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.023114427756518126, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.024632622571662068, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025457214191555978, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.026255047600716352, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02750746889039874, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.028661347031593322, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.029138209745287896, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.029585071010515093, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030121824750676752, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.030616509411484003, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.031066853310912846, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03181243730708957, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.032393995756283406, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.033121914826333525, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03347089556977153, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03437809920869768, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03508063247427344, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03546362000517547, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03584705994464457, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03599493610672653, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03661620675586164, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.036753026377409695, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03691445683129132, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.037396763879805804, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03735193675383926, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03729690253734588, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0366576786339283, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03540094239637256, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.035307274274528025, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03485491563566029, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03492612618021667, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.033474749084562064, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1205151081085205, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.120020627975464, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1191728115081787, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.118264675140381, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1172847747802734, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1156837940216064, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.113424062728882, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.109651803970337, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0990498065948486, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0570638179779053, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9252538681030273, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.730602502822876, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.623734951019287, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5271780490875244, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4659926891326904, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4320061206817627, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.405625581741333, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3772764205932617, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3624870777130127, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3569140434265137, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.357529401779175, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.364305257797241, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.378471612930298, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.401822805404663, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4194436073303223, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.428323984146118, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4433014392852783, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4925074577331543, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.537132978439331, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.551147937774658, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5930771827697754, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.612337827682495, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.603377342224121, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6316301822662354, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6191258430480957, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6016252040863037, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6365272998809814, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6357946395874023, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6760904788970947, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.789433002471924, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.747936964035034, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.794250011444092, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.850658655166626, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.768972396850586, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.703946828842163, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09782207456626062, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.14581026208933184, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18180140273163528, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.20930232558139536, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2351421188630491, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2748246585455888, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28645256552233295, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.29365079365079366, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2953119232189, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2912513842746401, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2929125138427464, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28755998523440385, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2853451458102621, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2858988556662975, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2833148763381321, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2722406792174234, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.271686969361388, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2513842746400886, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2558139534883721, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2412329272794389, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24603174603174602, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.25249169435215946, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005172407044572083, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0051755765199161426, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005564243845962672, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005374422637997072, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005837707140774677, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006493207350106292, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00866286118172191, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010910404890951528, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.015095850150310551, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03510533197431685, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06723398001443091, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10176468749339877, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12827521516233628, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.15260346464796407, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1788239779008953, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19350641572403982, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19978369986861086, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21213718538758689, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.21943393875003758, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22143325281940837, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2240639393632127, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22254365254975358, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2285793216455684, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22826985150766665, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22944215280185243, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2342807059726154, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.23562394337237125, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22609154100620057, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20931897227224247, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21703595439249243, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2175005045868156, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2198570988477387, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2104229325829402, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21554882114938026, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21642200225845773, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22487846770582165, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21373330134863522, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.22135369055674223, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21901403836759337, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20186202204653414, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20174551122096354, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18818880474950447, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19020027650435534, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19853641654485754, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19486011785988577, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.0972046709060668, "validation/loss_best": 2.357529401779175, "validation/acc_best": 0.2953119232189, "validation/f1_best": 0.2240639393632127} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.2996086478233337, "train/grad": 0.1927880731970072, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123428955078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.122625732421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12092529296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1193896484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.117757568359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.115233154296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.111903076171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.106617431640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0926904296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.037354736328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8967269897460937, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.712268981933594, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.605438537597656, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5000579833984373, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4256247901916503, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.372123260498047, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.312358703613281, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2439048290252686, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1829223823547363, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.133424265384674, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.076667354106903, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0253764462471007, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9720463943481445, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9220761203765868, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8720418345928191, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8292781281471253, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7874272918701173, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.7597841161489487, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7091471886634826, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6699731123447419, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.646465567946434, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6298353886604309, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6324050170183182, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.618476583957672, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6168760246038436, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6048455029726028, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6170791709423065, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6374664735794067, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.6726106733083725, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.726349354982376, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.790196053981781, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8345351660251616, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8849797719717025, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9401082819700242, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.06450192630291, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008479110309854149, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008480069746728986, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008480237659532576, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008480634638108313, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008480399022810161, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008482815511524678, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00848990581696853, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008519068986643105, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008713643334340304, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010020226896740496, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.013665882367640735, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.018709117542020978, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021491749407723547, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.023819443192332982, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.02521496091969311, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02593435558490455, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02679504983127117, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028211645781993866, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02922618357464671, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02960040689446032, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0299866147339344, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03050592384301126, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03101885298267007, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03152394833043218, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03222966525703669, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03279248921200633, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.033512326423078775, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03404633187688887, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.035240108203142884, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.035629775701090695, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.036261252500116824, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03674441762268543, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03676246955059469, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03707600767724216, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03710094777867198, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.037203543186187744, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03704444740898907, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03699815978296101, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0365332523547113, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.036276331869885325, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03476558064110577, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03453362636268139, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.034609874291345474, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03465745945461094, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.032675546631217, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.120394468307495, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119826555252075, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.118870973587036, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1178178787231445, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1166536808013916, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.114760398864746, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.111950397491455, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.106922149658203, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.091032028198242, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0208663940429688, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8649306297302246, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.687556266784668, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.590907096862793, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.500188112258911, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.446347713470459, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4181759357452393, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.395503520965576, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3727381229400635, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.36458683013916, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3641481399536133, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.366912364959717, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3757338523864746, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.38775634765625, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4093894958496094, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4330475330352783, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.453810930252075, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4715497493743896, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.505828857421875, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.551204204559326, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5594730377197266, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.573840856552124, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.603766918182373, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6171228885650635, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6346914768218994, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.64131498336792, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6115620136260986, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.636367082595825, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6426804065704346, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.624290943145752, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.615719795227051, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.594416618347168, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5388998985290527, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5363128185272217, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.534623384475708, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.584841012954712, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08084163898117387, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.11701734957548911, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.15873015873015872, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.19915097822074565, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22535991140642303, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24658545588778147, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2672572905131045, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2739018087855297, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2833148763381321, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28552971576227393, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.29198966408268734, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.29309708379475824, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2918050941306755, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.28903654485049834, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2842377260981912, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2783314876338132, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27648578811369506, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2739018087855297, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.266703580657069, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.257844222960502, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2703949796973053, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26836471022517533, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.27464008859357697, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2751937984496124, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.27464008859357697, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.26651901070505724, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2702104097452935, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.26891842008121075, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2576596530084902, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0059265058398106606, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005895307773613333, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006168437204910292, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006572627358036494, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006685519196864037, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008489728832482765, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00964267830128933, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01307339097102679, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02266477793166809, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05101671187478881, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07850968468626308, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.11959236211073897, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14405451672067437, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16527323418579173, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18868623385892638, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.19812644380101493, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21012757717116445, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21415669295214002, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2198798348471551, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22419360664951862, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22633373259361755, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2268025607228036, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22569071744266686, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22660156262496445, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22416051163130435, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2212355999724993, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22286858544306046, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.21840605507285185, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21205908955449213, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21675846660351916, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2197580556915997, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22072293243019458, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2137025273205615, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21538392751846366, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21532214546676953, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.222930097792314, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2118294084666824, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20707114067345045, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21464455628471404, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21621227443875743, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2172405853961136, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21269129051232472, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2121617263366097, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.20463712802298514, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1950322295214485, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.076667354106903, "validation/loss_best": 2.366912364959717, "validation/acc_best": 0.29309708379475824, "validation/f1_best": 0.22633373259361755} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.256561676263809, "train/grad": 0.19167964078485966, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1215625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120499267578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.118935546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1172021484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.115433349609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.112628173828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.108701171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.102314453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.08257568359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0003973388671876, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8462728881835937, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6739656066894533, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.573307113647461, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.468920364379883, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.395348606109619, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.341649875640869, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.280622386932373, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2115992069244386, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.148853464126587, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0996389865875242, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0425308322906495, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9905196475982665, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9364384508132935, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8873271441459656, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.836452374458313, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7899470055103301, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.744123987555504, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.710914937853813, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6551283240318297, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6068575102090836, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.577828089594841, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.556764485836029, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5547879147529602, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5350685709714889, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.531917644739151, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.5229004055261612, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5337088125944138, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5471318900585174, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.5823120892047882, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.6360818195343017, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.6982700103521347, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7426464086771012, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.7998615980148316, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.8418864691257477, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.9821898543834686, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008331053869333117, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008332080270629377, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008333287895657121, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00833450820762664, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00833583765430376, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008339335541240871, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008351071383804082, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00839641886530444, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008708024225197732, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010644255694933236, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.014563513626344502, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019176995395682753, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.021623332733288408, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02388279525563121, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025153394946828486, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.025849260101094843, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02679728385992348, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028298226753249764, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029263988472521305, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02962492370046675, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03003127527423203, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03053126163780689, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.031005966467782854, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03142961660400033, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03214305261150002, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.032677824180573224, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03343916383571923, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03394694324582815, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.035169344721361996, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03553074265830219, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0360667675640434, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.036547101642936466, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03621289388276636, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03647634083405137, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03646540990099311, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03683738106861711, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03713381296955049, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.036951729990541936, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03666282321326435, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03605207300744951, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03464812940917909, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03420506549999118, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03378731874749064, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03320115641690791, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0318657002877444, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.120020866394043, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.119415283203125, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1183152198791504, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1171538829803467, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1158523559570312, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.113739013671875, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1104538440704346, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.104334592819214, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0826375484466553, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9863739013671875, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8255908489227295, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6643173694610596, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.576303482055664, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4896116256713867, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4401190280914307, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.412872791290283, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3878064155578613, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.363797187805176, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.356382369995117, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.355485439300537, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3584256172180176, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3695671558380127, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3826465606689453, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4165761470794678, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4440627098083496, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4577910900115967, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.479649066925049, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.519768238067627, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5656137466430664, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5920445919036865, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6058034896850586, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6275296211242676, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6458582878112793, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.689582586288452, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6798408031463623, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6528847217559814, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7005767822265625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6632583141326904, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.640679121017456, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6379175186157227, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5804646015167236, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.566683769226074, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.577749252319336, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5423922538757324, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.437957763671875, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0754891103728313, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08748615725359911, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1286452565522333, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.16020671834625322, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20339608711701734, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22369878183831673, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24916943521594684, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2702104097452935, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27703949796973054, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.28146917681801403, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2868217054263566, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29328165374677, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.29198966408268734, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2943890734588409, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2914359542266519, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2912513842746401, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2851605758582503, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2851605758582503, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27703949796973054, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2526762643041713, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26651901070505724, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2576596530084902, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2552602436323367, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2500922849760059, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26559616094499816, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006353437348212911, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006562924328202145, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007342907752910786, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008066824233660586, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008651096814877338, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00946083914876331, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012048980699065221, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016115559791784605, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.027075176418581, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05669317712916083, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.08087953153386389, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12225948590632639, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1418582086868974, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.16979741043441196, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19381687085452337, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20289371823388305, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2096959743064224, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21774373249396595, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22765650735613133, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2256593032739188, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22837699857370386, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22826359029664398, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2326673574240452, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2307347807992253, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.23329749719790516, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22686385834286024, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.23121518736076474, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2273731746663524, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21276115491258296, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22023977383747514, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22217783143154599, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22069207884207317, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.22010639561512338, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2168263998501574, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.22365021761300904, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.23225613501961004, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.22055578579237123, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2233789774901769, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.22435667750117408, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2292732041498187, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2344438712656566, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22722935533784971, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.22595126266838836, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21978928662422184, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2315234001362101, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.0425308322906495, "validation/loss_best": 2.3584256172180176, "validation/acc_best": 0.2943890734588409, "validation/f1_best": 0.22837699857370386} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.2142641806602477, "train/grad": 0.19186579175293444, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.121502685546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120411376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.118619384765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.116917724609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.114945068359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.111983642578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10764892578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10009765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.07443603515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9700421142578124, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.814494934082031, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.653262939453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.554837951660156, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4489971923828127, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3763661193847656, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3214468002319335, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2570956325531006, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.187755994796753, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1245531320571898, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0743556690216063, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0165579652786256, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9643375039100648, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.907482659816742, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8553691291809082, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8030358958244324, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7529952359199523, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.7036223512887956, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.663536176085472, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.601737539768219, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5525795978307724, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5147320872545242, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4890755802392959, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4843425679206848, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.458136312365532, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.440577203631401, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.431067099571228, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.434807950258255, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.449130546450615, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4775346344709397, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.5238880020380021, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.5810431414842605, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6287423479557037, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6921048468351365, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.7393101799488067, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.8759295296669007, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008476514797657729, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008476673688273878, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00847675178432837, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008477140348404646, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008478328953497111, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008482317302841692, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008497595977969468, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008560789606999606, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009012120489496738, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01151119401678443, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015575738893821835, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019970820932649076, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.022270543882623315, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02446095290593803, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025555109325796365, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02617623785510659, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027112221429124474, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02858589413575828, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029455168712884186, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.029764742059633136, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.030125245777890088, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030582132879644633, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.031052033863961697, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03147237951867282, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03213117402978241, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03267670120112598, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03337882721796632, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03377212897874415, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.034879031339660284, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03524148495867849, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03571969042532146, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03603094775229693, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03605679363012314, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03660047757439315, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03687117271125317, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0369677425455302, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03681952291168272, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.036835259106010196, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03615525988861919, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.036013917764648795, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03443297938443721, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03440819320268929, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03411755275912583, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.033361663892865184, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03116252077743411, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1198244094848633, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1191701889038086, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1180338859558105, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1167938709259033, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.115421772003174, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.113124132156372, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.109485387802124, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1023178100585938, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.074937105178833, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9595792293548584, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7992732524871826, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6461377143859863, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.560839891433716, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4762868881225586, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4312448501586914, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.407317638397217, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3849260807037354, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.363067865371704, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.357365131378174, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.357398748397827, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.358243465423584, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3654556274414062, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3743367195129395, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4002745151519775, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4208486080169678, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.442112445831299, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.466150999069214, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.508814573287964, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.55352520942688, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5904648303985596, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6015725135803223, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.627758741378784, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.637101650238037, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6774396896362305, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7106807231903076, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6965723037719727, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7646758556365967, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7572426795959473, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7479639053344727, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.772916793823242, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.683960437774658, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.634646415710449, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6135928630828857, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5644800662994385, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.542433023452759, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07567368032484312, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09210040605389443, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.13824289405684753, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.16961978589885568, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2070874861572536, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23181985972683647, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2748246585455888, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27851605758582504, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.28349944629014395, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2912513842746401, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2956810631229236, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.29198966408268734, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2956810631229236, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2943890734588409, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.29309708379475824, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2886674049464747, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2884828349944629, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2838685861941676, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2809154669619786, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27445551864156514, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26596530084902176, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.257844222960502, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2563676633444075, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2602436323366556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2617201919527501, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.262827611664821, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.26688815060908083, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2739018087855297, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006202814724375299, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00630636154446218, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006899006293868754, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0072215951864818785, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00838739473833753, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009647321582463167, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012630072224354522, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01664667804045684, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.032104554744362405, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06301853298981154, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09017836265602924, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12618195230568882, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.14933091697254072, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1773930027765568, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19608815997374054, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20367104125353727, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20850926319978755, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21859388262380405, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2247032904624946, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2205693337497305, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22862676216811104, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2286895150118391, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.23159292959395553, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2309345092558582, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.23365065546361055, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2323943001297251, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.23373021091886628, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.23007577338502336, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21491190851043704, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21981138454346916, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2289232733004971, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22487606690051098, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.22206938003398188, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21986927888166083, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.22128377893361698, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22751925249443183, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21287275967743305, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21357627587477948, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2178716256870182, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2156409603127012, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2128918053423999, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21228502070174338, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21086062096604316, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21058281153284944, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2165077173705482, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 18, "lr_best": 0.00011399999999999999, "wd_best": 0.05, "train/loss_best": 2.1245531320571898, "validation/loss_best": 2.357365131378174, "validation/acc_best": 0.2956810631229236, "validation/f1_best": 0.2247032904624946} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.194193172454834, "train/grad": 0.191048993319273, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12284423828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1218701171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.120185546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.118238525390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.116396484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.11322021484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.108768310546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.100382080078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.070291748046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.95381103515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8014508056640626, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.648682632446289, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.55592041015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4562585830688475, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3886181259155275, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3362266921997072, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2724155235290526, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.2012345027923583, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1369430303573607, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0855572748184206, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.027688133716583, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9735385584831238, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9159040594100951, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8626338994503022, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8070660996437073, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7521225249767303, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.696393699645996, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6570958149433137, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5891971695423126, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5284628927707673, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4872053050994873, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4591948473453522, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4435440093278884, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.412850878238678, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3848509174585342, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3570358407497407, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.3557152438163758, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.362920958995819, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3866198754310608, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4307124412059784, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.5049475157260894, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5482696294784546, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6052431374788285, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.6474626994132995, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.8019761162996293, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00845205398509279, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00845240110065788, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008452802025713026, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008453354893717915, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0084546417160891, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008459752246271818, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008478419112507254, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008557618868071586, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009128826942760498, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012001796420663595, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016114476937800645, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020295516448095442, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02246670762076974, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02465164616703987, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025740948924794792, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026405319944024085, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027431577192619443, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028916869293898344, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0297448920737952, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.030024006944149733, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.030349126392975448, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030804976634681226, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.031271888203918935, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03172315356321633, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.032432480957359074, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03292536324821413, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03354151687584817, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03398021725937724, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03505137322470546, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0355491029843688, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0359943379368633, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03621973071247339, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03608538374304771, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03623473424464464, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03602073487825692, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.035933981547132135, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.035660531055182215, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03582924612797797, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03545320495963097, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.035193832796067, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.034440892320126294, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0339042888302356, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.033391372375190256, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03270090293139219, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03000377930700779, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119784355163574, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1191017627716064, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1179635524749756, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1167054176330566, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1152937412261963, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1129212379455566, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1090567111968994, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.101168394088745, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.069437265396118, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9429218769073486, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.784918785095215, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6379706859588623, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5556654930114746, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.473839282989502, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4316816329956055, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.409177541732788, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.387969970703125, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3681259155273438, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3666951656341553, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3701531887054443, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.375380516052246, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3875229358673096, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3980607986450195, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4281911849975586, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.454594135284424, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4761605262756348, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5062334537506104, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5564115047454834, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.612668514251709, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6515872478485107, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6656296253204346, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6931803226470947, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.718780994415283, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.769019842147827, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.794532299041748, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7950479984283447, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8428902626037598, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.857830762863159, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.846252679824829, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7917258739471436, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.772674798965454, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.724555730819702, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7569923400878906, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7280211448669434, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5737316608428955, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07585825027685493, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09357696566998892, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1421188630490956, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17275747508305647, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.20967146548541898, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23163528977482467, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2571059431524548, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.27464008859357697, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2783314876338132, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2836840162421558, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2901439645625692, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29069767441860467, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2918050941306755, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.29254337393872276, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2884828349944629, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2901439645625692, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2853451458102621, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2827611664820967, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27870062753783686, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26799557032115173, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25544481358434845, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25507567368032485, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2543373938722776, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2526762643041713, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26965669988925806, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0062059865297921695, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00630796977771905, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006640520297813906, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007879471583844081, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008462163446873916, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01011876454449857, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013035892434320961, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01774629473501893, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03320661459654458, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06527003563040826, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09387584124403421, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.1286811895554619, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1509989122642266, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1771419004855833, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19964662272013745, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20574997928548933, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.21177580261497767, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.22133281392014795, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22382847697364627, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2238975252187377, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22664284355328346, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2256367664752639, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2287250033254249, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22796770115099677, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2272766985679121, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22598625633823274, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.22639549954549665, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22054594661519134, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2060681857327712, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2165854963361494, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22015847697396987, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21563261315589577, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21385095571424337, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21221981462370967, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21498645912542522, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.21649062454990597, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20959593853272454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20535389535633805, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21234197552129133, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.22414353886475755, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22034350392472998, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22249073711054032, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2110795555827106, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21768626062390517, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.23016975313952767, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.027688133716583, "validation/loss_best": 2.375380516052246, "validation/acc_best": 0.29254337393872276, "validation/f1_best": 0.22664284355328346} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.1581492227315904, "train/grad": 0.18826903589069843, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123897705078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1229150390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.121212158203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11928955078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.11732177734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.114193115234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10938720703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10058349609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0671563720703126, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9436456298828126, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7902879333496093, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.636892852783203, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.543736343383789, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4440870094299316, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.376293830871582, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3226720237731935, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.257480430603027, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1853054904937745, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1201358318328856, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.06831148147583, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0094191002845765, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9520341181755065, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8926879787445068, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8347281503677368, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7761804211139678, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7198570883274078, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6601843625307082, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6162132972478866, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5452087283134461, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4807062035799026, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.435633161664009, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3959335160255433, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3773027497529984, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.3408519726991655, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.3103149843215942, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2808371961116791, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2766326022148133, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2846596598625184, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2952897787094115, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.325369079709053, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3896346122026444, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.4291995814442635, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4951688688993454, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.541724527478218, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.7112369775772094, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008315358425024897, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008315483680926264, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008314435528591275, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008313817363232374, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008314581725280733, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008319021021015942, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008338954218197614, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008426309048663825, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0090679907402955, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012102928296662867, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016193101154640316, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020284474175423384, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.02244895136915147, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.024588971901685, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025616470063105225, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026274623079225422, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027307621287181973, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028801437290385364, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02960182199254632, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0298515809699893, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.030160776674747466, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03060800166800618, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.031089021172374488, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.031492510372772814, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03212181265465915, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03261241003870964, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0332801119890064, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03367351865395904, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.034577890262007714, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03495347417891025, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.035200729547068474, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03536238355562091, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03512258158065379, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0352505577262491, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.035335376234725116, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03522050412371755, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03511908343061805, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.035076366178691386, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03469191749580205, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.034530507028102876, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.033349729357287285, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.032997251143679025, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03285821022465825, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03229337869212032, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.029829018879681826, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119694232940674, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1190202236175537, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117825984954834, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1165406703948975, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1150991916656494, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.112630605697632, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1085996627807617, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.100189685821533, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0654211044311523, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.932380437850952, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7756707668304443, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.632628917694092, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.552443504333496, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4733245372772217, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4338648319244385, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.412761926651001, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3916282653808594, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.37141752243042, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3681910037994385, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.369386911392212, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3715977668762207, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3822367191314697, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3912923336029053, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4210703372955322, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.445208787918091, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.464733600616455, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4946742057800293, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5345890522003174, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.580420732498169, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.599285364151001, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6125974655151367, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6449368000030518, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6754698753356934, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7384884357452393, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7690622806549072, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7483274936676025, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.817702293395996, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8133513927459717, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8142778873443604, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8435325622558594, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.794196128845215, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7671775817871094, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7705116271972656, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7279398441314697, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5563883781433105, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09579180509413067, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14396456256921372, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17349575489110372, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21077888519748986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2320044296788483, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2757475083056478, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27722406792174237, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2822074566260613, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2884828349944629, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29051310446659284, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2918050941306755, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.29549649317091176, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2901439645625692, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2886674049464747, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2870062753783684, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2866371354743448, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28054632705795496, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27722406792174237, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26836471022517533, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27260981912144705, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2530454042081949, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25359911406423036, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2563676633444075, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24916943521594684, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.25655223329641935, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.25839793281653745, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0061981349627160875, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00630636154446218, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00691008561416653, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007847311143774986, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009048046965683466, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010311845684267835, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013602465072583616, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017485618569248303, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03406819131288553, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06616829685630572, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09532607837737804, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.12870803491420116, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15090650555601373, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.17990583622781778, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.20028849811178293, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20426258113618845, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20835755602162745, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2182532367359142, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2227067482312309, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2233277168330204, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22801099593171667, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22582804957750632, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22666693856806866, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.23123260464539055, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.23302128580135392, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2282472955453847, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.23008566574989417, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22254913731838646, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2133705540255261, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22689231373694518, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.23095812131508894, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.23046066669508444, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2228661948434448, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2200258703741452, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2253992401895447, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.228413297944884, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2192287665649714, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21756020374970064, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2208460952286988, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.22100645423449075, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22314885168062912, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2211357452522714, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21281466474309627, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21863768064811814, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.21558975605540187, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.0094191002845765, "validation/loss_best": 2.3715977668762207, "validation/acc_best": 0.29549649317091176, "validation/f1_best": 0.22801099593171667} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.1349106192588807, "train/grad": 0.18513906091451646, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.122198486328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.121141357421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.119287109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11728759765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.115145263671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.111817626953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.106728515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.097271728515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0615179443359377, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.933579406738281, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7807115173339843, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6319703674316406, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.541633377075195, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4420769119262697, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.374188995361328, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3200292587280273, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.254225425720215, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.181380023956299, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1161867904663088, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.062962460517883, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0025659561157227, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9459696197509766, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8846499919891357, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8263779735565187, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7690204930305482, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7082928824424743, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6495614993572234, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.604168108701706, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5255209136009216, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4563324737548828, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4066110914945602, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3683569741249084, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.352062425017357, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.3071185767650604, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.271795152425766, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.228071798980236, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.209072449505329, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.2028812590241431, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.21949049949646, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2483651614189148, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.312407649755478, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3443804913759232, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4008893698453904, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.4449163281917572, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.6229027408361434, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008385099491570146, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008384915920905768, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00838416358223185, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008384396089240909, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008385099184233696, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008391278244089336, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008414267201442272, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00851112486794591, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009211170775815845, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012373857898637652, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016500420509837566, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020562790730036796, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.022673302451148628, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02476029940880835, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025758100925013423, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02641253468580544, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02744956811890006, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028934957832098006, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.029716768246144058, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.029934856053441764, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.030204530442133545, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030590325966477393, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.030943499645218253, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03125628161244094, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03185991330072284, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03224544692784548, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03281070638448, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.033185344142839315, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03410701776854694, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.034447973230853676, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0346190204937011, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03477657497860491, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.034393726224079726, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03448654737323523, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03436796032823622, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03431878941133618, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03375403775833547, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.033749095955863596, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03334652485325933, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.032963838586583735, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03223391997627914, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.032084136670455336, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03158114699646831, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.031051838556304574, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.028712346358224748, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1196210384368896, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1189301013946533, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117729663848877, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.116425037384033, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1149563789367676, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.112438440322876, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.108266592025757, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0995736122131348, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0632081031799316, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9269819259643555, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7707149982452393, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6286089420318604, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.548281669616699, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4683685302734375, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.428589344024658, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4068603515625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3856635093688965, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3663346767425537, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.364718437194824, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3672432899475098, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3709723949432373, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.382023572921753, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3937041759490967, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.423316478729248, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.452153205871582, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4748151302337646, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5082356929779053, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.551804304122925, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6008920669555664, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6261770725250244, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6430511474609375, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.671828031539917, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7058653831481934, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.789332866668701, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.813261032104492, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.81772780418396, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8946125507354736, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8893377780914307, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.887035846710205, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9104888439178467, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8617324829101562, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8161776065826416, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8405921459198, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8114476203918457, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6699776649475098, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07733480989294943, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09579180509413067, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14414913252122555, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1744186046511628, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21225544481358435, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23458840900701367, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2633813215208564, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.27500922849760057, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2792543373938723, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2825765965300849, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28959025470653377, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.28940568475452194, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28959025470653377, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.29217423403469917, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29217423403469917, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2901439645625692, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2857142857142857, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2847914359542267, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27648578811369506, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25193798449612403, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2513842746400886, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25489110372831303, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24492432631967515, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2454780361757106, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2552602436323367, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006190539155336609, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00644418901660281, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0070093935286527805, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008069036066078599, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00887148849191496, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010697996815431293, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013969841516442356, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.018114036886267542, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.033249491454305724, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06641886121609868, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09638182918435449, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13025844645104287, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15293177069880173, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18165204317146633, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1992635670457539, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20505421297553586, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20984814883756162, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21897610152140035, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22202742817446705, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.22005947898339154, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22609777774749285, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2279738055308468, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22759029720172327, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.22928788597785701, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.22959062624228951, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2238122529238348, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2268949642786935, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22022340161094625, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2051789222642771, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2194169488046386, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22511443326540803, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22570570196993645, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2207558402776241, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21169990424931986, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21788879776011405, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22007159573842636, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20913726524885345, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2041250658323991, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21049925864217842, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21593543069740595, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21810523167581417, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2211282569019574, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.208338392088303, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2077036457247919, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.21014370310568467, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 2.0025659561157227, "validation/loss_best": 2.3709723949432373, "validation/acc_best": 0.29217423403469917, "validation/f1_best": 0.22609777774749285} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.1089651811122896, "train/grad": 0.1814025964587927, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.119283447265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.118175048828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.116312255859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.114259033203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1121435546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10876220703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.103428955078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.093507080078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0550531005859374, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9195510864257814, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.763486328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.614790191650391, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5252003479003906, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4273273086547853, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3607685279846193, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3066438674926757, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2389786529541014, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.164465932846069, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0968511724472045, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.0419371128082275, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9798439359664917, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9223373222351074, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.861054379940033, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8026513135433198, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7427492070198058, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.682626375555992, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6226061242818832, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5766417974233626, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5022127068042754, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4387968921661376, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3824029397964477, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.334987285733223, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3152819877862931, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2646810692548751, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2205373227596283, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.1905436170101167, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.171561477780342, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1723964992165565, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1658035457134246, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1920576569437982, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2420761740207673, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2699535876512527, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3173705366253854, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.353433746099472, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.5262630480527877, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008227337102871388, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008227214289363474, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008226884070318193, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008227590420283377, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008228430931922048, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008235234471503644, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00825859238160774, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008357046185992659, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009072711451444775, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012282344321720302, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016411158763803543, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020407998035661876, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.022492543775588274, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.024582729572430254, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025576920704916118, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02621881792321801, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.027240333268418907, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.028705445658415554, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02949566386640072, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.029755532778799533, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03004794454202056, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030447244737297298, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.030809401432052255, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.031167965484783053, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.031727330079302195, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03204544302076101, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.032568900091573594, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03294869381003082, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.033775267172604796, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.033887569699436425, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03398368489928544, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03405673417262733, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.033689939714968205, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03366634781472385, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03336444223299623, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0331156618706882, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.032805894101038575, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03257787462323904, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.032036627642810345, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.031556129073724154, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030883039170876144, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.030551392287015915, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03014720505103469, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.029567867051810026, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.027633051658049225, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119603157043457, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1189229488372803, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1177141666412354, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1164066791534424, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1149561405181885, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1124067306518555, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1082112789154053, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.099428415298462, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0624775886535645, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.925166130065918, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7692558765411377, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6279847621917725, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.547971487045288, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4684622287750244, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.429054021835327, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4076664447784424, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.386270761489868, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3665733337402344, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3641769886016846, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3657383918762207, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3684511184692383, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.378297805786133, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.388211965560913, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.416245460510254, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4448065757751465, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.467113733291626, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.498136520385742, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5391087532043457, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.590559959411621, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.617044448852539, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6321940422058105, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6651318073272705, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.696770668029785, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.772580862045288, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7997379302978516, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8054141998291016, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.874321222305298, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8763742446899414, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8754422664642334, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8990752696990967, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.853229284286499, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.816253662109375, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8520469665527344, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8154056072235107, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.673496961593628, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07733480989294943, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09579180509413067, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14451827242524917, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17386489479512734, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21262458471760798, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23440383905500184, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2648578811369509, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.27445551864156514, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27870062753783686, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.28313030638612036, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.290328534514581, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2897748246585456, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2912513842746401, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.29494278331487633, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.29217423403469917, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2912513842746401, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2877445551864157, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2866371354743448, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2812846068660022, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27888519748984864, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26375046142488, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25802879291251385, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25341454411221853, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25655223329641935, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25378368401624213, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2467700258397933, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24732373569582872, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2552602436323367, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006193547268597978, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006305654689026514, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00690301475559798, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007954958361324906, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008924748766530525, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010508194911445516, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01390724442012304, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.018026168341713632, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.033911265633130475, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06636613337517745, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09598618712789268, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13101545721531957, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15278484620887564, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18291430088281813, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19885213329331738, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20448637739296652, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2097750450240529, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21969014337291326, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22243432475487604, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2217042005537699, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2281138098665909, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.22788251632746578, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22912660663043657, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2306623525137892, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.23232164587057302, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22892368214674153, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.23121578465303805, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22395605485602402, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20757719622784165, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22185221607098093, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2253384173808166, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22676400970176683, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2240176047442334, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21800599128221032, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.22289695301552895, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22444926767981718, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21349926599380184, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21194894482696225, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2175096734481429, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.22346710034626005, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22633445748498857, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22363601311795456, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21379417144171906, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21271599146111683, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.21608692573156416, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 1.9798439359664917, "validation/loss_best": 2.3684511184692383, "validation/acc_best": 0.29494278331487633, "validation/f1_best": 0.2281138098665909} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.1092126685380936, "train/grad": 0.18218766644597054, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1204833984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.119351806640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.117562255859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.115494384765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.113438720703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.110048828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1049267578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.094967041015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.056719970703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9226333618164064, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7707510375976563, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6238099670410158, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.532857131958008, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.43403564453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3670221900939943, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.313451452255249, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.248034553527832, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1762357711791993, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1109391403198243, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.057942018508911, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9958455562591553, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9371929955482483, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8763735723495483, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.816070510149002, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.755760122537613, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6959433710575105, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6334665673971176, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5892364943027497, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5123726946115494, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.441276903152466, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3797360152006148, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3409907603263855, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3103788423538207, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2633949601650238, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2163573282957076, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.182781073153019, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.158756037056446, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1462495160102844, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1465211859345437, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1696849983930588, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2239563381671905, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2451125943660737, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2890948164463043, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3320789456367492, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.494585210084915, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008397247123066337, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008397344970144332, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008396588012110441, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008396553420461715, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008397336609195918, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008403951963409782, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008426621803082526, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008526222810614855, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009250696515664458, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012469803020358085, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01657544494140893, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.020628898637369275, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.022784252045676114, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.02495366061106324, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.025964770633727312, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.026606027921661734, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02763332823291421, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02909513594582677, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02986985454335809, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.030078384773805738, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03036416297778487, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.030739698708057404, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.031112596411257982, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.031386556094512345, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.031976385368034245, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03234612108208239, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03286922755651176, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03313905474729836, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03388513896614313, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03407700231298804, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03422907075844705, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.034239471210166815, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03383247216232121, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03371612833812833, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03340023219585419, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03312882087193429, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03277272464707494, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.032452120343223215, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.032016866113990544, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03137098503299057, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03051170689985156, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.030229228409007193, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02980239565484226, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.029227595757693053, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.027322066240012644, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.119601249694824, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.118924379348755, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.117708683013916, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1163997650146484, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1149370670318604, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.112396001815796, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.108192205429077, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.099385976791382, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0623371601104736, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.924912214279175, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.769010066986084, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.627751350402832, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.547675132751465, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.468266725540161, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.428799867630005, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4073171615600586, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.385806083679199, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3659229278564453, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3634684085845947, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.364825487136841, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3674747943878174, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3776021003723145, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3876101970672607, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.416137933731079, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.444687604904175, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4666318893432617, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4979617595672607, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5405845642089844, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.591782569885254, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.618532419204712, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.633568286895752, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6660618782043457, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6948628425598145, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7698185443878174, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.796795606613159, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7960731983184814, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8668136596679688, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.871248722076416, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8699874877929688, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.893049955368042, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.851452589035034, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8205647468566895, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.850156307220459, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8143088817596436, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.671440601348877, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07733480989294943, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09616094499815431, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.14433370247323735, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17404946474713917, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21280915466961978, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23477297895902546, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.26448874123292726, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.27556293835363604, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2783314876338132, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.28294573643410853, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.29088224437061644, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29051310446659284, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.290328534514581, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.29494278331487633, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2927279438907346, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2914359542266519, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2877445551864157, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2853451458102621, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.28054632705795496, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27759320782576596, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2698412698412698, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.257844222960502, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25249169435215946, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2572905131044666, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25359911406423036, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24880029531192321, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.25839793281653745, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006189050027014892, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006464631836687742, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006893748306697531, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00794729783732829, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00888501759827118, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01047676954596244, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01396277496822712, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.018067388660614123, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0341215902176766, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06626801696687244, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09623813288131328, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.13107314767027303, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.15305176690316824, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18265587829804375, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.19973572493125882, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.20442794027931152, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20970438607176614, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.21994439563574852, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22280781980862466, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2203459806023256, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22846606487678567, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2287051312680226, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.22935251775111962, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.23172255245875997, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.23102926119274644, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.22875052031276585, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.23090781615555298, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.22537733456104125, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20851318699694601, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.22279394491477297, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.22571551859489816, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.22734749380462269, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2239562846571619, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21764648035871, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.22404819490809358, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22556980818410452, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21497923887742276, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21225567955985283, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.21731671053102938, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2198241611778113, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.22616473784508262, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.22287688056126806, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21452639124037995, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.214540129892781, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.21383603972386256, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 20, "lr_best": 0.000156, "wd_best": 0.05, "train/loss_best": 1.9958455562591553, "validation/loss_best": 2.3674747943878174, "validation/acc_best": 0.29494278331487633, "validation/f1_best": 0.22846606487678567} diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_log.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..6ba2f7e20118b7fc3ee44193b975254bc479d252 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 12, "eval/id_best": 46, "eval/lr_best": 0.010799999999999999, "eval/wd_best": 0.05, "eval/train/loss": 2.9561731815338135, "eval/train/acc": 0.13442330741571654, "eval/train/acc_std": 0.0016399786261972085, "eval/train/f1": 0.07360312856380823, "eval/train/f1_std": 0.0011894892872814158, "eval/validation/loss": 3.050022840499878, "eval/validation/acc": 0.11517165005537099, "eval/validation/acc_std": 0.0037073851707885345, "eval/validation/f1": 0.0568927381373181, "eval/validation/f1_std": 0.0025098501705171287, "eval/test/loss": 3.0346412658691406, "eval/test/acc": 0.11706864564007421, "eval/test/acc_std": 0.0036309939339685808, "eval/test/f1": 0.05047890849878861, "eval/test/f1_std": 0.0020235796960419747, "eval/testid/loss": 3.0452094078063965, "eval/testid/acc": 0.10776942355889724, "eval/testid/acc_std": 0.0037217302058737472, "eval/testid/f1": 0.05534874186236579, "eval/testid/f1_std": 0.0025537881427831616} diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..57fbb43b19ee28ec3fd4ed525fae746a05afc6c1 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 48, "eval/last/lr_best": 0.015, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.909435749053955, "eval/last/train/acc": 0.15160269215403055, "eval/last/train/acc_std": 0.0017969187787028554, "eval/last/train/f1": 0.09924394846514734, "eval/last/train/f1_std": 0.0015441521680767947, "eval/last/validation/loss": 3.0152688026428223, "eval/last/validation/acc": 0.11351052048726468, "eval/last/validation/acc_std": 0.0035745682190531473, "eval/last/validation/f1": 0.06564991315905983, "eval/last/validation/f1_std": 0.002770352672686336, "eval/last/test/loss": 3.0052855014801025, "eval/last/test/acc": 0.12393320964749537, "eval/last/test/acc_std": 0.0037463069176298263, "eval/last/test/f1": 0.05954316439826204, "eval/last/test/f1_std": 0.0025967099322259223, "eval/last/testid/loss": 3.0140411853790283, "eval/last/testid/acc": 0.11490264121843069, "eval/last/testid/acc_std": 0.003935210204753251, "eval/last/testid/f1": 0.07020355932941731, "eval/last/testid/f1_std": 0.0029887924236395194} diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table.csv b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..a647fb31ca460336fff2a2c5565705ec09900f6d --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",train,2.9561731815338135,0.13442330741571654,0.0016399786261972085,0.07360312856380823,0.0011894892872814158 +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",validation,3.050022840499878,0.11517165005537099,0.0037073851707885345,0.0568927381373181,0.0025098501705171287 +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",test,3.0346412658691406,0.11706864564007421,0.0036309939339685808,0.05047890849878861,0.0020235796960419747 +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",testid,3.0452094078063965,0.10776942355889724,0.0037217302058737472,0.05534874186236579,0.0025537881427831616 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..a647fb31ca460336fff2a2c5565705ec09900f6d --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",train,2.9561731815338135,0.13442330741571654,0.0016399786261972085,0.07360312856380823,0.0011894892872814158 +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",validation,3.050022840499878,0.11517165005537099,0.0037073851707885345,0.0568927381373181,0.0025098501705171287 +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",test,3.0346412658691406,0.11706864564007421,0.0036309939339685808,0.05047890849878861,0.0020235796960419747 +flat_mae,patch,linear,nsd_cococlip,best,12,0.010799999999999999,0.05,46,"[36, 1.0]",testid,3.0452094078063965,0.10776942355889724,0.0037217302058737472,0.05534874186236579,0.0025537881427831616 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..b3bf1babc632fb2dadb3459226c6ee66b9632f72 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",train,2.909435749053955,0.15160269215403055,0.0017969187787028554,0.09924394846514734,0.0015441521680767947 +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",validation,3.0152688026428223,0.11351052048726468,0.0035745682190531473,0.06564991315905983,0.002770352672686336 +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",test,3.0052855014801025,0.12393320964749537,0.0037463069176298263,0.05954316439826204,0.0025967099322259223 +flat_mae,patch,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",testid,3.0140411853790283,0.11490264121843069,0.003935210204753251,0.07020355932941731,0.0029887924236395194 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/log.txt b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b83b72bac9c5193527f1acab89054dbfe92fdf92 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/log.txt @@ -0,0 +1,956 @@ +fMRI foundation model probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 23:07:30 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (nsd_cococlip patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:18 lr: nan time: 3.6457 data: 3.2831 max mem: 3910 +train: [0] [ 20/400] eta: 0:03:08 lr: 0.000003 loss: 3.1782 (3.1830) grad: 0.0810 (0.0840) time: 0.3384 data: 0.0038 max mem: 3953 +train: [0] [ 40/400] eta: 0:02:32 lr: 0.000006 loss: 3.1785 (3.1807) grad: 0.0810 (0.0804) time: 0.3462 data: 0.0040 max mem: 3953 +train: [0] [ 60/400] eta: 0:02:16 lr: 0.000009 loss: 3.1779 (3.1803) grad: 0.0757 (0.0780) time: 0.3562 data: 0.0043 max mem: 3953 +train: [0] [ 80/400] eta: 0:02:04 lr: 0.000012 loss: 3.1742 (3.1780) grad: 0.0705 (0.0761) time: 0.3488 data: 0.0037 max mem: 3953 +train: [0] [100/400] eta: 0:01:54 lr: 0.000015 loss: 3.1697 (3.1763) grad: 0.0694 (0.0752) time: 0.3625 data: 0.0042 max mem: 3953 +train: [0] [120/400] eta: 0:01:45 lr: 0.000018 loss: 3.1685 (3.1761) grad: 0.0710 (0.0749) time: 0.3526 data: 0.0042 max mem: 3953 +train: [0] [140/400] eta: 0:01:37 lr: 0.000021 loss: 3.1655 (3.1742) grad: 0.0749 (0.0755) time: 0.3591 data: 0.0045 max mem: 3953 +train: [0] [160/400] eta: 0:01:29 lr: 0.000024 loss: 3.1645 (3.1732) grad: 0.0744 (0.0753) time: 0.3451 data: 0.0042 max mem: 3953 +train: [0] [180/400] eta: 0:01:21 lr: 0.000027 loss: 3.1656 (3.1722) grad: 0.0741 (0.0750) time: 0.3533 data: 0.0043 max mem: 3953 +train: [0] [200/400] eta: 0:01:13 lr: 0.000030 loss: 3.1652 (3.1713) grad: 0.0722 (0.0744) time: 0.3402 data: 0.0042 max mem: 3953 +train: [0] [220/400] eta: 0:01:05 lr: 0.000033 loss: 3.1624 (3.1702) grad: 0.0720 (0.0741) time: 0.3415 data: 0.0042 max mem: 3953 +train: [0] [240/400] eta: 0:00:58 lr: 0.000036 loss: 3.1596 (3.1695) grad: 0.0709 (0.0739) time: 0.3472 data: 0.0042 max mem: 3953 +train: [0] [260/400] eta: 0:00:50 lr: 0.000039 loss: 3.1591 (3.1686) grad: 0.0694 (0.0736) time: 0.3532 data: 0.0041 max mem: 3953 +train: [0] [280/400] eta: 0:00:43 lr: 0.000042 loss: 3.1518 (3.1674) grad: 0.0681 (0.0734) time: 0.3482 data: 0.0041 max mem: 3953 +train: [0] [300/400] eta: 0:00:36 lr: 0.000045 loss: 3.1467 (3.1663) grad: 0.0737 (0.0736) time: 0.3480 data: 0.0040 max mem: 3953 +train: [0] [320/400] eta: 0:00:28 lr: 0.000048 loss: 3.1467 (3.1651) grad: 0.0745 (0.0735) time: 0.3622 data: 0.0044 max mem: 3953 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 3.1551 (3.1652) grad: 0.0732 (0.0733) time: 0.3684 data: 0.0041 max mem: 3953 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 3.1552 (3.1647) grad: 0.0694 (0.0732) time: 0.3442 data: 0.0041 max mem: 3953 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 3.1495 (3.1637) grad: 0.0698 (0.0732) time: 0.3429 data: 0.0042 max mem: 3953 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1498 (3.1630) grad: 0.0710 (0.0734) time: 0.3518 data: 0.0040 max mem: 3953 +train: [0] Total time: 0:02:23 (0.3590 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1498 (3.1630) grad: 0.0710 (0.0734) +eval (validation): [0] [ 0/85] eta: 0:04:53 time: 3.4578 data: 3.1789 max mem: 3953 +eval (validation): [0] [20/85] eta: 0:00:32 time: 0.3464 data: 0.0139 max mem: 3953 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3369 data: 0.0083 max mem: 3953 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3387 data: 0.0031 max mem: 3953 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3192 data: 0.0041 max mem: 3953 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3135 data: 0.0039 max mem: 3953 +eval (validation): [0] Total time: 0:00:31 (0.3744 s / it) +cv: [0] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 3.123 acc: 0.069 f1: 0.010 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:01 lr: nan time: 3.3034 data: 3.0143 max mem: 3953 +train: [1] [ 20/400] eta: 0:03:09 lr: 0.000063 loss: 3.1469 (3.1488) grad: 0.0683 (0.0684) time: 0.3591 data: 0.0037 max mem: 3953 +train: [1] [ 40/400] eta: 0:02:32 lr: 0.000066 loss: 3.1515 (3.1520) grad: 0.0683 (0.0678) time: 0.3424 data: 0.0041 max mem: 3953 +train: [1] [ 60/400] eta: 0:02:16 lr: 0.000069 loss: 3.1531 (3.1524) grad: 0.0712 (0.0690) time: 0.3566 data: 0.0042 max mem: 3953 +train: [1] [ 80/400] eta: 0:02:04 lr: 0.000072 loss: 3.1431 (3.1475) grad: 0.0714 (0.0704) time: 0.3520 data: 0.0044 max mem: 3953 +train: [1] [100/400] eta: 0:01:54 lr: 0.000075 loss: 3.1420 (3.1490) grad: 0.0697 (0.0701) time: 0.3598 data: 0.0041 max mem: 3953 +train: [1] [120/400] eta: 0:01:45 lr: 0.000078 loss: 3.1429 (3.1465) grad: 0.0676 (0.0694) time: 0.3500 data: 0.0040 max mem: 3953 +train: [1] [140/400] eta: 0:01:37 lr: 0.000081 loss: 3.1322 (3.1445) grad: 0.0690 (0.0696) time: 0.3527 data: 0.0041 max mem: 3953 +train: [1] [160/400] eta: 0:01:28 lr: 0.000084 loss: 3.1409 (3.1466) grad: 0.0683 (0.0691) time: 0.3460 data: 0.0038 max mem: 3953 +train: [1] [180/400] eta: 0:01:20 lr: 0.000087 loss: 3.1506 (3.1461) grad: 0.0667 (0.0689) time: 0.3461 data: 0.0041 max mem: 3953 +train: [1] [200/400] eta: 0:01:13 lr: 0.000090 loss: 3.1320 (3.1454) grad: 0.0655 (0.0684) time: 0.3442 data: 0.0038 max mem: 3953 +train: [1] [220/400] eta: 0:01:05 lr: 0.000093 loss: 3.1317 (3.1450) grad: 0.0712 (0.0690) time: 0.3490 data: 0.0040 max mem: 3953 +train: [1] [240/400] eta: 0:00:58 lr: 0.000096 loss: 3.1326 (3.1435) grad: 0.0719 (0.0691) time: 0.3488 data: 0.0038 max mem: 3953 +train: [1] [260/400] eta: 0:00:50 lr: 0.000099 loss: 3.1347 (3.1440) grad: 0.0684 (0.0688) time: 0.3682 data: 0.0042 max mem: 3953 +train: [1] [280/400] eta: 0:00:43 lr: 0.000102 loss: 3.1339 (3.1421) grad: 0.0701 (0.0690) time: 0.3425 data: 0.0040 max mem: 3953 +train: [1] [300/400] eta: 0:00:36 lr: 0.000105 loss: 3.1339 (3.1422) grad: 0.0692 (0.0689) time: 0.3841 data: 0.0039 max mem: 3953 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 3.1401 (3.1430) grad: 0.0664 (0.0685) time: 0.3366 data: 0.0039 max mem: 3953 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 3.1345 (3.1423) grad: 0.0670 (0.0686) time: 0.3555 data: 0.0042 max mem: 3953 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 3.1293 (3.1421) grad: 0.0670 (0.0684) time: 0.3550 data: 0.0041 max mem: 3953 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 3.1274 (3.1414) grad: 0.0682 (0.0687) time: 0.3483 data: 0.0042 max mem: 3953 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.1279 (3.1410) grad: 0.0730 (0.0688) time: 0.3660 data: 0.0040 max mem: 3953 +train: [1] Total time: 0:02:24 (0.3606 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.1279 (3.1410) grad: 0.0730 (0.0688) +eval (validation): [1] [ 0/85] eta: 0:04:59 time: 3.5271 data: 3.2414 max mem: 3953 +eval (validation): [1] [20/85] eta: 0:00:33 time: 0.3706 data: 0.0113 max mem: 3953 +eval (validation): [1] [40/85] eta: 0:00:19 time: 0.3493 data: 0.0040 max mem: 3953 +eval (validation): [1] [60/85] eta: 0:00:10 time: 0.3384 data: 0.0040 max mem: 3953 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3310 data: 0.0044 max mem: 3953 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3175 data: 0.0041 max mem: 3953 +eval (validation): [1] Total time: 0:00:32 (0.3853 s / it) +cv: [1] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.148 acc: 0.079 f1: 0.023 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:21:10 lr: nan time: 3.1756 data: 2.9628 max mem: 3953 +train: [2] [ 20/400] eta: 0:03:08 lr: 0.000123 loss: 3.1116 (3.1236) grad: 0.0620 (0.0640) time: 0.3610 data: 0.0312 max mem: 3953 +train: [2] [ 40/400] eta: 0:02:34 lr: 0.000126 loss: 3.1290 (3.1303) grad: 0.0645 (0.0663) time: 0.3611 data: 0.0043 max mem: 3953 +train: [2] [ 60/400] eta: 0:02:17 lr: 0.000129 loss: 3.1307 (3.1308) grad: 0.0662 (0.0658) time: 0.3516 data: 0.0032 max mem: 3953 +train: [2] [ 80/400] eta: 0:02:04 lr: 0.000132 loss: 3.1307 (3.1303) grad: 0.0638 (0.0663) time: 0.3457 data: 0.0034 max mem: 3953 +train: [2] [100/400] eta: 0:01:54 lr: 0.000135 loss: 3.1319 (3.1297) grad: 0.0662 (0.0672) time: 0.3541 data: 0.0038 max mem: 3953 +train: [2] [120/400] eta: 0:01:46 lr: 0.000138 loss: 3.1365 (3.1327) grad: 0.0679 (0.0672) time: 0.3677 data: 0.0040 max mem: 3953 +train: [2] [140/400] eta: 0:01:38 lr: 0.000141 loss: 3.1441 (3.1333) grad: 0.0668 (0.0671) time: 0.3831 data: 0.0043 max mem: 3953 +train: [2] [160/400] eta: 0:01:30 lr: 0.000144 loss: 3.1306 (3.1342) grad: 0.0657 (0.0670) time: 0.3494 data: 0.0043 max mem: 3953 +train: [2] [180/400] eta: 0:01:22 lr: 0.000147 loss: 3.1309 (3.1334) grad: 0.0680 (0.0672) time: 0.3540 data: 0.0040 max mem: 3953 +train: [2] [200/400] eta: 0:01:14 lr: 0.000150 loss: 3.1181 (3.1319) grad: 0.0685 (0.0675) time: 0.3488 data: 0.0042 max mem: 3953 +train: [2] [220/400] eta: 0:01:06 lr: 0.000153 loss: 3.1063 (3.1300) grad: 0.0687 (0.0679) time: 0.3479 data: 0.0041 max mem: 3953 +train: [2] [240/400] eta: 0:00:58 lr: 0.000156 loss: 3.1096 (3.1301) grad: 0.0664 (0.0680) time: 0.3534 data: 0.0040 max mem: 3953 +train: [2] [260/400] eta: 0:00:51 lr: 0.000159 loss: 3.1368 (3.1306) grad: 0.0649 (0.0676) time: 0.3788 data: 0.0044 max mem: 3953 +train: [2] [280/400] eta: 0:00:44 lr: 0.000162 loss: 3.1247 (3.1297) grad: 0.0666 (0.0677) time: 0.3541 data: 0.0043 max mem: 3953 +train: [2] [300/400] eta: 0:00:36 lr: 0.000165 loss: 3.1247 (3.1300) grad: 0.0666 (0.0675) time: 0.3534 data: 0.0040 max mem: 3953 +train: [2] [320/400] eta: 0:00:29 lr: 0.000168 loss: 3.1256 (3.1296) grad: 0.0645 (0.0674) time: 0.3376 data: 0.0045 max mem: 3953 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 3.1200 (3.1300) grad: 0.0678 (0.0674) time: 0.3527 data: 0.0037 max mem: 3953 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 3.1204 (3.1293) grad: 0.0626 (0.0671) time: 0.3547 data: 0.0042 max mem: 3953 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 3.1306 (3.1298) grad: 0.0615 (0.0670) time: 0.3465 data: 0.0042 max mem: 3953 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.1453 (3.1308) grad: 0.0662 (0.0671) time: 0.3442 data: 0.0041 max mem: 3953 +train: [2] Total time: 0:02:24 (0.3623 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.1453 (3.1308) grad: 0.0662 (0.0671) +eval (validation): [2] [ 0/85] eta: 0:04:59 time: 3.5238 data: 3.2100 max mem: 3953 +eval (validation): [2] [20/85] eta: 0:00:33 time: 0.3590 data: 0.0053 max mem: 3953 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3343 data: 0.0044 max mem: 3953 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3444 data: 0.0043 max mem: 3953 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3222 data: 0.0041 max mem: 3953 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3160 data: 0.0040 max mem: 3953 +eval (validation): [2] Total time: 0:00:32 (0.3784 s / it) +cv: [2] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.106 acc: 0.089 f1: 0.033 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:57 lr: nan time: 3.4435 data: 3.1913 max mem: 3953 +train: [3] [ 20/400] eta: 0:03:45 lr: 0.000183 loss: 3.1199 (3.1282) grad: 0.0681 (0.0694) time: 0.4506 data: 0.0296 max mem: 3953 +train: [3] [ 40/400] eta: 0:02:53 lr: 0.000186 loss: 3.1199 (3.1228) grad: 0.0660 (0.0677) time: 0.3646 data: 0.0040 max mem: 3953 +train: [3] [ 60/400] eta: 0:02:32 lr: 0.000189 loss: 3.1292 (3.1290) grad: 0.0640 (0.0671) time: 0.3784 data: 0.0044 max mem: 3953 +train: [3] [ 80/400] eta: 0:02:16 lr: 0.000192 loss: 3.1395 (3.1317) grad: 0.0678 (0.0688) time: 0.3637 data: 0.0043 max mem: 3953 +train: [3] [100/400] eta: 0:02:04 lr: 0.000195 loss: 3.1370 (3.1321) grad: 0.0675 (0.0680) time: 0.3676 data: 0.0045 max mem: 3953 +train: [3] [120/400] eta: 0:01:54 lr: 0.000198 loss: 3.1288 (3.1315) grad: 0.0649 (0.0674) time: 0.3693 data: 0.0042 max mem: 3953 +train: [3] [140/400] eta: 0:01:44 lr: 0.000201 loss: 3.1154 (3.1302) grad: 0.0645 (0.0675) time: 0.3745 data: 0.0043 max mem: 3953 +train: [3] [160/400] eta: 0:01:35 lr: 0.000204 loss: 3.1096 (3.1269) grad: 0.0660 (0.0676) time: 0.3774 data: 0.0044 max mem: 3953 +train: [3] [180/400] eta: 0:01:27 lr: 0.000207 loss: 3.1132 (3.1269) grad: 0.0708 (0.0681) time: 0.3636 data: 0.0042 max mem: 3953 +train: [3] [200/400] eta: 0:01:18 lr: 0.000210 loss: 3.1178 (3.1260) grad: 0.0683 (0.0680) time: 0.3619 data: 0.0043 max mem: 3953 +train: [3] [220/400] eta: 0:01:10 lr: 0.000213 loss: 3.1152 (3.1263) grad: 0.0660 (0.0679) time: 0.3712 data: 0.0041 max mem: 3953 +train: [3] [240/400] eta: 0:01:02 lr: 0.000216 loss: 3.1252 (3.1275) grad: 0.0654 (0.0681) time: 0.4137 data: 0.0042 max mem: 3953 +train: [3] [260/400] eta: 0:00:54 lr: 0.000219 loss: 3.1252 (3.1275) grad: 0.0689 (0.0682) time: 0.3696 data: 0.0042 max mem: 3953 +train: [3] [280/400] eta: 0:00:46 lr: 0.000222 loss: 3.1224 (3.1275) grad: 0.0693 (0.0683) time: 0.3592 data: 0.0043 max mem: 3953 +train: [3] [300/400] eta: 0:00:38 lr: 0.000225 loss: 3.1191 (3.1261) grad: 0.0683 (0.0681) time: 0.3540 data: 0.0041 max mem: 3953 +train: [3] [320/400] eta: 0:00:30 lr: 0.000228 loss: 3.1186 (3.1266) grad: 0.0663 (0.0681) time: 0.3575 data: 0.0043 max mem: 3953 +train: [3] [340/400] eta: 0:00:23 lr: 0.000231 loss: 3.1193 (3.1259) grad: 0.0663 (0.0681) time: 0.3674 data: 0.0040 max mem: 3953 +train: [3] [360/400] eta: 0:00:15 lr: 0.000234 loss: 3.1206 (3.1260) grad: 0.0654 (0.0679) time: 0.3574 data: 0.0042 max mem: 3953 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 3.1238 (3.1257) grad: 0.0661 (0.0679) time: 0.3595 data: 0.0039 max mem: 3953 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.1247 (3.1256) grad: 0.0688 (0.0680) time: 0.3524 data: 0.0044 max mem: 3953 +train: [3] Total time: 0:02:31 (0.3797 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.1247 (3.1256) grad: 0.0688 (0.0680) +eval (validation): [3] [ 0/85] eta: 0:04:44 time: 3.3444 data: 3.1186 max mem: 3953 +eval (validation): [3] [20/85] eta: 0:00:34 time: 0.3910 data: 0.0053 max mem: 3953 +eval (validation): [3] [40/85] eta: 0:00:19 time: 0.3181 data: 0.0041 max mem: 3953 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3199 data: 0.0042 max mem: 3953 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3193 data: 0.0044 max mem: 3953 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3125 data: 0.0042 max mem: 3953 +eval (validation): [3] Total time: 0:00:31 (0.3726 s / it) +cv: [3] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.107 acc: 0.104 f1: 0.047 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:22 lr: nan time: 3.3571 data: 3.1324 max mem: 3953 +train: [4] [ 20/400] eta: 0:03:15 lr: 0.000243 loss: 3.1151 (3.1134) grad: 0.0632 (0.0645) time: 0.3734 data: 0.0073 max mem: 3953 +train: [4] [ 40/400] eta: 0:02:34 lr: 0.000246 loss: 3.0830 (3.1058) grad: 0.0611 (0.0630) time: 0.3359 data: 0.0039 max mem: 3953 +train: [4] [ 60/400] eta: 0:02:14 lr: 0.000249 loss: 3.1096 (3.1093) grad: 0.0618 (0.0638) time: 0.3301 data: 0.0043 max mem: 3953 +train: [4] [ 80/400] eta: 0:02:01 lr: 0.000252 loss: 3.1142 (3.1091) grad: 0.0665 (0.0648) time: 0.3316 data: 0.0041 max mem: 3953 +train: [4] [100/400] eta: 0:01:53 lr: 0.000255 loss: 3.1057 (3.1106) grad: 0.0671 (0.0661) time: 0.3675 data: 0.0040 max mem: 3953 +train: [4] [120/400] eta: 0:01:44 lr: 0.000258 loss: 3.0981 (3.1095) grad: 0.0676 (0.0670) time: 0.3554 data: 0.0041 max mem: 3953 +train: [4] [140/400] eta: 0:01:37 lr: 0.000261 loss: 3.0887 (3.1084) grad: 0.0682 (0.0671) time: 0.3814 data: 0.0046 max mem: 3953 +train: [4] [160/400] eta: 0:01:29 lr: 0.000264 loss: 3.1189 (3.1107) grad: 0.0679 (0.0669) time: 0.3487 data: 0.0040 max mem: 3953 +train: [4] [180/400] eta: 0:01:21 lr: 0.000267 loss: 3.1189 (3.1097) grad: 0.0649 (0.0669) time: 0.3438 data: 0.0038 max mem: 3953 +train: [4] [200/400] eta: 0:01:13 lr: 0.000270 loss: 3.0828 (3.1093) grad: 0.0673 (0.0670) time: 0.3672 data: 0.0041 max mem: 3953 +train: [4] [220/400] eta: 0:01:06 lr: 0.000273 loss: 3.1164 (3.1104) grad: 0.0667 (0.0671) time: 0.3607 data: 0.0042 max mem: 3953 +train: [4] [240/400] eta: 0:00:58 lr: 0.000276 loss: 3.1134 (3.1104) grad: 0.0698 (0.0674) time: 0.3723 data: 0.0041 max mem: 3953 +train: [4] [260/400] eta: 0:00:51 lr: 0.000279 loss: 3.0940 (3.1107) grad: 0.0684 (0.0671) time: 0.3717 data: 0.0043 max mem: 3953 +train: [4] [280/400] eta: 0:00:44 lr: 0.000282 loss: 3.1087 (3.1116) grad: 0.0679 (0.0672) time: 0.3482 data: 0.0042 max mem: 3953 +train: [4] [300/400] eta: 0:00:36 lr: 0.000285 loss: 3.1233 (3.1117) grad: 0.0679 (0.0672) time: 0.3381 data: 0.0044 max mem: 3953 +train: [4] [320/400] eta: 0:00:29 lr: 0.000288 loss: 3.1228 (3.1124) grad: 0.0667 (0.0672) time: 0.3364 data: 0.0044 max mem: 3953 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 3.1239 (3.1127) grad: 0.0660 (0.0672) time: 0.3698 data: 0.0037 max mem: 3953 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 3.1203 (3.1130) grad: 0.0682 (0.0673) time: 0.3413 data: 0.0041 max mem: 3953 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1143 (3.1126) grad: 0.0669 (0.0673) time: 0.3568 data: 0.0044 max mem: 3953 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.1090 (3.1117) grad: 0.0658 (0.0673) time: 0.3548 data: 0.0043 max mem: 3953 +train: [4] Total time: 0:02:24 (0.3618 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.1090 (3.1117) grad: 0.0658 (0.0673) +eval (validation): [4] [ 0/85] eta: 0:05:01 time: 3.5453 data: 3.2452 max mem: 3953 +eval (validation): [4] [20/85] eta: 0:00:35 time: 0.3932 data: 0.0042 max mem: 3953 +eval (validation): [4] [40/85] eta: 0:00:19 time: 0.3104 data: 0.0038 max mem: 3953 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3605 data: 0.0049 max mem: 3953 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3280 data: 0.0045 max mem: 3953 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3049 data: 0.0042 max mem: 3953 +eval (validation): [4] Total time: 0:00:32 (0.3861 s / it) +cv: [4] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 3.080 acc: 0.092 f1: 0.034 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:23:31 lr: nan time: 3.5299 data: 3.2921 max mem: 3953 +train: [5] [ 20/400] eta: 0:03:16 lr: 0.000300 loss: 3.0858 (3.0825) grad: 0.0676 (0.0670) time: 0.3657 data: 0.0041 max mem: 3953 +train: [5] [ 40/400] eta: 0:02:37 lr: 0.000300 loss: 3.1016 (3.0979) grad: 0.0654 (0.0658) time: 0.3568 data: 0.0036 max mem: 3953 +train: [5] [ 60/400] eta: 0:02:19 lr: 0.000300 loss: 3.1221 (3.0990) grad: 0.0652 (0.0661) time: 0.3488 data: 0.0043 max mem: 3953 +train: [5] [ 80/400] eta: 0:02:07 lr: 0.000300 loss: 3.0935 (3.0999) grad: 0.0657 (0.0661) time: 0.3701 data: 0.0043 max mem: 3953 +train: [5] [100/400] eta: 0:01:57 lr: 0.000300 loss: 3.0935 (3.0971) grad: 0.0666 (0.0664) time: 0.3567 data: 0.0042 max mem: 3953 +train: [5] [120/400] eta: 0:01:47 lr: 0.000300 loss: 3.0989 (3.1008) grad: 0.0666 (0.0663) time: 0.3563 data: 0.0042 max mem: 3953 +train: [5] [140/400] eta: 0:01:39 lr: 0.000300 loss: 3.1055 (3.1019) grad: 0.0661 (0.0666) time: 0.3585 data: 0.0041 max mem: 3953 +train: [5] [160/400] eta: 0:01:30 lr: 0.000299 loss: 3.0932 (3.1005) grad: 0.0672 (0.0672) time: 0.3603 data: 0.0040 max mem: 3953 +train: [5] [180/400] eta: 0:01:22 lr: 0.000299 loss: 3.0932 (3.0998) grad: 0.0707 (0.0675) time: 0.3571 data: 0.0044 max mem: 3953 +train: [5] [200/400] eta: 0:01:14 lr: 0.000299 loss: 3.0870 (3.0974) grad: 0.0685 (0.0675) time: 0.3562 data: 0.0038 max mem: 3953 +train: [5] [220/400] eta: 0:01:07 lr: 0.000299 loss: 3.0784 (3.0970) grad: 0.0652 (0.0672) time: 0.3736 data: 0.0042 max mem: 3953 +train: [5] [240/400] eta: 0:00:59 lr: 0.000299 loss: 3.1041 (3.0987) grad: 0.0662 (0.0674) time: 0.3716 data: 0.0043 max mem: 3953 +train: [5] [260/400] eta: 0:00:52 lr: 0.000299 loss: 3.1165 (3.1004) grad: 0.0697 (0.0675) time: 0.3562 data: 0.0043 max mem: 3953 +train: [5] [280/400] eta: 0:00:44 lr: 0.000298 loss: 3.1191 (3.1015) grad: 0.0671 (0.0675) time: 0.3590 data: 0.0040 max mem: 3953 +train: [5] [300/400] eta: 0:00:36 lr: 0.000298 loss: 3.1216 (3.1026) grad: 0.0662 (0.0673) time: 0.3427 data: 0.0042 max mem: 3953 +train: [5] [320/400] eta: 0:00:29 lr: 0.000298 loss: 3.1141 (3.1035) grad: 0.0633 (0.0672) time: 0.3391 data: 0.0039 max mem: 3953 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 3.0993 (3.1024) grad: 0.0641 (0.0672) time: 0.3582 data: 0.0041 max mem: 3953 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 3.0834 (3.1015) grad: 0.0691 (0.0674) time: 0.3467 data: 0.0040 max mem: 3953 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.0864 (3.1019) grad: 0.0658 (0.0671) time: 0.3488 data: 0.0040 max mem: 3953 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 3.0864 (3.1014) grad: 0.0647 (0.0672) time: 0.3475 data: 0.0040 max mem: 3953 +train: [5] Total time: 0:02:25 (0.3647 s / it) +train: [5] Summary: lr: 0.000297 loss: 3.0864 (3.1014) grad: 0.0647 (0.0672) +eval (validation): [5] [ 0/85] eta: 0:04:56 time: 3.4833 data: 3.2424 max mem: 3953 +eval (validation): [5] [20/85] eta: 0:00:32 time: 0.3481 data: 0.0036 max mem: 3953 +eval (validation): [5] [40/85] eta: 0:00:18 time: 0.3384 data: 0.0038 max mem: 3953 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3552 data: 0.0048 max mem: 3953 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3382 data: 0.0043 max mem: 3953 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3252 data: 0.0040 max mem: 3953 +eval (validation): [5] Total time: 0:00:32 (0.3839 s / it) +cv: [5] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.099 acc: 0.097 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:22:55 lr: nan time: 3.4378 data: 3.1840 max mem: 3953 +train: [6] [ 20/400] eta: 0:03:15 lr: 0.000296 loss: 3.0766 (3.0917) grad: 0.0641 (0.0670) time: 0.3672 data: 0.0047 max mem: 3953 +train: [6] [ 40/400] eta: 0:02:39 lr: 0.000296 loss: 3.0927 (3.0954) grad: 0.0641 (0.0661) time: 0.3707 data: 0.0037 max mem: 3953 +train: [6] [ 60/400] eta: 0:02:22 lr: 0.000296 loss: 3.0986 (3.1012) grad: 0.0644 (0.0663) time: 0.3692 data: 0.0041 max mem: 3953 +train: [6] [ 80/400] eta: 0:02:09 lr: 0.000295 loss: 3.0932 (3.0973) grad: 0.0646 (0.0668) time: 0.3552 data: 0.0042 max mem: 3953 +train: [6] [100/400] eta: 0:01:59 lr: 0.000295 loss: 3.0833 (3.0979) grad: 0.0646 (0.0665) time: 0.3835 data: 0.0044 max mem: 3953 +train: [6] [120/400] eta: 0:01:50 lr: 0.000295 loss: 3.1089 (3.0983) grad: 0.0638 (0.0659) time: 0.3700 data: 0.0039 max mem: 3953 +train: [6] [140/400] eta: 0:01:41 lr: 0.000294 loss: 3.1089 (3.0997) grad: 0.0671 (0.0664) time: 0.3681 data: 0.0042 max mem: 3953 +train: [6] [160/400] eta: 0:01:32 lr: 0.000294 loss: 3.0985 (3.0990) grad: 0.0676 (0.0667) time: 0.3554 data: 0.0043 max mem: 3953 +train: [6] [180/400] eta: 0:01:24 lr: 0.000293 loss: 3.0908 (3.0999) grad: 0.0660 (0.0669) time: 0.3519 data: 0.0041 max mem: 3953 +train: [6] [200/400] eta: 0:01:16 lr: 0.000293 loss: 3.0752 (3.0980) grad: 0.0658 (0.0669) time: 0.3746 data: 0.0041 max mem: 3953 +train: [6] [220/400] eta: 0:01:08 lr: 0.000292 loss: 3.0789 (3.0970) grad: 0.0664 (0.0671) time: 0.3712 data: 0.0043 max mem: 3953 +train: [6] [240/400] eta: 0:01:00 lr: 0.000292 loss: 3.1058 (3.0982) grad: 0.0692 (0.0672) time: 0.3649 data: 0.0038 max mem: 3953 +train: [6] [260/400] eta: 0:00:52 lr: 0.000291 loss: 3.1003 (3.0981) grad: 0.0686 (0.0672) time: 0.3518 data: 0.0041 max mem: 3953 +train: [6] [280/400] eta: 0:00:45 lr: 0.000291 loss: 3.0846 (3.0962) grad: 0.0664 (0.0672) time: 0.3629 data: 0.0044 max mem: 3953 +train: [6] [300/400] eta: 0:00:37 lr: 0.000290 loss: 3.0890 (3.0965) grad: 0.0686 (0.0672) time: 0.3576 data: 0.0040 max mem: 3953 +train: [6] [320/400] eta: 0:00:29 lr: 0.000290 loss: 3.1034 (3.0971) grad: 0.0689 (0.0672) time: 0.3662 data: 0.0041 max mem: 3953 +train: [6] [340/400] eta: 0:00:22 lr: 0.000289 loss: 3.1028 (3.0972) grad: 0.0651 (0.0670) time: 0.3692 data: 0.0043 max mem: 3953 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 3.0950 (3.0971) grad: 0.0647 (0.0669) time: 0.3631 data: 0.0042 max mem: 3953 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 3.0950 (3.0961) grad: 0.0674 (0.0669) time: 0.3436 data: 0.0041 max mem: 3953 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 3.0999 (3.0970) grad: 0.0627 (0.0666) time: 0.3537 data: 0.0043 max mem: 3953 +train: [6] Total time: 0:02:28 (0.3715 s / it) +train: [6] Summary: lr: 0.000287 loss: 3.0999 (3.0970) grad: 0.0627 (0.0666) +eval (validation): [6] [ 0/85] eta: 0:04:54 time: 3.4632 data: 3.2228 max mem: 3953 +eval (validation): [6] [20/85] eta: 0:00:34 time: 0.3847 data: 0.0057 max mem: 3953 +eval (validation): [6] [40/85] eta: 0:00:19 time: 0.3174 data: 0.0040 max mem: 3953 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3295 data: 0.0041 max mem: 3953 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3467 data: 0.0045 max mem: 3953 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3327 data: 0.0033 max mem: 3953 +eval (validation): [6] Total time: 0:00:32 (0.3830 s / it) +cv: [6] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 3.071 acc: 0.097 f1: 0.043 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:23:37 lr: nan time: 3.5425 data: 3.2392 max mem: 3953 +train: [7] [ 20/400] eta: 0:03:21 lr: 0.000286 loss: 3.0695 (3.0677) grad: 0.0639 (0.0653) time: 0.3795 data: 0.0045 max mem: 3953 +train: [7] [ 40/400] eta: 0:02:44 lr: 0.000286 loss: 3.0695 (3.0607) grad: 0.0643 (0.0672) time: 0.3774 data: 0.0042 max mem: 3953 +train: [7] [ 60/400] eta: 0:02:26 lr: 0.000285 loss: 3.0711 (3.0663) grad: 0.0646 (0.0668) time: 0.3792 data: 0.0036 max mem: 3953 +train: [7] [ 80/400] eta: 0:02:14 lr: 0.000284 loss: 3.0855 (3.0745) grad: 0.0646 (0.0667) time: 0.3886 data: 0.0044 max mem: 3953 +train: [7] [100/400] eta: 0:02:02 lr: 0.000284 loss: 3.0975 (3.0780) grad: 0.0678 (0.0667) time: 0.3560 data: 0.0044 max mem: 3953 +train: [7] [120/400] eta: 0:01:52 lr: 0.000283 loss: 3.0704 (3.0761) grad: 0.0692 (0.0674) time: 0.3787 data: 0.0042 max mem: 3953 +train: [7] [140/400] eta: 0:01:43 lr: 0.000282 loss: 3.0822 (3.0803) grad: 0.0687 (0.0674) time: 0.3631 data: 0.0044 max mem: 3953 +train: [7] [160/400] eta: 0:01:34 lr: 0.000282 loss: 3.1046 (3.0832) grad: 0.0666 (0.0674) time: 0.3655 data: 0.0044 max mem: 3953 +train: [7] [180/400] eta: 0:01:25 lr: 0.000281 loss: 3.0673 (3.0807) grad: 0.0665 (0.0674) time: 0.3711 data: 0.0041 max mem: 3953 +train: [7] [200/400] eta: 0:01:17 lr: 0.000280 loss: 3.0776 (3.0828) grad: 0.0659 (0.0675) time: 0.3658 data: 0.0041 max mem: 3953 +train: [7] [220/400] eta: 0:01:09 lr: 0.000279 loss: 3.0979 (3.0842) grad: 0.0666 (0.0674) time: 0.3722 data: 0.0041 max mem: 3953 +train: [7] [240/400] eta: 0:01:01 lr: 0.000278 loss: 3.0979 (3.0860) grad: 0.0675 (0.0679) time: 0.3507 data: 0.0041 max mem: 3953 +train: [7] [260/400] eta: 0:00:53 lr: 0.000278 loss: 3.1240 (3.0894) grad: 0.0670 (0.0679) time: 0.3628 data: 0.0040 max mem: 3953 +train: [7] [280/400] eta: 0:00:45 lr: 0.000277 loss: 3.1244 (3.0918) grad: 0.0672 (0.0682) time: 0.3665 data: 0.0041 max mem: 3953 +train: [7] [300/400] eta: 0:00:38 lr: 0.000276 loss: 3.0899 (3.0916) grad: 0.0695 (0.0683) time: 0.3657 data: 0.0042 max mem: 3953 +train: [7] [320/400] eta: 0:00:30 lr: 0.000275 loss: 3.0899 (3.0928) grad: 0.0677 (0.0683) time: 0.3644 data: 0.0040 max mem: 3953 +train: [7] [340/400] eta: 0:00:22 lr: 0.000274 loss: 3.0831 (3.0913) grad: 0.0670 (0.0683) time: 0.3525 data: 0.0042 max mem: 3953 +train: [7] [360/400] eta: 0:00:15 lr: 0.000273 loss: 3.0714 (3.0922) grad: 0.0670 (0.0683) time: 0.3419 data: 0.0044 max mem: 3953 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 3.0833 (3.0918) grad: 0.0673 (0.0683) time: 0.3564 data: 0.0041 max mem: 3953 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 3.0651 (3.0899) grad: 0.0666 (0.0685) time: 0.3545 data: 0.0042 max mem: 3953 +train: [7] Total time: 0:02:29 (0.3738 s / it) +train: [7] Summary: lr: 0.000271 loss: 3.0651 (3.0899) grad: 0.0666 (0.0685) +eval (validation): [7] [ 0/85] eta: 0:04:52 time: 3.4375 data: 3.1450 max mem: 3953 +eval (validation): [7] [20/85] eta: 0:00:32 time: 0.3527 data: 0.0029 max mem: 3953 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3479 data: 0.0043 max mem: 3953 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3757 data: 0.0049 max mem: 3953 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3453 data: 0.0041 max mem: 3953 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3387 data: 0.0039 max mem: 3953 +eval (validation): [7] Total time: 0:00:33 (0.3934 s / it) +cv: [7] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.116 acc: 0.111 f1: 0.049 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:23:21 lr: nan time: 3.5050 data: 3.2585 max mem: 3953 +train: [8] [ 20/400] eta: 0:03:41 lr: 0.000270 loss: 3.0791 (3.0851) grad: 0.0690 (0.0666) time: 0.4357 data: 0.0087 max mem: 3953 +train: [8] [ 40/400] eta: 0:02:53 lr: 0.000270 loss: 3.0865 (3.0872) grad: 0.0657 (0.0658) time: 0.3757 data: 0.0040 max mem: 3953 +train: [8] [ 60/400] eta: 0:02:31 lr: 0.000269 loss: 3.0917 (3.0930) grad: 0.0644 (0.0664) time: 0.3722 data: 0.0040 max mem: 3953 +train: [8] [ 80/400] eta: 0:02:17 lr: 0.000268 loss: 3.0807 (3.0874) grad: 0.0644 (0.0657) time: 0.3771 data: 0.0042 max mem: 3953 +train: [8] [100/400] eta: 0:02:04 lr: 0.000267 loss: 3.0807 (3.0875) grad: 0.0645 (0.0665) time: 0.3548 data: 0.0043 max mem: 3953 +train: [8] [120/400] eta: 0:01:53 lr: 0.000266 loss: 3.0689 (3.0835) grad: 0.0652 (0.0658) time: 0.3561 data: 0.0041 max mem: 3953 +train: [8] [140/400] eta: 0:01:43 lr: 0.000265 loss: 3.0714 (3.0822) grad: 0.0624 (0.0658) time: 0.3601 data: 0.0037 max mem: 3953 +train: [8] [160/400] eta: 0:01:34 lr: 0.000264 loss: 3.0767 (3.0830) grad: 0.0625 (0.0656) time: 0.3496 data: 0.0042 max mem: 3953 +train: [8] [180/400] eta: 0:01:25 lr: 0.000263 loss: 3.0813 (3.0826) grad: 0.0632 (0.0655) time: 0.3642 data: 0.0040 max mem: 3953 +train: [8] [200/400] eta: 0:01:17 lr: 0.000262 loss: 3.0747 (3.0828) grad: 0.0632 (0.0653) time: 0.3664 data: 0.0043 max mem: 3953 +train: [8] [220/400] eta: 0:01:09 lr: 0.000260 loss: 3.0808 (3.0826) grad: 0.0665 (0.0655) time: 0.3514 data: 0.0039 max mem: 3953 +train: [8] [240/400] eta: 0:01:01 lr: 0.000259 loss: 3.0817 (3.0841) grad: 0.0678 (0.0656) time: 0.3591 data: 0.0042 max mem: 3953 +train: [8] [260/400] eta: 0:00:53 lr: 0.000258 loss: 3.0688 (3.0825) grad: 0.0679 (0.0659) time: 0.3556 data: 0.0044 max mem: 3953 +train: [8] [280/400] eta: 0:00:45 lr: 0.000257 loss: 3.0767 (3.0841) grad: 0.0631 (0.0659) time: 0.3851 data: 0.0042 max mem: 3953 +train: [8] [300/400] eta: 0:00:37 lr: 0.000256 loss: 3.1019 (3.0846) grad: 0.0620 (0.0656) time: 0.3577 data: 0.0045 max mem: 3953 +train: [8] [320/400] eta: 0:00:30 lr: 0.000255 loss: 3.0993 (3.0855) grad: 0.0622 (0.0657) time: 0.3589 data: 0.0041 max mem: 3953 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 3.0902 (3.0848) grad: 0.0656 (0.0656) time: 0.3600 data: 0.0041 max mem: 3953 +train: [8] [360/400] eta: 0:00:14 lr: 0.000253 loss: 3.0572 (3.0837) grad: 0.0641 (0.0656) time: 0.3320 data: 0.0041 max mem: 3953 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 3.0660 (3.0825) grad: 0.0687 (0.0656) time: 0.3481 data: 0.0045 max mem: 3953 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 3.0554 (3.0813) grad: 0.0628 (0.0654) time: 0.4154 data: 0.0040 max mem: 3953 +train: [8] Total time: 0:02:29 (0.3748 s / it) +train: [8] Summary: lr: 0.000250 loss: 3.0554 (3.0813) grad: 0.0628 (0.0654) +eval (validation): [8] [ 0/85] eta: 0:04:46 time: 3.3692 data: 3.0933 max mem: 3953 +eval (validation): [8] [20/85] eta: 0:00:33 time: 0.3742 data: 0.0050 max mem: 3953 +eval (validation): [8] [40/85] eta: 0:00:19 time: 0.3544 data: 0.0042 max mem: 3953 +eval (validation): [8] [60/85] eta: 0:00:10 time: 0.3637 data: 0.0043 max mem: 3953 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3283 data: 0.0042 max mem: 3953 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3253 data: 0.0041 max mem: 3953 +eval (validation): [8] Total time: 0:00:33 (0.3932 s / it) +cv: [8] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 3.060 acc: 0.101 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:27:17 lr: nan time: 4.0937 data: 3.8438 max mem: 3953 +train: [9] [ 20/400] eta: 0:03:27 lr: 0.000249 loss: 3.0696 (3.0898) grad: 0.0593 (0.0636) time: 0.3675 data: 0.0038 max mem: 3953 +train: [9] [ 40/400] eta: 0:02:43 lr: 0.000248 loss: 3.0687 (3.0813) grad: 0.0601 (0.0639) time: 0.3570 data: 0.0042 max mem: 3953 +train: [9] [ 60/400] eta: 0:02:22 lr: 0.000247 loss: 3.0574 (3.0806) grad: 0.0635 (0.0639) time: 0.3519 data: 0.0041 max mem: 3953 +train: [9] [ 80/400] eta: 0:02:09 lr: 0.000246 loss: 3.0555 (3.0783) grad: 0.0640 (0.0649) time: 0.3531 data: 0.0042 max mem: 3953 +train: [9] [100/400] eta: 0:01:58 lr: 0.000244 loss: 3.0554 (3.0775) grad: 0.0640 (0.0651) time: 0.3528 data: 0.0041 max mem: 3953 +train: [9] [120/400] eta: 0:01:47 lr: 0.000243 loss: 3.0561 (3.0746) grad: 0.0630 (0.0649) time: 0.3345 data: 0.0043 max mem: 3953 +train: [9] [140/400] eta: 0:01:37 lr: 0.000242 loss: 3.0668 (3.0757) grad: 0.0638 (0.0651) time: 0.3182 data: 0.0041 max mem: 3953 +train: [9] [160/400] eta: 0:01:28 lr: 0.000241 loss: 3.0891 (3.0788) grad: 0.0638 (0.0648) time: 0.3132 data: 0.0048 max mem: 3953 +train: [9] [180/400] eta: 0:01:19 lr: 0.000240 loss: 3.1027 (3.0806) grad: 0.0606 (0.0643) time: 0.3377 data: 0.0048 max mem: 3953 +train: [9] [200/400] eta: 0:01:11 lr: 0.000238 loss: 3.0914 (3.0788) grad: 0.0636 (0.0644) time: 0.3163 data: 0.0038 max mem: 3953 +train: [9] [220/400] eta: 0:01:03 lr: 0.000237 loss: 3.0687 (3.0788) grad: 0.0696 (0.0649) time: 0.3200 data: 0.0043 max mem: 3953 +train: [9] [240/400] eta: 0:00:56 lr: 0.000236 loss: 3.0687 (3.0786) grad: 0.0711 (0.0656) time: 0.3241 data: 0.0040 max mem: 3953 +train: [9] [260/400] eta: 0:00:49 lr: 0.000234 loss: 3.0679 (3.0781) grad: 0.0697 (0.0656) time: 0.3241 data: 0.0043 max mem: 3953 +train: [9] [280/400] eta: 0:00:41 lr: 0.000233 loss: 3.0493 (3.0756) grad: 0.0637 (0.0655) time: 0.3422 data: 0.0041 max mem: 3953 +train: [9] [300/400] eta: 0:00:35 lr: 0.000232 loss: 3.0721 (3.0767) grad: 0.0637 (0.0654) time: 0.3524 data: 0.0045 max mem: 3953 +train: [9] [320/400] eta: 0:00:28 lr: 0.000230 loss: 3.0866 (3.0778) grad: 0.0683 (0.0657) time: 0.3498 data: 0.0041 max mem: 3953 +train: [9] [340/400] eta: 0:00:21 lr: 0.000229 loss: 3.0726 (3.0768) grad: 0.0645 (0.0656) time: 0.3905 data: 0.0043 max mem: 3953 +train: [9] [360/400] eta: 0:00:14 lr: 0.000228 loss: 3.0826 (3.0780) grad: 0.0644 (0.0657) time: 0.3535 data: 0.0040 max mem: 3953 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 3.0944 (3.0781) grad: 0.0672 (0.0657) time: 0.3297 data: 0.0042 max mem: 3953 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 3.0762 (3.0779) grad: 0.0650 (0.0655) time: 0.3849 data: 0.0041 max mem: 3953 +train: [9] Total time: 0:02:21 (0.3534 s / it) +train: [9] Summary: lr: 0.000225 loss: 3.0762 (3.0779) grad: 0.0650 (0.0655) +eval (validation): [9] [ 0/85] eta: 0:05:15 time: 3.7093 data: 3.4020 max mem: 3953 +eval (validation): [9] [20/85] eta: 0:00:36 time: 0.4023 data: 0.0034 max mem: 3953 +eval (validation): [9] [40/85] eta: 0:00:20 time: 0.3492 data: 0.0042 max mem: 3953 +eval (validation): [9] [60/85] eta: 0:00:10 time: 0.3467 data: 0.0041 max mem: 3953 +eval (validation): [9] [80/85] eta: 0:00:02 time: 0.3467 data: 0.0044 max mem: 3953 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3423 data: 0.0042 max mem: 3953 +eval (validation): [9] Total time: 0:00:34 (0.4018 s / it) +cv: [9] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.105 acc: 0.099 f1: 0.055 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:24:32 lr: nan time: 3.6813 data: 3.3634 max mem: 3953 +train: [10] [ 20/400] eta: 0:03:23 lr: 0.000224 loss: 3.1046 (3.1094) grad: 0.0659 (0.0639) time: 0.3781 data: 0.0046 max mem: 3953 +train: [10] [ 40/400] eta: 0:02:44 lr: 0.000222 loss: 3.0902 (3.0939) grad: 0.0659 (0.0653) time: 0.3750 data: 0.0035 max mem: 3953 +train: [10] [ 60/400] eta: 0:02:25 lr: 0.000221 loss: 3.0660 (3.0812) grad: 0.0684 (0.0663) time: 0.3686 data: 0.0037 max mem: 3953 +train: [10] [ 80/400] eta: 0:02:13 lr: 0.000220 loss: 3.0660 (3.0796) grad: 0.0658 (0.0657) time: 0.3862 data: 0.0041 max mem: 3953 +train: [10] [100/400] eta: 0:02:02 lr: 0.000218 loss: 3.0721 (3.0780) grad: 0.0631 (0.0662) time: 0.3748 data: 0.0043 max mem: 3953 +train: [10] [120/400] eta: 0:01:53 lr: 0.000217 loss: 3.0874 (3.0799) grad: 0.0672 (0.0663) time: 0.3777 data: 0.0042 max mem: 3953 +train: [10] [140/400] eta: 0:01:43 lr: 0.000215 loss: 3.0776 (3.0789) grad: 0.0674 (0.0666) time: 0.3594 data: 0.0043 max mem: 3953 +train: [10] [160/400] eta: 0:01:34 lr: 0.000214 loss: 3.0624 (3.0781) grad: 0.0665 (0.0665) time: 0.3791 data: 0.0043 max mem: 3953 +train: [10] [180/400] eta: 0:01:26 lr: 0.000213 loss: 3.0693 (3.0791) grad: 0.0661 (0.0665) time: 0.3823 data: 0.0043 max mem: 3953 +train: [10] [200/400] eta: 0:01:17 lr: 0.000211 loss: 3.0745 (3.0789) grad: 0.0652 (0.0666) time: 0.3513 data: 0.0039 max mem: 3953 +train: [10] [220/400] eta: 0:01:09 lr: 0.000210 loss: 3.0664 (3.0776) grad: 0.0649 (0.0663) time: 0.3697 data: 0.0042 max mem: 3953 +train: [10] [240/400] eta: 0:01:02 lr: 0.000208 loss: 3.0405 (3.0748) grad: 0.0641 (0.0662) time: 0.3953 data: 0.0041 max mem: 3953 +train: [10] [260/400] eta: 0:00:54 lr: 0.000207 loss: 3.0586 (3.0752) grad: 0.0660 (0.0661) time: 0.3622 data: 0.0041 max mem: 3953 +train: [10] [280/400] eta: 0:00:46 lr: 0.000205 loss: 3.0913 (3.0760) grad: 0.0628 (0.0658) time: 0.3666 data: 0.0040 max mem: 3953 +train: [10] [300/400] eta: 0:00:38 lr: 0.000204 loss: 3.1030 (3.0762) grad: 0.0628 (0.0658) time: 0.3755 data: 0.0040 max mem: 3953 +train: [10] [320/400] eta: 0:00:30 lr: 0.000202 loss: 3.0933 (3.0763) grad: 0.0653 (0.0659) time: 0.3751 data: 0.0040 max mem: 3953 +train: [10] [340/400] eta: 0:00:22 lr: 0.000201 loss: 3.0700 (3.0753) grad: 0.0644 (0.0657) time: 0.3523 data: 0.0042 max mem: 3953 +train: [10] [360/400] eta: 0:00:15 lr: 0.000199 loss: 3.0667 (3.0748) grad: 0.0633 (0.0655) time: 0.3654 data: 0.0043 max mem: 3953 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 3.0612 (3.0742) grad: 0.0641 (0.0656) time: 0.3582 data: 0.0040 max mem: 3953 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 3.0770 (3.0749) grad: 0.0651 (0.0658) time: 0.3302 data: 0.0042 max mem: 3953 +train: [10] Total time: 0:02:31 (0.3777 s / it) +train: [10] Summary: lr: 0.000196 loss: 3.0770 (3.0749) grad: 0.0651 (0.0658) +eval (validation): [10] [ 0/85] eta: 0:04:59 time: 3.5223 data: 3.2774 max mem: 3953 +eval (validation): [10] [20/85] eta: 0:00:35 time: 0.3961 data: 0.0061 max mem: 3953 +eval (validation): [10] [40/85] eta: 0:00:20 time: 0.3534 data: 0.0036 max mem: 3953 +eval (validation): [10] [60/85] eta: 0:00:10 time: 0.3472 data: 0.0043 max mem: 3953 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3409 data: 0.0042 max mem: 3953 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3395 data: 0.0040 max mem: 3953 +eval (validation): [10] Total time: 0:00:33 (0.3979 s / it) +cv: [10] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.065 acc: 0.104 f1: 0.068 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:26:06 lr: nan time: 3.9174 data: 3.6104 max mem: 3953 +train: [11] [ 20/400] eta: 0:03:29 lr: 0.000195 loss: 3.0621 (3.0725) grad: 0.0650 (0.0662) time: 0.3821 data: 0.0186 max mem: 3953 +train: [11] [ 40/400] eta: 0:02:46 lr: 0.000193 loss: 3.0830 (3.0785) grad: 0.0654 (0.0666) time: 0.3728 data: 0.0038 max mem: 3953 +train: [11] [ 60/400] eta: 0:02:29 lr: 0.000192 loss: 3.0742 (3.0702) grad: 0.0671 (0.0681) time: 0.3869 data: 0.0026 max mem: 3953 +train: [11] [ 80/400] eta: 0:02:15 lr: 0.000190 loss: 3.0550 (3.0663) grad: 0.0654 (0.0673) time: 0.3762 data: 0.0038 max mem: 3953 +train: [11] [100/400] eta: 0:02:04 lr: 0.000189 loss: 3.0486 (3.0672) grad: 0.0654 (0.0672) time: 0.3758 data: 0.0037 max mem: 3953 +train: [11] [120/400] eta: 0:01:54 lr: 0.000187 loss: 3.0486 (3.0622) grad: 0.0657 (0.0666) time: 0.3820 data: 0.0039 max mem: 3953 +train: [11] [140/400] eta: 0:01:44 lr: 0.000186 loss: 3.0531 (3.0632) grad: 0.0657 (0.0663) time: 0.3707 data: 0.0037 max mem: 3953 +train: [11] [160/400] eta: 0:01:36 lr: 0.000184 loss: 3.0604 (3.0634) grad: 0.0663 (0.0665) time: 0.3832 data: 0.0041 max mem: 3953 +train: [11] [180/400] eta: 0:01:27 lr: 0.000183 loss: 3.0633 (3.0640) grad: 0.0657 (0.0662) time: 0.3836 data: 0.0040 max mem: 3953 +train: [11] [200/400] eta: 0:01:18 lr: 0.000181 loss: 3.0661 (3.0631) grad: 0.0639 (0.0663) time: 0.3517 data: 0.0038 max mem: 3953 +train: [11] [220/400] eta: 0:01:10 lr: 0.000180 loss: 3.0784 (3.0648) grad: 0.0632 (0.0661) time: 0.3778 data: 0.0046 max mem: 3953 +train: [11] [240/400] eta: 0:01:02 lr: 0.000178 loss: 3.0851 (3.0658) grad: 0.0640 (0.0658) time: 0.3653 data: 0.0043 max mem: 3953 +train: [11] [260/400] eta: 0:00:54 lr: 0.000177 loss: 3.0736 (3.0661) grad: 0.0617 (0.0655) time: 0.3697 data: 0.0040 max mem: 3953 +train: [11] [280/400] eta: 0:00:46 lr: 0.000175 loss: 3.0623 (3.0653) grad: 0.0609 (0.0653) time: 0.3655 data: 0.0041 max mem: 3953 +train: [11] [300/400] eta: 0:00:38 lr: 0.000174 loss: 3.0700 (3.0655) grad: 0.0628 (0.0654) time: 0.3662 data: 0.0040 max mem: 3953 +train: [11] [320/400] eta: 0:00:30 lr: 0.000172 loss: 3.0781 (3.0664) grad: 0.0665 (0.0654) time: 0.3728 data: 0.0042 max mem: 3953 +train: [11] [340/400] eta: 0:00:22 lr: 0.000170 loss: 3.0863 (3.0683) grad: 0.0639 (0.0652) time: 0.3556 data: 0.0042 max mem: 3953 +train: [11] [360/400] eta: 0:00:15 lr: 0.000169 loss: 3.0748 (3.0668) grad: 0.0611 (0.0651) time: 0.3696 data: 0.0041 max mem: 3953 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 3.0633 (3.0671) grad: 0.0666 (0.0653) time: 0.3499 data: 0.0039 max mem: 3953 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 3.0600 (3.0669) grad: 0.0676 (0.0656) time: 0.3779 data: 0.0043 max mem: 3953 +train: [11] Total time: 0:02:32 (0.3810 s / it) +train: [11] Summary: lr: 0.000166 loss: 3.0600 (3.0669) grad: 0.0676 (0.0656) +eval (validation): [11] [ 0/85] eta: 0:04:56 time: 3.4917 data: 3.2334 max mem: 3953 +eval (validation): [11] [20/85] eta: 0:00:34 time: 0.3817 data: 0.0058 max mem: 3953 +eval (validation): [11] [40/85] eta: 0:00:20 time: 0.3712 data: 0.0038 max mem: 3953 +eval (validation): [11] [60/85] eta: 0:00:10 time: 0.3321 data: 0.0042 max mem: 3953 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3322 data: 0.0044 max mem: 3953 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3351 data: 0.0042 max mem: 3953 +eval (validation): [11] Total time: 0:00:33 (0.3939 s / it) +cv: [11] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.059 acc: 0.099 f1: 0.050 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:23:46 lr: nan time: 3.5670 data: 3.3165 max mem: 3953 +train: [12] [ 20/400] eta: 0:03:28 lr: 0.000164 loss: 3.0487 (3.0477) grad: 0.0653 (0.0647) time: 0.3981 data: 0.0042 max mem: 3953 +train: [12] [ 40/400] eta: 0:02:49 lr: 0.000163 loss: 3.0538 (3.0471) grad: 0.0622 (0.0627) time: 0.3901 data: 0.0038 max mem: 3953 +train: [12] [ 60/400] eta: 0:02:30 lr: 0.000161 loss: 3.0817 (3.0597) grad: 0.0618 (0.0633) time: 0.3870 data: 0.0042 max mem: 3953 +train: [12] [ 80/400] eta: 0:02:16 lr: 0.000160 loss: 3.0576 (3.0500) grad: 0.0647 (0.0641) time: 0.3744 data: 0.0041 max mem: 3953 +train: [12] [100/400] eta: 0:02:04 lr: 0.000158 loss: 3.0404 (3.0516) grad: 0.0648 (0.0648) time: 0.3750 data: 0.0044 max mem: 3953 +train: [12] [120/400] eta: 0:01:54 lr: 0.000156 loss: 3.0627 (3.0547) grad: 0.0648 (0.0650) time: 0.3744 data: 0.0042 max mem: 3953 +train: [12] [140/400] eta: 0:01:45 lr: 0.000155 loss: 3.0627 (3.0552) grad: 0.0591 (0.0644) time: 0.3842 data: 0.0042 max mem: 3953 +train: [12] [160/400] eta: 0:01:36 lr: 0.000153 loss: 3.0501 (3.0563) grad: 0.0658 (0.0651) time: 0.3735 data: 0.0044 max mem: 3953 +train: [12] [180/400] eta: 0:01:27 lr: 0.000152 loss: 3.0581 (3.0598) grad: 0.0662 (0.0647) time: 0.3702 data: 0.0042 max mem: 3953 +train: [12] [200/400] eta: 0:01:18 lr: 0.000150 loss: 3.0708 (3.0586) grad: 0.0628 (0.0650) time: 0.3596 data: 0.0040 max mem: 3953 +train: [12] [220/400] eta: 0:01:10 lr: 0.000149 loss: 3.0564 (3.0564) grad: 0.0599 (0.0645) time: 0.3788 data: 0.0042 max mem: 3953 +train: [12] [240/400] eta: 0:01:03 lr: 0.000147 loss: 3.0740 (3.0588) grad: 0.0599 (0.0646) time: 0.4135 data: 0.0043 max mem: 3953 +train: [12] [260/400] eta: 0:00:54 lr: 0.000145 loss: 3.0769 (3.0597) grad: 0.0634 (0.0646) time: 0.3690 data: 0.0041 max mem: 3953 +train: [12] [280/400] eta: 0:00:47 lr: 0.000144 loss: 3.0731 (3.0610) grad: 0.0634 (0.0645) time: 0.3780 data: 0.0041 max mem: 3953 +train: [12] [300/400] eta: 0:00:39 lr: 0.000142 loss: 3.0616 (3.0595) grad: 0.0626 (0.0643) time: 0.3861 data: 0.0041 max mem: 3953 +train: [12] [320/400] eta: 0:00:31 lr: 0.000141 loss: 3.0448 (3.0595) grad: 0.0631 (0.0642) time: 0.3682 data: 0.0041 max mem: 3953 +train: [12] [340/400] eta: 0:00:23 lr: 0.000139 loss: 3.0737 (3.0602) grad: 0.0634 (0.0642) time: 0.3674 data: 0.0041 max mem: 3953 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 3.0800 (3.0623) grad: 0.0626 (0.0640) time: 0.3754 data: 0.0042 max mem: 3953 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 3.0896 (3.0633) grad: 0.0626 (0.0641) time: 0.3553 data: 0.0041 max mem: 3953 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 3.0754 (3.0632) grad: 0.0694 (0.0644) time: 0.3572 data: 0.0043 max mem: 3953 +train: [12] Total time: 0:02:34 (0.3851 s / it) +train: [12] Summary: lr: 0.000134 loss: 3.0754 (3.0632) grad: 0.0694 (0.0644) +eval (validation): [12] [ 0/85] eta: 0:04:57 time: 3.5047 data: 3.2709 max mem: 3953 +eval (validation): [12] [20/85] eta: 0:00:37 time: 0.4279 data: 0.0349 max mem: 3953 +eval (validation): [12] [40/85] eta: 0:00:21 time: 0.3774 data: 0.0040 max mem: 3953 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3186 data: 0.0038 max mem: 3953 +eval (validation): [12] [80/85] eta: 0:00:02 time: 0.3384 data: 0.0041 max mem: 3953 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3246 data: 0.0036 max mem: 3953 +eval (validation): [12] Total time: 0:00:34 (0.4033 s / it) +cv: [12] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.050 acc: 0.115 f1: 0.057 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:23:32 lr: nan time: 3.5309 data: 3.2413 max mem: 3953 +train: [13] [ 20/400] eta: 0:03:28 lr: 0.000133 loss: 3.0321 (3.0440) grad: 0.0615 (0.0625) time: 0.3986 data: 0.0043 max mem: 3953 +train: [13] [ 40/400] eta: 0:02:48 lr: 0.000131 loss: 3.0472 (3.0381) grad: 0.0611 (0.0623) time: 0.3843 data: 0.0040 max mem: 3953 +train: [13] [ 60/400] eta: 0:02:30 lr: 0.000130 loss: 3.0425 (3.0440) grad: 0.0619 (0.0630) time: 0.3919 data: 0.0041 max mem: 3953 +train: [13] [ 80/400] eta: 0:02:16 lr: 0.000128 loss: 3.0554 (3.0477) grad: 0.0630 (0.0636) time: 0.3702 data: 0.0043 max mem: 3953 +train: [13] [100/400] eta: 0:02:04 lr: 0.000127 loss: 3.0639 (3.0510) grad: 0.0624 (0.0640) time: 0.3806 data: 0.0042 max mem: 3953 +train: [13] [120/400] eta: 0:01:55 lr: 0.000125 loss: 3.0553 (3.0523) grad: 0.0622 (0.0641) time: 0.3884 data: 0.0041 max mem: 3953 +train: [13] [140/400] eta: 0:01:46 lr: 0.000124 loss: 3.0587 (3.0538) grad: 0.0659 (0.0641) time: 0.3856 data: 0.0040 max mem: 3953 +train: [13] [160/400] eta: 0:01:36 lr: 0.000122 loss: 3.0509 (3.0521) grad: 0.0652 (0.0637) time: 0.3748 data: 0.0041 max mem: 3953 +train: [13] [180/400] eta: 0:01:27 lr: 0.000120 loss: 3.0369 (3.0522) grad: 0.0648 (0.0637) time: 0.3602 data: 0.0038 max mem: 3953 +train: [13] [200/400] eta: 0:01:19 lr: 0.000119 loss: 3.0447 (3.0535) grad: 0.0672 (0.0640) time: 0.3684 data: 0.0042 max mem: 3953 +train: [13] [220/400] eta: 0:01:11 lr: 0.000117 loss: 3.0611 (3.0523) grad: 0.0691 (0.0641) time: 0.3849 data: 0.0039 max mem: 3953 +train: [13] [240/400] eta: 0:01:03 lr: 0.000116 loss: 3.0395 (3.0528) grad: 0.0689 (0.0643) time: 0.3844 data: 0.0038 max mem: 3953 +train: [13] [260/400] eta: 0:00:54 lr: 0.000114 loss: 3.0628 (3.0550) grad: 0.0589 (0.0638) time: 0.3762 data: 0.0039 max mem: 3953 +train: [13] [280/400] eta: 0:00:46 lr: 0.000113 loss: 3.0707 (3.0554) grad: 0.0591 (0.0640) time: 0.3772 data: 0.0040 max mem: 3953 +train: [13] [300/400] eta: 0:00:38 lr: 0.000111 loss: 3.0445 (3.0555) grad: 0.0628 (0.0639) time: 0.3658 data: 0.0041 max mem: 3953 +train: [13] [320/400] eta: 0:00:31 lr: 0.000110 loss: 3.0464 (3.0562) grad: 0.0598 (0.0638) time: 0.3571 data: 0.0041 max mem: 3953 +train: [13] [340/400] eta: 0:00:23 lr: 0.000108 loss: 3.0610 (3.0556) grad: 0.0603 (0.0636) time: 0.3735 data: 0.0040 max mem: 3953 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 3.0344 (3.0560) grad: 0.0611 (0.0635) time: 0.3870 data: 0.0041 max mem: 3953 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 3.0742 (3.0570) grad: 0.0647 (0.0636) time: 0.3668 data: 0.0038 max mem: 3953 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 3.0583 (3.0570) grad: 0.0649 (0.0637) time: 0.3568 data: 0.0039 max mem: 3953 +train: [13] Total time: 0:02:33 (0.3848 s / it) +train: [13] Summary: lr: 0.000104 loss: 3.0583 (3.0570) grad: 0.0649 (0.0637) +eval (validation): [13] [ 0/85] eta: 0:04:57 time: 3.4988 data: 3.2268 max mem: 3953 +eval (validation): [13] [20/85] eta: 0:00:34 time: 0.3893 data: 0.0429 max mem: 3953 +eval (validation): [13] [40/85] eta: 0:00:20 time: 0.3837 data: 0.0046 max mem: 3953 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3334 data: 0.0037 max mem: 3953 +eval (validation): [13] [80/85] eta: 0:00:02 time: 0.3495 data: 0.0039 max mem: 3953 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3396 data: 0.0038 max mem: 3953 +eval (validation): [13] Total time: 0:00:34 (0.4023 s / it) +cv: [13] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.037 acc: 0.111 f1: 0.065 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:23:47 lr: nan time: 3.5695 data: 3.3147 max mem: 3953 +train: [14] [ 20/400] eta: 0:03:24 lr: 0.000102 loss: 3.0730 (3.0773) grad: 0.0632 (0.0671) time: 0.3855 data: 0.0143 max mem: 3953 +train: [14] [ 40/400] eta: 0:02:53 lr: 0.000101 loss: 3.0607 (3.0710) grad: 0.0640 (0.0657) time: 0.4237 data: 0.0038 max mem: 3953 +train: [14] [ 60/400] eta: 0:02:30 lr: 0.000099 loss: 3.0601 (3.0699) grad: 0.0648 (0.0649) time: 0.3607 data: 0.0041 max mem: 3953 +train: [14] [ 80/400] eta: 0:02:14 lr: 0.000098 loss: 3.0710 (3.0714) grad: 0.0596 (0.0633) time: 0.3583 data: 0.0041 max mem: 3953 +train: [14] [100/400] eta: 0:02:04 lr: 0.000096 loss: 3.0515 (3.0641) grad: 0.0581 (0.0634) time: 0.3823 data: 0.0042 max mem: 3953 +train: [14] [120/400] eta: 0:01:53 lr: 0.000095 loss: 3.0281 (3.0605) grad: 0.0604 (0.0629) time: 0.3716 data: 0.0042 max mem: 3953 +train: [14] [140/400] eta: 0:01:45 lr: 0.000093 loss: 3.0417 (3.0612) grad: 0.0615 (0.0635) time: 0.3902 data: 0.0041 max mem: 3953 +train: [14] [160/400] eta: 0:01:36 lr: 0.000092 loss: 3.0546 (3.0608) grad: 0.0659 (0.0637) time: 0.3745 data: 0.0043 max mem: 3953 +train: [14] [180/400] eta: 0:01:26 lr: 0.000090 loss: 3.0499 (3.0598) grad: 0.0652 (0.0639) time: 0.3498 data: 0.0040 max mem: 3953 +train: [14] [200/400] eta: 0:01:18 lr: 0.000089 loss: 3.0478 (3.0596) grad: 0.0623 (0.0634) time: 0.3685 data: 0.0048 max mem: 3953 +train: [14] [220/400] eta: 0:01:10 lr: 0.000088 loss: 3.0460 (3.0583) grad: 0.0629 (0.0637) time: 0.3572 data: 0.0038 max mem: 3953 +train: [14] [240/400] eta: 0:01:01 lr: 0.000086 loss: 3.0471 (3.0591) grad: 0.0659 (0.0639) time: 0.3507 data: 0.0043 max mem: 3953 +train: [14] [260/400] eta: 0:00:53 lr: 0.000085 loss: 3.0584 (3.0589) grad: 0.0656 (0.0639) time: 0.3549 data: 0.0043 max mem: 3953 +train: [14] [280/400] eta: 0:00:45 lr: 0.000083 loss: 3.0426 (3.0591) grad: 0.0600 (0.0637) time: 0.3395 data: 0.0044 max mem: 3953 +train: [14] [300/400] eta: 0:00:37 lr: 0.000082 loss: 3.0521 (3.0599) grad: 0.0611 (0.0636) time: 0.3422 data: 0.0040 max mem: 3953 +train: [14] [320/400] eta: 0:00:30 lr: 0.000081 loss: 3.0521 (3.0586) grad: 0.0624 (0.0635) time: 0.3476 data: 0.0042 max mem: 3953 +train: [14] [340/400] eta: 0:00:22 lr: 0.000079 loss: 3.0561 (3.0599) grad: 0.0626 (0.0637) time: 0.3442 data: 0.0042 max mem: 3953 +train: [14] [360/400] eta: 0:00:14 lr: 0.000078 loss: 3.0748 (3.0598) grad: 0.0617 (0.0637) time: 0.3245 data: 0.0043 max mem: 3953 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 3.0519 (3.0590) grad: 0.0632 (0.0636) time: 0.3245 data: 0.0042 max mem: 3953 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 3.0519 (3.0585) grad: 0.0609 (0.0635) time: 0.3252 data: 0.0041 max mem: 3953 +train: [14] Total time: 0:02:26 (0.3671 s / it) +train: [14] Summary: lr: 0.000075 loss: 3.0519 (3.0585) grad: 0.0609 (0.0635) +eval (validation): [14] [ 0/85] eta: 0:04:52 time: 3.4358 data: 3.1605 max mem: 3953 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3541 data: 0.0047 max mem: 3953 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3563 data: 0.0043 max mem: 3953 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3093 data: 0.0047 max mem: 3953 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3000 data: 0.0040 max mem: 3953 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.2955 data: 0.0040 max mem: 3953 +eval (validation): [14] Total time: 0:00:31 (0.3673 s / it) +cv: [14] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.038 acc: 0.107 f1: 0.057 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:50 lr: nan time: 3.5770 data: 3.2700 max mem: 3953 +train: [15] [ 20/400] eta: 0:03:32 lr: 0.000074 loss: 3.0622 (3.0524) grad: 0.0653 (0.0673) time: 0.4090 data: 0.0517 max mem: 3953 +train: [15] [ 40/400] eta: 0:02:50 lr: 0.000072 loss: 3.0594 (3.0472) grad: 0.0633 (0.0635) time: 0.3839 data: 0.0034 max mem: 3953 +train: [15] [ 60/400] eta: 0:02:29 lr: 0.000071 loss: 3.0351 (3.0397) grad: 0.0597 (0.0630) time: 0.3665 data: 0.0039 max mem: 3953 +train: [15] [ 80/400] eta: 0:02:17 lr: 0.000070 loss: 3.0234 (3.0347) grad: 0.0605 (0.0619) time: 0.4037 data: 0.0044 max mem: 3953 +train: [15] [100/400] eta: 0:02:04 lr: 0.000068 loss: 3.0349 (3.0406) grad: 0.0592 (0.0615) time: 0.3539 data: 0.0040 max mem: 3953 +train: [15] [120/400] eta: 0:01:54 lr: 0.000067 loss: 3.0371 (3.0387) grad: 0.0635 (0.0627) time: 0.3838 data: 0.0049 max mem: 3953 +train: [15] [140/400] eta: 0:01:45 lr: 0.000066 loss: 3.0193 (3.0379) grad: 0.0653 (0.0630) time: 0.3907 data: 0.0040 max mem: 3953 +train: [15] [160/400] eta: 0:01:36 lr: 0.000064 loss: 3.0370 (3.0390) grad: 0.0651 (0.0634) time: 0.3644 data: 0.0044 max mem: 3953 +train: [15] [180/400] eta: 0:01:27 lr: 0.000063 loss: 3.0596 (3.0425) grad: 0.0654 (0.0636) time: 0.3458 data: 0.0041 max mem: 3953 +train: [15] [200/400] eta: 0:01:18 lr: 0.000062 loss: 3.0662 (3.0444) grad: 0.0621 (0.0635) time: 0.3487 data: 0.0040 max mem: 3953 +train: [15] [220/400] eta: 0:01:10 lr: 0.000061 loss: 3.0483 (3.0440) grad: 0.0626 (0.0634) time: 0.3705 data: 0.0044 max mem: 3953 +train: [15] [240/400] eta: 0:01:01 lr: 0.000059 loss: 3.0477 (3.0443) grad: 0.0632 (0.0635) time: 0.3616 data: 0.0040 max mem: 3953 +train: [15] [260/400] eta: 0:00:53 lr: 0.000058 loss: 3.0495 (3.0457) grad: 0.0625 (0.0632) time: 0.3713 data: 0.0045 max mem: 3953 +train: [15] [280/400] eta: 0:00:46 lr: 0.000057 loss: 3.0502 (3.0477) grad: 0.0640 (0.0634) time: 0.3609 data: 0.0041 max mem: 3953 +train: [15] [300/400] eta: 0:00:38 lr: 0.000056 loss: 3.0499 (3.0489) grad: 0.0649 (0.0634) time: 0.3470 data: 0.0043 max mem: 3953 +train: [15] [320/400] eta: 0:00:30 lr: 0.000054 loss: 3.0579 (3.0499) grad: 0.0649 (0.0635) time: 0.3516 data: 0.0042 max mem: 3953 +train: [15] [340/400] eta: 0:00:22 lr: 0.000053 loss: 3.0528 (3.0484) grad: 0.0633 (0.0635) time: 0.3533 data: 0.0042 max mem: 3953 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 3.0620 (3.0501) grad: 0.0610 (0.0633) time: 0.3509 data: 0.0041 max mem: 3953 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 3.0495 (3.0498) grad: 0.0610 (0.0633) time: 0.3408 data: 0.0042 max mem: 3953 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 3.0495 (3.0504) grad: 0.0630 (0.0633) time: 0.3491 data: 0.0043 max mem: 3953 +train: [15] Total time: 0:02:29 (0.3738 s / it) +train: [15] Summary: lr: 0.000050 loss: 3.0495 (3.0504) grad: 0.0630 (0.0633) +eval (validation): [15] [ 0/85] eta: 0:05:00 time: 3.5367 data: 3.2884 max mem: 3953 +eval (validation): [15] [20/85] eta: 0:00:34 time: 0.3817 data: 0.0054 max mem: 3953 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3430 data: 0.0039 max mem: 3953 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3536 data: 0.0043 max mem: 3953 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3562 data: 0.0046 max mem: 3953 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3664 data: 0.0044 max mem: 3953 +eval (validation): [15] Total time: 0:00:33 (0.3990 s / it) +cv: [15] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 3.033 acc: 0.105 f1: 0.056 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:24:23 lr: nan time: 3.6593 data: 3.3534 max mem: 3953 +train: [16] [ 20/400] eta: 0:03:25 lr: 0.000048 loss: 3.0406 (3.0510) grad: 0.0574 (0.0592) time: 0.3861 data: 0.0043 max mem: 3953 +train: [16] [ 40/400] eta: 0:02:45 lr: 0.000047 loss: 3.0544 (3.0509) grad: 0.0591 (0.0620) time: 0.3732 data: 0.0040 max mem: 3953 +train: [16] [ 60/400] eta: 0:02:29 lr: 0.000046 loss: 3.0577 (3.0604) grad: 0.0649 (0.0634) time: 0.4012 data: 0.0046 max mem: 3953 +train: [16] [ 80/400] eta: 0:02:16 lr: 0.000045 loss: 3.0551 (3.0501) grad: 0.0619 (0.0629) time: 0.3831 data: 0.0043 max mem: 3953 +train: [16] [100/400] eta: 0:02:05 lr: 0.000044 loss: 3.0551 (3.0567) grad: 0.0630 (0.0639) time: 0.3808 data: 0.0044 max mem: 3953 +train: [16] [120/400] eta: 0:01:53 lr: 0.000043 loss: 3.0577 (3.0552) grad: 0.0632 (0.0639) time: 0.3506 data: 0.0045 max mem: 3953 +train: [16] [140/400] eta: 0:01:43 lr: 0.000042 loss: 3.0524 (3.0547) grad: 0.0621 (0.0639) time: 0.3352 data: 0.0038 max mem: 3953 +train: [16] [160/400] eta: 0:01:33 lr: 0.000041 loss: 3.0604 (3.0565) grad: 0.0606 (0.0638) time: 0.3282 data: 0.0044 max mem: 3953 +train: [16] [180/400] eta: 0:01:24 lr: 0.000040 loss: 3.0683 (3.0586) grad: 0.0627 (0.0636) time: 0.3537 data: 0.0041 max mem: 3953 +train: [16] [200/400] eta: 0:01:16 lr: 0.000039 loss: 3.0582 (3.0585) grad: 0.0627 (0.0637) time: 0.3763 data: 0.0044 max mem: 3953 +train: [16] [220/400] eta: 0:01:08 lr: 0.000038 loss: 3.0404 (3.0572) grad: 0.0630 (0.0634) time: 0.3601 data: 0.0039 max mem: 3953 +train: [16] [240/400] eta: 0:01:00 lr: 0.000036 loss: 3.0396 (3.0565) grad: 0.0630 (0.0637) time: 0.3558 data: 0.0041 max mem: 3953 +train: [16] [260/400] eta: 0:00:52 lr: 0.000035 loss: 3.0417 (3.0558) grad: 0.0648 (0.0639) time: 0.3609 data: 0.0043 max mem: 3953 +train: [16] [280/400] eta: 0:00:45 lr: 0.000034 loss: 3.0228 (3.0533) grad: 0.0630 (0.0636) time: 0.3480 data: 0.0047 max mem: 3953 +train: [16] [300/400] eta: 0:00:37 lr: 0.000033 loss: 3.0333 (3.0524) grad: 0.0605 (0.0635) time: 0.3527 data: 0.0045 max mem: 3953 +train: [16] [320/400] eta: 0:00:29 lr: 0.000032 loss: 3.0528 (3.0535) grad: 0.0622 (0.0635) time: 0.3623 data: 0.0038 max mem: 3953 +train: [16] [340/400] eta: 0:00:22 lr: 0.000031 loss: 3.0525 (3.0517) grad: 0.0595 (0.0631) time: 0.3590 data: 0.0041 max mem: 3953 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 3.0364 (3.0516) grad: 0.0591 (0.0632) time: 0.3776 data: 0.0046 max mem: 3953 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 3.0364 (3.0511) grad: 0.0609 (0.0631) time: 0.3475 data: 0.0043 max mem: 3953 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 3.0408 (3.0511) grad: 0.0615 (0.0631) time: 0.3730 data: 0.0046 max mem: 3953 +train: [16] Total time: 0:02:28 (0.3718 s / it) +train: [16] Summary: lr: 0.000029 loss: 3.0408 (3.0511) grad: 0.0615 (0.0631) +eval (validation): [16] [ 0/85] eta: 0:04:57 time: 3.4989 data: 3.2529 max mem: 3953 +eval (validation): [16] [20/85] eta: 0:00:36 time: 0.4079 data: 0.0041 max mem: 3953 +eval (validation): [16] [40/85] eta: 0:00:20 time: 0.3299 data: 0.0038 max mem: 3953 +eval (validation): [16] [60/85] eta: 0:00:10 time: 0.3176 data: 0.0043 max mem: 3953 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3379 data: 0.0039 max mem: 3953 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3350 data: 0.0038 max mem: 3953 +eval (validation): [16] Total time: 0:00:32 (0.3868 s / it) +cv: [16] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.027 acc: 0.110 f1: 0.061 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:23:36 lr: nan time: 3.5423 data: 3.2834 max mem: 3953 +train: [17] [ 20/400] eta: 0:03:18 lr: 0.000028 loss: 3.0577 (3.0473) grad: 0.0639 (0.0620) time: 0.3709 data: 0.0039 max mem: 3953 +train: [17] [ 40/400] eta: 0:02:41 lr: 0.000027 loss: 3.0629 (3.0576) grad: 0.0651 (0.0641) time: 0.3702 data: 0.0035 max mem: 3953 +train: [17] [ 60/400] eta: 0:02:24 lr: 0.000026 loss: 3.0700 (3.0643) grad: 0.0651 (0.0637) time: 0.3748 data: 0.0042 max mem: 3953 +train: [17] [ 80/400] eta: 0:02:14 lr: 0.000025 loss: 3.0569 (3.0584) grad: 0.0602 (0.0634) time: 0.4058 data: 0.0042 max mem: 3953 +train: [17] [100/400] eta: 0:02:02 lr: 0.000024 loss: 3.0241 (3.0541) grad: 0.0612 (0.0633) time: 0.3693 data: 0.0043 max mem: 3953 +train: [17] [120/400] eta: 0:01:52 lr: 0.000023 loss: 3.0276 (3.0500) grad: 0.0619 (0.0632) time: 0.3584 data: 0.0040 max mem: 3953 +train: [17] [140/400] eta: 0:01:42 lr: 0.000023 loss: 3.0347 (3.0515) grad: 0.0650 (0.0638) time: 0.3598 data: 0.0038 max mem: 3953 +train: [17] [160/400] eta: 0:01:33 lr: 0.000022 loss: 3.0469 (3.0510) grad: 0.0684 (0.0643) time: 0.3647 data: 0.0046 max mem: 3953 +train: [17] [180/400] eta: 0:01:26 lr: 0.000021 loss: 3.0641 (3.0527) grad: 0.0668 (0.0645) time: 0.3978 data: 0.0038 max mem: 3953 +train: [17] [200/400] eta: 0:01:18 lr: 0.000020 loss: 3.0555 (3.0516) grad: 0.0663 (0.0646) time: 0.3782 data: 0.0041 max mem: 3953 +train: [17] [220/400] eta: 0:01:09 lr: 0.000019 loss: 3.0394 (3.0501) grad: 0.0656 (0.0648) time: 0.3697 data: 0.0040 max mem: 3953 +train: [17] [240/400] eta: 0:01:01 lr: 0.000019 loss: 3.0436 (3.0508) grad: 0.0606 (0.0646) time: 0.3675 data: 0.0041 max mem: 3953 +train: [17] [260/400] eta: 0:00:53 lr: 0.000018 loss: 3.0458 (3.0512) grad: 0.0600 (0.0642) time: 0.3491 data: 0.0037 max mem: 3953 +train: [17] [280/400] eta: 0:00:45 lr: 0.000017 loss: 3.0398 (3.0496) grad: 0.0590 (0.0638) time: 0.3661 data: 0.0041 max mem: 3953 +train: [17] [300/400] eta: 0:00:38 lr: 0.000016 loss: 3.0432 (3.0496) grad: 0.0627 (0.0639) time: 0.3659 data: 0.0038 max mem: 3953 +train: [17] [320/400] eta: 0:00:30 lr: 0.000016 loss: 3.0506 (3.0491) grad: 0.0644 (0.0639) time: 0.3617 data: 0.0040 max mem: 3953 +train: [17] [340/400] eta: 0:00:22 lr: 0.000015 loss: 3.0389 (3.0475) grad: 0.0626 (0.0638) time: 0.3542 data: 0.0039 max mem: 3953 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 3.0251 (3.0481) grad: 0.0638 (0.0638) time: 0.3619 data: 0.0042 max mem: 3953 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 3.0468 (3.0486) grad: 0.0638 (0.0638) time: 0.3397 data: 0.0037 max mem: 3953 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 3.0351 (3.0470) grad: 0.0619 (0.0636) time: 0.3593 data: 0.0041 max mem: 3953 +train: [17] Total time: 0:02:30 (0.3756 s / it) +train: [17] Summary: lr: 0.000013 loss: 3.0351 (3.0470) grad: 0.0619 (0.0636) +eval (validation): [17] [ 0/85] eta: 0:04:58 time: 3.5093 data: 3.2566 max mem: 3953 +eval (validation): [17] [20/85] eta: 0:00:33 time: 0.3691 data: 0.0055 max mem: 3953 +eval (validation): [17] [40/85] eta: 0:00:19 time: 0.3610 data: 0.0041 max mem: 3953 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.3287 data: 0.0039 max mem: 3953 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3465 data: 0.0039 max mem: 3953 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3353 data: 0.0035 max mem: 3953 +eval (validation): [17] Total time: 0:00:33 (0.3895 s / it) +cv: [17] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.023 acc: 0.108 f1: 0.059 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:26:06 lr: nan time: 3.9169 data: 3.6756 max mem: 3953 +train: [18] [ 20/400] eta: 0:03:34 lr: 0.000012 loss: 3.0191 (3.0301) grad: 0.0612 (0.0623) time: 0.3979 data: 0.0220 max mem: 3953 +train: [18] [ 40/400] eta: 0:02:52 lr: 0.000012 loss: 3.0415 (3.0589) grad: 0.0622 (0.0632) time: 0.3892 data: 0.0042 max mem: 3953 +train: [18] [ 60/400] eta: 0:02:30 lr: 0.000011 loss: 3.0682 (3.0563) grad: 0.0620 (0.0620) time: 0.3685 data: 0.0031 max mem: 3953 +train: [18] [ 80/400] eta: 0:02:15 lr: 0.000011 loss: 3.0470 (3.0535) grad: 0.0618 (0.0626) time: 0.3667 data: 0.0043 max mem: 3953 +train: [18] [100/400] eta: 0:02:04 lr: 0.000010 loss: 3.0584 (3.0548) grad: 0.0626 (0.0631) time: 0.3806 data: 0.0044 max mem: 3953 +train: [18] [120/400] eta: 0:01:54 lr: 0.000009 loss: 3.0527 (3.0545) grad: 0.0626 (0.0626) time: 0.3692 data: 0.0039 max mem: 3953 +train: [18] [140/400] eta: 0:01:44 lr: 0.000009 loss: 3.0285 (3.0484) grad: 0.0611 (0.0625) time: 0.3520 data: 0.0042 max mem: 3953 +train: [18] [160/400] eta: 0:01:34 lr: 0.000008 loss: 3.0269 (3.0475) grad: 0.0607 (0.0622) time: 0.3330 data: 0.0041 max mem: 3953 +train: [18] [180/400] eta: 0:01:25 lr: 0.000008 loss: 3.0363 (3.0465) grad: 0.0592 (0.0622) time: 0.3646 data: 0.0042 max mem: 3953 +train: [18] [200/400] eta: 0:01:17 lr: 0.000007 loss: 3.0555 (3.0491) grad: 0.0647 (0.0628) time: 0.3744 data: 0.0042 max mem: 3953 +train: [18] [220/400] eta: 0:01:09 lr: 0.000007 loss: 3.0666 (3.0496) grad: 0.0625 (0.0626) time: 0.3600 data: 0.0038 max mem: 3953 +train: [18] [240/400] eta: 0:01:01 lr: 0.000006 loss: 3.0462 (3.0479) grad: 0.0584 (0.0623) time: 0.3495 data: 0.0040 max mem: 3953 +train: [18] [260/400] eta: 0:00:53 lr: 0.000006 loss: 3.0299 (3.0459) grad: 0.0592 (0.0623) time: 0.3745 data: 0.0041 max mem: 3953 +train: [18] [280/400] eta: 0:00:45 lr: 0.000006 loss: 3.0315 (3.0450) grad: 0.0607 (0.0621) time: 0.3768 data: 0.0044 max mem: 3953 +train: [18] [300/400] eta: 0:00:38 lr: 0.000005 loss: 3.0372 (3.0450) grad: 0.0592 (0.0621) time: 0.3712 data: 0.0040 max mem: 3953 +train: [18] [320/400] eta: 0:00:30 lr: 0.000005 loss: 3.0517 (3.0469) grad: 0.0613 (0.0621) time: 0.3603 data: 0.0039 max mem: 3953 +train: [18] [340/400] eta: 0:00:22 lr: 0.000004 loss: 3.0517 (3.0475) grad: 0.0613 (0.0621) time: 0.3714 data: 0.0042 max mem: 3953 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 3.0449 (3.0477) grad: 0.0641 (0.0623) time: 0.3797 data: 0.0041 max mem: 3953 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 3.0449 (3.0474) grad: 0.0641 (0.0622) time: 0.3617 data: 0.0042 max mem: 3953 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 3.0545 (3.0484) grad: 0.0588 (0.0620) time: 0.3664 data: 0.0043 max mem: 3953 +train: [18] Total time: 0:02:30 (0.3775 s / it) +train: [18] Summary: lr: 0.000003 loss: 3.0545 (3.0484) grad: 0.0588 (0.0620) +eval (validation): [18] [ 0/85] eta: 0:05:31 time: 3.9052 data: 3.5606 max mem: 3953 +eval (validation): [18] [20/85] eta: 0:00:38 time: 0.4257 data: 0.0032 max mem: 3953 +eval (validation): [18] [40/85] eta: 0:00:21 time: 0.3655 data: 0.0051 max mem: 3953 +eval (validation): [18] [60/85] eta: 0:00:10 time: 0.3495 data: 0.0047 max mem: 3953 +eval (validation): [18] [80/85] eta: 0:00:02 time: 0.3479 data: 0.0044 max mem: 3953 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3490 data: 0.0042 max mem: 3953 +eval (validation): [18] Total time: 0:00:35 (0.4162 s / it) +cv: [18] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.020 acc: 0.112 f1: 0.064 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:24:54 lr: nan time: 3.7354 data: 3.4869 max mem: 3953 +train: [19] [ 20/400] eta: 0:03:26 lr: 0.000003 loss: 3.0570 (3.0583) grad: 0.0632 (0.0643) time: 0.3830 data: 0.0033 max mem: 3953 +train: [19] [ 40/400] eta: 0:02:45 lr: 0.000003 loss: 3.0545 (3.0495) grad: 0.0625 (0.0625) time: 0.3738 data: 0.0038 max mem: 3953 +train: [19] [ 60/400] eta: 0:02:26 lr: 0.000002 loss: 3.0545 (3.0513) grad: 0.0602 (0.0616) time: 0.3740 data: 0.0040 max mem: 3953 +train: [19] [ 80/400] eta: 0:02:15 lr: 0.000002 loss: 3.0481 (3.0459) grad: 0.0598 (0.0612) time: 0.3984 data: 0.0040 max mem: 3953 +train: [19] [100/400] eta: 0:02:04 lr: 0.000002 loss: 3.0394 (3.0447) grad: 0.0608 (0.0616) time: 0.3733 data: 0.0041 max mem: 3953 +train: [19] [120/400] eta: 0:01:52 lr: 0.000002 loss: 3.0514 (3.0478) grad: 0.0630 (0.0614) time: 0.3439 data: 0.0039 max mem: 3953 +train: [19] [140/400] eta: 0:01:43 lr: 0.000001 loss: 3.0689 (3.0494) grad: 0.0620 (0.0618) time: 0.3786 data: 0.0041 max mem: 3953 +train: [19] [160/400] eta: 0:01:35 lr: 0.000001 loss: 3.0714 (3.0528) grad: 0.0641 (0.0621) time: 0.3843 data: 0.0041 max mem: 3953 +train: [19] [180/400] eta: 0:01:27 lr: 0.000001 loss: 3.0865 (3.0572) grad: 0.0639 (0.0620) time: 0.4142 data: 0.0041 max mem: 3953 +train: [19] [200/400] eta: 0:01:19 lr: 0.000001 loss: 3.0776 (3.0563) grad: 0.0606 (0.0620) time: 0.3905 data: 0.0043 max mem: 3953 +train: [19] [220/400] eta: 0:01:11 lr: 0.000001 loss: 3.0370 (3.0558) grad: 0.0623 (0.0622) time: 0.3623 data: 0.0040 max mem: 3953 +train: [19] [240/400] eta: 0:01:02 lr: 0.000001 loss: 3.0408 (3.0555) grad: 0.0628 (0.0623) time: 0.3719 data: 0.0040 max mem: 3953 +train: [19] [260/400] eta: 0:00:54 lr: 0.000000 loss: 3.0338 (3.0538) grad: 0.0652 (0.0626) time: 0.3563 data: 0.0041 max mem: 3953 +train: [19] [280/400] eta: 0:00:46 lr: 0.000000 loss: 3.0281 (3.0532) grad: 0.0615 (0.0623) time: 0.3728 data: 0.0041 max mem: 3953 +train: [19] [300/400] eta: 0:00:38 lr: 0.000000 loss: 3.0416 (3.0534) grad: 0.0622 (0.0625) time: 0.3552 data: 0.0040 max mem: 3953 +train: [19] [320/400] eta: 0:00:30 lr: 0.000000 loss: 3.0337 (3.0523) grad: 0.0660 (0.0627) time: 0.3498 data: 0.0041 max mem: 3953 +train: [19] [340/400] eta: 0:00:22 lr: 0.000000 loss: 3.0337 (3.0516) grad: 0.0663 (0.0629) time: 0.3457 data: 0.0038 max mem: 3953 +train: [19] [360/400] eta: 0:00:15 lr: 0.000000 loss: 3.0505 (3.0511) grad: 0.0638 (0.0630) time: 0.3414 data: 0.0041 max mem: 3953 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 3.0464 (3.0513) grad: 0.0635 (0.0630) time: 0.3351 data: 0.0038 max mem: 3953 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 3.0430 (3.0511) grad: 0.0596 (0.0629) time: 0.3352 data: 0.0038 max mem: 3953 +train: [19] Total time: 0:02:30 (0.3758 s / it) +train: [19] Summary: lr: 0.000000 loss: 3.0430 (3.0511) grad: 0.0596 (0.0629) +eval (validation): [19] [ 0/85] eta: 0:05:27 time: 3.8560 data: 3.5815 max mem: 3953 +eval (validation): [19] [20/85] eta: 0:00:32 time: 0.3319 data: 0.0038 max mem: 3953 +eval (validation): [19] [40/85] eta: 0:00:17 time: 0.2925 data: 0.0041 max mem: 3953 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3310 data: 0.0047 max mem: 3953 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.2981 data: 0.0043 max mem: 3953 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.2932 data: 0.0040 max mem: 3953 +eval (validation): [19] Total time: 0:00:30 (0.3581 s / it) +cv: [19] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.015 acc: 0.114 f1: 0.066 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +eval model info: +{"score": 0.11351052048726468, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 19, "is_best": false, "best_score": 0.11517165005537099} +eval (train): [20] [ 0/509] eta: 0:29:32 time: 3.4825 data: 3.2764 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:03:49 time: 0.3186 data: 0.0040 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:03:06 time: 0.3229 data: 0.0062 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:02:44 time: 0.3004 data: 0.0041 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:33 time: 0.3345 data: 0.0240 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:22 time: 0.3144 data: 0.0033 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:17 time: 0.3697 data: 0.0050 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:09 time: 0.3335 data: 0.0044 max mem: 3953 +eval (train): [20] [160/509] eta: 0:02:02 time: 0.3460 data: 0.0041 max mem: 3953 +eval (train): [20] [180/509] eta: 0:01:54 time: 0.3235 data: 0.0046 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:46 time: 0.3181 data: 0.0039 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:38 time: 0.3195 data: 0.0052 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:31 time: 0.3307 data: 0.0034 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:24 time: 0.3350 data: 0.0043 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:17 time: 0.3411 data: 0.0042 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:11 time: 0.3508 data: 0.0047 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:04 time: 0.3524 data: 0.0043 max mem: 3953 +eval (train): [20] [340/509] eta: 0:00:57 time: 0.3256 data: 0.0044 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:50 time: 0.3255 data: 0.0041 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:43 time: 0.3208 data: 0.0040 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:36 time: 0.3363 data: 0.0042 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:30 time: 0.3679 data: 0.0053 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3207 data: 0.0043 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3226 data: 0.0042 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.2886 data: 0.0038 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.2864 data: 0.0039 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2887 data: 0.0038 max mem: 3953 +eval (train): [20] Total time: 0:02:50 (0.3351 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:49 time: 3.4112 data: 3.1242 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:36 time: 0.4185 data: 0.0043 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:20 time: 0.3503 data: 0.0051 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3090 data: 0.0043 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3204 data: 0.0045 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3154 data: 0.0041 max mem: 3953 +eval (validation): [20] Total time: 0:00:32 (0.3868 s / it) +eval (test): [20] [ 0/85] eta: 0:04:57 time: 3.5011 data: 3.2164 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3202 data: 0.0043 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3302 data: 0.0050 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3052 data: 0.0038 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3011 data: 0.0041 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2907 data: 0.0039 max mem: 3953 +eval (test): [20] Total time: 0:00:29 (0.3522 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:44 time: 3.4753 data: 3.1963 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:32 time: 0.3804 data: 0.0056 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.3252 data: 0.0037 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3068 data: 0.0041 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3177 data: 0.0039 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3079 data: 0.0034 max mem: 3953 +eval (testid): [20] Total time: 0:00:30 (0.3722 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +eval model info: +{"score": 0.11517165005537099, "hparam": [36, 1.0], "hparam_id": 46, "epoch": 12, "is_best": true, "best_score": 0.11517165005537099} +eval (train): [20] [ 0/509] eta: 0:28:12 time: 3.3252 data: 3.0939 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:04:05 time: 0.3607 data: 0.0394 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:03:15 time: 0.3268 data: 0.0036 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:02:58 time: 0.3568 data: 0.0048 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:42 time: 0.3223 data: 0.0039 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:32 time: 0.3559 data: 0.0048 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:24 time: 0.3534 data: 0.0044 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:15 time: 0.3381 data: 0.0045 max mem: 3953 +eval (train): [20] [160/509] eta: 0:02:07 time: 0.3602 data: 0.0043 max mem: 3953 +eval (train): [20] [180/509] eta: 0:01:58 time: 0.3329 data: 0.0044 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:50 time: 0.3232 data: 0.0045 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:42 time: 0.3338 data: 0.0039 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:35 time: 0.3494 data: 0.0044 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:27 time: 0.3323 data: 0.0041 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:20 time: 0.3272 data: 0.0048 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:13 time: 0.3300 data: 0.0041 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:06 time: 0.3626 data: 0.0044 max mem: 3953 +eval (train): [20] [340/509] eta: 0:00:59 time: 0.3349 data: 0.0045 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:52 time: 0.3376 data: 0.0044 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:45 time: 0.3503 data: 0.0048 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:38 time: 0.3407 data: 0.0041 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3561 data: 0.0043 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3438 data: 0.0041 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3564 data: 0.0043 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3442 data: 0.0042 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3049 data: 0.0044 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2832 data: 0.0040 max mem: 3953 +eval (train): [20] Total time: 0:02:56 (0.3476 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:50 time: 3.4141 data: 3.1282 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3418 data: 0.0052 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3380 data: 0.0038 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3221 data: 0.0035 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.2953 data: 0.0038 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2927 data: 0.0038 max mem: 3953 +eval (validation): [20] Total time: 0:00:30 (0.3624 s / it) +eval (test): [20] [ 0/85] eta: 0:04:45 time: 3.3590 data: 3.1290 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:34 time: 0.3877 data: 0.0183 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3478 data: 0.0036 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3390 data: 0.0046 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3190 data: 0.0040 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2962 data: 0.0037 max mem: 3953 +eval (test): [20] Total time: 0:00:32 (0.3832 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:37 time: 3.3865 data: 3.1487 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:34 time: 0.4225 data: 0.0191 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:19 time: 0.3686 data: 0.0044 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3402 data: 0.0042 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.2933 data: 0.0038 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2825 data: 0.0037 max mem: 3953 +eval (testid): [20] Total time: 0:00:32 (0.3933 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-------:|--------:|----------:|---------:|----------:| +| flat_mae | patch | linear | nsd_cococlip | best | 12 | 0.0108 | 0.05 | 46 | [36, 1.0] | train | 2.9562 | 0.13442 | 0.00164 | 0.073603 | 0.0011895 | +| flat_mae | patch | linear | nsd_cococlip | best | 12 | 0.0108 | 0.05 | 46 | [36, 1.0] | validation | 3.05 | 0.11517 | 0.0037074 | 0.056893 | 0.0025099 | +| flat_mae | patch | linear | nsd_cococlip | best | 12 | 0.0108 | 0.05 | 46 | [36, 1.0] | test | 3.0346 | 0.11707 | 0.003631 | 0.050479 | 0.0020236 | +| flat_mae | patch | linear | nsd_cococlip | best | 12 | 0.0108 | 0.05 | 46 | [36, 1.0] | testid | 3.0452 | 0.10777 | 0.0037217 | 0.055349 | 0.0025538 | + + +done! total time: 1:11:03 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/train_log.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..e6bbf7758ce9d6090cac361116d0f8aeaf749f99 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__patch__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.162961667776108, "train/grad": 0.07338828312233091, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.184447021484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.184359130859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1841943359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.184022216796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1838330078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.18366455078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.18341064453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.183167724609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1827880859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.182440185546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.18203857421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.181507568359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1809619140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1801611328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.17942138671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1786669921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.177745361328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.17655029296875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.17522705078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.173924560546875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.172373046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.170721435546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.168861083984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.166983642578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.16487060546875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.162586669921875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.16058349609375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.15880615234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.156700439453125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.154415283203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.152674560546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1511669921875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.149559326171875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.148265380859375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.14683837890625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.145562744140625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.14447509765625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.14353515625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.142706298828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.14177490234375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1411572265625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.140740966796875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.140196533203125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.13987060546875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.13949462890625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.139234619140625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.13927734375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.139375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.13978515625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011209654610138387, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011206636640708893, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011201510347891599, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011196326238568872, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01119122948963195, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011184321369510144, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011176391940098255, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011167597100138664, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011155574151780456, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011142866921145468, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011130165359936654, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011110713121015579, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011092055244371296, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011064448449760676, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011037117603700608, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011010168497450649, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010975688223261386, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010934237968176603, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01088626596610993, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01084083409048617, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010782808372750878, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010721457151230424, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010652118199504911, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010577905112877489, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010501018052455038, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010412142586428672, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010335572671610862, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010269776559434831, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010187703738920391, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010101992818526924, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010034985672682524, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009982408389914781, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00992143022827804, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00987433404661715, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009826712023932488, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009786597557831556, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009751820112578571, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009723667996004224, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009700081574264914, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009678174932487309, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009667033152654768, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009661553699988872, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009661209578625858, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009667495035100728, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009684483271557838, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009714095683302731, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009751509544439613, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009810469821095466, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009869170158635825, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.184032917022705, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1837382316589355, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1832239627838135, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.182727098464966, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.182248830795288, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1815743446350098, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1808300018310547, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1799705028533936, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1788251399993896, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.177645683288574, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1764893531799316, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1747066974639893, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1730170249938965, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.170557737350464, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.168215751647949, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.165987253189087, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.16313099861145, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1598360538482666, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1561851501464844, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.152862071990967, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1489291191101074, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.145047187805176, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1410186290740967, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.137120008468628, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1335854530334473, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1300878524780273, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1276423931121826, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.125920295715332, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.124222755432129, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1229538917541504, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.122286319732666, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.121857166290283, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1214206218719482, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1211049556732178, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1207499504089355, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.120518684387207, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1204240322113037, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.120579242706299, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.121131658554077, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1225976943969727, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.124271869659424, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1260454654693604, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.128520965576172, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1306204795837402, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1329257488250732, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.135084390640259, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1363821029663086, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1369428634643555, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1362526416778564, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.027316352897748246, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.027131782945736434, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.027131782945736434, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.027500922849760058, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.02768549280177187, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.027870062753783682, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.029715762273901807, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.03156146179401993, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.03414544112218531, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.03433001107419712, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.035622000738279806, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.04023624953857512, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.04171280915466962, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.046511627906976744, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.05204872646733112, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.054817275747508304, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.056109265411590996, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.05666297526762643, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.05721668512366187, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.058508674787744554, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.05832410483573274, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06201550387596899, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06386120339608711, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06109265411590993, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06035437430786268, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.059616094499815434, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.05887781469176818, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.059616094499815434, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06090808416389812, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06293835363602805, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06312292358803986, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.062200073827980804, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011759836030769535, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011670620707794671, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011911611821421433, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012165882723461988, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012091214488879587, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012240635260754066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013588919670633052, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014579636242667315, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01597884344669868, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015347018939942675, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.015726217600213005, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.016847491348775747, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017831488564886477, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.018857231753966388, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.020276245394573126, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01941014268310161, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.016374136293800984, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014961961782410034, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014601503317105939, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.012967703969443077, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.012418125659651084, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01294369983542383, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013209731578263441, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012011153294668687, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.011242365732768829, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.010683723801659066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009975985177694907, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009881717778386213, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.009796171973337415, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.010157873787613209, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.010078370310192977, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009951185979106145, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.009752915869838013, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01007257457907685, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.009459545293167415, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.008508564857806641, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.008472330816872582, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.009776369271492622, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.011131703985626908, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.01192988254677142, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.010790482160935382, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.00943809616468448, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.008435692269615413, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.007407559921022291, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.007074009376098978, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.00839636366268149, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.00951499155147883, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.01000281976463215, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.010102866585139033, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 3.154415283203125, "validation/loss_best": 3.1229538917541504, "validation/acc_best": 0.06902916205241787, "validation/f1_best": 0.010157873787613209} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.140995478630066, "train/grad": 0.06875521874055267, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1806396484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1799853515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17900634765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.178121337890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.177117919921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.175843505859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.17440185546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.172843017578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.17080078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1687890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.166796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.16400390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.161490478515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.15799560546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.154862060546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.15217041015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1489208984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.145650634765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1423974609375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.139871826171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.137117919921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1350244140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.13301513671875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.131396484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.130274658203125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.129134521484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12843505859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1279052734375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.12735595703125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12664794921875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.126273193359375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.125797119140625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.12524658203125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.124774169921875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1240966796875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.123502197265625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.122784423828125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1222412109375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.12158935546875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.120859375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.120142822265625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.11962646484375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1189739990234373, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1186029052734376, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1181231689453126, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1180322265625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1183538818359375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.119769287109375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.121976318359375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01094911884982139, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010927818189375103, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010892718597315252, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010858554721344262, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010824552837293595, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010778473089449108, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01072777037974447, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010671650785952806, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010599645639304071, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010525603070855141, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010454207160510123, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010349944399204105, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01025306577095762, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01012014196254313, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010000893066171556, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009894952168688178, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009770898048300296, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009639719210099429, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009512609350495041, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009411596260033548, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00930852112127468, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009224357013590635, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009152759755961597, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00909809913719073, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009059858326800167, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009032720485702157, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009021434658207, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00901816833531484, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009022044446319342, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009034024286083877, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009049569335766137, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009066834056284279, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009093282553367317, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009119809097610414, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009154383691493422, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009192283120937646, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009238106883130967, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009285944669973106, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009343845807015895, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009427815538365393, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009499911633320153, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009568021756131202, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009662734386511147, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009749752767384053, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00985725572798401, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00998556132428348, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010114413506817072, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010306069788057357, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010515926447696984, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1782174110412598, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1771388053894043, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1753249168395996, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1736042499542236, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1719326972961426, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.169658660888672, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1671793460845947, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.164558172225952, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1612868309020996, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1579861640930176, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.154944658279419, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1507678031921387, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.147118091583252, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1424577236175537, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1386351585388184, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1355550289154053, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1323280334472656, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.129382848739624, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1270058155059814, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1254844665527344, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.124264717102051, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.123507499694824, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1230530738830566, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1228299140930176, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1227152347564697, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.122609853744507, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1225361824035645, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1224405765533447, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.122225284576416, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.121939182281494, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1215713024139404, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.121199131011963, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1206107139587402, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1201765537261963, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.119821310043335, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1198039054870605, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.120084047317505, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1205074787139893, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1211140155792236, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.122168779373169, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1238746643066406, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1265177726745605, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1310460567474365, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1348233222961426, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.139692783355713, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1476047039031982, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1555070877075195, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1629931926727295, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.165971040725708, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.03359173126614987, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.03506829088224437, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.03783684016242156, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.04023624953857512, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.04226651901070506, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.050387596899224806, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05370985603543743, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.05758582502768549, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.060723514211886306, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07290513104466592, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07401255075673681, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.073827980804725, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07419712070874862, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0769656699889258, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0754891103728313, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07936507936507936, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07899593946105574, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07881136950904392, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07327427094868956, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01510602835416095, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.015462671596247812, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015614531634281498, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016911315547606647, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01679913053105499, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.019730791925940912, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.018661975292958016, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01855500859814838, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.015099493751350597, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014468701041554734, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014483756238028429, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012780679748740734, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013682390892869302, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013803920237695777, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012969971600968716, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012592168718932309, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012387592800411752, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01140990608553076, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.010450346287793023, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009236222475862279, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008761858267998869, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.006817155788311956, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005650744948371016, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.00537765519702123, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.00519109805989543, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.005006459948320414, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0058785041498442304, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0065598831005256745, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.007974785742900156, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.011888213006801027, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.014182508336966224, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.01628725809473194, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.01777646826746776, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.018918164621708245, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01984486051039675, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.02121463368609421, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.024087726412014846, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.024535405234797216, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.024135862062654685, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.02254055396482427, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02348677627348662, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.023663579394060403, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.023631987892923697, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.023842345766356843, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.021621191786781974, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.022553631615206085, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02431496703232422, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.02779117789246895, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03060604822801705, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.1180322265625, "validation/loss_best": 3.1476047039031982, "validation/acc_best": 0.07936507936507936, "validation/f1_best": 0.022553631615206085} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.1308220911026, "train/grad": 0.0671437562815845, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.174049072265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.17261474609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17039306640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.16837890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.166392822265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.163963623046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.161248779296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.158475341796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.15521484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.15216064453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.14953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1460595703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.14343994140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.140413818359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.138232421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.136685791015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1352490234375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.134111328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.133326416015625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.132841796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.132259521484375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.131788330078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.13130859375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.13072021484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1301025390625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.12917724609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12838623046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1276220703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.126448974609375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12499267578125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.123681640625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.12239990234375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.120665283203125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.119273681640625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1175390625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.115653076171875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.113385009765625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1112158203125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1086297607421876, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1057373046875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1036553955078126, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.102213134765625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.100736083984375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.099927978515625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1000103759765625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1013055419921876, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1033599853515623, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.106199951171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1091070556640625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010629648317117244, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01057930130744353, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010498077103402465, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01042061861604452, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01034668285632506, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010248426655307412, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010142243553418665, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010031675139907747, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009899019370786846, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00977222652407363, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009661430353298783, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009518485087901353, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009402823846321552, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009269703049212694, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00917506230995059, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009107552322093397, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00904681506101042, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00900147452019155, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008973810791503637, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008960839970968663, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008954021472018212, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008953544883988798, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008956370747182519, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008961398408282549, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008967441283166408, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008976180381141603, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008984486602712423, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008992788416799158, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00900536454282701, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00902161124860868, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009037561565637588, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009053761423565447, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009079558006487787, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009106304633896799, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009142632763832807, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009183840190526099, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009232943970710039, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009286264777183533, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009354587765410543, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00946268395287916, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009563942963723093, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009666668237186968, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009812487396411598, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00994769342476502, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010117226545698941, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010331450912635773, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010547136308159679, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010816161362454295, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011066990632098168, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1697654724121094, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1676957607269287, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1644248962402344, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1614086627960205, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1585700511932373, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.154930353164673, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.151219367980957, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.147524118423462, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1433334350585938, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.139552116394043, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.136462688446045, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.132758378982544, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1300482749938965, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.127268075942993, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.125478744506836, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1243197917938232, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123344659805298, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1226115226745605, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1220223903656006, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1216084957122803, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1211767196655273, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.120724678039551, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1202664375305176, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.119784355163574, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.119323492050171, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1187682151794434, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1183273792266846, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1179096698760986, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1173629760742188, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.116659641265869, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.115968942642212, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.115309238433838, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.11441969871521, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.11357045173645, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1124446392059326, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.110930919647217, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1088075637817383, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.106689453125, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.104830265045166, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.103600025177002, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1034200191497803, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.103654146194458, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1056716442108154, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1112592220306396, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.117126226425171, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.108870267868042, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.098670721054077, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.09794545173645, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1072142124176025, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04706533776301218, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.052417866371354746, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05629383536360281, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.058508674787744554, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.067921742340347, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07401255075673681, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07401255075673681, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07881136950904392, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08305647840531562, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08693244739756367, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08859357696567, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08471760797342193, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08453303802141011, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08379475821336287, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0843484680693983, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07881136950904392, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01806474878973296, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.018896583193671598, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.017981438336747507, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01563173917519134, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014313845306278826, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014298830297612272, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012766510360716507, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013453184680398798, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013632282133133411, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013374358572557409, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012976574082224489, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012038295575828471, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011315908992252871, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011111974026789572, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010638283756348649, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010431604992542323, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010281603949738325, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010119512285788633, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.010403368683369454, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010381578932117401, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010484287240048283, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010568379548472758, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.011490794321101621, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012766716230792952, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014435919989333565, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.015848952836607588, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01707287983245175, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.017236657366880365, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01906506031910123, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.01956206214336109, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.020707649588732065, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.02101564786866512, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.020154166887164832, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.019522643538877792, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0193910446592721, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.021198164370967595, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.023308800562032033, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.024046400618098502, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.027626427894007263, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.028144750011227137, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.030096243098802086, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.029678347429767393, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.032676964826472844, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03344620275432874, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03441487916136792, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.034225055575961935, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04205819821093529, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.046548228372086935, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04450322293847484, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 3.100736083984375, "validation/loss_best": 3.1056716442108154, "validation/acc_best": 0.08877814691768181, "validation/f1_best": 0.032676964826472844} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.125594643354416, "train/grad": 0.0679710958339274, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.166361083984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.16419189453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.160919189453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1579052734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.155294189453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.152017822265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.14893310546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.14578857421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1427294921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.140330810546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.138387451171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.136435546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.135008544921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.13390869140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.133282470703125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.132840576171875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.132379150390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.132022705078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.13155029296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1309912109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.130394287109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.129642333984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1287890625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.127811279296875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12670654296875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.12542236328125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.124034423828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.122899169921875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.121094970703125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.118853759765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1169775390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.11493408203125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.112427978515625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.110098876953125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1073394775390626, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1048565673828126, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.10238525390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1004498291015623, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.098604736328125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0972064208984373, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.09683349609375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0971356201171876, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.098807373046875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.101309814453125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1043707275390626, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1076092529296875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.11120849609375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1188055419921876, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.125853271484375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010449455499183387, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010367822835687547, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010239334863144904, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010121294751297683, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010013901004567742, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0098803992359899, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009749153999146075, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009625470121391118, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009492595323827117, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00938098484883085, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009297523947898298, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009208647792693227, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009151948848739266, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00910500964615494, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009082610928453505, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009072270449250937, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009067548995371908, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009067706861533225, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009071061084978283, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009075784010346978, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009082233500666916, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009089650583919138, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009099022031296044, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009109593397006392, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009121856198180466, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0091363409999758, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009150928610470146, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009165137456730008, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009185912352986634, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00921212171204388, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009237025841139257, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009261243720538914, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009296321549918503, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009330764873884618, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009376704092137516, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009430092531256378, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009500182785559445, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009582780310884118, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00969083935022354, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00985457256436348, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010005461045075208, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010150730281602592, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010358833896461875, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010554090114310384, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010768315952736885, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010975260781124234, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011158656547777354, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011456734002567828, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011734861629083753, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.160069704055786, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.157217264175415, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1528830528259277, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.149075508117676, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.145754814147949, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1417911052703857, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1380882263183594, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1347692012786865, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1314477920532227, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.128908395767212, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1270864009857178, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125298500061035, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1241884231567383, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123225688934326, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1226766109466553, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1223068237304688, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.12194561958313, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.121563196182251, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1211535930633545, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.12079119682312, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.120332717895508, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.119840621948242, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.119248867034912, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1185336112976074, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1176867485046387, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1165473461151123, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1153388023376465, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1141366958618164, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.112308979034424, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1098875999450684, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1073944568634033, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1049258708953857, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1013617515563965, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.098222494125366, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0949478149414062, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.092205286026001, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.090014696121216, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.088986396789551, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.089412212371826, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0921881198883057, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.093813896179199, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0942912101745605, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0947265625, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.092270851135254, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0929067134857178, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1065993309020996, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1182825565338135, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.117351531982422, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1215262413024902, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.067921742340347, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07954964931709117, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08139534883720931, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.082687338501292, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08250276854928018, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08471760797342193, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08693244739756367, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09117755629383537, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09357696566998892, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09043927648578812, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09394610557401255, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09892949427833149, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10428202288667406, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10225175341454411, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09671465485418974, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08822443706164636, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.014779780389893532, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014103693880448472, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013269455060068373, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012951646203511177, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013622413944736173, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013667988571954802, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01310409379681412, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012681685973816808, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01227774711050273, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011584023748245362, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011205743251757536, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010264030735716927, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010065737226858716, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009302510293189537, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00875186861677024, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007978919292724103, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006579132101118718, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005731693950350831, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005405653631182199, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005414883433101894, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005214628695466386, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005448069643581906, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005937720188537339, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005934484872995826, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006364785478348401, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0075060530875290426, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.00926483926998681, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.010147098580876916, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.013946753454791358, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.020309035409459542, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.022880598501052705, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.026348716027105392, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.027859210105311494, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.029138750711449196, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03133160308255389, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.032927160552490405, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.034602188010741004, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.037954066414949854, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03646626375052152, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.036822696843140275, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03733572116328516, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.035876205443157845, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.036636484266593834, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04261056208578707, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04673133405226588, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.047090397307060494, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04750071110678126, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04371059369307114, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.037638790340312686, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.1076092529296875, "validation/loss_best": 3.1065993309020996, "validation/acc_best": 0.10428202288667406, "validation/f1_best": 0.047090397307060494} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.1117060375213623, "train/grad": 0.06730935789644718, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.157086181640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.154306640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.15030517578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14704833984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14419921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.14093017578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1381982421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13587890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.133707275390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1321533203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.13109130859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.130087890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129427490234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128714599609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128150634765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.127564697265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126824951171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.125958251953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.124937744140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.123968505859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.122685546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12144287109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.119864501953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11813232421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.11620361328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.113822021484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.111605224609375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.10957275390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.106605224609375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1031689453125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.09989501953125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.097042236328125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0932513427734376, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.089974365234375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0864434814453126, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.083138427734375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.08017333984375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0776397705078127, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0754241943359375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0735894775390626, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0732403564453126, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0734881591796874, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0750616455078124, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0774285888671873, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0805670166015626, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0841433715820314, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0892755126953126, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0988348388671874, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1113455200195315, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010062183300033212, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00995326994685456, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00979445371311158, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009659949794877321, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009545979835093022, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009414482654538005, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009298031534999609, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009200102302711457, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009111648527905344, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009052570664789528, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009016105874907225, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008986372561194002, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008972118594683706, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008964001561980694, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00896267450414598, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008963168615009636, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008964996740687639, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008967381913680583, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00897061756812036, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00897352275904268, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008977516344748438, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008982609985396265, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008988508856855332, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008996297181583941, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009005869207903743, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00901881067082286, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009032363723963498, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009046313799917698, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009068039725534618, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00909654307179153, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009126132314559072, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009155562873929738, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0092022634181194, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00924940298544243, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009313658736646175, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009389356998726726, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009483284908346832, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009583306687418372, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009706199704669415, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009899866997729987, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0100809033238329, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010252522677183152, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010491785556077958, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010710378549993039, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010948365337681025, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011188909250777215, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011443630899302662, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01188105134293437, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01236741560511291, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1502323150634766, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.146970272064209, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1423192024230957, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.138545036315918, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1354966163635254, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.132195234298706, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1294355392456055, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1272761821746826, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1253955364227295, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124147415161133, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123349666595459, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.122584104537964, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.122087001800537, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1215436458587646, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121105909347534, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1207051277160645, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1202073097229004, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1196320056915283, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1189615726470947, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1183173656463623, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1174795627593994, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.116588830947876, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.115588426589966, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.114459991455078, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1133158206939697, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1119961738586426, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.110832452774048, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1097359657287598, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.108302116394043, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1065359115600586, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.104997158050537, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1036782264709473, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.102107524871826, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.100815534591675, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0992493629455566, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0968706607818604, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0922272205352783, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0862009525299072, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.080359935760498, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.076110601425171, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0755693912506104, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.080378293991089, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0941591262817383, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1050188541412354, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1180965900421143, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1362195014953613, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1561927795410156, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1760551929473877, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1869261264801025, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06976744186046512, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07124400147655961, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07235142118863049, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07862679955703211, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08656330749354005, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09136212624584718, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09191583610188261, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09080841638981174, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08914728682170543, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08748615725359911, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08397932816537468, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013218995662816145, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0139989890012131, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013469658166553789, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012987869060594294, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012181360811206104, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011693316150243974, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01095458168255274, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010415249783448783, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01007933812642432, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010081767262306536, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01016438258046032, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010258432794304589, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01020209673544979, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01050363173817391, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01035590741283144, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01060986015075237, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009962260451623909, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00970643038409016, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009044058342399157, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008953362873431844, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008470101620978355, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00782878117709722, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.008032378065240578, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.009066145324999777, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.009619889698793325, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.010035965885535012, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.010656101955382429, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.011759470491501556, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.012764477281674819, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.013550123437914174, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.013840558903703856, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.014396818384260518, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.014931511889253955, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01632724832539089, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01864926473821484, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.02009199665337449, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.02250828745155554, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02594519205786912, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03303067482585302, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03543857712503709, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03562891089453669, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.034123013160538125, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03203847670261128, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.032839853964953994, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03567733258603157, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03989198647621292, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.041500035404011267, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.041062805098364824, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03638668895914641, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 3.0734881591796874, "validation/loss_best": 3.080378293991089, "validation/acc_best": 0.09191583610188261, "validation/f1_best": 0.034123013160538125} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 3.101351680755615, "train/grad": 0.06716355778276921, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.147279052734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.144381103515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.140362548828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.137235107421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1349169921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1324853515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130555419921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12917236328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127998046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127188720703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126566162109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125887451171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12538818359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12460205078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12380126953125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12314697265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.122083740234375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12095458984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1195703125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.118187255859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.116510009765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11469482421875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11259521484375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.110203857421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.107713623046875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.104620361328125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1018017578125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.099376220703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.095814208984375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.09165771484375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.087987060546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.084647216796875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0803546142578124, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0765228271484375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0722308349609375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.06812255859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.06405029296875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.06045166015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0572998046875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.05451171875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.05349365234375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0536846923828125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0558261108398437, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0590939331054687, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0638473510742186, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.070504455566406, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0781588745117188, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0889460754394533, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.099751281738281, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009699720372445882, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009584198391530662, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009426753905136137, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009303736151196063, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00920771505916491, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009111732286401093, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009040560442954301, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008992530214600265, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00895772002870217, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008940441170707344, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008933136011473835, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008930531428195537, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008931212679017335, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008934053916018456, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00893731229705736, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008940181930083781, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008944380062166602, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008949604926165193, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00895522851496935, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008960691636893899, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008967158743180334, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00897480107145384, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008984003791119903, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008995398371480405, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009007941726595163, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009026727038435638, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009045582998078316, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009065887399483472, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009097021985799075, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009139621309004723, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009182431970257312, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009223342053592204, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009284397575538606, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009344920257572085, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009426876546349376, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00951307126088068, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009608634267933666, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009707657536491752, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009832992756273598, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010015187503304332, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010170023741666227, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010326596396043896, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010563022112473846, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010781954631675035, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011024282365106046, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011308565894141793, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011630512969568373, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01201117858523503, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012283320287242532, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.142289638519287, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1390717029571533, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.134834051132202, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.131688117980957, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.129378080368042, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.127072811126709, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.125375747680664, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1241705417633057, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1231982707977295, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1225531101226807, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1220951080322266, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.12160062789917, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1211657524108887, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1206135749816895, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1200969219207764, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1196086406707764, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.118962526321411, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.118236541748047, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.117398500442505, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1165761947631836, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1156129837036133, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.114560604095459, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1133270263671875, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1119067668914795, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.110326051712036, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.108269453048706, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.106259346008301, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1043360233306885, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.101658344268799, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.098639726638794, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0962178707122803, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0942230224609375, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.091855525970459, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.090071201324463, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.088242769241333, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0867204666137695, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0855937004089355, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0856130123138428, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0862958431243896, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0875864028930664, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.089060068130493, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.091069459915161, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0965847969055176, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0993711948394775, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.098726272583008, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.100770950317383, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1097750663757324, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1208608150482178, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1325926780700684, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08084163898117387, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08157991878922112, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0843484680693983, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08471760797342193, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08231819859726837, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08564045773348099, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08637873754152824, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08914728682170543, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09449981543004798, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09708379475821337, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09579180509413067, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09339239571797711, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09246954595791805, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013680673804233198, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012996598017975274, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011968025439683061, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011464784847507764, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010958945763838412, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010842627916551674, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010138469636480735, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010135354460507834, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010019365564841317, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009885216192899735, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009883851225758473, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010226588273672219, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010339453546852952, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010509541344006045, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010930004218132469, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010764181464880224, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010681015246521515, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.011419522203479216, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.011683038630101039, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0114754059210856, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.011679482517412248, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.011166067249200412, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.011479535626633605, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.011633159463441456, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.012239776989864865, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013872084213626209, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.016271087860762406, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01976177436111386, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.022058829274071264, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.02522071343580289, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.029090614463902206, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03092222039825637, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.033170297684781636, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03434004363277193, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03520001208324387, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03338702096173605, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.033211241152930594, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03338347164386695, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.035650823192492694, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03886257429216205, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04073538765452818, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04096194474316779, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03953218692669803, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.042621711147356, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.045992814524465214, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.044971186655905514, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.044524354295863426, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04573193405889526, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04530167094177481, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.0638473510742186, "validation/loss_best": 3.098726272583008, "validation/acc_best": 0.09708379475821337, "validation/f1_best": 0.045992814524465214} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 3.0969537019729616, "train/grad": 0.06662335628643631, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.14237548828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.139752197265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.136214599609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.133765869140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.132071533203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13041748046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129219970703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12839111328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127674560546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126986083984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1266455078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12592041015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12519775390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12416748046875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.123206787109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12225830078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.121063232421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11953369140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1178076171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.116212158203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11400390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.111824951171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10906494140625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.106307373046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.10305419921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.099263916015625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0957568359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.092525634765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0883160400390626, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.083336181640625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0791851806640627, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0754376220703126, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0709136962890624, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.06721923828125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0632818603515624, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.059853515625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0566943359375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.053892822265625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0509503173828123, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0482012939453127, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0470623779296875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0470571899414063, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0496466064453127, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0541766357421873, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0609912109375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.067352600097656, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.072787170410156, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0817794799804688, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0919155883789062, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009392018769867718, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00928498218068853, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009148072039242833, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009053112915717065, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008989062570035457, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008933624003548175, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008899359207134694, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008879314174409956, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008868943830020726, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008866447836626322, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008866448616608978, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008868630356155337, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008870977268088609, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008874271400272846, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008877941600512713, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008881232843268663, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008885708125308155, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00889017423382029, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008896017998922616, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008900929039809853, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008908180415164679, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00891608678502962, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008925177257042378, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008936726993415505, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008948480060789734, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008963852217420935, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00898098569130525, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008997878094669431, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009024036074988544, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009061915238853545, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009102763093542307, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009144289838150143, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009210644632112235, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009278607389423996, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00936955083394423, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009468053579330444, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009577024362515658, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009678825826849789, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0097917496599257, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009961432348936795, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010121910274028778, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010287251335103064, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010539366609882563, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01078830117592588, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011107742595486343, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011395002321805806, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011611499106511474, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011915651601739227, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01223441625246778, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1366665363311768, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1337952613830566, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1302525997161865, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1278529167175293, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1262097358703613, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1246914863586426, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1236331462860107, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122927665710449, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122311592102051, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1218385696411133, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1214520931243896, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1209402084350586, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.12044620513916, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1197755336761475, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1191298961639404, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1185109615325928, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1177330017089844, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.116798162460327, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1157569885253906, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1148083209991455, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.113600015640259, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.112285614013672, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.110780954360962, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1090800762176514, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1072020530700684, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.104822874069214, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1025686264038086, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.100350856781006, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0970022678375244, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.092581272125244, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.088376522064209, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0847160816192627, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.080303907394409, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0770535469055176, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0737669467926025, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0712151527404785, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0704007148742676, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0736007690429688, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.082282543182373, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0921740531921387, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.093860387802124, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0953376293182373, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.100971221923828, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.108137845993042, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.122175693511963, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1352598667144775, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1480510234832764, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1620452404022217, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1778695583343506, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.067921742340347, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.067921742340347, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0753045404208195, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0769656699889258, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07973421926910298, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08194905869324474, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08564045773348099, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08527131782945736, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08896271686969362, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09634551495016612, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09726836471022518, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09726836471022518, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08656330749354005, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08822443706164636, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09302325581395349, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09043927648578812, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0858250276854928, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08342561830933924, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0828719084533038, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08803986710963455, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09449981543004798, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09246954595791805, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08324104835732743, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01247450988141658, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01206331786609941, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011198087265508238, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01070529784330728, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010593814656162458, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010215756197034442, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009940750107435377, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009957892214264429, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009934863707189809, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009914135299873663, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01003171880134029, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010140688171436124, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009924298135464216, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009287912007623045, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009228119095181689, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009276100271887786, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009324756230403278, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00957609048414366, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009703780888692292, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009628609369383293, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010371449840178288, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.012392435858932084, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014362960269183862, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.017501902774526987, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.019798110731022427, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.021512964236019047, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.022184011177131407, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.02328666130241584, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.023787062911617182, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.027783070769758476, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.028099534430858154, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.032808031349568924, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.038161447148925304, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0420110407868075, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04312824439892159, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04293319437041727, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04157519427763335, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03866023262644174, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03251694008711088, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.033405686959000105, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03727953392399857, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03504846884114808, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0315793293705692, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.031073526739275895, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03135119179498582, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03678377896144414, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.044925466044079286, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05063814919371885, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0522005369522468, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 3.059853515625, "validation/loss_best": 3.0712151527404785, "validation/acc_best": 0.09726836471022518, "validation/f1_best": 0.04293319437041727} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 3.0898989737033844, "train/grad": 0.0684657390229404, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.137442626953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13496337890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.132138671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13029541015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128939208984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127861328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12698974609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126304931640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12572021484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12509521484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124554443359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12368896484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122955322265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121734619140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1206005859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.119613037109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11816162109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.116490478515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.114560546875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.112730712890625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.110347900390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1079150390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.105035400390625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.101888427734375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.098427734375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.09431884765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0905450439453124, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.087113037109375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.08241455078125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0768341064453124, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0721710205078123, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.06806396484375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0627484130859375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0582867431640626, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0534259033203126, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0487994384765624, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.044473876953125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.04076171875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.037440185546875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0346063232421874, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0335873413085936, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0337481689453125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.035425109863281, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.038279724121094, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.04320556640625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.049085693359375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0547409057617188, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0674818420410155, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0830397033691406, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00950130956247449, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009407511402387173, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009298214691225439, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009230935780797154, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009189700197894127, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009156995767261833, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009139311613980681, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009131141994148493, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00912759979488328, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009127381662838161, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00912801940459758, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009130217949859798, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009132350876461715, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009135606070049106, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00913870607735589, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009142074515111745, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009146764141041786, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00915276259649545, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00915921704377979, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00916562560480088, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009174491674639285, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00918427733471617, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009196331151761114, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009210265672300011, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009225481427274645, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009245670994278043, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009265219550579787, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009284587071742862, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009313579134177416, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009350968981161714, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0093896370427683, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009428255970124155, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009485664188396185, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009544564867392183, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009625457271467894, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009716660706326366, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00982727978611365, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009946072718594223, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010085671893320977, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010283354613929986, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01045981036964804, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01062449085758999, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010846630199812352, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01104860401013866, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011295464392751454, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011549484827555715, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011789776957593858, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012258294872008264, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012757750039454549, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1327829360961914, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.130336046218872, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.127497434616089, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.125709056854248, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1245288848876953, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123511791229248, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12282657623291, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122297763824463, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121812582015991, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.121389389038086, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1210057735443115, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1204700469970703, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119946241378784, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1191911697387695, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118447780609131, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1177289485931396, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.116811752319336, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1156365871429443, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1142804622650146, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.112980604171753, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1112725734710693, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1094186305999756, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.107255220413208, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1048591136932373, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1023144721984863, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0992650985717773, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0965542793273926, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0941731929779053, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0910837650299072, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0876317024230957, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.084714651107788, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.082148790359497, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.078871965408325, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0762836933135986, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0740883350372314, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.073140859603882, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0739307403564453, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.076543092727661, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.081374406814575, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.089185953140259, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.096325635910034, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.101780891418457, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1050362586975098, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1053671836853027, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1159207820892334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1441023349761963, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.166118621826172, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.204491138458252, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.240770101547241, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07604282022886674, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07641196013289037, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07788851974898486, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08231819859726837, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08453303802141011, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08803986710963455, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0946843853820598, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09542266519010704, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09542266519010704, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09708379475821337, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09505352528608342, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0946843853820598, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09708379475821337, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09892949427833149, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10557401255075674, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1111111111111111, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10686600221483943, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10446659283868587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10003691399040236, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08951642672572906, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011456461992452177, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011155773196273117, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010758842900701155, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010226218963099965, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010213457340139674, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010014001882733367, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00997503610443419, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009890604890604891, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009869906581705421, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010041436425877702, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0102335395009599, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009825769127439229, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010013620470417232, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009899369199431789, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01014314014398001, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011104961664565432, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012445356585464635, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013170937635611462, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014413114262977138, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01563789073936259, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.017376619606403063, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01855206478741441, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02051839947882621, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02179805799754489, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.023244862651356182, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.026327126008315865, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03262537695517008, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.033662870439526, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.037970658426320844, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04123208491931681, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.042636370587665125, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0433684410528146, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04168930248334698, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04250067903017698, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04247869977915692, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04092791556149633, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03646105354411446, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0356121649080172, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03555079698306111, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03322822347921473, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03311879890432671, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03431936742218126, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03735861722482823, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04140291713859608, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04898593393850718, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04821878389935839, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.053324461051386496, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05052535828075056, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.039069609550817674, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.04320556640625, "validation/loss_best": 3.1159207820892334, "validation/acc_best": 0.1111111111111111, "validation/f1_best": 0.04898593393850718} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 3.081333396434784, "train/grad": 0.06539211247116328, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.133338623046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.131251220703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12873779296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1272607421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126336669921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12542236328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1247265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12406982421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1233349609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1227392578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122083740234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121053466796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12006591796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.118677978515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11730712890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.116051025390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.114368896484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11227294921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.109981689453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.107724609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1049951171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.10188232421875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.09853515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.094893798828125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.09091064453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0862176513671873, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0818914794921874, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0779705810546876, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.072659912109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0666839599609377, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0615771484375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0571649169921873, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.051448974609375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.046611328125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0412353515625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.03606201171875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0310980224609376, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0268792724609375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0235357666015625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0207040405273435, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0198660278320313, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0197552490234374, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0204205322265625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.02219970703125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0254052734375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0303399658203123, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0373992919921875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0488836669921877, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.061307067871094, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009092170686926693, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00901259769918397, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008928110983688384, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008881371333263815, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008855272775981575, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00883686137618497, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008828248251229525, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008825115996878595, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008824535610619933, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008825081966351718, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008826334930490702, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008827677930239588, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008829616827424615, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00883212081855163, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00883437789278105, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008837022334337235, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008840053188614548, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008843221522402018, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008846636302769184, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008850387230049819, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008855278897099196, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008861630482133478, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00886889609741047, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008877163683064283, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00888730592560023, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008900523365009577, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00891289368737489, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008925059370230883, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008943820109125226, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008970472873188555, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008999046280514449, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009029301926493644, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009074174964334816, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009115488308016211, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009165790567640214, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009217739719897509, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009285680793691426, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009371121455915272, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009488705629482865, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00966613853815943, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009821575388778002, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009964568584691733, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010164019425865263, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010372545642312617, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010628174629528076, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010907052822876722, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011209057804662734, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0116076674987562, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011984267800580711, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.13018536567688, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1281344890594482, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.125913143157959, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1245696544647217, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123731851577759, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123030662536621, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122514486312866, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1221041679382324, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1216838359832764, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.121281862258911, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1208879947662354, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.120309352874756, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119731903076172, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.118901252746582, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1180710792541504, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.117264986038208, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.116201639175415, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1149308681488037, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1134305000305176, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.111987352371216, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1101038455963135, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.108067750930786, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1057145595550537, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.103142499923706, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1004486083984375, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.09731125831604, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0946249961853027, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.09230375289917, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0893499851226807, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0858993530273438, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0828380584716797, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.080069065093994, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.076408624649048, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0733821392059326, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0700504779815674, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0667169094085693, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0631954669952393, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0605790615081787, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.060304641723633, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0639946460723877, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.067121744155884, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0679469108581543, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0664124488830566, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0652143955230713, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0701801776885986, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0830514430999756, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0929713249206543, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.124274969100952, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1630353927612305, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07438169066076043, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08139534883720931, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.082687338501292, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08508674787744555, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09376153562200074, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09486895533407161, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09708379475821337, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09708379475821337, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10003691399040236, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10022148394241417, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10077519379844961, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09948320413436693, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09782207456626062, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09929863418235511, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1005906238464378, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09929863418235511, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09856035437430787, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09579180509413067, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09376153562200074, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09579180509413067, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0932078257659653, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011037357535689454, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010696028912181951, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01017914780219951, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010175157280434126, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010044391965922534, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009926954929011847, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010065307699311049, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010095462261576198, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01024890620450679, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010327660428817236, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009884157080100335, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009731927187653621, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009623103600738397, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010274885967797987, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0099968944449597, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010160563520100451, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010820817122840207, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.011516282504448026, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01218451080171057, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013404026455836889, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.014941605053951057, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.016743990919884485, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.021116735839421596, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.025013990545303264, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.028265060062294775, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.032664746558281804, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03412698304998819, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03507427335812929, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03606731912337966, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.038985890863729694, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04127638606683603, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0433738719188241, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04330817521610696, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04312102669950526, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04401202384600256, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04243744664034004, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.044205873956863706, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04524704163518172, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04595264586275722, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04771299063242055, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04955933305428284, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.051295841777459335, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05379415616055339, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05442031973424049, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.054898074337279175, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05053322530404899, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04860693861673171, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05037820094278472, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04845247196082064, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 3.0235357666015625, "validation/loss_best": 3.060304641723633, "validation/acc_best": 0.10077519379844961, "validation/f1_best": 0.04595264586275722} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 3.0779273962974547, "train/grad": 0.06548531781882047, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.132091064453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13052978515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12866455078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126845703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12618896484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125640869140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12497802734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.124212646484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.123492431640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122738037109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1216845703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1205859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.119005126953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.117445068359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.116021728515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11400146484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11173828125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10919677734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.106680908203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1035595703125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.10015869140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.09652587890625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.09239013671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0880511474609373, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0829888916015626, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.078323974609375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0742138671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0687213134765625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.062540283203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0572283935546873, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0526068115234377, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0466265869140625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0415777587890624, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0359234619140625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.030919189453125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0260162353515625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.02188232421875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0176815795898437, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0129568481445315, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.010240478515625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0086944580078123, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.00812255859375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0094943237304688, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0136483764648436, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.021481628417969, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.030115051269531, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0424481201171876, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0539874267578124, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009068737644702196, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009005865869112313, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008943980124313385, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008912061334121972, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008895972368773073, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008885483490303159, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0088812842592597, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008880907357670366, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008880789997056127, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008881497166585177, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008882662367541342, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008884226849768312, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008886128549929708, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008888257308863104, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008890827354043722, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0088926421222277, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008894929911475629, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00889785828301683, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008900939370505512, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008904045645613224, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008908430130686611, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008913151500746608, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008919115581084042, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008926881500519812, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008936591139063239, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008950199589598924, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008965412240941077, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008980436371639372, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009005030952394008, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009039166204165667, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009073026000987739, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009107422512024642, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009157889029011131, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00920568402390927, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009265844367910177, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009327614030335099, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009397660738322884, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00946353722596541, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00953526257770136, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009627793545369058, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009719101947266608, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0098242597701028, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010000288721639662, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01019558790838346, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010485069144051522, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0108357347198762, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01112905924441293, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011480410960502922, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011790618626400828, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1282973289489746, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.126607894897461, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12480092048645, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1237564086914062, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1231067180633545, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122553825378418, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1220669746398926, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1216795444488525, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.121230363845825, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120774269104004, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120325803756714, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119642734527588, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.118997097015381, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1180458068847656, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.117131233215332, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1162829399108887, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1151609420776367, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1138393878936768, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.112358808517456, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1109445095062256, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1091911792755127, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1073620319366455, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1053307056427, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1031813621520996, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1010076999664307, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0984981060028076, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.09631085395813, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.094409227371216, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0918385982513428, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.088758945465088, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.085948944091797, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.083273410797119, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.079578161239624, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0763051509857178, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.073075532913208, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.071239948272705, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0714502334594727, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.07462477684021, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.082308769226074, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0971484184265137, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.107752799987793, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1140332221984863, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1133980751037598, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1024882793426514, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.08562970161438, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.076535224914551, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.083613872528076, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1034445762634277, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1047000885009766, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07327427094868956, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07973421926910298, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08803986710963455, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08840900701365817, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08803986710963455, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08896271686969362, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08859357696567, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08803986710963455, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08840900701365817, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08840900701365817, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09394610557401255, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09837578442229605, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09800664451827243, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0976375046142488, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09726836471022518, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09856035437430787, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010821661386621856, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010893720089016524, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010101173008795565, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010047222396348013, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009942815056184417, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009868236861633947, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009975945130817959, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.009751116851688491, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00898646237212921, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008339333622306296, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00817772541957922, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007855251773273324, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007875873555176856, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007930318522058338, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007285244753179603, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007115283119093194, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0073808270177086336, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008596251512348335, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009023425391969766, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009218287087064791, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.009770752543251729, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010289864950498535, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.012136365839740057, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.014078148037835877, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.016218157857104742, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.019105421038142025, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01977903796386914, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.021223152553752515, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02418118685990237, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.025546570963943315, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02564474761267366, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.02819018900186936, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.030772412326823345, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.032870913160919175, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.033862645235788386, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03458807457433797, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03546104896718498, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.035282792007217255, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0346205924688909, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03326567820244409, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.033367006558449534, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03257887022326296, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03564021911932374, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03921110272381877, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04850218512099474, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05340384560230264, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05453463086361779, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05332097362352628, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05466650742575043, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.0539874267578124, "validation/loss_best": 3.1047000885009766, "validation/acc_best": 0.09856035437430787, "validation/f1_best": 0.05466650742575043} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 3.074911842346191, "train/grad": 0.06580111408606172, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.131641845703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130196533203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1287109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127745361328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12703857421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12631591796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12564453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.125037841796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.124205322265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12332763671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122430419921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121217041015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.120045166015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.118272705078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1165771484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.114970703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11292236328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.110452880859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.107755126953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.105084228515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1017431640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.098343505859375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.094410400390625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.09012451171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.08557861328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.08011962890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0751934814453126, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0708624267578126, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0648480224609376, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0581573486328124, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0525543212890627, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0478436279296877, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0418328857421875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0369561767578124, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.03162353515625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0268798828125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.02238525390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0186572265625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.01530517578125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0116372680664063, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.009610290527344, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.008349609375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.007431945800781, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0071749877929688, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.008594665527344, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.012440490722656, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.017166748046875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.023750762939453, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0315150451660156, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009082630912307649, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009037789874710142, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008996889900881797, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0089789367467165, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008971236841753126, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00896747478749603, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00896635598037392, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008967272383160889, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008968251848127693, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008969056275673211, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008969544770661742, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008970576943829656, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00897196911741048, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00897351152729243, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008975658230483533, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008977565278764815, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008980388750787825, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008983268518932164, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00898722180398181, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008990580749232322, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008995095831342042, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009000206922646612, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009006144334562123, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009012830913998187, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009019788124132901, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009028947497718036, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009038398938719184, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0090484350733459, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00906376295723021, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009086652267724276, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009109760022256523, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009135295909363777, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0091758835548535, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009217303034383804, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00927334797102958, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00933655617525801, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009416883676312864, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00950744699453935, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009621023179497569, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00978192371316254, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00992039427626878, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010049465971533209, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01021614087279886, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010355234777089209, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010543683508876711, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01078312809811905, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010971995322033763, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011150027129333466, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01134278894867748, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1270980834960938, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125628709793091, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124119758605957, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123255968093872, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1227006912231445, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1221745014190674, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1217076778411865, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121299982070923, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1207523345947266, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120192527770996, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1196482181549072, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.118821859359741, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1180014610290527, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.116792678833008, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.115638017654419, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1145153045654297, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1130313873291016, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1112585067749023, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1093008518218994, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.107445001602173, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.105163335800171, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1028122901916504, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1002283096313477, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0975258350372314, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0948383808135986, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.091792583465576, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0891172885894775, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0867929458618164, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.083712577819824, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0801444053649902, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.077139377593994, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0744576454162598, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0710723400115967, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0680761337280273, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.064329147338867, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.060533285140991, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0570523738861084, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0551085472106934, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.054633378982544, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0571229457855225, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0614030361175537, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0657269954681396, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0694379806518555, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.068387508392334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0630011558532715, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.057915687561035, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.057692527770996, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.065248727798462, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0833873748779297, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08471760797342193, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08619416758951642, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0902547065337763, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09228497600590624, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0917312661498708, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09689922480620156, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09874492432631968, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10243632336655592, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10280546327057954, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09449981543004798, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08988556662975268, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08840900701365817, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08933185677371724, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09948320413436693, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10022148394241417, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10188261351052048, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10446659283868587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09819121447028424, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010773969239275816, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010386159904060398, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010148719056082478, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009973297079504154, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009869111768465963, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009873389358552625, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01037394885444397, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010411942605476147, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010049145744354568, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009742358723704046, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009613253009811586, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009701205349754374, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009686522028447823, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009812879421924629, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01042946871085011, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010776507326396213, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011844709045773961, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013094093653015193, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014128626611287965, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01596214859045393, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01850582378802348, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.022017918715257826, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.024833755074117014, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.028028676110049954, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.028929398289909616, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.029512925809061466, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03099174179768882, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.032987075533764544, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03420079337669734, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.035884567815560174, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03753203670723684, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03880275632649197, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03809442290546617, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.040039532056651665, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04257100646077888, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04436201356795257, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04804833341718415, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04876945090351991, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.048421293101727915, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.044611205809248794, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04191885658698256, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.041551656415327945, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.042370267191818696, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04654444914613163, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05596387935757962, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06029469376791363, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06470911038015476, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06789915608886571, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06224880970109961, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.023750762939453, "validation/loss_best": 3.065248727798462, "validation/acc_best": 0.10446659283868587, "validation/f1_best": 0.06789915608886571} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 3.06694638133049, "train/grad": 0.06560209766030312, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1319287109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130692138671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12946533203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128712158203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12811279296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127454833984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126800537109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12607177734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125089111328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124149169921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121644287109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12022705078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.118280029296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.116341552734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11452880859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.112135009765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1093310546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10608154296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.103153076171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.099403076171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0953271484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.09088623046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.085899658203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.08073486328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.07452392578125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.068885498046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.06395263671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.057120361328125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0493572998046874, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0428106689453127, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.03716552734375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.029964599609375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.02407470703125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.017509765625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0117987060546874, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0064129638671875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0019439697265624, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9979974365234376, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9939169311523437, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9912554931640627, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9892849731445312, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9874526977539064, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9870404052734374, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9878826904296876, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.989723663330078, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.992384948730469, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.997366943359375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.004896240234375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009118121610954403, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009077557714190334, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009041741664987057, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009025269963312894, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009018184465821833, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009013822847045959, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009012821642681957, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009012867156416178, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009013414732180536, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00901429496705532, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009015343240462244, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009016616467852146, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009017971770372241, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009020236353389919, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009022399934474378, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009024639502167702, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00902802194468677, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009031267031095922, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0090351099986583, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009039146131835879, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009044067552313208, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009049385252874345, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00905515598366037, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009061530015897006, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009068894791416824, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009077615009155125, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009085513979662209, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009092902813572437, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00910373691469431, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00911860413616523, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00913448396138847, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009150471007451415, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009176879450678825, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009204929010011256, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009245530539192259, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009300102666020393, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009374464889988303, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009458823616150767, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00956203266279772, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009691577029880136, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009785680833738297, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009867698887828737, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009989668629132212, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010120622694958002, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010288263815455138, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010472492198459804, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010644746334291995, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010885914142709225, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01114967605797574, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1262192726135254, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1249287128448486, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1236462593078613, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1228976249694824, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122410297393799, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1219005584716797, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121448516845703, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1210100650787354, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1204628944396973, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119875907897949, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.119323492050171, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1184654235839844, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1176528930664062, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1164722442626953, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.115339756011963, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.114238739013672, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.112833261489868, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.11114239692688, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1091952323913574, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1073548793792725, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1050195693969727, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1025025844573975, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0996735095977783, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0965168476104736, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.093230962753296, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0892412662506104, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.085721492767334, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0825302600860596, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0782923698425293, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0733702182769775, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0691988468170166, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0656397342681885, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0613996982574463, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.058204174041748, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.05525803565979, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.053011178970337, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0508995056152344, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0489730834960938, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0471479892730713, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.045988082885742, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.047332763671875, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0502004623413086, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0556564331054688, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0596017837524414, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0589864253997803, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.05588436126709, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.058687925338745, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0737898349761963, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0994575023651123, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07678110003691399, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07973421926910298, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08047249907715023, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0873015873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09246954595791805, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09486895533407161, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09800664451827243, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09837578442229605, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09837578442229605, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09745293466223699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.0991140642303433, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09856035437430787, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09579180509413067, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09782207456626062, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09856035437430787, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09929863418235511, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09597637504614248, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09449981543004798, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0976375046142488, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09283868586194167, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010357913646247725, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010130356941842349, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010007407557526304, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009845340665206054, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01006870995314287, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00995363241836019, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01031449858132428, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010192097022469733, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009731858474190667, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009647504337412112, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009320331929025608, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009202012674531997, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009402000402319416, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009708118008999142, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010031364093778328, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011016337483043176, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011505152822195865, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.012803682044759948, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01445502101755458, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01643800795993307, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01995298587264972, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.021186589871467206, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02422102068733796, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.026026884013612958, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.029869106969508303, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.033714489390391546, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03468011599633985, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03571055711461931, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0369483732307946, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.039664952400258094, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.041202064602201625, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.042183668941246734, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04370795873435482, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.044415907422923735, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04425311543451365, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.043250882164816935, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04399337850896314, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.044557651664211016, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04448647998951172, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.046493053219101466, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04587332050530455, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04432554631403388, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.046696279418302906, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04797491524285715, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04991089174827301, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.049714465681562126, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04874810146549522, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04817766364441814, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.041325475648049455, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 2.9878826904296876, "validation/loss_best": 3.0589864253997803, "validation/acc_best": 0.09929863418235511, "validation/f1_best": 0.04991089174827301} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 3.063222420215607, "train/grad": 0.06443326784297825, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13108642578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130107421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12911376953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1283349609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127889404296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12730224609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1266259765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126007080078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1250390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124022216796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12300537109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121531982421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.120028076171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11791259765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1159130859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11393798828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.111439208984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.108411865234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.105064697265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1018505859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.09797607421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.093643798828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0887890625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.083817138671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0783551025390623, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0719976806640625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0663592529296877, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.061241455078125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.054512939453125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.046759033203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.040322265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0346343994140623, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0273724365234376, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0212042236328127, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.01420654296875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.007711181640625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.001104736328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.995401611328125, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.989889831542969, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9840521240234374, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.980523681640625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9783551025390627, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9765374755859373, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.975877380371094, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.976216125488281, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9774014282226564, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9801995849609373, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.98615478515625, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9926612854003904, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008978707282803953, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008942453451454639, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008911499872338026, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00889747632900253, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00889225154183805, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008889258846174926, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008888124874792992, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008888195045292377, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008888288622256369, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008888755578082054, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008889055247418582, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008889948860742151, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008890317622572183, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008891364554874598, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00889194555580616, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008892838277388364, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008894311070907861, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00889600025024265, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008897598509211093, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008899350070860236, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008901827051304281, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008904834745917469, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008908729169052094, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008913642612751573, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008919972567819059, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008929973216727376, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008940857865381987, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008951859853696079, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008969582414720208, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008993298076093196, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00901711270213127, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00903935234528035, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00907213976373896, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009101850641891361, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009138606414198875, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00917783068260178, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009224925958551466, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009275149726308883, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0093376490380615, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009429354832973332, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009514175348449498, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009601912524085493, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009732668539509177, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009861367363482714, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010023618296254427, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010210751618724317, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010388951918575912, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010622851781081409, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010800713361240923, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1256330013275146, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124511480331421, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1233673095703125, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1227238178253174, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122274398803711, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121824026107788, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1213910579681396, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1209747791290283, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120417356491089, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1198348999023438, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1192739009857178, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.118455648422241, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1176562309265137, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1164839267730713, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.115349292755127, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1142430305480957, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1128153800964355, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1110684871673584, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1090664863586426, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1071460247039795, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.104715347290039, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.102137804031372, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.099200487136841, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.09600567817688, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0926387310028076, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.088695526123047, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.085239887237549, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0821876525878906, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.078248977661133, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0738165378570557, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0700557231903076, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0667595863342285, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0625598430633545, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0590999126434326, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.055725336074829, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0531351566314697, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0513105392456055, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0505497455596924, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0507748126983643, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0523695945739746, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0540292263031006, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0549614429473877, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.054643154144287, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0540430545806885, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0546045303344727, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.053924083709717, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.050022840499878, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0479705333709717, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.054600954055786, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07770394979697305, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08619416758951642, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08840900701365817, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0902547065337763, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09283868586194167, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09505352528608342, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09560723514211886, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09856035437430787, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09874492432631968, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0991140642303433, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10169804355850867, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10188261351052048, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1020671834625323, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10465116279069768, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10520487264673312, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1050203026947213, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10834256183093392, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1094499815430048, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11295681063122924, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11517165005537099, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11074197120708748, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11092654115909929, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010222191269923657, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010153994768403448, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010031542218184765, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00993334296469304, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009795436934667728, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009989275224549987, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009729595648406478, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00923896980268775, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008297412819187071, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008208625177867848, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008263396614756011, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008268008243084898, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008630476926594218, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00883588135719513, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009022728523806466, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009702318513610057, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01100395498700256, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.011861843797537408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013245340014007142, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01393452301860531, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01627385495509952, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.019546681679347453, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02296115024473193, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.026092050814532405, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02968580462034838, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.033001750025956914, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03508232487911173, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0376053832108544, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04063718157382005, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04348152729724655, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.043026305183377515, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04322944033297512, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04530137907979812, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04618273619904605, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0470207873313695, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04805028352277139, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04773710157032977, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0486019322227828, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.048768180486279046, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05097454071992685, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05093767048082884, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05008468461607226, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04909057936710871, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0480139985547788, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.049317442978167474, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05398164578628589, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0568927381373181, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05645408290640693, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05722533531667571, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.9801995849609373, "validation/loss_best": 3.050022840499878, "validation/acc_best": 0.11517165005537099, "validation/f1_best": 0.0568927381373181} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 3.056967372894287, "train/grad": 0.06372882096096873, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12886474609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1278369140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.126705322265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126026611328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.125389404296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12470703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12396728515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123153076171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12216552734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.119876708984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.118297119140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.116766357421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.114490966796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1124609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.110372314453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.107796630859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.10470703125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10129638671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.09802978515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.09392333984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.089564208984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0848394775390626, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.079727783203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0742041015625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.067757568359375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0620294189453126, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.056947021484375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.050208740234375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0424407958984374, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0358447265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0300128173828127, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.022552490234375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.016162109375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0090380859375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.002275390625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9954132080078124, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9892523193359377, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.982908020019531, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.975785217285156, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9709814453125, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.967119140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.963074951171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9606137084960937, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9591937255859375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.959278259277344, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9608255004882813, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9648931884765624, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.970611877441406, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008934081501793116, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0089033281407319, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0088777519389987, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00886732894461602, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008863529257941991, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008861232325434685, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008860790173057466, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008860290751326829, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008861034079454839, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008860732633620501, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008860791947226972, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008861288952175528, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00886139513226226, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008861978484783322, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008862676164135337, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008863502598833293, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008864809847436846, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008865966654848307, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00886785478098318, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008869245471432806, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00887112567666918, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00887368386844173, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008876554016023875, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00887988781556487, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008884648042730987, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00889112958451733, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008898585059214384, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00890606850385666, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008917573762591929, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008933260682970285, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008948230452369898, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008962696834933013, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00898380742641166, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009005260705016553, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009033555937930942, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00906582954339683, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009105130950920283, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009147751999553293, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009200285256374627, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009278933198656887, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009348301128484308, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009415301149711014, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00951416093390435, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009609177764505148, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009731202106922864, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009875422117765993, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010022174229379743, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010249692890793085, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010491161905229092, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1252551078796387, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1242387294769287, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1232104301452637, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1226067543029785, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1222245693206787, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121783971786499, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121354341506958, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120910167694092, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1203651428222656, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1197664737701416, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.119187116622925, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.118314504623413, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1174185276031494, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1161623001098633, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.114908218383789, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1136550903320312, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.112048387527466, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.110069751739502, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1077775955200195, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.105576992034912, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.102769374847412, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0998387336730957, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.096522569656372, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0929079055786133, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.089158773422241, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.084716796875, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.080833673477173, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.077385187149048, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.072878360748291, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0679354667663574, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0638928413391113, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.060513734817505, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0565693378448486, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.053518772125244, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.050459623336792, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.048022747039795, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.046008348464966, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0446078777313232, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.043658971786499, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0427210330963135, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0413424968719482, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.039659023284912, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.036719799041748, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0346035957336426, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0332694053649902, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.033041000366211, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.033332109451294, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.036755323410034, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.042114734649658, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07770394979697305, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07936507936507936, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08194905869324474, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08637873754152824, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08988556662975268, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09689922480620156, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09745293466223699, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09708379475821337, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09966777408637874, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10280546327057954, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10299003322259136, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10631229235880399, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10686600221483943, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10612772240679218, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10631229235880399, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10705057216685124, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1094499815430048, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10741971207087486, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10760428202288667, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11129568106312292, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1111111111111111, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010180522270643002, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010107524732387754, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009927821971735437, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009943046481557099, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009926636964516766, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009809966177297317, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009259809930942449, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008672359785406413, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008237532439778069, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007840418387684421, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007838065653265022, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00786552753508788, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008010744426273262, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008361989422519658, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009167519934890981, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009698382748369793, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012060111483495561, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013264658021127652, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.015143624220202432, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01668398574800828, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01861948356510861, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.022128764228032, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02410573997019104, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02612180513386349, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.028502863358212602, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03091874785410283, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03277040807349419, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03401864139681265, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03716206315312793, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03922301279710641, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.041288907160776656, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04171181954544917, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04232965675902003, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04438386050210178, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.046346019755466615, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04998223662994952, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05345053574463635, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05608501588150324, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05646686943643645, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05981520511544775, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06038045251147079, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.060674771079175266, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.060509277844510954, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0609368421054571, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06361153502260936, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06126061662106199, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06008435351551916, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0649528046078464, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06660423039003821, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.9648931884765624, "validation/loss_best": 3.036755323410034, "validation/acc_best": 0.11129568106312292, "validation/f1_best": 0.0649528046078464} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 3.058539505004883, "train/grad": 0.06353647794574499, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13037109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129627685546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128717041015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128192138671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12778564453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127142333984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12643310546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.125716552734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12483642578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.123673095703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122608642578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121007080078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11947998046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.117391357421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.115301513671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1131884765625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.110692138671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.107470703125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10401123046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.100667724609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.096591796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.092147216796875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.087215576171875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.082088623046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.076549072265625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.06983642578125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0641259765625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.058890380859375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0519476318359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0440234375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0372113037109374, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0313671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0239862060546874, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0174945068359373, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0103363037109374, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.003558349609375, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9967852783203126, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9905361938476562, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.984180908203125, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.977020568847656, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9722625732421877, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9688397216796876, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9650643920898436, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.962405090332031, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9599227905273438, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.958332214355469, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9581414794921876, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9599688720703123, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9632949829101562, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008960542026907206, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008934307547751813, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008913338461425155, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00890520534478128, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00890235899714753, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008900667391717434, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00890037876786664, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008900238734204322, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008900179578922689, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008899563048034907, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008899636431597174, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00889949476113543, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008899858419317752, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008899803748354316, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008899974152445794, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008900031060911716, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00890040138270706, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008900711808819324, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008901669327169657, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008902599003631622, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008904256587848068, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00890656805364415, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008909641078207641, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00891265265410766, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008916023627389223, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008920866418629885, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00892545608105138, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008930384183768183, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008936967069748789, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00894652990391478, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008955306159332394, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00896510689286515, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008980092599522323, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008995800046250224, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009016406782902777, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009038958144374191, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009066529881674796, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00909374570241198, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009129400290548801, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009184143096208573, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009241487325634807, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00930484471609816, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009401105949655176, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009489836792927236, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00958551151677966, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009683491964824497, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009776652418076992, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00991543848067522, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010054090397898108, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124981164932251, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1240074634552, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123070001602173, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122511625289917, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122081756591797, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1216633319854736, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121206283569336, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120741605758667, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120142698287964, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1195220947265625, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.118905544281006, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.117957830429077, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.117046594619751, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115668773651123, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.114339590072632, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.113027572631836, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1113576889038086, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1093192100524902, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1070101261138916, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1048104763031006, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1021039485931396, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0992629528045654, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.096102476119995, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0927109718322754, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0891833305358887, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0850515365600586, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0814616680145264, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.07826566696167, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.074146270751953, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.069591522216797, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0658304691314697, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.062662124633789, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0588648319244385, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.055820941925049, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0525736808776855, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0497710704803467, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0471861362457275, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.044948101043701, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.042829990386963, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0408999919891357, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0399131774902344, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0394175052642822, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.039236307144165, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0388436317443848, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0383617877960205, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.038661003112793, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.040184259414673, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0444111824035645, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.049513339996338, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08213362864525656, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08471760797342193, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0902547065337763, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09117755629383537, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09376153562200074, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09726836471022518, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09782207456626062, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1020671834625323, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10335917312661498, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10280546327057954, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10299003322259136, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1050203026947213, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1035437430786268, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10409745293466224, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10280546327057954, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10335917312661498, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10446659283868587, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10612772240679218, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10668143226282761, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10575858250276855, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1037283130306386, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10262089331856773, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10317460317460317, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01006977445252427, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010033286430639457, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009987738016203873, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009862867019593291, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009919942251625532, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009685125882151079, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00874307726904471, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008345657487847298, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008152986807877552, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007704160386848458, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007613406027506798, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008356647162719555, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00870028815983231, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009081484897374119, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010346524379407676, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011969920108093966, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013592847348692559, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.015059848814117644, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0164122968455597, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.018391329101903754, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.021812681263365292, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.025700001080777555, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.028086694646984017, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.030504877549582154, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03316326234460096, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03777928895448266, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03908746329869927, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.04108695923622577, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.041929345863178834, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.042028876031534906, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04492412518972605, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04540969877375812, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04734928779987224, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04911383326318411, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04960297384012911, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.049851160610271145, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.050264500592122924, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05245840561444461, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.052359542983213235, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.053776563761818885, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05361727946380534, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.0541299589635921, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.054966842243812285, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.056566406900652906, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.057148265713548384, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05664632514509427, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05464788122767702, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.053508420067527866, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05377947665753593, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 2.9599227905273438, "validation/loss_best": 3.0383617877960205, "validation/acc_best": 0.10668143226282761, "validation/f1_best": 0.057148265713548384} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 3.0503757572174073, "train/grad": 0.06334351100027562, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127618408203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.126658935546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125599365234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12493896484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124259033203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123587646484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12273193359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121951904296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1207568359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11947509765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.118370361328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116649169921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1149853515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.112628173828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11031982421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.107958984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.105330810546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.10196533203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.098184814453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.094632568359375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.090301513671875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.085689697265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.080579833984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0750445556640624, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0692626953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.062308349609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0563055419921876, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0508331298828124, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.043621826171875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0354144287109377, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0283990478515626, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0222393798828127, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.01444580078125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.00775390625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0004119873046875, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9933282470703126, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.98632080078125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.980041198730469, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9736294555664062, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9662380981445313, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.961045837402344, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9568951416015623, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9519967651367187, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9483737182617187, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9448614501953125, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.94211669921875, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9406640625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9403565979003905, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9413319396972657, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008979288532864303, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008954309474211187, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008934518911410123, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008926977377850562, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008924119134899228, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008922684942372144, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008922379445284605, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008922571677248924, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008922830340452492, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008922523257788272, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008922752512153237, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008923360204789788, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008923702316824347, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00892411629203707, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008924409169703723, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008924608728848397, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00892484346870333, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008925346655305475, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00892635022290051, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00892693010158837, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008927327394485474, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008928210027515888, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008928994697052986, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008930324432440103, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00893239644356072, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008934998807962984, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008937856664415449, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008941170840989799, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008945759979542344, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008952149185352027, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0089594207983464, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008966293383855373, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008977170260623097, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008988817061763257, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009004777811933309, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00902339307591319, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009046635781414807, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0090728525724262, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009104716121219098, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00914896365487948, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009185800598934292, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009222296853549779, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009275560630485416, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00932748790597543, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009393229652196168, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009476292340550571, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009556785982567817, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009663426473271102, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009751481539569794, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1248128414154053, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123887538909912, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1229701042175293, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122429609298706, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12202787399292, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121588945388794, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1211423873901367, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1206769943237305, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1200544834136963, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1194047927856445, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1187872886657715, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1178112030029297, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1168713569641113, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115489959716797, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1141304969787598, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1128108501434326, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.111112594604492, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.109093427658081, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1067700386047363, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1045901775360107, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.101853132247925, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0989906787872314, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0957655906677246, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0922770500183105, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0886144638061523, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.084306001663208, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0804736614227295, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.077061891555786, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.072573184967041, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0674829483032227, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0631680488586426, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.059363842010498, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0545432567596436, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0505101680755615, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0462048053741455, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0423660278320312, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.039029598236084, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0365967750549316, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0346148014068604, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.033341646194458, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0329642295837402, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.033015727996826, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0336410999298096, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.034661293029785, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0366199016571045, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0393433570861816, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.041975975036621, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.045609712600708, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.049809694290161, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07788851974898486, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08047249907715023, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08194905869324474, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0873015873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08970099667774087, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09634551495016612, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09892949427833149, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10077519379844961, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09966777408637874, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10095976375046142, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10335917312661498, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1037283130306386, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10465116279069768, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1035437430786268, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10335917312661498, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10225175341454411, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10132890365448505, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10299003322259136, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10188261351052048, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10095976375046142, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10022148394241417, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010107211644799755, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00990357704500953, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010021465842933492, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009824134976072102, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00983029428952721, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009699319610826459, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00880464281944702, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008387342322663102, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008131536756619094, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007825761227070153, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007926007303085882, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008386400474095229, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008728803845568461, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009983402903343675, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010457677313552842, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01194934919417928, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013889920790527026, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01464560590143127, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01678880818774026, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.017572981471343573, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.020836262539155576, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.023698417572350236, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.026349754067709768, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.030343191933269443, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.032428392567841684, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.034291942137677674, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03709055330991763, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.038793565355367966, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.040330888901253956, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.041282682624889495, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04278596408615307, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04431009112152743, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04670744636406155, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.047934413484126435, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04832969950091711, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.047846302422013896, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04870509069222099, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05073644829913453, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05291302704220343, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05405530844185553, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05601207097812919, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.055672349209308164, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.054321359621373265, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.052916689570815696, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05133410265176567, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.050455597917776616, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04991352095554689, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05004894352896374, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04824232812774637, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 2.961045837402344, "validation/loss_best": 3.0329642295837402, "validation/acc_best": 0.10465116279069768, "validation/f1_best": 0.05601207097812919} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 3.0511358273029328, "train/grad": 0.06314100444316864, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128114013671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127303466796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12639892578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.125738525390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12510986328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.124403076171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123712158203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1229150390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121763916015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12062744140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.119556884765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.117952880859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1163330078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.114095458984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.111807861328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.109747314453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.107066650390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1039453125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.100306396484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.09689208984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.092620849609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.08831298828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.083240966796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0778717041015624, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.07224853515625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.065562744140625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0596142578125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.054072265625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0470574951171874, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0387994384765626, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.03171875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.02546630859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0175445556640623, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.010665283203125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.002899169921875, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.99553466796875, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.987940673828125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9811026000976564, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9740499877929687, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.965681457519531, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.95977783203125, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9550015258789064, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9493777465820314, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.945098876953125, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.94096923828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.937442626953125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9351992797851563, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.933603515625, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.933392333984375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009008959671482443, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008986475910060108, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008969365474767984, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00896307201590389, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008960797055624425, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008959418493323029, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008958435086533427, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008958125780336558, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008957700924947859, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008957973262295128, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008957461488898843, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00895687003619969, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008956495919264854, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008956328211352229, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008955569576937706, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008955170509871095, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008954462504480034, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008953596178907902, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008953013624995947, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008952844615560025, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008952213884331286, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008951864198315888, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008951831569429487, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008952130102552474, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008951741382479667, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008952039394062012, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00895242322003469, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008952995890285819, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0089534908416681, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0089539855113253, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00895543502876535, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008957205035258084, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008960513351485132, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008965321592986584, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008972553887870162, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008980942524503916, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00899236697005108, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009005047837272287, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009022302210796624, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009047975153662265, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009071561181917787, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009096782850101591, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0091347697051242, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00917354220058769, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00922512807417661, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009283971751574426, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009337205754127354, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009403489835094661, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009465054110623896, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124722480773926, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1238038539886475, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122926950454712, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122389078140259, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121990919113159, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1215579509735107, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1211016178131104, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1206092834472656, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1200122833251953, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119352340698242, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1187028884887695, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1177196502685547, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.116767644882202, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115365505218506, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.114006519317627, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.112677812576294, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1109776496887207, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1089255809783936, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.106597423553467, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.104391574859619, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1015915870666504, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0986785888671875, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0953776836395264, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0918097496032715, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.088104724884033, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0837295055389404, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.079932451248169, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0766303539276123, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0723111629486084, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.067586898803711, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.063724994659424, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0604145526885986, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0563905239105225, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.053069591522217, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.049415349960327, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0461413860321045, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0429794788360596, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.040271520614624, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.037605047225952, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.034719228744507, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.032758951187134, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0313708782196045, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0297634601593018, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.028576374053955, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.027661085128784, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0269107818603516, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0265817642211914, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0263173580169678, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0266036987304688, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0753045404208195, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08176448874123293, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08324104835732743, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08693244739756367, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09080841638981174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09136212624584718, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09486895533407161, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09560723514211886, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09837578442229605, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09837578442229605, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09966777408637874, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10077519379844961, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10262089331856773, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1020671834625323, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10483573274270949, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1064968623108158, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10575858250276855, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10446659283868587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10723514211886305, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10834256183093392, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10778885197489849, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1064968623108158, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10705057216685124, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10963455149501661, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010002453797077905, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010171114703108886, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009980645186542044, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009859608442377767, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009951419346978558, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009608838249986791, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008899248160040589, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008469781096606151, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008077835238781991, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008142465319879671, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008179290489242964, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008277565942728805, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008741870539386363, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009882556159799152, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01081709407334766, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01254080213587677, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013614821439345516, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01428066184618032, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01608325318949048, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.017342863139940955, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.021450789805672544, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.02517203303739964, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.028120804189867305, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.031159760416792286, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.032555800713366674, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03607225055968651, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03933407846516457, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.040427028634326886, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04166941830004187, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04345079464503986, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04443534984257013, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0461787597705797, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.046227091925658804, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.047733538145866124, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04875198589343561, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04978361436979384, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05177026344076996, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05257995211401951, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.055238032781332186, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05689551640658732, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.056992686649442285, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05649391575390753, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.059095796657559506, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05989854600771163, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.059002786937172924, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05852968034098211, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.059976237281153776, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05947589222098942, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06143271703558431, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.933392333984375, "validation/loss_best": 3.0266036987304688, "validation/acc_best": 0.10963455149501661, "validation/f1_best": 0.06143271703558431} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 3.0470498621463777, "train/grad": 0.06361957259476185, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127198486328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1264013671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125421142578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12480224609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12411376953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123453369140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12277587890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121895751953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120775146484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.119613037109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.118448486328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116748046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.115113525390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.112655029296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.110396728515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.108310546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10548583984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1021923828125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0984765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.094954833984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.09046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.08591552734375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0807391357421876, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.075281982421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.06939697265625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0624652099609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.05625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.050740966796875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0434100341796877, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.035067138671875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.027808837890625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.021363525390625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0132861328125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0061590576171877, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9981591796875, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9904864501953123, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9826312255859375, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9754534912109376, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.967838134765625, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9589364624023435, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9525, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9470947265625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.940538024902344, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.935511169433594, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9303607177734374, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9259149169921876, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.922801513671875, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9203610229492187, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9192739868164064, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009122027496341617, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00910160509403795, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009086019084788859, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009080454523209483, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009078091657720506, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0090775993373245, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009077219415921718, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009077067414764314, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009076779438182712, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009076194781810045, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009075833566021175, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009075322658754886, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00907403941033408, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009072935380972922, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009071893461514264, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009071060193236917, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009069527280516923, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009068262251093983, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009066402141470462, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009065414478536695, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009063949258998037, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009062687591649592, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00906147931702435, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009060300739947706, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00905970432329923, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009058570412453264, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009058094997890294, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009057838721200823, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009057624037377537, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009057671341579407, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009057806383352726, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009058031297754496, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009058703526388854, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009059083936735988, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009059321542736143, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009061139519326388, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009063264338765293, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009065701784566045, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009069624757394194, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009076200863346458, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00908319097943604, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009091566768474876, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009106049644760788, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009121824542526157, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009144131026696414, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009172726336400957, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00920338165713474, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009247207727748901, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009291351297870279, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124666452407837, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123785972595215, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12290096282959, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1223604679107666, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121983528137207, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1215457916259766, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1210944652557373, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120628833770752, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.119988441467285, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1193418502807617, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.118695020675659, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.117722749710083, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1167755126953125, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1153743267059326, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.114015817642212, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1126961708068848, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.110994338989258, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1089582443237305, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.106642246246338, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.10443377494812, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1016757488250732, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0987770557403564, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.095482587814331, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.091968536376953, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.088294267654419, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0839169025421143, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0801191329956055, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.076768159866333, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0723605155944824, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.067432165145874, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.063312292098999, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.05985426902771, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.055523157119751, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.052063226699829, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.048290729522705, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0449233055114746, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.041715383529663, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0389506816864014, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0362792015075684, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.033442735671997, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.031338691711426, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.029764175415039, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.027898073196411, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.026554584503174, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0251266956329346, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0239408016204834, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.023160934448242, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.022507429122925, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0221030712127686, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07456626061277224, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07715023994093761, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07918050941306755, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08305647840531562, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08674787744555186, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09394610557401255, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09929863418235511, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09929863418235511, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1005906238464378, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10077519379844961, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10169804355850867, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1037283130306386, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10465116279069768, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10428202288667406, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10538944259874493, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10483573274270949, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10465116279069768, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10575858250276855, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10741971207087486, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10631229235880399, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10723514211886305, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.10760428202288667, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.10723514211886305, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010035399721469102, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009963191086550515, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009930831179815513, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00975767082328336, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010002085130251394, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00958107432972164, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00883660592848907, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008483150327707748, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008125016480914937, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008036696617793543, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008228214842879429, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00819745949515656, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008536020290064275, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00946512367986562, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010545598273847717, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012124495368433788, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01324590328512104, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014408918694176725, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01595782799220818, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.017267436930340694, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02073435444667539, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.024523144392268947, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.027863219101647196, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03116381886623984, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03311950004340507, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03650337417483821, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04091977046131402, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.04075607967419228, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.042645064921023684, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04263217749535895, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04538167581541905, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.047639868476277436, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04821983161937813, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04903213039124734, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04918303417734854, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.050570922166545955, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05277948580571484, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.054742926773866, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.055540185772263495, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05573010352686882, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05756604476650936, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05723101653657716, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05690877345972937, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05705370088330949, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05842139132830946, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05765871692049926, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0587806015283878, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05884872081317765, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05884089656632128, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.9203610229492187, "validation/loss_best": 3.022507429122925, "validation/acc_best": 0.10760428202288667, "validation/f1_best": 0.05884872081317765} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 3.048351889848709, "train/grad": 0.062025404758751394, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128304443359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12749755859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1265234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12585205078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.124539794921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123717041015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12287841796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1217724609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.120677490234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11952392578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.117894287109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.116300048828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11382568359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.111583251953125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.109453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10662353515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.103486328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.099818115234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.09637451171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.092032470703125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.08761474609375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0824542236328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.076951904296875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0712860107421873, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.06447509765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0584869384765625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0529571533203126, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0457275390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0373681640625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0302044677734377, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0239501953125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0158050537109373, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.008765869140625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0006787109375, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9930230712890626, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9849005126953125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.977408447265625, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.96973388671875, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.960410461425781, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.953826599121094, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9482760620117188, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.94144287109375, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9360842895507813, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.93057373046875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9254971313476563, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9219015502929686, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9187142944335935, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.916892242431641, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00892058876575902, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008898402769118548, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008881687065586447, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008874963740818203, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008872583436314016, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008871513893827796, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008870685736183078, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008870313668157905, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008869636768940837, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008869217047467827, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008868135144002736, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008867336374241858, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008866510461084545, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008864878197200596, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008863648055121303, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008862596419639886, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008860873174853623, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00885929784970358, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008857436934486032, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00885551551124081, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008853477681986988, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008851676953490824, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008849385341163725, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008846530492883175, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00884423469658941, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008841405198909342, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008839734452776611, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00883784808218479, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008836042250040919, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008834701946470886, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008833936017472297, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008833135352469981, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008833287141751498, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00883389263181016, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008835029834881426, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008835869699250907, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008836938294116407, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008838472806382924, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008841373503673821, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00884498811326921, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008849106624256819, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008853018719237297, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008859908245503902, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00886531367432326, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008873752919025719, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00888411863008514, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008894039955921472, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00890940624056384, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008923523933626712, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124636173248291, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1237735748291016, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122882604598999, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122349262237549, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121973752975464, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121530055999756, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121088743209839, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1205992698669434, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.119990587234497, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1193180084228516, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.118664026260376, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.117682695388794, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1167333126068115, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115319013595581, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1139419078826904, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.112619400024414, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.110900640487671, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1088449954986572, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.106505870819092, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1042823791503906, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1014957427978516, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0985496044158936, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0952327251434326, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.091596841812134, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0878725051879883, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.083428144454956, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0795226097106934, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0760533809661865, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.07149600982666, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.066378116607666, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.06207275390625, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0583975315093994, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.053744077682495, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0499534606933594, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0457775592803955, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.04203462600708, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.03839373588562, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0353081226348877, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0323731899261475, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0291879177093506, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0271482467651367, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.025486469268799, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0236897468566895, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0224106311798096, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.021214723587036, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0204226970672607, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0198869705200195, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0197620391845703, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0198733806610107, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0784422296050203, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08176448874123293, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08914728682170543, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09136212624584718, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09062384643779993, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09413067552602436, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09579180509413067, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09948320413436693, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10003691399040236, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10243632336655592, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10243632336655592, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10188261351052048, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10188261351052048, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.10409745293466224, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.10446659283868587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10852713178294573, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10741971207087486, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10778885197489849, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.10871170173495755, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.10981912144702842, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11037283130306386, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1111111111111111, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11221853082318199, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11166482096714656, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010079938024510774, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00993498439302104, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01005843580913794, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009823122332094182, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010033632934470202, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009643055769288271, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008910735913344993, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008569960017886999, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008084118113176554, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008131888594983422, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008150024089995411, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008238579467749958, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008833378108423254, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009703532206711872, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010884499262999697, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012291575876928931, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01344647283492647, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01470070606368732, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.016062808863104055, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01755684470639653, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02112821880986523, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.025734125641821672, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.027561167589461515, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.031236633862447554, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03363957373479562, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03842975615406009, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04057299409356601, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0409264620927701, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04269335723844305, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04337247572578525, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04525021948066354, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04770944596620994, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04800591082982275, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04997967369357193, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.050681035077671834, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05082128185038166, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05192620375172671, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.054484675482575955, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05546286663608623, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.057083959609701716, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05930697877932998, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05856131462902676, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05955151695065634, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06035043564158187, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06184545838741798, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06205582170538485, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0627834915831866, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0639633224663662, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06376325424281792, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.9187142944335935, "validation/loss_best": 3.0197620391845703, "validation/acc_best": 0.11221853082318199, "validation/f1_best": 0.0639633224663662} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 3.0510744667053222, "train/grad": 0.06285045262426138, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.131549072265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1309716796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1301513671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129619140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12907958984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128497314453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12773193359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126865234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12577392578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124642333984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123502197265625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121798095703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1202490234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.117869873046875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.115596923828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.113487548828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.110673828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1074072265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.103663330078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1002783203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.09595947265625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.091319580078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0861383056640626, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0806927490234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0748358154296875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0679974365234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.061748046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.056197509765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.048818359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.04030517578125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.03299072265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0265380859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0181494140625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.010946044921875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0027325439453123, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9948944091796874, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9867572021484374, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.97925048828125, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9714694213867188, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9620330810546873, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9550967407226563, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9493511962890624, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9422265625, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9366619873046873, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9308486938476563, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9252386474609375, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9213601684570314, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.917569885253906, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.915116271972656, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009066371782682835, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009045006562955678, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00902870278339833, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009022419010289013, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009020104249939322, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009019167653750628, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009018188004847615, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009017652424518019, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009017038487363606, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009016115225385875, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009015491160098463, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009014400315936654, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009013329695444555, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009011510808486492, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009010172646958381, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009008750913199037, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009006625758484006, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009004609461408108, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009002382918260991, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008999768323265015, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008997019585222006, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008994946724269539, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008991403081454337, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008988450332544744, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008985268892720341, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008981172491330654, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00897771371761337, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008975128973834217, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00897140266140923, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008966808198019862, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008963122200220823, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008959216275252401, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00895482044434175, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00895067882956937, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008946553007699549, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00894255175953731, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008938349327072501, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008934541398193687, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008931506520602851, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008927604923956096, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008925802905578166, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008923824753146618, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008921534079127014, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008920311506371945, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008919503442011773, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008919348164927215, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008919749762862922, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008919844552874565, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008921172686386853, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1246330738067627, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123769998550415, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122884750366211, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122345447540283, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12196683883667, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1215317249298096, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121081590652466, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120596170425415, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.119983196258545, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119310140609741, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1186630725860596, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.117676258087158, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.116734266281128, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.115312337875366, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.113924980163574, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1126067638397217, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.110877513885498, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.108820676803589, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1064658164978027, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1042399406433105, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1014363765716553, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0984954833984375, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.095162868499756, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0915329456329346, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0877673625946045, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0833449363708496, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0794129371643066, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0758981704711914, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.071338415145874, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0661611557006836, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0618205070495605, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.058159112930298, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.053480863571167, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.04958438873291, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.045384645462036, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0416147708892822, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.037933826446533, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.034721851348877, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.031661033630371, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0283286571502686, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0260672569274902, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0242209434509277, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.022136926651001, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0205328464508057, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0190041065216064, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.01763916015625, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.016765594482422, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.015815019607544, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0152688026428223, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.067921742340347, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0753045404208195, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08231819859726837, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09080841638981174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09099298634182355, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09486895533407161, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09671465485418974, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10040605389442599, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.10114433370247324, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.10188261351052048, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10243632336655592, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.10299003322259136, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10225175341454411, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1037283130306386, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1050203026947213, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10594315245478036, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.10723514211886305, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.10741971207087486, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.10834256183093392, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1094499815430048, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.11074197120708748, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.11037283130306386, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.11166482096714656, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11221853082318199, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.11351052048726468, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010079938024510774, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00993498439302104, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01005843580913794, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009819885450400108, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010033632934470202, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009631552942544952, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00880898581159489, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008576843229940392, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00809682764614982, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008131888594983422, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008157424321992722, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008238579467749958, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008833378108423254, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009828278362509943, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010762672125882326, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012306639667511374, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01351624609236584, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014703131988800562, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.016166896467186845, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0178194562036447, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0214942378449753, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0255603885949956, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.027591847453554835, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.031753036120595345, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03353769019296428, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03840214850533911, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04036272071659083, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.041118544539375926, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.042349143473574824, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04399188092556807, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04596748856954652, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.048406150577291036, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04903524250126706, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04979867148608399, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.050460935239123095, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05162005805568021, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.052315264641457006, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05387275706097164, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.056000368082042916, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05725027830916446, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.058867398384895325, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05907127662635498, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06006891086390425, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06126576876707459, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0619165075195964, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06216988305179048, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06384311759214309, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06488032388525161, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06564991315905983, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.915116271972656, "validation/loss_best": 3.0152688026428223, "validation/acc_best": 0.11351052048726468, "validation/f1_best": 0.06564991315905983} diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/config.yaml b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cd9428d653e9aa953cc486272f74c98f9d263dfe --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear +remote_dir: null diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..331afb7376f9a0ea7b7ab4330e91647e2e0cbb48 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 18, "eval/id_best": 43, "eval/lr_best": 0.006599999999999999, "eval/wd_best": 0.05, "eval/train/loss": 2.879481077194214, "eval/train/acc": 0.16165217124066505, "eval/train/acc_std": 0.0019354588929069469, "eval/train/f1": 0.12374415963161867, "eval/train/f1_std": 0.001887014383860702, "eval/validation/loss": 3.0988214015960693, "eval/validation/acc": 0.09985234403839055, "eval/validation/acc_std": 0.003640842031181821, "eval/validation/f1": 0.06452619678823363, "eval/validation/f1_std": 0.0030336272268828616, "eval/test/loss": 3.1099181175231934, "eval/test/acc": 0.09554730983302412, "eval/test/acc_std": 0.003614483775401817, "eval/test/f1": 0.05449483415174141, "eval/test/f1_std": 0.002546630842390943, "eval/testid/loss": 3.0890469551086426, "eval/testid/acc": 0.08906882591093117, "eval/testid/acc_std": 0.0037257488471356074, "eval/testid/f1": 0.05759498017735291, "eval/testid/f1_std": 0.002917014074849025} diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..bc8ae18fddb34c10a919c5e212248d19e3928d53 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 18, "eval/best/id_best": 43, "eval/best/lr_best": 0.006599999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.879481077194214, "eval/best/train/acc": 0.16165217124066505, "eval/best/train/acc_std": 0.0019354588929069469, "eval/best/train/f1": 0.12374415963161867, "eval/best/train/f1_std": 0.001887014383860702, "eval/best/validation/loss": 3.0988214015960693, "eval/best/validation/acc": 0.09985234403839055, "eval/best/validation/acc_std": 0.003640842031181821, "eval/best/validation/f1": 0.06452619678823363, "eval/best/validation/f1_std": 0.0030336272268828616, "eval/best/test/loss": 3.1099181175231934, "eval/best/test/acc": 0.09554730983302412, "eval/best/test/acc_std": 0.003614483775401817, "eval/best/test/f1": 0.05449483415174141, "eval/best/test/f1_std": 0.002546630842390943, "eval/best/testid/loss": 3.0890469551086426, "eval/best/testid/acc": 0.08906882591093117, "eval/best/testid/acc_std": 0.0037257488471356074, "eval/best/testid/f1": 0.05759498017735291, "eval/best/testid/f1_std": 0.002917014074849025} diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..64bd57016a22bc27a4143d946863b3d9ab0784d9 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 42, "eval/last/lr_best": 0.005699999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.8835718631744385, "eval/last/train/acc": 0.16057653892252374, "eval/last/train/acc_std": 0.0018725516137403234, "eval/last/train/f1": 0.12181827700813404, "eval/last/train/f1_std": 0.0018328703108259601, "eval/last/validation/loss": 3.0897200107574463, "eval/last/validation/acc": 0.0991140642303433, "eval/last/validation/acc_std": 0.0036937271359197563, "eval/last/validation/f1": 0.06544945249719547, "eval/last/validation/f1_std": 0.0031338644378837398, "eval/last/test/loss": 3.1047823429107666, "eval/last/test/acc": 0.09591836734693877, "eval/last/test/acc_std": 0.0036089969227164906, "eval/last/test/f1": 0.054489990563806094, "eval/last/test/f1_std": 0.0024231825441281235, "eval/last/testid/loss": 3.0852785110473633, "eval/last/testid/acc": 0.09196067090803933, "eval/last/testid/acc_std": 0.003719449500282173, "eval/last/testid/f1": 0.05927300427590613, "eval/last/testid/f1_std": 0.0028982974633330084} diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table.csv b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..d64b1238533b794a0973248c2d736b980887e40a --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",train,2.879481077194214,0.16165217124066505,0.0019354588929069469,0.12374415963161867,0.001887014383860702 +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",validation,3.0988214015960693,0.09985234403839055,0.003640842031181821,0.06452619678823363,0.0030336272268828616 +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",test,3.1099181175231934,0.09554730983302412,0.003614483775401817,0.05449483415174141,0.002546630842390943 +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",testid,3.0890469551086426,0.08906882591093117,0.0037257488471356074,0.05759498017735291,0.002917014074849025 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..d64b1238533b794a0973248c2d736b980887e40a --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",train,2.879481077194214,0.16165217124066505,0.0019354588929069469,0.12374415963161867,0.001887014383860702 +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",validation,3.0988214015960693,0.09985234403839055,0.003640842031181821,0.06452619678823363,0.0030336272268828616 +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",test,3.1099181175231934,0.09554730983302412,0.003614483775401817,0.05449483415174141,0.002546630842390943 +flat_mae,reg,linear,nsd_cococlip,best,18,0.006599999999999999,0.05,43,"[22, 1.0]",testid,3.0890469551086426,0.08906882591093117,0.0037257488471356074,0.05759498017735291,0.002917014074849025 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..b9b0f5de7d1477860662bc3f32c35c5b41f82b23 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",train,2.8835718631744385,0.16057653892252374,0.0018725516137403234,0.12181827700813404,0.0018328703108259601 +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",validation,3.0897200107574463,0.0991140642303433,0.0036937271359197563,0.06544945249719547,0.0031338644378837398 +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",test,3.1047823429107666,0.09591836734693877,0.0036089969227164906,0.054489990563806094,0.0024231825441281235 +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",testid,3.0852785110473633,0.09196067090803933,0.003719449500282173,0.05927300427590613,0.0028982974633330084 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/log.txt b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e1e65bd31227e6a8fe9445d0a7120927d2a88aab --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/log.txt @@ -0,0 +1,957 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 21:52:40 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:15 lr: nan time: 3.3394 data: 2.9969 max mem: 3910 +train: [0] [ 20/400] eta: 0:03:02 lr: 0.000003 loss: 3.1594 (3.1900) grad: 0.3217 (0.3215) time: 0.3382 data: 0.0060 max mem: 3953 +train: [0] [ 40/400] eta: 0:02:29 lr: 0.000006 loss: 3.2019 (3.1962) grad: 0.3170 (0.3093) time: 0.3436 data: 0.0038 max mem: 3953 +train: [0] [ 60/400] eta: 0:02:11 lr: 0.000009 loss: 3.2098 (3.2012) grad: 0.2866 (0.3014) time: 0.3342 data: 0.0042 max mem: 3953 +train: [0] [ 80/400] eta: 0:01:59 lr: 0.000012 loss: 3.1924 (3.1951) grad: 0.2756 (0.2941) time: 0.3338 data: 0.0042 max mem: 3953 +train: [0] [100/400] eta: 0:01:49 lr: 0.000015 loss: 3.1825 (3.1939) grad: 0.2668 (0.2898) time: 0.3261 data: 0.0037 max mem: 3953 +train: [0] [120/400] eta: 0:01:40 lr: 0.000018 loss: 3.1948 (3.1957) grad: 0.2703 (0.2891) time: 0.3344 data: 0.0044 max mem: 3953 +train: [0] [140/400] eta: 0:01:32 lr: 0.000021 loss: 3.1834 (3.1921) grad: 0.2876 (0.2899) time: 0.3344 data: 0.0039 max mem: 3953 +train: [0] [160/400] eta: 0:01:25 lr: 0.000024 loss: 3.1831 (3.1929) grad: 0.2945 (0.2904) time: 0.3421 data: 0.0037 max mem: 3953 +train: [0] [180/400] eta: 0:01:17 lr: 0.000027 loss: 3.1941 (3.1911) grad: 0.2914 (0.2897) time: 0.3340 data: 0.0036 max mem: 3953 +train: [0] [200/400] eta: 0:01:10 lr: 0.000030 loss: 3.1953 (3.1909) grad: 0.2808 (0.2882) time: 0.3368 data: 0.0036 max mem: 3953 +train: [0] [220/400] eta: 0:01:02 lr: 0.000033 loss: 3.1734 (3.1884) grad: 0.2685 (0.2871) time: 0.3348 data: 0.0036 max mem: 3953 +train: [0] [240/400] eta: 0:00:55 lr: 0.000036 loss: 3.1576 (3.1882) grad: 0.2737 (0.2871) time: 0.3389 data: 0.0036 max mem: 3953 +train: [0] [260/400] eta: 0:00:48 lr: 0.000039 loss: 3.1835 (3.1871) grad: 0.2730 (0.2860) time: 0.3482 data: 0.0037 max mem: 3953 +train: [0] [280/400] eta: 0:00:41 lr: 0.000042 loss: 3.1835 (3.1875) grad: 0.2706 (0.2859) time: 0.3427 data: 0.0042 max mem: 3953 +train: [0] [300/400] eta: 0:00:34 lr: 0.000045 loss: 3.1766 (3.1867) grad: 0.2952 (0.2869) time: 0.3446 data: 0.0041 max mem: 3953 +train: [0] [320/400] eta: 0:00:27 lr: 0.000048 loss: 3.1709 (3.1848) grad: 0.2953 (0.2866) time: 0.3550 data: 0.0040 max mem: 3953 +train: [0] [340/400] eta: 0:00:20 lr: 0.000051 loss: 3.1798 (3.1857) grad: 0.2920 (0.2863) time: 0.3364 data: 0.0044 max mem: 3953 +train: [0] [360/400] eta: 0:00:13 lr: 0.000054 loss: 3.1896 (3.1856) grad: 0.2799 (0.2865) time: 0.3393 data: 0.0036 max mem: 3953 +train: [0] [380/400] eta: 0:00:06 lr: 0.000057 loss: 3.1707 (3.1843) grad: 0.2799 (0.2863) time: 0.3447 data: 0.0040 max mem: 3953 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1637 (3.1835) grad: 0.2815 (0.2871) time: 0.3393 data: 0.0039 max mem: 3953 +train: [0] Total time: 0:02:18 (0.3468 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1637 (3.1835) grad: 0.2815 (0.2871) +eval (validation): [0] [ 0/85] eta: 0:04:43 time: 3.3296 data: 3.0751 max mem: 3953 +eval (validation): [0] [20/85] eta: 0:00:32 time: 0.3514 data: 0.0041 max mem: 3953 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3205 data: 0.0042 max mem: 3953 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3127 data: 0.0046 max mem: 3953 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3104 data: 0.0039 max mem: 3953 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3009 data: 0.0039 max mem: 3953 +eval (validation): [0] Total time: 0:00:30 (0.3609 s / it) +cv: [0] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 3.157 acc: 0.065 f1: 0.017 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:25 lr: nan time: 3.3631 data: 3.1140 max mem: 3953 +train: [1] [ 20/400] eta: 0:03:21 lr: 0.000063 loss: 3.1458 (3.1548) grad: 0.2733 (0.2762) time: 0.3885 data: 0.0049 max mem: 3953 +train: [1] [ 40/400] eta: 0:02:38 lr: 0.000066 loss: 3.1604 (3.1589) grad: 0.2722 (0.2742) time: 0.3452 data: 0.0038 max mem: 3953 +train: [1] [ 60/400] eta: 0:02:17 lr: 0.000069 loss: 3.1632 (3.1634) grad: 0.2755 (0.2785) time: 0.3354 data: 0.0043 max mem: 3953 +train: [1] [ 80/400] eta: 0:02:04 lr: 0.000072 loss: 3.1569 (3.1595) grad: 0.2834 (0.2817) time: 0.3324 data: 0.0042 max mem: 3953 +train: [1] [100/400] eta: 0:01:53 lr: 0.000075 loss: 3.1801 (3.1651) grad: 0.2834 (0.2822) time: 0.3358 data: 0.0048 max mem: 3953 +train: [1] [120/400] eta: 0:01:43 lr: 0.000078 loss: 3.1720 (3.1635) grad: 0.2717 (0.2792) time: 0.3251 data: 0.0041 max mem: 3953 +train: [1] [140/400] eta: 0:01:34 lr: 0.000081 loss: 3.1577 (3.1622) grad: 0.2769 (0.2795) time: 0.3407 data: 0.0043 max mem: 3953 +train: [1] [160/400] eta: 0:01:26 lr: 0.000084 loss: 3.1831 (3.1666) grad: 0.2789 (0.2786) time: 0.3444 data: 0.0045 max mem: 3953 +train: [1] [180/400] eta: 0:01:19 lr: 0.000087 loss: 3.1852 (3.1668) grad: 0.2695 (0.2780) time: 0.3440 data: 0.0040 max mem: 3953 +train: [1] [200/400] eta: 0:01:11 lr: 0.000090 loss: 3.1669 (3.1660) grad: 0.2678 (0.2767) time: 0.3451 data: 0.0044 max mem: 3953 +train: [1] [220/400] eta: 0:01:04 lr: 0.000093 loss: 3.1741 (3.1662) grad: 0.2874 (0.2789) time: 0.3363 data: 0.0039 max mem: 3953 +train: [1] [240/400] eta: 0:00:56 lr: 0.000096 loss: 3.1636 (3.1656) grad: 0.2948 (0.2795) time: 0.3357 data: 0.0038 max mem: 3953 +train: [1] [260/400] eta: 0:00:49 lr: 0.000099 loss: 3.1571 (3.1682) grad: 0.2905 (0.2798) time: 0.3324 data: 0.0041 max mem: 3953 +train: [1] [280/400] eta: 0:00:42 lr: 0.000102 loss: 3.1571 (3.1658) grad: 0.2905 (0.2808) time: 0.3323 data: 0.0042 max mem: 3953 +train: [1] [300/400] eta: 0:00:35 lr: 0.000105 loss: 3.1436 (3.1654) grad: 0.2842 (0.2803) time: 0.3339 data: 0.0036 max mem: 3953 +train: [1] [320/400] eta: 0:00:27 lr: 0.000108 loss: 3.1724 (3.1663) grad: 0.2787 (0.2797) time: 0.3281 data: 0.0043 max mem: 3953 +train: [1] [340/400] eta: 0:00:20 lr: 0.000111 loss: 3.1760 (3.1663) grad: 0.2762 (0.2798) time: 0.3300 data: 0.0040 max mem: 3953 +train: [1] [360/400] eta: 0:00:13 lr: 0.000114 loss: 3.1685 (3.1669) grad: 0.2691 (0.2792) time: 0.3216 data: 0.0041 max mem: 3953 +train: [1] [380/400] eta: 0:00:06 lr: 0.000117 loss: 3.1634 (3.1663) grad: 0.2729 (0.2803) time: 0.3375 data: 0.0042 max mem: 3953 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.1528 (3.1661) grad: 0.2906 (0.2805) time: 0.3549 data: 0.0045 max mem: 3953 +train: [1] Total time: 0:02:18 (0.3467 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.1528 (3.1661) grad: 0.2906 (0.2805) +eval (validation): [1] [ 0/85] eta: 0:04:55 time: 3.4819 data: 3.2091 max mem: 3953 +eval (validation): [1] [20/85] eta: 0:00:34 time: 0.3765 data: 0.0052 max mem: 3953 +eval (validation): [1] [40/85] eta: 0:00:19 time: 0.3205 data: 0.0039 max mem: 3953 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3323 data: 0.0048 max mem: 3953 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.2969 data: 0.0042 max mem: 3953 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.2919 data: 0.0039 max mem: 3953 +eval (validation): [1] Total time: 0:00:31 (0.3707 s / it) +cv: [1] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 3.260 acc: 0.068 f1: 0.020 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:21:39 lr: nan time: 3.2499 data: 3.0354 max mem: 3953 +train: [2] [ 20/400] eta: 0:03:08 lr: 0.000123 loss: 3.1352 (3.1518) grad: 0.2633 (0.2728) time: 0.3597 data: 0.0050 max mem: 3953 +train: [2] [ 40/400] eta: 0:02:33 lr: 0.000126 loss: 3.1534 (3.1601) grad: 0.2672 (0.2785) time: 0.3511 data: 0.0035 max mem: 3953 +train: [2] [ 60/400] eta: 0:02:16 lr: 0.000129 loss: 3.1504 (3.1569) grad: 0.2687 (0.2747) time: 0.3482 data: 0.0043 max mem: 3953 +train: [2] [ 80/400] eta: 0:02:04 lr: 0.000132 loss: 3.1499 (3.1516) grad: 0.2629 (0.2758) time: 0.3501 data: 0.0041 max mem: 3953 +train: [2] [100/400] eta: 0:01:52 lr: 0.000135 loss: 3.1499 (3.1517) grad: 0.2788 (0.2794) time: 0.3301 data: 0.0042 max mem: 3953 +train: [2] [120/400] eta: 0:01:44 lr: 0.000138 loss: 3.1670 (3.1575) grad: 0.2860 (0.2809) time: 0.3567 data: 0.0046 max mem: 3953 +train: [2] [140/400] eta: 0:01:35 lr: 0.000141 loss: 3.1777 (3.1594) grad: 0.2829 (0.2811) time: 0.3400 data: 0.0040 max mem: 3953 +train: [2] [160/400] eta: 0:01:27 lr: 0.000144 loss: 3.1692 (3.1623) grad: 0.2810 (0.2819) time: 0.3416 data: 0.0039 max mem: 3953 +train: [2] [180/400] eta: 0:01:19 lr: 0.000147 loss: 3.1759 (3.1632) grad: 0.2850 (0.2827) time: 0.3336 data: 0.0042 max mem: 3953 +train: [2] [200/400] eta: 0:01:11 lr: 0.000150 loss: 3.1526 (3.1623) grad: 0.2843 (0.2837) time: 0.3354 data: 0.0043 max mem: 3953 +train: [2] [220/400] eta: 0:01:04 lr: 0.000153 loss: 3.1496 (3.1603) grad: 0.2843 (0.2850) time: 0.3330 data: 0.0041 max mem: 3953 +train: [2] [240/400] eta: 0:00:56 lr: 0.000156 loss: 3.1594 (3.1621) grad: 0.2778 (0.2861) time: 0.3323 data: 0.0042 max mem: 3953 +train: [2] [260/400] eta: 0:00:49 lr: 0.000159 loss: 3.1743 (3.1632) grad: 0.2778 (0.2856) time: 0.3486 data: 0.0041 max mem: 3953 +train: [2] [280/400] eta: 0:00:42 lr: 0.000162 loss: 3.1647 (3.1622) grad: 0.2867 (0.2862) time: 0.3409 data: 0.0038 max mem: 3953 +train: [2] [300/400] eta: 0:00:35 lr: 0.000165 loss: 3.1511 (3.1625) grad: 0.2867 (0.2856) time: 0.3528 data: 0.0038 max mem: 3953 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 3.1589 (3.1627) grad: 0.2845 (0.2852) time: 0.3536 data: 0.0044 max mem: 3953 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 3.1664 (3.1636) grad: 0.2867 (0.2856) time: 0.3346 data: 0.0043 max mem: 3953 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 3.1557 (3.1635) grad: 0.2722 (0.2844) time: 0.3432 data: 0.0037 max mem: 3953 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 3.1642 (3.1655) grad: 0.2639 (0.2841) time: 0.3407 data: 0.0042 max mem: 3953 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.1897 (3.1670) grad: 0.2880 (0.2849) time: 0.3450 data: 0.0044 max mem: 3953 +train: [2] Total time: 0:02:20 (0.3511 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.1897 (3.1670) grad: 0.2880 (0.2849) +eval (validation): [2] [ 0/85] eta: 0:04:52 time: 3.4458 data: 3.1876 max mem: 3953 +eval (validation): [2] [20/85] eta: 0:00:33 time: 0.3732 data: 0.0062 max mem: 3953 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3218 data: 0.0040 max mem: 3953 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3412 data: 0.0042 max mem: 3953 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3393 data: 0.0042 max mem: 3953 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3146 data: 0.0041 max mem: 3953 +eval (validation): [2] Total time: 0:00:32 (0.3822 s / it) +cv: [2] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 3.139 acc: 0.068 f1: 0.026 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [3] [ 0/400] eta: 0:22:48 lr: nan time: 3.4211 data: 3.2090 max mem: 3953 +train: [3] [ 20/400] eta: 0:03:07 lr: 0.000183 loss: 3.1593 (3.1664) grad: 0.2881 (0.2911) time: 0.3479 data: 0.0041 max mem: 3953 +train: [3] [ 40/400] eta: 0:02:29 lr: 0.000186 loss: 3.1504 (3.1520) grad: 0.2770 (0.2858) time: 0.3352 data: 0.0040 max mem: 3953 +train: [3] [ 60/400] eta: 0:02:12 lr: 0.000189 loss: 3.1566 (3.1651) grad: 0.2755 (0.2850) time: 0.3364 data: 0.0040 max mem: 3953 +train: [3] [ 80/400] eta: 0:02:02 lr: 0.000192 loss: 3.1770 (3.1655) grad: 0.2891 (0.2919) time: 0.3583 data: 0.0044 max mem: 3953 +train: [3] [100/400] eta: 0:01:52 lr: 0.000195 loss: 3.1662 (3.1669) grad: 0.2960 (0.2896) time: 0.3478 data: 0.0043 max mem: 3953 +train: [3] [120/400] eta: 0:01:43 lr: 0.000198 loss: 3.1579 (3.1647) grad: 0.2791 (0.2872) time: 0.3436 data: 0.0042 max mem: 3953 +train: [3] [140/400] eta: 0:01:35 lr: 0.000201 loss: 3.1493 (3.1665) grad: 0.2818 (0.2881) time: 0.3426 data: 0.0042 max mem: 3953 +train: [3] [160/400] eta: 0:01:27 lr: 0.000204 loss: 3.1411 (3.1638) grad: 0.2922 (0.2905) time: 0.3390 data: 0.0041 max mem: 3953 +train: [3] [180/400] eta: 0:01:19 lr: 0.000207 loss: 3.1539 (3.1652) grad: 0.3073 (0.2930) time: 0.3383 data: 0.0039 max mem: 3953 +train: [3] [200/400] eta: 0:01:11 lr: 0.000210 loss: 3.1773 (3.1672) grad: 0.3060 (0.2935) time: 0.3428 data: 0.0042 max mem: 3953 +train: [3] [220/400] eta: 0:01:04 lr: 0.000213 loss: 3.1780 (3.1687) grad: 0.2905 (0.2936) time: 0.3428 data: 0.0041 max mem: 3953 +train: [3] [240/400] eta: 0:00:56 lr: 0.000216 loss: 3.1780 (3.1707) grad: 0.2879 (0.2941) time: 0.3420 data: 0.0040 max mem: 3953 +train: [3] [260/400] eta: 0:00:49 lr: 0.000219 loss: 3.1779 (3.1712) grad: 0.2992 (0.2948) time: 0.3380 data: 0.0040 max mem: 3953 +train: [3] [280/400] eta: 0:00:42 lr: 0.000222 loss: 3.1779 (3.1712) grad: 0.3010 (0.2955) time: 0.3246 data: 0.0041 max mem: 3953 +train: [3] [300/400] eta: 0:00:35 lr: 0.000225 loss: 3.1592 (3.1704) grad: 0.2972 (0.2950) time: 0.3495 data: 0.0042 max mem: 3953 +train: [3] [320/400] eta: 0:00:28 lr: 0.000228 loss: 3.1757 (3.1714) grad: 0.2877 (0.2950) time: 0.3440 data: 0.0041 max mem: 3953 +train: [3] [340/400] eta: 0:00:21 lr: 0.000231 loss: 3.1782 (3.1713) grad: 0.2917 (0.2954) time: 0.3425 data: 0.0041 max mem: 3953 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 3.1741 (3.1715) grad: 0.2852 (0.2949) time: 0.3404 data: 0.0040 max mem: 3953 +train: [3] [380/400] eta: 0:00:06 lr: 0.000237 loss: 3.1713 (3.1710) grad: 0.2839 (0.2952) time: 0.3181 data: 0.0042 max mem: 3953 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.1719 (3.1718) grad: 0.3025 (0.2957) time: 0.3536 data: 0.0041 max mem: 3953 +train: [3] Total time: 0:02:19 (0.3493 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.1719 (3.1718) grad: 0.3025 (0.2957) +eval (validation): [3] [ 0/85] eta: 0:04:59 time: 3.5284 data: 3.2492 max mem: 3953 +eval (validation): [3] [20/85] eta: 0:00:32 time: 0.3500 data: 0.0053 max mem: 3953 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3134 data: 0.0040 max mem: 3953 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3659 data: 0.0041 max mem: 3953 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3150 data: 0.0039 max mem: 3953 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3079 data: 0.0042 max mem: 3953 +eval (validation): [3] Total time: 0:00:31 (0.3757 s / it) +cv: [3] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 3.179 acc: 0.082 f1: 0.037 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:49 lr: nan time: 3.4236 data: 3.1516 max mem: 3953 +train: [4] [ 20/400] eta: 0:03:16 lr: 0.000243 loss: 3.1280 (3.1505) grad: 0.2834 (0.2854) time: 0.3725 data: 0.0044 max mem: 3953 +train: [4] [ 40/400] eta: 0:02:34 lr: 0.000246 loss: 3.1280 (3.1463) grad: 0.2765 (0.2799) time: 0.3367 data: 0.0046 max mem: 3953 +train: [4] [ 60/400] eta: 0:02:16 lr: 0.000249 loss: 3.1369 (3.1488) grad: 0.2765 (0.2805) time: 0.3473 data: 0.0039 max mem: 3953 +train: [4] [ 80/400] eta: 0:02:03 lr: 0.000252 loss: 3.1451 (3.1472) grad: 0.2900 (0.2841) time: 0.3374 data: 0.0044 max mem: 3953 +train: [4] [100/400] eta: 0:01:53 lr: 0.000255 loss: 3.1570 (3.1510) grad: 0.2974 (0.2898) time: 0.3388 data: 0.0041 max mem: 3953 +train: [4] [120/400] eta: 0:01:43 lr: 0.000258 loss: 3.1558 (3.1534) grad: 0.3000 (0.2939) time: 0.3334 data: 0.0054 max mem: 3953 +train: [4] [140/400] eta: 0:01:34 lr: 0.000261 loss: 3.1362 (3.1537) grad: 0.3010 (0.2947) time: 0.3348 data: 0.0033 max mem: 3953 +train: [4] [160/400] eta: 0:01:27 lr: 0.000264 loss: 3.1587 (3.1563) grad: 0.2986 (0.2944) time: 0.3464 data: 0.0043 max mem: 3953 +train: [4] [180/400] eta: 0:01:19 lr: 0.000267 loss: 3.1587 (3.1557) grad: 0.2876 (0.2943) time: 0.3363 data: 0.0042 max mem: 3953 +train: [4] [200/400] eta: 0:01:11 lr: 0.000270 loss: 3.1524 (3.1565) grad: 0.3020 (0.2953) time: 0.3424 data: 0.0043 max mem: 3953 +train: [4] [220/400] eta: 0:01:04 lr: 0.000273 loss: 3.1562 (3.1577) grad: 0.3026 (0.2958) time: 0.3395 data: 0.0035 max mem: 3953 +train: [4] [240/400] eta: 0:00:56 lr: 0.000276 loss: 3.1669 (3.1604) grad: 0.3034 (0.2971) time: 0.3474 data: 0.0040 max mem: 3953 +train: [4] [260/400] eta: 0:00:49 lr: 0.000279 loss: 3.1689 (3.1616) grad: 0.3029 (0.2964) time: 0.3569 data: 0.0045 max mem: 3953 +train: [4] [280/400] eta: 0:00:42 lr: 0.000282 loss: 3.1730 (3.1630) grad: 0.2999 (0.2967) time: 0.3393 data: 0.0042 max mem: 3953 +train: [4] [300/400] eta: 0:00:35 lr: 0.000285 loss: 3.1730 (3.1637) grad: 0.3017 (0.2973) time: 0.3529 data: 0.0045 max mem: 3953 +train: [4] [320/400] eta: 0:00:28 lr: 0.000288 loss: 3.1892 (3.1662) grad: 0.3078 (0.2978) time: 0.3617 data: 0.0045 max mem: 3953 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 3.1905 (3.1672) grad: 0.3118 (0.2990) time: 0.3787 data: 0.0045 max mem: 3953 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 3.1800 (3.1679) grad: 0.3115 (0.2995) time: 0.3349 data: 0.0045 max mem: 3953 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1770 (3.1690) grad: 0.3061 (0.3002) time: 0.3360 data: 0.0042 max mem: 3953 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.1775 (3.1695) grad: 0.2975 (0.3005) time: 0.3477 data: 0.0042 max mem: 3953 +train: [4] Total time: 0:02:21 (0.3540 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.1775 (3.1695) grad: 0.2975 (0.3005) +eval (validation): [4] [ 0/85] eta: 0:04:47 time: 3.3814 data: 3.1803 max mem: 3953 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3405 data: 0.0389 max mem: 3953 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3475 data: 0.0040 max mem: 3953 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3362 data: 0.0045 max mem: 3953 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3416 data: 0.0039 max mem: 3953 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3182 data: 0.0041 max mem: 3953 +eval (validation): [4] Total time: 0:00:32 (0.3797 s / it) +cv: [4] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 3.130 acc: 0.079 f1: 0.030 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:57 lr: nan time: 3.4437 data: 3.1768 max mem: 3953 +train: [5] [ 20/400] eta: 0:03:09 lr: 0.000300 loss: 3.1416 (3.1367) grad: 0.3007 (0.3011) time: 0.3518 data: 0.0151 max mem: 3953 +train: [5] [ 40/400] eta: 0:02:30 lr: 0.000300 loss: 3.1554 (3.1484) grad: 0.3007 (0.2969) time: 0.3349 data: 0.0107 max mem: 3953 +train: [5] [ 60/400] eta: 0:02:17 lr: 0.000300 loss: 3.1721 (3.1559) grad: 0.2972 (0.2989) time: 0.3707 data: 0.0034 max mem: 3953 +train: [5] [ 80/400] eta: 0:02:04 lr: 0.000300 loss: 3.1690 (3.1574) grad: 0.2949 (0.2976) time: 0.3481 data: 0.0044 max mem: 3953 +train: [5] [100/400] eta: 0:01:54 lr: 0.000300 loss: 3.1427 (3.1555) grad: 0.3020 (0.2986) time: 0.3488 data: 0.0040 max mem: 3953 +train: [5] [120/400] eta: 0:01:44 lr: 0.000300 loss: 3.1528 (3.1602) grad: 0.2993 (0.2980) time: 0.3394 data: 0.0040 max mem: 3953 +train: [5] [140/400] eta: 0:01:35 lr: 0.000300 loss: 3.1652 (3.1608) grad: 0.2967 (0.2992) time: 0.3333 data: 0.0035 max mem: 3953 +train: [5] [160/400] eta: 0:01:27 lr: 0.000299 loss: 3.1536 (3.1598) grad: 0.3106 (0.3021) time: 0.3366 data: 0.0040 max mem: 3953 +train: [5] [180/400] eta: 0:01:20 lr: 0.000299 loss: 3.1506 (3.1603) grad: 0.3133 (0.3044) time: 0.3558 data: 0.0040 max mem: 3953 +train: [5] [200/400] eta: 0:01:12 lr: 0.000299 loss: 3.1354 (3.1574) grad: 0.3041 (0.3046) time: 0.3452 data: 0.0040 max mem: 3953 +train: [5] [220/400] eta: 0:01:04 lr: 0.000299 loss: 3.1331 (3.1567) grad: 0.2971 (0.3037) time: 0.3465 data: 0.0037 max mem: 3953 +train: [5] [240/400] eta: 0:00:57 lr: 0.000299 loss: 3.1727 (3.1589) grad: 0.3063 (0.3044) time: 0.3556 data: 0.0039 max mem: 3953 +train: [5] [260/400] eta: 0:00:50 lr: 0.000299 loss: 3.1788 (3.1604) grad: 0.3063 (0.3047) time: 0.3302 data: 0.0039 max mem: 3953 +train: [5] [280/400] eta: 0:00:42 lr: 0.000298 loss: 3.1678 (3.1607) grad: 0.3031 (0.3044) time: 0.3307 data: 0.0041 max mem: 3953 +train: [5] [300/400] eta: 0:00:35 lr: 0.000298 loss: 3.1653 (3.1622) grad: 0.2954 (0.3036) time: 0.3367 data: 0.0042 max mem: 3953 +train: [5] [320/400] eta: 0:00:28 lr: 0.000298 loss: 3.1809 (3.1626) grad: 0.2882 (0.3028) time: 0.3338 data: 0.0042 max mem: 3953 +train: [5] [340/400] eta: 0:00:21 lr: 0.000298 loss: 3.1536 (3.1611) grad: 0.2895 (0.3027) time: 0.3335 data: 0.0041 max mem: 3953 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 3.1398 (3.1612) grad: 0.3048 (0.3033) time: 0.3303 data: 0.0039 max mem: 3953 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1767 (3.1624) grad: 0.2956 (0.3026) time: 0.3348 data: 0.0040 max mem: 3953 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 3.1818 (3.1625) grad: 0.2952 (0.3026) time: 0.3351 data: 0.0041 max mem: 3953 +train: [5] Total time: 0:02:19 (0.3496 s / it) +train: [5] Summary: lr: 0.000297 loss: 3.1818 (3.1625) grad: 0.2952 (0.3026) +eval (validation): [5] [ 0/85] eta: 0:04:43 time: 3.3316 data: 3.0732 max mem: 3953 +eval (validation): [5] [20/85] eta: 0:00:32 time: 0.3652 data: 0.0125 max mem: 3953 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3459 data: 0.0035 max mem: 3953 +eval (validation): [5] [60/85] eta: 0:00:10 time: 0.3569 data: 0.0045 max mem: 3953 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3400 data: 0.0046 max mem: 3953 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3259 data: 0.0043 max mem: 3953 +eval (validation): [5] Total time: 0:00:33 (0.3889 s / it) +cv: [5] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 3.169 acc: 0.080 f1: 0.036 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:28:33 lr: nan time: 4.2842 data: 4.0140 max mem: 3953 +train: [6] [ 20/400] eta: 0:03:23 lr: 0.000296 loss: 3.1160 (3.1546) grad: 0.3017 (0.3075) time: 0.3470 data: 0.0030 max mem: 3953 +train: [6] [ 40/400] eta: 0:02:38 lr: 0.000296 loss: 3.1275 (3.1439) grad: 0.2976 (0.3014) time: 0.3401 data: 0.0045 max mem: 3953 +train: [6] [ 60/400] eta: 0:02:17 lr: 0.000296 loss: 3.1275 (3.1439) grad: 0.2882 (0.3006) time: 0.3318 data: 0.0029 max mem: 3953 +train: [6] [ 80/400] eta: 0:02:03 lr: 0.000295 loss: 3.1439 (3.1431) grad: 0.2929 (0.3010) time: 0.3285 data: 0.0039 max mem: 3953 +train: [6] [100/400] eta: 0:01:51 lr: 0.000295 loss: 3.1506 (3.1450) grad: 0.2957 (0.2998) time: 0.3235 data: 0.0040 max mem: 3953 +train: [6] [120/400] eta: 0:01:42 lr: 0.000295 loss: 3.1564 (3.1455) grad: 0.2956 (0.2976) time: 0.3222 data: 0.0041 max mem: 3953 +train: [6] [140/400] eta: 0:01:33 lr: 0.000294 loss: 3.1534 (3.1478) grad: 0.2972 (0.2986) time: 0.3320 data: 0.0036 max mem: 3953 +train: [6] [160/400] eta: 0:01:25 lr: 0.000294 loss: 3.1523 (3.1466) grad: 0.3024 (0.2995) time: 0.3392 data: 0.0042 max mem: 3953 +train: [6] [180/400] eta: 0:01:18 lr: 0.000293 loss: 3.1411 (3.1497) grad: 0.3024 (0.3008) time: 0.3335 data: 0.0041 max mem: 3953 +train: [6] [200/400] eta: 0:01:10 lr: 0.000293 loss: 3.1411 (3.1487) grad: 0.2990 (0.3006) time: 0.3301 data: 0.0041 max mem: 3953 +train: [6] [220/400] eta: 0:01:03 lr: 0.000292 loss: 3.1444 (3.1482) grad: 0.3039 (0.3011) time: 0.3348 data: 0.0040 max mem: 3953 +train: [6] [240/400] eta: 0:00:55 lr: 0.000292 loss: 3.1462 (3.1495) grad: 0.3073 (0.3013) time: 0.3254 data: 0.0040 max mem: 3953 +train: [6] [260/400] eta: 0:00:48 lr: 0.000291 loss: 3.1432 (3.1494) grad: 0.3035 (0.3018) time: 0.3428 data: 0.0042 max mem: 3953 +train: [6] [280/400] eta: 0:00:41 lr: 0.000291 loss: 3.1378 (3.1478) grad: 0.3006 (0.3014) time: 0.3314 data: 0.0044 max mem: 3953 +train: [6] [300/400] eta: 0:00:34 lr: 0.000290 loss: 3.1543 (3.1497) grad: 0.3016 (0.3017) time: 0.3550 data: 0.0040 max mem: 3953 +train: [6] [320/400] eta: 0:00:27 lr: 0.000290 loss: 3.1629 (3.1501) grad: 0.3029 (0.3015) time: 0.3392 data: 0.0040 max mem: 3953 +train: [6] [340/400] eta: 0:00:20 lr: 0.000289 loss: 3.1576 (3.1503) grad: 0.2876 (0.3002) time: 0.3365 data: 0.0043 max mem: 3953 +train: [6] [360/400] eta: 0:00:13 lr: 0.000288 loss: 3.1719 (3.1509) grad: 0.2858 (0.3001) time: 0.3265 data: 0.0042 max mem: 3953 +train: [6] [380/400] eta: 0:00:06 lr: 0.000288 loss: 3.1549 (3.1501) grad: 0.3014 (0.3004) time: 0.3674 data: 0.0040 max mem: 3953 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 3.1514 (3.1506) grad: 0.2885 (0.2995) time: 0.3479 data: 0.0044 max mem: 3953 +train: [6] Total time: 0:02:18 (0.3468 s / it) +train: [6] Summary: lr: 0.000287 loss: 3.1514 (3.1506) grad: 0.2885 (0.2995) +eval (validation): [6] [ 0/85] eta: 0:04:55 time: 3.4774 data: 3.2374 max mem: 3953 +eval (validation): [6] [20/85] eta: 0:00:30 time: 0.3205 data: 0.0034 max mem: 3953 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3562 data: 0.0048 max mem: 3953 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3203 data: 0.0042 max mem: 3953 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3101 data: 0.0038 max mem: 3953 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3011 data: 0.0041 max mem: 3953 +eval (validation): [6] Total time: 0:00:31 (0.3664 s / it) +cv: [6] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.291 acc: 0.087 f1: 0.043 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:21:58 lr: nan time: 3.2951 data: 3.0396 max mem: 3953 +train: [7] [ 20/400] eta: 0:03:31 lr: 0.000286 loss: 3.1220 (3.1083) grad: 0.2864 (0.2973) time: 0.4199 data: 0.0281 max mem: 3953 +train: [7] [ 40/400] eta: 0:02:42 lr: 0.000286 loss: 3.1098 (3.0976) grad: 0.2876 (0.3014) time: 0.3418 data: 0.0036 max mem: 3953 +train: [7] [ 60/400] eta: 0:02:25 lr: 0.000285 loss: 3.1038 (3.1031) grad: 0.2971 (0.3013) time: 0.3752 data: 0.0041 max mem: 3953 +train: [7] [ 80/400] eta: 0:02:10 lr: 0.000284 loss: 3.1275 (3.1147) grad: 0.2971 (0.3015) time: 0.3541 data: 0.0047 max mem: 3953 +train: [7] [100/400] eta: 0:01:58 lr: 0.000284 loss: 3.1496 (3.1220) grad: 0.2992 (0.3007) time: 0.3317 data: 0.0039 max mem: 3953 +train: [7] [120/400] eta: 0:01:47 lr: 0.000283 loss: 3.1409 (3.1214) grad: 0.3060 (0.3033) time: 0.3359 data: 0.0041 max mem: 3953 +train: [7] [140/400] eta: 0:01:37 lr: 0.000282 loss: 3.1480 (3.1275) grad: 0.3055 (0.3036) time: 0.3327 data: 0.0040 max mem: 3953 +train: [7] [160/400] eta: 0:01:29 lr: 0.000282 loss: 3.1816 (3.1353) grad: 0.3022 (0.3044) time: 0.3392 data: 0.0046 max mem: 3953 +train: [7] [180/400] eta: 0:01:22 lr: 0.000281 loss: 3.1346 (3.1332) grad: 0.3000 (0.3042) time: 0.3819 data: 0.0043 max mem: 3953 +train: [7] [200/400] eta: 0:01:13 lr: 0.000280 loss: 3.1492 (3.1371) grad: 0.3019 (0.3046) time: 0.3289 data: 0.0047 max mem: 3953 +train: [7] [220/400] eta: 0:01:05 lr: 0.000279 loss: 3.1609 (3.1386) grad: 0.3019 (0.3038) time: 0.3229 data: 0.0039 max mem: 3953 +train: [7] [240/400] eta: 0:00:57 lr: 0.000278 loss: 3.1510 (3.1393) grad: 0.3068 (0.3052) time: 0.3186 data: 0.0038 max mem: 3953 +train: [7] [260/400] eta: 0:00:50 lr: 0.000278 loss: 3.1649 (3.1430) grad: 0.3093 (0.3047) time: 0.3510 data: 0.0041 max mem: 3953 +train: [7] [280/400] eta: 0:00:43 lr: 0.000277 loss: 3.1649 (3.1447) grad: 0.3068 (0.3059) time: 0.3465 data: 0.0043 max mem: 3953 +train: [7] [300/400] eta: 0:00:35 lr: 0.000276 loss: 3.1417 (3.1429) grad: 0.3081 (0.3061) time: 0.3313 data: 0.0042 max mem: 3953 +train: [7] [320/400] eta: 0:00:28 lr: 0.000275 loss: 3.1485 (3.1444) grad: 0.3075 (0.3063) time: 0.3327 data: 0.0041 max mem: 3953 +train: [7] [340/400] eta: 0:00:21 lr: 0.000274 loss: 3.1503 (3.1427) grad: 0.3108 (0.3065) time: 0.3126 data: 0.0040 max mem: 3953 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 3.1110 (3.1432) grad: 0.3108 (0.3064) time: 0.3363 data: 0.0042 max mem: 3953 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 3.1501 (3.1436) grad: 0.3007 (0.3066) time: 0.3340 data: 0.0044 max mem: 3953 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 3.1249 (3.1415) grad: 0.2986 (0.3069) time: 0.3313 data: 0.0041 max mem: 3953 +train: [7] Total time: 0:02:20 (0.3507 s / it) +train: [7] Summary: lr: 0.000271 loss: 3.1249 (3.1415) grad: 0.2986 (0.3069) +eval (validation): [7] [ 0/85] eta: 0:04:43 time: 3.3352 data: 3.1243 max mem: 3953 +eval (validation): [7] [20/85] eta: 0:00:30 time: 0.3277 data: 0.0036 max mem: 3953 +eval (validation): [7] [40/85] eta: 0:00:17 time: 0.3249 data: 0.0042 max mem: 3953 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3570 data: 0.0049 max mem: 3953 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3325 data: 0.0039 max mem: 3953 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3190 data: 0.0038 max mem: 3953 +eval (validation): [7] Total time: 0:00:31 (0.3726 s / it) +cv: [7] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 3.229 acc: 0.085 f1: 0.039 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:35 lr: nan time: 3.3881 data: 3.1342 max mem: 3953 +train: [8] [ 20/400] eta: 0:02:59 lr: 0.000270 loss: 3.1209 (3.1364) grad: 0.2948 (0.2966) time: 0.3266 data: 0.0040 max mem: 3953 +train: [8] [ 40/400] eta: 0:02:26 lr: 0.000270 loss: 3.1272 (3.1351) grad: 0.2948 (0.2960) time: 0.3374 data: 0.0043 max mem: 3953 +train: [8] [ 60/400] eta: 0:02:10 lr: 0.000269 loss: 3.1272 (3.1368) grad: 0.2869 (0.2971) time: 0.3401 data: 0.0037 max mem: 3953 +train: [8] [ 80/400] eta: 0:01:59 lr: 0.000268 loss: 3.1196 (3.1303) grad: 0.2849 (0.2945) time: 0.3402 data: 0.0041 max mem: 3953 +train: [8] [100/400] eta: 0:01:49 lr: 0.000267 loss: 3.1309 (3.1341) grad: 0.2971 (0.2976) time: 0.3361 data: 0.0042 max mem: 3953 +train: [8] [120/400] eta: 0:01:41 lr: 0.000266 loss: 3.1232 (3.1290) grad: 0.2897 (0.2951) time: 0.3349 data: 0.0045 max mem: 3953 +train: [8] [140/400] eta: 0:01:32 lr: 0.000265 loss: 3.1033 (3.1250) grad: 0.2823 (0.2950) time: 0.3332 data: 0.0044 max mem: 3953 +train: [8] [160/400] eta: 0:01:25 lr: 0.000264 loss: 3.1118 (3.1253) grad: 0.2805 (0.2939) time: 0.3534 data: 0.0047 max mem: 3953 +train: [8] [180/400] eta: 0:01:18 lr: 0.000263 loss: 3.1173 (3.1249) grad: 0.2866 (0.2932) time: 0.3396 data: 0.0042 max mem: 3953 +train: [8] [200/400] eta: 0:01:11 lr: 0.000262 loss: 3.1167 (3.1250) grad: 0.2872 (0.2928) time: 0.3592 data: 0.0043 max mem: 3953 +train: [8] [220/400] eta: 0:01:03 lr: 0.000260 loss: 3.1141 (3.1249) grad: 0.3064 (0.2939) time: 0.3395 data: 0.0043 max mem: 3953 +train: [8] [240/400] eta: 0:00:56 lr: 0.000259 loss: 3.1251 (3.1261) grad: 0.3059 (0.2943) time: 0.3342 data: 0.0044 max mem: 3953 +train: [8] [260/400] eta: 0:00:49 lr: 0.000258 loss: 3.1169 (3.1238) grad: 0.3002 (0.2952) time: 0.3307 data: 0.0042 max mem: 3953 +train: [8] [280/400] eta: 0:00:41 lr: 0.000257 loss: 3.1247 (3.1263) grad: 0.2917 (0.2954) time: 0.3289 data: 0.0043 max mem: 3953 +train: [8] [300/400] eta: 0:00:34 lr: 0.000256 loss: 3.1541 (3.1273) grad: 0.2815 (0.2943) time: 0.3434 data: 0.0037 max mem: 3953 +train: [8] [320/400] eta: 0:00:27 lr: 0.000255 loss: 3.1541 (3.1293) grad: 0.2865 (0.2943) time: 0.3442 data: 0.0040 max mem: 3953 +train: [8] [340/400] eta: 0:00:20 lr: 0.000254 loss: 3.1712 (3.1293) grad: 0.2975 (0.2944) time: 0.3494 data: 0.0045 max mem: 3953 +train: [8] [360/400] eta: 0:00:13 lr: 0.000253 loss: 3.1155 (3.1283) grad: 0.2937 (0.2941) time: 0.3716 data: 0.0048 max mem: 3953 +train: [8] [380/400] eta: 0:00:06 lr: 0.000252 loss: 3.0900 (3.1269) grad: 0.2937 (0.2941) time: 0.3286 data: 0.0039 max mem: 3953 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 3.0928 (3.1260) grad: 0.2842 (0.2934) time: 0.3448 data: 0.0042 max mem: 3953 +train: [8] Total time: 0:02:19 (0.3487 s / it) +train: [8] Summary: lr: 0.000250 loss: 3.0928 (3.1260) grad: 0.2842 (0.2934) +eval (validation): [8] [ 0/85] eta: 0:04:44 time: 3.3517 data: 3.1432 max mem: 3953 +eval (validation): [8] [20/85] eta: 0:00:29 time: 0.3107 data: 0.0073 max mem: 3953 +eval (validation): [8] [40/85] eta: 0:00:17 time: 0.3259 data: 0.0041 max mem: 3953 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3172 data: 0.0041 max mem: 3953 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3226 data: 0.0042 max mem: 3953 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3177 data: 0.0040 max mem: 3953 +eval (validation): [8] Total time: 0:00:30 (0.3574 s / it) +cv: [8] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 3.126 acc: 0.084 f1: 0.040 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:20 lr: nan time: 3.3503 data: 3.0972 max mem: 3953 +train: [9] [ 20/400] eta: 0:03:03 lr: 0.000249 loss: 3.0943 (3.1054) grad: 0.2752 (0.2822) time: 0.3388 data: 0.0054 max mem: 3953 +train: [9] [ 40/400] eta: 0:02:26 lr: 0.000248 loss: 3.0943 (3.1048) grad: 0.2759 (0.2836) time: 0.3263 data: 0.0044 max mem: 3953 +train: [9] [ 60/400] eta: 0:02:09 lr: 0.000247 loss: 3.0857 (3.1084) grad: 0.2894 (0.2849) time: 0.3322 data: 0.0042 max mem: 3953 +train: [9] [ 80/400] eta: 0:01:58 lr: 0.000246 loss: 3.0982 (3.1101) grad: 0.2915 (0.2894) time: 0.3343 data: 0.0039 max mem: 3953 +train: [9] [100/400] eta: 0:01:49 lr: 0.000244 loss: 3.1007 (3.1097) grad: 0.2915 (0.2894) time: 0.3470 data: 0.0041 max mem: 3953 +train: [9] [120/400] eta: 0:01:40 lr: 0.000243 loss: 3.0927 (3.1065) grad: 0.2786 (0.2888) time: 0.3354 data: 0.0044 max mem: 3953 +train: [9] [140/400] eta: 0:01:32 lr: 0.000242 loss: 3.1071 (3.1061) grad: 0.2892 (0.2895) time: 0.3215 data: 0.0034 max mem: 3953 +train: [9] [160/400] eta: 0:01:24 lr: 0.000241 loss: 3.1223 (3.1102) grad: 0.2866 (0.2894) time: 0.3465 data: 0.0041 max mem: 3953 +train: [9] [180/400] eta: 0:01:17 lr: 0.000240 loss: 3.1321 (3.1124) grad: 0.2752 (0.2875) time: 0.3458 data: 0.0042 max mem: 3953 +train: [9] [200/400] eta: 0:01:10 lr: 0.000238 loss: 3.1309 (3.1122) grad: 0.2865 (0.2882) time: 0.3399 data: 0.0040 max mem: 3953 +train: [9] [220/400] eta: 0:01:02 lr: 0.000237 loss: 3.1267 (3.1122) grad: 0.2992 (0.2897) time: 0.3253 data: 0.0040 max mem: 3953 +train: [9] [240/400] eta: 0:00:55 lr: 0.000236 loss: 3.1154 (3.1125) grad: 0.3114 (0.2922) time: 0.3200 data: 0.0041 max mem: 3953 +train: [9] [260/400] eta: 0:00:48 lr: 0.000234 loss: 3.1042 (3.1143) grad: 0.3077 (0.2923) time: 0.3258 data: 0.0042 max mem: 3953 +train: [9] [280/400] eta: 0:00:41 lr: 0.000233 loss: 3.0894 (3.1119) grad: 0.2870 (0.2918) time: 0.3220 data: 0.0038 max mem: 3953 +train: [9] [300/400] eta: 0:00:34 lr: 0.000232 loss: 3.0894 (3.1126) grad: 0.2870 (0.2915) time: 0.3192 data: 0.0040 max mem: 3953 +train: [9] [320/400] eta: 0:00:27 lr: 0.000230 loss: 3.1261 (3.1137) grad: 0.2944 (0.2919) time: 0.3301 data: 0.0039 max mem: 3953 +train: [9] [340/400] eta: 0:00:20 lr: 0.000229 loss: 3.1169 (3.1133) grad: 0.2827 (0.2912) time: 0.3326 data: 0.0040 max mem: 3953 +train: [9] [360/400] eta: 0:00:13 lr: 0.000228 loss: 3.1249 (3.1153) grad: 0.2840 (0.2917) time: 0.3282 data: 0.0039 max mem: 3953 +train: [9] [380/400] eta: 0:00:06 lr: 0.000226 loss: 3.1438 (3.1164) grad: 0.2943 (0.2914) time: 0.3382 data: 0.0041 max mem: 3953 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 3.1014 (3.1147) grad: 0.2810 (0.2906) time: 0.3341 data: 0.0038 max mem: 3953 +train: [9] Total time: 0:02:15 (0.3400 s / it) +train: [9] Summary: lr: 0.000225 loss: 3.1014 (3.1147) grad: 0.2810 (0.2906) +eval (validation): [9] [ 0/85] eta: 0:04:48 time: 3.3945 data: 3.1787 max mem: 3953 +eval (validation): [9] [20/85] eta: 0:00:32 time: 0.3574 data: 0.0213 max mem: 3953 +eval (validation): [9] [40/85] eta: 0:00:19 time: 0.3430 data: 0.0044 max mem: 3953 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3132 data: 0.0039 max mem: 3953 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3137 data: 0.0043 max mem: 3953 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3082 data: 0.0042 max mem: 3953 +eval (validation): [9] Total time: 0:00:31 (0.3705 s / it) +cv: [9] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 3.144 acc: 0.086 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:31 lr: nan time: 3.3778 data: 3.1293 max mem: 3953 +train: [10] [ 20/400] eta: 0:03:00 lr: 0.000224 loss: 3.1093 (3.1172) grad: 0.2873 (0.2831) time: 0.3300 data: 0.0037 max mem: 3953 +train: [10] [ 40/400] eta: 0:02:23 lr: 0.000222 loss: 3.1039 (3.1043) grad: 0.2873 (0.2882) time: 0.3195 data: 0.0039 max mem: 3953 +train: [10] [ 60/400] eta: 0:02:07 lr: 0.000221 loss: 3.0839 (3.0975) grad: 0.2936 (0.2897) time: 0.3248 data: 0.0038 max mem: 3953 +train: [10] [ 80/400] eta: 0:01:55 lr: 0.000220 loss: 3.0922 (3.1020) grad: 0.2870 (0.2878) time: 0.3232 data: 0.0040 max mem: 3953 +train: [10] [100/400] eta: 0:01:46 lr: 0.000218 loss: 3.1008 (3.0983) grad: 0.2773 (0.2904) time: 0.3213 data: 0.0041 max mem: 3953 +train: [10] [120/400] eta: 0:01:37 lr: 0.000217 loss: 3.1146 (3.1027) grad: 0.2885 (0.2905) time: 0.3261 data: 0.0040 max mem: 3953 +train: [10] [140/400] eta: 0:01:30 lr: 0.000215 loss: 3.1146 (3.1040) grad: 0.2919 (0.2917) time: 0.3287 data: 0.0039 max mem: 3953 +train: [10] [160/400] eta: 0:01:22 lr: 0.000214 loss: 3.0993 (3.1048) grad: 0.2959 (0.2924) time: 0.3247 data: 0.0038 max mem: 3953 +train: [10] [180/400] eta: 0:01:15 lr: 0.000213 loss: 3.1257 (3.1083) grad: 0.2920 (0.2928) time: 0.3215 data: 0.0040 max mem: 3953 +train: [10] [200/400] eta: 0:01:08 lr: 0.000211 loss: 3.1257 (3.1075) grad: 0.2826 (0.2922) time: 0.3295 data: 0.0039 max mem: 3953 +train: [10] [220/400] eta: 0:01:01 lr: 0.000210 loss: 3.0955 (3.1055) grad: 0.2795 (0.2908) time: 0.3377 data: 0.0039 max mem: 3953 +train: [10] [240/400] eta: 0:00:54 lr: 0.000208 loss: 3.0617 (3.1017) grad: 0.2758 (0.2900) time: 0.3224 data: 0.0042 max mem: 3953 +train: [10] [260/400] eta: 0:00:47 lr: 0.000207 loss: 3.0686 (3.1016) grad: 0.2758 (0.2893) time: 0.3270 data: 0.0042 max mem: 3953 +train: [10] [280/400] eta: 0:00:40 lr: 0.000205 loss: 3.1101 (3.1027) grad: 0.2736 (0.2883) time: 0.3160 data: 0.0040 max mem: 3953 +train: [10] [300/400] eta: 0:00:33 lr: 0.000204 loss: 3.1185 (3.1031) grad: 0.2686 (0.2880) time: 0.3281 data: 0.0039 max mem: 3953 +train: [10] [320/400] eta: 0:00:26 lr: 0.000202 loss: 3.0966 (3.1030) grad: 0.2828 (0.2884) time: 0.3294 data: 0.0041 max mem: 3953 +train: [10] [340/400] eta: 0:00:20 lr: 0.000201 loss: 3.0922 (3.1026) grad: 0.2841 (0.2881) time: 0.3466 data: 0.0041 max mem: 3953 +train: [10] [360/400] eta: 0:00:13 lr: 0.000199 loss: 3.0800 (3.1021) grad: 0.2822 (0.2875) time: 0.3314 data: 0.0040 max mem: 3953 +train: [10] [380/400] eta: 0:00:06 lr: 0.000198 loss: 3.0808 (3.1022) grad: 0.2775 (0.2874) time: 0.3098 data: 0.0039 max mem: 3953 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 3.1049 (3.1028) grad: 0.2839 (0.2882) time: 0.3253 data: 0.0040 max mem: 3953 +train: [10] Total time: 0:02:13 (0.3341 s / it) +train: [10] Summary: lr: 0.000196 loss: 3.1049 (3.1028) grad: 0.2839 (0.2882) +eval (validation): [10] [ 0/85] eta: 0:04:46 time: 3.3719 data: 3.1368 max mem: 3953 +eval (validation): [10] [20/85] eta: 0:00:33 time: 0.3674 data: 0.0156 max mem: 3953 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3240 data: 0.0048 max mem: 3953 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3043 data: 0.0037 max mem: 3953 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.2975 data: 0.0041 max mem: 3953 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.2920 data: 0.0039 max mem: 3953 +eval (validation): [10] Total time: 0:00:30 (0.3624 s / it) +cv: [10] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 3.113 acc: 0.084 f1: 0.037 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:00 lr: nan time: 3.3024 data: 3.0392 max mem: 3953 +train: [11] [ 20/400] eta: 0:03:01 lr: 0.000195 loss: 3.0948 (3.1010) grad: 0.2951 (0.2908) time: 0.3376 data: 0.0050 max mem: 3953 +train: [11] [ 40/400] eta: 0:02:25 lr: 0.000193 loss: 3.0948 (3.0943) grad: 0.2898 (0.2905) time: 0.3254 data: 0.0034 max mem: 3953 +train: [11] [ 60/400] eta: 0:02:10 lr: 0.000192 loss: 3.0885 (3.0895) grad: 0.2890 (0.2959) time: 0.3418 data: 0.0042 max mem: 3953 +train: [11] [ 80/400] eta: 0:01:59 lr: 0.000190 loss: 3.0755 (3.0893) grad: 0.2944 (0.2940) time: 0.3461 data: 0.0042 max mem: 3953 +train: [11] [100/400] eta: 0:01:51 lr: 0.000189 loss: 3.0755 (3.0933) grad: 0.2863 (0.2928) time: 0.3612 data: 0.0044 max mem: 3953 +train: [11] [120/400] eta: 0:01:41 lr: 0.000187 loss: 3.0678 (3.0856) grad: 0.2791 (0.2903) time: 0.3178 data: 0.0038 max mem: 3953 +train: [11] [140/400] eta: 0:01:33 lr: 0.000186 loss: 3.0907 (3.0877) grad: 0.2753 (0.2883) time: 0.3386 data: 0.0040 max mem: 3953 +train: [11] [160/400] eta: 0:01:25 lr: 0.000184 loss: 3.0865 (3.0857) grad: 0.2809 (0.2884) time: 0.3315 data: 0.0039 max mem: 3953 +train: [11] [180/400] eta: 0:01:17 lr: 0.000183 loss: 3.0798 (3.0865) grad: 0.2851 (0.2876) time: 0.3242 data: 0.0039 max mem: 3953 +train: [11] [200/400] eta: 0:01:10 lr: 0.000181 loss: 3.0842 (3.0847) grad: 0.2810 (0.2870) time: 0.3362 data: 0.0041 max mem: 3953 +train: [11] [220/400] eta: 0:01:02 lr: 0.000180 loss: 3.0987 (3.0860) grad: 0.2716 (0.2864) time: 0.3117 data: 0.0042 max mem: 3953 +train: [11] [240/400] eta: 0:00:55 lr: 0.000178 loss: 3.1091 (3.0873) grad: 0.2723 (0.2851) time: 0.3299 data: 0.0044 max mem: 3953 +train: [11] [260/400] eta: 0:00:48 lr: 0.000177 loss: 3.1018 (3.0875) grad: 0.2667 (0.2837) time: 0.3198 data: 0.0042 max mem: 3953 +train: [11] [280/400] eta: 0:00:41 lr: 0.000175 loss: 3.0679 (3.0863) grad: 0.2667 (0.2825) time: 0.3191 data: 0.0042 max mem: 3953 +train: [11] [300/400] eta: 0:00:34 lr: 0.000174 loss: 3.0793 (3.0863) grad: 0.2617 (0.2824) time: 0.3202 data: 0.0040 max mem: 3953 +train: [11] [320/400] eta: 0:00:27 lr: 0.000172 loss: 3.0906 (3.0872) grad: 0.2844 (0.2826) time: 0.3183 data: 0.0041 max mem: 3953 +train: [11] [340/400] eta: 0:00:20 lr: 0.000170 loss: 3.1041 (3.0890) grad: 0.2763 (0.2820) time: 0.3234 data: 0.0042 max mem: 3953 +train: [11] [360/400] eta: 0:00:13 lr: 0.000169 loss: 3.0916 (3.0879) grad: 0.2579 (0.2815) time: 0.3094 data: 0.0043 max mem: 3953 +train: [11] [380/400] eta: 0:00:06 lr: 0.000167 loss: 3.0745 (3.0881) grad: 0.2893 (0.2822) time: 0.3197 data: 0.0041 max mem: 3953 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 3.0813 (3.0882) grad: 0.2923 (0.2833) time: 0.3138 data: 0.0040 max mem: 3953 +train: [11] Total time: 0:02:14 (0.3350 s / it) +train: [11] Summary: lr: 0.000166 loss: 3.0813 (3.0882) grad: 0.2923 (0.2833) +eval (validation): [11] [ 0/85] eta: 0:04:32 time: 3.2070 data: 3.0089 max mem: 3953 +eval (validation): [11] [20/85] eta: 0:00:30 time: 0.3371 data: 0.0052 max mem: 3953 +eval (validation): [11] [40/85] eta: 0:00:17 time: 0.3190 data: 0.0047 max mem: 3953 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3130 data: 0.0045 max mem: 3953 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.2996 data: 0.0041 max mem: 3953 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.2966 data: 0.0040 max mem: 3953 +eval (validation): [11] Total time: 0:00:30 (0.3540 s / it) +cv: [11] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 3.111 acc: 0.083 f1: 0.039 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:26:51 lr: nan time: 4.0291 data: 3.7590 max mem: 3953 +train: [12] [ 20/400] eta: 0:03:12 lr: 0.000164 loss: 3.0624 (3.0651) grad: 0.2908 (0.2868) time: 0.3292 data: 0.0031 max mem: 3953 +train: [12] [ 40/400] eta: 0:02:31 lr: 0.000163 loss: 3.0624 (3.0598) grad: 0.2739 (0.2777) time: 0.3294 data: 0.0041 max mem: 3953 +train: [12] [ 60/400] eta: 0:02:11 lr: 0.000161 loss: 3.0836 (3.0713) grad: 0.2739 (0.2779) time: 0.3159 data: 0.0041 max mem: 3953 +train: [12] [ 80/400] eta: 0:01:57 lr: 0.000160 loss: 3.0534 (3.0595) grad: 0.2805 (0.2786) time: 0.3150 data: 0.0042 max mem: 3953 +train: [12] [100/400] eta: 0:01:47 lr: 0.000158 loss: 3.0484 (3.0628) grad: 0.2861 (0.2814) time: 0.3197 data: 0.0043 max mem: 3953 +train: [12] [120/400] eta: 0:01:38 lr: 0.000156 loss: 3.0800 (3.0660) grad: 0.2878 (0.2824) time: 0.3215 data: 0.0042 max mem: 3953 +train: [12] [140/400] eta: 0:01:30 lr: 0.000155 loss: 3.0807 (3.0658) grad: 0.2647 (0.2805) time: 0.3211 data: 0.0041 max mem: 3953 +train: [12] [160/400] eta: 0:01:22 lr: 0.000153 loss: 3.0807 (3.0685) grad: 0.2820 (0.2824) time: 0.3282 data: 0.0042 max mem: 3953 +train: [12] [180/400] eta: 0:01:15 lr: 0.000152 loss: 3.0818 (3.0702) grad: 0.2834 (0.2810) time: 0.3328 data: 0.0043 max mem: 3953 +train: [12] [200/400] eta: 0:01:08 lr: 0.000150 loss: 3.0636 (3.0687) grad: 0.2801 (0.2820) time: 0.3437 data: 0.0043 max mem: 3953 +train: [12] [220/400] eta: 0:01:01 lr: 0.000149 loss: 3.0636 (3.0675) grad: 0.2673 (0.2800) time: 0.3264 data: 0.0041 max mem: 3953 +train: [12] [240/400] eta: 0:00:54 lr: 0.000147 loss: 3.0816 (3.0695) grad: 0.2640 (0.2797) time: 0.3346 data: 0.0041 max mem: 3953 +train: [12] [260/400] eta: 0:00:48 lr: 0.000145 loss: 3.0901 (3.0712) grad: 0.2722 (0.2798) time: 0.3565 data: 0.0042 max mem: 3953 +train: [12] [280/400] eta: 0:00:41 lr: 0.000144 loss: 3.0895 (3.0727) grad: 0.2769 (0.2791) time: 0.3332 data: 0.0040 max mem: 3953 +train: [12] [300/400] eta: 0:00:34 lr: 0.000142 loss: 3.0612 (3.0707) grad: 0.2678 (0.2781) time: 0.3323 data: 0.0040 max mem: 3953 +train: [12] [320/400] eta: 0:00:27 lr: 0.000141 loss: 3.0472 (3.0704) grad: 0.2675 (0.2779) time: 0.3394 data: 0.0042 max mem: 3953 +train: [12] [340/400] eta: 0:00:20 lr: 0.000139 loss: 3.0661 (3.0707) grad: 0.2679 (0.2773) time: 0.3170 data: 0.0042 max mem: 3953 +train: [12] [360/400] eta: 0:00:13 lr: 0.000138 loss: 3.1058 (3.0736) grad: 0.2665 (0.2763) time: 0.3282 data: 0.0041 max mem: 3953 +train: [12] [380/400] eta: 0:00:06 lr: 0.000136 loss: 3.1119 (3.0750) grad: 0.2689 (0.2764) time: 0.3299 data: 0.0043 max mem: 3953 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 3.0952 (3.0755) grad: 0.2846 (0.2776) time: 0.3217 data: 0.0042 max mem: 3953 +train: [12] Total time: 0:02:15 (0.3383 s / it) +train: [12] Summary: lr: 0.000134 loss: 3.0952 (3.0755) grad: 0.2846 (0.2776) +eval (validation): [12] [ 0/85] eta: 0:04:33 time: 3.2137 data: 3.0253 max mem: 3953 +eval (validation): [12] [20/85] eta: 0:00:28 time: 0.2952 data: 0.0048 max mem: 3953 +eval (validation): [12] [40/85] eta: 0:00:16 time: 0.3042 data: 0.0044 max mem: 3953 +eval (validation): [12] [60/85] eta: 0:00:08 time: 0.3007 data: 0.0036 max mem: 3953 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.2929 data: 0.0039 max mem: 3953 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.2902 data: 0.0034 max mem: 3953 +eval (validation): [12] Total time: 0:00:28 (0.3359 s / it) +cv: [12] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 3.129 acc: 0.093 f1: 0.049 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:21:32 lr: nan time: 3.2306 data: 2.9874 max mem: 3953 +train: [13] [ 20/400] eta: 0:03:07 lr: 0.000133 loss: 3.0463 (3.0522) grad: 0.2674 (0.2684) time: 0.3573 data: 0.0264 max mem: 3953 +train: [13] [ 40/400] eta: 0:02:27 lr: 0.000131 loss: 3.0454 (3.0425) grad: 0.2620 (0.2675) time: 0.3184 data: 0.0035 max mem: 3953 +train: [13] [ 60/400] eta: 0:02:08 lr: 0.000130 loss: 3.0385 (3.0460) grad: 0.2632 (0.2709) time: 0.3136 data: 0.0042 max mem: 3953 +train: [13] [ 80/400] eta: 0:01:56 lr: 0.000128 loss: 3.0634 (3.0495) grad: 0.2809 (0.2731) time: 0.3255 data: 0.0043 max mem: 3953 +train: [13] [100/400] eta: 0:01:46 lr: 0.000127 loss: 3.0637 (3.0542) grad: 0.2806 (0.2739) time: 0.3200 data: 0.0042 max mem: 3953 +train: [13] [120/400] eta: 0:01:38 lr: 0.000125 loss: 3.0654 (3.0543) grad: 0.2735 (0.2745) time: 0.3250 data: 0.0043 max mem: 3953 +train: [13] [140/400] eta: 0:01:30 lr: 0.000124 loss: 3.0701 (3.0575) grad: 0.2742 (0.2747) time: 0.3212 data: 0.0043 max mem: 3953 +train: [13] [160/400] eta: 0:01:22 lr: 0.000122 loss: 3.0508 (3.0565) grad: 0.2681 (0.2730) time: 0.3119 data: 0.0042 max mem: 3953 +train: [13] [180/400] eta: 0:01:15 lr: 0.000120 loss: 3.0470 (3.0581) grad: 0.2815 (0.2736) time: 0.3340 data: 0.0042 max mem: 3953 +train: [13] [200/400] eta: 0:01:07 lr: 0.000119 loss: 3.0687 (3.0598) grad: 0.2875 (0.2746) time: 0.3194 data: 0.0042 max mem: 3953 +train: [13] [220/400] eta: 0:01:00 lr: 0.000117 loss: 3.0490 (3.0579) grad: 0.2884 (0.2747) time: 0.3183 data: 0.0044 max mem: 3953 +train: [13] [240/400] eta: 0:00:53 lr: 0.000116 loss: 3.0391 (3.0579) grad: 0.2846 (0.2750) time: 0.3360 data: 0.0042 max mem: 3953 +train: [13] [260/400] eta: 0:00:46 lr: 0.000114 loss: 3.0780 (3.0598) grad: 0.2548 (0.2733) time: 0.3183 data: 0.0041 max mem: 3953 +train: [13] [280/400] eta: 0:00:40 lr: 0.000113 loss: 3.0780 (3.0606) grad: 0.2548 (0.2740) time: 0.3170 data: 0.0044 max mem: 3953 +train: [13] [300/400] eta: 0:00:33 lr: 0.000111 loss: 3.0622 (3.0601) grad: 0.2702 (0.2737) time: 0.3208 data: 0.0041 max mem: 3953 +train: [13] [320/400] eta: 0:00:26 lr: 0.000110 loss: 3.0575 (3.0611) grad: 0.2551 (0.2728) time: 0.3202 data: 0.0041 max mem: 3953 +train: [13] [340/400] eta: 0:00:19 lr: 0.000108 loss: 3.0478 (3.0605) grad: 0.2537 (0.2719) time: 0.3362 data: 0.0042 max mem: 3953 +train: [13] [360/400] eta: 0:00:13 lr: 0.000107 loss: 3.0412 (3.0606) grad: 0.2551 (0.2714) time: 0.3325 data: 0.0042 max mem: 3953 +train: [13] [380/400] eta: 0:00:06 lr: 0.000105 loss: 3.0719 (3.0618) grad: 0.2717 (0.2714) time: 0.3406 data: 0.0041 max mem: 3953 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 3.0705 (3.0618) grad: 0.2717 (0.2719) time: 0.3202 data: 0.0042 max mem: 3953 +train: [13] Total time: 0:02:13 (0.3328 s / it) +train: [13] Summary: lr: 0.000104 loss: 3.0705 (3.0618) grad: 0.2717 (0.2719) +eval (validation): [13] [ 0/85] eta: 0:04:40 time: 3.3014 data: 3.0421 max mem: 3953 +eval (validation): [13] [20/85] eta: 0:00:29 time: 0.3163 data: 0.0063 max mem: 3953 +eval (validation): [13] [40/85] eta: 0:00:17 time: 0.3355 data: 0.0041 max mem: 3953 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3485 data: 0.0044 max mem: 3953 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3090 data: 0.0040 max mem: 3953 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3002 data: 0.0039 max mem: 3953 +eval (validation): [13] Total time: 0:00:30 (0.3643 s / it) +cv: [13] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.243 acc: 0.094 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:22:03 lr: nan time: 3.3093 data: 3.0559 max mem: 3953 +train: [14] [ 20/400] eta: 0:03:09 lr: 0.000102 loss: 3.0772 (3.0721) grad: 0.2628 (0.2807) time: 0.3592 data: 0.0048 max mem: 3953 +train: [14] [ 40/400] eta: 0:02:29 lr: 0.000101 loss: 3.0555 (3.0623) grad: 0.2695 (0.2762) time: 0.3248 data: 0.0034 max mem: 3953 +train: [14] [ 60/400] eta: 0:02:11 lr: 0.000099 loss: 3.0561 (3.0654) grad: 0.2714 (0.2743) time: 0.3343 data: 0.0042 max mem: 3953 +train: [14] [ 80/400] eta: 0:01:59 lr: 0.000098 loss: 3.0643 (3.0655) grad: 0.2594 (0.2683) time: 0.3295 data: 0.0043 max mem: 3953 +train: [14] [100/400] eta: 0:01:48 lr: 0.000096 loss: 3.0567 (3.0609) grad: 0.2523 (0.2688) time: 0.3211 data: 0.0043 max mem: 3953 +train: [14] [120/400] eta: 0:01:39 lr: 0.000095 loss: 3.0530 (3.0590) grad: 0.2705 (0.2678) time: 0.3186 data: 0.0043 max mem: 3953 +train: [14] [140/400] eta: 0:01:31 lr: 0.000093 loss: 3.0589 (3.0597) grad: 0.2705 (0.2697) time: 0.3163 data: 0.0044 max mem: 3953 +train: [14] [160/400] eta: 0:01:23 lr: 0.000092 loss: 3.0637 (3.0616) grad: 0.2721 (0.2701) time: 0.3179 data: 0.0042 max mem: 3953 +train: [14] [180/400] eta: 0:01:15 lr: 0.000090 loss: 3.0557 (3.0607) grad: 0.2731 (0.2702) time: 0.3215 data: 0.0042 max mem: 3953 +train: [14] [200/400] eta: 0:01:08 lr: 0.000089 loss: 3.0507 (3.0598) grad: 0.2565 (0.2683) time: 0.3169 data: 0.0041 max mem: 3953 +train: [14] [220/400] eta: 0:01:00 lr: 0.000088 loss: 3.0385 (3.0582) grad: 0.2626 (0.2689) time: 0.3186 data: 0.0043 max mem: 3953 +train: [14] [240/400] eta: 0:00:54 lr: 0.000086 loss: 3.0442 (3.0585) grad: 0.2724 (0.2696) time: 0.3279 data: 0.0042 max mem: 3953 +train: [14] [260/400] eta: 0:00:47 lr: 0.000085 loss: 3.0623 (3.0588) grad: 0.2717 (0.2695) time: 0.3220 data: 0.0043 max mem: 3953 +train: [14] [280/400] eta: 0:00:40 lr: 0.000083 loss: 3.0354 (3.0584) grad: 0.2609 (0.2687) time: 0.3178 data: 0.0043 max mem: 3953 +train: [14] [300/400] eta: 0:00:33 lr: 0.000082 loss: 3.0407 (3.0580) grad: 0.2582 (0.2682) time: 0.3240 data: 0.0042 max mem: 3953 +train: [14] [320/400] eta: 0:00:26 lr: 0.000081 loss: 3.0401 (3.0564) grad: 0.2658 (0.2679) time: 0.3125 data: 0.0041 max mem: 3953 +train: [14] [340/400] eta: 0:00:19 lr: 0.000079 loss: 3.0361 (3.0575) grad: 0.2641 (0.2680) time: 0.3221 data: 0.0041 max mem: 3953 +train: [14] [360/400] eta: 0:00:13 lr: 0.000078 loss: 3.0367 (3.0573) grad: 0.2612 (0.2680) time: 0.3311 data: 0.0041 max mem: 3953 +train: [14] [380/400] eta: 0:00:06 lr: 0.000076 loss: 3.0361 (3.0562) grad: 0.2653 (0.2679) time: 0.3209 data: 0.0042 max mem: 3953 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 3.0375 (3.0557) grad: 0.2607 (0.2675) time: 0.3197 data: 0.0042 max mem: 3953 +train: [14] Total time: 0:02:12 (0.3316 s / it) +train: [14] Summary: lr: 0.000075 loss: 3.0375 (3.0557) grad: 0.2607 (0.2675) +eval (validation): [14] [ 0/85] eta: 0:04:39 time: 3.2901 data: 3.0453 max mem: 3953 +eval (validation): [14] [20/85] eta: 0:00:31 time: 0.3509 data: 0.0039 max mem: 3953 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3090 data: 0.0040 max mem: 3953 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3025 data: 0.0042 max mem: 3953 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3010 data: 0.0042 max mem: 3953 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.2882 data: 0.0041 max mem: 3953 +eval (validation): [14] Total time: 0:00:29 (0.3522 s / it) +cv: [14] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 3.128 acc: 0.093 f1: 0.053 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:49 lr: nan time: 3.4246 data: 3.2149 max mem: 3953 +train: [15] [ 20/400] eta: 0:03:03 lr: 0.000074 loss: 3.0550 (3.0518) grad: 0.2753 (0.2796) time: 0.3356 data: 0.0033 max mem: 3953 +train: [15] [ 40/400] eta: 0:02:29 lr: 0.000072 loss: 3.0550 (3.0453) grad: 0.2683 (0.2654) time: 0.3437 data: 0.0036 max mem: 3953 +train: [15] [ 60/400] eta: 0:02:11 lr: 0.000071 loss: 3.0181 (3.0363) grad: 0.2529 (0.2631) time: 0.3281 data: 0.0039 max mem: 3953 +train: [15] [ 80/400] eta: 0:01:58 lr: 0.000070 loss: 3.0040 (3.0320) grad: 0.2514 (0.2593) time: 0.3243 data: 0.0043 max mem: 3953 +train: [15] [100/400] eta: 0:01:49 lr: 0.000068 loss: 3.0344 (3.0348) grad: 0.2462 (0.2572) time: 0.3341 data: 0.0042 max mem: 3953 +train: [15] [120/400] eta: 0:01:39 lr: 0.000067 loss: 3.0270 (3.0314) grad: 0.2687 (0.2608) time: 0.3199 data: 0.0040 max mem: 3953 +train: [15] [140/400] eta: 0:01:31 lr: 0.000066 loss: 3.0069 (3.0304) grad: 0.2691 (0.2619) time: 0.3353 data: 0.0043 max mem: 3953 +train: [15] [160/400] eta: 0:01:24 lr: 0.000064 loss: 3.0275 (3.0320) grad: 0.2726 (0.2635) time: 0.3487 data: 0.0043 max mem: 3953 +train: [15] [180/400] eta: 0:01:17 lr: 0.000063 loss: 3.0525 (3.0364) grad: 0.2636 (0.2642) time: 0.3312 data: 0.0043 max mem: 3953 +train: [15] [200/400] eta: 0:01:09 lr: 0.000062 loss: 3.0550 (3.0378) grad: 0.2615 (0.2638) time: 0.3235 data: 0.0043 max mem: 3953 +train: [15] [220/400] eta: 0:01:02 lr: 0.000061 loss: 3.0319 (3.0378) grad: 0.2622 (0.2637) time: 0.3231 data: 0.0039 max mem: 3953 +train: [15] [240/400] eta: 0:00:55 lr: 0.000059 loss: 3.0282 (3.0369) grad: 0.2639 (0.2638) time: 0.3373 data: 0.0043 max mem: 3953 +train: [15] [260/400] eta: 0:00:48 lr: 0.000058 loss: 3.0406 (3.0387) grad: 0.2627 (0.2627) time: 0.3330 data: 0.0041 max mem: 3953 +train: [15] [280/400] eta: 0:00:41 lr: 0.000057 loss: 3.0546 (3.0396) grad: 0.2671 (0.2633) time: 0.3204 data: 0.0043 max mem: 3953 +train: [15] [300/400] eta: 0:00:34 lr: 0.000056 loss: 3.0514 (3.0401) grad: 0.2698 (0.2635) time: 0.3168 data: 0.0041 max mem: 3953 +train: [15] [320/400] eta: 0:00:27 lr: 0.000054 loss: 3.0461 (3.0401) grad: 0.2698 (0.2639) time: 0.3187 data: 0.0043 max mem: 3953 +train: [15] [340/400] eta: 0:00:20 lr: 0.000053 loss: 3.0283 (3.0384) grad: 0.2574 (0.2637) time: 0.3187 data: 0.0041 max mem: 3953 +train: [15] [360/400] eta: 0:00:13 lr: 0.000052 loss: 3.0477 (3.0411) grad: 0.2541 (0.2631) time: 0.3194 data: 0.0043 max mem: 3953 +train: [15] [380/400] eta: 0:00:06 lr: 0.000051 loss: 3.0452 (3.0406) grad: 0.2541 (0.2630) time: 0.3245 data: 0.0041 max mem: 3953 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 3.0377 (3.0415) grad: 0.2612 (0.2632) time: 0.3249 data: 0.0042 max mem: 3953 +train: [15] Total time: 0:02:14 (0.3361 s / it) +train: [15] Summary: lr: 0.000050 loss: 3.0377 (3.0415) grad: 0.2612 (0.2632) +eval (validation): [15] [ 0/85] eta: 0:04:37 time: 3.2627 data: 3.0212 max mem: 3953 +eval (validation): [15] [20/85] eta: 0:00:30 time: 0.3304 data: 0.0046 max mem: 3953 +eval (validation): [15] [40/85] eta: 0:00:17 time: 0.3049 data: 0.0041 max mem: 3953 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3184 data: 0.0042 max mem: 3953 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3060 data: 0.0042 max mem: 3953 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.2945 data: 0.0040 max mem: 3953 +eval (validation): [15] Total time: 0:00:29 (0.3513 s / it) +cv: [15] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 3.097 acc: 0.093 f1: 0.052 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:44 lr: nan time: 3.2614 data: 3.0381 max mem: 3953 +train: [16] [ 20/400] eta: 0:03:03 lr: 0.000048 loss: 3.0262 (3.0306) grad: 0.2378 (0.2489) time: 0.3451 data: 0.0049 max mem: 3953 +train: [16] [ 40/400] eta: 0:02:26 lr: 0.000047 loss: 3.0262 (3.0320) grad: 0.2503 (0.2575) time: 0.3238 data: 0.0035 max mem: 3953 +train: [16] [ 60/400] eta: 0:02:08 lr: 0.000046 loss: 3.0514 (3.0446) grad: 0.2693 (0.2614) time: 0.3205 data: 0.0044 max mem: 3953 +train: [16] [ 80/400] eta: 0:01:56 lr: 0.000045 loss: 3.0569 (3.0402) grad: 0.2553 (0.2602) time: 0.3199 data: 0.0042 max mem: 3953 +train: [16] [100/400] eta: 0:01:46 lr: 0.000044 loss: 3.0476 (3.0437) grad: 0.2615 (0.2635) time: 0.3195 data: 0.0042 max mem: 3953 +train: [16] [120/400] eta: 0:01:37 lr: 0.000043 loss: 3.0490 (3.0428) grad: 0.2630 (0.2638) time: 0.3239 data: 0.0041 max mem: 3953 +train: [16] [140/400] eta: 0:01:29 lr: 0.000042 loss: 3.0313 (3.0427) grad: 0.2615 (0.2636) time: 0.3154 data: 0.0042 max mem: 3953 +train: [16] [160/400] eta: 0:01:22 lr: 0.000041 loss: 3.0313 (3.0440) grad: 0.2515 (0.2632) time: 0.3264 data: 0.0041 max mem: 3953 +train: [16] [180/400] eta: 0:01:15 lr: 0.000040 loss: 3.0532 (3.0461) grad: 0.2524 (0.2620) time: 0.3390 data: 0.0040 max mem: 3953 +train: [16] [200/400] eta: 0:01:08 lr: 0.000039 loss: 3.0644 (3.0474) grad: 0.2524 (0.2623) time: 0.3392 data: 0.0039 max mem: 3953 +train: [16] [220/400] eta: 0:01:01 lr: 0.000038 loss: 3.0644 (3.0479) grad: 0.2618 (0.2612) time: 0.3329 data: 0.0040 max mem: 3953 +train: [16] [240/400] eta: 0:00:54 lr: 0.000036 loss: 3.0417 (3.0473) grad: 0.2650 (0.2625) time: 0.3249 data: 0.0038 max mem: 3953 +train: [16] [260/400] eta: 0:00:47 lr: 0.000035 loss: 3.0417 (3.0472) grad: 0.2654 (0.2626) time: 0.3388 data: 0.0040 max mem: 3953 +train: [16] [280/400] eta: 0:00:40 lr: 0.000034 loss: 3.0056 (3.0438) grad: 0.2547 (0.2617) time: 0.3251 data: 0.0039 max mem: 3953 +train: [16] [300/400] eta: 0:00:33 lr: 0.000033 loss: 3.0058 (3.0426) grad: 0.2486 (0.2613) time: 0.3230 data: 0.0038 max mem: 3953 +train: [16] [320/400] eta: 0:00:27 lr: 0.000032 loss: 3.0393 (3.0430) grad: 0.2528 (0.2611) time: 0.3531 data: 0.0040 max mem: 3953 +train: [16] [340/400] eta: 0:00:20 lr: 0.000031 loss: 3.0240 (3.0412) grad: 0.2460 (0.2599) time: 0.3365 data: 0.0040 max mem: 3953 +train: [16] [360/400] eta: 0:00:13 lr: 0.000031 loss: 3.0226 (3.0412) grad: 0.2446 (0.2602) time: 0.3234 data: 0.0040 max mem: 3953 +train: [16] [380/400] eta: 0:00:06 lr: 0.000030 loss: 3.0174 (3.0400) grad: 0.2470 (0.2597) time: 0.3239 data: 0.0039 max mem: 3953 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 3.0172 (3.0399) grad: 0.2499 (0.2597) time: 0.3223 data: 0.0042 max mem: 3953 +train: [16] Total time: 0:02:14 (0.3365 s / it) +train: [16] Summary: lr: 0.000029 loss: 3.0172 (3.0399) grad: 0.2499 (0.2597) +eval (validation): [16] [ 0/85] eta: 0:04:39 time: 3.2860 data: 3.0405 max mem: 3953 +eval (validation): [16] [20/85] eta: 0:00:31 time: 0.3411 data: 0.0035 max mem: 3953 +eval (validation): [16] [40/85] eta: 0:00:17 time: 0.3060 data: 0.0041 max mem: 3953 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3075 data: 0.0041 max mem: 3953 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3052 data: 0.0039 max mem: 3953 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.2980 data: 0.0038 max mem: 3953 +eval (validation): [16] Total time: 0:00:29 (0.3518 s / it) +cv: [16] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 3.100 acc: 0.093 f1: 0.056 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:08 lr: nan time: 3.3217 data: 3.0692 max mem: 3953 +train: [17] [ 20/400] eta: 0:03:13 lr: 0.000028 loss: 3.0487 (3.0370) grad: 0.2555 (0.2538) time: 0.3682 data: 0.0040 max mem: 3953 +train: [17] [ 40/400] eta: 0:02:29 lr: 0.000027 loss: 3.0487 (3.0420) grad: 0.2588 (0.2610) time: 0.3148 data: 0.0038 max mem: 3953 +train: [17] [ 60/400] eta: 0:02:10 lr: 0.000026 loss: 3.0582 (3.0491) grad: 0.2644 (0.2608) time: 0.3219 data: 0.0043 max mem: 3953 +train: [17] [ 80/400] eta: 0:01:57 lr: 0.000025 loss: 3.0262 (3.0413) grad: 0.2516 (0.2596) time: 0.3220 data: 0.0044 max mem: 3953 +train: [17] [100/400] eta: 0:01:47 lr: 0.000024 loss: 3.0110 (3.0367) grad: 0.2516 (0.2589) time: 0.3186 data: 0.0043 max mem: 3953 +train: [17] [120/400] eta: 0:01:38 lr: 0.000023 loss: 3.0115 (3.0348) grad: 0.2576 (0.2584) time: 0.3132 data: 0.0041 max mem: 3953 +train: [17] [140/400] eta: 0:01:30 lr: 0.000023 loss: 3.0275 (3.0345) grad: 0.2616 (0.2605) time: 0.3189 data: 0.0041 max mem: 3953 +train: [17] [160/400] eta: 0:01:22 lr: 0.000022 loss: 3.0275 (3.0331) grad: 0.2770 (0.2620) time: 0.3132 data: 0.0040 max mem: 3953 +train: [17] [180/400] eta: 0:01:15 lr: 0.000021 loss: 3.0342 (3.0343) grad: 0.2742 (0.2629) time: 0.3413 data: 0.0044 max mem: 3953 +train: [17] [200/400] eta: 0:01:08 lr: 0.000020 loss: 3.0315 (3.0338) grad: 0.2661 (0.2632) time: 0.3281 data: 0.0042 max mem: 3953 +train: [17] [220/400] eta: 0:01:01 lr: 0.000019 loss: 3.0170 (3.0324) grad: 0.2617 (0.2640) time: 0.3254 data: 0.0041 max mem: 3953 +train: [17] [240/400] eta: 0:00:54 lr: 0.000019 loss: 3.0377 (3.0333) grad: 0.2480 (0.2633) time: 0.3196 data: 0.0041 max mem: 3953 +train: [17] [260/400] eta: 0:00:47 lr: 0.000018 loss: 3.0272 (3.0339) grad: 0.2463 (0.2619) time: 0.3219 data: 0.0038 max mem: 3953 +train: [17] [280/400] eta: 0:00:40 lr: 0.000017 loss: 3.0253 (3.0324) grad: 0.2413 (0.2605) time: 0.3233 data: 0.0039 max mem: 3953 +train: [17] [300/400] eta: 0:00:33 lr: 0.000016 loss: 3.0300 (3.0326) grad: 0.2485 (0.2606) time: 0.3259 data: 0.0041 max mem: 3953 +train: [17] [320/400] eta: 0:00:26 lr: 0.000016 loss: 3.0335 (3.0312) grad: 0.2620 (0.2608) time: 0.3179 data: 0.0042 max mem: 3953 +train: [17] [340/400] eta: 0:00:19 lr: 0.000015 loss: 3.0150 (3.0299) grad: 0.2533 (0.2603) time: 0.3210 data: 0.0043 max mem: 3953 +train: [17] [360/400] eta: 0:00:13 lr: 0.000014 loss: 3.0325 (3.0304) grad: 0.2556 (0.2604) time: 0.3362 data: 0.0043 max mem: 3953 +train: [17] [380/400] eta: 0:00:06 lr: 0.000014 loss: 3.0386 (3.0309) grad: 0.2611 (0.2601) time: 0.3346 data: 0.0043 max mem: 3953 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 3.0076 (3.0296) grad: 0.2550 (0.2594) time: 0.3256 data: 0.0041 max mem: 3953 +train: [17] Total time: 0:02:13 (0.3333 s / it) +train: [17] Summary: lr: 0.000013 loss: 3.0076 (3.0296) grad: 0.2550 (0.2594) +eval (validation): [17] [ 0/85] eta: 0:05:35 time: 3.9504 data: 3.7366 max mem: 3953 +eval (validation): [17] [20/85] eta: 0:00:33 time: 0.3407 data: 0.0039 max mem: 3953 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.2998 data: 0.0039 max mem: 3953 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3066 data: 0.0043 max mem: 3953 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3178 data: 0.0042 max mem: 3953 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3056 data: 0.0039 max mem: 3953 +eval (validation): [17] Total time: 0:00:30 (0.3621 s / it) +cv: [17] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.096 acc: 0.094 f1: 0.059 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:21:43 lr: nan time: 3.2600 data: 3.0175 max mem: 3953 +train: [18] [ 20/400] eta: 0:03:14 lr: 0.000012 loss: 2.9799 (3.0068) grad: 0.2502 (0.2554) time: 0.3734 data: 0.0060 max mem: 3953 +train: [18] [ 40/400] eta: 0:02:31 lr: 0.000012 loss: 3.0316 (3.0317) grad: 0.2504 (0.2567) time: 0.3270 data: 0.0035 max mem: 3953 +train: [18] [ 60/400] eta: 0:02:11 lr: 0.000011 loss: 3.0320 (3.0332) grad: 0.2504 (0.2527) time: 0.3141 data: 0.0042 max mem: 3953 +train: [18] [ 80/400] eta: 0:01:59 lr: 0.000011 loss: 3.0248 (3.0298) grad: 0.2569 (0.2538) time: 0.3336 data: 0.0039 max mem: 3953 +train: [18] [100/400] eta: 0:01:49 lr: 0.000010 loss: 3.0336 (3.0335) grad: 0.2608 (0.2563) time: 0.3323 data: 0.0043 max mem: 3953 +train: [18] [120/400] eta: 0:01:40 lr: 0.000009 loss: 3.0498 (3.0340) grad: 0.2590 (0.2539) time: 0.3236 data: 0.0041 max mem: 3953 +train: [18] [140/400] eta: 0:01:31 lr: 0.000009 loss: 3.0120 (3.0298) grad: 0.2510 (0.2534) time: 0.3187 data: 0.0041 max mem: 3953 +train: [18] [160/400] eta: 0:01:23 lr: 0.000008 loss: 3.0097 (3.0295) grad: 0.2459 (0.2524) time: 0.3219 data: 0.0041 max mem: 3953 +train: [18] [180/400] eta: 0:01:16 lr: 0.000008 loss: 3.0213 (3.0290) grad: 0.2422 (0.2524) time: 0.3224 data: 0.0042 max mem: 3953 +train: [18] [200/400] eta: 0:01:08 lr: 0.000007 loss: 3.0489 (3.0314) grad: 0.2634 (0.2548) time: 0.3257 data: 0.0043 max mem: 3953 +train: [18] [220/400] eta: 0:01:01 lr: 0.000007 loss: 3.0450 (3.0315) grad: 0.2582 (0.2541) time: 0.3186 data: 0.0041 max mem: 3953 +train: [18] [240/400] eta: 0:00:54 lr: 0.000006 loss: 3.0142 (3.0294) grad: 0.2404 (0.2531) time: 0.3232 data: 0.0040 max mem: 3953 +train: [18] [260/400] eta: 0:00:47 lr: 0.000006 loss: 3.0010 (3.0272) grad: 0.2424 (0.2528) time: 0.3232 data: 0.0043 max mem: 3953 +train: [18] [280/400] eta: 0:00:40 lr: 0.000006 loss: 3.0010 (3.0263) grad: 0.2424 (0.2524) time: 0.3209 data: 0.0041 max mem: 3953 +train: [18] [300/400] eta: 0:00:33 lr: 0.000005 loss: 3.0201 (3.0266) grad: 0.2373 (0.2520) time: 0.3160 data: 0.0039 max mem: 3953 +train: [18] [320/400] eta: 0:00:26 lr: 0.000005 loss: 3.0335 (3.0275) grad: 0.2499 (0.2524) time: 0.3176 data: 0.0042 max mem: 3953 +train: [18] [340/400] eta: 0:00:20 lr: 0.000004 loss: 3.0368 (3.0282) grad: 0.2527 (0.2522) time: 0.3195 data: 0.0041 max mem: 3953 +train: [18] [360/400] eta: 0:00:13 lr: 0.000004 loss: 3.0179 (3.0273) grad: 0.2538 (0.2530) time: 0.3404 data: 0.0042 max mem: 3953 +train: [18] [380/400] eta: 0:00:06 lr: 0.000004 loss: 3.0170 (3.0277) grad: 0.2600 (0.2526) time: 0.3243 data: 0.0041 max mem: 3953 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 3.0235 (3.0283) grad: 0.2405 (0.2519) time: 0.3250 data: 0.0040 max mem: 3953 +train: [18] Total time: 0:02:13 (0.3338 s / it) +train: [18] Summary: lr: 0.000003 loss: 3.0235 (3.0283) grad: 0.2405 (0.2519) +eval (validation): [18] [ 0/85] eta: 0:04:37 time: 3.2637 data: 3.0159 max mem: 3953 +eval (validation): [18] [20/85] eta: 0:00:31 time: 0.3493 data: 0.0051 max mem: 3953 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3316 data: 0.0042 max mem: 3953 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3099 data: 0.0042 max mem: 3953 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3221 data: 0.0045 max mem: 3953 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3106 data: 0.0042 max mem: 3953 +eval (validation): [18] Total time: 0:00:30 (0.3638 s / it) +cv: [18] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 3.099 acc: 0.100 f1: 0.065 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [19] [ 0/400] eta: 0:23:59 lr: nan time: 3.5980 data: 3.3451 max mem: 3953 +train: [19] [ 20/400] eta: 0:03:31 lr: 0.000003 loss: 3.0311 (3.0427) grad: 0.2611 (0.2596) time: 0.4053 data: 0.0045 max mem: 3953 +train: [19] [ 40/400] eta: 0:02:40 lr: 0.000003 loss: 3.0311 (3.0341) grad: 0.2505 (0.2528) time: 0.3288 data: 0.0040 max mem: 3953 +train: [19] [ 60/400] eta: 0:02:16 lr: 0.000002 loss: 3.0366 (3.0365) grad: 0.2435 (0.2488) time: 0.3147 data: 0.0036 max mem: 3953 +train: [19] [ 80/400] eta: 0:02:03 lr: 0.000002 loss: 3.0209 (3.0268) grad: 0.2416 (0.2480) time: 0.3338 data: 0.0036 max mem: 3953 +train: [19] [100/400] eta: 0:01:52 lr: 0.000002 loss: 3.0040 (3.0273) grad: 0.2454 (0.2490) time: 0.3286 data: 0.0040 max mem: 3953 +train: [19] [120/400] eta: 0:01:42 lr: 0.000002 loss: 3.0328 (3.0303) grad: 0.2576 (0.2483) time: 0.3240 data: 0.0040 max mem: 3953 +train: [19] [140/400] eta: 0:01:34 lr: 0.000001 loss: 3.0328 (3.0307) grad: 0.2475 (0.2499) time: 0.3411 data: 0.0041 max mem: 3953 +train: [19] [160/400] eta: 0:01:25 lr: 0.000001 loss: 3.0331 (3.0337) grad: 0.2581 (0.2508) time: 0.3211 data: 0.0043 max mem: 3953 +train: [19] [180/400] eta: 0:01:17 lr: 0.000001 loss: 3.0588 (3.0381) grad: 0.2581 (0.2506) time: 0.3219 data: 0.0042 max mem: 3953 +train: [19] [200/400] eta: 0:01:10 lr: 0.000001 loss: 3.0361 (3.0374) grad: 0.2468 (0.2505) time: 0.3246 data: 0.0042 max mem: 3953 +train: [19] [220/400] eta: 0:01:02 lr: 0.000001 loss: 3.0242 (3.0351) grad: 0.2471 (0.2515) time: 0.3140 data: 0.0041 max mem: 3953 +train: [19] [240/400] eta: 0:00:55 lr: 0.000001 loss: 3.0303 (3.0356) grad: 0.2556 (0.2518) time: 0.3185 data: 0.0040 max mem: 3953 +train: [19] [260/400] eta: 0:00:48 lr: 0.000000 loss: 3.0231 (3.0324) grad: 0.2563 (0.2532) time: 0.3293 data: 0.0040 max mem: 3953 +train: [19] [280/400] eta: 0:00:41 lr: 0.000000 loss: 3.0031 (3.0318) grad: 0.2498 (0.2519) time: 0.3192 data: 0.0040 max mem: 3953 +train: [19] [300/400] eta: 0:00:34 lr: 0.000000 loss: 3.0240 (3.0321) grad: 0.2500 (0.2525) time: 0.3150 data: 0.0041 max mem: 3953 +train: [19] [320/400] eta: 0:00:27 lr: 0.000000 loss: 3.0182 (3.0316) grad: 0.2618 (0.2533) time: 0.3161 data: 0.0041 max mem: 3953 +train: [19] [340/400] eta: 0:00:20 lr: 0.000000 loss: 3.0142 (3.0309) grad: 0.2618 (0.2538) time: 0.3136 data: 0.0041 max mem: 3953 +train: [19] [360/400] eta: 0:00:13 lr: 0.000000 loss: 3.0197 (3.0299) grad: 0.2602 (0.2541) time: 0.3204 data: 0.0043 max mem: 3953 +train: [19] [380/400] eta: 0:00:06 lr: 0.000000 loss: 3.0197 (3.0300) grad: 0.2602 (0.2543) time: 0.3164 data: 0.0041 max mem: 3953 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 3.0014 (3.0293) grad: 0.2493 (0.2538) time: 0.3175 data: 0.0040 max mem: 3953 +train: [19] Total time: 0:02:13 (0.3347 s / it) +train: [19] Summary: lr: 0.000000 loss: 3.0014 (3.0293) grad: 0.2493 (0.2538) +eval (validation): [19] [ 0/85] eta: 0:04:37 time: 3.2688 data: 3.0340 max mem: 3953 +eval (validation): [19] [20/85] eta: 0:00:31 time: 0.3408 data: 0.0054 max mem: 3953 +eval (validation): [19] [40/85] eta: 0:00:17 time: 0.3020 data: 0.0040 max mem: 3953 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3015 data: 0.0043 max mem: 3953 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.2877 data: 0.0044 max mem: 3953 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.2793 data: 0.0040 max mem: 3953 +eval (validation): [19] Total time: 0:00:29 (0.3437 s / it) +cv: [19] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.090 acc: 0.099 f1: 0.065 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +eval model info: +{"score": 0.0991140642303433, "hparam": [19, 1.0], "hparam_id": 42, "epoch": 19, "is_best": false, "best_score": 0.09985234403839055} +eval (train): [20] [ 0/509] eta: 0:26:58 time: 3.1790 data: 2.9339 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:03:35 time: 0.3046 data: 0.0042 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:02:59 time: 0.3232 data: 0.0049 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:02:43 time: 0.3239 data: 0.0041 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:29 time: 0.2986 data: 0.0044 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:19 time: 0.3162 data: 0.0041 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:10 time: 0.3050 data: 0.0043 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:02 time: 0.3111 data: 0.0044 max mem: 3953 +eval (train): [20] [160/509] eta: 0:01:54 time: 0.3087 data: 0.0044 max mem: 3953 +eval (train): [20] [180/509] eta: 0:01:47 time: 0.3080 data: 0.0042 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:42 time: 0.3665 data: 0.0049 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:36 time: 0.3477 data: 0.0047 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:29 time: 0.3419 data: 0.0042 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:22 time: 0.3127 data: 0.0040 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:15 time: 0.3192 data: 0.0036 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:09 time: 0.3509 data: 0.0043 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:02 time: 0.3048 data: 0.0041 max mem: 3953 +eval (train): [20] [340/509] eta: 0:00:55 time: 0.3164 data: 0.0044 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:48 time: 0.3174 data: 0.0044 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:42 time: 0.3362 data: 0.0041 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:35 time: 0.3193 data: 0.0043 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:29 time: 0.3196 data: 0.0041 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:22 time: 0.3194 data: 0.0041 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3246 data: 0.0042 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3071 data: 0.0044 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.2967 data: 0.0041 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2874 data: 0.0040 max mem: 3953 +eval (train): [20] Total time: 0:02:46 (0.3265 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:39 time: 3.2912 data: 3.0350 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3445 data: 0.0037 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3126 data: 0.0043 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3156 data: 0.0049 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.2979 data: 0.0042 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2899 data: 0.0041 max mem: 3953 +eval (validation): [20] Total time: 0:00:30 (0.3538 s / it) +eval (test): [20] [ 0/85] eta: 0:04:32 time: 3.2030 data: 3.0036 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3539 data: 0.0051 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3196 data: 0.0040 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3095 data: 0.0044 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3073 data: 0.0043 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2955 data: 0.0042 max mem: 3953 +eval (test): [20] Total time: 0:00:30 (0.3578 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:18 time: 3.1466 data: 2.9589 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:27 time: 0.3146 data: 0.0125 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:15 time: 0.3043 data: 0.0037 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:07 time: 0.3179 data: 0.0038 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.2864 data: 0.0042 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2781 data: 0.0040 max mem: 3953 +eval (testid): [20] Total time: 0:00:28 (0.3428 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +eval model info: +{"score": 0.09985234403839055, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 18, "is_best": true, "best_score": 0.09985234403839055} +eval (train): [20] [ 0/509] eta: 0:27:25 time: 3.2329 data: 3.0360 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:03:32 time: 0.2938 data: 0.0041 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:03:02 time: 0.3402 data: 0.0048 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:02:48 time: 0.3489 data: 0.0041 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:34 time: 0.3105 data: 0.0040 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:25 time: 0.3377 data: 0.0046 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:15 time: 0.3192 data: 0.0040 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:07 time: 0.3307 data: 0.0042 max mem: 3953 +eval (train): [20] [160/509] eta: 0:02:00 time: 0.3325 data: 0.0046 max mem: 3953 +eval (train): [20] [180/509] eta: 0:01:51 time: 0.3020 data: 0.0041 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:44 time: 0.3197 data: 0.0045 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:36 time: 0.3086 data: 0.0044 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:29 time: 0.3188 data: 0.0044 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:22 time: 0.3071 data: 0.0037 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:16 time: 0.3351 data: 0.0042 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:09 time: 0.3198 data: 0.0046 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:02 time: 0.3253 data: 0.0042 max mem: 3953 +eval (train): [20] [340/509] eta: 0:00:55 time: 0.3130 data: 0.0045 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:49 time: 0.3144 data: 0.0042 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:42 time: 0.3059 data: 0.0044 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:35 time: 0.3048 data: 0.0043 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:28 time: 0.3032 data: 0.0043 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:22 time: 0.2985 data: 0.0046 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:15 time: 0.3132 data: 0.0046 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3167 data: 0.0043 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.2968 data: 0.0042 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2849 data: 0.0040 max mem: 3953 +eval (train): [20] Total time: 0:02:44 (0.3234 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:31 time: 3.1915 data: 2.9585 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:28 time: 0.2973 data: 0.0137 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:16 time: 0.2973 data: 0.0037 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:08 time: 0.3434 data: 0.0046 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.2975 data: 0.0033 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2892 data: 0.0036 max mem: 3953 +eval (validation): [20] Total time: 0:00:29 (0.3454 s / it) +eval (test): [20] [ 0/85] eta: 0:04:31 time: 3.1987 data: 2.9628 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3252 data: 0.0236 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:17 time: 0.3286 data: 0.0040 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3236 data: 0.0045 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.2945 data: 0.0044 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2895 data: 0.0040 max mem: 3953 +eval (test): [20] Total time: 0:00:30 (0.3540 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:19 time: 3.1658 data: 2.9621 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3561 data: 0.0055 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3239 data: 0.0044 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3198 data: 0.0040 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.2931 data: 0.0039 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2836 data: 0.0037 max mem: 3953 +eval (testid): [20] Total time: 0:00:29 (0.3593 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-------:|---------:|----------:|---------:|----------:| +| flat_mae | reg | linear | nsd_cococlip | best | 18 | 0.0066 | 0.05 | 43 | [22, 1.0] | train | 2.8795 | 0.16165 | 0.0019355 | 0.12374 | 0.001887 | +| flat_mae | reg | linear | nsd_cococlip | best | 18 | 0.0066 | 0.05 | 43 | [22, 1.0] | validation | 3.0988 | 0.099852 | 0.0036408 | 0.064526 | 0.0030336 | +| flat_mae | reg | linear | nsd_cococlip | best | 18 | 0.0066 | 0.05 | 43 | [22, 1.0] | test | 3.1099 | 0.095547 | 0.0036145 | 0.054495 | 0.0025466 | +| flat_mae | reg | linear | nsd_cococlip | best | 18 | 0.0066 | 0.05 | 43 | [22, 1.0] | testid | 3.089 | 0.089069 | 0.0037257 | 0.057595 | 0.002917 | + + +done! total time: 1:05:51 diff --git a/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/train_log.json b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..420073d446fa649b137edc2156f67804aec021a2 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/nsd_cococlip__reg__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.183514566421509, "train/grad": 0.2870556718111038, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.211082763671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.210721435546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.210179443359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.20958740234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.209110107421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.20852783203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.207647705078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.206795654296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.205625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.20450439453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.20340087890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.20173095703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.200211181640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.19819091796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.196229248046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.194451904296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1923095703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.189989013671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.18762451171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.18550537109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.18319091796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.18099365234375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.178765869140625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.176807861328125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.174871826171875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1728173828125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.171143798828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1698095703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.168267822265625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1666357421875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.165423583984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.164483642578125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.16345458984375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.162763671875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1619970703125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1615380859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.161297607421875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.161414794921875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1619390869140624, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1629766845703124, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1641131591796876, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.165430908203125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.167276611328125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.168909912109375, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1717938232421874, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1763934326171874, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.18241943359375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1918096923828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.20005126953125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04357640016824007, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04353936195373535, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.04347774272784591, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.04341772306710481, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04335763137787581, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0432762729935348, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.04318520788103342, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.04308608286082745, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.04295713031664491, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.04282405659556389, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.04269443184137344, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.042507378458976744, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.04233141278848052, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.04208777282387018, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.04186364629305899, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.04165873181074858, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.041414430690929295, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.04114630984142423, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.04087143674492836, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.04063996625132859, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.040382663067430255, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.04014735302887857, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03991755152121186, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.039704909930005666, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.039518804093822836, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03932932454161346, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03918958259746432, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03907987638376653, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.038961510248482226, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.038856239980086686, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0387876864336431, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.038743569012731315, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03870907817967236, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03870005268603563, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03871711092069745, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03876130600459873, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.038841469194740054, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03895903897471726, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.039133209986612204, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0394053343962878, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03963343136943877, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03982677607797086, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.040084205362945796, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04034468222409487, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.040733756395056844, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04127813990227878, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04192241949029267, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04291861710138619, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04379791259765625, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.2067294120788574, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.205620765686035, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.203861951828003, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.2021703720092773, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.20054030418396, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1983437538146973, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.195934772491455, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.193305253982544, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1899430751800537, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1865837574005127, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.183464288711548, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.179133176803589, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.175259590148926, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1700730323791504, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1657819747924805, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1621556282043457, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.158149480819702, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1542277336120605, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.150726318359375, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.148157835006714, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.145660400390625, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1437699794769287, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1421048641204834, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1407032012939453, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.13944411277771, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1380958557128906, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.137057304382324, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.136258125305176, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1355631351470947, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.135347366333008, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1359148025512695, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.13700270652771, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.139155626296997, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1413838863372803, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.14444899559021, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1472928524017334, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1501576900482178, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.152678966522217, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.154900074005127, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.156874418258667, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.157989025115967, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.15963077545166, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.166358470916748, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1733386516571045, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1743414402008057, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1781060695648193, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1873090267181396, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.2027552127838135, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2262511253356934, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05057216685123662, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05094130675526024, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05075673680324843, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05001845699520118, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05020302694721299, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05020302694721299, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05001845699520118, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.049464747139165745, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05001845699520118, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.05057216685123662, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05167958656330749, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05352528608342562, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.052417866371354746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.05426356589147287, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.05758582502768549, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.059431524547803614, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.059616094499815434, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.059616094499815434, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.05998523440383906, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06016980435585087, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06109265411590993, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.061461794019933555, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06109265411590993, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06035437430786268, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.059431524547803614, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.05887781469176818, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.060538944259874494, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06016980435585087, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06109265411590993, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06496862310815799, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06423034330011074, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.060723514211886306, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.059431524547803614, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0592469545957918, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06016980435585087, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06016980435585087, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.059616094499815434, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.05795496493170912, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.055740125507567365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.021247284357625667, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.021464029663914905, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021438452494711113, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02151997401911278, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021856023625857025, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021891679446192223, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022065322216728748, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.021817810673695533, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022630024556095116, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.022877437231887704, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02371383499932692, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.024959136418541906, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.024074735956353125, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.024488432139573153, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.025380578212077027, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.025793701716018733, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02479327243481692, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.023644220928395392, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.022574059732691835, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02188941939941724, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.022447164487282886, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.02290756806225981, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.022734373313449897, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.023339798750180052, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02334638797005768, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.022548499727647355, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.02264644014108956, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.022892381766750205, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.021737640907893624, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.021392677903689785, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02047426141855962, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.018831416824530038, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.016278733068205212, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.014729999359627736, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01342319419851834, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.013966455126705836, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.013612646871820575, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.014281588391648226, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.01362992180145905, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.01674677282777179, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.016555478858585607, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.014203733886519436, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.01028210821608471, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.00972560957083197, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.013261836431874155, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.01765935380646171, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.019111569559370798, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.024260055632091243, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.028699640883634577, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 3.1629766845703124, "validation/loss_best": 3.156874418258667, "validation/acc_best": 0.06496862310815799, "validation/f1_best": 0.01674677282777179} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.166144559383392, "train/grad": 0.2804982505738735, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.198492431640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.196607666015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.193807373046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.19109130859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.18866455078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1854931640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.182213134765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.179005126953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.175238037109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.17172607421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.168848876953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.165042724609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.162186279296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.15877197265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.156243896484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.154248046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.152203369140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.150338134765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.14859130859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.14740966796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.145943603515625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.14467529296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.143515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.142442626953125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.141435546875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.14053955078125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.13985107421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.139337158203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.138885498046875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.13884765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.13896484375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.139261474609375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1398199462890624, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1406573486328124, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1419708251953127, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.143492431640625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1456280517578126, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.148143310546875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1517376708984375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1576953125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1636712646484373, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1691748046875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1758111572265624, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1821966552734375, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1928802490234376, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.211854248046875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.232159423828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.253155517578125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.27111572265625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.04155729033052921, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.04134500447660685, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0410119098238647, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.040706144310534, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.04041812838986516, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.04005174287594855, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03967860990203917, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03930682178586722, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.038883370170369747, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03850119670853019, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.038187525058165195, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03780272004194558, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03751169873401523, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03719727288000286, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03698584746569395, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03683734009973705, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036709409710019826, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03661857867613435, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03656844134442508, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03655308457091451, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03655980238690972, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03658723680302501, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03663805816322565, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0367040737811476, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03678731196559966, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03689935016445815, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.037012192113325, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03712249746546149, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.037287044422701004, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.037502639451995494, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03771515141241252, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03792339269071818, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.038221003236249086, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.038503040503710506, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.038851460162550214, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.039210317144170406, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.039633057452738284, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.040080533400177955, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04065212057903409, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04156870332546532, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04239011842757463, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04301835805177689, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.043698144620284436, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04436195394024253, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04549989790655672, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0473191578220576, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04881571182049811, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05016097171232104, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0514350357837975, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.18847393989563, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1855685710906982, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.181104898452759, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1770875453948975, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.173487901687622, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1690750122070312, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1648433208465576, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1608173847198486, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.156625270843506, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.152984619140625, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1502878665924072, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1472551822662354, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1451423168182373, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1430211067199707, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1416330337524414, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.140613555908203, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1396217346191406, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1387526988983154, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.137917995452881, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1372432708740234, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1365456581115723, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1359195709228516, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.135331153869629, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1348352432250977, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.134446859359741, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.134394407272339, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.13480806350708, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1355373859405518, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.137143850326538, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.139470100402832, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.141791582107544, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.143852472305298, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1474273204803467, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1520848274230957, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1588151454925537, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.166757822036743, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.177086591720581, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1882145404815674, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1990103721618652, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2055187225341797, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.209596872329712, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.220614433288574, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.249180555343628, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.2602548599243164, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.2893548011779785, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.324584722518921, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.340055465698242, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.3224823474884033, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.333651304244995, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05094130675526024, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05075673680324843, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05278700627537837, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05278700627537837, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05278700627537837, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05444813584348468, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.055924695459579184, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.05813953488372093, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0592469545957918, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06109265411590993, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.061461794019933555, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.061461794019933555, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06127722406792174, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06109265411590993, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06016980435585087, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.060538944259874494, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.060538944259874494, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.060723514211886306, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.05906238464377999, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.05647840531561462, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.05721668512366187, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.05629383536360281, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.05758582502768549, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.05813953488372093, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.05795496493170912, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.05629383536360281, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.05666297526762643, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.05813953488372093, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.05758582502768549, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.05795496493170912, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.059431524547803614, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.05998523440383906, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06183093392395718, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.05832410483573274, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.05887781469176818, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.058693244739756366, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.05666297526762643, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.05297157622739018, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.05555555555555555, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06699889258028793, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06459948320413436, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06755260243632337, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0636766334440753, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06626061277224068, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06496862310815799, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06681432262827612, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.05795496493170912, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02315684123176842, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.023107772351380017, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02405362485219599, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.024091327646754035, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.023707814490482478, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0239524245733754, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02384771722489147, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.024550459183049652, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023209697905674523, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.023426855779882582, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023532571576945813, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.023045887445860395, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022628191888229524, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.022884751010619583, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.022749415170481013, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02276920124652546, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.022209941682008207, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02262470226839136, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.022923479680003928, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.023338972334073144, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0227468810795573, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.021665525440838784, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.022207941883554183, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.022560781189901416, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02382213010517263, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.025134417594102582, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.025062376230286666, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.024669643521420353, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02414130364418383, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.024522219701469127, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02335108404919802, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.022010007308597628, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.019996104596394133, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01827605595013055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.018028806066919322, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.017647259756580564, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.017914235307838887, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.017561605039451478, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.01816513854185527, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.01813629252936963, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.017462123729201792, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.017226055319411303, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.013920410576034714, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.019805603754829374, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.020658168462969716, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.023916888390419482, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.028152790012455787, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.02936645611534346, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.026666380892992458, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 3.1821966552734375, "validation/loss_best": 3.2602548599243164, "validation/acc_best": 0.06755260243632337, "validation/f1_best": 0.019805603754829374} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.1669720649719237, "train/grad": 0.28490820750594137, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.183140869140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.18040283203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.176568603515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.173397216796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.170908203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.167933349609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.16523193359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.162962646484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1607562255859376, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.158865966796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.157578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.156019287109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.154854736328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.15343017578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.152105712890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.15105712890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1496484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.148211669921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.146778564453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.145556640625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.144259033203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1430419921875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.141796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1407958984375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.13993896484375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.138975830078125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.138302001953125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.13783935546875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.137257080078125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.136439208984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.135946044921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.135882568359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.13598388671875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1367718505859377, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1382440185546874, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1404840087890626, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.14383056640625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.148009033203125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1534906005859376, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.160455322265625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.16808837890625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1772174072265624, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1910198974609374, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.2052215576171874, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.2262844848632812, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.249905700683594, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.272097473144531, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.3076983642578126, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.340948486328125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03929183858446777, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.038958471128717066, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0384858116786927, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03809890007600188, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03778103296644986, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03743344472721219, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03713621985167265, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03689608029089868, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03668120929971337, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03653575360774994, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03644805084913969, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.036379138249903915, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03634654376655817, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036331106629222634, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.036331673264503477, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03633872345089913, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03635345939546823, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03637143987230956, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036399993915110826, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036427569752559064, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0364649573341012, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036511990381404756, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03657106561586261, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03664466648362577, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03673652314580977, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.036866193963214756, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.036995548149570824, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.037128304215148095, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03731882971711457, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03757409380748868, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03783981677144766, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.038120256373658776, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03855004710145295, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03897782743908465, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03952115473337472, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0400845979899168, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04075717483647168, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04150282049551606, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04240664955228567, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.043558488814160225, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04468705188483, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04583245694637299, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04720690526068211, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04839948961511254, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05029984848573804, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05241473127156496, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05421891240403056, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.056515394058078525, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0580957105755806, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.169686794281006, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1661746501922607, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1612284183502197, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.157336473464966, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.154256582260132, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1510047912597656, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.148219108581543, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1459882259368896, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.14389967918396, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.142317533493042, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1411712169647217, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1398448944091797, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1388182640075684, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.137599468231201, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.136718273162842, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.135993480682373, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1352639198303223, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1346309185028076, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1342031955718994, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.133960723876953, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.133817434310913, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.133805990219116, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.133862257003784, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.134046792984009, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1344001293182373, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1349611282348633, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.13542103767395, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1356992721557617, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.136019706726074, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.136972427368164, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.138920307159424, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1415176391601562, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.145718812942505, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.149646520614624, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.156085252761841, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.16601300239563, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1705965995788574, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1651580333709717, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1632466316223145, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1788790225982666, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.20318341255188, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2304279804229736, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2742435932159424, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.3138794898986816, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.355832815170288, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.39784836769104, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.4058055877685547, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.4059064388275146, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.432629108428955, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.054078995939461055, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05647840531561462, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05795496493170912, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05887781469176818, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06127722406792174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06109265411590993, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06016980435585087, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.059431524547803614, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.059616094499815434, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.05906238464377999, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.05813953488372093, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.059616094499815434, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.058508674787744554, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.05906238464377999, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.059616094499815434, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.060538944259874494, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.060538944259874494, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.05260243632336656, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.05094130675526024, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.04891103728313031, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.052417866371354746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.049464747139165745, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.05389442598744924, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.049464747139165745, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.047619047619047616, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.062384643779992616, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.05906238464377999, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.024003546329079722, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02461038847271572, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.024685741716210328, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02408286781237369, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.023313807308657928, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.023741012273817353, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022868013545601317, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0229935075479176, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02237189149790666, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.022701937265092884, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02241643259231901, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.022374621051300603, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022611891834932774, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.022279612559786947, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.022314651174225073, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.022218004430584668, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.022319510707562912, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.021879756714444056, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.021124127379860667, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.021144364707927226, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.020009930387621232, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01941603968226664, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.020281877221987998, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.019879369074555658, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.01995975153912522, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.020197699015073182, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.02071093838219079, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.021167315767666003, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0228636674773592, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.024329005991057848, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.026192938380806094, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.02526511748757591, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.024434581763023117, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.02546481682677147, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.025246775505641778, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.028523492791251423, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.028870289374670205, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02732056392581401, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.029492178592158077, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.030092333499647534, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.025721482632017234, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.023277535716591632, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.02369269183351431, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.01868538658988378, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.021951498105784253, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0259003361278969, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0253732399853074, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.030983413224109396, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.024222294709787106, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 3.135946044921875, "validation/loss_best": 3.138920307159424, "validation/acc_best": 0.06755260243632337, "validation/f1_best": 0.026192938380806094} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.171776798963547, "train/grad": 0.295665198341012, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.171976318359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.169110107421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.165394287109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.162664794921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.16058837890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1583294677734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1565032958984376, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.15473388671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.153125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1516259765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1503564453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.148763427734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.147177734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.14544189453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.14395263671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.142628173828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.141181640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.139739990234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1383642578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.137293701171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.136041259765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.13496337890625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.133878173828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.132728271484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1318115234375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.130760498046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.130015869140625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.129608154296875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.12944091796875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1297296142578124, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.130509033203125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1316668701171877, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.13401611328125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.13705810546875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.14194580078125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1475201416015626, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1528265380859377, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.157880859375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1654437255859373, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1777557373046874, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1879391479492187, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.198100891113281, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.21339111328125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.231401062011719, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.2608688354492186, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.304869384765625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.3549609375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.4014125061035156, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.429570617675781, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03822232138365507, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03792947876267135, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.037563364468514916, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.037314175181090835, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.037141848905012015, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03698501331731677, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.036881148731335994, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.036817788714542984, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03677983816713095, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03676754537038505, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03676772067323327, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03677312675863505, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036785240452736616, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0368063495028764, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03683138193562627, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03685446908697486, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036889962237328294, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03693720621056855, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036990074589848515, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03704403336159885, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03711472493596375, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03719163578934968, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03728819309733808, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03739785502664745, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.037524377992376685, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03768945435993373, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03785450380295515, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03803081102669239, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03830991374328732, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03870947429910302, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.039126823423430324, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03955599830485881, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.040208644131198526, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.040839456524699926, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04164874790236354, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.042442517131567, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.043181109428405764, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.043795557990670204, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0446424238756299, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04600371880456805, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04714564546942711, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04816448578611016, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.049578678999096154, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05119139634072781, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05373647656291723, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.056774888560175894, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.060019513908773664, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06193561578169465, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06354887746274471, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.155728340148926, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1528141498565674, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.149157762527466, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1466617584228516, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.144831418991089, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1429898738861084, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1414549350738525, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.140171527862549, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.138835906982422, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1377017498016357, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1367435455322266, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.135565996170044, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1346170902252197, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1335136890411377, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.132838487625122, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.132258415222168, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.131747007369995, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.131197452545166, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.130675792694092, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.13030743598938, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1296956539154053, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1290159225463867, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1280579566955566, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1267685890197754, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.125335216522217, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1239826679229736, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1233294010162354, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.123140573501587, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1238551139831543, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1260478496551514, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.129605531692505, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.133786201477051, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1394078731536865, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1448073387145996, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.149447202682495, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1502180099487305, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1601715087890625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1790475845336914, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1907386779785156, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1910414695739746, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.2125420570373535, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2429909706115723, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.312349557876587, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.369971990585327, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.3940417766571045, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.4081192016601562, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.4808835983276367, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.6658520698547363, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.619966745376587, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06109265411590993, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.059800664451827246, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07032115171650055, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07419712070874862, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08176448874123293, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06995201181247693, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06884459210040605, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06921373200442968, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07013658176448874, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0664451827242525, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06441491325212255, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06109265411590993, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.05149501661129568, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.052233296419342934, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.051310446659283866, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.023376371502226007, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.023197555894156976, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02349065691106951, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.023149139604646315, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.022508062335684167, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.022594396434419576, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022025245622426068, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02188787517249074, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02258315746881959, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.022632417224553045, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.022603580328894677, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02178803483259603, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022319195642116693, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.020950420894045498, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02161062422654174, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.021310590667809926, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.021715539050434066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.022455689968101832, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.022741098601505152, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.023951295310196144, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.025100598187316744, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.025542469245961836, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.026296816584137312, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.028152417311865855, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.027550000819743875, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.027447763076630976, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.027990187365809254, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.02810335316946075, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02696143917586681, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.027490194426635653, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.028285009070502885, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.028393573118894788, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0288475535898113, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.02820710819034938, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.030192945505569505, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.035072134029746196, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.035536987549809496, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.037246375637485264, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03503666414667142, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03193352300427677, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.029463095860953064, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03172162936370283, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.031874396221514174, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.029877898575708616, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0298501844198605, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03486291386274261, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03236274525283451, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.027212736272794, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.02620575430224296, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 3.157880859375, "validation/loss_best": 3.1790475845336914, "validation/acc_best": 0.08176448874123293, "validation/f1_best": 0.037246375637485264} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.1694869709014895, "train/grad": 0.3004502998292446, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.159320068359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1572064208984374, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1547784423828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1529913330078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.15158447265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.15008056640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1486163330078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1470745849609374, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.14538818359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.143787841796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1422845458984376, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1404425048828126, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1387799072265623, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.13688720703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.135228271484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1337841796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.13228759765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.13076171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.129176025390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.127750244140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12632080078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.124871826171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.123370361328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12186279296875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.120628662109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.11934326171875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.118411865234375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1179425048828127, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.11771240234375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.11776123046875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.118311767578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.119412841796875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.121629638671875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.12417236328125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1283453369140624, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1334576416015625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1390557861328126, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1455517578125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.155172119140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1715386962890624, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1870361328125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.202120056152344, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.2276275634765623, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.2614251708984376, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.30543701171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.342315979003906, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.380052185058594, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.4464671325683596, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.529299621582031, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036896714260801676, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03671896178275347, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.036534776808694006, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.036434633024036885, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.036379116605967286, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03634349097497761, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03632385096512735, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03631476553156972, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03631058874540031, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.036308801230043174, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0363106725551188, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03631776268593967, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03632319292984903, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03634195462800562, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.036362461429089304, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036388006852939726, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036422839546576144, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03646845175884664, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0365267553832382, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03658705458045006, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.036670939419418576, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03676330024376512, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03687839941121638, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03701520051807165, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03717952838167548, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.037403589272871615, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03763846074230969, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.037885572286322715, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03825703375041485, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03873509555123746, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.039218789543956516, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.039722312232479455, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04047193425707519, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.041144349006935955, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.041991666248068216, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04287867269478738, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.043766517899930475, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.044638116378337145, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04589220110327005, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04795739317312837, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04963068133220076, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.051102735698223115, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.053486991934478284, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05599435718730092, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05819640845060348, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.059502130448818205, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.061504495833069085, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06430207792669534, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0677571994252503, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.147475004196167, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1455347537994385, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1433024406433105, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1417367458343506, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1405396461486816, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1392626762390137, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.138077735900879, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.136941432952881, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.135741710662842, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1346662044525146, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1337995529174805, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.132730007171631, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1319353580474854, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1310694217681885, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1304051876068115, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1299595832824707, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1295793056488037, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1292977333068848, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1291675567626953, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.129082202911377, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.129016160964966, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.129028081893921, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1291637420654297, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.129507541656494, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1300721168518066, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1306910514831543, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1310853958129883, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.130521535873413, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.127878189086914, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1241776943206787, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1230714321136475, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1242148876190186, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1301722526550293, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.142829656600952, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.160399913787842, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1746575832366943, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.192697525024414, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.2117888927459717, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.2392661571502686, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2591123580932617, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.263918399810791, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.278975009918213, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.338454484939575, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.4736361503601074, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.5538158416748047, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.530451536178589, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.4840126037597656, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.580684185028076, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.5892333984375, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.05998523440383906, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05998523440383906, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.05887781469176818, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.05758582502768549, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.05906238464377999, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06090808416389812, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.060538944259874494, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.060538944259874494, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06127722406792174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06090808416389812, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.061461794019933555, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07567368032484312, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07327427094868956, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.073827980804725, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07087486157253599, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07069029162052418, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07308970099667775, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07438169066076043, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07419712070874862, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07401255075673681, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06699889258028793, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06127722406792174, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06478405315614617, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06312292358803986, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02317887225105642, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.023030775921851848, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.022545735413460544, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.022591149863829582, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02217206007065846, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021399535784765233, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02235606837319574, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02169837487857271, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02211282724016926, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.023467014183780496, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023997181117282818, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.022746935335562764, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02076957379278214, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01886807221176748, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01863927236193949, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0183279726751062, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.016973211250000297, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.016223373465954802, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.015995022478075802, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01566077946383467, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.016030384057457114, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0159048608872486, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.015378611806009973, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.014777793626689276, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014350306793080699, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013291687833217769, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01264228739743716, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.012700504005531361, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01556040266134894, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.019780147101990424, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02281314246689121, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.026761472256271124, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.029813073271180702, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.027481095067905328, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.027321048825373215, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.02851454663665297, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.030091161469241873, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02887543444574707, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03378043216454801, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03222787621816268, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03052255667579687, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03179466713519631, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.031051384856411568, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.028976714952664944, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0318100208275866, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04021954548069293, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.040510162797067144, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03429077160080516, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.031765216576202016, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 3.121629638671875, "validation/loss_best": 3.1301722526550293, "validation/acc_best": 0.07936507936507936, "validation/f1_best": 0.029813073271180702} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 3.162473862171173, "train/grad": 0.3025519695132971, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.151024169921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.149794921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14812255859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.146746826171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.145611572265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.14412353515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.14263671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.141121826171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.139320068359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1377978515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.13630859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13456787109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.132969970703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.131126708984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129613037109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1281201171875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126575927734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124866943359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123216552734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.121815185546875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.120135498046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11860595703125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.117032470703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1152490234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.113408203125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1112939453125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1096197509765626, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.108089599609375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1060699462890624, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.104134521484375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1030926513671875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1027081298828123, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.103262939453125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1052667236328126, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.10942626953125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.114749755859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1210015869140624, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.12853759765625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.139178466796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.153788757324219, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1675885009765623, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1827947998046877, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.207109069824219, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.2417327880859377, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.2969293212890625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.3564189147949217, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.4052674865722654, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.495647277832031, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.5676014709472654, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03633367479778826, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.036269661020487544, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.036220405036583546, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03620160568505525, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03619587044231594, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.036195160783827306, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.036196728451177475, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.036199889918789266, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.036205970449373126, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03621502419933677, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.036229206388816236, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03624893205240369, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036267840806394815, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03630183631554246, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03633673284202814, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036372208883985874, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03642436491325498, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036488855239003894, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03657145603559911, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03666051608510315, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03677974788472056, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03691682310774922, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03707964050583541, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03726607340388, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03747987457551062, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.037765287794172764, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03803700361400843, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03828857038170099, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.038638138184323906, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.039100762875750664, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03958274561911821, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.040046623442322016, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.040709303226321936, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.041380780665203926, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.042290263464674356, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.043187667727470395, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04411398082971573, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04515298819169402, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04651785770431161, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0479040586668998, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.049010196980088946, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05028659097850323, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05230810135602951, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05511876726523042, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05860565351322293, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.06123524943366647, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06373121095821262, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06772219313308597, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.07010981040075422, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1432337760925293, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.141831636428833, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.140113353729248, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.138847827911377, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1378228664398193, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1366138458251953, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1355342864990234, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1345672607421875, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.13352632522583, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.132699966430664, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1320641040802, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1313719749450684, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1308884620666504, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.130378484725952, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1300642490386963, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.129819631576538, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1294877529144287, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1291661262512207, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1286895275115967, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1282670497894287, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1278305053710938, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.127600908279419, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.127639055252075, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1281485557556152, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.129194974899292, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.130936622619629, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.132833480834961, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.134793758392334, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1377170085906982, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.142073392868042, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.145780086517334, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.148942232131958, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.153085708618164, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.158491611480713, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1651670932769775, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1638786792755127, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.163452625274658, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.168619394302368, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.183854818344116, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.194312810897827, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.2369837760925293, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.3043248653411865, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.368603467941284, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.396986246109009, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.4476382732391357, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.4576895236968994, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.46561598777771, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.6366889476776123, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.6777563095092773, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05998523440383906, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06127722406792174, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.067921742340347, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.067921742340347, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07973421926910298, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07973421926910298, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0769656699889258, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07733480989294943, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07050572166851236, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06699889258028793, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06626061277224068, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07272056109265411, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07622739018087855, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07585825027685493, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07715023994093761, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07327427094868956, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06404577334809892, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02248249096973323, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02210970147252067, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02200157353258073, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02169190357225668, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.022158387996217346, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02177107098219638, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021340903679922973, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02213933139211652, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023281406622971398, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.022591782978445416, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.022342299341071164, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.021984815789215535, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022419054089776454, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02201134793911154, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.021959405069264467, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.021620595338806132, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02168148528146416, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02081008336852273, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.021609796190611392, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02231304707676807, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.022622865938903423, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.02282316779164528, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.023696169257932873, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02512053897020926, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0276805446490712, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.026348378644007686, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.023416251436162105, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.022473090001275425, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02059750224525713, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.02093076906975932, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02470247572182861, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.024893713043685487, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.030002353147423333, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.030379068026541983, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03240539456736359, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.036108689108244815, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03623959032484166, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03599464169232711, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03530726333327958, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03698967931119722, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03374994108450531, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.028739297400073124, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.024978293865161098, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.027623247056920416, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.031365122238998046, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03881067173517646, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.046164012542465445, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03851176051542222, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03553540136968484, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 3.12853759765625, "validation/loss_best": 3.168619394302368, "validation/acc_best": 0.08010335917312661, "validation/f1_best": 0.03599464169232711} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 3.1506312787532806, "train/grad": 0.29946719273924827, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.147252197265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.145950927734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1441650390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14261962890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14119140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.139466552734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13783935546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.136292724609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13447509765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.132659912109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1312451171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.129385986328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.127701416015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.125731201171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.124000244140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.122344970703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1204638671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1184228515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.116302490234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.114356689453125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.112318115234375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1103076171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1082080078125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.106173095703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.104376220703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1024853515625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1011077880859377, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.100028076171875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.09865966796875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0973004150390624, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0961920166015626, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0958001708984373, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0958685302734374, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0974566650390627, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.101827392578125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1081781005859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.11504150390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1201177978515626, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1265655517578126, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1377093505859377, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.153628234863281, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.173450927734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1987750244140627, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.2235455322265625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.257127685546875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.301694183349609, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.3665306091308596, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.443141403198242, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.4954530334472658, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036036762353032825, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.036010574540123345, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0359922497626394, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03598402559757233, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03598034849390388, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03598006901331246, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.035982399843633175, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03598573370836675, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03599418637342751, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03600360975600779, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03601563110016286, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03603661613538861, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03605644864030182, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036090613715350627, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03612638017162681, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036160606928169726, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03620828814804554, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036266971305012705, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03634221425279975, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036418044660240415, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03652470105327666, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03665436130948365, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03681851624511182, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03701816571876407, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03725450426340103, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.037579139415174725, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03790202293545008, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03819876806810498, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.038598805842921136, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03905446277931333, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.039488245453685525, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.039943675119429825, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04064551656134427, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04137150802649558, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.042338912459090355, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04340542963705957, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04451426917687058, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04532166253775358, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0461742234043777, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04750207224860788, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04921969867311418, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05113628281280398, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05308734972029924, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.054475634153932334, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.056320067159831524, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05883756134659052, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06251044267788529, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06556110970675945, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06705137733370066, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1409430503845215, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1397879123687744, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.138261556625366, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1370601654052734, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1360583305358887, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.13486647605896, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.133772134780884, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.132784128189087, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1317548751831055, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1308820247650146, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.130211591720581, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1295173168182373, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1289775371551514, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1283857822418213, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1279115676879883, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.127544403076172, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.127138376235962, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1266329288482666, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.126171588897705, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1255526542663574, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1245882511138916, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.123324394226074, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.121931552886963, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120622158050537, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.119727849960327, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.119109869003296, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.118745803833008, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.11883282661438, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1210556030273438, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.130187749862671, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.141855239868164, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1492435932159424, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1539714336395264, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.159520387649536, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1680192947387695, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.177406072616577, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1934616565704346, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.2110488414764404, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.232088088989258, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.253533124923706, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.2762179374694824, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.287346124649048, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2910993099212646, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.2923035621643066, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.2972776889801025, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.325317144393921, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.3924403190612793, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.539241313934326, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.5973196029663086, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.059616094499815434, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06035437430786268, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.061461794019933555, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.073827980804725, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07604282022886674, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07604282022886674, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.073827980804725, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06183093392395718, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06201550387596899, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07216685123661867, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08693244739756367, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08084163898117387, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06884459210040605, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06164636397194537, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06349206349206349, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06995201181247693, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07013658176448874, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02206084448086307, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02183930830458308, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021171531460321604, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02143772460423977, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021179504007639172, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020978786121760826, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02177096534138889, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022750962724084427, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02224533237726664, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.021997384589199576, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02139828100831516, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.021519698875682416, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022040626603859182, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.021860369523752903, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02103217166317149, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.021332017191479768, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.021678156716853858, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.021427019875489686, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.02241156101405338, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.024270140228400048, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.024357554480407353, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0248272909868163, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.026890999386275417, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.028428711137071724, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0328792393857522, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03457591526924978, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.034916619659599475, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03485171950147872, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03402878057132278, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.029750651461810423, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02687494845948586, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.028167333134462652, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.031829339774845256, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03227434911665091, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.02667852781071629, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.026528355869548798, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.028197890440622504, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03207447935743241, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03519201000480168, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04090177609818958, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.044676538640874036, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04585246290638212, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.043139347104484554, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04168420178625104, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04668413754783216, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.041375538703857656, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0382327673980797, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03788152346960265, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.034369212962658414, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 3.1987750244140627, "validation/loss_best": 3.2910993099212646, "validation/acc_best": 0.08693244739756367, "validation/f1_best": 0.043139347104484554} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 3.141538093090057, "train/grad": 0.3069150932133198, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.144951171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1437298583984377, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14208984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1404248046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.139132080078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.137554931640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.135880126953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.134393310546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13275390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.131038818359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129669189453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127938232421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.126346435546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12435546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12241943359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.120904541015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.118876953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.116673583984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1142626953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11205078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.109453125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.10689208984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.104068603515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1011590576171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0982330322265623, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.095025634765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0921240234375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0897735595703124, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0867706298828126, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0838360595703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.081861572265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.08105224609375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0812158203125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0824755859375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0852960205078124, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0893148803710937, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0950088500976562, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.100543212890625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1085891723632812, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1264328002929687, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1418917846679686, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.153694763183594, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.173329162597656, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.2007598876953125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.243040771484375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.2876712036132814, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.3375309753417968, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.4052931213378907, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.497585906982422, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03694364508613944, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0369316207524389, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.036922986982390285, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.036918856780976055, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03691893411800265, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03692130097188055, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.036924345893785356, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03693370792083442, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03694939103908837, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.036968607315793635, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03698611529543996, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03701697563752532, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03704675740562379, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03709521920420229, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.037141257701441645, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.037187697840854524, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.037247246382758024, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03732025230303407, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03740729920566082, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03749077511951327, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03760347357951105, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03772894940339029, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.037885295590385795, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.038070175535976886, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03828654895536601, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0385703011136502, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03886388891376555, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03915359851904213, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0395824774634093, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.04012858746573329, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.04064154236577451, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.04116332310251892, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.04193898196332157, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04265136431902647, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04350331254303455, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04438252106308937, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04536111751571298, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04624515613541007, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0474368461035192, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.049617622364312414, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.05130583891645074, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.05243102639913559, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05391743209213019, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05549908753484487, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05789257494732738, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05999424716457725, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.06219418855383992, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06482783108949661, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06945049362257123, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.139552593231201, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.138503074645996, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1371376514434814, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1360208988189697, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.135080337524414, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1340417861938477, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1330485343933105, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.132244348526001, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.131357192993164, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.130596876144409, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1299545764923096, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1292073726654053, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.128574848175049, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1276936531066895, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.126939058303833, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1262991428375244, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.125544309616089, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.124781847000122, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1240904331207275, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.123520851135254, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1229307651519775, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1225500106811523, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1221251487731934, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1217072010040283, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1214730739593506, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.121636390686035, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.122095823287964, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1231484413146973, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.125260353088379, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1291873455047607, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.13376784324646, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.139157772064209, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.147855043411255, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1555235385894775, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.160012722015381, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.168384075164795, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.196152687072754, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.2291970252990723, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.265183448791504, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.3214313983917236, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.3288748264312744, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.295395612716675, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.286454677581787, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.2893433570861816, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.309652805328369, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.3730177879333496, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.46787691116333, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.4430124759674072, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.431208848953247, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.058693244739756366, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.05740125507567368, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05703211517165006, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.057770394979697305, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0592469545957918, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06127722406792174, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06090808416389812, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.067921742340347, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.073827980804725, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0753045404208195, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07401255075673681, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07475083056478406, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07604282022886674, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0769656699889258, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.082687338501292, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08471760797342193, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07881136950904392, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07641196013289037, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07641196013289037, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07327427094868956, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0754891103728313, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07364341085271318, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0664451827242525, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.060538944259874494, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.05740125507567368, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06459948320413436, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06127722406792174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.021766174326992706, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.021605063275792244, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02153724941526432, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021894557330832037, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02165860349174867, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.022692012925218514, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022734117935763746, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.023168721092029994, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023418735229831303, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0230729753384145, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.022995295550865505, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.023845931773342908, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.024400178843798036, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.025761804028925073, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02617761097114696, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.026341729699824026, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02603043353534894, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.025452079638995085, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.027100275487927043, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.028540214575561815, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.030503323196798025, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.031276155726389074, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03292580844274238, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.033204890606038547, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.034072645102311276, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.035378772155276475, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03495493539807038, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.033077006081564504, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.031168148354610164, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.028835821271616404, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.027368841028139038, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.025044287889340596, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.02758744242796755, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.031181954269380214, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03661660837074452, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03809915783670453, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.035525902183578345, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.039094022967979807, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0373998337483753, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03161514889031533, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03108950477516717, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03285276873883778, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03399469217991452, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03342782961851151, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0356019021992427, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03503332795028852, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02915184615861541, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.036713547931967176, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.035288765413733415, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 3.100543212890625, "validation/loss_best": 3.2291970252990723, "validation/acc_best": 0.08471760797342193, "validation/f1_best": 0.039094022967979807} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 3.12599232673645, "train/grad": 0.2933743478357792, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.142666015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.141353759765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.139517822265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.137955322265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13651611328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13481689453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1331982421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.131473388671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12967529296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12799072265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12655517578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1244921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122779541015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.120345458984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.118251953125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11642578125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.113966064453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.111416015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.108648681640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.10598388671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.10297607421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.09976806640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0966156005859373, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0931036376953127, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.089608154296875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.085411376953125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.081612548828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.078262939453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0740423583984375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.069844970703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0671435546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0654229736328125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0641802978515624, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0638897705078123, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0642462158203125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0660382080078126, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0684609985351563, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.072471008300781, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.080541076660156, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0944158935546877, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.10783935546875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1225146484375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.144032745361328, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1672882080078124, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.200637741088867, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.253381538391113, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.302153396606445, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.3604718017578126, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.4132235717773436, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0358521455898881, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.035844898261129854, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.035834982385858895, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03583026365377009, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03582804090343416, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0358290592674166, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03582955666817725, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03583450354635716, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03584337556734681, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03585279052145779, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03586368191987276, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03588385419920087, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03590322060510516, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.035930115589872004, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03595989991910756, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03599043761380017, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036029963111504915, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03607827280648053, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03613145011477172, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03618746055290103, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03626499842852354, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036356165129691365, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03647522184997797, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03661455565132201, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03677220210433006, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03696088175289333, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03712993983179331, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03729741979390383, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03756044492125511, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03796784500591457, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.038411783119663596, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.038856424679979684, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03949982878752053, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.040102815302088854, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04089119739830494, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04178615184500813, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04267318906262517, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.043663461413234475, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04500655485317111, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04679044894874096, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.048242144528776405, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.049531726213172075, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.05114486822858453, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05276916306465864, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0551205151155591, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0584644259698689, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.060877417232841256, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.062485011853277685, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06449424140155316, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.13873291015625, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.137769937515259, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1364340782165527, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1353070735931396, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1343860626220703, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1333110332489014, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.132319450378418, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1314592361450195, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.130546808242798, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1297707557678223, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1291322708129883, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1283247470855713, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.12770938873291, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1268327236175537, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.126255989074707, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1256802082061768, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1252169609069824, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.124843120574951, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1245782375335693, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1244332790374756, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1244611740112305, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124368667602539, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124224901199341, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.123933792114258, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1235458850860596, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1230432987213135, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.122330904006958, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.121547222137451, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1199333667755127, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.118764877319336, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1199052333831787, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1226773262023926, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1258225440979004, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.127274751663208, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.128403663635254, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1324329376220703, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1450605392456055, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1589114665985107, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1809229850769043, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.2341713905334473, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.2760329246520996, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.3239657878875732, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.365776538848877, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.3876094818115234, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.388793468475342, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.4314539432525635, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.508514642715454, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.6383705139160156, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.7057323455810547, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.05998523440383906, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05998523440383906, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.059800664451827246, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06090808416389812, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.073827980804725, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08231819859726837, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08324104835732743, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08084163898117387, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08047249907715023, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0754891103728313, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0725359911406423, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06939830195644149, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07032115171650055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07641196013289037, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07493540051679587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07198228128460686, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06847545219638243, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06921373200442968, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.022034919716463472, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.021768936330619517, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02153297288595148, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021232562146953623, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021493373592648374, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021526753533912507, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02197173558635451, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.021947721560537318, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022249590248143682, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.021665023342621676, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.021581281178618576, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.021511025623106955, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022278269383666813, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02322412306107126, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.024050177327208568, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.024166213883609927, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.025338694435760107, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.026639049657084076, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.02607909796826499, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02626063448028891, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.027139162658150126, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.027745027635764277, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02879283162007355, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.029479470230832455, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.029817094232403012, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03272832953702179, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.031891717346027006, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.032006211349599065, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03305331924194548, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.034108389978531224, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.036278449793706834, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03808098424795368, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04029689522165347, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.040376341544763654, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.04593666136905655, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04888995594929301, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.046978935973707024, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04189361519514609, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0422873643679422, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.042158077275772476, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03945790239730389, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.038652335859726716, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03474547555833148, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.037056625779724524, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.041397811569655836, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.036449290935844016, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03452902077320264, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.035568302850094435, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03217705052032744, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 3.0641802978515624, "validation/loss_best": 3.1258225440979004, "validation/acc_best": 0.08379475821336287, "validation/f1_best": 0.04029689522165347} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 3.1146719896793367, "train/grad": 0.29062572561204436, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.140428466796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.139210205078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.137174072265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13566650390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13419189453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.132547607421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130777587890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12919921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12737060546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125638427734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124056396484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12209716796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12017822265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.117598876953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.115458984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11341796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.110858154296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1080419921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1050439453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.10233642578125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0989984130859374, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0958416748046873, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0922149658203124, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.088385009765625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0845257568359377, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0798040771484376, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.075721435546875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0722412109375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0678472900390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0629010009765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0584710693359374, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0549298095703126, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0510986328125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.04882080078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.047584228515625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0485638427734374, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0525494384765626, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.058976135253906, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0677166748046876, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.080181884765625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0912786865234376, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1043817138671876, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1247265625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1457627868652343, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.175883941650391, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.216047821044922, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.2507865905761717, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.303260955810547, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.348135452270508, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036018501585349444, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03601121984422207, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.036004753485322, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03599935855716467, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03599812936969102, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03599933481775224, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03599955125711858, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03600392240099609, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.036011017002165316, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0360190983582288, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03602910700254142, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03604858878999948, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03606452105566859, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03608829831704497, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03611640823073685, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03614413790404797, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03618269649334252, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03623888386413455, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0363094085175544, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036380185829475525, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03647771958261728, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036588078159838916, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03672709456644952, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03688767410814762, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03706644603982568, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03728520818054676, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.037490202840417625, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03767802231945097, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03793400900438428, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.038224268704652786, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03846761464141309, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.038699162108823654, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.039112001610919836, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.039597396347671746, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.040309322392567994, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04120176839642227, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.042370024640113114, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04353765496052801, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04471887350082397, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.046200052332133056, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.047414715643972156, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.048613400720059874, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04998436454683542, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.051302971169352535, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.053387456238269806, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.056022037882357836, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05790771393105388, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.060613843202590945, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06322158973664045, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1376514434814453, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1366732120513916, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1352641582489014, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.134167194366455, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1333279609680176, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1322898864746094, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.131417751312256, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.130716562271118, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1299667358398438, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1294238567352295, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.12896466255188, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1284852027893066, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.128121852874756, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.127807855606079, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1275634765625, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.127440929412842, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1274492740631104, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.127498149871826, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1275229454040527, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.127687692642212, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.127720355987549, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.12762713432312, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1274585723876953, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1271469593048096, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1268138885498047, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1267826557159424, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1271328926086426, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.127955675125122, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.130208969116211, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.136368989944458, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1460907459259033, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.156541347503662, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.168260335922241, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1733579635620117, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.168635606765747, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.154849052429199, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1437509059906006, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1455776691436768, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1660959720611572, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1894659996032715, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1882376670837402, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.19354248046875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.211846351623535, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.241791009902954, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.3069822788238525, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.380732536315918, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.3682286739349365, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.3708930015563965, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.471144676208496, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06016980435585087, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0754891103728313, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07733480989294943, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07715023994093761, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08102620893318568, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0858250276854928, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08619416758951642, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08305647840531562, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08010335917312661, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08065706902916205, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07936507936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07825765965300849, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0753045404208195, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06662975267626431, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06275378368401624, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06662975267626431, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06939830195644149, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0636766334440753, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02203162780623051, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0223307917980094, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021942052621644333, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021664137458735123, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021901622258034784, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021723503703993022, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02336921407535232, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0225029599476244, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021946243722752574, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02144094349390166, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02116221024596145, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.020717451953553463, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.019139239166287004, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.018892610374942814, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01792820725642953, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.018347447990186803, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017210165699831317, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.017256293029603263, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.016649939608916125, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.016661345523571094, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.017855799262486056, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.019984835965029205, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.020970599638077857, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.025246341770378832, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02610893618671095, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.028322283444675318, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.028521136853994784, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.028293859068988375, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.030298234104569086, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03116307134078943, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03197918774653178, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03135021266860242, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.029811873640174427, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0309695716366122, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03355867711132094, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04030615330527263, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.045710233012973216, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04990795084702651, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.047941694053783644, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04528487787988986, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.048478481191713246, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04979965859460298, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04950991396164791, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05091049913491772, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04750844421842811, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04451903218770898, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04747714450739448, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.046559277841212075, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03721817241088682, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 3.0525494384765626, "validation/loss_best": 3.1437509059906006, "validation/acc_best": 0.08619416758951642, "validation/f1_best": 0.045710233012973216} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 3.102758512496948, "train/grad": 0.28820125833153726, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.140206298828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1388525390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.136806640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.135101318359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.133531494140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13177001953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130079345703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128316650390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126422119140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1245263671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1230078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.120614013671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.118638916015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11592529296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.113480224609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.111065673828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1083251953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.105081787109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1015283203125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0982861328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0943408203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.090496826171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0863909912109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0819927978515627, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.077706298828125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0728936767578126, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0688555908203123, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.065355224609375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0610400390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0565936279296877, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0528546142578126, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0497955322265624, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0463775634765624, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0440631103515625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.041800537109375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0405673217773437, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0411947631835936, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.04349853515625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.046939697265625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0523748779296875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0609170532226564, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0717031860351565, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0888186645507814, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1071832275390623, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1307022094726564, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.162450866699219, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1996028137207033, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.2528131103515623, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.304280548095703, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03633351962082088, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.036327119600027796, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.036319909561425445, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0363134712073952, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03631137629039585, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03630875127390027, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03631345628760755, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03631985836662352, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03632760046981275, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03634059801697731, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03635052828118205, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03636986979283392, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03638862749561667, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03641301244497299, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03643912988714874, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03646198921836913, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03649542549625039, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03653120344504714, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03657652349211275, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03662265282124281, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03668500939384103, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036762576354667544, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036861314848065374, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03698002907447517, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03712520458735526, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03732430486939847, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03752363158389926, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.037727660425007345, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03804328779689967, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03847191009670496, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.038890031008049844, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.039294267566874624, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03987485614605248, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.04041622753255069, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04101433515548706, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04161728922277689, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.042386223394423723, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.043170753512531516, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04382722050882876, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04454097562469542, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04549525594338775, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0465858874283731, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.048117346893996, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.049782208036631345, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.05156455820426345, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.053271843213588, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.055596758741885424, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05876155953854322, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.061118277441710236, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.136845350265503, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.135840892791748, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.134408712387085, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.133307695388794, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1323800086975098, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.131312131881714, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1303234100341797, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1293773651123047, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1283810138702393, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1274874210357666, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.12673282623291, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125764846801758, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1249406337738037, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1239545345306396, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1232171058654785, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122573137283325, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122016191482544, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1214487552642822, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1209142208099365, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.120429039001465, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.119817018508911, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.119210958480835, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1185097694396973, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.117783784866333, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.117006540298462, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.115884780883789, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1147332191467285, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1135451793670654, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1125566959381104, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1125235557556152, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1138622760772705, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.116795301437378, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1231558322906494, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1301560401916504, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.135744094848633, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1363139152526855, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1340317726135254, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.132568120956421, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1366608142852783, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.158482789993286, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1875836849212646, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2155563831329346, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2367279529571533, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.261934757232666, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.3185431957244873, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.39036226272583, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.393197536468506, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.4203829765319824, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.477780342102051, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.058693244739756366, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0592469545957918, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05758582502768549, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.058693244739756366, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.057770394979697305, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.058693244739756366, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06090808416389812, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.067921742340347, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.073827980804725, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08102620893318568, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08139534883720931, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07788851974898486, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07862679955703211, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08231819859726837, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08176448874123293, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08194905869324474, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0799187892211148, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07678110003691399, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07456626061277224, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06496862310815799, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.05813953488372093, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.057770394979697305, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.054078995939461055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06164636397194537, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02148435459507204, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022166715299432534, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0221515369389496, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.022590461574630714, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0221137645658589, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02261478960412294, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022076434248956316, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02244429771858134, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.021839913652281284, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.022170344937536945, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02283696573277333, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.024077729052887912, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02484818216869621, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.024427448525135814, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02366683121021872, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02383463206952964, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.024042762697638175, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.023979571713144767, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.024329340288648055, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.025517072167397098, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02544692934547736, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.026545455418101133, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02821413928986223, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.028759029028765915, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.029274555316939243, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0316165820988546, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03276098569272135, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03451352533031592, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03652313928403411, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.035343574889782806, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03452083073624663, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.032014714877682614, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.032519454232273926, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03477002106051475, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03636919520751247, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04354746663080644, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.048278378156781855, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05051216027874361, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05358379943207861, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.054616740619337745, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0538317448041821, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.050398077053049016, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.046205202952655976, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0482909904313182, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04346586275769259, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.040222037416141304, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03787958086854377, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03359703397861114, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0362007155700202, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 3.0610400390625, "validation/loss_best": 3.1125566959381104, "validation/acc_best": 0.08397932816537468, "validation/f1_best": 0.03652313928403411} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 3.0882013916969298, "train/grad": 0.2833305376768112, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.140927734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13967529296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.137529296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1357470703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.134200439453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.132386474609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130672607421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128870849609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1268896484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124967041015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123280029296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.120919189453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.118634033203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.115645751953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.112891845703125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.110477294921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1072412109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.10365478515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.09971923828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0960400390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.091612548828125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.087044677734375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.082066650390625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0769757080078124, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.071708984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0655499267578126, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0606146240234375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0562646484375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.05085693359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.045230712890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.040931396484375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0373291015625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0326849365234376, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0289788818359376, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.025384521484375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.02284423828125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0215704345703127, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0209722900390625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0211920166015624, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0253421020507814, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.03224853515625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0405682373046874, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.055971374511719, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0713485717773437, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0829290771484374, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1044522094726563, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1330142211914063, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1737608337402343, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.222053680419922, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03650305769406259, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03649607778526843, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0364870104752481, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03648445169441402, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03648240739479661, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03648436085321009, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03648992708884179, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.036496940422803166, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03650848277844489, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03651959149166942, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03653197973035276, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.036550805708393454, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036569658666849136, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036594699081033466, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03662205109372735, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03664672293700278, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03667757258750498, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03671171460300684, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03675149854272604, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03678920637816191, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03684010057710111, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03689221547916532, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036960481936112045, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0370449731964618, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.037142174560576675, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03728318707086146, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.037442931123077866, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.037615619506686925, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.037900792881846425, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.038291856152936815, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03865350244566798, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.038962229788303375, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.039348064996302126, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03969854075461626, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.04018231918103993, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.04073152084834874, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.04136610347777605, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04197668100707233, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04269121764227748, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.043832531925290824, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.044899121122434736, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04593576782383025, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04749193319119513, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.048572734352201226, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.048865405451506375, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.049999782610684634, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05185550117865205, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05434287955984473, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.057053248211741445, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1361210346221924, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.13511061668396, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.133758306503296, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.132642984390259, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.131767749786377, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1307268142700195, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1298410892486572, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1290462017059326, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1281845569610596, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1274142265319824, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1267924308776855, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125950574874878, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.125260353088379, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1242904663085938, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1234138011932373, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122586488723755, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.121565341949463, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.120457410812378, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.11917781829834, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.117961883544922, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.116384267807007, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.114715337753296, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.112886428833008, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.110905885696411, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.109137535095215, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1075336933135986, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.10654616355896, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1059272289276123, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1051957607269287, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.104097366333008, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1033217906951904, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.103287696838379, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1057798862457275, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.110713243484497, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.118806838989258, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1246676445007324, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.126596212387085, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1295111179351807, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1400763988494873, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.169912815093994, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.2000720500946045, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.2193562984466553, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.2393991947174072, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.2645246982574463, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.2921969890594482, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.3177855014801025, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.3576576709747314, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.4153192043304443, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.467965841293335, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05998523440383906, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05813953488372093, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07862679955703211, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07954964931709117, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08028792912513842, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08194905869324474, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08305647840531562, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08047249907715023, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07770394979697305, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07641196013289037, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07770394979697305, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07456626061277224, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07659653008490218, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07622739018087855, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07401255075673681, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07087486157253599, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06552233296419344, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.05998523440383906, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.021526826615265674, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.021494250046268478, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.022856953181030305, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.022247971820441123, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.022196331341862455, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021779387026383153, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021640106548877325, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022433503872204216, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02234592026967241, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02217090189950446, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023468096160912444, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.023907449214792115, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.023689663290894437, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02401232016365244, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.024592921715279686, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.025052204825046064, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02659835833401344, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.027222988059343797, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.028466278671070943, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.029644771879120874, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.030950708787596672, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.031056387291562872, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.032452106783559594, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.032967909000957446, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03409119013635653, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03403308569458233, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03403973379739993, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.034893359113945484, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.035390509135288066, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.035525920198388, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03802936985044725, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03923580621963157, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.039397583950434543, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.039050401991508006, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.039744250047934006, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.039130725974386306, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04169925305438831, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.041912967694790526, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.041987824365349626, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03929654160065754, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.033384692985666216, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.034306165177012266, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03410794597982652, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03534811213594045, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03799769662557279, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04199141966385663, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04264954770228268, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04176674451106965, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03567018783141937, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 3.0289788818359376, "validation/loss_best": 3.110713243484497, "validation/acc_best": 0.08305647840531562, "validation/f1_best": 0.039050401991508006} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 3.0755209386348725, "train/grad": 0.27755893856287, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1432666015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.141746826171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13943603515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.137569580078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1358154296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.133756103515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13172119140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1297314453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127457275390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125262451171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1231689453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.120291748046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11786376953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.114373779296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11120361328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.10824462890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.104697265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.100721435546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.096258544921875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.092230224609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.087398681640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0824786376953126, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0770697021484374, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.07132080078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0653350830078123, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.058348388671875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.052078857421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.04653076171875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.03959716796875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0316888427734376, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.02539794921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.020284423828125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.01438232421875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.009925537109375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0056561279296874, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.00234375, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.999369812011719, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9976797485351563, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9979061889648437, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.000850830078125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.00422119140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0091644287109376, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0198300170898436, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0321258544921874, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.047464599609375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.069444580078125, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0945535278320313, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1307603454589845, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1725039672851563, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03608556541614234, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03607788417488336, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03606913832016289, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03606476775370538, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03606296692043543, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0360608225595206, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03606211624108255, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.036063503501936794, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.036070513473823666, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.036074037421494724, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0360819436237216, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03609326835721731, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03610769931226969, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0361228780914098, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.036140740886330604, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036160463243722914, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0361896041687578, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03622388195246458, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03627187451347709, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036320866122841834, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03638532685115933, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036456832615658644, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03654587620869279, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.036641442757099865, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03674734679050744, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0368746948055923, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03699698803946376, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03711434368975461, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03728963691741228, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.037521543828770515, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0377562150452286, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.037993416273966435, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.038357051191851496, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03872309076599777, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03920700366608799, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.039738913141191004, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.040359419798478485, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.04098814100958407, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04173901657573879, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04264530778862536, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04322303105145693, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04387747982516885, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04519215732812881, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04655234102159739, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0477773361466825, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.049026445969939235, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.050444069430232046, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05269673177972436, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.055539869051426646, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.135807752609253, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.134859323501587, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.133561849594116, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.132568120956421, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1317684650421143, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1309008598327637, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1301121711730957, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.129420280456543, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1286871433258057, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1280505657196045, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1274571418762207, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.126723527908325, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1260569095611572, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.12512469291687, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1242852210998535, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123448133468628, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122469425201416, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1213107109069824, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1200973987579346, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1189892292022705, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.117649555206299, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.11625599861145, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1146597862243652, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1129961013793945, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1112380027770996, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1093833446502686, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1081857681274414, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1074702739715576, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1071009635925293, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.107783555984497, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1092278957366943, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.111196994781494, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.113893747329712, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1155524253845215, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1169700622558594, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1192140579223633, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.122974157333374, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1243607997894287, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1235740184783936, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1292126178741455, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1413803100585938, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1586239337921143, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1974780559539795, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.2440855503082275, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.289254665374756, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.302882194519043, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.301382541656494, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.307386875152588, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.3360838890075684, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08231819859726837, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08453303802141011, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08545588778146918, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08785529715762273, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08988556662975268, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0902547065337763, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09228497600590624, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09302325581395349, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08988556662975268, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08803986710963455, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08416389811738649, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08305647840531562, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08010335917312661, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08139534883720931, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07825765965300849, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06902916205241787, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0651531930601698, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.022326911183055905, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022425059908950717, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.022653359478549854, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02220378230188001, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.022186109837109544, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.022606936631804478, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02243892079507059, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02248833628267793, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02202963196495665, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02212609324971171, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02188754129715534, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.022285261390040306, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.022740583498003352, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02319974706245596, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02325141152477367, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.024098964146959778, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.025393479778307467, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.026833947860493684, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.02700497220948267, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.028507717674393532, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02885904745319901, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03007355290326755, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.031648313730100616, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03390868990407784, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0354170192604159, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.035193702434696966, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.036891972320129786, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03769841912024032, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.037661792046452744, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03859130159024566, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03797440645815904, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03804521711953426, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03913166513391391, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03874291433271587, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03885572236493062, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03809735357826405, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.0408300292018084, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.042496225919576115, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04603547346702579, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.049489365486843774, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05083084428425557, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05158189278829103, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.047197601735202634, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.041611303494063744, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03646314907476962, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03965066313301045, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.043027813847310914, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.043308890873404025, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04571302230680321, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 3.000850830078125, "validation/loss_best": 3.1292126178741455, "validation/acc_best": 0.09302325581395349, "validation/f1_best": 0.049489365486843774} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 3.061771842241287, "train/grad": 0.2718770236521959, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.138785400390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1372607421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13509765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.133289794921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13166748046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12966064453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127703857421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12582763671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123441162109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.119146728515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116248779296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11373779296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.110103759765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.106951904296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.10386962890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.100283203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0960791015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.091591796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.087418212890625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.082569580078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.077489013671875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0719140625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.065968017578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.059942626953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0526837158203124, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0463104248046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0406475830078126, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.033154296875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.024677734375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0175970458984374, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0115679931640624, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0040130615234375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.997919921875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.991446533203125, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9864056396484373, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9820184326171875, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9790243530273437, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.97719482421875, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9780767822265624, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9812142944335935, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.985517883300781, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.99346923828125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0020381164550782, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0128619384765627, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.026965789794922, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0417266845703126, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.063946533203125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0891236877441406, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03593313852325082, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03592361549846828, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03591085356660187, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03590342403389513, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03589838840998709, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03589489433914423, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03589090334251523, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.035891860984265805, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03589190812781453, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.035896671395748855, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03590062713250518, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.035908481692895296, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.035916819144040345, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03593030717223883, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.035945409275591374, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03596011540852487, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03598152005113661, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03601009959354997, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03604455776512623, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036082319682464004, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03612917458638549, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03618152725510299, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036242614416405555, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03631120960228145, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036388360392302276, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.036490659341216085, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03658987086266279, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03668772483244538, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.036836756002157925, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03703190832398832, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.037227684799581766, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03742706588469446, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03772844940423965, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03802043916657567, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.038391847852617504, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03879093364812434, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.039231175519526006, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03968903097324073, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.04030630306340754, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04135682104155421, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.042285660868510606, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.043125416357070206, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04429875887930393, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.045311635602265594, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04614590020850301, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04709752609021962, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04821518225595355, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04969603527337313, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.05106234297156334, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.135554313659668, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1346116065979004, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1333343982696533, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.132326126098633, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.131493091583252, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.130544662475586, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1296651363372803, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.128859281539917, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1279094219207764, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1270179748535156, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1262288093566895, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125162124633789, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124173402786255, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122814416885376, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1216604709625244, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.120633840560913, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1193954944610596, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1179604530334473, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1164846420288086, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1151602268218994, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1136529445648193, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1122260093688965, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1107711791992188, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1095523834228516, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1085033416748047, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1076085567474365, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1072213649749756, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1070473194122314, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1072213649749756, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1077992916107178, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.108234405517578, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1084816455841064, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1084659099578857, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1078732013702393, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.107374906539917, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1077287197113037, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.109306573867798, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1117563247680664, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.116013765335083, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1262083053588867, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1373088359832764, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.149916887283325, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1672098636627197, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1738121509552, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.174734115600586, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.187734365463257, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.2051873207092285, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.2358195781707764, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2431647777557373, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07807308970099668, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0812107788851975, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.082687338501292, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08693244739756367, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08951642672572906, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08840900701365817, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08914728682170543, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0917312661498708, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08988556662975268, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09246954595791805, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09117755629383537, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08693244739756367, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08342561830933924, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08305647840531562, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08084163898117387, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08047249907715023, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08490217792543374, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08748615725359911, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09136212624584718, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09062384643779993, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09376153562200074, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.022197884095058937, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02170857046523979, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021718395594037296, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021472344409370205, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.022041672492288698, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.022073401463694492, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02174637756186672, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02252958519144878, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022977966329545758, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.022129875486581727, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023076316861959874, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02320544826694528, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.023918585209968753, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.024975562421025374, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.024890587502878175, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.025515576679569996, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.025883846675486443, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.026520605038503314, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.028424719148636077, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.029087528331975546, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.031255131399808955, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03279919635851736, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03522035416729576, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03664800257890441, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03831056449839792, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04192377069689616, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04629590803016656, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.046284971073435245, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04956149989991451, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.05084092992106789, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.052243891347624326, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.052772798614734766, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.052029229479745205, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05182990801156356, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.052309380503226, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05247161424174731, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05102812706912322, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05176548548196675, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05173085711351875, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.053382047804654026, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0568762459850784, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.0555908430408601, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05350565834022261, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0522689127613147, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04919842788428417, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.047699009065958274, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04430075313623968, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.042105726755820944, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04626917549224268, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.0891236877441406, "validation/loss_best": 3.2431647777557373, "validation/acc_best": 0.09376153562200074, "validation/f1_best": 0.04626917549224268} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 3.0556656980514525, "train/grad": 0.2675180683284998, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.14063720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.139132080078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.137088623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.135142822265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.133529052734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13149658203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129547119140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127615966796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125384521484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1232177734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.121185302734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1184375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11587646484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.112410888671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.109237060546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.106309814453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1026953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.09843505859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.09380126953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.089639892578125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.084432373046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0791656494140627, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.07321044921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.067061767578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0605426025390625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0529437255859375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0461273193359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0400213623046874, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.031988525390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0226971435546877, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.014932861328125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.008311767578125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.000244140625, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9936962890625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9869317626953125, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.980721435546875, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.974599609375, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9697698974609374, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.965919189453125, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9636285400390623, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9638311767578127, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.96545654296875, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.969687194824219, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9752252197265623, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9836196899414062, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.994163818359375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.005218505859375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0222396850585938, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.040413818359375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036068648295477033, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03606100307777524, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03605197344906628, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03604450561106205, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03603877510875463, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0360361064132303, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03603380410932004, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.036031857300549745, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.036032628398388625, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.036037502130493525, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.036039853859692814, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.036046276427805425, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03605269161053002, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03606432881206274, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0360765612218529, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036088007474318146, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036103464970365165, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03612296524457634, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03614331420511007, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036165409721434116, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.036192308822646735, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03622278390452266, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036262032026425, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03630570196546614, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03636062916368246, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03643248843960464, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03650279051624238, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03657481397502124, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03666943225078285, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03679661351256072, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.036929949214681984, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03706697147339583, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03730170140974223, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03755939061753452, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03790432322770357, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03823563222773373, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03855872704647481, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.038869310142472385, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.039274348299950364, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.039896400906145574, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04043514950200915, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04098581430502236, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04185278506949544, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04271332842297852, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04378614895045757, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04498430280014873, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04591027012094855, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04706981735303998, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.048185576014220716, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.135256290435791, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.13427472114563, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1330034732818604, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.131944417953491, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1311211585998535, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.13018536567688, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1292693614959717, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.128471851348877, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1275038719177246, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1266095638275146, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1258695125579834, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124868154525757, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123995780944824, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122865915298462, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1218907833099365, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1210317611694336, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119948148727417, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.118785858154297, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.117548704147339, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.116374969482422, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1150646209716797, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1137592792510986, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1123404502868652, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1109132766723633, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.109483242034912, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1078286170959473, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.106416940689087, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.105154037475586, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1035027503967285, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.101670980453491, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1003036499023438, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.099470853805542, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.099067211151123, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0992543697357178, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0996522903442383, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1002824306488037, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.101888418197632, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1049258708953857, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1108205318450928, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.120284080505371, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.128281831741333, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1342270374298096, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1396617889404297, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.142245054244995, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1434364318847656, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1524691581726074, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.171583414077759, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.2086422443389893, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2418465614318848, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05998523440383906, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.060723514211886306, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06090808416389812, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07770394979697305, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08028792912513842, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08084163898117387, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08305647840531562, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0858250276854928, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08637873754152824, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08619416758951642, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09136212624584718, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08896271686969362, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09191583610188261, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0932078257659653, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09228497600590624, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09283868586194167, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09136212624584718, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09191583610188261, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08859357696567, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08803986710963455, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08711701734957548, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08637873754152824, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.022053594440724886, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02181690991988984, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.022015704200244, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021589909231307627, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021478072594841715, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.022122533477633845, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022272516410545142, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022898639966912354, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023062122271491844, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02183221510571774, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.022034867085618, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02205700509875556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02386724388729429, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.025028071467303997, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02496808464786021, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.025586667693497652, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.027418303994239324, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.028613516052590948, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.030429242357319475, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.032004433248892336, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.034214370436482656, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03561387538205897, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03618317189343643, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03712184076151781, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03792388195163377, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0380443508574049, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03879881487318739, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.039072773581092374, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04018012434841473, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04056295481180818, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.042050569800345695, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0429665677999895, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.043459001900410445, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.045156642645818014, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.047382684402726805, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05084145357863079, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05162067689209999, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05050169855103686, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05194170380480247, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05267089704290643, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05294107533768502, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05155273995963691, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.051080623849161455, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04949499077483305, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.051238545069275526, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05072209388647575, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.050478028822866595, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04772208685341889, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04718707422962539, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 2.9638311767578127, "validation/loss_best": 3.128281831741333, "validation/acc_best": 0.0932078257659653, "validation/f1_best": 0.05294107533768502} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 3.041487821340561, "train/grad": 0.2631588540226221, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13732666015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13576416015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.133365478515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131456298828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129710693359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127791748046875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125628662109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12366943359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121240234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.118944091796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.116873779296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.113798828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1111083984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.107403564453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.103929443359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1007763671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.09693603515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0923193359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.087423095703125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.082972412109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.07753173828125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0718505859375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.065699462890625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.05907470703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0522900390625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0443603515625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.03732666015625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0310076904296874, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0227520751953123, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0134332275390623, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.005391845703125, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9984869384765624, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.989649658203125, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.982353515625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9741851806640627, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.966669616699219, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9591583251953124, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.952760009765625, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.946561279296875, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.940490417480469, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.937288818359375, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9358160400390627, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.9355340576171876, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9370672607421877, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9408538818359373, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.948430480957031, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9575770568847655, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.969801330566406, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.981065216064453, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.036143006673082706, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03613591330125928, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03612806954421103, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03612197771668434, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03611862384714186, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.036118407119065526, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03611758383922279, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03611794214695692, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03611615211702883, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03611853701062501, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.036119223888963464, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03612191637046635, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03612405116669834, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03612931526266038, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03613502802327275, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.036140694925561545, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03615013607777655, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036160532319918275, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036174319284036756, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03618932326324284, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03621080106124282, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03623120558448136, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03626153281889856, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.036297742407768965, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036336642811074855, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.036394746825098995, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.036454613711684944, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03651439080014825, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.036604278394952415, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03672700804658234, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03683975317515433, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.036948112109676, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.037104095108807085, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03724799140356481, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03743925141170621, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.037647015284746885, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.037898129178211094, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.038167885448783634, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03849139222875238, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03891546499915421, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03923980638384819, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03953837258741259, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0400026342086494, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0404723702929914, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04105027777142823, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04181061641313136, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.042606922583654526, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.043787057381123304, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.044801779724657535, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1351125240325928, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1341469287872314, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.132831335067749, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.131836414337158, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1309924125671387, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.130047082901001, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1291606426239014, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1283295154571533, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.127422571182251, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12656569480896, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1258137226104736, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1248183250427246, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123934745788574, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1228103637695312, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121746301651001, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1207501888275146, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119595527648926, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1182281970977783, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1166937351226807, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1152806282043457, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.113494634628296, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1116836071014404, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1095945835113525, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.107435464859009, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1052119731903076, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1026155948638916, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.100491762161255, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0987448692321777, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0968964099884033, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0953335762023926, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0946104526519775, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0944392681121826, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.094637632369995, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.095290422439575, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0965986251831055, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.098609685897827, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.100935220718384, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1036338806152344, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.106830596923828, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.111724376678467, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.117213726043701, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.124063014984131, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.134636878967285, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1442904472351074, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1582694053649902, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.175483465194702, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1904544830322266, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.210134267807007, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.218545913696289, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.061461794019933555, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07419712070874862, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07954964931709117, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08194905869324474, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0843484680693983, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08527131782945736, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08564045773348099, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08933185677371724, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09117755629383537, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09080841638981174, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09283868586194167, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09007013658176449, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09080841638981174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08748615725359911, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08840900701365817, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08711701734957548, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08822443706164636, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08361018826135105, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0828719084533038, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08084163898117387, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07770394979697305, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07438169066076043, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07438169066076043, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07456626061277224, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02225206212722507, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022396659007813523, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.022144925949951835, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021490947749916892, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02230571942058336, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021851528536156337, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022198486017097504, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022242127867175592, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022504926358985006, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02319419822610405, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023155016363513747, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02432463292817046, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02572113430553082, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.025386771053390166, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02625090488326118, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.026967027388929643, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02781897384623018, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02900574796500296, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.02961822681326759, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03051783858713267, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03175923297953024, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03438422686299208, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03587189982389669, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03730747134459913, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0398051123328495, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.041182650386939974, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.042026490524515264, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.041489780271923335, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.042574956090422965, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04408159921839929, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.046563851735318774, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04900255159436014, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.049994929791267094, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05166315712190233, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.052024120289107495, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04923504700701948, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04952088794543615, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04732753568549469, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.047114808717759867, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.047401598975646636, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.046295452532390424, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.049078305082933205, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04646919850335588, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04712463536972485, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.047057630108494175, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.043821917153718304, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.041864118318389175, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04297209956112028, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.043463079352807556, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 2.9741851806640627, "validation/loss_best": 3.0965986251831055, "validation/acc_best": 0.09283868586194167, "validation/f1_best": 0.052024120289107495} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 3.039902811050415, "train/grad": 0.2597401510924101, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13796142578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.136435546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.134366455078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.132598876953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.131138916015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129278564453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12735595703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1254638671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12319580078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121043701171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.118951416015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116148681640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11353759765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.109959716796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.10669189453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.103641357421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.099864501953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.09557861328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.090802001953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.08645263671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0810931396484373, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.075550537109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.069482421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.06296875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.056219482421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0481512451171877, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.04111083984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0347430419921877, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0261578369140625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0165155029296873, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0080718994140625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.000948486328125, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9915667724609376, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.983763427734375, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.97500244140625, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9669696044921876, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9590142822265624, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9518362426757814, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.944716796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9369964599609375, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.932317810058594, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9289260864257813, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.92592041015625, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9247451782226563, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.925145263671875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9276690673828125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9321279907226563, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.93931640625, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.947725830078125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03626297968439758, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.036253086002543566, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03624258868396282, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03623419717885554, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03622974894940853, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03622332844883203, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03622133774682879, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03621553847566247, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03621200622990727, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03621158942580223, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03621186383999884, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.036210676543414595, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03621378542855382, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.036213533654809, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.036217997148633004, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03622041193768382, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03622396521270275, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03622870242223144, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03623119536787271, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03623532678000629, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.036238485081121326, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.036243667434901, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03624833958223462, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03626074532046914, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03627512629143894, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.036296010129153726, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03632501044310629, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03635084553621709, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.036391114573925736, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.036452221451327205, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.036507554976269604, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03657181737013161, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0366646296530962, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03676404045894742, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03689658181741834, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.037048765253275634, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03722580943256617, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03740183546207845, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.037600144632160666, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03785375609062612, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03809343253262341, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03832989967428148, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03870070255361498, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.039068004712462426, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03956343284808099, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04010368631221354, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0405904551409185, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.041194636542350054, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.041809825040400025, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.135023355484009, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1340761184692383, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.132772207260132, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.131747007369995, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.130924940109253, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.129976272583008, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1291027069091797, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.128284454345703, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.127338171005249, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1264758110046387, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.125729560852051, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1247332096099854, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123837471008301, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122636318206787, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1215012073516846, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1204888820648193, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.11928129196167, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1178295612335205, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.116321325302124, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1149885654449463, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.113424062728882, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.111847162246704, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1102263927459717, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.108505964279175, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1068460941314697, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1049647331237793, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1033523082733154, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1019344329833984, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1002228260040283, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0984227657318115, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.097017765045166, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0959877967834473, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0949935913085938, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.094395875930786, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.094318151473999, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0947301387786865, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.095604658126831, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0968308448791504, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.098384380340576, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1004161834716797, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1026363372802734, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1051137447357178, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.109149217605591, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.112863779067993, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1187028884887695, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.126220226287842, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1336941719055176, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.142207145690918, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1471476554870605, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08157991878922112, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08213362864525656, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08490217792543374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08711701734957548, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08877814691768181, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08951642672572906, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0902547065337763, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08970099667774087, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08988556662975268, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09154669619785899, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09265411590992986, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0917312661498708, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09246954595791805, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.0932078257659653, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09265411590992986, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09117755629383537, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09099298634182355, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08951642672572906, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08988556662975268, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08840900701365817, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08785529715762273, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08767072720561092, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08693244739756367, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0224170978946705, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022161357212466454, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.022214786385318253, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021854724791812916, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021668022136712164, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021852886375651775, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021998216402841622, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022647538576898874, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022815906952984254, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02307780669979907, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.022663640890637802, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02425200814495988, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.025571194056085378, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02542009042037227, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.026498754173918154, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02675098167928819, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.027081283057453664, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02810375585794926, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.02910141078966924, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03175483727680068, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03345012832364508, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03385015987140516, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.035232446696969115, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03625337001438558, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03738315847352805, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.038606048734549654, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03983879427905941, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.041294453195599566, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04215801424018282, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04351789532709923, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.045732300640149465, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.046624810538815335, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.047367677349667514, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04787760130351112, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.048319721758437205, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05039890280137727, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05252262054636428, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05362005509245712, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.055363947817396654, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05649007814364924, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05804132268820553, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05731780586591483, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.058006979856876244, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05730566401226329, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05987025664107809, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05876021011158996, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0595229728813623, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06008119153796677, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05963326838235547, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 2.9369964599609375, "validation/loss_best": 3.1004161834716797, "validation/acc_best": 0.0932078257659653, "validation/f1_best": 0.05649007814364924} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 3.0296094012260437, "train/grad": 0.25937489941716196, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.137913818359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1363232421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.133961181640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.132000732421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13028076171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128172607421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126014404296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123955078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121431884765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11907470703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.116923828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11385009765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11108154296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.107232666015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1038427734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.100596923828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.096663818359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.092099609375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.087054443359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.082537841796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.076861572265625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.071053466796875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.06458740234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.05767578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.05046142578125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0419287109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0342291259765624, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0272869873046875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.018040771484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0074359130859376, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.99834228515625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9904296875, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.980072021484375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.971365966796875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9616033935546877, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.95238037109375, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.943296203613281, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9350631713867186, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.92701171875, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.9181585693359375, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.91229248046875, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.907903747558594, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.90311767578125, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.900137634277344, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8982925415039062, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8975540161132813, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.898428955078125, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.900870666503906, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.903969421386719, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03674793103709817, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03674019321799278, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.03672402393072843, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03671203786507249, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.03670727901160717, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03669707024469972, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03669000442139805, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.036683842958882454, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03667766015976667, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03667279221117496, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03667118485085666, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.036666802521795036, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03666422733105719, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03666181373409927, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03665854005143046, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03665720327757299, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03665782869793475, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036658423133194444, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036655504610389474, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.036655313521623614, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03665764194913208, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03665677985176444, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.036657393649220466, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03665945163927972, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036656293598935005, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03665806200355291, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.036659258948639036, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03665864023379981, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0366617990937084, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03666689107194543, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03667316788807511, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03668738734908402, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03670858906581998, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03673592070117593, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03678154700435698, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03683650641702116, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.036909143626689914, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.036994684459641575, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.037106051705777646, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03728378918021917, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03744362497702241, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.037601204272359606, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.037823788058012724, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03803458353504539, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03828628228046, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03856977920979261, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03885803989134729, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03926716236397624, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.039655576515942814, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.134976863861084, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1340487003326416, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.13275408744812, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1317291259765625, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1308846473693848, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.129957675933838, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.129070520401001, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1282269954681396, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.127361297607422, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.126481533050537, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1257455348968506, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1247477531433105, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123854398727417, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1226236820220947, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121534585952759, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.120499610900879, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119234085083008, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1178267002105713, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.116267442703247, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1148273944854736, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.113102912902832, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1113948822021484, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1095046997070312, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.107534408569336, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1055963039398193, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.103435516357422, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1016921997070312, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.100188970565796, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.098296880722046, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0963690280914307, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0947425365448, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.093578815460205, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.092179298400879, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.091212272644043, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.090445041656494, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0900113582611084, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0897629261016846, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0898876190185547, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.09047532081604, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.091722011566162, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.09297251701355, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.094247579574585, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.09648060798645, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0985586643218994, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1018271446228027, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1059582233428955, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.110142230987549, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.114671230316162, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.117774486541748, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07567368032484312, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07918050941306755, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08619416758951642, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08785529715762273, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.08840900701365817, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09136212624584718, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09117755629383537, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09228497600590624, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09117755629383537, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09136212624584718, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0932078257659653, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09376153562200074, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0932078257659653, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09246954595791805, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09099298634182355, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08748615725359911, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02243614193921892, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02231266739635066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02192895422304728, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021954236107260175, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.022188548035704858, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021618376382700064, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022298835788931454, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022622857704418065, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.022909402450095998, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.022995623601424275, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023145748183850567, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.023959235852610995, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.025394811065003603, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02573443687938769, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02597038694102392, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.025967305881196362, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.027131057585142133, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02851840480688204, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.03056106282851104, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03164938604198913, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.033862925298707935, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.034661256754224774, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03705685790509683, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03811786842374329, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03914360473361389, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03969997029197613, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04138239142623122, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.04245442940855789, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.043612404822364094, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04621050641845508, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04685001804837352, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0481492078507294, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04831108835406931, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0491523456803904, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05218912871716815, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05351575381667412, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05443845953533392, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.055784797091333445, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05522714570707488, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.05677541717861448, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.05760228667491805, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.058749583106900254, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05949880658636695, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.059665904802936966, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05972242639995432, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0589139118907449, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05907856533894565, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0577523495767428, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05629607533323258, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.90311767578125, "validation/loss_best": 3.09648060798645, "validation/acc_best": 0.09376153562200074, "validation/f1_best": 0.05949880658636695} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 3.028341886997223, "train/grad": 0.25193015672266483, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.137679443359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1361962890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13383056640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1320263671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130274658203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128411865234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126409912109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12435302734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1220947265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11981201171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.117742919921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.114808349609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1120849609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.10837158203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.104871826171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.101708984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.097791748046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.09319091796875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.088189697265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.08367919921875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0780279541015627, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.07233154296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.06591064453125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.059136962890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0519793701171873, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.043560791015625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0360308837890626, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0293475341796876, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.02017578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.009652099609375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0005712890625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9925921630859373, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9821905517578124, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.973238525390625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9630706787109373, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.953502197265625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.943746337890625, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9349551391601563, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9259219360351563, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.915749206542969, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9086837768554688, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.903072509765625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.896578674316406, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.892056579589844, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8879971313476562, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8849087524414063, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.883611145019531, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.8829910278320314, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.8836355590820313, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03596039718016982, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.035952218575403094, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.035938974833115936, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.03592948201112449, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.035925226686522364, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03591866662725806, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.03591302005574107, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03590554566122592, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03590222494676709, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.03589803531765938, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.03589484411291778, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.035891733085736635, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.03588815455324948, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03588300539180636, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.03588043224066496, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03587661510333419, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.03587261379696429, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.03586866524070501, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.03586446825414896, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.035861194636672734, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.03585826038382947, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03585652162320912, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03585405995137989, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.035851800069212916, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.03585126206278801, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03584913741797209, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03584965264424682, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03584813546389341, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.035846826629713176, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03584719612263143, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.035852095149457454, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03585745410993695, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03586613170802593, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03587598676793277, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03588702918030322, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0359045693743974, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03592444856651127, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.035950242318212984, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03597349795512855, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0360230765491724, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.036067748824134466, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03611391756683588, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03617929204367101, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03624755926430225, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03634034098125994, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03645550510846078, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.036568320645019414, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03670896304771304, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03683867562562227, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1349551677703857, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.134002447128296, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.132716655731201, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1316885948181152, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1308481693267822, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1299312114715576, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1290359497070312, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.128178834915161, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.127300977706909, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1264238357543945, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1256532669067383, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124628782272339, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123687505722046, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1224777698516846, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121309280395508, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1202778816223145, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1189756393432617, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1174557209014893, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1158692836761475, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.114330291748047, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.112539768218994, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1106648445129395, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1086506843566895, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1065127849578857, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.104393482208252, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1019160747528076, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0998106002807617, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0980336666107178, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0958163738250732, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.093506336212158, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.091787099838257, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0904624462127686, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.08899188041687, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0880794525146484, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0874435901641846, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0872528553009033, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.087337017059326, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.087867259979248, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0888800621032715, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.090679407119751, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.092527151107788, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0944528579711914, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0968570709228516, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0988214015960693, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.101052761077881, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1029038429260254, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1035852432250977, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1037938594818115, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1033029556274414, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07807308970099668, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08065706902916205, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08176448874123293, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08453303802141011, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08453303802141011, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08527131782945736, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08840900701365817, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.08896271686969362, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09117755629383537, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09099298634182355, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09228497600590624, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09283868586194167, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09505352528608342, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09634551495016612, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09523809523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09634551495016612, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09708379475821337, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09579180509413067, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09745293466223699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09819121447028424, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09985234403839055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09929863418235511, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09966777408637874, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09929863418235511, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09892949427833149, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09856035437430787, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02243104911380302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022449807404259618, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021827231384407387, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021944859966999967, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.022468440061799117, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02160944483325071, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.022229763397752626, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02248287374144467, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023047975213045486, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02313697339478465, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023087621182293145, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02426329220306198, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02533825067987663, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.025795247898906786, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02616029661657515, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.025888122128468843, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.027277289291689377, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.028652458277811488, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.030035359071424596, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03191758481498671, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.034168286023729885, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.035347938797233185, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03667324747386139, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.038729613404626544, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03985321457710928, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04264915655915406, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04285497478145283, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.04291867288458049, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04587577186118435, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.046759636586911624, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.04932281775262193, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04985506687912519, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0508858103140793, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05154582703097626, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.054164074508236716, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05707663734354546, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.057795884229443484, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05865368848988808, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0609610279164555, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06129729808169543, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06042440212810086, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.062232306954568495, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06257883025390894, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06452619678823363, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0645501443486761, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06458584749380508, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06440323525324008, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.064358440790321, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06390485983943706, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.892056579589844, "validation/loss_best": 3.0988214015960693, "validation/acc_best": 0.09985234403839055, "validation/f1_best": 0.06452619678823363} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 3.0292702746391296, "train/grad": 0.25380806781351567, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.141055908203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.139500732421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13737060546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13556884765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.133974609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.132015380859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130186767578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128194580078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125872802734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12362548828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.121639404296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.118714599609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.115933837890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.112264404296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.108861083984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.105682373046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.101783447265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.09729736328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.09222900390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.08772705078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.08211669921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.076348876953125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.069952392578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0630963134765623, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0558740234375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0472479248046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0395916748046874, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.032674560546875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.023394775390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0125714111328126, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.003056640625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.994833984375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.983988037109375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.97469970703125, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9641510009765626, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9540179443359373, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.943772277832031, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9342446899414063, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9246792602539062, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.913511047363281, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9055853271484375, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.8992303466796874, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.891651611328125, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.8858633422851563, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8805218505859376, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.875696105957031, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.8728338623046876, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.8703268432617186, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.869216003417969, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.03646938563324511, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.03646180476062, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.036447797399014235, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.036438887296244504, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.036431626081466675, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.03642424889840186, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.036417229017242786, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.03641024818643927, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.03640348847955465, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.036397522306069734, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.036392211802303794, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.03638297804631293, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.036375532811507585, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.03636797032319009, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0363586803060025, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.03635021581314504, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.036340990457683804, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.036330644628033044, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.036318575972691176, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.03630890848115086, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.036300940914079545, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.03629033443517983, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.03627914078533649, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.03626489760354161, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.036253699576482175, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03623783624731004, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.036225412096828224, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.036218493226915595, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03620430956594646, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03619193561375141, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.036180745987221596, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.036172020994126794, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.036159009588882324, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0361480225995183, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03614026923663914, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03612978087738156, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.036119858296588064, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03611236638389528, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03610261010937393, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.036087257331237195, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03608484635129571, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03608085040003061, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.036082436935976146, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.036079553905874494, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03609163263812661, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.036097304280847314, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03610919630154967, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03613266211934388, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.036155070308595896, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1349432468414307, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1340017318725586, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.132702112197876, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.131687879562378, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1308326721191406, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1299116611480713, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.129023790359497, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1281702518463135, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1272847652435303, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.126406192779541, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.125620126724243, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124600648880005, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123659610748291, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1224355697631836, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121258497238159, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1201953887939453, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.118896484375, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.117382049560547, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.115750551223755, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.114206314086914, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.112351179122925, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.110524892807007, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1084609031677246, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.106293201446533, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.104154109954834, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1016087532043457, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.099493980407715, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.097686529159546, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0953783988952637, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.092998743057251, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.091148614883423, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0896987915039062, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0880863666534424, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.086984395980835, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.08603835105896, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.085444688796997, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0851333141326904, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0852222442626953, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.085604429244995, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.086566209793091, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0874392986297607, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.088386297225952, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0897200107574463, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.091085195541382, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.092397451400757, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.093862771987915, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.09483003616333, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.095515727996826, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0960066318511963, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0753045404208195, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07807308970099668, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08194905869324474, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0858250276854928, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08674787744555186, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08859357696567, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09062384643779993, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.09302325581395349, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.09357696566998892, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09449981543004798, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.09597637504614248, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09542266519010704, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09523809523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09616094499815431, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09782207456626062, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09653008490217793, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09819121447028424, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0991140642303433, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09819121447028424, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09819121447028424, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09819121447028424, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0976375046142488, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09579180509413067, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09634551495016612, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02242881994621784, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022441983098318657, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021776034860743972, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.021928722373115283, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02201143802237898, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021868417931423464, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021882775281114732, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022594375590634524, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023086244087060993, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.023123261833567554, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.023106684060263255, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.024137649956400522, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.025249812272299662, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0251654830213984, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.026211898905049852, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02580957061269008, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02757050879767539, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.029164100722628844, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.030441681504788116, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03248983988477575, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03476183909905329, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03542083615063906, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03644854382380779, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03883641994486957, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04057594466339732, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04240696764720834, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04377332678824819, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.044355016335201496, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.045700934344465705, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0478911118289236, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.05065160295442922, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0506912987823826, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.051377527900948385, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.052829602992628344, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05512601190518083, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.05727245247212107, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.058753180005678286, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.059798670013992604, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.060440740926437364, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.0627442635648639, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06227379312611647, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06368555568830093, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06544945249719547, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06504507098345295, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06571771035697407, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06619344814000049, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.06626335614921508, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.06488821632998891, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.06551197920505274, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.891651611328125, "validation/loss_best": 3.0897200107574463, "validation/acc_best": 0.0991140642303433, "validation/f1_best": 0.06544945249719547} diff --git a/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/config.yaml b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..24de1ab9e42d2eeefbb8af8cda17b4a5da8e5266 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..c6cedfa931fca89c033e48fde30d6620e731c88a --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,train,0.8167259786476868,0.015010712857408954,0.7970471812887641,0.017475004133794485,0.7866092299472384,0.017422679135215936 +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,test,0.62,0.03990414013608112,0.5386109762020399,0.049260935441646704,0.5478335478335479,0.04253909601080385 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,train,0.7580071174377224,0.01589057674218355,0.7204470973782771,0.01991948851343222,0.7112770284735603,0.01839826129386761 +flat_mae,patch,logistic,ppmi_dx,1,0.005994842503189409,test,0.66,0.04351608438267395,0.6026180458158018,0.05348800420035311,0.6035653650254669,0.0477754169644722 +flat_mae,patch,logistic,ppmi_dx,2,0.005994842503189409,train,0.7313167259786477,0.01566997951500847,0.6862482669377946,0.02004857663549945,0.680033718689788,0.018046528651283807 +flat_mae,patch,logistic,ppmi_dx,2,0.005994842503189409,test,0.68,0.04127054155205622,0.6323529411764706,0.05020928766836231,0.6298811544991512,0.046045348457448676 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,train,0.7384341637010676,0.01578775197094075,0.6955142026293385,0.020223977673097197,0.6884232498394348,0.018335447699326216 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,test,0.63,0.041220863649370575,0.5636277862955537,0.051867540337308476,0.5691850594227504,0.04517756018602569 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,train,0.7473309608540926,0.01681338372295706,0.7035380477584439,0.021588571977838387,0.6956486833654464,0.01941223289577233 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,test,0.66,0.04456191647584291,0.6212121212121212,0.04968895579944259,0.6188455008488964,0.047120091797266166 +flat_mae,patch,logistic,ppmi_dx,5,0.046415888336127774,train,0.8185053380782918,0.01625627255355278,0.8006953619358876,0.0184567328065184,0.791720188396489,0.01838282515557353 +flat_mae,patch,logistic,ppmi_dx,5,0.046415888336127774,test,0.65,0.044350760985579496,0.6178622120318812,0.04913234805992817,0.615874363327674,0.047545420042052325 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,train,0.7455516014234875,0.015880780426049224,0.7064995489721313,0.02004173635022068,0.6985522372083066,0.018495962612513347 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,test,0.64,0.04379440603547444,0.5792426367461431,0.05450481665304654,0.5823429541595926,0.04798877377186772 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,train,0.7384341637010676,0.0160786442959635,0.6991861925828827,0.01976834582702206,0.6919021622778848,0.018273005084083697 +flat_mae,patch,logistic,ppmi_dx,7,0.005994842503189409,test,0.6,0.0467744545665687,0.5755517826825127,0.04992052189576302,0.5755517826825127,0.04998428196306503 +flat_mae,patch,logistic,ppmi_dx,8,0.005994842503189409,train,0.7384341637010676,0.015930032090909166,0.6935898434457513,0.020480195040902333,0.6866837936202098,0.018398441728572152 +flat_mae,patch,logistic,ppmi_dx,8,0.005994842503189409,test,0.67,0.04009337102315044,0.6239316239316239,0.04716111682626796,0.6218166383701189,0.04337524365732208 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,train,0.7544483985765125,0.015589029206071355,0.7137098560354375,0.0200892892467773,0.7049079426247057,0.018360676444630974 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,test,0.72,0.03803793369782329,0.6666666666666667,0.0502818283119577,0.6621392190152802,0.044171427933047375 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,train,0.7313167259786477,0.017139440287495533,0.6832124472250946,0.021977401365153054,0.6774245343609505,0.019557936438005182 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,test,0.71,0.03967457120121149,0.6640018537828757,0.048583211883612316,0.6591680814940577,0.04415224280363166 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,train,0.8042704626334519,0.015547511209147637,0.7818969531900481,0.018261391051853582,0.7714622136587455,0.01803060969176929 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,test,0.67,0.04498655354658766,0.6296711929076422,0.05201982146977735,0.6269100169779287,0.04879030120868502 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,train,0.8149466192170819,0.015428380212166654,0.7953272075302555,0.01781647300243942,0.7853511025476343,0.017829764838571526 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,test,0.64,0.039113394125286555,0.5714285714285714,0.04863305855020712,0.5772495755517827,0.04235885246199127 +flat_mae,patch,logistic,ppmi_dx,13,0.005994842503189409,train,0.7366548042704626,0.016990790428494277,0.6929641934293097,0.021308626702586396,0.68610843502462,0.0193079219330032 +flat_mae,patch,logistic,ppmi_dx,13,0.005994842503189409,test,0.67,0.040240651088172014,0.6176572818908586,0.049134900855981246,0.616723259762309,0.04400799319339476 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,train,0.7491103202846975,0.016009489213798054,0.7079421943587532,0.02024660696043915,0.6997029543994862,0.018527223399880395 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,test,0.66,0.03803397954461246,0.5783730158730158,0.053457628358837085,0.5882852292020373,0.04310708474937606 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,train,0.7313167259786477,0.015282026786418972,0.6811077917441708,0.020257545383509296,0.6756850781417255,0.01780958504489245 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,test,0.7,0.04060139899067518,0.66078697421981,0.048891224639434454,0.6561969439728353,0.04568817696058325 +flat_mae,patch,logistic,ppmi_dx,16,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,16,1291.5496650148827,test,0.62,0.046701481775207096,0.6006725514922235,0.0483212366169874,0.6018675721561969,0.048812763629875106 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,train,0.8220640569395018,0.015461026006893953,0.8036749807866974,0.01787019589739811,0.7937406336972811,0.017964510769757757 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,test,0.58,0.04223967329419109,0.5174632352941176,0.047753999177591426,0.5237691001697793,0.043651854987671955 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,train,0.7544483985765125,0.015097886892700054,0.7137098560354375,0.019312511974032942,0.7049079426247057,0.017581679975317885 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,test,0.59,0.044603546944161285,0.5249681381068243,0.051248332593987395,0.5318336162988115,0.0462666725317313 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,train,0.9092526690391459,0.012114939045581913,0.903156813520609,0.01300560291366805,0.8993390066366945,0.013441650456100861 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,test,0.62,0.04810260284017903,0.6100164203612479,0.04867103642129283,0.6171477079796265,0.04983891001570774 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,train,0.7366548042704626,0.01649204891640287,0.6889965749839219,0.021406688794120537,0.68262952258617,0.01902567982521728 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,test,0.66,0.03843683129499621,0.5952380952380952,0.04999959043331171,0.5984719864176571,0.042835900702690444 +flat_mae,patch,logistic,ppmi_dx,21,0.005994842503189409,train,0.7437722419928826,0.016556847617353907,0.6993625273043375,0.021295866192441264,0.6918887818454292,0.019166933657024446 +flat_mae,patch,logistic,ppmi_dx,21,0.005994842503189409,test,0.7,0.03962815160968273,0.6493688639551192,0.050336163564792896,0.6460101867572157,0.04506881317652539 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,train,0.8167259786476868,0.01530089332054114,0.7970471812887641,0.017636551490553768,0.7867961892528367,0.017606882182963666 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,test,0.63,0.045663372630588735,0.5906626839252129,0.050152792386993626,0.5895585738539898,0.04808722834542306 +flat_mae,patch,logistic,ppmi_dx,23,0.005994842503189409,train,0.7491103202846975,0.015331963259886684,0.70973094745325,0.019156795502265515,0.7014424106187112,0.01758166872193179 +flat_mae,patch,logistic,ppmi_dx,23,0.005994842503189409,test,0.67,0.045875483648676656,0.6296711929076422,0.05375044665802366,0.6269100169779287,0.050451958505389326 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,train,0.7508896797153025,0.01521356725139801,0.7086443891456333,0.019578109623457154,0.700278312995076,0.01775973402923886 +flat_mae,patch,logistic,ppmi_dx,24,0.005994842503189409,test,0.64,0.04265056154378275,0.5714285714285714,0.0533558552268493,0.5772495755517827,0.04625832482992758 +flat_mae,patch,logistic,ppmi_dx,25,0.005994842503189409,train,0.7473309608540926,0.016013394995769505,0.7044821661334282,0.020540649389893747,0.6965184114750589,0.018604973977878504 +flat_mae,patch,logistic,ppmi_dx,25,0.005994842503189409,test,0.69,0.03846423793603611,0.627359057579036,0.05157446144813842,0.6277589134125636,0.04400182805702498 +flat_mae,patch,logistic,ppmi_dx,26,0.3593813663804626,train,0.9199288256227758,0.011345826971548489,0.914218554435094,0.012364121838294136,0.9088792549775209,0.013240087144651238 +flat_mae,patch,logistic,ppmi_dx,26,0.3593813663804626,test,0.57,0.050336225523970296,0.5501621508525996,0.05113078301735352,0.551358234295416,0.051528495584043585 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,train,0.7206405693950177,0.01669393879852833,0.6626560379270134,0.02275207809523602,0.6600567330336116,0.01943991864404982 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,test,0.65,0.03938821651204837,0.5706048337627285,0.05343300219223018,0.580220713073005,0.04411414299087545 +flat_mae,patch,logistic,ppmi_dx,28,0.046415888336127774,train,0.8149466192170819,0.013982117188354634,0.7953272075302555,0.016184903336507572,0.7853511025476343,0.01615048858465593 +flat_mae,patch,logistic,ppmi_dx,28,0.046415888336127774,test,0.69,0.040464675953231104,0.6467236467236468,0.0483475483466815,0.6430390492359932,0.04461013925169826 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,train,0.797153024911032,0.015975219773542514,0.7756471313312416,0.01844561210999804,0.7665515949475488,0.018183500416036988 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,test,0.64,0.044397459386771226,0.5989304812834224,0.05075168320996248,0.597623089983022,0.04785729767237496 +flat_mae,patch,logistic,ppmi_dx,30,0.005994842503189409,train,0.7295373665480427,0.01637490994055702,0.683671051072402,0.02045181869390619,0.6777189038749732,0.018431282464556883 +flat_mae,patch,logistic,ppmi_dx,30,0.005994842503189409,test,0.71,0.03419999415204628,0.6277756385573097,0.05399901708505434,0.6337011884550086,0.04143297574966433 +flat_mae,patch,logistic,ppmi_dx,31,0.046415888336127774,train,0.8149466192170819,0.015515735085150917,0.7972582972582972,0.017688100605174874,0.7888300149860843,0.017805699456089563 +flat_mae,patch,logistic,ppmi_dx,31,0.046415888336127774,test,0.64,0.04836881640065219,0.609375,0.05143805076340605,0.6078098471986417,0.050193191013174515 +flat_mae,patch,logistic,ppmi_dx,32,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,32,1291.5496650148827,test,0.59,0.04722323157091221,0.5710848415106182,0.04918003504938041,0.5725806451612903,0.04990330326497817 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,train,0.905693950177936,0.011837587105674946,0.8993590415018093,0.012773363320067057,0.8955791051166774,0.013377924385898935 +flat_mae,patch,logistic,ppmi_dx,33,0.3593813663804626,test,0.64,0.04563325103474439,0.6216897856242118,0.047684013984501006,0.6230899830220713,0.048240541885276336 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,train,0.8202846975088968,0.01550396990819932,0.7994863697219543,0.018072749636268218,0.7879469064440163,0.01785281225651754 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,test,0.64,0.04700503802785399,0.6043956043956044,0.052401693075633096,0.6027164685908319,0.050360989978081014 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,train,0.7402135231316725,0.01659937852860378,0.6961577201090177,0.021450370630881604,0.6889986084350246,0.01937669102360199 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,test,0.65,0.046106186135918895,0.6178622120318812,0.05058459272144312,0.615874363327674,0.04919154286318017 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,train,0.7259786476868327,0.016046507220949073,0.6824858757062147,0.020107458084891658,0.6765681866837936,0.01827003430223143 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,test,0.65,0.038,0.5706048337627285,0.05111362213711494,0.580220713073005,0.04216550963915673 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,train,0.7900355871886121,0.016351948772073643,0.765435766836446,0.019095076501678947,0.7555528794690645,0.018550084004820867 +flat_mae,patch,logistic,ppmi_dx,37,0.046415888336127774,test,0.63,0.04354190625133448,0.5960257670051315,0.04884268996584415,0.5946519524617997,0.047436959986519756 +flat_mae,patch,logistic,ppmi_dx,38,0.005994842503189409,train,0.7437722419928826,0.015731628981239153,0.7003199431212228,0.020339212600454862,0.6927585099550417,0.018453149949312957 +flat_mae,patch,logistic,ppmi_dx,38,0.005994842503189409,test,0.64,0.04456586586166592,0.5989304812834224,0.05130434850559296,0.597623089983022,0.04865022888800847 +flat_mae,patch,logistic,ppmi_dx,39,0.005994842503189409,train,0.7224199288256228,0.01612600732851334,0.6753466050479915,0.021048003037161533,0.670199100834939,0.018847069809842933 +flat_mae,patch,logistic,ppmi_dx,39,0.005994842503189409,test,0.75,0.03834790215904908,0.7103464256748928,0.04819102622466781,0.7016129032258065,0.04412215109458873 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,train,0.7419928825622776,0.01601268636245947,0.6958000321035676,0.0207253837962585,0.688704238921002,0.01854070391536122 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,test,0.7,0.041854887408760276,0.6493688639551192,0.05228315287751872,0.6460101867572157,0.04691954014230938 +flat_mae,patch,logistic,ppmi_dx,41,0.005994842503189409,train,0.7348754448398577,0.01676337909814911,0.6884225409759819,0.021649725423449933,0.6820541639905802,0.019364211985124252 +flat_mae,patch,logistic,ppmi_dx,41,0.005994842503189409,test,0.72,0.04161120522167076,0.6923076923076923,0.0470971605290822,0.6876061120543294,0.04578174321899416 +flat_mae,patch,logistic,ppmi_dx,42,0.005994842503189409,train,0.7366548042704626,0.014756360249206409,0.6879651860744298,0.01965050242435871,0.6817597944765574,0.017333888615422594 +flat_mae,patch,logistic,ppmi_dx,42,0.005994842503189409,test,0.68,0.037831119465329056,0.6114618746964546,0.050545403309114945,0.6146010186757216,0.042817880543508574 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7437722419928826,0.016109396579254393,0.7012624584717608,0.020495573331026112,0.6936282380646542,0.018636651212327583 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.67,0.04024005964210291,0.6108031607500884,0.05030351873782526,0.6116298811544991,0.0441540627377756 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.7402135231316725,0.015754476935826375,0.694200954084675,0.020552599792455484,0.6872591522157996,0.01840003927510977 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.71,0.03841039442650908,0.6514004087029691,0.05247320498416896,0.648981324278438,0.04495865472293448 +flat_mae,patch,logistic,ppmi_dx,45,0.005994842503189409,train,0.7188612099644128,0.016423590103125527,0.6657632834966951,0.02158083457318492,0.6620905587668594,0.018882267178420523 +flat_mae,patch,logistic,ppmi_dx,45,0.005994842503189409,test,0.74,0.03439611024520071,0.6775793650793651,0.05092965523700596,0.6731748726655349,0.04231291097348486 +flat_mae,patch,logistic,ppmi_dx,46,0.005994842503189409,train,0.7348754448398577,0.015678367599901363,0.6884225409759819,0.01994080615459162,0.6820541639905802,0.01786043212406471 +flat_mae,patch,logistic,ppmi_dx,46,0.005994842503189409,test,0.69,0.03764195000262339,0.627359057579036,0.05023544100428511,0.6277589134125636,0.04273356438510761 +flat_mae,patch,logistic,ppmi_dx,47,0.005994842503189409,train,0.7348754448398577,0.017035775271106706,0.6884225409759819,0.021811996196403532,0.6820541639905802,0.01952369177917132 +flat_mae,patch,logistic,ppmi_dx,47,0.005994842503189409,test,0.7,0.04180248317983035,0.6553308823529411,0.051215962966782186,0.6511035653650254,0.04701481021632671 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,train,0.7455516014234875,0.01620001530681481,0.6990071272607424,0.021393161617809735,0.6915944123314065,0.019066218983346366 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,test,0.71,0.041232996495525275,0.6791680495630048,0.04744638521889345,0.6744482173174873,0.04569114086713613 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,train,0.7384341637010676,0.01612712287256335,0.6905877462050989,0.02105007725759309,0.6840746092913723,0.01867119829419848 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,test,0.69,0.03435282230035837,0.6112852664576802,0.05069974920152426,0.6175721561969439,0.04013433477190354 +flat_mae,patch,logistic,ppmi_dx,50,0.005994842503189409,train,0.7348754448398577,0.015539609128974527,0.6884225409759819,0.01977748577935632,0.6820541639905802,0.017776557877857136 +flat_mae,patch,logistic,ppmi_dx,50,0.005994842503189409,test,0.71,0.03996686627695496,0.6579785352046232,0.0511354072651013,0.6540747028862479,0.04540507316019319 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,train,0.8149466192170819,0.015258895111269264,0.7948242694862182,0.01777249562737583,0.7844813744380219,0.017662438980334077 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,test,0.58,0.048007578568388554,0.5320855614973261,0.0524687768469741,0.533955857385399,0.049758115567197815 +flat_mae,patch,logistic,ppmi_dx,52,0.046415888336127774,train,0.8096085409252669,0.0159604771892005,0.7886438324868636,0.018319217032146902,0.7784066581031899,0.018014037453588632 +flat_mae,patch,logistic,ppmi_dx,52,0.046415888336127774,test,0.68,0.04473219869400563,0.6483516483516483,0.0499623517524493,0.6451612903225806,0.048424320296354906 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,train,0.806049822064057,0.015338061365184574,0.7841530921096677,0.017662816903366796,0.7737770284735603,0.017330338835752905 +flat_mae,patch,logistic,ppmi_dx,53,0.046415888336127774,test,0.64,0.0423869980064642,0.5989304812834224,0.04734312478331106,0.597623089983022,0.04496308391750575 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,train,0.7544483985765125,0.015901513528459768,0.717184240850679,0.019631571798810886,0.7083868550631557,0.018143487612850315 +flat_mae,patch,logistic,ppmi_dx,54,0.005994842503189409,test,0.51,0.047789249837175724,0.47147017581706396,0.04847143272001594,0.4724108658743633,0.04779593704249449 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,train,0.7402135231316725,0.01607932048651823,0.6961577201090177,0.020961459437839544,0.6889986084350246,0.018878262833371115 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,test,0.68,0.041821889005639136,0.6323529411764706,0.050506613585562896,0.6298811544991512,0.04593436039350052 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,train,0.7419928825622776,0.016082771096605795,0.702394647559154,0.02012009548267066,0.6947923356882895,0.0185055666728181 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,test,0.63,0.046073311146476115,0.5783475783475784,0.053622312186681266,0.5793718166383701,0.04931958785912151 +flat_mae,patch,logistic,ppmi_dx,57,0.005994842503189409,train,0.7366548042704626,0.01511138803025753,0.6889965749839219,0.01992079960243914,0.68262952258617,0.017664004430876325 +flat_mae,patch,logistic,ppmi_dx,57,0.005994842503189409,test,0.7,0.040437131451179865,0.6493688639551192,0.04975013747301422,0.6460101867572157,0.04493805697953351 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,train,0.7437722419928826,0.015374691461085895,0.6963985594237695,0.02096732965811559,0.6892795975165917,0.0185085464008619 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,test,0.68,0.039671773340751976,0.6190476190476191,0.05134648671558357,0.6196943972835314,0.044758912349953855 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,train,0.9199288256227758,0.011167575054124605,0.914550129577008,0.01203415884550803,0.9106187111967459,0.012669745445013847 +flat_mae,patch,logistic,ppmi_dx,59,0.3593813663804626,test,0.61,0.047603272996717357,0.5741893219783819,0.05262681232778399,0.5734295415959253,0.050652788397655926 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,train,0.8185053380782918,0.014787213003760595,0.8006953619358876,0.01680150607790527,0.791720188396489,0.016858018513302077 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,test,0.7,0.041989765419682926,0.6553308823529411,0.051258493422226076,0.6511035653650254,0.0472019946272192 +flat_mae,patch,logistic,ppmi_dx,61,0.005994842503189409,train,0.7455516014234875,0.016163265036405052,0.6990071272607424,0.02133917341336202,0.6915944123314065,0.019048637011202543 +flat_mae,patch,logistic,ppmi_dx,61,0.005994842503189409,test,0.69,0.037915506062823415,0.627359057579036,0.05030744225484978,0.6277589134125636,0.043072153812826336 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,train,0.7455516014234875,0.01606332373523237,0.7047137193520059,0.020462199629717463,0.6968127809890816,0.018745434069611037 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,test,0.65,0.03821518022985107,0.5706048337627285,0.051407063340034795,0.580220713073005,0.04234868317624393 +flat_mae,patch,logistic,ppmi_dx,63,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,63,1291.5496650148827,test,0.53,0.04774515682244639,0.5037482842360892,0.04956166085790679,0.5038200339558574,0.049642538818819595 +flat_mae,patch,logistic,ppmi_dx,64,0.005994842503189409,train,0.7580071174377224,0.01580346670542012,0.717858988556663,0.020179010540260264,0.7086678441447227,0.018460260708589766 +flat_mae,patch,logistic,ppmi_dx,64,0.005994842503189409,test,0.63,0.040774869711625084,0.5636277862955537,0.050110981027884506,0.5691850594227504,0.044202296820841085 +flat_mae,patch,logistic,ppmi_dx,65,0.005994842503189409,train,0.7544483985765125,0.016090719291710628,0.7154743561523222,0.020465109587367896,0.7066473988439306,0.018825032766688017 +flat_mae,patch,logistic,ppmi_dx,65,0.005994842503189409,test,0.61,0.040205253388083506,0.5400400990682863,0.04944841665066762,0.547962648556876,0.04304905872093102 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,train,0.7455516014234875,0.01739524894861295,0.7073716023085186,0.021413499942497232,0.699421965317919,0.019803769969608472 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,test,0.58,0.04418091895830144,0.5091164095371669,0.05134770593071911,0.5186757215619694,0.04590784484916845 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,train,0.8202846975088968,0.01562759837692627,0.8019490375187978,0.01803641007742213,0.7922955469920787,0.018160305299723116 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,test,0.58,0.047192524831799365,0.5495495495495495,0.0501552282367562,0.5492359932088284,0.04959944626737635 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,train,0.7491103202846975,0.01637814439843518,0.7079421943587532,0.02096795676133002,0.6997029543994862,0.019181267710190526 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,test,0.71,0.04182131513953142,0.6640018537828757,0.05171246465112901,0.6591680814940577,0.04706924191849381 +flat_mae,patch,logistic,ppmi_dx,69,0.005994842503189409,train,0.7330960854092526,0.01618321444840631,0.6878332740846071,0.02072215025613819,0.6814788053949904,0.01866923922941869 +flat_mae,patch,logistic,ppmi_dx,69,0.005994842503189409,test,0.7,0.040016051779254776,0.6428571428571428,0.051733262398035086,0.6409168081494058,0.045419007331508575 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,train,0.7455516014234875,0.015191576853465224,0.7019275347805607,0.019602272763062725,0.694203596660244,0.01765920761814776 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,test,0.65,0.04739098648477366,0.612789025334661,0.05268014541966053,0.6107809847198642,0.05052340763647285 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,train,0.7491103202846975,0.016312797720221782,0.7079421943587532,0.020799350623769322,0.6997029543994862,0.018969655964671244 +flat_mae,patch,logistic,ppmi_dx,71,0.005994842503189409,test,0.65,0.03989724301251905,0.5706048337627285,0.05261641183359767,0.580220713073005,0.04362207458448587 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,train,0.7402135231316725,0.01632190450932316,0.694200954084675,0.021070207079979746,0.6872591522157996,0.018860621627603297 +flat_mae,patch,logistic,ppmi_dx,72,0.005994842503189409,test,0.62,0.04596681846723787,0.5824175824175825,0.05061672234844486,0.5814940577249575,0.04857194533730602 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,train,0.7508896797153025,0.016219893752160996,0.7113507960965588,0.02067533174408423,0.7028874973239134,0.018974758501499 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,test,0.67,0.041870103892873246,0.6239316239316239,0.049309776834903334,0.6218166383701189,0.045556411954456005 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7526690391459074,0.016183060672891676,0.7129734754540478,0.02018028058468308,0.7043325840291158,0.018556526555680512 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.62,0.04368360790960381,0.5703301673450927,0.04982647239073261,0.5713073005093379,0.04646484427791653 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,train,0.7562277580071174,0.015072297831718972,0.716227522178363,0.019177816586797704,0.7072227574395205,0.017562169999746954 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,test,0.68,0.04235081581268534,0.6323529411764706,0.05125800637873745,0.6298811544991512,0.0469134938142789 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,train,0.7366548042704626,0.01592203231629497,0.6919954970968124,0.020357953595881675,0.6852387069150075,0.018316677336337475 +flat_mae,patch,logistic,ppmi_dx,76,0.005994842503189409,test,0.7,0.044583741431154025,0.6703296703296704,0.050529996500963174,0.666383701188455,0.048890246871667646 +flat_mae,patch,logistic,ppmi_dx,77,0.005994842503189409,train,0.7526690391459074,0.015348045658672961,0.7111821794990295,0.01976823521952802,0.7025931278098908,0.017969794934000548 +flat_mae,patch,logistic,ppmi_dx,77,0.005994842503189409,test,0.67,0.039395309365456176,0.6108031607500884,0.05078984413320575,0.6116298811544991,0.04446861630658278 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,train,0.8149466192170819,0.01531085222211784,0.7967874278561992,0.017417034031605372,0.7879602868764719,0.017419594851367362 +flat_mae,patch,logistic,ppmi_dx,78,0.046415888336127774,test,0.63,0.04049914073162541,0.5460679671205987,0.05160558201838709,0.5589983022071308,0.04346168935748628 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,train,0.7348754448398577,0.015783586548573737,0.6842684724699211,0.02102211378658196,0.6785752515521302,0.018467322097430423 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,test,0.69,0.04134800599787128,0.6343908479773559,0.0510852549729224,0.6328522920203735,0.04544262562258599 +flat_mae,patch,logistic,ppmi_dx,80,0.005994842503189409,train,0.7313167259786477,0.016234023186530513,0.6821683651494552,0.021097057522624623,0.676554806251338,0.018644639105542763 +flat_mae,patch,logistic,ppmi_dx,80,0.005994842503189409,test,0.7,0.041468498887709926,0.6493688639551192,0.052122437365062134,0.6460101867572157,0.046710387051826945 +flat_mae,patch,logistic,ppmi_dx,81,0.005994842503189409,train,0.7295373665480427,0.015044995266697229,0.6826604454879117,0.019511646533123664,0.6768491757653607,0.017453478518872512 +flat_mae,patch,logistic,ppmi_dx,81,0.005994842503189409,test,0.7,0.041298348635266276,0.6703296703296704,0.04535754969972444,0.666383701188455,0.04387130345553744 +flat_mae,patch,logistic,ppmi_dx,82,0.005994842503189409,train,0.7419928825622776,0.015894610545529826,0.6987152232184121,0.020429686886801485,0.6913134232498395,0.018513860812833714 +flat_mae,patch,logistic,ppmi_dx,82,0.005994842503189409,test,0.62,0.03690989569207695,0.5386109762020399,0.04754938235935523,0.5509337860780985,0.03986957128031496 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,train,0.7526690391459074,0.016004181897989453,0.7163914131054339,0.019641561985458553,0.7078114964675658,0.0183162048020705 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,test,0.55,0.0469122201563729,0.5021573182874212,0.05036032287367769,0.5046689303904923,0.04825502616775756 +flat_mae,patch,logistic,ppmi_dx,84,0.005994842503189409,train,0.7544483985765125,0.016541731854449807,0.7196500867553499,0.020350858935387756,0.7109960393919932,0.019068536577727856 +flat_mae,patch,logistic,ppmi_dx,84,0.005994842503189409,test,0.62,0.043822637985406594,0.5558672276764843,0.053148710282979426,0.5611205432937181,0.047403203748304146 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,train,0.7526690391459074,0.0148848388495869,0.7111821794990295,0.01912947876852764,0.7025931278098908,0.017340611919874807 +flat_mae,patch,logistic,ppmi_dx,85,0.005994842503189409,test,0.64,0.03792940811560339,0.5714285714285714,0.04801656681772023,0.5772495755517827,0.04159579882867716 +flat_mae,patch,logistic,ppmi_dx,86,0.005994842503189409,train,0.7473309608540926,0.015908218075506225,0.7072272360407954,0.0200903354416129,0.6991275958038964,0.018401043515721013 +flat_mae,patch,logistic,ppmi_dx,86,0.005994842503189409,test,0.61,0.039817563963658056,0.5311936530833032,0.05104009001399678,0.5428692699490663,0.04291518162119365 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,train,0.7508896797153025,0.015862999203626296,0.7086443891456333,0.020772822269353126,0.700278312995076,0.0187878207944138 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,test,0.64,0.04846248445963125,0.6043956043956044,0.054164786931007534,0.6027164685908319,0.05198778121718141 +flat_mae,patch,logistic,ppmi_dx,88,0.005994842503189409,train,0.7330960854092526,0.01600064904143236,0.6897815591144607,0.0202867767461595,0.6832182616142154,0.01842678489888598 +flat_mae,patch,logistic,ppmi_dx,88,0.005994842503189409,test,0.67,0.0375621671366283,0.6033177064551027,0.049650947248438736,0.6065365025466893,0.04214251989434343 +flat_mae,patch,logistic,ppmi_dx,89,0.005994842503189409,train,0.7259786476868327,0.015532187773481428,0.6805167958656331,0.019610704089668307,0.6748287304645686,0.017696560320393254 +flat_mae,patch,logistic,ppmi_dx,89,0.005994842503189409,test,0.76,0.035323074611364184,0.7085964060223409,0.049815082889859946,0.6994906621392191,0.0433154382331668 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,train,0.7330960854092526,0.015065732378267083,0.6878332740846071,0.01892907281168485,0.6814788053949904,0.017044145705716638 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,test,0.65,0.03843341775070232,0.5792763553311696,0.05039459623667844,0.5853140916808149,0.042606268936664166 +flat_mae,patch,logistic,ppmi_dx,91,0.005994842503189409,train,0.7508896797153025,0.015555786223275647,0.7077135682125504,0.02021486999922255,0.6994085848854634,0.018223123716934776 +flat_mae,patch,logistic,ppmi_dx,91,0.005994842503189409,test,0.67,0.039021717030392186,0.6108031607500884,0.049618995488409263,0.6116298811544991,0.043589888781884426 +flat_mae,patch,logistic,ppmi_dx,92,0.000774263682681127,train,0.6868327402135231,0.01444481267844738,0.5981604563108374,0.022055524062960796,0.6108568828944552,0.016904358236122914 +flat_mae,patch,logistic,ppmi_dx,92,0.000774263682681127,test,0.67,0.03675902066160087,0.5862068965517242,0.051877573806358476,0.5963497453310695,0.041784655658815055 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,train,0.7473309608540926,0.015265028628324564,0.7044821661334282,0.01958414136742985,0.6965184114750589,0.01774565659949393 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,test,0.6,0.04509763186687301,0.5659722222222222,0.048933770795471156,0.565365025466893,0.04761857360200256 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,train,0.7384341637010676,0.016885575742409027,0.6973790728767926,0.021350597239446233,0.6901627060586598,0.019518899630962618 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,test,0.69,0.03996476448072726,0.6408295678368672,0.04908374172008467,0.6379456706281834,0.04442053606841127 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,train,0.7473309608540926,0.01600498111443429,0.7081138810861423,0.02021111914834729,0.6999973239135089,0.01864287951999549 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,test,0.62,0.03790376762275751,0.5386109762020399,0.048389724214338146,0.5509337860780985,0.0407576426736104 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,train,0.7473309608540926,0.016504637905838216,0.706326542628356,0.021128702896215684,0.6982578676942839,0.019334032570504162 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,test,0.57,0.041887468293034844,0.5017958521608157,0.0482793981806282,0.5106112054329371,0.04353005157478247 +flat_mae,patch,logistic,ppmi_dx,97,0.005994842503189409,train,0.7384341637010676,0.01598795788017825,0.6945595711248729,0.02026807066602962,0.6875535217298223,0.018351653444131148 +flat_mae,patch,logistic,ppmi_dx,97,0.005994842503189409,test,0.68,0.04126505058763408,0.6259934548854604,0.050821378958185934,0.6247877758913413,0.04531790359503978 +flat_mae,patch,logistic,ppmi_dx,98,0.005994842503189409,train,0.7491103202846975,0.01518217035299792,0.7022264810326363,0.020227265135687233,0.6944845857418112,0.017902383565353695 +flat_mae,patch,logistic,ppmi_dx,98,0.005994842503189409,test,0.65,0.03886003602674604,0.5706048337627285,0.050860824346020156,0.580220713073005,0.042321753467052296 +flat_mae,patch,logistic,ppmi_dx,99,0.005994842503189409,train,0.7491103202846975,0.015913140375980975,0.7032168177885643,0.020920279105449413,0.6953543138514237,0.01871263533528873 +flat_mae,patch,logistic,ppmi_dx,99,0.005994842503189409,test,0.68,0.03874930192919608,0.6259934548854604,0.04875472331549811,0.6247877758913413,0.043446136997064067 +flat_mae,patch,logistic,ppmi_dx,100,0.005994842503189409,train,0.7473309608540926,0.015512742480480794,0.7016048219440332,0.020486314874953563,0.6939092271462214,0.018336073839254403 +flat_mae,patch,logistic,ppmi_dx,100,0.005994842503189409,test,0.65,0.04068218283229158,0.5944849959448499,0.050381577807762215,0.5955008488964346,0.04506405900895245 diff --git a/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/log.txt b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..065b5027251de671c30f69032414f29a6cce8b0e --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:57:17 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:19:55 time: 5.1511 data: 4.0234 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:39 time: 0.2362 data: 0.0884 max mem: 3005 +extract (train) [ 40/232] eta: 0:01:03 time: 0.1834 data: 0.0601 max mem: 3005 +extract (train) [ 60/232] eta: 0:00:49 time: 0.1950 data: 0.0687 max mem: 3005 +extract (train) [ 80/232] eta: 0:00:39 time: 0.1766 data: 0.0582 max mem: 3005 +extract (train) [100/232] eta: 0:00:31 time: 0.1710 data: 0.0571 max mem: 3005 +extract (train) [120/232] eta: 0:00:25 time: 0.1669 data: 0.0536 max mem: 3005 +extract (train) [140/232] eta: 0:00:20 time: 0.1829 data: 0.0622 max mem: 3005 +extract (train) [160/232] eta: 0:00:15 time: 0.1624 data: 0.0513 max mem: 3005 +extract (train) [180/232] eta: 0:00:10 time: 0.1627 data: 0.0517 max mem: 3005 +extract (train) [200/232] eta: 0:00:06 time: 0.1845 data: 0.0617 max mem: 3005 +extract (train) [220/232] eta: 0:00:02 time: 0.1596 data: 0.0502 max mem: 3005 +extract (train) [231/232] eta: 0:00:00 time: 0.1556 data: 0.0487 max mem: 3005 +extract (train) Total time: 0:00:46 (0.2020 s / it) +extract (validation) [ 0/50] eta: 0:02:50 time: 3.4117 data: 3.2507 max mem: 3005 +extract (validation) [20/50] eta: 0:00:10 time: 0.2098 data: 0.0768 max mem: 3005 +extract (validation) [40/50] eta: 0:00:02 time: 0.1451 data: 0.0409 max mem: 3005 +extract (validation) [49/50] eta: 0:00:00 time: 0.1478 data: 0.0446 max mem: 3005 +extract (validation) Total time: 0:00:12 (0.2434 s / it) +extract (test) [ 0/50] eta: 0:03:06 time: 3.7350 data: 3.5107 max mem: 3005 +extract (test) [20/50] eta: 0:00:11 time: 0.2063 data: 0.0744 max mem: 3005 +extract (test) [40/50] eta: 0:00:02 time: 0.1493 data: 0.0430 max mem: 3005 +extract (test) [49/50] eta: 0:00:00 time: 0.1511 data: 0.0442 max mem: 3005 +extract (test) Total time: 0:00:12 (0.2516 s / it) +feature extraction time: 0:01:11 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | train | 0.81673 | 0.015011 | 0.79705 | 0.017475 | 0.78661 | 0.017423 | +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | test | 0.62 | 0.039904 | 0.53861 | 0.049261 | 0.54783 | 0.042539 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04351608438267395, "f1": 0.6026180458158018, "f1_std": 0.05348800420035311, "bacc": 0.6035653650254669, "bacc_std": 0.0477754169644722} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04127054155205622, "f1": 0.6323529411764706, "f1_std": 0.05020928766836231, "bacc": 0.6298811544991512, "bacc_std": 0.046045348457448676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.041220863649370575, "f1": 0.5636277862955537, "f1_std": 0.051867540337308476, "bacc": 0.5691850594227504, "bacc_std": 0.04517756018602569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04456191647584291, "f1": 0.6212121212121212, "f1_std": 0.04968895579944259, "bacc": 0.6188455008488964, "bacc_std": 0.047120091797266166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.044350760985579496, "f1": 0.6178622120318812, "f1_std": 0.04913234805992817, "bacc": 0.615874363327674, "bacc_std": 0.047545420042052325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04379440603547444, "f1": 0.5792426367461431, "f1_std": 0.05450481665304654, "bacc": 0.5823429541595926, "bacc_std": 0.04798877377186772} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0467744545665687, "f1": 0.5755517826825127, "f1_std": 0.04992052189576302, "bacc": 0.5755517826825127, "bacc_std": 0.04998428196306503} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04009337102315044, "f1": 0.6239316239316239, "f1_std": 0.04716111682626796, "bacc": 0.6218166383701189, "bacc_std": 0.04337524365732208} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.03803793369782329, "f1": 0.6666666666666667, "f1_std": 0.0502818283119577, "bacc": 0.6621392190152802, "bacc_std": 0.044171427933047375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03967457120121149, "f1": 0.6640018537828757, "f1_std": 0.048583211883612316, "bacc": 0.6591680814940577, "bacc_std": 0.04415224280363166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04498655354658766, "f1": 0.6296711929076422, "f1_std": 0.05201982146977735, "bacc": 0.6269100169779287, "bacc_std": 0.04879030120868502} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.039113394125286555, "f1": 0.5714285714285714, "f1_std": 0.04863305855020712, "bacc": 0.5772495755517827, "bacc_std": 0.04235885246199127} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.040240651088172014, "f1": 0.6176572818908586, "f1_std": 0.049134900855981246, "bacc": 0.616723259762309, "bacc_std": 0.04400799319339476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03803397954461246, "f1": 0.5783730158730158, "f1_std": 0.053457628358837085, "bacc": 0.5882852292020373, "bacc_std": 0.04310708474937606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04060139899067518, "f1": 0.66078697421981, "f1_std": 0.048891224639434454, "bacc": 0.6561969439728353, "bacc_std": 0.04568817696058325} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 1291.5496650148827, "split": "test", "acc": 0.62, "acc_std": 0.046701481775207096, "f1": 0.6006725514922235, "f1_std": 0.0483212366169874, "bacc": 0.6018675721561969, "bacc_std": 0.048812763629875106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04223967329419109, "f1": 0.5174632352941176, "f1_std": 0.047753999177591426, "bacc": 0.5237691001697793, "bacc_std": 0.043651854987671955} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.044603546944161285, "f1": 0.5249681381068243, "f1_std": 0.051248332593987395, "bacc": 0.5318336162988115, "bacc_std": 0.0462666725317313} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04810260284017903, "f1": 0.6100164203612479, "f1_std": 0.04867103642129283, "bacc": 0.6171477079796265, "bacc_std": 0.04983891001570774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03843683129499621, "f1": 0.5952380952380952, "f1_std": 0.04999959043331171, "bacc": 0.5984719864176571, "bacc_std": 0.042835900702690444} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.03962815160968273, "f1": 0.6493688639551192, "f1_std": 0.050336163564792896, "bacc": 0.6460101867572157, "bacc_std": 0.04506881317652539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.045663372630588735, "f1": 0.5906626839252129, "f1_std": 0.050152792386993626, "bacc": 0.5895585738539898, "bacc_std": 0.04808722834542306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.045875483648676656, "f1": 0.6296711929076422, "f1_std": 0.05375044665802366, "bacc": 0.6269100169779287, "bacc_std": 0.050451958505389326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04265056154378275, "f1": 0.5714285714285714, "f1_std": 0.0533558552268493, "bacc": 0.5772495755517827, "bacc_std": 0.04625832482992758} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03846423793603611, "f1": 0.627359057579036, "f1_std": 0.05157446144813842, "bacc": 0.6277589134125636, "bacc_std": 0.04400182805702498} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.050336225523970296, "f1": 0.5501621508525996, "f1_std": 0.05113078301735352, "bacc": 0.551358234295416, "bacc_std": 0.051528495584043585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.03938821651204837, "f1": 0.5706048337627285, "f1_std": 0.05343300219223018, "bacc": 0.580220713073005, "bacc_std": 0.04411414299087545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.040464675953231104, "f1": 0.6467236467236468, "f1_std": 0.0483475483466815, "bacc": 0.6430390492359932, "bacc_std": 0.04461013925169826} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.044397459386771226, "f1": 0.5989304812834224, "f1_std": 0.05075168320996248, "bacc": 0.597623089983022, "bacc_std": 0.04785729767237496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03419999415204628, "f1": 0.6277756385573097, "f1_std": 0.05399901708505434, "bacc": 0.6337011884550086, "bacc_std": 0.04143297574966433} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04836881640065219, "f1": 0.609375, "f1_std": 0.05143805076340605, "bacc": 0.6078098471986417, "bacc_std": 0.050193191013174515} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 1291.5496650148827, "split": "test", "acc": 0.59, "acc_std": 0.04722323157091221, "f1": 0.5710848415106182, "f1_std": 0.04918003504938041, "bacc": 0.5725806451612903, "bacc_std": 0.04990330326497817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04563325103474439, "f1": 0.6216897856242118, "f1_std": 0.047684013984501006, "bacc": 0.6230899830220713, "bacc_std": 0.048240541885276336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04700503802785399, "f1": 0.6043956043956044, "f1_std": 0.052401693075633096, "bacc": 0.6027164685908319, "bacc_std": 0.050360989978081014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.046106186135918895, "f1": 0.6178622120318812, "f1_std": 0.05058459272144312, "bacc": 0.615874363327674, "bacc_std": 0.04919154286318017} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.038, "f1": 0.5706048337627285, "f1_std": 0.05111362213711494, "bacc": 0.580220713073005, "bacc_std": 0.04216550963915673} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04354190625133448, "f1": 0.5960257670051315, "f1_std": 0.04884268996584415, "bacc": 0.5946519524617997, "bacc_std": 0.047436959986519756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04456586586166592, "f1": 0.5989304812834224, "f1_std": 0.05130434850559296, "bacc": 0.597623089983022, "bacc_std": 0.04865022888800847} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.75, "acc_std": 0.03834790215904908, "f1": 0.7103464256748928, "f1_std": 0.04819102622466781, "bacc": 0.7016129032258065, "bacc_std": 0.04412215109458873} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.041854887408760276, "f1": 0.6493688639551192, "f1_std": 0.05228315287751872, "bacc": 0.6460101867572157, "bacc_std": 0.04691954014230938} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.04161120522167076, "f1": 0.6923076923076923, "f1_std": 0.0470971605290822, "bacc": 0.6876061120543294, "bacc_std": 0.04578174321899416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.037831119465329056, "f1": 0.6114618746964546, "f1_std": 0.050545403309114945, "bacc": 0.6146010186757216, "bacc_std": 0.042817880543508574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04024005964210291, "f1": 0.6108031607500884, "f1_std": 0.05030351873782526, "bacc": 0.6116298811544991, "bacc_std": 0.0441540627377756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03841039442650908, "f1": 0.6514004087029691, "f1_std": 0.05247320498416896, "bacc": 0.648981324278438, "bacc_std": 0.04495865472293448} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.74, "acc_std": 0.03439611024520071, "f1": 0.6775793650793651, "f1_std": 0.05092965523700596, "bacc": 0.6731748726655349, "bacc_std": 0.04231291097348486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03764195000262339, "f1": 0.627359057579036, "f1_std": 0.05023544100428511, "bacc": 0.6277589134125636, "bacc_std": 0.04273356438510761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04180248317983035, "f1": 0.6553308823529411, "f1_std": 0.051215962966782186, "bacc": 0.6511035653650254, "bacc_std": 0.04701481021632671} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.041232996495525275, "f1": 0.6791680495630048, "f1_std": 0.04744638521889345, "bacc": 0.6744482173174873, "bacc_std": 0.04569114086713613} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03435282230035837, "f1": 0.6112852664576802, "f1_std": 0.05069974920152426, "bacc": 0.6175721561969439, "bacc_std": 0.04013433477190354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03996686627695496, "f1": 0.6579785352046232, "f1_std": 0.0511354072651013, "bacc": 0.6540747028862479, "bacc_std": 0.04540507316019319} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.048007578568388554, "f1": 0.5320855614973261, "f1_std": 0.0524687768469741, "bacc": 0.533955857385399, "bacc_std": 0.049758115567197815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04473219869400563, "f1": 0.6483516483516483, "f1_std": 0.0499623517524493, "bacc": 0.6451612903225806, "bacc_std": 0.048424320296354906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.0423869980064642, "f1": 0.5989304812834224, "f1_std": 0.04734312478331106, "bacc": 0.597623089983022, "bacc_std": 0.04496308391750575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.51, "acc_std": 0.047789249837175724, "f1": 0.47147017581706396, "f1_std": 0.04847143272001594, "bacc": 0.4724108658743633, "bacc_std": 0.04779593704249449} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.041821889005639136, "f1": 0.6323529411764706, "f1_std": 0.050506613585562896, "bacc": 0.6298811544991512, "bacc_std": 0.04593436039350052} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.046073311146476115, "f1": 0.5783475783475784, "f1_std": 0.053622312186681266, "bacc": 0.5793718166383701, "bacc_std": 0.04931958785912151} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.040437131451179865, "f1": 0.6493688639551192, "f1_std": 0.04975013747301422, "bacc": 0.6460101867572157, "bacc_std": 0.04493805697953351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.039671773340751976, "f1": 0.6190476190476191, "f1_std": 0.05134648671558357, "bacc": 0.6196943972835314, "bacc_std": 0.044758912349953855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.047603272996717357, "f1": 0.5741893219783819, "f1_std": 0.05262681232778399, "bacc": 0.5734295415959253, "bacc_std": 0.050652788397655926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.041989765419682926, "f1": 0.6553308823529411, "f1_std": 0.051258493422226076, "bacc": 0.6511035653650254, "bacc_std": 0.0472019946272192} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.037915506062823415, "f1": 0.627359057579036, "f1_std": 0.05030744225484978, "bacc": 0.6277589134125636, "bacc_std": 0.043072153812826336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.03821518022985107, "f1": 0.5706048337627285, "f1_std": 0.051407063340034795, "bacc": 0.580220713073005, "bacc_std": 0.04234868317624393} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 1291.5496650148827, "split": "test", "acc": 0.53, "acc_std": 0.04774515682244639, "f1": 0.5037482842360892, "f1_std": 0.04956166085790679, "bacc": 0.5038200339558574, "bacc_std": 0.049642538818819595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.040774869711625084, "f1": 0.5636277862955537, "f1_std": 0.050110981027884506, "bacc": 0.5691850594227504, "bacc_std": 0.044202296820841085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.040205253388083506, "f1": 0.5400400990682863, "f1_std": 0.04944841665066762, "bacc": 0.547962648556876, "bacc_std": 0.04304905872093102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04418091895830144, "f1": 0.5091164095371669, "f1_std": 0.05134770593071911, "bacc": 0.5186757215619694, "bacc_std": 0.04590784484916845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.047192524831799365, "f1": 0.5495495495495495, "f1_std": 0.0501552282367562, "bacc": 0.5492359932088284, "bacc_std": 0.04959944626737635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.04182131513953142, "f1": 0.6640018537828757, "f1_std": 0.05171246465112901, "bacc": 0.6591680814940577, "bacc_std": 0.04706924191849381} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.040016051779254776, "f1": 0.6428571428571428, "f1_std": 0.051733262398035086, "bacc": 0.6409168081494058, "bacc_std": 0.045419007331508575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04739098648477366, "f1": 0.612789025334661, "f1_std": 0.05268014541966053, "bacc": 0.6107809847198642, "bacc_std": 0.05052340763647285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.03989724301251905, "f1": 0.5706048337627285, "f1_std": 0.05261641183359767, "bacc": 0.580220713073005, "bacc_std": 0.04362207458448587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04596681846723787, "f1": 0.5824175824175825, "f1_std": 0.05061672234844486, "bacc": 0.5814940577249575, "bacc_std": 0.04857194533730602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.041870103892873246, "f1": 0.6239316239316239, "f1_std": 0.049309776834903334, "bacc": 0.6218166383701189, "bacc_std": 0.045556411954456005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04368360790960381, "f1": 0.5703301673450927, "f1_std": 0.04982647239073261, "bacc": 0.5713073005093379, "bacc_std": 0.04646484427791653} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04235081581268534, "f1": 0.6323529411764706, "f1_std": 0.05125800637873745, "bacc": 0.6298811544991512, "bacc_std": 0.0469134938142789} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.044583741431154025, "f1": 0.6703296703296704, "f1_std": 0.050529996500963174, "bacc": 0.666383701188455, "bacc_std": 0.048890246871667646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.039395309365456176, "f1": 0.6108031607500884, "f1_std": 0.05078984413320575, "bacc": 0.6116298811544991, "bacc_std": 0.04446861630658278} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04049914073162541, "f1": 0.5460679671205987, "f1_std": 0.05160558201838709, "bacc": 0.5589983022071308, "bacc_std": 0.04346168935748628} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.04134800599787128, "f1": 0.6343908479773559, "f1_std": 0.0510852549729224, "bacc": 0.6328522920203735, "bacc_std": 0.04544262562258599} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.041468498887709926, "f1": 0.6493688639551192, "f1_std": 0.052122437365062134, "bacc": 0.6460101867572157, "bacc_std": 0.046710387051826945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.041298348635266276, "f1": 0.6703296703296704, "f1_std": 0.04535754969972444, "bacc": 0.666383701188455, "bacc_std": 0.04387130345553744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03690989569207695, "f1": 0.5386109762020399, "f1_std": 0.04754938235935523, "bacc": 0.5509337860780985, "bacc_std": 0.03986957128031496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.55, "acc_std": 0.0469122201563729, "f1": 0.5021573182874212, "f1_std": 0.05036032287367769, "bacc": 0.5046689303904923, "bacc_std": 0.04825502616775756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.043822637985406594, "f1": 0.5558672276764843, "f1_std": 0.053148710282979426, "bacc": 0.5611205432937181, "bacc_std": 0.047403203748304146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.03792940811560339, "f1": 0.5714285714285714, "f1_std": 0.04801656681772023, "bacc": 0.5772495755517827, "bacc_std": 0.04159579882867716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.039817563963658056, "f1": 0.5311936530833032, "f1_std": 0.05104009001399678, "bacc": 0.5428692699490663, "bacc_std": 0.04291518162119365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04846248445963125, "f1": 0.6043956043956044, "f1_std": 0.054164786931007534, "bacc": 0.6027164685908319, "bacc_std": 0.05198778121718141} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.0375621671366283, "f1": 0.6033177064551027, "f1_std": 0.049650947248438736, "bacc": 0.6065365025466893, "bacc_std": 0.04214251989434343} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.76, "acc_std": 0.035323074611364184, "f1": 0.7085964060223409, "f1_std": 0.049815082889859946, "bacc": 0.6994906621392191, "bacc_std": 0.0433154382331668} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.03843341775070232, "f1": 0.5792763553311696, "f1_std": 0.05039459623667844, "bacc": 0.5853140916808149, "bacc_std": 0.042606268936664166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.039021717030392186, "f1": 0.6108031607500884, "f1_std": 0.049618995488409263, "bacc": 0.6116298811544991, "bacc_std": 0.043589888781884426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.000774263682681127, "split": "test", "acc": 0.67, "acc_std": 0.03675902066160087, "f1": 0.5862068965517242, "f1_std": 0.051877573806358476, "bacc": 0.5963497453310695, "bacc_std": 0.041784655658815055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04509763186687301, "f1": 0.5659722222222222, "f1_std": 0.048933770795471156, "bacc": 0.565365025466893, "bacc_std": 0.04761857360200256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03996476448072726, "f1": 0.6408295678368672, "f1_std": 0.04908374172008467, "bacc": 0.6379456706281834, "bacc_std": 0.04442053606841127} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03790376762275751, "f1": 0.5386109762020399, "f1_std": 0.048389724214338146, "bacc": 0.5509337860780985, "bacc_std": 0.0407576426736104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.041887468293034844, "f1": 0.5017958521608157, "f1_std": 0.0482793981806282, "bacc": 0.5106112054329371, "bacc_std": 0.04353005157478247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04126505058763408, "f1": 0.6259934548854604, "f1_std": 0.050821378958185934, "bacc": 0.6247877758913413, "bacc_std": 0.04531790359503978} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.03886003602674604, "f1": 0.5706048337627285, "f1_std": 0.050860824346020156, "bacc": 0.580220713073005, "bacc_std": 0.042321753467052296} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03874930192919608, "f1": 0.6259934548854604, "f1_std": 0.04875472331549811, "bacc": 0.6247877758913413, "bacc_std": 0.043446136997064067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04068218283229158, "f1": 0.5944849959448499, "f1_std": 0.050381577807762215, "bacc": 0.5955008488964346, "bacc_std": 0.04506405900895245} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 38.773 | 221.43 | 0.76746 | 0.058837 | 0.7299 | 0.072044 | 0.72276 | 0.072351 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 38.773 | 221.43 | 0.6548 | 0.046089 | 0.60301 | 0.047876 | 0.60406 | 0.044318 | + + +done! total time: 0:05:37 diff --git a/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/config.yaml b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..07e3c563c308d74b62830c5434b689ca4244e9f8 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic +remote_dir: null diff --git a/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/eval_table.csv b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b177815794b0aa863052f4a0a21986418c567d1f --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,ppmi_dx,,0.3593813663804626,train,0.9661921708185054,0.007341718948728805,0.9639893026847833,0.0079014919937162,0.9596406865691578,0.008861295341998806 +flat_mae,reg,logistic,ppmi_dx,,0.3593813663804626,test,0.66,0.044403441308078814,0.6155585707824514,0.04995857478485883,0.613041613041613,0.04738454323036989 +flat_mae,reg,logistic,ppmi_dx,1,0.046415888336127774,train,0.8701067615658363,0.01404452986173785,0.8597089951613179,0.015468826085389303,0.8527617212588311,0.015936164463631212 +flat_mae,reg,logistic,ppmi_dx,1,0.046415888336127774,test,0.62,0.04952145393665255,0.5766488413547237,0.05570788566604609,0.5764006791171477,0.05285197280380837 +flat_mae,reg,logistic,ppmi_dx,2,0.046415888336127774,train,0.8701067615658363,0.013837870885178481,0.8584934620571669,0.015430150513394183,0.8492828088203811,0.015778097533680074 +flat_mae,reg,logistic,ppmi_dx,2,0.046415888336127774,test,0.69,0.042512943911237194,0.6570417081535569,0.04850288626645294,0.6532258064516129,0.04650848350253953 +flat_mae,reg,logistic,ppmi_dx,3,0.3593813663804626,train,0.9715302491103203,0.006668567228657099,0.9697035040431267,0.007154413424511116,0.966441875401413,0.008039798038685042 +flat_mae,reg,logistic,ppmi_dx,3,0.3593813663804626,test,0.64,0.04748983470175486,0.625,0.04898638042359684,0.6281833616298811,0.050018224884669185 +flat_mae,reg,logistic,ppmi_dx,4,0.005994842503189409,train,0.7686832740213523,0.015602074092858215,0.732780313670412,0.01955592945937157,0.7225567330336116,0.018125535344343337 +flat_mae,reg,logistic,ppmi_dx,4,0.005994842503189409,test,0.66,0.043453883600893486,0.6212121212121212,0.04892343990985682,0.6188455008488964,0.04627842002989132 +flat_mae,reg,logistic,ppmi_dx,5,0.3593813663804626,train,0.9822064056939501,0.005614276877915258,0.9810995870158872,0.006001617521936997,0.9785913080710769,0.006823678667748933 +flat_mae,reg,logistic,ppmi_dx,5,0.3593813663804626,test,0.61,0.04642335188243089,0.584,0.049116337642184524,0.583616298811545,0.04889873994606864 +flat_mae,reg,logistic,ppmi_dx,6,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,6,1291.5496650148827,test,0.6,0.045008172591208366,0.5755517826825127,0.04767560151533296,0.5755517826825127,0.04774967770780004 +flat_mae,reg,logistic,ppmi_dx,7,0.046415888336127774,train,0.8736654804270463,0.01290661328176118,0.8641139070231539,0.014133499184632092,0.8582610789980731,0.0146873798008875 +flat_mae,reg,logistic,ppmi_dx,7,0.046415888336127774,test,0.59,0.05198761006239852,0.5626666666666666,0.053903271421685335,0.5623938879456706,0.05356077009907835 +flat_mae,reg,logistic,ppmi_dx,8,0.005994842503189409,train,0.7722419928825622,0.014740400822934383,0.7344555186415651,0.018794777577314622,0.7237074502247912,0.017279720021557022 +flat_mae,reg,logistic,ppmi_dx,8,0.005994842503189409,test,0.67,0.038251880999501185,0.6033177064551027,0.05010412317671512,0.6065365025466893,0.04270222918510206 +flat_mae,reg,logistic,ppmi_dx,9,0.005994842503189409,train,0.7722419928825622,0.015530736347067517,0.7384525887143689,0.019351354963453984,0.7280560907728538,0.018196062357628422 +flat_mae,reg,logistic,ppmi_dx,9,0.005994842503189409,test,0.7,0.041802100425696306,0.66078697421981,0.04937492808436804,0.6561969439728353,0.04633498010277153 +flat_mae,reg,logistic,ppmi_dx,10,0.005994842503189409,train,0.7562277580071174,0.016203859533014245,0.7144340717827748,0.02078240489395408,0.7054833012202955,0.018855062397890934 +flat_mae,reg,logistic,ppmi_dx,10,0.005994842503189409,test,0.68,0.03980280894610328,0.6323529411764706,0.04734298374316082,0.6298811544991512,0.04347786473163675 +flat_mae,reg,logistic,ppmi_dx,11,0.005994842503189409,train,0.7651245551601423,0.01605885874486842,0.7286692415730337,0.0202944587335446,0.7187968315135945,0.018877641484314072 +flat_mae,reg,logistic,ppmi_dx,11,0.005994842503189409,test,0.7,0.0386621209971724,0.6428571428571428,0.05098502038705891,0.6409168081494058,0.04405285057483844 +flat_mae,reg,logistic,ppmi_dx,12,0.005994842503189409,train,0.7686832740213523,0.015912837949936108,0.7351401516799351,0.01961067825343842,0.7251659173624492,0.018457979270919824 +flat_mae,reg,logistic,ppmi_dx,12,0.005994842503189409,test,0.63,0.039616415789417395,0.5552350042072365,0.04976977811400029,0.5640916808149405,0.04279524994480864 +flat_mae,reg,logistic,ppmi_dx,13,0.005994842503189409,train,0.7562277580071174,0.016242649017845924,0.7204721121974419,0.020225919893127584,0.711571397987583,0.018854031077583253 +flat_mae,reg,logistic,ppmi_dx,13,0.005994842503189409,test,0.67,0.04043837781118327,0.6176572818908586,0.049505278046492046,0.616723259762309,0.044440226175004795 +flat_mae,reg,logistic,ppmi_dx,14,0.005994842503189409,train,0.7651245551601423,0.016165330693795325,0.7294805782049973,0.020200185285965448,0.719666559623207,0.018888255096018162 +flat_mae,reg,logistic,ppmi_dx,14,0.005994842503189409,test,0.66,0.041426677395127884,0.587178241864983,0.053508759064354525,0.5933786078098472,0.04533967367777042 +flat_mae,reg,logistic,ppmi_dx,15,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,15,2.782559402207126,test,0.64,0.04920162598939186,0.6138996138996139,0.052867099398570455,0.6129032258064516,0.05222047395292094 +flat_mae,reg,logistic,ppmi_dx,16,0.3593813663804626,train,0.9733096085409253,0.006867866412719093,0.9715167098590026,0.0074101477195165,0.9670172339970027,0.008530559144770224 +flat_mae,reg,logistic,ppmi_dx,16,0.3593813663804626,test,0.59,0.047230206436135756,0.5670995670995671,0.04971475761902281,0.5674872665534805,0.05015254481354647 +flat_mae,reg,logistic,ppmi_dx,17,0.005994842503189409,train,0.7811387900355872,0.01649365262741112,0.7482986509366978,0.020751400881622084,0.7370209805180903,0.019538902277328202 +flat_mae,reg,logistic,ppmi_dx,17,0.005994842503189409,test,0.65,0.041532753339984574,0.5944849959448499,0.050738435677190157,0.5955008488964346,0.04557578939969868 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,train,0.7775800711743772,0.015337215835583217,0.7449563067494909,0.01902019444618549,0.7341308071076857,0.01792696902718479 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,test,0.61,0.04625753992594072,0.5481404240528328,0.0544008819393325,0.5530560271646858,0.049157151499731516 +flat_mae,reg,logistic,ppmi_dx,19,0.046415888336127774,train,0.8701067615658363,0.01381001697823346,0.8602861297562006,0.015112339353930184,0.8545011774780561,0.015569354155730242 +flat_mae,reg,logistic,ppmi_dx,19,0.046415888336127774,test,0.65,0.04713444175971536,0.6338529134846741,0.048887575334434705,0.6362478777589134,0.049438984069135515 +flat_mae,reg,logistic,ppmi_dx,20,0.005994842503189409,train,0.7562277580071174,0.01571109327494344,0.716227522178363,0.019978368234856297,0.7072227574395205,0.018274301391102157 +flat_mae,reg,logistic,ppmi_dx,20,0.005994842503189409,test,0.69,0.0388910015299169,0.6408295678368672,0.04784690609885569,0.6379456706281834,0.0431162133886556 +flat_mae,reg,logistic,ppmi_dx,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,21,21.54434690031882,test,0.58,0.050948958772481304,0.5625,0.05168077808513794,0.564516129032258,0.05230847184462766 +flat_mae,reg,logistic,ppmi_dx,22,0.046415888336127774,train,0.8736654804270463,0.013749003355657992,0.8626734993787922,0.015366897050001974,0.8539124384500107,0.015935810717304127 +flat_mae,reg,logistic,ppmi_dx,22,0.046415888336127774,test,0.64,0.044609613313724206,0.609375,0.04912400208804288,0.6078098471986417,0.04808713628012754 +flat_mae,reg,logistic,ppmi_dx,23,0.046415888336127774,train,0.8807829181494662,0.012305415349323454,0.8692365126495459,0.014015488423503204,0.857953329051595,0.014626679739492544 +flat_mae,reg,logistic,ppmi_dx,23,0.046415888336127774,test,0.57,0.046667243329770396,0.5174503422735944,0.0516651982911007,0.5207979626485568,0.04867921072844272 +flat_mae,reg,logistic,ppmi_dx,24,0.005994842503189409,train,0.7651245551601423,0.01578960527871785,0.7286692415730337,0.01992922209899433,0.7187968315135945,0.018548197530113532 +flat_mae,reg,logistic,ppmi_dx,24,0.005994842503189409,test,0.64,0.04052477760580557,0.5714285714285714,0.05178949157043787,0.5772495755517827,0.044480658711372044 +flat_mae,reg,logistic,ppmi_dx,25,0.046415888336127774,train,0.8754448398576512,0.012890178830206062,0.8653330047102641,0.014243968327052837,0.8579667094840505,0.014793856090570408 +flat_mae,reg,logistic,ppmi_dx,25,0.046415888336127774,test,0.66,0.0423787635496837,0.6155585707824514,0.049057775499717994,0.6137521222410866,0.04594501629853134 +flat_mae,reg,logistic,ppmi_dx,26,0.046415888336127774,train,0.8701067615658363,0.013479290237552944,0.8581764756719384,0.015223678651691367,0.8484130807107686,0.01578257576329488 +flat_mae,reg,logistic,ppmi_dx,26,0.046415888336127774,test,0.67,0.046944098670652946,0.6515679442508711,0.04871839696965553,0.652376910016978,0.048730132822854044 +flat_mae,reg,logistic,ppmi_dx,27,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,27,2.782559402207126,test,0.63,0.04517101282902566,0.6093337556752191,0.04748621536234211,0.6099320882852293,0.04758811964118473 +flat_mae,reg,logistic,ppmi_dx,28,0.3593813663804626,train,0.9786476868327402,0.006139317115956005,0.9773606187560425,0.006533147578796497,0.9757011346606722,0.007086399186726526 +flat_mae,reg,logistic,ppmi_dx,28,0.3593813663804626,test,0.61,0.04542124612997755,0.5793334052421529,0.049358227021803945,0.5785229202037352,0.04831947256779907 +flat_mae,reg,logistic,ppmi_dx,29,0.046415888336127774,train,0.8612099644128114,0.014230644833963801,0.8482910419867935,0.016142969834556202,0.8385784628559194,0.01662266415855877 +flat_mae,reg,logistic,ppmi_dx,29,0.046415888336127774,test,0.66,0.04282277431460974,0.6212121212121212,0.04956577793453368,0.6188455008488964,0.046649151394833 +flat_mae,reg,logistic,ppmi_dx,30,0.046415888336127774,train,0.8665480427046264,0.012673644650517847,0.8532805630684726,0.014402365193162077,0.842043994861914,0.014769826545073339 +flat_mae,reg,logistic,ppmi_dx,30,0.046415888336127774,test,0.65,0.04476613005386997,0.612789025334661,0.05088660069041465,0.6107809847198642,0.04868435235916302 +flat_mae,reg,logistic,ppmi_dx,31,0.046415888336127774,train,0.8718861209964412,0.013188932822160965,0.861190773495067,0.014695587247997072,0.8533370798544209,0.015312805969268458 +flat_mae,reg,logistic,ppmi_dx,31,0.046415888336127774,test,0.66,0.04499367066599479,0.6263736263736264,0.04924443688053769,0.6239388794567062,0.04747490708288465 +flat_mae,reg,logistic,ppmi_dx,32,0.3593813663804626,train,0.9857651245551602,0.005163842090041816,0.9849339856577977,0.005471294227221288,0.984090665810319,0.005766798427268768 +flat_mae,reg,logistic,ppmi_dx,32,0.3593813663804626,test,0.63,0.04896370492517902,0.6053333333333333,0.05197763345449849,0.6048387096774194,0.05175542611869431 +flat_mae,reg,logistic,ppmi_dx,33,0.046415888336127774,train,0.8683274021352313,0.013731721497190446,0.8576377478365648,0.01523974077684957,0.8504469064440163,0.015806589820884908 +flat_mae,reg,logistic,ppmi_dx,33,0.046415888336127774,test,0.67,0.04349208663653653,0.648,0.04704471978736863,0.6472835314091681,0.04705982646298678 +flat_mae,reg,logistic,ppmi_dx,34,0.005994842503189409,train,0.7740213523131673,0.016119764590425283,0.7423646831627773,0.019784668315251167,0.7321103618068936,0.01880371997495172 +flat_mae,reg,logistic,ppmi_dx,34,0.005994842503189409,test,0.65,0.04220890427386145,0.5792763553311696,0.05373250348313509,0.5853140916808149,0.04623485012399437 +flat_mae,reg,logistic,ppmi_dx,35,0.005994842503189409,train,0.7651245551601423,0.016043024734165336,0.7302792321116929,0.020054321546788916,0.7205362877328195,0.01873645958980712 +flat_mae,reg,logistic,ppmi_dx,35,0.005994842503189409,test,0.64,0.046152664061785205,0.609375,0.049531280657596786,0.6078098471986417,0.04818780944897796 +flat_mae,reg,logistic,ppmi_dx,36,0.046415888336127774,train,0.8665480427046264,0.012292321852692667,0.8539597185216496,0.013977136210495044,0.843783451081139,0.01456252896692197 +flat_mae,reg,logistic,ppmi_dx,36,0.046415888336127774,test,0.63,0.04237177834360979,0.5783475783475784,0.049751963873476676,0.5793718166383701,0.04574951571173548 +flat_mae,reg,logistic,ppmi_dx,37,0.005994842503189409,train,0.7633451957295374,0.015771613664142065,0.7294193880025919,0.019160571159013772,0.7199609291372298,0.01794922604091918 +flat_mae,reg,logistic,ppmi_dx,37,0.005994842503189409,test,0.68,0.04098758836526003,0.6323529411764706,0.0502754601510319,0.6298811544991512,0.045905204188279036 +flat_mae,reg,logistic,ppmi_dx,38,0.005994842503189409,train,0.7597864768683275,0.016508342152410888,0.7212332315560895,0.020708924812225714,0.7118523870691501,0.019077752285200762 +flat_mae,reg,logistic,ppmi_dx,38,0.005994842503189409,test,0.68,0.0462192860178519,0.6381727725011307,0.055599192971099866,0.634974533106961,0.05183077649144274 +flat_mae,reg,logistic,ppmi_dx,39,0.005994842503189409,train,0.7615658362989324,0.014897011388740269,0.719335122242099,0.01981254500714413,0.7098185613359024,0.01790917525798269 +flat_mae,reg,logistic,ppmi_dx,39,0.005994842503189409,test,0.77,0.03757873866962542,0.7378917378917379,0.04613124377433619,0.7279286926994907,0.04344623652504512 +flat_mae,reg,logistic,ppmi_dx,40,0.005994842503189409,train,0.7526690391459074,0.015859949152111405,0.7111821794990295,0.020335461999528067,0.7025931278098908,0.018499806558846137 +flat_mae,reg,logistic,ppmi_dx,40,0.005994842503189409,test,0.68,0.04150173008441937,0.6381727725011307,0.0485768109610742,0.634974533106961,0.04550203467527192 +flat_mae,reg,logistic,ppmi_dx,41,0.3593813663804626,train,0.9768683274021353,0.006421132049068963,0.9754959668628733,0.006828639728856625,0.9742560479554698,0.007342372667136327 +flat_mae,reg,logistic,ppmi_dx,41,0.3593813663804626,test,0.59,0.046863081418105655,0.5670995670995671,0.049456906049059994,0.5674872665534805,0.04967911319493318 +flat_mae,reg,logistic,ppmi_dx,42,0.005994842503189409,train,0.7597864768683275,0.015758897575679262,0.7212332315560895,0.019965862415644933,0.7118523870691501,0.01831392980680671 +flat_mae,reg,logistic,ppmi_dx,42,0.005994842503189409,test,0.69,0.037565814246466156,0.627359057579036,0.049093141257944325,0.6277589134125636,0.04236841224220484 +flat_mae,reg,logistic,ppmi_dx,43,0.005994842503189409,train,0.7686832740213523,0.016222568939979056,0.7351401516799351,0.019980026264510727,0.7251659173624492,0.018795845860713936 +flat_mae,reg,logistic,ppmi_dx,43,0.005994842503189409,test,0.67,0.043957251961422694,0.6349153667441089,0.05002710084929576,0.6320033955857385,0.047981906195953425 +flat_mae,reg,logistic,ppmi_dx,44,0.005994842503189409,train,0.7437722419928826,0.01581438605500635,0.7021902967498823,0.020053366336905694,0.6944979661742667,0.018312425833676288 +flat_mae,reg,logistic,ppmi_dx,44,0.005994842503189409,test,0.71,0.03956994313870062,0.6640018537828757,0.04984818533800049,0.6591680814940577,0.04562450990858954 +flat_mae,reg,logistic,ppmi_dx,45,0.046415888336127774,train,0.8736654804270463,0.013335275078867323,0.8629715482752107,0.014856595825019237,0.8547821665596231,0.015430558233317243 +flat_mae,reg,logistic,ppmi_dx,45,0.046415888336127774,test,0.64,0.04339888938671126,0.6043956043956044,0.04892066734387949,0.6027164685908319,0.047055988840898344 +flat_mae,reg,logistic,ppmi_dx,46,0.046415888336127774,train,0.8594306049822064,0.01492322181567407,0.8468627877057011,0.01668297170222462,0.8380031042603298,0.01704836463763024 +flat_mae,reg,logistic,ppmi_dx,46,0.046415888336127774,test,0.6,0.04548582196685029,0.554367201426025,0.051189771955055106,0.5551782682512734,0.048346685057663735 +flat_mae,reg,logistic,ppmi_dx,47,0.046415888336127774,train,0.8451957295373665,0.014803573673035517,0.8317266823373932,0.016502536157616304,0.8238332262898738,0.01684189072431043 +flat_mae,reg,logistic,ppmi_dx,47,0.046415888336127774,test,0.68,0.0463227978429628,0.6567996567996568,0.05022535010981531,0.6553480475382003,0.05000628708804277 +flat_mae,reg,logistic,ppmi_dx,48,0.046415888336127774,train,0.8665480427046264,0.013917704960458488,0.8542908996629505,0.015611105468233858,0.8446531791907514,0.0159867813488334 +flat_mae,reg,logistic,ppmi_dx,48,0.046415888336127774,test,0.68,0.04258624660615208,0.6604414261460102,0.045697233310599945,0.6604414261460102,0.045993346542883236 +flat_mae,reg,logistic,ppmi_dx,49,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,49,21.54434690031882,test,0.63,0.04440477001404241,0.5960257670051315,0.048539035858431744,0.5946519524617997,0.046928429739255456 +flat_mae,reg,logistic,ppmi_dx,50,0.005994842503189409,train,0.7562277580071174,0.015838411630836092,0.7179655305042216,0.01953799885201784,0.7089622136587455,0.018039899336179027 +flat_mae,reg,logistic,ppmi_dx,50,0.005994842503189409,test,0.68,0.04358081688082498,0.6259934548854604,0.053290821013731386,0.6247877758913413,0.04799134062991036 +flat_mae,reg,logistic,ppmi_dx,51,0.046415888336127774,train,0.8772241992882562,0.013475155579242061,0.8671162604216998,0.014930550870414895,0.8594117961892529,0.015472115391030638 +flat_mae,reg,logistic,ppmi_dx,51,0.046415888336127774,test,0.6,0.046782543752985475,0.5604395604395604,0.05206210957966023,0.5602716468590832,0.0499030406795085 +flat_mae,reg,logistic,ppmi_dx,52,0.005994842503189409,train,0.7651245551601423,0.016768766350868766,0.7286692415730337,0.02091201182077649,0.7187968315135945,0.019366720206453622 +flat_mae,reg,logistic,ppmi_dx,52,0.005994842503189409,test,0.62,0.04147721784305211,0.5476190476190476,0.05202129968933117,0.5560271646859083,0.044943089705938785 +flat_mae,reg,logistic,ppmi_dx,53,0.046415888336127774,train,0.8772241992882562,0.012912832842195632,0.8659476276899144,0.014527758306758872,0.8559328837508028,0.015079629086326155 +flat_mae,reg,logistic,ppmi_dx,53,0.046415888336127774,test,0.67,0.044437547187035416,0.6296711929076422,0.052340102989190326,0.6269100169779287,0.04900492040947786 +flat_mae,reg,logistic,ppmi_dx,54,0.005994842503189409,train,0.7758007117437722,0.016574564137262212,0.7454710144927537,0.019896574052752913,0.7352949047313209,0.01887574929530163 +flat_mae,reg,logistic,ppmi_dx,54,0.005994842503189409,test,0.52,0.049476180127410806,0.47916666666666663,0.050753703311144774,0.48047538200339557,0.04974930776591758 +flat_mae,reg,logistic,ppmi_dx,55,0.046415888336127774,train,0.8665480427046264,0.013665578198790215,0.8542908996629505,0.015397622168674472,0.8446531791907514,0.015856765036262297 +flat_mae,reg,logistic,ppmi_dx,55,0.046415888336127774,test,0.7,0.0459750193039655,0.6816638370118846,0.04892094962197341,0.6816638370118846,0.0492911065579874 +flat_mae,reg,logistic,ppmi_dx,56,0.3593813663804626,train,0.9768683274021353,0.006044582198065032,0.9754518360722937,0.006450549176820377,0.9733863198458574,0.007123603311658483 +flat_mae,reg,logistic,ppmi_dx,56,0.3593813663804626,test,0.66,0.04482450668997931,0.6212121212121212,0.05136192482623712,0.6188455008488964,0.04847634472510594 +flat_mae,reg,logistic,ppmi_dx,57,0.005994842503189409,train,0.7562277580071174,0.015561604558315205,0.716227522178363,0.019959334989933696,0.7072227574395205,0.01820685530955921 +flat_mae,reg,logistic,ppmi_dx,57,0.005994842503189409,test,0.7,0.03589078433247175,0.6279761904761905,0.051434727664473844,0.6307300509337861,0.04217535408627037 +flat_mae,reg,logistic,ppmi_dx,58,0.046415888336127774,train,0.8629893238434164,0.013831690502694647,0.8507396791561898,0.015531446109329314,0.8417630057803468,0.01595265730914626 +flat_mae,reg,logistic,ppmi_dx,58,0.046415888336127774,test,0.68,0.045095538581992785,0.6527777777777778,0.04935318106516789,0.6502546689303905,0.0483268639717604 +flat_mae,reg,logistic,ppmi_dx,59,0.005994842503189409,train,0.7544483985765125,0.014863000720430633,0.7163360252808989,0.018601849858590196,0.7075171269535432,0.01715403001001206 +flat_mae,reg,logistic,ppmi_dx,59,0.005994842503189409,test,0.6,0.04474855975335966,0.5477159656264134,0.05119401115158754,0.5500848896434635,0.047362123617635005 +flat_mae,reg,logistic,ppmi_dx,60,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,60,2.782559402207126,test,0.62,0.04691215194381942,0.6041666666666667,0.048720763946501544,0.6069609507640068,0.04974894917076368 +flat_mae,reg,logistic,ppmi_dx,61,0.3593813663804626,train,0.9733096085409253,0.006783112326519729,0.9715705021195657,0.0072931207482613315,0.9678869621066153,0.008288536040111993 +flat_mae,reg,logistic,ppmi_dx,61,0.3593813663804626,test,0.62,0.04849020932105779,0.6006725514922235,0.0502734410567677,0.6018675721561969,0.050773908181167685 +flat_mae,reg,logistic,ppmi_dx,62,0.005994842503189409,train,0.7846975088967971,0.015555997896432675,0.7531177049335072,0.019344181498947163,0.74165061014772,0.018325371842072852 +flat_mae,reg,logistic,ppmi_dx,62,0.005994842503189409,test,0.64,0.03884250764304489,0.5628946090335114,0.05204937973888966,0.5721561969439728,0.04306117763449482 +flat_mae,reg,logistic,ppmi_dx,63,0.3593813663804626,train,0.9822064056939501,0.0052300383360635696,0.9810995870158872,0.005588171068904779,0.9785913080710769,0.006359419810122286 +flat_mae,reg,logistic,ppmi_dx,63,0.3593813663804626,test,0.59,0.04641349372757883,0.5626666666666666,0.04927385899265517,0.5623938879456706,0.04900298540760564 +flat_mae,reg,logistic,ppmi_dx,64,0.046415888336127774,train,0.8772241992882562,0.013392292222166209,0.8656429410399177,0.015123645426952263,0.8550631556411903,0.01565703538977575 +flat_mae,reg,logistic,ppmi_dx,64,0.046415888336127774,test,0.65,0.03780928986373588,0.5706048337627285,0.050338524091829664,0.580220713073005,0.04162860072755914 +flat_mae,reg,logistic,ppmi_dx,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,65,21.54434690031882,test,0.56,0.053153453321491725,0.548440065681445,0.0527324899775548,0.5534804753820034,0.05373496745197361 +flat_mae,reg,logistic,ppmi_dx,66,0.005994842503189409,train,0.7811387900355872,0.016352152849867976,0.7518763796909492,0.01980051054912276,0.7413696210661529,0.01896311736532455 +flat_mae,reg,logistic,ppmi_dx,66,0.005994842503189409,test,0.63,0.04627436007121006,0.5783475783475784,0.05370757138761157,0.5793718166383701,0.049404911478270294 +flat_mae,reg,logistic,ppmi_dx,67,0.046415888336127774,train,0.8896797153024911,0.012957390669961287,0.8807235184576624,0.014360353143973223,0.873006315564119,0.015096196768471449 +flat_mae,reg,logistic,ppmi_dx,67,0.046415888336127774,test,0.66,0.0472139809802139,0.6392190152801358,0.049597395570738355,0.6392190152801358,0.04984311709279077 +flat_mae,reg,logistic,ppmi_dx,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,68,2.782559402207126,test,0.62,0.048023094444235886,0.5967741935483871,0.051066673003096655,0.5967741935483871,0.05107152530226998 +flat_mae,reg,logistic,ppmi_dx,69,0.046415888336127774,train,0.8629893238434164,0.013655847639179859,0.8513916791153695,0.015064230611173911,0.8435024619995719,0.015388767221411541 +flat_mae,reg,logistic,ppmi_dx,69,0.046415888336127774,test,0.7,0.04654234630957059,0.6816638370118846,0.04890278307229904,0.6816638370118846,0.04908577443480196 +flat_mae,reg,logistic,ppmi_dx,70,0.005994842503189409,train,0.7846975088967971,0.015802825593590194,0.7531177049335072,0.01972176227487625,0.74165061014772,0.018677126546594758 +flat_mae,reg,logistic,ppmi_dx,70,0.005994842503189409,test,0.63,0.04618283663873409,0.5960257670051315,0.049273163190097696,0.5946519524617997,0.04773374148106287 +flat_mae,reg,logistic,ppmi_dx,71,0.046415888336127774,train,0.8843416370106761,0.01291867444008438,0.8745514174350522,0.014363148953261795,0.8660618711196746,0.014955843351953336 +flat_mae,reg,logistic,ppmi_dx,71,0.046415888336127774,test,0.6,0.0428500828470611,0.5404411764705883,0.04841306538733922,0.5449915110356536,0.044339851278983496 +flat_mae,reg,logistic,ppmi_dx,72,0.005994842503189409,train,0.7758007117437722,0.01557380069847086,0.7417769155593156,0.019232590102716492,0.7309462641832585,0.01793991886305121 +flat_mae,reg,logistic,ppmi_dx,72,0.005994842503189409,test,0.66,0.04541460558014349,0.6263736263736264,0.050542036970551305,0.6239388794567062,0.04866957530586481 +flat_mae,reg,logistic,ppmi_dx,73,0.046415888336127774,train,0.8612099644128114,0.013975693855527544,0.848632596685083,0.01566479894426401,0.839448190965532,0.016061004288506067 +flat_mae,reg,logistic,ppmi_dx,73,0.046415888336127774,test,0.63,0.04781020393179682,0.5960257670051315,0.05258587321606418,0.5946519524617997,0.05083774064797116 +flat_mae,reg,logistic,ppmi_dx,74,0.005994842503189409,train,0.7758007117437722,0.016347029997812138,0.7417769155593156,0.02015137833883424,0.7309462641832585,0.01885637033375829 +flat_mae,reg,logistic,ppmi_dx,74,0.005994842503189409,test,0.61,0.042292746422997886,0.5623386825272135,0.04762133400508143,0.5632427843803056,0.04468843244886258 +flat_mae,reg,logistic,ppmi_dx,75,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,75,2.782559402207126,test,0.51,0.05187116347258851,0.4873940788785438,0.05282956812806291,0.4876910016977929,0.05337798938629218 +flat_mae,reg,logistic,ppmi_dx,76,0.005994842503189409,train,0.7633451957295374,0.015859551883644945,0.7278351266226082,0.019826841834519535,0.7182214729180048,0.018488235892902327 +flat_mae,reg,logistic,ppmi_dx,76,0.005994842503189409,test,0.7,0.04238331747279818,0.6657754010695187,0.04896676833620426,0.6612903225806452,0.046813549024006626 +flat_mae,reg,logistic,ppmi_dx,77,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,77,21.54434690031882,test,0.59,0.044350508452553276,0.5805626598465473,0.0447204986814865,0.5878607809847198,0.046484589101169635 +flat_mae,reg,logistic,ppmi_dx,78,0.005994842503189409,train,0.7615658362989324,0.01667796963942024,0.7285493893911212,0.02035878172498055,0.7193855705416399,0.019264087022186866 +flat_mae,reg,logistic,ppmi_dx,78,0.005994842503189409,test,0.68,0.03718633620027656,0.6031746031746031,0.05182348695731351,0.6095076400679117,0.042340320073538815 +flat_mae,reg,logistic,ppmi_dx,79,0.046415888336127774,train,0.8629893238434164,0.013771557359278486,0.8507396791561898,0.015501514603003426,0.8417630057803468,0.0159902052717429 +flat_mae,reg,logistic,ppmi_dx,79,0.046415888336127774,test,0.72,0.041675791534174854,0.6961805555555556,0.04568123076118576,0.6926994906621392,0.04481411112192359 +flat_mae,reg,logistic,ppmi_dx,80,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,80,2.782559402207126,test,0.66,0.04798937799138472,0.6486151302190988,0.04860121661326754,0.6544991511035654,0.04927056671347943 +flat_mae,reg,logistic,ppmi_dx,81,0.005994842503189409,train,0.7544483985765125,0.015460745864335813,0.718841084091008,0.019318212057540137,0.7101263112823806,0.018099919366021566 +flat_mae,reg,logistic,ppmi_dx,81,0.005994842503189409,test,0.73,0.03684896742108251,0.6871741397288842,0.04557341404072206,0.6803904923599321,0.04163695263669992 +flat_mae,reg,logistic,ppmi_dx,82,0.005994842503189409,train,0.7633451957295374,0.016177998177465534,0.7270240560370171,0.020159758943297905,0.7173517448083921,0.018793788130833967 +flat_mae,reg,logistic,ppmi_dx,82,0.005994842503189409,test,0.66,0.041199703882431,0.6026180458158018,0.05080271659616854,0.6035653650254669,0.04546293217664128 +flat_mae,reg,logistic,ppmi_dx,83,0.005994842503189409,train,0.7829181494661922,0.015392769779420818,0.7521544245228455,0.018890470271049616,0.7410752515521302,0.017921620620140688 +flat_mae,reg,logistic,ppmi_dx,83,0.005994842503189409,test,0.52,0.04810446964680101,0.47916666666666663,0.04975056095569098,0.48047538200339557,0.04880194708914833 +flat_mae,reg,logistic,ppmi_dx,84,0.005994842503189409,train,0.7846975088967971,0.015600944140881465,0.7538326763031099,0.0194292176767864,0.7425203382573324,0.018476191186015754 +flat_mae,reg,logistic,ppmi_dx,84,0.005994842503189409,test,0.57,0.04618316143357879,0.5174503422735944,0.052023392723662264,0.5207979626485568,0.048730004048073566 +flat_mae,reg,logistic,ppmi_dx,85,0.005994842503189409,train,0.7651245551601423,0.01531799057804568,0.7302792321116929,0.018850132588699244,0.7205362877328195,0.017566649616622288 +flat_mae,reg,logistic,ppmi_dx,85,0.005994842503189409,test,0.68,0.036004133096076606,0.6031746031746031,0.05033178833570285,0.6095076400679117,0.04108333729725875 +flat_mae,reg,logistic,ppmi_dx,86,0.3593813663804626,train,0.9875444839857651,0.005023987242819239,0.9867817578850813,0.005363143935751162,0.9846660244059088,0.006233419449184573 +flat_mae,reg,logistic,ppmi_dx,86,0.3593813663804626,test,0.58,0.04761119196155458,0.5442708333333334,0.05100091933820613,0.5441426146010186,0.04965871881852639 +flat_mae,reg,logistic,ppmi_dx,87,0.005994842503189409,train,0.7526690391459074,0.017097935413310228,0.7163914131054339,0.021020402969727674,0.7078114964675658,0.01955267150393689 +flat_mae,reg,logistic,ppmi_dx,87,0.005994842503189409,test,0.64,0.044795642645239504,0.5792426367461431,0.05470373193254503,0.5823429541595926,0.048649358779436394 +flat_mae,reg,logistic,ppmi_dx,88,0.005994842503189409,train,0.7722419928825622,0.017038828905026938,0.7421463904222525,0.020491301700244227,0.7324047313209163,0.01950761250458331 +flat_mae,reg,logistic,ppmi_dx,88,0.005994842503189409,test,0.64,0.03747039364618419,0.5535714285714286,0.05098712344478414,0.567062818336163,0.04141587416836367 +flat_mae,reg,logistic,ppmi_dx,89,0.005994842503189409,train,0.7526690391459074,0.015704479162701002,0.7155570120341543,0.019353638996313403,0.7069417683579533,0.01793740883038409 +flat_mae,reg,logistic,ppmi_dx,89,0.005994842503189409,test,0.72,0.037846315540617695,0.6600291403593979,0.05263354070721799,0.6570458404074703,0.04456218211612602 +flat_mae,reg,logistic,ppmi_dx,90,0.005994842503189409,train,0.7562277580071174,0.015765323777891787,0.7196497168969723,0.019182133163729114,0.7107016698779705,0.01780830083075481 +flat_mae,reg,logistic,ppmi_dx,90,0.005994842503189409,test,0.69,0.040342905200295126,0.6467236467236468,0.04820229273364632,0.6430390492359932,0.044520192177676075 +flat_mae,reg,logistic,ppmi_dx,91,0.005994842503189409,train,0.7544483985765125,0.015792654481217718,0.7128066121578386,0.020205111058870864,0.7040382145150931,0.018330859573538468 +flat_mae,reg,logistic,ppmi_dx,91,0.005994842503189409,test,0.68,0.040294595171064804,0.6190476190476191,0.05265926153525735,0.6196943972835314,0.04544159027943502 +flat_mae,reg,logistic,ppmi_dx,92,0.005994842503189409,train,0.7615658362989324,0.01589253041980216,0.7228715261422516,0.0201534704668844,0.7132974737743524,0.018575618577706603 +flat_mae,reg,logistic,ppmi_dx,92,0.005994842503189409,test,0.72,0.040977340079609854,0.6783088235294117,0.0501138311373395,0.6723259762308998,0.04645936042282219 +flat_mae,reg,logistic,ppmi_dx,93,0.005994842503189409,train,0.7793594306049823,0.01544446430164782,0.7473644523716303,0.018927708541041283,0.7364456219225005,0.017877364549571288 +flat_mae,reg,logistic,ppmi_dx,93,0.005994842503189409,test,0.58,0.04424811408410532,0.5442708333333334,0.04816688835173655,0.5441426146010186,0.04683554669445004 +flat_mae,reg,logistic,ppmi_dx,94,0.046415888336127774,train,0.8665480427046264,0.013309144186620566,0.8549367951184426,0.014806720121217743,0.8463926354099764,0.015191836027644009 +flat_mae,reg,logistic,ppmi_dx,94,0.046415888336127774,test,0.7,0.04194489718666622,0.6657754010695187,0.048520056537520125,0.6612903225806452,0.04617753866710422 +flat_mae,reg,logistic,ppmi_dx,95,0.005994842503189409,train,0.7704626334519573,0.015639870591152686,0.7375571507694312,0.019266854920547857,0.727480732177264,0.01817907610654874 +flat_mae,reg,logistic,ppmi_dx,95,0.005994842503189409,test,0.63,0.039054321143760784,0.5552350042072365,0.04946181806089218,0.5640916808149405,0.04218734848041521 +flat_mae,reg,logistic,ppmi_dx,96,0.005994842503189409,train,0.7740213523131673,0.015914277207741634,0.7377527437601732,0.02047011012612059,0.7268919931492186,0.0189781108204649 +flat_mae,reg,logistic,ppmi_dx,96,0.005994842503189409,test,0.65,0.04260255391405544,0.6072270227808326,0.048595741777500666,0.6056876061120543,0.04584531272881027 +flat_mae,reg,logistic,ppmi_dx,97,0.005994842503189409,train,0.7669039145907474,0.016308457332783525,0.7342501849946758,0.019992435320534987,0.7245905587668593,0.018908327363086765 +flat_mae,reg,logistic,ppmi_dx,97,0.005994842503189409,test,0.67,0.037430527647897234,0.6033177064551027,0.04843023381731555,0.6065365025466893,0.04132224699183524 +flat_mae,reg,logistic,ppmi_dx,98,0.046415888336127774,train,0.8718861209964412,0.013235872020842667,0.8608910891089109,0.014835072678793047,0.8524673517448084,0.015455570416905788 +flat_mae,reg,logistic,ppmi_dx,98,0.046415888336127774,test,0.61,0.04952686139863902,0.568536342515765,0.05517021841674904,0.5683361629881154,0.05258804308028223 +flat_mae,reg,logistic,ppmi_dx,99,0.005994842503189409,train,0.7686832740213523,0.016113782726093425,0.732780313670412,0.02053714221332322,0.7225567330336116,0.01910311215544916 +flat_mae,reg,logistic,ppmi_dx,99,0.005994842503189409,test,0.66,0.03950139238052248,0.6026180458158018,0.04938583523477659,0.6035653650254669,0.0438495772030738 +flat_mae,reg,logistic,ppmi_dx,100,0.046415888336127774,train,0.8576512455516014,0.013602357828654286,0.8444010687044036,0.015349632562783,0.8348185613359024,0.015789739457557014 +flat_mae,reg,logistic,ppmi_dx,100,0.046415888336127774,test,0.61,0.04690949157686534,0.5920075321686369,0.04891873324298145,0.5938030560271647,0.04969080449024414 diff --git a/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/log.txt b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f3fa40e9c55a9dd6bd91ba14cb802eed6dce8669 --- /dev/null +++ b/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:30:12 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations cross_reg1_pep4; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/eval_v2/ppmi_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:19:00 time: 4.9165 data: 4.1681 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:35 time: 0.2285 data: 0.0827 max mem: 3005 +extract (train) [ 40/232] eta: 0:01:02 time: 0.1933 data: 0.0644 max mem: 3005 +extract (train) [ 60/232] eta: 0:00:49 time: 0.2054 data: 0.0729 max mem: 3005 +extract (train) [ 80/232] eta: 0:00:39 time: 0.1696 data: 0.0555 max mem: 3005 +extract (train) [100/232] eta: 0:00:31 time: 0.1784 data: 0.0595 max mem: 3005 +extract (train) [120/232] eta: 0:00:26 time: 0.2094 data: 0.0770 max mem: 3005 +extract (train) [140/232] eta: 0:00:21 time: 0.1840 data: 0.0607 max mem: 3005 +extract (train) [160/232] eta: 0:00:15 time: 0.1596 data: 0.0511 max mem: 3005 +extract (train) [180/232] eta: 0:00:11 time: 0.1822 data: 0.0625 max mem: 3005 +extract (train) [200/232] eta: 0:00:06 time: 0.1690 data: 0.0563 max mem: 3005 +extract (train) [220/232] eta: 0:00:02 time: 0.1524 data: 0.0457 max mem: 3005 +extract (train) [231/232] eta: 0:00:00 time: 0.1433 data: 0.0416 max mem: 3005 +extract (train) Total time: 0:00:47 (0.2043 s / it) +extract (validation) [ 0/50] eta: 0:02:59 time: 3.5822 data: 3.3811 max mem: 3005 +extract (validation) [20/50] eta: 0:00:11 time: 0.2100 data: 0.0725 max mem: 3005 +extract (validation) [40/50] eta: 0:00:02 time: 0.1440 data: 0.0374 max mem: 3005 +extract (validation) [49/50] eta: 0:00:00 time: 0.1434 data: 0.0395 max mem: 3005 +extract (validation) Total time: 0:00:12 (0.2457 s / it) +extract (test) [ 0/50] eta: 0:02:52 time: 3.4564 data: 3.3262 max mem: 3005 +extract (test) [20/50] eta: 0:00:10 time: 0.1892 data: 0.0602 max mem: 3005 +extract (test) [40/50] eta: 0:00:02 time: 0.1417 data: 0.0373 max mem: 3005 +extract (test) [49/50] eta: 0:00:00 time: 0.1416 data: 0.0379 max mem: 3005 +extract (test) Total time: 0:00:11 (0.2333 s / it) +feature extraction time: 0:01:11 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|----------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | | 0.35938 | train | 0.96619 | 0.0073417 | 0.96399 | 0.0079015 | 0.95964 | 0.0088613 | +| flat_mae | reg | logistic | ppmi_dx | | 0.35938 | test | 0.66 | 0.044403 | 0.61556 | 0.049959 | 0.61304 | 0.047385 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04952145393665255, "f1": 0.5766488413547237, "f1_std": 0.05570788566604609, "bacc": 0.5764006791171477, "bacc_std": 0.05285197280380837} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.042512943911237194, "f1": 0.6570417081535569, "f1_std": 0.04850288626645294, "bacc": 0.6532258064516129, "bacc_std": 0.04650848350253953} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04748983470175486, "f1": 0.625, "f1_std": 0.04898638042359684, "bacc": 0.6281833616298811, "bacc_std": 0.050018224884669185} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.043453883600893486, "f1": 0.6212121212121212, "f1_std": 0.04892343990985682, "bacc": 0.6188455008488964, "bacc_std": 0.04627842002989132} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04642335188243089, "f1": 0.584, "f1_std": 0.049116337642184524, "bacc": 0.583616298811545, "bacc_std": 0.04889873994606864} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.045008172591208366, "f1": 0.5755517826825127, "f1_std": 0.04767560151533296, "bacc": 0.5755517826825127, "bacc_std": 0.04774967770780004} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.05198761006239852, "f1": 0.5626666666666666, "f1_std": 0.053903271421685335, "bacc": 0.5623938879456706, "bacc_std": 0.05356077009907835} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.038251880999501185, "f1": 0.6033177064551027, "f1_std": 0.05010412317671512, "bacc": 0.6065365025466893, "bacc_std": 0.04270222918510206} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.041802100425696306, "f1": 0.66078697421981, "f1_std": 0.04937492808436804, "bacc": 0.6561969439728353, "bacc_std": 0.04633498010277153} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03980280894610328, "f1": 0.6323529411764706, "f1_std": 0.04734298374316082, "bacc": 0.6298811544991512, "bacc_std": 0.04347786473163675} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.0386621209971724, "f1": 0.6428571428571428, "f1_std": 0.05098502038705891, "bacc": 0.6409168081494058, "bacc_std": 0.04405285057483844} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.039616415789417395, "f1": 0.5552350042072365, "f1_std": 0.04976977811400029, "bacc": 0.5640916808149405, "bacc_std": 0.04279524994480864} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04043837781118327, "f1": 0.6176572818908586, "f1_std": 0.049505278046492046, "bacc": 0.616723259762309, "bacc_std": 0.044440226175004795} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.041426677395127884, "f1": 0.587178241864983, "f1_std": 0.053508759064354525, "bacc": 0.5933786078098472, "bacc_std": 0.04533967367777042} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.64, "acc_std": 0.04920162598939186, "f1": 0.6138996138996139, "f1_std": 0.052867099398570455, "bacc": 0.6129032258064516, "bacc_std": 0.05222047395292094} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.047230206436135756, "f1": 0.5670995670995671, "f1_std": 0.04971475761902281, "bacc": 0.5674872665534805, "bacc_std": 0.05015254481354647} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.041532753339984574, "f1": 0.5944849959448499, "f1_std": 0.050738435677190157, "bacc": 0.5955008488964346, "bacc_std": 0.04557578939969868} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04625753992594072, "f1": 0.5481404240528328, "f1_std": 0.0544008819393325, "bacc": 0.5530560271646858, "bacc_std": 0.049157151499731516} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04713444175971536, "f1": 0.6338529134846741, "f1_std": 0.048887575334434705, "bacc": 0.6362478777589134, "bacc_std": 0.049438984069135515} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.0388910015299169, "f1": 0.6408295678368672, "f1_std": 0.04784690609885569, "bacc": 0.6379456706281834, "bacc_std": 0.0431162133886556} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.58, "acc_std": 0.050948958772481304, "f1": 0.5625, "f1_std": 0.05168077808513794, "bacc": 0.564516129032258, "bacc_std": 0.05230847184462766} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.044609613313724206, "f1": 0.609375, "f1_std": 0.04912400208804288, "bacc": 0.6078098471986417, "bacc_std": 0.04808713628012754} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.046667243329770396, "f1": 0.5174503422735944, "f1_std": 0.0516651982911007, "bacc": 0.5207979626485568, "bacc_std": 0.04867921072844272} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04052477760580557, "f1": 0.5714285714285714, "f1_std": 0.05178949157043787, "bacc": 0.5772495755517827, "bacc_std": 0.044480658711372044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.0423787635496837, "f1": 0.6155585707824514, "f1_std": 0.049057775499717994, "bacc": 0.6137521222410866, "bacc_std": 0.04594501629853134} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.046944098670652946, "f1": 0.6515679442508711, "f1_std": 0.04871839696965553, "bacc": 0.652376910016978, "bacc_std": 0.048730132822854044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.63, "acc_std": 0.04517101282902566, "f1": 0.6093337556752191, "f1_std": 0.04748621536234211, "bacc": 0.6099320882852293, "bacc_std": 0.04758811964118473} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04542124612997755, "f1": 0.5793334052421529, "f1_std": 0.049358227021803945, "bacc": 0.5785229202037352, "bacc_std": 0.04831947256779907} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04282277431460974, "f1": 0.6212121212121212, "f1_std": 0.04956577793453368, "bacc": 0.6188455008488964, "bacc_std": 0.046649151394833} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04476613005386997, "f1": 0.612789025334661, "f1_std": 0.05088660069041465, "bacc": 0.6107809847198642, "bacc_std": 0.04868435235916302} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04499367066599479, "f1": 0.6263736263736264, "f1_std": 0.04924443688053769, "bacc": 0.6239388794567062, "bacc_std": 0.04747490708288465} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04896370492517902, "f1": 0.6053333333333333, "f1_std": 0.05197763345449849, "bacc": 0.6048387096774194, "bacc_std": 0.05175542611869431} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04349208663653653, "f1": 0.648, "f1_std": 0.04704471978736863, "bacc": 0.6472835314091681, "bacc_std": 0.04705982646298678} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04220890427386145, "f1": 0.5792763553311696, "f1_std": 0.05373250348313509, "bacc": 0.5853140916808149, "bacc_std": 0.04623485012399437} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.046152664061785205, "f1": 0.609375, "f1_std": 0.049531280657596786, "bacc": 0.6078098471986417, "bacc_std": 0.04818780944897796} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04237177834360979, "f1": 0.5783475783475784, "f1_std": 0.049751963873476676, "bacc": 0.5793718166383701, "bacc_std": 0.04574951571173548} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04098758836526003, "f1": 0.6323529411764706, "f1_std": 0.0502754601510319, "bacc": 0.6298811544991512, "bacc_std": 0.045905204188279036} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.0462192860178519, "f1": 0.6381727725011307, "f1_std": 0.055599192971099866, "bacc": 0.634974533106961, "bacc_std": 0.05183077649144274} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.77, "acc_std": 0.03757873866962542, "f1": 0.7378917378917379, "f1_std": 0.04613124377433619, "bacc": 0.7279286926994907, "bacc_std": 0.04344623652504512} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04150173008441937, "f1": 0.6381727725011307, "f1_std": 0.0485768109610742, "bacc": 0.634974533106961, "bacc_std": 0.04550203467527192} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.046863081418105655, "f1": 0.5670995670995671, "f1_std": 0.049456906049059994, "bacc": 0.5674872665534805, "bacc_std": 0.04967911319493318} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.037565814246466156, "f1": 0.627359057579036, "f1_std": 0.049093141257944325, "bacc": 0.6277589134125636, "bacc_std": 0.04236841224220484} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.043957251961422694, "f1": 0.6349153667441089, "f1_std": 0.05002710084929576, "bacc": 0.6320033955857385, "bacc_std": 0.047981906195953425} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03956994313870062, "f1": 0.6640018537828757, "f1_std": 0.04984818533800049, "bacc": 0.6591680814940577, "bacc_std": 0.04562450990858954} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04339888938671126, "f1": 0.6043956043956044, "f1_std": 0.04892066734387949, "bacc": 0.6027164685908319, "bacc_std": 0.047055988840898344} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04548582196685029, "f1": 0.554367201426025, "f1_std": 0.051189771955055106, "bacc": 0.5551782682512734, "bacc_std": 0.048346685057663735} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.0463227978429628, "f1": 0.6567996567996568, "f1_std": 0.05022535010981531, "bacc": 0.6553480475382003, "bacc_std": 0.05000628708804277} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04258624660615208, "f1": 0.6604414261460102, "f1_std": 0.045697233310599945, "bacc": 0.6604414261460102, "bacc_std": 0.045993346542883236} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.04440477001404241, "f1": 0.5960257670051315, "f1_std": 0.048539035858431744, "bacc": 0.5946519524617997, "bacc_std": 0.046928429739255456} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04358081688082498, "f1": 0.6259934548854604, "f1_std": 0.053290821013731386, "bacc": 0.6247877758913413, "bacc_std": 0.04799134062991036} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.046782543752985475, "f1": 0.5604395604395604, "f1_std": 0.05206210957966023, "bacc": 0.5602716468590832, "bacc_std": 0.0499030406795085} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04147721784305211, "f1": 0.5476190476190476, "f1_std": 0.05202129968933117, "bacc": 0.5560271646859083, "bacc_std": 0.044943089705938785} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.044437547187035416, "f1": 0.6296711929076422, "f1_std": 0.052340102989190326, "bacc": 0.6269100169779287, "bacc_std": 0.04900492040947786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.52, "acc_std": 0.049476180127410806, "f1": 0.47916666666666663, "f1_std": 0.050753703311144774, "bacc": 0.48047538200339557, "bacc_std": 0.04974930776591758} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.0459750193039655, "f1": 0.6816638370118846, "f1_std": 0.04892094962197341, "bacc": 0.6816638370118846, "bacc_std": 0.0492911065579874} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.3593813663804626, "split": "test", "acc": 0.66, "acc_std": 0.04482450668997931, "f1": 0.6212121212121212, "f1_std": 0.05136192482623712, "bacc": 0.6188455008488964, "bacc_std": 0.04847634472510594} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.03589078433247175, "f1": 0.6279761904761905, "f1_std": 0.051434727664473844, "bacc": 0.6307300509337861, "bacc_std": 0.04217535408627037} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.045095538581992785, "f1": 0.6527777777777778, "f1_std": 0.04935318106516789, "bacc": 0.6502546689303905, "bacc_std": 0.0483268639717604} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04474855975335966, "f1": 0.5477159656264134, "f1_std": 0.05119401115158754, "bacc": 0.5500848896434635, "bacc_std": 0.047362123617635005} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.04691215194381942, "f1": 0.6041666666666667, "f1_std": 0.048720763946501544, "bacc": 0.6069609507640068, "bacc_std": 0.04974894917076368} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04849020932105779, "f1": 0.6006725514922235, "f1_std": 0.0502734410567677, "bacc": 0.6018675721561969, "bacc_std": 0.050773908181167685} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.03884250764304489, "f1": 0.5628946090335114, "f1_std": 0.05204937973888966, "bacc": 0.5721561969439728, "bacc_std": 0.04306117763449482} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04641349372757883, "f1": 0.5626666666666666, "f1_std": 0.04927385899265517, "bacc": 0.5623938879456706, "bacc_std": 0.04900298540760564} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.03780928986373588, "f1": 0.5706048337627285, "f1_std": 0.050338524091829664, "bacc": 0.580220713073005, "bacc_std": 0.04162860072755914} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.56, "acc_std": 0.053153453321491725, "f1": 0.548440065681445, "f1_std": 0.0527324899775548, "bacc": 0.5534804753820034, "bacc_std": 0.05373496745197361} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04627436007121006, "f1": 0.5783475783475784, "f1_std": 0.05370757138761157, "bacc": 0.5793718166383701, "bacc_std": 0.049404911478270294} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.0472139809802139, "f1": 0.6392190152801358, "f1_std": 0.049597395570738355, "bacc": 0.6392190152801358, "bacc_std": 0.04984311709279077} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.62, "acc_std": 0.048023094444235886, "f1": 0.5967741935483871, "f1_std": 0.051066673003096655, "bacc": 0.5967741935483871, "bacc_std": 0.05107152530226998} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04654234630957059, "f1": 0.6816638370118846, "f1_std": 0.04890278307229904, "bacc": 0.6816638370118846, "bacc_std": 0.04908577443480196} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04618283663873409, "f1": 0.5960257670051315, "f1_std": 0.049273163190097696, "bacc": 0.5946519524617997, "bacc_std": 0.04773374148106287} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.0428500828470611, "f1": 0.5404411764705883, "f1_std": 0.04841306538733922, "bacc": 0.5449915110356536, "bacc_std": 0.044339851278983496} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04541460558014349, "f1": 0.6263736263736264, "f1_std": 0.050542036970551305, "bacc": 0.6239388794567062, "bacc_std": 0.04866957530586481} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04781020393179682, "f1": 0.5960257670051315, "f1_std": 0.05258587321606418, "bacc": 0.5946519524617997, "bacc_std": 0.05083774064797116} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.042292746422997886, "f1": 0.5623386825272135, "f1_std": 0.04762133400508143, "bacc": 0.5632427843803056, "bacc_std": 0.04468843244886258} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.51, "acc_std": 0.05187116347258851, "f1": 0.4873940788785438, "f1_std": 0.05282956812806291, "bacc": 0.4876910016977929, "bacc_std": 0.05337798938629218} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04238331747279818, "f1": 0.6657754010695187, "f1_std": 0.04896676833620426, "bacc": 0.6612903225806452, "bacc_std": 0.046813549024006626} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 21.54434690031882, "split": "test", "acc": 0.59, "acc_std": 0.044350508452553276, "f1": 0.5805626598465473, "f1_std": 0.0447204986814865, "bacc": 0.5878607809847198, "bacc_std": 0.046484589101169635} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03718633620027656, "f1": 0.6031746031746031, "f1_std": 0.05182348695731351, "bacc": 0.6095076400679117, "bacc_std": 0.042340320073538815} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.72, "acc_std": 0.041675791534174854, "f1": 0.6961805555555556, "f1_std": 0.04568123076118576, "bacc": 0.6926994906621392, "bacc_std": 0.04481411112192359} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.66, "acc_std": 0.04798937799138472, "f1": 0.6486151302190988, "f1_std": 0.04860121661326754, "bacc": 0.6544991511035654, "bacc_std": 0.04927056671347943} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.73, "acc_std": 0.03684896742108251, "f1": 0.6871741397288842, "f1_std": 0.04557341404072206, "bacc": 0.6803904923599321, "bacc_std": 0.04163695263669992} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.041199703882431, "f1": 0.6026180458158018, "f1_std": 0.05080271659616854, "bacc": 0.6035653650254669, "bacc_std": 0.04546293217664128} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.52, "acc_std": 0.04810446964680101, "f1": 0.47916666666666663, "f1_std": 0.04975056095569098, "bacc": 0.48047538200339557, "bacc_std": 0.04880194708914833} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.04618316143357879, "f1": 0.5174503422735944, "f1_std": 0.052023392723662264, "bacc": 0.5207979626485568, "bacc_std": 0.048730004048073566} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.036004133096076606, "f1": 0.6031746031746031, "f1_std": 0.05033178833570285, "bacc": 0.6095076400679117, "bacc_std": 0.04108333729725875} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04761119196155458, "f1": 0.5442708333333334, "f1_std": 0.05100091933820613, "bacc": 0.5441426146010186, "bacc_std": 0.04965871881852639} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.044795642645239504, "f1": 0.5792426367461431, "f1_std": 0.05470373193254503, "bacc": 0.5823429541595926, "bacc_std": 0.048649358779436394} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.03747039364618419, "f1": 0.5535714285714286, "f1_std": 0.05098712344478414, "bacc": 0.567062818336163, "bacc_std": 0.04141587416836367} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.037846315540617695, "f1": 0.6600291403593979, "f1_std": 0.05263354070721799, "bacc": 0.6570458404074703, "bacc_std": 0.04456218211612602} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.040342905200295126, "f1": 0.6467236467236468, "f1_std": 0.04820229273364632, "bacc": 0.6430390492359932, "bacc_std": 0.044520192177676075} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.040294595171064804, "f1": 0.6190476190476191, "f1_std": 0.05265926153525735, "bacc": 0.6196943972835314, "bacc_std": 0.04544159027943502} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.72, "acc_std": 0.040977340079609854, "f1": 0.6783088235294117, "f1_std": 0.0501138311373395, "bacc": 0.6723259762308998, "bacc_std": 0.04645936042282219} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04424811408410532, "f1": 0.5442708333333334, "f1_std": 0.04816688835173655, "bacc": 0.5441426146010186, "bacc_std": 0.04683554669445004} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04194489718666622, "f1": 0.6657754010695187, "f1_std": 0.048520056537520125, "bacc": 0.6612903225806452, "bacc_std": 0.04617753866710422} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.039054321143760784, "f1": 0.5552350042072365, "f1_std": 0.04946181806089218, "bacc": 0.5640916808149405, "bacc_std": 0.04218734848041521} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04260255391405544, "f1": 0.6072270227808326, "f1_std": 0.048595741777500666, "bacc": 0.6056876061120543, "bacc_std": 0.04584531272881027} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.037430527647897234, "f1": 0.6033177064551027, "f1_std": 0.04843023381731555, "bacc": 0.6065365025466893, "bacc_std": 0.04132224699183524} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04952686139863902, "f1": 0.568536342515765, "f1_std": 0.05517021841674904, "bacc": 0.5683361629881154, "bacc_std": 0.05258804308028223} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03950139238052248, "f1": 0.6026180458158018, "f1_std": 0.04938583523477659, "bacc": 0.6035653650254669, "bacc_std": 0.0438495772030738} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04690949157686534, "f1": 0.5920075321686369, "f1_std": 0.04891873324298145, "bacc": 0.5938030560271647, "bacc_std": 0.04969080449024414} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | train | 100 | 13.997 | 129.12 | 0.84418 | 0.088309 | 0.82322 | 0.10287 | 0.81555 | 0.10595 | +| flat_mae | reg | logistic | ppmi_dx | test | 100 | 13.997 | 129.12 | 0.6449 | 0.046308 | 0.60341 | 0.047062 | 0.60392 | 0.044913 | + + +done! total time: 0:05:12 diff --git a/decoders/cross_reg1_pep4/pretrain/config.yaml b/decoders/cross_reg1_pep4/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b99b89974aba62fd5cf52e1be8465d6e8189e1bb --- /dev/null +++ b/decoders/cross_reg1_pep4/pretrain/config.yaml @@ -0,0 +1,100 @@ +name: decoders/cross_reg1_pep4/pretrain +notes: decoder ablations cross_reg1_pep4 (model_kwargs.decoding=cross model_kwargs.reg_tokens=1 + model_kwargs.pred_edge_pad=4) +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: cross + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 4 + class_token: false + reg_tokens: 1 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/decoders/cross_reg1_pep4/pretrain/log.json b/decoders/cross_reg1_pep4/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..79cae65691ef9f93dd043efdbe1df2ccd68359d2 --- /dev/null +++ b/decoders/cross_reg1_pep4/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.043306161762028936, "train/loss": 0.9940133341789246, "eval/hcp-train-subset/loss": 0.9921385165183775, "eval/hcp-val/loss": 0.9911508694771798} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.06954341174930334, "train/loss": 0.9898502607536316, "eval/hcp-train-subset/loss": 0.9923523212632825, "eval/hcp-val/loss": 0.9901730514341786} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.11286997924726958, "train/loss": 0.9863783397293091, "eval/hcp-train-subset/loss": 0.9843246292683386, "eval/hcp-val/loss": 0.9814443924734669} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.2135762106272408, "train/loss": 0.9723050631427765, "eval/hcp-train-subset/loss": 0.9608782481762671, "eval/hcp-val/loss": 0.9567078063564916} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.22277176788341488, "train/loss": 0.9392080404376983, "eval/hcp-train-subset/loss": 0.9316647014310283, "eval/hcp-val/loss": 0.9265559661772943} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.14793895895225975, "train/loss": 0.9200997159385681, "eval/hcp-train-subset/loss": 0.9172237323176476, "eval/hcp-val/loss": 0.9117579508212305} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.10929266933651614, "train/loss": 0.9080339381408692, "eval/hcp-train-subset/loss": 0.9097109898444145, "eval/hcp-val/loss": 0.903834339111082} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.08871609552986395, "train/loss": 0.9020696842288971, "eval/hcp-train-subset/loss": 0.9048098114229017, "eval/hcp-val/loss": 0.8993943766240151} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.07687517543858036, "train/loss": 0.8974671233081818, "eval/hcp-train-subset/loss": 0.9019980074897889, "eval/hcp-val/loss": 0.8965724091376027} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.06992403422058306, "train/loss": 0.8952614644813538, "eval/hcp-train-subset/loss": 0.8988527107623315, "eval/hcp-val/loss": 0.8941772176373389} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.06862875966381145, "train/loss": 0.891781220998764, "eval/hcp-train-subset/loss": 0.8977469600016071, "eval/hcp-val/loss": 0.8925889615089663} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.06513536432100728, "train/loss": 0.8914334305095672, "eval/hcp-train-subset/loss": 0.8960292743098351, "eval/hcp-val/loss": 0.8916244795245509} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.06283860048599695, "train/loss": 0.8897771519374847, "eval/hcp-train-subset/loss": 0.8954159665492273, "eval/hcp-val/loss": 0.891025992170457} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.06476476678038051, "train/loss": 0.8869076965999604, "eval/hcp-train-subset/loss": 0.8950686714341564, "eval/hcp-val/loss": 0.8894112312024639} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.06327737117705297, "train/loss": 0.8868895906257629, "eval/hcp-train-subset/loss": 0.893605770603303, "eval/hcp-val/loss": 0.889106604360765} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.06335866753783, "train/loss": 0.884539160490036, "eval/hcp-train-subset/loss": 0.8935203369586698, "eval/hcp-val/loss": 0.889762798624654} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.06448445029665249, "train/loss": 0.8821574166965485, "eval/hcp-train-subset/loss": 0.8923897416360916, "eval/hcp-val/loss": 0.8892756710129399} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.06423828506233102, "train/loss": 0.8824474250030517, "eval/hcp-train-subset/loss": 0.8929197663261045, "eval/hcp-val/loss": 0.8901180663416463} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.0665373995772539, "train/loss": 0.8799967945766449, "eval/hcp-train-subset/loss": 0.8923428414329406, "eval/hcp-val/loss": 0.8885486010582216} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.06636518796175303, "train/loss": 0.8794410348987579, "eval/hcp-train-subset/loss": 0.8921154583654096, "eval/hcp-val/loss": 0.8888944022117122} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.06659177786948263, "train/loss": 0.8780322789096833, "eval/hcp-train-subset/loss": 0.8915032927067049, "eval/hcp-val/loss": 0.8890020030160104} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.06793315671074292, "train/loss": 0.8768888520050049, "eval/hcp-train-subset/loss": 0.8916240622920375, "eval/hcp-val/loss": 0.8879840393220225} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.07005295446607619, "train/loss": 0.8768345392990112, "eval/hcp-train-subset/loss": 0.8910557060472427, "eval/hcp-val/loss": 0.8876338101202442} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.070849089697063, "train/loss": 0.8759080522823334, "eval/hcp-train-subset/loss": 0.8931887342083838, "eval/hcp-val/loss": 0.8894934510031054} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.06889484462624781, "train/loss": 0.876193526468277, "eval/hcp-train-subset/loss": 0.8906047257684893, "eval/hcp-val/loss": 0.8880214931503418} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.06982916323532194, "train/loss": 0.8763540645408631, "eval/hcp-train-subset/loss": 0.8912051050893722, "eval/hcp-val/loss": 0.8874043351219546} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.06984771985625655, "train/loss": 0.8751276171779633, "eval/hcp-train-subset/loss": 0.8911552506108438, "eval/hcp-val/loss": 0.8890150122104152} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.07196085473571145, "train/loss": 0.8740874133586883, "eval/hcp-train-subset/loss": 0.890996209075374, "eval/hcp-val/loss": 0.8880120025527093} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.07188932318121156, "train/loss": 0.8726560315418244, "eval/hcp-train-subset/loss": 0.8917730912085502, "eval/hcp-val/loss": 0.8873988572628267} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.07377448534181219, "train/loss": 0.8722468136501312, "eval/hcp-train-subset/loss": 0.8892336391633556, "eval/hcp-val/loss": 0.887601766855486} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.07445251421463914, "train/loss": 0.872215450258255, "eval/hcp-train-subset/loss": 0.8887121206329714, "eval/hcp-val/loss": 0.886069118976593} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.07562959380805608, "train/loss": 0.8711133451080322, "eval/hcp-train-subset/loss": 0.8903548304111727, "eval/hcp-val/loss": 0.8887589939178959} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.07465894645691509, "train/loss": 0.8720420664787293, "eval/hcp-train-subset/loss": 0.8894342078316596, "eval/hcp-val/loss": 0.8876929571551662} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.07340978934082576, "train/loss": 0.8711733764076233, "eval/hcp-train-subset/loss": 0.8915024995803833, "eval/hcp-val/loss": 0.8876803353909524} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.07716968491084387, "train/loss": 0.8671901398944855, "eval/hcp-train-subset/loss": 0.8919991235579213, "eval/hcp-val/loss": 0.887235160796873} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.07747537247706589, "train/loss": 0.8698895174980164, "eval/hcp-train-subset/loss": 0.8884254251756976, "eval/hcp-val/loss": 0.8849316393175433} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.07662650975064028, "train/loss": 0.8681293442153931, "eval/hcp-train-subset/loss": 0.8915586529239532, "eval/hcp-val/loss": 0.8868103690685765} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.0792997460725862, "train/loss": 0.8677192155647278, "eval/hcp-train-subset/loss": 0.8889321271450289, "eval/hcp-val/loss": 0.8867482466082419} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.07595448505798791, "train/loss": 0.8705833373069763, "eval/hcp-train-subset/loss": 0.891109541539223, "eval/hcp-val/loss": 0.8866473532492115} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.07919467120012805, "train/loss": 0.8677849683189393, "eval/hcp-train-subset/loss": 0.8891933502689484, "eval/hcp-val/loss": 0.8863930538777383} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.08086913076519164, "train/loss": 0.8648072817993164, "eval/hcp-train-subset/loss": 0.8888222536733074, "eval/hcp-val/loss": 0.8843746887099359} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.08091696951200204, "train/loss": 0.8672370420265197, "eval/hcp-train-subset/loss": 0.8889781928831532, "eval/hcp-val/loss": 0.8860026578749379} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.08119071996085127, "train/loss": 0.8664438168048859, "eval/hcp-train-subset/loss": 0.8897403478622437, "eval/hcp-val/loss": 0.8863979991405241} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.07942633046430932, "train/loss": 0.8683908218765258, "eval/hcp-train-subset/loss": 0.8899700189790418, "eval/hcp-val/loss": 0.8879293011080834} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.0781357786232793, "train/loss": 0.8689384023761749, "eval/hcp-train-subset/loss": 0.8886375138836522, "eval/hcp-val/loss": 0.8868138520948349} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.08318433725983691, "train/loss": 0.8671080866146088, "eval/hcp-train-subset/loss": 0.8874628255444188, "eval/hcp-val/loss": 0.8859278703889539} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.07887973966763835, "train/loss": 0.8670050387763977, "eval/hcp-train-subset/loss": 0.8870970251098755, "eval/hcp-val/loss": 0.8850756912462173} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.08316350319195019, "train/loss": 0.8659486721038818, "eval/hcp-train-subset/loss": 0.8856797583641545, "eval/hcp-val/loss": 0.8847308764534612} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.08181000302517549, "train/loss": 0.8665114564800263, "eval/hcp-train-subset/loss": 0.8888004893256772, "eval/hcp-val/loss": 0.8857618676077935} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.08568808740583042, "train/loss": 0.8650277279090881, "eval/hcp-train-subset/loss": 0.88465212718133, "eval/hcp-val/loss": 0.8845954393186877} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.08463824700585611, "train/loss": 0.8659415705013275, "eval/hcp-train-subset/loss": 0.8865013507104689, "eval/hcp-val/loss": 0.8848219811916351} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.08581732149331765, "train/loss": 0.8634485957717896, "eval/hcp-train-subset/loss": 0.8838689625263214, "eval/hcp-val/loss": 0.8839333528472532} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.08608693851994975, "train/loss": 0.8660673032569886, "eval/hcp-train-subset/loss": 0.8869743606736583, "eval/hcp-val/loss": 0.8846564494794414} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.0899801711252534, "train/loss": 0.8631664330005646, "eval/hcp-train-subset/loss": 0.8828688658052876, "eval/hcp-val/loss": 0.8839305908449234} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.08823744714622672, "train/loss": 0.864900225906372, "eval/hcp-train-subset/loss": 0.8835109203092514, "eval/hcp-val/loss": 0.8839397113169393} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.09009814977338215, "train/loss": 0.8636086104774475, "eval/hcp-train-subset/loss": 0.8806020992417489, "eval/hcp-val/loss": 0.8832819500277119} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.09038908787075282, "train/loss": 0.8613414632987976, "eval/hcp-train-subset/loss": 0.8829087095875894, "eval/hcp-val/loss": 0.8833243529642781} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.0934141091531289, "train/loss": 0.8604634160041809, "eval/hcp-train-subset/loss": 0.8851900456413146, "eval/hcp-val/loss": 0.8826351550317579} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.09313110022825903, "train/loss": 0.863337167520523, "eval/hcp-train-subset/loss": 0.8833682633215382, "eval/hcp-val/loss": 0.8831537769686791} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.09633339347053085, "train/loss": 0.861639887828827, "eval/hcp-train-subset/loss": 0.8832691292608937, "eval/hcp-val/loss": 0.8834188907377182} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.09541177970336517, "train/loss": 0.8620720400524139, "eval/hcp-train-subset/loss": 0.8850571378584831, "eval/hcp-val/loss": 0.8834474692421574} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.09432539860294624, "train/loss": 0.8628071301841735, "eval/hcp-train-subset/loss": 0.8834527875146558, "eval/hcp-val/loss": 0.8822724386568992} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.09647434509483188, "train/loss": 0.8628229555702209, "eval/hcp-train-subset/loss": 0.8824947466773372, "eval/hcp-val/loss": 0.8813663240401975} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.0960352402866106, "train/loss": 0.8625036385440826, "eval/hcp-train-subset/loss": 0.8829072329305834, "eval/hcp-val/loss": 0.8823726725193762} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.09767381925608071, "train/loss": 0.8626319232463837, "eval/hcp-train-subset/loss": 0.8800202358153558, "eval/hcp-val/loss": 0.8800727907688387} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.1005918336906989, "train/loss": 0.8608205287742615, "eval/hcp-train-subset/loss": 0.8816171740331957, "eval/hcp-val/loss": 0.882846716911562} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.10223560099930826, "train/loss": 0.8602278140735626, "eval/hcp-train-subset/loss": 0.880116730928421, "eval/hcp-val/loss": 0.8809640138379989} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.10158883497505311, "train/loss": 0.8605931257534027, "eval/hcp-train-subset/loss": 0.8806551012300676, "eval/hcp-val/loss": 0.8820013115482945} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.10312082382088683, "train/loss": 0.8601891228485108, "eval/hcp-train-subset/loss": 0.8800525828715293, "eval/hcp-val/loss": 0.8808435980350741} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.10367849776604798, "train/loss": 0.8590990263271332, "eval/hcp-train-subset/loss": 0.8782193545372255, "eval/hcp-val/loss": 0.8812499065552989} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.1070010403413254, "train/loss": 0.8601598036670685, "eval/hcp-train-subset/loss": 0.8796307540708973, "eval/hcp-val/loss": 0.8792033801155705} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.10791317328379016, "train/loss": 0.8582571671676635, "eval/hcp-train-subset/loss": 0.8788712880303783, "eval/hcp-val/loss": 0.8799680298374545} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.11058794101662917, "train/loss": 0.8586054766654968, "eval/hcp-train-subset/loss": 0.8751182796493653, "eval/hcp-val/loss": 0.880316335347391} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.1124757065455475, "train/loss": 0.8582432020187378, "eval/hcp-train-subset/loss": 0.8756452270092503, "eval/hcp-val/loss": 0.8789390748546969} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.11143809240001341, "train/loss": 0.8611468462848664, "eval/hcp-train-subset/loss": 0.8768046834776478, "eval/hcp-val/loss": 0.8806307969554779} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.1119084063423714, "train/loss": 0.8596553239727021, "eval/hcp-train-subset/loss": 0.8762192014724978, "eval/hcp-val/loss": 0.8799852094342632} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.11218745883246561, "train/loss": 0.8607033846473694, "eval/hcp-train-subset/loss": 0.8743539202597833, "eval/hcp-val/loss": 0.8791931511894349} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.11605067233997426, "train/loss": 0.8595169685173034, "eval/hcp-train-subset/loss": 0.8749527104439274, "eval/hcp-val/loss": 0.8800167729777675} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.11592065297823194, "train/loss": 0.8598840094566346, "eval/hcp-train-subset/loss": 0.8740097889977116, "eval/hcp-val/loss": 0.8778418908196111} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.11967558563816887, "train/loss": 0.8597984107780456, "eval/hcp-train-subset/loss": 0.8740351065512626, "eval/hcp-val/loss": 0.8787233089247057} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.11948584944482152, "train/loss": 0.8618408188629151, "eval/hcp-train-subset/loss": 0.873308144269451, "eval/hcp-val/loss": 0.8784183850211482} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.12160484458674008, "train/loss": 0.8586058914470672, "eval/hcp-train-subset/loss": 0.8716486019472922, "eval/hcp-val/loss": 0.8775878077553164} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.12352818923557933, "train/loss": 0.8583797931194306, "eval/hcp-train-subset/loss": 0.8703485092809123, "eval/hcp-val/loss": 0.8782493587463133} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.12565030243410494, "train/loss": 0.8569268985271454, "eval/hcp-train-subset/loss": 0.8689413541747678, "eval/hcp-val/loss": 0.8773704969113872} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.12411732991645388, "train/loss": 0.8595782253456116, "eval/hcp-train-subset/loss": 0.8697737436140737, "eval/hcp-val/loss": 0.8774456468320662} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.12174403784770664, "train/loss": 0.8627467006492615, "eval/hcp-train-subset/loss": 0.8690292402621238, "eval/hcp-val/loss": 0.8766259983662636} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.12395254011743446, "train/loss": 0.8612383444309235, "eval/hcp-train-subset/loss": 0.8689470012341777, "eval/hcp-val/loss": 0.8772857256474034} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.12413888540781949, "train/loss": 0.8626029651355743, "eval/hcp-train-subset/loss": 0.8682481781128915, "eval/hcp-val/loss": 0.8755524254614307} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.1277006613509558, "train/loss": 0.8616526491355896, "eval/hcp-train-subset/loss": 0.8676149220235886, "eval/hcp-val/loss": 0.8756335358465871} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.12523877537568245, "train/loss": 0.8611980452060699, "eval/hcp-train-subset/loss": 0.8669056229053005, "eval/hcp-val/loss": 0.8752503712331096} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.1296798395679813, "train/loss": 0.8608626853847504, "eval/hcp-train-subset/loss": 0.866668886715366, "eval/hcp-val/loss": 0.8757733279658902} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.13008514772766722, "train/loss": 0.861338548746109, "eval/hcp-train-subset/loss": 0.8658544642309989, "eval/hcp-val/loss": 0.8749369219426186} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.12982412875509652, "train/loss": 0.8615646265029907, "eval/hcp-train-subset/loss": 0.8655219126132226, "eval/hcp-val/loss": 0.8747214549972165} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.13198649369492632, "train/loss": 0.8625209360980988, "eval/hcp-train-subset/loss": 0.8640454786439096, "eval/hcp-val/loss": 0.8741124983756773} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.13275415393146245, "train/loss": 0.8611412787246704, "eval/hcp-train-subset/loss": 0.8642505022787279, "eval/hcp-val/loss": 0.8745067677190227} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.1322341851463113, "train/loss": 0.8626681216812134, "eval/hcp-train-subset/loss": 0.864095808998231, "eval/hcp-val/loss": 0.874066557615034} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.1336915301839927, "train/loss": 0.8625738585472107, "eval/hcp-train-subset/loss": 0.8637164023614698, "eval/hcp-val/loss": 0.8741012523251195} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.13708263491703707, "train/loss": 0.8635443865013123, "eval/hcp-train-subset/loss": 0.8635885273256609, "eval/hcp-val/loss": 0.8734150019384199} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.13270402630713246, "train/loss": 0.8656090934467315, "eval/hcp-train-subset/loss": 0.8633416804575151, "eval/hcp-val/loss": 0.8741086586829154} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.13580701028255604, "train/loss": 0.8648015269374847, "eval/hcp-train-subset/loss": 0.8633236000614781, "eval/hcp-val/loss": 0.873481749526916} diff --git a/decoders/cross_reg1_pep4/pretrain/log.txt b/decoders/cross_reg1_pep4/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e21c0a652acb0667e60e20072e1443fb4e2fecc9 --- /dev/null +++ b/decoders/cross_reg1_pep4/pretrain/log.txt @@ -0,0 +1,7775 @@ +pretraining fmri mae +start: 2026-01-16 00:35:13 +cwd: /admin/home/connor/fmri-fm +sha: 2aed6b255d374bef42df4612ad8a0584663a3c8f, status: has uncommitted changes, branch: dev/clane9 +config: +name: decoders/cross_reg1_pep4/pretrain +notes: decoder ablations cross_reg1_pep4 (model_kwargs.decoding=cross model_kwargs.reg_tokens=1 + model_kwargs.pred_edge_pad=4) +output_dir: experiments/decoders/output/decoders/cross_reg1_pep4/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: cross + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 4 + class_token: false + reg_tokens: 1 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +val transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=cross, t_pred_stride=2, pred_edge_pad=4, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=True, class_token=False, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Identity() + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=768, out_features=512, bias=True) + (v): Linear(in_features=768, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 100.4M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 9:51:11 lr: 0.000000 grad: 0.0183 (0.0183) loss: 0.9948 (0.9948) time: 5.6755 data: 3.9977 max mem: 7454 +Train: [0] [ 100/6250] eta: 0:18:06 lr: 0.000000 grad: 0.0165 (0.0174) loss: 0.9957 (0.9958) time: 0.1253 data: 0.0529 max mem: 8290 +Train: [0] [ 200/6250] eta: 0:15:43 lr: 0.000001 grad: 0.0146 (0.0165) loss: 0.9957 (0.9958) time: 0.1249 data: 0.0408 max mem: 8292 +Train: [0] [ 300/6250] eta: 0:14:48 lr: 0.000001 grad: 0.0139 (0.0158) loss: 0.9956 (0.9957) time: 0.1102 data: 0.0317 max mem: 8292 +Train: [0] [ 400/6250] eta: 0:14:12 lr: 0.000002 grad: 0.0139 (0.0154) loss: 0.9953 (0.9957) time: 0.1363 data: 0.0448 max mem: 8292 +Train: [0] [ 500/6250] eta: 0:13:35 lr: 0.000002 grad: 0.0140 (0.0151) loss: 0.9961 (0.9957) time: 0.1299 data: 0.0432 max mem: 8292 +Train: [0] [ 600/6250] eta: 0:13:06 lr: 0.000002 grad: 0.0139 (0.0150) loss: 0.9956 (0.9957) time: 0.1222 data: 0.0407 max mem: 8292 +Train: [0] [ 700/6250] eta: 0:12:42 lr: 0.000003 grad: 0.0139 (0.0149) loss: 0.9960 (0.9957) time: 0.1467 data: 0.0586 max mem: 8292 +Train: [0] [ 800/6250] eta: 0:12:37 lr: 0.000003 grad: 0.0141 (0.0148) loss: 0.9957 (0.9957) time: 0.1563 data: 0.0789 max mem: 8292 +Train: [0] [ 900/6250] eta: 0:12:33 lr: 0.000004 grad: 0.0141 (0.0148) loss: 0.9963 (0.9957) time: 0.1442 data: 0.0705 max mem: 8292 +Train: [0] [1000/6250] eta: 0:12:44 lr: 0.000004 grad: 0.0142 (0.0147) loss: 0.9959 (0.9957) time: 0.2802 data: 0.2108 max mem: 8292 +Train: [0] [1100/6250] eta: 0:12:36 lr: 0.000004 grad: 0.0141 (0.0147) loss: 0.9958 (0.9957) time: 0.1719 data: 0.1054 max mem: 8292 +Train: [0] [1200/6250] eta: 0:12:28 lr: 0.000005 grad: 0.0147 (0.0146) loss: 0.9949 (0.9957) time: 0.1513 data: 0.0747 max mem: 8292 +Train: [0] [1300/6250] eta: 0:12:15 lr: 0.000005 grad: 0.0149 (0.0146) loss: 0.9955 (0.9957) time: 0.1506 data: 0.0794 max mem: 8292 +Train: [0] [1400/6250] eta: 0:12:06 lr: 0.000006 grad: 0.0148 (0.0146) loss: 0.9959 (0.9957) time: 0.1685 data: 0.0948 max mem: 8292 +Train: [0] [1500/6250] eta: 0:11:57 lr: 0.000006 grad: 0.0146 (0.0146) loss: 0.9955 (0.9957) time: 0.1948 data: 0.1183 max mem: 8292 +Train: [0] [1600/6250] eta: 0:11:38 lr: 0.000006 grad: 0.0146 (0.0146) loss: 0.9957 (0.9957) time: 0.1424 data: 0.0698 max mem: 8292 +Train: [0] [1700/6250] eta: 0:11:20 lr: 0.000007 grad: 0.0135 (0.0146) loss: 0.9961 (0.9957) time: 0.1486 data: 0.0693 max mem: 8292 +Train: [0] [1800/6250] eta: 0:11:03 lr: 0.000007 grad: 0.0151 (0.0146) loss: 0.9959 (0.9957) time: 0.1526 data: 0.0798 max mem: 8292 +Train: [0] [1900/6250] eta: 0:10:48 lr: 0.000008 grad: 0.0164 (0.0147) loss: 0.9960 (0.9957) time: 0.1884 data: 0.1155 max mem: 8292 +Train: [0] [2000/6250] eta: 0:10:28 lr: 0.000008 grad: 0.0174 (0.0148) loss: 0.9950 (0.9957) time: 0.1318 data: 0.0505 max mem: 8292 +Train: [0] [2100/6250] eta: 0:10:11 lr: 0.000008 grad: 0.0217 (0.0151) loss: 0.9962 (0.9957) time: 0.1213 data: 0.0465 max mem: 8292 +Train: [0] [2200/6250] eta: 0:09:56 lr: 0.000009 grad: 0.0223 (0.0155) loss: 0.9952 (0.9957) time: 0.1518 data: 0.0752 max mem: 8292 +Train: [0] [2300/6250] eta: 0:09:40 lr: 0.000009 grad: 0.0242 (0.0161) loss: 0.9955 (0.9957) time: 0.1347 data: 0.0640 max mem: 8292 +Train: [0] [2400/6250] eta: 0:09:24 lr: 0.000010 grad: 0.0355 (0.0169) loss: 0.9953 (0.9956) time: 0.1443 data: 0.0648 max mem: 8292 +Train: [0] [2500/6250] eta: 0:09:09 lr: 0.000010 grad: 0.0392 (0.0177) loss: 0.9947 (0.9956) time: 0.1534 data: 0.0789 max mem: 8292 +Train: [0] [2600/6250] eta: 0:08:53 lr: 0.000010 grad: 0.0474 (0.0187) loss: 0.9934 (0.9956) time: 0.1354 data: 0.0630 max mem: 8292 +Train: [0] [2700/6250] eta: 0:08:38 lr: 0.000011 grad: 0.0535 (0.0198) loss: 0.9938 (0.9955) time: 0.1522 data: 0.0713 max mem: 8292 +Train: [0] [2800/6250] eta: 0:08:22 lr: 0.000011 grad: 0.0416 (0.0208) loss: 0.9949 (0.9955) time: 0.1441 data: 0.0655 max mem: 8292 +Train: [0] [2900/6250] eta: 0:08:12 lr: 0.000012 grad: 0.0521 (0.0219) loss: 0.9947 (0.9955) time: 0.2133 data: 0.1328 max mem: 8292 +Train: [0] [3000/6250] eta: 0:08:02 lr: 0.000012 grad: 0.0531 (0.0230) loss: 0.9939 (0.9954) time: 0.1750 data: 0.0836 max mem: 8292 +Train: [0] [3100/6250] eta: 0:07:51 lr: 0.000012 grad: 0.0529 (0.0239) loss: 0.9941 (0.9954) time: 0.2037 data: 0.1174 max mem: 8292 +Train: [0] [3200/6250] eta: 0:07:37 lr: 0.000013 grad: 0.0316 (0.0247) loss: 0.9941 (0.9954) time: 0.1907 data: 0.1056 max mem: 8292 +Train: [0] [3300/6250] eta: 0:07:22 lr: 0.000013 grad: 0.0591 (0.0256) loss: 0.9935 (0.9953) time: 0.1660 data: 0.0850 max mem: 8299 +Train: [0] [3400/6250] eta: 0:07:08 lr: 0.000014 grad: 0.0458 (0.0265) loss: 0.9933 (0.9953) time: 0.1678 data: 0.0797 max mem: 8299 +Train: [0] [3500/6250] eta: 0:06:54 lr: 0.000014 grad: 0.0684 (0.0275) loss: 0.9927 (0.9952) time: 0.1660 data: 0.0820 max mem: 8299 +Train: [0] [3600/6250] eta: 0:06:39 lr: 0.000014 grad: 0.0518 (0.0282) loss: 0.9928 (0.9952) time: 0.1385 data: 0.0535 max mem: 8299 +Train: [0] [3700/6250] eta: 0:06:23 lr: 0.000015 grad: 0.0542 (0.0289) loss: 0.9936 (0.9951) time: 0.1305 data: 0.0486 max mem: 8299 +Train: [0] [3800/6250] eta: 0:06:09 lr: 0.000015 grad: 0.0564 (0.0297) loss: 0.9938 (0.9951) time: 0.1692 data: 0.0854 max mem: 8299 +Train: [0] [3900/6250] eta: 0:05:54 lr: 0.000016 grad: 0.0621 (0.0304) loss: 0.9921 (0.9950) time: 0.1542 data: 0.0796 max mem: 8299 +Train: [0] [4000/6250] eta: 0:05:40 lr: 0.000016 grad: 0.0604 (0.0311) loss: 0.9932 (0.9950) time: 0.1885 data: 0.1073 max mem: 8299 +Train: [0] [4100/6250] eta: 0:05:24 lr: 0.000016 grad: 0.0448 (0.0318) loss: 0.9932 (0.9950) time: 0.1426 data: 0.0677 max mem: 8299 +Train: [0] [4200/6250] eta: 0:05:09 lr: 0.000017 grad: 0.0520 (0.0325) loss: 0.9940 (0.9949) time: 0.1656 data: 0.0890 max mem: 8299 +Train: [0] [4300/6250] eta: 0:04:54 lr: 0.000017 grad: 0.0554 (0.0330) loss: 0.9925 (0.9949) time: 0.1521 data: 0.0738 max mem: 8299 +Train: [0] [4400/6250] eta: 0:04:39 lr: 0.000018 grad: 0.0475 (0.0336) loss: 0.9933 (0.9948) time: 0.1738 data: 0.0860 max mem: 8299 +Train: [0] [4500/6250] eta: 0:04:24 lr: 0.000018 grad: 0.0556 (0.0340) loss: 0.9922 (0.9948) time: 0.1293 data: 0.0501 max mem: 8299 +Train: [0] [4600/6250] eta: 0:04:09 lr: 0.000018 grad: 0.0560 (0.0345) loss: 0.9933 (0.9948) time: 0.1446 data: 0.0587 max mem: 8299 +Train: [0] [4700/6250] eta: 0:03:54 lr: 0.000019 grad: 0.0625 (0.0351) loss: 0.9927 (0.9947) time: 0.1543 data: 0.0671 max mem: 8299 +Train: [0] [4800/6250] eta: 0:03:39 lr: 0.000019 grad: 0.0638 (0.0356) loss: 0.9928 (0.9947) time: 0.1601 data: 0.0837 max mem: 8299 +Train: [0] [4900/6250] eta: 0:03:24 lr: 0.000020 grad: 0.0651 (0.0362) loss: 0.9931 (0.9947) time: 0.2050 data: 0.1351 max mem: 8299 +Train: [0] [5000/6250] eta: 0:03:09 lr: 0.000020 grad: 0.0556 (0.0367) loss: 0.9913 (0.9946) time: 0.1374 data: 0.0567 max mem: 8299 +Train: [0] [5100/6250] eta: 0:02:54 lr: 0.000020 grad: 0.0631 (0.0373) loss: 0.9923 (0.9946) time: 0.1553 data: 0.0879 max mem: 8299 +Train: [0] [5200/6250] eta: 0:02:39 lr: 0.000021 grad: 0.0615 (0.0380) loss: 0.9922 (0.9945) time: 0.1600 data: 0.0681 max mem: 8299 +Train: [0] [5300/6250] eta: 0:02:24 lr: 0.000021 grad: 0.0646 (0.0386) loss: 0.9916 (0.9945) time: 0.1604 data: 0.0792 max mem: 8299 +Train: [0] [5400/6250] eta: 0:02:09 lr: 0.000022 grad: 0.0612 (0.0392) loss: 0.9912 (0.9944) time: 0.1566 data: 0.0713 max mem: 8299 +Train: [0] [5500/6250] eta: 0:01:54 lr: 0.000022 grad: 0.0689 (0.0398) loss: 0.9913 (0.9944) time: 0.1608 data: 0.0807 max mem: 8299 +Train: [0] [5600/6250] eta: 0:01:39 lr: 0.000022 grad: 0.0655 (0.0404) loss: 0.9921 (0.9943) time: 0.1538 data: 0.0722 max mem: 8299 +Train: [0] [5700/6250] eta: 0:01:24 lr: 0.000023 grad: 0.0693 (0.0410) loss: 0.9915 (0.9942) time: 0.1255 data: 0.0402 max mem: 8299 +Train: [0] [5800/6250] eta: 0:01:08 lr: 0.000023 grad: 0.0660 (0.0415) loss: 0.9900 (0.9942) time: 0.1731 data: 0.0951 max mem: 8299 +Train: [0] [5900/6250] eta: 0:00:53 lr: 0.000024 grad: 0.0703 (0.0420) loss: 0.9916 (0.9942) time: 0.1390 data: 0.0642 max mem: 8299 +Train: [0] [6000/6250] eta: 0:00:38 lr: 0.000024 grad: 0.0620 (0.0424) loss: 0.9923 (0.9941) time: 0.1694 data: 0.0905 max mem: 8299 +Train: [0] [6100/6250] eta: 0:00:22 lr: 0.000024 grad: 0.0723 (0.0428) loss: 0.9903 (0.9941) time: 0.1781 data: 0.0955 max mem: 8299 +Train: [0] [6200/6250] eta: 0:00:07 lr: 0.000025 grad: 0.0661 (0.0431) loss: 0.9912 (0.9940) time: 0.1642 data: 0.0808 max mem: 8299 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0737 (0.0433) loss: 0.9917 (0.9940) time: 0.1351 data: 0.0587 max mem: 8299 +Train: [0] Total time: 0:16:06 (0.1546 s / it) +Averaged stats: lr: 0.000025 grad: 0.0737 (0.0433) loss: 0.9917 (0.9940) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:04:26 loss: 0.9906 (0.9906) time: 4.2929 data: 4.2015 max mem: 8299 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9924 (0.9921) time: 0.0819 data: 0.0572 max mem: 8299 +Eval (hcp-train-subset): [0] Total time: 0:00:13 (0.2244 s / it) +Averaged stats (hcp-train-subset): loss: 0.9924 (0.9921) +Eval (hcp-val): [0] [ 0/62] eta: 0:04:56 loss: 0.9889 (0.9889) time: 4.7802 data: 4.7512 max mem: 8299 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9919 (0.9912) time: 0.1373 data: 0.1111 max mem: 8299 +Eval (hcp-val): [0] Total time: 0:00:12 (0.2043 s / it) +Averaged stats (hcp-val): loss: 0.9919 (0.9912) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 9:31:13 lr: 0.000025 grad: 0.2370 (0.2370) loss: 0.9925 (0.9925) time: 5.4837 data: 5.3920 max mem: 8299 +Train: [1] [ 100/6250] eta: 0:21:23 lr: 0.000025 grad: 0.0641 (0.0804) loss: 0.9920 (0.9910) time: 0.1793 data: 0.0839 max mem: 8299 +Train: [1] [ 200/6250] eta: 0:18:33 lr: 0.000026 grad: 0.0815 (0.0815) loss: 0.9911 (0.9906) time: 0.1643 data: 0.0741 max mem: 8299 +Train: [1] [ 300/6250] eta: 0:17:55 lr: 0.000026 grad: 0.0625 (0.0812) loss: 0.9916 (0.9904) time: 0.1713 data: 0.0709 max mem: 8299 +Train: [1] [ 400/6250] eta: 0:17:21 lr: 0.000027 grad: 0.0617 (0.0804) loss: 0.9923 (0.9904) time: 0.1888 data: 0.1041 max mem: 8299 +Train: [1] [ 500/6250] eta: 0:16:40 lr: 0.000027 grad: 0.0575 (0.0776) loss: 0.9923 (0.9905) time: 0.1878 data: 0.0914 max mem: 8299 +Train: [1] [ 600/6250] eta: 0:16:10 lr: 0.000027 grad: 0.0691 (0.0766) loss: 0.9894 (0.9905) time: 0.1806 data: 0.0943 max mem: 8299 +Train: [1] [ 700/6250] eta: 0:15:51 lr: 0.000028 grad: 0.0587 (0.0752) loss: 0.9914 (0.9906) time: 0.1456 data: 0.0551 max mem: 8299 +Train: [1] [ 800/6250] eta: 0:15:41 lr: 0.000028 grad: 0.0649 (0.0743) loss: 0.9911 (0.9907) time: 0.1824 data: 0.1044 max mem: 8299 +Train: [1] [ 900/6250] eta: 0:15:44 lr: 0.000029 grad: 0.0608 (0.0735) loss: 0.9903 (0.9907) time: 0.1670 data: 0.0727 max mem: 8299 +Train: [1] [1000/6250] eta: 0:15:20 lr: 0.000029 grad: 0.0660 (0.0728) loss: 0.9916 (0.9908) time: 0.1592 data: 0.0796 max mem: 8299 +Train: [1] [1100/6250] eta: 0:15:06 lr: 0.000029 grad: 0.0668 (0.0723) loss: 0.9891 (0.9907) time: 0.2150 data: 0.1336 max mem: 8299 +Train: [1] [1200/6250] eta: 0:14:44 lr: 0.000030 grad: 0.0837 (0.0722) loss: 0.9896 (0.9906) time: 0.2133 data: 0.1454 max mem: 8299 +Train: [1] [1300/6250] eta: 0:14:26 lr: 0.000030 grad: 0.0661 (0.0720) loss: 0.9902 (0.9907) time: 0.1843 data: 0.1091 max mem: 8299 +Train: [1] [1400/6250] eta: 0:14:06 lr: 0.000031 grad: 0.0809 (0.0722) loss: 0.9911 (0.9907) time: 0.1540 data: 0.0654 max mem: 8299 +Train: [1] [1500/6250] eta: 0:13:47 lr: 0.000031 grad: 0.0727 (0.0720) loss: 0.9880 (0.9906) time: 0.1684 data: 0.0835 max mem: 8299 +Train: [1] [1600/6250] eta: 0:13:26 lr: 0.000031 grad: 0.0704 (0.0721) loss: 0.9905 (0.9906) time: 0.1781 data: 0.0915 max mem: 8299 +Train: [1] [1700/6250] eta: 0:13:03 lr: 0.000032 grad: 0.0692 (0.0720) loss: 0.9899 (0.9906) time: 0.1472 data: 0.0485 max mem: 8299 +Train: [1] [1800/6250] eta: 0:12:40 lr: 0.000032 grad: 0.0687 (0.0719) loss: 0.9904 (0.9906) time: 0.1247 data: 0.0438 max mem: 8299 +Train: [1] [1900/6250] eta: 0:12:22 lr: 0.000033 grad: 0.0631 (0.0719) loss: 0.9898 (0.9905) time: 0.1303 data: 0.0446 max mem: 8299 +Train: [1] [2000/6250] eta: 0:12:05 lr: 0.000033 grad: 0.0648 (0.0716) loss: 0.9905 (0.9905) time: 0.2106 data: 0.1093 max mem: 8299 +Train: [1] [2100/6250] eta: 0:11:47 lr: 0.000033 grad: 0.0571 (0.0715) loss: 0.9909 (0.9906) time: 0.1526 data: 0.0646 max mem: 8299 +Train: [1] [2200/6250] eta: 0:11:28 lr: 0.000034 grad: 0.0630 (0.0713) loss: 0.9907 (0.9905) time: 0.1718 data: 0.0858 max mem: 8299 +Train: [1] [2300/6250] eta: 0:11:09 lr: 0.000034 grad: 0.0573 (0.0711) loss: 0.9908 (0.9905) time: 0.1599 data: 0.0722 max mem: 8299 +Train: [1] [2400/6250] eta: 0:10:51 lr: 0.000035 grad: 0.0646 (0.0711) loss: 0.9909 (0.9905) time: 0.1721 data: 0.0982 max mem: 8299 +Train: [1] [2500/6250] eta: 0:10:33 lr: 0.000035 grad: 0.0661 (0.0709) loss: 0.9898 (0.9905) time: 0.1570 data: 0.0625 max mem: 8299 +Train: [1] [2600/6250] eta: 0:10:14 lr: 0.000035 grad: 0.0573 (0.0708) loss: 0.9903 (0.9905) time: 0.1637 data: 0.0867 max mem: 8299 +Train: [1] [2700/6250] eta: 0:09:55 lr: 0.000036 grad: 0.0613 (0.0706) loss: 0.9916 (0.9905) time: 0.1411 data: 0.0570 max mem: 8299 +Train: [1] [2800/6250] eta: 0:09:37 lr: 0.000036 grad: 0.0571 (0.0705) loss: 0.9897 (0.9904) time: 0.1308 data: 0.0442 max mem: 8299 +Train: [1] [2900/6250] eta: 0:09:19 lr: 0.000037 grad: 0.0588 (0.0703) loss: 0.9893 (0.9904) time: 0.1725 data: 0.0826 max mem: 8299 +Train: [1] [3000/6250] eta: 0:09:02 lr: 0.000037 grad: 0.0707 (0.0703) loss: 0.9896 (0.9904) time: 0.1604 data: 0.0749 max mem: 8299 +Train: [1] [3100/6250] eta: 0:08:45 lr: 0.000037 grad: 0.0629 (0.0702) loss: 0.9904 (0.9904) time: 0.1162 data: 0.0415 max mem: 8299 +Train: [1] [3200/6250] eta: 0:08:27 lr: 0.000038 grad: 0.0689 (0.0701) loss: 0.9899 (0.9904) time: 0.1653 data: 0.0756 max mem: 8299 +Train: [1] [3300/6250] eta: 0:08:10 lr: 0.000038 grad: 0.0599 (0.0700) loss: 0.9909 (0.9904) time: 0.1412 data: 0.0593 max mem: 8299 +Train: [1] [3400/6250] eta: 0:07:52 lr: 0.000039 grad: 0.0665 (0.0700) loss: 0.9879 (0.9903) time: 0.1649 data: 0.0801 max mem: 8299 +Train: [1] [3500/6250] eta: 0:07:34 lr: 0.000039 grad: 0.0544 (0.0699) loss: 0.9903 (0.9903) time: 0.1483 data: 0.0640 max mem: 8299 +Train: [1] [3600/6250] eta: 0:07:17 lr: 0.000039 grad: 0.0648 (0.0699) loss: 0.9881 (0.9903) time: 0.1793 data: 0.0899 max mem: 8299 +Train: [1] [3700/6250] eta: 0:07:00 lr: 0.000040 grad: 0.0658 (0.0700) loss: 0.9884 (0.9902) time: 0.1624 data: 0.0850 max mem: 8299 +Train: [1] [3800/6250] eta: 0:06:43 lr: 0.000040 grad: 0.0708 (0.0700) loss: 0.9899 (0.9902) time: 0.1510 data: 0.0588 max mem: 8299 +Train: [1] [3900/6250] eta: 0:06:26 lr: 0.000041 grad: 0.0593 (0.0699) loss: 0.9895 (0.9902) time: 0.1508 data: 0.0783 max mem: 8299 +Train: [1] [4000/6250] eta: 0:06:09 lr: 0.000041 grad: 0.0637 (0.0700) loss: 0.9891 (0.9902) time: 0.1519 data: 0.0704 max mem: 8299 +Train: [1] [4100/6250] eta: 0:05:52 lr: 0.000041 grad: 0.0710 (0.0699) loss: 0.9900 (0.9902) time: 0.1531 data: 0.0665 max mem: 8299 +Train: [1] [4200/6250] eta: 0:05:35 lr: 0.000042 grad: 0.0622 (0.0700) loss: 0.9891 (0.9901) time: 0.1449 data: 0.0771 max mem: 8299 +Train: [1] [4300/6250] eta: 0:05:18 lr: 0.000042 grad: 0.0628 (0.0700) loss: 0.9892 (0.9901) time: 0.1492 data: 0.0798 max mem: 8299 +Train: [1] [4400/6250] eta: 0:05:01 lr: 0.000043 grad: 0.0637 (0.0700) loss: 0.9901 (0.9901) time: 0.1660 data: 0.0791 max mem: 8299 +Train: [1] [4500/6250] eta: 0:04:45 lr: 0.000043 grad: 0.0566 (0.0699) loss: 0.9903 (0.9901) time: 0.1686 data: 0.0937 max mem: 8299 +Train: [1] [4600/6250] eta: 0:04:29 lr: 0.000043 grad: 0.0612 (0.0698) loss: 0.9895 (0.9901) time: 0.1751 data: 0.1028 max mem: 8299 +Train: [1] [4700/6250] eta: 0:04:12 lr: 0.000044 grad: 0.0659 (0.0698) loss: 0.9897 (0.9901) time: 0.1398 data: 0.0484 max mem: 8299 +Train: [1] [4800/6250] eta: 0:03:55 lr: 0.000044 grad: 0.0619 (0.0697) loss: 0.9902 (0.9901) time: 0.1484 data: 0.0664 max mem: 8299 +Train: [1] [4900/6250] eta: 0:03:39 lr: 0.000045 grad: 0.0637 (0.0696) loss: 0.9889 (0.9901) time: 0.1484 data: 0.0748 max mem: 8299 +Train: [1] [5000/6250] eta: 0:03:23 lr: 0.000045 grad: 0.0622 (0.0696) loss: 0.9898 (0.9901) time: 0.1542 data: 0.0717 max mem: 8299 +Train: [1] [5100/6250] eta: 0:03:07 lr: 0.000045 grad: 0.0645 (0.0696) loss: 0.9889 (0.9900) time: 0.1734 data: 0.0949 max mem: 8299 +Train: [1] [5200/6250] eta: 0:02:50 lr: 0.000046 grad: 0.0650 (0.0696) loss: 0.9888 (0.9900) time: 0.1698 data: 0.0769 max mem: 8299 +Train: [1] [5300/6250] eta: 0:02:35 lr: 0.000046 grad: 0.0587 (0.0696) loss: 0.9898 (0.9900) time: 0.2066 data: 0.1173 max mem: 8299 +Train: [1] [5400/6250] eta: 0:02:18 lr: 0.000047 grad: 0.0645 (0.0697) loss: 0.9899 (0.9900) time: 0.1584 data: 0.0690 max mem: 8299 +Train: [1] [5500/6250] eta: 0:02:02 lr: 0.000047 grad: 0.0685 (0.0697) loss: 0.9888 (0.9899) time: 0.1505 data: 0.0621 max mem: 8299 +Train: [1] [5600/6250] eta: 0:01:45 lr: 0.000047 grad: 0.0631 (0.0697) loss: 0.9898 (0.9899) time: 0.1836 data: 0.0739 max mem: 8299 +Train: [1] [5700/6250] eta: 0:01:29 lr: 0.000048 grad: 0.0610 (0.0697) loss: 0.9886 (0.9899) time: 0.1548 data: 0.0628 max mem: 8299 +Train: [1] [5800/6250] eta: 0:01:13 lr: 0.000048 grad: 0.0665 (0.0697) loss: 0.9884 (0.9899) time: 0.1442 data: 0.0582 max mem: 8299 +Train: [1] [5900/6250] eta: 0:00:56 lr: 0.000049 grad: 0.0662 (0.0696) loss: 0.9894 (0.9899) time: 0.1586 data: 0.0626 max mem: 8299 +Train: [1] [6000/6250] eta: 0:00:40 lr: 0.000049 grad: 0.0573 (0.0696) loss: 0.9904 (0.9899) time: 0.1859 data: 0.1060 max mem: 8299 +Train: [1] [6100/6250] eta: 0:00:24 lr: 0.000049 grad: 0.0589 (0.0695) loss: 0.9895 (0.9899) time: 0.1878 data: 0.1094 max mem: 8299 +Train: [1] [6200/6250] eta: 0:00:08 lr: 0.000050 grad: 0.0645 (0.0695) loss: 0.9904 (0.9899) time: 0.2052 data: 0.1330 max mem: 8299 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0708 (0.0695) loss: 0.9896 (0.9899) time: 0.1693 data: 0.0842 max mem: 8299 +Train: [1] Total time: 0:17:04 (0.1639 s / it) +Averaged stats: lr: 0.000050 grad: 0.0708 (0.0695) loss: 0.9896 (0.9899) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:06:11 loss: 0.9960 (0.9960) time: 5.9929 data: 5.9613 max mem: 8299 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9920 (0.9924) time: 0.1163 data: 0.0897 max mem: 8299 +Eval (hcp-train-subset): [1] Total time: 0:00:14 (0.2297 s / it) +Averaged stats (hcp-train-subset): loss: 0.9920 (0.9924) +Eval (hcp-val): [1] [ 0/62] eta: 0:03:53 loss: 0.9832 (0.9832) time: 3.7589 data: 3.6911 max mem: 8299 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9920 (0.9902) time: 0.1455 data: 0.1190 max mem: 8299 +Eval (hcp-val): [1] Total time: 0:00:13 (0.2167 s / it) +Averaged stats (hcp-val): loss: 0.9920 (0.9902) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 8:24:00 lr: 0.000050 grad: 0.1779 (0.1779) loss: 0.9896 (0.9896) time: 4.8384 data: 4.5658 max mem: 8299 +Train: [2] [ 100/6250] eta: 0:22:28 lr: 0.000050 grad: 0.0629 (0.0759) loss: 0.9908 (0.9890) time: 0.1665 data: 0.0618 max mem: 8299 +Train: [2] [ 200/6250] eta: 0:19:29 lr: 0.000051 grad: 0.0586 (0.0717) loss: 0.9891 (0.9890) time: 0.1472 data: 0.0539 max mem: 8299 +Train: [2] [ 300/6250] eta: 0:18:06 lr: 0.000051 grad: 0.0538 (0.0702) loss: 0.9886 (0.9890) time: 0.1617 data: 0.0812 max mem: 8299 +Train: [2] [ 400/6250] eta: 0:17:15 lr: 0.000052 grad: 0.0630 (0.0700) loss: 0.9874 (0.9885) time: 0.1340 data: 0.0451 max mem: 8299 +Train: [2] [ 500/6250] eta: 0:16:43 lr: 0.000052 grad: 0.0602 (0.0707) loss: 0.9900 (0.9884) time: 0.1647 data: 0.0446 max mem: 8299 +Train: [2] [ 600/6250] eta: 0:16:13 lr: 0.000052 grad: 0.0697 (0.0709) loss: 0.9912 (0.9884) time: 0.1510 data: 0.0609 max mem: 8299 +Train: [2] [ 700/6250] eta: 0:16:08 lr: 0.000053 grad: 0.0757 (0.0719) loss: 0.9874 (0.9883) time: 0.2068 data: 0.1210 max mem: 8299 +Train: [2] [ 800/6250] eta: 0:15:55 lr: 0.000053 grad: 0.0634 (0.0718) loss: 0.9889 (0.9882) time: 0.2060 data: 0.1226 max mem: 8299 +Train: [2] [ 900/6250] eta: 0:15:41 lr: 0.000054 grad: 0.0622 (0.0720) loss: 0.9873 (0.9881) time: 0.1348 data: 0.0064 max mem: 8299 +Train: [2] [1000/6250] eta: 0:15:26 lr: 0.000054 grad: 0.0669 (0.0721) loss: 0.9876 (0.9880) time: 0.1378 data: 0.0560 max mem: 8299 +Train: [2] [1100/6250] eta: 0:15:02 lr: 0.000054 grad: 0.0665 (0.0723) loss: 0.9900 (0.9880) time: 0.1582 data: 0.0791 max mem: 8299 +Train: [2] [1200/6250] eta: 0:14:36 lr: 0.000055 grad: 0.0746 (0.0726) loss: 0.9888 (0.9879) time: 0.1470 data: 0.0579 max mem: 8299 +Train: [2] [1300/6250] eta: 0:14:13 lr: 0.000055 grad: 0.0612 (0.0727) loss: 0.9888 (0.9879) time: 0.1710 data: 0.0863 max mem: 8299 +Train: [2] [1400/6250] eta: 0:13:52 lr: 0.000056 grad: 0.0666 (0.0725) loss: 0.9864 (0.9879) time: 0.1674 data: 0.0871 max mem: 8299 +Train: [2] [1500/6250] eta: 0:13:28 lr: 0.000056 grad: 0.0717 (0.0726) loss: 0.9881 (0.9879) time: 0.1249 data: 0.0420 max mem: 8299 +Train: [2] [1600/6250] eta: 0:13:08 lr: 0.000056 grad: 0.0718 (0.0728) loss: 0.9885 (0.9879) time: 0.1760 data: 0.0880 max mem: 8299 +Train: [2] [1700/6250] eta: 0:12:50 lr: 0.000057 grad: 0.0731 (0.0726) loss: 0.9879 (0.9879) time: 0.1747 data: 0.0864 max mem: 8299 +Train: [2] [1800/6250] eta: 0:12:35 lr: 0.000057 grad: 0.0661 (0.0725) loss: 0.9883 (0.9879) time: 0.1931 data: 0.1097 max mem: 8299 +Train: [2] [1900/6250] eta: 0:12:13 lr: 0.000058 grad: 0.0620 (0.0722) loss: 0.9881 (0.9879) time: 0.1588 data: 0.0656 max mem: 8299 +Train: [2] [2000/6250] eta: 0:11:57 lr: 0.000058 grad: 0.0604 (0.0720) loss: 0.9887 (0.9879) time: 0.2012 data: 0.1194 max mem: 8299 +Train: [2] [2100/6250] eta: 0:11:39 lr: 0.000058 grad: 0.0666 (0.0718) loss: 0.9887 (0.9880) time: 0.1727 data: 0.0953 max mem: 8299 +Train: [2] [2200/6250] eta: 0:11:19 lr: 0.000059 grad: 0.0676 (0.0718) loss: 0.9904 (0.9880) time: 0.1665 data: 0.0835 max mem: 8299 +Train: [2] [2300/6250] eta: 0:11:01 lr: 0.000059 grad: 0.0650 (0.0717) loss: 0.9887 (0.9880) time: 0.1043 data: 0.0297 max mem: 8299 +Train: [2] [2400/6250] eta: 0:10:43 lr: 0.000060 grad: 0.0746 (0.0720) loss: 0.9864 (0.9879) time: 0.1632 data: 0.0908 max mem: 8299 +Train: [2] [2500/6250] eta: 0:10:26 lr: 0.000060 grad: 0.0691 (0.0720) loss: 0.9896 (0.9879) time: 0.1835 data: 0.1000 max mem: 8299 +Train: [2] [2600/6250] eta: 0:10:06 lr: 0.000060 grad: 0.0694 (0.0719) loss: 0.9867 (0.9879) time: 0.1451 data: 0.0425 max mem: 8299 +Train: [2] [2700/6250] eta: 0:09:47 lr: 0.000061 grad: 0.0727 (0.0720) loss: 0.9852 (0.9879) time: 0.1323 data: 0.0551 max mem: 8299 +Train: [2] [2800/6250] eta: 0:09:30 lr: 0.000061 grad: 0.0689 (0.0720) loss: 0.9892 (0.9879) time: 0.1417 data: 0.0507 max mem: 8299 +Train: [2] [2900/6250] eta: 0:09:14 lr: 0.000062 grad: 0.0665 (0.0722) loss: 0.9877 (0.9879) time: 0.1774 data: 0.0939 max mem: 8299 +Train: [2] [3000/6250] eta: 0:08:57 lr: 0.000062 grad: 0.0795 (0.0724) loss: 0.9872 (0.9878) time: 0.1653 data: 0.0817 max mem: 8299 +Train: [2] [3100/6250] eta: 0:08:39 lr: 0.000062 grad: 0.0733 (0.0725) loss: 0.9860 (0.9878) time: 0.1508 data: 0.0691 max mem: 8299 +Train: [2] [3200/6250] eta: 0:08:22 lr: 0.000063 grad: 0.0549 (0.0725) loss: 0.9887 (0.9878) time: 0.1367 data: 0.0538 max mem: 8299 +Train: [2] [3300/6250] eta: 0:08:04 lr: 0.000063 grad: 0.0744 (0.0725) loss: 0.9871 (0.9878) time: 0.1428 data: 0.0656 max mem: 8299 +Train: [2] [3400/6250] eta: 0:07:47 lr: 0.000064 grad: 0.0688 (0.0728) loss: 0.9885 (0.9878) time: 0.1529 data: 0.0658 max mem: 8299 +Train: [2] [3500/6250] eta: 0:07:31 lr: 0.000064 grad: 0.0751 (0.0732) loss: 0.9855 (0.9877) time: 0.1821 data: 0.0927 max mem: 8299 +Train: [2] [3600/6250] eta: 0:07:13 lr: 0.000064 grad: 0.0803 (0.0737) loss: 0.9840 (0.9877) time: 0.1856 data: 0.1038 max mem: 8299 +Train: [2] [3700/6250] eta: 0:06:56 lr: 0.000065 grad: 0.0936 (0.0740) loss: 0.9857 (0.9876) time: 0.1435 data: 0.0556 max mem: 8299 +Train: [2] [3800/6250] eta: 0:06:39 lr: 0.000065 grad: 0.0890 (0.0745) loss: 0.9858 (0.9876) time: 0.1334 data: 0.0443 max mem: 8299 +Train: [2] [3900/6250] eta: 0:06:22 lr: 0.000066 grad: 0.0750 (0.0749) loss: 0.9865 (0.9876) time: 0.1749 data: 0.0883 max mem: 8299 +Train: [2] [4000/6250] eta: 0:06:06 lr: 0.000066 grad: 0.0990 (0.0755) loss: 0.9852 (0.9875) time: 0.1989 data: 0.1027 max mem: 8299 +Train: [2] [4100/6250] eta: 0:05:49 lr: 0.000066 grad: 0.1147 (0.0762) loss: 0.9825 (0.9875) time: 0.1507 data: 0.0724 max mem: 8299 +Train: [2] [4200/6250] eta: 0:05:33 lr: 0.000067 grad: 0.1037 (0.0773) loss: 0.9849 (0.9874) time: 0.1561 data: 0.0841 max mem: 8299 +Train: [2] [4300/6250] eta: 0:05:16 lr: 0.000067 grad: 0.1214 (0.0782) loss: 0.9841 (0.9874) time: 0.1447 data: 0.0629 max mem: 8299 +Train: [2] [4400/6250] eta: 0:05:00 lr: 0.000068 grad: 0.1236 (0.0796) loss: 0.9882 (0.9874) time: 0.1729 data: 0.0891 max mem: 8299 +Train: [2] [4500/6250] eta: 0:04:43 lr: 0.000068 grad: 0.1056 (0.0804) loss: 0.9857 (0.9873) time: 0.1556 data: 0.0694 max mem: 8299 +Train: [2] [4600/6250] eta: 0:04:27 lr: 0.000068 grad: 0.1965 (0.0822) loss: 0.9856 (0.9873) time: 0.1616 data: 0.0751 max mem: 8299 +Train: [2] [4700/6250] eta: 0:04:10 lr: 0.000069 grad: 0.1506 (0.0843) loss: 0.9849 (0.9872) time: 0.1422 data: 0.0517 max mem: 8299 +Train: [2] [4800/6250] eta: 0:03:54 lr: 0.000069 grad: 0.1757 (0.0862) loss: 0.9836 (0.9872) time: 0.1575 data: 0.0806 max mem: 8299 +Train: [2] [4900/6250] eta: 0:03:37 lr: 0.000070 grad: 0.1526 (0.0884) loss: 0.9867 (0.9871) time: 0.1107 data: 0.0271 max mem: 8299 +Train: [2] [5000/6250] eta: 0:03:22 lr: 0.000070 grad: 0.1933 (0.0905) loss: 0.9864 (0.9871) time: 0.1948 data: 0.1032 max mem: 8299 +Train: [2] [5100/6250] eta: 0:03:05 lr: 0.000070 grad: 0.1986 (0.0928) loss: 0.9857 (0.9871) time: 0.1627 data: 0.0873 max mem: 8299 +Train: [2] [5200/6250] eta: 0:02:49 lr: 0.000071 grad: 0.0904 (0.0944) loss: 0.9851 (0.9870) time: 0.1655 data: 0.0751 max mem: 8299 +Train: [2] [5300/6250] eta: 0:02:33 lr: 0.000071 grad: 0.1540 (0.0964) loss: 0.9860 (0.9870) time: 0.1806 data: 0.1018 max mem: 8299 +Train: [2] [5400/6250] eta: 0:02:17 lr: 0.000072 grad: 0.1923 (0.0988) loss: 0.9855 (0.9869) time: 0.1440 data: 0.0547 max mem: 8299 +Train: [2] [5500/6250] eta: 0:02:01 lr: 0.000072 grad: 0.1756 (0.1004) loss: 0.9851 (0.9869) time: 0.1370 data: 0.0518 max mem: 8299 +Train: [2] [5600/6250] eta: 0:01:45 lr: 0.000072 grad: 0.1319 (0.1022) loss: 0.9816 (0.9868) time: 0.1603 data: 0.0837 max mem: 8299 +Train: [2] [5700/6250] eta: 0:01:29 lr: 0.000073 grad: 0.1576 (0.1039) loss: 0.9839 (0.9868) time: 0.1923 data: 0.0968 max mem: 8299 +Train: [2] [5800/6250] eta: 0:01:12 lr: 0.000073 grad: 0.1663 (0.1058) loss: 0.9826 (0.9867) time: 0.1802 data: 0.0949 max mem: 8299 +Train: [2] [5900/6250] eta: 0:00:56 lr: 0.000074 grad: 0.1128 (0.1073) loss: 0.9816 (0.9866) time: 0.1514 data: 0.0577 max mem: 8299 +Train: [2] [6000/6250] eta: 0:00:40 lr: 0.000074 grad: 0.1212 (0.1091) loss: 0.9813 (0.9866) time: 0.1196 data: 0.0413 max mem: 8299 +Train: [2] [6100/6250] eta: 0:00:24 lr: 0.000074 grad: 0.2266 (0.1109) loss: 0.9818 (0.9865) time: 0.2006 data: 0.1124 max mem: 8299 +Train: [2] [6200/6250] eta: 0:00:08 lr: 0.000075 grad: 0.1365 (0.1122) loss: 0.9808 (0.9864) time: 0.2321 data: 0.1491 max mem: 8299 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.1411 (0.1129) loss: 0.9804 (0.9864) time: 0.2054 data: 0.1138 max mem: 8299 +Train: [2] Total time: 0:16:59 (0.1632 s / it) +Averaged stats: lr: 0.000075 grad: 0.1411 (0.1129) loss: 0.9804 (0.9864) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:03:13 loss: 0.9804 (0.9804) time: 3.1233 data: 3.0616 max mem: 8299 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9856 (0.9843) time: 0.1313 data: 0.1054 max mem: 8299 +Eval (hcp-train-subset): [2] Total time: 0:00:13 (0.2198 s / it) +Averaged stats (hcp-train-subset): loss: 0.9856 (0.9843) +Eval (hcp-val): [2] [ 0/62] eta: 0:05:04 loss: 0.9769 (0.9769) time: 4.9061 data: 4.8756 max mem: 8299 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9814 (0.9814) time: 0.1523 data: 0.1274 max mem: 8299 +Eval (hcp-val): [2] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-val): loss: 0.9814 (0.9814) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 7:58:03 lr: 0.000075 grad: 0.1044 (0.1044) loss: 0.9903 (0.9903) time: 4.5894 data: 4.3487 max mem: 8299 +Train: [3] [ 100/6250] eta: 0:21:51 lr: 0.000075 grad: 0.3071 (0.2037) loss: 0.9836 (0.9855) time: 0.1841 data: 0.0877 max mem: 8299 +Train: [3] [ 200/6250] eta: 0:19:08 lr: 0.000076 grad: 0.2270 (0.2092) loss: 0.9818 (0.9843) time: 0.1711 data: 0.0688 max mem: 8299 +Train: [3] [ 300/6250] eta: 0:17:43 lr: 0.000076 grad: 0.1882 (0.2094) loss: 0.9805 (0.9836) time: 0.1420 data: 0.0460 max mem: 8299 +Train: [3] [ 400/6250] eta: 0:17:07 lr: 0.000077 grad: 0.1577 (0.2071) loss: 0.9844 (0.9834) time: 0.1661 data: 0.0894 max mem: 8299 +Train: [3] [ 500/6250] eta: 0:16:38 lr: 0.000077 grad: 0.1272 (0.2066) loss: 0.9833 (0.9833) time: 0.1682 data: 0.0830 max mem: 8299 +Train: [3] [ 600/6250] eta: 0:15:52 lr: 0.000077 grad: 0.2013 (0.2114) loss: 0.9797 (0.9829) time: 0.1579 data: 0.0694 max mem: 8299 +Train: [3] [ 700/6250] eta: 0:15:26 lr: 0.000078 grad: 0.1448 (0.2147) loss: 0.9780 (0.9824) time: 0.1743 data: 0.0653 max mem: 8299 +Train: [3] [ 800/6250] eta: 0:15:02 lr: 0.000078 grad: 0.1812 (0.2151) loss: 0.9762 (0.9819) time: 0.1368 data: 0.0326 max mem: 8299 +Train: [3] [ 900/6250] eta: 0:14:44 lr: 0.000079 grad: 0.1883 (0.2157) loss: 0.9789 (0.9816) time: 0.1733 data: 0.0677 max mem: 8299 +Train: [3] [1000/6250] eta: 0:14:25 lr: 0.000079 grad: 0.2099 (0.2180) loss: 0.9791 (0.9814) time: 0.1680 data: 0.0888 max mem: 8299 +Train: [3] [1100/6250] eta: 0:14:07 lr: 0.000079 grad: 0.1991 (0.2159) loss: 0.9793 (0.9812) time: 0.1904 data: 0.1193 max mem: 8299 +Train: [3] [1200/6250] eta: 0:13:48 lr: 0.000080 grad: 0.1636 (0.2163) loss: 0.9794 (0.9810) time: 0.1657 data: 0.0958 max mem: 8299 +Train: [3] [1300/6250] eta: 0:13:38 lr: 0.000080 grad: 0.2645 (0.2176) loss: 0.9819 (0.9808) time: 0.2026 data: 0.1352 max mem: 8299 +Train: [3] [1400/6250] eta: 0:13:24 lr: 0.000081 grad: 0.2013 (0.2163) loss: 0.9785 (0.9806) time: 0.1946 data: 0.1201 max mem: 8299 +Train: [3] [1500/6250] eta: 0:13:12 lr: 0.000081 grad: 0.1445 (0.2170) loss: 0.9785 (0.9804) time: 0.1951 data: 0.1198 max mem: 8299 +Train: [3] [1600/6250] eta: 0:12:50 lr: 0.000081 grad: 0.1809 (0.2170) loss: 0.9790 (0.9804) time: 0.1618 data: 0.0747 max mem: 8299 +Train: [3] [1700/6250] eta: 0:12:32 lr: 0.000082 grad: 0.2109 (0.2171) loss: 0.9794 (0.9803) time: 0.1483 data: 0.0635 max mem: 8299 +Train: [3] [1800/6250] eta: 0:12:14 lr: 0.000082 grad: 0.1414 (0.2160) loss: 0.9788 (0.9802) time: 0.1518 data: 0.0577 max mem: 8299 +Train: [3] [1900/6250] eta: 0:11:54 lr: 0.000083 grad: 0.2173 (0.2164) loss: 0.9773 (0.9801) time: 0.1559 data: 0.0668 max mem: 8299 +Train: [3] [2000/6250] eta: 0:11:36 lr: 0.000083 grad: 0.1485 (0.2151) loss: 0.9782 (0.9800) time: 0.1506 data: 0.0686 max mem: 8299 +Train: [3] [2100/6250] eta: 0:11:17 lr: 0.000083 grad: 0.1560 (0.2146) loss: 0.9777 (0.9799) time: 0.1476 data: 0.0679 max mem: 8299 +Train: [3] [2200/6250] eta: 0:11:00 lr: 0.000084 grad: 0.2197 (0.2155) loss: 0.9756 (0.9798) time: 0.1811 data: 0.0988 max mem: 8299 +Train: [3] [2300/6250] eta: 0:10:44 lr: 0.000084 grad: 0.1393 (0.2154) loss: 0.9794 (0.9797) time: 0.1725 data: 0.0904 max mem: 8299 +Train: [3] [2400/6250] eta: 0:10:30 lr: 0.000085 grad: 0.1843 (0.2149) loss: 0.9772 (0.9796) time: 0.1521 data: 0.0640 max mem: 8299 +Train: [3] [2500/6250] eta: 0:10:14 lr: 0.000085 grad: 0.2116 (0.2145) loss: 0.9762 (0.9795) time: 0.1167 data: 0.0375 max mem: 8299 +Train: [3] [2600/6250] eta: 0:09:57 lr: 0.000085 grad: 0.1526 (0.2136) loss: 0.9759 (0.9794) time: 0.1480 data: 0.0691 max mem: 8299 +Train: [3] [2700/6250] eta: 0:09:40 lr: 0.000086 grad: 0.1588 (0.2131) loss: 0.9781 (0.9793) time: 0.1530 data: 0.0610 max mem: 8299 +Train: [3] [2800/6250] eta: 0:09:22 lr: 0.000086 grad: 0.2519 (0.2129) loss: 0.9802 (0.9793) time: 0.1674 data: 0.0885 max mem: 8299 +Train: [3] [2900/6250] eta: 0:09:05 lr: 0.000087 grad: 0.1728 (0.2128) loss: 0.9775 (0.9792) time: 0.1062 data: 0.0322 max mem: 8299 +Train: [3] [3000/6250] eta: 0:08:47 lr: 0.000087 grad: 0.1423 (0.2116) loss: 0.9775 (0.9791) time: 0.1373 data: 0.0482 max mem: 8299 +Train: [3] [3100/6250] eta: 0:08:31 lr: 0.000087 grad: 0.1949 (0.2116) loss: 0.9733 (0.9790) time: 0.1567 data: 0.0815 max mem: 8299 +Train: [3] [3200/6250] eta: 0:08:15 lr: 0.000088 grad: 0.1549 (0.2112) loss: 0.9737 (0.9789) time: 0.1537 data: 0.0708 max mem: 8299 +Train: [3] [3300/6250] eta: 0:07:57 lr: 0.000088 grad: 0.1419 (0.2120) loss: 0.9752 (0.9788) time: 0.1538 data: 0.0722 max mem: 8299 +Train: [3] [3400/6250] eta: 0:07:40 lr: 0.000089 grad: 0.1541 (0.2116) loss: 0.9742 (0.9786) time: 0.1236 data: 0.0368 max mem: 8299 +Train: [3] [3500/6250] eta: 0:07:23 lr: 0.000089 grad: 0.2234 (0.2125) loss: 0.9769 (0.9785) time: 0.1208 data: 0.0415 max mem: 8299 +Train: [3] [3600/6250] eta: 0:07:07 lr: 0.000089 grad: 0.2511 (0.2118) loss: 0.9734 (0.9784) time: 0.1643 data: 0.0858 max mem: 8299 +Train: [3] [3700/6250] eta: 0:06:51 lr: 0.000090 grad: 0.1646 (0.2117) loss: 0.9717 (0.9782) time: 0.1521 data: 0.0560 max mem: 8299 +Train: [3] [3800/6250] eta: 0:06:34 lr: 0.000090 grad: 0.1596 (0.2112) loss: 0.9709 (0.9781) time: 0.1547 data: 0.0793 max mem: 8299 +Train: [3] [3900/6250] eta: 0:06:18 lr: 0.000091 grad: 0.2340 (0.2115) loss: 0.9711 (0.9779) time: 0.1773 data: 0.0888 max mem: 8299 +Train: [3] [4000/6250] eta: 0:06:01 lr: 0.000091 grad: 0.1450 (0.2112) loss: 0.9726 (0.9777) time: 0.1577 data: 0.0655 max mem: 8299 +Train: [3] [4100/6250] eta: 0:05:45 lr: 0.000091 grad: 0.1625 (0.2112) loss: 0.9675 (0.9775) time: 0.1356 data: 0.0461 max mem: 8299 +Train: [3] [4200/6250] eta: 0:05:28 lr: 0.000092 grad: 0.1478 (0.2104) loss: 0.9678 (0.9773) time: 0.1565 data: 0.0791 max mem: 8299 +Train: [3] [4300/6250] eta: 0:05:13 lr: 0.000092 grad: 0.1510 (0.2107) loss: 0.9685 (0.9771) time: 0.1568 data: 0.0778 max mem: 8299 +Train: [3] [4400/6250] eta: 0:04:56 lr: 0.000093 grad: 0.1466 (0.2107) loss: 0.9660 (0.9768) time: 0.1448 data: 0.0637 max mem: 8299 +Train: [3] [4500/6250] eta: 0:04:40 lr: 0.000093 grad: 0.1915 (0.2112) loss: 0.9663 (0.9766) time: 0.1469 data: 0.0713 max mem: 8299 +Train: [3] [4600/6250] eta: 0:04:24 lr: 0.000093 grad: 0.1862 (0.2112) loss: 0.9668 (0.9764) time: 0.1320 data: 0.0556 max mem: 8299 +Train: [3] [4700/6250] eta: 0:04:08 lr: 0.000094 grad: 0.2430 (0.2110) loss: 0.9640 (0.9761) time: 0.1516 data: 0.0639 max mem: 8299 +Train: [3] [4800/6250] eta: 0:03:51 lr: 0.000094 grad: 0.2253 (0.2111) loss: 0.9645 (0.9759) time: 0.1371 data: 0.0403 max mem: 8299 +Train: [3] [4900/6250] eta: 0:03:35 lr: 0.000095 grad: 0.1893 (0.2111) loss: 0.9659 (0.9756) time: 0.1746 data: 0.0905 max mem: 8299 +Train: [3] [5000/6250] eta: 0:03:20 lr: 0.000095 grad: 0.1607 (0.2111) loss: 0.9629 (0.9754) time: 0.1576 data: 0.0762 max mem: 8299 +Train: [3] [5100/6250] eta: 0:03:04 lr: 0.000095 grad: 0.1664 (0.2109) loss: 0.9611 (0.9751) time: 0.1957 data: 0.1111 max mem: 8299 +Train: [3] [5200/6250] eta: 0:02:48 lr: 0.000096 grad: 0.1822 (0.2109) loss: 0.9623 (0.9749) time: 0.1589 data: 0.0752 max mem: 8299 +Train: [3] [5300/6250] eta: 0:02:32 lr: 0.000096 grad: 0.1556 (0.2110) loss: 0.9632 (0.9746) time: 0.1788 data: 0.0893 max mem: 8299 +Train: [3] [5400/6250] eta: 0:02:16 lr: 0.000097 grad: 0.1744 (0.2111) loss: 0.9623 (0.9744) time: 0.1747 data: 0.0844 max mem: 8299 +Train: [3] [5500/6250] eta: 0:02:00 lr: 0.000097 grad: 0.2240 (0.2114) loss: 0.9597 (0.9742) time: 0.1948 data: 0.1067 max mem: 8299 +Train: [3] [5600/6250] eta: 0:01:44 lr: 0.000097 grad: 0.2788 (0.2117) loss: 0.9630 (0.9739) time: 0.1921 data: 0.1093 max mem: 8299 +Train: [3] [5700/6250] eta: 0:01:28 lr: 0.000098 grad: 0.2150 (0.2119) loss: 0.9604 (0.9737) time: 0.1425 data: 0.0616 max mem: 8299 +Train: [3] [5800/6250] eta: 0:01:12 lr: 0.000098 grad: 0.1973 (0.2120) loss: 0.9593 (0.9734) time: 0.1040 data: 0.0037 max mem: 8299 +Train: [3] [5900/6250] eta: 0:00:56 lr: 0.000099 grad: 0.1951 (0.2125) loss: 0.9591 (0.9732) time: 0.1501 data: 0.0557 max mem: 8299 +Train: [3] [6000/6250] eta: 0:00:40 lr: 0.000099 grad: 0.1804 (0.2127) loss: 0.9567 (0.9730) time: 0.1588 data: 0.0660 max mem: 8299 +Train: [3] [6100/6250] eta: 0:00:24 lr: 0.000099 grad: 0.2020 (0.2136) loss: 0.9596 (0.9727) time: 0.1864 data: 0.1035 max mem: 8299 +Train: [3] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.2190 (0.2135) loss: 0.9539 (0.9724) time: 0.1488 data: 0.0650 max mem: 8299 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.2082 (0.2136) loss: 0.9548 (0.9723) time: 0.1974 data: 0.1088 max mem: 8299 +Train: [3] Total time: 0:16:55 (0.1625 s / it) +Averaged stats: lr: 0.000100 grad: 0.2082 (0.2136) loss: 0.9548 (0.9723) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:04:08 loss: 0.9577 (0.9577) time: 4.0078 data: 3.9773 max mem: 8299 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9614 (0.9609) time: 0.1636 data: 0.1377 max mem: 8299 +Eval (hcp-train-subset): [3] Total time: 0:00:14 (0.2312 s / it) +Averaged stats (hcp-train-subset): loss: 0.9614 (0.9609) +Eval (hcp-val): [3] [ 0/62] eta: 0:05:50 loss: 0.9538 (0.9538) time: 5.6513 data: 5.6204 max mem: 8299 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9578 (0.9567) time: 0.1146 data: 0.0890 max mem: 8299 +Eval (hcp-val): [3] Total time: 0:00:13 (0.2208 s / it) +Averaged stats (hcp-val): loss: 0.9578 (0.9567) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 9:55:46 lr: 0.000100 grad: 0.4334 (0.4334) loss: 0.9783 (0.9783) time: 5.7194 data: 5.4844 max mem: 8299 +Train: [4] [ 100/6250] eta: 0:22:51 lr: 0.000100 grad: 0.2025 (0.2924) loss: 0.9551 (0.9594) time: 0.2019 data: 0.1071 max mem: 8299 +Train: [4] [ 200/6250] eta: 0:19:39 lr: 0.000101 grad: 0.2770 (0.2986) loss: 0.9621 (0.9578) time: 0.1558 data: 0.0656 max mem: 8299 +Train: [4] [ 300/6250] eta: 0:18:08 lr: 0.000101 grad: 0.2709 (0.2833) loss: 0.9601 (0.9572) time: 0.1484 data: 0.0556 max mem: 8299 +Train: [4] [ 400/6250] eta: 0:17:04 lr: 0.000102 grad: 0.1939 (0.2696) loss: 0.9547 (0.9568) time: 0.1311 data: 0.0369 max mem: 8299 +Train: [4] [ 500/6250] eta: 0:16:13 lr: 0.000102 grad: 0.1972 (0.2622) loss: 0.9543 (0.9561) time: 0.1362 data: 0.0371 max mem: 8299 +Train: [4] [ 600/6250] eta: 0:15:36 lr: 0.000102 grad: 0.2096 (0.2656) loss: 0.9555 (0.9558) time: 0.1275 data: 0.0309 max mem: 8299 +Train: [4] [ 700/6250] eta: 0:15:15 lr: 0.000103 grad: 0.1974 (0.2615) loss: 0.9527 (0.9554) time: 0.1567 data: 0.0665 max mem: 8299 +Train: [4] [ 800/6250] eta: 0:15:00 lr: 0.000103 grad: 0.2069 (0.2583) loss: 0.9503 (0.9548) time: 0.1674 data: 0.0800 max mem: 8299 +Train: [4] [ 900/6250] eta: 0:14:42 lr: 0.000104 grad: 0.1856 (0.2575) loss: 0.9502 (0.9543) time: 0.1349 data: 0.0578 max mem: 8299 +Train: [4] [1000/6250] eta: 0:14:26 lr: 0.000104 grad: 0.2091 (0.2543) loss: 0.9472 (0.9538) time: 0.1595 data: 0.0667 max mem: 8299 +Train: [4] [1100/6250] eta: 0:14:06 lr: 0.000104 grad: 0.2059 (0.2554) loss: 0.9477 (0.9533) time: 0.1422 data: 0.0593 max mem: 8299 +Train: [4] [1200/6250] eta: 0:13:47 lr: 0.000105 grad: 0.2118 (0.2562) loss: 0.9484 (0.9529) time: 0.1548 data: 0.0713 max mem: 8299 +Train: [4] [1300/6250] eta: 0:13:55 lr: 0.000105 grad: 0.2936 (0.2570) loss: 0.9465 (0.9525) time: 0.1529 data: 0.0592 max mem: 8299 +Train: [4] [1400/6250] eta: 0:13:38 lr: 0.000106 grad: 0.2798 (0.2592) loss: 0.9470 (0.9521) time: 0.1565 data: 0.0806 max mem: 8299 +Train: [4] [1500/6250] eta: 0:13:21 lr: 0.000106 grad: 0.1565 (0.2582) loss: 0.9467 (0.9518) time: 0.1698 data: 0.0784 max mem: 8299 +Train: [4] [1600/6250] eta: 0:13:06 lr: 0.000106 grad: 0.2160 (0.2573) loss: 0.9466 (0.9514) time: 0.1770 data: 0.0930 max mem: 8299 +Train: [4] [1700/6250] eta: 0:12:45 lr: 0.000107 grad: 0.2045 (0.2547) loss: 0.9469 (0.9511) time: 0.1651 data: 0.0796 max mem: 8299 +Train: [4] [1800/6250] eta: 0:12:28 lr: 0.000107 grad: 0.2741 (0.2542) loss: 0.9465 (0.9508) time: 0.1301 data: 0.0480 max mem: 8299 +Train: [4] [1900/6250] eta: 0:12:08 lr: 0.000108 grad: 0.2138 (0.2522) loss: 0.9451 (0.9505) time: 0.1607 data: 0.0779 max mem: 8299 +Train: [4] [2000/6250] eta: 0:11:48 lr: 0.000108 grad: 0.2081 (0.2532) loss: 0.9440 (0.9502) time: 0.1630 data: 0.0865 max mem: 8299 +Train: [4] [2100/6250] eta: 0:11:30 lr: 0.000108 grad: 0.1646 (0.2523) loss: 0.9450 (0.9499) time: 0.1716 data: 0.0969 max mem: 8299 +Train: [4] [2200/6250] eta: 0:11:10 lr: 0.000109 grad: 0.2361 (0.2515) loss: 0.9435 (0.9497) time: 0.1453 data: 0.0511 max mem: 8299 +Train: [4] [2300/6250] eta: 0:10:52 lr: 0.000109 grad: 0.2308 (0.2511) loss: 0.9428 (0.9494) time: 0.1674 data: 0.0824 max mem: 8299 +Train: [4] [2400/6250] eta: 0:10:34 lr: 0.000110 grad: 0.1891 (0.2499) loss: 0.9470 (0.9492) time: 0.1617 data: 0.0660 max mem: 8299 +Train: [4] [2500/6250] eta: 0:10:17 lr: 0.000110 grad: 0.2126 (0.2487) loss: 0.9440 (0.9489) time: 0.1673 data: 0.0819 max mem: 8299 +Train: [4] [2600/6250] eta: 0:09:59 lr: 0.000110 grad: 0.2597 (0.2474) loss: 0.9437 (0.9487) time: 0.1530 data: 0.0641 max mem: 8299 +Train: [4] [2700/6250] eta: 0:09:41 lr: 0.000111 grad: 0.2293 (0.2459) loss: 0.9417 (0.9484) time: 0.1296 data: 0.0552 max mem: 8299 +Train: [4] [2800/6250] eta: 0:09:23 lr: 0.000111 grad: 0.1834 (0.2447) loss: 0.9409 (0.9482) time: 0.1606 data: 0.0837 max mem: 8299 +Train: [4] [2900/6250] eta: 0:09:05 lr: 0.000112 grad: 0.2033 (0.2443) loss: 0.9426 (0.9479) time: 0.1323 data: 0.0513 max mem: 8299 +Train: [4] [3000/6250] eta: 0:08:48 lr: 0.000112 grad: 0.2173 (0.2440) loss: 0.9348 (0.9476) time: 0.1485 data: 0.0867 max mem: 8299 +Train: [4] [3100/6250] eta: 0:08:31 lr: 0.000112 grad: 0.1924 (0.2429) loss: 0.9405 (0.9473) time: 0.1836 data: 0.0868 max mem: 8299 +Train: [4] [3200/6250] eta: 0:08:16 lr: 0.000113 grad: 0.1809 (0.2418) loss: 0.9378 (0.9470) time: 0.1832 data: 0.1087 max mem: 8299 +Train: [4] [3300/6250] eta: 0:07:59 lr: 0.000113 grad: 0.1695 (0.2416) loss: 0.9410 (0.9467) time: 0.1473 data: 0.0663 max mem: 8299 +Train: [4] [3400/6250] eta: 0:07:41 lr: 0.000114 grad: 0.1996 (0.2406) loss: 0.9363 (0.9464) time: 0.1352 data: 0.0680 max mem: 8299 +Train: [4] [3500/6250] eta: 0:07:24 lr: 0.000114 grad: 0.1588 (0.2392) loss: 0.9341 (0.9461) time: 0.1550 data: 0.0772 max mem: 8299 +Train: [4] [3600/6250] eta: 0:07:08 lr: 0.000114 grad: 0.1561 (0.2390) loss: 0.9353 (0.9458) time: 0.1768 data: 0.0954 max mem: 8299 +Train: [4] [3700/6250] eta: 0:06:52 lr: 0.000115 grad: 0.1877 (0.2387) loss: 0.9355 (0.9455) time: 0.1094 data: 0.0141 max mem: 8299 +Train: [4] [3800/6250] eta: 0:06:36 lr: 0.000115 grad: 0.2267 (0.2381) loss: 0.9383 (0.9452) time: 0.1473 data: 0.0477 max mem: 8299 +Train: [4] [3900/6250] eta: 0:06:19 lr: 0.000116 grad: 0.1662 (0.2375) loss: 0.9375 (0.9450) time: 0.1168 data: 0.0333 max mem: 8299 +Train: [4] [4000/6250] eta: 0:06:03 lr: 0.000116 grad: 0.1660 (0.2369) loss: 0.9334 (0.9447) time: 0.1510 data: 0.0589 max mem: 8299 +Train: [4] [4100/6250] eta: 0:05:47 lr: 0.000116 grad: 0.1701 (0.2359) loss: 0.9336 (0.9445) time: 0.1265 data: 0.0289 max mem: 8299 +Train: [4] [4200/6250] eta: 0:05:30 lr: 0.000117 grad: 0.1833 (0.2352) loss: 0.9343 (0.9442) time: 0.1745 data: 0.0841 max mem: 8299 +Train: [4] [4300/6250] eta: 0:05:14 lr: 0.000117 grad: 0.1761 (0.2346) loss: 0.9312 (0.9439) time: 0.1440 data: 0.0539 max mem: 8299 +Train: [4] [4400/6250] eta: 0:04:57 lr: 0.000118 grad: 0.2085 (0.2340) loss: 0.9337 (0.9436) time: 0.1513 data: 0.0804 max mem: 8299 +Train: [4] [4500/6250] eta: 0:04:41 lr: 0.000118 grad: 0.1673 (0.2331) loss: 0.9326 (0.9434) time: 0.1328 data: 0.0513 max mem: 8299 +Train: [4] [4600/6250] eta: 0:04:25 lr: 0.000118 grad: 0.1804 (0.2323) loss: 0.9278 (0.9431) time: 0.1389 data: 0.0585 max mem: 8299 +Train: [4] [4700/6250] eta: 0:04:09 lr: 0.000119 grad: 0.2228 (0.2319) loss: 0.9332 (0.9428) time: 0.1622 data: 0.0717 max mem: 8299 +Train: [4] [4800/6250] eta: 0:03:53 lr: 0.000119 grad: 0.1896 (0.2316) loss: 0.9260 (0.9425) time: 0.1660 data: 0.0756 max mem: 8299 +Train: [4] [4900/6250] eta: 0:03:36 lr: 0.000120 grad: 0.1842 (0.2308) loss: 0.9317 (0.9423) time: 0.1485 data: 0.0605 max mem: 8299 +Train: [4] [5000/6250] eta: 0:03:21 lr: 0.000120 grad: 0.1733 (0.2303) loss: 0.9345 (0.9420) time: 0.1806 data: 0.1061 max mem: 8299 +Train: [4] [5100/6250] eta: 0:03:05 lr: 0.000120 grad: 0.1690 (0.2295) loss: 0.9296 (0.9418) time: 0.1750 data: 0.0963 max mem: 8299 +Train: [4] [5200/6250] eta: 0:02:49 lr: 0.000121 grad: 0.2010 (0.2293) loss: 0.9247 (0.9415) time: 0.1376 data: 0.0626 max mem: 8299 +Train: [4] [5300/6250] eta: 0:02:32 lr: 0.000121 grad: 0.1843 (0.2287) loss: 0.9294 (0.9412) time: 0.1433 data: 0.0553 max mem: 8299 +Train: [4] [5400/6250] eta: 0:02:16 lr: 0.000122 grad: 0.1721 (0.2280) loss: 0.9249 (0.9410) time: 0.1526 data: 0.0683 max mem: 8299 +Train: [4] [5500/6250] eta: 0:02:00 lr: 0.000122 grad: 0.2479 (0.2281) loss: 0.9285 (0.9408) time: 0.1562 data: 0.0863 max mem: 8299 +Train: [4] [5600/6250] eta: 0:01:44 lr: 0.000122 grad: 0.1632 (0.2274) loss: 0.9295 (0.9405) time: 0.1482 data: 0.0736 max mem: 8299 +Train: [4] [5700/6250] eta: 0:01:27 lr: 0.000123 grad: 0.1487 (0.2265) loss: 0.9249 (0.9403) time: 0.1338 data: 0.0605 max mem: 8299 +Train: [4] [5800/6250] eta: 0:01:11 lr: 0.000123 grad: 0.1945 (0.2260) loss: 0.9251 (0.9401) time: 0.1192 data: 0.0381 max mem: 8299 +Train: [4] [5900/6250] eta: 0:00:55 lr: 0.000124 grad: 0.1355 (0.2253) loss: 0.9297 (0.9399) time: 0.1618 data: 0.0857 max mem: 8299 +Train: [4] [6000/6250] eta: 0:00:39 lr: 0.000124 grad: 0.1559 (0.2247) loss: 0.9257 (0.9397) time: 0.1775 data: 0.0906 max mem: 8299 +Train: [4] [6100/6250] eta: 0:00:23 lr: 0.000124 grad: 0.1849 (0.2240) loss: 0.9221 (0.9395) time: 0.1556 data: 0.0765 max mem: 8299 +Train: [4] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.1737 (0.2232) loss: 0.9263 (0.9393) time: 0.1223 data: 0.0423 max mem: 8299 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1576 (0.2228) loss: 0.9270 (0.9392) time: 0.1312 data: 0.0450 max mem: 8299 +Train: [4] Total time: 0:16:37 (0.1597 s / it) +Averaged stats: lr: 0.000125 grad: 0.1576 (0.2228) loss: 0.9270 (0.9392) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:03:21 loss: 0.9407 (0.9407) time: 3.2469 data: 3.1825 max mem: 8299 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9320 (0.9317) time: 0.0905 data: 0.0660 max mem: 8299 +Eval (hcp-train-subset): [4] Total time: 0:00:14 (0.2388 s / it) +Averaged stats (hcp-train-subset): loss: 0.9320 (0.9317) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [4] [ 0/62] eta: 0:04:44 loss: 0.9283 (0.9283) time: 4.5895 data: 4.5597 max mem: 8299 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9267 (0.9266) time: 0.1248 data: 0.0998 max mem: 8299 +Eval (hcp-val): [4] Total time: 0:00:15 (0.2560 s / it) +Averaged stats (hcp-val): loss: 0.9267 (0.9266) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 7:03:07 lr: 0.000125 grad: 0.2378 (0.2378) loss: 0.8837 (0.8837) time: 4.0620 data: 3.8557 max mem: 8299 +Train: [5] [ 100/6250] eta: 0:20:33 lr: 0.000125 grad: 0.1560 (0.1774) loss: 0.9332 (0.9346) time: 0.1736 data: 0.0880 max mem: 8299 +Train: [5] [ 200/6250] eta: 0:18:05 lr: 0.000125 grad: 0.2123 (0.1760) loss: 0.9210 (0.9321) time: 0.1615 data: 0.0786 max mem: 8299 +Train: [5] [ 300/6250] eta: 0:16:57 lr: 0.000125 grad: 0.1389 (0.1886) loss: 0.9236 (0.9299) time: 0.1325 data: 0.0429 max mem: 8299 +Train: [5] [ 400/6250] eta: 0:16:16 lr: 0.000125 grad: 0.1433 (0.1840) loss: 0.9258 (0.9289) time: 0.1677 data: 0.0760 max mem: 8299 +Train: [5] [ 500/6250] eta: 0:15:46 lr: 0.000125 grad: 0.1547 (0.1797) loss: 0.9242 (0.9283) time: 0.1381 data: 0.0354 max mem: 8299 +Train: [5] [ 600/6250] eta: 0:15:11 lr: 0.000125 grad: 0.1604 (0.1784) loss: 0.9215 (0.9277) time: 0.1389 data: 0.0521 max mem: 8299 +Train: [5] [ 700/6250] eta: 0:14:42 lr: 0.000125 grad: 0.1496 (0.1777) loss: 0.9242 (0.9273) time: 0.1397 data: 0.0536 max mem: 8299 +Train: [5] [ 800/6250] eta: 0:14:14 lr: 0.000125 grad: 0.1386 (0.1763) loss: 0.9271 (0.9269) time: 0.1523 data: 0.0604 max mem: 8299 +Train: [5] [ 900/6250] eta: 0:14:01 lr: 0.000125 grad: 0.1467 (0.1772) loss: 0.9268 (0.9267) time: 0.1681 data: 0.0720 max mem: 8299 +Train: [5] [1000/6250] eta: 0:13:43 lr: 0.000125 grad: 0.1331 (0.1752) loss: 0.9268 (0.9264) time: 0.1635 data: 0.0900 max mem: 8299 +Train: [5] [1100/6250] eta: 0:13:29 lr: 0.000125 grad: 0.1648 (0.1759) loss: 0.9257 (0.9262) time: 0.1840 data: 0.0915 max mem: 8299 +Train: [5] [1200/6250] eta: 0:13:14 lr: 0.000125 grad: 0.1361 (0.1742) loss: 0.9239 (0.9261) time: 0.1726 data: 0.0869 max mem: 8299 +Train: [5] [1300/6250] eta: 0:12:58 lr: 0.000125 grad: 0.1476 (0.1739) loss: 0.9198 (0.9258) time: 0.1716 data: 0.0722 max mem: 8299 +Train: [5] [1400/6250] eta: 0:12:42 lr: 0.000125 grad: 0.1564 (0.1724) loss: 0.9255 (0.9256) time: 0.1482 data: 0.0793 max mem: 8299 +Train: [5] [1500/6250] eta: 0:12:23 lr: 0.000125 grad: 0.1357 (0.1711) loss: 0.9242 (0.9254) time: 0.1350 data: 0.0544 max mem: 8299 +Train: [5] [1600/6250] eta: 0:12:05 lr: 0.000125 grad: 0.1397 (0.1712) loss: 0.9230 (0.9252) time: 0.1662 data: 0.0687 max mem: 8299 +Train: [5] [1700/6250] eta: 0:11:46 lr: 0.000125 grad: 0.1629 (0.1709) loss: 0.9232 (0.9251) time: 0.1420 data: 0.0578 max mem: 8299 +Train: [5] [1800/6250] eta: 0:11:28 lr: 0.000125 grad: 0.1176 (0.1702) loss: 0.9213 (0.9250) time: 0.1512 data: 0.0681 max mem: 8299 +Train: [5] [1900/6250] eta: 0:11:13 lr: 0.000125 grad: 0.1394 (0.1703) loss: 0.9262 (0.9250) time: 0.1243 data: 0.0388 max mem: 8299 +Train: [5] [2000/6250] eta: 0:10:56 lr: 0.000125 grad: 0.1574 (0.1701) loss: 0.9223 (0.9248) time: 0.1294 data: 0.0426 max mem: 8299 +Train: [5] [2100/6250] eta: 0:10:38 lr: 0.000125 grad: 0.1311 (0.1688) loss: 0.9195 (0.9247) time: 0.1395 data: 0.0579 max mem: 8299 +Train: [5] [2200/6250] eta: 0:10:23 lr: 0.000125 grad: 0.1268 (0.1681) loss: 0.9224 (0.9246) time: 0.1277 data: 0.0366 max mem: 8299 +Train: [5] [2300/6250] eta: 0:10:08 lr: 0.000125 grad: 0.1501 (0.1675) loss: 0.9259 (0.9244) time: 0.1478 data: 0.0593 max mem: 8299 +Train: [5] [2400/6250] eta: 0:09:52 lr: 0.000125 grad: 0.1435 (0.1668) loss: 0.9221 (0.9243) time: 0.1498 data: 0.0796 max mem: 8299 +Train: [5] [2500/6250] eta: 0:09:36 lr: 0.000125 grad: 0.1379 (0.1658) loss: 0.9221 (0.9241) time: 0.1195 data: 0.0226 max mem: 8299 +Train: [5] [2600/6250] eta: 0:09:21 lr: 0.000125 grad: 0.1629 (0.1655) loss: 0.9219 (0.9240) time: 0.1429 data: 0.0614 max mem: 8299 +Train: [5] [2700/6250] eta: 0:09:07 lr: 0.000125 grad: 0.1181 (0.1655) loss: 0.9195 (0.9239) time: 0.1759 data: 0.0948 max mem: 8299 +Train: [5] [2800/6250] eta: 0:08:52 lr: 0.000125 grad: 0.1259 (0.1651) loss: 0.9217 (0.9237) time: 0.1419 data: 0.0553 max mem: 8299 +Train: [5] [2900/6250] eta: 0:08:36 lr: 0.000125 grad: 0.1704 (0.1646) loss: 0.9199 (0.9236) time: 0.1119 data: 0.0350 max mem: 8299 +Train: [5] [3000/6250] eta: 0:08:21 lr: 0.000125 grad: 0.1350 (0.1645) loss: 0.9215 (0.9235) time: 0.1480 data: 0.0696 max mem: 8299 +Train: [5] [3100/6250] eta: 0:08:05 lr: 0.000125 grad: 0.1203 (0.1636) loss: 0.9163 (0.9233) time: 0.1450 data: 0.0611 max mem: 8299 +Train: [5] [3200/6250] eta: 0:07:50 lr: 0.000125 grad: 0.1164 (0.1632) loss: 0.9204 (0.9233) time: 0.1411 data: 0.0589 max mem: 8299 +Train: [5] [3300/6250] eta: 0:07:34 lr: 0.000125 grad: 0.1223 (0.1627) loss: 0.9178 (0.9231) time: 0.1666 data: 0.0831 max mem: 8299 +Train: [5] [3400/6250] eta: 0:07:19 lr: 0.000125 grad: 0.1227 (0.1619) loss: 0.9188 (0.9230) time: 0.1421 data: 0.0524 max mem: 8299 +Train: [5] [3500/6250] eta: 0:07:02 lr: 0.000125 grad: 0.1153 (0.1610) loss: 0.9215 (0.9230) time: 0.1573 data: 0.0768 max mem: 8299 +Train: [5] [3600/6250] eta: 0:06:47 lr: 0.000125 grad: 0.1092 (0.1605) loss: 0.9178 (0.9229) time: 0.1505 data: 0.0610 max mem: 8299 +Train: [5] [3700/6250] eta: 0:06:32 lr: 0.000125 grad: 0.1069 (0.1598) loss: 0.9200 (0.9228) time: 0.1511 data: 0.0695 max mem: 8299 +Train: [5] [3800/6250] eta: 0:06:17 lr: 0.000125 grad: 0.1556 (0.1593) loss: 0.9180 (0.9228) time: 0.1403 data: 0.0554 max mem: 8299 +Train: [5] [3900/6250] eta: 0:06:02 lr: 0.000125 grad: 0.1393 (0.1592) loss: 0.9237 (0.9227) time: 0.1553 data: 0.0718 max mem: 8299 +Train: [5] [4000/6250] eta: 0:05:46 lr: 0.000125 grad: 0.1247 (0.1584) loss: 0.9181 (0.9226) time: 0.1614 data: 0.0713 max mem: 8299 +Train: [5] [4100/6250] eta: 0:05:31 lr: 0.000125 grad: 0.1877 (0.1583) loss: 0.9202 (0.9225) time: 0.1608 data: 0.0752 max mem: 8299 +Train: [5] [4200/6250] eta: 0:05:15 lr: 0.000125 grad: 0.1191 (0.1577) loss: 0.9220 (0.9224) time: 0.1447 data: 0.0676 max mem: 8299 +Train: [5] [4300/6250] eta: 0:05:00 lr: 0.000125 grad: 0.1204 (0.1570) loss: 0.9178 (0.9223) time: 0.1359 data: 0.0619 max mem: 8299 +Train: [5] [4400/6250] eta: 0:04:45 lr: 0.000125 grad: 0.1071 (0.1562) loss: 0.9164 (0.9222) time: 0.1522 data: 0.0704 max mem: 8299 +Train: [5] [4500/6250] eta: 0:04:29 lr: 0.000125 grad: 0.1241 (0.1559) loss: 0.9175 (0.9221) time: 0.1519 data: 0.0782 max mem: 8299 +Train: [5] [4600/6250] eta: 0:04:14 lr: 0.000125 grad: 0.1327 (0.1553) loss: 0.9185 (0.9220) time: 0.1428 data: 0.0564 max mem: 8299 +Train: [5] [4700/6250] eta: 0:03:59 lr: 0.000125 grad: 0.1191 (0.1547) loss: 0.9113 (0.9218) time: 0.1684 data: 0.0947 max mem: 8299 +Train: [5] [4800/6250] eta: 0:03:43 lr: 0.000125 grad: 0.1041 (0.1541) loss: 0.9214 (0.9218) time: 0.1279 data: 0.0555 max mem: 8299 +Train: [5] [4900/6250] eta: 0:03:28 lr: 0.000125 grad: 0.1240 (0.1537) loss: 0.9173 (0.9217) time: 0.1433 data: 0.0615 max mem: 8299 +Train: [5] [5000/6250] eta: 0:03:12 lr: 0.000125 grad: 0.1278 (0.1532) loss: 0.9129 (0.9216) time: 0.1342 data: 0.0582 max mem: 8299 +Train: [5] [5100/6250] eta: 0:02:57 lr: 0.000125 grad: 0.1134 (0.1527) loss: 0.9163 (0.9215) time: 0.1367 data: 0.0443 max mem: 8299 +Train: [5] [5200/6250] eta: 0:02:41 lr: 0.000125 grad: 0.1338 (0.1523) loss: 0.9158 (0.9213) time: 0.1493 data: 0.0492 max mem: 8299 +Train: [5] [5300/6250] eta: 0:02:26 lr: 0.000125 grad: 0.1531 (0.1520) loss: 0.9157 (0.9212) time: 0.1303 data: 0.0515 max mem: 8299 +Train: [5] [5400/6250] eta: 0:02:10 lr: 0.000125 grad: 0.1059 (0.1515) loss: 0.9162 (0.9211) time: 0.1218 data: 0.0484 max mem: 8299 +Train: [5] [5500/6250] eta: 0:01:55 lr: 0.000125 grad: 0.1330 (0.1512) loss: 0.9172 (0.9210) time: 0.1359 data: 0.0563 max mem: 8299 +Train: [5] [5600/6250] eta: 0:01:39 lr: 0.000125 grad: 0.1031 (0.1506) loss: 0.9163 (0.9209) time: 0.1618 data: 0.0903 max mem: 8299 +Train: [5] [5700/6250] eta: 0:01:24 lr: 0.000125 grad: 0.1084 (0.1501) loss: 0.9117 (0.9207) time: 0.1391 data: 0.0719 max mem: 8299 +Train: [5] [5800/6250] eta: 0:01:09 lr: 0.000125 grad: 0.1355 (0.1498) loss: 0.9136 (0.9206) time: 0.1451 data: 0.0502 max mem: 8299 +Train: [5] [5900/6250] eta: 0:00:53 lr: 0.000125 grad: 0.1211 (0.1494) loss: 0.9146 (0.9205) time: 0.1581 data: 0.0667 max mem: 8299 +Train: [5] [6000/6250] eta: 0:00:38 lr: 0.000125 grad: 0.1204 (0.1489) loss: 0.9111 (0.9204) time: 0.1221 data: 0.0424 max mem: 8299 +Train: [5] [6100/6250] eta: 0:00:23 lr: 0.000125 grad: 0.1191 (0.1485) loss: 0.9121 (0.9203) time: 0.1795 data: 0.0948 max mem: 8299 +Train: [5] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.1073 (0.1482) loss: 0.9147 (0.9202) time: 0.1284 data: 0.0554 max mem: 8299 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1169 (0.1479) loss: 0.9110 (0.9201) time: 0.1598 data: 0.0798 max mem: 8299 +Train: [5] Total time: 0:16:08 (0.1550 s / it) +Averaged stats: lr: 0.000125 grad: 0.1169 (0.1479) loss: 0.9110 (0.9201) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:04:21 loss: 0.9249 (0.9249) time: 4.2148 data: 4.1838 max mem: 8299 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.9175 (0.9172) time: 0.1384 data: 0.1113 max mem: 8299 +Eval (hcp-train-subset): [5] Total time: 0:00:15 (0.2512 s / it) +Averaged stats (hcp-train-subset): loss: 0.9175 (0.9172) +Eval (hcp-val): [5] [ 0/62] eta: 0:06:06 loss: 0.9104 (0.9104) time: 5.9061 data: 5.8583 max mem: 8299 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.9115 (0.9118) time: 0.1436 data: 0.1189 max mem: 8299 +Eval (hcp-val): [5] Total time: 0:00:14 (0.2349 s / it) +Averaged stats (hcp-val): loss: 0.9115 (0.9118) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 11:08:31 lr: 0.000125 grad: 0.1060 (0.1060) loss: 0.9424 (0.9424) time: 6.4179 data: 6.3221 max mem: 8299 +Train: [6] [ 100/6250] eta: 0:22:19 lr: 0.000125 grad: 0.1140 (0.1453) loss: 0.9093 (0.9173) time: 0.1752 data: 0.0738 max mem: 8299 +Train: [6] [ 200/6250] eta: 0:19:36 lr: 0.000125 grad: 0.1593 (0.1419) loss: 0.9125 (0.9151) time: 0.1780 data: 0.0895 max mem: 8299 +Train: [6] [ 300/6250] eta: 0:17:53 lr: 0.000125 grad: 0.1163 (0.1349) loss: 0.9119 (0.9140) time: 0.1412 data: 0.0508 max mem: 8299 +Train: [6] [ 400/6250] eta: 0:17:10 lr: 0.000125 grad: 0.1278 (0.1339) loss: 0.9113 (0.9134) time: 0.1573 data: 0.0656 max mem: 8299 +Train: [6] [ 500/6250] eta: 0:16:17 lr: 0.000125 grad: 0.1048 (0.1341) loss: 0.9092 (0.9131) time: 0.1310 data: 0.0383 max mem: 8299 +Train: [6] [ 600/6250] eta: 0:15:41 lr: 0.000125 grad: 0.1037 (0.1319) loss: 0.9124 (0.9129) time: 0.1472 data: 0.0537 max mem: 8299 +Train: [6] [ 700/6250] eta: 0:15:12 lr: 0.000125 grad: 0.1289 (0.1310) loss: 0.9151 (0.9126) time: 0.1482 data: 0.0584 max mem: 8299 +Train: [6] [ 800/6250] eta: 0:14:44 lr: 0.000125 grad: 0.1012 (0.1290) loss: 0.9057 (0.9122) time: 0.1495 data: 0.0613 max mem: 8299 +Train: [6] [ 900/6250] eta: 0:14:30 lr: 0.000125 grad: 0.1096 (0.1274) loss: 0.9051 (0.9117) time: 0.1705 data: 0.0652 max mem: 8299 +Train: [6] [1000/6250] eta: 0:14:12 lr: 0.000125 grad: 0.0953 (0.1263) loss: 0.9079 (0.9115) time: 0.1490 data: 0.0689 max mem: 8299 +Train: [6] [1100/6250] eta: 0:13:54 lr: 0.000125 grad: 0.0988 (0.1251) loss: 0.9109 (0.9114) time: 0.1637 data: 0.0882 max mem: 8299 +Train: [6] [1200/6250] eta: 0:13:39 lr: 0.000125 grad: 0.1123 (0.1247) loss: 0.9108 (0.9112) time: 0.1513 data: 0.0722 max mem: 8299 +Train: [6] [1300/6250] eta: 0:13:23 lr: 0.000125 grad: 0.0940 (0.1239) loss: 0.9103 (0.9112) time: 0.1510 data: 0.0618 max mem: 8299 +Train: [6] [1400/6250] eta: 0:13:11 lr: 0.000125 grad: 0.1091 (0.1230) loss: 0.9083 (0.9109) time: 0.1666 data: 0.0945 max mem: 8299 +Train: [6] [1500/6250] eta: 0:12:54 lr: 0.000125 grad: 0.1005 (0.1227) loss: 0.9146 (0.9107) time: 0.1542 data: 0.0742 max mem: 8299 +Train: [6] [1600/6250] eta: 0:12:33 lr: 0.000125 grad: 0.1066 (0.1224) loss: 0.9079 (0.9107) time: 0.1353 data: 0.0590 max mem: 8299 +Train: [6] [1700/6250] eta: 0:12:16 lr: 0.000125 grad: 0.1124 (0.1217) loss: 0.9046 (0.9106) time: 0.1584 data: 0.0763 max mem: 8299 +Train: [6] [1800/6250] eta: 0:11:56 lr: 0.000125 grad: 0.1039 (0.1210) loss: 0.9102 (0.9105) time: 0.1498 data: 0.0689 max mem: 8299 +Train: [6] [1900/6250] eta: 0:11:36 lr: 0.000125 grad: 0.0966 (0.1206) loss: 0.9100 (0.9105) time: 0.1601 data: 0.0697 max mem: 8299 +Train: [6] [2000/6250] eta: 0:11:18 lr: 0.000125 grad: 0.0958 (0.1202) loss: 0.9138 (0.9105) time: 0.1478 data: 0.0614 max mem: 8299 +Train: [6] [2100/6250] eta: 0:11:01 lr: 0.000125 grad: 0.1001 (0.1197) loss: 0.9094 (0.9104) time: 0.1413 data: 0.0569 max mem: 8299 +Train: [6] [2200/6250] eta: 0:10:44 lr: 0.000125 grad: 0.1149 (0.1194) loss: 0.9111 (0.9104) time: 0.1487 data: 0.0611 max mem: 8299 +Train: [6] [2300/6250] eta: 0:10:26 lr: 0.000125 grad: 0.1074 (0.1188) loss: 0.9107 (0.9104) time: 0.1465 data: 0.0551 max mem: 8299 +Train: [6] [2400/6250] eta: 0:10:11 lr: 0.000125 grad: 0.1099 (0.1182) loss: 0.9096 (0.9104) time: 0.1609 data: 0.0786 max mem: 8299 +Train: [6] [2500/6250] eta: 0:09:57 lr: 0.000125 grad: 0.0973 (0.1178) loss: 0.9090 (0.9103) time: 0.1691 data: 0.0877 max mem: 8299 +Train: [6] [2600/6250] eta: 0:09:41 lr: 0.000125 grad: 0.1011 (0.1173) loss: 0.9087 (0.9102) time: 0.1673 data: 0.0775 max mem: 8299 +Train: [6] [2700/6250] eta: 0:09:26 lr: 0.000125 grad: 0.1079 (0.1172) loss: 0.9075 (0.9101) time: 0.1849 data: 0.1101 max mem: 8299 +Train: [6] [2800/6250] eta: 0:09:09 lr: 0.000125 grad: 0.1074 (0.1170) loss: 0.9044 (0.9100) time: 0.1304 data: 0.0476 max mem: 8299 +Train: [6] [2900/6250] eta: 0:08:53 lr: 0.000125 grad: 0.0882 (0.1165) loss: 0.9079 (0.9099) time: 0.1543 data: 0.0792 max mem: 8299 +Train: [6] [3000/6250] eta: 0:08:37 lr: 0.000125 grad: 0.1040 (0.1164) loss: 0.9060 (0.9098) time: 0.1473 data: 0.0683 max mem: 8299 +Train: [6] [3100/6250] eta: 0:08:20 lr: 0.000125 grad: 0.1092 (0.1160) loss: 0.9087 (0.9098) time: 0.1475 data: 0.0631 max mem: 8299 +Train: [6] [3200/6250] eta: 0:08:05 lr: 0.000125 grad: 0.0880 (0.1157) loss: 0.9122 (0.9097) time: 0.1629 data: 0.0853 max mem: 8299 +Train: [6] [3300/6250] eta: 0:07:48 lr: 0.000125 grad: 0.0991 (0.1156) loss: 0.9086 (0.9097) time: 0.1339 data: 0.0553 max mem: 8299 +Train: [6] [3400/6250] eta: 0:07:33 lr: 0.000125 grad: 0.1042 (0.1154) loss: 0.9093 (0.9097) time: 0.1650 data: 0.0784 max mem: 8299 +Train: [6] [3500/6250] eta: 0:07:16 lr: 0.000125 grad: 0.0963 (0.1150) loss: 0.9098 (0.9097) time: 0.1379 data: 0.0550 max mem: 8299 +Train: [6] [3600/6250] eta: 0:07:00 lr: 0.000125 grad: 0.0972 (0.1147) loss: 0.9065 (0.9096) time: 0.1563 data: 0.0843 max mem: 8299 +Train: [6] [3700/6250] eta: 0:06:44 lr: 0.000125 grad: 0.0952 (0.1145) loss: 0.9083 (0.9096) time: 0.1697 data: 0.0901 max mem: 8299 +Train: [6] [3800/6250] eta: 0:06:27 lr: 0.000125 grad: 0.0974 (0.1142) loss: 0.9062 (0.9096) time: 0.1591 data: 0.0872 max mem: 8299 +Train: [6] [3900/6250] eta: 0:06:12 lr: 0.000125 grad: 0.0857 (0.1138) loss: 0.9030 (0.9095) time: 0.1588 data: 0.0765 max mem: 8299 +Train: [6] [4000/6250] eta: 0:05:55 lr: 0.000125 grad: 0.0792 (0.1135) loss: 0.9049 (0.9095) time: 0.1339 data: 0.0587 max mem: 8299 +Train: [6] [4100/6250] eta: 0:05:39 lr: 0.000125 grad: 0.1013 (0.1135) loss: 0.9049 (0.9094) time: 0.1680 data: 0.0709 max mem: 8299 +Train: [6] [4200/6250] eta: 0:05:23 lr: 0.000125 grad: 0.0941 (0.1132) loss: 0.9069 (0.9094) time: 0.1369 data: 0.0486 max mem: 8299 +Train: [6] [4300/6250] eta: 0:05:08 lr: 0.000125 grad: 0.0963 (0.1130) loss: 0.9061 (0.9093) time: 0.1692 data: 0.0693 max mem: 8299 +Train: [6] [4400/6250] eta: 0:04:52 lr: 0.000125 grad: 0.0954 (0.1127) loss: 0.9045 (0.9092) time: 0.1676 data: 0.0737 max mem: 8299 +Train: [6] [4500/6250] eta: 0:04:36 lr: 0.000125 grad: 0.0951 (0.1123) loss: 0.9058 (0.9091) time: 0.1542 data: 0.0765 max mem: 8299 +Train: [6] [4600/6250] eta: 0:04:20 lr: 0.000125 grad: 0.0907 (0.1121) loss: 0.9044 (0.9091) time: 0.1736 data: 0.0934 max mem: 8299 +Train: [6] [4700/6250] eta: 0:04:04 lr: 0.000125 grad: 0.0928 (0.1119) loss: 0.9012 (0.9090) time: 0.2039 data: 0.1208 max mem: 8299 +Train: [6] [4800/6250] eta: 0:03:48 lr: 0.000125 grad: 0.0990 (0.1117) loss: 0.9061 (0.9089) time: 0.1417 data: 0.0601 max mem: 8299 +Train: [6] [4900/6250] eta: 0:03:32 lr: 0.000125 grad: 0.0909 (0.1114) loss: 0.9014 (0.9088) time: 0.1725 data: 0.0865 max mem: 8299 +Train: [6] [5000/6250] eta: 0:03:17 lr: 0.000125 grad: 0.0991 (0.1112) loss: 0.9030 (0.9087) time: 0.1691 data: 0.0942 max mem: 8299 +Train: [6] [5100/6250] eta: 0:03:01 lr: 0.000125 grad: 0.0923 (0.1109) loss: 0.9051 (0.9086) time: 0.1618 data: 0.0841 max mem: 8299 +Train: [6] [5200/6250] eta: 0:02:45 lr: 0.000125 grad: 0.0930 (0.1109) loss: 0.9036 (0.9085) time: 0.1779 data: 0.1006 max mem: 8299 +Train: [6] [5300/6250] eta: 0:02:29 lr: 0.000125 grad: 0.0929 (0.1108) loss: 0.9066 (0.9085) time: 0.1470 data: 0.0695 max mem: 8299 +Train: [6] [5400/6250] eta: 0:02:14 lr: 0.000125 grad: 0.1029 (0.1107) loss: 0.9030 (0.9084) time: 0.1976 data: 0.1114 max mem: 8299 +Train: [6] [5500/6250] eta: 0:01:58 lr: 0.000125 grad: 0.0939 (0.1105) loss: 0.9055 (0.9084) time: 0.1321 data: 0.0510 max mem: 8299 +Train: [6] [5600/6250] eta: 0:01:42 lr: 0.000125 grad: 0.0847 (0.1104) loss: 0.9055 (0.9083) time: 0.1629 data: 0.0708 max mem: 8299 +Train: [6] [5700/6250] eta: 0:01:26 lr: 0.000125 grad: 0.0866 (0.1102) loss: 0.9050 (0.9083) time: 0.1657 data: 0.0760 max mem: 8299 +Train: [6] [5800/6250] eta: 0:01:11 lr: 0.000125 grad: 0.0915 (0.1101) loss: 0.9043 (0.9082) time: 0.1285 data: 0.0411 max mem: 8299 +Train: [6] [5900/6250] eta: 0:00:55 lr: 0.000125 grad: 0.0979 (0.1100) loss: 0.9067 (0.9082) time: 0.1664 data: 0.0742 max mem: 8299 +Train: [6] [6000/6250] eta: 0:00:39 lr: 0.000125 grad: 0.0856 (0.1097) loss: 0.9057 (0.9081) time: 0.1580 data: 0.0679 max mem: 8299 +Train: [6] [6100/6250] eta: 0:00:23 lr: 0.000125 grad: 0.0957 (0.1095) loss: 0.9028 (0.9081) time: 0.1174 data: 0.0381 max mem: 8299 +Train: [6] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0913 (0.1092) loss: 0.9076 (0.9081) time: 0.1959 data: 0.1161 max mem: 8299 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0903 (0.1093) loss: 0.9045 (0.9080) time: 0.1332 data: 0.0501 max mem: 8299 +Train: [6] Total time: 0:16:35 (0.1593 s / it) +Averaged stats: lr: 0.000125 grad: 0.0903 (0.1093) loss: 0.9045 (0.9080) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:05:03 loss: 0.9118 (0.9118) time: 4.8908 data: 4.8573 max mem: 8299 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.9082 (0.9097) time: 0.1182 data: 0.0931 max mem: 8299 +Eval (hcp-train-subset): [6] Total time: 0:00:15 (0.2487 s / it) +Averaged stats (hcp-train-subset): loss: 0.9082 (0.9097) +Eval (hcp-val): [6] [ 0/62] eta: 0:03:29 loss: 0.9009 (0.9009) time: 3.3820 data: 3.2923 max mem: 8299 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.9026 (0.9038) time: 0.1328 data: 0.1058 max mem: 8299 +Eval (hcp-val): [6] Total time: 0:00:13 (0.2195 s / it) +Averaged stats (hcp-val): loss: 0.9026 (0.9038) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 9:45:36 lr: 0.000125 grad: 0.0730 (0.0730) loss: 0.9161 (0.9161) time: 5.6219 data: 5.5141 max mem: 8299 +Train: [7] [ 100/6250] eta: 0:21:50 lr: 0.000125 grad: 0.0973 (0.1077) loss: 0.9004 (0.9076) time: 0.1748 data: 0.0848 max mem: 8299 +Train: [7] [ 200/6250] eta: 0:19:48 lr: 0.000125 grad: 0.0918 (0.1069) loss: 0.9069 (0.9069) time: 0.2398 data: 0.1411 max mem: 8299 +Train: [7] [ 300/6250] eta: 0:18:02 lr: 0.000125 grad: 0.0961 (0.1042) loss: 0.9009 (0.9059) time: 0.1441 data: 0.0481 max mem: 8299 +Train: [7] [ 400/6250] eta: 0:17:07 lr: 0.000125 grad: 0.0972 (0.1043) loss: 0.9052 (0.9054) time: 0.1425 data: 0.0521 max mem: 8299 +Train: [7] [ 500/6250] eta: 0:16:34 lr: 0.000125 grad: 0.0927 (0.1040) loss: 0.9055 (0.9052) time: 0.1730 data: 0.0759 max mem: 8299 +Train: [7] [ 600/6250] eta: 0:15:54 lr: 0.000125 grad: 0.0869 (0.1020) loss: 0.9027 (0.9050) time: 0.1204 data: 0.0181 max mem: 8299 +Train: [7] [ 700/6250] eta: 0:15:10 lr: 0.000125 grad: 0.0973 (0.1021) loss: 0.9062 (0.9050) time: 0.1198 data: 0.0290 max mem: 8299 +Train: [7] [ 800/6250] eta: 0:14:43 lr: 0.000125 grad: 0.0964 (0.1012) loss: 0.9055 (0.9052) time: 0.1579 data: 0.0630 max mem: 8299 +Train: [7] [ 900/6250] eta: 0:14:23 lr: 0.000125 grad: 0.0888 (0.1005) loss: 0.9057 (0.9052) time: 0.1478 data: 0.0615 max mem: 8299 +Train: [7] [1000/6250] eta: 0:14:05 lr: 0.000125 grad: 0.0878 (0.0999) loss: 0.9039 (0.9053) time: 0.1496 data: 0.0524 max mem: 8299 +Train: [7] [1100/6250] eta: 0:13:47 lr: 0.000125 grad: 0.0868 (0.0989) loss: 0.9057 (0.9053) time: 0.1655 data: 0.0725 max mem: 8299 +Train: [7] [1200/6250] eta: 0:13:26 lr: 0.000125 grad: 0.0846 (0.0983) loss: 0.9052 (0.9052) time: 0.1348 data: 0.0429 max mem: 8299 +Train: [7] [1300/6250] eta: 0:13:05 lr: 0.000125 grad: 0.0803 (0.0977) loss: 0.9050 (0.9051) time: 0.1469 data: 0.0562 max mem: 8299 +Train: [7] [1400/6250] eta: 0:12:48 lr: 0.000125 grad: 0.0903 (0.0978) loss: 0.8992 (0.9050) time: 0.1255 data: 0.0414 max mem: 8299 +Train: [7] [1500/6250] eta: 0:12:27 lr: 0.000125 grad: 0.0820 (0.0971) loss: 0.9050 (0.9049) time: 0.1507 data: 0.0650 max mem: 8299 +Train: [7] [1600/6250] eta: 0:12:09 lr: 0.000125 grad: 0.0862 (0.0966) loss: 0.9024 (0.9048) time: 0.1342 data: 0.0553 max mem: 8299 +Train: [7] [1700/6250] eta: 0:11:52 lr: 0.000125 grad: 0.0866 (0.0961) loss: 0.9044 (0.9047) time: 0.1679 data: 0.0805 max mem: 8299 +Train: [7] [1800/6250] eta: 0:11:35 lr: 0.000125 grad: 0.0941 (0.0958) loss: 0.9013 (0.9046) time: 0.1397 data: 0.0556 max mem: 8299 +Train: [7] [1900/6250] eta: 0:11:17 lr: 0.000125 grad: 0.0803 (0.0954) loss: 0.9047 (0.9045) time: 0.1474 data: 0.0669 max mem: 8299 +Train: [7] [2000/6250] eta: 0:10:58 lr: 0.000125 grad: 0.0883 (0.0956) loss: 0.9018 (0.9044) time: 0.1406 data: 0.0504 max mem: 8299 +Train: [7] [2100/6250] eta: 0:10:43 lr: 0.000125 grad: 0.0862 (0.0952) loss: 0.9039 (0.9044) time: 0.1575 data: 0.0609 max mem: 8299 +Train: [7] [2200/6250] eta: 0:10:25 lr: 0.000125 grad: 0.0889 (0.0949) loss: 0.9025 (0.9043) time: 0.1468 data: 0.0520 max mem: 8299 +Train: [7] [2300/6250] eta: 0:10:12 lr: 0.000125 grad: 0.0859 (0.0946) loss: 0.9039 (0.9043) time: 0.1909 data: 0.1002 max mem: 8299 +Train: [7] [2400/6250] eta: 0:09:58 lr: 0.000125 grad: 0.0804 (0.0944) loss: 0.9007 (0.9042) time: 0.2141 data: 0.1360 max mem: 8299 +Train: [7] [2500/6250] eta: 0:09:40 lr: 0.000125 grad: 0.1034 (0.0942) loss: 0.9038 (0.9041) time: 0.1567 data: 0.0720 max mem: 8299 +Train: [7] [2600/6250] eta: 0:09:25 lr: 0.000125 grad: 0.1091 (0.0940) loss: 0.9028 (0.9040) time: 0.1766 data: 0.1029 max mem: 8299 +Train: [7] [2700/6250] eta: 0:09:10 lr: 0.000125 grad: 0.0884 (0.0939) loss: 0.9001 (0.9039) time: 0.1518 data: 0.0614 max mem: 8299 +Train: [7] [2800/6250] eta: 0:08:54 lr: 0.000125 grad: 0.0894 (0.0938) loss: 0.9029 (0.9038) time: 0.1493 data: 0.0638 max mem: 8299 +Train: [7] [2900/6250] eta: 0:08:39 lr: 0.000125 grad: 0.0927 (0.0935) loss: 0.9029 (0.9038) time: 0.1561 data: 0.0735 max mem: 8299 +Train: [7] [3000/6250] eta: 0:08:24 lr: 0.000125 grad: 0.0886 (0.0933) loss: 0.8962 (0.9038) time: 0.1371 data: 0.0579 max mem: 8299 +Train: [7] [3100/6250] eta: 0:08:09 lr: 0.000125 grad: 0.0897 (0.0932) loss: 0.9034 (0.9037) time: 0.1368 data: 0.0568 max mem: 8299 +Train: [7] [3200/6250] eta: 0:07:54 lr: 0.000125 grad: 0.0826 (0.0930) loss: 0.9028 (0.9036) time: 0.1586 data: 0.0756 max mem: 8299 +Train: [7] [3300/6250] eta: 0:07:41 lr: 0.000125 grad: 0.0884 (0.0929) loss: 0.9014 (0.9036) time: 0.1381 data: 0.0330 max mem: 8299 +Train: [7] [3400/6250] eta: 0:07:24 lr: 0.000125 grad: 0.0785 (0.0927) loss: 0.9039 (0.9035) time: 0.1443 data: 0.0677 max mem: 8299 +Train: [7] [3500/6250] eta: 0:07:09 lr: 0.000125 grad: 0.0817 (0.0924) loss: 0.9035 (0.9035) time: 0.1543 data: 0.0680 max mem: 8299 +Train: [7] [3600/6250] eta: 0:06:54 lr: 0.000125 grad: 0.0813 (0.0921) loss: 0.8990 (0.9035) time: 0.1810 data: 0.0971 max mem: 8299 +Train: [7] [3700/6250] eta: 0:06:38 lr: 0.000125 grad: 0.0847 (0.0921) loss: 0.8996 (0.9034) time: 0.1465 data: 0.0572 max mem: 8299 +Train: [7] [3800/6250] eta: 0:06:23 lr: 0.000125 grad: 0.0822 (0.0920) loss: 0.9002 (0.9033) time: 0.1806 data: 0.0976 max mem: 8299 +Train: [7] [3900/6250] eta: 0:06:07 lr: 0.000125 grad: 0.0973 (0.0920) loss: 0.8993 (0.9033) time: 0.1364 data: 0.0548 max mem: 8299 +Train: [7] [4000/6250] eta: 0:05:51 lr: 0.000125 grad: 0.0830 (0.0919) loss: 0.9020 (0.9032) time: 0.1733 data: 0.0849 max mem: 8299 +Train: [7] [4100/6250] eta: 0:05:35 lr: 0.000125 grad: 0.0794 (0.0918) loss: 0.8967 (0.9031) time: 0.1372 data: 0.0549 max mem: 8299 +Train: [7] [4200/6250] eta: 0:05:19 lr: 0.000125 grad: 0.0775 (0.0916) loss: 0.8978 (0.9030) time: 0.1897 data: 0.1134 max mem: 8299 +Train: [7] [4300/6250] eta: 0:05:03 lr: 0.000125 grad: 0.0764 (0.0913) loss: 0.8965 (0.9029) time: 0.1368 data: 0.0605 max mem: 8299 +Train: [7] [4400/6250] eta: 0:04:47 lr: 0.000125 grad: 0.0733 (0.0910) loss: 0.9014 (0.9028) time: 0.1177 data: 0.0309 max mem: 8299 +Train: [7] [4500/6250] eta: 0:04:32 lr: 0.000125 grad: 0.0882 (0.0909) loss: 0.8993 (0.9027) time: 0.1468 data: 0.0703 max mem: 8299 +Train: [7] [4600/6250] eta: 0:04:16 lr: 0.000125 grad: 0.0826 (0.0908) loss: 0.8994 (0.9026) time: 0.1544 data: 0.0623 max mem: 8299 +Train: [7] [4700/6250] eta: 0:04:00 lr: 0.000125 grad: 0.0901 (0.0907) loss: 0.8993 (0.9026) time: 0.1150 data: 0.0424 max mem: 8299 +Train: [7] [4800/6250] eta: 0:03:44 lr: 0.000125 grad: 0.0752 (0.0905) loss: 0.9042 (0.9025) time: 0.1717 data: 0.0874 max mem: 8299 +Train: [7] [4900/6250] eta: 0:03:29 lr: 0.000125 grad: 0.0814 (0.0903) loss: 0.9001 (0.9025) time: 0.1270 data: 0.0487 max mem: 8299 +Train: [7] [5000/6250] eta: 0:03:13 lr: 0.000125 grad: 0.0770 (0.0902) loss: 0.8979 (0.9024) time: 0.1593 data: 0.0769 max mem: 8299 +Train: [7] [5100/6250] eta: 0:02:57 lr: 0.000125 grad: 0.0847 (0.0901) loss: 0.9019 (0.9023) time: 0.1564 data: 0.0738 max mem: 8299 +Train: [7] [5200/6250] eta: 0:02:42 lr: 0.000125 grad: 0.0733 (0.0899) loss: 0.9029 (0.9023) time: 0.1619 data: 0.0791 max mem: 8299 +Train: [7] [5300/6250] eta: 0:02:26 lr: 0.000125 grad: 0.0754 (0.0897) loss: 0.9012 (0.9023) time: 0.1827 data: 0.1063 max mem: 8299 +Train: [7] [5400/6250] eta: 0:02:11 lr: 0.000125 grad: 0.0760 (0.0897) loss: 0.9031 (0.9022) time: 0.1511 data: 0.0604 max mem: 8299 +Train: [7] [5500/6250] eta: 0:01:55 lr: 0.000125 grad: 0.0759 (0.0896) loss: 0.9056 (0.9022) time: 0.1552 data: 0.0743 max mem: 8299 +Train: [7] [5600/6250] eta: 0:01:40 lr: 0.000125 grad: 0.0770 (0.0894) loss: 0.9043 (0.9022) time: 0.1161 data: 0.0342 max mem: 8299 +Train: [7] [5700/6250] eta: 0:01:24 lr: 0.000125 grad: 0.0816 (0.0894) loss: 0.9000 (0.9021) time: 0.1530 data: 0.0740 max mem: 8299 +Train: [7] [5800/6250] eta: 0:01:09 lr: 0.000125 grad: 0.0763 (0.0892) loss: 0.9051 (0.9022) time: 0.1711 data: 0.0930 max mem: 8299 +Train: [7] [5900/6250] eta: 0:00:54 lr: 0.000125 grad: 0.0727 (0.0891) loss: 0.9036 (0.9021) time: 0.1549 data: 0.0732 max mem: 8299 +Train: [7] [6000/6250] eta: 0:00:38 lr: 0.000125 grad: 0.0714 (0.0890) loss: 0.9017 (0.9021) time: 0.1622 data: 0.0757 max mem: 8299 +Train: [7] [6100/6250] eta: 0:00:23 lr: 0.000125 grad: 0.0822 (0.0889) loss: 0.9036 (0.9021) time: 0.1699 data: 0.0946 max mem: 8299 +Train: [7] [6200/6250] eta: 0:00:07 lr: 0.000125 grad: 0.0910 (0.0888) loss: 0.9017 (0.9021) time: 0.1426 data: 0.0557 max mem: 8299 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0687 (0.0887) loss: 0.9023 (0.9021) time: 0.1507 data: 0.0758 max mem: 8299 +Train: [7] Total time: 0:16:15 (0.1561 s / it) +Averaged stats: lr: 0.000125 grad: 0.0687 (0.0887) loss: 0.9023 (0.9021) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:03:19 loss: 0.9111 (0.9111) time: 3.2124 data: 3.1324 max mem: 8299 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.9059 (0.9048) time: 0.1591 data: 0.1344 max mem: 8299 +Eval (hcp-train-subset): [7] Total time: 0:00:14 (0.2379 s / it) +Averaged stats (hcp-train-subset): loss: 0.9059 (0.9048) +Eval (hcp-val): [7] [ 0/62] eta: 0:03:58 loss: 0.8954 (0.8954) time: 3.8542 data: 3.7898 max mem: 8299 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8993 (0.8994) time: 0.1353 data: 0.1104 max mem: 8299 +Eval (hcp-val): [7] Total time: 0:00:13 (0.2203 s / it) +Averaged stats (hcp-val): loss: 0.8993 (0.8994) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 13:02:57 lr: 0.000125 grad: 0.1300 (0.1300) loss: 0.9343 (0.9343) time: 7.5164 data: 7.4084 max mem: 8299 +Train: [8] [ 100/6250] eta: 0:22:43 lr: 0.000125 grad: 0.0673 (0.0842) loss: 0.9018 (0.9041) time: 0.1789 data: 0.0829 max mem: 8299 +Train: [8] [ 200/6250] eta: 0:19:24 lr: 0.000125 grad: 0.0700 (0.0818) loss: 0.8995 (0.9026) time: 0.1422 data: 0.0527 max mem: 8299 +Train: [8] [ 300/6250] eta: 0:17:54 lr: 0.000125 grad: 0.0689 (0.0788) loss: 0.9059 (0.9032) time: 0.1468 data: 0.0665 max mem: 8299 +Train: [8] [ 400/6250] eta: 0:17:02 lr: 0.000125 grad: 0.0843 (0.0781) loss: 0.9010 (0.9026) time: 0.1337 data: 0.0443 max mem: 8299 +Train: [8] [ 500/6250] eta: 0:16:23 lr: 0.000125 grad: 0.0756 (0.0778) loss: 0.8945 (0.9018) time: 0.1662 data: 0.0772 max mem: 8299 +Train: [8] [ 600/6250] eta: 0:15:43 lr: 0.000125 grad: 0.0739 (0.0774) loss: 0.8964 (0.9016) time: 0.1731 data: 0.0762 max mem: 8299 +Train: [8] [ 700/6250] eta: 0:15:00 lr: 0.000125 grad: 0.0694 (0.0768) loss: 0.9026 (0.9016) time: 0.1132 data: 0.0274 max mem: 8299 +Train: [8] [ 800/6250] eta: 0:14:34 lr: 0.000125 grad: 0.0740 (0.0768) loss: 0.8991 (0.9013) time: 0.1527 data: 0.0592 max mem: 8299 +Train: [8] [ 900/6250] eta: 0:14:22 lr: 0.000125 grad: 0.0736 (0.0775) loss: 0.9001 (0.9011) time: 0.1696 data: 0.0809 max mem: 8299 +Train: [8] [1000/6250] eta: 0:14:05 lr: 0.000125 grad: 0.0709 (0.0784) loss: 0.9022 (0.9010) time: 0.1658 data: 0.0779 max mem: 8299 +Train: [8] [1100/6250] eta: 0:13:47 lr: 0.000125 grad: 0.0730 (0.0782) loss: 0.8981 (0.9008) time: 0.1054 data: 0.0142 max mem: 8299 +Train: [8] [1200/6250] eta: 0:13:28 lr: 0.000125 grad: 0.0779 (0.0781) loss: 0.8972 (0.9006) time: 0.1375 data: 0.0561 max mem: 8299 +Train: [8] [1300/6250] eta: 0:13:08 lr: 0.000125 grad: 0.0748 (0.0782) loss: 0.8958 (0.9004) time: 0.1431 data: 0.0510 max mem: 8299 +Train: [8] [1400/6250] eta: 0:12:52 lr: 0.000125 grad: 0.0744 (0.0784) loss: 0.9008 (0.9002) time: 0.1824 data: 0.1032 max mem: 8299 +Train: [8] [1500/6250] eta: 0:12:33 lr: 0.000125 grad: 0.0750 (0.0787) loss: 0.9001 (0.9001) time: 0.1624 data: 0.0755 max mem: 8299 +Train: [8] [1600/6250] eta: 0:12:15 lr: 0.000125 grad: 0.0692 (0.0787) loss: 0.8938 (0.8999) time: 0.1589 data: 0.0792 max mem: 8299 +Train: [8] [1700/6250] eta: 0:11:57 lr: 0.000125 grad: 0.0785 (0.0789) loss: 0.8977 (0.8998) time: 0.1439 data: 0.0689 max mem: 8299 +Train: [8] [1800/6250] eta: 0:11:41 lr: 0.000125 grad: 0.0791 (0.0790) loss: 0.8981 (0.8996) time: 0.1822 data: 0.1057 max mem: 8299 +Train: [8] [1900/6250] eta: 0:11:24 lr: 0.000125 grad: 0.0741 (0.0789) loss: 0.8977 (0.8994) time: 0.1292 data: 0.0567 max mem: 8299 +Train: [8] [2000/6250] eta: 0:11:04 lr: 0.000125 grad: 0.0734 (0.0789) loss: 0.9001 (0.8993) time: 0.1552 data: 0.0578 max mem: 8299 +Train: [8] [2100/6250] eta: 0:10:53 lr: 0.000125 grad: 0.0740 (0.0787) loss: 0.8957 (0.8992) time: 0.1595 data: 0.0655 max mem: 8299 +Train: [8] [2200/6250] eta: 0:10:40 lr: 0.000125 grad: 0.0734 (0.0787) loss: 0.8996 (0.8992) time: 0.1523 data: 0.0751 max mem: 8299 +Train: [8] [2300/6250] eta: 0:10:22 lr: 0.000125 grad: 0.0908 (0.0789) loss: 0.8985 (0.8992) time: 0.1287 data: 0.0425 max mem: 8299 +Train: [8] [2400/6250] eta: 0:10:04 lr: 0.000125 grad: 0.0659 (0.0789) loss: 0.8993 (0.8991) time: 0.1101 data: 0.0128 max mem: 8299 +Train: [8] [2500/6250] eta: 0:09:48 lr: 0.000125 grad: 0.0715 (0.0789) loss: 0.9001 (0.8991) time: 0.1669 data: 0.0826 max mem: 8299 +Train: [8] [2600/6250] eta: 0:09:32 lr: 0.000125 grad: 0.0788 (0.0789) loss: 0.9005 (0.8990) time: 0.1389 data: 0.0559 max mem: 8299 +Train: [8] [2700/6250] eta: 0:09:17 lr: 0.000125 grad: 0.0712 (0.0789) loss: 0.8966 (0.8990) time: 0.1746 data: 0.1007 max mem: 8299 +Train: [8] [2800/6250] eta: 0:09:01 lr: 0.000125 grad: 0.0702 (0.0788) loss: 0.9011 (0.8990) time: 0.1534 data: 0.0584 max mem: 8299 +Train: [8] [2900/6250] eta: 0:08:46 lr: 0.000125 grad: 0.0687 (0.0787) loss: 0.8941 (0.8990) time: 0.1530 data: 0.0754 max mem: 8299 +Train: [8] [3000/6250] eta: 0:08:31 lr: 0.000125 grad: 0.0692 (0.0786) loss: 0.8980 (0.8990) time: 0.1913 data: 0.1017 max mem: 8299 +Train: [8] [3100/6250] eta: 0:08:15 lr: 0.000125 grad: 0.0790 (0.0786) loss: 0.8963 (0.8990) time: 0.2085 data: 0.1308 max mem: 8299 +Train: [8] [3200/6250] eta: 0:08:00 lr: 0.000125 grad: 0.0770 (0.0785) loss: 0.8979 (0.8990) time: 0.1362 data: 0.0336 max mem: 8299 +Train: [8] [3300/6250] eta: 0:07:43 lr: 0.000125 grad: 0.0733 (0.0785) loss: 0.8993 (0.8990) time: 0.1225 data: 0.0461 max mem: 8299 +Train: [8] [3400/6250] eta: 0:07:28 lr: 0.000125 grad: 0.0757 (0.0783) loss: 0.9003 (0.8989) time: 0.1740 data: 0.0943 max mem: 8299 +Train: [8] [3500/6250] eta: 0:07:12 lr: 0.000125 grad: 0.0691 (0.0781) loss: 0.8982 (0.8989) time: 0.1860 data: 0.1000 max mem: 8299 +Train: [8] [3600/6250] eta: 0:06:56 lr: 0.000125 grad: 0.0692 (0.0780) loss: 0.8997 (0.8989) time: 0.1576 data: 0.0584 max mem: 8299 +Train: [8] [3700/6250] eta: 0:06:39 lr: 0.000125 grad: 0.0701 (0.0780) loss: 0.9000 (0.8989) time: 0.1233 data: 0.0383 max mem: 8299 +Train: [8] [3800/6250] eta: 0:06:24 lr: 0.000125 grad: 0.0716 (0.0779) loss: 0.8951 (0.8989) time: 0.1617 data: 0.0790 max mem: 8299 +Train: [8] [3900/6250] eta: 0:06:08 lr: 0.000125 grad: 0.0716 (0.0778) loss: 0.8973 (0.8988) time: 0.1429 data: 0.0649 max mem: 8299 +Train: [8] [4000/6250] eta: 0:05:52 lr: 0.000125 grad: 0.0684 (0.0777) loss: 0.8985 (0.8988) time: 0.1767 data: 0.0958 max mem: 8299 +Train: [8] [4100/6250] eta: 0:05:36 lr: 0.000125 grad: 0.0787 (0.0781) loss: 0.8984 (0.8987) time: 0.1450 data: 0.0593 max mem: 8299 +Train: [8] [4200/6250] eta: 0:05:21 lr: 0.000125 grad: 0.0742 (0.0781) loss: 0.8963 (0.8987) time: 0.1457 data: 0.0639 max mem: 8299 +Train: [8] [4300/6250] eta: 0:05:05 lr: 0.000125 grad: 0.0753 (0.0780) loss: 0.8963 (0.8986) time: 0.1226 data: 0.0393 max mem: 8299 +Train: [8] [4400/6250] eta: 0:04:50 lr: 0.000125 grad: 0.0751 (0.0781) loss: 0.8948 (0.8985) time: 0.1684 data: 0.0865 max mem: 8299 +Train: [8] [4500/6250] eta: 0:04:33 lr: 0.000125 grad: 0.0705 (0.0780) loss: 0.8988 (0.8985) time: 0.1374 data: 0.0539 max mem: 8299 +Train: [8] [4600/6250] eta: 0:04:18 lr: 0.000125 grad: 0.0738 (0.0779) loss: 0.8896 (0.8984) time: 0.1569 data: 0.0767 max mem: 8299 +Train: [8] [4700/6250] eta: 0:04:02 lr: 0.000125 grad: 0.0697 (0.0779) loss: 0.8975 (0.8983) time: 0.1548 data: 0.0689 max mem: 8299 +Train: [8] [4800/6250] eta: 0:03:46 lr: 0.000125 grad: 0.0647 (0.0778) loss: 0.9000 (0.8982) time: 0.1456 data: 0.0682 max mem: 8299 +Train: [8] [4900/6250] eta: 0:03:30 lr: 0.000125 grad: 0.0720 (0.0777) loss: 0.8903 (0.8982) time: 0.1326 data: 0.0530 max mem: 8299 +Train: [8] [5000/6250] eta: 0:03:15 lr: 0.000125 grad: 0.0708 (0.0776) loss: 0.8942 (0.8981) time: 0.1368 data: 0.0638 max mem: 8299 +Train: [8] [5100/6250] eta: 0:02:59 lr: 0.000125 grad: 0.0733 (0.0775) loss: 0.8925 (0.8980) time: 0.1475 data: 0.0607 max mem: 8299 +Train: [8] [5200/6250] eta: 0:02:44 lr: 0.000124 grad: 0.0752 (0.0775) loss: 0.8936 (0.8980) time: 0.1360 data: 0.0561 max mem: 8299 +Train: [8] [5300/6250] eta: 0:02:28 lr: 0.000124 grad: 0.0759 (0.0775) loss: 0.8981 (0.8980) time: 0.1483 data: 0.0696 max mem: 8299 +Train: [8] [5400/6250] eta: 0:02:12 lr: 0.000124 grad: 0.0691 (0.0775) loss: 0.8987 (0.8980) time: 0.1708 data: 0.0826 max mem: 8299 +Train: [8] [5500/6250] eta: 0:01:56 lr: 0.000124 grad: 0.0669 (0.0774) loss: 0.8977 (0.8980) time: 0.1469 data: 0.0618 max mem: 8299 +Train: [8] [5600/6250] eta: 0:01:41 lr: 0.000124 grad: 0.0653 (0.0773) loss: 0.8962 (0.8979) time: 0.1777 data: 0.0905 max mem: 8299 +Train: [8] [5700/6250] eta: 0:01:25 lr: 0.000124 grad: 0.0748 (0.0772) loss: 0.8937 (0.8978) time: 0.1560 data: 0.0660 max mem: 8299 +Train: [8] [5800/6250] eta: 0:01:10 lr: 0.000124 grad: 0.0785 (0.0772) loss: 0.8915 (0.8978) time: 0.1837 data: 0.1004 max mem: 8299 +Train: [8] [5900/6250] eta: 0:00:54 lr: 0.000124 grad: 0.0714 (0.0771) loss: 0.8933 (0.8977) time: 0.1342 data: 0.0336 max mem: 8299 +Train: [8] [6000/6250] eta: 0:00:38 lr: 0.000124 grad: 0.0729 (0.0770) loss: 0.8965 (0.8976) time: 0.1302 data: 0.0570 max mem: 8299 +Train: [8] [6100/6250] eta: 0:00:23 lr: 0.000124 grad: 0.0708 (0.0769) loss: 0.8910 (0.8976) time: 0.1750 data: 0.0982 max mem: 8299 +Train: [8] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0720 (0.0769) loss: 0.8887 (0.8975) time: 0.2592 data: 0.1744 max mem: 8299 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0751 (0.0769) loss: 0.8940 (0.8975) time: 0.1438 data: 0.0513 max mem: 8299 +Train: [8] Total time: 0:16:20 (0.1568 s / it) +Averaged stats: lr: 0.000124 grad: 0.0751 (0.0769) loss: 0.8940 (0.8975) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:05:43 loss: 0.9135 (0.9135) time: 5.5428 data: 5.5116 max mem: 8299 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.9010 (0.9020) time: 0.1295 data: 0.1043 max mem: 8299 +Eval (hcp-train-subset): [8] Total time: 0:00:14 (0.2405 s / it) +Averaged stats (hcp-train-subset): loss: 0.9010 (0.9020) +Eval (hcp-val): [8] [ 0/62] eta: 0:05:19 loss: 0.8874 (0.8874) time: 5.1577 data: 5.0987 max mem: 8299 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8958 (0.8966) time: 0.1486 data: 0.1233 max mem: 8299 +Eval (hcp-val): [8] Total time: 0:00:14 (0.2401 s / it) +Averaged stats (hcp-val): loss: 0.8958 (0.8966) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 10:51:55 lr: 0.000124 grad: 0.0787 (0.0787) loss: 0.9092 (0.9092) time: 6.2585 data: 6.1600 max mem: 8299 +Train: [9] [ 100/6250] eta: 0:21:48 lr: 0.000124 grad: 0.0859 (0.0840) loss: 0.8994 (0.9001) time: 0.1680 data: 0.0668 max mem: 8299 +Train: [9] [ 200/6250] eta: 0:18:44 lr: 0.000124 grad: 0.0756 (0.0826) loss: 0.9000 (0.8974) time: 0.1606 data: 0.0665 max mem: 8299 +Train: [9] [ 300/6250] eta: 0:17:45 lr: 0.000124 grad: 0.0675 (0.0808) loss: 0.8924 (0.8958) time: 0.1529 data: 0.0692 max mem: 8299 +Train: [9] [ 400/6250] eta: 0:16:46 lr: 0.000124 grad: 0.0652 (0.0783) loss: 0.8949 (0.8956) time: 0.1169 data: 0.0230 max mem: 8299 +Train: [9] [ 500/6250] eta: 0:16:12 lr: 0.000124 grad: 0.0719 (0.0773) loss: 0.8908 (0.8954) time: 0.1554 data: 0.0496 max mem: 8299 +Train: [9] [ 600/6250] eta: 0:15:34 lr: 0.000124 grad: 0.0714 (0.0762) loss: 0.8928 (0.8954) time: 0.1494 data: 0.0520 max mem: 8299 +Train: [9] [ 700/6250] eta: 0:15:03 lr: 0.000124 grad: 0.0649 (0.0758) loss: 0.8966 (0.8954) time: 0.1345 data: 0.0329 max mem: 8299 +Train: [9] [ 800/6250] eta: 0:14:37 lr: 0.000124 grad: 0.0634 (0.0748) loss: 0.8944 (0.8956) time: 0.1653 data: 0.0597 max mem: 8299 +Train: [9] [ 900/6250] eta: 0:14:15 lr: 0.000124 grad: 0.0641 (0.0742) loss: 0.8932 (0.8956) time: 0.1832 data: 0.0949 max mem: 8299 +Train: [9] [1000/6250] eta: 0:14:00 lr: 0.000124 grad: 0.0673 (0.0738) loss: 0.8970 (0.8957) time: 0.1633 data: 0.0869 max mem: 8299 +Train: [9] [1100/6250] eta: 0:13:57 lr: 0.000124 grad: 0.0722 (0.0734) loss: 0.8950 (0.8959) time: 0.2201 data: 0.1441 max mem: 8299 +Train: [9] [1200/6250] eta: 0:13:49 lr: 0.000124 grad: 0.0662 (0.0730) loss: 0.8994 (0.8959) time: 0.1939 data: 0.1178 max mem: 8299 +Train: [9] [1300/6250] eta: 0:13:39 lr: 0.000124 grad: 0.0618 (0.0726) loss: 0.8990 (0.8959) time: 0.1410 data: 0.0531 max mem: 8299 +Train: [9] [1400/6250] eta: 0:13:23 lr: 0.000124 grad: 0.0702 (0.0725) loss: 0.8954 (0.8960) time: 0.1938 data: 0.1171 max mem: 8299 +Train: [9] [1500/6250] eta: 0:13:07 lr: 0.000124 grad: 0.0646 (0.0723) loss: 0.9014 (0.8962) time: 0.1800 data: 0.1082 max mem: 8299 +Train: [9] [1600/6250] eta: 0:12:48 lr: 0.000124 grad: 0.0699 (0.0721) loss: 0.8977 (0.8962) time: 0.1681 data: 0.0875 max mem: 8299 +Train: [9] [1700/6250] eta: 0:12:31 lr: 0.000124 grad: 0.0688 (0.0720) loss: 0.8939 (0.8962) time: 0.1820 data: 0.1088 max mem: 8299 +Train: [9] [1800/6250] eta: 0:12:09 lr: 0.000124 grad: 0.0704 (0.0717) loss: 0.8963 (0.8962) time: 0.1475 data: 0.0559 max mem: 8299 +Train: [9] [1900/6250] eta: 0:11:50 lr: 0.000124 grad: 0.0668 (0.0715) loss: 0.8989 (0.8962) time: 0.1268 data: 0.0502 max mem: 8299 +Train: [9] [2000/6250] eta: 0:11:33 lr: 0.000124 grad: 0.0681 (0.0712) loss: 0.8978 (0.8963) time: 0.1624 data: 0.0781 max mem: 8299 +Train: [9] [2100/6250] eta: 0:11:14 lr: 0.000124 grad: 0.0684 (0.0711) loss: 0.8948 (0.8963) time: 0.1362 data: 0.0608 max mem: 8299 +Train: [9] [2200/6250] eta: 0:10:57 lr: 0.000124 grad: 0.0631 (0.0709) loss: 0.8959 (0.8963) time: 0.1895 data: 0.1102 max mem: 8299 +Train: [9] [2300/6250] eta: 0:10:41 lr: 0.000124 grad: 0.0663 (0.0708) loss: 0.8971 (0.8963) time: 0.1684 data: 0.0789 max mem: 8299 +Train: [9] [2400/6250] eta: 0:10:24 lr: 0.000124 grad: 0.0662 (0.0707) loss: 0.8956 (0.8963) time: 0.1606 data: 0.0808 max mem: 8299 +Train: [9] [2500/6250] eta: 0:10:07 lr: 0.000124 grad: 0.0696 (0.0706) loss: 0.8957 (0.8962) time: 0.1826 data: 0.1010 max mem: 8299 +Train: [9] [2600/6250] eta: 0:09:50 lr: 0.000124 grad: 0.0651 (0.0705) loss: 0.8965 (0.8962) time: 0.1665 data: 0.0761 max mem: 8299 +Train: [9] [2700/6250] eta: 0:09:32 lr: 0.000124 grad: 0.0655 (0.0707) loss: 0.8976 (0.8961) time: 0.1472 data: 0.0629 max mem: 8299 +Train: [9] [2800/6250] eta: 0:09:15 lr: 0.000124 grad: 0.0658 (0.0706) loss: 0.8961 (0.8961) time: 0.1665 data: 0.0789 max mem: 8299 +Train: [9] [2900/6250] eta: 0:08:58 lr: 0.000124 grad: 0.0694 (0.0707) loss: 0.8945 (0.8961) time: 0.1472 data: 0.0624 max mem: 8299 +Train: [9] [3000/6250] eta: 0:08:42 lr: 0.000124 grad: 0.0676 (0.0706) loss: 0.9001 (0.8961) time: 0.1543 data: 0.0824 max mem: 8299 +Train: [9] [3100/6250] eta: 0:08:27 lr: 0.000124 grad: 0.0618 (0.0705) loss: 0.8973 (0.8961) time: 0.2675 data: 0.1774 max mem: 8299 +Train: [9] [3200/6250] eta: 0:08:10 lr: 0.000124 grad: 0.0662 (0.0705) loss: 0.8952 (0.8961) time: 0.1627 data: 0.0715 max mem: 8299 +Train: [9] [3300/6250] eta: 0:07:54 lr: 0.000124 grad: 0.0688 (0.0705) loss: 0.8985 (0.8961) time: 0.1583 data: 0.0770 max mem: 8299 +Train: [9] [3400/6250] eta: 0:07:37 lr: 0.000124 grad: 0.0632 (0.0705) loss: 0.8986 (0.8961) time: 0.1448 data: 0.0760 max mem: 8299 +Train: [9] [3500/6250] eta: 0:07:21 lr: 0.000124 grad: 0.0630 (0.0705) loss: 0.9018 (0.8961) time: 0.1666 data: 0.0944 max mem: 8299 +Train: [9] [3600/6250] eta: 0:07:05 lr: 0.000124 grad: 0.0698 (0.0705) loss: 0.8929 (0.8961) time: 0.1566 data: 0.0770 max mem: 8299 +Train: [9] [3700/6250] eta: 0:06:50 lr: 0.000124 grad: 0.0711 (0.0705) loss: 0.8933 (0.8960) time: 0.1818 data: 0.0793 max mem: 8299 +Train: [9] [3800/6250] eta: 0:06:33 lr: 0.000124 grad: 0.0643 (0.0705) loss: 0.8965 (0.8960) time: 0.1254 data: 0.0538 max mem: 8299 +Train: [9] [3900/6250] eta: 0:06:16 lr: 0.000124 grad: 0.0719 (0.0707) loss: 0.8916 (0.8959) time: 0.1693 data: 0.0788 max mem: 8299 +Train: [9] [4000/6250] eta: 0:06:00 lr: 0.000124 grad: 0.0633 (0.0706) loss: 0.9028 (0.8958) time: 0.1200 data: 0.0309 max mem: 8299 +Train: [9] [4100/6250] eta: 0:05:43 lr: 0.000124 grad: 0.0644 (0.0706) loss: 0.8927 (0.8958) time: 0.1546 data: 0.0719 max mem: 8299 +Train: [9] [4200/6250] eta: 0:05:26 lr: 0.000124 grad: 0.0655 (0.0706) loss: 0.8961 (0.8958) time: 0.1512 data: 0.0679 max mem: 8299 +Train: [9] [4300/6250] eta: 0:05:10 lr: 0.000124 grad: 0.0669 (0.0706) loss: 0.8909 (0.8957) time: 0.1355 data: 0.0546 max mem: 8299 +Train: [9] [4400/6250] eta: 0:04:55 lr: 0.000124 grad: 0.0674 (0.0705) loss: 0.8940 (0.8957) time: 0.1576 data: 0.0807 max mem: 8299 +Train: [9] [4500/6250] eta: 0:04:40 lr: 0.000124 grad: 0.0671 (0.0705) loss: 0.8938 (0.8957) time: 0.2508 data: 0.1757 max mem: 8299 +Train: [9] [4600/6250] eta: 0:04:23 lr: 0.000124 grad: 0.0634 (0.0704) loss: 0.8950 (0.8957) time: 0.1494 data: 0.0615 max mem: 8299 +Train: [9] [4700/6250] eta: 0:04:08 lr: 0.000124 grad: 0.0649 (0.0704) loss: 0.8973 (0.8957) time: 0.1964 data: 0.1279 max mem: 8299 +Train: [9] [4800/6250] eta: 0:03:52 lr: 0.000124 grad: 0.0670 (0.0704) loss: 0.8923 (0.8957) time: 0.1919 data: 0.1171 max mem: 8299 +Train: [9] [4900/6250] eta: 0:03:36 lr: 0.000124 grad: 0.0654 (0.0703) loss: 0.8911 (0.8956) time: 0.1514 data: 0.0568 max mem: 8299 +Train: [9] [5000/6250] eta: 0:03:20 lr: 0.000124 grad: 0.0634 (0.0703) loss: 0.8942 (0.8956) time: 0.1899 data: 0.1080 max mem: 8299 +Train: [9] [5100/6250] eta: 0:03:04 lr: 0.000124 grad: 0.0678 (0.0704) loss: 0.8930 (0.8956) time: 0.1911 data: 0.1073 max mem: 8299 +Train: [9] [5200/6250] eta: 0:02:48 lr: 0.000124 grad: 0.0734 (0.0704) loss: 0.8930 (0.8956) time: 0.1900 data: 0.1037 max mem: 8299 +Train: [9] [5300/6250] eta: 0:02:32 lr: 0.000124 grad: 0.0618 (0.0704) loss: 0.8957 (0.8956) time: 0.1659 data: 0.0819 max mem: 8299 +Train: [9] [5400/6250] eta: 0:02:16 lr: 0.000124 grad: 0.0610 (0.0703) loss: 0.8936 (0.8955) time: 0.1419 data: 0.0607 max mem: 8299 +Train: [9] [5500/6250] eta: 0:02:00 lr: 0.000124 grad: 0.0661 (0.0703) loss: 0.8893 (0.8955) time: 0.2123 data: 0.1328 max mem: 8299 +Train: [9] [5600/6250] eta: 0:01:44 lr: 0.000124 grad: 0.0661 (0.0702) loss: 0.8927 (0.8955) time: 0.1745 data: 0.0919 max mem: 8299 +Train: [9] [5700/6250] eta: 0:01:28 lr: 0.000124 grad: 0.0633 (0.0702) loss: 0.8935 (0.8954) time: 0.1679 data: 0.0832 max mem: 8299 +Train: [9] [5800/6250] eta: 0:01:12 lr: 0.000124 grad: 0.0598 (0.0701) loss: 0.8936 (0.8953) time: 0.1640 data: 0.0876 max mem: 8299 +Train: [9] [5900/6250] eta: 0:00:56 lr: 0.000124 grad: 0.0627 (0.0700) loss: 0.8928 (0.8953) time: 0.2190 data: 0.1404 max mem: 8299 +Train: [9] [6000/6250] eta: 0:00:40 lr: 0.000124 grad: 0.0700 (0.0700) loss: 0.8934 (0.8953) time: 0.1911 data: 0.1086 max mem: 8299 +Train: [9] [6100/6250] eta: 0:00:24 lr: 0.000124 grad: 0.0686 (0.0699) loss: 0.8928 (0.8953) time: 0.1687 data: 0.0849 max mem: 8299 +Train: [9] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0625 (0.0699) loss: 0.8975 (0.8953) time: 0.1902 data: 0.1052 max mem: 8299 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0648 (0.0699) loss: 0.8959 (0.8953) time: 0.1532 data: 0.0795 max mem: 8299 +Train: [9] Total time: 0:16:46 (0.1610 s / it) +Averaged stats: lr: 0.000124 grad: 0.0648 (0.0699) loss: 0.8959 (0.8953) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:05:36 loss: 0.9074 (0.9074) time: 5.4216 data: 5.3911 max mem: 8299 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8976 (0.8989) time: 0.1073 data: 0.0818 max mem: 8299 +Eval (hcp-train-subset): [9] Total time: 0:00:15 (0.2442 s / it) +Averaged stats (hcp-train-subset): loss: 0.8976 (0.8989) +Making plots (hcp-train-subset): example=54 +Eval (hcp-val): [9] [ 0/62] eta: 0:03:53 loss: 0.8884 (0.8884) time: 3.7645 data: 3.6847 max mem: 8299 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8934 (0.8942) time: 0.1594 data: 0.1346 max mem: 8299 +Eval (hcp-val): [9] Total time: 0:00:13 (0.2225 s / it) +Averaged stats (hcp-val): loss: 0.8934 (0.8942) +Making plots (hcp-val): example=9 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 10:03:29 lr: 0.000124 grad: 0.0637 (0.0637) loss: 0.9171 (0.9171) time: 5.7935 data: 5.6771 max mem: 8299 +Train: [10] [ 100/6250] eta: 0:22:05 lr: 0.000124 grad: 0.0583 (0.0644) loss: 0.9003 (0.9045) time: 0.1844 data: 0.0928 max mem: 8299 +Train: [10] [ 200/6250] eta: 0:18:51 lr: 0.000124 grad: 0.0608 (0.0658) loss: 0.8985 (0.9016) time: 0.1135 data: 0.0154 max mem: 8299 +Train: [10] [ 300/6250] eta: 0:17:46 lr: 0.000124 grad: 0.0629 (0.0661) loss: 0.8974 (0.8998) time: 0.1643 data: 0.0690 max mem: 8299 +Train: [10] [ 400/6250] eta: 0:16:56 lr: 0.000124 grad: 0.0662 (0.0668) loss: 0.8965 (0.8984) time: 0.1610 data: 0.0579 max mem: 8299 +Train: [10] [ 500/6250] eta: 0:16:14 lr: 0.000124 grad: 0.0666 (0.0670) loss: 0.8919 (0.8970) time: 0.1640 data: 0.0868 max mem: 8299 +Train: [10] [ 600/6250] eta: 0:15:48 lr: 0.000124 grad: 0.0686 (0.0675) loss: 0.8860 (0.8960) time: 0.1721 data: 0.0982 max mem: 8299 +Train: [10] [ 700/6250] eta: 0:15:18 lr: 0.000124 grad: 0.0658 (0.0678) loss: 0.8946 (0.8953) time: 0.1698 data: 0.0923 max mem: 8299 +Train: [10] [ 800/6250] eta: 0:14:46 lr: 0.000124 grad: 0.0666 (0.0677) loss: 0.8921 (0.8949) time: 0.1616 data: 0.0792 max mem: 8299 +Train: [10] [ 900/6250] eta: 0:14:29 lr: 0.000124 grad: 0.0719 (0.0678) loss: 0.8864 (0.8944) time: 0.1514 data: 0.0424 max mem: 8299 +Train: [10] [1000/6250] eta: 0:14:05 lr: 0.000124 grad: 0.0716 (0.0678) loss: 0.8934 (0.8943) time: 0.1617 data: 0.0677 max mem: 8299 +Train: [10] [1100/6250] eta: 0:13:43 lr: 0.000124 grad: 0.0615 (0.0680) loss: 0.8919 (0.8941) time: 0.1456 data: 0.0737 max mem: 8299 +Train: [10] [1200/6250] eta: 0:13:24 lr: 0.000124 grad: 0.0655 (0.0681) loss: 0.8915 (0.8939) time: 0.1448 data: 0.0576 max mem: 8299 +Train: [10] [1300/6250] eta: 0:13:09 lr: 0.000124 grad: 0.0648 (0.0681) loss: 0.8902 (0.8937) time: 0.1619 data: 0.0834 max mem: 8299 +Train: [10] [1400/6250] eta: 0:12:56 lr: 0.000124 grad: 0.0642 (0.0682) loss: 0.8901 (0.8933) time: 0.1695 data: 0.0854 max mem: 8299 +Train: [10] [1500/6250] eta: 0:12:43 lr: 0.000124 grad: 0.0670 (0.0684) loss: 0.8865 (0.8931) time: 0.2034 data: 0.1211 max mem: 8299 +Train: [10] [1600/6250] eta: 0:12:26 lr: 0.000124 grad: 0.0650 (0.0684) loss: 0.8891 (0.8929) time: 0.1575 data: 0.0766 max mem: 8299 +Train: [10] [1700/6250] eta: 0:12:12 lr: 0.000124 grad: 0.0662 (0.0683) loss: 0.8855 (0.8926) time: 0.1860 data: 0.1119 max mem: 8299 +Train: [10] [1800/6250] eta: 0:11:55 lr: 0.000124 grad: 0.0662 (0.0684) loss: 0.8930 (0.8925) time: 0.1727 data: 0.0850 max mem: 8299 +Train: [10] [1900/6250] eta: 0:11:35 lr: 0.000124 grad: 0.0719 (0.0685) loss: 0.8874 (0.8923) time: 0.1562 data: 0.0726 max mem: 8299 +Train: [10] [2000/6250] eta: 0:11:19 lr: 0.000124 grad: 0.0649 (0.0686) loss: 0.8916 (0.8923) time: 0.1761 data: 0.0906 max mem: 8299 +Train: [10] [2100/6250] eta: 0:11:03 lr: 0.000124 grad: 0.0683 (0.0686) loss: 0.8907 (0.8921) time: 0.1766 data: 0.0912 max mem: 8299 +Train: [10] [2200/6250] eta: 0:10:46 lr: 0.000124 grad: 0.0666 (0.0686) loss: 0.8953 (0.8922) time: 0.1542 data: 0.0781 max mem: 8299 +Train: [10] [2300/6250] eta: 0:10:29 lr: 0.000124 grad: 0.0636 (0.0685) loss: 0.8891 (0.8922) time: 0.1528 data: 0.0729 max mem: 8299 +Train: [10] [2400/6250] eta: 0:10:14 lr: 0.000124 grad: 0.0621 (0.0684) loss: 0.8976 (0.8922) time: 0.1571 data: 0.0732 max mem: 8299 +Train: [10] [2500/6250] eta: 0:09:57 lr: 0.000124 grad: 0.0690 (0.0684) loss: 0.8953 (0.8922) time: 0.1378 data: 0.0613 max mem: 8299 +Train: [10] [2600/6250] eta: 0:09:40 lr: 0.000124 grad: 0.0615 (0.0684) loss: 0.8979 (0.8922) time: 0.1502 data: 0.0633 max mem: 8299 +Train: [10] [2700/6250] eta: 0:09:23 lr: 0.000124 grad: 0.0627 (0.0684) loss: 0.8931 (0.8922) time: 0.1234 data: 0.0359 max mem: 8299 +Train: [10] [2800/6250] eta: 0:09:06 lr: 0.000124 grad: 0.0646 (0.0684) loss: 0.8954 (0.8922) time: 0.1654 data: 0.0882 max mem: 8299 +Train: [10] [2900/6250] eta: 0:08:50 lr: 0.000124 grad: 0.0675 (0.0684) loss: 0.8948 (0.8922) time: 0.1396 data: 0.0464 max mem: 8299 +Train: [10] [3000/6250] eta: 0:08:35 lr: 0.000124 grad: 0.0654 (0.0684) loss: 0.8897 (0.8922) time: 0.1710 data: 0.0917 max mem: 8299 +Train: [10] [3100/6250] eta: 0:08:19 lr: 0.000124 grad: 0.0650 (0.0684) loss: 0.8925 (0.8922) time: 0.1658 data: 0.0685 max mem: 8299 +Train: [10] [3200/6250] eta: 0:08:02 lr: 0.000124 grad: 0.0675 (0.0685) loss: 0.8923 (0.8922) time: 0.1442 data: 0.0533 max mem: 8299 +Train: [10] [3300/6250] eta: 0:07:45 lr: 0.000124 grad: 0.0700 (0.0687) loss: 0.8925 (0.8922) time: 0.1368 data: 0.0624 max mem: 8299 +Train: [10] [3400/6250] eta: 0:07:30 lr: 0.000124 grad: 0.0664 (0.0687) loss: 0.8887 (0.8922) time: 0.1696 data: 0.0947 max mem: 8299 +Train: [10] [3500/6250] eta: 0:07:12 lr: 0.000124 grad: 0.0686 (0.0687) loss: 0.8912 (0.8921) time: 0.1076 data: 0.0276 max mem: 8299 +Train: [10] [3600/6250] eta: 0:06:56 lr: 0.000124 grad: 0.0621 (0.0686) loss: 0.8950 (0.8921) time: 0.1417 data: 0.0595 max mem: 8299 +Train: [10] [3700/6250] eta: 0:06:40 lr: 0.000124 grad: 0.0715 (0.0686) loss: 0.8964 (0.8921) time: 0.1570 data: 0.0715 max mem: 8299 +Train: [10] [3800/6250] eta: 0:06:25 lr: 0.000124 grad: 0.0635 (0.0687) loss: 0.8899 (0.8921) time: 0.1377 data: 0.0610 max mem: 8299 +Train: [10] [3900/6250] eta: 0:06:09 lr: 0.000124 grad: 0.0660 (0.0688) loss: 0.8967 (0.8921) time: 0.1605 data: 0.0881 max mem: 8299 +Train: [10] [4000/6250] eta: 0:05:54 lr: 0.000124 grad: 0.0650 (0.0687) loss: 0.8940 (0.8921) time: 0.1430 data: 0.0760 max mem: 8299 +Train: [10] [4100/6250] eta: 0:05:38 lr: 0.000124 grad: 0.0663 (0.0687) loss: 0.8884 (0.8921) time: 0.1466 data: 0.0726 max mem: 8299 +Train: [10] [4200/6250] eta: 0:05:22 lr: 0.000124 grad: 0.0674 (0.0687) loss: 0.8908 (0.8921) time: 0.1670 data: 0.0831 max mem: 8299 +Train: [10] [4300/6250] eta: 0:05:07 lr: 0.000124 grad: 0.0665 (0.0688) loss: 0.8938 (0.8920) time: 0.1844 data: 0.0990 max mem: 8299 +Train: [10] [4400/6250] eta: 0:04:51 lr: 0.000124 grad: 0.0666 (0.0689) loss: 0.8908 (0.8920) time: 0.1338 data: 0.0567 max mem: 8299 +Train: [10] [4500/6250] eta: 0:04:36 lr: 0.000124 grad: 0.0740 (0.0689) loss: 0.8914 (0.8920) time: 0.1852 data: 0.0969 max mem: 8299 +Train: [10] [4600/6250] eta: 0:04:21 lr: 0.000124 grad: 0.0628 (0.0689) loss: 0.8940 (0.8920) time: 0.1594 data: 0.0922 max mem: 8299 +Train: [10] [4700/6250] eta: 0:04:05 lr: 0.000124 grad: 0.0623 (0.0689) loss: 0.8947 (0.8920) time: 0.1462 data: 0.0677 max mem: 8299 +Train: [10] [4800/6250] eta: 0:03:49 lr: 0.000124 grad: 0.0672 (0.0688) loss: 0.8951 (0.8920) time: 0.1288 data: 0.0467 max mem: 8299 +Train: [10] [4900/6250] eta: 0:03:33 lr: 0.000124 grad: 0.0664 (0.0688) loss: 0.8903 (0.8921) time: 0.1438 data: 0.0677 max mem: 8299 +Train: [10] [5000/6250] eta: 0:03:17 lr: 0.000124 grad: 0.0653 (0.0689) loss: 0.8914 (0.8920) time: 0.1522 data: 0.0692 max mem: 8299 +Train: [10] [5100/6250] eta: 0:03:01 lr: 0.000124 grad: 0.0611 (0.0687) loss: 0.8906 (0.8920) time: 0.1388 data: 0.0651 max mem: 8299 +Train: [10] [5200/6250] eta: 0:02:45 lr: 0.000124 grad: 0.0623 (0.0687) loss: 0.8932 (0.8920) time: 0.1452 data: 0.0655 max mem: 8299 +Train: [10] [5300/6250] eta: 0:02:29 lr: 0.000124 grad: 0.0609 (0.0686) loss: 0.8918 (0.8920) time: 0.1440 data: 0.0695 max mem: 8299 +Train: [10] [5400/6250] eta: 0:02:14 lr: 0.000124 grad: 0.0636 (0.0686) loss: 0.8929 (0.8920) time: 0.1582 data: 0.0823 max mem: 8299 +Train: [10] [5500/6250] eta: 0:01:58 lr: 0.000124 grad: 0.0648 (0.0687) loss: 0.8894 (0.8919) time: 0.1623 data: 0.0826 max mem: 8299 +Train: [10] [5600/6250] eta: 0:01:42 lr: 0.000124 grad: 0.0649 (0.0687) loss: 0.8914 (0.8919) time: 0.1722 data: 0.0890 max mem: 8299 +Train: [10] [5700/6250] eta: 0:01:26 lr: 0.000124 grad: 0.0649 (0.0687) loss: 0.8920 (0.8919) time: 0.1503 data: 0.0604 max mem: 8299 +Train: [10] [5800/6250] eta: 0:01:11 lr: 0.000124 grad: 0.0620 (0.0687) loss: 0.8924 (0.8919) time: 0.1556 data: 0.0617 max mem: 8299 +Train: [10] [5900/6250] eta: 0:00:55 lr: 0.000124 grad: 0.0662 (0.0687) loss: 0.8884 (0.8919) time: 0.1875 data: 0.1030 max mem: 8299 +Train: [10] [6000/6250] eta: 0:00:39 lr: 0.000124 grad: 0.0670 (0.0687) loss: 0.8911 (0.8918) time: 0.1656 data: 0.0831 max mem: 8299 +Train: [10] [6100/6250] eta: 0:00:23 lr: 0.000124 grad: 0.0604 (0.0687) loss: 0.8896 (0.8918) time: 0.1592 data: 0.0830 max mem: 8299 +Train: [10] [6200/6250] eta: 0:00:07 lr: 0.000124 grad: 0.0643 (0.0686) loss: 0.8924 (0.8918) time: 0.1596 data: 0.0713 max mem: 8299 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0645 (0.0686) loss: 0.8851 (0.8918) time: 0.1335 data: 0.0532 max mem: 8299 +Train: [10] Total time: 0:16:33 (0.1590 s / it) +Averaged stats: lr: 0.000124 grad: 0.0645 (0.0686) loss: 0.8851 (0.8918) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:04:54 loss: 0.9064 (0.9064) time: 4.7438 data: 4.7126 max mem: 8299 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8969 (0.8977) time: 0.1395 data: 0.1128 max mem: 8299 +Eval (hcp-train-subset): [10] Total time: 0:00:14 (0.2287 s / it) +Averaged stats (hcp-train-subset): loss: 0.8969 (0.8977) +Eval (hcp-val): [10] [ 0/62] eta: 0:04:07 loss: 0.8891 (0.8891) time: 3.9995 data: 3.9203 max mem: 8299 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8905 (0.8926) time: 0.1301 data: 0.1055 max mem: 8299 +Eval (hcp-val): [10] Total time: 0:00:13 (0.2144 s / it) +Averaged stats (hcp-val): loss: 0.8905 (0.8926) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 10:06:32 lr: 0.000124 grad: 0.0647 (0.0647) loss: 0.9303 (0.9303) time: 5.8228 data: 5.6637 max mem: 8299 +Train: [11] [ 100/6250] eta: 0:22:52 lr: 0.000124 grad: 0.0650 (0.0693) loss: 0.8934 (0.9012) time: 0.1954 data: 0.1039 max mem: 8299 +Train: [11] [ 200/6250] eta: 0:19:44 lr: 0.000124 grad: 0.0645 (0.0695) loss: 0.8961 (0.8969) time: 0.1553 data: 0.0643 max mem: 8299 +Train: [11] [ 300/6250] eta: 0:17:56 lr: 0.000124 grad: 0.0680 (0.0693) loss: 0.8837 (0.8956) time: 0.1406 data: 0.0459 max mem: 8299 +Train: [11] [ 400/6250] eta: 0:17:05 lr: 0.000124 grad: 0.0633 (0.0681) loss: 0.8869 (0.8947) time: 0.1643 data: 0.0685 max mem: 8299 +Train: [11] [ 500/6250] eta: 0:16:08 lr: 0.000124 grad: 0.0656 (0.0678) loss: 0.8841 (0.8940) time: 0.1308 data: 0.0420 max mem: 8299 +Train: [11] [ 600/6250] eta: 0:15:43 lr: 0.000124 grad: 0.0640 (0.0673) loss: 0.8873 (0.8931) time: 0.1577 data: 0.0621 max mem: 8299 +Train: [11] [ 700/6250] eta: 0:15:29 lr: 0.000124 grad: 0.0631 (0.0670) loss: 0.8863 (0.8926) time: 0.1546 data: 0.0626 max mem: 8299 +Train: [11] [ 800/6250] eta: 0:15:12 lr: 0.000124 grad: 0.0616 (0.0671) loss: 0.8923 (0.8921) time: 0.1991 data: 0.1049 max mem: 8299 +Train: [11] [ 900/6250] eta: 0:14:53 lr: 0.000124 grad: 0.0679 (0.0671) loss: 0.8887 (0.8920) time: 0.1250 data: 0.0262 max mem: 8299 +Train: [11] [1000/6250] eta: 0:14:36 lr: 0.000124 grad: 0.0634 (0.0674) loss: 0.8869 (0.8919) time: 0.1269 data: 0.0374 max mem: 8299 +Train: [11] [1100/6250] eta: 0:14:16 lr: 0.000124 grad: 0.0661 (0.0673) loss: 0.8901 (0.8918) time: 0.1485 data: 0.0597 max mem: 8299 +Train: [11] [1200/6250] eta: 0:13:59 lr: 0.000124 grad: 0.0708 (0.0676) loss: 0.8840 (0.8914) time: 0.1459 data: 0.0694 max mem: 8299 +Train: [11] [1300/6250] eta: 0:13:38 lr: 0.000124 grad: 0.0647 (0.0676) loss: 0.8884 (0.8912) time: 0.1618 data: 0.0725 max mem: 8299 +Train: [11] [1400/6250] eta: 0:13:19 lr: 0.000124 grad: 0.0660 (0.0675) loss: 0.8920 (0.8911) time: 0.1441 data: 0.0635 max mem: 8299 +Train: [11] [1500/6250] eta: 0:12:58 lr: 0.000124 grad: 0.0627 (0.0674) loss: 0.8924 (0.8910) time: 0.1372 data: 0.0610 max mem: 8299 +Train: [11] [1600/6250] eta: 0:12:39 lr: 0.000124 grad: 0.0629 (0.0676) loss: 0.8910 (0.8909) time: 0.1479 data: 0.0704 max mem: 8299 +Train: [11] [1700/6250] eta: 0:12:24 lr: 0.000124 grad: 0.0628 (0.0678) loss: 0.8940 (0.8909) time: 0.1740 data: 0.0964 max mem: 8299 +Train: [11] [1800/6250] eta: 0:12:04 lr: 0.000124 grad: 0.0655 (0.0677) loss: 0.8919 (0.8908) time: 0.1520 data: 0.0745 max mem: 8299 +Train: [11] [1900/6250] eta: 0:11:46 lr: 0.000124 grad: 0.0637 (0.0676) loss: 0.8906 (0.8908) time: 0.1565 data: 0.0679 max mem: 8299 +Train: [11] [2000/6250] eta: 0:11:29 lr: 0.000124 grad: 0.0610 (0.0675) loss: 0.8917 (0.8909) time: 0.1891 data: 0.1054 max mem: 8299 +Train: [11] [2100/6250] eta: 0:11:10 lr: 0.000124 grad: 0.0664 (0.0676) loss: 0.8931 (0.8909) time: 0.1580 data: 0.0677 max mem: 8299 +Train: [11] [2200/6250] eta: 0:10:54 lr: 0.000124 grad: 0.0637 (0.0675) loss: 0.8916 (0.8909) time: 0.1605 data: 0.0862 max mem: 8299 +Train: [11] [2300/6250] eta: 0:10:37 lr: 0.000124 grad: 0.0639 (0.0674) loss: 0.8895 (0.8909) time: 0.1562 data: 0.0822 max mem: 8299 +Train: [11] [2400/6250] eta: 0:10:22 lr: 0.000124 grad: 0.0648 (0.0673) loss: 0.8899 (0.8910) time: 0.1885 data: 0.0809 max mem: 8299 +Train: [11] [2500/6250] eta: 0:10:06 lr: 0.000124 grad: 0.0599 (0.0672) loss: 0.8895 (0.8911) time: 0.1742 data: 0.0856 max mem: 8299 +Train: [11] [2600/6250] eta: 0:09:48 lr: 0.000124 grad: 0.0588 (0.0670) loss: 0.8938 (0.8910) time: 0.1610 data: 0.0793 max mem: 8299 +Train: [11] [2700/6250] eta: 0:09:32 lr: 0.000124 grad: 0.0599 (0.0671) loss: 0.8864 (0.8910) time: 0.1846 data: 0.1024 max mem: 8299 +Train: [11] [2800/6250] eta: 0:09:15 lr: 0.000124 grad: 0.0606 (0.0669) loss: 0.8931 (0.8910) time: 0.1361 data: 0.0516 max mem: 8299 +Train: [11] [2900/6250] eta: 0:08:58 lr: 0.000124 grad: 0.0619 (0.0668) loss: 0.8968 (0.8911) time: 0.1171 data: 0.0421 max mem: 8299 +Train: [11] [3000/6250] eta: 0:08:40 lr: 0.000124 grad: 0.0633 (0.0667) loss: 0.8930 (0.8912) time: 0.1590 data: 0.0615 max mem: 8299 +Train: [11] [3100/6250] eta: 0:08:25 lr: 0.000124 grad: 0.0586 (0.0666) loss: 0.8936 (0.8913) time: 0.1520 data: 0.0683 max mem: 8299 +Train: [11] [3200/6250] eta: 0:08:10 lr: 0.000124 grad: 0.0604 (0.0665) loss: 0.8949 (0.8914) time: 0.1404 data: 0.0573 max mem: 8299 +Train: [11] [3300/6250] eta: 0:07:56 lr: 0.000124 grad: 0.0591 (0.0664) loss: 0.8931 (0.8915) time: 0.1722 data: 0.1032 max mem: 8299 +Train: [11] [3400/6250] eta: 0:07:41 lr: 0.000124 grad: 0.0654 (0.0664) loss: 0.8914 (0.8915) time: 0.1418 data: 0.0585 max mem: 8299 +Train: [11] [3500/6250] eta: 0:07:26 lr: 0.000124 grad: 0.0614 (0.0662) loss: 0.8967 (0.8916) time: 0.1675 data: 0.0872 max mem: 8299 +Train: [11] [3600/6250] eta: 0:07:11 lr: 0.000124 grad: 0.0586 (0.0661) loss: 0.8926 (0.8917) time: 0.1763 data: 0.0960 max mem: 8299 +Train: [11] [3700/6250] eta: 0:06:55 lr: 0.000124 grad: 0.0654 (0.0661) loss: 0.8906 (0.8917) time: 0.1480 data: 0.0648 max mem: 8299 +Train: [11] [3800/6250] eta: 0:06:39 lr: 0.000124 grad: 0.0611 (0.0660) loss: 0.8924 (0.8917) time: 0.1810 data: 0.1017 max mem: 8299 +Train: [11] [3900/6250] eta: 0:06:22 lr: 0.000124 grad: 0.0635 (0.0661) loss: 0.8956 (0.8917) time: 0.1451 data: 0.0674 max mem: 8299 +Train: [11] [4000/6250] eta: 0:06:05 lr: 0.000123 grad: 0.0612 (0.0661) loss: 0.8923 (0.8917) time: 0.1507 data: 0.0664 max mem: 8299 +Train: [11] [4100/6250] eta: 0:05:48 lr: 0.000123 grad: 0.0583 (0.0660) loss: 0.8972 (0.8917) time: 0.1551 data: 0.0760 max mem: 8299 +Train: [11] [4200/6250] eta: 0:05:32 lr: 0.000123 grad: 0.0560 (0.0659) loss: 0.8929 (0.8917) time: 0.1536 data: 0.0637 max mem: 8299 +Train: [11] [4300/6250] eta: 0:05:16 lr: 0.000123 grad: 0.0585 (0.0658) loss: 0.8921 (0.8917) time: 0.1416 data: 0.0652 max mem: 8299 +Train: [11] [4400/6250] eta: 0:04:59 lr: 0.000123 grad: 0.0604 (0.0658) loss: 0.8963 (0.8918) time: 0.1459 data: 0.0692 max mem: 8299 +Train: [11] [4500/6250] eta: 0:04:42 lr: 0.000123 grad: 0.0634 (0.0657) loss: 0.8904 (0.8918) time: 0.1602 data: 0.0768 max mem: 8299 +Train: [11] [4600/6250] eta: 0:04:26 lr: 0.000123 grad: 0.0620 (0.0656) loss: 0.8867 (0.8918) time: 0.1203 data: 0.0353 max mem: 8299 +Train: [11] [4700/6250] eta: 0:04:10 lr: 0.000123 grad: 0.0604 (0.0656) loss: 0.8919 (0.8918) time: 0.1533 data: 0.0793 max mem: 8299 +Train: [11] [4800/6250] eta: 0:03:54 lr: 0.000123 grad: 0.0590 (0.0656) loss: 0.8942 (0.8918) time: 0.1646 data: 0.0879 max mem: 8299 +Train: [11] [4900/6250] eta: 0:03:37 lr: 0.000123 grad: 0.0652 (0.0656) loss: 0.8893 (0.8918) time: 0.1445 data: 0.0672 max mem: 8299 +Train: [11] [5000/6250] eta: 0:03:21 lr: 0.000123 grad: 0.0662 (0.0656) loss: 0.8884 (0.8918) time: 0.1338 data: 0.0545 max mem: 8299 +Train: [11] [5100/6250] eta: 0:03:04 lr: 0.000123 grad: 0.0614 (0.0655) loss: 0.8865 (0.8918) time: 0.1531 data: 0.0672 max mem: 8299 +Train: [11] [5200/6250] eta: 0:02:48 lr: 0.000123 grad: 0.0601 (0.0654) loss: 0.8899 (0.8917) time: 0.1577 data: 0.0731 max mem: 8299 +Train: [11] [5300/6250] eta: 0:02:32 lr: 0.000123 grad: 0.0582 (0.0654) loss: 0.8878 (0.8917) time: 0.1587 data: 0.0675 max mem: 8299 +Train: [11] [5400/6250] eta: 0:02:16 lr: 0.000123 grad: 0.0542 (0.0654) loss: 0.8973 (0.8917) time: 0.1589 data: 0.0774 max mem: 8299 +Train: [11] [5500/6250] eta: 0:02:00 lr: 0.000123 grad: 0.0638 (0.0653) loss: 0.8886 (0.8917) time: 0.1790 data: 0.0957 max mem: 8299 +Train: [11] [5600/6250] eta: 0:01:44 lr: 0.000123 grad: 0.0593 (0.0653) loss: 0.8933 (0.8917) time: 0.1574 data: 0.0771 max mem: 8299 +Train: [11] [5700/6250] eta: 0:01:28 lr: 0.000123 grad: 0.0713 (0.0653) loss: 0.8871 (0.8916) time: 0.1697 data: 0.0826 max mem: 8299 +Train: [11] [5800/6250] eta: 0:01:12 lr: 0.000123 grad: 0.0586 (0.0652) loss: 0.8928 (0.8916) time: 0.1560 data: 0.0816 max mem: 8299 +Train: [11] [5900/6250] eta: 0:00:56 lr: 0.000123 grad: 0.0608 (0.0652) loss: 0.8885 (0.8916) time: 0.2158 data: 0.1361 max mem: 8299 +Train: [11] [6000/6250] eta: 0:00:40 lr: 0.000123 grad: 0.0567 (0.0652) loss: 0.8867 (0.8915) time: 0.1714 data: 0.0904 max mem: 8299 +Train: [11] [6100/6250] eta: 0:00:24 lr: 0.000123 grad: 0.0591 (0.0651) loss: 0.8881 (0.8915) time: 0.1644 data: 0.0851 max mem: 8299 +Train: [11] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.0581 (0.0651) loss: 0.8921 (0.8915) time: 0.1639 data: 0.0813 max mem: 8299 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0557 (0.0651) loss: 0.8927 (0.8914) time: 0.1651 data: 0.0786 max mem: 8299 +Train: [11] Total time: 0:16:54 (0.1623 s / it) +Averaged stats: lr: 0.000123 grad: 0.0557 (0.0651) loss: 0.8927 (0.8914) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:05:35 loss: 0.9051 (0.9051) time: 5.4034 data: 5.3673 max mem: 8299 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8957 (0.8960) time: 0.1495 data: 0.1229 max mem: 8299 +Eval (hcp-train-subset): [11] Total time: 0:00:13 (0.2163 s / it) +Averaged stats (hcp-train-subset): loss: 0.8957 (0.8960) +Eval (hcp-val): [11] [ 0/62] eta: 0:04:58 loss: 0.8859 (0.8859) time: 4.8194 data: 4.7889 max mem: 8299 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8903 (0.8916) time: 0.1325 data: 0.1077 max mem: 8299 +Eval (hcp-val): [11] Total time: 0:00:13 (0.2254 s / it) +Averaged stats (hcp-val): loss: 0.8903 (0.8916) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 8:30:09 lr: 0.000123 grad: 0.0442 (0.0442) loss: 0.9219 (0.9219) time: 4.8976 data: 4.5968 max mem: 8299 +Train: [12] [ 100/6250] eta: 0:22:02 lr: 0.000123 grad: 0.0700 (0.0784) loss: 0.8877 (0.8934) time: 0.1591 data: 0.0624 max mem: 8299 +Train: [12] [ 200/6250] eta: 0:18:42 lr: 0.000123 grad: 0.0655 (0.0769) loss: 0.8912 (0.8899) time: 0.1604 data: 0.0571 max mem: 8299 +Train: [12] [ 300/6250] eta: 0:17:21 lr: 0.000123 grad: 0.0580 (0.0742) loss: 0.8930 (0.8908) time: 0.1447 data: 0.0518 max mem: 8299 +Train: [12] [ 400/6250] eta: 0:16:30 lr: 0.000123 grad: 0.0709 (0.0733) loss: 0.8906 (0.8913) time: 0.1342 data: 0.0256 max mem: 8299 +Train: [12] [ 500/6250] eta: 0:15:47 lr: 0.000123 grad: 0.0620 (0.0721) loss: 0.8981 (0.8919) time: 0.1169 data: 0.0233 max mem: 8299 +Train: [12] [ 600/6250] eta: 0:15:20 lr: 0.000123 grad: 0.0630 (0.0707) loss: 0.8906 (0.8920) time: 0.1725 data: 0.0576 max mem: 8299 +Train: [12] [ 700/6250] eta: 0:14:58 lr: 0.000123 grad: 0.0593 (0.0694) loss: 0.8952 (0.8920) time: 0.1913 data: 0.1090 max mem: 8299 +Train: [12] [ 800/6250] eta: 0:14:35 lr: 0.000123 grad: 0.0661 (0.0686) loss: 0.8930 (0.8919) time: 0.1425 data: 0.0573 max mem: 8299 +Train: [12] [ 900/6250] eta: 0:14:07 lr: 0.000123 grad: 0.0612 (0.0678) loss: 0.8917 (0.8919) time: 0.1199 data: 0.0438 max mem: 8299 +Train: [12] [1000/6250] eta: 0:13:46 lr: 0.000123 grad: 0.0569 (0.0669) loss: 0.8976 (0.8921) time: 0.1567 data: 0.0770 max mem: 8299 +Train: [12] [1100/6250] eta: 0:13:28 lr: 0.000123 grad: 0.0591 (0.0664) loss: 0.8910 (0.8921) time: 0.1434 data: 0.0652 max mem: 8299 +Train: [12] [1200/6250] eta: 0:13:10 lr: 0.000123 grad: 0.0597 (0.0659) loss: 0.8918 (0.8921) time: 0.1422 data: 0.0643 max mem: 8299 +Train: [12] [1300/6250] eta: 0:12:55 lr: 0.000123 grad: 0.0596 (0.0655) loss: 0.8923 (0.8921) time: 0.1599 data: 0.0775 max mem: 8299 +Train: [12] [1400/6250] eta: 0:12:39 lr: 0.000123 grad: 0.0568 (0.0652) loss: 0.8902 (0.8920) time: 0.1228 data: 0.0321 max mem: 8299 +Train: [12] [1500/6250] eta: 0:12:22 lr: 0.000123 grad: 0.0560 (0.0648) loss: 0.8928 (0.8921) time: 0.1629 data: 0.0854 max mem: 8299 +Train: [12] [1600/6250] eta: 0:12:04 lr: 0.000123 grad: 0.0608 (0.0646) loss: 0.8872 (0.8920) time: 0.1617 data: 0.0883 max mem: 8299 +Train: [12] [1700/6250] eta: 0:11:48 lr: 0.000123 grad: 0.0568 (0.0643) loss: 0.8883 (0.8919) time: 0.1063 data: 0.0284 max mem: 8299 +Train: [12] [1800/6250] eta: 0:11:35 lr: 0.000123 grad: 0.0609 (0.0641) loss: 0.8875 (0.8918) time: 0.1682 data: 0.0888 max mem: 8299 +Train: [12] [1900/6250] eta: 0:11:19 lr: 0.000123 grad: 0.0589 (0.0640) loss: 0.8908 (0.8917) time: 0.1472 data: 0.0759 max mem: 8299 +Train: [12] [2000/6250] eta: 0:11:05 lr: 0.000123 grad: 0.0553 (0.0638) loss: 0.8863 (0.8916) time: 0.1530 data: 0.0689 max mem: 8299 +Train: [12] [2100/6250] eta: 0:10:47 lr: 0.000123 grad: 0.0564 (0.0637) loss: 0.8884 (0.8914) time: 0.1433 data: 0.0634 max mem: 8299 +Train: [12] [2200/6250] eta: 0:10:31 lr: 0.000123 grad: 0.0579 (0.0635) loss: 0.8858 (0.8913) time: 0.1694 data: 0.1024 max mem: 8299 +Train: [12] [2300/6250] eta: 0:10:15 lr: 0.000123 grad: 0.0586 (0.0634) loss: 0.8907 (0.8913) time: 0.1604 data: 0.0748 max mem: 8299 +Train: [12] [2400/6250] eta: 0:10:00 lr: 0.000123 grad: 0.0589 (0.0632) loss: 0.8895 (0.8913) time: 0.1646 data: 0.0863 max mem: 8299 +Train: [12] [2500/6250] eta: 0:09:44 lr: 0.000123 grad: 0.0609 (0.0632) loss: 0.8877 (0.8912) time: 0.1691 data: 0.0782 max mem: 8299 +Train: [12] [2600/6250] eta: 0:09:29 lr: 0.000123 grad: 0.0572 (0.0631) loss: 0.8876 (0.8912) time: 0.1486 data: 0.0734 max mem: 8299 +Train: [12] [2700/6250] eta: 0:09:13 lr: 0.000123 grad: 0.0588 (0.0631) loss: 0.8863 (0.8911) time: 0.1501 data: 0.0637 max mem: 8299 +Train: [12] [2800/6250] eta: 0:08:58 lr: 0.000123 grad: 0.0594 (0.0629) loss: 0.8873 (0.8911) time: 0.1570 data: 0.0843 max mem: 8299 +Train: [12] [2900/6250] eta: 0:08:42 lr: 0.000123 grad: 0.0603 (0.0629) loss: 0.8899 (0.8910) time: 0.1473 data: 0.0709 max mem: 8299 +Train: [12] [3000/6250] eta: 0:08:25 lr: 0.000123 grad: 0.0614 (0.0629) loss: 0.8909 (0.8909) time: 0.1519 data: 0.0705 max mem: 8299 +Train: [12] [3100/6250] eta: 0:08:09 lr: 0.000123 grad: 0.0583 (0.0628) loss: 0.8887 (0.8908) time: 0.1565 data: 0.0798 max mem: 8299 +Train: [12] [3200/6250] eta: 0:07:54 lr: 0.000123 grad: 0.0557 (0.0628) loss: 0.8855 (0.8906) time: 0.1641 data: 0.0805 max mem: 8299 +Train: [12] [3300/6250] eta: 0:07:38 lr: 0.000123 grad: 0.0596 (0.0628) loss: 0.8863 (0.8906) time: 0.1563 data: 0.0721 max mem: 8299 +Train: [12] [3400/6250] eta: 0:07:22 lr: 0.000123 grad: 0.0603 (0.0628) loss: 0.8850 (0.8905) time: 0.1342 data: 0.0546 max mem: 8299 +Train: [12] [3500/6250] eta: 0:07:06 lr: 0.000123 grad: 0.0637 (0.0628) loss: 0.8917 (0.8905) time: 0.1525 data: 0.0709 max mem: 8299 +Train: [12] [3600/6250] eta: 0:06:50 lr: 0.000123 grad: 0.0588 (0.0627) loss: 0.8909 (0.8905) time: 0.1549 data: 0.0778 max mem: 8299 +Train: [12] [3700/6250] eta: 0:06:35 lr: 0.000123 grad: 0.0580 (0.0627) loss: 0.8900 (0.8904) time: 0.1217 data: 0.0410 max mem: 8299 +Train: [12] [3800/6250] eta: 0:06:19 lr: 0.000123 grad: 0.0636 (0.0627) loss: 0.8912 (0.8904) time: 0.1537 data: 0.0744 max mem: 8299 +Train: [12] [3900/6250] eta: 0:06:03 lr: 0.000123 grad: 0.0646 (0.0627) loss: 0.8853 (0.8903) time: 0.1520 data: 0.0640 max mem: 8299 +Train: [12] [4000/6250] eta: 0:05:48 lr: 0.000123 grad: 0.0584 (0.0628) loss: 0.8847 (0.8903) time: 0.1565 data: 0.0894 max mem: 8299 +Train: [12] [4100/6250] eta: 0:05:33 lr: 0.000123 grad: 0.0666 (0.0628) loss: 0.8867 (0.8902) time: 0.1382 data: 0.0583 max mem: 8299 +Train: [12] [4200/6250] eta: 0:05:18 lr: 0.000123 grad: 0.0599 (0.0628) loss: 0.8901 (0.8902) time: 0.1655 data: 0.0787 max mem: 8299 +Train: [12] [4300/6250] eta: 0:05:03 lr: 0.000123 grad: 0.0614 (0.0628) loss: 0.8904 (0.8901) time: 0.1806 data: 0.0912 max mem: 8299 +Train: [12] [4400/6250] eta: 0:04:47 lr: 0.000123 grad: 0.0621 (0.0628) loss: 0.8869 (0.8901) time: 0.1848 data: 0.0978 max mem: 8299 +Train: [12] [4500/6250] eta: 0:04:31 lr: 0.000123 grad: 0.0593 (0.0628) loss: 0.8934 (0.8901) time: 0.1513 data: 0.0738 max mem: 8299 +Train: [12] [4600/6250] eta: 0:04:16 lr: 0.000123 grad: 0.0601 (0.0628) loss: 0.8862 (0.8901) time: 0.2002 data: 0.1052 max mem: 8299 +Train: [12] [4700/6250] eta: 0:04:01 lr: 0.000123 grad: 0.0595 (0.0628) loss: 0.8915 (0.8901) time: 0.1601 data: 0.0779 max mem: 8299 +Train: [12] [4800/6250] eta: 0:03:45 lr: 0.000123 grad: 0.0621 (0.0628) loss: 0.8889 (0.8901) time: 0.1805 data: 0.1078 max mem: 8299 +Train: [12] [4900/6250] eta: 0:03:29 lr: 0.000123 grad: 0.0603 (0.0628) loss: 0.8917 (0.8901) time: 0.1474 data: 0.0554 max mem: 8299 +Train: [12] [5000/6250] eta: 0:03:13 lr: 0.000123 grad: 0.0590 (0.0628) loss: 0.8886 (0.8901) time: 0.1571 data: 0.0678 max mem: 8299 +Train: [12] [5100/6250] eta: 0:02:58 lr: 0.000123 grad: 0.0603 (0.0628) loss: 0.8897 (0.8901) time: 0.1342 data: 0.0457 max mem: 8299 +Train: [12] [5200/6250] eta: 0:02:42 lr: 0.000123 grad: 0.0615 (0.0628) loss: 0.8849 (0.8900) time: 0.1801 data: 0.0949 max mem: 8299 +Train: [12] [5300/6250] eta: 0:02:27 lr: 0.000123 grad: 0.0590 (0.0628) loss: 0.8888 (0.8900) time: 0.1685 data: 0.0898 max mem: 8299 +Train: [12] [5400/6250] eta: 0:02:11 lr: 0.000123 grad: 0.0572 (0.0628) loss: 0.8922 (0.8900) time: 0.1382 data: 0.0551 max mem: 8299 +Train: [12] [5500/6250] eta: 0:01:56 lr: 0.000123 grad: 0.0613 (0.0628) loss: 0.8950 (0.8900) time: 0.1556 data: 0.0768 max mem: 8299 +Train: [12] [5600/6250] eta: 0:01:40 lr: 0.000123 grad: 0.0617 (0.0627) loss: 0.8885 (0.8900) time: 0.1614 data: 0.0810 max mem: 8299 +Train: [12] [5700/6250] eta: 0:01:25 lr: 0.000123 grad: 0.0568 (0.0627) loss: 0.8910 (0.8900) time: 0.1591 data: 0.0796 max mem: 8299 +Train: [12] [5800/6250] eta: 0:01:09 lr: 0.000123 grad: 0.0629 (0.0627) loss: 0.8872 (0.8900) time: 0.1551 data: 0.0715 max mem: 8299 +Train: [12] [5900/6250] eta: 0:00:54 lr: 0.000123 grad: 0.0678 (0.0628) loss: 0.8809 (0.8899) time: 0.1160 data: 0.0460 max mem: 8299 +Train: [12] [6000/6250] eta: 0:00:38 lr: 0.000123 grad: 0.0618 (0.0628) loss: 0.8882 (0.8899) time: 0.1407 data: 0.0490 max mem: 8299 +Train: [12] [6100/6250] eta: 0:00:23 lr: 0.000123 grad: 0.0631 (0.0628) loss: 0.8852 (0.8898) time: 0.1617 data: 0.0729 max mem: 8299 +Train: [12] [6200/6250] eta: 0:00:07 lr: 0.000123 grad: 0.0585 (0.0628) loss: 0.8883 (0.8898) time: 0.1574 data: 0.0684 max mem: 8299 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0687 (0.0628) loss: 0.8874 (0.8898) time: 0.1679 data: 0.1032 max mem: 8299 +Train: [12] Total time: 0:16:17 (0.1564 s / it) +Averaged stats: lr: 0.000123 grad: 0.0687 (0.0628) loss: 0.8874 (0.8898) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:05:36 loss: 0.9043 (0.9043) time: 5.4344 data: 5.4027 max mem: 8299 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8958 (0.8954) time: 0.1108 data: 0.0861 max mem: 8299 +Eval (hcp-train-subset): [12] Total time: 0:00:13 (0.2220 s / it) +Averaged stats (hcp-train-subset): loss: 0.8958 (0.8954) +Eval (hcp-val): [12] [ 0/62] eta: 0:03:54 loss: 0.8850 (0.8850) time: 3.7768 data: 3.7069 max mem: 8299 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8898 (0.8910) time: 0.1435 data: 0.1182 max mem: 8299 +Eval (hcp-val): [12] Total time: 0:00:13 (0.2201 s / it) +Averaged stats (hcp-val): loss: 0.8898 (0.8910) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 7:18:33 lr: 0.000123 grad: 0.0459 (0.0459) loss: 0.8899 (0.8899) time: 4.2102 data: 3.8718 max mem: 8299 +Train: [13] [ 100/6250] eta: 0:21:24 lr: 0.000123 grad: 0.0579 (0.0703) loss: 0.8953 (0.8957) time: 0.1612 data: 0.0769 max mem: 8299 +Train: [13] [ 200/6250] eta: 0:18:26 lr: 0.000123 grad: 0.0671 (0.0694) loss: 0.8842 (0.8920) time: 0.1561 data: 0.0662 max mem: 8299 +Train: [13] [ 300/6250] eta: 0:16:58 lr: 0.000123 grad: 0.0573 (0.0661) loss: 0.8817 (0.8911) time: 0.1248 data: 0.0330 max mem: 8299 +Train: [13] [ 400/6250] eta: 0:16:13 lr: 0.000123 grad: 0.0634 (0.0653) loss: 0.8881 (0.8902) time: 0.1484 data: 0.0549 max mem: 8299 +Train: [13] [ 500/6250] eta: 0:15:30 lr: 0.000123 grad: 0.0564 (0.0645) loss: 0.8915 (0.8903) time: 0.1464 data: 0.0729 max mem: 8299 +Train: [13] [ 600/6250] eta: 0:14:53 lr: 0.000123 grad: 0.0598 (0.0640) loss: 0.8911 (0.8903) time: 0.1493 data: 0.0552 max mem: 8299 +Train: [13] [ 700/6250] eta: 0:14:47 lr: 0.000123 grad: 0.0557 (0.0639) loss: 0.8910 (0.8906) time: 0.2083 data: 0.1155 max mem: 8299 +Train: [13] [ 800/6250] eta: 0:14:33 lr: 0.000123 grad: 0.0558 (0.0640) loss: 0.8950 (0.8908) time: 0.1494 data: 0.0612 max mem: 8299 +Train: [13] [ 900/6250] eta: 0:14:28 lr: 0.000123 grad: 0.0567 (0.0636) loss: 0.8890 (0.8909) time: 0.2193 data: 0.1460 max mem: 8299 +Train: [13] [1000/6250] eta: 0:14:12 lr: 0.000123 grad: 0.0586 (0.0632) loss: 0.8961 (0.8912) time: 0.1366 data: 0.0656 max mem: 8299 +Train: [13] [1100/6250] eta: 0:13:58 lr: 0.000123 grad: 0.0618 (0.0628) loss: 0.8919 (0.8912) time: 0.1990 data: 0.1256 max mem: 8299 +Train: [13] [1200/6250] eta: 0:13:49 lr: 0.000123 grad: 0.0566 (0.0625) loss: 0.8890 (0.8913) time: 0.2203 data: 0.1385 max mem: 8299 +Train: [13] [1300/6250] eta: 0:13:37 lr: 0.000123 grad: 0.0544 (0.0625) loss: 0.8893 (0.8912) time: 0.1624 data: 0.0865 max mem: 8299 +Train: [13] [1400/6250] eta: 0:13:24 lr: 0.000123 grad: 0.0590 (0.0622) loss: 0.8894 (0.8912) time: 0.1750 data: 0.1054 max mem: 8299 +Train: [13] [1500/6250] eta: 0:13:10 lr: 0.000123 grad: 0.0566 (0.0620) loss: 0.8927 (0.8912) time: 0.1655 data: 0.0793 max mem: 8299 +Train: [13] [1600/6250] eta: 0:12:54 lr: 0.000123 grad: 0.0592 (0.0619) loss: 0.8951 (0.8912) time: 0.1936 data: 0.1115 max mem: 8299 +Train: [13] [1700/6250] eta: 0:12:38 lr: 0.000123 grad: 0.0628 (0.0619) loss: 0.8908 (0.8912) time: 0.1670 data: 0.0967 max mem: 8299 +Train: [13] [1800/6250] eta: 0:12:22 lr: 0.000123 grad: 0.0584 (0.0618) loss: 0.8891 (0.8911) time: 0.1639 data: 0.0893 max mem: 8299 +Train: [13] [1900/6250] eta: 0:12:06 lr: 0.000123 grad: 0.0623 (0.0618) loss: 0.8856 (0.8910) time: 0.1760 data: 0.0979 max mem: 8299 +Train: [13] [2000/6250] eta: 0:11:48 lr: 0.000123 grad: 0.0592 (0.0617) loss: 0.8915 (0.8909) time: 0.1780 data: 0.1038 max mem: 8299 +Train: [13] [2100/6250] eta: 0:11:29 lr: 0.000123 grad: 0.0611 (0.0617) loss: 0.8897 (0.8907) time: 0.1642 data: 0.0833 max mem: 8299 +Train: [13] [2200/6250] eta: 0:11:09 lr: 0.000123 grad: 0.0599 (0.0617) loss: 0.8889 (0.8907) time: 0.1607 data: 0.0799 max mem: 8299 +Train: [13] [2300/6250] eta: 0:10:51 lr: 0.000123 grad: 0.0565 (0.0617) loss: 0.8945 (0.8906) time: 0.1600 data: 0.0794 max mem: 8299 +Train: [13] [2400/6250] eta: 0:10:33 lr: 0.000123 grad: 0.0612 (0.0617) loss: 0.8897 (0.8905) time: 0.1593 data: 0.0708 max mem: 8299 +Train: [13] [2500/6250] eta: 0:10:15 lr: 0.000123 grad: 0.0657 (0.0619) loss: 0.8861 (0.8904) time: 0.1385 data: 0.0586 max mem: 8299 +Train: [13] [2600/6250] eta: 0:09:58 lr: 0.000123 grad: 0.0584 (0.0619) loss: 0.8866 (0.8903) time: 0.1864 data: 0.1015 max mem: 8299 +Train: [13] [2700/6250] eta: 0:09:40 lr: 0.000123 grad: 0.0619 (0.0620) loss: 0.8911 (0.8901) time: 0.1700 data: 0.0782 max mem: 8299 +Train: [13] [2800/6250] eta: 0:09:24 lr: 0.000123 grad: 0.0661 (0.0622) loss: 0.8872 (0.8899) time: 0.1491 data: 0.0660 max mem: 8299 +Train: [13] [2900/6250] eta: 0:09:07 lr: 0.000123 grad: 0.0647 (0.0623) loss: 0.8858 (0.8898) time: 0.1471 data: 0.0595 max mem: 8299 +Train: [13] [3000/6250] eta: 0:08:51 lr: 0.000123 grad: 0.0632 (0.0625) loss: 0.8859 (0.8896) time: 0.1559 data: 0.0609 max mem: 8299 +Train: [13] [3100/6250] eta: 0:08:33 lr: 0.000123 grad: 0.0636 (0.0627) loss: 0.8847 (0.8895) time: 0.1588 data: 0.0660 max mem: 8299 +Train: [13] [3200/6250] eta: 0:08:16 lr: 0.000123 grad: 0.0697 (0.0628) loss: 0.8868 (0.8893) time: 0.1566 data: 0.0643 max mem: 8299 +Train: [13] [3300/6250] eta: 0:07:58 lr: 0.000123 grad: 0.0687 (0.0630) loss: 0.8822 (0.8891) time: 0.1278 data: 0.0396 max mem: 8299 +Train: [13] [3400/6250] eta: 0:07:41 lr: 0.000123 grad: 0.0658 (0.0631) loss: 0.8851 (0.8890) time: 0.1697 data: 0.0893 max mem: 8299 +Train: [13] [3500/6250] eta: 0:07:24 lr: 0.000123 grad: 0.0657 (0.0632) loss: 0.8834 (0.8888) time: 0.1522 data: 0.0661 max mem: 8299 +Train: [13] [3600/6250] eta: 0:07:07 lr: 0.000123 grad: 0.0688 (0.0634) loss: 0.8854 (0.8887) time: 0.1645 data: 0.0790 max mem: 8299 +Train: [13] [3700/6250] eta: 0:06:52 lr: 0.000122 grad: 0.0695 (0.0635) loss: 0.8854 (0.8885) time: 0.2014 data: 0.1218 max mem: 8299 +Train: [13] [3800/6250] eta: 0:06:36 lr: 0.000122 grad: 0.0732 (0.0638) loss: 0.8747 (0.8884) time: 0.1527 data: 0.0837 max mem: 8299 +Train: [13] [3900/6250] eta: 0:06:20 lr: 0.000122 grad: 0.0739 (0.0640) loss: 0.8844 (0.8882) time: 0.1740 data: 0.0939 max mem: 8299 +Train: [13] [4000/6250] eta: 0:06:04 lr: 0.000122 grad: 0.0658 (0.0640) loss: 0.8795 (0.8881) time: 0.1520 data: 0.0839 max mem: 8299 +Train: [13] [4100/6250] eta: 0:05:48 lr: 0.000122 grad: 0.0636 (0.0641) loss: 0.8888 (0.8880) time: 0.2083 data: 0.1292 max mem: 8299 +Train: [13] [4200/6250] eta: 0:05:31 lr: 0.000122 grad: 0.0659 (0.0643) loss: 0.8822 (0.8879) time: 0.1698 data: 0.0927 max mem: 8299 +Train: [13] [4300/6250] eta: 0:05:14 lr: 0.000122 grad: 0.0621 (0.0643) loss: 0.8890 (0.8878) time: 0.1707 data: 0.1017 max mem: 8299 +Train: [13] [4400/6250] eta: 0:04:58 lr: 0.000122 grad: 0.0595 (0.0644) loss: 0.8895 (0.8878) time: 0.1392 data: 0.0635 max mem: 8299 +Train: [13] [4500/6250] eta: 0:04:42 lr: 0.000122 grad: 0.0662 (0.0645) loss: 0.8889 (0.8877) time: 0.1674 data: 0.0843 max mem: 8299 +Train: [13] [4600/6250] eta: 0:04:26 lr: 0.000122 grad: 0.0699 (0.0646) loss: 0.8866 (0.8876) time: 0.1557 data: 0.0690 max mem: 8299 +Train: [13] [4700/6250] eta: 0:04:10 lr: 0.000122 grad: 0.0633 (0.0646) loss: 0.8835 (0.8876) time: 0.1482 data: 0.0694 max mem: 8299 +Train: [13] [4800/6250] eta: 0:03:54 lr: 0.000122 grad: 0.0642 (0.0646) loss: 0.8855 (0.8876) time: 0.1700 data: 0.1010 max mem: 8299 +Train: [13] [4900/6250] eta: 0:03:37 lr: 0.000122 grad: 0.0604 (0.0646) loss: 0.8843 (0.8875) time: 0.1556 data: 0.0717 max mem: 8299 +Train: [13] [5000/6250] eta: 0:03:21 lr: 0.000122 grad: 0.0704 (0.0647) loss: 0.8841 (0.8875) time: 0.1681 data: 0.0821 max mem: 8299 +Train: [13] [5100/6250] eta: 0:03:05 lr: 0.000122 grad: 0.0651 (0.0648) loss: 0.8827 (0.8874) time: 0.1826 data: 0.0964 max mem: 8299 +Train: [13] [5200/6250] eta: 0:02:48 lr: 0.000122 grad: 0.0620 (0.0648) loss: 0.8871 (0.8874) time: 0.1432 data: 0.0592 max mem: 8299 +Train: [13] [5300/6250] eta: 0:02:32 lr: 0.000122 grad: 0.0641 (0.0649) loss: 0.8884 (0.8873) time: 0.1467 data: 0.0669 max mem: 8299 +Train: [13] [5400/6250] eta: 0:02:16 lr: 0.000122 grad: 0.0637 (0.0648) loss: 0.8899 (0.8873) time: 0.1691 data: 0.0931 max mem: 8299 +Train: [13] [5500/6250] eta: 0:02:00 lr: 0.000122 grad: 0.0604 (0.0648) loss: 0.8830 (0.8872) time: 0.1589 data: 0.0786 max mem: 8299 +Train: [13] [5600/6250] eta: 0:01:44 lr: 0.000122 grad: 0.0609 (0.0648) loss: 0.8858 (0.8872) time: 0.1657 data: 0.0825 max mem: 8299 +Train: [13] [5700/6250] eta: 0:01:28 lr: 0.000122 grad: 0.0618 (0.0648) loss: 0.8911 (0.8871) time: 0.1713 data: 0.0973 max mem: 8299 +Train: [13] [5800/6250] eta: 0:01:12 lr: 0.000122 grad: 0.0624 (0.0648) loss: 0.8811 (0.8871) time: 0.1611 data: 0.0729 max mem: 8299 +Train: [13] [5900/6250] eta: 0:00:56 lr: 0.000122 grad: 0.0622 (0.0648) loss: 0.8846 (0.8870) time: 0.1707 data: 0.0938 max mem: 8299 +Train: [13] [6000/6250] eta: 0:00:40 lr: 0.000122 grad: 0.0593 (0.0648) loss: 0.8810 (0.8870) time: 0.2014 data: 0.1332 max mem: 8299 +Train: [13] [6100/6250] eta: 0:00:24 lr: 0.000122 grad: 0.0640 (0.0648) loss: 0.8832 (0.8870) time: 0.1462 data: 0.0779 max mem: 8299 +Train: [13] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0637 (0.0648) loss: 0.8818 (0.8869) time: 0.1334 data: 0.0547 max mem: 8299 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0615 (0.0648) loss: 0.8810 (0.8869) time: 0.1669 data: 0.0792 max mem: 8299 +Train: [13] Total time: 0:16:49 (0.1615 s / it) +Averaged stats: lr: 0.000122 grad: 0.0615 (0.0648) loss: 0.8810 (0.8869) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:05:33 loss: 0.9055 (0.9055) time: 5.3807 data: 5.3496 max mem: 8299 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8940 (0.8951) time: 0.1293 data: 0.1034 max mem: 8299 +Eval (hcp-train-subset): [13] Total time: 0:00:13 (0.2137 s / it) +Averaged stats (hcp-train-subset): loss: 0.8940 (0.8951) +Eval (hcp-val): [13] [ 0/62] eta: 0:04:48 loss: 0.8856 (0.8856) time: 4.6539 data: 4.6237 max mem: 8299 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8879 (0.8894) time: 0.1477 data: 0.1228 max mem: 8299 +Eval (hcp-val): [13] Total time: 0:00:13 (0.2192 s / it) +Averaged stats (hcp-val): loss: 0.8879 (0.8894) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 8:30:17 lr: 0.000122 grad: 0.0793 (0.0793) loss: 0.9073 (0.9073) time: 4.8989 data: 4.6258 max mem: 8299 +Train: [14] [ 100/6250] eta: 0:21:18 lr: 0.000122 grad: 0.0664 (0.0711) loss: 0.8987 (0.8967) time: 0.1439 data: 0.0466 max mem: 8299 +Train: [14] [ 200/6250] eta: 0:18:43 lr: 0.000122 grad: 0.0599 (0.0686) loss: 0.8908 (0.8933) time: 0.1691 data: 0.0665 max mem: 8299 +Train: [14] [ 300/6250] eta: 0:17:11 lr: 0.000122 grad: 0.0611 (0.0675) loss: 0.8869 (0.8920) time: 0.1344 data: 0.0268 max mem: 8299 +Train: [14] [ 400/6250] eta: 0:16:07 lr: 0.000122 grad: 0.0563 (0.0659) loss: 0.8824 (0.8904) time: 0.1333 data: 0.0432 max mem: 8299 +Train: [14] [ 500/6250] eta: 0:15:37 lr: 0.000122 grad: 0.0607 (0.0651) loss: 0.8867 (0.8899) time: 0.1429 data: 0.0525 max mem: 8299 +Train: [14] [ 600/6250] eta: 0:15:09 lr: 0.000122 grad: 0.0592 (0.0645) loss: 0.8848 (0.8893) time: 0.1228 data: 0.0003 max mem: 8299 +Train: [14] [ 700/6250] eta: 0:14:45 lr: 0.000122 grad: 0.0591 (0.0644) loss: 0.8854 (0.8892) time: 0.1626 data: 0.0496 max mem: 8299 +Train: [14] [ 800/6250] eta: 0:14:33 lr: 0.000122 grad: 0.0578 (0.0638) loss: 0.8819 (0.8889) time: 0.1774 data: 0.0988 max mem: 8299 +Train: [14] [ 900/6250] eta: 0:14:13 lr: 0.000122 grad: 0.0581 (0.0639) loss: 0.8890 (0.8888) time: 0.1744 data: 0.0794 max mem: 8299 +Train: [14] [1000/6250] eta: 0:13:57 lr: 0.000122 grad: 0.0569 (0.0634) loss: 0.8941 (0.8889) time: 0.1741 data: 0.0808 max mem: 8299 +Train: [14] [1100/6250] eta: 0:13:42 lr: 0.000122 grad: 0.0560 (0.0632) loss: 0.8873 (0.8888) time: 0.1942 data: 0.1161 max mem: 8299 +Train: [14] [1200/6250] eta: 0:13:17 lr: 0.000122 grad: 0.0581 (0.0629) loss: 0.8942 (0.8888) time: 0.1408 data: 0.0581 max mem: 8299 +Train: [14] [1300/6250] eta: 0:12:58 lr: 0.000122 grad: 0.0583 (0.0635) loss: 0.8873 (0.8887) time: 0.1382 data: 0.0558 max mem: 8299 +Train: [14] [1400/6250] eta: 0:12:39 lr: 0.000122 grad: 0.0576 (0.0633) loss: 0.8863 (0.8886) time: 0.1186 data: 0.0285 max mem: 8299 +Train: [14] [1500/6250] eta: 0:12:22 lr: 0.000122 grad: 0.0589 (0.0631) loss: 0.8861 (0.8885) time: 0.1369 data: 0.0481 max mem: 8299 +Train: [14] [1600/6250] eta: 0:12:04 lr: 0.000122 grad: 0.0588 (0.0630) loss: 0.8890 (0.8884) time: 0.1342 data: 0.0457 max mem: 8299 +Train: [14] [1700/6250] eta: 0:11:49 lr: 0.000122 grad: 0.0612 (0.0629) loss: 0.8873 (0.8883) time: 0.1293 data: 0.0533 max mem: 8299 +Train: [14] [1800/6250] eta: 0:11:33 lr: 0.000122 grad: 0.0621 (0.0630) loss: 0.8857 (0.8881) time: 0.1755 data: 0.0990 max mem: 8299 +Train: [14] [1900/6250] eta: 0:11:17 lr: 0.000122 grad: 0.0612 (0.0629) loss: 0.8856 (0.8881) time: 0.1577 data: 0.0731 max mem: 8299 +Train: [14] [2000/6250] eta: 0:10:58 lr: 0.000122 grad: 0.0592 (0.0629) loss: 0.8826 (0.8879) time: 0.1310 data: 0.0422 max mem: 8299 +Train: [14] [2100/6250] eta: 0:10:43 lr: 0.000122 grad: 0.0574 (0.0630) loss: 0.8879 (0.8878) time: 0.1182 data: 0.0265 max mem: 8299 +Train: [14] [2200/6250] eta: 0:10:26 lr: 0.000122 grad: 0.0617 (0.0630) loss: 0.8886 (0.8877) time: 0.1192 data: 0.0318 max mem: 8299 +Train: [14] [2300/6250] eta: 0:10:11 lr: 0.000122 grad: 0.0593 (0.0630) loss: 0.8879 (0.8877) time: 0.1472 data: 0.0550 max mem: 8299 +Train: [14] [2400/6250] eta: 0:09:55 lr: 0.000122 grad: 0.0628 (0.0633) loss: 0.8870 (0.8877) time: 0.1628 data: 0.0836 max mem: 8299 +Train: [14] [2500/6250] eta: 0:09:39 lr: 0.000122 grad: 0.0716 (0.0633) loss: 0.8840 (0.8876) time: 0.1548 data: 0.0691 max mem: 8299 +Train: [14] [2600/6250] eta: 0:09:23 lr: 0.000122 grad: 0.0606 (0.0633) loss: 0.8884 (0.8875) time: 0.1551 data: 0.0774 max mem: 8299 +Train: [14] [2700/6250] eta: 0:09:07 lr: 0.000122 grad: 0.0611 (0.0634) loss: 0.8874 (0.8875) time: 0.1473 data: 0.0639 max mem: 8299 +Train: [14] [2800/6250] eta: 0:08:52 lr: 0.000122 grad: 0.0670 (0.0635) loss: 0.8924 (0.8875) time: 0.1318 data: 0.0525 max mem: 8299 +Train: [14] [2900/6250] eta: 0:08:37 lr: 0.000122 grad: 0.0600 (0.0637) loss: 0.8806 (0.8875) time: 0.1663 data: 0.0808 max mem: 8299 +Train: [14] [3000/6250] eta: 0:08:21 lr: 0.000122 grad: 0.0602 (0.0637) loss: 0.8881 (0.8875) time: 0.1465 data: 0.0572 max mem: 8299 +Train: [14] [3100/6250] eta: 0:08:08 lr: 0.000122 grad: 0.0630 (0.0637) loss: 0.8913 (0.8876) time: 0.2035 data: 0.1209 max mem: 8299 +Train: [14] [3200/6250] eta: 0:07:51 lr: 0.000122 grad: 0.0582 (0.0636) loss: 0.8885 (0.8877) time: 0.1563 data: 0.0849 max mem: 8299 +Train: [14] [3300/6250] eta: 0:07:36 lr: 0.000122 grad: 0.0582 (0.0635) loss: 0.8911 (0.8877) time: 0.1637 data: 0.0851 max mem: 8299 +Train: [14] [3400/6250] eta: 0:07:21 lr: 0.000122 grad: 0.0627 (0.0635) loss: 0.8912 (0.8878) time: 0.1694 data: 0.0849 max mem: 8299 +Train: [14] [3500/6250] eta: 0:07:05 lr: 0.000122 grad: 0.0564 (0.0634) loss: 0.8926 (0.8878) time: 0.1804 data: 0.1028 max mem: 8299 +Train: [14] [3600/6250] eta: 0:06:50 lr: 0.000122 grad: 0.0561 (0.0634) loss: 0.8911 (0.8879) time: 0.1571 data: 0.0838 max mem: 8299 +Train: [14] [3700/6250] eta: 0:06:36 lr: 0.000122 grad: 0.0633 (0.0634) loss: 0.8841 (0.8879) time: 0.1894 data: 0.1004 max mem: 8299 +Train: [14] [3800/6250] eta: 0:06:21 lr: 0.000122 grad: 0.0612 (0.0634) loss: 0.8861 (0.8879) time: 0.1671 data: 0.0894 max mem: 8299 +Train: [14] [3900/6250] eta: 0:06:06 lr: 0.000122 grad: 0.0573 (0.0634) loss: 0.8878 (0.8879) time: 0.1530 data: 0.0751 max mem: 8299 +Train: [14] [4000/6250] eta: 0:05:51 lr: 0.000122 grad: 0.0583 (0.0633) loss: 0.8881 (0.8879) time: 0.1490 data: 0.0648 max mem: 8299 +Train: [14] [4100/6250] eta: 0:05:35 lr: 0.000122 grad: 0.0611 (0.0633) loss: 0.8818 (0.8878) time: 0.1587 data: 0.0883 max mem: 8299 +Train: [14] [4200/6250] eta: 0:05:20 lr: 0.000122 grad: 0.0611 (0.0632) loss: 0.8848 (0.8877) time: 0.1485 data: 0.0647 max mem: 8299 +Train: [14] [4300/6250] eta: 0:05:04 lr: 0.000122 grad: 0.0608 (0.0632) loss: 0.8842 (0.8877) time: 0.1367 data: 0.0557 max mem: 8299 +Train: [14] [4400/6250] eta: 0:04:49 lr: 0.000122 grad: 0.0572 (0.0632) loss: 0.8828 (0.8877) time: 0.1851 data: 0.0956 max mem: 8299 +Train: [14] [4500/6250] eta: 0:04:33 lr: 0.000122 grad: 0.0615 (0.0632) loss: 0.8818 (0.8876) time: 0.1611 data: 0.0719 max mem: 8299 +Train: [14] [4600/6250] eta: 0:04:17 lr: 0.000122 grad: 0.0560 (0.0631) loss: 0.8886 (0.8876) time: 0.2084 data: 0.1254 max mem: 8299 +Train: [14] [4700/6250] eta: 0:04:02 lr: 0.000122 grad: 0.0627 (0.0632) loss: 0.8857 (0.8876) time: 0.1467 data: 0.0701 max mem: 8299 +Train: [14] [4800/6250] eta: 0:03:46 lr: 0.000122 grad: 0.0592 (0.0631) loss: 0.8874 (0.8875) time: 0.1737 data: 0.1059 max mem: 8299 +Train: [14] [4900/6250] eta: 0:03:30 lr: 0.000122 grad: 0.0575 (0.0631) loss: 0.8869 (0.8875) time: 0.1616 data: 0.0868 max mem: 8299 +Train: [14] [5000/6250] eta: 0:03:15 lr: 0.000122 grad: 0.0600 (0.0631) loss: 0.8847 (0.8874) time: 0.1687 data: 0.0783 max mem: 8299 +Train: [14] [5100/6250] eta: 0:02:59 lr: 0.000122 grad: 0.0593 (0.0631) loss: 0.8846 (0.8874) time: 0.1623 data: 0.0795 max mem: 8299 +Train: [14] [5200/6250] eta: 0:02:43 lr: 0.000122 grad: 0.0593 (0.0632) loss: 0.8830 (0.8873) time: 0.1533 data: 0.0615 max mem: 8299 +Train: [14] [5300/6250] eta: 0:02:27 lr: 0.000122 grad: 0.0619 (0.0632) loss: 0.8849 (0.8872) time: 0.1476 data: 0.0600 max mem: 8299 +Train: [14] [5400/6250] eta: 0:02:12 lr: 0.000122 grad: 0.0627 (0.0632) loss: 0.8803 (0.8872) time: 0.1308 data: 0.0541 max mem: 8299 +Train: [14] [5500/6250] eta: 0:01:56 lr: 0.000122 grad: 0.0621 (0.0632) loss: 0.8861 (0.8871) time: 0.1637 data: 0.0686 max mem: 8299 +Train: [14] [5600/6250] eta: 0:01:41 lr: 0.000122 grad: 0.0618 (0.0632) loss: 0.8819 (0.8870) time: 0.1617 data: 0.0854 max mem: 8299 +Train: [14] [5700/6250] eta: 0:01:25 lr: 0.000122 grad: 0.0659 (0.0632) loss: 0.8825 (0.8870) time: 0.1738 data: 0.0901 max mem: 8299 +Train: [14] [5800/6250] eta: 0:01:10 lr: 0.000122 grad: 0.0567 (0.0632) loss: 0.8864 (0.8870) time: 0.1228 data: 0.0309 max mem: 8299 +Train: [14] [5900/6250] eta: 0:00:54 lr: 0.000122 grad: 0.0606 (0.0632) loss: 0.8872 (0.8870) time: 0.1482 data: 0.0546 max mem: 8299 +Train: [14] [6000/6250] eta: 0:00:39 lr: 0.000122 grad: 0.0569 (0.0632) loss: 0.8913 (0.8869) time: 0.2363 data: 0.1629 max mem: 8299 +Train: [14] [6100/6250] eta: 0:00:23 lr: 0.000122 grad: 0.0601 (0.0633) loss: 0.8851 (0.8869) time: 0.1525 data: 0.0713 max mem: 8299 +Train: [14] [6200/6250] eta: 0:00:07 lr: 0.000122 grad: 0.0650 (0.0633) loss: 0.8878 (0.8869) time: 0.1506 data: 0.0751 max mem: 8299 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0583 (0.0633) loss: 0.8868 (0.8869) time: 0.1315 data: 0.0550 max mem: 8299 +Train: [14] Total time: 0:16:22 (0.1572 s / it) +Averaged stats: lr: 0.000122 grad: 0.0583 (0.0633) loss: 0.8868 (0.8869) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:06:29 loss: 0.9031 (0.9031) time: 6.2750 data: 6.2435 max mem: 8299 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8921 (0.8936) time: 0.1523 data: 0.1255 max mem: 8299 +Eval (hcp-train-subset): [14] Total time: 0:00:14 (0.2294 s / it) +Averaged stats (hcp-train-subset): loss: 0.8921 (0.8936) +Making plots (hcp-train-subset): example=46 +Eval (hcp-val): [14] [ 0/62] eta: 0:04:21 loss: 0.8842 (0.8842) time: 4.2221 data: 4.1288 max mem: 8299 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8880 (0.8891) time: 0.1502 data: 0.1239 max mem: 8299 +Eval (hcp-val): [14] Total time: 0:00:13 (0.2213 s / it) +Averaged stats (hcp-val): loss: 0.8880 (0.8891) +Making plots (hcp-val): example=55 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 9:00:58 lr: 0.000122 grad: 0.0428 (0.0428) loss: 0.9166 (0.9166) time: 5.1933 data: 4.9273 max mem: 8299 +Train: [15] [ 100/6250] eta: 0:21:15 lr: 0.000122 grad: 0.0611 (0.0772) loss: 0.8954 (0.8881) time: 0.1673 data: 0.0697 max mem: 8299 +Train: [15] [ 200/6250] eta: 0:18:04 lr: 0.000122 grad: 0.0628 (0.0748) loss: 0.8899 (0.8887) time: 0.1563 data: 0.0703 max mem: 8299 +Train: [15] [ 300/6250] eta: 0:16:43 lr: 0.000122 grad: 0.0573 (0.0721) loss: 0.8882 (0.8885) time: 0.1466 data: 0.0422 max mem: 8299 +Train: [15] [ 400/6250] eta: 0:15:50 lr: 0.000122 grad: 0.0639 (0.0706) loss: 0.8875 (0.8876) time: 0.1524 data: 0.0606 max mem: 8299 +Train: [15] [ 500/6250] eta: 0:15:11 lr: 0.000122 grad: 0.0606 (0.0693) loss: 0.8859 (0.8873) time: 0.1494 data: 0.0570 max mem: 8299 +Train: [15] [ 600/6250] eta: 0:14:40 lr: 0.000122 grad: 0.0595 (0.0688) loss: 0.8820 (0.8865) time: 0.1490 data: 0.0460 max mem: 8299 +Train: [15] [ 700/6250] eta: 0:14:19 lr: 0.000122 grad: 0.0598 (0.0679) loss: 0.8862 (0.8865) time: 0.1591 data: 0.0600 max mem: 8299 +Train: [15] [ 800/6250] eta: 0:14:08 lr: 0.000122 grad: 0.0596 (0.0676) loss: 0.8855 (0.8861) time: 0.1036 data: 0.0129 max mem: 8299 +Train: [15] [ 900/6250] eta: 0:14:04 lr: 0.000122 grad: 0.0625 (0.0670) loss: 0.8817 (0.8857) time: 0.1717 data: 0.0805 max mem: 8299 +Train: [15] [1000/6250] eta: 0:13:41 lr: 0.000122 grad: 0.0601 (0.0667) loss: 0.8842 (0.8856) time: 0.1332 data: 0.0471 max mem: 8299 +Train: [15] [1100/6250] eta: 0:13:22 lr: 0.000121 grad: 0.0636 (0.0660) loss: 0.8839 (0.8856) time: 0.1098 data: 0.0160 max mem: 8299 +Train: [15] [1200/6250] eta: 0:13:07 lr: 0.000121 grad: 0.0598 (0.0657) loss: 0.8855 (0.8855) time: 0.1729 data: 0.0837 max mem: 8299 +Train: [15] [1300/6250] eta: 0:12:49 lr: 0.000121 grad: 0.0614 (0.0655) loss: 0.8892 (0.8854) time: 0.1421 data: 0.0598 max mem: 8299 +Train: [15] [1400/6250] eta: 0:12:31 lr: 0.000121 grad: 0.0616 (0.0653) loss: 0.8842 (0.8852) time: 0.1480 data: 0.0680 max mem: 8299 +Train: [15] [1500/6250] eta: 0:12:19 lr: 0.000121 grad: 0.0582 (0.0650) loss: 0.8870 (0.8851) time: 0.2211 data: 0.1359 max mem: 8299 +Train: [15] [1600/6250] eta: 0:12:03 lr: 0.000121 grad: 0.0587 (0.0646) loss: 0.8825 (0.8851) time: 0.1456 data: 0.0608 max mem: 8299 +Train: [15] [1700/6250] eta: 0:11:45 lr: 0.000121 grad: 0.0558 (0.0643) loss: 0.8852 (0.8851) time: 0.1413 data: 0.0614 max mem: 8299 +Train: [15] [1800/6250] eta: 0:11:31 lr: 0.000121 grad: 0.0616 (0.0641) loss: 0.8849 (0.8850) time: 0.1740 data: 0.0879 max mem: 8299 +Train: [15] [1900/6250] eta: 0:11:14 lr: 0.000121 grad: 0.0576 (0.0639) loss: 0.8826 (0.8849) time: 0.1355 data: 0.0670 max mem: 8299 +Train: [15] [2000/6250] eta: 0:10:58 lr: 0.000121 grad: 0.0615 (0.0638) loss: 0.8794 (0.8848) time: 0.1738 data: 0.0852 max mem: 8299 +Train: [15] [2100/6250] eta: 0:10:39 lr: 0.000121 grad: 0.0603 (0.0638) loss: 0.8824 (0.8847) time: 0.1448 data: 0.0544 max mem: 8299 +Train: [15] [2200/6250] eta: 0:10:21 lr: 0.000121 grad: 0.0628 (0.0638) loss: 0.8847 (0.8846) time: 0.1324 data: 0.0419 max mem: 8299 +Train: [15] [2300/6250] eta: 0:10:05 lr: 0.000121 grad: 0.0566 (0.0638) loss: 0.8852 (0.8845) time: 0.1518 data: 0.0711 max mem: 8299 +Train: [15] [2400/6250] eta: 0:09:50 lr: 0.000121 grad: 0.0608 (0.0637) loss: 0.8830 (0.8845) time: 0.1188 data: 0.0234 max mem: 8299 +Train: [15] [2500/6250] eta: 0:09:34 lr: 0.000121 grad: 0.0621 (0.0637) loss: 0.8824 (0.8845) time: 0.1494 data: 0.0461 max mem: 8299 +Train: [15] [2600/6250] eta: 0:09:19 lr: 0.000121 grad: 0.0615 (0.0636) loss: 0.8831 (0.8843) time: 0.1485 data: 0.0655 max mem: 8299 +Train: [15] [2700/6250] eta: 0:09:03 lr: 0.000121 grad: 0.0533 (0.0636) loss: 0.8884 (0.8844) time: 0.1618 data: 0.0864 max mem: 8299 +Train: [15] [2800/6250] eta: 0:08:47 lr: 0.000121 grad: 0.0633 (0.0635) loss: 0.8889 (0.8844) time: 0.1437 data: 0.0672 max mem: 8299 +Train: [15] [2900/6250] eta: 0:08:32 lr: 0.000121 grad: 0.0617 (0.0635) loss: 0.8854 (0.8844) time: 0.1525 data: 0.0505 max mem: 8299 +Train: [15] [3000/6250] eta: 0:08:17 lr: 0.000121 grad: 0.0594 (0.0635) loss: 0.8838 (0.8844) time: 0.1934 data: 0.1117 max mem: 8299 +Train: [15] [3100/6250] eta: 0:08:02 lr: 0.000121 grad: 0.0610 (0.0635) loss: 0.8849 (0.8844) time: 0.1755 data: 0.0904 max mem: 8299 +Train: [15] [3200/6250] eta: 0:07:46 lr: 0.000121 grad: 0.0613 (0.0634) loss: 0.8837 (0.8844) time: 0.1997 data: 0.1150 max mem: 8299 +Train: [15] [3300/6250] eta: 0:07:30 lr: 0.000121 grad: 0.0558 (0.0634) loss: 0.8886 (0.8844) time: 0.1851 data: 0.0980 max mem: 8299 +Train: [15] [3400/6250] eta: 0:07:14 lr: 0.000121 grad: 0.0633 (0.0634) loss: 0.8808 (0.8844) time: 0.1449 data: 0.0608 max mem: 8299 +Train: [15] [3500/6250] eta: 0:06:58 lr: 0.000121 grad: 0.0601 (0.0633) loss: 0.8805 (0.8844) time: 0.1284 data: 0.0438 max mem: 8299 +Train: [15] [3600/6250] eta: 0:06:43 lr: 0.000121 grad: 0.0603 (0.0632) loss: 0.8841 (0.8844) time: 0.1707 data: 0.0786 max mem: 8299 +Train: [15] [3700/6250] eta: 0:06:28 lr: 0.000121 grad: 0.0573 (0.0631) loss: 0.8887 (0.8844) time: 0.1701 data: 0.0844 max mem: 8299 +Train: [15] [3800/6250] eta: 0:06:12 lr: 0.000121 grad: 0.0588 (0.0631) loss: 0.8830 (0.8844) time: 0.1474 data: 0.0768 max mem: 8299 +Train: [15] [3900/6250] eta: 0:05:57 lr: 0.000121 grad: 0.0605 (0.0631) loss: 0.8820 (0.8844) time: 0.1594 data: 0.0775 max mem: 8299 +Train: [15] [4000/6250] eta: 0:05:42 lr: 0.000121 grad: 0.0602 (0.0631) loss: 0.8864 (0.8845) time: 0.1486 data: 0.0648 max mem: 8299 +Train: [15] [4100/6250] eta: 0:05:27 lr: 0.000121 grad: 0.0580 (0.0630) loss: 0.8847 (0.8845) time: 0.1428 data: 0.0641 max mem: 8299 +Train: [15] [4200/6250] eta: 0:05:12 lr: 0.000121 grad: 0.0595 (0.0630) loss: 0.8871 (0.8845) time: 0.1438 data: 0.0534 max mem: 8299 +Train: [15] [4300/6250] eta: 0:04:57 lr: 0.000121 grad: 0.0638 (0.0630) loss: 0.8836 (0.8846) time: 0.1756 data: 0.0966 max mem: 8299 +Train: [15] [4400/6250] eta: 0:04:42 lr: 0.000121 grad: 0.0590 (0.0630) loss: 0.8891 (0.8846) time: 0.1678 data: 0.0822 max mem: 8299 +Train: [15] [4500/6250] eta: 0:04:27 lr: 0.000121 grad: 0.0622 (0.0630) loss: 0.8871 (0.8846) time: 0.1841 data: 0.1064 max mem: 8299 +Train: [15] [4600/6250] eta: 0:04:11 lr: 0.000121 grad: 0.0568 (0.0630) loss: 0.8867 (0.8846) time: 0.1469 data: 0.0656 max mem: 8299 +Train: [15] [4700/6250] eta: 0:03:56 lr: 0.000121 grad: 0.0613 (0.0630) loss: 0.8896 (0.8846) time: 0.1477 data: 0.0578 max mem: 8299 +Train: [15] [4800/6250] eta: 0:03:41 lr: 0.000121 grad: 0.0639 (0.0630) loss: 0.8863 (0.8847) time: 0.1693 data: 0.0879 max mem: 8299 +Train: [15] [4900/6250] eta: 0:03:26 lr: 0.000121 grad: 0.0610 (0.0630) loss: 0.8861 (0.8847) time: 0.1646 data: 0.0952 max mem: 8299 +Train: [15] [5000/6250] eta: 0:03:11 lr: 0.000121 grad: 0.0662 (0.0631) loss: 0.8843 (0.8847) time: 0.1706 data: 0.0915 max mem: 8299 +Train: [15] [5100/6250] eta: 0:02:55 lr: 0.000121 grad: 0.0602 (0.0631) loss: 0.8779 (0.8847) time: 0.1243 data: 0.0457 max mem: 8299 +Train: [15] [5200/6250] eta: 0:02:40 lr: 0.000121 grad: 0.0578 (0.0631) loss: 0.8833 (0.8847) time: 0.1389 data: 0.0597 max mem: 8299 +Train: [15] [5300/6250] eta: 0:02:25 lr: 0.000121 grad: 0.0613 (0.0631) loss: 0.8875 (0.8847) time: 0.1351 data: 0.0648 max mem: 8299 +Train: [15] [5400/6250] eta: 0:02:09 lr: 0.000121 grad: 0.0605 (0.0632) loss: 0.8829 (0.8847) time: 0.1691 data: 0.0906 max mem: 8299 +Train: [15] [5500/6250] eta: 0:01:54 lr: 0.000121 grad: 0.0674 (0.0632) loss: 0.8795 (0.8847) time: 0.0999 data: 0.0002 max mem: 8299 +Train: [15] [5600/6250] eta: 0:01:39 lr: 0.000121 grad: 0.0620 (0.0632) loss: 0.8849 (0.8847) time: 0.1563 data: 0.0730 max mem: 8299 +Train: [15] [5700/6250] eta: 0:01:24 lr: 0.000121 grad: 0.0623 (0.0632) loss: 0.8818 (0.8846) time: 0.1501 data: 0.0635 max mem: 8299 +Train: [15] [5800/6250] eta: 0:01:08 lr: 0.000121 grad: 0.0621 (0.0633) loss: 0.8834 (0.8846) time: 0.1220 data: 0.0334 max mem: 8299 +Train: [15] [5900/6250] eta: 0:00:53 lr: 0.000121 grad: 0.0715 (0.0633) loss: 0.8766 (0.8846) time: 0.1343 data: 0.0569 max mem: 8299 +Train: [15] [6000/6250] eta: 0:00:38 lr: 0.000121 grad: 0.0628 (0.0634) loss: 0.8880 (0.8846) time: 0.1533 data: 0.0745 max mem: 8299 +Train: [15] [6100/6250] eta: 0:00:22 lr: 0.000121 grad: 0.0582 (0.0634) loss: 0.8846 (0.8846) time: 0.1582 data: 0.0852 max mem: 8299 +Train: [15] [6200/6250] eta: 0:00:07 lr: 0.000121 grad: 0.0589 (0.0634) loss: 0.8838 (0.8845) time: 0.1352 data: 0.0704 max mem: 8299 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0568 (0.0634) loss: 0.8883 (0.8845) time: 0.1599 data: 0.0823 max mem: 8299 +Train: [15] Total time: 0:16:03 (0.1541 s / it) +Averaged stats: lr: 0.000121 grad: 0.0568 (0.0634) loss: 0.8883 (0.8845) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:05:33 loss: 0.9028 (0.9028) time: 5.3760 data: 5.3433 max mem: 8299 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8942 (0.8935) time: 0.1329 data: 0.1085 max mem: 8299 +Eval (hcp-train-subset): [15] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-train-subset): loss: 0.8942 (0.8935) +Eval (hcp-val): [15] [ 0/62] eta: 0:05:30 loss: 0.8851 (0.8851) time: 5.3250 data: 5.2937 max mem: 8299 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8903 (0.8898) time: 0.1295 data: 0.1034 max mem: 8299 +Eval (hcp-val): [15] Total time: 0:00:13 (0.2209 s / it) +Averaged stats (hcp-val): loss: 0.8903 (0.8898) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 7:00:09 lr: 0.000121 grad: 0.0579 (0.0579) loss: 0.9223 (0.9223) time: 4.0334 data: 3.7714 max mem: 8299 +Train: [16] [ 100/6250] eta: 0:21:43 lr: 0.000121 grad: 0.0672 (0.0742) loss: 0.8774 (0.8861) time: 0.1707 data: 0.0720 max mem: 8299 +Train: [16] [ 200/6250] eta: 0:18:51 lr: 0.000121 grad: 0.0642 (0.0725) loss: 0.8829 (0.8820) time: 0.1449 data: 0.0578 max mem: 8299 +Train: [16] [ 300/6250] eta: 0:17:34 lr: 0.000121 grad: 0.0567 (0.0704) loss: 0.8852 (0.8810) time: 0.1331 data: 0.0456 max mem: 8299 +Train: [16] [ 400/6250] eta: 0:16:27 lr: 0.000121 grad: 0.0564 (0.0688) loss: 0.8822 (0.8803) time: 0.1709 data: 0.0716 max mem: 8299 +Train: [16] [ 500/6250] eta: 0:15:57 lr: 0.000121 grad: 0.0582 (0.0671) loss: 0.8880 (0.8807) time: 0.1672 data: 0.0648 max mem: 8299 +Train: [16] [ 600/6250] eta: 0:15:22 lr: 0.000121 grad: 0.0632 (0.0663) loss: 0.8806 (0.8810) time: 0.1533 data: 0.0677 max mem: 8299 +Train: [16] [ 700/6250] eta: 0:14:49 lr: 0.000121 grad: 0.0589 (0.0655) loss: 0.8871 (0.8812) time: 0.1479 data: 0.0577 max mem: 8299 +Train: [16] [ 800/6250] eta: 0:14:29 lr: 0.000121 grad: 0.0601 (0.0650) loss: 0.8836 (0.8814) time: 0.1319 data: 0.0494 max mem: 8299 +Train: [16] [ 900/6250] eta: 0:14:21 lr: 0.000121 grad: 0.0558 (0.0646) loss: 0.8849 (0.8818) time: 0.1242 data: 0.0476 max mem: 8299 +Train: [16] [1000/6250] eta: 0:14:02 lr: 0.000121 grad: 0.0577 (0.0643) loss: 0.8854 (0.8824) time: 0.1556 data: 0.0672 max mem: 8299 +Train: [16] [1100/6250] eta: 0:13:39 lr: 0.000121 grad: 0.0599 (0.0641) loss: 0.8850 (0.8826) time: 0.1419 data: 0.0485 max mem: 8299 +Train: [16] [1200/6250] eta: 0:13:22 lr: 0.000121 grad: 0.0613 (0.0640) loss: 0.8851 (0.8827) time: 0.1568 data: 0.0744 max mem: 8299 +Train: [16] [1300/6250] eta: 0:13:07 lr: 0.000121 grad: 0.0604 (0.0639) loss: 0.8857 (0.8828) time: 0.1360 data: 0.0544 max mem: 8299 +Train: [16] [1400/6250] eta: 0:12:50 lr: 0.000121 grad: 0.0567 (0.0638) loss: 0.8837 (0.8829) time: 0.1560 data: 0.0843 max mem: 8299 +Train: [16] [1500/6250] eta: 0:12:36 lr: 0.000121 grad: 0.0646 (0.0638) loss: 0.8829 (0.8828) time: 0.1935 data: 0.1052 max mem: 8299 +Train: [16] [1600/6250] eta: 0:12:22 lr: 0.000121 grad: 0.0663 (0.0637) loss: 0.8809 (0.8828) time: 0.2161 data: 0.1368 max mem: 8299 +Train: [16] [1700/6250] eta: 0:12:04 lr: 0.000121 grad: 0.0605 (0.0638) loss: 0.8785 (0.8827) time: 0.1233 data: 0.0432 max mem: 8299 +Train: [16] [1800/6250] eta: 0:11:49 lr: 0.000121 grad: 0.0635 (0.0639) loss: 0.8805 (0.8825) time: 0.1859 data: 0.0989 max mem: 8299 +Train: [16] [1900/6250] eta: 0:11:34 lr: 0.000121 grad: 0.0611 (0.0639) loss: 0.8834 (0.8824) time: 0.1626 data: 0.0805 max mem: 8299 +Train: [16] [2000/6250] eta: 0:11:18 lr: 0.000121 grad: 0.0624 (0.0639) loss: 0.8764 (0.8822) time: 0.1698 data: 0.0854 max mem: 8299 +Train: [16] [2100/6250] eta: 0:11:02 lr: 0.000121 grad: 0.0627 (0.0639) loss: 0.8760 (0.8821) time: 0.1464 data: 0.0631 max mem: 8299 +Train: [16] [2200/6250] eta: 0:10:47 lr: 0.000121 grad: 0.0641 (0.0640) loss: 0.8805 (0.8820) time: 0.1899 data: 0.1129 max mem: 8299 +Train: [16] [2300/6250] eta: 0:10:31 lr: 0.000121 grad: 0.0631 (0.0640) loss: 0.8845 (0.8819) time: 0.1446 data: 0.0735 max mem: 8299 +Train: [16] [2400/6250] eta: 0:10:13 lr: 0.000121 grad: 0.0612 (0.0641) loss: 0.8830 (0.8818) time: 0.1366 data: 0.0484 max mem: 8299 +Train: [16] [2500/6250] eta: 0:09:57 lr: 0.000121 grad: 0.0629 (0.0641) loss: 0.8838 (0.8818) time: 0.1525 data: 0.0700 max mem: 8299 +Train: [16] [2600/6250] eta: 0:09:43 lr: 0.000121 grad: 0.0592 (0.0641) loss: 0.8833 (0.8819) time: 0.1830 data: 0.1034 max mem: 8299 +Train: [16] [2700/6250] eta: 0:09:28 lr: 0.000121 grad: 0.0609 (0.0641) loss: 0.8805 (0.8819) time: 0.1722 data: 0.0927 max mem: 8299 +Train: [16] [2800/6250] eta: 0:09:12 lr: 0.000121 grad: 0.0583 (0.0642) loss: 0.8817 (0.8818) time: 0.1814 data: 0.1029 max mem: 8299 +Train: [16] [2900/6250] eta: 0:08:56 lr: 0.000121 grad: 0.0671 (0.0643) loss: 0.8831 (0.8818) time: 0.1380 data: 0.0624 max mem: 8299 +Train: [16] [3000/6250] eta: 0:08:41 lr: 0.000121 grad: 0.0592 (0.0643) loss: 0.8818 (0.8818) time: 0.2018 data: 0.1174 max mem: 8299 +Train: [16] [3100/6250] eta: 0:08:25 lr: 0.000121 grad: 0.0580 (0.0643) loss: 0.8819 (0.8819) time: 0.1309 data: 0.0558 max mem: 8299 +Train: [16] [3200/6250] eta: 0:08:10 lr: 0.000121 grad: 0.0590 (0.0643) loss: 0.8854 (0.8819) time: 0.1771 data: 0.1131 max mem: 8299 +Train: [16] [3300/6250] eta: 0:07:55 lr: 0.000121 grad: 0.0595 (0.0645) loss: 0.8790 (0.8819) time: 0.1742 data: 0.0877 max mem: 8299 +Train: [16] [3400/6250] eta: 0:07:40 lr: 0.000121 grad: 0.0608 (0.0646) loss: 0.8828 (0.8819) time: 0.1735 data: 0.0955 max mem: 8299 +Train: [16] [3500/6250] eta: 0:07:23 lr: 0.000120 grad: 0.0653 (0.0646) loss: 0.8817 (0.8819) time: 0.1766 data: 0.0948 max mem: 8299 +Train: [16] [3600/6250] eta: 0:07:06 lr: 0.000120 grad: 0.0633 (0.0647) loss: 0.8831 (0.8820) time: 0.1201 data: 0.0443 max mem: 8299 +Train: [16] [3700/6250] eta: 0:06:49 lr: 0.000120 grad: 0.0622 (0.0648) loss: 0.8801 (0.8820) time: 0.1480 data: 0.0588 max mem: 8299 +Train: [16] [3800/6250] eta: 0:06:33 lr: 0.000120 grad: 0.0637 (0.0647) loss: 0.8819 (0.8820) time: 0.1496 data: 0.0694 max mem: 8299 +Train: [16] [3900/6250] eta: 0:06:15 lr: 0.000120 grad: 0.0633 (0.0648) loss: 0.8791 (0.8820) time: 0.1493 data: 0.0717 max mem: 8299 +Train: [16] [4000/6250] eta: 0:05:58 lr: 0.000120 grad: 0.0597 (0.0648) loss: 0.8851 (0.8820) time: 0.1384 data: 0.0521 max mem: 8299 +Train: [16] [4100/6250] eta: 0:05:42 lr: 0.000120 grad: 0.0610 (0.0648) loss: 0.8809 (0.8819) time: 0.1619 data: 0.0837 max mem: 8299 +Train: [16] [4200/6250] eta: 0:05:26 lr: 0.000120 grad: 0.0572 (0.0647) loss: 0.8816 (0.8820) time: 0.1550 data: 0.0695 max mem: 8299 +Train: [16] [4300/6250] eta: 0:05:10 lr: 0.000120 grad: 0.0607 (0.0647) loss: 0.8776 (0.8820) time: 0.1242 data: 0.0412 max mem: 8299 +Train: [16] [4400/6250] eta: 0:04:54 lr: 0.000120 grad: 0.0566 (0.0646) loss: 0.8864 (0.8820) time: 0.1784 data: 0.0941 max mem: 8299 +Train: [16] [4500/6250] eta: 0:04:38 lr: 0.000120 grad: 0.0612 (0.0646) loss: 0.8802 (0.8819) time: 0.1530 data: 0.0779 max mem: 8299 +Train: [16] [4600/6250] eta: 0:04:22 lr: 0.000120 grad: 0.0599 (0.0646) loss: 0.8825 (0.8819) time: 0.1501 data: 0.0709 max mem: 8299 +Train: [16] [4700/6250] eta: 0:04:06 lr: 0.000120 grad: 0.0659 (0.0646) loss: 0.8728 (0.8819) time: 0.1693 data: 0.0880 max mem: 8299 +Train: [16] [4800/6250] eta: 0:03:50 lr: 0.000120 grad: 0.0650 (0.0647) loss: 0.8773 (0.8819) time: 0.1673 data: 0.0806 max mem: 8299 +Train: [16] [4900/6250] eta: 0:03:34 lr: 0.000120 grad: 0.0639 (0.0647) loss: 0.8820 (0.8818) time: 0.1350 data: 0.0621 max mem: 8299 +Train: [16] [5000/6250] eta: 0:03:18 lr: 0.000120 grad: 0.0609 (0.0647) loss: 0.8813 (0.8819) time: 0.1650 data: 0.0729 max mem: 8299 +Train: [16] [5100/6250] eta: 0:03:02 lr: 0.000120 grad: 0.0632 (0.0647) loss: 0.8784 (0.8819) time: 0.1655 data: 0.0630 max mem: 8299 +Train: [16] [5200/6250] eta: 0:02:46 lr: 0.000120 grad: 0.0586 (0.0647) loss: 0.8864 (0.8819) time: 0.1736 data: 0.0911 max mem: 8299 +Train: [16] [5300/6250] eta: 0:02:30 lr: 0.000120 grad: 0.0616 (0.0647) loss: 0.8808 (0.8819) time: 0.1189 data: 0.0352 max mem: 8299 +Train: [16] [5400/6250] eta: 0:02:14 lr: 0.000120 grad: 0.0616 (0.0647) loss: 0.8835 (0.8820) time: 0.1456 data: 0.0650 max mem: 8299 +Train: [16] [5500/6250] eta: 0:01:58 lr: 0.000120 grad: 0.0621 (0.0647) loss: 0.8812 (0.8820) time: 0.1491 data: 0.0697 max mem: 8299 +Train: [16] [5600/6250] eta: 0:01:42 lr: 0.000120 grad: 0.0655 (0.0646) loss: 0.8795 (0.8820) time: 0.1493 data: 0.0596 max mem: 8299 +Train: [16] [5700/6250] eta: 0:01:26 lr: 0.000120 grad: 0.0596 (0.0646) loss: 0.8880 (0.8820) time: 0.1476 data: 0.0624 max mem: 8299 +Train: [16] [5800/6250] eta: 0:01:11 lr: 0.000120 grad: 0.0573 (0.0646) loss: 0.8816 (0.8821) time: 0.1474 data: 0.0745 max mem: 8299 +Train: [16] [5900/6250] eta: 0:00:55 lr: 0.000120 grad: 0.0589 (0.0645) loss: 0.8864 (0.8821) time: 0.1584 data: 0.0741 max mem: 8299 +Train: [16] [6000/6250] eta: 0:00:39 lr: 0.000120 grad: 0.0654 (0.0645) loss: 0.8806 (0.8821) time: 0.1183 data: 0.0326 max mem: 8299 +Train: [16] [6100/6250] eta: 0:00:23 lr: 0.000120 grad: 0.0578 (0.0645) loss: 0.8878 (0.8822) time: 0.1853 data: 0.0906 max mem: 8299 +Train: [16] [6200/6250] eta: 0:00:07 lr: 0.000120 grad: 0.0661 (0.0645) loss: 0.8798 (0.8821) time: 0.1522 data: 0.0681 max mem: 8299 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0595 (0.0645) loss: 0.8795 (0.8822) time: 0.1448 data: 0.0625 max mem: 8299 +Train: [16] Total time: 0:16:34 (0.1591 s / it) +Averaged stats: lr: 0.000120 grad: 0.0595 (0.0645) loss: 0.8795 (0.8822) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:04:49 loss: 0.9013 (0.9013) time: 4.6640 data: 4.6334 max mem: 8299 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8927 (0.8924) time: 0.1322 data: 0.1075 max mem: 8299 +Eval (hcp-train-subset): [16] Total time: 0:00:14 (0.2321 s / it) +Averaged stats (hcp-train-subset): loss: 0.8927 (0.8924) +Eval (hcp-val): [16] [ 0/62] eta: 0:04:14 loss: 0.8904 (0.8904) time: 4.1062 data: 4.0328 max mem: 8299 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8869 (0.8893) time: 0.1146 data: 0.0896 max mem: 8299 +Eval (hcp-val): [16] Total time: 0:00:13 (0.2239 s / it) +Averaged stats (hcp-val): loss: 0.8869 (0.8893) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 7:04:14 lr: 0.000120 grad: 0.0492 (0.0492) loss: 0.9238 (0.9238) time: 4.0727 data: 3.7368 max mem: 8299 +Train: [17] [ 100/6250] eta: 0:21:43 lr: 0.000120 grad: 0.0634 (0.0713) loss: 0.8872 (0.8858) time: 0.2066 data: 0.1095 max mem: 8299 +Train: [17] [ 200/6250] eta: 0:18:07 lr: 0.000120 grad: 0.0601 (0.0694) loss: 0.8883 (0.8856) time: 0.1632 data: 0.0753 max mem: 8299 +Train: [17] [ 300/6250] eta: 0:16:57 lr: 0.000120 grad: 0.0565 (0.0669) loss: 0.8882 (0.8855) time: 0.1342 data: 0.0438 max mem: 8299 +Train: [17] [ 400/6250] eta: 0:16:05 lr: 0.000120 grad: 0.0585 (0.0661) loss: 0.8823 (0.8846) time: 0.1359 data: 0.0418 max mem: 8299 +Train: [17] [ 500/6250] eta: 0:15:25 lr: 0.000120 grad: 0.0596 (0.0659) loss: 0.8813 (0.8840) time: 0.1269 data: 0.0435 max mem: 8299 +Train: [17] [ 600/6250] eta: 0:14:52 lr: 0.000120 grad: 0.0586 (0.0653) loss: 0.8805 (0.8838) time: 0.1290 data: 0.0397 max mem: 8299 +Train: [17] [ 700/6250] eta: 0:14:35 lr: 0.000120 grad: 0.0609 (0.0649) loss: 0.8871 (0.8839) time: 0.1703 data: 0.0804 max mem: 8299 +Train: [17] [ 800/6250] eta: 0:14:56 lr: 0.000120 grad: 0.0555 (0.0647) loss: 0.8865 (0.8840) time: 0.3107 data: 0.2389 max mem: 8299 +Train: [17] [ 900/6250] eta: 0:14:42 lr: 0.000120 grad: 0.0581 (0.0641) loss: 0.8814 (0.8841) time: 0.1903 data: 0.1098 max mem: 8299 +Train: [17] [1000/6250] eta: 0:14:37 lr: 0.000120 grad: 0.0584 (0.0638) loss: 0.8842 (0.8842) time: 0.1820 data: 0.1071 max mem: 8299 +Train: [17] [1100/6250] eta: 0:14:10 lr: 0.000120 grad: 0.0657 (0.0636) loss: 0.8806 (0.8840) time: 0.1572 data: 0.0675 max mem: 8299 +Train: [17] [1200/6250] eta: 0:13:56 lr: 0.000120 grad: 0.0608 (0.0636) loss: 0.8813 (0.8838) time: 0.1604 data: 0.0804 max mem: 8299 +Train: [17] [1300/6250] eta: 0:13:42 lr: 0.000120 grad: 0.0586 (0.0636) loss: 0.8816 (0.8837) time: 0.1413 data: 0.0498 max mem: 8299 +Train: [17] [1400/6250] eta: 0:13:22 lr: 0.000120 grad: 0.0611 (0.0636) loss: 0.8808 (0.8837) time: 0.1623 data: 0.0780 max mem: 8299 +Train: [17] [1500/6250] eta: 0:13:03 lr: 0.000120 grad: 0.0558 (0.0635) loss: 0.8829 (0.8836) time: 0.1511 data: 0.0672 max mem: 8299 +Train: [17] [1600/6250] eta: 0:12:44 lr: 0.000120 grad: 0.0575 (0.0633) loss: 0.8888 (0.8837) time: 0.1362 data: 0.0417 max mem: 8299 +Train: [17] [1700/6250] eta: 0:12:24 lr: 0.000120 grad: 0.0616 (0.0633) loss: 0.8813 (0.8836) time: 0.1452 data: 0.0562 max mem: 8299 +Train: [17] [1800/6250] eta: 0:12:06 lr: 0.000120 grad: 0.0613 (0.0633) loss: 0.8792 (0.8835) time: 0.2071 data: 0.1153 max mem: 8299 +Train: [17] [1900/6250] eta: 0:11:44 lr: 0.000120 grad: 0.0536 (0.0631) loss: 0.8809 (0.8836) time: 0.1738 data: 0.0891 max mem: 8299 +Train: [17] [2000/6250] eta: 0:11:23 lr: 0.000120 grad: 0.0587 (0.0630) loss: 0.8836 (0.8837) time: 0.1285 data: 0.0439 max mem: 8299 +Train: [17] [2100/6250] eta: 0:11:06 lr: 0.000120 grad: 0.0614 (0.0629) loss: 0.8875 (0.8837) time: 0.1865 data: 0.1067 max mem: 8299 +Train: [17] [2200/6250] eta: 0:10:49 lr: 0.000120 grad: 0.0585 (0.0628) loss: 0.8917 (0.8838) time: 0.1667 data: 0.0670 max mem: 8299 +Train: [17] [2300/6250] eta: 0:10:32 lr: 0.000120 grad: 0.0594 (0.0627) loss: 0.8848 (0.8839) time: 0.1202 data: 0.0444 max mem: 8299 +Train: [17] [2400/6250] eta: 0:10:13 lr: 0.000120 grad: 0.0543 (0.0626) loss: 0.8826 (0.8839) time: 0.1309 data: 0.0447 max mem: 8299 +Train: [17] [2500/6250] eta: 0:09:57 lr: 0.000120 grad: 0.0587 (0.0626) loss: 0.8873 (0.8839) time: 0.1438 data: 0.0650 max mem: 8299 +Train: [17] [2600/6250] eta: 0:09:39 lr: 0.000120 grad: 0.0573 (0.0625) loss: 0.8848 (0.8840) time: 0.1408 data: 0.0642 max mem: 8299 +Train: [17] [2700/6250] eta: 0:09:22 lr: 0.000120 grad: 0.0645 (0.0625) loss: 0.8851 (0.8840) time: 0.1459 data: 0.0545 max mem: 8299 +Train: [17] [2800/6250] eta: 0:09:04 lr: 0.000120 grad: 0.0605 (0.0624) loss: 0.8841 (0.8840) time: 0.1454 data: 0.0529 max mem: 8299 +Train: [17] [2900/6250] eta: 0:08:48 lr: 0.000120 grad: 0.0578 (0.0624) loss: 0.8830 (0.8840) time: 0.1300 data: 0.0477 max mem: 8299 +Train: [17] [3000/6250] eta: 0:08:32 lr: 0.000120 grad: 0.0586 (0.0623) loss: 0.8850 (0.8839) time: 0.1641 data: 0.0858 max mem: 8299 +Train: [17] [3100/6250] eta: 0:08:15 lr: 0.000120 grad: 0.0664 (0.0623) loss: 0.8851 (0.8839) time: 0.1262 data: 0.0424 max mem: 8299 +Train: [17] [3200/6250] eta: 0:07:59 lr: 0.000120 grad: 0.0588 (0.0623) loss: 0.8837 (0.8839) time: 0.1624 data: 0.0850 max mem: 8299 +Train: [17] [3300/6250] eta: 0:07:43 lr: 0.000120 grad: 0.0626 (0.0623) loss: 0.8874 (0.8839) time: 0.1430 data: 0.0552 max mem: 8299 +Train: [17] [3400/6250] eta: 0:07:28 lr: 0.000120 grad: 0.0610 (0.0625) loss: 0.8786 (0.8838) time: 0.1830 data: 0.0872 max mem: 8299 +Train: [17] [3500/6250] eta: 0:07:12 lr: 0.000120 grad: 0.0625 (0.0626) loss: 0.8847 (0.8838) time: 0.1850 data: 0.1155 max mem: 8299 +Train: [17] [3600/6250] eta: 0:06:56 lr: 0.000120 grad: 0.0609 (0.0626) loss: 0.8806 (0.8838) time: 0.1464 data: 0.0675 max mem: 8299 +Train: [17] [3700/6250] eta: 0:06:40 lr: 0.000120 grad: 0.0650 (0.0627) loss: 0.8803 (0.8838) time: 0.1680 data: 0.0831 max mem: 8299 +Train: [17] [3800/6250] eta: 0:06:24 lr: 0.000120 grad: 0.0641 (0.0628) loss: 0.8817 (0.8837) time: 0.1633 data: 0.0829 max mem: 8299 +Train: [17] [3900/6250] eta: 0:06:08 lr: 0.000120 grad: 0.0624 (0.0630) loss: 0.8830 (0.8837) time: 0.1503 data: 0.0695 max mem: 8299 +Train: [17] [4000/6250] eta: 0:05:53 lr: 0.000120 grad: 0.0640 (0.0630) loss: 0.8773 (0.8836) time: 0.1956 data: 0.1240 max mem: 8299 +Train: [17] [4100/6250] eta: 0:05:37 lr: 0.000120 grad: 0.0593 (0.0631) loss: 0.8805 (0.8836) time: 0.1752 data: 0.0968 max mem: 8299 +Train: [17] [4200/6250] eta: 0:05:22 lr: 0.000120 grad: 0.0658 (0.0632) loss: 0.8811 (0.8835) time: 0.1559 data: 0.0774 max mem: 8299 +Train: [17] [4300/6250] eta: 0:05:07 lr: 0.000120 grad: 0.0671 (0.0633) loss: 0.8766 (0.8834) time: 0.1555 data: 0.0831 max mem: 8299 +Train: [17] [4400/6250] eta: 0:04:51 lr: 0.000120 grad: 0.0601 (0.0634) loss: 0.8769 (0.8833) time: 0.1583 data: 0.0616 max mem: 8299 +Train: [17] [4500/6250] eta: 0:04:35 lr: 0.000120 grad: 0.0662 (0.0635) loss: 0.8774 (0.8833) time: 0.1744 data: 0.1022 max mem: 8299 +Train: [17] [4600/6250] eta: 0:04:20 lr: 0.000120 grad: 0.0628 (0.0635) loss: 0.8802 (0.8832) time: 0.1775 data: 0.0937 max mem: 8299 +Train: [17] [4700/6250] eta: 0:04:04 lr: 0.000120 grad: 0.0630 (0.0636) loss: 0.8766 (0.8831) time: 0.1657 data: 0.0714 max mem: 8299 +Train: [17] [4800/6250] eta: 0:03:49 lr: 0.000120 grad: 0.0623 (0.0636) loss: 0.8774 (0.8831) time: 0.1767 data: 0.0986 max mem: 8299 +Train: [17] [4900/6250] eta: 0:03:33 lr: 0.000119 grad: 0.0659 (0.0637) loss: 0.8815 (0.8830) time: 0.1560 data: 0.0667 max mem: 8299 +Train: [17] [5000/6250] eta: 0:03:17 lr: 0.000119 grad: 0.0696 (0.0637) loss: 0.8800 (0.8829) time: 0.1840 data: 0.1018 max mem: 8299 +Train: [17] [5100/6250] eta: 0:03:02 lr: 0.000119 grad: 0.0638 (0.0637) loss: 0.8802 (0.8829) time: 0.1713 data: 0.1001 max mem: 8299 +Train: [17] [5200/6250] eta: 0:02:46 lr: 0.000119 grad: 0.0590 (0.0637) loss: 0.8830 (0.8829) time: 0.1404 data: 0.0491 max mem: 8299 +Train: [17] [5300/6250] eta: 0:02:30 lr: 0.000119 grad: 0.0578 (0.0637) loss: 0.8781 (0.8828) time: 0.1518 data: 0.0676 max mem: 8299 +Train: [17] [5400/6250] eta: 0:02:15 lr: 0.000119 grad: 0.0635 (0.0638) loss: 0.8795 (0.8828) time: 0.1569 data: 0.0667 max mem: 8299 +Train: [17] [5500/6250] eta: 0:01:59 lr: 0.000119 grad: 0.0633 (0.0639) loss: 0.8760 (0.8827) time: 0.1625 data: 0.0910 max mem: 8299 +Train: [17] [5600/6250] eta: 0:01:43 lr: 0.000119 grad: 0.0689 (0.0640) loss: 0.8797 (0.8827) time: 0.1605 data: 0.0677 max mem: 8299 +Train: [17] [5700/6250] eta: 0:01:27 lr: 0.000119 grad: 0.0647 (0.0641) loss: 0.8809 (0.8826) time: 0.1507 data: 0.0662 max mem: 8299 +Train: [17] [5800/6250] eta: 0:01:11 lr: 0.000119 grad: 0.0679 (0.0641) loss: 0.8763 (0.8826) time: 0.1444 data: 0.0528 max mem: 8299 +Train: [17] [5900/6250] eta: 0:00:55 lr: 0.000119 grad: 0.0624 (0.0641) loss: 0.8826 (0.8825) time: 0.1368 data: 0.0567 max mem: 8299 +Train: [17] [6000/6250] eta: 0:00:39 lr: 0.000119 grad: 0.0618 (0.0642) loss: 0.8809 (0.8825) time: 0.1283 data: 0.0484 max mem: 8299 +Train: [17] [6100/6250] eta: 0:00:23 lr: 0.000119 grad: 0.0652 (0.0642) loss: 0.8803 (0.8825) time: 0.1609 data: 0.0684 max mem: 8299 +Train: [17] [6200/6250] eta: 0:00:07 lr: 0.000119 grad: 0.0653 (0.0642) loss: 0.8778 (0.8825) time: 0.1806 data: 0.0961 max mem: 8299 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0661 (0.0642) loss: 0.8782 (0.8824) time: 0.1372 data: 0.0542 max mem: 8299 +Train: [17] Total time: 0:16:34 (0.1592 s / it) +Averaged stats: lr: 0.000119 grad: 0.0661 (0.0642) loss: 0.8782 (0.8824) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:04:55 loss: 0.9056 (0.9056) time: 4.7685 data: 4.7180 max mem: 8299 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8929 (0.8929) time: 0.1275 data: 0.1025 max mem: 8299 +Eval (hcp-train-subset): [17] Total time: 0:00:14 (0.2281 s / it) +Averaged stats (hcp-train-subset): loss: 0.8929 (0.8929) +Eval (hcp-val): [17] [ 0/62] eta: 0:05:59 loss: 0.8842 (0.8842) time: 5.7933 data: 5.7623 max mem: 8299 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8884 (0.8901) time: 0.1333 data: 0.1086 max mem: 8299 +Eval (hcp-val): [17] Total time: 0:00:13 (0.2195 s / it) +Averaged stats (hcp-val): loss: 0.8884 (0.8901) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 8:44:08 lr: 0.000119 grad: 0.0663 (0.0663) loss: 0.8575 (0.8575) time: 5.0318 data: 4.8317 max mem: 8299 +Train: [18] [ 100/6250] eta: 0:21:20 lr: 0.000119 grad: 0.0620 (0.0715) loss: 0.8878 (0.8857) time: 0.1706 data: 0.0715 max mem: 8299 +Train: [18] [ 200/6250] eta: 0:18:04 lr: 0.000119 grad: 0.0601 (0.0684) loss: 0.8870 (0.8862) time: 0.1335 data: 0.0414 max mem: 8299 +Train: [18] [ 300/6250] eta: 0:16:50 lr: 0.000119 grad: 0.0568 (0.0664) loss: 0.8873 (0.8859) time: 0.1572 data: 0.0710 max mem: 8299 +Train: [18] [ 400/6250] eta: 0:15:53 lr: 0.000119 grad: 0.0606 (0.0653) loss: 0.8823 (0.8854) time: 0.1406 data: 0.0315 max mem: 8299 +Train: [18] [ 500/6250] eta: 0:15:12 lr: 0.000119 grad: 0.0578 (0.0642) loss: 0.8816 (0.8848) time: 0.1443 data: 0.0507 max mem: 8299 +Train: [18] [ 600/6250] eta: 0:14:46 lr: 0.000119 grad: 0.0602 (0.0638) loss: 0.8792 (0.8845) time: 0.1849 data: 0.0959 max mem: 8299 +Train: [18] [ 700/6250] eta: 0:14:55 lr: 0.000119 grad: 0.0592 (0.0631) loss: 0.8752 (0.8840) time: 0.2500 data: 0.1664 max mem: 8299 +Train: [18] [ 800/6250] eta: 0:14:42 lr: 0.000119 grad: 0.0617 (0.0632) loss: 0.8781 (0.8833) time: 0.1531 data: 0.0527 max mem: 8299 +Train: [18] [ 900/6250] eta: 0:14:24 lr: 0.000119 grad: 0.0628 (0.0632) loss: 0.8800 (0.8830) time: 0.1691 data: 0.0820 max mem: 8299 +Train: [18] [1000/6250] eta: 0:14:11 lr: 0.000119 grad: 0.0577 (0.0629) loss: 0.8829 (0.8829) time: 0.2031 data: 0.1290 max mem: 8299 +Train: [18] [1100/6250] eta: 0:13:49 lr: 0.000119 grad: 0.0590 (0.0628) loss: 0.8785 (0.8825) time: 0.1596 data: 0.0843 max mem: 8299 +Train: [18] [1200/6250] eta: 0:13:30 lr: 0.000119 grad: 0.0619 (0.0628) loss: 0.8783 (0.8822) time: 0.1478 data: 0.0582 max mem: 8299 +Train: [18] [1300/6250] eta: 0:13:13 lr: 0.000119 grad: 0.0616 (0.0629) loss: 0.8755 (0.8820) time: 0.1571 data: 0.0765 max mem: 8299 +Train: [18] [1400/6250] eta: 0:12:59 lr: 0.000119 grad: 0.0584 (0.0631) loss: 0.8790 (0.8819) time: 0.1444 data: 0.0338 max mem: 8299 +Train: [18] [1500/6250] eta: 0:12:39 lr: 0.000119 grad: 0.0631 (0.0634) loss: 0.8778 (0.8818) time: 0.1473 data: 0.0625 max mem: 8299 +Train: [18] [1600/6250] eta: 0:12:21 lr: 0.000119 grad: 0.0603 (0.0637) loss: 0.8762 (0.8816) time: 0.1386 data: 0.0642 max mem: 8299 +Train: [18] [1700/6250] eta: 0:12:00 lr: 0.000119 grad: 0.0607 (0.0638) loss: 0.8808 (0.8814) time: 0.1467 data: 0.0619 max mem: 8299 +Train: [18] [1800/6250] eta: 0:11:43 lr: 0.000119 grad: 0.0659 (0.0639) loss: 0.8816 (0.8814) time: 0.1584 data: 0.0747 max mem: 8299 +Train: [18] [1900/6250] eta: 0:11:27 lr: 0.000119 grad: 0.0686 (0.0642) loss: 0.8777 (0.8812) time: 0.1389 data: 0.0452 max mem: 8299 +Train: [18] [2000/6250] eta: 0:11:10 lr: 0.000119 grad: 0.0632 (0.0644) loss: 0.8826 (0.8810) time: 0.1402 data: 0.0502 max mem: 8299 +Train: [18] [2100/6250] eta: 0:10:54 lr: 0.000119 grad: 0.0630 (0.0646) loss: 0.8783 (0.8808) time: 0.1470 data: 0.0721 max mem: 8299 +Train: [18] [2200/6250] eta: 0:10:40 lr: 0.000119 grad: 0.0674 (0.0648) loss: 0.8809 (0.8807) time: 0.1918 data: 0.1074 max mem: 8299 +Train: [18] [2300/6250] eta: 0:10:24 lr: 0.000119 grad: 0.0585 (0.0649) loss: 0.8849 (0.8806) time: 0.1282 data: 0.0338 max mem: 8299 +Train: [18] [2400/6250] eta: 0:10:06 lr: 0.000119 grad: 0.0616 (0.0651) loss: 0.8795 (0.8805) time: 0.1354 data: 0.0591 max mem: 8299 +Train: [18] [2500/6250] eta: 0:09:51 lr: 0.000119 grad: 0.0719 (0.0653) loss: 0.8817 (0.8805) time: 0.1553 data: 0.0701 max mem: 8299 +Train: [18] [2600/6250] eta: 0:09:35 lr: 0.000119 grad: 0.0657 (0.0654) loss: 0.8797 (0.8805) time: 0.1511 data: 0.0639 max mem: 8299 +Train: [18] [2700/6250] eta: 0:09:18 lr: 0.000119 grad: 0.0708 (0.0657) loss: 0.8826 (0.8805) time: 0.1295 data: 0.0481 max mem: 8299 +Train: [18] [2800/6250] eta: 0:09:04 lr: 0.000119 grad: 0.0620 (0.0658) loss: 0.8791 (0.8805) time: 0.2072 data: 0.1134 max mem: 8299 +Train: [18] [2900/6250] eta: 0:08:46 lr: 0.000119 grad: 0.0624 (0.0657) loss: 0.8727 (0.8805) time: 0.1595 data: 0.0759 max mem: 8299 +Train: [18] [3000/6250] eta: 0:08:30 lr: 0.000119 grad: 0.0638 (0.0658) loss: 0.8756 (0.8804) time: 0.2052 data: 0.1246 max mem: 8299 +Train: [18] [3100/6250] eta: 0:08:13 lr: 0.000119 grad: 0.0671 (0.0658) loss: 0.8810 (0.8803) time: 0.1549 data: 0.0646 max mem: 8299 +Train: [18] [3200/6250] eta: 0:07:57 lr: 0.000119 grad: 0.0719 (0.0660) loss: 0.8827 (0.8803) time: 0.1632 data: 0.0807 max mem: 8299 +Train: [18] [3300/6250] eta: 0:07:41 lr: 0.000119 grad: 0.0612 (0.0660) loss: 0.8797 (0.8802) time: 0.1579 data: 0.0724 max mem: 8299 +Train: [18] [3400/6250] eta: 0:07:25 lr: 0.000119 grad: 0.0625 (0.0660) loss: 0.8813 (0.8803) time: 0.1409 data: 0.0608 max mem: 8299 +Train: [18] [3500/6250] eta: 0:07:09 lr: 0.000119 grad: 0.0619 (0.0660) loss: 0.8824 (0.8802) time: 0.1435 data: 0.0587 max mem: 8299 +Train: [18] [3600/6250] eta: 0:06:54 lr: 0.000119 grad: 0.0606 (0.0660) loss: 0.8805 (0.8803) time: 0.1679 data: 0.0869 max mem: 8299 +Train: [18] [3700/6250] eta: 0:06:38 lr: 0.000119 grad: 0.0684 (0.0660) loss: 0.8792 (0.8803) time: 0.1460 data: 0.0508 max mem: 8299 +Train: [18] [3800/6250] eta: 0:06:22 lr: 0.000119 grad: 0.0626 (0.0659) loss: 0.8822 (0.8803) time: 0.1729 data: 0.0866 max mem: 8299 +Train: [18] [3900/6250] eta: 0:06:07 lr: 0.000119 grad: 0.0622 (0.0659) loss: 0.8757 (0.8803) time: 0.1634 data: 0.0834 max mem: 8299 +Train: [18] [4000/6250] eta: 0:05:51 lr: 0.000119 grad: 0.0589 (0.0659) loss: 0.8818 (0.8803) time: 0.1738 data: 0.0786 max mem: 8299 +Train: [18] [4100/6250] eta: 0:05:35 lr: 0.000119 grad: 0.0626 (0.0660) loss: 0.8828 (0.8803) time: 0.1649 data: 0.0822 max mem: 8299 +Train: [18] [4200/6250] eta: 0:05:19 lr: 0.000119 grad: 0.0662 (0.0660) loss: 0.8778 (0.8803) time: 0.1818 data: 0.0936 max mem: 8299 +Train: [18] [4300/6250] eta: 0:05:04 lr: 0.000119 grad: 0.0599 (0.0659) loss: 0.8803 (0.8803) time: 0.1558 data: 0.0648 max mem: 8299 +Train: [18] [4400/6250] eta: 0:04:48 lr: 0.000119 grad: 0.0638 (0.0659) loss: 0.8814 (0.8803) time: 0.1632 data: 0.0806 max mem: 8299 +Train: [18] [4500/6250] eta: 0:04:32 lr: 0.000119 grad: 0.0602 (0.0659) loss: 0.8795 (0.8803) time: 0.1519 data: 0.0699 max mem: 8299 +Train: [18] [4600/6250] eta: 0:04:17 lr: 0.000119 grad: 0.0618 (0.0660) loss: 0.8767 (0.8802) time: 0.1381 data: 0.0452 max mem: 8299 +Train: [18] [4700/6250] eta: 0:04:01 lr: 0.000119 grad: 0.0631 (0.0660) loss: 0.8792 (0.8802) time: 0.1639 data: 0.0642 max mem: 8299 +Train: [18] [4800/6250] eta: 0:03:45 lr: 0.000119 grad: 0.0629 (0.0660) loss: 0.8786 (0.8802) time: 0.1426 data: 0.0670 max mem: 8299 +Train: [18] [4900/6250] eta: 0:03:29 lr: 0.000119 grad: 0.0639 (0.0660) loss: 0.8785 (0.8802) time: 0.1455 data: 0.0620 max mem: 8299 +Train: [18] [5000/6250] eta: 0:03:13 lr: 0.000119 grad: 0.0642 (0.0660) loss: 0.8804 (0.8802) time: 0.1337 data: 0.0546 max mem: 8299 +Train: [18] [5100/6250] eta: 0:02:58 lr: 0.000119 grad: 0.0656 (0.0660) loss: 0.8761 (0.8801) time: 0.1498 data: 0.0695 max mem: 8299 +Train: [18] [5200/6250] eta: 0:02:42 lr: 0.000119 grad: 0.0657 (0.0661) loss: 0.8778 (0.8801) time: 0.1714 data: 0.0965 max mem: 8299 +Train: [18] [5300/6250] eta: 0:02:27 lr: 0.000119 grad: 0.0597 (0.0661) loss: 0.8739 (0.8800) time: 0.1435 data: 0.0636 max mem: 8299 +Train: [18] [5400/6250] eta: 0:02:11 lr: 0.000119 grad: 0.0634 (0.0662) loss: 0.8791 (0.8800) time: 0.1458 data: 0.0710 max mem: 8299 +Train: [18] [5500/6250] eta: 0:01:56 lr: 0.000119 grad: 0.0616 (0.0662) loss: 0.8753 (0.8800) time: 0.1327 data: 0.0429 max mem: 8299 +Train: [18] [5600/6250] eta: 0:01:40 lr: 0.000119 grad: 0.0613 (0.0663) loss: 0.8765 (0.8799) time: 0.1397 data: 0.0608 max mem: 8299 +Train: [18] [5700/6250] eta: 0:01:25 lr: 0.000119 grad: 0.0651 (0.0664) loss: 0.8771 (0.8799) time: 0.1372 data: 0.0714 max mem: 8299 +Train: [18] [5800/6250] eta: 0:01:09 lr: 0.000118 grad: 0.0593 (0.0664) loss: 0.8807 (0.8800) time: 0.1771 data: 0.1013 max mem: 8299 +Train: [18] [5900/6250] eta: 0:00:54 lr: 0.000118 grad: 0.0590 (0.0663) loss: 0.8858 (0.8800) time: 0.1815 data: 0.1046 max mem: 8299 +Train: [18] [6000/6250] eta: 0:00:38 lr: 0.000118 grad: 0.0679 (0.0664) loss: 0.8806 (0.8800) time: 0.1778 data: 0.1053 max mem: 8299 +Train: [18] [6100/6250] eta: 0:00:23 lr: 0.000118 grad: 0.0636 (0.0665) loss: 0.8842 (0.8800) time: 0.1465 data: 0.0711 max mem: 8299 +Train: [18] [6200/6250] eta: 0:00:07 lr: 0.000118 grad: 0.0611 (0.0665) loss: 0.8770 (0.8800) time: 0.1567 data: 0.0707 max mem: 8299 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0695 (0.0665) loss: 0.8752 (0.8800) time: 0.1530 data: 0.0826 max mem: 8299 +Train: [18] Total time: 0:16:20 (0.1569 s / it) +Averaged stats: lr: 0.000118 grad: 0.0695 (0.0665) loss: 0.8752 (0.8800) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:04:11 loss: 0.9069 (0.9069) time: 4.0555 data: 3.9795 max mem: 8299 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8917 (0.8923) time: 0.1419 data: 0.1171 max mem: 8299 +Eval (hcp-train-subset): [18] Total time: 0:00:14 (0.2313 s / it) +Averaged stats (hcp-train-subset): loss: 0.8917 (0.8923) +Eval (hcp-val): [18] [ 0/62] eta: 0:06:39 loss: 0.8878 (0.8878) time: 6.4497 data: 6.4201 max mem: 8299 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8866 (0.8885) time: 0.1370 data: 0.1113 max mem: 8299 +Eval (hcp-val): [18] Total time: 0:00:14 (0.2303 s / it) +Averaged stats (hcp-val): loss: 0.8866 (0.8885) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 9:13:41 lr: 0.000118 grad: 0.0424 (0.0424) loss: 0.9468 (0.9468) time: 5.3154 data: 5.0760 max mem: 8299 +Train: [19] [ 100/6250] eta: 0:21:51 lr: 0.000118 grad: 0.0685 (0.0782) loss: 0.8789 (0.8904) time: 0.1752 data: 0.0724 max mem: 8299 +Train: [19] [ 200/6250] eta: 0:18:51 lr: 0.000118 grad: 0.0601 (0.0754) loss: 0.8823 (0.8884) time: 0.1262 data: 0.0315 max mem: 8299 +Train: [19] [ 300/6250] eta: 0:17:38 lr: 0.000118 grad: 0.0640 (0.0729) loss: 0.8807 (0.8852) time: 0.1531 data: 0.0596 max mem: 8299 +Train: [19] [ 400/6250] eta: 0:16:33 lr: 0.000118 grad: 0.0595 (0.0714) loss: 0.8851 (0.8836) time: 0.1199 data: 0.0092 max mem: 8299 +Train: [19] [ 500/6250] eta: 0:15:55 lr: 0.000118 grad: 0.0617 (0.0700) loss: 0.8788 (0.8826) time: 0.1382 data: 0.0250 max mem: 8299 +Train: [19] [ 600/6250] eta: 0:15:27 lr: 0.000118 grad: 0.0600 (0.0690) loss: 0.8829 (0.8825) time: 0.1455 data: 0.0597 max mem: 8299 +Train: [19] [ 700/6250] eta: 0:15:16 lr: 0.000118 grad: 0.0640 (0.0685) loss: 0.8803 (0.8826) time: 0.1588 data: 0.0775 max mem: 8299 +Train: [19] [ 800/6250] eta: 0:14:51 lr: 0.000118 grad: 0.0621 (0.0680) loss: 0.8825 (0.8826) time: 0.1243 data: 0.0452 max mem: 8299 +Train: [19] [ 900/6250] eta: 0:14:26 lr: 0.000118 grad: 0.0574 (0.0672) loss: 0.8820 (0.8826) time: 0.1692 data: 0.0851 max mem: 8299 +Train: [19] [1000/6250] eta: 0:14:01 lr: 0.000118 grad: 0.0629 (0.0668) loss: 0.8866 (0.8827) time: 0.1516 data: 0.0660 max mem: 8299 +Train: [19] [1100/6250] eta: 0:13:41 lr: 0.000118 grad: 0.0584 (0.0665) loss: 0.8879 (0.8828) time: 0.1530 data: 0.0693 max mem: 8299 +Train: [19] [1200/6250] eta: 0:13:20 lr: 0.000118 grad: 0.0663 (0.0664) loss: 0.8816 (0.8827) time: 0.1172 data: 0.0366 max mem: 8299 +Train: [19] [1300/6250] eta: 0:13:05 lr: 0.000118 grad: 0.0647 (0.0662) loss: 0.8839 (0.8826) time: 0.1785 data: 0.0954 max mem: 8299 +Train: [19] [1400/6250] eta: 0:12:48 lr: 0.000118 grad: 0.0634 (0.0662) loss: 0.8796 (0.8824) time: 0.1554 data: 0.0621 max mem: 8299 +Train: [19] [1500/6250] eta: 0:12:34 lr: 0.000118 grad: 0.0619 (0.0663) loss: 0.8767 (0.8822) time: 0.1595 data: 0.0869 max mem: 8299 +Train: [19] [1600/6250] eta: 0:12:22 lr: 0.000118 grad: 0.0650 (0.0663) loss: 0.8759 (0.8818) time: 0.2008 data: 0.1126 max mem: 8299 +Train: [19] [1700/6250] eta: 0:12:06 lr: 0.000118 grad: 0.0647 (0.0665) loss: 0.8762 (0.8816) time: 0.1501 data: 0.0716 max mem: 8299 +Train: [19] [1800/6250] eta: 0:11:50 lr: 0.000118 grad: 0.0653 (0.0664) loss: 0.8778 (0.8814) time: 0.1420 data: 0.0670 max mem: 8299 +Train: [19] [1900/6250] eta: 0:11:31 lr: 0.000118 grad: 0.0671 (0.0665) loss: 0.8737 (0.8812) time: 0.1531 data: 0.0661 max mem: 8299 +Train: [19] [2000/6250] eta: 0:11:13 lr: 0.000118 grad: 0.0651 (0.0669) loss: 0.8795 (0.8810) time: 0.1084 data: 0.0160 max mem: 8299 +Train: [19] [2100/6250] eta: 0:10:57 lr: 0.000118 grad: 0.0660 (0.0670) loss: 0.8773 (0.8808) time: 0.1501 data: 0.0649 max mem: 8299 +Train: [19] [2200/6250] eta: 0:10:40 lr: 0.000118 grad: 0.0606 (0.0669) loss: 0.8775 (0.8807) time: 0.1586 data: 0.0773 max mem: 8299 +Train: [19] [2300/6250] eta: 0:10:22 lr: 0.000118 grad: 0.0660 (0.0670) loss: 0.8754 (0.8806) time: 0.1398 data: 0.0526 max mem: 8299 +Train: [19] [2400/6250] eta: 0:10:05 lr: 0.000118 grad: 0.0655 (0.0670) loss: 0.8749 (0.8805) time: 0.1493 data: 0.0526 max mem: 8299 +Train: [19] [2500/6250] eta: 0:09:49 lr: 0.000118 grad: 0.0648 (0.0670) loss: 0.8827 (0.8804) time: 0.1223 data: 0.0362 max mem: 8299 +Train: [19] [2600/6250] eta: 0:09:33 lr: 0.000118 grad: 0.0672 (0.0669) loss: 0.8775 (0.8804) time: 0.1533 data: 0.0770 max mem: 8299 +Train: [19] [2700/6250] eta: 0:09:16 lr: 0.000118 grad: 0.0680 (0.0669) loss: 0.8799 (0.8803) time: 0.1549 data: 0.0777 max mem: 8299 +Train: [19] [2800/6250] eta: 0:08:59 lr: 0.000118 grad: 0.0678 (0.0670) loss: 0.8780 (0.8802) time: 0.1212 data: 0.0468 max mem: 8299 +Train: [19] [2900/6250] eta: 0:08:44 lr: 0.000118 grad: 0.0649 (0.0670) loss: 0.8746 (0.8801) time: 0.1632 data: 0.0842 max mem: 8299 +Train: [19] [3000/6250] eta: 0:08:27 lr: 0.000118 grad: 0.0618 (0.0670) loss: 0.8811 (0.8801) time: 0.1403 data: 0.0590 max mem: 8299 +Train: [19] [3100/6250] eta: 0:08:12 lr: 0.000118 grad: 0.0705 (0.0672) loss: 0.8754 (0.8800) time: 0.1704 data: 0.0860 max mem: 8299 +Train: [19] [3200/6250] eta: 0:07:55 lr: 0.000118 grad: 0.0641 (0.0671) loss: 0.8822 (0.8799) time: 0.1200 data: 0.0295 max mem: 8299 +Train: [19] [3300/6250] eta: 0:07:39 lr: 0.000118 grad: 0.0644 (0.0672) loss: 0.8782 (0.8799) time: 0.1459 data: 0.0575 max mem: 8299 +Train: [19] [3400/6250] eta: 0:07:23 lr: 0.000118 grad: 0.0674 (0.0672) loss: 0.8816 (0.8799) time: 0.1420 data: 0.0626 max mem: 8299 +Train: [19] [3500/6250] eta: 0:07:08 lr: 0.000118 grad: 0.0652 (0.0672) loss: 0.8802 (0.8799) time: 0.1476 data: 0.0631 max mem: 8299 +Train: [19] [3600/6250] eta: 0:06:52 lr: 0.000118 grad: 0.0655 (0.0671) loss: 0.8804 (0.8799) time: 0.1554 data: 0.0577 max mem: 8299 +Train: [19] [3700/6250] eta: 0:06:37 lr: 0.000118 grad: 0.0617 (0.0671) loss: 0.8812 (0.8799) time: 0.1221 data: 0.0340 max mem: 8299 +Train: [19] [3800/6250] eta: 0:06:21 lr: 0.000118 grad: 0.0599 (0.0671) loss: 0.8790 (0.8798) time: 0.1833 data: 0.0989 max mem: 8299 +Train: [19] [3900/6250] eta: 0:06:05 lr: 0.000118 grad: 0.0631 (0.0671) loss: 0.8765 (0.8797) time: 0.1554 data: 0.0763 max mem: 8299 +Train: [19] [4000/6250] eta: 0:05:50 lr: 0.000118 grad: 0.0619 (0.0670) loss: 0.8796 (0.8798) time: 0.1546 data: 0.0778 max mem: 8299 +Train: [19] [4100/6250] eta: 0:05:34 lr: 0.000118 grad: 0.0609 (0.0670) loss: 0.8797 (0.8797) time: 0.1602 data: 0.0712 max mem: 8299 +Train: [19] [4200/6250] eta: 0:05:18 lr: 0.000118 grad: 0.0650 (0.0670) loss: 0.8765 (0.8797) time: 0.1653 data: 0.0809 max mem: 8299 +Train: [19] [4300/6250] eta: 0:05:03 lr: 0.000118 grad: 0.0635 (0.0671) loss: 0.8806 (0.8797) time: 0.1605 data: 0.0730 max mem: 8299 +Train: [19] [4400/6250] eta: 0:04:48 lr: 0.000118 grad: 0.0671 (0.0670) loss: 0.8805 (0.8797) time: 0.1673 data: 0.0846 max mem: 8299 +Train: [19] [4500/6250] eta: 0:04:32 lr: 0.000118 grad: 0.0613 (0.0670) loss: 0.8797 (0.8797) time: 0.1474 data: 0.0670 max mem: 8299 +Train: [19] [4600/6250] eta: 0:04:17 lr: 0.000118 grad: 0.0665 (0.0669) loss: 0.8799 (0.8798) time: 0.1695 data: 0.0780 max mem: 8299 +Train: [19] [4700/6250] eta: 0:04:02 lr: 0.000118 grad: 0.0649 (0.0669) loss: 0.8820 (0.8798) time: 0.2014 data: 0.1218 max mem: 8299 +Train: [19] [4800/6250] eta: 0:03:46 lr: 0.000118 grad: 0.0612 (0.0668) loss: 0.8801 (0.8798) time: 0.1327 data: 0.0466 max mem: 8299 +Train: [19] [4900/6250] eta: 0:03:31 lr: 0.000118 grad: 0.0639 (0.0668) loss: 0.8843 (0.8798) time: 0.1728 data: 0.0888 max mem: 8299 +Train: [19] [5000/6250] eta: 0:03:15 lr: 0.000118 grad: 0.0613 (0.0667) loss: 0.8834 (0.8798) time: 0.1628 data: 0.0905 max mem: 8299 +Train: [19] [5100/6250] eta: 0:03:00 lr: 0.000118 grad: 0.0612 (0.0666) loss: 0.8798 (0.8799) time: 0.1461 data: 0.0559 max mem: 8299 +Train: [19] [5200/6250] eta: 0:02:44 lr: 0.000118 grad: 0.0663 (0.0666) loss: 0.8776 (0.8798) time: 0.1434 data: 0.0705 max mem: 8299 +Train: [19] [5300/6250] eta: 0:02:29 lr: 0.000118 grad: 0.0647 (0.0666) loss: 0.8792 (0.8798) time: 0.1719 data: 0.0825 max mem: 8299 +Train: [19] [5400/6250] eta: 0:02:13 lr: 0.000118 grad: 0.0624 (0.0665) loss: 0.8776 (0.8798) time: 0.1630 data: 0.0769 max mem: 8299 +Train: [19] [5500/6250] eta: 0:01:58 lr: 0.000118 grad: 0.0605 (0.0665) loss: 0.8756 (0.8797) time: 0.1569 data: 0.0820 max mem: 8299 +Train: [19] [5600/6250] eta: 0:01:42 lr: 0.000118 grad: 0.0725 (0.0665) loss: 0.8721 (0.8796) time: 0.1771 data: 0.1017 max mem: 8299 +Train: [19] [5700/6250] eta: 0:01:26 lr: 0.000118 grad: 0.0634 (0.0665) loss: 0.8741 (0.8795) time: 0.1574 data: 0.0787 max mem: 8299 +Train: [19] [5800/6250] eta: 0:01:10 lr: 0.000118 grad: 0.0657 (0.0665) loss: 0.8744 (0.8795) time: 0.1730 data: 0.0929 max mem: 8299 +Train: [19] [5900/6250] eta: 0:00:55 lr: 0.000118 grad: 0.0679 (0.0665) loss: 0.8784 (0.8795) time: 0.1467 data: 0.0569 max mem: 8299 +Train: [19] [6000/6250] eta: 0:00:39 lr: 0.000118 grad: 0.0567 (0.0664) loss: 0.8814 (0.8795) time: 0.1691 data: 0.0982 max mem: 8299 +Train: [19] [6100/6250] eta: 0:00:23 lr: 0.000117 grad: 0.0618 (0.0664) loss: 0.8764 (0.8795) time: 0.1833 data: 0.1161 max mem: 8299 +Train: [19] [6200/6250] eta: 0:00:07 lr: 0.000117 grad: 0.0603 (0.0664) loss: 0.8756 (0.8794) time: 0.0992 data: 0.0224 max mem: 8299 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0650 (0.0664) loss: 0.8826 (0.8794) time: 0.1342 data: 0.0562 max mem: 8299 +Train: [19] Total time: 0:16:31 (0.1587 s / it) +Averaged stats: lr: 0.000117 grad: 0.0650 (0.0664) loss: 0.8826 (0.8794) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:03:35 loss: 0.8995 (0.8995) time: 3.4694 data: 3.3920 max mem: 8299 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8910 (0.8921) time: 0.1295 data: 0.1050 max mem: 8299 +Eval (hcp-train-subset): [19] Total time: 0:00:13 (0.2159 s / it) +Averaged stats (hcp-train-subset): loss: 0.8910 (0.8921) +Making plots (hcp-train-subset): example=6 +Eval (hcp-val): [19] [ 0/62] eta: 0:05:41 loss: 0.8862 (0.8862) time: 5.5034 data: 5.4711 max mem: 8299 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8879 (0.8889) time: 0.1378 data: 0.1118 max mem: 8299 +Eval (hcp-val): [19] Total time: 0:00:13 (0.2257 s / it) +Averaged stats (hcp-val): loss: 0.8879 (0.8889) +Making plots (hcp-val): example=51 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-00019.pth +Train: [20] [ 0/6250] eta: 9:34:59 lr: 0.000117 grad: nan (nan) loss: 0.8696 (0.8696) time: 5.5199 data: 5.3962 max mem: 8299 +Train: [20] [ 100/6250] eta: 0:21:20 lr: 0.000117 grad: 0.0687 (0.0733) loss: 0.8815 (0.8821) time: 0.1607 data: 0.0570 max mem: 8299 +Train: [20] [ 200/6250] eta: 0:18:19 lr: 0.000117 grad: 0.0590 (0.0692) loss: 0.8812 (0.8822) time: 0.1607 data: 0.0724 max mem: 8299 +Train: [20] [ 300/6250] eta: 0:16:32 lr: 0.000117 grad: 0.0623 (0.0681) loss: 0.8736 (0.8808) time: 0.1405 data: 0.0581 max mem: 8299 +Train: [20] [ 400/6250] eta: 0:15:40 lr: 0.000117 grad: 0.0594 (0.0666) loss: 0.8855 (0.8807) time: 0.1298 data: 0.0371 max mem: 8299 +Train: [20] [ 500/6250] eta: 0:15:04 lr: 0.000117 grad: 0.0589 (0.0662) loss: 0.8807 (0.8804) time: 0.1500 data: 0.0684 max mem: 8299 +Train: [20] [ 600/6250] eta: 0:14:40 lr: 0.000117 grad: 0.0654 (0.0662) loss: 0.8805 (0.8799) time: 0.1511 data: 0.0592 max mem: 8299 +Train: [20] [ 700/6250] eta: 0:14:53 lr: 0.000117 grad: 0.0644 (0.0660) loss: 0.8807 (0.8797) time: 0.1942 data: 0.1204 max mem: 8299 +Train: [20] [ 800/6250] eta: 0:15:15 lr: 0.000117 grad: 0.0673 (0.0663) loss: 0.8777 (0.8795) time: 0.2435 data: 0.1618 max mem: 8299 +Train: [20] [ 900/6250] eta: 0:15:12 lr: 0.000117 grad: 0.0630 (0.0663) loss: 0.8762 (0.8793) time: 0.1940 data: 0.1210 max mem: 8299 +Train: [20] [1000/6250] eta: 0:14:54 lr: 0.000117 grad: 0.0678 (0.0665) loss: 0.8736 (0.8791) time: 0.1948 data: 0.1099 max mem: 8299 +Train: [20] [1100/6250] eta: 0:14:39 lr: 0.000117 grad: 0.0600 (0.0666) loss: 0.8746 (0.8789) time: 0.1582 data: 0.0810 max mem: 8299 +Train: [20] [1200/6250] eta: 0:14:22 lr: 0.000117 grad: 0.0595 (0.0666) loss: 0.8804 (0.8787) time: 0.1914 data: 0.1054 max mem: 8299 +Train: [20] [1300/6250] eta: 0:14:06 lr: 0.000117 grad: 0.0628 (0.0666) loss: 0.8773 (0.8784) time: 0.1902 data: 0.1080 max mem: 8299 +Train: [20] [1400/6250] eta: 0:13:45 lr: 0.000117 grad: 0.0629 (0.0667) loss: 0.8766 (0.8782) time: 0.1522 data: 0.0807 max mem: 8299 +Train: [20] [1500/6250] eta: 0:13:27 lr: 0.000117 grad: 0.0679 (0.0667) loss: 0.8687 (0.8780) time: 0.1130 data: 0.0184 max mem: 8299 +Train: [20] [1600/6250] eta: 0:13:10 lr: 0.000117 grad: 0.0662 (0.0667) loss: 0.8803 (0.8780) time: 0.1528 data: 0.0810 max mem: 8299 +Train: [20] [1700/6250] eta: 0:12:48 lr: 0.000117 grad: 0.0622 (0.0667) loss: 0.8820 (0.8779) time: 0.1665 data: 0.0771 max mem: 8299 +Train: [20] [1800/6250] eta: 0:12:29 lr: 0.000117 grad: 0.0641 (0.0666) loss: 0.8773 (0.8780) time: 0.1761 data: 0.0947 max mem: 8299 +Train: [20] [1900/6250] eta: 0:12:05 lr: 0.000117 grad: 0.0668 (0.0667) loss: 0.8786 (0.8780) time: 0.1350 data: 0.0502 max mem: 8299 +Train: [20] [2000/6250] eta: 0:11:47 lr: 0.000117 grad: 0.0645 (0.0667) loss: 0.8759 (0.8781) time: 0.1828 data: 0.0926 max mem: 8299 +Train: [20] [2100/6250] eta: 0:11:28 lr: 0.000117 grad: 0.0587 (0.0667) loss: 0.8795 (0.8781) time: 0.1555 data: 0.0823 max mem: 8299 +Train: [20] [2200/6250] eta: 0:11:08 lr: 0.000117 grad: 0.0567 (0.0666) loss: 0.8847 (0.8781) time: 0.1449 data: 0.0631 max mem: 8299 +Train: [20] [2300/6250] eta: 0:10:50 lr: 0.000117 grad: 0.0614 (0.0667) loss: 0.8787 (0.8782) time: 0.1525 data: 0.0684 max mem: 8299 +Train: [20] [2400/6250] eta: 0:10:33 lr: 0.000117 grad: 0.0646 (0.0666) loss: 0.8797 (0.8783) time: 0.1769 data: 0.0933 max mem: 8299 +Train: [20] [2500/6250] eta: 0:10:15 lr: 0.000117 grad: 0.0646 (0.0666) loss: 0.8775 (0.8783) time: 0.1458 data: 0.0610 max mem: 8299 +Train: [20] [2600/6250] eta: 0:09:57 lr: 0.000117 grad: 0.0574 (0.0664) loss: 0.8815 (0.8784) time: 0.1565 data: 0.0693 max mem: 8299 +Train: [20] [2700/6250] eta: 0:09:41 lr: 0.000117 grad: 0.0629 (0.0664) loss: 0.8834 (0.8784) time: 0.1510 data: 0.0669 max mem: 8299 +Train: [20] [2800/6250] eta: 0:09:25 lr: 0.000117 grad: 0.0644 (0.0664) loss: 0.8792 (0.8784) time: 0.1557 data: 0.0715 max mem: 8299 +Train: [20] [2900/6250] eta: 0:09:07 lr: 0.000117 grad: 0.0666 (0.0665) loss: 0.8771 (0.8784) time: 0.1548 data: 0.0660 max mem: 8299 +Train: [20] [3000/6250] eta: 0:08:51 lr: 0.000117 grad: 0.0653 (0.0665) loss: 0.8747 (0.8784) time: 0.1517 data: 0.0784 max mem: 8299 +Train: [20] [3100/6250] eta: 0:08:33 lr: 0.000117 grad: 0.0596 (0.0664) loss: 0.8760 (0.8784) time: 0.1511 data: 0.0558 max mem: 8299 +Train: [20] [3200/6250] eta: 0:08:15 lr: 0.000117 grad: 0.0630 (0.0663) loss: 0.8829 (0.8784) time: 0.1435 data: 0.0555 max mem: 8299 +Train: [20] [3300/6250] eta: 0:07:58 lr: 0.000117 grad: 0.0632 (0.0664) loss: 0.8810 (0.8785) time: 0.1221 data: 0.0315 max mem: 8299 +Train: [20] [3400/6250] eta: 0:07:42 lr: 0.000117 grad: 0.0606 (0.0664) loss: 0.8822 (0.8786) time: 0.1667 data: 0.0867 max mem: 8299 +Train: [20] [3500/6250] eta: 0:07:26 lr: 0.000117 grad: 0.0671 (0.0665) loss: 0.8812 (0.8786) time: 0.1814 data: 0.1077 max mem: 8299 +Train: [20] [3600/6250] eta: 0:07:11 lr: 0.000117 grad: 0.0647 (0.0664) loss: 0.8812 (0.8787) time: 0.1574 data: 0.0822 max mem: 8299 +Train: [20] [3700/6250] eta: 0:06:54 lr: 0.000117 grad: 0.0599 (0.0663) loss: 0.8793 (0.8787) time: 0.1620 data: 0.0822 max mem: 8299 +Train: [20] [3800/6250] eta: 0:06:38 lr: 0.000117 grad: 0.0667 (0.0664) loss: 0.8805 (0.8787) time: 0.1652 data: 0.0868 max mem: 8299 +Train: [20] [3900/6250] eta: 0:06:22 lr: 0.000117 grad: 0.0618 (0.0664) loss: 0.8819 (0.8787) time: 0.1760 data: 0.0884 max mem: 8299 +Train: [20] [4000/6250] eta: 0:06:04 lr: 0.000117 grad: 0.0646 (0.0663) loss: 0.8758 (0.8787) time: 0.1502 data: 0.0571 max mem: 8299 +Train: [20] [4100/6250] eta: 0:05:47 lr: 0.000117 grad: 0.0632 (0.0664) loss: 0.8743 (0.8786) time: 0.1283 data: 0.0562 max mem: 8299 +Train: [20] [4200/6250] eta: 0:05:31 lr: 0.000117 grad: 0.0662 (0.0664) loss: 0.8772 (0.8785) time: 0.1669 data: 0.0930 max mem: 8299 +Train: [20] [4300/6250] eta: 0:05:15 lr: 0.000117 grad: 0.0666 (0.0664) loss: 0.8771 (0.8784) time: 0.1548 data: 0.0680 max mem: 8299 +Train: [20] [4400/6250] eta: 0:04:58 lr: 0.000117 grad: 0.0644 (0.0664) loss: 0.8799 (0.8784) time: 0.1636 data: 0.0835 max mem: 8299 +Train: [20] [4500/6250] eta: 0:04:42 lr: 0.000117 grad: 0.0577 (0.0664) loss: 0.8809 (0.8784) time: 0.1604 data: 0.0968 max mem: 8299 +Train: [20] [4600/6250] eta: 0:04:26 lr: 0.000117 grad: 0.0648 (0.0664) loss: 0.8797 (0.8783) time: 0.1667 data: 0.1027 max mem: 8299 +Train: [20] [4700/6250] eta: 0:04:09 lr: 0.000117 grad: 0.0625 (0.0664) loss: 0.8770 (0.8783) time: 0.1550 data: 0.0798 max mem: 8299 +Train: [20] [4800/6250] eta: 0:03:54 lr: 0.000117 grad: 0.0651 (0.0665) loss: 0.8741 (0.8782) time: 0.1894 data: 0.1257 max mem: 8299 +Train: [20] [4900/6250] eta: 0:03:37 lr: 0.000117 grad: 0.0652 (0.0664) loss: 0.8782 (0.8782) time: 0.1496 data: 0.0812 max mem: 8299 +Train: [20] [5000/6250] eta: 0:03:22 lr: 0.000117 grad: 0.0694 (0.0664) loss: 0.8762 (0.8782) time: 0.1523 data: 0.0672 max mem: 8299 +Train: [20] [5100/6250] eta: 0:03:06 lr: 0.000117 grad: 0.0653 (0.0665) loss: 0.8775 (0.8782) time: 0.1735 data: 0.0936 max mem: 8299 +Train: [20] [5200/6250] eta: 0:02:49 lr: 0.000117 grad: 0.0668 (0.0665) loss: 0.8781 (0.8782) time: 0.1717 data: 0.0872 max mem: 8299 +Train: [20] [5300/6250] eta: 0:02:33 lr: 0.000117 grad: 0.0705 (0.0664) loss: 0.8773 (0.8782) time: 0.1571 data: 0.0780 max mem: 8299 +Train: [20] [5400/6250] eta: 0:02:17 lr: 0.000117 grad: 0.0658 (0.0665) loss: 0.8816 (0.8782) time: 0.1793 data: 0.1075 max mem: 8299 +Train: [20] [5500/6250] eta: 0:02:01 lr: 0.000117 grad: 0.0641 (0.0665) loss: 0.8817 (0.8782) time: 0.1616 data: 0.0826 max mem: 8299 +Train: [20] [5600/6250] eta: 0:01:45 lr: 0.000117 grad: 0.0628 (0.0665) loss: 0.8750 (0.8782) time: 0.1708 data: 0.0978 max mem: 8299 +Train: [20] [5700/6250] eta: 0:01:29 lr: 0.000117 grad: 0.0647 (0.0665) loss: 0.8738 (0.8782) time: 0.1492 data: 0.0714 max mem: 8299 +Train: [20] [5800/6250] eta: 0:01:12 lr: 0.000117 grad: 0.0611 (0.0665) loss: 0.8738 (0.8782) time: 0.1871 data: 0.1142 max mem: 8299 +Train: [20] [5900/6250] eta: 0:00:56 lr: 0.000117 grad: 0.0691 (0.0665) loss: 0.8757 (0.8782) time: 0.1542 data: 0.0690 max mem: 8299 +Train: [20] [6000/6250] eta: 0:00:40 lr: 0.000116 grad: 0.0694 (0.0666) loss: 0.8736 (0.8782) time: 0.1476 data: 0.0666 max mem: 8299 +Train: [20] [6100/6250] eta: 0:00:24 lr: 0.000116 grad: 0.0672 (0.0666) loss: 0.8769 (0.8781) time: 0.1587 data: 0.0731 max mem: 8299 +Train: [20] [6200/6250] eta: 0:00:08 lr: 0.000116 grad: 0.0627 (0.0666) loss: 0.8743 (0.8781) time: 0.1863 data: 0.1025 max mem: 8299 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0703 (0.0666) loss: 0.8704 (0.8780) time: 0.1739 data: 0.0848 max mem: 8299 +Train: [20] Total time: 0:16:58 (0.1630 s / it) +Averaged stats: lr: 0.000116 grad: 0.0703 (0.0666) loss: 0.8704 (0.8780) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:04:52 loss: 0.8944 (0.8944) time: 4.7134 data: 4.6809 max mem: 8299 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8912 (0.8915) time: 0.1152 data: 0.0905 max mem: 8299 +Eval (hcp-train-subset): [20] Total time: 0:00:13 (0.2240 s / it) +Averaged stats (hcp-train-subset): loss: 0.8912 (0.8915) +Eval (hcp-val): [20] [ 0/62] eta: 0:05:23 loss: 0.8855 (0.8855) time: 5.2198 data: 5.1886 max mem: 8299 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8880 (0.8890) time: 0.1261 data: 0.1004 max mem: 8299 +Eval (hcp-val): [20] Total time: 0:00:13 (0.2212 s / it) +Averaged stats (hcp-val): loss: 0.8880 (0.8890) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 9:22:31 lr: 0.000116 grad: 0.0434 (0.0434) loss: 0.8946 (0.8946) time: 5.4002 data: 5.1985 max mem: 8299 +Train: [21] [ 100/6250] eta: 0:21:30 lr: 0.000116 grad: 0.0629 (0.0670) loss: 0.8894 (0.8911) time: 0.1559 data: 0.0595 max mem: 8299 +Train: [21] [ 200/6250] eta: 0:18:20 lr: 0.000116 grad: 0.0617 (0.0655) loss: 0.8833 (0.8889) time: 0.1309 data: 0.0368 max mem: 8299 +Train: [21] [ 300/6250] eta: 0:16:46 lr: 0.000116 grad: 0.0617 (0.0655) loss: 0.8767 (0.8860) time: 0.1390 data: 0.0351 max mem: 8299 +Train: [21] [ 400/6250] eta: 0:15:54 lr: 0.000116 grad: 0.0621 (0.0655) loss: 0.8768 (0.8834) time: 0.1435 data: 0.0280 max mem: 8299 +Train: [21] [ 500/6250] eta: 0:15:17 lr: 0.000116 grad: 0.0617 (0.0662) loss: 0.8689 (0.8817) time: 0.1486 data: 0.0531 max mem: 8299 +Train: [21] [ 600/6250] eta: 0:15:00 lr: 0.000116 grad: 0.0613 (0.0664) loss: 0.8750 (0.8811) time: 0.1665 data: 0.0777 max mem: 8299 +Train: [21] [ 700/6250] eta: 0:15:04 lr: 0.000116 grad: 0.0614 (0.0661) loss: 0.8760 (0.8802) time: 0.2063 data: 0.1281 max mem: 8299 +Train: [21] [ 800/6250] eta: 0:14:59 lr: 0.000116 grad: 0.0646 (0.0658) loss: 0.8806 (0.8800) time: 0.1901 data: 0.1114 max mem: 8299 +Train: [21] [ 900/6250] eta: 0:14:45 lr: 0.000116 grad: 0.0730 (0.0658) loss: 0.8806 (0.8796) time: 0.1610 data: 0.0792 max mem: 8299 +Train: [21] [1000/6250] eta: 0:14:25 lr: 0.000116 grad: 0.0566 (0.0654) loss: 0.8839 (0.8797) time: 0.1403 data: 0.0594 max mem: 8299 +Train: [21] [1100/6250] eta: 0:14:02 lr: 0.000116 grad: 0.0677 (0.0652) loss: 0.8793 (0.8798) time: 0.1202 data: 0.0230 max mem: 8299 +Train: [21] [1200/6250] eta: 0:13:43 lr: 0.000116 grad: 0.0567 (0.0652) loss: 0.8837 (0.8797) time: 0.1769 data: 0.0817 max mem: 8299 +Train: [21] [1300/6250] eta: 0:13:24 lr: 0.000116 grad: 0.0635 (0.0651) loss: 0.8786 (0.8796) time: 0.1661 data: 0.0662 max mem: 8299 +Train: [21] [1400/6250] eta: 0:13:05 lr: 0.000116 grad: 0.0692 (0.0652) loss: 0.8716 (0.8793) time: 0.1589 data: 0.0766 max mem: 8299 +Train: [21] [1500/6250] eta: 0:12:50 lr: 0.000116 grad: 0.0631 (0.0650) loss: 0.8752 (0.8792) time: 0.1878 data: 0.1017 max mem: 8299 +Train: [21] [1600/6250] eta: 0:12:32 lr: 0.000116 grad: 0.0623 (0.0651) loss: 0.8753 (0.8790) time: 0.1581 data: 0.0738 max mem: 8299 +Train: [21] [1700/6250] eta: 0:12:12 lr: 0.000116 grad: 0.0628 (0.0650) loss: 0.8792 (0.8789) time: 0.1726 data: 0.0972 max mem: 8299 +Train: [21] [1800/6250] eta: 0:11:50 lr: 0.000116 grad: 0.0607 (0.0650) loss: 0.8830 (0.8788) time: 0.1528 data: 0.0700 max mem: 8299 +Train: [21] [1900/6250] eta: 0:11:34 lr: 0.000116 grad: 0.0634 (0.0650) loss: 0.8761 (0.8787) time: 0.1324 data: 0.0512 max mem: 8299 +Train: [21] [2000/6250] eta: 0:11:17 lr: 0.000116 grad: 0.0627 (0.0650) loss: 0.8761 (0.8786) time: 0.1670 data: 0.0823 max mem: 8299 +Train: [21] [2100/6250] eta: 0:11:03 lr: 0.000116 grad: 0.0617 (0.0650) loss: 0.8779 (0.8786) time: 0.1705 data: 0.0876 max mem: 8299 +Train: [21] [2200/6250] eta: 0:10:45 lr: 0.000116 grad: 0.0595 (0.0650) loss: 0.8798 (0.8784) time: 0.1555 data: 0.0655 max mem: 8299 +Train: [21] [2300/6250] eta: 0:10:27 lr: 0.000116 grad: 0.0630 (0.0651) loss: 0.8782 (0.8783) time: 0.1266 data: 0.0416 max mem: 8299 +Train: [21] [2400/6250] eta: 0:10:13 lr: 0.000116 grad: 0.0649 (0.0652) loss: 0.8775 (0.8783) time: 0.1993 data: 0.1310 max mem: 8299 +Train: [21] [2500/6250] eta: 0:10:00 lr: 0.000116 grad: 0.0708 (0.0652) loss: 0.8814 (0.8782) time: 0.2154 data: 0.1447 max mem: 8299 +Train: [21] [2600/6250] eta: 0:09:43 lr: 0.000116 grad: 0.0669 (0.0653) loss: 0.8717 (0.8782) time: 0.1821 data: 0.1075 max mem: 8299 +Train: [21] [2700/6250] eta: 0:09:25 lr: 0.000116 grad: 0.0654 (0.0654) loss: 0.8805 (0.8782) time: 0.1350 data: 0.0416 max mem: 8299 +Train: [21] [2800/6250] eta: 0:09:09 lr: 0.000116 grad: 0.0625 (0.0654) loss: 0.8816 (0.8782) time: 0.1418 data: 0.0672 max mem: 8299 +Train: [21] [2900/6250] eta: 0:08:54 lr: 0.000116 grad: 0.0617 (0.0654) loss: 0.8795 (0.8782) time: 0.1512 data: 0.0706 max mem: 8299 +Train: [21] [3000/6250] eta: 0:08:38 lr: 0.000116 grad: 0.0634 (0.0655) loss: 0.8807 (0.8782) time: 0.1761 data: 0.1015 max mem: 8299 +Train: [21] [3100/6250] eta: 0:08:22 lr: 0.000116 grad: 0.0673 (0.0655) loss: 0.8718 (0.8782) time: 0.1445 data: 0.0587 max mem: 8299 +Train: [21] [3200/6250] eta: 0:08:07 lr: 0.000116 grad: 0.0665 (0.0658) loss: 0.8785 (0.8781) time: 0.1584 data: 0.0867 max mem: 8299 +Train: [21] [3300/6250] eta: 0:07:51 lr: 0.000116 grad: 0.0651 (0.0658) loss: 0.8795 (0.8781) time: 0.1629 data: 0.0828 max mem: 8299 +Train: [21] [3400/6250] eta: 0:07:35 lr: 0.000116 grad: 0.0667 (0.0659) loss: 0.8791 (0.8780) time: 0.1650 data: 0.0841 max mem: 8299 +Train: [21] [3500/6250] eta: 0:07:18 lr: 0.000116 grad: 0.0602 (0.0661) loss: 0.8748 (0.8780) time: 0.1285 data: 0.0420 max mem: 8299 +Train: [21] [3600/6250] eta: 0:07:02 lr: 0.000116 grad: 0.0687 (0.0662) loss: 0.8762 (0.8780) time: 0.1472 data: 0.0646 max mem: 8299 +Train: [21] [3700/6250] eta: 0:06:45 lr: 0.000116 grad: 0.0616 (0.0662) loss: 0.8781 (0.8780) time: 0.1686 data: 0.0842 max mem: 8299 +Train: [21] [3800/6250] eta: 0:06:29 lr: 0.000116 grad: 0.0659 (0.0663) loss: 0.8756 (0.8779) time: 0.1532 data: 0.0657 max mem: 8299 +Train: [21] [3900/6250] eta: 0:06:13 lr: 0.000116 grad: 0.0669 (0.0664) loss: 0.8732 (0.8779) time: 0.1429 data: 0.0539 max mem: 8299 +Train: [21] [4000/6250] eta: 0:05:56 lr: 0.000116 grad: 0.0662 (0.0665) loss: 0.8764 (0.8779) time: 0.1299 data: 0.0546 max mem: 8299 +Train: [21] [4100/6250] eta: 0:05:41 lr: 0.000116 grad: 0.0687 (0.0666) loss: 0.8765 (0.8778) time: 0.1374 data: 0.0533 max mem: 8299 +Train: [21] [4200/6250] eta: 0:05:25 lr: 0.000116 grad: 0.0708 (0.0668) loss: 0.8737 (0.8778) time: 0.1470 data: 0.0691 max mem: 8299 +Train: [21] [4300/6250] eta: 0:05:09 lr: 0.000116 grad: 0.0652 (0.0668) loss: 0.8735 (0.8777) time: 0.1428 data: 0.0488 max mem: 8299 +Train: [21] [4400/6250] eta: 0:04:53 lr: 0.000116 grad: 0.0672 (0.0669) loss: 0.8804 (0.8777) time: 0.1595 data: 0.0729 max mem: 8299 +Train: [21] [4500/6250] eta: 0:04:37 lr: 0.000116 grad: 0.0707 (0.0670) loss: 0.8720 (0.8776) time: 0.1585 data: 0.0748 max mem: 8299 +Train: [21] [4600/6250] eta: 0:04:21 lr: 0.000116 grad: 0.0674 (0.0670) loss: 0.8780 (0.8776) time: 0.1394 data: 0.0461 max mem: 8299 +Train: [21] [4700/6250] eta: 0:04:05 lr: 0.000116 grad: 0.0639 (0.0671) loss: 0.8787 (0.8776) time: 0.1366 data: 0.0468 max mem: 8299 +Train: [21] [4800/6250] eta: 0:03:49 lr: 0.000116 grad: 0.0656 (0.0671) loss: 0.8788 (0.8776) time: 0.1728 data: 0.0907 max mem: 8299 +Train: [21] [4900/6250] eta: 0:03:33 lr: 0.000116 grad: 0.0617 (0.0671) loss: 0.8826 (0.8776) time: 0.1546 data: 0.0587 max mem: 8299 +Train: [21] [5000/6250] eta: 0:03:17 lr: 0.000116 grad: 0.0681 (0.0671) loss: 0.8809 (0.8776) time: 0.1139 data: 0.0390 max mem: 8299 +Train: [21] [5100/6250] eta: 0:03:01 lr: 0.000116 grad: 0.0682 (0.0671) loss: 0.8765 (0.8776) time: 0.1385 data: 0.0603 max mem: 8299 +Train: [21] [5200/6250] eta: 0:02:45 lr: 0.000116 grad: 0.0648 (0.0673) loss: 0.8755 (0.8776) time: 0.1858 data: 0.1040 max mem: 8299 +Train: [21] [5300/6250] eta: 0:02:29 lr: 0.000116 grad: 0.0682 (0.0673) loss: 0.8776 (0.8775) time: 0.1896 data: 0.1092 max mem: 8299 +Train: [21] [5400/6250] eta: 0:02:14 lr: 0.000116 grad: 0.0703 (0.0674) loss: 0.8736 (0.8775) time: 0.1760 data: 0.0926 max mem: 8299 +Train: [21] [5500/6250] eta: 0:01:58 lr: 0.000116 grad: 0.0662 (0.0675) loss: 0.8766 (0.8774) time: 0.1527 data: 0.0673 max mem: 8299 +Train: [21] [5600/6250] eta: 0:01:42 lr: 0.000115 grad: 0.0659 (0.0675) loss: 0.8762 (0.8774) time: 0.1630 data: 0.0880 max mem: 8299 +Train: [21] [5700/6250] eta: 0:01:26 lr: 0.000115 grad: 0.0676 (0.0676) loss: 0.8698 (0.8773) time: 0.1453 data: 0.0505 max mem: 8299 +Train: [21] [5800/6250] eta: 0:01:10 lr: 0.000115 grad: 0.0682 (0.0678) loss: 0.8802 (0.8772) time: 0.1585 data: 0.0660 max mem: 8299 +Train: [21] [5900/6250] eta: 0:00:55 lr: 0.000115 grad: 0.0637 (0.0678) loss: 0.8759 (0.8771) time: 0.1865 data: 0.1142 max mem: 8299 +Train: [21] [6000/6250] eta: 0:00:39 lr: 0.000115 grad: 0.0669 (0.0678) loss: 0.8730 (0.8771) time: 0.1488 data: 0.0767 max mem: 8299 +Train: [21] [6100/6250] eta: 0:00:23 lr: 0.000115 grad: 0.0673 (0.0679) loss: 0.8702 (0.8770) time: 0.1280 data: 0.0523 max mem: 8299 +Train: [21] [6200/6250] eta: 0:00:07 lr: 0.000115 grad: 0.0671 (0.0679) loss: 0.8704 (0.8769) time: 0.1865 data: 0.0999 max mem: 8299 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0649 (0.0679) loss: 0.8697 (0.8769) time: 0.1510 data: 0.0742 max mem: 8299 +Train: [21] Total time: 0:16:33 (0.1589 s / it) +Averaged stats: lr: 0.000115 grad: 0.0649 (0.0679) loss: 0.8697 (0.8769) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:05:48 loss: 0.9031 (0.9031) time: 5.6223 data: 5.5895 max mem: 8299 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8910 (0.8916) time: 0.1272 data: 0.1022 max mem: 8299 +Eval (hcp-train-subset): [21] Total time: 0:00:14 (0.2282 s / it) +Averaged stats (hcp-train-subset): loss: 0.8910 (0.8916) +Eval (hcp-val): [21] [ 0/62] eta: 0:03:41 loss: 0.8842 (0.8842) time: 3.5801 data: 3.4952 max mem: 8299 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8866 (0.8880) time: 0.1212 data: 0.0969 max mem: 8299 +Eval (hcp-val): [21] Total time: 0:00:12 (0.2047 s / it) +Averaged stats (hcp-val): loss: 0.8866 (0.8880) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 11:40:13 lr: 0.000115 grad: 0.0760 (0.0760) loss: 0.8710 (0.8710) time: 6.7222 data: 6.6266 max mem: 8299 +Train: [22] [ 100/6250] eta: 0:20:39 lr: 0.000115 grad: 0.0591 (0.0792) loss: 0.8806 (0.8886) time: 0.1309 data: 0.0247 max mem: 8299 +Train: [22] [ 200/6250] eta: 0:17:33 lr: 0.000115 grad: 0.0597 (0.0723) loss: 0.8835 (0.8864) time: 0.1520 data: 0.0593 max mem: 8299 +Train: [22] [ 300/6250] eta: 0:16:14 lr: 0.000115 grad: 0.0606 (0.0699) loss: 0.8829 (0.8854) time: 0.1590 data: 0.0654 max mem: 8299 +Train: [22] [ 400/6250] eta: 0:15:41 lr: 0.000115 grad: 0.0578 (0.0689) loss: 0.8790 (0.8849) time: 0.1529 data: 0.0497 max mem: 8299 +Train: [22] [ 500/6250] eta: 0:15:04 lr: 0.000115 grad: 0.0642 (0.0680) loss: 0.8778 (0.8841) time: 0.1560 data: 0.0606 max mem: 8299 +Train: [22] [ 600/6250] eta: 0:15:09 lr: 0.000115 grad: 0.0642 (0.0678) loss: 0.8798 (0.8833) time: 0.1528 data: 0.0729 max mem: 8299 +Train: [22] [ 700/6250] eta: 0:15:04 lr: 0.000115 grad: 0.0652 (0.0676) loss: 0.8768 (0.8825) time: 0.1688 data: 0.0880 max mem: 8299 +Train: [22] [ 800/6250] eta: 0:14:57 lr: 0.000115 grad: 0.0619 (0.0674) loss: 0.8873 (0.8821) time: 0.2222 data: 0.1392 max mem: 8299 +Train: [22] [ 900/6250] eta: 0:14:44 lr: 0.000115 grad: 0.0686 (0.0674) loss: 0.8756 (0.8818) time: 0.1908 data: 0.0888 max mem: 8299 +Train: [22] [1000/6250] eta: 0:14:26 lr: 0.000115 grad: 0.0620 (0.0674) loss: 0.8811 (0.8815) time: 0.1798 data: 0.1049 max mem: 8299 +Train: [22] [1100/6250] eta: 0:14:06 lr: 0.000115 grad: 0.0639 (0.0675) loss: 0.8816 (0.8814) time: 0.1717 data: 0.0927 max mem: 8299 +Train: [22] [1200/6250] eta: 0:13:43 lr: 0.000115 grad: 0.0635 (0.0676) loss: 0.8796 (0.8811) time: 0.1683 data: 0.0981 max mem: 8299 +Train: [22] [1300/6250] eta: 0:13:26 lr: 0.000115 grad: 0.0663 (0.0679) loss: 0.8761 (0.8808) time: 0.1728 data: 0.0964 max mem: 8299 +Train: [22] [1400/6250] eta: 0:13:09 lr: 0.000115 grad: 0.0620 (0.0678) loss: 0.8840 (0.8806) time: 0.2176 data: 0.1364 max mem: 8299 +Train: [22] [1500/6250] eta: 0:12:47 lr: 0.000115 grad: 0.0678 (0.0680) loss: 0.8792 (0.8804) time: 0.1548 data: 0.0791 max mem: 8299 +Train: [22] [1600/6250] eta: 0:12:31 lr: 0.000115 grad: 0.0676 (0.0683) loss: 0.8742 (0.8801) time: 0.1911 data: 0.1109 max mem: 8299 +Train: [22] [1700/6250] eta: 0:12:08 lr: 0.000115 grad: 0.0671 (0.0685) loss: 0.8806 (0.8799) time: 0.1532 data: 0.0756 max mem: 8299 +Train: [22] [1800/6250] eta: 0:11:50 lr: 0.000115 grad: 0.0625 (0.0685) loss: 0.8788 (0.8798) time: 0.1527 data: 0.0813 max mem: 8299 +Train: [22] [1900/6250] eta: 0:11:37 lr: 0.000115 grad: 0.0636 (0.0686) loss: 0.8765 (0.8797) time: 0.2027 data: 0.1391 max mem: 8299 +Train: [22] [2000/6250] eta: 0:11:20 lr: 0.000115 grad: 0.0697 (0.0687) loss: 0.8778 (0.8795) time: 0.1506 data: 0.0587 max mem: 8299 +Train: [22] [2100/6250] eta: 0:11:04 lr: 0.000115 grad: 0.0634 (0.0688) loss: 0.8793 (0.8794) time: 0.1493 data: 0.0720 max mem: 8299 +Train: [22] [2200/6250] eta: 0:10:51 lr: 0.000115 grad: 0.0623 (0.0688) loss: 0.8742 (0.8794) time: 0.2092 data: 0.1284 max mem: 8299 +Train: [22] [2300/6250] eta: 0:10:35 lr: 0.000115 grad: 0.0672 (0.0689) loss: 0.8792 (0.8792) time: 0.1564 data: 0.0808 max mem: 8299 +Train: [22] [2400/6250] eta: 0:10:19 lr: 0.000115 grad: 0.0737 (0.0689) loss: 0.8769 (0.8791) time: 0.1544 data: 0.0798 max mem: 8299 +Train: [22] [2500/6250] eta: 0:10:05 lr: 0.000115 grad: 0.0636 (0.0689) loss: 0.8754 (0.8791) time: 0.2008 data: 0.1101 max mem: 8299 +Train: [22] [2600/6250] eta: 0:09:50 lr: 0.000115 grad: 0.0618 (0.0689) loss: 0.8813 (0.8790) time: 0.1661 data: 0.0862 max mem: 8299 +Train: [22] [2700/6250] eta: 0:09:34 lr: 0.000115 grad: 0.0690 (0.0690) loss: 0.8766 (0.8790) time: 0.1660 data: 0.0826 max mem: 8299 +Train: [22] [2800/6250] eta: 0:09:17 lr: 0.000115 grad: 0.0671 (0.0689) loss: 0.8791 (0.8790) time: 0.1524 data: 0.0613 max mem: 8299 +Train: [22] [2900/6250] eta: 0:09:00 lr: 0.000115 grad: 0.0674 (0.0689) loss: 0.8786 (0.8790) time: 0.1650 data: 0.0879 max mem: 8299 +Train: [22] [3000/6250] eta: 0:08:45 lr: 0.000115 grad: 0.0679 (0.0689) loss: 0.8799 (0.8790) time: 0.1643 data: 0.0828 max mem: 8299 +Train: [22] [3100/6250] eta: 0:08:30 lr: 0.000115 grad: 0.0641 (0.0688) loss: 0.8770 (0.8789) time: 0.1733 data: 0.0876 max mem: 8299 +Train: [22] [3200/6250] eta: 0:08:13 lr: 0.000115 grad: 0.0682 (0.0689) loss: 0.8812 (0.8789) time: 0.1419 data: 0.0708 max mem: 8299 +Train: [22] [3300/6250] eta: 0:07:55 lr: 0.000115 grad: 0.0685 (0.0690) loss: 0.8743 (0.8788) time: 0.1358 data: 0.0565 max mem: 8299 +Train: [22] [3400/6250] eta: 0:07:40 lr: 0.000115 grad: 0.0654 (0.0691) loss: 0.8796 (0.8787) time: 0.1791 data: 0.0858 max mem: 8299 +Train: [22] [3500/6250] eta: 0:07:24 lr: 0.000115 grad: 0.0670 (0.0690) loss: 0.8784 (0.8786) time: 0.1050 data: 0.0257 max mem: 8299 +Train: [22] [3600/6250] eta: 0:07:07 lr: 0.000115 grad: 0.0663 (0.0691) loss: 0.8742 (0.8785) time: 0.1502 data: 0.0516 max mem: 8299 +Train: [22] [3700/6250] eta: 0:06:50 lr: 0.000115 grad: 0.0635 (0.0691) loss: 0.8759 (0.8784) time: 0.1383 data: 0.0557 max mem: 8299 +Train: [22] [3800/6250] eta: 0:06:33 lr: 0.000115 grad: 0.0702 (0.0691) loss: 0.8770 (0.8783) time: 0.1418 data: 0.0584 max mem: 8299 +Train: [22] [3900/6250] eta: 0:06:17 lr: 0.000115 grad: 0.0739 (0.0692) loss: 0.8753 (0.8782) time: 0.1725 data: 0.0992 max mem: 8299 +Train: [22] [4000/6250] eta: 0:06:02 lr: 0.000115 grad: 0.0659 (0.0693) loss: 0.8778 (0.8780) time: 0.1677 data: 0.0955 max mem: 8299 +Train: [22] [4100/6250] eta: 0:05:46 lr: 0.000115 grad: 0.0631 (0.0693) loss: 0.8741 (0.8779) time: 0.1467 data: 0.0802 max mem: 8299 +Train: [22] [4200/6250] eta: 0:05:31 lr: 0.000115 grad: 0.0627 (0.0693) loss: 0.8745 (0.8778) time: 0.1852 data: 0.1088 max mem: 8299 +Train: [22] [4300/6250] eta: 0:05:15 lr: 0.000115 grad: 0.0653 (0.0693) loss: 0.8787 (0.8778) time: 0.2190 data: 0.1506 max mem: 8299 +Train: [22] [4400/6250] eta: 0:05:00 lr: 0.000115 grad: 0.0656 (0.0695) loss: 0.8773 (0.8776) time: 0.1788 data: 0.1019 max mem: 8299 +Train: [22] [4500/6250] eta: 0:04:45 lr: 0.000115 grad: 0.0661 (0.0695) loss: 0.8703 (0.8775) time: 0.2315 data: 0.1648 max mem: 8299 +Train: [22] [4600/6250] eta: 0:04:30 lr: 0.000115 grad: 0.0628 (0.0696) loss: 0.8776 (0.8774) time: 0.1987 data: 0.1242 max mem: 8299 +Train: [22] [4700/6250] eta: 0:04:14 lr: 0.000115 grad: 0.0614 (0.0696) loss: 0.8741 (0.8773) time: 0.1631 data: 0.0914 max mem: 8299 +Train: [22] [4800/6250] eta: 0:03:58 lr: 0.000115 grad: 0.0668 (0.0697) loss: 0.8737 (0.8772) time: 0.1789 data: 0.0988 max mem: 8299 +Train: [22] [4900/6250] eta: 0:03:43 lr: 0.000114 grad: 0.0665 (0.0697) loss: 0.8803 (0.8772) time: 0.1574 data: 0.0831 max mem: 8299 +Train: [22] [5000/6250] eta: 0:03:26 lr: 0.000114 grad: 0.0732 (0.0697) loss: 0.8760 (0.8771) time: 0.1659 data: 0.0911 max mem: 8299 +Train: [22] [5100/6250] eta: 0:03:09 lr: 0.000114 grad: 0.0684 (0.0697) loss: 0.8709 (0.8771) time: 0.1893 data: 0.1158 max mem: 8299 +Train: [22] [5200/6250] eta: 0:02:53 lr: 0.000114 grad: 0.0629 (0.0699) loss: 0.8743 (0.8770) time: 0.1861 data: 0.1090 max mem: 8299 +Train: [22] [5300/6250] eta: 0:02:36 lr: 0.000114 grad: 0.0651 (0.0699) loss: 0.8684 (0.8770) time: 0.1404 data: 0.0646 max mem: 8299 +Train: [22] [5400/6250] eta: 0:02:19 lr: 0.000114 grad: 0.0657 (0.0700) loss: 0.8681 (0.8769) time: 0.1218 data: 0.0499 max mem: 8299 +Train: [22] [5500/6250] eta: 0:02:03 lr: 0.000114 grad: 0.0632 (0.0700) loss: 0.8763 (0.8769) time: 0.1595 data: 0.0860 max mem: 8299 +Train: [22] [5600/6250] eta: 0:01:46 lr: 0.000114 grad: 0.0743 (0.0700) loss: 0.8763 (0.8769) time: 0.1670 data: 0.0896 max mem: 8299 +Train: [22] [5700/6250] eta: 0:01:30 lr: 0.000114 grad: 0.0643 (0.0701) loss: 0.8785 (0.8769) time: 0.1650 data: 0.0821 max mem: 8299 +Train: [22] [5800/6250] eta: 0:01:13 lr: 0.000114 grad: 0.0640 (0.0701) loss: 0.8697 (0.8769) time: 0.1767 data: 0.0975 max mem: 8299 +Train: [22] [5900/6250] eta: 0:00:57 lr: 0.000114 grad: 0.0709 (0.0701) loss: 0.8769 (0.8769) time: 0.1829 data: 0.0963 max mem: 8299 +Train: [22] [6000/6250] eta: 0:00:41 lr: 0.000114 grad: 0.0685 (0.0701) loss: 0.8763 (0.8768) time: 0.1515 data: 0.0639 max mem: 8299 +Train: [22] [6100/6250] eta: 0:00:24 lr: 0.000114 grad: 0.0622 (0.0701) loss: 0.8782 (0.8768) time: 0.1924 data: 0.1065 max mem: 8299 +Train: [22] [6200/6250] eta: 0:00:08 lr: 0.000114 grad: 0.0666 (0.0701) loss: 0.8765 (0.8768) time: 0.1369 data: 0.0556 max mem: 8299 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0718 (0.0701) loss: 0.8806 (0.8768) time: 0.1423 data: 0.0617 max mem: 8299 +Train: [22] Total time: 0:17:13 (0.1653 s / it) +Averaged stats: lr: 0.000114 grad: 0.0718 (0.0701) loss: 0.8806 (0.8768) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:04:40 loss: 0.9037 (0.9037) time: 4.5205 data: 4.4878 max mem: 8299 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8909 (0.8911) time: 0.1329 data: 0.1083 max mem: 8299 +Eval (hcp-train-subset): [22] Total time: 0:00:12 (0.2065 s / it) +Averaged stats (hcp-train-subset): loss: 0.8909 (0.8911) +Eval (hcp-val): [22] [ 0/62] eta: 0:04:08 loss: 0.8858 (0.8858) time: 4.0112 data: 3.9238 max mem: 8299 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8866 (0.8876) time: 0.1176 data: 0.0934 max mem: 8299 +Eval (hcp-val): [22] Total time: 0:00:13 (0.2139 s / it) +Averaged stats (hcp-val): loss: 0.8866 (0.8876) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 9:37:40 lr: 0.000114 grad: 0.0535 (0.0535) loss: 0.9019 (0.9019) time: 5.5456 data: 5.4056 max mem: 8299 +Train: [23] [ 100/6250] eta: 0:21:07 lr: 0.000114 grad: 0.0687 (0.0714) loss: 0.8912 (0.8922) time: 0.1706 data: 0.0559 max mem: 8299 +Train: [23] [ 200/6250] eta: 0:18:41 lr: 0.000114 grad: 0.0685 (0.0719) loss: 0.8769 (0.8876) time: 0.1536 data: 0.0445 max mem: 8299 +Train: [23] [ 300/6250] eta: 0:16:55 lr: 0.000114 grad: 0.0611 (0.0717) loss: 0.8846 (0.8845) time: 0.1448 data: 0.0458 max mem: 8299 +Train: [23] [ 400/6250] eta: 0:16:02 lr: 0.000114 grad: 0.0618 (0.0710) loss: 0.8850 (0.8833) time: 0.1428 data: 0.0419 max mem: 8299 +Train: [23] [ 500/6250] eta: 0:15:13 lr: 0.000114 grad: 0.0599 (0.0698) loss: 0.8786 (0.8827) time: 0.1223 data: 0.0367 max mem: 8299 +Train: [23] [ 600/6250] eta: 0:14:48 lr: 0.000114 grad: 0.0562 (0.0688) loss: 0.8892 (0.8825) time: 0.1750 data: 0.0893 max mem: 8299 +Train: [23] [ 700/6250] eta: 0:14:48 lr: 0.000114 grad: 0.0606 (0.0681) loss: 0.8826 (0.8824) time: 0.1639 data: 0.0790 max mem: 8299 +Train: [23] [ 800/6250] eta: 0:14:45 lr: 0.000114 grad: 0.0611 (0.0678) loss: 0.8798 (0.8818) time: 0.1489 data: 0.0318 max mem: 8299 +Train: [23] [ 900/6250] eta: 0:14:29 lr: 0.000114 grad: 0.0585 (0.0675) loss: 0.8803 (0.8812) time: 0.1364 data: 0.0483 max mem: 8299 +Train: [23] [1000/6250] eta: 0:14:10 lr: 0.000114 grad: 0.0645 (0.0672) loss: 0.8860 (0.8810) time: 0.1412 data: 0.0610 max mem: 8299 +Train: [23] [1100/6250] eta: 0:13:47 lr: 0.000114 grad: 0.0676 (0.0670) loss: 0.8716 (0.8806) time: 0.1447 data: 0.0638 max mem: 8299 +Train: [23] [1200/6250] eta: 0:13:28 lr: 0.000114 grad: 0.0648 (0.0670) loss: 0.8795 (0.8800) time: 0.1635 data: 0.0877 max mem: 8299 +Train: [23] [1300/6250] eta: 0:13:09 lr: 0.000114 grad: 0.0627 (0.0670) loss: 0.8792 (0.8796) time: 0.1506 data: 0.0741 max mem: 8299 +Train: [23] [1400/6250] eta: 0:12:51 lr: 0.000114 grad: 0.0674 (0.0672) loss: 0.8720 (0.8791) time: 0.1612 data: 0.0825 max mem: 8299 +Train: [23] [1500/6250] eta: 0:12:33 lr: 0.000114 grad: 0.0601 (0.0673) loss: 0.8759 (0.8787) time: 0.1491 data: 0.0747 max mem: 8299 +Train: [23] [1600/6250] eta: 0:12:17 lr: 0.000114 grad: 0.0672 (0.0674) loss: 0.8765 (0.8783) time: 0.1804 data: 0.1005 max mem: 8299 +Train: [23] [1700/6250] eta: 0:12:09 lr: 0.000114 grad: 0.0661 (0.0675) loss: 0.8737 (0.8780) time: 0.2704 data: 0.1905 max mem: 8299 +Train: [23] [1800/6250] eta: 0:11:46 lr: 0.000114 grad: 0.0718 (0.0677) loss: 0.8675 (0.8776) time: 0.1625 data: 0.0776 max mem: 8299 +Train: [23] [1900/6250] eta: 0:11:29 lr: 0.000114 grad: 0.0642 (0.0679) loss: 0.8744 (0.8772) time: 0.1516 data: 0.0744 max mem: 8299 +Train: [23] [2000/6250] eta: 0:11:12 lr: 0.000114 grad: 0.0649 (0.0680) loss: 0.8700 (0.8770) time: 0.1535 data: 0.0661 max mem: 8299 +Train: [23] [2100/6250] eta: 0:10:57 lr: 0.000114 grad: 0.0682 (0.0682) loss: 0.8735 (0.8767) time: 0.1750 data: 0.0901 max mem: 8299 +Train: [23] [2200/6250] eta: 0:10:41 lr: 0.000114 grad: 0.0684 (0.0682) loss: 0.8779 (0.8766) time: 0.1513 data: 0.0701 max mem: 8299 +Train: [23] [2300/6250] eta: 0:10:24 lr: 0.000114 grad: 0.0687 (0.0684) loss: 0.8774 (0.8765) time: 0.1367 data: 0.0458 max mem: 8299 +Train: [23] [2400/6250] eta: 0:10:07 lr: 0.000114 grad: 0.0681 (0.0685) loss: 0.8741 (0.8765) time: 0.1592 data: 0.0743 max mem: 8299 +Train: [23] [2500/6250] eta: 0:09:49 lr: 0.000114 grad: 0.0641 (0.0684) loss: 0.8746 (0.8765) time: 0.1411 data: 0.0587 max mem: 8299 +Train: [23] [2600/6250] eta: 0:09:33 lr: 0.000114 grad: 0.0632 (0.0684) loss: 0.8779 (0.8765) time: 0.1715 data: 0.0949 max mem: 8299 +Train: [23] [2700/6250] eta: 0:09:17 lr: 0.000114 grad: 0.0692 (0.0686) loss: 0.8736 (0.8765) time: 0.1566 data: 0.0746 max mem: 8299 +Train: [23] [2800/6250] eta: 0:09:02 lr: 0.000114 grad: 0.0642 (0.0687) loss: 0.8764 (0.8765) time: 0.1165 data: 0.0287 max mem: 8299 +Train: [23] [2900/6250] eta: 0:08:46 lr: 0.000114 grad: 0.0658 (0.0688) loss: 0.8756 (0.8765) time: 0.1482 data: 0.0678 max mem: 8299 +Train: [23] [3000/6250] eta: 0:08:31 lr: 0.000114 grad: 0.0621 (0.0688) loss: 0.8785 (0.8765) time: 0.1590 data: 0.0810 max mem: 8299 +Train: [23] [3100/6250] eta: 0:08:15 lr: 0.000114 grad: 0.0675 (0.0688) loss: 0.8813 (0.8766) time: 0.1479 data: 0.0636 max mem: 8299 +Train: [23] [3200/6250] eta: 0:08:00 lr: 0.000114 grad: 0.0643 (0.0688) loss: 0.8782 (0.8766) time: 0.1892 data: 0.1078 max mem: 8299 +Train: [23] [3300/6250] eta: 0:07:44 lr: 0.000114 grad: 0.0700 (0.0689) loss: 0.8821 (0.8765) time: 0.1625 data: 0.0801 max mem: 8299 +Train: [23] [3400/6250] eta: 0:07:28 lr: 0.000114 grad: 0.0668 (0.0689) loss: 0.8823 (0.8765) time: 0.1307 data: 0.0493 max mem: 8299 +Train: [23] [3500/6250] eta: 0:07:12 lr: 0.000114 grad: 0.0687 (0.0690) loss: 0.8686 (0.8765) time: 0.1649 data: 0.0884 max mem: 8299 +Train: [23] [3600/6250] eta: 0:06:56 lr: 0.000114 grad: 0.0678 (0.0690) loss: 0.8756 (0.8765) time: 0.1441 data: 0.0634 max mem: 8299 +Train: [23] [3700/6250] eta: 0:06:41 lr: 0.000114 grad: 0.0637 (0.0691) loss: 0.8806 (0.8765) time: 0.1629 data: 0.0766 max mem: 8299 +Train: [23] [3800/6250] eta: 0:06:25 lr: 0.000114 grad: 0.0643 (0.0690) loss: 0.8796 (0.8766) time: 0.1390 data: 0.0535 max mem: 8299 +Train: [23] [3900/6250] eta: 0:06:09 lr: 0.000114 grad: 0.0671 (0.0691) loss: 0.8724 (0.8766) time: 0.1357 data: 0.0521 max mem: 8299 +Train: [23] [4000/6250] eta: 0:05:54 lr: 0.000113 grad: 0.0721 (0.0691) loss: 0.8743 (0.8765) time: 0.1279 data: 0.0447 max mem: 8299 +Train: [23] [4100/6250] eta: 0:05:39 lr: 0.000113 grad: 0.0667 (0.0692) loss: 0.8783 (0.8766) time: 0.2130 data: 0.1384 max mem: 8299 +Train: [23] [4200/6250] eta: 0:05:24 lr: 0.000113 grad: 0.0665 (0.0693) loss: 0.8750 (0.8766) time: 0.1774 data: 0.1028 max mem: 8299 +Train: [23] [4300/6250] eta: 0:05:09 lr: 0.000113 grad: 0.0703 (0.0693) loss: 0.8759 (0.8765) time: 0.1462 data: 0.0724 max mem: 8299 +Train: [23] [4400/6250] eta: 0:04:54 lr: 0.000113 grad: 0.0678 (0.0694) loss: 0.8738 (0.8765) time: 0.1753 data: 0.1039 max mem: 8299 +Train: [23] [4500/6250] eta: 0:04:39 lr: 0.000113 grad: 0.0661 (0.0695) loss: 0.8733 (0.8764) time: 0.1630 data: 0.0892 max mem: 8299 +Train: [23] [4600/6250] eta: 0:04:23 lr: 0.000113 grad: 0.0745 (0.0695) loss: 0.8704 (0.8764) time: 0.1698 data: 0.0855 max mem: 8299 +Train: [23] [4700/6250] eta: 0:04:08 lr: 0.000113 grad: 0.0638 (0.0695) loss: 0.8750 (0.8764) time: 0.1799 data: 0.1084 max mem: 8299 +Train: [23] [4800/6250] eta: 0:03:52 lr: 0.000113 grad: 0.0735 (0.0696) loss: 0.8741 (0.8764) time: 0.1862 data: 0.1041 max mem: 8299 +Train: [23] [4900/6250] eta: 0:03:36 lr: 0.000113 grad: 0.0674 (0.0696) loss: 0.8754 (0.8763) time: 0.1578 data: 0.0792 max mem: 8299 +Train: [23] [5000/6250] eta: 0:03:20 lr: 0.000113 grad: 0.0670 (0.0697) loss: 0.8768 (0.8763) time: 0.1693 data: 0.0904 max mem: 8299 +Train: [23] [5100/6250] eta: 0:03:04 lr: 0.000113 grad: 0.0724 (0.0698) loss: 0.8761 (0.8763) time: 0.1715 data: 0.0861 max mem: 8299 +Train: [23] [5200/6250] eta: 0:02:48 lr: 0.000113 grad: 0.0697 (0.0699) loss: 0.8746 (0.8763) time: 0.1485 data: 0.0692 max mem: 8299 +Train: [23] [5300/6250] eta: 0:02:32 lr: 0.000113 grad: 0.0707 (0.0701) loss: 0.8778 (0.8763) time: 0.1418 data: 0.0654 max mem: 8299 +Train: [23] [5400/6250] eta: 0:02:16 lr: 0.000113 grad: 0.0655 (0.0703) loss: 0.8741 (0.8762) time: 0.1396 data: 0.0690 max mem: 8299 +Train: [23] [5500/6250] eta: 0:01:59 lr: 0.000113 grad: 0.0708 (0.0704) loss: 0.8773 (0.8762) time: 0.1525 data: 0.0753 max mem: 8299 +Train: [23] [5600/6250] eta: 0:01:43 lr: 0.000113 grad: 0.0742 (0.0705) loss: 0.8748 (0.8761) time: 0.1179 data: 0.0404 max mem: 8299 +Train: [23] [5700/6250] eta: 0:01:27 lr: 0.000113 grad: 0.0661 (0.0706) loss: 0.8709 (0.8761) time: 0.1211 data: 0.0491 max mem: 8299 +Train: [23] [5800/6250] eta: 0:01:11 lr: 0.000113 grad: 0.0666 (0.0707) loss: 0.8725 (0.8760) time: 0.1559 data: 0.0759 max mem: 8299 +Train: [23] [5900/6250] eta: 0:00:55 lr: 0.000113 grad: 0.0703 (0.0707) loss: 0.8762 (0.8760) time: 0.1603 data: 0.0804 max mem: 8299 +Train: [23] [6000/6250] eta: 0:00:39 lr: 0.000113 grad: 0.0731 (0.0708) loss: 0.8759 (0.8759) time: 0.1811 data: 0.0763 max mem: 8299 +Train: [23] [6100/6250] eta: 0:00:23 lr: 0.000113 grad: 0.0711 (0.0708) loss: 0.8756 (0.8759) time: 0.1622 data: 0.0696 max mem: 8299 +Train: [23] [6200/6250] eta: 0:00:07 lr: 0.000113 grad: 0.0648 (0.0709) loss: 0.8754 (0.8759) time: 0.1630 data: 0.0812 max mem: 8299 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0671 (0.0708) loss: 0.8806 (0.8759) time: 0.1594 data: 0.0789 max mem: 8299 +Train: [23] Total time: 0:16:40 (0.1600 s / it) +Averaged stats: lr: 0.000113 grad: 0.0671 (0.0708) loss: 0.8806 (0.8759) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:03:25 loss: 0.9047 (0.9047) time: 3.3084 data: 3.2515 max mem: 8299 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8925 (0.8932) time: 0.1257 data: 0.1011 max mem: 8299 +Eval (hcp-train-subset): [23] Total time: 0:00:13 (0.2245 s / it) +Averaged stats (hcp-train-subset): loss: 0.8925 (0.8932) +Eval (hcp-val): [23] [ 0/62] eta: 0:06:00 loss: 0.8902 (0.8902) time: 5.8111 data: 5.7801 max mem: 8299 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8881 (0.8895) time: 0.1058 data: 0.0808 max mem: 8299 +Eval (hcp-val): [23] Total time: 0:00:13 (0.2151 s / it) +Averaged stats (hcp-val): loss: 0.8881 (0.8895) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 7:11:09 lr: 0.000113 grad: 0.0352 (0.0352) loss: 0.9126 (0.9126) time: 4.1392 data: 3.8002 max mem: 8299 +Train: [24] [ 100/6250] eta: 0:20:10 lr: 0.000113 grad: 0.0585 (0.0632) loss: 0.8890 (0.8951) time: 0.1278 data: 0.0158 max mem: 8299 +Train: [24] [ 200/6250] eta: 0:17:40 lr: 0.000113 grad: 0.0699 (0.0647) loss: 0.8766 (0.8893) time: 0.1597 data: 0.0577 max mem: 8299 +Train: [24] [ 300/6250] eta: 0:16:23 lr: 0.000113 grad: 0.0611 (0.0649) loss: 0.8799 (0.8871) time: 0.1403 data: 0.0471 max mem: 8299 +Train: [24] [ 400/6250] eta: 0:15:55 lr: 0.000113 grad: 0.0677 (0.0656) loss: 0.8701 (0.8845) time: 0.1886 data: 0.0969 max mem: 8299 +Train: [24] [ 500/6250] eta: 0:15:44 lr: 0.000113 grad: 0.0585 (0.0656) loss: 0.8849 (0.8834) time: 0.1565 data: 0.0654 max mem: 8299 +Train: [24] [ 600/6250] eta: 0:15:26 lr: 0.000113 grad: 0.0629 (0.0653) loss: 0.8776 (0.8826) time: 0.1522 data: 0.0626 max mem: 8299 +Train: [24] [ 700/6250] eta: 0:15:20 lr: 0.000113 grad: 0.0705 (0.0657) loss: 0.8747 (0.8817) time: 0.2141 data: 0.1297 max mem: 8299 +Train: [24] [ 800/6250] eta: 0:14:58 lr: 0.000113 grad: 0.0643 (0.0659) loss: 0.8772 (0.8811) time: 0.1527 data: 0.0662 max mem: 8299 +Train: [24] [ 900/6250] eta: 0:14:47 lr: 0.000113 grad: 0.0687 (0.0662) loss: 0.8791 (0.8804) time: 0.1441 data: 0.0652 max mem: 8299 +Train: [24] [1000/6250] eta: 0:14:21 lr: 0.000113 grad: 0.0614 (0.0662) loss: 0.8746 (0.8798) time: 0.1407 data: 0.0468 max mem: 8299 +Train: [24] [1100/6250] eta: 0:14:00 lr: 0.000113 grad: 0.0634 (0.0661) loss: 0.8737 (0.8793) time: 0.1528 data: 0.0713 max mem: 8299 +Train: [24] [1200/6250] eta: 0:13:37 lr: 0.000113 grad: 0.0641 (0.0661) loss: 0.8766 (0.8790) time: 0.1484 data: 0.0606 max mem: 8299 +Train: [24] [1300/6250] eta: 0:13:21 lr: 0.000113 grad: 0.0687 (0.0660) loss: 0.8717 (0.8787) time: 0.1943 data: 0.1109 max mem: 8299 +Train: [24] [1400/6250] eta: 0:13:00 lr: 0.000113 grad: 0.0584 (0.0660) loss: 0.8781 (0.8785) time: 0.1474 data: 0.0693 max mem: 8299 +Train: [24] [1500/6250] eta: 0:12:38 lr: 0.000113 grad: 0.0638 (0.0661) loss: 0.8736 (0.8782) time: 0.1605 data: 0.0763 max mem: 8299 +Train: [24] [1600/6250] eta: 0:12:25 lr: 0.000113 grad: 0.0600 (0.0661) loss: 0.8761 (0.8781) time: 0.1921 data: 0.1116 max mem: 8299 +Train: [24] [1700/6250] eta: 0:12:05 lr: 0.000113 grad: 0.0659 (0.0661) loss: 0.8736 (0.8779) time: 0.1766 data: 0.0942 max mem: 8299 +Train: [24] [1800/6250] eta: 0:11:48 lr: 0.000113 grad: 0.0625 (0.0661) loss: 0.8771 (0.8778) time: 0.2020 data: 0.1287 max mem: 8299 +Train: [24] [1900/6250] eta: 0:11:32 lr: 0.000113 grad: 0.0681 (0.0662) loss: 0.8747 (0.8776) time: 0.1646 data: 0.0901 max mem: 8299 +Train: [24] [2000/6250] eta: 0:11:14 lr: 0.000113 grad: 0.0606 (0.0662) loss: 0.8760 (0.8776) time: 0.1526 data: 0.0741 max mem: 8299 +Train: [24] [2100/6250] eta: 0:10:58 lr: 0.000113 grad: 0.0716 (0.0662) loss: 0.8751 (0.8776) time: 0.1921 data: 0.1058 max mem: 8299 +Train: [24] [2200/6250] eta: 0:10:39 lr: 0.000113 grad: 0.0657 (0.0663) loss: 0.8781 (0.8775) time: 0.1395 data: 0.0467 max mem: 8299 +Train: [24] [2300/6250] eta: 0:10:21 lr: 0.000113 grad: 0.0654 (0.0664) loss: 0.8773 (0.8775) time: 0.1543 data: 0.0757 max mem: 8299 +Train: [24] [2400/6250] eta: 0:10:04 lr: 0.000113 grad: 0.0721 (0.0666) loss: 0.8802 (0.8774) time: 0.1635 data: 0.0782 max mem: 8299 +Train: [24] [2500/6250] eta: 0:09:46 lr: 0.000113 grad: 0.0687 (0.0667) loss: 0.8738 (0.8773) time: 0.1531 data: 0.0718 max mem: 8299 +Train: [24] [2600/6250] eta: 0:09:29 lr: 0.000113 grad: 0.0725 (0.0670) loss: 0.8783 (0.8772) time: 0.1248 data: 0.0516 max mem: 8299 +Train: [24] [2700/6250] eta: 0:09:13 lr: 0.000113 grad: 0.0731 (0.0672) loss: 0.8736 (0.8771) time: 0.1623 data: 0.0779 max mem: 8299 +Train: [24] [2800/6250] eta: 0:08:58 lr: 0.000113 grad: 0.0658 (0.0673) loss: 0.8750 (0.8770) time: 0.1673 data: 0.0945 max mem: 8299 +Train: [24] [2900/6250] eta: 0:08:42 lr: 0.000112 grad: 0.0680 (0.0675) loss: 0.8757 (0.8769) time: 0.1807 data: 0.1004 max mem: 8299 +Train: [24] [3000/6250] eta: 0:08:26 lr: 0.000112 grad: 0.0741 (0.0677) loss: 0.8674 (0.8768) time: 0.1416 data: 0.0633 max mem: 8299 +Train: [24] [3100/6250] eta: 0:08:10 lr: 0.000112 grad: 0.0717 (0.0678) loss: 0.8746 (0.8767) time: 0.1514 data: 0.0633 max mem: 8299 +Train: [24] [3200/6250] eta: 0:07:55 lr: 0.000112 grad: 0.0721 (0.0679) loss: 0.8692 (0.8766) time: 0.1605 data: 0.0809 max mem: 8299 +Train: [24] [3300/6250] eta: 0:07:39 lr: 0.000112 grad: 0.0664 (0.0679) loss: 0.8693 (0.8765) time: 0.1644 data: 0.0760 max mem: 8299 +Train: [24] [3400/6250] eta: 0:07:22 lr: 0.000112 grad: 0.0698 (0.0680) loss: 0.8736 (0.8764) time: 0.1339 data: 0.0528 max mem: 8299 +Train: [24] [3500/6250] eta: 0:07:07 lr: 0.000112 grad: 0.0696 (0.0681) loss: 0.8639 (0.8762) time: 0.1573 data: 0.0843 max mem: 8299 +Train: [24] [3600/6250] eta: 0:06:52 lr: 0.000112 grad: 0.0704 (0.0682) loss: 0.8688 (0.8761) time: 0.1552 data: 0.0825 max mem: 8299 +Train: [24] [3700/6250] eta: 0:06:37 lr: 0.000112 grad: 0.0635 (0.0682) loss: 0.8725 (0.8760) time: 0.1634 data: 0.0782 max mem: 8299 +Train: [24] [3800/6250] eta: 0:06:20 lr: 0.000112 grad: 0.0705 (0.0683) loss: 0.8715 (0.8760) time: 0.1488 data: 0.0591 max mem: 8299 +Train: [24] [3900/6250] eta: 0:06:04 lr: 0.000112 grad: 0.0641 (0.0683) loss: 0.8750 (0.8759) time: 0.1260 data: 0.0489 max mem: 8299 +Train: [24] [4000/6250] eta: 0:05:49 lr: 0.000112 grad: 0.0687 (0.0683) loss: 0.8724 (0.8759) time: 0.1560 data: 0.0707 max mem: 8299 +Train: [24] [4100/6250] eta: 0:05:33 lr: 0.000112 grad: 0.0661 (0.0685) loss: 0.8708 (0.8758) time: 0.1800 data: 0.1017 max mem: 8299 +Train: [24] [4200/6250] eta: 0:05:17 lr: 0.000112 grad: 0.0630 (0.0685) loss: 0.8800 (0.8759) time: 0.1325 data: 0.0497 max mem: 8299 +Train: [24] [4300/6250] eta: 0:05:02 lr: 0.000112 grad: 0.0642 (0.0684) loss: 0.8773 (0.8758) time: 0.1806 data: 0.0968 max mem: 8299 +Train: [24] [4400/6250] eta: 0:04:47 lr: 0.000112 grad: 0.0644 (0.0684) loss: 0.8763 (0.8758) time: 0.1645 data: 0.0965 max mem: 8299 +Train: [24] [4500/6250] eta: 0:04:31 lr: 0.000112 grad: 0.0744 (0.0685) loss: 0.8697 (0.8759) time: 0.1466 data: 0.0661 max mem: 8299 +Train: [24] [4600/6250] eta: 0:04:16 lr: 0.000112 grad: 0.0680 (0.0685) loss: 0.8811 (0.8759) time: 0.1784 data: 0.0976 max mem: 8299 +Train: [24] [4700/6250] eta: 0:04:01 lr: 0.000112 grad: 0.0620 (0.0685) loss: 0.8773 (0.8759) time: 0.1587 data: 0.0724 max mem: 8299 +Train: [24] [4800/6250] eta: 0:03:45 lr: 0.000112 grad: 0.0662 (0.0686) loss: 0.8718 (0.8759) time: 0.1426 data: 0.0544 max mem: 8299 +Train: [24] [4900/6250] eta: 0:03:29 lr: 0.000112 grad: 0.0739 (0.0686) loss: 0.8722 (0.8758) time: 0.1486 data: 0.0611 max mem: 8299 +Train: [24] [5000/6250] eta: 0:03:14 lr: 0.000112 grad: 0.0654 (0.0686) loss: 0.8797 (0.8759) time: 0.1868 data: 0.1171 max mem: 8299 +Train: [24] [5100/6250] eta: 0:02:58 lr: 0.000112 grad: 0.0612 (0.0686) loss: 0.8795 (0.8759) time: 0.1332 data: 0.0576 max mem: 8299 +Train: [24] [5200/6250] eta: 0:02:43 lr: 0.000112 grad: 0.0671 (0.0686) loss: 0.8774 (0.8759) time: 0.1416 data: 0.0542 max mem: 8299 +Train: [24] [5300/6250] eta: 0:02:27 lr: 0.000112 grad: 0.0691 (0.0686) loss: 0.8769 (0.8760) time: 0.1672 data: 0.0833 max mem: 8299 +Train: [24] [5400/6250] eta: 0:02:12 lr: 0.000112 grad: 0.0681 (0.0687) loss: 0.8790 (0.8760) time: 0.1337 data: 0.0576 max mem: 8299 +Train: [24] [5500/6250] eta: 0:01:56 lr: 0.000112 grad: 0.0682 (0.0687) loss: 0.8822 (0.8760) time: 0.1535 data: 0.0795 max mem: 8299 +Train: [24] [5600/6250] eta: 0:01:40 lr: 0.000112 grad: 0.0630 (0.0688) loss: 0.8824 (0.8760) time: 0.1435 data: 0.0574 max mem: 8299 +Train: [24] [5700/6250] eta: 0:01:25 lr: 0.000112 grad: 0.0679 (0.0688) loss: 0.8721 (0.8760) time: 0.1566 data: 0.0734 max mem: 8299 +Train: [24] [5800/6250] eta: 0:01:10 lr: 0.000112 grad: 0.0651 (0.0689) loss: 0.8788 (0.8761) time: 0.1415 data: 0.0520 max mem: 8299 +Train: [24] [5900/6250] eta: 0:00:54 lr: 0.000112 grad: 0.0679 (0.0689) loss: 0.8763 (0.8761) time: 0.1406 data: 0.0598 max mem: 8299 +Train: [24] [6000/6250] eta: 0:00:38 lr: 0.000112 grad: 0.0633 (0.0689) loss: 0.8831 (0.8762) time: 0.1834 data: 0.0967 max mem: 8299 +Train: [24] [6100/6250] eta: 0:00:23 lr: 0.000112 grad: 0.0668 (0.0689) loss: 0.8774 (0.8762) time: 0.1501 data: 0.0566 max mem: 8299 +Train: [24] [6200/6250] eta: 0:00:07 lr: 0.000112 grad: 0.0673 (0.0689) loss: 0.8756 (0.8762) time: 0.1641 data: 0.0806 max mem: 8299 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0640 (0.0689) loss: 0.8729 (0.8762) time: 0.1420 data: 0.0532 max mem: 8299 +Train: [24] Total time: 0:16:19 (0.1568 s / it) +Averaged stats: lr: 0.000112 grad: 0.0640 (0.0689) loss: 0.8729 (0.8762) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:05:20 loss: 0.9005 (0.9005) time: 5.1703 data: 5.1393 max mem: 8299 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8927 (0.8906) time: 0.1339 data: 0.1089 max mem: 8299 +Eval (hcp-train-subset): [24] Total time: 0:00:13 (0.2158 s / it) +Averaged stats (hcp-train-subset): loss: 0.8927 (0.8906) +Making plots (hcp-train-subset): example=34 +Eval (hcp-val): [24] [ 0/62] eta: 0:03:37 loss: 0.8863 (0.8863) time: 3.5096 data: 3.4318 max mem: 8299 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8877 (0.8880) time: 0.1068 data: 0.0824 max mem: 8299 +Eval (hcp-val): [24] Total time: 0:00:13 (0.2109 s / it) +Averaged stats (hcp-val): loss: 0.8877 (0.8880) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 10:36:33 lr: 0.000112 grad: 0.0449 (0.0449) loss: 0.8891 (0.8891) time: 6.1109 data: 5.9787 max mem: 8299 +Train: [25] [ 100/6250] eta: 0:21:28 lr: 0.000112 grad: 0.0649 (0.0713) loss: 0.8812 (0.8811) time: 0.1678 data: 0.0706 max mem: 8299 +Train: [25] [ 200/6250] eta: 0:18:33 lr: 0.000112 grad: 0.0636 (0.0679) loss: 0.8678 (0.8801) time: 0.1580 data: 0.0610 max mem: 8299 +Train: [25] [ 300/6250] eta: 0:16:53 lr: 0.000112 grad: 0.0620 (0.0669) loss: 0.8770 (0.8792) time: 0.1439 data: 0.0594 max mem: 8299 +Train: [25] [ 400/6250] eta: 0:15:48 lr: 0.000112 grad: 0.0577 (0.0670) loss: 0.8812 (0.8782) time: 0.1424 data: 0.0512 max mem: 8299 +Train: [25] [ 500/6250] eta: 0:15:07 lr: 0.000112 grad: 0.0587 (0.0669) loss: 0.8776 (0.8782) time: 0.1138 data: 0.0201 max mem: 8299 +Train: [25] [ 600/6250] eta: 0:14:49 lr: 0.000112 grad: 0.0569 (0.0664) loss: 0.8755 (0.8778) time: 0.1590 data: 0.0693 max mem: 8299 +Train: [25] [ 700/6250] eta: 0:14:35 lr: 0.000112 grad: 0.0667 (0.0663) loss: 0.8750 (0.8777) time: 0.1776 data: 0.0849 max mem: 8299 +Train: [25] [ 800/6250] eta: 0:14:25 lr: 0.000112 grad: 0.0663 (0.0663) loss: 0.8807 (0.8779) time: 0.1980 data: 0.1127 max mem: 8299 +Train: [25] [ 900/6250] eta: 0:14:13 lr: 0.000112 grad: 0.0669 (0.0666) loss: 0.8781 (0.8775) time: 0.1769 data: 0.0929 max mem: 8299 +Train: [25] [1000/6250] eta: 0:13:55 lr: 0.000112 grad: 0.0646 (0.0668) loss: 0.8737 (0.8775) time: 0.1411 data: 0.0635 max mem: 8299 +Train: [25] [1100/6250] eta: 0:13:33 lr: 0.000112 grad: 0.0647 (0.0671) loss: 0.8728 (0.8775) time: 0.1653 data: 0.0929 max mem: 8299 +Train: [25] [1200/6250] eta: 0:13:17 lr: 0.000112 grad: 0.0627 (0.0672) loss: 0.8760 (0.8773) time: 0.1598 data: 0.0776 max mem: 8299 +Train: [25] [1300/6250] eta: 0:13:01 lr: 0.000112 grad: 0.0686 (0.0672) loss: 0.8792 (0.8772) time: 0.1562 data: 0.0719 max mem: 8299 +Train: [25] [1400/6250] eta: 0:12:47 lr: 0.000112 grad: 0.0703 (0.0674) loss: 0.8789 (0.8771) time: 0.1796 data: 0.0933 max mem: 8299 +Train: [25] [1500/6250] eta: 0:12:33 lr: 0.000112 grad: 0.0635 (0.0675) loss: 0.8761 (0.8771) time: 0.1346 data: 0.0605 max mem: 8299 +Train: [25] [1600/6250] eta: 0:12:20 lr: 0.000111 grad: 0.0659 (0.0675) loss: 0.8742 (0.8771) time: 0.1695 data: 0.0957 max mem: 8299 +Train: [25] [1700/6250] eta: 0:12:06 lr: 0.000111 grad: 0.0653 (0.0675) loss: 0.8786 (0.8770) time: 0.1835 data: 0.1005 max mem: 8299 +Train: [25] [1800/6250] eta: 0:11:51 lr: 0.000111 grad: 0.0673 (0.0675) loss: 0.8729 (0.8770) time: 0.1590 data: 0.0775 max mem: 8299 +Train: [25] [1900/6250] eta: 0:11:36 lr: 0.000111 grad: 0.0649 (0.0675) loss: 0.8801 (0.8770) time: 0.1615 data: 0.0972 max mem: 8299 +Train: [25] [2000/6250] eta: 0:11:22 lr: 0.000111 grad: 0.0620 (0.0674) loss: 0.8794 (0.8771) time: 0.1176 data: 0.0312 max mem: 8299 +Train: [25] [2100/6250] eta: 0:11:06 lr: 0.000111 grad: 0.0672 (0.0674) loss: 0.8785 (0.8771) time: 0.1623 data: 0.0880 max mem: 8299 +Train: [25] [2200/6250] eta: 0:10:51 lr: 0.000111 grad: 0.0654 (0.0675) loss: 0.8784 (0.8770) time: 0.1686 data: 0.0845 max mem: 8299 +Train: [25] [2300/6250] eta: 0:10:38 lr: 0.000111 grad: 0.0682 (0.0676) loss: 0.8829 (0.8770) time: 0.1812 data: 0.1038 max mem: 8299 +Train: [25] [2400/6250] eta: 0:10:21 lr: 0.000111 grad: 0.0688 (0.0677) loss: 0.8809 (0.8770) time: 0.1612 data: 0.0784 max mem: 8299 +Train: [25] [2500/6250] eta: 0:10:05 lr: 0.000111 grad: 0.0660 (0.0678) loss: 0.8700 (0.8769) time: 0.1628 data: 0.0888 max mem: 8299 +Train: [25] [2600/6250] eta: 0:09:48 lr: 0.000111 grad: 0.0694 (0.0680) loss: 0.8751 (0.8767) time: 0.1444 data: 0.0650 max mem: 8299 +Train: [25] [2700/6250] eta: 0:09:33 lr: 0.000111 grad: 0.0639 (0.0681) loss: 0.8780 (0.8766) time: 0.1842 data: 0.0967 max mem: 8299 +Train: [25] [2800/6250] eta: 0:09:15 lr: 0.000111 grad: 0.0681 (0.0682) loss: 0.8728 (0.8765) time: 0.1385 data: 0.0456 max mem: 8299 +Train: [25] [2900/6250] eta: 0:08:59 lr: 0.000111 grad: 0.0625 (0.0683) loss: 0.8771 (0.8765) time: 0.1754 data: 0.0839 max mem: 8299 +Train: [25] [3000/6250] eta: 0:08:42 lr: 0.000111 grad: 0.0670 (0.0683) loss: 0.8757 (0.8765) time: 0.1447 data: 0.0721 max mem: 8299 +Train: [25] [3100/6250] eta: 0:08:26 lr: 0.000111 grad: 0.0653 (0.0683) loss: 0.8801 (0.8765) time: 0.1567 data: 0.0880 max mem: 8299 +Train: [25] [3200/6250] eta: 0:08:11 lr: 0.000111 grad: 0.0627 (0.0683) loss: 0.8823 (0.8765) time: 0.1873 data: 0.1154 max mem: 8299 +Train: [25] [3300/6250] eta: 0:07:54 lr: 0.000111 grad: 0.0610 (0.0682) loss: 0.8791 (0.8766) time: 0.1349 data: 0.0501 max mem: 8299 +Train: [25] [3400/6250] eta: 0:07:37 lr: 0.000111 grad: 0.0639 (0.0683) loss: 0.8774 (0.8766) time: 0.1223 data: 0.0307 max mem: 8299 +Train: [25] [3500/6250] eta: 0:07:20 lr: 0.000111 grad: 0.0627 (0.0683) loss: 0.8764 (0.8765) time: 0.1665 data: 0.0773 max mem: 8299 +Train: [25] [3600/6250] eta: 0:07:04 lr: 0.000111 grad: 0.0658 (0.0684) loss: 0.8735 (0.8765) time: 0.1819 data: 0.0981 max mem: 8299 +Train: [25] [3700/6250] eta: 0:06:47 lr: 0.000111 grad: 0.0706 (0.0685) loss: 0.8714 (0.8765) time: 0.1545 data: 0.0783 max mem: 8299 +Train: [25] [3800/6250] eta: 0:06:31 lr: 0.000111 grad: 0.0650 (0.0686) loss: 0.8763 (0.8766) time: 0.1597 data: 0.0787 max mem: 8299 +Train: [25] [3900/6250] eta: 0:06:15 lr: 0.000111 grad: 0.0736 (0.0688) loss: 0.8748 (0.8765) time: 0.1475 data: 0.0753 max mem: 8299 +Train: [25] [4000/6250] eta: 0:05:58 lr: 0.000111 grad: 0.0649 (0.0688) loss: 0.8726 (0.8764) time: 0.1903 data: 0.1087 max mem: 8299 +Train: [25] [4100/6250] eta: 0:05:42 lr: 0.000111 grad: 0.0642 (0.0689) loss: 0.8779 (0.8764) time: 0.1575 data: 0.0626 max mem: 8299 +Train: [25] [4200/6250] eta: 0:05:26 lr: 0.000111 grad: 0.0733 (0.0691) loss: 0.8705 (0.8763) time: 0.1329 data: 0.0546 max mem: 8299 +Train: [25] [4300/6250] eta: 0:05:10 lr: 0.000111 grad: 0.0754 (0.0691) loss: 0.8749 (0.8763) time: 0.1567 data: 0.0734 max mem: 8299 +Train: [25] [4400/6250] eta: 0:04:53 lr: 0.000111 grad: 0.0684 (0.0692) loss: 0.8785 (0.8763) time: 0.1747 data: 0.0940 max mem: 8299 +Train: [25] [4500/6250] eta: 0:04:38 lr: 0.000111 grad: 0.0652 (0.0693) loss: 0.8759 (0.8762) time: 0.1577 data: 0.0817 max mem: 8299 +Train: [25] [4600/6250] eta: 0:04:22 lr: 0.000111 grad: 0.0724 (0.0694) loss: 0.8673 (0.8762) time: 0.1146 data: 0.0328 max mem: 8299 +Train: [25] [4700/6250] eta: 0:04:06 lr: 0.000111 grad: 0.0714 (0.0696) loss: 0.8791 (0.8762) time: 0.1614 data: 0.0867 max mem: 8299 +Train: [25] [4800/6250] eta: 0:03:50 lr: 0.000111 grad: 0.0646 (0.0696) loss: 0.8786 (0.8762) time: 0.1735 data: 0.0940 max mem: 8299 +Train: [25] [4900/6250] eta: 0:03:33 lr: 0.000111 grad: 0.0707 (0.0697) loss: 0.8786 (0.8762) time: 0.1537 data: 0.0715 max mem: 8299 +Train: [25] [5000/6250] eta: 0:03:17 lr: 0.000111 grad: 0.0673 (0.0698) loss: 0.8771 (0.8761) time: 0.1509 data: 0.0715 max mem: 8299 +Train: [25] [5100/6250] eta: 0:03:01 lr: 0.000111 grad: 0.0672 (0.0698) loss: 0.8739 (0.8761) time: 0.1237 data: 0.0423 max mem: 8299 +Train: [25] [5200/6250] eta: 0:02:46 lr: 0.000111 grad: 0.0627 (0.0698) loss: 0.8749 (0.8761) time: 0.1730 data: 0.0829 max mem: 8299 +Train: [25] [5300/6250] eta: 0:02:30 lr: 0.000111 grad: 0.0690 (0.0698) loss: 0.8759 (0.8761) time: 0.1756 data: 0.0927 max mem: 8299 +Train: [25] [5400/6250] eta: 0:02:14 lr: 0.000111 grad: 0.0693 (0.0698) loss: 0.8746 (0.8762) time: 0.1462 data: 0.0656 max mem: 8299 +Train: [25] [5500/6250] eta: 0:01:58 lr: 0.000111 grad: 0.0703 (0.0698) loss: 0.8746 (0.8762) time: 0.1717 data: 0.0855 max mem: 8299 +Train: [25] [5600/6250] eta: 0:01:42 lr: 0.000111 grad: 0.0636 (0.0698) loss: 0.8783 (0.8762) time: 0.1401 data: 0.0553 max mem: 8299 +Train: [25] [5700/6250] eta: 0:01:27 lr: 0.000111 grad: 0.0653 (0.0698) loss: 0.8805 (0.8762) time: 0.1555 data: 0.0863 max mem: 8299 +Train: [25] [5800/6250] eta: 0:01:11 lr: 0.000111 grad: 0.0665 (0.0698) loss: 0.8732 (0.8763) time: 0.1325 data: 0.0543 max mem: 8299 +Train: [25] [5900/6250] eta: 0:00:55 lr: 0.000111 grad: 0.0655 (0.0698) loss: 0.8754 (0.8763) time: 0.1443 data: 0.0688 max mem: 8299 +Train: [25] [6000/6250] eta: 0:00:39 lr: 0.000111 grad: 0.0674 (0.0698) loss: 0.8793 (0.8763) time: 0.1643 data: 0.0767 max mem: 8299 +Train: [25] [6100/6250] eta: 0:00:23 lr: 0.000111 grad: 0.0651 (0.0699) loss: 0.8786 (0.8763) time: 0.1491 data: 0.0649 max mem: 8299 +Train: [25] [6200/6250] eta: 0:00:07 lr: 0.000111 grad: 0.0735 (0.0699) loss: 0.8727 (0.8763) time: 0.1422 data: 0.0495 max mem: 8299 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0633 (0.0698) loss: 0.8744 (0.8764) time: 0.1361 data: 0.0605 max mem: 8299 +Train: [25] Total time: 0:16:32 (0.1589 s / it) +Averaged stats: lr: 0.000111 grad: 0.0633 (0.0698) loss: 0.8744 (0.8764) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:03:49 loss: 0.9008 (0.9008) time: 3.7058 data: 3.6299 max mem: 8299 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8919 (0.8912) time: 0.1304 data: 0.1049 max mem: 8299 +Eval (hcp-train-subset): [25] Total time: 0:00:13 (0.2177 s / it) +Averaged stats (hcp-train-subset): loss: 0.8919 (0.8912) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:40 loss: 0.8846 (0.8846) time: 5.4916 data: 5.4617 max mem: 8299 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8869 (0.8874) time: 0.1354 data: 0.1106 max mem: 8299 +Eval (hcp-val): [25] Total time: 0:00:13 (0.2147 s / it) +Averaged stats (hcp-val): loss: 0.8869 (0.8874) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 10:57:13 lr: 0.000111 grad: 0.0440 (0.0440) loss: 0.8949 (0.8949) time: 6.3093 data: 6.1725 max mem: 8299 +Train: [26] [ 100/6250] eta: 0:21:57 lr: 0.000111 grad: 0.0693 (0.0759) loss: 0.8797 (0.8928) time: 0.1288 data: 0.0038 max mem: 8299 +Train: [26] [ 200/6250] eta: 0:18:35 lr: 0.000110 grad: 0.0697 (0.0756) loss: 0.8761 (0.8840) time: 0.1701 data: 0.0635 max mem: 8299 +Train: [26] [ 300/6250] eta: 0:17:30 lr: 0.000110 grad: 0.0630 (0.0747) loss: 0.8716 (0.8815) time: 0.1849 data: 0.1009 max mem: 8299 +Train: [26] [ 400/6250] eta: 0:16:42 lr: 0.000110 grad: 0.0729 (0.0730) loss: 0.8774 (0.8801) time: 0.1484 data: 0.0574 max mem: 8299 +Train: [26] [ 500/6250] eta: 0:16:32 lr: 0.000110 grad: 0.0677 (0.0719) loss: 0.8769 (0.8797) time: 0.1606 data: 0.0704 max mem: 8299 +Train: [26] [ 600/6250] eta: 0:16:03 lr: 0.000110 grad: 0.0627 (0.0709) loss: 0.8763 (0.8791) time: 0.1745 data: 0.0817 max mem: 8299 +Train: [26] [ 700/6250] eta: 0:15:44 lr: 0.000110 grad: 0.0631 (0.0701) loss: 0.8799 (0.8790) time: 0.1986 data: 0.1087 max mem: 8299 +Train: [26] [ 800/6250] eta: 0:15:18 lr: 0.000110 grad: 0.0666 (0.0695) loss: 0.8812 (0.8790) time: 0.1500 data: 0.0661 max mem: 8299 +Train: [26] [ 900/6250] eta: 0:15:03 lr: 0.000110 grad: 0.0608 (0.0689) loss: 0.8773 (0.8789) time: 0.1525 data: 0.0705 max mem: 8299 +Train: [26] [1000/6250] eta: 0:14:38 lr: 0.000110 grad: 0.0606 (0.0686) loss: 0.8743 (0.8786) time: 0.1253 data: 0.0505 max mem: 8299 +Train: [26] [1100/6250] eta: 0:14:17 lr: 0.000110 grad: 0.0601 (0.0686) loss: 0.8759 (0.8781) time: 0.1488 data: 0.0767 max mem: 8299 +Train: [26] [1200/6250] eta: 0:13:58 lr: 0.000110 grad: 0.0670 (0.0687) loss: 0.8705 (0.8775) time: 0.1518 data: 0.0712 max mem: 8299 +Train: [26] [1300/6250] eta: 0:13:38 lr: 0.000110 grad: 0.0622 (0.0698) loss: 0.8703 (0.8770) time: 0.1607 data: 0.0762 max mem: 8299 +Train: [26] [1400/6250] eta: 0:13:21 lr: 0.000110 grad: 0.0687 (0.0699) loss: 0.8683 (0.8765) time: 0.1690 data: 0.0868 max mem: 8299 +Train: [26] [1500/6250] eta: 0:13:05 lr: 0.000110 grad: 0.0642 (0.0699) loss: 0.8760 (0.8762) time: 0.1678 data: 0.0918 max mem: 8299 +Train: [26] [1600/6250] eta: 0:12:49 lr: 0.000110 grad: 0.0673 (0.0702) loss: 0.8723 (0.8760) time: 0.1871 data: 0.1118 max mem: 8299 +Train: [26] [1700/6250] eta: 0:12:35 lr: 0.000110 grad: 0.0640 (0.0702) loss: 0.8728 (0.8757) time: 0.1611 data: 0.0866 max mem: 8299 +Train: [26] [1800/6250] eta: 0:12:21 lr: 0.000110 grad: 0.0720 (0.0703) loss: 0.8700 (0.8755) time: 0.2033 data: 0.1307 max mem: 8299 +Train: [26] [1900/6250] eta: 0:12:04 lr: 0.000110 grad: 0.0637 (0.0704) loss: 0.8756 (0.8753) time: 0.1807 data: 0.1010 max mem: 8299 +Train: [26] [2000/6250] eta: 0:11:50 lr: 0.000110 grad: 0.0708 (0.0704) loss: 0.8738 (0.8752) time: 0.1674 data: 0.0863 max mem: 8299 +Train: [26] [2100/6250] eta: 0:11:33 lr: 0.000110 grad: 0.0670 (0.0704) loss: 0.8717 (0.8750) time: 0.1812 data: 0.1070 max mem: 8299 +Train: [26] [2200/6250] eta: 0:11:17 lr: 0.000110 grad: 0.0708 (0.0705) loss: 0.8694 (0.8749) time: 0.1719 data: 0.0849 max mem: 8299 +Train: [26] [2300/6250] eta: 0:11:01 lr: 0.000110 grad: 0.0636 (0.0705) loss: 0.8771 (0.8749) time: 0.1647 data: 0.0838 max mem: 8299 +Train: [26] [2400/6250] eta: 0:10:44 lr: 0.000110 grad: 0.0662 (0.0704) loss: 0.8751 (0.8749) time: 0.1567 data: 0.0833 max mem: 8299 +Train: [26] [2500/6250] eta: 0:10:27 lr: 0.000110 grad: 0.0678 (0.0704) loss: 0.8690 (0.8749) time: 0.1766 data: 0.0890 max mem: 8299 +Train: [26] [2600/6250] eta: 0:10:09 lr: 0.000110 grad: 0.0686 (0.0704) loss: 0.8766 (0.8748) time: 0.1575 data: 0.0713 max mem: 8299 +Train: [26] [2700/6250] eta: 0:09:52 lr: 0.000110 grad: 0.0652 (0.0703) loss: 0.8794 (0.8748) time: 0.1501 data: 0.0697 max mem: 8299 +Train: [26] [2800/6250] eta: 0:09:34 lr: 0.000110 grad: 0.0673 (0.0702) loss: 0.8738 (0.8749) time: 0.1513 data: 0.0567 max mem: 8299 +Train: [26] [2900/6250] eta: 0:09:16 lr: 0.000110 grad: 0.0721 (0.0703) loss: 0.8765 (0.8749) time: 0.1575 data: 0.0834 max mem: 8299 +Train: [26] [3000/6250] eta: 0:08:58 lr: 0.000110 grad: 0.0639 (0.0702) loss: 0.8777 (0.8750) time: 0.1642 data: 0.0831 max mem: 8299 +Train: [26] [3100/6250] eta: 0:08:41 lr: 0.000110 grad: 0.0674 (0.0701) loss: 0.8787 (0.8750) time: 0.1291 data: 0.0517 max mem: 8299 +Train: [26] [3200/6250] eta: 0:08:23 lr: 0.000110 grad: 0.0665 (0.0701) loss: 0.8773 (0.8751) time: 0.1317 data: 0.0448 max mem: 8299 +Train: [26] [3300/6250] eta: 0:08:05 lr: 0.000110 grad: 0.0661 (0.0700) loss: 0.8701 (0.8751) time: 0.1386 data: 0.0666 max mem: 8299 +Train: [26] [3400/6250] eta: 0:07:47 lr: 0.000110 grad: 0.0645 (0.0700) loss: 0.8781 (0.8751) time: 0.1537 data: 0.0756 max mem: 8299 +Train: [26] [3500/6250] eta: 0:07:30 lr: 0.000110 grad: 0.0693 (0.0699) loss: 0.8766 (0.8751) time: 0.1730 data: 0.0913 max mem: 8299 +Train: [26] [3600/6250] eta: 0:07:12 lr: 0.000110 grad: 0.0642 (0.0699) loss: 0.8725 (0.8752) time: 0.1619 data: 0.0797 max mem: 8299 +Train: [26] [3700/6250] eta: 0:06:56 lr: 0.000110 grad: 0.0702 (0.0698) loss: 0.8797 (0.8752) time: 0.1655 data: 0.0783 max mem: 8299 +Train: [26] [3800/6250] eta: 0:06:39 lr: 0.000110 grad: 0.0685 (0.0698) loss: 0.8766 (0.8752) time: 0.1729 data: 0.0987 max mem: 8299 +Train: [26] [3900/6250] eta: 0:06:22 lr: 0.000110 grad: 0.0626 (0.0697) loss: 0.8794 (0.8753) time: 0.1105 data: 0.0203 max mem: 8299 +Train: [26] [4000/6250] eta: 0:06:06 lr: 0.000110 grad: 0.0660 (0.0695) loss: 0.8741 (0.8754) time: 0.1771 data: 0.1035 max mem: 8299 +Train: [26] [4100/6250] eta: 0:05:49 lr: 0.000110 grad: 0.0642 (0.0694) loss: 0.8792 (0.8754) time: 0.1252 data: 0.0396 max mem: 8299 +Train: [26] [4200/6250] eta: 0:05:32 lr: 0.000110 grad: 0.0626 (0.0694) loss: 0.8774 (0.8755) time: 0.1587 data: 0.0896 max mem: 8299 +Train: [26] [4300/6250] eta: 0:05:16 lr: 0.000110 grad: 0.0642 (0.0693) loss: 0.8756 (0.8755) time: 0.1547 data: 0.0561 max mem: 8299 +Train: [26] [4400/6250] eta: 0:05:00 lr: 0.000110 grad: 0.0666 (0.0693) loss: 0.8743 (0.8755) time: 0.1690 data: 0.0978 max mem: 8299 +Train: [26] [4500/6250] eta: 0:04:44 lr: 0.000110 grad: 0.0667 (0.0693) loss: 0.8769 (0.8755) time: 0.1875 data: 0.1070 max mem: 8299 +Train: [26] [4600/6250] eta: 0:04:28 lr: 0.000110 grad: 0.0673 (0.0693) loss: 0.8694 (0.8754) time: 0.1971 data: 0.1109 max mem: 8299 +Train: [26] [4700/6250] eta: 0:04:11 lr: 0.000110 grad: 0.0650 (0.0693) loss: 0.8761 (0.8754) time: 0.1577 data: 0.0775 max mem: 8299 +Train: [26] [4800/6250] eta: 0:03:55 lr: 0.000109 grad: 0.0735 (0.0693) loss: 0.8737 (0.8754) time: 0.1501 data: 0.0759 max mem: 8299 +Train: [26] [4900/6250] eta: 0:03:38 lr: 0.000109 grad: 0.0671 (0.0694) loss: 0.8750 (0.8754) time: 0.1436 data: 0.0694 max mem: 8299 +Train: [26] [5000/6250] eta: 0:03:22 lr: 0.000109 grad: 0.0606 (0.0693) loss: 0.8746 (0.8754) time: 0.1465 data: 0.0606 max mem: 8299 +Train: [26] [5100/6250] eta: 0:03:05 lr: 0.000109 grad: 0.0639 (0.0693) loss: 0.8796 (0.8754) time: 0.1420 data: 0.0569 max mem: 8299 +Train: [26] [5200/6250] eta: 0:02:49 lr: 0.000109 grad: 0.0716 (0.0693) loss: 0.8741 (0.8754) time: 0.1457 data: 0.0669 max mem: 8299 +Train: [26] [5300/6250] eta: 0:02:33 lr: 0.000109 grad: 0.0665 (0.0693) loss: 0.8782 (0.8755) time: 0.1747 data: 0.0954 max mem: 8299 +Train: [26] [5400/6250] eta: 0:02:17 lr: 0.000109 grad: 0.0630 (0.0693) loss: 0.8821 (0.8755) time: 0.1643 data: 0.0895 max mem: 8299 +Train: [26] [5500/6250] eta: 0:02:00 lr: 0.000109 grad: 0.0675 (0.0694) loss: 0.8752 (0.8755) time: 0.1528 data: 0.0769 max mem: 8299 +Train: [26] [5600/6250] eta: 0:01:44 lr: 0.000109 grad: 0.0719 (0.0695) loss: 0.8709 (0.8754) time: 0.1314 data: 0.0566 max mem: 8299 +Train: [26] [5700/6250] eta: 0:01:28 lr: 0.000109 grad: 0.0702 (0.0695) loss: 0.8750 (0.8754) time: 0.1700 data: 0.0881 max mem: 8299 +Train: [26] [5800/6250] eta: 0:01:12 lr: 0.000109 grad: 0.0661 (0.0695) loss: 0.8744 (0.8754) time: 0.1442 data: 0.0614 max mem: 8299 +Train: [26] [5900/6250] eta: 0:00:56 lr: 0.000109 grad: 0.0760 (0.0696) loss: 0.8710 (0.8754) time: 0.1334 data: 0.0500 max mem: 8299 +Train: [26] [6000/6250] eta: 0:00:40 lr: 0.000109 grad: 0.0680 (0.0697) loss: 0.8744 (0.8753) time: 0.1676 data: 0.0761 max mem: 8299 +Train: [26] [6100/6250] eta: 0:00:24 lr: 0.000109 grad: 0.0787 (0.0697) loss: 0.8662 (0.8753) time: 0.1238 data: 0.0285 max mem: 8299 +Train: [26] [6200/6250] eta: 0:00:08 lr: 0.000109 grad: 0.0747 (0.0698) loss: 0.8656 (0.8752) time: 0.1401 data: 0.0635 max mem: 8299 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0731 (0.0698) loss: 0.8680 (0.8751) time: 0.1347 data: 0.0414 max mem: 8299 +Train: [26] Total time: 0:16:49 (0.1615 s / it) +Averaged stats: lr: 0.000109 grad: 0.0731 (0.0698) loss: 0.8680 (0.8751) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:04:17 loss: 0.9051 (0.9051) time: 4.1561 data: 4.0938 max mem: 8299 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8906 (0.8912) time: 0.1188 data: 0.0931 max mem: 8299 +Eval (hcp-train-subset): [26] Total time: 0:00:13 (0.2099 s / it) +Averaged stats (hcp-train-subset): loss: 0.8906 (0.8912) +Eval (hcp-val): [26] [ 0/62] eta: 0:03:39 loss: 0.8893 (0.8893) time: 3.5475 data: 3.4602 max mem: 8299 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8870 (0.8890) time: 0.1211 data: 0.0951 max mem: 8299 +Eval (hcp-val): [26] Total time: 0:00:13 (0.2124 s / it) +Averaged stats (hcp-val): loss: 0.8870 (0.8890) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 11:29:56 lr: 0.000109 grad: 0.0623 (0.0623) loss: 0.9057 (0.9057) time: 6.6235 data: 6.5230 max mem: 8299 +Train: [27] [ 100/6250] eta: 0:21:03 lr: 0.000109 grad: 0.0665 (0.0752) loss: 0.8816 (0.8847) time: 0.1487 data: 0.0496 max mem: 8299 +Train: [27] [ 200/6250] eta: 0:18:16 lr: 0.000109 grad: 0.0633 (0.0737) loss: 0.8787 (0.8817) time: 0.1508 data: 0.0558 max mem: 8299 +Train: [27] [ 300/6250] eta: 0:16:46 lr: 0.000109 grad: 0.0717 (0.0726) loss: 0.8700 (0.8796) time: 0.1406 data: 0.0399 max mem: 8299 +Train: [27] [ 400/6250] eta: 0:16:01 lr: 0.000109 grad: 0.0596 (0.0715) loss: 0.8869 (0.8797) time: 0.1713 data: 0.0853 max mem: 8299 +Train: [27] [ 500/6250] eta: 0:15:50 lr: 0.000109 grad: 0.0687 (0.0705) loss: 0.8844 (0.8801) time: 0.2228 data: 0.1421 max mem: 8299 +Train: [27] [ 600/6250] eta: 0:15:30 lr: 0.000109 grad: 0.0608 (0.0693) loss: 0.8855 (0.8807) time: 0.1605 data: 0.0736 max mem: 8299 +Train: [27] [ 700/6250] eta: 0:15:21 lr: 0.000109 grad: 0.0623 (0.0690) loss: 0.8773 (0.8805) time: 0.2006 data: 0.1197 max mem: 8299 +Train: [27] [ 800/6250] eta: 0:15:04 lr: 0.000109 grad: 0.0659 (0.0695) loss: 0.8744 (0.8800) time: 0.1697 data: 0.0855 max mem: 8299 +Train: [27] [ 900/6250] eta: 0:14:43 lr: 0.000109 grad: 0.0630 (0.0693) loss: 0.8771 (0.8795) time: 0.1704 data: 0.0917 max mem: 8299 +Train: [27] [1000/6250] eta: 0:14:19 lr: 0.000109 grad: 0.0667 (0.0695) loss: 0.8756 (0.8789) time: 0.1364 data: 0.0551 max mem: 8299 +Train: [27] [1100/6250] eta: 0:13:56 lr: 0.000109 grad: 0.0653 (0.0695) loss: 0.8763 (0.8788) time: 0.1378 data: 0.0515 max mem: 8299 +Train: [27] [1200/6250] eta: 0:13:37 lr: 0.000109 grad: 0.0666 (0.0693) loss: 0.8700 (0.8784) time: 0.1414 data: 0.0679 max mem: 8299 +Train: [27] [1300/6250] eta: 0:13:17 lr: 0.000109 grad: 0.0705 (0.0693) loss: 0.8700 (0.8780) time: 0.1429 data: 0.0598 max mem: 8299 +Train: [27] [1400/6250] eta: 0:12:56 lr: 0.000109 grad: 0.0685 (0.0693) loss: 0.8678 (0.8776) time: 0.1360 data: 0.0585 max mem: 8299 +Train: [27] [1500/6250] eta: 0:12:38 lr: 0.000109 grad: 0.0693 (0.0694) loss: 0.8691 (0.8773) time: 0.1623 data: 0.0796 max mem: 8299 +Train: [27] [1600/6250] eta: 0:12:23 lr: 0.000109 grad: 0.0688 (0.0693) loss: 0.8758 (0.8770) time: 0.1923 data: 0.1123 max mem: 8299 +Train: [27] [1700/6250] eta: 0:12:04 lr: 0.000109 grad: 0.0664 (0.0695) loss: 0.8727 (0.8767) time: 0.1353 data: 0.0633 max mem: 8299 +Train: [27] [1800/6250] eta: 0:11:49 lr: 0.000109 grad: 0.0653 (0.0697) loss: 0.8718 (0.8764) time: 0.1912 data: 0.0973 max mem: 8299 +Train: [27] [1900/6250] eta: 0:11:32 lr: 0.000109 grad: 0.0750 (0.0699) loss: 0.8769 (0.8761) time: 0.1315 data: 0.0425 max mem: 8299 +Train: [27] [2000/6250] eta: 0:11:16 lr: 0.000109 grad: 0.0684 (0.0701) loss: 0.8716 (0.8759) time: 0.1784 data: 0.0965 max mem: 8299 +Train: [27] [2100/6250] eta: 0:10:59 lr: 0.000109 grad: 0.0634 (0.0701) loss: 0.8708 (0.8756) time: 0.1738 data: 0.0953 max mem: 8299 +Train: [27] [2200/6250] eta: 0:10:42 lr: 0.000109 grad: 0.0646 (0.0702) loss: 0.8718 (0.8755) time: 0.1492 data: 0.0699 max mem: 8299 +Train: [27] [2300/6250] eta: 0:10:25 lr: 0.000109 grad: 0.0677 (0.0703) loss: 0.8711 (0.8753) time: 0.1406 data: 0.0590 max mem: 8299 +Train: [27] [2400/6250] eta: 0:10:08 lr: 0.000109 grad: 0.0685 (0.0704) loss: 0.8709 (0.8751) time: 0.1411 data: 0.0587 max mem: 8299 +Train: [27] [2500/6250] eta: 0:09:53 lr: 0.000109 grad: 0.0717 (0.0705) loss: 0.8686 (0.8750) time: 0.1511 data: 0.0709 max mem: 8299 +Train: [27] [2600/6250] eta: 0:09:37 lr: 0.000109 grad: 0.0693 (0.0706) loss: 0.8685 (0.8748) time: 0.1481 data: 0.0713 max mem: 8299 +Train: [27] [2700/6250] eta: 0:09:22 lr: 0.000109 grad: 0.0696 (0.0707) loss: 0.8706 (0.8747) time: 0.1434 data: 0.0624 max mem: 8299 +Train: [27] [2800/6250] eta: 0:09:07 lr: 0.000109 grad: 0.0662 (0.0707) loss: 0.8730 (0.8745) time: 0.1775 data: 0.0795 max mem: 8299 +Train: [27] [2900/6250] eta: 0:08:51 lr: 0.000109 grad: 0.0674 (0.0707) loss: 0.8685 (0.8744) time: 0.1702 data: 0.0855 max mem: 8299 +Train: [27] [3000/6250] eta: 0:08:33 lr: 0.000109 grad: 0.0728 (0.0708) loss: 0.8721 (0.8743) time: 0.1336 data: 0.0557 max mem: 8299 +Train: [27] [3100/6250] eta: 0:08:17 lr: 0.000108 grad: 0.0717 (0.0709) loss: 0.8733 (0.8743) time: 0.1487 data: 0.0712 max mem: 8299 +Train: [27] [3200/6250] eta: 0:08:01 lr: 0.000108 grad: 0.0665 (0.0709) loss: 0.8706 (0.8742) time: 0.1381 data: 0.0557 max mem: 8299 +Train: [27] [3300/6250] eta: 0:07:45 lr: 0.000108 grad: 0.0697 (0.0709) loss: 0.8724 (0.8741) time: 0.1471 data: 0.0635 max mem: 8299 +Train: [27] [3400/6250] eta: 0:07:30 lr: 0.000108 grad: 0.0675 (0.0709) loss: 0.8695 (0.8740) time: 0.1395 data: 0.0574 max mem: 8299 +Train: [27] [3500/6250] eta: 0:07:13 lr: 0.000108 grad: 0.0734 (0.0710) loss: 0.8655 (0.8740) time: 0.1704 data: 0.0880 max mem: 8299 +Train: [27] [3600/6250] eta: 0:06:58 lr: 0.000108 grad: 0.0690 (0.0711) loss: 0.8720 (0.8739) time: 0.1863 data: 0.1123 max mem: 8299 +Train: [27] [3700/6250] eta: 0:06:43 lr: 0.000108 grad: 0.0719 (0.0712) loss: 0.8743 (0.8739) time: 0.2480 data: 0.1638 max mem: 8299 +Train: [27] [3800/6250] eta: 0:06:27 lr: 0.000108 grad: 0.0714 (0.0712) loss: 0.8677 (0.8738) time: 0.1524 data: 0.0784 max mem: 8299 +Train: [27] [3900/6250] eta: 0:06:12 lr: 0.000108 grad: 0.0689 (0.0712) loss: 0.8735 (0.8738) time: 0.1727 data: 0.1014 max mem: 8299 +Train: [27] [4000/6250] eta: 0:05:56 lr: 0.000108 grad: 0.0743 (0.0712) loss: 0.8682 (0.8738) time: 0.1120 data: 0.0274 max mem: 8299 +Train: [27] [4100/6250] eta: 0:05:40 lr: 0.000108 grad: 0.0748 (0.0713) loss: 0.8779 (0.8738) time: 0.1574 data: 0.0895 max mem: 8299 +Train: [27] [4200/6250] eta: 0:05:24 lr: 0.000108 grad: 0.0771 (0.0713) loss: 0.8791 (0.8738) time: 0.1626 data: 0.0711 max mem: 8299 +Train: [27] [4300/6250] eta: 0:05:08 lr: 0.000108 grad: 0.0698 (0.0714) loss: 0.8765 (0.8738) time: 0.1416 data: 0.0692 max mem: 8299 +Train: [27] [4400/6250] eta: 0:04:52 lr: 0.000108 grad: 0.0670 (0.0713) loss: 0.8686 (0.8738) time: 0.1429 data: 0.0639 max mem: 8299 +Train: [27] [4500/6250] eta: 0:04:36 lr: 0.000108 grad: 0.0708 (0.0713) loss: 0.8741 (0.8739) time: 0.1603 data: 0.0813 max mem: 8299 +Train: [27] [4600/6250] eta: 0:04:20 lr: 0.000108 grad: 0.0753 (0.0714) loss: 0.8745 (0.8739) time: 0.1565 data: 0.0798 max mem: 8299 +Train: [27] [4700/6250] eta: 0:04:04 lr: 0.000108 grad: 0.0722 (0.0714) loss: 0.8772 (0.8739) time: 0.1286 data: 0.0530 max mem: 8299 +Train: [27] [4800/6250] eta: 0:03:49 lr: 0.000108 grad: 0.0676 (0.0715) loss: 0.8749 (0.8740) time: 0.1702 data: 0.0861 max mem: 8299 +Train: [27] [4900/6250] eta: 0:03:33 lr: 0.000108 grad: 0.0734 (0.0715) loss: 0.8725 (0.8740) time: 0.1660 data: 0.0777 max mem: 8299 +Train: [27] [5000/6250] eta: 0:03:17 lr: 0.000108 grad: 0.0682 (0.0715) loss: 0.8734 (0.8741) time: 0.1371 data: 0.0539 max mem: 8299 +Train: [27] [5100/6250] eta: 0:03:01 lr: 0.000108 grad: 0.0694 (0.0715) loss: 0.8755 (0.8741) time: 0.1372 data: 0.0496 max mem: 8299 +Train: [27] [5200/6250] eta: 0:02:45 lr: 0.000108 grad: 0.0681 (0.0716) loss: 0.8750 (0.8741) time: 0.1508 data: 0.0734 max mem: 8299 +Train: [27] [5300/6250] eta: 0:02:29 lr: 0.000108 grad: 0.0670 (0.0716) loss: 0.8710 (0.8741) time: 0.1280 data: 0.0440 max mem: 8299 +Train: [27] [5400/6250] eta: 0:02:13 lr: 0.000108 grad: 0.0681 (0.0717) loss: 0.8714 (0.8741) time: 0.1471 data: 0.0668 max mem: 8299 +Train: [27] [5500/6250] eta: 0:01:57 lr: 0.000108 grad: 0.0698 (0.0717) loss: 0.8752 (0.8741) time: 0.2265 data: 0.1533 max mem: 8299 +Train: [27] [5600/6250] eta: 0:01:42 lr: 0.000108 grad: 0.0703 (0.0718) loss: 0.8767 (0.8741) time: 0.1377 data: 0.0605 max mem: 8299 +Train: [27] [5700/6250] eta: 0:01:26 lr: 0.000108 grad: 0.0689 (0.0718) loss: 0.8743 (0.8741) time: 0.1626 data: 0.0748 max mem: 8299 +Train: [27] [5800/6250] eta: 0:01:10 lr: 0.000108 grad: 0.0689 (0.0719) loss: 0.8752 (0.8741) time: 0.1707 data: 0.0784 max mem: 8299 +Train: [27] [5900/6250] eta: 0:00:55 lr: 0.000108 grad: 0.0742 (0.0719) loss: 0.8722 (0.8741) time: 0.1900 data: 0.1115 max mem: 8299 +Train: [27] [6000/6250] eta: 0:00:39 lr: 0.000108 grad: 0.0705 (0.0719) loss: 0.8784 (0.8741) time: 0.1717 data: 0.0779 max mem: 8299 +Train: [27] [6100/6250] eta: 0:00:23 lr: 0.000108 grad: 0.0675 (0.0719) loss: 0.8799 (0.8741) time: 0.1638 data: 0.0831 max mem: 8299 +Train: [27] [6200/6250] eta: 0:00:07 lr: 0.000108 grad: 0.0672 (0.0720) loss: 0.8727 (0.8741) time: 0.1319 data: 0.0417 max mem: 8299 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0644 (0.0720) loss: 0.8774 (0.8741) time: 0.1362 data: 0.0447 max mem: 8299 +Train: [27] Total time: 0:16:26 (0.1578 s / it) +Averaged stats: lr: 0.000108 grad: 0.0644 (0.0720) loss: 0.8774 (0.8741) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:04:29 loss: 0.9013 (0.9013) time: 4.3532 data: 4.3191 max mem: 8299 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8907 (0.8910) time: 0.1234 data: 0.0988 max mem: 8299 +Eval (hcp-train-subset): [27] Total time: 0:00:13 (0.2142 s / it) +Averaged stats (hcp-train-subset): loss: 0.8907 (0.8910) +Eval (hcp-val): [27] [ 0/62] eta: 0:03:48 loss: 0.8863 (0.8863) time: 3.6801 data: 3.5862 max mem: 8299 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8870 (0.8880) time: 0.1279 data: 0.1022 max mem: 8299 +Eval (hcp-val): [27] Total time: 0:00:12 (0.2087 s / it) +Averaged stats (hcp-val): loss: 0.8870 (0.8880) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 7:39:18 lr: 0.000108 grad: 0.1049 (0.1049) loss: 0.8860 (0.8860) time: 4.4094 data: 4.1527 max mem: 8299 +Train: [28] [ 100/6250] eta: 0:19:44 lr: 0.000108 grad: 0.0615 (0.0752) loss: 0.8788 (0.8845) time: 0.1408 data: 0.0324 max mem: 8299 +Train: [28] [ 200/6250] eta: 0:17:02 lr: 0.000108 grad: 0.0588 (0.0742) loss: 0.8755 (0.8781) time: 0.1361 data: 0.0434 max mem: 8299 +Train: [28] [ 300/6250] eta: 0:15:49 lr: 0.000108 grad: 0.0752 (0.0730) loss: 0.8790 (0.8769) time: 0.1574 data: 0.0674 max mem: 8299 +Train: [28] [ 400/6250] eta: 0:15:19 lr: 0.000108 grad: 0.0585 (0.0716) loss: 0.8800 (0.8774) time: 0.1433 data: 0.0683 max mem: 8299 +Train: [28] [ 500/6250] eta: 0:14:59 lr: 0.000108 grad: 0.0676 (0.0710) loss: 0.8802 (0.8777) time: 0.1706 data: 0.0859 max mem: 8299 +Train: [28] [ 600/6250] eta: 0:14:47 lr: 0.000108 grad: 0.0635 (0.0707) loss: 0.8730 (0.8776) time: 0.1469 data: 0.0622 max mem: 8299 +Train: [28] [ 700/6250] eta: 0:14:37 lr: 0.000108 grad: 0.0553 (0.0698) loss: 0.8815 (0.8778) time: 0.2081 data: 0.1285 max mem: 8299 +Train: [28] [ 800/6250] eta: 0:14:16 lr: 0.000108 grad: 0.0583 (0.0690) loss: 0.8766 (0.8776) time: 0.1483 data: 0.0745 max mem: 8299 +Train: [28] [ 900/6250] eta: 0:14:03 lr: 0.000108 grad: 0.0634 (0.0691) loss: 0.8785 (0.8778) time: 0.1633 data: 0.0832 max mem: 8299 +Train: [28] [1000/6250] eta: 0:13:50 lr: 0.000108 grad: 0.0625 (0.0690) loss: 0.8770 (0.8775) time: 0.1723 data: 0.0985 max mem: 8299 +Train: [28] [1100/6250] eta: 0:13:34 lr: 0.000108 grad: 0.0662 (0.0691) loss: 0.8690 (0.8770) time: 0.1586 data: 0.0896 max mem: 8299 +Train: [28] [1200/6250] eta: 0:13:13 lr: 0.000108 grad: 0.0639 (0.0690) loss: 0.8697 (0.8767) time: 0.1398 data: 0.0579 max mem: 8299 +Train: [28] [1300/6250] eta: 0:12:57 lr: 0.000107 grad: 0.0671 (0.0690) loss: 0.8676 (0.8763) time: 0.1434 data: 0.0693 max mem: 8299 +Train: [28] [1400/6250] eta: 0:12:37 lr: 0.000107 grad: 0.0715 (0.0692) loss: 0.8651 (0.8756) time: 0.1389 data: 0.0637 max mem: 8299 +Train: [28] [1500/6250] eta: 0:12:17 lr: 0.000107 grad: 0.0620 (0.0693) loss: 0.8800 (0.8753) time: 0.1266 data: 0.0400 max mem: 8299 +Train: [28] [1600/6250] eta: 0:12:03 lr: 0.000107 grad: 0.0669 (0.0693) loss: 0.8709 (0.8750) time: 0.1465 data: 0.0563 max mem: 8299 +Train: [28] [1700/6250] eta: 0:11:48 lr: 0.000107 grad: 0.0656 (0.0693) loss: 0.8755 (0.8748) time: 0.1511 data: 0.0745 max mem: 8299 +Train: [28] [1800/6250] eta: 0:11:29 lr: 0.000107 grad: 0.0720 (0.0694) loss: 0.8741 (0.8746) time: 0.1514 data: 0.0670 max mem: 8299 +Train: [28] [1900/6250] eta: 0:11:12 lr: 0.000107 grad: 0.0714 (0.0695) loss: 0.8667 (0.8745) time: 0.1419 data: 0.0585 max mem: 8299 +Train: [28] [2000/6250] eta: 0:10:55 lr: 0.000107 grad: 0.0711 (0.0695) loss: 0.8808 (0.8746) time: 0.1521 data: 0.0695 max mem: 8299 +Train: [28] [2100/6250] eta: 0:10:37 lr: 0.000107 grad: 0.0674 (0.0695) loss: 0.8742 (0.8747) time: 0.1312 data: 0.0467 max mem: 8299 +Train: [28] [2200/6250] eta: 0:10:21 lr: 0.000107 grad: 0.0666 (0.0695) loss: 0.8758 (0.8746) time: 0.1563 data: 0.0702 max mem: 8299 +Train: [28] [2300/6250] eta: 0:10:04 lr: 0.000107 grad: 0.0697 (0.0696) loss: 0.8720 (0.8746) time: 0.1355 data: 0.0541 max mem: 8299 +Train: [28] [2400/6250] eta: 0:09:47 lr: 0.000107 grad: 0.0644 (0.0696) loss: 0.8706 (0.8746) time: 0.1319 data: 0.0593 max mem: 8299 +Train: [28] [2500/6250] eta: 0:09:31 lr: 0.000107 grad: 0.0589 (0.0696) loss: 0.8828 (0.8746) time: 0.1652 data: 0.0920 max mem: 8299 +Train: [28] [2600/6250] eta: 0:09:17 lr: 0.000107 grad: 0.0642 (0.0696) loss: 0.8769 (0.8746) time: 0.1628 data: 0.0870 max mem: 8299 +Train: [28] [2700/6250] eta: 0:08:59 lr: 0.000107 grad: 0.0646 (0.0696) loss: 0.8724 (0.8746) time: 0.1322 data: 0.0499 max mem: 8299 +Train: [28] [2800/6250] eta: 0:08:45 lr: 0.000107 grad: 0.0736 (0.0697) loss: 0.8761 (0.8745) time: 0.1239 data: 0.0479 max mem: 8299 +Train: [28] [2900/6250] eta: 0:08:29 lr: 0.000107 grad: 0.0632 (0.0697) loss: 0.8801 (0.8746) time: 0.1349 data: 0.0598 max mem: 8299 +Train: [28] [3000/6250] eta: 0:08:13 lr: 0.000107 grad: 0.0645 (0.0697) loss: 0.8775 (0.8747) time: 0.1471 data: 0.0685 max mem: 8299 +Train: [28] [3100/6250] eta: 0:07:59 lr: 0.000107 grad: 0.0651 (0.0698) loss: 0.8728 (0.8746) time: 0.1488 data: 0.0813 max mem: 8299 +Train: [28] [3200/6250] eta: 0:07:43 lr: 0.000107 grad: 0.0674 (0.0699) loss: 0.8770 (0.8746) time: 0.1561 data: 0.0737 max mem: 8299 +Train: [28] [3300/6250] eta: 0:07:27 lr: 0.000107 grad: 0.0676 (0.0699) loss: 0.8742 (0.8746) time: 0.1661 data: 0.0889 max mem: 8299 +Train: [28] [3400/6250] eta: 0:07:11 lr: 0.000107 grad: 0.0697 (0.0700) loss: 0.8757 (0.8745) time: 0.1518 data: 0.0645 max mem: 8299 +Train: [28] [3500/6250] eta: 0:06:56 lr: 0.000107 grad: 0.0695 (0.0700) loss: 0.8724 (0.8745) time: 0.1325 data: 0.0401 max mem: 8299 +Train: [28] [3600/6250] eta: 0:06:41 lr: 0.000107 grad: 0.0737 (0.0701) loss: 0.8648 (0.8744) time: 0.1587 data: 0.0707 max mem: 8299 +Train: [28] [3700/6250] eta: 0:06:26 lr: 0.000107 grad: 0.0682 (0.0701) loss: 0.8693 (0.8744) time: 0.1594 data: 0.0869 max mem: 8299 +Train: [28] [3800/6250] eta: 0:06:10 lr: 0.000107 grad: 0.0705 (0.0702) loss: 0.8712 (0.8743) time: 0.1453 data: 0.0674 max mem: 8299 +Train: [28] [3900/6250] eta: 0:05:55 lr: 0.000107 grad: 0.0664 (0.0703) loss: 0.8689 (0.8742) time: 0.1399 data: 0.0522 max mem: 8299 +Train: [28] [4000/6250] eta: 0:05:40 lr: 0.000107 grad: 0.0638 (0.0703) loss: 0.8715 (0.8741) time: 0.1138 data: 0.0277 max mem: 8299 +Train: [28] [4100/6250] eta: 0:05:24 lr: 0.000107 grad: 0.0700 (0.0706) loss: 0.8727 (0.8740) time: 0.1237 data: 0.0466 max mem: 8299 +Train: [28] [4200/6250] eta: 0:05:09 lr: 0.000107 grad: 0.0712 (0.0708) loss: 0.8645 (0.8738) time: 0.1181 data: 0.0372 max mem: 8299 +Train: [28] [4300/6250] eta: 0:04:54 lr: 0.000107 grad: 0.0687 (0.0708) loss: 0.8717 (0.8738) time: 0.1565 data: 0.0791 max mem: 8299 +Train: [28] [4400/6250] eta: 0:04:39 lr: 0.000107 grad: 0.0679 (0.0710) loss: 0.8691 (0.8737) time: 0.1422 data: 0.0691 max mem: 8299 +Train: [28] [4500/6250] eta: 0:04:24 lr: 0.000107 grad: 0.0721 (0.0710) loss: 0.8700 (0.8736) time: 0.1775 data: 0.1051 max mem: 8299 +Train: [28] [4600/6250] eta: 0:04:09 lr: 0.000107 grad: 0.0670 (0.0711) loss: 0.8712 (0.8735) time: 0.1365 data: 0.0489 max mem: 8299 +Train: [28] [4700/6250] eta: 0:03:53 lr: 0.000107 grad: 0.0725 (0.0712) loss: 0.8681 (0.8735) time: 0.1338 data: 0.0380 max mem: 8299 +Train: [28] [4800/6250] eta: 0:03:38 lr: 0.000107 grad: 0.0723 (0.0713) loss: 0.8722 (0.8734) time: 0.1498 data: 0.0674 max mem: 8299 +Train: [28] [4900/6250] eta: 0:03:23 lr: 0.000107 grad: 0.0683 (0.0713) loss: 0.8693 (0.8734) time: 0.1282 data: 0.0379 max mem: 8299 +Train: [28] [5000/6250] eta: 0:03:08 lr: 0.000107 grad: 0.0716 (0.0714) loss: 0.8735 (0.8734) time: 0.1446 data: 0.0770 max mem: 8299 +Train: [28] [5100/6250] eta: 0:02:53 lr: 0.000107 grad: 0.0690 (0.0713) loss: 0.8742 (0.8733) time: 0.1498 data: 0.0607 max mem: 8299 +Train: [28] [5200/6250] eta: 0:02:38 lr: 0.000107 grad: 0.0632 (0.0714) loss: 0.8758 (0.8733) time: 0.1669 data: 0.0833 max mem: 8299 +Train: [28] [5300/6250] eta: 0:02:22 lr: 0.000107 grad: 0.0705 (0.0715) loss: 0.8781 (0.8733) time: 0.1612 data: 0.0803 max mem: 8299 +Train: [28] [5400/6250] eta: 0:02:07 lr: 0.000107 grad: 0.0689 (0.0715) loss: 0.8635 (0.8732) time: 0.1429 data: 0.0690 max mem: 8299 +Train: [28] [5500/6250] eta: 0:01:52 lr: 0.000107 grad: 0.0733 (0.0716) loss: 0.8695 (0.8731) time: 0.1397 data: 0.0512 max mem: 8299 +Train: [28] [5600/6250] eta: 0:01:37 lr: 0.000106 grad: 0.0707 (0.0716) loss: 0.8700 (0.8731) time: 0.1346 data: 0.0666 max mem: 8299 +Train: [28] [5700/6250] eta: 0:01:22 lr: 0.000106 grad: 0.0667 (0.0717) loss: 0.8714 (0.8730) time: 0.1264 data: 0.0481 max mem: 8299 +Train: [28] [5800/6250] eta: 0:01:07 lr: 0.000106 grad: 0.0695 (0.0717) loss: 0.8651 (0.8729) time: 0.1761 data: 0.0944 max mem: 8299 +Train: [28] [5900/6250] eta: 0:00:52 lr: 0.000106 grad: 0.0726 (0.0717) loss: 0.8701 (0.8729) time: 0.1429 data: 0.0571 max mem: 8299 +Train: [28] [6000/6250] eta: 0:00:37 lr: 0.000106 grad: 0.0713 (0.0718) loss: 0.8647 (0.8728) time: 0.1514 data: 0.0731 max mem: 8299 +Train: [28] [6100/6250] eta: 0:00:22 lr: 0.000106 grad: 0.0685 (0.0718) loss: 0.8720 (0.8727) time: 0.1706 data: 0.0967 max mem: 8299 +Train: [28] [6200/6250] eta: 0:00:07 lr: 0.000106 grad: 0.0715 (0.0719) loss: 0.8573 (0.8727) time: 0.1613 data: 0.0825 max mem: 8299 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0658 (0.0719) loss: 0.8684 (0.8727) time: 0.1405 data: 0.0491 max mem: 8299 +Train: [28] Total time: 0:15:48 (0.1518 s / it) +Averaged stats: lr: 0.000106 grad: 0.0658 (0.0719) loss: 0.8684 (0.8727) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:03:34 loss: 0.9040 (0.9040) time: 3.4540 data: 3.3595 max mem: 8299 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8923 (0.8918) time: 0.1459 data: 0.1213 max mem: 8299 +Eval (hcp-train-subset): [28] Total time: 0:00:14 (0.2310 s / it) +Averaged stats (hcp-train-subset): loss: 0.8923 (0.8918) +Eval (hcp-val): [28] [ 0/62] eta: 0:06:01 loss: 0.8890 (0.8890) time: 5.8332 data: 5.8033 max mem: 8299 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8856 (0.8874) time: 0.1040 data: 0.0784 max mem: 8299 +Eval (hcp-val): [28] Total time: 0:00:13 (0.2179 s / it) +Averaged stats (hcp-val): loss: 0.8856 (0.8874) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 10:18:53 lr: 0.000106 grad: 0.0435 (0.0435) loss: 0.9143 (0.9143) time: 5.9413 data: 5.8230 max mem: 8299 +Train: [29] [ 100/6250] eta: 0:20:46 lr: 0.000106 grad: 0.0647 (0.0722) loss: 0.8751 (0.8818) time: 0.1267 data: 0.0290 max mem: 8299 +Train: [29] [ 200/6250] eta: 0:17:49 lr: 0.000106 grad: 0.0727 (0.0711) loss: 0.8789 (0.8798) time: 0.1445 data: 0.0451 max mem: 8299 +Train: [29] [ 300/6250] eta: 0:16:44 lr: 0.000106 grad: 0.0703 (0.0724) loss: 0.8725 (0.8788) time: 0.1674 data: 0.0663 max mem: 8299 +Train: [29] [ 400/6250] eta: 0:15:47 lr: 0.000106 grad: 0.0661 (0.0739) loss: 0.8717 (0.8779) time: 0.1526 data: 0.0564 max mem: 8299 +Train: [29] [ 500/6250] eta: 0:15:20 lr: 0.000106 grad: 0.0634 (0.0722) loss: 0.8802 (0.8773) time: 0.1448 data: 0.0614 max mem: 8299 +Train: [29] [ 600/6250] eta: 0:15:00 lr: 0.000106 grad: 0.0598 (0.0709) loss: 0.8734 (0.8771) time: 0.1665 data: 0.0780 max mem: 8299 +Train: [29] [ 700/6250] eta: 0:14:37 lr: 0.000106 grad: 0.0626 (0.0701) loss: 0.8728 (0.8768) time: 0.1515 data: 0.0674 max mem: 8299 +Train: [29] [ 800/6250] eta: 0:14:27 lr: 0.000106 grad: 0.0653 (0.0693) loss: 0.8775 (0.8768) time: 0.1627 data: 0.0678 max mem: 8299 +Train: [29] [ 900/6250] eta: 0:14:09 lr: 0.000106 grad: 0.0630 (0.0688) loss: 0.8744 (0.8768) time: 0.1762 data: 0.0941 max mem: 8299 +Train: [29] [1000/6250] eta: 0:13:46 lr: 0.000106 grad: 0.0674 (0.0688) loss: 0.8719 (0.8768) time: 0.1576 data: 0.0622 max mem: 8299 +Train: [29] [1100/6250] eta: 0:13:28 lr: 0.000106 grad: 0.0644 (0.0689) loss: 0.8746 (0.8765) time: 0.1742 data: 0.0931 max mem: 8299 +Train: [29] [1200/6250] eta: 0:13:13 lr: 0.000106 grad: 0.0717 (0.0690) loss: 0.8678 (0.8760) time: 0.1577 data: 0.0833 max mem: 8299 +Train: [29] [1300/6250] eta: 0:13:03 lr: 0.000106 grad: 0.0684 (0.0693) loss: 0.8724 (0.8758) time: 0.1821 data: 0.1014 max mem: 8299 +Train: [29] [1400/6250] eta: 0:12:47 lr: 0.000106 grad: 0.0699 (0.0695) loss: 0.8699 (0.8755) time: 0.1597 data: 0.0858 max mem: 8299 +Train: [29] [1500/6250] eta: 0:12:35 lr: 0.000106 grad: 0.0643 (0.0694) loss: 0.8763 (0.8754) time: 0.1548 data: 0.0718 max mem: 8299 +Train: [29] [1600/6250] eta: 0:12:19 lr: 0.000106 grad: 0.0680 (0.0696) loss: 0.8708 (0.8752) time: 0.1790 data: 0.0907 max mem: 8299 +Train: [29] [1700/6250] eta: 0:12:03 lr: 0.000106 grad: 0.0703 (0.0698) loss: 0.8708 (0.8749) time: 0.1402 data: 0.0558 max mem: 8299 +Train: [29] [1800/6250] eta: 0:11:44 lr: 0.000106 grad: 0.0675 (0.0700) loss: 0.8639 (0.8747) time: 0.1684 data: 0.0909 max mem: 8299 +Train: [29] [1900/6250] eta: 0:11:28 lr: 0.000106 grad: 0.0666 (0.0702) loss: 0.8730 (0.8745) time: 0.1806 data: 0.1016 max mem: 8299 +Train: [29] [2000/6250] eta: 0:11:10 lr: 0.000106 grad: 0.0656 (0.0703) loss: 0.8816 (0.8745) time: 0.1442 data: 0.0649 max mem: 8299 +Train: [29] [2100/6250] eta: 0:10:54 lr: 0.000106 grad: 0.0667 (0.0703) loss: 0.8752 (0.8745) time: 0.1436 data: 0.0652 max mem: 8299 +Train: [29] [2200/6250] eta: 0:10:37 lr: 0.000106 grad: 0.0721 (0.0707) loss: 0.8792 (0.8744) time: 0.1334 data: 0.0601 max mem: 8299 +Train: [29] [2300/6250] eta: 0:10:20 lr: 0.000106 grad: 0.0669 (0.0708) loss: 0.8729 (0.8742) time: 0.1645 data: 0.0902 max mem: 8299 +Train: [29] [2400/6250] eta: 0:10:03 lr: 0.000106 grad: 0.0711 (0.0708) loss: 0.8752 (0.8741) time: 0.1300 data: 0.0307 max mem: 8299 +Train: [29] [2500/6250] eta: 0:09:47 lr: 0.000106 grad: 0.0679 (0.0708) loss: 0.8688 (0.8739) time: 0.1619 data: 0.0873 max mem: 8299 +Train: [29] [2600/6250] eta: 0:09:30 lr: 0.000106 grad: 0.0716 (0.0710) loss: 0.8673 (0.8737) time: 0.1486 data: 0.0673 max mem: 8299 +Train: [29] [2700/6250] eta: 0:09:14 lr: 0.000106 grad: 0.0654 (0.0710) loss: 0.8787 (0.8736) time: 0.1574 data: 0.0694 max mem: 8299 +Train: [29] [2800/6250] eta: 0:08:57 lr: 0.000106 grad: 0.0699 (0.0711) loss: 0.8683 (0.8736) time: 0.1219 data: 0.0484 max mem: 8299 +Train: [29] [2900/6250] eta: 0:08:41 lr: 0.000106 grad: 0.0689 (0.0712) loss: 0.8682 (0.8735) time: 0.1854 data: 0.1023 max mem: 8299 +Train: [29] [3000/6250] eta: 0:08:24 lr: 0.000106 grad: 0.0713 (0.0714) loss: 0.8682 (0.8734) time: 0.1676 data: 0.0866 max mem: 8299 +Train: [29] [3100/6250] eta: 0:08:07 lr: 0.000106 grad: 0.0708 (0.0715) loss: 0.8712 (0.8732) time: 0.1179 data: 0.0422 max mem: 8299 +Train: [29] [3200/6250] eta: 0:07:50 lr: 0.000106 grad: 0.0673 (0.0716) loss: 0.8739 (0.8731) time: 0.1367 data: 0.0513 max mem: 8299 +Train: [29] [3300/6250] eta: 0:07:35 lr: 0.000106 grad: 0.0681 (0.0716) loss: 0.8685 (0.8730) time: 0.1242 data: 0.0483 max mem: 8299 +Train: [29] [3400/6250] eta: 0:07:19 lr: 0.000106 grad: 0.0735 (0.0718) loss: 0.8676 (0.8729) time: 0.1446 data: 0.0657 max mem: 8299 +Train: [29] [3500/6250] eta: 0:07:03 lr: 0.000105 grad: 0.0743 (0.0720) loss: 0.8697 (0.8728) time: 0.1169 data: 0.0375 max mem: 8299 +Train: [29] [3600/6250] eta: 0:06:48 lr: 0.000105 grad: 0.0749 (0.0721) loss: 0.8724 (0.8727) time: 0.1689 data: 0.0771 max mem: 8299 +Train: [29] [3700/6250] eta: 0:06:32 lr: 0.000105 grad: 0.0686 (0.0722) loss: 0.8715 (0.8727) time: 0.1556 data: 0.0651 max mem: 8299 +Train: [29] [3800/6250] eta: 0:06:17 lr: 0.000105 grad: 0.0691 (0.0723) loss: 0.8731 (0.8726) time: 0.0953 data: 0.0147 max mem: 8299 +Train: [29] [3900/6250] eta: 0:06:01 lr: 0.000105 grad: 0.0754 (0.0723) loss: 0.8716 (0.8726) time: 0.1584 data: 0.0710 max mem: 8299 +Train: [29] [4000/6250] eta: 0:05:46 lr: 0.000105 grad: 0.0673 (0.0724) loss: 0.8723 (0.8726) time: 0.1217 data: 0.0351 max mem: 8299 +Train: [29] [4100/6250] eta: 0:05:30 lr: 0.000105 grad: 0.0728 (0.0724) loss: 0.8701 (0.8726) time: 0.1600 data: 0.0781 max mem: 8299 +Train: [29] [4200/6250] eta: 0:05:15 lr: 0.000105 grad: 0.0711 (0.0725) loss: 0.8733 (0.8725) time: 0.1912 data: 0.1197 max mem: 8299 +Train: [29] [4300/6250] eta: 0:04:59 lr: 0.000105 grad: 0.0706 (0.0726) loss: 0.8721 (0.8725) time: 0.1423 data: 0.0584 max mem: 8299 +Train: [29] [4400/6250] eta: 0:04:43 lr: 0.000105 grad: 0.0675 (0.0726) loss: 0.8699 (0.8725) time: 0.1311 data: 0.0383 max mem: 8299 +Train: [29] [4500/6250] eta: 0:04:28 lr: 0.000105 grad: 0.0726 (0.0727) loss: 0.8701 (0.8724) time: 0.1280 data: 0.0531 max mem: 8299 +Train: [29] [4600/6250] eta: 0:04:12 lr: 0.000105 grad: 0.0714 (0.0727) loss: 0.8747 (0.8724) time: 0.1510 data: 0.0661 max mem: 8299 +Train: [29] [4700/6250] eta: 0:03:57 lr: 0.000105 grad: 0.0744 (0.0728) loss: 0.8695 (0.8724) time: 0.1359 data: 0.0619 max mem: 8299 +Train: [29] [4800/6250] eta: 0:03:41 lr: 0.000105 grad: 0.0735 (0.0729) loss: 0.8731 (0.8724) time: 0.0950 data: 0.0002 max mem: 8299 +Train: [29] [4900/6250] eta: 0:03:26 lr: 0.000105 grad: 0.0692 (0.0729) loss: 0.8675 (0.8724) time: 0.1601 data: 0.0794 max mem: 8299 +Train: [29] [5000/6250] eta: 0:03:10 lr: 0.000105 grad: 0.0787 (0.0730) loss: 0.8644 (0.8723) time: 0.1193 data: 0.0412 max mem: 8299 +Train: [29] [5100/6250] eta: 0:02:55 lr: 0.000105 grad: 0.0716 (0.0730) loss: 0.8679 (0.8723) time: 0.1622 data: 0.0802 max mem: 8299 +Train: [29] [5200/6250] eta: 0:02:40 lr: 0.000105 grad: 0.0695 (0.0730) loss: 0.8736 (0.8723) time: 0.1351 data: 0.0640 max mem: 8299 +Train: [29] [5300/6250] eta: 0:02:24 lr: 0.000105 grad: 0.0743 (0.0731) loss: 0.8721 (0.8723) time: 0.1376 data: 0.0510 max mem: 8299 +Train: [29] [5400/6250] eta: 0:02:09 lr: 0.000105 grad: 0.0782 (0.0732) loss: 0.8730 (0.8723) time: 0.1440 data: 0.0726 max mem: 8299 +Train: [29] [5500/6250] eta: 0:01:54 lr: 0.000105 grad: 0.0726 (0.0732) loss: 0.8783 (0.8723) time: 0.1735 data: 0.0886 max mem: 8299 +Train: [29] [5600/6250] eta: 0:01:39 lr: 0.000105 grad: 0.0734 (0.0733) loss: 0.8707 (0.8722) time: 0.1296 data: 0.0484 max mem: 8299 +Train: [29] [5700/6250] eta: 0:01:23 lr: 0.000105 grad: 0.0785 (0.0734) loss: 0.8745 (0.8722) time: 0.1654 data: 0.0864 max mem: 8299 +Train: [29] [5800/6250] eta: 0:01:08 lr: 0.000105 grad: 0.0720 (0.0735) loss: 0.8742 (0.8722) time: 0.1493 data: 0.0761 max mem: 8299 +Train: [29] [5900/6250] eta: 0:00:53 lr: 0.000105 grad: 0.0730 (0.0735) loss: 0.8776 (0.8722) time: 0.1573 data: 0.0802 max mem: 8299 +Train: [29] [6000/6250] eta: 0:00:38 lr: 0.000105 grad: 0.0690 (0.0736) loss: 0.8788 (0.8723) time: 0.1561 data: 0.0764 max mem: 8299 +Train: [29] [6100/6250] eta: 0:00:22 lr: 0.000105 grad: 0.0721 (0.0737) loss: 0.8747 (0.8722) time: 0.1606 data: 0.0788 max mem: 8299 +Train: [29] [6200/6250] eta: 0:00:07 lr: 0.000105 grad: 0.0778 (0.0737) loss: 0.8733 (0.8722) time: 0.1068 data: 0.0280 max mem: 8299 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0827 (0.0738) loss: 0.8738 (0.8722) time: 0.1375 data: 0.0488 max mem: 8299 +Train: [29] Total time: 0:16:01 (0.1539 s / it) +Averaged stats: lr: 0.000105 grad: 0.0827 (0.0738) loss: 0.8738 (0.8722) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:05:42 loss: 0.9003 (0.9003) time: 5.5232 data: 5.4911 max mem: 8299 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8872 (0.8892) time: 0.1663 data: 0.1412 max mem: 8299 +Eval (hcp-train-subset): [29] Total time: 0:00:14 (0.2320 s / it) +Averaged stats (hcp-train-subset): loss: 0.8872 (0.8892) +Making plots (hcp-train-subset): example=10 +Eval (hcp-val): [29] [ 0/62] eta: 0:04:34 loss: 0.8902 (0.8902) time: 4.4210 data: 4.3035 max mem: 8299 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8849 (0.8876) time: 0.1212 data: 0.0955 max mem: 8299 +Eval (hcp-val): [29] Total time: 0:00:13 (0.2195 s / it) +Averaged stats (hcp-val): loss: 0.8849 (0.8876) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 8:41:13 lr: 0.000105 grad: 0.0385 (0.0385) loss: 0.9037 (0.9037) time: 5.0037 data: 4.7056 max mem: 8299 +Train: [30] [ 100/6250] eta: 0:19:55 lr: 0.000105 grad: 0.0664 (0.0883) loss: 0.8907 (0.8865) time: 0.1351 data: 0.0388 max mem: 8299 +Train: [30] [ 200/6250] eta: 0:17:28 lr: 0.000105 grad: 0.0664 (0.0888) loss: 0.8757 (0.8785) time: 0.1547 data: 0.0612 max mem: 8299 +Train: [30] [ 300/6250] eta: 0:16:11 lr: 0.000105 grad: 0.0726 (0.0845) loss: 0.8693 (0.8744) time: 0.1391 data: 0.0478 max mem: 8299 +Train: [30] [ 400/6250] eta: 0:15:31 lr: 0.000105 grad: 0.0653 (0.0815) loss: 0.8699 (0.8732) time: 0.1588 data: 0.0483 max mem: 8299 +Train: [30] [ 500/6250] eta: 0:15:05 lr: 0.000105 grad: 0.0703 (0.0792) loss: 0.8773 (0.8732) time: 0.1384 data: 0.0367 max mem: 8299 +Train: [30] [ 600/6250] eta: 0:14:53 lr: 0.000105 grad: 0.0700 (0.0777) loss: 0.8748 (0.8733) time: 0.1734 data: 0.0810 max mem: 8299 +Train: [30] [ 700/6250] eta: 0:14:42 lr: 0.000105 grad: 0.0656 (0.0762) loss: 0.8800 (0.8738) time: 0.1149 data: 0.0281 max mem: 8299 +Train: [30] [ 800/6250] eta: 0:14:32 lr: 0.000105 grad: 0.0632 (0.0752) loss: 0.8736 (0.8739) time: 0.1605 data: 0.0765 max mem: 8299 +Train: [30] [ 900/6250] eta: 0:14:27 lr: 0.000105 grad: 0.0655 (0.0745) loss: 0.8775 (0.8740) time: 0.1835 data: 0.1051 max mem: 8299 +Train: [30] [1000/6250] eta: 0:14:16 lr: 0.000105 grad: 0.0656 (0.0741) loss: 0.8710 (0.8740) time: 0.1623 data: 0.0836 max mem: 8299 +Train: [30] [1100/6250] eta: 0:13:56 lr: 0.000105 grad: 0.0652 (0.0734) loss: 0.8694 (0.8739) time: 0.1541 data: 0.0690 max mem: 8299 +Train: [30] [1200/6250] eta: 0:13:39 lr: 0.000105 grad: 0.0648 (0.0731) loss: 0.8772 (0.8739) time: 0.1671 data: 0.0921 max mem: 8299 +Train: [30] [1300/6250] eta: 0:13:19 lr: 0.000105 grad: 0.0601 (0.0728) loss: 0.8769 (0.8738) time: 0.1539 data: 0.0713 max mem: 8299 +Train: [30] [1400/6250] eta: 0:12:59 lr: 0.000104 grad: 0.0638 (0.0724) loss: 0.8716 (0.8739) time: 0.1254 data: 0.0386 max mem: 8299 +Train: [30] [1500/6250] eta: 0:12:40 lr: 0.000104 grad: 0.0708 (0.0723) loss: 0.8704 (0.8739) time: 0.1372 data: 0.0538 max mem: 8299 +Train: [30] [1600/6250] eta: 0:12:21 lr: 0.000104 grad: 0.0682 (0.0722) loss: 0.8661 (0.8738) time: 0.1693 data: 0.0874 max mem: 8299 +Train: [30] [1700/6250] eta: 0:12:04 lr: 0.000104 grad: 0.0701 (0.0720) loss: 0.8681 (0.8737) time: 0.1677 data: 0.0942 max mem: 8299 +Train: [30] [1800/6250] eta: 0:11:45 lr: 0.000104 grad: 0.0676 (0.0719) loss: 0.8689 (0.8737) time: 0.1658 data: 0.0811 max mem: 8299 +Train: [30] [1900/6250] eta: 0:11:28 lr: 0.000104 grad: 0.0697 (0.0720) loss: 0.8679 (0.8735) time: 0.1573 data: 0.0843 max mem: 8299 +Train: [30] [2000/6250] eta: 0:11:12 lr: 0.000104 grad: 0.0688 (0.0719) loss: 0.8706 (0.8734) time: 0.1840 data: 0.0968 max mem: 8299 +Train: [30] [2100/6250] eta: 0:10:54 lr: 0.000104 grad: 0.0718 (0.0719) loss: 0.8702 (0.8731) time: 0.1771 data: 0.0954 max mem: 8299 +Train: [30] [2200/6250] eta: 0:10:38 lr: 0.000104 grad: 0.0673 (0.0719) loss: 0.8670 (0.8730) time: 0.1099 data: 0.0348 max mem: 8299 +Train: [30] [2300/6250] eta: 0:10:19 lr: 0.000104 grad: 0.0696 (0.0718) loss: 0.8740 (0.8730) time: 0.1540 data: 0.0716 max mem: 8299 +Train: [30] [2400/6250] eta: 0:10:03 lr: 0.000104 grad: 0.0673 (0.0719) loss: 0.8697 (0.8729) time: 0.1786 data: 0.1000 max mem: 8299 +Train: [30] [2500/6250] eta: 0:09:46 lr: 0.000104 grad: 0.0677 (0.0720) loss: 0.8649 (0.8728) time: 0.1716 data: 0.0985 max mem: 8299 +Train: [30] [2600/6250] eta: 0:09:30 lr: 0.000104 grad: 0.0705 (0.0720) loss: 0.8688 (0.8727) time: 0.2021 data: 0.1123 max mem: 8299 +Train: [30] [2700/6250] eta: 0:09:12 lr: 0.000104 grad: 0.0665 (0.0721) loss: 0.8797 (0.8727) time: 0.1516 data: 0.0768 max mem: 8299 +Train: [30] [2800/6250] eta: 0:08:57 lr: 0.000104 grad: 0.0703 (0.0721) loss: 0.8700 (0.8726) time: 0.1449 data: 0.0703 max mem: 8299 +Train: [30] [2900/6250] eta: 0:08:42 lr: 0.000104 grad: 0.0672 (0.0721) loss: 0.8713 (0.8725) time: 0.1411 data: 0.0584 max mem: 8299 +Train: [30] [3000/6250] eta: 0:08:26 lr: 0.000104 grad: 0.0699 (0.0722) loss: 0.8763 (0.8725) time: 0.1663 data: 0.0811 max mem: 8299 +Train: [30] [3100/6250] eta: 0:08:11 lr: 0.000104 grad: 0.0730 (0.0722) loss: 0.8756 (0.8725) time: 0.1833 data: 0.0884 max mem: 8299 +Train: [30] [3200/6250] eta: 0:07:55 lr: 0.000104 grad: 0.0719 (0.0724) loss: 0.8712 (0.8725) time: 0.2076 data: 0.1252 max mem: 8299 +Train: [30] [3300/6250] eta: 0:07:38 lr: 0.000104 grad: 0.0680 (0.0724) loss: 0.8775 (0.8725) time: 0.1558 data: 0.0785 max mem: 8299 +Train: [30] [3400/6250] eta: 0:07:22 lr: 0.000104 grad: 0.0778 (0.0725) loss: 0.8703 (0.8725) time: 0.1560 data: 0.0796 max mem: 8299 +Train: [30] [3500/6250] eta: 0:07:06 lr: 0.000104 grad: 0.0755 (0.0726) loss: 0.8720 (0.8724) time: 0.1195 data: 0.0351 max mem: 8299 +Train: [30] [3600/6250] eta: 0:06:50 lr: 0.000104 grad: 0.0707 (0.0728) loss: 0.8684 (0.8723) time: 0.1477 data: 0.0630 max mem: 8299 +Train: [30] [3700/6250] eta: 0:06:34 lr: 0.000104 grad: 0.0710 (0.0731) loss: 0.8747 (0.8723) time: 0.1758 data: 0.0899 max mem: 8299 +Train: [30] [3800/6250] eta: 0:06:18 lr: 0.000104 grad: 0.0716 (0.0732) loss: 0.8695 (0.8723) time: 0.1290 data: 0.0514 max mem: 8299 +Train: [30] [3900/6250] eta: 0:06:02 lr: 0.000104 grad: 0.0715 (0.0732) loss: 0.8742 (0.8723) time: 0.1318 data: 0.0451 max mem: 8299 +Train: [30] [4000/6250] eta: 0:05:47 lr: 0.000104 grad: 0.0761 (0.0733) loss: 0.8711 (0.8722) time: 0.1968 data: 0.1213 max mem: 8299 +Train: [30] [4100/6250] eta: 0:05:30 lr: 0.000104 grad: 0.0687 (0.0733) loss: 0.8705 (0.8722) time: 0.1627 data: 0.0788 max mem: 8299 +Train: [30] [4200/6250] eta: 0:05:15 lr: 0.000104 grad: 0.0747 (0.0734) loss: 0.8683 (0.8722) time: 0.1624 data: 0.0902 max mem: 8299 +Train: [30] [4300/6250] eta: 0:04:59 lr: 0.000104 grad: 0.0734 (0.0735) loss: 0.8735 (0.8721) time: 0.1565 data: 0.0776 max mem: 8299 +Train: [30] [4400/6250] eta: 0:04:43 lr: 0.000104 grad: 0.0784 (0.0736) loss: 0.8625 (0.8721) time: 0.1715 data: 0.1005 max mem: 8299 +Train: [30] [4500/6250] eta: 0:04:28 lr: 0.000104 grad: 0.0751 (0.0737) loss: 0.8734 (0.8720) time: 0.1688 data: 0.1011 max mem: 8299 +Train: [30] [4600/6250] eta: 0:04:12 lr: 0.000104 grad: 0.0696 (0.0738) loss: 0.8736 (0.8720) time: 0.1342 data: 0.0622 max mem: 8299 +Train: [30] [4700/6250] eta: 0:03:57 lr: 0.000104 grad: 0.0727 (0.0739) loss: 0.8749 (0.8720) time: 0.1723 data: 0.0987 max mem: 8299 +Train: [30] [4800/6250] eta: 0:03:41 lr: 0.000104 grad: 0.0749 (0.0740) loss: 0.8719 (0.8719) time: 0.1243 data: 0.0493 max mem: 8299 +Train: [30] [4900/6250] eta: 0:03:26 lr: 0.000104 grad: 0.0697 (0.0740) loss: 0.8718 (0.8719) time: 0.1125 data: 0.0398 max mem: 8299 +Train: [30] [5000/6250] eta: 0:03:11 lr: 0.000104 grad: 0.0728 (0.0740) loss: 0.8717 (0.8720) time: 0.1511 data: 0.0652 max mem: 8299 +Train: [30] [5100/6250] eta: 0:02:55 lr: 0.000104 grad: 0.0676 (0.0741) loss: 0.8770 (0.8720) time: 0.1839 data: 0.1057 max mem: 8299 +Train: [30] [5200/6250] eta: 0:02:40 lr: 0.000104 grad: 0.0686 (0.0742) loss: 0.8732 (0.8720) time: 0.1316 data: 0.0480 max mem: 8299 +Train: [30] [5300/6250] eta: 0:02:25 lr: 0.000104 grad: 0.0721 (0.0743) loss: 0.8798 (0.8720) time: 0.1607 data: 0.0775 max mem: 8299 +Train: [30] [5400/6250] eta: 0:02:09 lr: 0.000103 grad: 0.0683 (0.0743) loss: 0.8649 (0.8720) time: 0.1703 data: 0.0900 max mem: 8299 +Train: [30] [5500/6250] eta: 0:01:54 lr: 0.000103 grad: 0.0683 (0.0743) loss: 0.8737 (0.8721) time: 0.1247 data: 0.0526 max mem: 8299 +Train: [30] [5600/6250] eta: 0:01:39 lr: 0.000103 grad: 0.0734 (0.0744) loss: 0.8705 (0.8721) time: 0.1395 data: 0.0591 max mem: 8299 +Train: [30] [5700/6250] eta: 0:01:24 lr: 0.000103 grad: 0.0772 (0.0744) loss: 0.8764 (0.8721) time: 0.1325 data: 0.0654 max mem: 8299 +Train: [30] [5800/6250] eta: 0:01:09 lr: 0.000103 grad: 0.0711 (0.0744) loss: 0.8743 (0.8721) time: 0.1545 data: 0.0767 max mem: 8299 +Train: [30] [5900/6250] eta: 0:00:53 lr: 0.000103 grad: 0.0723 (0.0744) loss: 0.8699 (0.8721) time: 0.1576 data: 0.0736 max mem: 8299 +Train: [30] [6000/6250] eta: 0:00:38 lr: 0.000103 grad: 0.0698 (0.0744) loss: 0.8742 (0.8721) time: 0.1521 data: 0.0753 max mem: 8299 +Train: [30] [6100/6250] eta: 0:00:23 lr: 0.000103 grad: 0.0667 (0.0744) loss: 0.8790 (0.8722) time: 0.1625 data: 0.0748 max mem: 8299 +Train: [30] [6200/6250] eta: 0:00:07 lr: 0.000103 grad: 0.0666 (0.0745) loss: 0.8775 (0.8722) time: 0.1211 data: 0.0326 max mem: 8299 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0685 (0.0745) loss: 0.8691 (0.8722) time: 0.1657 data: 0.0755 max mem: 8299 +Train: [30] Total time: 0:16:04 (0.1543 s / it) +Averaged stats: lr: 0.000103 grad: 0.0685 (0.0745) loss: 0.8691 (0.8722) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:04:06 loss: 0.8920 (0.8920) time: 3.9693 data: 3.8626 max mem: 8299 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8884 (0.8887) time: 0.1202 data: 0.0945 max mem: 8299 +Eval (hcp-train-subset): [30] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-train-subset): loss: 0.8884 (0.8887) +Eval (hcp-val): [30] [ 0/62] eta: 0:05:11 loss: 0.8813 (0.8813) time: 5.0194 data: 4.9894 max mem: 8299 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8844 (0.8861) time: 0.1287 data: 0.1035 max mem: 8299 +Eval (hcp-val): [30] Total time: 0:00:13 (0.2256 s / it) +Averaged stats (hcp-val): loss: 0.8844 (0.8861) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 11:27:25 lr: 0.000103 grad: 0.0990 (0.0990) loss: 0.9200 (0.9200) time: 6.5993 data: 6.4605 max mem: 8299 +Train: [31] [ 100/6250] eta: 0:20:49 lr: 0.000103 grad: 0.0685 (0.0834) loss: 0.8826 (0.8825) time: 0.1189 data: 0.0041 max mem: 8299 +Train: [31] [ 200/6250] eta: 0:17:39 lr: 0.000103 grad: 0.0791 (0.0821) loss: 0.8723 (0.8778) time: 0.1416 data: 0.0331 max mem: 8299 +Train: [31] [ 300/6250] eta: 0:16:15 lr: 0.000103 grad: 0.0669 (0.0799) loss: 0.8797 (0.8765) time: 0.1225 data: 0.0506 max mem: 8299 +Train: [31] [ 400/6250] eta: 0:15:35 lr: 0.000103 grad: 0.0715 (0.0783) loss: 0.8751 (0.8756) time: 0.1439 data: 0.0546 max mem: 8299 +Train: [31] [ 500/6250] eta: 0:15:18 lr: 0.000103 grad: 0.0688 (0.0772) loss: 0.8769 (0.8751) time: 0.1419 data: 0.0583 max mem: 8299 +Train: [31] [ 600/6250] eta: 0:15:07 lr: 0.000103 grad: 0.0688 (0.0760) loss: 0.8705 (0.8748) time: 0.1893 data: 0.1021 max mem: 8299 +Train: [31] [ 700/6250] eta: 0:14:49 lr: 0.000103 grad: 0.0657 (0.0750) loss: 0.8724 (0.8745) time: 0.1773 data: 0.0768 max mem: 8299 +Train: [31] [ 800/6250] eta: 0:14:28 lr: 0.000103 grad: 0.0631 (0.0743) loss: 0.8744 (0.8742) time: 0.1399 data: 0.0498 max mem: 8299 +Train: [31] [ 900/6250] eta: 0:14:08 lr: 0.000103 grad: 0.0735 (0.0743) loss: 0.8690 (0.8740) time: 0.1619 data: 0.0810 max mem: 8299 +Train: [31] [1000/6250] eta: 0:13:48 lr: 0.000103 grad: 0.0746 (0.0742) loss: 0.8674 (0.8737) time: 0.1371 data: 0.0488 max mem: 8299 +Train: [31] [1100/6250] eta: 0:13:26 lr: 0.000103 grad: 0.0658 (0.0739) loss: 0.8737 (0.8735) time: 0.1368 data: 0.0565 max mem: 8299 +Train: [31] [1200/6250] eta: 0:13:06 lr: 0.000103 grad: 0.0688 (0.0741) loss: 0.8727 (0.8732) time: 0.1487 data: 0.0624 max mem: 8299 +Train: [31] [1300/6250] eta: 0:12:51 lr: 0.000103 grad: 0.0781 (0.0741) loss: 0.8668 (0.8729) time: 0.1817 data: 0.1078 max mem: 8299 +Train: [31] [1400/6250] eta: 0:12:35 lr: 0.000103 grad: 0.0671 (0.0744) loss: 0.8666 (0.8728) time: 0.1879 data: 0.1063 max mem: 8299 +Train: [31] [1500/6250] eta: 0:12:16 lr: 0.000103 grad: 0.0681 (0.0745) loss: 0.8748 (0.8727) time: 0.1600 data: 0.0820 max mem: 8299 +Train: [31] [1600/6250] eta: 0:12:00 lr: 0.000103 grad: 0.0741 (0.0744) loss: 0.8682 (0.8725) time: 0.1521 data: 0.0664 max mem: 8299 +Train: [31] [1700/6250] eta: 0:11:43 lr: 0.000103 grad: 0.0764 (0.0747) loss: 0.8715 (0.8723) time: 0.1290 data: 0.0506 max mem: 8299 +Train: [31] [1800/6250] eta: 0:11:29 lr: 0.000103 grad: 0.0757 (0.0748) loss: 0.8701 (0.8721) time: 0.1670 data: 0.0868 max mem: 8299 +Train: [31] [1900/6250] eta: 0:11:12 lr: 0.000103 grad: 0.0748 (0.0748) loss: 0.8733 (0.8720) time: 0.1468 data: 0.0609 max mem: 8299 +Train: [31] [2000/6250] eta: 0:10:55 lr: 0.000103 grad: 0.0714 (0.0748) loss: 0.8731 (0.8719) time: 0.1329 data: 0.0571 max mem: 8299 +Train: [31] [2100/6250] eta: 0:10:39 lr: 0.000103 grad: 0.0729 (0.0749) loss: 0.8713 (0.8719) time: 0.1743 data: 0.0972 max mem: 8299 +Train: [31] [2200/6250] eta: 0:10:23 lr: 0.000103 grad: 0.0752 (0.0750) loss: 0.8706 (0.8719) time: 0.1141 data: 0.0320 max mem: 8299 +Train: [31] [2300/6250] eta: 0:10:09 lr: 0.000103 grad: 0.0681 (0.0749) loss: 0.8744 (0.8720) time: 0.1656 data: 0.0808 max mem: 8299 +Train: [31] [2400/6250] eta: 0:09:53 lr: 0.000103 grad: 0.0758 (0.0749) loss: 0.8742 (0.8720) time: 0.1692 data: 0.0961 max mem: 8299 +Train: [31] [2500/6250] eta: 0:09:38 lr: 0.000103 grad: 0.0779 (0.0749) loss: 0.8707 (0.8720) time: 0.1339 data: 0.0589 max mem: 8299 +Train: [31] [2600/6250] eta: 0:09:23 lr: 0.000103 grad: 0.0741 (0.0748) loss: 0.8674 (0.8721) time: 0.1221 data: 0.0294 max mem: 8299 +Train: [31] [2700/6250] eta: 0:09:08 lr: 0.000103 grad: 0.0685 (0.0748) loss: 0.8749 (0.8721) time: 0.2231 data: 0.1395 max mem: 8299 +Train: [31] [2800/6250] eta: 0:08:51 lr: 0.000103 grad: 0.0729 (0.0748) loss: 0.8748 (0.8721) time: 0.1247 data: 0.0416 max mem: 8299 +Train: [31] [2900/6250] eta: 0:08:33 lr: 0.000103 grad: 0.0741 (0.0748) loss: 0.8740 (0.8721) time: 0.1237 data: 0.0429 max mem: 8299 +Train: [31] [3000/6250] eta: 0:08:19 lr: 0.000103 grad: 0.0732 (0.0750) loss: 0.8686 (0.8719) time: 0.1731 data: 0.0892 max mem: 8299 +Train: [31] [3100/6250] eta: 0:08:03 lr: 0.000103 grad: 0.0731 (0.0750) loss: 0.8703 (0.8718) time: 0.1428 data: 0.0642 max mem: 8299 +Train: [31] [3200/6250] eta: 0:07:48 lr: 0.000102 grad: 0.0802 (0.0751) loss: 0.8692 (0.8717) time: 0.1846 data: 0.1016 max mem: 8299 +Train: [31] [3300/6250] eta: 0:07:32 lr: 0.000102 grad: 0.0706 (0.0753) loss: 0.8690 (0.8716) time: 0.1240 data: 0.0434 max mem: 8299 +Train: [31] [3400/6250] eta: 0:07:17 lr: 0.000102 grad: 0.0743 (0.0754) loss: 0.8720 (0.8715) time: 0.1556 data: 0.0723 max mem: 8299 +Train: [31] [3500/6250] eta: 0:07:01 lr: 0.000102 grad: 0.0794 (0.0755) loss: 0.8691 (0.8715) time: 0.1530 data: 0.0753 max mem: 8299 +Train: [31] [3600/6250] eta: 0:06:46 lr: 0.000102 grad: 0.0777 (0.0756) loss: 0.8664 (0.8714) time: 0.1320 data: 0.0433 max mem: 8299 +Train: [31] [3700/6250] eta: 0:06:31 lr: 0.000102 grad: 0.0726 (0.0757) loss: 0.8748 (0.8714) time: 0.1497 data: 0.0713 max mem: 8299 +Train: [31] [3800/6250] eta: 0:06:16 lr: 0.000102 grad: 0.0763 (0.0757) loss: 0.8680 (0.8713) time: 0.1455 data: 0.0710 max mem: 8299 +Train: [31] [3900/6250] eta: 0:06:00 lr: 0.000102 grad: 0.0775 (0.0757) loss: 0.8708 (0.8713) time: 0.1639 data: 0.0755 max mem: 8299 +Train: [31] [4000/6250] eta: 0:05:45 lr: 0.000102 grad: 0.0807 (0.0759) loss: 0.8734 (0.8713) time: 0.1593 data: 0.0806 max mem: 8299 +Train: [31] [4100/6250] eta: 0:05:29 lr: 0.000102 grad: 0.0731 (0.0759) loss: 0.8797 (0.8713) time: 0.1508 data: 0.0692 max mem: 8299 +Train: [31] [4200/6250] eta: 0:05:14 lr: 0.000102 grad: 0.0763 (0.0759) loss: 0.8704 (0.8713) time: 0.1336 data: 0.0589 max mem: 8299 +Train: [31] [4300/6250] eta: 0:04:58 lr: 0.000102 grad: 0.0713 (0.0759) loss: 0.8701 (0.8713) time: 0.0974 data: 0.0164 max mem: 8299 +Train: [31] [4400/6250] eta: 0:04:43 lr: 0.000102 grad: 0.0710 (0.0759) loss: 0.8763 (0.8712) time: 0.1347 data: 0.0413 max mem: 8299 +Train: [31] [4500/6250] eta: 0:04:27 lr: 0.000102 grad: 0.0729 (0.0758) loss: 0.8699 (0.8712) time: 0.1519 data: 0.0818 max mem: 8299 +Train: [31] [4600/6250] eta: 0:04:12 lr: 0.000102 grad: 0.0736 (0.0758) loss: 0.8735 (0.8712) time: 0.1877 data: 0.1038 max mem: 8299 +Train: [31] [4700/6250] eta: 0:03:57 lr: 0.000102 grad: 0.0694 (0.0758) loss: 0.8763 (0.8712) time: 0.1964 data: 0.1209 max mem: 8299 +Train: [31] [4800/6250] eta: 0:03:41 lr: 0.000102 grad: 0.0702 (0.0758) loss: 0.8685 (0.8712) time: 0.1954 data: 0.1116 max mem: 8299 +Train: [31] [4900/6250] eta: 0:03:26 lr: 0.000102 grad: 0.0760 (0.0758) loss: 0.8681 (0.8712) time: 0.1387 data: 0.0625 max mem: 8299 +Train: [31] [5000/6250] eta: 0:03:11 lr: 0.000102 grad: 0.0704 (0.0758) loss: 0.8701 (0.8712) time: 0.2253 data: 0.1346 max mem: 8299 +Train: [31] [5100/6250] eta: 0:02:56 lr: 0.000102 grad: 0.0750 (0.0758) loss: 0.8716 (0.8712) time: 0.1594 data: 0.0647 max mem: 8299 +Train: [31] [5200/6250] eta: 0:02:40 lr: 0.000102 grad: 0.0724 (0.0757) loss: 0.8762 (0.8711) time: 0.1310 data: 0.0559 max mem: 8299 +Train: [31] [5300/6250] eta: 0:02:25 lr: 0.000102 grad: 0.0706 (0.0757) loss: 0.8723 (0.8711) time: 0.2036 data: 0.1149 max mem: 8299 +Train: [31] [5400/6250] eta: 0:02:10 lr: 0.000102 grad: 0.0724 (0.0756) loss: 0.8735 (0.8711) time: 0.2190 data: 0.1518 max mem: 8299 +Train: [31] [5500/6250] eta: 0:01:55 lr: 0.000102 grad: 0.0728 (0.0757) loss: 0.8675 (0.8711) time: 0.1554 data: 0.0713 max mem: 8299 +Train: [31] [5600/6250] eta: 0:01:39 lr: 0.000102 grad: 0.0736 (0.0757) loss: 0.8715 (0.8711) time: 0.1483 data: 0.0706 max mem: 8299 +Train: [31] [5700/6250] eta: 0:01:24 lr: 0.000102 grad: 0.0731 (0.0757) loss: 0.8708 (0.8711) time: 0.1783 data: 0.0968 max mem: 8299 +Train: [31] [5800/6250] eta: 0:01:09 lr: 0.000102 grad: 0.0714 (0.0757) loss: 0.8715 (0.8711) time: 0.1568 data: 0.0841 max mem: 8299 +Train: [31] [5900/6250] eta: 0:00:53 lr: 0.000102 grad: 0.0754 (0.0757) loss: 0.8720 (0.8711) time: 0.1316 data: 0.0513 max mem: 8299 +Train: [31] [6000/6250] eta: 0:00:38 lr: 0.000102 grad: 0.0767 (0.0756) loss: 0.8719 (0.8711) time: 0.1547 data: 0.0514 max mem: 8299 +Train: [31] [6100/6250] eta: 0:00:22 lr: 0.000102 grad: 0.0739 (0.0756) loss: 0.8693 (0.8711) time: 0.1391 data: 0.0592 max mem: 8299 +Train: [31] [6200/6250] eta: 0:00:07 lr: 0.000102 grad: 0.0717 (0.0756) loss: 0.8693 (0.8711) time: 0.1405 data: 0.0594 max mem: 8299 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0743 (0.0756) loss: 0.8695 (0.8711) time: 0.1449 data: 0.0447 max mem: 8299 +Train: [31] Total time: 0:16:00 (0.1537 s / it) +Averaged stats: lr: 0.000102 grad: 0.0743 (0.0756) loss: 0.8695 (0.8711) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:04:56 loss: 0.9042 (0.9042) time: 4.7755 data: 4.7393 max mem: 8299 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8905 (0.8904) time: 0.1343 data: 0.1093 max mem: 8299 +Eval (hcp-train-subset): [31] Total time: 0:00:13 (0.2249 s / it) +Averaged stats (hcp-train-subset): loss: 0.8905 (0.8904) +Eval (hcp-val): [31] [ 0/62] eta: 0:03:36 loss: 0.8885 (0.8885) time: 3.4924 data: 3.4172 max mem: 8299 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8878 (0.8888) time: 0.1369 data: 0.1112 max mem: 8299 +Eval (hcp-val): [31] Total time: 0:00:13 (0.2208 s / it) +Averaged stats (hcp-val): loss: 0.8878 (0.8888) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 9:21:49 lr: 0.000102 grad: nan (nan) loss: 0.9245 (0.9245) time: 5.3935 data: 5.0366 max mem: 8299 +Train: [32] [ 100/6250] eta: 0:21:33 lr: 0.000102 grad: 0.0707 (0.0825) loss: 0.8785 (0.8787) time: 0.1688 data: 0.0632 max mem: 8299 +Train: [32] [ 200/6250] eta: 0:17:51 lr: 0.000102 grad: 0.0690 (0.0777) loss: 0.8810 (0.8780) time: 0.1351 data: 0.0501 max mem: 8299 +Train: [32] [ 300/6250] eta: 0:16:40 lr: 0.000102 grad: 0.0652 (0.0755) loss: 0.8799 (0.8776) time: 0.1567 data: 0.0698 max mem: 8299 +Train: [32] [ 400/6250] eta: 0:15:46 lr: 0.000102 grad: 0.0670 (0.0737) loss: 0.8781 (0.8774) time: 0.1498 data: 0.0621 max mem: 8299 +Train: [32] [ 500/6250] eta: 0:15:14 lr: 0.000102 grad: 0.0658 (0.0726) loss: 0.8758 (0.8769) time: 0.1395 data: 0.0600 max mem: 8299 +Train: [32] [ 600/6250] eta: 0:15:01 lr: 0.000102 grad: 0.0655 (0.0723) loss: 0.8706 (0.8763) time: 0.1665 data: 0.0790 max mem: 8299 +Train: [32] [ 700/6250] eta: 0:14:47 lr: 0.000102 grad: 0.0605 (0.0724) loss: 0.8722 (0.8757) time: 0.1707 data: 0.0866 max mem: 8299 +Train: [32] [ 800/6250] eta: 0:14:28 lr: 0.000101 grad: 0.0673 (0.0721) loss: 0.8704 (0.8755) time: 0.1478 data: 0.0573 max mem: 8299 +Train: [32] [ 900/6250] eta: 0:14:07 lr: 0.000101 grad: 0.0667 (0.0718) loss: 0.8746 (0.8755) time: 0.1566 data: 0.0709 max mem: 8299 +Train: [32] [1000/6250] eta: 0:13:45 lr: 0.000101 grad: 0.0728 (0.0719) loss: 0.8701 (0.8752) time: 0.1522 data: 0.0656 max mem: 8299 +Train: [32] [1100/6250] eta: 0:13:22 lr: 0.000101 grad: 0.0644 (0.0719) loss: 0.8777 (0.8752) time: 0.1453 data: 0.0638 max mem: 8299 +Train: [32] [1200/6250] eta: 0:13:05 lr: 0.000101 grad: 0.0701 (0.0721) loss: 0.8687 (0.8752) time: 0.1255 data: 0.0511 max mem: 8299 +Train: [32] [1300/6250] eta: 0:12:46 lr: 0.000101 grad: 0.0710 (0.0720) loss: 0.8770 (0.8752) time: 0.1194 data: 0.0440 max mem: 8299 +Train: [32] [1400/6250] eta: 0:12:27 lr: 0.000101 grad: 0.0695 (0.0719) loss: 0.8752 (0.8751) time: 0.1384 data: 0.0527 max mem: 8299 +Train: [32] [1500/6250] eta: 0:12:10 lr: 0.000101 grad: 0.0719 (0.0719) loss: 0.8694 (0.8750) time: 0.1432 data: 0.0661 max mem: 8299 +Train: [32] [1600/6250] eta: 0:12:02 lr: 0.000101 grad: 0.0693 (0.0718) loss: 0.8764 (0.8749) time: 0.2108 data: 0.1284 max mem: 8299 +Train: [32] [1700/6250] eta: 0:11:43 lr: 0.000101 grad: 0.0667 (0.0719) loss: 0.8725 (0.8748) time: 0.1446 data: 0.0666 max mem: 8299 +Train: [32] [1800/6250] eta: 0:11:24 lr: 0.000101 grad: 0.0761 (0.0720) loss: 0.8661 (0.8747) time: 0.1572 data: 0.0855 max mem: 8299 +Train: [32] [1900/6250] eta: 0:11:05 lr: 0.000101 grad: 0.0671 (0.0722) loss: 0.8730 (0.8745) time: 0.1298 data: 0.0515 max mem: 8299 +Train: [32] [2000/6250] eta: 0:10:47 lr: 0.000101 grad: 0.0698 (0.0723) loss: 0.8728 (0.8743) time: 0.1363 data: 0.0603 max mem: 8299 +Train: [32] [2100/6250] eta: 0:10:29 lr: 0.000101 grad: 0.0697 (0.0723) loss: 0.8678 (0.8740) time: 0.1329 data: 0.0513 max mem: 8299 +Train: [32] [2200/6250] eta: 0:10:10 lr: 0.000101 grad: 0.0744 (0.0725) loss: 0.8721 (0.8738) time: 0.1404 data: 0.0719 max mem: 8299 +Train: [32] [2300/6250] eta: 0:09:51 lr: 0.000101 grad: 0.0726 (0.0726) loss: 0.8703 (0.8736) time: 0.1281 data: 0.0560 max mem: 8299 +Train: [32] [2400/6250] eta: 0:09:32 lr: 0.000101 grad: 0.0700 (0.0727) loss: 0.8669 (0.8735) time: 0.1197 data: 0.0477 max mem: 8299 +Train: [32] [2500/6250] eta: 0:09:14 lr: 0.000101 grad: 0.0724 (0.0729) loss: 0.8705 (0.8734) time: 0.1129 data: 0.0284 max mem: 8299 +Train: [32] [2600/6250] eta: 0:08:56 lr: 0.000101 grad: 0.0721 (0.0730) loss: 0.8745 (0.8733) time: 0.1231 data: 0.0397 max mem: 8299 +Train: [32] [2700/6250] eta: 0:08:40 lr: 0.000101 grad: 0.0733 (0.0732) loss: 0.8702 (0.8732) time: 0.1204 data: 0.0425 max mem: 8299 +Train: [32] [2800/6250] eta: 0:08:23 lr: 0.000101 grad: 0.0758 (0.0733) loss: 0.8689 (0.8731) time: 0.1318 data: 0.0595 max mem: 8299 +Train: [32] [2900/6250] eta: 0:08:06 lr: 0.000101 grad: 0.0716 (0.0735) loss: 0.8693 (0.8730) time: 0.1232 data: 0.0493 max mem: 8299 +Train: [32] [3000/6250] eta: 0:07:49 lr: 0.000101 grad: 0.0705 (0.0736) loss: 0.8698 (0.8729) time: 0.1260 data: 0.0493 max mem: 8299 +Train: [32] [3100/6250] eta: 0:07:32 lr: 0.000101 grad: 0.0797 (0.0738) loss: 0.8718 (0.8729) time: 0.1372 data: 0.0639 max mem: 8299 +Train: [32] [3200/6250] eta: 0:07:17 lr: 0.000101 grad: 0.0695 (0.0738) loss: 0.8698 (0.8728) time: 0.1469 data: 0.0677 max mem: 8299 +Train: [32] [3300/6250] eta: 0:07:00 lr: 0.000101 grad: 0.0648 (0.0738) loss: 0.8697 (0.8728) time: 0.1084 data: 0.0357 max mem: 8299 +Train: [32] [3400/6250] eta: 0:06:45 lr: 0.000101 grad: 0.0672 (0.0738) loss: 0.8723 (0.8727) time: 0.1503 data: 0.0651 max mem: 8299 +Train: [32] [3500/6250] eta: 0:06:29 lr: 0.000101 grad: 0.0722 (0.0738) loss: 0.8674 (0.8726) time: 0.0943 data: 0.0180 max mem: 8299 +Train: [32] [3600/6250] eta: 0:06:14 lr: 0.000101 grad: 0.0707 (0.0738) loss: 0.8711 (0.8725) time: 0.1071 data: 0.0276 max mem: 8299 +Train: [32] [3700/6250] eta: 0:05:59 lr: 0.000101 grad: 0.0770 (0.0739) loss: 0.8722 (0.8724) time: 0.1357 data: 0.0579 max mem: 8299 +Train: [32] [3800/6250] eta: 0:05:44 lr: 0.000101 grad: 0.0741 (0.0740) loss: 0.8718 (0.8724) time: 0.1170 data: 0.0359 max mem: 8299 +Train: [32] [3900/6250] eta: 0:05:28 lr: 0.000101 grad: 0.0755 (0.0740) loss: 0.8684 (0.8723) time: 0.1047 data: 0.0344 max mem: 8299 +Train: [32] [4000/6250] eta: 0:05:14 lr: 0.000101 grad: 0.0758 (0.0741) loss: 0.8664 (0.8722) time: 0.1157 data: 0.0419 max mem: 8299 +Train: [32] [4100/6250] eta: 0:04:59 lr: 0.000101 grad: 0.0735 (0.0741) loss: 0.8679 (0.8721) time: 0.1142 data: 0.0299 max mem: 8299 +Train: [32] [4200/6250] eta: 0:04:44 lr: 0.000101 grad: 0.0708 (0.0742) loss: 0.8720 (0.8721) time: 0.1285 data: 0.0491 max mem: 8299 +Train: [32] [4300/6250] eta: 0:04:30 lr: 0.000101 grad: 0.0698 (0.0742) loss: 0.8691 (0.8721) time: 0.1379 data: 0.0640 max mem: 8299 +Train: [32] [4400/6250] eta: 0:04:15 lr: 0.000101 grad: 0.0728 (0.0743) loss: 0.8724 (0.8720) time: 0.1122 data: 0.0293 max mem: 8299 +Train: [32] [4500/6250] eta: 0:04:01 lr: 0.000101 grad: 0.0754 (0.0743) loss: 0.8746 (0.8720) time: 0.1274 data: 0.0517 max mem: 8299 +Train: [32] [4600/6250] eta: 0:03:47 lr: 0.000101 grad: 0.0699 (0.0743) loss: 0.8725 (0.8720) time: 0.1203 data: 0.0379 max mem: 8299 +Train: [32] [4700/6250] eta: 0:03:33 lr: 0.000100 grad: 0.0684 (0.0743) loss: 0.8777 (0.8721) time: 0.1224 data: 0.0448 max mem: 8299 +Train: [32] [4800/6250] eta: 0:03:19 lr: 0.000100 grad: 0.0673 (0.0742) loss: 0.8681 (0.8721) time: 0.1282 data: 0.0495 max mem: 8299 +Train: [32] [4900/6250] eta: 0:03:05 lr: 0.000100 grad: 0.0707 (0.0742) loss: 0.8697 (0.8721) time: 0.1251 data: 0.0421 max mem: 8299 +Train: [32] [5000/6250] eta: 0:02:51 lr: 0.000100 grad: 0.0700 (0.0743) loss: 0.8704 (0.8721) time: 0.1328 data: 0.0511 max mem: 8299 +Train: [32] [5100/6250] eta: 0:02:37 lr: 0.000100 grad: 0.0755 (0.0744) loss: 0.8682 (0.8721) time: 0.1282 data: 0.0419 max mem: 8299 +Train: [32] [5200/6250] eta: 0:02:23 lr: 0.000100 grad: 0.0731 (0.0744) loss: 0.8715 (0.8721) time: 0.1267 data: 0.0499 max mem: 8299 +Train: [32] [5300/6250] eta: 0:02:09 lr: 0.000100 grad: 0.0741 (0.0744) loss: 0.8703 (0.8721) time: 0.0924 data: 0.0094 max mem: 8299 +Train: [32] [5400/6250] eta: 0:01:55 lr: 0.000100 grad: 0.0709 (0.0744) loss: 0.8711 (0.8721) time: 0.1425 data: 0.0757 max mem: 8299 +Train: [32] [5500/6250] eta: 0:01:42 lr: 0.000100 grad: 0.0714 (0.0745) loss: 0.8705 (0.8720) time: 0.1473 data: 0.0757 max mem: 8299 +Train: [32] [5600/6250] eta: 0:01:28 lr: 0.000100 grad: 0.0762 (0.0745) loss: 0.8694 (0.8720) time: 0.1429 data: 0.0621 max mem: 8299 +Train: [32] [5700/6250] eta: 0:01:15 lr: 0.000100 grad: 0.0721 (0.0746) loss: 0.8716 (0.8720) time: 0.1451 data: 0.0727 max mem: 8299 +Train: [32] [5800/6250] eta: 0:01:01 lr: 0.000100 grad: 0.0691 (0.0746) loss: 0.8765 (0.8721) time: 0.1340 data: 0.0595 max mem: 8299 +Train: [32] [5900/6250] eta: 0:00:47 lr: 0.000100 grad: 0.0710 (0.0746) loss: 0.8753 (0.8721) time: 0.1356 data: 0.0548 max mem: 8299 +Train: [32] [6000/6250] eta: 0:00:34 lr: 0.000100 grad: 0.0718 (0.0746) loss: 0.8740 (0.8721) time: 0.1312 data: 0.0534 max mem: 8299 +Train: [32] [6100/6250] eta: 0:00:20 lr: 0.000100 grad: 0.0743 (0.0746) loss: 0.8711 (0.8721) time: 0.1295 data: 0.0465 max mem: 8299 +Train: [32] [6200/6250] eta: 0:00:06 lr: 0.000100 grad: 0.0768 (0.0746) loss: 0.8753 (0.8721) time: 0.1258 data: 0.0530 max mem: 8299 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0856 (0.0747) loss: 0.8705 (0.8720) time: 0.0869 data: 0.0128 max mem: 8299 +Train: [32] Total time: 0:14:17 (0.1372 s / it) +Averaged stats: lr: 0.000100 grad: 0.0856 (0.0747) loss: 0.8705 (0.8720) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:03:56 loss: 0.9043 (0.9043) time: 3.8216 data: 3.7102 max mem: 8299 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8888 (0.8894) time: 0.1379 data: 0.1134 max mem: 8299 +Eval (hcp-train-subset): [32] Total time: 0:00:13 (0.2147 s / it) +Averaged stats (hcp-train-subset): loss: 0.8888 (0.8894) +Eval (hcp-val): [32] [ 0/62] eta: 0:04:00 loss: 0.8860 (0.8860) time: 3.8789 data: 3.8025 max mem: 8299 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8860 (0.8877) time: 0.1133 data: 0.0890 max mem: 8299 +Eval (hcp-val): [32] Total time: 0:00:12 (0.1961 s / it) +Averaged stats (hcp-val): loss: 0.8860 (0.8877) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 9:32:14 lr: 0.000100 grad: 0.1477 (0.1477) loss: 0.8672 (0.8672) time: 5.4935 data: 5.3963 max mem: 8299 +Train: [33] [ 100/6250] eta: 0:18:24 lr: 0.000100 grad: 0.0757 (0.0800) loss: 0.8793 (0.8828) time: 0.1321 data: 0.0379 max mem: 8299 +Train: [33] [ 200/6250] eta: 0:16:04 lr: 0.000100 grad: 0.0686 (0.0759) loss: 0.8688 (0.8795) time: 0.1241 data: 0.0327 max mem: 8299 +Train: [33] [ 300/6250] eta: 0:14:56 lr: 0.000100 grad: 0.0682 (0.0750) loss: 0.8654 (0.8765) time: 0.1208 data: 0.0280 max mem: 8299 +Train: [33] [ 400/6250] eta: 0:14:05 lr: 0.000100 grad: 0.0641 (0.0736) loss: 0.8733 (0.8743) time: 0.1225 data: 0.0381 max mem: 8299 +Train: [33] [ 500/6250] eta: 0:13:31 lr: 0.000100 grad: 0.0592 (0.0719) loss: 0.8707 (0.8740) time: 0.1237 data: 0.0378 max mem: 8299 +Train: [33] [ 600/6250] eta: 0:13:13 lr: 0.000100 grad: 0.0693 (0.0711) loss: 0.8716 (0.8743) time: 0.1563 data: 0.0752 max mem: 8299 +Train: [33] [ 700/6250] eta: 0:12:43 lr: 0.000100 grad: 0.0619 (0.0707) loss: 0.8766 (0.8741) time: 0.1259 data: 0.0572 max mem: 8299 +Train: [33] [ 800/6250] eta: 0:12:27 lr: 0.000100 grad: 0.0671 (0.0705) loss: 0.8750 (0.8739) time: 0.1460 data: 0.0620 max mem: 8299 +Train: [33] [ 900/6250] eta: 0:12:14 lr: 0.000100 grad: 0.0674 (0.0703) loss: 0.8652 (0.8735) time: 0.0959 data: 0.0085 max mem: 8299 +Train: [33] [1000/6250] eta: 0:12:02 lr: 0.000100 grad: 0.0669 (0.0700) loss: 0.8626 (0.8734) time: 0.1402 data: 0.0578 max mem: 8299 +Train: [33] [1100/6250] eta: 0:11:42 lr: 0.000100 grad: 0.0684 (0.0703) loss: 0.8753 (0.8731) time: 0.1223 data: 0.0385 max mem: 8299 +Train: [33] [1200/6250] eta: 0:11:27 lr: 0.000100 grad: 0.0660 (0.0704) loss: 0.8730 (0.8730) time: 0.1048 data: 0.0216 max mem: 8299 +Train: [33] [1300/6250] eta: 0:11:18 lr: 0.000100 grad: 0.0663 (0.0704) loss: 0.8688 (0.8729) time: 0.1517 data: 0.0649 max mem: 8299 +Train: [33] [1400/6250] eta: 0:11:09 lr: 0.000100 grad: 0.0700 (0.0706) loss: 0.8709 (0.8726) time: 0.1490 data: 0.0695 max mem: 8299 +Train: [33] [1500/6250] eta: 0:10:55 lr: 0.000100 grad: 0.0660 (0.0704) loss: 0.8702 (0.8725) time: 0.1346 data: 0.0542 max mem: 8299 +Train: [33] [1600/6250] eta: 0:10:42 lr: 0.000100 grad: 0.0671 (0.0706) loss: 0.8714 (0.8722) time: 0.1316 data: 0.0474 max mem: 8299 +Train: [33] [1700/6250] eta: 0:10:29 lr: 0.000100 grad: 0.0667 (0.0706) loss: 0.8718 (0.8722) time: 0.1329 data: 0.0556 max mem: 8299 +Train: [33] [1800/6250] eta: 0:10:13 lr: 0.000100 grad: 0.0689 (0.0708) loss: 0.8743 (0.8722) time: 0.1270 data: 0.0537 max mem: 8299 +Train: [33] [1900/6250] eta: 0:09:57 lr: 0.000100 grad: 0.0750 (0.0709) loss: 0.8687 (0.8721) time: 0.1156 data: 0.0366 max mem: 8299 +Train: [33] [2000/6250] eta: 0:09:42 lr: 0.000100 grad: 0.0727 (0.0708) loss: 0.8764 (0.8720) time: 0.1228 data: 0.0521 max mem: 8299 +Train: [33] [2100/6250] eta: 0:09:26 lr: 0.000100 grad: 0.0656 (0.0708) loss: 0.8718 (0.8720) time: 0.1127 data: 0.0370 max mem: 8299 +Train: [33] [2200/6250] eta: 0:09:10 lr: 0.000099 grad: 0.0676 (0.0709) loss: 0.8644 (0.8719) time: 0.1277 data: 0.0565 max mem: 8299 +Train: [33] [2300/6250] eta: 0:08:55 lr: 0.000099 grad: 0.0600 (0.0709) loss: 0.8786 (0.8719) time: 0.1202 data: 0.0384 max mem: 8299 +Train: [33] [2400/6250] eta: 0:08:41 lr: 0.000099 grad: 0.0664 (0.0710) loss: 0.8745 (0.8719) time: 0.1490 data: 0.0753 max mem: 8299 +Train: [33] [2500/6250] eta: 0:08:27 lr: 0.000099 grad: 0.0665 (0.0710) loss: 0.8757 (0.8719) time: 0.1350 data: 0.0533 max mem: 8299 +Train: [33] [2600/6250] eta: 0:08:12 lr: 0.000099 grad: 0.0725 (0.0711) loss: 0.8679 (0.8719) time: 0.1244 data: 0.0440 max mem: 8299 +Train: [33] [2700/6250] eta: 0:07:58 lr: 0.000099 grad: 0.0694 (0.0712) loss: 0.8697 (0.8718) time: 0.1217 data: 0.0430 max mem: 8299 +Train: [33] [2800/6250] eta: 0:07:44 lr: 0.000099 grad: 0.0794 (0.0713) loss: 0.8711 (0.8718) time: 0.1545 data: 0.0882 max mem: 8299 +Train: [33] [2900/6250] eta: 0:07:30 lr: 0.000099 grad: 0.0696 (0.0714) loss: 0.8696 (0.8717) time: 0.1345 data: 0.0607 max mem: 8299 +Train: [33] [3000/6250] eta: 0:07:16 lr: 0.000099 grad: 0.0687 (0.0715) loss: 0.8736 (0.8717) time: 0.1362 data: 0.0582 max mem: 8299 +Train: [33] [3100/6250] eta: 0:07:03 lr: 0.000099 grad: 0.0769 (0.0717) loss: 0.8694 (0.8716) time: 0.1359 data: 0.0566 max mem: 8299 +Train: [33] [3200/6250] eta: 0:06:50 lr: 0.000099 grad: 0.0695 (0.0717) loss: 0.8662 (0.8716) time: 0.0928 data: 0.0180 max mem: 8299 +Train: [33] [3300/6250] eta: 0:06:36 lr: 0.000099 grad: 0.0750 (0.0719) loss: 0.8707 (0.8715) time: 0.1041 data: 0.0347 max mem: 8299 +Train: [33] [3400/6250] eta: 0:06:23 lr: 0.000099 grad: 0.0759 (0.0721) loss: 0.8630 (0.8714) time: 0.1549 data: 0.0884 max mem: 8299 +Train: [33] [3500/6250] eta: 0:06:09 lr: 0.000099 grad: 0.0715 (0.0723) loss: 0.8686 (0.8713) time: 0.1429 data: 0.0661 max mem: 8299 +Train: [33] [3600/6250] eta: 0:05:55 lr: 0.000099 grad: 0.0794 (0.0725) loss: 0.8628 (0.8712) time: 0.0956 data: 0.0147 max mem: 8299 +Train: [33] [3700/6250] eta: 0:05:42 lr: 0.000099 grad: 0.0753 (0.0727) loss: 0.8666 (0.8711) time: 0.1210 data: 0.0330 max mem: 8299 +Train: [33] [3800/6250] eta: 0:05:29 lr: 0.000099 grad: 0.0779 (0.0728) loss: 0.8624 (0.8711) time: 0.1671 data: 0.0945 max mem: 8299 +Train: [33] [3900/6250] eta: 0:05:15 lr: 0.000099 grad: 0.0689 (0.0728) loss: 0.8720 (0.8712) time: 0.1230 data: 0.0423 max mem: 8299 +Train: [33] [4000/6250] eta: 0:05:02 lr: 0.000099 grad: 0.0731 (0.0728) loss: 0.8660 (0.8711) time: 0.1607 data: 0.0874 max mem: 8299 +Train: [33] [4100/6250] eta: 0:04:48 lr: 0.000099 grad: 0.0688 (0.0729) loss: 0.8648 (0.8711) time: 0.1233 data: 0.0468 max mem: 8299 +Train: [33] [4200/6250] eta: 0:04:34 lr: 0.000099 grad: 0.0778 (0.0729) loss: 0.8614 (0.8711) time: 0.1387 data: 0.0618 max mem: 8299 +Train: [33] [4300/6250] eta: 0:04:21 lr: 0.000099 grad: 0.0724 (0.0730) loss: 0.8738 (0.8711) time: 0.1305 data: 0.0513 max mem: 8299 +Train: [33] [4400/6250] eta: 0:04:08 lr: 0.000099 grad: 0.0703 (0.0731) loss: 0.8685 (0.8710) time: 0.1478 data: 0.0757 max mem: 8299 +Train: [33] [4500/6250] eta: 0:03:54 lr: 0.000099 grad: 0.0718 (0.0732) loss: 0.8669 (0.8710) time: 0.1234 data: 0.0353 max mem: 8299 +Train: [33] [4600/6250] eta: 0:03:41 lr: 0.000099 grad: 0.0748 (0.0732) loss: 0.8654 (0.8710) time: 0.1400 data: 0.0654 max mem: 8299 +Train: [33] [4700/6250] eta: 0:03:27 lr: 0.000099 grad: 0.0703 (0.0731) loss: 0.8653 (0.8711) time: 0.1345 data: 0.0536 max mem: 8299 +Train: [33] [4800/6250] eta: 0:03:14 lr: 0.000099 grad: 0.0763 (0.0732) loss: 0.8699 (0.8710) time: 0.1511 data: 0.0732 max mem: 8299 +Train: [33] [4900/6250] eta: 0:03:01 lr: 0.000099 grad: 0.0692 (0.0733) loss: 0.8698 (0.8710) time: 0.1435 data: 0.0730 max mem: 8299 +Train: [33] [5000/6250] eta: 0:02:47 lr: 0.000099 grad: 0.0672 (0.0732) loss: 0.8724 (0.8710) time: 0.1588 data: 0.0772 max mem: 8299 +Train: [33] [5100/6250] eta: 0:02:34 lr: 0.000099 grad: 0.0709 (0.0732) loss: 0.8751 (0.8710) time: 0.1204 data: 0.0389 max mem: 8299 +Train: [33] [5200/6250] eta: 0:02:20 lr: 0.000099 grad: 0.0713 (0.0732) loss: 0.8696 (0.8710) time: 0.1069 data: 0.0189 max mem: 8299 +Train: [33] [5300/6250] eta: 0:02:07 lr: 0.000099 grad: 0.0679 (0.0732) loss: 0.8717 (0.8711) time: 0.1867 data: 0.1167 max mem: 8299 +Train: [33] [5400/6250] eta: 0:01:54 lr: 0.000099 grad: 0.0735 (0.0733) loss: 0.8686 (0.8711) time: 0.1103 data: 0.0352 max mem: 8299 +Train: [33] [5500/6250] eta: 0:01:40 lr: 0.000099 grad: 0.0738 (0.0733) loss: 0.8726 (0.8711) time: 0.1456 data: 0.0610 max mem: 8299 +Train: [33] [5600/6250] eta: 0:01:27 lr: 0.000099 grad: 0.0657 (0.0733) loss: 0.8692 (0.8711) time: 0.1128 data: 0.0270 max mem: 8299 +Train: [33] [5700/6250] eta: 0:01:14 lr: 0.000099 grad: 0.0736 (0.0734) loss: 0.8675 (0.8711) time: 0.1374 data: 0.0458 max mem: 8299 +Train: [33] [5800/6250] eta: 0:01:00 lr: 0.000099 grad: 0.0677 (0.0734) loss: 0.8711 (0.8711) time: 0.1541 data: 0.0685 max mem: 8299 +Train: [33] [5900/6250] eta: 0:00:47 lr: 0.000098 grad: 0.0747 (0.0734) loss: 0.8694 (0.8711) time: 0.1324 data: 0.0450 max mem: 8299 +Train: [33] [6000/6250] eta: 0:00:33 lr: 0.000098 grad: 0.0727 (0.0734) loss: 0.8751 (0.8711) time: 0.1248 data: 0.0484 max mem: 8299 +Train: [33] [6100/6250] eta: 0:00:20 lr: 0.000098 grad: 0.0742 (0.0734) loss: 0.8771 (0.8712) time: 0.1172 data: 0.0441 max mem: 8299 +Train: [33] [6200/6250] eta: 0:00:06 lr: 0.000098 grad: 0.0661 (0.0734) loss: 0.8731 (0.8712) time: 0.1274 data: 0.0404 max mem: 8299 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0709 (0.0734) loss: 0.8692 (0.8712) time: 0.0990 data: 0.0222 max mem: 8299 +Train: [33] Total time: 0:14:03 (0.1350 s / it) +Averaged stats: lr: 0.000098 grad: 0.0709 (0.0734) loss: 0.8692 (0.8712) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:05:02 loss: 0.9018 (0.9018) time: 4.8742 data: 4.8444 max mem: 8299 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8919 (0.8915) time: 0.1171 data: 0.0927 max mem: 8299 +Eval (hcp-train-subset): [33] Total time: 0:00:12 (0.2061 s / it) +Averaged stats (hcp-train-subset): loss: 0.8919 (0.8915) +Eval (hcp-val): [33] [ 0/62] eta: 0:03:30 loss: 0.8841 (0.8841) time: 3.3882 data: 3.2848 max mem: 8299 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8857 (0.8877) time: 0.1021 data: 0.0766 max mem: 8299 +Eval (hcp-val): [33] Total time: 0:00:12 (0.1966 s / it) +Averaged stats (hcp-val): loss: 0.8857 (0.8877) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 7:12:30 lr: 0.000098 grad: 0.0882 (0.0882) loss: 0.9263 (0.9263) time: 4.1521 data: 3.8552 max mem: 8299 +Train: [34] [ 100/6250] eta: 0:18:22 lr: 0.000098 grad: 0.0665 (0.0768) loss: 0.8853 (0.8879) time: 0.1210 data: 0.0220 max mem: 8299 +Train: [34] [ 200/6250] eta: 0:15:34 lr: 0.000098 grad: 0.0668 (0.0768) loss: 0.8855 (0.8840) time: 0.1278 data: 0.0445 max mem: 8299 +Train: [34] [ 300/6250] eta: 0:14:26 lr: 0.000098 grad: 0.0704 (0.0764) loss: 0.8733 (0.8818) time: 0.1322 data: 0.0488 max mem: 8299 +Train: [34] [ 400/6250] eta: 0:13:52 lr: 0.000098 grad: 0.0684 (0.0747) loss: 0.8813 (0.8812) time: 0.1269 data: 0.0427 max mem: 8299 +Train: [34] [ 500/6250] eta: 0:13:18 lr: 0.000098 grad: 0.0613 (0.0732) loss: 0.8773 (0.8809) time: 0.1051 data: 0.0270 max mem: 8299 +Train: [34] [ 600/6250] eta: 0:12:59 lr: 0.000098 grad: 0.0600 (0.0722) loss: 0.8753 (0.8806) time: 0.1245 data: 0.0337 max mem: 8299 +Train: [34] [ 700/6250] eta: 0:12:50 lr: 0.000098 grad: 0.0670 (0.0717) loss: 0.8759 (0.8801) time: 0.1258 data: 0.0500 max mem: 8299 +Train: [34] [ 800/6250] eta: 0:12:39 lr: 0.000098 grad: 0.0683 (0.0716) loss: 0.8686 (0.8789) time: 0.1581 data: 0.0831 max mem: 8299 +Train: [34] [ 900/6250] eta: 0:12:29 lr: 0.000098 grad: 0.0661 (0.0714) loss: 0.8700 (0.8778) time: 0.1633 data: 0.0774 max mem: 8299 +Train: [34] [1000/6250] eta: 0:12:16 lr: 0.000098 grad: 0.0695 (0.0713) loss: 0.8700 (0.8768) time: 0.1579 data: 0.0781 max mem: 8299 +Train: [34] [1100/6250] eta: 0:11:58 lr: 0.000098 grad: 0.0703 (0.0714) loss: 0.8615 (0.8760) time: 0.1176 data: 0.0358 max mem: 8299 +Train: [34] [1200/6250] eta: 0:11:42 lr: 0.000098 grad: 0.0719 (0.0720) loss: 0.8603 (0.8751) time: 0.1137 data: 0.0372 max mem: 8299 +Train: [34] [1300/6250] eta: 0:11:32 lr: 0.000098 grad: 0.0712 (0.0725) loss: 0.8637 (0.8742) time: 0.1588 data: 0.0862 max mem: 8299 +Train: [34] [1400/6250] eta: 0:11:14 lr: 0.000098 grad: 0.0704 (0.0726) loss: 0.8587 (0.8735) time: 0.1404 data: 0.0519 max mem: 8299 +Train: [34] [1500/6250] eta: 0:10:59 lr: 0.000098 grad: 0.0723 (0.0728) loss: 0.8691 (0.8729) time: 0.1412 data: 0.0570 max mem: 8299 +Train: [34] [1600/6250] eta: 0:10:44 lr: 0.000098 grad: 0.0696 (0.0731) loss: 0.8684 (0.8724) time: 0.1437 data: 0.0707 max mem: 8299 +Train: [34] [1700/6250] eta: 0:10:28 lr: 0.000098 grad: 0.0765 (0.0733) loss: 0.8606 (0.8720) time: 0.1427 data: 0.0737 max mem: 8299 +Train: [34] [1800/6250] eta: 0:10:13 lr: 0.000098 grad: 0.0719 (0.0736) loss: 0.8713 (0.8717) time: 0.1266 data: 0.0442 max mem: 8299 +Train: [34] [1900/6250] eta: 0:10:00 lr: 0.000098 grad: 0.0711 (0.0739) loss: 0.8696 (0.8715) time: 0.1931 data: 0.1217 max mem: 8299 +Train: [34] [2000/6250] eta: 0:09:45 lr: 0.000098 grad: 0.0732 (0.0740) loss: 0.8705 (0.8713) time: 0.1225 data: 0.0485 max mem: 8299 +Train: [34] [2100/6250] eta: 0:09:31 lr: 0.000098 grad: 0.0706 (0.0741) loss: 0.8601 (0.8711) time: 0.1307 data: 0.0472 max mem: 8299 +Train: [34] [2200/6250] eta: 0:09:18 lr: 0.000098 grad: 0.0780 (0.0743) loss: 0.8592 (0.8708) time: 0.1514 data: 0.0756 max mem: 8299 +Train: [34] [2300/6250] eta: 0:09:03 lr: 0.000098 grad: 0.0714 (0.0743) loss: 0.8619 (0.8705) time: 0.1602 data: 0.0882 max mem: 8299 +Train: [34] [2400/6250] eta: 0:08:49 lr: 0.000098 grad: 0.0770 (0.0746) loss: 0.8671 (0.8702) time: 0.1503 data: 0.0739 max mem: 8299 +Train: [34] [2500/6250] eta: 0:08:35 lr: 0.000098 grad: 0.0799 (0.0749) loss: 0.8648 (0.8700) time: 0.1361 data: 0.0620 max mem: 8299 +Train: [34] [2600/6250] eta: 0:08:22 lr: 0.000098 grad: 0.0777 (0.0750) loss: 0.8655 (0.8698) time: 0.1459 data: 0.0747 max mem: 8299 +Train: [34] [2700/6250] eta: 0:08:07 lr: 0.000098 grad: 0.0822 (0.0753) loss: 0.8664 (0.8696) time: 0.1008 data: 0.0154 max mem: 8299 +Train: [34] [2800/6250] eta: 0:07:54 lr: 0.000098 grad: 0.0800 (0.0755) loss: 0.8575 (0.8695) time: 0.0926 data: 0.0113 max mem: 8299 +Train: [34] [2900/6250] eta: 0:07:41 lr: 0.000098 grad: 0.0771 (0.0757) loss: 0.8632 (0.8693) time: 0.1610 data: 0.0969 max mem: 8299 +Train: [34] [3000/6250] eta: 0:07:27 lr: 0.000098 grad: 0.0750 (0.0757) loss: 0.8654 (0.8692) time: 0.1306 data: 0.0536 max mem: 8299 +Train: [34] [3100/6250] eta: 0:07:13 lr: 0.000098 grad: 0.0756 (0.0758) loss: 0.8659 (0.8691) time: 0.1479 data: 0.0673 max mem: 8299 +Train: [34] [3200/6250] eta: 0:06:59 lr: 0.000098 grad: 0.0722 (0.0759) loss: 0.8639 (0.8689) time: 0.1751 data: 0.0971 max mem: 8299 +Train: [34] [3300/6250] eta: 0:06:44 lr: 0.000097 grad: 0.0718 (0.0760) loss: 0.8626 (0.8688) time: 0.1414 data: 0.0456 max mem: 8299 +Train: [34] [3400/6250] eta: 0:06:31 lr: 0.000097 grad: 0.0720 (0.0761) loss: 0.8698 (0.8687) time: 0.1392 data: 0.0665 max mem: 8299 +Train: [34] [3500/6250] eta: 0:06:17 lr: 0.000097 grad: 0.0760 (0.0762) loss: 0.8689 (0.8686) time: 0.1259 data: 0.0567 max mem: 8299 +Train: [34] [3600/6250] eta: 0:06:03 lr: 0.000097 grad: 0.0719 (0.0762) loss: 0.8624 (0.8686) time: 0.1304 data: 0.0490 max mem: 8299 +Train: [34] [3700/6250] eta: 0:05:50 lr: 0.000097 grad: 0.0728 (0.0762) loss: 0.8721 (0.8686) time: 0.1416 data: 0.0652 max mem: 8299 +Train: [34] [3800/6250] eta: 0:05:36 lr: 0.000097 grad: 0.0721 (0.0762) loss: 0.8738 (0.8686) time: 0.1440 data: 0.0699 max mem: 8299 +Train: [34] [3900/6250] eta: 0:05:22 lr: 0.000097 grad: 0.0743 (0.0763) loss: 0.8628 (0.8685) time: 0.1201 data: 0.0452 max mem: 8299 +Train: [34] [4000/6250] eta: 0:05:08 lr: 0.000097 grad: 0.0793 (0.0764) loss: 0.8643 (0.8684) time: 0.1166 data: 0.0382 max mem: 8299 +Train: [34] [4100/6250] eta: 0:04:55 lr: 0.000097 grad: 0.0732 (0.0764) loss: 0.8664 (0.8684) time: 0.1512 data: 0.0840 max mem: 8299 +Train: [34] [4200/6250] eta: 0:04:42 lr: 0.000097 grad: 0.0727 (0.0765) loss: 0.8717 (0.8683) time: 0.1797 data: 0.1118 max mem: 8299 +Train: [34] [4300/6250] eta: 0:04:29 lr: 0.000097 grad: 0.0792 (0.0767) loss: 0.8690 (0.8683) time: 0.1556 data: 0.0793 max mem: 8299 +Train: [34] [4400/6250] eta: 0:04:15 lr: 0.000097 grad: 0.0815 (0.0767) loss: 0.8642 (0.8682) time: 0.1514 data: 0.0811 max mem: 8299 +Train: [34] [4500/6250] eta: 0:04:01 lr: 0.000097 grad: 0.0701 (0.0767) loss: 0.8635 (0.8681) time: 0.1815 data: 0.1028 max mem: 8299 +Train: [34] [4600/6250] eta: 0:03:47 lr: 0.000097 grad: 0.0746 (0.0768) loss: 0.8729 (0.8680) time: 0.1342 data: 0.0603 max mem: 8299 +Train: [34] [4700/6250] eta: 0:03:33 lr: 0.000097 grad: 0.0701 (0.0768) loss: 0.8615 (0.8680) time: 0.1118 data: 0.0366 max mem: 8299 +Train: [34] [4800/6250] eta: 0:03:19 lr: 0.000097 grad: 0.0775 (0.0768) loss: 0.8566 (0.8679) time: 0.1180 data: 0.0323 max mem: 8299 +Train: [34] [4900/6250] eta: 0:03:05 lr: 0.000097 grad: 0.0714 (0.0769) loss: 0.8638 (0.8678) time: 0.1390 data: 0.0573 max mem: 8299 +Train: [34] [5000/6250] eta: 0:02:51 lr: 0.000097 grad: 0.0800 (0.0770) loss: 0.8670 (0.8678) time: 0.1463 data: 0.0689 max mem: 8299 +Train: [34] [5100/6250] eta: 0:02:37 lr: 0.000097 grad: 0.0762 (0.0770) loss: 0.8650 (0.8677) time: 0.1278 data: 0.0545 max mem: 8299 +Train: [34] [5200/6250] eta: 0:02:23 lr: 0.000097 grad: 0.0700 (0.0770) loss: 0.8691 (0.8677) time: 0.1255 data: 0.0571 max mem: 8299 +Train: [34] [5300/6250] eta: 0:02:10 lr: 0.000097 grad: 0.0784 (0.0771) loss: 0.8656 (0.8676) time: 0.1541 data: 0.0809 max mem: 8299 +Train: [34] [5400/6250] eta: 0:01:56 lr: 0.000097 grad: 0.0756 (0.0771) loss: 0.8652 (0.8676) time: 0.1436 data: 0.0721 max mem: 8299 +Train: [34] [5500/6250] eta: 0:01:42 lr: 0.000097 grad: 0.0768 (0.0771) loss: 0.8645 (0.8675) time: 0.1357 data: 0.0643 max mem: 8299 +Train: [34] [5600/6250] eta: 0:01:29 lr: 0.000097 grad: 0.0691 (0.0771) loss: 0.8692 (0.8674) time: 0.1450 data: 0.0642 max mem: 8299 +Train: [34] [5700/6250] eta: 0:01:15 lr: 0.000097 grad: 0.0744 (0.0771) loss: 0.8628 (0.8674) time: 0.1522 data: 0.0631 max mem: 8299 +Train: [34] [5800/6250] eta: 0:01:01 lr: 0.000097 grad: 0.0738 (0.0771) loss: 0.8581 (0.8673) time: 0.1290 data: 0.0453 max mem: 8299 +Train: [34] [5900/6250] eta: 0:00:48 lr: 0.000097 grad: 0.0763 (0.0771) loss: 0.8623 (0.8673) time: 0.1492 data: 0.0661 max mem: 8299 +Train: [34] [6000/6250] eta: 0:00:34 lr: 0.000097 grad: 0.0717 (0.0771) loss: 0.8605 (0.8673) time: 0.1102 data: 0.0314 max mem: 8299 +Train: [34] [6100/6250] eta: 0:00:20 lr: 0.000097 grad: 0.0777 (0.0771) loss: 0.8635 (0.8672) time: 0.1465 data: 0.0658 max mem: 8299 +Train: [34] [6200/6250] eta: 0:00:06 lr: 0.000097 grad: 0.0810 (0.0772) loss: 0.8545 (0.8672) time: 0.1316 data: 0.0510 max mem: 8299 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0749 (0.0772) loss: 0.8675 (0.8672) time: 0.1199 data: 0.0441 max mem: 8299 +Train: [34] Total time: 0:14:19 (0.1375 s / it) +Averaged stats: lr: 0.000097 grad: 0.0749 (0.0772) loss: 0.8675 (0.8672) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:03:57 loss: 0.9061 (0.9061) time: 3.8234 data: 3.7426 max mem: 8299 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8920 (0.8920) time: 0.1290 data: 0.1045 max mem: 8299 +Eval (hcp-train-subset): [34] Total time: 0:00:13 (0.2163 s / it) +Averaged stats (hcp-train-subset): loss: 0.8920 (0.8920) +Making plots (hcp-train-subset): example=16 +Eval (hcp-val): [34] [ 0/62] eta: 0:04:27 loss: 0.8824 (0.8824) time: 4.3201 data: 4.2901 max mem: 8299 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8834 (0.8872) time: 0.1210 data: 0.0954 max mem: 8299 +Eval (hcp-val): [34] Total time: 0:00:11 (0.1921 s / it) +Averaged stats (hcp-val): loss: 0.8834 (0.8872) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 6:38:03 lr: 0.000097 grad: 0.0379 (0.0379) loss: 0.9275 (0.9275) time: 3.8214 data: 3.5292 max mem: 8299 +Train: [35] [ 100/6250] eta: 0:19:01 lr: 0.000097 grad: 0.0850 (0.0877) loss: 0.8755 (0.8785) time: 0.1266 data: 0.0385 max mem: 8299 +Train: [35] [ 200/6250] eta: 0:16:14 lr: 0.000097 grad: 0.0815 (0.0823) loss: 0.8719 (0.8750) time: 0.1530 data: 0.0702 max mem: 8299 +Train: [35] [ 300/6250] eta: 0:14:50 lr: 0.000097 grad: 0.0698 (0.0788) loss: 0.8802 (0.8738) time: 0.1267 data: 0.0313 max mem: 8299 +Train: [35] [ 400/6250] eta: 0:13:59 lr: 0.000097 grad: 0.0669 (0.0767) loss: 0.8769 (0.8738) time: 0.1265 data: 0.0415 max mem: 8299 +Train: [35] [ 500/6250] eta: 0:13:21 lr: 0.000097 grad: 0.0680 (0.0757) loss: 0.8697 (0.8737) time: 0.1216 data: 0.0347 max mem: 8299 +Train: [35] [ 600/6250] eta: 0:12:52 lr: 0.000097 grad: 0.0704 (0.0751) loss: 0.8682 (0.8737) time: 0.1299 data: 0.0318 max mem: 8299 +Train: [35] [ 700/6250] eta: 0:12:30 lr: 0.000096 grad: 0.0646 (0.0746) loss: 0.8768 (0.8738) time: 0.1380 data: 0.0641 max mem: 8299 +Train: [35] [ 800/6250] eta: 0:12:05 lr: 0.000096 grad: 0.0624 (0.0738) loss: 0.8841 (0.8740) time: 0.1249 data: 0.0489 max mem: 8299 +Train: [35] [ 900/6250] eta: 0:11:47 lr: 0.000096 grad: 0.0653 (0.0732) loss: 0.8760 (0.8742) time: 0.1288 data: 0.0450 max mem: 8299 +Train: [35] [1000/6250] eta: 0:11:33 lr: 0.000096 grad: 0.0658 (0.0729) loss: 0.8751 (0.8744) time: 0.1060 data: 0.0255 max mem: 8299 +Train: [35] [1100/6250] eta: 0:11:16 lr: 0.000096 grad: 0.0672 (0.0728) loss: 0.8789 (0.8744) time: 0.1430 data: 0.0703 max mem: 8299 +Train: [35] [1200/6250] eta: 0:11:00 lr: 0.000096 grad: 0.0664 (0.0724) loss: 0.8794 (0.8746) time: 0.1261 data: 0.0549 max mem: 8299 +Train: [35] [1300/6250] eta: 0:10:47 lr: 0.000096 grad: 0.0731 (0.0724) loss: 0.8773 (0.8746) time: 0.1272 data: 0.0505 max mem: 8299 +Train: [35] [1400/6250] eta: 0:10:34 lr: 0.000096 grad: 0.0718 (0.0726) loss: 0.8684 (0.8746) time: 0.1420 data: 0.0690 max mem: 8299 +Train: [35] [1500/6250] eta: 0:10:19 lr: 0.000096 grad: 0.0671 (0.0725) loss: 0.8763 (0.8747) time: 0.1204 data: 0.0436 max mem: 8299 +Train: [35] [1600/6250] eta: 0:10:05 lr: 0.000096 grad: 0.0700 (0.0726) loss: 0.8717 (0.8746) time: 0.1198 data: 0.0505 max mem: 8299 +Train: [35] [1700/6250] eta: 0:09:53 lr: 0.000096 grad: 0.0670 (0.0732) loss: 0.8779 (0.8746) time: 0.1387 data: 0.0616 max mem: 8299 +Train: [35] [1800/6250] eta: 0:09:40 lr: 0.000096 grad: 0.0637 (0.0732) loss: 0.8720 (0.8746) time: 0.1531 data: 0.0795 max mem: 8299 +Train: [35] [1900/6250] eta: 0:09:26 lr: 0.000096 grad: 0.0664 (0.0732) loss: 0.8723 (0.8746) time: 0.1272 data: 0.0509 max mem: 8299 +Train: [35] [2000/6250] eta: 0:09:13 lr: 0.000096 grad: 0.0724 (0.0733) loss: 0.8727 (0.8746) time: 0.1172 data: 0.0366 max mem: 8299 +Train: [35] [2100/6250] eta: 0:09:01 lr: 0.000096 grad: 0.0723 (0.0735) loss: 0.8674 (0.8744) time: 0.1036 data: 0.0199 max mem: 8299 +Train: [35] [2200/6250] eta: 0:08:49 lr: 0.000096 grad: 0.0720 (0.0735) loss: 0.8621 (0.8742) time: 0.1252 data: 0.0554 max mem: 8299 +Train: [35] [2300/6250] eta: 0:08:36 lr: 0.000096 grad: 0.0678 (0.0735) loss: 0.8780 (0.8741) time: 0.1233 data: 0.0547 max mem: 8299 +Train: [35] [2400/6250] eta: 0:08:25 lr: 0.000096 grad: 0.0785 (0.0737) loss: 0.8707 (0.8740) time: 0.1453 data: 0.0692 max mem: 8299 +Train: [35] [2500/6250] eta: 0:08:12 lr: 0.000096 grad: 0.0718 (0.0738) loss: 0.8704 (0.8738) time: 0.1511 data: 0.0797 max mem: 8299 +Train: [35] [2600/6250] eta: 0:07:59 lr: 0.000096 grad: 0.0729 (0.0743) loss: 0.8712 (0.8737) time: 0.1230 data: 0.0457 max mem: 8299 +Train: [35] [2700/6250] eta: 0:07:46 lr: 0.000096 grad: 0.0744 (0.0745) loss: 0.8684 (0.8735) time: 0.1317 data: 0.0569 max mem: 8299 +Train: [35] [2800/6250] eta: 0:07:33 lr: 0.000096 grad: 0.0718 (0.0745) loss: 0.8750 (0.8734) time: 0.1361 data: 0.0628 max mem: 8299 +Train: [35] [2900/6250] eta: 0:07:20 lr: 0.000096 grad: 0.0786 (0.0746) loss: 0.8723 (0.8734) time: 0.1309 data: 0.0626 max mem: 8299 +Train: [35] [3000/6250] eta: 0:07:07 lr: 0.000096 grad: 0.0728 (0.0748) loss: 0.8788 (0.8732) time: 0.1071 data: 0.0241 max mem: 8299 +Train: [35] [3100/6250] eta: 0:06:54 lr: 0.000096 grad: 0.0714 (0.0748) loss: 0.8693 (0.8732) time: 0.1251 data: 0.0443 max mem: 8299 +Train: [35] [3200/6250] eta: 0:06:42 lr: 0.000096 grad: 0.0698 (0.0749) loss: 0.8674 (0.8731) time: 0.1489 data: 0.0797 max mem: 8299 +Train: [35] [3300/6250] eta: 0:06:29 lr: 0.000096 grad: 0.0764 (0.0751) loss: 0.8677 (0.8731) time: 0.1554 data: 0.0821 max mem: 8299 +Train: [35] [3400/6250] eta: 0:06:15 lr: 0.000096 grad: 0.0735 (0.0754) loss: 0.8739 (0.8730) time: 0.1352 data: 0.0641 max mem: 8299 +Train: [35] [3500/6250] eta: 0:06:02 lr: 0.000096 grad: 0.0793 (0.0756) loss: 0.8688 (0.8729) time: 0.1403 data: 0.0637 max mem: 8299 +Train: [35] [3600/6250] eta: 0:05:50 lr: 0.000096 grad: 0.0747 (0.0757) loss: 0.8758 (0.8728) time: 0.0918 data: 0.0180 max mem: 8299 +Train: [35] [3700/6250] eta: 0:05:36 lr: 0.000096 grad: 0.0757 (0.0758) loss: 0.8701 (0.8727) time: 0.1101 data: 0.0361 max mem: 8299 +Train: [35] [3800/6250] eta: 0:05:23 lr: 0.000096 grad: 0.0793 (0.0760) loss: 0.8692 (0.8726) time: 0.1458 data: 0.0680 max mem: 8299 +Train: [35] [3900/6250] eta: 0:05:10 lr: 0.000096 grad: 0.0797 (0.0761) loss: 0.8738 (0.8724) time: 0.1220 data: 0.0459 max mem: 8299 +Train: [35] [4000/6250] eta: 0:04:57 lr: 0.000096 grad: 0.0740 (0.0762) loss: 0.8684 (0.8722) time: 0.1257 data: 0.0499 max mem: 8299 +Train: [35] [4100/6250] eta: 0:04:44 lr: 0.000096 grad: 0.0738 (0.0763) loss: 0.8706 (0.8720) time: 0.1202 data: 0.0511 max mem: 8299 +Train: [35] [4200/6250] eta: 0:04:31 lr: 0.000096 grad: 0.0741 (0.0764) loss: 0.8709 (0.8719) time: 0.1424 data: 0.0700 max mem: 8299 +Train: [35] [4300/6250] eta: 0:04:18 lr: 0.000095 grad: 0.0719 (0.0765) loss: 0.8642 (0.8718) time: 0.1175 data: 0.0476 max mem: 8299 +Train: [35] [4400/6250] eta: 0:04:05 lr: 0.000095 grad: 0.0709 (0.0766) loss: 0.8654 (0.8716) time: 0.1580 data: 0.0908 max mem: 8299 +Train: [35] [4500/6250] eta: 0:03:52 lr: 0.000095 grad: 0.0763 (0.0767) loss: 0.8655 (0.8714) time: 0.1211 data: 0.0387 max mem: 8299 +Train: [35] [4600/6250] eta: 0:03:38 lr: 0.000095 grad: 0.0804 (0.0768) loss: 0.8620 (0.8712) time: 0.1468 data: 0.0728 max mem: 8299 +Train: [35] [4700/6250] eta: 0:03:25 lr: 0.000095 grad: 0.0749 (0.0769) loss: 0.8731 (0.8710) time: 0.1246 data: 0.0388 max mem: 8299 +Train: [35] [4800/6250] eta: 0:03:12 lr: 0.000095 grad: 0.0739 (0.0769) loss: 0.8689 (0.8709) time: 0.1255 data: 0.0387 max mem: 8299 +Train: [35] [4900/6250] eta: 0:02:59 lr: 0.000095 grad: 0.0799 (0.0771) loss: 0.8627 (0.8707) time: 0.1365 data: 0.0663 max mem: 8299 +Train: [35] [5000/6250] eta: 0:02:45 lr: 0.000095 grad: 0.0734 (0.0771) loss: 0.8688 (0.8706) time: 0.1392 data: 0.0691 max mem: 8299 +Train: [35] [5100/6250] eta: 0:02:32 lr: 0.000095 grad: 0.0795 (0.0772) loss: 0.8635 (0.8705) time: 0.1298 data: 0.0556 max mem: 8299 +Train: [35] [5200/6250] eta: 0:02:19 lr: 0.000095 grad: 0.0803 (0.0773) loss: 0.8645 (0.8704) time: 0.1342 data: 0.0538 max mem: 8299 +Train: [35] [5300/6250] eta: 0:02:06 lr: 0.000095 grad: 0.0816 (0.0774) loss: 0.8637 (0.8703) time: 0.1120 data: 0.0391 max mem: 8299 +Train: [35] [5400/6250] eta: 0:01:53 lr: 0.000095 grad: 0.0779 (0.0775) loss: 0.8675 (0.8701) time: 0.1671 data: 0.0992 max mem: 8299 +Train: [35] [5500/6250] eta: 0:01:40 lr: 0.000095 grad: 0.0764 (0.0776) loss: 0.8674 (0.8700) time: 0.1418 data: 0.0670 max mem: 8299 +Train: [35] [5600/6250] eta: 0:01:27 lr: 0.000095 grad: 0.0744 (0.0776) loss: 0.8679 (0.8699) time: 0.1396 data: 0.0632 max mem: 8299 +Train: [35] [5700/6250] eta: 0:01:13 lr: 0.000095 grad: 0.0687 (0.0776) loss: 0.8685 (0.8699) time: 0.1413 data: 0.0650 max mem: 8299 +Train: [35] [5800/6250] eta: 0:01:00 lr: 0.000095 grad: 0.0751 (0.0776) loss: 0.8667 (0.8698) time: 0.1432 data: 0.0696 max mem: 8299 +Train: [35] [5900/6250] eta: 0:00:46 lr: 0.000095 grad: 0.0703 (0.0776) loss: 0.8697 (0.8698) time: 0.1315 data: 0.0639 max mem: 8299 +Train: [35] [6000/6250] eta: 0:00:33 lr: 0.000095 grad: 0.0768 (0.0775) loss: 0.8721 (0.8698) time: 0.1271 data: 0.0510 max mem: 8299 +Train: [35] [6100/6250] eta: 0:00:20 lr: 0.000095 grad: 0.0803 (0.0775) loss: 0.8663 (0.8698) time: 0.1214 data: 0.0383 max mem: 8299 +Train: [35] [6200/6250] eta: 0:00:06 lr: 0.000095 grad: 0.0697 (0.0775) loss: 0.8771 (0.8699) time: 0.1208 data: 0.0365 max mem: 8299 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0739 (0.0775) loss: 0.8752 (0.8699) time: 0.1358 data: 0.0621 max mem: 8299 +Train: [35] Total time: 0:14:01 (0.1346 s / it) +Averaged stats: lr: 0.000095 grad: 0.0739 (0.0775) loss: 0.8752 (0.8699) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:05:39 loss: 0.8936 (0.8936) time: 5.4687 data: 5.4380 max mem: 8299 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8874 (0.8884) time: 0.1144 data: 0.0898 max mem: 8299 +Eval (hcp-train-subset): [35] Total time: 0:00:12 (0.2050 s / it) +Averaged stats (hcp-train-subset): loss: 0.8874 (0.8884) +Eval (hcp-val): [35] [ 0/62] eta: 0:03:14 loss: 0.8841 (0.8841) time: 3.1444 data: 3.0322 max mem: 8299 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8841 (0.8849) time: 0.1055 data: 0.0812 max mem: 8299 +Eval (hcp-val): [35] Total time: 0:00:11 (0.1921 s / it) +Averaged stats (hcp-val): loss: 0.8841 (0.8849) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 8:23:25 lr: 0.000095 grad: nan (nan) loss: 0.9254 (0.9254) time: 4.8330 data: 4.5791 max mem: 8299 +Train: [36] [ 100/6250] eta: 0:19:15 lr: 0.000095 grad: 0.0647 (0.0770) loss: 0.8880 (0.8853) time: 0.1420 data: 0.0478 max mem: 8299 +Train: [36] [ 200/6250] eta: 0:16:19 lr: 0.000095 grad: 0.0706 (0.0790) loss: 0.8728 (0.8794) time: 0.1259 data: 0.0421 max mem: 8299 +Train: [36] [ 300/6250] eta: 0:14:57 lr: 0.000095 grad: 0.0682 (0.0777) loss: 0.8646 (0.8767) time: 0.1189 data: 0.0412 max mem: 8299 +Train: [36] [ 400/6250] eta: 0:14:12 lr: 0.000095 grad: 0.0688 (0.0759) loss: 0.8592 (0.8743) time: 0.1657 data: 0.0784 max mem: 8299 +Train: [36] [ 500/6250] eta: 0:13:29 lr: 0.000095 grad: 0.0685 (0.0750) loss: 0.8796 (0.8733) time: 0.1277 data: 0.0545 max mem: 8299 +Train: [36] [ 600/6250] eta: 0:13:13 lr: 0.000095 grad: 0.0699 (0.0741) loss: 0.8703 (0.8730) time: 0.1181 data: 0.0428 max mem: 8299 +Train: [36] [ 700/6250] eta: 0:12:57 lr: 0.000095 grad: 0.0642 (0.0729) loss: 0.8749 (0.8734) time: 0.1170 data: 0.0367 max mem: 8299 +Train: [36] [ 800/6250] eta: 0:12:37 lr: 0.000095 grad: 0.0641 (0.0720) loss: 0.8696 (0.8736) time: 0.1349 data: 0.0604 max mem: 8299 +Train: [36] [ 900/6250] eta: 0:12:26 lr: 0.000095 grad: 0.0746 (0.0720) loss: 0.8676 (0.8734) time: 0.1425 data: 0.0597 max mem: 8299 +Train: [36] [1000/6250] eta: 0:12:05 lr: 0.000095 grad: 0.0682 (0.0720) loss: 0.8651 (0.8730) time: 0.1151 data: 0.0396 max mem: 8299 +Train: [36] [1100/6250] eta: 0:11:44 lr: 0.000095 grad: 0.0688 (0.0721) loss: 0.8748 (0.8728) time: 0.1141 data: 0.0463 max mem: 8299 +Train: [36] [1200/6250] eta: 0:11:26 lr: 0.000095 grad: 0.0751 (0.0725) loss: 0.8710 (0.8723) time: 0.1313 data: 0.0602 max mem: 8299 +Train: [36] [1300/6250] eta: 0:11:12 lr: 0.000095 grad: 0.0737 (0.0729) loss: 0.8708 (0.8719) time: 0.1430 data: 0.0689 max mem: 8299 +Train: [36] [1400/6250] eta: 0:10:57 lr: 0.000095 grad: 0.0696 (0.0731) loss: 0.8719 (0.8717) time: 0.1271 data: 0.0449 max mem: 8299 +Train: [36] [1500/6250] eta: 0:10:44 lr: 0.000095 grad: 0.0691 (0.0731) loss: 0.8690 (0.8715) time: 0.1586 data: 0.0878 max mem: 8299 +Train: [36] [1600/6250] eta: 0:10:29 lr: 0.000094 grad: 0.0720 (0.0732) loss: 0.8700 (0.8713) time: 0.1504 data: 0.0710 max mem: 8299 +Train: [36] [1700/6250] eta: 0:10:14 lr: 0.000094 grad: 0.0757 (0.0735) loss: 0.8652 (0.8709) time: 0.1334 data: 0.0554 max mem: 8299 +Train: [36] [1800/6250] eta: 0:10:00 lr: 0.000094 grad: 0.0674 (0.0737) loss: 0.8695 (0.8705) time: 0.1406 data: 0.0630 max mem: 8299 +Train: [36] [1900/6250] eta: 0:09:46 lr: 0.000094 grad: 0.0740 (0.0739) loss: 0.8647 (0.8704) time: 0.1285 data: 0.0468 max mem: 8299 +Train: [36] [2000/6250] eta: 0:09:32 lr: 0.000094 grad: 0.0733 (0.0741) loss: 0.8661 (0.8702) time: 0.0928 data: 0.0178 max mem: 8299 +Train: [36] [2100/6250] eta: 0:09:17 lr: 0.000094 grad: 0.0755 (0.0744) loss: 0.8618 (0.8699) time: 0.1044 data: 0.0193 max mem: 8299 +Train: [36] [2200/6250] eta: 0:09:03 lr: 0.000094 grad: 0.0686 (0.0746) loss: 0.8675 (0.8697) time: 0.1331 data: 0.0594 max mem: 8299 +Train: [36] [2300/6250] eta: 0:08:50 lr: 0.000094 grad: 0.0814 (0.0748) loss: 0.8629 (0.8695) time: 0.1246 data: 0.0545 max mem: 8299 +Train: [36] [2400/6250] eta: 0:08:37 lr: 0.000094 grad: 0.0792 (0.0750) loss: 0.8676 (0.8693) time: 0.0971 data: 0.0164 max mem: 8299 +Train: [36] [2500/6250] eta: 0:08:24 lr: 0.000094 grad: 0.0770 (0.0751) loss: 0.8658 (0.8691) time: 0.1259 data: 0.0506 max mem: 8299 +Train: [36] [2600/6250] eta: 0:08:11 lr: 0.000094 grad: 0.0813 (0.0752) loss: 0.8671 (0.8691) time: 0.1214 data: 0.0388 max mem: 8299 +Train: [36] [2700/6250] eta: 0:07:57 lr: 0.000094 grad: 0.0726 (0.0753) loss: 0.8701 (0.8690) time: 0.1189 data: 0.0416 max mem: 8299 +Train: [36] [2800/6250] eta: 0:07:44 lr: 0.000094 grad: 0.0708 (0.0755) loss: 0.8765 (0.8690) time: 0.1295 data: 0.0525 max mem: 8299 +Train: [36] [2900/6250] eta: 0:07:30 lr: 0.000094 grad: 0.0696 (0.0755) loss: 0.8739 (0.8689) time: 0.1207 data: 0.0487 max mem: 8299 +Train: [36] [3000/6250] eta: 0:07:17 lr: 0.000094 grad: 0.0785 (0.0756) loss: 0.8662 (0.8688) time: 0.1440 data: 0.0644 max mem: 8299 +Train: [36] [3100/6250] eta: 0:07:03 lr: 0.000094 grad: 0.0757 (0.0757) loss: 0.8680 (0.8688) time: 0.1296 data: 0.0485 max mem: 8299 +Train: [36] [3200/6250] eta: 0:06:50 lr: 0.000094 grad: 0.0728 (0.0758) loss: 0.8645 (0.8687) time: 0.1351 data: 0.0661 max mem: 8299 +Train: [36] [3300/6250] eta: 0:06:36 lr: 0.000094 grad: 0.0773 (0.0759) loss: 0.8679 (0.8687) time: 0.1033 data: 0.0254 max mem: 8299 +Train: [36] [3400/6250] eta: 0:06:22 lr: 0.000094 grad: 0.0704 (0.0759) loss: 0.8682 (0.8686) time: 0.1346 data: 0.0572 max mem: 8299 +Train: [36] [3500/6250] eta: 0:06:09 lr: 0.000094 grad: 0.0720 (0.0759) loss: 0.8717 (0.8687) time: 0.1065 data: 0.0311 max mem: 8299 +Train: [36] [3600/6250] eta: 0:05:55 lr: 0.000094 grad: 0.0728 (0.0758) loss: 0.8662 (0.8687) time: 0.1375 data: 0.0607 max mem: 8299 +Train: [36] [3700/6250] eta: 0:05:42 lr: 0.000094 grad: 0.0726 (0.0759) loss: 0.8644 (0.8687) time: 0.1537 data: 0.0844 max mem: 8299 +Train: [36] [3800/6250] eta: 0:05:29 lr: 0.000094 grad: 0.0717 (0.0759) loss: 0.8670 (0.8688) time: 0.1347 data: 0.0642 max mem: 8299 +Train: [36] [3900/6250] eta: 0:05:16 lr: 0.000094 grad: 0.0771 (0.0759) loss: 0.8660 (0.8688) time: 0.1492 data: 0.0754 max mem: 8299 +Train: [36] [4000/6250] eta: 0:05:03 lr: 0.000094 grad: 0.0773 (0.0760) loss: 0.8644 (0.8688) time: 0.1483 data: 0.0795 max mem: 8299 +Train: [36] [4100/6250] eta: 0:04:49 lr: 0.000094 grad: 0.0760 (0.0760) loss: 0.8610 (0.8687) time: 0.1360 data: 0.0690 max mem: 8299 +Train: [36] [4200/6250] eta: 0:04:36 lr: 0.000094 grad: 0.0733 (0.0760) loss: 0.8648 (0.8687) time: 0.1566 data: 0.0840 max mem: 8299 +Train: [36] [4300/6250] eta: 0:04:22 lr: 0.000094 grad: 0.0732 (0.0761) loss: 0.8599 (0.8687) time: 0.1272 data: 0.0583 max mem: 8299 +Train: [36] [4400/6250] eta: 0:04:09 lr: 0.000094 grad: 0.0764 (0.0762) loss: 0.8688 (0.8686) time: 0.1117 data: 0.0331 max mem: 8299 +Train: [36] [4500/6250] eta: 0:03:56 lr: 0.000094 grad: 0.0712 (0.0762) loss: 0.8711 (0.8686) time: 0.1077 data: 0.0375 max mem: 8299 +Train: [36] [4600/6250] eta: 0:03:42 lr: 0.000094 grad: 0.0740 (0.0762) loss: 0.8685 (0.8686) time: 0.0911 data: 0.0113 max mem: 8299 +Train: [36] [4700/6250] eta: 0:03:29 lr: 0.000094 grad: 0.0760 (0.0763) loss: 0.8697 (0.8686) time: 0.1031 data: 0.0257 max mem: 8299 +Train: [36] [4800/6250] eta: 0:03:15 lr: 0.000094 grad: 0.0799 (0.0763) loss: 0.8713 (0.8685) time: 0.1374 data: 0.0599 max mem: 8299 +Train: [36] [4900/6250] eta: 0:03:02 lr: 0.000094 grad: 0.0746 (0.0764) loss: 0.8673 (0.8685) time: 0.1636 data: 0.0877 max mem: 8299 +Train: [36] [5000/6250] eta: 0:02:49 lr: 0.000094 grad: 0.0731 (0.0764) loss: 0.8643 (0.8685) time: 0.2031 data: 0.1287 max mem: 8299 +Train: [36] [5100/6250] eta: 0:02:35 lr: 0.000093 grad: 0.0759 (0.0764) loss: 0.8671 (0.8685) time: 0.1361 data: 0.0635 max mem: 8299 +Train: [36] [5200/6250] eta: 0:02:22 lr: 0.000093 grad: 0.0767 (0.0765) loss: 0.8674 (0.8685) time: 0.1654 data: 0.0782 max mem: 8299 +Train: [36] [5300/6250] eta: 0:02:09 lr: 0.000093 grad: 0.0804 (0.0765) loss: 0.8610 (0.8684) time: 0.1593 data: 0.0821 max mem: 8299 +Train: [36] [5400/6250] eta: 0:01:55 lr: 0.000093 grad: 0.0726 (0.0765) loss: 0.8665 (0.8684) time: 0.1425 data: 0.0669 max mem: 8299 +Train: [36] [5500/6250] eta: 0:01:42 lr: 0.000093 grad: 0.0731 (0.0765) loss: 0.8732 (0.8684) time: 0.1370 data: 0.0559 max mem: 8299 +Train: [36] [5600/6250] eta: 0:01:28 lr: 0.000093 grad: 0.0736 (0.0765) loss: 0.8690 (0.8684) time: 0.1170 data: 0.0394 max mem: 8299 +Train: [36] [5700/6250] eta: 0:01:14 lr: 0.000093 grad: 0.0799 (0.0766) loss: 0.8654 (0.8684) time: 0.1202 data: 0.0434 max mem: 8299 +Train: [36] [5800/6250] eta: 0:01:01 lr: 0.000093 grad: 0.0743 (0.0766) loss: 0.8702 (0.8683) time: 0.1258 data: 0.0490 max mem: 8299 +Train: [36] [5900/6250] eta: 0:00:47 lr: 0.000093 grad: 0.0730 (0.0766) loss: 0.8671 (0.8683) time: 0.1480 data: 0.0717 max mem: 8299 +Train: [36] [6000/6250] eta: 0:00:33 lr: 0.000093 grad: 0.0776 (0.0766) loss: 0.8656 (0.8683) time: 0.1167 data: 0.0329 max mem: 8299 +Train: [36] [6100/6250] eta: 0:00:20 lr: 0.000093 grad: 0.0687 (0.0766) loss: 0.8669 (0.8682) time: 0.1428 data: 0.0701 max mem: 8299 +Train: [36] [6200/6250] eta: 0:00:06 lr: 0.000093 grad: 0.0688 (0.0766) loss: 0.8652 (0.8682) time: 0.1223 data: 0.0418 max mem: 8299 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0760 (0.0766) loss: 0.8547 (0.8681) time: 0.1290 data: 0.0548 max mem: 8299 +Train: [36] Total time: 0:14:09 (0.1359 s / it) +Averaged stats: lr: 0.000093 grad: 0.0760 (0.0766) loss: 0.8547 (0.8681) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:03:57 loss: 0.9009 (0.9009) time: 3.8380 data: 3.7996 max mem: 8299 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8909 (0.8916) time: 0.1269 data: 0.1023 max mem: 8299 +Eval (hcp-train-subset): [36] Total time: 0:00:12 (0.2060 s / it) +Averaged stats (hcp-train-subset): loss: 0.8909 (0.8916) +Eval (hcp-val): [36] [ 0/62] eta: 0:03:58 loss: 0.8859 (0.8859) time: 3.8545 data: 3.7680 max mem: 8299 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8848 (0.8868) time: 0.1248 data: 0.0994 max mem: 8299 +Eval (hcp-val): [36] Total time: 0:00:12 (0.1985 s / it) +Averaged stats (hcp-val): loss: 0.8848 (0.8868) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 10:19:19 lr: 0.000093 grad: nan (nan) loss: 0.8923 (0.8923) time: 5.9454 data: 5.8545 max mem: 8299 +Train: [37] [ 100/6250] eta: 0:19:39 lr: 0.000093 grad: 0.0681 (0.0846) loss: 0.8688 (0.8741) time: 0.1478 data: 0.0504 max mem: 8299 +Train: [37] [ 200/6250] eta: 0:16:32 lr: 0.000093 grad: 0.0736 (0.0826) loss: 0.8763 (0.8734) time: 0.1380 data: 0.0532 max mem: 8299 +Train: [37] [ 300/6250] eta: 0:15:03 lr: 0.000093 grad: 0.0703 (0.0816) loss: 0.8686 (0.8722) time: 0.1182 data: 0.0368 max mem: 8299 +Train: [37] [ 400/6250] eta: 0:14:13 lr: 0.000093 grad: 0.0694 (0.0803) loss: 0.8675 (0.8712) time: 0.1264 data: 0.0344 max mem: 8299 +Train: [37] [ 500/6250] eta: 0:13:37 lr: 0.000093 grad: 0.0691 (0.0787) loss: 0.8746 (0.8710) time: 0.1127 data: 0.0226 max mem: 8299 +Train: [37] [ 600/6250] eta: 0:13:06 lr: 0.000093 grad: 0.0707 (0.0782) loss: 0.8689 (0.8706) time: 0.1149 data: 0.0315 max mem: 8299 +Train: [37] [ 700/6250] eta: 0:12:52 lr: 0.000093 grad: 0.0673 (0.0785) loss: 0.8763 (0.8706) time: 0.1540 data: 0.0720 max mem: 8299 +Train: [37] [ 800/6250] eta: 0:12:36 lr: 0.000093 grad: 0.0737 (0.0786) loss: 0.8726 (0.8708) time: 0.1491 data: 0.0685 max mem: 8299 +Train: [37] [ 900/6250] eta: 0:12:23 lr: 0.000093 grad: 0.0651 (0.0783) loss: 0.8764 (0.8711) time: 0.1292 data: 0.0346 max mem: 8299 +Train: [37] [1000/6250] eta: 0:12:04 lr: 0.000093 grad: 0.0746 (0.0781) loss: 0.8665 (0.8710) time: 0.1320 data: 0.0477 max mem: 8299 +Train: [37] [1100/6250] eta: 0:11:46 lr: 0.000093 grad: 0.0691 (0.0778) loss: 0.8737 (0.8707) time: 0.1231 data: 0.0463 max mem: 8299 +Train: [37] [1200/6250] eta: 0:11:27 lr: 0.000093 grad: 0.0736 (0.0774) loss: 0.8727 (0.8706) time: 0.1081 data: 0.0380 max mem: 8299 +Train: [37] [1300/6250] eta: 0:11:16 lr: 0.000093 grad: 0.0710 (0.0772) loss: 0.8721 (0.8705) time: 0.1385 data: 0.0676 max mem: 8299 +Train: [37] [1400/6250] eta: 0:11:03 lr: 0.000093 grad: 0.0719 (0.0770) loss: 0.8651 (0.8705) time: 0.1654 data: 0.0973 max mem: 8299 +Train: [37] [1500/6250] eta: 0:10:50 lr: 0.000093 grad: 0.0738 (0.0770) loss: 0.8740 (0.8704) time: 0.1457 data: 0.0758 max mem: 8299 +Train: [37] [1600/6250] eta: 0:10:38 lr: 0.000093 grad: 0.0769 (0.0770) loss: 0.8704 (0.8703) time: 0.1474 data: 0.0624 max mem: 8299 +Train: [37] [1700/6250] eta: 0:10:27 lr: 0.000093 grad: 0.0751 (0.0768) loss: 0.8656 (0.8702) time: 0.1940 data: 0.1174 max mem: 8299 +Train: [37] [1800/6250] eta: 0:10:10 lr: 0.000093 grad: 0.0700 (0.0768) loss: 0.8760 (0.8702) time: 0.1537 data: 0.0777 max mem: 8299 +Train: [37] [1900/6250] eta: 0:09:56 lr: 0.000093 grad: 0.0737 (0.0766) loss: 0.8698 (0.8701) time: 0.1333 data: 0.0519 max mem: 8299 +Train: [37] [2000/6250] eta: 0:09:43 lr: 0.000093 grad: 0.0678 (0.0766) loss: 0.8762 (0.8701) time: 0.1366 data: 0.0406 max mem: 8299 +Train: [37] [2100/6250] eta: 0:09:29 lr: 0.000093 grad: 0.0654 (0.0767) loss: 0.8714 (0.8700) time: 0.1495 data: 0.0712 max mem: 8299 +Train: [37] [2200/6250] eta: 0:09:15 lr: 0.000093 grad: 0.0714 (0.0767) loss: 0.8735 (0.8698) time: 0.1311 data: 0.0577 max mem: 8299 +Train: [37] [2300/6250] eta: 0:08:59 lr: 0.000092 grad: 0.0776 (0.0768) loss: 0.8633 (0.8697) time: 0.1070 data: 0.0302 max mem: 8299 +Train: [37] [2400/6250] eta: 0:08:46 lr: 0.000092 grad: 0.0777 (0.0769) loss: 0.8648 (0.8696) time: 0.1589 data: 0.0812 max mem: 8299 +Train: [37] [2500/6250] eta: 0:08:31 lr: 0.000092 grad: 0.0772 (0.0769) loss: 0.8673 (0.8695) time: 0.1433 data: 0.0681 max mem: 8299 +Train: [37] [2600/6250] eta: 0:08:17 lr: 0.000092 grad: 0.0723 (0.0769) loss: 0.8725 (0.8695) time: 0.1283 data: 0.0458 max mem: 8299 +Train: [37] [2700/6250] eta: 0:08:03 lr: 0.000092 grad: 0.0763 (0.0770) loss: 0.8681 (0.8696) time: 0.1280 data: 0.0549 max mem: 8299 +Train: [37] [2800/6250] eta: 0:07:49 lr: 0.000092 grad: 0.0762 (0.0771) loss: 0.8716 (0.8694) time: 0.1535 data: 0.0784 max mem: 8299 +Train: [37] [2900/6250] eta: 0:07:34 lr: 0.000092 grad: 0.0749 (0.0772) loss: 0.8665 (0.8693) time: 0.1391 data: 0.0551 max mem: 8299 +Train: [37] [3000/6250] eta: 0:07:21 lr: 0.000092 grad: 0.0755 (0.0773) loss: 0.8692 (0.8693) time: 0.1656 data: 0.0889 max mem: 8299 +Train: [37] [3100/6250] eta: 0:07:07 lr: 0.000092 grad: 0.0769 (0.0775) loss: 0.8689 (0.8692) time: 0.1135 data: 0.0278 max mem: 8299 +Train: [37] [3200/6250] eta: 0:06:53 lr: 0.000092 grad: 0.0854 (0.0776) loss: 0.8554 (0.8690) time: 0.1620 data: 0.0986 max mem: 8299 +Train: [37] [3300/6250] eta: 0:06:39 lr: 0.000092 grad: 0.0856 (0.0777) loss: 0.8655 (0.8689) time: 0.0943 data: 0.0134 max mem: 8299 +Train: [37] [3400/6250] eta: 0:06:26 lr: 0.000092 grad: 0.0800 (0.0778) loss: 0.8619 (0.8689) time: 0.1725 data: 0.0918 max mem: 8299 +Train: [37] [3500/6250] eta: 0:06:12 lr: 0.000092 grad: 0.0797 (0.0779) loss: 0.8712 (0.8688) time: 0.1517 data: 0.0774 max mem: 8299 +Train: [37] [3600/6250] eta: 0:05:58 lr: 0.000092 grad: 0.0778 (0.0780) loss: 0.8670 (0.8687) time: 0.1339 data: 0.0473 max mem: 8299 +Train: [37] [3700/6250] eta: 0:05:45 lr: 0.000092 grad: 0.0797 (0.0780) loss: 0.8662 (0.8687) time: 0.1606 data: 0.0714 max mem: 8299 +Train: [37] [3800/6250] eta: 0:05:32 lr: 0.000092 grad: 0.0744 (0.0781) loss: 0.8663 (0.8687) time: 0.1432 data: 0.0683 max mem: 8299 +Train: [37] [3900/6250] eta: 0:05:19 lr: 0.000092 grad: 0.0823 (0.0781) loss: 0.8658 (0.8687) time: 0.1405 data: 0.0599 max mem: 8299 +Train: [37] [4000/6250] eta: 0:05:06 lr: 0.000092 grad: 0.0784 (0.0782) loss: 0.8618 (0.8687) time: 0.1437 data: 0.0704 max mem: 8299 +Train: [37] [4100/6250] eta: 0:04:52 lr: 0.000092 grad: 0.0787 (0.0782) loss: 0.8695 (0.8687) time: 0.1323 data: 0.0533 max mem: 8299 +Train: [37] [4200/6250] eta: 0:04:38 lr: 0.000092 grad: 0.0768 (0.0783) loss: 0.8665 (0.8687) time: 0.1352 data: 0.0551 max mem: 8299 +Train: [37] [4300/6250] eta: 0:04:24 lr: 0.000092 grad: 0.0810 (0.0783) loss: 0.8651 (0.8687) time: 0.1231 data: 0.0426 max mem: 8299 +Train: [37] [4400/6250] eta: 0:04:10 lr: 0.000092 grad: 0.0792 (0.0784) loss: 0.8569 (0.8686) time: 0.1522 data: 0.0818 max mem: 8299 +Train: [37] [4500/6250] eta: 0:03:56 lr: 0.000092 grad: 0.0784 (0.0785) loss: 0.8638 (0.8686) time: 0.1459 data: 0.0682 max mem: 8299 +Train: [37] [4600/6250] eta: 0:03:42 lr: 0.000092 grad: 0.0741 (0.0785) loss: 0.8698 (0.8686) time: 0.1251 data: 0.0442 max mem: 8299 +Train: [37] [4700/6250] eta: 0:03:29 lr: 0.000092 grad: 0.0772 (0.0786) loss: 0.8675 (0.8686) time: 0.1247 data: 0.0471 max mem: 8299 +Train: [37] [4800/6250] eta: 0:03:15 lr: 0.000092 grad: 0.0792 (0.0786) loss: 0.8727 (0.8685) time: 0.1091 data: 0.0181 max mem: 8299 +Train: [37] [4900/6250] eta: 0:03:01 lr: 0.000092 grad: 0.0805 (0.0787) loss: 0.8646 (0.8684) time: 0.1435 data: 0.0724 max mem: 8299 +Train: [37] [5000/6250] eta: 0:02:48 lr: 0.000092 grad: 0.0764 (0.0788) loss: 0.8761 (0.8684) time: 0.1332 data: 0.0627 max mem: 8299 +Train: [37] [5100/6250] eta: 0:02:34 lr: 0.000092 grad: 0.0832 (0.0788) loss: 0.8593 (0.8683) time: 0.1278 data: 0.0523 max mem: 8299 +Train: [37] [5200/6250] eta: 0:02:21 lr: 0.000092 grad: 0.0824 (0.0789) loss: 0.8660 (0.8683) time: 0.1554 data: 0.0794 max mem: 8299 +Train: [37] [5300/6250] eta: 0:02:08 lr: 0.000092 grad: 0.0776 (0.0789) loss: 0.8655 (0.8683) time: 0.1285 data: 0.0590 max mem: 8299 +Train: [37] [5400/6250] eta: 0:01:55 lr: 0.000092 grad: 0.0747 (0.0789) loss: 0.8598 (0.8682) time: 0.1548 data: 0.0877 max mem: 8299 +Train: [37] [5500/6250] eta: 0:01:41 lr: 0.000092 grad: 0.0788 (0.0790) loss: 0.8652 (0.8681) time: 0.1415 data: 0.0551 max mem: 8299 +Train: [37] [5600/6250] eta: 0:01:28 lr: 0.000092 grad: 0.0746 (0.0791) loss: 0.8660 (0.8680) time: 0.1331 data: 0.0601 max mem: 8299 +Train: [37] [5700/6250] eta: 0:01:14 lr: 0.000091 grad: 0.0746 (0.0791) loss: 0.8626 (0.8680) time: 0.1113 data: 0.0355 max mem: 8299 +Train: [37] [5800/6250] eta: 0:01:00 lr: 0.000091 grad: 0.0695 (0.0791) loss: 0.8710 (0.8679) time: 0.1142 data: 0.0301 max mem: 8299 +Train: [37] [5900/6250] eta: 0:00:47 lr: 0.000091 grad: 0.0713 (0.0791) loss: 0.8700 (0.8679) time: 0.1155 data: 0.0355 max mem: 8299 +Train: [37] [6000/6250] eta: 0:00:33 lr: 0.000091 grad: 0.0725 (0.0791) loss: 0.8638 (0.8678) time: 0.1363 data: 0.0694 max mem: 8299 +Train: [37] [6100/6250] eta: 0:00:20 lr: 0.000091 grad: 0.0800 (0.0792) loss: 0.8596 (0.8678) time: 0.1147 data: 0.0306 max mem: 8299 +Train: [37] [6200/6250] eta: 0:00:06 lr: 0.000091 grad: 0.0812 (0.0793) loss: 0.8675 (0.8677) time: 0.1209 data: 0.0417 max mem: 8299 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0837 (0.0793) loss: 0.8656 (0.8677) time: 0.1351 data: 0.0585 max mem: 8299 +Train: [37] Total time: 0:14:07 (0.1356 s / it) +Averaged stats: lr: 0.000091 grad: 0.0837 (0.0793) loss: 0.8656 (0.8677) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:04:18 loss: 0.8978 (0.8978) time: 4.1720 data: 4.1421 max mem: 8299 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8865 (0.8889) time: 0.1086 data: 0.0833 max mem: 8299 +Eval (hcp-train-subset): [37] Total time: 0:00:11 (0.1902 s / it) +Averaged stats (hcp-train-subset): loss: 0.8865 (0.8889) +Eval (hcp-val): [37] [ 0/62] eta: 0:03:02 loss: 0.8880 (0.8880) time: 2.9491 data: 2.8532 max mem: 8299 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8849 (0.8867) time: 0.1084 data: 0.0841 max mem: 8299 +Eval (hcp-val): [37] Total time: 0:00:11 (0.1900 s / it) +Averaged stats (hcp-val): loss: 0.8849 (0.8867) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 7:47:43 lr: 0.000091 grad: 0.1879 (0.1879) loss: 0.9380 (0.9380) time: 4.4901 data: 4.2305 max mem: 8299 +Train: [38] [ 100/6250] eta: 0:19:19 lr: 0.000091 grad: 0.0600 (0.0699) loss: 0.8843 (0.8835) time: 0.1285 data: 0.0286 max mem: 8299 +Train: [38] [ 200/6250] eta: 0:16:40 lr: 0.000091 grad: 0.0687 (0.0699) loss: 0.8795 (0.8806) time: 0.1723 data: 0.0846 max mem: 8299 +Train: [38] [ 300/6250] eta: 0:15:20 lr: 0.000091 grad: 0.0604 (0.0687) loss: 0.8798 (0.8796) time: 0.1439 data: 0.0683 max mem: 8299 +Train: [38] [ 400/6250] eta: 0:14:23 lr: 0.000091 grad: 0.0628 (0.0690) loss: 0.8785 (0.8779) time: 0.1376 data: 0.0491 max mem: 8299 +Train: [38] [ 500/6250] eta: 0:13:45 lr: 0.000091 grad: 0.0673 (0.0688) loss: 0.8713 (0.8768) time: 0.1321 data: 0.0475 max mem: 8299 +Train: [38] [ 600/6250] eta: 0:13:21 lr: 0.000091 grad: 0.0692 (0.0685) loss: 0.8727 (0.8765) time: 0.1584 data: 0.0746 max mem: 8299 +Train: [38] [ 700/6250] eta: 0:13:08 lr: 0.000091 grad: 0.0666 (0.0687) loss: 0.8736 (0.8762) time: 0.1200 data: 0.0372 max mem: 8299 +Train: [38] [ 800/6250] eta: 0:12:59 lr: 0.000091 grad: 0.0709 (0.0689) loss: 0.8697 (0.8757) time: 0.1466 data: 0.0641 max mem: 8299 +Train: [38] [ 900/6250] eta: 0:12:49 lr: 0.000091 grad: 0.0647 (0.0690) loss: 0.8732 (0.8756) time: 0.1825 data: 0.1089 max mem: 8299 +Train: [38] [1000/6250] eta: 0:12:29 lr: 0.000091 grad: 0.0681 (0.0690) loss: 0.8703 (0.8752) time: 0.1296 data: 0.0593 max mem: 8299 +Train: [38] [1100/6250] eta: 0:12:14 lr: 0.000091 grad: 0.0739 (0.0692) loss: 0.8669 (0.8748) time: 0.1264 data: 0.0502 max mem: 8299 +Train: [38] [1200/6250] eta: 0:11:59 lr: 0.000091 grad: 0.0673 (0.0695) loss: 0.8677 (0.8743) time: 0.1324 data: 0.0565 max mem: 8299 +Train: [38] [1300/6250] eta: 0:11:45 lr: 0.000091 grad: 0.0663 (0.0696) loss: 0.8746 (0.8742) time: 0.1379 data: 0.0575 max mem: 8299 +Train: [38] [1400/6250] eta: 0:11:26 lr: 0.000091 grad: 0.0638 (0.0696) loss: 0.8702 (0.8740) time: 0.1292 data: 0.0571 max mem: 8299 +Train: [38] [1500/6250] eta: 0:11:13 lr: 0.000091 grad: 0.0673 (0.0696) loss: 0.8699 (0.8739) time: 0.1486 data: 0.0783 max mem: 8299 +Train: [38] [1600/6250] eta: 0:10:57 lr: 0.000091 grad: 0.0651 (0.0696) loss: 0.8745 (0.8738) time: 0.1378 data: 0.0692 max mem: 8299 +Train: [38] [1700/6250] eta: 0:10:41 lr: 0.000091 grad: 0.0702 (0.0697) loss: 0.8751 (0.8737) time: 0.1345 data: 0.0559 max mem: 8299 +Train: [38] [1800/6250] eta: 0:10:27 lr: 0.000091 grad: 0.0671 (0.0697) loss: 0.8678 (0.8736) time: 0.1669 data: 0.0872 max mem: 8299 +Train: [38] [1900/6250] eta: 0:10:11 lr: 0.000091 grad: 0.0668 (0.0697) loss: 0.8729 (0.8735) time: 0.1216 data: 0.0435 max mem: 8299 +Train: [38] [2000/6250] eta: 0:09:57 lr: 0.000091 grad: 0.0662 (0.0698) loss: 0.8775 (0.8734) time: 0.1468 data: 0.0687 max mem: 8299 +Train: [38] [2100/6250] eta: 0:09:41 lr: 0.000091 grad: 0.0714 (0.0701) loss: 0.8746 (0.8733) time: 0.1240 data: 0.0515 max mem: 8299 +Train: [38] [2200/6250] eta: 0:09:27 lr: 0.000091 grad: 0.0723 (0.0702) loss: 0.8712 (0.8733) time: 0.1425 data: 0.0606 max mem: 8299 +Train: [38] [2300/6250] eta: 0:09:12 lr: 0.000091 grad: 0.0687 (0.0703) loss: 0.8685 (0.8733) time: 0.1383 data: 0.0674 max mem: 8299 +Train: [38] [2400/6250] eta: 0:08:58 lr: 0.000091 grad: 0.0660 (0.0704) loss: 0.8707 (0.8733) time: 0.1664 data: 0.0976 max mem: 8299 +Train: [38] [2500/6250] eta: 0:08:42 lr: 0.000091 grad: 0.0651 (0.0705) loss: 0.8750 (0.8733) time: 0.1600 data: 0.0827 max mem: 8299 +Train: [38] [2600/6250] eta: 0:08:27 lr: 0.000091 grad: 0.0680 (0.0704) loss: 0.8716 (0.8734) time: 0.1283 data: 0.0540 max mem: 8299 +Train: [38] [2700/6250] eta: 0:08:12 lr: 0.000091 grad: 0.0695 (0.0706) loss: 0.8697 (0.8734) time: 0.1201 data: 0.0374 max mem: 8299 +Train: [38] [2800/6250] eta: 0:07:57 lr: 0.000091 grad: 0.0710 (0.0708) loss: 0.8719 (0.8733) time: 0.1264 data: 0.0563 max mem: 8299 +Train: [38] [2900/6250] eta: 0:07:43 lr: 0.000090 grad: 0.0669 (0.0708) loss: 0.8740 (0.8734) time: 0.1173 data: 0.0411 max mem: 8299 +Train: [38] [3000/6250] eta: 0:07:29 lr: 0.000090 grad: 0.0704 (0.0710) loss: 0.8758 (0.8734) time: 0.1314 data: 0.0492 max mem: 8299 +Train: [38] [3100/6250] eta: 0:07:14 lr: 0.000090 grad: 0.0816 (0.0712) loss: 0.8700 (0.8733) time: 0.0932 data: 0.0167 max mem: 8299 +Train: [38] [3200/6250] eta: 0:07:00 lr: 0.000090 grad: 0.0718 (0.0714) loss: 0.8770 (0.8732) time: 0.1604 data: 0.0816 max mem: 8299 +Train: [38] [3300/6250] eta: 0:06:45 lr: 0.000090 grad: 0.0767 (0.0716) loss: 0.8705 (0.8732) time: 0.1488 data: 0.0768 max mem: 8299 +Train: [38] [3400/6250] eta: 0:06:31 lr: 0.000090 grad: 0.0795 (0.0718) loss: 0.8700 (0.8730) time: 0.1225 data: 0.0401 max mem: 8299 +Train: [38] [3500/6250] eta: 0:06:17 lr: 0.000090 grad: 0.0820 (0.0721) loss: 0.8699 (0.8729) time: 0.1360 data: 0.0554 max mem: 8299 +Train: [38] [3600/6250] eta: 0:06:03 lr: 0.000090 grad: 0.0710 (0.0723) loss: 0.8665 (0.8728) time: 0.1173 data: 0.0321 max mem: 8299 +Train: [38] [3700/6250] eta: 0:05:49 lr: 0.000090 grad: 0.0705 (0.0726) loss: 0.8751 (0.8726) time: 0.0859 data: 0.0003 max mem: 8299 +Train: [38] [3800/6250] eta: 0:05:34 lr: 0.000090 grad: 0.0786 (0.0729) loss: 0.8695 (0.8725) time: 0.1202 data: 0.0433 max mem: 8299 +Train: [38] [3900/6250] eta: 0:05:20 lr: 0.000090 grad: 0.0773 (0.0731) loss: 0.8692 (0.8724) time: 0.1080 data: 0.0361 max mem: 8299 +Train: [38] [4000/6250] eta: 0:05:07 lr: 0.000090 grad: 0.0699 (0.0732) loss: 0.8766 (0.8722) time: 0.1537 data: 0.0688 max mem: 8299 +Train: [38] [4100/6250] eta: 0:04:53 lr: 0.000090 grad: 0.0747 (0.0734) loss: 0.8662 (0.8722) time: 0.1478 data: 0.0682 max mem: 8299 +Train: [38] [4200/6250] eta: 0:04:39 lr: 0.000090 grad: 0.0766 (0.0735) loss: 0.8651 (0.8721) time: 0.1673 data: 0.0970 max mem: 8299 +Train: [38] [4300/6250] eta: 0:04:25 lr: 0.000090 grad: 0.0780 (0.0737) loss: 0.8633 (0.8720) time: 0.1363 data: 0.0533 max mem: 8299 +Train: [38] [4400/6250] eta: 0:04:11 lr: 0.000090 grad: 0.0757 (0.0738) loss: 0.8656 (0.8719) time: 0.1341 data: 0.0591 max mem: 8299 +Train: [38] [4500/6250] eta: 0:03:58 lr: 0.000090 grad: 0.0714 (0.0739) loss: 0.8687 (0.8718) time: 0.1533 data: 0.0764 max mem: 8299 +Train: [38] [4600/6250] eta: 0:03:44 lr: 0.000090 grad: 0.0814 (0.0740) loss: 0.8703 (0.8718) time: 0.1295 data: 0.0459 max mem: 8299 +Train: [38] [4700/6250] eta: 0:03:30 lr: 0.000090 grad: 0.0708 (0.0742) loss: 0.8746 (0.8718) time: 0.1480 data: 0.0742 max mem: 8299 +Train: [38] [4800/6250] eta: 0:03:17 lr: 0.000090 grad: 0.0712 (0.0743) loss: 0.8748 (0.8717) time: 0.1323 data: 0.0650 max mem: 8299 +Train: [38] [4900/6250] eta: 0:03:03 lr: 0.000090 grad: 0.0777 (0.0744) loss: 0.8705 (0.8717) time: 0.1403 data: 0.0567 max mem: 8299 +Train: [38] [5000/6250] eta: 0:02:50 lr: 0.000090 grad: 0.0790 (0.0745) loss: 0.8647 (0.8717) time: 0.1719 data: 0.0977 max mem: 8299 +Train: [38] [5100/6250] eta: 0:02:36 lr: 0.000090 grad: 0.0792 (0.0747) loss: 0.8710 (0.8716) time: 0.1347 data: 0.0598 max mem: 8299 +Train: [38] [5200/6250] eta: 0:02:23 lr: 0.000090 grad: 0.0748 (0.0747) loss: 0.8684 (0.8716) time: 0.1570 data: 0.0893 max mem: 8299 +Train: [38] [5300/6250] eta: 0:02:09 lr: 0.000090 grad: 0.0772 (0.0748) loss: 0.8707 (0.8715) time: 0.1591 data: 0.0822 max mem: 8299 +Train: [38] [5400/6250] eta: 0:01:56 lr: 0.000090 grad: 0.0840 (0.0749) loss: 0.8672 (0.8714) time: 0.1359 data: 0.0663 max mem: 8299 +Train: [38] [5500/6250] eta: 0:01:42 lr: 0.000090 grad: 0.0793 (0.0751) loss: 0.8640 (0.8713) time: 0.1507 data: 0.0706 max mem: 8299 +Train: [38] [5600/6250] eta: 0:01:29 lr: 0.000090 grad: 0.0737 (0.0752) loss: 0.8646 (0.8712) time: 0.1429 data: 0.0557 max mem: 8299 +Train: [38] [5700/6250] eta: 0:01:15 lr: 0.000090 grad: 0.0727 (0.0753) loss: 0.8716 (0.8711) time: 0.1339 data: 0.0638 max mem: 8299 +Train: [38] [5800/6250] eta: 0:01:01 lr: 0.000090 grad: 0.0836 (0.0754) loss: 0.8616 (0.8709) time: 0.1167 data: 0.0352 max mem: 8299 +Train: [38] [5900/6250] eta: 0:00:47 lr: 0.000090 grad: 0.0813 (0.0755) loss: 0.8658 (0.8709) time: 0.1343 data: 0.0506 max mem: 8299 +Train: [38] [6000/6250] eta: 0:00:34 lr: 0.000090 grad: 0.0786 (0.0756) loss: 0.8664 (0.8708) time: 0.1394 data: 0.0510 max mem: 8299 +Train: [38] [6100/6250] eta: 0:00:20 lr: 0.000090 grad: 0.0836 (0.0757) loss: 0.8715 (0.8708) time: 0.1198 data: 0.0357 max mem: 8299 +Train: [38] [6200/6250] eta: 0:00:06 lr: 0.000089 grad: 0.0835 (0.0759) loss: 0.8644 (0.8706) time: 0.1334 data: 0.0542 max mem: 8299 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0843 (0.0760) loss: 0.8642 (0.8706) time: 0.1498 data: 0.0733 max mem: 8299 +Train: [38] Total time: 0:14:12 (0.1364 s / it) +Averaged stats: lr: 0.000089 grad: 0.0843 (0.0760) loss: 0.8642 (0.8706) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:04:36 loss: 0.9004 (0.9004) time: 4.4646 data: 4.4349 max mem: 8299 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8919 (0.8911) time: 0.1237 data: 0.0990 max mem: 8299 +Eval (hcp-train-subset): [38] Total time: 0:00:12 (0.1996 s / it) +Averaged stats (hcp-train-subset): loss: 0.8919 (0.8911) +Eval (hcp-val): [38] [ 0/62] eta: 0:05:18 loss: 0.8854 (0.8854) time: 5.1316 data: 5.1028 max mem: 8299 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8860 (0.8866) time: 0.1098 data: 0.0841 max mem: 8299 +Eval (hcp-val): [38] Total time: 0:00:12 (0.2003 s / it) +Averaged stats (hcp-val): loss: 0.8860 (0.8866) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 8:00:39 lr: 0.000089 grad: 0.0504 (0.0504) loss: 0.9052 (0.9052) time: 4.6144 data: 4.4661 max mem: 8299 +Train: [39] [ 100/6250] eta: 0:18:36 lr: 0.000089 grad: 0.0633 (0.0921) loss: 0.8805 (0.8786) time: 0.1384 data: 0.0531 max mem: 8299 +Train: [39] [ 200/6250] eta: 0:15:46 lr: 0.000089 grad: 0.0763 (0.0837) loss: 0.8728 (0.8743) time: 0.1381 data: 0.0554 max mem: 8299 +Train: [39] [ 300/6250] eta: 0:15:08 lr: 0.000089 grad: 0.0693 (0.0803) loss: 0.8590 (0.8730) time: 0.1419 data: 0.0582 max mem: 8299 +Train: [39] [ 400/6250] eta: 0:14:20 lr: 0.000089 grad: 0.0672 (0.0780) loss: 0.8738 (0.8719) time: 0.1285 data: 0.0473 max mem: 8299 +Train: [39] [ 500/6250] eta: 0:13:51 lr: 0.000089 grad: 0.0725 (0.0769) loss: 0.8663 (0.8715) time: 0.1373 data: 0.0459 max mem: 8299 +Train: [39] [ 600/6250] eta: 0:13:21 lr: 0.000089 grad: 0.0703 (0.0771) loss: 0.8694 (0.8710) time: 0.1458 data: 0.0609 max mem: 8299 +Train: [39] [ 700/6250] eta: 0:12:52 lr: 0.000089 grad: 0.0736 (0.0768) loss: 0.8658 (0.8706) time: 0.1180 data: 0.0440 max mem: 8299 +Train: [39] [ 800/6250] eta: 0:12:29 lr: 0.000089 grad: 0.0683 (0.0768) loss: 0.8692 (0.8705) time: 0.1286 data: 0.0520 max mem: 8299 +Train: [39] [ 900/6250] eta: 0:12:08 lr: 0.000089 grad: 0.0703 (0.0763) loss: 0.8704 (0.8705) time: 0.1497 data: 0.0684 max mem: 8299 +Train: [39] [1000/6250] eta: 0:11:49 lr: 0.000089 grad: 0.0716 (0.0759) loss: 0.8652 (0.8705) time: 0.1225 data: 0.0434 max mem: 8299 +Train: [39] [1100/6250] eta: 0:11:33 lr: 0.000089 grad: 0.0703 (0.0759) loss: 0.8702 (0.8705) time: 0.1236 data: 0.0496 max mem: 8299 +Train: [39] [1200/6250] eta: 0:11:18 lr: 0.000089 grad: 0.0739 (0.0758) loss: 0.8667 (0.8703) time: 0.1152 data: 0.0324 max mem: 8299 +Train: [39] [1300/6250] eta: 0:11:08 lr: 0.000089 grad: 0.0712 (0.0758) loss: 0.8654 (0.8700) time: 0.1462 data: 0.0694 max mem: 8299 +Train: [39] [1400/6250] eta: 0:10:50 lr: 0.000089 grad: 0.0777 (0.0759) loss: 0.8641 (0.8698) time: 0.1252 data: 0.0456 max mem: 8299 +Train: [39] [1500/6250] eta: 0:10:35 lr: 0.000089 grad: 0.0747 (0.0761) loss: 0.8659 (0.8695) time: 0.1375 data: 0.0602 max mem: 8299 +Train: [39] [1600/6250] eta: 0:10:23 lr: 0.000089 grad: 0.0800 (0.0764) loss: 0.8608 (0.8692) time: 0.1489 data: 0.0723 max mem: 8299 +Train: [39] [1700/6250] eta: 0:10:09 lr: 0.000089 grad: 0.0746 (0.0766) loss: 0.8722 (0.8689) time: 0.1377 data: 0.0545 max mem: 8299 +Train: [39] [1800/6250] eta: 0:09:55 lr: 0.000089 grad: 0.0786 (0.0770) loss: 0.8713 (0.8686) time: 0.1286 data: 0.0505 max mem: 8299 +Train: [39] [1900/6250] eta: 0:09:41 lr: 0.000089 grad: 0.0757 (0.0773) loss: 0.8659 (0.8683) time: 0.1394 data: 0.0580 max mem: 8299 +Train: [39] [2000/6250] eta: 0:09:28 lr: 0.000089 grad: 0.0852 (0.0774) loss: 0.8719 (0.8682) time: 0.1326 data: 0.0514 max mem: 8299 +Train: [39] [2100/6250] eta: 0:09:14 lr: 0.000089 grad: 0.0731 (0.0775) loss: 0.8745 (0.8681) time: 0.1385 data: 0.0591 max mem: 8299 +Train: [39] [2200/6250] eta: 0:09:01 lr: 0.000089 grad: 0.0757 (0.0776) loss: 0.8715 (0.8681) time: 0.1212 data: 0.0353 max mem: 8299 +Train: [39] [2300/6250] eta: 0:08:49 lr: 0.000089 grad: 0.0820 (0.0778) loss: 0.8647 (0.8680) time: 0.1390 data: 0.0652 max mem: 8299 +Train: [39] [2400/6250] eta: 0:08:35 lr: 0.000089 grad: 0.0714 (0.0779) loss: 0.8683 (0.8680) time: 0.1357 data: 0.0532 max mem: 8299 +Train: [39] [2500/6250] eta: 0:08:21 lr: 0.000089 grad: 0.0830 (0.0780) loss: 0.8681 (0.8679) time: 0.1291 data: 0.0498 max mem: 8299 +Train: [39] [2600/6250] eta: 0:08:07 lr: 0.000089 grad: 0.0777 (0.0781) loss: 0.8623 (0.8679) time: 0.1093 data: 0.0301 max mem: 8299 +Train: [39] [2700/6250] eta: 0:07:54 lr: 0.000089 grad: 0.0824 (0.0783) loss: 0.8629 (0.8678) time: 0.1413 data: 0.0650 max mem: 8299 +Train: [39] [2800/6250] eta: 0:07:40 lr: 0.000089 grad: 0.0779 (0.0783) loss: 0.8714 (0.8679) time: 0.1232 data: 0.0408 max mem: 8299 +Train: [39] [2900/6250] eta: 0:07:27 lr: 0.000089 grad: 0.0781 (0.0784) loss: 0.8699 (0.8678) time: 0.1440 data: 0.0754 max mem: 8299 +Train: [39] [3000/6250] eta: 0:07:13 lr: 0.000089 grad: 0.0749 (0.0785) loss: 0.8625 (0.8678) time: 0.1285 data: 0.0547 max mem: 8299 +Train: [39] [3100/6250] eta: 0:06:59 lr: 0.000089 grad: 0.0751 (0.0786) loss: 0.8679 (0.8678) time: 0.1567 data: 0.0881 max mem: 8299 +Train: [39] [3200/6250] eta: 0:06:45 lr: 0.000089 grad: 0.0745 (0.0786) loss: 0.8675 (0.8678) time: 0.1292 data: 0.0587 max mem: 8299 +Train: [39] [3300/6250] eta: 0:06:32 lr: 0.000088 grad: 0.0805 (0.0787) loss: 0.8690 (0.8678) time: 0.1504 data: 0.0755 max mem: 8299 +Train: [39] [3400/6250] eta: 0:06:19 lr: 0.000088 grad: 0.0795 (0.0787) loss: 0.8699 (0.8679) time: 0.1551 data: 0.0806 max mem: 8299 +Train: [39] [3500/6250] eta: 0:06:06 lr: 0.000088 grad: 0.0776 (0.0787) loss: 0.8662 (0.8679) time: 0.1524 data: 0.0750 max mem: 8299 +Train: [39] [3600/6250] eta: 0:05:52 lr: 0.000088 grad: 0.0711 (0.0787) loss: 0.8767 (0.8679) time: 0.1317 data: 0.0565 max mem: 8299 +Train: [39] [3700/6250] eta: 0:05:39 lr: 0.000088 grad: 0.0748 (0.0789) loss: 0.8687 (0.8679) time: 0.1424 data: 0.0655 max mem: 8299 +Train: [39] [3800/6250] eta: 0:05:25 lr: 0.000088 grad: 0.0738 (0.0788) loss: 0.8735 (0.8679) time: 0.1176 data: 0.0480 max mem: 8299 +Train: [39] [3900/6250] eta: 0:05:13 lr: 0.000088 grad: 0.0766 (0.0788) loss: 0.8638 (0.8680) time: 0.1832 data: 0.1091 max mem: 8299 +Train: [39] [4000/6250] eta: 0:04:59 lr: 0.000088 grad: 0.0796 (0.0788) loss: 0.8717 (0.8680) time: 0.1156 data: 0.0428 max mem: 8299 +Train: [39] [4100/6250] eta: 0:04:46 lr: 0.000088 grad: 0.0735 (0.0788) loss: 0.8724 (0.8680) time: 0.1330 data: 0.0486 max mem: 8299 +Train: [39] [4200/6250] eta: 0:04:32 lr: 0.000088 grad: 0.0838 (0.0788) loss: 0.8661 (0.8680) time: 0.1252 data: 0.0489 max mem: 8299 +Train: [39] [4300/6250] eta: 0:04:19 lr: 0.000088 grad: 0.0722 (0.0788) loss: 0.8694 (0.8680) time: 0.1359 data: 0.0625 max mem: 8299 +Train: [39] [4400/6250] eta: 0:04:05 lr: 0.000088 grad: 0.0776 (0.0788) loss: 0.8724 (0.8680) time: 0.1246 data: 0.0454 max mem: 8299 +Train: [39] [4500/6250] eta: 0:03:52 lr: 0.000088 grad: 0.0743 (0.0788) loss: 0.8661 (0.8680) time: 0.1265 data: 0.0545 max mem: 8299 +Train: [39] [4600/6250] eta: 0:03:39 lr: 0.000088 grad: 0.0828 (0.0788) loss: 0.8659 (0.8680) time: 0.1329 data: 0.0594 max mem: 8299 +Train: [39] [4700/6250] eta: 0:03:25 lr: 0.000088 grad: 0.0849 (0.0789) loss: 0.8621 (0.8679) time: 0.1313 data: 0.0611 max mem: 8299 +Train: [39] [4800/6250] eta: 0:03:12 lr: 0.000088 grad: 0.0765 (0.0789) loss: 0.8658 (0.8679) time: 0.1322 data: 0.0470 max mem: 8299 +Train: [39] [4900/6250] eta: 0:02:59 lr: 0.000088 grad: 0.0807 (0.0789) loss: 0.8712 (0.8679) time: 0.1561 data: 0.0819 max mem: 8299 +Train: [39] [5000/6250] eta: 0:02:46 lr: 0.000088 grad: 0.0759 (0.0789) loss: 0.8667 (0.8679) time: 0.1136 data: 0.0406 max mem: 8299 +Train: [39] [5100/6250] eta: 0:02:33 lr: 0.000088 grad: 0.0783 (0.0790) loss: 0.8710 (0.8680) time: 0.1764 data: 0.0942 max mem: 8299 +Train: [39] [5200/6250] eta: 0:02:19 lr: 0.000088 grad: 0.0814 (0.0790) loss: 0.8670 (0.8679) time: 0.1313 data: 0.0636 max mem: 8299 +Train: [39] [5300/6250] eta: 0:02:06 lr: 0.000088 grad: 0.0805 (0.0790) loss: 0.8667 (0.8679) time: 0.1459 data: 0.0718 max mem: 8299 +Train: [39] [5400/6250] eta: 0:01:53 lr: 0.000088 grad: 0.0770 (0.0790) loss: 0.8678 (0.8679) time: 0.1533 data: 0.0770 max mem: 8299 +Train: [39] [5500/6250] eta: 0:01:40 lr: 0.000088 grad: 0.0765 (0.0790) loss: 0.8654 (0.8679) time: 0.1265 data: 0.0509 max mem: 8299 +Train: [39] [5600/6250] eta: 0:01:26 lr: 0.000088 grad: 0.0753 (0.0789) loss: 0.8697 (0.8679) time: 0.1540 data: 0.0751 max mem: 8299 +Train: [39] [5700/6250] eta: 0:01:13 lr: 0.000088 grad: 0.0743 (0.0789) loss: 0.8701 (0.8679) time: 0.1319 data: 0.0511 max mem: 8299 +Train: [39] [5800/6250] eta: 0:01:00 lr: 0.000088 grad: 0.0757 (0.0789) loss: 0.8604 (0.8679) time: 0.1216 data: 0.0395 max mem: 8299 +Train: [39] [5900/6250] eta: 0:00:46 lr: 0.000088 grad: 0.0804 (0.0790) loss: 0.8628 (0.8679) time: 0.1272 data: 0.0471 max mem: 8299 +Train: [39] [6000/6250] eta: 0:00:33 lr: 0.000088 grad: 0.0738 (0.0791) loss: 0.8633 (0.8679) time: 0.1202 data: 0.0422 max mem: 8299 +Train: [39] [6100/6250] eta: 0:00:19 lr: 0.000088 grad: 0.0834 (0.0792) loss: 0.8707 (0.8678) time: 0.1247 data: 0.0444 max mem: 8299 +Train: [39] [6200/6250] eta: 0:00:06 lr: 0.000088 grad: 0.0813 (0.0792) loss: 0.8626 (0.8678) time: 0.1210 data: 0.0507 max mem: 8299 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0729 (0.0792) loss: 0.8659 (0.8678) time: 0.1229 data: 0.0459 max mem: 8299 +Train: [39] Total time: 0:13:54 (0.1335 s / it) +Averaged stats: lr: 0.000088 grad: 0.0729 (0.0792) loss: 0.8659 (0.8678) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:03:36 loss: 0.9046 (0.9046) time: 3.4899 data: 3.4372 max mem: 8299 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8884 (0.8892) time: 0.1297 data: 0.1051 max mem: 8299 +Eval (hcp-train-subset): [39] Total time: 0:00:12 (0.1998 s / it) +Averaged stats (hcp-train-subset): loss: 0.8884 (0.8892) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [39] [ 0/62] eta: 0:04:56 loss: 0.8872 (0.8872) time: 4.7839 data: 4.7539 max mem: 8299 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8831 (0.8864) time: 0.1291 data: 0.1048 max mem: 8299 +Eval (hcp-val): [39] Total time: 0:00:12 (0.2030 s / it) +Averaged stats (hcp-val): loss: 0.8831 (0.8864) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-00039.pth +Train: [40] [ 0/6250] eta: 6:56:06 lr: 0.000088 grad: 0.0583 (0.0583) loss: 0.8999 (0.8999) time: 3.9946 data: 3.6618 max mem: 8299 +Train: [40] [ 100/6250] eta: 0:18:27 lr: 0.000088 grad: 0.0847 (0.0962) loss: 0.8734 (0.8786) time: 0.1502 data: 0.0590 max mem: 8299 +Train: [40] [ 200/6250] eta: 0:16:14 lr: 0.000088 grad: 0.0755 (0.0903) loss: 0.8723 (0.8744) time: 0.1408 data: 0.0474 max mem: 8299 +Train: [40] [ 300/6250] eta: 0:14:44 lr: 0.000088 grad: 0.0816 (0.0872) loss: 0.8604 (0.8711) time: 0.1100 data: 0.0299 max mem: 8299 +Train: [40] [ 400/6250] eta: 0:14:07 lr: 0.000087 grad: 0.0659 (0.0841) loss: 0.8742 (0.8708) time: 0.1290 data: 0.0514 max mem: 8299 +Train: [40] [ 500/6250] eta: 0:13:27 lr: 0.000087 grad: 0.0720 (0.0828) loss: 0.8667 (0.8701) time: 0.1246 data: 0.0365 max mem: 8299 +Train: [40] [ 600/6250] eta: 0:12:55 lr: 0.000087 grad: 0.0821 (0.0820) loss: 0.8638 (0.8695) time: 0.1288 data: 0.0373 max mem: 8299 +Train: [40] [ 700/6250] eta: 0:12:31 lr: 0.000087 grad: 0.0679 (0.0817) loss: 0.8613 (0.8685) time: 0.1226 data: 0.0374 max mem: 8299 +Train: [40] [ 800/6250] eta: 0:12:13 lr: 0.000087 grad: 0.0763 (0.0815) loss: 0.8668 (0.8677) time: 0.1190 data: 0.0348 max mem: 8299 +Train: [40] [ 900/6250] eta: 0:11:56 lr: 0.000087 grad: 0.0762 (0.0814) loss: 0.8608 (0.8669) time: 0.1271 data: 0.0577 max mem: 8299 +Train: [40] [1000/6250] eta: 0:11:42 lr: 0.000087 grad: 0.0799 (0.0812) loss: 0.8663 (0.8666) time: 0.1350 data: 0.0578 max mem: 8299 +Train: [40] [1100/6250] eta: 0:11:26 lr: 0.000087 grad: 0.0762 (0.0810) loss: 0.8605 (0.8661) time: 0.1373 data: 0.0569 max mem: 8299 +Train: [40] [1200/6250] eta: 0:11:15 lr: 0.000087 grad: 0.0814 (0.0810) loss: 0.8664 (0.8659) time: 0.1565 data: 0.0793 max mem: 8299 +Train: [40] [1300/6250] eta: 0:11:00 lr: 0.000087 grad: 0.0762 (0.0809) loss: 0.8553 (0.8655) time: 0.1625 data: 0.0858 max mem: 8299 +Train: [40] [1400/6250] eta: 0:10:42 lr: 0.000087 grad: 0.0762 (0.0807) loss: 0.8572 (0.8652) time: 0.1145 data: 0.0469 max mem: 8299 +Train: [40] [1500/6250] eta: 0:10:29 lr: 0.000087 grad: 0.0784 (0.0808) loss: 0.8638 (0.8649) time: 0.1247 data: 0.0439 max mem: 8299 +Train: [40] [1600/6250] eta: 0:10:15 lr: 0.000087 grad: 0.0755 (0.0809) loss: 0.8660 (0.8646) time: 0.1413 data: 0.0596 max mem: 8299 +Train: [40] [1700/6250] eta: 0:09:59 lr: 0.000087 grad: 0.0736 (0.0808) loss: 0.8621 (0.8645) time: 0.1181 data: 0.0380 max mem: 8299 +Train: [40] [1800/6250] eta: 0:09:46 lr: 0.000087 grad: 0.0754 (0.0809) loss: 0.8605 (0.8643) time: 0.1484 data: 0.0688 max mem: 8299 +Train: [40] [1900/6250] eta: 0:09:33 lr: 0.000087 grad: 0.0784 (0.0807) loss: 0.8644 (0.8643) time: 0.1681 data: 0.0888 max mem: 8299 +Train: [40] [2000/6250] eta: 0:09:17 lr: 0.000087 grad: 0.0710 (0.0806) loss: 0.8670 (0.8643) time: 0.0961 data: 0.0209 max mem: 8299 +Train: [40] [2100/6250] eta: 0:09:04 lr: 0.000087 grad: 0.0768 (0.0805) loss: 0.8666 (0.8643) time: 0.1291 data: 0.0508 max mem: 8299 +Train: [40] [2200/6250] eta: 0:08:52 lr: 0.000087 grad: 0.0772 (0.0804) loss: 0.8653 (0.8643) time: 0.1465 data: 0.0756 max mem: 8299 +Train: [40] [2300/6250] eta: 0:08:38 lr: 0.000087 grad: 0.0778 (0.0804) loss: 0.8623 (0.8643) time: 0.1579 data: 0.0851 max mem: 8299 +Train: [40] [2400/6250] eta: 0:08:24 lr: 0.000087 grad: 0.0759 (0.0803) loss: 0.8679 (0.8644) time: 0.1124 data: 0.0315 max mem: 8299 +Train: [40] [2500/6250] eta: 0:08:12 lr: 0.000087 grad: 0.0783 (0.0802) loss: 0.8688 (0.8644) time: 0.1150 data: 0.0314 max mem: 8299 +Train: [40] [2600/6250] eta: 0:07:58 lr: 0.000087 grad: 0.0795 (0.0802) loss: 0.8643 (0.8644) time: 0.1152 data: 0.0434 max mem: 8299 +Train: [40] [2700/6250] eta: 0:07:45 lr: 0.000087 grad: 0.0795 (0.0802) loss: 0.8677 (0.8644) time: 0.1214 data: 0.0539 max mem: 8299 +Train: [40] [2800/6250] eta: 0:07:32 lr: 0.000087 grad: 0.0740 (0.0802) loss: 0.8713 (0.8645) time: 0.1314 data: 0.0570 max mem: 8299 +Train: [40] [2900/6250] eta: 0:07:19 lr: 0.000087 grad: 0.0792 (0.0802) loss: 0.8661 (0.8646) time: 0.1206 data: 0.0466 max mem: 8299 +Train: [40] [3000/6250] eta: 0:07:06 lr: 0.000087 grad: 0.0708 (0.0800) loss: 0.8679 (0.8647) time: 0.1325 data: 0.0538 max mem: 8299 +Train: [40] [3100/6250] eta: 0:06:54 lr: 0.000087 grad: 0.0806 (0.0801) loss: 0.8663 (0.8647) time: 0.1491 data: 0.0751 max mem: 8299 +Train: [40] [3200/6250] eta: 0:06:42 lr: 0.000087 grad: 0.0726 (0.0800) loss: 0.8667 (0.8649) time: 0.1404 data: 0.0670 max mem: 8299 +Train: [40] [3300/6250] eta: 0:06:29 lr: 0.000087 grad: 0.0702 (0.0800) loss: 0.8642 (0.8649) time: 0.1186 data: 0.0515 max mem: 8299 +Train: [40] [3400/6250] eta: 0:06:16 lr: 0.000087 grad: 0.0832 (0.0801) loss: 0.8696 (0.8650) time: 0.1531 data: 0.0729 max mem: 8299 +Train: [40] [3500/6250] eta: 0:06:04 lr: 0.000087 grad: 0.0724 (0.0801) loss: 0.8700 (0.8650) time: 0.1359 data: 0.0546 max mem: 8299 +Train: [40] [3600/6250] eta: 0:05:50 lr: 0.000087 grad: 0.0795 (0.0802) loss: 0.8637 (0.8651) time: 0.1325 data: 0.0565 max mem: 8299 +Train: [40] [3700/6250] eta: 0:05:37 lr: 0.000086 grad: 0.0764 (0.0802) loss: 0.8682 (0.8652) time: 0.1469 data: 0.0695 max mem: 8299 +Train: [40] [3800/6250] eta: 0:05:22 lr: 0.000086 grad: 0.0760 (0.0801) loss: 0.8742 (0.8653) time: 0.1344 data: 0.0569 max mem: 8299 +Train: [40] [3900/6250] eta: 0:05:08 lr: 0.000086 grad: 0.0791 (0.0802) loss: 0.8636 (0.8653) time: 0.1118 data: 0.0354 max mem: 8299 +Train: [40] [4000/6250] eta: 0:04:55 lr: 0.000086 grad: 0.0787 (0.0802) loss: 0.8633 (0.8653) time: 0.1387 data: 0.0603 max mem: 8299 +Train: [40] [4100/6250] eta: 0:04:41 lr: 0.000086 grad: 0.0847 (0.0803) loss: 0.8602 (0.8652) time: 0.1194 data: 0.0414 max mem: 8299 +Train: [40] [4200/6250] eta: 0:04:28 lr: 0.000086 grad: 0.0790 (0.0804) loss: 0.8633 (0.8652) time: 0.1353 data: 0.0568 max mem: 8299 +Train: [40] [4300/6250] eta: 0:04:15 lr: 0.000086 grad: 0.0836 (0.0805) loss: 0.8604 (0.8651) time: 0.1368 data: 0.0623 max mem: 8299 +Train: [40] [4400/6250] eta: 0:04:02 lr: 0.000086 grad: 0.0851 (0.0806) loss: 0.8529 (0.8650) time: 0.1249 data: 0.0500 max mem: 8299 +Train: [40] [4500/6250] eta: 0:03:49 lr: 0.000086 grad: 0.0829 (0.0806) loss: 0.8658 (0.8649) time: 0.1169 data: 0.0427 max mem: 8299 +Train: [40] [4600/6250] eta: 0:03:35 lr: 0.000086 grad: 0.0806 (0.0806) loss: 0.8594 (0.8648) time: 0.1221 data: 0.0505 max mem: 8299 +Train: [40] [4700/6250] eta: 0:03:22 lr: 0.000086 grad: 0.0840 (0.0807) loss: 0.8595 (0.8648) time: 0.1258 data: 0.0518 max mem: 8299 +Train: [40] [4800/6250] eta: 0:03:09 lr: 0.000086 grad: 0.0771 (0.0807) loss: 0.8664 (0.8648) time: 0.1259 data: 0.0514 max mem: 8299 +Train: [40] [4900/6250] eta: 0:02:56 lr: 0.000086 grad: 0.0758 (0.0806) loss: 0.8636 (0.8648) time: 0.1619 data: 0.0894 max mem: 8299 +Train: [40] [5000/6250] eta: 0:02:43 lr: 0.000086 grad: 0.0749 (0.0806) loss: 0.8664 (0.8648) time: 0.1175 data: 0.0484 max mem: 8299 +Train: [40] [5100/6250] eta: 0:02:30 lr: 0.000086 grad: 0.0780 (0.0807) loss: 0.8632 (0.8647) time: 0.1239 data: 0.0493 max mem: 8299 +Train: [40] [5200/6250] eta: 0:02:17 lr: 0.000086 grad: 0.0778 (0.0807) loss: 0.8672 (0.8647) time: 0.1474 data: 0.0783 max mem: 8299 +Train: [40] [5300/6250] eta: 0:02:04 lr: 0.000086 grad: 0.0758 (0.0807) loss: 0.8693 (0.8647) time: 0.1446 data: 0.0559 max mem: 8299 +Train: [40] [5400/6250] eta: 0:01:51 lr: 0.000086 grad: 0.0802 (0.0808) loss: 0.8662 (0.8647) time: 0.1512 data: 0.0731 max mem: 8299 +Train: [40] [5500/6250] eta: 0:01:38 lr: 0.000086 grad: 0.0771 (0.0808) loss: 0.8654 (0.8647) time: 0.1321 data: 0.0618 max mem: 8299 +Train: [40] [5600/6250] eta: 0:01:25 lr: 0.000086 grad: 0.0836 (0.0808) loss: 0.8659 (0.8647) time: 0.1286 data: 0.0569 max mem: 8299 +Train: [40] [5700/6250] eta: 0:01:12 lr: 0.000086 grad: 0.0735 (0.0808) loss: 0.8709 (0.8647) time: 0.1184 data: 0.0360 max mem: 8299 +Train: [40] [5800/6250] eta: 0:00:59 lr: 0.000086 grad: 0.0815 (0.0808) loss: 0.8671 (0.8647) time: 0.1075 data: 0.0346 max mem: 8299 +Train: [40] [5900/6250] eta: 0:00:45 lr: 0.000086 grad: 0.0762 (0.0808) loss: 0.8587 (0.8647) time: 0.1277 data: 0.0482 max mem: 8299 +Train: [40] [6000/6250] eta: 0:00:32 lr: 0.000086 grad: 0.0759 (0.0808) loss: 0.8624 (0.8648) time: 0.1393 data: 0.0621 max mem: 8299 +Train: [40] [6100/6250] eta: 0:00:19 lr: 0.000086 grad: 0.0774 (0.0809) loss: 0.8669 (0.8648) time: 0.1297 data: 0.0585 max mem: 8299 +Train: [40] [6200/6250] eta: 0:00:06 lr: 0.000086 grad: 0.0687 (0.0809) loss: 0.8715 (0.8648) time: 0.1374 data: 0.0530 max mem: 8299 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0759 (0.0809) loss: 0.8616 (0.8648) time: 0.1295 data: 0.0467 max mem: 8299 +Train: [40] Total time: 0:13:45 (0.1320 s / it) +Averaged stats: lr: 0.000086 grad: 0.0759 (0.0809) loss: 0.8616 (0.8648) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:03:18 loss: 0.8991 (0.8991) time: 3.2031 data: 3.1481 max mem: 8299 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8906 (0.8888) time: 0.1196 data: 0.0951 max mem: 8299 +Eval (hcp-train-subset): [40] Total time: 0:00:12 (0.2007 s / it) +Averaged stats (hcp-train-subset): loss: 0.8906 (0.8888) +Eval (hcp-val): [40] [ 0/62] eta: 0:05:20 loss: 0.8810 (0.8810) time: 5.1635 data: 5.1163 max mem: 8299 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8831 (0.8844) time: 0.1053 data: 0.0798 max mem: 8299 +Eval (hcp-val): [40] Total time: 0:00:12 (0.2013 s / it) +Averaged stats (hcp-val): loss: 0.8831 (0.8844) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 7:52:27 lr: 0.000086 grad: nan (nan) loss: 0.8879 (0.8879) time: 4.5355 data: 4.2808 max mem: 8299 +Train: [41] [ 100/6250] eta: 0:18:18 lr: 0.000086 grad: 0.0697 (0.0793) loss: 0.8821 (0.8833) time: 0.1343 data: 0.0410 max mem: 8299 +Train: [41] [ 200/6250] eta: 0:15:40 lr: 0.000086 grad: 0.0697 (0.0770) loss: 0.8706 (0.8780) time: 0.1187 data: 0.0357 max mem: 8299 +Train: [41] [ 300/6250] eta: 0:14:36 lr: 0.000086 grad: 0.0765 (0.0787) loss: 0.8690 (0.8766) time: 0.1422 data: 0.0578 max mem: 8299 +Train: [41] [ 400/6250] eta: 0:13:42 lr: 0.000086 grad: 0.0736 (0.0789) loss: 0.8788 (0.8758) time: 0.1110 data: 0.0339 max mem: 8299 +Train: [41] [ 500/6250] eta: 0:13:08 lr: 0.000086 grad: 0.0748 (0.0778) loss: 0.8691 (0.8754) time: 0.1234 data: 0.0381 max mem: 8299 +Train: [41] [ 600/6250] eta: 0:12:44 lr: 0.000086 grad: 0.0720 (0.0772) loss: 0.8747 (0.8748) time: 0.1331 data: 0.0507 max mem: 8299 +Train: [41] [ 700/6250] eta: 0:12:27 lr: 0.000085 grad: 0.0709 (0.0773) loss: 0.8667 (0.8737) time: 0.1613 data: 0.0817 max mem: 8299 +Train: [41] [ 800/6250] eta: 0:12:13 lr: 0.000085 grad: 0.0712 (0.0776) loss: 0.8614 (0.8728) time: 0.1528 data: 0.0740 max mem: 8299 +Train: [41] [ 900/6250] eta: 0:11:57 lr: 0.000085 grad: 0.0702 (0.0774) loss: 0.8695 (0.8721) time: 0.1304 data: 0.0399 max mem: 8299 +Train: [41] [1000/6250] eta: 0:11:40 lr: 0.000085 grad: 0.0769 (0.0775) loss: 0.8631 (0.8714) time: 0.1244 data: 0.0433 max mem: 8299 +Train: [41] [1100/6250] eta: 0:11:29 lr: 0.000085 grad: 0.0721 (0.0772) loss: 0.8643 (0.8710) time: 0.1355 data: 0.0533 max mem: 8299 +Train: [41] [1200/6250] eta: 0:11:14 lr: 0.000085 grad: 0.0732 (0.0771) loss: 0.8621 (0.8706) time: 0.1188 data: 0.0489 max mem: 8299 +Train: [41] [1300/6250] eta: 0:11:00 lr: 0.000085 grad: 0.0738 (0.0771) loss: 0.8664 (0.8701) time: 0.1246 data: 0.0415 max mem: 8299 +Train: [41] [1400/6250] eta: 0:10:47 lr: 0.000085 grad: 0.0689 (0.0773) loss: 0.8664 (0.8697) time: 0.1264 data: 0.0549 max mem: 8299 +Train: [41] [1500/6250] eta: 0:10:32 lr: 0.000085 grad: 0.0709 (0.0773) loss: 0.8659 (0.8694) time: 0.1306 data: 0.0570 max mem: 8299 +Train: [41] [1600/6250] eta: 0:10:18 lr: 0.000085 grad: 0.0791 (0.0774) loss: 0.8675 (0.8693) time: 0.1336 data: 0.0624 max mem: 8299 +Train: [41] [1700/6250] eta: 0:10:06 lr: 0.000085 grad: 0.0795 (0.0773) loss: 0.8648 (0.8692) time: 0.1509 data: 0.0819 max mem: 8299 +Train: [41] [1800/6250] eta: 0:09:51 lr: 0.000085 grad: 0.0698 (0.0775) loss: 0.8731 (0.8691) time: 0.1127 data: 0.0309 max mem: 8299 +Train: [41] [1900/6250] eta: 0:09:37 lr: 0.000085 grad: 0.0830 (0.0775) loss: 0.8597 (0.8689) time: 0.1378 data: 0.0617 max mem: 8299 +Train: [41] [2000/6250] eta: 0:09:24 lr: 0.000085 grad: 0.0699 (0.0775) loss: 0.8708 (0.8689) time: 0.0940 data: 0.0093 max mem: 8299 +Train: [41] [2100/6250] eta: 0:09:10 lr: 0.000085 grad: 0.0790 (0.0775) loss: 0.8725 (0.8689) time: 0.1263 data: 0.0535 max mem: 8299 +Train: [41] [2200/6250] eta: 0:08:56 lr: 0.000085 grad: 0.0783 (0.0776) loss: 0.8672 (0.8689) time: 0.1295 data: 0.0500 max mem: 8299 +Train: [41] [2300/6250] eta: 0:08:44 lr: 0.000085 grad: 0.0794 (0.0776) loss: 0.8729 (0.8690) time: 0.1077 data: 0.0302 max mem: 8299 +Train: [41] [2400/6250] eta: 0:08:30 lr: 0.000085 grad: 0.0805 (0.0781) loss: 0.8719 (0.8690) time: 0.1325 data: 0.0648 max mem: 8299 +Train: [41] [2500/6250] eta: 0:08:16 lr: 0.000085 grad: 0.0790 (0.0782) loss: 0.8687 (0.8690) time: 0.1350 data: 0.0557 max mem: 8299 +Train: [41] [2600/6250] eta: 0:08:03 lr: 0.000085 grad: 0.0829 (0.0783) loss: 0.8650 (0.8690) time: 0.1250 data: 0.0516 max mem: 8299 +Train: [41] [2700/6250] eta: 0:07:51 lr: 0.000085 grad: 0.0727 (0.0785) loss: 0.8674 (0.8690) time: 0.1263 data: 0.0535 max mem: 8299 +Train: [41] [2800/6250] eta: 0:07:38 lr: 0.000085 grad: 0.0757 (0.0788) loss: 0.8633 (0.8689) time: 0.1089 data: 0.0301 max mem: 8299 +Train: [41] [2900/6250] eta: 0:07:26 lr: 0.000085 grad: 0.0853 (0.0790) loss: 0.8701 (0.8689) time: 0.1576 data: 0.0839 max mem: 8299 +Train: [41] [3000/6250] eta: 0:07:13 lr: 0.000085 grad: 0.0797 (0.0791) loss: 0.8697 (0.8688) time: 0.1416 data: 0.0659 max mem: 8299 +Train: [41] [3100/6250] eta: 0:07:01 lr: 0.000085 grad: 0.0836 (0.0792) loss: 0.8618 (0.8687) time: 0.1681 data: 0.0331 max mem: 8299 +Train: [41] [3200/6250] eta: 0:06:48 lr: 0.000085 grad: 0.0760 (0.0792) loss: 0.8651 (0.8688) time: 0.1456 data: 0.0733 max mem: 8299 +Train: [41] [3300/6250] eta: 0:06:35 lr: 0.000085 grad: 0.0826 (0.0794) loss: 0.8673 (0.8688) time: 0.1638 data: 0.0893 max mem: 8299 +Train: [41] [3400/6250] eta: 0:06:22 lr: 0.000085 grad: 0.0806 (0.0795) loss: 0.8663 (0.8688) time: 0.1823 data: 0.1006 max mem: 8299 +Train: [41] [3500/6250] eta: 0:06:08 lr: 0.000085 grad: 0.0770 (0.0796) loss: 0.8728 (0.8688) time: 0.1246 data: 0.0527 max mem: 8299 +Train: [41] [3600/6250] eta: 0:05:55 lr: 0.000085 grad: 0.0736 (0.0796) loss: 0.8791 (0.8688) time: 0.1282 data: 0.0501 max mem: 8299 +Train: [41] [3700/6250] eta: 0:05:42 lr: 0.000085 grad: 0.0817 (0.0797) loss: 0.8648 (0.8688) time: 0.1218 data: 0.0387 max mem: 8299 +Train: [41] [3800/6250] eta: 0:05:28 lr: 0.000085 grad: 0.0823 (0.0798) loss: 0.8629 (0.8688) time: 0.1482 data: 0.0700 max mem: 8299 +Train: [41] [3900/6250] eta: 0:05:15 lr: 0.000084 grad: 0.0776 (0.0799) loss: 0.8661 (0.8688) time: 0.1412 data: 0.0686 max mem: 8299 +Train: [41] [4000/6250] eta: 0:05:02 lr: 0.000084 grad: 0.0799 (0.0801) loss: 0.8700 (0.8687) time: 0.1241 data: 0.0457 max mem: 8299 +Train: [41] [4100/6250] eta: 0:04:48 lr: 0.000084 grad: 0.0802 (0.0801) loss: 0.8684 (0.8687) time: 0.1103 data: 0.0380 max mem: 8299 +Train: [41] [4200/6250] eta: 0:04:35 lr: 0.000084 grad: 0.0841 (0.0801) loss: 0.8686 (0.8687) time: 0.1438 data: 0.0670 max mem: 8299 +Train: [41] [4300/6250] eta: 0:04:22 lr: 0.000084 grad: 0.0835 (0.0802) loss: 0.8609 (0.8686) time: 0.0967 data: 0.0002 max mem: 8299 +Train: [41] [4400/6250] eta: 0:04:08 lr: 0.000084 grad: 0.0812 (0.0802) loss: 0.8708 (0.8685) time: 0.1323 data: 0.0527 max mem: 8299 +Train: [41] [4500/6250] eta: 0:03:55 lr: 0.000084 grad: 0.0779 (0.0803) loss: 0.8649 (0.8685) time: 0.1469 data: 0.0698 max mem: 8299 +Train: [41] [4600/6250] eta: 0:03:41 lr: 0.000084 grad: 0.0835 (0.0803) loss: 0.8628 (0.8685) time: 0.1144 data: 0.0278 max mem: 8299 +Train: [41] [4700/6250] eta: 0:03:28 lr: 0.000084 grad: 0.0839 (0.0804) loss: 0.8619 (0.8684) time: 0.1057 data: 0.0223 max mem: 8299 +Train: [41] [4800/6250] eta: 0:03:14 lr: 0.000084 grad: 0.0876 (0.0804) loss: 0.8654 (0.8684) time: 0.1465 data: 0.0671 max mem: 8299 +Train: [41] [4900/6250] eta: 0:03:01 lr: 0.000084 grad: 0.0788 (0.0804) loss: 0.8603 (0.8683) time: 0.1319 data: 0.0569 max mem: 8299 +Train: [41] [5000/6250] eta: 0:02:47 lr: 0.000084 grad: 0.0837 (0.0805) loss: 0.8596 (0.8681) time: 0.1389 data: 0.0626 max mem: 8299 +Train: [41] [5100/6250] eta: 0:02:34 lr: 0.000084 grad: 0.0761 (0.0805) loss: 0.8631 (0.8681) time: 0.0981 data: 0.0002 max mem: 8299 +Train: [41] [5200/6250] eta: 0:02:21 lr: 0.000084 grad: 0.0811 (0.0805) loss: 0.8649 (0.8680) time: 0.1494 data: 0.0727 max mem: 8299 +Train: [41] [5300/6250] eta: 0:02:08 lr: 0.000084 grad: 0.0779 (0.0805) loss: 0.8628 (0.8679) time: 0.1379 data: 0.0636 max mem: 8299 +Train: [41] [5400/6250] eta: 0:01:54 lr: 0.000084 grad: 0.0806 (0.0806) loss: 0.8660 (0.8678) time: 0.1433 data: 0.0705 max mem: 8299 +Train: [41] [5500/6250] eta: 0:01:41 lr: 0.000084 grad: 0.0825 (0.0806) loss: 0.8590 (0.8677) time: 0.1126 data: 0.0349 max mem: 8299 +Train: [41] [5600/6250] eta: 0:01:27 lr: 0.000084 grad: 0.0771 (0.0806) loss: 0.8696 (0.8677) time: 0.1330 data: 0.0570 max mem: 8299 +Train: [41] [5700/6250] eta: 0:01:14 lr: 0.000084 grad: 0.0820 (0.0807) loss: 0.8573 (0.8676) time: 0.1553 data: 0.0773 max mem: 8299 +Train: [41] [5800/6250] eta: 0:01:00 lr: 0.000084 grad: 0.0830 (0.0806) loss: 0.8633 (0.8676) time: 0.1295 data: 0.0546 max mem: 8299 +Train: [41] [5900/6250] eta: 0:00:47 lr: 0.000084 grad: 0.0854 (0.0807) loss: 0.8608 (0.8675) time: 0.1115 data: 0.0360 max mem: 8299 +Train: [41] [6000/6250] eta: 0:00:33 lr: 0.000084 grad: 0.0819 (0.0808) loss: 0.8633 (0.8674) time: 0.1239 data: 0.0373 max mem: 8299 +Train: [41] [6100/6250] eta: 0:00:20 lr: 0.000084 grad: 0.0775 (0.0808) loss: 0.8619 (0.8673) time: 0.1184 data: 0.0371 max mem: 8299 +Train: [41] [6200/6250] eta: 0:00:06 lr: 0.000084 grad: 0.0768 (0.0809) loss: 0.8691 (0.8673) time: 0.1285 data: 0.0503 max mem: 8299 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0766 (0.0809) loss: 0.8601 (0.8672) time: 0.1459 data: 0.0703 max mem: 8299 +Train: [41] Total time: 0:14:04 (0.1350 s / it) +Averaged stats: lr: 0.000084 grad: 0.0766 (0.0809) loss: 0.8601 (0.8672) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:05:01 loss: 0.8995 (0.8995) time: 4.8610 data: 4.8214 max mem: 8299 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8905 (0.8890) time: 0.1162 data: 0.0908 max mem: 8299 +Eval (hcp-train-subset): [41] Total time: 0:00:12 (0.2034 s / it) +Averaged stats (hcp-train-subset): loss: 0.8905 (0.8890) +Eval (hcp-val): [41] [ 0/62] eta: 0:04:04 loss: 0.8868 (0.8868) time: 3.9490 data: 3.9197 max mem: 8299 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8845 (0.8860) time: 0.1104 data: 0.0863 max mem: 8299 +Eval (hcp-val): [41] Total time: 0:00:11 (0.1901 s / it) +Averaged stats (hcp-val): loss: 0.8845 (0.8860) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 9:56:41 lr: 0.000084 grad: 0.0774 (0.0774) loss: 0.8587 (0.8587) time: 5.7282 data: 5.6194 max mem: 8299 +Train: [42] [ 100/6250] eta: 0:19:12 lr: 0.000084 grad: 0.0723 (0.0850) loss: 0.8800 (0.8830) time: 0.1298 data: 0.0377 max mem: 8299 +Train: [42] [ 200/6250] eta: 0:16:10 lr: 0.000084 grad: 0.0699 (0.0801) loss: 0.8842 (0.8798) time: 0.1392 data: 0.0545 max mem: 8299 +Train: [42] [ 300/6250] eta: 0:14:54 lr: 0.000084 grad: 0.0706 (0.0812) loss: 0.8665 (0.8770) time: 0.1260 data: 0.0403 max mem: 8299 +Train: [42] [ 400/6250] eta: 0:14:07 lr: 0.000084 grad: 0.0695 (0.0801) loss: 0.8694 (0.8744) time: 0.1269 data: 0.0410 max mem: 8299 +Train: [42] [ 500/6250] eta: 0:13:26 lr: 0.000084 grad: 0.0720 (0.0794) loss: 0.8720 (0.8732) time: 0.1229 data: 0.0338 max mem: 8299 +Train: [42] [ 600/6250] eta: 0:12:47 lr: 0.000084 grad: 0.0709 (0.0784) loss: 0.8667 (0.8724) time: 0.1058 data: 0.0274 max mem: 8299 +Train: [42] [ 700/6250] eta: 0:12:15 lr: 0.000084 grad: 0.0665 (0.0780) loss: 0.8747 (0.8720) time: 0.0975 data: 0.0179 max mem: 8299 +Train: [42] [ 800/6250] eta: 0:11:58 lr: 0.000084 grad: 0.0725 (0.0773) loss: 0.8790 (0.8723) time: 0.1487 data: 0.0759 max mem: 8299 +Train: [42] [ 900/6250] eta: 0:11:44 lr: 0.000083 grad: 0.0675 (0.0770) loss: 0.8691 (0.8721) time: 0.1306 data: 0.0540 max mem: 8299 +Train: [42] [1000/6250] eta: 0:11:37 lr: 0.000083 grad: 0.0686 (0.0767) loss: 0.8740 (0.8719) time: 0.1511 data: 0.0782 max mem: 8299 +Train: [42] [1100/6250] eta: 0:11:24 lr: 0.000083 grad: 0.0659 (0.0764) loss: 0.8694 (0.8719) time: 0.1430 data: 0.0674 max mem: 8299 +Train: [42] [1200/6250] eta: 0:11:10 lr: 0.000083 grad: 0.0762 (0.0764) loss: 0.8723 (0.8715) time: 0.1373 data: 0.0640 max mem: 8299 +Train: [42] [1300/6250] eta: 0:10:56 lr: 0.000083 grad: 0.0693 (0.0764) loss: 0.8719 (0.8712) time: 0.1288 data: 0.0552 max mem: 8299 +Train: [42] [1400/6250] eta: 0:10:41 lr: 0.000083 grad: 0.0736 (0.0764) loss: 0.8701 (0.8712) time: 0.1208 data: 0.0500 max mem: 8299 +Train: [42] [1500/6250] eta: 0:10:32 lr: 0.000083 grad: 0.0727 (0.0765) loss: 0.8670 (0.8709) time: 0.1333 data: 0.0552 max mem: 8299 +Train: [42] [1600/6250] eta: 0:10:18 lr: 0.000083 grad: 0.0730 (0.0765) loss: 0.8705 (0.8708) time: 0.1405 data: 0.0656 max mem: 8299 +Train: [42] [1700/6250] eta: 0:10:04 lr: 0.000083 grad: 0.0723 (0.0767) loss: 0.8663 (0.8707) time: 0.1144 data: 0.0369 max mem: 8299 +Train: [42] [1800/6250] eta: 0:09:50 lr: 0.000083 grad: 0.0783 (0.0768) loss: 0.8657 (0.8704) time: 0.1193 data: 0.0525 max mem: 8299 +Train: [42] [1900/6250] eta: 0:09:38 lr: 0.000083 grad: 0.0803 (0.0770) loss: 0.8632 (0.8702) time: 0.1463 data: 0.0744 max mem: 8299 +Train: [42] [2000/6250] eta: 0:09:23 lr: 0.000083 grad: 0.0841 (0.0773) loss: 0.8591 (0.8700) time: 0.1160 data: 0.0376 max mem: 8299 +Train: [42] [2100/6250] eta: 0:09:09 lr: 0.000083 grad: 0.0752 (0.0773) loss: 0.8703 (0.8699) time: 0.1241 data: 0.0476 max mem: 8299 +Train: [42] [2200/6250] eta: 0:08:55 lr: 0.000083 grad: 0.0743 (0.0773) loss: 0.8670 (0.8698) time: 0.1183 data: 0.0465 max mem: 8299 +Train: [42] [2300/6250] eta: 0:08:42 lr: 0.000083 grad: 0.0752 (0.0773) loss: 0.8703 (0.8699) time: 0.1500 data: 0.0796 max mem: 8299 +Train: [42] [2400/6250] eta: 0:08:29 lr: 0.000083 grad: 0.0750 (0.0772) loss: 0.8734 (0.8700) time: 0.1435 data: 0.0713 max mem: 8299 +Train: [42] [2500/6250] eta: 0:08:15 lr: 0.000083 grad: 0.0758 (0.0776) loss: 0.8701 (0.8699) time: 0.1238 data: 0.0486 max mem: 8299 +Train: [42] [2600/6250] eta: 0:08:01 lr: 0.000083 grad: 0.0814 (0.0777) loss: 0.8660 (0.8699) time: 0.1198 data: 0.0517 max mem: 8299 +Train: [42] [2700/6250] eta: 0:07:49 lr: 0.000083 grad: 0.0744 (0.0777) loss: 0.8674 (0.8698) time: 0.1410 data: 0.0689 max mem: 8299 +Train: [42] [2800/6250] eta: 0:07:36 lr: 0.000083 grad: 0.0813 (0.0778) loss: 0.8665 (0.8696) time: 0.1273 data: 0.0516 max mem: 8299 +Train: [42] [2900/6250] eta: 0:07:23 lr: 0.000083 grad: 0.0813 (0.0781) loss: 0.8656 (0.8695) time: 0.1468 data: 0.0693 max mem: 8299 +Train: [42] [3000/6250] eta: 0:07:09 lr: 0.000083 grad: 0.0857 (0.0784) loss: 0.8605 (0.8694) time: 0.1444 data: 0.0724 max mem: 8299 +Train: [42] [3100/6250] eta: 0:06:56 lr: 0.000083 grad: 0.0764 (0.0785) loss: 0.8677 (0.8692) time: 0.1122 data: 0.0375 max mem: 8299 +Train: [42] [3200/6250] eta: 0:06:42 lr: 0.000083 grad: 0.0870 (0.0788) loss: 0.8645 (0.8691) time: 0.1246 data: 0.0483 max mem: 8299 +Train: [42] [3300/6250] eta: 0:06:30 lr: 0.000083 grad: 0.0779 (0.0790) loss: 0.8685 (0.8689) time: 0.1266 data: 0.0550 max mem: 8299 +Train: [42] [3400/6250] eta: 0:06:16 lr: 0.000083 grad: 0.0774 (0.0792) loss: 0.8647 (0.8688) time: 0.1083 data: 0.0310 max mem: 8299 +Train: [42] [3500/6250] eta: 0:06:03 lr: 0.000083 grad: 0.0798 (0.0794) loss: 0.8602 (0.8687) time: 0.1555 data: 0.0793 max mem: 8299 +Train: [42] [3600/6250] eta: 0:05:50 lr: 0.000083 grad: 0.0841 (0.0796) loss: 0.8627 (0.8686) time: 0.1292 data: 0.0457 max mem: 8299 +Train: [42] [3700/6250] eta: 0:05:36 lr: 0.000083 grad: 0.0785 (0.0797) loss: 0.8656 (0.8685) time: 0.1534 data: 0.0775 max mem: 8299 +Train: [42] [3800/6250] eta: 0:05:23 lr: 0.000083 grad: 0.0836 (0.0797) loss: 0.8636 (0.8683) time: 0.1370 data: 0.0649 max mem: 8299 +Train: [42] [3900/6250] eta: 0:05:10 lr: 0.000083 grad: 0.0858 (0.0798) loss: 0.8645 (0.8682) time: 0.1384 data: 0.0610 max mem: 8299 +Train: [42] [4000/6250] eta: 0:04:57 lr: 0.000083 grad: 0.0735 (0.0798) loss: 0.8628 (0.8681) time: 0.1176 data: 0.0452 max mem: 8299 +Train: [42] [4100/6250] eta: 0:04:44 lr: 0.000082 grad: 0.0748 (0.0798) loss: 0.8668 (0.8680) time: 0.1647 data: 0.0871 max mem: 8299 +Train: [42] [4200/6250] eta: 0:04:31 lr: 0.000082 grad: 0.0796 (0.0798) loss: 0.8658 (0.8679) time: 0.0879 data: 0.0046 max mem: 8299 +Train: [42] [4300/6250] eta: 0:04:17 lr: 0.000082 grad: 0.0776 (0.0800) loss: 0.8635 (0.8678) time: 0.1259 data: 0.0468 max mem: 8299 +Train: [42] [4400/6250] eta: 0:04:04 lr: 0.000082 grad: 0.0771 (0.0800) loss: 0.8659 (0.8678) time: 0.1429 data: 0.0710 max mem: 8299 +Train: [42] [4500/6250] eta: 0:03:51 lr: 0.000082 grad: 0.0747 (0.0800) loss: 0.8652 (0.8677) time: 0.1243 data: 0.0510 max mem: 8299 +Train: [42] [4600/6250] eta: 0:03:38 lr: 0.000082 grad: 0.0746 (0.0800) loss: 0.8623 (0.8677) time: 0.1403 data: 0.0657 max mem: 8299 +Train: [42] [4700/6250] eta: 0:03:25 lr: 0.000082 grad: 0.0781 (0.0801) loss: 0.8699 (0.8676) time: 0.1729 data: 0.1005 max mem: 8299 +Train: [42] [4800/6250] eta: 0:03:11 lr: 0.000082 grad: 0.0825 (0.0801) loss: 0.8601 (0.8675) time: 0.1343 data: 0.0507 max mem: 8299 +Train: [42] [4900/6250] eta: 0:02:58 lr: 0.000082 grad: 0.0771 (0.0801) loss: 0.8580 (0.8674) time: 0.1330 data: 0.0511 max mem: 8299 +Train: [42] [5000/6250] eta: 0:02:45 lr: 0.000082 grad: 0.0802 (0.0802) loss: 0.8706 (0.8673) time: 0.1333 data: 0.0611 max mem: 8299 +Train: [42] [5100/6250] eta: 0:02:32 lr: 0.000082 grad: 0.0816 (0.0803) loss: 0.8693 (0.8672) time: 0.1421 data: 0.0633 max mem: 8299 +Train: [42] [5200/6250] eta: 0:02:19 lr: 0.000082 grad: 0.0800 (0.0805) loss: 0.8628 (0.8671) time: 0.1372 data: 0.0477 max mem: 8299 +Train: [42] [5300/6250] eta: 0:02:06 lr: 0.000082 grad: 0.0765 (0.0805) loss: 0.8590 (0.8670) time: 0.1451 data: 0.0619 max mem: 8299 +Train: [42] [5400/6250] eta: 0:01:53 lr: 0.000082 grad: 0.0782 (0.0806) loss: 0.8596 (0.8669) time: 0.1457 data: 0.0660 max mem: 8299 +Train: [42] [5500/6250] eta: 0:01:39 lr: 0.000082 grad: 0.0886 (0.0807) loss: 0.8626 (0.8668) time: 0.1329 data: 0.0502 max mem: 8299 +Train: [42] [5600/6250] eta: 0:01:26 lr: 0.000082 grad: 0.0790 (0.0807) loss: 0.8698 (0.8668) time: 0.1193 data: 0.0311 max mem: 8299 +Train: [42] [5700/6250] eta: 0:01:13 lr: 0.000082 grad: 0.0809 (0.0808) loss: 0.8649 (0.8667) time: 0.1308 data: 0.0514 max mem: 8299 +Train: [42] [5800/6250] eta: 0:00:59 lr: 0.000082 grad: 0.0781 (0.0809) loss: 0.8633 (0.8666) time: 0.1217 data: 0.0451 max mem: 8299 +Train: [42] [5900/6250] eta: 0:00:46 lr: 0.000082 grad: 0.0862 (0.0810) loss: 0.8693 (0.8666) time: 0.1363 data: 0.0607 max mem: 8299 +Train: [42] [6000/6250] eta: 0:00:33 lr: 0.000082 grad: 0.0750 (0.0811) loss: 0.8702 (0.8666) time: 0.1271 data: 0.0396 max mem: 8299 +Train: [42] [6100/6250] eta: 0:00:19 lr: 0.000082 grad: 0.0779 (0.0812) loss: 0.8698 (0.8665) time: 0.1360 data: 0.0671 max mem: 8299 +Train: [42] [6200/6250] eta: 0:00:06 lr: 0.000082 grad: 0.0834 (0.0812) loss: 0.8698 (0.8664) time: 0.1346 data: 0.0582 max mem: 8299 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0805 (0.0812) loss: 0.8616 (0.8664) time: 0.1468 data: 0.0707 max mem: 8299 +Train: [42] Total time: 0:13:52 (0.1331 s / it) +Averaged stats: lr: 0.000082 grad: 0.0805 (0.0812) loss: 0.8616 (0.8664) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:03:12 loss: 0.9012 (0.9012) time: 3.1047 data: 3.0239 max mem: 8299 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8910 (0.8897) time: 0.1169 data: 0.0926 max mem: 8299 +Eval (hcp-train-subset): [42] Total time: 0:00:13 (0.2122 s / it) +Averaged stats (hcp-train-subset): loss: 0.8910 (0.8897) +Eval (hcp-val): [42] [ 0/62] eta: 0:05:25 loss: 0.8869 (0.8869) time: 5.2551 data: 5.2249 max mem: 8299 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8840 (0.8864) time: 0.1170 data: 0.0915 max mem: 8299 +Eval (hcp-val): [42] Total time: 0:00:13 (0.2104 s / it) +Averaged stats (hcp-val): loss: 0.8840 (0.8864) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 9:03:23 lr: 0.000082 grad: 0.0463 (0.0463) loss: 0.9103 (0.9103) time: 5.2165 data: 5.0728 max mem: 8299 +Train: [43] [ 100/6250] eta: 0:18:18 lr: 0.000082 grad: 0.0744 (0.0847) loss: 0.8841 (0.8844) time: 0.1172 data: 0.0303 max mem: 8299 +Train: [43] [ 200/6250] eta: 0:15:45 lr: 0.000082 grad: 0.0679 (0.0820) loss: 0.8690 (0.8792) time: 0.1401 data: 0.0469 max mem: 8299 +Train: [43] [ 300/6250] eta: 0:14:27 lr: 0.000082 grad: 0.0751 (0.0815) loss: 0.8665 (0.8763) time: 0.1167 data: 0.0261 max mem: 8299 +Train: [43] [ 400/6250] eta: 0:13:32 lr: 0.000082 grad: 0.0701 (0.0808) loss: 0.8663 (0.8732) time: 0.1098 data: 0.0231 max mem: 8299 +Train: [43] [ 500/6250] eta: 0:12:59 lr: 0.000082 grad: 0.0666 (0.0795) loss: 0.8699 (0.8715) time: 0.1168 data: 0.0350 max mem: 8299 +Train: [43] [ 600/6250] eta: 0:12:36 lr: 0.000082 grad: 0.0724 (0.0787) loss: 0.8675 (0.8707) time: 0.1277 data: 0.0440 max mem: 8299 +Train: [43] [ 700/6250] eta: 0:12:18 lr: 0.000082 grad: 0.0698 (0.0781) loss: 0.8677 (0.8701) time: 0.1151 data: 0.0274 max mem: 8299 +Train: [43] [ 800/6250] eta: 0:12:03 lr: 0.000082 grad: 0.0681 (0.0773) loss: 0.8728 (0.8699) time: 0.1435 data: 0.0671 max mem: 8299 +Train: [43] [ 900/6250] eta: 0:11:49 lr: 0.000082 grad: 0.0654 (0.0769) loss: 0.8763 (0.8699) time: 0.1246 data: 0.0377 max mem: 8299 +Train: [43] [1000/6250] eta: 0:11:36 lr: 0.000081 grad: 0.0739 (0.0764) loss: 0.8663 (0.8700) time: 0.1558 data: 0.0808 max mem: 8299 +Train: [43] [1100/6250] eta: 0:11:20 lr: 0.000081 grad: 0.0748 (0.0762) loss: 0.8694 (0.8701) time: 0.1289 data: 0.0541 max mem: 8299 +Train: [43] [1200/6250] eta: 0:11:02 lr: 0.000081 grad: 0.0783 (0.0760) loss: 0.8632 (0.8701) time: 0.1222 data: 0.0440 max mem: 8299 +Train: [43] [1300/6250] eta: 0:10:46 lr: 0.000081 grad: 0.0767 (0.0759) loss: 0.8704 (0.8701) time: 0.1309 data: 0.0461 max mem: 8299 +Train: [43] [1400/6250] eta: 0:10:32 lr: 0.000081 grad: 0.0768 (0.0761) loss: 0.8667 (0.8699) time: 0.1515 data: 0.0887 max mem: 8299 +Train: [43] [1500/6250] eta: 0:10:17 lr: 0.000081 grad: 0.0711 (0.0761) loss: 0.8702 (0.8698) time: 0.1270 data: 0.0410 max mem: 8299 +Train: [43] [1600/6250] eta: 0:10:03 lr: 0.000081 grad: 0.0762 (0.0761) loss: 0.8600 (0.8696) time: 0.1048 data: 0.0260 max mem: 8299 +Train: [43] [1700/6250] eta: 0:09:49 lr: 0.000081 grad: 0.0711 (0.0762) loss: 0.8701 (0.8695) time: 0.1139 data: 0.0431 max mem: 8299 +Train: [43] [1800/6250] eta: 0:09:38 lr: 0.000081 grad: 0.0784 (0.0763) loss: 0.8604 (0.8693) time: 0.1423 data: 0.0652 max mem: 8299 +Train: [43] [1900/6250] eta: 0:09:26 lr: 0.000081 grad: 0.0725 (0.0763) loss: 0.8745 (0.8693) time: 0.1286 data: 0.0531 max mem: 8299 +Train: [43] [2000/6250] eta: 0:09:13 lr: 0.000081 grad: 0.0809 (0.0765) loss: 0.8616 (0.8691) time: 0.1340 data: 0.0676 max mem: 8299 +Train: [43] [2100/6250] eta: 0:08:59 lr: 0.000081 grad: 0.0723 (0.0767) loss: 0.8659 (0.8691) time: 0.1325 data: 0.0488 max mem: 8299 +Train: [43] [2200/6250] eta: 0:08:46 lr: 0.000081 grad: 0.0781 (0.0768) loss: 0.8717 (0.8689) time: 0.1232 data: 0.0431 max mem: 8299 +Train: [43] [2300/6250] eta: 0:08:31 lr: 0.000081 grad: 0.0806 (0.0770) loss: 0.8663 (0.8688) time: 0.1268 data: 0.0582 max mem: 8299 +Train: [43] [2400/6250] eta: 0:08:18 lr: 0.000081 grad: 0.0760 (0.0773) loss: 0.8674 (0.8688) time: 0.1325 data: 0.0621 max mem: 8299 +Train: [43] [2500/6250] eta: 0:08:05 lr: 0.000081 grad: 0.0729 (0.0774) loss: 0.8709 (0.8687) time: 0.1515 data: 0.0795 max mem: 8299 +Train: [43] [2600/6250] eta: 0:07:52 lr: 0.000081 grad: 0.0782 (0.0775) loss: 0.8677 (0.8686) time: 0.1156 data: 0.0360 max mem: 8299 +Train: [43] [2700/6250] eta: 0:07:38 lr: 0.000081 grad: 0.0712 (0.0775) loss: 0.8737 (0.8686) time: 0.1238 data: 0.0410 max mem: 8299 +Train: [43] [2800/6250] eta: 0:07:26 lr: 0.000081 grad: 0.0753 (0.0776) loss: 0.8730 (0.8686) time: 0.0963 data: 0.0196 max mem: 8299 +Train: [43] [2900/6250] eta: 0:07:13 lr: 0.000081 grad: 0.0759 (0.0778) loss: 0.8686 (0.8686) time: 0.1430 data: 0.0671 max mem: 8299 +Train: [43] [3000/6250] eta: 0:07:00 lr: 0.000081 grad: 0.0806 (0.0781) loss: 0.8688 (0.8686) time: 0.1404 data: 0.0676 max mem: 8299 +Train: [43] [3100/6250] eta: 0:06:47 lr: 0.000081 grad: 0.0701 (0.0781) loss: 0.8723 (0.8686) time: 0.1374 data: 0.0690 max mem: 8299 +Train: [43] [3200/6250] eta: 0:06:34 lr: 0.000081 grad: 0.0748 (0.0784) loss: 0.8765 (0.8686) time: 0.1241 data: 0.0436 max mem: 8299 +Train: [43] [3300/6250] eta: 0:06:22 lr: 0.000081 grad: 0.0774 (0.0783) loss: 0.8627 (0.8685) time: 0.1309 data: 0.0491 max mem: 8299 +Train: [43] [3400/6250] eta: 0:06:09 lr: 0.000081 grad: 0.0806 (0.0783) loss: 0.8629 (0.8685) time: 0.1249 data: 0.0492 max mem: 8299 +Train: [43] [3500/6250] eta: 0:05:56 lr: 0.000081 grad: 0.0711 (0.0784) loss: 0.8681 (0.8685) time: 0.1333 data: 0.0534 max mem: 8299 +Train: [43] [3600/6250] eta: 0:05:43 lr: 0.000081 grad: 0.0809 (0.0785) loss: 0.8637 (0.8684) time: 0.1275 data: 0.0515 max mem: 8299 +Train: [43] [3700/6250] eta: 0:05:31 lr: 0.000081 grad: 0.0790 (0.0786) loss: 0.8673 (0.8685) time: 0.1232 data: 0.0575 max mem: 8299 +Train: [43] [3800/6250] eta: 0:05:18 lr: 0.000081 grad: 0.0792 (0.0787) loss: 0.8715 (0.8684) time: 0.1438 data: 0.0568 max mem: 8299 +Train: [43] [3900/6250] eta: 0:05:07 lr: 0.000081 grad: 0.0780 (0.0787) loss: 0.8732 (0.8685) time: 0.1627 data: 0.0854 max mem: 8299 +Train: [43] [4000/6250] eta: 0:04:54 lr: 0.000081 grad: 0.0728 (0.0786) loss: 0.8671 (0.8685) time: 0.1256 data: 0.0429 max mem: 8299 +Train: [43] [4100/6250] eta: 0:04:41 lr: 0.000081 grad: 0.0868 (0.0788) loss: 0.8668 (0.8685) time: 0.1274 data: 0.0516 max mem: 8299 +Train: [43] [4200/6250] eta: 0:04:28 lr: 0.000080 grad: 0.0817 (0.0788) loss: 0.8624 (0.8685) time: 0.1096 data: 0.0329 max mem: 8299 +Train: [43] [4300/6250] eta: 0:04:14 lr: 0.000080 grad: 0.0715 (0.0788) loss: 0.8715 (0.8685) time: 0.1155 data: 0.0295 max mem: 8299 +Train: [43] [4400/6250] eta: 0:04:01 lr: 0.000080 grad: 0.0730 (0.0788) loss: 0.8733 (0.8685) time: 0.1205 data: 0.0456 max mem: 8299 +Train: [43] [4500/6250] eta: 0:03:48 lr: 0.000080 grad: 0.0756 (0.0788) loss: 0.8715 (0.8685) time: 0.1394 data: 0.0572 max mem: 8299 +Train: [43] [4600/6250] eta: 0:03:35 lr: 0.000080 grad: 0.0775 (0.0787) loss: 0.8699 (0.8686) time: 0.1280 data: 0.0457 max mem: 8299 +Train: [43] [4700/6250] eta: 0:03:22 lr: 0.000080 grad: 0.0698 (0.0787) loss: 0.8709 (0.8686) time: 0.1171 data: 0.0421 max mem: 8299 +Train: [43] [4800/6250] eta: 0:03:09 lr: 0.000080 grad: 0.0803 (0.0787) loss: 0.8697 (0.8686) time: 0.1131 data: 0.0417 max mem: 8299 +Train: [43] [4900/6250] eta: 0:02:56 lr: 0.000080 grad: 0.0704 (0.0787) loss: 0.8754 (0.8686) time: 0.1307 data: 0.0539 max mem: 8299 +Train: [43] [5000/6250] eta: 0:02:43 lr: 0.000080 grad: 0.0753 (0.0786) loss: 0.8702 (0.8687) time: 0.1136 data: 0.0320 max mem: 8299 +Train: [43] [5100/6250] eta: 0:02:30 lr: 0.000080 grad: 0.0794 (0.0787) loss: 0.8672 (0.8687) time: 0.1317 data: 0.0650 max mem: 8299 +Train: [43] [5200/6250] eta: 0:02:17 lr: 0.000080 grad: 0.0784 (0.0788) loss: 0.8705 (0.8687) time: 0.1532 data: 0.0782 max mem: 8299 +Train: [43] [5300/6250] eta: 0:02:04 lr: 0.000080 grad: 0.0756 (0.0788) loss: 0.8663 (0.8686) time: 0.1438 data: 0.0700 max mem: 8299 +Train: [43] [5400/6250] eta: 0:01:51 lr: 0.000080 grad: 0.0754 (0.0788) loss: 0.8775 (0.8687) time: 0.1378 data: 0.0636 max mem: 8299 +Train: [43] [5500/6250] eta: 0:01:38 lr: 0.000080 grad: 0.0804 (0.0789) loss: 0.8697 (0.8687) time: 0.1820 data: 0.1104 max mem: 8299 +Train: [43] [5600/6250] eta: 0:01:25 lr: 0.000080 grad: 0.0781 (0.0790) loss: 0.8647 (0.8686) time: 0.1139 data: 0.0457 max mem: 8299 +Train: [43] [5700/6250] eta: 0:01:12 lr: 0.000080 grad: 0.0838 (0.0790) loss: 0.8676 (0.8686) time: 0.1285 data: 0.0501 max mem: 8299 +Train: [43] [5800/6250] eta: 0:00:58 lr: 0.000080 grad: 0.0804 (0.0791) loss: 0.8715 (0.8686) time: 0.1109 data: 0.0314 max mem: 8299 +Train: [43] [5900/6250] eta: 0:00:45 lr: 0.000080 grad: 0.0840 (0.0792) loss: 0.8692 (0.8686) time: 0.1254 data: 0.0356 max mem: 8299 +Train: [43] [6000/6250] eta: 0:00:32 lr: 0.000080 grad: 0.0830 (0.0792) loss: 0.8627 (0.8686) time: 0.1061 data: 0.0263 max mem: 8299 +Train: [43] [6100/6250] eta: 0:00:19 lr: 0.000080 grad: 0.0750 (0.0793) loss: 0.8661 (0.8685) time: 0.1220 data: 0.0416 max mem: 8299 +Train: [43] [6200/6250] eta: 0:00:06 lr: 0.000080 grad: 0.0852 (0.0794) loss: 0.8561 (0.8684) time: 0.1299 data: 0.0614 max mem: 8299 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0882 (0.0794) loss: 0.8645 (0.8684) time: 0.1397 data: 0.0650 max mem: 8299 +Train: [43] Total time: 0:13:41 (0.1314 s / it) +Averaged stats: lr: 0.000080 grad: 0.0882 (0.0794) loss: 0.8645 (0.8684) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:04:02 loss: 0.8977 (0.8977) time: 3.9102 data: 3.8578 max mem: 8299 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8878 (0.8900) time: 0.1107 data: 0.0855 max mem: 8299 +Eval (hcp-train-subset): [43] Total time: 0:00:11 (0.1897 s / it) +Averaged stats (hcp-train-subset): loss: 0.8878 (0.8900) +Eval (hcp-val): [43] [ 0/62] eta: 0:04:08 loss: 0.8903 (0.8903) time: 4.0150 data: 3.9437 max mem: 8299 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8862 (0.8879) time: 0.1112 data: 0.0857 max mem: 8299 +Eval (hcp-val): [43] Total time: 0:00:12 (0.1978 s / it) +Averaged stats (hcp-val): loss: 0.8862 (0.8879) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 8:33:01 lr: 0.000080 grad: nan (nan) loss: 0.9153 (0.9153) time: 4.9251 data: 4.7753 max mem: 8299 +Train: [44] [ 100/6250] eta: 0:19:10 lr: 0.000080 grad: 0.0744 (0.0908) loss: 0.8691 (0.8771) time: 0.1457 data: 0.0546 max mem: 8299 +Train: [44] [ 200/6250] eta: 0:16:37 lr: 0.000080 grad: 0.0676 (0.0824) loss: 0.8798 (0.8768) time: 0.1710 data: 0.0875 max mem: 8299 +Train: [44] [ 300/6250] eta: 0:14:59 lr: 0.000080 grad: 0.0667 (0.0787) loss: 0.8759 (0.8778) time: 0.1170 data: 0.0382 max mem: 8299 +Train: [44] [ 400/6250] eta: 0:14:04 lr: 0.000080 grad: 0.0706 (0.0774) loss: 0.8766 (0.8780) time: 0.1278 data: 0.0325 max mem: 8299 +Train: [44] [ 500/6250] eta: 0:13:23 lr: 0.000080 grad: 0.0685 (0.0767) loss: 0.8750 (0.8771) time: 0.1161 data: 0.0360 max mem: 8299 +Train: [44] [ 600/6250] eta: 0:12:58 lr: 0.000080 grad: 0.0674 (0.0761) loss: 0.8787 (0.8766) time: 0.1383 data: 0.0627 max mem: 8299 +Train: [44] [ 700/6250] eta: 0:12:41 lr: 0.000080 grad: 0.0684 (0.0758) loss: 0.8822 (0.8766) time: 0.1630 data: 0.0941 max mem: 8299 +Train: [44] [ 800/6250] eta: 0:12:24 lr: 0.000080 grad: 0.0698 (0.0755) loss: 0.8761 (0.8764) time: 0.1397 data: 0.0455 max mem: 8299 +Train: [44] [ 900/6250] eta: 0:12:07 lr: 0.000080 grad: 0.0652 (0.0748) loss: 0.8759 (0.8764) time: 0.1371 data: 0.0421 max mem: 8299 +Train: [44] [1000/6250] eta: 0:11:47 lr: 0.000080 grad: 0.0677 (0.0743) loss: 0.8726 (0.8762) time: 0.1269 data: 0.0479 max mem: 8299 +Train: [44] [1100/6250] eta: 0:11:27 lr: 0.000079 grad: 0.0653 (0.0741) loss: 0.8750 (0.8759) time: 0.1238 data: 0.0266 max mem: 8299 +Train: [44] [1200/6250] eta: 0:11:12 lr: 0.000079 grad: 0.0691 (0.0741) loss: 0.8727 (0.8756) time: 0.1525 data: 0.0761 max mem: 8299 +Train: [44] [1300/6250] eta: 0:10:54 lr: 0.000079 grad: 0.0770 (0.0741) loss: 0.8650 (0.8752) time: 0.1309 data: 0.0512 max mem: 8299 +Train: [44] [1400/6250] eta: 0:10:38 lr: 0.000079 grad: 0.0743 (0.0744) loss: 0.8683 (0.8748) time: 0.1235 data: 0.0430 max mem: 8299 +Train: [44] [1500/6250] eta: 0:10:25 lr: 0.000079 grad: 0.0752 (0.0745) loss: 0.8682 (0.8746) time: 0.1323 data: 0.0439 max mem: 8299 +Train: [44] [1600/6250] eta: 0:10:10 lr: 0.000079 grad: 0.0764 (0.0746) loss: 0.8719 (0.8743) time: 0.1207 data: 0.0386 max mem: 8299 +Train: [44] [1700/6250] eta: 0:09:54 lr: 0.000079 grad: 0.0751 (0.0748) loss: 0.8634 (0.8741) time: 0.1151 data: 0.0267 max mem: 8299 +Train: [44] [1800/6250] eta: 0:09:40 lr: 0.000079 grad: 0.0756 (0.0748) loss: 0.8678 (0.8737) time: 0.1140 data: 0.0381 max mem: 8299 +Train: [44] [1900/6250] eta: 0:09:27 lr: 0.000079 grad: 0.0675 (0.0748) loss: 0.8716 (0.8737) time: 0.1162 data: 0.0311 max mem: 8299 +Train: [44] [2000/6250] eta: 0:09:13 lr: 0.000079 grad: 0.0699 (0.0748) loss: 0.8694 (0.8735) time: 0.1517 data: 0.0802 max mem: 8299 +Train: [44] [2100/6250] eta: 0:09:04 lr: 0.000079 grad: 0.0743 (0.0748) loss: 0.8677 (0.8733) time: 0.1290 data: 0.0489 max mem: 8299 +Train: [44] [2200/6250] eta: 0:08:54 lr: 0.000079 grad: 0.0689 (0.0749) loss: 0.8696 (0.8731) time: 0.1553 data: 0.0797 max mem: 8299 +Train: [44] [2300/6250] eta: 0:08:43 lr: 0.000079 grad: 0.0733 (0.0750) loss: 0.8654 (0.8728) time: 0.1564 data: 0.0765 max mem: 8299 +Train: [44] [2400/6250] eta: 0:08:32 lr: 0.000079 grad: 0.0668 (0.0750) loss: 0.8755 (0.8727) time: 0.1410 data: 0.0711 max mem: 8299 +Train: [44] [2500/6250] eta: 0:08:19 lr: 0.000079 grad: 0.0744 (0.0751) loss: 0.8696 (0.8726) time: 0.1373 data: 0.0578 max mem: 8299 +Train: [44] [2600/6250] eta: 0:08:08 lr: 0.000079 grad: 0.0801 (0.0753) loss: 0.8665 (0.8724) time: 0.1411 data: 0.0636 max mem: 8299 +Train: [44] [2700/6250] eta: 0:07:55 lr: 0.000079 grad: 0.0739 (0.0753) loss: 0.8730 (0.8724) time: 0.1283 data: 0.0469 max mem: 8299 +Train: [44] [2800/6250] eta: 0:07:41 lr: 0.000079 grad: 0.0729 (0.0753) loss: 0.8703 (0.8723) time: 0.1194 data: 0.0427 max mem: 8299 +Train: [44] [2900/6250] eta: 0:07:28 lr: 0.000079 grad: 0.0712 (0.0754) loss: 0.8738 (0.8722) time: 0.1608 data: 0.0898 max mem: 8299 +Train: [44] [3000/6250] eta: 0:07:14 lr: 0.000079 grad: 0.0748 (0.0754) loss: 0.8687 (0.8722) time: 0.1423 data: 0.0650 max mem: 8299 +Train: [44] [3100/6250] eta: 0:07:00 lr: 0.000079 grad: 0.0766 (0.0755) loss: 0.8674 (0.8721) time: 0.1329 data: 0.0511 max mem: 8299 +Train: [44] [3200/6250] eta: 0:06:47 lr: 0.000079 grad: 0.0672 (0.0755) loss: 0.8729 (0.8721) time: 0.1358 data: 0.0586 max mem: 8299 +Train: [44] [3300/6250] eta: 0:06:33 lr: 0.000079 grad: 0.0764 (0.0756) loss: 0.8690 (0.8720) time: 0.1193 data: 0.0438 max mem: 8299 +Train: [44] [3400/6250] eta: 0:06:20 lr: 0.000079 grad: 0.0698 (0.0757) loss: 0.8732 (0.8720) time: 0.1261 data: 0.0494 max mem: 8299 +Train: [44] [3500/6250] eta: 0:06:06 lr: 0.000079 grad: 0.0754 (0.0758) loss: 0.8646 (0.8718) time: 0.1370 data: 0.0627 max mem: 8299 +Train: [44] [3600/6250] eta: 0:05:53 lr: 0.000079 grad: 0.0707 (0.0759) loss: 0.8671 (0.8717) time: 0.1546 data: 0.0770 max mem: 8299 +Train: [44] [3700/6250] eta: 0:05:39 lr: 0.000079 grad: 0.0791 (0.0760) loss: 0.8685 (0.8716) time: 0.1093 data: 0.0215 max mem: 8299 +Train: [44] [3800/6250] eta: 0:05:25 lr: 0.000079 grad: 0.0739 (0.0761) loss: 0.8684 (0.8716) time: 0.1131 data: 0.0310 max mem: 8299 +Train: [44] [3900/6250] eta: 0:05:12 lr: 0.000079 grad: 0.0843 (0.0761) loss: 0.8651 (0.8715) time: 0.1111 data: 0.0339 max mem: 8299 +Train: [44] [4000/6250] eta: 0:04:59 lr: 0.000079 grad: 0.0791 (0.0762) loss: 0.8673 (0.8714) time: 0.1375 data: 0.0603 max mem: 8299 +Train: [44] [4100/6250] eta: 0:04:45 lr: 0.000079 grad: 0.0797 (0.0763) loss: 0.8655 (0.8713) time: 0.1271 data: 0.0407 max mem: 8299 +Train: [44] [4200/6250] eta: 0:04:32 lr: 0.000078 grad: 0.0715 (0.0762) loss: 0.8735 (0.8713) time: 0.1303 data: 0.0497 max mem: 8299 +Train: [44] [4300/6250] eta: 0:04:18 lr: 0.000078 grad: 0.0889 (0.0764) loss: 0.8694 (0.8713) time: 0.1017 data: 0.0199 max mem: 8299 +Train: [44] [4400/6250] eta: 0:04:05 lr: 0.000078 grad: 0.0762 (0.0765) loss: 0.8723 (0.8712) time: 0.1545 data: 0.0852 max mem: 8299 +Train: [44] [4500/6250] eta: 0:03:52 lr: 0.000078 grad: 0.0807 (0.0766) loss: 0.8680 (0.8712) time: 0.1366 data: 0.0615 max mem: 8299 +Train: [44] [4600/6250] eta: 0:03:39 lr: 0.000078 grad: 0.0802 (0.0766) loss: 0.8628 (0.8711) time: 0.1193 data: 0.0347 max mem: 8299 +Train: [44] [4700/6250] eta: 0:03:25 lr: 0.000078 grad: 0.0743 (0.0767) loss: 0.8705 (0.8710) time: 0.1490 data: 0.0650 max mem: 8299 +Train: [44] [4800/6250] eta: 0:03:12 lr: 0.000078 grad: 0.0758 (0.0768) loss: 0.8672 (0.8709) time: 0.1131 data: 0.0426 max mem: 8299 +Train: [44] [4900/6250] eta: 0:02:59 lr: 0.000078 grad: 0.0800 (0.0769) loss: 0.8650 (0.8708) time: 0.1546 data: 0.0868 max mem: 8299 +Train: [44] [5000/6250] eta: 0:02:46 lr: 0.000078 grad: 0.0789 (0.0771) loss: 0.8672 (0.8706) time: 0.1526 data: 0.0854 max mem: 8299 +Train: [44] [5100/6250] eta: 0:02:32 lr: 0.000078 grad: 0.0730 (0.0771) loss: 0.8670 (0.8705) time: 0.1780 data: 0.1143 max mem: 8299 +Train: [44] [5200/6250] eta: 0:02:19 lr: 0.000078 grad: 0.0784 (0.0772) loss: 0.8640 (0.8703) time: 0.1603 data: 0.0950 max mem: 8299 +Train: [44] [5300/6250] eta: 0:02:06 lr: 0.000078 grad: 0.0781 (0.0773) loss: 0.8621 (0.8702) time: 0.1322 data: 0.0601 max mem: 8299 +Train: [44] [5400/6250] eta: 0:01:53 lr: 0.000078 grad: 0.0794 (0.0774) loss: 0.8659 (0.8700) time: 0.1581 data: 0.0852 max mem: 8299 +Train: [44] [5500/6250] eta: 0:01:40 lr: 0.000078 grad: 0.0794 (0.0774) loss: 0.8651 (0.8699) time: 0.1541 data: 0.0771 max mem: 8299 +Train: [44] [5600/6250] eta: 0:01:26 lr: 0.000078 grad: 0.0817 (0.0776) loss: 0.8630 (0.8697) time: 0.1349 data: 0.0589 max mem: 8299 +Train: [44] [5700/6250] eta: 0:01:13 lr: 0.000078 grad: 0.0873 (0.0777) loss: 0.8621 (0.8696) time: 0.1198 data: 0.0485 max mem: 8299 +Train: [44] [5800/6250] eta: 0:01:00 lr: 0.000078 grad: 0.0806 (0.0777) loss: 0.8661 (0.8695) time: 0.1326 data: 0.0592 max mem: 8299 +Train: [44] [5900/6250] eta: 0:00:46 lr: 0.000078 grad: 0.0761 (0.0778) loss: 0.8644 (0.8693) time: 0.1332 data: 0.0547 max mem: 8299 +Train: [44] [6000/6250] eta: 0:00:33 lr: 0.000078 grad: 0.0768 (0.0779) loss: 0.8700 (0.8692) time: 0.1183 data: 0.0367 max mem: 8299 +Train: [44] [6100/6250] eta: 0:00:19 lr: 0.000078 grad: 0.0856 (0.0780) loss: 0.8580 (0.8691) time: 0.1201 data: 0.0331 max mem: 8299 +Train: [44] [6200/6250] eta: 0:00:06 lr: 0.000078 grad: 0.0747 (0.0781) loss: 0.8660 (0.8690) time: 0.1196 data: 0.0390 max mem: 8299 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0760 (0.0781) loss: 0.8622 (0.8689) time: 0.1092 data: 0.0213 max mem: 8299 +Train: [44] Total time: 0:13:54 (0.1335 s / it) +Averaged stats: lr: 0.000078 grad: 0.0760 (0.0781) loss: 0.8622 (0.8689) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:04:24 loss: 0.8994 (0.8994) time: 4.2658 data: 4.2101 max mem: 8299 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8897 (0.8886) time: 0.1313 data: 0.1068 max mem: 8299 +Eval (hcp-train-subset): [44] Total time: 0:00:13 (0.2130 s / it) +Averaged stats (hcp-train-subset): loss: 0.8897 (0.8886) +Making plots (hcp-train-subset): example=14 +Eval (hcp-val): [44] [ 0/62] eta: 0:03:37 loss: 0.8874 (0.8874) time: 3.5054 data: 3.4289 max mem: 8299 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8851 (0.8868) time: 0.1172 data: 0.0917 max mem: 8299 +Eval (hcp-val): [44] Total time: 0:00:12 (0.1999 s / it) +Averaged stats (hcp-val): loss: 0.8851 (0.8868) +Making plots (hcp-val): example=45 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 9:04:48 lr: 0.000078 grad: 0.0886 (0.0886) loss: 0.8649 (0.8649) time: 5.2302 data: 5.1241 max mem: 8299 +Train: [45] [ 100/6250] eta: 0:18:57 lr: 0.000078 grad: 0.0708 (0.0791) loss: 0.8757 (0.8816) time: 0.1322 data: 0.0495 max mem: 8299 +Train: [45] [ 200/6250] eta: 0:16:08 lr: 0.000078 grad: 0.0739 (0.0819) loss: 0.8665 (0.8754) time: 0.1434 data: 0.0595 max mem: 8299 +Train: [45] [ 300/6250] eta: 0:15:08 lr: 0.000078 grad: 0.0770 (0.0834) loss: 0.8688 (0.8731) time: 0.1142 data: 0.0320 max mem: 8299 +Train: [45] [ 400/6250] eta: 0:14:30 lr: 0.000078 grad: 0.0707 (0.0820) loss: 0.8714 (0.8727) time: 0.1368 data: 0.0644 max mem: 8299 +Train: [45] [ 500/6250] eta: 0:14:04 lr: 0.000078 grad: 0.0760 (0.0808) loss: 0.8689 (0.8721) time: 0.1206 data: 0.0455 max mem: 8299 +Train: [45] [ 600/6250] eta: 0:13:32 lr: 0.000078 grad: 0.0670 (0.0793) loss: 0.8693 (0.8722) time: 0.1462 data: 0.0781 max mem: 8299 +Train: [45] [ 700/6250] eta: 0:13:10 lr: 0.000078 grad: 0.0785 (0.0788) loss: 0.8614 (0.8718) time: 0.1449 data: 0.0629 max mem: 8299 +Train: [45] [ 800/6250] eta: 0:12:49 lr: 0.000078 grad: 0.0729 (0.0784) loss: 0.8687 (0.8714) time: 0.1291 data: 0.0401 max mem: 8299 +Train: [45] [ 900/6250] eta: 0:12:24 lr: 0.000078 grad: 0.0756 (0.0784) loss: 0.8664 (0.8711) time: 0.1252 data: 0.0414 max mem: 8299 +Train: [45] [1000/6250] eta: 0:12:00 lr: 0.000078 grad: 0.0762 (0.0784) loss: 0.8688 (0.8707) time: 0.1259 data: 0.0371 max mem: 8299 +Train: [45] [1100/6250] eta: 0:11:37 lr: 0.000077 grad: 0.0841 (0.0788) loss: 0.8517 (0.8700) time: 0.1113 data: 0.0274 max mem: 8299 +Train: [45] [1200/6250] eta: 0:11:14 lr: 0.000077 grad: 0.0945 (0.0794) loss: 0.8616 (0.8695) time: 0.1201 data: 0.0370 max mem: 8299 +Train: [45] [1300/6250] eta: 0:10:55 lr: 0.000077 grad: 0.0879 (0.0796) loss: 0.8639 (0.8690) time: 0.1309 data: 0.0546 max mem: 8299 +Train: [45] [1400/6250] eta: 0:10:39 lr: 0.000077 grad: 0.0840 (0.0805) loss: 0.8609 (0.8685) time: 0.1280 data: 0.0594 max mem: 8299 +Train: [45] [1500/6250] eta: 0:10:24 lr: 0.000077 grad: 0.0867 (0.0809) loss: 0.8619 (0.8681) time: 0.1070 data: 0.0379 max mem: 8299 +Train: [45] [1600/6250] eta: 0:10:09 lr: 0.000077 grad: 0.0846 (0.0819) loss: 0.8652 (0.8679) time: 0.1269 data: 0.0481 max mem: 8299 +Train: [45] [1700/6250] eta: 0:09:55 lr: 0.000077 grad: 0.0780 (0.0820) loss: 0.8691 (0.8678) time: 0.1309 data: 0.0583 max mem: 8299 +Train: [45] [1800/6250] eta: 0:09:40 lr: 0.000077 grad: 0.0793 (0.0820) loss: 0.8713 (0.8678) time: 0.1227 data: 0.0386 max mem: 8299 +Train: [45] [1900/6250] eta: 0:09:27 lr: 0.000077 grad: 0.0830 (0.0821) loss: 0.8619 (0.8676) time: 0.1454 data: 0.0698 max mem: 8299 +Train: [45] [2000/6250] eta: 0:09:12 lr: 0.000077 grad: 0.0800 (0.0823) loss: 0.8679 (0.8674) time: 0.1292 data: 0.0591 max mem: 8299 +Train: [45] [2100/6250] eta: 0:08:58 lr: 0.000077 grad: 0.0810 (0.0822) loss: 0.8663 (0.8674) time: 0.1288 data: 0.0557 max mem: 8299 +Train: [45] [2200/6250] eta: 0:08:44 lr: 0.000077 grad: 0.0809 (0.0822) loss: 0.8617 (0.8673) time: 0.1158 data: 0.0368 max mem: 8299 +Train: [45] [2300/6250] eta: 0:08:31 lr: 0.000077 grad: 0.0746 (0.0822) loss: 0.8676 (0.8673) time: 0.1220 data: 0.0474 max mem: 8299 +Train: [45] [2400/6250] eta: 0:08:17 lr: 0.000077 grad: 0.0789 (0.0822) loss: 0.8674 (0.8673) time: 0.1424 data: 0.0791 max mem: 8299 +Train: [45] [2500/6250] eta: 0:08:04 lr: 0.000077 grad: 0.0808 (0.0823) loss: 0.8676 (0.8673) time: 0.1116 data: 0.0411 max mem: 8299 +Train: [45] [2600/6250] eta: 0:07:52 lr: 0.000077 grad: 0.0799 (0.0824) loss: 0.8675 (0.8673) time: 0.1421 data: 0.0694 max mem: 8299 +Train: [45] [2700/6250] eta: 0:07:38 lr: 0.000077 grad: 0.0822 (0.0823) loss: 0.8640 (0.8672) time: 0.1500 data: 0.0789 max mem: 8299 +Train: [45] [2800/6250] eta: 0:07:26 lr: 0.000077 grad: 0.0818 (0.0823) loss: 0.8639 (0.8673) time: 0.1343 data: 0.0504 max mem: 8299 +Train: [45] [2900/6250] eta: 0:07:12 lr: 0.000077 grad: 0.0703 (0.0822) loss: 0.8659 (0.8673) time: 0.1202 data: 0.0404 max mem: 8299 +Train: [45] [3000/6250] eta: 0:06:59 lr: 0.000077 grad: 0.0773 (0.0821) loss: 0.8765 (0.8674) time: 0.1181 data: 0.0406 max mem: 8299 +Train: [45] [3100/6250] eta: 0:06:47 lr: 0.000077 grad: 0.0797 (0.0822) loss: 0.8755 (0.8674) time: 0.1286 data: 0.0581 max mem: 8299 +Train: [45] [3200/6250] eta: 0:06:34 lr: 0.000077 grad: 0.0795 (0.0822) loss: 0.8637 (0.8674) time: 0.1324 data: 0.0648 max mem: 8299 +Train: [45] [3300/6250] eta: 0:06:21 lr: 0.000077 grad: 0.0769 (0.0821) loss: 0.8718 (0.8676) time: 0.1347 data: 0.0631 max mem: 8299 +Train: [45] [3400/6250] eta: 0:06:08 lr: 0.000077 grad: 0.0768 (0.0820) loss: 0.8670 (0.8676) time: 0.1153 data: 0.0378 max mem: 8299 +Train: [45] [3500/6250] eta: 0:05:55 lr: 0.000077 grad: 0.0770 (0.0818) loss: 0.8699 (0.8677) time: 0.1358 data: 0.0681 max mem: 8299 +Train: [45] [3600/6250] eta: 0:05:42 lr: 0.000077 grad: 0.0793 (0.0817) loss: 0.8652 (0.8678) time: 0.1382 data: 0.0678 max mem: 8299 +Train: [45] [3700/6250] eta: 0:05:29 lr: 0.000077 grad: 0.0738 (0.0816) loss: 0.8672 (0.8679) time: 0.1356 data: 0.0533 max mem: 8299 +Train: [45] [3800/6250] eta: 0:05:16 lr: 0.000077 grad: 0.0720 (0.0816) loss: 0.8775 (0.8680) time: 0.1334 data: 0.0618 max mem: 8299 +Train: [45] [3900/6250] eta: 0:05:04 lr: 0.000077 grad: 0.0780 (0.0816) loss: 0.8654 (0.8681) time: 0.1176 data: 0.0384 max mem: 8299 +Train: [45] [4000/6250] eta: 0:04:51 lr: 0.000077 grad: 0.0761 (0.0815) loss: 0.8729 (0.8682) time: 0.1245 data: 0.0424 max mem: 8299 +Train: [45] [4100/6250] eta: 0:04:38 lr: 0.000077 grad: 0.0827 (0.0815) loss: 0.8660 (0.8682) time: 0.1386 data: 0.0642 max mem: 8299 +Train: [45] [4200/6250] eta: 0:04:25 lr: 0.000076 grad: 0.0784 (0.0815) loss: 0.8702 (0.8682) time: 0.1310 data: 0.0572 max mem: 8299 +Train: [45] [4300/6250] eta: 0:04:12 lr: 0.000076 grad: 0.0841 (0.0815) loss: 0.8693 (0.8682) time: 0.1288 data: 0.0605 max mem: 8299 +Train: [45] [4400/6250] eta: 0:03:59 lr: 0.000076 grad: 0.0754 (0.0816) loss: 0.8726 (0.8682) time: 0.1341 data: 0.0544 max mem: 8299 +Train: [45] [4500/6250] eta: 0:03:47 lr: 0.000076 grad: 0.0782 (0.0817) loss: 0.8691 (0.8682) time: 0.1308 data: 0.0536 max mem: 8299 +Train: [45] [4600/6250] eta: 0:03:34 lr: 0.000076 grad: 0.0877 (0.0818) loss: 0.8642 (0.8682) time: 0.1492 data: 0.0700 max mem: 8299 +Train: [45] [4700/6250] eta: 0:03:21 lr: 0.000076 grad: 0.0811 (0.0819) loss: 0.8636 (0.8681) time: 0.1065 data: 0.0369 max mem: 8299 +Train: [45] [4800/6250] eta: 0:03:08 lr: 0.000076 grad: 0.0783 (0.0819) loss: 0.8716 (0.8681) time: 0.1343 data: 0.0661 max mem: 8299 +Train: [45] [4900/6250] eta: 0:02:55 lr: 0.000076 grad: 0.0837 (0.0819) loss: 0.8696 (0.8680) time: 0.1310 data: 0.0588 max mem: 8299 +Train: [45] [5000/6250] eta: 0:02:42 lr: 0.000076 grad: 0.0797 (0.0820) loss: 0.8692 (0.8680) time: 0.1302 data: 0.0527 max mem: 8299 +Train: [45] [5100/6250] eta: 0:02:29 lr: 0.000076 grad: 0.0912 (0.0822) loss: 0.8605 (0.8679) time: 0.1313 data: 0.0489 max mem: 8299 +Train: [45] [5200/6250] eta: 0:02:17 lr: 0.000076 grad: 0.0797 (0.0822) loss: 0.8658 (0.8678) time: 0.1494 data: 0.0793 max mem: 8299 +Train: [45] [5300/6250] eta: 0:02:04 lr: 0.000076 grad: 0.0865 (0.0824) loss: 0.8579 (0.8677) time: 0.1509 data: 0.0681 max mem: 8299 +Train: [45] [5400/6250] eta: 0:01:51 lr: 0.000076 grad: 0.0872 (0.0824) loss: 0.8558 (0.8676) time: 0.1364 data: 0.0578 max mem: 8299 +Train: [45] [5500/6250] eta: 0:01:38 lr: 0.000076 grad: 0.0910 (0.0825) loss: 0.8595 (0.8675) time: 0.1367 data: 0.0565 max mem: 8299 +Train: [45] [5600/6250] eta: 0:01:25 lr: 0.000076 grad: 0.0800 (0.0826) loss: 0.8634 (0.8674) time: 0.1046 data: 0.0276 max mem: 8299 +Train: [45] [5700/6250] eta: 0:01:12 lr: 0.000076 grad: 0.0915 (0.0827) loss: 0.8598 (0.8673) time: 0.1284 data: 0.0518 max mem: 8299 +Train: [45] [5800/6250] eta: 0:00:58 lr: 0.000076 grad: 0.0847 (0.0828) loss: 0.8633 (0.8672) time: 0.1193 data: 0.0409 max mem: 8299 +Train: [45] [5900/6250] eta: 0:00:45 lr: 0.000076 grad: 0.0854 (0.0830) loss: 0.8635 (0.8672) time: 0.1081 data: 0.0290 max mem: 8299 +Train: [45] [6000/6250] eta: 0:00:32 lr: 0.000076 grad: 0.0845 (0.0831) loss: 0.8676 (0.8671) time: 0.1135 data: 0.0290 max mem: 8299 +Train: [45] [6100/6250] eta: 0:00:19 lr: 0.000076 grad: 0.0837 (0.0831) loss: 0.8649 (0.8671) time: 0.1471 data: 0.0718 max mem: 8299 +Train: [45] [6200/6250] eta: 0:00:06 lr: 0.000076 grad: 0.0820 (0.0832) loss: 0.8675 (0.8671) time: 0.1486 data: 0.0713 max mem: 8299 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0765 (0.0832) loss: 0.8703 (0.8671) time: 0.1368 data: 0.0611 max mem: 8299 +Train: [45] Total time: 0:13:43 (0.1318 s / it) +Averaged stats: lr: 0.000076 grad: 0.0765 (0.0832) loss: 0.8703 (0.8671) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:05:01 loss: 0.8986 (0.8986) time: 4.8552 data: 4.8222 max mem: 8299 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8866 (0.8875) time: 0.1134 data: 0.0887 max mem: 8299 +Eval (hcp-train-subset): [45] Total time: 0:00:13 (0.2159 s / it) +Averaged stats (hcp-train-subset): loss: 0.8866 (0.8875) +Eval (hcp-val): [45] [ 0/62] eta: 0:04:26 loss: 0.8854 (0.8854) time: 4.2974 data: 4.2113 max mem: 8299 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8844 (0.8859) time: 0.1102 data: 0.0848 max mem: 8299 +Eval (hcp-val): [45] Total time: 0:00:12 (0.2030 s / it) +Averaged stats (hcp-val): loss: 0.8844 (0.8859) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 6:21:56 lr: 0.000076 grad: 0.0515 (0.0515) loss: 0.9094 (0.9094) time: 3.6666 data: 3.5094 max mem: 8299 +Train: [46] [ 100/6250] eta: 0:19:11 lr: 0.000076 grad: 0.0625 (0.0786) loss: 0.8776 (0.8889) time: 0.1268 data: 0.0375 max mem: 8299 +Train: [46] [ 200/6250] eta: 0:16:24 lr: 0.000076 grad: 0.0765 (0.0826) loss: 0.8631 (0.8794) time: 0.1347 data: 0.0552 max mem: 8299 +Train: [46] [ 300/6250] eta: 0:14:49 lr: 0.000076 grad: 0.0695 (0.0813) loss: 0.8685 (0.8764) time: 0.1258 data: 0.0334 max mem: 8299 +Train: [46] [ 400/6250] eta: 0:13:53 lr: 0.000076 grad: 0.0671 (0.0793) loss: 0.8726 (0.8756) time: 0.1144 data: 0.0265 max mem: 8299 +Train: [46] [ 500/6250] eta: 0:13:14 lr: 0.000076 grad: 0.0659 (0.0773) loss: 0.8777 (0.8746) time: 0.1224 data: 0.0370 max mem: 8299 +Train: [46] [ 600/6250] eta: 0:12:47 lr: 0.000076 grad: 0.0646 (0.0757) loss: 0.8763 (0.8744) time: 0.1353 data: 0.0524 max mem: 8299 +Train: [46] [ 700/6250] eta: 0:12:29 lr: 0.000076 grad: 0.0666 (0.0751) loss: 0.8709 (0.8741) time: 0.1332 data: 0.0473 max mem: 8299 +Train: [46] [ 800/6250] eta: 0:12:13 lr: 0.000076 grad: 0.0645 (0.0749) loss: 0.8694 (0.8739) time: 0.1130 data: 0.0337 max mem: 8299 +Train: [46] [ 900/6250] eta: 0:12:02 lr: 0.000076 grad: 0.0709 (0.0744) loss: 0.8714 (0.8738) time: 0.1650 data: 0.0764 max mem: 8299 +Train: [46] [1000/6250] eta: 0:11:43 lr: 0.000076 grad: 0.0782 (0.0744) loss: 0.8703 (0.8734) time: 0.1230 data: 0.0405 max mem: 8299 +Train: [46] [1100/6250] eta: 0:11:25 lr: 0.000075 grad: 0.0676 (0.0743) loss: 0.8726 (0.8732) time: 0.1143 data: 0.0321 max mem: 8299 +Train: [46] [1200/6250] eta: 0:11:09 lr: 0.000075 grad: 0.0750 (0.0745) loss: 0.8652 (0.8726) time: 0.1079 data: 0.0203 max mem: 8299 +Train: [46] [1300/6250] eta: 0:10:54 lr: 0.000075 grad: 0.0762 (0.0747) loss: 0.8710 (0.8724) time: 0.1301 data: 0.0451 max mem: 8299 +Train: [46] [1400/6250] eta: 0:10:38 lr: 0.000075 grad: 0.0790 (0.0749) loss: 0.8581 (0.8718) time: 0.1104 data: 0.0236 max mem: 8299 +Train: [46] [1500/6250] eta: 0:10:24 lr: 0.000075 grad: 0.0751 (0.0750) loss: 0.8693 (0.8713) time: 0.1370 data: 0.0567 max mem: 8299 +Train: [46] [1600/6250] eta: 0:10:11 lr: 0.000075 grad: 0.0719 (0.0752) loss: 0.8688 (0.8708) time: 0.1331 data: 0.0513 max mem: 8299 +Train: [46] [1700/6250] eta: 0:09:56 lr: 0.000075 grad: 0.0793 (0.0756) loss: 0.8608 (0.8704) time: 0.1224 data: 0.0396 max mem: 8299 +Train: [46] [1800/6250] eta: 0:09:42 lr: 0.000075 grad: 0.0742 (0.0756) loss: 0.8665 (0.8701) time: 0.1465 data: 0.0704 max mem: 8299 +Train: [46] [1900/6250] eta: 0:09:27 lr: 0.000075 grad: 0.0781 (0.0758) loss: 0.8577 (0.8698) time: 0.1224 data: 0.0528 max mem: 8299 +Train: [46] [2000/6250] eta: 0:09:13 lr: 0.000075 grad: 0.0722 (0.0758) loss: 0.8661 (0.8696) time: 0.1212 data: 0.0419 max mem: 8299 +Train: [46] [2100/6250] eta: 0:09:01 lr: 0.000075 grad: 0.0782 (0.0760) loss: 0.8654 (0.8694) time: 0.1472 data: 0.0721 max mem: 8299 +Train: [46] [2200/6250] eta: 0:08:46 lr: 0.000075 grad: 0.0745 (0.0762) loss: 0.8693 (0.8692) time: 0.1239 data: 0.0514 max mem: 8299 +Train: [46] [2300/6250] eta: 0:08:34 lr: 0.000075 grad: 0.0724 (0.0763) loss: 0.8720 (0.8691) time: 0.1221 data: 0.0427 max mem: 8299 +Train: [46] [2400/6250] eta: 0:08:21 lr: 0.000075 grad: 0.0705 (0.0763) loss: 0.8715 (0.8690) time: 0.1303 data: 0.0502 max mem: 8299 +Train: [46] [2500/6250] eta: 0:08:07 lr: 0.000075 grad: 0.0733 (0.0764) loss: 0.8721 (0.8690) time: 0.1419 data: 0.0621 max mem: 8299 +Train: [46] [2600/6250] eta: 0:07:54 lr: 0.000075 grad: 0.0731 (0.0764) loss: 0.8673 (0.8690) time: 0.1087 data: 0.0237 max mem: 8299 +Train: [46] [2700/6250] eta: 0:07:41 lr: 0.000075 grad: 0.0782 (0.0766) loss: 0.8682 (0.8690) time: 0.1136 data: 0.0291 max mem: 8299 +Train: [46] [2800/6250] eta: 0:07:28 lr: 0.000075 grad: 0.0722 (0.0766) loss: 0.8730 (0.8690) time: 0.1355 data: 0.0557 max mem: 8299 +Train: [46] [2900/6250] eta: 0:07:15 lr: 0.000075 grad: 0.0774 (0.0768) loss: 0.8731 (0.8690) time: 0.1224 data: 0.0459 max mem: 8299 +Train: [46] [3000/6250] eta: 0:07:02 lr: 0.000075 grad: 0.0762 (0.0768) loss: 0.8699 (0.8689) time: 0.1191 data: 0.0494 max mem: 8299 +Train: [46] [3100/6250] eta: 0:06:49 lr: 0.000075 grad: 0.0756 (0.0769) loss: 0.8673 (0.8688) time: 0.1250 data: 0.0469 max mem: 8299 +Train: [46] [3200/6250] eta: 0:06:36 lr: 0.000075 grad: 0.0795 (0.0769) loss: 0.8627 (0.8687) time: 0.0998 data: 0.0074 max mem: 8299 +Train: [46] [3300/6250] eta: 0:06:24 lr: 0.000075 grad: 0.0777 (0.0770) loss: 0.8713 (0.8686) time: 0.1161 data: 0.0359 max mem: 8299 +Train: [46] [3400/6250] eta: 0:06:10 lr: 0.000075 grad: 0.0726 (0.0770) loss: 0.8664 (0.8685) time: 0.1151 data: 0.0427 max mem: 8299 +Train: [46] [3500/6250] eta: 0:05:58 lr: 0.000075 grad: 0.0749 (0.0771) loss: 0.8627 (0.8684) time: 0.1346 data: 0.0613 max mem: 8299 +Train: [46] [3600/6250] eta: 0:05:46 lr: 0.000075 grad: 0.0789 (0.0771) loss: 0.8665 (0.8684) time: 0.1587 data: 0.0853 max mem: 8299 +Train: [46] [3700/6250] eta: 0:05:33 lr: 0.000075 grad: 0.0768 (0.0772) loss: 0.8631 (0.8683) time: 0.1100 data: 0.0329 max mem: 8299 +Train: [46] [3800/6250] eta: 0:05:20 lr: 0.000075 grad: 0.0747 (0.0773) loss: 0.8665 (0.8682) time: 0.1447 data: 0.0519 max mem: 8299 +Train: [46] [3900/6250] eta: 0:05:07 lr: 0.000075 grad: 0.0758 (0.0774) loss: 0.8673 (0.8682) time: 0.1127 data: 0.0261 max mem: 8299 +Train: [46] [4000/6250] eta: 0:04:54 lr: 0.000075 grad: 0.0769 (0.0774) loss: 0.8696 (0.8681) time: 0.1480 data: 0.0770 max mem: 8299 +Train: [46] [4100/6250] eta: 0:04:41 lr: 0.000075 grad: 0.0805 (0.0775) loss: 0.8630 (0.8680) time: 0.1469 data: 0.0671 max mem: 8299 +Train: [46] [4200/6250] eta: 0:04:29 lr: 0.000074 grad: 0.0699 (0.0776) loss: 0.8681 (0.8680) time: 0.1501 data: 0.0734 max mem: 8299 +Train: [46] [4300/6250] eta: 0:04:15 lr: 0.000074 grad: 0.0830 (0.0776) loss: 0.8680 (0.8680) time: 0.1445 data: 0.0696 max mem: 8299 +Train: [46] [4400/6250] eta: 0:04:03 lr: 0.000074 grad: 0.0744 (0.0776) loss: 0.8631 (0.8679) time: 0.1292 data: 0.0447 max mem: 8299 +Train: [46] [4500/6250] eta: 0:03:49 lr: 0.000074 grad: 0.0851 (0.0777) loss: 0.8676 (0.8679) time: 0.1214 data: 0.0358 max mem: 8299 +Train: [46] [4600/6250] eta: 0:03:36 lr: 0.000074 grad: 0.0808 (0.0777) loss: 0.8626 (0.8678) time: 0.1311 data: 0.0374 max mem: 8299 +Train: [46] [4700/6250] eta: 0:03:22 lr: 0.000074 grad: 0.0776 (0.0778) loss: 0.8619 (0.8678) time: 0.1216 data: 0.0460 max mem: 8299 +Train: [46] [4800/6250] eta: 0:03:09 lr: 0.000074 grad: 0.0762 (0.0778) loss: 0.8631 (0.8677) time: 0.1138 data: 0.0424 max mem: 8299 +Train: [46] [4900/6250] eta: 0:02:56 lr: 0.000074 grad: 0.0771 (0.0778) loss: 0.8593 (0.8677) time: 0.0930 data: 0.0226 max mem: 8299 +Train: [46] [5000/6250] eta: 0:02:43 lr: 0.000074 grad: 0.0757 (0.0779) loss: 0.8671 (0.8677) time: 0.1105 data: 0.0194 max mem: 8299 +Train: [46] [5100/6250] eta: 0:02:30 lr: 0.000074 grad: 0.0773 (0.0780) loss: 0.8622 (0.8677) time: 0.1345 data: 0.0604 max mem: 8299 +Train: [46] [5200/6250] eta: 0:02:17 lr: 0.000074 grad: 0.0780 (0.0781) loss: 0.8618 (0.8676) time: 0.1325 data: 0.0574 max mem: 8299 +Train: [46] [5300/6250] eta: 0:02:04 lr: 0.000074 grad: 0.0804 (0.0781) loss: 0.8655 (0.8675) time: 0.1249 data: 0.0481 max mem: 8299 +Train: [46] [5400/6250] eta: 0:01:51 lr: 0.000074 grad: 0.0784 (0.0782) loss: 0.8619 (0.8673) time: 0.1425 data: 0.0729 max mem: 8299 +Train: [46] [5500/6250] eta: 0:01:38 lr: 0.000074 grad: 0.0869 (0.0783) loss: 0.8643 (0.8673) time: 0.1304 data: 0.0503 max mem: 8299 +Train: [46] [5600/6250] eta: 0:01:25 lr: 0.000074 grad: 0.0818 (0.0784) loss: 0.8655 (0.8672) time: 0.1172 data: 0.0449 max mem: 8299 +Train: [46] [5700/6250] eta: 0:01:12 lr: 0.000074 grad: 0.0838 (0.0785) loss: 0.8675 (0.8672) time: 0.1163 data: 0.0289 max mem: 8299 +Train: [46] [5800/6250] eta: 0:00:59 lr: 0.000074 grad: 0.0730 (0.0785) loss: 0.8708 (0.8671) time: 0.1150 data: 0.0223 max mem: 8299 +Train: [46] [5900/6250] eta: 0:00:45 lr: 0.000074 grad: 0.0856 (0.0787) loss: 0.8642 (0.8670) time: 0.1098 data: 0.0345 max mem: 8299 +Train: [46] [6000/6250] eta: 0:00:32 lr: 0.000074 grad: 0.0798 (0.0787) loss: 0.8686 (0.8670) time: 0.1278 data: 0.0433 max mem: 8299 +Train: [46] [6100/6250] eta: 0:00:19 lr: 0.000074 grad: 0.0846 (0.0788) loss: 0.8599 (0.8670) time: 0.1188 data: 0.0420 max mem: 8299 +Train: [46] [6200/6250] eta: 0:00:06 lr: 0.000074 grad: 0.0789 (0.0788) loss: 0.8652 (0.8670) time: 0.1323 data: 0.0563 max mem: 8299 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0813 (0.0789) loss: 0.8639 (0.8670) time: 0.1201 data: 0.0439 max mem: 8299 +Train: [46] Total time: 0:13:41 (0.1315 s / it) +Averaged stats: lr: 0.000074 grad: 0.0813 (0.0789) loss: 0.8639 (0.8670) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:27 loss: 0.9009 (0.9009) time: 3.3418 data: 3.2659 max mem: 8299 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8866 (0.8871) time: 0.1174 data: 0.0932 max mem: 8299 +Eval (hcp-train-subset): [46] Total time: 0:00:11 (0.1921 s / it) +Averaged stats (hcp-train-subset): loss: 0.8866 (0.8871) +Eval (hcp-val): [46] [ 0/62] eta: 0:03:05 loss: 0.8862 (0.8862) time: 2.9970 data: 2.9249 max mem: 8299 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8827 (0.8851) time: 0.1171 data: 0.0929 max mem: 8299 +Eval (hcp-val): [46] Total time: 0:00:12 (0.1942 s / it) +Averaged stats (hcp-val): loss: 0.8827 (0.8851) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 6:14:54 lr: 0.000074 grad: 0.0577 (0.0577) loss: 0.8752 (0.8752) time: 3.5991 data: 3.4031 max mem: 8299 +Train: [47] [ 100/6250] eta: 0:19:07 lr: 0.000074 grad: 0.0777 (0.0914) loss: 0.8752 (0.8756) time: 0.1459 data: 0.0526 max mem: 8299 +Train: [47] [ 200/6250] eta: 0:16:22 lr: 0.000074 grad: 0.0817 (0.0909) loss: 0.8767 (0.8718) time: 0.1098 data: 0.0242 max mem: 8299 +Train: [47] [ 300/6250] eta: 0:15:13 lr: 0.000074 grad: 0.0818 (0.0895) loss: 0.8677 (0.8700) time: 0.1387 data: 0.0581 max mem: 8299 +Train: [47] [ 400/6250] eta: 0:14:12 lr: 0.000074 grad: 0.0734 (0.0869) loss: 0.8648 (0.8696) time: 0.1222 data: 0.0360 max mem: 8299 +Train: [47] [ 500/6250] eta: 0:13:37 lr: 0.000074 grad: 0.0706 (0.0844) loss: 0.8720 (0.8699) time: 0.1034 data: 0.0232 max mem: 8299 +Train: [47] [ 600/6250] eta: 0:13:10 lr: 0.000074 grad: 0.0679 (0.0831) loss: 0.8774 (0.8702) time: 0.1222 data: 0.0275 max mem: 8299 +Train: [47] [ 700/6250] eta: 0:12:41 lr: 0.000074 grad: 0.0720 (0.0823) loss: 0.8686 (0.8704) time: 0.1331 data: 0.0495 max mem: 8299 +Train: [47] [ 800/6250] eta: 0:12:17 lr: 0.000074 grad: 0.0741 (0.0818) loss: 0.8683 (0.8702) time: 0.1328 data: 0.0528 max mem: 8299 +Train: [47] [ 900/6250] eta: 0:12:04 lr: 0.000074 grad: 0.0759 (0.0810) loss: 0.8745 (0.8703) time: 0.1431 data: 0.0590 max mem: 8299 +Train: [47] [1000/6250] eta: 0:11:48 lr: 0.000073 grad: 0.0823 (0.0805) loss: 0.8721 (0.8702) time: 0.1402 data: 0.0660 max mem: 8299 +Train: [47] [1100/6250] eta: 0:11:31 lr: 0.000073 grad: 0.0697 (0.0801) loss: 0.8661 (0.8699) time: 0.1360 data: 0.0497 max mem: 8299 +Train: [47] [1200/6250] eta: 0:11:12 lr: 0.000073 grad: 0.0807 (0.0799) loss: 0.8660 (0.8699) time: 0.1016 data: 0.0336 max mem: 8299 +Train: [47] [1300/6250] eta: 0:10:56 lr: 0.000073 grad: 0.0759 (0.0798) loss: 0.8691 (0.8697) time: 0.1333 data: 0.0621 max mem: 8299 +Train: [47] [1400/6250] eta: 0:10:42 lr: 0.000073 grad: 0.0773 (0.0798) loss: 0.8692 (0.8694) time: 0.1228 data: 0.0494 max mem: 8299 +Train: [47] [1500/6250] eta: 0:10:31 lr: 0.000073 grad: 0.0783 (0.0799) loss: 0.8743 (0.8690) time: 0.1379 data: 0.0613 max mem: 8299 +Train: [47] [1600/6250] eta: 0:10:16 lr: 0.000073 grad: 0.0796 (0.0805) loss: 0.8707 (0.8687) time: 0.1348 data: 0.0651 max mem: 8299 +Train: [47] [1700/6250] eta: 0:10:03 lr: 0.000073 grad: 0.0778 (0.0807) loss: 0.8658 (0.8683) time: 0.1268 data: 0.0584 max mem: 8299 +Train: [47] [1800/6250] eta: 0:09:50 lr: 0.000073 grad: 0.0793 (0.0811) loss: 0.8660 (0.8681) time: 0.0961 data: 0.0253 max mem: 8299 +Train: [47] [1900/6250] eta: 0:09:38 lr: 0.000073 grad: 0.0764 (0.0812) loss: 0.8694 (0.8679) time: 0.1347 data: 0.0638 max mem: 8299 +Train: [47] [2000/6250] eta: 0:09:22 lr: 0.000073 grad: 0.0853 (0.0814) loss: 0.8588 (0.8676) time: 0.1377 data: 0.0600 max mem: 8299 +Train: [47] [2100/6250] eta: 0:09:08 lr: 0.000073 grad: 0.0806 (0.0816) loss: 0.8622 (0.8674) time: 0.1101 data: 0.0343 max mem: 8299 +Train: [47] [2200/6250] eta: 0:08:54 lr: 0.000073 grad: 0.0800 (0.0816) loss: 0.8645 (0.8673) time: 0.1210 data: 0.0506 max mem: 8299 +Train: [47] [2300/6250] eta: 0:08:40 lr: 0.000073 grad: 0.0842 (0.0817) loss: 0.8640 (0.8672) time: 0.1249 data: 0.0400 max mem: 8299 +Train: [47] [2400/6250] eta: 0:08:28 lr: 0.000073 grad: 0.0795 (0.0817) loss: 0.8667 (0.8671) time: 0.1424 data: 0.0637 max mem: 8299 +Train: [47] [2500/6250] eta: 0:08:14 lr: 0.000073 grad: 0.0771 (0.0817) loss: 0.8671 (0.8671) time: 0.1343 data: 0.0603 max mem: 8299 +Train: [47] [2600/6250] eta: 0:08:01 lr: 0.000073 grad: 0.0712 (0.0816) loss: 0.8721 (0.8671) time: 0.1351 data: 0.0623 max mem: 8299 +Train: [47] [2700/6250] eta: 0:07:47 lr: 0.000073 grad: 0.0739 (0.0814) loss: 0.8724 (0.8672) time: 0.1238 data: 0.0386 max mem: 8299 +Train: [47] [2800/6250] eta: 0:07:35 lr: 0.000073 grad: 0.0766 (0.0814) loss: 0.8676 (0.8672) time: 0.1286 data: 0.0575 max mem: 8299 +Train: [47] [2900/6250] eta: 0:07:21 lr: 0.000073 grad: 0.0733 (0.0814) loss: 0.8708 (0.8672) time: 0.1125 data: 0.0354 max mem: 8299 +Train: [47] [3000/6250] eta: 0:07:08 lr: 0.000073 grad: 0.0744 (0.0814) loss: 0.8755 (0.8672) time: 0.1348 data: 0.0606 max mem: 8299 +Train: [47] [3100/6250] eta: 0:06:55 lr: 0.000073 grad: 0.0774 (0.0815) loss: 0.8692 (0.8671) time: 0.0982 data: 0.0225 max mem: 8299 +Train: [47] [3200/6250] eta: 0:06:43 lr: 0.000073 grad: 0.0745 (0.0814) loss: 0.8699 (0.8671) time: 0.1513 data: 0.0691 max mem: 8299 +Train: [47] [3300/6250] eta: 0:06:29 lr: 0.000073 grad: 0.0766 (0.0814) loss: 0.8697 (0.8671) time: 0.1261 data: 0.0479 max mem: 8299 +Train: [47] [3400/6250] eta: 0:06:16 lr: 0.000073 grad: 0.0856 (0.0814) loss: 0.8675 (0.8671) time: 0.0984 data: 0.0220 max mem: 8299 +Train: [47] [3500/6250] eta: 0:06:03 lr: 0.000073 grad: 0.0849 (0.0814) loss: 0.8577 (0.8670) time: 0.1332 data: 0.0664 max mem: 8299 +Train: [47] [3600/6250] eta: 0:05:49 lr: 0.000073 grad: 0.0780 (0.0814) loss: 0.8686 (0.8670) time: 0.1259 data: 0.0540 max mem: 8299 +Train: [47] [3700/6250] eta: 0:05:36 lr: 0.000073 grad: 0.0903 (0.0815) loss: 0.8686 (0.8670) time: 0.1389 data: 0.0636 max mem: 8299 +Train: [47] [3800/6250] eta: 0:05:23 lr: 0.000073 grad: 0.0837 (0.0815) loss: 0.8698 (0.8671) time: 0.1379 data: 0.0645 max mem: 8299 +Train: [47] [3900/6250] eta: 0:05:10 lr: 0.000073 grad: 0.0843 (0.0816) loss: 0.8653 (0.8670) time: 0.1496 data: 0.0656 max mem: 8299 +Train: [47] [4000/6250] eta: 0:04:56 lr: 0.000073 grad: 0.0837 (0.0817) loss: 0.8703 (0.8670) time: 0.1461 data: 0.0691 max mem: 8299 +Train: [47] [4100/6250] eta: 0:04:43 lr: 0.000072 grad: 0.0835 (0.0818) loss: 0.8651 (0.8669) time: 0.1084 data: 0.0253 max mem: 8299 +Train: [47] [4200/6250] eta: 0:04:30 lr: 0.000072 grad: 0.0812 (0.0818) loss: 0.8689 (0.8669) time: 0.1310 data: 0.0618 max mem: 8299 +Train: [47] [4300/6250] eta: 0:04:17 lr: 0.000072 grad: 0.0793 (0.0819) loss: 0.8626 (0.8668) time: 0.1243 data: 0.0550 max mem: 8299 +Train: [47] [4400/6250] eta: 0:04:03 lr: 0.000072 grad: 0.0850 (0.0820) loss: 0.8611 (0.8667) time: 0.1410 data: 0.0647 max mem: 8299 +Train: [47] [4500/6250] eta: 0:03:50 lr: 0.000072 grad: 0.0732 (0.0820) loss: 0.8688 (0.8667) time: 0.1365 data: 0.0548 max mem: 8299 +Train: [47] [4600/6250] eta: 0:03:37 lr: 0.000072 grad: 0.0840 (0.0821) loss: 0.8610 (0.8667) time: 0.1289 data: 0.0495 max mem: 8299 +Train: [47] [4700/6250] eta: 0:03:24 lr: 0.000072 grad: 0.0833 (0.0821) loss: 0.8762 (0.8666) time: 0.1434 data: 0.0759 max mem: 8299 +Train: [47] [4800/6250] eta: 0:03:11 lr: 0.000072 grad: 0.0759 (0.0821) loss: 0.8748 (0.8667) time: 0.1378 data: 0.0627 max mem: 8299 +Train: [47] [4900/6250] eta: 0:02:58 lr: 0.000072 grad: 0.0792 (0.0821) loss: 0.8679 (0.8667) time: 0.1324 data: 0.0673 max mem: 8299 +Train: [47] [5000/6250] eta: 0:02:44 lr: 0.000072 grad: 0.0804 (0.0823) loss: 0.8665 (0.8667) time: 0.1142 data: 0.0369 max mem: 8299 +Train: [47] [5100/6250] eta: 0:02:31 lr: 0.000072 grad: 0.0805 (0.0823) loss: 0.8641 (0.8666) time: 0.1308 data: 0.0583 max mem: 8299 +Train: [47] [5200/6250] eta: 0:02:18 lr: 0.000072 grad: 0.0777 (0.0823) loss: 0.8625 (0.8666) time: 0.1401 data: 0.0657 max mem: 8299 +Train: [47] [5300/6250] eta: 0:02:05 lr: 0.000072 grad: 0.0842 (0.0824) loss: 0.8618 (0.8665) time: 0.1379 data: 0.0611 max mem: 8299 +Train: [47] [5400/6250] eta: 0:01:52 lr: 0.000072 grad: 0.0770 (0.0825) loss: 0.8679 (0.8665) time: 0.1559 data: 0.0731 max mem: 8299 +Train: [47] [5500/6250] eta: 0:01:39 lr: 0.000072 grad: 0.0846 (0.0825) loss: 0.8699 (0.8665) time: 0.1405 data: 0.0681 max mem: 8299 +Train: [47] [5600/6250] eta: 0:01:26 lr: 0.000072 grad: 0.0810 (0.0826) loss: 0.8657 (0.8664) time: 0.1658 data: 0.0886 max mem: 8299 +Train: [47] [5700/6250] eta: 0:01:13 lr: 0.000072 grad: 0.0836 (0.0826) loss: 0.8581 (0.8664) time: 0.1347 data: 0.0445 max mem: 8299 +Train: [47] [5800/6250] eta: 0:00:59 lr: 0.000072 grad: 0.0883 (0.0827) loss: 0.8631 (0.8664) time: 0.1224 data: 0.0396 max mem: 8299 +Train: [47] [5900/6250] eta: 0:00:46 lr: 0.000072 grad: 0.0848 (0.0829) loss: 0.8659 (0.8663) time: 0.1344 data: 0.0457 max mem: 8299 +Train: [47] [6000/6250] eta: 0:00:33 lr: 0.000072 grad: 0.0894 (0.0829) loss: 0.8581 (0.8662) time: 0.1257 data: 0.0430 max mem: 8299 +Train: [47] [6100/6250] eta: 0:00:19 lr: 0.000072 grad: 0.0850 (0.0830) loss: 0.8649 (0.8661) time: 0.1271 data: 0.0409 max mem: 8299 +Train: [47] [6200/6250] eta: 0:00:06 lr: 0.000072 grad: 0.0925 (0.0831) loss: 0.8470 (0.8660) time: 0.1212 data: 0.0368 max mem: 8299 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0904 (0.0832) loss: 0.8641 (0.8659) time: 0.1237 data: 0.0463 max mem: 8299 +Train: [47] Total time: 0:13:49 (0.1327 s / it) +Averaged stats: lr: 0.000072 grad: 0.0904 (0.0832) loss: 0.8641 (0.8659) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:03:45 loss: 0.8974 (0.8974) time: 3.6398 data: 3.5706 max mem: 8299 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8861 (0.8857) time: 0.1282 data: 0.1038 max mem: 8299 +Eval (hcp-train-subset): [47] Total time: 0:00:13 (0.2126 s / it) +Averaged stats (hcp-train-subset): loss: 0.8861 (0.8857) +Eval (hcp-val): [47] [ 0/62] eta: 0:03:25 loss: 0.8836 (0.8836) time: 3.3135 data: 3.2371 max mem: 8299 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8845 (0.8847) time: 0.1268 data: 0.1013 max mem: 8299 +Eval (hcp-val): [47] Total time: 0:00:12 (0.1972 s / it) +Averaged stats (hcp-val): loss: 0.8845 (0.8847) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 9:14:49 lr: 0.000072 grad: 0.1809 (0.1809) loss: 0.8868 (0.8868) time: 5.3263 data: 5.2237 max mem: 8299 +Train: [48] [ 100/6250] eta: 0:18:54 lr: 0.000072 grad: 0.0768 (0.0887) loss: 0.8688 (0.8766) time: 0.1235 data: 0.0300 max mem: 8299 +Train: [48] [ 200/6250] eta: 0:16:31 lr: 0.000072 grad: 0.0757 (0.0857) loss: 0.8708 (0.8747) time: 0.1504 data: 0.0596 max mem: 8299 +Train: [48] [ 300/6250] eta: 0:15:16 lr: 0.000072 grad: 0.0751 (0.0826) loss: 0.8753 (0.8750) time: 0.1379 data: 0.0499 max mem: 8299 +Train: [48] [ 400/6250] eta: 0:14:18 lr: 0.000072 grad: 0.0697 (0.0807) loss: 0.8762 (0.8751) time: 0.1242 data: 0.0278 max mem: 8299 +Train: [48] [ 500/6250] eta: 0:13:40 lr: 0.000072 grad: 0.0745 (0.0808) loss: 0.8722 (0.8746) time: 0.1132 data: 0.0332 max mem: 8299 +Train: [48] [ 600/6250] eta: 0:13:07 lr: 0.000072 grad: 0.0711 (0.0802) loss: 0.8678 (0.8738) time: 0.1354 data: 0.0600 max mem: 8299 +Train: [48] [ 700/6250] eta: 0:12:44 lr: 0.000072 grad: 0.0772 (0.0802) loss: 0.8621 (0.8730) time: 0.1233 data: 0.0486 max mem: 8299 +Train: [48] [ 800/6250] eta: 0:12:29 lr: 0.000072 grad: 0.0801 (0.0800) loss: 0.8692 (0.8727) time: 0.1523 data: 0.0726 max mem: 8299 +Train: [48] [ 900/6250] eta: 0:12:14 lr: 0.000071 grad: 0.0723 (0.0797) loss: 0.8720 (0.8725) time: 0.1302 data: 0.0533 max mem: 8299 +Train: [48] [1000/6250] eta: 0:11:56 lr: 0.000071 grad: 0.0684 (0.0790) loss: 0.8711 (0.8725) time: 0.1235 data: 0.0363 max mem: 8299 +Train: [48] [1100/6250] eta: 0:11:41 lr: 0.000071 grad: 0.0704 (0.0787) loss: 0.8713 (0.8722) time: 0.1234 data: 0.0342 max mem: 8299 +Train: [48] [1200/6250] eta: 0:11:30 lr: 0.000071 grad: 0.0705 (0.0783) loss: 0.8662 (0.8719) time: 0.1433 data: 0.0643 max mem: 8299 +Train: [48] [1300/6250] eta: 0:11:14 lr: 0.000071 grad: 0.0733 (0.0782) loss: 0.8700 (0.8716) time: 0.1201 data: 0.0422 max mem: 8299 +Train: [48] [1400/6250] eta: 0:11:02 lr: 0.000071 grad: 0.0693 (0.0779) loss: 0.8670 (0.8715) time: 0.1231 data: 0.0495 max mem: 8299 +Train: [48] [1500/6250] eta: 0:10:47 lr: 0.000071 grad: 0.0797 (0.0780) loss: 0.8668 (0.8712) time: 0.1266 data: 0.0529 max mem: 8299 +Train: [48] [1600/6250] eta: 0:10:30 lr: 0.000071 grad: 0.0797 (0.0780) loss: 0.8643 (0.8710) time: 0.1335 data: 0.0403 max mem: 8299 +Train: [48] [1700/6250] eta: 0:10:12 lr: 0.000071 grad: 0.0740 (0.0778) loss: 0.8689 (0.8709) time: 0.1239 data: 0.0461 max mem: 8299 +Train: [48] [1800/6250] eta: 0:09:56 lr: 0.000071 grad: 0.0760 (0.0779) loss: 0.8700 (0.8708) time: 0.1229 data: 0.0367 max mem: 8299 +Train: [48] [1900/6250] eta: 0:09:40 lr: 0.000071 grad: 0.0733 (0.0781) loss: 0.8742 (0.8707) time: 0.1313 data: 0.0476 max mem: 8299 +Train: [48] [2000/6250] eta: 0:09:26 lr: 0.000071 grad: 0.0729 (0.0782) loss: 0.8750 (0.8707) time: 0.1273 data: 0.0488 max mem: 8299 +Train: [48] [2100/6250] eta: 0:09:11 lr: 0.000071 grad: 0.0768 (0.0782) loss: 0.8683 (0.8706) time: 0.1483 data: 0.0675 max mem: 8299 +Train: [48] [2200/6250] eta: 0:08:56 lr: 0.000071 grad: 0.0750 (0.0782) loss: 0.8681 (0.8706) time: 0.1109 data: 0.0301 max mem: 8299 +Train: [48] [2300/6250] eta: 0:08:42 lr: 0.000071 grad: 0.0818 (0.0784) loss: 0.8675 (0.8705) time: 0.1185 data: 0.0438 max mem: 8299 +Train: [48] [2400/6250] eta: 0:08:29 lr: 0.000071 grad: 0.0768 (0.0785) loss: 0.8691 (0.8703) time: 0.1581 data: 0.0809 max mem: 8299 +Train: [48] [2500/6250] eta: 0:08:16 lr: 0.000071 grad: 0.0814 (0.0786) loss: 0.8668 (0.8701) time: 0.1383 data: 0.0521 max mem: 8299 +Train: [48] [2600/6250] eta: 0:08:01 lr: 0.000071 grad: 0.0796 (0.0787) loss: 0.8688 (0.8700) time: 0.1326 data: 0.0547 max mem: 8299 +Train: [48] [2700/6250] eta: 0:07:48 lr: 0.000071 grad: 0.0763 (0.0787) loss: 0.8697 (0.8699) time: 0.1364 data: 0.0608 max mem: 8299 +Train: [48] [2800/6250] eta: 0:07:34 lr: 0.000071 grad: 0.0768 (0.0787) loss: 0.8718 (0.8699) time: 0.1254 data: 0.0374 max mem: 8299 +Train: [48] [2900/6250] eta: 0:07:21 lr: 0.000071 grad: 0.0736 (0.0787) loss: 0.8715 (0.8699) time: 0.1454 data: 0.0621 max mem: 8299 +Train: [48] [3000/6250] eta: 0:07:08 lr: 0.000071 grad: 0.0753 (0.0787) loss: 0.8687 (0.8698) time: 0.1412 data: 0.0628 max mem: 8299 +Train: [48] [3100/6250] eta: 0:06:54 lr: 0.000071 grad: 0.0795 (0.0788) loss: 0.8638 (0.8697) time: 0.1297 data: 0.0506 max mem: 8299 +Train: [48] [3200/6250] eta: 0:06:41 lr: 0.000071 grad: 0.0780 (0.0788) loss: 0.8743 (0.8697) time: 0.1321 data: 0.0569 max mem: 8299 +Train: [48] [3300/6250] eta: 0:06:27 lr: 0.000071 grad: 0.0854 (0.0790) loss: 0.8640 (0.8695) time: 0.1210 data: 0.0476 max mem: 8299 +Train: [48] [3400/6250] eta: 0:06:14 lr: 0.000071 grad: 0.0832 (0.0791) loss: 0.8656 (0.8694) time: 0.1276 data: 0.0442 max mem: 8299 +Train: [48] [3500/6250] eta: 0:06:01 lr: 0.000071 grad: 0.0825 (0.0793) loss: 0.8672 (0.8693) time: 0.1325 data: 0.0530 max mem: 8299 +Train: [48] [3600/6250] eta: 0:05:48 lr: 0.000071 grad: 0.0851 (0.0794) loss: 0.8637 (0.8692) time: 0.1271 data: 0.0552 max mem: 8299 +Train: [48] [3700/6250] eta: 0:05:35 lr: 0.000071 grad: 0.0872 (0.0796) loss: 0.8618 (0.8690) time: 0.1359 data: 0.0559 max mem: 8299 +Train: [48] [3800/6250] eta: 0:05:22 lr: 0.000071 grad: 0.0819 (0.0797) loss: 0.8650 (0.8689) time: 0.1467 data: 0.0771 max mem: 8299 +Train: [48] [3900/6250] eta: 0:05:09 lr: 0.000070 grad: 0.0790 (0.0798) loss: 0.8660 (0.8688) time: 0.1333 data: 0.0466 max mem: 8299 +Train: [48] [4000/6250] eta: 0:04:55 lr: 0.000070 grad: 0.0789 (0.0799) loss: 0.8600 (0.8688) time: 0.0975 data: 0.0204 max mem: 8299 +Train: [48] [4100/6250] eta: 0:04:42 lr: 0.000070 grad: 0.0776 (0.0800) loss: 0.8670 (0.8687) time: 0.1253 data: 0.0520 max mem: 8299 +Train: [48] [4200/6250] eta: 0:04:29 lr: 0.000070 grad: 0.0808 (0.0801) loss: 0.8679 (0.8686) time: 0.1490 data: 0.0725 max mem: 8299 +Train: [48] [4300/6250] eta: 0:04:16 lr: 0.000070 grad: 0.0837 (0.0802) loss: 0.8636 (0.8686) time: 0.1372 data: 0.0615 max mem: 8299 +Train: [48] [4400/6250] eta: 0:04:03 lr: 0.000070 grad: 0.0867 (0.0803) loss: 0.8638 (0.8684) time: 0.1363 data: 0.0548 max mem: 8299 +Train: [48] [4500/6250] eta: 0:03:50 lr: 0.000070 grad: 0.0840 (0.0804) loss: 0.8607 (0.8684) time: 0.1316 data: 0.0459 max mem: 8299 +Train: [48] [4600/6250] eta: 0:03:37 lr: 0.000070 grad: 0.0872 (0.0806) loss: 0.8639 (0.8682) time: 0.1370 data: 0.0540 max mem: 8299 +Train: [48] [4700/6250] eta: 0:03:23 lr: 0.000070 grad: 0.0838 (0.0807) loss: 0.8637 (0.8682) time: 0.1431 data: 0.0669 max mem: 8299 +Train: [48] [4800/6250] eta: 0:03:10 lr: 0.000070 grad: 0.0832 (0.0808) loss: 0.8659 (0.8680) time: 0.1363 data: 0.0664 max mem: 8299 +Train: [48] [4900/6250] eta: 0:02:57 lr: 0.000070 grad: 0.0831 (0.0809) loss: 0.8595 (0.8679) time: 0.1387 data: 0.0652 max mem: 8299 +Train: [48] [5000/6250] eta: 0:02:44 lr: 0.000070 grad: 0.0861 (0.0811) loss: 0.8588 (0.8677) time: 0.1342 data: 0.0581 max mem: 8299 +Train: [48] [5100/6250] eta: 0:02:31 lr: 0.000070 grad: 0.0785 (0.0812) loss: 0.8610 (0.8675) time: 0.1593 data: 0.0826 max mem: 8299 +Train: [48] [5200/6250] eta: 0:02:18 lr: 0.000070 grad: 0.0801 (0.0812) loss: 0.8628 (0.8674) time: 0.1172 data: 0.0467 max mem: 8299 +Train: [48] [5300/6250] eta: 0:02:05 lr: 0.000070 grad: 0.0795 (0.0813) loss: 0.8606 (0.8673) time: 0.1412 data: 0.0642 max mem: 8299 +Train: [48] [5400/6250] eta: 0:01:52 lr: 0.000070 grad: 0.0786 (0.0814) loss: 0.8623 (0.8672) time: 0.1179 data: 0.0458 max mem: 8299 +Train: [48] [5500/6250] eta: 0:01:39 lr: 0.000070 grad: 0.0822 (0.0815) loss: 0.8632 (0.8671) time: 0.1300 data: 0.0485 max mem: 8299 +Train: [48] [5600/6250] eta: 0:01:26 lr: 0.000070 grad: 0.0815 (0.0815) loss: 0.8641 (0.8670) time: 0.1185 data: 0.0410 max mem: 8299 +Train: [48] [5700/6250] eta: 0:01:12 lr: 0.000070 grad: 0.0859 (0.0816) loss: 0.8604 (0.8669) time: 0.1749 data: 0.0902 max mem: 8299 +Train: [48] [5800/6250] eta: 0:00:59 lr: 0.000070 grad: 0.0817 (0.0817) loss: 0.8600 (0.8668) time: 0.1433 data: 0.0728 max mem: 8299 +Train: [48] [5900/6250] eta: 0:00:46 lr: 0.000070 grad: 0.0758 (0.0817) loss: 0.8662 (0.8667) time: 0.1324 data: 0.0496 max mem: 8299 +Train: [48] [6000/6250] eta: 0:00:33 lr: 0.000070 grad: 0.0809 (0.0817) loss: 0.8619 (0.8666) time: 0.1167 data: 0.0252 max mem: 8299 +Train: [48] [6100/6250] eta: 0:00:19 lr: 0.000070 grad: 0.0750 (0.0818) loss: 0.8619 (0.8666) time: 0.1196 data: 0.0283 max mem: 8299 +Train: [48] [6200/6250] eta: 0:00:06 lr: 0.000070 grad: 0.0813 (0.0818) loss: 0.8636 (0.8665) time: 0.1273 data: 0.0483 max mem: 8299 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.0845 (0.0818) loss: 0.8570 (0.8665) time: 0.1098 data: 0.0319 max mem: 8299 +Train: [48] Total time: 0:13:49 (0.1327 s / it) +Averaged stats: lr: 0.000070 grad: 0.0845 (0.0818) loss: 0.8570 (0.8665) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:05:20 loss: 0.9041 (0.9041) time: 5.1694 data: 5.1397 max mem: 8299 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8863 (0.8888) time: 0.1308 data: 0.1064 max mem: 8299 +Eval (hcp-train-subset): [48] Total time: 0:00:13 (0.2151 s / it) +Averaged stats (hcp-train-subset): loss: 0.8863 (0.8888) +Eval (hcp-val): [48] [ 0/62] eta: 0:03:42 loss: 0.8835 (0.8835) time: 3.5823 data: 3.4773 max mem: 8299 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8856 (0.8858) time: 0.1111 data: 0.0868 max mem: 8299 +Eval (hcp-val): [48] Total time: 0:00:12 (0.1995 s / it) +Averaged stats (hcp-val): loss: 0.8856 (0.8858) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 8:19:03 lr: 0.000070 grad: 0.0942 (0.0942) loss: 0.8857 (0.8857) time: 4.7910 data: 4.6597 max mem: 8299 +Train: [49] [ 100/6250] eta: 0:18:17 lr: 0.000070 grad: 0.0735 (0.0986) loss: 0.8832 (0.8798) time: 0.1411 data: 0.0440 max mem: 8299 +Train: [49] [ 200/6250] eta: 0:15:46 lr: 0.000070 grad: 0.0747 (0.0906) loss: 0.8783 (0.8796) time: 0.1084 data: 0.0162 max mem: 8299 +Train: [49] [ 300/6250] eta: 0:14:37 lr: 0.000070 grad: 0.0722 (0.0879) loss: 0.8707 (0.8760) time: 0.1217 data: 0.0370 max mem: 8299 +Train: [49] [ 400/6250] eta: 0:13:52 lr: 0.000070 grad: 0.0743 (0.0867) loss: 0.8691 (0.8732) time: 0.1313 data: 0.0395 max mem: 8299 +Train: [49] [ 500/6250] eta: 0:13:19 lr: 0.000070 grad: 0.0821 (0.0863) loss: 0.8690 (0.8711) time: 0.1279 data: 0.0503 max mem: 8299 +Train: [49] [ 600/6250] eta: 0:12:52 lr: 0.000070 grad: 0.0763 (0.0859) loss: 0.8624 (0.8701) time: 0.1182 data: 0.0443 max mem: 8299 +Train: [49] [ 700/6250] eta: 0:12:26 lr: 0.000069 grad: 0.0811 (0.0853) loss: 0.8640 (0.8698) time: 0.1290 data: 0.0462 max mem: 8299 +Train: [49] [ 800/6250] eta: 0:12:09 lr: 0.000069 grad: 0.0838 (0.0848) loss: 0.8695 (0.8696) time: 0.1398 data: 0.0642 max mem: 8299 +Train: [49] [ 900/6250] eta: 0:11:54 lr: 0.000069 grad: 0.0799 (0.0844) loss: 0.8675 (0.8694) time: 0.1308 data: 0.0409 max mem: 8299 +Train: [49] [1000/6250] eta: 0:11:37 lr: 0.000069 grad: 0.0760 (0.0841) loss: 0.8610 (0.8690) time: 0.0944 data: 0.0167 max mem: 8299 +Train: [49] [1100/6250] eta: 0:11:18 lr: 0.000069 grad: 0.0841 (0.0841) loss: 0.8663 (0.8683) time: 0.1107 data: 0.0409 max mem: 8299 +Train: [49] [1200/6250] eta: 0:11:00 lr: 0.000069 grad: 0.0765 (0.0839) loss: 0.8779 (0.8680) time: 0.1003 data: 0.0211 max mem: 8299 +Train: [49] [1300/6250] eta: 0:10:48 lr: 0.000069 grad: 0.0874 (0.0840) loss: 0.8634 (0.8676) time: 0.1384 data: 0.0544 max mem: 8299 +Train: [49] [1400/6250] eta: 0:10:32 lr: 0.000069 grad: 0.0797 (0.0840) loss: 0.8672 (0.8674) time: 0.1121 data: 0.0324 max mem: 8299 +Train: [49] [1500/6250] eta: 0:10:20 lr: 0.000069 grad: 0.0849 (0.0841) loss: 0.8663 (0.8671) time: 0.1320 data: 0.0605 max mem: 8299 +Train: [49] [1600/6250] eta: 0:10:06 lr: 0.000069 grad: 0.0809 (0.0841) loss: 0.8698 (0.8670) time: 0.1271 data: 0.0564 max mem: 8299 +Train: [49] [1700/6250] eta: 0:09:53 lr: 0.000069 grad: 0.0869 (0.0840) loss: 0.8644 (0.8669) time: 0.1235 data: 0.0435 max mem: 8299 +Train: [49] [1800/6250] eta: 0:09:41 lr: 0.000069 grad: 0.0844 (0.0841) loss: 0.8682 (0.8667) time: 0.1481 data: 0.0716 max mem: 8299 +Train: [49] [1900/6250] eta: 0:09:30 lr: 0.000069 grad: 0.0849 (0.0841) loss: 0.8626 (0.8665) time: 0.1315 data: 0.0481 max mem: 8299 +Train: [49] [2000/6250] eta: 0:09:17 lr: 0.000069 grad: 0.0800 (0.0840) loss: 0.8713 (0.8664) time: 0.1379 data: 0.0694 max mem: 8299 +Train: [49] [2100/6250] eta: 0:09:03 lr: 0.000069 grad: 0.0777 (0.0842) loss: 0.8657 (0.8664) time: 0.1305 data: 0.0566 max mem: 8299 +Train: [49] [2200/6250] eta: 0:08:49 lr: 0.000069 grad: 0.0820 (0.0842) loss: 0.8709 (0.8664) time: 0.1244 data: 0.0457 max mem: 8299 +Train: [49] [2300/6250] eta: 0:08:35 lr: 0.000069 grad: 0.0823 (0.0842) loss: 0.8699 (0.8664) time: 0.1144 data: 0.0316 max mem: 8299 +Train: [49] [2400/6250] eta: 0:08:23 lr: 0.000069 grad: 0.0804 (0.0842) loss: 0.8669 (0.8664) time: 0.1491 data: 0.0692 max mem: 8299 +Train: [49] [2500/6250] eta: 0:08:10 lr: 0.000069 grad: 0.0822 (0.0843) loss: 0.8679 (0.8665) time: 0.1342 data: 0.0412 max mem: 8299 +Train: [49] [2600/6250] eta: 0:07:56 lr: 0.000069 grad: 0.0809 (0.0843) loss: 0.8662 (0.8665) time: 0.1110 data: 0.0379 max mem: 8299 +Train: [49] [2700/6250] eta: 0:07:43 lr: 0.000069 grad: 0.0817 (0.0845) loss: 0.8577 (0.8664) time: 0.1438 data: 0.0638 max mem: 8299 +Train: [49] [2800/6250] eta: 0:07:31 lr: 0.000069 grad: 0.0822 (0.0845) loss: 0.8661 (0.8664) time: 0.1567 data: 0.0804 max mem: 8299 +Train: [49] [2900/6250] eta: 0:07:17 lr: 0.000069 grad: 0.0829 (0.0845) loss: 0.8700 (0.8664) time: 0.1296 data: 0.0517 max mem: 8299 +Train: [49] [3000/6250] eta: 0:07:04 lr: 0.000069 grad: 0.0772 (0.0845) loss: 0.8696 (0.8664) time: 0.1265 data: 0.0492 max mem: 8299 +Train: [49] [3100/6250] eta: 0:06:50 lr: 0.000069 grad: 0.0808 (0.0845) loss: 0.8661 (0.8664) time: 0.1160 data: 0.0320 max mem: 8299 +Train: [49] [3200/6250] eta: 0:06:39 lr: 0.000069 grad: 0.0764 (0.0845) loss: 0.8700 (0.8664) time: 0.1272 data: 0.0535 max mem: 8299 +Train: [49] [3300/6250] eta: 0:06:25 lr: 0.000069 grad: 0.0786 (0.0844) loss: 0.8626 (0.8663) time: 0.1324 data: 0.0666 max mem: 8299 +Train: [49] [3400/6250] eta: 0:06:12 lr: 0.000069 grad: 0.0806 (0.0844) loss: 0.8642 (0.8663) time: 0.1271 data: 0.0413 max mem: 8299 +Train: [49] [3500/6250] eta: 0:06:00 lr: 0.000069 grad: 0.0869 (0.0845) loss: 0.8613 (0.8662) time: 0.1701 data: 0.0973 max mem: 8299 +Train: [49] [3600/6250] eta: 0:05:46 lr: 0.000069 grad: 0.0818 (0.0845) loss: 0.8627 (0.8662) time: 0.1239 data: 0.0427 max mem: 8299 +Train: [49] [3700/6250] eta: 0:05:33 lr: 0.000069 grad: 0.0771 (0.0845) loss: 0.8638 (0.8661) time: 0.1421 data: 0.0707 max mem: 8299 +Train: [49] [3800/6250] eta: 0:05:20 lr: 0.000068 grad: 0.0758 (0.0844) loss: 0.8640 (0.8660) time: 0.0850 data: 0.0039 max mem: 8299 +Train: [49] [3900/6250] eta: 0:05:07 lr: 0.000068 grad: 0.0847 (0.0845) loss: 0.8584 (0.8659) time: 0.1439 data: 0.0871 max mem: 8299 +Train: [49] [4000/6250] eta: 0:04:54 lr: 0.000068 grad: 0.0811 (0.0845) loss: 0.8623 (0.8659) time: 0.1300 data: 0.0563 max mem: 8299 +Train: [49] [4100/6250] eta: 0:04:41 lr: 0.000068 grad: 0.0802 (0.0846) loss: 0.8619 (0.8659) time: 0.1231 data: 0.0531 max mem: 8299 +Train: [49] [4200/6250] eta: 0:04:28 lr: 0.000068 grad: 0.0873 (0.0846) loss: 0.8694 (0.8659) time: 0.1324 data: 0.0599 max mem: 8299 +Train: [49] [4300/6250] eta: 0:04:16 lr: 0.000068 grad: 0.0820 (0.0847) loss: 0.8700 (0.8659) time: 0.1800 data: 0.1022 max mem: 8299 +Train: [49] [4400/6250] eta: 0:04:03 lr: 0.000068 grad: 0.0835 (0.0847) loss: 0.8684 (0.8659) time: 0.1463 data: 0.0762 max mem: 8299 +Train: [49] [4500/6250] eta: 0:03:50 lr: 0.000068 grad: 0.0883 (0.0847) loss: 0.8655 (0.8658) time: 0.1403 data: 0.0689 max mem: 8299 +Train: [49] [4600/6250] eta: 0:03:37 lr: 0.000068 grad: 0.0780 (0.0847) loss: 0.8713 (0.8658) time: 0.1374 data: 0.0641 max mem: 8299 +Train: [49] [4700/6250] eta: 0:03:24 lr: 0.000068 grad: 0.0825 (0.0846) loss: 0.8688 (0.8658) time: 0.1291 data: 0.0492 max mem: 8299 +Train: [49] [4800/6250] eta: 0:03:10 lr: 0.000068 grad: 0.0802 (0.0846) loss: 0.8690 (0.8657) time: 0.1164 data: 0.0415 max mem: 8299 +Train: [49] [4900/6250] eta: 0:02:57 lr: 0.000068 grad: 0.0880 (0.0847) loss: 0.8682 (0.8658) time: 0.1366 data: 0.0716 max mem: 8299 +Train: [49] [5000/6250] eta: 0:02:44 lr: 0.000068 grad: 0.0849 (0.0848) loss: 0.8638 (0.8657) time: 0.1118 data: 0.0432 max mem: 8299 +Train: [49] [5100/6250] eta: 0:02:31 lr: 0.000068 grad: 0.0896 (0.0849) loss: 0.8620 (0.8657) time: 0.1288 data: 0.0557 max mem: 8299 +Train: [49] [5200/6250] eta: 0:02:18 lr: 0.000068 grad: 0.0822 (0.0849) loss: 0.8679 (0.8656) time: 0.1230 data: 0.0507 max mem: 8299 +Train: [49] [5300/6250] eta: 0:02:04 lr: 0.000068 grad: 0.0823 (0.0850) loss: 0.8628 (0.8656) time: 0.1234 data: 0.0557 max mem: 8299 +Train: [49] [5400/6250] eta: 0:01:51 lr: 0.000068 grad: 0.0852 (0.0850) loss: 0.8630 (0.8655) time: 0.1341 data: 0.0695 max mem: 8299 +Train: [49] [5500/6250] eta: 0:01:38 lr: 0.000068 grad: 0.0871 (0.0851) loss: 0.8611 (0.8655) time: 0.1202 data: 0.0505 max mem: 8299 +Train: [49] [5600/6250] eta: 0:01:25 lr: 0.000068 grad: 0.0778 (0.0851) loss: 0.8658 (0.8655) time: 0.1299 data: 0.0612 max mem: 8299 +Train: [49] [5700/6250] eta: 0:01:11 lr: 0.000068 grad: 0.0810 (0.0851) loss: 0.8558 (0.8654) time: 0.1367 data: 0.0658 max mem: 8299 +Train: [49] [5800/6250] eta: 0:00:58 lr: 0.000068 grad: 0.0784 (0.0851) loss: 0.8618 (0.8654) time: 0.0968 data: 0.0222 max mem: 8299 +Train: [49] [5900/6250] eta: 0:00:45 lr: 0.000068 grad: 0.0889 (0.0853) loss: 0.8635 (0.8653) time: 0.1301 data: 0.0573 max mem: 8299 +Train: [49] [6000/6250] eta: 0:00:32 lr: 0.000068 grad: 0.0786 (0.0857) loss: 0.8579 (0.8652) time: 0.1332 data: 0.0685 max mem: 8299 +Train: [49] [6100/6250] eta: 0:00:19 lr: 0.000068 grad: 0.0785 (0.0857) loss: 0.8622 (0.8651) time: 0.1136 data: 0.0421 max mem: 8299 +Train: [49] [6200/6250] eta: 0:00:06 lr: 0.000068 grad: 0.0826 (0.0857) loss: 0.8625 (0.8651) time: 0.1216 data: 0.0557 max mem: 8299 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0835 (0.0857) loss: 0.8579 (0.8650) time: 0.0893 data: 0.0108 max mem: 8299 +Train: [49] Total time: 0:13:36 (0.1306 s / it) +Averaged stats: lr: 0.000068 grad: 0.0835 (0.0857) loss: 0.8579 (0.8650) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:02:53 loss: 0.8987 (0.8987) time: 2.8028 data: 2.7376 max mem: 8299 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8837 (0.8847) time: 0.0940 data: 0.0699 max mem: 8299 +Eval (hcp-train-subset): [49] Total time: 0:00:11 (0.1822 s / it) +Averaged stats (hcp-train-subset): loss: 0.8837 (0.8847) +Making plots (hcp-train-subset): example=33 +Eval (hcp-val): [49] [ 0/62] eta: 0:04:30 loss: 0.8821 (0.8821) time: 4.3687 data: 4.3397 max mem: 8299 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8819 (0.8846) time: 0.0899 data: 0.0647 max mem: 8299 +Eval (hcp-val): [49] Total time: 0:00:10 (0.1687 s / it) +Averaged stats (hcp-val): loss: 0.8819 (0.8846) +Making plots (hcp-val): example=47 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 7:52:55 lr: 0.000068 grad: 0.1526 (0.1526) loss: 0.9021 (0.9021) time: 4.5401 data: 4.4219 max mem: 8299 +Train: [50] [ 100/6250] eta: 0:16:26 lr: 0.000068 grad: 0.0722 (0.0945) loss: 0.8801 (0.8820) time: 0.1297 data: 0.0420 max mem: 8299 +Train: [50] [ 200/6250] eta: 0:14:15 lr: 0.000068 grad: 0.0722 (0.0865) loss: 0.8702 (0.8793) time: 0.1123 data: 0.0421 max mem: 8299 +Train: [50] [ 300/6250] eta: 0:13:15 lr: 0.000068 grad: 0.0728 (0.0834) loss: 0.8729 (0.8779) time: 0.1232 data: 0.0510 max mem: 8299 +Train: [50] [ 400/6250] eta: 0:12:42 lr: 0.000068 grad: 0.0810 (0.0831) loss: 0.8690 (0.8759) time: 0.1251 data: 0.0556 max mem: 8299 +Train: [50] [ 500/6250] eta: 0:12:15 lr: 0.000067 grad: 0.0773 (0.0822) loss: 0.8731 (0.8748) time: 0.1402 data: 0.0694 max mem: 8299 +Train: [50] [ 600/6250] eta: 0:11:51 lr: 0.000067 grad: 0.0753 (0.0810) loss: 0.8758 (0.8743) time: 0.1202 data: 0.0478 max mem: 8299 +Train: [50] [ 700/6250] eta: 0:11:32 lr: 0.000067 grad: 0.0743 (0.0800) loss: 0.8763 (0.8741) time: 0.1262 data: 0.0487 max mem: 8299 +Train: [50] [ 800/6250] eta: 0:11:12 lr: 0.000067 grad: 0.0822 (0.0797) loss: 0.8681 (0.8737) time: 0.1075 data: 0.0334 max mem: 8299 +Train: [50] [ 900/6250] eta: 0:10:55 lr: 0.000067 grad: 0.0723 (0.0794) loss: 0.8679 (0.8733) time: 0.1194 data: 0.0406 max mem: 8299 +Train: [50] [1000/6250] eta: 0:10:37 lr: 0.000067 grad: 0.0773 (0.0792) loss: 0.8656 (0.8729) time: 0.1163 data: 0.0399 max mem: 8299 +Train: [50] [1100/6250] eta: 0:10:17 lr: 0.000067 grad: 0.0787 (0.0790) loss: 0.8668 (0.8725) time: 0.1110 data: 0.0395 max mem: 8299 +Train: [50] [1200/6250] eta: 0:09:59 lr: 0.000067 grad: 0.0777 (0.0794) loss: 0.8694 (0.8717) time: 0.1063 data: 0.0359 max mem: 8299 +Train: [50] [1300/6250] eta: 0:09:44 lr: 0.000067 grad: 0.0773 (0.0795) loss: 0.8663 (0.8712) time: 0.1083 data: 0.0352 max mem: 8299 +Train: [50] [1400/6250] eta: 0:09:28 lr: 0.000067 grad: 0.0864 (0.0797) loss: 0.8587 (0.8707) time: 0.1017 data: 0.0275 max mem: 8299 +Train: [50] [1500/6250] eta: 0:09:13 lr: 0.000067 grad: 0.0847 (0.0801) loss: 0.8666 (0.8703) time: 0.0988 data: 0.0205 max mem: 8299 +Train: [50] [1600/6250] eta: 0:09:00 lr: 0.000067 grad: 0.0728 (0.0805) loss: 0.8663 (0.8698) time: 0.1071 data: 0.0184 max mem: 8299 +Train: [50] [1700/6250] eta: 0:08:47 lr: 0.000067 grad: 0.0821 (0.0812) loss: 0.8673 (0.8692) time: 0.1132 data: 0.0438 max mem: 8299 +Train: [50] [1800/6250] eta: 0:08:34 lr: 0.000067 grad: 0.0950 (0.0817) loss: 0.8591 (0.8686) time: 0.1119 data: 0.0292 max mem: 8299 +Train: [50] [1900/6250] eta: 0:08:21 lr: 0.000067 grad: 0.0874 (0.0822) loss: 0.8543 (0.8681) time: 0.1110 data: 0.0422 max mem: 8299 +Train: [50] [2000/6250] eta: 0:08:09 lr: 0.000067 grad: 0.0839 (0.0826) loss: 0.8685 (0.8677) time: 0.1184 data: 0.0473 max mem: 8299 +Train: [50] [2100/6250] eta: 0:07:56 lr: 0.000067 grad: 0.0865 (0.0829) loss: 0.8622 (0.8674) time: 0.1023 data: 0.0303 max mem: 8299 +Train: [50] [2200/6250] eta: 0:07:43 lr: 0.000067 grad: 0.0803 (0.0831) loss: 0.8656 (0.8672) time: 0.0939 data: 0.0148 max mem: 8299 +Train: [50] [2300/6250] eta: 0:07:31 lr: 0.000067 grad: 0.0874 (0.0834) loss: 0.8598 (0.8670) time: 0.1087 data: 0.0456 max mem: 8299 +Train: [50] [2400/6250] eta: 0:07:19 lr: 0.000067 grad: 0.0821 (0.0835) loss: 0.8642 (0.8669) time: 0.1098 data: 0.0361 max mem: 8299 +Train: [50] [2500/6250] eta: 0:07:07 lr: 0.000067 grad: 0.0787 (0.0836) loss: 0.8677 (0.8668) time: 0.1182 data: 0.0482 max mem: 8299 +Train: [50] [2600/6250] eta: 0:06:55 lr: 0.000067 grad: 0.0815 (0.0838) loss: 0.8581 (0.8666) time: 0.1200 data: 0.0513 max mem: 8299 +Train: [50] [2700/6250] eta: 0:06:43 lr: 0.000067 grad: 0.0818 (0.0840) loss: 0.8621 (0.8665) time: 0.1220 data: 0.0494 max mem: 8299 +Train: [50] [2800/6250] eta: 0:06:31 lr: 0.000067 grad: 0.0808 (0.0842) loss: 0.8703 (0.8664) time: 0.1073 data: 0.0353 max mem: 8299 +Train: [50] [2900/6250] eta: 0:06:19 lr: 0.000067 grad: 0.0789 (0.0843) loss: 0.8614 (0.8662) time: 0.1031 data: 0.0168 max mem: 8299 +Train: [50] [3000/6250] eta: 0:06:08 lr: 0.000067 grad: 0.0826 (0.0844) loss: 0.8653 (0.8662) time: 0.1204 data: 0.0546 max mem: 8299 +Train: [50] [3100/6250] eta: 0:05:56 lr: 0.000067 grad: 0.0788 (0.0844) loss: 0.8669 (0.8661) time: 0.1061 data: 0.0316 max mem: 8299 +Train: [50] [3200/6250] eta: 0:05:44 lr: 0.000067 grad: 0.0759 (0.0844) loss: 0.8664 (0.8661) time: 0.0871 data: 0.0119 max mem: 8299 +Train: [50] [3300/6250] eta: 0:05:32 lr: 0.000067 grad: 0.0794 (0.0843) loss: 0.8649 (0.8661) time: 0.0967 data: 0.0183 max mem: 8299 +Train: [50] [3400/6250] eta: 0:05:21 lr: 0.000067 grad: 0.0768 (0.0844) loss: 0.8690 (0.8662) time: 0.1123 data: 0.0421 max mem: 8299 +Train: [50] [3500/6250] eta: 0:05:09 lr: 0.000067 grad: 0.0804 (0.0843) loss: 0.8690 (0.8662) time: 0.1123 data: 0.0384 max mem: 8299 +Train: [50] [3600/6250] eta: 0:04:58 lr: 0.000066 grad: 0.0767 (0.0842) loss: 0.8689 (0.8663) time: 0.1157 data: 0.0398 max mem: 8299 +Train: [50] [3700/6250] eta: 0:04:47 lr: 0.000066 grad: 0.0799 (0.0842) loss: 0.8662 (0.8663) time: 0.0936 data: 0.0188 max mem: 8299 +Train: [50] [3800/6250] eta: 0:04:35 lr: 0.000066 grad: 0.0911 (0.0842) loss: 0.8594 (0.8663) time: 0.1027 data: 0.0326 max mem: 8299 +Train: [50] [3900/6250] eta: 0:04:24 lr: 0.000066 grad: 0.0784 (0.0842) loss: 0.8652 (0.8663) time: 0.1048 data: 0.0277 max mem: 8299 +Train: [50] [4000/6250] eta: 0:04:12 lr: 0.000066 grad: 0.0821 (0.0842) loss: 0.8658 (0.8662) time: 0.1060 data: 0.0397 max mem: 8299 +Train: [50] [4100/6250] eta: 0:04:01 lr: 0.000066 grad: 0.0826 (0.0842) loss: 0.8674 (0.8662) time: 0.1122 data: 0.0389 max mem: 8299 +Train: [50] [4200/6250] eta: 0:03:50 lr: 0.000066 grad: 0.0901 (0.0843) loss: 0.8660 (0.8662) time: 0.1279 data: 0.0561 max mem: 8299 +Train: [50] [4300/6250] eta: 0:03:38 lr: 0.000066 grad: 0.0813 (0.0843) loss: 0.8652 (0.8662) time: 0.1186 data: 0.0383 max mem: 8299 +Train: [50] [4400/6250] eta: 0:03:27 lr: 0.000066 grad: 0.0801 (0.0843) loss: 0.8627 (0.8661) time: 0.0862 data: 0.0106 max mem: 8299 +Train: [50] [4500/6250] eta: 0:03:16 lr: 0.000066 grad: 0.0877 (0.0844) loss: 0.8681 (0.8661) time: 0.1131 data: 0.0424 max mem: 8299 +Train: [50] [4600/6250] eta: 0:03:04 lr: 0.000066 grad: 0.0765 (0.0844) loss: 0.8648 (0.8661) time: 0.1159 data: 0.0472 max mem: 8299 +Train: [50] [4700/6250] eta: 0:02:53 lr: 0.000066 grad: 0.0824 (0.0846) loss: 0.8629 (0.8661) time: 0.1103 data: 0.0410 max mem: 8299 +Train: [50] [4800/6250] eta: 0:02:42 lr: 0.000066 grad: 0.0828 (0.0847) loss: 0.8658 (0.8661) time: 0.1100 data: 0.0384 max mem: 8299 +Train: [50] [4900/6250] eta: 0:02:30 lr: 0.000066 grad: 0.0866 (0.0847) loss: 0.8614 (0.8660) time: 0.1120 data: 0.0501 max mem: 8299 +Train: [50] [5000/6250] eta: 0:02:19 lr: 0.000066 grad: 0.0841 (0.0847) loss: 0.8619 (0.8660) time: 0.1127 data: 0.0355 max mem: 8299 +Train: [50] [5100/6250] eta: 0:02:08 lr: 0.000066 grad: 0.0792 (0.0848) loss: 0.8687 (0.8660) time: 0.1146 data: 0.0441 max mem: 8299 +Train: [50] [5200/6250] eta: 0:01:57 lr: 0.000066 grad: 0.0828 (0.0848) loss: 0.8701 (0.8660) time: 0.1651 data: 0.1002 max mem: 8299 +Train: [50] [5300/6250] eta: 0:01:46 lr: 0.000066 grad: 0.0809 (0.0849) loss: 0.8687 (0.8660) time: 0.1707 data: 0.1022 max mem: 8299 +Train: [50] [5400/6250] eta: 0:01:35 lr: 0.000066 grad: 0.0817 (0.0848) loss: 0.8596 (0.8660) time: 0.1126 data: 0.0454 max mem: 8299 +Train: [50] [5500/6250] eta: 0:01:24 lr: 0.000066 grad: 0.0841 (0.0848) loss: 0.8651 (0.8661) time: 0.1187 data: 0.0554 max mem: 8299 +Train: [50] [5600/6250] eta: 0:01:13 lr: 0.000066 grad: 0.0879 (0.0847) loss: 0.8606 (0.8661) time: 0.1536 data: 0.0840 max mem: 8299 +Train: [50] [5700/6250] eta: 0:01:02 lr: 0.000066 grad: 0.0779 (0.0847) loss: 0.8683 (0.8661) time: 0.1352 data: 0.0681 max mem: 8299 +Train: [50] [5800/6250] eta: 0:00:50 lr: 0.000066 grad: 0.0835 (0.0846) loss: 0.8629 (0.8661) time: 0.1328 data: 0.0603 max mem: 8299 +Train: [50] [5900/6250] eta: 0:00:39 lr: 0.000066 grad: 0.0812 (0.0846) loss: 0.8630 (0.8661) time: 0.1139 data: 0.0443 max mem: 8299 +Train: [50] [6000/6250] eta: 0:00:28 lr: 0.000066 grad: 0.0849 (0.0846) loss: 0.8597 (0.8661) time: 0.1224 data: 0.0531 max mem: 8299 +Train: [50] [6100/6250] eta: 0:00:17 lr: 0.000066 grad: 0.0823 (0.0846) loss: 0.8642 (0.8660) time: 0.1170 data: 0.0394 max mem: 8299 +Train: [50] [6200/6250] eta: 0:00:05 lr: 0.000066 grad: 0.0801 (0.0846) loss: 0.8576 (0.8660) time: 0.1210 data: 0.0436 max mem: 8299 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0822 (0.0846) loss: 0.8641 (0.8659) time: 0.1089 data: 0.0316 max mem: 8299 +Train: [50] Total time: 0:11:56 (0.1146 s / it) +Averaged stats: lr: 0.000066 grad: 0.0822 (0.0846) loss: 0.8641 (0.8659) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:03:45 loss: 0.8991 (0.8991) time: 3.6426 data: 3.5755 max mem: 8299 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8870 (0.8865) time: 0.1055 data: 0.0815 max mem: 8299 +Eval (hcp-train-subset): [50] Total time: 0:00:10 (0.1739 s / it) +Averaged stats (hcp-train-subset): loss: 0.8870 (0.8865) +Eval (hcp-val): [50] [ 0/62] eta: 0:03:56 loss: 0.8832 (0.8832) time: 3.8218 data: 3.7928 max mem: 8299 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8840 (0.8848) time: 0.0843 data: 0.0602 max mem: 8299 +Eval (hcp-val): [50] Total time: 0:00:10 (0.1743 s / it) +Averaged stats (hcp-val): loss: 0.8840 (0.8848) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 8:17:34 lr: 0.000066 grad: 0.1399 (0.1399) loss: 0.8990 (0.8990) time: 4.7767 data: 4.6728 max mem: 8299 +Train: [51] [ 100/6250] eta: 0:16:36 lr: 0.000066 grad: 0.0757 (0.0797) loss: 0.8870 (0.8900) time: 0.1143 data: 0.0293 max mem: 8299 +Train: [51] [ 200/6250] eta: 0:14:04 lr: 0.000066 grad: 0.0845 (0.0835) loss: 0.8629 (0.8805) time: 0.0938 data: 0.0093 max mem: 8299 +Train: [51] [ 300/6250] eta: 0:13:15 lr: 0.000065 grad: 0.0804 (0.0844) loss: 0.8725 (0.8756) time: 0.1148 data: 0.0397 max mem: 8299 +Train: [51] [ 400/6250] eta: 0:12:45 lr: 0.000065 grad: 0.0792 (0.0858) loss: 0.8669 (0.8729) time: 0.1275 data: 0.0456 max mem: 8299 +Train: [51] [ 500/6250] eta: 0:12:19 lr: 0.000065 grad: 0.0727 (0.0847) loss: 0.8721 (0.8722) time: 0.1392 data: 0.0635 max mem: 8299 +Train: [51] [ 600/6250] eta: 0:11:52 lr: 0.000065 grad: 0.0758 (0.0838) loss: 0.8643 (0.8715) time: 0.1121 data: 0.0299 max mem: 8299 +Train: [51] [ 700/6250] eta: 0:11:31 lr: 0.000065 grad: 0.0668 (0.0824) loss: 0.8673 (0.8714) time: 0.1126 data: 0.0234 max mem: 8299 +Train: [51] [ 800/6250] eta: 0:11:13 lr: 0.000065 grad: 0.0771 (0.0819) loss: 0.8675 (0.8709) time: 0.1215 data: 0.0417 max mem: 8299 +Train: [51] [ 900/6250] eta: 0:10:51 lr: 0.000065 grad: 0.0782 (0.0814) loss: 0.8686 (0.8705) time: 0.1064 data: 0.0370 max mem: 8299 +Train: [51] [1000/6250] eta: 0:10:32 lr: 0.000065 grad: 0.0722 (0.0807) loss: 0.8707 (0.8703) time: 0.1078 data: 0.0357 max mem: 8299 +Train: [51] [1100/6250] eta: 0:10:12 lr: 0.000065 grad: 0.0744 (0.0801) loss: 0.8701 (0.8703) time: 0.1095 data: 0.0381 max mem: 8299 +Train: [51] [1200/6250] eta: 0:09:56 lr: 0.000065 grad: 0.0740 (0.0799) loss: 0.8647 (0.8701) time: 0.0977 data: 0.0197 max mem: 8299 +Train: [51] [1300/6250] eta: 0:09:38 lr: 0.000065 grad: 0.0726 (0.0797) loss: 0.8676 (0.8698) time: 0.1070 data: 0.0303 max mem: 8299 +Train: [51] [1400/6250] eta: 0:09:23 lr: 0.000065 grad: 0.0780 (0.0799) loss: 0.8616 (0.8694) time: 0.1252 data: 0.0501 max mem: 8299 +Train: [51] [1500/6250] eta: 0:09:08 lr: 0.000065 grad: 0.0723 (0.0799) loss: 0.8688 (0.8690) time: 0.1137 data: 0.0395 max mem: 8299 +Train: [51] [1600/6250] eta: 0:08:54 lr: 0.000065 grad: 0.0705 (0.0799) loss: 0.8687 (0.8688) time: 0.1120 data: 0.0369 max mem: 8299 +Train: [51] [1700/6250] eta: 0:08:40 lr: 0.000065 grad: 0.0767 (0.0802) loss: 0.8649 (0.8683) time: 0.1101 data: 0.0406 max mem: 8299 +Train: [51] [1800/6250] eta: 0:08:26 lr: 0.000065 grad: 0.0803 (0.0803) loss: 0.8611 (0.8682) time: 0.1142 data: 0.0401 max mem: 8299 +Train: [51] [1900/6250] eta: 0:08:13 lr: 0.000065 grad: 0.0730 (0.0804) loss: 0.8752 (0.8681) time: 0.1161 data: 0.0396 max mem: 8299 +Train: [51] [2000/6250] eta: 0:08:00 lr: 0.000065 grad: 0.0806 (0.0805) loss: 0.8670 (0.8680) time: 0.1088 data: 0.0324 max mem: 8299 +Train: [51] [2100/6250] eta: 0:07:48 lr: 0.000065 grad: 0.0841 (0.0806) loss: 0.8684 (0.8678) time: 0.1142 data: 0.0453 max mem: 8299 +Train: [51] [2200/6250] eta: 0:07:35 lr: 0.000065 grad: 0.0833 (0.0808) loss: 0.8624 (0.8675) time: 0.1009 data: 0.0297 max mem: 8299 +Train: [51] [2300/6250] eta: 0:07:23 lr: 0.000065 grad: 0.0810 (0.0813) loss: 0.8676 (0.8673) time: 0.1230 data: 0.0493 max mem: 8299 +Train: [51] [2400/6250] eta: 0:07:11 lr: 0.000065 grad: 0.0809 (0.0815) loss: 0.8603 (0.8670) time: 0.1091 data: 0.0360 max mem: 8299 +Train: [51] [2500/6250] eta: 0:06:59 lr: 0.000065 grad: 0.0803 (0.0816) loss: 0.8650 (0.8668) time: 0.1153 data: 0.0387 max mem: 8299 +Train: [51] [2600/6250] eta: 0:06:48 lr: 0.000065 grad: 0.0806 (0.0817) loss: 0.8668 (0.8666) time: 0.1112 data: 0.0375 max mem: 8299 +Train: [51] [2700/6250] eta: 0:06:36 lr: 0.000065 grad: 0.0813 (0.0818) loss: 0.8651 (0.8664) time: 0.1145 data: 0.0454 max mem: 8299 +Train: [51] [2800/6250] eta: 0:06:25 lr: 0.000065 grad: 0.0837 (0.0820) loss: 0.8567 (0.8661) time: 0.1130 data: 0.0403 max mem: 8299 +Train: [51] [2900/6250] eta: 0:06:13 lr: 0.000065 grad: 0.0842 (0.0821) loss: 0.8599 (0.8658) time: 0.1042 data: 0.0314 max mem: 8299 +Train: [51] [3000/6250] eta: 0:06:02 lr: 0.000065 grad: 0.0907 (0.0823) loss: 0.8546 (0.8657) time: 0.0942 data: 0.0160 max mem: 8299 +Train: [51] [3100/6250] eta: 0:05:50 lr: 0.000065 grad: 0.0816 (0.0826) loss: 0.8614 (0.8655) time: 0.1108 data: 0.0385 max mem: 8299 +Train: [51] [3200/6250] eta: 0:05:38 lr: 0.000065 grad: 0.0832 (0.0828) loss: 0.8602 (0.8654) time: 0.0977 data: 0.0210 max mem: 8299 +Train: [51] [3300/6250] eta: 0:05:27 lr: 0.000065 grad: 0.0825 (0.0829) loss: 0.8557 (0.8652) time: 0.1089 data: 0.0341 max mem: 8299 +Train: [51] [3400/6250] eta: 0:05:15 lr: 0.000064 grad: 0.0806 (0.0830) loss: 0.8630 (0.8650) time: 0.1101 data: 0.0410 max mem: 8299 +Train: [51] [3500/6250] eta: 0:05:04 lr: 0.000064 grad: 0.0872 (0.0832) loss: 0.8570 (0.8649) time: 0.1043 data: 0.0311 max mem: 8299 +Train: [51] [3600/6250] eta: 0:04:53 lr: 0.000064 grad: 0.0909 (0.0835) loss: 0.8580 (0.8647) time: 0.1101 data: 0.0305 max mem: 8299 +Train: [51] [3700/6250] eta: 0:04:41 lr: 0.000064 grad: 0.0882 (0.0836) loss: 0.8584 (0.8646) time: 0.1117 data: 0.0383 max mem: 8299 +Train: [51] [3800/6250] eta: 0:04:30 lr: 0.000064 grad: 0.0901 (0.0837) loss: 0.8552 (0.8645) time: 0.1007 data: 0.0309 max mem: 8299 +Train: [51] [3900/6250] eta: 0:04:19 lr: 0.000064 grad: 0.0878 (0.0839) loss: 0.8592 (0.8644) time: 0.1032 data: 0.0258 max mem: 8299 +Train: [51] [4000/6250] eta: 0:04:08 lr: 0.000064 grad: 0.0876 (0.0840) loss: 0.8562 (0.8642) time: 0.1026 data: 0.0364 max mem: 8299 +Train: [51] [4100/6250] eta: 0:03:57 lr: 0.000064 grad: 0.0832 (0.0840) loss: 0.8594 (0.8642) time: 0.1189 data: 0.0451 max mem: 8299 +Train: [51] [4200/6250] eta: 0:03:45 lr: 0.000064 grad: 0.0883 (0.0842) loss: 0.8537 (0.8640) time: 0.1045 data: 0.0358 max mem: 8299 +Train: [51] [4300/6250] eta: 0:03:34 lr: 0.000064 grad: 0.0913 (0.0844) loss: 0.8569 (0.8639) time: 0.1044 data: 0.0322 max mem: 8299 +Train: [51] [4400/6250] eta: 0:03:23 lr: 0.000064 grad: 0.0925 (0.0846) loss: 0.8616 (0.8637) time: 0.0966 data: 0.0147 max mem: 8299 +Train: [51] [4500/6250] eta: 0:03:12 lr: 0.000064 grad: 0.0897 (0.0847) loss: 0.8562 (0.8636) time: 0.1095 data: 0.0367 max mem: 8299 +Train: [51] [4600/6250] eta: 0:03:01 lr: 0.000064 grad: 0.0900 (0.0849) loss: 0.8620 (0.8636) time: 0.1072 data: 0.0332 max mem: 8299 +Train: [51] [4700/6250] eta: 0:02:50 lr: 0.000064 grad: 0.0874 (0.0850) loss: 0.8620 (0.8635) time: 0.1149 data: 0.0405 max mem: 8299 +Train: [51] [4800/6250] eta: 0:02:39 lr: 0.000064 grad: 0.0849 (0.0851) loss: 0.8637 (0.8634) time: 0.1087 data: 0.0399 max mem: 8299 +Train: [51] [4900/6250] eta: 0:02:28 lr: 0.000064 grad: 0.0892 (0.0852) loss: 0.8576 (0.8634) time: 0.0982 data: 0.0257 max mem: 8299 +Train: [51] [5000/6250] eta: 0:02:17 lr: 0.000064 grad: 0.0848 (0.0852) loss: 0.8677 (0.8634) time: 0.1065 data: 0.0386 max mem: 8299 +Train: [51] [5100/6250] eta: 0:02:06 lr: 0.000064 grad: 0.0866 (0.0852) loss: 0.8660 (0.8633) time: 0.0937 data: 0.0215 max mem: 8299 +Train: [51] [5200/6250] eta: 0:01:55 lr: 0.000064 grad: 0.0833 (0.0852) loss: 0.8631 (0.8634) time: 0.1760 data: 0.1144 max mem: 8299 +Train: [51] [5300/6250] eta: 0:01:45 lr: 0.000064 grad: 0.0849 (0.0853) loss: 0.8641 (0.8634) time: 0.1434 data: 0.0646 max mem: 8299 +Train: [51] [5400/6250] eta: 0:01:34 lr: 0.000064 grad: 0.0829 (0.0853) loss: 0.8652 (0.8634) time: 0.1415 data: 0.0748 max mem: 8299 +Train: [51] [5500/6250] eta: 0:01:23 lr: 0.000064 grad: 0.0825 (0.0854) loss: 0.8683 (0.8634) time: 0.1346 data: 0.0668 max mem: 8299 +Train: [51] [5600/6250] eta: 0:01:12 lr: 0.000064 grad: 0.0862 (0.0854) loss: 0.8696 (0.8634) time: 0.1120 data: 0.0376 max mem: 8299 +Train: [51] [5700/6250] eta: 0:01:01 lr: 0.000064 grad: 0.0887 (0.0855) loss: 0.8594 (0.8634) time: 0.1187 data: 0.0462 max mem: 8299 +Train: [51] [5800/6250] eta: 0:00:50 lr: 0.000064 grad: 0.0837 (0.0855) loss: 0.8679 (0.8634) time: 0.1063 data: 0.0315 max mem: 8299 +Train: [51] [5900/6250] eta: 0:00:39 lr: 0.000064 grad: 0.0817 (0.0856) loss: 0.8642 (0.8634) time: 0.1228 data: 0.0523 max mem: 8299 +Train: [51] [6000/6250] eta: 0:00:28 lr: 0.000064 grad: 0.0919 (0.0857) loss: 0.8650 (0.8634) time: 0.1003 data: 0.0187 max mem: 8299 +Train: [51] [6100/6250] eta: 0:00:16 lr: 0.000064 grad: 0.0841 (0.0857) loss: 0.8621 (0.8635) time: 0.1227 data: 0.0442 max mem: 8299 +Train: [51] [6200/6250] eta: 0:00:05 lr: 0.000064 grad: 0.0846 (0.0858) loss: 0.8649 (0.8635) time: 0.0809 data: 0.0002 max mem: 8299 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.0829 (0.0858) loss: 0.8681 (0.8634) time: 0.1236 data: 0.0488 max mem: 8299 +Train: [51] Total time: 0:11:44 (0.1128 s / it) +Averaged stats: lr: 0.000064 grad: 0.0829 (0.0858) loss: 0.8681 (0.8634) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:03:15 loss: 0.8888 (0.8888) time: 3.1452 data: 3.0782 max mem: 8299 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8833 (0.8839) time: 0.1046 data: 0.0794 max mem: 8299 +Eval (hcp-train-subset): [51] Total time: 0:00:10 (0.1671 s / it) +Averaged stats (hcp-train-subset): loss: 0.8833 (0.8839) +Eval (hcp-val): [51] [ 0/62] eta: 0:03:09 loss: 0.8885 (0.8885) time: 3.0575 data: 2.9917 max mem: 8299 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8824 (0.8839) time: 0.1029 data: 0.0789 max mem: 8299 +Eval (hcp-val): [51] Total time: 0:00:10 (0.1711 s / it) +Averaged stats (hcp-val): loss: 0.8824 (0.8839) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 8:13:54 lr: 0.000064 grad: 0.0903 (0.0903) loss: 0.9094 (0.9094) time: 4.7416 data: 4.6389 max mem: 8299 +Train: [52] [ 100/6250] eta: 0:17:05 lr: 0.000063 grad: 0.0725 (0.0938) loss: 0.8763 (0.8808) time: 0.1385 data: 0.0511 max mem: 8299 +Train: [52] [ 200/6250] eta: 0:14:18 lr: 0.000063 grad: 0.0767 (0.0912) loss: 0.8678 (0.8758) time: 0.1227 data: 0.0418 max mem: 8299 +Train: [52] [ 300/6250] eta: 0:13:21 lr: 0.000063 grad: 0.0790 (0.0890) loss: 0.8716 (0.8734) time: 0.1262 data: 0.0545 max mem: 8299 +Train: [52] [ 400/6250] eta: 0:12:35 lr: 0.000063 grad: 0.0769 (0.0873) loss: 0.8733 (0.8727) time: 0.1005 data: 0.0284 max mem: 8299 +Train: [52] [ 500/6250] eta: 0:12:11 lr: 0.000063 grad: 0.0838 (0.0866) loss: 0.8699 (0.8724) time: 0.1380 data: 0.0617 max mem: 8299 +Train: [52] [ 600/6250] eta: 0:11:42 lr: 0.000063 grad: 0.0834 (0.0858) loss: 0.8693 (0.8719) time: 0.1018 data: 0.0265 max mem: 8299 +Train: [52] [ 700/6250] eta: 0:11:19 lr: 0.000063 grad: 0.0852 (0.0856) loss: 0.8650 (0.8712) time: 0.1004 data: 0.0103 max mem: 8299 +Train: [52] [ 800/6250] eta: 0:10:59 lr: 0.000063 grad: 0.0825 (0.0854) loss: 0.8684 (0.8708) time: 0.1240 data: 0.0399 max mem: 8299 +Train: [52] [ 900/6250] eta: 0:10:39 lr: 0.000063 grad: 0.0721 (0.0847) loss: 0.8738 (0.8708) time: 0.1018 data: 0.0240 max mem: 8299 +Train: [52] [1000/6250] eta: 0:10:21 lr: 0.000063 grad: 0.0768 (0.0842) loss: 0.8768 (0.8709) time: 0.1136 data: 0.0314 max mem: 8299 +Train: [52] [1100/6250] eta: 0:10:06 lr: 0.000063 grad: 0.0821 (0.0840) loss: 0.8633 (0.8706) time: 0.1208 data: 0.0471 max mem: 8299 +Train: [52] [1200/6250] eta: 0:09:52 lr: 0.000063 grad: 0.0813 (0.0841) loss: 0.8671 (0.8702) time: 0.1258 data: 0.0550 max mem: 8299 +Train: [52] [1300/6250] eta: 0:09:37 lr: 0.000063 grad: 0.0793 (0.0841) loss: 0.8648 (0.8698) time: 0.1217 data: 0.0456 max mem: 8299 +Train: [52] [1400/6250] eta: 0:09:23 lr: 0.000063 grad: 0.0766 (0.0839) loss: 0.8661 (0.8694) time: 0.1099 data: 0.0381 max mem: 8299 +Train: [52] [1500/6250] eta: 0:09:10 lr: 0.000063 grad: 0.0805 (0.0839) loss: 0.8665 (0.8690) time: 0.1091 data: 0.0340 max mem: 8299 +Train: [52] [1600/6250] eta: 0:08:58 lr: 0.000063 grad: 0.0838 (0.0839) loss: 0.8649 (0.8688) time: 0.1197 data: 0.0511 max mem: 8299 +Train: [52] [1700/6250] eta: 0:08:46 lr: 0.000063 grad: 0.0797 (0.0839) loss: 0.8629 (0.8686) time: 0.1102 data: 0.0374 max mem: 8299 +Train: [52] [1800/6250] eta: 0:08:34 lr: 0.000063 grad: 0.0813 (0.0839) loss: 0.8636 (0.8685) time: 0.1210 data: 0.0479 max mem: 8299 +Train: [52] [1900/6250] eta: 0:08:20 lr: 0.000063 grad: 0.0827 (0.0838) loss: 0.8666 (0.8684) time: 0.1122 data: 0.0382 max mem: 8299 +Train: [52] [2000/6250] eta: 0:08:08 lr: 0.000063 grad: 0.0846 (0.0838) loss: 0.8629 (0.8683) time: 0.1219 data: 0.0517 max mem: 8299 +Train: [52] [2100/6250] eta: 0:07:56 lr: 0.000063 grad: 0.0843 (0.0839) loss: 0.8658 (0.8682) time: 0.1104 data: 0.0379 max mem: 8299 +Train: [52] [2200/6250] eta: 0:07:44 lr: 0.000063 grad: 0.0783 (0.0838) loss: 0.8718 (0.8682) time: 0.1181 data: 0.0473 max mem: 8299 +Train: [52] [2300/6250] eta: 0:07:32 lr: 0.000063 grad: 0.0776 (0.0838) loss: 0.8714 (0.8682) time: 0.1111 data: 0.0347 max mem: 8299 +Train: [52] [2400/6250] eta: 0:07:20 lr: 0.000063 grad: 0.0819 (0.0837) loss: 0.8705 (0.8682) time: 0.0994 data: 0.0213 max mem: 8299 +Train: [52] [2500/6250] eta: 0:07:10 lr: 0.000063 grad: 0.0903 (0.0838) loss: 0.8715 (0.8682) time: 0.1612 data: 0.0972 max mem: 8299 +Train: [52] [2600/6250] eta: 0:06:58 lr: 0.000063 grad: 0.0837 (0.0838) loss: 0.8630 (0.8682) time: 0.0989 data: 0.0280 max mem: 8299 +Train: [52] [2700/6250] eta: 0:06:46 lr: 0.000063 grad: 0.0866 (0.0839) loss: 0.8716 (0.8681) time: 0.1115 data: 0.0375 max mem: 8299 +Train: [52] [2800/6250] eta: 0:06:34 lr: 0.000063 grad: 0.0873 (0.0841) loss: 0.8648 (0.8680) time: 0.1088 data: 0.0298 max mem: 8299 +Train: [52] [2900/6250] eta: 0:06:22 lr: 0.000063 grad: 0.0860 (0.0842) loss: 0.8649 (0.8679) time: 0.1175 data: 0.0411 max mem: 8299 +Train: [52] [3000/6250] eta: 0:06:11 lr: 0.000063 grad: 0.0904 (0.0848) loss: 0.8609 (0.8678) time: 0.1059 data: 0.0316 max mem: 8299 +Train: [52] [3100/6250] eta: 0:05:59 lr: 0.000063 grad: 0.0820 (0.0848) loss: 0.8672 (0.8677) time: 0.1024 data: 0.0281 max mem: 8299 +Train: [52] [3200/6250] eta: 0:05:48 lr: 0.000062 grad: 0.0773 (0.0849) loss: 0.8634 (0.8676) time: 0.1270 data: 0.0551 max mem: 8299 +Train: [52] [3300/6250] eta: 0:05:37 lr: 0.000062 grad: 0.0799 (0.0851) loss: 0.8624 (0.8674) time: 0.1204 data: 0.0525 max mem: 8299 +Train: [52] [3400/6250] eta: 0:05:25 lr: 0.000062 grad: 0.0818 (0.0852) loss: 0.8655 (0.8673) time: 0.1070 data: 0.0344 max mem: 8299 +Train: [52] [3500/6250] eta: 0:05:14 lr: 0.000062 grad: 0.0798 (0.0852) loss: 0.8655 (0.8672) time: 0.1116 data: 0.0367 max mem: 8299 +Train: [52] [3600/6250] eta: 0:05:02 lr: 0.000062 grad: 0.0836 (0.0853) loss: 0.8647 (0.8671) time: 0.1188 data: 0.0432 max mem: 8299 +Train: [52] [3700/6250] eta: 0:04:51 lr: 0.000062 grad: 0.0792 (0.0852) loss: 0.8698 (0.8671) time: 0.1111 data: 0.0335 max mem: 8299 +Train: [52] [3800/6250] eta: 0:04:40 lr: 0.000062 grad: 0.0820 (0.0853) loss: 0.8696 (0.8671) time: 0.1262 data: 0.0502 max mem: 8299 +Train: [52] [3900/6250] eta: 0:04:28 lr: 0.000062 grad: 0.0850 (0.0854) loss: 0.8682 (0.8670) time: 0.1152 data: 0.0440 max mem: 8299 +Train: [52] [4000/6250] eta: 0:04:17 lr: 0.000062 grad: 0.0826 (0.0854) loss: 0.8731 (0.8670) time: 0.1114 data: 0.0391 max mem: 8299 +Train: [52] [4100/6250] eta: 0:04:06 lr: 0.000062 grad: 0.0817 (0.0855) loss: 0.8700 (0.8670) time: 0.1091 data: 0.0324 max mem: 8299 +Train: [52] [4200/6250] eta: 0:03:54 lr: 0.000062 grad: 0.0810 (0.0855) loss: 0.8648 (0.8669) time: 0.1170 data: 0.0450 max mem: 8299 +Train: [52] [4300/6250] eta: 0:03:43 lr: 0.000062 grad: 0.0906 (0.0855) loss: 0.8643 (0.8668) time: 0.1244 data: 0.0550 max mem: 8299 +Train: [52] [4400/6250] eta: 0:03:32 lr: 0.000062 grad: 0.0811 (0.0856) loss: 0.8629 (0.8668) time: 0.1282 data: 0.0626 max mem: 8299 +Train: [52] [4500/6250] eta: 0:03:21 lr: 0.000062 grad: 0.0826 (0.0856) loss: 0.8685 (0.8667) time: 0.1024 data: 0.0322 max mem: 8299 +Train: [52] [4600/6250] eta: 0:03:09 lr: 0.000062 grad: 0.0878 (0.0857) loss: 0.8657 (0.8667) time: 0.1162 data: 0.0487 max mem: 8299 +Train: [52] [4700/6250] eta: 0:02:58 lr: 0.000062 grad: 0.0859 (0.0857) loss: 0.8649 (0.8666) time: 0.1185 data: 0.0498 max mem: 8299 +Train: [52] [4800/6250] eta: 0:02:46 lr: 0.000062 grad: 0.0865 (0.0857) loss: 0.8632 (0.8666) time: 0.1246 data: 0.0553 max mem: 8299 +Train: [52] [4900/6250] eta: 0:02:35 lr: 0.000062 grad: 0.0843 (0.0858) loss: 0.8668 (0.8665) time: 0.1194 data: 0.0465 max mem: 8299 +Train: [52] [5000/6250] eta: 0:02:23 lr: 0.000062 grad: 0.0850 (0.0857) loss: 0.8660 (0.8665) time: 0.1252 data: 0.0530 max mem: 8299 +Train: [52] [5100/6250] eta: 0:02:12 lr: 0.000062 grad: 0.0850 (0.0857) loss: 0.8612 (0.8665) time: 0.1049 data: 0.0321 max mem: 8299 +Train: [52] [5200/6250] eta: 0:02:01 lr: 0.000062 grad: 0.0898 (0.0858) loss: 0.8615 (0.8664) time: 0.1545 data: 0.0873 max mem: 8299 +Train: [52] [5300/6250] eta: 0:01:49 lr: 0.000062 grad: 0.0802 (0.0858) loss: 0.8668 (0.8663) time: 0.1331 data: 0.0518 max mem: 8299 +Train: [52] [5400/6250] eta: 0:01:38 lr: 0.000062 grad: 0.0886 (0.0859) loss: 0.8630 (0.8662) time: 0.1326 data: 0.0585 max mem: 8299 +Train: [52] [5500/6250] eta: 0:01:27 lr: 0.000062 grad: 0.0822 (0.0859) loss: 0.8674 (0.8662) time: 0.1532 data: 0.0732 max mem: 8299 +Train: [52] [5600/6250] eta: 0:01:15 lr: 0.000062 grad: 0.0954 (0.0860) loss: 0.8610 (0.8661) time: 0.1183 data: 0.0450 max mem: 8299 +Train: [52] [5700/6250] eta: 0:01:04 lr: 0.000062 grad: 0.0880 (0.0860) loss: 0.8671 (0.8661) time: 0.1229 data: 0.0533 max mem: 8299 +Train: [52] [5800/6250] eta: 0:00:52 lr: 0.000062 grad: 0.0844 (0.0861) loss: 0.8738 (0.8660) time: 0.1082 data: 0.0365 max mem: 8299 +Train: [52] [5900/6250] eta: 0:00:40 lr: 0.000062 grad: 0.0835 (0.0861) loss: 0.8622 (0.8660) time: 0.1035 data: 0.0327 max mem: 8299 +Train: [52] [6000/6250] eta: 0:00:29 lr: 0.000062 grad: 0.0852 (0.0861) loss: 0.8586 (0.8660) time: 0.0961 data: 0.0232 max mem: 8299 +Train: [52] [6100/6250] eta: 0:00:17 lr: 0.000062 grad: 0.0822 (0.0861) loss: 0.8712 (0.8660) time: 0.1026 data: 0.0285 max mem: 8299 +Train: [52] [6200/6250] eta: 0:00:05 lr: 0.000061 grad: 0.0839 (0.0861) loss: 0.8622 (0.8660) time: 0.1035 data: 0.0313 max mem: 8299 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0797 (0.0861) loss: 0.8719 (0.8661) time: 0.0958 data: 0.0204 max mem: 8299 +Train: [52] Total time: 0:12:09 (0.1167 s / it) +Averaged stats: lr: 0.000061 grad: 0.0797 (0.0861) loss: 0.8719 (0.8661) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:04:02 loss: 0.8926 (0.8926) time: 3.9074 data: 3.8790 max mem: 8299 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8862 (0.8870) time: 0.1097 data: 0.0846 max mem: 8299 +Eval (hcp-train-subset): [52] Total time: 0:00:10 (0.1735 s / it) +Averaged stats (hcp-train-subset): loss: 0.8862 (0.8870) +Eval (hcp-val): [52] [ 0/62] eta: 0:03:55 loss: 0.8831 (0.8831) time: 3.7960 data: 3.7667 max mem: 8299 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8809 (0.8847) time: 0.0911 data: 0.0669 max mem: 8299 +Eval (hcp-val): [52] Total time: 0:00:10 (0.1708 s / it) +Averaged stats (hcp-val): loss: 0.8809 (0.8847) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 7:03:52 lr: 0.000061 grad: 0.2145 (0.2145) loss: 0.9131 (0.9131) time: 4.0692 data: 3.8794 max mem: 8299 +Train: [53] [ 100/6250] eta: 0:16:37 lr: 0.000061 grad: 0.0759 (0.0954) loss: 0.8797 (0.8761) time: 0.1200 data: 0.0268 max mem: 8299 +Train: [53] [ 200/6250] eta: 0:14:18 lr: 0.000061 grad: 0.0749 (0.0925) loss: 0.8682 (0.8703) time: 0.1120 data: 0.0218 max mem: 8299 +Train: [53] [ 300/6250] eta: 0:13:21 lr: 0.000061 grad: 0.0757 (0.0902) loss: 0.8661 (0.8682) time: 0.1083 data: 0.0284 max mem: 8299 +Train: [53] [ 400/6250] eta: 0:12:45 lr: 0.000061 grad: 0.0730 (0.0884) loss: 0.8622 (0.8674) time: 0.1174 data: 0.0429 max mem: 8299 +Train: [53] [ 500/6250] eta: 0:12:17 lr: 0.000061 grad: 0.0795 (0.0879) loss: 0.8658 (0.8673) time: 0.1320 data: 0.0554 max mem: 8299 +Train: [53] [ 600/6250] eta: 0:11:48 lr: 0.000061 grad: 0.0848 (0.0870) loss: 0.8721 (0.8673) time: 0.1113 data: 0.0307 max mem: 8299 +Train: [53] [ 700/6250] eta: 0:11:30 lr: 0.000061 grad: 0.0756 (0.0864) loss: 0.8703 (0.8669) time: 0.1118 data: 0.0356 max mem: 8299 +Train: [53] [ 800/6250] eta: 0:11:09 lr: 0.000061 grad: 0.0865 (0.0861) loss: 0.8638 (0.8672) time: 0.1045 data: 0.0202 max mem: 8299 +Train: [53] [ 900/6250] eta: 0:10:50 lr: 0.000061 grad: 0.0807 (0.0862) loss: 0.8606 (0.8670) time: 0.1145 data: 0.0275 max mem: 8299 +Train: [53] [1000/6250] eta: 0:10:34 lr: 0.000061 grad: 0.0824 (0.0861) loss: 0.8608 (0.8671) time: 0.1012 data: 0.0328 max mem: 8299 +Train: [53] [1100/6250] eta: 0:10:17 lr: 0.000061 grad: 0.0840 (0.0868) loss: 0.8595 (0.8669) time: 0.1065 data: 0.0380 max mem: 8299 +Train: [53] [1200/6250] eta: 0:10:02 lr: 0.000061 grad: 0.0885 (0.0867) loss: 0.8676 (0.8667) time: 0.1138 data: 0.0336 max mem: 8299 +Train: [53] [1300/6250] eta: 0:09:47 lr: 0.000061 grad: 0.0777 (0.0865) loss: 0.8673 (0.8669) time: 0.1055 data: 0.0286 max mem: 8299 +Train: [53] [1400/6250] eta: 0:09:35 lr: 0.000061 grad: 0.0832 (0.0866) loss: 0.8594 (0.8666) time: 0.1354 data: 0.0685 max mem: 8299 +Train: [53] [1500/6250] eta: 0:09:20 lr: 0.000061 grad: 0.0783 (0.0866) loss: 0.8707 (0.8666) time: 0.1264 data: 0.0569 max mem: 8299 +Train: [53] [1600/6250] eta: 0:09:06 lr: 0.000061 grad: 0.0877 (0.0867) loss: 0.8636 (0.8665) time: 0.1060 data: 0.0379 max mem: 8299 +Train: [53] [1700/6250] eta: 0:08:53 lr: 0.000061 grad: 0.0800 (0.0867) loss: 0.8635 (0.8663) time: 0.1018 data: 0.0273 max mem: 8299 +Train: [53] [1800/6250] eta: 0:08:43 lr: 0.000061 grad: 0.0872 (0.0868) loss: 0.8683 (0.8662) time: 0.1240 data: 0.0548 max mem: 8299 +Train: [53] [1900/6250] eta: 0:08:31 lr: 0.000061 grad: 0.0941 (0.0870) loss: 0.8551 (0.8661) time: 0.1098 data: 0.0374 max mem: 8299 +Train: [53] [2000/6250] eta: 0:08:19 lr: 0.000061 grad: 0.0863 (0.0872) loss: 0.8645 (0.8660) time: 0.1168 data: 0.0472 max mem: 8299 +Train: [53] [2100/6250] eta: 0:08:07 lr: 0.000061 grad: 0.0880 (0.0874) loss: 0.8666 (0.8658) time: 0.1190 data: 0.0505 max mem: 8299 +Train: [53] [2200/6250] eta: 0:07:55 lr: 0.000061 grad: 0.0959 (0.0876) loss: 0.8494 (0.8656) time: 0.1272 data: 0.0589 max mem: 8299 +Train: [53] [2300/6250] eta: 0:07:44 lr: 0.000061 grad: 0.0807 (0.0876) loss: 0.8718 (0.8655) time: 0.1258 data: 0.0476 max mem: 8299 +Train: [53] [2400/6250] eta: 0:07:32 lr: 0.000061 grad: 0.0867 (0.0878) loss: 0.8615 (0.8655) time: 0.1212 data: 0.0527 max mem: 8299 +Train: [53] [2500/6250] eta: 0:07:20 lr: 0.000061 grad: 0.0899 (0.0879) loss: 0.8648 (0.8654) time: 0.1107 data: 0.0386 max mem: 8299 +Train: [53] [2600/6250] eta: 0:07:09 lr: 0.000061 grad: 0.0852 (0.0880) loss: 0.8610 (0.8654) time: 0.1341 data: 0.0601 max mem: 8299 +Train: [53] [2700/6250] eta: 0:06:58 lr: 0.000061 grad: 0.0848 (0.0881) loss: 0.8667 (0.8652) time: 0.1091 data: 0.0357 max mem: 8299 +Train: [53] [2800/6250] eta: 0:06:46 lr: 0.000061 grad: 0.0854 (0.0881) loss: 0.8614 (0.8651) time: 0.1185 data: 0.0474 max mem: 8299 +Train: [53] [2900/6250] eta: 0:06:34 lr: 0.000061 grad: 0.0892 (0.0882) loss: 0.8623 (0.8649) time: 0.1102 data: 0.0414 max mem: 8299 +Train: [53] [3000/6250] eta: 0:06:23 lr: 0.000060 grad: 0.0859 (0.0883) loss: 0.8589 (0.8648) time: 0.1044 data: 0.0285 max mem: 8299 +Train: [53] [3100/6250] eta: 0:06:11 lr: 0.000060 grad: 0.0871 (0.0883) loss: 0.8601 (0.8648) time: 0.1201 data: 0.0439 max mem: 8299 +Train: [53] [3200/6250] eta: 0:05:59 lr: 0.000060 grad: 0.0918 (0.0884) loss: 0.8637 (0.8646) time: 0.1384 data: 0.0697 max mem: 8299 +Train: [53] [3300/6250] eta: 0:05:47 lr: 0.000060 grad: 0.0877 (0.0884) loss: 0.8647 (0.8645) time: 0.1416 data: 0.0749 max mem: 8299 +Train: [53] [3400/6250] eta: 0:05:35 lr: 0.000060 grad: 0.0902 (0.0885) loss: 0.8657 (0.8645) time: 0.1204 data: 0.0540 max mem: 8299 +Train: [53] [3500/6250] eta: 0:05:23 lr: 0.000060 grad: 0.0839 (0.0886) loss: 0.8658 (0.8645) time: 0.1152 data: 0.0513 max mem: 8299 +Train: [53] [3600/6250] eta: 0:05:12 lr: 0.000060 grad: 0.0892 (0.0887) loss: 0.8596 (0.8644) time: 0.1233 data: 0.0527 max mem: 8299 +Train: [53] [3700/6250] eta: 0:05:00 lr: 0.000060 grad: 0.0977 (0.0887) loss: 0.8582 (0.8644) time: 0.1150 data: 0.0420 max mem: 8299 +Train: [53] [3800/6250] eta: 0:04:48 lr: 0.000060 grad: 0.0875 (0.0887) loss: 0.8592 (0.8644) time: 0.1378 data: 0.0715 max mem: 8299 +Train: [53] [3900/6250] eta: 0:04:36 lr: 0.000060 grad: 0.0872 (0.0888) loss: 0.8618 (0.8643) time: 0.1092 data: 0.0429 max mem: 8299 +Train: [53] [4000/6250] eta: 0:04:25 lr: 0.000060 grad: 0.0923 (0.0889) loss: 0.8642 (0.8643) time: 0.1335 data: 0.0623 max mem: 8299 +Train: [53] [4100/6250] eta: 0:04:13 lr: 0.000060 grad: 0.0852 (0.0890) loss: 0.8617 (0.8642) time: 0.1238 data: 0.0513 max mem: 8299 +Train: [53] [4200/6250] eta: 0:04:01 lr: 0.000060 grad: 0.0900 (0.0890) loss: 0.8658 (0.8643) time: 0.1157 data: 0.0445 max mem: 8299 +Train: [53] [4300/6250] eta: 0:03:50 lr: 0.000060 grad: 0.0884 (0.0891) loss: 0.8665 (0.8643) time: 0.1109 data: 0.0349 max mem: 8299 +Train: [53] [4400/6250] eta: 0:03:38 lr: 0.000060 grad: 0.0881 (0.0892) loss: 0.8684 (0.8644) time: 0.1164 data: 0.0491 max mem: 8299 +Train: [53] [4500/6250] eta: 0:03:26 lr: 0.000060 grad: 0.0863 (0.0893) loss: 0.8659 (0.8643) time: 0.1204 data: 0.0473 max mem: 8299 +Train: [53] [4600/6250] eta: 0:03:15 lr: 0.000060 grad: 0.0878 (0.0893) loss: 0.8625 (0.8643) time: 0.1325 data: 0.0626 max mem: 8299 +Train: [53] [4700/6250] eta: 0:03:03 lr: 0.000060 grad: 0.0881 (0.0893) loss: 0.8634 (0.8643) time: 0.1258 data: 0.0603 max mem: 8299 +Train: [53] [4800/6250] eta: 0:02:51 lr: 0.000060 grad: 0.0845 (0.0893) loss: 0.8657 (0.8643) time: 0.1495 data: 0.0767 max mem: 8299 +Train: [53] [4900/6250] eta: 0:02:39 lr: 0.000060 grad: 0.0897 (0.0893) loss: 0.8634 (0.8642) time: 0.1274 data: 0.0598 max mem: 8299 +Train: [53] [5000/6250] eta: 0:02:28 lr: 0.000060 grad: 0.0854 (0.0894) loss: 0.8638 (0.8642) time: 0.1005 data: 0.0290 max mem: 8299 +Train: [53] [5100/6250] eta: 0:02:16 lr: 0.000060 grad: 0.0873 (0.0895) loss: 0.8674 (0.8642) time: 0.1249 data: 0.0566 max mem: 8299 +Train: [53] [5200/6250] eta: 0:02:04 lr: 0.000060 grad: 0.0898 (0.0895) loss: 0.8538 (0.8642) time: 0.1012 data: 0.0321 max mem: 8299 +Train: [53] [5300/6250] eta: 0:01:52 lr: 0.000060 grad: 0.0869 (0.0895) loss: 0.8720 (0.8641) time: 0.1356 data: 0.0630 max mem: 8299 +Train: [53] [5400/6250] eta: 0:01:41 lr: 0.000060 grad: 0.0865 (0.0895) loss: 0.8629 (0.8641) time: 0.1161 data: 0.0393 max mem: 8299 +Train: [53] [5500/6250] eta: 0:01:29 lr: 0.000060 grad: 0.0830 (0.0895) loss: 0.8627 (0.8639) time: 0.1302 data: 0.0547 max mem: 8299 +Train: [53] [5600/6250] eta: 0:01:17 lr: 0.000060 grad: 0.0936 (0.0896) loss: 0.8572 (0.8638) time: 0.1232 data: 0.0543 max mem: 8299 +Train: [53] [5700/6250] eta: 0:01:05 lr: 0.000060 grad: 0.0837 (0.0896) loss: 0.8644 (0.8638) time: 0.1237 data: 0.0487 max mem: 8299 +Train: [53] [5800/6250] eta: 0:00:53 lr: 0.000060 grad: 0.0897 (0.0897) loss: 0.8546 (0.8637) time: 0.1068 data: 0.0267 max mem: 8299 +Train: [53] [5900/6250] eta: 0:00:41 lr: 0.000060 grad: 0.0965 (0.0898) loss: 0.8592 (0.8635) time: 0.1004 data: 0.0316 max mem: 8299 +Train: [53] [6000/6250] eta: 0:00:29 lr: 0.000059 grad: 0.0842 (0.0899) loss: 0.8507 (0.8634) time: 0.0996 data: 0.0240 max mem: 8299 +Train: [53] [6100/6250] eta: 0:00:17 lr: 0.000059 grad: 0.0898 (0.0899) loss: 0.8684 (0.8633) time: 0.1038 data: 0.0374 max mem: 8299 +Train: [53] [6200/6250] eta: 0:00:05 lr: 0.000059 grad: 0.0921 (0.0900) loss: 0.8472 (0.8632) time: 0.1124 data: 0.0323 max mem: 8299 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.0896 (0.0900) loss: 0.8496 (0.8632) time: 0.0982 data: 0.0254 max mem: 8299 +Train: [53] Total time: 0:12:27 (0.1196 s / it) +Averaged stats: lr: 0.000059 grad: 0.0896 (0.0900) loss: 0.8496 (0.8632) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:04:07 loss: 0.8949 (0.8949) time: 3.9988 data: 3.9690 max mem: 8299 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8829 (0.8829) time: 0.1197 data: 0.0954 max mem: 8299 +Eval (hcp-train-subset): [53] Total time: 0:00:11 (0.1899 s / it) +Averaged stats (hcp-train-subset): loss: 0.8829 (0.8829) +Eval (hcp-val): [53] [ 0/62] eta: 0:03:14 loss: 0.8825 (0.8825) time: 3.1395 data: 3.0401 max mem: 8299 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8828 (0.8839) time: 0.1063 data: 0.0821 max mem: 8299 +Eval (hcp-val): [53] Total time: 0:00:11 (0.1863 s / it) +Averaged stats (hcp-val): loss: 0.8828 (0.8839) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 9:00:22 lr: 0.000059 grad: 0.1138 (0.1138) loss: 0.8964 (0.8964) time: 5.1877 data: 5.0713 max mem: 8299 +Train: [54] [ 100/6250] eta: 0:17:18 lr: 0.000059 grad: 0.0849 (0.1055) loss: 0.8712 (0.8758) time: 0.1449 data: 0.0676 max mem: 8299 +Train: [54] [ 200/6250] eta: 0:14:30 lr: 0.000059 grad: 0.0759 (0.1021) loss: 0.8736 (0.8693) time: 0.1274 data: 0.0372 max mem: 8299 +Train: [54] [ 300/6250] eta: 0:13:38 lr: 0.000059 grad: 0.0836 (0.0963) loss: 0.8671 (0.8686) time: 0.1373 data: 0.0668 max mem: 8299 +Train: [54] [ 400/6250] eta: 0:12:53 lr: 0.000059 grad: 0.0743 (0.0929) loss: 0.8659 (0.8683) time: 0.1204 data: 0.0491 max mem: 8299 +Train: [54] [ 500/6250] eta: 0:12:16 lr: 0.000059 grad: 0.0738 (0.0897) loss: 0.8653 (0.8685) time: 0.1221 data: 0.0389 max mem: 8299 +Train: [54] [ 600/6250] eta: 0:11:45 lr: 0.000059 grad: 0.0778 (0.0879) loss: 0.8684 (0.8685) time: 0.1204 data: 0.0384 max mem: 8299 +Train: [54] [ 700/6250] eta: 0:11:20 lr: 0.000059 grad: 0.0823 (0.0869) loss: 0.8677 (0.8686) time: 0.1059 data: 0.0279 max mem: 8299 +Train: [54] [ 800/6250] eta: 0:11:00 lr: 0.000059 grad: 0.0784 (0.0863) loss: 0.8721 (0.8689) time: 0.1096 data: 0.0286 max mem: 8299 +Train: [54] [ 900/6250] eta: 0:10:38 lr: 0.000059 grad: 0.0782 (0.0857) loss: 0.8691 (0.8692) time: 0.1082 data: 0.0291 max mem: 8299 +Train: [54] [1000/6250] eta: 0:10:18 lr: 0.000059 grad: 0.0767 (0.0851) loss: 0.8727 (0.8697) time: 0.0980 data: 0.0253 max mem: 8299 +Train: [54] [1100/6250] eta: 0:10:01 lr: 0.000059 grad: 0.0801 (0.0848) loss: 0.8680 (0.8699) time: 0.1076 data: 0.0345 max mem: 8299 +Train: [54] [1200/6250] eta: 0:09:44 lr: 0.000059 grad: 0.0768 (0.0848) loss: 0.8712 (0.8698) time: 0.1003 data: 0.0283 max mem: 8299 +Train: [54] [1300/6250] eta: 0:09:29 lr: 0.000059 grad: 0.0802 (0.0849) loss: 0.8727 (0.8698) time: 0.0827 data: 0.0089 max mem: 8299 +Train: [54] [1400/6250] eta: 0:09:14 lr: 0.000059 grad: 0.0878 (0.0849) loss: 0.8643 (0.8696) time: 0.1010 data: 0.0258 max mem: 8299 +Train: [54] [1500/6250] eta: 0:09:00 lr: 0.000059 grad: 0.0796 (0.0851) loss: 0.8681 (0.8693) time: 0.1221 data: 0.0551 max mem: 8299 +Train: [54] [1600/6250] eta: 0:08:46 lr: 0.000059 grad: 0.0858 (0.0853) loss: 0.8647 (0.8691) time: 0.1026 data: 0.0229 max mem: 8299 +Train: [54] [1700/6250] eta: 0:08:32 lr: 0.000059 grad: 0.0893 (0.0855) loss: 0.8605 (0.8689) time: 0.0983 data: 0.0234 max mem: 8299 +Train: [54] [1800/6250] eta: 0:08:20 lr: 0.000059 grad: 0.0859 (0.0856) loss: 0.8667 (0.8687) time: 0.1148 data: 0.0403 max mem: 8299 +Train: [54] [1900/6250] eta: 0:08:06 lr: 0.000059 grad: 0.0854 (0.0857) loss: 0.8707 (0.8685) time: 0.0952 data: 0.0215 max mem: 8299 +Train: [54] [2000/6250] eta: 0:07:55 lr: 0.000059 grad: 0.0948 (0.0860) loss: 0.8678 (0.8682) time: 0.0952 data: 0.0178 max mem: 8299 +Train: [54] [2100/6250] eta: 0:07:42 lr: 0.000059 grad: 0.0791 (0.0863) loss: 0.8644 (0.8679) time: 0.1045 data: 0.0343 max mem: 8299 +Train: [54] [2200/6250] eta: 0:07:30 lr: 0.000059 grad: 0.0958 (0.0867) loss: 0.8668 (0.8677) time: 0.0944 data: 0.0115 max mem: 8299 +Train: [54] [2300/6250] eta: 0:07:18 lr: 0.000059 grad: 0.0880 (0.0869) loss: 0.8607 (0.8675) time: 0.1057 data: 0.0256 max mem: 8299 +Train: [54] [2400/6250] eta: 0:07:07 lr: 0.000059 grad: 0.0804 (0.0869) loss: 0.8703 (0.8675) time: 0.1020 data: 0.0302 max mem: 8299 +Train: [54] [2500/6250] eta: 0:06:56 lr: 0.000059 grad: 0.0917 (0.0872) loss: 0.8648 (0.8673) time: 0.1129 data: 0.0400 max mem: 8299 +Train: [54] [2600/6250] eta: 0:06:45 lr: 0.000059 grad: 0.0863 (0.0874) loss: 0.8629 (0.8672) time: 0.1114 data: 0.0435 max mem: 8299 +Train: [54] [2700/6250] eta: 0:06:34 lr: 0.000059 grad: 0.0922 (0.0875) loss: 0.8573 (0.8670) time: 0.0916 data: 0.0148 max mem: 8299 +Train: [54] [2800/6250] eta: 0:06:23 lr: 0.000058 grad: 0.0897 (0.0878) loss: 0.8693 (0.8669) time: 0.1074 data: 0.0400 max mem: 8299 +Train: [54] [2900/6250] eta: 0:06:12 lr: 0.000058 grad: 0.0842 (0.0879) loss: 0.8675 (0.8667) time: 0.1173 data: 0.0430 max mem: 8299 +Train: [54] [3000/6250] eta: 0:06:01 lr: 0.000058 grad: 0.0833 (0.0880) loss: 0.8645 (0.8665) time: 0.1020 data: 0.0318 max mem: 8299 +Train: [54] [3100/6250] eta: 0:05:50 lr: 0.000058 grad: 0.0905 (0.0881) loss: 0.8673 (0.8663) time: 0.1118 data: 0.0381 max mem: 8299 +Train: [54] [3200/6250] eta: 0:05:39 lr: 0.000058 grad: 0.0812 (0.0881) loss: 0.8665 (0.8663) time: 0.0972 data: 0.0233 max mem: 8299 +Train: [54] [3300/6250] eta: 0:05:29 lr: 0.000058 grad: 0.0876 (0.0881) loss: 0.8593 (0.8662) time: 0.1405 data: 0.0624 max mem: 8299 +Train: [54] [3400/6250] eta: 0:05:17 lr: 0.000058 grad: 0.0848 (0.0881) loss: 0.8620 (0.8661) time: 0.1182 data: 0.0412 max mem: 8299 +Train: [54] [3500/6250] eta: 0:05:06 lr: 0.000058 grad: 0.0846 (0.0880) loss: 0.8595 (0.8660) time: 0.1048 data: 0.0225 max mem: 8299 +Train: [54] [3600/6250] eta: 0:04:55 lr: 0.000058 grad: 0.0765 (0.0880) loss: 0.8636 (0.8659) time: 0.1217 data: 0.0501 max mem: 8299 +Train: [54] [3700/6250] eta: 0:04:44 lr: 0.000058 grad: 0.0823 (0.0879) loss: 0.8735 (0.8659) time: 0.1071 data: 0.0353 max mem: 8299 +Train: [54] [3800/6250] eta: 0:04:33 lr: 0.000058 grad: 0.0864 (0.0878) loss: 0.8643 (0.8659) time: 0.1229 data: 0.0528 max mem: 8299 +Train: [54] [3900/6250] eta: 0:04:22 lr: 0.000058 grad: 0.0788 (0.0877) loss: 0.8645 (0.8659) time: 0.1250 data: 0.0541 max mem: 8299 +Train: [54] [4000/6250] eta: 0:04:11 lr: 0.000058 grad: 0.0858 (0.0877) loss: 0.8708 (0.8659) time: 0.1116 data: 0.0429 max mem: 8299 +Train: [54] [4100/6250] eta: 0:03:59 lr: 0.000058 grad: 0.0810 (0.0877) loss: 0.8674 (0.8659) time: 0.0922 data: 0.0205 max mem: 8299 +Train: [54] [4200/6250] eta: 0:03:48 lr: 0.000058 grad: 0.0839 (0.0877) loss: 0.8654 (0.8658) time: 0.1119 data: 0.0453 max mem: 8299 +Train: [54] [4300/6250] eta: 0:03:37 lr: 0.000058 grad: 0.0853 (0.0876) loss: 0.8677 (0.8658) time: 0.0880 data: 0.0162 max mem: 8299 +Train: [54] [4400/6250] eta: 0:03:26 lr: 0.000058 grad: 0.0889 (0.0876) loss: 0.8571 (0.8657) time: 0.1246 data: 0.0539 max mem: 8299 +Train: [54] [4500/6250] eta: 0:03:15 lr: 0.000058 grad: 0.0787 (0.0876) loss: 0.8633 (0.8656) time: 0.1171 data: 0.0457 max mem: 8299 +Train: [54] [4600/6250] eta: 0:03:04 lr: 0.000058 grad: 0.0746 (0.0876) loss: 0.8677 (0.8655) time: 0.1035 data: 0.0307 max mem: 8299 +Train: [54] [4700/6250] eta: 0:02:53 lr: 0.000058 grad: 0.0891 (0.0877) loss: 0.8592 (0.8654) time: 0.1321 data: 0.0560 max mem: 8299 +Train: [54] [4800/6250] eta: 0:02:42 lr: 0.000058 grad: 0.0866 (0.0878) loss: 0.8600 (0.8653) time: 0.0967 data: 0.0264 max mem: 8299 +Train: [54] [4900/6250] eta: 0:02:31 lr: 0.000058 grad: 0.0902 (0.0878) loss: 0.8585 (0.8652) time: 0.1179 data: 0.0536 max mem: 8299 +Train: [54] [5000/6250] eta: 0:02:20 lr: 0.000058 grad: 0.0873 (0.0878) loss: 0.8568 (0.8651) time: 0.1132 data: 0.0448 max mem: 8299 +Train: [54] [5100/6250] eta: 0:02:09 lr: 0.000058 grad: 0.0861 (0.0878) loss: 0.8664 (0.8651) time: 0.1162 data: 0.0403 max mem: 8299 +Train: [54] [5200/6250] eta: 0:01:58 lr: 0.000058 grad: 0.0809 (0.0878) loss: 0.8709 (0.8650) time: 0.1393 data: 0.0679 max mem: 8299 +Train: [54] [5300/6250] eta: 0:01:47 lr: 0.000058 grad: 0.0811 (0.0879) loss: 0.8731 (0.8650) time: 0.1364 data: 0.0604 max mem: 8299 +Train: [54] [5400/6250] eta: 0:01:36 lr: 0.000058 grad: 0.0883 (0.0879) loss: 0.8636 (0.8650) time: 0.1395 data: 0.0681 max mem: 8299 +Train: [54] [5500/6250] eta: 0:01:25 lr: 0.000058 grad: 0.0817 (0.0879) loss: 0.8692 (0.8650) time: 0.1369 data: 0.0632 max mem: 8299 +Train: [54] [5600/6250] eta: 0:01:14 lr: 0.000058 grad: 0.0847 (0.0880) loss: 0.8682 (0.8650) time: 0.1175 data: 0.0389 max mem: 8299 +Train: [54] [5700/6250] eta: 0:01:02 lr: 0.000058 grad: 0.0855 (0.0881) loss: 0.8608 (0.8650) time: 0.1185 data: 0.0452 max mem: 8299 +Train: [54] [5800/6250] eta: 0:00:51 lr: 0.000057 grad: 0.0844 (0.0881) loss: 0.8662 (0.8650) time: 0.1061 data: 0.0337 max mem: 8299 +Train: [54] [5900/6250] eta: 0:00:39 lr: 0.000057 grad: 0.0821 (0.0881) loss: 0.8724 (0.8649) time: 0.1160 data: 0.0425 max mem: 8299 +Train: [54] [6000/6250] eta: 0:00:28 lr: 0.000057 grad: 0.0849 (0.0882) loss: 0.8687 (0.8650) time: 0.1157 data: 0.0371 max mem: 8299 +Train: [54] [6100/6250] eta: 0:00:17 lr: 0.000057 grad: 0.0844 (0.0882) loss: 0.8648 (0.8649) time: 0.0837 data: 0.0002 max mem: 8299 +Train: [54] [6200/6250] eta: 0:00:05 lr: 0.000057 grad: 0.0868 (0.0882) loss: 0.8653 (0.8649) time: 0.1187 data: 0.0402 max mem: 8299 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.0765 (0.0882) loss: 0.8644 (0.8649) time: 0.1085 data: 0.0247 max mem: 8299 +Train: [54] Total time: 0:11:56 (0.1146 s / it) +Averaged stats: lr: 0.000057 grad: 0.0765 (0.0882) loss: 0.8644 (0.8649) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:04:16 loss: 0.8925 (0.8925) time: 4.1422 data: 4.1117 max mem: 8299 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8838 (0.8835) time: 0.1203 data: 0.0958 max mem: 8299 +Eval (hcp-train-subset): [54] Total time: 0:00:11 (0.1848 s / it) +Averaged stats (hcp-train-subset): loss: 0.8838 (0.8835) +Making plots (hcp-train-subset): example=12 +Eval (hcp-val): [54] [ 0/62] eta: 0:04:15 loss: 0.8815 (0.8815) time: 4.1194 data: 4.0910 max mem: 8299 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8823 (0.8839) time: 0.1138 data: 0.0896 max mem: 8299 +Eval (hcp-val): [54] Total time: 0:00:11 (0.1831 s / it) +Averaged stats (hcp-val): loss: 0.8823 (0.8839) +Making plots (hcp-val): example=36 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 8:41:53 lr: 0.000057 grad: 0.0593 (0.0593) loss: 0.9146 (0.9146) time: 5.0101 data: 4.8923 max mem: 8299 +Train: [55] [ 100/6250] eta: 0:16:13 lr: 0.000057 grad: 0.0749 (0.0912) loss: 0.8730 (0.8824) time: 0.1106 data: 0.0373 max mem: 8299 +Train: [55] [ 200/6250] eta: 0:14:00 lr: 0.000057 grad: 0.0698 (0.0899) loss: 0.8657 (0.8765) time: 0.1090 data: 0.0244 max mem: 8299 +Train: [55] [ 300/6250] eta: 0:13:09 lr: 0.000057 grad: 0.0776 (0.0893) loss: 0.8617 (0.8732) time: 0.1169 data: 0.0418 max mem: 8299 +Train: [55] [ 400/6250] eta: 0:12:27 lr: 0.000057 grad: 0.0733 (0.0879) loss: 0.8722 (0.8720) time: 0.1198 data: 0.0366 max mem: 8299 +Train: [55] [ 500/6250] eta: 0:11:56 lr: 0.000057 grad: 0.0826 (0.0877) loss: 0.8651 (0.8708) time: 0.1117 data: 0.0391 max mem: 8299 +Train: [55] [ 600/6250] eta: 0:11:29 lr: 0.000057 grad: 0.0812 (0.0880) loss: 0.8631 (0.8698) time: 0.1163 data: 0.0388 max mem: 8299 +Train: [55] [ 700/6250] eta: 0:11:05 lr: 0.000057 grad: 0.0841 (0.0875) loss: 0.8661 (0.8693) time: 0.1036 data: 0.0275 max mem: 8299 +Train: [55] [ 800/6250] eta: 0:10:50 lr: 0.000057 grad: 0.0804 (0.0871) loss: 0.8692 (0.8692) time: 0.1065 data: 0.0423 max mem: 8299 +Train: [55] [ 900/6250] eta: 0:10:34 lr: 0.000057 grad: 0.0813 (0.0869) loss: 0.8673 (0.8687) time: 0.1082 data: 0.0342 max mem: 8299 +Train: [55] [1000/6250] eta: 0:10:20 lr: 0.000057 grad: 0.0781 (0.0865) loss: 0.8686 (0.8685) time: 0.1219 data: 0.0508 max mem: 8299 +Train: [55] [1100/6250] eta: 0:10:09 lr: 0.000057 grad: 0.0824 (0.0865) loss: 0.8582 (0.8679) time: 0.1209 data: 0.0560 max mem: 8299 +Train: [55] [1200/6250] eta: 0:09:55 lr: 0.000057 grad: 0.0896 (0.0866) loss: 0.8625 (0.8674) time: 0.1186 data: 0.0502 max mem: 8299 +Train: [55] [1300/6250] eta: 0:09:42 lr: 0.000057 grad: 0.0898 (0.0867) loss: 0.8677 (0.8671) time: 0.1104 data: 0.0341 max mem: 8299 +Train: [55] [1400/6250] eta: 0:09:29 lr: 0.000057 grad: 0.0914 (0.0866) loss: 0.8625 (0.8669) time: 0.1160 data: 0.0474 max mem: 8299 +Train: [55] [1500/6250] eta: 0:09:18 lr: 0.000057 grad: 0.0797 (0.0868) loss: 0.8609 (0.8666) time: 0.1273 data: 0.0631 max mem: 8299 +Train: [55] [1600/6250] eta: 0:09:06 lr: 0.000057 grad: 0.0923 (0.0869) loss: 0.8666 (0.8665) time: 0.0962 data: 0.0227 max mem: 8299 +Train: [55] [1700/6250] eta: 0:08:54 lr: 0.000057 grad: 0.0872 (0.0870) loss: 0.8645 (0.8663) time: 0.1283 data: 0.0584 max mem: 8299 +Train: [55] [1800/6250] eta: 0:08:42 lr: 0.000057 grad: 0.0880 (0.0871) loss: 0.8618 (0.8661) time: 0.1316 data: 0.0551 max mem: 8299 +Train: [55] [1900/6250] eta: 0:08:29 lr: 0.000057 grad: 0.0872 (0.0872) loss: 0.8639 (0.8660) time: 0.1169 data: 0.0398 max mem: 8299 +Train: [55] [2000/6250] eta: 0:08:17 lr: 0.000057 grad: 0.0895 (0.0872) loss: 0.8649 (0.8659) time: 0.1133 data: 0.0379 max mem: 8299 +Train: [55] [2100/6250] eta: 0:08:05 lr: 0.000057 grad: 0.0903 (0.0874) loss: 0.8561 (0.8658) time: 0.1214 data: 0.0441 max mem: 8299 +Train: [55] [2200/6250] eta: 0:07:53 lr: 0.000057 grad: 0.0891 (0.0875) loss: 0.8679 (0.8656) time: 0.0822 data: 0.0002 max mem: 8299 +Train: [55] [2300/6250] eta: 0:07:41 lr: 0.000057 grad: 0.0882 (0.0876) loss: 0.8644 (0.8655) time: 0.1187 data: 0.0458 max mem: 8299 +Train: [55] [2400/6250] eta: 0:07:30 lr: 0.000057 grad: 0.0852 (0.0878) loss: 0.8611 (0.8655) time: 0.1317 data: 0.0591 max mem: 8299 +Train: [55] [2500/6250] eta: 0:07:17 lr: 0.000057 grad: 0.0922 (0.0879) loss: 0.8591 (0.8654) time: 0.1098 data: 0.0402 max mem: 8299 +Train: [55] [2600/6250] eta: 0:07:06 lr: 0.000056 grad: 0.0841 (0.0880) loss: 0.8619 (0.8653) time: 0.0997 data: 0.0231 max mem: 8299 +Train: [55] [2700/6250] eta: 0:06:55 lr: 0.000056 grad: 0.0811 (0.0881) loss: 0.8609 (0.8652) time: 0.1075 data: 0.0335 max mem: 8299 +Train: [55] [2800/6250] eta: 0:06:43 lr: 0.000056 grad: 0.0853 (0.0882) loss: 0.8622 (0.8651) time: 0.1087 data: 0.0342 max mem: 8299 +Train: [55] [2900/6250] eta: 0:06:31 lr: 0.000056 grad: 0.0903 (0.0884) loss: 0.8686 (0.8649) time: 0.1168 data: 0.0500 max mem: 8299 +Train: [55] [3000/6250] eta: 0:06:19 lr: 0.000056 grad: 0.0864 (0.0885) loss: 0.8576 (0.8648) time: 0.0944 data: 0.0165 max mem: 8299 +Train: [55] [3100/6250] eta: 0:06:07 lr: 0.000056 grad: 0.0849 (0.0885) loss: 0.8631 (0.8648) time: 0.1100 data: 0.0411 max mem: 8299 +Train: [55] [3200/6250] eta: 0:05:55 lr: 0.000056 grad: 0.0868 (0.0886) loss: 0.8591 (0.8646) time: 0.1122 data: 0.0444 max mem: 8299 +Train: [55] [3300/6250] eta: 0:05:44 lr: 0.000056 grad: 0.0971 (0.0887) loss: 0.8633 (0.8646) time: 0.1195 data: 0.0501 max mem: 8299 +Train: [55] [3400/6250] eta: 0:05:32 lr: 0.000056 grad: 0.0865 (0.0887) loss: 0.8687 (0.8646) time: 0.1144 data: 0.0423 max mem: 8299 +Train: [55] [3500/6250] eta: 0:05:21 lr: 0.000056 grad: 0.0906 (0.0887) loss: 0.8673 (0.8646) time: 0.1119 data: 0.0463 max mem: 8299 +Train: [55] [3600/6250] eta: 0:05:09 lr: 0.000056 grad: 0.0886 (0.0888) loss: 0.8653 (0.8646) time: 0.0932 data: 0.0230 max mem: 8299 +Train: [55] [3700/6250] eta: 0:04:58 lr: 0.000056 grad: 0.0824 (0.0889) loss: 0.8725 (0.8646) time: 0.1753 data: 0.1057 max mem: 8299 +Train: [55] [3800/6250] eta: 0:04:46 lr: 0.000056 grad: 0.0837 (0.0889) loss: 0.8666 (0.8646) time: 0.1204 data: 0.0494 max mem: 8299 +Train: [55] [3900/6250] eta: 0:04:35 lr: 0.000056 grad: 0.0880 (0.0890) loss: 0.8690 (0.8646) time: 0.1091 data: 0.0406 max mem: 8299 +Train: [55] [4000/6250] eta: 0:04:23 lr: 0.000056 grad: 0.0881 (0.0891) loss: 0.8670 (0.8646) time: 0.1080 data: 0.0337 max mem: 8299 +Train: [55] [4100/6250] eta: 0:04:11 lr: 0.000056 grad: 0.0884 (0.0892) loss: 0.8669 (0.8646) time: 0.1174 data: 0.0400 max mem: 8299 +Train: [55] [4200/6250] eta: 0:04:00 lr: 0.000056 grad: 0.0850 (0.0892) loss: 0.8642 (0.8645) time: 0.1212 data: 0.0588 max mem: 8299 +Train: [55] [4300/6250] eta: 0:03:48 lr: 0.000056 grad: 0.0853 (0.0892) loss: 0.8668 (0.8646) time: 0.1132 data: 0.0287 max mem: 8299 +Train: [55] [4400/6250] eta: 0:03:37 lr: 0.000056 grad: 0.0904 (0.0893) loss: 0.8695 (0.8646) time: 0.0830 data: 0.0097 max mem: 8299 +Train: [55] [4500/6250] eta: 0:03:25 lr: 0.000056 grad: 0.0873 (0.0894) loss: 0.8634 (0.8646) time: 0.1085 data: 0.0388 max mem: 8299 +Train: [55] [4600/6250] eta: 0:03:13 lr: 0.000056 grad: 0.0838 (0.0893) loss: 0.8628 (0.8645) time: 0.1248 data: 0.0514 max mem: 8299 +Train: [55] [4700/6250] eta: 0:03:01 lr: 0.000056 grad: 0.0917 (0.0894) loss: 0.8667 (0.8645) time: 0.1063 data: 0.0322 max mem: 8299 +Train: [55] [4800/6250] eta: 0:02:50 lr: 0.000056 grad: 0.0826 (0.0894) loss: 0.8670 (0.8644) time: 0.1529 data: 0.0876 max mem: 8299 +Train: [55] [4900/6250] eta: 0:02:38 lr: 0.000056 grad: 0.0830 (0.0894) loss: 0.8674 (0.8644) time: 0.1109 data: 0.0301 max mem: 8299 +Train: [55] [5000/6250] eta: 0:02:27 lr: 0.000056 grad: 0.0880 (0.0894) loss: 0.8635 (0.8644) time: 0.1688 data: 0.1031 max mem: 8299 +Train: [55] [5100/6250] eta: 0:02:15 lr: 0.000056 grad: 0.0855 (0.0894) loss: 0.8616 (0.8643) time: 0.1288 data: 0.0571 max mem: 8299 +Train: [55] [5200/6250] eta: 0:02:03 lr: 0.000056 grad: 0.0933 (0.0895) loss: 0.8630 (0.8643) time: 0.1359 data: 0.0650 max mem: 8299 +Train: [55] [5300/6250] eta: 0:01:52 lr: 0.000056 grad: 0.0886 (0.0895) loss: 0.8613 (0.8643) time: 0.1307 data: 0.0615 max mem: 8299 +Train: [55] [5400/6250] eta: 0:01:40 lr: 0.000056 grad: 0.0865 (0.0895) loss: 0.8674 (0.8642) time: 0.1067 data: 0.0344 max mem: 8299 +Train: [55] [5500/6250] eta: 0:01:28 lr: 0.000056 grad: 0.0931 (0.0896) loss: 0.8488 (0.8641) time: 0.1213 data: 0.0520 max mem: 8299 +Train: [55] [5600/6250] eta: 0:01:17 lr: 0.000055 grad: 0.0927 (0.0897) loss: 0.8607 (0.8640) time: 0.1287 data: 0.0574 max mem: 8299 +Train: [55] [5700/6250] eta: 0:01:05 lr: 0.000055 grad: 0.0883 (0.0898) loss: 0.8565 (0.8639) time: 0.1252 data: 0.0560 max mem: 8299 +Train: [55] [5800/6250] eta: 0:00:53 lr: 0.000055 grad: 0.0905 (0.0899) loss: 0.8542 (0.8638) time: 0.0933 data: 0.0132 max mem: 8299 +Train: [55] [5900/6250] eta: 0:00:41 lr: 0.000055 grad: 0.0911 (0.0899) loss: 0.8615 (0.8638) time: 0.1026 data: 0.0304 max mem: 8299 +Train: [55] [6000/6250] eta: 0:00:29 lr: 0.000055 grad: 0.0889 (0.0900) loss: 0.8570 (0.8637) time: 0.1093 data: 0.0375 max mem: 8299 +Train: [55] [6100/6250] eta: 0:00:17 lr: 0.000055 grad: 0.0885 (0.0901) loss: 0.8609 (0.8637) time: 0.1017 data: 0.0299 max mem: 8299 +Train: [55] [6200/6250] eta: 0:00:05 lr: 0.000055 grad: 0.0899 (0.0901) loss: 0.8619 (0.8636) time: 0.1064 data: 0.0363 max mem: 8299 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.0849 (0.0901) loss: 0.8587 (0.8636) time: 0.1134 data: 0.0372 max mem: 8299 +Train: [55] Total time: 0:12:20 (0.1185 s / it) +Averaged stats: lr: 0.000055 grad: 0.0849 (0.0901) loss: 0.8587 (0.8636) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:04:55 loss: 0.8909 (0.8909) time: 4.7588 data: 4.7280 max mem: 8299 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8798 (0.8806) time: 0.1127 data: 0.0884 max mem: 8299 +Eval (hcp-train-subset): [55] Total time: 0:00:11 (0.1864 s / it) +Averaged stats (hcp-train-subset): loss: 0.8798 (0.8806) +Eval (hcp-val): [55] [ 0/62] eta: 0:04:16 loss: 0.8830 (0.8830) time: 4.1372 data: 4.1082 max mem: 8299 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8819 (0.8833) time: 0.0996 data: 0.0744 max mem: 8299 +Eval (hcp-val): [55] Total time: 0:00:11 (0.1781 s / it) +Averaged stats (hcp-val): loss: 0.8819 (0.8833) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 6:43:47 lr: 0.000055 grad: 0.1320 (0.1320) loss: 0.9014 (0.9014) time: 3.8763 data: 3.6450 max mem: 8299 +Train: [56] [ 100/6250] eta: 0:16:06 lr: 0.000055 grad: 0.0751 (0.0984) loss: 0.8810 (0.8804) time: 0.1089 data: 0.0162 max mem: 8299 +Train: [56] [ 200/6250] eta: 0:13:57 lr: 0.000055 grad: 0.0762 (0.0910) loss: 0.8764 (0.8768) time: 0.1171 data: 0.0300 max mem: 8299 +Train: [56] [ 300/6250] eta: 0:13:09 lr: 0.000055 grad: 0.0824 (0.0900) loss: 0.8576 (0.8729) time: 0.1147 data: 0.0287 max mem: 8299 +Train: [56] [ 400/6250] eta: 0:12:33 lr: 0.000055 grad: 0.0877 (0.0889) loss: 0.8592 (0.8702) time: 0.1253 data: 0.0413 max mem: 8299 +Train: [56] [ 500/6250] eta: 0:12:01 lr: 0.000055 grad: 0.0783 (0.0886) loss: 0.8542 (0.8681) time: 0.1103 data: 0.0292 max mem: 8299 +Train: [56] [ 600/6250] eta: 0:11:32 lr: 0.000055 grad: 0.0865 (0.0885) loss: 0.8638 (0.8664) time: 0.1119 data: 0.0315 max mem: 8299 +Train: [56] [ 700/6250] eta: 0:11:12 lr: 0.000055 grad: 0.0800 (0.0882) loss: 0.8663 (0.8655) time: 0.1128 data: 0.0315 max mem: 8299 +Train: [56] [ 800/6250] eta: 0:10:53 lr: 0.000055 grad: 0.0881 (0.0879) loss: 0.8598 (0.8652) time: 0.1151 data: 0.0382 max mem: 8299 +Train: [56] [ 900/6250] eta: 0:10:35 lr: 0.000055 grad: 0.0752 (0.0874) loss: 0.8676 (0.8649) time: 0.1173 data: 0.0377 max mem: 8299 +Train: [56] [1000/6250] eta: 0:10:22 lr: 0.000055 grad: 0.0793 (0.0870) loss: 0.8647 (0.8648) time: 0.1165 data: 0.0447 max mem: 8299 +Train: [56] [1100/6250] eta: 0:10:11 lr: 0.000055 grad: 0.0800 (0.0865) loss: 0.8595 (0.8647) time: 0.1294 data: 0.0590 max mem: 8299 +Train: [56] [1200/6250] eta: 0:09:55 lr: 0.000055 grad: 0.0781 (0.0863) loss: 0.8710 (0.8646) time: 0.1065 data: 0.0370 max mem: 8299 +Train: [56] [1300/6250] eta: 0:09:39 lr: 0.000055 grad: 0.0807 (0.0861) loss: 0.8654 (0.8644) time: 0.1078 data: 0.0411 max mem: 8299 +Train: [56] [1400/6250] eta: 0:09:27 lr: 0.000055 grad: 0.0792 (0.0859) loss: 0.8664 (0.8643) time: 0.1203 data: 0.0481 max mem: 8299 +Train: [56] [1500/6250] eta: 0:09:14 lr: 0.000055 grad: 0.0841 (0.0858) loss: 0.8540 (0.8641) time: 0.1288 data: 0.0565 max mem: 8299 +Train: [56] [1600/6250] eta: 0:09:02 lr: 0.000055 grad: 0.0861 (0.0859) loss: 0.8613 (0.8638) time: 0.1203 data: 0.0489 max mem: 8299 +Train: [56] [1700/6250] eta: 0:08:49 lr: 0.000055 grad: 0.0836 (0.0860) loss: 0.8594 (0.8636) time: 0.0898 data: 0.0150 max mem: 8299 +Train: [56] [1800/6250] eta: 0:08:38 lr: 0.000055 grad: 0.0787 (0.0861) loss: 0.8568 (0.8634) time: 0.1286 data: 0.0573 max mem: 8299 +Train: [56] [1900/6250] eta: 0:08:26 lr: 0.000055 grad: 0.0904 (0.0863) loss: 0.8616 (0.8633) time: 0.1217 data: 0.0496 max mem: 8299 +Train: [56] [2000/6250] eta: 0:08:14 lr: 0.000055 grad: 0.0883 (0.0865) loss: 0.8524 (0.8631) time: 0.1119 data: 0.0412 max mem: 8299 +Train: [56] [2100/6250] eta: 0:08:03 lr: 0.000055 grad: 0.0812 (0.0866) loss: 0.8601 (0.8629) time: 0.1158 data: 0.0439 max mem: 8299 +Train: [56] [2200/6250] eta: 0:07:51 lr: 0.000055 grad: 0.0853 (0.0868) loss: 0.8567 (0.8627) time: 0.1380 data: 0.0645 max mem: 8299 +Train: [56] [2300/6250] eta: 0:07:39 lr: 0.000055 grad: 0.0913 (0.0869) loss: 0.8620 (0.8625) time: 0.1201 data: 0.0499 max mem: 8299 +Train: [56] [2400/6250] eta: 0:07:29 lr: 0.000054 grad: 0.0823 (0.0870) loss: 0.8533 (0.8624) time: 0.1456 data: 0.0751 max mem: 8299 +Train: [56] [2500/6250] eta: 0:07:16 lr: 0.000054 grad: 0.0887 (0.0871) loss: 0.8603 (0.8624) time: 0.1108 data: 0.0352 max mem: 8299 +Train: [56] [2600/6250] eta: 0:07:04 lr: 0.000054 grad: 0.0878 (0.0872) loss: 0.8525 (0.8623) time: 0.1035 data: 0.0289 max mem: 8299 +Train: [56] [2700/6250] eta: 0:06:54 lr: 0.000054 grad: 0.0871 (0.0873) loss: 0.8563 (0.8622) time: 0.1177 data: 0.0372 max mem: 8299 +Train: [56] [2800/6250] eta: 0:06:42 lr: 0.000054 grad: 0.0877 (0.0874) loss: 0.8596 (0.8622) time: 0.1251 data: 0.0539 max mem: 8299 +Train: [56] [2900/6250] eta: 0:06:31 lr: 0.000054 grad: 0.0849 (0.0874) loss: 0.8636 (0.8622) time: 0.1608 data: 0.0928 max mem: 8299 +Train: [56] [3000/6250] eta: 0:06:18 lr: 0.000054 grad: 0.0841 (0.0874) loss: 0.8622 (0.8622) time: 0.1099 data: 0.0401 max mem: 8299 +Train: [56] [3100/6250] eta: 0:06:07 lr: 0.000054 grad: 0.0862 (0.0875) loss: 0.8629 (0.8623) time: 0.1135 data: 0.0410 max mem: 8299 +Train: [56] [3200/6250] eta: 0:05:55 lr: 0.000054 grad: 0.0898 (0.0876) loss: 0.8655 (0.8623) time: 0.1282 data: 0.0537 max mem: 8299 +Train: [56] [3300/6250] eta: 0:05:44 lr: 0.000054 grad: 0.0888 (0.0876) loss: 0.8666 (0.8623) time: 0.1159 data: 0.0403 max mem: 8299 +Train: [56] [3400/6250] eta: 0:05:32 lr: 0.000054 grad: 0.0862 (0.0877) loss: 0.8646 (0.8622) time: 0.1031 data: 0.0364 max mem: 8299 +Train: [56] [3500/6250] eta: 0:05:20 lr: 0.000054 grad: 0.0880 (0.0879) loss: 0.8558 (0.8622) time: 0.1115 data: 0.0363 max mem: 8299 +Train: [56] [3600/6250] eta: 0:05:09 lr: 0.000054 grad: 0.0858 (0.0880) loss: 0.8586 (0.8622) time: 0.1134 data: 0.0417 max mem: 8299 +Train: [56] [3700/6250] eta: 0:04:58 lr: 0.000054 grad: 0.0856 (0.0881) loss: 0.8666 (0.8621) time: 0.1329 data: 0.0585 max mem: 8299 +Train: [56] [3800/6250] eta: 0:04:46 lr: 0.000054 grad: 0.0882 (0.0881) loss: 0.8586 (0.8620) time: 0.1219 data: 0.0496 max mem: 8299 +Train: [56] [3900/6250] eta: 0:04:35 lr: 0.000054 grad: 0.0838 (0.0882) loss: 0.8577 (0.8619) time: 0.1189 data: 0.0505 max mem: 8299 +Train: [56] [4000/6250] eta: 0:04:23 lr: 0.000054 grad: 0.0946 (0.0884) loss: 0.8640 (0.8618) time: 0.1263 data: 0.0507 max mem: 8299 +Train: [56] [4100/6250] eta: 0:04:12 lr: 0.000054 grad: 0.0864 (0.0885) loss: 0.8541 (0.8618) time: 0.1293 data: 0.0554 max mem: 8299 +Train: [56] [4200/6250] eta: 0:04:00 lr: 0.000054 grad: 0.0942 (0.0886) loss: 0.8570 (0.8617) time: 0.0986 data: 0.0280 max mem: 8299 +Train: [56] [4300/6250] eta: 0:03:48 lr: 0.000054 grad: 0.0939 (0.0887) loss: 0.8505 (0.8615) time: 0.1171 data: 0.0461 max mem: 8299 +Train: [56] [4400/6250] eta: 0:03:37 lr: 0.000054 grad: 0.0887 (0.0889) loss: 0.8522 (0.8614) time: 0.1168 data: 0.0400 max mem: 8299 +Train: [56] [4500/6250] eta: 0:03:25 lr: 0.000054 grad: 0.0957 (0.0890) loss: 0.8538 (0.8613) time: 0.1221 data: 0.0553 max mem: 8299 +Train: [56] [4600/6250] eta: 0:03:13 lr: 0.000054 grad: 0.0867 (0.0893) loss: 0.8606 (0.8613) time: 0.1279 data: 0.0595 max mem: 8299 +Train: [56] [4700/6250] eta: 0:03:02 lr: 0.000054 grad: 0.0927 (0.0894) loss: 0.8563 (0.8612) time: 0.1220 data: 0.0528 max mem: 8299 +Train: [56] [4800/6250] eta: 0:02:50 lr: 0.000054 grad: 0.0922 (0.0896) loss: 0.8603 (0.8611) time: 0.1417 data: 0.0699 max mem: 8299 +Train: [56] [4900/6250] eta: 0:02:38 lr: 0.000054 grad: 0.0950 (0.0897) loss: 0.8582 (0.8611) time: 0.0999 data: 0.0241 max mem: 8299 +Train: [56] [5000/6250] eta: 0:02:27 lr: 0.000054 grad: 0.0916 (0.0897) loss: 0.8595 (0.8611) time: 0.1279 data: 0.0622 max mem: 8299 +Train: [56] [5100/6250] eta: 0:02:15 lr: 0.000054 grad: 0.0841 (0.0898) loss: 0.8630 (0.8611) time: 0.1228 data: 0.0553 max mem: 8299 +Train: [56] [5200/6250] eta: 0:02:03 lr: 0.000054 grad: 0.0881 (0.0898) loss: 0.8653 (0.8611) time: 0.1222 data: 0.0580 max mem: 8299 +Train: [56] [5300/6250] eta: 0:01:52 lr: 0.000054 grad: 0.0875 (0.0899) loss: 0.8593 (0.8611) time: 0.1337 data: 0.0630 max mem: 8299 +Train: [56] [5400/6250] eta: 0:01:40 lr: 0.000054 grad: 0.0860 (0.0899) loss: 0.8603 (0.8611) time: 0.1391 data: 0.0701 max mem: 8299 +Train: [56] [5500/6250] eta: 0:01:29 lr: 0.000053 grad: 0.0872 (0.0900) loss: 0.8587 (0.8611) time: 0.1300 data: 0.0640 max mem: 8299 +Train: [56] [5600/6250] eta: 0:01:17 lr: 0.000053 grad: 0.0952 (0.0901) loss: 0.8591 (0.8611) time: 0.1253 data: 0.0555 max mem: 8299 +Train: [56] [5700/6250] eta: 0:01:05 lr: 0.000053 grad: 0.0953 (0.0901) loss: 0.8587 (0.8612) time: 0.1109 data: 0.0406 max mem: 8299 +Train: [56] [5800/6250] eta: 0:00:53 lr: 0.000053 grad: 0.0939 (0.0902) loss: 0.8561 (0.8612) time: 0.1110 data: 0.0368 max mem: 8299 +Train: [56] [5900/6250] eta: 0:00:41 lr: 0.000053 grad: 0.0904 (0.0903) loss: 0.8664 (0.8612) time: 0.1022 data: 0.0279 max mem: 8299 +Train: [56] [6000/6250] eta: 0:00:29 lr: 0.000053 grad: 0.0907 (0.0903) loss: 0.8676 (0.8612) time: 0.1109 data: 0.0370 max mem: 8299 +Train: [56] [6100/6250] eta: 0:00:17 lr: 0.000053 grad: 0.0887 (0.0903) loss: 0.8601 (0.8613) time: 0.1096 data: 0.0380 max mem: 8299 +Train: [56] [6200/6250] eta: 0:00:05 lr: 0.000053 grad: 0.0873 (0.0903) loss: 0.8671 (0.8613) time: 0.1195 data: 0.0473 max mem: 8299 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.0881 (0.0904) loss: 0.8591 (0.8613) time: 0.1166 data: 0.0419 max mem: 8299 +Train: [56] Total time: 0:12:23 (0.1190 s / it) +Averaged stats: lr: 0.000053 grad: 0.0881 (0.0904) loss: 0.8591 (0.8613) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:03:47 loss: 0.8941 (0.8941) time: 3.6753 data: 3.5871 max mem: 8299 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8801 (0.8829) time: 0.1064 data: 0.0821 max mem: 8299 +Eval (hcp-train-subset): [56] Total time: 0:00:11 (0.1924 s / it) +Averaged stats (hcp-train-subset): loss: 0.8801 (0.8829) +Eval (hcp-val): [56] [ 0/62] eta: 0:03:42 loss: 0.8836 (0.8836) time: 3.5887 data: 3.4926 max mem: 8299 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8808 (0.8833) time: 0.1156 data: 0.0912 max mem: 8299 +Eval (hcp-val): [56] Total time: 0:00:11 (0.1852 s / it) +Averaged stats (hcp-val): loss: 0.8808 (0.8833) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 7:50:26 lr: 0.000053 grad: 0.2162 (0.2162) loss: 0.9213 (0.9213) time: 4.5162 data: 4.3298 max mem: 8299 +Train: [57] [ 100/6250] eta: 0:16:52 lr: 0.000053 grad: 0.0827 (0.1034) loss: 0.8685 (0.8808) time: 0.1168 data: 0.0388 max mem: 8299 +Train: [57] [ 200/6250] eta: 0:14:27 lr: 0.000053 grad: 0.0826 (0.1005) loss: 0.8670 (0.8730) time: 0.1207 data: 0.0441 max mem: 8299 +Train: [57] [ 300/6250] eta: 0:13:39 lr: 0.000053 grad: 0.0801 (0.0972) loss: 0.8617 (0.8704) time: 0.1514 data: 0.0791 max mem: 8299 +Train: [57] [ 400/6250] eta: 0:12:47 lr: 0.000053 grad: 0.0839 (0.0940) loss: 0.8696 (0.8686) time: 0.0976 data: 0.0178 max mem: 8299 +Train: [57] [ 500/6250] eta: 0:12:09 lr: 0.000053 grad: 0.0863 (0.0926) loss: 0.8600 (0.8674) time: 0.0951 data: 0.0214 max mem: 8299 +Train: [57] [ 600/6250] eta: 0:11:41 lr: 0.000053 grad: 0.0868 (0.0920) loss: 0.8538 (0.8664) time: 0.1088 data: 0.0334 max mem: 8299 +Train: [57] [ 700/6250] eta: 0:11:19 lr: 0.000053 grad: 0.0824 (0.0915) loss: 0.8634 (0.8657) time: 0.1093 data: 0.0271 max mem: 8299 +Train: [57] [ 800/6250] eta: 0:10:55 lr: 0.000053 grad: 0.0854 (0.0910) loss: 0.8672 (0.8653) time: 0.1064 data: 0.0306 max mem: 8299 +Train: [57] [ 900/6250] eta: 0:10:41 lr: 0.000053 grad: 0.0846 (0.0911) loss: 0.8586 (0.8649) time: 0.1165 data: 0.0323 max mem: 8299 +Train: [57] [1000/6250] eta: 0:10:27 lr: 0.000053 grad: 0.0784 (0.0906) loss: 0.8690 (0.8648) time: 0.1171 data: 0.0453 max mem: 8299 +Train: [57] [1100/6250] eta: 0:10:12 lr: 0.000053 grad: 0.0885 (0.0903) loss: 0.8566 (0.8644) time: 0.1225 data: 0.0512 max mem: 8299 +Train: [57] [1200/6250] eta: 0:09:57 lr: 0.000053 grad: 0.0950 (0.0903) loss: 0.8538 (0.8638) time: 0.1082 data: 0.0341 max mem: 8299 +Train: [57] [1300/6250] eta: 0:09:46 lr: 0.000053 grad: 0.0898 (0.0902) loss: 0.8528 (0.8633) time: 0.1250 data: 0.0510 max mem: 8299 +Train: [57] [1400/6250] eta: 0:09:33 lr: 0.000053 grad: 0.0907 (0.0903) loss: 0.8504 (0.8628) time: 0.1293 data: 0.0582 max mem: 8299 +Train: [57] [1500/6250] eta: 0:09:21 lr: 0.000053 grad: 0.0864 (0.0903) loss: 0.8484 (0.8624) time: 0.1020 data: 0.0329 max mem: 8299 +Train: [57] [1600/6250] eta: 0:09:08 lr: 0.000053 grad: 0.0911 (0.0903) loss: 0.8607 (0.8621) time: 0.0981 data: 0.0242 max mem: 8299 +Train: [57] [1700/6250] eta: 0:08:57 lr: 0.000053 grad: 0.0886 (0.0905) loss: 0.8568 (0.8616) time: 0.1255 data: 0.0507 max mem: 8299 +Train: [57] [1800/6250] eta: 0:08:44 lr: 0.000053 grad: 0.0859 (0.0905) loss: 0.8601 (0.8613) time: 0.0918 data: 0.0179 max mem: 8299 +Train: [57] [1900/6250] eta: 0:08:32 lr: 0.000053 grad: 0.0817 (0.0904) loss: 0.8532 (0.8609) time: 0.0844 data: 0.0060 max mem: 8299 +Train: [57] [2000/6250] eta: 0:08:19 lr: 0.000053 grad: 0.0836 (0.0904) loss: 0.8557 (0.8608) time: 0.1277 data: 0.0471 max mem: 8299 +Train: [57] [2100/6250] eta: 0:08:07 lr: 0.000053 grad: 0.0915 (0.0906) loss: 0.8641 (0.8606) time: 0.1321 data: 0.0624 max mem: 8299 +Train: [57] [2200/6250] eta: 0:07:56 lr: 0.000053 grad: 0.0967 (0.0908) loss: 0.8541 (0.8605) time: 0.0975 data: 0.0166 max mem: 8299 +Train: [57] [2300/6250] eta: 0:07:43 lr: 0.000052 grad: 0.0882 (0.0909) loss: 0.8570 (0.8603) time: 0.1119 data: 0.0454 max mem: 8299 +Train: [57] [2400/6250] eta: 0:07:32 lr: 0.000052 grad: 0.0913 (0.0910) loss: 0.8571 (0.8602) time: 0.1282 data: 0.0620 max mem: 8299 +Train: [57] [2500/6250] eta: 0:07:20 lr: 0.000052 grad: 0.0934 (0.0911) loss: 0.8553 (0.8600) time: 0.1140 data: 0.0402 max mem: 8299 +Train: [57] [2600/6250] eta: 0:07:08 lr: 0.000052 grad: 0.0907 (0.0911) loss: 0.8588 (0.8599) time: 0.1234 data: 0.0556 max mem: 8299 +Train: [57] [2700/6250] eta: 0:06:56 lr: 0.000052 grad: 0.0940 (0.0912) loss: 0.8581 (0.8598) time: 0.0951 data: 0.0204 max mem: 8299 +Train: [57] [2800/6250] eta: 0:06:44 lr: 0.000052 grad: 0.0901 (0.0912) loss: 0.8656 (0.8598) time: 0.1240 data: 0.0519 max mem: 8299 +Train: [57] [2900/6250] eta: 0:06:33 lr: 0.000052 grad: 0.0883 (0.0912) loss: 0.8572 (0.8599) time: 0.1235 data: 0.0527 max mem: 8299 +Train: [57] [3000/6250] eta: 0:06:22 lr: 0.000052 grad: 0.0947 (0.0913) loss: 0.8613 (0.8599) time: 0.1384 data: 0.0752 max mem: 8299 +Train: [57] [3100/6250] eta: 0:06:10 lr: 0.000052 grad: 0.0912 (0.0914) loss: 0.8604 (0.8599) time: 0.1182 data: 0.0409 max mem: 8299 +Train: [57] [3200/6250] eta: 0:05:58 lr: 0.000052 grad: 0.0875 (0.0914) loss: 0.8605 (0.8599) time: 0.1286 data: 0.0606 max mem: 8299 +Train: [57] [3300/6250] eta: 0:05:47 lr: 0.000052 grad: 0.0848 (0.0915) loss: 0.8537 (0.8598) time: 0.1332 data: 0.0646 max mem: 8299 +Train: [57] [3400/6250] eta: 0:05:35 lr: 0.000052 grad: 0.0935 (0.0916) loss: 0.8616 (0.8598) time: 0.1141 data: 0.0436 max mem: 8299 +Train: [57] [3500/6250] eta: 0:05:23 lr: 0.000052 grad: 0.0919 (0.0916) loss: 0.8575 (0.8598) time: 0.1118 data: 0.0424 max mem: 8299 +Train: [57] [3600/6250] eta: 0:05:11 lr: 0.000052 grad: 0.0914 (0.0917) loss: 0.8565 (0.8598) time: 0.1323 data: 0.0652 max mem: 8299 +Train: [57] [3700/6250] eta: 0:04:59 lr: 0.000052 grad: 0.0906 (0.0918) loss: 0.8656 (0.8598) time: 0.1089 data: 0.0346 max mem: 8299 +Train: [57] [3800/6250] eta: 0:04:47 lr: 0.000052 grad: 0.0971 (0.0919) loss: 0.8590 (0.8598) time: 0.1029 data: 0.0317 max mem: 8299 +Train: [57] [3900/6250] eta: 0:04:36 lr: 0.000052 grad: 0.0883 (0.0920) loss: 0.8599 (0.8599) time: 0.1349 data: 0.0614 max mem: 8299 +Train: [57] [4000/6250] eta: 0:04:24 lr: 0.000052 grad: 0.0893 (0.0920) loss: 0.8645 (0.8600) time: 0.1089 data: 0.0337 max mem: 8299 +Train: [57] [4100/6250] eta: 0:04:12 lr: 0.000052 grad: 0.0894 (0.0921) loss: 0.8631 (0.8600) time: 0.1164 data: 0.0498 max mem: 8299 +Train: [57] [4200/6250] eta: 0:04:00 lr: 0.000052 grad: 0.0866 (0.0922) loss: 0.8610 (0.8601) time: 0.1083 data: 0.0411 max mem: 8299 +Train: [57] [4300/6250] eta: 0:03:49 lr: 0.000052 grad: 0.0912 (0.0922) loss: 0.8618 (0.8601) time: 0.0912 data: 0.0173 max mem: 8299 +Train: [57] [4400/6250] eta: 0:03:37 lr: 0.000052 grad: 0.0880 (0.0923) loss: 0.8593 (0.8601) time: 0.1149 data: 0.0463 max mem: 8299 +Train: [57] [4500/6250] eta: 0:03:26 lr: 0.000052 grad: 0.0901 (0.0923) loss: 0.8613 (0.8601) time: 0.1169 data: 0.0425 max mem: 8299 +Train: [57] [4600/6250] eta: 0:03:14 lr: 0.000052 grad: 0.0966 (0.0925) loss: 0.8593 (0.8601) time: 0.1138 data: 0.0425 max mem: 8299 +Train: [57] [4700/6250] eta: 0:03:02 lr: 0.000052 grad: 0.0853 (0.0924) loss: 0.8672 (0.8601) time: 0.1331 data: 0.0590 max mem: 8299 +Train: [57] [4800/6250] eta: 0:02:50 lr: 0.000052 grad: 0.0911 (0.0925) loss: 0.8564 (0.8601) time: 0.1145 data: 0.0430 max mem: 8299 +Train: [57] [4900/6250] eta: 0:02:39 lr: 0.000052 grad: 0.0872 (0.0925) loss: 0.8694 (0.8602) time: 0.1276 data: 0.0574 max mem: 8299 +Train: [57] [5000/6250] eta: 0:02:27 lr: 0.000052 grad: 0.0840 (0.0927) loss: 0.8635 (0.8602) time: 0.1023 data: 0.0224 max mem: 8299 +Train: [57] [5100/6250] eta: 0:02:16 lr: 0.000052 grad: 0.0887 (0.0926) loss: 0.8654 (0.8603) time: 0.1336 data: 0.0558 max mem: 8299 +Train: [57] [5200/6250] eta: 0:02:04 lr: 0.000052 grad: 0.0939 (0.0930) loss: 0.8576 (0.8604) time: 0.1306 data: 0.0579 max mem: 8299 +Train: [57] [5300/6250] eta: 0:01:52 lr: 0.000052 grad: 0.0909 (0.0934) loss: 0.8652 (0.8604) time: 0.1326 data: 0.0467 max mem: 8299 +Train: [57] [5400/6250] eta: 0:01:41 lr: 0.000051 grad: 0.0867 (0.0934) loss: 0.8642 (0.8604) time: 0.1139 data: 0.0453 max mem: 8299 +Train: [57] [5500/6250] eta: 0:01:29 lr: 0.000051 grad: 0.0883 (0.0934) loss: 0.8710 (0.8604) time: 0.1035 data: 0.0311 max mem: 8299 +Train: [57] [5600/6250] eta: 0:01:17 lr: 0.000051 grad: 0.0930 (0.0935) loss: 0.8675 (0.8605) time: 0.1331 data: 0.0579 max mem: 8299 +Train: [57] [5700/6250] eta: 0:01:05 lr: 0.000051 grad: 0.0891 (0.0934) loss: 0.8610 (0.8605) time: 0.0997 data: 0.0261 max mem: 8299 +Train: [57] [5800/6250] eta: 0:00:53 lr: 0.000051 grad: 0.0881 (0.0935) loss: 0.8561 (0.8605) time: 0.1030 data: 0.0274 max mem: 8299 +Train: [57] [5900/6250] eta: 0:00:41 lr: 0.000051 grad: 0.0903 (0.0935) loss: 0.8670 (0.8605) time: 0.1177 data: 0.0483 max mem: 8299 +Train: [57] [6000/6250] eta: 0:00:29 lr: 0.000051 grad: 0.0933 (0.0934) loss: 0.8581 (0.8605) time: 0.1048 data: 0.0265 max mem: 8299 +Train: [57] [6100/6250] eta: 0:00:17 lr: 0.000051 grad: 0.0889 (0.0934) loss: 0.8582 (0.8605) time: 0.1056 data: 0.0289 max mem: 8299 +Train: [57] [6200/6250] eta: 0:00:05 lr: 0.000051 grad: 0.0880 (0.0934) loss: 0.8585 (0.8605) time: 0.1120 data: 0.0378 max mem: 8299 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.0911 (0.0934) loss: 0.8573 (0.8605) time: 0.0877 data: 0.0165 max mem: 8299 +Train: [57] Total time: 0:12:21 (0.1186 s / it) +Averaged stats: lr: 0.000051 grad: 0.0911 (0.0934) loss: 0.8573 (0.8605) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:03:09 loss: 0.8984 (0.8984) time: 3.0623 data: 2.9926 max mem: 8299 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8849 (0.8852) time: 0.1101 data: 0.0849 max mem: 8299 +Eval (hcp-train-subset): [57] Total time: 0:00:10 (0.1767 s / it) +Averaged stats (hcp-train-subset): loss: 0.8849 (0.8852) +Eval (hcp-val): [57] [ 0/62] eta: 0:04:29 loss: 0.8777 (0.8777) time: 4.3461 data: 4.3178 max mem: 8299 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8800 (0.8826) time: 0.1052 data: 0.0799 max mem: 8299 +Eval (hcp-val): [57] Total time: 0:00:10 (0.1727 s / it) +Averaged stats (hcp-val): loss: 0.8800 (0.8826) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 9:17:28 lr: 0.000051 grad: 0.0962 (0.0962) loss: 0.9196 (0.9196) time: 5.3518 data: 5.2596 max mem: 8299 +Train: [58] [ 100/6250] eta: 0:16:55 lr: 0.000051 grad: 0.0920 (0.1084) loss: 0.8629 (0.8730) time: 0.1134 data: 0.0330 max mem: 8299 +Train: [58] [ 200/6250] eta: 0:14:40 lr: 0.000051 grad: 0.0867 (0.1027) loss: 0.8519 (0.8664) time: 0.1210 data: 0.0435 max mem: 8299 +Train: [58] [ 300/6250] eta: 0:13:35 lr: 0.000051 grad: 0.0860 (0.0982) loss: 0.8654 (0.8647) time: 0.1206 data: 0.0422 max mem: 8299 +Train: [58] [ 400/6250] eta: 0:12:46 lr: 0.000051 grad: 0.0795 (0.0955) loss: 0.8687 (0.8655) time: 0.1089 data: 0.0359 max mem: 8299 +Train: [58] [ 500/6250] eta: 0:12:16 lr: 0.000051 grad: 0.0815 (0.0942) loss: 0.8661 (0.8654) time: 0.1191 data: 0.0364 max mem: 8299 +Train: [58] [ 600/6250] eta: 0:11:42 lr: 0.000051 grad: 0.0866 (0.0932) loss: 0.8599 (0.8657) time: 0.1122 data: 0.0291 max mem: 8299 +Train: [58] [ 700/6250] eta: 0:11:16 lr: 0.000051 grad: 0.0765 (0.0916) loss: 0.8650 (0.8661) time: 0.1006 data: 0.0172 max mem: 8299 +Train: [58] [ 800/6250] eta: 0:10:53 lr: 0.000051 grad: 0.0751 (0.0910) loss: 0.8704 (0.8664) time: 0.1091 data: 0.0356 max mem: 8299 +Train: [58] [ 900/6250] eta: 0:10:40 lr: 0.000051 grad: 0.0882 (0.0905) loss: 0.8657 (0.8665) time: 0.1357 data: 0.0650 max mem: 8299 +Train: [58] [1000/6250] eta: 0:10:33 lr: 0.000051 grad: 0.0828 (0.0897) loss: 0.8682 (0.8666) time: 0.1247 data: 0.0520 max mem: 8299 +Train: [58] [1100/6250] eta: 0:10:22 lr: 0.000051 grad: 0.0768 (0.0893) loss: 0.8717 (0.8667) time: 0.0917 data: 0.0152 max mem: 8299 +Train: [58] [1200/6250] eta: 0:10:14 lr: 0.000051 grad: 0.0820 (0.0891) loss: 0.8680 (0.8665) time: 0.1503 data: 0.0815 max mem: 8299 +Train: [58] [1300/6250] eta: 0:10:01 lr: 0.000051 grad: 0.0836 (0.0888) loss: 0.8642 (0.8664) time: 0.1145 data: 0.0365 max mem: 8299 +Train: [58] [1400/6250] eta: 0:09:51 lr: 0.000051 grad: 0.0883 (0.0889) loss: 0.8644 (0.8663) time: 0.1479 data: 0.0765 max mem: 8299 +Train: [58] [1500/6250] eta: 0:09:38 lr: 0.000051 grad: 0.0799 (0.0888) loss: 0.8745 (0.8663) time: 0.1188 data: 0.0468 max mem: 8299 +Train: [58] [1600/6250] eta: 0:09:26 lr: 0.000051 grad: 0.0869 (0.0890) loss: 0.8659 (0.8661) time: 0.1388 data: 0.0697 max mem: 8299 +Train: [58] [1700/6250] eta: 0:09:13 lr: 0.000051 grad: 0.0886 (0.0889) loss: 0.8655 (0.8661) time: 0.1068 data: 0.0351 max mem: 8299 +Train: [58] [1800/6250] eta: 0:09:02 lr: 0.000051 grad: 0.0832 (0.0887) loss: 0.8637 (0.8661) time: 0.1224 data: 0.0582 max mem: 8299 +Train: [58] [1900/6250] eta: 0:08:49 lr: 0.000051 grad: 0.0861 (0.0886) loss: 0.8658 (0.8660) time: 0.1209 data: 0.0510 max mem: 8299 +Train: [58] [2000/6250] eta: 0:08:37 lr: 0.000051 grad: 0.0791 (0.0886) loss: 0.8664 (0.8659) time: 0.1239 data: 0.0548 max mem: 8299 +Train: [58] [2100/6250] eta: 0:08:24 lr: 0.000051 grad: 0.0829 (0.0885) loss: 0.8655 (0.8660) time: 0.1305 data: 0.0663 max mem: 8299 +Train: [58] [2200/6250] eta: 0:08:11 lr: 0.000050 grad: 0.0891 (0.0885) loss: 0.8571 (0.8660) time: 0.1196 data: 0.0454 max mem: 8299 +Train: [58] [2300/6250] eta: 0:07:58 lr: 0.000050 grad: 0.0855 (0.0885) loss: 0.8659 (0.8659) time: 0.1078 data: 0.0266 max mem: 8299 +Train: [58] [2400/6250] eta: 0:07:46 lr: 0.000050 grad: 0.0887 (0.0887) loss: 0.8675 (0.8659) time: 0.0981 data: 0.0275 max mem: 8299 +Train: [58] [2500/6250] eta: 0:07:33 lr: 0.000050 grad: 0.0817 (0.0888) loss: 0.8675 (0.8659) time: 0.1318 data: 0.0627 max mem: 8299 +Train: [58] [2600/6250] eta: 0:07:20 lr: 0.000050 grad: 0.0789 (0.0889) loss: 0.8641 (0.8658) time: 0.1390 data: 0.0655 max mem: 8299 +Train: [58] [2700/6250] eta: 0:07:08 lr: 0.000050 grad: 0.0948 (0.0891) loss: 0.8652 (0.8657) time: 0.1264 data: 0.0591 max mem: 8299 +Train: [58] [2800/6250] eta: 0:06:56 lr: 0.000050 grad: 0.0889 (0.0892) loss: 0.8643 (0.8656) time: 0.1103 data: 0.0343 max mem: 8299 +Train: [58] [2900/6250] eta: 0:06:43 lr: 0.000050 grad: 0.0904 (0.0893) loss: 0.8684 (0.8656) time: 0.1105 data: 0.0343 max mem: 8299 +Train: [58] [3000/6250] eta: 0:06:31 lr: 0.000050 grad: 0.0897 (0.0894) loss: 0.8617 (0.8655) time: 0.1213 data: 0.0483 max mem: 8299 +Train: [58] [3100/6250] eta: 0:06:19 lr: 0.000050 grad: 0.0820 (0.0895) loss: 0.8665 (0.8654) time: 0.1372 data: 0.0682 max mem: 8299 +Train: [58] [3200/6250] eta: 0:06:07 lr: 0.000050 grad: 0.0908 (0.0896) loss: 0.8605 (0.8654) time: 0.1048 data: 0.0396 max mem: 8299 +Train: [58] [3300/6250] eta: 0:05:55 lr: 0.000050 grad: 0.0902 (0.0897) loss: 0.8669 (0.8653) time: 0.1048 data: 0.0407 max mem: 8299 +Train: [58] [3400/6250] eta: 0:05:43 lr: 0.000050 grad: 0.0964 (0.0897) loss: 0.8595 (0.8653) time: 0.1307 data: 0.0595 max mem: 8299 +Train: [58] [3500/6250] eta: 0:05:31 lr: 0.000050 grad: 0.0904 (0.0899) loss: 0.8664 (0.8653) time: 0.1238 data: 0.0514 max mem: 8299 +Train: [58] [3600/6250] eta: 0:05:19 lr: 0.000050 grad: 0.0903 (0.0900) loss: 0.8689 (0.8652) time: 0.1226 data: 0.0519 max mem: 8299 +Train: [58] [3700/6250] eta: 0:05:07 lr: 0.000050 grad: 0.0947 (0.0901) loss: 0.8617 (0.8651) time: 0.1388 data: 0.0719 max mem: 8299 +Train: [58] [3800/6250] eta: 0:04:56 lr: 0.000050 grad: 0.0941 (0.0901) loss: 0.8635 (0.8651) time: 0.1130 data: 0.0428 max mem: 8299 +Train: [58] [3900/6250] eta: 0:04:44 lr: 0.000050 grad: 0.0923 (0.0902) loss: 0.8569 (0.8650) time: 0.1463 data: 0.0654 max mem: 8299 +Train: [58] [4000/6250] eta: 0:04:32 lr: 0.000050 grad: 0.0993 (0.0905) loss: 0.8612 (0.8649) time: 0.1443 data: 0.0778 max mem: 8299 +Train: [58] [4100/6250] eta: 0:04:19 lr: 0.000050 grad: 0.0976 (0.0907) loss: 0.8585 (0.8647) time: 0.1174 data: 0.0410 max mem: 8299 +Train: [58] [4200/6250] eta: 0:04:08 lr: 0.000050 grad: 0.0887 (0.0909) loss: 0.8590 (0.8646) time: 0.1292 data: 0.0586 max mem: 8299 +Train: [58] [4300/6250] eta: 0:03:55 lr: 0.000050 grad: 0.0946 (0.0912) loss: 0.8536 (0.8645) time: 0.1204 data: 0.0520 max mem: 8299 +Train: [58] [4400/6250] eta: 0:03:43 lr: 0.000050 grad: 0.0957 (0.0913) loss: 0.8540 (0.8644) time: 0.1065 data: 0.0317 max mem: 8299 +Train: [58] [4500/6250] eta: 0:03:31 lr: 0.000050 grad: 0.0916 (0.0917) loss: 0.8657 (0.8643) time: 0.1395 data: 0.0735 max mem: 8299 +Train: [58] [4600/6250] eta: 0:03:19 lr: 0.000050 grad: 0.0960 (0.0918) loss: 0.8530 (0.8642) time: 0.1206 data: 0.0514 max mem: 8299 +Train: [58] [4700/6250] eta: 0:03:07 lr: 0.000050 grad: 0.0924 (0.0920) loss: 0.8642 (0.8642) time: 0.1261 data: 0.0581 max mem: 8299 +Train: [58] [4800/6250] eta: 0:02:55 lr: 0.000050 grad: 0.0872 (0.0922) loss: 0.8647 (0.8641) time: 0.1240 data: 0.0589 max mem: 8299 +Train: [58] [4900/6250] eta: 0:02:43 lr: 0.000050 grad: 0.0977 (0.0923) loss: 0.8623 (0.8640) time: 0.1340 data: 0.0716 max mem: 8299 +Train: [58] [5000/6250] eta: 0:02:31 lr: 0.000050 grad: 0.1001 (0.0923) loss: 0.8630 (0.8639) time: 0.1260 data: 0.0538 max mem: 8299 +Train: [58] [5100/6250] eta: 0:02:19 lr: 0.000050 grad: 0.0891 (0.0924) loss: 0.8588 (0.8638) time: 0.1360 data: 0.0729 max mem: 8299 +Train: [58] [5200/6250] eta: 0:02:07 lr: 0.000050 grad: 0.1036 (0.0926) loss: 0.8564 (0.8638) time: 0.1375 data: 0.0692 max mem: 8299 +Train: [58] [5300/6250] eta: 0:01:55 lr: 0.000049 grad: 0.1068 (0.0928) loss: 0.8517 (0.8636) time: 0.1301 data: 0.0548 max mem: 8299 +Train: [58] [5400/6250] eta: 0:01:43 lr: 0.000049 grad: 0.0942 (0.0929) loss: 0.8592 (0.8636) time: 0.1402 data: 0.0665 max mem: 8299 +Train: [58] [5500/6250] eta: 0:01:31 lr: 0.000049 grad: 0.0833 (0.0929) loss: 0.8664 (0.8635) time: 0.1339 data: 0.0682 max mem: 8299 +Train: [58] [5600/6250] eta: 0:01:19 lr: 0.000049 grad: 0.0878 (0.0930) loss: 0.8595 (0.8635) time: 0.0965 data: 0.0294 max mem: 8299 +Train: [58] [5700/6250] eta: 0:01:07 lr: 0.000049 grad: 0.0950 (0.0930) loss: 0.8549 (0.8635) time: 0.1053 data: 0.0326 max mem: 8299 +Train: [58] [5800/6250] eta: 0:00:54 lr: 0.000049 grad: 0.0853 (0.0931) loss: 0.8649 (0.8634) time: 0.1022 data: 0.0269 max mem: 8299 +Train: [58] [5900/6250] eta: 0:00:42 lr: 0.000049 grad: 0.0887 (0.0932) loss: 0.8682 (0.8633) time: 0.1004 data: 0.0210 max mem: 8299 +Train: [58] [6000/6250] eta: 0:00:30 lr: 0.000049 grad: 0.0936 (0.0932) loss: 0.8561 (0.8633) time: 0.1023 data: 0.0284 max mem: 8299 +Train: [58] [6100/6250] eta: 0:00:18 lr: 0.000049 grad: 0.0906 (0.0932) loss: 0.8613 (0.8633) time: 0.1026 data: 0.0292 max mem: 8299 +Train: [58] [6200/6250] eta: 0:00:06 lr: 0.000049 grad: 0.0894 (0.0931) loss: 0.8653 (0.8633) time: 0.0980 data: 0.0221 max mem: 8299 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.0886 (0.0931) loss: 0.8616 (0.8633) time: 0.0965 data: 0.0177 max mem: 8299 +Train: [58] Total time: 0:12:37 (0.1213 s / it) +Averaged stats: lr: 0.000049 grad: 0.0886 (0.0931) loss: 0.8616 (0.8633) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:03:12 loss: 0.8953 (0.8953) time: 3.0988 data: 3.0164 max mem: 8299 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8851 (0.8834) time: 0.1243 data: 0.0999 max mem: 8299 +Eval (hcp-train-subset): [58] Total time: 0:00:11 (0.1927 s / it) +Averaged stats (hcp-train-subset): loss: 0.8851 (0.8834) +Eval (hcp-val): [58] [ 0/62] eta: 0:03:53 loss: 0.8805 (0.8805) time: 3.7688 data: 3.6955 max mem: 8299 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8809 (0.8832) time: 0.0931 data: 0.0689 max mem: 8299 +Eval (hcp-val): [58] Total time: 0:00:11 (0.1857 s / it) +Averaged stats (hcp-val): loss: 0.8809 (0.8832) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 8:53:53 lr: 0.000049 grad: 0.0797 (0.0797) loss: 0.8706 (0.8706) time: 5.1254 data: 5.0153 max mem: 8299 +Train: [59] [ 100/6250] eta: 0:16:23 lr: 0.000049 grad: 0.0852 (0.1070) loss: 0.8668 (0.8708) time: 0.1242 data: 0.0424 max mem: 8299 +Train: [59] [ 200/6250] eta: 0:14:04 lr: 0.000049 grad: 0.0913 (0.1018) loss: 0.8697 (0.8694) time: 0.1249 data: 0.0486 max mem: 8299 +Train: [59] [ 300/6250] eta: 0:13:25 lr: 0.000049 grad: 0.0926 (0.0988) loss: 0.8635 (0.8682) time: 0.1180 data: 0.0319 max mem: 8299 +Train: [59] [ 400/6250] eta: 0:12:41 lr: 0.000049 grad: 0.0878 (0.0975) loss: 0.8617 (0.8666) time: 0.1127 data: 0.0396 max mem: 8299 +Train: [59] [ 500/6250] eta: 0:12:09 lr: 0.000049 grad: 0.0866 (0.0970) loss: 0.8610 (0.8653) time: 0.1164 data: 0.0327 max mem: 8299 +Train: [59] [ 600/6250] eta: 0:11:42 lr: 0.000049 grad: 0.0902 (0.0963) loss: 0.8583 (0.8646) time: 0.1213 data: 0.0464 max mem: 8299 +Train: [59] [ 700/6250] eta: 0:11:16 lr: 0.000049 grad: 0.0905 (0.0958) loss: 0.8630 (0.8641) time: 0.1078 data: 0.0250 max mem: 8299 +Train: [59] [ 800/6250] eta: 0:10:58 lr: 0.000049 grad: 0.0819 (0.0952) loss: 0.8660 (0.8638) time: 0.1150 data: 0.0357 max mem: 8299 +Train: [59] [ 900/6250] eta: 0:10:38 lr: 0.000049 grad: 0.0898 (0.0952) loss: 0.8631 (0.8637) time: 0.1116 data: 0.0336 max mem: 8299 +Train: [59] [1000/6250] eta: 0:10:27 lr: 0.000049 grad: 0.0867 (0.0949) loss: 0.8658 (0.8634) time: 0.1171 data: 0.0462 max mem: 8299 +Train: [59] [1100/6250] eta: 0:10:15 lr: 0.000049 grad: 0.0845 (0.0948) loss: 0.8667 (0.8632) time: 0.1193 data: 0.0480 max mem: 8299 +Train: [59] [1200/6250] eta: 0:10:02 lr: 0.000049 grad: 0.0840 (0.0946) loss: 0.8653 (0.8632) time: 0.1222 data: 0.0513 max mem: 8299 +Train: [59] [1300/6250] eta: 0:09:50 lr: 0.000049 grad: 0.0890 (0.0946) loss: 0.8620 (0.8629) time: 0.1286 data: 0.0601 max mem: 8299 +Train: [59] [1400/6250] eta: 0:09:38 lr: 0.000049 grad: 0.0947 (0.0945) loss: 0.8576 (0.8627) time: 0.1320 data: 0.0646 max mem: 8299 +Train: [59] [1500/6250] eta: 0:09:25 lr: 0.000049 grad: 0.0922 (0.0945) loss: 0.8585 (0.8625) time: 0.1259 data: 0.0606 max mem: 8299 +Train: [59] [1600/6250] eta: 0:09:13 lr: 0.000049 grad: 0.1071 (0.0946) loss: 0.8556 (0.8622) time: 0.1248 data: 0.0597 max mem: 8299 +Train: [59] [1700/6250] eta: 0:09:01 lr: 0.000049 grad: 0.0840 (0.0947) loss: 0.8595 (0.8622) time: 0.1220 data: 0.0546 max mem: 8299 +Train: [59] [1800/6250] eta: 0:08:47 lr: 0.000049 grad: 0.0908 (0.0946) loss: 0.8589 (0.8621) time: 0.1242 data: 0.0577 max mem: 8299 +Train: [59] [1900/6250] eta: 0:08:34 lr: 0.000049 grad: 0.0986 (0.0948) loss: 0.8539 (0.8617) time: 0.1160 data: 0.0471 max mem: 8299 +Train: [59] [2000/6250] eta: 0:08:23 lr: 0.000049 grad: 0.0920 (0.0950) loss: 0.8543 (0.8615) time: 0.1432 data: 0.0701 max mem: 8299 +Train: [59] [2100/6250] eta: 0:08:11 lr: 0.000048 grad: 0.0962 (0.0952) loss: 0.8496 (0.8612) time: 0.1450 data: 0.0722 max mem: 8299 +Train: [59] [2200/6250] eta: 0:07:57 lr: 0.000048 grad: 0.0899 (0.0954) loss: 0.8536 (0.8611) time: 0.1196 data: 0.0503 max mem: 8299 +Train: [59] [2300/6250] eta: 0:07:45 lr: 0.000048 grad: 0.0915 (0.0956) loss: 0.8579 (0.8609) time: 0.1362 data: 0.0656 max mem: 8299 +Train: [59] [2400/6250] eta: 0:07:32 lr: 0.000048 grad: 0.0896 (0.0958) loss: 0.8604 (0.8608) time: 0.1211 data: 0.0519 max mem: 8299 +Train: [59] [2500/6250] eta: 0:07:21 lr: 0.000048 grad: 0.0923 (0.0962) loss: 0.8618 (0.8608) time: 0.0914 data: 0.0236 max mem: 8299 +Train: [59] [2600/6250] eta: 0:07:08 lr: 0.000048 grad: 0.0993 (0.0964) loss: 0.8585 (0.8607) time: 0.1031 data: 0.0337 max mem: 8299 +Train: [59] [2700/6250] eta: 0:06:57 lr: 0.000048 grad: 0.0964 (0.0965) loss: 0.8616 (0.8607) time: 0.1180 data: 0.0467 max mem: 8299 +Train: [59] [2800/6250] eta: 0:06:45 lr: 0.000048 grad: 0.0948 (0.0966) loss: 0.8589 (0.8606) time: 0.1115 data: 0.0435 max mem: 8299 +Train: [59] [2900/6250] eta: 0:06:33 lr: 0.000048 grad: 0.0968 (0.0966) loss: 0.8646 (0.8607) time: 0.1216 data: 0.0473 max mem: 8299 +Train: [59] [3000/6250] eta: 0:06:21 lr: 0.000048 grad: 0.0924 (0.0966) loss: 0.8597 (0.8607) time: 0.1446 data: 0.0739 max mem: 8299 +Train: [59] [3100/6250] eta: 0:06:09 lr: 0.000048 grad: 0.0938 (0.0966) loss: 0.8642 (0.8608) time: 0.1170 data: 0.0481 max mem: 8299 +Train: [59] [3200/6250] eta: 0:05:58 lr: 0.000048 grad: 0.0932 (0.0966) loss: 0.8602 (0.8609) time: 0.1353 data: 0.0678 max mem: 8299 +Train: [59] [3300/6250] eta: 0:05:46 lr: 0.000048 grad: 0.0963 (0.0966) loss: 0.8677 (0.8610) time: 0.1207 data: 0.0558 max mem: 8299 +Train: [59] [3400/6250] eta: 0:05:34 lr: 0.000048 grad: 0.0970 (0.0967) loss: 0.8615 (0.8610) time: 0.0943 data: 0.0260 max mem: 8299 +Train: [59] [3500/6250] eta: 0:05:22 lr: 0.000048 grad: 0.0906 (0.0966) loss: 0.8617 (0.8611) time: 0.1147 data: 0.0463 max mem: 8299 +Train: [59] [3600/6250] eta: 0:05:11 lr: 0.000048 grad: 0.0866 (0.0965) loss: 0.8708 (0.8612) time: 0.1165 data: 0.0507 max mem: 8299 +Train: [59] [3700/6250] eta: 0:04:59 lr: 0.000048 grad: 0.0928 (0.0964) loss: 0.8686 (0.8613) time: 0.1406 data: 0.0692 max mem: 8299 +Train: [59] [3800/6250] eta: 0:04:47 lr: 0.000048 grad: 0.0883 (0.0963) loss: 0.8712 (0.8614) time: 0.1202 data: 0.0486 max mem: 8299 +Train: [59] [3900/6250] eta: 0:04:35 lr: 0.000048 grad: 0.0921 (0.0963) loss: 0.8576 (0.8615) time: 0.1185 data: 0.0478 max mem: 8299 +Train: [59] [4000/6250] eta: 0:04:24 lr: 0.000048 grad: 0.0908 (0.0963) loss: 0.8645 (0.8615) time: 0.1213 data: 0.0442 max mem: 8299 +Train: [59] [4100/6250] eta: 0:04:12 lr: 0.000048 grad: 0.1003 (0.0963) loss: 0.8617 (0.8615) time: 0.1312 data: 0.0559 max mem: 8299 +Train: [59] [4200/6250] eta: 0:04:01 lr: 0.000048 grad: 0.0974 (0.0962) loss: 0.8619 (0.8616) time: 0.1189 data: 0.0473 max mem: 8299 +Train: [59] [4300/6250] eta: 0:03:49 lr: 0.000048 grad: 0.1013 (0.0963) loss: 0.8610 (0.8616) time: 0.1244 data: 0.0561 max mem: 8299 +Train: [59] [4400/6250] eta: 0:03:37 lr: 0.000048 grad: 0.0931 (0.0963) loss: 0.8657 (0.8616) time: 0.1135 data: 0.0401 max mem: 8299 +Train: [59] [4500/6250] eta: 0:03:26 lr: 0.000048 grad: 0.0977 (0.0963) loss: 0.8581 (0.8616) time: 0.1374 data: 0.0700 max mem: 8299 +Train: [59] [4600/6250] eta: 0:03:14 lr: 0.000048 grad: 0.0928 (0.0964) loss: 0.8644 (0.8616) time: 0.1022 data: 0.0270 max mem: 8299 +Train: [59] [4700/6250] eta: 0:03:02 lr: 0.000048 grad: 0.0964 (0.0964) loss: 0.8641 (0.8617) time: 0.1132 data: 0.0394 max mem: 8299 +Train: [59] [4800/6250] eta: 0:02:51 lr: 0.000048 grad: 0.0872 (0.0964) loss: 0.8660 (0.8617) time: 0.1367 data: 0.0693 max mem: 8299 +Train: [59] [4900/6250] eta: 0:02:39 lr: 0.000048 grad: 0.0955 (0.0963) loss: 0.8619 (0.8617) time: 0.1208 data: 0.0464 max mem: 8299 +Train: [59] [5000/6250] eta: 0:02:27 lr: 0.000048 grad: 0.0865 (0.0963) loss: 0.8649 (0.8618) time: 0.1626 data: 0.0971 max mem: 8299 +Train: [59] [5100/6250] eta: 0:02:16 lr: 0.000048 grad: 0.0921 (0.0962) loss: 0.8608 (0.8618) time: 0.1030 data: 0.0233 max mem: 8299 +Train: [59] [5200/6250] eta: 0:02:04 lr: 0.000047 grad: 0.1052 (0.0962) loss: 0.8616 (0.8618) time: 0.1323 data: 0.0654 max mem: 8299 +Train: [59] [5300/6250] eta: 0:01:52 lr: 0.000047 grad: 0.0886 (0.0962) loss: 0.8627 (0.8619) time: 0.1209 data: 0.0509 max mem: 8299 +Train: [59] [5400/6250] eta: 0:01:41 lr: 0.000047 grad: 0.0905 (0.0962) loss: 0.8621 (0.8619) time: 0.1332 data: 0.0676 max mem: 8299 +Train: [59] [5500/6250] eta: 0:01:29 lr: 0.000047 grad: 0.0973 (0.0962) loss: 0.8613 (0.8619) time: 0.1144 data: 0.0420 max mem: 8299 +Train: [59] [5600/6250] eta: 0:01:17 lr: 0.000047 grad: 0.0934 (0.0962) loss: 0.8558 (0.8618) time: 0.1220 data: 0.0517 max mem: 8299 +Train: [59] [5700/6250] eta: 0:01:05 lr: 0.000047 grad: 0.0911 (0.0963) loss: 0.8643 (0.8618) time: 0.0978 data: 0.0264 max mem: 8299 +Train: [59] [5800/6250] eta: 0:00:53 lr: 0.000047 grad: 0.0895 (0.0964) loss: 0.8593 (0.8618) time: 0.1015 data: 0.0278 max mem: 8299 +Train: [59] [5900/6250] eta: 0:00:41 lr: 0.000047 grad: 0.0884 (0.0964) loss: 0.8653 (0.8617) time: 0.0975 data: 0.0219 max mem: 8299 +Train: [59] [6000/6250] eta: 0:00:29 lr: 0.000047 grad: 0.0932 (0.0964) loss: 0.8589 (0.8617) time: 0.1098 data: 0.0335 max mem: 8299 +Train: [59] [6100/6250] eta: 0:00:17 lr: 0.000047 grad: 0.0966 (0.0964) loss: 0.8639 (0.8617) time: 0.1064 data: 0.0254 max mem: 8299 +Train: [59] [6200/6250] eta: 0:00:05 lr: 0.000047 grad: 0.0887 (0.0963) loss: 0.8628 (0.8617) time: 0.1072 data: 0.0303 max mem: 8299 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.0957 (0.0963) loss: 0.8585 (0.8616) time: 0.1058 data: 0.0266 max mem: 8299 +Train: [59] Total time: 0:12:21 (0.1186 s / it) +Averaged stats: lr: 0.000047 grad: 0.0957 (0.0963) loss: 0.8585 (0.8616) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:03:27 loss: 0.8940 (0.8940) time: 3.3413 data: 3.2785 max mem: 8299 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8815 (0.8833) time: 0.0945 data: 0.0705 max mem: 8299 +Eval (hcp-train-subset): [59] Total time: 0:00:10 (0.1754 s / it) +Averaged stats (hcp-train-subset): loss: 0.8815 (0.8833) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [59] [ 0/62] eta: 0:03:08 loss: 0.8834 (0.8834) time: 3.0426 data: 2.9579 max mem: 8299 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8828 (0.8834) time: 0.0900 data: 0.0648 max mem: 8299 +Eval (hcp-val): [59] Total time: 0:00:11 (0.1779 s / it) +Averaged stats (hcp-val): loss: 0.8828 (0.8834) +Making plots (hcp-val): example=59 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-00059.pth +Train: [60] [ 0/6250] eta: 9:46:53 lr: 0.000047 grad: nan (nan) loss: 0.9020 (0.9020) time: 5.6342 data: 5.5532 max mem: 8299 +Train: [60] [ 100/6250] eta: 0:16:26 lr: 0.000047 grad: 0.0911 (0.1244) loss: 0.8669 (0.8700) time: 0.1046 data: 0.0216 max mem: 8299 +Train: [60] [ 200/6250] eta: 0:14:20 lr: 0.000047 grad: 0.0907 (0.1140) loss: 0.8671 (0.8673) time: 0.1425 data: 0.0597 max mem: 8299 +Train: [60] [ 300/6250] eta: 0:13:16 lr: 0.000047 grad: 0.0890 (0.1055) loss: 0.8647 (0.8663) time: 0.1266 data: 0.0531 max mem: 8299 +Train: [60] [ 400/6250] eta: 0:12:36 lr: 0.000047 grad: 0.0875 (0.1013) loss: 0.8749 (0.8669) time: 0.1141 data: 0.0424 max mem: 8299 +Train: [60] [ 500/6250] eta: 0:12:09 lr: 0.000047 grad: 0.0810 (0.0992) loss: 0.8664 (0.8670) time: 0.1079 data: 0.0334 max mem: 8299 +Train: [60] [ 600/6250] eta: 0:11:47 lr: 0.000047 grad: 0.0798 (0.0974) loss: 0.8693 (0.8673) time: 0.1228 data: 0.0540 max mem: 8299 +Train: [60] [ 700/6250] eta: 0:11:27 lr: 0.000047 grad: 0.0874 (0.0961) loss: 0.8666 (0.8673) time: 0.1172 data: 0.0429 max mem: 8299 +Train: [60] [ 800/6250] eta: 0:11:08 lr: 0.000047 grad: 0.0817 (0.0948) loss: 0.8663 (0.8673) time: 0.0796 data: 0.0004 max mem: 8299 +Train: [60] [ 900/6250] eta: 0:10:50 lr: 0.000047 grad: 0.0881 (0.0940) loss: 0.8712 (0.8676) time: 0.1183 data: 0.0431 max mem: 8299 +Train: [60] [1000/6250] eta: 0:10:31 lr: 0.000047 grad: 0.0842 (0.0933) loss: 0.8686 (0.8676) time: 0.1073 data: 0.0312 max mem: 8299 +Train: [60] [1100/6250] eta: 0:10:10 lr: 0.000047 grad: 0.0858 (0.0931) loss: 0.8677 (0.8675) time: 0.1017 data: 0.0287 max mem: 8299 +Train: [60] [1200/6250] eta: 0:09:54 lr: 0.000047 grad: 0.0927 (0.0927) loss: 0.8678 (0.8671) time: 0.0979 data: 0.0244 max mem: 8299 +Train: [60] [1300/6250] eta: 0:09:38 lr: 0.000047 grad: 0.0844 (0.0924) loss: 0.8620 (0.8670) time: 0.1052 data: 0.0376 max mem: 8299 +Train: [60] [1400/6250] eta: 0:09:24 lr: 0.000047 grad: 0.0909 (0.0923) loss: 0.8623 (0.8668) time: 0.1160 data: 0.0476 max mem: 8299 +Train: [60] [1500/6250] eta: 0:09:08 lr: 0.000047 grad: 0.0832 (0.0921) loss: 0.8729 (0.8667) time: 0.0931 data: 0.0190 max mem: 8299 +Train: [60] [1600/6250] eta: 0:08:54 lr: 0.000047 grad: 0.0946 (0.0921) loss: 0.8624 (0.8667) time: 0.1125 data: 0.0385 max mem: 8299 +Train: [60] [1700/6250] eta: 0:08:41 lr: 0.000047 grad: 0.0945 (0.0922) loss: 0.8607 (0.8664) time: 0.1145 data: 0.0451 max mem: 8299 +Train: [60] [1800/6250] eta: 0:08:27 lr: 0.000047 grad: 0.0916 (0.0923) loss: 0.8661 (0.8662) time: 0.1068 data: 0.0319 max mem: 8299 +Train: [60] [1900/6250] eta: 0:08:14 lr: 0.000047 grad: 0.0912 (0.0925) loss: 0.8577 (0.8659) time: 0.1073 data: 0.0316 max mem: 8299 +Train: [60] [2000/6250] eta: 0:08:02 lr: 0.000047 grad: 0.0854 (0.0926) loss: 0.8613 (0.8656) time: 0.1066 data: 0.0340 max mem: 8299 +Train: [60] [2100/6250] eta: 0:07:49 lr: 0.000046 grad: 0.0962 (0.0928) loss: 0.8602 (0.8654) time: 0.0975 data: 0.0213 max mem: 8299 +Train: [60] [2200/6250] eta: 0:07:37 lr: 0.000046 grad: 0.0959 (0.0930) loss: 0.8605 (0.8653) time: 0.0982 data: 0.0262 max mem: 8299 +Train: [60] [2300/6250] eta: 0:07:24 lr: 0.000046 grad: 0.0945 (0.0932) loss: 0.8601 (0.8650) time: 0.1123 data: 0.0433 max mem: 8299 +Train: [60] [2400/6250] eta: 0:07:12 lr: 0.000046 grad: 0.0957 (0.0933) loss: 0.8629 (0.8648) time: 0.1159 data: 0.0425 max mem: 8299 +Train: [60] [2500/6250] eta: 0:07:00 lr: 0.000046 grad: 0.0885 (0.0934) loss: 0.8593 (0.8646) time: 0.1134 data: 0.0406 max mem: 8299 +Train: [60] [2600/6250] eta: 0:06:48 lr: 0.000046 grad: 0.0957 (0.0935) loss: 0.8503 (0.8644) time: 0.1131 data: 0.0383 max mem: 8299 +Train: [60] [2700/6250] eta: 0:06:36 lr: 0.000046 grad: 0.0930 (0.0936) loss: 0.8629 (0.8643) time: 0.1097 data: 0.0357 max mem: 8299 +Train: [60] [2800/6250] eta: 0:06:24 lr: 0.000046 grad: 0.0879 (0.0937) loss: 0.8597 (0.8642) time: 0.0844 data: 0.0101 max mem: 8299 +Train: [60] [2900/6250] eta: 0:06:12 lr: 0.000046 grad: 0.0888 (0.0937) loss: 0.8655 (0.8641) time: 0.1100 data: 0.0381 max mem: 8299 +Train: [60] [3000/6250] eta: 0:06:01 lr: 0.000046 grad: 0.1044 (0.0939) loss: 0.8597 (0.8640) time: 0.1113 data: 0.0448 max mem: 8299 +Train: [60] [3100/6250] eta: 0:05:50 lr: 0.000046 grad: 0.0937 (0.0940) loss: 0.8578 (0.8639) time: 0.0963 data: 0.0238 max mem: 8299 +Train: [60] [3200/6250] eta: 0:05:38 lr: 0.000046 grad: 0.1017 (0.0942) loss: 0.8558 (0.8638) time: 0.1143 data: 0.0425 max mem: 8299 +Train: [60] [3300/6250] eta: 0:05:27 lr: 0.000046 grad: 0.0933 (0.0942) loss: 0.8613 (0.8637) time: 0.1249 data: 0.0512 max mem: 8299 +Train: [60] [3400/6250] eta: 0:05:16 lr: 0.000046 grad: 0.0907 (0.0944) loss: 0.8666 (0.8636) time: 0.1132 data: 0.0406 max mem: 8299 +Train: [60] [3500/6250] eta: 0:05:04 lr: 0.000046 grad: 0.0931 (0.0943) loss: 0.8656 (0.8636) time: 0.1034 data: 0.0349 max mem: 8299 +Train: [60] [3600/6250] eta: 0:04:53 lr: 0.000046 grad: 0.0910 (0.0944) loss: 0.8623 (0.8635) time: 0.1116 data: 0.0424 max mem: 8299 +Train: [60] [3700/6250] eta: 0:04:42 lr: 0.000046 grad: 0.0951 (0.0945) loss: 0.8623 (0.8633) time: 0.1115 data: 0.0411 max mem: 8299 +Train: [60] [3800/6250] eta: 0:04:31 lr: 0.000046 grad: 0.0941 (0.0945) loss: 0.8573 (0.8632) time: 0.1134 data: 0.0474 max mem: 8299 +Train: [60] [3900/6250] eta: 0:04:19 lr: 0.000046 grad: 0.0957 (0.0946) loss: 0.8638 (0.8631) time: 0.1227 data: 0.0481 max mem: 8299 +Train: [60] [4000/6250] eta: 0:04:08 lr: 0.000046 grad: 0.1008 (0.0948) loss: 0.8558 (0.8630) time: 0.1242 data: 0.0449 max mem: 8299 +Train: [60] [4100/6250] eta: 0:03:57 lr: 0.000046 grad: 0.0913 (0.0948) loss: 0.8594 (0.8629) time: 0.1105 data: 0.0403 max mem: 8299 +Train: [60] [4200/6250] eta: 0:03:46 lr: 0.000046 grad: 0.0896 (0.0947) loss: 0.8591 (0.8628) time: 0.1095 data: 0.0418 max mem: 8299 +Train: [60] [4300/6250] eta: 0:03:35 lr: 0.000046 grad: 0.0939 (0.0948) loss: 0.8566 (0.8628) time: 0.1004 data: 0.0297 max mem: 8299 +Train: [60] [4400/6250] eta: 0:03:24 lr: 0.000046 grad: 0.0950 (0.0949) loss: 0.8568 (0.8627) time: 0.1167 data: 0.0514 max mem: 8299 +Train: [60] [4500/6250] eta: 0:03:13 lr: 0.000046 grad: 0.0910 (0.0949) loss: 0.8579 (0.8627) time: 0.1027 data: 0.0338 max mem: 8299 +Train: [60] [4600/6250] eta: 0:03:02 lr: 0.000046 grad: 0.0903 (0.0949) loss: 0.8566 (0.8626) time: 0.1035 data: 0.0296 max mem: 8299 +Train: [60] [4700/6250] eta: 0:02:51 lr: 0.000046 grad: 0.0893 (0.0949) loss: 0.8603 (0.8625) time: 0.0996 data: 0.0297 max mem: 8299 +Train: [60] [4800/6250] eta: 0:02:39 lr: 0.000046 grad: 0.0928 (0.0949) loss: 0.8629 (0.8625) time: 0.1041 data: 0.0344 max mem: 8299 +Train: [60] [4900/6250] eta: 0:02:28 lr: 0.000046 grad: 0.0940 (0.0949) loss: 0.8545 (0.8624) time: 0.1121 data: 0.0429 max mem: 8299 +Train: [60] [5000/6250] eta: 0:02:17 lr: 0.000046 grad: 0.0907 (0.0948) loss: 0.8588 (0.8624) time: 0.1119 data: 0.0417 max mem: 8299 +Train: [60] [5100/6250] eta: 0:02:07 lr: 0.000046 grad: 0.0911 (0.0947) loss: 0.8635 (0.8625) time: 0.1260 data: 0.0447 max mem: 8299 +Train: [60] [5200/6250] eta: 0:01:56 lr: 0.000045 grad: 0.0943 (0.0947) loss: 0.8653 (0.8625) time: 0.1163 data: 0.0374 max mem: 8299 +Train: [60] [5300/6250] eta: 0:01:45 lr: 0.000045 grad: 0.0900 (0.0947) loss: 0.8621 (0.8625) time: 0.1219 data: 0.0488 max mem: 8299 +Train: [60] [5400/6250] eta: 0:01:34 lr: 0.000045 grad: 0.0862 (0.0947) loss: 0.8681 (0.8625) time: 0.1106 data: 0.0355 max mem: 8299 +Train: [60] [5500/6250] eta: 0:01:23 lr: 0.000045 grad: 0.0932 (0.0948) loss: 0.8597 (0.8625) time: 0.1197 data: 0.0542 max mem: 8299 +Train: [60] [5600/6250] eta: 0:01:12 lr: 0.000045 grad: 0.0912 (0.0948) loss: 0.8584 (0.8625) time: 0.1106 data: 0.0457 max mem: 8299 +Train: [60] [5700/6250] eta: 0:01:01 lr: 0.000045 grad: 0.0980 (0.0949) loss: 0.8577 (0.8624) time: 0.1059 data: 0.0417 max mem: 8299 +Train: [60] [5800/6250] eta: 0:00:50 lr: 0.000045 grad: 0.0987 (0.0950) loss: 0.8619 (0.8623) time: 0.1036 data: 0.0304 max mem: 8299 +Train: [60] [5900/6250] eta: 0:00:39 lr: 0.000045 grad: 0.0943 (0.0951) loss: 0.8571 (0.8623) time: 0.1001 data: 0.0277 max mem: 8299 +Train: [60] [6000/6250] eta: 0:00:27 lr: 0.000045 grad: 0.1019 (0.0953) loss: 0.8591 (0.8622) time: 0.1104 data: 0.0399 max mem: 8299 +Train: [60] [6100/6250] eta: 0:00:16 lr: 0.000045 grad: 0.1008 (0.0953) loss: 0.8596 (0.8622) time: 0.1118 data: 0.0394 max mem: 8299 +Train: [60] [6200/6250] eta: 0:00:05 lr: 0.000045 grad: 0.0961 (0.0954) loss: 0.8575 (0.8621) time: 0.1078 data: 0.0296 max mem: 8299 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.0891 (0.0954) loss: 0.8574 (0.8621) time: 0.0985 data: 0.0235 max mem: 8299 +Train: [60] Total time: 0:11:38 (0.1118 s / it) +Averaged stats: lr: 0.000045 grad: 0.0891 (0.0954) loss: 0.8574 (0.8621) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:04:43 loss: 0.8990 (0.8990) time: 4.5698 data: 4.5389 max mem: 8299 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8848 (0.8851) time: 0.1078 data: 0.0835 max mem: 8299 +Eval (hcp-train-subset): [60] Total time: 0:00:12 (0.1942 s / it) +Averaged stats (hcp-train-subset): loss: 0.8848 (0.8851) +Eval (hcp-val): [60] [ 0/62] eta: 0:03:51 loss: 0.8763 (0.8763) time: 3.7323 data: 3.6598 max mem: 8299 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8805 (0.8834) time: 0.1073 data: 0.0831 max mem: 8299 +Eval (hcp-val): [60] Total time: 0:00:11 (0.1864 s / it) +Averaged stats (hcp-val): loss: 0.8805 (0.8834) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 8:02:25 lr: 0.000045 grad: 0.0903 (0.0903) loss: 0.8709 (0.8709) time: 4.6313 data: 4.4564 max mem: 8299 +Train: [61] [ 100/6250] eta: 0:16:37 lr: 0.000045 grad: 0.0901 (0.1162) loss: 0.8694 (0.8719) time: 0.1388 data: 0.0519 max mem: 8299 +Train: [61] [ 200/6250] eta: 0:14:09 lr: 0.000045 grad: 0.0838 (0.1065) loss: 0.8601 (0.8679) time: 0.1110 data: 0.0332 max mem: 8299 +Train: [61] [ 300/6250] eta: 0:13:08 lr: 0.000045 grad: 0.0939 (0.1035) loss: 0.8651 (0.8661) time: 0.1139 data: 0.0360 max mem: 8299 +Train: [61] [ 400/6250] eta: 0:12:30 lr: 0.000045 grad: 0.0957 (0.1023) loss: 0.8641 (0.8653) time: 0.1219 data: 0.0440 max mem: 8299 +Train: [61] [ 500/6250] eta: 0:11:57 lr: 0.000045 grad: 0.0847 (0.1008) loss: 0.8709 (0.8651) time: 0.1002 data: 0.0231 max mem: 8299 +Train: [61] [ 600/6250] eta: 0:11:31 lr: 0.000045 grad: 0.0925 (0.0998) loss: 0.8632 (0.8652) time: 0.1077 data: 0.0291 max mem: 8299 +Train: [61] [ 700/6250] eta: 0:11:09 lr: 0.000045 grad: 0.0834 (0.0984) loss: 0.8623 (0.8647) time: 0.1092 data: 0.0300 max mem: 8299 +Train: [61] [ 800/6250] eta: 0:10:58 lr: 0.000045 grad: 0.0923 (0.0974) loss: 0.8603 (0.8647) time: 0.1431 data: 0.0666 max mem: 8299 +Train: [61] [ 900/6250] eta: 0:10:50 lr: 0.000045 grad: 0.0831 (0.0965) loss: 0.8633 (0.8649) time: 0.1275 data: 0.0539 max mem: 8299 +Train: [61] [1000/6250] eta: 0:10:42 lr: 0.000045 grad: 0.0897 (0.0958) loss: 0.8662 (0.8652) time: 0.1337 data: 0.0718 max mem: 8299 +Train: [61] [1100/6250] eta: 0:10:32 lr: 0.000045 grad: 0.0883 (0.0952) loss: 0.8673 (0.8654) time: 0.1250 data: 0.0600 max mem: 8299 +Train: [61] [1200/6250] eta: 0:10:20 lr: 0.000045 grad: 0.0875 (0.0948) loss: 0.8628 (0.8652) time: 0.1344 data: 0.0660 max mem: 8299 +Train: [61] [1300/6250] eta: 0:10:08 lr: 0.000045 grad: 0.0911 (0.0946) loss: 0.8597 (0.8651) time: 0.1219 data: 0.0557 max mem: 8299 +Train: [61] [1400/6250] eta: 0:09:56 lr: 0.000045 grad: 0.0934 (0.0947) loss: 0.8655 (0.8650) time: 0.1434 data: 0.0749 max mem: 8299 +Train: [61] [1500/6250] eta: 0:09:40 lr: 0.000045 grad: 0.0863 (0.0943) loss: 0.8597 (0.8648) time: 0.1059 data: 0.0326 max mem: 8299 +Train: [61] [1600/6250] eta: 0:09:28 lr: 0.000045 grad: 0.0895 (0.0943) loss: 0.8621 (0.8647) time: 0.1146 data: 0.0455 max mem: 8299 +Train: [61] [1700/6250] eta: 0:09:14 lr: 0.000045 grad: 0.0988 (0.0943) loss: 0.8598 (0.8645) time: 0.0860 data: 0.0070 max mem: 8299 +Train: [61] [1800/6250] eta: 0:09:02 lr: 0.000045 grad: 0.0910 (0.0941) loss: 0.8580 (0.8644) time: 0.1385 data: 0.0659 max mem: 8299 +Train: [61] [1900/6250] eta: 0:08:48 lr: 0.000045 grad: 0.0818 (0.0940) loss: 0.8635 (0.8644) time: 0.1205 data: 0.0554 max mem: 8299 +Train: [61] [2000/6250] eta: 0:08:37 lr: 0.000045 grad: 0.0967 (0.0939) loss: 0.8674 (0.8644) time: 0.1208 data: 0.0477 max mem: 8299 +Train: [61] [2100/6250] eta: 0:08:23 lr: 0.000044 grad: 0.0898 (0.0938) loss: 0.8652 (0.8643) time: 0.1084 data: 0.0380 max mem: 8299 +Train: [61] [2200/6250] eta: 0:08:11 lr: 0.000044 grad: 0.0951 (0.0939) loss: 0.8698 (0.8643) time: 0.1323 data: 0.0642 max mem: 8299 +Train: [61] [2300/6250] eta: 0:07:59 lr: 0.000044 grad: 0.0918 (0.0939) loss: 0.8602 (0.8642) time: 0.1320 data: 0.0643 max mem: 8299 +Train: [61] [2400/6250] eta: 0:07:47 lr: 0.000044 grad: 0.0894 (0.0939) loss: 0.8617 (0.8642) time: 0.1312 data: 0.0646 max mem: 8299 +Train: [61] [2500/6250] eta: 0:07:34 lr: 0.000044 grad: 0.0876 (0.0938) loss: 0.8707 (0.8642) time: 0.1278 data: 0.0597 max mem: 8299 +Train: [61] [2600/6250] eta: 0:07:21 lr: 0.000044 grad: 0.0904 (0.0938) loss: 0.8662 (0.8642) time: 0.1204 data: 0.0452 max mem: 8299 +Train: [61] [2700/6250] eta: 0:07:09 lr: 0.000044 grad: 0.0875 (0.0938) loss: 0.8678 (0.8642) time: 0.1198 data: 0.0493 max mem: 8299 +Train: [61] [2800/6250] eta: 0:06:58 lr: 0.000044 grad: 0.0921 (0.0939) loss: 0.8660 (0.8642) time: 0.1309 data: 0.0634 max mem: 8299 +Train: [61] [2900/6250] eta: 0:06:45 lr: 0.000044 grad: 0.0906 (0.0939) loss: 0.8672 (0.8641) time: 0.1206 data: 0.0480 max mem: 8299 +Train: [61] [3000/6250] eta: 0:06:33 lr: 0.000044 grad: 0.0928 (0.0940) loss: 0.8576 (0.8640) time: 0.1235 data: 0.0565 max mem: 8299 +Train: [61] [3100/6250] eta: 0:06:20 lr: 0.000044 grad: 0.0921 (0.0940) loss: 0.8638 (0.8640) time: 0.1305 data: 0.0621 max mem: 8299 +Train: [61] [3200/6250] eta: 0:06:08 lr: 0.000044 grad: 0.0927 (0.0941) loss: 0.8655 (0.8640) time: 0.1136 data: 0.0446 max mem: 8299 +Train: [61] [3300/6250] eta: 0:05:56 lr: 0.000044 grad: 0.0951 (0.0942) loss: 0.8625 (0.8639) time: 0.1159 data: 0.0439 max mem: 8299 +Train: [61] [3400/6250] eta: 0:05:44 lr: 0.000044 grad: 0.0884 (0.0942) loss: 0.8636 (0.8640) time: 0.1273 data: 0.0619 max mem: 8299 +Train: [61] [3500/6250] eta: 0:05:32 lr: 0.000044 grad: 0.0947 (0.0942) loss: 0.8635 (0.8640) time: 0.1076 data: 0.0415 max mem: 8299 +Train: [61] [3600/6250] eta: 0:05:20 lr: 0.000044 grad: 0.0882 (0.0941) loss: 0.8656 (0.8640) time: 0.0841 data: 0.0141 max mem: 8299 +Train: [61] [3700/6250] eta: 0:05:08 lr: 0.000044 grad: 0.0841 (0.0940) loss: 0.8726 (0.8641) time: 0.1140 data: 0.0494 max mem: 8299 +Train: [61] [3800/6250] eta: 0:04:56 lr: 0.000044 grad: 0.0979 (0.0942) loss: 0.8594 (0.8640) time: 0.1243 data: 0.0530 max mem: 8299 +Train: [61] [3900/6250] eta: 0:04:44 lr: 0.000044 grad: 0.0910 (0.0942) loss: 0.8635 (0.8639) time: 0.1168 data: 0.0459 max mem: 8299 +Train: [61] [4000/6250] eta: 0:04:32 lr: 0.000044 grad: 0.0825 (0.0943) loss: 0.8646 (0.8638) time: 0.1737 data: 0.1024 max mem: 8299 +Train: [61] [4100/6250] eta: 0:04:20 lr: 0.000044 grad: 0.0924 (0.0943) loss: 0.8644 (0.8637) time: 0.1164 data: 0.0455 max mem: 8299 +Train: [61] [4200/6250] eta: 0:04:08 lr: 0.000044 grad: 0.0920 (0.0943) loss: 0.8633 (0.8637) time: 0.1328 data: 0.0592 max mem: 8299 +Train: [61] [4300/6250] eta: 0:03:55 lr: 0.000044 grad: 0.0833 (0.0943) loss: 0.8617 (0.8636) time: 0.1038 data: 0.0343 max mem: 8299 +Train: [61] [4400/6250] eta: 0:03:43 lr: 0.000044 grad: 0.0832 (0.0943) loss: 0.8632 (0.8636) time: 0.1190 data: 0.0476 max mem: 8299 +Train: [61] [4500/6250] eta: 0:03:31 lr: 0.000044 grad: 0.0891 (0.0942) loss: 0.8635 (0.8635) time: 0.1220 data: 0.0471 max mem: 8299 +Train: [61] [4600/6250] eta: 0:03:19 lr: 0.000044 grad: 0.0869 (0.0943) loss: 0.8604 (0.8635) time: 0.1352 data: 0.0649 max mem: 8299 +Train: [61] [4700/6250] eta: 0:03:07 lr: 0.000044 grad: 0.0918 (0.0943) loss: 0.8595 (0.8634) time: 0.1493 data: 0.0794 max mem: 8299 +Train: [61] [4800/6250] eta: 0:02:55 lr: 0.000044 grad: 0.0863 (0.0943) loss: 0.8662 (0.8634) time: 0.1170 data: 0.0515 max mem: 8299 +Train: [61] [4900/6250] eta: 0:02:43 lr: 0.000044 grad: 0.0848 (0.0942) loss: 0.8626 (0.8634) time: 0.1417 data: 0.0758 max mem: 8299 +Train: [61] [5000/6250] eta: 0:02:31 lr: 0.000044 grad: 0.0947 (0.0942) loss: 0.8580 (0.8633) time: 0.1071 data: 0.0350 max mem: 8299 +Train: [61] [5100/6250] eta: 0:02:19 lr: 0.000044 grad: 0.0937 (0.0942) loss: 0.8661 (0.8633) time: 0.1430 data: 0.0702 max mem: 8299 +Train: [61] [5200/6250] eta: 0:02:07 lr: 0.000044 grad: 0.0898 (0.0941) loss: 0.8615 (0.8633) time: 0.1505 data: 0.0808 max mem: 8299 +Train: [61] [5300/6250] eta: 0:01:55 lr: 0.000043 grad: 0.0927 (0.0942) loss: 0.8609 (0.8632) time: 0.1311 data: 0.0587 max mem: 8299 +Train: [61] [5400/6250] eta: 0:01:43 lr: 0.000043 grad: 0.0916 (0.0943) loss: 0.8627 (0.8631) time: 0.1241 data: 0.0513 max mem: 8299 +Train: [61] [5500/6250] eta: 0:01:31 lr: 0.000043 grad: 0.0880 (0.0943) loss: 0.8622 (0.8631) time: 0.1329 data: 0.0605 max mem: 8299 +Train: [61] [5600/6250] eta: 0:01:18 lr: 0.000043 grad: 0.0939 (0.0942) loss: 0.8613 (0.8631) time: 0.1289 data: 0.0618 max mem: 8299 +Train: [61] [5700/6250] eta: 0:01:06 lr: 0.000043 grad: 0.0895 (0.0943) loss: 0.8582 (0.8630) time: 0.0945 data: 0.0216 max mem: 8299 +Train: [61] [5800/6250] eta: 0:00:54 lr: 0.000043 grad: 0.1040 (0.0944) loss: 0.8624 (0.8629) time: 0.1105 data: 0.0374 max mem: 8299 +Train: [61] [5900/6250] eta: 0:00:42 lr: 0.000043 grad: 0.0870 (0.0944) loss: 0.8635 (0.8629) time: 0.1044 data: 0.0255 max mem: 8299 +Train: [61] [6000/6250] eta: 0:00:30 lr: 0.000043 grad: 0.0922 (0.0944) loss: 0.8580 (0.8629) time: 0.0937 data: 0.0139 max mem: 8299 +Train: [61] [6100/6250] eta: 0:00:18 lr: 0.000043 grad: 0.0852 (0.0944) loss: 0.8601 (0.8628) time: 0.0955 data: 0.0240 max mem: 8299 +Train: [61] [6200/6250] eta: 0:00:05 lr: 0.000043 grad: 0.0817 (0.0943) loss: 0.8643 (0.8628) time: 0.1106 data: 0.0380 max mem: 8299 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.0939 (0.0943) loss: 0.8648 (0.8628) time: 0.1185 data: 0.0478 max mem: 8299 +Train: [61] Total time: 0:12:33 (0.1205 s / it) +Averaged stats: lr: 0.000043 grad: 0.0939 (0.0943) loss: 0.8648 (0.8628) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:03:58 loss: 0.8907 (0.8907) time: 3.8475 data: 3.7712 max mem: 8299 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8845 (0.8835) time: 0.1193 data: 0.0949 max mem: 8299 +Eval (hcp-train-subset): [61] Total time: 0:00:12 (0.2005 s / it) +Averaged stats (hcp-train-subset): loss: 0.8845 (0.8835) +Eval (hcp-val): [61] [ 0/62] eta: 0:03:28 loss: 0.8778 (0.8778) time: 3.3574 data: 3.2980 max mem: 8299 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8810 (0.8823) time: 0.1264 data: 0.1022 max mem: 8299 +Eval (hcp-val): [61] Total time: 0:00:11 (0.1916 s / it) +Averaged stats (hcp-val): loss: 0.8810 (0.8823) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 7:03:02 lr: 0.000043 grad: 0.2469 (0.2469) loss: 0.8777 (0.8777) time: 4.0612 data: 3.7333 max mem: 8299 +Train: [62] [ 100/6250] eta: 0:16:55 lr: 0.000043 grad: 0.0802 (0.1093) loss: 0.8665 (0.8716) time: 0.1259 data: 0.0415 max mem: 8299 +Train: [62] [ 200/6250] eta: 0:14:14 lr: 0.000043 grad: 0.0781 (0.0979) loss: 0.8722 (0.8734) time: 0.1123 data: 0.0325 max mem: 8299 +Train: [62] [ 300/6250] eta: 0:13:19 lr: 0.000043 grad: 0.0865 (0.0934) loss: 0.8713 (0.8736) time: 0.0969 data: 0.0119 max mem: 8299 +Train: [62] [ 400/6250] eta: 0:12:42 lr: 0.000043 grad: 0.0827 (0.0914) loss: 0.8686 (0.8728) time: 0.0937 data: 0.0142 max mem: 8299 +Train: [62] [ 500/6250] eta: 0:12:11 lr: 0.000043 grad: 0.0912 (0.0907) loss: 0.8672 (0.8722) time: 0.1191 data: 0.0426 max mem: 8299 +Train: [62] [ 600/6250] eta: 0:11:40 lr: 0.000043 grad: 0.0848 (0.0903) loss: 0.8737 (0.8718) time: 0.1082 data: 0.0228 max mem: 8299 +Train: [62] [ 700/6250] eta: 0:11:19 lr: 0.000043 grad: 0.0877 (0.0904) loss: 0.8702 (0.8711) time: 0.1079 data: 0.0272 max mem: 8299 +Train: [62] [ 800/6250] eta: 0:10:58 lr: 0.000043 grad: 0.0800 (0.0902) loss: 0.8638 (0.8707) time: 0.1011 data: 0.0192 max mem: 8299 +Train: [62] [ 900/6250] eta: 0:10:39 lr: 0.000043 grad: 0.0907 (0.0908) loss: 0.8659 (0.8702) time: 0.1048 data: 0.0265 max mem: 8299 +Train: [62] [1000/6250] eta: 0:10:20 lr: 0.000043 grad: 0.0847 (0.0906) loss: 0.8668 (0.8697) time: 0.1124 data: 0.0395 max mem: 8299 +Train: [62] [1100/6250] eta: 0:10:04 lr: 0.000043 grad: 0.0879 (0.0908) loss: 0.8653 (0.8691) time: 0.0973 data: 0.0217 max mem: 8299 +Train: [62] [1200/6250] eta: 0:09:48 lr: 0.000043 grad: 0.0828 (0.0908) loss: 0.8647 (0.8686) time: 0.1227 data: 0.0558 max mem: 8299 +Train: [62] [1300/6250] eta: 0:09:31 lr: 0.000043 grad: 0.0903 (0.0912) loss: 0.8567 (0.8681) time: 0.1143 data: 0.0523 max mem: 8299 +Train: [62] [1400/6250] eta: 0:09:18 lr: 0.000043 grad: 0.0880 (0.0914) loss: 0.8634 (0.8675) time: 0.1191 data: 0.0449 max mem: 8299 +Train: [62] [1500/6250] eta: 0:09:02 lr: 0.000043 grad: 0.1002 (0.0916) loss: 0.8516 (0.8671) time: 0.1062 data: 0.0251 max mem: 8299 +Train: [62] [1600/6250] eta: 0:08:49 lr: 0.000043 grad: 0.0871 (0.0919) loss: 0.8566 (0.8667) time: 0.1112 data: 0.0421 max mem: 8299 +Train: [62] [1700/6250] eta: 0:08:37 lr: 0.000043 grad: 0.0961 (0.0922) loss: 0.8621 (0.8664) time: 0.1301 data: 0.0589 max mem: 8299 +Train: [62] [1800/6250] eta: 0:08:25 lr: 0.000043 grad: 0.1019 (0.0924) loss: 0.8510 (0.8660) time: 0.1020 data: 0.0267 max mem: 8299 +Train: [62] [1900/6250] eta: 0:08:13 lr: 0.000043 grad: 0.0993 (0.0927) loss: 0.8571 (0.8657) time: 0.1271 data: 0.0543 max mem: 8299 +Train: [62] [2000/6250] eta: 0:08:00 lr: 0.000043 grad: 0.0907 (0.0929) loss: 0.8585 (0.8654) time: 0.1140 data: 0.0386 max mem: 8299 +Train: [62] [2100/6250] eta: 0:07:49 lr: 0.000043 grad: 0.0962 (0.0931) loss: 0.8648 (0.8652) time: 0.1086 data: 0.0395 max mem: 8299 +Train: [62] [2200/6250] eta: 0:07:37 lr: 0.000042 grad: 0.0912 (0.0933) loss: 0.8599 (0.8650) time: 0.1266 data: 0.0583 max mem: 8299 +Train: [62] [2300/6250] eta: 0:07:26 lr: 0.000042 grad: 0.0923 (0.0936) loss: 0.8618 (0.8648) time: 0.1194 data: 0.0527 max mem: 8299 +Train: [62] [2400/6250] eta: 0:07:14 lr: 0.000042 grad: 0.0909 (0.0937) loss: 0.8703 (0.8647) time: 0.1052 data: 0.0327 max mem: 8299 +Train: [62] [2500/6250] eta: 0:07:04 lr: 0.000042 grad: 0.0966 (0.0940) loss: 0.8646 (0.8646) time: 0.1388 data: 0.0692 max mem: 8299 +Train: [62] [2600/6250] eta: 0:06:51 lr: 0.000042 grad: 0.0950 (0.0941) loss: 0.8611 (0.8645) time: 0.1191 data: 0.0497 max mem: 8299 +Train: [62] [2700/6250] eta: 0:06:41 lr: 0.000042 grad: 0.0903 (0.0943) loss: 0.8645 (0.8644) time: 0.1204 data: 0.0512 max mem: 8299 +Train: [62] [2800/6250] eta: 0:06:30 lr: 0.000042 grad: 0.0926 (0.0944) loss: 0.8591 (0.8643) time: 0.1114 data: 0.0417 max mem: 8299 +Train: [62] [2900/6250] eta: 0:06:18 lr: 0.000042 grad: 0.0982 (0.0945) loss: 0.8552 (0.8643) time: 0.1234 data: 0.0531 max mem: 8299 +Train: [62] [3000/6250] eta: 0:06:08 lr: 0.000042 grad: 0.0922 (0.0946) loss: 0.8624 (0.8643) time: 0.1366 data: 0.0699 max mem: 8299 +Train: [62] [3100/6250] eta: 0:05:57 lr: 0.000042 grad: 0.1004 (0.0947) loss: 0.8623 (0.8642) time: 0.1345 data: 0.0683 max mem: 8299 +Train: [62] [3200/6250] eta: 0:05:45 lr: 0.000042 grad: 0.0936 (0.0949) loss: 0.8665 (0.8641) time: 0.1084 data: 0.0357 max mem: 8299 +Train: [62] [3300/6250] eta: 0:05:34 lr: 0.000042 grad: 0.0961 (0.0950) loss: 0.8556 (0.8640) time: 0.1214 data: 0.0442 max mem: 8299 +Train: [62] [3400/6250] eta: 0:05:23 lr: 0.000042 grad: 0.0913 (0.0951) loss: 0.8633 (0.8639) time: 0.1182 data: 0.0462 max mem: 8299 +Train: [62] [3500/6250] eta: 0:05:12 lr: 0.000042 grad: 0.0924 (0.0951) loss: 0.8602 (0.8638) time: 0.1055 data: 0.0350 max mem: 8299 +Train: [62] [3600/6250] eta: 0:05:00 lr: 0.000042 grad: 0.0935 (0.0952) loss: 0.8606 (0.8636) time: 0.0910 data: 0.0161 max mem: 8299 +Train: [62] [3700/6250] eta: 0:04:49 lr: 0.000042 grad: 0.1068 (0.0954) loss: 0.8554 (0.8634) time: 0.1080 data: 0.0360 max mem: 8299 +Train: [62] [3800/6250] eta: 0:04:38 lr: 0.000042 grad: 0.0926 (0.0955) loss: 0.8594 (0.8633) time: 0.1181 data: 0.0475 max mem: 8299 +Train: [62] [3900/6250] eta: 0:04:27 lr: 0.000042 grad: 0.0941 (0.0956) loss: 0.8564 (0.8632) time: 0.1102 data: 0.0364 max mem: 8299 +Train: [62] [4000/6250] eta: 0:04:16 lr: 0.000042 grad: 0.0901 (0.0955) loss: 0.8654 (0.8632) time: 0.0927 data: 0.0110 max mem: 8299 +Train: [62] [4100/6250] eta: 0:04:04 lr: 0.000042 grad: 0.0956 (0.0955) loss: 0.8666 (0.8632) time: 0.1138 data: 0.0433 max mem: 8299 +Train: [62] [4200/6250] eta: 0:03:53 lr: 0.000042 grad: 0.0894 (0.0956) loss: 0.8606 (0.8632) time: 0.1112 data: 0.0360 max mem: 8299 +Train: [62] [4300/6250] eta: 0:03:42 lr: 0.000042 grad: 0.0951 (0.0956) loss: 0.8601 (0.8632) time: 0.1114 data: 0.0388 max mem: 8299 +Train: [62] [4400/6250] eta: 0:03:30 lr: 0.000042 grad: 0.0839 (0.0956) loss: 0.8601 (0.8632) time: 0.1202 data: 0.0489 max mem: 8299 +Train: [62] [4500/6250] eta: 0:03:19 lr: 0.000042 grad: 0.0875 (0.0957) loss: 0.8653 (0.8632) time: 0.1173 data: 0.0466 max mem: 8299 +Train: [62] [4600/6250] eta: 0:03:08 lr: 0.000042 grad: 0.0910 (0.0958) loss: 0.8588 (0.8632) time: 0.1303 data: 0.0632 max mem: 8299 +Train: [62] [4700/6250] eta: 0:02:57 lr: 0.000042 grad: 0.0892 (0.0958) loss: 0.8636 (0.8631) time: 0.1189 data: 0.0480 max mem: 8299 +Train: [62] [4800/6250] eta: 0:02:45 lr: 0.000042 grad: 0.0961 (0.0959) loss: 0.8539 (0.8631) time: 0.1127 data: 0.0377 max mem: 8299 +Train: [62] [4900/6250] eta: 0:02:34 lr: 0.000042 grad: 0.0978 (0.0960) loss: 0.8538 (0.8630) time: 0.1302 data: 0.0668 max mem: 8299 +Train: [62] [5000/6250] eta: 0:02:22 lr: 0.000042 grad: 0.0924 (0.0961) loss: 0.8610 (0.8629) time: 0.1031 data: 0.0347 max mem: 8299 +Train: [62] [5100/6250] eta: 0:02:11 lr: 0.000042 grad: 0.1009 (0.0961) loss: 0.8660 (0.8628) time: 0.1165 data: 0.0478 max mem: 8299 +Train: [62] [5200/6250] eta: 0:02:00 lr: 0.000042 grad: 0.0947 (0.0962) loss: 0.8641 (0.8628) time: 0.1237 data: 0.0530 max mem: 8299 +Train: [62] [5300/6250] eta: 0:01:49 lr: 0.000042 grad: 0.0975 (0.0964) loss: 0.8696 (0.8627) time: 0.1257 data: 0.0576 max mem: 8299 +Train: [62] [5400/6250] eta: 0:01:38 lr: 0.000041 grad: 0.0985 (0.0963) loss: 0.8591 (0.8628) time: 0.1234 data: 0.0417 max mem: 8299 +Train: [62] [5500/6250] eta: 0:01:26 lr: 0.000041 grad: 0.0953 (0.0964) loss: 0.8639 (0.8628) time: 0.1175 data: 0.0437 max mem: 8299 +Train: [62] [5600/6250] eta: 0:01:15 lr: 0.000041 grad: 0.0940 (0.0964) loss: 0.8637 (0.8628) time: 0.1220 data: 0.0493 max mem: 8299 +Train: [62] [5700/6250] eta: 0:01:03 lr: 0.000041 grad: 0.0972 (0.0964) loss: 0.8573 (0.8628) time: 0.1201 data: 0.0406 max mem: 8299 +Train: [62] [5800/6250] eta: 0:00:51 lr: 0.000041 grad: 0.0901 (0.0964) loss: 0.8655 (0.8628) time: 0.1124 data: 0.0381 max mem: 8299 +Train: [62] [5900/6250] eta: 0:00:40 lr: 0.000041 grad: 0.0987 (0.0964) loss: 0.8578 (0.8628) time: 0.1082 data: 0.0345 max mem: 8299 +Train: [62] [6000/6250] eta: 0:00:28 lr: 0.000041 grad: 0.0928 (0.0964) loss: 0.8645 (0.8628) time: 0.1179 data: 0.0452 max mem: 8299 +Train: [62] [6100/6250] eta: 0:00:17 lr: 0.000041 grad: 0.0943 (0.0965) loss: 0.8603 (0.8628) time: 0.1079 data: 0.0362 max mem: 8299 +Train: [62] [6200/6250] eta: 0:00:05 lr: 0.000041 grad: 0.0907 (0.0965) loss: 0.8636 (0.8628) time: 0.1229 data: 0.0467 max mem: 8299 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1006 (0.0965) loss: 0.8574 (0.8628) time: 0.1063 data: 0.0305 max mem: 8299 +Train: [62] Total time: 0:12:01 (0.1154 s / it) +Averaged stats: lr: 0.000041 grad: 0.1006 (0.0965) loss: 0.8574 (0.8628) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:05:04 loss: 0.8949 (0.8949) time: 4.9135 data: 4.8829 max mem: 8299 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8819 (0.8825) time: 0.1274 data: 0.1031 max mem: 8299 +Eval (hcp-train-subset): [62] Total time: 0:00:12 (0.1991 s / it) +Averaged stats (hcp-train-subset): loss: 0.8819 (0.8825) +Eval (hcp-val): [62] [ 0/62] eta: 0:03:28 loss: 0.8801 (0.8801) time: 3.3596 data: 3.2907 max mem: 8299 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8804 (0.8814) time: 0.1147 data: 0.0893 max mem: 8299 +Eval (hcp-val): [62] Total time: 0:00:11 (0.1886 s / it) +Averaged stats (hcp-val): loss: 0.8804 (0.8814) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 8:37:19 lr: 0.000041 grad: 0.0896 (0.0896) loss: 0.8865 (0.8865) time: 4.9663 data: 4.8595 max mem: 8299 +Train: [63] [ 100/6250] eta: 0:16:40 lr: 0.000041 grad: 0.0907 (0.0984) loss: 0.8652 (0.8718) time: 0.1311 data: 0.0420 max mem: 8299 +Train: [63] [ 200/6250] eta: 0:13:58 lr: 0.000041 grad: 0.0926 (0.0965) loss: 0.8653 (0.8697) time: 0.1041 data: 0.0147 max mem: 8299 +Train: [63] [ 300/6250] eta: 0:13:15 lr: 0.000041 grad: 0.0904 (0.1001) loss: 0.8580 (0.8646) time: 0.1258 data: 0.0461 max mem: 8299 +Train: [63] [ 400/6250] eta: 0:12:39 lr: 0.000041 grad: 0.1014 (0.0991) loss: 0.8541 (0.8627) time: 0.1233 data: 0.0508 max mem: 8299 +Train: [63] [ 500/6250] eta: 0:12:08 lr: 0.000041 grad: 0.0935 (0.0997) loss: 0.8543 (0.8614) time: 0.1132 data: 0.0402 max mem: 8299 +Train: [63] [ 600/6250] eta: 0:11:40 lr: 0.000041 grad: 0.0951 (0.0997) loss: 0.8535 (0.8606) time: 0.1169 data: 0.0370 max mem: 8299 +Train: [63] [ 700/6250] eta: 0:11:19 lr: 0.000041 grad: 0.0929 (0.0996) loss: 0.8576 (0.8600) time: 0.1376 data: 0.0626 max mem: 8299 +Train: [63] [ 800/6250] eta: 0:10:55 lr: 0.000041 grad: 0.1013 (0.0997) loss: 0.8554 (0.8593) time: 0.1071 data: 0.0374 max mem: 8299 +Train: [63] [ 900/6250] eta: 0:10:41 lr: 0.000041 grad: 0.0884 (0.0989) loss: 0.8617 (0.8596) time: 0.1519 data: 0.0803 max mem: 8299 +Train: [63] [1000/6250] eta: 0:10:27 lr: 0.000041 grad: 0.0850 (0.0985) loss: 0.8660 (0.8598) time: 0.1171 data: 0.0389 max mem: 8299 +Train: [63] [1100/6250] eta: 0:10:14 lr: 0.000041 grad: 0.0885 (0.0983) loss: 0.8634 (0.8598) time: 0.1180 data: 0.0495 max mem: 8299 +Train: [63] [1200/6250] eta: 0:10:01 lr: 0.000041 grad: 0.0897 (0.0981) loss: 0.8587 (0.8600) time: 0.1047 data: 0.0366 max mem: 8299 +Train: [63] [1300/6250] eta: 0:09:52 lr: 0.000041 grad: 0.0856 (0.0978) loss: 0.8648 (0.8602) time: 0.1004 data: 0.0228 max mem: 8299 +Train: [63] [1400/6250] eta: 0:09:40 lr: 0.000041 grad: 0.0982 (0.0975) loss: 0.8560 (0.8603) time: 0.1126 data: 0.0397 max mem: 8299 +Train: [63] [1500/6250] eta: 0:09:29 lr: 0.000041 grad: 0.0956 (0.0973) loss: 0.8657 (0.8603) time: 0.1163 data: 0.0462 max mem: 8299 +Train: [63] [1600/6250] eta: 0:09:17 lr: 0.000041 grad: 0.0922 (0.0971) loss: 0.8610 (0.8603) time: 0.1275 data: 0.0511 max mem: 8299 +Train: [63] [1700/6250] eta: 0:09:05 lr: 0.000041 grad: 0.0965 (0.0968) loss: 0.8601 (0.8603) time: 0.1130 data: 0.0412 max mem: 8299 +Train: [63] [1800/6250] eta: 0:08:53 lr: 0.000041 grad: 0.0899 (0.0967) loss: 0.8673 (0.8604) time: 0.1160 data: 0.0434 max mem: 8299 +Train: [63] [1900/6250] eta: 0:08:41 lr: 0.000041 grad: 0.0894 (0.0966) loss: 0.8595 (0.8604) time: 0.1120 data: 0.0381 max mem: 8299 +Train: [63] [2000/6250] eta: 0:08:28 lr: 0.000041 grad: 0.0963 (0.0966) loss: 0.8577 (0.8604) time: 0.1123 data: 0.0522 max mem: 8299 +Train: [63] [2100/6250] eta: 0:08:16 lr: 0.000041 grad: 0.0962 (0.0966) loss: 0.8618 (0.8605) time: 0.1181 data: 0.0477 max mem: 8299 +Train: [63] [2200/6250] eta: 0:08:02 lr: 0.000041 grad: 0.0936 (0.0965) loss: 0.8602 (0.8605) time: 0.1015 data: 0.0298 max mem: 8299 +Train: [63] [2300/6250] eta: 0:07:50 lr: 0.000041 grad: 0.0942 (0.0966) loss: 0.8634 (0.8606) time: 0.1217 data: 0.0511 max mem: 8299 +Train: [63] [2400/6250] eta: 0:07:38 lr: 0.000040 grad: 0.0872 (0.0965) loss: 0.8644 (0.8606) time: 0.1233 data: 0.0502 max mem: 8299 +Train: [63] [2500/6250] eta: 0:07:25 lr: 0.000040 grad: 0.0947 (0.0966) loss: 0.8663 (0.8607) time: 0.0910 data: 0.0170 max mem: 8299 +Train: [63] [2600/6250] eta: 0:07:13 lr: 0.000040 grad: 0.0907 (0.0966) loss: 0.8626 (0.8608) time: 0.1256 data: 0.0547 max mem: 8299 +Train: [63] [2700/6250] eta: 0:07:01 lr: 0.000040 grad: 0.0944 (0.0966) loss: 0.8626 (0.8609) time: 0.1144 data: 0.0435 max mem: 8299 +Train: [63] [2800/6250] eta: 0:06:49 lr: 0.000040 grad: 0.0870 (0.0965) loss: 0.8625 (0.8610) time: 0.1321 data: 0.0629 max mem: 8299 +Train: [63] [2900/6250] eta: 0:06:37 lr: 0.000040 grad: 0.0915 (0.0965) loss: 0.8580 (0.8611) time: 0.1093 data: 0.0400 max mem: 8299 +Train: [63] [3000/6250] eta: 0:06:25 lr: 0.000040 grad: 0.0906 (0.0965) loss: 0.8668 (0.8611) time: 0.1229 data: 0.0527 max mem: 8299 +Train: [63] [3100/6250] eta: 0:06:14 lr: 0.000040 grad: 0.0863 (0.0964) loss: 0.8689 (0.8611) time: 0.1288 data: 0.0581 max mem: 8299 +Train: [63] [3200/6250] eta: 0:06:02 lr: 0.000040 grad: 0.0890 (0.0963) loss: 0.8671 (0.8612) time: 0.1314 data: 0.0629 max mem: 8299 +Train: [63] [3300/6250] eta: 0:05:50 lr: 0.000040 grad: 0.0926 (0.0963) loss: 0.8656 (0.8613) time: 0.1131 data: 0.0395 max mem: 8299 +Train: [63] [3400/6250] eta: 0:05:38 lr: 0.000040 grad: 0.0942 (0.0962) loss: 0.8626 (0.8615) time: 0.1260 data: 0.0496 max mem: 8299 +Train: [63] [3500/6250] eta: 0:05:26 lr: 0.000040 grad: 0.0871 (0.0962) loss: 0.8642 (0.8616) time: 0.1208 data: 0.0490 max mem: 8299 +Train: [63] [3600/6250] eta: 0:05:14 lr: 0.000040 grad: 0.0894 (0.0961) loss: 0.8643 (0.8617) time: 0.1214 data: 0.0502 max mem: 8299 +Train: [63] [3700/6250] eta: 0:05:03 lr: 0.000040 grad: 0.0934 (0.0962) loss: 0.8611 (0.8617) time: 0.1381 data: 0.0704 max mem: 8299 +Train: [63] [3800/6250] eta: 0:04:51 lr: 0.000040 grad: 0.0966 (0.0962) loss: 0.8627 (0.8617) time: 0.0947 data: 0.0239 max mem: 8299 +Train: [63] [3900/6250] eta: 0:04:39 lr: 0.000040 grad: 0.0915 (0.0963) loss: 0.8615 (0.8617) time: 0.1195 data: 0.0409 max mem: 8299 +Train: [63] [4000/6250] eta: 0:04:27 lr: 0.000040 grad: 0.0969 (0.0963) loss: 0.8644 (0.8617) time: 0.1256 data: 0.0566 max mem: 8299 +Train: [63] [4100/6250] eta: 0:04:15 lr: 0.000040 grad: 0.0914 (0.0963) loss: 0.8645 (0.8617) time: 0.0920 data: 0.0131 max mem: 8299 +Train: [63] [4200/6250] eta: 0:04:03 lr: 0.000040 grad: 0.0991 (0.0964) loss: 0.8591 (0.8617) time: 0.1473 data: 0.0857 max mem: 8299 +Train: [63] [4300/6250] eta: 0:03:52 lr: 0.000040 grad: 0.0988 (0.0964) loss: 0.8575 (0.8617) time: 0.1237 data: 0.0498 max mem: 8299 +Train: [63] [4400/6250] eta: 0:03:40 lr: 0.000040 grad: 0.1055 (0.0965) loss: 0.8599 (0.8617) time: 0.1120 data: 0.0402 max mem: 8299 +Train: [63] [4500/6250] eta: 0:03:28 lr: 0.000040 grad: 0.0969 (0.0965) loss: 0.8631 (0.8618) time: 0.1062 data: 0.0405 max mem: 8299 +Train: [63] [4600/6250] eta: 0:03:16 lr: 0.000040 grad: 0.0971 (0.0965) loss: 0.8629 (0.8618) time: 0.1155 data: 0.0427 max mem: 8299 +Train: [63] [4700/6250] eta: 0:03:04 lr: 0.000040 grad: 0.0939 (0.0965) loss: 0.8616 (0.8619) time: 0.1228 data: 0.0547 max mem: 8299 +Train: [63] [4800/6250] eta: 0:02:52 lr: 0.000040 grad: 0.0853 (0.0964) loss: 0.8653 (0.8619) time: 0.1354 data: 0.0690 max mem: 8299 +Train: [63] [4900/6250] eta: 0:02:40 lr: 0.000040 grad: 0.0902 (0.0964) loss: 0.8642 (0.8620) time: 0.1292 data: 0.0542 max mem: 8299 +Train: [63] [5000/6250] eta: 0:02:29 lr: 0.000040 grad: 0.0937 (0.0963) loss: 0.8654 (0.8620) time: 0.1191 data: 0.0517 max mem: 8299 +Train: [63] [5100/6250] eta: 0:02:17 lr: 0.000040 grad: 0.0875 (0.0962) loss: 0.8620 (0.8621) time: 0.1459 data: 0.0624 max mem: 8299 +Train: [63] [5200/6250] eta: 0:02:05 lr: 0.000040 grad: 0.0868 (0.0962) loss: 0.8644 (0.8622) time: 0.1352 data: 0.0632 max mem: 8299 +Train: [63] [5300/6250] eta: 0:01:53 lr: 0.000040 grad: 0.0995 (0.0962) loss: 0.8627 (0.8622) time: 0.1236 data: 0.0505 max mem: 8299 +Train: [63] [5400/6250] eta: 0:01:41 lr: 0.000040 grad: 0.0910 (0.0962) loss: 0.8651 (0.8622) time: 0.1055 data: 0.0363 max mem: 8299 +Train: [63] [5500/6250] eta: 0:01:29 lr: 0.000040 grad: 0.0935 (0.0962) loss: 0.8666 (0.8622) time: 0.1153 data: 0.0457 max mem: 8299 +Train: [63] [5600/6250] eta: 0:01:17 lr: 0.000039 grad: 0.0919 (0.0962) loss: 0.8574 (0.8623) time: 0.1293 data: 0.0635 max mem: 8299 +Train: [63] [5700/6250] eta: 0:01:05 lr: 0.000039 grad: 0.0866 (0.0962) loss: 0.8659 (0.8623) time: 0.1112 data: 0.0409 max mem: 8299 +Train: [63] [5800/6250] eta: 0:00:53 lr: 0.000039 grad: 0.0860 (0.0961) loss: 0.8626 (0.8624) time: 0.1155 data: 0.0415 max mem: 8299 +Train: [63] [5900/6250] eta: 0:00:41 lr: 0.000039 grad: 0.0816 (0.0961) loss: 0.8710 (0.8624) time: 0.1013 data: 0.0219 max mem: 8299 +Train: [63] [6000/6250] eta: 0:00:29 lr: 0.000039 grad: 0.0921 (0.0961) loss: 0.8534 (0.8625) time: 0.1243 data: 0.0574 max mem: 8299 +Train: [63] [6100/6250] eta: 0:00:17 lr: 0.000039 grad: 0.0945 (0.0960) loss: 0.8606 (0.8625) time: 0.1058 data: 0.0314 max mem: 8299 +Train: [63] [6200/6250] eta: 0:00:05 lr: 0.000039 grad: 0.0907 (0.0960) loss: 0.8624 (0.8625) time: 0.0968 data: 0.0214 max mem: 8299 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.0882 (0.0960) loss: 0.8565 (0.8625) time: 0.1096 data: 0.0346 max mem: 8299 +Train: [63] Total time: 0:12:23 (0.1190 s / it) +Averaged stats: lr: 0.000039 grad: 0.0882 (0.0960) loss: 0.8565 (0.8625) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:03:15 loss: 0.8923 (0.8923) time: 3.1613 data: 3.0655 max mem: 8299 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8829 (0.8829) time: 0.1087 data: 0.0845 max mem: 8299 +Eval (hcp-train-subset): [63] Total time: 0:00:12 (0.1960 s / it) +Averaged stats (hcp-train-subset): loss: 0.8829 (0.8829) +Eval (hcp-val): [63] [ 0/62] eta: 0:04:44 loss: 0.8828 (0.8828) time: 4.5964 data: 4.5681 max mem: 8299 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8803 (0.8824) time: 0.1127 data: 0.0883 max mem: 8299 +Eval (hcp-val): [63] Total time: 0:00:11 (0.1863 s / it) +Averaged stats (hcp-val): loss: 0.8803 (0.8824) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 8:09:22 lr: 0.000039 grad: 0.0733 (0.0733) loss: 0.8814 (0.8814) time: 4.6981 data: 4.5731 max mem: 8299 +Train: [64] [ 100/6250] eta: 0:17:42 lr: 0.000039 grad: 0.0894 (0.1028) loss: 0.8769 (0.8791) time: 0.1124 data: 0.0252 max mem: 8299 +Train: [64] [ 200/6250] eta: 0:14:34 lr: 0.000039 grad: 0.0952 (0.0985) loss: 0.8628 (0.8721) time: 0.1227 data: 0.0388 max mem: 8299 +Train: [64] [ 300/6250] eta: 0:13:34 lr: 0.000039 grad: 0.0921 (0.0972) loss: 0.8606 (0.8683) time: 0.1146 data: 0.0395 max mem: 8299 +Train: [64] [ 400/6250] eta: 0:12:53 lr: 0.000039 grad: 0.0826 (0.0946) loss: 0.8655 (0.8674) time: 0.1212 data: 0.0450 max mem: 8299 +Train: [64] [ 500/6250] eta: 0:12:18 lr: 0.000039 grad: 0.0844 (0.0932) loss: 0.8642 (0.8666) time: 0.1115 data: 0.0304 max mem: 8299 +Train: [64] [ 600/6250] eta: 0:11:49 lr: 0.000039 grad: 0.0858 (0.0924) loss: 0.8589 (0.8662) time: 0.1256 data: 0.0514 max mem: 8299 +Train: [64] [ 700/6250] eta: 0:11:33 lr: 0.000039 grad: 0.0861 (0.0918) loss: 0.8639 (0.8658) time: 0.1230 data: 0.0451 max mem: 8299 +Train: [64] [ 800/6250] eta: 0:11:16 lr: 0.000039 grad: 0.0850 (0.0914) loss: 0.8657 (0.8654) time: 0.1389 data: 0.0685 max mem: 8299 +Train: [64] [ 900/6250] eta: 0:11:04 lr: 0.000039 grad: 0.0834 (0.0911) loss: 0.8631 (0.8652) time: 0.1366 data: 0.0595 max mem: 8299 +Train: [64] [1000/6250] eta: 0:10:42 lr: 0.000039 grad: 0.0803 (0.0908) loss: 0.8721 (0.8652) time: 0.1114 data: 0.0331 max mem: 8299 +Train: [64] [1100/6250] eta: 0:10:27 lr: 0.000039 grad: 0.0873 (0.0910) loss: 0.8654 (0.8648) time: 0.1317 data: 0.0477 max mem: 8299 +Train: [64] [1200/6250] eta: 0:10:10 lr: 0.000039 grad: 0.0928 (0.0907) loss: 0.8596 (0.8648) time: 0.1069 data: 0.0275 max mem: 8299 +Train: [64] [1300/6250] eta: 0:09:55 lr: 0.000039 grad: 0.0859 (0.0906) loss: 0.8649 (0.8646) time: 0.1230 data: 0.0483 max mem: 8299 +Train: [64] [1400/6250] eta: 0:09:39 lr: 0.000039 grad: 0.0946 (0.0907) loss: 0.8625 (0.8644) time: 0.1023 data: 0.0242 max mem: 8299 +Train: [64] [1500/6250] eta: 0:09:25 lr: 0.000039 grad: 0.0864 (0.0907) loss: 0.8709 (0.8642) time: 0.1097 data: 0.0359 max mem: 8299 +Train: [64] [1600/6250] eta: 0:09:11 lr: 0.000039 grad: 0.0928 (0.0909) loss: 0.8621 (0.8639) time: 0.1082 data: 0.0388 max mem: 8299 +Train: [64] [1700/6250] eta: 0:08:57 lr: 0.000039 grad: 0.0888 (0.0911) loss: 0.8612 (0.8638) time: 0.0809 data: 0.0029 max mem: 8299 +Train: [64] [1800/6250] eta: 0:08:44 lr: 0.000039 grad: 0.0899 (0.0912) loss: 0.8631 (0.8637) time: 0.1134 data: 0.0452 max mem: 8299 +Train: [64] [1900/6250] eta: 0:08:31 lr: 0.000039 grad: 0.0913 (0.0913) loss: 0.8600 (0.8636) time: 0.1199 data: 0.0541 max mem: 8299 +Train: [64] [2000/6250] eta: 0:08:17 lr: 0.000039 grad: 0.0886 (0.0915) loss: 0.8624 (0.8635) time: 0.1063 data: 0.0274 max mem: 8299 +Train: [64] [2100/6250] eta: 0:08:04 lr: 0.000039 grad: 0.0944 (0.0916) loss: 0.8688 (0.8635) time: 0.1120 data: 0.0402 max mem: 8299 +Train: [64] [2200/6250] eta: 0:07:52 lr: 0.000039 grad: 0.0933 (0.0918) loss: 0.8635 (0.8635) time: 0.1235 data: 0.0543 max mem: 8299 +Train: [64] [2300/6250] eta: 0:07:39 lr: 0.000039 grad: 0.0912 (0.0921) loss: 0.8679 (0.8635) time: 0.1137 data: 0.0355 max mem: 8299 +Train: [64] [2400/6250] eta: 0:07:27 lr: 0.000039 grad: 0.0899 (0.0921) loss: 0.8644 (0.8635) time: 0.0960 data: 0.0148 max mem: 8299 +Train: [64] [2500/6250] eta: 0:07:15 lr: 0.000039 grad: 0.0905 (0.0923) loss: 0.8672 (0.8635) time: 0.1076 data: 0.0361 max mem: 8299 +Train: [64] [2600/6250] eta: 0:07:03 lr: 0.000039 grad: 0.0966 (0.0924) loss: 0.8650 (0.8635) time: 0.0816 data: 0.0024 max mem: 8299 +Train: [64] [2700/6250] eta: 0:06:51 lr: 0.000038 grad: 0.0935 (0.0928) loss: 0.8682 (0.8635) time: 0.1122 data: 0.0393 max mem: 8299 +Train: [64] [2800/6250] eta: 0:06:39 lr: 0.000038 grad: 0.0956 (0.0929) loss: 0.8617 (0.8635) time: 0.1179 data: 0.0463 max mem: 8299 +Train: [64] [2900/6250] eta: 0:06:28 lr: 0.000038 grad: 0.0913 (0.0931) loss: 0.8646 (0.8635) time: 0.1218 data: 0.0472 max mem: 8299 +Train: [64] [3000/6250] eta: 0:06:16 lr: 0.000038 grad: 0.0901 (0.0933) loss: 0.8698 (0.8636) time: 0.1267 data: 0.0550 max mem: 8299 +Train: [64] [3100/6250] eta: 0:06:04 lr: 0.000038 grad: 0.1036 (0.0935) loss: 0.8583 (0.8636) time: 0.1139 data: 0.0382 max mem: 8299 +Train: [64] [3200/6250] eta: 0:05:52 lr: 0.000038 grad: 0.0973 (0.0939) loss: 0.8549 (0.8635) time: 0.1016 data: 0.0315 max mem: 8299 +Train: [64] [3300/6250] eta: 0:05:41 lr: 0.000038 grad: 0.1035 (0.0942) loss: 0.8663 (0.8634) time: 0.1114 data: 0.0413 max mem: 8299 +Train: [64] [3400/6250] eta: 0:05:30 lr: 0.000038 grad: 0.0990 (0.0945) loss: 0.8645 (0.8633) time: 0.1294 data: 0.0642 max mem: 8299 +Train: [64] [3500/6250] eta: 0:05:18 lr: 0.000038 grad: 0.0962 (0.0948) loss: 0.8635 (0.8632) time: 0.1216 data: 0.0509 max mem: 8299 +Train: [64] [3600/6250] eta: 0:05:06 lr: 0.000038 grad: 0.1026 (0.0951) loss: 0.8584 (0.8631) time: 0.1190 data: 0.0527 max mem: 8299 +Train: [64] [3700/6250] eta: 0:04:55 lr: 0.000038 grad: 0.1028 (0.0953) loss: 0.8592 (0.8631) time: 0.1002 data: 0.0357 max mem: 8299 +Train: [64] [3800/6250] eta: 0:04:43 lr: 0.000038 grad: 0.0956 (0.0955) loss: 0.8649 (0.8630) time: 0.1009 data: 0.0236 max mem: 8299 +Train: [64] [3900/6250] eta: 0:04:32 lr: 0.000038 grad: 0.0991 (0.0957) loss: 0.8601 (0.8630) time: 0.1128 data: 0.0410 max mem: 8299 +Train: [64] [4000/6250] eta: 0:04:20 lr: 0.000038 grad: 0.0992 (0.0958) loss: 0.8534 (0.8629) time: 0.1311 data: 0.0572 max mem: 8299 +Train: [64] [4100/6250] eta: 0:04:09 lr: 0.000038 grad: 0.0955 (0.0961) loss: 0.8662 (0.8628) time: 0.1494 data: 0.0773 max mem: 8299 +Train: [64] [4200/6250] eta: 0:03:57 lr: 0.000038 grad: 0.1010 (0.0963) loss: 0.8601 (0.8627) time: 0.0956 data: 0.0241 max mem: 8299 +Train: [64] [4300/6250] eta: 0:03:45 lr: 0.000038 grad: 0.0954 (0.0965) loss: 0.8661 (0.8627) time: 0.1191 data: 0.0531 max mem: 8299 +Train: [64] [4400/6250] eta: 0:03:34 lr: 0.000038 grad: 0.1018 (0.0967) loss: 0.8560 (0.8626) time: 0.0975 data: 0.0237 max mem: 8299 +Train: [64] [4500/6250] eta: 0:03:22 lr: 0.000038 grad: 0.1022 (0.0968) loss: 0.8638 (0.8625) time: 0.1167 data: 0.0379 max mem: 8299 +Train: [64] [4600/6250] eta: 0:03:11 lr: 0.000038 grad: 0.0965 (0.0970) loss: 0.8583 (0.8625) time: 0.1181 data: 0.0388 max mem: 8299 +Train: [64] [4700/6250] eta: 0:02:59 lr: 0.000038 grad: 0.0952 (0.0970) loss: 0.8647 (0.8624) time: 0.1169 data: 0.0397 max mem: 8299 +Train: [64] [4800/6250] eta: 0:02:48 lr: 0.000038 grad: 0.0965 (0.0971) loss: 0.8608 (0.8623) time: 0.1144 data: 0.0417 max mem: 8299 +Train: [64] [4900/6250] eta: 0:02:36 lr: 0.000038 grad: 0.1010 (0.0973) loss: 0.8632 (0.8622) time: 0.1345 data: 0.0606 max mem: 8299 +Train: [64] [5000/6250] eta: 0:02:25 lr: 0.000038 grad: 0.1012 (0.0974) loss: 0.8572 (0.8622) time: 0.1330 data: 0.0599 max mem: 8299 +Train: [64] [5100/6250] eta: 0:02:14 lr: 0.000038 grad: 0.0946 (0.0975) loss: 0.8636 (0.8622) time: 0.1274 data: 0.0583 max mem: 8299 +Train: [64] [5200/6250] eta: 0:02:02 lr: 0.000038 grad: 0.1064 (0.0976) loss: 0.8568 (0.8621) time: 0.1250 data: 0.0544 max mem: 8299 +Train: [64] [5300/6250] eta: 0:01:51 lr: 0.000038 grad: 0.0950 (0.0976) loss: 0.8607 (0.8622) time: 0.1392 data: 0.0701 max mem: 8299 +Train: [64] [5400/6250] eta: 0:01:39 lr: 0.000038 grad: 0.0898 (0.0976) loss: 0.8654 (0.8622) time: 0.1237 data: 0.0474 max mem: 8299 +Train: [64] [5500/6250] eta: 0:01:27 lr: 0.000038 grad: 0.0917 (0.0976) loss: 0.8693 (0.8623) time: 0.1065 data: 0.0364 max mem: 8299 +Train: [64] [5600/6250] eta: 0:01:16 lr: 0.000038 grad: 0.0927 (0.0976) loss: 0.8724 (0.8624) time: 0.1067 data: 0.0320 max mem: 8299 +Train: [64] [5700/6250] eta: 0:01:04 lr: 0.000038 grad: 0.0981 (0.0976) loss: 0.8624 (0.8624) time: 0.1109 data: 0.0374 max mem: 8299 +Train: [64] [5800/6250] eta: 0:00:52 lr: 0.000038 grad: 0.0961 (0.0976) loss: 0.8622 (0.8624) time: 0.1087 data: 0.0353 max mem: 8299 +Train: [64] [5900/6250] eta: 0:00:40 lr: 0.000037 grad: 0.0960 (0.0976) loss: 0.8646 (0.8625) time: 0.0846 data: 0.0036 max mem: 8299 +Train: [64] [6000/6250] eta: 0:00:29 lr: 0.000037 grad: 0.0876 (0.0976) loss: 0.8693 (0.8625) time: 0.1157 data: 0.0503 max mem: 8299 +Train: [64] [6100/6250] eta: 0:00:17 lr: 0.000037 grad: 0.0900 (0.0977) loss: 0.8593 (0.8626) time: 0.1125 data: 0.0381 max mem: 8299 +Train: [64] [6200/6250] eta: 0:00:05 lr: 0.000037 grad: 0.0893 (0.0977) loss: 0.8664 (0.8626) time: 0.0950 data: 0.0124 max mem: 8299 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1032 (0.0977) loss: 0.8606 (0.8626) time: 0.1086 data: 0.0349 max mem: 8299 +Train: [64] Total time: 0:12:10 (0.1168 s / it) +Averaged stats: lr: 0.000037 grad: 0.1032 (0.0977) loss: 0.8606 (0.8626) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:03:50 loss: 0.8903 (0.8903) time: 3.7188 data: 3.6473 max mem: 8299 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8792 (0.8800) time: 0.1258 data: 0.1014 max mem: 8299 +Eval (hcp-train-subset): [64] Total time: 0:00:12 (0.1973 s / it) +Averaged stats (hcp-train-subset): loss: 0.8792 (0.8800) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [64] [ 0/62] eta: 0:04:30 loss: 0.8817 (0.8817) time: 4.3650 data: 4.3354 max mem: 8299 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8787 (0.8801) time: 0.1196 data: 0.0943 max mem: 8299 +Eval (hcp-val): [64] Total time: 0:00:11 (0.1907 s / it) +Averaged stats (hcp-val): loss: 0.8787 (0.8801) +Making plots (hcp-val): example=43 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 7:45:34 lr: 0.000037 grad: 0.0552 (0.0552) loss: 0.9037 (0.9037) time: 4.4695 data: 4.3256 max mem: 8299 +Train: [65] [ 100/6250] eta: 0:16:51 lr: 0.000037 grad: 0.0969 (0.1041) loss: 0.8622 (0.8737) time: 0.1155 data: 0.0297 max mem: 8299 +Train: [65] [ 200/6250] eta: 0:14:06 lr: 0.000037 grad: 0.0991 (0.1066) loss: 0.8626 (0.8686) time: 0.1025 data: 0.0221 max mem: 8299 +Train: [65] [ 300/6250] eta: 0:13:11 lr: 0.000037 grad: 0.0929 (0.1054) loss: 0.8579 (0.8673) time: 0.1301 data: 0.0511 max mem: 8299 +Train: [65] [ 400/6250] eta: 0:12:35 lr: 0.000037 grad: 0.0909 (0.1049) loss: 0.8621 (0.8651) time: 0.1197 data: 0.0439 max mem: 8299 +Train: [65] [ 500/6250] eta: 0:12:02 lr: 0.000037 grad: 0.0898 (0.1040) loss: 0.8623 (0.8641) time: 0.1104 data: 0.0347 max mem: 8299 +Train: [65] [ 600/6250] eta: 0:11:34 lr: 0.000037 grad: 0.0946 (0.1026) loss: 0.8622 (0.8637) time: 0.1040 data: 0.0246 max mem: 8299 +Train: [65] [ 700/6250] eta: 0:11:12 lr: 0.000037 grad: 0.1042 (0.1018) loss: 0.8610 (0.8639) time: 0.1124 data: 0.0376 max mem: 8299 +Train: [65] [ 800/6250] eta: 0:10:49 lr: 0.000037 grad: 0.0966 (0.1007) loss: 0.8598 (0.8640) time: 0.0996 data: 0.0141 max mem: 8299 +Train: [65] [ 900/6250] eta: 0:10:28 lr: 0.000037 grad: 0.0892 (0.1000) loss: 0.8615 (0.8639) time: 0.1045 data: 0.0310 max mem: 8299 +Train: [65] [1000/6250] eta: 0:10:09 lr: 0.000037 grad: 0.0939 (0.0995) loss: 0.8642 (0.8639) time: 0.1076 data: 0.0400 max mem: 8299 +Train: [65] [1100/6250] eta: 0:09:54 lr: 0.000037 grad: 0.0982 (0.0992) loss: 0.8599 (0.8637) time: 0.1112 data: 0.0386 max mem: 8299 +Train: [65] [1200/6250] eta: 0:09:38 lr: 0.000037 grad: 0.0941 (0.0989) loss: 0.8539 (0.8634) time: 0.1079 data: 0.0339 max mem: 8299 +Train: [65] [1300/6250] eta: 0:09:22 lr: 0.000037 grad: 0.0929 (0.0987) loss: 0.8576 (0.8633) time: 0.0970 data: 0.0111 max mem: 8299 +Train: [65] [1400/6250] eta: 0:09:07 lr: 0.000037 grad: 0.0872 (0.0985) loss: 0.8630 (0.8633) time: 0.0979 data: 0.0245 max mem: 8299 +Train: [65] [1500/6250] eta: 0:08:54 lr: 0.000037 grad: 0.0951 (0.0983) loss: 0.8634 (0.8631) time: 0.1118 data: 0.0379 max mem: 8299 +Train: [65] [1600/6250] eta: 0:08:40 lr: 0.000037 grad: 0.0961 (0.0984) loss: 0.8689 (0.8630) time: 0.1018 data: 0.0287 max mem: 8299 +Train: [65] [1700/6250] eta: 0:08:27 lr: 0.000037 grad: 0.0979 (0.0984) loss: 0.8606 (0.8627) time: 0.1035 data: 0.0337 max mem: 8299 +Train: [65] [1800/6250] eta: 0:08:14 lr: 0.000037 grad: 0.0969 (0.0984) loss: 0.8642 (0.8626) time: 0.0869 data: 0.0117 max mem: 8299 +Train: [65] [1900/6250] eta: 0:08:02 lr: 0.000037 grad: 0.0913 (0.0984) loss: 0.8634 (0.8625) time: 0.1059 data: 0.0287 max mem: 8299 +Train: [65] [2000/6250] eta: 0:07:49 lr: 0.000037 grad: 0.0925 (0.0983) loss: 0.8577 (0.8624) time: 0.1087 data: 0.0290 max mem: 8299 +Train: [65] [2100/6250] eta: 0:07:37 lr: 0.000037 grad: 0.1006 (0.0984) loss: 0.8569 (0.8624) time: 0.1093 data: 0.0403 max mem: 8299 +Train: [65] [2200/6250] eta: 0:07:25 lr: 0.000037 grad: 0.1053 (0.0983) loss: 0.8598 (0.8624) time: 0.1043 data: 0.0264 max mem: 8299 +Train: [65] [2300/6250] eta: 0:07:15 lr: 0.000037 grad: 0.1001 (0.0983) loss: 0.8595 (0.8624) time: 0.1270 data: 0.0590 max mem: 8299 +Train: [65] [2400/6250] eta: 0:07:02 lr: 0.000037 grad: 0.0936 (0.0983) loss: 0.8581 (0.8622) time: 0.0986 data: 0.0174 max mem: 8299 +Train: [65] [2500/6250] eta: 0:06:51 lr: 0.000037 grad: 0.0961 (0.0982) loss: 0.8587 (0.8621) time: 0.1149 data: 0.0404 max mem: 8299 +Train: [65] [2600/6250] eta: 0:06:40 lr: 0.000037 grad: 0.0918 (0.0982) loss: 0.8658 (0.8620) time: 0.1034 data: 0.0278 max mem: 8299 +Train: [65] [2700/6250] eta: 0:06:29 lr: 0.000037 grad: 0.0968 (0.0981) loss: 0.8615 (0.8620) time: 0.1068 data: 0.0313 max mem: 8299 +Train: [65] [2800/6250] eta: 0:06:18 lr: 0.000037 grad: 0.0952 (0.0981) loss: 0.8534 (0.8619) time: 0.1057 data: 0.0326 max mem: 8299 +Train: [65] [2900/6250] eta: 0:06:07 lr: 0.000037 grad: 0.0944 (0.0980) loss: 0.8553 (0.8618) time: 0.1058 data: 0.0349 max mem: 8299 +Train: [65] [3000/6250] eta: 0:05:56 lr: 0.000036 grad: 0.1001 (0.0981) loss: 0.8534 (0.8616) time: 0.1285 data: 0.0559 max mem: 8299 +Train: [65] [3100/6250] eta: 0:05:45 lr: 0.000036 grad: 0.0962 (0.0982) loss: 0.8646 (0.8615) time: 0.1081 data: 0.0396 max mem: 8299 +Train: [65] [3200/6250] eta: 0:05:34 lr: 0.000036 grad: 0.1014 (0.0983) loss: 0.8475 (0.8612) time: 0.1079 data: 0.0201 max mem: 8299 +Train: [65] [3300/6250] eta: 0:05:23 lr: 0.000036 grad: 0.1005 (0.0984) loss: 0.8629 (0.8611) time: 0.1166 data: 0.0473 max mem: 8299 +Train: [65] [3400/6250] eta: 0:05:12 lr: 0.000036 grad: 0.0986 (0.0986) loss: 0.8664 (0.8610) time: 0.1048 data: 0.0344 max mem: 8299 +Train: [65] [3500/6250] eta: 0:05:01 lr: 0.000036 grad: 0.0957 (0.0987) loss: 0.8614 (0.8609) time: 0.1145 data: 0.0437 max mem: 8299 +Train: [65] [3600/6250] eta: 0:04:50 lr: 0.000036 grad: 0.0936 (0.0987) loss: 0.8665 (0.8609) time: 0.1117 data: 0.0405 max mem: 8299 +Train: [65] [3700/6250] eta: 0:04:40 lr: 0.000036 grad: 0.1013 (0.0989) loss: 0.8526 (0.8608) time: 0.1185 data: 0.0512 max mem: 8299 +Train: [65] [3800/6250] eta: 0:04:29 lr: 0.000036 grad: 0.0982 (0.0990) loss: 0.8596 (0.8608) time: 0.1032 data: 0.0304 max mem: 8299 +Train: [65] [3900/6250] eta: 0:04:18 lr: 0.000036 grad: 0.1016 (0.0991) loss: 0.8724 (0.8608) time: 0.1150 data: 0.0513 max mem: 8299 +Train: [65] [4000/6250] eta: 0:04:07 lr: 0.000036 grad: 0.0949 (0.0992) loss: 0.8652 (0.8608) time: 0.1135 data: 0.0404 max mem: 8299 +Train: [65] [4100/6250] eta: 0:03:56 lr: 0.000036 grad: 0.1017 (0.0993) loss: 0.8600 (0.8608) time: 0.1080 data: 0.0251 max mem: 8299 +Train: [65] [4200/6250] eta: 0:03:45 lr: 0.000036 grad: 0.0974 (0.0995) loss: 0.8570 (0.8608) time: 0.0897 data: 0.0207 max mem: 8299 +Train: [65] [4300/6250] eta: 0:03:33 lr: 0.000036 grad: 0.0925 (0.0996) loss: 0.8658 (0.8609) time: 0.1221 data: 0.0492 max mem: 8299 +Train: [65] [4400/6250] eta: 0:03:23 lr: 0.000036 grad: 0.0951 (0.0996) loss: 0.8679 (0.8608) time: 0.1112 data: 0.0381 max mem: 8299 +Train: [65] [4500/6250] eta: 0:03:12 lr: 0.000036 grad: 0.0968 (0.0997) loss: 0.8600 (0.8609) time: 0.1184 data: 0.0544 max mem: 8299 +Train: [65] [4600/6250] eta: 0:03:01 lr: 0.000036 grad: 0.1020 (0.0997) loss: 0.8629 (0.8609) time: 0.1140 data: 0.0396 max mem: 8299 +Train: [65] [4700/6250] eta: 0:02:50 lr: 0.000036 grad: 0.0987 (0.0998) loss: 0.8589 (0.8609) time: 0.1292 data: 0.0602 max mem: 8299 +Train: [65] [4800/6250] eta: 0:02:39 lr: 0.000036 grad: 0.0975 (0.0999) loss: 0.8618 (0.8608) time: 0.1200 data: 0.0492 max mem: 8299 +Train: [65] [4900/6250] eta: 0:02:28 lr: 0.000036 grad: 0.0937 (0.0999) loss: 0.8631 (0.8609) time: 0.1057 data: 0.0348 max mem: 8299 +Train: [65] [5000/6250] eta: 0:02:17 lr: 0.000036 grad: 0.0928 (0.1001) loss: 0.8595 (0.8608) time: 0.1461 data: 0.0857 max mem: 8299 +Train: [65] [5100/6250] eta: 0:02:06 lr: 0.000036 grad: 0.0983 (0.1002) loss: 0.8558 (0.8608) time: 0.1189 data: 0.0563 max mem: 8299 +Train: [65] [5200/6250] eta: 0:01:56 lr: 0.000036 grad: 0.0967 (0.1003) loss: 0.8636 (0.8609) time: 0.1316 data: 0.0572 max mem: 8299 +Train: [65] [5300/6250] eta: 0:01:45 lr: 0.000036 grad: 0.0982 (0.1003) loss: 0.8617 (0.8609) time: 0.1328 data: 0.0580 max mem: 8299 +Train: [65] [5400/6250] eta: 0:01:34 lr: 0.000036 grad: 0.0975 (0.1002) loss: 0.8663 (0.8609) time: 0.1337 data: 0.0628 max mem: 8299 +Train: [65] [5500/6250] eta: 0:01:23 lr: 0.000036 grad: 0.1064 (0.1002) loss: 0.8549 (0.8609) time: 0.0967 data: 0.0213 max mem: 8299 +Train: [65] [5600/6250] eta: 0:01:12 lr: 0.000036 grad: 0.0962 (0.1003) loss: 0.8619 (0.8609) time: 0.1115 data: 0.0425 max mem: 8299 +Train: [65] [5700/6250] eta: 0:01:01 lr: 0.000036 grad: 0.1029 (0.1003) loss: 0.8605 (0.8609) time: 0.1233 data: 0.0509 max mem: 8299 +Train: [65] [5800/6250] eta: 0:00:50 lr: 0.000036 grad: 0.0998 (0.1004) loss: 0.8577 (0.8609) time: 0.1075 data: 0.0377 max mem: 8299 +Train: [65] [5900/6250] eta: 0:00:38 lr: 0.000036 grad: 0.1028 (0.1005) loss: 0.8585 (0.8608) time: 0.0730 data: 0.0002 max mem: 8299 +Train: [65] [6000/6250] eta: 0:00:27 lr: 0.000036 grad: 0.0973 (0.1005) loss: 0.8638 (0.8608) time: 0.1134 data: 0.0375 max mem: 8299 +Train: [65] [6100/6250] eta: 0:00:16 lr: 0.000036 grad: 0.0983 (0.1006) loss: 0.8613 (0.8608) time: 0.0961 data: 0.0201 max mem: 8299 +Train: [65] [6200/6250] eta: 0:00:05 lr: 0.000036 grad: 0.0906 (0.1006) loss: 0.8618 (0.8608) time: 0.1181 data: 0.0378 max mem: 8299 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1031 (0.1006) loss: 0.8557 (0.8608) time: 0.1342 data: 0.0597 max mem: 8299 +Train: [65] Total time: 0:11:37 (0.1117 s / it) +Averaged stats: lr: 0.000036 grad: 0.1031 (0.1006) loss: 0.8557 (0.8608) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:04:57 loss: 0.8925 (0.8925) time: 4.7933 data: 4.7647 max mem: 8299 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8832 (0.8816) time: 0.1153 data: 0.0901 max mem: 8299 +Eval (hcp-train-subset): [65] Total time: 0:00:11 (0.1812 s / it) +Averaged stats (hcp-train-subset): loss: 0.8832 (0.8816) +Eval (hcp-val): [65] [ 0/62] eta: 0:03:17 loss: 0.8822 (0.8822) time: 3.1871 data: 3.1089 max mem: 8299 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8808 (0.8828) time: 0.0876 data: 0.0637 max mem: 8299 +Eval (hcp-val): [65] Total time: 0:00:11 (0.1840 s / it) +Averaged stats (hcp-val): loss: 0.8808 (0.8828) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 6:20:37 lr: 0.000036 grad: 0.0698 (0.0698) loss: 0.9105 (0.9105) time: 3.6541 data: 3.4528 max mem: 8299 +Train: [66] [ 100/6250] eta: 0:17:13 lr: 0.000035 grad: 0.0891 (0.1189) loss: 0.8580 (0.8703) time: 0.1169 data: 0.0302 max mem: 8299 +Train: [66] [ 200/6250] eta: 0:14:44 lr: 0.000035 grad: 0.0938 (0.1141) loss: 0.8606 (0.8641) time: 0.1127 data: 0.0259 max mem: 8299 +Train: [66] [ 300/6250] eta: 0:13:37 lr: 0.000035 grad: 0.0858 (0.1084) loss: 0.8684 (0.8632) time: 0.1089 data: 0.0246 max mem: 8299 +Train: [66] [ 400/6250] eta: 0:12:54 lr: 0.000035 grad: 0.0903 (0.1071) loss: 0.8639 (0.8630) time: 0.1150 data: 0.0372 max mem: 8299 +Train: [66] [ 500/6250] eta: 0:12:09 lr: 0.000035 grad: 0.0893 (0.1057) loss: 0.8696 (0.8625) time: 0.1055 data: 0.0264 max mem: 8299 +Train: [66] [ 600/6250] eta: 0:11:41 lr: 0.000035 grad: 0.0967 (0.1049) loss: 0.8547 (0.8621) time: 0.1170 data: 0.0387 max mem: 8299 +Train: [66] [ 700/6250] eta: 0:11:16 lr: 0.000035 grad: 0.0874 (0.1038) loss: 0.8661 (0.8618) time: 0.1149 data: 0.0401 max mem: 8299 +Train: [66] [ 800/6250] eta: 0:11:09 lr: 0.000035 grad: 0.0855 (0.1022) loss: 0.8712 (0.8620) time: 0.1369 data: 0.0677 max mem: 8299 +Train: [66] [ 900/6250] eta: 0:10:59 lr: 0.000035 grad: 0.0861 (0.1016) loss: 0.8670 (0.8621) time: 0.1183 data: 0.0382 max mem: 8299 +Train: [66] [1000/6250] eta: 0:10:51 lr: 0.000035 grad: 0.0961 (0.1012) loss: 0.8661 (0.8622) time: 0.1136 data: 0.0413 max mem: 8299 +Train: [66] [1100/6250] eta: 0:10:44 lr: 0.000035 grad: 0.1027 (0.1010) loss: 0.8579 (0.8623) time: 0.1360 data: 0.0708 max mem: 8299 +Train: [66] [1200/6250] eta: 0:10:35 lr: 0.000035 grad: 0.0979 (0.1008) loss: 0.8615 (0.8622) time: 0.1234 data: 0.0542 max mem: 8299 +Train: [66] [1300/6250] eta: 0:10:21 lr: 0.000035 grad: 0.0997 (0.1007) loss: 0.8643 (0.8621) time: 0.1233 data: 0.0517 max mem: 8299 +Train: [66] [1400/6250] eta: 0:10:10 lr: 0.000035 grad: 0.0947 (0.1006) loss: 0.8599 (0.8620) time: 0.1414 data: 0.0743 max mem: 8299 +Train: [66] [1500/6250] eta: 0:09:57 lr: 0.000035 grad: 0.0990 (0.1003) loss: 0.8572 (0.8620) time: 0.1213 data: 0.0477 max mem: 8299 +Train: [66] [1600/6250] eta: 0:09:43 lr: 0.000035 grad: 0.0957 (0.1002) loss: 0.8697 (0.8620) time: 0.0916 data: 0.0162 max mem: 8299 +Train: [66] [1700/6250] eta: 0:09:30 lr: 0.000035 grad: 0.0928 (0.1001) loss: 0.8643 (0.8620) time: 0.1160 data: 0.0519 max mem: 8299 +Train: [66] [1800/6250] eta: 0:09:19 lr: 0.000035 grad: 0.0988 (0.1001) loss: 0.8559 (0.8619) time: 0.1214 data: 0.0496 max mem: 8299 +Train: [66] [1900/6250] eta: 0:09:04 lr: 0.000035 grad: 0.0934 (0.1002) loss: 0.8602 (0.8618) time: 0.1167 data: 0.0465 max mem: 8299 +Train: [66] [2000/6250] eta: 0:08:50 lr: 0.000035 grad: 0.0961 (0.1002) loss: 0.8624 (0.8617) time: 0.1123 data: 0.0402 max mem: 8299 +Train: [66] [2100/6250] eta: 0:08:38 lr: 0.000035 grad: 0.0995 (0.1003) loss: 0.8648 (0.8616) time: 0.1278 data: 0.0559 max mem: 8299 +Train: [66] [2200/6250] eta: 0:08:25 lr: 0.000035 grad: 0.0999 (0.1003) loss: 0.8557 (0.8615) time: 0.1312 data: 0.0631 max mem: 8299 +Train: [66] [2300/6250] eta: 0:08:10 lr: 0.000035 grad: 0.0884 (0.1002) loss: 0.8702 (0.8615) time: 0.1033 data: 0.0330 max mem: 8299 +Train: [66] [2400/6250] eta: 0:07:57 lr: 0.000035 grad: 0.1013 (0.1002) loss: 0.8593 (0.8614) time: 0.1234 data: 0.0511 max mem: 8299 +Train: [66] [2500/6250] eta: 0:07:44 lr: 0.000035 grad: 0.0898 (0.1001) loss: 0.8622 (0.8614) time: 0.1166 data: 0.0449 max mem: 8299 +Train: [66] [2600/6250] eta: 0:07:31 lr: 0.000035 grad: 0.0950 (0.1001) loss: 0.8589 (0.8614) time: 0.1062 data: 0.0296 max mem: 8299 +Train: [66] [2700/6250] eta: 0:07:17 lr: 0.000035 grad: 0.0975 (0.1001) loss: 0.8721 (0.8614) time: 0.1125 data: 0.0388 max mem: 8299 +Train: [66] [2800/6250] eta: 0:07:05 lr: 0.000035 grad: 0.0887 (0.1002) loss: 0.8633 (0.8613) time: 0.1119 data: 0.0411 max mem: 8299 +Train: [66] [2900/6250] eta: 0:06:52 lr: 0.000035 grad: 0.1033 (0.1003) loss: 0.8550 (0.8612) time: 0.1218 data: 0.0547 max mem: 8299 +Train: [66] [3000/6250] eta: 0:06:39 lr: 0.000035 grad: 0.1040 (0.1004) loss: 0.8586 (0.8611) time: 0.1297 data: 0.0583 max mem: 8299 +Train: [66] [3100/6250] eta: 0:06:27 lr: 0.000035 grad: 0.0980 (0.1005) loss: 0.8550 (0.8610) time: 0.1246 data: 0.0498 max mem: 8299 +Train: [66] [3200/6250] eta: 0:06:14 lr: 0.000035 grad: 0.0979 (0.1006) loss: 0.8559 (0.8609) time: 0.1304 data: 0.0629 max mem: 8299 +Train: [66] [3300/6250] eta: 0:06:02 lr: 0.000035 grad: 0.0963 (0.1006) loss: 0.8647 (0.8609) time: 0.1327 data: 0.0671 max mem: 8299 +Train: [66] [3400/6250] eta: 0:05:49 lr: 0.000035 grad: 0.1019 (0.1008) loss: 0.8564 (0.8608) time: 0.1231 data: 0.0559 max mem: 8299 +Train: [66] [3500/6250] eta: 0:05:37 lr: 0.000034 grad: 0.0897 (0.1008) loss: 0.8581 (0.8608) time: 0.0908 data: 0.0222 max mem: 8299 +Train: [66] [3600/6250] eta: 0:05:24 lr: 0.000034 grad: 0.0980 (0.1009) loss: 0.8597 (0.8607) time: 0.1120 data: 0.0454 max mem: 8299 +Train: [66] [3700/6250] eta: 0:05:12 lr: 0.000034 grad: 0.1031 (0.1009) loss: 0.8591 (0.8606) time: 0.1300 data: 0.0583 max mem: 8299 +Train: [66] [3800/6250] eta: 0:05:00 lr: 0.000034 grad: 0.1075 (0.1010) loss: 0.8522 (0.8606) time: 0.1163 data: 0.0496 max mem: 8299 +Train: [66] [3900/6250] eta: 0:04:47 lr: 0.000034 grad: 0.1084 (0.1011) loss: 0.8583 (0.8604) time: 0.1055 data: 0.0330 max mem: 8299 +Train: [66] [4000/6250] eta: 0:04:35 lr: 0.000034 grad: 0.1137 (0.1013) loss: 0.8572 (0.8604) time: 0.0951 data: 0.0326 max mem: 8299 +Train: [66] [4100/6250] eta: 0:04:22 lr: 0.000034 grad: 0.0993 (0.1014) loss: 0.8563 (0.8603) time: 0.1146 data: 0.0416 max mem: 8299 +Train: [66] [4200/6250] eta: 0:04:10 lr: 0.000034 grad: 0.0993 (0.1017) loss: 0.8595 (0.8603) time: 0.1234 data: 0.0561 max mem: 8299 +Train: [66] [4300/6250] eta: 0:03:58 lr: 0.000034 grad: 0.1017 (0.1018) loss: 0.8646 (0.8602) time: 0.1099 data: 0.0395 max mem: 8299 +Train: [66] [4400/6250] eta: 0:03:45 lr: 0.000034 grad: 0.1067 (0.1019) loss: 0.8579 (0.8601) time: 0.1179 data: 0.0459 max mem: 8299 +Train: [66] [4500/6250] eta: 0:03:33 lr: 0.000034 grad: 0.1061 (0.1020) loss: 0.8612 (0.8601) time: 0.1126 data: 0.0443 max mem: 8299 +Train: [66] [4600/6250] eta: 0:03:20 lr: 0.000034 grad: 0.1135 (0.1022) loss: 0.8526 (0.8600) time: 0.1127 data: 0.0417 max mem: 8299 +Train: [66] [4700/6250] eta: 0:03:08 lr: 0.000034 grad: 0.1011 (0.1023) loss: 0.8588 (0.8599) time: 0.1146 data: 0.0403 max mem: 8299 +Train: [66] [4800/6250] eta: 0:02:56 lr: 0.000034 grad: 0.0989 (0.1024) loss: 0.8621 (0.8599) time: 0.1073 data: 0.0331 max mem: 8299 +Train: [66] [4900/6250] eta: 0:02:44 lr: 0.000034 grad: 0.1044 (0.1025) loss: 0.8605 (0.8599) time: 0.1430 data: 0.0687 max mem: 8299 +Train: [66] [5000/6250] eta: 0:02:32 lr: 0.000034 grad: 0.0933 (0.1026) loss: 0.8606 (0.8598) time: 0.1331 data: 0.0650 max mem: 8299 +Train: [66] [5100/6250] eta: 0:02:20 lr: 0.000034 grad: 0.0969 (0.1026) loss: 0.8584 (0.8598) time: 0.1339 data: 0.0617 max mem: 8299 +Train: [66] [5200/6250] eta: 0:02:08 lr: 0.000034 grad: 0.1050 (0.1026) loss: 0.8583 (0.8598) time: 0.1268 data: 0.0554 max mem: 8299 +Train: [66] [5300/6250] eta: 0:01:56 lr: 0.000034 grad: 0.0930 (0.1025) loss: 0.8606 (0.8598) time: 0.1189 data: 0.0513 max mem: 8299 +Train: [66] [5400/6250] eta: 0:01:43 lr: 0.000034 grad: 0.0893 (0.1024) loss: 0.8660 (0.8599) time: 0.1235 data: 0.0484 max mem: 8299 +Train: [66] [5500/6250] eta: 0:01:31 lr: 0.000034 grad: 0.1002 (0.1023) loss: 0.8630 (0.8600) time: 0.1188 data: 0.0547 max mem: 8299 +Train: [66] [5600/6250] eta: 0:01:19 lr: 0.000034 grad: 0.1054 (0.1023) loss: 0.8661 (0.8600) time: 0.1010 data: 0.0284 max mem: 8299 +Train: [66] [5700/6250] eta: 0:01:06 lr: 0.000034 grad: 0.0950 (0.1023) loss: 0.8663 (0.8601) time: 0.1253 data: 0.0525 max mem: 8299 +Train: [66] [5800/6250] eta: 0:00:54 lr: 0.000034 grad: 0.0956 (0.1022) loss: 0.8611 (0.8601) time: 0.1090 data: 0.0364 max mem: 8299 +Train: [66] [5900/6250] eta: 0:00:42 lr: 0.000034 grad: 0.0889 (0.1022) loss: 0.8615 (0.8601) time: 0.1120 data: 0.0383 max mem: 8299 +Train: [66] [6000/6250] eta: 0:00:30 lr: 0.000034 grad: 0.1005 (0.1022) loss: 0.8668 (0.8602) time: 0.1160 data: 0.0448 max mem: 8299 +Train: [66] [6100/6250] eta: 0:00:18 lr: 0.000034 grad: 0.0987 (0.1023) loss: 0.8675 (0.8602) time: 0.1025 data: 0.0329 max mem: 8299 +Train: [66] [6200/6250] eta: 0:00:06 lr: 0.000034 grad: 0.0990 (0.1023) loss: 0.8634 (0.8602) time: 0.1252 data: 0.0564 max mem: 8299 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.0961 (0.1022) loss: 0.8659 (0.8602) time: 0.1341 data: 0.0610 max mem: 8299 +Train: [66] Total time: 0:12:39 (0.1216 s / it) +Averaged stats: lr: 0.000034 grad: 0.0961 (0.1022) loss: 0.8659 (0.8602) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:03:18 loss: 0.8889 (0.8889) time: 3.1991 data: 3.1320 max mem: 8299 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8805 (0.8801) time: 0.1058 data: 0.0818 max mem: 8299 +Eval (hcp-train-subset): [66] Total time: 0:00:10 (0.1763 s / it) +Averaged stats (hcp-train-subset): loss: 0.8805 (0.8801) +Eval (hcp-val): [66] [ 0/62] eta: 0:03:59 loss: 0.8820 (0.8820) time: 3.8644 data: 3.8287 max mem: 8299 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8807 (0.8810) time: 0.1210 data: 0.0966 max mem: 8299 +Eval (hcp-val): [66] Total time: 0:00:11 (0.1921 s / it) +Averaged stats (hcp-val): loss: 0.8807 (0.8810) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 6:57:19 lr: 0.000034 grad: 0.0503 (0.0503) loss: 0.9105 (0.9105) time: 4.0064 data: 3.6979 max mem: 8299 +Train: [67] [ 100/6250] eta: 0:16:33 lr: 0.000034 grad: 0.0888 (0.1096) loss: 0.8764 (0.8770) time: 0.1287 data: 0.0437 max mem: 8299 +Train: [67] [ 200/6250] eta: 0:14:20 lr: 0.000034 grad: 0.0902 (0.1021) loss: 0.8703 (0.8734) time: 0.1265 data: 0.0481 max mem: 8299 +Train: [67] [ 300/6250] eta: 0:13:24 lr: 0.000034 grad: 0.0899 (0.1004) loss: 0.8702 (0.8720) time: 0.1098 data: 0.0333 max mem: 8299 +Train: [67] [ 400/6250] eta: 0:12:42 lr: 0.000034 grad: 0.0878 (0.0993) loss: 0.8761 (0.8721) time: 0.1181 data: 0.0516 max mem: 8299 +Train: [67] [ 500/6250] eta: 0:12:12 lr: 0.000034 grad: 0.0879 (0.0986) loss: 0.8676 (0.8719) time: 0.1261 data: 0.0502 max mem: 8299 +Train: [67] [ 600/6250] eta: 0:11:39 lr: 0.000033 grad: 0.1011 (0.0984) loss: 0.8637 (0.8713) time: 0.1027 data: 0.0201 max mem: 8299 +Train: [67] [ 700/6250] eta: 0:11:17 lr: 0.000033 grad: 0.0971 (0.0977) loss: 0.8649 (0.8708) time: 0.1266 data: 0.0480 max mem: 8299 +Train: [67] [ 800/6250] eta: 0:10:53 lr: 0.000033 grad: 0.0902 (0.0981) loss: 0.8560 (0.8696) time: 0.0970 data: 0.0123 max mem: 8299 +Train: [67] [ 900/6250] eta: 0:10:38 lr: 0.000033 grad: 0.0934 (0.0981) loss: 0.8528 (0.8687) time: 0.1222 data: 0.0461 max mem: 8299 +Train: [67] [1000/6250] eta: 0:10:29 lr: 0.000033 grad: 0.0888 (0.0980) loss: 0.8577 (0.8678) time: 0.0918 data: 0.0216 max mem: 8299 +Train: [67] [1100/6250] eta: 0:10:16 lr: 0.000033 grad: 0.0907 (0.0983) loss: 0.8620 (0.8672) time: 0.1026 data: 0.0244 max mem: 8299 +Train: [67] [1200/6250] eta: 0:10:04 lr: 0.000033 grad: 0.1022 (0.0986) loss: 0.8548 (0.8666) time: 0.1026 data: 0.0378 max mem: 8299 +Train: [67] [1300/6250] eta: 0:09:52 lr: 0.000033 grad: 0.0912 (0.0985) loss: 0.8634 (0.8662) time: 0.1046 data: 0.0324 max mem: 8299 +Train: [67] [1400/6250] eta: 0:09:39 lr: 0.000033 grad: 0.0932 (0.0987) loss: 0.8605 (0.8658) time: 0.0976 data: 0.0252 max mem: 8299 +Train: [67] [1500/6250] eta: 0:09:29 lr: 0.000033 grad: 0.0965 (0.0987) loss: 0.8510 (0.8653) time: 0.1193 data: 0.0429 max mem: 8299 +Train: [67] [1600/6250] eta: 0:09:16 lr: 0.000033 grad: 0.0905 (0.0988) loss: 0.8601 (0.8648) time: 0.1256 data: 0.0595 max mem: 8299 +Train: [67] [1700/6250] eta: 0:09:06 lr: 0.000033 grad: 0.0971 (0.0987) loss: 0.8629 (0.8644) time: 0.1529 data: 0.0817 max mem: 8299 +Train: [67] [1800/6250] eta: 0:08:51 lr: 0.000033 grad: 0.0933 (0.0985) loss: 0.8627 (0.8643) time: 0.1031 data: 0.0314 max mem: 8299 +Train: [67] [1900/6250] eta: 0:08:40 lr: 0.000033 grad: 0.0998 (0.0986) loss: 0.8548 (0.8640) time: 0.1208 data: 0.0509 max mem: 8299 +Train: [67] [2000/6250] eta: 0:08:27 lr: 0.000033 grad: 0.0965 (0.0985) loss: 0.8558 (0.8639) time: 0.1210 data: 0.0509 max mem: 8299 +Train: [67] [2100/6250] eta: 0:08:14 lr: 0.000033 grad: 0.0935 (0.0985) loss: 0.8686 (0.8639) time: 0.1230 data: 0.0487 max mem: 8299 +Train: [67] [2200/6250] eta: 0:08:02 lr: 0.000033 grad: 0.0954 (0.0985) loss: 0.8647 (0.8638) time: 0.1239 data: 0.0553 max mem: 8299 +Train: [67] [2300/6250] eta: 0:07:50 lr: 0.000033 grad: 0.1001 (0.0988) loss: 0.8591 (0.8636) time: 0.1206 data: 0.0467 max mem: 8299 +Train: [67] [2400/6250] eta: 0:07:38 lr: 0.000033 grad: 0.1007 (0.0989) loss: 0.8604 (0.8634) time: 0.1098 data: 0.0407 max mem: 8299 +Train: [67] [2500/6250] eta: 0:07:25 lr: 0.000033 grad: 0.1067 (0.0991) loss: 0.8629 (0.8632) time: 0.1086 data: 0.0356 max mem: 8299 +Train: [67] [2600/6250] eta: 0:07:13 lr: 0.000033 grad: 0.0965 (0.0992) loss: 0.8582 (0.8631) time: 0.1088 data: 0.0427 max mem: 8299 +Train: [67] [2700/6250] eta: 0:07:01 lr: 0.000033 grad: 0.1011 (0.0993) loss: 0.8580 (0.8629) time: 0.1272 data: 0.0568 max mem: 8299 +Train: [67] [2800/6250] eta: 0:06:50 lr: 0.000033 grad: 0.1029 (0.0994) loss: 0.8580 (0.8628) time: 0.1500 data: 0.0806 max mem: 8299 +Train: [67] [2900/6250] eta: 0:06:38 lr: 0.000033 grad: 0.0999 (0.0995) loss: 0.8598 (0.8627) time: 0.0952 data: 0.0213 max mem: 8299 +Train: [67] [3000/6250] eta: 0:06:25 lr: 0.000033 grad: 0.1011 (0.0996) loss: 0.8594 (0.8626) time: 0.1110 data: 0.0379 max mem: 8299 +Train: [67] [3100/6250] eta: 0:06:13 lr: 0.000033 grad: 0.0982 (0.0997) loss: 0.8639 (0.8625) time: 0.1038 data: 0.0401 max mem: 8299 +Train: [67] [3200/6250] eta: 0:06:01 lr: 0.000033 grad: 0.1023 (0.0998) loss: 0.8634 (0.8624) time: 0.1434 data: 0.0734 max mem: 8299 +Train: [67] [3300/6250] eta: 0:05:49 lr: 0.000033 grad: 0.0910 (0.0999) loss: 0.8611 (0.8622) time: 0.1185 data: 0.0519 max mem: 8299 +Train: [67] [3400/6250] eta: 0:05:37 lr: 0.000033 grad: 0.1011 (0.1000) loss: 0.8603 (0.8621) time: 0.1101 data: 0.0437 max mem: 8299 +Train: [67] [3500/6250] eta: 0:05:25 lr: 0.000033 grad: 0.1097 (0.1000) loss: 0.8650 (0.8621) time: 0.0824 data: 0.0062 max mem: 8299 +Train: [67] [3600/6250] eta: 0:05:14 lr: 0.000033 grad: 0.1047 (0.1001) loss: 0.8540 (0.8621) time: 0.1357 data: 0.0711 max mem: 8299 +Train: [67] [3700/6250] eta: 0:05:01 lr: 0.000033 grad: 0.1011 (0.1001) loss: 0.8700 (0.8620) time: 0.1236 data: 0.0369 max mem: 8299 +Train: [67] [3800/6250] eta: 0:04:50 lr: 0.000033 grad: 0.0980 (0.1002) loss: 0.8594 (0.8619) time: 0.1247 data: 0.0472 max mem: 8299 +Train: [67] [3900/6250] eta: 0:04:38 lr: 0.000033 grad: 0.0976 (0.1003) loss: 0.8614 (0.8619) time: 0.1274 data: 0.0635 max mem: 8299 +Train: [67] [4000/6250] eta: 0:04:26 lr: 0.000032 grad: 0.0937 (0.1003) loss: 0.8644 (0.8619) time: 0.1199 data: 0.0526 max mem: 8299 +Train: [67] [4100/6250] eta: 0:04:14 lr: 0.000032 grad: 0.0950 (0.1003) loss: 0.8578 (0.8619) time: 0.1147 data: 0.0450 max mem: 8299 +Train: [67] [4200/6250] eta: 0:04:02 lr: 0.000032 grad: 0.0977 (0.1003) loss: 0.8618 (0.8620) time: 0.1206 data: 0.0507 max mem: 8299 +Train: [67] [4300/6250] eta: 0:03:50 lr: 0.000032 grad: 0.0940 (0.1004) loss: 0.8623 (0.8620) time: 0.1121 data: 0.0392 max mem: 8299 +Train: [67] [4400/6250] eta: 0:03:38 lr: 0.000032 grad: 0.1006 (0.1005) loss: 0.8594 (0.8619) time: 0.1242 data: 0.0605 max mem: 8299 +Train: [67] [4500/6250] eta: 0:03:26 lr: 0.000032 grad: 0.0992 (0.1005) loss: 0.8635 (0.8620) time: 0.1142 data: 0.0399 max mem: 8299 +Train: [67] [4600/6250] eta: 0:03:14 lr: 0.000032 grad: 0.1040 (0.1006) loss: 0.8562 (0.8619) time: 0.1146 data: 0.0453 max mem: 8299 +Train: [67] [4700/6250] eta: 0:03:03 lr: 0.000032 grad: 0.1018 (0.1007) loss: 0.8584 (0.8619) time: 0.1188 data: 0.0426 max mem: 8299 +Train: [67] [4800/6250] eta: 0:02:51 lr: 0.000032 grad: 0.0996 (0.1008) loss: 0.8583 (0.8618) time: 0.1073 data: 0.0339 max mem: 8299 +Train: [67] [4900/6250] eta: 0:02:39 lr: 0.000032 grad: 0.0994 (0.1008) loss: 0.8575 (0.8617) time: 0.1147 data: 0.0441 max mem: 8299 +Train: [67] [5000/6250] eta: 0:02:27 lr: 0.000032 grad: 0.1048 (0.1009) loss: 0.8569 (0.8616) time: 0.1148 data: 0.0396 max mem: 8299 +Train: [67] [5100/6250] eta: 0:02:16 lr: 0.000032 grad: 0.0984 (0.1010) loss: 0.8584 (0.8615) time: 0.1310 data: 0.0569 max mem: 8299 +Train: [67] [5200/6250] eta: 0:02:04 lr: 0.000032 grad: 0.1113 (0.1010) loss: 0.8510 (0.8614) time: 0.1156 data: 0.0411 max mem: 8299 +Train: [67] [5300/6250] eta: 0:01:53 lr: 0.000032 grad: 0.0974 (0.1010) loss: 0.8707 (0.8614) time: 0.1364 data: 0.0654 max mem: 8299 +Train: [67] [5400/6250] eta: 0:01:41 lr: 0.000032 grad: 0.1041 (0.1011) loss: 0.8586 (0.8613) time: 0.1267 data: 0.0570 max mem: 8299 +Train: [67] [5500/6250] eta: 0:01:29 lr: 0.000032 grad: 0.1065 (0.1011) loss: 0.8553 (0.8613) time: 0.1260 data: 0.0562 max mem: 8299 +Train: [67] [5600/6250] eta: 0:01:17 lr: 0.000032 grad: 0.1041 (0.1011) loss: 0.8481 (0.8611) time: 0.1090 data: 0.0318 max mem: 8299 +Train: [67] [5700/6250] eta: 0:01:05 lr: 0.000032 grad: 0.1015 (0.1012) loss: 0.8557 (0.8610) time: 0.1032 data: 0.0188 max mem: 8299 +Train: [67] [5800/6250] eta: 0:00:53 lr: 0.000032 grad: 0.0999 (0.1013) loss: 0.8600 (0.8609) time: 0.1086 data: 0.0407 max mem: 8299 +Train: [67] [5900/6250] eta: 0:00:41 lr: 0.000032 grad: 0.0999 (0.1013) loss: 0.8592 (0.8609) time: 0.1013 data: 0.0191 max mem: 8299 +Train: [67] [6000/6250] eta: 0:00:29 lr: 0.000032 grad: 0.0994 (0.1014) loss: 0.8627 (0.8608) time: 0.1051 data: 0.0309 max mem: 8299 +Train: [67] [6100/6250] eta: 0:00:17 lr: 0.000032 grad: 0.1040 (0.1015) loss: 0.8571 (0.8607) time: 0.0965 data: 0.0150 max mem: 8299 +Train: [67] [6200/6250] eta: 0:00:05 lr: 0.000032 grad: 0.1075 (0.1015) loss: 0.8602 (0.8606) time: 0.1017 data: 0.0305 max mem: 8299 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1014 (0.1016) loss: 0.8584 (0.8606) time: 0.1184 data: 0.0471 max mem: 8299 +Train: [67] Total time: 0:12:20 (0.1185 s / it) +Averaged stats: lr: 0.000032 grad: 0.1014 (0.1016) loss: 0.8584 (0.8606) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:04:17 loss: 0.8857 (0.8857) time: 4.1487 data: 4.1182 max mem: 8299 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8791 (0.8807) time: 0.1250 data: 0.0993 max mem: 8299 +Eval (hcp-train-subset): [67] Total time: 0:00:12 (0.1985 s / it) +Averaged stats (hcp-train-subset): loss: 0.8791 (0.8807) +Eval (hcp-val): [67] [ 0/62] eta: 0:04:56 loss: 0.8806 (0.8806) time: 4.7811 data: 4.7520 max mem: 8299 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8800 (0.8820) time: 0.1180 data: 0.0937 max mem: 8299 +Eval (hcp-val): [67] Total time: 0:00:11 (0.1929 s / it) +Averaged stats (hcp-val): loss: 0.8800 (0.8820) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 9:45:38 lr: 0.000032 grad: 0.3149 (0.3149) loss: 0.8920 (0.8920) time: 5.6222 data: 5.5374 max mem: 8299 +Train: [68] [ 100/6250] eta: 0:17:19 lr: 0.000032 grad: 0.1007 (0.1125) loss: 0.8745 (0.8785) time: 0.1382 data: 0.0594 max mem: 8299 +Train: [68] [ 200/6250] eta: 0:14:37 lr: 0.000032 grad: 0.0951 (0.1111) loss: 0.8666 (0.8726) time: 0.1351 data: 0.0519 max mem: 8299 +Train: [68] [ 300/6250] eta: 0:13:26 lr: 0.000032 grad: 0.1003 (0.1079) loss: 0.8546 (0.8691) time: 0.1197 data: 0.0400 max mem: 8299 +Train: [68] [ 400/6250] eta: 0:12:38 lr: 0.000032 grad: 0.0958 (0.1050) loss: 0.8672 (0.8687) time: 0.1119 data: 0.0370 max mem: 8299 +Train: [68] [ 500/6250] eta: 0:12:02 lr: 0.000032 grad: 0.0991 (0.1037) loss: 0.8656 (0.8679) time: 0.1116 data: 0.0358 max mem: 8299 +Train: [68] [ 600/6250] eta: 0:11:35 lr: 0.000032 grad: 0.0910 (0.1023) loss: 0.8692 (0.8675) time: 0.1107 data: 0.0253 max mem: 8299 +Train: [68] [ 700/6250] eta: 0:11:13 lr: 0.000032 grad: 0.0972 (0.1012) loss: 0.8625 (0.8673) time: 0.0967 data: 0.0137 max mem: 8299 +Train: [68] [ 800/6250] eta: 0:10:59 lr: 0.000032 grad: 0.0966 (0.1010) loss: 0.8662 (0.8669) time: 0.1303 data: 0.0524 max mem: 8299 +Train: [68] [ 900/6250] eta: 0:10:52 lr: 0.000032 grad: 0.0988 (0.1010) loss: 0.8612 (0.8664) time: 0.1287 data: 0.0548 max mem: 8299 +Train: [68] [1000/6250] eta: 0:10:40 lr: 0.000032 grad: 0.0954 (0.1008) loss: 0.8672 (0.8661) time: 0.1257 data: 0.0595 max mem: 8299 +Train: [68] [1100/6250] eta: 0:10:28 lr: 0.000032 grad: 0.0928 (0.1005) loss: 0.8717 (0.8659) time: 0.1151 data: 0.0512 max mem: 8299 +Train: [68] [1200/6250] eta: 0:10:14 lr: 0.000032 grad: 0.1030 (0.1008) loss: 0.8562 (0.8654) time: 0.1199 data: 0.0470 max mem: 8299 +Train: [68] [1300/6250] eta: 0:10:03 lr: 0.000031 grad: 0.1001 (0.1010) loss: 0.8606 (0.8649) time: 0.1089 data: 0.0343 max mem: 8299 +Train: [68] [1400/6250] eta: 0:09:50 lr: 0.000031 grad: 0.1020 (0.1010) loss: 0.8585 (0.8644) time: 0.1355 data: 0.0659 max mem: 8299 +Train: [68] [1500/6250] eta: 0:09:37 lr: 0.000031 grad: 0.1036 (0.1014) loss: 0.8598 (0.8638) time: 0.1314 data: 0.0607 max mem: 8299 +Train: [68] [1600/6250] eta: 0:09:26 lr: 0.000031 grad: 0.0968 (0.1015) loss: 0.8574 (0.8633) time: 0.1365 data: 0.0734 max mem: 8299 +Train: [68] [1700/6250] eta: 0:09:11 lr: 0.000031 grad: 0.0983 (0.1016) loss: 0.8560 (0.8630) time: 0.1068 data: 0.0311 max mem: 8299 +Train: [68] [1800/6250] eta: 0:09:00 lr: 0.000031 grad: 0.0943 (0.1016) loss: 0.8617 (0.8628) time: 0.1295 data: 0.0596 max mem: 8299 +Train: [68] [1900/6250] eta: 0:08:47 lr: 0.000031 grad: 0.0910 (0.1017) loss: 0.8650 (0.8626) time: 0.1116 data: 0.0428 max mem: 8299 +Train: [68] [2000/6250] eta: 0:08:34 lr: 0.000031 grad: 0.0937 (0.1016) loss: 0.8645 (0.8626) time: 0.1179 data: 0.0471 max mem: 8299 +Train: [68] [2100/6250] eta: 0:08:23 lr: 0.000031 grad: 0.0967 (0.1015) loss: 0.8624 (0.8625) time: 0.1152 data: 0.0573 max mem: 8299 +Train: [68] [2200/6250] eta: 0:08:11 lr: 0.000031 grad: 0.0936 (0.1015) loss: 0.8588 (0.8624) time: 0.1200 data: 0.0518 max mem: 8299 +Train: [68] [2300/6250] eta: 0:07:58 lr: 0.000031 grad: 0.0930 (0.1015) loss: 0.8633 (0.8623) time: 0.1115 data: 0.0436 max mem: 8299 +Train: [68] [2400/6250] eta: 0:07:45 lr: 0.000031 grad: 0.0943 (0.1015) loss: 0.8548 (0.8621) time: 0.1122 data: 0.0426 max mem: 8299 +Train: [68] [2500/6250] eta: 0:07:34 lr: 0.000031 grad: 0.0966 (0.1015) loss: 0.8574 (0.8621) time: 0.1377 data: 0.0710 max mem: 8299 +Train: [68] [2600/6250] eta: 0:07:21 lr: 0.000031 grad: 0.0996 (0.1016) loss: 0.8624 (0.8620) time: 0.0799 data: 0.0002 max mem: 8299 +Train: [68] [2700/6250] eta: 0:07:10 lr: 0.000031 grad: 0.0940 (0.1016) loss: 0.8546 (0.8618) time: 0.0917 data: 0.0090 max mem: 8299 +Train: [68] [2800/6250] eta: 0:06:57 lr: 0.000031 grad: 0.0990 (0.1016) loss: 0.8491 (0.8617) time: 0.1308 data: 0.0529 max mem: 8299 +Train: [68] [2900/6250] eta: 0:06:45 lr: 0.000031 grad: 0.1009 (0.1017) loss: 0.8607 (0.8617) time: 0.1221 data: 0.0490 max mem: 8299 +Train: [68] [3000/6250] eta: 0:06:32 lr: 0.000031 grad: 0.0940 (0.1017) loss: 0.8593 (0.8615) time: 0.1093 data: 0.0396 max mem: 8299 +Train: [68] [3100/6250] eta: 0:06:19 lr: 0.000031 grad: 0.0962 (0.1018) loss: 0.8646 (0.8614) time: 0.0910 data: 0.0093 max mem: 8299 +Train: [68] [3200/6250] eta: 0:06:07 lr: 0.000031 grad: 0.0950 (0.1018) loss: 0.8533 (0.8613) time: 0.1212 data: 0.0450 max mem: 8299 +Train: [68] [3300/6250] eta: 0:05:55 lr: 0.000031 grad: 0.0998 (0.1020) loss: 0.8623 (0.8611) time: 0.1211 data: 0.0448 max mem: 8299 +Train: [68] [3400/6250] eta: 0:05:43 lr: 0.000031 grad: 0.0972 (0.1020) loss: 0.8587 (0.8611) time: 0.0769 data: 0.0098 max mem: 8299 +Train: [68] [3500/6250] eta: 0:05:31 lr: 0.000031 grad: 0.0959 (0.1019) loss: 0.8650 (0.8611) time: 0.1006 data: 0.0295 max mem: 8299 +Train: [68] [3600/6250] eta: 0:05:19 lr: 0.000031 grad: 0.0968 (0.1019) loss: 0.8610 (0.8610) time: 0.1229 data: 0.0555 max mem: 8299 +Train: [68] [3700/6250] eta: 0:05:07 lr: 0.000031 grad: 0.0942 (0.1018) loss: 0.8633 (0.8611) time: 0.1268 data: 0.0541 max mem: 8299 +Train: [68] [3800/6250] eta: 0:04:55 lr: 0.000031 grad: 0.0993 (0.1019) loss: 0.8600 (0.8612) time: 0.1377 data: 0.0588 max mem: 8299 +Train: [68] [3900/6250] eta: 0:04:43 lr: 0.000031 grad: 0.0924 (0.1018) loss: 0.8673 (0.8611) time: 0.1244 data: 0.0447 max mem: 8299 +Train: [68] [4000/6250] eta: 0:04:31 lr: 0.000031 grad: 0.1092 (0.1018) loss: 0.8521 (0.8611) time: 0.0860 data: 0.0176 max mem: 8299 +Train: [68] [4100/6250] eta: 0:04:18 lr: 0.000031 grad: 0.1048 (0.1020) loss: 0.8578 (0.8611) time: 0.1057 data: 0.0355 max mem: 8299 +Train: [68] [4200/6250] eta: 0:04:06 lr: 0.000031 grad: 0.0950 (0.1020) loss: 0.8646 (0.8611) time: 0.1022 data: 0.0186 max mem: 8299 +Train: [68] [4300/6250] eta: 0:03:54 lr: 0.000031 grad: 0.0954 (0.1020) loss: 0.8603 (0.8611) time: 0.1025 data: 0.0340 max mem: 8299 +Train: [68] [4400/6250] eta: 0:03:42 lr: 0.000031 grad: 0.1012 (0.1020) loss: 0.8586 (0.8611) time: 0.1422 data: 0.0742 max mem: 8299 +Train: [68] [4500/6250] eta: 0:03:30 lr: 0.000031 grad: 0.1040 (0.1021) loss: 0.8533 (0.8610) time: 0.1192 data: 0.0413 max mem: 8299 +Train: [68] [4600/6250] eta: 0:03:18 lr: 0.000031 grad: 0.1073 (0.1021) loss: 0.8574 (0.8609) time: 0.1390 data: 0.0667 max mem: 8299 +Train: [68] [4700/6250] eta: 0:03:06 lr: 0.000031 grad: 0.1057 (0.1022) loss: 0.8562 (0.8609) time: 0.1231 data: 0.0563 max mem: 8299 +Train: [68] [4800/6250] eta: 0:02:54 lr: 0.000030 grad: 0.1051 (0.1023) loss: 0.8616 (0.8608) time: 0.1231 data: 0.0523 max mem: 8299 +Train: [68] [4900/6250] eta: 0:02:42 lr: 0.000030 grad: 0.1030 (0.1025) loss: 0.8517 (0.8607) time: 0.1346 data: 0.0707 max mem: 8299 +Train: [68] [5000/6250] eta: 0:02:30 lr: 0.000030 grad: 0.1020 (0.1025) loss: 0.8653 (0.8606) time: 0.1155 data: 0.0529 max mem: 8299 +Train: [68] [5100/6250] eta: 0:02:18 lr: 0.000030 grad: 0.0942 (0.1025) loss: 0.8610 (0.8606) time: 0.1389 data: 0.0643 max mem: 8299 +Train: [68] [5200/6250] eta: 0:02:07 lr: 0.000030 grad: 0.0979 (0.1025) loss: 0.8576 (0.8606) time: 0.1320 data: 0.0576 max mem: 8299 +Train: [68] [5300/6250] eta: 0:01:55 lr: 0.000030 grad: 0.0988 (0.1025) loss: 0.8643 (0.8606) time: 0.1218 data: 0.0523 max mem: 8299 +Train: [68] [5400/6250] eta: 0:01:43 lr: 0.000030 grad: 0.1006 (0.1025) loss: 0.8615 (0.8606) time: 0.1217 data: 0.0412 max mem: 8299 +Train: [68] [5500/6250] eta: 0:01:30 lr: 0.000030 grad: 0.1071 (0.1025) loss: 0.8530 (0.8605) time: 0.1408 data: 0.0724 max mem: 8299 +Train: [68] [5600/6250] eta: 0:01:18 lr: 0.000030 grad: 0.0971 (0.1025) loss: 0.8583 (0.8605) time: 0.1118 data: 0.0361 max mem: 8299 +Train: [68] [5700/6250] eta: 0:01:06 lr: 0.000030 grad: 0.0997 (0.1026) loss: 0.8570 (0.8604) time: 0.1071 data: 0.0312 max mem: 8299 +Train: [68] [5800/6250] eta: 0:00:54 lr: 0.000030 grad: 0.0994 (0.1027) loss: 0.8594 (0.8604) time: 0.1015 data: 0.0323 max mem: 8299 +Train: [68] [5900/6250] eta: 0:00:42 lr: 0.000030 grad: 0.1121 (0.1029) loss: 0.8492 (0.8603) time: 0.0818 data: 0.0002 max mem: 8299 +Train: [68] [6000/6250] eta: 0:00:30 lr: 0.000030 grad: 0.1017 (0.1030) loss: 0.8595 (0.8603) time: 0.0970 data: 0.0171 max mem: 8299 +Train: [68] [6100/6250] eta: 0:00:18 lr: 0.000030 grad: 0.1060 (0.1030) loss: 0.8567 (0.8602) time: 0.1028 data: 0.0219 max mem: 8299 +Train: [68] [6200/6250] eta: 0:00:05 lr: 0.000030 grad: 0.1067 (0.1031) loss: 0.8634 (0.8602) time: 0.0963 data: 0.0191 max mem: 8299 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1130 (0.1031) loss: 0.8634 (0.8602) time: 0.1031 data: 0.0321 max mem: 8299 +Train: [68] Total time: 0:12:33 (0.1206 s / it) +Averaged stats: lr: 0.000030 grad: 0.1130 (0.1031) loss: 0.8634 (0.8602) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:04:18 loss: 0.8895 (0.8895) time: 4.1724 data: 4.1437 max mem: 8299 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8795 (0.8801) time: 0.1273 data: 0.1028 max mem: 8299 +Eval (hcp-train-subset): [68] Total time: 0:00:12 (0.1957 s / it) +Averaged stats (hcp-train-subset): loss: 0.8795 (0.8801) +Eval (hcp-val): [68] [ 0/62] eta: 0:03:09 loss: 0.8805 (0.8805) time: 3.0577 data: 2.9962 max mem: 8299 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8787 (0.8808) time: 0.1134 data: 0.0890 max mem: 8299 +Eval (hcp-val): [68] Total time: 0:00:11 (0.1931 s / it) +Averaged stats (hcp-val): loss: 0.8787 (0.8808) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 9:12:37 lr: 0.000030 grad: 0.2751 (0.2751) loss: 0.8731 (0.8731) time: 5.3051 data: 5.2190 max mem: 8299 +Train: [69] [ 100/6250] eta: 0:16:45 lr: 0.000030 grad: 0.1015 (0.1190) loss: 0.8701 (0.8723) time: 0.1227 data: 0.0390 max mem: 8299 +Train: [69] [ 200/6250] eta: 0:14:35 lr: 0.000030 grad: 0.1007 (0.1116) loss: 0.8606 (0.8700) time: 0.1229 data: 0.0339 max mem: 8299 +Train: [69] [ 300/6250] eta: 0:13:35 lr: 0.000030 grad: 0.1009 (0.1093) loss: 0.8665 (0.8676) time: 0.1217 data: 0.0434 max mem: 8299 +Train: [69] [ 400/6250] eta: 0:12:46 lr: 0.000030 grad: 0.0980 (0.1084) loss: 0.8539 (0.8647) time: 0.1326 data: 0.0635 max mem: 8299 +Train: [69] [ 500/6250] eta: 0:12:18 lr: 0.000030 grad: 0.0947 (0.1076) loss: 0.8574 (0.8632) time: 0.1147 data: 0.0367 max mem: 8299 +Train: [69] [ 600/6250] eta: 0:11:55 lr: 0.000030 grad: 0.0951 (0.1073) loss: 0.8684 (0.8625) time: 0.1080 data: 0.0319 max mem: 8299 +Train: [69] [ 700/6250] eta: 0:11:31 lr: 0.000030 grad: 0.0963 (0.1067) loss: 0.8606 (0.8617) time: 0.1116 data: 0.0312 max mem: 8299 +Train: [69] [ 800/6250] eta: 0:11:09 lr: 0.000030 grad: 0.0925 (0.1055) loss: 0.8603 (0.8617) time: 0.1173 data: 0.0413 max mem: 8299 +Train: [69] [ 900/6250] eta: 0:10:48 lr: 0.000030 grad: 0.1049 (0.1051) loss: 0.8545 (0.8615) time: 0.1052 data: 0.0328 max mem: 8299 +Train: [69] [1000/6250] eta: 0:10:28 lr: 0.000030 grad: 0.0975 (0.1045) loss: 0.8704 (0.8616) time: 0.1070 data: 0.0231 max mem: 8299 +Train: [69] [1100/6250] eta: 0:10:09 lr: 0.000030 grad: 0.0943 (0.1038) loss: 0.8630 (0.8616) time: 0.1021 data: 0.0247 max mem: 8299 +Train: [69] [1200/6250] eta: 0:09:53 lr: 0.000030 grad: 0.0945 (0.1032) loss: 0.8597 (0.8616) time: 0.1107 data: 0.0447 max mem: 8299 +Train: [69] [1300/6250] eta: 0:09:37 lr: 0.000030 grad: 0.1030 (0.1030) loss: 0.8611 (0.8614) time: 0.1067 data: 0.0346 max mem: 8299 +Train: [69] [1400/6250] eta: 0:09:22 lr: 0.000030 grad: 0.1002 (0.1028) loss: 0.8599 (0.8614) time: 0.1225 data: 0.0470 max mem: 8299 +Train: [69] [1500/6250] eta: 0:09:07 lr: 0.000030 grad: 0.0982 (0.1027) loss: 0.8650 (0.8614) time: 0.1055 data: 0.0318 max mem: 8299 +Train: [69] [1600/6250] eta: 0:08:51 lr: 0.000030 grad: 0.0953 (0.1026) loss: 0.8598 (0.8614) time: 0.1023 data: 0.0264 max mem: 8299 +Train: [69] [1700/6250] eta: 0:08:38 lr: 0.000030 grad: 0.0983 (0.1027) loss: 0.8598 (0.8612) time: 0.1062 data: 0.0365 max mem: 8299 +Train: [69] [1800/6250] eta: 0:08:26 lr: 0.000030 grad: 0.1064 (0.1027) loss: 0.8568 (0.8611) time: 0.1117 data: 0.0377 max mem: 8299 +Train: [69] [1900/6250] eta: 0:08:14 lr: 0.000030 grad: 0.0921 (0.1027) loss: 0.8589 (0.8610) time: 0.1077 data: 0.0380 max mem: 8299 +Train: [69] [2000/6250] eta: 0:08:02 lr: 0.000030 grad: 0.0951 (0.1027) loss: 0.8534 (0.8608) time: 0.1157 data: 0.0375 max mem: 8299 +Train: [69] [2100/6250] eta: 0:07:49 lr: 0.000029 grad: 0.0983 (0.1028) loss: 0.8603 (0.8607) time: 0.0901 data: 0.0148 max mem: 8299 +Train: [69] [2200/6250] eta: 0:07:37 lr: 0.000029 grad: 0.1021 (0.1028) loss: 0.8634 (0.8606) time: 0.1168 data: 0.0431 max mem: 8299 +Train: [69] [2300/6250] eta: 0:07:24 lr: 0.000029 grad: 0.0998 (0.1028) loss: 0.8521 (0.8605) time: 0.0967 data: 0.0239 max mem: 8299 +Train: [69] [2400/6250] eta: 0:07:12 lr: 0.000029 grad: 0.1047 (0.1029) loss: 0.8493 (0.8603) time: 0.1031 data: 0.0343 max mem: 8299 +Train: [69] [2500/6250] eta: 0:07:00 lr: 0.000029 grad: 0.1022 (0.1029) loss: 0.8529 (0.8602) time: 0.1078 data: 0.0238 max mem: 8299 +Train: [69] [2600/6250] eta: 0:06:48 lr: 0.000029 grad: 0.1034 (0.1031) loss: 0.8557 (0.8600) time: 0.1167 data: 0.0411 max mem: 8299 +Train: [69] [2700/6250] eta: 0:06:36 lr: 0.000029 grad: 0.1003 (0.1031) loss: 0.8532 (0.8599) time: 0.0978 data: 0.0254 max mem: 8299 +Train: [69] [2800/6250] eta: 0:06:25 lr: 0.000029 grad: 0.1022 (0.1031) loss: 0.8550 (0.8597) time: 0.1099 data: 0.0438 max mem: 8299 +Train: [69] [2900/6250] eta: 0:06:14 lr: 0.000029 grad: 0.1046 (0.1031) loss: 0.8576 (0.8596) time: 0.0803 data: 0.0064 max mem: 8299 +Train: [69] [3000/6250] eta: 0:06:03 lr: 0.000029 grad: 0.0951 (0.1032) loss: 0.8598 (0.8595) time: 0.1046 data: 0.0359 max mem: 8299 +Train: [69] [3100/6250] eta: 0:05:52 lr: 0.000029 grad: 0.0933 (0.1032) loss: 0.8587 (0.8594) time: 0.1229 data: 0.0506 max mem: 8299 +Train: [69] [3200/6250] eta: 0:05:41 lr: 0.000029 grad: 0.1036 (0.1034) loss: 0.8546 (0.8592) time: 0.1127 data: 0.0336 max mem: 8299 +Train: [69] [3300/6250] eta: 0:05:30 lr: 0.000029 grad: 0.0993 (0.1035) loss: 0.8557 (0.8592) time: 0.1023 data: 0.0223 max mem: 8299 +Train: [69] [3400/6250] eta: 0:05:19 lr: 0.000029 grad: 0.1031 (0.1036) loss: 0.8529 (0.8591) time: 0.1068 data: 0.0255 max mem: 8299 +Train: [69] [3500/6250] eta: 0:05:08 lr: 0.000029 grad: 0.0970 (0.1036) loss: 0.8533 (0.8591) time: 0.1303 data: 0.0544 max mem: 8299 +Train: [69] [3600/6250] eta: 0:04:57 lr: 0.000029 grad: 0.1047 (0.1036) loss: 0.8600 (0.8591) time: 0.1350 data: 0.0614 max mem: 8299 +Train: [69] [3700/6250] eta: 0:04:45 lr: 0.000029 grad: 0.1013 (0.1036) loss: 0.8528 (0.8591) time: 0.1023 data: 0.0245 max mem: 8299 +Train: [69] [3800/6250] eta: 0:04:35 lr: 0.000029 grad: 0.1026 (0.1037) loss: 0.8577 (0.8591) time: 0.0929 data: 0.0054 max mem: 8299 +Train: [69] [3900/6250] eta: 0:04:23 lr: 0.000029 grad: 0.1009 (0.1037) loss: 0.8549 (0.8590) time: 0.1216 data: 0.0430 max mem: 8299 +Train: [69] [4000/6250] eta: 0:04:12 lr: 0.000029 grad: 0.1085 (0.1038) loss: 0.8571 (0.8590) time: 0.1112 data: 0.0409 max mem: 8299 +Train: [69] [4100/6250] eta: 0:04:01 lr: 0.000029 grad: 0.1046 (0.1039) loss: 0.8531 (0.8589) time: 0.1102 data: 0.0352 max mem: 8299 +Train: [69] [4200/6250] eta: 0:03:50 lr: 0.000029 grad: 0.1007 (0.1039) loss: 0.8594 (0.8589) time: 0.1129 data: 0.0434 max mem: 8299 +Train: [69] [4300/6250] eta: 0:03:38 lr: 0.000029 grad: 0.1087 (0.1039) loss: 0.8594 (0.8589) time: 0.0963 data: 0.0262 max mem: 8299 +Train: [69] [4400/6250] eta: 0:03:27 lr: 0.000029 grad: 0.1007 (0.1040) loss: 0.8518 (0.8589) time: 0.1090 data: 0.0325 max mem: 8299 +Train: [69] [4500/6250] eta: 0:03:16 lr: 0.000029 grad: 0.1103 (0.1041) loss: 0.8597 (0.8589) time: 0.1011 data: 0.0226 max mem: 8299 +Train: [69] [4600/6250] eta: 0:03:06 lr: 0.000029 grad: 0.1046 (0.1041) loss: 0.8553 (0.8588) time: 0.1445 data: 0.0763 max mem: 8299 +Train: [69] [4700/6250] eta: 0:02:54 lr: 0.000029 grad: 0.1016 (0.1041) loss: 0.8522 (0.8588) time: 0.1352 data: 0.0634 max mem: 8299 +Train: [69] [4800/6250] eta: 0:02:43 lr: 0.000029 grad: 0.1053 (0.1041) loss: 0.8580 (0.8588) time: 0.1054 data: 0.0319 max mem: 8299 +Train: [69] [4900/6250] eta: 0:02:32 lr: 0.000029 grad: 0.0993 (0.1041) loss: 0.8624 (0.8588) time: 0.1302 data: 0.0448 max mem: 8299 +Train: [69] [5000/6250] eta: 0:02:22 lr: 0.000029 grad: 0.0995 (0.1042) loss: 0.8553 (0.8588) time: 0.1388 data: 0.0658 max mem: 8299 +Train: [69] [5100/6250] eta: 0:02:11 lr: 0.000029 grad: 0.0936 (0.1041) loss: 0.8596 (0.8587) time: 0.1272 data: 0.0585 max mem: 8299 +Train: [69] [5200/6250] eta: 0:02:00 lr: 0.000029 grad: 0.0933 (0.1041) loss: 0.8641 (0.8588) time: 0.1378 data: 0.0663 max mem: 8299 +Train: [69] [5300/6250] eta: 0:01:48 lr: 0.000029 grad: 0.0999 (0.1041) loss: 0.8574 (0.8588) time: 0.1121 data: 0.0406 max mem: 8299 +Train: [69] [5400/6250] eta: 0:01:37 lr: 0.000029 grad: 0.0995 (0.1040) loss: 0.8591 (0.8588) time: 0.1189 data: 0.0488 max mem: 8299 +Train: [69] [5500/6250] eta: 0:01:25 lr: 0.000029 grad: 0.1021 (0.1040) loss: 0.8658 (0.8589) time: 0.1232 data: 0.0589 max mem: 8299 +Train: [69] [5600/6250] eta: 0:01:14 lr: 0.000028 grad: 0.0960 (0.1040) loss: 0.8626 (0.8589) time: 0.1140 data: 0.0361 max mem: 8299 +Train: [69] [5700/6250] eta: 0:01:02 lr: 0.000028 grad: 0.1008 (0.1039) loss: 0.8555 (0.8589) time: 0.1088 data: 0.0329 max mem: 8299 +Train: [69] [5800/6250] eta: 0:00:51 lr: 0.000028 grad: 0.0948 (0.1039) loss: 0.8649 (0.8590) time: 0.1225 data: 0.0481 max mem: 8299 +Train: [69] [5900/6250] eta: 0:00:40 lr: 0.000028 grad: 0.0980 (0.1038) loss: 0.8613 (0.8590) time: 0.0878 data: 0.0002 max mem: 8299 +Train: [69] [6000/6250] eta: 0:00:28 lr: 0.000028 grad: 0.0988 (0.1038) loss: 0.8590 (0.8590) time: 0.1144 data: 0.0399 max mem: 8299 +Train: [69] [6100/6250] eta: 0:00:17 lr: 0.000028 grad: 0.0950 (0.1037) loss: 0.8645 (0.8591) time: 0.0990 data: 0.0153 max mem: 8299 +Train: [69] [6200/6250] eta: 0:00:05 lr: 0.000028 grad: 0.0927 (0.1037) loss: 0.8659 (0.8591) time: 0.1007 data: 0.0129 max mem: 8299 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1011 (0.1037) loss: 0.8643 (0.8591) time: 0.0929 data: 0.0106 max mem: 8299 +Train: [69] Total time: 0:11:55 (0.1145 s / it) +Averaged stats: lr: 0.000028 grad: 0.1011 (0.1037) loss: 0.8643 (0.8591) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:04:03 loss: 0.8836 (0.8836) time: 3.9232 data: 3.8594 max mem: 8299 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8770 (0.8782) time: 0.1168 data: 0.0912 max mem: 8299 +Eval (hcp-train-subset): [69] Total time: 0:00:12 (0.1961 s / it) +Averaged stats (hcp-train-subset): loss: 0.8770 (0.8782) +Making plots (hcp-train-subset): example=47 +Eval (hcp-val): [69] [ 0/62] eta: 0:03:28 loss: 0.8777 (0.8777) time: 3.3548 data: 3.2790 max mem: 8299 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8817 (0.8812) time: 0.1192 data: 0.0937 max mem: 8299 +Eval (hcp-val): [69] Total time: 0:00:12 (0.1974 s / it) +Averaged stats (hcp-val): loss: 0.8817 (0.8812) +Making plots (hcp-val): example=54 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 10:02:31 lr: 0.000028 grad: 0.1282 (0.1282) loss: 0.8733 (0.8733) time: 5.7842 data: 5.6969 max mem: 8299 +Train: [70] [ 100/6250] eta: 0:17:36 lr: 0.000028 grad: 0.1162 (0.1254) loss: 0.8669 (0.8738) time: 0.1375 data: 0.0563 max mem: 8299 +Train: [70] [ 200/6250] eta: 0:14:53 lr: 0.000028 grad: 0.1134 (0.1195) loss: 0.8516 (0.8680) time: 0.1322 data: 0.0499 max mem: 8299 +Train: [70] [ 300/6250] eta: 0:13:44 lr: 0.000028 grad: 0.1093 (0.1176) loss: 0.8597 (0.8651) time: 0.1255 data: 0.0488 max mem: 8299 +Train: [70] [ 400/6250] eta: 0:12:59 lr: 0.000028 grad: 0.1052 (0.1154) loss: 0.8585 (0.8640) time: 0.1101 data: 0.0377 max mem: 8299 +Train: [70] [ 500/6250] eta: 0:12:25 lr: 0.000028 grad: 0.1043 (0.1137) loss: 0.8626 (0.8633) time: 0.1148 data: 0.0351 max mem: 8299 +Train: [70] [ 600/6250] eta: 0:11:52 lr: 0.000028 grad: 0.0999 (0.1121) loss: 0.8591 (0.8630) time: 0.0983 data: 0.0230 max mem: 8299 +Train: [70] [ 700/6250] eta: 0:11:28 lr: 0.000028 grad: 0.1013 (0.1107) loss: 0.8661 (0.8632) time: 0.1125 data: 0.0249 max mem: 8299 +Train: [70] [ 800/6250] eta: 0:11:06 lr: 0.000028 grad: 0.0930 (0.1090) loss: 0.8629 (0.8632) time: 0.1213 data: 0.0502 max mem: 8299 +Train: [70] [ 900/6250] eta: 0:10:46 lr: 0.000028 grad: 0.1002 (0.1082) loss: 0.8656 (0.8632) time: 0.1072 data: 0.0313 max mem: 8299 +Train: [70] [1000/6250] eta: 0:10:26 lr: 0.000028 grad: 0.0931 (0.1073) loss: 0.8703 (0.8634) time: 0.1073 data: 0.0291 max mem: 8299 +Train: [70] [1100/6250] eta: 0:10:10 lr: 0.000028 grad: 0.0945 (0.1065) loss: 0.8669 (0.8635) time: 0.1116 data: 0.0315 max mem: 8299 +Train: [70] [1200/6250] eta: 0:09:54 lr: 0.000028 grad: 0.0885 (0.1058) loss: 0.8629 (0.8635) time: 0.1099 data: 0.0387 max mem: 8299 +Train: [70] [1300/6250] eta: 0:09:40 lr: 0.000028 grad: 0.0952 (0.1053) loss: 0.8608 (0.8635) time: 0.0918 data: 0.0187 max mem: 8299 +Train: [70] [1400/6250] eta: 0:09:26 lr: 0.000028 grad: 0.1018 (0.1050) loss: 0.8622 (0.8636) time: 0.1148 data: 0.0455 max mem: 8299 +Train: [70] [1500/6250] eta: 0:09:14 lr: 0.000028 grad: 0.0948 (0.1049) loss: 0.8619 (0.8636) time: 0.1248 data: 0.0437 max mem: 8299 +Train: [70] [1600/6250] eta: 0:09:00 lr: 0.000028 grad: 0.0990 (0.1046) loss: 0.8604 (0.8634) time: 0.1128 data: 0.0445 max mem: 8299 +Train: [70] [1700/6250] eta: 0:08:47 lr: 0.000028 grad: 0.1002 (0.1043) loss: 0.8690 (0.8633) time: 0.1239 data: 0.0516 max mem: 8299 +Train: [70] [1800/6250] eta: 0:08:34 lr: 0.000028 grad: 0.1055 (0.1044) loss: 0.8587 (0.8631) time: 0.1198 data: 0.0529 max mem: 8299 +Train: [70] [1900/6250] eta: 0:08:21 lr: 0.000028 grad: 0.0932 (0.1043) loss: 0.8638 (0.8630) time: 0.0946 data: 0.0213 max mem: 8299 +Train: [70] [2000/6250] eta: 0:08:11 lr: 0.000028 grad: 0.1087 (0.1043) loss: 0.8566 (0.8628) time: 0.1661 data: 0.0978 max mem: 8299 +Train: [70] [2100/6250] eta: 0:07:57 lr: 0.000028 grad: 0.0977 (0.1045) loss: 0.8594 (0.8626) time: 0.1042 data: 0.0316 max mem: 8299 +Train: [70] [2200/6250] eta: 0:07:45 lr: 0.000028 grad: 0.1046 (0.1046) loss: 0.8539 (0.8623) time: 0.1115 data: 0.0405 max mem: 8299 +Train: [70] [2300/6250] eta: 0:07:33 lr: 0.000028 grad: 0.1061 (0.1049) loss: 0.8610 (0.8621) time: 0.1122 data: 0.0293 max mem: 8299 +Train: [70] [2400/6250] eta: 0:07:21 lr: 0.000028 grad: 0.1062 (0.1052) loss: 0.8548 (0.8618) time: 0.1216 data: 0.0433 max mem: 8299 +Train: [70] [2500/6250] eta: 0:07:10 lr: 0.000028 grad: 0.1067 (0.1054) loss: 0.8444 (0.8614) time: 0.1004 data: 0.0303 max mem: 8299 +Train: [70] [2600/6250] eta: 0:06:59 lr: 0.000028 grad: 0.1028 (0.1054) loss: 0.8488 (0.8611) time: 0.1023 data: 0.0274 max mem: 8299 +Train: [70] [2700/6250] eta: 0:06:48 lr: 0.000028 grad: 0.1029 (0.1057) loss: 0.8561 (0.8608) time: 0.1170 data: 0.0452 max mem: 8299 +Train: [70] [2800/6250] eta: 0:06:36 lr: 0.000028 grad: 0.0994 (0.1059) loss: 0.8522 (0.8604) time: 0.1225 data: 0.0470 max mem: 8299 +Train: [70] [2900/6250] eta: 0:06:25 lr: 0.000028 grad: 0.1061 (0.1060) loss: 0.8504 (0.8602) time: 0.1442 data: 0.0761 max mem: 8299 +Train: [70] [3000/6250] eta: 0:06:13 lr: 0.000027 grad: 0.1135 (0.1062) loss: 0.8552 (0.8600) time: 0.0882 data: 0.0136 max mem: 8299 +Train: [70] [3100/6250] eta: 0:06:02 lr: 0.000027 grad: 0.1068 (0.1064) loss: 0.8610 (0.8599) time: 0.1427 data: 0.0705 max mem: 8299 +Train: [70] [3200/6250] eta: 0:05:51 lr: 0.000027 grad: 0.0992 (0.1063) loss: 0.8643 (0.8599) time: 0.1099 data: 0.0390 max mem: 8299 +Train: [70] [3300/6250] eta: 0:05:40 lr: 0.000027 grad: 0.0980 (0.1063) loss: 0.8650 (0.8599) time: 0.1691 data: 0.0956 max mem: 8299 +Train: [70] [3400/6250] eta: 0:05:28 lr: 0.000027 grad: 0.1050 (0.1062) loss: 0.8587 (0.8599) time: 0.1336 data: 0.0454 max mem: 8299 +Train: [70] [3500/6250] eta: 0:05:17 lr: 0.000027 grad: 0.0993 (0.1061) loss: 0.8645 (0.8600) time: 0.0788 data: 0.0002 max mem: 8299 +Train: [70] [3600/6250] eta: 0:05:06 lr: 0.000027 grad: 0.1045 (0.1063) loss: 0.8614 (0.8601) time: 0.1271 data: 0.0556 max mem: 8299 +Train: [70] [3700/6250] eta: 0:04:54 lr: 0.000027 grad: 0.1109 (0.1064) loss: 0.8688 (0.8601) time: 0.1190 data: 0.0396 max mem: 8299 +Train: [70] [3800/6250] eta: 0:04:43 lr: 0.000027 grad: 0.1027 (0.1064) loss: 0.8559 (0.8602) time: 0.1211 data: 0.0508 max mem: 8299 +Train: [70] [3900/6250] eta: 0:04:31 lr: 0.000027 grad: 0.1021 (0.1063) loss: 0.8598 (0.8603) time: 0.1260 data: 0.0617 max mem: 8299 +Train: [70] [4000/6250] eta: 0:04:20 lr: 0.000027 grad: 0.1013 (0.1063) loss: 0.8616 (0.8603) time: 0.1000 data: 0.0379 max mem: 8299 +Train: [70] [4100/6250] eta: 0:04:08 lr: 0.000027 grad: 0.0996 (0.1064) loss: 0.8620 (0.8604) time: 0.1228 data: 0.0529 max mem: 8299 +Train: [70] [4200/6250] eta: 0:03:57 lr: 0.000027 grad: 0.0990 (0.1064) loss: 0.8616 (0.8604) time: 0.1218 data: 0.0542 max mem: 8299 +Train: [70] [4300/6250] eta: 0:03:45 lr: 0.000027 grad: 0.1021 (0.1064) loss: 0.8681 (0.8605) time: 0.1162 data: 0.0457 max mem: 8299 +Train: [70] [4400/6250] eta: 0:03:34 lr: 0.000027 grad: 0.1096 (0.1064) loss: 0.8653 (0.8605) time: 0.1197 data: 0.0491 max mem: 8299 +Train: [70] [4500/6250] eta: 0:03:22 lr: 0.000027 grad: 0.1109 (0.1065) loss: 0.8582 (0.8605) time: 0.1260 data: 0.0520 max mem: 8299 +Train: [70] [4600/6250] eta: 0:03:11 lr: 0.000027 grad: 0.1038 (0.1066) loss: 0.8651 (0.8605) time: 0.1243 data: 0.0548 max mem: 8299 +Train: [70] [4700/6250] eta: 0:02:59 lr: 0.000027 grad: 0.1069 (0.1067) loss: 0.8622 (0.8605) time: 0.1266 data: 0.0583 max mem: 8299 +Train: [70] [4800/6250] eta: 0:02:48 lr: 0.000027 grad: 0.1118 (0.1067) loss: 0.8572 (0.8604) time: 0.1714 data: 0.1081 max mem: 8299 +Train: [70] [4900/6250] eta: 0:02:37 lr: 0.000027 grad: 0.1009 (0.1068) loss: 0.8622 (0.8604) time: 0.1184 data: 0.0438 max mem: 8299 +Train: [70] [5000/6250] eta: 0:02:26 lr: 0.000027 grad: 0.1028 (0.1068) loss: 0.8527 (0.8603) time: 0.1640 data: 0.0981 max mem: 8299 +Train: [70] [5100/6250] eta: 0:02:14 lr: 0.000027 grad: 0.1108 (0.1069) loss: 0.8570 (0.8603) time: 0.1397 data: 0.0706 max mem: 8299 +Train: [70] [5200/6250] eta: 0:02:03 lr: 0.000027 grad: 0.1048 (0.1069) loss: 0.8571 (0.8603) time: 0.1136 data: 0.0403 max mem: 8299 +Train: [70] [5300/6250] eta: 0:01:51 lr: 0.000027 grad: 0.1017 (0.1069) loss: 0.8609 (0.8603) time: 0.1200 data: 0.0487 max mem: 8299 +Train: [70] [5400/6250] eta: 0:01:39 lr: 0.000027 grad: 0.1010 (0.1069) loss: 0.8538 (0.8602) time: 0.0980 data: 0.0295 max mem: 8299 +Train: [70] [5500/6250] eta: 0:01:27 lr: 0.000027 grad: 0.1064 (0.1070) loss: 0.8608 (0.8602) time: 0.1168 data: 0.0480 max mem: 8299 +Train: [70] [5600/6250] eta: 0:01:15 lr: 0.000027 grad: 0.1052 (0.1070) loss: 0.8607 (0.8602) time: 0.1062 data: 0.0441 max mem: 8299 +Train: [70] [5700/6250] eta: 0:01:04 lr: 0.000027 grad: 0.1014 (0.1070) loss: 0.8652 (0.8602) time: 0.1043 data: 0.0163 max mem: 8299 +Train: [70] [5800/6250] eta: 0:00:52 lr: 0.000027 grad: 0.1119 (0.1071) loss: 0.8646 (0.8602) time: 0.1032 data: 0.0298 max mem: 8299 +Train: [70] [5900/6250] eta: 0:00:40 lr: 0.000027 grad: 0.1113 (0.1071) loss: 0.8599 (0.8602) time: 0.1063 data: 0.0397 max mem: 8299 +Train: [70] [6000/6250] eta: 0:00:29 lr: 0.000027 grad: 0.0994 (0.1070) loss: 0.8592 (0.8602) time: 0.1047 data: 0.0311 max mem: 8299 +Train: [70] [6100/6250] eta: 0:00:17 lr: 0.000027 grad: 0.1010 (0.1070) loss: 0.8590 (0.8602) time: 0.1212 data: 0.0463 max mem: 8299 +Train: [70] [6200/6250] eta: 0:00:05 lr: 0.000027 grad: 0.1104 (0.1070) loss: 0.8525 (0.8602) time: 0.1724 data: 0.1038 max mem: 8299 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1096 (0.1070) loss: 0.8543 (0.8602) time: 0.0854 data: 0.0125 max mem: 8299 +Train: [70] Total time: 0:12:10 (0.1169 s / it) +Averaged stats: lr: 0.000027 grad: 0.1096 (0.1070) loss: 0.8543 (0.8602) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:03:20 loss: 0.8859 (0.8859) time: 3.2269 data: 3.1424 max mem: 8299 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8784 (0.8796) time: 0.1297 data: 0.1049 max mem: 8299 +Eval (hcp-train-subset): [70] Total time: 0:00:11 (0.1912 s / it) +Averaged stats (hcp-train-subset): loss: 0.8784 (0.8796) +Eval (hcp-val): [70] [ 0/62] eta: 0:03:14 loss: 0.8783 (0.8783) time: 3.1411 data: 3.0612 max mem: 8299 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8779 (0.8792) time: 0.1180 data: 0.0925 max mem: 8299 +Eval (hcp-val): [70] Total time: 0:00:12 (0.1988 s / it) +Averaged stats (hcp-val): loss: 0.8779 (0.8792) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 8:46:23 lr: 0.000027 grad: 0.1422 (0.1422) loss: 0.9005 (0.9005) time: 5.0534 data: 4.9449 max mem: 8299 +Train: [71] [ 100/6250] eta: 0:17:12 lr: 0.000027 grad: 0.0867 (0.1175) loss: 0.8725 (0.8806) time: 0.1330 data: 0.0351 max mem: 8299 +Train: [71] [ 200/6250] eta: 0:14:27 lr: 0.000027 grad: 0.1000 (0.1105) loss: 0.8706 (0.8760) time: 0.1167 data: 0.0417 max mem: 8299 +Train: [71] [ 300/6250] eta: 0:13:27 lr: 0.000027 grad: 0.1080 (0.1092) loss: 0.8704 (0.8735) time: 0.1256 data: 0.0415 max mem: 8299 +Train: [71] [ 400/6250] eta: 0:12:50 lr: 0.000026 grad: 0.1009 (0.1090) loss: 0.8635 (0.8713) time: 0.1281 data: 0.0599 max mem: 8299 +Train: [71] [ 500/6250] eta: 0:12:21 lr: 0.000026 grad: 0.0988 (0.1082) loss: 0.8559 (0.8688) time: 0.1255 data: 0.0490 max mem: 8299 +Train: [71] [ 600/6250] eta: 0:11:52 lr: 0.000026 grad: 0.1042 (0.1082) loss: 0.8622 (0.8669) time: 0.1032 data: 0.0225 max mem: 8299 +Train: [71] [ 700/6250] eta: 0:11:25 lr: 0.000026 grad: 0.0994 (0.1076) loss: 0.8536 (0.8652) time: 0.1020 data: 0.0213 max mem: 8299 +Train: [71] [ 800/6250] eta: 0:11:05 lr: 0.000026 grad: 0.0980 (0.1073) loss: 0.8605 (0.8641) time: 0.1093 data: 0.0335 max mem: 8299 +Train: [71] [ 900/6250] eta: 0:10:46 lr: 0.000026 grad: 0.0994 (0.1075) loss: 0.8574 (0.8633) time: 0.1263 data: 0.0518 max mem: 8299 +Train: [71] [1000/6250] eta: 0:10:25 lr: 0.000026 grad: 0.1126 (0.1077) loss: 0.8556 (0.8623) time: 0.1094 data: 0.0272 max mem: 8299 +Train: [71] [1100/6250] eta: 0:10:09 lr: 0.000026 grad: 0.1050 (0.1075) loss: 0.8534 (0.8619) time: 0.1011 data: 0.0283 max mem: 8299 +Train: [71] [1200/6250] eta: 0:09:55 lr: 0.000026 grad: 0.1024 (0.1078) loss: 0.8563 (0.8612) time: 0.1042 data: 0.0333 max mem: 8299 +Train: [71] [1300/6250] eta: 0:09:41 lr: 0.000026 grad: 0.1042 (0.1080) loss: 0.8604 (0.8606) time: 0.1153 data: 0.0424 max mem: 8299 +Train: [71] [1400/6250] eta: 0:09:29 lr: 0.000026 grad: 0.1104 (0.1081) loss: 0.8565 (0.8602) time: 0.1210 data: 0.0431 max mem: 8299 +Train: [71] [1500/6250] eta: 0:09:19 lr: 0.000026 grad: 0.1025 (0.1079) loss: 0.8568 (0.8598) time: 0.1485 data: 0.0779 max mem: 8299 +Train: [71] [1600/6250] eta: 0:09:03 lr: 0.000026 grad: 0.1088 (0.1077) loss: 0.8553 (0.8596) time: 0.1072 data: 0.0318 max mem: 8299 +Train: [71] [1700/6250] eta: 0:08:51 lr: 0.000026 grad: 0.1054 (0.1075) loss: 0.8510 (0.8594) time: 0.1108 data: 0.0356 max mem: 8299 +Train: [71] [1800/6250] eta: 0:08:39 lr: 0.000026 grad: 0.1036 (0.1074) loss: 0.8602 (0.8594) time: 0.0995 data: 0.0279 max mem: 8299 +Train: [71] [1900/6250] eta: 0:08:26 lr: 0.000026 grad: 0.1091 (0.1075) loss: 0.8577 (0.8592) time: 0.0908 data: 0.0159 max mem: 8299 +Train: [71] [2000/6250] eta: 0:08:15 lr: 0.000026 grad: 0.1019 (0.1076) loss: 0.8603 (0.8591) time: 0.1231 data: 0.0499 max mem: 8299 +Train: [71] [2100/6250] eta: 0:08:04 lr: 0.000026 grad: 0.1046 (0.1076) loss: 0.8607 (0.8591) time: 0.1322 data: 0.0613 max mem: 8299 +Train: [71] [2200/6250] eta: 0:07:51 lr: 0.000026 grad: 0.1020 (0.1076) loss: 0.8609 (0.8592) time: 0.1124 data: 0.0427 max mem: 8299 +Train: [71] [2300/6250] eta: 0:07:40 lr: 0.000026 grad: 0.1023 (0.1074) loss: 0.8616 (0.8593) time: 0.1099 data: 0.0380 max mem: 8299 +Train: [71] [2400/6250] eta: 0:07:28 lr: 0.000026 grad: 0.0987 (0.1072) loss: 0.8618 (0.8594) time: 0.1506 data: 0.0821 max mem: 8299 +Train: [71] [2500/6250] eta: 0:07:16 lr: 0.000026 grad: 0.1087 (0.1071) loss: 0.8634 (0.8595) time: 0.1102 data: 0.0358 max mem: 8299 +Train: [71] [2600/6250] eta: 0:07:04 lr: 0.000026 grad: 0.0975 (0.1070) loss: 0.8726 (0.8595) time: 0.1060 data: 0.0367 max mem: 8299 +Train: [71] [2700/6250] eta: 0:06:54 lr: 0.000026 grad: 0.1035 (0.1069) loss: 0.8652 (0.8596) time: 0.1657 data: 0.0980 max mem: 8299 +Train: [71] [2800/6250] eta: 0:06:41 lr: 0.000026 grad: 0.0992 (0.1069) loss: 0.8637 (0.8596) time: 0.1125 data: 0.0407 max mem: 8299 +Train: [71] [2900/6250] eta: 0:06:30 lr: 0.000026 grad: 0.1026 (0.1070) loss: 0.8597 (0.8596) time: 0.1150 data: 0.0485 max mem: 8299 +Train: [71] [3000/6250] eta: 0:06:19 lr: 0.000026 grad: 0.1016 (0.1070) loss: 0.8588 (0.8596) time: 0.1471 data: 0.0808 max mem: 8299 +Train: [71] [3100/6250] eta: 0:06:07 lr: 0.000026 grad: 0.1110 (0.1072) loss: 0.8591 (0.8596) time: 0.1538 data: 0.0840 max mem: 8299 +Train: [71] [3200/6250] eta: 0:05:55 lr: 0.000026 grad: 0.1047 (0.1071) loss: 0.8559 (0.8596) time: 0.1135 data: 0.0444 max mem: 8299 +Train: [71] [3300/6250] eta: 0:05:43 lr: 0.000026 grad: 0.1037 (0.1073) loss: 0.8613 (0.8595) time: 0.1186 data: 0.0511 max mem: 8299 +Train: [71] [3400/6250] eta: 0:05:32 lr: 0.000026 grad: 0.1093 (0.1074) loss: 0.8616 (0.8594) time: 0.1376 data: 0.0719 max mem: 8299 +Train: [71] [3500/6250] eta: 0:05:20 lr: 0.000026 grad: 0.1016 (0.1075) loss: 0.8579 (0.8593) time: 0.1241 data: 0.0537 max mem: 8299 +Train: [71] [3600/6250] eta: 0:05:08 lr: 0.000026 grad: 0.1035 (0.1076) loss: 0.8505 (0.8593) time: 0.1314 data: 0.0610 max mem: 8299 +Train: [71] [3700/6250] eta: 0:04:57 lr: 0.000026 grad: 0.1056 (0.1076) loss: 0.8544 (0.8593) time: 0.0911 data: 0.0156 max mem: 8299 +Train: [71] [3800/6250] eta: 0:04:45 lr: 0.000026 grad: 0.1101 (0.1076) loss: 0.8629 (0.8593) time: 0.1132 data: 0.0353 max mem: 8299 +Train: [71] [3900/6250] eta: 0:04:33 lr: 0.000026 grad: 0.1048 (0.1077) loss: 0.8619 (0.8593) time: 0.1238 data: 0.0591 max mem: 8299 +Train: [71] [4000/6250] eta: 0:04:22 lr: 0.000026 grad: 0.1087 (0.1077) loss: 0.8557 (0.8592) time: 0.0755 data: 0.0008 max mem: 8299 +Train: [71] [4100/6250] eta: 0:04:10 lr: 0.000026 grad: 0.1090 (0.1078) loss: 0.8557 (0.8591) time: 0.1314 data: 0.0665 max mem: 8299 +Train: [71] [4200/6250] eta: 0:03:59 lr: 0.000025 grad: 0.1059 (0.1078) loss: 0.8558 (0.8590) time: 0.1154 data: 0.0455 max mem: 8299 +Train: [71] [4300/6250] eta: 0:03:47 lr: 0.000025 grad: 0.1129 (0.1079) loss: 0.8572 (0.8590) time: 0.0807 data: 0.0002 max mem: 8299 +Train: [71] [4400/6250] eta: 0:03:36 lr: 0.000025 grad: 0.1021 (0.1080) loss: 0.8558 (0.8589) time: 0.1363 data: 0.0684 max mem: 8299 +Train: [71] [4500/6250] eta: 0:03:24 lr: 0.000025 grad: 0.1037 (0.1080) loss: 0.8565 (0.8588) time: 0.1048 data: 0.0301 max mem: 8299 +Train: [71] [4600/6250] eta: 0:03:13 lr: 0.000025 grad: 0.1060 (0.1081) loss: 0.8576 (0.8587) time: 0.0810 data: 0.0002 max mem: 8299 +Train: [71] [4700/6250] eta: 0:03:01 lr: 0.000025 grad: 0.1030 (0.1081) loss: 0.8534 (0.8586) time: 0.0820 data: 0.0069 max mem: 8299 +Train: [71] [4800/6250] eta: 0:02:50 lr: 0.000025 grad: 0.1012 (0.1082) loss: 0.8557 (0.8586) time: 0.1939 data: 0.1246 max mem: 8299 +Train: [71] [4900/6250] eta: 0:02:38 lr: 0.000025 grad: 0.1037 (0.1082) loss: 0.8555 (0.8585) time: 0.1034 data: 0.0327 max mem: 8299 +Train: [71] [5000/6250] eta: 0:02:26 lr: 0.000025 grad: 0.1030 (0.1082) loss: 0.8552 (0.8584) time: 0.1214 data: 0.0452 max mem: 8299 +Train: [71] [5100/6250] eta: 0:02:15 lr: 0.000025 grad: 0.1059 (0.1082) loss: 0.8495 (0.8583) time: 0.1476 data: 0.0810 max mem: 8299 +Train: [71] [5200/6250] eta: 0:02:03 lr: 0.000025 grad: 0.1122 (0.1082) loss: 0.8529 (0.8582) time: 0.1365 data: 0.0664 max mem: 8299 +Train: [71] [5300/6250] eta: 0:01:52 lr: 0.000025 grad: 0.1066 (0.1082) loss: 0.8545 (0.8582) time: 0.1133 data: 0.0431 max mem: 8299 +Train: [71] [5400/6250] eta: 0:01:40 lr: 0.000025 grad: 0.1046 (0.1082) loss: 0.8605 (0.8582) time: 0.1303 data: 0.0602 max mem: 8299 +Train: [71] [5500/6250] eta: 0:01:28 lr: 0.000025 grad: 0.1069 (0.1082) loss: 0.8629 (0.8582) time: 0.1107 data: 0.0401 max mem: 8299 +Train: [71] [5600/6250] eta: 0:01:16 lr: 0.000025 grad: 0.1050 (0.1081) loss: 0.8626 (0.8583) time: 0.1154 data: 0.0369 max mem: 8299 +Train: [71] [5700/6250] eta: 0:01:04 lr: 0.000025 grad: 0.1030 (0.1081) loss: 0.8644 (0.8583) time: 0.1093 data: 0.0407 max mem: 8299 +Train: [71] [5800/6250] eta: 0:00:52 lr: 0.000025 grad: 0.0998 (0.1080) loss: 0.8612 (0.8583) time: 0.1098 data: 0.0440 max mem: 8299 +Train: [71] [5900/6250] eta: 0:00:40 lr: 0.000025 grad: 0.0938 (0.1080) loss: 0.8679 (0.8583) time: 0.1138 data: 0.0281 max mem: 8299 +Train: [71] [6000/6250] eta: 0:00:29 lr: 0.000025 grad: 0.1032 (0.1080) loss: 0.8586 (0.8583) time: 0.1063 data: 0.0406 max mem: 8299 +Train: [71] [6100/6250] eta: 0:00:17 lr: 0.000025 grad: 0.1102 (0.1080) loss: 0.8576 (0.8583) time: 0.1107 data: 0.0392 max mem: 8299 +Train: [71] [6200/6250] eta: 0:00:05 lr: 0.000025 grad: 0.1020 (0.1079) loss: 0.8594 (0.8583) time: 0.1078 data: 0.0360 max mem: 8299 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1025 (0.1079) loss: 0.8538 (0.8583) time: 0.1095 data: 0.0364 max mem: 8299 +Train: [71] Total time: 0:12:15 (0.1177 s / it) +Averaged stats: lr: 0.000025 grad: 0.1025 (0.1079) loss: 0.8538 (0.8583) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:04:07 loss: 0.8875 (0.8875) time: 3.9977 data: 3.9597 max mem: 8299 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8772 (0.8789) time: 0.1314 data: 0.1059 max mem: 8299 +Eval (hcp-train-subset): [71] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-train-subset): loss: 0.8772 (0.8789) +Eval (hcp-val): [71] [ 0/62] eta: 0:03:55 loss: 0.8790 (0.8790) time: 3.8033 data: 3.7226 max mem: 8299 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8781 (0.8800) time: 0.1002 data: 0.0758 max mem: 8299 +Eval (hcp-val): [71] Total time: 0:00:12 (0.1987 s / it) +Averaged stats (hcp-val): loss: 0.8781 (0.8800) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 8:54:19 lr: 0.000025 grad: 0.0766 (0.0766) loss: 0.8847 (0.8847) time: 5.1295 data: 5.0348 max mem: 8299 +Train: [72] [ 100/6250] eta: 0:16:58 lr: 0.000025 grad: 0.1038 (0.1194) loss: 0.8652 (0.8690) time: 0.1200 data: 0.0344 max mem: 8299 +Train: [72] [ 200/6250] eta: 0:14:33 lr: 0.000025 grad: 0.1137 (0.1218) loss: 0.8663 (0.8655) time: 0.1236 data: 0.0392 max mem: 8299 +Train: [72] [ 300/6250] eta: 0:13:25 lr: 0.000025 grad: 0.1088 (0.1218) loss: 0.8568 (0.8633) time: 0.1122 data: 0.0315 max mem: 8299 +Train: [72] [ 400/6250] eta: 0:12:45 lr: 0.000025 grad: 0.0980 (0.1200) loss: 0.8640 (0.8630) time: 0.1226 data: 0.0467 max mem: 8299 +Train: [72] [ 500/6250] eta: 0:12:15 lr: 0.000025 grad: 0.1061 (0.1185) loss: 0.8560 (0.8622) time: 0.1154 data: 0.0345 max mem: 8299 +Train: [72] [ 600/6250] eta: 0:11:48 lr: 0.000025 grad: 0.1057 (0.1181) loss: 0.8590 (0.8614) time: 0.1129 data: 0.0401 max mem: 8299 +Train: [72] [ 700/6250] eta: 0:11:25 lr: 0.000025 grad: 0.1037 (0.1174) loss: 0.8572 (0.8609) time: 0.1085 data: 0.0284 max mem: 8299 +Train: [72] [ 800/6250] eta: 0:11:03 lr: 0.000025 grad: 0.1069 (0.1168) loss: 0.8558 (0.8604) time: 0.1046 data: 0.0250 max mem: 8299 +Train: [72] [ 900/6250] eta: 0:10:44 lr: 0.000025 grad: 0.1033 (0.1161) loss: 0.8574 (0.8604) time: 0.1085 data: 0.0235 max mem: 8299 +Train: [72] [1000/6250] eta: 0:10:27 lr: 0.000025 grad: 0.1037 (0.1153) loss: 0.8631 (0.8605) time: 0.1142 data: 0.0335 max mem: 8299 +Train: [72] [1100/6250] eta: 0:10:08 lr: 0.000025 grad: 0.1134 (0.1146) loss: 0.8672 (0.8605) time: 0.1096 data: 0.0289 max mem: 8299 +Train: [72] [1200/6250] eta: 0:09:53 lr: 0.000025 grad: 0.1068 (0.1139) loss: 0.8532 (0.8604) time: 0.1103 data: 0.0340 max mem: 8299 +Train: [72] [1300/6250] eta: 0:09:38 lr: 0.000025 grad: 0.1008 (0.1137) loss: 0.8543 (0.8601) time: 0.1200 data: 0.0512 max mem: 8299 +Train: [72] [1400/6250] eta: 0:09:23 lr: 0.000025 grad: 0.1069 (0.1136) loss: 0.8531 (0.8599) time: 0.0887 data: 0.0074 max mem: 8299 +Train: [72] [1500/6250] eta: 0:09:11 lr: 0.000025 grad: 0.1115 (0.1135) loss: 0.8549 (0.8597) time: 0.1204 data: 0.0466 max mem: 8299 +Train: [72] [1600/6250] eta: 0:08:58 lr: 0.000025 grad: 0.1034 (0.1136) loss: 0.8565 (0.8595) time: 0.1190 data: 0.0378 max mem: 8299 +Train: [72] [1700/6250] eta: 0:08:44 lr: 0.000024 grad: 0.1139 (0.1138) loss: 0.8530 (0.8591) time: 0.1150 data: 0.0493 max mem: 8299 +Train: [72] [1800/6250] eta: 0:08:32 lr: 0.000024 grad: 0.0994 (0.1136) loss: 0.8595 (0.8590) time: 0.1069 data: 0.0377 max mem: 8299 +Train: [72] [1900/6250] eta: 0:08:20 lr: 0.000024 grad: 0.1108 (0.1136) loss: 0.8507 (0.8587) time: 0.1047 data: 0.0361 max mem: 8299 +Train: [72] [2000/6250] eta: 0:08:10 lr: 0.000024 grad: 0.1173 (0.1136) loss: 0.8450 (0.8586) time: 0.1560 data: 0.0854 max mem: 8299 +Train: [72] [2100/6250] eta: 0:07:56 lr: 0.000024 grad: 0.1048 (0.1136) loss: 0.8620 (0.8584) time: 0.1082 data: 0.0442 max mem: 8299 +Train: [72] [2200/6250] eta: 0:07:44 lr: 0.000024 grad: 0.1028 (0.1134) loss: 0.8531 (0.8583) time: 0.1148 data: 0.0458 max mem: 8299 +Train: [72] [2300/6250] eta: 0:07:32 lr: 0.000024 grad: 0.1042 (0.1134) loss: 0.8521 (0.8583) time: 0.1158 data: 0.0452 max mem: 8299 +Train: [72] [2400/6250] eta: 0:07:21 lr: 0.000024 grad: 0.1066 (0.1133) loss: 0.8569 (0.8582) time: 0.1348 data: 0.0652 max mem: 8299 +Train: [72] [2500/6250] eta: 0:07:10 lr: 0.000024 grad: 0.1070 (0.1133) loss: 0.8543 (0.8582) time: 0.1184 data: 0.0495 max mem: 8299 +Train: [72] [2600/6250] eta: 0:06:59 lr: 0.000024 grad: 0.0972 (0.1131) loss: 0.8615 (0.8582) time: 0.0923 data: 0.0246 max mem: 8299 +Train: [72] [2700/6250] eta: 0:06:48 lr: 0.000024 grad: 0.1005 (0.1130) loss: 0.8550 (0.8581) time: 0.1377 data: 0.0678 max mem: 8299 +Train: [72] [2800/6250] eta: 0:06:37 lr: 0.000024 grad: 0.1057 (0.1130) loss: 0.8597 (0.8581) time: 0.1048 data: 0.0375 max mem: 8299 +Train: [72] [2900/6250] eta: 0:06:25 lr: 0.000024 grad: 0.1067 (0.1131) loss: 0.8625 (0.8579) time: 0.1252 data: 0.0519 max mem: 8299 +Train: [72] [3000/6250] eta: 0:06:13 lr: 0.000024 grad: 0.1072 (0.1132) loss: 0.8549 (0.8578) time: 0.1090 data: 0.0388 max mem: 8299 +Train: [72] [3100/6250] eta: 0:06:02 lr: 0.000024 grad: 0.0964 (0.1132) loss: 0.8526 (0.8576) time: 0.1064 data: 0.0317 max mem: 8299 +Train: [72] [3200/6250] eta: 0:05:50 lr: 0.000024 grad: 0.1129 (0.1132) loss: 0.8455 (0.8575) time: 0.1045 data: 0.0360 max mem: 8299 +Train: [72] [3300/6250] eta: 0:05:40 lr: 0.000024 grad: 0.1097 (0.1131) loss: 0.8584 (0.8574) time: 0.1018 data: 0.0329 max mem: 8299 +Train: [72] [3400/6250] eta: 0:05:29 lr: 0.000024 grad: 0.1103 (0.1131) loss: 0.8580 (0.8574) time: 0.1847 data: 0.1124 max mem: 8299 +Train: [72] [3500/6250] eta: 0:05:17 lr: 0.000024 grad: 0.1028 (0.1130) loss: 0.8570 (0.8573) time: 0.1275 data: 0.0580 max mem: 8299 +Train: [72] [3600/6250] eta: 0:05:05 lr: 0.000024 grad: 0.1121 (0.1130) loss: 0.8534 (0.8573) time: 0.1180 data: 0.0453 max mem: 8299 +Train: [72] [3700/6250] eta: 0:04:54 lr: 0.000024 grad: 0.1071 (0.1130) loss: 0.8583 (0.8573) time: 0.1178 data: 0.0462 max mem: 8299 +Train: [72] [3800/6250] eta: 0:04:42 lr: 0.000024 grad: 0.1069 (0.1129) loss: 0.8633 (0.8573) time: 0.1152 data: 0.0469 max mem: 8299 +Train: [72] [3900/6250] eta: 0:04:30 lr: 0.000024 grad: 0.1023 (0.1129) loss: 0.8542 (0.8574) time: 0.0926 data: 0.0290 max mem: 8299 +Train: [72] [4000/6250] eta: 0:04:18 lr: 0.000024 grad: 0.1050 (0.1127) loss: 0.8598 (0.8574) time: 0.1061 data: 0.0379 max mem: 8299 +Train: [72] [4100/6250] eta: 0:04:07 lr: 0.000024 grad: 0.1011 (0.1127) loss: 0.8629 (0.8575) time: 0.0954 data: 0.0218 max mem: 8299 +Train: [72] [4200/6250] eta: 0:03:56 lr: 0.000024 grad: 0.1049 (0.1126) loss: 0.8547 (0.8575) time: 0.1656 data: 0.0448 max mem: 8299 +Train: [72] [4300/6250] eta: 0:03:45 lr: 0.000024 grad: 0.1039 (0.1125) loss: 0.8598 (0.8576) time: 0.1021 data: 0.0305 max mem: 8299 +Train: [72] [4400/6250] eta: 0:03:34 lr: 0.000024 grad: 0.1044 (0.1123) loss: 0.8622 (0.8576) time: 0.1127 data: 0.0326 max mem: 8299 +Train: [72] [4500/6250] eta: 0:03:22 lr: 0.000024 grad: 0.1072 (0.1122) loss: 0.8590 (0.8577) time: 0.1149 data: 0.0421 max mem: 8299 +Train: [72] [4600/6250] eta: 0:03:11 lr: 0.000024 grad: 0.1083 (0.1121) loss: 0.8653 (0.8578) time: 0.1618 data: 0.0815 max mem: 8299 +Train: [72] [4700/6250] eta: 0:02:59 lr: 0.000024 grad: 0.1127 (0.1120) loss: 0.8568 (0.8579) time: 0.1023 data: 0.0243 max mem: 8299 +Train: [72] [4800/6250] eta: 0:02:48 lr: 0.000024 grad: 0.1028 (0.1118) loss: 0.8608 (0.8579) time: 0.1081 data: 0.0288 max mem: 8299 +Train: [72] [4900/6250] eta: 0:02:36 lr: 0.000024 grad: 0.0978 (0.1117) loss: 0.8660 (0.8580) time: 0.1386 data: 0.0698 max mem: 8299 +Train: [72] [5000/6250] eta: 0:02:25 lr: 0.000024 grad: 0.1011 (0.1115) loss: 0.8608 (0.8581) time: 0.1222 data: 0.0418 max mem: 8299 +Train: [72] [5100/6250] eta: 0:02:13 lr: 0.000024 grad: 0.1023 (0.1114) loss: 0.8564 (0.8581) time: 0.1417 data: 0.0705 max mem: 8299 +Train: [72] [5200/6250] eta: 0:02:02 lr: 0.000024 grad: 0.1081 (0.1113) loss: 0.8591 (0.8582) time: 0.1480 data: 0.0615 max mem: 8299 +Train: [72] [5300/6250] eta: 0:01:51 lr: 0.000024 grad: 0.0969 (0.1112) loss: 0.8586 (0.8582) time: 0.1351 data: 0.0543 max mem: 8299 +Train: [72] [5400/6250] eta: 0:01:39 lr: 0.000024 grad: 0.1016 (0.1110) loss: 0.8613 (0.8582) time: 0.0976 data: 0.0269 max mem: 8299 +Train: [72] [5500/6250] eta: 0:01:27 lr: 0.000023 grad: 0.1069 (0.1109) loss: 0.8641 (0.8583) time: 0.0979 data: 0.0197 max mem: 8299 +Train: [72] [5600/6250] eta: 0:01:15 lr: 0.000023 grad: 0.1036 (0.1109) loss: 0.8504 (0.8583) time: 0.0968 data: 0.0247 max mem: 8299 +Train: [72] [5700/6250] eta: 0:01:04 lr: 0.000023 grad: 0.1052 (0.1108) loss: 0.8564 (0.8583) time: 0.1077 data: 0.0431 max mem: 8299 +Train: [72] [5800/6250] eta: 0:00:52 lr: 0.000023 grad: 0.1138 (0.1107) loss: 0.8591 (0.8584) time: 0.1000 data: 0.0195 max mem: 8299 +Train: [72] [5900/6250] eta: 0:00:40 lr: 0.000023 grad: 0.1120 (0.1107) loss: 0.8626 (0.8584) time: 0.1115 data: 0.0385 max mem: 8299 +Train: [72] [6000/6250] eta: 0:00:28 lr: 0.000023 grad: 0.1047 (0.1106) loss: 0.8650 (0.8585) time: 0.1040 data: 0.0241 max mem: 8299 +Train: [72] [6100/6250] eta: 0:00:17 lr: 0.000023 grad: 0.0946 (0.1106) loss: 0.8620 (0.8586) time: 0.0946 data: 0.0132 max mem: 8299 +Train: [72] [6200/6250] eta: 0:00:05 lr: 0.000023 grad: 0.1111 (0.1106) loss: 0.8642 (0.8586) time: 0.1184 data: 0.0386 max mem: 8299 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1128 (0.1106) loss: 0.8589 (0.8586) time: 0.1018 data: 0.0319 max mem: 8299 +Train: [72] Total time: 0:12:07 (0.1165 s / it) +Averaged stats: lr: 0.000023 grad: 0.1128 (0.1106) loss: 0.8589 (0.8586) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:05:03 loss: 0.8791 (0.8791) time: 4.8939 data: 4.8656 max mem: 8299 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8712 (0.8751) time: 0.1091 data: 0.0851 max mem: 8299 +Eval (hcp-train-subset): [72] Total time: 0:00:11 (0.1866 s / it) +Averaged stats (hcp-train-subset): loss: 0.8712 (0.8751) +Eval (hcp-val): [72] [ 0/62] eta: 0:03:34 loss: 0.8759 (0.8759) time: 3.4667 data: 3.3980 max mem: 8299 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8796 (0.8803) time: 0.1176 data: 0.0933 max mem: 8299 +Eval (hcp-val): [72] Total time: 0:00:11 (0.1841 s / it) +Averaged stats (hcp-val): loss: 0.8796 (0.8803) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 9:46:45 lr: 0.000023 grad: 0.0797 (0.0797) loss: 0.9025 (0.9025) time: 5.6328 data: 5.5055 max mem: 8299 +Train: [73] [ 100/6250] eta: 0:18:45 lr: 0.000023 grad: 0.1088 (0.1271) loss: 0.8703 (0.8744) time: 0.1402 data: 0.0543 max mem: 8299 +Train: [73] [ 200/6250] eta: 0:15:59 lr: 0.000023 grad: 0.1022 (0.1186) loss: 0.8719 (0.8726) time: 0.1462 data: 0.0729 max mem: 8299 +Train: [73] [ 300/6250] eta: 0:14:43 lr: 0.000023 grad: 0.1004 (0.1145) loss: 0.8599 (0.8701) time: 0.1321 data: 0.0428 max mem: 8299 +Train: [73] [ 400/6250] eta: 0:14:11 lr: 0.000023 grad: 0.1034 (0.1133) loss: 0.8610 (0.8671) time: 0.1497 data: 0.0746 max mem: 8299 +Train: [73] [ 500/6250] eta: 0:13:28 lr: 0.000023 grad: 0.1074 (0.1116) loss: 0.8524 (0.8649) time: 0.1271 data: 0.0427 max mem: 8299 +Train: [73] [ 600/6250] eta: 0:13:04 lr: 0.000023 grad: 0.0934 (0.1110) loss: 0.8605 (0.8635) time: 0.1173 data: 0.0359 max mem: 8299 +Train: [73] [ 700/6250] eta: 0:12:46 lr: 0.000023 grad: 0.1076 (0.1112) loss: 0.8554 (0.8623) time: 0.1200 data: 0.0436 max mem: 8299 +Train: [73] [ 800/6250] eta: 0:12:27 lr: 0.000023 grad: 0.1009 (0.1112) loss: 0.8580 (0.8618) time: 0.1386 data: 0.0649 max mem: 8299 +Train: [73] [ 900/6250] eta: 0:12:09 lr: 0.000023 grad: 0.1037 (0.1113) loss: 0.8570 (0.8611) time: 0.1258 data: 0.0458 max mem: 8299 +Train: [73] [1000/6250] eta: 0:11:50 lr: 0.000023 grad: 0.1126 (0.1114) loss: 0.8515 (0.8605) time: 0.1336 data: 0.0598 max mem: 8299 +Train: [73] [1100/6250] eta: 0:11:34 lr: 0.000023 grad: 0.1175 (0.1118) loss: 0.8529 (0.8599) time: 0.1156 data: 0.0447 max mem: 8299 +Train: [73] [1200/6250] eta: 0:11:22 lr: 0.000023 grad: 0.1112 (0.1118) loss: 0.8630 (0.8596) time: 0.1219 data: 0.0444 max mem: 8299 +Train: [73] [1300/6250] eta: 0:11:07 lr: 0.000023 grad: 0.1102 (0.1119) loss: 0.8562 (0.8592) time: 0.1289 data: 0.0538 max mem: 8299 +Train: [73] [1400/6250] eta: 0:10:52 lr: 0.000023 grad: 0.1109 (0.1121) loss: 0.8502 (0.8587) time: 0.1345 data: 0.0550 max mem: 8299 +Train: [73] [1500/6250] eta: 0:10:37 lr: 0.000023 grad: 0.1095 (0.1124) loss: 0.8513 (0.8584) time: 0.1306 data: 0.0662 max mem: 8299 +Train: [73] [1600/6250] eta: 0:10:24 lr: 0.000023 grad: 0.1007 (0.1123) loss: 0.8568 (0.8582) time: 0.1229 data: 0.0522 max mem: 8299 +Train: [73] [1700/6250] eta: 0:10:08 lr: 0.000023 grad: 0.1022 (0.1123) loss: 0.8617 (0.8579) time: 0.1146 data: 0.0469 max mem: 8299 +Train: [73] [1800/6250] eta: 0:09:52 lr: 0.000023 grad: 0.1029 (0.1122) loss: 0.8543 (0.8579) time: 0.1206 data: 0.0536 max mem: 8299 +Train: [73] [1900/6250] eta: 0:09:41 lr: 0.000023 grad: 0.1025 (0.1121) loss: 0.8568 (0.8578) time: 0.1425 data: 0.0573 max mem: 8299 +Train: [73] [2000/6250] eta: 0:09:28 lr: 0.000023 grad: 0.1050 (0.1120) loss: 0.8683 (0.8581) time: 0.1313 data: 0.0632 max mem: 8299 +Train: [73] [2100/6250] eta: 0:09:12 lr: 0.000023 grad: 0.1014 (0.1118) loss: 0.8638 (0.8581) time: 0.1284 data: 0.0582 max mem: 8299 +Train: [73] [2200/6250] eta: 0:09:02 lr: 0.000023 grad: 0.1041 (0.1118) loss: 0.8570 (0.8581) time: 0.1280 data: 0.0569 max mem: 8299 +Train: [73] [2300/6250] eta: 0:08:48 lr: 0.000023 grad: 0.1068 (0.1117) loss: 0.8593 (0.8580) time: 0.1337 data: 0.0598 max mem: 8299 +Train: [73] [2400/6250] eta: 0:08:36 lr: 0.000023 grad: 0.1049 (0.1115) loss: 0.8614 (0.8580) time: 0.1469 data: 0.0685 max mem: 8299 +Train: [73] [2500/6250] eta: 0:08:21 lr: 0.000023 grad: 0.1089 (0.1113) loss: 0.8568 (0.8581) time: 0.1201 data: 0.0479 max mem: 8299 +Train: [73] [2600/6250] eta: 0:08:08 lr: 0.000023 grad: 0.0994 (0.1112) loss: 0.8656 (0.8580) time: 0.1458 data: 0.0537 max mem: 8299 +Train: [73] [2700/6250] eta: 0:07:55 lr: 0.000023 grad: 0.1054 (0.1111) loss: 0.8575 (0.8580) time: 0.1322 data: 0.0584 max mem: 8299 +Train: [73] [2800/6250] eta: 0:07:43 lr: 0.000023 grad: 0.1041 (0.1109) loss: 0.8597 (0.8581) time: 0.1440 data: 0.0723 max mem: 8299 +Train: [73] [2900/6250] eta: 0:07:29 lr: 0.000023 grad: 0.1185 (0.1109) loss: 0.8504 (0.8580) time: 0.1137 data: 0.0388 max mem: 8299 +Train: [73] [3000/6250] eta: 0:07:15 lr: 0.000023 grad: 0.0985 (0.1109) loss: 0.8643 (0.8580) time: 0.1236 data: 0.0485 max mem: 8299 +Train: [73] [3100/6250] eta: 0:07:01 lr: 0.000023 grad: 0.1069 (0.1109) loss: 0.8642 (0.8581) time: 0.1336 data: 0.0616 max mem: 8299 +Train: [73] [3200/6250] eta: 0:06:48 lr: 0.000022 grad: 0.1007 (0.1108) loss: 0.8674 (0.8582) time: 0.1148 data: 0.0362 max mem: 8299 +Train: [73] [3300/6250] eta: 0:06:36 lr: 0.000022 grad: 0.1136 (0.1108) loss: 0.8612 (0.8584) time: 0.1254 data: 0.0531 max mem: 8299 +Train: [73] [3400/6250] eta: 0:06:22 lr: 0.000022 grad: 0.1059 (0.1108) loss: 0.8644 (0.8585) time: 0.1574 data: 0.0867 max mem: 8299 +Train: [73] [3500/6250] eta: 0:06:08 lr: 0.000022 grad: 0.1063 (0.1108) loss: 0.8632 (0.8585) time: 0.1313 data: 0.0609 max mem: 8299 +Train: [73] [3600/6250] eta: 0:05:55 lr: 0.000022 grad: 0.1157 (0.1108) loss: 0.8627 (0.8586) time: 0.1287 data: 0.0588 max mem: 8299 +Train: [73] [3700/6250] eta: 0:05:41 lr: 0.000022 grad: 0.1081 (0.1109) loss: 0.8567 (0.8586) time: 0.1515 data: 0.0920 max mem: 8299 +Train: [73] [3800/6250] eta: 0:05:28 lr: 0.000022 grad: 0.1196 (0.1111) loss: 0.8556 (0.8586) time: 0.1435 data: 0.0695 max mem: 8299 +Train: [73] [3900/6250] eta: 0:05:14 lr: 0.000022 grad: 0.1131 (0.1111) loss: 0.8573 (0.8586) time: 0.1464 data: 0.0701 max mem: 8299 +Train: [73] [4000/6250] eta: 0:05:01 lr: 0.000022 grad: 0.1099 (0.1112) loss: 0.8546 (0.8586) time: 0.1438 data: 0.0670 max mem: 8299 +Train: [73] [4100/6250] eta: 0:04:48 lr: 0.000022 grad: 0.1170 (0.1114) loss: 0.8499 (0.8586) time: 0.1362 data: 0.0645 max mem: 8299 +Train: [73] [4200/6250] eta: 0:04:35 lr: 0.000022 grad: 0.1134 (0.1116) loss: 0.8608 (0.8586) time: 0.1292 data: 0.0566 max mem: 8299 +Train: [73] [4300/6250] eta: 0:04:21 lr: 0.000022 grad: 0.1069 (0.1116) loss: 0.8572 (0.8586) time: 0.1457 data: 0.0704 max mem: 8299 +Train: [73] [4400/6250] eta: 0:04:08 lr: 0.000022 grad: 0.1049 (0.1117) loss: 0.8582 (0.8585) time: 0.1554 data: 0.0792 max mem: 8299 +Train: [73] [4500/6250] eta: 0:03:55 lr: 0.000022 grad: 0.1144 (0.1117) loss: 0.8514 (0.8585) time: 0.1475 data: 0.0754 max mem: 8299 +Train: [73] [4600/6250] eta: 0:03:41 lr: 0.000022 grad: 0.1035 (0.1118) loss: 0.8584 (0.8585) time: 0.1174 data: 0.0382 max mem: 8299 +Train: [73] [4700/6250] eta: 0:03:27 lr: 0.000022 grad: 0.1038 (0.1118) loss: 0.8636 (0.8585) time: 0.1216 data: 0.0451 max mem: 8299 +Train: [73] [4800/6250] eta: 0:03:14 lr: 0.000022 grad: 0.1068 (0.1118) loss: 0.8608 (0.8585) time: 0.1959 data: 0.1305 max mem: 8299 +Train: [73] [4900/6250] eta: 0:03:02 lr: 0.000022 grad: 0.1105 (0.1118) loss: 0.8597 (0.8586) time: 0.1515 data: 0.0778 max mem: 8299 +Train: [73] [5000/6250] eta: 0:02:48 lr: 0.000022 grad: 0.1128 (0.1118) loss: 0.8593 (0.8586) time: 0.1361 data: 0.0714 max mem: 8299 +Train: [73] [5100/6250] eta: 0:02:35 lr: 0.000022 grad: 0.1037 (0.1118) loss: 0.8617 (0.8586) time: 0.1607 data: 0.0843 max mem: 8299 +Train: [73] [5200/6250] eta: 0:02:21 lr: 0.000022 grad: 0.1096 (0.1119) loss: 0.8577 (0.8586) time: 0.1256 data: 0.0537 max mem: 8299 +Train: [73] [5300/6250] eta: 0:02:08 lr: 0.000022 grad: 0.1039 (0.1119) loss: 0.8592 (0.8586) time: 0.1359 data: 0.0634 max mem: 8299 +Train: [73] [5400/6250] eta: 0:01:54 lr: 0.000022 grad: 0.1077 (0.1120) loss: 0.8631 (0.8585) time: 0.1371 data: 0.0637 max mem: 8299 +Train: [73] [5500/6250] eta: 0:01:41 lr: 0.000022 grad: 0.1105 (0.1121) loss: 0.8519 (0.8585) time: 0.1185 data: 0.0505 max mem: 8299 +Train: [73] [5600/6250] eta: 0:01:27 lr: 0.000022 grad: 0.1110 (0.1121) loss: 0.8637 (0.8585) time: 0.1345 data: 0.0613 max mem: 8299 +Train: [73] [5700/6250] eta: 0:01:14 lr: 0.000022 grad: 0.1129 (0.1123) loss: 0.8524 (0.8584) time: 0.1492 data: 0.0782 max mem: 8299 +Train: [73] [5800/6250] eta: 0:01:00 lr: 0.000022 grad: 0.1109 (0.1123) loss: 0.8473 (0.8583) time: 0.1304 data: 0.0538 max mem: 8299 +Train: [73] [5900/6250] eta: 0:00:47 lr: 0.000022 grad: 0.1024 (0.1123) loss: 0.8602 (0.8583) time: 0.1358 data: 0.0706 max mem: 8299 +Train: [73] [6000/6250] eta: 0:00:33 lr: 0.000022 grad: 0.1097 (0.1123) loss: 0.8619 (0.8583) time: 0.1303 data: 0.0569 max mem: 8299 +Train: [73] [6100/6250] eta: 0:00:20 lr: 0.000022 grad: 0.1064 (0.1124) loss: 0.8588 (0.8583) time: 0.1403 data: 0.0627 max mem: 8299 +Train: [73] [6200/6250] eta: 0:00:06 lr: 0.000022 grad: 0.1046 (0.1124) loss: 0.8626 (0.8583) time: 0.1365 data: 0.0623 max mem: 8299 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1092 (0.1125) loss: 0.8584 (0.8582) time: 0.1223 data: 0.0457 max mem: 8299 +Train: [73] Total time: 0:14:04 (0.1351 s / it) +Averaged stats: lr: 0.000022 grad: 0.1092 (0.1125) loss: 0.8584 (0.8582) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:05:57 loss: 0.8821 (0.8821) time: 5.7629 data: 5.7347 max mem: 8299 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8745 (0.8756) time: 0.1011 data: 0.0771 max mem: 8299 +Eval (hcp-train-subset): [73] Total time: 0:00:12 (0.2069 s / it) +Averaged stats (hcp-train-subset): loss: 0.8745 (0.8756) +Eval (hcp-val): [73] [ 0/62] eta: 0:04:31 loss: 0.8761 (0.8761) time: 4.3850 data: 4.3565 max mem: 8299 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8775 (0.8789) time: 0.1066 data: 0.0825 max mem: 8299 +Eval (hcp-val): [73] Total time: 0:00:11 (0.1841 s / it) +Averaged stats (hcp-val): loss: 0.8775 (0.8789) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 8:41:45 lr: 0.000022 grad: 0.1423 (0.1423) loss: 0.8790 (0.8790) time: 5.0088 data: 4.9044 max mem: 8299 +Train: [74] [ 100/6250] eta: 0:18:21 lr: 0.000022 grad: 0.1117 (0.1381) loss: 0.8663 (0.8749) time: 0.1564 data: 0.0671 max mem: 8299 +Train: [74] [ 200/6250] eta: 0:15:54 lr: 0.000022 grad: 0.0993 (0.1236) loss: 0.8743 (0.8725) time: 0.1381 data: 0.0497 max mem: 8299 +Train: [74] [ 300/6250] eta: 0:14:54 lr: 0.000022 grad: 0.0947 (0.1179) loss: 0.8691 (0.8715) time: 0.1373 data: 0.0505 max mem: 8299 +Train: [74] [ 400/6250] eta: 0:14:06 lr: 0.000022 grad: 0.1087 (0.1158) loss: 0.8691 (0.8701) time: 0.1220 data: 0.0293 max mem: 8299 +Train: [74] [ 500/6250] eta: 0:13:39 lr: 0.000022 grad: 0.1055 (0.1148) loss: 0.8595 (0.8682) time: 0.1499 data: 0.0709 max mem: 8299 +Train: [74] [ 600/6250] eta: 0:13:18 lr: 0.000022 grad: 0.1014 (0.1138) loss: 0.8654 (0.8674) time: 0.1371 data: 0.0555 max mem: 8299 +Train: [74] [ 700/6250] eta: 0:12:50 lr: 0.000022 grad: 0.1068 (0.1138) loss: 0.8719 (0.8664) time: 0.1187 data: 0.0434 max mem: 8299 +Train: [74] [ 800/6250] eta: 0:12:28 lr: 0.000022 grad: 0.1119 (0.1135) loss: 0.8641 (0.8659) time: 0.1334 data: 0.0533 max mem: 8299 +Train: [74] [ 900/6250] eta: 0:12:10 lr: 0.000021 grad: 0.1045 (0.1129) loss: 0.8615 (0.8654) time: 0.1332 data: 0.0542 max mem: 8299 +Train: [74] [1000/6250] eta: 0:11:48 lr: 0.000021 grad: 0.1027 (0.1125) loss: 0.8633 (0.8652) time: 0.1162 data: 0.0368 max mem: 8299 +Train: [74] [1100/6250] eta: 0:11:31 lr: 0.000021 grad: 0.1041 (0.1122) loss: 0.8622 (0.8650) time: 0.1265 data: 0.0481 max mem: 8299 +Train: [74] [1200/6250] eta: 0:11:11 lr: 0.000021 grad: 0.1088 (0.1123) loss: 0.8581 (0.8645) time: 0.1234 data: 0.0429 max mem: 8299 +Train: [74] [1300/6250] eta: 0:10:56 lr: 0.000021 grad: 0.1078 (0.1121) loss: 0.8622 (0.8643) time: 0.1390 data: 0.0568 max mem: 8299 +Train: [74] [1400/6250] eta: 0:10:42 lr: 0.000021 grad: 0.1040 (0.1121) loss: 0.8642 (0.8640) time: 0.1375 data: 0.0648 max mem: 8299 +Train: [74] [1500/6250] eta: 0:10:28 lr: 0.000021 grad: 0.1089 (0.1123) loss: 0.8539 (0.8635) time: 0.1282 data: 0.0512 max mem: 8299 +Train: [74] [1600/6250] eta: 0:10:12 lr: 0.000021 grad: 0.1040 (0.1123) loss: 0.8606 (0.8632) time: 0.1316 data: 0.0505 max mem: 8299 +Train: [74] [1700/6250] eta: 0:09:56 lr: 0.000021 grad: 0.1039 (0.1121) loss: 0.8642 (0.8630) time: 0.1241 data: 0.0355 max mem: 8299 +Train: [74] [1800/6250] eta: 0:09:43 lr: 0.000021 grad: 0.1287 (0.1123) loss: 0.8642 (0.8627) time: 0.1315 data: 0.0516 max mem: 8299 +Train: [74] [1900/6250] eta: 0:09:30 lr: 0.000021 grad: 0.1012 (0.1123) loss: 0.8637 (0.8626) time: 0.1282 data: 0.0427 max mem: 8299 +Train: [74] [2000/6250] eta: 0:09:16 lr: 0.000021 grad: 0.1025 (0.1122) loss: 0.8639 (0.8626) time: 0.1227 data: 0.0561 max mem: 8299 +Train: [74] [2100/6250] eta: 0:09:04 lr: 0.000021 grad: 0.0996 (0.1122) loss: 0.8666 (0.8624) time: 0.1056 data: 0.0351 max mem: 8299 +Train: [74] [2200/6250] eta: 0:08:51 lr: 0.000021 grad: 0.1110 (0.1123) loss: 0.8567 (0.8623) time: 0.1231 data: 0.0579 max mem: 8299 +Train: [74] [2300/6250] eta: 0:08:37 lr: 0.000021 grad: 0.1109 (0.1122) loss: 0.8632 (0.8622) time: 0.1300 data: 0.0568 max mem: 8299 +Train: [74] [2400/6250] eta: 0:08:23 lr: 0.000021 grad: 0.1061 (0.1122) loss: 0.8628 (0.8622) time: 0.1364 data: 0.0647 max mem: 8299 +Train: [74] [2500/6250] eta: 0:08:10 lr: 0.000021 grad: 0.0968 (0.1121) loss: 0.8638 (0.8622) time: 0.1399 data: 0.0628 max mem: 8299 +Train: [74] [2600/6250] eta: 0:07:56 lr: 0.000021 grad: 0.1113 (0.1120) loss: 0.8603 (0.8622) time: 0.1305 data: 0.0532 max mem: 8299 +Train: [74] [2700/6250] eta: 0:07:42 lr: 0.000021 grad: 0.1009 (0.1117) loss: 0.8618 (0.8623) time: 0.1344 data: 0.0477 max mem: 8299 +Train: [74] [2800/6250] eta: 0:07:29 lr: 0.000021 grad: 0.1080 (0.1116) loss: 0.8642 (0.8623) time: 0.1624 data: 0.0898 max mem: 8299 +Train: [74] [2900/6250] eta: 0:07:15 lr: 0.000021 grad: 0.1024 (0.1114) loss: 0.8655 (0.8623) time: 0.1356 data: 0.0585 max mem: 8299 +Train: [74] [3000/6250] eta: 0:07:03 lr: 0.000021 grad: 0.0986 (0.1113) loss: 0.8616 (0.8623) time: 0.1463 data: 0.0682 max mem: 8299 +Train: [74] [3100/6250] eta: 0:06:50 lr: 0.000021 grad: 0.1091 (0.1112) loss: 0.8652 (0.8623) time: 0.1361 data: 0.0645 max mem: 8299 +Train: [74] [3200/6250] eta: 0:06:36 lr: 0.000021 grad: 0.1064 (0.1113) loss: 0.8595 (0.8622) time: 0.1247 data: 0.0430 max mem: 8299 +Train: [74] [3300/6250] eta: 0:06:23 lr: 0.000021 grad: 0.1020 (0.1112) loss: 0.8644 (0.8622) time: 0.1345 data: 0.0613 max mem: 8299 +Train: [74] [3400/6250] eta: 0:06:10 lr: 0.000021 grad: 0.1031 (0.1111) loss: 0.8612 (0.8622) time: 0.1345 data: 0.0671 max mem: 8299 +Train: [74] [3500/6250] eta: 0:05:57 lr: 0.000021 grad: 0.1087 (0.1111) loss: 0.8573 (0.8621) time: 0.1471 data: 0.0807 max mem: 8299 +Train: [74] [3600/6250] eta: 0:05:44 lr: 0.000021 grad: 0.1006 (0.1110) loss: 0.8620 (0.8621) time: 0.1510 data: 0.0818 max mem: 8299 +Train: [74] [3700/6250] eta: 0:05:32 lr: 0.000021 grad: 0.1049 (0.1109) loss: 0.8604 (0.8621) time: 0.1316 data: 0.0452 max mem: 8299 +Train: [74] [3800/6250] eta: 0:05:20 lr: 0.000021 grad: 0.1041 (0.1109) loss: 0.8569 (0.8620) time: 0.1472 data: 0.0815 max mem: 8299 +Train: [74] [3900/6250] eta: 0:05:06 lr: 0.000021 grad: 0.1019 (0.1109) loss: 0.8641 (0.8620) time: 0.0984 data: 0.0243 max mem: 8299 +Train: [74] [4000/6250] eta: 0:04:53 lr: 0.000021 grad: 0.1021 (0.1108) loss: 0.8599 (0.8620) time: 0.1250 data: 0.0558 max mem: 8299 +Train: [74] [4100/6250] eta: 0:04:40 lr: 0.000021 grad: 0.1052 (0.1108) loss: 0.8618 (0.8619) time: 0.1456 data: 0.0625 max mem: 8299 +Train: [74] [4200/6250] eta: 0:04:27 lr: 0.000021 grad: 0.0990 (0.1108) loss: 0.8612 (0.8618) time: 0.1423 data: 0.0719 max mem: 8299 +Train: [74] [4300/6250] eta: 0:04:14 lr: 0.000021 grad: 0.1047 (0.1108) loss: 0.8616 (0.8618) time: 0.1412 data: 0.0637 max mem: 8299 +Train: [74] [4400/6250] eta: 0:04:01 lr: 0.000021 grad: 0.1199 (0.1108) loss: 0.8548 (0.8617) time: 0.1304 data: 0.0431 max mem: 8299 +Train: [74] [4500/6250] eta: 0:03:48 lr: 0.000021 grad: 0.1032 (0.1108) loss: 0.8629 (0.8617) time: 0.1445 data: 0.0731 max mem: 8299 +Train: [74] [4600/6250] eta: 0:03:35 lr: 0.000021 grad: 0.1122 (0.1109) loss: 0.8554 (0.8617) time: 0.1418 data: 0.0686 max mem: 8299 +Train: [74] [4700/6250] eta: 0:03:22 lr: 0.000021 grad: 0.1115 (0.1109) loss: 0.8568 (0.8616) time: 0.1350 data: 0.0664 max mem: 8299 +Train: [74] [4800/6250] eta: 0:03:09 lr: 0.000021 grad: 0.1103 (0.1109) loss: 0.8514 (0.8616) time: 0.2235 data: 0.1336 max mem: 8299 +Train: [74] [4900/6250] eta: 0:02:57 lr: 0.000020 grad: 0.1050 (0.1109) loss: 0.8602 (0.8615) time: 0.1484 data: 0.0753 max mem: 8299 +Train: [74] [5000/6250] eta: 0:02:44 lr: 0.000020 grad: 0.1091 (0.1110) loss: 0.8567 (0.8615) time: 0.1337 data: 0.0593 max mem: 8299 +Train: [74] [5100/6250] eta: 0:02:31 lr: 0.000020 grad: 0.1148 (0.1111) loss: 0.8584 (0.8613) time: 0.1329 data: 0.0627 max mem: 8299 +Train: [74] [5200/6250] eta: 0:02:18 lr: 0.000020 grad: 0.1033 (0.1110) loss: 0.8600 (0.8613) time: 0.1414 data: 0.0626 max mem: 8299 +Train: [74] [5300/6250] eta: 0:02:05 lr: 0.000020 grad: 0.1059 (0.1110) loss: 0.8611 (0.8613) time: 0.1432 data: 0.0770 max mem: 8299 +Train: [74] [5400/6250] eta: 0:01:52 lr: 0.000020 grad: 0.1108 (0.1110) loss: 0.8602 (0.8614) time: 0.1262 data: 0.0545 max mem: 8299 +Train: [74] [5500/6250] eta: 0:01:38 lr: 0.000020 grad: 0.1064 (0.1109) loss: 0.8640 (0.8614) time: 0.1418 data: 0.0640 max mem: 8299 +Train: [74] [5600/6250] eta: 0:01:25 lr: 0.000020 grad: 0.1014 (0.1110) loss: 0.8564 (0.8614) time: 0.1371 data: 0.0635 max mem: 8299 +Train: [74] [5700/6250] eta: 0:01:12 lr: 0.000020 grad: 0.0998 (0.1110) loss: 0.8668 (0.8614) time: 0.1342 data: 0.0571 max mem: 8299 +Train: [74] [5800/6250] eta: 0:00:59 lr: 0.000020 grad: 0.1123 (0.1110) loss: 0.8613 (0.8614) time: 0.1197 data: 0.0450 max mem: 8299 +Train: [74] [5900/6250] eta: 0:00:45 lr: 0.000020 grad: 0.1196 (0.1111) loss: 0.8653 (0.8614) time: 0.1028 data: 0.0236 max mem: 8299 +Train: [74] [6000/6250] eta: 0:00:32 lr: 0.000020 grad: 0.1208 (0.1111) loss: 0.8578 (0.8613) time: 0.1310 data: 0.0588 max mem: 8299 +Train: [74] [6100/6250] eta: 0:00:19 lr: 0.000020 grad: 0.1133 (0.1112) loss: 0.8567 (0.8613) time: 0.1209 data: 0.0465 max mem: 8299 +Train: [74] [6200/6250] eta: 0:00:06 lr: 0.000020 grad: 0.1214 (0.1114) loss: 0.8560 (0.8612) time: 0.1236 data: 0.0515 max mem: 8299 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1255 (0.1114) loss: 0.8511 (0.8611) time: 0.1153 data: 0.0443 max mem: 8299 +Train: [74] Total time: 0:13:44 (0.1320 s / it) +Averaged stats: lr: 0.000020 grad: 0.1255 (0.1114) loss: 0.8511 (0.8611) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:03:55 loss: 0.8827 (0.8827) time: 3.8003 data: 3.7266 max mem: 8299 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8750 (0.8768) time: 0.1102 data: 0.0859 max mem: 8299 +Eval (hcp-train-subset): [74] Total time: 0:00:12 (0.2083 s / it) +Averaged stats (hcp-train-subset): loss: 0.8750 (0.8768) +Making plots (hcp-train-subset): example=30 +Eval (hcp-val): [74] [ 0/62] eta: 0:04:55 loss: 0.8802 (0.8802) time: 4.7592 data: 4.7298 max mem: 8299 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8784 (0.8806) time: 0.0928 data: 0.0676 max mem: 8299 +Eval (hcp-val): [74] Total time: 0:00:12 (0.2053 s / it) +Averaged stats (hcp-val): loss: 0.8784 (0.8806) +Making plots (hcp-val): example=48 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 7:05:16 lr: 0.000020 grad: 0.0489 (0.0489) loss: 0.8970 (0.8970) time: 4.0826 data: 3.8425 max mem: 8299 +Train: [75] [ 100/6250] eta: 0:18:27 lr: 0.000020 grad: 0.1237 (0.1348) loss: 0.8781 (0.8794) time: 0.1281 data: 0.0312 max mem: 8299 +Train: [75] [ 200/6250] eta: 0:15:46 lr: 0.000020 grad: 0.0934 (0.1233) loss: 0.8714 (0.8736) time: 0.1474 data: 0.0655 max mem: 8299 +Train: [75] [ 300/6250] eta: 0:14:52 lr: 0.000020 grad: 0.0974 (0.1176) loss: 0.8706 (0.8717) time: 0.1331 data: 0.0483 max mem: 8299 +Train: [75] [ 400/6250] eta: 0:14:15 lr: 0.000020 grad: 0.1074 (0.1170) loss: 0.8636 (0.8693) time: 0.1329 data: 0.0535 max mem: 8299 +Train: [75] [ 500/6250] eta: 0:13:50 lr: 0.000020 grad: 0.1113 (0.1179) loss: 0.8627 (0.8674) time: 0.1342 data: 0.0545 max mem: 8299 +Train: [75] [ 600/6250] eta: 0:13:22 lr: 0.000020 grad: 0.1163 (0.1179) loss: 0.8604 (0.8658) time: 0.1076 data: 0.0325 max mem: 8299 +Train: [75] [ 700/6250] eta: 0:13:00 lr: 0.000020 grad: 0.1130 (0.1178) loss: 0.8574 (0.8648) time: 0.1497 data: 0.0778 max mem: 8299 +Train: [75] [ 800/6250] eta: 0:12:36 lr: 0.000020 grad: 0.0996 (0.1173) loss: 0.8564 (0.8636) time: 0.1211 data: 0.0406 max mem: 8299 +Train: [75] [ 900/6250] eta: 0:12:20 lr: 0.000020 grad: 0.1158 (0.1169) loss: 0.8510 (0.8632) time: 0.1261 data: 0.0450 max mem: 8299 +Train: [75] [1000/6250] eta: 0:11:59 lr: 0.000020 grad: 0.1223 (0.1165) loss: 0.8573 (0.8629) time: 0.1257 data: 0.0458 max mem: 8299 +Train: [75] [1100/6250] eta: 0:11:38 lr: 0.000020 grad: 0.1113 (0.1165) loss: 0.8547 (0.8623) time: 0.1281 data: 0.0626 max mem: 8299 +Train: [75] [1200/6250] eta: 0:11:25 lr: 0.000020 grad: 0.1030 (0.1160) loss: 0.8586 (0.8618) time: 0.1288 data: 0.0501 max mem: 8299 +Train: [75] [1300/6250] eta: 0:11:04 lr: 0.000020 grad: 0.1099 (0.1158) loss: 0.8572 (0.8616) time: 0.1209 data: 0.0516 max mem: 8299 +Train: [75] [1400/6250] eta: 0:10:47 lr: 0.000020 grad: 0.1166 (0.1159) loss: 0.8589 (0.8611) time: 0.1069 data: 0.0371 max mem: 8299 +Train: [75] [1500/6250] eta: 0:10:34 lr: 0.000020 grad: 0.1105 (0.1159) loss: 0.8509 (0.8607) time: 0.1265 data: 0.0459 max mem: 8299 +Train: [75] [1600/6250] eta: 0:10:19 lr: 0.000020 grad: 0.1111 (0.1158) loss: 0.8503 (0.8605) time: 0.1245 data: 0.0486 max mem: 8299 +Train: [75] [1700/6250] eta: 0:10:05 lr: 0.000020 grad: 0.1127 (0.1156) loss: 0.8517 (0.8603) time: 0.1298 data: 0.0543 max mem: 8299 +Train: [75] [1800/6250] eta: 0:09:49 lr: 0.000020 grad: 0.1137 (0.1156) loss: 0.8563 (0.8602) time: 0.1169 data: 0.0484 max mem: 8299 +Train: [75] [1900/6250] eta: 0:09:34 lr: 0.000020 grad: 0.1219 (0.1154) loss: 0.8567 (0.8599) time: 0.1390 data: 0.0699 max mem: 8299 +Train: [75] [2000/6250] eta: 0:09:19 lr: 0.000020 grad: 0.1079 (0.1153) loss: 0.8588 (0.8598) time: 0.1322 data: 0.0607 max mem: 8299 +Train: [75] [2100/6250] eta: 0:09:04 lr: 0.000020 grad: 0.1078 (0.1152) loss: 0.8540 (0.8597) time: 0.1045 data: 0.0335 max mem: 8299 +Train: [75] [2200/6250] eta: 0:08:49 lr: 0.000020 grad: 0.1137 (0.1151) loss: 0.8595 (0.8594) time: 0.1258 data: 0.0551 max mem: 8299 +Train: [75] [2300/6250] eta: 0:08:37 lr: 0.000020 grad: 0.1075 (0.1150) loss: 0.8491 (0.8591) time: 0.1286 data: 0.0457 max mem: 8299 +Train: [75] [2400/6250] eta: 0:08:22 lr: 0.000020 grad: 0.1132 (0.1149) loss: 0.8548 (0.8589) time: 0.1192 data: 0.0527 max mem: 8299 +Train: [75] [2500/6250] eta: 0:08:08 lr: 0.000020 grad: 0.1014 (0.1147) loss: 0.8660 (0.8589) time: 0.1177 data: 0.0389 max mem: 8299 +Train: [75] [2600/6250] eta: 0:07:55 lr: 0.000020 grad: 0.1023 (0.1146) loss: 0.8593 (0.8589) time: 0.1238 data: 0.0565 max mem: 8299 +Train: [75] [2700/6250] eta: 0:07:41 lr: 0.000020 grad: 0.1056 (0.1144) loss: 0.8450 (0.8588) time: 0.1276 data: 0.0570 max mem: 8299 +Train: [75] [2800/6250] eta: 0:07:28 lr: 0.000019 grad: 0.1068 (0.1142) loss: 0.8656 (0.8589) time: 0.1440 data: 0.0784 max mem: 8299 +Train: [75] [2900/6250] eta: 0:07:14 lr: 0.000019 grad: 0.1119 (0.1142) loss: 0.8552 (0.8588) time: 0.1208 data: 0.0524 max mem: 8299 +Train: [75] [3000/6250] eta: 0:07:00 lr: 0.000019 grad: 0.1097 (0.1141) loss: 0.8652 (0.8589) time: 0.1219 data: 0.0545 max mem: 8299 +Train: [75] [3100/6250] eta: 0:06:46 lr: 0.000019 grad: 0.1143 (0.1141) loss: 0.8582 (0.8589) time: 0.1254 data: 0.0519 max mem: 8299 +Train: [75] [3200/6250] eta: 0:06:33 lr: 0.000019 grad: 0.1186 (0.1140) loss: 0.8623 (0.8589) time: 0.1185 data: 0.0437 max mem: 8299 +Train: [75] [3300/6250] eta: 0:06:20 lr: 0.000019 grad: 0.1021 (0.1139) loss: 0.8606 (0.8589) time: 0.1325 data: 0.0656 max mem: 8299 +Train: [75] [3400/6250] eta: 0:06:06 lr: 0.000019 grad: 0.1093 (0.1139) loss: 0.8574 (0.8588) time: 0.1122 data: 0.0387 max mem: 8299 +Train: [75] [3500/6250] eta: 0:05:52 lr: 0.000019 grad: 0.1032 (0.1137) loss: 0.8623 (0.8588) time: 0.1116 data: 0.0363 max mem: 8299 +Train: [75] [3600/6250] eta: 0:05:39 lr: 0.000019 grad: 0.1101 (0.1137) loss: 0.8632 (0.8587) time: 0.1150 data: 0.0396 max mem: 8299 +Train: [75] [3700/6250] eta: 0:05:25 lr: 0.000019 grad: 0.1088 (0.1137) loss: 0.8620 (0.8587) time: 0.1102 data: 0.0428 max mem: 8299 +Train: [75] [3800/6250] eta: 0:05:12 lr: 0.000019 grad: 0.1074 (0.1137) loss: 0.8583 (0.8587) time: 0.1106 data: 0.0354 max mem: 8299 +Train: [75] [3900/6250] eta: 0:04:58 lr: 0.000019 grad: 0.1131 (0.1136) loss: 0.8604 (0.8587) time: 0.1112 data: 0.0426 max mem: 8299 +Train: [75] [4000/6250] eta: 0:04:46 lr: 0.000019 grad: 0.1160 (0.1135) loss: 0.8580 (0.8587) time: 0.1355 data: 0.0359 max mem: 8299 +Train: [75] [4100/6250] eta: 0:04:33 lr: 0.000019 grad: 0.1073 (0.1135) loss: 0.8564 (0.8587) time: 0.1378 data: 0.0782 max mem: 8299 +Train: [75] [4200/6250] eta: 0:04:20 lr: 0.000019 grad: 0.1055 (0.1135) loss: 0.8647 (0.8587) time: 0.1126 data: 0.0444 max mem: 8299 +Train: [75] [4300/6250] eta: 0:04:07 lr: 0.000019 grad: 0.1108 (0.1134) loss: 0.8569 (0.8588) time: 0.1280 data: 0.0593 max mem: 8299 +Train: [75] [4400/6250] eta: 0:03:54 lr: 0.000019 grad: 0.1059 (0.1134) loss: 0.8615 (0.8587) time: 0.1279 data: 0.0436 max mem: 8299 +Train: [75] [4500/6250] eta: 0:03:41 lr: 0.000019 grad: 0.1104 (0.1133) loss: 0.8634 (0.8588) time: 0.1427 data: 0.0729 max mem: 8299 +Train: [75] [4600/6250] eta: 0:03:29 lr: 0.000019 grad: 0.1083 (0.1133) loss: 0.8681 (0.8589) time: 0.1348 data: 0.0605 max mem: 8299 +Train: [75] [4700/6250] eta: 0:03:16 lr: 0.000019 grad: 0.1084 (0.1132) loss: 0.8668 (0.8590) time: 0.1181 data: 0.0546 max mem: 8299 +Train: [75] [4800/6250] eta: 0:03:04 lr: 0.000019 grad: 0.1100 (0.1132) loss: 0.8630 (0.8590) time: 0.1422 data: 0.0665 max mem: 8299 +Train: [75] [4900/6250] eta: 0:02:52 lr: 0.000019 grad: 0.1122 (0.1132) loss: 0.8687 (0.8591) time: 0.1533 data: 0.0787 max mem: 8299 +Train: [75] [5000/6250] eta: 0:02:39 lr: 0.000019 grad: 0.1047 (0.1131) loss: 0.8643 (0.8591) time: 0.1332 data: 0.0592 max mem: 8299 +Train: [75] [5100/6250] eta: 0:02:27 lr: 0.000019 grad: 0.1164 (0.1130) loss: 0.8577 (0.8591) time: 0.1443 data: 0.0682 max mem: 8299 +Train: [75] [5200/6250] eta: 0:02:14 lr: 0.000019 grad: 0.1069 (0.1130) loss: 0.8605 (0.8592) time: 0.1273 data: 0.0486 max mem: 8299 +Train: [75] [5300/6250] eta: 0:02:02 lr: 0.000019 grad: 0.1034 (0.1129) loss: 0.8587 (0.8592) time: 0.1385 data: 0.0616 max mem: 8299 +Train: [75] [5400/6250] eta: 0:01:49 lr: 0.000019 grad: 0.1011 (0.1127) loss: 0.8629 (0.8592) time: 0.1398 data: 0.0665 max mem: 8299 +Train: [75] [5500/6250] eta: 0:01:36 lr: 0.000019 grad: 0.1013 (0.1126) loss: 0.8632 (0.8593) time: 0.1420 data: 0.0639 max mem: 8299 +Train: [75] [5600/6250] eta: 0:01:23 lr: 0.000019 grad: 0.1036 (0.1125) loss: 0.8612 (0.8593) time: 0.1507 data: 0.0843 max mem: 8299 +Train: [75] [5700/6250] eta: 0:01:11 lr: 0.000019 grad: 0.1006 (0.1124) loss: 0.8622 (0.8593) time: 0.1427 data: 0.0692 max mem: 8299 +Train: [75] [5800/6250] eta: 0:00:58 lr: 0.000019 grad: 0.1068 (0.1123) loss: 0.8635 (0.8594) time: 0.1087 data: 0.0393 max mem: 8299 +Train: [75] [5900/6250] eta: 0:00:45 lr: 0.000019 grad: 0.1039 (0.1122) loss: 0.8646 (0.8594) time: 0.1580 data: 0.0865 max mem: 8299 +Train: [75] [6000/6250] eta: 0:00:32 lr: 0.000019 grad: 0.1092 (0.1121) loss: 0.8654 (0.8595) time: 0.1423 data: 0.0621 max mem: 8299 +Train: [75] [6100/6250] eta: 0:00:19 lr: 0.000019 grad: 0.1095 (0.1121) loss: 0.8633 (0.8595) time: 0.1319 data: 0.0631 max mem: 8299 +Train: [75] [6200/6250] eta: 0:00:06 lr: 0.000019 grad: 0.1041 (0.1120) loss: 0.8600 (0.8596) time: 0.1287 data: 0.0506 max mem: 8299 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1053 (0.1119) loss: 0.8642 (0.8597) time: 0.1388 data: 0.0638 max mem: 8299 +Train: [75] Total time: 0:13:42 (0.1316 s / it) +Averaged stats: lr: 0.000019 grad: 0.1053 (0.1119) loss: 0.8642 (0.8597) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:06:13 loss: 0.8833 (0.8833) time: 6.0165 data: 5.9850 max mem: 8299 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8757 (0.8762) time: 0.1420 data: 0.1163 max mem: 8299 +Eval (hcp-train-subset): [75] Total time: 0:00:14 (0.2393 s / it) +Averaged stats (hcp-train-subset): loss: 0.8757 (0.8762) +Eval (hcp-val): [75] [ 0/62] eta: 0:06:05 loss: 0.8767 (0.8767) time: 5.8999 data: 5.8595 max mem: 8299 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8781 (0.8800) time: 0.1037 data: 0.0792 max mem: 8299 +Eval (hcp-val): [75] Total time: 0:00:14 (0.2326 s / it) +Averaged stats (hcp-val): loss: 0.8781 (0.8800) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 8:16:56 lr: 0.000019 grad: 0.0582 (0.0582) loss: 0.9077 (0.9077) time: 4.7707 data: 4.5141 max mem: 8299 +Train: [76] [ 100/6250] eta: 0:20:24 lr: 0.000019 grad: 0.1161 (0.1592) loss: 0.8744 (0.8697) time: 0.1681 data: 0.0868 max mem: 8299 +Train: [76] [ 200/6250] eta: 0:16:57 lr: 0.000019 grad: 0.1052 (0.1402) loss: 0.8657 (0.8676) time: 0.1415 data: 0.0561 max mem: 8299 +Train: [76] [ 300/6250] eta: 0:15:56 lr: 0.000019 grad: 0.0914 (0.1290) loss: 0.8768 (0.8682) time: 0.1416 data: 0.0653 max mem: 8299 +Train: [76] [ 400/6250] eta: 0:15:29 lr: 0.000019 grad: 0.0952 (0.1215) loss: 0.8736 (0.8688) time: 0.1485 data: 0.0599 max mem: 8299 +Train: [76] [ 500/6250] eta: 0:14:55 lr: 0.000019 grad: 0.1093 (0.1184) loss: 0.8648 (0.8685) time: 0.1482 data: 0.0613 max mem: 8299 +Train: [76] [ 600/6250] eta: 0:14:29 lr: 0.000019 grad: 0.0944 (0.1156) loss: 0.8655 (0.8679) time: 0.1598 data: 0.0804 max mem: 8299 +Train: [76] [ 700/6250] eta: 0:14:05 lr: 0.000019 grad: 0.1040 (0.1142) loss: 0.8637 (0.8673) time: 0.1383 data: 0.0631 max mem: 8299 +Train: [76] [ 800/6250] eta: 0:13:46 lr: 0.000018 grad: 0.1075 (0.1133) loss: 0.8588 (0.8667) time: 0.1575 data: 0.0802 max mem: 8299 +Train: [76] [ 900/6250] eta: 0:13:26 lr: 0.000018 grad: 0.1016 (0.1123) loss: 0.8597 (0.8665) time: 0.1591 data: 0.0820 max mem: 8299 +Train: [76] [1000/6250] eta: 0:13:03 lr: 0.000018 grad: 0.1066 (0.1116) loss: 0.8672 (0.8666) time: 0.1253 data: 0.0519 max mem: 8299 +Train: [76] [1100/6250] eta: 0:12:43 lr: 0.000018 grad: 0.1057 (0.1115) loss: 0.8687 (0.8664) time: 0.1603 data: 0.0904 max mem: 8299 +Train: [76] [1200/6250] eta: 0:12:23 lr: 0.000018 grad: 0.1090 (0.1115) loss: 0.8618 (0.8660) time: 0.1809 data: 0.0866 max mem: 8299 +Train: [76] [1300/6250] eta: 0:12:11 lr: 0.000018 grad: 0.1049 (0.1116) loss: 0.8589 (0.8655) time: 0.1466 data: 0.0653 max mem: 8299 +Train: [76] [1400/6250] eta: 0:11:52 lr: 0.000018 grad: 0.0992 (0.1118) loss: 0.8565 (0.8652) time: 0.1297 data: 0.0545 max mem: 8299 +Train: [76] [1500/6250] eta: 0:11:31 lr: 0.000018 grad: 0.1084 (0.1116) loss: 0.8578 (0.8650) time: 0.1236 data: 0.0478 max mem: 8299 +Train: [76] [1600/6250] eta: 0:11:18 lr: 0.000018 grad: 0.1067 (0.1116) loss: 0.8615 (0.8648) time: 0.1680 data: 0.0867 max mem: 8299 +Train: [76] [1700/6250] eta: 0:11:07 lr: 0.000018 grad: 0.1000 (0.1114) loss: 0.8631 (0.8645) time: 0.1732 data: 0.0959 max mem: 8299 +Train: [76] [1800/6250] eta: 0:10:51 lr: 0.000018 grad: 0.1113 (0.1110) loss: 0.8551 (0.8643) time: 0.1159 data: 0.0510 max mem: 8299 +Train: [76] [1900/6250] eta: 0:10:34 lr: 0.000018 grad: 0.1133 (0.1110) loss: 0.8643 (0.8641) time: 0.1331 data: 0.0606 max mem: 8299 +Train: [76] [2000/6250] eta: 0:10:17 lr: 0.000018 grad: 0.1134 (0.1109) loss: 0.8537 (0.8639) time: 0.1393 data: 0.0745 max mem: 8299 +Train: [76] [2100/6250] eta: 0:10:03 lr: 0.000018 grad: 0.1119 (0.1109) loss: 0.8563 (0.8635) time: 0.1589 data: 0.0823 max mem: 8299 +Train: [76] [2200/6250] eta: 0:09:50 lr: 0.000018 grad: 0.1073 (0.1109) loss: 0.8646 (0.8633) time: 0.1380 data: 0.0622 max mem: 8299 +Train: [76] [2300/6250] eta: 0:09:35 lr: 0.000018 grad: 0.1159 (0.1110) loss: 0.8524 (0.8631) time: 0.1384 data: 0.0613 max mem: 8299 +Train: [76] [2400/6250] eta: 0:09:20 lr: 0.000018 grad: 0.1144 (0.1110) loss: 0.8577 (0.8630) time: 0.1644 data: 0.0910 max mem: 8299 +Train: [76] [2500/6250] eta: 0:09:07 lr: 0.000018 grad: 0.1069 (0.1110) loss: 0.8621 (0.8629) time: 0.1760 data: 0.1048 max mem: 8299 +Train: [76] [2600/6250] eta: 0:08:53 lr: 0.000018 grad: 0.1051 (0.1110) loss: 0.8590 (0.8627) time: 0.1721 data: 0.0985 max mem: 8299 +Train: [76] [2700/6250] eta: 0:08:38 lr: 0.000018 grad: 0.1108 (0.1109) loss: 0.8524 (0.8626) time: 0.1318 data: 0.0570 max mem: 8299 +Train: [76] [2800/6250] eta: 0:08:22 lr: 0.000018 grad: 0.1143 (0.1110) loss: 0.8566 (0.8623) time: 0.1447 data: 0.0721 max mem: 8299 +Train: [76] [2900/6250] eta: 0:08:07 lr: 0.000018 grad: 0.1077 (0.1110) loss: 0.8598 (0.8621) time: 0.1499 data: 0.0788 max mem: 8299 +Train: [76] [3000/6250] eta: 0:07:52 lr: 0.000018 grad: 0.1074 (0.1111) loss: 0.8609 (0.8620) time: 0.1307 data: 0.0563 max mem: 8299 +Train: [76] [3100/6250] eta: 0:07:37 lr: 0.000018 grad: 0.1083 (0.1111) loss: 0.8595 (0.8619) time: 0.1399 data: 0.0647 max mem: 8299 +Train: [76] [3200/6250] eta: 0:07:22 lr: 0.000018 grad: 0.1045 (0.1113) loss: 0.8583 (0.8617) time: 0.1342 data: 0.0533 max mem: 8299 +Train: [76] [3300/6250] eta: 0:07:07 lr: 0.000018 grad: 0.1083 (0.1115) loss: 0.8610 (0.8616) time: 0.1433 data: 0.0634 max mem: 8299 +Train: [76] [3400/6250] eta: 0:06:52 lr: 0.000018 grad: 0.1089 (0.1115) loss: 0.8604 (0.8615) time: 0.1473 data: 0.0838 max mem: 8299 +Train: [76] [3500/6250] eta: 0:06:38 lr: 0.000018 grad: 0.1021 (0.1116) loss: 0.8628 (0.8614) time: 0.1553 data: 0.0766 max mem: 8299 +Train: [76] [3600/6250] eta: 0:06:23 lr: 0.000018 grad: 0.1137 (0.1116) loss: 0.8640 (0.8613) time: 0.1364 data: 0.0648 max mem: 8299 +Train: [76] [3700/6250] eta: 0:06:08 lr: 0.000018 grad: 0.1152 (0.1117) loss: 0.8575 (0.8613) time: 0.1331 data: 0.0531 max mem: 8299 +Train: [76] [3800/6250] eta: 0:05:54 lr: 0.000018 grad: 0.1217 (0.1119) loss: 0.8537 (0.8611) time: 0.1708 data: 0.0993 max mem: 8299 +Train: [76] [3900/6250] eta: 0:05:40 lr: 0.000018 grad: 0.1152 (0.1120) loss: 0.8546 (0.8610) time: 0.1398 data: 0.0685 max mem: 8299 +Train: [76] [4000/6250] eta: 0:05:26 lr: 0.000018 grad: 0.1099 (0.1120) loss: 0.8530 (0.8610) time: 0.1570 data: 0.0832 max mem: 8299 +Train: [76] [4100/6250] eta: 0:05:11 lr: 0.000018 grad: 0.1147 (0.1121) loss: 0.8578 (0.8609) time: 0.1439 data: 0.0665 max mem: 8299 +Train: [76] [4200/6250] eta: 0:04:56 lr: 0.000018 grad: 0.1177 (0.1122) loss: 0.8604 (0.8608) time: 0.1235 data: 0.0416 max mem: 8299 +Train: [76] [4300/6250] eta: 0:04:42 lr: 0.000018 grad: 0.1051 (0.1122) loss: 0.8598 (0.8608) time: 0.1655 data: 0.0966 max mem: 8299 +Train: [76] [4400/6250] eta: 0:04:27 lr: 0.000018 grad: 0.1054 (0.1122) loss: 0.8598 (0.8609) time: 0.1494 data: 0.0739 max mem: 8299 +Train: [76] [4500/6250] eta: 0:04:13 lr: 0.000018 grad: 0.1114 (0.1121) loss: 0.8646 (0.8609) time: 0.1419 data: 0.0677 max mem: 8299 +Train: [76] [4600/6250] eta: 0:03:58 lr: 0.000018 grad: 0.1170 (0.1122) loss: 0.8614 (0.8610) time: 0.1367 data: 0.0682 max mem: 8299 +Train: [76] [4700/6250] eta: 0:03:44 lr: 0.000018 grad: 0.1173 (0.1122) loss: 0.8636 (0.8610) time: 0.1814 data: 0.1182 max mem: 8299 +Train: [76] [4800/6250] eta: 0:03:30 lr: 0.000018 grad: 0.1120 (0.1122) loss: 0.8591 (0.8610) time: 0.1405 data: 0.0678 max mem: 8299 +Train: [76] [4900/6250] eta: 0:03:16 lr: 0.000018 grad: 0.1131 (0.1122) loss: 0.8623 (0.8611) time: 0.1386 data: 0.0671 max mem: 8299 +Train: [76] [5000/6250] eta: 0:03:01 lr: 0.000018 grad: 0.1097 (0.1123) loss: 0.8572 (0.8610) time: 0.1463 data: 0.0744 max mem: 8299 +Train: [76] [5100/6250] eta: 0:02:47 lr: 0.000017 grad: 0.1016 (0.1122) loss: 0.8608 (0.8611) time: 0.1330 data: 0.0606 max mem: 8299 +Train: [76] [5200/6250] eta: 0:02:32 lr: 0.000017 grad: 0.1060 (0.1121) loss: 0.8583 (0.8610) time: 0.1432 data: 0.0683 max mem: 8299 +Train: [76] [5300/6250] eta: 0:02:18 lr: 0.000017 grad: 0.1140 (0.1121) loss: 0.8640 (0.8610) time: 0.1853 data: 0.1148 max mem: 8299 +Train: [76] [5400/6250] eta: 0:02:03 lr: 0.000017 grad: 0.1109 (0.1122) loss: 0.8611 (0.8610) time: 0.1363 data: 0.0617 max mem: 8299 +Train: [76] [5500/6250] eta: 0:01:49 lr: 0.000017 grad: 0.1124 (0.1121) loss: 0.8622 (0.8610) time: 0.1248 data: 0.0599 max mem: 8299 +Train: [76] [5600/6250] eta: 0:01:34 lr: 0.000017 grad: 0.1028 (0.1120) loss: 0.8612 (0.8610) time: 0.1217 data: 0.0487 max mem: 8299 +Train: [76] [5700/6250] eta: 0:01:19 lr: 0.000017 grad: 0.1049 (0.1120) loss: 0.8629 (0.8610) time: 0.1599 data: 0.0825 max mem: 8299 +Train: [76] [5800/6250] eta: 0:01:05 lr: 0.000017 grad: 0.1137 (0.1120) loss: 0.8560 (0.8610) time: 0.1573 data: 0.0782 max mem: 8299 +Train: [76] [5900/6250] eta: 0:00:50 lr: 0.000017 grad: 0.1032 (0.1120) loss: 0.8664 (0.8609) time: 0.1361 data: 0.0572 max mem: 8299 +Train: [76] [6000/6250] eta: 0:00:36 lr: 0.000017 grad: 0.1055 (0.1120) loss: 0.8567 (0.8609) time: 0.1393 data: 0.0630 max mem: 8299 +Train: [76] [6100/6250] eta: 0:00:21 lr: 0.000017 grad: 0.1106 (0.1121) loss: 0.8598 (0.8608) time: 0.1301 data: 0.0536 max mem: 8299 +Train: [76] [6200/6250] eta: 0:00:07 lr: 0.000017 grad: 0.1210 (0.1122) loss: 0.8526 (0.8607) time: 0.1186 data: 0.0378 max mem: 8299 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1029 (0.1122) loss: 0.8650 (0.8607) time: 0.1188 data: 0.0256 max mem: 8299 +Train: [76] Total time: 0:15:13 (0.1462 s / it) +Averaged stats: lr: 0.000017 grad: 0.1029 (0.1122) loss: 0.8650 (0.8607) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:05:24 loss: 0.8816 (0.8816) time: 5.2364 data: 5.2069 max mem: 8299 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8725 (0.8744) time: 0.1445 data: 0.1197 max mem: 8299 +Eval (hcp-train-subset): [76] Total time: 0:00:15 (0.2442 s / it) +Averaged stats (hcp-train-subset): loss: 0.8725 (0.8744) +Eval (hcp-val): [76] [ 0/62] eta: 0:05:45 loss: 0.8768 (0.8768) time: 5.5687 data: 5.5367 max mem: 8299 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8779 (0.8792) time: 0.1309 data: 0.1066 max mem: 8299 +Eval (hcp-val): [76] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-val): loss: 0.8779 (0.8792) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 11:00:48 lr: 0.000017 grad: 0.4141 (0.4141) loss: 0.8429 (0.8429) time: 6.3438 data: 6.2283 max mem: 8299 +Train: [77] [ 100/6250] eta: 0:20:41 lr: 0.000017 grad: 0.0950 (0.1441) loss: 0.8788 (0.8764) time: 0.1687 data: 0.0701 max mem: 8299 +Train: [77] [ 200/6250] eta: 0:17:48 lr: 0.000017 grad: 0.1322 (0.1328) loss: 0.8575 (0.8698) time: 0.1419 data: 0.0532 max mem: 8299 +Train: [77] [ 300/6250] eta: 0:16:37 lr: 0.000017 grad: 0.1096 (0.1277) loss: 0.8611 (0.8663) time: 0.1309 data: 0.0465 max mem: 8299 +Train: [77] [ 400/6250] eta: 0:15:50 lr: 0.000017 grad: 0.1070 (0.1242) loss: 0.8662 (0.8645) time: 0.1529 data: 0.0579 max mem: 8299 +Train: [77] [ 500/6250] eta: 0:15:16 lr: 0.000017 grad: 0.1122 (0.1221) loss: 0.8575 (0.8634) time: 0.1651 data: 0.0702 max mem: 8299 +Train: [77] [ 600/6250] eta: 0:14:48 lr: 0.000017 grad: 0.1037 (0.1209) loss: 0.8697 (0.8627) time: 0.1541 data: 0.0591 max mem: 8299 +Train: [77] [ 700/6250] eta: 0:14:25 lr: 0.000017 grad: 0.1160 (0.1205) loss: 0.8625 (0.8621) time: 0.1502 data: 0.0628 max mem: 8299 +Train: [77] [ 800/6250] eta: 0:13:56 lr: 0.000017 grad: 0.1160 (0.1199) loss: 0.8616 (0.8617) time: 0.1305 data: 0.0420 max mem: 8299 +Train: [77] [ 900/6250] eta: 0:13:29 lr: 0.000017 grad: 0.1049 (0.1194) loss: 0.8575 (0.8612) time: 0.1211 data: 0.0436 max mem: 8299 +Train: [77] [1000/6250] eta: 0:13:10 lr: 0.000017 grad: 0.0987 (0.1185) loss: 0.8654 (0.8609) time: 0.1595 data: 0.0663 max mem: 8299 +Train: [77] [1100/6250] eta: 0:12:52 lr: 0.000017 grad: 0.1088 (0.1181) loss: 0.8563 (0.8606) time: 0.1344 data: 0.0609 max mem: 8299 +Train: [77] [1200/6250] eta: 0:12:33 lr: 0.000017 grad: 0.1020 (0.1173) loss: 0.8612 (0.8606) time: 0.1414 data: 0.0618 max mem: 8299 +Train: [77] [1300/6250] eta: 0:12:15 lr: 0.000017 grad: 0.1020 (0.1166) loss: 0.8592 (0.8607) time: 0.1475 data: 0.0740 max mem: 8299 +Train: [77] [1400/6250] eta: 0:12:01 lr: 0.000017 grad: 0.1143 (0.1162) loss: 0.8631 (0.8605) time: 0.1369 data: 0.0638 max mem: 8299 +Train: [77] [1500/6250] eta: 0:11:47 lr: 0.000017 grad: 0.1011 (0.1156) loss: 0.8618 (0.8606) time: 0.1530 data: 0.0684 max mem: 8299 +Train: [77] [1600/6250] eta: 0:11:30 lr: 0.000017 grad: 0.1076 (0.1153) loss: 0.8677 (0.8607) time: 0.1368 data: 0.0584 max mem: 8299 +Train: [77] [1700/6250] eta: 0:11:12 lr: 0.000017 grad: 0.1043 (0.1150) loss: 0.8600 (0.8609) time: 0.1303 data: 0.0590 max mem: 8299 +Train: [77] [1800/6250] eta: 0:10:53 lr: 0.000017 grad: 0.1110 (0.1148) loss: 0.8604 (0.8609) time: 0.1206 data: 0.0396 max mem: 8299 +Train: [77] [1900/6250] eta: 0:10:38 lr: 0.000017 grad: 0.1123 (0.1146) loss: 0.8642 (0.8609) time: 0.1382 data: 0.0567 max mem: 8299 +Train: [77] [2000/6250] eta: 0:10:25 lr: 0.000017 grad: 0.1185 (0.1145) loss: 0.8579 (0.8607) time: 0.1565 data: 0.0740 max mem: 8299 +Train: [77] [2100/6250] eta: 0:10:10 lr: 0.000017 grad: 0.1084 (0.1144) loss: 0.8569 (0.8606) time: 0.1542 data: 0.0796 max mem: 8299 +Train: [77] [2200/6250] eta: 0:09:56 lr: 0.000017 grad: 0.1134 (0.1144) loss: 0.8562 (0.8605) time: 0.1842 data: 0.1159 max mem: 8299 +Train: [77] [2300/6250] eta: 0:09:39 lr: 0.000017 grad: 0.1090 (0.1144) loss: 0.8637 (0.8604) time: 0.1381 data: 0.0582 max mem: 8299 +Train: [77] [2400/6250] eta: 0:09:24 lr: 0.000017 grad: 0.1162 (0.1145) loss: 0.8599 (0.8602) time: 0.1340 data: 0.0594 max mem: 8299 +Train: [77] [2500/6250] eta: 0:09:08 lr: 0.000017 grad: 0.1128 (0.1146) loss: 0.8521 (0.8602) time: 0.1401 data: 0.0611 max mem: 8299 +Train: [77] [2600/6250] eta: 0:08:53 lr: 0.000017 grad: 0.1200 (0.1146) loss: 0.8588 (0.8601) time: 0.1496 data: 0.0743 max mem: 8299 +Train: [77] [2700/6250] eta: 0:08:36 lr: 0.000017 grad: 0.1086 (0.1146) loss: 0.8657 (0.8601) time: 0.1368 data: 0.0607 max mem: 8299 +Train: [77] [2800/6250] eta: 0:08:20 lr: 0.000017 grad: 0.1139 (0.1148) loss: 0.8586 (0.8600) time: 0.1561 data: 0.0693 max mem: 8299 +Train: [77] [2900/6250] eta: 0:08:07 lr: 0.000017 grad: 0.1148 (0.1148) loss: 0.8611 (0.8600) time: 0.1503 data: 0.0721 max mem: 8299 +Train: [77] [3000/6250] eta: 0:07:53 lr: 0.000017 grad: 0.1125 (0.1149) loss: 0.8561 (0.8600) time: 0.1635 data: 0.0974 max mem: 8299 +Train: [77] [3100/6250] eta: 0:07:38 lr: 0.000017 grad: 0.1125 (0.1151) loss: 0.8642 (0.8600) time: 0.1632 data: 0.0774 max mem: 8299 +Train: [77] [3200/6250] eta: 0:07:24 lr: 0.000017 grad: 0.1056 (0.1151) loss: 0.8619 (0.8600) time: 0.1698 data: 0.0876 max mem: 8299 +Train: [77] [3300/6250] eta: 0:07:11 lr: 0.000016 grad: 0.1117 (0.1151) loss: 0.8584 (0.8599) time: 0.1448 data: 0.0584 max mem: 8299 +Train: [77] [3400/6250] eta: 0:06:57 lr: 0.000016 grad: 0.1084 (0.1152) loss: 0.8532 (0.8598) time: 0.1538 data: 0.0863 max mem: 8299 +Train: [77] [3500/6250] eta: 0:06:41 lr: 0.000016 grad: 0.1137 (0.1151) loss: 0.8651 (0.8598) time: 0.1518 data: 0.0643 max mem: 8299 +Train: [77] [3600/6250] eta: 0:06:27 lr: 0.000016 grad: 0.1086 (0.1151) loss: 0.8541 (0.8598) time: 0.1329 data: 0.0514 max mem: 8299 +Train: [77] [3700/6250] eta: 0:06:12 lr: 0.000016 grad: 0.1131 (0.1151) loss: 0.8576 (0.8598) time: 0.1406 data: 0.0563 max mem: 8299 +Train: [77] [3800/6250] eta: 0:05:56 lr: 0.000016 grad: 0.1107 (0.1152) loss: 0.8607 (0.8598) time: 0.1371 data: 0.0669 max mem: 8299 +Train: [77] [3900/6250] eta: 0:05:42 lr: 0.000016 grad: 0.1133 (0.1153) loss: 0.8572 (0.8597) time: 0.1656 data: 0.0855 max mem: 8299 +Train: [77] [4000/6250] eta: 0:05:27 lr: 0.000016 grad: 0.1081 (0.1152) loss: 0.8559 (0.8597) time: 0.1211 data: 0.0430 max mem: 8299 +Train: [77] [4100/6250] eta: 0:05:12 lr: 0.000016 grad: 0.1111 (0.1153) loss: 0.8609 (0.8597) time: 0.1261 data: 0.0463 max mem: 8299 +Train: [77] [4200/6250] eta: 0:04:57 lr: 0.000016 grad: 0.1171 (0.1154) loss: 0.8557 (0.8596) time: 0.1443 data: 0.0606 max mem: 8299 +Train: [77] [4300/6250] eta: 0:04:42 lr: 0.000016 grad: 0.1109 (0.1154) loss: 0.8598 (0.8596) time: 0.1415 data: 0.0615 max mem: 8299 +Train: [77] [4400/6250] eta: 0:04:28 lr: 0.000016 grad: 0.1102 (0.1154) loss: 0.8616 (0.8596) time: 0.1442 data: 0.0677 max mem: 8299 +Train: [77] [4500/6250] eta: 0:04:14 lr: 0.000016 grad: 0.1152 (0.1154) loss: 0.8609 (0.8596) time: 0.1385 data: 0.0600 max mem: 8299 +Train: [77] [4600/6250] eta: 0:03:59 lr: 0.000016 grad: 0.1200 (0.1156) loss: 0.8605 (0.8596) time: 0.1252 data: 0.0477 max mem: 8299 +Train: [77] [4700/6250] eta: 0:03:46 lr: 0.000016 grad: 0.1212 (0.1157) loss: 0.8638 (0.8597) time: 0.1710 data: 0.0885 max mem: 8299 +Train: [77] [4800/6250] eta: 0:03:31 lr: 0.000016 grad: 0.1175 (0.1157) loss: 0.8555 (0.8597) time: 0.1666 data: 0.0951 max mem: 8299 +Train: [77] [4900/6250] eta: 0:03:16 lr: 0.000016 grad: 0.1162 (0.1157) loss: 0.8594 (0.8597) time: 0.1443 data: 0.0690 max mem: 8299 +Train: [77] [5000/6250] eta: 0:03:02 lr: 0.000016 grad: 0.1064 (0.1157) loss: 0.8610 (0.8596) time: 0.1468 data: 0.0666 max mem: 8299 +Train: [77] [5100/6250] eta: 0:02:47 lr: 0.000016 grad: 0.1125 (0.1157) loss: 0.8558 (0.8596) time: 0.1476 data: 0.0694 max mem: 8299 +Train: [77] [5200/6250] eta: 0:02:33 lr: 0.000016 grad: 0.1081 (0.1156) loss: 0.8585 (0.8596) time: 0.1281 data: 0.0561 max mem: 8299 +Train: [77] [5300/6250] eta: 0:02:18 lr: 0.000016 grad: 0.1099 (0.1156) loss: 0.8642 (0.8596) time: 0.1393 data: 0.0667 max mem: 8299 +Train: [77] [5400/6250] eta: 0:02:04 lr: 0.000016 grad: 0.1162 (0.1156) loss: 0.8590 (0.8596) time: 0.1505 data: 0.0765 max mem: 8299 +Train: [77] [5500/6250] eta: 0:01:49 lr: 0.000016 grad: 0.1144 (0.1156) loss: 0.8608 (0.8596) time: 0.1480 data: 0.0612 max mem: 8299 +Train: [77] [5600/6250] eta: 0:01:34 lr: 0.000016 grad: 0.1142 (0.1157) loss: 0.8565 (0.8596) time: 0.1332 data: 0.0494 max mem: 8299 +Train: [77] [5700/6250] eta: 0:01:20 lr: 0.000016 grad: 0.1071 (0.1158) loss: 0.8566 (0.8596) time: 0.1412 data: 0.0596 max mem: 8299 +Train: [77] [5800/6250] eta: 0:01:05 lr: 0.000016 grad: 0.1188 (0.1158) loss: 0.8570 (0.8596) time: 0.1373 data: 0.0498 max mem: 8299 +Train: [77] [5900/6250] eta: 0:00:50 lr: 0.000016 grad: 0.1172 (0.1159) loss: 0.8539 (0.8596) time: 0.1362 data: 0.0604 max mem: 8299 +Train: [77] [6000/6250] eta: 0:00:36 lr: 0.000016 grad: 0.1156 (0.1159) loss: 0.8638 (0.8596) time: 0.1491 data: 0.0656 max mem: 8299 +Train: [77] [6100/6250] eta: 0:00:21 lr: 0.000016 grad: 0.1166 (0.1160) loss: 0.8577 (0.8596) time: 0.1413 data: 0.0673 max mem: 8299 +Train: [77] [6200/6250] eta: 0:00:07 lr: 0.000016 grad: 0.1185 (0.1160) loss: 0.8558 (0.8595) time: 0.1510 data: 0.0781 max mem: 8299 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1234 (0.1161) loss: 0.8525 (0.8595) time: 0.1506 data: 0.0615 max mem: 8299 +Train: [77] Total time: 0:15:13 (0.1462 s / it) +Averaged stats: lr: 0.000016 grad: 0.1234 (0.1161) loss: 0.8525 (0.8595) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:05:36 loss: 0.8905 (0.8905) time: 5.4272 data: 5.3973 max mem: 8299 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8724 (0.8750) time: 0.1222 data: 0.0977 max mem: 8299 +Eval (hcp-train-subset): [77] Total time: 0:00:14 (0.2335 s / it) +Averaged stats (hcp-train-subset): loss: 0.8724 (0.8750) +Eval (hcp-val): [77] [ 0/62] eta: 0:06:17 loss: 0.8758 (0.8758) time: 6.0867 data: 6.0578 max mem: 8299 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8776 (0.8800) time: 0.1311 data: 0.1057 max mem: 8299 +Eval (hcp-val): [77] Total time: 0:00:13 (0.2255 s / it) +Averaged stats (hcp-val): loss: 0.8776 (0.8800) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 11:17:56 lr: 0.000016 grad: 0.0760 (0.0760) loss: 0.8882 (0.8882) time: 6.5083 data: 6.4208 max mem: 8299 +Train: [78] [ 100/6250] eta: 0:20:25 lr: 0.000016 grad: 0.1160 (0.1463) loss: 0.8596 (0.8635) time: 0.1342 data: 0.0300 max mem: 8299 +Train: [78] [ 200/6250] eta: 0:17:27 lr: 0.000016 grad: 0.1063 (0.1362) loss: 0.8669 (0.8629) time: 0.1478 data: 0.0482 max mem: 8299 +Train: [78] [ 300/6250] eta: 0:16:20 lr: 0.000016 grad: 0.1010 (0.1292) loss: 0.8597 (0.8639) time: 0.1620 data: 0.0838 max mem: 8299 +Train: [78] [ 400/6250] eta: 0:15:21 lr: 0.000016 grad: 0.1092 (0.1259) loss: 0.8607 (0.8636) time: 0.1493 data: 0.0668 max mem: 8299 +Train: [78] [ 500/6250] eta: 0:15:00 lr: 0.000016 grad: 0.1004 (0.1229) loss: 0.8651 (0.8635) time: 0.1165 data: 0.0333 max mem: 8299 +Train: [78] [ 600/6250] eta: 0:14:26 lr: 0.000016 grad: 0.1106 (0.1210) loss: 0.8655 (0.8634) time: 0.1215 data: 0.0426 max mem: 8299 +Train: [78] [ 700/6250] eta: 0:14:05 lr: 0.000016 grad: 0.1088 (0.1203) loss: 0.8610 (0.8633) time: 0.1554 data: 0.0710 max mem: 8299 +Train: [78] [ 800/6250] eta: 0:13:41 lr: 0.000016 grad: 0.1054 (0.1193) loss: 0.8629 (0.8632) time: 0.1266 data: 0.0457 max mem: 8299 +Train: [78] [ 900/6250] eta: 0:13:23 lr: 0.000016 grad: 0.1052 (0.1185) loss: 0.8545 (0.8631) time: 0.1390 data: 0.0615 max mem: 8299 +Train: [78] [1000/6250] eta: 0:13:03 lr: 0.000016 grad: 0.1106 (0.1177) loss: 0.8672 (0.8631) time: 0.1528 data: 0.0716 max mem: 8299 +Train: [78] [1100/6250] eta: 0:12:48 lr: 0.000016 grad: 0.1115 (0.1172) loss: 0.8619 (0.8630) time: 0.1486 data: 0.0748 max mem: 8299 +Train: [78] [1200/6250] eta: 0:12:30 lr: 0.000016 grad: 0.1073 (0.1167) loss: 0.8632 (0.8628) time: 0.1230 data: 0.0425 max mem: 8299 +Train: [78] [1300/6250] eta: 0:12:14 lr: 0.000016 grad: 0.1109 (0.1160) loss: 0.8633 (0.8627) time: 0.1490 data: 0.0691 max mem: 8299 +Train: [78] [1400/6250] eta: 0:11:53 lr: 0.000016 grad: 0.1116 (0.1157) loss: 0.8615 (0.8626) time: 0.1359 data: 0.0560 max mem: 8299 +Train: [78] [1500/6250] eta: 0:11:42 lr: 0.000015 grad: 0.1063 (0.1154) loss: 0.8561 (0.8624) time: 0.1901 data: 0.1051 max mem: 8299 +Train: [78] [1600/6250] eta: 0:11:26 lr: 0.000015 grad: 0.1099 (0.1152) loss: 0.8630 (0.8621) time: 0.1506 data: 0.0765 max mem: 8299 +Train: [78] [1700/6250] eta: 0:11:08 lr: 0.000015 grad: 0.1169 (0.1153) loss: 0.8583 (0.8618) time: 0.1355 data: 0.0626 max mem: 8299 +Train: [78] [1800/6250] eta: 0:10:50 lr: 0.000015 grad: 0.1144 (0.1154) loss: 0.8608 (0.8614) time: 0.1469 data: 0.0670 max mem: 8299 +Train: [78] [1900/6250] eta: 0:10:35 lr: 0.000015 grad: 0.1207 (0.1155) loss: 0.8586 (0.8610) time: 0.1358 data: 0.0493 max mem: 8299 +Train: [78] [2000/6250] eta: 0:10:21 lr: 0.000015 grad: 0.1097 (0.1154) loss: 0.8637 (0.8608) time: 0.1355 data: 0.0594 max mem: 8299 +Train: [78] [2100/6250] eta: 0:10:07 lr: 0.000015 grad: 0.1105 (0.1154) loss: 0.8580 (0.8606) time: 0.1303 data: 0.0442 max mem: 8299 +Train: [78] [2200/6250] eta: 0:09:52 lr: 0.000015 grad: 0.1197 (0.1155) loss: 0.8539 (0.8603) time: 0.1372 data: 0.0611 max mem: 8299 +Train: [78] [2300/6250] eta: 0:09:36 lr: 0.000015 grad: 0.1082 (0.1155) loss: 0.8563 (0.8601) time: 0.1583 data: 0.0903 max mem: 8299 +Train: [78] [2400/6250] eta: 0:09:21 lr: 0.000015 grad: 0.1167 (0.1155) loss: 0.8597 (0.8600) time: 0.1265 data: 0.0357 max mem: 8299 +Train: [78] [2500/6250] eta: 0:09:06 lr: 0.000015 grad: 0.1037 (0.1153) loss: 0.8657 (0.8600) time: 0.1499 data: 0.0773 max mem: 8299 +Train: [78] [2600/6250] eta: 0:08:51 lr: 0.000015 grad: 0.1074 (0.1154) loss: 0.8626 (0.8600) time: 0.1308 data: 0.0507 max mem: 8299 +Train: [78] [2700/6250] eta: 0:08:36 lr: 0.000015 grad: 0.1177 (0.1154) loss: 0.8607 (0.8600) time: 0.1408 data: 0.0610 max mem: 8299 +Train: [78] [2800/6250] eta: 0:08:22 lr: 0.000015 grad: 0.1109 (0.1153) loss: 0.8583 (0.8600) time: 0.1527 data: 0.0778 max mem: 8299 +Train: [78] [2900/6250] eta: 0:08:07 lr: 0.000015 grad: 0.1067 (0.1153) loss: 0.8627 (0.8600) time: 0.1472 data: 0.0732 max mem: 8299 +Train: [78] [3000/6250] eta: 0:07:53 lr: 0.000015 grad: 0.1095 (0.1152) loss: 0.8602 (0.8600) time: 0.1425 data: 0.0640 max mem: 8299 +Train: [78] [3100/6250] eta: 0:07:38 lr: 0.000015 grad: 0.1216 (0.1153) loss: 0.8536 (0.8600) time: 0.1294 data: 0.0561 max mem: 8299 +Train: [78] [3200/6250] eta: 0:07:23 lr: 0.000015 grad: 0.1071 (0.1152) loss: 0.8622 (0.8600) time: 0.1291 data: 0.0548 max mem: 8299 +Train: [78] [3300/6250] eta: 0:07:08 lr: 0.000015 grad: 0.1113 (0.1151) loss: 0.8549 (0.8601) time: 0.1322 data: 0.0576 max mem: 8299 +Train: [78] [3400/6250] eta: 0:06:52 lr: 0.000015 grad: 0.1052 (0.1150) loss: 0.8634 (0.8602) time: 0.1296 data: 0.0613 max mem: 8299 +Train: [78] [3500/6250] eta: 0:06:37 lr: 0.000015 grad: 0.1094 (0.1149) loss: 0.8629 (0.8602) time: 0.1245 data: 0.0554 max mem: 8299 +Train: [78] [3600/6250] eta: 0:06:21 lr: 0.000015 grad: 0.1101 (0.1149) loss: 0.8588 (0.8603) time: 0.1279 data: 0.0611 max mem: 8299 +Train: [78] [3700/6250] eta: 0:06:05 lr: 0.000015 grad: 0.1067 (0.1149) loss: 0.8629 (0.8603) time: 0.1232 data: 0.0459 max mem: 8299 +Train: [78] [3800/6250] eta: 0:05:49 lr: 0.000015 grad: 0.1070 (0.1148) loss: 0.8587 (0.8603) time: 0.1132 data: 0.0390 max mem: 8299 +Train: [78] [3900/6250] eta: 0:05:34 lr: 0.000015 grad: 0.1100 (0.1148) loss: 0.8617 (0.8603) time: 0.1226 data: 0.0546 max mem: 8299 +Train: [78] [4000/6250] eta: 0:05:19 lr: 0.000015 grad: 0.1184 (0.1150) loss: 0.8604 (0.8603) time: 0.1495 data: 0.0835 max mem: 8299 +Train: [78] [4100/6250] eta: 0:05:04 lr: 0.000015 grad: 0.1087 (0.1149) loss: 0.8610 (0.8603) time: 0.1233 data: 0.0555 max mem: 8299 +Train: [78] [4200/6250] eta: 0:04:49 lr: 0.000015 grad: 0.1172 (0.1149) loss: 0.8636 (0.8604) time: 0.1126 data: 0.0394 max mem: 8299 +Train: [78] [4300/6250] eta: 0:04:34 lr: 0.000015 grad: 0.1072 (0.1149) loss: 0.8617 (0.8604) time: 0.1150 data: 0.0444 max mem: 8299 +Train: [78] [4400/6250] eta: 0:04:19 lr: 0.000015 grad: 0.1076 (0.1150) loss: 0.8597 (0.8604) time: 0.1163 data: 0.0453 max mem: 8299 +Train: [78] [4500/6250] eta: 0:04:04 lr: 0.000015 grad: 0.1089 (0.1150) loss: 0.8609 (0.8605) time: 0.1305 data: 0.0619 max mem: 8299 +Train: [78] [4600/6250] eta: 0:03:50 lr: 0.000015 grad: 0.1128 (0.1150) loss: 0.8575 (0.8605) time: 0.1353 data: 0.0650 max mem: 8299 +Train: [78] [4700/6250] eta: 0:03:36 lr: 0.000015 grad: 0.1046 (0.1149) loss: 0.8644 (0.8606) time: 0.1369 data: 0.0523 max mem: 8299 +Train: [78] [4800/6250] eta: 0:03:22 lr: 0.000015 grad: 0.1151 (0.1149) loss: 0.8603 (0.8606) time: 0.0936 data: 0.0175 max mem: 8299 +Train: [78] [4900/6250] eta: 0:03:08 lr: 0.000015 grad: 0.1126 (0.1149) loss: 0.8620 (0.8606) time: 0.1360 data: 0.0614 max mem: 8299 +Train: [78] [5000/6250] eta: 0:02:54 lr: 0.000015 grad: 0.1162 (0.1150) loss: 0.8598 (0.8606) time: 0.1270 data: 0.0519 max mem: 8299 +Train: [78] [5100/6250] eta: 0:02:39 lr: 0.000015 grad: 0.1142 (0.1151) loss: 0.8615 (0.8606) time: 0.1203 data: 0.0521 max mem: 8299 +Train: [78] [5200/6250] eta: 0:02:25 lr: 0.000015 grad: 0.1123 (0.1152) loss: 0.8586 (0.8605) time: 0.1090 data: 0.0363 max mem: 8299 +Train: [78] [5300/6250] eta: 0:02:11 lr: 0.000015 grad: 0.1176 (0.1153) loss: 0.8561 (0.8605) time: 0.1247 data: 0.0577 max mem: 8299 +Train: [78] [5400/6250] eta: 0:01:57 lr: 0.000015 grad: 0.1032 (0.1153) loss: 0.8608 (0.8604) time: 0.1056 data: 0.0270 max mem: 8299 +Train: [78] [5500/6250] eta: 0:01:42 lr: 0.000015 grad: 0.1168 (0.1154) loss: 0.8613 (0.8603) time: 0.1179 data: 0.0463 max mem: 8299 +Train: [78] [5600/6250] eta: 0:01:28 lr: 0.000015 grad: 0.1190 (0.1154) loss: 0.8564 (0.8603) time: 0.1215 data: 0.0464 max mem: 8299 +Train: [78] [5700/6250] eta: 0:01:14 lr: 0.000015 grad: 0.1142 (0.1155) loss: 0.8594 (0.8602) time: 0.1063 data: 0.0240 max mem: 8299 +Train: [78] [5800/6250] eta: 0:01:01 lr: 0.000015 grad: 0.1081 (0.1156) loss: 0.8579 (0.8602) time: 0.1111 data: 0.0382 max mem: 8299 +Train: [78] [5900/6250] eta: 0:00:47 lr: 0.000015 grad: 0.1159 (0.1157) loss: 0.8578 (0.8601) time: 0.0951 data: 0.0187 max mem: 8299 +Train: [78] [6000/6250] eta: 0:00:33 lr: 0.000015 grad: 0.1106 (0.1157) loss: 0.8550 (0.8601) time: 0.0943 data: 0.0243 max mem: 8299 +Train: [78] [6100/6250] eta: 0:00:20 lr: 0.000015 grad: 0.1165 (0.1158) loss: 0.8503 (0.8600) time: 0.0936 data: 0.0207 max mem: 8299 +Train: [78] [6200/6250] eta: 0:00:06 lr: 0.000014 grad: 0.1142 (0.1159) loss: 0.8550 (0.8599) time: 0.1014 data: 0.0300 max mem: 8299 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1217 (0.1159) loss: 0.8568 (0.8599) time: 0.1085 data: 0.0306 max mem: 8299 +Train: [78] Total time: 0:13:58 (0.1341 s / it) +Averaged stats: lr: 0.000014 grad: 0.1217 (0.1159) loss: 0.8568 (0.8599) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:05:09 loss: 0.8829 (0.8829) time: 4.9925 data: 4.9643 max mem: 8299 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8726 (0.8740) time: 0.0975 data: 0.0734 max mem: 8299 +Eval (hcp-train-subset): [78] Total time: 0:00:11 (0.1822 s / it) +Averaged stats (hcp-train-subset): loss: 0.8726 (0.8740) +Eval (hcp-val): [78] [ 0/62] eta: 0:03:51 loss: 0.8760 (0.8760) time: 3.7332 data: 3.6587 max mem: 8299 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8771 (0.8778) time: 0.1131 data: 0.0890 max mem: 8299 +Eval (hcp-val): [78] Total time: 0:00:11 (0.1851 s / it) +Averaged stats (hcp-val): loss: 0.8771 (0.8778) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 9:29:08 lr: 0.000014 grad: 0.2691 (0.2691) loss: 0.8229 (0.8229) time: 5.4638 data: 5.3418 max mem: 8299 +Train: [79] [ 100/6250] eta: 0:17:47 lr: 0.000014 grad: 0.1111 (0.1477) loss: 0.8628 (0.8632) time: 0.1332 data: 0.0566 max mem: 8299 +Train: [79] [ 200/6250] eta: 0:14:56 lr: 0.000014 grad: 0.1036 (0.1338) loss: 0.8582 (0.8623) time: 0.1311 data: 0.0526 max mem: 8299 +Train: [79] [ 300/6250] eta: 0:13:55 lr: 0.000014 grad: 0.1095 (0.1289) loss: 0.8681 (0.8629) time: 0.1235 data: 0.0424 max mem: 8299 +Train: [79] [ 400/6250] eta: 0:13:08 lr: 0.000014 grad: 0.1105 (0.1242) loss: 0.8602 (0.8633) time: 0.1001 data: 0.0166 max mem: 8299 +Train: [79] [ 500/6250] eta: 0:12:33 lr: 0.000014 grad: 0.1036 (0.1209) loss: 0.8679 (0.8638) time: 0.1139 data: 0.0315 max mem: 8299 +Train: [79] [ 600/6250] eta: 0:12:02 lr: 0.000014 grad: 0.1075 (0.1193) loss: 0.8635 (0.8642) time: 0.1179 data: 0.0392 max mem: 8299 +Train: [79] [ 700/6250] eta: 0:11:38 lr: 0.000014 grad: 0.1147 (0.1185) loss: 0.8674 (0.8642) time: 0.1192 data: 0.0421 max mem: 8299 +Train: [79] [ 800/6250] eta: 0:11:12 lr: 0.000014 grad: 0.0993 (0.1177) loss: 0.8660 (0.8643) time: 0.1036 data: 0.0281 max mem: 8299 +Train: [79] [ 900/6250] eta: 0:10:52 lr: 0.000014 grad: 0.1076 (0.1169) loss: 0.8699 (0.8645) time: 0.0992 data: 0.0252 max mem: 8299 +Train: [79] [1000/6250] eta: 0:10:30 lr: 0.000014 grad: 0.1181 (0.1166) loss: 0.8630 (0.8644) time: 0.0954 data: 0.0205 max mem: 8299 +Train: [79] [1100/6250] eta: 0:10:10 lr: 0.000014 grad: 0.1093 (0.1162) loss: 0.8595 (0.8644) time: 0.1024 data: 0.0212 max mem: 8299 +Train: [79] [1200/6250] eta: 0:09:52 lr: 0.000014 grad: 0.1184 (0.1162) loss: 0.8637 (0.8644) time: 0.1095 data: 0.0339 max mem: 8299 +Train: [79] [1300/6250] eta: 0:09:34 lr: 0.000014 grad: 0.1215 (0.1163) loss: 0.8596 (0.8642) time: 0.1023 data: 0.0211 max mem: 8299 +Train: [79] [1400/6250] eta: 0:09:18 lr: 0.000014 grad: 0.1181 (0.1162) loss: 0.8668 (0.8642) time: 0.1036 data: 0.0237 max mem: 8299 +Train: [79] [1500/6250] eta: 0:09:03 lr: 0.000014 grad: 0.1084 (0.1163) loss: 0.8582 (0.8640) time: 0.0999 data: 0.0209 max mem: 8299 +Train: [79] [1600/6250] eta: 0:08:51 lr: 0.000014 grad: 0.1144 (0.1164) loss: 0.8633 (0.8639) time: 0.1292 data: 0.0620 max mem: 8299 +Train: [79] [1700/6250] eta: 0:08:38 lr: 0.000014 grad: 0.1172 (0.1169) loss: 0.8632 (0.8638) time: 0.0979 data: 0.0293 max mem: 8299 +Train: [79] [1800/6250] eta: 0:08:25 lr: 0.000014 grad: 0.1218 (0.1170) loss: 0.8589 (0.8636) time: 0.1140 data: 0.0438 max mem: 8299 +Train: [79] [1900/6250] eta: 0:08:13 lr: 0.000014 grad: 0.1197 (0.1172) loss: 0.8535 (0.8634) time: 0.1091 data: 0.0301 max mem: 8299 +Train: [79] [2000/6250] eta: 0:08:01 lr: 0.000014 grad: 0.1180 (0.1173) loss: 0.8598 (0.8633) time: 0.0910 data: 0.0139 max mem: 8299 +Train: [79] [2100/6250] eta: 0:07:49 lr: 0.000014 grad: 0.1159 (0.1176) loss: 0.8603 (0.8631) time: 0.1125 data: 0.0328 max mem: 8299 +Train: [79] [2200/6250] eta: 0:07:36 lr: 0.000014 grad: 0.1236 (0.1178) loss: 0.8579 (0.8628) time: 0.1042 data: 0.0307 max mem: 8299 +Train: [79] [2300/6250] eta: 0:07:24 lr: 0.000014 grad: 0.1256 (0.1181) loss: 0.8622 (0.8626) time: 0.1113 data: 0.0444 max mem: 8299 +Train: [79] [2400/6250] eta: 0:07:12 lr: 0.000014 grad: 0.1231 (0.1183) loss: 0.8606 (0.8624) time: 0.0997 data: 0.0179 max mem: 8299 +Train: [79] [2500/6250] eta: 0:07:00 lr: 0.000014 grad: 0.1251 (0.1185) loss: 0.8532 (0.8622) time: 0.1069 data: 0.0341 max mem: 8299 +Train: [79] [2600/6250] eta: 0:06:48 lr: 0.000014 grad: 0.1209 (0.1187) loss: 0.8584 (0.8621) time: 0.0885 data: 0.0067 max mem: 8299 +Train: [79] [2700/6250] eta: 0:06:37 lr: 0.000014 grad: 0.1184 (0.1189) loss: 0.8683 (0.8619) time: 0.1181 data: 0.0431 max mem: 8299 +Train: [79] [2800/6250] eta: 0:06:25 lr: 0.000014 grad: 0.1121 (0.1189) loss: 0.8645 (0.8618) time: 0.0983 data: 0.0114 max mem: 8299 +Train: [79] [2900/6250] eta: 0:06:13 lr: 0.000014 grad: 0.1098 (0.1190) loss: 0.8602 (0.8615) time: 0.1004 data: 0.0240 max mem: 8299 +Train: [79] [3000/6250] eta: 0:06:02 lr: 0.000014 grad: 0.1125 (0.1191) loss: 0.8568 (0.8613) time: 0.0920 data: 0.0149 max mem: 8299 +Train: [79] [3100/6250] eta: 0:05:50 lr: 0.000014 grad: 0.1080 (0.1192) loss: 0.8668 (0.8613) time: 0.1124 data: 0.0350 max mem: 8299 +Train: [79] [3200/6250] eta: 0:05:39 lr: 0.000014 grad: 0.1167 (0.1191) loss: 0.8592 (0.8613) time: 0.1133 data: 0.0392 max mem: 8299 +Train: [79] [3300/6250] eta: 0:05:28 lr: 0.000014 grad: 0.1111 (0.1191) loss: 0.8553 (0.8612) time: 0.1189 data: 0.0433 max mem: 8299 +Train: [79] [3400/6250] eta: 0:05:16 lr: 0.000014 grad: 0.1133 (0.1191) loss: 0.8542 (0.8611) time: 0.0915 data: 0.0187 max mem: 8299 +Train: [79] [3500/6250] eta: 0:05:05 lr: 0.000014 grad: 0.1291 (0.1192) loss: 0.8571 (0.8610) time: 0.1058 data: 0.0356 max mem: 8299 +Train: [79] [3600/6250] eta: 0:04:54 lr: 0.000014 grad: 0.1177 (0.1191) loss: 0.8563 (0.8610) time: 0.1114 data: 0.0433 max mem: 8299 +Train: [79] [3700/6250] eta: 0:04:43 lr: 0.000014 grad: 0.1183 (0.1191) loss: 0.8569 (0.8610) time: 0.1055 data: 0.0358 max mem: 8299 +Train: [79] [3800/6250] eta: 0:04:32 lr: 0.000014 grad: 0.1135 (0.1192) loss: 0.8572 (0.8609) time: 0.1090 data: 0.0363 max mem: 8299 +Train: [79] [3900/6250] eta: 0:04:21 lr: 0.000014 grad: 0.1168 (0.1193) loss: 0.8568 (0.8608) time: 0.1096 data: 0.0339 max mem: 8299 +Train: [79] [4000/6250] eta: 0:04:09 lr: 0.000014 grad: 0.1146 (0.1193) loss: 0.8595 (0.8607) time: 0.1111 data: 0.0428 max mem: 8299 +Train: [79] [4100/6250] eta: 0:03:58 lr: 0.000014 grad: 0.1237 (0.1194) loss: 0.8528 (0.8606) time: 0.0954 data: 0.0290 max mem: 8299 +Train: [79] [4200/6250] eta: 0:03:47 lr: 0.000014 grad: 0.1144 (0.1195) loss: 0.8574 (0.8604) time: 0.0860 data: 0.0002 max mem: 8299 +Train: [79] [4300/6250] eta: 0:03:36 lr: 0.000014 grad: 0.1210 (0.1195) loss: 0.8547 (0.8603) time: 0.1006 data: 0.0306 max mem: 8299 +Train: [79] [4400/6250] eta: 0:03:25 lr: 0.000014 grad: 0.1153 (0.1195) loss: 0.8571 (0.8602) time: 0.1050 data: 0.0313 max mem: 8299 +Train: [79] [4500/6250] eta: 0:03:14 lr: 0.000014 grad: 0.1182 (0.1197) loss: 0.8556 (0.8601) time: 0.1118 data: 0.0355 max mem: 8299 +Train: [79] [4600/6250] eta: 0:03:03 lr: 0.000014 grad: 0.1214 (0.1197) loss: 0.8596 (0.8601) time: 0.1403 data: 0.0762 max mem: 8299 +Train: [79] [4700/6250] eta: 0:02:53 lr: 0.000013 grad: 0.1197 (0.1198) loss: 0.8567 (0.8600) time: 0.1340 data: 0.0631 max mem: 8299 +Train: [79] [4800/6250] eta: 0:02:42 lr: 0.000013 grad: 0.1147 (0.1199) loss: 0.8564 (0.8600) time: 0.1248 data: 0.0459 max mem: 8299 +Train: [79] [4900/6250] eta: 0:02:31 lr: 0.000013 grad: 0.1084 (0.1199) loss: 0.8537 (0.8599) time: 0.1264 data: 0.0601 max mem: 8299 +Train: [79] [5000/6250] eta: 0:02:20 lr: 0.000013 grad: 0.1166 (0.1199) loss: 0.8574 (0.8598) time: 0.1236 data: 0.0536 max mem: 8299 +Train: [79] [5100/6250] eta: 0:02:09 lr: 0.000013 grad: 0.1159 (0.1200) loss: 0.8555 (0.8598) time: 0.1197 data: 0.0477 max mem: 8299 +Train: [79] [5200/6250] eta: 0:01:58 lr: 0.000013 grad: 0.1151 (0.1201) loss: 0.8588 (0.8597) time: 0.1278 data: 0.0623 max mem: 8299 +Train: [79] [5300/6250] eta: 0:01:47 lr: 0.000013 grad: 0.1152 (0.1200) loss: 0.8588 (0.8597) time: 0.1218 data: 0.0556 max mem: 8299 +Train: [79] [5400/6250] eta: 0:01:35 lr: 0.000013 grad: 0.1144 (0.1200) loss: 0.8617 (0.8597) time: 0.1139 data: 0.0304 max mem: 8299 +Train: [79] [5500/6250] eta: 0:01:24 lr: 0.000013 grad: 0.1074 (0.1200) loss: 0.8585 (0.8597) time: 0.1101 data: 0.0281 max mem: 8299 +Train: [79] [5600/6250] eta: 0:01:13 lr: 0.000013 grad: 0.1163 (0.1199) loss: 0.8595 (0.8597) time: 0.0996 data: 0.0222 max mem: 8299 +Train: [79] [5700/6250] eta: 0:01:01 lr: 0.000013 grad: 0.1141 (0.1199) loss: 0.8532 (0.8597) time: 0.1205 data: 0.0441 max mem: 8299 +Train: [79] [5800/6250] eta: 0:00:50 lr: 0.000013 grad: 0.1115 (0.1199) loss: 0.8584 (0.8597) time: 0.1034 data: 0.0294 max mem: 8299 +Train: [79] [5900/6250] eta: 0:00:39 lr: 0.000013 grad: 0.1131 (0.1198) loss: 0.8582 (0.8597) time: 0.0980 data: 0.0255 max mem: 8299 +Train: [79] [6000/6250] eta: 0:00:27 lr: 0.000013 grad: 0.1157 (0.1198) loss: 0.8621 (0.8597) time: 0.1068 data: 0.0320 max mem: 8299 +Train: [79] [6100/6250] eta: 0:00:16 lr: 0.000013 grad: 0.1157 (0.1197) loss: 0.8585 (0.8598) time: 0.0930 data: 0.0139 max mem: 8299 +Train: [79] [6200/6250] eta: 0:00:05 lr: 0.000013 grad: 0.1071 (0.1197) loss: 0.8608 (0.8598) time: 0.1085 data: 0.0274 max mem: 8299 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1071 (0.1197) loss: 0.8619 (0.8598) time: 0.1072 data: 0.0341 max mem: 8299 +Train: [79] Total time: 0:11:42 (0.1124 s / it) +Averaged stats: lr: 0.000013 grad: 0.1071 (0.1197) loss: 0.8619 (0.8598) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:04:24 loss: 0.8829 (0.8829) time: 4.2631 data: 4.2339 max mem: 8299 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8727 (0.8740) time: 0.1097 data: 0.0853 max mem: 8299 +Eval (hcp-train-subset): [79] Total time: 0:00:12 (0.1955 s / it) +Averaged stats (hcp-train-subset): loss: 0.8727 (0.8740) +Making plots (hcp-train-subset): example=26 +Eval (hcp-val): [79] [ 0/62] eta: 0:04:58 loss: 0.8758 (0.8758) time: 4.8084 data: 4.7550 max mem: 8299 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8779 (0.8787) time: 0.1282 data: 0.1038 max mem: 8299 +Eval (hcp-val): [79] Total time: 0:00:12 (0.2004 s / it) +Averaged stats (hcp-val): loss: 0.8779 (0.8787) +Making plots (hcp-val): example=1 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-00079.pth +Train: [80] [ 0/6250] eta: 9:14:57 lr: 0.000013 grad: 0.0815 (0.0815) loss: 0.8852 (0.8852) time: 5.3276 data: 5.2103 max mem: 8299 +Train: [80] [ 100/6250] eta: 0:16:54 lr: 0.000013 grad: 0.1142 (0.1261) loss: 0.8752 (0.8730) time: 0.1342 data: 0.0579 max mem: 8299 +Train: [80] [ 200/6250] eta: 0:14:40 lr: 0.000013 grad: 0.1333 (0.1278) loss: 0.8665 (0.8724) time: 0.1273 data: 0.0516 max mem: 8299 +Train: [80] [ 300/6250] eta: 0:13:28 lr: 0.000013 grad: 0.1172 (0.1254) loss: 0.8673 (0.8712) time: 0.1049 data: 0.0165 max mem: 8299 +Train: [80] [ 400/6250] eta: 0:12:44 lr: 0.000013 grad: 0.1120 (0.1226) loss: 0.8653 (0.8699) time: 0.1142 data: 0.0337 max mem: 8299 +Train: [80] [ 500/6250] eta: 0:12:09 lr: 0.000013 grad: 0.1125 (0.1202) loss: 0.8696 (0.8693) time: 0.1056 data: 0.0282 max mem: 8299 +Train: [80] [ 600/6250] eta: 0:11:42 lr: 0.000013 grad: 0.1096 (0.1195) loss: 0.8642 (0.8684) time: 0.1073 data: 0.0340 max mem: 8299 +Train: [80] [ 700/6250] eta: 0:11:16 lr: 0.000013 grad: 0.1094 (0.1188) loss: 0.8655 (0.8681) time: 0.0985 data: 0.0138 max mem: 8299 +Train: [80] [ 800/6250] eta: 0:10:54 lr: 0.000013 grad: 0.1129 (0.1191) loss: 0.8659 (0.8678) time: 0.1037 data: 0.0264 max mem: 8299 +Train: [80] [ 900/6250] eta: 0:10:36 lr: 0.000013 grad: 0.1006 (0.1185) loss: 0.8676 (0.8675) time: 0.1104 data: 0.0240 max mem: 8299 +Train: [80] [1000/6250] eta: 0:10:17 lr: 0.000013 grad: 0.1073 (0.1179) loss: 0.8612 (0.8672) time: 0.1128 data: 0.0398 max mem: 8299 +Train: [80] [1100/6250] eta: 0:09:59 lr: 0.000013 grad: 0.1049 (0.1175) loss: 0.8635 (0.8668) time: 0.1108 data: 0.0395 max mem: 8299 +Train: [80] [1200/6250] eta: 0:09:42 lr: 0.000013 grad: 0.1098 (0.1172) loss: 0.8638 (0.8664) time: 0.0981 data: 0.0261 max mem: 8299 +Train: [80] [1300/6250] eta: 0:09:26 lr: 0.000013 grad: 0.1134 (0.1171) loss: 0.8646 (0.8661) time: 0.0883 data: 0.0097 max mem: 8299 +Train: [80] [1400/6250] eta: 0:09:12 lr: 0.000013 grad: 0.1180 (0.1174) loss: 0.8611 (0.8658) time: 0.1071 data: 0.0303 max mem: 8299 +Train: [80] [1500/6250] eta: 0:08:56 lr: 0.000013 grad: 0.1199 (0.1176) loss: 0.8671 (0.8656) time: 0.1012 data: 0.0284 max mem: 8299 +Train: [80] [1600/6250] eta: 0:08:42 lr: 0.000013 grad: 0.1127 (0.1174) loss: 0.8628 (0.8654) time: 0.1082 data: 0.0339 max mem: 8299 +Train: [80] [1700/6250] eta: 0:08:29 lr: 0.000013 grad: 0.1163 (0.1174) loss: 0.8570 (0.8650) time: 0.0949 data: 0.0232 max mem: 8299 +Train: [80] [1800/6250] eta: 0:08:16 lr: 0.000013 grad: 0.1129 (0.1173) loss: 0.8631 (0.8648) time: 0.1025 data: 0.0234 max mem: 8299 +Train: [80] [1900/6250] eta: 0:08:04 lr: 0.000013 grad: 0.1192 (0.1173) loss: 0.8578 (0.8646) time: 0.1032 data: 0.0356 max mem: 8299 +Train: [80] [2000/6250] eta: 0:07:51 lr: 0.000013 grad: 0.1121 (0.1174) loss: 0.8661 (0.8643) time: 0.1113 data: 0.0395 max mem: 8299 +Train: [80] [2100/6250] eta: 0:07:39 lr: 0.000013 grad: 0.1109 (0.1173) loss: 0.8602 (0.8640) time: 0.1051 data: 0.0374 max mem: 8299 +Train: [80] [2200/6250] eta: 0:07:27 lr: 0.000013 grad: 0.1133 (0.1173) loss: 0.8660 (0.8640) time: 0.1107 data: 0.0296 max mem: 8299 +Train: [80] [2300/6250] eta: 0:07:16 lr: 0.000013 grad: 0.1137 (0.1172) loss: 0.8604 (0.8638) time: 0.1216 data: 0.0483 max mem: 8299 +Train: [80] [2400/6250] eta: 0:07:03 lr: 0.000013 grad: 0.1063 (0.1171) loss: 0.8617 (0.8637) time: 0.1110 data: 0.0333 max mem: 8299 +Train: [80] [2500/6250] eta: 0:06:51 lr: 0.000013 grad: 0.1185 (0.1171) loss: 0.8609 (0.8636) time: 0.0994 data: 0.0265 max mem: 8299 +Train: [80] [2600/6250] eta: 0:06:40 lr: 0.000013 grad: 0.1125 (0.1172) loss: 0.8630 (0.8635) time: 0.1081 data: 0.0377 max mem: 8299 +Train: [80] [2700/6250] eta: 0:06:28 lr: 0.000013 grad: 0.1190 (0.1171) loss: 0.8564 (0.8634) time: 0.0978 data: 0.0176 max mem: 8299 +Train: [80] [2800/6250] eta: 0:06:17 lr: 0.000013 grad: 0.1199 (0.1172) loss: 0.8586 (0.8634) time: 0.1067 data: 0.0290 max mem: 8299 +Train: [80] [2900/6250] eta: 0:06:06 lr: 0.000013 grad: 0.1122 (0.1173) loss: 0.8574 (0.8634) time: 0.0948 data: 0.0123 max mem: 8299 +Train: [80] [3000/6250] eta: 0:05:55 lr: 0.000013 grad: 0.1171 (0.1176) loss: 0.8670 (0.8634) time: 0.1116 data: 0.0408 max mem: 8299 +Train: [80] [3100/6250] eta: 0:05:45 lr: 0.000013 grad: 0.1136 (0.1176) loss: 0.8596 (0.8634) time: 0.1353 data: 0.0666 max mem: 8299 +Train: [80] [3200/6250] eta: 0:05:33 lr: 0.000013 grad: 0.1195 (0.1178) loss: 0.8594 (0.8633) time: 0.1063 data: 0.0358 max mem: 8299 +Train: [80] [3300/6250] eta: 0:05:23 lr: 0.000013 grad: 0.1160 (0.1179) loss: 0.8603 (0.8633) time: 0.1188 data: 0.0491 max mem: 8299 +Train: [80] [3400/6250] eta: 0:05:12 lr: 0.000012 grad: 0.1234 (0.1180) loss: 0.8597 (0.8632) time: 0.1101 data: 0.0360 max mem: 8299 +Train: [80] [3500/6250] eta: 0:05:01 lr: 0.000012 grad: 0.1209 (0.1181) loss: 0.8600 (0.8632) time: 0.1219 data: 0.0527 max mem: 8299 +Train: [80] [3600/6250] eta: 0:04:50 lr: 0.000012 grad: 0.1104 (0.1183) loss: 0.8565 (0.8631) time: 0.1301 data: 0.0597 max mem: 8299 +Train: [80] [3700/6250] eta: 0:04:39 lr: 0.000012 grad: 0.1249 (0.1184) loss: 0.8545 (0.8630) time: 0.1237 data: 0.0519 max mem: 8299 +Train: [80] [3800/6250] eta: 0:04:28 lr: 0.000012 grad: 0.1180 (0.1185) loss: 0.8608 (0.8629) time: 0.1124 data: 0.0385 max mem: 8299 +Train: [80] [3900/6250] eta: 0:04:18 lr: 0.000012 grad: 0.1188 (0.1185) loss: 0.8575 (0.8628) time: 0.0970 data: 0.0317 max mem: 8299 +Train: [80] [4000/6250] eta: 0:04:07 lr: 0.000012 grad: 0.1153 (0.1186) loss: 0.8663 (0.8628) time: 0.1071 data: 0.0357 max mem: 8299 +Train: [80] [4100/6250] eta: 0:03:56 lr: 0.000012 grad: 0.1241 (0.1187) loss: 0.8635 (0.8628) time: 0.1147 data: 0.0441 max mem: 8299 +Train: [80] [4200/6250] eta: 0:03:45 lr: 0.000012 grad: 0.1136 (0.1188) loss: 0.8587 (0.8628) time: 0.1265 data: 0.0589 max mem: 8299 +Train: [80] [4300/6250] eta: 0:03:34 lr: 0.000012 grad: 0.1151 (0.1189) loss: 0.8657 (0.8628) time: 0.1152 data: 0.0501 max mem: 8299 +Train: [80] [4400/6250] eta: 0:03:23 lr: 0.000012 grad: 0.1078 (0.1189) loss: 0.8595 (0.8628) time: 0.1251 data: 0.0576 max mem: 8299 +Train: [80] [4500/6250] eta: 0:03:12 lr: 0.000012 grad: 0.1254 (0.1190) loss: 0.8606 (0.8627) time: 0.1006 data: 0.0271 max mem: 8299 +Train: [80] [4600/6250] eta: 0:03:02 lr: 0.000012 grad: 0.1128 (0.1191) loss: 0.8670 (0.8627) time: 0.1476 data: 0.0808 max mem: 8299 +Train: [80] [4700/6250] eta: 0:02:51 lr: 0.000012 grad: 0.1168 (0.1191) loss: 0.8621 (0.8626) time: 0.1077 data: 0.0351 max mem: 8299 +Train: [80] [4800/6250] eta: 0:02:41 lr: 0.000012 grad: 0.1184 (0.1191) loss: 0.8537 (0.8626) time: 0.1223 data: 0.0582 max mem: 8299 +Train: [80] [4900/6250] eta: 0:02:31 lr: 0.000012 grad: 0.1157 (0.1192) loss: 0.8597 (0.8625) time: 0.1228 data: 0.0442 max mem: 8299 +Train: [80] [5000/6250] eta: 0:02:20 lr: 0.000012 grad: 0.1199 (0.1192) loss: 0.8646 (0.8625) time: 0.1144 data: 0.0462 max mem: 8299 +Train: [80] [5100/6250] eta: 0:02:09 lr: 0.000012 grad: 0.1156 (0.1192) loss: 0.8594 (0.8624) time: 0.0792 data: 0.0011 max mem: 8299 +Train: [80] [5200/6250] eta: 0:01:57 lr: 0.000012 grad: 0.1201 (0.1192) loss: 0.8573 (0.8623) time: 0.1001 data: 0.0293 max mem: 8299 +Train: [80] [5300/6250] eta: 0:01:46 lr: 0.000012 grad: 0.1232 (0.1193) loss: 0.8567 (0.8622) time: 0.0979 data: 0.0303 max mem: 8299 +Train: [80] [5400/6250] eta: 0:01:35 lr: 0.000012 grad: 0.1150 (0.1193) loss: 0.8608 (0.8622) time: 0.0901 data: 0.0040 max mem: 8299 +Train: [80] [5500/6250] eta: 0:01:23 lr: 0.000012 grad: 0.1177 (0.1192) loss: 0.8577 (0.8622) time: 0.1050 data: 0.0327 max mem: 8299 +Train: [80] [5600/6250] eta: 0:01:12 lr: 0.000012 grad: 0.1167 (0.1192) loss: 0.8650 (0.8622) time: 0.1033 data: 0.0187 max mem: 8299 +Train: [80] [5700/6250] eta: 0:01:01 lr: 0.000012 grad: 0.1274 (0.1193) loss: 0.8586 (0.8621) time: 0.1137 data: 0.0369 max mem: 8299 +Train: [80] [5800/6250] eta: 0:00:50 lr: 0.000012 grad: 0.1285 (0.1193) loss: 0.8596 (0.8621) time: 0.0869 data: 0.0064 max mem: 8299 +Train: [80] [5900/6250] eta: 0:00:39 lr: 0.000012 grad: 0.1190 (0.1194) loss: 0.8572 (0.8620) time: 0.1353 data: 0.0618 max mem: 8299 +Train: [80] [6000/6250] eta: 0:00:27 lr: 0.000012 grad: 0.1169 (0.1194) loss: 0.8560 (0.8620) time: 0.1329 data: 0.0603 max mem: 8299 +Train: [80] [6100/6250] eta: 0:00:16 lr: 0.000012 grad: 0.1258 (0.1194) loss: 0.8532 (0.8619) time: 0.1125 data: 0.0361 max mem: 8299 +Train: [80] [6200/6250] eta: 0:00:05 lr: 0.000012 grad: 0.1185 (0.1195) loss: 0.8566 (0.8619) time: 0.1205 data: 0.0494 max mem: 8299 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1099 (0.1195) loss: 0.8599 (0.8618) time: 0.1451 data: 0.0789 max mem: 8299 +Train: [80] Total time: 0:11:47 (0.1132 s / it) +Averaged stats: lr: 0.000012 grad: 0.1099 (0.1195) loss: 0.8599 (0.8618) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:03:31 loss: 0.8864 (0.8864) time: 3.4111 data: 3.3451 max mem: 8299 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8701 (0.8733) time: 0.1162 data: 0.0910 max mem: 8299 +Eval (hcp-train-subset): [80] Total time: 0:00:11 (0.1838 s / it) +Averaged stats (hcp-train-subset): loss: 0.8701 (0.8733) +Eval (hcp-val): [80] [ 0/62] eta: 0:04:34 loss: 0.8767 (0.8767) time: 4.4349 data: 4.4062 max mem: 8299 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8770 (0.8784) time: 0.1081 data: 0.0829 max mem: 8299 +Eval (hcp-val): [80] Total time: 0:00:11 (0.1890 s / it) +Averaged stats (hcp-val): loss: 0.8770 (0.8784) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 6:59:56 lr: 0.000012 grad: 0.1725 (0.1725) loss: 0.8732 (0.8732) time: 4.0315 data: 3.7109 max mem: 8299 +Train: [81] [ 100/6250] eta: 0:18:02 lr: 0.000012 grad: 0.1221 (0.1581) loss: 0.8771 (0.8660) time: 0.1257 data: 0.0163 max mem: 8299 +Train: [81] [ 200/6250] eta: 0:15:16 lr: 0.000012 grad: 0.1157 (0.1423) loss: 0.8551 (0.8657) time: 0.1334 data: 0.0467 max mem: 8299 +Train: [81] [ 300/6250] eta: 0:13:56 lr: 0.000012 grad: 0.1011 (0.1344) loss: 0.8758 (0.8653) time: 0.1206 data: 0.0374 max mem: 8299 +Train: [81] [ 400/6250] eta: 0:13:05 lr: 0.000012 grad: 0.1154 (0.1293) loss: 0.8579 (0.8656) time: 0.1203 data: 0.0391 max mem: 8299 +Train: [81] [ 500/6250] eta: 0:12:24 lr: 0.000012 grad: 0.1074 (0.1263) loss: 0.8602 (0.8648) time: 0.1009 data: 0.0217 max mem: 8299 +Train: [81] [ 600/6250] eta: 0:11:54 lr: 0.000012 grad: 0.1074 (0.1245) loss: 0.8590 (0.8640) time: 0.1149 data: 0.0334 max mem: 8299 +Train: [81] [ 700/6250] eta: 0:11:24 lr: 0.000012 grad: 0.1007 (0.1230) loss: 0.8585 (0.8637) time: 0.0888 data: 0.0074 max mem: 8299 +Train: [81] [ 800/6250] eta: 0:11:02 lr: 0.000012 grad: 0.1046 (0.1220) loss: 0.8601 (0.8631) time: 0.1118 data: 0.0330 max mem: 8299 +Train: [81] [ 900/6250] eta: 0:10:44 lr: 0.000012 grad: 0.1067 (0.1215) loss: 0.8516 (0.8625) time: 0.1059 data: 0.0264 max mem: 8299 +Train: [81] [1000/6250] eta: 0:10:31 lr: 0.000012 grad: 0.1198 (0.1209) loss: 0.8538 (0.8623) time: 0.1414 data: 0.0683 max mem: 8299 +Train: [81] [1100/6250] eta: 0:10:19 lr: 0.000012 grad: 0.1167 (0.1206) loss: 0.8502 (0.8619) time: 0.1303 data: 0.0546 max mem: 8299 +Train: [81] [1200/6250] eta: 0:10:06 lr: 0.000012 grad: 0.1150 (0.1204) loss: 0.8575 (0.8614) time: 0.0961 data: 0.0188 max mem: 8299 +Train: [81] [1300/6250] eta: 0:09:53 lr: 0.000012 grad: 0.1034 (0.1202) loss: 0.8656 (0.8613) time: 0.1167 data: 0.0415 max mem: 8299 +Train: [81] [1400/6250] eta: 0:09:40 lr: 0.000012 grad: 0.1098 (0.1198) loss: 0.8563 (0.8610) time: 0.0979 data: 0.0273 max mem: 8299 +Train: [81] [1500/6250] eta: 0:09:28 lr: 0.000012 grad: 0.1117 (0.1195) loss: 0.8560 (0.8607) time: 0.1211 data: 0.0461 max mem: 8299 +Train: [81] [1600/6250] eta: 0:09:15 lr: 0.000012 grad: 0.1098 (0.1194) loss: 0.8625 (0.8606) time: 0.1204 data: 0.0520 max mem: 8299 +Train: [81] [1700/6250] eta: 0:09:01 lr: 0.000012 grad: 0.1136 (0.1192) loss: 0.8557 (0.8604) time: 0.1181 data: 0.0436 max mem: 8299 +Train: [81] [1800/6250] eta: 0:08:49 lr: 0.000012 grad: 0.1088 (0.1190) loss: 0.8628 (0.8603) time: 0.1257 data: 0.0532 max mem: 8299 +Train: [81] [1900/6250] eta: 0:08:38 lr: 0.000012 grad: 0.1038 (0.1187) loss: 0.8661 (0.8602) time: 0.1218 data: 0.0553 max mem: 8299 +Train: [81] [2000/6250] eta: 0:08:26 lr: 0.000012 grad: 0.1217 (0.1189) loss: 0.8581 (0.8601) time: 0.1323 data: 0.0634 max mem: 8299 +Train: [81] [2100/6250] eta: 0:08:14 lr: 0.000012 grad: 0.1158 (0.1192) loss: 0.8531 (0.8598) time: 0.1127 data: 0.0377 max mem: 8299 +Train: [81] [2200/6250] eta: 0:08:01 lr: 0.000012 grad: 0.1136 (0.1191) loss: 0.8582 (0.8597) time: 0.1116 data: 0.0462 max mem: 8299 +Train: [81] [2300/6250] eta: 0:07:49 lr: 0.000011 grad: 0.1106 (0.1191) loss: 0.8586 (0.8596) time: 0.1110 data: 0.0390 max mem: 8299 +Train: [81] [2400/6250] eta: 0:07:37 lr: 0.000011 grad: 0.1140 (0.1191) loss: 0.8583 (0.8595) time: 0.1219 data: 0.0474 max mem: 8299 +Train: [81] [2500/6250] eta: 0:07:25 lr: 0.000011 grad: 0.1202 (0.1191) loss: 0.8524 (0.8595) time: 0.1372 data: 0.0728 max mem: 8299 +Train: [81] [2600/6250] eta: 0:07:13 lr: 0.000011 grad: 0.1109 (0.1191) loss: 0.8638 (0.8595) time: 0.1197 data: 0.0460 max mem: 8299 +Train: [81] [2700/6250] eta: 0:07:01 lr: 0.000011 grad: 0.1150 (0.1190) loss: 0.8551 (0.8594) time: 0.1025 data: 0.0280 max mem: 8299 +Train: [81] [2800/6250] eta: 0:06:49 lr: 0.000011 grad: 0.1252 (0.1191) loss: 0.8572 (0.8593) time: 0.1349 data: 0.0644 max mem: 8299 +Train: [81] [2900/6250] eta: 0:06:38 lr: 0.000011 grad: 0.1241 (0.1193) loss: 0.8591 (0.8593) time: 0.1688 data: 0.0958 max mem: 8299 +Train: [81] [3000/6250] eta: 0:06:25 lr: 0.000011 grad: 0.1153 (0.1195) loss: 0.8544 (0.8591) time: 0.1233 data: 0.0569 max mem: 8299 +Train: [81] [3100/6250] eta: 0:06:13 lr: 0.000011 grad: 0.1209 (0.1197) loss: 0.8575 (0.8590) time: 0.1137 data: 0.0389 max mem: 8299 +Train: [81] [3200/6250] eta: 0:06:00 lr: 0.000011 grad: 0.1207 (0.1198) loss: 0.8527 (0.8590) time: 0.1106 data: 0.0370 max mem: 8299 +Train: [81] [3300/6250] eta: 0:05:49 lr: 0.000011 grad: 0.1245 (0.1200) loss: 0.8522 (0.8589) time: 0.1267 data: 0.0603 max mem: 8299 +Train: [81] [3400/6250] eta: 0:05:37 lr: 0.000011 grad: 0.1174 (0.1201) loss: 0.8620 (0.8588) time: 0.1280 data: 0.0579 max mem: 8299 +Train: [81] [3500/6250] eta: 0:05:26 lr: 0.000011 grad: 0.1192 (0.1204) loss: 0.8583 (0.8588) time: 0.1232 data: 0.0503 max mem: 8299 +Train: [81] [3600/6250] eta: 0:05:14 lr: 0.000011 grad: 0.1337 (0.1207) loss: 0.8539 (0.8586) time: 0.1162 data: 0.0433 max mem: 8299 +Train: [81] [3700/6250] eta: 0:05:02 lr: 0.000011 grad: 0.1220 (0.1209) loss: 0.8560 (0.8585) time: 0.1286 data: 0.0656 max mem: 8299 +Train: [81] [3800/6250] eta: 0:04:50 lr: 0.000011 grad: 0.1322 (0.1211) loss: 0.8444 (0.8583) time: 0.1113 data: 0.0419 max mem: 8299 +Train: [81] [3900/6250] eta: 0:04:39 lr: 0.000011 grad: 0.1202 (0.1212) loss: 0.8567 (0.8583) time: 0.1174 data: 0.0466 max mem: 8299 +Train: [81] [4000/6250] eta: 0:04:27 lr: 0.000011 grad: 0.1218 (0.1213) loss: 0.8588 (0.8582) time: 0.1328 data: 0.0625 max mem: 8299 +Train: [81] [4100/6250] eta: 0:04:15 lr: 0.000011 grad: 0.1348 (0.1214) loss: 0.8527 (0.8582) time: 0.1187 data: 0.0440 max mem: 8299 +Train: [81] [4200/6250] eta: 0:04:03 lr: 0.000011 grad: 0.1195 (0.1214) loss: 0.8558 (0.8581) time: 0.1334 data: 0.0634 max mem: 8299 +Train: [81] [4300/6250] eta: 0:03:52 lr: 0.000011 grad: 0.1200 (0.1215) loss: 0.8606 (0.8581) time: 0.1268 data: 0.0541 max mem: 8299 +Train: [81] [4400/6250] eta: 0:03:40 lr: 0.000011 grad: 0.1202 (0.1216) loss: 0.8552 (0.8580) time: 0.1059 data: 0.0366 max mem: 8299 +Train: [81] [4500/6250] eta: 0:03:28 lr: 0.000011 grad: 0.1218 (0.1216) loss: 0.8599 (0.8580) time: 0.1183 data: 0.0553 max mem: 8299 +Train: [81] [4600/6250] eta: 0:03:16 lr: 0.000011 grad: 0.1183 (0.1216) loss: 0.8621 (0.8580) time: 0.1316 data: 0.0630 max mem: 8299 +Train: [81] [4700/6250] eta: 0:03:05 lr: 0.000011 grad: 0.1191 (0.1216) loss: 0.8606 (0.8580) time: 0.1450 data: 0.0744 max mem: 8299 +Train: [81] [4800/6250] eta: 0:02:53 lr: 0.000011 grad: 0.1120 (0.1216) loss: 0.8537 (0.8580) time: 0.1220 data: 0.0514 max mem: 8299 +Train: [81] [4900/6250] eta: 0:02:41 lr: 0.000011 grad: 0.1136 (0.1216) loss: 0.8612 (0.8581) time: 0.1431 data: 0.0750 max mem: 8299 +Train: [81] [5000/6250] eta: 0:02:30 lr: 0.000011 grad: 0.1209 (0.1216) loss: 0.8574 (0.8582) time: 0.1208 data: 0.0551 max mem: 8299 +Train: [81] [5100/6250] eta: 0:02:18 lr: 0.000011 grad: 0.1185 (0.1216) loss: 0.8589 (0.8582) time: 0.1148 data: 0.0404 max mem: 8299 +Train: [81] [5200/6250] eta: 0:02:05 lr: 0.000011 grad: 0.1171 (0.1216) loss: 0.8605 (0.8582) time: 0.1166 data: 0.0464 max mem: 8299 +Train: [81] [5300/6250] eta: 0:01:53 lr: 0.000011 grad: 0.1087 (0.1217) loss: 0.8632 (0.8583) time: 0.1076 data: 0.0333 max mem: 8299 +Train: [81] [5400/6250] eta: 0:01:41 lr: 0.000011 grad: 0.1231 (0.1217) loss: 0.8529 (0.8583) time: 0.1157 data: 0.0375 max mem: 8299 +Train: [81] [5500/6250] eta: 0:01:29 lr: 0.000011 grad: 0.1152 (0.1216) loss: 0.8628 (0.8583) time: 0.1070 data: 0.0288 max mem: 8299 +Train: [81] [5600/6250] eta: 0:01:17 lr: 0.000011 grad: 0.1166 (0.1216) loss: 0.8650 (0.8584) time: 0.1042 data: 0.0340 max mem: 8299 +Train: [81] [5700/6250] eta: 0:01:05 lr: 0.000011 grad: 0.1164 (0.1216) loss: 0.8601 (0.8584) time: 0.0920 data: 0.0152 max mem: 8299 +Train: [81] [5800/6250] eta: 0:00:53 lr: 0.000011 grad: 0.1164 (0.1216) loss: 0.8606 (0.8584) time: 0.1119 data: 0.0358 max mem: 8299 +Train: [81] [5900/6250] eta: 0:00:41 lr: 0.000011 grad: 0.1195 (0.1216) loss: 0.8608 (0.8585) time: 0.1205 data: 0.0476 max mem: 8299 +Train: [81] [6000/6250] eta: 0:00:29 lr: 0.000011 grad: 0.1220 (0.1216) loss: 0.8626 (0.8586) time: 0.1284 data: 0.0549 max mem: 8299 +Train: [81] [6100/6250] eta: 0:00:17 lr: 0.000011 grad: 0.1267 (0.1216) loss: 0.8604 (0.8586) time: 0.0926 data: 0.0199 max mem: 8299 +Train: [81] [6200/6250] eta: 0:00:05 lr: 0.000011 grad: 0.1263 (0.1216) loss: 0.8596 (0.8586) time: 0.1273 data: 0.0653 max mem: 8299 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1132 (0.1216) loss: 0.8632 (0.8586) time: 0.1272 data: 0.0559 max mem: 8299 +Train: [81] Total time: 0:12:24 (0.1191 s / it) +Averaged stats: lr: 0.000011 grad: 0.1132 (0.1216) loss: 0.8632 (0.8586) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:05:19 loss: 0.8768 (0.8768) time: 5.1543 data: 5.1262 max mem: 8299 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8695 (0.8716) time: 0.1126 data: 0.0886 max mem: 8299 +Eval (hcp-train-subset): [81] Total time: 0:00:11 (0.1917 s / it) +Averaged stats (hcp-train-subset): loss: 0.8695 (0.8716) +Eval (hcp-val): [81] [ 0/62] eta: 0:03:05 loss: 0.8750 (0.8750) time: 2.9984 data: 2.9371 max mem: 8299 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8757 (0.8776) time: 0.1269 data: 0.1017 max mem: 8299 +Eval (hcp-val): [81] Total time: 0:00:12 (0.1986 s / it) +Averaged stats (hcp-val): loss: 0.8757 (0.8776) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 8:06:52 lr: 0.000011 grad: 0.0894 (0.0894) loss: 0.8871 (0.8871) time: 4.6739 data: 4.4354 max mem: 8299 +Train: [82] [ 100/6250] eta: 0:17:34 lr: 0.000011 grad: 0.1164 (0.1350) loss: 0.8681 (0.8728) time: 0.1378 data: 0.0577 max mem: 8299 +Train: [82] [ 200/6250] eta: 0:14:37 lr: 0.000011 grad: 0.1233 (0.1304) loss: 0.8637 (0.8708) time: 0.1106 data: 0.0289 max mem: 8299 +Train: [82] [ 300/6250] eta: 0:13:42 lr: 0.000011 grad: 0.1173 (0.1273) loss: 0.8549 (0.8678) time: 0.1286 data: 0.0490 max mem: 8299 +Train: [82] [ 400/6250] eta: 0:12:51 lr: 0.000011 grad: 0.1206 (0.1249) loss: 0.8627 (0.8668) time: 0.1040 data: 0.0180 max mem: 8299 +Train: [82] [ 500/6250] eta: 0:12:13 lr: 0.000011 grad: 0.1124 (0.1234) loss: 0.8614 (0.8660) time: 0.1147 data: 0.0426 max mem: 8299 +Train: [82] [ 600/6250] eta: 0:11:43 lr: 0.000011 grad: 0.1157 (0.1215) loss: 0.8642 (0.8660) time: 0.0995 data: 0.0146 max mem: 8299 +Train: [82] [ 700/6250] eta: 0:11:19 lr: 0.000011 grad: 0.1017 (0.1204) loss: 0.8724 (0.8660) time: 0.1193 data: 0.0391 max mem: 8299 +Train: [82] [ 800/6250] eta: 0:11:08 lr: 0.000011 grad: 0.1112 (0.1194) loss: 0.8668 (0.8665) time: 0.1234 data: 0.0524 max mem: 8299 +Train: [82] [ 900/6250] eta: 0:11:00 lr: 0.000011 grad: 0.1065 (0.1185) loss: 0.8654 (0.8665) time: 0.1278 data: 0.0519 max mem: 8299 +Train: [82] [1000/6250] eta: 0:10:49 lr: 0.000011 grad: 0.1185 (0.1183) loss: 0.8626 (0.8665) time: 0.1297 data: 0.0663 max mem: 8299 +Train: [82] [1100/6250] eta: 0:10:39 lr: 0.000011 grad: 0.1053 (0.1182) loss: 0.8719 (0.8663) time: 0.1149 data: 0.0401 max mem: 8299 +Train: [82] [1200/6250] eta: 0:10:27 lr: 0.000011 grad: 0.1091 (0.1181) loss: 0.8665 (0.8662) time: 0.1189 data: 0.0472 max mem: 8299 +Train: [82] [1300/6250] eta: 0:10:19 lr: 0.000011 grad: 0.1199 (0.1183) loss: 0.8640 (0.8659) time: 0.1597 data: 0.0949 max mem: 8299 +Train: [82] [1400/6250] eta: 0:10:05 lr: 0.000010 grad: 0.1117 (0.1186) loss: 0.8607 (0.8656) time: 0.1497 data: 0.0803 max mem: 8299 +Train: [82] [1500/6250] eta: 0:09:56 lr: 0.000010 grad: 0.1125 (0.1185) loss: 0.8585 (0.8653) time: 0.1781 data: 0.1075 max mem: 8299 +Train: [82] [1600/6250] eta: 0:09:41 lr: 0.000010 grad: 0.1166 (0.1188) loss: 0.8575 (0.8649) time: 0.1265 data: 0.0581 max mem: 8299 +Train: [82] [1700/6250] eta: 0:09:26 lr: 0.000010 grad: 0.1202 (0.1191) loss: 0.8546 (0.8645) time: 0.1246 data: 0.0489 max mem: 8299 +Train: [82] [1800/6250] eta: 0:09:14 lr: 0.000010 grad: 0.1156 (0.1193) loss: 0.8571 (0.8641) time: 0.1274 data: 0.0618 max mem: 8299 +Train: [82] [1900/6250] eta: 0:09:01 lr: 0.000010 grad: 0.1192 (0.1195) loss: 0.8644 (0.8638) time: 0.1343 data: 0.0570 max mem: 8299 +Train: [82] [2000/6250] eta: 0:08:48 lr: 0.000010 grad: 0.1310 (0.1197) loss: 0.8548 (0.8633) time: 0.0809 data: 0.0101 max mem: 8299 +Train: [82] [2100/6250] eta: 0:08:34 lr: 0.000010 grad: 0.1260 (0.1200) loss: 0.8466 (0.8629) time: 0.1227 data: 0.0525 max mem: 8299 +Train: [82] [2200/6250] eta: 0:08:21 lr: 0.000010 grad: 0.1143 (0.1200) loss: 0.8579 (0.8626) time: 0.1211 data: 0.0481 max mem: 8299 +Train: [82] [2300/6250] eta: 0:08:09 lr: 0.000010 grad: 0.1145 (0.1200) loss: 0.8590 (0.8624) time: 0.1230 data: 0.0507 max mem: 8299 +Train: [82] [2400/6250] eta: 0:07:56 lr: 0.000010 grad: 0.1202 (0.1202) loss: 0.8547 (0.8622) time: 0.1194 data: 0.0492 max mem: 8299 +Train: [82] [2500/6250] eta: 0:07:43 lr: 0.000010 grad: 0.1180 (0.1202) loss: 0.8610 (0.8621) time: 0.1293 data: 0.0623 max mem: 8299 +Train: [82] [2600/6250] eta: 0:07:32 lr: 0.000010 grad: 0.1243 (0.1203) loss: 0.8525 (0.8618) time: 0.1417 data: 0.0723 max mem: 8299 +Train: [82] [2700/6250] eta: 0:07:19 lr: 0.000010 grad: 0.1212 (0.1204) loss: 0.8529 (0.8616) time: 0.1280 data: 0.0511 max mem: 8299 +Train: [82] [2800/6250] eta: 0:07:06 lr: 0.000010 grad: 0.1327 (0.1206) loss: 0.8540 (0.8614) time: 0.1035 data: 0.0259 max mem: 8299 +Train: [82] [2900/6250] eta: 0:06:53 lr: 0.000010 grad: 0.1134 (0.1205) loss: 0.8566 (0.8613) time: 0.1320 data: 0.0614 max mem: 8299 +Train: [82] [3000/6250] eta: 0:06:40 lr: 0.000010 grad: 0.1180 (0.1205) loss: 0.8568 (0.8613) time: 0.1118 data: 0.0373 max mem: 8299 +Train: [82] [3100/6250] eta: 0:06:28 lr: 0.000010 grad: 0.1204 (0.1205) loss: 0.8556 (0.8612) time: 0.1025 data: 0.0285 max mem: 8299 +Train: [82] [3200/6250] eta: 0:06:15 lr: 0.000010 grad: 0.1271 (0.1205) loss: 0.8536 (0.8611) time: 0.1254 data: 0.0604 max mem: 8299 +Train: [82] [3300/6250] eta: 0:06:03 lr: 0.000010 grad: 0.1041 (0.1205) loss: 0.8637 (0.8609) time: 0.1067 data: 0.0316 max mem: 8299 +Train: [82] [3400/6250] eta: 0:05:50 lr: 0.000010 grad: 0.1216 (0.1205) loss: 0.8598 (0.8608) time: 0.1407 data: 0.0665 max mem: 8299 +Train: [82] [3500/6250] eta: 0:05:38 lr: 0.000010 grad: 0.1174 (0.1205) loss: 0.8609 (0.8608) time: 0.1318 data: 0.0634 max mem: 8299 +Train: [82] [3600/6250] eta: 0:05:26 lr: 0.000010 grad: 0.1277 (0.1206) loss: 0.8598 (0.8606) time: 0.1110 data: 0.0380 max mem: 8299 +Train: [82] [3700/6250] eta: 0:05:13 lr: 0.000010 grad: 0.1171 (0.1207) loss: 0.8548 (0.8605) time: 0.1243 data: 0.0579 max mem: 8299 +Train: [82] [3800/6250] eta: 0:05:01 lr: 0.000010 grad: 0.1147 (0.1207) loss: 0.8575 (0.8604) time: 0.1178 data: 0.0473 max mem: 8299 +Train: [82] [3900/6250] eta: 0:04:48 lr: 0.000010 grad: 0.1204 (0.1208) loss: 0.8633 (0.8603) time: 0.1270 data: 0.0544 max mem: 8299 +Train: [82] [4000/6250] eta: 0:04:36 lr: 0.000010 grad: 0.1202 (0.1209) loss: 0.8545 (0.8602) time: 0.1168 data: 0.0488 max mem: 8299 +Train: [82] [4100/6250] eta: 0:04:24 lr: 0.000010 grad: 0.1172 (0.1211) loss: 0.8602 (0.8601) time: 0.0949 data: 0.0162 max mem: 8299 +Train: [82] [4200/6250] eta: 0:04:11 lr: 0.000010 grad: 0.1286 (0.1212) loss: 0.8543 (0.8599) time: 0.1127 data: 0.0409 max mem: 8299 +Train: [82] [4300/6250] eta: 0:03:59 lr: 0.000010 grad: 0.1183 (0.1213) loss: 0.8502 (0.8598) time: 0.0948 data: 0.0215 max mem: 8299 +Train: [82] [4400/6250] eta: 0:03:47 lr: 0.000010 grad: 0.1277 (0.1213) loss: 0.8518 (0.8597) time: 0.1246 data: 0.0537 max mem: 8299 +Train: [82] [4500/6250] eta: 0:03:34 lr: 0.000010 grad: 0.1206 (0.1215) loss: 0.8556 (0.8595) time: 0.1105 data: 0.0404 max mem: 8299 +Train: [82] [4600/6250] eta: 0:03:22 lr: 0.000010 grad: 0.1177 (0.1215) loss: 0.8541 (0.8595) time: 0.1182 data: 0.0533 max mem: 8299 +Train: [82] [4700/6250] eta: 0:03:10 lr: 0.000010 grad: 0.1184 (0.1216) loss: 0.8565 (0.8594) time: 0.1080 data: 0.0264 max mem: 8299 +Train: [82] [4800/6250] eta: 0:02:58 lr: 0.000010 grad: 0.1231 (0.1217) loss: 0.8576 (0.8593) time: 0.1357 data: 0.0585 max mem: 8299 +Train: [82] [4900/6250] eta: 0:02:46 lr: 0.000010 grad: 0.1288 (0.1218) loss: 0.8594 (0.8592) time: 0.1141 data: 0.0438 max mem: 8299 +Train: [82] [5000/6250] eta: 0:02:34 lr: 0.000010 grad: 0.1227 (0.1220) loss: 0.8597 (0.8591) time: 0.1181 data: 0.0493 max mem: 8299 +Train: [82] [5100/6250] eta: 0:02:21 lr: 0.000010 grad: 0.1137 (0.1220) loss: 0.8591 (0.8591) time: 0.1153 data: 0.0421 max mem: 8299 +Train: [82] [5200/6250] eta: 0:02:09 lr: 0.000010 grad: 0.1221 (0.1221) loss: 0.8615 (0.8591) time: 0.0799 data: 0.0038 max mem: 8299 +Train: [82] [5300/6250] eta: 0:01:56 lr: 0.000010 grad: 0.1270 (0.1222) loss: 0.8573 (0.8590) time: 0.1143 data: 0.0408 max mem: 8299 +Train: [82] [5400/6250] eta: 0:01:44 lr: 0.000010 grad: 0.1306 (0.1223) loss: 0.8565 (0.8590) time: 0.1152 data: 0.0462 max mem: 8299 +Train: [82] [5500/6250] eta: 0:01:31 lr: 0.000010 grad: 0.1237 (0.1224) loss: 0.8598 (0.8590) time: 0.1035 data: 0.0302 max mem: 8299 +Train: [82] [5600/6250] eta: 0:01:19 lr: 0.000010 grad: 0.1323 (0.1226) loss: 0.8602 (0.8589) time: 0.1103 data: 0.0372 max mem: 8299 +Train: [82] [5700/6250] eta: 0:01:06 lr: 0.000010 grad: 0.1343 (0.1228) loss: 0.8487 (0.8589) time: 0.1097 data: 0.0282 max mem: 8299 +Train: [82] [5800/6250] eta: 0:00:54 lr: 0.000010 grad: 0.1237 (0.1229) loss: 0.8484 (0.8588) time: 0.0998 data: 0.0319 max mem: 8299 +Train: [82] [5900/6250] eta: 0:00:42 lr: 0.000010 grad: 0.1216 (0.1230) loss: 0.8545 (0.8587) time: 0.0945 data: 0.0139 max mem: 8299 +Train: [82] [6000/6250] eta: 0:00:30 lr: 0.000010 grad: 0.1360 (0.1232) loss: 0.8517 (0.8586) time: 0.1214 data: 0.0542 max mem: 8299 +Train: [82] [6100/6250] eta: 0:00:18 lr: 0.000010 grad: 0.1244 (0.1234) loss: 0.8595 (0.8585) time: 0.1252 data: 0.0520 max mem: 8299 +Train: [82] [6200/6250] eta: 0:00:06 lr: 0.000010 grad: 0.1298 (0.1235) loss: 0.8514 (0.8584) time: 0.1195 data: 0.0469 max mem: 8299 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1216 (0.1235) loss: 0.8585 (0.8584) time: 0.1225 data: 0.0524 max mem: 8299 +Train: [82] Total time: 0:12:38 (0.1214 s / it) +Averaged stats: lr: 0.000010 grad: 0.1216 (0.1235) loss: 0.8585 (0.8584) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:04:22 loss: 0.8771 (0.8771) time: 4.2313 data: 4.2032 max mem: 8299 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8692 (0.8703) time: 0.0998 data: 0.0745 max mem: 8299 +Eval (hcp-train-subset): [82] Total time: 0:00:11 (0.1918 s / it) +Averaged stats (hcp-train-subset): loss: 0.8692 (0.8703) +Eval (hcp-val): [82] [ 0/62] eta: 0:03:31 loss: 0.8729 (0.8729) time: 3.4171 data: 3.3266 max mem: 8299 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8759 (0.8782) time: 0.1155 data: 0.0908 max mem: 8299 +Eval (hcp-val): [82] Total time: 0:00:11 (0.1887 s / it) +Averaged stats (hcp-val): loss: 0.8759 (0.8782) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 7:24:10 lr: 0.000010 grad: 0.0735 (0.0735) loss: 0.8986 (0.8986) time: 4.2641 data: 4.0257 max mem: 8299 +Train: [83] [ 100/6250] eta: 0:18:21 lr: 0.000010 grad: 0.1314 (0.1602) loss: 0.8671 (0.8614) time: 0.1120 data: 0.0218 max mem: 8299 +Train: [83] [ 200/6250] eta: 0:15:23 lr: 0.000010 grad: 0.1126 (0.1461) loss: 0.8651 (0.8594) time: 0.1092 data: 0.0195 max mem: 8299 +Train: [83] [ 300/6250] eta: 0:14:03 lr: 0.000010 grad: 0.1118 (0.1380) loss: 0.8680 (0.8600) time: 0.1020 data: 0.0132 max mem: 8299 +Train: [83] [ 400/6250] eta: 0:13:08 lr: 0.000010 grad: 0.1216 (0.1360) loss: 0.8689 (0.8606) time: 0.1047 data: 0.0237 max mem: 8299 +Train: [83] [ 500/6250] eta: 0:12:28 lr: 0.000010 grad: 0.1184 (0.1343) loss: 0.8667 (0.8606) time: 0.1145 data: 0.0372 max mem: 8299 +Train: [83] [ 600/6250] eta: 0:11:54 lr: 0.000010 grad: 0.1117 (0.1317) loss: 0.8631 (0.8608) time: 0.1040 data: 0.0290 max mem: 8299 +Train: [83] [ 700/6250] eta: 0:11:29 lr: 0.000009 grad: 0.1208 (0.1302) loss: 0.8657 (0.8610) time: 0.1127 data: 0.0299 max mem: 8299 +Train: [83] [ 800/6250] eta: 0:11:06 lr: 0.000009 grad: 0.1133 (0.1286) loss: 0.8634 (0.8611) time: 0.0910 data: 0.0089 max mem: 8299 +Train: [83] [ 900/6250] eta: 0:10:48 lr: 0.000009 grad: 0.1158 (0.1278) loss: 0.8631 (0.8610) time: 0.1120 data: 0.0407 max mem: 8299 +Train: [83] [1000/6250] eta: 0:10:38 lr: 0.000009 grad: 0.1109 (0.1276) loss: 0.8632 (0.8608) time: 0.1389 data: 0.0595 max mem: 8299 +Train: [83] [1100/6250] eta: 0:10:26 lr: 0.000009 grad: 0.1215 (0.1271) loss: 0.8534 (0.8604) time: 0.1216 data: 0.0504 max mem: 8299 +Train: [83] [1200/6250] eta: 0:10:15 lr: 0.000009 grad: 0.1272 (0.1269) loss: 0.8537 (0.8599) time: 0.0967 data: 0.0193 max mem: 8299 +Train: [83] [1300/6250] eta: 0:10:02 lr: 0.000009 grad: 0.1199 (0.1269) loss: 0.8564 (0.8594) time: 0.1185 data: 0.0431 max mem: 8299 +Train: [83] [1400/6250] eta: 0:09:48 lr: 0.000009 grad: 0.1182 (0.1270) loss: 0.8636 (0.8590) time: 0.1075 data: 0.0370 max mem: 8299 +Train: [83] [1500/6250] eta: 0:09:37 lr: 0.000009 grad: 0.1151 (0.1270) loss: 0.8610 (0.8586) time: 0.1170 data: 0.0446 max mem: 8299 +Train: [83] [1600/6250] eta: 0:09:26 lr: 0.000009 grad: 0.1227 (0.1268) loss: 0.8486 (0.8583) time: 0.1130 data: 0.0464 max mem: 8299 +Train: [83] [1700/6250] eta: 0:09:15 lr: 0.000009 grad: 0.1292 (0.1268) loss: 0.8543 (0.8580) time: 0.1329 data: 0.0595 max mem: 8299 +Train: [83] [1800/6250] eta: 0:09:03 lr: 0.000009 grad: 0.1220 (0.1265) loss: 0.8546 (0.8580) time: 0.1369 data: 0.0603 max mem: 8299 +Train: [83] [1900/6250] eta: 0:08:51 lr: 0.000009 grad: 0.1340 (0.1264) loss: 0.8517 (0.8578) time: 0.1295 data: 0.0652 max mem: 8299 +Train: [83] [2000/6250] eta: 0:08:38 lr: 0.000009 grad: 0.1219 (0.1264) loss: 0.8557 (0.8575) time: 0.1105 data: 0.0365 max mem: 8299 +Train: [83] [2100/6250] eta: 0:08:26 lr: 0.000009 grad: 0.1299 (0.1264) loss: 0.8508 (0.8572) time: 0.1030 data: 0.0342 max mem: 8299 +Train: [83] [2200/6250] eta: 0:08:14 lr: 0.000009 grad: 0.1352 (0.1265) loss: 0.8570 (0.8571) time: 0.1116 data: 0.0310 max mem: 8299 +Train: [83] [2300/6250] eta: 0:08:02 lr: 0.000009 grad: 0.1317 (0.1266) loss: 0.8581 (0.8570) time: 0.1094 data: 0.0283 max mem: 8299 +Train: [83] [2400/6250] eta: 0:07:51 lr: 0.000009 grad: 0.1331 (0.1269) loss: 0.8452 (0.8567) time: 0.1329 data: 0.0644 max mem: 8299 +Train: [83] [2500/6250] eta: 0:07:39 lr: 0.000009 grad: 0.1372 (0.1270) loss: 0.8504 (0.8565) time: 0.1284 data: 0.0578 max mem: 8299 +Train: [83] [2600/6250] eta: 0:07:26 lr: 0.000009 grad: 0.1308 (0.1272) loss: 0.8527 (0.8564) time: 0.1195 data: 0.0517 max mem: 8299 +Train: [83] [2700/6250] eta: 0:07:13 lr: 0.000009 grad: 0.1178 (0.1272) loss: 0.8550 (0.8564) time: 0.1114 data: 0.0372 max mem: 8299 +Train: [83] [2800/6250] eta: 0:07:00 lr: 0.000009 grad: 0.1237 (0.1273) loss: 0.8589 (0.8563) time: 0.1109 data: 0.0374 max mem: 8299 +Train: [83] [2900/6250] eta: 0:06:48 lr: 0.000009 grad: 0.1186 (0.1272) loss: 0.8572 (0.8563) time: 0.1157 data: 0.0446 max mem: 8299 +Train: [83] [3000/6250] eta: 0:06:36 lr: 0.000009 grad: 0.1162 (0.1271) loss: 0.8647 (0.8562) time: 0.1220 data: 0.0510 max mem: 8299 +Train: [83] [3100/6250] eta: 0:06:23 lr: 0.000009 grad: 0.1104 (0.1271) loss: 0.8603 (0.8563) time: 0.1240 data: 0.0558 max mem: 8299 +Train: [83] [3200/6250] eta: 0:06:11 lr: 0.000009 grad: 0.1204 (0.1272) loss: 0.8549 (0.8563) time: 0.1067 data: 0.0366 max mem: 8299 +Train: [83] [3300/6250] eta: 0:05:58 lr: 0.000009 grad: 0.1226 (0.1270) loss: 0.8563 (0.8564) time: 0.1392 data: 0.0726 max mem: 8299 +Train: [83] [3400/6250] eta: 0:05:46 lr: 0.000009 grad: 0.1146 (0.1268) loss: 0.8632 (0.8564) time: 0.1050 data: 0.0264 max mem: 8299 +Train: [83] [3500/6250] eta: 0:05:34 lr: 0.000009 grad: 0.1194 (0.1268) loss: 0.8509 (0.8564) time: 0.1148 data: 0.0476 max mem: 8299 +Train: [83] [3600/6250] eta: 0:05:22 lr: 0.000009 grad: 0.1240 (0.1267) loss: 0.8549 (0.8565) time: 0.1150 data: 0.0380 max mem: 8299 +Train: [83] [3700/6250] eta: 0:05:11 lr: 0.000009 grad: 0.1271 (0.1267) loss: 0.8548 (0.8565) time: 0.2215 data: 0.1506 max mem: 8299 +Train: [83] [3800/6250] eta: 0:04:58 lr: 0.000009 grad: 0.1153 (0.1266) loss: 0.8646 (0.8566) time: 0.1192 data: 0.0485 max mem: 8299 +Train: [83] [3900/6250] eta: 0:04:46 lr: 0.000009 grad: 0.1282 (0.1266) loss: 0.8545 (0.8566) time: 0.1304 data: 0.0577 max mem: 8299 +Train: [83] [4000/6250] eta: 0:04:34 lr: 0.000009 grad: 0.1213 (0.1266) loss: 0.8561 (0.8566) time: 0.0937 data: 0.0244 max mem: 8299 +Train: [83] [4100/6250] eta: 0:04:21 lr: 0.000009 grad: 0.1291 (0.1265) loss: 0.8564 (0.8566) time: 0.1055 data: 0.0336 max mem: 8299 +Train: [83] [4200/6250] eta: 0:04:09 lr: 0.000009 grad: 0.1260 (0.1265) loss: 0.8553 (0.8566) time: 0.1185 data: 0.0465 max mem: 8299 +Train: [83] [4300/6250] eta: 0:03:56 lr: 0.000009 grad: 0.1102 (0.1263) loss: 0.8632 (0.8567) time: 0.1164 data: 0.0481 max mem: 8299 +Train: [83] [4400/6250] eta: 0:03:44 lr: 0.000009 grad: 0.1097 (0.1261) loss: 0.8633 (0.8568) time: 0.1043 data: 0.0302 max mem: 8299 +Train: [83] [4500/6250] eta: 0:03:32 lr: 0.000009 grad: 0.1178 (0.1260) loss: 0.8586 (0.8568) time: 0.1068 data: 0.0327 max mem: 8299 +Train: [83] [4600/6250] eta: 0:03:20 lr: 0.000009 grad: 0.1217 (0.1260) loss: 0.8581 (0.8569) time: 0.1323 data: 0.0673 max mem: 8299 +Train: [83] [4700/6250] eta: 0:03:08 lr: 0.000009 grad: 0.1165 (0.1260) loss: 0.8557 (0.8568) time: 0.1334 data: 0.0575 max mem: 8299 +Train: [83] [4800/6250] eta: 0:02:56 lr: 0.000009 grad: 0.1164 (0.1259) loss: 0.8503 (0.8568) time: 0.1298 data: 0.0536 max mem: 8299 +Train: [83] [4900/6250] eta: 0:02:44 lr: 0.000009 grad: 0.1098 (0.1257) loss: 0.8529 (0.8568) time: 0.1232 data: 0.0434 max mem: 8299 +Train: [83] [5000/6250] eta: 0:02:32 lr: 0.000009 grad: 0.1181 (0.1257) loss: 0.8555 (0.8568) time: 0.1135 data: 0.0391 max mem: 8299 +Train: [83] [5100/6250] eta: 0:02:19 lr: 0.000009 grad: 0.1236 (0.1257) loss: 0.8595 (0.8568) time: 0.1183 data: 0.0387 max mem: 8299 +Train: [83] [5200/6250] eta: 0:02:07 lr: 0.000009 grad: 0.1263 (0.1256) loss: 0.8596 (0.8569) time: 0.1093 data: 0.0332 max mem: 8299 +Train: [83] [5300/6250] eta: 0:01:55 lr: 0.000009 grad: 0.1135 (0.1257) loss: 0.8566 (0.8569) time: 0.0946 data: 0.0241 max mem: 8299 +Train: [83] [5400/6250] eta: 0:01:42 lr: 0.000009 grad: 0.1207 (0.1256) loss: 0.8566 (0.8569) time: 0.1091 data: 0.0329 max mem: 8299 +Train: [83] [5500/6250] eta: 0:01:30 lr: 0.000009 grad: 0.1133 (0.1256) loss: 0.8612 (0.8569) time: 0.1060 data: 0.0278 max mem: 8299 +Train: [83] [5600/6250] eta: 0:01:18 lr: 0.000009 grad: 0.1271 (0.1257) loss: 0.8541 (0.8569) time: 0.0892 data: 0.0159 max mem: 8299 +Train: [83] [5700/6250] eta: 0:01:06 lr: 0.000009 grad: 0.1306 (0.1257) loss: 0.8552 (0.8569) time: 0.0975 data: 0.0210 max mem: 8299 +Train: [83] [5800/6250] eta: 0:00:54 lr: 0.000009 grad: 0.1193 (0.1257) loss: 0.8653 (0.8569) time: 0.1262 data: 0.0541 max mem: 8299 +Train: [83] [5900/6250] eta: 0:00:42 lr: 0.000009 grad: 0.1222 (0.1257) loss: 0.8549 (0.8569) time: 0.1079 data: 0.0449 max mem: 8299 +Train: [83] [6000/6250] eta: 0:00:30 lr: 0.000009 grad: 0.1305 (0.1257) loss: 0.8648 (0.8569) time: 0.1219 data: 0.0462 max mem: 8299 +Train: [83] [6100/6250] eta: 0:00:17 lr: 0.000009 grad: 0.1227 (0.1257) loss: 0.8553 (0.8569) time: 0.1108 data: 0.0343 max mem: 8299 +Train: [83] [6200/6250] eta: 0:00:05 lr: 0.000009 grad: 0.1210 (0.1257) loss: 0.8615 (0.8569) time: 0.1202 data: 0.0510 max mem: 8299 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1268 (0.1257) loss: 0.8427 (0.8569) time: 0.1112 data: 0.0416 max mem: 8299 +Train: [83] Total time: 0:12:33 (0.1206 s / it) +Averaged stats: lr: 0.000009 grad: 0.1268 (0.1257) loss: 0.8427 (0.8569) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:05:10 loss: 0.8746 (0.8746) time: 5.0157 data: 4.9825 max mem: 8299 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8662 (0.8689) time: 0.1302 data: 0.1060 max mem: 8299 +Eval (hcp-train-subset): [83] Total time: 0:00:12 (0.2035 s / it) +Averaged stats (hcp-train-subset): loss: 0.8662 (0.8689) +Eval (hcp-val): [83] [ 0/62] eta: 0:04:02 loss: 0.8759 (0.8759) time: 3.9170 data: 3.8265 max mem: 8299 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8750 (0.8774) time: 0.1291 data: 0.1037 max mem: 8299 +Eval (hcp-val): [83] Total time: 0:00:12 (0.1976 s / it) +Averaged stats (hcp-val): loss: 0.8750 (0.8774) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 7:51:07 lr: 0.000009 grad: 0.0594 (0.0594) loss: 0.8908 (0.8908) time: 4.5228 data: 4.2822 max mem: 8299 +Train: [84] [ 100/6250] eta: 0:17:49 lr: 0.000009 grad: 0.1236 (0.1299) loss: 0.8644 (0.8751) time: 0.1390 data: 0.0471 max mem: 8299 +Train: [84] [ 200/6250] eta: 0:14:47 lr: 0.000009 grad: 0.1143 (0.1246) loss: 0.8662 (0.8726) time: 0.1076 data: 0.0198 max mem: 8299 +Train: [84] [ 300/6250] eta: 0:13:47 lr: 0.000008 grad: 0.1061 (0.1246) loss: 0.8707 (0.8713) time: 0.1243 data: 0.0342 max mem: 8299 +Train: [84] [ 400/6250] eta: 0:13:00 lr: 0.000008 grad: 0.1082 (0.1232) loss: 0.8579 (0.8700) time: 0.1181 data: 0.0342 max mem: 8299 +Train: [84] [ 500/6250] eta: 0:12:19 lr: 0.000008 grad: 0.0980 (0.1208) loss: 0.8734 (0.8697) time: 0.1103 data: 0.0301 max mem: 8299 +Train: [84] [ 600/6250] eta: 0:11:50 lr: 0.000008 grad: 0.1053 (0.1197) loss: 0.8672 (0.8693) time: 0.1138 data: 0.0303 max mem: 8299 +Train: [84] [ 700/6250] eta: 0:11:23 lr: 0.000008 grad: 0.1120 (0.1198) loss: 0.8659 (0.8689) time: 0.1069 data: 0.0227 max mem: 8299 +Train: [84] [ 800/6250] eta: 0:11:01 lr: 0.000008 grad: 0.1186 (0.1195) loss: 0.8600 (0.8683) time: 0.1198 data: 0.0474 max mem: 8299 +Train: [84] [ 900/6250] eta: 0:10:41 lr: 0.000008 grad: 0.1118 (0.1190) loss: 0.8643 (0.8677) time: 0.0997 data: 0.0091 max mem: 8299 +Train: [84] [1000/6250] eta: 0:10:30 lr: 0.000008 grad: 0.1091 (0.1188) loss: 0.8648 (0.8674) time: 0.1218 data: 0.0493 max mem: 8299 +Train: [84] [1100/6250] eta: 0:10:17 lr: 0.000008 grad: 0.1178 (0.1188) loss: 0.8555 (0.8669) time: 0.1201 data: 0.0502 max mem: 8299 +Train: [84] [1200/6250] eta: 0:10:04 lr: 0.000008 grad: 0.1144 (0.1189) loss: 0.8597 (0.8664) time: 0.1153 data: 0.0409 max mem: 8299 +Train: [84] [1300/6250] eta: 0:09:53 lr: 0.000008 grad: 0.1127 (0.1192) loss: 0.8624 (0.8658) time: 0.1346 data: 0.0677 max mem: 8299 +Train: [84] [1400/6250] eta: 0:09:39 lr: 0.000008 grad: 0.1178 (0.1191) loss: 0.8592 (0.8655) time: 0.1096 data: 0.0339 max mem: 8299 +Train: [84] [1500/6250] eta: 0:09:29 lr: 0.000008 grad: 0.1172 (0.1193) loss: 0.8613 (0.8652) time: 0.1511 data: 0.0810 max mem: 8299 +Train: [84] [1600/6250] eta: 0:09:16 lr: 0.000008 grad: 0.1246 (0.1197) loss: 0.8593 (0.8647) time: 0.1213 data: 0.0479 max mem: 8299 +Train: [84] [1700/6250] eta: 0:09:04 lr: 0.000008 grad: 0.1209 (0.1200) loss: 0.8614 (0.8642) time: 0.1227 data: 0.0437 max mem: 8299 +Train: [84] [1800/6250] eta: 0:09:00 lr: 0.000008 grad: 0.1171 (0.1203) loss: 0.8624 (0.8639) time: 0.1336 data: 0.0501 max mem: 8299 +Train: [84] [1900/6250] eta: 0:08:50 lr: 0.000008 grad: 0.1198 (0.1202) loss: 0.8529 (0.8637) time: 0.1160 data: 0.0409 max mem: 8299 +Train: [84] [2000/6250] eta: 0:08:37 lr: 0.000008 grad: 0.1207 (0.1204) loss: 0.8526 (0.8635) time: 0.1061 data: 0.0248 max mem: 8299 +Train: [84] [2100/6250] eta: 0:08:24 lr: 0.000008 grad: 0.1166 (0.1206) loss: 0.8534 (0.8633) time: 0.1160 data: 0.0345 max mem: 8299 +Train: [84] [2200/6250] eta: 0:08:12 lr: 0.000008 grad: 0.1164 (0.1208) loss: 0.8530 (0.8630) time: 0.1116 data: 0.0388 max mem: 8299 +Train: [84] [2300/6250] eta: 0:07:58 lr: 0.000008 grad: 0.1216 (0.1210) loss: 0.8587 (0.8628) time: 0.1100 data: 0.0382 max mem: 8299 +Train: [84] [2400/6250] eta: 0:07:46 lr: 0.000008 grad: 0.1275 (0.1212) loss: 0.8610 (0.8625) time: 0.1169 data: 0.0444 max mem: 8299 +Train: [84] [2500/6250] eta: 0:07:33 lr: 0.000008 grad: 0.1205 (0.1214) loss: 0.8554 (0.8623) time: 0.1077 data: 0.0405 max mem: 8299 +Train: [84] [2600/6250] eta: 0:07:20 lr: 0.000008 grad: 0.1153 (0.1215) loss: 0.8540 (0.8620) time: 0.1202 data: 0.0541 max mem: 8299 +Train: [84] [2700/6250] eta: 0:07:08 lr: 0.000008 grad: 0.1287 (0.1217) loss: 0.8531 (0.8618) time: 0.1359 data: 0.0632 max mem: 8299 +Train: [84] [2800/6250] eta: 0:06:55 lr: 0.000008 grad: 0.1209 (0.1218) loss: 0.8562 (0.8616) time: 0.1166 data: 0.0477 max mem: 8299 +Train: [84] [2900/6250] eta: 0:06:42 lr: 0.000008 grad: 0.1202 (0.1219) loss: 0.8583 (0.8614) time: 0.1107 data: 0.0427 max mem: 8299 +Train: [84] [3000/6250] eta: 0:06:30 lr: 0.000008 grad: 0.1154 (0.1220) loss: 0.8574 (0.8613) time: 0.1283 data: 0.0557 max mem: 8299 +Train: [84] [3100/6250] eta: 0:06:18 lr: 0.000008 grad: 0.1297 (0.1220) loss: 0.8563 (0.8612) time: 0.1109 data: 0.0458 max mem: 8299 +Train: [84] [3200/6250] eta: 0:06:06 lr: 0.000008 grad: 0.1203 (0.1220) loss: 0.8543 (0.8611) time: 0.1065 data: 0.0356 max mem: 8299 +Train: [84] [3300/6250] eta: 0:05:54 lr: 0.000008 grad: 0.1230 (0.1221) loss: 0.8580 (0.8610) time: 0.1180 data: 0.0495 max mem: 8299 +Train: [84] [3400/6250] eta: 0:05:42 lr: 0.000008 grad: 0.1263 (0.1222) loss: 0.8529 (0.8609) time: 0.0975 data: 0.0221 max mem: 8299 +Train: [84] [3500/6250] eta: 0:05:30 lr: 0.000008 grad: 0.1215 (0.1222) loss: 0.8567 (0.8608) time: 0.1305 data: 0.0620 max mem: 8299 +Train: [84] [3600/6250] eta: 0:05:18 lr: 0.000008 grad: 0.1206 (0.1224) loss: 0.8579 (0.8607) time: 0.1309 data: 0.0574 max mem: 8299 +Train: [84] [3700/6250] eta: 0:05:05 lr: 0.000008 grad: 0.1250 (0.1225) loss: 0.8588 (0.8606) time: 0.1099 data: 0.0328 max mem: 8299 +Train: [84] [3800/6250] eta: 0:04:53 lr: 0.000008 grad: 0.1148 (0.1226) loss: 0.8569 (0.8606) time: 0.1138 data: 0.0299 max mem: 8299 +Train: [84] [3900/6250] eta: 0:04:41 lr: 0.000008 grad: 0.1135 (0.1227) loss: 0.8635 (0.8606) time: 0.1174 data: 0.0450 max mem: 8299 +Train: [84] [4000/6250] eta: 0:04:29 lr: 0.000008 grad: 0.1276 (0.1228) loss: 0.8538 (0.8606) time: 0.1329 data: 0.0642 max mem: 8299 +Train: [84] [4100/6250] eta: 0:04:17 lr: 0.000008 grad: 0.1325 (0.1229) loss: 0.8574 (0.8605) time: 0.1269 data: 0.0539 max mem: 8299 +Train: [84] [4200/6250] eta: 0:04:05 lr: 0.000008 grad: 0.1321 (0.1231) loss: 0.8550 (0.8604) time: 0.1188 data: 0.0466 max mem: 8299 +Train: [84] [4300/6250] eta: 0:03:53 lr: 0.000008 grad: 0.1272 (0.1233) loss: 0.8576 (0.8604) time: 0.1327 data: 0.0666 max mem: 8299 +Train: [84] [4400/6250] eta: 0:03:41 lr: 0.000008 grad: 0.1260 (0.1233) loss: 0.8564 (0.8603) time: 0.1090 data: 0.0387 max mem: 8299 +Train: [84] [4500/6250] eta: 0:03:30 lr: 0.000008 grad: 0.1377 (0.1234) loss: 0.8565 (0.8602) time: 0.1238 data: 0.0543 max mem: 8299 +Train: [84] [4600/6250] eta: 0:03:18 lr: 0.000008 grad: 0.1187 (0.1235) loss: 0.8579 (0.8602) time: 0.1279 data: 0.0491 max mem: 8299 +Train: [84] [4700/6250] eta: 0:03:06 lr: 0.000008 grad: 0.1209 (0.1236) loss: 0.8581 (0.8601) time: 0.1264 data: 0.0588 max mem: 8299 +Train: [84] [4800/6250] eta: 0:02:55 lr: 0.000008 grad: 0.1206 (0.1236) loss: 0.8640 (0.8601) time: 0.1255 data: 0.0542 max mem: 8299 +Train: [84] [4900/6250] eta: 0:02:43 lr: 0.000008 grad: 0.1330 (0.1237) loss: 0.8511 (0.8600) time: 0.1271 data: 0.0565 max mem: 8299 +Train: [84] [5000/6250] eta: 0:02:30 lr: 0.000008 grad: 0.1222 (0.1238) loss: 0.8579 (0.8599) time: 0.1166 data: 0.0441 max mem: 8299 +Train: [84] [5100/6250] eta: 0:02:18 lr: 0.000008 grad: 0.1298 (0.1238) loss: 0.8538 (0.8598) time: 0.1077 data: 0.0317 max mem: 8299 +Train: [84] [5200/6250] eta: 0:02:06 lr: 0.000008 grad: 0.1176 (0.1238) loss: 0.8557 (0.8598) time: 0.1010 data: 0.0262 max mem: 8299 +Train: [84] [5300/6250] eta: 0:01:54 lr: 0.000008 grad: 0.1248 (0.1239) loss: 0.8520 (0.8597) time: 0.1029 data: 0.0298 max mem: 8299 +Train: [84] [5400/6250] eta: 0:01:41 lr: 0.000008 grad: 0.1254 (0.1240) loss: 0.8577 (0.8596) time: 0.1106 data: 0.0375 max mem: 8299 +Train: [84] [5500/6250] eta: 0:01:29 lr: 0.000008 grad: 0.1250 (0.1240) loss: 0.8591 (0.8596) time: 0.0967 data: 0.0281 max mem: 8299 +Train: [84] [5600/6250] eta: 0:01:17 lr: 0.000008 grad: 0.1160 (0.1240) loss: 0.8617 (0.8596) time: 0.1305 data: 0.0617 max mem: 8299 +Train: [84] [5700/6250] eta: 0:01:05 lr: 0.000008 grad: 0.1140 (0.1240) loss: 0.8699 (0.8596) time: 0.0984 data: 0.0231 max mem: 8299 +Train: [84] [5800/6250] eta: 0:00:53 lr: 0.000008 grad: 0.1240 (0.1241) loss: 0.8510 (0.8596) time: 0.0926 data: 0.0153 max mem: 8299 +Train: [84] [5900/6250] eta: 0:00:41 lr: 0.000008 grad: 0.1208 (0.1241) loss: 0.8604 (0.8595) time: 0.1093 data: 0.0277 max mem: 8299 +Train: [84] [6000/6250] eta: 0:00:29 lr: 0.000008 grad: 0.1224 (0.1242) loss: 0.8566 (0.8595) time: 0.1046 data: 0.0328 max mem: 8299 +Train: [84] [6100/6250] eta: 0:00:17 lr: 0.000008 grad: 0.1155 (0.1242) loss: 0.8648 (0.8596) time: 0.0964 data: 0.0257 max mem: 8299 +Train: [84] [6200/6250] eta: 0:00:05 lr: 0.000008 grad: 0.1204 (0.1241) loss: 0.8614 (0.8596) time: 0.0984 data: 0.0292 max mem: 8299 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1130 (0.1241) loss: 0.8577 (0.8596) time: 0.1055 data: 0.0294 max mem: 8299 +Train: [84] Total time: 0:12:20 (0.1184 s / it) +Averaged stats: lr: 0.000008 grad: 0.1130 (0.1241) loss: 0.8577 (0.8596) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:04:13 loss: 0.8722 (0.8722) time: 4.0942 data: 4.0345 max mem: 8299 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8680 (0.8698) time: 0.1150 data: 0.0908 max mem: 8299 +Eval (hcp-train-subset): [84] Total time: 0:00:12 (0.2014 s / it) +Averaged stats (hcp-train-subset): loss: 0.8680 (0.8698) +Making plots (hcp-train-subset): example=9 +Eval (hcp-val): [84] [ 0/62] eta: 0:05:23 loss: 0.8749 (0.8749) time: 5.2115 data: 5.1809 max mem: 8299 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8743 (0.8774) time: 0.1256 data: 0.1014 max mem: 8299 +Eval (hcp-val): [84] Total time: 0:00:12 (0.1992 s / it) +Averaged stats (hcp-val): loss: 0.8743 (0.8774) +Making plots (hcp-val): example=39 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 11:23:54 lr: 0.000008 grad: 0.6258 (0.6258) loss: 0.8402 (0.8402) time: 6.5655 data: 6.4148 max mem: 8299 +Train: [85] [ 100/6250] eta: 0:18:27 lr: 0.000008 grad: 0.0997 (0.1570) loss: 0.8691 (0.8654) time: 0.1019 data: 0.0236 max mem: 8299 +Train: [85] [ 200/6250] eta: 0:15:25 lr: 0.000008 grad: 0.1145 (0.1414) loss: 0.8697 (0.8677) time: 0.1310 data: 0.0546 max mem: 8299 +Train: [85] [ 300/6250] eta: 0:14:04 lr: 0.000007 grad: 0.1234 (0.1361) loss: 0.8614 (0.8663) time: 0.1236 data: 0.0477 max mem: 8299 +Train: [85] [ 400/6250] eta: 0:13:16 lr: 0.000007 grad: 0.1091 (0.1317) loss: 0.8605 (0.8655) time: 0.1006 data: 0.0107 max mem: 8299 +Train: [85] [ 500/6250] eta: 0:12:35 lr: 0.000007 grad: 0.1138 (0.1286) loss: 0.8604 (0.8654) time: 0.1225 data: 0.0441 max mem: 8299 +Train: [85] [ 600/6250] eta: 0:12:03 lr: 0.000007 grad: 0.1149 (0.1268) loss: 0.8641 (0.8650) time: 0.1132 data: 0.0371 max mem: 8299 +Train: [85] [ 700/6250] eta: 0:11:31 lr: 0.000007 grad: 0.1060 (0.1255) loss: 0.8649 (0.8652) time: 0.1017 data: 0.0227 max mem: 8299 +Train: [85] [ 800/6250] eta: 0:11:08 lr: 0.000007 grad: 0.1095 (0.1240) loss: 0.8631 (0.8654) time: 0.1134 data: 0.0260 max mem: 8299 +Train: [85] [ 900/6250] eta: 0:10:56 lr: 0.000007 grad: 0.1110 (0.1231) loss: 0.8588 (0.8653) time: 0.1221 data: 0.0483 max mem: 8299 +Train: [85] [1000/6250] eta: 0:10:47 lr: 0.000007 grad: 0.1162 (0.1225) loss: 0.8657 (0.8653) time: 0.1277 data: 0.0519 max mem: 8299 +Train: [85] [1100/6250] eta: 0:10:37 lr: 0.000007 grad: 0.1140 (0.1218) loss: 0.8649 (0.8654) time: 0.1433 data: 0.0740 max mem: 8299 +Train: [85] [1200/6250] eta: 0:10:24 lr: 0.000007 grad: 0.1145 (0.1212) loss: 0.8652 (0.8655) time: 0.1251 data: 0.0522 max mem: 8299 +Train: [85] [1300/6250] eta: 0:10:15 lr: 0.000007 grad: 0.1153 (0.1212) loss: 0.8680 (0.8656) time: 0.1460 data: 0.0730 max mem: 8299 +Train: [85] [1400/6250] eta: 0:10:06 lr: 0.000007 grad: 0.1195 (0.1212) loss: 0.8699 (0.8656) time: 0.1421 data: 0.0691 max mem: 8299 +Train: [85] [1500/6250] eta: 0:09:57 lr: 0.000007 grad: 0.1102 (0.1210) loss: 0.8696 (0.8656) time: 0.1511 data: 0.0839 max mem: 8299 +Train: [85] [1600/6250] eta: 0:09:47 lr: 0.000007 grad: 0.1102 (0.1208) loss: 0.8709 (0.8654) time: 0.1576 data: 0.0900 max mem: 8299 +Train: [85] [1700/6250] eta: 0:09:36 lr: 0.000007 grad: 0.1140 (0.1206) loss: 0.8700 (0.8653) time: 0.1364 data: 0.0744 max mem: 8299 +Train: [85] [1800/6250] eta: 0:09:25 lr: 0.000007 grad: 0.1086 (0.1206) loss: 0.8684 (0.8651) time: 0.1467 data: 0.0796 max mem: 8299 +Train: [85] [1900/6250] eta: 0:09:13 lr: 0.000007 grad: 0.1258 (0.1206) loss: 0.8611 (0.8650) time: 0.1341 data: 0.0601 max mem: 8299 +Train: [85] [2000/6250] eta: 0:09:01 lr: 0.000007 grad: 0.1235 (0.1207) loss: 0.8549 (0.8649) time: 0.1339 data: 0.0633 max mem: 8299 +Train: [85] [2100/6250] eta: 0:08:48 lr: 0.000007 grad: 0.1159 (0.1208) loss: 0.8642 (0.8647) time: 0.1260 data: 0.0584 max mem: 8299 +Train: [85] [2200/6250] eta: 0:08:36 lr: 0.000007 grad: 0.1184 (0.1209) loss: 0.8612 (0.8646) time: 0.1360 data: 0.0741 max mem: 8299 +Train: [85] [2300/6250] eta: 0:08:24 lr: 0.000007 grad: 0.1185 (0.1210) loss: 0.8598 (0.8644) time: 0.1345 data: 0.0655 max mem: 8299 +Train: [85] [2400/6250] eta: 0:08:11 lr: 0.000007 grad: 0.1128 (0.1211) loss: 0.8669 (0.8644) time: 0.1242 data: 0.0561 max mem: 8299 +Train: [85] [2500/6250] eta: 0:08:00 lr: 0.000007 grad: 0.1103 (0.1210) loss: 0.8668 (0.8645) time: 0.1243 data: 0.0501 max mem: 8299 +Train: [85] [2600/6250] eta: 0:07:48 lr: 0.000007 grad: 0.1220 (0.1211) loss: 0.8588 (0.8644) time: 0.1544 data: 0.0877 max mem: 8299 +Train: [85] [2700/6250] eta: 0:07:36 lr: 0.000007 grad: 0.1272 (0.1212) loss: 0.8567 (0.8644) time: 0.1257 data: 0.0511 max mem: 8299 +Train: [85] [2800/6250] eta: 0:07:23 lr: 0.000007 grad: 0.1224 (0.1213) loss: 0.8579 (0.8643) time: 0.0988 data: 0.0229 max mem: 8299 +Train: [85] [2900/6250] eta: 0:07:11 lr: 0.000007 grad: 0.1184 (0.1212) loss: 0.8595 (0.8644) time: 0.1224 data: 0.0515 max mem: 8299 +Train: [85] [3000/6250] eta: 0:06:59 lr: 0.000007 grad: 0.1087 (0.1212) loss: 0.8703 (0.8644) time: 0.0997 data: 0.0279 max mem: 8299 +Train: [85] [3100/6250] eta: 0:06:47 lr: 0.000007 grad: 0.1123 (0.1213) loss: 0.8701 (0.8644) time: 0.1248 data: 0.0624 max mem: 8299 +Train: [85] [3200/6250] eta: 0:06:34 lr: 0.000007 grad: 0.1118 (0.1214) loss: 0.8650 (0.8644) time: 0.1414 data: 0.0733 max mem: 8299 +Train: [85] [3300/6250] eta: 0:06:22 lr: 0.000007 grad: 0.1212 (0.1214) loss: 0.8632 (0.8644) time: 0.1323 data: 0.0643 max mem: 8299 +Train: [85] [3400/6250] eta: 0:06:09 lr: 0.000007 grad: 0.1231 (0.1215) loss: 0.8534 (0.8643) time: 0.1293 data: 0.0650 max mem: 8299 +Train: [85] [3500/6250] eta: 0:05:56 lr: 0.000007 grad: 0.1224 (0.1215) loss: 0.8616 (0.8642) time: 0.1354 data: 0.0603 max mem: 8299 +Train: [85] [3600/6250] eta: 0:05:43 lr: 0.000007 grad: 0.1176 (0.1215) loss: 0.8586 (0.8641) time: 0.1326 data: 0.0640 max mem: 8299 +Train: [85] [3700/6250] eta: 0:05:30 lr: 0.000007 grad: 0.1140 (0.1216) loss: 0.8646 (0.8641) time: 0.1176 data: 0.0484 max mem: 8299 +Train: [85] [3800/6250] eta: 0:05:16 lr: 0.000007 grad: 0.1174 (0.1215) loss: 0.8667 (0.8640) time: 0.1259 data: 0.0585 max mem: 8299 +Train: [85] [3900/6250] eta: 0:05:03 lr: 0.000007 grad: 0.1211 (0.1216) loss: 0.8668 (0.8640) time: 0.1178 data: 0.0473 max mem: 8299 +Train: [85] [4000/6250] eta: 0:04:50 lr: 0.000007 grad: 0.1258 (0.1216) loss: 0.8603 (0.8639) time: 0.1157 data: 0.0375 max mem: 8299 +Train: [85] [4100/6250] eta: 0:04:37 lr: 0.000007 grad: 0.1193 (0.1217) loss: 0.8610 (0.8638) time: 0.1373 data: 0.0733 max mem: 8299 +Train: [85] [4200/6250] eta: 0:04:24 lr: 0.000007 grad: 0.1196 (0.1218) loss: 0.8623 (0.8638) time: 0.1316 data: 0.0622 max mem: 8299 +Train: [85] [4300/6250] eta: 0:04:11 lr: 0.000007 grad: 0.1152 (0.1219) loss: 0.8568 (0.8636) time: 0.1274 data: 0.0518 max mem: 8299 +Train: [85] [4400/6250] eta: 0:03:58 lr: 0.000007 grad: 0.1201 (0.1220) loss: 0.8529 (0.8635) time: 0.1211 data: 0.0479 max mem: 8299 +Train: [85] [4500/6250] eta: 0:03:45 lr: 0.000007 grad: 0.1182 (0.1221) loss: 0.8593 (0.8634) time: 0.1304 data: 0.0593 max mem: 8299 +Train: [85] [4600/6250] eta: 0:03:32 lr: 0.000007 grad: 0.1132 (0.1222) loss: 0.8637 (0.8633) time: 0.1314 data: 0.0558 max mem: 8299 +Train: [85] [4700/6250] eta: 0:03:19 lr: 0.000007 grad: 0.1227 (0.1222) loss: 0.8619 (0.8631) time: 0.1241 data: 0.0471 max mem: 8299 +Train: [85] [4800/6250] eta: 0:03:06 lr: 0.000007 grad: 0.1158 (0.1222) loss: 0.8654 (0.8631) time: 0.1253 data: 0.0531 max mem: 8299 +Train: [85] [4900/6250] eta: 0:02:54 lr: 0.000007 grad: 0.1220 (0.1223) loss: 0.8617 (0.8630) time: 0.1477 data: 0.0761 max mem: 8299 +Train: [85] [5000/6250] eta: 0:02:40 lr: 0.000007 grad: 0.1238 (0.1223) loss: 0.8603 (0.8629) time: 0.1105 data: 0.0348 max mem: 8299 +Train: [85] [5100/6250] eta: 0:02:27 lr: 0.000007 grad: 0.1239 (0.1222) loss: 0.8655 (0.8629) time: 0.1036 data: 0.0225 max mem: 8299 +Train: [85] [5200/6250] eta: 0:02:14 lr: 0.000007 grad: 0.1267 (0.1222) loss: 0.8594 (0.8629) time: 0.1191 data: 0.0393 max mem: 8299 +Train: [85] [5300/6250] eta: 0:02:01 lr: 0.000007 grad: 0.1159 (0.1222) loss: 0.8639 (0.8629) time: 0.1147 data: 0.0403 max mem: 8299 +Train: [85] [5400/6250] eta: 0:01:48 lr: 0.000007 grad: 0.1158 (0.1222) loss: 0.8627 (0.8629) time: 0.1154 data: 0.0419 max mem: 8299 +Train: [85] [5500/6250] eta: 0:01:35 lr: 0.000007 grad: 0.1083 (0.1221) loss: 0.8625 (0.8629) time: 0.1017 data: 0.0246 max mem: 8299 +Train: [85] [5600/6250] eta: 0:01:22 lr: 0.000007 grad: 0.1118 (0.1221) loss: 0.8583 (0.8628) time: 0.1200 data: 0.0420 max mem: 8299 +Train: [85] [5700/6250] eta: 0:01:09 lr: 0.000007 grad: 0.1123 (0.1220) loss: 0.8652 (0.8628) time: 0.1070 data: 0.0335 max mem: 8299 +Train: [85] [5800/6250] eta: 0:00:57 lr: 0.000007 grad: 0.1175 (0.1220) loss: 0.8602 (0.8628) time: 0.1128 data: 0.0370 max mem: 8299 +Train: [85] [5900/6250] eta: 0:00:44 lr: 0.000007 grad: 0.1097 (0.1220) loss: 0.8682 (0.8628) time: 0.1221 data: 0.0551 max mem: 8299 +Train: [85] [6000/6250] eta: 0:00:31 lr: 0.000007 grad: 0.1156 (0.1220) loss: 0.8605 (0.8628) time: 0.1195 data: 0.0518 max mem: 8299 +Train: [85] [6100/6250] eta: 0:00:18 lr: 0.000007 grad: 0.1118 (0.1218) loss: 0.8609 (0.8628) time: 0.1209 data: 0.0449 max mem: 8299 +Train: [85] [6200/6250] eta: 0:00:06 lr: 0.000007 grad: 0.1258 (0.1218) loss: 0.8603 (0.8628) time: 0.1229 data: 0.0340 max mem: 8299 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1240 (0.1217) loss: 0.8617 (0.8627) time: 0.1324 data: 0.0582 max mem: 8299 +Train: [85] Total time: 0:13:16 (0.1275 s / it) +Averaged stats: lr: 0.000007 grad: 0.1240 (0.1217) loss: 0.8617 (0.8627) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:04:46 loss: 0.8740 (0.8740) time: 4.6172 data: 4.5682 max mem: 8299 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8647 (0.8690) time: 0.1291 data: 0.1046 max mem: 8299 +Eval (hcp-train-subset): [85] Total time: 0:00:13 (0.2118 s / it) +Averaged stats (hcp-train-subset): loss: 0.8647 (0.8690) +Eval (hcp-val): [85] [ 0/62] eta: 0:05:21 loss: 0.8773 (0.8773) time: 5.1846 data: 5.1539 max mem: 8299 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8750 (0.8766) time: 0.1133 data: 0.0878 max mem: 8299 +Eval (hcp-val): [85] Total time: 0:00:12 (0.2004 s / it) +Averaged stats (hcp-val): loss: 0.8750 (0.8766) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 10:22:53 lr: 0.000007 grad: 0.1672 (0.1672) loss: 0.8730 (0.8730) time: 5.9797 data: 5.8748 max mem: 8299 +Train: [86] [ 100/6250] eta: 0:19:12 lr: 0.000007 grad: 0.1287 (0.1457) loss: 0.8720 (0.8757) time: 0.1399 data: 0.0446 max mem: 8299 +Train: [86] [ 200/6250] eta: 0:16:32 lr: 0.000007 grad: 0.1244 (0.1400) loss: 0.8618 (0.8711) time: 0.1268 data: 0.0340 max mem: 8299 +Train: [86] [ 300/6250] eta: 0:15:33 lr: 0.000007 grad: 0.1158 (0.1351) loss: 0.8661 (0.8693) time: 0.1312 data: 0.0406 max mem: 8299 +Train: [86] [ 400/6250] eta: 0:14:49 lr: 0.000007 grad: 0.0994 (0.1309) loss: 0.8734 (0.8690) time: 0.1235 data: 0.0185 max mem: 8299 +Train: [86] [ 500/6250] eta: 0:14:17 lr: 0.000007 grad: 0.1159 (0.1289) loss: 0.8623 (0.8682) time: 0.1349 data: 0.0483 max mem: 8299 +Train: [86] [ 600/6250] eta: 0:13:40 lr: 0.000006 grad: 0.1072 (0.1272) loss: 0.8647 (0.8673) time: 0.1194 data: 0.0351 max mem: 8299 +Train: [86] [ 700/6250] eta: 0:13:13 lr: 0.000006 grad: 0.1085 (0.1259) loss: 0.8618 (0.8666) time: 0.1396 data: 0.0404 max mem: 8299 +Train: [86] [ 800/6250] eta: 0:12:51 lr: 0.000006 grad: 0.1099 (0.1245) loss: 0.8601 (0.8662) time: 0.1321 data: 0.0450 max mem: 8299 +Train: [86] [ 900/6250] eta: 0:12:35 lr: 0.000006 grad: 0.1141 (0.1243) loss: 0.8597 (0.8658) time: 0.1468 data: 0.0726 max mem: 8299 +Train: [86] [1000/6250] eta: 0:12:15 lr: 0.000006 grad: 0.1204 (0.1241) loss: 0.8613 (0.8651) time: 0.1346 data: 0.0459 max mem: 8299 +Train: [86] [1100/6250] eta: 0:11:59 lr: 0.000006 grad: 0.1250 (0.1242) loss: 0.8637 (0.8644) time: 0.1484 data: 0.0765 max mem: 8299 +Train: [86] [1200/6250] eta: 0:11:45 lr: 0.000006 grad: 0.1176 (0.1243) loss: 0.8559 (0.8640) time: 0.1471 data: 0.0703 max mem: 8299 +Train: [86] [1300/6250] eta: 0:11:29 lr: 0.000006 grad: 0.1203 (0.1245) loss: 0.8627 (0.8635) time: 0.1425 data: 0.0652 max mem: 8299 +Train: [86] [1400/6250] eta: 0:11:12 lr: 0.000006 grad: 0.1066 (0.1244) loss: 0.8635 (0.8631) time: 0.1506 data: 0.0729 max mem: 8299 +Train: [86] [1500/6250] eta: 0:10:56 lr: 0.000006 grad: 0.1165 (0.1244) loss: 0.8577 (0.8627) time: 0.1451 data: 0.0760 max mem: 8299 +Train: [86] [1600/6250] eta: 0:10:41 lr: 0.000006 grad: 0.1204 (0.1247) loss: 0.8663 (0.8625) time: 0.1425 data: 0.0667 max mem: 8299 +Train: [86] [1700/6250] eta: 0:10:26 lr: 0.000006 grad: 0.1166 (0.1246) loss: 0.8655 (0.8623) time: 0.1349 data: 0.0461 max mem: 8299 +Train: [86] [1800/6250] eta: 0:10:10 lr: 0.000006 grad: 0.1241 (0.1246) loss: 0.8576 (0.8620) time: 0.1359 data: 0.0518 max mem: 8299 +Train: [86] [1900/6250] eta: 0:09:56 lr: 0.000006 grad: 0.1183 (0.1246) loss: 0.8582 (0.8617) time: 0.1496 data: 0.0750 max mem: 8299 +Train: [86] [2000/6250] eta: 0:09:43 lr: 0.000006 grad: 0.1158 (0.1245) loss: 0.8621 (0.8614) time: 0.1393 data: 0.0630 max mem: 8299 +Train: [86] [2100/6250] eta: 0:09:28 lr: 0.000006 grad: 0.1220 (0.1244) loss: 0.8584 (0.8612) time: 0.1378 data: 0.0495 max mem: 8299 +Train: [86] [2200/6250] eta: 0:09:13 lr: 0.000006 grad: 0.1229 (0.1242) loss: 0.8632 (0.8612) time: 0.1605 data: 0.0768 max mem: 8299 +Train: [86] [2300/6250] eta: 0:08:58 lr: 0.000006 grad: 0.1218 (0.1241) loss: 0.8582 (0.8610) time: 0.1226 data: 0.0411 max mem: 8299 +Train: [86] [2400/6250] eta: 0:08:44 lr: 0.000006 grad: 0.1199 (0.1239) loss: 0.8641 (0.8610) time: 0.1235 data: 0.0473 max mem: 8299 +Train: [86] [2500/6250] eta: 0:08:30 lr: 0.000006 grad: 0.1212 (0.1237) loss: 0.8605 (0.8609) time: 0.1461 data: 0.0770 max mem: 8299 +Train: [86] [2600/6250] eta: 0:08:16 lr: 0.000006 grad: 0.1152 (0.1236) loss: 0.8651 (0.8610) time: 0.1367 data: 0.0580 max mem: 8299 +Train: [86] [2700/6250] eta: 0:08:03 lr: 0.000006 grad: 0.1126 (0.1236) loss: 0.8586 (0.8609) time: 0.1361 data: 0.0614 max mem: 8299 +Train: [86] [2800/6250] eta: 0:07:49 lr: 0.000006 grad: 0.1201 (0.1236) loss: 0.8594 (0.8609) time: 0.1193 data: 0.0371 max mem: 8299 +Train: [86] [2900/6250] eta: 0:07:35 lr: 0.000006 grad: 0.1109 (0.1235) loss: 0.8649 (0.8610) time: 0.1065 data: 0.0234 max mem: 8299 +Train: [86] [3000/6250] eta: 0:07:21 lr: 0.000006 grad: 0.1186 (0.1233) loss: 0.8578 (0.8610) time: 0.1405 data: 0.0615 max mem: 8299 +Train: [86] [3100/6250] eta: 0:07:06 lr: 0.000006 grad: 0.1083 (0.1232) loss: 0.8598 (0.8611) time: 0.1216 data: 0.0427 max mem: 8299 +Train: [86] [3200/6250] eta: 0:06:53 lr: 0.000006 grad: 0.1088 (0.1230) loss: 0.8616 (0.8611) time: 0.1239 data: 0.0411 max mem: 8299 +Train: [86] [3300/6250] eta: 0:06:40 lr: 0.000006 grad: 0.1205 (0.1228) loss: 0.8638 (0.8611) time: 0.1356 data: 0.0530 max mem: 8299 +Train: [86] [3400/6250] eta: 0:06:26 lr: 0.000006 grad: 0.1279 (0.1228) loss: 0.8569 (0.8611) time: 0.1290 data: 0.0376 max mem: 8299 +Train: [86] [3500/6250] eta: 0:06:12 lr: 0.000006 grad: 0.1276 (0.1229) loss: 0.8604 (0.8612) time: 0.1251 data: 0.0528 max mem: 8299 +Train: [86] [3600/6250] eta: 0:05:59 lr: 0.000006 grad: 0.1242 (0.1231) loss: 0.8636 (0.8611) time: 0.1208 data: 0.0501 max mem: 8299 +Train: [86] [3700/6250] eta: 0:05:46 lr: 0.000006 grad: 0.1225 (0.1232) loss: 0.8613 (0.8612) time: 0.1744 data: 0.0939 max mem: 8299 +Train: [86] [3800/6250] eta: 0:05:32 lr: 0.000006 grad: 0.1214 (0.1233) loss: 0.8640 (0.8612) time: 0.1410 data: 0.0643 max mem: 8299 +Train: [86] [3900/6250] eta: 0:05:18 lr: 0.000006 grad: 0.1325 (0.1235) loss: 0.8635 (0.8611) time: 0.1367 data: 0.0600 max mem: 8299 +Train: [86] [4000/6250] eta: 0:05:05 lr: 0.000006 grad: 0.1101 (0.1237) loss: 0.8585 (0.8610) time: 0.1533 data: 0.0828 max mem: 8299 +Train: [86] [4100/6250] eta: 0:04:51 lr: 0.000006 grad: 0.1254 (0.1239) loss: 0.8608 (0.8610) time: 0.1307 data: 0.0461 max mem: 8299 +Train: [86] [4200/6250] eta: 0:04:37 lr: 0.000006 grad: 0.1222 (0.1239) loss: 0.8643 (0.8610) time: 0.1605 data: 0.0864 max mem: 8299 +Train: [86] [4300/6250] eta: 0:04:24 lr: 0.000006 grad: 0.1171 (0.1240) loss: 0.8637 (0.8610) time: 0.1305 data: 0.0527 max mem: 8299 +Train: [86] [4400/6250] eta: 0:04:11 lr: 0.000006 grad: 0.1281 (0.1240) loss: 0.8581 (0.8610) time: 0.1638 data: 0.0899 max mem: 8299 +Train: [86] [4500/6250] eta: 0:03:58 lr: 0.000006 grad: 0.1197 (0.1239) loss: 0.8672 (0.8610) time: 0.1459 data: 0.0655 max mem: 8299 +Train: [86] [4600/6250] eta: 0:03:44 lr: 0.000006 grad: 0.1188 (0.1239) loss: 0.8643 (0.8611) time: 0.1530 data: 0.0705 max mem: 8299 +Train: [86] [4700/6250] eta: 0:03:31 lr: 0.000006 grad: 0.1224 (0.1239) loss: 0.8593 (0.8611) time: 0.1368 data: 0.0550 max mem: 8299 +Train: [86] [4800/6250] eta: 0:03:18 lr: 0.000006 grad: 0.1213 (0.1239) loss: 0.8632 (0.8611) time: 0.1356 data: 0.0654 max mem: 8299 +Train: [86] [4900/6250] eta: 0:03:04 lr: 0.000006 grad: 0.1277 (0.1239) loss: 0.8592 (0.8612) time: 0.1339 data: 0.0577 max mem: 8299 +Train: [86] [5000/6250] eta: 0:02:50 lr: 0.000006 grad: 0.1257 (0.1239) loss: 0.8621 (0.8612) time: 0.1452 data: 0.0600 max mem: 8299 +Train: [86] [5100/6250] eta: 0:02:36 lr: 0.000006 grad: 0.1146 (0.1238) loss: 0.8630 (0.8612) time: 0.1269 data: 0.0416 max mem: 8299 +Train: [86] [5200/6250] eta: 0:02:22 lr: 0.000006 grad: 0.1242 (0.1238) loss: 0.8647 (0.8612) time: 0.1186 data: 0.0335 max mem: 8299 +Train: [86] [5300/6250] eta: 0:02:09 lr: 0.000006 grad: 0.1178 (0.1238) loss: 0.8594 (0.8612) time: 0.1271 data: 0.0506 max mem: 8299 +Train: [86] [5400/6250] eta: 0:01:55 lr: 0.000006 grad: 0.1128 (0.1236) loss: 0.8635 (0.8613) time: 0.1483 data: 0.0616 max mem: 8299 +Train: [86] [5500/6250] eta: 0:01:41 lr: 0.000006 grad: 0.1148 (0.1235) loss: 0.8590 (0.8613) time: 0.1298 data: 0.0536 max mem: 8299 +Train: [86] [5600/6250] eta: 0:01:28 lr: 0.000006 grad: 0.1198 (0.1235) loss: 0.8637 (0.8613) time: 0.1462 data: 0.0734 max mem: 8299 +Train: [86] [5700/6250] eta: 0:01:14 lr: 0.000006 grad: 0.1264 (0.1235) loss: 0.8610 (0.8613) time: 0.1376 data: 0.0673 max mem: 8299 +Train: [86] [5800/6250] eta: 0:01:01 lr: 0.000006 grad: 0.1245 (0.1235) loss: 0.8644 (0.8613) time: 0.1369 data: 0.0573 max mem: 8299 +Train: [86] [5900/6250] eta: 0:00:47 lr: 0.000006 grad: 0.1253 (0.1236) loss: 0.8595 (0.8613) time: 0.1286 data: 0.0499 max mem: 8299 +Train: [86] [6000/6250] eta: 0:00:33 lr: 0.000006 grad: 0.1246 (0.1236) loss: 0.8633 (0.8613) time: 0.1261 data: 0.0404 max mem: 8299 +Train: [86] [6100/6250] eta: 0:00:20 lr: 0.000006 grad: 0.1231 (0.1237) loss: 0.8625 (0.8613) time: 0.1395 data: 0.0466 max mem: 8299 +Train: [86] [6200/6250] eta: 0:00:06 lr: 0.000006 grad: 0.1192 (0.1239) loss: 0.8622 (0.8613) time: 0.1391 data: 0.0611 max mem: 8299 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1278 (0.1240) loss: 0.8556 (0.8612) time: 0.1303 data: 0.0546 max mem: 8299 +Train: [86] Total time: 0:14:12 (0.1364 s / it) +Averaged stats: lr: 0.000006 grad: 0.1278 (0.1240) loss: 0.8556 (0.8612) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:04:27 loss: 0.8742 (0.8742) time: 4.3073 data: 4.2216 max mem: 8299 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8672 (0.8689) time: 0.1210 data: 0.0965 max mem: 8299 +Eval (hcp-train-subset): [86] Total time: 0:00:13 (0.2233 s / it) +Averaged stats (hcp-train-subset): loss: 0.8672 (0.8689) +Eval (hcp-val): [86] [ 0/62] eta: 0:04:26 loss: 0.8789 (0.8789) time: 4.3039 data: 4.2359 max mem: 8299 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8754 (0.8773) time: 0.1192 data: 0.0947 max mem: 8299 +Eval (hcp-val): [86] Total time: 0:00:13 (0.2105 s / it) +Averaged stats (hcp-val): loss: 0.8754 (0.8773) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 11:37:19 lr: 0.000006 grad: 0.3291 (0.3291) loss: 0.8441 (0.8441) time: 6.6943 data: 6.5459 max mem: 8299 +Train: [87] [ 100/6250] eta: 0:19:37 lr: 0.000006 grad: 0.1388 (0.1627) loss: 0.8747 (0.8660) time: 0.1262 data: 0.0309 max mem: 8299 +Train: [87] [ 200/6250] eta: 0:16:23 lr: 0.000006 grad: 0.1351 (0.1535) loss: 0.8669 (0.8647) time: 0.1201 data: 0.0174 max mem: 8299 +Train: [87] [ 300/6250] eta: 0:15:08 lr: 0.000006 grad: 0.1234 (0.1481) loss: 0.8695 (0.8640) time: 0.1410 data: 0.0433 max mem: 8299 +Train: [87] [ 400/6250] eta: 0:14:28 lr: 0.000006 grad: 0.1159 (0.1435) loss: 0.8667 (0.8639) time: 0.1274 data: 0.0554 max mem: 8299 +Train: [87] [ 500/6250] eta: 0:13:56 lr: 0.000006 grad: 0.1184 (0.1400) loss: 0.8650 (0.8643) time: 0.1568 data: 0.0731 max mem: 8299 +Train: [87] [ 600/6250] eta: 0:13:24 lr: 0.000006 grad: 0.1078 (0.1367) loss: 0.8640 (0.8644) time: 0.1223 data: 0.0288 max mem: 8299 +Train: [87] [ 700/6250] eta: 0:13:00 lr: 0.000006 grad: 0.1164 (0.1340) loss: 0.8654 (0.8647) time: 0.1235 data: 0.0380 max mem: 8299 +Train: [87] [ 800/6250] eta: 0:12:39 lr: 0.000006 grad: 0.1126 (0.1320) loss: 0.8646 (0.8648) time: 0.1394 data: 0.0478 max mem: 8299 +Train: [87] [ 900/6250] eta: 0:12:21 lr: 0.000006 grad: 0.1177 (0.1304) loss: 0.8648 (0.8648) time: 0.1280 data: 0.0496 max mem: 8299 +Train: [87] [1000/6250] eta: 0:12:07 lr: 0.000006 grad: 0.1195 (0.1291) loss: 0.8650 (0.8649) time: 0.1178 data: 0.0236 max mem: 8299 +Train: [87] [1100/6250] eta: 0:11:54 lr: 0.000006 grad: 0.1122 (0.1284) loss: 0.8665 (0.8649) time: 0.1359 data: 0.0648 max mem: 8299 +Train: [87] [1200/6250] eta: 0:11:40 lr: 0.000006 grad: 0.1159 (0.1275) loss: 0.8678 (0.8649) time: 0.1407 data: 0.0563 max mem: 8299 +Train: [87] [1300/6250] eta: 0:11:23 lr: 0.000006 grad: 0.1128 (0.1271) loss: 0.8691 (0.8651) time: 0.1208 data: 0.0401 max mem: 8299 +Train: [87] [1400/6250] eta: 0:11:08 lr: 0.000005 grad: 0.1082 (0.1265) loss: 0.8718 (0.8653) time: 0.1390 data: 0.0718 max mem: 8299 +Train: [87] [1500/6250] eta: 0:10:51 lr: 0.000005 grad: 0.1154 (0.1258) loss: 0.8661 (0.8653) time: 0.1237 data: 0.0415 max mem: 8299 +Train: [87] [1600/6250] eta: 0:10:37 lr: 0.000005 grad: 0.1040 (0.1252) loss: 0.8726 (0.8655) time: 0.1256 data: 0.0518 max mem: 8299 +Train: [87] [1700/6250] eta: 0:10:21 lr: 0.000005 grad: 0.1167 (0.1249) loss: 0.8652 (0.8656) time: 0.1206 data: 0.0378 max mem: 8299 +Train: [87] [1800/6250] eta: 0:10:06 lr: 0.000005 grad: 0.1193 (0.1247) loss: 0.8628 (0.8657) time: 0.1335 data: 0.0579 max mem: 8299 +Train: [87] [1900/6250] eta: 0:09:52 lr: 0.000005 grad: 0.1124 (0.1246) loss: 0.8577 (0.8656) time: 0.1314 data: 0.0498 max mem: 8299 +Train: [87] [2000/6250] eta: 0:09:39 lr: 0.000005 grad: 0.1222 (0.1244) loss: 0.8620 (0.8657) time: 0.1383 data: 0.0613 max mem: 8299 +Train: [87] [2100/6250] eta: 0:09:25 lr: 0.000005 grad: 0.1174 (0.1242) loss: 0.8647 (0.8656) time: 0.1229 data: 0.0409 max mem: 8299 +Train: [87] [2200/6250] eta: 0:09:11 lr: 0.000005 grad: 0.1101 (0.1241) loss: 0.8603 (0.8655) time: 0.1349 data: 0.0596 max mem: 8299 +Train: [87] [2300/6250] eta: 0:08:57 lr: 0.000005 grad: 0.1173 (0.1239) loss: 0.8645 (0.8655) time: 0.1264 data: 0.0430 max mem: 8299 +Train: [87] [2400/6250] eta: 0:08:44 lr: 0.000005 grad: 0.1135 (0.1237) loss: 0.8670 (0.8655) time: 0.1717 data: 0.0989 max mem: 8299 +Train: [87] [2500/6250] eta: 0:08:30 lr: 0.000005 grad: 0.1213 (0.1236) loss: 0.8662 (0.8655) time: 0.1367 data: 0.0488 max mem: 8299 +Train: [87] [2600/6250] eta: 0:08:17 lr: 0.000005 grad: 0.1197 (0.1235) loss: 0.8648 (0.8654) time: 0.1439 data: 0.0511 max mem: 8299 +Train: [87] [2700/6250] eta: 0:08:05 lr: 0.000005 grad: 0.1152 (0.1235) loss: 0.8624 (0.8653) time: 0.1582 data: 0.0713 max mem: 8299 +Train: [87] [2800/6250] eta: 0:07:50 lr: 0.000005 grad: 0.1200 (0.1234) loss: 0.8662 (0.8653) time: 0.1136 data: 0.0407 max mem: 8299 +Train: [87] [2900/6250] eta: 0:07:36 lr: 0.000005 grad: 0.1168 (0.1234) loss: 0.8630 (0.8652) time: 0.1316 data: 0.0545 max mem: 8299 +Train: [87] [3000/6250] eta: 0:07:22 lr: 0.000005 grad: 0.1256 (0.1234) loss: 0.8602 (0.8651) time: 0.1318 data: 0.0497 max mem: 8299 +Train: [87] [3100/6250] eta: 0:07:09 lr: 0.000005 grad: 0.1167 (0.1234) loss: 0.8625 (0.8650) time: 0.1386 data: 0.0605 max mem: 8299 +Train: [87] [3200/6250] eta: 0:06:55 lr: 0.000005 grad: 0.1105 (0.1233) loss: 0.8632 (0.8649) time: 0.1446 data: 0.0671 max mem: 8299 +Train: [87] [3300/6250] eta: 0:06:41 lr: 0.000005 grad: 0.1123 (0.1233) loss: 0.8685 (0.8649) time: 0.1217 data: 0.0450 max mem: 8299 +Train: [87] [3400/6250] eta: 0:06:28 lr: 0.000005 grad: 0.1182 (0.1233) loss: 0.8633 (0.8649) time: 0.1314 data: 0.0469 max mem: 8299 +Train: [87] [3500/6250] eta: 0:06:15 lr: 0.000005 grad: 0.1204 (0.1233) loss: 0.8649 (0.8648) time: 0.1875 data: 0.1081 max mem: 8299 +Train: [87] [3600/6250] eta: 0:06:01 lr: 0.000005 grad: 0.1265 (0.1234) loss: 0.8625 (0.8648) time: 0.1360 data: 0.0654 max mem: 8299 +Train: [87] [3700/6250] eta: 0:05:46 lr: 0.000005 grad: 0.1219 (0.1233) loss: 0.8567 (0.8647) time: 0.1099 data: 0.0315 max mem: 8299 +Train: [87] [3800/6250] eta: 0:05:33 lr: 0.000005 grad: 0.1174 (0.1233) loss: 0.8631 (0.8646) time: 0.1559 data: 0.0866 max mem: 8299 +Train: [87] [3900/6250] eta: 0:05:20 lr: 0.000005 grad: 0.1149 (0.1234) loss: 0.8630 (0.8646) time: 0.1248 data: 0.0534 max mem: 8299 +Train: [87] [4000/6250] eta: 0:05:06 lr: 0.000005 grad: 0.1278 (0.1234) loss: 0.8578 (0.8645) time: 0.1442 data: 0.0586 max mem: 8299 +Train: [87] [4100/6250] eta: 0:04:52 lr: 0.000005 grad: 0.1290 (0.1234) loss: 0.8621 (0.8644) time: 0.1261 data: 0.0449 max mem: 8299 +Train: [87] [4200/6250] eta: 0:04:39 lr: 0.000005 grad: 0.1235 (0.1235) loss: 0.8601 (0.8643) time: 0.1493 data: 0.0635 max mem: 8299 +Train: [87] [4300/6250] eta: 0:04:26 lr: 0.000005 grad: 0.1186 (0.1235) loss: 0.8605 (0.8642) time: 0.1777 data: 0.1107 max mem: 8299 +Train: [87] [4400/6250] eta: 0:04:12 lr: 0.000005 grad: 0.1203 (0.1236) loss: 0.8650 (0.8642) time: 0.1286 data: 0.0547 max mem: 8299 +Train: [87] [4500/6250] eta: 0:03:59 lr: 0.000005 grad: 0.1115 (0.1236) loss: 0.8602 (0.8641) time: 0.1284 data: 0.0587 max mem: 8299 +Train: [87] [4600/6250] eta: 0:03:46 lr: 0.000005 grad: 0.1219 (0.1236) loss: 0.8580 (0.8640) time: 0.1845 data: 0.1067 max mem: 8299 +Train: [87] [4700/6250] eta: 0:03:32 lr: 0.000005 grad: 0.1261 (0.1236) loss: 0.8571 (0.8639) time: 0.1439 data: 0.0697 max mem: 8299 +Train: [87] [4800/6250] eta: 0:03:18 lr: 0.000005 grad: 0.1223 (0.1236) loss: 0.8594 (0.8638) time: 0.1471 data: 0.0592 max mem: 8299 +Train: [87] [4900/6250] eta: 0:03:05 lr: 0.000005 grad: 0.1052 (0.1237) loss: 0.8683 (0.8637) time: 0.1531 data: 0.0732 max mem: 8299 +Train: [87] [5000/6250] eta: 0:02:51 lr: 0.000005 grad: 0.1282 (0.1238) loss: 0.8636 (0.8636) time: 0.1390 data: 0.0563 max mem: 8299 +Train: [87] [5100/6250] eta: 0:02:37 lr: 0.000005 grad: 0.1172 (0.1239) loss: 0.8600 (0.8635) time: 0.1121 data: 0.0275 max mem: 8299 +Train: [87] [5200/6250] eta: 0:02:23 lr: 0.000005 grad: 0.1188 (0.1239) loss: 0.8571 (0.8634) time: 0.1155 data: 0.0397 max mem: 8299 +Train: [87] [5300/6250] eta: 0:02:09 lr: 0.000005 grad: 0.1213 (0.1239) loss: 0.8568 (0.8633) time: 0.1199 data: 0.0392 max mem: 8299 +Train: [87] [5400/6250] eta: 0:01:55 lr: 0.000005 grad: 0.1208 (0.1240) loss: 0.8610 (0.8632) time: 0.1323 data: 0.0428 max mem: 8299 +Train: [87] [5500/6250] eta: 0:01:42 lr: 0.000005 grad: 0.1255 (0.1240) loss: 0.8636 (0.8631) time: 0.1388 data: 0.0615 max mem: 8299 +Train: [87] [5600/6250] eta: 0:01:28 lr: 0.000005 grad: 0.1199 (0.1240) loss: 0.8586 (0.8631) time: 0.1421 data: 0.0668 max mem: 8299 +Train: [87] [5700/6250] eta: 0:01:14 lr: 0.000005 grad: 0.1274 (0.1240) loss: 0.8609 (0.8630) time: 0.1175 data: 0.0275 max mem: 8299 +Train: [87] [5800/6250] eta: 0:01:01 lr: 0.000005 grad: 0.1146 (0.1240) loss: 0.8513 (0.8629) time: 0.1325 data: 0.0534 max mem: 8299 +Train: [87] [5900/6250] eta: 0:00:47 lr: 0.000005 grad: 0.1207 (0.1240) loss: 0.8625 (0.8628) time: 0.1417 data: 0.0655 max mem: 8299 +Train: [87] [6000/6250] eta: 0:00:33 lr: 0.000005 grad: 0.1250 (0.1241) loss: 0.8568 (0.8627) time: 0.1153 data: 0.0335 max mem: 8299 +Train: [87] [6100/6250] eta: 0:00:20 lr: 0.000005 grad: 0.1171 (0.1241) loss: 0.8582 (0.8627) time: 0.1145 data: 0.0353 max mem: 8299 +Train: [87] [6200/6250] eta: 0:00:06 lr: 0.000005 grad: 0.1173 (0.1241) loss: 0.8495 (0.8626) time: 0.1485 data: 0.0613 max mem: 8299 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1145 (0.1241) loss: 0.8614 (0.8626) time: 0.1450 data: 0.0725 max mem: 8299 +Train: [87] Total time: 0:14:14 (0.1367 s / it) +Averaged stats: lr: 0.000005 grad: 0.1145 (0.1241) loss: 0.8614 (0.8626) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:04:35 loss: 0.8739 (0.8739) time: 4.4512 data: 4.3423 max mem: 8299 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8665 (0.8682) time: 0.1040 data: 0.0796 max mem: 8299 +Eval (hcp-train-subset): [87] Total time: 0:00:13 (0.2195 s / it) +Averaged stats (hcp-train-subset): loss: 0.8665 (0.8682) +Eval (hcp-val): [87] [ 0/62] eta: 0:04:37 loss: 0.8745 (0.8745) time: 4.4772 data: 4.4221 max mem: 8299 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8740 (0.8756) time: 0.1203 data: 0.0957 max mem: 8299 +Eval (hcp-val): [87] Total time: 0:00:13 (0.2133 s / it) +Averaged stats (hcp-val): loss: 0.8740 (0.8756) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 8:38:03 lr: 0.000005 grad: 0.0789 (0.0789) loss: 0.9019 (0.9019) time: 4.9734 data: 4.6166 max mem: 8299 +Train: [88] [ 100/6250] eta: 0:19:38 lr: 0.000005 grad: 0.1114 (0.1324) loss: 0.8775 (0.8736) time: 0.1181 data: 0.0331 max mem: 8299 +Train: [88] [ 200/6250] eta: 0:16:20 lr: 0.000005 grad: 0.1222 (0.1303) loss: 0.8656 (0.8718) time: 0.1191 data: 0.0236 max mem: 8299 +Train: [88] [ 300/6250] eta: 0:15:19 lr: 0.000005 grad: 0.1270 (0.1332) loss: 0.8712 (0.8707) time: 0.1630 data: 0.0763 max mem: 8299 +Train: [88] [ 400/6250] eta: 0:14:46 lr: 0.000005 grad: 0.1285 (0.1342) loss: 0.8619 (0.8683) time: 0.1708 data: 0.0765 max mem: 8299 +Train: [88] [ 500/6250] eta: 0:13:58 lr: 0.000005 grad: 0.1178 (0.1335) loss: 0.8602 (0.8675) time: 0.1173 data: 0.0297 max mem: 8299 +Train: [88] [ 600/6250] eta: 0:13:30 lr: 0.000005 grad: 0.1328 (0.1335) loss: 0.8693 (0.8663) time: 0.1134 data: 0.0247 max mem: 8299 +Train: [88] [ 700/6250] eta: 0:13:16 lr: 0.000005 grad: 0.1359 (0.1329) loss: 0.8587 (0.8656) time: 0.1457 data: 0.0605 max mem: 8299 +Train: [88] [ 800/6250] eta: 0:13:04 lr: 0.000005 grad: 0.1240 (0.1329) loss: 0.8685 (0.8652) time: 0.1394 data: 0.0453 max mem: 8299 +Train: [88] [ 900/6250] eta: 0:12:56 lr: 0.000005 grad: 0.1255 (0.1327) loss: 0.8675 (0.8653) time: 0.1716 data: 0.0764 max mem: 8299 +Train: [88] [1000/6250] eta: 0:12:46 lr: 0.000005 grad: 0.1182 (0.1323) loss: 0.8678 (0.8654) time: 0.1497 data: 0.0545 max mem: 8299 +Train: [88] [1100/6250] eta: 0:12:36 lr: 0.000005 grad: 0.1317 (0.1317) loss: 0.8598 (0.8654) time: 0.1534 data: 0.0583 max mem: 8299 +Train: [88] [1200/6250] eta: 0:12:23 lr: 0.000005 grad: 0.1278 (0.1313) loss: 0.8618 (0.8652) time: 0.1165 data: 0.0255 max mem: 8299 +Train: [88] [1300/6250] eta: 0:12:06 lr: 0.000005 grad: 0.1322 (0.1311) loss: 0.8600 (0.8651) time: 0.1484 data: 0.0547 max mem: 8299 +Train: [88] [1400/6250] eta: 0:11:48 lr: 0.000005 grad: 0.1260 (0.1305) loss: 0.8577 (0.8651) time: 0.1329 data: 0.0398 max mem: 8299 +Train: [88] [1500/6250] eta: 0:11:32 lr: 0.000005 grad: 0.1233 (0.1302) loss: 0.8537 (0.8648) time: 0.1562 data: 0.0311 max mem: 8299 +Train: [88] [1600/6250] eta: 0:11:15 lr: 0.000005 grad: 0.1274 (0.1300) loss: 0.8623 (0.8645) time: 0.1263 data: 0.0404 max mem: 8299 +Train: [88] [1700/6250] eta: 0:10:59 lr: 0.000005 grad: 0.1181 (0.1298) loss: 0.8664 (0.8644) time: 0.1697 data: 0.0880 max mem: 8299 +Train: [88] [1800/6250] eta: 0:10:42 lr: 0.000005 grad: 0.1144 (0.1296) loss: 0.8643 (0.8643) time: 0.1548 data: 0.0761 max mem: 8299 +Train: [88] [1900/6250] eta: 0:10:24 lr: 0.000005 grad: 0.1212 (0.1294) loss: 0.8641 (0.8643) time: 0.1316 data: 0.0450 max mem: 8299 +Train: [88] [2000/6250] eta: 0:10:11 lr: 0.000005 grad: 0.1300 (0.1292) loss: 0.8644 (0.8643) time: 0.1706 data: 0.0794 max mem: 8299 +Train: [88] [2100/6250] eta: 0:09:57 lr: 0.000005 grad: 0.1243 (0.1289) loss: 0.8620 (0.8641) time: 0.1489 data: 0.0744 max mem: 8299 +Train: [88] [2200/6250] eta: 0:09:43 lr: 0.000005 grad: 0.1230 (0.1287) loss: 0.8627 (0.8640) time: 0.1624 data: 0.0703 max mem: 8299 +Train: [88] [2300/6250] eta: 0:09:30 lr: 0.000005 grad: 0.1131 (0.1285) loss: 0.8648 (0.8639) time: 0.1471 data: 0.0552 max mem: 8299 +Train: [88] [2400/6250] eta: 0:09:16 lr: 0.000005 grad: 0.1193 (0.1284) loss: 0.8635 (0.8638) time: 0.1506 data: 0.0637 max mem: 8299 +Train: [88] [2500/6250] eta: 0:09:01 lr: 0.000005 grad: 0.1229 (0.1284) loss: 0.8608 (0.8637) time: 0.1231 data: 0.0413 max mem: 8299 +Train: [88] [2600/6250] eta: 0:08:48 lr: 0.000005 grad: 0.1280 (0.1284) loss: 0.8608 (0.8635) time: 0.1289 data: 0.0487 max mem: 8299 +Train: [88] [2700/6250] eta: 0:08:32 lr: 0.000005 grad: 0.1239 (0.1285) loss: 0.8535 (0.8633) time: 0.1292 data: 0.0366 max mem: 8299 +Train: [88] [2800/6250] eta: 0:08:19 lr: 0.000005 grad: 0.1185 (0.1285) loss: 0.8642 (0.8631) time: 0.1784 data: 0.1032 max mem: 8299 +Train: [88] [2900/6250] eta: 0:08:03 lr: 0.000004 grad: 0.1260 (0.1285) loss: 0.8603 (0.8630) time: 0.1339 data: 0.0676 max mem: 8299 +Train: [88] [3000/6250] eta: 0:07:47 lr: 0.000004 grad: 0.1269 (0.1285) loss: 0.8530 (0.8628) time: 0.1337 data: 0.0573 max mem: 8299 +Train: [88] [3100/6250] eta: 0:07:31 lr: 0.000004 grad: 0.1167 (0.1284) loss: 0.8618 (0.8626) time: 0.1403 data: 0.0709 max mem: 8299 +Train: [88] [3200/6250] eta: 0:07:15 lr: 0.000004 grad: 0.1227 (0.1283) loss: 0.8640 (0.8624) time: 0.1253 data: 0.0550 max mem: 8299 +Train: [88] [3300/6250] eta: 0:07:00 lr: 0.000004 grad: 0.1137 (0.1281) loss: 0.8583 (0.8624) time: 0.1334 data: 0.0616 max mem: 8299 +Train: [88] [3400/6250] eta: 0:06:44 lr: 0.000004 grad: 0.1250 (0.1281) loss: 0.8610 (0.8623) time: 0.1225 data: 0.0491 max mem: 8299 +Train: [88] [3500/6250] eta: 0:06:30 lr: 0.000004 grad: 0.1229 (0.1280) loss: 0.8579 (0.8623) time: 0.1270 data: 0.0477 max mem: 8299 +Train: [88] [3600/6250] eta: 0:06:15 lr: 0.000004 grad: 0.1194 (0.1279) loss: 0.8599 (0.8622) time: 0.1238 data: 0.0555 max mem: 8299 +Train: [88] [3700/6250] eta: 0:05:59 lr: 0.000004 grad: 0.1244 (0.1277) loss: 0.8583 (0.8622) time: 0.1180 data: 0.0426 max mem: 8299 +Train: [88] [3800/6250] eta: 0:05:44 lr: 0.000004 grad: 0.1217 (0.1276) loss: 0.8623 (0.8622) time: 0.1263 data: 0.0536 max mem: 8299 +Train: [88] [3900/6250] eta: 0:05:31 lr: 0.000004 grad: 0.1166 (0.1275) loss: 0.8552 (0.8622) time: 0.1513 data: 0.0726 max mem: 8299 +Train: [88] [4000/6250] eta: 0:05:16 lr: 0.000004 grad: 0.1227 (0.1275) loss: 0.8595 (0.8621) time: 0.1279 data: 0.0429 max mem: 8299 +Train: [88] [4100/6250] eta: 0:05:02 lr: 0.000004 grad: 0.1278 (0.1275) loss: 0.8588 (0.8621) time: 0.1208 data: 0.0456 max mem: 8299 +Train: [88] [4200/6250] eta: 0:04:47 lr: 0.000004 grad: 0.1239 (0.1276) loss: 0.8586 (0.8620) time: 0.1332 data: 0.0496 max mem: 8299 +Train: [88] [4300/6250] eta: 0:04:34 lr: 0.000004 grad: 0.1307 (0.1276) loss: 0.8653 (0.8620) time: 0.1473 data: 0.0613 max mem: 8299 +Train: [88] [4400/6250] eta: 0:04:20 lr: 0.000004 grad: 0.1198 (0.1277) loss: 0.8556 (0.8619) time: 0.1266 data: 0.0460 max mem: 8299 +Train: [88] [4500/6250] eta: 0:04:06 lr: 0.000004 grad: 0.1164 (0.1276) loss: 0.8669 (0.8620) time: 0.1368 data: 0.0646 max mem: 8299 +Train: [88] [4600/6250] eta: 0:03:52 lr: 0.000004 grad: 0.1284 (0.1276) loss: 0.8638 (0.8620) time: 0.1383 data: 0.0630 max mem: 8299 +Train: [88] [4700/6250] eta: 0:03:38 lr: 0.000004 grad: 0.1200 (0.1275) loss: 0.8586 (0.8619) time: 0.1517 data: 0.0782 max mem: 8299 +Train: [88] [4800/6250] eta: 0:03:24 lr: 0.000004 grad: 0.1160 (0.1274) loss: 0.8679 (0.8620) time: 0.1293 data: 0.0497 max mem: 8299 +Train: [88] [4900/6250] eta: 0:03:09 lr: 0.000004 grad: 0.1216 (0.1273) loss: 0.8656 (0.8620) time: 0.1359 data: 0.0529 max mem: 8299 +Train: [88] [5000/6250] eta: 0:02:55 lr: 0.000004 grad: 0.1233 (0.1273) loss: 0.8624 (0.8620) time: 0.1132 data: 0.0225 max mem: 8299 +Train: [88] [5100/6250] eta: 0:02:41 lr: 0.000004 grad: 0.1250 (0.1272) loss: 0.8707 (0.8621) time: 0.1232 data: 0.0362 max mem: 8299 +Train: [88] [5200/6250] eta: 0:02:26 lr: 0.000004 grad: 0.1253 (0.1272) loss: 0.8513 (0.8620) time: 0.1297 data: 0.0528 max mem: 8299 +Train: [88] [5300/6250] eta: 0:02:12 lr: 0.000004 grad: 0.1234 (0.1272) loss: 0.8608 (0.8621) time: 0.1153 data: 0.0295 max mem: 8299 +Train: [88] [5400/6250] eta: 0:01:58 lr: 0.000004 grad: 0.1236 (0.1273) loss: 0.8671 (0.8621) time: 0.1316 data: 0.0468 max mem: 8299 +Train: [88] [5500/6250] eta: 0:01:44 lr: 0.000004 grad: 0.1301 (0.1273) loss: 0.8539 (0.8620) time: 0.1270 data: 0.0538 max mem: 8299 +Train: [88] [5600/6250] eta: 0:01:30 lr: 0.000004 grad: 0.1200 (0.1274) loss: 0.8606 (0.8620) time: 0.1333 data: 0.0459 max mem: 8299 +Train: [88] [5700/6250] eta: 0:01:16 lr: 0.000004 grad: 0.1346 (0.1274) loss: 0.8589 (0.8619) time: 0.1405 data: 0.0618 max mem: 8299 +Train: [88] [5800/6250] eta: 0:01:02 lr: 0.000004 grad: 0.1300 (0.1274) loss: 0.8592 (0.8619) time: 0.1155 data: 0.0427 max mem: 8299 +Train: [88] [5900/6250] eta: 0:00:48 lr: 0.000004 grad: 0.1308 (0.1275) loss: 0.8629 (0.8619) time: 0.1325 data: 0.0575 max mem: 8299 +Train: [88] [6000/6250] eta: 0:00:34 lr: 0.000004 grad: 0.1250 (0.1276) loss: 0.8575 (0.8618) time: 0.1369 data: 0.0554 max mem: 8299 +Train: [88] [6100/6250] eta: 0:00:20 lr: 0.000004 grad: 0.1281 (0.1276) loss: 0.8537 (0.8618) time: 0.1386 data: 0.0567 max mem: 8299 +Train: [88] [6200/6250] eta: 0:00:06 lr: 0.000004 grad: 0.1272 (0.1277) loss: 0.8603 (0.8617) time: 0.1175 data: 0.0360 max mem: 8299 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1321 (0.1277) loss: 0.8558 (0.8617) time: 0.1382 data: 0.0598 max mem: 8299 +Train: [88] Total time: 0:14:29 (0.1392 s / it) +Averaged stats: lr: 0.000004 grad: 0.1321 (0.1277) loss: 0.8558 (0.8617) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:06:22 loss: 0.8701 (0.8701) time: 6.1689 data: 6.1394 max mem: 8299 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8651 (0.8676) time: 0.1083 data: 0.0825 max mem: 8299 +Eval (hcp-train-subset): [88] Total time: 0:00:14 (0.2296 s / it) +Averaged stats (hcp-train-subset): loss: 0.8651 (0.8676) +Eval (hcp-val): [88] [ 0/62] eta: 0:04:59 loss: 0.8751 (0.8751) time: 4.8362 data: 4.7786 max mem: 8299 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8735 (0.8756) time: 0.1228 data: 0.0983 max mem: 8299 +Eval (hcp-val): [88] Total time: 0:00:13 (0.2126 s / it) +Averaged stats (hcp-val): loss: 0.8735 (0.8756) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 9:42:38 lr: 0.000004 grad: 0.0755 (0.0755) loss: 0.9052 (0.9052) time: 5.5934 data: 5.4747 max mem: 8299 +Train: [89] [ 100/6250] eta: 0:19:30 lr: 0.000004 grad: 0.1177 (0.1573) loss: 0.8709 (0.8660) time: 0.1425 data: 0.0416 max mem: 8299 +Train: [89] [ 200/6250] eta: 0:16:23 lr: 0.000004 grad: 0.1181 (0.1462) loss: 0.8680 (0.8671) time: 0.1246 data: 0.0406 max mem: 8299 +Train: [89] [ 300/6250] eta: 0:15:16 lr: 0.000004 grad: 0.1212 (0.1393) loss: 0.8631 (0.8666) time: 0.1559 data: 0.0663 max mem: 8299 +Train: [89] [ 400/6250] eta: 0:14:38 lr: 0.000004 grad: 0.1303 (0.1366) loss: 0.8579 (0.8658) time: 0.1464 data: 0.0513 max mem: 8299 +Train: [89] [ 500/6250] eta: 0:14:02 lr: 0.000004 grad: 0.1038 (0.1333) loss: 0.8601 (0.8653) time: 0.1116 data: 0.0241 max mem: 8299 +Train: [89] [ 600/6250] eta: 0:13:32 lr: 0.000004 grad: 0.1087 (0.1312) loss: 0.8662 (0.8650) time: 0.1330 data: 0.0489 max mem: 8299 +Train: [89] [ 700/6250] eta: 0:13:05 lr: 0.000004 grad: 0.1214 (0.1302) loss: 0.8610 (0.8648) time: 0.1339 data: 0.0399 max mem: 8299 +Train: [89] [ 800/6250] eta: 0:12:51 lr: 0.000004 grad: 0.1151 (0.1292) loss: 0.8649 (0.8648) time: 0.1616 data: 0.0778 max mem: 8299 +Train: [89] [ 900/6250] eta: 0:12:36 lr: 0.000004 grad: 0.1209 (0.1287) loss: 0.8666 (0.8646) time: 0.1365 data: 0.0414 max mem: 8299 +Train: [89] [1000/6250] eta: 0:12:18 lr: 0.000004 grad: 0.1215 (0.1283) loss: 0.8613 (0.8646) time: 0.1231 data: 0.0448 max mem: 8299 +Train: [89] [1100/6250] eta: 0:11:59 lr: 0.000004 grad: 0.1226 (0.1280) loss: 0.8611 (0.8644) time: 0.1216 data: 0.0349 max mem: 8299 +Train: [89] [1200/6250] eta: 0:11:42 lr: 0.000004 grad: 0.1328 (0.1279) loss: 0.8559 (0.8642) time: 0.1316 data: 0.0624 max mem: 8299 +Train: [89] [1300/6250] eta: 0:11:28 lr: 0.000004 grad: 0.1111 (0.1274) loss: 0.8585 (0.8641) time: 0.1509 data: 0.0729 max mem: 8299 +Train: [89] [1400/6250] eta: 0:11:09 lr: 0.000004 grad: 0.1296 (0.1274) loss: 0.8701 (0.8640) time: 0.1320 data: 0.0542 max mem: 8299 +Train: [89] [1500/6250] eta: 0:10:52 lr: 0.000004 grad: 0.1390 (0.1275) loss: 0.8528 (0.8639) time: 0.1144 data: 0.0193 max mem: 8299 +Train: [89] [1600/6250] eta: 0:10:37 lr: 0.000004 grad: 0.1249 (0.1274) loss: 0.8564 (0.8638) time: 0.1360 data: 0.0474 max mem: 8299 +Train: [89] [1700/6250] eta: 0:10:25 lr: 0.000004 grad: 0.1219 (0.1273) loss: 0.8665 (0.8637) time: 0.1434 data: 0.0667 max mem: 8299 +Train: [89] [1800/6250] eta: 0:10:10 lr: 0.000004 grad: 0.1182 (0.1271) loss: 0.8650 (0.8636) time: 0.1217 data: 0.0429 max mem: 8299 +Train: [89] [1900/6250] eta: 0:09:53 lr: 0.000004 grad: 0.1247 (0.1268) loss: 0.8569 (0.8633) time: 0.1331 data: 0.0546 max mem: 8299 +Train: [89] [2000/6250] eta: 0:09:39 lr: 0.000004 grad: 0.1001 (0.1265) loss: 0.8652 (0.8633) time: 0.1433 data: 0.0626 max mem: 8299 +Train: [89] [2100/6250] eta: 0:09:26 lr: 0.000004 grad: 0.1158 (0.1262) loss: 0.8610 (0.8632) time: 0.1581 data: 0.0791 max mem: 8299 +Train: [89] [2200/6250] eta: 0:09:12 lr: 0.000004 grad: 0.1239 (0.1260) loss: 0.8651 (0.8632) time: 0.1398 data: 0.0634 max mem: 8299 +Train: [89] [2300/6250] eta: 0:08:57 lr: 0.000004 grad: 0.1272 (0.1261) loss: 0.8482 (0.8630) time: 0.1286 data: 0.0478 max mem: 8299 +Train: [89] [2400/6250] eta: 0:08:44 lr: 0.000004 grad: 0.1164 (0.1258) loss: 0.8639 (0.8629) time: 0.1591 data: 0.0785 max mem: 8299 +Train: [89] [2500/6250] eta: 0:08:31 lr: 0.000004 grad: 0.1226 (0.1258) loss: 0.8635 (0.8629) time: 0.1365 data: 0.0593 max mem: 8299 +Train: [89] [2600/6250] eta: 0:08:19 lr: 0.000004 grad: 0.1220 (0.1257) loss: 0.8687 (0.8628) time: 0.1248 data: 0.0420 max mem: 8299 +Train: [89] [2700/6250] eta: 0:08:06 lr: 0.000004 grad: 0.1308 (0.1258) loss: 0.8636 (0.8628) time: 0.1697 data: 0.0818 max mem: 8299 +Train: [89] [2800/6250] eta: 0:07:51 lr: 0.000004 grad: 0.1228 (0.1260) loss: 0.8548 (0.8627) time: 0.1234 data: 0.0459 max mem: 8299 +Train: [89] [2900/6250] eta: 0:07:37 lr: 0.000004 grad: 0.1203 (0.1261) loss: 0.8569 (0.8627) time: 0.1295 data: 0.0513 max mem: 8299 +Train: [89] [3000/6250] eta: 0:07:24 lr: 0.000004 grad: 0.1199 (0.1262) loss: 0.8586 (0.8626) time: 0.1311 data: 0.0522 max mem: 8299 +Train: [89] [3100/6250] eta: 0:07:10 lr: 0.000004 grad: 0.1240 (0.1262) loss: 0.8577 (0.8625) time: 0.1395 data: 0.0596 max mem: 8299 +Train: [89] [3200/6250] eta: 0:06:57 lr: 0.000004 grad: 0.1250 (0.1263) loss: 0.8563 (0.8624) time: 0.1289 data: 0.0471 max mem: 8299 +Train: [89] [3300/6250] eta: 0:06:43 lr: 0.000004 grad: 0.1297 (0.1264) loss: 0.8549 (0.8623) time: 0.1483 data: 0.0601 max mem: 8299 +Train: [89] [3400/6250] eta: 0:06:30 lr: 0.000004 grad: 0.1220 (0.1264) loss: 0.8634 (0.8622) time: 0.1656 data: 0.0905 max mem: 8299 +Train: [89] [3500/6250] eta: 0:06:15 lr: 0.000004 grad: 0.1280 (0.1264) loss: 0.8598 (0.8621) time: 0.1364 data: 0.0619 max mem: 8299 +Train: [89] [3600/6250] eta: 0:06:01 lr: 0.000004 grad: 0.1112 (0.1264) loss: 0.8573 (0.8621) time: 0.1156 data: 0.0338 max mem: 8299 +Train: [89] [3700/6250] eta: 0:05:47 lr: 0.000004 grad: 0.1166 (0.1262) loss: 0.8583 (0.8620) time: 0.1355 data: 0.0590 max mem: 8299 +Train: [89] [3800/6250] eta: 0:05:33 lr: 0.000004 grad: 0.1120 (0.1262) loss: 0.8677 (0.8620) time: 0.1329 data: 0.0530 max mem: 8299 +Train: [89] [3900/6250] eta: 0:05:19 lr: 0.000004 grad: 0.1203 (0.1261) loss: 0.8566 (0.8620) time: 0.1172 data: 0.0408 max mem: 8299 +Train: [89] [4000/6250] eta: 0:05:06 lr: 0.000004 grad: 0.1140 (0.1259) loss: 0.8674 (0.8621) time: 0.1423 data: 0.0680 max mem: 8299 +Train: [89] [4100/6250] eta: 0:04:52 lr: 0.000004 grad: 0.1107 (0.1258) loss: 0.8680 (0.8621) time: 0.1556 data: 0.0708 max mem: 8299 +Train: [89] [4200/6250] eta: 0:04:40 lr: 0.000004 grad: 0.1220 (0.1257) loss: 0.8662 (0.8621) time: 0.1581 data: 0.0762 max mem: 8299 +Train: [89] [4300/6250] eta: 0:04:26 lr: 0.000004 grad: 0.1177 (0.1256) loss: 0.8644 (0.8622) time: 0.1390 data: 0.0520 max mem: 8299 +Train: [89] [4400/6250] eta: 0:04:13 lr: 0.000004 grad: 0.1119 (0.1256) loss: 0.8635 (0.8622) time: 0.1281 data: 0.0520 max mem: 8299 +Train: [89] [4500/6250] eta: 0:03:59 lr: 0.000004 grad: 0.1202 (0.1254) loss: 0.8560 (0.8622) time: 0.1481 data: 0.0649 max mem: 8299 +Train: [89] [4600/6250] eta: 0:03:46 lr: 0.000004 grad: 0.1139 (0.1253) loss: 0.8650 (0.8623) time: 0.1407 data: 0.0643 max mem: 8299 +Train: [89] [4700/6250] eta: 0:03:32 lr: 0.000004 grad: 0.1225 (0.1253) loss: 0.8628 (0.8622) time: 0.1328 data: 0.0497 max mem: 8299 +Train: [89] [4800/6250] eta: 0:03:18 lr: 0.000004 grad: 0.1213 (0.1252) loss: 0.8558 (0.8622) time: 0.1309 data: 0.0452 max mem: 8299 +Train: [89] [4900/6250] eta: 0:03:05 lr: 0.000004 grad: 0.1230 (0.1252) loss: 0.8581 (0.8621) time: 0.1429 data: 0.0647 max mem: 8299 +Train: [89] [5000/6250] eta: 0:02:51 lr: 0.000004 grad: 0.1242 (0.1252) loss: 0.8640 (0.8621) time: 0.1231 data: 0.0264 max mem: 8299 +Train: [89] [5100/6250] eta: 0:02:37 lr: 0.000004 grad: 0.1153 (0.1251) loss: 0.8583 (0.8620) time: 0.1310 data: 0.0418 max mem: 8299 +Train: [89] [5200/6250] eta: 0:02:23 lr: 0.000003 grad: 0.1220 (0.1252) loss: 0.8595 (0.8619) time: 0.1195 data: 0.0351 max mem: 8299 +Train: [89] [5300/6250] eta: 0:02:09 lr: 0.000003 grad: 0.1102 (0.1251) loss: 0.8569 (0.8618) time: 0.1399 data: 0.0606 max mem: 8299 +Train: [89] [5400/6250] eta: 0:01:55 lr: 0.000003 grad: 0.1189 (0.1251) loss: 0.8602 (0.8616) time: 0.1346 data: 0.0498 max mem: 8299 +Train: [89] [5500/6250] eta: 0:01:42 lr: 0.000003 grad: 0.1219 (0.1251) loss: 0.8585 (0.8616) time: 0.1248 data: 0.0475 max mem: 8299 +Train: [89] [5600/6250] eta: 0:01:28 lr: 0.000003 grad: 0.1263 (0.1252) loss: 0.8547 (0.8615) time: 0.1237 data: 0.0430 max mem: 8299 +Train: [89] [5700/6250] eta: 0:01:14 lr: 0.000003 grad: 0.1228 (0.1251) loss: 0.8606 (0.8614) time: 0.1191 data: 0.0310 max mem: 8299 +Train: [89] [5800/6250] eta: 0:01:01 lr: 0.000003 grad: 0.1209 (0.1252) loss: 0.8621 (0.8614) time: 0.1344 data: 0.0616 max mem: 8299 +Train: [89] [5900/6250] eta: 0:00:47 lr: 0.000003 grad: 0.1144 (0.1252) loss: 0.8674 (0.8613) time: 0.1642 data: 0.0829 max mem: 8299 +Train: [89] [6000/6250] eta: 0:00:33 lr: 0.000003 grad: 0.1110 (0.1252) loss: 0.8638 (0.8613) time: 0.1185 data: 0.0362 max mem: 8299 +Train: [89] [6100/6250] eta: 0:00:20 lr: 0.000003 grad: 0.1180 (0.1251) loss: 0.8637 (0.8613) time: 0.1486 data: 0.0793 max mem: 8299 +Train: [89] [6200/6250] eta: 0:00:06 lr: 0.000003 grad: 0.1286 (0.1253) loss: 0.8530 (0.8612) time: 0.1382 data: 0.0545 max mem: 8299 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1290 (0.1252) loss: 0.8558 (0.8612) time: 0.1456 data: 0.0608 max mem: 8299 +Train: [89] Total time: 0:14:15 (0.1369 s / it) +Averaged stats: lr: 0.000003 grad: 0.1290 (0.1252) loss: 0.8558 (0.8612) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:04:47 loss: 0.8720 (0.8720) time: 4.6404 data: 4.5915 max mem: 8299 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8638 (0.8669) time: 0.1357 data: 0.1097 max mem: 8299 +Eval (hcp-train-subset): [89] Total time: 0:00:14 (0.2311 s / it) +Averaged stats (hcp-train-subset): loss: 0.8638 (0.8669) +Making plots (hcp-train-subset): example=55 +Eval (hcp-val): [89] [ 0/62] eta: 0:05:41 loss: 0.8702 (0.8702) time: 5.5055 data: 5.4762 max mem: 8299 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8740 (0.8753) time: 0.1141 data: 0.0898 max mem: 8299 +Eval (hcp-val): [89] Total time: 0:00:12 (0.2055 s / it) +Averaged stats (hcp-val): loss: 0.8740 (0.8753) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 10:42:48 lr: 0.000003 grad: 0.2637 (0.2637) loss: 0.8425 (0.8425) time: 6.1709 data: 6.0775 max mem: 8299 +Train: [90] [ 100/6250] eta: 0:20:18 lr: 0.000003 grad: 0.1198 (0.1436) loss: 0.8823 (0.8728) time: 0.1393 data: 0.0345 max mem: 8299 +Train: [90] [ 200/6250] eta: 0:17:21 lr: 0.000003 grad: 0.1292 (0.1415) loss: 0.8643 (0.8701) time: 0.1412 data: 0.0443 max mem: 8299 +Train: [90] [ 300/6250] eta: 0:15:51 lr: 0.000003 grad: 0.1166 (0.1378) loss: 0.8635 (0.8674) time: 0.1425 data: 0.0517 max mem: 8299 +Train: [90] [ 400/6250] eta: 0:14:54 lr: 0.000003 grad: 0.1161 (0.1336) loss: 0.8624 (0.8666) time: 0.1102 data: 0.0217 max mem: 8299 +Train: [90] [ 500/6250] eta: 0:14:23 lr: 0.000003 grad: 0.1199 (0.1320) loss: 0.8690 (0.8662) time: 0.1462 data: 0.0546 max mem: 8299 +Train: [90] [ 600/6250] eta: 0:13:54 lr: 0.000003 grad: 0.1188 (0.1303) loss: 0.8656 (0.8661) time: 0.1341 data: 0.0383 max mem: 8299 +Train: [90] [ 700/6250] eta: 0:13:29 lr: 0.000003 grad: 0.1164 (0.1288) loss: 0.8642 (0.8660) time: 0.1395 data: 0.0629 max mem: 8299 +Train: [90] [ 800/6250] eta: 0:12:58 lr: 0.000003 grad: 0.1235 (0.1282) loss: 0.8685 (0.8657) time: 0.1241 data: 0.0418 max mem: 8299 +Train: [90] [ 900/6250] eta: 0:12:35 lr: 0.000003 grad: 0.1163 (0.1275) loss: 0.8642 (0.8655) time: 0.1294 data: 0.0338 max mem: 8299 +Train: [90] [1000/6250] eta: 0:12:19 lr: 0.000003 grad: 0.1221 (0.1272) loss: 0.8609 (0.8652) time: 0.1436 data: 0.0694 max mem: 8299 +Train: [90] [1100/6250] eta: 0:11:59 lr: 0.000003 grad: 0.1195 (0.1268) loss: 0.8654 (0.8650) time: 0.1346 data: 0.0479 max mem: 8299 +Train: [90] [1200/6250] eta: 0:11:38 lr: 0.000003 grad: 0.1282 (0.1265) loss: 0.8601 (0.8648) time: 0.1082 data: 0.0101 max mem: 8299 +Train: [90] [1300/6250] eta: 0:11:21 lr: 0.000003 grad: 0.1113 (0.1263) loss: 0.8669 (0.8645) time: 0.1326 data: 0.0431 max mem: 8299 +Train: [90] [1400/6250] eta: 0:11:08 lr: 0.000003 grad: 0.1251 (0.1264) loss: 0.8587 (0.8643) time: 0.1489 data: 0.0617 max mem: 8299 +Train: [90] [1500/6250] eta: 0:10:54 lr: 0.000003 grad: 0.1263 (0.1265) loss: 0.8574 (0.8641) time: 0.1304 data: 0.0555 max mem: 8299 +Train: [90] [1600/6250] eta: 0:10:40 lr: 0.000003 grad: 0.1256 (0.1265) loss: 0.8568 (0.8640) time: 0.1314 data: 0.0505 max mem: 8299 +Train: [90] [1700/6250] eta: 0:10:23 lr: 0.000003 grad: 0.1187 (0.1264) loss: 0.8616 (0.8638) time: 0.1306 data: 0.0446 max mem: 8299 +Train: [90] [1800/6250] eta: 0:10:10 lr: 0.000003 grad: 0.1275 (0.1264) loss: 0.8630 (0.8637) time: 0.1238 data: 0.0441 max mem: 8299 +Train: [90] [1900/6250] eta: 0:09:56 lr: 0.000003 grad: 0.1231 (0.1263) loss: 0.8635 (0.8637) time: 0.1496 data: 0.0644 max mem: 8299 +Train: [90] [2000/6250] eta: 0:09:40 lr: 0.000003 grad: 0.1190 (0.1264) loss: 0.8628 (0.8636) time: 0.1387 data: 0.0550 max mem: 8299 +Train: [90] [2100/6250] eta: 0:09:24 lr: 0.000003 grad: 0.1213 (0.1264) loss: 0.8650 (0.8636) time: 0.1307 data: 0.0519 max mem: 8299 +Train: [90] [2200/6250] eta: 0:09:10 lr: 0.000003 grad: 0.1197 (0.1265) loss: 0.8670 (0.8635) time: 0.1451 data: 0.0592 max mem: 8299 +Train: [90] [2300/6250] eta: 0:08:57 lr: 0.000003 grad: 0.1200 (0.1265) loss: 0.8702 (0.8636) time: 0.1152 data: 0.0373 max mem: 8299 +Train: [90] [2400/6250] eta: 0:08:42 lr: 0.000003 grad: 0.1301 (0.1266) loss: 0.8619 (0.8635) time: 0.1134 data: 0.0371 max mem: 8299 +Train: [90] [2500/6250] eta: 0:08:28 lr: 0.000003 grad: 0.1290 (0.1269) loss: 0.8592 (0.8634) time: 0.1350 data: 0.0451 max mem: 8299 +Train: [90] [2600/6250] eta: 0:08:16 lr: 0.000003 grad: 0.1276 (0.1270) loss: 0.8613 (0.8632) time: 0.1495 data: 0.0680 max mem: 8299 +Train: [90] [2700/6250] eta: 0:08:03 lr: 0.000003 grad: 0.1245 (0.1270) loss: 0.8616 (0.8631) time: 0.1376 data: 0.0595 max mem: 8299 +Train: [90] [2800/6250] eta: 0:07:50 lr: 0.000003 grad: 0.1371 (0.1270) loss: 0.8560 (0.8630) time: 0.1137 data: 0.0331 max mem: 8299 +Train: [90] [2900/6250] eta: 0:07:36 lr: 0.000003 grad: 0.1291 (0.1271) loss: 0.8542 (0.8630) time: 0.1048 data: 0.0280 max mem: 8299 +Train: [90] [3000/6250] eta: 0:07:21 lr: 0.000003 grad: 0.1301 (0.1273) loss: 0.8633 (0.8629) time: 0.1338 data: 0.0575 max mem: 8299 +Train: [90] [3100/6250] eta: 0:07:08 lr: 0.000003 grad: 0.1202 (0.1275) loss: 0.8647 (0.8628) time: 0.1504 data: 0.0725 max mem: 8299 +Train: [90] [3200/6250] eta: 0:06:54 lr: 0.000003 grad: 0.1316 (0.1278) loss: 0.8592 (0.8627) time: 0.1289 data: 0.0551 max mem: 8299 +Train: [90] [3300/6250] eta: 0:06:40 lr: 0.000003 grad: 0.1213 (0.1278) loss: 0.8612 (0.8627) time: 0.1395 data: 0.0639 max mem: 8299 +Train: [90] [3400/6250] eta: 0:06:27 lr: 0.000003 grad: 0.1233 (0.1280) loss: 0.8611 (0.8626) time: 0.1184 data: 0.0390 max mem: 8299 +Train: [90] [3500/6250] eta: 0:06:14 lr: 0.000003 grad: 0.1251 (0.1282) loss: 0.8606 (0.8624) time: 0.1420 data: 0.0565 max mem: 8299 +Train: [90] [3600/6250] eta: 0:06:01 lr: 0.000003 grad: 0.1407 (0.1285) loss: 0.8532 (0.8622) time: 0.1551 data: 0.0792 max mem: 8299 +Train: [90] [3700/6250] eta: 0:05:48 lr: 0.000003 grad: 0.1309 (0.1287) loss: 0.8643 (0.8621) time: 0.1530 data: 0.0730 max mem: 8299 +Train: [90] [3800/6250] eta: 0:05:34 lr: 0.000003 grad: 0.1252 (0.1289) loss: 0.8579 (0.8620) time: 0.1164 data: 0.0314 max mem: 8299 +Train: [90] [3900/6250] eta: 0:05:20 lr: 0.000003 grad: 0.1312 (0.1290) loss: 0.8580 (0.8619) time: 0.1054 data: 0.0239 max mem: 8299 +Train: [90] [4000/6250] eta: 0:05:06 lr: 0.000003 grad: 0.1357 (0.1291) loss: 0.8626 (0.8619) time: 0.1251 data: 0.0517 max mem: 8299 +Train: [90] [4100/6250] eta: 0:04:53 lr: 0.000003 grad: 0.1292 (0.1293) loss: 0.8526 (0.8617) time: 0.1222 data: 0.0506 max mem: 8299 +Train: [90] [4200/6250] eta: 0:04:41 lr: 0.000003 grad: 0.1211 (0.1294) loss: 0.8604 (0.8616) time: 0.1733 data: 0.0985 max mem: 8299 +Train: [90] [4300/6250] eta: 0:04:28 lr: 0.000003 grad: 0.1358 (0.1294) loss: 0.8521 (0.8615) time: 0.1482 data: 0.0808 max mem: 8299 +Train: [90] [4400/6250] eta: 0:04:15 lr: 0.000003 grad: 0.1309 (0.1295) loss: 0.8563 (0.8614) time: 0.1689 data: 0.0757 max mem: 8299 +Train: [90] [4500/6250] eta: 0:04:01 lr: 0.000003 grad: 0.1245 (0.1295) loss: 0.8551 (0.8613) time: 0.1128 data: 0.0378 max mem: 8299 +Train: [90] [4600/6250] eta: 0:03:46 lr: 0.000003 grad: 0.1350 (0.1296) loss: 0.8565 (0.8612) time: 0.1233 data: 0.0541 max mem: 8299 +Train: [90] [4700/6250] eta: 0:03:32 lr: 0.000003 grad: 0.1325 (0.1296) loss: 0.8540 (0.8611) time: 0.1168 data: 0.0448 max mem: 8299 +Train: [90] [4800/6250] eta: 0:03:18 lr: 0.000003 grad: 0.1259 (0.1296) loss: 0.8547 (0.8611) time: 0.1366 data: 0.0497 max mem: 8299 +Train: [90] [4900/6250] eta: 0:03:04 lr: 0.000003 grad: 0.1192 (0.1296) loss: 0.8586 (0.8610) time: 0.1215 data: 0.0431 max mem: 8299 +Train: [90] [5000/6250] eta: 0:02:50 lr: 0.000003 grad: 0.1236 (0.1295) loss: 0.8621 (0.8609) time: 0.1311 data: 0.0487 max mem: 8299 +Train: [90] [5100/6250] eta: 0:02:37 lr: 0.000003 grad: 0.1183 (0.1295) loss: 0.8573 (0.8609) time: 0.1165 data: 0.0308 max mem: 8299 +Train: [90] [5200/6250] eta: 0:02:23 lr: 0.000003 grad: 0.1274 (0.1295) loss: 0.8593 (0.8608) time: 0.1446 data: 0.0514 max mem: 8299 +Train: [90] [5300/6250] eta: 0:02:10 lr: 0.000003 grad: 0.1224 (0.1295) loss: 0.8662 (0.8608) time: 0.1670 data: 0.0826 max mem: 8299 +Train: [90] [5400/6250] eta: 0:01:56 lr: 0.000003 grad: 0.1164 (0.1294) loss: 0.8523 (0.8608) time: 0.1311 data: 0.0606 max mem: 8299 +Train: [90] [5500/6250] eta: 0:01:42 lr: 0.000003 grad: 0.1261 (0.1294) loss: 0.8611 (0.8608) time: 0.1163 data: 0.0335 max mem: 8299 +Train: [90] [5600/6250] eta: 0:01:29 lr: 0.000003 grad: 0.1297 (0.1295) loss: 0.8640 (0.8608) time: 0.1782 data: 0.1021 max mem: 8299 +Train: [90] [5700/6250] eta: 0:01:15 lr: 0.000003 grad: 0.1203 (0.1295) loss: 0.8607 (0.8608) time: 0.1525 data: 0.0744 max mem: 8299 +Train: [90] [5800/6250] eta: 0:01:01 lr: 0.000003 grad: 0.1217 (0.1295) loss: 0.8601 (0.8608) time: 0.1512 data: 0.0443 max mem: 8299 +Train: [90] [5900/6250] eta: 0:00:48 lr: 0.000003 grad: 0.1180 (0.1295) loss: 0.8647 (0.8609) time: 0.1529 data: 0.0650 max mem: 8299 +Train: [90] [6000/6250] eta: 0:00:34 lr: 0.000003 grad: 0.1245 (0.1295) loss: 0.8578 (0.8609) time: 0.1451 data: 0.0562 max mem: 8299 +Train: [90] [6100/6250] eta: 0:00:20 lr: 0.000003 grad: 0.1247 (0.1296) loss: 0.8591 (0.8609) time: 0.1558 data: 0.0813 max mem: 8299 +Train: [90] [6200/6250] eta: 0:00:06 lr: 0.000003 grad: 0.1316 (0.1297) loss: 0.8635 (0.8609) time: 0.1331 data: 0.0571 max mem: 8299 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1245 (0.1297) loss: 0.8614 (0.8609) time: 0.1458 data: 0.0553 max mem: 8299 +Train: [90] Total time: 0:14:28 (0.1389 s / it) +Averaged stats: lr: 0.000003 grad: 0.1245 (0.1297) loss: 0.8614 (0.8609) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:06:18 loss: 0.8707 (0.8707) time: 6.1002 data: 6.0619 max mem: 8299 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8635 (0.8667) time: 0.1354 data: 0.1110 max mem: 8299 +Eval (hcp-train-subset): [90] Total time: 0:00:14 (0.2287 s / it) +Averaged stats (hcp-train-subset): loss: 0.8635 (0.8667) +Eval (hcp-val): [90] [ 0/62] eta: 0:05:47 loss: 0.8754 (0.8754) time: 5.6012 data: 5.5709 max mem: 8299 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8748 (0.8758) time: 0.1244 data: 0.1001 max mem: 8299 +Eval (hcp-val): [90] Total time: 0:00:13 (0.2189 s / it) +Averaged stats (hcp-val): loss: 0.8748 (0.8758) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 9:29:07 lr: 0.000003 grad: 0.2174 (0.2174) loss: 0.8708 (0.8708) time: 5.4637 data: 5.3722 max mem: 8299 +Train: [91] [ 100/6250] eta: 0:19:27 lr: 0.000003 grad: 0.1591 (0.1852) loss: 0.8525 (0.8516) time: 0.1293 data: 0.0304 max mem: 8299 +Train: [91] [ 200/6250] eta: 0:16:15 lr: 0.000003 grad: 0.1327 (0.1720) loss: 0.8495 (0.8501) time: 0.1313 data: 0.0540 max mem: 8299 +Train: [91] [ 300/6250] eta: 0:14:57 lr: 0.000003 grad: 0.1243 (0.1627) loss: 0.8636 (0.8526) time: 0.1363 data: 0.0411 max mem: 8299 +Train: [91] [ 400/6250] eta: 0:13:53 lr: 0.000003 grad: 0.1309 (0.1571) loss: 0.8638 (0.8548) time: 0.0969 data: 0.0088 max mem: 8299 +Train: [91] [ 500/6250] eta: 0:13:10 lr: 0.000003 grad: 0.1169 (0.1532) loss: 0.8653 (0.8565) time: 0.1103 data: 0.0361 max mem: 8299 +Train: [91] [ 600/6250] eta: 0:12:42 lr: 0.000003 grad: 0.1277 (0.1504) loss: 0.8552 (0.8576) time: 0.1333 data: 0.0570 max mem: 8299 +Train: [91] [ 700/6250] eta: 0:12:18 lr: 0.000003 grad: 0.1249 (0.1474) loss: 0.8696 (0.8589) time: 0.1256 data: 0.0501 max mem: 8299 +Train: [91] [ 800/6250] eta: 0:12:02 lr: 0.000003 grad: 0.1146 (0.1455) loss: 0.8680 (0.8594) time: 0.1279 data: 0.0422 max mem: 8299 +Train: [91] [ 900/6250] eta: 0:11:53 lr: 0.000003 grad: 0.1121 (0.1433) loss: 0.8711 (0.8603) time: 0.1506 data: 0.0654 max mem: 8299 +Train: [91] [1000/6250] eta: 0:11:33 lr: 0.000003 grad: 0.1218 (0.1412) loss: 0.8696 (0.8609) time: 0.1219 data: 0.0463 max mem: 8299 +Train: [91] [1100/6250] eta: 0:11:19 lr: 0.000003 grad: 0.1216 (0.1398) loss: 0.8621 (0.8613) time: 0.1480 data: 0.0764 max mem: 8299 +Train: [91] [1200/6250] eta: 0:11:09 lr: 0.000003 grad: 0.1085 (0.1386) loss: 0.8679 (0.8616) time: 0.1551 data: 0.0804 max mem: 8299 +Train: [91] [1300/6250] eta: 0:10:56 lr: 0.000003 grad: 0.1224 (0.1376) loss: 0.8600 (0.8616) time: 0.1286 data: 0.0500 max mem: 8299 +Train: [91] [1400/6250] eta: 0:10:42 lr: 0.000003 grad: 0.1268 (0.1368) loss: 0.8592 (0.8617) time: 0.1214 data: 0.0430 max mem: 8299 +Train: [91] [1500/6250] eta: 0:10:28 lr: 0.000003 grad: 0.1291 (0.1359) loss: 0.8613 (0.8619) time: 0.1223 data: 0.0453 max mem: 8299 +Train: [91] [1600/6250] eta: 0:10:15 lr: 0.000003 grad: 0.1283 (0.1353) loss: 0.8625 (0.8619) time: 0.1342 data: 0.0639 max mem: 8299 +Train: [91] [1700/6250] eta: 0:10:01 lr: 0.000003 grad: 0.1203 (0.1345) loss: 0.8672 (0.8621) time: 0.1423 data: 0.0647 max mem: 8299 +Train: [91] [1800/6250] eta: 0:09:45 lr: 0.000003 grad: 0.1219 (0.1339) loss: 0.8595 (0.8622) time: 0.0950 data: 0.0173 max mem: 8299 +Train: [91] [1900/6250] eta: 0:09:32 lr: 0.000003 grad: 0.1348 (0.1337) loss: 0.8562 (0.8624) time: 0.1285 data: 0.0515 max mem: 8299 +Train: [91] [2000/6250] eta: 0:09:18 lr: 0.000003 grad: 0.1208 (0.1335) loss: 0.8640 (0.8623) time: 0.1448 data: 0.0596 max mem: 8299 +Train: [91] [2100/6250] eta: 0:09:03 lr: 0.000003 grad: 0.1194 (0.1332) loss: 0.8649 (0.8623) time: 0.1216 data: 0.0494 max mem: 8299 +Train: [91] [2200/6250] eta: 0:08:49 lr: 0.000003 grad: 0.1208 (0.1328) loss: 0.8660 (0.8624) time: 0.1360 data: 0.0521 max mem: 8299 +Train: [91] [2300/6250] eta: 0:08:37 lr: 0.000003 grad: 0.1329 (0.1326) loss: 0.8650 (0.8624) time: 0.1345 data: 0.0554 max mem: 8299 +Train: [91] [2400/6250] eta: 0:08:25 lr: 0.000003 grad: 0.1220 (0.1324) loss: 0.8599 (0.8624) time: 0.1317 data: 0.0629 max mem: 8299 +Train: [91] [2500/6250] eta: 0:08:12 lr: 0.000003 grad: 0.1187 (0.1321) loss: 0.8666 (0.8625) time: 0.1244 data: 0.0510 max mem: 8299 +Train: [91] [2600/6250] eta: 0:07:58 lr: 0.000003 grad: 0.1149 (0.1318) loss: 0.8619 (0.8625) time: 0.1417 data: 0.0753 max mem: 8299 +Train: [91] [2700/6250] eta: 0:07:45 lr: 0.000002 grad: 0.1269 (0.1317) loss: 0.8651 (0.8625) time: 0.1401 data: 0.0626 max mem: 8299 +Train: [91] [2800/6250] eta: 0:07:33 lr: 0.000002 grad: 0.1213 (0.1316) loss: 0.8643 (0.8626) time: 0.1158 data: 0.0360 max mem: 8299 +Train: [91] [2900/6250] eta: 0:07:20 lr: 0.000002 grad: 0.1150 (0.1312) loss: 0.8644 (0.8626) time: 0.1376 data: 0.0578 max mem: 8299 +Train: [91] [3000/6250] eta: 0:07:07 lr: 0.000002 grad: 0.1199 (0.1310) loss: 0.8625 (0.8627) time: 0.1214 data: 0.0388 max mem: 8299 +Train: [91] [3100/6250] eta: 0:06:55 lr: 0.000002 grad: 0.1230 (0.1307) loss: 0.8643 (0.8627) time: 0.1641 data: 0.0925 max mem: 8299 +Train: [91] [3200/6250] eta: 0:06:41 lr: 0.000002 grad: 0.1215 (0.1305) loss: 0.8573 (0.8627) time: 0.1400 data: 0.0636 max mem: 8299 +Train: [91] [3300/6250] eta: 0:06:28 lr: 0.000002 grad: 0.1183 (0.1305) loss: 0.8623 (0.8626) time: 0.1300 data: 0.0451 max mem: 8299 +Train: [91] [3400/6250] eta: 0:06:14 lr: 0.000002 grad: 0.1131 (0.1303) loss: 0.8658 (0.8626) time: 0.1226 data: 0.0446 max mem: 8299 +Train: [91] [3500/6250] eta: 0:06:01 lr: 0.000002 grad: 0.1391 (0.1303) loss: 0.8598 (0.8626) time: 0.1346 data: 0.0587 max mem: 8299 +Train: [91] [3600/6250] eta: 0:05:48 lr: 0.000002 grad: 0.1186 (0.1301) loss: 0.8637 (0.8626) time: 0.1056 data: 0.0215 max mem: 8299 +Train: [91] [3700/6250] eta: 0:05:34 lr: 0.000002 grad: 0.1240 (0.1301) loss: 0.8603 (0.8625) time: 0.1468 data: 0.0844 max mem: 8299 +Train: [91] [3800/6250] eta: 0:05:21 lr: 0.000002 grad: 0.1193 (0.1301) loss: 0.8593 (0.8625) time: 0.1439 data: 0.0667 max mem: 8299 +Train: [91] [3900/6250] eta: 0:05:08 lr: 0.000002 grad: 0.1188 (0.1300) loss: 0.8650 (0.8625) time: 0.1248 data: 0.0505 max mem: 8299 +Train: [91] [4000/6250] eta: 0:04:56 lr: 0.000002 grad: 0.1250 (0.1299) loss: 0.8622 (0.8625) time: 0.1905 data: 0.1242 max mem: 8299 +Train: [91] [4100/6250] eta: 0:04:43 lr: 0.000002 grad: 0.1191 (0.1298) loss: 0.8615 (0.8624) time: 0.1103 data: 0.0465 max mem: 8299 +Train: [91] [4200/6250] eta: 0:04:30 lr: 0.000002 grad: 0.1222 (0.1298) loss: 0.8611 (0.8623) time: 0.1168 data: 0.0484 max mem: 8299 +Train: [91] [4300/6250] eta: 0:04:18 lr: 0.000002 grad: 0.1194 (0.1298) loss: 0.8574 (0.8623) time: 0.1345 data: 0.0530 max mem: 8299 +Train: [91] [4400/6250] eta: 0:04:05 lr: 0.000002 grad: 0.1249 (0.1298) loss: 0.8613 (0.8622) time: 0.1316 data: 0.0552 max mem: 8299 +Train: [91] [4500/6250] eta: 0:03:51 lr: 0.000002 grad: 0.1267 (0.1298) loss: 0.8580 (0.8621) time: 0.1403 data: 0.0651 max mem: 8299 +Train: [91] [4600/6250] eta: 0:03:38 lr: 0.000002 grad: 0.1250 (0.1299) loss: 0.8611 (0.8621) time: 0.1312 data: 0.0582 max mem: 8299 +Train: [91] [4700/6250] eta: 0:03:25 lr: 0.000002 grad: 0.1314 (0.1300) loss: 0.8537 (0.8620) time: 0.1238 data: 0.0493 max mem: 8299 +Train: [91] [4800/6250] eta: 0:03:11 lr: 0.000002 grad: 0.1361 (0.1301) loss: 0.8602 (0.8620) time: 0.1280 data: 0.0517 max mem: 8299 +Train: [91] [4900/6250] eta: 0:02:58 lr: 0.000002 grad: 0.1256 (0.1302) loss: 0.8532 (0.8618) time: 0.1238 data: 0.0431 max mem: 8299 +Train: [91] [5000/6250] eta: 0:02:45 lr: 0.000002 grad: 0.1321 (0.1303) loss: 0.8597 (0.8617) time: 0.1315 data: 0.0651 max mem: 8299 +Train: [91] [5100/6250] eta: 0:02:31 lr: 0.000002 grad: 0.1255 (0.1303) loss: 0.8579 (0.8617) time: 0.1199 data: 0.0473 max mem: 8299 +Train: [91] [5200/6250] eta: 0:02:18 lr: 0.000002 grad: 0.1243 (0.1303) loss: 0.8598 (0.8616) time: 0.1279 data: 0.0591 max mem: 8299 +Train: [91] [5300/6250] eta: 0:02:05 lr: 0.000002 grad: 0.1263 (0.1303) loss: 0.8530 (0.8616) time: 0.1253 data: 0.0536 max mem: 8299 +Train: [91] [5400/6250] eta: 0:01:51 lr: 0.000002 grad: 0.1213 (0.1303) loss: 0.8634 (0.8615) time: 0.1225 data: 0.0361 max mem: 8299 +Train: [91] [5500/6250] eta: 0:01:38 lr: 0.000002 grad: 0.1304 (0.1303) loss: 0.8595 (0.8615) time: 0.1277 data: 0.0468 max mem: 8299 +Train: [91] [5600/6250] eta: 0:01:25 lr: 0.000002 grad: 0.1261 (0.1304) loss: 0.8600 (0.8615) time: 0.1373 data: 0.0636 max mem: 8299 +Train: [91] [5700/6250] eta: 0:01:12 lr: 0.000002 grad: 0.1297 (0.1304) loss: 0.8634 (0.8614) time: 0.1157 data: 0.0404 max mem: 8299 +Train: [91] [5800/6250] eta: 0:00:59 lr: 0.000002 grad: 0.1221 (0.1303) loss: 0.8632 (0.8614) time: 0.1249 data: 0.0507 max mem: 8299 +Train: [91] [5900/6250] eta: 0:00:46 lr: 0.000002 grad: 0.1324 (0.1303) loss: 0.8587 (0.8614) time: 0.1437 data: 0.0724 max mem: 8299 +Train: [91] [6000/6250] eta: 0:00:32 lr: 0.000002 grad: 0.1198 (0.1302) loss: 0.8580 (0.8614) time: 0.1289 data: 0.0580 max mem: 8299 +Train: [91] [6100/6250] eta: 0:00:19 lr: 0.000002 grad: 0.1222 (0.1302) loss: 0.8597 (0.8614) time: 0.1861 data: 0.1177 max mem: 8299 +Train: [91] [6200/6250] eta: 0:00:06 lr: 0.000002 grad: 0.1250 (0.1301) loss: 0.8628 (0.8613) time: 0.1200 data: 0.0441 max mem: 8299 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1138 (0.1301) loss: 0.8618 (0.8613) time: 0.1282 data: 0.0579 max mem: 8299 +Train: [91] Total time: 0:13:48 (0.1325 s / it) +Averaged stats: lr: 0.000002 grad: 0.1138 (0.1301) loss: 0.8618 (0.8613) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:04:47 loss: 0.8705 (0.8705) time: 4.6339 data: 4.6049 max mem: 8299 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8624 (0.8659) time: 0.1295 data: 0.1052 max mem: 8299 +Eval (hcp-train-subset): [91] Total time: 0:00:12 (0.2044 s / it) +Averaged stats (hcp-train-subset): loss: 0.8624 (0.8659) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:26 loss: 0.8743 (0.8743) time: 4.2910 data: 4.1994 max mem: 8299 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8740 (0.8749) time: 0.1251 data: 0.0990 max mem: 8299 +Eval (hcp-val): [91] Total time: 0:00:14 (0.2326 s / it) +Averaged stats (hcp-val): loss: 0.8740 (0.8749) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 9:12:06 lr: 0.000002 grad: 0.2586 (0.2586) loss: 0.8830 (0.8830) time: 5.3002 data: 5.1430 max mem: 8299 +Train: [92] [ 100/6250] eta: 0:19:12 lr: 0.000002 grad: 0.1534 (0.1873) loss: 0.8668 (0.8625) time: 0.1453 data: 0.0491 max mem: 8299 +Train: [92] [ 200/6250] eta: 0:16:42 lr: 0.000002 grad: 0.1158 (0.1649) loss: 0.8815 (0.8640) time: 0.1307 data: 0.0225 max mem: 8299 +Train: [92] [ 300/6250] eta: 0:15:29 lr: 0.000002 grad: 0.1286 (0.1535) loss: 0.8612 (0.8653) time: 0.1234 data: 0.0341 max mem: 8299 +Train: [92] [ 400/6250] eta: 0:14:38 lr: 0.000002 grad: 0.1223 (0.1472) loss: 0.8632 (0.8653) time: 0.1275 data: 0.0319 max mem: 8299 +Train: [92] [ 500/6250] eta: 0:14:02 lr: 0.000002 grad: 0.1183 (0.1456) loss: 0.8593 (0.8646) time: 0.1276 data: 0.0379 max mem: 8299 +Train: [92] [ 600/6250] eta: 0:13:37 lr: 0.000002 grad: 0.1280 (0.1436) loss: 0.8636 (0.8648) time: 0.1359 data: 0.0487 max mem: 8299 +Train: [92] [ 700/6250] eta: 0:13:18 lr: 0.000002 grad: 0.1295 (0.1420) loss: 0.8605 (0.8646) time: 0.1438 data: 0.0662 max mem: 8299 +Train: [92] [ 800/6250] eta: 0:12:59 lr: 0.000002 grad: 0.1233 (0.1410) loss: 0.8653 (0.8643) time: 0.1440 data: 0.0596 max mem: 8299 +Train: [92] [ 900/6250] eta: 0:12:41 lr: 0.000002 grad: 0.1141 (0.1398) loss: 0.8638 (0.8642) time: 0.1386 data: 0.0455 max mem: 8299 +Train: [92] [1000/6250] eta: 0:12:22 lr: 0.000002 grad: 0.1096 (0.1390) loss: 0.8663 (0.8640) time: 0.1367 data: 0.0698 max mem: 8299 +Train: [92] [1100/6250] eta: 0:11:59 lr: 0.000002 grad: 0.1274 (0.1378) loss: 0.8691 (0.8640) time: 0.1283 data: 0.0537 max mem: 8299 +Train: [92] [1200/6250] eta: 0:11:41 lr: 0.000002 grad: 0.1197 (0.1369) loss: 0.8638 (0.8639) time: 0.1478 data: 0.0746 max mem: 8299 +Train: [92] [1300/6250] eta: 0:11:22 lr: 0.000002 grad: 0.1245 (0.1362) loss: 0.8624 (0.8638) time: 0.1354 data: 0.0539 max mem: 8299 +Train: [92] [1400/6250] eta: 0:11:05 lr: 0.000002 grad: 0.1222 (0.1356) loss: 0.8618 (0.8637) time: 0.1353 data: 0.0635 max mem: 8299 +Train: [92] [1500/6250] eta: 0:10:49 lr: 0.000002 grad: 0.1224 (0.1349) loss: 0.8594 (0.8635) time: 0.1302 data: 0.0529 max mem: 8299 +Train: [92] [1600/6250] eta: 0:10:31 lr: 0.000002 grad: 0.1190 (0.1341) loss: 0.8657 (0.8634) time: 0.1230 data: 0.0478 max mem: 8299 +Train: [92] [1700/6250] eta: 0:10:19 lr: 0.000002 grad: 0.1229 (0.1335) loss: 0.8617 (0.8632) time: 0.1595 data: 0.0809 max mem: 8299 +Train: [92] [1800/6250] eta: 0:10:06 lr: 0.000002 grad: 0.1275 (0.1330) loss: 0.8604 (0.8631) time: 0.1133 data: 0.0345 max mem: 8299 +Train: [92] [1900/6250] eta: 0:09:52 lr: 0.000002 grad: 0.1107 (0.1325) loss: 0.8640 (0.8630) time: 0.1457 data: 0.0632 max mem: 8299 +Train: [92] [2000/6250] eta: 0:09:38 lr: 0.000002 grad: 0.1169 (0.1321) loss: 0.8611 (0.8629) time: 0.1452 data: 0.0639 max mem: 8299 +Train: [92] [2100/6250] eta: 0:09:24 lr: 0.000002 grad: 0.1170 (0.1318) loss: 0.8574 (0.8627) time: 0.1398 data: 0.0607 max mem: 8299 +Train: [92] [2200/6250] eta: 0:09:10 lr: 0.000002 grad: 0.1214 (0.1315) loss: 0.8622 (0.8626) time: 0.1312 data: 0.0489 max mem: 8299 +Train: [92] [2300/6250] eta: 0:08:56 lr: 0.000002 grad: 0.1204 (0.1313) loss: 0.8605 (0.8625) time: 0.1404 data: 0.0676 max mem: 8299 +Train: [92] [2400/6250] eta: 0:08:42 lr: 0.000002 grad: 0.1250 (0.1313) loss: 0.8560 (0.8624) time: 0.0899 data: 0.0011 max mem: 8299 +Train: [92] [2500/6250] eta: 0:08:28 lr: 0.000002 grad: 0.1207 (0.1312) loss: 0.8576 (0.8622) time: 0.1496 data: 0.0684 max mem: 8299 +Train: [92] [2600/6250] eta: 0:08:12 lr: 0.000002 grad: 0.1190 (0.1312) loss: 0.8552 (0.8620) time: 0.1173 data: 0.0389 max mem: 8299 +Train: [92] [2700/6250] eta: 0:07:58 lr: 0.000002 grad: 0.1294 (0.1311) loss: 0.8573 (0.8618) time: 0.1181 data: 0.0445 max mem: 8299 +Train: [92] [2800/6250] eta: 0:07:43 lr: 0.000002 grad: 0.1231 (0.1309) loss: 0.8630 (0.8617) time: 0.1336 data: 0.0629 max mem: 8299 +Train: [92] [2900/6250] eta: 0:07:30 lr: 0.000002 grad: 0.1267 (0.1309) loss: 0.8479 (0.8616) time: 0.1458 data: 0.0679 max mem: 8299 +Train: [92] [3000/6250] eta: 0:07:16 lr: 0.000002 grad: 0.1328 (0.1308) loss: 0.8581 (0.8615) time: 0.1481 data: 0.0805 max mem: 8299 +Train: [92] [3100/6250] eta: 0:07:02 lr: 0.000002 grad: 0.1101 (0.1307) loss: 0.8627 (0.8614) time: 0.1209 data: 0.0478 max mem: 8299 +Train: [92] [3200/6250] eta: 0:06:49 lr: 0.000002 grad: 0.1194 (0.1306) loss: 0.8583 (0.8613) time: 0.1214 data: 0.0214 max mem: 8299 +Train: [92] [3300/6250] eta: 0:06:36 lr: 0.000002 grad: 0.1303 (0.1305) loss: 0.8596 (0.8613) time: 0.1378 data: 0.0577 max mem: 8299 +Train: [92] [3400/6250] eta: 0:06:23 lr: 0.000002 grad: 0.1322 (0.1305) loss: 0.8537 (0.8612) time: 0.1295 data: 0.0464 max mem: 8299 +Train: [92] [3500/6250] eta: 0:06:10 lr: 0.000002 grad: 0.1264 (0.1303) loss: 0.8662 (0.8612) time: 0.1636 data: 0.0915 max mem: 8299 +Train: [92] [3600/6250] eta: 0:05:56 lr: 0.000002 grad: 0.1270 (0.1304) loss: 0.8584 (0.8611) time: 0.1339 data: 0.0604 max mem: 8299 +Train: [92] [3700/6250] eta: 0:05:43 lr: 0.000002 grad: 0.1164 (0.1304) loss: 0.8622 (0.8610) time: 0.1280 data: 0.0474 max mem: 8299 +Train: [92] [3800/6250] eta: 0:05:29 lr: 0.000002 grad: 0.1366 (0.1305) loss: 0.8561 (0.8610) time: 0.1398 data: 0.0671 max mem: 8299 +Train: [92] [3900/6250] eta: 0:05:16 lr: 0.000002 grad: 0.1183 (0.1305) loss: 0.8650 (0.8609) time: 0.1196 data: 0.0508 max mem: 8299 +Train: [92] [4000/6250] eta: 0:05:02 lr: 0.000002 grad: 0.1211 (0.1306) loss: 0.8602 (0.8609) time: 0.1272 data: 0.0603 max mem: 8299 +Train: [92] [4100/6250] eta: 0:04:50 lr: 0.000002 grad: 0.1183 (0.1304) loss: 0.8608 (0.8609) time: 0.1537 data: 0.0778 max mem: 8299 +Train: [92] [4200/6250] eta: 0:04:36 lr: 0.000002 grad: 0.1278 (0.1303) loss: 0.8655 (0.8610) time: 0.1232 data: 0.0428 max mem: 8299 +Train: [92] [4300/6250] eta: 0:04:23 lr: 0.000002 grad: 0.1163 (0.1302) loss: 0.8679 (0.8611) time: 0.1354 data: 0.0528 max mem: 8299 +Train: [92] [4400/6250] eta: 0:04:10 lr: 0.000002 grad: 0.1215 (0.1300) loss: 0.8654 (0.8612) time: 0.1411 data: 0.0667 max mem: 8299 +Train: [92] [4500/6250] eta: 0:03:57 lr: 0.000002 grad: 0.1199 (0.1299) loss: 0.8673 (0.8612) time: 0.1679 data: 0.0834 max mem: 8299 +Train: [92] [4600/6250] eta: 0:03:42 lr: 0.000002 grad: 0.1174 (0.1299) loss: 0.8703 (0.8613) time: 0.1263 data: 0.0487 max mem: 8299 +Train: [92] [4700/6250] eta: 0:03:29 lr: 0.000002 grad: 0.1235 (0.1298) loss: 0.8651 (0.8614) time: 0.1467 data: 0.0726 max mem: 8299 +Train: [92] [4800/6250] eta: 0:03:15 lr: 0.000002 grad: 0.1229 (0.1298) loss: 0.8608 (0.8614) time: 0.1057 data: 0.0164 max mem: 8299 +Train: [92] [4900/6250] eta: 0:03:02 lr: 0.000002 grad: 0.1213 (0.1298) loss: 0.8609 (0.8614) time: 0.1218 data: 0.0367 max mem: 8299 +Train: [92] [5000/6250] eta: 0:02:48 lr: 0.000002 grad: 0.1230 (0.1298) loss: 0.8606 (0.8614) time: 0.1539 data: 0.0719 max mem: 8299 +Train: [92] [5100/6250] eta: 0:02:35 lr: 0.000002 grad: 0.1169 (0.1297) loss: 0.8651 (0.8614) time: 0.1039 data: 0.0239 max mem: 8299 +Train: [92] [5200/6250] eta: 0:02:21 lr: 0.000002 grad: 0.1226 (0.1297) loss: 0.8566 (0.8614) time: 0.0889 data: 0.0298 max mem: 8299 +Train: [92] [5300/6250] eta: 0:02:07 lr: 0.000002 grad: 0.1294 (0.1299) loss: 0.8563 (0.8614) time: 0.1696 data: 0.1028 max mem: 8299 +Train: [92] [5400/6250] eta: 0:01:54 lr: 0.000002 grad: 0.1257 (0.1299) loss: 0.8617 (0.8614) time: 0.1407 data: 0.0525 max mem: 8299 +Train: [92] [5500/6250] eta: 0:01:41 lr: 0.000002 grad: 0.1202 (0.1299) loss: 0.8629 (0.8614) time: 0.1276 data: 0.0494 max mem: 8299 +Train: [92] [5600/6250] eta: 0:01:27 lr: 0.000002 grad: 0.1203 (0.1299) loss: 0.8644 (0.8614) time: 0.1195 data: 0.0425 max mem: 8299 +Train: [92] [5700/6250] eta: 0:01:13 lr: 0.000002 grad: 0.1209 (0.1300) loss: 0.8601 (0.8614) time: 0.1363 data: 0.0534 max mem: 8299 +Train: [92] [5800/6250] eta: 0:01:00 lr: 0.000002 grad: 0.1252 (0.1299) loss: 0.8633 (0.8615) time: 0.1114 data: 0.0215 max mem: 8299 +Train: [92] [5900/6250] eta: 0:00:47 lr: 0.000002 grad: 0.1361 (0.1300) loss: 0.8604 (0.8615) time: 0.1192 data: 0.0421 max mem: 8299 +Train: [92] [6000/6250] eta: 0:00:33 lr: 0.000002 grad: 0.1304 (0.1299) loss: 0.8569 (0.8615) time: 0.1236 data: 0.0459 max mem: 8299 +Train: [92] [6100/6250] eta: 0:00:20 lr: 0.000002 grad: 0.1238 (0.1299) loss: 0.8604 (0.8615) time: 0.1374 data: 0.0586 max mem: 8299 +Train: [92] [6200/6250] eta: 0:00:06 lr: 0.000002 grad: 0.1262 (0.1299) loss: 0.8672 (0.8616) time: 0.1129 data: 0.0322 max mem: 8299 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1183 (0.1298) loss: 0.8644 (0.8616) time: 0.1496 data: 0.0789 max mem: 8299 +Train: [92] Total time: 0:14:06 (0.1355 s / it) +Averaged stats: lr: 0.000002 grad: 0.1183 (0.1298) loss: 0.8644 (0.8616) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:05:47 loss: 0.8712 (0.8712) time: 5.5976 data: 5.5686 max mem: 8299 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8618 (0.8655) time: 0.1007 data: 0.0765 max mem: 8299 +Eval (hcp-train-subset): [92] Total time: 0:00:12 (0.2024 s / it) +Averaged stats (hcp-train-subset): loss: 0.8618 (0.8655) +Eval (hcp-val): [92] [ 0/62] eta: 0:03:25 loss: 0.8694 (0.8694) time: 3.3101 data: 3.2427 max mem: 8299 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8724 (0.8747) time: 0.1228 data: 0.0980 max mem: 8299 +Eval (hcp-val): [92] Total time: 0:00:12 (0.1949 s / it) +Averaged stats (hcp-val): loss: 0.8724 (0.8747) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 7:53:55 lr: 0.000002 grad: 0.2062 (0.2062) loss: 0.8331 (0.8331) time: 4.5497 data: 4.3355 max mem: 8299 +Train: [93] [ 100/6250] eta: 0:18:51 lr: 0.000002 grad: 0.1295 (0.1480) loss: 0.8787 (0.8760) time: 0.1492 data: 0.0557 max mem: 8299 +Train: [93] [ 200/6250] eta: 0:15:46 lr: 0.000002 grad: 0.1513 (0.1488) loss: 0.8655 (0.8719) time: 0.1204 data: 0.0291 max mem: 8299 +Train: [93] [ 300/6250] eta: 0:14:51 lr: 0.000002 grad: 0.1616 (0.1543) loss: 0.8676 (0.8671) time: 0.1369 data: 0.0448 max mem: 8299 +Train: [93] [ 400/6250] eta: 0:14:19 lr: 0.000002 grad: 0.1439 (0.1538) loss: 0.8659 (0.8649) time: 0.1563 data: 0.0652 max mem: 8299 +Train: [93] [ 500/6250] eta: 0:13:39 lr: 0.000002 grad: 0.1439 (0.1523) loss: 0.8515 (0.8641) time: 0.1371 data: 0.0553 max mem: 8299 +Train: [93] [ 600/6250] eta: 0:13:13 lr: 0.000002 grad: 0.1401 (0.1506) loss: 0.8620 (0.8633) time: 0.1510 data: 0.0602 max mem: 8299 +Train: [93] [ 700/6250] eta: 0:12:52 lr: 0.000002 grad: 0.1214 (0.1480) loss: 0.8663 (0.8633) time: 0.1601 data: 0.0719 max mem: 8299 +Train: [93] [ 800/6250] eta: 0:12:44 lr: 0.000002 grad: 0.1391 (0.1468) loss: 0.8607 (0.8634) time: 0.1589 data: 0.0959 max mem: 8299 +Train: [93] [ 900/6250] eta: 0:12:35 lr: 0.000002 grad: 0.1274 (0.1457) loss: 0.8684 (0.8634) time: 0.1332 data: 0.0454 max mem: 8299 +Train: [93] [1000/6250] eta: 0:12:15 lr: 0.000002 grad: 0.1453 (0.1449) loss: 0.8542 (0.8631) time: 0.1267 data: 0.0451 max mem: 8299 +Train: [93] [1100/6250] eta: 0:11:59 lr: 0.000002 grad: 0.1375 (0.1438) loss: 0.8600 (0.8630) time: 0.1346 data: 0.0559 max mem: 8299 +Train: [93] [1200/6250] eta: 0:11:44 lr: 0.000002 grad: 0.1361 (0.1430) loss: 0.8571 (0.8629) time: 0.1113 data: 0.0364 max mem: 8299 +Train: [93] [1300/6250] eta: 0:11:27 lr: 0.000002 grad: 0.1316 (0.1421) loss: 0.8573 (0.8629) time: 0.1245 data: 0.0514 max mem: 8299 +Train: [93] [1400/6250] eta: 0:11:13 lr: 0.000002 grad: 0.1379 (0.1414) loss: 0.8577 (0.8629) time: 0.1365 data: 0.0586 max mem: 8299 +Train: [93] [1500/6250] eta: 0:10:57 lr: 0.000002 grad: 0.1230 (0.1408) loss: 0.8601 (0.8628) time: 0.1262 data: 0.0531 max mem: 8299 +Train: [93] [1600/6250] eta: 0:10:40 lr: 0.000002 grad: 0.1322 (0.1403) loss: 0.8555 (0.8626) time: 0.1349 data: 0.0677 max mem: 8299 +Train: [93] [1700/6250] eta: 0:10:23 lr: 0.000002 grad: 0.1183 (0.1394) loss: 0.8579 (0.8627) time: 0.1118 data: 0.0342 max mem: 8299 +Train: [93] [1800/6250] eta: 0:10:07 lr: 0.000002 grad: 0.1252 (0.1390) loss: 0.8623 (0.8626) time: 0.0957 data: 0.0137 max mem: 8299 +Train: [93] [1900/6250] eta: 0:09:57 lr: 0.000002 grad: 0.1223 (0.1387) loss: 0.8575 (0.8625) time: 0.2293 data: 0.1531 max mem: 8299 +Train: [93] [2000/6250] eta: 0:09:40 lr: 0.000002 grad: 0.1325 (0.1383) loss: 0.8561 (0.8623) time: 0.1326 data: 0.0497 max mem: 8299 +Train: [93] [2100/6250] eta: 0:09:24 lr: 0.000002 grad: 0.1339 (0.1381) loss: 0.8592 (0.8622) time: 0.1154 data: 0.0346 max mem: 8299 +Train: [93] [2200/6250] eta: 0:09:09 lr: 0.000002 grad: 0.1258 (0.1378) loss: 0.8592 (0.8621) time: 0.1387 data: 0.0631 max mem: 8299 +Train: [93] [2300/6250] eta: 0:08:55 lr: 0.000001 grad: 0.1252 (0.1375) loss: 0.8597 (0.8621) time: 0.1410 data: 0.0624 max mem: 8299 +Train: [93] [2400/6250] eta: 0:08:42 lr: 0.000001 grad: 0.1241 (0.1373) loss: 0.8639 (0.8621) time: 0.1469 data: 0.0750 max mem: 8299 +Train: [93] [2500/6250] eta: 0:08:28 lr: 0.000001 grad: 0.1205 (0.1369) loss: 0.8614 (0.8620) time: 0.1293 data: 0.0593 max mem: 8299 +Train: [93] [2600/6250] eta: 0:08:14 lr: 0.000001 grad: 0.1259 (0.1365) loss: 0.8637 (0.8620) time: 0.1397 data: 0.0722 max mem: 8299 +Train: [93] [2700/6250] eta: 0:08:00 lr: 0.000001 grad: 0.1278 (0.1362) loss: 0.8596 (0.8620) time: 0.1384 data: 0.0622 max mem: 8299 +Train: [93] [2800/6250] eta: 0:07:46 lr: 0.000001 grad: 0.1196 (0.1358) loss: 0.8633 (0.8621) time: 0.1210 data: 0.0429 max mem: 8299 +Train: [93] [2900/6250] eta: 0:07:32 lr: 0.000001 grad: 0.1164 (0.1354) loss: 0.8617 (0.8622) time: 0.1199 data: 0.0505 max mem: 8299 +Train: [93] [3000/6250] eta: 0:07:18 lr: 0.000001 grad: 0.1195 (0.1350) loss: 0.8579 (0.8623) time: 0.1339 data: 0.0595 max mem: 8299 +Train: [93] [3100/6250] eta: 0:07:04 lr: 0.000001 grad: 0.1299 (0.1347) loss: 0.8639 (0.8623) time: 0.1134 data: 0.0439 max mem: 8299 +Train: [93] [3200/6250] eta: 0:06:49 lr: 0.000001 grad: 0.1158 (0.1342) loss: 0.8659 (0.8624) time: 0.1263 data: 0.0465 max mem: 8299 +Train: [93] [3300/6250] eta: 0:06:35 lr: 0.000001 grad: 0.1188 (0.1340) loss: 0.8602 (0.8624) time: 0.1070 data: 0.0301 max mem: 8299 +Train: [93] [3400/6250] eta: 0:06:21 lr: 0.000001 grad: 0.1178 (0.1338) loss: 0.8675 (0.8625) time: 0.1354 data: 0.0579 max mem: 8299 +Train: [93] [3500/6250] eta: 0:06:08 lr: 0.000001 grad: 0.1314 (0.1337) loss: 0.8627 (0.8625) time: 0.1372 data: 0.0649 max mem: 8299 +Train: [93] [3600/6250] eta: 0:05:55 lr: 0.000001 grad: 0.1269 (0.1336) loss: 0.8630 (0.8625) time: 0.1400 data: 0.0727 max mem: 8299 +Train: [93] [3700/6250] eta: 0:05:40 lr: 0.000001 grad: 0.1282 (0.1335) loss: 0.8560 (0.8624) time: 0.1297 data: 0.0564 max mem: 8299 +Train: [93] [3800/6250] eta: 0:05:26 lr: 0.000001 grad: 0.1318 (0.1334) loss: 0.8648 (0.8624) time: 0.1297 data: 0.0539 max mem: 8299 +Train: [93] [3900/6250] eta: 0:05:13 lr: 0.000001 grad: 0.1203 (0.1332) loss: 0.8651 (0.8624) time: 0.1219 data: 0.0434 max mem: 8299 +Train: [93] [4000/6250] eta: 0:05:01 lr: 0.000001 grad: 0.1241 (0.1332) loss: 0.8606 (0.8624) time: 0.1494 data: 0.0610 max mem: 8299 +Train: [93] [4100/6250] eta: 0:04:48 lr: 0.000001 grad: 0.1143 (0.1331) loss: 0.8635 (0.8624) time: 0.1596 data: 0.0804 max mem: 8299 +Train: [93] [4200/6250] eta: 0:04:34 lr: 0.000001 grad: 0.1230 (0.1330) loss: 0.8640 (0.8625) time: 0.1345 data: 0.0507 max mem: 8299 +Train: [93] [4300/6250] eta: 0:04:21 lr: 0.000001 grad: 0.1241 (0.1329) loss: 0.8684 (0.8625) time: 0.1205 data: 0.0448 max mem: 8299 +Train: [93] [4400/6250] eta: 0:04:08 lr: 0.000001 grad: 0.1288 (0.1328) loss: 0.8657 (0.8625) time: 0.1472 data: 0.0648 max mem: 8299 +Train: [93] [4500/6250] eta: 0:03:55 lr: 0.000001 grad: 0.1211 (0.1327) loss: 0.8635 (0.8625) time: 0.1459 data: 0.0603 max mem: 8299 +Train: [93] [4600/6250] eta: 0:03:42 lr: 0.000001 grad: 0.1260 (0.1327) loss: 0.8627 (0.8624) time: 0.1213 data: 0.0452 max mem: 8299 +Train: [93] [4700/6250] eta: 0:03:28 lr: 0.000001 grad: 0.1270 (0.1327) loss: 0.8639 (0.8624) time: 0.1143 data: 0.0370 max mem: 8299 +Train: [93] [4800/6250] eta: 0:03:14 lr: 0.000001 grad: 0.1204 (0.1325) loss: 0.8695 (0.8625) time: 0.1318 data: 0.0381 max mem: 8299 +Train: [93] [4900/6250] eta: 0:03:01 lr: 0.000001 grad: 0.1329 (0.1324) loss: 0.8598 (0.8625) time: 0.1526 data: 0.0753 max mem: 8299 +Train: [93] [5000/6250] eta: 0:02:47 lr: 0.000001 grad: 0.1232 (0.1321) loss: 0.8680 (0.8626) time: 0.1428 data: 0.0613 max mem: 8299 +Train: [93] [5100/6250] eta: 0:02:34 lr: 0.000001 grad: 0.1231 (0.1319) loss: 0.8618 (0.8626) time: 0.1263 data: 0.0485 max mem: 8299 +Train: [93] [5200/6250] eta: 0:02:20 lr: 0.000001 grad: 0.1154 (0.1318) loss: 0.8591 (0.8626) time: 0.1308 data: 0.0596 max mem: 8299 +Train: [93] [5300/6250] eta: 0:02:07 lr: 0.000001 grad: 0.1192 (0.1317) loss: 0.8714 (0.8627) time: 0.1392 data: 0.0718 max mem: 8299 +Train: [93] [5400/6250] eta: 0:01:53 lr: 0.000001 grad: 0.1260 (0.1317) loss: 0.8625 (0.8627) time: 0.1188 data: 0.0496 max mem: 8299 +Train: [93] [5500/6250] eta: 0:01:40 lr: 0.000001 grad: 0.1249 (0.1317) loss: 0.8629 (0.8626) time: 0.1338 data: 0.0559 max mem: 8299 +Train: [93] [5600/6250] eta: 0:01:26 lr: 0.000001 grad: 0.1287 (0.1317) loss: 0.8612 (0.8626) time: 0.1167 data: 0.0419 max mem: 8299 +Train: [93] [5700/6250] eta: 0:01:13 lr: 0.000001 grad: 0.1254 (0.1317) loss: 0.8649 (0.8626) time: 0.1132 data: 0.0355 max mem: 8299 +Train: [93] [5800/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1299 (0.1317) loss: 0.8604 (0.8626) time: 0.1316 data: 0.0507 max mem: 8299 +Train: [93] [5900/6250] eta: 0:00:46 lr: 0.000001 grad: 0.1247 (0.1319) loss: 0.8642 (0.8625) time: 0.1347 data: 0.0587 max mem: 8299 +Train: [93] [6000/6250] eta: 0:00:33 lr: 0.000001 grad: 0.1238 (0.1320) loss: 0.8644 (0.8625) time: 0.1497 data: 0.0776 max mem: 8299 +Train: [93] [6100/6250] eta: 0:00:19 lr: 0.000001 grad: 0.1322 (0.1320) loss: 0.8625 (0.8625) time: 0.1275 data: 0.0546 max mem: 8299 +Train: [93] [6200/6250] eta: 0:00:06 lr: 0.000001 grad: 0.1217 (0.1320) loss: 0.8623 (0.8625) time: 0.1231 data: 0.0499 max mem: 8299 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1195 (0.1320) loss: 0.8646 (0.8625) time: 0.1322 data: 0.0554 max mem: 8299 +Train: [93] Total time: 0:13:56 (0.1339 s / it) +Averaged stats: lr: 0.000001 grad: 0.1195 (0.1320) loss: 0.8646 (0.8625) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:06:06 loss: 0.8681 (0.8681) time: 5.9091 data: 5.8792 max mem: 8299 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8596 (0.8640) time: 0.1436 data: 0.1189 max mem: 8299 +Eval (hcp-train-subset): [93] Total time: 0:00:13 (0.2249 s / it) +Averaged stats (hcp-train-subset): loss: 0.8596 (0.8640) +Eval (hcp-val): [93] [ 0/62] eta: 0:05:15 loss: 0.8711 (0.8711) time: 5.0930 data: 5.0634 max mem: 8299 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8730 (0.8741) time: 0.1030 data: 0.0786 max mem: 8299 +Eval (hcp-val): [93] Total time: 0:00:13 (0.2160 s / it) +Averaged stats (hcp-val): loss: 0.8730 (0.8741) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 10:58:11 lr: 0.000001 grad: 0.2044 (0.2044) loss: 0.8587 (0.8587) time: 6.3186 data: 6.2295 max mem: 8299 +Train: [94] [ 100/6250] eta: 0:18:24 lr: 0.000001 grad: 0.1655 (0.1544) loss: 0.8661 (0.8597) time: 0.1262 data: 0.0378 max mem: 8299 +Train: [94] [ 200/6250] eta: 0:15:47 lr: 0.000001 grad: 0.1520 (0.1644) loss: 0.8431 (0.8528) time: 0.1321 data: 0.0442 max mem: 8299 +Train: [94] [ 300/6250] eta: 0:14:37 lr: 0.000001 grad: 0.1274 (0.1583) loss: 0.8611 (0.8528) time: 0.1226 data: 0.0250 max mem: 8299 +Train: [94] [ 400/6250] eta: 0:14:05 lr: 0.000001 grad: 0.1367 (0.1565) loss: 0.8539 (0.8531) time: 0.1512 data: 0.0643 max mem: 8299 +Train: [94] [ 500/6250] eta: 0:13:43 lr: 0.000001 grad: 0.1443 (0.1570) loss: 0.8615 (0.8538) time: 0.1401 data: 0.0531 max mem: 8299 +Train: [94] [ 600/6250] eta: 0:13:21 lr: 0.000001 grad: 0.1459 (0.1568) loss: 0.8580 (0.8545) time: 0.1332 data: 0.0489 max mem: 8299 +Train: [94] [ 700/6250] eta: 0:12:57 lr: 0.000001 grad: 0.1367 (0.1564) loss: 0.8595 (0.8548) time: 0.1333 data: 0.0562 max mem: 8299 +Train: [94] [ 800/6250] eta: 0:12:39 lr: 0.000001 grad: 0.1507 (0.1550) loss: 0.8597 (0.8555) time: 0.1489 data: 0.0719 max mem: 8299 +Train: [94] [ 900/6250] eta: 0:12:29 lr: 0.000001 grad: 0.1237 (0.1529) loss: 0.8715 (0.8563) time: 0.1370 data: 0.0526 max mem: 8299 +Train: [94] [1000/6250] eta: 0:12:25 lr: 0.000001 grad: 0.1284 (0.1513) loss: 0.8621 (0.8567) time: 0.1582 data: 0.0832 max mem: 8299 +Train: [94] [1100/6250] eta: 0:12:10 lr: 0.000001 grad: 0.1313 (0.1499) loss: 0.8568 (0.8570) time: 0.1314 data: 0.0517 max mem: 8299 +Train: [94] [1200/6250] eta: 0:11:49 lr: 0.000001 grad: 0.1261 (0.1485) loss: 0.8525 (0.8570) time: 0.1054 data: 0.0176 max mem: 8299 +Train: [94] [1300/6250] eta: 0:11:33 lr: 0.000001 grad: 0.1325 (0.1477) loss: 0.8554 (0.8571) time: 0.1439 data: 0.0701 max mem: 8299 +Train: [94] [1400/6250] eta: 0:11:18 lr: 0.000001 grad: 0.1210 (0.1465) loss: 0.8599 (0.8574) time: 0.1300 data: 0.0499 max mem: 8299 +Train: [94] [1500/6250] eta: 0:11:06 lr: 0.000001 grad: 0.1246 (0.1451) loss: 0.8668 (0.8578) time: 0.1062 data: 0.0229 max mem: 8299 +Train: [94] [1600/6250] eta: 0:10:52 lr: 0.000001 grad: 0.1225 (0.1438) loss: 0.8697 (0.8581) time: 0.1086 data: 0.0147 max mem: 8299 +Train: [94] [1700/6250] eta: 0:10:35 lr: 0.000001 grad: 0.1258 (0.1429) loss: 0.8618 (0.8584) time: 0.1306 data: 0.0555 max mem: 8299 +Train: [94] [1800/6250] eta: 0:10:20 lr: 0.000001 grad: 0.1244 (0.1422) loss: 0.8688 (0.8587) time: 0.1436 data: 0.0647 max mem: 8299 +Train: [94] [1900/6250] eta: 0:10:06 lr: 0.000001 grad: 0.1263 (0.1414) loss: 0.8620 (0.8588) time: 0.1368 data: 0.0514 max mem: 8299 +Train: [94] [2000/6250] eta: 0:09:51 lr: 0.000001 grad: 0.1328 (0.1409) loss: 0.8627 (0.8589) time: 0.1395 data: 0.0642 max mem: 8299 +Train: [94] [2100/6250] eta: 0:09:39 lr: 0.000001 grad: 0.1297 (0.1406) loss: 0.8629 (0.8590) time: 0.1772 data: 0.1043 max mem: 8299 +Train: [94] [2200/6250] eta: 0:09:24 lr: 0.000001 grad: 0.1307 (0.1403) loss: 0.8673 (0.8591) time: 0.0884 data: 0.0123 max mem: 8299 +Train: [94] [2300/6250] eta: 0:09:07 lr: 0.000001 grad: 0.1234 (0.1399) loss: 0.8657 (0.8591) time: 0.1263 data: 0.0538 max mem: 8299 +Train: [94] [2400/6250] eta: 0:08:52 lr: 0.000001 grad: 0.1183 (0.1393) loss: 0.8615 (0.8592) time: 0.1006 data: 0.0162 max mem: 8299 +Train: [94] [2500/6250] eta: 0:08:40 lr: 0.000001 grad: 0.1231 (0.1388) loss: 0.8649 (0.8594) time: 0.1697 data: 0.0893 max mem: 8299 +Train: [94] [2600/6250] eta: 0:08:25 lr: 0.000001 grad: 0.1249 (0.1385) loss: 0.8552 (0.8594) time: 0.1284 data: 0.0515 max mem: 8299 +Train: [94] [2700/6250] eta: 0:08:11 lr: 0.000001 grad: 0.1199 (0.1381) loss: 0.8674 (0.8595) time: 0.1548 data: 0.0807 max mem: 8299 +Train: [94] [2800/6250] eta: 0:07:55 lr: 0.000001 grad: 0.1186 (0.1377) loss: 0.8649 (0.8596) time: 0.1260 data: 0.0525 max mem: 8299 +Train: [94] [2900/6250] eta: 0:07:40 lr: 0.000001 grad: 0.1311 (0.1375) loss: 0.8636 (0.8597) time: 0.1302 data: 0.0425 max mem: 8299 +Train: [94] [3000/6250] eta: 0:07:29 lr: 0.000001 grad: 0.1149 (0.1371) loss: 0.8642 (0.8597) time: 0.1875 data: 0.1213 max mem: 8299 +Train: [94] [3100/6250] eta: 0:07:14 lr: 0.000001 grad: 0.1297 (0.1368) loss: 0.8617 (0.8598) time: 0.1344 data: 0.0480 max mem: 8299 +Train: [94] [3200/6250] eta: 0:07:01 lr: 0.000001 grad: 0.1224 (0.1366) loss: 0.8611 (0.8599) time: 0.1278 data: 0.0511 max mem: 8299 +Train: [94] [3300/6250] eta: 0:06:47 lr: 0.000001 grad: 0.1197 (0.1362) loss: 0.8587 (0.8600) time: 0.0909 data: 0.0002 max mem: 8299 +Train: [94] [3400/6250] eta: 0:06:33 lr: 0.000001 grad: 0.1217 (0.1359) loss: 0.8689 (0.8602) time: 0.1326 data: 0.0539 max mem: 8299 +Train: [94] [3500/6250] eta: 0:06:20 lr: 0.000001 grad: 0.1183 (0.1356) loss: 0.8661 (0.8603) time: 0.1346 data: 0.0543 max mem: 8299 +Train: [94] [3600/6250] eta: 0:06:06 lr: 0.000001 grad: 0.1167 (0.1353) loss: 0.8670 (0.8605) time: 0.1171 data: 0.0422 max mem: 8299 +Train: [94] [3700/6250] eta: 0:05:52 lr: 0.000001 grad: 0.1196 (0.1349) loss: 0.8646 (0.8605) time: 0.1068 data: 0.0170 max mem: 8299 +Train: [94] [3800/6250] eta: 0:05:38 lr: 0.000001 grad: 0.1102 (0.1346) loss: 0.8698 (0.8606) time: 0.1279 data: 0.0423 max mem: 8299 +Train: [94] [3900/6250] eta: 0:05:24 lr: 0.000001 grad: 0.1232 (0.1343) loss: 0.8665 (0.8607) time: 0.1502 data: 0.0838 max mem: 8299 +Train: [94] [4000/6250] eta: 0:05:11 lr: 0.000001 grad: 0.1252 (0.1341) loss: 0.8680 (0.8608) time: 0.1714 data: 0.0850 max mem: 8299 +Train: [94] [4100/6250] eta: 0:04:58 lr: 0.000001 grad: 0.1255 (0.1339) loss: 0.8608 (0.8609) time: 0.1335 data: 0.0533 max mem: 8299 +Train: [94] [4200/6250] eta: 0:04:44 lr: 0.000001 grad: 0.1269 (0.1339) loss: 0.8605 (0.8609) time: 0.1363 data: 0.0603 max mem: 8299 +Train: [94] [4300/6250] eta: 0:04:30 lr: 0.000001 grad: 0.1303 (0.1338) loss: 0.8610 (0.8609) time: 0.1370 data: 0.0637 max mem: 8299 +Train: [94] [4400/6250] eta: 0:04:16 lr: 0.000001 grad: 0.1204 (0.1336) loss: 0.8651 (0.8610) time: 0.1353 data: 0.0479 max mem: 8299 +Train: [94] [4500/6250] eta: 0:04:02 lr: 0.000001 grad: 0.1191 (0.1334) loss: 0.8641 (0.8610) time: 0.1354 data: 0.0513 max mem: 8299 +Train: [94] [4600/6250] eta: 0:03:48 lr: 0.000001 grad: 0.1275 (0.1334) loss: 0.8618 (0.8610) time: 0.1349 data: 0.0548 max mem: 8299 +Train: [94] [4700/6250] eta: 0:03:34 lr: 0.000001 grad: 0.1264 (0.1333) loss: 0.8584 (0.8610) time: 0.1329 data: 0.0635 max mem: 8299 +Train: [94] [4800/6250] eta: 0:03:20 lr: 0.000001 grad: 0.1229 (0.1333) loss: 0.8618 (0.8610) time: 0.1454 data: 0.0668 max mem: 8299 +Train: [94] [4900/6250] eta: 0:03:06 lr: 0.000001 grad: 0.1177 (0.1332) loss: 0.8624 (0.8609) time: 0.1186 data: 0.0480 max mem: 8299 +Train: [94] [5000/6250] eta: 0:02:52 lr: 0.000001 grad: 0.1313 (0.1332) loss: 0.8620 (0.8609) time: 0.1421 data: 0.0579 max mem: 8299 +Train: [94] [5100/6250] eta: 0:02:38 lr: 0.000001 grad: 0.1208 (0.1332) loss: 0.8613 (0.8609) time: 0.1336 data: 0.0543 max mem: 8299 +Train: [94] [5200/6250] eta: 0:02:24 lr: 0.000001 grad: 0.1221 (0.1332) loss: 0.8621 (0.8609) time: 0.1327 data: 0.0630 max mem: 8299 +Train: [94] [5300/6250] eta: 0:02:10 lr: 0.000001 grad: 0.1273 (0.1332) loss: 0.8599 (0.8609) time: 0.1356 data: 0.0560 max mem: 8299 +Train: [94] [5400/6250] eta: 0:01:56 lr: 0.000001 grad: 0.1247 (0.1332) loss: 0.8629 (0.8609) time: 0.1143 data: 0.0368 max mem: 8299 +Train: [94] [5500/6250] eta: 0:01:42 lr: 0.000001 grad: 0.1185 (0.1331) loss: 0.8678 (0.8610) time: 0.1389 data: 0.0718 max mem: 8299 +Train: [94] [5600/6250] eta: 0:01:28 lr: 0.000001 grad: 0.1311 (0.1330) loss: 0.8649 (0.8610) time: 0.1263 data: 0.0595 max mem: 8299 +Train: [94] [5700/6250] eta: 0:01:14 lr: 0.000001 grad: 0.1163 (0.1330) loss: 0.8660 (0.8610) time: 0.1347 data: 0.0671 max mem: 8299 +Train: [94] [5800/6250] eta: 0:01:01 lr: 0.000001 grad: 0.1362 (0.1330) loss: 0.8594 (0.8610) time: 0.1112 data: 0.0325 max mem: 8299 +Train: [94] [5900/6250] eta: 0:00:47 lr: 0.000001 grad: 0.1293 (0.1329) loss: 0.8619 (0.8611) time: 0.1247 data: 0.0455 max mem: 8299 +Train: [94] [6000/6250] eta: 0:00:33 lr: 0.000001 grad: 0.1305 (0.1328) loss: 0.8614 (0.8611) time: 0.1216 data: 0.0468 max mem: 8299 +Train: [94] [6100/6250] eta: 0:00:20 lr: 0.000001 grad: 0.1336 (0.1328) loss: 0.8636 (0.8611) time: 0.1183 data: 0.0391 max mem: 8299 +Train: [94] [6200/6250] eta: 0:00:06 lr: 0.000001 grad: 0.1179 (0.1327) loss: 0.8663 (0.8611) time: 0.1158 data: 0.0297 max mem: 8299 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1331 (0.1328) loss: 0.8679 (0.8611) time: 0.1335 data: 0.0589 max mem: 8299 +Train: [94] Total time: 0:14:11 (0.1362 s / it) +Averaged stats: lr: 0.000001 grad: 0.1331 (0.1328) loss: 0.8679 (0.8611) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:04:51 loss: 0.8686 (0.8686) time: 4.7048 data: 4.6742 max mem: 8299 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8616 (0.8643) time: 0.1202 data: 0.0959 max mem: 8299 +Eval (hcp-train-subset): [94] Total time: 0:00:13 (0.2130 s / it) +Averaged stats (hcp-train-subset): loss: 0.8616 (0.8643) +Making plots (hcp-train-subset): example=2 +Eval (hcp-val): [94] [ 0/62] eta: 0:04:45 loss: 0.8727 (0.8727) time: 4.6124 data: 4.5823 max mem: 8299 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8711 (0.8745) time: 0.0998 data: 0.0743 max mem: 8299 +Eval (hcp-val): [94] Total time: 0:00:12 (0.1954 s / it) +Averaged stats (hcp-val): loss: 0.8711 (0.8745) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 8:06:10 lr: 0.000001 grad: 0.0797 (0.0797) loss: 0.8865 (0.8865) time: 4.6672 data: 4.4413 max mem: 8299 +Train: [95] [ 100/6250] eta: 0:18:50 lr: 0.000001 grad: 0.0966 (0.1505) loss: 0.8839 (0.8758) time: 0.1284 data: 0.0223 max mem: 8299 +Train: [95] [ 200/6250] eta: 0:16:29 lr: 0.000001 grad: 0.1559 (0.1503) loss: 0.8610 (0.8714) time: 0.1411 data: 0.0392 max mem: 8299 +Train: [95] [ 300/6250] eta: 0:15:19 lr: 0.000001 grad: 0.1678 (0.1541) loss: 0.8546 (0.8676) time: 0.0983 data: 0.0031 max mem: 8299 +Train: [95] [ 400/6250] eta: 0:14:39 lr: 0.000001 grad: 0.1474 (0.1541) loss: 0.8584 (0.8652) time: 0.1163 data: 0.0203 max mem: 8299 +Train: [95] [ 500/6250] eta: 0:14:10 lr: 0.000001 grad: 0.1239 (0.1542) loss: 0.8582 (0.8630) time: 0.1437 data: 0.0529 max mem: 8299 +Train: [95] [ 600/6250] eta: 0:13:43 lr: 0.000001 grad: 0.1311 (0.1525) loss: 0.8614 (0.8621) time: 0.1302 data: 0.0419 max mem: 8299 +Train: [95] [ 700/6250] eta: 0:13:23 lr: 0.000001 grad: 0.1502 (0.1511) loss: 0.8615 (0.8615) time: 0.1492 data: 0.0591 max mem: 8299 +Train: [95] [ 800/6250] eta: 0:12:59 lr: 0.000001 grad: 0.1124 (0.1492) loss: 0.8674 (0.8613) time: 0.1360 data: 0.0458 max mem: 8299 +Train: [95] [ 900/6250] eta: 0:12:38 lr: 0.000001 grad: 0.1240 (0.1482) loss: 0.8625 (0.8611) time: 0.1312 data: 0.0434 max mem: 8299 +Train: [95] [1000/6250] eta: 0:12:19 lr: 0.000001 grad: 0.1396 (0.1475) loss: 0.8606 (0.8610) time: 0.1301 data: 0.0566 max mem: 8299 +Train: [95] [1100/6250] eta: 0:12:00 lr: 0.000001 grad: 0.1230 (0.1469) loss: 0.8616 (0.8609) time: 0.1272 data: 0.0493 max mem: 8299 +Train: [95] [1200/6250] eta: 0:11:41 lr: 0.000001 grad: 0.1285 (0.1461) loss: 0.8617 (0.8611) time: 0.1261 data: 0.0445 max mem: 8299 +Train: [95] [1300/6250] eta: 0:11:25 lr: 0.000001 grad: 0.1314 (0.1450) loss: 0.8643 (0.8611) time: 0.1363 data: 0.0554 max mem: 8299 +Train: [95] [1400/6250] eta: 0:11:08 lr: 0.000001 grad: 0.1329 (0.1440) loss: 0.8602 (0.8612) time: 0.1360 data: 0.0637 max mem: 8299 +Train: [95] [1500/6250] eta: 0:10:53 lr: 0.000001 grad: 0.1281 (0.1434) loss: 0.8613 (0.8612) time: 0.1192 data: 0.0370 max mem: 8299 +Train: [95] [1600/6250] eta: 0:10:39 lr: 0.000001 grad: 0.1263 (0.1428) loss: 0.8578 (0.8612) time: 0.1368 data: 0.0573 max mem: 8299 +Train: [95] [1700/6250] eta: 0:10:23 lr: 0.000001 grad: 0.1273 (0.1422) loss: 0.8560 (0.8612) time: 0.1229 data: 0.0333 max mem: 8299 +Train: [95] [1800/6250] eta: 0:10:07 lr: 0.000001 grad: 0.1250 (0.1415) loss: 0.8623 (0.8612) time: 0.1188 data: 0.0451 max mem: 8299 +Train: [95] [1900/6250] eta: 0:09:51 lr: 0.000001 grad: 0.1307 (0.1410) loss: 0.8609 (0.8613) time: 0.1075 data: 0.0235 max mem: 8299 +Train: [95] [2000/6250] eta: 0:09:35 lr: 0.000001 grad: 0.1178 (0.1404) loss: 0.8649 (0.8614) time: 0.1452 data: 0.0648 max mem: 8299 +Train: [95] [2100/6250] eta: 0:09:17 lr: 0.000001 grad: 0.1232 (0.1401) loss: 0.8664 (0.8614) time: 0.1294 data: 0.0559 max mem: 8299 +Train: [95] [2200/6250] eta: 0:09:05 lr: 0.000001 grad: 0.1217 (0.1398) loss: 0.8644 (0.8614) time: 0.1442 data: 0.0591 max mem: 8299 +Train: [95] [2300/6250] eta: 0:08:52 lr: 0.000001 grad: 0.1296 (0.1394) loss: 0.8625 (0.8614) time: 0.1389 data: 0.0544 max mem: 8299 +Train: [95] [2400/6250] eta: 0:08:37 lr: 0.000001 grad: 0.1177 (0.1389) loss: 0.8620 (0.8615) time: 0.1165 data: 0.0433 max mem: 8299 +Train: [95] [2500/6250] eta: 0:08:22 lr: 0.000001 grad: 0.1292 (0.1385) loss: 0.8602 (0.8616) time: 0.1232 data: 0.0443 max mem: 8299 +Train: [95] [2600/6250] eta: 0:08:07 lr: 0.000001 grad: 0.1251 (0.1381) loss: 0.8617 (0.8616) time: 0.1233 data: 0.0504 max mem: 8299 +Train: [95] [2700/6250] eta: 0:07:53 lr: 0.000001 grad: 0.1299 (0.1378) loss: 0.8648 (0.8617) time: 0.1355 data: 0.0676 max mem: 8299 +Train: [95] [2800/6250] eta: 0:07:40 lr: 0.000001 grad: 0.1212 (0.1375) loss: 0.8637 (0.8618) time: 0.1414 data: 0.0617 max mem: 8299 +Train: [95] [2900/6250] eta: 0:07:28 lr: 0.000001 grad: 0.1155 (0.1371) loss: 0.8658 (0.8619) time: 0.1502 data: 0.0819 max mem: 8299 +Train: [95] [3000/6250] eta: 0:07:14 lr: 0.000001 grad: 0.1295 (0.1367) loss: 0.8644 (0.8620) time: 0.1324 data: 0.0533 max mem: 8299 +Train: [95] [3100/6250] eta: 0:07:00 lr: 0.000001 grad: 0.1245 (0.1364) loss: 0.8616 (0.8620) time: 0.1295 data: 0.0498 max mem: 8299 +Train: [95] [3200/6250] eta: 0:06:47 lr: 0.000001 grad: 0.1197 (0.1364) loss: 0.8705 (0.8621) time: 0.1504 data: 0.0745 max mem: 8299 +Train: [95] [3300/6250] eta: 0:06:34 lr: 0.000001 grad: 0.1269 (0.1362) loss: 0.8615 (0.8621) time: 0.1362 data: 0.0537 max mem: 8299 +Train: [95] [3400/6250] eta: 0:06:20 lr: 0.000001 grad: 0.1225 (0.1360) loss: 0.8704 (0.8622) time: 0.1100 data: 0.0225 max mem: 8299 +Train: [95] [3500/6250] eta: 0:06:07 lr: 0.000001 grad: 0.1269 (0.1359) loss: 0.8609 (0.8622) time: 0.1322 data: 0.0582 max mem: 8299 +Train: [95] [3600/6250] eta: 0:05:53 lr: 0.000001 grad: 0.1227 (0.1357) loss: 0.8579 (0.8622) time: 0.1289 data: 0.0488 max mem: 8299 +Train: [95] [3700/6250] eta: 0:05:40 lr: 0.000001 grad: 0.1197 (0.1355) loss: 0.8664 (0.8622) time: 0.1403 data: 0.0655 max mem: 8299 +Train: [95] [3800/6250] eta: 0:05:27 lr: 0.000001 grad: 0.1066 (0.1353) loss: 0.8653 (0.8623) time: 0.1263 data: 0.0575 max mem: 8299 +Train: [95] [3900/6250] eta: 0:05:14 lr: 0.000001 grad: 0.1234 (0.1349) loss: 0.8624 (0.8623) time: 0.1678 data: 0.0899 max mem: 8299 +Train: [95] [4000/6250] eta: 0:05:01 lr: 0.000001 grad: 0.1169 (0.1347) loss: 0.8647 (0.8623) time: 0.1428 data: 0.0715 max mem: 8299 +Train: [95] [4100/6250] eta: 0:04:48 lr: 0.000001 grad: 0.1148 (0.1344) loss: 0.8665 (0.8624) time: 0.1211 data: 0.0497 max mem: 8299 +Train: [95] [4200/6250] eta: 0:04:35 lr: 0.000001 grad: 0.1267 (0.1342) loss: 0.8624 (0.8624) time: 0.1509 data: 0.0624 max mem: 8299 +Train: [95] [4300/6250] eta: 0:04:21 lr: 0.000001 grad: 0.1199 (0.1339) loss: 0.8659 (0.8625) time: 0.1156 data: 0.0377 max mem: 8299 +Train: [95] [4400/6250] eta: 0:04:08 lr: 0.000001 grad: 0.1232 (0.1338) loss: 0.8574 (0.8626) time: 0.1223 data: 0.0428 max mem: 8299 +Train: [95] [4500/6250] eta: 0:03:54 lr: 0.000001 grad: 0.1226 (0.1337) loss: 0.8647 (0.8626) time: 0.1267 data: 0.0477 max mem: 8299 +Train: [95] [4600/6250] eta: 0:03:40 lr: 0.000001 grad: 0.1255 (0.1336) loss: 0.8663 (0.8627) time: 0.1123 data: 0.0296 max mem: 8299 +Train: [95] [4700/6250] eta: 0:03:26 lr: 0.000001 grad: 0.1305 (0.1335) loss: 0.8644 (0.8627) time: 0.1381 data: 0.0601 max mem: 8299 +Train: [95] [4800/6250] eta: 0:03:13 lr: 0.000001 grad: 0.1267 (0.1334) loss: 0.8668 (0.8627) time: 0.1489 data: 0.0685 max mem: 8299 +Train: [95] [4900/6250] eta: 0:03:00 lr: 0.000001 grad: 0.1217 (0.1333) loss: 0.8648 (0.8627) time: 0.1388 data: 0.0616 max mem: 8299 +Train: [95] [5000/6250] eta: 0:02:47 lr: 0.000001 grad: 0.1174 (0.1331) loss: 0.8618 (0.8627) time: 0.1510 data: 0.0779 max mem: 8299 +Train: [95] [5100/6250] eta: 0:02:33 lr: 0.000001 grad: 0.1357 (0.1331) loss: 0.8610 (0.8627) time: 0.1341 data: 0.0566 max mem: 8299 +Train: [95] [5200/6250] eta: 0:02:20 lr: 0.000001 grad: 0.1287 (0.1330) loss: 0.8652 (0.8627) time: 0.1335 data: 0.0635 max mem: 8299 +Train: [95] [5300/6250] eta: 0:02:06 lr: 0.000001 grad: 0.1342 (0.1330) loss: 0.8617 (0.8626) time: 0.1297 data: 0.0446 max mem: 8299 +Train: [95] [5400/6250] eta: 0:01:53 lr: 0.000001 grad: 0.1200 (0.1329) loss: 0.8644 (0.8627) time: 0.1340 data: 0.0551 max mem: 8299 +Train: [95] [5500/6250] eta: 0:01:40 lr: 0.000001 grad: 0.1271 (0.1328) loss: 0.8652 (0.8627) time: 0.1281 data: 0.0517 max mem: 8299 +Train: [95] [5600/6250] eta: 0:01:26 lr: 0.000001 grad: 0.1194 (0.1328) loss: 0.8658 (0.8627) time: 0.1184 data: 0.0424 max mem: 8299 +Train: [95] [5700/6250] eta: 0:01:13 lr: 0.000001 grad: 0.1279 (0.1327) loss: 0.8635 (0.8628) time: 0.1369 data: 0.0560 max mem: 8299 +Train: [95] [5800/6250] eta: 0:00:59 lr: 0.000001 grad: 0.1333 (0.1327) loss: 0.8580 (0.8627) time: 0.1495 data: 0.0675 max mem: 8299 +Train: [95] [5900/6250] eta: 0:00:46 lr: 0.000001 grad: 0.1326 (0.1326) loss: 0.8547 (0.8627) time: 0.1235 data: 0.0485 max mem: 8299 +Train: [95] [6000/6250] eta: 0:00:33 lr: 0.000001 grad: 0.1139 (0.1325) loss: 0.8653 (0.8627) time: 0.1482 data: 0.0784 max mem: 8299 +Train: [95] [6100/6250] eta: 0:00:20 lr: 0.000001 grad: 0.1170 (0.1324) loss: 0.8647 (0.8627) time: 0.1568 data: 0.0792 max mem: 8299 +Train: [95] [6200/6250] eta: 0:00:06 lr: 0.000001 grad: 0.1198 (0.1323) loss: 0.8658 (0.8627) time: 0.1400 data: 0.0726 max mem: 8299 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1231 (0.1322) loss: 0.8566 (0.8627) time: 0.1391 data: 0.0721 max mem: 8299 +Train: [95] Total time: 0:13:59 (0.1343 s / it) +Averaged stats: lr: 0.000001 grad: 0.1231 (0.1322) loss: 0.8566 (0.8627) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:05:42 loss: 0.8693 (0.8693) time: 5.5178 data: 5.4862 max mem: 8299 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8596 (0.8641) time: 0.1341 data: 0.1094 max mem: 8299 +Eval (hcp-train-subset): [95] Total time: 0:00:13 (0.2175 s / it) +Averaged stats (hcp-train-subset): loss: 0.8596 (0.8641) +Eval (hcp-val): [95] [ 0/62] eta: 0:04:01 loss: 0.8694 (0.8694) time: 3.8893 data: 3.8022 max mem: 8299 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8735 (0.8741) time: 0.1198 data: 0.0949 max mem: 8299 +Eval (hcp-val): [95] Total time: 0:00:12 (0.2091 s / it) +Averaged stats (hcp-val): loss: 0.8735 (0.8741) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 10:45:40 lr: 0.000001 grad: 0.1655 (0.1655) loss: 0.8441 (0.8441) time: 6.1985 data: 6.0818 max mem: 8299 +Train: [96] [ 100/6250] eta: 0:19:15 lr: 0.000001 grad: 0.1320 (0.1537) loss: 0.8629 (0.8594) time: 0.1459 data: 0.0488 max mem: 8299 +Train: [96] [ 200/6250] eta: 0:16:07 lr: 0.000001 grad: 0.1309 (0.1488) loss: 0.8630 (0.8592) time: 0.1140 data: 0.0219 max mem: 8299 +Train: [96] [ 300/6250] eta: 0:14:57 lr: 0.000001 grad: 0.1215 (0.1434) loss: 0.8681 (0.8599) time: 0.1383 data: 0.0458 max mem: 8299 +Train: [96] [ 400/6250] eta: 0:14:12 lr: 0.000001 grad: 0.1323 (0.1410) loss: 0.8565 (0.8600) time: 0.1268 data: 0.0428 max mem: 8299 +Train: [96] [ 500/6250] eta: 0:13:50 lr: 0.000001 grad: 0.1285 (0.1410) loss: 0.8661 (0.8601) time: 0.1496 data: 0.0652 max mem: 8299 +Train: [96] [ 600/6250] eta: 0:13:35 lr: 0.000001 grad: 0.1323 (0.1421) loss: 0.8553 (0.8599) time: 0.1469 data: 0.0678 max mem: 8299 +Train: [96] [ 700/6250] eta: 0:13:15 lr: 0.000001 grad: 0.1312 (0.1421) loss: 0.8608 (0.8598) time: 0.1398 data: 0.0457 max mem: 8299 +Train: [96] [ 800/6250] eta: 0:12:56 lr: 0.000001 grad: 0.1250 (0.1413) loss: 0.8641 (0.8604) time: 0.1340 data: 0.0520 max mem: 8299 +Train: [96] [ 900/6250] eta: 0:12:44 lr: 0.000001 grad: 0.1232 (0.1398) loss: 0.8652 (0.8610) time: 0.1201 data: 0.0344 max mem: 8299 +Train: [96] [1000/6250] eta: 0:12:24 lr: 0.000001 grad: 0.1290 (0.1392) loss: 0.8649 (0.8613) time: 0.1298 data: 0.0557 max mem: 8299 +Train: [96] [1100/6250] eta: 0:12:04 lr: 0.000000 grad: 0.1242 (0.1383) loss: 0.8666 (0.8617) time: 0.1391 data: 0.0519 max mem: 8299 +Train: [96] [1200/6250] eta: 0:11:45 lr: 0.000000 grad: 0.1148 (0.1372) loss: 0.8669 (0.8622) time: 0.1365 data: 0.0518 max mem: 8299 +Train: [96] [1300/6250] eta: 0:11:32 lr: 0.000000 grad: 0.1215 (0.1363) loss: 0.8677 (0.8626) time: 0.1382 data: 0.0605 max mem: 8299 +Train: [96] [1400/6250] eta: 0:11:18 lr: 0.000000 grad: 0.1282 (0.1359) loss: 0.8607 (0.8628) time: 0.1372 data: 0.0670 max mem: 8299 +Train: [96] [1500/6250] eta: 0:10:58 lr: 0.000000 grad: 0.1207 (0.1356) loss: 0.8655 (0.8629) time: 0.1231 data: 0.0439 max mem: 8299 +Train: [96] [1600/6250] eta: 0:10:39 lr: 0.000000 grad: 0.1243 (0.1353) loss: 0.8660 (0.8631) time: 0.1318 data: 0.0574 max mem: 8299 +Train: [96] [1700/6250] eta: 0:10:22 lr: 0.000000 grad: 0.1306 (0.1350) loss: 0.8646 (0.8631) time: 0.1176 data: 0.0418 max mem: 8299 +Train: [96] [1800/6250] eta: 0:10:06 lr: 0.000000 grad: 0.1281 (0.1348) loss: 0.8633 (0.8631) time: 0.1258 data: 0.0511 max mem: 8299 +Train: [96] [1900/6250] eta: 0:09:51 lr: 0.000000 grad: 0.1273 (0.1348) loss: 0.8609 (0.8631) time: 0.1315 data: 0.0575 max mem: 8299 +Train: [96] [2000/6250] eta: 0:09:37 lr: 0.000000 grad: 0.1306 (0.1348) loss: 0.8662 (0.8632) time: 0.1444 data: 0.0597 max mem: 8299 +Train: [96] [2100/6250] eta: 0:09:22 lr: 0.000000 grad: 0.1309 (0.1349) loss: 0.8596 (0.8632) time: 0.1068 data: 0.0291 max mem: 8299 +Train: [96] [2200/6250] eta: 0:09:11 lr: 0.000000 grad: 0.1253 (0.1349) loss: 0.8684 (0.8631) time: 0.1595 data: 0.0843 max mem: 8299 +Train: [96] [2300/6250] eta: 0:08:57 lr: 0.000000 grad: 0.1371 (0.1349) loss: 0.8581 (0.8631) time: 0.1612 data: 0.0866 max mem: 8299 +Train: [96] [2400/6250] eta: 0:08:42 lr: 0.000000 grad: 0.1318 (0.1349) loss: 0.8615 (0.8630) time: 0.1472 data: 0.0748 max mem: 8299 +Train: [96] [2500/6250] eta: 0:08:28 lr: 0.000000 grad: 0.1301 (0.1349) loss: 0.8613 (0.8630) time: 0.1248 data: 0.0483 max mem: 8299 +Train: [96] [2600/6250] eta: 0:08:14 lr: 0.000000 grad: 0.1251 (0.1348) loss: 0.8640 (0.8628) time: 0.1140 data: 0.0350 max mem: 8299 +Train: [96] [2700/6250] eta: 0:08:01 lr: 0.000000 grad: 0.1230 (0.1345) loss: 0.8584 (0.8628) time: 0.1140 data: 0.0352 max mem: 8299 +Train: [96] [2800/6250] eta: 0:07:47 lr: 0.000000 grad: 0.1277 (0.1344) loss: 0.8595 (0.8628) time: 0.1215 data: 0.0426 max mem: 8299 +Train: [96] [2900/6250] eta: 0:07:33 lr: 0.000000 grad: 0.1370 (0.1343) loss: 0.8611 (0.8628) time: 0.1319 data: 0.0495 max mem: 8299 +Train: [96] [3000/6250] eta: 0:07:19 lr: 0.000000 grad: 0.1292 (0.1342) loss: 0.8581 (0.8628) time: 0.1151 data: 0.0369 max mem: 8299 +Train: [96] [3100/6250] eta: 0:07:05 lr: 0.000000 grad: 0.1300 (0.1342) loss: 0.8566 (0.8627) time: 0.1115 data: 0.0199 max mem: 8299 +Train: [96] [3200/6250] eta: 0:06:51 lr: 0.000000 grad: 0.1263 (0.1341) loss: 0.8639 (0.8627) time: 0.1447 data: 0.0747 max mem: 8299 +Train: [96] [3300/6250] eta: 0:06:37 lr: 0.000000 grad: 0.1365 (0.1342) loss: 0.8592 (0.8627) time: 0.1268 data: 0.0501 max mem: 8299 +Train: [96] [3400/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1321 (0.1342) loss: 0.8606 (0.8627) time: 0.1224 data: 0.0443 max mem: 8299 +Train: [96] [3500/6250] eta: 0:06:10 lr: 0.000000 grad: 0.1253 (0.1342) loss: 0.8678 (0.8627) time: 0.1312 data: 0.0552 max mem: 8299 +Train: [96] [3600/6250] eta: 0:05:56 lr: 0.000000 grad: 0.1289 (0.1341) loss: 0.8621 (0.8628) time: 0.1369 data: 0.0715 max mem: 8299 +Train: [96] [3700/6250] eta: 0:05:43 lr: 0.000000 grad: 0.1196 (0.1342) loss: 0.8629 (0.8628) time: 0.1019 data: 0.0259 max mem: 8299 +Train: [96] [3800/6250] eta: 0:05:29 lr: 0.000000 grad: 0.1317 (0.1343) loss: 0.8609 (0.8628) time: 0.1298 data: 0.0579 max mem: 8299 +Train: [96] [3900/6250] eta: 0:05:16 lr: 0.000000 grad: 0.1278 (0.1344) loss: 0.8638 (0.8628) time: 0.1778 data: 0.1098 max mem: 8299 +Train: [96] [4000/6250] eta: 0:05:03 lr: 0.000000 grad: 0.1362 (0.1344) loss: 0.8615 (0.8628) time: 0.1475 data: 0.0776 max mem: 8299 +Train: [96] [4100/6250] eta: 0:04:50 lr: 0.000000 grad: 0.1257 (0.1344) loss: 0.8605 (0.8628) time: 0.1350 data: 0.0528 max mem: 8299 +Train: [96] [4200/6250] eta: 0:04:36 lr: 0.000000 grad: 0.1392 (0.1344) loss: 0.8573 (0.8628) time: 0.1392 data: 0.0696 max mem: 8299 +Train: [96] [4300/6250] eta: 0:04:23 lr: 0.000000 grad: 0.1151 (0.1343) loss: 0.8669 (0.8628) time: 0.1361 data: 0.0590 max mem: 8299 +Train: [96] [4400/6250] eta: 0:04:10 lr: 0.000000 grad: 0.1258 (0.1342) loss: 0.8650 (0.8628) time: 0.1360 data: 0.0548 max mem: 8299 +Train: [96] [4500/6250] eta: 0:03:57 lr: 0.000000 grad: 0.1198 (0.1342) loss: 0.8675 (0.8628) time: 0.1451 data: 0.0642 max mem: 8299 +Train: [96] [4600/6250] eta: 0:03:43 lr: 0.000000 grad: 0.1285 (0.1342) loss: 0.8608 (0.8627) time: 0.1231 data: 0.0494 max mem: 8299 +Train: [96] [4700/6250] eta: 0:03:29 lr: 0.000000 grad: 0.1350 (0.1341) loss: 0.8594 (0.8627) time: 0.1222 data: 0.0465 max mem: 8299 +Train: [96] [4800/6250] eta: 0:03:15 lr: 0.000000 grad: 0.1254 (0.1340) loss: 0.8580 (0.8627) time: 0.1277 data: 0.0372 max mem: 8299 +Train: [96] [4900/6250] eta: 0:03:02 lr: 0.000000 grad: 0.1391 (0.1341) loss: 0.8610 (0.8626) time: 0.1611 data: 0.0779 max mem: 8299 +Train: [96] [5000/6250] eta: 0:02:48 lr: 0.000000 grad: 0.1310 (0.1340) loss: 0.8617 (0.8626) time: 0.0979 data: 0.0139 max mem: 8299 +Train: [96] [5100/6250] eta: 0:02:35 lr: 0.000000 grad: 0.1231 (0.1339) loss: 0.8614 (0.8625) time: 0.1339 data: 0.0562 max mem: 8299 +Train: [96] [5200/6250] eta: 0:02:21 lr: 0.000000 grad: 0.1295 (0.1339) loss: 0.8621 (0.8625) time: 0.1562 data: 0.0795 max mem: 8299 +Train: [96] [5300/6250] eta: 0:02:08 lr: 0.000000 grad: 0.1265 (0.1338) loss: 0.8593 (0.8625) time: 0.1347 data: 0.0645 max mem: 8299 +Train: [96] [5400/6250] eta: 0:01:54 lr: 0.000000 grad: 0.1282 (0.1338) loss: 0.8588 (0.8625) time: 0.1472 data: 0.0671 max mem: 8299 +Train: [96] [5500/6250] eta: 0:01:40 lr: 0.000000 grad: 0.1247 (0.1337) loss: 0.8675 (0.8625) time: 0.1312 data: 0.0548 max mem: 8299 +Train: [96] [5600/6250] eta: 0:01:27 lr: 0.000000 grad: 0.1291 (0.1337) loss: 0.8620 (0.8625) time: 0.1287 data: 0.0465 max mem: 8299 +Train: [96] [5700/6250] eta: 0:01:13 lr: 0.000000 grad: 0.1290 (0.1337) loss: 0.8607 (0.8625) time: 0.1387 data: 0.0592 max mem: 8299 +Train: [96] [5800/6250] eta: 0:01:00 lr: 0.000000 grad: 0.1311 (0.1337) loss: 0.8647 (0.8625) time: 0.1389 data: 0.0587 max mem: 8299 +Train: [96] [5900/6250] eta: 0:00:47 lr: 0.000000 grad: 0.1308 (0.1337) loss: 0.8638 (0.8625) time: 0.1337 data: 0.0610 max mem: 8299 +Train: [96] [6000/6250] eta: 0:00:33 lr: 0.000000 grad: 0.1221 (0.1337) loss: 0.8680 (0.8626) time: 0.1433 data: 0.0718 max mem: 8299 +Train: [96] [6100/6250] eta: 0:00:20 lr: 0.000000 grad: 0.1376 (0.1337) loss: 0.8625 (0.8626) time: 0.1418 data: 0.0639 max mem: 8299 +Train: [96] [6200/6250] eta: 0:00:06 lr: 0.000000 grad: 0.1280 (0.1337) loss: 0.8577 (0.8626) time: 0.1471 data: 0.0731 max mem: 8299 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1311 (0.1337) loss: 0.8597 (0.8626) time: 0.1363 data: 0.0589 max mem: 8299 +Train: [96] Total time: 0:14:05 (0.1352 s / it) +Averaged stats: lr: 0.000000 grad: 0.1311 (0.1337) loss: 0.8597 (0.8626) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:06:05 loss: 0.8691 (0.8691) time: 5.8923 data: 5.8615 max mem: 8299 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8605 (0.8637) time: 0.1416 data: 0.1158 max mem: 8299 +Eval (hcp-train-subset): [96] Total time: 0:00:14 (0.2271 s / it) +Averaged stats (hcp-train-subset): loss: 0.8605 (0.8637) +Eval (hcp-val): [96] [ 0/62] eta: 0:05:37 loss: 0.8742 (0.8742) time: 5.4434 data: 5.4104 max mem: 8299 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8734 (0.8741) time: 0.1013 data: 0.0769 max mem: 8299 +Eval (hcp-val): [96] Total time: 0:00:12 (0.2042 s / it) +Averaged stats (hcp-val): loss: 0.8734 (0.8741) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 8:57:35 lr: 0.000000 grad: 0.1821 (0.1821) loss: 0.9013 (0.9013) time: 5.1609 data: 5.0357 max mem: 8299 +Train: [97] [ 100/6250] eta: 0:17:48 lr: 0.000000 grad: 0.1693 (0.1491) loss: 0.8802 (0.8727) time: 0.1218 data: 0.0281 max mem: 8299 +Train: [97] [ 200/6250] eta: 0:15:21 lr: 0.000000 grad: 0.1287 (0.1482) loss: 0.8690 (0.8700) time: 0.1162 data: 0.0250 max mem: 8299 +Train: [97] [ 300/6250] eta: 0:14:24 lr: 0.000000 grad: 0.1230 (0.1494) loss: 0.8507 (0.8666) time: 0.1258 data: 0.0364 max mem: 8299 +Train: [97] [ 400/6250] eta: 0:13:58 lr: 0.000000 grad: 0.1219 (0.1486) loss: 0.8670 (0.8656) time: 0.1225 data: 0.0245 max mem: 8299 +Train: [97] [ 500/6250] eta: 0:13:45 lr: 0.000000 grad: 0.1373 (0.1474) loss: 0.8652 (0.8656) time: 0.1634 data: 0.0742 max mem: 8299 +Train: [97] [ 600/6250] eta: 0:13:22 lr: 0.000000 grad: 0.1206 (0.1463) loss: 0.8688 (0.8661) time: 0.1262 data: 0.0438 max mem: 8299 +Train: [97] [ 700/6250] eta: 0:13:02 lr: 0.000000 grad: 0.1469 (0.1447) loss: 0.8598 (0.8660) time: 0.1370 data: 0.0550 max mem: 8299 +Train: [97] [ 800/6250] eta: 0:12:39 lr: 0.000000 grad: 0.1221 (0.1434) loss: 0.8627 (0.8658) time: 0.1349 data: 0.0504 max mem: 8299 +Train: [97] [ 900/6250] eta: 0:12:26 lr: 0.000000 grad: 0.1335 (0.1430) loss: 0.8568 (0.8652) time: 0.1753 data: 0.0890 max mem: 8299 +Train: [97] [1000/6250] eta: 0:12:14 lr: 0.000000 grad: 0.1268 (0.1432) loss: 0.8621 (0.8646) time: 0.1546 data: 0.0674 max mem: 8299 +Train: [97] [1100/6250] eta: 0:11:55 lr: 0.000000 grad: 0.1178 (0.1428) loss: 0.8634 (0.8644) time: 0.1243 data: 0.0512 max mem: 8299 +Train: [97] [1200/6250] eta: 0:11:42 lr: 0.000000 grad: 0.1195 (0.1424) loss: 0.8682 (0.8643) time: 0.1395 data: 0.0635 max mem: 8299 +Train: [97] [1300/6250] eta: 0:11:24 lr: 0.000000 grad: 0.1213 (0.1419) loss: 0.8651 (0.8642) time: 0.1169 data: 0.0322 max mem: 8299 +Train: [97] [1400/6250] eta: 0:11:10 lr: 0.000000 grad: 0.1272 (0.1415) loss: 0.8644 (0.8642) time: 0.1306 data: 0.0524 max mem: 8299 +Train: [97] [1500/6250] eta: 0:10:54 lr: 0.000000 grad: 0.1325 (0.1408) loss: 0.8731 (0.8642) time: 0.1505 data: 0.0683 max mem: 8299 +Train: [97] [1600/6250] eta: 0:10:39 lr: 0.000000 grad: 0.1342 (0.1407) loss: 0.8673 (0.8641) time: 0.1338 data: 0.0502 max mem: 8299 +Train: [97] [1700/6250] eta: 0:10:23 lr: 0.000000 grad: 0.1434 (0.1405) loss: 0.8662 (0.8640) time: 0.1446 data: 0.0603 max mem: 8299 +Train: [97] [1800/6250] eta: 0:10:08 lr: 0.000000 grad: 0.1309 (0.1402) loss: 0.8658 (0.8640) time: 0.1235 data: 0.0331 max mem: 8299 +Train: [97] [1900/6250] eta: 0:09:53 lr: 0.000000 grad: 0.1232 (0.1399) loss: 0.8672 (0.8639) time: 0.1437 data: 0.0594 max mem: 8299 +Train: [97] [2000/6250] eta: 0:09:37 lr: 0.000000 grad: 0.1241 (0.1396) loss: 0.8653 (0.8638) time: 0.1366 data: 0.0522 max mem: 8299 +Train: [97] [2100/6250] eta: 0:09:23 lr: 0.000000 grad: 0.1246 (0.1392) loss: 0.8578 (0.8636) time: 0.1308 data: 0.0494 max mem: 8299 +Train: [97] [2200/6250] eta: 0:09:09 lr: 0.000000 grad: 0.1282 (0.1389) loss: 0.8609 (0.8635) time: 0.1301 data: 0.0577 max mem: 8299 +Train: [97] [2300/6250] eta: 0:08:55 lr: 0.000000 grad: 0.1182 (0.1386) loss: 0.8662 (0.8635) time: 0.1311 data: 0.0476 max mem: 8299 +Train: [97] [2400/6250] eta: 0:08:42 lr: 0.000000 grad: 0.1365 (0.1386) loss: 0.8559 (0.8634) time: 0.1364 data: 0.0590 max mem: 8299 +Train: [97] [2500/6250] eta: 0:08:29 lr: 0.000000 grad: 0.1319 (0.1385) loss: 0.8637 (0.8633) time: 0.1383 data: 0.0662 max mem: 8299 +Train: [97] [2600/6250] eta: 0:08:16 lr: 0.000000 grad: 0.1326 (0.1384) loss: 0.8627 (0.8632) time: 0.1383 data: 0.0666 max mem: 8299 +Train: [97] [2700/6250] eta: 0:08:01 lr: 0.000000 grad: 0.1230 (0.1383) loss: 0.8572 (0.8631) time: 0.1347 data: 0.0607 max mem: 8299 +Train: [97] [2800/6250] eta: 0:07:46 lr: 0.000000 grad: 0.1352 (0.1383) loss: 0.8559 (0.8630) time: 0.1151 data: 0.0378 max mem: 8299 +Train: [97] [2900/6250] eta: 0:07:32 lr: 0.000000 grad: 0.1264 (0.1382) loss: 0.8606 (0.8630) time: 0.1405 data: 0.0607 max mem: 8299 +Train: [97] [3000/6250] eta: 0:07:19 lr: 0.000000 grad: 0.1262 (0.1382) loss: 0.8578 (0.8630) time: 0.1304 data: 0.0418 max mem: 8299 +Train: [97] [3100/6250] eta: 0:07:05 lr: 0.000000 grad: 0.1278 (0.1381) loss: 0.8647 (0.8630) time: 0.1102 data: 0.0332 max mem: 8299 +Train: [97] [3200/6250] eta: 0:06:51 lr: 0.000000 grad: 0.1294 (0.1379) loss: 0.8631 (0.8631) time: 0.1166 data: 0.0420 max mem: 8299 +Train: [97] [3300/6250] eta: 0:06:37 lr: 0.000000 grad: 0.1418 (0.1379) loss: 0.8647 (0.8631) time: 0.1651 data: 0.0795 max mem: 8299 +Train: [97] [3400/6250] eta: 0:06:23 lr: 0.000000 grad: 0.1321 (0.1379) loss: 0.8615 (0.8632) time: 0.1370 data: 0.0474 max mem: 8299 +Train: [97] [3500/6250] eta: 0:06:10 lr: 0.000000 grad: 0.1155 (0.1378) loss: 0.8647 (0.8632) time: 0.1197 data: 0.0314 max mem: 8299 +Train: [97] [3600/6250] eta: 0:05:57 lr: 0.000000 grad: 0.1284 (0.1377) loss: 0.8615 (0.8633) time: 0.1246 data: 0.0472 max mem: 8299 +Train: [97] [3700/6250] eta: 0:05:43 lr: 0.000000 grad: 0.1277 (0.1378) loss: 0.8706 (0.8633) time: 0.1402 data: 0.0633 max mem: 8299 +Train: [97] [3800/6250] eta: 0:05:30 lr: 0.000000 grad: 0.1242 (0.1379) loss: 0.8605 (0.8633) time: 0.1512 data: 0.0698 max mem: 8299 +Train: [97] [3900/6250] eta: 0:05:15 lr: 0.000000 grad: 0.1276 (0.1380) loss: 0.8607 (0.8633) time: 0.1244 data: 0.0395 max mem: 8299 +Train: [97] [4000/6250] eta: 0:05:03 lr: 0.000000 grad: 0.1211 (0.1379) loss: 0.8627 (0.8634) time: 0.1487 data: 0.0636 max mem: 8299 +Train: [97] [4100/6250] eta: 0:04:50 lr: 0.000000 grad: 0.1258 (0.1379) loss: 0.8685 (0.8634) time: 0.1300 data: 0.0558 max mem: 8299 +Train: [97] [4200/6250] eta: 0:04:36 lr: 0.000000 grad: 0.1264 (0.1379) loss: 0.8667 (0.8635) time: 0.1244 data: 0.0456 max mem: 8299 +Train: [97] [4300/6250] eta: 0:04:23 lr: 0.000000 grad: 0.1238 (0.1378) loss: 0.8655 (0.8635) time: 0.1269 data: 0.0433 max mem: 8299 +Train: [97] [4400/6250] eta: 0:04:09 lr: 0.000000 grad: 0.1295 (0.1378) loss: 0.8629 (0.8635) time: 0.1271 data: 0.0462 max mem: 8299 +Train: [97] [4500/6250] eta: 0:03:55 lr: 0.000000 grad: 0.1546 (0.1380) loss: 0.8612 (0.8635) time: 0.1308 data: 0.0486 max mem: 8299 +Train: [97] [4600/6250] eta: 0:03:42 lr: 0.000000 grad: 0.1336 (0.1379) loss: 0.8611 (0.8635) time: 0.1281 data: 0.0534 max mem: 8299 +Train: [97] [4700/6250] eta: 0:03:29 lr: 0.000000 grad: 0.1279 (0.1379) loss: 0.8670 (0.8635) time: 0.1414 data: 0.0637 max mem: 8299 +Train: [97] [4800/6250] eta: 0:03:15 lr: 0.000000 grad: 0.1290 (0.1379) loss: 0.8642 (0.8635) time: 0.1326 data: 0.0599 max mem: 8299 +Train: [97] [4900/6250] eta: 0:03:01 lr: 0.000000 grad: 0.1371 (0.1379) loss: 0.8660 (0.8635) time: 0.1205 data: 0.0446 max mem: 8299 +Train: [97] [5000/6250] eta: 0:02:48 lr: 0.000000 grad: 0.1221 (0.1379) loss: 0.8593 (0.8635) time: 0.1280 data: 0.0559 max mem: 8299 +Train: [97] [5100/6250] eta: 0:02:35 lr: 0.000000 grad: 0.1395 (0.1378) loss: 0.8602 (0.8635) time: 0.1321 data: 0.0451 max mem: 8299 +Train: [97] [5200/6250] eta: 0:02:21 lr: 0.000000 grad: 0.1280 (0.1379) loss: 0.8682 (0.8635) time: 0.1417 data: 0.0711 max mem: 8299 +Train: [97] [5300/6250] eta: 0:02:08 lr: 0.000000 grad: 0.1235 (0.1378) loss: 0.8664 (0.8635) time: 0.1351 data: 0.0641 max mem: 8299 +Train: [97] [5400/6250] eta: 0:01:55 lr: 0.000000 grad: 0.1260 (0.1378) loss: 0.8594 (0.8635) time: 0.1387 data: 0.0658 max mem: 8299 +Train: [97] [5500/6250] eta: 0:01:41 lr: 0.000000 grad: 0.1304 (0.1378) loss: 0.8626 (0.8634) time: 0.1358 data: 0.0502 max mem: 8299 +Train: [97] [5600/6250] eta: 0:01:28 lr: 0.000000 grad: 0.1202 (0.1377) loss: 0.8651 (0.8634) time: 0.1231 data: 0.0507 max mem: 8299 +Train: [97] [5700/6250] eta: 0:01:14 lr: 0.000000 grad: 0.1210 (0.1376) loss: 0.8662 (0.8634) time: 0.1310 data: 0.0546 max mem: 8299 +Train: [97] [5800/6250] eta: 0:01:00 lr: 0.000000 grad: 0.1189 (0.1375) loss: 0.8646 (0.8634) time: 0.1344 data: 0.0628 max mem: 8299 +Train: [97] [5900/6250] eta: 0:00:47 lr: 0.000000 grad: 0.1201 (0.1373) loss: 0.8561 (0.8634) time: 0.1136 data: 0.0329 max mem: 8299 +Train: [97] [6000/6250] eta: 0:00:33 lr: 0.000000 grad: 0.1251 (0.1371) loss: 0.8604 (0.8635) time: 0.1304 data: 0.0467 max mem: 8299 +Train: [97] [6100/6250] eta: 0:00:20 lr: 0.000000 grad: 0.1320 (0.1371) loss: 0.8651 (0.8635) time: 0.1610 data: 0.0866 max mem: 8299 +Train: [97] [6200/6250] eta: 0:00:06 lr: 0.000000 grad: 0.1195 (0.1371) loss: 0.8700 (0.8635) time: 0.1477 data: 0.0751 max mem: 8299 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1225 (0.1371) loss: 0.8658 (0.8635) time: 0.1269 data: 0.0508 max mem: 8299 +Train: [97] Total time: 0:14:11 (0.1362 s / it) +Averaged stats: lr: 0.000000 grad: 0.1225 (0.1371) loss: 0.8658 (0.8635) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:05:35 loss: 0.8677 (0.8677) time: 5.4106 data: 5.3807 max mem: 8299 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8599 (0.8636) time: 0.1101 data: 0.0851 max mem: 8299 +Eval (hcp-train-subset): [97] Total time: 0:00:12 (0.2046 s / it) +Averaged stats (hcp-train-subset): loss: 0.8599 (0.8636) +Eval (hcp-val): [97] [ 0/62] eta: 0:03:56 loss: 0.8691 (0.8691) time: 3.8135 data: 3.7307 max mem: 8299 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8720 (0.8734) time: 0.1228 data: 0.0983 max mem: 8299 +Eval (hcp-val): [97] Total time: 0:00:13 (0.2130 s / it) +Averaged stats (hcp-val): loss: 0.8720 (0.8734) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 7:52:31 lr: 0.000000 grad: 0.0649 (0.0649) loss: 0.8937 (0.8937) time: 4.5362 data: 4.2804 max mem: 8299 +Train: [98] [ 100/6250] eta: 0:20:17 lr: 0.000000 grad: 0.1156 (0.1436) loss: 0.8755 (0.8707) time: 0.1339 data: 0.0315 max mem: 8299 +Train: [98] [ 200/6250] eta: 0:16:38 lr: 0.000000 grad: 0.1122 (0.1335) loss: 0.8751 (0.8744) time: 0.1331 data: 0.0411 max mem: 8299 +Train: [98] [ 300/6250] eta: 0:15:19 lr: 0.000000 grad: 0.1359 (0.1297) loss: 0.8710 (0.8755) time: 0.1365 data: 0.0377 max mem: 8299 +Train: [98] [ 400/6250] eta: 0:14:42 lr: 0.000000 grad: 0.1277 (0.1292) loss: 0.8740 (0.8755) time: 0.1435 data: 0.0595 max mem: 8299 +Train: [98] [ 500/6250] eta: 0:14:21 lr: 0.000000 grad: 0.1271 (0.1292) loss: 0.8717 (0.8747) time: 0.1289 data: 0.0348 max mem: 8299 +Train: [98] [ 600/6250] eta: 0:14:00 lr: 0.000000 grad: 0.1194 (0.1319) loss: 0.8669 (0.8736) time: 0.1194 data: 0.0357 max mem: 8299 +Train: [98] [ 700/6250] eta: 0:13:45 lr: 0.000000 grad: 0.1265 (0.1328) loss: 0.8625 (0.8723) time: 0.1431 data: 0.0571 max mem: 8299 +Train: [98] [ 800/6250] eta: 0:13:26 lr: 0.000000 grad: 0.1279 (0.1329) loss: 0.8615 (0.8712) time: 0.1540 data: 0.0727 max mem: 8299 +Train: [98] [ 900/6250] eta: 0:13:08 lr: 0.000000 grad: 0.1205 (0.1327) loss: 0.8715 (0.8707) time: 0.1459 data: 0.0615 max mem: 8299 +Train: [98] [1000/6250] eta: 0:12:52 lr: 0.000000 grad: 0.1232 (0.1329) loss: 0.8649 (0.8702) time: 0.1566 data: 0.0638 max mem: 8299 +Train: [98] [1100/6250] eta: 0:12:32 lr: 0.000000 grad: 0.1194 (0.1326) loss: 0.8661 (0.8699) time: 0.1367 data: 0.0531 max mem: 8299 +Train: [98] [1200/6250] eta: 0:12:13 lr: 0.000000 grad: 0.1140 (0.1324) loss: 0.8704 (0.8698) time: 0.1460 data: 0.0735 max mem: 8299 +Train: [98] [1300/6250] eta: 0:11:59 lr: 0.000000 grad: 0.1179 (0.1326) loss: 0.8646 (0.8696) time: 0.1538 data: 0.0819 max mem: 8299 +Train: [98] [1400/6250] eta: 0:11:48 lr: 0.000000 grad: 0.1237 (0.1326) loss: 0.8680 (0.8695) time: 0.1036 data: 0.0205 max mem: 8299 +Train: [98] [1500/6250] eta: 0:11:29 lr: 0.000000 grad: 0.1180 (0.1322) loss: 0.8658 (0.8693) time: 0.1384 data: 0.0590 max mem: 8299 +Train: [98] [1600/6250] eta: 0:11:13 lr: 0.000000 grad: 0.1130 (0.1318) loss: 0.8767 (0.8693) time: 0.1353 data: 0.0614 max mem: 8299 +Train: [98] [1700/6250] eta: 0:10:55 lr: 0.000000 grad: 0.1171 (0.1316) loss: 0.8672 (0.8692) time: 0.1142 data: 0.0361 max mem: 8299 +Train: [98] [1800/6250] eta: 0:10:36 lr: 0.000000 grad: 0.1321 (0.1317) loss: 0.8649 (0.8690) time: 0.1454 data: 0.0719 max mem: 8299 +Train: [98] [1900/6250] eta: 0:10:20 lr: 0.000000 grad: 0.1200 (0.1313) loss: 0.8688 (0.8688) time: 0.1485 data: 0.0624 max mem: 8299 +Train: [98] [2000/6250] eta: 0:10:06 lr: 0.000000 grad: 0.1378 (0.1313) loss: 0.8647 (0.8687) time: 0.1480 data: 0.0740 max mem: 8299 +Train: [98] [2100/6250] eta: 0:09:50 lr: 0.000000 grad: 0.1222 (0.1311) loss: 0.8575 (0.8686) time: 0.1284 data: 0.0534 max mem: 8299 +Train: [98] [2200/6250] eta: 0:09:32 lr: 0.000000 grad: 0.1361 (0.1313) loss: 0.8641 (0.8684) time: 0.1098 data: 0.0405 max mem: 8299 +Train: [98] [2300/6250] eta: 0:09:16 lr: 0.000000 grad: 0.1248 (0.1311) loss: 0.8605 (0.8682) time: 0.1414 data: 0.0591 max mem: 8299 +Train: [98] [2400/6250] eta: 0:09:02 lr: 0.000000 grad: 0.1169 (0.1308) loss: 0.8616 (0.8681) time: 0.1795 data: 0.1040 max mem: 8299 +Train: [98] [2500/6250] eta: 0:08:48 lr: 0.000000 grad: 0.1268 (0.1308) loss: 0.8596 (0.8679) time: 0.1798 data: 0.1030 max mem: 8299 +Train: [98] [2600/6250] eta: 0:08:34 lr: 0.000000 grad: 0.1279 (0.1311) loss: 0.8640 (0.8677) time: 0.1383 data: 0.0577 max mem: 8299 +Train: [98] [2700/6250] eta: 0:08:19 lr: 0.000000 grad: 0.1212 (0.1313) loss: 0.8644 (0.8675) time: 0.1352 data: 0.0492 max mem: 8299 +Train: [98] [2800/6250] eta: 0:08:03 lr: 0.000000 grad: 0.1271 (0.1313) loss: 0.8685 (0.8674) time: 0.0906 data: 0.0057 max mem: 8299 +Train: [98] [2900/6250] eta: 0:07:49 lr: 0.000000 grad: 0.1246 (0.1313) loss: 0.8665 (0.8674) time: 0.1543 data: 0.0805 max mem: 8299 +Train: [98] [3000/6250] eta: 0:07:36 lr: 0.000000 grad: 0.1246 (0.1312) loss: 0.8654 (0.8673) time: 0.1595 data: 0.0772 max mem: 8299 +Train: [98] [3100/6250] eta: 0:07:23 lr: 0.000000 grad: 0.1240 (0.1312) loss: 0.8546 (0.8672) time: 0.1732 data: 0.1038 max mem: 8299 +Train: [98] [3200/6250] eta: 0:07:09 lr: 0.000000 grad: 0.1327 (0.1313) loss: 0.8675 (0.8671) time: 0.1873 data: 0.1048 max mem: 8299 +Train: [98] [3300/6250] eta: 0:06:55 lr: 0.000000 grad: 0.1229 (0.1311) loss: 0.8616 (0.8669) time: 0.1326 data: 0.0522 max mem: 8299 +Train: [98] [3400/6250] eta: 0:06:41 lr: 0.000000 grad: 0.1186 (0.1310) loss: 0.8677 (0.8669) time: 0.1752 data: 0.1003 max mem: 8299 +Train: [98] [3500/6250] eta: 0:06:27 lr: 0.000000 grad: 0.1230 (0.1311) loss: 0.8583 (0.8667) time: 0.1523 data: 0.0849 max mem: 8299 +Train: [98] [3600/6250] eta: 0:06:13 lr: 0.000000 grad: 0.1120 (0.1310) loss: 0.8622 (0.8667) time: 0.1347 data: 0.0553 max mem: 8299 +Train: [98] [3700/6250] eta: 0:05:59 lr: 0.000000 grad: 0.1269 (0.1310) loss: 0.8625 (0.8665) time: 0.1193 data: 0.0511 max mem: 8299 +Train: [98] [3800/6250] eta: 0:05:45 lr: 0.000000 grad: 0.1307 (0.1311) loss: 0.8638 (0.8665) time: 0.1212 data: 0.0395 max mem: 8299 +Train: [98] [3900/6250] eta: 0:05:31 lr: 0.000000 grad: 0.1313 (0.1313) loss: 0.8673 (0.8664) time: 0.1274 data: 0.0504 max mem: 8299 +Train: [98] [4000/6250] eta: 0:05:17 lr: 0.000000 grad: 0.1218 (0.1313) loss: 0.8643 (0.8664) time: 0.1455 data: 0.0705 max mem: 8299 +Train: [98] [4100/6250] eta: 0:05:03 lr: 0.000000 grad: 0.1228 (0.1314) loss: 0.8632 (0.8663) time: 0.1441 data: 0.0660 max mem: 8299 +Train: [98] [4200/6250] eta: 0:04:49 lr: 0.000000 grad: 0.1186 (0.1315) loss: 0.8648 (0.8663) time: 0.1400 data: 0.0571 max mem: 8299 +Train: [98] [4300/6250] eta: 0:04:35 lr: 0.000000 grad: 0.1421 (0.1317) loss: 0.8635 (0.8663) time: 0.1418 data: 0.0596 max mem: 8299 +Train: [98] [4400/6250] eta: 0:04:21 lr: 0.000000 grad: 0.1320 (0.1319) loss: 0.8623 (0.8662) time: 0.1464 data: 0.0590 max mem: 8299 +Train: [98] [4500/6250] eta: 0:04:07 lr: 0.000000 grad: 0.1253 (0.1320) loss: 0.8673 (0.8662) time: 0.1406 data: 0.0592 max mem: 8299 +Train: [98] [4600/6250] eta: 0:03:53 lr: 0.000000 grad: 0.1152 (0.1320) loss: 0.8621 (0.8661) time: 0.1301 data: 0.0534 max mem: 8299 +Train: [98] [4700/6250] eta: 0:03:38 lr: 0.000000 grad: 0.1292 (0.1320) loss: 0.8666 (0.8661) time: 0.1241 data: 0.0604 max mem: 8299 +Train: [98] [4800/6250] eta: 0:03:24 lr: 0.000000 grad: 0.1328 (0.1320) loss: 0.8628 (0.8660) time: 0.1452 data: 0.0468 max mem: 8299 +Train: [98] [4900/6250] eta: 0:03:10 lr: 0.000000 grad: 0.1279 (0.1320) loss: 0.8652 (0.8660) time: 0.1300 data: 0.0550 max mem: 8299 +Train: [98] [5000/6250] eta: 0:02:55 lr: 0.000000 grad: 0.1258 (0.1321) loss: 0.8674 (0.8659) time: 0.1133 data: 0.0452 max mem: 8299 +Train: [98] [5100/6250] eta: 0:02:41 lr: 0.000000 grad: 0.1252 (0.1321) loss: 0.8649 (0.8659) time: 0.1440 data: 0.0691 max mem: 8299 +Train: [98] [5200/6250] eta: 0:02:27 lr: 0.000000 grad: 0.1199 (0.1322) loss: 0.8667 (0.8659) time: 0.1338 data: 0.0515 max mem: 8299 +Train: [98] [5300/6250] eta: 0:02:13 lr: 0.000000 grad: 0.1225 (0.1323) loss: 0.8662 (0.8658) time: 0.0928 data: 0.0173 max mem: 8299 +Train: [98] [5400/6250] eta: 0:01:58 lr: 0.000000 grad: 0.1322 (0.1324) loss: 0.8610 (0.8658) time: 0.1243 data: 0.0539 max mem: 8299 +Train: [98] [5500/6250] eta: 0:01:44 lr: 0.000000 grad: 0.1320 (0.1325) loss: 0.8653 (0.8658) time: 0.1387 data: 0.0658 max mem: 8299 +Train: [98] [5600/6250] eta: 0:01:30 lr: 0.000000 grad: 0.1292 (0.1325) loss: 0.8661 (0.8658) time: 0.1372 data: 0.0665 max mem: 8299 +Train: [98] [5700/6250] eta: 0:01:16 lr: 0.000000 grad: 0.1292 (0.1325) loss: 0.8662 (0.8658) time: 0.0871 data: 0.0171 max mem: 8299 +Train: [98] [5800/6250] eta: 0:01:02 lr: 0.000000 grad: 0.1310 (0.1326) loss: 0.8632 (0.8657) time: 0.1260 data: 0.0549 max mem: 8299 +Train: [98] [5900/6250] eta: 0:00:48 lr: 0.000000 grad: 0.1362 (0.1326) loss: 0.8638 (0.8657) time: 0.1224 data: 0.0425 max mem: 8299 +Train: [98] [6000/6250] eta: 0:00:34 lr: 0.000000 grad: 0.1286 (0.1326) loss: 0.8627 (0.8657) time: 0.1260 data: 0.0558 max mem: 8299 +Train: [98] [6100/6250] eta: 0:00:20 lr: 0.000000 grad: 0.1417 (0.1327) loss: 0.8611 (0.8656) time: 0.1143 data: 0.0467 max mem: 8299 +Train: [98] [6200/6250] eta: 0:00:06 lr: 0.000000 grad: 0.1329 (0.1327) loss: 0.8683 (0.8656) time: 0.1279 data: 0.0483 max mem: 8299 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1237 (0.1327) loss: 0.8690 (0.8656) time: 0.1198 data: 0.0470 max mem: 8299 +Train: [98] Total time: 0:14:26 (0.1387 s / it) +Averaged stats: lr: 0.000000 grad: 0.1237 (0.1327) loss: 0.8690 (0.8656) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:05:03 loss: 0.8636 (0.8636) time: 4.9002 data: 4.8714 max mem: 8299 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8600 (0.8633) time: 0.1108 data: 0.0852 max mem: 8299 +Eval (hcp-train-subset): [98] Total time: 0:00:11 (0.1886 s / it) +Averaged stats (hcp-train-subset): loss: 0.8600 (0.8633) +Eval (hcp-val): [98] [ 0/62] eta: 0:05:05 loss: 0.8724 (0.8724) time: 4.9276 data: 4.8984 max mem: 8299 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8725 (0.8741) time: 0.1222 data: 0.0980 max mem: 8299 +Eval (hcp-val): [98] Total time: 0:00:12 (0.1962 s / it) +Averaged stats (hcp-val): loss: 0.8725 (0.8741) +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 8:22:45 lr: 0.000000 grad: 0.1900 (0.1900) loss: 0.8591 (0.8591) time: 4.8264 data: 4.5111 max mem: 8299 +Train: [99] [ 100/6250] eta: 0:18:52 lr: 0.000000 grad: 0.1217 (0.1617) loss: 0.8638 (0.8628) time: 0.1326 data: 0.0331 max mem: 8299 +Train: [99] [ 200/6250] eta: 0:15:41 lr: 0.000000 grad: 0.1037 (0.1471) loss: 0.8702 (0.8649) time: 0.1149 data: 0.0137 max mem: 8299 +Train: [99] [ 300/6250] eta: 0:14:17 lr: 0.000000 grad: 0.1339 (0.1453) loss: 0.8657 (0.8635) time: 0.1260 data: 0.0517 max mem: 8299 +Train: [99] [ 400/6250] eta: 0:13:27 lr: 0.000000 grad: 0.1335 (0.1447) loss: 0.8584 (0.8632) time: 0.1282 data: 0.0478 max mem: 8299 +Train: [99] [ 500/6250] eta: 0:12:46 lr: 0.000000 grad: 0.1370 (0.1438) loss: 0.8589 (0.8626) time: 0.1166 data: 0.0342 max mem: 8299 +Train: [99] [ 600/6250] eta: 0:12:11 lr: 0.000000 grad: 0.1338 (0.1432) loss: 0.8688 (0.8625) time: 0.1113 data: 0.0249 max mem: 8299 +Train: [99] [ 700/6250] eta: 0:11:51 lr: 0.000000 grad: 0.1354 (0.1425) loss: 0.8643 (0.8628) time: 0.1237 data: 0.0389 max mem: 8299 +Train: [99] [ 800/6250] eta: 0:11:26 lr: 0.000000 grad: 0.1221 (0.1421) loss: 0.8662 (0.8630) time: 0.1195 data: 0.0520 max mem: 8299 +Train: [99] [ 900/6250] eta: 0:11:09 lr: 0.000000 grad: 0.1275 (0.1412) loss: 0.8660 (0.8633) time: 0.1125 data: 0.0295 max mem: 8299 +Train: [99] [1000/6250] eta: 0:10:54 lr: 0.000000 grad: 0.1267 (0.1403) loss: 0.8655 (0.8633) time: 0.1041 data: 0.0324 max mem: 8299 +Train: [99] [1100/6250] eta: 0:10:40 lr: 0.000000 grad: 0.1138 (0.1394) loss: 0.8653 (0.8633) time: 0.1212 data: 0.0482 max mem: 8299 +Train: [99] [1200/6250] eta: 0:10:26 lr: 0.000000 grad: 0.1172 (0.1387) loss: 0.8660 (0.8634) time: 0.0864 data: 0.0086 max mem: 8299 +Train: [99] [1300/6250] eta: 0:10:11 lr: 0.000000 grad: 0.1193 (0.1382) loss: 0.8683 (0.8636) time: 0.1200 data: 0.0515 max mem: 8299 +Train: [99] [1400/6250] eta: 0:09:59 lr: 0.000000 grad: 0.1303 (0.1378) loss: 0.8632 (0.8636) time: 0.1175 data: 0.0502 max mem: 8299 +Train: [99] [1500/6250] eta: 0:09:44 lr: 0.000000 grad: 0.1251 (0.1371) loss: 0.8673 (0.8636) time: 0.1254 data: 0.0508 max mem: 8299 +Train: [99] [1600/6250] eta: 0:09:31 lr: 0.000000 grad: 0.1223 (0.1366) loss: 0.8622 (0.8637) time: 0.1272 data: 0.0554 max mem: 8299 +Train: [99] [1700/6250] eta: 0:09:19 lr: 0.000000 grad: 0.1276 (0.1364) loss: 0.8628 (0.8636) time: 0.1203 data: 0.0446 max mem: 8299 +Train: [99] [1800/6250] eta: 0:09:07 lr: 0.000000 grad: 0.1276 (0.1361) loss: 0.8648 (0.8636) time: 0.1247 data: 0.0479 max mem: 8299 +Train: [99] [1900/6250] eta: 0:08:55 lr: 0.000000 grad: 0.1330 (0.1357) loss: 0.8631 (0.8637) time: 0.1310 data: 0.0620 max mem: 8299 +Train: [99] [2000/6250] eta: 0:08:42 lr: 0.000000 grad: 0.1301 (0.1357) loss: 0.8635 (0.8636) time: 0.1239 data: 0.0334 max mem: 8299 +Train: [99] [2100/6250] eta: 0:08:30 lr: 0.000000 grad: 0.1333 (0.1358) loss: 0.8560 (0.8634) time: 0.1390 data: 0.0721 max mem: 8299 +Train: [99] [2200/6250] eta: 0:08:17 lr: 0.000000 grad: 0.1471 (0.1359) loss: 0.8598 (0.8632) time: 0.1245 data: 0.0518 max mem: 8299 +Train: [99] [2300/6250] eta: 0:08:04 lr: 0.000000 grad: 0.1251 (0.1358) loss: 0.8660 (0.8632) time: 0.1123 data: 0.0442 max mem: 8299 +Train: [99] [2400/6250] eta: 0:07:51 lr: 0.000000 grad: 0.1166 (0.1358) loss: 0.8608 (0.8631) time: 0.1098 data: 0.0302 max mem: 8299 +Train: [99] [2500/6250] eta: 0:07:39 lr: 0.000000 grad: 0.1221 (0.1357) loss: 0.8709 (0.8632) time: 0.1172 data: 0.0460 max mem: 8299 +Train: [99] [2600/6250] eta: 0:07:27 lr: 0.000000 grad: 0.1285 (0.1354) loss: 0.8642 (0.8633) time: 0.1319 data: 0.0585 max mem: 8299 +Train: [99] [2700/6250] eta: 0:07:15 lr: 0.000000 grad: 0.1214 (0.1353) loss: 0.8647 (0.8633) time: 0.1104 data: 0.0435 max mem: 8299 +Train: [99] [2800/6250] eta: 0:07:02 lr: 0.000000 grad: 0.1291 (0.1349) loss: 0.8637 (0.8635) time: 0.1253 data: 0.0562 max mem: 8299 +Train: [99] [2900/6250] eta: 0:06:49 lr: 0.000000 grad: 0.1244 (0.1348) loss: 0.8680 (0.8636) time: 0.1071 data: 0.0343 max mem: 8299 +Train: [99] [3000/6250] eta: 0:06:37 lr: 0.000000 grad: 0.1383 (0.1350) loss: 0.8682 (0.8637) time: 0.0981 data: 0.0218 max mem: 8299 +Train: [99] [3100/6250] eta: 0:06:26 lr: 0.000000 grad: 0.1382 (0.1350) loss: 0.8674 (0.8638) time: 0.1370 data: 0.0677 max mem: 8299 +Train: [99] [3200/6250] eta: 0:06:13 lr: 0.000000 grad: 0.1284 (0.1350) loss: 0.8658 (0.8639) time: 0.1187 data: 0.0429 max mem: 8299 +Train: [99] [3300/6250] eta: 0:06:00 lr: 0.000000 grad: 0.1354 (0.1351) loss: 0.8656 (0.8640) time: 0.1029 data: 0.0319 max mem: 8299 +Train: [99] [3400/6250] eta: 0:05:48 lr: 0.000000 grad: 0.1413 (0.1352) loss: 0.8640 (0.8640) time: 0.1190 data: 0.0487 max mem: 8299 +Train: [99] [3500/6250] eta: 0:05:36 lr: 0.000000 grad: 0.1308 (0.1353) loss: 0.8654 (0.8640) time: 0.0987 data: 0.0257 max mem: 8299 +Train: [99] [3600/6250] eta: 0:05:24 lr: 0.000000 grad: 0.1213 (0.1354) loss: 0.8693 (0.8641) time: 0.1117 data: 0.0405 max mem: 8299 +Train: [99] [3700/6250] eta: 0:05:13 lr: 0.000000 grad: 0.1331 (0.1354) loss: 0.8597 (0.8641) time: 0.1309 data: 0.0615 max mem: 8299 +Train: [99] [3800/6250] eta: 0:05:00 lr: 0.000000 grad: 0.1287 (0.1355) loss: 0.8616 (0.8642) time: 0.1250 data: 0.0484 max mem: 8299 +Train: [99] [3900/6250] eta: 0:04:49 lr: 0.000000 grad: 0.1230 (0.1354) loss: 0.8736 (0.8643) time: 0.1245 data: 0.0438 max mem: 8299 +Train: [99] [4000/6250] eta: 0:04:37 lr: 0.000000 grad: 0.1259 (0.1353) loss: 0.8669 (0.8644) time: 0.1475 data: 0.0712 max mem: 8299 +Train: [99] [4100/6250] eta: 0:04:25 lr: 0.000000 grad: 0.1215 (0.1352) loss: 0.8737 (0.8645) time: 0.1247 data: 0.0437 max mem: 8299 +Train: [99] [4200/6250] eta: 0:04:13 lr: 0.000000 grad: 0.1418 (0.1354) loss: 0.8647 (0.8646) time: 0.1284 data: 0.0550 max mem: 8299 +Train: [99] [4300/6250] eta: 0:04:00 lr: 0.000000 grad: 0.1364 (0.1355) loss: 0.8633 (0.8646) time: 0.1115 data: 0.0421 max mem: 8299 +Train: [99] [4400/6250] eta: 0:03:48 lr: 0.000000 grad: 0.1393 (0.1355) loss: 0.8615 (0.8645) time: 0.1163 data: 0.0481 max mem: 8299 +Train: [99] [4500/6250] eta: 0:03:36 lr: 0.000000 grad: 0.1431 (0.1357) loss: 0.8622 (0.8645) time: 0.1319 data: 0.0642 max mem: 8299 +Train: [99] [4600/6250] eta: 0:03:23 lr: 0.000000 grad: 0.1358 (0.1358) loss: 0.8535 (0.8644) time: 0.1383 data: 0.0713 max mem: 8299 +Train: [99] [4700/6250] eta: 0:03:10 lr: 0.000000 grad: 0.1272 (0.1358) loss: 0.8612 (0.8643) time: 0.1256 data: 0.0587 max mem: 8299 +Train: [99] [4800/6250] eta: 0:02:58 lr: 0.000000 grad: 0.1323 (0.1360) loss: 0.8627 (0.8642) time: 0.1240 data: 0.0569 max mem: 8299 +Train: [99] [4900/6250] eta: 0:02:46 lr: 0.000000 grad: 0.1283 (0.1361) loss: 0.8681 (0.8642) time: 0.1330 data: 0.0659 max mem: 8299 +Train: [99] [5000/6250] eta: 0:02:33 lr: 0.000000 grad: 0.1305 (0.1362) loss: 0.8624 (0.8642) time: 0.1207 data: 0.0563 max mem: 8299 +Train: [99] [5100/6250] eta: 0:02:21 lr: 0.000000 grad: 0.1512 (0.1362) loss: 0.8633 (0.8642) time: 0.1255 data: 0.0591 max mem: 8299 +Train: [99] [5200/6250] eta: 0:02:08 lr: 0.000000 grad: 0.1344 (0.1363) loss: 0.8664 (0.8642) time: 0.1097 data: 0.0390 max mem: 8299 +Train: [99] [5300/6250] eta: 0:01:56 lr: 0.000000 grad: 0.1304 (0.1363) loss: 0.8650 (0.8641) time: 0.1284 data: 0.0621 max mem: 8299 +Train: [99] [5400/6250] eta: 0:01:44 lr: 0.000000 grad: 0.1329 (0.1363) loss: 0.8659 (0.8642) time: 0.1215 data: 0.0541 max mem: 8299 +Train: [99] [5500/6250] eta: 0:01:32 lr: 0.000000 grad: 0.1360 (0.1363) loss: 0.8671 (0.8642) time: 0.1190 data: 0.0516 max mem: 8299 +Train: [99] [5600/6250] eta: 0:01:19 lr: 0.000000 grad: 0.1422 (0.1363) loss: 0.8710 (0.8643) time: 0.1187 data: 0.0501 max mem: 8299 +Train: [99] [5700/6250] eta: 0:01:07 lr: 0.000000 grad: 0.1241 (0.1363) loss: 0.8696 (0.8644) time: 0.1271 data: 0.0592 max mem: 8299 +Train: [99] [5800/6250] eta: 0:00:55 lr: 0.000000 grad: 0.1222 (0.1361) loss: 0.8723 (0.8645) time: 0.1148 data: 0.0515 max mem: 8299 +Train: [99] [5900/6250] eta: 0:00:42 lr: 0.000000 grad: 0.1270 (0.1361) loss: 0.8731 (0.8646) time: 0.1231 data: 0.0592 max mem: 8299 +Train: [99] [6000/6250] eta: 0:00:30 lr: 0.000000 grad: 0.1344 (0.1360) loss: 0.8644 (0.8646) time: 0.1149 data: 0.0464 max mem: 8299 +Train: [99] [6100/6250] eta: 0:00:18 lr: 0.000000 grad: 0.1226 (0.1359) loss: 0.8683 (0.8647) time: 0.1211 data: 0.0529 max mem: 8299 +Train: [99] [6200/6250] eta: 0:00:06 lr: 0.000000 grad: 0.1259 (0.1358) loss: 0.8705 (0.8648) time: 0.1139 data: 0.0443 max mem: 8299 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1282 (0.1358) loss: 0.8663 (0.8648) time: 0.1284 data: 0.0571 max mem: 8299 +Train: [99] Total time: 0:12:48 (0.1230 s / it) +Averaged stats: lr: 0.000000 grad: 0.1282 (0.1358) loss: 0.8663 (0.8648) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:03:56 loss: 0.8668 (0.8668) time: 3.8169 data: 3.7883 max mem: 8299 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8610 (0.8633) time: 0.1046 data: 0.0780 max mem: 8299 +Eval (hcp-train-subset): [99] Total time: 0:00:10 (0.1768 s / it) +Averaged stats (hcp-train-subset): loss: 0.8610 (0.8633) +Making plots (hcp-train-subset): example=56 +Eval (hcp-val): [99] [ 0/62] eta: 0:03:43 loss: 0.8722 (0.8722) time: 3.6061 data: 3.5314 max mem: 8299 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8710 (0.8735) time: 0.1071 data: 0.0822 max mem: 8299 +Eval (hcp-val): [99] Total time: 0:00:10 (0.1706 s / it) +Averaged stats (hcp-val): loss: 0.8710 (0.8735) +Making plots (hcp-val): example=50 +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/cross_reg1_pep4/pretrain/checkpoint-00099.pth +done! training time: 1 day, 0:45:34 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..89a02f1deb7fe8eaf190a96e0a1b32786a34a387 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..a2bdb1e9b4827b5a0875a2cbb93ffd719c7698dc --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,9.999999999999999e-05,train,0.5059055118110236,0.02134394962579258,0.48913730124319066,0.021987962276876015,0.504428640941587,0.021174942712385094 +flat_mae,patch,logistic,aabc_age,,9.999999999999999e-05,test,0.36538461538461536,0.06227154697074883,0.33051476654017486,0.05468135161033249,0.3543956043956044,0.06080231895329169 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,train,0.7303149606299213,0.018534427467553547,0.7295839340572436,0.018762312903588235,0.730243637667845,0.018631031008069055 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,test,0.36538461538461536,0.06020974188411274,0.36151368760064406,0.05963039172932883,0.3660714285714286,0.06022285640664828 +flat_mae,patch,logistic,aabc_age,2,9.999999999999999e-05,train,0.4940944881889764,0.019153664289783073,0.4716656725151871,0.019946401936449212,0.4929561948947907,0.018925950919415915 +flat_mae,patch,logistic,aabc_age,2,9.999999999999999e-05,test,0.4807692307692308,0.06038147958540828,0.4575892857142857,0.061274292757061616,0.47435897435897434,0.05956821850009557 +flat_mae,patch,logistic,aabc_age,3,9.999999999999999e-05,train,0.5019685039370079,0.02028882642670481,0.47964019822063464,0.020917455354454818,0.501505833456402,0.02019780506005826 +flat_mae,patch,logistic,aabc_age,3,9.999999999999999e-05,test,0.38461538461538464,0.06409331215284396,0.37353479853479854,0.0673107152909018,0.37957875457875456,0.06377240653703946 +flat_mae,patch,logistic,aabc_age,4,9.999999999999999e-05,train,0.4862204724409449,0.02124477849216664,0.4642686708368303,0.022169028862402927,0.4851092466469374,0.021188394786671314 +flat_mae,patch,logistic,aabc_age,4,9.999999999999999e-05,test,0.5576923076923077,0.06242150099911286,0.504235347985348,0.06603969495289239,0.5455586080586081,0.061572755976112864 +flat_mae,patch,logistic,aabc_age,5,0.000774263682681127,train,0.6003937007874016,0.020890995449412697,0.5965113427593706,0.02129600100429964,0.6004983802880383,0.020825836371913767 +flat_mae,patch,logistic,aabc_age,5,0.000774263682681127,test,0.3076923076923077,0.06264508603820197,0.28638953638953635,0.054221630014512946,0.30219780219780223,0.061249028626816075 +flat_mae,patch,logistic,aabc_age,6,0.000774263682681127,train,0.5846456692913385,0.02047829829896524,0.5770690593750999,0.021013546277306824,0.5847221316521829,0.020367335066105444 +flat_mae,patch,logistic,aabc_age,6,0.000774263682681127,test,0.5576923076923077,0.06841937984563685,0.5584160463192721,0.0690016123457342,0.5560897435897436,0.06847088136652654 +flat_mae,patch,logistic,aabc_age,7,9.999999999999999e-05,train,0.4862204724409449,0.020098070053237438,0.4596082932667951,0.020774773439351617,0.48474171875509453,0.020022689577105308 +flat_mae,patch,logistic,aabc_age,7,9.999999999999999e-05,test,0.4807692307692308,0.054170670463467026,0.4250356125356125,0.05784875003385051,0.47687728937728935,0.05355369820825996 +flat_mae,patch,logistic,aabc_age,8,9.999999999999999e-05,train,0.5019685039370079,0.02025913826808452,0.47332638557808987,0.020921974901182066,0.49978291160726446,0.020133311592925352 +flat_mae,patch,logistic,aabc_age,8,9.999999999999999e-05,test,0.40384615384615385,0.05390484438824316,0.34088669950738915,0.04759603946916128,0.3983516483516484,0.05260278091581552 +flat_mae,patch,logistic,aabc_age,9,9.999999999999999e-05,train,0.4881889763779528,0.01960470971958744,0.4644132714204589,0.020976620688155975,0.48729295689015295,0.019569664111485936 +flat_mae,patch,logistic,aabc_age,9,9.999999999999999e-05,test,0.4807692307692308,0.05965884272086494,0.42133995037220845,0.04847572869434771,0.47115384615384615,0.05795642551766949 +flat_mae,patch,logistic,aabc_age,10,9.999999999999999e-05,train,0.5078740157480315,0.019763032893635995,0.4863963458948791,0.020905092178024113,0.5067339356986817,0.019593651373307222 +flat_mae,patch,logistic,aabc_age,10,9.999999999999999e-05,test,0.36538461538461536,0.06131762056469557,0.3408333333333333,0.05880383646397843,0.36149267399267404,0.06036463418924889 +flat_mae,patch,logistic,aabc_age,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,11,166.81005372000556,test,0.38461538461538464,0.0699162114764447,0.3760143304970891,0.07097004128295395,0.38278388278388276,0.06972501192447234 +flat_mae,patch,logistic,aabc_age,12,9.999999999999999e-05,train,0.5098425196850394,0.019449221759352073,0.48143839871782174,0.01996147605532329,0.5081149822876969,0.01927842985347032 +flat_mae,patch,logistic,aabc_age,12,9.999999999999999e-05,test,0.40384615384615385,0.06184456322103019,0.39352779889864287,0.06223769235434818,0.39880952380952384,0.06113074764501607 +flat_mae,patch,logistic,aabc_age,13,9.999999999999999e-05,train,0.5039370078740157,0.01849871722323139,0.4749293227851947,0.019562971876254342,0.5015814727583435,0.01836230113209632 +flat_mae,patch,logistic,aabc_age,13,9.999999999999999e-05,test,0.4230769230769231,0.05722129522493295,0.3981950844854071,0.061121435954466063,0.42216117216117216,0.05728642623495482 +flat_mae,patch,logistic,aabc_age,14,0.000774263682681127,train,0.5767716535433071,0.02105904886188068,0.5694185510024905,0.02175331287083511,0.5775278870478664,0.021050493214245448 +flat_mae,patch,logistic,aabc_age,14,0.000774263682681127,test,0.4807692307692308,0.061336821088981905,0.4562745098039216,0.062780746046052,0.47435897435897434,0.060551393184067076 +flat_mae,patch,logistic,aabc_age,15,0.000774263682681127,train,0.5885826771653543,0.021285934338947904,0.5846708555543397,0.021654397635381045,0.5889543363975842,0.021298379752043458 +flat_mae,patch,logistic,aabc_age,15,0.000774263682681127,test,0.38461538461538464,0.052893705512473195,0.34926108374384235,0.04317938774851884,0.3804945054945055,0.051827771347068445 +flat_mae,patch,logistic,aabc_age,16,9.999999999999999e-05,train,0.49803149606299213,0.02071786418673008,0.4718117387178109,0.021272659278088673,0.49580064021296955,0.020556221099094503 +flat_mae,patch,logistic,aabc_age,16,9.999999999999999e-05,test,0.3269230769230769,0.06338452203129795,0.32134149375528687,0.06428239021428947,0.3232600732600733,0.0628498815278943 +flat_mae,patch,logistic,aabc_age,17,9.999999999999999e-05,train,0.4881889763779528,0.02062870818997649,0.4635581920779892,0.021595309999551084,0.48767810598228956,0.020532413905316946 +flat_mae,patch,logistic,aabc_age,17,9.999999999999999e-05,test,0.4423076923076923,0.06004646869189614,0.40844941348973607,0.059440752775240704,0.4356684981684982,0.058944310174277204 +flat_mae,patch,logistic,aabc_age,18,9.999999999999999e-05,train,0.5059055118110236,0.020564034958126955,0.4878756913693606,0.02166265192070005,0.5059556060829822,0.020605807434161405 +flat_mae,patch,logistic,aabc_age,18,9.999999999999999e-05,test,0.4807692307692308,0.058533091333578896,0.4188834154351395,0.0496187623151034,0.4697802197802198,0.056966769317070676 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,train,0.9114173228346457,0.0124067255895212,0.9113508954110799,0.012447674748754654,0.9110352347287726,0.01247709888117159 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,test,0.40384615384615385,0.06674568665007899,0.40408026755852844,0.0672549848198668,0.402014652014652,0.06667006335563559 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,train,0.7244094488188977,0.018648596463012986,0.7239163614163615,0.01886686777964629,0.7248479542146076,0.018701638123839744 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,test,0.46153846153846156,0.0602174928878988,0.455106100795756,0.06060392674268266,0.46543040293040294,0.060674741015453296 +flat_mae,patch,logistic,aabc_age,21,9.999999999999999e-05,train,0.49606299212598426,0.020870561112740653,0.4736737346065758,0.021971843553038033,0.4945371881646909,0.020735325649955266 +flat_mae,patch,logistic,aabc_age,21,9.999999999999999e-05,test,0.4423076923076923,0.05878256997226626,0.39615199615199614,0.061542344293316426,0.4384157509157509,0.058295852552716354 +flat_mae,patch,logistic,aabc_age,22,0.000774263682681127,train,0.594488188976378,0.02165760305536004,0.5886817878577627,0.022003077993333366,0.5940324786292002,0.021672094467376845 +flat_mae,patch,logistic,aabc_age,22,0.000774263682681127,test,0.28846153846153844,0.05814356848537092,0.275093808630394,0.053500790776044686,0.2802197802197802,0.05676531130509463 +flat_mae,patch,logistic,aabc_age,23,0.005994842503189409,train,0.7322834645669292,0.019284548057644176,0.7325165867185865,0.019422542385758225,0.7338151073382829,0.01916084508400079 +flat_mae,patch,logistic,aabc_age,23,0.005994842503189409,test,0.4807692307692308,0.058923227555541545,0.4767914653784219,0.05659616541262062,0.4800824175824176,0.05884347283200148 +flat_mae,patch,logistic,aabc_age,24,0.000774263682681127,train,0.5787401574803149,0.02144083210648698,0.5739367581402981,0.022056825077793826,0.5798615573017459,0.021472021929396706 +flat_mae,patch,logistic,aabc_age,24,0.000774263682681127,test,0.4230769230769231,0.06608532900772433,0.4182027649769585,0.06519898500470542,0.4196428571428571,0.06576807025158533 +flat_mae,patch,logistic,aabc_age,25,0.000774263682681127,train,0.5984251968503937,0.02042249320373146,0.593784861495193,0.02085219090725175,0.598649832466738,0.020494935453464442 +flat_mae,patch,logistic,aabc_age,25,0.000774263682681127,test,0.3076923076923077,0.054440062584471594,0.2731667664926842,0.0464700383412188,0.30494505494505497,0.05363858850257645 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,train,0.59251968503937,0.020522749739411483,0.588825634352635,0.02104612516189687,0.5928190132511426,0.020495123031387733 +flat_mae,patch,logistic,aabc_age,26,0.000774263682681127,test,0.4230769230769231,0.0627277389260065,0.4067460317460317,0.0625576973042809,0.4194139194139194,0.06249612838543171 +flat_mae,patch,logistic,aabc_age,27,0.000774263682681127,train,0.5885826771653543,0.02133008627373929,0.5833596614458696,0.02204815804222718,0.5884192272947837,0.021230707710366146 +flat_mae,patch,logistic,aabc_age,27,0.000774263682681127,test,0.34615384615384615,0.06219432944718205,0.3256127450980392,0.060875366441564056,0.3408882783882784,0.061301371743944046 +flat_mae,patch,logistic,aabc_age,28,0.000774263682681127,train,0.5866141732283464,0.02074368277574526,0.5801044644731881,0.02105422386312802,0.5872233831170202,0.02064292522082761 +flat_mae,patch,logistic,aabc_age,28,0.000774263682681127,test,0.4423076923076923,0.06323033642000478,0.4156066634514911,0.06514398039112278,0.43864468864468864,0.06277937232153669 +flat_mae,patch,logistic,aabc_age,29,9.999999999999999e-05,train,0.5118110236220472,0.01964139097845362,0.479610605136921,0.020376972467638126,0.5093784343359756,0.019449814634858696 +flat_mae,patch,logistic,aabc_age,29,9.999999999999999e-05,test,0.3076923076923077,0.06087715586744239,0.2980113636363636,0.05766294981813126,0.30654761904761907,0.060668963305978346 +flat_mae,patch,logistic,aabc_age,30,9.999999999999999e-05,train,0.484251968503937,0.02035241732428317,0.4575008697742219,0.020835077650877668,0.4824580351714363,0.02014418397870094 +flat_mae,patch,logistic,aabc_age,30,9.999999999999999e-05,test,0.46153846153846156,0.06348931792927263,0.4348020434227331,0.06371105691305387,0.4592490842490842,0.06311284502863726 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,train,0.4921259842519685,0.02082458311291065,0.47020088977013563,0.021496679123784824,0.4907224979813537,0.02062995008293008 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,test,0.46153846153846156,0.058376595679064086,0.39741379310344827,0.04829408986750106,0.45192307692307687,0.05675735374772072 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,train,0.718503937007874,0.01962560278892269,0.7192761846809437,0.0196056639466318,0.7197022041124765,0.019566296453932888 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,test,0.4423076923076923,0.06026925531392166,0.4222807017543859,0.06294702042540254,0.4429945054945055,0.06046189209446701 +flat_mae,patch,logistic,aabc_age,33,9.999999999999999e-05,train,0.49803149606299213,0.02024605141268775,0.47746680402930397,0.02119347736172218,0.49573303234245447,0.020147775498237017 +flat_mae,patch,logistic,aabc_age,33,9.999999999999999e-05,test,0.46153846153846156,0.047959471918960515,0.3892249103942652,0.04207475612005249,0.45741758241758246,0.04682509094826972 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,train,0.75,0.01921658140913731,0.7500402238590845,0.019218035729866346,0.7508724292227109,0.019213605432139964 +flat_mae,patch,logistic,aabc_age,34,0.005994842503189409,test,0.2692307692307692,0.05826042076074403,0.2647692484649007,0.054884378209687626,0.26671245421245426,0.05786289079106854 +flat_mae,patch,logistic,aabc_age,35,9.999999999999999e-05,train,0.5118110236220472,0.020356919298074712,0.48610469876091555,0.021887855445221267,0.5100135167792186,0.020237270070035368 +flat_mae,patch,logistic,aabc_age,35,9.999999999999999e-05,test,0.38461538461538464,0.06042869532709532,0.3636814574314574,0.058118651722676704,0.3807234432234432,0.05983318445950297 +flat_mae,patch,logistic,aabc_age,36,0.005994842503189409,train,0.7303149606299213,0.01874106065447495,0.7298872459092459,0.018843733121737573,0.7309963146518244,0.01880003076074826 +flat_mae,patch,logistic,aabc_age,36,0.005994842503189409,test,0.5,0.05891939886090299,0.4831094831094831,0.0618012689507013,0.5070970695970697,0.0590642624969339 +flat_mae,patch,logistic,aabc_age,37,0.000774263682681127,train,0.5767716535433071,0.021550871835732163,0.5722117830147748,0.022184771146927008,0.5775778737180877,0.021632761354719383 +flat_mae,patch,logistic,aabc_age,37,0.000774263682681127,test,0.38461538461538464,0.06570882291050438,0.3810599078341014,0.06640844783537336,0.38118131868131866,0.06556183654633342 +flat_mae,patch,logistic,aabc_age,38,0.000774263682681127,train,0.5964566929133859,0.020587229674437785,0.5891363372972175,0.021297793868198293,0.5954635118884365,0.020540195042121612 +flat_mae,patch,logistic,aabc_age,38,0.000774263682681127,test,0.38461538461538464,0.06447901130917164,0.39492283079239604,0.06343422731979519,0.3839285714285714,0.06443367473900743 +flat_mae,patch,logistic,aabc_age,39,9.999999999999999e-05,train,0.49606299212598426,0.02088739780505877,0.47094609046034397,0.021067787379209484,0.4951399051380063,0.020787405608248252 +flat_mae,patch,logistic,aabc_age,39,9.999999999999999e-05,test,0.4807692307692308,0.05989728634289373,0.44127854903716973,0.06048334567263321,0.4741300366300366,0.05901264953933888 +flat_mae,patch,logistic,aabc_age,40,0.000774263682681127,train,0.594488188976378,0.021381200359462,0.5896844383686489,0.021742888199004575,0.5947851556131794,0.021300846539369547 +flat_mae,patch,logistic,aabc_age,40,0.000774263682681127,test,0.46153846153846156,0.06197794988695052,0.4325962146645258,0.059425936260881496,0.4548992673992674,0.06083475549456195 +flat_mae,patch,logistic,aabc_age,41,9.999999999999999e-05,train,0.5137795275590551,0.019577756474557992,0.49327257652762857,0.020541647684530012,0.5123971737033195,0.019508628861904475 +flat_mae,patch,logistic,aabc_age,41,9.999999999999999e-05,test,0.38461538461538464,0.057220364542208184,0.3503416494517718,0.05681256458818805,0.38209706959706957,0.0566350858738483 +flat_mae,patch,logistic,aabc_age,42,9.999999999999999e-05,train,0.484251968503937,0.02014425008734808,0.46202216907936666,0.020662290649679418,0.4835282533770371,0.020061497158641157 +flat_mae,patch,logistic,aabc_age,42,9.999999999999999e-05,test,0.46153846153846156,0.05592022000955611,0.4133190883190883,0.05879528517956972,0.45627289377289376,0.05509937603952688 +flat_mae,patch,logistic,aabc_age,43,9.999999999999999e-05,train,0.4921259842519685,0.019399319760424954,0.46466755638848417,0.020224946331698936,0.49100767373304766,0.019267015314858586 +flat_mae,patch,logistic,aabc_age,43,9.999999999999999e-05,test,0.5,0.06605174365780729,0.47399626517273574,0.06923072418504925,0.49221611721611724,0.06552317287724678 +flat_mae,patch,logistic,aabc_age,44,9.999999999999999e-05,train,0.49803149606299213,0.020541624471221154,0.4703306882282806,0.02153511237542758,0.496620925067464,0.02037538758102395 +flat_mae,patch,logistic,aabc_age,44,9.999999999999999e-05,test,0.4423076923076923,0.06175772236886129,0.4063223938223939,0.06193462105354696,0.4329212454212454,0.06083034890881154 +flat_mae,patch,logistic,aabc_age,45,9.999999999999999e-05,train,0.49803149606299213,0.019680284465098393,0.46816963613596024,0.01995467074904984,0.49526553111016913,0.019544559190210194 +flat_mae,patch,logistic,aabc_age,45,9.999999999999999e-05,test,0.4423076923076923,0.06077653315424072,0.40341827053402,0.061167389385911236,0.43704212454212454,0.05986503533663126 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,train,0.5885826771653543,0.020186224584288318,0.5811702259688525,0.02087861267670982,0.5878841181919834,0.020236522447987255 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,test,0.46153846153846156,0.06036114193437117,0.45564379699248125,0.062037031861402275,0.459478021978022,0.06035509916688669 +flat_mae,patch,logistic,aabc_age,47,9.999999999999999e-05,train,0.49015748031496065,0.020237407284662407,0.46496565509395493,0.020652850239381296,0.48860639560865304,0.020125082231668263 +flat_mae,patch,logistic,aabc_age,47,9.999999999999999e-05,test,0.38461538461538464,0.05879050913622914,0.3331447963800905,0.04922781751187377,0.37774725274725274,0.05755457106018172 +flat_mae,patch,logistic,aabc_age,48,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,48,0.3593813663804626,test,0.4230769230769231,0.06540185293142624,0.42171277997364953,0.06343194583428498,0.41666666666666663,0.06491441812813603 +flat_mae,patch,logistic,aabc_age,49,9.999999999999999e-05,train,0.5078740157480315,0.01966347283173366,0.4818117710961538,0.0207066332709666,0.5061488399256601,0.01958176461515428 +flat_mae,patch,logistic,aabc_age,49,9.999999999999999e-05,test,0.34615384615384615,0.05661737036651327,0.3176571852322687,0.05615112228790518,0.3450091575091575,0.05647172410394855 +flat_mae,patch,logistic,aabc_age,50,9.999999999999999e-05,train,0.515748031496063,0.02036544534260737,0.48804806177212146,0.02122523889550533,0.5139957881735134,0.02028917351086431 +flat_mae,patch,logistic,aabc_age,50,9.999999999999999e-05,test,0.38461538461538464,0.06294902605804799,0.37707431457431456,0.06409220670737584,0.3823260073260073,0.06285472135375157 +flat_mae,patch,logistic,aabc_age,51,9.999999999999999e-05,train,0.5059055118110236,0.020246051029896288,0.4814096042502757,0.021408656256152174,0.5048354012071601,0.020096655836210637 +flat_mae,patch,logistic,aabc_age,51,9.999999999999999e-05,test,0.40384615384615385,0.06339698348338745,0.37248232162720485,0.061981761064427925,0.39720695970695974,0.06236433975531614 +flat_mae,patch,logistic,aabc_age,52,9.999999999999999e-05,train,0.515748031496063,0.019842627093197618,0.48516542340443153,0.021045015903851997,0.5138958148330709,0.019700536817919723 +flat_mae,patch,logistic,aabc_age,52,9.999999999999999e-05,test,0.3269230769230769,0.05490005712373485,0.271264367816092,0.04763611212723448,0.3173076923076923,0.05320833957259384 +flat_mae,patch,logistic,aabc_age,53,0.000774263682681127,train,0.5846456692913385,0.0222542068157785,0.5817124736153098,0.022793219191502883,0.5862098644198477,0.02221600361245384 +flat_mae,patch,logistic,aabc_age,53,0.000774263682681127,test,0.4807692307692308,0.06231832767731369,0.45563172355516224,0.06526537581795884,0.47298534798534797,0.06192199806071284 +flat_mae,patch,logistic,aabc_age,54,0.000774263682681127,train,0.5984251968503937,0.021871377807864203,0.5953527695083756,0.022310859113128696,0.5993525227804959,0.021894248982181817 +flat_mae,patch,logistic,aabc_age,54,0.000774263682681127,test,0.4230769230769231,0.0669482158796443,0.4113095238095238,0.06883428785792034,0.41964285714285715,0.06693650841188681 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,train,0.75,0.018952078325675668,0.7494155879495277,0.019084114494202376,0.7506548613415319,0.018976532996892743 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,test,0.4230769230769231,0.057241365851078724,0.390530303030303,0.054978121419840834,0.42055860805860806,0.05673344400851 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,train,0.5,0.021127312198352195,0.4821870892730765,0.02152777586134834,0.4987194062398708,0.0210043200139864 +flat_mae,patch,logistic,aabc_age,56,9.999999999999999e-05,test,0.4230769230769231,0.06516791011591319,0.39590964590964595,0.06237083162267443,0.4178113553113553,0.06424317822446857 +flat_mae,patch,logistic,aabc_age,57,9.999999999999999e-05,train,0.4921259842519685,0.021251402159485556,0.46834987958556296,0.022072791735880865,0.49001980766759556,0.021065860275270343 +flat_mae,patch,logistic,aabc_age,57,9.999999999999999e-05,test,0.5,0.05511091559529273,0.4241935483870968,0.04752165265069149,0.4917582417582418,0.05344307842297933 +flat_mae,patch,logistic,aabc_age,58,9.999999999999999e-05,train,0.49606299212598426,0.019972584517489577,0.4685704142548319,0.020973094267505,0.49395209239166915,0.019858127926523167 +flat_mae,patch,logistic,aabc_age,58,9.999999999999999e-05,test,0.36538461538461536,0.052534730693076584,0.33402777777777776,0.05240562308004035,0.3642399267399268,0.05243465172757664 +flat_mae,patch,logistic,aabc_age,59,0.005994842503189409,train,0.7303149606299213,0.019166756252143726,0.7298848421772143,0.019353865173551886,0.7310639225223394,0.019151058750367392 +flat_mae,patch,logistic,aabc_age,59,0.005994842503189409,test,0.34615384615384615,0.06371413598457061,0.3407095735286479,0.06296663731048828,0.3424908424908425,0.0633638099992098 +flat_mae,patch,logistic,aabc_age,60,0.000774263682681127,train,0.6023622047244095,0.02171295214623249,0.5981896083851571,0.02207738566749783,0.6028996584124329,0.02167056865548521 +flat_mae,patch,logistic,aabc_age,60,0.000774263682681127,test,0.4230769230769231,0.0645255327657062,0.41332785987958404,0.06542673287777656,0.4210164835164835,0.06463041258429496 +flat_mae,patch,logistic,aabc_age,61,0.000774263682681127,train,0.594488188976378,0.020819997633155563,0.5882268748713616,0.021715346737629634,0.5946851822727369,0.020835488116216588 +flat_mae,patch,logistic,aabc_age,61,0.000774263682681127,test,0.36538461538461536,0.06417703878874678,0.35027089783281734,0.06782761745291505,0.358974358974359,0.06360896296663432 +flat_mae,patch,logistic,aabc_age,62,0.000774263682681127,train,0.5984251968503937,0.020941327920607863,0.5959549976358777,0.021401007742402355,0.5992349282397595,0.02082835335098809 +flat_mae,patch,logistic,aabc_age,62,0.000774263682681127,test,0.4230769230769231,0.05946072991787827,0.40604395604395604,0.05919800709698063,0.42078754578754574,0.05922505413946471 +flat_mae,patch,logistic,aabc_age,63,9.999999999999999e-05,train,0.5,0.019965427912685053,0.47678659261776585,0.020586606215382733,0.498569446229207,0.01988352102971627 +flat_mae,patch,logistic,aabc_age,63,9.999999999999999e-05,test,0.46153846153846156,0.05962153814395337,0.42016129032258065,0.06084581086576707,0.4521520146520146,0.058790058999060965 +flat_mae,patch,logistic,aabc_age,64,9.999999999999999e-05,train,0.49606299212598426,0.018623857929982397,0.4695749018327112,0.01946984882627292,0.4948223639163849,0.01852337219784993 +flat_mae,patch,logistic,aabc_age,64,9.999999999999999e-05,test,0.38461538461538464,0.05642834645835078,0.32299777530589546,0.04783136028553161,0.3791208791208791,0.055163433883958155 +flat_mae,patch,logistic,aabc_age,65,9.999999999999999e-05,train,0.4940944881889764,0.01952626480026413,0.4719112917005652,0.02057843526722605,0.49230349125125383,0.019434907766711244 +flat_mae,patch,logistic,aabc_age,65,9.999999999999999e-05,test,0.5384615384615384,0.051066495691877274,0.45856273543900317,0.04469701981272529,0.5302197802197802,0.04931050805421362 +flat_mae,patch,logistic,aabc_age,66,9.999999999999999e-05,train,0.5039370078740157,0.02092925531564504,0.478185066534764,0.02187382225382446,0.5027692855046808,0.020727658769824096 +flat_mae,patch,logistic,aabc_age,66,9.999999999999999e-05,test,0.46153846153846156,0.05913542526024532,0.42581786030061886,0.05770983488621251,0.45352564102564097,0.058137222503618684 +flat_mae,patch,logistic,aabc_age,67,9.999999999999999e-05,train,0.484251968503937,0.02126658394136644,0.4544219924285804,0.02161325103322729,0.4821904806200361,0.021029391693833117 +flat_mae,patch,logistic,aabc_age,67,9.999999999999999e-05,test,0.4423076923076923,0.058330876251436126,0.37395833333333334,0.0503321404556629,0.43543956043956045,0.056935036491851505 +flat_mae,patch,logistic,aabc_age,68,9.999999999999999e-05,train,0.4822834645669291,0.019512735674264304,0.45736454410398786,0.019956458081755557,0.4804918928093995,0.019398997690648522 +flat_mae,patch,logistic,aabc_age,68,9.999999999999999e-05,test,0.5192307692307693,0.058755284289608044,0.46264068592697627,0.06162172771167571,0.512591575091575,0.05777604362747846 +flat_mae,patch,logistic,aabc_age,69,9.999999999999999e-05,train,0.5039370078740157,0.019636347258904015,0.48147082671876473,0.020290626795481045,0.5028692588451233,0.019503970070288437 +flat_mae,patch,logistic,aabc_age,69,9.999999999999999e-05,test,0.4230769230769231,0.05895435000587645,0.37103174603174605,0.05037330955192419,0.41346153846153844,0.057338641511718524 +flat_mae,patch,logistic,aabc_age,70,9.999999999999999e-05,train,0.5,0.020813296624673194,0.475126009240166,0.021906596274795506,0.4983018916778068,0.020678340376983472 +flat_mae,patch,logistic,aabc_age,70,9.999999999999999e-05,test,0.34615384615384615,0.05965397014320299,0.3018181818181818,0.05106983110826969,0.34065934065934067,0.05851420802468361 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,train,0.7362204724409449,0.018298431194098807,0.7358082777333,0.018464266170219106,0.7363919981050617,0.018305336139035445 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,test,0.3269230769230769,0.06178311942718533,0.3278439153439153,0.060203609868031464,0.3289835164835165,0.06219615821307459 +flat_mae,patch,logistic,aabc_age,72,9.999999999999999e-05,train,0.49015748031496065,0.01912384463027418,0.46281941591710474,0.02065569625291287,0.4881212731760739,0.01902412793116796 +flat_mae,patch,logistic,aabc_age,72,9.999999999999999e-05,test,0.5576923076923077,0.05216757250727481,0.49789915966386555,0.056400909970865234,0.5510531135531136,0.05111390855110268 +flat_mae,patch,logistic,aabc_age,73,9.999999999999999e-05,train,0.5059055118110236,0.020779197856272677,0.4824338915391741,0.022143570774578635,0.5046678199962025,0.02069194798500894 +flat_mae,patch,logistic,aabc_age,73,9.999999999999999e-05,test,0.46153846153846156,0.057863847539469805,0.41425318514502574,0.06138531123608081,0.4548992673992674,0.057027270992506464 +flat_mae,patch,logistic,aabc_age,74,9.999999999999999e-05,train,0.5,0.02009016928076524,0.4713212236652544,0.02092186530088822,0.4986370540997221,0.01993625344794184 +flat_mae,patch,logistic,aabc_age,74,9.999999999999999e-05,test,0.4230769230769231,0.0664826800419638,0.3848985645426135,0.06695962245621347,0.41781135531135527,0.06571534578057799 +flat_mae,patch,logistic,aabc_age,75,9.999999999999999e-05,train,0.4921259842519685,0.020002217931455606,0.46736568296999825,0.020677206312509275,0.491760350717027,0.019907476719662493 +flat_mae,patch,logistic,aabc_age,75,9.999999999999999e-05,test,0.4807692307692308,0.06228483673875981,0.4184321238073774,0.05329952135825774,0.4684065934065934,0.06083676076163657 +flat_mae,patch,logistic,aabc_age,76,0.000774263682681127,train,0.5964566929133859,0.021618532540898763,0.5938875602810902,0.021934199352269593,0.5963485276827858,0.021613778804634387 +flat_mae,patch,logistic,aabc_age,76,0.000774263682681127,test,0.40384615384615385,0.06884614310270651,0.4029610622352558,0.06948705086980891,0.402014652014652,0.06884147112772951 +flat_mae,patch,logistic,aabc_age,77,9.999999999999999e-05,train,0.5059055118110236,0.0203715605808922,0.48130342511969776,0.02111821986095189,0.5048354012071601,0.020192571782190794 +flat_mae,patch,logistic,aabc_age,77,9.999999999999999e-05,test,0.36538461538461536,0.061769410383875276,0.3439278937381404,0.05939048785263411,0.361492673992674,0.06097350005985635 +flat_mae,patch,logistic,aabc_age,78,9.999999999999999e-05,train,0.484251968503937,0.019526057219362566,0.4573254782612392,0.02031666465026355,0.4825080218416576,0.01944172383564297 +flat_mae,patch,logistic,aabc_age,78,9.999999999999999e-05,test,0.5,0.061631792207032944,0.4613844613844613,0.062195307339337286,0.4906135531135531,0.060702306020101134 +flat_mae,patch,logistic,aabc_age,79,9.999999999999999e-05,train,0.5078740157480315,0.020636706223312082,0.48296682675287295,0.021867444066386715,0.5066339623582392,0.020536923776377218 +flat_mae,patch,logistic,aabc_age,79,9.999999999999999e-05,test,0.46153846153846156,0.059627182455436925,0.41539682539682543,0.06262447165569378,0.45627289377289376,0.0587582974405637 +flat_mae,patch,logistic,aabc_age,80,9.999999999999999e-05,train,0.49803149606299213,0.020602733106197896,0.47837068860743415,0.021549659715129853,0.4971384129699705,0.02047133550014516 +flat_mae,patch,logistic,aabc_age,80,9.999999999999999e-05,test,0.38461538461538464,0.05500773210845887,0.3391941391941392,0.046323318572941675,0.3791208791208791,0.05380782135239243 +flat_mae,patch,logistic,aabc_age,81,0.000774263682681127,train,0.6082677165354331,0.021276263707681257,0.6058151329925722,0.021536678431542916,0.6084453018763343,0.02129258743928813 +flat_mae,patch,logistic,aabc_age,81,0.000774263682681127,test,0.28846153846153844,0.05684884713095195,0.2859694989106754,0.05507328104685769,0.2859432234432234,0.0566416506303228 +flat_mae,patch,logistic,aabc_age,82,9.999999999999999e-05,train,0.49015748031496065,0.020293360838978546,0.4655788267114094,0.020922775637206667,0.4890915180412322,0.020176311869790447 +flat_mae,patch,logistic,aabc_age,82,9.999999999999999e-05,test,0.4807692307692308,0.06299331936025969,0.46875,0.06531918619849714,0.4773351648351648,0.06257073335785185 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,train,0.7539370078740157,0.019286762674394803,0.7542472834553823,0.019309126276596453,0.7543019703139116,0.01936049588831668 +flat_mae,patch,logistic,aabc_age,83,0.005994842503189409,test,0.3269230769230769,0.06251409308563571,0.3105555555555556,0.06205092842745719,0.326007326007326,0.06247179544471641 +flat_mae,patch,logistic,aabc_age,84,9.999999999999999e-05,train,0.49606299212598426,0.02049968621648316,0.4695811026230078,0.021173045445015568,0.4944372148242483,0.02030502973534277 +flat_mae,patch,logistic,aabc_age,84,9.999999999999999e-05,test,0.4423076923076923,0.0542331559758474,0.37589285714285714,0.049170340999460556,0.4340659340659341,0.05258475219305428 +flat_mae,patch,logistic,aabc_age,85,0.000774263682681127,train,0.594488188976378,0.021651053543332233,0.5919599020316075,0.022099703456295867,0.594182438639864,0.021642773017497986 +flat_mae,patch,logistic,aabc_age,85,0.000774263682681127,test,0.4807692307692308,0.05845500975691026,0.44364091790562377,0.063904953710719,0.4771062271062271,0.057788641662707266 +flat_mae,patch,logistic,aabc_age,86,0.000774263682681127,train,0.6003937007874016,0.020953012970871404,0.5973108921008415,0.021399582114541033,0.6012510572720177,0.021044474181275044 +flat_mae,patch,logistic,aabc_age,86,0.000774263682681127,test,0.4807692307692308,0.06418372298221713,0.450890006385696,0.06733591961263247,0.47710622710622713,0.06385792774509234 +flat_mae,patch,logistic,aabc_age,87,9.999999999999999e-05,train,0.4940944881889764,0.020290921503051326,0.46976117904341586,0.02092544332218383,0.49268864034339044,0.020215947759301977 +flat_mae,patch,logistic,aabc_age,87,9.999999999999999e-05,test,0.4423076923076923,0.05518259094311599,0.384012539184953,0.046184045744934434,0.4340659340659341,0.05377687682995685 +flat_mae,patch,logistic,aabc_age,88,0.000774263682681127,train,0.6082677165354331,0.020481325676562124,0.6031728462555033,0.021086202682987488,0.6083953152061128,0.020545781988889258 +flat_mae,patch,logistic,aabc_age,88,0.000774263682681127,test,0.28846153846153844,0.05749035164742323,0.2855911330049261,0.05294623559668663,0.28731684981684985,0.05717742692280119 +flat_mae,patch,logistic,aabc_age,89,9.999999999999999e-05,train,0.49803149606299213,0.02043548868313149,0.4721625155234584,0.021022497042904195,0.4968884796188642,0.020287626802211606 +flat_mae,patch,logistic,aabc_age,89,9.999999999999999e-05,test,0.4230769230769231,0.06372178572773492,0.3845494663382594,0.06396153594809265,0.4164377289377289,0.06287311243703485 +flat_mae,patch,logistic,aabc_age,90,9.999999999999999e-05,train,0.4881889763779528,0.01918656224414216,0.46535495506973823,0.02024258372974199,0.4866402532466162,0.0191752220568202 +flat_mae,patch,logistic,aabc_age,90,9.999999999999999e-05,test,0.5,0.05101993751141448,0.4597542242703533,0.053643671351490535,0.4961080586080586,0.05030363179759492 +flat_mae,patch,logistic,aabc_age,91,9.999999999999999e-05,train,0.5078740157480315,0.020272941880357304,0.4850246468859608,0.021190700749565916,0.5064663811472816,0.02015388719904113 +flat_mae,patch,logistic,aabc_age,91,9.999999999999999e-05,test,0.40384615384615385,0.060736834110377204,0.37515573506952815,0.06363866774464101,0.40293040293040294,0.06052250034518828 +flat_mae,patch,logistic,aabc_age,92,9.999999999999999e-05,train,0.49606299212598426,0.019245735509371174,0.46630255641454266,0.0199886309968936,0.49346696995909,0.01907009631846962 +flat_mae,patch,logistic,aabc_age,92,9.999999999999999e-05,test,0.4230769230769231,0.04933888369011791,0.35,0.04385040846481775,0.41895604395604397,0.04806392006262094 +flat_mae,patch,logistic,aabc_age,93,9.999999999999999e-05,train,0.5,0.019017133269836322,0.4765318086088405,0.02048457997251009,0.4992221498727438,0.01896619575843789 +flat_mae,patch,logistic,aabc_age,93,9.999999999999999e-05,test,0.46153846153846156,0.06431427091856816,0.4337973137973138,0.0676537617291445,0.45650183150183155,0.06380020582851925 +flat_mae,patch,logistic,aabc_age,94,9.999999999999999e-05,train,0.49015748031496065,0.02021644917906294,0.461382398795998,0.021101139468473702,0.48872399014938944,0.020046508406245563 +flat_mae,patch,logistic,aabc_age,94,9.999999999999999e-05,test,0.38461538461538464,0.0635177373540642,0.37503498199593277,0.06300010508328333,0.38095238095238093,0.06294466935086762 +flat_mae,patch,logistic,aabc_age,95,9.999999999999999e-05,train,0.5019685039370079,0.019783947970746243,0.47892506592931605,0.02074836496384494,0.5001504394991072,0.019697599851269388 +flat_mae,patch,logistic,aabc_age,95,9.999999999999999e-05,test,0.4230769230769231,0.05973580889136202,0.3759090909090909,0.05041904384039932,0.41483516483516486,0.058297762571809915 +flat_mae,patch,logistic,aabc_age,96,9.999999999999999e-05,train,0.4881889763779528,0.019857706895738143,0.46173097409534436,0.020599866937339086,0.48675784778735265,0.0196439682578789 +flat_mae,patch,logistic,aabc_age,96,9.999999999999999e-05,test,0.6153846153846154,0.05806260648807758,0.5907631421744325,0.06367602471177458,0.6078296703296704,0.05787854679329393 +flat_mae,patch,logistic,aabc_age,97,9.999999999999999e-05,train,0.5019685039370079,0.020715688083659336,0.47626607011487054,0.02196332392134213,0.5001004528288859,0.020581173856232423 +flat_mae,patch,logistic,aabc_age,97,9.999999999999999e-05,test,0.40384615384615385,0.062484211023417224,0.37820263975155277,0.06279048925561488,0.3985805860805861,0.0616452158902816 +flat_mae,patch,logistic,aabc_age,98,0.000774263682681127,train,0.59251968503937,0.020354141853248974,0.5901283766852268,0.020746763873422978,0.593136554472764,0.020317126260022418 +flat_mae,patch,logistic,aabc_age,98,0.000774263682681127,test,0.38461538461538464,0.06045286441987714,0.35666226498145004,0.05915458872101264,0.37934981684981683,0.05961772116045624 +flat_mae,patch,logistic,aabc_age,99,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,99,2.782559402207126,test,0.3269230769230769,0.06551763618208134,0.33327228327228325,0.06611447651334895,0.32623626373626374,0.06591228243857586 +flat_mae,patch,logistic,aabc_age,100,0.000774263682681127,train,0.6003937007874016,0.019601442968137147,0.594163505416654,0.020158759322085412,0.6017038142346693,0.019571337739303564 +flat_mae,patch,logistic,aabc_age,100,0.000774263682681127,test,0.36538461538461536,0.06169848185103013,0.35137788248732776,0.05689596287436201,0.3587454212454213,0.06058495752122709 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..4de0490db7b2e8b044135c832d8f250b2843ff28 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:45:45 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:21:34 time: 5.6778 data: 4.5316 max mem: 3205 +extract (train) [ 20/228] eta: 0:01:46 time: 0.2526 data: 0.0877 max mem: 3581 +extract (train) [ 40/228] eta: 0:01:10 time: 0.2335 data: 0.0822 max mem: 3581 +extract (train) [ 60/228] eta: 0:00:55 time: 0.2437 data: 0.0870 max mem: 3581 +extract (train) [ 80/228] eta: 0:00:45 time: 0.2180 data: 0.0731 max mem: 3581 +extract (train) [100/228] eta: 0:00:36 time: 0.2215 data: 0.0751 max mem: 3581 +extract (train) [120/228] eta: 0:00:29 time: 0.2254 data: 0.0774 max mem: 3581 +extract (train) [140/228] eta: 0:00:23 time: 0.2377 data: 0.0859 max mem: 3581 +extract (train) [160/228] eta: 0:00:18 time: 0.2275 data: 0.0786 max mem: 3581 +extract (train) [180/228] eta: 0:00:12 time: 0.1966 data: 0.0613 max mem: 3581 +extract (train) [200/228] eta: 0:00:07 time: 0.2271 data: 0.0776 max mem: 3581 +extract (train) [220/228] eta: 0:00:01 time: 0.1899 data: 0.0584 max mem: 3581 +extract (train) [227/228] eta: 0:00:00 time: 0.1844 data: 0.0567 max mem: 3581 +extract (train) Total time: 0:00:56 (0.2497 s / it) +extract (validation) [ 0/27] eta: 0:02:12 time: 4.8906 data: 4.6724 max mem: 3581 +extract (validation) [20/27] eta: 0:00:03 time: 0.2086 data: 0.0698 max mem: 3581 +extract (validation) [26/27] eta: 0:00:00 time: 0.1938 data: 0.0604 max mem: 3581 +extract (validation) Total time: 0:00:10 (0.3879 s / it) +extract (test) [ 0/26] eta: 0:02:03 time: 4.7611 data: 4.6206 max mem: 3581 +extract (test) [20/26] eta: 0:00:02 time: 0.1971 data: 0.0636 max mem: 3581 +extract (test) [25/26] eta: 0:00:00 time: 0.1957 data: 0.0629 max mem: 3581 +extract (test) Total time: 0:00:10 (0.3885 s / it) +feature extraction time: 0:01:17 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.0001 | train | 0.50591 | 0.021344 | 0.48914 | 0.021988 | 0.50443 | 0.021175 | +| flat_mae | patch | logistic | aabc_age | | 0.0001 | test | 0.36538 | 0.062272 | 0.33051 | 0.054681 | 0.3544 | 0.060802 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06020974188411274, "f1": 0.36151368760064406, "f1_std": 0.05963039172932883, "bacc": 0.3660714285714286, "bacc_std": 0.06022285640664828} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06038147958540828, "f1": 0.4575892857142857, "f1_std": 0.061274292757061616, "bacc": 0.47435897435897434, "bacc_std": 0.05956821850009557} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06409331215284396, "f1": 0.37353479853479854, "f1_std": 0.0673107152909018, "bacc": 0.37957875457875456, "bacc_std": 0.06377240653703946} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06242150099911286, "f1": 0.504235347985348, "f1_std": 0.06603969495289239, "bacc": 0.5455586080586081, "bacc_std": 0.061572755976112864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.000774263682681127, "split": "test", "acc": 0.3076923076923077, "acc_std": 0.06264508603820197, "f1": 0.28638953638953635, "f1_std": 0.054221630014512946, "bacc": 0.30219780219780223, "bacc_std": 0.061249028626816075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.000774263682681127, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06841937984563685, "f1": 0.5584160463192721, "f1_std": 0.0690016123457342, "bacc": 0.5560897435897436, "bacc_std": 0.06847088136652654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.054170670463467026, "f1": 0.4250356125356125, "f1_std": 0.05784875003385051, "bacc": 0.47687728937728935, "bacc_std": 0.05355369820825996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05390484438824316, "f1": 0.34088669950738915, "f1_std": 0.04759603946916128, "bacc": 0.3983516483516484, "bacc_std": 0.05260278091581552} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05965884272086494, "f1": 0.42133995037220845, "f1_std": 0.04847572869434771, "bacc": 0.47115384615384615, "bacc_std": 0.05795642551766949} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06131762056469557, "f1": 0.3408333333333333, "f1_std": 0.05880383646397843, "bacc": 0.36149267399267404, "bacc_std": 0.06036463418924889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.0699162114764447, "f1": 0.3760143304970891, "f1_std": 0.07097004128295395, "bacc": 0.38278388278388276, "bacc_std": 0.06972501192447234} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06184456322103019, "f1": 0.39352779889864287, "f1_std": 0.06223769235434818, "bacc": 0.39880952380952384, "bacc_std": 0.06113074764501607} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05722129522493295, "f1": 0.3981950844854071, "f1_std": 0.061121435954466063, "bacc": 0.42216117216117216, "bacc_std": 0.05728642623495482} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.061336821088981905, "f1": 0.4562745098039216, "f1_std": 0.062780746046052, "bacc": 0.47435897435897434, "bacc_std": 0.060551393184067076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.052893705512473195, "f1": 0.34926108374384235, "f1_std": 0.04317938774851884, "bacc": 0.3804945054945055, "bacc_std": 0.051827771347068445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06338452203129795, "f1": 0.32134149375528687, "f1_std": 0.06428239021428947, "bacc": 0.3232600732600733, "bacc_std": 0.0628498815278943} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06004646869189614, "f1": 0.40844941348973607, "f1_std": 0.059440752775240704, "bacc": 0.4356684981684982, "bacc_std": 0.058944310174277204} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.058533091333578896, "f1": 0.4188834154351395, "f1_std": 0.0496187623151034, "bacc": 0.4697802197802198, "bacc_std": 0.056966769317070676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06674568665007899, "f1": 0.40408026755852844, "f1_std": 0.0672549848198668, "bacc": 0.402014652014652, "bacc_std": 0.06667006335563559} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0602174928878988, "f1": 0.455106100795756, "f1_std": 0.06060392674268266, "bacc": 0.46543040293040294, "bacc_std": 0.060674741015453296} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05878256997226626, "f1": 0.39615199615199614, "f1_std": 0.061542344293316426, "bacc": 0.4384157509157509, "bacc_std": 0.058295852552716354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.000774263682681127, "split": "test", "acc": 0.28846153846153844, "acc_std": 0.05814356848537092, "f1": 0.275093808630394, "f1_std": 0.053500790776044686, "bacc": 0.2802197802197802, "bacc_std": 0.05676531130509463} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.058923227555541545, "f1": 0.4767914653784219, "f1_std": 0.05659616541262062, "bacc": 0.4800824175824176, "bacc_std": 0.05884347283200148} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06608532900772433, "f1": 0.4182027649769585, "f1_std": 0.06519898500470542, "bacc": 0.4196428571428571, "bacc_std": 0.06576807025158533} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 0.000774263682681127, "split": "test", "acc": 0.3076923076923077, "acc_std": 0.054440062584471594, "f1": 0.2731667664926842, "f1_std": 0.0464700383412188, "bacc": 0.30494505494505497, "bacc_std": 0.05363858850257645} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0627277389260065, "f1": 0.4067460317460317, "f1_std": 0.0625576973042809, "bacc": 0.4194139194139194, "bacc_std": 0.06249612838543171} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.000774263682681127, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06219432944718205, "f1": 0.3256127450980392, "f1_std": 0.060875366441564056, "bacc": 0.3408882783882784, "bacc_std": 0.061301371743944046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06323033642000478, "f1": 0.4156066634514911, "f1_std": 0.06514398039112278, "bacc": 0.43864468864468864, "bacc_std": 0.06277937232153669} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3076923076923077, "acc_std": 0.06087715586744239, "f1": 0.2980113636363636, "f1_std": 0.05766294981813126, "bacc": 0.30654761904761907, "bacc_std": 0.060668963305978346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06348931792927263, "f1": 0.4348020434227331, "f1_std": 0.06371105691305387, "bacc": 0.4592490842490842, "bacc_std": 0.06311284502863726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.058376595679064086, "f1": 0.39741379310344827, "f1_std": 0.04829408986750106, "bacc": 0.45192307692307687, "bacc_std": 0.05675735374772072} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06026925531392166, "f1": 0.4222807017543859, "f1_std": 0.06294702042540254, "bacc": 0.4429945054945055, "bacc_std": 0.06046189209446701} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.047959471918960515, "f1": 0.3892249103942652, "f1_std": 0.04207475612005249, "bacc": 0.45741758241758246, "bacc_std": 0.04682509094826972} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.2692307692307692, "acc_std": 0.05826042076074403, "f1": 0.2647692484649007, "f1_std": 0.054884378209687626, "bacc": 0.26671245421245426, "bacc_std": 0.05786289079106854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06042869532709532, "f1": 0.3636814574314574, "f1_std": 0.058118651722676704, "bacc": 0.3807234432234432, "bacc_std": 0.05983318445950297} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.05891939886090299, "f1": 0.4831094831094831, "f1_std": 0.0618012689507013, "bacc": 0.5070970695970697, "bacc_std": 0.0590642624969339} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06570882291050438, "f1": 0.3810599078341014, "f1_std": 0.06640844783537336, "bacc": 0.38118131868131866, "bacc_std": 0.06556183654633342} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06447901130917164, "f1": 0.39492283079239604, "f1_std": 0.06343422731979519, "bacc": 0.3839285714285714, "bacc_std": 0.06443367473900743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05989728634289373, "f1": 0.44127854903716973, "f1_std": 0.06048334567263321, "bacc": 0.4741300366300366, "bacc_std": 0.05901264953933888} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06197794988695052, "f1": 0.4325962146645258, "f1_std": 0.059425936260881496, "bacc": 0.4548992673992674, "bacc_std": 0.06083475549456195} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.057220364542208184, "f1": 0.3503416494517718, "f1_std": 0.05681256458818805, "bacc": 0.38209706959706957, "bacc_std": 0.0566350858738483} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05592022000955611, "f1": 0.4133190883190883, "f1_std": 0.05879528517956972, "bacc": 0.45627289377289376, "bacc_std": 0.05509937603952688} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.06605174365780729, "f1": 0.47399626517273574, "f1_std": 0.06923072418504925, "bacc": 0.49221611721611724, "bacc_std": 0.06552317287724678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06175772236886129, "f1": 0.4063223938223939, "f1_std": 0.06193462105354696, "bacc": 0.4329212454212454, "bacc_std": 0.06083034890881154} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06077653315424072, "f1": 0.40341827053402, "f1_std": 0.061167389385911236, "bacc": 0.43704212454212454, "bacc_std": 0.05986503533663126} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06036114193437117, "f1": 0.45564379699248125, "f1_std": 0.062037031861402275, "bacc": 0.459478021978022, "bacc_std": 0.06035509916688669} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.05879050913622914, "f1": 0.3331447963800905, "f1_std": 0.04922781751187377, "bacc": 0.37774725274725274, "bacc_std": 0.05755457106018172} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06540185293142624, "f1": 0.42171277997364953, "f1_std": 0.06343194583428498, "bacc": 0.41666666666666663, "bacc_std": 0.06491441812813603} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.05661737036651327, "f1": 0.3176571852322687, "f1_std": 0.05615112228790518, "bacc": 0.3450091575091575, "bacc_std": 0.05647172410394855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06294902605804799, "f1": 0.37707431457431456, "f1_std": 0.06409220670737584, "bacc": 0.3823260073260073, "bacc_std": 0.06285472135375157} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06339698348338745, "f1": 0.37248232162720485, "f1_std": 0.061981761064427925, "bacc": 0.39720695970695974, "bacc_std": 0.06236433975531614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.05490005712373485, "f1": 0.271264367816092, "f1_std": 0.04763611212723448, "bacc": 0.3173076923076923, "bacc_std": 0.05320833957259384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06231832767731369, "f1": 0.45563172355516224, "f1_std": 0.06526537581795884, "bacc": 0.47298534798534797, "bacc_std": 0.06192199806071284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0669482158796443, "f1": 0.4113095238095238, "f1_std": 0.06883428785792034, "bacc": 0.41964285714285715, "bacc_std": 0.06693650841188681} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.057241365851078724, "f1": 0.390530303030303, "f1_std": 0.054978121419840834, "bacc": 0.42055860805860806, "bacc_std": 0.05673344400851} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06516791011591319, "f1": 0.39590964590964595, "f1_std": 0.06237083162267443, "bacc": 0.4178113553113553, "bacc_std": 0.06424317822446857} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.05511091559529273, "f1": 0.4241935483870968, "f1_std": 0.04752165265069149, "bacc": 0.4917582417582418, "bacc_std": 0.05344307842297933} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.052534730693076584, "f1": 0.33402777777777776, "f1_std": 0.05240562308004035, "bacc": 0.3642399267399268, "bacc_std": 0.05243465172757664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06371413598457061, "f1": 0.3407095735286479, "f1_std": 0.06296663731048828, "bacc": 0.3424908424908425, "bacc_std": 0.0633638099992098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0645255327657062, "f1": 0.41332785987958404, "f1_std": 0.06542673287777656, "bacc": 0.4210164835164835, "bacc_std": 0.06463041258429496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.000774263682681127, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06417703878874678, "f1": 0.35027089783281734, "f1_std": 0.06782761745291505, "bacc": 0.358974358974359, "bacc_std": 0.06360896296663432} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05946072991787827, "f1": 0.40604395604395604, "f1_std": 0.05919800709698063, "bacc": 0.42078754578754574, "bacc_std": 0.05922505413946471} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05962153814395337, "f1": 0.42016129032258065, "f1_std": 0.06084581086576707, "bacc": 0.4521520146520146, "bacc_std": 0.058790058999060965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.05642834645835078, "f1": 0.32299777530589546, "f1_std": 0.04783136028553161, "bacc": 0.3791208791208791, "bacc_std": 0.055163433883958155} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.051066495691877274, "f1": 0.45856273543900317, "f1_std": 0.04469701981272529, "bacc": 0.5302197802197802, "bacc_std": 0.04931050805421362} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05913542526024532, "f1": 0.42581786030061886, "f1_std": 0.05770983488621251, "bacc": 0.45352564102564097, "bacc_std": 0.058137222503618684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.058330876251436126, "f1": 0.37395833333333334, "f1_std": 0.0503321404556629, "bacc": 0.43543956043956045, "bacc_std": 0.056935036491851505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.058755284289608044, "f1": 0.46264068592697627, "f1_std": 0.06162172771167571, "bacc": 0.512591575091575, "bacc_std": 0.05777604362747846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05895435000587645, "f1": 0.37103174603174605, "f1_std": 0.05037330955192419, "bacc": 0.41346153846153844, "bacc_std": 0.057338641511718524} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.05965397014320299, "f1": 0.3018181818181818, "f1_std": 0.05106983110826969, "bacc": 0.34065934065934067, "bacc_std": 0.05851420802468361} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06178311942718533, "f1": 0.3278439153439153, "f1_std": 0.060203609868031464, "bacc": 0.3289835164835165, "bacc_std": 0.06219615821307459} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05216757250727481, "f1": 0.49789915966386555, "f1_std": 0.056400909970865234, "bacc": 0.5510531135531136, "bacc_std": 0.05111390855110268} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.057863847539469805, "f1": 0.41425318514502574, "f1_std": 0.06138531123608081, "bacc": 0.4548992673992674, "bacc_std": 0.057027270992506464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0664826800419638, "f1": 0.3848985645426135, "f1_std": 0.06695962245621347, "bacc": 0.41781135531135527, "bacc_std": 0.06571534578057799} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06228483673875981, "f1": 0.4184321238073774, "f1_std": 0.05329952135825774, "bacc": 0.4684065934065934, "bacc_std": 0.06083676076163657} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06884614310270651, "f1": 0.4029610622352558, "f1_std": 0.06948705086980891, "bacc": 0.402014652014652, "bacc_std": 0.06884147112772951} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.061769410383875276, "f1": 0.3439278937381404, "f1_std": 0.05939048785263411, "bacc": 0.361492673992674, "bacc_std": 0.06097350005985635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.061631792207032944, "f1": 0.4613844613844613, "f1_std": 0.062195307339337286, "bacc": 0.4906135531135531, "bacc_std": 0.060702306020101134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.059627182455436925, "f1": 0.41539682539682543, "f1_std": 0.06262447165569378, "bacc": 0.45627289377289376, "bacc_std": 0.0587582974405637} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.05500773210845887, "f1": 0.3391941391941392, "f1_std": 0.046323318572941675, "bacc": 0.3791208791208791, "bacc_std": 0.05380782135239243} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 0.000774263682681127, "split": "test", "acc": 0.28846153846153844, "acc_std": 0.05684884713095195, "f1": 0.2859694989106754, "f1_std": 0.05507328104685769, "bacc": 0.2859432234432234, "bacc_std": 0.0566416506303228} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06299331936025969, "f1": 0.46875, "f1_std": 0.06531918619849714, "bacc": 0.4773351648351648, "bacc_std": 0.06257073335785185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06251409308563571, "f1": 0.3105555555555556, "f1_std": 0.06205092842745719, "bacc": 0.326007326007326, "bacc_std": 0.06247179544471641} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0542331559758474, "f1": 0.37589285714285714, "f1_std": 0.049170340999460556, "bacc": 0.4340659340659341, "bacc_std": 0.05258475219305428} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05845500975691026, "f1": 0.44364091790562377, "f1_std": 0.063904953710719, "bacc": 0.4771062271062271, "bacc_std": 0.057788641662707266} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06418372298221713, "f1": 0.450890006385696, "f1_std": 0.06733591961263247, "bacc": 0.47710622710622713, "bacc_std": 0.06385792774509234} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05518259094311599, "f1": 0.384012539184953, "f1_std": 0.046184045744934434, "bacc": 0.4340659340659341, "bacc_std": 0.05377687682995685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.28846153846153844, "acc_std": 0.05749035164742323, "f1": 0.2855911330049261, "f1_std": 0.05294623559668663, "bacc": 0.28731684981684985, "bacc_std": 0.05717742692280119} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06372178572773492, "f1": 0.3845494663382594, "f1_std": 0.06396153594809265, "bacc": 0.4164377289377289, "bacc_std": 0.06287311243703485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.05101993751141448, "f1": 0.4597542242703533, "f1_std": 0.053643671351490535, "bacc": 0.4961080586080586, "bacc_std": 0.05030363179759492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.060736834110377204, "f1": 0.37515573506952815, "f1_std": 0.06363866774464101, "bacc": 0.40293040293040294, "bacc_std": 0.06052250034518828} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.04933888369011791, "f1": 0.35, "f1_std": 0.04385040846481775, "bacc": 0.41895604395604397, "bacc_std": 0.04806392006262094} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06431427091856816, "f1": 0.4337973137973138, "f1_std": 0.0676537617291445, "bacc": 0.45650183150183155, "bacc_std": 0.06380020582851925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.0635177373540642, "f1": 0.37503498199593277, "f1_std": 0.06300010508328333, "bacc": 0.38095238095238093, "bacc_std": 0.06294466935086762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05973580889136202, "f1": 0.3759090909090909, "f1_std": 0.05041904384039932, "bacc": 0.41483516483516486, "bacc_std": 0.058297762571809915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 9.999999999999999e-05, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05806260648807758, "f1": 0.5907631421744325, "f1_std": 0.06367602471177458, "bacc": 0.6078296703296704, "bacc_std": 0.05787854679329393} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.062484211023417224, "f1": 0.37820263975155277, "f1_std": 0.06279048925561488, "bacc": 0.3985805860805861, "bacc_std": 0.0616452158902816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06045286441987714, "f1": 0.35666226498145004, "f1_std": 0.05915458872101264, "bacc": 0.37934981684981683, "bacc_std": 0.05961772116045624} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 2.782559402207126, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06551763618208134, "f1": 0.33327228327228325, "f1_std": 0.06611447651334895, "bacc": 0.32623626373626374, "bacc_std": 0.06591228243857586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.000774263682681127, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06169848185103013, "f1": 0.35137788248732776, "f1_std": 0.05689596287436201, "bacc": 0.3587454212454213, "bacc_std": 0.06058495752122709} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 1.7008 | 16.68 | 0.56567 | 0.11358 | 0.54941 | 0.12252 | 0.56494 | 0.11422 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 1.7008 | 16.68 | 0.42154 | 0.066206 | 0.39173 | 0.060595 | 0.41686 | 0.065259 | + + +done! total time: 0:05:37 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e7913cd147720033349a01ed27fd66fbf25cd77f --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_age reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..be4814ce743956b918982565d2fb1a34094f1d23 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,aabc_age,,9.999999999999999e-05,train,0.515748031496063,0.020911854176789067,0.48957148536976564,0.021631441139754626,0.5119216099090571,0.020721165409048132 +flat_mae,reg,logistic,aabc_age,,9.999999999999999e-05,test,0.4423076923076923,0.06380187296688744,0.4169746466479679,0.062184244907475136,0.43154761904761907,0.06282011084161856 +flat_mae,reg,logistic,aabc_age,1,0.005994842503189409,train,0.7677165354330708,0.017650629382246836,0.7681632806668486,0.017583767646141297,0.7698026329669403,0.017586609516377086 +flat_mae,reg,logistic,aabc_age,1,0.005994842503189409,test,0.4423076923076923,0.05873029066350786,0.43643999678482437,0.05828819657079274,0.44024725274725274,0.0584780500906276 +flat_mae,reg,logistic,aabc_age,2,9.999999999999999e-05,train,0.5039370078740157,0.018833099688348908,0.481675222941245,0.019677933571892004,0.5030868267263022,0.01865870540813764 +flat_mae,reg,logistic,aabc_age,2,9.999999999999999e-05,test,0.46153846153846156,0.05824067591778916,0.41863799283154124,0.057254474265564265,0.4535256410256411,0.0572159119192848 +flat_mae,reg,logistic,aabc_age,3,0.046415888336127774,train,0.9350393700787402,0.010901136164159171,0.9355750269713735,0.010839192916781992,0.9358462443588185,0.0107459688998117 +flat_mae,reg,logistic,aabc_age,3,0.046415888336127774,test,0.46153846153846156,0.06545249869790165,0.440625,0.06632365428479227,0.4565018315018315,0.06503433857361934 +flat_mae,reg,logistic,aabc_age,4,9.999999999999999e-05,train,0.49015748031496065,0.019748874449853692,0.45628248533689375,0.020419106988453516,0.48813889437636776,0.019626342823244096 +flat_mae,reg,logistic,aabc_age,4,9.999999999999999e-05,test,0.5961538461538461,0.061863695847446144,0.5552380952380952,0.06898757825502741,0.5842490842490843,0.06166350954850679 +flat_mae,reg,logistic,aabc_age,5,9.999999999999999e-05,train,0.5059055118110236,0.01964348527458983,0.4774316937256918,0.02026324675510036,0.5031624660282438,0.019603920775998207 +flat_mae,reg,logistic,aabc_age,5,9.999999999999999e-05,test,0.3269230769230769,0.06028880198652495,0.2944966910484152,0.05135145789086585,0.3228021978021978,0.05902837260837487 +flat_mae,reg,logistic,aabc_age,6,0.000774263682681127,train,0.6141732283464567,0.020197307403771732,0.6090714397543253,0.020814453746470497,0.6148788380652449,0.020124627553957393 +flat_mae,reg,logistic,aabc_age,6,0.000774263682681127,test,0.4807692307692308,0.06923370720261737,0.48001567398119127,0.06889160966891524,0.4819139194139194,0.06943891662091849 +flat_mae,reg,logistic,aabc_age,7,0.000774263682681127,train,0.6003937007874016,0.020992770943657344,0.5978220200100735,0.021286885131541058,0.6015685984936391,0.02101324051005818 +flat_mae,reg,logistic,aabc_age,7,0.000774263682681127,test,0.4807692307692308,0.05744834314562531,0.45519303166752784,0.06173118410257922,0.48443223443223443,0.05844143930161434 +flat_mae,reg,logistic,aabc_age,8,9.999999999999999e-05,train,0.5039370078740157,0.02000007750000484,0.4706671143362099,0.02073919127572631,0.5005612412229641,0.01989630683832055 +flat_mae,reg,logistic,aabc_age,8,9.999999999999999e-05,test,0.40384615384615385,0.05725351078354427,0.36,0.05944952131467443,0.40132783882783885,0.05669684359754293 +flat_mae,reg,logistic,aabc_age,9,9.999999999999999e-05,train,0.49015748031496065,0.020258580128432926,0.469201934264843,0.02170737909876573,0.4884888010679167,0.02023596277759629 +flat_mae,reg,logistic,aabc_age,9,9.999999999999999e-05,test,0.4807692307692308,0.06043054353318342,0.42024886877828055,0.04884771478425988,0.47115384615384615,0.058697604119079094 +flat_mae,reg,logistic,aabc_age,10,9.999999999999999e-05,train,0.5059055118110236,0.019310266706412952,0.47161020831742706,0.020119145252016055,0.5034476417799378,0.019022973547413235 +flat_mae,reg,logistic,aabc_age,10,9.999999999999999e-05,test,0.34615384615384615,0.06163179220703295,0.32975928641251223,0.058605699560590356,0.34226190476190477,0.06070471438901633 +flat_mae,reg,logistic,aabc_age,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,11,166.81005372000556,test,0.38461538461538464,0.06940742418894667,0.3839673913043478,0.07042894282016683,0.39010989010989017,0.0697280947516965 +flat_mae,reg,logistic,aabc_age,12,0.000774263682681127,train,0.6358267716535433,0.020176238119658706,0.6319061196885074,0.020672618007583975,0.636603500457432,0.020165920167410555 +flat_mae,reg,logistic,aabc_age,12,0.000774263682681127,test,0.34615384615384615,0.061902899244795015,0.3459404789583818,0.06007309199734729,0.3424908424908425,0.06129882410799714 +flat_mae,reg,logistic,aabc_age,13,0.000774263682681127,train,0.6161417322834646,0.019672296663036364,0.6133814945711507,0.020187484127296314,0.6166097913458091,0.019644831900249477 +flat_mae,reg,logistic,aabc_age,13,0.000774263682681127,test,0.4423076923076923,0.06860161771170357,0.4407042510490786,0.06923804588563694,0.44184981684981683,0.0687533422662764 +flat_mae,reg,logistic,aabc_age,14,0.000774263682681127,train,0.6023622047244095,0.021548472351267074,0.5990072153246933,0.021839350086142094,0.6033171729744969,0.021488330650498697 +flat_mae,reg,logistic,aabc_age,14,0.000774263682681127,test,0.5,0.061560765188965014,0.48825194413429707,0.06416681918062424,0.4951923076923077,0.061137949062441806 +flat_mae,reg,logistic,aabc_age,15,9.999999999999999e-05,train,0.5,0.021167080729061653,0.46919162937288605,0.02199047031673814,0.497014105591027,0.020973342257597612 +flat_mae,reg,logistic,aabc_age,15,9.999999999999999e-05,test,0.5192307692307693,0.05676042249781248,0.4909366096866097,0.05455272714285594,0.5112179487179487,0.0557181604747863 +flat_mae,reg,logistic,aabc_age,16,0.000774263682681127,train,0.6259842519685039,0.02169107841961219,0.6216983149690871,0.02219731721886892,0.6259877461933412,0.02168663383507544 +flat_mae,reg,logistic,aabc_age,16,0.000774263682681127,test,0.34615384615384615,0.06504099753960378,0.3514726507713885,0.0657213112539017,0.34706959706959706,0.06536830865463213 +flat_mae,reg,logistic,aabc_age,17,9.999999999999999e-05,train,0.49015748031496065,0.020476187952071203,0.4591643260445412,0.021196174794162387,0.4875361774030522,0.02031626579990805 +flat_mae,reg,logistic,aabc_age,17,9.999999999999999e-05,test,0.4423076923076923,0.0576868715387565,0.40617668621700875,0.05805627398985904,0.4342948717948718,0.05672475644934179 +flat_mae,reg,logistic,aabc_age,18,0.046415888336127774,train,0.9409448818897638,0.010152974646170845,0.9408714706444373,0.010203784269349567,0.941091967801392,0.010116938211328644 +flat_mae,reg,logistic,aabc_age,18,0.046415888336127774,test,0.2692307692307692,0.0625174413533758,0.29247541407867494,0.0603808311469473,0.2667124542124542,0.062075003621818614 +flat_mae,reg,logistic,aabc_age,19,9.999999999999999e-05,train,0.5019685039370079,0.020013745354131147,0.47344425061590123,0.021175664368781228,0.4992977891746853,0.019864601820432145 +flat_mae,reg,logistic,aabc_age,19,9.999999999999999e-05,test,0.40384615384615385,0.0561100329603946,0.33871090770404266,0.05060397109457702,0.39148351648351654,0.05484926230675062 +flat_mae,reg,logistic,aabc_age,20,0.000774263682681127,train,0.610236220472441,0.020371980955106356,0.6059295258777873,0.020855571450295356,0.6123019472984662,0.020439211901761442 +flat_mae,reg,logistic,aabc_age,20,0.000774263682681127,test,0.4807692307692308,0.06060224135132903,0.45755469039673713,0.06359656053297755,0.48008241758241754,0.060304122119134614 +flat_mae,reg,logistic,aabc_age,21,9.999999999999999e-05,train,0.5039370078740157,0.021251973974028754,0.4778796187547001,0.02230329154402456,0.5014138915473859,0.021080972951032496 +flat_mae,reg,logistic,aabc_age,21,9.999999999999999e-05,test,0.4807692307692308,0.061931246474948555,0.43495997536945813,0.06409130122195261,0.4741300366300366,0.06111514141358766 +flat_mae,reg,logistic,aabc_age,22,0.046415888336127774,train,0.9547244094488189,0.009049997696403935,0.9547700023042065,0.009065454725880476,0.9554548043783049,0.008926376509334689 +flat_mae,reg,logistic,aabc_age,22,0.046415888336127774,test,0.2692307692307692,0.05644911831534556,0.26159951159951156,0.05313445864676363,0.26694139194139194,0.05611395992712976 +flat_mae,reg,logistic,aabc_age,23,9.999999999999999e-05,train,0.4921259842519685,0.01975819634411616,0.4598604193238627,0.020812810875862953,0.4893347385541314,0.019561396505632014 +flat_mae,reg,logistic,aabc_age,23,9.999999999999999e-05,test,0.4423076923076923,0.05639568576390454,0.39083034647550774,0.04825232054203755,0.43543956043956045,0.05494391283153634 +flat_mae,reg,logistic,aabc_age,24,0.000774263682681127,train,0.6122047244094488,0.020304453120969127,0.6081379402197785,0.02085860042518793,0.6137829672279239,0.020289830305201966 +flat_mae,reg,logistic,aabc_age,24,0.000774263682681127,test,0.4230769230769231,0.07176848874214477,0.41646965937288516,0.07172412031136939,0.41826923076923084,0.07156494237054259 +flat_mae,reg,logistic,aabc_age,25,0.000774263682681127,train,0.6200787401574803,0.020715598296260365,0.6158230218261788,0.021185743097030516,0.621779875486441,0.020766175857095392 +flat_mae,reg,logistic,aabc_age,25,0.000774263682681127,test,0.3269230769230769,0.05773448458295243,0.290927750410509,0.049403509268661924,0.32280219780219777,0.05666235071534126 +flat_mae,reg,logistic,aabc_age,26,0.000774263682681127,train,0.6181102362204725,0.020304151964984248,0.6154806143431065,0.02083812959488897,0.6191110428106461,0.020253604891205874 +flat_mae,reg,logistic,aabc_age,26,0.000774263682681127,test,0.4423076923076923,0.0639227529381774,0.424477969348659,0.06507852501687421,0.43727106227106227,0.06370927738945657 +flat_mae,reg,logistic,aabc_age,27,9.999999999999999e-05,train,0.5039370078740157,0.019532185681908593,0.4666110925591263,0.020081565776717568,0.5006788357637004,0.019318208859670977 +flat_mae,reg,logistic,aabc_age,27,9.999999999999999e-05,test,0.40384615384615385,0.06206814111935233,0.36948051948051946,0.0631092830099514,0.394459706959707,0.06106723064500022 +flat_mae,reg,logistic,aabc_age,28,0.005994842503189409,train,0.7834645669291339,0.01783975479129975,0.7833992913705976,0.017826598096338547,0.7845262845974886,0.017720526353648593 +flat_mae,reg,logistic,aabc_age,28,0.005994842503189409,test,0.38461538461538464,0.06487133373708609,0.37624303232998885,0.06383407928492123,0.3853021978021979,0.06519415161990755 +flat_mae,reg,logistic,aabc_age,29,9.999999999999999e-05,train,0.5039370078740157,0.020333347520515226,0.4712758235360892,0.02145106947522426,0.5010463636555431,0.02021701762513018 +flat_mae,reg,logistic,aabc_age,29,9.999999999999999e-05,test,0.36538461538461536,0.061539230764423136,0.3488641908376254,0.05858401993935968,0.3628663003663004,0.060995735571263365 +flat_mae,reg,logistic,aabc_age,30,0.000774263682681127,train,0.6240157480314961,0.020178854932140534,0.6202921397383646,0.02054922047625974,0.6235364813987254,0.02008034311810597 +flat_mae,reg,logistic,aabc_age,30,0.000774263682681127,test,0.5,0.0659713493488745,0.489496954658245,0.06506567135102563,0.49793956043956045,0.06569223619231229 +flat_mae,reg,logistic,aabc_age,31,9.999999999999999e-05,train,0.4940944881889764,0.02057707211514295,0.4646604157324784,0.021039335327216697,0.49210354457036876,0.020320415139669146 +flat_mae,reg,logistic,aabc_age,31,9.999999999999999e-05,test,0.5192307692307693,0.05706649033825917,0.44523326572008115,0.047486149632700536,0.5082417582417582,0.05548867448421321 +flat_mae,reg,logistic,aabc_age,32,0.000774263682681127,train,0.6181102362204725,0.02120335854681581,0.6138752531363729,0.021838199457280386,0.6187435149188034,0.021050426969936874 +flat_mae,reg,logistic,aabc_age,32,0.000774263682681127,test,0.46153846153846156,0.05671921655512547,0.4266263997188009,0.058568327838253255,0.46062271062271065,0.056534953296357965 +flat_mae,reg,logistic,aabc_age,33,0.005994842503189409,train,0.7736220472440944,0.018780748652091592,0.7739095571483063,0.018834196138252837,0.7741780848847981,0.01877224614100607 +flat_mae,reg,logistic,aabc_age,33,0.005994842503189409,test,0.40384615384615385,0.059076660155664935,0.3803622303622304,0.056136443869706516,0.4088827838827839,0.05997693923987953 +flat_mae,reg,logistic,aabc_age,34,0.005994842503189409,train,0.7736220472440944,0.018417287487384162,0.7741288343914572,0.018446722693394303,0.7755834655123143,0.018339593276094936 +flat_mae,reg,logistic,aabc_age,34,0.005994842503189409,test,0.28846153846153844,0.0583786862297976,0.2901989606933506,0.05541593595405135,0.2845695970695971,0.05774833185036737 +flat_mae,reg,logistic,aabc_age,35,0.000774263682681127,train,0.6279527559055118,0.020397134359663855,0.6256826062377405,0.020799011135625992,0.6286889443390635,0.020343752391488036 +flat_mae,reg,logistic,aabc_age,35,0.000774263682681127,test,0.4230769230769231,0.07003891564082079,0.4253713527851459,0.06989175607491666,0.4212454212454212,0.07004073740119637 +flat_mae,reg,logistic,aabc_age,36,0.005994842503189409,train,0.7578740157480315,0.01795391970257373,0.7577865945017734,0.018009826785242176,0.759086905362407,0.01800465698781327 +flat_mae,reg,logistic,aabc_age,36,0.005994842503189409,test,0.46153846153846156,0.06220865823792789,0.44078144078144077,0.06330387055873683,0.4684065934065934,0.06289075659686603 +flat_mae,reg,logistic,aabc_age,37,0.000774263682681127,train,0.6043307086614174,0.021508641873520293,0.6032926818107559,0.021821277033922844,0.6061359656609556,0.021609994389605935 +flat_mae,reg,logistic,aabc_age,37,0.000774263682681127,test,0.4423076923076923,0.06633574054288369,0.4361566091954023,0.06825971472832107,0.4375,0.06609169394895081 +flat_mae,reg,logistic,aabc_age,38,0.000774263682681127,train,0.6220472440944882,0.020409145035165038,0.6184446860025131,0.020910230839414155,0.6230933142049411,0.020387743446723127 +flat_mae,reg,logistic,aabc_age,38,0.000774263682681127,test,0.46153846153846156,0.06517777237551403,0.4576973684210527,0.06507274578024079,0.4581043956043956,0.06500269846118782 +flat_mae,reg,logistic,aabc_age,39,0.005994842503189409,train,0.781496062992126,0.019193579637133844,0.7821183761401154,0.01916581880112142,0.7819574252621364,0.019155456280808995 +flat_mae,reg,logistic,aabc_age,39,0.005994842503189409,test,0.40384615384615385,0.06749204423858385,0.4148654244306418,0.06626575676172156,0.40201465201465203,0.06745040248682672 +flat_mae,reg,logistic,aabc_age,40,9.999999999999999e-05,train,0.5,0.020668511046388845,0.47474024426004136,0.021527874624005808,0.49607622619579617,0.020556509392444182 +flat_mae,reg,logistic,aabc_age,40,9.999999999999999e-05,test,0.5,0.05701660715198915,0.43730842212815646,0.048753660241390495,0.4903846153846154,0.05532419219473303 +flat_mae,reg,logistic,aabc_age,41,0.000774263682681127,train,0.6240157480314961,0.02051523540566296,0.6215416700338456,0.020913724661161814,0.6247742808152839,0.02053186353255442 +flat_mae,reg,logistic,aabc_age,41,0.000774263682681127,test,0.4807692307692308,0.059388949622620084,0.4573750749737592,0.0639429277866896,0.48008241758241754,0.05938537399194924 +flat_mae,reg,logistic,aabc_age,42,9.999999999999999e-05,train,0.49606299212598426,0.019966884280050695,0.46923822537235793,0.020866645310317164,0.49351695662931133,0.01989487198810029 +flat_mae,reg,logistic,aabc_age,42,9.999999999999999e-05,test,0.46153846153846156,0.0561038238737293,0.41767857142857145,0.058514930425701224,0.45627289377289376,0.05530129927591583 +flat_mae,reg,logistic,aabc_age,43,9.999999999999999e-05,train,0.5019685039370079,0.019866378918817155,0.46847845953858613,0.02101528212905654,0.4994153837154217,0.01974485313935084 +flat_mae,reg,logistic,aabc_age,43,9.999999999999999e-05,test,0.5,0.06227220024278026,0.4546703296703297,0.0630136255476935,0.4892399267399268,0.0613985329199036 +flat_mae,reg,logistic,aabc_age,44,9.999999999999999e-05,train,0.5177165354330708,0.020238493698723103,0.4913110217808909,0.021347242405249274,0.5160119172057716,0.020108578667184483 +flat_mae,reg,logistic,aabc_age,44,9.999999999999999e-05,test,0.4230769230769231,0.05969131640731229,0.3873376623376623,0.06032793468129017,0.41369047619047616,0.05867688301666563 +flat_mae,reg,logistic,aabc_age,45,0.000774263682681127,train,0.6200787401574803,0.019962557176057823,0.6150749136075384,0.02062748821263614,0.6198893724263458,0.01998908011431171 +flat_mae,reg,logistic,aabc_age,45,0.000774263682681127,test,0.4230769230769231,0.06735689410470136,0.42083850931677025,0.06713024245708535,0.423992673992674,0.0675712312803574 +flat_mae,reg,logistic,aabc_age,46,0.005994842503189409,train,0.7834645669291339,0.018664431714413992,0.783511093116628,0.018737640537189366,0.7853789349219106,0.018533218430822434 +flat_mae,reg,logistic,aabc_age,46,0.005994842503189409,test,0.38461538461538464,0.05972570437687286,0.3847402597402597,0.060033309196120564,0.3839285714285714,0.059746503854348064 +flat_mae,reg,logistic,aabc_age,47,9.999999999999999e-05,train,0.49803149606299213,0.020669755900291076,0.4692844629221238,0.020884647913260442,0.4954830989913481,0.02047392946267407 +flat_mae,reg,logistic,aabc_age,47,9.999999999999999e-05,test,0.38461538461538464,0.06010119671149524,0.33241221144446953,0.05305388585555245,0.375,0.058577351294779374 +flat_mae,reg,logistic,aabc_age,48,0.005994842503189409,train,0.7677165354330708,0.017986463382936906,0.7676683457015467,0.018021057000807004,0.7694850917453188,0.01793449187868033 +flat_mae,reg,logistic,aabc_age,48,0.005994842503189409,test,0.34615384615384615,0.06403441890681705,0.34383713061132415,0.06458136639580034,0.3427197802197802,0.06383822804359368 +flat_mae,reg,logistic,aabc_age,49,9.999999999999999e-05,train,0.5078740157480315,0.019467078361538485,0.4703025242043063,0.02025215804637524,0.5044935259470376,0.01927822163243636 +flat_mae,reg,logistic,aabc_age,49,9.999999999999999e-05,test,0.3269230769230769,0.052952404105873374,0.28563748079877116,0.04451995692294936,0.3241758241758242,0.05223913227830912 +flat_mae,reg,logistic,aabc_age,50,9.999999999999999e-05,train,0.5098425196850394,0.019194621769313656,0.4777216213551618,0.020018719511513315,0.5064420471087806,0.019068726109747115 +flat_mae,reg,logistic,aabc_age,50,9.999999999999999e-05,test,0.38461538461538464,0.06289997460042196,0.38946759259259256,0.06328029532055728,0.3853021978021978,0.06332846416600277 +flat_mae,reg,logistic,aabc_age,51,9.999999999999999e-05,train,0.5059055118110236,0.020439038468298525,0.4781482678390294,0.021890212518616285,0.5043002921043597,0.020316336813771235 +flat_mae,reg,logistic,aabc_age,51,9.999999999999999e-05,test,0.40384615384615385,0.06148328054831044,0.34763291517323774,0.05298466003866515,0.39560439560439564,0.05974512797196864 +flat_mae,reg,logistic,aabc_age,52,9.999999999999999e-05,train,0.515748031496063,0.019173434896783925,0.47793908059044976,0.019799341927631275,0.5119553251027544,0.01899934535654982 +flat_mae,reg,logistic,aabc_age,52,9.999999999999999e-05,test,0.36538461538461536,0.06053039727345956,0.3351190476190476,0.06132615825407568,0.35737179487179493,0.05953260321596172 +flat_mae,reg,logistic,aabc_age,53,0.000774263682681127,train,0.6023622047244095,0.021482827037513363,0.6001700618669128,0.021896391902841542,0.6034171463149396,0.021495835775619088 +flat_mae,reg,logistic,aabc_age,53,0.000774263682681127,test,0.4230769230769231,0.06363471708851161,0.4093956809474051,0.06395270228454203,0.4180402930402931,0.06336936015422263 +flat_mae,reg,logistic,aabc_age,54,9.999999999999999e-05,train,0.5059055118110236,0.020251078754288162,0.4693308209024457,0.021419929621199353,0.5036152229908955,0.020129124869727445 +flat_mae,reg,logistic,aabc_age,54,9.999999999999999e-05,test,0.4230769230769231,0.06065152914944256,0.36264705882352943,0.05285707212266343,0.41208791208791207,0.05926808055131913 +flat_mae,reg,logistic,aabc_age,55,0.000774263682681127,train,0.6122047244094488,0.021810672202177625,0.6079381172956736,0.022321619112428134,0.6129626823734295,0.021792003389706504 +flat_mae,reg,logistic,aabc_age,55,0.000774263682681127,test,0.46153846153846156,0.06368914893690834,0.4443809585999739,0.06269262664024815,0.4551282051282052,0.06312155396676154 +flat_mae,reg,logistic,aabc_age,56,9.999999999999999e-05,train,0.5078740157480315,0.020163191243167886,0.4790534476930237,0.020331557568349395,0.504040768984386,0.01997654550904625 +flat_mae,reg,logistic,aabc_age,56,9.999999999999999e-05,test,0.40384615384615385,0.06382644505812146,0.3752737922996544,0.06200303735797707,0.3999542124542125,0.0630393316724233 +flat_mae,reg,logistic,aabc_age,57,9.999999999999999e-05,train,0.5,0.021356961025379255,0.467138212528024,0.022290138209447266,0.4960938473960901,0.02114937136490381 +flat_mae,reg,logistic,aabc_age,57,9.999999999999999e-05,test,0.5,0.055718863197092704,0.4291316526610644,0.0477698783437679,0.4903846153846154,0.05414397308081231 +flat_mae,reg,logistic,aabc_age,58,9.999999999999999e-05,train,0.5059055118110236,0.020312050011231052,0.4757082673289673,0.02122562300394683,0.5024597757144857,0.020137477010086408 +flat_mae,reg,logistic,aabc_age,58,9.999999999999999e-05,test,0.40384615384615385,0.057065829317899566,0.37231973434535104,0.057208783451856794,0.3985805860805861,0.05622764706006076 +flat_mae,reg,logistic,aabc_age,59,0.000774263682681127,train,0.6161417322834646,0.02039890639791173,0.6122130640159309,0.02102519531431376,0.6167273858865454,0.020429111234209756 +flat_mae,reg,logistic,aabc_age,59,0.000774263682681127,test,0.36538461538461536,0.057824157028829,0.33251231527093594,0.04840510245888632,0.3598901098901099,0.05655984441706884 +flat_mae,reg,logistic,aabc_age,60,0.000774263682681127,train,0.6259842519685039,0.021185720890957167,0.6224108778264013,0.021528180955408992,0.6269080043882782,0.021093603739519014 +flat_mae,reg,logistic,aabc_age,60,0.000774263682681127,test,0.4423076923076923,0.06596999273024366,0.43771209633278596,0.06716216161970864,0.4432234432234432,0.06641503037164499 +flat_mae,reg,logistic,aabc_age,61,9.999999999999999e-05,train,0.5118110236220472,0.01980021580935653,0.489203812298203,0.02090635916129961,0.508925677373324,0.019688658899396635 +flat_mae,reg,logistic,aabc_age,61,9.999999999999999e-05,test,0.34615384615384615,0.05858281954261104,0.3002117362371446,0.051302101913491376,0.33791208791208793,0.05716324683776404 +flat_mae,reg,logistic,aabc_age,62,9.999999999999999e-05,train,0.4921259842519685,0.020919964383091558,0.4640943271895653,0.02170829899670301,0.48943471189457394,0.020792307758221617 +flat_mae,reg,logistic,aabc_age,62,9.999999999999999e-05,test,0.46153846153846156,0.05884553795555027,0.4311776585483482,0.0568717924718722,0.4548992673992674,0.057944891914070394 +flat_mae,reg,logistic,aabc_age,63,0.000774263682681127,train,0.6299212598425197,0.02008000420600398,0.6277522143512232,0.02064184380915574,0.6310902224634581,0.020139520792030793 +flat_mae,reg,logistic,aabc_age,63,0.000774263682681127,test,0.4423076923076923,0.06464056286004868,0.433517260894171,0.06619384461119805,0.4375,0.06442459089473317 +flat_mae,reg,logistic,aabc_age,64,9.999999999999999e-05,train,0.49803149606299213,0.0180038384317455,0.46325848625142213,0.018559991384512472,0.4944128807857473,0.017907813958934284 +flat_mae,reg,logistic,aabc_age,64,9.999999999999999e-05,test,0.38461538461538464,0.05642834645835078,0.3214285714285714,0.04805987855687749,0.3791208791208791,0.055163433883958155 +flat_mae,reg,logistic,aabc_age,65,9.999999999999999e-05,train,0.49606299212598426,0.01999138749089586,0.467726600484351,0.021001435291134827,0.49303183419673213,0.019875162939508615 +flat_mae,reg,logistic,aabc_age,65,9.999999999999999e-05,test,0.5576923076923077,0.05030703069430858,0.4781968390804598,0.042871394904597154,0.5480769230769231,0.04858892913241654 +flat_mae,reg,logistic,aabc_age,66,9.999999999999999e-05,train,0.5078740157480315,0.021333170057642382,0.4797167808716583,0.022318433096852983,0.5047434592981439,0.02121070169916723 +flat_mae,reg,logistic,aabc_age,66,9.999999999999999e-05,test,0.46153846153846156,0.060337549026167836,0.42038421348766175,0.06099802567791795,0.45352564102564097,0.059547430675219955 +flat_mae,reg,logistic,aabc_age,67,0.005994842503189409,train,0.7677165354330708,0.019400051629416003,0.7677978978117931,0.01942272469214695,0.769317510534361,0.01928473446352293 +flat_mae,reg,logistic,aabc_age,67,0.005994842503189409,test,0.40384615384615385,0.06339127812256064,0.3877077930558406,0.06288973459960698,0.4015567765567766,0.06328940086652717 +flat_mae,reg,logistic,aabc_age,68,9.999999999999999e-05,train,0.5,0.019360787733979295,0.46598244426150853,0.019773544626515097,0.4962614286070477,0.019198985306646824 +flat_mae,reg,logistic,aabc_age,68,9.999999999999999e-05,test,0.5192307692307693,0.06313318316517905,0.4906536363154828,0.06807521599315697,0.5128205128205128,0.06272939723869825 +flat_mae,reg,logistic,aabc_age,69,0.000774263682681127,train,0.6141732283464567,0.01938708802833381,0.6086658341311141,0.020141794077021855,0.6150964059464239,0.019373119293446844 +flat_mae,reg,logistic,aabc_age,69,0.000774263682681127,test,0.4423076923076923,0.065239783031068,0.42363834422657953,0.06629884021996298,0.43727106227106227,0.06462289838946264 +flat_mae,reg,logistic,aabc_age,70,0.000774263682681127,train,0.6358267716535433,0.021071747021475105,0.6314482235513466,0.021442291843019677,0.6370386362197897,0.02105441919860571 +flat_mae,reg,logistic,aabc_age,70,0.000774263682681127,test,0.34615384615384615,0.06423855319024808,0.32676821844382276,0.06287075943569098,0.3408882783882784,0.06355372551984974 +flat_mae,reg,logistic,aabc_age,71,9.999999999999999e-05,train,0.4940944881889764,0.01857823040015624,0.4542067165000021,0.01843293193063069,0.4900630814996097,0.01837226666710224 +flat_mae,reg,logistic,aabc_age,71,9.999999999999999e-05,test,0.5,0.06331143086446955,0.480575875737166,0.06575427182014103,0.49496336996337,0.06258026601987786 +flat_mae,reg,logistic,aabc_age,72,9.999999999999999e-05,train,0.49803149606299213,0.01907780909658129,0.46678873447480995,0.02020426048249656,0.49456284079641116,0.018935033290658765 +flat_mae,reg,logistic,aabc_age,72,9.999999999999999e-05,test,0.5,0.05788383592626236,0.45594425735554767,0.0590493951132229,0.4933608058608059,0.05705767806590972 +flat_mae,reg,logistic,aabc_age,73,9.999999999999999e-05,train,0.5098425196850394,0.019433742044203933,0.4772417027012663,0.019869236901327195,0.5068771828711385,0.019273433967111238 +flat_mae,reg,logistic,aabc_age,73,9.999999999999999e-05,test,0.46153846153846156,0.05548729797608089,0.387825311942959,0.04935477698938478,0.4519230769230769,0.053843509900888216 +flat_mae,reg,logistic,aabc_age,74,9.999999999999999e-05,train,0.49606299212598426,0.01926355222094015,0.45750035566936975,0.019547212260569154,0.4934346044891626,0.01908671563705753 +flat_mae,reg,logistic,aabc_age,74,9.999999999999999e-05,test,0.4423076923076923,0.06432327516389888,0.4223292765382015,0.06567094666701749,0.43864468864468864,0.06388690820428121 +flat_mae,reg,logistic,aabc_age,75,9.999999999999999e-05,train,0.4881889763779528,0.019638172160759044,0.452982535933935,0.020029065914885433,0.48563764291153055,0.019515240933501352 +flat_mae,reg,logistic,aabc_age,75,9.999999999999999e-05,test,0.4807692307692308,0.06228483673875981,0.41293103448275864,0.0533942280193391,0.4684065934065934,0.06083676076163657 +flat_mae,reg,logistic,aabc_age,76,0.005994842503189409,train,0.7637795275590551,0.01856598576407013,0.7645222233451805,0.01852598671897214,0.765285252469845,0.01853091529196 +flat_mae,reg,logistic,aabc_age,76,0.005994842503189409,test,0.40384615384615385,0.0651749012387383,0.39701815758787273,0.06537986325701309,0.39903846153846156,0.06508449570433472 +flat_mae,reg,logistic,aabc_age,77,9.999999999999999e-05,train,0.5177165354330708,0.01927817765755539,0.4811883796158253,0.01989566331799539,0.5144565765675916,0.019080633500464076 +flat_mae,reg,logistic,aabc_age,77,9.999999999999999e-05,test,0.36538461538461536,0.061769410383875276,0.34678649237472764,0.05958256083232817,0.361492673992674,0.06097350005985635 +flat_mae,reg,logistic,aabc_age,78,9.999999999999999e-05,train,0.4921259842519685,0.01915104498519723,0.45349151902546914,0.01933737049475918,0.4887496427811097,0.019018241762739682 +flat_mae,reg,logistic,aabc_age,78,9.999999999999999e-05,test,0.46153846153846156,0.05935820456941182,0.4076923076923077,0.05006585235273207,0.45054945054945056,0.05791478421012255 +flat_mae,reg,logistic,aabc_age,79,0.000774263682681127,train,0.6141732283464567,0.022140060532088897,0.6083688792193682,0.022684929248067757,0.6134734574377289,0.022063748513082005 +flat_mae,reg,logistic,aabc_age,79,0.000774263682681127,test,0.4423076923076923,0.06249028326834965,0.421422558922559,0.06354068442047475,0.440018315018315,0.0621249084018933 +flat_mae,reg,logistic,aabc_age,80,9.999999999999999e-05,train,0.5039370078740157,0.019802930056233535,0.47973362844052503,0.020714183402196454,0.5012463103364283,0.019676182140747372 +flat_mae,reg,logistic,aabc_age,80,9.999999999999999e-05,test,0.34615384615384615,0.05261988284865254,0.29867770996803256,0.04520488153815294,0.34065934065934067,0.05135683865097888 +flat_mae,reg,logistic,aabc_age,81,0.005994842503189409,train,0.7696850393700787,0.01780815504932425,0.7699100361972171,0.017857343555518858,0.7719363565399346,0.017761630245108143 +flat_mae,reg,logistic,aabc_age,81,0.005994842503189409,test,0.3269230769230769,0.05550792896077814,0.3156989247311828,0.05179834291242198,0.32875457875457875,0.0559804508550838 +flat_mae,reg,logistic,aabc_age,82,9.999999999999999e-05,train,0.4822834645669291,0.019141420931790578,0.4493855706763831,0.019497484246352927,0.47893655217121955,0.019010309765756038 +flat_mae,reg,logistic,aabc_age,82,9.999999999999999e-05,test,0.5192307692307693,0.06652841186890618,0.5144511445465723,0.06788139976221873,0.5173992673992673,0.06631660077887035 +flat_mae,reg,logistic,aabc_age,83,0.005994842503189409,train,0.7893700787401575,0.0184872914744127,0.7897500626951595,0.018495186981417035,0.7905570504939691,0.018500315160047534 +flat_mae,reg,logistic,aabc_age,83,0.005994842503189409,test,0.38461538461538464,0.06520336870086414,0.37274286243974786,0.0645016722315493,0.380952380952381,0.06491179251831314 +flat_mae,reg,logistic,aabc_age,84,9.999999999999999e-05,train,0.49803149606299213,0.020083283027844682,0.46169369129895443,0.020369912927122747,0.4944128807857473,0.019896040275119643 +flat_mae,reg,logistic,aabc_age,84,9.999999999999999e-05,test,0.4423076923076923,0.0542331559758474,0.37589285714285714,0.049170340999460556,0.4340659340659341,0.05258475219305428 +flat_mae,reg,logistic,aabc_age,85,9.999999999999999e-05,train,0.49015748031496065,0.020824568226623173,0.4581292263104362,0.02104944958750062,0.4875361774030522,0.020603140070114285 +flat_mae,reg,logistic,aabc_age,85,9.999999999999999e-05,test,0.46153846153846156,0.05318243414676643,0.39022058823529415,0.04849831662353647,0.4532967032967033,0.05145627013086649 +flat_mae,reg,logistic,aabc_age,86,0.000774263682681127,train,0.6240157480314961,0.021321905619510608,0.6246927309816271,0.02130285614131345,0.6252917687177904,0.021382904711063237 +flat_mae,reg,logistic,aabc_age,86,0.000774263682681127,test,0.4807692307692308,0.06807622772352394,0.46360696170133553,0.0703822709378761,0.47870879120879123,0.06812092168430067 +flat_mae,reg,logistic,aabc_age,87,9.999999999999999e-05,train,0.5,0.019853118654071467,0.4689540294569987,0.020612073499167168,0.497231673472206,0.019695553985494076 +flat_mae,reg,logistic,aabc_age,87,9.999999999999999e-05,test,0.46153846153846156,0.060589266141765026,0.42417582417582417,0.061291119693695655,0.453525641025641,0.05975539104609702 +flat_mae,reg,logistic,aabc_age,88,9.999999999999999e-05,train,0.4921259842519685,0.019036360911846396,0.4575876846506627,0.020031460827096236,0.48950231976508907,0.01886579665823683 +flat_mae,reg,logistic,aabc_age,88,9.999999999999999e-05,test,0.4230769230769231,0.059419081269697464,0.3746947496947497,0.04991716748621416,0.41346153846153844,0.05801083470874941 +flat_mae,reg,logistic,aabc_age,89,9.999999999999999e-05,train,0.49803149606299213,0.01969953954141355,0.4646270166352231,0.020099355409168466,0.4955507068618632,0.019593879052576132 +flat_mae,reg,logistic,aabc_age,89,9.999999999999999e-05,test,0.4423076923076923,0.05937857432405561,0.37421788097886544,0.05142017303555028,0.4326923076923077,0.057877753430561035 +flat_mae,reg,logistic,aabc_age,90,9.999999999999999e-05,train,0.49606299212598426,0.01919815636040125,0.471201963321049,0.019889267045264922,0.49204396813128004,0.019173181979880976 +flat_mae,reg,logistic,aabc_age,90,9.999999999999999e-05,test,0.5,0.05609547809513609,0.4770161290322581,0.06000016400020127,0.4977106227106227,0.05583737981407257 +flat_mae,reg,logistic,aabc_age,91,9.999999999999999e-05,train,0.5059055118110236,0.019413568664037442,0.4720059809538923,0.01982663205916082,0.5036652096611167,0.0192383314581115 +flat_mae,reg,logistic,aabc_age,91,9.999999999999999e-05,test,0.40384615384615385,0.05836195972716532,0.36210628452007765,0.05889336248127792,0.3999542124542125,0.05747799508149825 +flat_mae,reg,logistic,aabc_age,92,0.046415888336127774,train,0.9488188976377953,0.009390643581159572,0.9489321899507308,0.009418069875802501,0.9488213215085091,0.00936335847729017 +flat_mae,reg,logistic,aabc_age,92,0.046415888336127774,test,0.36538461538461536,0.06046266391592957,0.3575135509168493,0.06009931559223221,0.36904761904761907,0.0611849748234283 +flat_mae,reg,logistic,aabc_age,93,9.999999999999999e-05,train,0.5,0.018617458358205382,0.472769432392512,0.019769089490037847,0.4971140789314695,0.018513855242027095 +flat_mae,reg,logistic,aabc_age,93,9.999999999999999e-05,test,0.40384615384615385,0.06178406517913152,0.36713381277275803,0.062100202971111476,0.3985805860805861,0.06094421165326057 +flat_mae,reg,logistic,aabc_age,94,9.999999999999999e-05,train,0.5039370078740157,0.019090376617158678,0.4648577833556756,0.019440322505484862,0.5004112812123003,0.018870835517208126 +flat_mae,reg,logistic,aabc_age,94,9.999999999999999e-05,test,0.40384615384615385,0.06356751058808945,0.3873563218390805,0.06616943554316208,0.39743589743589747,0.06303156060283724 +flat_mae,reg,logistic,aabc_age,95,0.000774263682681127,train,0.639763779527559,0.02082660196706844,0.6388587044013008,0.0210502373340498,0.6409356785432758,0.020794498410517066 +flat_mae,reg,logistic,aabc_age,95,0.000774263682681127,test,0.3269230769230769,0.058977718689138425,0.3172172030867683,0.05165772239655147,0.32005494505494503,0.057725544782255306 +flat_mae,reg,logistic,aabc_age,96,9.999999999999999e-05,train,0.4822834645669291,0.020345428230265875,0.44587203840935186,0.02059230884680424,0.4795392691445351,0.020134137798592848 +flat_mae,reg,logistic,aabc_age,96,9.999999999999999e-05,test,0.5769230769230769,0.05676447499362409,0.5428571428571428,0.06191759307626926,0.5663919413919415,0.05645208212854524 +flat_mae,reg,logistic,aabc_age,97,9.999999999999999e-05,train,0.5,0.019634320092966062,0.47239674994437186,0.020391707415407953,0.49689651105029065,0.019480734767358267 +flat_mae,reg,logistic,aabc_age,97,9.999999999999999e-05,test,0.4230769230769231,0.06156730093465767,0.3920284582423801,0.06380491405204727,0.41506410256410253,0.06068667413816151 +flat_mae,reg,logistic,aabc_age,98,0.000774263682681127,train,0.6181102362204725,0.02012506005049634,0.6142989478438702,0.02065301664433864,0.618140797945488,0.0201206140106052 +flat_mae,reg,logistic,aabc_age,98,0.000774263682681127,test,0.38461538461538464,0.06297783023089726,0.36989898989898995,0.06296532246525437,0.3823260073260073,0.06262224305522504 +flat_mae,reg,logistic,aabc_age,99,0.000774263682681127,train,0.6122047244094488,0.021144412138253674,0.6087111594147142,0.02159538633538594,0.6134478048060086,0.021157835040372063 +flat_mae,reg,logistic,aabc_age,99,0.000774263682681127,test,0.4423076923076923,0.06679176994618707,0.44415007742681767,0.06817257411784756,0.44184981684981683,0.06706898066505797 +flat_mae,reg,logistic,aabc_age,100,9.999999999999999e-05,train,0.4940944881889764,0.019481704162459555,0.46042917436479536,0.019770996196179988,0.4921711524408839,0.019261850182388105 +flat_mae,reg,logistic,aabc_age,100,9.999999999999999e-05,test,0.46153846153846156,0.061321383955171095,0.4239772727272727,0.06047895100557252,0.4535256410256411,0.06016935552031693 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a910ac7293685f0665cda6631f42e150ce254379 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:18:44 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_age reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_age__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:19:24 time: 5.1085 data: 4.1793 max mem: 3205 +extract (train) [ 20/228] eta: 0:01:37 time: 0.2384 data: 0.0839 max mem: 3581 +extract (train) [ 40/228] eta: 0:01:05 time: 0.2208 data: 0.0729 max mem: 3581 +extract (train) [ 60/228] eta: 0:00:51 time: 0.2175 data: 0.0730 max mem: 3581 +extract (train) [ 80/228] eta: 0:00:41 time: 0.2134 data: 0.0711 max mem: 3581 +extract (train) [100/228] eta: 0:00:34 time: 0.2353 data: 0.0840 max mem: 3581 +extract (train) [120/228] eta: 0:00:28 time: 0.1880 data: 0.0554 max mem: 3581 +extract (train) [140/228] eta: 0:00:22 time: 0.2039 data: 0.0640 max mem: 3581 +extract (train) [160/228] eta: 0:00:16 time: 0.2151 data: 0.0717 max mem: 3581 +extract (train) [180/228] eta: 0:00:11 time: 0.2110 data: 0.0689 max mem: 3581 +extract (train) [200/228] eta: 0:00:06 time: 0.2057 data: 0.0668 max mem: 3581 +extract (train) [220/228] eta: 0:00:01 time: 0.1830 data: 0.0553 max mem: 3581 +extract (train) [227/228] eta: 0:00:00 time: 0.1808 data: 0.0547 max mem: 3581 +extract (train) Total time: 0:00:53 (0.2346 s / it) +extract (validation) [ 0/27] eta: 0:01:54 time: 4.2408 data: 4.0964 max mem: 3581 +extract (validation) [20/27] eta: 0:00:02 time: 0.1763 data: 0.0460 max mem: 3581 +extract (validation) [26/27] eta: 0:00:00 time: 0.1568 data: 0.0395 max mem: 3581 +extract (validation) Total time: 0:00:09 (0.3341 s / it) +extract (test) [ 0/26] eta: 0:01:45 time: 4.0684 data: 3.9339 max mem: 3581 +extract (test) [20/26] eta: 0:00:02 time: 0.1688 data: 0.0442 max mem: 3581 +extract (test) [25/26] eta: 0:00:00 time: 0.1661 data: 0.0432 max mem: 3581 +extract (test) Total time: 0:00:08 (0.3319 s / it) +feature extraction time: 0:01:11 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_age | | 0.0001 | train | 0.51575 | 0.020912 | 0.48957 | 0.021631 | 0.51192 | 0.020721 | +| flat_mae | reg | logistic | aabc_age | | 0.0001 | test | 0.44231 | 0.063802 | 0.41697 | 0.062184 | 0.43155 | 0.06282 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05873029066350786, "f1": 0.43643999678482437, "f1_std": 0.05828819657079274, "bacc": 0.44024725274725274, "bacc_std": 0.0584780500906276} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05824067591778916, "f1": 0.41863799283154124, "f1_std": 0.057254474265564265, "bacc": 0.4535256410256411, "bacc_std": 0.0572159119192848} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06545249869790165, "f1": 0.440625, "f1_std": 0.06632365428479227, "bacc": 0.4565018315018315, "bacc_std": 0.06503433857361934} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.061863695847446144, "f1": 0.5552380952380952, "f1_std": 0.06898757825502741, "bacc": 0.5842490842490843, "bacc_std": 0.06166350954850679} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06028880198652495, "f1": 0.2944966910484152, "f1_std": 0.05135145789086585, "bacc": 0.3228021978021978, "bacc_std": 0.05902837260837487} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06923370720261737, "f1": 0.48001567398119127, "f1_std": 0.06889160966891524, "bacc": 0.4819139194139194, "bacc_std": 0.06943891662091849} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05744834314562531, "f1": 0.45519303166752784, "f1_std": 0.06173118410257922, "bacc": 0.48443223443223443, "bacc_std": 0.05844143930161434} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05725351078354427, "f1": 0.36, "f1_std": 0.05944952131467443, "bacc": 0.40132783882783885, "bacc_std": 0.05669684359754293} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06043054353318342, "f1": 0.42024886877828055, "f1_std": 0.04884771478425988, "bacc": 0.47115384615384615, "bacc_std": 0.058697604119079094} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06163179220703295, "f1": 0.32975928641251223, "f1_std": 0.058605699560590356, "bacc": 0.34226190476190477, "bacc_std": 0.06070471438901633} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06940742418894667, "f1": 0.3839673913043478, "f1_std": 0.07042894282016683, "bacc": 0.39010989010989017, "bacc_std": 0.0697280947516965} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.000774263682681127, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.061902899244795015, "f1": 0.3459404789583818, "f1_std": 0.06007309199734729, "bacc": 0.3424908424908425, "bacc_std": 0.06129882410799714} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06860161771170357, "f1": 0.4407042510490786, "f1_std": 0.06923804588563694, "bacc": 0.44184981684981683, "bacc_std": 0.0687533422662764} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.061560765188965014, "f1": 0.48825194413429707, "f1_std": 0.06416681918062424, "bacc": 0.4951923076923077, "bacc_std": 0.061137949062441806} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05676042249781248, "f1": 0.4909366096866097, "f1_std": 0.05455272714285594, "bacc": 0.5112179487179487, "bacc_std": 0.0557181604747863} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.000774263682681127, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06504099753960378, "f1": 0.3514726507713885, "f1_std": 0.0657213112539017, "bacc": 0.34706959706959706, "bacc_std": 0.06536830865463213} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0576868715387565, "f1": 0.40617668621700875, "f1_std": 0.05805627398985904, "bacc": 0.4342948717948718, "bacc_std": 0.05672475644934179} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.2692307692307692, "acc_std": 0.0625174413533758, "f1": 0.29247541407867494, "f1_std": 0.0603808311469473, "bacc": 0.2667124542124542, "bacc_std": 0.062075003621818614} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0561100329603946, "f1": 0.33871090770404266, "f1_std": 0.05060397109457702, "bacc": 0.39148351648351654, "bacc_std": 0.05484926230675062} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06060224135132903, "f1": 0.45755469039673713, "f1_std": 0.06359656053297755, "bacc": 0.48008241758241754, "bacc_std": 0.060304122119134614} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.061931246474948555, "f1": 0.43495997536945813, "f1_std": 0.06409130122195261, "bacc": 0.4741300366300366, "bacc_std": 0.06111514141358766} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.2692307692307692, "acc_std": 0.05644911831534556, "f1": 0.26159951159951156, "f1_std": 0.05313445864676363, "bacc": 0.26694139194139194, "bacc_std": 0.05611395992712976} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05639568576390454, "f1": 0.39083034647550774, "f1_std": 0.04825232054203755, "bacc": 0.43543956043956045, "bacc_std": 0.05494391283153634} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.07176848874214477, "f1": 0.41646965937288516, "f1_std": 0.07172412031136939, "bacc": 0.41826923076923084, "bacc_std": 0.07156494237054259} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 0.000774263682681127, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.05773448458295243, "f1": 0.290927750410509, "f1_std": 0.049403509268661924, "bacc": 0.32280219780219777, "bacc_std": 0.05666235071534126} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0639227529381774, "f1": 0.424477969348659, "f1_std": 0.06507852501687421, "bacc": 0.43727106227106227, "bacc_std": 0.06370927738945657} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06206814111935233, "f1": 0.36948051948051946, "f1_std": 0.0631092830099514, "bacc": 0.394459706959707, "bacc_std": 0.06106723064500022} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06487133373708609, "f1": 0.37624303232998885, "f1_std": 0.06383407928492123, "bacc": 0.3853021978021979, "bacc_std": 0.06519415161990755} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.061539230764423136, "f1": 0.3488641908376254, "f1_std": 0.05858401993935968, "bacc": 0.3628663003663004, "bacc_std": 0.060995735571263365} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.0659713493488745, "f1": 0.489496954658245, "f1_std": 0.06506567135102563, "bacc": 0.49793956043956045, "bacc_std": 0.06569223619231229} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05706649033825917, "f1": 0.44523326572008115, "f1_std": 0.047486149632700536, "bacc": 0.5082417582417582, "bacc_std": 0.05548867448421321} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05671921655512547, "f1": 0.4266263997188009, "f1_std": 0.058568327838253255, "bacc": 0.46062271062271065, "bacc_std": 0.056534953296357965} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.059076660155664935, "f1": 0.3803622303622304, "f1_std": 0.056136443869706516, "bacc": 0.4088827838827839, "bacc_std": 0.05997693923987953} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.28846153846153844, "acc_std": 0.0583786862297976, "f1": 0.2901989606933506, "f1_std": 0.05541593595405135, "bacc": 0.2845695970695971, "bacc_std": 0.05774833185036737} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.07003891564082079, "f1": 0.4253713527851459, "f1_std": 0.06989175607491666, "bacc": 0.4212454212454212, "bacc_std": 0.07004073740119637} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06220865823792789, "f1": 0.44078144078144077, "f1_std": 0.06330387055873683, "bacc": 0.4684065934065934, "bacc_std": 0.06289075659686603} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06633574054288369, "f1": 0.4361566091954023, "f1_std": 0.06825971472832107, "bacc": 0.4375, "bacc_std": 0.06609169394895081} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06517777237551403, "f1": 0.4576973684210527, "f1_std": 0.06507274578024079, "bacc": 0.4581043956043956, "bacc_std": 0.06500269846118782} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06749204423858385, "f1": 0.4148654244306418, "f1_std": 0.06626575676172156, "bacc": 0.40201465201465203, "bacc_std": 0.06745040248682672} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.05701660715198915, "f1": 0.43730842212815646, "f1_std": 0.048753660241390495, "bacc": 0.4903846153846154, "bacc_std": 0.05532419219473303} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.059388949622620084, "f1": 0.4573750749737592, "f1_std": 0.0639429277866896, "bacc": 0.48008241758241754, "bacc_std": 0.05938537399194924} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0561038238737293, "f1": 0.41767857142857145, "f1_std": 0.058514930425701224, "bacc": 0.45627289377289376, "bacc_std": 0.05530129927591583} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.06227220024278026, "f1": 0.4546703296703297, "f1_std": 0.0630136255476935, "bacc": 0.4892399267399268, "bacc_std": 0.0613985329199036} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05969131640731229, "f1": 0.3873376623376623, "f1_std": 0.06032793468129017, "bacc": 0.41369047619047616, "bacc_std": 0.05867688301666563} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06735689410470136, "f1": 0.42083850931677025, "f1_std": 0.06713024245708535, "bacc": 0.423992673992674, "bacc_std": 0.0675712312803574} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.05972570437687286, "f1": 0.3847402597402597, "f1_std": 0.060033309196120564, "bacc": 0.3839285714285714, "bacc_std": 0.059746503854348064} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06010119671149524, "f1": 0.33241221144446953, "f1_std": 0.05305388585555245, "bacc": 0.375, "bacc_std": 0.058577351294779374} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06403441890681705, "f1": 0.34383713061132415, "f1_std": 0.06458136639580034, "bacc": 0.3427197802197802, "bacc_std": 0.06383822804359368} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.052952404105873374, "f1": 0.28563748079877116, "f1_std": 0.04451995692294936, "bacc": 0.3241758241758242, "bacc_std": 0.05223913227830912} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06289997460042196, "f1": 0.38946759259259256, "f1_std": 0.06328029532055728, "bacc": 0.3853021978021978, "bacc_std": 0.06332846416600277} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06148328054831044, "f1": 0.34763291517323774, "f1_std": 0.05298466003866515, "bacc": 0.39560439560439564, "bacc_std": 0.05974512797196864} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06053039727345956, "f1": 0.3351190476190476, "f1_std": 0.06132615825407568, "bacc": 0.35737179487179493, "bacc_std": 0.05953260321596172} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06363471708851161, "f1": 0.4093956809474051, "f1_std": 0.06395270228454203, "bacc": 0.4180402930402931, "bacc_std": 0.06336936015422263} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06065152914944256, "f1": 0.36264705882352943, "f1_std": 0.05285707212266343, "bacc": 0.41208791208791207, "bacc_std": 0.05926808055131913} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06368914893690834, "f1": 0.4443809585999739, "f1_std": 0.06269262664024815, "bacc": 0.4551282051282052, "bacc_std": 0.06312155396676154} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06382644505812146, "f1": 0.3752737922996544, "f1_std": 0.06200303735797707, "bacc": 0.3999542124542125, "bacc_std": 0.0630393316724233} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.055718863197092704, "f1": 0.4291316526610644, "f1_std": 0.0477698783437679, "bacc": 0.4903846153846154, "bacc_std": 0.05414397308081231} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.057065829317899566, "f1": 0.37231973434535104, "f1_std": 0.057208783451856794, "bacc": 0.3985805860805861, "bacc_std": 0.05622764706006076} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.000774263682681127, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.057824157028829, "f1": 0.33251231527093594, "f1_std": 0.04840510245888632, "bacc": 0.3598901098901099, "bacc_std": 0.05655984441706884} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06596999273024366, "f1": 0.43771209633278596, "f1_std": 0.06716216161970864, "bacc": 0.4432234432234432, "bacc_std": 0.06641503037164499} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.05858281954261104, "f1": 0.3002117362371446, "f1_std": 0.051302101913491376, "bacc": 0.33791208791208793, "bacc_std": 0.05716324683776404} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05884553795555027, "f1": 0.4311776585483482, "f1_std": 0.0568717924718722, "bacc": 0.4548992673992674, "bacc_std": 0.057944891914070394} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06464056286004868, "f1": 0.433517260894171, "f1_std": 0.06619384461119805, "bacc": 0.4375, "bacc_std": 0.06442459089473317} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 9.999999999999999e-05, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.05642834645835078, "f1": 0.3214285714285714, "f1_std": 0.04805987855687749, "bacc": 0.3791208791208791, "bacc_std": 0.055163433883958155} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.05030703069430858, "f1": 0.4781968390804598, "f1_std": 0.042871394904597154, "bacc": 0.5480769230769231, "bacc_std": 0.04858892913241654} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.060337549026167836, "f1": 0.42038421348766175, "f1_std": 0.06099802567791795, "bacc": 0.45352564102564097, "bacc_std": 0.059547430675219955} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06339127812256064, "f1": 0.3877077930558406, "f1_std": 0.06288973459960698, "bacc": 0.4015567765567766, "bacc_std": 0.06328940086652717} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06313318316517905, "f1": 0.4906536363154828, "f1_std": 0.06807521599315697, "bacc": 0.5128205128205128, "bacc_std": 0.06272939723869825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.065239783031068, "f1": 0.42363834422657953, "f1_std": 0.06629884021996298, "bacc": 0.43727106227106227, "bacc_std": 0.06462289838946264} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.000774263682681127, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06423855319024808, "f1": 0.32676821844382276, "f1_std": 0.06287075943569098, "bacc": 0.3408882783882784, "bacc_std": 0.06355372551984974} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.06331143086446955, "f1": 0.480575875737166, "f1_std": 0.06575427182014103, "bacc": 0.49496336996337, "bacc_std": 0.06258026601987786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.05788383592626236, "f1": 0.45594425735554767, "f1_std": 0.0590493951132229, "bacc": 0.4933608058608059, "bacc_std": 0.05705767806590972} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05548729797608089, "f1": 0.387825311942959, "f1_std": 0.04935477698938478, "bacc": 0.4519230769230769, "bacc_std": 0.053843509900888216} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06432327516389888, "f1": 0.4223292765382015, "f1_std": 0.06567094666701749, "bacc": 0.43864468864468864, "bacc_std": 0.06388690820428121} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06228483673875981, "f1": 0.41293103448275864, "f1_std": 0.0533942280193391, "bacc": 0.4684065934065934, "bacc_std": 0.06083676076163657} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0651749012387383, "f1": 0.39701815758787273, "f1_std": 0.06537986325701309, "bacc": 0.39903846153846156, "bacc_std": 0.06508449570433472} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 9.999999999999999e-05, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.061769410383875276, "f1": 0.34678649237472764, "f1_std": 0.05958256083232817, "bacc": 0.361492673992674, "bacc_std": 0.06097350005985635} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05935820456941182, "f1": 0.4076923076923077, "f1_std": 0.05006585235273207, "bacc": 0.45054945054945056, "bacc_std": 0.05791478421012255} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06249028326834965, "f1": 0.421422558922559, "f1_std": 0.06354068442047475, "bacc": 0.440018315018315, "bacc_std": 0.0621249084018933} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.05261988284865254, "f1": 0.29867770996803256, "f1_std": 0.04520488153815294, "bacc": 0.34065934065934067, "bacc_std": 0.05135683865097888} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.05550792896077814, "f1": 0.3156989247311828, "f1_std": 0.05179834291242198, "bacc": 0.32875457875457875, "bacc_std": 0.0559804508550838} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06652841186890618, "f1": 0.5144511445465723, "f1_std": 0.06788139976221873, "bacc": 0.5173992673992673, "bacc_std": 0.06631660077887035} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06520336870086414, "f1": 0.37274286243974786, "f1_std": 0.0645016722315493, "bacc": 0.380952380952381, "bacc_std": 0.06491179251831314} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0542331559758474, "f1": 0.37589285714285714, "f1_std": 0.049170340999460556, "bacc": 0.4340659340659341, "bacc_std": 0.05258475219305428} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05318243414676643, "f1": 0.39022058823529415, "f1_std": 0.04849831662353647, "bacc": 0.4532967032967033, "bacc_std": 0.05145627013086649} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06807622772352394, "f1": 0.46360696170133553, "f1_std": 0.0703822709378761, "bacc": 0.47870879120879123, "bacc_std": 0.06812092168430067} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.060589266141765026, "f1": 0.42417582417582417, "f1_std": 0.061291119693695655, "bacc": 0.453525641025641, "bacc_std": 0.05975539104609702} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.059419081269697464, "f1": 0.3746947496947497, "f1_std": 0.04991716748621416, "bacc": 0.41346153846153844, "bacc_std": 0.05801083470874941} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05937857432405561, "f1": 0.37421788097886544, "f1_std": 0.05142017303555028, "bacc": 0.4326923076923077, "bacc_std": 0.057877753430561035} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.05609547809513609, "f1": 0.4770161290322581, "f1_std": 0.06000016400020127, "bacc": 0.4977106227106227, "bacc_std": 0.05583737981407257} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05836195972716532, "f1": 0.36210628452007765, "f1_std": 0.05889336248127792, "bacc": 0.3999542124542125, "bacc_std": 0.05747799508149825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06046266391592957, "f1": 0.3575135509168493, "f1_std": 0.06009931559223221, "bacc": 0.36904761904761907, "bacc_std": 0.0611849748234283} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06178406517913152, "f1": 0.36713381277275803, "f1_std": 0.062100202971111476, "bacc": 0.3985805860805861, "bacc_std": 0.06094421165326057} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 9.999999999999999e-05, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06356751058808945, "f1": 0.3873563218390805, "f1_std": 0.06616943554316208, "bacc": 0.39743589743589747, "bacc_std": 0.06303156060283724} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.000774263682681127, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.058977718689138425, "f1": 0.3172172030867683, "f1_std": 0.05165772239655147, "bacc": 0.32005494505494503, "bacc_std": 0.057725544782255306} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.05676447499362409, "f1": 0.5428571428571428, "f1_std": 0.06191759307626926, "bacc": 0.5663919413919415, "bacc_std": 0.05645208212854524} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06156730093465767, "f1": 0.3920284582423801, "f1_std": 0.06380491405204727, "bacc": 0.41506410256410253, "bacc_std": 0.06068667413816151} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06297783023089726, "f1": 0.36989898989898995, "f1_std": 0.06296532246525437, "bacc": 0.3823260073260073, "bacc_std": 0.06262224305522504} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06679176994618707, "f1": 0.44415007742681767, "f1_std": 0.06817257411784756, "bacc": 0.44184981684981683, "bacc_std": 0.06706898066505797} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.061321383955171095, "f1": 0.4239772727272727, "f1_std": 0.06047895100557252, "bacc": 0.4535256410256411, "bacc_std": 0.06016935552031693} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_age | train | 100 | 1.671 | 16.681 | 0.59012 | 0.12478 | 0.57215 | 0.13731 | 0.589 | 0.12628 | +| flat_mae | reg | logistic | aabc_age | test | 100 | 1.671 | 16.681 | 0.42731 | 0.06302 | 0.39957 | 0.059009 | 0.42256 | 0.061918 | + + +done! total time: 0:05:26 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..eee005efbf28ae95b353c411f694015d7ef7c7f8 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..0add51367e8cdabc1e99f41c01f605f502540104 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,train,0.8506616257088847,0.015090871622394482,0.8460038986354776,0.015608260379058412,0.8438158665105386,0.015683181914603373 +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,test,0.7636363636363637,0.054248537322704765,0.7623795280824195,0.05399756678580033,0.7803030303030303,0.05220715914091416 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,train,0.9300567107750473,0.010609345064313467,0.9282475209414007,0.010899853355238378,0.9279873384331311,0.011078525104922384 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,test,0.6909090909090909,0.059885632046592245,0.6803418803418804,0.062312056593004914,0.6793478260869565,0.06205869447657637 +flat_mae,patch,logistic,aabc_sex,2,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,2,166.81005372000556,test,0.7454545454545455,0.058703344407521625,0.7348484848484849,0.06160426238180184,0.7323369565217391,0.060888849817812334 +flat_mae,patch,logistic,aabc_sex,3,0.3593813663804626,train,0.994328922495274,0.003312297669950584,0.9941822314276811,0.003401172822321493,0.99388170813916,0.0036182218970063013 +flat_mae,patch,logistic,aabc_sex,3,0.3593813663804626,test,0.7818181818181819,0.056211395568296796,0.78,0.05648434217925837,0.7880434782608696,0.056373279418786004 +flat_mae,patch,logistic,aabc_sex,4,0.046415888336127774,train,0.9281663516068053,0.010795274351999925,0.9262625818000411,0.011123946126336146,0.9257451859667634,0.01141312906862641 +flat_mae,patch,logistic,aabc_sex,4,0.046415888336127774,test,0.7454545454545455,0.055561970465269415,0.7348484848484849,0.058766793403595814,0.7323369565217391,0.05801141347371512 +flat_mae,patch,logistic,aabc_sex,5,0.3593813663804626,train,0.994328922495274,0.003393821784919788,0.9941822314276811,0.0034839073348069366,0.99388170813916,0.0036636484183006027 +flat_mae,patch,logistic,aabc_sex,5,0.3593813663804626,test,0.7090909090909091,0.06065091552251301,0.7066666666666667,0.0608828573328687,0.7133152173913043,0.060740790775012876 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,train,0.9262759924385633,0.010984958941068169,0.9244609453091532,0.01124444510201062,0.9247193645769219,0.01130168908026061 +flat_mae,patch,logistic,aabc_sex,6,0.046415888336127774,test,0.7272727272727273,0.05851043560237922,0.7213779128672746,0.06016850107603374,0.7228260869565217,0.06019587044988747 +flat_mae,patch,logistic,aabc_sex,7,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,7,21.54434690031882,test,0.6727272727272727,0.061867744837190174,0.6673387096774194,0.06328794528129167,0.6698369565217391,0.06379448973624834 +flat_mae,patch,logistic,aabc_sex,8,0.3593813663804626,train,0.994328922495274,0.0030882614388054556,0.9941822314276811,0.003170990706289709,0.99388170813916,0.0033731185796326956 +flat_mae,patch,logistic,aabc_sex,8,0.3593813663804626,test,0.7272727272727273,0.0574680766574865,0.7239879558380728,0.05831388485667318,0.7289402173913043,0.058781968082110135 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,train,0.9924385633270322,0.003999455010561098,0.9922381665052675,0.004112618301795998,0.9916395556727923,0.004442966368467496 +flat_mae,patch,logistic,aabc_sex,9,0.3593813663804626,test,0.7818181818181819,0.05594957588152311,0.7727272727272727,0.058565752179610256,0.7697010869565217,0.0584091091425106 +flat_mae,patch,logistic,aabc_sex,10,0.005994842503189409,train,0.8506616257088847,0.01529554728027665,0.845127315715551,0.016097300992338585,0.841723086843108,0.016395313904596615 +flat_mae,patch,logistic,aabc_sex,10,0.005994842503189409,test,0.7272727272727273,0.05890572380949633,0.7083775185577943,0.0648516654700307,0.7044836956521738,0.06208469615050987 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,train,0.9262759924385633,0.01080373655517999,0.9244609453091532,0.011073650776933109,0.9247193645769219,0.01116792879783818 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,test,0.7454545454545455,0.05804277704367831,0.7303921568627451,0.06431344226440523,0.7262228260869565,0.06243357877713029 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,train,0.996219281663516,0.0027542319004089173,0.9961238606055277,0.002823421535596257,0.9961238606055277,0.002835231094146425 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,test,0.7090909090909091,0.05763813017080602,0.7010869565217391,0.0588704173205572,0.7010869565217391,0.058587691495223505 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,train,0.996219281663516,0.0024088220189689724,0.9961238606055277,0.002469782519413108,0.9961238606055277,0.00250338790291344 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,test,0.6181818181818182,0.06547453230199733,0.6176762661370407,0.06568961285593536,0.6290760869565217,0.0657276018949385 +flat_mae,patch,logistic,aabc_sex,14,0.3593813663804626,train,0.994328922495274,0.003299150658457233,0.9941893034853195,0.0033776299892968303,0.9944898736774231,0.0032420512454174122 +flat_mae,patch,logistic,aabc_sex,14,0.3593813663804626,test,0.8727272727272727,0.04300357855568581,0.8699763593380614,0.04394402425191906,0.8722826086956521,0.043879497619258655 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,train,0.996219281663516,0.002579281307733281,0.9961190832526338,0.002652853091129505,0.9955156950672646,0.003059282089217277 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,test,0.6909090909090909,0.05944092143040743,0.6694945210321668,0.06605318664493222,0.6671195652173914,0.06266771711979759 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,train,0.9281663516068053,0.010823585828382143,0.9264417447306792,0.011069829049345501,0.9269615170432897,0.011112802507949415 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,test,0.7636363636363637,0.05885756444639876,0.7585275244849713,0.06011709326215933,0.7601902173913043,0.06015387942448184 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,train,0.9281663516068053,0.011568938804103155,0.9264417447306792,0.011846077404173387,0.9269615170432897,0.011913519467576008 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,test,0.6909090909090909,0.058851543159303875,0.6754599097535579,0.06264610641071351,0.6732336956521738,0.060975447308642294 +flat_mae,patch,logistic,aabc_sex,18,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,18,166.81005372000556,test,0.6545454545454545,0.058498004486696994,0.637278722665741,0.06228674587335408,0.6358695652173914,0.06063274722182528 +flat_mae,patch,logistic,aabc_sex,19,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,19,166.81005372000556,test,0.7272727272727273,0.06249015525770626,0.7258225324027916,0.06247189013782252,0.7350543478260869,0.06175023897009066 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,train,0.9149338374291115,0.012426376318960592,0.9125128171203651,0.012845979872024491,0.9112664497787157,0.013141577504320255 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,test,0.8,0.0504825114959839,0.7931623931623932,0.05298607450028878,0.7914402173913043,0.05303487184055098 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,train,0.8431001890359168,0.01563064554188901,0.8375240992166135,0.016307763130779276,0.8345789735924265,0.01642381323715103 +flat_mae,patch,logistic,aabc_sex,21,0.005994842503189409,test,0.6545454545454545,0.06316281990365709,0.637278722665741,0.06731942084251373,0.6358695652173914,0.06554065552676862 +flat_mae,patch,logistic,aabc_sex,22,0.046415888336127774,train,0.9187145557655955,0.011890546098951063,0.916611983796763,0.012180821335246264,0.9163589202497142,0.012189418965790101 +flat_mae,patch,logistic,aabc_sex,22,0.046415888336127774,test,0.7818181818181819,0.05609432433981618,0.78,0.05633609996071867,0.7880434782608696,0.05540665705078125 +flat_mae,patch,logistic,aabc_sex,23,0.005994842503189409,train,0.8525519848771267,0.015397294659472082,0.8476382488479263,0.01607482589344868,0.845181570386002,0.016304868674839965 +flat_mae,patch,logistic,aabc_sex,23,0.005994842503189409,test,0.6727272727272727,0.06323756598783763,0.6673387096774194,0.06452013724767909,0.6698369565217391,0.06465986230442497 +flat_mae,patch,logistic,aabc_sex,24,0.3593813663804626,train,0.996219281663516,0.002718176101023617,0.9961190832526338,0.0027953847083997427,0.9955156950672646,0.0032240250166849643 +flat_mae,patch,logistic,aabc_sex,24,0.3593813663804626,test,0.7454545454545455,0.05938082724775818,0.7348484848484849,0.06340720697019447,0.7323369565217391,0.06279304474444133 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,train,0.9319470699432892,0.011461703926936196,0.9301434985474073,0.011763128225233177,0.9296213253612357,0.011860172281892085 +flat_mae,patch,logistic,aabc_sex,25,0.046415888336127774,test,0.7454545454545455,0.05710525586961225,0.741263440860215,0.057904869003620935,0.7445652173913043,0.05776302919318838 +flat_mae,patch,logistic,aabc_sex,26,0.005994842503189409,train,0.8298676748582231,0.015517082752023903,0.823163665537529,0.016382036729616155,0.8194920718661156,0.016558855559913897 +flat_mae,patch,logistic,aabc_sex,26,0.005994842503189409,test,0.7636363636363637,0.05380053764823981,0.7518222839291913,0.058453778787460935,0.7479619565217391,0.057449863381568156 +flat_mae,patch,logistic,aabc_sex,27,0.3593813663804626,train,0.996219281663516,0.002713955418025076,0.9961238606055277,0.002783333509252779,0.9961238606055277,0.0028499349817176253 +flat_mae,patch,logistic,aabc_sex,27,0.3593813663804626,test,0.7272727272727273,0.05851697782878809,0.7239879558380728,0.058992323682769916,0.7289402173913043,0.05906976899638587 +flat_mae,patch,logistic,aabc_sex,28,0.046415888336127774,train,0.9281663516068053,0.011475558259302477,0.9263533515050265,0.01178281654510451,0.9263533515050265,0.011991097396220424 +flat_mae,patch,logistic,aabc_sex,28,0.046415888336127774,test,0.7272727272727273,0.05865642785684806,0.7083775185577943,0.06498899514590395,0.7044836956521738,0.062414527803666284 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,train,0.9300567107750473,0.011365885068861676,0.9282475209414007,0.01166714007639984,0.9279873384331311,0.011815097657703862 +flat_mae,patch,logistic,aabc_sex,29,0.046415888336127774,test,0.7636363636363637,0.054155832694881834,0.7518222839291913,0.05833449714145467,0.7479619565217391,0.05716317478768701 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,train,0.9130434782608695,0.011998345970629654,0.9109557962529274,0.012270493858273638,0.9114569594654005,0.012326806931835431 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,test,0.7454545454545455,0.06060516847828239,0.7384510869565217,0.06241181705796986,0.7384510869565217,0.06226437477027643 +flat_mae,patch,logistic,aabc_sex,31,0.3593813663804626,train,0.994328922495274,0.0030814014150070943,0.9941822314276811,0.0031638978394793525,0.99388170813916,0.0033589898425415822 +flat_mae,patch,logistic,aabc_sex,31,0.3593813663804626,test,0.7454545454545455,0.06037791725922636,0.741263440860215,0.06118763086967882,0.7445652173913043,0.06126756605182177 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,train,0.9319470699432892,0.010544663375746645,0.9301434985474073,0.01083594590153545,0.9296213253612357,0.01096867130029426 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,test,0.7636363636363637,0.05727128425310541,0.7585275244849713,0.05838204451522331,0.7601902173913043,0.05806208055278851 +flat_mae,patch,logistic,aabc_sex,33,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,33,2.782559402207126,test,0.8181818181818182,0.05238659850075529,0.8106060606060606,0.05544783827040848,0.8070652173913043,0.05544762046306893 +flat_mae,patch,logistic,aabc_sex,34,0.3593813663804626,train,0.996219281663516,0.002651855241052207,0.9961190832526338,0.0027272227506526464,0.9955156950672646,0.0031453619338937637 +flat_mae,patch,logistic,aabc_sex,34,0.3593813663804626,test,0.6181818181818182,0.06491674006368364,0.5990975355779243,0.06835076033920359,0.5985054347826086,0.06628256775429384 +flat_mae,patch,logistic,aabc_sex,35,0.046415888336127774,train,0.9357277882797732,0.011003334992429071,0.9339410589410589,0.011342156352169324,0.9328892992174448,0.011601022123732851 +flat_mae,patch,logistic,aabc_sex,35,0.046415888336127774,test,0.6363636363636364,0.06291118230890383,0.6263586956521738,0.06418775965944291,0.6263586956521738,0.06386222034386947 +flat_mae,patch,logistic,aabc_sex,36,0.3593813663804626,train,0.9924385633270322,0.0037410012121093183,0.9922477212110554,0.0038345250211468066,0.9922477212110554,0.003855723765552007 +flat_mae,patch,logistic,aabc_sex,36,0.3593813663804626,test,0.7090909090909091,0.059679308262669616,0.6918767507002801,0.06496551984890338,0.6888586956521738,0.06278995858014699 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,train,0.9357277882797732,0.01076254307126015,0.9339410589410589,0.01108339228426199,0.9328892992174448,0.01129351363131567 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,test,0.7454545454545455,0.05921800039048883,0.7348484848484849,0.06309596908080636,0.7323369565217391,0.061869823657258925 +flat_mae,patch,logistic,aabc_sex,38,0.046415888336127774,train,0.9224952741020794,0.01161214632997336,0.9205871476326994,0.01191428070375298,0.9208432251824497,0.012166591804098343 +flat_mae,patch,logistic,aabc_sex,38,0.046415888336127774,test,0.7636363636363637,0.05753619055116958,0.7585275244849713,0.05889780105391976,0.7601902173913043,0.05902126489870734 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,train,0.9262759924385633,0.011936802556078829,0.9244609453091532,0.012232347627418186,0.9247193645769219,0.012323841003914735 +flat_mae,patch,logistic,aabc_sex,39,0.046415888336127774,test,0.7636363636363637,0.05676002550975262,0.7555555555555555,0.05952719048182725,0.7540760869565217,0.05912198504004762 +flat_mae,patch,logistic,aabc_sex,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,40,21.54434690031882,test,0.7454545454545455,0.05683970210633753,0.7348484848484849,0.05976209040638553,0.7323369565217391,0.0586073988671487 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,train,0.9395085066162571,0.010221932578144253,0.9379053320421398,0.010492762797403946,0.9373736041501802,0.010602931246573603 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,test,0.6545454545454545,0.06329423876749785,0.6427350427350427,0.06551196995725968,0.6419836956521738,0.06473735191287484 +flat_mae,patch,logistic,aabc_sex,42,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,42,166.81005372000556,test,0.7454545454545455,0.05821566061203693,0.7384510869565217,0.059817929476071785,0.7384510869565217,0.059473417401575496 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,train,0.9300567107750473,0.011510669396272885,0.9279718555536338,0.011926790838715891,0.9261628418183416,0.01231975511517555 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,test,0.7818181818181819,0.05908412828227249,0.7782258064516129,0.05987452018827968,0.7819293478260869,0.05986709893849308 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,train,0.9338374291115312,0.010512824922542477,0.9319544133158395,0.010865860051578786,0.9306471467510771,0.0112015996381856 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,test,0.7818181818181819,0.05561704952932245,0.7758152173913043,0.05696206486525225,0.7758152173913043,0.056417639213274605 +flat_mae,patch,logistic,aabc_sex,45,0.005994842503189409,train,0.8393194706994329,0.015066577637761274,0.834307992202729,0.01561207885687196,0.8325273308127437,0.01579123180209247 +flat_mae,patch,logistic,aabc_sex,45,0.005994842503189409,test,0.7272727272727273,0.057891765640077184,0.717948717948718,0.06049730386883231,0.7167119565217391,0.05993542935012728 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,train,0.9281663516068053,0.011222175753415622,0.9262625818000411,0.011549585284442412,0.9257451859667634,0.011784110479865627 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,test,0.7454545454545455,0.05861921948100285,0.741263440860215,0.05941766072832224,0.7445652173913043,0.05968150195270569 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,train,0.9281663516068053,0.011396991572855808,0.9262625818000411,0.011698980208218348,0.9257451859667634,0.011808650227523742 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,test,0.7636363636363637,0.059478460577987995,0.7518222839291913,0.0634909806367939,0.7479619565217391,0.062492005913024076 +flat_mae,patch,logistic,aabc_sex,48,0.3593813663804626,train,0.994328922495274,0.0031302407179831034,0.9941822314276811,0.003214311196786194,0.99388170813916,0.003432087267655881 +flat_mae,patch,logistic,aabc_sex,48,0.3593813663804626,test,0.8181818181818182,0.05146371906659376,0.8131793478260869,0.05287543825138895,0.8131793478260869,0.052609746665750114 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,train,0.831758034026465,0.016629699653543713,0.8249939596691758,0.01749776985707685,0.8211260587942202,0.017565670015851083 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,test,0.7090909090909091,0.05970191519278048,0.6918767507002801,0.0655964578187696,0.6888586956521738,0.06357891416067643 +flat_mae,patch,logistic,aabc_sex,50,0.000774263682681127,train,0.7561436672967864,0.017524139287788416,0.7383367139959431,0.019707016642475306,0.7332644567543012,0.018938711643373806 +flat_mae,patch,logistic,aabc_sex,50,0.000774263682681127,test,0.7636363636363637,0.054593142789817674,0.7472605160834218,0.05951947039449525,0.7418478260869565,0.05758231481374666 +flat_mae,patch,logistic,aabc_sex,51,0.3593813663804626,train,0.994328922495274,0.003148344247019896,0.9941749710950833,0.0032413586160996736,0.9932735426008968,0.003734246875949616 +flat_mae,patch,logistic,aabc_sex,51,0.3593813663804626,test,0.7636363636363637,0.056571066985118025,0.7555555555555555,0.05899458597472636,0.7540760869565217,0.058688641200143554 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,train,0.9243856332703214,0.01123328403841773,0.9223816650526748,0.011534506130990493,0.9218690465722911,0.01166624532700488 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,test,0.7272727272727273,0.0586298206356509,0.7136410968413746,0.06285186591391409,0.7105978260869565,0.06182117861397927 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,train,0.9187145557655955,0.012126509523867238,0.9167133499562459,0.012386458735015137,0.9169670857879774,0.012300863307520745 +flat_mae,patch,logistic,aabc_sex,53,0.046415888336127774,test,0.7454545454545455,0.056144512474432764,0.7348484848484849,0.05938099005616225,0.7323369565217391,0.05916052635552334 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.9376181474480151,0.010736989799793544,0.9360823383385143,0.010999170925865059,0.9363477827603388,0.011104546416098067 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.7090909090909091,0.05972494529850231,0.7010869565217391,0.061568100996957885,0.7010869565217391,0.061197984763130944 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,test,0.7090909090909091,0.062058346313025765,0.7082228116710876,0.06191368306501306,0.7194293478260869,0.06104089581354641 +flat_mae,patch,logistic,aabc_sex,56,0.046415888336127774,train,0.9224952741020794,0.011583846433444168,0.9205871476326994,0.011853370274849314,0.9208432251824497,0.011875950182655328 +flat_mae,patch,logistic,aabc_sex,56,0.046415888336127774,test,0.8363636363636363,0.04894360390936043,0.8281846581048247,0.05325521841818853,0.8226902173913043,0.05326223510616367 +flat_mae,patch,logistic,aabc_sex,57,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,57,10000.0,test,0.7636363636363637,0.055512625322965345,0.7518222839291913,0.06003229339578201,0.7479619565217391,0.05889944133631518 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,train,0.996219281663516,0.002781568289923409,0.9961238606055277,0.002852149858879429,0.9961238606055277,0.002906340192865927 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,test,0.8,0.054456606426319595,0.795677136102668,0.05575505403658943,0.7975543478260869,0.0560001680400984 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,train,0.8260869565217391,0.015509368820959558,0.8195074914701083,0.01620844323543602,0.8162240980099065,0.016219350689687537 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,test,0.7818181818181819,0.05545305512155348,0.7758152173913043,0.05721137034518433,0.7758152173913043,0.05687625408563058 +flat_mae,patch,logistic,aabc_sex,60,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,60,21.54434690031882,test,0.7272727272727273,0.05985630175264868,0.7213779128672746,0.06108857001897618,0.7228260869565217,0.06129108399190027 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,train,0.9357277882797732,0.01135544275206752,0.9340244152947736,0.011666971756202987,0.9334974647557079,0.011769487565526425 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,test,0.6545454545454545,0.0649747668759074,0.6540880503144654,0.06519884890526467,0.6664402173913043,0.06434666728355824 +flat_mae,patch,logistic,aabc_sex,62,0.046415888336127774,train,0.9319470699432892,0.011157229706111077,0.9300552388787683,0.011529678441136901,0.9290131598229725,0.011909783356048396 +flat_mae,patch,logistic,aabc_sex,62,0.046415888336127774,test,0.7636363636363637,0.05321145716435249,0.7555555555555555,0.05587686549829248,0.7540760869565217,0.05561255655353503 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,train,0.9281663516068053,0.011384105784014296,0.9262625818000411,0.011751514658778483,0.9257451859667634,0.012159927804155103 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,test,0.8,0.05478660631399755,0.7975911676145868,0.05518302074143437,0.8036684782608696,0.05457026522302871 +flat_mae,patch,logistic,aabc_sex,64,0.046415888336127774,train,0.941398865784499,0.010304833842578649,0.9401638297484174,0.01049909720631321,0.9420484187696005,0.010454523671360037 +flat_mae,patch,logistic,aabc_sex,64,0.046415888336127774,test,0.6545454545454545,0.06326414779868782,0.6470786896318811,0.06477661711052035,0.6480978260869565,0.06487498251406151 +flat_mae,patch,logistic,aabc_sex,65,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,65,166.81005372000556,test,0.8,0.05521499377152986,0.795677136102668,0.05634808214693229,0.7975543478260869,0.056408938052215085 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,train,0.8506616257088847,0.01566141796193983,0.8455759815242494,0.016286153464246677,0.8429394179196342,0.016413720839359516 +flat_mae,patch,logistic,aabc_sex,66,0.005994842503189409,test,0.6909090909090909,0.05860861640881291,0.6694945210321668,0.0643655594168592,0.6671195652173914,0.061391518748567145 +flat_mae,patch,logistic,aabc_sex,67,0.3593813663804626,train,0.996219281663516,0.0026543227702787277,0.9961238606055277,0.0027214569268102988,0.9961238606055277,0.0027585034966007083 +flat_mae,patch,logistic,aabc_sex,67,0.3593813663804626,test,0.8,0.055251897989163745,0.795677136102668,0.05656716829810373,0.7975543478260869,0.056559571939977016 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,test,0.7818181818181819,0.05629968219160772,0.7758152173913043,0.05760833087537815,0.7758152173913043,0.05721014481818375 +flat_mae,patch,logistic,aabc_sex,69,0.3593813663804626,train,0.996219281663516,0.002770737808581349,0.9961285128805621,0.0028322302747594372,0.9967320261437909,0.002394967811665902 +flat_mae,patch,logistic,aabc_sex,69,0.3593813663804626,test,0.8181818181818182,0.05080158779323779,0.8074229691876751,0.05508206052427673,0.8009510869565217,0.054370448739273755 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,train,0.996219281663516,0.002811642216990085,0.9961238606055277,0.0028815235075275586,0.9961238606055277,0.0028736585683685916 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,test,0.7818181818181819,0.056247516749594086,0.78,0.05642779996022463,0.7880434782608696,0.05556511373484923 +flat_mae,patch,logistic,aabc_sex,71,0.046415888336127774,train,0.9243856332703214,0.012087935069686162,0.9225702576112412,0.012375410391030886,0.9230853776488174,0.012453796654914326 +flat_mae,patch,logistic,aabc_sex,71,0.046415888336127774,test,0.7272727272727273,0.05891847287804558,0.7136410968413746,0.06378533516687401,0.7105978260869565,0.06239086080253926 +flat_mae,patch,logistic,aabc_sex,72,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,72,166.81005372000556,test,0.6181818181818182,0.060237282873100165,0.591728525980912,0.0654032013739891,0.592391304347826,0.06182170225756517 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,train,0.9300567107750473,0.01139170713213754,0.9282475209414007,0.011698697592485336,0.9279873384331311,0.01183027450155213 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,test,0.7818181818181819,0.0571510858301944,0.78,0.05720512215278529,0.7880434782608696,0.05625519043738124 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,train,0.9243856332703214,0.011603957089748429,0.9224772121105542,0.011922579266532276,0.9224772121105542,0.012111361000445216 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,test,0.7272727272727273,0.0564680674773637,0.7083775185577943,0.062225104959607605,0.7044836956521738,0.05972827854867801 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,train,0.9262759924385633,0.011031527131678145,0.9244609453091532,0.011311934698063637,0.9247193645769219,0.011474313900543957 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,test,0.7818181818181819,0.05550072592779661,0.7782258064516129,0.05640221240388509,0.7819293478260869,0.05637577625417037 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,train,0.9376181474480151,0.010456009750761481,0.9360823383385143,0.010709114120785708,0.9363477827603388,0.010779640653230201 +flat_mae,patch,logistic,aabc_sex,76,0.046415888336127774,test,0.7272727272727273,0.06004396185605928,0.7136410968413746,0.06369866181292706,0.7105978260869565,0.062360657686652776 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,train,0.9924385633270322,0.003593987917896189,0.9922283598754187,0.003705126551253609,0.9910313901345291,0.004262824234455349 +flat_mae,patch,logistic,aabc_sex,77,0.3593813663804626,test,0.6909090909090909,0.056804271751833946,0.6623329721921272,0.06507068767505052,0.6610054347826086,0.06040128972749116 +flat_mae,patch,logistic,aabc_sex,78,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,78,166.81005372000556,test,0.7090909090909091,0.061275165853820625,0.696969696969697,0.06483605930009796,0.6949728260869565,0.06388359787065237 +flat_mae,patch,logistic,aabc_sex,79,0.005994842503189409,train,0.8374291115311909,0.01544386928556153,0.8317728671163176,0.01610630947934334,0.8290688472698496,0.016222312589172238 +flat_mae,patch,logistic,aabc_sex,79,0.005994842503189409,test,0.7818181818181819,0.05367148310950194,0.76890756302521,0.05930701113888251,0.7635869565217391,0.05788373580860351 +flat_mae,patch,logistic,aabc_sex,80,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,80,2.782559402207126,test,0.8,0.05599641074684093,0.7989365237620472,0.05601892155356306,0.8097826086956521,0.054499141866108776 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,train,0.9262759924385633,0.01103885008529643,0.9243690085598548,0.011323249566955296,0.9241111990386588,0.011425384234864541 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,test,0.7090909090909091,0.05161428465226744,0.6696696696696697,0.06451894745597272,0.670516304347826,0.056425415022138777 +flat_mae,patch,logistic,aabc_sex,82,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,82,166.81005372000556,test,0.7818181818181819,0.05423342264905843,0.7811671087533156,0.05422661118361694,0.7941576086956521,0.052722062121492455 +flat_mae,patch,logistic,aabc_sex,83,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,83,21.54434690031882,test,0.7636363636363637,0.055692793723490584,0.7585275244849713,0.05716357565759338,0.7601902173913043,0.05787720499957419 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,train,0.9300567107750473,0.012327657553441718,0.9282475209414007,0.012646802980332826,0.9279873384331311,0.012772929219286399 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,test,0.7454545454545455,0.06016549078160782,0.7384510869565217,0.06230789907992237,0.7384510869565217,0.06215336975509371 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,train,0.9281663516068053,0.010881984521668579,0.9263533515050265,0.011166208728176695,0.9263533515050265,0.011314540384858171 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,test,0.7090909090909091,0.061419204469660406,0.6918767507002801,0.06724662955926493,0.6888586956521738,0.06485517904664953 +flat_mae,patch,logistic,aabc_sex,86,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,86,21.54434690031882,test,0.8181818181818182,0.04763124191758565,0.8106060606060606,0.05040513531186905,0.8070652173913043,0.050411593270237275 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,train,0.9224952741020794,0.011581946002019977,0.9207728021566572,0.011819015893350302,0.922059556258976,0.011844607444200619 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,test,0.6363636363636364,0.06128039876442772,0.6148459383753502,0.06619553396220339,0.6141304347826086,0.06347499642626063 +flat_mae,patch,logistic,aabc_sex,88,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,88,2.782559402207126,test,0.7090909090909091,0.06141570585460886,0.7010869565217391,0.06286380688066105,0.7010869565217391,0.06257828680353213 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,train,0.9319470699432892,0.010448310455254706,0.9302294908994988,0.010703543668249525,0.9302294908994988,0.010757177492908282 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,test,0.6909090909090909,0.06468296747206129,0.6803418803418804,0.06715178461016298,0.6793478260869565,0.06643907841114952 +flat_mae,patch,logistic,aabc_sex,90,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,90,2.782559402207126,test,0.6909090909090909,0.06274651615234267,0.6803418803418804,0.06485063480057303,0.6793478260869565,0.06425217688444314 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,train,0.9262759924385633,0.01150848425981946,0.9243690085598548,0.011819972871137565,0.9241111990386588,0.011962696171546825 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,test,0.6727272727272727,0.06208813783247276,0.6637228260869565,0.06386039126513159,0.6637228260869565,0.06360053150513527 +flat_mae,patch,logistic,aabc_sex,92,0.046415888336127774,train,0.9357277882797732,0.010716636692881362,0.9340244152947736,0.011003991298375934,0.9334974647557079,0.011138633570765558 +flat_mae,patch,logistic,aabc_sex,92,0.046415888336127774,test,0.7272727272727273,0.05397856936241664,0.7020585048754062,0.06398106456460491,0.6983695652173914,0.05906705200200019 +flat_mae,patch,logistic,aabc_sex,93,0.005994842503189409,train,0.8544423440453687,0.014635567949351386,0.8496965000645744,0.015229379394125978,0.8474237228523697,0.01544513517980186 +flat_mae,patch,logistic,aabc_sex,93,0.005994842503189409,test,0.6909090909090909,0.057388903814167225,0.6623329721921272,0.06642024737230977,0.6610054347826086,0.06117769152747517 +flat_mae,patch,logistic,aabc_sex,94,0.046415888336127774,train,0.9206049149338374,0.011315994405039935,0.9186010727160819,0.01158247956671043,0.9186010727160819,0.011608841629864182 +flat_mae,patch,logistic,aabc_sex,94,0.046415888336127774,test,0.8,0.05625096068968418,0.7931623931623932,0.05861868899274305,0.7914402173913043,0.05856909002184618 +flat_mae,patch,logistic,aabc_sex,95,0.3593813663804626,train,0.9886578449905482,0.004757512402940818,0.9883572497579012,0.0048914202867483166,0.98776341627832,0.005165073030443774 +flat_mae,patch,logistic,aabc_sex,95,0.3593813663804626,test,0.8,0.05313834742389103,0.7931623931623932,0.0557110863702641,0.7914402173913043,0.05588930286503917 +flat_mae,patch,logistic,aabc_sex,96,0.046415888336127774,train,0.9206049149338374,0.012263202126993413,0.9186010727160819,0.01255908729018194,0.9186010727160819,0.012577801388422355 +flat_mae,patch,logistic,aabc_sex,96,0.046415888336127774,test,0.6909090909090909,0.06074816189444517,0.6892655367231638,0.06078603447551249,0.6976902173913043,0.06042438378239402 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,train,0.996219281663516,0.002747195964343182,0.9961190832526338,0.0028257174329615036,0.9955156950672646,0.0032584454375281274 +flat_mae,patch,logistic,aabc_sex,97,0.3593813663804626,test,0.7454545454545455,0.05744178224173967,0.7348484848484849,0.06070414212714564,0.7323369565217391,0.059760747902151884 +flat_mae,patch,logistic,aabc_sex,98,0.3593813663804626,train,0.9924385633270322,0.003884214782199223,0.9922381665052675,0.00399319946918552,0.9916395556727923,0.004319350814242418 +flat_mae,patch,logistic,aabc_sex,98,0.3593813663804626,test,0.6909090909090909,0.05964190661601446,0.6754599097535579,0.0635831110933265,0.6732336956521738,0.06212827256245735 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,train,0.9262759924385633,0.010979228832380138,0.9243690085598548,0.011247653646601864,0.9241111990386588,0.011262265841082607 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,test,0.7636363636363637,0.056320969187753984,0.7555555555555555,0.058771768862086474,0.7540760869565217,0.05804841316637023 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,train,0.9924385633270322,0.003643002177812924,0.9922477212110554,0.003735479983408941,0.9922477212110554,0.003803609326052018 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,test,0.7818181818181819,0.056135609122643766,0.78,0.05642636957451899,0.7880434782608696,0.056015518218168796 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..bc149fd7b3bdebb4ad1633cdf49a88412441541c --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:45:49 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:26:59 time: 6.8639 data: 5.5448 max mem: 3205 +extract (train) [ 20/236] eta: 0:02:07 time: 0.2789 data: 0.1043 max mem: 3581 +extract (train) [ 40/236] eta: 0:01:22 time: 0.2367 data: 0.0830 max mem: 3581 +extract (train) [ 60/236] eta: 0:01:03 time: 0.2364 data: 0.0842 max mem: 3581 +extract (train) [ 80/236] eta: 0:00:51 time: 0.2338 data: 0.0813 max mem: 3581 +extract (train) [100/236] eta: 0:00:41 time: 0.2276 data: 0.0778 max mem: 3581 +extract (train) [120/236] eta: 0:00:34 time: 0.2214 data: 0.0754 max mem: 3581 +extract (train) [140/236] eta: 0:00:27 time: 0.2419 data: 0.0865 max mem: 3581 +extract (train) [160/236] eta: 0:00:21 time: 0.2102 data: 0.0690 max mem: 3581 +extract (train) [180/236] eta: 0:00:15 time: 0.2249 data: 0.0783 max mem: 3581 +extract (train) [200/236] eta: 0:00:09 time: 0.2713 data: 0.1055 max mem: 3581 +extract (train) [220/236] eta: 0:00:04 time: 0.2015 data: 0.0677 max mem: 3581 +extract (train) [235/236] eta: 0:00:00 time: 0.1996 data: 0.0643 max mem: 3581 +extract (train) Total time: 0:01:01 (0.2627 s / it) +extract (validation) [ 0/29] eta: 0:02:28 time: 5.1228 data: 4.9308 max mem: 3581 +extract (validation) [20/29] eta: 0:00:04 time: 0.2179 data: 0.0729 max mem: 3581 +extract (validation) [28/29] eta: 0:00:00 time: 0.1857 data: 0.0554 max mem: 3581 +extract (validation) Total time: 0:00:11 (0.3901 s / it) +extract (test) [ 0/28] eta: 0:02:15 time: 4.8452 data: 4.6841 max mem: 3581 +extract (test) [20/28] eta: 0:00:03 time: 0.2177 data: 0.0745 max mem: 3581 +extract (test) [27/28] eta: 0:00:00 time: 0.1962 data: 0.0647 max mem: 3581 +extract (test) Total time: 0:00:10 (0.3891 s / it) +feature extraction time: 0:01:24 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | train | 0.85066 | 0.015091 | 0.846 | 0.015608 | 0.84382 | 0.015683 | +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | test | 0.76364 | 0.054249 | 0.76238 | 0.053998 | 0.7803 | 0.052207 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.059885632046592245, "f1": 0.6803418803418804, "f1_std": 0.062312056593004914, "bacc": 0.6793478260869565, "bacc_std": 0.06205869447657637} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 166.81005372000556, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.058703344407521625, "f1": 0.7348484848484849, "f1_std": 0.06160426238180184, "bacc": 0.7323369565217391, "bacc_std": 0.060888849817812334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.056211395568296796, "f1": 0.78, "f1_std": 0.05648434217925837, "bacc": 0.7880434782608696, "bacc_std": 0.056373279418786004} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.055561970465269415, "f1": 0.7348484848484849, "f1_std": 0.058766793403595814, "bacc": 0.7323369565217391, "bacc_std": 0.05801141347371512} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06065091552251301, "f1": 0.7066666666666667, "f1_std": 0.0608828573328687, "bacc": 0.7133152173913043, "bacc_std": 0.060740790775012876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05851043560237922, "f1": 0.7213779128672746, "f1_std": 0.06016850107603374, "bacc": 0.7228260869565217, "bacc_std": 0.06019587044988747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 21.54434690031882, "split": "test", "acc": 0.6727272727272727, "acc_std": 0.061867744837190174, "f1": 0.6673387096774194, "f1_std": 0.06328794528129167, "bacc": 0.6698369565217391, "bacc_std": 0.06379448973624834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.0574680766574865, "f1": 0.7239879558380728, "f1_std": 0.05831388485667318, "bacc": 0.7289402173913043, "bacc_std": 0.058781968082110135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05594957588152311, "f1": 0.7727272727272727, "f1_std": 0.058565752179610256, "bacc": 0.7697010869565217, "bacc_std": 0.0584091091425106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05890572380949633, "f1": 0.7083775185577943, "f1_std": 0.0648516654700307, "bacc": 0.7044836956521738, "bacc_std": 0.06208469615050987} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05804277704367831, "f1": 0.7303921568627451, "f1_std": 0.06431344226440523, "bacc": 0.7262228260869565, "bacc_std": 0.06243357877713029} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.05763813017080602, "f1": 0.7010869565217391, "f1_std": 0.0588704173205572, "bacc": 0.7010869565217391, "bacc_std": 0.058587691495223505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.6181818181818182, "acc_std": 0.06547453230199733, "f1": 0.6176762661370407, "f1_std": 0.06568961285593536, "bacc": 0.6290760869565217, "bacc_std": 0.0657276018949385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04300357855568581, "f1": 0.8699763593380614, "f1_std": 0.04394402425191906, "bacc": 0.8722826086956521, "bacc_std": 0.043879497619258655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.05944092143040743, "f1": 0.6694945210321668, "f1_std": 0.06605318664493222, "bacc": 0.6671195652173914, "bacc_std": 0.06266771711979759} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05885756444639876, "f1": 0.7585275244849713, "f1_std": 0.06011709326215933, "bacc": 0.7601902173913043, "bacc_std": 0.06015387942448184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.058851543159303875, "f1": 0.6754599097535579, "f1_std": 0.06264610641071351, "bacc": 0.6732336956521738, "bacc_std": 0.060975447308642294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 166.81005372000556, "split": "test", "acc": 0.6545454545454545, "acc_std": 0.058498004486696994, "f1": 0.637278722665741, "f1_std": 0.06228674587335408, "bacc": 0.6358695652173914, "bacc_std": 0.06063274722182528} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 166.81005372000556, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.06249015525770626, "f1": 0.7258225324027916, "f1_std": 0.06247189013782252, "bacc": 0.7350543478260869, "bacc_std": 0.06175023897009066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.0504825114959839, "f1": 0.7931623931623932, "f1_std": 0.05298607450028878, "bacc": 0.7914402173913043, "bacc_std": 0.05303487184055098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.6545454545454545, "acc_std": 0.06316281990365709, "f1": 0.637278722665741, "f1_std": 0.06731942084251373, "bacc": 0.6358695652173914, "bacc_std": 0.06554065552676862} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05609432433981618, "f1": 0.78, "f1_std": 0.05633609996071867, "bacc": 0.7880434782608696, "bacc_std": 0.05540665705078125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6727272727272727, "acc_std": 0.06323756598783763, "f1": 0.6673387096774194, "f1_std": 0.06452013724767909, "bacc": 0.6698369565217391, "bacc_std": 0.06465986230442497} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05938082724775818, "f1": 0.7348484848484849, "f1_std": 0.06340720697019447, "bacc": 0.7323369565217391, "bacc_std": 0.06279304474444133} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05710525586961225, "f1": 0.741263440860215, "f1_std": 0.057904869003620935, "bacc": 0.7445652173913043, "bacc_std": 0.05776302919318838} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05380053764823981, "f1": 0.7518222839291913, "f1_std": 0.058453778787460935, "bacc": 0.7479619565217391, "bacc_std": 0.057449863381568156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05851697782878809, "f1": 0.7239879558380728, "f1_std": 0.058992323682769916, "bacc": 0.7289402173913043, "bacc_std": 0.05906976899638587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05865642785684806, "f1": 0.7083775185577943, "f1_std": 0.06498899514590395, "bacc": 0.7044836956521738, "bacc_std": 0.062414527803666284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.054155832694881834, "f1": 0.7518222839291913, "f1_std": 0.05833449714145467, "bacc": 0.7479619565217391, "bacc_std": 0.05716317478768701} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.06060516847828239, "f1": 0.7384510869565217, "f1_std": 0.06241181705796986, "bacc": 0.7384510869565217, "bacc_std": 0.06226437477027643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.06037791725922636, "f1": 0.741263440860215, "f1_std": 0.06118763086967882, "bacc": 0.7445652173913043, "bacc_std": 0.06126756605182177} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05727128425310541, "f1": 0.7585275244849713, "f1_std": 0.05838204451522331, "bacc": 0.7601902173913043, "bacc_std": 0.05806208055278851} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 2.782559402207126, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05238659850075529, "f1": 0.8106060606060606, "f1_std": 0.05544783827040848, "bacc": 0.8070652173913043, "bacc_std": 0.05544762046306893} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.6181818181818182, "acc_std": 0.06491674006368364, "f1": 0.5990975355779243, "f1_std": 0.06835076033920359, "bacc": 0.5985054347826086, "bacc_std": 0.06628256775429384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.6363636363636364, "acc_std": 0.06291118230890383, "f1": 0.6263586956521738, "f1_std": 0.06418775965944291, "bacc": 0.6263586956521738, "bacc_std": 0.06386222034386947} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.059679308262669616, "f1": 0.6918767507002801, "f1_std": 0.06496551984890338, "bacc": 0.6888586956521738, "bacc_std": 0.06278995858014699} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05921800039048883, "f1": 0.7348484848484849, "f1_std": 0.06309596908080636, "bacc": 0.7323369565217391, "bacc_std": 0.061869823657258925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05753619055116958, "f1": 0.7585275244849713, "f1_std": 0.05889780105391976, "bacc": 0.7601902173913043, "bacc_std": 0.05902126489870734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05676002550975262, "f1": 0.7555555555555555, "f1_std": 0.05952719048182725, "bacc": 0.7540760869565217, "bacc_std": 0.05912198504004762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05683970210633753, "f1": 0.7348484848484849, "f1_std": 0.05976209040638553, "bacc": 0.7323369565217391, "bacc_std": 0.0586073988671487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.6545454545454545, "acc_std": 0.06329423876749785, "f1": 0.6427350427350427, "f1_std": 0.06551196995725968, "bacc": 0.6419836956521738, "bacc_std": 0.06473735191287484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 166.81005372000556, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05821566061203693, "f1": 0.7384510869565217, "f1_std": 0.059817929476071785, "bacc": 0.7384510869565217, "bacc_std": 0.059473417401575496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05908412828227249, "f1": 0.7782258064516129, "f1_std": 0.05987452018827968, "bacc": 0.7819293478260869, "bacc_std": 0.05986709893849308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05561704952932245, "f1": 0.7758152173913043, "f1_std": 0.05696206486525225, "bacc": 0.7758152173913043, "bacc_std": 0.056417639213274605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.057891765640077184, "f1": 0.717948717948718, "f1_std": 0.06049730386883231, "bacc": 0.7167119565217391, "bacc_std": 0.05993542935012728} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05861921948100285, "f1": 0.741263440860215, "f1_std": 0.05941766072832224, "bacc": 0.7445652173913043, "bacc_std": 0.05968150195270569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.059478460577987995, "f1": 0.7518222839291913, "f1_std": 0.0634909806367939, "bacc": 0.7479619565217391, "bacc_std": 0.062492005913024076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05146371906659376, "f1": 0.8131793478260869, "f1_std": 0.05287543825138895, "bacc": 0.8131793478260869, "bacc_std": 0.052609746665750114} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.05970191519278048, "f1": 0.6918767507002801, "f1_std": 0.0655964578187696, "bacc": 0.6888586956521738, "bacc_std": 0.06357891416067643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.000774263682681127, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.054593142789817674, "f1": 0.7472605160834218, "f1_std": 0.05951947039449525, "bacc": 0.7418478260869565, "bacc_std": 0.05758231481374666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.056571066985118025, "f1": 0.7555555555555555, "f1_std": 0.05899458597472636, "bacc": 0.7540760869565217, "bacc_std": 0.058688641200143554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.0586298206356509, "f1": 0.7136410968413746, "f1_std": 0.06285186591391409, "bacc": 0.7105978260869565, "bacc_std": 0.06182117861397927} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.056144512474432764, "f1": 0.7348484848484849, "f1_std": 0.05938099005616225, "bacc": 0.7323369565217391, "bacc_std": 0.05916052635552334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.05972494529850231, "f1": 0.7010869565217391, "f1_std": 0.061568100996957885, "bacc": 0.7010869565217391, "bacc_std": 0.061197984763130944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.062058346313025765, "f1": 0.7082228116710876, "f1_std": 0.06191368306501306, "bacc": 0.7194293478260869, "bacc_std": 0.06104089581354641} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04894360390936043, "f1": 0.8281846581048247, "f1_std": 0.05325521841818853, "bacc": 0.8226902173913043, "bacc_std": 0.05326223510616367} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 10000.0, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.055512625322965345, "f1": 0.7518222839291913, "f1_std": 0.06003229339578201, "bacc": 0.7479619565217391, "bacc_std": 0.05889944133631518} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.054456606426319595, "f1": 0.795677136102668, "f1_std": 0.05575505403658943, "bacc": 0.7975543478260869, "bacc_std": 0.0560001680400984} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05545305512155348, "f1": 0.7758152173913043, "f1_std": 0.05721137034518433, "bacc": 0.7758152173913043, "bacc_std": 0.05687625408563058} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 21.54434690031882, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05985630175264868, "f1": 0.7213779128672746, "f1_std": 0.06108857001897618, "bacc": 0.7228260869565217, "bacc_std": 0.06129108399190027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.6545454545454545, "acc_std": 0.0649747668759074, "f1": 0.6540880503144654, "f1_std": 0.06519884890526467, "bacc": 0.6664402173913043, "bacc_std": 0.06434666728355824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05321145716435249, "f1": 0.7555555555555555, "f1_std": 0.05587686549829248, "bacc": 0.7540760869565217, "bacc_std": 0.05561255655353503} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05478660631399755, "f1": 0.7975911676145868, "f1_std": 0.05518302074143437, "bacc": 0.8036684782608696, "bacc_std": 0.05457026522302871} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.6545454545454545, "acc_std": 0.06326414779868782, "f1": 0.6470786896318811, "f1_std": 0.06477661711052035, "bacc": 0.6480978260869565, "bacc_std": 0.06487498251406151} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 166.81005372000556, "split": "test", "acc": 0.8, "acc_std": 0.05521499377152986, "f1": 0.795677136102668, "f1_std": 0.05634808214693229, "bacc": 0.7975543478260869, "bacc_std": 0.056408938052215085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.05860861640881291, "f1": 0.6694945210321668, "f1_std": 0.0643655594168592, "bacc": 0.6671195652173914, "bacc_std": 0.061391518748567145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.055251897989163745, "f1": 0.795677136102668, "f1_std": 0.05656716829810373, "bacc": 0.7975543478260869, "bacc_std": 0.056559571939977016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 21.54434690031882, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05629968219160772, "f1": 0.7758152173913043, "f1_std": 0.05760833087537815, "bacc": 0.7758152173913043, "bacc_std": 0.05721014481818375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05080158779323779, "f1": 0.8074229691876751, "f1_std": 0.05508206052427673, "bacc": 0.8009510869565217, "bacc_std": 0.054370448739273755} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.056247516749594086, "f1": 0.78, "f1_std": 0.05642779996022463, "bacc": 0.7880434782608696, "bacc_std": 0.05556511373484923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05891847287804558, "f1": 0.7136410968413746, "f1_std": 0.06378533516687401, "bacc": 0.7105978260869565, "bacc_std": 0.06239086080253926} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 166.81005372000556, "split": "test", "acc": 0.6181818181818182, "acc_std": 0.060237282873100165, "f1": 0.591728525980912, "f1_std": 0.0654032013739891, "bacc": 0.592391304347826, "bacc_std": 0.06182170225756517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.0571510858301944, "f1": 0.78, "f1_std": 0.05720512215278529, "bacc": 0.7880434782608696, "bacc_std": 0.05625519043738124} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.0564680674773637, "f1": 0.7083775185577943, "f1_std": 0.062225104959607605, "bacc": 0.7044836956521738, "bacc_std": 0.05972827854867801} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05550072592779661, "f1": 0.7782258064516129, "f1_std": 0.05640221240388509, "bacc": 0.7819293478260869, "bacc_std": 0.05637577625417037} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.06004396185605928, "f1": 0.7136410968413746, "f1_std": 0.06369866181292706, "bacc": 0.7105978260869565, "bacc_std": 0.062360657686652776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.056804271751833946, "f1": 0.6623329721921272, "f1_std": 0.06507068767505052, "bacc": 0.6610054347826086, "bacc_std": 0.06040128972749116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 166.81005372000556, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.061275165853820625, "f1": 0.696969696969697, "f1_std": 0.06483605930009796, "bacc": 0.6949728260869565, "bacc_std": 0.06388359787065237} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05367148310950194, "f1": 0.76890756302521, "f1_std": 0.05930701113888251, "bacc": 0.7635869565217391, "bacc_std": 0.05788373580860351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.8, "acc_std": 0.05599641074684093, "f1": 0.7989365237620472, "f1_std": 0.05601892155356306, "bacc": 0.8097826086956521, "bacc_std": 0.054499141866108776} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.05161428465226744, "f1": 0.6696696696696697, "f1_std": 0.06451894745597272, "bacc": 0.670516304347826, "bacc_std": 0.056425415022138777} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 166.81005372000556, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05423342264905843, "f1": 0.7811671087533156, "f1_std": 0.05422661118361694, "bacc": 0.7941576086956521, "bacc_std": 0.052722062121492455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 21.54434690031882, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.055692793723490584, "f1": 0.7585275244849713, "f1_std": 0.05716357565759338, "bacc": 0.7601902173913043, "bacc_std": 0.05787720499957419} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.06016549078160782, "f1": 0.7384510869565217, "f1_std": 0.06230789907992237, "bacc": 0.7384510869565217, "bacc_std": 0.06215336975509371} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.061419204469660406, "f1": 0.6918767507002801, "f1_std": 0.06724662955926493, "bacc": 0.6888586956521738, "bacc_std": 0.06485517904664953} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 21.54434690031882, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04763124191758565, "f1": 0.8106060606060606, "f1_std": 0.05040513531186905, "bacc": 0.8070652173913043, "bacc_std": 0.050411593270237275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.6363636363636364, "acc_std": 0.06128039876442772, "f1": 0.6148459383753502, "f1_std": 0.06619553396220339, "bacc": 0.6141304347826086, "bacc_std": 0.06347499642626063} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06141570585460886, "f1": 0.7010869565217391, "f1_std": 0.06286380688066105, "bacc": 0.7010869565217391, "bacc_std": 0.06257828680353213} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.06468296747206129, "f1": 0.6803418803418804, "f1_std": 0.06715178461016298, "bacc": 0.6793478260869565, "bacc_std": 0.06643907841114952} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 2.782559402207126, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.06274651615234267, "f1": 0.6803418803418804, "f1_std": 0.06485063480057303, "bacc": 0.6793478260869565, "bacc_std": 0.06425217688444314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.6727272727272727, "acc_std": 0.06208813783247276, "f1": 0.6637228260869565, "f1_std": 0.06386039126513159, "bacc": 0.6637228260869565, "bacc_std": 0.06360053150513527} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05397856936241664, "f1": 0.7020585048754062, "f1_std": 0.06398106456460491, "bacc": 0.6983695652173914, "bacc_std": 0.05906705200200019} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.057388903814167225, "f1": 0.6623329721921272, "f1_std": 0.06642024737230977, "bacc": 0.6610054347826086, "bacc_std": 0.06117769152747517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05625096068968418, "f1": 0.7931623931623932, "f1_std": 0.05861868899274305, "bacc": 0.7914402173913043, "bacc_std": 0.05856909002184618} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.05313834742389103, "f1": 0.7931623931623932, "f1_std": 0.0557110863702641, "bacc": 0.7914402173913043, "bacc_std": 0.05588930286503917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.06074816189444517, "f1": 0.6892655367231638, "f1_std": 0.06078603447551249, "bacc": 0.6976902173913043, "bacc_std": 0.06042438378239402} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05744178224173967, "f1": 0.7348484848484849, "f1_std": 0.06070414212714564, "bacc": 0.7323369565217391, "bacc_std": 0.059760747902151884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.05964190661601446, "f1": 0.6754599097535579, "f1_std": 0.0635831110933265, "bacc": 0.6732336956521738, "bacc_std": 0.06212827256245735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.056320969187753984, "f1": 0.7555555555555555, "f1_std": 0.058771768862086474, "bacc": 0.7540760869565217, "bacc_std": 0.05804841316637023} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.056135609122643766, "f1": 0.78, "f1_std": 0.05642636957451899, "bacc": 0.7880434782608696, "bacc_std": 0.056015518218168796} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 114.86 | 999.53 | 0.94809 | 0.052856 | 0.94648 | 0.054975 | 0.946 | 0.055734 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 114.86 | 999.53 | 0.73782 | 0.051438 | 0.72809 | 0.054798 | 0.72853 | 0.055148 | + + +done! total time: 0:05:25 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bd62a2d965b5de7c83c4486e4401a4fd1263261 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_sex reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..aef0fdae6273508a5e2a1429b0d7d628d0a87448 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,aabc_sex,,0.046415888336127774,train,0.941398865784499,0.010159867202687849,0.9400272819365054,0.010387280633725411,0.9402883489461358,0.010409739494415768 +flat_mae,reg,logistic,aabc_sex,,0.046415888336127774,test,0.8181818181818182,0.050951605624381224,0.8166666666666667,0.05083648440743584,0.8333333333333333,0.048638289398294926 +flat_mae,reg,logistic,aabc_sex,1,0.046415888336127774,train,0.9376181474480151,0.010567242340482907,0.9359246820459175,0.010875403239895354,0.9351314516838125,0.011100246258125536 +flat_mae,reg,logistic,aabc_sex,1,0.046415888336127774,test,0.7454545454545455,0.05686435651022805,0.741263440860215,0.05780518248124952,0.7445652173913043,0.05813856314203359 +flat_mae,reg,logistic,aabc_sex,2,0.046415888336127774,train,0.943289224952741,0.010149591698270958,0.9417126990656403,0.01044422677837072,0.9406415780063895,0.010590074751880152 +flat_mae,reg,logistic,aabc_sex,2,0.046415888336127774,test,0.8363636363636363,0.045108075911046035,0.8281846581048247,0.04883491683309754,0.8226902173913043,0.0489720873066438 +flat_mae,reg,logistic,aabc_sex,3,0.3593813663804626,train,0.998109640831758,0.0017651501403643083,0.9980631011617731,0.0018067541979653356,0.9983660130718954,0.0015257588631580217 +flat_mae,reg,logistic,aabc_sex,3,0.3593813663804626,test,0.7090909090909091,0.058983241771857174,0.7066666666666667,0.059443315963299936,0.7133152173913043,0.059719948927988896 +flat_mae,reg,logistic,aabc_sex,4,0.005994842503189409,train,0.8846880907372401,0.013322544928259105,0.8805900006290774,0.013961920501663436,0.8772165069316217,0.014314749096909303 +flat_mae,reg,logistic,aabc_sex,4,0.005994842503189409,test,0.7090909090909091,0.06090690905183037,0.7043010752688172,0.06186255079016478,0.7072010869565217,0.06226453783756901 +flat_mae,reg,logistic,aabc_sex,5,0.046415888336127774,train,0.9395085066162571,0.00976757929713813,0.9378268790033496,0.010058031973069098,0.9367654386119171,0.010294798989038722 +flat_mae,reg,logistic,aabc_sex,5,0.046415888336127774,test,0.7272727272727273,0.05826470232645219,0.7239879558380728,0.059322542319658146,0.7289402173913043,0.05936297651804229 +flat_mae,reg,logistic,aabc_sex,6,0.046415888336127774,train,0.9338374291115312,0.0112029108667426,0.9320413294426397,0.01152221315922779,0.9312553122893402,0.011697567373546623 +flat_mae,reg,logistic,aabc_sex,6,0.046415888336127774,test,0.7636363636363637,0.05657321738791099,0.7555555555555555,0.05926562723403219,0.7540760869565217,0.05939082964790558 +flat_mae,reg,logistic,aabc_sex,7,0.046415888336127774,train,0.947069943289225,0.008958614534770195,0.9455985191279309,0.009227916867569252,0.9445177174008617,0.009476771585621411 +flat_mae,reg,logistic,aabc_sex,7,0.046415888336127774,test,0.6909090909090909,0.06000087051710099,0.6754599097535579,0.06498946610654509,0.6732336956521738,0.06325298261278592 +flat_mae,reg,logistic,aabc_sex,8,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,8,0.3593813663804626,test,0.7818181818181819,0.054346047625949606,0.7727272727272727,0.057705932151778515,0.7697010869565217,0.057483461393271824 +flat_mae,reg,logistic,aabc_sex,9,0.3593813663804626,train,0.996219281663516,0.002527361428567283,0.9961190832526338,0.0025988327366406917,0.9955156950672646,0.0029976999903858627 +flat_mae,reg,logistic,aabc_sex,9,0.3593813663804626,test,0.7454545454545455,0.06060869206408441,0.7384510869565217,0.0621754429444348,0.7384510869565217,0.06176852943339552 +flat_mae,reg,logistic,aabc_sex,10,0.3593813663804626,train,0.998109640831758,0.0018134013615846941,0.998060743809227,0.0018625992416127092,0.9977578475336323,0.0021508729154221993 +flat_mae,reg,logistic,aabc_sex,10,0.3593813663804626,test,0.7636363636363637,0.05772405144913582,0.7585275244849713,0.059019737975447274,0.7601902173913043,0.05881140262157492 +flat_mae,reg,logistic,aabc_sex,11,0.005994842503189409,train,0.8733459357277883,0.014768406775027384,0.8692164351211232,0.015334915507690873,0.8668044198247311,0.015522279029087479 +flat_mae,reg,logistic,aabc_sex,11,0.005994842503189409,test,0.7636363636363637,0.056419866379796124,0.7555555555555555,0.05910907874497819,0.7540760869565217,0.05868370354113446 +flat_mae,reg,logistic,aabc_sex,12,0.3593813663804626,train,0.998109640831758,0.0019052869945482677,0.998060743809227,0.0019569458781900986,0.9977578475336323,0.002259858341067333 +flat_mae,reg,logistic,aabc_sex,12,0.3593813663804626,test,0.6909090909090909,0.06030336531047498,0.6803418803418804,0.06313648953972331,0.6793478260869565,0.062444686579051153 +flat_mae,reg,logistic,aabc_sex,13,0.000774263682681127,train,0.7977315689981096,0.016910277014450217,0.785971678672036,0.018367348745997006,0.7801591488613383,0.018120481341249217 +flat_mae,reg,logistic,aabc_sex,13,0.000774263682681127,test,0.7454545454545455,0.06050344160691185,0.7348484848484849,0.06312614894348424,0.7323369565217391,0.062487001409989855 +flat_mae,reg,logistic,aabc_sex,14,0.005994842503189409,train,0.8714555765595463,0.01530209258471789,0.8671718066879357,0.01590728134278252,0.8645622673583634,0.01613635564547439 +flat_mae,reg,logistic,aabc_sex,14,0.005994842503189409,test,0.8,0.053471549552731736,0.790003471017008,0.05794684940331213,0.7853260869565217,0.05773269985192296 +flat_mae,reg,logistic,aabc_sex,15,0.005994842503189409,train,0.8752362948960303,0.014674628714180706,0.8714317277949624,0.015185287549892077,0.869654737829362,0.01536083546715879 +flat_mae,reg,logistic,aabc_sex,15,0.005994842503189409,test,0.7272727272727273,0.05871405423992843,0.7083775185577943,0.06539705135685858,0.7044836956521738,0.06250435433496747 +flat_mae,reg,logistic,aabc_sex,16,0.005994842503189409,train,0.8790170132325141,0.013843685509095508,0.8753277360435999,0.014324667542287733,0.8735308772238342,0.0144840473980665 +flat_mae,reg,logistic,aabc_sex,16,0.005994842503189409,test,0.7454545454545455,0.06017235849850601,0.7384510869565217,0.06231039893096374,0.7384510869565217,0.06230097706983681 +flat_mae,reg,logistic,aabc_sex,17,0.005994842503189409,train,0.8657844990548205,0.014193767322049694,0.8617838309272432,0.014649107522690377,0.8602684721123128,0.014747891756241941 +flat_mae,reg,logistic,aabc_sex,17,0.005994842503189409,test,0.7272727272727273,0.05639548660212899,0.7136410968413746,0.06060400635726474,0.7105978260869565,0.05935312120218117 +flat_mae,reg,logistic,aabc_sex,18,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,18,2.782559402207126,test,0.6363636363636364,0.0658721526585231,0.6303763440860215,0.06636224991091373,0.6324728260869565,0.06633442614493465 +flat_mae,reg,logistic,aabc_sex,19,0.005994842503189409,train,0.8676748582230623,0.015380584864893675,0.8636397112976875,0.015963109597171468,0.8619024590404174,0.016262085551037468 +flat_mae,reg,logistic,aabc_sex,19,0.005994842503189409,test,0.7454545454545455,0.05933070226623783,0.7384510869565217,0.061112030859034695,0.7384510869565217,0.061178434136570106 +flat_mae,reg,logistic,aabc_sex,20,0.005994842503189409,train,0.8582230623818525,0.0152698041829813,0.8533949191685912,0.01593033032389848,0.8506916967085788,0.01613733781323331 +flat_mae,reg,logistic,aabc_sex,20,0.005994842503189409,test,0.8,0.054897421999113565,0.795677136102668,0.05620131585932542,0.7975543478260869,0.05603043979785281 +flat_mae,reg,logistic,aabc_sex,21,0.046415888336127774,train,0.9527410207939508,0.009110959358943568,0.9515185952306762,0.009360036650398052,0.9512441747999649,0.009549221384069948 +flat_mae,reg,logistic,aabc_sex,21,0.046415888336127774,test,0.7454545454545455,0.05712327976323744,0.7348484848484849,0.060834277722005885,0.7323369565217391,0.06014456225607166 +flat_mae,reg,logistic,aabc_sex,22,0.3593813663804626,train,0.998109640831758,0.0017938741590034016,0.998060743809227,0.0018424465249252187,0.9977578475336323,0.002127711726710307 +flat_mae,reg,logistic,aabc_sex,22,0.3593813663804626,test,0.7818181818181819,0.05516231795631913,0.78,0.055361044737783735,0.7880434782608696,0.054291640454489885 +flat_mae,reg,logistic,aabc_sex,23,0.005994842503189409,train,0.8733459357277883,0.014062956521178066,0.8692164351211232,0.014690184762355134,0.8668044198247311,0.015069088569742366 +flat_mae,reg,logistic,aabc_sex,23,0.005994842503189409,test,0.7272727272727273,0.059257990359846024,0.7213779128672746,0.060892428929681816,0.7228260869565217,0.060999983052617814 +flat_mae,reg,logistic,aabc_sex,24,0.005994842503189409,train,0.8676748582230623,0.015227409962706513,0.8636397112976875,0.015766871358185695,0.8619024590404174,0.01594795008271404 +flat_mae,reg,logistic,aabc_sex,24,0.005994842503189409,test,0.7636363636363637,0.056768970688729686,0.7518222839291913,0.061427975173266855,0.7479619565217391,0.06054477222475154 +flat_mae,reg,logistic,aabc_sex,25,0.3593813663804626,train,0.996219281663516,0.0025375211492149226,0.9961285128805621,0.00259448008309317,0.9967320261437909,0.0021933802090436127 +flat_mae,reg,logistic,aabc_sex,25,0.3593813663804626,test,0.7090909090909091,0.060235076681364984,0.7066666666666667,0.06049694700768868,0.7133152173913043,0.06058201313226821 +flat_mae,reg,logistic,aabc_sex,26,0.3593813663804626,train,0.996219281663516,0.00267337157348411,0.9961238606055277,0.0027412239989799757,0.9961238606055277,0.002786941954286319 +flat_mae,reg,logistic,aabc_sex,26,0.3593813663804626,test,0.7272727272727273,0.059906472559694716,0.717948717948718,0.061872962103562704,0.7167119565217391,0.06145906093541241 +flat_mae,reg,logistic,aabc_sex,27,0.005994842503189409,train,0.8790170132325141,0.015210372578559036,0.8751585592495355,0.01583328889695118,0.8729227116855711,0.016125285450646936 +flat_mae,reg,logistic,aabc_sex,27,0.005994842503189409,test,0.7454545454545455,0.05722544657350601,0.7348484848484849,0.06015377101312881,0.7323369565217391,0.059582090596493595 +flat_mae,reg,logistic,aabc_sex,28,0.3593813663804626,train,0.998109640831758,0.0019750408902244293,0.9980631011617731,0.002021120332629881,0.9983660130718954,0.0017071840374652196 +flat_mae,reg,logistic,aabc_sex,28,0.3593813663804626,test,0.6909090909090909,0.06052607934594589,0.6803418803418804,0.06333841138479059,0.6793478260869565,0.06297982430867961 +flat_mae,reg,logistic,aabc_sex,29,0.005994842503189409,train,0.8506616257088847,0.016273696181787978,0.8455759815242494,0.01698643027663376,0.8429394179196342,0.017195036221845563 +flat_mae,reg,logistic,aabc_sex,29,0.005994842503189409,test,0.6909090909090909,0.05924733421488473,0.6754599097535579,0.06323499334919024,0.6732336956521738,0.0616323153013269 +flat_mae,reg,logistic,aabc_sex,30,0.005994842503189409,train,0.8790170132325141,0.014092244070451312,0.8749852298239396,0.014702735227304147,0.8723145461473079,0.015009455016126813 +flat_mae,reg,logistic,aabc_sex,30,0.005994842503189409,test,0.7272727272727273,0.06211108150950999,0.7258225324027916,0.062184076098976825,0.7350543478260869,0.061294169170219494 +flat_mae,reg,logistic,aabc_sex,31,0.046415888336127774,train,0.943289224952741,0.010457975376064785,0.9417862487895061,0.010737642048878733,0.9412497435446525,0.010834697958158945 +flat_mae,reg,logistic,aabc_sex,31,0.046415888336127774,test,0.7454545454545455,0.0575121805280491,0.741263440860215,0.05845243566912999,0.7445652173913043,0.058563382568656314 +flat_mae,reg,logistic,aabc_sex,32,0.046415888336127774,train,0.947069943289225,0.009691231175270376,0.9456671655368724,0.009949303070451835,0.9451258829391249,0.010040314069238944 +flat_mae,reg,logistic,aabc_sex,32,0.046415888336127774,test,0.7636363636363637,0.057057036853883795,0.7555555555555555,0.05923354735340611,0.7540760869565217,0.058760358104306284 +flat_mae,reg,logistic,aabc_sex,33,0.046415888336127774,train,0.947069943289225,0.009366575358440644,0.945734048477388,0.009598366194798029,0.945734048477388,0.009668129939414441 +flat_mae,reg,logistic,aabc_sex,33,0.046415888336127774,test,0.7636363636363637,0.05756624355205239,0.7472605160834218,0.06427914923876564,0.7418478260869565,0.06211539716274644 +flat_mae,reg,logistic,aabc_sex,34,0.005994842503189409,train,0.8752362948960303,0.014544699596358776,0.8714317277949624,0.01508591656093111,0.869654737829362,0.015307604350386427 +flat_mae,reg,logistic,aabc_sex,34,0.005994842503189409,test,0.7272727272727273,0.05755777837303722,0.7083775185577943,0.06306969324400177,0.7044836956521738,0.06076183425577814 +flat_mae,reg,logistic,aabc_sex,35,0.005994842503189409,train,0.8846880907372401,0.013888164552342841,0.8810916179337231,0.01443073473897898,0.8790410035464111,0.014773990858011872 +flat_mae,reg,logistic,aabc_sex,35,0.005994842503189409,test,0.7090909090909091,0.06063748397493022,0.696969696969697,0.06357647779132708,0.6949728260869565,0.06286764735774836 +flat_mae,reg,logistic,aabc_sex,36,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,36,2.782559402207126,test,0.7090909090909091,0.06298454749492527,0.7010869565217391,0.06560497548760205,0.7010869565217391,0.06550089145475921 +flat_mae,reg,logistic,aabc_sex,37,0.005994842503189409,train,0.8771266540642723,0.014083713213379588,0.8729422632794457,0.01471754242387496,0.8700723936809402,0.01504888213576399 +flat_mae,reg,logistic,aabc_sex,37,0.005994842503189409,test,0.8181818181818182,0.051846882004164103,0.8106060606060606,0.05508712712865352,0.8070652173913043,0.05478176117235523 +flat_mae,reg,logistic,aabc_sex,38,0.000774263682681127,train,0.7977315689981096,0.01640003972634355,0.7851527953328247,0.018292485708069354,0.778942817784812,0.018072246951716376 +flat_mae,reg,logistic,aabc_sex,38,0.000774263682681127,test,0.7818181818181819,0.055146458642658505,0.7758152173913043,0.056735038602484585,0.7758152173913043,0.05689894578381109 +flat_mae,reg,logistic,aabc_sex,39,0.005994842503189409,train,0.8771266540642723,0.014843258119374328,0.8732943469785575,0.015380579299432809,0.8712887247574665,0.015592303586782428 +flat_mae,reg,logistic,aabc_sex,39,0.005994842503189409,test,0.7636363636363637,0.0581100807743657,0.7555555555555555,0.061003276269182706,0.7540760869565217,0.06054418132690288 +flat_mae,reg,logistic,aabc_sex,40,0.046415888336127774,train,0.9395085066162571,0.010017921983514267,0.9378268790033496,0.010327199055589783,0.9367654386119171,0.01060654887562952 +flat_mae,reg,logistic,aabc_sex,40,0.046415888336127774,test,0.7818181818181819,0.05596929500602158,0.7758152173913043,0.057900207829809036,0.7758152173913043,0.05815728167010988 +flat_mae,reg,logistic,aabc_sex,41,0.005994842503189409,train,0.8903591682419659,0.013809984456342602,0.887165342747867,0.014246559604196452,0.8857674609455142,0.014398240724742765 +flat_mae,reg,logistic,aabc_sex,41,0.005994842503189409,test,0.6363636363636364,0.06559720816474027,0.6303763440860215,0.066870267478454,0.6324728260869565,0.06724219039551839 +flat_mae,reg,logistic,aabc_sex,42,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,42,21.54434690031882,test,0.6727272727272727,0.06633623344574666,0.6673387096774194,0.06714636079918689,0.6698369565217391,0.06692186277630337 +flat_mae,reg,logistic,aabc_sex,43,0.005994842503189409,train,0.8695652173913043,0.014381881871405815,0.8656772441405604,0.014900552071513208,0.864144611506785,0.015133971028412494 +flat_mae,reg,logistic,aabc_sex,43,0.005994842503189409,test,0.7818181818181819,0.05792601722088597,0.7758152173913043,0.05990458566968057,0.7758152173913043,0.05974629269984236 +flat_mae,reg,logistic,aabc_sex,44,0.046415888336127774,train,0.9527410207939508,0.0091107907047976,0.9512670565302144,0.00945071474718187,0.9488115126469123,0.009916104689832178 +flat_mae,reg,logistic,aabc_sex,44,0.046415888336127774,test,0.8363636363636363,0.051833375762873134,0.8343927735028438,0.052015482655581695,0.8410326086956521,0.050723901818792216 +flat_mae,reg,logistic,aabc_sex,45,0.005994842503189409,train,0.8752362948960303,0.014071760004439233,0.8708954561590344,0.014687376957474263,0.8678302412145725,0.014927012417795022 +flat_mae,reg,logistic,aabc_sex,45,0.005994842503189409,test,0.7818181818181819,0.05339166369449555,0.7758152173913043,0.05499757277201123,0.7758152173913043,0.05496629710954507 +flat_mae,reg,logistic,aabc_sex,46,0.005994842503189409,train,0.8714555765595463,0.014684679909447756,0.8677110914974993,0.015185433403317137,0.8663867639731528,0.015347237791069642 +flat_mae,reg,logistic,aabc_sex,46,0.005994842503189409,test,0.7818181818181819,0.05674736241003512,0.78,0.05690939624060673,0.7880434782608696,0.05621512208641315 +flat_mae,reg,logistic,aabc_sex,47,0.005994842503189409,train,0.8752362948960303,0.013452231498718888,0.8707080432528514,0.014088086695328197,0.8672220756763094,0.014385447351914311 +flat_mae,reg,logistic,aabc_sex,47,0.005994842503189409,test,0.8,0.057506489752343265,0.7931623931623932,0.06000923035031473,0.7914402173913043,0.06022658209321617 +flat_mae,reg,logistic,aabc_sex,48,0.046415888336127774,train,0.941398865784499,0.010186697074190107,0.9398080346491953,0.01049873404874299,0.9390075910782849,0.010797842521095601 +flat_mae,reg,logistic,aabc_sex,48,0.046415888336127774,test,0.7818181818181819,0.0559141135955275,0.7758152173913043,0.05764935256372829,0.7758152173913043,0.057242569965207234 +flat_mae,reg,logistic,aabc_sex,49,0.005994842503189409,train,0.8676748582230623,0.015082839259329923,0.8630709383504911,0.01573499462903462,0.860077962425628,0.015968350908838295 +flat_mae,reg,logistic,aabc_sex,49,0.005994842503189409,test,0.8363636363636363,0.04690142291097763,0.8307692307692308,0.0491593420399302,0.8288043478260869,0.049412050355457045 +flat_mae,reg,logistic,aabc_sex,50,0.046415888336127774,train,0.947069943289225,0.00925828061903877,0.9457991803278689,0.009458665341054714,0.9463422140156511,0.009405810384981455 +flat_mae,reg,logistic,aabc_sex,50,0.046415888336127774,test,0.7818181818181819,0.05617044898203124,0.78,0.05633226566131222,0.7880434782608696,0.05530833089002614 +flat_mae,reg,logistic,aabc_sex,51,0.046415888336127774,train,0.945179584120983,0.009592268807988892,0.943691387252473,0.009859339713963517,0.9428837304727571,0.009995940482222814 +flat_mae,reg,logistic,aabc_sex,51,0.046415888336127774,test,0.7454545454545455,0.060961540511109163,0.7433333333333334,0.06132309481999507,0.7506793478260869,0.061262962462586036 +flat_mae,reg,logistic,aabc_sex,52,0.046415888336127774,train,0.9395085066162571,0.010171728112833739,0.9379053320421398,0.010463988670689855,0.9373736041501802,0.010649539322611602 +flat_mae,reg,logistic,aabc_sex,52,0.046415888336127774,test,0.7636363636363637,0.05289791822053223,0.7417840375586855,0.06162662117485513,0.7357336956521738,0.057939345976673155 +flat_mae,reg,logistic,aabc_sex,53,0.005994842503189409,train,0.8809073724007561,0.013410190352281704,0.8770244091437427,0.013895211471154391,0.8745566986136757,0.014032300346690068 +flat_mae,reg,logistic,aabc_sex,53,0.005994842503189409,test,0.8181818181818182,0.04995940169959819,0.8106060606060606,0.05342324293619793,0.8070652173913043,0.05335744521336223 +flat_mae,reg,logistic,aabc_sex,54,0.005994842503189409,train,0.8865784499054821,0.013937831846388436,0.8834253981312805,0.014381199973934972,0.882499487089305,0.01457923578842835 +flat_mae,reg,logistic,aabc_sex,54,0.005994842503189409,test,0.7454545454545455,0.058186363458820695,0.741263440860215,0.0588594520890131,0.7445652173913043,0.058643268237730695 +flat_mae,reg,logistic,aabc_sex,55,0.046415888336127774,train,0.9508506616257089,0.009263975847047577,0.9494843391902215,0.009541260869974231,0.9483938567953341,0.009769372126223379 +flat_mae,reg,logistic,aabc_sex,55,0.046415888336127774,test,0.7272727272727273,0.0583507094151922,0.7269116186693148,0.058300880630144485,0.7411684782608696,0.05674260782124716 +flat_mae,reg,logistic,aabc_sex,56,0.046415888336127774,train,0.9376181474480151,0.010406715492660062,0.9357586819802679,0.010760598085995303,0.9339151206072862,0.011037486152287194 +flat_mae,reg,logistic,aabc_sex,56,0.046415888336127774,test,0.7636363636363637,0.05609437148588701,0.7585275244849713,0.05754945587676633,0.7601902173913043,0.057702394623882144 +flat_mae,reg,logistic,aabc_sex,57,0.046415888336127774,train,0.9338374291115312,0.01155281619073709,0.9318652687669509,0.011951076095653147,0.930038981212814,0.012284228961983893 +flat_mae,reg,logistic,aabc_sex,57,0.046415888336127774,test,0.8181818181818182,0.048984544703760464,0.8074229691876751,0.05421283994002026,0.8009510869565217,0.053779021817230446 +flat_mae,reg,logistic,aabc_sex,58,0.005994842503189409,train,0.8752362948960303,0.013835877483842749,0.8717679379444085,0.01429531266996852,0.8708710689058883,0.014578497336386102 +flat_mae,reg,logistic,aabc_sex,58,0.005994842503189409,test,0.7636363636363637,0.05907872321902431,0.7585275244849713,0.06051784761400008,0.7601902173913043,0.06047640759153292 +flat_mae,reg,logistic,aabc_sex,59,0.005994842503189409,train,0.8714555765595463,0.014525293515613501,0.8675357195463249,0.015062363518905735,0.8657785984348896,0.015319384233231174 +flat_mae,reg,logistic,aabc_sex,59,0.005994842503189409,test,0.6909090909090909,0.0618446467414805,0.6842283012495778,0.06306130285870268,0.6854619565217391,0.06307073440685028 +flat_mae,reg,logistic,aabc_sex,60,0.046415888336127774,train,0.9395085066162571,0.010695418298712392,0.9379053320421398,0.011005863065272913,0.9373736041501802,0.01124366137236868 +flat_mae,reg,logistic,aabc_sex,60,0.046415888336127774,test,0.8727272727272727,0.0463196083284658,0.8699763593380614,0.04726466715635542,0.8722826086956521,0.04690989900847402 +flat_mae,reg,logistic,aabc_sex,61,0.005994842503189409,train,0.8941398865784499,0.013456686615095649,0.89091176903815,0.013933251322984841,0.8890354348017233,0.01417173477914222 +flat_mae,reg,logistic,aabc_sex,61,0.005994842503189409,test,0.6909090909090909,0.06250166543235616,0.6892655367231638,0.06268857306621861,0.6976902173913043,0.06230779891405676 +flat_mae,reg,logistic,aabc_sex,62,0.005994842503189409,train,0.8865784499054821,0.01367436171385246,0.8831197525408749,0.014194458046963832,0.8812831560127787,0.014517704304119177 +flat_mae,reg,logistic,aabc_sex,62,0.005994842503189409,test,0.7090909090909091,0.05850902310861094,0.7082228116710876,0.058687950164569985,0.7194293478260869,0.05836545816543731 +flat_mae,reg,logistic,aabc_sex,63,0.3593813663804626,train,0.996219281663516,0.0024908708356471145,0.9961238606055277,0.0025545512879319695,0.9961238606055277,0.0026343700818264606 +flat_mae,reg,logistic,aabc_sex,63,0.3593813663804626,test,0.8181818181818182,0.05278993142166534,0.8151881720430108,0.05330421372783843,0.8192934782608696,0.05276652279663882 +flat_mae,reg,logistic,aabc_sex,64,0.046415888336127774,train,0.947069943289225,0.010095225933273815,0.9455280964989703,0.010436346056992056,0.9439095518625986,0.010789052374952871 +flat_mae,reg,logistic,aabc_sex,64,0.046415888336127774,test,0.7090909090909091,0.06095899177058255,0.696969696969697,0.0642823199810322,0.6949728260869565,0.06362399550664577 +flat_mae,reg,logistic,aabc_sex,65,0.046415888336127774,train,0.9489603024574669,0.009969274662598225,0.9475747398557507,0.010276717600380297,0.9467598698672295,0.010568327561996178 +flat_mae,reg,logistic,aabc_sex,65,0.046415888336127774,test,0.8181818181818182,0.051759137014278034,0.8131793478260869,0.05337524731097951,0.8131793478260869,0.05333847044425869 +flat_mae,reg,logistic,aabc_sex,66,0.000774263682681127,train,0.8128544423440454,0.015792881873505703,0.8015986967969239,0.017310079673620048,0.7950555409009643,0.017160719966707424 +flat_mae,reg,logistic,aabc_sex,66,0.000774263682681127,test,0.7090909090909091,0.05348391277402801,0.6857142857142857,0.059169943358793324,0.6827445652173914,0.05606006941261015 +flat_mae,reg,logistic,aabc_sex,67,0.000774263682681127,train,0.8015122873345936,0.016742145665014033,0.7895743753906768,0.018387237568484503,0.7834271227175474,0.01817972599822949 +flat_mae,reg,logistic,aabc_sex,67,0.000774263682681127,test,0.7090909090909091,0.05692435461874234,0.6857142857142857,0.0645108380465425,0.6827445652173914,0.06096761113213914 +flat_mae,reg,logistic,aabc_sex,68,0.005994842503189409,train,0.8790170132325141,0.013893239686384002,0.8754927919976463,0.014341125060235538,0.8741390427620974,0.01450366883629813 +flat_mae,reg,logistic,aabc_sex,68,0.005994842503189409,test,0.7818181818181819,0.05717625352313797,0.7782258064516129,0.05779277969899829,0.7819293478260869,0.05739258846811508 +flat_mae,reg,logistic,aabc_sex,69,0.046415888336127774,train,0.941398865784499,0.009340498598908278,0.9397310517940294,0.009627487934732944,0.9383994255400216,0.009887391832595183 +flat_mae,reg,logistic,aabc_sex,69,0.046415888336127774,test,0.7818181818181819,0.053838276346851954,0.76890756302521,0.05858255742517174,0.7635869565217391,0.057629345711253395 +flat_mae,reg,logistic,aabc_sex,70,0.046415888336127774,train,0.9376181474480151,0.010366188478535814,0.9360045457044925,0.010657543122532767,0.9357396172220757,0.01088035521451684 +flat_mae,reg,logistic,aabc_sex,70,0.046415888336127774,test,0.8,0.05536475592240162,0.7975911676145868,0.05566791624642805,0.8036684782608696,0.05484813834575139 +flat_mae,reg,logistic,aabc_sex,71,0.046415888336127774,train,0.941398865784499,0.010551482304605541,0.9397310517940294,0.010871716719730714,0.9383994255400216,0.01104272487252926 +flat_mae,reg,logistic,aabc_sex,71,0.046415888336127774,test,0.7636363636363637,0.05231890766418536,0.7555555555555555,0.054490950928459264,0.7540760869565217,0.054098637472921915 +flat_mae,reg,logistic,aabc_sex,72,0.046415888336127774,train,0.945179584120983,0.009369748997859502,0.9436193710331242,0.009658647725644506,0.942275564934494,0.009887396933224525 +flat_mae,reg,logistic,aabc_sex,72,0.046415888336127774,test,0.8,0.050851538897701616,0.790003471017008,0.05478050225874464,0.7853260869565217,0.054299158423413 +flat_mae,reg,logistic,aabc_sex,73,0.005994842503189409,train,0.8809073724007561,0.013723882057678365,0.8773574837805116,0.014193703505853878,0.875773029690202,0.014414409790998296 +flat_mae,reg,logistic,aabc_sex,73,0.005994842503189409,test,0.7818181818181819,0.05353828938014423,0.7758152173913043,0.05534715495341467,0.7758152173913043,0.05556445464803174 +flat_mae,reg,logistic,aabc_sex,74,0.000774263682681127,train,0.7920604914933838,0.01676871120765599,0.7789133738601823,0.01842009724556785,0.772824525923972,0.018051921004175756 +flat_mae,reg,logistic,aabc_sex,74,0.000774263682681127,test,0.6545454545454545,0.05424278449177816,0.6019047619047619,0.06850631027860868,0.6114130434782609,0.05803401884377181 +flat_mae,reg,logistic,aabc_sex,75,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,75,2.782559402207126,test,0.7090909090909091,0.06074904345742193,0.696969696969697,0.0639900734931278,0.6949728260869565,0.06305149809605932 +flat_mae,reg,logistic,aabc_sex,76,0.046415888336127774,train,0.9527410207939508,0.009241729917284034,0.9514580924590283,0.009513877944853965,0.9506360092617017,0.009769661626255439 +flat_mae,reg,logistic,aabc_sex,76,0.046415888336127774,test,0.7454545454545455,0.060015413998033645,0.7348484848484849,0.06289254397634586,0.7323369565217391,0.062195796113683685 +flat_mae,reg,logistic,aabc_sex,77,0.046415888336127774,train,0.947069943289225,0.009755234340549326,0.9455280964989703,0.010085536959409508,0.9439095518625986,0.010407969417586324 +flat_mae,reg,logistic,aabc_sex,77,0.046415888336127774,test,0.6909090909090909,0.0599671094423938,0.6754599097535579,0.06470910504804414,0.6732336956521738,0.06325315842446516 +flat_mae,reg,logistic,aabc_sex,78,0.3593813663804626,train,0.998109640831758,0.0018204227494683272,0.998060743809227,0.0018696410134150276,0.9977578475336323,0.002159200974145158 +flat_mae,reg,logistic,aabc_sex,78,0.3593813663804626,test,0.7454545454545455,0.0566743809365877,0.7384510869565217,0.058835603884003856,0.7384510869565217,0.05877436114787314 +flat_mae,reg,logistic,aabc_sex,79,0.046415888336127774,train,0.945179584120983,0.00966510454919167,0.943691387252473,0.009955159131514747,0.9428837304727571,0.01021647221781722 +flat_mae,reg,logistic,aabc_sex,79,0.046415888336127774,test,0.7636363636363637,0.05798653591229121,0.7585275244849713,0.05927327015180988,0.7601902173913043,0.059247363433676564 +flat_mae,reg,logistic,aabc_sex,80,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,80,21.54434690031882,test,0.7272727272727273,0.06068083145265171,0.7213779128672746,0.061735021443458785,0.7228260869565217,0.061749761955752 +flat_mae,reg,logistic,aabc_sex,81,0.046415888336127774,train,0.9395085066162571,0.009666576693152795,0.9378268790033496,0.009970521428700786,0.9367654386119171,0.010247701255146045 +flat_mae,reg,logistic,aabc_sex,81,0.046415888336127774,test,0.7818181818181819,0.05092169973726554,0.7642857142857142,0.05863371590337411,0.7574728260869565,0.05583878484268214 +flat_mae,reg,logistic,aabc_sex,82,0.046415888336127774,train,0.941398865784499,0.010230249372458658,0.939571150097466,0.01059826337315429,0.9371830944634953,0.01094324983511833 +flat_mae,reg,logistic,aabc_sex,82,0.046415888336127774,test,0.8181818181818182,0.05327165993345911,0.8166666666666667,0.05343491135336073,0.8254076086956521,0.05250007883523202 +flat_mae,reg,logistic,aabc_sex,83,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,83,0.3593813663804626,test,0.7454545454545455,0.0580824037022807,0.7303921568627451,0.06325109172848836,0.7262228260869565,0.06170058423528727 +flat_mae,reg,logistic,aabc_sex,84,0.046415888336127774,train,0.9527410207939508,0.0099221169429599,0.9515185952306762,0.01018417462926753,0.9512441747999649,0.010312297430885598 +flat_mae,reg,logistic,aabc_sex,84,0.046415888336127774,test,0.7272727272727273,0.05908368067676599,0.7239879558380728,0.05972968440911708,0.7289402173913043,0.0598051661216153 +flat_mae,reg,logistic,aabc_sex,85,0.005994842503189409,train,0.8752362948960303,0.012651078993812785,0.8714317277949624,0.013133483840223982,0.869654737829362,0.013429058690329787 +flat_mae,reg,logistic,aabc_sex,85,0.005994842503189409,test,0.8,0.05196376359803749,0.790003471017008,0.05602761469954495,0.7853260869565217,0.05542158468944219 +flat_mae,reg,logistic,aabc_sex,86,0.046415888336127774,train,0.9338374291115312,0.01085026049330002,0.9320413294426397,0.011164639465335975,0.9312553122893402,0.01137034461406842 +flat_mae,reg,logistic,aabc_sex,86,0.046415888336127774,test,0.8363636363636363,0.05372339318403677,0.8328267477203647,0.05483168939243797,0.8349184782608696,0.05473168421679525 +flat_mae,reg,logistic,aabc_sex,87,0.046415888336127774,train,0.9376181474480151,0.010438274394540469,0.9360823383385143,0.010679475568484628,0.9363477827603388,0.010700698240408032 +flat_mae,reg,logistic,aabc_sex,87,0.046415888336127774,test,0.7454545454545455,0.05378144938099625,0.7303921568627451,0.05845705330491706,0.7262228260869565,0.056824916212969985 +flat_mae,reg,logistic,aabc_sex,88,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,88,2.782559402207126,test,0.6727272727272727,0.06309379086947457,0.6590909090909092,0.06614570709766047,0.6576086956521738,0.06511274501770409 +flat_mae,reg,logistic,aabc_sex,89,0.005994842503189409,train,0.8846880907372401,0.013874057216968692,0.8807612009237875,0.01444990469999439,0.8778246724698848,0.014702591562559375 +flat_mae,reg,logistic,aabc_sex,89,0.005994842503189409,test,0.6727272727272727,0.060243033958258356,0.6590909090909092,0.06306504725757171,0.6576086956521738,0.06189317859583564 +flat_mae,reg,logistic,aabc_sex,90,0.046415888336127774,train,0.9546313799621928,0.009272304021708467,0.9533701592525121,0.009563536850766843,0.9522699961898062,0.009915114642536933 +flat_mae,reg,logistic,aabc_sex,90,0.046415888336127774,test,0.7090909090909091,0.06026825980975284,0.7066666666666667,0.06045897725926979,0.7133152173913043,0.06031455934219918 +flat_mae,reg,logistic,aabc_sex,91,0.046415888336127774,train,0.943289224952741,0.010107748881675833,0.9417126990656403,0.010413382420310136,0.9406415780063895,0.010683228305208885 +flat_mae,reg,logistic,aabc_sex,91,0.046415888336127774,test,0.7090909090909091,0.059132807523572195,0.696969696969697,0.062188532585697245,0.6949728260869565,0.06137780496025041 +flat_mae,reg,logistic,aabc_sex,92,0.005994842503189409,train,0.8771266540642723,0.014460828045360214,0.8734640705671946,0.014924527111081085,0.8718968902957296,0.015034377327045552 +flat_mae,reg,logistic,aabc_sex,92,0.005994842503189409,test,0.7272727272727273,0.05569009882769124,0.7020585048754062,0.06514089178585111,0.6983695652173914,0.06027487144590829 +flat_mae,reg,logistic,aabc_sex,93,0.005994842503189409,train,0.8733459357277883,0.014345444385409276,0.8688447547893146,0.015033178360771086,0.8655880887482048,0.015394399421912591 +flat_mae,reg,logistic,aabc_sex,93,0.005994842503189409,test,0.7272727272727273,0.05554426125782651,0.7020585048754062,0.06514241552131578,0.6983695652173914,0.060132784577739115 +flat_mae,reg,logistic,aabc_sex,94,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,94,0.3593813663804626,test,0.8545454545454545,0.04693129847830232,0.8484848484848485,0.0498917681143379,0.8444293478260869,0.05039427653513253 +flat_mae,reg,logistic,aabc_sex,95,0.046415888336127774,train,0.9357277882797732,0.01082697400596142,0.9338555457487496,0.011181918060439349,0.9322811336791816,0.01146489136857427 +flat_mae,reg,logistic,aabc_sex,95,0.046415888336127774,test,0.8181818181818182,0.05074836967621113,0.8106060606060606,0.0537946149708118,0.8070652173913043,0.05399110886059457 +flat_mae,reg,logistic,aabc_sex,96,0.046415888336127774,train,0.941398865784499,0.010342964021127395,0.9397310517940294,0.01065498678513776,0.9383994255400216,0.010847839541462873 +flat_mae,reg,logistic,aabc_sex,96,0.046415888336127774,test,0.6909090909090909,0.062007954701642866,0.6842283012495778,0.06328495981921806,0.6854619565217391,0.06325803182367894 +flat_mae,reg,logistic,aabc_sex,97,0.000774263682681127,train,0.8109640831758034,0.0163401824225145,0.7990121580547113,0.01801432984445442,0.7922052228963334,0.017785257144516783 +flat_mae,reg,logistic,aabc_sex,97,0.000774263682681127,test,0.6363636363636364,0.06327853682837885,0.6148459383753502,0.06854776365341021,0.6141304347826086,0.06555718348716522 +flat_mae,reg,logistic,aabc_sex,98,0.046415888336127774,train,0.945179584120983,0.009628518026664139,0.943691387252473,0.009914851812919184,0.9428837304727571,0.01018543440626163 +flat_mae,reg,logistic,aabc_sex,98,0.046415888336127774,test,0.8,0.052674280580855985,0.790003471017008,0.05663044977609679,0.7853260869565217,0.056369005646708485 +flat_mae,reg,logistic,aabc_sex,99,0.005994842503189409,train,0.8676748582230623,0.014420642549845555,0.8632650951199339,0.01497895616096308,0.8606861279638911,0.015144443606027682 +flat_mae,reg,logistic,aabc_sex,99,0.005994842503189409,test,0.8545454545454545,0.04587794082721513,0.8505434782608696,0.0472775772746343,0.8505434782608696,0.04727981633746122 +flat_mae,reg,logistic,aabc_sex,100,0.046415888336127774,train,0.945179584120983,0.009932547908223592,0.9437615704675844,0.010197714591915851,0.9434918960110203,0.01039660145759797 +flat_mae,reg,logistic,aabc_sex,100,0.046415888336127774,test,0.7818181818181819,0.054720627805590956,0.7811671087533156,0.05467831151228022,0.7941576086956521,0.052870420540671405 diff --git a/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7965d2c3531139a68344bd40c2517f1f35d70f1c --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:19:08 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (aabc_sex reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/aabc_sex__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:20:30 time: 5.2121 data: 4.5042 max mem: 3205 +extract (train) [ 20/236] eta: 0:01:41 time: 0.2316 data: 0.0798 max mem: 3581 +extract (train) [ 40/236] eta: 0:01:05 time: 0.1882 data: 0.0575 max mem: 3581 +extract (train) [ 60/236] eta: 0:00:49 time: 0.1858 data: 0.0568 max mem: 3581 +extract (train) [ 80/236] eta: 0:00:41 time: 0.2036 data: 0.0666 max mem: 3581 +extract (train) [100/236] eta: 0:00:34 time: 0.2193 data: 0.0772 max mem: 3581 +extract (train) [120/236] eta: 0:00:28 time: 0.2082 data: 0.0689 max mem: 3581 +extract (train) [140/236] eta: 0:00:23 time: 0.2196 data: 0.0760 max mem: 3581 +extract (train) [160/236] eta: 0:00:17 time: 0.1886 data: 0.0599 max mem: 3581 +extract (train) [180/236] eta: 0:00:13 time: 0.2080 data: 0.0710 max mem: 3581 +extract (train) [200/236] eta: 0:00:08 time: 0.2064 data: 0.0705 max mem: 3581 +extract (train) [220/236] eta: 0:00:03 time: 0.1933 data: 0.0609 max mem: 3581 +extract (train) [235/236] eta: 0:00:00 time: 0.1774 data: 0.0563 max mem: 3581 +extract (train) Total time: 0:00:53 (0.2262 s / it) +extract (validation) [ 0/29] eta: 0:02:07 time: 4.4089 data: 4.2545 max mem: 3581 +extract (validation) [20/29] eta: 0:00:03 time: 0.1932 data: 0.0603 max mem: 3581 +extract (validation) [28/29] eta: 0:00:00 time: 0.1709 data: 0.0499 max mem: 3581 +extract (validation) Total time: 0:00:10 (0.3452 s / it) +extract (test) [ 0/28] eta: 0:02:01 time: 4.3402 data: 4.1975 max mem: 3581 +extract (test) [20/28] eta: 0:00:03 time: 0.2000 data: 0.0659 max mem: 3581 +extract (test) [27/28] eta: 0:00:00 time: 0.1719 data: 0.0529 max mem: 3581 +extract (test) Total time: 0:00:09 (0.3521 s / it) +feature extraction time: 0:01:13 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_sex | | 0.046416 | train | 0.9414 | 0.01016 | 0.94003 | 0.010387 | 0.94029 | 0.01041 | +| flat_mae | reg | logistic | aabc_sex | | 0.046416 | test | 0.81818 | 0.050952 | 0.81667 | 0.050836 | 0.83333 | 0.048638 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05686435651022805, "f1": 0.741263440860215, "f1_std": 0.05780518248124952, "bacc": 0.7445652173913043, "bacc_std": 0.05813856314203359} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.045108075911046035, "f1": 0.8281846581048247, "f1_std": 0.04883491683309754, "bacc": 0.8226902173913043, "bacc_std": 0.0489720873066438} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.058983241771857174, "f1": 0.7066666666666667, "f1_std": 0.059443315963299936, "bacc": 0.7133152173913043, "bacc_std": 0.059719948927988896} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06090690905183037, "f1": 0.7043010752688172, "f1_std": 0.06186255079016478, "bacc": 0.7072010869565217, "bacc_std": 0.06226453783756901} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05826470232645219, "f1": 0.7239879558380728, "f1_std": 0.059322542319658146, "bacc": 0.7289402173913043, "bacc_std": 0.05936297651804229} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05657321738791099, "f1": 0.7555555555555555, "f1_std": 0.05926562723403219, "bacc": 0.7540760869565217, "bacc_std": 0.05939082964790558} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.06000087051710099, "f1": 0.6754599097535579, "f1_std": 0.06498946610654509, "bacc": 0.6732336956521738, "bacc_std": 0.06325298261278592} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.054346047625949606, "f1": 0.7727272727272727, "f1_std": 0.057705932151778515, "bacc": 0.7697010869565217, "bacc_std": 0.057483461393271824} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.06060869206408441, "f1": 0.7384510869565217, "f1_std": 0.0621754429444348, "bacc": 0.7384510869565217, "bacc_std": 0.06176852943339552} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05772405144913582, "f1": 0.7585275244849713, "f1_std": 0.059019737975447274, "bacc": 0.7601902173913043, "bacc_std": 0.05881140262157492} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.056419866379796124, "f1": 0.7555555555555555, "f1_std": 0.05910907874497819, "bacc": 0.7540760869565217, "bacc_std": 0.05868370354113446} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.06030336531047498, "f1": 0.6803418803418804, "f1_std": 0.06313648953972331, "bacc": 0.6793478260869565, "bacc_std": 0.062444686579051153} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.000774263682681127, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.06050344160691185, "f1": 0.7348484848484849, "f1_std": 0.06312614894348424, "bacc": 0.7323369565217391, "bacc_std": 0.062487001409989855} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.053471549552731736, "f1": 0.790003471017008, "f1_std": 0.05794684940331213, "bacc": 0.7853260869565217, "bacc_std": 0.05773269985192296} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05871405423992843, "f1": 0.7083775185577943, "f1_std": 0.06539705135685858, "bacc": 0.7044836956521738, "bacc_std": 0.06250435433496747} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.06017235849850601, "f1": 0.7384510869565217, "f1_std": 0.06231039893096374, "bacc": 0.7384510869565217, "bacc_std": 0.06230097706983681} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05639548660212899, "f1": 0.7136410968413746, "f1_std": 0.06060400635726474, "bacc": 0.7105978260869565, "bacc_std": 0.05935312120218117} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 2.782559402207126, "split": "test", "acc": 0.6363636363636364, "acc_std": 0.0658721526585231, "f1": 0.6303763440860215, "f1_std": 0.06636224991091373, "bacc": 0.6324728260869565, "bacc_std": 0.06633442614493465} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05933070226623783, "f1": 0.7384510869565217, "f1_std": 0.061112030859034695, "bacc": 0.7384510869565217, "bacc_std": 0.061178434136570106} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.054897421999113565, "f1": 0.795677136102668, "f1_std": 0.05620131585932542, "bacc": 0.7975543478260869, "bacc_std": 0.05603043979785281} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05712327976323744, "f1": 0.7348484848484849, "f1_std": 0.060834277722005885, "bacc": 0.7323369565217391, "bacc_std": 0.06014456225607166} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05516231795631913, "f1": 0.78, "f1_std": 0.055361044737783735, "bacc": 0.7880434782608696, "bacc_std": 0.054291640454489885} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.059257990359846024, "f1": 0.7213779128672746, "f1_std": 0.060892428929681816, "bacc": 0.7228260869565217, "bacc_std": 0.060999983052617814} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.056768970688729686, "f1": 0.7518222839291913, "f1_std": 0.061427975173266855, "bacc": 0.7479619565217391, "bacc_std": 0.06054477222475154} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.060235076681364984, "f1": 0.7066666666666667, "f1_std": 0.06049694700768868, "bacc": 0.7133152173913043, "bacc_std": 0.06058201313226821} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.059906472559694716, "f1": 0.717948717948718, "f1_std": 0.061872962103562704, "bacc": 0.7167119565217391, "bacc_std": 0.06145906093541241} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05722544657350601, "f1": 0.7348484848484849, "f1_std": 0.06015377101312881, "bacc": 0.7323369565217391, "bacc_std": 0.059582090596493595} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.06052607934594589, "f1": 0.6803418803418804, "f1_std": 0.06333841138479059, "bacc": 0.6793478260869565, "bacc_std": 0.06297982430867961} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.05924733421488473, "f1": 0.6754599097535579, "f1_std": 0.06323499334919024, "bacc": 0.6732336956521738, "bacc_std": 0.0616323153013269} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.06211108150950999, "f1": 0.7258225324027916, "f1_std": 0.062184076098976825, "bacc": 0.7350543478260869, "bacc_std": 0.061294169170219494} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.0575121805280491, "f1": 0.741263440860215, "f1_std": 0.05845243566912999, "bacc": 0.7445652173913043, "bacc_std": 0.058563382568656314} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.057057036853883795, "f1": 0.7555555555555555, "f1_std": 0.05923354735340611, "bacc": 0.7540760869565217, "bacc_std": 0.058760358104306284} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05756624355205239, "f1": 0.7472605160834218, "f1_std": 0.06427914923876564, "bacc": 0.7418478260869565, "bacc_std": 0.06211539716274644} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05755777837303722, "f1": 0.7083775185577943, "f1_std": 0.06306969324400177, "bacc": 0.7044836956521738, "bacc_std": 0.06076183425577814} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06063748397493022, "f1": 0.696969696969697, "f1_std": 0.06357647779132708, "bacc": 0.6949728260869565, "bacc_std": 0.06286764735774836} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 2.782559402207126, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06298454749492527, "f1": 0.7010869565217391, "f1_std": 0.06560497548760205, "bacc": 0.7010869565217391, "bacc_std": 0.06550089145475921} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.051846882004164103, "f1": 0.8106060606060606, "f1_std": 0.05508712712865352, "bacc": 0.8070652173913043, "bacc_std": 0.05478176117235523} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.000774263682681127, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.055146458642658505, "f1": 0.7758152173913043, "f1_std": 0.056735038602484585, "bacc": 0.7758152173913043, "bacc_std": 0.05689894578381109} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.0581100807743657, "f1": 0.7555555555555555, "f1_std": 0.061003276269182706, "bacc": 0.7540760869565217, "bacc_std": 0.06054418132690288} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05596929500602158, "f1": 0.7758152173913043, "f1_std": 0.057900207829809036, "bacc": 0.7758152173913043, "bacc_std": 0.05815728167010988} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.6363636363636364, "acc_std": 0.06559720816474027, "f1": 0.6303763440860215, "f1_std": 0.066870267478454, "bacc": 0.6324728260869565, "bacc_std": 0.06724219039551839} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 21.54434690031882, "split": "test", "acc": 0.6727272727272727, "acc_std": 0.06633623344574666, "f1": 0.6673387096774194, "f1_std": 0.06714636079918689, "bacc": 0.6698369565217391, "bacc_std": 0.06692186277630337} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05792601722088597, "f1": 0.7758152173913043, "f1_std": 0.05990458566968057, "bacc": 0.7758152173913043, "bacc_std": 0.05974629269984236} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.051833375762873134, "f1": 0.8343927735028438, "f1_std": 0.052015482655581695, "bacc": 0.8410326086956521, "bacc_std": 0.050723901818792216} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05339166369449555, "f1": 0.7758152173913043, "f1_std": 0.05499757277201123, "bacc": 0.7758152173913043, "bacc_std": 0.05496629710954507} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05674736241003512, "f1": 0.78, "f1_std": 0.05690939624060673, "bacc": 0.7880434782608696, "bacc_std": 0.05621512208641315} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.057506489752343265, "f1": 0.7931623931623932, "f1_std": 0.06000923035031473, "bacc": 0.7914402173913043, "bacc_std": 0.06022658209321617} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.0559141135955275, "f1": 0.7758152173913043, "f1_std": 0.05764935256372829, "bacc": 0.7758152173913043, "bacc_std": 0.057242569965207234} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04690142291097763, "f1": 0.8307692307692308, "f1_std": 0.0491593420399302, "bacc": 0.8288043478260869, "bacc_std": 0.049412050355457045} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05617044898203124, "f1": 0.78, "f1_std": 0.05633226566131222, "bacc": 0.7880434782608696, "bacc_std": 0.05530833089002614} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.060961540511109163, "f1": 0.7433333333333334, "f1_std": 0.06132309481999507, "bacc": 0.7506793478260869, "bacc_std": 0.061262962462586036} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05289791822053223, "f1": 0.7417840375586855, "f1_std": 0.06162662117485513, "bacc": 0.7357336956521738, "bacc_std": 0.057939345976673155} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04995940169959819, "f1": 0.8106060606060606, "f1_std": 0.05342324293619793, "bacc": 0.8070652173913043, "bacc_std": 0.05335744521336223} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.058186363458820695, "f1": 0.741263440860215, "f1_std": 0.0588594520890131, "bacc": 0.7445652173913043, "bacc_std": 0.058643268237730695} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.0583507094151922, "f1": 0.7269116186693148, "f1_std": 0.058300880630144485, "bacc": 0.7411684782608696, "bacc_std": 0.05674260782124716} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05609437148588701, "f1": 0.7585275244849713, "f1_std": 0.05754945587676633, "bacc": 0.7601902173913043, "bacc_std": 0.057702394623882144} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.048984544703760464, "f1": 0.8074229691876751, "f1_std": 0.05421283994002026, "bacc": 0.8009510869565217, "bacc_std": 0.053779021817230446} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05907872321902431, "f1": 0.7585275244849713, "f1_std": 0.06051784761400008, "bacc": 0.7601902173913043, "bacc_std": 0.06047640759153292} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.0618446467414805, "f1": 0.6842283012495778, "f1_std": 0.06306130285870268, "bacc": 0.6854619565217391, "bacc_std": 0.06307073440685028} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0463196083284658, "f1": 0.8699763593380614, "f1_std": 0.04726466715635542, "bacc": 0.8722826086956521, "bacc_std": 0.04690989900847402} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.06250166543235616, "f1": 0.6892655367231638, "f1_std": 0.06268857306621861, "bacc": 0.6976902173913043, "bacc_std": 0.06230779891405676} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.05850902310861094, "f1": 0.7082228116710876, "f1_std": 0.058687950164569985, "bacc": 0.7194293478260869, "bacc_std": 0.05836545816543731} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05278993142166534, "f1": 0.8151881720430108, "f1_std": 0.05330421372783843, "bacc": 0.8192934782608696, "bacc_std": 0.05276652279663882} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06095899177058255, "f1": 0.696969696969697, "f1_std": 0.0642823199810322, "bacc": 0.6949728260869565, "bacc_std": 0.06362399550664577} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.051759137014278034, "f1": 0.8131793478260869, "f1_std": 0.05337524731097951, "bacc": 0.8131793478260869, "bacc_std": 0.05333847044425869} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.000774263682681127, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.05348391277402801, "f1": 0.6857142857142857, "f1_std": 0.059169943358793324, "bacc": 0.6827445652173914, "bacc_std": 0.05606006941261015} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.000774263682681127, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.05692435461874234, "f1": 0.6857142857142857, "f1_std": 0.0645108380465425, "bacc": 0.6827445652173914, "bacc_std": 0.06096761113213914} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05717625352313797, "f1": 0.7782258064516129, "f1_std": 0.05779277969899829, "bacc": 0.7819293478260869, "bacc_std": 0.05739258846811508} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.053838276346851954, "f1": 0.76890756302521, "f1_std": 0.05858255742517174, "bacc": 0.7635869565217391, "bacc_std": 0.057629345711253395} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05536475592240162, "f1": 0.7975911676145868, "f1_std": 0.05566791624642805, "bacc": 0.8036684782608696, "bacc_std": 0.05484813834575139} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05231890766418536, "f1": 0.7555555555555555, "f1_std": 0.054490950928459264, "bacc": 0.7540760869565217, "bacc_std": 0.054098637472921915} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.050851538897701616, "f1": 0.790003471017008, "f1_std": 0.05478050225874464, "bacc": 0.7853260869565217, "bacc_std": 0.054299158423413} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05353828938014423, "f1": 0.7758152173913043, "f1_std": 0.05534715495341467, "bacc": 0.7758152173913043, "bacc_std": 0.05556445464803174} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.000774263682681127, "split": "test", "acc": 0.6545454545454545, "acc_std": 0.05424278449177816, "f1": 0.6019047619047619, "f1_std": 0.06850631027860868, "bacc": 0.6114130434782609, "bacc_std": 0.05803401884377181} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06074904345742193, "f1": 0.696969696969697, "f1_std": 0.0639900734931278, "bacc": 0.6949728260869565, "bacc_std": 0.06305149809605932} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.060015413998033645, "f1": 0.7348484848484849, "f1_std": 0.06289254397634586, "bacc": 0.7323369565217391, "bacc_std": 0.062195796113683685} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.0599671094423938, "f1": 0.6754599097535579, "f1_std": 0.06470910504804414, "bacc": 0.6732336956521738, "bacc_std": 0.06325315842446516} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.0566743809365877, "f1": 0.7384510869565217, "f1_std": 0.058835603884003856, "bacc": 0.7384510869565217, "bacc_std": 0.05877436114787314} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05798653591229121, "f1": 0.7585275244849713, "f1_std": 0.05927327015180988, "bacc": 0.7601902173913043, "bacc_std": 0.059247363433676564} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 21.54434690031882, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.06068083145265171, "f1": 0.7213779128672746, "f1_std": 0.061735021443458785, "bacc": 0.7228260869565217, "bacc_std": 0.061749761955752} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05092169973726554, "f1": 0.7642857142857142, "f1_std": 0.05863371590337411, "bacc": 0.7574728260869565, "bacc_std": 0.05583878484268214} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05327165993345911, "f1": 0.8166666666666667, "f1_std": 0.05343491135336073, "bacc": 0.8254076086956521, "bacc_std": 0.05250007883523202} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.0580824037022807, "f1": 0.7303921568627451, "f1_std": 0.06325109172848836, "bacc": 0.7262228260869565, "bacc_std": 0.06170058423528727} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05908368067676599, "f1": 0.7239879558380728, "f1_std": 0.05972968440911708, "bacc": 0.7289402173913043, "bacc_std": 0.0598051661216153} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.05196376359803749, "f1": 0.790003471017008, "f1_std": 0.05602761469954495, "bacc": 0.7853260869565217, "bacc_std": 0.05542158468944219} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05372339318403677, "f1": 0.8328267477203647, "f1_std": 0.05483168939243797, "bacc": 0.8349184782608696, "bacc_std": 0.05473168421679525} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05378144938099625, "f1": 0.7303921568627451, "f1_std": 0.05845705330491706, "bacc": 0.7262228260869565, "bacc_std": 0.056824916212969985} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 2.782559402207126, "split": "test", "acc": 0.6727272727272727, "acc_std": 0.06309379086947457, "f1": 0.6590909090909092, "f1_std": 0.06614570709766047, "bacc": 0.6576086956521738, "bacc_std": 0.06511274501770409} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.6727272727272727, "acc_std": 0.060243033958258356, "f1": 0.6590909090909092, "f1_std": 0.06306504725757171, "bacc": 0.6576086956521738, "bacc_std": 0.06189317859583564} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.06026825980975284, "f1": 0.7066666666666667, "f1_std": 0.06045897725926979, "bacc": 0.7133152173913043, "bacc_std": 0.06031455934219918} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.7090909090909091, "acc_std": 0.059132807523572195, "f1": 0.696969696969697, "f1_std": 0.062188532585697245, "bacc": 0.6949728260869565, "bacc_std": 0.06137780496025041} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05569009882769124, "f1": 0.7020585048754062, "f1_std": 0.06514089178585111, "bacc": 0.6983695652173914, "bacc_std": 0.06027487144590829} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.7272727272727273, "acc_std": 0.05554426125782651, "f1": 0.7020585048754062, "f1_std": 0.06514241552131578, "bacc": 0.6983695652173914, "bacc_std": 0.060132784577739115} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04693129847830232, "f1": 0.8484848484848485, "f1_std": 0.0498917681143379, "bacc": 0.8444293478260869, "bacc_std": 0.05039427653513253} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05074836967621113, "f1": 0.8106060606060606, "f1_std": 0.0537946149708118, "bacc": 0.8070652173913043, "bacc_std": 0.05399110886059457} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.6909090909090909, "acc_std": 0.062007954701642866, "f1": 0.6842283012495778, "f1_std": 0.06328495981921806, "bacc": 0.6854619565217391, "bacc_std": 0.06325803182367894} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.000774263682681127, "split": "test", "acc": 0.6363636363636364, "acc_std": 0.06327853682837885, "f1": 0.6148459383753502, "f1_std": 0.06854776365341021, "bacc": 0.6141304347826086, "bacc_std": 0.06555718348716522} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.052674280580855985, "f1": 0.790003471017008, "f1_std": 0.05663044977609679, "bacc": 0.7853260869565217, "bacc_std": 0.056369005646708485} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04587794082721513, "f1": 0.8505434782608696, "f1_std": 0.0472775772746343, "bacc": 0.8505434782608696, "bacc_std": 0.04727981633746122} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.054720627805590956, "f1": 0.7811671087533156, "f1_std": 0.05467831151228022, "bacc": 0.7941576086956521, "bacc_std": 0.052870420540671405} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|--------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_sex | train | 100 | 0.60922 | 3.0549 | 0.92104 | 0.054794 | 0.91828 | 0.057358 | 0.91676 | 0.05869 | +| flat_mae | reg | logistic | aabc_sex | test | 100 | 0.60922 | 3.0549 | 0.75145 | 0.050578 | 0.74257 | 0.053585 | 0.743 | 0.05348 | + + +done! total time: 0:04:58 diff --git a/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..34b3ee00940c3cdffaf721cae533a6fae0681b28 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..de0817d56d8d303212ec0a27c031067174bbfcd0 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.3593813663804626,train,0.9629629629629629,0.00710605735752364,0.9625,0.007207931854607594,0.9619393919495699,0.007356897317842956 +flat_mae,patch,logistic,abide_dx,,0.3593813663804626,test,0.532258064516129,0.04481259392627998,0.5278361344537815,0.04494582457272667,0.5278868813825609,0.04484830762834818 +flat_mae,patch,logistic,abide_dx,1,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,1,2.782559402207126,test,0.6290322580645161,0.04377692719731147,0.6255252100840336,0.044481887428298034,0.6255252100840336,0.04441878959292454 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,train,0.9472934472934473,0.008531231402192158,0.9466516046213094,0.008642646740014217,0.9459948320413436,0.008730615089406136 +flat_mae,patch,logistic,abide_dx,2,0.3593813663804626,test,0.5483870967741935,0.04328874510370435,0.5473272490221643,0.04324560861526853,0.5488445378151261,0.04314501015380844 +flat_mae,patch,logistic,abide_dx,3,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,3,1291.5496650148827,test,0.6048387096774194,0.042551612169587756,0.5953379953379954,0.04388299792023957,0.5955882352941176,0.04304450952136265 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,train,0.9572649572649573,0.007386432609405558,0.9568357709713387,0.007458957928749552,0.9571059431524548,0.0074697638631237954 +flat_mae,patch,logistic,abide_dx,4,0.3593813663804626,test,0.6209677419354839,0.04242290859638592,0.6197559861681998,0.042623309280797946,0.6213235294117647,0.042828472385558154 +flat_mae,patch,logistic,abide_dx,5,0.000774263682681127,train,0.6752136752136753,0.014904624775857103,0.6512546083652179,0.017143218835508355,0.6552233296419343,0.01560595593436567 +flat_mae,patch,logistic,abide_dx,5,0.000774263682681127,test,0.6290322580645161,0.04248766730533587,0.6145945945945945,0.04526711285428143,0.6160714285714286,0.043450496095729145 +flat_mae,patch,logistic,abide_dx,6,0.000774263682681127,train,0.6737891737891738,0.016940803401247206,0.652696732379152,0.01886390621003319,0.6554078995939461,0.017511459220456646 +flat_mae,patch,logistic,abide_dx,6,0.000774263682681127,test,0.5564516129032258,0.03855289486398319,0.5077589317935763,0.044444423355268346,0.5309873949579832,0.03910035705634258 +flat_mae,patch,logistic,abide_dx,7,0.000774263682681127,train,0.6737891737891738,0.01710340933806183,0.6556781891823005,0.018963261886142828,0.6571797711332595,0.017802705472718276 +flat_mae,patch,logistic,abide_dx,7,0.000774263682681127,test,0.6209677419354839,0.03839503848453504,0.5881563140414104,0.04459846788490249,0.5992647058823529,0.03959961296941128 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,train,0.9501424501424501,0.008126390970730507,0.9496560753868,0.008201339043606254,0.9500553709856034,0.008197467534001199 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,test,0.5967741935483871,0.04439035528174495,0.5941345902068604,0.044767177849436283,0.5945378151260504,0.04486696554948261 +flat_mae,patch,logistic,abide_dx,9,0.005994842503189409,train,0.7706552706552706,0.015518045420968022,0.7663767960163628,0.01590717644454647,0.7648209671465486,0.01585147269573369 +flat_mae,patch,logistic,abide_dx,9,0.005994842503189409,test,0.5645161290322581,0.04166845504313284,0.555142173797502,0.04247270127119367,0.555672268907563,0.041874646639430614 +flat_mae,patch,logistic,abide_dx,10,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,10,2.782559402207126,test,0.6451612903225806,0.04363890234787019,0.6428384393820372,0.044146039347922966,0.6433823529411764,0.04431831886363558 +flat_mae,patch,logistic,abide_dx,11,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,11,21.54434690031882,test,0.5564516129032258,0.044795230137595295,0.551522325244953,0.04514515495360564,0.5514705882352942,0.04513333160893818 +flat_mae,patch,logistic,abide_dx,12,0.3593813663804626,train,0.9487179487179487,0.008624497264685211,0.9481727574750831,0.008724596765107267,0.9481727574750831,0.008796349070678219 +flat_mae,patch,logistic,abide_dx,12,0.3593813663804626,test,0.6693548387096774,0.0393280282817837,0.6644445911160979,0.040334940196631516,0.6638655462184874,0.039939439360959526 +flat_mae,patch,logistic,abide_dx,13,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,13,21.54434690031882,test,0.6451612903225806,0.043663679522794485,0.6450689565443664,0.043757028242016265,0.6496848739495797,0.043327385976290454 +flat_mae,patch,logistic,abide_dx,14,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,14,21.54434690031882,test,0.5645161290322581,0.04326564125029431,0.5626959247648903,0.04335304009637541,0.5635504201680672,0.0435570283829187 +flat_mae,patch,logistic,abide_dx,15,0.005994842503189409,train,0.7549857549857549,0.01648704336266942,0.7494875391088575,0.017122262135192533,0.74765596160945,0.01701889003212262 +flat_mae,patch,logistic,abide_dx,15,0.005994842503189409,test,0.6612903225806451,0.04306199098553012,0.6539994685091681,0.04439593196954897,0.6533613445378151,0.043673558770929315 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,train,0.8561253561253561,0.01343280250414621,0.8545525411559567,0.013602260427716461,0.8544481358434847,0.013695804703578663 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,test,0.5483870967741935,0.04102098077427774,0.5386659580122243,0.04227896228714021,0.539390756302521,0.04148991056035934 +flat_mae,patch,logistic,abide_dx,17,0.005994842503189409,train,0.7521367521367521,0.015769404487959812,0.7454231692677071,0.016436910802599916,0.7433001107419712,0.016204593877488113 +flat_mae,patch,logistic,abide_dx,17,0.005994842503189409,test,0.6129032258064516,0.041204986791946105,0.6092436974789917,0.04188094829160947,0.6092436974789917,0.04179415137359002 +flat_mae,patch,logistic,abide_dx,18,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,18,1291.5496650148827,test,0.5564516129032258,0.043560977869235656,0.5498646953996436,0.04433698163615193,0.5498949579831933,0.043965191201077385 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,train,0.9629629629629629,0.007123233581186115,0.9625692137320044,0.0071982091318168314,0.9625692137320044,0.007225635436601837 +flat_mae,patch,logistic,abide_dx,19,0.3593813663804626,test,0.5564516129032258,0.04520603773916625,0.5457875457875458,0.04642376503345621,0.5467436974789917,0.04571350217667228 +flat_mae,patch,logistic,abide_dx,20,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,20,166.81005372000556,test,0.5241935483870968,0.04402273322480928,0.5040336248389939,0.04650046842527766,0.509453781512605,0.0444828419824594 +flat_mae,patch,logistic,abide_dx,21,0.3593813663804626,train,0.9572649572649573,0.007419788031869225,0.9568601745257896,0.007488232612303167,0.9574012550756736,0.007491614967106633 +flat_mae,patch,logistic,abide_dx,21,0.3593813663804626,test,0.6129032258064516,0.04297434077004773,0.6119947848761408,0.0430724058929432,0.6139705882352942,0.043328353819962966 +flat_mae,patch,logistic,abide_dx,22,0.046415888336127774,train,0.8504273504273504,0.014383277436522998,0.8484091287689488,0.014651126485372696,0.8475083056478405,0.014770893730184089 +flat_mae,patch,logistic,abide_dx,22,0.046415888336127774,test,0.6048387096774194,0.04102530880491969,0.578494623655914,0.04608675152223312,0.5861344537815126,0.042123531722596814 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,train,0.8490028490028491,0.013086008178036292,0.8469140882159315,0.013294991557608571,0.8459210040605389,0.013354298408107363 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,test,0.5725806451612904,0.04350626397661507,0.5573516535327002,0.045784194660096464,0.5598739495798319,0.044157319734755236 +flat_mae,patch,logistic,abide_dx,24,0.000774263682681127,train,0.6780626780626781,0.015502764642501119,0.6564695081285674,0.01750233026140233,0.6592838685861941,0.016161662793897025 +flat_mae,patch,logistic,abide_dx,24,0.000774263682681127,test,0.6209677419354839,0.04102220154710216,0.5956989247311828,0.04592016933128449,0.6024159663865546,0.04212714371621047 +flat_mae,patch,logistic,abide_dx,25,0.005994842503189409,train,0.7621082621082621,0.016131136400707603,0.7560080169329613,0.016765436840537808,0.7538205980066446,0.016589396593365516 +flat_mae,patch,logistic,abide_dx,25,0.005994842503189409,test,0.5887096774193549,0.041188900134341955,0.5712833028269271,0.04442189067426689,0.5745798319327731,0.04226015773288047 +flat_mae,patch,logistic,abide_dx,26,0.005994842503189409,train,0.7592592592592593,0.01588630046343164,0.7528555209515972,0.016508513834832587,0.7506459948320413,0.01630156592454361 +flat_mae,patch,logistic,abide_dx,26,0.005994842503189409,test,0.532258064516129,0.04492425119546752,0.5170561375235025,0.046759789607849135,0.5199579831932774,0.04538828146876544 +flat_mae,patch,logistic,abide_dx,27,0.046415888336127774,train,0.8475783475783476,0.013401776023634238,0.8452007790039877,0.013675414090583912,0.8437430786267996,0.013735798008962814 +flat_mae,patch,logistic,abide_dx,27,0.046415888336127774,test,0.5645161290322581,0.04243367537005286,0.5588932806324111,0.04307026792753677,0.5588235294117647,0.042784335761109044 +flat_mae,patch,logistic,abide_dx,28,0.046415888336127774,train,0.8532763532763533,0.013589356549882784,0.8516723934560746,0.013727164359461218,0.8515688445921004,0.013726687999461978 +flat_mae,patch,logistic,abide_dx,28,0.046415888336127774,test,0.6209677419354839,0.043142300176464025,0.6137071651090342,0.044338139465088425,0.6134453781512605,0.0436725746137288 +flat_mae,patch,logistic,abide_dx,29,0.005994842503189409,train,0.7435897435897436,0.016054392442326634,0.7363919323748092,0.016883697014891192,0.7343669250645994,0.01667063471415173 +flat_mae,patch,logistic,abide_dx,29,0.005994842503189409,test,0.6370967741935484,0.038657895473165,0.6129032258064516,0.043657395269401295,0.6186974789915967,0.039878340238292335 +flat_mae,patch,logistic,abide_dx,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,30,166.81005372000556,test,0.6290322580645161,0.04328316788624037,0.6242424242424243,0.04399884505726737,0.6239495798319328,0.04376057233017527 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,train,0.9586894586894587,0.007426254786371738,0.9581320450885669,0.007552948928367879,0.9569213732004429,0.007794921669511657 +flat_mae,patch,logistic,abide_dx,31,0.3593813663804626,test,0.5806451612903226,0.04428827556766626,0.5766806722689075,0.044724181857276675,0.5766806722689075,0.0446086531846911 +flat_mae,patch,logistic,abide_dx,32,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,32,166.81005372000556,test,0.6048387096774194,0.04454853892665257,0.602745995423341,0.04482218065832809,0.6034663865546219,0.044980669686373556 +flat_mae,patch,logistic,abide_dx,33,0.000774263682681127,train,0.6894586894586895,0.015713034362213742,0.6719907407407408,0.01704026953182832,0.6728682170542635,0.01612554114838324 +flat_mae,patch,logistic,abide_dx,33,0.000774263682681127,test,0.49193548387096775,0.03611945077441761,0.4479542081831672,0.03884791534395827,0.4690126050420168,0.03586043026986065 +flat_mae,patch,logistic,abide_dx,34,0.005994842503189409,train,0.7549857549857549,0.015313573443548197,0.7488183996804687,0.015872216462758663,0.7467700258397932,0.01570877070060733 +flat_mae,patch,logistic,abide_dx,34,0.005994842503189409,test,0.5725806451612904,0.04299839069659932,0.5478500171998624,0.04703033221914887,0.5551470588235294,0.04372187549967274 +flat_mae,patch,logistic,abide_dx,35,0.005994842503189409,train,0.7578347578347578,0.015467144631359007,0.752400474700615,0.01595188331081961,0.7505352528608342,0.015829232407084257 +flat_mae,patch,logistic,abide_dx,35,0.005994842503189409,test,0.5806451612903226,0.043184730122032715,0.5766806722689075,0.04361862108781553,0.5766806722689075,0.04356753444831961 +flat_mae,patch,logistic,abide_dx,36,0.000774263682681127,train,0.6837606837606838,0.01602507020192624,0.6655047777672845,0.017731031241402035,0.6668143226282761,0.016647355237335428 +flat_mae,patch,logistic,abide_dx,36,0.000774263682681127,test,0.6048387096774194,0.04075789537475913,0.5907590759075907,0.043085552642135996,0.592436974789916,0.04141956016592495 +flat_mae,patch,logistic,abide_dx,37,0.000774263682681127,train,0.6737891737891738,0.01699730930087986,0.6521737248987947,0.018907683092885357,0.6551125876707272,0.01755859782798685 +flat_mae,patch,logistic,abide_dx,37,0.000774263682681127,test,0.6209677419354839,0.04199358258291095,0.5920767130958213,0.04753369166404827,0.6008403361344538,0.04314657420722829 +flat_mae,patch,logistic,abide_dx,38,0.000774263682681127,train,0.6595441595441596,0.016176920916876916,0.6401428464186516,0.017663448503106218,0.6424880029531193,0.01660918174630035 +flat_mae,patch,logistic,abide_dx,38,0.000774263682681127,test,0.6048387096774194,0.0371220951452213,0.566216891554223,0.04324312193332159,0.58140756302521,0.03806441249254088 +flat_mae,patch,logistic,abide_dx,39,0.3593813663804626,train,0.9558404558404558,0.007362662909799348,0.9553840697223857,0.007431079933298554,0.9555186415651531,0.0073952130664021055 +flat_mae,patch,logistic,abide_dx,39,0.3593813663804626,test,0.5806451612903226,0.041375906766740855,0.5735449735449736,0.042562346542897575,0.5735294117647058,0.04215186375591522 +flat_mae,patch,logistic,abide_dx,40,0.000774263682681127,train,0.6809116809116809,0.01712843140729269,0.660532792193774,0.019271538132152963,0.6627537836840163,0.017879391606855637 +flat_mae,patch,logistic,abide_dx,40,0.000774263682681127,test,0.5967741935483871,0.03921584060053084,0.5639943741209563,0.04406416342054804,0.5756302521008403,0.03993059411043034 +flat_mae,patch,logistic,abide_dx,41,0.3593813663804626,train,0.9515669515669516,0.0083511553647972,0.9510805404341838,0.008428099521537408,0.9513473606496863,0.008395734210878613 +flat_mae,patch,logistic,abide_dx,41,0.3593813663804626,test,0.5887096774193549,0.04250206581255866,0.5788211788211788,0.04412446113420484,0.5793067226890757,0.043108657298479486 +flat_mae,patch,logistic,abide_dx,42,0.000774263682681127,train,0.6752136752136753,0.016687530710686953,0.6539539227895392,0.018590459907108416,0.6566998892580288,0.017278917385306538 +flat_mae,patch,logistic,abide_dx,42,0.000774263682681127,test,0.5806451612903226,0.043342272084279106,0.5545730864879801,0.04804572968899776,0.5625,0.0442178280702285 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,train,0.8361823361823362,0.014260146947900733,0.8335062272754459,0.014592632008161825,0.8319306016980436,0.014684054986807757 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,test,0.5967741935483871,0.04336455824230737,0.5810810810810811,0.045710087061864864,0.5835084033613446,0.043959655317026385 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.7621082621082621,0.01633365907949505,0.7557803076858979,0.01706576684707959,0.7535252860834256,0.01691933662000577 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.5967741935483871,0.041036578566408834,0.575109649122807,0.044900539560058635,0.5803571428571428,0.04195895611711056 +flat_mae,patch,logistic,abide_dx,45,0.046415888336127774,train,0.8532763532763533,0.012724771985358563,0.8516723934560746,0.01285207410736678,0.8515688445921004,0.012853444638447804 +flat_mae,patch,logistic,abide_dx,45,0.046415888336127774,test,0.6129032258064516,0.04223740876606413,0.6092436974789917,0.04240910725578033,0.6092436974789917,0.04222591134572192 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,train,0.9558404558404558,0.007350429558956357,0.9552740344004784,0.0074577456881269035,0.9543373938722776,0.0076105160382080265 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,test,0.5483870967741935,0.04382966212507142,0.5454307410316837,0.04430015898466531,0.5456932773109244,0.04450111302630659 +flat_mae,patch,logistic,abide_dx,47,0.000774263682681127,train,0.6851851851851852,0.015623234163738902,0.6643248611468717,0.017518088893381415,0.6666297526762643,0.016240027482123654 +flat_mae,patch,logistic,abide_dx,47,0.000774263682681127,test,0.6370967741935484,0.03560367970202885,0.6056815772736909,0.04079536875401219,0.615546218487395,0.03662179202146294 +flat_mae,patch,logistic,abide_dx,48,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,48,21.54434690031882,test,0.5806451612903226,0.042718800799265974,0.5778999738151349,0.042986292099479996,0.5782563025210083,0.04294437153818764 +flat_mae,patch,logistic,abide_dx,49,0.046415888336127774,train,0.8561253561253561,0.013406693018769825,0.8539846245410119,0.01367031039413178,0.8526762643041712,0.013755979729932075 +flat_mae,patch,logistic,abide_dx,49,0.046415888336127774,test,0.5403225806451613,0.04549166028017473,0.5352140461629513,0.045870377298101894,0.5351890756302521,0.04566915474528348 +flat_mae,patch,logistic,abide_dx,50,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,50,2.782559402207126,test,0.5887096774193549,0.04334846283282468,0.5854473942969518,0.043790071072607274,0.585609243697479,0.0437324542252678 +flat_mae,patch,logistic,abide_dx,51,0.000774263682681127,train,0.6908831908831908,0.016434845261367917,0.6741679019000135,0.01784637611571835,0.674750830564784,0.01689833987356449 +flat_mae,patch,logistic,abide_dx,51,0.000774263682681127,test,0.5887096774193549,0.03951517773706822,0.5612903225806452,0.04439937718859952,0.5698529411764706,0.0404807653547977 +flat_mae,patch,logistic,abide_dx,52,0.000774263682681127,train,0.6951566951566952,0.016047980630721336,0.6747100652190858,0.018106638016993675,0.6765596160944998,0.01675147294212843 +flat_mae,patch,logistic,abide_dx,52,0.000774263682681127,test,0.5725806451612904,0.0449170353255306,0.5573516535327002,0.046820273380092994,0.5598739495798319,0.04541648872682065 +flat_mae,patch,logistic,abide_dx,53,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,53,166.81005372000556,test,0.5887096774193549,0.043457883854309945,0.5826018084614877,0.04453456361628661,0.5824579831932774,0.04403509328010831 +flat_mae,patch,logistic,abide_dx,54,0.046415888336127774,train,0.8333333333333334,0.013815735759982318,0.8309704372163855,0.014038948679415927,0.8299372462163159,0.014083752724016676 +flat_mae,patch,logistic,abide_dx,54,0.046415888336127774,test,0.6048387096774194,0.04252337301839545,0.5931704050887178,0.04468840063737031,0.5940126050420168,0.04337411284593554 +flat_mae,patch,logistic,abide_dx,55,0.005994842503189409,train,0.7564102564102564,0.01594096298911342,0.7499307342172967,0.016628267759734822,0.747766703580657,0.016470149024975376 +flat_mae,patch,logistic,abide_dx,55,0.005994842503189409,test,0.5645161290322581,0.042801407194815455,0.5528846153846154,0.0445449858119839,0.5540966386554622,0.0434637714805865 +flat_mae,patch,logistic,abide_dx,56,0.000774263682681127,train,0.6737891737891738,0.01591792836208774,0.652696732379152,0.01772797196505046,0.6554078995939461,0.01646744259919505 +flat_mae,patch,logistic,abide_dx,56,0.000774263682681127,test,0.532258064516129,0.04129252451286022,0.5107482993197279,0.04337257148296088,0.5168067226890757,0.04149394593657492 +flat_mae,patch,logistic,abide_dx,57,0.000774263682681127,train,0.6823361823361823,0.01603952548263112,0.6632803845864298,0.017689174927459198,0.6649317091177556,0.01659805910935959 +flat_mae,patch,logistic,abide_dx,57,0.000774263682681127,test,0.6370967741935484,0.0385530804269364,0.6190346145968457,0.042128043234822124,0.6218487394957983,0.03968019660724164 +flat_mae,patch,logistic,abide_dx,58,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,58,21.54434690031882,test,0.6290322580645161,0.044037055156391114,0.6266038229903116,0.04425508211186732,0.6271008403361344,0.044277488851512725 +flat_mae,patch,logistic,abide_dx,59,0.000774263682681127,train,0.6709401709401709,0.016462467147157173,0.6531464762161434,0.01801131673169961,0.6545957918050942,0.016995577632270574 +flat_mae,patch,logistic,abide_dx,59,0.000774263682681127,test,0.6129032258064516,0.0398334037213635,0.5978378378378378,0.042371859254084425,0.5997899159663866,0.04059901611002986 +flat_mae,patch,logistic,abide_dx,60,0.005994842503189409,train,0.7706552706552706,0.01567258607576679,0.7633914272256241,0.016555320695866196,0.7606866002214839,0.01630784596244999 +flat_mae,patch,logistic,abide_dx,60,0.005994842503189409,test,0.5967741935483871,0.04386356673815658,0.5929621848739496,0.044490973256672776,0.5929621848739496,0.044422961784538216 +flat_mae,patch,logistic,abide_dx,61,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,61,166.81005372000556,test,0.5806451612903226,0.04278787549390596,0.5752305665349143,0.04335207687429001,0.5751050420168067,0.043033043925578184 +flat_mae,patch,logistic,abide_dx,62,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,62,166.81005372000556,test,0.5564516129032258,0.040535730182593294,0.543354536324071,0.04257794387192294,0.5451680672268907,0.04117415525774854 +flat_mae,patch,logistic,abide_dx,63,0.046415888336127774,train,0.8461538461538461,0.013475284740474316,0.8433450145464163,0.013811365726017525,0.8412698412698412,0.013858154235251139 +flat_mae,patch,logistic,abide_dx,63,0.046415888336127774,test,0.6048387096774194,0.04734780645684353,0.602745995423341,0.04769065184807548,0.6034663865546219,0.04777276598510858 +flat_mae,patch,logistic,abide_dx,64,0.005994842503189409,train,0.7564102564102564,0.01660903763032133,0.751261388760534,0.017121333864478557,0.7495385751199705,0.017034969551031117 +flat_mae,patch,logistic,abide_dx,64,0.005994842503189409,test,0.5967741935483871,0.04452667885743154,0.5929621848739496,0.04517006457034381,0.5929621848739496,0.04514634767027715 +flat_mae,patch,logistic,abide_dx,65,0.046415888336127774,train,0.8561253561253561,0.013656419896918012,0.8541840191015604,0.013861467363854957,0.8532668881506091,0.01388636712290936 +flat_mae,patch,logistic,abide_dx,65,0.046415888336127774,test,0.5241935483870968,0.044020440337800115,0.5040336248389939,0.04555446231087554,0.509453781512605,0.044059268836293054 +flat_mae,patch,logistic,abide_dx,66,0.000774263682681127,train,0.6809116809116809,0.01634783951236194,0.6620125180548868,0.01805796757985871,0.663639719453673,0.016929156317242417 +flat_mae,patch,logistic,abide_dx,66,0.000774263682681127,test,0.5725806451612904,0.04106405683548232,0.5478500171998624,0.04498775148018315,0.5551470588235294,0.041788398751812075 +flat_mae,patch,logistic,abide_dx,67,0.3593813663804626,train,0.9501424501424501,0.008401521011819879,0.9495667916720548,0.008511060763121947,0.9491694352159468,0.008624692536310664 +flat_mae,patch,logistic,abide_dx,67,0.3593813663804626,test,0.5806451612903226,0.043571711197166955,0.5788923719958203,0.043839083838471606,0.5798319327731092,0.04388669647108308 +flat_mae,patch,logistic,abide_dx,68,0.046415888336127774,train,0.8404558404558404,0.013975098359615362,0.8379087123242486,0.014256525245045778,0.8363971945367294,0.014277446519055412 +flat_mae,patch,logistic,abide_dx,68,0.046415888336127774,test,0.6129032258064516,0.04265633546444118,0.6092436974789917,0.04316971950316128,0.6092436974789917,0.04293640465642508 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,69,21.54434690031882,test,0.6209677419354839,0.044411901710325066,0.6179613241560145,0.04480054752458687,0.618172268907563,0.044739154802597075 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,test,0.5806451612903226,0.04432563261314689,0.5788923719958203,0.044515907203323726,0.5798319327731092,0.04468473659717821 +flat_mae,patch,logistic,abide_dx,71,0.005994842503189409,train,0.7549857549857549,0.01594416540873441,0.7490460157126824,0.016498529765891456,0.7470653377630121,0.016354044641542498 +flat_mae,patch,logistic,abide_dx,71,0.005994842503189409,test,0.6370967741935484,0.04198862637735642,0.626380984265149,0.043983826107817425,0.6265756302521008,0.04271422417022086 +flat_mae,patch,logistic,abide_dx,72,0.000774263682681127,train,0.6937321937321937,0.01654832973895588,0.6776067755337443,0.018042268028799102,0.6779254337393872,0.017101047279281748 +flat_mae,patch,logistic,abide_dx,72,0.000774263682681127,test,0.5645161290322581,0.04626522585948701,0.5528846153846154,0.04818911287454669,0.5540966386554622,0.04701337794738415 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,train,0.9544159544159544,0.008037135504274243,0.9539037362925997,0.008140230662542804,0.9536360280546328,0.00825330665346403 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,test,0.5967741935483871,0.044953586308061066,0.5929621848739496,0.045713950851821596,0.5929621848739496,0.04570900429629719 +flat_mae,patch,logistic,abide_dx,74,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,74,10000.0,test,0.5483870967741935,0.04391208639937176,0.5454307410316837,0.04414174707395286,0.5456932773109244,0.0441262687153829 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,test,0.5887096774193549,0.04341759031548538,0.5826018084614877,0.0446515179723668,0.5824579831932774,0.044321436139511804 +flat_mae,patch,logistic,abide_dx,76,0.005994842503189409,train,0.7635327635327636,0.01623592307230348,0.7573564319327031,0.016881088523436286,0.7551125876707272,0.01669399413750872 +flat_mae,patch,logistic,abide_dx,76,0.005994842503189409,test,0.5483870967741935,0.04095345191464679,0.5337093741606231,0.04240032462380671,0.5362394957983193,0.04124343095380982 +flat_mae,patch,logistic,abide_dx,77,0.005994842503189409,train,0.7592592592592593,0.016817569703296537,0.7535332550820081,0.01735728828366081,0.7515319306016981,0.01720968190221013 +flat_mae,patch,logistic,abide_dx,77,0.005994842503189409,test,0.6370967741935484,0.043066630369751314,0.6351748937561295,0.04326330974279589,0.6360294117647058,0.04321221968962662 +flat_mae,patch,logistic,abide_dx,78,0.005994842503189409,train,0.7991452991452992,0.014576673546906614,0.7943679820506695,0.015106737744223837,0.791842008121078,0.015034518875958428 +flat_mae,patch,logistic,abide_dx,78,0.005994842503189409,test,0.5483870967741935,0.04165500183578975,0.5386659580122243,0.04251723271154876,0.539390756302521,0.041881019503858544 +flat_mae,patch,logistic,abide_dx,79,0.005994842503189409,train,0.7777777777777778,0.015064211068288386,0.7719735143463957,0.015699364982661064,0.7695090439276486,0.015565563321297531 +flat_mae,patch,logistic,abide_dx,79,0.005994842503189409,test,0.5725806451612904,0.04339022653299713,0.5623043623043623,0.044679292207003306,0.5630252100840336,0.04379020386845396 +flat_mae,patch,logistic,abide_dx,80,0.000774263682681127,train,0.6866096866096866,0.015721503759926175,0.6685182482378496,0.017419289415010083,0.6696936138796603,0.016333457696975365 +flat_mae,patch,logistic,abide_dx,80,0.000774263682681127,test,0.5806451612903226,0.04408798317167255,0.5613605442176871,0.046140684042599876,0.5656512605042017,0.044359150221676226 +flat_mae,patch,logistic,abide_dx,81,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,81,21.54434690031882,test,0.5887096774193549,0.04126512588062478,0.5712833028269271,0.04433508011310735,0.5745798319327731,0.042056626037086375 +flat_mae,patch,logistic,abide_dx,82,0.005994842503189409,train,0.7606837606837606,0.016800069756169,0.7537253591713999,0.01763449474729737,0.7513473606496862,0.01738783956609031 +flat_mae,patch,logistic,abide_dx,82,0.005994842503189409,test,0.6774193548387096,0.042304210214505235,0.6669352672575879,0.04508697722794599,0.6664915966386555,0.04362538052304314 +flat_mae,patch,logistic,abide_dx,83,0.046415888336127774,train,0.8390313390313391,0.013175706442764537,0.8368593481037259,0.0133769636720083,0.8359911406423035,0.013409181267901131 +flat_mae,patch,logistic,abide_dx,83,0.046415888336127774,test,0.6209677419354839,0.043620680734270105,0.6097756946769334,0.04561112327390135,0.6102941176470589,0.044476065820764146 +flat_mae,patch,logistic,abide_dx,84,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,84,2.782559402207126,test,0.6129032258064516,0.04441279205155623,0.6119947848761408,0.04446328157055765,0.6139705882352942,0.04458761535185911 +flat_mae,patch,logistic,abide_dx,85,0.3593813663804626,train,0.9601139601139601,0.00738920127294874,0.9597133862399161,0.007457944707163694,0.9599852344038391,0.007423815872720944 +flat_mae,patch,logistic,abide_dx,85,0.3593813663804626,test,0.5564516129032258,0.04453133213978223,0.5498646953996436,0.044976037125406085,0.5498949579831933,0.0446421998345085 +flat_mae,patch,logistic,abide_dx,86,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,86,2.782559402207126,test,0.5403225806451613,0.042999963700587264,0.531517200238616,0.044615301423886644,0.5320378151260504,0.04372396976748105 +flat_mae,patch,logistic,abide_dx,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,87,166.81005372000556,test,0.6290322580645161,0.04447011120789863,0.628161668839635,0.044376468554319384,0.6302521008403361,0.0443212361699049 +flat_mae,patch,logistic,abide_dx,88,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,88,166.81005372000556,test,0.5564516129032258,0.04248166648700364,0.5529334644378892,0.04288710029210345,0.553046218487395,0.04294487313266584 +flat_mae,patch,logistic,abide_dx,89,0.000774263682681127,train,0.6780626780626781,0.015043254113465156,0.6589947726803769,0.016571387904041685,0.6607604282022886,0.015516220077667323 +flat_mae,patch,logistic,abide_dx,89,0.000774263682681127,test,0.6290322580645161,0.042668930348270455,0.6169755573462261,0.044707924252205176,0.6176470588235294,0.04331782261636747 +flat_mae,patch,logistic,abide_dx,90,0.046415888336127774,train,0.8532763532763533,0.013506764949828188,0.8512965739352546,0.013718296247264021,0.8503875968992247,0.013771712090492574 +flat_mae,patch,logistic,abide_dx,90,0.046415888336127774,test,0.6209677419354839,0.04610787920143035,0.6167554415729598,0.04701270587431229,0.6165966386554622,0.046841702506412425 +flat_mae,patch,logistic,abide_dx,91,0.005994842503189409,train,0.7635327635327636,0.01588634338165091,0.7586349740267272,0.016451087485395074,0.7568844592100405,0.016396752121987667 +flat_mae,patch,logistic,abide_dx,91,0.005994842503189409,test,0.6290322580645161,0.04221412083555494,0.6210470369386127,0.04349770023752278,0.6207983193277311,0.04285306069906153 +flat_mae,patch,logistic,abide_dx,92,0.3593813663804626,train,0.9544159544159544,0.007395530144703387,0.9539037362925997,0.007481700236296725,0.9536360280546328,0.007534103321436029 +flat_mae,patch,logistic,abide_dx,92,0.3593813663804626,test,0.5887096774193549,0.04591990719950595,0.5841388834089565,0.04658710622977248,0.5840336134453781,0.046380208422524966 +flat_mae,patch,logistic,abide_dx,93,0.000774263682681127,train,0.6937321937321937,0.016387867314329004,0.6758230074810075,0.017919849164595613,0.6767441860465115,0.016904187088499383 +flat_mae,patch,logistic,abide_dx,93,0.000774263682681127,test,0.6048387096774194,0.039348307231670314,0.574718275355218,0.044538868681577026,0.5845588235294117,0.0403837887594712 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,train,0.8433048433048433,0.014066377354936198,0.8408031996041727,0.014406793345262701,0.8392764857881136,0.014518507804889379 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,test,0.5564516129032258,0.04176191125954305,0.5479551932126997,0.04236626419146795,0.5483193277310925,0.041884946072517575 +flat_mae,patch,logistic,abide_dx,95,0.000774263682681127,train,0.6809116809116809,0.01713789501532929,0.6647793164608773,0.01847791972763799,0.6654115909929863,0.017569493134448014 +flat_mae,patch,logistic,abide_dx,95,0.000774263682681127,test,0.5806451612903226,0.041704525291155946,0.5581140350877193,0.04567810868466739,0.5640756302521008,0.04262920222422063 +flat_mae,patch,logistic,abide_dx,96,0.000774263682681127,train,0.6780626780626781,0.016530040235181013,0.6585044556373498,0.018547787631551457,0.6604651162790698,0.01726003717170142 +flat_mae,patch,logistic,abide_dx,96,0.000774263682681127,test,0.5967741935483871,0.040313921650915706,0.575109649122807,0.04387450473932039,0.5803571428571428,0.04102089371018664 +flat_mae,patch,logistic,abide_dx,97,0.005994842503189409,train,0.7521367521367521,0.016654267674700865,0.7465746035170999,0.017220888377762675,0.7447766703580657,0.017106724746365192 +flat_mae,patch,logistic,abide_dx,97,0.005994842503189409,test,0.5967741935483871,0.040884761656294226,0.5810810810810811,0.04333494557102323,0.5835084033613446,0.04164021071216353 +flat_mae,patch,logistic,abide_dx,98,0.3593813663804626,train,0.9487179487179487,0.008404148427877857,0.948076923076923,0.008526310766311261,0.9472868217054264,0.008675337412900452 +flat_mae,patch,logistic,abide_dx,98,0.3593813663804626,test,0.6129032258064516,0.04350943299590779,0.610369206598586,0.04394723104831792,0.6108193277310925,0.04403938299881905 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,train,0.9658119658119658,0.006632411935126407,0.9654485049833887,0.006701016958820985,0.9654485049833887,0.0067016513791176326 +flat_mae,patch,logistic,abide_dx,99,0.3593813663804626,test,0.6129032258064516,0.04388134068546445,0.6092436974789917,0.04426940309364152,0.6092436974789917,0.04412279845625132 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,train,0.8547008547008547,0.0126855370265588,0.8526909150757077,0.012902651157123517,0.8516795865633076,0.012966407729831188 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,test,0.6612903225806451,0.042874993742851225,0.6590730557737627,0.04307228407780876,0.6596638655462186,0.04303058077846806 diff --git a/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..243de85d897851dd8a94416efc2d3ac1b87c35a6 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:43:10 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:23:46 time: 4.9345 data: 4.1383 max mem: 2698 +extract (train) [ 20/289] eta: 0:01:59 time: 0.2197 data: 0.0841 max mem: 3005 +extract (train) [ 40/289] eta: 0:01:16 time: 0.1669 data: 0.0526 max mem: 3005 +extract (train) [ 60/289] eta: 0:01:01 time: 0.1807 data: 0.0629 max mem: 3005 +extract (train) [ 80/289] eta: 0:00:52 time: 0.2039 data: 0.0738 max mem: 3005 +extract (train) [100/289] eta: 0:00:45 time: 0.1904 data: 0.0670 max mem: 3005 +extract (train) [120/289] eta: 0:00:39 time: 0.1986 data: 0.0718 max mem: 3005 +extract (train) [140/289] eta: 0:00:33 time: 0.1996 data: 0.0720 max mem: 3005 +extract (train) [160/289] eta: 0:00:28 time: 0.1841 data: 0.0633 max mem: 3005 +extract (train) [180/289] eta: 0:00:23 time: 0.1832 data: 0.0620 max mem: 3005 +extract (train) [200/289] eta: 0:00:19 time: 0.1764 data: 0.0582 max mem: 3005 +extract (train) [220/289] eta: 0:00:14 time: 0.1748 data: 0.0571 max mem: 3005 +extract (train) [240/289] eta: 0:00:10 time: 0.1779 data: 0.0593 max mem: 3005 +extract (train) [260/289] eta: 0:00:06 time: 0.2020 data: 0.0743 max mem: 3005 +extract (train) [280/289] eta: 0:00:01 time: 0.1582 data: 0.0497 max mem: 3005 +extract (train) [288/289] eta: 0:00:00 time: 0.1586 data: 0.0497 max mem: 3005 +extract (train) Total time: 0:00:58 (0.2040 s / it) +extract (validation) [ 0/62] eta: 0:04:22 time: 4.2399 data: 4.0744 max mem: 3005 +extract (validation) [20/62] eta: 0:00:17 time: 0.2251 data: 0.0854 max mem: 3005 +extract (validation) [40/62] eta: 0:00:06 time: 0.1796 data: 0.0625 max mem: 3005 +extract (validation) [60/62] eta: 0:00:00 time: 0.1688 data: 0.0555 max mem: 3005 +extract (validation) [61/62] eta: 0:00:00 time: 0.1691 data: 0.0557 max mem: 3005 +extract (validation) Total time: 0:00:16 (0.2630 s / it) +extract (test) [ 0/62] eta: 0:04:11 time: 4.0521 data: 3.9180 max mem: 3005 +extract (test) [20/62] eta: 0:00:16 time: 0.2215 data: 0.0803 max mem: 3005 +extract (test) [40/62] eta: 0:00:06 time: 0.1690 data: 0.0525 max mem: 3005 +extract (test) [60/62] eta: 0:00:00 time: 0.1736 data: 0.0562 max mem: 3005 +extract (test) [61/62] eta: 0:00:00 time: 0.1747 data: 0.0568 max mem: 3005 +extract (test) Total time: 0:00:15 (0.2563 s / it) +feature extraction time: 0:01:31 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|----------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.35938 | train | 0.96296 | 0.0071061 | 0.9625 | 0.0072079 | 0.96194 | 0.0073569 | +| flat_mae | patch | logistic | abide_dx | | 0.35938 | test | 0.53226 | 0.044813 | 0.52784 | 0.044946 | 0.52789 | 0.044848 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04377692719731147, "f1": 0.6255252100840336, "f1_std": 0.044481887428298034, "bacc": 0.6255252100840336, "bacc_std": 0.04441878959292454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04328874510370435, "f1": 0.5473272490221643, "f1_std": 0.04324560861526853, "bacc": 0.5488445378151261, "bacc_std": 0.04314501015380844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 1291.5496650148827, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.042551612169587756, "f1": 0.5953379953379954, "f1_std": 0.04388299792023957, "bacc": 0.5955882352941176, "bacc_std": 0.04304450952136265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04242290859638592, "f1": 0.6197559861681998, "f1_std": 0.042623309280797946, "bacc": 0.6213235294117647, "bacc_std": 0.042828472385558154} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 0.000774263682681127, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04248766730533587, "f1": 0.6145945945945945, "f1_std": 0.04526711285428143, "bacc": 0.6160714285714286, "bacc_std": 0.043450496095729145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.000774263682681127, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.03855289486398319, "f1": 0.5077589317935763, "f1_std": 0.044444423355268346, "bacc": 0.5309873949579832, "bacc_std": 0.03910035705634258} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.000774263682681127, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.03839503848453504, "f1": 0.5881563140414104, "f1_std": 0.04459846788490249, "bacc": 0.5992647058823529, "bacc_std": 0.03959961296941128} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04439035528174495, "f1": 0.5941345902068604, "f1_std": 0.044767177849436283, "bacc": 0.5945378151260504, "bacc_std": 0.04486696554948261} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04166845504313284, "f1": 0.555142173797502, "f1_std": 0.04247270127119367, "bacc": 0.555672268907563, "bacc_std": 0.041874646639430614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04363890234787019, "f1": 0.6428384393820372, "f1_std": 0.044146039347922966, "bacc": 0.6433823529411764, "bacc_std": 0.04431831886363558} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 21.54434690031882, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.044795230137595295, "f1": 0.551522325244953, "f1_std": 0.04514515495360564, "bacc": 0.5514705882352942, "bacc_std": 0.04513333160893818} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.0393280282817837, "f1": 0.6644445911160979, "f1_std": 0.040334940196631516, "bacc": 0.6638655462184874, "bacc_std": 0.039939439360959526} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 21.54434690031882, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.043663679522794485, "f1": 0.6450689565443664, "f1_std": 0.043757028242016265, "bacc": 0.6496848739495797, "bacc_std": 0.043327385976290454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 21.54434690031882, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04326564125029431, "f1": 0.5626959247648903, "f1_std": 0.04335304009637541, "bacc": 0.5635504201680672, "bacc_std": 0.0435570283829187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04306199098553012, "f1": 0.6539994685091681, "f1_std": 0.04439593196954897, "bacc": 0.6533613445378151, "bacc_std": 0.043673558770929315} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04102098077427774, "f1": 0.5386659580122243, "f1_std": 0.04227896228714021, "bacc": 0.539390756302521, "bacc_std": 0.04148991056035934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041204986791946105, "f1": 0.6092436974789917, "f1_std": 0.04188094829160947, "bacc": 0.6092436974789917, "bacc_std": 0.04179415137359002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 1291.5496650148827, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.043560977869235656, "f1": 0.5498646953996436, "f1_std": 0.04433698163615193, "bacc": 0.5498949579831933, "bacc_std": 0.043965191201077385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04520603773916625, "f1": 0.5457875457875458, "f1_std": 0.04642376503345621, "bacc": 0.5467436974789917, "bacc_std": 0.04571350217667228} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 166.81005372000556, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.04402273322480928, "f1": 0.5040336248389939, "f1_std": 0.04650046842527766, "bacc": 0.509453781512605, "bacc_std": 0.0444828419824594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04297434077004773, "f1": 0.6119947848761408, "f1_std": 0.0430724058929432, "bacc": 0.6139705882352942, "bacc_std": 0.043328353819962966} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04102530880491969, "f1": 0.578494623655914, "f1_std": 0.04608675152223312, "bacc": 0.5861344537815126, "bacc_std": 0.042123531722596814} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04350626397661507, "f1": 0.5573516535327002, "f1_std": 0.045784194660096464, "bacc": 0.5598739495798319, "bacc_std": 0.044157319734755236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.000774263682681127, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04102220154710216, "f1": 0.5956989247311828, "f1_std": 0.04592016933128449, "bacc": 0.6024159663865546, "bacc_std": 0.04212714371621047} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.041188900134341955, "f1": 0.5712833028269271, "f1_std": 0.04442189067426689, "bacc": 0.5745798319327731, "bacc_std": 0.04226015773288047} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04492425119546752, "f1": 0.5170561375235025, "f1_std": 0.046759789607849135, "bacc": 0.5199579831932774, "bacc_std": 0.04538828146876544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04243367537005286, "f1": 0.5588932806324111, "f1_std": 0.04307026792753677, "bacc": 0.5588235294117647, "bacc_std": 0.042784335761109044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043142300176464025, "f1": 0.6137071651090342, "f1_std": 0.044338139465088425, "bacc": 0.6134453781512605, "bacc_std": 0.0436725746137288} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.038657895473165, "f1": 0.6129032258064516, "f1_std": 0.043657395269401295, "bacc": 0.6186974789915967, "bacc_std": 0.039878340238292335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04328316788624037, "f1": 0.6242424242424243, "f1_std": 0.04399884505726737, "bacc": 0.6239495798319328, "bacc_std": 0.04376057233017527} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04428827556766626, "f1": 0.5766806722689075, "f1_std": 0.044724181857276675, "bacc": 0.5766806722689075, "bacc_std": 0.0446086531846911} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 166.81005372000556, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04454853892665257, "f1": 0.602745995423341, "f1_std": 0.04482218065832809, "bacc": 0.6034663865546219, "bacc_std": 0.044980669686373556} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.000774263682681127, "split": "test", "acc": 0.49193548387096775, "acc_std": 0.03611945077441761, "f1": 0.4479542081831672, "f1_std": 0.03884791534395827, "bacc": 0.4690126050420168, "bacc_std": 0.03586043026986065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04299839069659932, "f1": 0.5478500171998624, "f1_std": 0.04703033221914887, "bacc": 0.5551470588235294, "bacc_std": 0.04372187549967274} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043184730122032715, "f1": 0.5766806722689075, "f1_std": 0.04361862108781553, "bacc": 0.5766806722689075, "bacc_std": 0.04356753444831961} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04075789537475913, "f1": 0.5907590759075907, "f1_std": 0.043085552642135996, "bacc": 0.592436974789916, "bacc_std": 0.04141956016592495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04199358258291095, "f1": 0.5920767130958213, "f1_std": 0.04753369166404827, "bacc": 0.6008403361344538, "bacc_std": 0.04314657420722829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.000774263682681127, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.0371220951452213, "f1": 0.566216891554223, "f1_std": 0.04324312193332159, "bacc": 0.58140756302521, "bacc_std": 0.03806441249254088} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.041375906766740855, "f1": 0.5735449735449736, "f1_std": 0.042562346542897575, "bacc": 0.5735294117647058, "bacc_std": 0.04215186375591522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.000774263682681127, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.03921584060053084, "f1": 0.5639943741209563, "f1_std": 0.04406416342054804, "bacc": 0.5756302521008403, "bacc_std": 0.03993059411043034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04250206581255866, "f1": 0.5788211788211788, "f1_std": 0.04412446113420484, "bacc": 0.5793067226890757, "bacc_std": 0.043108657298479486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.000774263682681127, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043342272084279106, "f1": 0.5545730864879801, "f1_std": 0.04804572968899776, "bacc": 0.5625, "bacc_std": 0.0442178280702285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04336455824230737, "f1": 0.5810810810810811, "f1_std": 0.045710087061864864, "bacc": 0.5835084033613446, "bacc_std": 0.043959655317026385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.041036578566408834, "f1": 0.575109649122807, "f1_std": 0.044900539560058635, "bacc": 0.5803571428571428, "bacc_std": 0.04195895611711056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04223740876606413, "f1": 0.6092436974789917, "f1_std": 0.04240910725578033, "bacc": 0.6092436974789917, "bacc_std": 0.04222591134572192} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04382966212507142, "f1": 0.5454307410316837, "f1_std": 0.04430015898466531, "bacc": 0.5456932773109244, "bacc_std": 0.04450111302630659} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.000774263682681127, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.03560367970202885, "f1": 0.6056815772736909, "f1_std": 0.04079536875401219, "bacc": 0.615546218487395, "bacc_std": 0.03662179202146294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 21.54434690031882, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042718800799265974, "f1": 0.5778999738151349, "f1_std": 0.042986292099479996, "bacc": 0.5782563025210083, "bacc_std": 0.04294437153818764} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04549166028017473, "f1": 0.5352140461629513, "f1_std": 0.045870377298101894, "bacc": 0.5351890756302521, "bacc_std": 0.04566915474528348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04334846283282468, "f1": 0.5854473942969518, "f1_std": 0.043790071072607274, "bacc": 0.585609243697479, "bacc_std": 0.0437324542252678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.000774263682681127, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.03951517773706822, "f1": 0.5612903225806452, "f1_std": 0.04439937718859952, "bacc": 0.5698529411764706, "bacc_std": 0.0404807653547977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.000774263682681127, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.0449170353255306, "f1": 0.5573516535327002, "f1_std": 0.046820273380092994, "bacc": 0.5598739495798319, "bacc_std": 0.04541648872682065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 166.81005372000556, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043457883854309945, "f1": 0.5826018084614877, "f1_std": 0.04453456361628661, "bacc": 0.5824579831932774, "bacc_std": 0.04403509328010831} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04252337301839545, "f1": 0.5931704050887178, "f1_std": 0.04468840063737031, "bacc": 0.5940126050420168, "bacc_std": 0.04337411284593554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.042801407194815455, "f1": 0.5528846153846154, "f1_std": 0.0445449858119839, "bacc": 0.5540966386554622, "bacc_std": 0.0434637714805865} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04129252451286022, "f1": 0.5107482993197279, "f1_std": 0.04337257148296088, "bacc": 0.5168067226890757, "bacc_std": 0.04149394593657492} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.000774263682681127, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.0385530804269364, "f1": 0.6190346145968457, "f1_std": 0.042128043234822124, "bacc": 0.6218487394957983, "bacc_std": 0.03968019660724164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 21.54434690031882, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.044037055156391114, "f1": 0.6266038229903116, "f1_std": 0.04425508211186732, "bacc": 0.6271008403361344, "bacc_std": 0.044277488851512725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.000774263682681127, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.0398334037213635, "f1": 0.5978378378378378, "f1_std": 0.042371859254084425, "bacc": 0.5997899159663866, "bacc_std": 0.04059901611002986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04386356673815658, "f1": 0.5929621848739496, "f1_std": 0.044490973256672776, "bacc": 0.5929621848739496, "bacc_std": 0.044422961784538216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 166.81005372000556, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04278787549390596, "f1": 0.5752305665349143, "f1_std": 0.04335207687429001, "bacc": 0.5751050420168067, "bacc_std": 0.043033043925578184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 166.81005372000556, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.040535730182593294, "f1": 0.543354536324071, "f1_std": 0.04257794387192294, "bacc": 0.5451680672268907, "bacc_std": 0.04117415525774854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04734780645684353, "f1": 0.602745995423341, "f1_std": 0.04769065184807548, "bacc": 0.6034663865546219, "bacc_std": 0.04777276598510858} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04452667885743154, "f1": 0.5929621848739496, "f1_std": 0.04517006457034381, "bacc": 0.5929621848739496, "bacc_std": 0.04514634767027715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.044020440337800115, "f1": 0.5040336248389939, "f1_std": 0.04555446231087554, "bacc": 0.509453781512605, "bacc_std": 0.044059268836293054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.000774263682681127, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04106405683548232, "f1": 0.5478500171998624, "f1_std": 0.04498775148018315, "bacc": 0.5551470588235294, "bacc_std": 0.041788398751812075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043571711197166955, "f1": 0.5788923719958203, "f1_std": 0.043839083838471606, "bacc": 0.5798319327731092, "bacc_std": 0.04388669647108308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04265633546444118, "f1": 0.6092436974789917, "f1_std": 0.04316971950316128, "bacc": 0.6092436974789917, "bacc_std": 0.04293640465642508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 21.54434690031882, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.044411901710325066, "f1": 0.6179613241560145, "f1_std": 0.04480054752458687, "bacc": 0.618172268907563, "bacc_std": 0.044739154802597075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04432563261314689, "f1": 0.5788923719958203, "f1_std": 0.044515907203323726, "bacc": 0.5798319327731092, "bacc_std": 0.04468473659717821} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04198862637735642, "f1": 0.626380984265149, "f1_std": 0.043983826107817425, "bacc": 0.6265756302521008, "bacc_std": 0.04271422417022086} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.000774263682681127, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04626522585948701, "f1": 0.5528846153846154, "f1_std": 0.04818911287454669, "bacc": 0.5540966386554622, "bacc_std": 0.04701337794738415} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044953586308061066, "f1": 0.5929621848739496, "f1_std": 0.045713950851821596, "bacc": 0.5929621848739496, "bacc_std": 0.04570900429629719} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 10000.0, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04391208639937176, "f1": 0.5454307410316837, "f1_std": 0.04414174707395286, "bacc": 0.5456932773109244, "bacc_std": 0.0441262687153829} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04341759031548538, "f1": 0.5826018084614877, "f1_std": 0.0446515179723668, "bacc": 0.5824579831932774, "bacc_std": 0.044321436139511804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04095345191464679, "f1": 0.5337093741606231, "f1_std": 0.04240032462380671, "bacc": 0.5362394957983193, "bacc_std": 0.04124343095380982} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.043066630369751314, "f1": 0.6351748937561295, "f1_std": 0.04326330974279589, "bacc": 0.6360294117647058, "bacc_std": 0.04321221968962662} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04165500183578975, "f1": 0.5386659580122243, "f1_std": 0.04251723271154876, "bacc": 0.539390756302521, "bacc_std": 0.041881019503858544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04339022653299713, "f1": 0.5623043623043623, "f1_std": 0.044679292207003306, "bacc": 0.5630252100840336, "bacc_std": 0.04379020386845396} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.000774263682681127, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04408798317167255, "f1": 0.5613605442176871, "f1_std": 0.046140684042599876, "bacc": 0.5656512605042017, "bacc_std": 0.044359150221676226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 21.54434690031882, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04126512588062478, "f1": 0.5712833028269271, "f1_std": 0.04433508011310735, "bacc": 0.5745798319327731, "bacc_std": 0.042056626037086375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.042304210214505235, "f1": 0.6669352672575879, "f1_std": 0.04508697722794599, "bacc": 0.6664915966386555, "bacc_std": 0.04362538052304314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043620680734270105, "f1": 0.6097756946769334, "f1_std": 0.04561112327390135, "bacc": 0.6102941176470589, "bacc_std": 0.044476065820764146} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04441279205155623, "f1": 0.6119947848761408, "f1_std": 0.04446328157055765, "bacc": 0.6139705882352942, "bacc_std": 0.04458761535185911} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04453133213978223, "f1": 0.5498646953996436, "f1_std": 0.044976037125406085, "bacc": 0.5498949579831933, "bacc_std": 0.0446421998345085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 2.782559402207126, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.042999963700587264, "f1": 0.531517200238616, "f1_std": 0.044615301423886644, "bacc": 0.5320378151260504, "bacc_std": 0.04372396976748105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04447011120789863, "f1": 0.628161668839635, "f1_std": 0.044376468554319384, "bacc": 0.6302521008403361, "bacc_std": 0.0443212361699049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 166.81005372000556, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04248166648700364, "f1": 0.5529334644378892, "f1_std": 0.04288710029210345, "bacc": 0.553046218487395, "bacc_std": 0.04294487313266584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.000774263682681127, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.042668930348270455, "f1": 0.6169755573462261, "f1_std": 0.044707924252205176, "bacc": 0.6176470588235294, "bacc_std": 0.04331782261636747} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04610787920143035, "f1": 0.6167554415729598, "f1_std": 0.04701270587431229, "bacc": 0.6165966386554622, "bacc_std": 0.046841702506412425} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04221412083555494, "f1": 0.6210470369386127, "f1_std": 0.04349770023752278, "bacc": 0.6207983193277311, "bacc_std": 0.04285306069906153} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04591990719950595, "f1": 0.5841388834089565, "f1_std": 0.04658710622977248, "bacc": 0.5840336134453781, "bacc_std": 0.046380208422524966} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.000774263682681127, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.039348307231670314, "f1": 0.574718275355218, "f1_std": 0.044538868681577026, "bacc": 0.5845588235294117, "bacc_std": 0.0403837887594712} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04176191125954305, "f1": 0.5479551932126997, "f1_std": 0.04236626419146795, "bacc": 0.5483193277310925, "bacc_std": 0.041884946072517575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.000774263682681127, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.041704525291155946, "f1": 0.5581140350877193, "f1_std": 0.04567810868466739, "bacc": 0.5640756302521008, "bacc_std": 0.04262920222422063} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.000774263682681127, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.040313921650915706, "f1": 0.575109649122807, "f1_std": 0.04387450473932039, "bacc": 0.5803571428571428, "bacc_std": 0.04102089371018664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.040884761656294226, "f1": 0.5810810810810811, "f1_std": 0.04333494557102323, "bacc": 0.5835084033613446, "bacc_std": 0.04164021071216353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04350943299590779, "f1": 0.610369206598586, "f1_std": 0.04394723104831792, "bacc": 0.6108193277310925, "bacc_std": 0.04403938299881905} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04388134068546445, "f1": 0.6092436974789917, "f1_std": 0.04426940309364152, "bacc": 0.6092436974789917, "bacc_std": 0.04412279845625132} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.042874993742851225, "f1": 0.6590730557737627, "f1_std": 0.04307228407780876, "bacc": 0.6596638655462186, "bacc_std": 0.04303058077846806} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 140.94 | 1012.9 | 0.84734 | 0.12552 | 0.84128 | 0.13231 | 0.84109 | 0.13197 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 140.94 | 1012.9 | 0.59258 | 0.034852 | 0.58099 | 0.038097 | 0.58359 | 0.036525 | + + +done! total time: 0:05:55 diff --git a/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..780a88cab4988f392300e03b2683d3eb4f25f085 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (abide_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic +model: flat_mae +representation: reg +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..dfb5eafff7e8306bdf2c32858f00d2786773acc9 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,abide_dx,,0.005994842503189409,train,0.8162393162393162,0.013777337106104563,0.8126625223678359,0.014113014329836191,0.8106819226475803,0.014078812104786759 +flat_mae,reg,logistic,abide_dx,,0.005994842503189409,test,0.5806451612903226,0.0423222702339128,0.5694444444444444,0.043824866492476876,0.5713537575281487,0.04272984459974005 +flat_mae,reg,logistic,abide_dx,1,0.3593813663804626,train,0.99002849002849,0.003655983391639893,0.9899194830504128,0.003697126993599387,0.9897748246585456,0.0037668522314195547 +flat_mae,reg,logistic,abide_dx,1,0.3593813663804626,test,0.6129032258064516,0.04302262067445718,0.6125,0.04308666710504642,0.615546218487395,0.0430640372870933 +flat_mae,reg,logistic,abide_dx,2,0.046415888336127774,train,0.8931623931623932,0.011895876211746833,0.8913364277856779,0.012184851646170664,0.8892211148025102,0.012352805582943549 +flat_mae,reg,logistic,abide_dx,2,0.046415888336127774,test,0.5806451612903226,0.042884740135909115,0.5806451612903226,0.04304070703248366,0.5861344537815126,0.042764587609295635 +flat_mae,reg,logistic,abide_dx,3,0.046415888336127774,train,0.9017094017094017,0.011068517600946041,0.9001037363652675,0.01131815651086729,0.8981543004798819,0.011479401845866648 +flat_mae,reg,logistic,abide_dx,3,0.046415888336127774,test,0.6129032258064516,0.044117381974678495,0.6045708211533352,0.04549149727665772,0.6045168067226891,0.044784804126661554 +flat_mae,reg,logistic,abide_dx,4,0.005994842503189409,train,0.7977207977207977,0.01514013270466235,0.7933582089552238,0.015598299918118194,0.7911406423034331,0.015541913870848148 +flat_mae,reg,logistic,abide_dx,4,0.005994842503189409,test,0.6209677419354839,0.042872666778633654,0.6118548118548119,0.04420678731524125,0.6118697478991597,0.043412533133996026 +flat_mae,reg,logistic,abide_dx,5,0.046415888336127774,train,0.8974358974358975,0.011567310844489769,0.8959460460979767,0.01177059322089116,0.8945736434108527,0.011857510043439101 +flat_mae,reg,logistic,abide_dx,5,0.046415888336127774,test,0.5967741935483871,0.0418612867181886,0.5929621848739496,0.042517752034177646,0.5929621848739496,0.04245722637465348 +flat_mae,reg,logistic,abide_dx,6,0.046415888336127774,train,0.886039886039886,0.012026364222694746,0.884303513745138,0.012245865993981276,0.8827611664820967,0.012312151483214165 +flat_mae,reg,logistic,abide_dx,6,0.046415888336127774,test,0.6370967741935484,0.04127170384150949,0.626380984265149,0.042536629026512264,0.6265756302521008,0.04158219779200473 +flat_mae,reg,logistic,abide_dx,7,0.000774263682681127,train,0.7193732193732194,0.01646500246087066,0.7045978361867331,0.018172831704204886,0.7038390550018457,0.017233336357885883 +flat_mae,reg,logistic,abide_dx,7,0.000774263682681127,test,0.6048387096774194,0.04028571217713727,0.574718275355218,0.045812694956875934,0.5845588235294117,0.04131633299312512 +flat_mae,reg,logistic,abide_dx,8,0.3593813663804626,train,0.9772079772079773,0.00561568670852478,0.9769080846374618,0.005703723038470528,0.9757844222960502,0.005946440778338548 +flat_mae,reg,logistic,abide_dx,8,0.3593813663804626,test,0.5967741935483871,0.04206148564187509,0.5941345902068604,0.04231342099116469,0.5945378151260504,0.04223628625511693 +flat_mae,reg,logistic,abide_dx,9,0.005994842503189409,train,0.8076923076923077,0.015360225469999883,0.803627412179369,0.015837672402689892,0.8013658176448875,0.0158111121338831 +flat_mae,reg,logistic,abide_dx,9,0.005994842503189409,test,0.5887096774193549,0.04160938657308653,0.5765651155005022,0.04268610893507543,0.5777310924369747,0.041833556588198685 +flat_mae,reg,logistic,abide_dx,10,0.005994842503189409,train,0.8091168091168092,0.0149205287570987,0.8044893378226712,0.015539608618727786,0.8017718715393134,0.0155200726470247 +flat_mae,reg,logistic,abide_dx,10,0.005994842503189409,test,0.6451612903225806,0.043937861121797636,0.6418067226890756,0.04441502347280435,0.6418067226890756,0.04432888947668008 +flat_mae,reg,logistic,abide_dx,11,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,11,2.782559402207126,test,0.5887096774193549,0.04343932280628793,0.5826018084614877,0.04433749565180021,0.5824579831932774,0.04402226347314493 +flat_mae,reg,logistic,abide_dx,12,0.3593813663804626,train,0.9814814814814815,0.00534844800442507,0.9812900937545488,0.00540242728281851,0.9814322628276116,0.0054090124682498585 +flat_mae,reg,logistic,abide_dx,12,0.3593813663804626,test,0.5161290322580645,0.04390386278602168,0.5129615082482325,0.044174183552552586,0.5131302521008403,0.04423233565867662 +flat_mae,reg,logistic,abide_dx,13,0.046415888336127774,train,0.8931623931623932,0.012346469987080272,0.8916477161643497,0.012542422062499538,0.8904023624953858,0.012595496040525225 +flat_mae,reg,logistic,abide_dx,13,0.046415888336127774,test,0.6048387096774194,0.04438966081772879,0.6041951664386684,0.04437383028066331,0.6066176470588236,0.04439890154375602 +flat_mae,reg,logistic,abide_dx,14,0.3593813663804626,train,0.9914529914529915,0.003262345877709261,0.9913621262458472,0.00329649055849463,0.9913621262458472,0.0032913368368173842 +flat_mae,reg,logistic,abide_dx,14,0.3593813663804626,test,0.6048387096774194,0.043960590974109114,0.6035753898349319,0.04400106766929949,0.6050420168067226,0.04403133407234343 +flat_mae,reg,logistic,abide_dx,15,0.005994842503189409,train,0.8062678062678063,0.014609182969749258,0.8006348145673237,0.015363686389383591,0.7974160206718346,0.015263773875024512 +flat_mae,reg,logistic,abide_dx,15,0.005994842503189409,test,0.6532258064516129,0.039730635699814096,0.6526610644257702,0.039766138423536226,0.6554621848739496,0.0398270830796502 +flat_mae,reg,logistic,abide_dx,16,0.005994842503189409,train,0.8062678062678063,0.015155248094064842,0.8024172185430463,0.015572763825866946,0.8003691399040236,0.015546004546327041 +flat_mae,reg,logistic,abide_dx,16,0.005994842503189409,test,0.5806451612903226,0.03879320289755654,0.5581140350877193,0.04213117157077213,0.5640756302521008,0.03949008345253527 +flat_mae,reg,logistic,abide_dx,17,0.046415888336127774,train,0.9074074074074074,0.011327063147999566,0.9061580320950635,0.011514537645291686,0.905094130675526,0.0116491233183708 +flat_mae,reg,logistic,abide_dx,17,0.046415888336127774,test,0.6129032258064516,0.044949025933407306,0.6119947848761408,0.045094328383577416,0.6139705882352942,0.04525716203175383 +flat_mae,reg,logistic,abide_dx,18,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,18,166.81005372000556,test,0.5725806451612904,0.042900121158586914,0.5623043623043623,0.044323968930829065,0.5630252100840336,0.04335847781129747 +flat_mae,reg,logistic,abide_dx,19,0.005994842503189409,train,0.8062678062678063,0.01420386763971328,0.8010204081632653,0.014789522473802488,0.7980066445182724,0.014697404578343714 +flat_mae,reg,logistic,abide_dx,19,0.005994842503189409,test,0.6209677419354839,0.04328294249866049,0.6153389215233318,0.044105161532270364,0.6150210084033614,0.043838383793386705 +flat_mae,reg,logistic,abide_dx,20,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,20,2.782559402207126,test,0.5241935483870968,0.045225748930063286,0.5150792072645324,0.046107639264786775,0.5157563025210083,0.045554000234481945 +flat_mae,reg,logistic,abide_dx,21,0.005994842503189409,train,0.8190883190883191,0.014107429878017028,0.8149483476863874,0.014598468391674535,0.8122923588039868,0.014612067116840974 +flat_mae,reg,logistic,abide_dx,21,0.005994842503189409,test,0.6129032258064516,0.04505188071873942,0.6125,0.04521286897297581,0.615546218487395,0.04521116737625754 +flat_mae,reg,logistic,abide_dx,22,0.046415888336127774,train,0.8888888888888888,0.011465022879198225,0.8871149960829589,0.011724026433243707,0.8853451458102621,0.011880692990917607 +flat_mae,reg,logistic,abide_dx,22,0.046415888336127774,test,0.6048387096774194,0.04092897581658232,0.5907590759075907,0.0430340084514928,0.592436974789916,0.041520244590889585 +flat_mae,reg,logistic,abide_dx,23,0.005994842503189409,train,0.8091168091168092,0.01395807880973357,0.8046631005382417,0.01439144479087171,0.8020671834625323,0.014321994442026564 +flat_mae,reg,logistic,abide_dx,23,0.005994842503189409,test,0.5725806451612904,0.0428686830382255,0.5573516535327002,0.04491170217156621,0.5598739495798319,0.04341343794202899 +flat_mae,reg,logistic,abide_dx,24,0.005994842503189409,train,0.8005698005698005,0.01449126080220991,0.7959166722041331,0.015165341005698565,0.7934293097083795,0.015190247062943224 +flat_mae,reg,logistic,abide_dx,24,0.005994842503189409,test,0.6451612903225806,0.04087969965536183,0.6391534391534391,0.041795905441736135,0.6386554621848739,0.041498248203676535 +flat_mae,reg,logistic,abide_dx,25,0.046415888336127774,train,0.8988603988603988,0.011179395697370023,0.8974956965961465,0.01137600764514767,0.8964562569213732,0.0115325179483545 +flat_mae,reg,logistic,abide_dx,25,0.046415888336127774,test,0.5564516129032258,0.04263826441228081,0.5529334644378892,0.043010729355763534,0.553046218487395,0.04290706634341999 +flat_mae,reg,logistic,abide_dx,26,0.005994842503189409,train,0.8005698005698005,0.014772020978654222,0.7959166722041331,0.015274436845345424,0.7934293097083795,0.015199799550173766 +flat_mae,reg,logistic,abide_dx,26,0.005994842503189409,test,0.5806451612903226,0.04368924650466842,0.5694444444444444,0.04555551950846896,0.5703781512605042,0.04446724336882759 +flat_mae,reg,logistic,abide_dx,27,0.005994842503189409,train,0.811965811965812,0.01486197048083878,0.8074074074074074,0.015481735194276746,0.8046511627906976,0.015466784768395725 +flat_mae,reg,logistic,abide_dx,27,0.005994842503189409,test,0.6370967741935484,0.04168404458975978,0.626380984265149,0.0433349745376252,0.6265756302521008,0.04227477092333316 +flat_mae,reg,logistic,abide_dx,28,0.005994842503189409,train,0.7877492877492878,0.015199630723050256,0.7828921559470213,0.015624246272880412,0.7806201550387597,0.015501221973266272 +flat_mae,reg,logistic,abide_dx,28,0.005994842503189409,test,0.6612903225806451,0.04220056109721617,0.6502820306204673,0.04457058529396927,0.6502100840336134,0.04312623712672943 +flat_mae,reg,logistic,abide_dx,29,0.005994842503189409,train,0.8076923076923077,0.014202757552374873,0.8039491513151771,0.014635573076019868,0.8019564414913252,0.014656149646361034 +flat_mae,reg,logistic,abide_dx,29,0.005994842503189409,test,0.6693548387096774,0.04198856442108495,0.6595915634415801,0.04404721572849947,0.6591386554621849,0.04294610920499959 +flat_mae,reg,logistic,abide_dx,30,0.000774263682681127,train,0.698005698005698,0.01741704378874812,0.681891244870041,0.01897850248371357,0.6820967146548542,0.018005857867737597 +flat_mae,reg,logistic,abide_dx,30,0.000774263682681127,test,0.5564516129032258,0.04230599042952057,0.5343756400628115,0.04548069640892707,0.5404411764705883,0.04289293801952597 +flat_mae,reg,logistic,abide_dx,31,0.005994842503189409,train,0.8247863247863247,0.014201795120726769,0.8209313659411649,0.01469480001261378,0.8183462532299741,0.014731093490876932 +flat_mae,reg,logistic,abide_dx,31,0.005994842503189409,test,0.6048387096774194,0.04296907389197765,0.5931704050887178,0.045058357262803786,0.5940126050420168,0.04379618098676921 +flat_mae,reg,logistic,abide_dx,32,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,32,2.782559402207126,test,0.5483870967741935,0.04434968885059558,0.5479166666666666,0.04446141921597849,0.5504201680672269,0.04461821459023731 +flat_mae,reg,logistic,abide_dx,33,0.005994842503189409,train,0.8005698005698005,0.014726472026124074,0.7960945085769771,0.015167116034931481,0.7937246216315983,0.015088116342821907 +flat_mae,reg,logistic,abide_dx,33,0.005994842503189409,test,0.5967741935483871,0.042092939511416384,0.5860042735042735,0.04365335817085198,0.5866596638655462,0.04271377486357096 +flat_mae,reg,logistic,abide_dx,34,0.000774263682681127,train,0.707977207977208,0.01568016110805546,0.6926018092298492,0.016999954933741377,0.6923218899963086,0.016155705857062618 +flat_mae,reg,logistic,abide_dx,34,0.000774263682681127,test,0.5967741935483871,0.040166960993620854,0.5639943741209563,0.045382662437967,0.5756302521008403,0.040975089721394936 +flat_mae,reg,logistic,abide_dx,35,0.000774263682681127,train,0.7293447293447294,0.01627238972258054,0.7152847152847153,0.017791439338212808,0.7140642303433001,0.01693694542226742 +flat_mae,reg,logistic,abide_dx,35,0.000774263682681127,test,0.5887096774193549,0.04239652274041667,0.5826018084614877,0.042925312185141125,0.5824579831932774,0.04273381108732241 +flat_mae,reg,logistic,abide_dx,36,0.3593813663804626,train,0.9914529914529915,0.0036095089642537116,0.9913621262458472,0.0036473956014551148,0.9913621262458472,0.0036438122386457735 +flat_mae,reg,logistic,abide_dx,36,0.3593813663804626,test,0.5725806451612904,0.0457373257379656,0.5662332519305657,0.046666879224178316,0.5661764705882353,0.04628617344892488 +flat_mae,reg,logistic,abide_dx,37,0.000774263682681127,train,0.7008547008547008,0.016077369884026593,0.6822187349106712,0.018076487694755363,0.6832041343669251,0.01683891466157984 +flat_mae,reg,logistic,abide_dx,37,0.000774263682681127,test,0.6451612903225806,0.0397776435465781,0.6163150492264415,0.04598212853974836,0.6244747899159664,0.041214430215073726 +flat_mae,reg,logistic,abide_dx,38,0.046415888336127774,train,0.8874643874643875,0.011274723511673777,0.8854540384794126,0.011549252664534165,0.8831672203765227,0.01167960543656152 +flat_mae,reg,logistic,abide_dx,38,0.046415888336127774,test,0.6774193548387096,0.04056549732668247,0.671957671957672,0.041553221558509545,0.671218487394958,0.04123682171538047 +flat_mae,reg,logistic,abide_dx,39,0.046415888336127774,train,0.8945868945868946,0.01158540764404302,0.892825311942959,0.011873587613073618,0.8908084163898118,0.012080256067409974 +flat_mae,reg,logistic,abide_dx,39,0.046415888336127774,test,0.5564516129032258,0.04164163799093594,0.5529334644378892,0.04188418939078813,0.553046218487395,0.0419382787703537 +flat_mae,reg,logistic,abide_dx,40,0.046415888336127774,train,0.896011396011396,0.011221753164857367,0.8939873188593179,0.011557684679607737,0.8912144702842377,0.011759127854871453 +flat_mae,reg,logistic,abide_dx,40,0.046415888336127774,test,0.5806451612903226,0.04364051187595083,0.5735449735449736,0.044505960363405886,0.5735294117647058,0.04413228362399165 +flat_mae,reg,logistic,abide_dx,41,0.005994842503189409,train,0.8034188034188035,0.013800603619203801,0.7984705764878179,0.014331912388759855,0.7957179771133259,0.014270592785169286 +flat_mae,reg,logistic,abide_dx,41,0.005994842503189409,test,0.6290322580645161,0.039670006519707965,0.6145945945945945,0.04291624141774532,0.6160714285714286,0.040926654186235895 +flat_mae,reg,logistic,abide_dx,42,0.005994842503189409,train,0.7962962962962963,0.01461613433374749,0.7918145148746876,0.015165101207406887,0.7895533407161315,0.015159538018108865 +flat_mae,reg,logistic,abide_dx,42,0.005994842503189409,test,0.6209677419354839,0.041428121873890424,0.6118548118548119,0.04348886153441063,0.6118697478991597,0.042461167910363994 +flat_mae,reg,logistic,abide_dx,43,0.005994842503189409,train,0.7877492877492878,0.014970880792198679,0.7818962047962901,0.01565877592029476,0.7791435954226652,0.015527427532777102 +flat_mae,reg,logistic,abide_dx,43,0.005994842503189409,test,0.6370967741935484,0.04204503061451673,0.6301451580831179,0.04322589035904723,0.6297268907563025,0.042767793289440546 +flat_mae,reg,logistic,abide_dx,44,0.005994842503189409,train,0.8219373219373219,0.01518462900474373,0.8190285079080932,0.015511617260381763,0.8175341454411222,0.015555970754619041 +flat_mae,reg,logistic,abide_dx,44,0.005994842503189409,test,0.6129032258064516,0.04339758837053934,0.6003223207091055,0.04543233482994681,0.6013655462184874,0.043999294468984936 +flat_mae,reg,logistic,abide_dx,45,0.000774263682681127,train,0.717948717948718,0.01621419033884865,0.7028984268125855,0.01771470612112643,0.7022517534145442,0.016817766597889312 +flat_mae,reg,logistic,abide_dx,45,0.000774263682681127,test,0.5645161290322581,0.03964992490869749,0.5334448160535117,0.04336624974835806,0.5446428571428572,0.040068125771453515 +flat_mae,reg,logistic,abide_dx,46,0.000774263682681127,train,0.7037037037037037,0.016426786892233685,0.688723650999386,0.0177993235690101,0.6884459210040605,0.01695806600292581 +flat_mae,reg,logistic,abide_dx,46,0.000774263682681127,test,0.5887096774193549,0.04369420033093446,0.5765651155005022,0.04527750456037661,0.5777310924369747,0.04416791018070244 +flat_mae,reg,logistic,abide_dx,47,0.3593813663804626,train,0.9829059829059829,0.004971060967977018,0.982703253201048,0.005038970615578752,0.9821336286452566,0.0052369927485725 +flat_mae,reg,logistic,abide_dx,47,0.3593813663804626,test,0.5483870967741935,0.04640643804684464,0.5441176470588236,0.046875613611318416,0.5441176470588236,0.04683560282102705 +flat_mae,reg,logistic,abide_dx,48,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,48,1291.5496650148827,test,0.5645161290322581,0.044404309654817474,0.5588932806324111,0.04486859276954172,0.5588235294117647,0.04469156616079761 +flat_mae,reg,logistic,abide_dx,49,0.046415888336127774,train,0.8931623931623932,0.011484132232731144,0.8913364277856779,0.011751865726472334,0.8892211148025102,0.01190255146149509 +flat_mae,reg,logistic,abide_dx,49,0.046415888336127774,test,0.5645161290322581,0.04262293537741512,0.5588932806324111,0.04318492466789194,0.5588235294117647,0.04291989724769259 +flat_mae,reg,logistic,abide_dx,50,0.046415888336127774,train,0.9045584045584045,0.011050459048816404,0.9030696466660484,0.01129354632089327,0.901328903654485,0.011476251753322187 +flat_mae,reg,logistic,abide_dx,50,0.046415888336127774,test,0.5564516129032258,0.043629923668670655,0.5457875457875458,0.044936815637702895,0.5467436974789917,0.044128061045797216 +flat_mae,reg,logistic,abide_dx,51,0.000774263682681127,train,0.7193732193732194,0.015883057758822743,0.7057593249404791,0.01723085237118964,0.7047249907715024,0.016471626720471297 +flat_mae,reg,logistic,abide_dx,51,0.000774263682681127,test,0.5806451612903226,0.038960544624799316,0.5507246376811594,0.044278558784575504,0.5609243697478992,0.03994609393487123 +flat_mae,reg,logistic,abide_dx,52,0.000774263682681127,train,0.707977207977208,0.016824387047170278,0.6913359142921488,0.01859903451174634,0.6914359542266519,0.01752164477258432 +flat_mae,reg,logistic,abide_dx,52,0.000774263682681127,test,0.6451612903225806,0.039450158889672356,0.6260964912280702,0.04233582178360562,0.6292016806722689,0.040206181415309475 +flat_mae,reg,logistic,abide_dx,53,0.005994842503189409,train,0.8148148148148148,0.014594965270874253,0.8097989195678271,0.01524841852753817,0.8066445182724252,0.015177190884385221 +flat_mae,reg,logistic,abide_dx,53,0.005994842503189409,test,0.6612903225806451,0.04194638816046785,0.6539994685091681,0.04328705686531138,0.6533613445378151,0.042652639138988764 +flat_mae,reg,logistic,abide_dx,54,0.046415888336127774,train,0.9031339031339032,0.01120960472933822,0.9017268213147558,0.011421267140008686,0.9003322259136213,0.011586604650665645 +flat_mae,reg,logistic,abide_dx,54,0.046415888336127774,test,0.6290322580645161,0.04178843946903286,0.6119727891156463,0.04535214254835566,0.6144957983193278,0.042869480995037054 +flat_mae,reg,logistic,abide_dx,55,0.046415888336127774,train,0.8874643874643875,0.012143415035040227,0.8856260169979149,0.012417113254746266,0.8837578442229606,0.012574911608305652 +flat_mae,reg,logistic,abide_dx,55,0.046415888336127774,test,0.5967741935483871,0.044592372763027945,0.5941345902068604,0.045075824434152756,0.5945378151260504,0.04501262557143645 +flat_mae,reg,logistic,abide_dx,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,56,21.54434690031882,test,0.5483870967741935,0.04447535240899466,0.5454307410316837,0.04490186155154641,0.5456932773109244,0.044849693009637794 +flat_mae,reg,logistic,abide_dx,57,0.046415888336127774,train,0.8945868945868946,0.01105224526458731,0.8929807502142528,0.011260699957450682,0.8913990402362495,0.01134258959634281 +flat_mae,reg,logistic,abide_dx,57,0.046415888336127774,test,0.6532258064516129,0.0399115143815532,0.6532032520325204,0.039928502460482414,0.6586134453781513,0.0397262024501651 +flat_mae,reg,logistic,abide_dx,58,0.005994842503189409,train,0.7834757834757835,0.01583630477081844,0.778423815535916,0.016354165684195197,0.7761535622000739,0.01623998225263659 +flat_mae,reg,logistic,abide_dx,58,0.005994842503189409,test,0.6370967741935484,0.04269923308120655,0.6301451580831179,0.04413383827708482,0.6297268907563025,0.04358112134192595 +flat_mae,reg,logistic,abide_dx,59,0.000774263682681127,train,0.6965811965811965,0.016151505480690706,0.6818616051386905,0.01757407083399517,0.6816906607604282,0.01672939334314424 +flat_mae,reg,logistic,abide_dx,59,0.000774263682681127,test,0.5645161290322581,0.04264746406842055,0.5503626107977437,0.04479231208794805,0.5525210084033614,0.043257866134231736 +flat_mae,reg,logistic,abide_dx,60,0.005994842503189409,train,0.8176638176638177,0.01444187027867114,0.8132435465768799,0.014998775488976991,0.8104097452934662,0.014998262048423933 +flat_mae,reg,logistic,abide_dx,60,0.005994842503189409,test,0.6209677419354839,0.04189966211968798,0.6153389215233318,0.04270476975734656,0.6150210084033614,0.0424407550421291 +flat_mae,reg,logistic,abide_dx,61,0.005994842503189409,train,0.8076923076923077,0.013660037578672972,0.803790038571189,0.014124874142025992,0.8016611295681063,0.01418204517215075 +flat_mae,reg,logistic,abide_dx,61,0.005994842503189409,test,0.5887096774193549,0.041798345863939386,0.5765651155005022,0.04366052135753652,0.5777310924369747,0.04245806822473076 +flat_mae,reg,logistic,abide_dx,62,0.000774263682681127,train,0.7136752136752137,0.01599868984132727,0.698192388395865,0.017651627844082418,0.6977851605758583,0.01669021437822466 +flat_mae,reg,logistic,abide_dx,62,0.000774263682681127,test,0.5645161290322581,0.04226367852391139,0.5475675675675675,0.04458494417553687,0.5509453781512605,0.04287193243536125 +flat_mae,reg,logistic,abide_dx,63,0.046415888336127774,train,0.8988603988603988,0.011257207026021345,0.8973555281426915,0.011479240293656497,0.8958656330749355,0.011613122628120169 +flat_mae,reg,logistic,abide_dx,63,0.046415888336127774,test,0.5806451612903226,0.04504765657793279,0.5802083333333333,0.04519930666156543,0.5829831932773109,0.04533171449081369 +flat_mae,reg,logistic,abide_dx,64,0.046415888336127774,train,0.9074074074074074,0.01112403368628157,0.9057533227995167,0.011450087028665873,0.9033222591362127,0.01177644220001862 +flat_mae,reg,logistic,abide_dx,64,0.046415888336127774,test,0.6290322580645161,0.042283100192803645,0.628935727296383,0.042463211224020005,0.6334033613445378,0.042641520162343245 +flat_mae,reg,logistic,abide_dx,65,0.005994842503189409,train,0.8091168091168092,0.015579227055498891,0.8057810628897055,0.015952259034882968,0.8041343669250646,0.015953280901442556 +flat_mae,reg,logistic,abide_dx,65,0.005994842503189409,test,0.5887096774193549,0.041167673182930395,0.5531057875768497,0.046343201475746235,0.5667016806722689,0.04186633269527928 +flat_mae,reg,logistic,abide_dx,66,0.005994842503189409,train,0.8048433048433048,0.014114868729142162,0.8005495701946308,0.014561330311064059,0.7981912144702843,0.014507100856772872 +flat_mae,reg,logistic,abide_dx,66,0.005994842503189409,test,0.6532258064516129,0.04221025059085491,0.6465831510572015,0.04318970432608874,0.6460084033613445,0.042655330196664724 +flat_mae,reg,logistic,abide_dx,67,0.005994842503189409,train,0.8091168091168092,0.015280755260102334,0.8048333153522494,0.015797233334252855,0.8023624953857512,0.015759802701135438 +flat_mae,reg,logistic,abide_dx,67,0.005994842503189409,test,0.5967741935483871,0.04204438712924569,0.5880946053680574,0.04323235449533133,0.5882352941176471,0.042438599322013174 +flat_mae,reg,logistic,abide_dx,68,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,68,166.81005372000556,test,0.6129032258064516,0.04451970532619128,0.6112852664576802,0.044556319240835154,0.6123949579831933,0.04468695148125871 +flat_mae,reg,logistic,abide_dx,69,0.005994842503189409,train,0.7934472934472935,0.014864427938149048,0.7895940088346125,0.01527851780315188,0.7878552971576227,0.015280432914944785 +flat_mae,reg,logistic,abide_dx,69,0.005994842503189409,test,0.6290322580645161,0.04201295573429387,0.6210470369386127,0.043544948358370854,0.6207983193277311,0.04278592403656117 +flat_mae,reg,logistic,abide_dx,70,0.005994842503189409,train,0.8105413105413105,0.015626236787603057,0.8065366357026376,0.016189489415888086,0.8042451088962717,0.016235992565182048 +flat_mae,reg,logistic,abide_dx,70,0.005994842503189409,test,0.5564516129032258,0.043160024572789925,0.5406479423452549,0.045414341785707635,0.54359243697479,0.043772828072901844 +flat_mae,reg,logistic,abide_dx,71,0.005994842503189409,train,0.8005698005698005,0.015422095055498946,0.7955498602050326,0.016032849876800623,0.7928386858619416,0.01595020572464615 +flat_mae,reg,logistic,abide_dx,71,0.005994842503189409,test,0.6451612903225806,0.04200445940351425,0.6336287939833467,0.0443408175499767,0.6339285714285714,0.042950004437164624 +flat_mae,reg,logistic,abide_dx,72,0.000774263682681127,train,0.7222222222222222,0.01578834276530049,0.7094833349250311,0.017206232205589374,0.7081949058693244,0.01647775470543224 +flat_mae,reg,logistic,abide_dx,72,0.000774263682681127,test,0.5887096774193549,0.043253105847472426,0.5788211788211788,0.04478776407150276,0.5793067226890757,0.043799617570984016 +flat_mae,reg,logistic,abide_dx,73,0.046415888336127774,train,0.9017094017094017,0.010806671526390825,0.9003831417624522,0.010965840785096359,0.8993355481727574,0.011011660105524543 +flat_mae,reg,logistic,abide_dx,73,0.046415888336127774,test,0.5967741935483871,0.046385189964846765,0.5915678524374176,0.04724491484739426,0.5913865546218487,0.04701819434339493 +flat_mae,reg,logistic,abide_dx,74,0.046415888336127774,train,0.8817663817663818,0.012209769255485442,0.8797456467494835,0.012483928268390936,0.8777039497969731,0.012567649153583346 +flat_mae,reg,logistic,abide_dx,74,0.046415888336127774,test,0.6370967741935484,0.04343204291438478,0.6301451580831179,0.04440772892799085,0.6297268907563025,0.043920379999762 +flat_mae,reg,logistic,abide_dx,75,0.046415888336127774,train,0.8974358974358975,0.010995947485921365,0.8958731623706242,0.011195430902272518,0.8942783314876339,0.011266729424653748 +flat_mae,reg,logistic,abide_dx,75,0.046415888336127774,test,0.6532258064516129,0.039530448360151835,0.6513893429225237,0.03961386463627362,0.6523109243697479,0.03961920158945896 +flat_mae,reg,logistic,abide_dx,76,0.005994842503189409,train,0.8076923076923077,0.015610096873185129,0.8031182806868111,0.016178753668990277,0.8004798818752307,0.01612565022337279 +flat_mae,reg,logistic,abide_dx,76,0.005994842503189409,test,0.5564516129032258,0.0452628207787486,0.543354536324071,0.04658306281940136,0.5451680672268907,0.04543985158880487 +flat_mae,reg,logistic,abide_dx,77,0.000774263682681127,train,0.717948717948718,0.015678467010705507,0.7024939854966995,0.017025703413662458,0.7019564414913252,0.016194679163568728 +flat_mae,reg,logistic,abide_dx,77,0.000774263682681127,test,0.5967741935483871,0.04000159661225607,0.5860042735042735,0.04167298278680317,0.5866596638655462,0.040618495076545906 +flat_mae,reg,logistic,abide_dx,78,0.005994842503189409,train,0.8190883190883191,0.014384843912440375,0.8154172955447481,0.014749638616689327,0.8131782945736434,0.014711129150163278 +flat_mae,reg,logistic,abide_dx,78,0.005994842503189409,test,0.5645161290322581,0.04176223206505073,0.5528846153846154,0.043161328751855625,0.5540966386554622,0.04213745153087503 +flat_mae,reg,logistic,abide_dx,79,0.005994842503189409,train,0.8034188034188035,0.013954148385229521,0.7990074441687345,0.014448658179898115,0.7966039128829827,0.014436451372999535 +flat_mae,reg,logistic,abide_dx,79,0.005994842503189409,test,0.5725806451612904,0.03958809772886041,0.5400013998740113,0.04375653815584479,0.5519957983193278,0.040161893061669944 +flat_mae,reg,logistic,abide_dx,80,0.005994842503189409,train,0.8148148148148148,0.013628975427133755,0.8106591865357644,0.014139905241237496,0.8081210778885197,0.014156175001720877 +flat_mae,reg,logistic,abide_dx,80,0.005994842503189409,test,0.6048387096774194,0.04439558245969393,0.5972691721349506,0.04536225940673821,0.5971638655462186,0.04478135432227121 +flat_mae,reg,logistic,abide_dx,81,0.000774263682681127,train,0.6994301994301995,0.016365190176635753,0.6836047890121861,0.017885884959426626,0.6836840162421558,0.016974391550529586 +flat_mae,reg,logistic,abide_dx,81,0.000774263682681127,test,0.5725806451612904,0.04275797325406112,0.5478500171998624,0.04693292921711341,0.5551470588235294,0.04363521875581149 +flat_mae,reg,logistic,abide_dx,82,0.000774263682681127,train,0.7022792022792023,0.015667029069729662,0.6839629245890622,0.017454372701848384,0.6847914359542266,0.016321419480746183 +flat_mae,reg,logistic,abide_dx,82,0.000774263682681127,test,0.6290322580645161,0.041312670363585054,0.6025641025641026,0.04628101130895942,0.6097689075630253,0.04227879209055774 +flat_mae,reg,logistic,abide_dx,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,83,166.81005372000556,test,0.5887096774193549,0.04751014733607908,0.5808311791608669,0.048995184517542555,0.5808823529411764,0.0483023725618578 +flat_mae,reg,logistic,abide_dx,84,0.005994842503189409,train,0.7905982905982906,0.015386883867786668,0.7856176834145278,0.01584005075314498,0.7832041343669252,0.01571679795336355 +flat_mae,reg,logistic,abide_dx,84,0.005994842503189409,test,0.6290322580645161,0.04104917928128421,0.6255252100840336,0.041882476316361966,0.6255252100840336,0.041910542238547996 +flat_mae,reg,logistic,abide_dx,85,0.005994842503189409,train,0.8162393162393162,0.01493676522211846,0.8123550827491748,0.015441262124749413,0.8100036913990403,0.015485912626791698 +flat_mae,reg,logistic,abide_dx,85,0.005994842503189409,test,0.5725806451612904,0.04121103779081578,0.5573516535327002,0.04295165107264002,0.5598739495798319,0.0414500830908768 +flat_mae,reg,logistic,abide_dx,86,0.046415888336127774,train,0.9017094017094017,0.011030931024806194,0.9001037363652675,0.011300834236207037,0.8981543004798819,0.011498505186374788 +flat_mae,reg,logistic,abide_dx,86,0.046415888336127774,test,0.5645161290322581,0.04481182763447311,0.5588932806324111,0.045603071821110945,0.5588235294117647,0.04543437483090676 +flat_mae,reg,logistic,abide_dx,87,0.000774263682681127,train,0.7037037037037037,0.01565658725918609,0.687468429208654,0.017312854802106526,0.6875599852344039,0.016325292344876955 +flat_mae,reg,logistic,abide_dx,87,0.000774263682681127,test,0.6290322580645161,0.04209221332356599,0.6191239316239316,0.04354692959468902,0.6192226890756303,0.042622159649891245 +flat_mae,reg,logistic,abide_dx,88,0.005994842503189409,train,0.8005698005698005,0.014718477864114878,0.7964391347213362,0.015122382018339675,0.7943152454780362,0.015071952466359385 +flat_mae,reg,logistic,abide_dx,88,0.005994842503189409,test,0.5241935483870968,0.046712695945952655,0.5150792072645324,0.047764210192027916,0.5157563025210083,0.04711505225800366 +flat_mae,reg,logistic,abide_dx,89,0.005994842503189409,train,0.8062678062678063,0.01463175970755651,0.8013912927706031,0.015215304242743926,0.7985972683647102,0.015140994962932726 +flat_mae,reg,logistic,abide_dx,89,0.005994842503189409,test,0.5887096774193549,0.04469497442457861,0.5854473942969518,0.044823118585106334,0.585609243697479,0.04464532048319953 +flat_mae,reg,logistic,abide_dx,90,0.000774263682681127,train,0.707977207977208,0.0168202493435923,0.6926018092298492,0.018402084731048575,0.6923218899963086,0.0174691185910971 +flat_mae,reg,logistic,abide_dx,90,0.000774263682681127,test,0.6129032258064516,0.041830252583716025,0.5852842809364549,0.047321329570710606,0.5934873949579832,0.04299667437909458 +flat_mae,reg,logistic,abide_dx,91,0.000774263682681127,train,0.7051282051282052,0.015938050978133528,0.6887571404398961,0.01738078601204251,0.6888519748984865,0.016454846063990794 +flat_mae,reg,logistic,abide_dx,91,0.000774263682681127,test,0.6532258064516129,0.04115872109991569,0.6408702094699266,0.043415734948990724,0.641281512605042,0.042054785605975836 +flat_mae,reg,logistic,abide_dx,92,0.005994842503189409,train,0.801994301994302,0.01502748163668397,0.7969168524172552,0.015633659925539438,0.7941306755260243,0.01554567610188909 +flat_mae,reg,logistic,abide_dx,92,0.005994842503189409,test,0.5725806451612904,0.04433364889739793,0.5691904293674206,0.04460476459264572,0.569327731092437,0.04465407792747012 +flat_mae,reg,logistic,abide_dx,93,0.005994842503189409,train,0.8062678062678063,0.014588600271980655,0.8022551594435837,0.015013411874118072,0.8000738279808047,0.014992632625533832 +flat_mae,reg,logistic,abide_dx,93,0.005994842503189409,test,0.5806451612903226,0.0430943445084854,0.5716183895827798,0.044477785561764835,0.571953781512605,0.04374033991024301 +flat_mae,reg,logistic,abide_dx,94,0.046415888336127774,train,0.8945868945868946,0.011567477497762274,0.892903970642807,0.011825439916285634,0.8911037283130306,0.011991634357556567 +flat_mae,reg,logistic,abide_dx,94,0.046415888336127774,test,0.5483870967741935,0.0428446453087631,0.5337093741606231,0.04432221906985984,0.5362394957983193,0.04303151597686858 +flat_mae,reg,logistic,abide_dx,95,0.005994842503189409,train,0.8005698005698005,0.01471712697331963,0.7964391347213362,0.015126678159127945,0.7943152454780362,0.015075668549243144 +flat_mae,reg,logistic,abide_dx,95,0.005994842503189409,test,0.5967741935483871,0.041824406240090345,0.5810810810810811,0.044522771362656276,0.5835084033613446,0.04260002553785869 +flat_mae,reg,logistic,abide_dx,96,0.005994842503189409,train,0.8048433048433048,0.014836111145133815,0.7998389120947047,0.015430010791954123,0.7970099667774087,0.015343974037146501 +flat_mae,reg,logistic,abide_dx,96,0.005994842503189409,test,0.6209677419354839,0.04558406660217663,0.6118548118548119,0.046964519351131155,0.6118697478991597,0.046028708670592555 +flat_mae,reg,logistic,abide_dx,97,0.000774263682681127,train,0.7022792022792023,0.01679993568376319,0.6861801451479392,0.01828737052418471,0.6862679955703211,0.017338191334929778 +flat_mae,reg,logistic,abide_dx,97,0.000774263682681127,test,0.6370967741935484,0.03747619431690826,0.6129032258064516,0.041952976161021976,0.6186974789915967,0.03851691529383629 +flat_mae,reg,logistic,abide_dx,98,0.046415888336127774,train,0.886039886039886,0.0121544618861692,0.8846153846153846,0.012307029226480947,0.8839424141749723,0.012311283972584373 +flat_mae,reg,logistic,abide_dx,98,0.046415888336127774,test,0.6612903225806451,0.044981355254143686,0.6604954367666231,0.04501709585655694,0.6628151260504203,0.045244331977391736 +flat_mae,reg,logistic,abide_dx,99,0.046415888336127774,train,0.8945868945868946,0.011682068944132465,0.8930556584895872,0.011896939936770523,0.8916943521594685,0.012011875545688423 +flat_mae,reg,logistic,abide_dx,99,0.046415888336127774,test,0.5967741935483871,0.04427898499250746,0.5941345902068604,0.04458463843668474,0.5945378151260504,0.044557964897986795 +flat_mae,reg,logistic,abide_dx,100,0.005994842503189409,train,0.8048433048433048,0.014411357836149122,0.800377351441221,0.01489293867694488,0.7978959025470653,0.014864832120504797 +flat_mae,reg,logistic,abide_dx,100,0.005994842503189409,test,0.6129032258064516,0.04618960606713198,0.610369206598586,0.04647705815015329,0.6108193277310925,0.046406912166710036 diff --git a/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..782f75b692da3269e3e1c704e28c8fda20baf6c6 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:18:00 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (abide_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic +model: flat_mae +representation: reg +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/abide_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:19:02 time: 3.9534 data: 3.3025 max mem: 2698 +extract (train) [ 20/289] eta: 0:01:39 time: 0.1895 data: 0.0637 max mem: 3005 +extract (train) [ 40/289] eta: 0:01:05 time: 0.1525 data: 0.0466 max mem: 3005 +extract (train) [ 60/289] eta: 0:00:52 time: 0.1543 data: 0.0461 max mem: 3005 +extract (train) [ 80/289] eta: 0:00:44 time: 0.1644 data: 0.0532 max mem: 3005 +extract (train) [100/289] eta: 0:00:37 time: 0.1560 data: 0.0485 max mem: 3005 +extract (train) [120/289] eta: 0:00:32 time: 0.1551 data: 0.0476 max mem: 3005 +extract (train) [140/289] eta: 0:00:27 time: 0.1544 data: 0.0460 max mem: 3005 +extract (train) [160/289] eta: 0:00:23 time: 0.1642 data: 0.0536 max mem: 3005 +extract (train) [180/289] eta: 0:00:19 time: 0.1723 data: 0.0550 max mem: 3005 +extract (train) [200/289] eta: 0:00:16 time: 0.1668 data: 0.0534 max mem: 3005 +extract (train) [220/289] eta: 0:00:12 time: 0.1661 data: 0.0537 max mem: 3005 +extract (train) [240/289] eta: 0:00:08 time: 0.1657 data: 0.0553 max mem: 3005 +extract (train) [260/289] eta: 0:00:05 time: 0.1625 data: 0.0531 max mem: 3005 +extract (train) [280/289] eta: 0:00:01 time: 0.1548 data: 0.0476 max mem: 3005 +extract (train) [288/289] eta: 0:00:00 time: 0.1556 data: 0.0487 max mem: 3005 +extract (train) Total time: 0:00:51 (0.1771 s / it) +extract (validation) [ 0/62] eta: 0:03:44 time: 3.6149 data: 3.4672 max mem: 3005 +extract (validation) [20/62] eta: 0:00:15 time: 0.2009 data: 0.0704 max mem: 3005 +extract (validation) [40/62] eta: 0:00:05 time: 0.1581 data: 0.0497 max mem: 3005 +extract (validation) [60/62] eta: 0:00:00 time: 0.1551 data: 0.0505 max mem: 3005 +extract (validation) [61/62] eta: 0:00:00 time: 0.1550 data: 0.0505 max mem: 3005 +extract (validation) Total time: 0:00:14 (0.2317 s / it) +extract (test) [ 0/62] eta: 0:03:53 time: 3.7728 data: 3.5997 max mem: 3005 +extract (test) [20/62] eta: 0:00:15 time: 0.2034 data: 0.0694 max mem: 3005 +extract (test) [40/62] eta: 0:00:05 time: 0.1635 data: 0.0509 max mem: 3005 +extract (test) [60/62] eta: 0:00:00 time: 0.1545 data: 0.0476 max mem: 3005 +extract (test) [61/62] eta: 0:00:00 time: 0.1542 data: 0.0474 max mem: 3005 +extract (test) Total time: 0:00:14 (0.2370 s / it) +feature extraction time: 0:01:20 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | abide_dx | | 0.0059948 | train | 0.81624 | 0.013777 | 0.81266 | 0.014113 | 0.81068 | 0.014079 | +| flat_mae | reg | logistic | abide_dx | | 0.0059948 | test | 0.58065 | 0.042322 | 0.56944 | 0.043825 | 0.57135 | 0.04273 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04302262067445718, "f1": 0.6125, "f1_std": 0.04308666710504642, "bacc": 0.615546218487395, "bacc_std": 0.0430640372870933} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042884740135909115, "f1": 0.5806451612903226, "f1_std": 0.04304070703248366, "bacc": 0.5861344537815126, "bacc_std": 0.042764587609295635} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.044117381974678495, "f1": 0.6045708211533352, "f1_std": 0.04549149727665772, "bacc": 0.6045168067226891, "bacc_std": 0.044784804126661554} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042872666778633654, "f1": 0.6118548118548119, "f1_std": 0.04420678731524125, "bacc": 0.6118697478991597, "bacc_std": 0.043412533133996026} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0418612867181886, "f1": 0.5929621848739496, "f1_std": 0.042517752034177646, "bacc": 0.5929621848739496, "bacc_std": 0.04245722637465348} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04127170384150949, "f1": 0.626380984265149, "f1_std": 0.042536629026512264, "bacc": 0.6265756302521008, "bacc_std": 0.04158219779200473} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.000774263682681127, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04028571217713727, "f1": 0.574718275355218, "f1_std": 0.045812694956875934, "bacc": 0.5845588235294117, "bacc_std": 0.04131633299312512} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04206148564187509, "f1": 0.5941345902068604, "f1_std": 0.04231342099116469, "bacc": 0.5945378151260504, "bacc_std": 0.04223628625511693} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04160938657308653, "f1": 0.5765651155005022, "f1_std": 0.04268610893507543, "bacc": 0.5777310924369747, "bacc_std": 0.041833556588198685} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.043937861121797636, "f1": 0.6418067226890756, "f1_std": 0.04441502347280435, "bacc": 0.6418067226890756, "bacc_std": 0.04432888947668008} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04343932280628793, "f1": 0.5826018084614877, "f1_std": 0.04433749565180021, "bacc": 0.5824579831932774, "bacc_std": 0.04402226347314493} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.5161290322580645, "acc_std": 0.04390386278602168, "f1": 0.5129615082482325, "f1_std": 0.044174183552552586, "bacc": 0.5131302521008403, "bacc_std": 0.04423233565867662} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04438966081772879, "f1": 0.6041951664386684, "f1_std": 0.04437383028066331, "bacc": 0.6066176470588236, "bacc_std": 0.04439890154375602} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043960590974109114, "f1": 0.6035753898349319, "f1_std": 0.04400106766929949, "bacc": 0.6050420168067226, "bacc_std": 0.04403133407234343} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.039730635699814096, "f1": 0.6526610644257702, "f1_std": 0.039766138423536226, "bacc": 0.6554621848739496, "bacc_std": 0.0398270830796502} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.03879320289755654, "f1": 0.5581140350877193, "f1_std": 0.04213117157077213, "bacc": 0.5640756302521008, "bacc_std": 0.03949008345253527} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.044949025933407306, "f1": 0.6119947848761408, "f1_std": 0.045094328383577416, "bacc": 0.6139705882352942, "bacc_std": 0.04525716203175383} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 166.81005372000556, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.042900121158586914, "f1": 0.5623043623043623, "f1_std": 0.044323968930829065, "bacc": 0.5630252100840336, "bacc_std": 0.04335847781129747} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04328294249866049, "f1": 0.6153389215233318, "f1_std": 0.044105161532270364, "bacc": 0.6150210084033614, "bacc_std": 0.043838383793386705} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 2.782559402207126, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.045225748930063286, "f1": 0.5150792072645324, "f1_std": 0.046107639264786775, "bacc": 0.5157563025210083, "bacc_std": 0.045554000234481945} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04505188071873942, "f1": 0.6125, "f1_std": 0.04521286897297581, "bacc": 0.615546218487395, "bacc_std": 0.04521116737625754} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04092897581658232, "f1": 0.5907590759075907, "f1_std": 0.0430340084514928, "bacc": 0.592436974789916, "bacc_std": 0.041520244590889585} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.0428686830382255, "f1": 0.5573516535327002, "f1_std": 0.04491170217156621, "bacc": 0.5598739495798319, "bacc_std": 0.04341343794202899} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04087969965536183, "f1": 0.6391534391534391, "f1_std": 0.041795905441736135, "bacc": 0.6386554621848739, "bacc_std": 0.041498248203676535} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04263826441228081, "f1": 0.5529334644378892, "f1_std": 0.043010729355763534, "bacc": 0.553046218487395, "bacc_std": 0.04290706634341999} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04368924650466842, "f1": 0.5694444444444444, "f1_std": 0.04555551950846896, "bacc": 0.5703781512605042, "bacc_std": 0.04446724336882759} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04168404458975978, "f1": 0.626380984265149, "f1_std": 0.0433349745376252, "bacc": 0.6265756302521008, "bacc_std": 0.04227477092333316} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04220056109721617, "f1": 0.6502820306204673, "f1_std": 0.04457058529396927, "bacc": 0.6502100840336134, "bacc_std": 0.04312623712672943} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04198856442108495, "f1": 0.6595915634415801, "f1_std": 0.04404721572849947, "bacc": 0.6591386554621849, "bacc_std": 0.04294610920499959} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.000774263682681127, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04230599042952057, "f1": 0.5343756400628115, "f1_std": 0.04548069640892707, "bacc": 0.5404411764705883, "bacc_std": 0.04289293801952597} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04296907389197765, "f1": 0.5931704050887178, "f1_std": 0.045058357262803786, "bacc": 0.5940126050420168, "bacc_std": 0.04379618098676921} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04434968885059558, "f1": 0.5479166666666666, "f1_std": 0.04446141921597849, "bacc": 0.5504201680672269, "bacc_std": 0.04461821459023731} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.042092939511416384, "f1": 0.5860042735042735, "f1_std": 0.04365335817085198, "bacc": 0.5866596638655462, "bacc_std": 0.04271377486357096} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.000774263682681127, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.040166960993620854, "f1": 0.5639943741209563, "f1_std": 0.045382662437967, "bacc": 0.5756302521008403, "bacc_std": 0.040975089721394936} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04239652274041667, "f1": 0.5826018084614877, "f1_std": 0.042925312185141125, "bacc": 0.5824579831932774, "bacc_std": 0.04273381108732241} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.0457373257379656, "f1": 0.5662332519305657, "f1_std": 0.046666879224178316, "bacc": 0.5661764705882353, "bacc_std": 0.04628617344892488} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.0397776435465781, "f1": 0.6163150492264415, "f1_std": 0.04598212853974836, "bacc": 0.6244747899159664, "bacc_std": 0.041214430215073726} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04056549732668247, "f1": 0.671957671957672, "f1_std": 0.041553221558509545, "bacc": 0.671218487394958, "bacc_std": 0.04123682171538047} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04164163799093594, "f1": 0.5529334644378892, "f1_std": 0.04188418939078813, "bacc": 0.553046218487395, "bacc_std": 0.0419382787703537} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04364051187595083, "f1": 0.5735449735449736, "f1_std": 0.044505960363405886, "bacc": 0.5735294117647058, "bacc_std": 0.04413228362399165} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.039670006519707965, "f1": 0.6145945945945945, "f1_std": 0.04291624141774532, "bacc": 0.6160714285714286, "bacc_std": 0.040926654186235895} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041428121873890424, "f1": 0.6118548118548119, "f1_std": 0.04348886153441063, "bacc": 0.6118697478991597, "bacc_std": 0.042461167910363994} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04204503061451673, "f1": 0.6301451580831179, "f1_std": 0.04322589035904723, "bacc": 0.6297268907563025, "bacc_std": 0.042767793289440546} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04339758837053934, "f1": 0.6003223207091055, "f1_std": 0.04543233482994681, "bacc": 0.6013655462184874, "bacc_std": 0.043999294468984936} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.03964992490869749, "f1": 0.5334448160535117, "f1_std": 0.04336624974835806, "bacc": 0.5446428571428572, "bacc_std": 0.040068125771453515} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04369420033093446, "f1": 0.5765651155005022, "f1_std": 0.04527750456037661, "bacc": 0.5777310924369747, "bacc_std": 0.04416791018070244} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04640643804684464, "f1": 0.5441176470588236, "f1_std": 0.046875613611318416, "bacc": 0.5441176470588236, "bacc_std": 0.04683560282102705} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 1291.5496650148827, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.044404309654817474, "f1": 0.5588932806324111, "f1_std": 0.04486859276954172, "bacc": 0.5588235294117647, "bacc_std": 0.04469156616079761} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04262293537741512, "f1": 0.5588932806324111, "f1_std": 0.04318492466789194, "bacc": 0.5588235294117647, "bacc_std": 0.04291989724769259} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.043629923668670655, "f1": 0.5457875457875458, "f1_std": 0.044936815637702895, "bacc": 0.5467436974789917, "bacc_std": 0.044128061045797216} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.000774263682681127, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.038960544624799316, "f1": 0.5507246376811594, "f1_std": 0.044278558784575504, "bacc": 0.5609243697478992, "bacc_std": 0.03994609393487123} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.000774263682681127, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.039450158889672356, "f1": 0.6260964912280702, "f1_std": 0.04233582178360562, "bacc": 0.6292016806722689, "bacc_std": 0.040206181415309475} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04194638816046785, "f1": 0.6539994685091681, "f1_std": 0.04328705686531138, "bacc": 0.6533613445378151, "bacc_std": 0.042652639138988764} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04178843946903286, "f1": 0.6119727891156463, "f1_std": 0.04535214254835566, "bacc": 0.6144957983193278, "bacc_std": 0.042869480995037054} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044592372763027945, "f1": 0.5941345902068604, "f1_std": 0.045075824434152756, "bacc": 0.5945378151260504, "bacc_std": 0.04501262557143645} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04447535240899466, "f1": 0.5454307410316837, "f1_std": 0.04490186155154641, "bacc": 0.5456932773109244, "bacc_std": 0.044849693009637794} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.0399115143815532, "f1": 0.6532032520325204, "f1_std": 0.039928502460482414, "bacc": 0.6586134453781513, "bacc_std": 0.0397262024501651} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04269923308120655, "f1": 0.6301451580831179, "f1_std": 0.04413383827708482, "bacc": 0.6297268907563025, "bacc_std": 0.04358112134192595} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.000774263682681127, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04264746406842055, "f1": 0.5503626107977437, "f1_std": 0.04479231208794805, "bacc": 0.5525210084033614, "bacc_std": 0.043257866134231736} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04189966211968798, "f1": 0.6153389215233318, "f1_std": 0.04270476975734656, "bacc": 0.6150210084033614, "bacc_std": 0.0424407550421291} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.041798345863939386, "f1": 0.5765651155005022, "f1_std": 0.04366052135753652, "bacc": 0.5777310924369747, "bacc_std": 0.04245806822473076} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 0.000774263682681127, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04226367852391139, "f1": 0.5475675675675675, "f1_std": 0.04458494417553687, "bacc": 0.5509453781512605, "bacc_std": 0.04287193243536125} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04504765657793279, "f1": 0.5802083333333333, "f1_std": 0.04519930666156543, "bacc": 0.5829831932773109, "bacc_std": 0.04533171449081369} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.042283100192803645, "f1": 0.628935727296383, "f1_std": 0.042463211224020005, "bacc": 0.6334033613445378, "bacc_std": 0.042641520162343245} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.041167673182930395, "f1": 0.5531057875768497, "f1_std": 0.046343201475746235, "bacc": 0.5667016806722689, "bacc_std": 0.04186633269527928} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04221025059085491, "f1": 0.6465831510572015, "f1_std": 0.04318970432608874, "bacc": 0.6460084033613445, "bacc_std": 0.042655330196664724} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04204438712924569, "f1": 0.5880946053680574, "f1_std": 0.04323235449533133, "bacc": 0.5882352941176471, "bacc_std": 0.042438599322013174} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 166.81005372000556, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04451970532619128, "f1": 0.6112852664576802, "f1_std": 0.044556319240835154, "bacc": 0.6123949579831933, "bacc_std": 0.04468695148125871} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04201295573429387, "f1": 0.6210470369386127, "f1_std": 0.043544948358370854, "bacc": 0.6207983193277311, "bacc_std": 0.04278592403656117} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.043160024572789925, "f1": 0.5406479423452549, "f1_std": 0.045414341785707635, "bacc": 0.54359243697479, "bacc_std": 0.043772828072901844} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04200445940351425, "f1": 0.6336287939833467, "f1_std": 0.0443408175499767, "bacc": 0.6339285714285714, "bacc_std": 0.042950004437164624} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.000774263682681127, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043253105847472426, "f1": 0.5788211788211788, "f1_std": 0.04478776407150276, "bacc": 0.5793067226890757, "bacc_std": 0.043799617570984016} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.046385189964846765, "f1": 0.5915678524374176, "f1_std": 0.04724491484739426, "bacc": 0.5913865546218487, "bacc_std": 0.04701819434339493} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04343204291438478, "f1": 0.6301451580831179, "f1_std": 0.04440772892799085, "bacc": 0.6297268907563025, "bacc_std": 0.043920379999762} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.039530448360151835, "f1": 0.6513893429225237, "f1_std": 0.03961386463627362, "bacc": 0.6523109243697479, "bacc_std": 0.03961920158945896} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.0452628207787486, "f1": 0.543354536324071, "f1_std": 0.04658306281940136, "bacc": 0.5451680672268907, "bacc_std": 0.04543985158880487} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.000774263682681127, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04000159661225607, "f1": 0.5860042735042735, "f1_std": 0.04167298278680317, "bacc": 0.5866596638655462, "bacc_std": 0.040618495076545906} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04176223206505073, "f1": 0.5528846153846154, "f1_std": 0.043161328751855625, "bacc": 0.5540966386554622, "bacc_std": 0.04213745153087503} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.03958809772886041, "f1": 0.5400013998740113, "f1_std": 0.04375653815584479, "bacc": 0.5519957983193278, "bacc_std": 0.040161893061669944} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04439558245969393, "f1": 0.5972691721349506, "f1_std": 0.04536225940673821, "bacc": 0.5971638655462186, "bacc_std": 0.04478135432227121} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 0.000774263682681127, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04275797325406112, "f1": 0.5478500171998624, "f1_std": 0.04693292921711341, "bacc": 0.5551470588235294, "bacc_std": 0.04363521875581149} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.000774263682681127, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.041312670363585054, "f1": 0.6025641025641026, "f1_std": 0.04628101130895942, "bacc": 0.6097689075630253, "bacc_std": 0.04227879209055774} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04751014733607908, "f1": 0.5808311791608669, "f1_std": 0.048995184517542555, "bacc": 0.5808823529411764, "bacc_std": 0.0483023725618578} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04104917928128421, "f1": 0.6255252100840336, "f1_std": 0.041882476316361966, "bacc": 0.6255252100840336, "bacc_std": 0.041910542238547996} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04121103779081578, "f1": 0.5573516535327002, "f1_std": 0.04295165107264002, "bacc": 0.5598739495798319, "bacc_std": 0.0414500830908768} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04481182763447311, "f1": 0.5588932806324111, "f1_std": 0.045603071821110945, "bacc": 0.5588235294117647, "bacc_std": 0.04543437483090676} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 0.000774263682681127, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04209221332356599, "f1": 0.6191239316239316, "f1_std": 0.04354692959468902, "bacc": 0.6192226890756303, "bacc_std": 0.042622159649891245} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.046712695945952655, "f1": 0.5150792072645324, "f1_std": 0.047764210192027916, "bacc": 0.5157563025210083, "bacc_std": 0.04711505225800366} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04469497442457861, "f1": 0.5854473942969518, "f1_std": 0.044823118585106334, "bacc": 0.585609243697479, "bacc_std": 0.04464532048319953} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041830252583716025, "f1": 0.5852842809364549, "f1_std": 0.047321329570710606, "bacc": 0.5934873949579832, "bacc_std": 0.04299667437909458} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.000774263682681127, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04115872109991569, "f1": 0.6408702094699266, "f1_std": 0.043415734948990724, "bacc": 0.641281512605042, "bacc_std": 0.042054785605975836} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04433364889739793, "f1": 0.5691904293674206, "f1_std": 0.04460476459264572, "bacc": 0.569327731092437, "bacc_std": 0.04465407792747012} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.0430943445084854, "f1": 0.5716183895827798, "f1_std": 0.044477785561764835, "bacc": 0.571953781512605, "bacc_std": 0.04374033991024301} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.0428446453087631, "f1": 0.5337093741606231, "f1_std": 0.04432221906985984, "bacc": 0.5362394957983193, "bacc_std": 0.04303151597686858} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.041824406240090345, "f1": 0.5810810810810811, "f1_std": 0.044522771362656276, "bacc": 0.5835084033613446, "bacc_std": 0.04260002553785869} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04558406660217663, "f1": 0.6118548118548119, "f1_std": 0.046964519351131155, "bacc": 0.6118697478991597, "bacc_std": 0.046028708670592555} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.000774263682681127, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.03747619431690826, "f1": 0.6129032258064516, "f1_std": 0.041952976161021976, "bacc": 0.6186974789915967, "bacc_std": 0.03851691529383629} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.044981355254143686, "f1": 0.6604954367666231, "f1_std": 0.04501709585655694, "bacc": 0.6628151260504203, "bacc_std": 0.045244331977391736} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04427898499250746, "f1": 0.5941345902068604, "f1_std": 0.04458463843668474, "bacc": 0.5945378151260504, "bacc_std": 0.044557964897986795} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04618960606713198, "f1": 0.610369206598586, "f1_std": 0.04647705815015329, "bacc": 0.6108193277310925, "bacc_std": 0.046406912166710036} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | abide_dx | train | 100 | 18.255 | 131.76 | 0.83615 | 0.089283 | 0.83092 | 0.093953 | 0.82941 | 0.094028 | +| flat_mae | reg | logistic | abide_dx | test | 100 | 18.255 | 131.76 | 0.60073 | 0.035208 | 0.59052 | 0.036948 | 0.59248 | 0.036191 | + + +done! total time: 0:05:16 diff --git a/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f83e29653211fbd1bd0c15bc0b1733ab7f9aa0c8 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..52f28f322264d8e4d3163632a575f5e4b9a52148 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,train,0.6438356164383562,0.021598109492408993,0.6167700458745236,0.024421938045522305,0.619893753434695,0.02252146578220332 +flat_mae,patch,logistic,adhd200_dx,,0.000774263682681127,test,0.6307692307692307,0.053016161430087194,0.587737843551797,0.06371790174844984,0.5974903474903475,0.05564760853965894 +flat_mae,patch,logistic,adhd200_dx,1,0.000774263682681127,train,0.6684931506849315,0.023679909622341767,0.6427386932640895,0.026618109170856757,0.6446082921169933,0.02470049686602684 +flat_mae,patch,logistic,adhd200_dx,1,0.000774263682681127,test,0.6615384615384615,0.05458277683140735,0.6425000000000001,0.05816779598910018,0.6418918918918919,0.05585433506353738 +flat_mae,patch,logistic,adhd200_dx,2,0.000774263682681127,train,0.673972602739726,0.02161848419924479,0.6400841888946893,0.025745889675919474,0.6451578433168468,0.02285601327340875 +flat_mae,patch,logistic,adhd200_dx,2,0.000774263682681127,test,0.676923076923077,0.05326767062419579,0.6500897205844656,0.060294453957874965,0.6510617760617761,0.05582676658916951 +flat_mae,patch,logistic,adhd200_dx,3,0.046415888336127774,train,0.9123287671232877,0.014660052529796519,0.9102918586789555,0.015112741888664512,0.9079807046467607,0.015466121868361335 +flat_mae,patch,logistic,adhd200_dx,3,0.046415888336127774,test,0.5538461538461539,0.05944413915999939,0.5167905665214048,0.06648543375191263,0.5255791505791506,0.06102948444079758 +flat_mae,patch,logistic,adhd200_dx,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,4,166.81005372000556,test,0.5230769230769231,0.061334083693206067,0.5230769230769231,0.061730884070689676,0.5333011583011583,0.06199841832793676 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,train,0.7945205479452054,0.02087270734244459,0.7880026949794392,0.02195483741648772,0.7849575624351224,0.022000148336815784 +flat_mae,patch,logistic,adhd200_dx,5,0.005994842503189409,test,0.46153846153846156,0.06372235634551544,0.4532564287430906,0.06419256675531515,0.4531853281853282,0.06439503835085006 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,train,0.8027397260273973,0.01950348131614078,0.793044793044793,0.021132483004855766,0.7879342981009954,0.020755070547584072 +flat_mae,patch,logistic,adhd200_dx,6,0.005994842503189409,test,0.6,0.05869956402366246,0.5775,0.06385545691331125,0.5791505791505791,0.060692420538455825 +flat_mae,patch,logistic,adhd200_dx,7,0.3593813663804626,train,0.9945205479452055,0.0038413850945392975,0.9944199841007766,0.003921161931619664,0.9937106918238994,0.0044091369795812695 +flat_mae,patch,logistic,adhd200_dx,7,0.3593813663804626,test,0.6153846153846154,0.058562051246125645,0.61207925519217,0.05863691487394823,0.6143822393822393,0.05872152147696279 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,train,0.8082191780821918,0.020510925556385392,0.8002283105022832,0.021915896087596594,0.7956585455211578,0.021714294725443378 +flat_mae,patch,logistic,adhd200_dx,8,0.005994842503189409,test,0.6153846153846154,0.05792593516290472,0.5905769715293525,0.06304229988180467,0.5926640926640927,0.059590463438365306 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7890410958904109,0.02098109238261974,0.7823494335122242,0.021753237450854043,0.7793857238810526,0.02155844288910556 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.5384615384615384,0.06158278403856737,0.5192307692307693,0.06437345748483865,0.5207528957528957,0.06253833709650634 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,train,0.8,0.02092523107525068,0.7923631404636664,0.022099881092791044,0.7883769921230994,0.021887246474434862 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,test,0.5076923076923077,0.05335575367009767,0.4616977225672878,0.05810147129353499,0.47635135135135137,0.05352959599264273 +flat_mae,patch,logistic,adhd200_dx,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,11,166.81005372000556,test,0.6,0.05922494277037207,0.588206627680312,0.06162202230735518,0.5878378378378378,0.06078169532661276 +flat_mae,patch,logistic,adhd200_dx,12,0.046415888336127774,train,0.9013698630136986,0.015805508658675527,0.8992454913507545,0.016210152075636284,0.8975544971606522,0.016423811247527537 +flat_mae,patch,logistic,adhd200_dx,12,0.046415888336127774,test,0.5076923076923077,0.05783845284254182,0.4715447154471545,0.06207864877294101,0.4806949806949807,0.058265914158232374 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,train,0.8027397260273973,0.02041015793224763,0.7962790697674418,0.021252222539162355,0.7929565854552115,0.021076993953668913 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,test,0.49230769230769234,0.06439801533198226,0.48000000000000004,0.06475373086103058,0.48021235521235517,0.06443108900286382 +flat_mae,patch,logistic,adhd200_dx,14,0.000774263682681127,train,0.6493150684931507,0.022911776261604264,0.6163447641571409,0.026557616464965402,0.6218782438786102,0.023940109210305014 +flat_mae,patch,logistic,adhd200_dx,14,0.000774263682681127,test,0.6,0.04766561039367044,0.5427489177489178,0.058322156303431835,0.5617760617760618,0.04923808239179693 +flat_mae,patch,logistic,adhd200_dx,15,0.000774263682681127,train,0.6575342465753424,0.022787851368945154,0.6272741383395012,0.026034165130371555,0.6313122061427612,0.023745994961933307 +flat_mae,patch,logistic,adhd200_dx,15,0.000774263682681127,test,0.47692307692307695,0.05939590167759619,0.4385162601626016,0.06222406102692797,0.44932432432432434,0.059227128542902165 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7698630136986301,0.02045934579048208,0.7618381804623415,0.02148033610022428,0.7588080845087622,0.02126653030528063 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.5692307692307692,0.05899573748517869,0.5512820512820513,0.06184089418031723,0.5521235521235521,0.06007862093873255 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,train,0.9068493150684932,0.014178140162676803,0.9046850998463902,0.014582291924127591,0.902408866092691,0.014826127252433065 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,test,0.5692307692307692,0.06318069512664759,0.5512820512820513,0.06675776505682737,0.5521235521235521,0.06420774843460915 +flat_mae,patch,logistic,adhd200_dx,18,0.000774263682681127,train,0.6657534246575343,0.022169737741640532,0.6316912591808377,0.026422261525093776,0.6371588202967576,0.023459899816570366 +flat_mae,patch,logistic,adhd200_dx,18,0.000774263682681127,test,0.6153846153846154,0.0554574222306931,0.5834401435529352,0.06317542307776587,0.5883204633204633,0.057792502697302954 +flat_mae,patch,logistic,adhd200_dx,19,0.000774263682681127,train,0.6465753424657534,0.023494523063873295,0.6153469107663652,0.026620725003437293,0.6201685290346217,0.024340110907818614 +flat_mae,patch,logistic,adhd200_dx,19,0.000774263682681127,test,0.6,0.05200035502837382,0.5427489177489178,0.06551889076776075,0.5617760617760618,0.05479271654197938 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,train,0.7808219178082192,0.020439528410321248,0.7740917249489385,0.021381097534708873,0.7713867008609635,0.021293622821616964 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,test,0.6,0.06040227277357217,0.5833333333333333,0.06349886377156135,0.5834942084942085,0.06194142220467539 +flat_mae,patch,logistic,adhd200_dx,21,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,21,0.3593813663804626,test,0.47692307692307695,0.06078012755272436,0.4666988416988417,0.061647408184550515,0.4666988416988417,0.06139976800421814 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.8054794520547945,0.019461147016494124,0.7980518215468537,0.020593487655176504,0.7939488306771691,0.020493481288402945 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.5076923076923077,0.05960774343089223,0.48,0.06234765782728307,0.48503861003861004,0.059814806170514344 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.8027397260273973,0.01913284292424078,0.7954290696226181,0.02024972299225812,0.7915216462111498,0.020124434493491824 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.5846153846153846,0.05925824737246964,0.5578231292517006,0.06463314412668242,0.5612934362934363,0.06094226843366889 +flat_mae,patch,logistic,adhd200_dx,24,0.000774263682681127,train,0.6794520547945205,0.021177993584673486,0.6499274524752232,0.02446950418727281,0.6528820907370092,0.022241140794866752 +flat_mae,patch,logistic,adhd200_dx,24,0.000774263682681127,test,0.6153846153846154,0.04947328727552025,0.5656241646618552,0.06013551610944254,0.5796332046332047,0.05148820483616115 +flat_mae,patch,logistic,adhd200_dx,25,0.000774263682681127,train,0.6684931506849315,0.021488385058854597,0.6340351836660286,0.02550806772166432,0.639586004762777,0.02266112829177605 +flat_mae,patch,logistic,adhd200_dx,25,0.000774263682681127,test,0.5538461538461539,0.04958621682895645,0.48342011510002736,0.057651509779598306,0.5125482625482626,0.04971704355793214 +flat_mae,patch,logistic,adhd200_dx,26,0.000774263682681127,train,0.663013698630137,0.022010308917190073,0.623682953202404,0.026577558714504262,0.6318617573426146,0.02323913081663461 +flat_mae,patch,logistic,adhd200_dx,26,0.000774263682681127,test,0.5846153846153846,0.054301015061289516,0.5411764705882354,0.06314482643572816,0.5526061776061776,0.05612994477911382 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,train,0.7835616438356164,0.02083481864224242,0.7757793485276164,0.02193173663195322,0.7723789460829211,0.021727308992080533 +flat_mae,patch,logistic,adhd200_dx,27,0.005994842503189409,test,0.6153846153846154,0.05863201056353,0.5966741126830479,0.06226108554775521,0.597007722007722,0.05982021554354425 +flat_mae,patch,logistic,adhd200_dx,28,0.005994842503189409,train,0.8054794520547945,0.01951967794264099,0.7984852372843134,0.02065552440825935,0.7946663002992,0.020648373822218923 +flat_mae,patch,logistic,adhd200_dx,28,0.005994842503189409,test,0.6153846153846154,0.052667315802555896,0.5751633986928104,0.060909626548533366,0.583976833976834,0.054448681661916395 +flat_mae,patch,logistic,adhd200_dx,29,0.000774263682681127,train,0.6821917808219178,0.023734987709787984,0.6601271512972,0.026141533405776685,0.6603315625572449,0.024578195784587073 +flat_mae,patch,logistic,adhd200_dx,29,0.000774263682681127,test,0.5230769230769231,0.05997408513328038,0.49987589972697943,0.06335410022803643,0.502895752895753,0.06106496881365972 +flat_mae,patch,logistic,adhd200_dx,30,0.3593813663804626,train,0.9972602739726028,0.002901523790657244,0.9972160568687123,0.002944270521705463,0.9975728155339806,0.002570524717451208 +flat_mae,patch,logistic,adhd200_dx,30,0.3593813663804626,test,0.4307692307692308,0.05997219079405931,0.42201393895698147,0.06047162867097293,0.4218146718146718,0.06061224534091329 +flat_mae,patch,logistic,adhd200_dx,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,31,166.81005372000556,test,0.5076923076923077,0.05996823616809507,0.4980694980694981,0.06081754998976135,0.4980694980694981,0.060371565646453754 +flat_mae,patch,logistic,adhd200_dx,32,0.005994842503189409,train,0.8,0.020340159271484123,0.793239646462687,0.021209904212975583,0.7898119313671612,0.02109574152384358 +flat_mae,patch,logistic,adhd200_dx,32,0.005994842503189409,test,0.5230769230769231,0.060418767412297486,0.5062484685126194,0.06211279167042906,0.5072393822393823,0.06097178096775775 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,train,0.7972602739726027,0.020643855796228697,0.7906201550387597,0.021715884231139904,0.7873847469011418,0.021719001262178315 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,test,0.5384615384615384,0.06081926664525208,0.5294401544401545,0.06202906365580947,0.5294401544401545,0.06174114851834983 +flat_mae,patch,logistic,adhd200_dx,34,0.005994842503189409,train,0.7890410958904109,0.020357805940558887,0.7819103120222861,0.02143069433163601,0.7786682542590218,0.02135262461238272 +flat_mae,patch,logistic,adhd200_dx,34,0.005994842503189409,test,0.5230769230769231,0.05848925658695513,0.5062484685126194,0.06043684203833445,0.5072393822393823,0.059191554447548894 +flat_mae,patch,logistic,adhd200_dx,35,0.000774263682681127,train,0.6602739726027397,0.021398620622219637,0.6256534109706875,0.024680148208664276,0.6315869817426879,0.022194672002608197 +flat_mae,patch,logistic,adhd200_dx,35,0.000774263682681127,test,0.5384615384615384,0.055873695264276255,0.4953416149068323,0.061136032634657306,0.5077220077220077,0.05628585343185203 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.6876712328767123,0.02270204833680064,0.6617733125243855,0.0260762869557916,0.663033522623191,0.02400591520942783 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.5538461538461539,0.05586919634818203,0.5250692869740489,0.059207587900959216,0.5299227799227799,0.05637866020391929 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,train,0.6712328767123288,0.021206949083617994,0.6377291073909879,0.0248168969203922,0.6427306588508274,0.022249556301196557 +flat_mae,patch,logistic,adhd200_dx,37,0.000774263682681127,test,0.6307692307692307,0.04928493174431127,0.577922077922078,0.06240816809054939,0.5931467181467182,0.05222104762727831 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7972602739726027,0.019418679451837558,0.7892872745428448,0.020522607089093325,0.7852323380350492,0.020278038133458874 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.5384615384615384,0.0570618765155799,0.5125,0.06015206301745572,0.5164092664092664,0.057323124712604714 +flat_mae,patch,logistic,adhd200_dx,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,39,166.81005372000556,test,0.5538461538461539,0.05647724786697045,0.5167905665214048,0.061878199956931626,0.5255791505791506,0.05731770159166456 +flat_mae,patch,logistic,adhd200_dx,40,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,40,2.782559402207126,test,0.6153846153846154,0.05584522991395068,0.5905769715293525,0.06099042460152087,0.5926640926640927,0.057642639581945675 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,train,0.6821917808219178,0.022741806143513944,0.6523124425174089,0.026529195535248566,0.6553092752030286,0.023958119554742523 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,test,0.5846153846153846,0.057220842811610224,0.5501153550371699,0.06305665053271943,0.556949806949807,0.058349982584456075 +flat_mae,patch,logistic,adhd200_dx,42,0.000774263682681127,train,0.6931506849315069,0.0227201440690645,0.6666014223266131,0.02550284135559094,0.6678878915552299,0.023606154663767327 +flat_mae,patch,logistic,adhd200_dx,42,0.000774263682681127,test,0.5230769230769231,0.05807890979790865,0.4834657780056396,0.06194704615761584,0.4942084942084942,0.058066674280761045 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,train,0.8054794520547945,0.020933178589197843,0.7980518215468537,0.022038494136178803,0.7939488306771691,0.021805866872362845 +flat_mae,patch,logistic,adhd200_dx,43,0.005994842503189409,test,0.49230769230769234,0.05979052981552598,0.4501409894898744,0.06302328530872858,0.46283783783783783,0.05944350980734723 +flat_mae,patch,logistic,adhd200_dx,44,0.005994842503189409,train,0.8054794520547945,0.020114691600040976,0.7989043136828873,0.021282851777931076,0.7953837699212309,0.021317378505018324 +flat_mae,patch,logistic,adhd200_dx,44,0.005994842503189409,test,0.5538461538461539,0.06037555836045972,0.5381034060279344,0.062392573272319896,0.5386100386100386,0.061220580077178385 +flat_mae,patch,logistic,adhd200_dx,45,0.000774263682681127,train,0.6904109589041096,0.021869055367365824,0.6569463274251637,0.026420505743095263,0.6611558893570251,0.023341492144371586 +flat_mae,patch,logistic,adhd200_dx,45,0.000774263682681127,test,0.5384615384615384,0.05492199093948977,0.4953416149068323,0.061019842964539675,0.5077220077220077,0.05556275730159983 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,train,0.8027397260273973,0.02008043499015603,0.7954290696226181,0.021248396742905018,0.7915216462111498,0.021116171614312895 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,test,0.5692307692307692,0.059999613410983366,0.5512820512820513,0.0632732784008258,0.5521235521235521,0.061302258477976795 +flat_mae,patch,logistic,adhd200_dx,47,0.000774263682681127,train,0.6876712328767123,0.02162145609071761,0.6617733125243855,0.02523587356916178,0.663033522623191,0.023005197143227095 +flat_mae,patch,logistic,adhd200_dx,47,0.000774263682681127,test,0.5692307692307692,0.05430722161487022,0.5376016260162602,0.060509814614598395,0.5434362934362934,0.055965161865090936 +flat_mae,patch,logistic,adhd200_dx,48,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,48,0.3593813663804626,test,0.5076923076923077,0.06201159654862044,0.5075757575757576,0.06249513905165893,0.5154440154440154,0.06290359526349577 +flat_mae,patch,logistic,adhd200_dx,49,0.000774263682681127,train,0.6958904109589041,0.022337474728727078,0.6732898418663161,0.02512288254344692,0.6731849545093729,0.02345338427880249 +flat_mae,patch,logistic,adhd200_dx,49,0.000774263682681127,test,0.4307692307692308,0.050033986082597987,0.3712418300653595,0.05085570891481752,0.39575289575289574,0.04862835637335675 +flat_mae,patch,logistic,adhd200_dx,50,0.000774263682681127,train,0.6684931506849315,0.023022111312986964,0.6366844629445298,0.027008721161092146,0.6410209440068388,0.024296397467016798 +flat_mae,patch,logistic,adhd200_dx,50,0.000774263682681127,test,0.6461538461538462,0.04698391012517889,0.5787545787545787,0.06561877685565559,0.6023166023166023,0.05085532358997731 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,train,0.7863013698630137,0.021026107675417065,0.7783814920911696,0.022187823366672937,0.7748061305489405,0.021966043237055605 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,test,0.5692307692307692,0.06161517526133645,0.5512820512820513,0.06475860137031064,0.5521235521235521,0.06297690948780775 +flat_mae,patch,logistic,adhd200_dx,52,0.046415888336127774,train,0.8876712328767123,0.016981351466147022,0.8855230445591891,0.017326738391848454,0.8847011052085242,0.01745472986897497 +flat_mae,patch,logistic,adhd200_dx,52,0.046415888336127774,test,0.5846153846153846,0.05659327327414149,0.5578231292517006,0.061205717037185144,0.5612934362934363,0.05802348482070051 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,train,0.7863013698630137,0.019633184097548193,0.7752321101496874,0.021401877833764835,0.7705013128167553,0.020940833351926834 +flat_mae,patch,logistic,adhd200_dx,53,0.005994842503189409,test,0.5230769230769231,0.058153772893726745,0.4834657780056396,0.062464111004496975,0.4942084942084942,0.05854725155308852 +flat_mae,patch,logistic,adhd200_dx,54,0.046415888336127774,train,0.9013698630136986,0.01618427473609324,0.8990783410138249,0.01666376275799031,0.8968370275386213,0.01687236568278534 +flat_mae,patch,logistic,adhd200_dx,54,0.046415888336127774,test,0.5230769230769231,0.05935871097023027,0.49987589972697943,0.06162719183480105,0.502895752895753,0.05972481591975175 +flat_mae,patch,logistic,adhd200_dx,55,0.046415888336127774,train,0.915068493150685,0.014380256893672536,0.9133089694378682,0.014722255161913823,0.9118428283568419,0.01495993437694061 +flat_mae,patch,logistic,adhd200_dx,55,0.046415888336127774,test,0.46153846153846156,0.06002018595350642,0.44253859348198965,0.06150887167346694,0.44449806949806947,0.06047586633789205 +flat_mae,patch,logistic,adhd200_dx,56,0.000774263682681127,train,0.673972602739726,0.021818242344548332,0.6414035087719299,0.025607607963722002,0.6458753129388777,0.02295248260118147 +flat_mae,patch,logistic,adhd200_dx,56,0.000774263682681127,test,0.5076923076923077,0.05623787180230125,0.4503171247357294,0.06089743639465138,0.472007722007722,0.055843652568109324 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,train,0.7917808219178082,0.02022906837587873,0.782601880877743,0.021669167737243297,0.7782255602369177,0.021377396013237883 +flat_mae,patch,logistic,adhd200_dx,57,0.005994842503189409,test,0.6,0.0567687804860191,0.570630081300813,0.06255617267717183,0.5748069498069498,0.0583688129918586 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.8082191780821918,0.0197412810125892,0.8015318170519512,0.020808344673546513,0.7978109543872505,0.020766493388558512 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.5538461538461539,0.056692080158190716,0.543030303030303,0.05842894871247427,0.542953667953668,0.057673075382614965 +flat_mae,patch,logistic,adhd200_dx,59,0.046415888336127774,train,0.8904109589041096,0.016999428423051532,0.8876715701360252,0.017583210944788118,0.8849758808084509,0.01793609474178389 +flat_mae,patch,logistic,adhd200_dx,59,0.046415888336127774,test,0.49230769230769234,0.060758254120629414,0.4879446168536643,0.061271300139612545,0.4888996138996139,0.06176345053314508 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.8082191780821918,0.02063740598530286,0.8015318170519512,0.021710303830444668,0.7978109543872505,0.02165336640479834 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6153846153846154,0.05691102575135162,0.5966741126830479,0.06076577111067979,0.597007722007722,0.05845589952992398 +flat_mae,patch,logistic,adhd200_dx,61,0.000774263682681127,train,0.6794520547945205,0.021834149243432008,0.6499274524752232,0.02555948720440885,0.6528820907370092,0.023128005014711284 +flat_mae,patch,logistic,adhd200_dx,61,0.000774263682681127,test,0.5538461538461539,0.05684284574531817,0.5167905665214048,0.06329509027918248,0.5255791505791506,0.058097141461517815 +flat_mae,patch,logistic,adhd200_dx,62,0.046415888336127774,train,0.8849315068493151,0.016484319303086036,0.8818442471328154,0.01710773909040222,0.8786865726323503,0.017420383625784082 +flat_mae,patch,logistic,adhd200_dx,62,0.046415888336127774,test,0.47692307692307695,0.06254163110522282,0.4666988416988417,0.06332196214751307,0.4666988416988417,0.06319083205110329 +flat_mae,patch,logistic,adhd200_dx,63,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,63,2.782559402207126,test,0.46153846153846156,0.06053304833583389,0.44253859348198965,0.0609144288021027,0.44449806949806947,0.06018364596989404 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,train,0.821917808219178,0.019999117263311668,0.8147077889113643,0.02138883948742033,0.8099468767173474,0.021349345563802913 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,test,0.5846153846153846,0.05935583997927222,0.5699583435432491,0.061671175778130125,0.5699806949806949,0.060288225924404415 +flat_mae,patch,logistic,adhd200_dx,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,65,21.54434690031882,test,0.5538461538461539,0.05641687606847302,0.5321419707123356,0.060305687382921615,0.5342664092664092,0.057884138979648336 +flat_mae,patch,logistic,adhd200_dx,66,0.000774263682681127,train,0.6794520547945205,0.021730163195289198,0.6486948939215702,0.02525457783139134,0.6521646211149783,0.022805814142196578 +flat_mae,patch,logistic,adhd200_dx,66,0.000774263682681127,test,0.5538461538461539,0.056892831881763695,0.5167905665214048,0.06147990565163112,0.5255791505791506,0.057422850146407814 +flat_mae,patch,logistic,adhd200_dx,67,0.000774263682681127,train,0.7068493150684931,0.02117466168836739,0.680946662418613,0.02480096700399773,0.6814587531293888,0.02261175405126097 +flat_mae,patch,logistic,adhd200_dx,67,0.000774263682681127,test,0.5692307692307692,0.044172828940062775,0.47940503432494275,0.05872773067948683,0.5217181467181468,0.04558766700920904 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,train,0.673972602739726,0.02171634740909815,0.6414035087719299,0.025928941901031375,0.6458753129388777,0.023039788175378762 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,test,0.6307692307692307,0.05357042370429777,0.5962732919254659,0.06180279161230033,0.6018339768339769,0.05595280396179508 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,train,0.7917808219178082,0.021207855164078634,0.7853871387014917,0.02212635111406867,0.782530377969103,0.022064995260781352 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,test,0.47692307692307695,0.06049186947176743,0.4551282051282051,0.06264931838692174,0.45801158301158307,0.060960311991994656 +flat_mae,patch,logistic,adhd200_dx,70,0.000774263682681127,train,0.6958904109589041,0.02190437944782236,0.6712111990261715,0.025256539479288728,0.6717500152653111,0.023229621257521812 +flat_mae,patch,logistic,adhd200_dx,70,0.000774263682681127,test,0.47692307692307695,0.05827383632471779,0.4385162601626016,0.06038115649272718,0.44932432432432434,0.05789890942014502 +flat_mae,patch,logistic,adhd200_dx,71,0.000774263682681127,train,0.6931506849315069,0.021550535858687707,0.6666014223266131,0.024839229928293554,0.6678878915552299,0.022755428523130047 +flat_mae,patch,logistic,adhd200_dx,71,0.000774263682681127,test,0.5538461538461539,0.04489145356914048,0.46886446886446886,0.05600358326497691,0.5082046332046332,0.04550463635942808 +flat_mae,patch,logistic,adhd200_dx,72,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,72,0.3593813663804626,test,0.46153846153846156,0.06054837373646114,0.4484848484848485,0.06183815882387,0.4488416988416989,0.06116550845879955 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.6602739726027397,0.022581060587171468,0.6332966035779103,0.025624798167837668,0.6358917994748733,0.02358548570445699 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5076923076923077,0.05958953087035601,0.48,0.06194824390050008,0.48503861003861004,0.059903850138557514 +flat_mae,patch,logistic,adhd200_dx,74,0.000774263682681127,train,0.6904109589041096,0.021948583872801276,0.663055821058909,0.02560749458048512,0.6647432374671796,0.02333184160663059 +flat_mae,patch,logistic,adhd200_dx,74,0.000774263682681127,test,0.6,0.05612324561378157,0.5626293995859213,0.06317589588378394,0.5704633204633205,0.05775676085418534 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,train,0.7561643835616438,0.021416180223840016,0.747922308701084,0.022494667004639503,0.7452372229346034,0.022270051683729017 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,test,0.5076923076923077,0.06507269671673493,0.5047619047619047,0.0652795243450451,0.5067567567567568,0.0654074700283941 +flat_mae,patch,logistic,adhd200_dx,76,0.000774263682681127,train,0.663013698630137,0.02194919601841391,0.6319750141406192,0.025062563137167287,0.6361665750748,0.02282286682576422 +flat_mae,patch,logistic,adhd200_dx,76,0.000774263682681127,test,0.5230769230769231,0.05003898125432225,0.4477939161414086,0.056526193983791696,0.4811776061776062,0.04961539107323613 +flat_mae,patch,logistic,adhd200_dx,77,0.046415888336127774,train,0.8876712328767123,0.01668027557234742,0.8849633712304653,0.01721826742180085,0.8825486963424315,0.017477725372093748 +flat_mae,patch,logistic,adhd200_dx,77,0.046415888336127774,test,0.6461538461538462,0.05926044411482579,0.6431129147767964,0.05966966752445548,0.6457528957528957,0.059757786860315514 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,train,0.821917808219178,0.01868338803732341,0.8151178647964153,0.019818499285175317,0.8106643463393783,0.019791207525405332 +flat_mae,patch,logistic,adhd200_dx,78,0.005994842503189409,test,0.47692307692307695,0.061051387802921575,0.4551282051282051,0.0619760071855894,0.45801158301158307,0.06088492985617606 +flat_mae,patch,logistic,adhd200_dx,79,0.000774263682681127,train,0.6821917808219178,0.021348588637598837,0.6569548872180451,0.024358349575495146,0.6581791536911522,0.022470223266245665 +flat_mae,patch,logistic,adhd200_dx,79,0.000774263682681127,test,0.5538461538461539,0.058463765139781465,0.5321419707123356,0.06114034570872993,0.5342664092664092,0.05916435797601838 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.7780821917808219,0.020954355312627407,0.7705809775818855,0.02190977060536756,0.7675245771508823,0.021752855008472113 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.5692307692307692,0.06127991070180587,0.5565302144249512,0.06280282923875505,0.5564671814671815,0.06194028999932819 +flat_mae,patch,logistic,adhd200_dx,81,0.000774263682681127,train,0.7013698630136986,0.022454264352566464,0.6801566054876236,0.025014157903792536,0.6794742626854735,0.023486754722150227 +flat_mae,patch,logistic,adhd200_dx,81,0.000774263682681127,test,0.5384615384615384,0.05218101402667517,0.4724025974025974,0.060158004402614845,0.49903474903474904,0.05260831262714374 +flat_mae,patch,logistic,adhd200_dx,82,0.000774263682681127,train,0.6794520547945205,0.022615850742845566,0.6474303405572754,0.02680962051651135,0.6514471514929474,0.024002136141771716 +flat_mae,patch,logistic,adhd200_dx,82,0.000774263682681127,test,0.676923076923077,0.0489377723453998,0.6351242983159583,0.0611871180939286,0.6423745173745173,0.05250820727485347 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,train,0.8,0.018619639266382375,0.7923631404636664,0.0198091728692074,0.7883769921230994,0.019750696310077025 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,test,0.5846153846153846,0.06346384890899066,0.578226387887527,0.0641602141892825,0.5786679536679536,0.06409260398977272 +flat_mae,patch,logistic,adhd200_dx,84,0.000774263682681127,train,0.6684931506849315,0.021823839659457354,0.6404116559871683,0.024686805654451388,0.6431733528729315,0.022701913880809006 +flat_mae,patch,logistic,adhd200_dx,84,0.000774263682681127,test,0.5538461538461539,0.052935410011976804,0.49612403100775193,0.06217646345795922,0.5168918918918919,0.05396233402707363 +flat_mae,patch,logistic,adhd200_dx,85,0.046415888336127774,train,0.9013698630136986,0.015445112595778175,0.8990783410138249,0.015928087777197772,0.8968370275386213,0.016206377956067688 +flat_mae,patch,logistic,adhd200_dx,85,0.046415888336127774,test,0.6,0.05892300461935712,0.5833333333333333,0.061891240280208905,0.5834942084942085,0.060313545219748965 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,train,0.8027397260273973,0.019462396633436692,0.7945205479452055,0.02070420318749722,0.790086706967088,0.020490009404529497 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,test,0.5230769230769231,0.05834566654631453,0.47320261437908495,0.06466354406444957,0.48986486486486486,0.05886899286792007 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,train,0.8,0.019316273934987294,0.7919025937004553,0.02056401145267659,0.7876595225010685,0.020385316526981827 +flat_mae,patch,logistic,adhd200_dx,87,0.005994842503189409,test,0.5384615384615384,0.061933340764283425,0.5125,0.06547087754823969,0.5164092664092664,0.06289846557613754 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,train,0.6904109589041096,0.02247195036483203,0.6674031723503939,0.0252909254782004,0.6676131159553031,0.023610412479549012 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,test,0.5076923076923077,0.0609418463705626,0.48,0.06399638171450527,0.48503861003861004,0.061449262862256965 +flat_mae,patch,logistic,adhd200_dx,89,0.000774263682681127,train,0.6821917808219178,0.02345022141086151,0.6601271512972,0.02619178338395485,0.6603315625572449,0.024557706607275815 +flat_mae,patch,logistic,adhd200_dx,89,0.000774263682681127,test,0.6,0.051745723317553546,0.5533826638477801,0.06021039070041826,0.5661196911196912,0.05321109551061686 +flat_mae,patch,logistic,adhd200_dx,90,0.000774263682681127,train,0.6904109589041096,0.021704368965744278,0.6618957446982925,0.025189252462762372,0.6640257678451487,0.022863329392443628 +flat_mae,patch,logistic,adhd200_dx,90,0.000774263682681127,test,0.5846153846153846,0.04793758269165777,0.5054945054945055,0.06110656769397677,0.5395752895752896,0.04946804070786595 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,train,0.8082191780821918,0.019487183406861813,0.8002283105022832,0.020775010641736383,0.7956585455211578,0.020587692602755697 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,test,0.6153846153846154,0.05512331522737729,0.5905769715293525,0.06033127922087831,0.5926640926640927,0.05697228280879233 +flat_mae,patch,logistic,adhd200_dx,92,0.3593813663804626,train,0.9972602739726028,0.0028206992980341797,0.9972120591807273,0.002874655813627762,0.9968553459119497,0.00323759510623421 +flat_mae,patch,logistic,adhd200_dx,92,0.3593813663804626,test,0.5846153846153846,0.06314265992938989,0.578226387887527,0.06416906895999108,0.5786679536679536,0.06384694008231567 +flat_mae,patch,logistic,adhd200_dx,93,9.999999999999999e-05,train,0.6054794520547945,0.013286164015634023,0.487719298245614,0.022653624749318677,0.5529095682970019,0.014388927130394028 +flat_mae,patch,logistic,adhd200_dx,93,9.999999999999999e-05,test,0.6,0.019893206000301065,0.43666666666666665,0.04443838519122845,0.5357142857142857,0.023090328393206586 +flat_mae,patch,logistic,adhd200_dx,94,0.000774263682681127,train,0.6876712328767123,0.022005126750434395,0.6617733125243855,0.02488195864749761,0.663033522623191,0.022981090029836275 +flat_mae,patch,logistic,adhd200_dx,94,0.000774263682681127,test,0.6153846153846154,0.04246014490466847,0.5277535600116245,0.062355044822991194,0.5666023166023166,0.04565068633139476 +flat_mae,patch,logistic,adhd200_dx,95,0.3593813663804626,train,0.9972602739726028,0.0026918055699653486,0.9972120591807273,0.0027430305738328233,0.9968553459119497,0.003089651047287282 +flat_mae,patch,logistic,adhd200_dx,95,0.3593813663804626,test,0.5538461538461539,0.05437068475701538,0.5167905665214048,0.060329578583930184,0.5255791505791506,0.055351183024685446 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,train,0.8082191780821918,0.019327856642924943,0.8011115954664342,0.02038990628108996,0.7970934847652196,0.020296760531888804 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,test,0.5230769230769231,0.05978336433229209,0.5062484685126194,0.06187737438459926,0.5072393822393823,0.060451464920462834 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,train,0.7972602739726027,0.019678188566863423,0.7892872745428448,0.021015207506802178,0.7852323380350492,0.02089357743884958 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,test,0.5384615384615384,0.05697231965701055,0.4846723044397463,0.06423068990692955,0.5033783783783784,0.057676133058271066 +flat_mae,patch,logistic,adhd200_dx,98,0.000774263682681127,train,0.6712328767123288,0.022186920489235235,0.6403232163973196,0.025881737951824836,0.6441655980948892,0.02339293470612363 +flat_mae,patch,logistic,adhd200_dx,98,0.000774263682681127,test,0.6,0.05307044776554559,0.5427489177489178,0.06350648693969092,0.5617760617760618,0.05449924135245666 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,train,0.6958904109589041,0.022539454783897028,0.6780154018548983,0.024668385039859596,0.6767723026195274,0.02351282662063588 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,test,0.5538461538461539,0.05515572360284874,0.5321419707123356,0.05807587600065702,0.5342664092664092,0.056046407809770674 +flat_mae,patch,logistic,adhd200_dx,100,0.000774263682681127,train,0.6904109589041096,0.021863153774399346,0.6652870764861026,0.025064338408878922,0.6661781767112414,0.023075001742908708 +flat_mae,patch,logistic,adhd200_dx,100,0.000774263682681127,test,0.5076923076923077,0.054612558973491945,0.4616977225672878,0.05981336694736562,0.47635135135135137,0.05515783886831236 diff --git a/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..4380f9ced0d4e75c381b1144de30a20693fe2fa9 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:43:27 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:12:33 time: 4.9916 data: 4.0208 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:57 time: 0.2081 data: 0.0750 max mem: 3005 +extract (train) [ 40/151] eta: 0:00:33 time: 0.1693 data: 0.0537 max mem: 3005 +extract (train) [ 60/151] eta: 0:00:23 time: 0.1689 data: 0.0550 max mem: 3005 +extract (train) [ 80/151] eta: 0:00:16 time: 0.1655 data: 0.0527 max mem: 3005 +extract (train) [100/151] eta: 0:00:11 time: 0.1649 data: 0.0523 max mem: 3005 +extract (train) [120/151] eta: 0:00:06 time: 0.1657 data: 0.0528 max mem: 3005 +extract (train) [140/151] eta: 0:00:02 time: 0.1668 data: 0.0538 max mem: 3005 +extract (train) [150/151] eta: 0:00:00 time: 0.1571 data: 0.0492 max mem: 3005 +extract (train) Total time: 0:00:31 (0.2054 s / it) +extract (validation) [ 0/32] eta: 0:02:12 time: 4.1342 data: 3.9301 max mem: 3005 +extract (validation) [20/32] eta: 0:00:04 time: 0.1925 data: 0.0667 max mem: 3005 +extract (validation) [31/32] eta: 0:00:00 time: 0.1530 data: 0.0474 max mem: 3005 +extract (validation) Total time: 0:00:10 (0.3129 s / it) +extract (test) [ 0/33] eta: 0:02:13 time: 4.0377 data: 3.8013 max mem: 3005 +extract (test) [20/33] eta: 0:00:04 time: 0.1988 data: 0.0701 max mem: 3005 +extract (test) [32/33] eta: 0:00:00 time: 0.1652 data: 0.0563 max mem: 3005 +extract (test) Total time: 0:00:10 (0.3149 s / it) +feature extraction time: 0:00:51 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | train | 0.64384 | 0.021598 | 0.61677 | 0.024422 | 0.61989 | 0.022521 | +| flat_mae | patch | logistic | adhd200_dx | | 0.00077426 | test | 0.63077 | 0.053016 | 0.58774 | 0.063718 | 0.59749 | 0.055648 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05458277683140735, "f1": 0.6425000000000001, "f1_std": 0.05816779598910018, "bacc": 0.6418918918918919, "bacc_std": 0.05585433506353738} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05326767062419579, "f1": 0.6500897205844656, "f1_std": 0.060294453957874965, "bacc": 0.6510617760617761, "bacc_std": 0.05582676658916951} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05944413915999939, "f1": 0.5167905665214048, "f1_std": 0.06648543375191263, "bacc": 0.5255791505791506, "bacc_std": 0.06102948444079758} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.061334083693206067, "f1": 0.5230769230769231, "f1_std": 0.061730884070689676, "bacc": 0.5333011583011583, "bacc_std": 0.06199841832793676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06372235634551544, "f1": 0.4532564287430906, "f1_std": 0.06419256675531515, "bacc": 0.4531853281853282, "bacc_std": 0.06439503835085006} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05869956402366246, "f1": 0.5775, "f1_std": 0.06385545691331125, "bacc": 0.5791505791505791, "bacc_std": 0.060692420538455825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058562051246125645, "f1": 0.61207925519217, "f1_std": 0.05863691487394823, "bacc": 0.6143822393822393, "bacc_std": 0.05872152147696279} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05792593516290472, "f1": 0.5905769715293525, "f1_std": 0.06304229988180467, "bacc": 0.5926640926640927, "bacc_std": 0.059590463438365306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06158278403856737, "f1": 0.5192307692307693, "f1_std": 0.06437345748483865, "bacc": 0.5207528957528957, "bacc_std": 0.06253833709650634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05335575367009767, "f1": 0.4616977225672878, "f1_std": 0.05810147129353499, "bacc": 0.47635135135135137, "bacc_std": 0.05352959599264273} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.05922494277037207, "f1": 0.588206627680312, "f1_std": 0.06162202230735518, "bacc": 0.5878378378378378, "bacc_std": 0.06078169532661276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05783845284254182, "f1": 0.4715447154471545, "f1_std": 0.06207864877294101, "bacc": 0.4806949806949807, "bacc_std": 0.058265914158232374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06439801533198226, "f1": 0.48000000000000004, "f1_std": 0.06475373086103058, "bacc": 0.48021235521235517, "bacc_std": 0.06443108900286382} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.04766561039367044, "f1": 0.5427489177489178, "f1_std": 0.058322156303431835, "bacc": 0.5617760617760618, "bacc_std": 0.04923808239179693} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.000774263682681127, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.05939590167759619, "f1": 0.4385162601626016, "f1_std": 0.06222406102692797, "bacc": 0.44932432432432434, "bacc_std": 0.059227128542902165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05899573748517869, "f1": 0.5512820512820513, "f1_std": 0.06184089418031723, "bacc": 0.5521235521235521, "bacc_std": 0.06007862093873255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06318069512664759, "f1": 0.5512820512820513, "f1_std": 0.06675776505682737, "bacc": 0.5521235521235521, "bacc_std": 0.06420774843460915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0554574222306931, "f1": 0.5834401435529352, "f1_std": 0.06317542307776587, "bacc": 0.5883204633204633, "bacc_std": 0.057792502697302954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05200035502837382, "f1": 0.5427489177489178, "f1_std": 0.06551889076776075, "bacc": 0.5617760617760618, "bacc_std": 0.05479271654197938} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06040227277357217, "f1": 0.5833333333333333, "f1_std": 0.06349886377156135, "bacc": 0.5834942084942085, "bacc_std": 0.06194142220467539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.3593813663804626, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.06078012755272436, "f1": 0.4666988416988417, "f1_std": 0.061647408184550515, "bacc": 0.4666988416988417, "bacc_std": 0.06139976800421814} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05960774343089223, "f1": 0.48, "f1_std": 0.06234765782728307, "bacc": 0.48503861003861004, "bacc_std": 0.059814806170514344} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05925824737246964, "f1": 0.5578231292517006, "f1_std": 0.06463314412668242, "bacc": 0.5612934362934363, "bacc_std": 0.06094226843366889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.04947328727552025, "f1": 0.5656241646618552, "f1_std": 0.06013551610944254, "bacc": 0.5796332046332047, "bacc_std": 0.05148820483616115} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.04958621682895645, "f1": 0.48342011510002736, "f1_std": 0.057651509779598306, "bacc": 0.5125482625482626, "bacc_std": 0.04971704355793214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.054301015061289516, "f1": 0.5411764705882354, "f1_std": 0.06314482643572816, "bacc": 0.5526061776061776, "bacc_std": 0.05612994477911382} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05863201056353, "f1": 0.5966741126830479, "f1_std": 0.06226108554775521, "bacc": 0.597007722007722, "bacc_std": 0.05982021554354425} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.052667315802555896, "f1": 0.5751633986928104, "f1_std": 0.060909626548533366, "bacc": 0.583976833976834, "bacc_std": 0.054448681661916395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05997408513328038, "f1": 0.49987589972697943, "f1_std": 0.06335410022803643, "bacc": 0.502895752895753, "bacc_std": 0.06106496881365972} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.4307692307692308, "acc_std": 0.05997219079405931, "f1": 0.42201393895698147, "f1_std": 0.06047162867097293, "bacc": 0.4218146718146718, "bacc_std": 0.06061224534091329} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05996823616809507, "f1": 0.4980694980694981, "f1_std": 0.06081754998976135, "bacc": 0.4980694980694981, "bacc_std": 0.060371565646453754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.060418767412297486, "f1": 0.5062484685126194, "f1_std": 0.06211279167042906, "bacc": 0.5072393822393823, "bacc_std": 0.06097178096775775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06081926664525208, "f1": 0.5294401544401545, "f1_std": 0.06202906365580947, "bacc": 0.5294401544401545, "bacc_std": 0.06174114851834983} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05848925658695513, "f1": 0.5062484685126194, "f1_std": 0.06043684203833445, "bacc": 0.5072393822393823, "bacc_std": 0.059191554447548894} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.055873695264276255, "f1": 0.4953416149068323, "f1_std": 0.061136032634657306, "bacc": 0.5077220077220077, "bacc_std": 0.05628585343185203} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05586919634818203, "f1": 0.5250692869740489, "f1_std": 0.059207587900959216, "bacc": 0.5299227799227799, "bacc_std": 0.05637866020391929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.04928493174431127, "f1": 0.577922077922078, "f1_std": 0.06240816809054939, "bacc": 0.5931467181467182, "bacc_std": 0.05222104762727831} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0570618765155799, "f1": 0.5125, "f1_std": 0.06015206301745572, "bacc": 0.5164092664092664, "bacc_std": 0.057323124712604714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05647724786697045, "f1": 0.5167905665214048, "f1_std": 0.061878199956931626, "bacc": 0.5255791505791506, "bacc_std": 0.05731770159166456} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 2.782559402207126, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05584522991395068, "f1": 0.5905769715293525, "f1_std": 0.06099042460152087, "bacc": 0.5926640926640927, "bacc_std": 0.057642639581945675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.057220842811610224, "f1": 0.5501153550371699, "f1_std": 0.06305665053271943, "bacc": 0.556949806949807, "bacc_std": 0.058349982584456075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05807890979790865, "f1": 0.4834657780056396, "f1_std": 0.06194704615761584, "bacc": 0.4942084942084942, "bacc_std": 0.058066674280761045} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.05979052981552598, "f1": 0.4501409894898744, "f1_std": 0.06302328530872858, "bacc": 0.46283783783783783, "bacc_std": 0.05944350980734723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06037555836045972, "f1": 0.5381034060279344, "f1_std": 0.062392573272319896, "bacc": 0.5386100386100386, "bacc_std": 0.061220580077178385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05492199093948977, "f1": 0.4953416149068323, "f1_std": 0.061019842964539675, "bacc": 0.5077220077220077, "bacc_std": 0.05556275730159983} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.059999613410983366, "f1": 0.5512820512820513, "f1_std": 0.0632732784008258, "bacc": 0.5521235521235521, "bacc_std": 0.061302258477976795} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05430722161487022, "f1": 0.5376016260162602, "f1_std": 0.060509814614598395, "bacc": 0.5434362934362934, "bacc_std": 0.055965161865090936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06201159654862044, "f1": 0.5075757575757576, "f1_std": 0.06249513905165893, "bacc": 0.5154440154440154, "bacc_std": 0.06290359526349577} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.000774263682681127, "split": "test", "acc": 0.4307692307692308, "acc_std": 0.050033986082597987, "f1": 0.3712418300653595, "f1_std": 0.05085570891481752, "bacc": 0.39575289575289574, "bacc_std": 0.04862835637335675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.000774263682681127, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.04698391012517889, "f1": 0.5787545787545787, "f1_std": 0.06561877685565559, "bacc": 0.6023166023166023, "bacc_std": 0.05085532358997731} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06161517526133645, "f1": 0.5512820512820513, "f1_std": 0.06475860137031064, "bacc": 0.5521235521235521, "bacc_std": 0.06297690948780775} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05659327327414149, "f1": 0.5578231292517006, "f1_std": 0.061205717037185144, "bacc": 0.5612934362934363, "bacc_std": 0.05802348482070051} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.058153772893726745, "f1": 0.4834657780056396, "f1_std": 0.062464111004496975, "bacc": 0.4942084942084942, "bacc_std": 0.05854725155308852} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05935871097023027, "f1": 0.49987589972697943, "f1_std": 0.06162719183480105, "bacc": 0.502895752895753, "bacc_std": 0.05972481591975175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06002018595350642, "f1": 0.44253859348198965, "f1_std": 0.06150887167346694, "bacc": 0.44449806949806947, "bacc_std": 0.06047586633789205} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05623787180230125, "f1": 0.4503171247357294, "f1_std": 0.06089743639465138, "bacc": 0.472007722007722, "bacc_std": 0.055843652568109324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0567687804860191, "f1": 0.570630081300813, "f1_std": 0.06255617267717183, "bacc": 0.5748069498069498, "bacc_std": 0.0583688129918586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.056692080158190716, "f1": 0.543030303030303, "f1_std": 0.05842894871247427, "bacc": 0.542953667953668, "bacc_std": 0.057673075382614965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.060758254120629414, "f1": 0.4879446168536643, "f1_std": 0.061271300139612545, "bacc": 0.4888996138996139, "bacc_std": 0.06176345053314508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05691102575135162, "f1": 0.5966741126830479, "f1_std": 0.06076577111067979, "bacc": 0.597007722007722, "bacc_std": 0.05845589952992398} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05684284574531817, "f1": 0.5167905665214048, "f1_std": 0.06329509027918248, "bacc": 0.5255791505791506, "bacc_std": 0.058097141461517815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.06254163110522282, "f1": 0.4666988416988417, "f1_std": 0.06332196214751307, "bacc": 0.4666988416988417, "bacc_std": 0.06319083205110329} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 2.782559402207126, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06053304833583389, "f1": 0.44253859348198965, "f1_std": 0.0609144288021027, "bacc": 0.44449806949806947, "bacc_std": 0.06018364596989404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05935583997927222, "f1": 0.5699583435432491, "f1_std": 0.061671175778130125, "bacc": 0.5699806949806949, "bacc_std": 0.060288225924404415} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05641687606847302, "f1": 0.5321419707123356, "f1_std": 0.060305687382921615, "bacc": 0.5342664092664092, "bacc_std": 0.057884138979648336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.056892831881763695, "f1": 0.5167905665214048, "f1_std": 0.06147990565163112, "bacc": 0.5255791505791506, "bacc_std": 0.057422850146407814} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.044172828940062775, "f1": 0.47940503432494275, "f1_std": 0.05872773067948683, "bacc": 0.5217181467181468, "bacc_std": 0.04558766700920904} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05357042370429777, "f1": 0.5962732919254659, "f1_std": 0.06180279161230033, "bacc": 0.6018339768339769, "bacc_std": 0.05595280396179508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.06049186947176743, "f1": 0.4551282051282051, "f1_std": 0.06264931838692174, "bacc": 0.45801158301158307, "bacc_std": 0.060960311991994656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.000774263682681127, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.05827383632471779, "f1": 0.4385162601626016, "f1_std": 0.06038115649272718, "bacc": 0.44932432432432434, "bacc_std": 0.05789890942014502} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.04489145356914048, "f1": 0.46886446886446886, "f1_std": 0.05600358326497691, "bacc": 0.5082046332046332, "bacc_std": 0.04550463635942808} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06054837373646114, "f1": 0.4484848484848485, "f1_std": 0.06183815882387, "bacc": 0.4488416988416989, "bacc_std": 0.06116550845879955} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05958953087035601, "f1": 0.48, "f1_std": 0.06194824390050008, "bacc": 0.48503861003861004, "bacc_std": 0.059903850138557514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05612324561378157, "f1": 0.5626293995859213, "f1_std": 0.06317589588378394, "bacc": 0.5704633204633205, "bacc_std": 0.05775676085418534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06507269671673493, "f1": 0.5047619047619047, "f1_std": 0.0652795243450451, "bacc": 0.5067567567567568, "bacc_std": 0.0654074700283941} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05003898125432225, "f1": 0.4477939161414086, "f1_std": 0.056526193983791696, "bacc": 0.4811776061776062, "bacc_std": 0.04961539107323613} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05926044411482579, "f1": 0.6431129147767964, "f1_std": 0.05966966752445548, "bacc": 0.6457528957528957, "bacc_std": 0.059757786860315514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.061051387802921575, "f1": 0.4551282051282051, "f1_std": 0.0619760071855894, "bacc": 0.45801158301158307, "bacc_std": 0.06088492985617606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.058463765139781465, "f1": 0.5321419707123356, "f1_std": 0.06114034570872993, "bacc": 0.5342664092664092, "bacc_std": 0.05916435797601838} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06127991070180587, "f1": 0.5565302144249512, "f1_std": 0.06280282923875505, "bacc": 0.5564671814671815, "bacc_std": 0.06194028999932819} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05218101402667517, "f1": 0.4724025974025974, "f1_std": 0.060158004402614845, "bacc": 0.49903474903474904, "bacc_std": 0.05260831262714374} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.000774263682681127, "split": "test", "acc": 0.676923076923077, "acc_std": 0.0489377723453998, "f1": 0.6351242983159583, "f1_std": 0.0611871180939286, "bacc": 0.6423745173745173, "bacc_std": 0.05250820727485347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06346384890899066, "f1": 0.578226387887527, "f1_std": 0.0641602141892825, "bacc": 0.5786679536679536, "bacc_std": 0.06409260398977272} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.052935410011976804, "f1": 0.49612403100775193, "f1_std": 0.06217646345795922, "bacc": 0.5168918918918919, "bacc_std": 0.05396233402707363} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.05892300461935712, "f1": 0.5833333333333333, "f1_std": 0.061891240280208905, "bacc": 0.5834942084942085, "bacc_std": 0.060313545219748965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05834566654631453, "f1": 0.47320261437908495, "f1_std": 0.06466354406444957, "bacc": 0.48986486486486486, "bacc_std": 0.05886899286792007} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.061933340764283425, "f1": 0.5125, "f1_std": 0.06547087754823969, "bacc": 0.5164092664092664, "bacc_std": 0.06289846557613754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.0609418463705626, "f1": 0.48, "f1_std": 0.06399638171450527, "bacc": 0.48503861003861004, "bacc_std": 0.061449262862256965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.051745723317553546, "f1": 0.5533826638477801, "f1_std": 0.06021039070041826, "bacc": 0.5661196911196912, "bacc_std": 0.05321109551061686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.04793758269165777, "f1": 0.5054945054945055, "f1_std": 0.06110656769397677, "bacc": 0.5395752895752896, "bacc_std": 0.04946804070786595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05512331522737729, "f1": 0.5905769715293525, "f1_std": 0.06033127922087831, "bacc": 0.5926640926640927, "bacc_std": 0.05697228280879233} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06314265992938989, "f1": 0.578226387887527, "f1_std": 0.06416906895999108, "bacc": 0.5786679536679536, "bacc_std": 0.06384694008231567} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 9.999999999999999e-05, "split": "test", "acc": 0.6, "acc_std": 0.019893206000301065, "f1": 0.43666666666666665, "f1_std": 0.04443838519122845, "bacc": 0.5357142857142857, "bacc_std": 0.023090328393206586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.04246014490466847, "f1": 0.5277535600116245, "f1_std": 0.062355044822991194, "bacc": 0.5666023166023166, "bacc_std": 0.04565068633139476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05437068475701538, "f1": 0.5167905665214048, "f1_std": 0.060329578583930184, "bacc": 0.5255791505791506, "bacc_std": 0.055351183024685446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.05978336433229209, "f1": 0.5062484685126194, "f1_std": 0.06187737438459926, "bacc": 0.5072393822393823, "bacc_std": 0.060451464920462834} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05697231965701055, "f1": 0.4846723044397463, "f1_std": 0.06423068990692955, "bacc": 0.5033783783783784, "bacc_std": 0.057676133058271066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05307044776554559, "f1": 0.5427489177489178, "f1_std": 0.06350648693969092, "bacc": 0.5617760617760618, "bacc_std": 0.05449924135245666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05515572360284874, "f1": 0.5321419707123356, "f1_std": 0.05807587600065702, "bacc": 0.5342664092664092, "bacc_std": 0.056046407809770674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.054612558973491945, "f1": 0.4616977225672878, "f1_std": 0.05981336694736562, "bacc": 0.47635135135135137, "bacc_std": 0.05515783886831236} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 6.9757 | 32.863 | 0.78638 | 0.1135 | 0.77088 | 0.12643 | 0.77108 | 0.12352 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 6.9757 | 32.863 | 0.554 | 0.053674 | 0.52155 | 0.054878 | 0.53049 | 0.052023 | + + +done! total time: 0:04:49 diff --git a/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5aa7c6f1ef4db6b65ac32fcfe813314e912afdba --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adhd200_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic +model: flat_mae +representation: reg +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..11f804f870ea9a635c5e552bff925d26b5a567b3 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,adhd200_dx,,0.000774263682681127,train,0.673972602739726,0.02135053288021387,0.646355264979116,0.0247518760162974,0.6487451914270013,0.022562153179266773 +flat_mae,reg,logistic,adhd200_dx,,0.000774263682681127,test,0.6,0.05388626198549339,0.5533826638477801,0.06451576690751301,0.5661196911196912,0.05627885583026897 +flat_mae,reg,logistic,adhd200_dx,1,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,1,166.81005372000556,test,0.6153846153846154,0.05912719015296276,0.61207925519217,0.05997563328105542,0.6143822393822393,0.060568491092861575 +flat_mae,reg,logistic,adhd200_dx,2,0.000774263682681127,train,0.6931506849315069,0.02096566029524679,0.6666014223266131,0.02416896013899953,0.6678878915552299,0.02211522175586972 +flat_mae,reg,logistic,adhd200_dx,2,0.000774263682681127,test,0.6153846153846154,0.05451328267647877,0.5751633986928104,0.06405906737450856,0.583976833976834,0.056974604337241525 +flat_mae,reg,logistic,adhd200_dx,3,0.005994842503189409,train,0.863013698630137,0.017557877056337545,0.8590777118853472,0.018278361019738818,0.8556817487940405,0.018505366246488623 +flat_mae,reg,logistic,adhd200_dx,3,0.005994842503189409,test,0.6153846153846154,0.056130498834486446,0.5905769715293525,0.06166988768994409,0.5926640926640927,0.057954397023842995 +flat_mae,reg,logistic,adhd200_dx,4,0.005994842503189409,train,0.8191780821917808,0.020793012380560326,0.8152834008097165,0.021335911527656876,0.8139769188496062,0.021476997930327823 +flat_mae,reg,logistic,adhd200_dx,4,0.005994842503189409,test,0.6461538461538462,0.057067583726893814,0.6233308138070043,0.06381744426563256,0.6240347490347491,0.05988501528961966 +flat_mae,reg,logistic,adhd200_dx,5,0.000774263682681127,train,0.6904109589041096,0.021810820385929994,0.6674031723503939,0.02483280578030318,0.6676131159553031,0.02302924998051709 +flat_mae,reg,logistic,adhd200_dx,5,0.000774263682681127,test,0.5076923076923077,0.06179499606328604,0.4871794871794872,0.06514920965399362,0.48938223938223935,0.06312646779427494 +flat_mae,reg,logistic,adhd200_dx,6,0.005994842503189409,train,0.852054794520548,0.017108715772267746,0.8472093023255813,0.01794514018564053,0.8431031324418392,0.018088723858887535 +flat_mae,reg,logistic,adhd200_dx,6,0.005994842503189409,test,0.676923076923077,0.055877558451148696,0.6612062546537603,0.059828918671433876,0.6597490347490347,0.05796157237630332 +flat_mae,reg,logistic,adhd200_dx,7,0.005994842503189409,train,0.8493150684931506,0.01836767253240961,0.8461933328736373,0.018777056319970703,0.8449807657080052,0.01884741029834851 +flat_mae,reg,logistic,adhd200_dx,7,0.005994842503189409,test,0.6461538461538462,0.06013988427386083,0.6336682185738789,0.06272832357519964,0.6327220077220077,0.06145441333284459 +flat_mae,reg,logistic,adhd200_dx,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,8,166.81005372000556,test,0.5692307692307692,0.06192899923901211,0.5608108108108107,0.06278016735547345,0.5608108108108107,0.06259184375942409 +flat_mae,reg,logistic,adhd200_dx,9,0.005994842503189409,train,0.8328767123287671,0.019436894729156943,0.8282352941176471,0.020154794373076962,0.8253953715576724,0.02021885949897145 +flat_mae,reg,logistic,adhd200_dx,9,0.005994842503189409,test,0.5538461538461539,0.05494818646021243,0.5071895424836601,0.06246969553221379,0.5212355212355213,0.05623060642541482 +flat_mae,reg,logistic,adhd200_dx,10,0.005994842503189409,train,0.8438356164383561,0.019373854774596924,0.8388820481843737,0.020240138985275356,0.8351041094217501,0.02028664499051504 +flat_mae,reg,logistic,adhd200_dx,10,0.005994842503189409,test,0.5384615384615384,0.0592998598040591,0.5125,0.06325059597124541,0.5164092664092664,0.0604683740359011 +flat_mae,reg,logistic,adhd200_dx,11,0.005994842503189409,train,0.8465753424657534,0.017943460335513882,0.8415503875968993,0.018794627231174952,0.8375312938877695,0.018932016661858703 +flat_mae,reg,logistic,adhd200_dx,11,0.005994842503189409,test,0.6153846153846154,0.05867091252342476,0.5966741126830479,0.06273326174835585,0.597007722007722,0.060430670100649425 +flat_mae,reg,logistic,adhd200_dx,12,0.000774263682681127,train,0.6931506849315069,0.023003883099230984,0.6718469047007449,0.025558428836866248,0.6714752396653844,0.024022184599710884 +flat_mae,reg,logistic,adhd200_dx,12,0.000774263682681127,test,0.5384615384615384,0.05065348110376022,0.4724025974025974,0.06052896125734757,0.49903474903474904,0.051635886197197736 +flat_mae,reg,logistic,adhd200_dx,13,0.005994842503189409,train,0.8410958904109589,0.018288958961383273,0.8374039938556068,0.018848344451890098,0.8355468034438542,0.018978998101976112 +flat_mae,reg,logistic,adhd200_dx,13,0.005994842503189409,test,0.49230769230769234,0.06422070671985503,0.4743935309973046,0.0654930033185754,0.47586872586872586,0.06434297931636668 +flat_mae,reg,logistic,adhd200_dx,14,0.000774263682681127,train,0.6986301369863014,0.021878553203099078,0.6736409155937053,0.025125010823076194,0.6741771997313305,0.023106418752609312 +flat_mae,reg,logistic,adhd200_dx,14,0.000774263682681127,test,0.5692307692307692,0.04903904011725047,0.5075757575757576,0.058871001936781554,0.5304054054054055,0.050244855801395864 +flat_mae,reg,logistic,adhd200_dx,15,0.005994842503189409,train,0.8246575342465754,0.01920610008181741,0.8196194712132444,0.019998232981204577,0.8166788789155524,0.02011562944388088 +flat_mae,reg,logistic,adhd200_dx,15,0.005994842503189409,test,0.5846153846153846,0.05862825620838047,0.5699583435432491,0.06166164454896467,0.5699806949806949,0.060320244813334215 +flat_mae,reg,logistic,adhd200_dx,16,0.000774263682681127,train,0.6876712328767123,0.021353421142360714,0.666970802919708,0.02370746757833164,0.6666208707333455,0.022302157620911492 +flat_mae,reg,logistic,adhd200_dx,16,0.000774263682681127,test,0.5692307692307692,0.052061283869172005,0.5289855072463768,0.058192394226506315,0.5390926640926641,0.053037701581549815 +flat_mae,reg,logistic,adhd200_dx,17,0.005994842503189409,train,0.8328767123287671,0.018907368390942723,0.8282352941176471,0.01957556687588961,0.8253953715576724,0.019603359648376333 +flat_mae,reg,logistic,adhd200_dx,17,0.005994842503189409,test,0.5846153846153846,0.062907810824427,0.5644080416976918,0.06621400272113988,0.5656370656370656,0.06389531587307802 +flat_mae,reg,logistic,adhd200_dx,18,0.046415888336127774,train,0.9643835616438357,0.009986688832515658,0.9637024287626698,0.010213814966951276,0.9627068449655004,0.01059304265330742 +flat_mae,reg,logistic,adhd200_dx,18,0.046415888336127774,test,0.6461538461538462,0.05769443278137413,0.6336682185738789,0.06018431588944861,0.6327220077220077,0.05905649982124226 +flat_mae,reg,logistic,adhd200_dx,19,0.005994842503189409,train,0.8410958904109589,0.020248113831105242,0.8352067505293312,0.021407229116759824,0.830524516089638,0.021477069103073395 +flat_mae,reg,logistic,adhd200_dx,19,0.005994842503189409,test,0.6,0.05723834523883857,0.5775,0.06267774487225675,0.5791505791505791,0.059544371149503374 +flat_mae,reg,logistic,adhd200_dx,20,0.005994842503189409,train,0.8383561643835616,0.01761664202357821,0.8335536129725385,0.018414340003076835,0.8302497404897112,0.01854297421856063 +flat_mae,reg,logistic,adhd200_dx,20,0.005994842503189409,test,0.5692307692307692,0.0589403790624362,0.5512820512820513,0.06195930436222086,0.5521235521235521,0.060347731690627224 +flat_mae,reg,logistic,adhd200_dx,21,0.046415888336127774,train,0.958904109589041,0.010047056109173202,0.9579844830364749,0.010337332448600753,0.9557000671673689,0.010861265776467947 +flat_mae,reg,logistic,adhd200_dx,21,0.046415888336127774,test,0.5846153846153846,0.06225943050165599,0.5810455956075435,0.06284237807722765,0.583011583011583,0.06312216438660417 +flat_mae,reg,logistic,adhd200_dx,22,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,22,0.3593813663804626,test,0.47692307692307695,0.06014464615856062,0.4738095238095238,0.06077239593766931,0.4753861003861004,0.061037875479670885 +flat_mae,reg,logistic,adhd200_dx,23,0.005994842503189409,train,0.8383561643835616,0.018228881132346317,0.8338669238187078,0.018986506122137765,0.8309672101117421,0.0191321357399748 +flat_mae,reg,logistic,adhd200_dx,23,0.005994842503189409,test,0.6307692307692307,0.05043011216542902,0.587737843551797,0.06048456809043723,0.5974903474903475,0.05293527413293622 +flat_mae,reg,logistic,adhd200_dx,24,0.005994842503189409,train,0.8465753424657534,0.018326560466712345,0.8424589961770872,0.018944380746755845,0.8396837027538622,0.0190298314661992 +flat_mae,reg,logistic,adhd200_dx,24,0.005994842503189409,test,0.6,0.056850506755377256,0.5626293995859213,0.0642846187971558,0.5704633204633205,0.05863457789573958 +flat_mae,reg,logistic,adhd200_dx,25,0.046415888336127774,train,0.947945205479452,0.011437752096263281,0.9469497035762096,0.011689860577706213,0.9459913293032912,0.011979943038603207 +flat_mae,reg,logistic,adhd200_dx,25,0.046415888336127774,test,0.5076923076923077,0.058790419056008306,0.49317738791423005,0.05936302423351538,0.49372586872586877,0.058751678432713915 +flat_mae,reg,logistic,adhd200_dx,26,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,26,2.782559402207126,test,0.5384615384615384,0.05925213600623841,0.5192307692307693,0.062354385902795434,0.5207528957528957,0.06026781275675587 +flat_mae,reg,logistic,adhd200_dx,27,0.005994842503189409,train,0.8246575342465754,0.019998437919857094,0.8192733799591508,0.02080894413388539,0.8159614092935215,0.020800155772095808 +flat_mae,reg,logistic,adhd200_dx,27,0.005994842503189409,test,0.6461538461538462,0.05521007540327674,0.6091503267973856,0.06494836751535418,0.6153474903474904,0.05787013652801411 +flat_mae,reg,logistic,adhd200_dx,28,0.005994842503189409,train,0.8328767123287671,0.018851908072682177,0.8282352941176471,0.01953190235412677,0.8253953715576724,0.01964757761201847 +flat_mae,reg,logistic,adhd200_dx,28,0.005994842503189409,test,0.6,0.05383059995136837,0.570630081300813,0.060244650784018534,0.5748069498069498,0.055662125194842337 +flat_mae,reg,logistic,adhd200_dx,29,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,29,0.3593813663804626,test,0.5384615384615384,0.06400185648194977,0.5330459770114943,0.06480107813620731,0.5337837837837838,0.06484745155468297 +flat_mae,reg,logistic,adhd200_dx,30,0.046415888336127774,train,0.9616438356164384,0.010230198618945472,0.960752688172043,0.010545999185049977,0.9581272516333883,0.011188220603745226 +flat_mae,reg,logistic,adhd200_dx,30,0.046415888336127774,test,0.5692307692307692,0.061216473012150385,0.5666666666666667,0.06143231101322497,0.5694980694980695,0.061898637622927896 +flat_mae,reg,logistic,adhd200_dx,31,0.046415888336127774,train,0.9506849315068493,0.010866873849900741,0.9497029642332191,0.011133975752161957,0.9484185137693106,0.011518756203494086 +flat_mae,reg,logistic,adhd200_dx,31,0.046415888336127774,test,0.6153846153846154,0.05696178309821254,0.606060606060606,0.05841968047377354,0.6056949806949807,0.057859117320471616 +flat_mae,reg,logistic,adhd200_dx,32,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,32,0.3593813663804626,test,0.5692307692307692,0.06065278814744769,0.5512820512820513,0.06292549070928305,0.5521235521235521,0.061343770375029374 +flat_mae,reg,logistic,adhd200_dx,33,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,33,0.3593813663804626,test,0.49230769230769234,0.06384226123444114,0.4879446168536643,0.06389144396757919,0.4888996138996139,0.06419551407280534 +flat_mae,reg,logistic,adhd200_dx,34,0.046415888336127774,train,0.947945205479452,0.011278575933978434,0.9469497035762096,0.01152593760136019,0.9459913293032912,0.011801773499084418 +flat_mae,reg,logistic,adhd200_dx,34,0.046415888336127774,test,0.5076923076923077,0.05997740008294839,0.5066413662239089,0.059993437663307,0.5111003861003861,0.060077675374945946 +flat_mae,reg,logistic,adhd200_dx,35,0.046415888336127774,train,0.9452054794520548,0.011787893385790381,0.9441144047035767,0.012048149686462119,0.9428466752152409,0.012250583697919678 +flat_mae,reg,logistic,adhd200_dx,35,0.046415888336127774,test,0.5538461538461539,0.056438150679048706,0.5469838981014179,0.05764294600351099,0.5472972972972974,0.05744919939540549 +flat_mae,reg,logistic,adhd200_dx,36,0.046415888336127774,train,0.958904109589041,0.010035955626114049,0.9581808877109096,0.010228487982510989,0.9578524760334616,0.01041611965875285 +flat_mae,reg,logistic,adhd200_dx,36,0.046415888336127774,test,0.5846153846153846,0.05916399832858537,0.5810455956075435,0.05956467190936209,0.583011583011583,0.059940334688042676 +flat_mae,reg,logistic,adhd200_dx,37,0.000774263682681127,train,0.6931506849315069,0.020149997846420072,0.6552654658301289,0.024915985326850527,0.6614306649569519,0.021514298787279385 +flat_mae,reg,logistic,adhd200_dx,37,0.000774263682681127,test,0.6615384615384615,0.0502893403364897,0.6299171842650104,0.05928753195874379,0.6332046332046332,0.05332752116366687 +flat_mae,reg,logistic,adhd200_dx,38,0.005994842503189409,train,0.8356164383561644,0.018614468834501224,0.8302325581395349,0.01946567499088855,0.82638761677963,0.019475302273491486 +flat_mae,reg,logistic,adhd200_dx,38,0.005994842503189409,test,0.6461538461538462,0.053567949439012434,0.6233308138070043,0.05980076862577742,0.6240347490347491,0.05583820215014248 +flat_mae,reg,logistic,adhd200_dx,39,0.000774263682681127,train,0.6931506849315069,0.021508933499920373,0.6618805002315886,0.025417577375739724,0.6650180130671064,0.022812221554592962 +flat_mae,reg,logistic,adhd200_dx,39,0.000774263682681127,test,0.5846153846153846,0.05426561891704272,0.5501153550371699,0.059206131688402164,0.556949806949807,0.055024350332580185 +flat_mae,reg,logistic,adhd200_dx,40,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,40,0.3593813663804626,test,0.6615384615384615,0.05713589323584596,0.6474358974358974,0.06041433782365034,0.6462355212355213,0.05891718792525474 +flat_mae,reg,logistic,adhd200_dx,41,0.000774263682681127,train,0.6904109589041096,0.022591016636077474,0.6641860919549588,0.025751404972561565,0.6654607070892105,0.02368325628482032 +flat_mae,reg,logistic,adhd200_dx,41,0.000774263682681127,test,0.676923076923077,0.05189931992120922,0.6431372549019607,0.06101865227626424,0.6467181467181468,0.05467766397744277 +flat_mae,reg,logistic,adhd200_dx,42,0.046415888336127774,train,0.9643835616438357,0.009651615790684426,0.9637024287626698,0.009864992766165152,0.9627068449655004,0.010200100200431881 +flat_mae,reg,logistic,adhd200_dx,42,0.046415888336127774,test,0.46153846153846156,0.05883002091574288,0.45691095726903797,0.059165422049422815,0.4575289575289575,0.059771995786176216 +flat_mae,reg,logistic,adhd200_dx,43,0.046415888336127774,train,0.9534246575342465,0.011220455544713308,0.9523824141080048,0.011554057331410671,0.9501282286132992,0.012114433437872984 +flat_mae,reg,logistic,adhd200_dx,43,0.046415888336127774,test,0.5692307692307692,0.057303973033671816,0.5376016260162602,0.062417206613820504,0.5434362934362934,0.058366908863648086 +flat_mae,reg,logistic,adhd200_dx,44,0.005994842503189409,train,0.8356164383561644,0.01902894576378881,0.8305687937117039,0.019847450527103953,0.8271050864016609,0.019914064565766765 +flat_mae,reg,logistic,adhd200_dx,44,0.005994842503189409,test,0.49230769230769234,0.05742593686525341,0.4595616024187452,0.060632461014299144,0.4671814671814672,0.057760496547616606 +flat_mae,reg,logistic,adhd200_dx,45,0.000774263682681127,train,0.7013698630136986,0.022216177355943854,0.6715376676986584,0.02641704995226562,0.6737345057092263,0.023698101063073882 +flat_mae,reg,logistic,adhd200_dx,45,0.000774263682681127,test,0.5230769230769231,0.053944314922205056,0.47320261437908495,0.06109088049883308,0.48986486486486486,0.05478862060754676 +flat_mae,reg,logistic,adhd200_dx,46,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,46,0.3593813663804626,test,0.5384615384615384,0.06255143966009331,0.5357142857142857,0.06320972536639737,0.5381274131274132,0.06365331078352039 +flat_mae,reg,logistic,adhd200_dx,47,0.005994842503189409,train,0.8547945205479452,0.0180108338781496,0.8504803641956702,0.018834401339384996,0.8469652561519204,0.019070666405153182 +flat_mae,reg,logistic,adhd200_dx,47,0.005994842503189409,test,0.47692307692307695,0.061228171572265976,0.4738095238095238,0.06093127338508031,0.4753861003861004,0.061317571107960614 +flat_mae,reg,logistic,adhd200_dx,48,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,48,0.3593813663804626,test,0.5230769230769231,0.060708830742961226,0.5189782764382908,0.06129651705770787,0.5202702702702703,0.06186589299950473 +flat_mae,reg,logistic,adhd200_dx,49,0.005994842503189409,train,0.8657534246575342,0.016734680763356508,0.8612156531050912,0.017584884980260895,0.8566739940159981,0.01774479130682696 +flat_mae,reg,logistic,adhd200_dx,49,0.005994842503189409,test,0.4461538461538462,0.057579508189230036,0.4353281853281853,0.05915444699978777,0.4353281853281853,0.05886951507970785 +flat_mae,reg,logistic,adhd200_dx,50,0.005994842503189409,train,0.8273972602739726,0.019184246367483643,0.8222691121571173,0.020053948175563312,0.8191060633815718,0.020190022608357342 +flat_mae,reg,logistic,adhd200_dx,50,0.005994842503189409,test,0.676923076923077,0.052363147074995724,0.6500897205844656,0.06010643935549929,0.6510617760617761,0.05509645355663618 +flat_mae,reg,logistic,adhd200_dx,51,0.005994842503189409,train,0.8246575342465754,0.0195251038182715,0.8196194712132444,0.020259131622451052,0.8166788789155524,0.020264265687298944 +flat_mae,reg,logistic,adhd200_dx,51,0.005994842503189409,test,0.5692307692307692,0.06190667532426646,0.5512820512820513,0.06490161220584327,0.5521235521235521,0.06315533443037899 +flat_mae,reg,logistic,adhd200_dx,52,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,52,0.3593813663804626,test,0.5538461538461539,0.05997960994761016,0.5469838981014179,0.061260909195417816,0.5472972972972974,0.061033812559188896 +flat_mae,reg,logistic,adhd200_dx,53,0.000774263682681127,train,0.6821917808219178,0.021289269170117385,0.6546943302668493,0.024365322432783477,0.6567442144470904,0.02233677159588764 +flat_mae,reg,logistic,adhd200_dx,53,0.000774263682681127,test,0.6,0.048320145381653634,0.5305555555555556,0.06180236575188934,0.5574324324324325,0.05043351649915053 +flat_mae,reg,logistic,adhd200_dx,54,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,54,166.81005372000556,test,0.5076923076923077,0.062434431404891244,0.5066413662239089,0.06237252415954412,0.5111003861003861,0.06342999287806739 +flat_mae,reg,logistic,adhd200_dx,55,0.005994842503189409,train,0.8410958904109589,0.018696849932820125,0.8379317736403724,0.019135119336522444,0.836981742687916,0.01927823502595609 +flat_mae,reg,logistic,adhd200_dx,55,0.005994842503189409,test,0.5076923076923077,0.06011866765974967,0.4871794871794872,0.06212847450160128,0.48938223938223935,0.06064954927094784 +flat_mae,reg,logistic,adhd200_dx,56,0.000774263682681127,train,0.7095890410958904,0.021808574375850417,0.6855085186630251,0.02502037921488973,0.68532087683947,0.023087807580963755 +flat_mae,reg,logistic,adhd200_dx,56,0.000774263682681127,test,0.5692307692307692,0.05996019192251319,0.5512820512820513,0.06254728381811087,0.5521235521235521,0.06084115042623747 +flat_mae,reg,logistic,adhd200_dx,57,0.005994842503189409,train,0.8301369863013699,0.020547734062842136,0.8242138951031568,0.02161238162780415,0.8200983086035294,0.021656842771002688 +flat_mae,reg,logistic,adhd200_dx,57,0.005994842503189409,test,0.6461538461538462,0.05144111127293114,0.6091503267973856,0.05966206756729213,0.6153474903474904,0.053773237010449844 +flat_mae,reg,logistic,adhd200_dx,58,0.005994842503189409,train,0.8410958904109589,0.01876894301746556,0.8371237766972364,0.019419910214088242,0.8348293338218233,0.019596069536425433 +flat_mae,reg,logistic,adhd200_dx,58,0.005994842503189409,test,0.6153846153846154,0.055221460539739545,0.5966741126830479,0.05962344555982288,0.597007722007722,0.0570874458965852 +flat_mae,reg,logistic,adhd200_dx,59,0.046415888336127774,train,0.9534246575342465,0.011117454439168199,0.9524597574336697,0.011406819397751632,0.95084569823533,0.011893672880564218 +flat_mae,reg,logistic,adhd200_dx,59,0.046415888336127774,test,0.5692307692307692,0.06081957797526021,0.564176245210728,0.06178931950813557,0.5651544401544402,0.06224922087650309 +flat_mae,reg,logistic,adhd200_dx,60,0.005994842503189409,train,0.8575342465753425,0.018942788304480363,0.853711925021581,0.019664161849196896,0.8508273798620016,0.01987710839194073 +flat_mae,reg,logistic,adhd200_dx,60,0.005994842503189409,test,0.6307692307692307,0.05237917287891525,0.6036585365853658,0.05925563722947038,0.6061776061776062,0.054893456787041016 +flat_mae,reg,logistic,adhd200_dx,61,0.000774263682681127,train,0.7041095890410959,0.020737457395691758,0.6785085143863769,0.02391262675715972,0.6790315686633693,0.02197120125784859 +flat_mae,reg,logistic,adhd200_dx,61,0.000774263682681127,test,0.5692307692307692,0.05447015142671905,0.5190274841437632,0.06355796055507101,0.5347490347490347,0.056032819364214705 +flat_mae,reg,logistic,adhd200_dx,62,0.046415888336127774,train,0.9452054794520548,0.012307834893872155,0.9442816144593027,0.012504726477097671,0.9442816144593027,0.012514204698747892 +flat_mae,reg,logistic,adhd200_dx,62,0.046415888336127774,test,0.4461538461538462,0.060403722601690794,0.4396551724137931,0.061291014862841844,0.4396718146718147,0.06142091935114261 +flat_mae,reg,logistic,adhd200_dx,63,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,63,0.3593813663804626,test,0.5076923076923077,0.06212473804309421,0.5066413662239089,0.062097024456553664,0.5111003861003861,0.06278937722362286 +flat_mae,reg,logistic,adhd200_dx,64,0.005994842503189409,train,0.8465753424657534,0.018797938105350083,0.8412254536415611,0.019889619289240986,0.8368138242657386,0.020055389484680074 +flat_mae,reg,logistic,adhd200_dx,64,0.005994842503189409,test,0.6307692307692307,0.05649803054639429,0.61,0.06059073715912128,0.6105212355212355,0.058069178585952654 +flat_mae,reg,logistic,adhd200_dx,65,0.046415888336127774,train,0.9726027397260274,0.008519339208629859,0.9720999205038832,0.008696339762162232,0.9714233376076205,0.008999774020472716 +flat_mae,reg,logistic,adhd200_dx,65,0.046415888336127774,test,0.5846153846153846,0.05903116015988916,0.5699583435432491,0.061390466036107504,0.5699806949806949,0.06008105970394124 +flat_mae,reg,logistic,adhd200_dx,66,0.046415888336127774,train,0.9753424657534246,0.008063569909925116,0.9748316362884133,0.008266289441036443,0.973133052451609,0.008805459998552676 +flat_mae,reg,logistic,adhd200_dx,66,0.046415888336127774,test,0.5538461538461539,0.05761737903500909,0.5381034060279344,0.0600527610174893,0.5386100386100386,0.05855683067991894 +flat_mae,reg,logistic,adhd200_dx,67,0.005994842503189409,train,0.8383561643835616,0.017849777430696143,0.832183908045977,0.018919837300011108,0.8273798620015875,0.018929283597690146 +flat_mae,reg,logistic,adhd200_dx,67,0.005994842503189409,test,0.5846153846153846,0.05292579599455075,0.5411764705882354,0.061212230672241644,0.5526061776061776,0.05469305536324634 +flat_mae,reg,logistic,adhd200_dx,68,0.005994842503189409,train,0.8575342465753425,0.01784441001159853,0.853711925021581,0.018475908069162886,0.8508273798620016,0.01858591758264733 +flat_mae,reg,logistic,adhd200_dx,68,0.005994842503189409,test,0.5846153846153846,0.056034570901316576,0.5644080416976918,0.05974306735058969,0.5656370656370656,0.05740834862964048 +flat_mae,reg,logistic,adhd200_dx,69,0.005994842503189409,train,0.8438356164383561,0.018458889826410717,0.8400710282960127,0.01904709781864828,0.8379739879098737,0.019165482864217268 +flat_mae,reg,logistic,adhd200_dx,69,0.005994842503189409,test,0.5846153846153846,0.060061790667818526,0.5699583435432491,0.06262764971944862,0.5699806949806949,0.061152156058274613 +flat_mae,reg,logistic,adhd200_dx,70,0.005994842503189409,train,0.8328767123287671,0.01919081768920775,0.8264952269627899,0.020311935530436035,0.8218080234475178,0.020334822446167453 +flat_mae,reg,logistic,adhd200_dx,70,0.005994842503189409,test,0.6153846153846154,0.05731669314963545,0.5905769715293525,0.06233265725959887,0.5926640926640927,0.05898923085653821 +flat_mae,reg,logistic,adhd200_dx,71,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,71,0.3593813663804626,test,0.5692307692307692,0.06071974616189116,0.5512820512820513,0.06260532795380232,0.5521235521235521,0.06107073231135797 +flat_mae,reg,logistic,adhd200_dx,72,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,72,0.3593813663804626,test,0.5846153846153846,0.059422897186683615,0.5699583435432491,0.06254284183033204,0.5699806949806949,0.060880229238481944 +flat_mae,reg,logistic,adhd200_dx,73,0.000774263682681127,train,0.6684931506849315,0.02227341656284174,0.6427386932640895,0.025473210214952226,0.6446082921169933,0.023413629324218296 +flat_mae,reg,logistic,adhd200_dx,73,0.000774263682681127,test,0.5384615384615384,0.05830972190500528,0.4953416149068323,0.06391722871640286,0.5077220077220077,0.058951260340134246 +flat_mae,reg,logistic,adhd200_dx,74,0.000774263682681127,train,0.7041095890410959,0.021889446718695083,0.6785085143863769,0.02537917472553564,0.6790315686633693,0.02324268627593691 +flat_mae,reg,logistic,adhd200_dx,74,0.000774263682681127,test,0.6153846153846154,0.05456796207672686,0.5834401435529352,0.06084169682198584,0.5883204633204633,0.05640330429031008 +flat_mae,reg,logistic,adhd200_dx,75,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,75,0.3593813663804626,test,0.5384615384615384,0.05976677353626269,0.5330459770114943,0.059845828598145835,0.5337837837837838,0.060001480615529915 +flat_mae,reg,logistic,adhd200_dx,76,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,76,0.3593813663804626,test,0.6153846153846154,0.059645175682937854,0.5905769715293525,0.06489403137494411,0.5926640926640927,0.06110842524287748 +flat_mae,reg,logistic,adhd200_dx,77,0.005994842503189409,train,0.8438356164383561,0.020037318532774337,0.839195863380249,0.02076459246799114,0.835821579043781,0.020738262987465922 +flat_mae,reg,logistic,adhd200_dx,77,0.005994842503189409,test,0.6923076923076923,0.053987506773085614,0.6697154471544715,0.06137076150505989,0.6689189189189189,0.057118956769991965 +flat_mae,reg,logistic,adhd200_dx,78,0.005994842503189409,train,0.8328767123287671,0.019013186207614823,0.8282352941176471,0.019687201725431328,0.8253953715576724,0.019726731469952272 +flat_mae,reg,logistic,adhd200_dx,78,0.005994842503189409,test,0.5076923076923077,0.0591537641291819,0.4871794871794872,0.06047524201294093,0.48938223938223935,0.05913027565690934 +flat_mae,reg,logistic,adhd200_dx,79,0.005994842503189409,train,0.8328767123287671,0.018413511727777408,0.8275755252499439,0.019198761601253653,0.8239604323136106,0.019204447874578333 +flat_mae,reg,logistic,adhd200_dx,79,0.005994842503189409,test,0.5076923076923077,0.06073109611642916,0.5047619047619047,0.06029260321022839,0.5067567567567568,0.06029945585420909 +flat_mae,reg,logistic,adhd200_dx,80,0.005994842503189409,train,0.8410958904109589,0.018820521971731334,0.8362165005879805,0.019671878578854156,0.8326769249557306,0.019839799184064425 +flat_mae,reg,logistic,adhd200_dx,80,0.005994842503189409,test,0.5846153846153846,0.05886219791339146,0.5745454545454545,0.06072757139720401,0.5743243243243243,0.060007174168471525 +flat_mae,reg,logistic,adhd200_dx,81,0.005994842503189409,train,0.8547945205479452,0.018735210543057695,0.8517863025873231,0.019235839552592872,0.8505526042620749,0.019432800176388057 +flat_mae,reg,logistic,adhd200_dx,81,0.005994842503189409,test,0.5692307692307692,0.053370656565649634,0.5289855072463768,0.05981129437090073,0.5390926640926641,0.054631187758657114 +flat_mae,reg,logistic,adhd200_dx,82,0.000774263682681127,train,0.6931506849315069,0.021999778227784098,0.6631065400843882,0.025684082743617716,0.6657354826891373,0.0231894395764421 +flat_mae,reg,logistic,adhd200_dx,82,0.000774263682681127,test,0.6153846153846154,0.051514933780088125,0.5656241646618552,0.06279866509815536,0.5796332046332047,0.05399894580362918 +flat_mae,reg,logistic,adhd200_dx,83,0.005994842503189409,train,0.8328767123287671,0.018587764061080404,0.8275755252499439,0.01950053291147505,0.8239604323136106,0.01963401943209559 +flat_mae,reg,logistic,adhd200_dx,83,0.005994842503189409,test,0.6,0.05793283195003917,0.588206627680312,0.05976528940883872,0.5878378378378378,0.05899779496579273 +flat_mae,reg,logistic,adhd200_dx,84,0.046415888336127774,train,0.9561643835616438,0.010096670663702676,0.9552202183781131,0.010362905304634892,0.9532728827013495,0.010797118430592924 +flat_mae,reg,logistic,adhd200_dx,84,0.046415888336127774,test,0.5230769230769231,0.06017645846879121,0.5062484685126194,0.0623214807941718,0.5072393822393823,0.06107373914203237 +flat_mae,reg,logistic,adhd200_dx,85,0.005994842503189409,train,0.8328767123287671,0.019395848567156905,0.8279113625648279,0.02021663781156445,0.8246779019356415,0.02030876049467095 +flat_mae,reg,logistic,adhd200_dx,85,0.005994842503189409,test,0.6307692307692307,0.05891583807713645,0.61,0.06285386865083226,0.6105212355212355,0.06022115053932282 +flat_mae,reg,logistic,adhd200_dx,86,0.046415888336127774,train,0.958904109589041,0.010600340955509555,0.9579844830364749,0.010915769264785546,0.9557000671673689,0.011515356209390228 +flat_mae,reg,logistic,adhd200_dx,86,0.046415888336127774,test,0.5692307692307692,0.05688839692012785,0.5289855072463768,0.06342460167051371,0.5390926640926641,0.05786385506036985 +flat_mae,reg,logistic,adhd200_dx,87,0.005994842503189409,train,0.852054794520548,0.017697760697928663,0.8475119143405335,0.018523868886891687,0.8438206020638701,0.01875267595949215 +flat_mae,reg,logistic,adhd200_dx,87,0.005994842503189409,test,0.6153846153846154,0.05836101479016004,0.5834401435529352,0.06599732305875308,0.5883204633204633,0.06073882480078708 +flat_mae,reg,logistic,adhd200_dx,88,0.000774263682681127,train,0.7068493150684931,0.02138180979722112,0.6830594441063096,0.024548902388939114,0.6828936923734505,0.02265878667226903 +flat_mae,reg,logistic,adhd200_dx,88,0.000774263682681127,test,0.5384615384615384,0.05932903736414584,0.5045731707317074,0.06447405782726118,0.5120656370656371,0.06031760941275564 +flat_mae,reg,logistic,adhd200_dx,89,0.000774263682681127,train,0.7041095890410959,0.023027964267383006,0.6816243458034503,0.02651407360758627,0.681183977529462,0.024547115086192735 +flat_mae,reg,logistic,adhd200_dx,89,0.000774263682681127,test,0.6153846153846154,0.049110034646277535,0.5656241646618552,0.059052171144390604,0.5796332046332047,0.05096131061461274 +flat_mae,reg,logistic,adhd200_dx,90,0.000774263682681127,train,0.7095890410958904,0.021330241456685103,0.6844620604162589,0.02438218161632779,0.6846034072174392,0.02241355990576653 +flat_mae,reg,logistic,adhd200_dx,90,0.000774263682681127,test,0.6,0.05394521876143367,0.5533826638477801,0.06380061872383266,0.5661196911196912,0.05598443213273479 +flat_mae,reg,logistic,adhd200_dx,91,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,91,0.3593813663804626,test,0.5384615384615384,0.05968085536452557,0.5248538011695907,0.0612706406208825,0.525096525096525,0.06053792829684318 +flat_mae,reg,logistic,adhd200_dx,92,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,92,166.81005372000556,test,0.6461538461538462,0.062148750743155824,0.6336682185738789,0.06487751158922139,0.6327220077220077,0.0635424986011646 +flat_mae,reg,logistic,adhd200_dx,93,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,93,2.782559402207126,test,0.5076923076923077,0.06108993467293277,0.4871794871794872,0.06260656317460578,0.48938223938223935,0.06119617397823978 +flat_mae,reg,logistic,adhd200_dx,94,0.005994842503189409,train,0.8575342465753425,0.01770368815294008,0.85315962121681,0.018408058385548313,0.8493924406179398,0.018472791660247026 +flat_mae,reg,logistic,adhd200_dx,94,0.005994842503189409,test,0.5846153846153846,0.057742714389685194,0.5501153550371699,0.06336118160602006,0.556949806949807,0.05879902037987293 +flat_mae,reg,logistic,adhd200_dx,95,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,95,166.81005372000556,test,0.5692307692307692,0.057956229147878666,0.545,0.0624897453209711,0.5477799227799228,0.059287821165458825 +flat_mae,reg,logistic,adhd200_dx,96,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,96,2.782559402207126,test,0.6307692307692307,0.061109667641789225,0.6285714285714286,0.061459666851921786,0.6322393822393823,0.06183159904032182 +flat_mae,reg,logistic,adhd200_dx,97,0.046415888336127774,train,0.9534246575342465,0.010259173267952209,0.9524597574336697,0.010525770350897152,0.95084569823533,0.010974414298760084 +flat_mae,reg,logistic,adhd200_dx,97,0.046415888336127774,test,0.47692307692307695,0.060326088246105615,0.4385162601626016,0.06252052983127758,0.44932432432432434,0.05995191073353923 +flat_mae,reg,logistic,adhd200_dx,98,0.005994842503189409,train,0.8465753424657534,0.018197658730215817,0.841864207464257,0.019005985978186445,0.8382487635098004,0.019146289760052847 +flat_mae,reg,logistic,adhd200_dx,98,0.005994842503189409,test,0.49230769230769234,0.059041102922621,0.46760982874162327,0.06090617697382251,0.47152509652509655,0.059064431846210144 +flat_mae,reg,logistic,adhd200_dx,99,0.000774263682681127,train,0.7287671232876712,0.02292649558179849,0.7135984275059643,0.025207153557014857,0.7109208035659766,0.02419270638439604 +flat_mae,reg,logistic,adhd200_dx,99,0.000774263682681127,test,0.5384615384615384,0.05622011684852263,0.5045731707317074,0.061782438175695856,0.5120656370656371,0.05740350002888549 +flat_mae,reg,logistic,adhd200_dx,100,0.005994842503189409,train,0.8383561643835616,0.019282579496037792,0.8332287867171588,0.02020520384139456,0.8295322708676803,0.020297449472406335 +flat_mae,reg,logistic,adhd200_dx,100,0.005994842503189409,test,0.5384615384615384,0.05805672802215995,0.5125,0.06186226282145222,0.5164092664092664,0.05894758182194584 diff --git a/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e697997abe01d76460564dc1341b4968ecaa3fad --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:18:07 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adhd200_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic +model: flat_mae +representation: reg +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adhd200_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:10:58 time: 4.3599 data: 3.3965 max mem: 2698 +extract (train) [ 20/151] eta: 0:00:50 time: 0.1878 data: 0.0647 max mem: 3005 +extract (train) [ 40/151] eta: 0:00:29 time: 0.1440 data: 0.0414 max mem: 3005 +extract (train) [ 60/151] eta: 0:00:20 time: 0.1510 data: 0.0458 max mem: 3005 +extract (train) [ 80/151] eta: 0:00:15 time: 0.1784 data: 0.0597 max mem: 3005 +extract (train) [100/151] eta: 0:00:10 time: 0.1734 data: 0.0580 max mem: 3005 +extract (train) [120/151] eta: 0:00:06 time: 0.1570 data: 0.0486 max mem: 3005 +extract (train) [140/151] eta: 0:00:02 time: 0.1510 data: 0.0461 max mem: 3005 +extract (train) [150/151] eta: 0:00:00 time: 0.1461 data: 0.0454 max mem: 3005 +extract (train) Total time: 0:00:28 (0.1920 s / it) +extract (validation) [ 0/32] eta: 0:01:53 time: 3.5483 data: 3.3497 max mem: 3005 +extract (validation) [20/32] eta: 0:00:04 time: 0.1735 data: 0.0573 max mem: 3005 +extract (validation) [31/32] eta: 0:00:00 time: 0.1398 data: 0.0404 max mem: 3005 +extract (validation) Total time: 0:00:08 (0.2759 s / it) +extract (test) [ 0/33] eta: 0:01:58 time: 3.5941 data: 3.4220 max mem: 3005 +extract (test) [20/33] eta: 0:00:04 time: 0.1769 data: 0.0555 max mem: 3005 +extract (test) [32/33] eta: 0:00:00 time: 0.1430 data: 0.0422 max mem: 3005 +extract (test) Total time: 0:00:09 (0.2791 s / it) +feature extraction time: 0:00:47 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adhd200_dx | | 0.00077426 | train | 0.67397 | 0.021351 | 0.64636 | 0.024752 | 0.64875 | 0.022562 | +| flat_mae | reg | logistic | adhd200_dx | | 0.00077426 | test | 0.6 | 0.053886 | 0.55338 | 0.064516 | 0.56612 | 0.056279 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 166.81005372000556, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05912719015296276, "f1": 0.61207925519217, "f1_std": 0.05997563328105542, "bacc": 0.6143822393822393, "bacc_std": 0.060568491092861575} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05451328267647877, "f1": 0.5751633986928104, "f1_std": 0.06405906737450856, "bacc": 0.583976833976834, "bacc_std": 0.056974604337241525} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.056130498834486446, "f1": 0.5905769715293525, "f1_std": 0.06166988768994409, "bacc": 0.5926640926640927, "bacc_std": 0.057954397023842995} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057067583726893814, "f1": 0.6233308138070043, "f1_std": 0.06381744426563256, "bacc": 0.6240347490347491, "bacc_std": 0.05988501528961966} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06179499606328604, "f1": 0.4871794871794872, "f1_std": 0.06514920965399362, "bacc": 0.48938223938223935, "bacc_std": 0.06312646779427494} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.055877558451148696, "f1": 0.6612062546537603, "f1_std": 0.059828918671433876, "bacc": 0.6597490347490347, "bacc_std": 0.05796157237630332} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06013988427386083, "f1": 0.6336682185738789, "f1_std": 0.06272832357519964, "bacc": 0.6327220077220077, "bacc_std": 0.06145441333284459} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06192899923901211, "f1": 0.5608108108108107, "f1_std": 0.06278016735547345, "bacc": 0.5608108108108107, "bacc_std": 0.06259184375942409} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05494818646021243, "f1": 0.5071895424836601, "f1_std": 0.06246969553221379, "bacc": 0.5212355212355213, "bacc_std": 0.05623060642541482} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0592998598040591, "f1": 0.5125, "f1_std": 0.06325059597124541, "bacc": 0.5164092664092664, "bacc_std": 0.0604683740359011} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05867091252342476, "f1": 0.5966741126830479, "f1_std": 0.06273326174835585, "bacc": 0.597007722007722, "bacc_std": 0.060430670100649425} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05065348110376022, "f1": 0.4724025974025974, "f1_std": 0.06052896125734757, "bacc": 0.49903474903474904, "bacc_std": 0.051635886197197736} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06422070671985503, "f1": 0.4743935309973046, "f1_std": 0.0654930033185754, "bacc": 0.47586872586872586, "bacc_std": 0.06434297931636668} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.04903904011725047, "f1": 0.5075757575757576, "f1_std": 0.058871001936781554, "bacc": 0.5304054054054055, "bacc_std": 0.050244855801395864} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05862825620838047, "f1": 0.5699583435432491, "f1_std": 0.06166164454896467, "bacc": 0.5699806949806949, "bacc_std": 0.060320244813334215} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.052061283869172005, "f1": 0.5289855072463768, "f1_std": 0.058192394226506315, "bacc": 0.5390926640926641, "bacc_std": 0.053037701581549815} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.062907810824427, "f1": 0.5644080416976918, "f1_std": 0.06621400272113988, "bacc": 0.5656370656370656, "bacc_std": 0.06389531587307802} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05769443278137413, "f1": 0.6336682185738789, "f1_std": 0.06018431588944861, "bacc": 0.6327220077220077, "bacc_std": 0.05905649982124226} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05723834523883857, "f1": 0.5775, "f1_std": 0.06267774487225675, "bacc": 0.5791505791505791, "bacc_std": 0.059544371149503374} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.0589403790624362, "f1": 0.5512820512820513, "f1_std": 0.06195930436222086, "bacc": 0.5521235521235521, "bacc_std": 0.060347731690627224} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06225943050165599, "f1": 0.5810455956075435, "f1_std": 0.06284237807722765, "bacc": 0.583011583011583, "bacc_std": 0.06312216438660417} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.06014464615856062, "f1": 0.4738095238095238, "f1_std": 0.06077239593766931, "bacc": 0.4753861003861004, "bacc_std": 0.061037875479670885} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05043011216542902, "f1": 0.587737843551797, "f1_std": 0.06048456809043723, "bacc": 0.5974903474903475, "bacc_std": 0.05293527413293622} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.056850506755377256, "f1": 0.5626293995859213, "f1_std": 0.0642846187971558, "bacc": 0.5704633204633205, "bacc_std": 0.05863457789573958} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.058790419056008306, "f1": 0.49317738791423005, "f1_std": 0.05936302423351538, "bacc": 0.49372586872586877, "bacc_std": 0.058751678432713915} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 2.782559402207126, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05925213600623841, "f1": 0.5192307692307693, "f1_std": 0.062354385902795434, "bacc": 0.5207528957528957, "bacc_std": 0.06026781275675587} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05521007540327674, "f1": 0.6091503267973856, "f1_std": 0.06494836751535418, "bacc": 0.6153474903474904, "bacc_std": 0.05787013652801411} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05383059995136837, "f1": 0.570630081300813, "f1_std": 0.060244650784018534, "bacc": 0.5748069498069498, "bacc_std": 0.055662125194842337} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06400185648194977, "f1": 0.5330459770114943, "f1_std": 0.06480107813620731, "bacc": 0.5337837837837838, "bacc_std": 0.06484745155468297} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.061216473012150385, "f1": 0.5666666666666667, "f1_std": 0.06143231101322497, "bacc": 0.5694980694980695, "bacc_std": 0.061898637622927896} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05696178309821254, "f1": 0.606060606060606, "f1_std": 0.05841968047377354, "bacc": 0.6056949806949807, "bacc_std": 0.057859117320471616} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06065278814744769, "f1": 0.5512820512820513, "f1_std": 0.06292549070928305, "bacc": 0.5521235521235521, "bacc_std": 0.061343770375029374} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06384226123444114, "f1": 0.4879446168536643, "f1_std": 0.06389144396757919, "bacc": 0.4888996138996139, "bacc_std": 0.06419551407280534} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05997740008294839, "f1": 0.5066413662239089, "f1_std": 0.059993437663307, "bacc": 0.5111003861003861, "bacc_std": 0.060077675374945946} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.056438150679048706, "f1": 0.5469838981014179, "f1_std": 0.05764294600351099, "bacc": 0.5472972972972974, "bacc_std": 0.05744919939540549} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05916399832858537, "f1": 0.5810455956075435, "f1_std": 0.05956467190936209, "bacc": 0.583011583011583, "bacc_std": 0.059940334688042676} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.0502893403364897, "f1": 0.6299171842650104, "f1_std": 0.05928753195874379, "bacc": 0.6332046332046332, "bacc_std": 0.05332752116366687} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.053567949439012434, "f1": 0.6233308138070043, "f1_std": 0.05980076862577742, "bacc": 0.6240347490347491, "bacc_std": 0.05583820215014248} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05426561891704272, "f1": 0.5501153550371699, "f1_std": 0.059206131688402164, "bacc": 0.556949806949807, "bacc_std": 0.055024350332580185} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05713589323584596, "f1": 0.6474358974358974, "f1_std": 0.06041433782365034, "bacc": 0.6462355212355213, "bacc_std": 0.05891718792525474} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05189931992120922, "f1": 0.6431372549019607, "f1_std": 0.06101865227626424, "bacc": 0.6467181467181468, "bacc_std": 0.05467766397744277} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05883002091574288, "f1": 0.45691095726903797, "f1_std": 0.059165422049422815, "bacc": 0.4575289575289575, "bacc_std": 0.059771995786176216} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.057303973033671816, "f1": 0.5376016260162602, "f1_std": 0.062417206613820504, "bacc": 0.5434362934362934, "bacc_std": 0.058366908863648086} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.05742593686525341, "f1": 0.4595616024187452, "f1_std": 0.060632461014299144, "bacc": 0.4671814671814672, "bacc_std": 0.057760496547616606} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.053944314922205056, "f1": 0.47320261437908495, "f1_std": 0.06109088049883308, "bacc": 0.48986486486486486, "bacc_std": 0.05478862060754676} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06255143966009331, "f1": 0.5357142857142857, "f1_std": 0.06320972536639737, "bacc": 0.5381274131274132, "bacc_std": 0.06365331078352039} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.061228171572265976, "f1": 0.4738095238095238, "f1_std": 0.06093127338508031, "bacc": 0.4753861003861004, "bacc_std": 0.061317571107960614} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.060708830742961226, "f1": 0.5189782764382908, "f1_std": 0.06129651705770787, "bacc": 0.5202702702702703, "bacc_std": 0.06186589299950473} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.4461538461538462, "acc_std": 0.057579508189230036, "f1": 0.4353281853281853, "f1_std": 0.05915444699978777, "bacc": 0.4353281853281853, "bacc_std": 0.05886951507970785} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.052363147074995724, "f1": 0.6500897205844656, "f1_std": 0.06010643935549929, "bacc": 0.6510617760617761, "bacc_std": 0.05509645355663618} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06190667532426646, "f1": 0.5512820512820513, "f1_std": 0.06490161220584327, "bacc": 0.5521235521235521, "bacc_std": 0.06315533443037899} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05997960994761016, "f1": 0.5469838981014179, "f1_std": 0.061260909195417816, "bacc": 0.5472972972972974, "bacc_std": 0.061033812559188896} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.048320145381653634, "f1": 0.5305555555555556, "f1_std": 0.06180236575188934, "bacc": 0.5574324324324325, "bacc_std": 0.05043351649915053} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 166.81005372000556, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.062434431404891244, "f1": 0.5066413662239089, "f1_std": 0.06237252415954412, "bacc": 0.5111003861003861, "bacc_std": 0.06342999287806739} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06011866765974967, "f1": 0.4871794871794872, "f1_std": 0.06212847450160128, "bacc": 0.48938223938223935, "bacc_std": 0.06064954927094784} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05996019192251319, "f1": 0.5512820512820513, "f1_std": 0.06254728381811087, "bacc": 0.5521235521235521, "bacc_std": 0.06084115042623747} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05144111127293114, "f1": 0.6091503267973856, "f1_std": 0.05966206756729213, "bacc": 0.6153474903474904, "bacc_std": 0.053773237010449844} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.055221460539739545, "f1": 0.5966741126830479, "f1_std": 0.05962344555982288, "bacc": 0.597007722007722, "bacc_std": 0.0570874458965852} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06081957797526021, "f1": 0.564176245210728, "f1_std": 0.06178931950813557, "bacc": 0.5651544401544402, "bacc_std": 0.06224922087650309} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05237917287891525, "f1": 0.6036585365853658, "f1_std": 0.05925563722947038, "bacc": 0.6061776061776062, "bacc_std": 0.054893456787041016} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05447015142671905, "f1": 0.5190274841437632, "f1_std": 0.06355796055507101, "bacc": 0.5347490347490347, "bacc_std": 0.056032819364214705} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.4461538461538462, "acc_std": 0.060403722601690794, "f1": 0.4396551724137931, "f1_std": 0.061291014862841844, "bacc": 0.4396718146718147, "bacc_std": 0.06142091935114261} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06212473804309421, "f1": 0.5066413662239089, "f1_std": 0.062097024456553664, "bacc": 0.5111003861003861, "bacc_std": 0.06278937722362286} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05649803054639429, "f1": 0.61, "f1_std": 0.06059073715912128, "bacc": 0.6105212355212355, "bacc_std": 0.058069178585952654} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05903116015988916, "f1": 0.5699583435432491, "f1_std": 0.061390466036107504, "bacc": 0.5699806949806949, "bacc_std": 0.06008105970394124} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05761737903500909, "f1": 0.5381034060279344, "f1_std": 0.0600527610174893, "bacc": 0.5386100386100386, "bacc_std": 0.05855683067991894} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05292579599455075, "f1": 0.5411764705882354, "f1_std": 0.061212230672241644, "bacc": 0.5526061776061776, "bacc_std": 0.05469305536324634} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.056034570901316576, "f1": 0.5644080416976918, "f1_std": 0.05974306735058969, "bacc": 0.5656370656370656, "bacc_std": 0.05740834862964048} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.060061790667818526, "f1": 0.5699583435432491, "f1_std": 0.06262764971944862, "bacc": 0.5699806949806949, "bacc_std": 0.061152156058274613} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05731669314963545, "f1": 0.5905769715293525, "f1_std": 0.06233265725959887, "bacc": 0.5926640926640927, "bacc_std": 0.05898923085653821} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06071974616189116, "f1": 0.5512820512820513, "f1_std": 0.06260532795380232, "bacc": 0.5521235521235521, "bacc_std": 0.06107073231135797} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059422897186683615, "f1": 0.5699583435432491, "f1_std": 0.06254284183033204, "bacc": 0.5699806949806949, "bacc_std": 0.060880229238481944} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05830972190500528, "f1": 0.4953416149068323, "f1_std": 0.06391722871640286, "bacc": 0.5077220077220077, "bacc_std": 0.058951260340134246} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05456796207672686, "f1": 0.5834401435529352, "f1_std": 0.06084169682198584, "bacc": 0.5883204633204633, "bacc_std": 0.05640330429031008} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05976677353626269, "f1": 0.5330459770114943, "f1_std": 0.059845828598145835, "bacc": 0.5337837837837838, "bacc_std": 0.060001480615529915} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.059645175682937854, "f1": 0.5905769715293525, "f1_std": 0.06489403137494411, "bacc": 0.5926640926640927, "bacc_std": 0.06110842524287748} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.053987506773085614, "f1": 0.6697154471544715, "f1_std": 0.06137076150505989, "bacc": 0.6689189189189189, "bacc_std": 0.057118956769991965} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.0591537641291819, "f1": 0.4871794871794872, "f1_std": 0.06047524201294093, "bacc": 0.48938223938223935, "bacc_std": 0.05913027565690934} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06073109611642916, "f1": 0.5047619047619047, "f1_std": 0.06029260321022839, "bacc": 0.5067567567567568, "bacc_std": 0.06029945585420909} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05886219791339146, "f1": 0.5745454545454545, "f1_std": 0.06072757139720401, "bacc": 0.5743243243243243, "bacc_std": 0.060007174168471525} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.053370656565649634, "f1": 0.5289855072463768, "f1_std": 0.05981129437090073, "bacc": 0.5390926640926641, "bacc_std": 0.054631187758657114} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.051514933780088125, "f1": 0.5656241646618552, "f1_std": 0.06279866509815536, "bacc": 0.5796332046332047, "bacc_std": 0.05399894580362918} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05793283195003917, "f1": 0.588206627680312, "f1_std": 0.05976528940883872, "bacc": 0.5878378378378378, "bacc_std": 0.05899779496579273} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06017645846879121, "f1": 0.5062484685126194, "f1_std": 0.0623214807941718, "bacc": 0.5072393822393823, "bacc_std": 0.06107373914203237} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05891583807713645, "f1": 0.61, "f1_std": 0.06285386865083226, "bacc": 0.6105212355212355, "bacc_std": 0.06022115053932282} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05688839692012785, "f1": 0.5289855072463768, "f1_std": 0.06342460167051371, "bacc": 0.5390926640926641, "bacc_std": 0.05786385506036985} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05836101479016004, "f1": 0.5834401435529352, "f1_std": 0.06599732305875308, "bacc": 0.5883204633204633, "bacc_std": 0.06073882480078708} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05932903736414584, "f1": 0.5045731707317074, "f1_std": 0.06447405782726118, "bacc": 0.5120656370656371, "bacc_std": 0.06031760941275564} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.049110034646277535, "f1": 0.5656241646618552, "f1_std": 0.059052171144390604, "bacc": 0.5796332046332047, "bacc_std": 0.05096131061461274} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05394521876143367, "f1": 0.5533826638477801, "f1_std": 0.06380061872383266, "bacc": 0.5661196911196912, "bacc_std": 0.05598443213273479} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05968085536452557, "f1": 0.5248538011695907, "f1_std": 0.0612706406208825, "bacc": 0.525096525096525, "bacc_std": 0.06053792829684318} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 166.81005372000556, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.062148750743155824, "f1": 0.6336682185738789, "f1_std": 0.06487751158922139, "bacc": 0.6327220077220077, "bacc_std": 0.0635424986011646} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 2.782559402207126, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06108993467293277, "f1": 0.4871794871794872, "f1_std": 0.06260656317460578, "bacc": 0.48938223938223935, "bacc_std": 0.06119617397823978} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.057742714389685194, "f1": 0.5501153550371699, "f1_std": 0.06336118160602006, "bacc": 0.556949806949807, "bacc_std": 0.05879902037987293} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 166.81005372000556, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.057956229147878666, "f1": 0.545, "f1_std": 0.0624897453209711, "bacc": 0.5477799227799228, "bacc_std": 0.059287821165458825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 2.782559402207126, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.061109667641789225, "f1": 0.6285714285714286, "f1_std": 0.061459666851921786, "bacc": 0.6322393822393823, "bacc_std": 0.06183159904032182} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.47692307692307695, "acc_std": 0.060326088246105615, "f1": 0.4385162601626016, "f1_std": 0.06252052983127758, "bacc": 0.44932432432432434, "bacc_std": 0.05995191073353923} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.059041102922621, "f1": 0.46760982874162327, "f1_std": 0.06090617697382251, "bacc": 0.47152509652509655, "bacc_std": 0.059064431846210144} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05622011684852263, "f1": 0.5045731707317074, "f1_std": 0.061782438175695856, "bacc": 0.5120656370656371, "bacc_std": 0.05740350002888549} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05805672802215995, "f1": 0.5125, "f1_std": 0.06186226282145222, "bacc": 0.5164092664092664, "bacc_std": 0.05894758182194584} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adhd200_dx | train | 100 | 8.4848 | 36.508 | 0.86847 | 0.10588 | 0.86149 | 0.11436 | 0.86008 | 0.11413 | +| flat_mae | reg | logistic | adhd200_dx | test | 100 | 8.4848 | 36.508 | 0.57292 | 0.055324 | 0.55037 | 0.053969 | 0.5545 | 0.052552 | + + +done! total time: 0:04:35 diff --git a/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..56c725fdc02ddfab4118642b30088750a29f9c33 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..589af9d372f7ebf98949903494d3f42b9481bc52 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,0.046415888336127774,train,0.948509485094851,0.011040865929383411,0.9245293174160629,0.017143044705723018,0.902726828075324,0.021332426422552623 +flat_mae,patch,logistic,adni_ad_vs_cn,,0.046415888336127774,test,0.7073170731707317,0.06307601902534483,0.5729166666666666,0.08363875160017421,0.5729166666666666,0.08409028401452982 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.005994842503189409,train,0.8428184281842819,0.013333439090069048,0.7188977618997583,0.030836059055023627,0.683026542854795,0.026828091241080952 +flat_mae,patch,logistic,adni_ad_vs_cn,1,0.005994842503189409,test,0.7560975609756098,0.04502246118003671,0.569327731092437,0.08846325644436882,0.567741935483871,0.06658169002368436 +flat_mae,patch,logistic,adni_ad_vs_cn,2,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,166.81005372000556,test,0.6341463414634146,0.06668840414994669,0.48621553884711777,0.08217089148509012,0.48709677419354835,0.07956194427027659 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.005994842503189409,train,0.8509485094850948,0.013970397618044913,0.7384563836230782,0.030521903562595654,0.7004684033199112,0.027325828477064867 +flat_mae,patch,logistic,adni_ad_vs_cn,3,0.005994842503189409,test,0.6829268292682927,0.052356236407703115,0.4696517412935323,0.06852727210842277,0.4854838709677419,0.05671375962407351 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,4,166.81005372000556,test,0.8292682926829268,0.05702311751380712,0.7759562841530054,0.0743059160644131,0.7854838709677419,0.07910630336483906 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,21.54434690031882,test,0.7317073170731707,0.04739335063815894,0.5512437810945273,0.08623682513047416,0.5516129032258065,0.06811503277475793 +flat_mae,patch,logistic,adni_ad_vs_cn,6,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,6,166.81005372000556,test,0.7073170731707317,0.06118986747022092,0.5729166666666666,0.08664652328059905,0.5693548387096774,0.0801035523225595 +flat_mae,patch,logistic,adni_ad_vs_cn,7,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,166.81005372000556,test,0.6585365853658537,0.06551682601724676,0.5370967741935484,0.08426213894087536,0.5370967741935484,0.08447522058461866 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,train,0.940379403794038,0.011572468137203213,0.9105868358445678,0.018798815759977144,0.8842345303640398,0.02292107060038656 +flat_mae,patch,logistic,adni_ad_vs_cn,8,0.046415888336127774,test,0.6585365853658537,0.06873506543753315,0.5370967741935484,0.08539773397622372,0.5370967741935484,0.08508963260893429 +flat_mae,patch,logistic,adni_ad_vs_cn,9,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,9,0.3593813663804626,test,0.7073170731707317,0.07022050762177899,0.603225806451613,0.09029296509655962,0.603225806451613,0.09033080025963629 +flat_mae,patch,logistic,adni_ad_vs_cn,10,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,10,166.81005372000556,test,0.7073170731707317,0.05442317716716354,0.5340909090909092,0.08203321286791762,0.535483870967742,0.06925208111539852 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,train,0.9322493224932249,0.011907507522320908,0.8979140153820617,0.01927262442956499,0.8708398389349987,0.022915878779323967 +flat_mae,patch,logistic,adni_ad_vs_cn,11,0.046415888336127774,test,0.6585365853658537,0.051244035940899456,0.4564393939393939,0.06535304781529389,0.4693548387096774,0.056376881317951585 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.005994842503189409,train,0.8509485094850948,0.013565134246314753,0.7281567702961544,0.03329524045308409,0.6883268962116854,0.028454103631492613 +flat_mae,patch,logistic,adni_ad_vs_cn,12,0.005994842503189409,test,0.7804878048780488,0.04869260375987426,0.6328358208955224,0.09116785937192974,0.6177419354838709,0.0754775527408112 +flat_mae,patch,logistic,adni_ad_vs_cn,13,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,13,166.81005372000556,test,0.6341463414634146,0.07607909406947408,0.5684210526315789,0.08249994810136749,0.5887096774193548,0.09312803551540975 +flat_mae,patch,logistic,adni_ad_vs_cn,14,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,0.3593813663804626,test,0.7073170731707317,0.06423504948539725,0.603225806451613,0.08621348977555308,0.603225806451613,0.08790997760397226 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,15,2.782559402207126,test,0.6829268292682927,0.06464796906955825,0.5547201336675021,0.08765067358253364,0.5532258064516129,0.08271757171324166 +flat_mae,patch,logistic,adni_ad_vs_cn,16,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,16,2.782559402207126,test,0.6829268292682927,0.055858152977121135,0.5176470588235295,0.07601738790112753,0.5193548387096775,0.06688838381735823 +flat_mae,patch,logistic,adni_ad_vs_cn,17,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,17,166.81005372000556,test,0.7073170731707317,0.0554919591047439,0.5340909090909092,0.08564650612726285,0.535483870967742,0.07295733960819512 +flat_mae,patch,logistic,adni_ad_vs_cn,18,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,18,166.81005372000556,test,0.7317073170731707,0.07166282010807111,0.6676492262343405,0.08428631351730476,0.6870967741935483,0.09110086781444654 +flat_mae,patch,logistic,adni_ad_vs_cn,19,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,166.81005372000556,test,0.6341463414634146,0.061460994919462414,0.48621553884711777,0.07331069866727306,0.48709677419354835,0.07164357632849101 +flat_mae,patch,logistic,adni_ad_vs_cn,20,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,20,166.81005372000556,test,0.7317073170731707,0.07054628344759833,0.6835087719298245,0.0754365385313211,0.7209677419354839,0.08149425622782842 +flat_mae,patch,logistic,adni_ad_vs_cn,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,21,21.54434690031882,test,0.7804878048780488,0.056181464295607074,0.6660633484162897,0.08765722493494801,0.6516129032258065,0.07999170580052817 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,22,166.81005372000556,test,0.6097560975609756,0.0680598644701517,0.47096774193548385,0.07813000252117863,0.47096774193548385,0.07876236047554379 +flat_mae,patch,logistic,adni_ad_vs_cn,23,0.046415888336127774,train,0.9322493224932249,0.01278918727207735,0.8979140153820617,0.020953374267435966,0.8708398389349987,0.02483338556781645 +flat_mae,patch,logistic,adni_ad_vs_cn,23,0.046415888336127774,test,0.6829268292682927,0.055252834038124206,0.5176470588235295,0.08016996164699491,0.5193548387096775,0.0716445858424843 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.046415888336127774,train,0.9376693766937669,0.011618749347637573,0.9069581328041922,0.018366047763664684,0.8824677459117429,0.022021126089278757 +flat_mae,patch,logistic,adni_ad_vs_cn,24,0.046415888336127774,test,0.6097560975609756,0.06215367341977209,0.4305555555555556,0.0626822754110178,0.43709677419354837,0.06130343450579287 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,25,0.3593813663804626,test,0.6585365853658537,0.06362552176313505,0.5017361111111112,0.08130904041655546,0.5032258064516129,0.07541599229513965 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.3593813663804626,test,0.8048780487804879,0.05858940706193506,0.7152777777777778,0.08806147145580419,0.7016129032258065,0.08543659526581067 +flat_mae,patch,logistic,adni_ad_vs_cn,27,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,2.782559402207126,test,0.7560975609756098,0.05487629265482837,0.6117424242424243,0.09228036874805785,0.6016129032258064,0.07960745158309385 +flat_mae,patch,logistic,adni_ad_vs_cn,28,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,21.54434690031882,test,0.6829268292682927,0.06404510234084179,0.5547201336675021,0.08312755389632737,0.5532258064516129,0.0801538901627401 +flat_mae,patch,logistic,adni_ad_vs_cn,29,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,29,21.54434690031882,test,0.7317073170731707,0.06854439674259788,0.6479313036690086,0.08417648904715533,0.6532258064516129,0.08696589276056468 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,test,0.5853658536585366,0.07590800343262823,0.5108771929824562,0.07784168731718742,0.5225806451612903,0.08724881973565803 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.005994842503189409,train,0.8428184281842819,0.013434480952278009,0.7152171598892911,0.030858243881963097,0.6789793738187198,0.02595129559175582 +flat_mae,patch,logistic,adni_ad_vs_cn,31,0.005994842503189409,test,0.6829268292682927,0.03914505734540004,0.4057971014492754,0.0139907045625245,0.45161290322580644,0.025886247599377445 +flat_mae,patch,logistic,adni_ad_vs_cn,32,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,32,166.81005372000556,test,0.7317073170731707,0.06463184533409903,0.6479313036690086,0.08426830500014607,0.6532258064516129,0.08699778723847669 +flat_mae,patch,logistic,adni_ad_vs_cn,33,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,2.782559402207126,test,0.7073170731707317,0.06338601605661025,0.603225806451613,0.07965641736610014,0.603225806451613,0.07952548371329474 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.046415888336127774,train,0.94579945799458,0.01029307393963668,0.9179416473937021,0.016919359107112272,0.8877680992686334,0.021314592430114958 +flat_mae,patch,logistic,adni_ad_vs_cn,34,0.046415888336127774,test,0.7073170731707317,0.059065818962077514,0.5729166666666666,0.08563461499063393,0.5693548387096774,0.07974128301225913 +flat_mae,patch,logistic,adni_ad_vs_cn,35,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,35,21.54434690031882,test,0.7073170731707317,0.06288665762558122,0.5729166666666666,0.08976015685754976,0.5693548387096774,0.08433281029836477 +flat_mae,patch,logistic,adni_ad_vs_cn,36,0.046415888336127774,train,0.9376693766937669,0.011172565854559682,0.9051784816490699,0.018492131101985294,0.8743734078395924,0.022579187479469208 +flat_mae,patch,logistic,adni_ad_vs_cn,36,0.046415888336127774,test,0.6097560975609756,0.07026429243360896,0.47096774193548385,0.07609385332612155,0.47096774193548385,0.07633982156043655 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.005994842503189409,train,0.8401084010840109,0.012410502752901252,0.7083863535904202,0.02981980686218573,0.6731654203303477,0.024818047032173565 +flat_mae,patch,logistic,adni_ad_vs_cn,37,0.005994842503189409,test,0.7560975609756098,0.03401826153387372,0.5119047619047619,0.08086225578081471,0.5338709677419355,0.05327733761585617 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,38,166.81005372000556,test,0.7560975609756098,0.05286679747096855,0.6117424242424243,0.0905416249653186,0.6016129032258064,0.07793982703931152 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.3593813663804626,test,0.7317073170731707,0.06401152483978255,0.6232247284878863,0.08848468057128013,0.6193548387096774,0.08699161267834256 +flat_mae,patch,logistic,adni_ad_vs_cn,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,40,166.81005372000556,test,0.6585365853658537,0.06882155840036153,0.5651515151515152,0.08124083485239827,0.5709677419354839,0.08677954768228356 +flat_mae,patch,logistic,adni_ad_vs_cn,41,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,41,166.81005372000556,test,0.6829268292682927,0.06492820361009007,0.5547201336675021,0.0852111783977531,0.5532258064516129,0.08194699404802329 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,test,0.7317073170731707,0.06664571552603658,0.6676492262343405,0.07835154119927978,0.6870967741935483,0.08590624054404936 +flat_mae,patch,logistic,adni_ad_vs_cn,43,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,2.782559402207126,test,0.7317073170731707,0.04787975718532954,0.5512437810945273,0.08302345291099689,0.5516129032258065,0.06613971424347187 +flat_mae,patch,logistic,adni_ad_vs_cn,44,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,44,166.81005372000556,test,0.7073170731707317,0.06702275710723783,0.603225806451613,0.08666705778645901,0.603225806451613,0.08658106214745026 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.046415888336127774,train,0.9349593495934959,0.011793782627158423,0.9005748158792886,0.019887575044750284,0.8685594543512203,0.024178258889175297 +flat_mae,patch,logistic,adni_ad_vs_cn,45,0.046415888336127774,test,0.7317073170731707,0.05878182368687441,0.5918552036199095,0.09166717346925447,0.5854838709677419,0.082473499732754 +flat_mae,patch,logistic,adni_ad_vs_cn,46,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,166.81005372000556,test,0.7073170731707317,0.062745057942855,0.5729166666666666,0.0862324728353296,0.5693548387096774,0.07915056181736276 +flat_mae,patch,logistic,adni_ad_vs_cn,47,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,166.81005372000556,test,0.6829268292682927,0.07097282703454492,0.5839188134270101,0.08753745869971474,0.5870967741935484,0.09062352921767507 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,48,0.3593813663804626,test,0.6341463414634146,0.060508965614119205,0.48621553884711777,0.07301989469590019,0.48709677419354835,0.07002237036631195 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.046415888336127774,train,0.9295392953929539,0.012223724362231165,0.8943298969072165,0.019621278086218823,0.8690730544827019,0.022859009321715574 +flat_mae,patch,logistic,adni_ad_vs_cn,49,0.046415888336127774,test,0.7560975609756098,0.052703947929023075,0.6117424242424243,0.09244397827587626,0.6016129032258064,0.07959798907462579 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,train,0.9349593495934959,0.011862491643836391,0.9015299768724425,0.019570447218162017,0.8726066233872956,0.023791997615052955 +flat_mae,patch,logistic,adni_ad_vs_cn,50,0.046415888336127774,test,0.7804878048780488,0.05672598171724005,0.6917293233082706,0.08193854857201946,0.685483870967742,0.08120947560598941 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,51,0.3593813663804626,test,0.7804878048780488,0.058791700175434156,0.6917293233082706,0.08468903101124754,0.685483870967742,0.08374840946196499 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.005994842503189409,train,0.8401084010840109,0.013394745871288386,0.7121951219512195,0.030642378920957315,0.6772125893664229,0.02608978868678462 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.005994842503189409,test,0.7317073170731707,0.051459507423057174,0.5512437810945273,0.0888722526182378,0.5516129032258065,0.0709066959584056 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,train,0.9376693766937669,0.011937773655374182,0.9060808941514966,0.019473541353908566,0.8784205768756677,0.023599340778884016 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,test,0.7317073170731707,0.06244771281013527,0.6479313036690086,0.08043511149955465,0.6532258064516129,0.0830901126236862 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.046415888336127774,train,0.9322493224932249,0.011996033451119614,0.8988675356567306,0.0193403656157455,0.874887007971074,0.023343562323938565 +flat_mae,patch,logistic,adni_ad_vs_cn,54,0.046415888336127774,test,0.7560975609756098,0.053165696785555584,0.6117424242424243,0.08865824274927217,0.6016129032258064,0.0768207012157254 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,55,0.3593813663804626,test,0.6829268292682927,0.06523122283903277,0.5839188134270101,0.08272359347867302,0.5870967741935484,0.08497754487012439 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.005994842503189409,train,0.8455284552845529,0.01189785108608498,0.7182715619432873,0.029056545460526304,0.6807461582710166,0.024536144498459707 +flat_mae,patch,logistic,adni_ad_vs_cn,56,0.005994842503189409,test,0.7317073170731707,0.02680992650920385,0.4225352112676056,0.009132940949010071,0.4838709677419355,0.01772914494963481 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,train,0.940379403794038,0.011401685328545373,0.9097358121330723,0.01890053291271651,0.8801873613279645,0.023517744049241274 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.046415888336127774,test,0.7317073170731707,0.04952120547594334,0.5512437810945273,0.08566140757860223,0.5516129032258065,0.06826491359930138 +flat_mae,patch,logistic,adni_ad_vs_cn,58,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,58,166.81005372000556,test,0.7073170731707317,0.06864874079927032,0.6272727272727273,0.08252659226625542,0.6370967741935484,0.08796832652963539 +flat_mae,patch,logistic,adni_ad_vs_cn,59,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,2.782559402207126,test,0.6585365853658537,0.06102210909931915,0.5017361111111112,0.07600933764227139,0.5032258064516129,0.0698301569671754 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,60,166.81005372000556,test,0.6829268292682927,0.0727095056984801,0.6072218128224024,0.08453496934532946,0.6209677419354839,0.09222880519558067 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,train,0.948509485094851,0.010963771594270423,0.9231393270991153,0.017583259085987506,0.8976292217930808,0.022211809932280252 +flat_mae,patch,logistic,adni_ad_vs_cn,61,0.046415888336127774,test,0.6829268292682927,0.04044958525195683,0.4057971014492754,0.01450810209912103,0.45161290322580644,0.026748919279519844 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.046415888336127774,train,0.9512195121951219,0.01056809250928554,0.9275207333042339,0.016761939941927987,0.9034431752814529,0.02131698313170885 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.046415888336127774,test,0.6097560975609756,0.07468195503661124,0.5030303030303029,0.08091250999269203,0.5048387096774194,0.08618468155088267 +flat_mae,patch,logistic,adni_ad_vs_cn,63,0.046415888336127774,train,0.94579945799458,0.01089683800816078,0.9187153053132435,0.017705003051047,0.8918152683047087,0.02224261616308509 +flat_mae,patch,logistic,adni_ad_vs_cn,63,0.046415888336127774,test,0.7317073170731707,0.049243920559558875,0.5512437810945273,0.0880732552511037,0.5516129032258065,0.0711191856252294 +flat_mae,patch,logistic,adni_ad_vs_cn,64,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,64,2.782559402207126,test,0.6341463414634146,0.0736259659857911,0.5684210526315789,0.07670697563376787,0.5887096774193548,0.08587042697534582 +flat_mae,patch,logistic,adni_ad_vs_cn,65,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,65,21.54434690031882,test,0.7560975609756098,0.05961005548605507,0.6440972222222222,0.08981731821684287,0.635483870967742,0.08400939414047785 +flat_mae,patch,logistic,adni_ad_vs_cn,66,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,66,166.81005372000556,test,0.7804878048780488,0.0644179356566579,0.7280766396462786,0.07442564178159215,0.7532258064516129,0.07854384142639427 +flat_mae,patch,logistic,adni_ad_vs_cn,67,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,67,2.782559402207126,test,0.6585365853658537,0.07359945942951265,0.5651515151515152,0.08451940586294561,0.5709677419354839,0.08931851660741467 +flat_mae,patch,logistic,adni_ad_vs_cn,68,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,68,166.81005372000556,test,0.5609756097560976,0.07399167115531945,0.4409090909090909,0.07238909857378104,0.43870967741935485,0.07649569465485236 +flat_mae,patch,logistic,adni_ad_vs_cn,69,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,1291.5496650148827,test,0.6829268292682927,0.06272184423468334,0.5547201336675021,0.08166902481633125,0.5532258064516129,0.07925072182301751 +flat_mae,patch,logistic,adni_ad_vs_cn,70,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,70,2.782559402207126,test,0.6829268292682927,0.06483972827579738,0.5547201336675021,0.08399484540717062,0.5532258064516129,0.08193459302284316 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,train,0.943089430894309,0.011569594171223128,0.9142477729209317,0.01875740331890208,0.8860013148163366,0.023095696965687293 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,test,0.7560975609756098,0.054900461547857306,0.6117424242424243,0.09090228034754227,0.6016129032258064,0.0791454128068474 +flat_mae,patch,logistic,adni_ad_vs_cn,72,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,0.3593813663804626,test,0.6585365853658537,0.06756185611823866,0.5370967741935484,0.08100025649039941,0.5370967741935484,0.08057239271774314 +flat_mae,patch,logistic,adni_ad_vs_cn,73,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,73,21.54434690031882,test,0.7073170731707317,0.07154453067234084,0.646551724137931,0.07907284055748377,0.6709677419354838,0.08696520983200022 +flat_mae,patch,logistic,adni_ad_vs_cn,74,0.005994842503189409,train,0.8482384823848238,0.013992538355088164,0.7285909425239046,0.032319073759439154,0.6906072807954639,0.028018829461419006 +flat_mae,patch,logistic,adni_ad_vs_cn,74,0.005994842503189409,test,0.7560975609756098,0.03473290625499833,0.5119047619047619,0.07645626350987944,0.5338709677419355,0.05009515139759923 +flat_mae,patch,logistic,adni_ad_vs_cn,75,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,75,166.81005372000556,test,0.6097560975609756,0.07060516856069138,0.5030303030303029,0.07883730121741953,0.5048387096774194,0.08354082784335683 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,test,0.6097560975609756,0.07509297825829109,0.5287356321839081,0.08179981748059816,0.5387096774193548,0.09043367499643638 +flat_mae,patch,logistic,adni_ad_vs_cn,77,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,77,2.782559402207126,test,0.6585365853658537,0.06972750565319469,0.5651515151515152,0.08196239501559577,0.5709677419354839,0.08767476294962326 +flat_mae,patch,logistic,adni_ad_vs_cn,78,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,78,2.782559402207126,test,0.6097560975609756,0.06912324215191233,0.47096774193548385,0.07694862480163871,0.47096774193548385,0.07774664816394601 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.046415888336127774,train,0.9376693766937669,0.011458834221721859,0.9060808941514966,0.018551906451358804,0.8784205768756677,0.022510480673977373 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.046415888336127774,test,0.7317073170731707,0.0641231711839712,0.6232247284878863,0.08905028013585563,0.6193548387096774,0.08746281808486686 +flat_mae,patch,logistic,adni_ad_vs_cn,80,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,80,21.54434690031882,test,0.5853658536585366,0.07049161944273749,0.4863669859985261,0.0763053522039931,0.4887096774193548,0.08254267492747702 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,81,0.3593813663804626,test,0.7560975609756098,0.0447249775505221,0.569327731092437,0.08740950044414621,0.567741935483871,0.06661006758004145 +flat_mae,patch,logistic,adni_ad_vs_cn,82,0.046415888336127774,train,0.940379403794038,0.011125610210755784,0.9097358121330723,0.018417139249880463,0.8801873613279645,0.0227035634206034 +flat_mae,patch,logistic,adni_ad_vs_cn,82,0.046415888336127774,test,0.7560975609756098,0.04802525114118927,0.569327731092437,0.09272213194674339,0.567741935483871,0.07049205761860616 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,test,0.7317073170731707,0.04723150422204167,0.5512437810945273,0.08193929908917189,0.5516129032258065,0.06515398841234034 +flat_mae,patch,logistic,adni_ad_vs_cn,84,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,84,166.81005372000556,test,0.6585365853658537,0.0650690568049059,0.5370967741935484,0.08045180704139074,0.5370967741935484,0.0797625312686405 +flat_mae,patch,logistic,adni_ad_vs_cn,85,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,85,1291.5496650148827,test,0.7073170731707317,0.07123748520292447,0.646551724137931,0.08020594902554645,0.6709677419354838,0.08829432051009413 +flat_mae,patch,logistic,adni_ad_vs_cn,86,0.005994842503189409,train,0.8590785907859079,0.013560402614302898,0.7511671335200747,0.03012525047826364,0.709815925712877,0.026939692148568672 +flat_mae,patch,logistic,adni_ad_vs_cn,86,0.005994842503189409,test,0.6341463414634146,0.04853509006153569,0.3880597014925373,0.018294029348801488,0.41935483870967744,0.03209578536327359 +flat_mae,patch,logistic,adni_ad_vs_cn,87,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,87,21.54434690031882,test,0.7073170731707317,0.06952674216633573,0.6272727272727273,0.08540681330609344,0.6370967741935484,0.09093753896909956 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,88,0.3593813663804626,test,0.7317073170731707,0.06387918027662691,0.6232247284878863,0.09209906093785253,0.6193548387096774,0.08989276094515837 +flat_mae,patch,logistic,adni_ad_vs_cn,89,0.046415888336127774,train,0.9349593495934959,0.012100322896734713,0.9024583663758922,0.019441034431656092,0.8766537924233708,0.02353258116682314 +flat_mae,patch,logistic,adni_ad_vs_cn,89,0.046415888336127774,test,0.7804878048780488,0.05085526698047083,0.6328358208955224,0.09584026502990133,0.6177419354838709,0.07953648264010438 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,train,0.943089430894309,0.010232390543380102,0.9142477729209317,0.016666539633554696,0.8860013148163366,0.020675627372453372 +flat_mae,patch,logistic,adni_ad_vs_cn,90,0.046415888336127774,test,0.6097560975609756,0.05423800196018431,0.3787878787878788,0.02149163787430754,0.4032258064516129,0.035867065812379945 +flat_mae,patch,logistic,adni_ad_vs_cn,91,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,91,166.81005372000556,test,0.7317073170731707,0.06723579398550592,0.6479313036690086,0.08403309421209965,0.6532258064516129,0.08909247402670883 +flat_mae,patch,logistic,adni_ad_vs_cn,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,92,21.54434690031882,test,0.6341463414634146,0.06585177955765639,0.48621553884711777,0.08000140515083039,0.48709677419354835,0.07740177347413099 +flat_mae,patch,logistic,adni_ad_vs_cn,93,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,93,2.782559402207126,test,0.6829268292682927,0.07425691370235935,0.6072218128224024,0.08775662440527096,0.6209677419354839,0.09431600060892999 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,train,0.948509485094851,0.01044841942577216,0.9245293174160629,0.01605220096406571,0.9057235598652313,0.019726115141752956 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,test,0.6585365853658537,0.06468246698140628,0.5017361111111112,0.08409938277984262,0.5032258064516129,0.07851810610599587 +flat_mae,patch,logistic,adni_ad_vs_cn,95,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,95,2.782559402207126,test,0.6097560975609756,0.07519595657867698,0.5494505494505495,0.08067736287502543,0.5725806451612903,0.09301943918664149 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,96,21.54434690031882,test,0.6829268292682927,0.05794210324945799,0.5176470588235295,0.08185176466887371,0.5193548387096775,0.0727472550089854 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,train,0.9322493224932249,0.011362150514668275,0.8969331322272499,0.01874169843208667,0.8667926698989235,0.022417158978658886 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.046415888336127774,test,0.7804878048780488,0.05154994459382486,0.6328358208955224,0.09320366438953274,0.6177419354838709,0.07744247638604625 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.005994842503189409,train,0.8401084010840109,0.012872119801664165,0.7121951219512195,0.02975728286938287,0.6772125893664229,0.025367122846439 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.005994842503189409,test,0.7073170731707317,0.05129842933145111,0.5340909090909092,0.08268764685001166,0.535483870967742,0.0699465245421493 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,train,0.948509485094851,0.0096747876386284,0.9224146516903668,0.015789705885230668,0.8935820527570055,0.020019134849404457 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,test,0.7317073170731707,0.051518546356427386,0.5512437810945273,0.0871117988477528,0.5516129032258065,0.06942776503497965 +flat_mae,patch,logistic,adni_ad_vs_cn,100,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,100,2.782559402207126,test,0.7804878048780488,0.059041239280290585,0.6917293233082706,0.084108048427422,0.685483870967742,0.08479293374393425 diff --git a/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..63b794b3e23d31e9d06a6f40031499eac2f6dcae --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:44:15 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:13:17 time: 4.8635 data: 3.6881 max mem: 2698 +extract (train) [ 20/164] eta: 0:00:59 time: 0.1872 data: 0.0659 max mem: 3005 +extract (train) [ 40/164] eta: 0:00:36 time: 0.1663 data: 0.0541 max mem: 3005 +extract (train) [ 60/164] eta: 0:00:26 time: 0.1930 data: 0.0706 max mem: 3005 +extract (train) [ 80/164] eta: 0:00:20 time: 0.1878 data: 0.0665 max mem: 3005 +extract (train) [100/164] eta: 0:00:14 time: 0.1894 data: 0.0672 max mem: 3005 +extract (train) [120/164] eta: 0:00:09 time: 0.1758 data: 0.0585 max mem: 3005 +extract (train) [140/164] eta: 0:00:05 time: 0.1712 data: 0.0576 max mem: 3005 +extract (train) [160/164] eta: 0:00:00 time: 0.1731 data: 0.0581 max mem: 3005 +extract (train) [163/164] eta: 0:00:00 time: 0.1728 data: 0.0584 max mem: 3005 +extract (train) Total time: 0:00:34 (0.2111 s / it) +extract (validation) [ 0/21] eta: 0:01:19 time: 3.7712 data: 3.6461 max mem: 3005 +extract (validation) [20/21] eta: 0:00:00 time: 0.1751 data: 0.0559 max mem: 3005 +extract (validation) Total time: 0:00:07 (0.3622 s / it) +extract (test) [ 0/21] eta: 0:01:21 time: 3.8803 data: 3.7441 max mem: 3005 +extract (test) [20/21] eta: 0:00:00 time: 0.1822 data: 0.0610 max mem: 3005 +extract (test) Total time: 0:00:07 (0.3744 s / it) +feature extraction time: 0:00:50 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.046416 | train | 0.94851 | 0.011041 | 0.92453 | 0.017143 | 0.90273 | 0.021332 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.046416 | test | 0.70732 | 0.063076 | 0.57292 | 0.083639 | 0.57292 | 0.08409 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04502246118003671, "f1": 0.569327731092437, "f1_std": 0.08846325644436882, "bacc": 0.567741935483871, "bacc_std": 0.06658169002368436} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06668840414994669, "f1": 0.48621553884711777, "f1_std": 0.08217089148509012, "bacc": 0.48709677419354835, "bacc_std": 0.07956194427027659} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.052356236407703115, "f1": 0.4696517412935323, "f1_std": 0.06852727210842277, "bacc": 0.4854838709677419, "bacc_std": 0.05671375962407351} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05702311751380712, "f1": 0.7759562841530054, "f1_std": 0.0743059160644131, "bacc": 0.7854838709677419, "bacc_std": 0.07910630336483906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04739335063815894, "f1": 0.5512437810945273, "f1_std": 0.08623682513047416, "bacc": 0.5516129032258065, "bacc_std": 0.06811503277475793} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06118986747022092, "f1": 0.5729166666666666, "f1_std": 0.08664652328059905, "bacc": 0.5693548387096774, "bacc_std": 0.0801035523225595} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06551682601724676, "f1": 0.5370967741935484, "f1_std": 0.08426213894087536, "bacc": 0.5370967741935484, "bacc_std": 0.08447522058461866} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06873506543753315, "f1": 0.5370967741935484, "f1_std": 0.08539773397622372, "bacc": 0.5370967741935484, "bacc_std": 0.08508963260893429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07022050762177899, "f1": 0.603225806451613, "f1_std": 0.09029296509655962, "bacc": 0.603225806451613, "bacc_std": 0.09033080025963629} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05442317716716354, "f1": 0.5340909090909092, "f1_std": 0.08203321286791762, "bacc": 0.535483870967742, "bacc_std": 0.06925208111539852} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.051244035940899456, "f1": 0.4564393939393939, "f1_std": 0.06535304781529389, "bacc": 0.4693548387096774, "bacc_std": 0.056376881317951585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04869260375987426, "f1": 0.6328358208955224, "f1_std": 0.09116785937192974, "bacc": 0.6177419354838709, "bacc_std": 0.0754775527408112} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07607909406947408, "f1": 0.5684210526315789, "f1_std": 0.08249994810136749, "bacc": 0.5887096774193548, "bacc_std": 0.09312803551540975} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06423504948539725, "f1": 0.603225806451613, "f1_std": 0.08621348977555308, "bacc": 0.603225806451613, "bacc_std": 0.08790997760397226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06464796906955825, "f1": 0.5547201336675021, "f1_std": 0.08765067358253364, "bacc": 0.5532258064516129, "bacc_std": 0.08271757171324166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.055858152977121135, "f1": 0.5176470588235295, "f1_std": 0.07601738790112753, "bacc": 0.5193548387096775, "bacc_std": 0.06688838381735823} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0554919591047439, "f1": 0.5340909090909092, "f1_std": 0.08564650612726285, "bacc": 0.535483870967742, "bacc_std": 0.07295733960819512} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.07166282010807111, "f1": 0.6676492262343405, "f1_std": 0.08428631351730476, "bacc": 0.6870967741935483, "bacc_std": 0.09110086781444654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.061460994919462414, "f1": 0.48621553884711777, "f1_std": 0.07331069866727306, "bacc": 0.48709677419354835, "bacc_std": 0.07164357632849101} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.07054628344759833, "f1": 0.6835087719298245, "f1_std": 0.0754365385313211, "bacc": 0.7209677419354839, "bacc_std": 0.08149425622782842} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.056181464295607074, "f1": 0.6660633484162897, "f1_std": 0.08765722493494801, "bacc": 0.6516129032258065, "bacc_std": 0.07999170580052817} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.0680598644701517, "f1": 0.47096774193548385, "f1_std": 0.07813000252117863, "bacc": 0.47096774193548385, "bacc_std": 0.07876236047554379} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.055252834038124206, "f1": 0.5176470588235295, "f1_std": 0.08016996164699491, "bacc": 0.5193548387096775, "bacc_std": 0.0716445858424843} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06215367341977209, "f1": 0.4305555555555556, "f1_std": 0.0626822754110178, "bacc": 0.43709677419354837, "bacc_std": 0.06130343450579287} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06362552176313505, "f1": 0.5017361111111112, "f1_std": 0.08130904041655546, "bacc": 0.5032258064516129, "bacc_std": 0.07541599229513965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05858940706193506, "f1": 0.7152777777777778, "f1_std": 0.08806147145580419, "bacc": 0.7016129032258065, "bacc_std": 0.08543659526581067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05487629265482837, "f1": 0.6117424242424243, "f1_std": 0.09228036874805785, "bacc": 0.6016129032258064, "bacc_std": 0.07960745158309385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06404510234084179, "f1": 0.5547201336675021, "f1_std": 0.08312755389632737, "bacc": 0.5532258064516129, "bacc_std": 0.0801538901627401} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06854439674259788, "f1": 0.6479313036690086, "f1_std": 0.08417648904715533, "bacc": 0.6532258064516129, "bacc_std": 0.08696589276056468} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07590800343262823, "f1": 0.5108771929824562, "f1_std": 0.07784168731718742, "bacc": 0.5225806451612903, "bacc_std": 0.08724881973565803} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.03914505734540004, "f1": 0.4057971014492754, "f1_std": 0.0139907045625245, "bacc": 0.45161290322580644, "bacc_std": 0.025886247599377445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06463184533409903, "f1": 0.6479313036690086, "f1_std": 0.08426830500014607, "bacc": 0.6532258064516129, "bacc_std": 0.08699778723847669} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06338601605661025, "f1": 0.603225806451613, "f1_std": 0.07965641736610014, "bacc": 0.603225806451613, "bacc_std": 0.07952548371329474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.059065818962077514, "f1": 0.5729166666666666, "f1_std": 0.08563461499063393, "bacc": 0.5693548387096774, "bacc_std": 0.07974128301225913} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06288665762558122, "f1": 0.5729166666666666, "f1_std": 0.08976015685754976, "bacc": 0.5693548387096774, "bacc_std": 0.08433281029836477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07026429243360896, "f1": 0.47096774193548385, "f1_std": 0.07609385332612155, "bacc": 0.47096774193548385, "bacc_std": 0.07633982156043655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.03401826153387372, "f1": 0.5119047619047619, "f1_std": 0.08086225578081471, "bacc": 0.5338709677419355, "bacc_std": 0.05327733761585617} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05286679747096855, "f1": 0.6117424242424243, "f1_std": 0.0905416249653186, "bacc": 0.6016129032258064, "bacc_std": 0.07793982703931152} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06401152483978255, "f1": 0.6232247284878863, "f1_std": 0.08848468057128013, "bacc": 0.6193548387096774, "bacc_std": 0.08699161267834256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06882155840036153, "f1": 0.5651515151515152, "f1_std": 0.08124083485239827, "bacc": 0.5709677419354839, "bacc_std": 0.08677954768228356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06492820361009007, "f1": 0.5547201336675021, "f1_std": 0.0852111783977531, "bacc": 0.5532258064516129, "bacc_std": 0.08194699404802329} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06664571552603658, "f1": 0.6676492262343405, "f1_std": 0.07835154119927978, "bacc": 0.6870967741935483, "bacc_std": 0.08590624054404936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04787975718532954, "f1": 0.5512437810945273, "f1_std": 0.08302345291099689, "bacc": 0.5516129032258065, "bacc_std": 0.06613971424347187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06702275710723783, "f1": 0.603225806451613, "f1_std": 0.08666705778645901, "bacc": 0.603225806451613, "bacc_std": 0.08658106214745026} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05878182368687441, "f1": 0.5918552036199095, "f1_std": 0.09166717346925447, "bacc": 0.5854838709677419, "bacc_std": 0.082473499732754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.062745057942855, "f1": 0.5729166666666666, "f1_std": 0.0862324728353296, "bacc": 0.5693548387096774, "bacc_std": 0.07915056181736276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07097282703454492, "f1": 0.5839188134270101, "f1_std": 0.08753745869971474, "bacc": 0.5870967741935484, "bacc_std": 0.09062352921767507} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.060508965614119205, "f1": 0.48621553884711777, "f1_std": 0.07301989469590019, "bacc": 0.48709677419354835, "bacc_std": 0.07002237036631195} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.052703947929023075, "f1": 0.6117424242424243, "f1_std": 0.09244397827587626, "bacc": 0.6016129032258064, "bacc_std": 0.07959798907462579} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05672598171724005, "f1": 0.6917293233082706, "f1_std": 0.08193854857201946, "bacc": 0.685483870967742, "bacc_std": 0.08120947560598941} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.058791700175434156, "f1": 0.6917293233082706, "f1_std": 0.08468903101124754, "bacc": 0.685483870967742, "bacc_std": 0.08374840946196499} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.051459507423057174, "f1": 0.5512437810945273, "f1_std": 0.0888722526182378, "bacc": 0.5516129032258065, "bacc_std": 0.0709066959584056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06244771281013527, "f1": 0.6479313036690086, "f1_std": 0.08043511149955465, "bacc": 0.6532258064516129, "bacc_std": 0.0830901126236862} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.053165696785555584, "f1": 0.6117424242424243, "f1_std": 0.08865824274927217, "bacc": 0.6016129032258064, "bacc_std": 0.0768207012157254} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06523122283903277, "f1": 0.5839188134270101, "f1_std": 0.08272359347867302, "bacc": 0.5870967741935484, "bacc_std": 0.08497754487012439} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.02680992650920385, "f1": 0.4225352112676056, "f1_std": 0.009132940949010071, "bacc": 0.4838709677419355, "bacc_std": 0.01772914494963481} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04952120547594334, "f1": 0.5512437810945273, "f1_std": 0.08566140757860223, "bacc": 0.5516129032258065, "bacc_std": 0.06826491359930138} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06864874079927032, "f1": 0.6272727272727273, "f1_std": 0.08252659226625542, "bacc": 0.6370967741935484, "bacc_std": 0.08796832652963539} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06102210909931915, "f1": 0.5017361111111112, "f1_std": 0.07600933764227139, "bacc": 0.5032258064516129, "bacc_std": 0.0698301569671754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0727095056984801, "f1": 0.6072218128224024, "f1_std": 0.08453496934532946, "bacc": 0.6209677419354839, "bacc_std": 0.09222880519558067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.04044958525195683, "f1": 0.4057971014492754, "f1_std": 0.01450810209912103, "bacc": 0.45161290322580644, "bacc_std": 0.026748919279519844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07468195503661124, "f1": 0.5030303030303029, "f1_std": 0.08091250999269203, "bacc": 0.5048387096774194, "bacc_std": 0.08618468155088267} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.049243920559558875, "f1": 0.5512437810945273, "f1_std": 0.0880732552511037, "bacc": 0.5516129032258065, "bacc_std": 0.0711191856252294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0736259659857911, "f1": 0.5684210526315789, "f1_std": 0.07670697563376787, "bacc": 0.5887096774193548, "bacc_std": 0.08587042697534582} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05961005548605507, "f1": 0.6440972222222222, "f1_std": 0.08981731821684287, "bacc": 0.635483870967742, "bacc_std": 0.08400939414047785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.0644179356566579, "f1": 0.7280766396462786, "f1_std": 0.07442564178159215, "bacc": 0.7532258064516129, "bacc_std": 0.07854384142639427} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07359945942951265, "f1": 0.5651515151515152, "f1_std": 0.08451940586294561, "bacc": 0.5709677419354839, "bacc_std": 0.08931851660741467} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 166.81005372000556, "split": "test", "acc": 0.5609756097560976, "acc_std": 0.07399167115531945, "f1": 0.4409090909090909, "f1_std": 0.07238909857378104, "bacc": 0.43870967741935485, "bacc_std": 0.07649569465485236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 1291.5496650148827, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06272184423468334, "f1": 0.5547201336675021, "f1_std": 0.08166902481633125, "bacc": 0.5532258064516129, "bacc_std": 0.07925072182301751} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06483972827579738, "f1": 0.5547201336675021, "f1_std": 0.08399484540717062, "bacc": 0.5532258064516129, "bacc_std": 0.08193459302284316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.054900461547857306, "f1": 0.6117424242424243, "f1_std": 0.09090228034754227, "bacc": 0.6016129032258064, "bacc_std": 0.0791454128068474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06756185611823866, "f1": 0.5370967741935484, "f1_std": 0.08100025649039941, "bacc": 0.5370967741935484, "bacc_std": 0.08057239271774314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07154453067234084, "f1": 0.646551724137931, "f1_std": 0.07907284055748377, "bacc": 0.6709677419354838, "bacc_std": 0.08696520983200022} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.03473290625499833, "f1": 0.5119047619047619, "f1_std": 0.07645626350987944, "bacc": 0.5338709677419355, "bacc_std": 0.05009515139759923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07060516856069138, "f1": 0.5030303030303029, "f1_std": 0.07883730121741953, "bacc": 0.5048387096774194, "bacc_std": 0.08354082784335683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07509297825829109, "f1": 0.5287356321839081, "f1_std": 0.08179981748059816, "bacc": 0.5387096774193548, "bacc_std": 0.09043367499643638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06972750565319469, "f1": 0.5651515151515152, "f1_std": 0.08196239501559577, "bacc": 0.5709677419354839, "bacc_std": 0.08767476294962326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06912324215191233, "f1": 0.47096774193548385, "f1_std": 0.07694862480163871, "bacc": 0.47096774193548385, "bacc_std": 0.07774664816394601} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0641231711839712, "f1": 0.6232247284878863, "f1_std": 0.08905028013585563, "bacc": 0.6193548387096774, "bacc_std": 0.08746281808486686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 21.54434690031882, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07049161944273749, "f1": 0.4863669859985261, "f1_std": 0.0763053522039931, "bacc": 0.4887096774193548, "bacc_std": 0.08254267492747702} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0447249775505221, "f1": 0.569327731092437, "f1_std": 0.08740950044414621, "bacc": 0.567741935483871, "bacc_std": 0.06661006758004145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04802525114118927, "f1": 0.569327731092437, "f1_std": 0.09272213194674339, "bacc": 0.567741935483871, "bacc_std": 0.07049205761860616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04723150422204167, "f1": 0.5512437810945273, "f1_std": 0.08193929908917189, "bacc": 0.5516129032258065, "bacc_std": 0.06515398841234034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0650690568049059, "f1": 0.5370967741935484, "f1_std": 0.08045180704139074, "bacc": 0.5370967741935484, "bacc_std": 0.0797625312686405} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07123748520292447, "f1": 0.646551724137931, "f1_std": 0.08020594902554645, "bacc": 0.6709677419354838, "bacc_std": 0.08829432051009413} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.04853509006153569, "f1": 0.3880597014925373, "f1_std": 0.018294029348801488, "bacc": 0.41935483870967744, "bacc_std": 0.03209578536327359} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06952674216633573, "f1": 0.6272727272727273, "f1_std": 0.08540681330609344, "bacc": 0.6370967741935484, "bacc_std": 0.09093753896909956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06387918027662691, "f1": 0.6232247284878863, "f1_std": 0.09209906093785253, "bacc": 0.6193548387096774, "bacc_std": 0.08989276094515837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05085526698047083, "f1": 0.6328358208955224, "f1_std": 0.09584026502990133, "bacc": 0.6177419354838709, "bacc_std": 0.07953648264010438} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.05423800196018431, "f1": 0.3787878787878788, "f1_std": 0.02149163787430754, "bacc": 0.4032258064516129, "bacc_std": 0.035867065812379945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06723579398550592, "f1": 0.6479313036690086, "f1_std": 0.08403309421209965, "bacc": 0.6532258064516129, "bacc_std": 0.08909247402670883} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06585177955765639, "f1": 0.48621553884711777, "f1_std": 0.08000140515083039, "bacc": 0.48709677419354835, "bacc_std": 0.07740177347413099} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07425691370235935, "f1": 0.6072218128224024, "f1_std": 0.08775662440527096, "bacc": 0.6209677419354839, "bacc_std": 0.09431600060892999} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06468246698140628, "f1": 0.5017361111111112, "f1_std": 0.08409938277984262, "bacc": 0.5032258064516129, "bacc_std": 0.07851810610599587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 2.782559402207126, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07519595657867698, "f1": 0.5494505494505495, "f1_std": 0.08067736287502543, "bacc": 0.5725806451612903, "bacc_std": 0.09301943918664149} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05794210324945799, "f1": 0.5176470588235295, "f1_std": 0.08185176466887371, "bacc": 0.5193548387096775, "bacc_std": 0.0727472550089854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05154994459382486, "f1": 0.6328358208955224, "f1_std": 0.09320366438953274, "bacc": 0.6177419354838709, "bacc_std": 0.07744247638604625} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05129842933145111, "f1": 0.5340909090909092, "f1_std": 0.08268764685001166, "bacc": 0.535483870967742, "bacc_std": 0.0699465245421493} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.051518546356427386, "f1": 0.5512437810945273, "f1_std": 0.0871117988477528, "bacc": 0.5516129032258065, "bacc_std": 0.06942776503497965} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.059041239280290585, "f1": 0.6917293233082706, "f1_std": 0.084108048427422, "bacc": 0.685483870967742, "bacc_std": 0.08479293374393425} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 77.016 | 189.5 | 0.9707 | 0.048864 | 0.95139 | 0.085532 | 0.9414 | 0.098896 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 77.016 | 189.5 | 0.69854 | 0.055631 | 0.56511 | 0.076629 | 0.56965 | 0.073486 | + + +done! total time: 0:04:47 diff --git a/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..27376c0519eb7ee825531e3380831d362e9373c9 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adni_ad_vs_cn reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic +model: flat_mae +representation: reg +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..27ba7b38e8c99b680dea8c89c222ff56b945a95d --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,adni_ad_vs_cn,,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,,21.54434690031882,test,0.6097560975609756,0.07512252137889426,0.5030303030303029,0.07831934160254232,0.5104166666666666,0.08788377444152438 +flat_mae,reg,logistic,adni_ad_vs_cn,1,0.005994842503189409,train,0.8644986449864499,0.014604812515580002,0.7665738866396761,0.031246360184897175,0.7254910017256965,0.029332111662329175 +flat_mae,reg,logistic,adni_ad_vs_cn,1,0.005994842503189409,test,0.7317073170731707,0.038897843600434086,0.4972129319955407,0.07575301881307256,0.5177419354838709,0.053008457103123595 +flat_mae,reg,logistic,adni_ad_vs_cn,2,0.046415888336127774,train,0.975609756097561,0.007496581575670782,0.9645665510802881,0.01135899894091697,0.9476744186046512,0.01608278256640995 +flat_mae,reg,logistic,adni_ad_vs_cn,2,0.046415888336127774,test,0.6829268292682927,0.05906225352787176,0.5176470588235295,0.08504389808163246,0.5193548387096775,0.07612972635003434 +flat_mae,reg,logistic,adni_ad_vs_cn,3,0.046415888336127774,train,0.967479674796748,0.008729099514861028,0.9521193771626297,0.013630644348971785,0.9302325581395349,0.018726963494091368 +flat_mae,reg,logistic,adni_ad_vs_cn,3,0.046415888336127774,test,0.7560975609756098,0.04525967117227266,0.569327731092437,0.08822115971390378,0.567741935483871,0.06601181830617461 +flat_mae,reg,logistic,adni_ad_vs_cn,4,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,4,2.782559402207126,test,0.8048780487804879,0.06670174766066858,0.7515151515151515,0.08044781092714269,0.7693548387096774,0.08432133887330097 +flat_mae,reg,logistic,adni_ad_vs_cn,5,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,5,166.81005372000556,test,0.6829268292682927,0.058798924342769614,0.5176470588235295,0.08284029776428156,0.5193548387096775,0.07341903055657167 +flat_mae,reg,logistic,adni_ad_vs_cn,6,0.046415888336127774,train,0.9701897018970189,0.007941065667690494,0.956306446925089,0.01223696566498589,0.936046511627907,0.017036355996382486 +flat_mae,reg,logistic,adni_ad_vs_cn,6,0.046415888336127774,test,0.7560975609756098,0.045419952008474346,0.569327731092437,0.0907422610644387,0.567741935483871,0.06794702985241392 +flat_mae,reg,logistic,adni_ad_vs_cn,7,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,7,166.81005372000556,test,0.7317073170731707,0.05955733993418186,0.5918552036199095,0.09243070877666976,0.5854838709677419,0.0836882615404754 +flat_mae,reg,logistic,adni_ad_vs_cn,8,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,8,0.3593813663804626,test,0.6829268292682927,0.06469227022978588,0.5547201336675021,0.08546961165128716,0.5532258064516129,0.08155891903203019 +flat_mae,reg,logistic,adni_ad_vs_cn,9,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,9,21.54434690031882,test,0.6585365853658537,0.07384528096312924,0.5876436781609196,0.08070623831801702,0.6048387096774194,0.08919638238512329 +flat_mae,reg,logistic,adni_ad_vs_cn,10,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,10,2.782559402207126,test,0.6829268292682927,0.06465715191127591,0.5547201336675021,0.0824877506067077,0.5532258064516129,0.07875200369087625 +flat_mae,reg,logistic,adni_ad_vs_cn,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,11,166.81005372000556,test,0.6585365853658537,0.06688036145509434,0.5651515151515152,0.07866046072834716,0.5709677419354839,0.08415228973002108 +flat_mae,reg,logistic,adni_ad_vs_cn,12,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,12,2.782559402207126,test,0.7317073170731707,0.06520336556971644,0.6479313036690086,0.07910272125261066,0.6532258064516129,0.08325613669638207 +flat_mae,reg,logistic,adni_ad_vs_cn,13,0.046415888336127774,train,0.981029810298103,0.006608244242873651,0.9726796763445977,0.009837822640262044,0.9593023255813953,0.014176989102444014 +flat_mae,reg,logistic,adni_ad_vs_cn,13,0.046415888336127774,test,0.7073170731707317,0.06867662110743428,0.603225806451613,0.08960584181060043,0.603225806451613,0.09026042792450911 +flat_mae,reg,logistic,adni_ad_vs_cn,14,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,14,0.3593813663804626,test,0.7560975609756098,0.06791566663983979,0.6893939393939394,0.08267247967039379,0.7032258064516128,0.08917651613612687 +flat_mae,reg,logistic,adni_ad_vs_cn,15,0.005994842503189409,train,0.8590785907859079,0.013882674001138096,0.7572368421052631,0.029655839727666156,0.7179102637850275,0.02741803986419169 +flat_mae,reg,logistic,adni_ad_vs_cn,15,0.005994842503189409,test,0.7560975609756098,0.036076592459625655,0.5119047619047619,0.0819849582388381,0.5338709677419355,0.05388275088441577 +flat_mae,reg,logistic,adni_ad_vs_cn,16,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,16,2.782559402207126,test,0.7560975609756098,0.045776894748354266,0.569327731092437,0.08714513877951263,0.567741935483871,0.06575394893242623 +flat_mae,reg,logistic,adni_ad_vs_cn,17,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,17,0.3593813663804626,test,0.7560975609756098,0.06577954275526858,0.6693548387096775,0.08727518300487007,0.6693548387096775,0.08822007553480853 +flat_mae,reg,logistic,adni_ad_vs_cn,18,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,18,0.3593813663804626,test,0.7804878048780488,0.06244672208647646,0.7119437939110069,0.08036940877558103,0.7193548387096774,0.08512536944044664 +flat_mae,reg,logistic,adni_ad_vs_cn,19,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,19,166.81005372000556,test,0.6341463414634146,0.07069763687427874,0.5199063231850116,0.08091621477505137,0.5209677419354839,0.08308151056970008 +flat_mae,reg,logistic,adni_ad_vs_cn,20,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,20,166.81005372000556,test,0.7804878048780488,0.06416314349179258,0.7515151515151515,0.06482464156989234,0.8209677419354839,0.06192544231434495 +flat_mae,reg,logistic,adni_ad_vs_cn,21,0.046415888336127774,train,0.9728997289972899,0.008171270549000976,0.9604552469135802,0.012522157562459007,0.9418604651162791,0.017530225770821833 +flat_mae,reg,logistic,adni_ad_vs_cn,21,0.046415888336127774,test,0.7804878048780488,0.04975444760535464,0.6328358208955224,0.09421244502928021,0.6177419354838709,0.07806205008101694 +flat_mae,reg,logistic,adni_ad_vs_cn,22,0.046415888336127774,train,0.9701897018970189,0.00822344941384348,0.956306446925089,0.01268455433599042,0.936046511627907,0.017642167637838605 +flat_mae,reg,logistic,adni_ad_vs_cn,22,0.046415888336127774,test,0.8292682926829268,0.045913298007961435,0.7144278606965174,0.092130603753538,0.6838709677419355,0.08060282863120051 +flat_mae,reg,logistic,adni_ad_vs_cn,23,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,23,166.81005372000556,test,0.6341463414634146,0.06750070394239321,0.48621553884711777,0.07999523379833683,0.48709677419354835,0.07796349602062869 +flat_mae,reg,logistic,adni_ad_vs_cn,24,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,24,0.3593813663804626,test,0.6829268292682927,0.06542181805190025,0.5547201336675021,0.0847316426180802,0.5532258064516129,0.0820708865959112 +flat_mae,reg,logistic,adni_ad_vs_cn,25,0.046415888336127774,train,0.9728997289972899,0.008408675650246788,0.9604552469135802,0.012875094788800454,0.9418604651162791,0.01803954252872709 +flat_mae,reg,logistic,adni_ad_vs_cn,25,0.046415888336127774,test,0.6829268292682927,0.06270285343326418,0.5547201336675021,0.08069932860559287,0.5532258064516129,0.07781910211179484 +flat_mae,reg,logistic,adni_ad_vs_cn,26,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,26,0.3593813663804626,test,0.7317073170731707,0.06753719754146531,0.6479313036690086,0.08530841397457992,0.6532258064516129,0.08877829862039101 +flat_mae,reg,logistic,adni_ad_vs_cn,27,0.046415888336127774,train,0.975609756097561,0.007640121551317709,0.9645665510802881,0.011597307938244287,0.9476744186046512,0.01639072588625714 +flat_mae,reg,logistic,adni_ad_vs_cn,27,0.046415888336127774,test,0.8048780487804879,0.043005028550929594,0.6554621848739496,0.09525092891769492,0.6338709677419355,0.07463297388448936 +flat_mae,reg,logistic,adni_ad_vs_cn,28,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,28,0.3593813663804626,test,0.7317073170731707,0.057507292039493965,0.5918552036199095,0.08299761452229977,0.5854838709677419,0.0741541726509039 +flat_mae,reg,logistic,adni_ad_vs_cn,29,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,29,2.782559402207126,test,0.6829268292682927,0.06786023358931176,0.5839188134270101,0.08151496384028864,0.5870967741935484,0.08447884298184054 +flat_mae,reg,logistic,adni_ad_vs_cn,30,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,30,21.54434690031882,test,0.6341463414634146,0.0715806912505378,0.5684210526315789,0.07700595616908829,0.5887096774193548,0.08551789529819528 +flat_mae,reg,logistic,adni_ad_vs_cn,31,0.005994842503189409,train,0.8672086720867209,0.01387585851838143,0.7726146610158835,0.02890617206728078,0.7313049552140686,0.02719268425434103 +flat_mae,reg,logistic,adni_ad_vs_cn,31,0.005994842503189409,test,0.7317073170731707,0.022844897714291535,0.4225352112676056,0.007699241549495224,0.4838709677419355,0.0151071097788057 +flat_mae,reg,logistic,adni_ad_vs_cn,32,0.005994842503189409,train,0.8590785907859079,0.013545012581720627,0.7572368421052631,0.028778128849430734,0.7179102637850275,0.02669162654400962 +flat_mae,reg,logistic,adni_ad_vs_cn,32,0.005994842503189409,test,0.8048780487804879,0.042893862063662046,0.6554621848739496,0.09705353779425079,0.6338709677419355,0.07511317433990705 +flat_mae,reg,logistic,adni_ad_vs_cn,33,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,33,0.3593813663804626,test,0.7560975609756098,0.06473909565055258,0.6893939393939394,0.07768253534738652,0.7032258064516128,0.08275886741175083 +flat_mae,reg,logistic,adni_ad_vs_cn,34,0.046415888336127774,train,0.964769647696477,0.00892789379955783,0.9478932446964512,0.01408420911280221,0.9244186046511628,0.019153446581609515 +flat_mae,reg,logistic,adni_ad_vs_cn,34,0.046415888336127774,test,0.7804878048780488,0.05795286192958776,0.6917293233082706,0.08475704711224323,0.685483870967742,0.08435172288083782 +flat_mae,reg,logistic,adni_ad_vs_cn,35,0.046415888336127774,train,0.967479674796748,0.008693848035358956,0.9521193771626297,0.01359238181255736,0.9302325581395349,0.018651336773531705 +flat_mae,reg,logistic,adni_ad_vs_cn,35,0.046415888336127774,test,0.8292682926829268,0.0546198587589778,0.7759562841530054,0.0714041202502219,0.7854838709677419,0.07684702454943833 +flat_mae,reg,logistic,adni_ad_vs_cn,36,0.046415888336127774,train,0.967479674796748,0.008699860673455979,0.9521193771626297,0.013584990711605955,0.9302325581395349,0.0186642359796817 +flat_mae,reg,logistic,adni_ad_vs_cn,36,0.046415888336127774,test,0.7073170731707317,0.06785677957437879,0.603225806451613,0.08420203070997596,0.603225806451613,0.08424093654642333 +flat_mae,reg,logistic,adni_ad_vs_cn,37,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,37,2.782559402207126,test,0.6829268292682927,0.06477372870997512,0.5547201336675021,0.0861017219440235,0.5532258064516129,0.08421137643404074 +flat_mae,reg,logistic,adni_ad_vs_cn,38,0.046415888336127774,train,0.978319783197832,0.007142346216803582,0.9686411149825784,0.010717898579713772,0.9534883720930232,0.015322824151165784 +flat_mae,reg,logistic,adni_ad_vs_cn,38,0.046415888336127774,test,0.7317073170731707,0.061209308254657493,0.6232247284878863,0.08194261260936386,0.6193548387096774,0.08122602705650434 +flat_mae,reg,logistic,adni_ad_vs_cn,39,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,39,166.81005372000556,test,0.5853658536585366,0.0696851762956793,0.4558938329430133,0.07123707417012,0.45483870967741935,0.07414007687451786 +flat_mae,reg,logistic,adni_ad_vs_cn,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,40,21.54434690031882,test,0.6585365853658537,0.0728993177570734,0.5651515151515152,0.0851079570703629,0.5709677419354839,0.09026226205969577 +flat_mae,reg,logistic,adni_ad_vs_cn,41,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,41,166.81005372000556,test,0.7317073170731707,0.06516187686302259,0.6479313036690086,0.0811985253153579,0.6532258064516129,0.08446541103179471 +flat_mae,reg,logistic,adni_ad_vs_cn,42,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,42,0.3593813663804626,test,0.6829268292682927,0.07341311075317583,0.6259649122807017,0.08002726110857303,0.6548387096774193,0.08960865192312463 +flat_mae,reg,logistic,adni_ad_vs_cn,43,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,43,0.3593813663804626,test,0.7317073170731707,0.05851892009870093,0.5918552036199095,0.08761406990683057,0.5854838709677419,0.07837334135249985 +flat_mae,reg,logistic,adni_ad_vs_cn,44,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,44,2.782559402207126,test,0.7317073170731707,0.06419415819574582,0.6232247284878863,0.08935797250815347,0.6193548387096774,0.08725343205162006 +flat_mae,reg,logistic,adni_ad_vs_cn,45,0.046415888336127774,train,0.964769647696477,0.008932367720950768,0.9478932446964512,0.014039335468807089,0.9244186046511628,0.01916304470366762 +flat_mae,reg,logistic,adni_ad_vs_cn,45,0.046415888336127774,test,0.7560975609756098,0.05799185567139388,0.6440972222222222,0.08979208627916044,0.635483870967742,0.08421809523514777 +flat_mae,reg,logistic,adni_ad_vs_cn,46,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,46,0.3593813663804626,test,0.7073170731707317,0.056572412310438455,0.5340909090909092,0.08366669925191175,0.535483870967742,0.07082674586087076 +flat_mae,reg,logistic,adni_ad_vs_cn,47,0.046415888336127774,train,0.9728997289972899,0.007957073380433546,0.9604552469135802,0.012162162451428956,0.9418604651162791,0.017070698124302168 +flat_mae,reg,logistic,adni_ad_vs_cn,47,0.046415888336127774,test,0.7560975609756098,0.04637921440529016,0.569327731092437,0.08948071425229473,0.567741935483871,0.06752687606157089 +flat_mae,reg,logistic,adni_ad_vs_cn,48,0.046415888336127774,train,0.967479674796748,0.009264450304179179,0.9521193771626297,0.014479017438151059,0.9302325581395349,0.019875477687454148 +flat_mae,reg,logistic,adni_ad_vs_cn,48,0.046415888336127774,test,0.6829268292682927,0.060621881301753985,0.5547201336675021,0.08257801702412902,0.5532258064516129,0.08012208809710705 +flat_mae,reg,logistic,adni_ad_vs_cn,49,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,49,21.54434690031882,test,0.6829268292682927,0.06753770841758426,0.5839188134270101,0.08275612557100018,0.5870967741935484,0.08442140043375654 +flat_mae,reg,logistic,adni_ad_vs_cn,50,0.046415888336127774,train,0.964769647696477,0.008861375888551409,0.9478932446964512,0.01398843187287432,0.9244186046511628,0.0190107424585783 +flat_mae,reg,logistic,adni_ad_vs_cn,50,0.046415888336127774,test,0.7560975609756098,0.06297821686995414,0.6693548387096775,0.08359887085679833,0.6693548387096775,0.08406073290078343 +flat_mae,reg,logistic,adni_ad_vs_cn,51,0.046415888336127774,train,0.9701897018970189,0.008153923486587044,0.956306446925089,0.012596430846601447,0.936046511627907,0.01749301027064311 +flat_mae,reg,logistic,adni_ad_vs_cn,51,0.046415888336127774,test,0.7317073170731707,0.060904622092797754,0.5918552036199095,0.09257328464596479,0.5854838709677419,0.08220669768723836 +flat_mae,reg,logistic,adni_ad_vs_cn,52,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,52,166.81005372000556,test,0.7317073170731707,0.055221989946996,0.6232247284878863,0.07990692923744148,0.6193548387096774,0.07646259203865319 +flat_mae,reg,logistic,adni_ad_vs_cn,53,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,53,166.81005372000556,test,0.7560975609756098,0.0638006263967206,0.6893939393939394,0.08008131460658896,0.7032258064516128,0.08604877884845974 +flat_mae,reg,logistic,adni_ad_vs_cn,54,0.046415888336127774,train,0.962059620596206,0.009348767097526007,0.9436272370144041,0.014829133550822878,0.9186046511627908,0.020056366622017992 +flat_mae,reg,logistic,adni_ad_vs_cn,54,0.046415888336127774,test,0.7073170731707317,0.06910223999034708,0.603225806451613,0.0888752723415763,0.603225806451613,0.0891135089747329 +flat_mae,reg,logistic,adni_ad_vs_cn,55,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,55,0.3593813663804626,test,0.7317073170731707,0.06580840360115885,0.6479313036690086,0.08372225556748769,0.6532258064516129,0.08650394774845016 +flat_mae,reg,logistic,adni_ad_vs_cn,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,56,21.54434690031882,test,0.6585365853658537,0.05351146140858138,0.4564393939393939,0.06429005640095066,0.4693548387096774,0.056540968451411565 +flat_mae,reg,logistic,adni_ad_vs_cn,57,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,57,166.81005372000556,test,0.7560975609756098,0.06343309299828419,0.6693548387096775,0.08598405183439879,0.6693548387096775,0.08629909819711787 +flat_mae,reg,logistic,adni_ad_vs_cn,58,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,58,166.81005372000556,test,0.7317073170731707,0.063967496207751,0.6479313036690086,0.08261556151662282,0.6532258064516129,0.0871339511456221 +flat_mae,reg,logistic,adni_ad_vs_cn,59,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,59,0.3593813663804626,test,0.6341463414634146,0.06560901259892447,0.48621553884711777,0.07466749717460948,0.48709677419354835,0.07194568595383136 +flat_mae,reg,logistic,adni_ad_vs_cn,60,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,60,166.81005372000556,test,0.7560975609756098,0.06481647545785946,0.6893939393939394,0.08001024209498118,0.7032258064516128,0.08529396623664988 +flat_mae,reg,logistic,adni_ad_vs_cn,61,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,61,21.54434690031882,test,0.7073170731707317,0.06060325331951233,0.5729166666666666,0.08879442790292279,0.5693548387096774,0.08128782247819547 +flat_mae,reg,logistic,adni_ad_vs_cn,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,62,21.54434690031882,test,0.7073170731707317,0.06010096601060165,0.5729166666666666,0.08634484721181052,0.5693548387096774,0.08055583284924425 +flat_mae,reg,logistic,adni_ad_vs_cn,63,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,63,0.3593813663804626,test,0.7560975609756098,0.05288182868318803,0.6117424242424243,0.09264516911684094,0.6016129032258064,0.07830203077119277 +flat_mae,reg,logistic,adni_ad_vs_cn,64,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,64,21.54434690031882,test,0.6585365853658537,0.07023609373941267,0.5651515151515152,0.08291480341179702,0.5709677419354839,0.08851338023569781 +flat_mae,reg,logistic,adni_ad_vs_cn,65,0.005994842503189409,train,0.8644986449864499,0.013609922302907496,0.7665738866396761,0.028795918278427503,0.7254910017256965,0.02688009080969971 +flat_mae,reg,logistic,adni_ad_vs_cn,65,0.005994842503189409,test,0.7560975609756098,0.04453207040400861,0.569327731092437,0.08949366259735736,0.567741935483871,0.06774571994037212 +flat_mae,reg,logistic,adni_ad_vs_cn,66,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,66,0.3593813663804626,test,0.6829268292682927,0.07606315670058392,0.6259649122807017,0.08002248206583591,0.6548387096774193,0.08818259978763936 +flat_mae,reg,logistic,adni_ad_vs_cn,67,0.046415888336127774,train,0.9701897018970189,0.008261976200194998,0.956306446925089,0.012747258107268308,0.936046511627907,0.017724821034139242 +flat_mae,reg,logistic,adni_ad_vs_cn,67,0.046415888336127774,test,0.7317073170731707,0.06631197335946871,0.6479313036690086,0.0843150984893372,0.6532258064516129,0.08748677670262389 +flat_mae,reg,logistic,adni_ad_vs_cn,68,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,68,0.3593813663804626,test,0.7073170731707317,0.06671935058894168,0.603225806451613,0.08466461628325508,0.603225806451613,0.08489878015618554 +flat_mae,reg,logistic,adni_ad_vs_cn,69,0.046415888336127774,train,0.975609756097561,0.007636798667271888,0.9645665510802881,0.011603703726810617,0.9476744186046512,0.016383597140833258 +flat_mae,reg,logistic,adni_ad_vs_cn,69,0.046415888336127774,test,0.7804878048780488,0.04767029337973674,0.6328358208955224,0.09264062455981392,0.6177419354838709,0.07642105173840079 +flat_mae,reg,logistic,adni_ad_vs_cn,70,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,70,21.54434690031882,test,0.6829268292682927,0.06903807500299365,0.5839188134270101,0.08550544216890339,0.5870967741935484,0.08941447899009264 +flat_mae,reg,logistic,adni_ad_vs_cn,71,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,71,166.81005372000556,test,0.7804878048780488,0.06064150417457034,0.6917293233082706,0.08657228202248445,0.685483870967742,0.08668189184950788 +flat_mae,reg,logistic,adni_ad_vs_cn,72,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,72,166.81005372000556,test,0.6585365853658537,0.06878353219347856,0.5370967741935484,0.0834936556093448,0.5370967741935484,0.08263900023621791 +flat_mae,reg,logistic,adni_ad_vs_cn,73,0.005994842503189409,train,0.8699186991869918,0.012700929941334847,0.775910931174089,0.02706272125505203,0.7330717396663654,0.025723312207936035 +flat_mae,reg,logistic,adni_ad_vs_cn,73,0.005994842503189409,test,0.7317073170731707,0.05388122306231787,0.5512437810945273,0.09095522643144548,0.5516129032258065,0.07393603022936114 +flat_mae,reg,logistic,adni_ad_vs_cn,74,0.046415888336127774,train,0.967479674796748,0.008892475646239054,0.9521193771626297,0.013856139735492138,0.9302325581395349,0.019077462287570974 +flat_mae,reg,logistic,adni_ad_vs_cn,74,0.046415888336127774,test,0.7073170731707317,0.045550006513685445,0.4831932773109243,0.06975956034232422,0.5016129032258064,0.05331721134881839 +flat_mae,reg,logistic,adni_ad_vs_cn,75,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,75,0.3593813663804626,test,0.7317073170731707,0.06413569419194315,0.6232247284878863,0.08905253122832428,0.6193548387096774,0.08590578388254486 +flat_mae,reg,logistic,adni_ad_vs_cn,76,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,76,166.81005372000556,test,0.6341463414634146,0.06875541836849493,0.5199063231850116,0.08137161694037863,0.5209677419354839,0.0845736226508185 +flat_mae,reg,logistic,adni_ad_vs_cn,77,0.005994842503189409,train,0.8672086720867209,0.014041012104941138,0.7752936059156155,0.02852509804898682,0.7353521242501437,0.027091675665132885 +flat_mae,reg,logistic,adni_ad_vs_cn,77,0.005994842503189409,test,0.7560975609756098,0.04801078106171425,0.569327731092437,0.09513392482534426,0.567741935483871,0.07260810921249163 +flat_mae,reg,logistic,adni_ad_vs_cn,78,0.046415888336127774,train,0.9701897018970189,0.008049236708393701,0.956306446925089,0.012437069405761335,0.936046511627907,0.017268420612774837 +flat_mae,reg,logistic,adni_ad_vs_cn,78,0.046415888336127774,test,0.7073170731707317,0.05789929512495542,0.5340909090909092,0.08400403510078056,0.535483870967742,0.07168083751032113 +flat_mae,reg,logistic,adni_ad_vs_cn,79,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,79,10000.0,test,0.7560975609756098,0.06498020565303168,0.7184065934065934,0.0676144474843503,0.7709677419354839,0.07102989243372626 +flat_mae,reg,logistic,adni_ad_vs_cn,80,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,80,166.81005372000556,test,0.6341463414634146,0.06204417838432612,0.48621553884711777,0.07636403309871119,0.48709677419354835,0.07349423473322145 +flat_mae,reg,logistic,adni_ad_vs_cn,81,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,81,166.81005372000556,test,0.6585365853658537,0.05454302069453282,0.4564393939393939,0.06945923055045826,0.4693548387096774,0.06034267898749721 +flat_mae,reg,logistic,adni_ad_vs_cn,82,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,82,21.54434690031882,test,0.7317073170731707,0.06532791035617974,0.6479313036690086,0.0841864038763423,0.6532258064516129,0.08849999447374127 +flat_mae,reg,logistic,adni_ad_vs_cn,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,83,166.81005372000556,test,0.7073170731707317,0.059474178181083664,0.5729166666666666,0.08128326156535075,0.5693548387096774,0.07582604901112043 +flat_mae,reg,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.964769647696477,0.008766317315104471,0.9478932446964512,0.013786599018982085,0.9244186046511628,0.018806808658567133 +flat_mae,reg,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7560975609756098,0.05400782105655274,0.6117424242424243,0.09064243997480538,0.6016129032258064,0.0774893097927321 +flat_mae,reg,logistic,adni_ad_vs_cn,85,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,85,166.81005372000556,test,0.7804878048780488,0.06352746060595407,0.7280766396462786,0.07688785060638173,0.7532258064516129,0.08377621198209358 +flat_mae,reg,logistic,adni_ad_vs_cn,86,0.046415888336127774,train,0.975609756097561,0.007667443999826209,0.9648738695859115,0.011394047980414625,0.9517215876407263,0.015205276084654934 +flat_mae,reg,logistic,adni_ad_vs_cn,86,0.046415888336127774,test,0.7073170731707317,0.0674452473642773,0.603225806451613,0.08799988429535313,0.603225806451613,0.08815282556768737 +flat_mae,reg,logistic,adni_ad_vs_cn,87,0.046415888336127774,train,0.967479674796748,0.008693814244746901,0.9521193771626297,0.013560625177329099,0.9302325581395349,0.018651264280881416 +flat_mae,reg,logistic,adni_ad_vs_cn,87,0.046415888336127774,test,0.7317073170731707,0.05417970846213771,0.5918552036199095,0.0873284452696744,0.5854838709677419,0.07758253796899608 +flat_mae,reg,logistic,adni_ad_vs_cn,88,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,88,166.81005372000556,test,0.6585365853658537,0.07107253460719393,0.5651515151515152,0.08561748648923428,0.5709677419354839,0.09166906978844769 +flat_mae,reg,logistic,adni_ad_vs_cn,89,0.046415888336127774,train,0.962059620596206,0.009380646753581042,0.9436272370144041,0.014892830896095976,0.9186046511627908,0.020124759605066298 +flat_mae,reg,logistic,adni_ad_vs_cn,89,0.046415888336127774,test,0.7560975609756098,0.06250109338722366,0.6693548387096775,0.08448246322968005,0.6693548387096775,0.08618995936124477 +flat_mae,reg,logistic,adni_ad_vs_cn,90,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,90,166.81005372000556,test,0.7073170731707317,0.06681643102625476,0.603225806451613,0.08659437682810801,0.603225806451613,0.08699972873042498 +flat_mae,reg,logistic,adni_ad_vs_cn,91,0.046415888336127774,train,0.978319783197832,0.007008899242453091,0.9686411149825784,0.010556834360410331,0.9534883720930232,0.015036533839913846 +flat_mae,reg,logistic,adni_ad_vs_cn,91,0.046415888336127774,test,0.7804878048780488,0.056875287553776875,0.6660633484162897,0.09079898029117087,0.6516129032258065,0.08471292496784477 +flat_mae,reg,logistic,adni_ad_vs_cn,92,0.046415888336127774,train,0.981029810298103,0.006290401982447961,0.9726796763445977,0.009358596395032025,0.9593023255813953,0.013495106578623788 +flat_mae,reg,logistic,adni_ad_vs_cn,92,0.046415888336127774,test,0.7073170731707317,0.05598969481114017,0.5340909090909092,0.08562649343758869,0.535483870967742,0.07289485956848292 +flat_mae,reg,logistic,adni_ad_vs_cn,93,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,93,2.782559402207126,test,0.6341463414634146,0.06785574508899295,0.5199063231850116,0.07928698708217709,0.5209677419354839,0.08110878885517 +flat_mae,reg,logistic,adni_ad_vs_cn,94,0.046415888336127774,train,0.978319783197832,0.007048694529097075,0.9686411149825784,0.010609545244135595,0.9534883720930232,0.015121908611841931 +flat_mae,reg,logistic,adni_ad_vs_cn,94,0.046415888336127774,test,0.6829268292682927,0.053235047250848926,0.4696517412935323,0.07093418985530682,0.4854838709677419,0.05916115172179212 +flat_mae,reg,logistic,adni_ad_vs_cn,95,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,95,0.3593813663804626,test,0.7317073170731707,0.06699285657178554,0.6676492262343405,0.07795514480193572,0.6870967741935483,0.08237561089006214 +flat_mae,reg,logistic,adni_ad_vs_cn,96,0.046415888336127774,train,0.9701897018970189,0.008660900644649971,0.956306446925089,0.013417646412157265,0.936046511627907,0.018580653127185095 +flat_mae,reg,logistic,adni_ad_vs_cn,96,0.046415888336127774,test,0.7560975609756098,0.05156655945028289,0.6117424242424243,0.08786031110283825,0.6016129032258064,0.07501648101955832 +flat_mae,reg,logistic,adni_ad_vs_cn,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,97,166.81005372000556,test,0.6585365853658537,0.06781744049268727,0.5370967741935484,0.08472825245365669,0.5370967741935484,0.08439739079711578 +flat_mae,reg,logistic,adni_ad_vs_cn,98,0.005994842503189409,train,0.8672086720867209,0.012799835258301926,0.7726146610158835,0.02679972166534393,0.7313049552140686,0.025470936692638953 +flat_mae,reg,logistic,adni_ad_vs_cn,98,0.005994842503189409,test,0.7317073170731707,0.055108459389210204,0.5918552036199095,0.08732511593403154,0.5854838709677419,0.07866206988309832 +flat_mae,reg,logistic,adni_ad_vs_cn,99,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,99,21.54434690031882,test,0.6341463414634146,0.06706937461541441,0.5199063231850116,0.07844156333693751,0.5209677419354839,0.08021442874298862 +flat_mae,reg,logistic,adni_ad_vs_cn,100,0.046415888336127774,train,0.9728997289972899,0.007939082554548305,0.9608013937282229,0.011939482737463033,0.9459076341523543,0.016411265224176626 +flat_mae,reg,logistic,adni_ad_vs_cn,100,0.046415888336127774,test,0.7317073170731707,0.0676937323828893,0.6479313036690086,0.08486261371421545,0.6532258064516129,0.08836860290390668 diff --git a/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..400b986e1659e25047755ac78c41344f2bd3c940 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:18:25 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (adni_ad_vs_cn reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic +model: flat_mae +representation: reg +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/adni_ad_vs_cn__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:11:51 time: 4.3396 data: 3.4284 max mem: 2698 +extract (train) [ 20/164] eta: 0:00:54 time: 0.1831 data: 0.0628 max mem: 3005 +extract (train) [ 40/164] eta: 0:00:34 time: 0.1711 data: 0.0565 max mem: 3005 +extract (train) [ 60/164] eta: 0:00:25 time: 0.1837 data: 0.0653 max mem: 3005 +extract (train) [ 80/164] eta: 0:00:19 time: 0.1720 data: 0.0574 max mem: 3005 +extract (train) [100/164] eta: 0:00:13 time: 0.1685 data: 0.0567 max mem: 3005 +extract (train) [120/164] eta: 0:00:09 time: 0.1682 data: 0.0585 max mem: 3005 +extract (train) [140/164] eta: 0:00:04 time: 0.1681 data: 0.0546 max mem: 3005 +extract (train) [160/164] eta: 0:00:00 time: 0.1660 data: 0.0537 max mem: 3005 +extract (train) [163/164] eta: 0:00:00 time: 0.1654 data: 0.0537 max mem: 3005 +extract (train) Total time: 0:00:32 (0.2001 s / it) +extract (validation) [ 0/21] eta: 0:01:15 time: 3.5960 data: 3.4522 max mem: 3005 +extract (validation) [20/21] eta: 0:00:00 time: 0.1609 data: 0.0535 max mem: 3005 +extract (validation) Total time: 0:00:07 (0.3349 s / it) +extract (test) [ 0/21] eta: 0:01:17 time: 3.7037 data: 3.5919 max mem: 3005 +extract (test) [20/21] eta: 0:00:00 time: 0.1564 data: 0.0509 max mem: 3005 +extract (test) Total time: 0:00:07 (0.3370 s / it) +feature extraction time: 0:00:47 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adni_ad_vs_cn | | 21.544 | train | 1 | 0 | 1 | 0 | 1 | 0 | +| flat_mae | reg | logistic | adni_ad_vs_cn | | 21.544 | test | 0.60976 | 0.075123 | 0.50303 | 0.078319 | 0.51042 | 0.087884 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.038897843600434086, "f1": 0.4972129319955407, "f1_std": 0.07575301881307256, "bacc": 0.5177419354838709, "bacc_std": 0.053008457103123595} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.05906225352787176, "f1": 0.5176470588235295, "f1_std": 0.08504389808163246, "bacc": 0.5193548387096775, "bacc_std": 0.07612972635003434} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04525967117227266, "f1": 0.569327731092437, "f1_std": 0.08822115971390378, "bacc": 0.567741935483871, "bacc_std": 0.06601181830617461} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06670174766066858, "f1": 0.7515151515151515, "f1_std": 0.08044781092714269, "bacc": 0.7693548387096774, "bacc_std": 0.08432133887330097} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.058798924342769614, "f1": 0.5176470588235295, "f1_std": 0.08284029776428156, "bacc": 0.5193548387096775, "bacc_std": 0.07341903055657167} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.045419952008474346, "f1": 0.569327731092437, "f1_std": 0.0907422610644387, "bacc": 0.567741935483871, "bacc_std": 0.06794702985241392} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05955733993418186, "f1": 0.5918552036199095, "f1_std": 0.09243070877666976, "bacc": 0.5854838709677419, "bacc_std": 0.0836882615404754} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06469227022978588, "f1": 0.5547201336675021, "f1_std": 0.08546961165128716, "bacc": 0.5532258064516129, "bacc_std": 0.08155891903203019} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07384528096312924, "f1": 0.5876436781609196, "f1_std": 0.08070623831801702, "bacc": 0.6048387096774194, "bacc_std": 0.08919638238512329} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06465715191127591, "f1": 0.5547201336675021, "f1_std": 0.0824877506067077, "bacc": 0.5532258064516129, "bacc_std": 0.07875200369087625} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06688036145509434, "f1": 0.5651515151515152, "f1_std": 0.07866046072834716, "bacc": 0.5709677419354839, "bacc_std": 0.08415228973002108} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06520336556971644, "f1": 0.6479313036690086, "f1_std": 0.07910272125261066, "bacc": 0.6532258064516129, "bacc_std": 0.08325613669638207} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06867662110743428, "f1": 0.603225806451613, "f1_std": 0.08960584181060043, "bacc": 0.603225806451613, "bacc_std": 0.09026042792450911} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06791566663983979, "f1": 0.6893939393939394, "f1_std": 0.08267247967039379, "bacc": 0.7032258064516128, "bacc_std": 0.08917651613612687} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.036076592459625655, "f1": 0.5119047619047619, "f1_std": 0.0819849582388381, "bacc": 0.5338709677419355, "bacc_std": 0.05388275088441577} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.045776894748354266, "f1": 0.569327731092437, "f1_std": 0.08714513877951263, "bacc": 0.567741935483871, "bacc_std": 0.06575394893242623} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06577954275526858, "f1": 0.6693548387096775, "f1_std": 0.08727518300487007, "bacc": 0.6693548387096775, "bacc_std": 0.08822007553480853} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06244672208647646, "f1": 0.7119437939110069, "f1_std": 0.08036940877558103, "bacc": 0.7193548387096774, "bacc_std": 0.08512536944044664} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07069763687427874, "f1": 0.5199063231850116, "f1_std": 0.08091621477505137, "bacc": 0.5209677419354839, "bacc_std": 0.08308151056970008} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06416314349179258, "f1": 0.7515151515151515, "f1_std": 0.06482464156989234, "bacc": 0.8209677419354839, "bacc_std": 0.06192544231434495} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04975444760535464, "f1": 0.6328358208955224, "f1_std": 0.09421244502928021, "bacc": 0.6177419354838709, "bacc_std": 0.07806205008101694} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.045913298007961435, "f1": 0.7144278606965174, "f1_std": 0.092130603753538, "bacc": 0.6838709677419355, "bacc_std": 0.08060282863120051} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06750070394239321, "f1": 0.48621553884711777, "f1_std": 0.07999523379833683, "bacc": 0.48709677419354835, "bacc_std": 0.07796349602062869} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06542181805190025, "f1": 0.5547201336675021, "f1_std": 0.0847316426180802, "bacc": 0.5532258064516129, "bacc_std": 0.0820708865959112} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06270285343326418, "f1": 0.5547201336675021, "f1_std": 0.08069932860559287, "bacc": 0.5532258064516129, "bacc_std": 0.07781910211179484} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06753719754146531, "f1": 0.6479313036690086, "f1_std": 0.08530841397457992, "bacc": 0.6532258064516129, "bacc_std": 0.08877829862039101} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.043005028550929594, "f1": 0.6554621848739496, "f1_std": 0.09525092891769492, "bacc": 0.6338709677419355, "bacc_std": 0.07463297388448936} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.057507292039493965, "f1": 0.5918552036199095, "f1_std": 0.08299761452229977, "bacc": 0.5854838709677419, "bacc_std": 0.0741541726509039} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06786023358931176, "f1": 0.5839188134270101, "f1_std": 0.08151496384028864, "bacc": 0.5870967741935484, "bacc_std": 0.08447884298184054} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0715806912505378, "f1": 0.5684210526315789, "f1_std": 0.07700595616908829, "bacc": 0.5887096774193548, "bacc_std": 0.08551789529819528} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.022844897714291535, "f1": 0.4225352112676056, "f1_std": 0.007699241549495224, "bacc": 0.4838709677419355, "bacc_std": 0.0151071097788057} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.042893862063662046, "f1": 0.6554621848739496, "f1_std": 0.09705353779425079, "bacc": 0.6338709677419355, "bacc_std": 0.07511317433990705} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06473909565055258, "f1": 0.6893939393939394, "f1_std": 0.07768253534738652, "bacc": 0.7032258064516128, "bacc_std": 0.08275886741175083} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05795286192958776, "f1": 0.6917293233082706, "f1_std": 0.08475704711224323, "bacc": 0.685483870967742, "bacc_std": 0.08435172288083782} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.0546198587589778, "f1": 0.7759562841530054, "f1_std": 0.0714041202502219, "bacc": 0.7854838709677419, "bacc_std": 0.07684702454943833} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06785677957437879, "f1": 0.603225806451613, "f1_std": 0.08420203070997596, "bacc": 0.603225806451613, "bacc_std": 0.08424093654642333} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06477372870997512, "f1": 0.5547201336675021, "f1_std": 0.0861017219440235, "bacc": 0.5532258064516129, "bacc_std": 0.08421137643404074} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.061209308254657493, "f1": 0.6232247284878863, "f1_std": 0.08194261260936386, "bacc": 0.6193548387096774, "bacc_std": 0.08122602705650434} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.0696851762956793, "f1": 0.4558938329430133, "f1_std": 0.07123707417012, "bacc": 0.45483870967741935, "bacc_std": 0.07414007687451786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0728993177570734, "f1": 0.5651515151515152, "f1_std": 0.0851079570703629, "bacc": 0.5709677419354839, "bacc_std": 0.09026226205969577} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06516187686302259, "f1": 0.6479313036690086, "f1_std": 0.0811985253153579, "bacc": 0.6532258064516129, "bacc_std": 0.08446541103179471} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07341311075317583, "f1": 0.6259649122807017, "f1_std": 0.08002726110857303, "bacc": 0.6548387096774193, "bacc_std": 0.08960865192312463} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05851892009870093, "f1": 0.5918552036199095, "f1_std": 0.08761406990683057, "bacc": 0.5854838709677419, "bacc_std": 0.07837334135249985} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06419415819574582, "f1": 0.6232247284878863, "f1_std": 0.08935797250815347, "bacc": 0.6193548387096774, "bacc_std": 0.08725343205162006} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05799185567139388, "f1": 0.6440972222222222, "f1_std": 0.08979208627916044, "bacc": 0.635483870967742, "bacc_std": 0.08421809523514777} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.056572412310438455, "f1": 0.5340909090909092, "f1_std": 0.08366669925191175, "bacc": 0.535483870967742, "bacc_std": 0.07082674586087076} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04637921440529016, "f1": 0.569327731092437, "f1_std": 0.08948071425229473, "bacc": 0.567741935483871, "bacc_std": 0.06752687606157089} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.060621881301753985, "f1": 0.5547201336675021, "f1_std": 0.08257801702412902, "bacc": 0.5532258064516129, "bacc_std": 0.08012208809710705} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06753770841758426, "f1": 0.5839188134270101, "f1_std": 0.08275612557100018, "bacc": 0.5870967741935484, "bacc_std": 0.08442140043375654} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06297821686995414, "f1": 0.6693548387096775, "f1_std": 0.08359887085679833, "bacc": 0.6693548387096775, "bacc_std": 0.08406073290078343} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.060904622092797754, "f1": 0.5918552036199095, "f1_std": 0.09257328464596479, "bacc": 0.5854838709677419, "bacc_std": 0.08220669768723836} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.055221989946996, "f1": 0.6232247284878863, "f1_std": 0.07990692923744148, "bacc": 0.6193548387096774, "bacc_std": 0.07646259203865319} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0638006263967206, "f1": 0.6893939393939394, "f1_std": 0.08008131460658896, "bacc": 0.7032258064516128, "bacc_std": 0.08604877884845974} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06910223999034708, "f1": 0.603225806451613, "f1_std": 0.0888752723415763, "bacc": 0.603225806451613, "bacc_std": 0.0891135089747329} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06580840360115885, "f1": 0.6479313036690086, "f1_std": 0.08372225556748769, "bacc": 0.6532258064516129, "bacc_std": 0.08650394774845016} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.05351146140858138, "f1": 0.4564393939393939, "f1_std": 0.06429005640095066, "bacc": 0.4693548387096774, "bacc_std": 0.056540968451411565} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06343309299828419, "f1": 0.6693548387096775, "f1_std": 0.08598405183439879, "bacc": 0.6693548387096775, "bacc_std": 0.08629909819711787} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.063967496207751, "f1": 0.6479313036690086, "f1_std": 0.08261556151662282, "bacc": 0.6532258064516129, "bacc_std": 0.0871339511456221} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06560901259892447, "f1": 0.48621553884711777, "f1_std": 0.07466749717460948, "bacc": 0.48709677419354835, "bacc_std": 0.07194568595383136} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06481647545785946, "f1": 0.6893939393939394, "f1_std": 0.08001024209498118, "bacc": 0.7032258064516128, "bacc_std": 0.08529396623664988} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06060325331951233, "f1": 0.5729166666666666, "f1_std": 0.08879442790292279, "bacc": 0.5693548387096774, "bacc_std": 0.08128782247819547} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06010096601060165, "f1": 0.5729166666666666, "f1_std": 0.08634484721181052, "bacc": 0.5693548387096774, "bacc_std": 0.08055583284924425} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05288182868318803, "f1": 0.6117424242424243, "f1_std": 0.09264516911684094, "bacc": 0.6016129032258064, "bacc_std": 0.07830203077119277} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 21.54434690031882, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07023609373941267, "f1": 0.5651515151515152, "f1_std": 0.08291480341179702, "bacc": 0.5709677419354839, "bacc_std": 0.08851338023569781} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04453207040400861, "f1": 0.569327731092437, "f1_std": 0.08949366259735736, "bacc": 0.567741935483871, "bacc_std": 0.06774571994037212} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07606315670058392, "f1": 0.6259649122807017, "f1_std": 0.08002248206583591, "bacc": 0.6548387096774193, "bacc_std": 0.08818259978763936} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06631197335946871, "f1": 0.6479313036690086, "f1_std": 0.0843150984893372, "bacc": 0.6532258064516129, "bacc_std": 0.08748677670262389} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06671935058894168, "f1": 0.603225806451613, "f1_std": 0.08466461628325508, "bacc": 0.603225806451613, "bacc_std": 0.08489878015618554} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04767029337973674, "f1": 0.6328358208955224, "f1_std": 0.09264062455981392, "bacc": 0.6177419354838709, "bacc_std": 0.07642105173840079} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06903807500299365, "f1": 0.5839188134270101, "f1_std": 0.08550544216890339, "bacc": 0.5870967741935484, "bacc_std": 0.08941447899009264} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06064150417457034, "f1": 0.6917293233082706, "f1_std": 0.08657228202248445, "bacc": 0.685483870967742, "bacc_std": 0.08668189184950788} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06878353219347856, "f1": 0.5370967741935484, "f1_std": 0.0834936556093448, "bacc": 0.5370967741935484, "bacc_std": 0.08263900023621791} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05388122306231787, "f1": 0.5512437810945273, "f1_std": 0.09095522643144548, "bacc": 0.5516129032258065, "bacc_std": 0.07393603022936114} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.045550006513685445, "f1": 0.4831932773109243, "f1_std": 0.06975956034232422, "bacc": 0.5016129032258064, "bacc_std": 0.05331721134881839} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06413569419194315, "f1": 0.6232247284878863, "f1_std": 0.08905253122832428, "bacc": 0.6193548387096774, "bacc_std": 0.08590578388254486} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06875541836849493, "f1": 0.5199063231850116, "f1_std": 0.08137161694037863, "bacc": 0.5209677419354839, "bacc_std": 0.0845736226508185} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04801078106171425, "f1": 0.569327731092437, "f1_std": 0.09513392482534426, "bacc": 0.567741935483871, "bacc_std": 0.07260810921249163} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05789929512495542, "f1": 0.5340909090909092, "f1_std": 0.08400403510078056, "bacc": 0.535483870967742, "bacc_std": 0.07168083751032113} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 10000.0, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06498020565303168, "f1": 0.7184065934065934, "f1_std": 0.0676144474843503, "bacc": 0.7709677419354839, "bacc_std": 0.07102989243372626} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06204417838432612, "f1": 0.48621553884711777, "f1_std": 0.07636403309871119, "bacc": 0.48709677419354835, "bacc_std": 0.07349423473322145} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.05454302069453282, "f1": 0.4564393939393939, "f1_std": 0.06945923055045826, "bacc": 0.4693548387096774, "bacc_std": 0.06034267898749721} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06532791035617974, "f1": 0.6479313036690086, "f1_std": 0.0841864038763423, "bacc": 0.6532258064516129, "bacc_std": 0.08849999447374127} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.059474178181083664, "f1": 0.5729166666666666, "f1_std": 0.08128326156535075, "bacc": 0.5693548387096774, "bacc_std": 0.07582604901112043} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05400782105655274, "f1": 0.6117424242424243, "f1_std": 0.09064243997480538, "bacc": 0.6016129032258064, "bacc_std": 0.0774893097927321} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06352746060595407, "f1": 0.7280766396462786, "f1_std": 0.07688785060638173, "bacc": 0.7532258064516129, "bacc_std": 0.08377621198209358} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0674452473642773, "f1": 0.603225806451613, "f1_std": 0.08799988429535313, "bacc": 0.603225806451613, "bacc_std": 0.08815282556768737} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05417970846213771, "f1": 0.5918552036199095, "f1_std": 0.0873284452696744, "bacc": 0.5854838709677419, "bacc_std": 0.07758253796899608} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07107253460719393, "f1": 0.5651515151515152, "f1_std": 0.08561748648923428, "bacc": 0.5709677419354839, "bacc_std": 0.09166906978844769} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06250109338722366, "f1": 0.6693548387096775, "f1_std": 0.08448246322968005, "bacc": 0.6693548387096775, "bacc_std": 0.08618995936124477} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06681643102625476, "f1": 0.603225806451613, "f1_std": 0.08659437682810801, "bacc": 0.603225806451613, "bacc_std": 0.08699972873042498} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.056875287553776875, "f1": 0.6660633484162897, "f1_std": 0.09079898029117087, "bacc": 0.6516129032258065, "bacc_std": 0.08471292496784477} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05598969481114017, "f1": 0.5340909090909092, "f1_std": 0.08562649343758869, "bacc": 0.535483870967742, "bacc_std": 0.07289485956848292} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 2.782559402207126, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06785574508899295, "f1": 0.5199063231850116, "f1_std": 0.07928698708217709, "bacc": 0.5209677419354839, "bacc_std": 0.08110878885517} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.053235047250848926, "f1": 0.4696517412935323, "f1_std": 0.07093418985530682, "bacc": 0.4854838709677419, "bacc_std": 0.05916115172179212} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06699285657178554, "f1": 0.6676492262343405, "f1_std": 0.07795514480193572, "bacc": 0.6870967741935483, "bacc_std": 0.08237561089006214} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05156655945028289, "f1": 0.6117424242424243, "f1_std": 0.08786031110283825, "bacc": 0.6016129032258064, "bacc_std": 0.07501648101955832} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06781744049268727, "f1": 0.5370967741935484, "f1_std": 0.08472825245365669, "bacc": 0.5370967741935484, "bacc_std": 0.08439739079711578} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.055108459389210204, "f1": 0.5918552036199095, "f1_std": 0.08732511593403154, "bacc": 0.5854838709677419, "bacc_std": 0.07866206988309832} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06706937461541441, "f1": 0.5199063231850116, "f1_std": 0.07844156333693751, "bacc": 0.5209677419354839, "bacc_std": 0.08021442874298862} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0676937323828893, "f1": 0.6479313036690086, "f1_std": 0.08486261371421545, "bacc": 0.6532258064516129, "bacc_std": 0.08836860290390668} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adni_ad_vs_cn | train | 100 | 141.04 | 998.26 | 0.98019 | 0.036788 | 0.96825 | 0.062626 | 0.95896 | 0.074559 | +| flat_mae | reg | logistic | adni_ad_vs_cn | test | 100 | 141.04 | 998.26 | 0.71878 | 0.048837 | 0.59645 | 0.071943 | 0.59997 | 0.07359 | + + +done! total time: 0:04:47 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/config.yaml b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b17989599843dcbdf9f10dd12e89dc8413228230 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..b173671ae0f8f98b65185f207a02434b85693f70 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 15, "eval/id_best": 43, "eval/lr_best": 0.006599999999999999, "eval/wd_best": 0.05, "eval/train/loss": 0.0003156071761623025, "eval/train/acc": 1.0, "eval/train/acc_std": 0.0, "eval/train/f1": 1.0, "eval/train/f1_std": 0.0, "eval/validation/loss": 0.08574532717466354, "eval/validation/acc": 0.9776785714285714, "eval/validation/acc_std": 0.002202283252069319, "eval/validation/f1": 0.975474184318534, "eval/validation/f1_std": 0.002714569026385903, "eval/test/loss": 0.11182167381048203, "eval/test/acc": 0.9767857142857143, "eval/test/acc_std": 0.0022300995586117217, "eval/test/f1": 0.9712546053426488, "eval/test/f1_std": 0.002995368109971733} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..8f5cf441d219a3536fb5c9ca36ac1aa3e8d18955 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 15, "eval/best/id_best": 43, "eval/best/lr_best": 0.006599999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.0003156071761623025, "eval/best/train/acc": 1.0, "eval/best/train/acc_std": 0.0, "eval/best/train/f1": 1.0, "eval/best/train/f1_std": 0.0, "eval/best/validation/loss": 0.08574532717466354, "eval/best/validation/acc": 0.9776785714285714, "eval/best/validation/acc_std": 0.002202283252069319, "eval/best/validation/f1": 0.975474184318534, "eval/best/validation/f1_std": 0.002714569026385903, "eval/best/test/loss": 0.11182167381048203, "eval/best/test/acc": 0.9767857142857143, "eval/best/test/acc_std": 0.0022300995586117217, "eval/best/test/f1": 0.9712546053426488, "eval/best/test/f1_std": 0.002995368109971733} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..1b3b1b19453b0e6b12b81dddad6ff14e0848d59b --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 43, "eval/last/lr_best": 0.006599999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.0003290567547082901, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.0840374305844307, "eval/last/validation/acc": 0.9774305555555556, "eval/last/validation/acc_std": 0.0022350400069863167, "eval/last/validation/f1": 0.9748701211457332, "eval/last/validation/f1_std": 0.0027651921731292875, "eval/last/test/loss": 0.10974621027708054, "eval/last/test/acc": 0.9773809523809524, "eval/last/test/acc_std": 0.002186660575722479, "eval/last/test/f1": 0.9717735609970924, "eval/last/test/f1_std": 0.0029760652307716158} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..28342138489d0cd4c33d0c6f483edc220289b198 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,15,0.006599999999999999,0.05,43,"[22, 1.0]",train,0.0003156071761623025,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,15,0.006599999999999999,0.05,43,"[22, 1.0]",validation,0.08574532717466354,0.9776785714285714,0.002202283252069319,0.975474184318534,0.002714569026385903 +flat_mae,patch,attn,hcpya_task21,best,15,0.006599999999999999,0.05,43,"[22, 1.0]",test,0.11182167381048203,0.9767857142857143,0.0022300995586117217,0.9712546053426488,0.002995368109971733 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..28342138489d0cd4c33d0c6f483edc220289b198 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,15,0.006599999999999999,0.05,43,"[22, 1.0]",train,0.0003156071761623025,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,15,0.006599999999999999,0.05,43,"[22, 1.0]",validation,0.08574532717466354,0.9776785714285714,0.002202283252069319,0.975474184318534,0.002714569026385903 +flat_mae,patch,attn,hcpya_task21,best,15,0.006599999999999999,0.05,43,"[22, 1.0]",test,0.11182167381048203,0.9767857142857143,0.0022300995586117217,0.9712546053426488,0.002995368109971733 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..1d960476f96cbbcd1b7e350fdf90ba498308ce82 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",train,0.0003290567547082901,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",validation,0.0840374305844307,0.9774305555555556,0.0022350400069863167,0.9748701211457332,0.0027651921731292875 +flat_mae,patch,attn,hcpya_task21,last,19,0.006599999999999999,0.05,43,"[22, 1.0]",test,0.10974621027708054,0.9773809523809524,0.002186660575722479,0.9717735609970924,0.0029760652307716158 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/log.txt b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f2b363bfb0f2ba5057cdcbd9b935dc786e2754c7 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,890 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 22:17:22 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:17 lr: nan time: 3.6427 data: 3.0838 max mem: 21740 +train: [0] [ 20/400] eta: 0:03:59 lr: 0.000003 loss: 3.0406 (3.0407) grad: 0.0451 (0.0443) time: 0.4809 data: 0.0032 max mem: 22446 +train: [0] [ 40/400] eta: 0:03:19 lr: 0.000006 loss: 3.0370 (3.0355) grad: 0.0443 (0.0434) time: 0.4728 data: 0.0034 max mem: 22446 +train: [0] [ 60/400] eta: 0:02:58 lr: 0.000009 loss: 3.0155 (3.0247) grad: 0.0439 (0.0440) time: 0.4674 data: 0.0035 max mem: 22446 +train: [0] [ 80/400] eta: 0:02:44 lr: 0.000012 loss: 2.9916 (3.0134) grad: 0.0439 (0.0440) time: 0.4823 data: 0.0035 max mem: 22446 +train: [0] [100/400] eta: 0:02:31 lr: 0.000015 loss: 2.9413 (2.9932) grad: 0.0461 (0.0447) time: 0.4697 data: 0.0034 max mem: 22446 +train: [0] [120/400] eta: 0:02:19 lr: 0.000018 loss: 2.9019 (2.9742) grad: 0.0474 (0.0450) time: 0.4588 data: 0.0036 max mem: 22446 +train: [0] [140/400] eta: 0:02:07 lr: 0.000021 loss: 2.8393 (2.9539) grad: 0.0445 (0.0449) time: 0.4553 data: 0.0036 max mem: 22446 +train: [0] [160/400] eta: 0:01:57 lr: 0.000024 loss: 2.7998 (2.9289) grad: 0.0442 (0.0450) time: 0.4595 data: 0.0036 max mem: 22446 +train: [0] [180/400] eta: 0:01:46 lr: 0.000027 loss: 2.7470 (2.9059) grad: 0.0442 (0.0449) time: 0.4662 data: 0.0035 max mem: 22446 +train: [0] [200/400] eta: 0:01:36 lr: 0.000030 loss: 2.6682 (2.8774) grad: 0.0439 (0.0450) time: 0.4683 data: 0.0035 max mem: 22446 +train: [0] [220/400] eta: 0:01:26 lr: 0.000033 loss: 2.5776 (2.8484) grad: 0.0458 (0.0450) time: 0.4664 data: 0.0035 max mem: 22446 +train: [0] [240/400] eta: 0:01:16 lr: 0.000036 loss: 2.5065 (2.8200) grad: 0.0447 (0.0451) time: 0.4609 data: 0.0034 max mem: 22446 +train: [0] [260/400] eta: 0:01:07 lr: 0.000039 loss: 2.4653 (2.7904) grad: 0.0443 (0.0451) time: 0.4680 data: 0.0037 max mem: 22446 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 2.4147 (2.7626) grad: 0.0433 (0.0450) time: 0.4607 data: 0.0035 max mem: 22446 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 2.3417 (2.7324) grad: 0.0447 (0.0451) time: 0.6524 data: 0.1781 max mem: 22446 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 2.2942 (2.7035) grad: 0.0452 (0.0451) time: 0.4520 data: 0.0034 max mem: 22446 +train: [0] [340/400] eta: 0:00:29 lr: 0.000051 loss: 2.2496 (2.6744) grad: 0.0440 (0.0451) time: 0.4633 data: 0.0032 max mem: 22446 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 2.2059 (2.6484) grad: 0.0426 (0.0450) time: 0.4640 data: 0.0035 max mem: 22446 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 2.1825 (2.6206) grad: 0.0437 (0.0451) time: 0.4758 data: 0.0033 max mem: 22446 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.1263 (2.5958) grad: 0.0444 (0.0450) time: 0.4676 data: 0.0035 max mem: 22446 +train: [0] Total time: 0:03:13 (0.4838 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.1263 (2.5958) grad: 0.0444 (0.0450) +eval (validation): [0] [ 0/63] eta: 0:03:31 time: 3.3544 data: 3.1075 max mem: 22446 +eval (validation): [0] [20/63] eta: 0:00:21 time: 0.3505 data: 0.0040 max mem: 22446 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3558 data: 0.0033 max mem: 22446 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3659 data: 0.0031 max mem: 22446 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3539 data: 0.0032 max mem: 22446 +eval (validation): [0] Total time: 0:00:25 (0.4096 s / it) +cv: [0] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.170 acc: 0.951 f1: 0.945 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:23:16 lr: nan time: 3.4921 data: 3.0833 max mem: 22446 +train: [1] [ 20/400] eta: 0:04:05 lr: 0.000063 loss: 2.0869 (2.0832) grad: 0.0426 (0.0437) time: 0.5051 data: 0.0029 max mem: 22446 +train: [1] [ 40/400] eta: 0:03:24 lr: 0.000066 loss: 2.0665 (2.0593) grad: 0.0433 (0.0443) time: 0.4860 data: 0.0035 max mem: 22446 +train: [1] [ 60/400] eta: 0:03:01 lr: 0.000069 loss: 2.0209 (2.0432) grad: 0.0443 (0.0445) time: 0.4594 data: 0.0033 max mem: 22446 +train: [1] [ 80/400] eta: 0:02:46 lr: 0.000072 loss: 1.9670 (2.0174) grad: 0.0452 (0.0452) time: 0.4769 data: 0.0035 max mem: 22446 +train: [1] [100/400] eta: 0:02:31 lr: 0.000075 loss: 1.9261 (1.9957) grad: 0.0445 (0.0449) time: 0.4539 data: 0.0034 max mem: 22446 +train: [1] [120/400] eta: 0:02:20 lr: 0.000078 loss: 1.8944 (1.9820) grad: 0.0423 (0.0445) time: 0.4818 data: 0.0035 max mem: 22446 +train: [1] [140/400] eta: 0:02:09 lr: 0.000081 loss: 1.8944 (1.9696) grad: 0.0407 (0.0441) time: 0.4721 data: 0.0035 max mem: 22446 +train: [1] [160/400] eta: 0:01:58 lr: 0.000084 loss: 1.8814 (1.9570) grad: 0.0399 (0.0437) time: 0.4654 data: 0.0035 max mem: 22446 +train: [1] [180/400] eta: 0:01:48 lr: 0.000087 loss: 1.8615 (1.9460) grad: 0.0407 (0.0435) time: 0.4728 data: 0.0036 max mem: 22446 +train: [1] [200/400] eta: 0:01:37 lr: 0.000090 loss: 1.8348 (1.9307) grad: 0.0414 (0.0435) time: 0.4687 data: 0.0036 max mem: 22446 +train: [1] [220/400] eta: 0:01:27 lr: 0.000093 loss: 1.7979 (1.9184) grad: 0.0426 (0.0434) time: 0.4614 data: 0.0034 max mem: 22446 +train: [1] [240/400] eta: 0:01:17 lr: 0.000096 loss: 1.7806 (1.9044) grad: 0.0423 (0.0433) time: 0.4780 data: 0.0034 max mem: 22446 +train: [1] [260/400] eta: 0:01:07 lr: 0.000099 loss: 1.7173 (1.8885) grad: 0.0418 (0.0432) time: 0.4690 data: 0.0031 max mem: 22446 +train: [1] [280/400] eta: 0:00:58 lr: 0.000102 loss: 1.6965 (1.8743) grad: 0.0417 (0.0432) time: 0.4665 data: 0.0035 max mem: 22446 +train: [1] [300/400] eta: 0:00:49 lr: 0.000105 loss: 1.6846 (1.8622) grad: 0.0417 (0.0430) time: 0.6318 data: 0.1815 max mem: 22446 +train: [1] [320/400] eta: 0:00:39 lr: 0.000108 loss: 1.6801 (1.8501) grad: 0.0408 (0.0429) time: 0.4556 data: 0.0030 max mem: 22446 +train: [1] [340/400] eta: 0:00:29 lr: 0.000111 loss: 1.6622 (1.8385) grad: 0.0422 (0.0429) time: 0.4641 data: 0.0034 max mem: 22446 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 1.6208 (1.8259) grad: 0.0419 (0.0428) time: 0.4466 data: 0.0033 max mem: 22446 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 1.5942 (1.8135) grad: 0.0404 (0.0427) time: 0.4929 data: 0.0034 max mem: 22446 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 1.5725 (1.8011) grad: 0.0404 (0.0427) time: 0.4648 data: 0.0033 max mem: 22446 +train: [1] Total time: 0:03:14 (0.4864 s / it) +train: [1] Summary: lr: 0.000120 loss: 1.5725 (1.8011) grad: 0.0404 (0.0427) +eval (validation): [1] [ 0/63] eta: 0:03:35 time: 3.4253 data: 3.1281 max mem: 22446 +eval (validation): [1] [20/63] eta: 0:00:23 time: 0.3907 data: 0.0032 max mem: 22446 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3607 data: 0.0030 max mem: 22446 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3373 data: 0.0033 max mem: 22446 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3376 data: 0.0033 max mem: 22446 +eval (validation): [1] Total time: 0:00:26 (0.4157 s / it) +cv: [1] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.132 acc: 0.962 f1: 0.957 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:23:32 lr: nan time: 3.5309 data: 3.1189 max mem: 22446 +train: [2] [ 20/400] eta: 0:03:54 lr: 0.000123 loss: 1.5439 (1.5535) grad: 0.0413 (0.0411) time: 0.4705 data: 0.0032 max mem: 22446 +train: [2] [ 40/400] eta: 0:03:17 lr: 0.000126 loss: 1.5423 (1.5460) grad: 0.0403 (0.0404) time: 0.4794 data: 0.0036 max mem: 22446 +train: [2] [ 60/400] eta: 0:02:57 lr: 0.000129 loss: 1.5173 (1.5343) grad: 0.0408 (0.0407) time: 0.4682 data: 0.0034 max mem: 22446 +train: [2] [ 80/400] eta: 0:02:43 lr: 0.000132 loss: 1.5068 (1.5270) grad: 0.0407 (0.0403) time: 0.4774 data: 0.0035 max mem: 22446 +train: [2] [100/400] eta: 0:02:29 lr: 0.000135 loss: 1.4961 (1.5220) grad: 0.0405 (0.0405) time: 0.4516 data: 0.0034 max mem: 22446 +train: [2] [120/400] eta: 0:02:18 lr: 0.000138 loss: 1.4862 (1.5161) grad: 0.0410 (0.0407) time: 0.4711 data: 0.0035 max mem: 22446 +train: [2] [140/400] eta: 0:02:07 lr: 0.000141 loss: 1.4802 (1.5101) grad: 0.0419 (0.0408) time: 0.4709 data: 0.0036 max mem: 22446 +train: [2] [160/400] eta: 0:01:57 lr: 0.000144 loss: 1.4523 (1.5030) grad: 0.0409 (0.0409) time: 0.4708 data: 0.0035 max mem: 22446 +train: [2] [180/400] eta: 0:01:46 lr: 0.000147 loss: 1.4307 (1.4939) grad: 0.0403 (0.0408) time: 0.4628 data: 0.0034 max mem: 22446 +train: [2] [200/400] eta: 0:01:36 lr: 0.000150 loss: 1.4052 (1.4859) grad: 0.0401 (0.0408) time: 0.4600 data: 0.0034 max mem: 22446 +train: [2] [220/400] eta: 0:01:26 lr: 0.000153 loss: 1.3907 (1.4785) grad: 0.0423 (0.0410) time: 0.4637 data: 0.0034 max mem: 22446 +train: [2] [240/400] eta: 0:01:16 lr: 0.000156 loss: 1.3911 (1.4713) grad: 0.0423 (0.0411) time: 0.4602 data: 0.0033 max mem: 22446 +train: [2] [260/400] eta: 0:01:06 lr: 0.000159 loss: 1.3760 (1.4627) grad: 0.0405 (0.0411) time: 0.4606 data: 0.0035 max mem: 22446 +train: [2] [280/400] eta: 0:00:57 lr: 0.000162 loss: 1.3686 (1.4569) grad: 0.0411 (0.0411) time: 0.4637 data: 0.0035 max mem: 22446 +train: [2] [300/400] eta: 0:00:48 lr: 0.000165 loss: 1.3539 (1.4480) grad: 0.0411 (0.0412) time: 0.6288 data: 0.1783 max mem: 22446 +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 1.3139 (1.4404) grad: 0.0401 (0.0411) time: 0.4601 data: 0.0030 max mem: 22446 +train: [2] [340/400] eta: 0:00:29 lr: 0.000171 loss: 1.3182 (1.4338) grad: 0.0398 (0.0411) time: 0.4759 data: 0.0033 max mem: 22446 +train: [2] [360/400] eta: 0:00:19 lr: 0.000174 loss: 1.3100 (1.4262) grad: 0.0396 (0.0410) time: 0.4568 data: 0.0033 max mem: 22446 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 1.2930 (1.4192) grad: 0.0397 (0.0410) time: 0.4797 data: 0.0035 max mem: 22446 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 1.2930 (1.4117) grad: 0.0390 (0.0409) time: 0.4866 data: 0.0034 max mem: 22446 +train: [2] Total time: 0:03:13 (0.4839 s / it) +train: [2] Summary: lr: 0.000180 loss: 1.2930 (1.4117) grad: 0.0390 (0.0409) +eval (validation): [2] [ 0/63] eta: 0:03:37 time: 3.4484 data: 3.1338 max mem: 22446 +eval (validation): [2] [20/63] eta: 0:00:23 time: 0.3896 data: 0.0035 max mem: 22446 +eval (validation): [2] [40/63] eta: 0:00:10 time: 0.3564 data: 0.0032 max mem: 22446 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3507 data: 0.0032 max mem: 22446 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3424 data: 0.0032 max mem: 22446 +eval (validation): [2] Total time: 0:00:26 (0.4184 s / it) +cv: [2] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.118 acc: 0.964 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:23:14 lr: nan time: 3.4853 data: 3.1359 max mem: 22446 +train: [3] [ 20/400] eta: 0:03:56 lr: 0.000183 loss: 1.2633 (1.2560) grad: 0.0383 (0.0402) time: 0.4780 data: 0.0035 max mem: 22446 +train: [3] [ 40/400] eta: 0:03:18 lr: 0.000186 loss: 1.2611 (1.2531) grad: 0.0387 (0.0399) time: 0.4790 data: 0.0033 max mem: 22446 +train: [3] [ 60/400] eta: 0:02:57 lr: 0.000189 loss: 1.2351 (1.2468) grad: 0.0390 (0.0397) time: 0.4632 data: 0.0035 max mem: 22446 +train: [3] [ 80/400] eta: 0:02:43 lr: 0.000192 loss: 1.2212 (1.2439) grad: 0.0413 (0.0408) time: 0.4730 data: 0.0034 max mem: 22446 +train: [3] [100/400] eta: 0:02:30 lr: 0.000195 loss: 1.2223 (1.2439) grad: 0.0416 (0.0411) time: 0.4699 data: 0.0035 max mem: 22446 +train: [3] [120/400] eta: 0:02:18 lr: 0.000198 loss: 1.2437 (1.2428) grad: 0.0414 (0.0414) time: 0.4627 data: 0.0034 max mem: 22446 +train: [3] [140/400] eta: 0:02:07 lr: 0.000201 loss: 1.2111 (1.2365) grad: 0.0418 (0.0416) time: 0.4625 data: 0.0037 max mem: 22446 +train: [3] [160/400] eta: 0:01:57 lr: 0.000204 loss: 1.2022 (1.2312) grad: 0.0438 (0.0418) time: 0.4661 data: 0.0036 max mem: 22446 +train: [3] [180/400] eta: 0:01:46 lr: 0.000207 loss: 1.1718 (1.2252) grad: 0.0427 (0.0418) time: 0.4698 data: 0.0035 max mem: 22446 +train: [3] [200/400] eta: 0:01:36 lr: 0.000210 loss: 1.1855 (1.2233) grad: 0.0403 (0.0418) time: 0.4582 data: 0.0035 max mem: 22446 +train: [3] [220/400] eta: 0:01:26 lr: 0.000213 loss: 1.1917 (1.2196) grad: 0.0410 (0.0420) time: 0.4745 data: 0.0035 max mem: 22446 +train: [3] [240/400] eta: 0:01:17 lr: 0.000216 loss: 1.1539 (1.2123) grad: 0.0427 (0.0421) time: 0.4697 data: 0.0034 max mem: 22446 +train: [3] [260/400] eta: 0:01:07 lr: 0.000219 loss: 1.1210 (1.2066) grad: 0.0436 (0.0422) time: 0.4755 data: 0.0034 max mem: 22446 +train: [3] [280/400] eta: 0:00:57 lr: 0.000222 loss: 1.1319 (1.2028) grad: 0.0432 (0.0422) time: 0.4619 data: 0.0034 max mem: 22446 +train: [3] [300/400] eta: 0:00:49 lr: 0.000225 loss: 1.1353 (1.1982) grad: 0.0432 (0.0424) time: 0.6677 data: 0.1912 max mem: 22446 +train: [3] [320/400] eta: 0:00:39 lr: 0.000228 loss: 1.1107 (1.1912) grad: 0.0444 (0.0426) time: 0.4756 data: 0.0029 max mem: 22446 +train: [3] [340/400] eta: 0:00:29 lr: 0.000231 loss: 1.1059 (1.1858) grad: 0.0448 (0.0427) time: 0.4574 data: 0.0032 max mem: 22446 +train: [3] [360/400] eta: 0:00:19 lr: 0.000234 loss: 1.0779 (1.1801) grad: 0.0428 (0.0427) time: 0.4652 data: 0.0034 max mem: 22446 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 1.0771 (1.1749) grad: 0.0428 (0.0427) time: 0.4767 data: 0.0035 max mem: 22446 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 1.0817 (1.1702) grad: 0.0440 (0.0429) time: 0.4712 data: 0.0036 max mem: 22446 +train: [3] Total time: 0:03:14 (0.4867 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.0817 (1.1702) grad: 0.0440 (0.0429) +eval (validation): [3] [ 0/63] eta: 0:03:34 time: 3.4078 data: 3.1622 max mem: 22446 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3550 data: 0.0038 max mem: 22446 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3486 data: 0.0028 max mem: 22446 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3224 data: 0.0029 max mem: 22446 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3222 data: 0.0028 max mem: 22446 +eval (validation): [3] Total time: 0:00:24 (0.3961 s / it) +cv: [3] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 0.120 acc: 0.965 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:23:09 lr: nan time: 3.4736 data: 3.1273 max mem: 22446 +train: [4] [ 20/400] eta: 0:03:57 lr: 0.000243 loss: 1.0904 (1.0921) grad: 0.0452 (0.0459) time: 0.4828 data: 0.0043 max mem: 22446 +train: [4] [ 40/400] eta: 0:03:20 lr: 0.000246 loss: 1.0854 (1.0704) grad: 0.0459 (0.0466) time: 0.4832 data: 0.0032 max mem: 22446 +train: [4] [ 60/400] eta: 0:02:57 lr: 0.000249 loss: 1.0222 (1.0632) grad: 0.0467 (0.0464) time: 0.4565 data: 0.0033 max mem: 22446 +train: [4] [ 80/400] eta: 0:02:44 lr: 0.000252 loss: 1.0619 (1.0699) grad: 0.0466 (0.0466) time: 0.4896 data: 0.0034 max mem: 22446 +train: [4] [100/400] eta: 0:02:32 lr: 0.000255 loss: 1.0543 (1.0621) grad: 0.0466 (0.0466) time: 0.4846 data: 0.0035 max mem: 22446 +train: [4] [120/400] eta: 0:02:20 lr: 0.000258 loss: 1.0258 (1.0592) grad: 0.0486 (0.0473) time: 0.4570 data: 0.0035 max mem: 22446 +train: [4] [140/400] eta: 0:02:09 lr: 0.000261 loss: 1.0383 (1.0566) grad: 0.0491 (0.0474) time: 0.4804 data: 0.0037 max mem: 22446 +train: [4] [160/400] eta: 0:01:58 lr: 0.000264 loss: 1.0366 (1.0510) grad: 0.0484 (0.0477) time: 0.4638 data: 0.0036 max mem: 22446 +train: [4] [180/400] eta: 0:01:47 lr: 0.000267 loss: 1.0089 (1.0475) grad: 0.0489 (0.0479) time: 0.4619 data: 0.0036 max mem: 22446 +train: [4] [200/400] eta: 0:01:37 lr: 0.000270 loss: 1.0089 (1.0440) grad: 0.0480 (0.0478) time: 0.4677 data: 0.0036 max mem: 22446 +train: [4] [220/400] eta: 0:01:27 lr: 0.000273 loss: 0.9939 (1.0402) grad: 0.0496 (0.0482) time: 0.4632 data: 0.0034 max mem: 22446 +train: [4] [240/400] eta: 0:01:17 lr: 0.000276 loss: 1.0003 (1.0403) grad: 0.0498 (0.0486) time: 0.4535 data: 0.0033 max mem: 22446 +train: [4] [260/400] eta: 0:01:07 lr: 0.000279 loss: 0.9970 (1.0353) grad: 0.0498 (0.0492) time: 0.4719 data: 0.0034 max mem: 22446 +train: [4] [280/400] eta: 0:00:57 lr: 0.000282 loss: 0.9849 (1.0352) grad: 0.0518 (0.0494) time: 0.4659 data: 0.0036 max mem: 22446 +train: [4] [300/400] eta: 0:00:49 lr: 0.000285 loss: 1.0130 (1.0314) grad: 0.0501 (0.0495) time: 0.6291 data: 0.1827 max mem: 22446 +train: [4] [320/400] eta: 0:00:39 lr: 0.000288 loss: 0.9936 (1.0288) grad: 0.0503 (0.0497) time: 0.4537 data: 0.0034 max mem: 22446 +train: [4] [340/400] eta: 0:00:29 lr: 0.000291 loss: 0.9897 (1.0251) grad: 0.0515 (0.0498) time: 0.4648 data: 0.0034 max mem: 22446 +train: [4] [360/400] eta: 0:00:19 lr: 0.000294 loss: 0.9371 (1.0191) grad: 0.0506 (0.0497) time: 0.4727 data: 0.0036 max mem: 22446 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.9369 (1.0161) grad: 0.0469 (0.0497) time: 0.4759 data: 0.0035 max mem: 22446 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.9486 (1.0136) grad: 0.0484 (0.0498) time: 0.4746 data: 0.0034 max mem: 22446 +train: [4] Total time: 0:03:14 (0.4855 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.9486 (1.0136) grad: 0.0484 (0.0498) +eval (validation): [4] [ 0/63] eta: 0:03:27 time: 3.2976 data: 3.0512 max mem: 22446 +eval (validation): [4] [20/63] eta: 0:00:22 time: 0.3803 data: 0.0177 max mem: 22446 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3426 data: 0.0022 max mem: 22446 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3480 data: 0.0030 max mem: 22446 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3473 data: 0.0024 max mem: 22446 +eval (validation): [4] Total time: 0:00:25 (0.4098 s / it) +cv: [4] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.104 acc: 0.971 f1: 0.968 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:23:37 lr: nan time: 3.5439 data: 3.1864 max mem: 22446 +train: [5] [ 20/400] eta: 0:04:01 lr: 0.000300 loss: 0.9329 (0.9433) grad: 0.0471 (0.0501) time: 0.4898 data: 0.0032 max mem: 22446 +train: [5] [ 40/400] eta: 0:03:19 lr: 0.000300 loss: 0.9329 (0.9335) grad: 0.0490 (0.0502) time: 0.4685 data: 0.0034 max mem: 22446 +train: [5] [ 60/400] eta: 0:02:57 lr: 0.000300 loss: 0.9336 (0.9291) grad: 0.0490 (0.0494) time: 0.4572 data: 0.0033 max mem: 22446 +train: [5] [ 80/400] eta: 0:02:44 lr: 0.000300 loss: 0.9044 (0.9212) grad: 0.0494 (0.0501) time: 0.4881 data: 0.0035 max mem: 22446 +train: [5] [100/400] eta: 0:02:32 lr: 0.000300 loss: 0.8995 (0.9149) grad: 0.0502 (0.0501) time: 0.4782 data: 0.0037 max mem: 22446 +train: [5] [120/400] eta: 0:02:19 lr: 0.000300 loss: 0.9016 (0.9183) grad: 0.0502 (0.0506) time: 0.4619 data: 0.0035 max mem: 22446 +train: [5] [140/400] eta: 0:02:08 lr: 0.000300 loss: 0.8868 (0.9135) grad: 0.0502 (0.0504) time: 0.4723 data: 0.0035 max mem: 22446 +train: [5] [160/400] eta: 0:01:58 lr: 0.000299 loss: 0.8867 (0.9179) grad: 0.0512 (0.0509) time: 0.4699 data: 0.0034 max mem: 22446 +train: [5] [180/400] eta: 0:01:47 lr: 0.000299 loss: 0.8867 (0.9104) grad: 0.0512 (0.0508) time: 0.4627 data: 0.0034 max mem: 22446 +train: [5] [200/400] eta: 0:01:37 lr: 0.000299 loss: 0.8663 (0.9101) grad: 0.0518 (0.0509) time: 0.4548 data: 0.0031 max mem: 22446 +train: [5] [220/400] eta: 0:01:27 lr: 0.000299 loss: 0.8547 (0.9053) grad: 0.0523 (0.0510) time: 0.4773 data: 0.0034 max mem: 22446 +train: [5] [240/400] eta: 0:01:17 lr: 0.000299 loss: 0.8547 (0.9031) grad: 0.0496 (0.0509) time: 0.4634 data: 0.0037 max mem: 22446 +train: [5] [260/400] eta: 0:01:07 lr: 0.000299 loss: 0.8703 (0.9008) grad: 0.0516 (0.0510) time: 0.4685 data: 0.0035 max mem: 22446 +train: [5] [280/400] eta: 0:00:57 lr: 0.000298 loss: 0.8540 (0.8992) grad: 0.0523 (0.0510) time: 0.4763 data: 0.0036 max mem: 22446 +train: [5] [300/400] eta: 0:00:49 lr: 0.000298 loss: 0.8540 (0.8979) grad: 0.0487 (0.0508) time: 0.6495 data: 0.1829 max mem: 22446 +train: [5] [320/400] eta: 0:00:39 lr: 0.000298 loss: 0.8219 (0.8927) grad: 0.0474 (0.0506) time: 0.4531 data: 0.0032 max mem: 22446 +train: [5] [340/400] eta: 0:00:29 lr: 0.000298 loss: 0.7915 (0.8869) grad: 0.0466 (0.0504) time: 0.4607 data: 0.0034 max mem: 22446 +train: [5] [360/400] eta: 0:00:19 lr: 0.000297 loss: 0.8134 (0.8832) grad: 0.0465 (0.0502) time: 0.4609 data: 0.0034 max mem: 22446 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.8066 (0.8781) grad: 0.0454 (0.0499) time: 0.4745 data: 0.0035 max mem: 22446 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.8002 (0.8741) grad: 0.0454 (0.0498) time: 0.4589 data: 0.0034 max mem: 22446 +train: [5] Total time: 0:03:14 (0.4853 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.8002 (0.8741) grad: 0.0454 (0.0498) +eval (validation): [5] [ 0/63] eta: 0:03:22 time: 3.2203 data: 2.9721 max mem: 22446 +eval (validation): [5] [20/63] eta: 0:00:21 time: 0.3640 data: 0.0039 max mem: 22446 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3542 data: 0.0031 max mem: 22446 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3354 data: 0.0031 max mem: 22446 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3311 data: 0.0032 max mem: 22446 +eval (validation): [5] Total time: 0:00:25 (0.4006 s / it) +cv: [5] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.096 acc: 0.972 f1: 0.970 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:23:00 lr: nan time: 3.4504 data: 3.0361 max mem: 22446 +train: [6] [ 20/400] eta: 0:03:52 lr: 0.000296 loss: 0.8325 (0.8232) grad: 0.0452 (0.0472) time: 0.4696 data: 0.0028 max mem: 22446 +train: [6] [ 40/400] eta: 0:03:12 lr: 0.000296 loss: 0.7926 (0.8003) grad: 0.0441 (0.0453) time: 0.4541 data: 0.0033 max mem: 22446 +train: [6] [ 60/400] eta: 0:02:52 lr: 0.000296 loss: 0.7800 (0.7940) grad: 0.0431 (0.0458) time: 0.4482 data: 0.0036 max mem: 22446 +train: [6] [ 80/400] eta: 0:02:38 lr: 0.000295 loss: 0.7708 (0.7883) grad: 0.0448 (0.0455) time: 0.4656 data: 0.0035 max mem: 22446 +train: [6] [100/400] eta: 0:02:26 lr: 0.000295 loss: 0.7525 (0.7826) grad: 0.0441 (0.0454) time: 0.4580 data: 0.0035 max mem: 22446 +train: [6] [120/400] eta: 0:02:15 lr: 0.000295 loss: 0.7549 (0.7823) grad: 0.0453 (0.0456) time: 0.4633 data: 0.0034 max mem: 22446 +train: [6] [140/400] eta: 0:02:05 lr: 0.000294 loss: 0.7816 (0.7824) grad: 0.0476 (0.0461) time: 0.4607 data: 0.0034 max mem: 22446 +train: [6] [160/400] eta: 0:01:54 lr: 0.000294 loss: 0.7683 (0.7821) grad: 0.0475 (0.0459) time: 0.4489 data: 0.0035 max mem: 22446 +train: [6] [180/400] eta: 0:01:44 lr: 0.000293 loss: 0.7537 (0.7814) grad: 0.0453 (0.0461) time: 0.4588 data: 0.0034 max mem: 22446 +train: [6] [200/400] eta: 0:01:34 lr: 0.000293 loss: 0.7426 (0.7794) grad: 0.0446 (0.0461) time: 0.4554 data: 0.0034 max mem: 22446 +train: [6] [220/400] eta: 0:01:24 lr: 0.000292 loss: 0.7604 (0.7785) grad: 0.0437 (0.0462) time: 0.4517 data: 0.0035 max mem: 22446 +train: [6] [240/400] eta: 0:01:15 lr: 0.000292 loss: 0.7658 (0.7770) grad: 0.0466 (0.0464) time: 0.4529 data: 0.0035 max mem: 22446 +train: [6] [260/400] eta: 0:01:05 lr: 0.000291 loss: 0.7711 (0.7774) grad: 0.0482 (0.0467) time: 0.4484 data: 0.0038 max mem: 22446 +train: [6] [280/400] eta: 0:00:56 lr: 0.000291 loss: 0.7529 (0.7736) grad: 0.0477 (0.0466) time: 0.4788 data: 0.0037 max mem: 22446 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 0.7427 (0.7726) grad: 0.0449 (0.0464) time: 0.6242 data: 0.1801 max mem: 22446 +train: [6] [320/400] eta: 0:00:38 lr: 0.000290 loss: 0.7202 (0.7688) grad: 0.0441 (0.0462) time: 0.4536 data: 0.0036 max mem: 22446 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.7077 (0.7667) grad: 0.0409 (0.0460) time: 0.4526 data: 0.0031 max mem: 22446 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 0.7053 (0.7627) grad: 0.0403 (0.0457) time: 0.4507 data: 0.0031 max mem: 22446 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.7053 (0.7603) grad: 0.0403 (0.0455) time: 0.4823 data: 0.0034 max mem: 22446 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.7012 (0.7567) grad: 0.0412 (0.0453) time: 0.4747 data: 0.0036 max mem: 22446 +train: [6] Total time: 0:03:10 (0.4753 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.7012 (0.7567) grad: 0.0412 (0.0453) +eval (validation): [6] [ 0/63] eta: 0:03:29 time: 3.3308 data: 3.0957 max mem: 22446 +eval (validation): [6] [20/63] eta: 0:00:20 time: 0.3332 data: 0.0077 max mem: 22446 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3519 data: 0.0031 max mem: 22446 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3517 data: 0.0030 max mem: 22446 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3393 data: 0.0033 max mem: 22446 +eval (validation): [6] Total time: 0:00:25 (0.3992 s / it) +cv: [6] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.089 acc: 0.972 f1: 0.968 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:23:07 lr: nan time: 3.4691 data: 3.0735 max mem: 22446 +train: [7] [ 20/400] eta: 0:03:59 lr: 0.000286 loss: 0.6839 (0.6988) grad: 0.0391 (0.0400) time: 0.4892 data: 0.0033 max mem: 22446 +train: [7] [ 40/400] eta: 0:03:19 lr: 0.000286 loss: 0.6839 (0.6928) grad: 0.0389 (0.0393) time: 0.4706 data: 0.0032 max mem: 22446 +train: [7] [ 60/400] eta: 0:02:57 lr: 0.000285 loss: 0.6923 (0.6949) grad: 0.0385 (0.0391) time: 0.4621 data: 0.0034 max mem: 22446 +train: [7] [ 80/400] eta: 0:02:43 lr: 0.000284 loss: 0.6923 (0.6956) grad: 0.0386 (0.0391) time: 0.4689 data: 0.0035 max mem: 22446 +train: [7] [100/400] eta: 0:02:30 lr: 0.000284 loss: 0.6894 (0.6955) grad: 0.0392 (0.0394) time: 0.4641 data: 0.0034 max mem: 22446 +train: [7] [120/400] eta: 0:02:18 lr: 0.000283 loss: 0.6838 (0.6926) grad: 0.0394 (0.0393) time: 0.4634 data: 0.0035 max mem: 22446 +train: [7] [140/400] eta: 0:02:07 lr: 0.000282 loss: 0.6654 (0.6891) grad: 0.0382 (0.0391) time: 0.4648 data: 0.0034 max mem: 22446 +train: [7] [160/400] eta: 0:01:56 lr: 0.000282 loss: 0.6597 (0.6859) grad: 0.0382 (0.0391) time: 0.4595 data: 0.0033 max mem: 22446 +train: [7] [180/400] eta: 0:01:46 lr: 0.000281 loss: 0.6634 (0.6850) grad: 0.0387 (0.0391) time: 0.4582 data: 0.0034 max mem: 22446 +train: [7] [200/400] eta: 0:01:36 lr: 0.000280 loss: 0.6634 (0.6838) grad: 0.0400 (0.0392) time: 0.4551 data: 0.0034 max mem: 22446 +train: [7] [220/400] eta: 0:01:26 lr: 0.000279 loss: 0.6553 (0.6823) grad: 0.0400 (0.0394) time: 0.4601 data: 0.0035 max mem: 22446 +train: [7] [240/400] eta: 0:01:16 lr: 0.000278 loss: 0.6571 (0.6803) grad: 0.0378 (0.0394) time: 0.4635 data: 0.0033 max mem: 22446 +train: [7] [260/400] eta: 0:01:06 lr: 0.000278 loss: 0.6605 (0.6799) grad: 0.0378 (0.0394) time: 0.4476 data: 0.0033 max mem: 22446 +train: [7] [280/400] eta: 0:00:56 lr: 0.000277 loss: 0.6549 (0.6775) grad: 0.0380 (0.0394) time: 0.4636 data: 0.0035 max mem: 22446 +train: [7] [300/400] eta: 0:00:48 lr: 0.000276 loss: 0.6298 (0.6764) grad: 0.0373 (0.0394) time: 0.6213 data: 0.1785 max mem: 22446 +train: [7] [320/400] eta: 0:00:38 lr: 0.000275 loss: 0.6578 (0.6748) grad: 0.0373 (0.0392) time: 0.4571 data: 0.0066 max mem: 22446 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 0.6339 (0.6723) grad: 0.0349 (0.0389) time: 0.4708 data: 0.0037 max mem: 22446 +train: [7] [360/400] eta: 0:00:19 lr: 0.000273 loss: 0.6314 (0.6706) grad: 0.0338 (0.0387) time: 0.4626 data: 0.0032 max mem: 22446 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.6199 (0.6675) grad: 0.0350 (0.0386) time: 0.4766 data: 0.0036 max mem: 22446 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.6223 (0.6656) grad: 0.0348 (0.0384) time: 0.4723 data: 0.0035 max mem: 22446 +train: [7] Total time: 0:03:12 (0.4804 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.6223 (0.6656) grad: 0.0348 (0.0384) +eval (validation): [7] [ 0/63] eta: 0:03:26 time: 3.2724 data: 2.9995 max mem: 22446 +eval (validation): [7] [20/63] eta: 0:00:22 time: 0.3754 data: 0.0039 max mem: 22446 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3887 data: 0.0034 max mem: 22446 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3372 data: 0.0034 max mem: 22446 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3380 data: 0.0034 max mem: 22446 +eval (validation): [7] Total time: 0:00:26 (0.4166 s / it) +cv: [7] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.091 acc: 0.976 f1: 0.973 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:23:24 lr: nan time: 3.5103 data: 3.1610 max mem: 22446 +train: [8] [ 20/400] eta: 0:03:56 lr: 0.000270 loss: 0.6070 (0.6159) grad: 0.0350 (0.0368) time: 0.4788 data: 0.0035 max mem: 22446 +train: [8] [ 40/400] eta: 0:03:10 lr: 0.000270 loss: 0.6078 (0.6197) grad: 0.0355 (0.0365) time: 0.4328 data: 0.0028 max mem: 22446 +train: [8] [ 60/400] eta: 0:02:54 lr: 0.000269 loss: 0.6154 (0.6182) grad: 0.0355 (0.0360) time: 0.4738 data: 0.0035 max mem: 22446 +train: [8] [ 80/400] eta: 0:02:40 lr: 0.000268 loss: 0.6255 (0.6181) grad: 0.0356 (0.0358) time: 0.4692 data: 0.0034 max mem: 22446 +train: [8] [100/400] eta: 0:02:27 lr: 0.000267 loss: 0.6170 (0.6175) grad: 0.0355 (0.0359) time: 0.4513 data: 0.0034 max mem: 22446 +train: [8] [120/400] eta: 0:02:16 lr: 0.000266 loss: 0.6184 (0.6194) grad: 0.0356 (0.0360) time: 0.4650 data: 0.0034 max mem: 22446 +train: [8] [140/400] eta: 0:02:05 lr: 0.000265 loss: 0.6225 (0.6205) grad: 0.0370 (0.0363) time: 0.4652 data: 0.0035 max mem: 22446 +train: [8] [160/400] eta: 0:01:55 lr: 0.000264 loss: 0.6305 (0.6205) grad: 0.0361 (0.0363) time: 0.4480 data: 0.0034 max mem: 22446 +train: [8] [180/400] eta: 0:01:44 lr: 0.000263 loss: 0.6272 (0.6202) grad: 0.0350 (0.0361) time: 0.4410 data: 0.0032 max mem: 22446 +train: [8] [200/400] eta: 0:01:34 lr: 0.000262 loss: 0.6019 (0.6182) grad: 0.0359 (0.0360) time: 0.4577 data: 0.0032 max mem: 22446 +train: [8] [220/400] eta: 0:01:24 lr: 0.000260 loss: 0.6082 (0.6177) grad: 0.0348 (0.0359) time: 0.4589 data: 0.0033 max mem: 22446 +train: [8] [240/400] eta: 0:01:15 lr: 0.000259 loss: 0.5906 (0.6140) grad: 0.0343 (0.0358) time: 0.4530 data: 0.0034 max mem: 22446 +train: [8] [260/400] eta: 0:01:05 lr: 0.000258 loss: 0.5724 (0.6116) grad: 0.0337 (0.0356) time: 0.4589 data: 0.0033 max mem: 22446 +train: [8] [280/400] eta: 0:00:56 lr: 0.000257 loss: 0.6057 (0.6108) grad: 0.0339 (0.0356) time: 0.4569 data: 0.0034 max mem: 22446 +train: [8] [300/400] eta: 0:00:47 lr: 0.000256 loss: 0.6057 (0.6093) grad: 0.0358 (0.0357) time: 0.5974 data: 0.1689 max mem: 22446 +train: [8] [320/400] eta: 0:00:38 lr: 0.000255 loss: 0.5741 (0.6083) grad: 0.0352 (0.0356) time: 0.4508 data: 0.0029 max mem: 22446 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.5737 (0.6060) grad: 0.0326 (0.0354) time: 0.4451 data: 0.0036 max mem: 22446 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 0.5672 (0.6039) grad: 0.0317 (0.0352) time: 0.4529 data: 0.0036 max mem: 22446 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.5693 (0.6027) grad: 0.0317 (0.0351) time: 0.4753 data: 0.0038 max mem: 22446 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.5783 (0.6015) grad: 0.0312 (0.0349) time: 0.4533 data: 0.0036 max mem: 22446 +train: [8] Total time: 0:03:08 (0.4722 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.5783 (0.6015) grad: 0.0312 (0.0349) +eval (validation): [8] [ 0/63] eta: 0:03:19 time: 3.1712 data: 2.9415 max mem: 22446 +eval (validation): [8] [20/63] eta: 0:00:20 time: 0.3537 data: 0.0036 max mem: 22446 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3491 data: 0.0031 max mem: 22446 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3448 data: 0.0032 max mem: 22446 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3441 data: 0.0031 max mem: 22446 +eval (validation): [8] Total time: 0:00:25 (0.3984 s / it) +cv: [8] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.090 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:22:59 lr: nan time: 3.4476 data: 3.1062 max mem: 22446 +train: [9] [ 20/400] eta: 0:03:45 lr: 0.000249 loss: 0.5508 (0.5597) grad: 0.0319 (0.0325) time: 0.4516 data: 0.0034 max mem: 22446 +train: [9] [ 40/400] eta: 0:03:07 lr: 0.000248 loss: 0.5648 (0.5685) grad: 0.0334 (0.0333) time: 0.4437 data: 0.0031 max mem: 22446 +train: [9] [ 60/400] eta: 0:02:50 lr: 0.000247 loss: 0.5881 (0.5684) grad: 0.0334 (0.0333) time: 0.4606 data: 0.0034 max mem: 22446 +train: [9] [ 80/400] eta: 0:02:37 lr: 0.000246 loss: 0.5489 (0.5631) grad: 0.0316 (0.0329) time: 0.4599 data: 0.0034 max mem: 22446 +train: [9] [100/400] eta: 0:02:24 lr: 0.000244 loss: 0.5489 (0.5634) grad: 0.0307 (0.0328) time: 0.4507 data: 0.0033 max mem: 22446 +train: [9] [120/400] eta: 0:02:13 lr: 0.000243 loss: 0.5515 (0.5630) grad: 0.0309 (0.0329) time: 0.4476 data: 0.0035 max mem: 22446 +train: [9] [140/400] eta: 0:02:03 lr: 0.000242 loss: 0.5515 (0.5628) grad: 0.0319 (0.0328) time: 0.4529 data: 0.0033 max mem: 22446 +train: [9] [160/400] eta: 0:01:53 lr: 0.000241 loss: 0.5510 (0.5608) grad: 0.0310 (0.0325) time: 0.4526 data: 0.0034 max mem: 22446 +train: [9] [180/400] eta: 0:01:43 lr: 0.000240 loss: 0.5376 (0.5588) grad: 0.0302 (0.0324) time: 0.4556 data: 0.0034 max mem: 22446 +train: [9] [200/400] eta: 0:01:33 lr: 0.000238 loss: 0.5436 (0.5584) grad: 0.0302 (0.0322) time: 0.4470 data: 0.0034 max mem: 22446 +train: [9] [220/400] eta: 0:01:23 lr: 0.000237 loss: 0.5547 (0.5575) grad: 0.0316 (0.0322) time: 0.4590 data: 0.0034 max mem: 22446 +train: [9] [240/400] eta: 0:01:14 lr: 0.000236 loss: 0.5485 (0.5572) grad: 0.0321 (0.0323) time: 0.4585 data: 0.0035 max mem: 22446 +train: [9] [260/400] eta: 0:01:05 lr: 0.000234 loss: 0.5520 (0.5573) grad: 0.0315 (0.0321) time: 0.4695 data: 0.0033 max mem: 22446 +train: [9] [280/400] eta: 0:00:55 lr: 0.000233 loss: 0.5390 (0.5548) grad: 0.0301 (0.0321) time: 0.4743 data: 0.0035 max mem: 22446 +train: [9] [300/400] eta: 0:00:47 lr: 0.000232 loss: 0.5402 (0.5560) grad: 0.0303 (0.0321) time: 0.6328 data: 0.1770 max mem: 22446 +train: [9] [320/400] eta: 0:00:38 lr: 0.000230 loss: 0.5345 (0.5533) grad: 0.0295 (0.0319) time: 0.4508 data: 0.0031 max mem: 22446 +train: [9] [340/400] eta: 0:00:28 lr: 0.000229 loss: 0.5189 (0.5528) grad: 0.0285 (0.0318) time: 0.4529 data: 0.0035 max mem: 22446 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 0.5516 (0.5529) grad: 0.0305 (0.0318) time: 0.4571 data: 0.0036 max mem: 22446 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.5580 (0.5531) grad: 0.0308 (0.0317) time: 0.4609 data: 0.0035 max mem: 22446 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.5210 (0.5510) grad: 0.0309 (0.0317) time: 0.4640 data: 0.0034 max mem: 22446 +train: [9] Total time: 0:03:09 (0.4729 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.5210 (0.5510) grad: 0.0309 (0.0317) +eval (validation): [9] [ 0/63] eta: 0:03:28 time: 3.3162 data: 3.0334 max mem: 22446 +eval (validation): [9] [20/63] eta: 0:00:21 time: 0.3574 data: 0.0027 max mem: 22446 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3407 data: 0.0030 max mem: 22446 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3181 data: 0.0031 max mem: 22446 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3176 data: 0.0032 max mem: 22446 +eval (validation): [9] Total time: 0:00:24 (0.3902 s / it) +cv: [9] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.089 acc: 0.976 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:52 lr: nan time: 3.4305 data: 3.0785 max mem: 22446 +train: [10] [ 20/400] eta: 0:03:45 lr: 0.000224 loss: 0.5206 (0.5186) grad: 0.0288 (0.0296) time: 0.4514 data: 0.0030 max mem: 22446 +train: [10] [ 40/400] eta: 0:03:08 lr: 0.000222 loss: 0.5278 (0.5277) grad: 0.0292 (0.0298) time: 0.4513 data: 0.0033 max mem: 22446 +train: [10] [ 60/400] eta: 0:02:49 lr: 0.000221 loss: 0.5264 (0.5258) grad: 0.0292 (0.0298) time: 0.4504 data: 0.0033 max mem: 22446 +train: [10] [ 80/400] eta: 0:02:36 lr: 0.000220 loss: 0.5142 (0.5215) grad: 0.0292 (0.0295) time: 0.4562 data: 0.0033 max mem: 22446 +train: [10] [100/400] eta: 0:02:24 lr: 0.000218 loss: 0.5174 (0.5255) grad: 0.0286 (0.0296) time: 0.4554 data: 0.0034 max mem: 22446 +train: [10] [120/400] eta: 0:02:13 lr: 0.000217 loss: 0.5177 (0.5234) grad: 0.0305 (0.0299) time: 0.4504 data: 0.0034 max mem: 22446 +train: [10] [140/400] eta: 0:02:02 lr: 0.000215 loss: 0.5077 (0.5220) grad: 0.0305 (0.0299) time: 0.4466 data: 0.0035 max mem: 22446 +train: [10] [160/400] eta: 0:01:52 lr: 0.000214 loss: 0.5183 (0.5216) grad: 0.0290 (0.0299) time: 0.4519 data: 0.0033 max mem: 22446 +train: [10] [180/400] eta: 0:01:42 lr: 0.000213 loss: 0.5183 (0.5209) grad: 0.0290 (0.0299) time: 0.4494 data: 0.0033 max mem: 22446 +train: [10] [200/400] eta: 0:01:33 lr: 0.000211 loss: 0.5128 (0.5198) grad: 0.0295 (0.0299) time: 0.4471 data: 0.0034 max mem: 22446 +train: [10] [220/400] eta: 0:01:23 lr: 0.000210 loss: 0.5104 (0.5178) grad: 0.0295 (0.0298) time: 0.4557 data: 0.0034 max mem: 22446 +train: [10] [240/400] eta: 0:01:14 lr: 0.000208 loss: 0.4965 (0.5163) grad: 0.0303 (0.0300) time: 0.4562 data: 0.0034 max mem: 22446 +train: [10] [260/400] eta: 0:01:04 lr: 0.000207 loss: 0.5147 (0.5173) grad: 0.0313 (0.0301) time: 0.4516 data: 0.0033 max mem: 22446 +train: [10] [280/400] eta: 0:00:55 lr: 0.000205 loss: 0.5147 (0.5165) grad: 0.0308 (0.0301) time: 0.4758 data: 0.0034 max mem: 22446 +train: [10] [300/400] eta: 0:00:47 lr: 0.000204 loss: 0.5024 (0.5154) grad: 0.0294 (0.0300) time: 0.6197 data: 0.1805 max mem: 22446 +train: [10] [320/400] eta: 0:00:37 lr: 0.000202 loss: 0.4898 (0.5147) grad: 0.0282 (0.0300) time: 0.4490 data: 0.0033 max mem: 22446 +train: [10] [340/400] eta: 0:00:28 lr: 0.000201 loss: 0.5047 (0.5154) grad: 0.0288 (0.0299) time: 0.4489 data: 0.0033 max mem: 22446 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 0.5047 (0.5142) grad: 0.0284 (0.0298) time: 0.4584 data: 0.0034 max mem: 22446 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.4957 (0.5128) grad: 0.0269 (0.0297) time: 0.4715 data: 0.0034 max mem: 22446 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.4982 (0.5119) grad: 0.0273 (0.0297) time: 0.4524 data: 0.0036 max mem: 22446 +train: [10] Total time: 0:03:08 (0.4702 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.4982 (0.5119) grad: 0.0273 (0.0297) +eval (validation): [10] [ 0/63] eta: 0:03:17 time: 3.1349 data: 2.9092 max mem: 22446 +eval (validation): [10] [20/63] eta: 0:00:20 time: 0.3426 data: 0.0041 max mem: 22446 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3459 data: 0.0031 max mem: 22446 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3337 data: 0.0032 max mem: 22446 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3331 data: 0.0032 max mem: 22446 +eval (validation): [10] Total time: 0:00:24 (0.3894 s / it) +cv: [10] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.089 acc: 0.976 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:23:21 lr: nan time: 3.5047 data: 3.1044 max mem: 22446 +train: [11] [ 20/400] eta: 0:03:46 lr: 0.000195 loss: 0.4833 (0.4893) grad: 0.0276 (0.0276) time: 0.4497 data: 0.0027 max mem: 22446 +train: [11] [ 40/400] eta: 0:03:08 lr: 0.000193 loss: 0.4973 (0.5013) grad: 0.0281 (0.0282) time: 0.4491 data: 0.0033 max mem: 22446 +train: [11] [ 60/400] eta: 0:02:50 lr: 0.000192 loss: 0.4915 (0.4969) grad: 0.0281 (0.0281) time: 0.4531 data: 0.0033 max mem: 22446 +train: [11] [ 80/400] eta: 0:02:37 lr: 0.000190 loss: 0.4988 (0.5002) grad: 0.0274 (0.0282) time: 0.4615 data: 0.0033 max mem: 22446 +train: [11] [100/400] eta: 0:02:25 lr: 0.000189 loss: 0.4988 (0.4987) grad: 0.0287 (0.0283) time: 0.4545 data: 0.0033 max mem: 22446 +train: [11] [120/400] eta: 0:02:14 lr: 0.000187 loss: 0.4910 (0.4981) grad: 0.0285 (0.0283) time: 0.4530 data: 0.0034 max mem: 22446 +train: [11] [140/400] eta: 0:02:03 lr: 0.000186 loss: 0.4935 (0.4965) grad: 0.0282 (0.0283) time: 0.4507 data: 0.0036 max mem: 22446 +train: [11] [160/400] eta: 0:01:53 lr: 0.000184 loss: 0.4856 (0.4943) grad: 0.0279 (0.0283) time: 0.4580 data: 0.0035 max mem: 22446 +train: [11] [180/400] eta: 0:01:43 lr: 0.000183 loss: 0.4797 (0.4931) grad: 0.0277 (0.0283) time: 0.4642 data: 0.0034 max mem: 22446 +train: [11] [200/400] eta: 0:01:33 lr: 0.000181 loss: 0.4904 (0.4932) grad: 0.0276 (0.0282) time: 0.4544 data: 0.0034 max mem: 22446 +train: [11] [220/400] eta: 0:01:24 lr: 0.000180 loss: 0.4904 (0.4938) grad: 0.0276 (0.0282) time: 0.4564 data: 0.0034 max mem: 22446 +train: [11] [240/400] eta: 0:01:14 lr: 0.000178 loss: 0.4853 (0.4922) grad: 0.0277 (0.0282) time: 0.4597 data: 0.0035 max mem: 22446 +train: [11] [260/400] eta: 0:01:05 lr: 0.000177 loss: 0.4853 (0.4917) grad: 0.0280 (0.0282) time: 0.4415 data: 0.0035 max mem: 22446 +train: [11] [280/400] eta: 0:00:55 lr: 0.000175 loss: 0.4627 (0.4903) grad: 0.0280 (0.0281) time: 0.4654 data: 0.0036 max mem: 22446 +train: [11] [300/400] eta: 0:00:47 lr: 0.000174 loss: 0.4621 (0.4897) grad: 0.0279 (0.0282) time: 0.6451 data: 0.1755 max mem: 22446 +train: [11] [320/400] eta: 0:00:38 lr: 0.000172 loss: 0.4691 (0.4893) grad: 0.0281 (0.0282) time: 0.4650 data: 0.0030 max mem: 22446 +train: [11] [340/400] eta: 0:00:28 lr: 0.000170 loss: 0.4729 (0.4887) grad: 0.0267 (0.0281) time: 0.4478 data: 0.0034 max mem: 22446 +train: [11] [360/400] eta: 0:00:19 lr: 0.000169 loss: 0.4814 (0.4892) grad: 0.0265 (0.0281) time: 0.4767 data: 0.0036 max mem: 22446 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.4825 (0.4886) grad: 0.0269 (0.0281) time: 0.4759 data: 0.0035 max mem: 22446 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.4624 (0.4876) grad: 0.0282 (0.0281) time: 0.4640 data: 0.0036 max mem: 22446 +train: [11] Total time: 0:03:10 (0.4751 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.4624 (0.4876) grad: 0.0282 (0.0281) +eval (validation): [11] [ 0/63] eta: 0:03:26 time: 3.2842 data: 3.0003 max mem: 22446 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3684 data: 0.0042 max mem: 22446 +eval (validation): [11] [40/63] eta: 0:00:10 time: 0.3683 data: 0.0033 max mem: 22446 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3262 data: 0.0032 max mem: 22446 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3254 data: 0.0031 max mem: 22446 +eval (validation): [11] Total time: 0:00:25 (0.4053 s / it) +cv: [11] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.101 acc: 0.977 f1: 0.976 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:23:35 lr: nan time: 3.5396 data: 3.1390 max mem: 22446 +train: [12] [ 20/400] eta: 0:03:49 lr: 0.000164 loss: 0.4509 (0.4577) grad: 0.0259 (0.0265) time: 0.4571 data: 0.0023 max mem: 22446 +train: [12] [ 40/400] eta: 0:03:07 lr: 0.000163 loss: 0.4693 (0.4725) grad: 0.0269 (0.0274) time: 0.4336 data: 0.0033 max mem: 22446 +train: [12] [ 60/400] eta: 0:02:50 lr: 0.000161 loss: 0.4791 (0.4698) grad: 0.0274 (0.0273) time: 0.4588 data: 0.0035 max mem: 22446 +train: [12] [ 80/400] eta: 0:02:36 lr: 0.000160 loss: 0.4540 (0.4671) grad: 0.0265 (0.0271) time: 0.4496 data: 0.0033 max mem: 22446 +train: [12] [100/400] eta: 0:02:23 lr: 0.000158 loss: 0.4624 (0.4700) grad: 0.0264 (0.0272) time: 0.4456 data: 0.0036 max mem: 22446 +train: [12] [120/400] eta: 0:02:13 lr: 0.000156 loss: 0.4643 (0.4713) grad: 0.0272 (0.0273) time: 0.4625 data: 0.0034 max mem: 22446 +train: [12] [140/400] eta: 0:02:03 lr: 0.000155 loss: 0.4643 (0.4715) grad: 0.0277 (0.0272) time: 0.4555 data: 0.0035 max mem: 22446 +train: [12] [160/400] eta: 0:01:53 lr: 0.000153 loss: 0.4640 (0.4701) grad: 0.0271 (0.0272) time: 0.4511 data: 0.0035 max mem: 22446 +train: [12] [180/400] eta: 0:01:42 lr: 0.000152 loss: 0.4498 (0.4688) grad: 0.0266 (0.0272) time: 0.4432 data: 0.0033 max mem: 22446 +train: [12] [200/400] eta: 0:01:33 lr: 0.000150 loss: 0.4573 (0.4682) grad: 0.0266 (0.0272) time: 0.4557 data: 0.0034 max mem: 22446 +train: [12] [220/400] eta: 0:01:23 lr: 0.000149 loss: 0.4595 (0.4675) grad: 0.0268 (0.0271) time: 0.4477 data: 0.0034 max mem: 22446 +train: [12] [240/400] eta: 0:01:14 lr: 0.000147 loss: 0.4595 (0.4690) grad: 0.0265 (0.0271) time: 0.4464 data: 0.0034 max mem: 22446 +train: [12] [260/400] eta: 0:01:04 lr: 0.000145 loss: 0.4731 (0.4687) grad: 0.0266 (0.0271) time: 0.4543 data: 0.0035 max mem: 22446 +train: [12] [280/400] eta: 0:00:55 lr: 0.000144 loss: 0.4622 (0.4683) grad: 0.0267 (0.0270) time: 0.4632 data: 0.0035 max mem: 22446 +train: [12] [300/400] eta: 0:00:47 lr: 0.000142 loss: 0.4700 (0.4685) grad: 0.0265 (0.0271) time: 0.6334 data: 0.1759 max mem: 22446 +train: [12] [320/400] eta: 0:00:37 lr: 0.000141 loss: 0.4773 (0.4683) grad: 0.0267 (0.0271) time: 0.4682 data: 0.0033 max mem: 22446 +train: [12] [340/400] eta: 0:00:28 lr: 0.000139 loss: 0.4494 (0.4674) grad: 0.0273 (0.0271) time: 0.4409 data: 0.0032 max mem: 22446 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 0.4464 (0.4661) grad: 0.0264 (0.0271) time: 0.4667 data: 0.0033 max mem: 22446 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.4563 (0.4665) grad: 0.0260 (0.0271) time: 0.4671 data: 0.0034 max mem: 22446 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.4746 (0.4667) grad: 0.0261 (0.0270) time: 0.4522 data: 0.0034 max mem: 22446 +train: [12] Total time: 0:03:08 (0.4706 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.4746 (0.4667) grad: 0.0261 (0.0270) +eval (validation): [12] [ 0/63] eta: 0:03:21 time: 3.1931 data: 2.9637 max mem: 22446 +eval (validation): [12] [20/63] eta: 0:00:21 time: 0.3680 data: 0.0034 max mem: 22446 +eval (validation): [12] [40/63] eta: 0:00:09 time: 0.3492 data: 0.0033 max mem: 22446 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3296 data: 0.0034 max mem: 22446 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3283 data: 0.0033 max mem: 22446 +eval (validation): [12] Total time: 0:00:25 (0.3978 s / it) +cv: [12] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.088 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:23:14 lr: nan time: 3.4862 data: 3.1381 max mem: 22446 +train: [13] [ 20/400] eta: 0:03:46 lr: 0.000133 loss: 0.4520 (0.4498) grad: 0.0266 (0.0273) time: 0.4510 data: 0.0029 max mem: 22446 +train: [13] [ 40/400] eta: 0:03:09 lr: 0.000131 loss: 0.4632 (0.4593) grad: 0.0269 (0.0272) time: 0.4535 data: 0.0028 max mem: 22446 +train: [13] [ 60/400] eta: 0:02:50 lr: 0.000130 loss: 0.4657 (0.4641) grad: 0.0269 (0.0272) time: 0.4530 data: 0.0033 max mem: 22446 +train: [13] [ 80/400] eta: 0:02:37 lr: 0.000128 loss: 0.4478 (0.4578) grad: 0.0267 (0.0270) time: 0.4569 data: 0.0034 max mem: 22446 +train: [13] [100/400] eta: 0:02:25 lr: 0.000127 loss: 0.4336 (0.4534) grad: 0.0260 (0.0269) time: 0.4567 data: 0.0034 max mem: 22446 +train: [13] [120/400] eta: 0:02:14 lr: 0.000125 loss: 0.4388 (0.4558) grad: 0.0269 (0.0269) time: 0.4558 data: 0.0036 max mem: 22446 +train: [13] [140/400] eta: 0:02:03 lr: 0.000124 loss: 0.4720 (0.4576) grad: 0.0270 (0.0269) time: 0.4528 data: 0.0034 max mem: 22446 +train: [13] [160/400] eta: 0:01:53 lr: 0.000122 loss: 0.4615 (0.4563) grad: 0.0269 (0.0270) time: 0.4538 data: 0.0033 max mem: 22446 +train: [13] [180/400] eta: 0:01:43 lr: 0.000120 loss: 0.4456 (0.4546) grad: 0.0267 (0.0270) time: 0.4505 data: 0.0034 max mem: 22446 +train: [13] [200/400] eta: 0:01:33 lr: 0.000119 loss: 0.4577 (0.4546) grad: 0.0265 (0.0269) time: 0.4595 data: 0.0033 max mem: 22446 +train: [13] [220/400] eta: 0:01:24 lr: 0.000117 loss: 0.4527 (0.4541) grad: 0.0263 (0.0269) time: 0.4572 data: 0.0034 max mem: 22446 +train: [13] [240/400] eta: 0:01:14 lr: 0.000116 loss: 0.4356 (0.4531) grad: 0.0260 (0.0269) time: 0.4551 data: 0.0033 max mem: 22446 +train: [13] [260/400] eta: 0:01:05 lr: 0.000114 loss: 0.4501 (0.4530) grad: 0.0261 (0.0269) time: 0.4462 data: 0.0034 max mem: 22446 +train: [13] [280/400] eta: 0:00:55 lr: 0.000113 loss: 0.4516 (0.4522) grad: 0.0264 (0.0269) time: 0.4597 data: 0.0036 max mem: 22446 +train: [13] [300/400] eta: 0:00:47 lr: 0.000111 loss: 0.4469 (0.4526) grad: 0.0268 (0.0269) time: 0.6302 data: 0.1829 max mem: 22446 +train: [13] [320/400] eta: 0:00:38 lr: 0.000110 loss: 0.4509 (0.4523) grad: 0.0268 (0.0269) time: 0.4582 data: 0.0037 max mem: 22446 +train: [13] [340/400] eta: 0:00:28 lr: 0.000108 loss: 0.4455 (0.4516) grad: 0.0261 (0.0268) time: 0.4482 data: 0.0033 max mem: 22446 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 0.4435 (0.4506) grad: 0.0252 (0.0267) time: 0.4614 data: 0.0033 max mem: 22446 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.4356 (0.4500) grad: 0.0254 (0.0267) time: 0.4768 data: 0.0037 max mem: 22446 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.4498 (0.4501) grad: 0.0264 (0.0267) time: 0.4674 data: 0.0036 max mem: 22446 +train: [13] Total time: 0:03:09 (0.4731 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.4498 (0.4501) grad: 0.0264 (0.0267) +eval (validation): [13] [ 0/63] eta: 0:03:23 time: 3.2236 data: 2.9504 max mem: 22446 +eval (validation): [13] [20/63] eta: 0:00:21 time: 0.3698 data: 0.0033 max mem: 22446 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3575 data: 0.0033 max mem: 22446 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3339 data: 0.0031 max mem: 22446 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3292 data: 0.0030 max mem: 22446 +eval (validation): [13] Total time: 0:00:25 (0.4029 s / it) +cv: [13] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.090 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:23:36 lr: nan time: 3.5408 data: 3.1397 max mem: 22446 +train: [14] [ 20/400] eta: 0:03:57 lr: 0.000102 loss: 0.4445 (0.4508) grad: 0.0267 (0.0271) time: 0.4794 data: 0.0031 max mem: 22446 +train: [14] [ 40/400] eta: 0:03:15 lr: 0.000101 loss: 0.4461 (0.4486) grad: 0.0266 (0.0271) time: 0.4546 data: 0.0032 max mem: 22446 +train: [14] [ 60/400] eta: 0:02:55 lr: 0.000099 loss: 0.4419 (0.4413) grad: 0.0266 (0.0272) time: 0.4678 data: 0.0035 max mem: 22446 +train: [14] [ 80/400] eta: 0:02:40 lr: 0.000098 loss: 0.4370 (0.4434) grad: 0.0259 (0.0269) time: 0.4576 data: 0.0035 max mem: 22446 +train: [14] [100/400] eta: 0:02:28 lr: 0.000096 loss: 0.4441 (0.4451) grad: 0.0262 (0.0269) time: 0.4615 data: 0.0034 max mem: 22446 +train: [14] [120/400] eta: 0:02:17 lr: 0.000095 loss: 0.4465 (0.4457) grad: 0.0269 (0.0271) time: 0.4642 data: 0.0033 max mem: 22446 +train: [14] [140/400] eta: 0:02:06 lr: 0.000093 loss: 0.4308 (0.4444) grad: 0.0274 (0.0271) time: 0.4647 data: 0.0033 max mem: 22446 +train: [14] [160/400] eta: 0:01:55 lr: 0.000092 loss: 0.4288 (0.4434) grad: 0.0269 (0.0271) time: 0.4588 data: 0.0030 max mem: 22446 +train: [14] [180/400] eta: 0:01:45 lr: 0.000090 loss: 0.4338 (0.4442) grad: 0.0262 (0.0270) time: 0.4568 data: 0.0034 max mem: 22446 +train: [14] [200/400] eta: 0:01:35 lr: 0.000089 loss: 0.4368 (0.4435) grad: 0.0256 (0.0269) time: 0.4519 data: 0.0033 max mem: 22446 +train: [14] [220/400] eta: 0:01:25 lr: 0.000088 loss: 0.4378 (0.4439) grad: 0.0257 (0.0269) time: 0.4512 data: 0.0033 max mem: 22446 +train: [14] [240/400] eta: 0:01:15 lr: 0.000086 loss: 0.4414 (0.4431) grad: 0.0270 (0.0270) time: 0.4567 data: 0.0035 max mem: 22446 +train: [14] [260/400] eta: 0:01:06 lr: 0.000085 loss: 0.4414 (0.4432) grad: 0.0264 (0.0270) time: 0.4546 data: 0.0034 max mem: 22446 +train: [14] [280/400] eta: 0:00:56 lr: 0.000083 loss: 0.4461 (0.4433) grad: 0.0260 (0.0270) time: 0.4652 data: 0.0037 max mem: 22446 +train: [14] [300/400] eta: 0:00:48 lr: 0.000082 loss: 0.4397 (0.4433) grad: 0.0260 (0.0269) time: 0.6285 data: 0.1812 max mem: 22446 +train: [14] [320/400] eta: 0:00:38 lr: 0.000081 loss: 0.4291 (0.4423) grad: 0.0258 (0.0268) time: 0.4581 data: 0.0030 max mem: 22446 +train: [14] [340/400] eta: 0:00:28 lr: 0.000079 loss: 0.4291 (0.4416) grad: 0.0261 (0.0268) time: 0.4535 data: 0.0033 max mem: 22446 +train: [14] [360/400] eta: 0:00:19 lr: 0.000078 loss: 0.4353 (0.4417) grad: 0.0261 (0.0268) time: 0.4575 data: 0.0033 max mem: 22446 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.4438 (0.4421) grad: 0.0261 (0.0268) time: 0.4797 data: 0.0034 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.4508 (0.4430) grad: 0.0272 (0.0268) time: 0.4709 data: 0.0034 max mem: 22446 +train: [14] Total time: 0:03:11 (0.4775 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.4508 (0.4430) grad: 0.0272 (0.0268) +eval (validation): [14] [ 0/63] eta: 0:03:19 time: 3.1737 data: 2.9398 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:21 time: 0.3631 data: 0.0026 max mem: 22446 +eval (validation): [14] [40/63] eta: 0:00:10 time: 0.3756 data: 0.0031 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3355 data: 0.0032 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3373 data: 0.0032 max mem: 22446 +eval (validation): [14] Total time: 0:00:25 (0.4074 s / it) +cv: [14] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.088 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:41 lr: nan time: 3.5528 data: 3.1594 max mem: 22446 +train: [15] [ 20/400] eta: 0:03:56 lr: 0.000074 loss: 0.4238 (0.4314) grad: 0.0262 (0.0261) time: 0.4768 data: 0.0022 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:12 lr: 0.000072 loss: 0.4379 (0.4311) grad: 0.0261 (0.0266) time: 0.4427 data: 0.0033 max mem: 22446 +train: [15] [ 60/400] eta: 0:02:54 lr: 0.000071 loss: 0.4215 (0.4236) grad: 0.0260 (0.0264) time: 0.4657 data: 0.0035 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:39 lr: 0.000070 loss: 0.4224 (0.4300) grad: 0.0254 (0.0262) time: 0.4591 data: 0.0035 max mem: 22446 +train: [15] [100/400] eta: 0:02:27 lr: 0.000068 loss: 0.4411 (0.4284) grad: 0.0259 (0.0265) time: 0.4544 data: 0.0034 max mem: 22446 +train: [15] [120/400] eta: 0:02:15 lr: 0.000067 loss: 0.4264 (0.4289) grad: 0.0265 (0.0266) time: 0.4586 data: 0.0034 max mem: 22446 +train: [15] [140/400] eta: 0:02:04 lr: 0.000066 loss: 0.4283 (0.4296) grad: 0.0258 (0.0266) time: 0.4504 data: 0.0035 max mem: 22446 +train: [15] [160/400] eta: 0:01:54 lr: 0.000064 loss: 0.4450 (0.4325) grad: 0.0264 (0.0267) time: 0.4529 data: 0.0035 max mem: 22446 +train: [15] [180/400] eta: 0:01:44 lr: 0.000063 loss: 0.4450 (0.4322) grad: 0.0270 (0.0266) time: 0.4531 data: 0.0035 max mem: 22446 +train: [15] [200/400] eta: 0:01:34 lr: 0.000062 loss: 0.4221 (0.4319) grad: 0.0271 (0.0267) time: 0.4636 data: 0.0034 max mem: 22446 +train: [15] [220/400] eta: 0:01:24 lr: 0.000061 loss: 0.4221 (0.4320) grad: 0.0271 (0.0268) time: 0.4453 data: 0.0034 max mem: 22446 +train: [15] [240/400] eta: 0:01:15 lr: 0.000059 loss: 0.4214 (0.4321) grad: 0.0263 (0.0267) time: 0.4537 data: 0.0035 max mem: 22446 +train: [15] [260/400] eta: 0:01:05 lr: 0.000058 loss: 0.4268 (0.4320) grad: 0.0261 (0.0268) time: 0.4529 data: 0.0033 max mem: 22446 +train: [15] [280/400] eta: 0:00:56 lr: 0.000057 loss: 0.4307 (0.4321) grad: 0.0269 (0.0268) time: 0.4618 data: 0.0035 max mem: 22446 +train: [15] [300/400] eta: 0:00:47 lr: 0.000056 loss: 0.4252 (0.4314) grad: 0.0266 (0.0268) time: 0.6190 data: 0.1808 max mem: 22446 +train: [15] [320/400] eta: 0:00:38 lr: 0.000054 loss: 0.4252 (0.4313) grad: 0.0264 (0.0268) time: 0.4554 data: 0.0036 max mem: 22446 +train: [15] [340/400] eta: 0:00:28 lr: 0.000053 loss: 0.4255 (0.4310) grad: 0.0262 (0.0268) time: 0.4426 data: 0.0029 max mem: 22446 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 0.4255 (0.4315) grad: 0.0264 (0.0268) time: 0.4611 data: 0.0033 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.4403 (0.4322) grad: 0.0264 (0.0268) time: 0.4738 data: 0.0035 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.4242 (0.4317) grad: 0.0273 (0.0268) time: 0.4548 data: 0.0034 max mem: 22446 +train: [15] Total time: 0:03:09 (0.4729 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.4242 (0.4317) grad: 0.0273 (0.0268) +eval (validation): [15] [ 0/63] eta: 0:03:19 time: 3.1641 data: 2.9184 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:20 time: 0.3447 data: 0.0039 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3439 data: 0.0028 max mem: 22446 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3208 data: 0.0030 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3223 data: 0.0027 max mem: 22446 +eval (validation): [15] Total time: 0:00:24 (0.3872 s / it) +cv: [15] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.086 acc: 0.978 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:23:23 lr: nan time: 3.5090 data: 3.1678 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:45 lr: 0.000048 loss: 0.4195 (0.4269) grad: 0.0260 (0.0261) time: 0.4481 data: 0.0027 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:07 lr: 0.000047 loss: 0.4261 (0.4289) grad: 0.0258 (0.0260) time: 0.4414 data: 0.0027 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:51 lr: 0.000046 loss: 0.4334 (0.4346) grad: 0.0258 (0.0258) time: 0.4727 data: 0.0037 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:37 lr: 0.000045 loss: 0.4347 (0.4329) grad: 0.0259 (0.0262) time: 0.4591 data: 0.0035 max mem: 22446 +train: [16] [100/400] eta: 0:02:25 lr: 0.000044 loss: 0.4299 (0.4314) grad: 0.0263 (0.0263) time: 0.4568 data: 0.0033 max mem: 22446 +train: [16] [120/400] eta: 0:02:14 lr: 0.000043 loss: 0.4363 (0.4311) grad: 0.0263 (0.0264) time: 0.4522 data: 0.0032 max mem: 22446 +train: [16] [140/400] eta: 0:02:03 lr: 0.000042 loss: 0.4292 (0.4314) grad: 0.0261 (0.0264) time: 0.4494 data: 0.0032 max mem: 22446 +train: [16] [160/400] eta: 0:01:53 lr: 0.000041 loss: 0.4204 (0.4290) grad: 0.0257 (0.0263) time: 0.4549 data: 0.0033 max mem: 22446 +train: [16] [180/400] eta: 0:01:43 lr: 0.000040 loss: 0.4201 (0.4273) grad: 0.0258 (0.0264) time: 0.4572 data: 0.0035 max mem: 22446 +train: [16] [200/400] eta: 0:01:34 lr: 0.000039 loss: 0.4208 (0.4266) grad: 0.0261 (0.0263) time: 0.4588 data: 0.0035 max mem: 22446 +train: [16] [220/400] eta: 0:01:24 lr: 0.000038 loss: 0.4227 (0.4270) grad: 0.0261 (0.0263) time: 0.4569 data: 0.0035 max mem: 22446 +train: [16] [240/400] eta: 0:01:14 lr: 0.000036 loss: 0.4163 (0.4267) grad: 0.0263 (0.0263) time: 0.4487 data: 0.0035 max mem: 22446 +train: [16] [260/400] eta: 0:01:05 lr: 0.000035 loss: 0.4163 (0.4267) grad: 0.0255 (0.0263) time: 0.4494 data: 0.0033 max mem: 22446 +train: [16] [280/400] eta: 0:00:55 lr: 0.000034 loss: 0.4417 (0.4271) grad: 0.0266 (0.0264) time: 0.4663 data: 0.0035 max mem: 22446 +train: [16] [300/400] eta: 0:00:47 lr: 0.000033 loss: 0.4187 (0.4268) grad: 0.0271 (0.0264) time: 0.6296 data: 0.1785 max mem: 22446 +train: [16] [320/400] eta: 0:00:38 lr: 0.000032 loss: 0.4255 (0.4275) grad: 0.0251 (0.0263) time: 0.4557 data: 0.0031 max mem: 22446 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 0.4233 (0.4265) grad: 0.0258 (0.0264) time: 0.4515 data: 0.0034 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.4015 (0.4259) grad: 0.0264 (0.0264) time: 0.4555 data: 0.0034 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.4116 (0.4255) grad: 0.0263 (0.0264) time: 0.4642 data: 0.0035 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.4252 (0.4258) grad: 0.0266 (0.0264) time: 0.4589 data: 0.0036 max mem: 22446 +train: [16] Total time: 0:03:08 (0.4723 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.4252 (0.4258) grad: 0.0266 (0.0264) +eval (validation): [16] [ 0/63] eta: 0:03:21 time: 3.2052 data: 2.9228 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3675 data: 0.0037 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3335 data: 0.0032 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3436 data: 0.0033 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3435 data: 0.0033 max mem: 22446 +eval (validation): [16] Total time: 0:00:25 (0.3983 s / it) +cv: [16] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.085 acc: 0.978 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:23:03 lr: nan time: 3.4591 data: 3.0724 max mem: 22446 +train: [17] [ 20/400] eta: 0:03:46 lr: 0.000028 loss: 0.4302 (0.4293) grad: 0.0259 (0.0269) time: 0.4524 data: 0.0033 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:09 lr: 0.000027 loss: 0.4183 (0.4208) grad: 0.0259 (0.0264) time: 0.4530 data: 0.0030 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:52 lr: 0.000026 loss: 0.4165 (0.4205) grad: 0.0261 (0.0265) time: 0.4730 data: 0.0034 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:39 lr: 0.000025 loss: 0.4239 (0.4215) grad: 0.0264 (0.0266) time: 0.4627 data: 0.0035 max mem: 22446 +train: [17] [100/400] eta: 0:02:26 lr: 0.000024 loss: 0.4265 (0.4248) grad: 0.0264 (0.0266) time: 0.4556 data: 0.0033 max mem: 22446 +train: [17] [120/400] eta: 0:02:14 lr: 0.000023 loss: 0.4333 (0.4250) grad: 0.0264 (0.0266) time: 0.4453 data: 0.0035 max mem: 22446 +train: [17] [140/400] eta: 0:02:04 lr: 0.000023 loss: 0.4273 (0.4249) grad: 0.0267 (0.0266) time: 0.4550 data: 0.0036 max mem: 22446 +train: [17] [160/400] eta: 0:01:53 lr: 0.000022 loss: 0.4279 (0.4262) grad: 0.0253 (0.0265) time: 0.4487 data: 0.0034 max mem: 22446 +train: [17] [180/400] eta: 0:01:43 lr: 0.000021 loss: 0.4294 (0.4258) grad: 0.0258 (0.0266) time: 0.4547 data: 0.0034 max mem: 22446 +train: [17] [200/400] eta: 0:01:33 lr: 0.000020 loss: 0.4161 (0.4247) grad: 0.0275 (0.0267) time: 0.4473 data: 0.0035 max mem: 22446 +train: [17] [220/400] eta: 0:01:24 lr: 0.000019 loss: 0.4217 (0.4248) grad: 0.0263 (0.0267) time: 0.4452 data: 0.0036 max mem: 22446 +train: [17] [240/400] eta: 0:01:14 lr: 0.000019 loss: 0.4119 (0.4245) grad: 0.0261 (0.0267) time: 0.4631 data: 0.0036 max mem: 22446 +train: [17] [260/400] eta: 0:01:05 lr: 0.000018 loss: 0.4238 (0.4258) grad: 0.0257 (0.0267) time: 0.4537 data: 0.0034 max mem: 22446 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 0.4279 (0.4259) grad: 0.0258 (0.0267) time: 0.4555 data: 0.0035 max mem: 22446 +train: [17] [300/400] eta: 0:00:47 lr: 0.000016 loss: 0.4188 (0.4255) grad: 0.0269 (0.0267) time: 0.6612 data: 0.1853 max mem: 22446 +train: [17] [320/400] eta: 0:00:38 lr: 0.000016 loss: 0.4248 (0.4264) grad: 0.0268 (0.0267) time: 0.4452 data: 0.0032 max mem: 22446 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 0.4336 (0.4273) grad: 0.0265 (0.0267) time: 0.4459 data: 0.0033 max mem: 22446 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 0.4170 (0.4268) grad: 0.0262 (0.0267) time: 0.4693 data: 0.0033 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.4152 (0.4263) grad: 0.0260 (0.0266) time: 0.4598 data: 0.0033 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.4194 (0.4264) grad: 0.0255 (0.0266) time: 0.4765 data: 0.0036 max mem: 22446 +train: [17] Total time: 0:03:09 (0.4740 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.4194 (0.4264) grad: 0.0255 (0.0266) +eval (validation): [17] [ 0/63] eta: 0:03:28 time: 3.3173 data: 3.0726 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:20 time: 0.3248 data: 0.0037 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3335 data: 0.0029 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3401 data: 0.0032 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3418 data: 0.0033 max mem: 22446 +eval (validation): [17] Total time: 0:00:24 (0.3856 s / it) +cv: [17] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.084 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:46 lr: nan time: 3.4168 data: 3.0825 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:43 lr: 0.000012 loss: 0.4080 (0.4134) grad: 0.0263 (0.0267) time: 0.4472 data: 0.0030 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:05 lr: 0.000012 loss: 0.4080 (0.4109) grad: 0.0266 (0.0271) time: 0.4402 data: 0.0030 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:50 lr: 0.000011 loss: 0.4149 (0.4120) grad: 0.0265 (0.0268) time: 0.4670 data: 0.0038 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:36 lr: 0.000011 loss: 0.4296 (0.4174) grad: 0.0258 (0.0266) time: 0.4559 data: 0.0028 max mem: 22446 +train: [18] [100/400] eta: 0:02:24 lr: 0.000010 loss: 0.4270 (0.4193) grad: 0.0250 (0.0265) time: 0.4527 data: 0.0032 max mem: 22446 +train: [18] [120/400] eta: 0:02:13 lr: 0.000009 loss: 0.4268 (0.4213) grad: 0.0255 (0.0265) time: 0.4547 data: 0.0034 max mem: 22446 +train: [18] [140/400] eta: 0:02:03 lr: 0.000009 loss: 0.4443 (0.4237) grad: 0.0263 (0.0265) time: 0.4526 data: 0.0035 max mem: 22446 +train: [18] [160/400] eta: 0:01:53 lr: 0.000008 loss: 0.4324 (0.4227) grad: 0.0255 (0.0263) time: 0.4628 data: 0.0034 max mem: 22446 +train: [18] [180/400] eta: 0:01:43 lr: 0.000008 loss: 0.4279 (0.4231) grad: 0.0258 (0.0264) time: 0.4626 data: 0.0035 max mem: 22446 +train: [18] [200/400] eta: 0:01:34 lr: 0.000007 loss: 0.4296 (0.4226) grad: 0.0265 (0.0264) time: 0.4593 data: 0.0035 max mem: 22446 +train: [18] [220/400] eta: 0:01:24 lr: 0.000007 loss: 0.4080 (0.4222) grad: 0.0265 (0.0264) time: 0.4628 data: 0.0036 max mem: 22446 +train: [18] [240/400] eta: 0:01:15 lr: 0.000006 loss: 0.4080 (0.4217) grad: 0.0263 (0.0264) time: 0.4613 data: 0.0035 max mem: 22446 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 0.4183 (0.4217) grad: 0.0267 (0.0264) time: 0.4605 data: 0.0036 max mem: 22446 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 0.4183 (0.4221) grad: 0.0267 (0.0264) time: 0.4427 data: 0.0033 max mem: 22446 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 0.4255 (0.4234) grad: 0.0257 (0.0263) time: 0.6650 data: 0.1896 max mem: 22446 +train: [18] [320/400] eta: 0:00:38 lr: 0.000005 loss: 0.4266 (0.4239) grad: 0.0258 (0.0263) time: 0.4563 data: 0.0032 max mem: 22446 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.4236 (0.4239) grad: 0.0265 (0.0264) time: 0.4532 data: 0.0033 max mem: 22446 +train: [18] [360/400] eta: 0:00:19 lr: 0.000004 loss: 0.4272 (0.4238) grad: 0.0260 (0.0264) time: 0.4555 data: 0.0034 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.4272 (0.4237) grad: 0.0258 (0.0264) time: 0.4644 data: 0.0035 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.4198 (0.4235) grad: 0.0260 (0.0264) time: 0.4490 data: 0.0034 max mem: 22446 +train: [18] Total time: 0:03:09 (0.4739 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.4198 (0.4235) grad: 0.0260 (0.0264) +eval (validation): [18] [ 0/63] eta: 0:03:35 time: 3.4171 data: 3.1210 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:22 time: 0.3906 data: 0.0043 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:10 time: 0.3814 data: 0.0034 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3410 data: 0.0031 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3430 data: 0.0032 max mem: 22446 +eval (validation): [18] Total time: 0:00:26 (0.4241 s / it) +cv: [18] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.084 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:20 lr: nan time: 3.5011 data: 3.1059 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:54 lr: 0.000003 loss: 0.4315 (0.4207) grad: 0.0254 (0.0262) time: 0.4741 data: 0.0029 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:14 lr: 0.000003 loss: 0.4233 (0.4177) grad: 0.0268 (0.0267) time: 0.4565 data: 0.0035 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:55 lr: 0.000002 loss: 0.4132 (0.4185) grad: 0.0272 (0.0270) time: 0.4712 data: 0.0034 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:41 lr: 0.000002 loss: 0.4196 (0.4199) grad: 0.0266 (0.0269) time: 0.4712 data: 0.0034 max mem: 22446 +train: [19] [100/400] eta: 0:02:29 lr: 0.000002 loss: 0.4196 (0.4204) grad: 0.0261 (0.0269) time: 0.4609 data: 0.0034 max mem: 22446 +train: [19] [120/400] eta: 0:02:17 lr: 0.000002 loss: 0.4184 (0.4255) grad: 0.0258 (0.0268) time: 0.4587 data: 0.0038 max mem: 22446 +train: [19] [140/400] eta: 0:02:06 lr: 0.000001 loss: 0.4301 (0.4258) grad: 0.0255 (0.0266) time: 0.4707 data: 0.0035 max mem: 22446 +train: [19] [160/400] eta: 0:01:55 lr: 0.000001 loss: 0.4230 (0.4251) grad: 0.0259 (0.0266) time: 0.4469 data: 0.0034 max mem: 22446 +train: [19] [180/400] eta: 0:01:45 lr: 0.000001 loss: 0.4208 (0.4248) grad: 0.0256 (0.0265) time: 0.4624 data: 0.0034 max mem: 22446 +train: [19] [200/400] eta: 0:01:35 lr: 0.000001 loss: 0.4191 (0.4235) grad: 0.0256 (0.0264) time: 0.4559 data: 0.0035 max mem: 22446 +train: [19] [220/400] eta: 0:01:25 lr: 0.000001 loss: 0.4192 (0.4237) grad: 0.0262 (0.0265) time: 0.4523 data: 0.0033 max mem: 22446 +train: [19] [240/400] eta: 0:01:15 lr: 0.000001 loss: 0.4296 (0.4243) grad: 0.0262 (0.0265) time: 0.4669 data: 0.0033 max mem: 22446 +train: [19] [260/400] eta: 0:01:06 lr: 0.000000 loss: 0.4236 (0.4230) grad: 0.0271 (0.0265) time: 0.4759 data: 0.0034 max mem: 22446 +train: [19] [280/400] eta: 0:00:56 lr: 0.000000 loss: 0.4129 (0.4234) grad: 0.0263 (0.0265) time: 0.4502 data: 0.0034 max mem: 22446 +train: [19] [300/400] eta: 0:00:48 lr: 0.000000 loss: 0.4256 (0.4237) grad: 0.0261 (0.0264) time: 0.6427 data: 0.1773 max mem: 22446 +train: [19] [320/400] eta: 0:00:38 lr: 0.000000 loss: 0.4275 (0.4241) grad: 0.0260 (0.0264) time: 0.4491 data: 0.0030 max mem: 22446 +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 0.4275 (0.4239) grad: 0.0260 (0.0264) time: 0.4504 data: 0.0033 max mem: 22446 +train: [19] [360/400] eta: 0:00:19 lr: 0.000000 loss: 0.4337 (0.4244) grad: 0.0253 (0.0263) time: 0.4541 data: 0.0033 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.4351 (0.4244) grad: 0.0253 (0.0263) time: 0.4451 data: 0.0034 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.4223 (0.4236) grad: 0.0256 (0.0263) time: 0.4476 data: 0.0034 max mem: 22446 +train: [19] Total time: 0:03:10 (0.4761 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.4223 (0.4236) grad: 0.0256 (0.0263) +eval (validation): [19] [ 0/63] eta: 0:03:21 time: 3.2063 data: 2.9658 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:20 time: 0.3370 data: 0.0040 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3449 data: 0.0026 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3481 data: 0.0032 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3491 data: 0.0032 max mem: 22446 +eval (validation): [19] Total time: 0:00:24 (0.3934 s / it) +cv: [19] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.084 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9774305555555556, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 19, "is_best": false, "best_score": 0.9776785714285714} +eval (train): [20] [ 0/297] eta: 0:15:12 time: 3.0710 data: 2.7991 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:20 time: 0.3797 data: 0.0040 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:49 time: 0.3378 data: 0.0032 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:35 time: 0.3576 data: 0.0036 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:24 time: 0.3450 data: 0.0035 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:14 time: 0.3454 data: 0.0033 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:06 time: 0.3547 data: 0.0035 max mem: 22446 +eval (train): [20] [140/297] eta: 0:00:58 time: 0.3432 data: 0.0035 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3442 data: 0.0034 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:42 time: 0.3566 data: 0.0034 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3348 data: 0.0032 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3419 data: 0.0034 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3379 data: 0.0034 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3597 data: 0.0033 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3356 data: 0.0033 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3179 data: 0.0031 max mem: 22446 +eval (train): [20] Total time: 0:01:46 (0.3571 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:04 time: 2.9236 data: 2.6864 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3537 data: 0.0144 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3378 data: 0.0028 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3205 data: 0.0032 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3218 data: 0.0031 max mem: 22446 +eval (validation): [20] Total time: 0:00:24 (0.3818 s / it) +eval (test): [20] [ 0/79] eta: 0:04:12 time: 3.1958 data: 2.9480 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3512 data: 0.0117 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3502 data: 0.0037 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3541 data: 0.0026 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3089 data: 0.0030 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3806 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9776785714285714, "hparam": [22, 1.0], "hparam_id": 43, "epoch": 15, "is_best": true, "best_score": 0.9776785714285714} +eval (train): [20] [ 0/297] eta: 0:15:31 time: 3.1372 data: 2.8522 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:17 time: 0.3644 data: 0.0027 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:50 time: 0.3591 data: 0.0033 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:35 time: 0.3479 data: 0.0034 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:25 time: 0.3705 data: 0.0035 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:16 time: 0.3548 data: 0.0033 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:07 time: 0.3397 data: 0.0033 max mem: 22446 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3654 data: 0.0036 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3516 data: 0.0034 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3449 data: 0.0034 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3396 data: 0.0034 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3335 data: 0.0036 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3453 data: 0.0036 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3381 data: 0.0034 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3489 data: 0.0035 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3301 data: 0.0032 max mem: 22446 +eval (train): [20] Total time: 0:01:46 (0.3594 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:12 time: 3.0531 data: 2.7701 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3614 data: 0.0026 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3368 data: 0.0033 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3213 data: 0.0033 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3224 data: 0.0033 max mem: 22446 +eval (validation): [20] Total time: 0:00:24 (0.3872 s / it) +eval (test): [20] [ 0/79] eta: 0:03:58 time: 3.0233 data: 2.7903 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3658 data: 0.0194 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3415 data: 0.0029 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3313 data: 0.0034 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3216 data: 0.0031 max mem: 22446 +eval (test): [20] Total time: 0:00:29 (0.3777 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 15 | 0.0066 | 0.05 | 43 | [22, 1.0] | train | 0.00031561 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 15 | 0.0066 | 0.05 | 43 | [22, 1.0] | validation | 0.085745 | 0.97768 | 0.0022023 | 0.97547 | 0.0027146 | +| flat_mae | patch | attn | hcpya_task21 | best | 15 | 0.0066 | 0.05 | 43 | [22, 1.0] | test | 0.11182 | 0.97679 | 0.0022301 | 0.97125 | 0.0029954 | + + +done! total time: 1:19:56 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/train_log.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..516c62817555c73a47ff115e92fe6623725ecfbb --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.5957983493804933, "train/grad": 0.044968210496008396, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.038973388671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.038546142578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.0378857421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.037298583984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.03665771484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.03576171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.034674072265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.03357666015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.03204345703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.030350341796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.028624267578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.026082763671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0235888671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.019722900390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.015931396484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.012098388671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.00695556640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.00052001953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.99287841796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.98519287109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.974803466796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9631817626953123, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.94921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9330291748046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9151629638671874, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8924945068359373, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.870736083984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8498394775390623, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.8190826416015624, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.778211822509766, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.73718994140625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.695882110595703, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6335269927978517, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.5720760726928713, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.493120403289795, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.4096128225326536, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3159404397010803, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.223470887541771, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1203104576468466, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.990038886964321, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8890498180687427, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.801639655381441, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6906731328368187, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.5984770439565181, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4979685172438622, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3982599461078644, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.3191972466930748, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.2319911988452077, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.1625718472898006, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0062951800925657156, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006293561246711761, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006291084229014814, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006288648403715342, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006286262283101678, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006283544499892741, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00628064306685701, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006278048565145582, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0062749738479033115, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006272487179376185, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006270382669754326, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00626725007314235, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006266008648090064, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006266249476466328, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006268258807249367, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006272439192980528, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006280686233658343, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006294458566699177, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006313814895693212, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00633530248189345, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006363808810710907, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0063924122089520094, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0064179248828440906, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0064334955951198935, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0064372662571258845, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0064342541433870795, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006436363102402538, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0064484959817491475, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0064811436389572916, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0065362984989769755, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006591012685094029, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006637579132802785, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006687932319473475, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006714968234300614, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006726232415530831, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006722282026894391, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006707246073056013, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006680159037932754, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006638815419282764, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006580508120823652, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00653381442418322, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006495065598282963, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006435191419441253, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.006358004614012316, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0062494736909866335, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006165037546306849, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.006126455490011722, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.006129351458512246, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006108818247448653, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.033884286880493, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0327236652374268, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0307722091674805, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0288302898406982, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.026876211166382, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0241546630859375, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0210399627685547, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0175418853759766, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.012906789779663, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0078697204589844, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.00283145904541, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.995112657546997, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.987382173538208, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9757769107818604, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.964123249053955, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.95241641998291, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.9367403984069824, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9169743061065674, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.893211841583252, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8694095611572266, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8379976749420166, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.80366587638855, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7639167308807373, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.7209513187408447, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.676111936569214, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.620495319366455, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.565007448196411, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5075812339782715, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.416865110397339, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.2893025875091553, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.157451868057251, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.02569580078125, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.8366763591766357, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.6653419733047485, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.4688249826431274, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.2874372005462646, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.1092309951782227, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9524842500686646, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7944061160087585, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6190469861030579, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5057107210159302, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.42375367879867554, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.34029823541641235, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.28466784954071045, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.23643967509269714, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.20318618416786194, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.18446066975593567, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.16981518268585205, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.16423818469047546, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17038690476190477, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17584325396825398, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18129960317460317, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.18377976190476192, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.18774801587301587, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.1884920634920635, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.18725198412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.18700396825396826, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1865079365079365, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.18501984126984128, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.18427579365079366, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18229166666666666, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18030753968253968, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17857142857142858, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1775793650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17559523809523808, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17485119047619047, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17410714285714285, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17311507936507936, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1728670634920635, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17311507936507936, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1728670634920635, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17336309523809523, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17633928571428573, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.18154761904761904, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.19196428571428573, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.20858134920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.22891865079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26711309523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.3288690476190476, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.408234126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.4809027777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.5597718253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6118551587301587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6460813492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.683531746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7202380952380952, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7643849206349206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8204365079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8650793650793651, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8841765873015873, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8980654761904762, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.908234126984127, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9213789682539683, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9337797619047619, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9429563492063492, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9456845238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9508928571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9508928571428571, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.029761921425769174, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03065277483368801, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.030815004107141067, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.030053219912975736, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03141208075817684, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.030446324699044614, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.029025350673923565, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.028596445462392584, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.028092873734459695, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02698586355078812, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.026483442633875993, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.024951877725913625, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02339230012454991, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02182634113586028, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.020936517190457443, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.019040117304710495, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01830228023427727, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01755256968211715, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01653823009447635, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01627943478948159, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01653823009447635, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01627943478948159, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01679562093447274, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.019778845606168088, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.024547621453847063, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03219290481891429, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04190928114424543, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.05279436693789485, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07819808037519019, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.13382519687116687, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20832536309307415, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2717026330976983, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.3358196990017972, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.38224167794372715, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.420081198528523, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.47373998567293363, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5532073371564856, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6542923520659003, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.7658643136386123, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8335668172494225, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.861320541348415, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8827413972915266, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8954396815161877, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9127222952712288, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.926080807778159, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9376706536486753, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9406507224304174, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9449232382994444, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9423001143090453, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 1.2319911988452077, "validation/loss_best": 0.16981518268585205, "validation/acc_best": 0.9508928571428571, "validation/f1_best": 0.9449232382994444} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.8010848289728165, "train/grad": 0.04268603265285492, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.023404541015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.020755615234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.01616943359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0116943359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.00729248046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.001025390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.99383544921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.985887451171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.975078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.963365478515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.951607666015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.93338623046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9152587890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8881494140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8617474365234377, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8360443115234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8033856201171874, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7645977783203124, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7199252319335936, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6764089965820315, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.618916015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.553395538330078, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.472146453857422, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.374833831787109, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2629480743408203, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.1181414222717283, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9814286041259765, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8543258905410767, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.68194011926651, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4830416417121888, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3142006957530976, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1703359842300416, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9927451598644257, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8519001030921936, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7070438180863857, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.5861670329421759, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.47910388201475146, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.3958860044181347, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.32374312363564967, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.25674157069996, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.21914881441742182, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.19438872070983051, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.17087629584595562, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1567462148144841, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1453477172460407, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.13882411155849694, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.13550657149404288, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13218941141851245, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.13212594480253756, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006245447502005845, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0062428805977106094, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006239332486875355, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006238035946153104, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006239230595529079, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006243849459569901, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006253621662035584, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006269172939937562, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006296120639890432, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006331738298758865, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0063703436544165016, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006431818353012204, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006489129881374538, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006557281601708383, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006598378370981663, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0066161373304203155, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00662030502455309, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0066205036779865625, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006635660007596016, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006668959935195744, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006732040767092258, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00681067536585033, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006895994986407459, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006969527264591307, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007018582252785563, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007032186242286116, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006999414837919176, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0069378667883574965, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006817844728939235, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006639390429481864, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006454985484015197, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00627284835325554, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006011146355886013, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005776743214810267, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0055229036940727385, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005312451950740069, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005109637936111539, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0049372255243361, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004796820387709886, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004668730120174587, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004580022401642054, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004516093120910228, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00444664979702793, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0044260657689301295, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004462472159648314, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004590546691324562, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004718266022391618, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004810518688173033, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004978255536407232, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0107593536376953, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0061182975769043, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.998445987701416, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9907543659210205, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9830307960510254, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.972233533859253, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9598276615142822, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.945774555206299, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9268877506256104, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.906257390975952, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.885575294494629, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.85390567779541, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8228204250335693, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7783191204071045, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7372047901153564, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6994550228118896, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.652606248855591, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.59584379196167, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.52618670463562, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.453001022338867, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3502049446105957, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.229457139968872, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.0795326232910156, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9074337482452393, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.724857211112976, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.5149672031402588, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.3402800559997559, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.1936705112457275, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.0119261741638184, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.8208950757980347, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6719539165496826, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5556007027626038, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4284503757953644, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3434310257434845, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.27310264110565186, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.2287832498550415, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.19841627776622772, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.17813345789909363, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.16195952892303467, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1485142856836319, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14119426906108856, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13697361946105957, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13195717334747314, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12784303724765778, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12517744302749634, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12716013193130493, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.13285291194915771, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.15379703044891357, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.18319196999073029, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.18452380952380953, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18353174603174602, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18055555555555555, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17906746031746032, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17807539682539683, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17633928571428573, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.1746031746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17237103174603174, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.171875, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17162698412698413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17162698412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17162698412698413, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17336309523809523, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17683531746031747, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18452380952380953, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19866071428571427, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22743055555555555, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2601686507936508, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.30183531746031744, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.37103174603174605, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.46403769841269843, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5379464285714286, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5930059523809523, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.636656746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6711309523809523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7103174603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7671130952380952, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8253968253968254, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8601190476190477, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8829365079365079, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9069940476190477, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9221230158730159, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9320436507936508, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9417162698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9449404761904762, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.949156746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9503968253968254, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9575892857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9556051587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.953125, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9469246031746031, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02677590964494994, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.026082965882537983, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02349272616142955, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.022279396511955516, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021368669910527893, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.019753966697379766, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.018061908189123302, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017306235311850746, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01627943478948159, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01575979178024608, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01523075119054338, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014964028515791103, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014964028515791103, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014963977814526306, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01679562093447274, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.020257871963189795, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.027005887150059825, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03746287375761688, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.05684457624086708, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0762159084335367, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.10693205399872442, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17379897249755102, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2591736799466776, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3174937886805933, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3625447142700517, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.40957741392143693, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.45716401678540375, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5322765955814412, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6506072735955003, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7589334288317995, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8154867358730823, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8565150301947688, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8916975913314008, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.912835087950349, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9258179475460317, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9367211090926235, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9410261154154655, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9452949469529235, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9459480665730802, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9499305015063234, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9527279966153299, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9542962171102003, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9567916801853549, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9570099585003501, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9547328127167483, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9512330238890152, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.94872250525259, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9477692832781797, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9435805768845846, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 0.17087629584595562, "validation/loss_best": 0.13195717334747314, "validation/acc_best": 0.9615575396825397, "validation/f1_best": 0.9567916801853549} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.411690993309021, "train/grad": 0.04086035426706076, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.992783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.98540283203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.973408203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.96112060546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.948873291015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.931458740234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.91162109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.889259033203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.859833984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.828648681640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7988287353515626, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7553228759765624, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7146923828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6565960693359374, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5996914672851563, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5422283935546877, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.463391876220703, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3611767578125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.23514835357666, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1094108390808106, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9478553199768067, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7796410417556763, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.596758828163147, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.4114374232292175, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.232631628215313, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.0392298465967178, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.8840242651104927, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.7577543984353542, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6099501650035382, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.4699986321479082, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.3750555706769228, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.310083426758647, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.24718480240553617, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.20863101674243809, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.17718681219965218, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.15575103159993886, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.13897472741082312, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.1265167388971895, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.11571952329017222, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.10517147022299468, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09890692431479692, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09462145804427564, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09134250974282622, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0913164896145463, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09282872657291591, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1002456832304597, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10770153573714197, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13040086533874273, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.15704154414124788, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006234320276416838, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006246975134126842, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006277086383197457, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0063157844450324775, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006359564072918147, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00642378151183948, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006495959185995162, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006568273499142379, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006635968296322971, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006668048179708421, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006664157074410469, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006621082383207977, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006576143784914165, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006556196487508714, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006601136694662273, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00669021847192198, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006832309479359537, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0069895548722706735, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007104108547791838, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007136630595196039, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007083388471510261, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006951184577774256, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006756038926541805, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006538130580447614, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006326921619474888, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006093767303973437, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005886171851307154, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005689927979838103, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005419086336623877, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005107195845339447, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004855720736086369, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004655749214580282, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004432654685806483, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004282774582970887, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004150641314918175, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004042920754291118, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003942669456009753, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0038660453108605, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003808450231445022, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003760203165584244, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003737705693929456, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037382136209635065, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0038276003242935985, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004004034355166369, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0042529379841289485, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004607761166407726, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0049740102101350206, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005796806275029666, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006502401910256595, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9720609188079834, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9615633487701416, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9439287185668945, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.926138162612915, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9082248210906982, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.883063316345215, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.854461431503296, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.822854518890381, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.782503843307495, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7419214248657227, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.704535961151123, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.651193857192993, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.599642038345337, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5204432010650635, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4367921352386475, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.349071741104126, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.2275373935699463, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.0737571716308594, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.895452857017517, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.7315566539764404, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.5403674840927124, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3600146770477295, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.1785045862197876, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0033414363861084, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.8394770622253418, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6670811176300049, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5361164808273315, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.43824827671051025, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3388206660747528, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.2621072828769684, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.21918293833732605, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.19265617430210114, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1683495193719864, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1535424143075943, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.14042647182941437, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1310931295156479, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12449594587087631, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.12057729065418243, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11758345365524292, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11708904802799225, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1192835196852684, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11697425693273544, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1157754585146904, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11683234572410583, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12479851394891739, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.14444030821323395, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.15122383832931519, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.21745207905769348, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.29219916462898254, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17633928571428573, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1746031746031746, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17261904761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17212301587301587, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.171875, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17162698412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17162698412698413, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17336309523809523, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17683531746031747, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18551587301587302, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.19915674603174602, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23065476190476192, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.26686507936507936, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.30505952380952384, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.37549603174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.46106150793650796, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5386904761904762, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5855654761904762, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6212797619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6654265873015873, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7212301587301587, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.785218253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8377976190476191, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8727678571428571, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9012896825396826, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9136904761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9253472222222222, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9392361111111112, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.951140873015873, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9543650793650794, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9632936507936508, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9429563492063492, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9347718253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019741651137875346, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.018061908189123302, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.017306235311850746, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01627943478948159, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01602213418851789, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015496001507004037, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01523075119054338, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014964028515791103, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.014963977814526306, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01679562093447274, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.020257871963189795, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.027690525909417934, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03754117419159492, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05710061479268064, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07823399082960882, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10841482936584212, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1766219031492878, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.2456224508473433, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.30580761237477266, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.3458332958532434, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3859067070380386, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.45351536480857857, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5740098431217142, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6975826972698469, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.795705021854651, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8462851459160738, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8855372058955069, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.901102181364975, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9154153194875011, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9321749932832113, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9426519416488943, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9472066589596341, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9504125091237718, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9525464548893487, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9546534144633041, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9554492175104092, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9573751522643195, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9571873874994985, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9591605665393643, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9561404056572833, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9539280872265673, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9545840203806792, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9557030258781716, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9550324287945938, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9524187750046192, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.946223022973442, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9463370014595023, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.92968143602057, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9156401988574252, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.11571952329017222, "validation/loss_best": 0.11758345365524292, "validation/acc_best": 0.9640376984126984, "validation/f1_best": 0.9591605665393643} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 1.1702293476462364, "train/grad": 0.042875177208334204, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.945496826171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.930892333984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.906446533203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.881878662109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.857564697265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.8243231201171874, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7880780029296877, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7496356201171874, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.702078857421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6537115478515627, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.606329345703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.532542724609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4558062744140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.335482940673828, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.2115238952636718, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.0876702499389648, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9284575653076172, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.745180606842041, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.552237992286682, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.3873574662208557, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.2030789160728455, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.032782445549965, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.863571320772171, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.7051718999445439, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5653349815309048, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.4335372722893953, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.34622795552015306, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2879766769334674, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.23292335890233518, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1908254114165902, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16524191111326217, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.14805155700072647, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.13028640828095375, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.11785256281495095, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.10570886290632188, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.09577674216590822, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.08698966093361378, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.08012754241004587, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.07438528311438858, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06970756592229009, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06754342148080468, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06852652883157134, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0719212025590241, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.07790724377147853, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09245837614871562, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.126814238531515, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1696424979530275, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.23442101275548338, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.413750900151208, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006468612640164792, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006528444036375731, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006627023154869675, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006713488851673901, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0067788912844844165, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006827112790197134, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006824961279053241, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006777046013157814, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006709317564964294, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006685416197869927, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006721598154399544, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006848958868067712, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0069972664536908265, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007174691907130182, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007262630024924875, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007267128534149379, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007178286723792553, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006988795255310833, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006742034079506993, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0065283618774265055, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006304309035185724, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006102740636561066, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005874415701255202, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005598402462201193, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005287337874760851, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004941240168409422, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004673180399695411, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004459882125956938, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0042161766299977895, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003980361839057878, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003810360713978298, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003690795313450508, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0035694398637861014, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0034885777212912217, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003409213059931062, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003344945933786221, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003292494573397562, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0032575411960715428, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003269440425792709, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003383934496087022, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0035153320047538726, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003673487968626432, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003875773508916609, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004134632684872486, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0047989567957120016, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006183414613478817, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007338943782960996, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009396175283472984, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013646977086318656, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.916567325592041, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.897361993789673, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.865373373031616, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.833829402923584, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.803205728530884, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7626636028289795, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.720130443572998, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.6761906147003174, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.6207334995269775, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.560544013977051, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.4981536865234375, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.397050619125366, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.2907822132110596, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.1269543170928955, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.9657670259475708, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.8139866590499878, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.6323261260986328, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.4391396045684814, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.248409390449524, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.091223120689392, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9189937710762024, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7628600597381592, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6123862266540527, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.47873246669769287, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3721748888492584, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2873688340187073, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.23942944407463074, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.20969556272029877, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.18212369084358215, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.16129864752292633, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.14951449632644653, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.14206264913082123, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.13436543941497803, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.12860465049743652, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.12347427755594254, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.11997975409030914, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11799150705337524, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11670445650815964, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11417358368635178, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11312706023454666, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1156197190284729, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11960966885089874, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11941073834896088, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.14649906754493713, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.20716260373592377, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.25874900817871094, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.28482767939567566, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5232658386230469, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7074299454689026, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17212301587301587, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.171875, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17162698412698413, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17212301587301587, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.1746031746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17981150793650794, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.19122023809523808, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21155753968253968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.23635912698412698, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.27728174603174605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3291170634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.4320436507936508, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5188492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.580109126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6267361111111112, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.658234126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.707093253968254, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7495039682539683, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8072916666666666, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8506944444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8846726190476191, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9087301587301587, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9228670634920635, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9347718253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9419642857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9583333333333334, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9578373015873016, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9471726190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9434523809523809, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9454365079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9208829365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9253472222222222, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.016283040775138306, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.015496001507004037, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01523075119054338, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014964028515791103, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014695821028922454, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015494504606880913, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.018061908189123302, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.023010123585393588, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03207668671192675, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04648901146506262, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0614350520747682, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08678694437607967, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.13237123865162564, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.23509255783838545, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.308679427666593, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.3593510391246103, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.40009370723746346, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.43798584494338605, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5289431660362401, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.615932494869018, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.7363091432293546, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8136962328673986, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8628886501263703, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8958023934742146, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9128240803053623, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9284307496152187, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9377858051885708, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9431884175749662, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9462762822069267, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9480639259349711, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.951597422837939, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9530581292766659, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.95325862161707, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9543544535029695, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9542466987592005, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9542831075918586, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9554116683765504, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.956927148784038, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9582454108686268, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.961899151196552, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9632220917476373, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9593349229048892, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9591301836537437, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9496701254546541, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.939660348548486, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9350362533937807, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9376022323194397, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9095606978863542, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9110480913812538, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 0.06852652883157134, "validation/loss_best": 0.11960966885089874, "validation/acc_best": 0.9645337301587301, "validation/f1_best": 0.9593349229048892} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.0136383759975434, "train/grad": 0.04980717794969678, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8818701171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8578448486328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.818533935546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.78125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.74619384765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7007598876953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.6522137451171877, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.599002685546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.5268215942382812, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.445272216796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.3599932861328123, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.2243758392333985, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.0878630828857423, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.8912158584594727, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.7124841785430909, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.5545260667800904, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.373644597530365, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.1866471445560456, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.004440484046936, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8561907023191452, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6978749403357506, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5611481986939907, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.43979321599006654, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3438327564299107, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.2746169779077172, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.22065570168197154, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.1884850126504898, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.1670116289705038, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.14512599969282747, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1256917819008231, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.11205158053897321, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1017193900141865, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.08989440245553851, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.08103593438863754, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.07222819672897458, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.06554279922507704, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.059645428489893675, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05520714519545436, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05277830874547362, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.05304954391904175, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.058062372542917726, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06255323386751116, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09303926440887153, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.12269645421765744, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.16358595287427305, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2861164757423103, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.36810941975563766, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.549906332148239, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7956792041007429, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00664420539746061, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0067098089773207905, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006761509117204696, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006746247785631567, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00669228199403733, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0066165272332727905, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0065914065670222045, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006648661091458052, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006800083792768419, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006978558951523155, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007126077641732991, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007258087764494121, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007279374697245658, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007166062123142183, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006969843569677323, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0067629188881255685, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006526992390863597, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006302909860387444, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006085391249507665, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005875909666065127, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005592536041513085, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005289307397324592, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004966443841112778, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0046545695280656215, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004377549523487687, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004106146203121171, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0039081413566600534, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0037586267408914863, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0035891891812207177, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003424499670509249, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0033012036309810356, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0032079793309094384, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0031073912512511017, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003039230642025359, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0029744180210400373, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002940392001182772, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002926706921425648, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00293886859799386, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003037578915100312, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0032661085700965487, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0036488552571972833, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003932788437232375, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005097603160829749, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.006589427719591185, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007837235320475883, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011103690156014636, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01291271110836533, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.016746283367974683, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.020734392488375306, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.84538197517395, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8163933753967285, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7706544399261475, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7286133766174316, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.689894676208496, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6388862133026123, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.5814971923828125, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.5150437355041504, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.421764612197876, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.3152055740356445, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.2053823471069336, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0359947681427, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.8739007711410522, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.6555206775665283, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.4702730178833008, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.313596487045288, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.1391083002090454, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9612575173377991, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.790518045425415, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6544806957244873, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5152886509895325, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.4038543105125427, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.3146761953830719, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.2521921694278717, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.21091607213020325, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1794854700565338, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.1603143811225891, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.14714235067367554, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.13409613072872162, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.12332481890916824, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.11654447019100189, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.11206945776939392, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.10831892490386963, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.10522808879613876, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.10191008448600769, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1019212156534195, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.10382426530122757, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10778269916772842, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11220172792673111, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11638142913579941, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1379823237657547, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14203166961669922, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2061845064163208, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.21035394072532654, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.30857402086257935, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.43880850076675415, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6229232549667358, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.001397728919983, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9402546882629395, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17336309523809523, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17708333333333334, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.18625992063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.20238095238095238, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22842261904761904, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.26711309523809523, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3179563492063492, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.3854166666666667, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.48387896825396826, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5612599206349206, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.621031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6545138888888888, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6912202380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7353670634920635, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8013392857142857, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.845734126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8712797619047619, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9010416666666666, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9164186507936508, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9310515873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9437003968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9518849206349206, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.966765873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.96875, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.970734126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9670138888888888, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9523809523809523, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.953125, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9432043650793651, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9437003968253969, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9389880952380952, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9352678571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9432043650793651, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.014695821028922454, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014695821028922454, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01469650577635825, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01679562093447274, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02049551468857267, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.028248148543345505, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.04044253796406442, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0577186165656944, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.08018341450012494, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.12264235574479891, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.19069745508154354, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.2779565607643096, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.34145793412553244, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.39361379045381684, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.4327957712599595, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.49588296238045326, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.592567265353493, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7256793357956862, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8031033325392001, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8459262653338203, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8867920725786667, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9060550084291243, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9239348990110257, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9400622796993284, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.943919056333912, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9487797062684116, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9531758319218098, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9569419793744455, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.959128808981882, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9607901899084437, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9641704045294046, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9659426489882973, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9669487511548653, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9660583736726874, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9684793678531476, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9684420935025774, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9679378406238544, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.966148871330532, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9635092353320328, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.958797041131301, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9562975765994349, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9607682857329823, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9465882361681077, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.943889718744568, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9302091626974526, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9335212384670681, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9290509196534755, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9201105029049133, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9362676613784954, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.059645428489893675, "validation/loss_best": 0.10382426530122757, "validation/acc_best": 0.970734126984127, "validation/f1_best": 0.9679378406238544} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.8740982493758201, "train/grad": 0.049790341090410944, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8108941650390626, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7788909912109374, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.729495849609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.68416015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.640770263671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.58027587890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.5087771606445313, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.424422607421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.3064364624023437, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1750677490234374, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.0446355056762697, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8535631370544434, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.6808746147155762, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4593525743484497, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2766387474536895, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.123905396461487, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.9547541421651841, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.7846189749240875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.6256631694734096, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5050568920373917, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.3902781009674072, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.3065301089733839, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.24451101295650005, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.20121293991804123, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.17077567297965288, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.14511691661551596, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.12780540369451046, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.11517367366701364, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.10118828165344894, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.08785678610205651, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.07791953132487833, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.07020905767567456, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.06127933437004685, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.05424728502519429, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04623662367463112, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.039624664708971975, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.03484274193644524, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03398378880694509, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.03510601444169879, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.03970573819242418, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.045827461760491135, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05374041515402496, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1033475510776043, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.14187573848292231, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.214148703943938, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2933527998998761, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3902614615019411, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5129641477204859, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7434386662766337, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00679766708984971, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0067713625938631596, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006674324118066579, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00660152519820258, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006597438191529363, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006686265831813216, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006846370436251164, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0070246767182834445, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0071962932497262955, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007275877860374749, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00725982690230012, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007112548642326146, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00690211248351261, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006597564732655883, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006362945633009076, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006182497013360262, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0059736530645750465, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005712859255727381, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005389692747266963, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005083748385077342, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004740962737705559, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0044482199370395395, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0041930930421222, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0039831220277119425, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003804247146472335, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0036199010809650645, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0034786010440438987, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0033677628968143834, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003240857608616352, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0031176206667441874, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003026068267645314, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002953241829527542, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0028586222924059258, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002761588662979193, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002600363165838644, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002451305225549731, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002376394570019329, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0025078473205212503, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0027413985118619165, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0031180007201328406, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003578889440977946, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004092141756555066, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006045929182873806, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00780046061205212, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009840123060275801, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012047303396393545, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014113811145361978, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.016597845731857887, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.02021688524459023, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.771207094192505, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.73573899269104, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6816415786743164, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.631086826324463, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5809760093688965, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.508805990219116, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.422041177749634, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.3196094036102295, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.17848539352417, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.0257833003997803, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8795194625854492, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6752249002456665, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.499315857887268, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.2816907167434692, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.105857491493225, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.9600256681442261, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.8001337647438049, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.6426955461502075, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.501152515411377, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.40016961097717285, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.3122801184654236, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.25359973311424255, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.2118108719587326, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.18245714902877808, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1615278720855713, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.14400333166122437, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.13278262317180634, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.1249677762389183, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.11711226403713226, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.11040905117988586, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10604477673768997, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10296069085597992, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0994114875793457, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09696023166179657, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09569571912288666, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09572778642177582, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09582733362913132, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09898899495601654, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10905471444129944, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12331506609916687, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16185608506202698, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.215377077460289, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2592879831790924, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2722220718860626, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.382535845041275, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4257562458515167, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4862380921840668, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.899853527545929, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9849438071250916, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.171875, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17336309523809523, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17981150793650794, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.1892361111111111, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2058531746031746, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.23487103174603174, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.27033730158730157, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3167162698412698, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3968253968253968, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4826388888888889, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5493551587301587, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.613343253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6493055555555556, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7026289682539683, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7509920634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8025793650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8482142857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8784722222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9050099206349206, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.917906746031746, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9305555555555556, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.941468253968254, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9464285714285714, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9521329365079365, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9630456349206349, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9637896825396826, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.970734126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9583333333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9489087301587301, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9456845238095238, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.953125, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9471726190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9523809523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9422123015873016, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9499007936507936, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01522997330801494, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01679562093447274, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.023010123585393588, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.030734991933324556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.04232267471251454, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.060020966113857786, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.07956219556857139, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.1184035365421144, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.1997837824801374, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.27551087157678544, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.3314395477096858, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.3878148068443653, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.42805821768372515, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5112140159788265, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6215252380214759, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7302597522917259, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.811233443284648, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8553674078089463, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8922224651549155, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9070427068615098, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9230737710902831, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9357626742306231, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9412429728479742, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9466608296856946, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9511036061064961, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9564890158511254, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.958443431742713, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9591685361631542, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9610751374685713, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9627085355582665, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9626066097947289, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9648074323698275, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9645530471095669, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9652920840150395, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9665684377411491, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9680099777839737, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.969964890350896, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9693181608354319, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9693904930998297, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9645776375569297, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9468955769094082, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9386067332623353, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9368695630713398, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.944058298134967, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9410666303818187, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9432254084868086, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.945126853330605, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.929711715741426, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9431512575152856, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.03484274193644524, "validation/loss_best": 0.09582733362913132, "validation/acc_best": 0.9719742063492064, "validation/f1_best": 0.969964890350896} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.7567235356569291, "train/grad": 0.04525151126086712, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.742784423828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.705499267578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.647318115234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5903311157226563, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5318759155273436, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.4463925170898437, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3435951232910157, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.2239818572998047, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0636737823486326, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.896760311126709, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.74262601852417, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.5347080945968627, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.359580078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.1446727871894837, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.9714322632551193, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.82890610486269, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.6754432439804077, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5291891425848008, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.40491454347968103, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.32210992500185964, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.25322707869112493, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.2073014396801591, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.17302771370857953, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.14726931029930712, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.12728062428534032, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.10889282401651144, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.09562303623184562, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.08541085816919804, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.073676315844059, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.06217337717302143, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.053432294949889186, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.04645615319721401, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.038187290150672196, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0319206434674561, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.025742310294881464, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.021346722850576042, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.01896883816458285, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.01834058463573456, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.02044024513103068, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.029109543934464455, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.04553188123740256, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.059822990633547304, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07905592645518482, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10552299931645394, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13570097463205458, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.18551445302553474, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3084463269356638, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3664094923995435, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.44982719228602946, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0066631038836203514, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0065858834725804625, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0065501737059094015, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006626862888224423, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006759181988891214, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006955378025304526, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007134547061286867, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007248708831612021, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007261191979050636, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00714922102401033, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006969969444908202, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006675693325232715, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0064321171259507535, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006167952874675393, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005957712377421558, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005750623794738203, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0054617934999987485, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005112775759771466, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004761338708922267, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004489112653536722, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004208884253166616, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003975595399970189, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003773278429871425, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0035992941819131376, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00344832532631699, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003292106449371204, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0031668892176821826, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0030606855772202833, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0029248348699184136, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0027742394732194952, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0026415638081380166, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0025118541190749964, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0023158821000833995, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002140286387584638, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0019502843472582753, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0018137778181699104, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0017589761701674433, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0017905511520075379, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002054549769454752, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0029222039917658547, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0036853261463693342, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0049746183829847725, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005725945235826657, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00691455964668421, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008113542472683548, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009724761461836807, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012833558736238046, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014697069008525432, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.016508251575270947, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7080209255218506, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6680281162261963, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6040587425231934, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5393271446228027, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.471977949142456, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.373140335083008, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.2551798820495605, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.120046615600586, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.9440629482269287, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.7670305967330933, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.6089463233947754, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.4019997119903564, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.2311358451843262, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.0237042903900146, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.8581175804138184, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.7235373854637146, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.581167459487915, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.44969362020492554, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3438863158226013, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.2777783274650574, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.2256890833377838, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1915370523929596, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.16619902849197388, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.14745476841926575, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.13370637595653534, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1222233921289444, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.11492825299501419, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.11009979248046875, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10533111542463303, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10043797641992569, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.09700413048267365, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.09434632211923599, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.092308908700943, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09089761972427368, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09029622375965118, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08996756374835968, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08924393355846405, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09227463603019714, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09634783864021301, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11834386736154556, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16570302844047546, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.23288299143314362, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.18136481940746307, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.21487708389759064, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.24862565100193024, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5330173373222351, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5275855660438538, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.753239095211029, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6623683571815491, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17683531746031747, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.18377976190476192, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.19915674603174602, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.22470238095238096, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2542162698412698, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2916666666666667, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3566468253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.439484126984127, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5275297619047619, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5860615079365079, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6259920634920635, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6681547619047619, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.716765873015873, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7827380952380952, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8333333333333334, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8638392857142857, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8918650793650794, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9139384920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9280753968253969, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9412202380952381, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9474206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9526289682539683, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.964781746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.970734126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.970734126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.966765873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9516369047619048, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9441964285714286, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.955109126984127, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9434523809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9573412698412699, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.020257871963189795, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.026393223935966652, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.037733801566418756, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0545171538340489, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.07056678309853272, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.09609177514372932, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.15708022786854942, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.23539894439039438, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3120436469223631, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3594896767460671, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.398796942305881, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4538008146847832, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5495538915013185, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6891777358408894, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.784262054358624, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8353084297034017, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8744714204204436, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9029114348392827, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9201125210855973, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9364056533718562, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9436116860662221, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9486816587916321, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9553733028768275, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9574679715702704, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9606426955282968, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9636035212670341, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9651638033721377, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9651677165316949, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9648293193539091, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9647088048161342, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9636598038712116, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9647937042225191, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9661113627461193, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.966917313679776, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9674767142148258, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9677196645423782, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9676608951675648, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9659236751296324, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9668243263571625, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9610268123935846, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9516498422045013, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9495579880479083, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9584013226668924, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9599276128962825, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9608277187709406, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9410143512362187, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9488347642401183, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9359943442160046, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9487438745378827, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.01896883816458285, "validation/loss_best": 0.08924393355846405, "validation/acc_best": 0.9724702380952381, "validation/f1_best": 0.9676608951675648} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.6656346306204796, "train/grad": 0.0384090634714812, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6870098876953126, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6446221923828124, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.574222412109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.501120300292969, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.424495849609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3124160766601562, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.180426712036133, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.032693557739258, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.8456001663208008, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.6630992126464843, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.503553214073181, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.2970965647697448, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.1275159311294556, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.9222717851400375, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.7604080522060395, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.6312257331609726, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.4985375702381134, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.3816473069787025, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.29247422598302364, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.23830188866704702, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.19482645373791457, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.16493958964943886, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.14116069350391627, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.12206515876576304, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.10637892913073302, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.09116194671019912, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.07971972689963877, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0706058836914599, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.05960823117755353, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.048286184389144185, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.039432257134467366, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03235257514752447, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.024266411662101747, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.018569821966812016, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.013579889079555868, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.010068541103973984, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.007908921483904123, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.007287307754158974, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.006829960178583861, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.01322861977852881, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.025297827534377575, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.04020460102707148, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.040735335992649196, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05461235214024782, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.07682543233036995, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.11235250337980687, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.13161071751266717, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1789776047691703, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.18446540795266628, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006540561439469457, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006539515305776149, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006659965242724866, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006837646027561277, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007007557803299278, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007184057477861643, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007276885169558227, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007261189483106136, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0071114699798636135, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006880066141020507, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0066537824389524755, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006379423681646585, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006177043842617422, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005917834434658289, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005654016598127782, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005381055844482035, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00503490810864605, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004666080102324486, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0043200142658315595, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00406200009630993, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003815862142946571, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00362156895105727, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003442446824046783, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003281004715827294, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0031366268987767397, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0029796841886127368, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0028487324161687866, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0027303917426615954, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0025629544240655376, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002354659040865954, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0021542553283507002, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0019677191504160873, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0017112121210084298, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0014768007848761045, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0012241310780518688, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0009995497859199532, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0008498885599692585, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0008525678174191853, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0009232403739588335, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0017472351999822421, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0029030134128333884, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00393411969042063, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004083912992791738, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0052135904978058535, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.006083223372738758, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.007050659202407133, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008592599779374623, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010527536463115439, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011072898741362316, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.653775453567505, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6076393127441406, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.529698133468628, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4479563236236572, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.362382411956787, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2380261421203613, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0940637588500977, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.9363226890563965, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.742187738418579, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.5581032037734985, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.4003381729125977, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.1989171504974365, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.0345828533172607, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.8373879194259644, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6837562918663025, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5626693964004517, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.4410227835178375, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.33796536922454834, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.2639158368110657, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.22093385457992554, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1865592747926712, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.162843257188797, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.14448682963848114, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.13040414452552795, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1196608915925026, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.11020722985267639, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10418783128261566, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.09993032366037369, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.09566539525985718, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0920054242014885, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.0895523950457573, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08844452351331711, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08801398426294327, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08776653558015823, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08787627518177032, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08811409771442413, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08766953647136688, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0909464880824089, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.0949888527393341, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11206106096506119, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13474446535110474, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2363722026348114, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.21604573726654053, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23796217143535614, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.25738176703453064, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.24923075735569, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4560743570327759, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.47895941138267517, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6880531907081604, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.18452380952380953, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1974206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22569444444444445, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.26066468253968256, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.29389880952380953, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3648313492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.451140873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5300099206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5952380952380952, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6316964285714286, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6676587301587301, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7264384920634921, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7782738095238095, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8407738095238095, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8720238095238095, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8955853174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9159226190476191, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9308035714285714, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9432043650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9471726190476191, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9533730158730159, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9608134920634921, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9642857142857143, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9652777777777778, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9561011904761905, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.026893495965660912, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0366814242304247, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05545136896403732, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07621371078344469, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.10126174701774701, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.16962053264586116, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.24740011055564304, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3131690522880808, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.36722912643780925, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.40460606902803214, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.45426770723829996, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.569435153431318, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6791523573668807, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.79874664319047, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8488599198402982, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8783378513148989, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9049925105379127, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9231334751448919, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.938696898783233, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9430767764417044, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9501912533854769, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9551620326165436, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9569596870985728, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9607151383456044, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9627836705013899, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9649429215894815, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9662809923847059, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9684741329869644, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9691038917800532, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9688497068678384, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9685375635621041, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9688188897897279, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9692027200547508, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9693293212499648, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9710086020064539, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9712091165165401, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9718354080131794, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9733159872111115, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9734817923589963, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9702670765003418, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9626313840680878, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.951282062027624, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9546558252342159, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9565772970434336, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.958607572423791, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9665454626083393, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.955459496003455, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9567982590943211, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9498991059417501, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.007287307754158974, "validation/loss_best": 0.0909464880824089, "validation/acc_best": 0.9756944444444444, "validation/f1_best": 0.9733159872111115} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.6015084153413772, "train/grad": 0.03488673367537558, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.629503173828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.579611511230469, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.493701171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.403261413574219, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3088642883300783, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.1731558990478517, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0187834167480467, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8534445571899414, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.6546504020690918, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.469883179664612, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.3128763055801391, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.1132371962070464, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9507243078947067, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.7575960081815719, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.6094583788514137, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.4955461302399635, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3846994371712208, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2946711551398039, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.23174403872340918, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.19432267505675554, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.16313697474077343, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.14035814248025416, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.12115735111758114, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.10486746120266616, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.09095475669950247, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.07702332217246294, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.06629025180824101, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.057625121418386695, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04735200485214591, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.036892641177400945, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02890056570060551, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.022797079188749195, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.016429120833054187, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.012089114412665367, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.008527321135625243, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0062687166035175325, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.004530146848410368, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0034836489427834748, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0029686685930937528, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.004526229649782181, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.009440311947837472, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.022180432537570596, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.016923210863023997, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.022505104346200823, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.04918144292198121, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06660126795060933, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09246934843249618, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.10755727916024625, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.1411411068495363, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006589124547317624, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006675734841264784, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006878853456582874, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007071386673487723, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0072132112178951505, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007307559174951166, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007287010177969932, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0071547995368018745, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006899163154885173, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00663057672791183, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00641756767174229, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0061775301396846775, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005977876475080848, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005671030646190047, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0053439067618455734, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005032157830428332, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004676243426511064, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004327598519157618, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00402629608521238, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003809071657015011, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003594015293056145, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003413998993928544, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0032440735213458537, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003080204848665744, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0029253655747743324, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0027516294666565955, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002603852496249601, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0024707009523990565, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002292085649096407, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0020623099186923353, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0018405547233123797, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016361231227347162, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0013713105542410631, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0011241952927230159, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0008682272164878669, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0006616034330363618, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.000504542165363091, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00040606339498481245, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00036775742219106176, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0007325026034595794, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0015213393437807099, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0025755200202729612, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0023939631565917806, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0028982931199175253, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004736248896197139, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005649234968514065, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.006984078688587942, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007527672806906196, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009063954383621073, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6052815914154053, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.551539659500122, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.458146095275879, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.359642267227173, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.257455587387085, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.1122710704803467, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.950024127960205, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.7794615030288696, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.5788382291793823, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3951284885406494, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.2405226230621338, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.045016884803772, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.8867548704147339, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.7006725072860718, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.5599117875099182, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.4534507989883423, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3524269461631775, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.27397677302360535, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.22087934613227844, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.18984216451644897, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1642259806394577, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.14598065614700317, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.131510391831398, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.12013053148984909, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1114179939031601, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10395286977291107, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09875618666410446, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.09530263394117355, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.09172392636537552, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08904003351926804, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08731333166360855, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08601205050945282, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08546243607997894, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08551647514104843, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08603542298078537, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08617352694272995, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0857064500451088, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08763737231492996, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09026353061199188, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10751575976610184, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11004749685525894, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1384236365556717, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1544155478477478, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.16460242867469788, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2767217755317688, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2899130582809448, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.44823768734931946, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.40520229935646057, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5367564558982849, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.19866071428571427, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21800595238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2584325396825397, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.29662698412698413, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.35267857142857145, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4439484126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5248015873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5835813492063492, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6309523809523809, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6721230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7113095238095238, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7705853174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8189484126984127, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8655753968253969, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8950892857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9117063492063492, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9263392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9424603174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9494047619047619, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.953125, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9595734126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9613095238095238, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.966765873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9675099206349206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.970734126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.972718253968254, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9729662698412699, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9714781746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9543650793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.037581457137606154, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05014690828155545, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.07456377875751635, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.10197603360913368, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1546776256456487, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.24040219215366435, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3090988585757743, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3563319887018603, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.40381288691360756, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4575565258898412, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5360650843191352, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6580264226990713, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7577962248210078, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8378142194968351, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8773567700351448, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9001275553309785, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9179687327330412, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9375955684875253, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9451813740242037, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9498901876143302, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9563169703388358, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9574344542649004, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9634502260315995, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9634092763944463, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9648394549960487, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9668010666539527, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9674197401107424, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.969255702902027, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.968611251804781, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.96826514919382, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.96898262969698, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9708398301606722, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9716367998595038, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9710302870730471, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9709336266265344, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9714959718955554, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9732557624099756, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9721576114711704, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9751406499981057, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9699944925346993, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9717447346590896, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9701336629200148, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9638353785624995, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9656235250855113, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9603686492089736, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9601286064001082, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9532749051791457, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9621510718887902, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.947668134470962, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.0029686685930937528, "validation/loss_best": 0.09026353061199188, "validation/acc_best": 0.9769345238095238, "validation/f1_best": 0.9751406499981057} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.551001208126545, "train/grad": 0.03168137139640748, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.5788150024414063, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.5204501342773438, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.4188632202148437, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.3119862365722654, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.202114715576172, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.0483078002929687, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.8796552658081054, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.7058895874023436, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.5045484924316406, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3216839361190795, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.1679926586151124, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.9735704404115677, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.816910443007946, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6346589808166027, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5000042270123959, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.40109784215688704, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.31078428745269776, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.24269611857831477, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.19643452890217306, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.16824508126825094, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.14360588846728206, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.1247620446421206, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.10813707252964377, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.09353033349849284, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.08055528341792524, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.06724460370838642, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.05688308699056506, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.04847914950922132, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0383637092076242, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.028216150999069215, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.020927797192707657, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.015735774692147972, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.010607573827728629, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.007480753790587187, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.005142960073426366, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.003904153574258089, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0031863029301166536, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0027980011980980636, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.002277085976675153, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0011478559859097004, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0024311743583530186, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0040189605765044685, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00869254901073873, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.008621145375072956, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.020000256141647698, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.034926016218960285, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0351880828756839, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.04527441905811429, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0722125379461795, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0067206333391368386, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006845997574273497, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007063712112139911, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007225993284955621, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00730924786766991, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007305541671812534, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007179147554561496, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006960863815620542, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00666010579559952, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0064008081099018455, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006209109546616674, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005972087546251714, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005741042080335319, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005374281529802829, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00502323406515643, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004721813715295866, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00440810558735393, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004114566805073991, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038633276207838208, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0036740068614017217, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0034842884476529432, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0033221006637904793, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003164515721146017, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0030073611956322566, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002853256959351711, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002671651421696879, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002508821340452414, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002355688485840801, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0021267902571707963, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0018348541627347004, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0015630543677252718, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0013208030893292744, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0010223415465588914, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0007956883589213249, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0005839218673645519, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00045531377429142595, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00038597192145971347, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0003458301446698897, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0002926801378998789, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00019905597740034863, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0005187556396322179, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0009438237385256798, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0015341317460161009, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0016801957585721539, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0029906968902793096, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004048808519276009, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003942130857682287, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005251163366236255, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006440718628550579, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.5611636638641357, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.4993948936462402, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.3912649154663086, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.277834415435791, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.1619656085968018, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.001282215118408, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.8274987936019897, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.6508972644805908, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.4493238925933838, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.268166422843933, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1168816089630127, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.9266785979270935, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.7750903367996216, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6003217101097107, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.47246912121772766, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.37966665625572205, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2968861758708954, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.23631983995437622, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.19562441110610962, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.1712881177663803, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.150664821267128, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.13581721484661102, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.12376880645751953, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.11440733075141907, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10711660981178284, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10101987421512604, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09697569161653519, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.09391476213932037, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.09100465476512909, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08887725323438644, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08815297484397888, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08809327334165573, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08853182941675186, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08917383849620819, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08996778726577759, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08969229459762573, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08924198895692825, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08974213153123856, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09012623131275177, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09552418440580368, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10920915752649307, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13513022661209106, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.12662659585475922, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.14909107983112335, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18925002217292786, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.27369269728660583, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.25993582606315613, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3295404314994812, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.35685083270072937, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.21254960317460317, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.23933531746031747, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.28273809523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.33903769841269843, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4117063492063492, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4972718253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5696924603174603, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6173115079365079, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6597222222222222, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7048611111111112, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7514880952380952, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8139880952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.855406746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8891369047619048, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9092261904761905, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9236111111111112, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9340277777777778, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9446924603174603, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9506448412698413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9543650793650794, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9588293650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.964781746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.972718253968254, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9729662698412699, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9650297619047619, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.04701984153623486, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.06371518753897243, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.09049383962279325, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.14213292641779537, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.21448503370179803, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.28639803979289047, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3470055849656481, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3909828045184797, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.44038329735697085, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5260453609061007, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.620483888912614, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7491781635170417, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8216430783641357, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8699621675702931, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8970322647957237, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9148102618847295, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9279532202573579, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9401202152057128, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9475783305815506, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9507346729924593, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9549403578432442, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9586977232944168, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9608683988656543, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9623016226313693, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9653789390898699, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9674474403709031, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.969032993933586, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9689847011402638, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9677162429482626, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9688281511727708, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.97030479395752, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9703011866698352, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9694119560298388, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9711332533771194, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9691659833852193, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9717336088550826, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9737175409536013, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9728472415553164, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9744292655094474, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9710073552494962, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9676522151621365, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9684732248503736, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9714557784818832, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9694489972463465, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9671635467543696, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9616316047997868, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9627499506337545, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.961734014286378, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9591639058145538, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.0031863029301166536, "validation/loss_best": 0.08924198895692825, "validation/acc_best": 0.9764384920634921, "validation/f1_best": 0.9737175409536013} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.5118805664777756, "train/grad": 0.02966628987342119, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.53222412109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.4656631469726564, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.349418029785156, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.2284678649902343, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.105927734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.93840576171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.760146598815918, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.5817702865600587, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.380209527015686, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.2001973485946655, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0502812457084656, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.8628205001354218, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.7143590235710144, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5455157345533371, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.42463660567998884, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.33898259438574313, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.26405861534178254, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.20912119202315807, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1710861572623253, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.14699178347364067, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.12527261214330793, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.10816212612204254, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09277458137832582, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.07917470451444387, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06701077384874225, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.05458366134203971, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0448900483828038, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03711011533625424, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.028098172061145305, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.01968137121759355, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.014161591799929738, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.01059104255400598, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.007271554078906775, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.005272708246484399, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0037256359215825795, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0027362359967082737, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0020545988343656065, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0016158673632889987, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0012059759348630906, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0007307225838303566, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.000893756989389658, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0011460010148584842, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.003422409286722541, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0056589746847748755, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.009935429925099016, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.012257205434143542, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.007773003997281194, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.023040509121492504, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0416129188798368, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006728225685656071, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006886096321977675, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007113407352007926, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007251410479657352, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007296326924115419, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007236688518896699, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007063902725931257, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006828353686723858, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006549917147494853, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006327397334389389, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006153938153292984, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005907339416444302, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00564690831117332, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005244135437533259, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004876704798080027, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004572507026605308, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00425202265731059, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003958485496696085, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0037152910232543944, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003534770489204675, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033538091043010354, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003192904741736129, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00303365959727671, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002871315639349632, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0027071875374531373, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00250571799260797, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002312684850767255, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0021254162056720816, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001858975829964038, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0015287569611973596, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0012475291451846714, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0010113567003281786, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0007419664988992736, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0005572727087201202, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00040621883355925094, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0002986889526437153, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00022747057413653239, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00018219974856947374, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00014332937771541766, "train/grad_039_lr1.2e+01_wd1.0e+00": 9.771396247742814e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00017168764519283287, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00029185994539602687, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0005969148971098548, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0010551877497300666, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0017427204774105576, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0022629955493334818, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0018449579139695515, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0033231798942660617, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0044348811553567204, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.5217504501342773, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.4525041580200195, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.331289052963257, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.205491542816162, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.0790374279022217, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.9075018167495728, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.7269536256790161, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.5482959747314453, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.3477600812911987, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.1694118976593018, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.021230936050415, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.8366289138793945, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6914393901824951, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5275145173072815, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.4114921987056732, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.33051443099975586, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.26149460673332214, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.21239832043647766, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1787673383951187, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.15823420882225037, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.14040178060531616, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1274717003107071, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11695047467947006, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10874905437231064, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10237114876508713, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09689625352621078, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09307226538658142, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.09052617102861404, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08787243068218231, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08617114275693893, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08522184938192368, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08466798812150955, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08453331142663956, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.085386723279953, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08649659901857376, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08713937550783157, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08745945245027542, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08881738781929016, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08904412388801575, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09415309876203537, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09946943819522858, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11785241961479187, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11023468524217606, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12671831250190735, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1692260056734085, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.15948888659477234, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19821760058403015, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.25771060585975647, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3010309040546417, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22941468253968253, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2594246031746032, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.31200396825396826, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.38492063492063494, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4585813492063492, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5419146825396826, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6014384920634921, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6376488095238095, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6889880952380952, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7380952380952381, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7857142857142857, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8447420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8727678571428571, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9035218253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9184027777777778, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9310515873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9484126984126984, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9565972222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9593253968253969, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9630456349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9729662698412699, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9704861111111112, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9677579365079365, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05774169878828147, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.07539535707010075, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.11607039222570727, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.1887442285021882, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.2536300667411571, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.32358923845594145, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3748827754699865, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.41389058884357766, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.49102184899461365, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5942285419807625, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6955776739833937, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8050442995809614, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8485998811838945, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8902163348949085, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9089218190327115, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9231949489016034, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9358360906551899, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.943865209671667, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9532816930436739, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9551367481015477, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9592617161775007, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9628399850781086, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9659448619693862, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9664520618364023, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9676243674673819, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9684486690669496, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9698112790244702, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9718389367803888, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9716785611793073, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9730737979404791, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9734026925404891, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9721319001272642, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9724527764079324, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9717696359817435, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.972082893077867, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9729819247454418, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.973562849524823, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9733571460789856, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9738952326249495, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9719911075742002, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9711377710709247, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9708272020961918, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9727442251365424, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9707923824572763, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9680429731755881, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9683085698382308, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9668524248871203, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9657417096475411, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9628289692295011, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.0012059759348630906, "validation/loss_best": 0.08904412388801575, "validation/acc_best": 0.9764384920634921, "validation/f1_best": 0.9738952326249495} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.48764722168445584, "train/grad": 0.028059862116351725, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.503867492675781, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.43082763671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.3031251525878904, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.1717261505126952, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.0408816528320313, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.8652478790283202, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.6827339267730712, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.503561601638794, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.3033050894737244, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.1250091415643693, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.9767235720157623, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7921212837100029, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6478728049993515, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.48723779499530795, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3755878473073244, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2994525033980608, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2355899965390563, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.18953953141346574, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.15678972866386176, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1355228809546679, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.115797333214432, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.09998433372937143, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0856519686151296, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.07285442520864308, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06153104918077588, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04975594357587397, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.040353113655000925, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0327692954055965, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.024114324506372214, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.01620061621069908, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.011122617125511169, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.007884628046303988, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.005263169156387448, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.004091777140274644, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00287389000877738, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0021387666929513216, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0016499475575983524, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0013275139965116978, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.001041603647172451, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0007057275623083114, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0005329220928251743, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00039207327179610727, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0006273516174405814, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0007723408658057451, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0017928049992769956, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0022144580353051424, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0025313354842364786, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.010760830035433173, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.011254524290561676, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0068393871979787945, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007001338677946478, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007202411973848939, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007292669604066759, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007281279088929295, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0071487245825119314, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006917623816989362, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006654394164215773, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00637939267558977, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006166733026038856, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00598943151300773, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005709731406532228, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005407916328404099, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004962743053911253, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004590870356187224, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004306910954182968, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004027083473047242, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0037781752820592374, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00356086999643594, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003395976054598577, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0032188184175174685, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003059559453977272, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002896154528716579, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0027263721957569943, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00255352878884878, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002341257590742316, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002141375857463572, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0019396536302519962, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001652893076534383, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0013124893074564171, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0010240133487968706, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.000778973623237107, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0005428234076680382, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00045049241518427155, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0003091546189898509, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00022322503369650803, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0001689029549197585, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00013698066904908047, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00010961998430502717, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.374028485377493e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 9.235321836968068e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 7.440319571742293e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00018564830530294784, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00029752952433454994, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00042258709449868095, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0007254015777651546, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0007218035630155839, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0017872332554484415, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0020499174777072683, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.4876251220703125, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.4116947650909424, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.279510974884033, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.143843173980713, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.009431838989258, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.830660104751587, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.6464910507202148, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.4673374891281128, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2684385776519775, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.092570424079895, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.9473959803581238, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.767936110496521, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6286060214042664, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.4745889902114868, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.36848708987236023, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.29700493812561035, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.23832790553569794, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1966225802898407, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16790233552455902, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14986878633499146, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1342262178659439, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12248475849628448, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11328143626451492, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10600254684686661, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10029194504022598, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09521213918924332, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09182457625865936, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08937014639377594, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08766570687294006, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08648709207773209, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08588864654302597, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08594366163015366, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.086055226624012, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08674750477075577, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08744987845420837, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08782532811164856, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08751193434000015, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08817548304796219, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08802483230829239, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09122183918952942, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09407420456409454, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11129909008741379, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09943900257349014, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.10086327791213989, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13921508193016052, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.142391636967659, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.16835787892341614, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.20986108481884003, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.22597575187683105, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2435515873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.27306547619047616, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.33779761904761907, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4226190476190476, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4930555555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5682043650793651, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6180555555555556, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6550099206349206, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.705109126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7594246031746031, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8058035714285714, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8549107142857143, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8824404761904762, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9074900793650794, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9233630952380952, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9345238095238095, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9459325396825397, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9508928571428571, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9563492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9603174603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9630456349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.96875, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9694940476190477, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9694940476190477, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0658585105482983, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.08294916489558714, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.14154968700524856, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.22472784732752418, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.28349623644955474, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.34590671171749604, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3909779360782992, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.43648858313334365, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5250531854024187, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6362713981049156, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.734993368925664, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8206757977098892, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8612409767156124, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8943834791025858, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.915311960530499, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9276399298749606, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9415842050991917, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9463771673827276, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9515182332254885, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9554377231748322, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9591028783211089, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9623152179462913, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.963623355055221, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9655342281470422, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9681070427917662, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9704151572634944, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9701599181653998, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9702061626986849, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9692731426891503, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9690024312189846, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9700810657695703, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9714172570106088, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9720935909426991, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.973350313868386, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9731799089286522, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9729109209178691, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9726446498819585, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9730152519646766, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9733965511589363, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.972822233476569, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9706028044835988, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9717386584140532, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9726759263605416, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9756560322757144, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.973157388825295, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9714597191281403, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9703734313316368, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9702110303714452, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9662476590100842, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.0007723408658057451, "validation/loss_best": 0.10086327791213989, "validation/acc_best": 0.9771825396825397, "validation/f1_best": 0.9756560322757144} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.4667418318986893, "train/grad": 0.027049779472872616, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.4681396484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.388707275390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.2509335327148436, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.1106922912597654, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.9729958724975587, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.7915456199645996, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.6064018630981445, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.4273559617996217, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.229047554731369, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.053753945827484, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.9091275605559349, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7311192262172699, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5942179068922997, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.44478429660201074, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3435241171717644, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.27611852169036866, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.22047214929014444, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.17974524941295386, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1500512308627367, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1301467188075185, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.11117716452106834, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.09552998140454293, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0810738083999604, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06806436378508807, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.056402979185804725, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.04449810853227973, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03510050815530121, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.027787438416853546, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.01970162620767951, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.012713108565658332, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.008617402501404286, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.006253450401127339, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.004270356148481369, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.003282549101859331, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0024227411299943924, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0018841958604753017, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0014863700326532125, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0012355551682412624, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0010044887382537127, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0007034540362656117, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00046014155261218546, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00035778669640421865, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0003344439715147018, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00025413215160369874, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0004949445277452469, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00038746164180338384, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00037565027363598344, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0028131953440606594, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0027822412084788084, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006853367981966585, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00701567447045818, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007194084278307855, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007245839720126241, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007195577921811492, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007019541133195162, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006763300481252372, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006498195980675518, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0062333338288590315, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006018331435043365, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005823636404238641, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0055094255530275405, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005184742454439402, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004737064704531804, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0043841038912069055, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0041155385586898775, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0038546072132885456, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0036289568617939947, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003430886114947498, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003278107199585065, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003110493067651987, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0029526053357403726, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0027866993163479493, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0026127190195256843, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0024275739985750986, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0021988968458026645, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001974103667889722, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001750956067990046, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0014315508637810126, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0010643439312116242, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00079030947847059, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.000597447710169945, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0004209851418272592, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00033636566553468583, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00024455878297885647, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00018611972398502986, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0001442732394389168, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00011985026225374895, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.840963488386479e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.548213828158623e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.10793532223397e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.9344712426536716e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.617591400868151e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 6.0088318948601225e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0001439115682484271, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00018261944193540103, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00011783697837728369, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005160910804863406, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006647284751348082, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.4590702056884766, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.3777849674224854, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.236722946166992, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.0935471057891846, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.953574538230896, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.7699856758117676, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.5840615034103394, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.405106544494629, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.2079079151153564, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.0342744588851929, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.8915391564369202, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7164913415908813, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.582392692565918, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.43619394302368164, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.33756327629089355, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2732369601726532, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2214658409357071, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18456555902957916, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.15890459716320038, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.1425158530473709, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.12808066606521606, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11730823665857315, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10866013914346695, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10180646181106567, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.09645776450634003, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09220978617668152, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08931791037321091, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08743546903133392, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08596567809581757, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08484402298927307, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08444628864526749, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0843992605805397, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08493457734584808, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08656538277864456, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08768768608570099, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08812640607357025, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08770135790109634, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08805900067090988, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08733224123716354, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08967304974794388, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09144458919763565, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10652396827936172, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09422056376934052, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09292237460613251, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13202156126499176, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12592241168022156, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.14516298472881317, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1728323996067047, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.182118758559227, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2562003968253968, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2854662698412698, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.3645833333333333, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4523809523809524, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5243055555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5880456349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6344246031746031, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.671875, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7247023809523809, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7790178571428571, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8256448412698413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8678075396825397, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8916170634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9136904761904762, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9280753968253969, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9486607142857143, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9543650793650794, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9603174603174603, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9625496031746031, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9660218253968254, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9692460317460317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.972718253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.972718253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9714781746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.07282885800878021, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0934020335048247, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.1683884445501954, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2499259643872076, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3111441643797838, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3619046220091399, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.40815386549032134, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4611948707526528, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5658002823159054, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6793658272858912, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7695519205846941, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8402274513317148, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8735678088516546, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9018236937574832, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9199400286470701, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9357198530714934, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9441357949932242, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9506834758773476, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9564711047594484, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9588937149381438, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9628029618028899, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9653678434517582, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9664262596021641, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9678922267194171, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9696038377847073, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9696482976955778, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.971570047030468, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9735375841293507, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.972783467919951, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.972231698811487, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.972237952770268, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9728615386073342, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9737699141371932, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9743684907018643, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9729746137307673, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9738813245629514, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9746977606881185, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9738257470116303, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9733836383173844, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9726562801462723, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9715261123372078, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9714450190199712, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9739896741773941, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9753968087269655, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9707970545416744, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.972101055664133, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9714045668328114, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9710446005187139, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9687205568367325, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.0014863700326532125, "validation/loss_best": 0.08770135790109634, "validation/acc_best": 0.9771825396825397, "validation/f1_best": 0.9746977606881185} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.450091116130352, "train/grad": 0.026723160399124025, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.44718505859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.36286865234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.217025146484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.069716567993164, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.92658504486084, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.7399902534484863, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.5521078777313233, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.3719018220901489, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.1736201405525208, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9991993379592895, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.8559008884429932, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6809391114115715, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5479885372519493, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.40516972824931147, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.31077606536448, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.25006671249866486, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20068851839751006, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1643656039983034, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1373923389054835, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11907687956467271, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.10144939943216741, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08689672661945223, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07342319973744452, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06129400903359056, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.05033959644846618, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.039019371680915356, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.030164443142712116, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.02340030997991562, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.016198069052770735, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.010359639087691903, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.007088377308100462, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.005192459691315889, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0035908323898911475, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0027698925603181126, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0020728556625545023, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0016348308511078358, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0013150446489453315, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0011045024637132883, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0009105488285422325, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006746813748031854, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0004611283261328936, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00037115161307156087, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0003562148567289114, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00026862974278628825, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00019216479733586312, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0002339545451104641, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00022934190928936005, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00036790703423321246, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0005215632542967797, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0069655269128270445, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0071227403823286295, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007272270061075687, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007287404178641737, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007200068675447255, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0069829295831732455, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00670269692549482, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006430967070627958, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006163426677230746, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005937174947466701, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0057234885357320305, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005383666628040374, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005046172575093806, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0046002945525106045, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004255101976450532, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004001631515566259, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003759177288739011, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003543510972522199, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003351289578713477, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0031993087497539817, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0030307990324217825, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00287021299242042, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002693676831841003, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0025057219591690227, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0023099372879369184, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0020668703620322047, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0018305464948934968, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0015939963424170854, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0012790124125604053, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0009277935737918596, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0006788769374543335, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0005140837841463509, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0003624213225702988, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00028339821627014315, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00021055496494227556, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00016468979732962906, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00012917031583128846, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010823916620211093, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.12357141260145e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.355484100116882e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.131466234819527e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.675544595305837e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.147812354811321e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.7943043532304725e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 4.85213609366042e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 7.163696247772578e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 6.852173849836163e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0001502301229288605, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00015994130750925705, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.436279296875, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.3507332801818848, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.203019618988037, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.0544254779815674, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.910439372062683, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.7238202095031738, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.5369571447372437, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.358577847480774, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1628237962722778, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.9910459518432617, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.8504519462585449, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6791017651557922, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5489853024482727, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.4089779555797577, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3164210021495819, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2575017213821411, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2108331024646759, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1772039830684662, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.15366066992282867, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13851608335971832, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.12524573504924774, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11543367803096771, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10737399011850357, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10126984864473343, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0965634360909462, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09225154668092728, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08943133801221848, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08754846453666687, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08605772256851196, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0850667729973793, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08454867452383041, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08466142416000366, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.085268534719944, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08674405515193939, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08800753206014633, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08870117366313934, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08827424794435501, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08879068493843079, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08788855373859406, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08926865458488464, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09019792824983597, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10378163307905197, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09162024408578873, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.08960527181625366, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12202966958284378, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11638353019952774, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.13127674162387848, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14008848369121552, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.14428211748600006, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2638888888888889, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.30084325396825395, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.38566468253968256, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.47445436507936506, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5424107142857143, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6011904761904762, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6423611111111112, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6850198412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7371031746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7966269841269841, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8382936507936508, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8735119047619048, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8973214285714286, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9188988095238095, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9305555555555556, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9437003968253969, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9508928571428571, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9548611111111112, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9618055555555556, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9642857142857143, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.96875, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.972718253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9739583333333334, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.07727206048577498, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.10715920988276569, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.19039118485891823, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2680961966325636, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.32506628194621034, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3744351896350381, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4199921433443997, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4821260055187938, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.592562471279098, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7166211702621146, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.7927954238282507, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8499688509181902, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8810018754892348, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.909140294465731, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9223627569061081, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9392905906537059, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9467347139277806, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9507308487377819, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9551582508832566, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.958147856722614, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9604100465578301, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9626574805040194, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.96359438987295, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9667007896772744, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9677261657649506, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9697378400113462, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9705672717872889, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9722510889246321, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9724890204387113, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9724385855040076, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9725382463030803, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9731709260910932, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9740695994013209, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9733988964179842, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9731035077682074, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9739681945186879, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9735378832602755, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9734687083813467, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9742675841019898, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9721208132672066, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9722763609095223, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9719356017262191, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9728649099917749, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9752742766078013, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9719377288689275, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9714546156271763, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.971315171044745, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.972748496612765, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9718430420044878, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.00026862974278628825, "validation/loss_best": 0.08960527181625366, "validation/acc_best": 0.9771825396825397, "validation/f1_best": 0.9752742766078013} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.44298833012580874, "train/grad": 0.02682159391231835, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.440262451171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.352877502441406, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.2022352600097657, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.0508103942871094, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.9045109176635742, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.715577449798584, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.5267356491088868, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.346625394821167, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.1488961327075957, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.975300760269165, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.8330622574687004, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6602956786751747, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5295736134052277, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.39009956911206245, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2986418510228395, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.24046987146139145, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.19349792335182428, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.15873178953304887, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1327780295535922, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11499308779835701, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0977739021461457, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08350533707998693, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07018825714476407, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05803982591256499, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04716652601957321, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03583946269936859, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.027085806149989365, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.020627333084121346, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.014036686103790998, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.009021549513563513, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.006267232382670045, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0046427702717483045, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0032829123083502054, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0025547506473958493, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0019394346699118615, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0015498296450823545, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0012602215167135, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0010800060164183377, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0009139489196240902, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.000697244880720973, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0005254060681909322, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00041834292002022264, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00038768540136516097, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.000316808894276619, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0002048293687403202, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.000244299815967679, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0002967575192451477, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0002723535429686308, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0003135404549539089, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0070234604529105125, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0071736351610161364, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007308233173098415, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007308466869872064, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007212602109648287, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006995192475151271, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0067280711513012645, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006481634117662906, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006242482997477055, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006031387557741254, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005817531358916312, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005463037556037307, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005106319786282256, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00464492074563168, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004289284183178097, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004024442160734907, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003766153990291059, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0035320996469818057, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0033274955971864984, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00316516897524707, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0029896677943179384, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0028253012767527255, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0026529343787115066, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002467593642359134, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00226779124874156, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002012292304134462, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001749061339360196, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0014972517061687541, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001158361846464686, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0008117052861052798, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005863934341323329, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0004440930882265093, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00031791758501640286, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0002496795433398802, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00018859088366298237, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0001491088549119013, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00012009341848170153, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00010274606167513411, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.714701629287446e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.10773308401258e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 6.281589557147527e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.797908777822158e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 6.312962608262751e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.9171430984861216e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 4.879514005097008e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.436129904841437e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.174387901613955e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.059717802552768e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00010335940274046607, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.4193150997161865, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.330583095550537, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.1780617237091064, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.0255374908447266, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.8789312839508057, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.6904293298721313, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.5029140710830688, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.3248969316482544, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1304223537445068, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.9599847793579102, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.8209024667739868, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6525422930717468, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5255985856056213, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.390298455953598, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3023458421230316, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.24719054996967316, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2033924162387848, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.17209190130233765, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1496623307466507, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13534216582775116, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.12242286652326584, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11298572272062302, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10551807284355164, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.09965438395738602, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.09546270221471786, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09170801937580109, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08918200433254242, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08762666583061218, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08654306828975677, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08588484674692154, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.085736945271492, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08613000810146332, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08679447323083878, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08844835311174393, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08961944282054901, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09014523029327393, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08946626633405685, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09002461284399033, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08887238055467606, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08955920487642288, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08936597406864166, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1020953431725502, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09010232985019684, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.08765264600515366, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11683152616024017, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10924437642097473, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12313640117645264, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.13349875807762146, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1328689455986023, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.27058531746031744, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.3115079365079365, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4025297619047619, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4851190476190476, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5528273809523809, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.609375, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6488095238095238, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6937003968253969, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7485119047619048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8055555555555556, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8454861111111112, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8792162698412699, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9020337301587301, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.919890873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9449404761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9508928571428571, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9561011904761905, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9719742063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.970734126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9744543650793651, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.08093324236743878, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11555663603960939, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.20687445489983547, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2769077321607069, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3333268835982057, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.38343959647958714, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4287039780256327, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5006188764396635, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6157954104529286, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7355406737862971, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.806357554818992, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.857762402417252, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.888098479103357, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9107161425661684, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9268751796614308, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9406459351785644, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9460793592941938, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9522609570623892, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9565052731184351, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9601301277955915, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9634612593475812, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9641861208508028, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9680085866845447, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9673905593454528, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9679228990198332, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9706627318077407, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9706706844030095, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9717261490806922, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9717333198230586, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.97103738420176, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9713090437368935, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9721741001516638, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.973036491894471, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.974250234571549, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9736089971809673, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9733312251563844, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9733875880138314, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9731358490305091, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9728754314928908, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9714221145138411, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9723601098776561, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9718392459313966, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9737378192152142, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9746194511807776, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9731357314862, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9716341475715973, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9713781502170004, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9728881924015572, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9724426341534866, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.000316808894276619, "validation/loss_best": 0.08765264600515366, "validation/acc_best": 0.9769345238095238, "validation/f1_best": 0.9746194511807776} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.43172369092702867, "train/grad": 0.026819560620933772, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.4134912109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.3230105590820314, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.167827911376953, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.013344421386719, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.8653417205810547, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.6757222175598145, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4874799203872682, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.3086547875404357, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.1127201235294342, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9408336186408996, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.8004293245077133, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6305023066699504, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.503089502453804, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.36872939363121987, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.28250684663653375, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.22835186555981635, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.18452414959669114, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1517093100771308, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.12687643516808747, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10972781851887703, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0930804758798331, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07918333379551769, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0662523651495576, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05449379170313477, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04397622987627983, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03327607568353415, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.025164933307096363, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.019014435885474086, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.012707855990156532, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007999470001086592, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005495055252686143, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0040875849965959785, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0028923097252845763, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.00225206196308136, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.001731271930038929, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0013911201152950526, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0011434863321483136, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009840634185820818, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0008352687489241362, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00064293647184968, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0004851486999541521, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0003969351854175329, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0003659487422555685, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00029606048949062827, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0002359407488256693, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0002588538639247417, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0003143700957298279, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0002746249549090862, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.00035588285885751247, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00711115264100954, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007253639181144535, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007364464192651212, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007334074312821031, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0072102083079516885, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006965810391120613, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006687779491767287, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006443948484957218, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006211717298720032, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006002727383747697, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005788119323551655, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0054320996091701094, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0050793355843052265, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004623063678154722, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004279179839650169, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004028464255388826, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0037855587422382085, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0035613022290635855, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0033584981790045275, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0031944448745343836, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003012959678308107, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.002841261680587195, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0026574286492541434, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002459609063807875, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002243143200466875, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0019640451413579286, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001691985551151447, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0014365516960970126, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001094912060070783, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0007549708525766618, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005388957467948785, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0004069926681404468, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002910080079891486, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00022688557066430804, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00017298470025707503, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0001371404458586767, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00011143639005240403, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.546845602017129e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.086355692284996e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.744432730556582e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.784920169389807e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.448283207442728e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.798588840207231e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.545209154206532e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 5.10318845601887e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.55985178696028e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.600544864544645e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.120065825664824e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 9.610410740833686e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.4074907302856445, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.316530466079712, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.160792112350464, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.005772352218628, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.8574413061141968, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.6677955389022827, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.480121374130249, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.302558422088623, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1086081266403198, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.9392016530036926, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.8012495040893555, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6349716782569885, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5102670192718506, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3779968321323395, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.2930450141429901, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2403506487607956, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.19881339371204376, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.168649822473526, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1469602733850479, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13299745321273804, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.12070783972740173, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1115213930606842, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10408417135477066, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.09832751005887985, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.09411518275737762, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09036726504564285, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08822502195835114, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08700829744338989, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08628742396831512, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08588266372680664, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08565744757652283, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08590732514858246, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08665229380130768, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0884522944688797, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08959780633449554, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08998331427574158, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08916591852903366, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08956393599510193, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08850590139627457, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08873526006937027, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08889120817184448, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10055555403232574, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.08881394565105438, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.08574532717466354, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11370573937892914, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10592354834079742, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1188749447464943, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1267002820968628, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1253165453672409, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2750496031746032, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.31845238095238093, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.41096230158730157, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.49603174603174605, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5595238095238095, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6155753968253969, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.654265873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6976686507936508, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7544642857142857, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8100198412698413, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8497023809523809, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8819444444444444, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9047619047619048, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9340277777777778, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9451884920634921, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9503968253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9563492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9608134920634921, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.972718253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9742063492063492, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.08448218155938568, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.12099585403580743, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.21377836532573596, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2860690348084367, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3383380648325832, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3900687127001981, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.43512343173203505, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5110867885912002, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.627592242339081, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7430937426987482, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8121561300090645, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8612138491460376, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8919149556553455, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9123814244997089, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9278628700324877, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9411085918329628, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9468154562188043, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9522682183711472, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.957135563058961, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9604220273130892, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.963891495218902, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9641656454566478, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9659830826402692, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.968818818997204, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9696570161137605, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9715217071635597, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9727608540985931, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9727137760793544, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9715747014237202, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9708948055150202, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9725793094175489, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.973215967601532, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9741104027590678, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9744841909607622, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9735371120040879, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9737432532644597, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9741740261075756, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.973926533731853, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9747740399511791, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9724622576789737, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.973718339438678, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.972143060375812, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9743137094665951, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.975474184318534, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9734940832246243, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9717323136655451, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9720415995825414, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.972830699089443, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9721519633037746, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.00029606048949062827, "validation/loss_best": 0.08574532717466354, "validation/acc_best": 0.9776785714285714, "validation/f1_best": 0.975474184318534} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.4258347189426422, "train/grad": 0.026445142971351743, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.3999383544921873, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.3079302978515623, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.150502395629883, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.994336395263672, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.8453562355041504, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.6553248500823974, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4673805189132691, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.28916335105896, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0939547896385193, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9229985469579697, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7834831753373146, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6155865775048732, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.49050062328577043, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3592018856853247, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.27510807409882543, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.22244400814175605, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.1797422518208623, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.14747733172029256, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1230185827985406, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10612857392989099, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.08971972149796784, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07605116466991603, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06340643980540335, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05199257140979171, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04174297137185931, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.031049598660320043, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.022987665701657535, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01716263667680323, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.011472267964854836, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007264963882043958, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005062746312469244, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0037848798744380473, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002704948140308261, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002124191485345364, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0016402212809771299, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00132099830545485, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0010893525928258895, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.000946071008220315, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.000815822770819068, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006399802304804325, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0005076656211167574, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0004196480941027403, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0003946935478597879, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0003211279399693012, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0002519796881824732, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00029756005853414535, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00037869318388402464, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00033436381258070467, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.00043986556120216845, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007050873474217951, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007196216904558242, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007305997109506279, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007274788608774543, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007151481374166906, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006908909622579813, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006635599422734231, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006394296693615615, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0061587072862312195, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0059393950900994245, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005712883563246578, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005344855304574594, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0049866649415344, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004532006818335503, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0041846771794371304, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003930855696089566, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0036875388072803617, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0034654081007465722, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0032637273077853026, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0031006750755477696, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0029190596344415096, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.002746984651312232, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025577899027848616, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002356680562370457, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0021388894485426134, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018596307982807047, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015874461767089087, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0013328376013669186, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00099788750805601, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006838152075943071, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0004919706245709676, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00037189788763498656, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00026645935475244186, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00020968731543689502, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00016084189895991584, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00012866935487181763, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00010487219360584276, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.981605063127063e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.762540523799544e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.441510699914944e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.7564506269045525e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.505978164364933e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.857261264281988e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.485867251763921e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 5.2626238095854204e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.754035686071803e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 8.032554882902331e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.919730982711372e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00010936334972711847, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.400118827819824, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.307861804962158, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.150139570236206, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.9934924840927124, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.8440779447555542, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.653809905052185, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.466090202331543, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2886873483657837, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.0952366590499878, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.926514208316803, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.7893378734588623, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6242547035217285, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5009480118751526, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3706856966018677, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.287496417760849, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2362823784351349, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.19574978947639465, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1665278971195221, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.14538270235061646, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13185830414295197, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.11973240971565247, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11091592907905579, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10367952287197113, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.09809789061546326, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.09417743980884552, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09054127335548401, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08852099627256393, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08729389309883118, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08669111132621765, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08614271134138107, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08585920184850693, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08615833520889282, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08676157891750336, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08855301141738892, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08980497717857361, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09016992896795273, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08951817452907562, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08991646021604538, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08857837319374084, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0885620266199112, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08839482814073563, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09945332258939743, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.08777563273906708, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.08475423604249954, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11149586737155914, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10400065779685974, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11558923870325089, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12354782968759537, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12066008895635605, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2775297619047619, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.3226686507936508, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4191468253968254, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5004960317460317, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.564484126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6185515873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6572420634920635, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7016369047619048, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7599206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8132440476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8511904761904762, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8824404761904762, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9052579365079365, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9233630952380952, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9370039682539683, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9451884920634921, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9518849206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.957093253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9635416666666666, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9680059523809523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9732142857142857, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.08570102586578823, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.125659191859851, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.2207705842554578, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2894706026533071, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3427529230717456, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3929551603958288, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.43823465035356013, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5185187077374485, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6396902348979595, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7488715304966321, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8152177690697662, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8626229419963477, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8922065526783886, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9145580447634695, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9317340909301303, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9407287788187271, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9484250198896201, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9531755601958888, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9582954639523674, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.959505487883869, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9637383693642286, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9645418467573963, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.966426750783229, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9672696455724025, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9688234897936361, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9701171557740421, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9712177253163914, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9724117663517022, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9712596475842046, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9721769104905303, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9719968222005959, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9726773627026342, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9739778141188931, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9744855616689705, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9729387759288506, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9735555007722597, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9746237965275009, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9735138440754075, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.974309011575887, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9727754977548211, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.97336295427461, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9718072024378515, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9730192382160119, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9754203597676213, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9738753289402637, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.971883956489277, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9719137841963963, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9720135154062964, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9712638094373267, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.0003211279399693012, "validation/loss_best": 0.08475423604249954, "validation/acc_best": 0.9776785714285714, "validation/f1_best": 0.9754203597676213} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.42641334861516955, "train/grad": 0.026578802056610583, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.3997061157226565, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.3063710021972654, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.1469256591796877, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.9891216659545898, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.8386907768249512, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.6475000858306885, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4589032649993896, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2807222831249236, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0862370055913926, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9165331089496612, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7786840891838074, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6135731643438339, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.4909521833062172, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.362382822483778, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.28026509821414947, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2290328685566783, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.18747776817530393, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.15591736800968647, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13163825636729598, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11463437173515559, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09783550659194588, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0836609789263457, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07035033515654504, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.058078054459765556, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04681722493842244, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.034611591435968876, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.025331487357616426, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01864971198141575, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.012184062320739032, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007499276651069522, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005138008017092943, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0038182085659354925, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0027222619764506817, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0021459492389112713, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0016529261786490679, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0013343572802841663, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0011003792099654674, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009481660183519125, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0008093877509236336, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006565176416188478, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.000506510166451335, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.000429218877106905, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00041431699879467486, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00034758989699184894, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00026945091784000394, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0003167780861258507, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0004303254745900631, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0003991431929171085, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0005278085172176361, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007115955092012882, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007251113383099437, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007345586365554482, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007302959682419896, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007170984135009348, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006925216843374073, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0066551831783726815, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006420896223280579, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00619193225633353, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005970406364649534, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005734525579027832, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005349191621644422, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004980677247513086, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00452350331004709, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0041898220288567245, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0039474589203018695, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0037148942542262376, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003503375493455678, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003307763242628425, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0031462273345096037, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0029617100645555183, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0027818564081098884, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002587009352282621, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00237946664536139, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002152568874589633, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018644571700133384, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001573737869184697, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0013048416865058244, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0009683861484518274, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006593192896252731, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0004720369742426556, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00035809105160296897, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000257810245238943, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00020436754446564008, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00015651165489543928, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00012531611613667338, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00010149347792321351, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.715286707229097e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.497806063838652e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.382248414411152e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.6445000955136495e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.3834618547625724e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.677838296378468e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.463087358748453e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 5.161005918580486e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.4490120262235e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 8.446995421536485e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.912942113511236e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00011290106463548, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.3962762355804443, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.303342819213867, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.1445505619049072, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.9871418476104736, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.8372489213943481, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.646573543548584, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.4587011337280273, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2813706398010254, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.0883111953735352, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.9199215173721313, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.7830548882484436, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6187025308609009, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.4961263835430145, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.36686936020851135, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.2845744788646698, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.23419524729251862, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.19419831037521362, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.16539518535137177, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.14463552832603455, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13104978203773499, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.11908142268657684, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1103539913892746, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.1032562106847763, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0978178009390831, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0938730537891388, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0903276652097702, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08812177926301956, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.0868956595659256, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08609417080879211, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08542026579380035, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08536349982023239, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08554303646087646, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08613806962966919, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08811535686254501, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08932186663150787, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08967314660549164, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08921988308429718, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08965656906366348, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08856578171253204, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08862557262182236, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08823901414871216, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09909620136022568, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.08738640695810318, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.08417737483978271, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11037691682577133, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1021089106798172, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11368754506111145, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12148763239383698, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11896217614412308, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.27901785714285715, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.3256448412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4226190476190476, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.503968253968254, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5654761904761905, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6205357142857143, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6577380952380952, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7038690476190477, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7626488095238095, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8154761904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8521825396825397, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8836805555555556, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9060019841269841, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9246031746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9375, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9516369047619048, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9575892857142857, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9680059523809523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9732142857142857, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.08640990345355161, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.12915253807619198, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.2232966353066676, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2932251038344611, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3437107742369187, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.395023661240992, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.43913976894236406, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5228720617220595, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6446468212771987, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7523994109857567, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.81677683127063, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8639427714406762, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8933166302099392, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9157164131429557, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9323431900511007, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9414212654149055, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9482445916331398, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9537310588042076, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9578022757135853, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9618235829469164, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9637413158041994, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9649490995914615, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9667079118836964, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9675469382722823, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9693228235100119, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9705251293787229, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9719633093836234, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9724884625832431, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9722855986198915, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9723849422381322, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9723147125002107, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9728573731903022, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9738983766233276, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9741276898331639, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9729494273869896, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9736036350857095, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9743472946882454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9734633533793354, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.974139015202106, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9729973051512301, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.973718339438678, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9718551654155361, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9735969350279509, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9748701211457332, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9741338691037951, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9713550597739394, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9720388152002128, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9725424032504034, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9713259758824107, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.00034758989699184894, "validation/loss_best": 0.08417737483978271, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.9748701211457332} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.42348485469818115, "train/grad": 0.026392000010237098, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.3911288452148436, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.2978163146972657, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.1386917877197265, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.9811512756347656, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.8316584968566894, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.6416028499603272, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4540459156036376, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2767030930519103, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0827419710159303, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9130669552087783, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7748338407278061, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6090050488710403, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.4856929337978363, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.35673283018171786, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2746137936413288, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.22356450941413641, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.1822356715798378, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.15080235490575433, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.12657126873731614, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10964560993015766, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09303709120489657, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07894130818545818, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06576347630470991, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05371123522520065, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04287952398881316, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.031787244258448484, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.023440823461860417, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.017348691821098328, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.011391185857355594, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007133921133354306, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004920132393017411, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003671938581392169, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0026209175866097213, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0020427107624709606, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0015752007253468036, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0012724401894956827, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0010553443245589734, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009159918874502182, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0007848401088267565, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006260782852768897, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0004986328538507223, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0004169617313891649, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00040822370909154415, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00034574286080896855, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00027377429418265817, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00030287470668554305, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0003958554659038782, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0003687022719532251, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0005220352113246918, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007121386649087072, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007255822755396366, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0073439373611472545, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007291674092411995, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007150588419754058, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006893808748573065, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006614421629346907, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006374510296154767, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006140981488861144, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005916698921937496, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005678130134474486, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0052868711133487525, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0049127814348321405, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004455090760020539, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004122914201579988, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038844831509049983, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0036567122989799826, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003448893472086638, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003256103008170612, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0030988486006390302, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002924137630034238, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0027479984040837736, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025571785314241423, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002348429746925831, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002121324833424296, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018343288416508585, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015464696307026316, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0012836216362484265, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0009496026831038762, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006395729731593746, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00045640908123459665, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0003465857875562506, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002500419032003265, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00019582197230192834, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00014988520753831836, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00012053120017299079, "train/grad_036_lr7.1e+00_wd1.0e+00": 9.851136352153844e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.514797489624471e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.34677784203086e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.172519325446046e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.5061411276255965e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.309471842792845e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.6268222760991196e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.5259069106341486e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 5.394909058622943e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.513653804631758e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 8.197842487788875e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.837573906703256e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00010902871396410774, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.3948476314544678, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.3016316890716553, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.14247989654541, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.9847346544265747, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.8346585035324097, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.6438695192337036, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.4561183452606201, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2788405418395996, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.0856692790985107, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.917367160320282, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.7807309627532959, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6167624592781067, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.4942956566810608, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.36552828550338745, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.28349658846855164, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2333824187517166, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.19366295635700226, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1649957299232483, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.14440558850765228, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13091206550598145, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1190510094165802, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11032132059335709, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10320709645748138, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.09774984419345856, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.09374623745679855, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09039008617401123, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08830166608095169, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08710476756095886, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08649235963821411, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08590521663427353, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08573928475379944, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08591539412736893, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08658979833126068, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08840718865394592, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08956707268953323, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0900382474064827, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08953928202390671, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08997118473052979, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08861459046602249, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08860552310943604, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08843498677015305, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09909570217132568, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.0872078686952591, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.08414946496486664, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11015418916940689, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10217567533254623, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1134488508105278, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12074321508407593, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11798440665006638, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.28000992063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.326140873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.42336309523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5059523809523809, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5662202380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.621031746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6567460317460317, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7041170634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7643849206349206, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8154761904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8524305555555556, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8849206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.90625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9243551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9382440476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9516369047619048, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9655257936507936, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9680059523809523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9694940476190477, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9734623015873016, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0881335098009692, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.12937354111675306, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.22448611231060284, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.29491971534840156, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.34384886496888106, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.39515939177710296, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.4380056482881258, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5230463071540526, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6482345999018104, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.753567630409089, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8163973202664578, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8652585836873657, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8934976342694395, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9153502341375541, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9332227968632839, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9414122107891342, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9482445916331398, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9540370462926179, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9578017209553297, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.962095594957073, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9635735097245354, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9644388710042474, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.966528135347672, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9668153665453357, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9691417273669993, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9705846271681257, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9726571938137761, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9725194613268829, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9717701395201576, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9723401823779451, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9722710933681104, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9727766269707995, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9735805423376327, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9740584169031737, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9731235593985681, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9738242376873887, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9743472946882454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9732826552188786, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.974139015202106, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.972823812347537, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.973533764625513, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9716267381630733, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9735969350279509, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9748701211457332, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9743330296845882, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.971883956489277, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9715387133359127, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9724929116796307, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9715479040612285, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.00034574286080896855, "validation/loss_best": 0.08414946496486664, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.9748701211457332} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.4236360743641853, "train/grad": 0.026323021650314332, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.3990234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.3056739807128905, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.1462567138671873, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.9882944869995116, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.8381165504455566, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.6471076011657715, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.458585786819458, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.2802704417705535, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.0853084206581116, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.9150140312314033, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.7764337420463562, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6099565160274506, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.48572113037109377, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3551193209737539, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.27187640361487864, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.22022533193230628, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.1784835295006633, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.14674342930316925, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.12240614013746381, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10528026323765516, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0887190689239651, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07474433375522495, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.061869634790346024, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05020922372117639, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03983700450509787, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.029327877284958958, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.021585607016459108, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01602405747398734, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.010702198771759867, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00684908646158874, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004788657799363136, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003589919898658991, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0025705011188983918, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002000569188967347, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0015542644821107388, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.001261243661865592, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0010421889182180167, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009054518956691026, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0007728253211826086, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006152229011058808, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00048105210065841676, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00039850289933383463, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00038073811680078507, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0003214357979595661, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.000245449710637331, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00028827041387557983, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00037023307755589484, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0003638758324086666, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0004522804077714682, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00709038937697187, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007225588071160019, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007316187536343932, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007266165036708116, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007127939821220935, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006875733144115656, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0066022426029667255, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006366193841677159, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006131548753473908, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005903248840477318, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005661250937264412, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005271727030631155, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004905845534522086, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004464431895175949, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004146681285928935, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003917529933387414, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003688977586571127, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0034722516569308938, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003270043703960255, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0031030712224310265, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0029156072565820067, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00272962216346059, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0025307883811183274, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002317023403593339, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0020919246636913157, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018010681495070457, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015119398449314758, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0012482090726552997, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0009211295207205694, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006223508568655233, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00044496269307273904, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00033823918318375945, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00024358152437343962, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00019089893299678806, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00014668866659121705, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011799973321103607, "train/grad_036_lr7.1e+00_wd1.0e+00": 9.62356604031811e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.309938655656879e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.160486108659825e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 6.061828424208216e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 5.385275429034664e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 5.1080553253086694e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 5.4049944092184885e-05, "train/grad_043_lr2.2e+01_wd1.0e+00": 5.372460981789118e-05, "train/grad_044_lr2.6e+01_wd1.0e+00": 4.9643489610389225e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 6.454779856767346e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 7.742029232076674e-05, "train/grad_047_lr4.3e+01_wd1.0e+00": 8.868318272334364e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00010529439272431773, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.394663095474243, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.301412343978882, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.142195463180542, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.9844098091125488, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.834266185760498, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.6434524059295654, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.4556879997253418, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.2784147262573242, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.0853360891342163, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.9169881343841553, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.7804346084594727, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.6164296865463257, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.4939820170402527, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3653721511363983, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.28332361578941345, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.23327678442001343, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.19361476600170135, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.16497886180877686, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.14429397881031036, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.13083991408348083, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.11905033886432648, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.110252745449543, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.10320533812046051, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.09774897992610931, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.09374875575304031, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09030217677354813, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0882621705532074, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.0870373398065567, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0863809809088707, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.08589767664670944, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08573365956544876, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.08597587049007416, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08666276186704636, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08840704709291458, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.08955942094326019, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09006931632757187, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08951728045940399, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08990992605686188, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.0885741114616394, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08870444446802139, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08830469846725464, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09895671904087067, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.08722317218780518, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.0840374305844307, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11007487773895264, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1020318865776062, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11368416249752045, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12041907757520676, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11786336451768875, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.28000992063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.326140873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.4236111111111111, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5062003968253969, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.5662202380952381, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6202876984126984, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6567460317460317, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7038690476190477, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7643849206349206, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.8159722222222222, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8521825396825397, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8854166666666666, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.90625, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9243551587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9382440476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9516369047619048, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9655257936507936, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9682539682539683, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9737103174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0881335098009692, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.12937354111675306, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.22453365487483273, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2951679782638857, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3438556174503414, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.394381430051373, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.43797718052005846, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5227613487138423, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6478470992282683, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7540701460441562, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.8161680118338699, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8656632443197758, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8934976342694395, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9153502341375541, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9332227968632839, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9414122107891342, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9481074059824574, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9540370462926179, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9578017209553297, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.962095594957073, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.963843418182712, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9645418467573963, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.966528135347672, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9675453574875222, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9689652738882375, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9705846271681257, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9726571938137761, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9725194613268829, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9717701395201576, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9723401823779451, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9721693258719543, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9727766269707995, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9741121818038971, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9738781673828595, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.973132835836416, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9738242376873887, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9743472946882454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9732826552188786, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.974139015202106, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.972823812347537, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.973533764625513, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9716267381630733, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9739736823243497, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9748701211457332, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9743330296845882, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.971883956489277, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9719137841963963, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9724929116796307, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9717074490337309, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.0003214357979595661, "validation/loss_best": 0.0840374305844307, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.9748701211457332} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/config.yaml b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0b74d988a5facd049c1eef26a0e9c0f94fefa757 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (hcpya_task21 patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..d2c3a89556ca1129b5fbaa2ecac1a517c3a62ab3 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 15, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 0.131548672914505, "eval/train/acc": 0.9787883572819622, "eval/train/acc_std": 0.001043201880715264, "eval/train/f1": 0.9781624932554975, "eval/train/f1_std": 0.0011665892820083461, "eval/validation/loss": 0.1726643443107605, "eval/validation/acc": 0.9645337301587301, "eval/validation/acc_std": 0.002903570032062416, "eval/validation/f1": 0.9601560884172378, "eval/validation/f1_std": 0.003640016998256415, "eval/test/loss": 0.1901678740978241, "eval/test/acc": 0.9557539682539683, "eval/test/acc_std": 0.00282098661508512, "eval/test/f1": 0.9485875215089431, "eval/test/f1_std": 0.003601265638232877} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log_best.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..e48b9a606e85056dcbc63eebd4187b8a3737226e --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 15, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.131548672914505, "eval/best/train/acc": 0.9787883572819622, "eval/best/train/acc_std": 0.001043201880715264, "eval/best/train/f1": 0.9781624932554975, "eval/best/train/f1_std": 0.0011665892820083461, "eval/best/validation/loss": 0.1726643443107605, "eval/best/validation/acc": 0.9645337301587301, "eval/best/validation/acc_std": 0.002903570032062416, "eval/best/validation/f1": 0.9601560884172378, "eval/best/validation/f1_std": 0.003640016998256415, "eval/best/test/loss": 0.1901678740978241, "eval/best/test/acc": 0.9557539682539683, "eval/best/test/acc_std": 0.00282098661508512, "eval/best/test/f1": 0.9485875215089431, "eval/best/test/f1_std": 0.003601265638232877} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log_last.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..2b141221a0da10208bfec7378dc92c97f26748bc --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 48, "eval/last/lr_best": 0.015, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.12836523354053497, "eval/last/train/acc": 0.9798936786146639, "eval/last/train/acc_std": 0.0009872378649127811, "eval/last/train/f1": 0.9795441070802993, "eval/last/train/f1_std": 0.0010826644288459769, "eval/last/validation/loss": 0.17021863162517548, "eval/last/validation/acc": 0.9625496031746031, "eval/last/validation/acc_std": 0.0029504883913695377, "eval/last/validation/f1": 0.9586458448009709, "eval/last/validation/f1_std": 0.00364657497974593, "eval/last/test/loss": 0.18734048306941986, "eval/last/test/acc": 0.9561507936507937, "eval/last/test/acc_std": 0.002840989915934945, "eval/last/test/f1": 0.9490338335319878, "eval/last/test/f1_std": 0.0036329073385516267} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..f457366a1e80f73d8a090fedf7c2c7aeb032124b --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,best,15,0.015,0.05,48,"[50, 1.0]",train,0.131548672914505,0.9787883572819622,0.001043201880715264,0.9781624932554975,0.0011665892820083461 +flat_mae,patch,linear,hcpya_task21,best,15,0.015,0.05,48,"[50, 1.0]",validation,0.1726643443107605,0.9645337301587301,0.002903570032062416,0.9601560884172378,0.003640016998256415 +flat_mae,patch,linear,hcpya_task21,best,15,0.015,0.05,48,"[50, 1.0]",test,0.1901678740978241,0.9557539682539683,0.00282098661508512,0.9485875215089431,0.003601265638232877 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..f457366a1e80f73d8a090fedf7c2c7aeb032124b --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,best,15,0.015,0.05,48,"[50, 1.0]",train,0.131548672914505,0.9787883572819622,0.001043201880715264,0.9781624932554975,0.0011665892820083461 +flat_mae,patch,linear,hcpya_task21,best,15,0.015,0.05,48,"[50, 1.0]",validation,0.1726643443107605,0.9645337301587301,0.002903570032062416,0.9601560884172378,0.003640016998256415 +flat_mae,patch,linear,hcpya_task21,best,15,0.015,0.05,48,"[50, 1.0]",test,0.1901678740978241,0.9557539682539683,0.00282098661508512,0.9485875215089431,0.003601265638232877 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..54dbefa31869c99114ba819f5f09ad4c58cb5867 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",train,0.12836523354053497,0.9798936786146639,0.0009872378649127811,0.9795441070802993,0.0010826644288459769 +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",validation,0.17021863162517548,0.9625496031746031,0.0029504883913695377,0.9586458448009709,0.00364657497974593 +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",test,0.18734048306941986,0.9561507936507937,0.002840989915934945,0.9490338335319878,0.0036329073385516267 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/log.txt b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..82a32c066fb0387fe6d7719bf10d7482878ab7db --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/log.txt @@ -0,0 +1,890 @@ +fMRI foundation model probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 23:03:42 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (hcpya_task21 patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 0.8M (0.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:29:15 lr: nan time: 4.3887 data: 4.0022 max mem: 3910 +train: [0] [ 20/400] eta: 0:03:16 lr: 0.000003 loss: 3.0455 (3.0467) grad: 0.0501 (0.0515) time: 0.3223 data: 0.0055 max mem: 3951 +train: [0] [ 40/400] eta: 0:02:35 lr: 0.000006 loss: 3.0429 (3.0437) grad: 0.0495 (0.0505) time: 0.3460 data: 0.0258 max mem: 3951 +train: [0] [ 60/400] eta: 0:02:14 lr: 0.000009 loss: 3.0393 (3.0417) grad: 0.0500 (0.0507) time: 0.3151 data: 0.0028 max mem: 3951 +train: [0] [ 80/400] eta: 0:02:00 lr: 0.000012 loss: 3.0332 (3.0385) grad: 0.0509 (0.0505) time: 0.3217 data: 0.0025 max mem: 3951 +train: [0] [100/400] eta: 0:01:49 lr: 0.000015 loss: 3.0241 (3.0346) grad: 0.0481 (0.0498) time: 0.3211 data: 0.0029 max mem: 3951 +train: [0] [120/400] eta: 0:01:40 lr: 0.000018 loss: 3.0129 (3.0305) grad: 0.0489 (0.0497) time: 0.3160 data: 0.0031 max mem: 3951 +train: [0] [140/400] eta: 0:01:30 lr: 0.000021 loss: 2.9982 (3.0250) grad: 0.0492 (0.0496) time: 0.2983 data: 0.0032 max mem: 3951 +train: [0] [160/400] eta: 0:01:22 lr: 0.000024 loss: 2.9896 (3.0202) grad: 0.0460 (0.0489) time: 0.2979 data: 0.0030 max mem: 3951 +train: [0] [180/400] eta: 0:01:14 lr: 0.000027 loss: 2.9725 (3.0142) grad: 0.0446 (0.0488) time: 0.3010 data: 0.0032 max mem: 3951 +train: [0] [200/400] eta: 0:01:06 lr: 0.000030 loss: 2.9615 (3.0083) grad: 0.0471 (0.0486) time: 0.3007 data: 0.0030 max mem: 3951 +train: [0] [220/400] eta: 0:00:59 lr: 0.000033 loss: 2.9358 (3.0011) grad: 0.0469 (0.0485) time: 0.3037 data: 0.0032 max mem: 3951 +train: [0] [240/400] eta: 0:00:52 lr: 0.000036 loss: 2.9241 (2.9945) grad: 0.0452 (0.0481) time: 0.3208 data: 0.0033 max mem: 3951 +train: [0] [260/400] eta: 0:00:46 lr: 0.000039 loss: 2.9086 (2.9873) grad: 0.0452 (0.0481) time: 0.3119 data: 0.0031 max mem: 3951 +train: [0] [280/400] eta: 0:00:39 lr: 0.000042 loss: 2.8968 (2.9804) grad: 0.0441 (0.0477) time: 0.3155 data: 0.0032 max mem: 3951 +train: [0] [300/400] eta: 0:00:33 lr: 0.000045 loss: 2.8740 (2.9725) grad: 0.0424 (0.0475) time: 0.4661 data: 0.1734 max mem: 3951 +train: [0] [320/400] eta: 0:00:27 lr: 0.000048 loss: 2.8523 (2.9647) grad: 0.0424 (0.0472) time: 0.3429 data: 0.0120 max mem: 3951 +train: [0] [340/400] eta: 0:00:20 lr: 0.000051 loss: 2.8419 (2.9569) grad: 0.0444 (0.0471) time: 0.3311 data: 0.0026 max mem: 3951 +train: [0] [360/400] eta: 0:00:13 lr: 0.000054 loss: 2.8176 (2.9484) grad: 0.0447 (0.0470) time: 0.3243 data: 0.0032 max mem: 3951 +train: [0] [380/400] eta: 0:00:06 lr: 0.000057 loss: 2.7829 (2.9397) grad: 0.0439 (0.0468) time: 0.3254 data: 0.0031 max mem: 3951 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.7701 (2.9301) grad: 0.0439 (0.0467) time: 0.3285 data: 0.0033 max mem: 3951 +train: [0] Total time: 0:02:14 (0.3359 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.7701 (2.9301) grad: 0.0439 (0.0467) +eval (validation): [0] [ 0/63] eta: 0:03:23 time: 3.2270 data: 3.0100 max mem: 3951 +eval (validation): [0] [20/63] eta: 0:00:19 time: 0.3155 data: 0.0046 max mem: 3951 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3404 data: 0.0032 max mem: 3951 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3155 data: 0.0034 max mem: 3951 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3087 data: 0.0033 max mem: 3951 +eval (validation): [0] Total time: 0:00:23 (0.3730 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 1.513 acc: 0.727 f1: 0.614 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:15 lr: nan time: 3.3396 data: 3.1164 max mem: 3951 +train: [1] [ 20/400] eta: 0:03:06 lr: 0.000063 loss: 2.7330 (2.7303) grad: 0.0445 (0.0447) time: 0.3482 data: 0.0044 max mem: 3951 +train: [1] [ 40/400] eta: 0:02:30 lr: 0.000066 loss: 2.7308 (2.7292) grad: 0.0437 (0.0438) time: 0.3443 data: 0.0026 max mem: 3951 +train: [1] [ 60/400] eta: 0:02:12 lr: 0.000069 loss: 2.7199 (2.7188) grad: 0.0435 (0.0443) time: 0.3309 data: 0.0035 max mem: 3951 +train: [1] [ 80/400] eta: 0:02:01 lr: 0.000072 loss: 2.6993 (2.7100) grad: 0.0422 (0.0437) time: 0.3505 data: 0.0034 max mem: 3951 +train: [1] [100/400] eta: 0:01:51 lr: 0.000075 loss: 2.6707 (2.7032) grad: 0.0398 (0.0429) time: 0.3443 data: 0.0035 max mem: 3951 +train: [1] [120/400] eta: 0:01:43 lr: 0.000078 loss: 2.6661 (2.6953) grad: 0.0409 (0.0431) time: 0.3600 data: 0.0033 max mem: 3951 +train: [1] [140/400] eta: 0:01:35 lr: 0.000081 loss: 2.6331 (2.6833) grad: 0.0420 (0.0430) time: 0.3489 data: 0.0034 max mem: 3951 +train: [1] [160/400] eta: 0:01:27 lr: 0.000084 loss: 2.6269 (2.6764) grad: 0.0410 (0.0428) time: 0.3421 data: 0.0033 max mem: 3951 +train: [1] [180/400] eta: 0:01:20 lr: 0.000087 loss: 2.6034 (2.6670) grad: 0.0406 (0.0428) time: 0.3601 data: 0.0033 max mem: 3951 +train: [1] [200/400] eta: 0:01:12 lr: 0.000090 loss: 2.5852 (2.6591) grad: 0.0404 (0.0424) time: 0.3652 data: 0.0035 max mem: 3951 +train: [1] [220/400] eta: 0:01:05 lr: 0.000093 loss: 2.5582 (2.6484) grad: 0.0411 (0.0424) time: 0.3812 data: 0.0035 max mem: 3951 +train: [1] [240/400] eta: 0:00:58 lr: 0.000096 loss: 2.5372 (2.6386) grad: 0.0415 (0.0423) time: 0.3779 data: 0.0034 max mem: 3951 +train: [1] [260/400] eta: 0:00:51 lr: 0.000099 loss: 2.5341 (2.6284) grad: 0.0413 (0.0423) time: 0.3767 data: 0.0035 max mem: 3951 +train: [1] [280/400] eta: 0:00:44 lr: 0.000102 loss: 2.5240 (2.6201) grad: 0.0381 (0.0421) time: 0.3930 data: 0.0034 max mem: 3951 +train: [1] [300/400] eta: 0:00:38 lr: 0.000105 loss: 2.4929 (2.6104) grad: 0.0381 (0.0420) time: 0.5451 data: 0.2015 max mem: 3951 +train: [1] [320/400] eta: 0:00:30 lr: 0.000108 loss: 2.4664 (2.6025) grad: 0.0385 (0.0418) time: 0.3669 data: 0.0041 max mem: 3951 +train: [1] [340/400] eta: 0:00:22 lr: 0.000111 loss: 2.4487 (2.5916) grad: 0.0406 (0.0419) time: 0.3570 data: 0.0024 max mem: 3951 +train: [1] [360/400] eta: 0:00:15 lr: 0.000114 loss: 2.4030 (2.5813) grad: 0.0423 (0.0418) time: 0.3681 data: 0.0034 max mem: 3951 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 2.4030 (2.5720) grad: 0.0403 (0.0418) time: 0.3618 data: 0.0034 max mem: 3951 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.3883 (2.5634) grad: 0.0396 (0.0417) time: 0.3912 data: 0.0033 max mem: 3951 +train: [1] Total time: 0:02:31 (0.3784 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.3883 (2.5634) grad: 0.0396 (0.0417) +eval (validation): [1] [ 0/63] eta: 0:03:44 time: 3.5645 data: 3.3293 max mem: 3951 +eval (validation): [1] [20/63] eta: 0:00:23 time: 0.3928 data: 0.0043 max mem: 3951 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3564 data: 0.0030 max mem: 3951 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3352 data: 0.0033 max mem: 3951 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3331 data: 0.0033 max mem: 3951 +eval (validation): [1] Total time: 0:00:26 (0.4166 s / it) +cv: [1] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.633 acc: 0.903 f1: 0.893 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:38 lr: nan time: 3.3959 data: 3.1874 max mem: 3951 +train: [2] [ 20/400] eta: 0:03:10 lr: 0.000123 loss: 2.3603 (2.3738) grad: 0.0385 (0.0395) time: 0.3569 data: 0.0030 max mem: 3951 +train: [2] [ 40/400] eta: 0:02:36 lr: 0.000126 loss: 2.3752 (2.3728) grad: 0.0391 (0.0397) time: 0.3628 data: 0.0030 max mem: 3951 +train: [2] [ 60/400] eta: 0:02:18 lr: 0.000129 loss: 2.3372 (2.3565) grad: 0.0387 (0.0392) time: 0.3524 data: 0.0034 max mem: 3951 +train: [2] [ 80/400] eta: 0:02:07 lr: 0.000132 loss: 2.3367 (2.3546) grad: 0.0383 (0.0388) time: 0.3759 data: 0.0038 max mem: 3951 +train: [2] [100/400] eta: 0:01:58 lr: 0.000135 loss: 2.3403 (2.3495) grad: 0.0375 (0.0386) time: 0.3784 data: 0.0034 max mem: 3951 +train: [2] [120/400] eta: 0:01:49 lr: 0.000138 loss: 2.3306 (2.3427) grad: 0.0382 (0.0388) time: 0.3759 data: 0.0036 max mem: 3951 +train: [2] [140/400] eta: 0:01:41 lr: 0.000141 loss: 2.3214 (2.3394) grad: 0.0387 (0.0388) time: 0.3727 data: 0.0034 max mem: 3951 +train: [2] [160/400] eta: 0:01:33 lr: 0.000144 loss: 2.3009 (2.3346) grad: 0.0375 (0.0385) time: 0.3946 data: 0.0037 max mem: 3951 +train: [2] [180/400] eta: 0:01:25 lr: 0.000147 loss: 2.2861 (2.3281) grad: 0.0359 (0.0382) time: 0.3794 data: 0.0035 max mem: 3951 +train: [2] [200/400] eta: 0:01:17 lr: 0.000150 loss: 2.2687 (2.3208) grad: 0.0361 (0.0381) time: 0.3537 data: 0.0034 max mem: 3951 +train: [2] [220/400] eta: 0:01:09 lr: 0.000153 loss: 2.2278 (2.3112) grad: 0.0365 (0.0381) time: 0.3722 data: 0.0034 max mem: 3951 +train: [2] [240/400] eta: 0:01:01 lr: 0.000156 loss: 2.2251 (2.3047) grad: 0.0361 (0.0381) time: 0.3578 data: 0.0037 max mem: 3951 +train: [2] [260/400] eta: 0:00:53 lr: 0.000159 loss: 2.2197 (2.2977) grad: 0.0366 (0.0381) time: 0.3780 data: 0.0035 max mem: 3951 +train: [2] [280/400] eta: 0:00:45 lr: 0.000162 loss: 2.2023 (2.2917) grad: 0.0365 (0.0380) time: 0.3644 data: 0.0034 max mem: 3951 +train: [2] [300/400] eta: 0:00:38 lr: 0.000165 loss: 2.2010 (2.2858) grad: 0.0365 (0.0379) time: 0.5211 data: 0.1877 max mem: 3951 +train: [2] [320/400] eta: 0:00:31 lr: 0.000168 loss: 2.1981 (2.2802) grad: 0.0352 (0.0377) time: 0.4168 data: 0.0110 max mem: 3951 +train: [2] [340/400] eta: 0:00:23 lr: 0.000171 loss: 2.1873 (2.2726) grad: 0.0340 (0.0375) time: 0.3597 data: 0.0028 max mem: 3951 +train: [2] [360/400] eta: 0:00:15 lr: 0.000174 loss: 2.1522 (2.2677) grad: 0.0352 (0.0374) time: 0.3757 data: 0.0033 max mem: 3951 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 2.1571 (2.2621) grad: 0.0358 (0.0374) time: 0.3727 data: 0.0033 max mem: 3951 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.1341 (2.2556) grad: 0.0367 (0.0374) time: 0.3654 data: 0.0036 max mem: 3951 +train: [2] Total time: 0:02:34 (0.3871 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.1341 (2.2556) grad: 0.0367 (0.0374) +eval (validation): [2] [ 0/63] eta: 0:03:41 time: 3.5118 data: 3.2436 max mem: 3951 +eval (validation): [2] [20/63] eta: 0:00:22 time: 0.3657 data: 0.0050 max mem: 3951 +eval (validation): [2] [40/63] eta: 0:00:10 time: 0.3610 data: 0.0029 max mem: 3951 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3363 data: 0.0034 max mem: 3951 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3326 data: 0.0030 max mem: 3951 +eval (validation): [2] Total time: 0:00:25 (0.4077 s / it) +cv: [2] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.390 acc: 0.934 f1: 0.927 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:24:06 lr: nan time: 3.6163 data: 3.3293 max mem: 3951 +train: [3] [ 20/400] eta: 0:03:21 lr: 0.000183 loss: 2.0845 (2.0975) grad: 0.0376 (0.0369) time: 0.3755 data: 0.0039 max mem: 3951 +train: [3] [ 40/400] eta: 0:02:41 lr: 0.000186 loss: 2.0912 (2.1010) grad: 0.0364 (0.0365) time: 0.3605 data: 0.0030 max mem: 3951 +train: [3] [ 60/400] eta: 0:02:20 lr: 0.000189 loss: 2.0912 (2.0988) grad: 0.0350 (0.0364) time: 0.3455 data: 0.0033 max mem: 3951 +train: [3] [ 80/400] eta: 0:02:09 lr: 0.000192 loss: 2.0933 (2.0986) grad: 0.0335 (0.0356) time: 0.3770 data: 0.0032 max mem: 3951 +train: [3] [100/400] eta: 0:01:59 lr: 0.000195 loss: 2.0946 (2.0983) grad: 0.0339 (0.0355) time: 0.3687 data: 0.0035 max mem: 3951 +train: [3] [120/400] eta: 0:01:49 lr: 0.000198 loss: 2.0829 (2.0936) grad: 0.0353 (0.0356) time: 0.3594 data: 0.0033 max mem: 3951 +train: [3] [140/400] eta: 0:01:40 lr: 0.000201 loss: 2.0524 (2.0869) grad: 0.0354 (0.0358) time: 0.3658 data: 0.0033 max mem: 3951 +train: [3] [160/400] eta: 0:01:32 lr: 0.000204 loss: 2.0562 (2.0844) grad: 0.0349 (0.0356) time: 0.3683 data: 0.0032 max mem: 3951 +train: [3] [180/400] eta: 0:01:23 lr: 0.000207 loss: 2.0562 (2.0807) grad: 0.0345 (0.0357) time: 0.3529 data: 0.0035 max mem: 3951 +train: [3] [200/400] eta: 0:01:15 lr: 0.000210 loss: 2.0304 (2.0751) grad: 0.0355 (0.0357) time: 0.3499 data: 0.0033 max mem: 3951 +train: [3] [220/400] eta: 0:01:07 lr: 0.000213 loss: 2.0146 (2.0695) grad: 0.0350 (0.0357) time: 0.3689 data: 0.0033 max mem: 3951 +train: [3] [240/400] eta: 0:01:00 lr: 0.000216 loss: 2.0007 (2.0638) grad: 0.0335 (0.0357) time: 0.3715 data: 0.0033 max mem: 3951 +train: [3] [260/400] eta: 0:00:52 lr: 0.000219 loss: 2.0007 (2.0592) grad: 0.0329 (0.0355) time: 0.3536 data: 0.0034 max mem: 3951 +train: [3] [280/400] eta: 0:00:44 lr: 0.000222 loss: 2.0262 (2.0566) grad: 0.0326 (0.0353) time: 0.3657 data: 0.0037 max mem: 3951 +train: [3] [300/400] eta: 0:00:38 lr: 0.000225 loss: 2.0094 (2.0523) grad: 0.0330 (0.0353) time: 0.5748 data: 0.2017 max mem: 3951 +train: [3] [320/400] eta: 0:00:30 lr: 0.000228 loss: 1.9678 (2.0464) grad: 0.0331 (0.0352) time: 0.3654 data: 0.0034 max mem: 3951 +train: [3] [340/400] eta: 0:00:23 lr: 0.000231 loss: 1.9609 (2.0414) grad: 0.0336 (0.0352) time: 0.3544 data: 0.0034 max mem: 3951 +train: [3] [360/400] eta: 0:00:15 lr: 0.000234 loss: 1.9613 (2.0371) grad: 0.0327 (0.0350) time: 0.3466 data: 0.0033 max mem: 3951 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 1.9361 (2.0309) grad: 0.0337 (0.0351) time: 0.3649 data: 0.0035 max mem: 3951 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 1.9345 (2.0279) grad: 0.0331 (0.0349) time: 0.3599 data: 0.0034 max mem: 3951 +train: [3] Total time: 0:02:32 (0.3808 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.9345 (2.0279) grad: 0.0331 (0.0349) +eval (validation): [3] [ 0/63] eta: 0:03:44 time: 3.5590 data: 3.2737 max mem: 3951 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3556 data: 0.0049 max mem: 3951 +eval (validation): [3] [40/63] eta: 0:00:10 time: 0.3818 data: 0.0030 max mem: 3951 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3494 data: 0.0034 max mem: 3951 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3472 data: 0.0034 max mem: 3951 +eval (validation): [3] Total time: 0:00:26 (0.4162 s / it) +cv: [3] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.303 acc: 0.941 f1: 0.934 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:23:36 lr: nan time: 3.5401 data: 3.2501 max mem: 3951 +train: [4] [ 20/400] eta: 0:03:29 lr: 0.000243 loss: 1.9216 (1.9253) grad: 0.0337 (0.0344) time: 0.4026 data: 0.0034 max mem: 3951 +train: [4] [ 40/400] eta: 0:02:43 lr: 0.000246 loss: 1.9200 (1.9209) grad: 0.0328 (0.0332) time: 0.3533 data: 0.0032 max mem: 3951 +train: [4] [ 60/400] eta: 0:02:22 lr: 0.000249 loss: 1.9196 (1.9250) grad: 0.0330 (0.0337) time: 0.3490 data: 0.0033 max mem: 3951 +train: [4] [ 80/400] eta: 0:02:09 lr: 0.000252 loss: 1.9177 (1.9182) grad: 0.0339 (0.0336) time: 0.3609 data: 0.0035 max mem: 3951 +train: [4] [100/400] eta: 0:01:59 lr: 0.000255 loss: 1.9034 (1.9199) grad: 0.0334 (0.0337) time: 0.3749 data: 0.0035 max mem: 3951 +train: [4] [120/400] eta: 0:01:51 lr: 0.000258 loss: 1.8983 (1.9161) grad: 0.0329 (0.0335) time: 0.3821 data: 0.0033 max mem: 3951 +train: [4] [140/400] eta: 0:01:42 lr: 0.000261 loss: 1.8890 (1.9115) grad: 0.0331 (0.0336) time: 0.3722 data: 0.0036 max mem: 3951 +train: [4] [160/400] eta: 0:01:34 lr: 0.000264 loss: 1.8736 (1.9071) grad: 0.0320 (0.0333) time: 0.4027 data: 0.0034 max mem: 3951 +train: [4] [180/400] eta: 0:01:26 lr: 0.000267 loss: 1.8532 (1.9014) grad: 0.0319 (0.0334) time: 0.3780 data: 0.0037 max mem: 3951 +train: [4] [200/400] eta: 0:01:17 lr: 0.000270 loss: 1.8252 (1.8933) grad: 0.0334 (0.0334) time: 0.3411 data: 0.0032 max mem: 3951 +train: [4] [220/400] eta: 0:01:09 lr: 0.000273 loss: 1.8368 (1.8890) grad: 0.0329 (0.0333) time: 0.3713 data: 0.0035 max mem: 3951 +train: [4] [240/400] eta: 0:01:01 lr: 0.000276 loss: 1.8536 (1.8853) grad: 0.0317 (0.0332) time: 0.3552 data: 0.0036 max mem: 3951 +train: [4] [260/400] eta: 0:00:53 lr: 0.000279 loss: 1.8369 (1.8821) grad: 0.0311 (0.0331) time: 0.3495 data: 0.0035 max mem: 3951 +train: [4] [280/400] eta: 0:00:45 lr: 0.000282 loss: 1.8324 (1.8778) grad: 0.0311 (0.0330) time: 0.3547 data: 0.0035 max mem: 3951 +train: [4] [300/400] eta: 0:00:39 lr: 0.000285 loss: 1.8338 (1.8761) grad: 0.0306 (0.0329) time: 0.5491 data: 0.1943 max mem: 3951 +train: [4] [320/400] eta: 0:00:31 lr: 0.000288 loss: 1.8086 (1.8703) grad: 0.0321 (0.0329) time: 0.3973 data: 0.0052 max mem: 3951 +train: [4] [340/400] eta: 0:00:23 lr: 0.000291 loss: 1.7819 (1.8651) grad: 0.0320 (0.0328) time: 0.3632 data: 0.0034 max mem: 3951 +train: [4] [360/400] eta: 0:00:15 lr: 0.000294 loss: 1.7666 (1.8611) grad: 0.0309 (0.0328) time: 0.3624 data: 0.0035 max mem: 3951 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.7650 (1.8568) grad: 0.0326 (0.0328) time: 0.3648 data: 0.0033 max mem: 3951 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 1.7485 (1.8524) grad: 0.0332 (0.0329) time: 0.3597 data: 0.0033 max mem: 3951 +train: [4] Total time: 0:02:34 (0.3854 s / it) +train: [4] Summary: lr: 0.000300 loss: 1.7485 (1.8524) grad: 0.0332 (0.0329) +eval (validation): [4] [ 0/63] eta: 0:03:43 time: 3.5419 data: 3.2662 max mem: 3951 +eval (validation): [4] [20/63] eta: 0:00:23 time: 0.3897 data: 0.0048 max mem: 3951 +eval (validation): [4] [40/63] eta: 0:00:10 time: 0.3597 data: 0.0035 max mem: 3951 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3377 data: 0.0032 max mem: 3951 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3348 data: 0.0032 max mem: 3951 +eval (validation): [4] Total time: 0:00:26 (0.4161 s / it) +cv: [4] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.253 acc: 0.950 f1: 0.944 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:24:07 lr: nan time: 3.6178 data: 3.3232 max mem: 3951 +train: [5] [ 20/400] eta: 0:03:18 lr: 0.000300 loss: 1.7758 (1.7661) grad: 0.0314 (0.0319) time: 0.3689 data: 0.0036 max mem: 3951 +train: [5] [ 40/400] eta: 0:02:38 lr: 0.000300 loss: 1.7786 (1.7740) grad: 0.0316 (0.0315) time: 0.3545 data: 0.0031 max mem: 3951 +train: [5] [ 60/400] eta: 0:02:19 lr: 0.000300 loss: 1.7771 (1.7782) grad: 0.0294 (0.0308) time: 0.3430 data: 0.0033 max mem: 3951 +train: [5] [ 80/400] eta: 0:02:08 lr: 0.000300 loss: 1.7736 (1.7799) grad: 0.0301 (0.0313) time: 0.3746 data: 0.0035 max mem: 3951 +train: [5] [100/400] eta: 0:01:57 lr: 0.000300 loss: 1.7404 (1.7668) grad: 0.0303 (0.0310) time: 0.3600 data: 0.0034 max mem: 3951 +train: [5] [120/400] eta: 0:01:47 lr: 0.000300 loss: 1.7326 (1.7647) grad: 0.0299 (0.0310) time: 0.3510 data: 0.0033 max mem: 3951 +train: [5] [140/400] eta: 0:01:39 lr: 0.000300 loss: 1.7241 (1.7580) grad: 0.0315 (0.0312) time: 0.3783 data: 0.0033 max mem: 3951 +train: [5] [160/400] eta: 0:01:31 lr: 0.000299 loss: 1.7225 (1.7547) grad: 0.0317 (0.0313) time: 0.3713 data: 0.0036 max mem: 3951 +train: [5] [180/400] eta: 0:01:23 lr: 0.000299 loss: 1.7225 (1.7501) grad: 0.0317 (0.0315) time: 0.3719 data: 0.0035 max mem: 3951 +train: [5] [200/400] eta: 0:01:16 lr: 0.000299 loss: 1.7051 (1.7445) grad: 0.0323 (0.0316) time: 0.3883 data: 0.0035 max mem: 3951 +train: [5] [220/400] eta: 0:01:08 lr: 0.000299 loss: 1.7051 (1.7423) grad: 0.0306 (0.0316) time: 0.3648 data: 0.0036 max mem: 3951 +train: [5] [240/400] eta: 0:01:00 lr: 0.000299 loss: 1.7303 (1.7414) grad: 0.0297 (0.0314) time: 0.3772 data: 0.0032 max mem: 3951 +train: [5] [260/400] eta: 0:00:53 lr: 0.000299 loss: 1.6964 (1.7376) grad: 0.0301 (0.0314) time: 0.3755 data: 0.0034 max mem: 3951 +train: [5] [280/400] eta: 0:00:45 lr: 0.000298 loss: 1.6953 (1.7371) grad: 0.0303 (0.0313) time: 0.3659 data: 0.0036 max mem: 3951 +train: [5] [300/400] eta: 0:00:38 lr: 0.000298 loss: 1.6953 (1.7335) grad: 0.0296 (0.0312) time: 0.5395 data: 0.1969 max mem: 3951 +train: [5] [320/400] eta: 0:00:31 lr: 0.000298 loss: 1.6747 (1.7302) grad: 0.0281 (0.0311) time: 0.3694 data: 0.0039 max mem: 3951 +train: [5] [340/400] eta: 0:00:23 lr: 0.000298 loss: 1.6613 (1.7263) grad: 0.0297 (0.0311) time: 0.3796 data: 0.0032 max mem: 3951 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 1.6613 (1.7230) grad: 0.0301 (0.0310) time: 0.3546 data: 0.0035 max mem: 3951 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.6674 (1.7206) grad: 0.0297 (0.0310) time: 0.3831 data: 0.0037 max mem: 3951 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 1.6615 (1.7177) grad: 0.0300 (0.0310) time: 0.3761 data: 0.0038 max mem: 3951 +train: [5] Total time: 0:02:34 (0.3858 s / it) +train: [5] Summary: lr: 0.000297 loss: 1.6615 (1.7177) grad: 0.0300 (0.0310) +eval (validation): [5] [ 0/63] eta: 0:03:43 time: 3.5532 data: 3.2773 max mem: 3951 +eval (validation): [5] [20/63] eta: 0:00:21 time: 0.3580 data: 0.0051 max mem: 3951 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3369 data: 0.0041 max mem: 3951 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3404 data: 0.0022 max mem: 3951 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3369 data: 0.0026 max mem: 3951 +eval (validation): [5] Total time: 0:00:25 (0.3990 s / it) +cv: [5] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.228 acc: 0.955 f1: 0.948 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:23:32 lr: nan time: 3.5316 data: 3.2834 max mem: 3951 +train: [6] [ 20/400] eta: 0:03:26 lr: 0.000296 loss: 1.6388 (1.6515) grad: 0.0294 (0.0303) time: 0.3951 data: 0.0050 max mem: 3951 +train: [6] [ 40/400] eta: 0:02:44 lr: 0.000296 loss: 1.6456 (1.6449) grad: 0.0308 (0.0314) time: 0.3668 data: 0.0029 max mem: 3951 +train: [6] [ 60/400] eta: 0:02:23 lr: 0.000296 loss: 1.6256 (1.6401) grad: 0.0304 (0.0310) time: 0.3477 data: 0.0033 max mem: 3951 +train: [6] [ 80/400] eta: 0:02:12 lr: 0.000295 loss: 1.6548 (1.6465) grad: 0.0280 (0.0300) time: 0.3877 data: 0.0035 max mem: 3951 +train: [6] [100/400] eta: 0:02:01 lr: 0.000295 loss: 1.6460 (1.6440) grad: 0.0283 (0.0299) time: 0.3646 data: 0.0034 max mem: 3951 +train: [6] [120/400] eta: 0:01:50 lr: 0.000295 loss: 1.6214 (1.6420) grad: 0.0307 (0.0302) time: 0.3596 data: 0.0033 max mem: 3951 +train: [6] [140/400] eta: 0:01:42 lr: 0.000294 loss: 1.6509 (1.6445) grad: 0.0306 (0.0302) time: 0.3750 data: 0.0035 max mem: 3951 +train: [6] [160/400] eta: 0:01:33 lr: 0.000294 loss: 1.6608 (1.6458) grad: 0.0301 (0.0301) time: 0.3645 data: 0.0034 max mem: 3951 +train: [6] [180/400] eta: 0:01:24 lr: 0.000293 loss: 1.6228 (1.6418) grad: 0.0287 (0.0300) time: 0.3564 data: 0.0034 max mem: 3951 +train: [6] [200/400] eta: 0:01:17 lr: 0.000293 loss: 1.6066 (1.6394) grad: 0.0287 (0.0299) time: 0.3758 data: 0.0036 max mem: 3951 +train: [6] [220/400] eta: 0:01:08 lr: 0.000292 loss: 1.6066 (1.6364) grad: 0.0290 (0.0299) time: 0.3658 data: 0.0034 max mem: 3951 +train: [6] [240/400] eta: 0:01:01 lr: 0.000292 loss: 1.6034 (1.6351) grad: 0.0300 (0.0300) time: 0.3595 data: 0.0033 max mem: 3951 +train: [6] [260/400] eta: 0:00:53 lr: 0.000291 loss: 1.5921 (1.6310) grad: 0.0300 (0.0300) time: 0.3680 data: 0.0035 max mem: 3951 +train: [6] [280/400] eta: 0:00:45 lr: 0.000291 loss: 1.5921 (1.6322) grad: 0.0276 (0.0298) time: 0.3890 data: 0.0034 max mem: 3951 +train: [6] [300/400] eta: 0:00:39 lr: 0.000290 loss: 1.6128 (1.6299) grad: 0.0277 (0.0298) time: 0.5328 data: 0.1937 max mem: 3951 +train: [6] [320/400] eta: 0:00:31 lr: 0.000290 loss: 1.5751 (1.6270) grad: 0.0280 (0.0296) time: 0.3680 data: 0.0036 max mem: 3951 +train: [6] [340/400] eta: 0:00:23 lr: 0.000289 loss: 1.5751 (1.6246) grad: 0.0280 (0.0296) time: 0.3760 data: 0.0028 max mem: 3951 +train: [6] [360/400] eta: 0:00:15 lr: 0.000288 loss: 1.5732 (1.6213) grad: 0.0282 (0.0296) time: 0.3618 data: 0.0034 max mem: 3951 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 1.5732 (1.6198) grad: 0.0282 (0.0295) time: 0.3895 data: 0.0037 max mem: 3951 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 1.5722 (1.6174) grad: 0.0279 (0.0295) time: 0.3829 data: 0.0034 max mem: 3951 +train: [6] Total time: 0:02:34 (0.3874 s / it) +train: [6] Summary: lr: 0.000287 loss: 1.5722 (1.6174) grad: 0.0279 (0.0295) +eval (validation): [6] [ 0/63] eta: 0:03:54 time: 3.7164 data: 3.4384 max mem: 3951 +eval (validation): [6] [20/63] eta: 0:00:24 time: 0.4182 data: 0.0041 max mem: 3951 +eval (validation): [6] [40/63] eta: 0:00:10 time: 0.3723 data: 0.0034 max mem: 3951 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3503 data: 0.0037 max mem: 3951 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3460 data: 0.0036 max mem: 3951 +eval (validation): [6] Total time: 0:00:27 (0.4371 s / it) +cv: [6] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.210 acc: 0.959 f1: 0.952 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:30:52 lr: nan time: 4.6311 data: 4.3643 max mem: 3951 +train: [7] [ 20/400] eta: 0:03:42 lr: 0.000286 loss: 1.5979 (1.5917) grad: 0.0266 (0.0291) time: 0.3829 data: 0.0029 max mem: 3951 +train: [7] [ 40/400] eta: 0:02:56 lr: 0.000286 loss: 1.5893 (1.5786) grad: 0.0297 (0.0291) time: 0.3918 data: 0.0031 max mem: 3951 +train: [7] [ 60/400] eta: 0:02:31 lr: 0.000285 loss: 1.5556 (1.5583) grad: 0.0297 (0.0296) time: 0.3520 data: 0.0033 max mem: 3951 +train: [7] [ 80/400] eta: 0:02:20 lr: 0.000284 loss: 1.5612 (1.5657) grad: 0.0280 (0.0290) time: 0.4159 data: 0.0037 max mem: 3951 +train: [7] [100/400] eta: 0:02:08 lr: 0.000284 loss: 1.5674 (1.5649) grad: 0.0279 (0.0291) time: 0.3888 data: 0.0034 max mem: 3951 +train: [7] [120/400] eta: 0:01:57 lr: 0.000283 loss: 1.5531 (1.5629) grad: 0.0281 (0.0289) time: 0.3844 data: 0.0035 max mem: 3951 +train: [7] [140/400] eta: 0:01:48 lr: 0.000282 loss: 1.5329 (1.5576) grad: 0.0284 (0.0291) time: 0.3859 data: 0.0034 max mem: 3951 +train: [7] [160/400] eta: 0:01:39 lr: 0.000282 loss: 1.5325 (1.5566) grad: 0.0291 (0.0291) time: 0.3956 data: 0.0036 max mem: 3951 +train: [7] [180/400] eta: 0:01:30 lr: 0.000281 loss: 1.5425 (1.5542) grad: 0.0285 (0.0291) time: 0.3917 data: 0.0034 max mem: 3951 +train: [7] [200/400] eta: 0:01:21 lr: 0.000280 loss: 1.5288 (1.5532) grad: 0.0279 (0.0289) time: 0.3715 data: 0.0034 max mem: 3951 +train: [7] [220/400] eta: 0:01:13 lr: 0.000279 loss: 1.5440 (1.5516) grad: 0.0263 (0.0288) time: 0.4220 data: 0.0035 max mem: 3951 +train: [7] [240/400] eta: 0:01:05 lr: 0.000278 loss: 1.5442 (1.5492) grad: 0.0272 (0.0287) time: 0.3943 data: 0.0037 max mem: 3951 +train: [7] [260/400] eta: 0:00:56 lr: 0.000278 loss: 1.5144 (1.5473) grad: 0.0282 (0.0287) time: 0.3863 data: 0.0036 max mem: 3951 +train: [7] [280/400] eta: 0:00:48 lr: 0.000277 loss: 1.5014 (1.5424) grad: 0.0284 (0.0287) time: 0.3911 data: 0.0036 max mem: 3951 +train: [7] [300/400] eta: 0:00:41 lr: 0.000276 loss: 1.5029 (1.5408) grad: 0.0272 (0.0286) time: 0.5968 data: 0.2067 max mem: 3951 +train: [7] [320/400] eta: 0:00:33 lr: 0.000275 loss: 1.5029 (1.5376) grad: 0.0273 (0.0285) time: 0.4017 data: 0.0034 max mem: 3951 +train: [7] [340/400] eta: 0:00:24 lr: 0.000274 loss: 1.5189 (1.5368) grad: 0.0270 (0.0284) time: 0.3907 data: 0.0037 max mem: 3951 +train: [7] [360/400] eta: 0:00:16 lr: 0.000273 loss: 1.5144 (1.5340) grad: 0.0267 (0.0284) time: 0.4070 data: 0.0035 max mem: 3951 +train: [7] [380/400] eta: 0:00:08 lr: 0.000272 loss: 1.4890 (1.5319) grad: 0.0278 (0.0284) time: 0.4047 data: 0.0035 max mem: 3951 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 1.4942 (1.5312) grad: 0.0279 (0.0285) time: 0.3746 data: 0.0035 max mem: 3951 +train: [7] Total time: 0:02:44 (0.4124 s / it) +train: [7] Summary: lr: 0.000271 loss: 1.4942 (1.5312) grad: 0.0279 (0.0285) +eval (validation): [7] [ 0/63] eta: 0:03:57 time: 3.7747 data: 3.4946 max mem: 3951 +eval (validation): [7] [20/63] eta: 0:00:23 time: 0.3949 data: 0.0034 max mem: 3951 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3646 data: 0.0035 max mem: 3951 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3390 data: 0.0033 max mem: 3951 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3338 data: 0.0033 max mem: 3951 +eval (validation): [7] Total time: 0:00:26 (0.4236 s / it) +cv: [7] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.210 acc: 0.957 f1: 0.952 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:23:40 lr: nan time: 3.5502 data: 3.3024 max mem: 3951 +train: [8] [ 20/400] eta: 0:03:32 lr: 0.000270 loss: 1.5180 (1.5243) grad: 0.0264 (0.0269) time: 0.4090 data: 0.0132 max mem: 3951 +train: [8] [ 40/400] eta: 0:02:54 lr: 0.000270 loss: 1.4978 (1.4948) grad: 0.0275 (0.0283) time: 0.4096 data: 0.0030 max mem: 3951 +train: [8] [ 60/400] eta: 0:02:32 lr: 0.000269 loss: 1.4790 (1.4924) grad: 0.0288 (0.0285) time: 0.3751 data: 0.0035 max mem: 3951 +train: [8] [ 80/400] eta: 0:02:18 lr: 0.000268 loss: 1.4831 (1.4889) grad: 0.0283 (0.0283) time: 0.3793 data: 0.0035 max mem: 3951 +train: [8] [100/400] eta: 0:02:08 lr: 0.000267 loss: 1.4730 (1.4882) grad: 0.0282 (0.0284) time: 0.4185 data: 0.0035 max mem: 3951 +train: [8] [120/400] eta: 0:01:58 lr: 0.000266 loss: 1.4679 (1.4863) grad: 0.0283 (0.0285) time: 0.3896 data: 0.0035 max mem: 3951 +train: [8] [140/400] eta: 0:01:49 lr: 0.000265 loss: 1.4970 (1.4881) grad: 0.0286 (0.0283) time: 0.4143 data: 0.0034 max mem: 3951 +train: [8] [160/400] eta: 0:01:40 lr: 0.000264 loss: 1.5031 (1.4883) grad: 0.0285 (0.0285) time: 0.3918 data: 0.0034 max mem: 3951 +train: [8] [180/400] eta: 0:01:31 lr: 0.000263 loss: 1.4869 (1.4872) grad: 0.0277 (0.0283) time: 0.3917 data: 0.0036 max mem: 3951 +train: [8] [200/400] eta: 0:01:22 lr: 0.000262 loss: 1.4717 (1.4860) grad: 0.0272 (0.0282) time: 0.3840 data: 0.0035 max mem: 3951 +train: [8] [220/400] eta: 0:01:13 lr: 0.000260 loss: 1.4594 (1.4837) grad: 0.0271 (0.0281) time: 0.3917 data: 0.0035 max mem: 3951 +train: [8] [240/400] eta: 0:01:05 lr: 0.000259 loss: 1.4650 (1.4818) grad: 0.0271 (0.0281) time: 0.3739 data: 0.0034 max mem: 3951 +train: [8] [260/400] eta: 0:00:56 lr: 0.000258 loss: 1.4675 (1.4805) grad: 0.0275 (0.0281) time: 0.3627 data: 0.0037 max mem: 3951 +train: [8] [280/400] eta: 0:00:48 lr: 0.000257 loss: 1.4481 (1.4781) grad: 0.0278 (0.0281) time: 0.3683 data: 0.0035 max mem: 3951 +train: [8] [300/400] eta: 0:00:41 lr: 0.000256 loss: 1.4683 (1.4788) grad: 0.0266 (0.0280) time: 0.5620 data: 0.2048 max mem: 3951 +train: [8] [320/400] eta: 0:00:32 lr: 0.000255 loss: 1.4713 (1.4782) grad: 0.0268 (0.0280) time: 0.3814 data: 0.0030 max mem: 3951 +train: [8] [340/400] eta: 0:00:24 lr: 0.000254 loss: 1.4555 (1.4763) grad: 0.0272 (0.0280) time: 0.3667 data: 0.0034 max mem: 3951 +train: [8] [360/400] eta: 0:00:16 lr: 0.000253 loss: 1.4341 (1.4749) grad: 0.0274 (0.0280) time: 0.3562 data: 0.0036 max mem: 3951 +train: [8] [380/400] eta: 0:00:08 lr: 0.000252 loss: 1.4627 (1.4743) grad: 0.0276 (0.0279) time: 0.3820 data: 0.0038 max mem: 3951 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 1.4660 (1.4736) grad: 0.0259 (0.0278) time: 0.3750 data: 0.0033 max mem: 3951 +train: [8] Total time: 0:02:40 (0.4024 s / it) +train: [8] Summary: lr: 0.000250 loss: 1.4660 (1.4736) grad: 0.0259 (0.0278) +eval (validation): [8] [ 0/63] eta: 0:03:43 time: 3.5552 data: 3.3224 max mem: 3951 +eval (validation): [8] [20/63] eta: 0:00:21 time: 0.3581 data: 0.0038 max mem: 3951 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3616 data: 0.0036 max mem: 3951 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3417 data: 0.0032 max mem: 3951 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3400 data: 0.0033 max mem: 3951 +eval (validation): [8] Total time: 0:00:25 (0.4081 s / it) +cv: [8] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.202 acc: 0.959 f1: 0.953 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:24:12 lr: nan time: 3.6314 data: 3.3451 max mem: 3951 +train: [9] [ 20/400] eta: 0:03:24 lr: 0.000249 loss: 1.4231 (1.4446) grad: 0.0268 (0.0266) time: 0.3838 data: 0.0029 max mem: 3951 +train: [9] [ 40/400] eta: 0:02:46 lr: 0.000248 loss: 1.4522 (1.4509) grad: 0.0265 (0.0267) time: 0.3804 data: 0.0033 max mem: 3951 +train: [9] [ 60/400] eta: 0:02:24 lr: 0.000247 loss: 1.4502 (1.4429) grad: 0.0265 (0.0271) time: 0.3472 data: 0.0034 max mem: 3951 +train: [9] [ 80/400] eta: 0:02:09 lr: 0.000246 loss: 1.4512 (1.4499) grad: 0.0271 (0.0270) time: 0.3467 data: 0.0034 max mem: 3951 +train: [9] [100/400] eta: 0:02:00 lr: 0.000244 loss: 1.4330 (1.4443) grad: 0.0271 (0.0269) time: 0.3816 data: 0.0032 max mem: 3951 +train: [9] [120/400] eta: 0:01:50 lr: 0.000243 loss: 1.4213 (1.4438) grad: 0.0271 (0.0269) time: 0.3704 data: 0.0033 max mem: 3951 +train: [9] [140/400] eta: 0:01:42 lr: 0.000242 loss: 1.4338 (1.4431) grad: 0.0267 (0.0270) time: 0.3855 data: 0.0035 max mem: 3951 +train: [9] [160/400] eta: 0:01:33 lr: 0.000241 loss: 1.4269 (1.4408) grad: 0.0269 (0.0270) time: 0.3754 data: 0.0034 max mem: 3951 +train: [9] [180/400] eta: 0:01:25 lr: 0.000240 loss: 1.4381 (1.4411) grad: 0.0269 (0.0270) time: 0.3819 data: 0.0035 max mem: 3951 +train: [9] [200/400] eta: 0:01:17 lr: 0.000238 loss: 1.4381 (1.4386) grad: 0.0269 (0.0269) time: 0.3587 data: 0.0034 max mem: 3951 +train: [9] [220/400] eta: 0:01:09 lr: 0.000237 loss: 1.4330 (1.4375) grad: 0.0271 (0.0269) time: 0.3829 data: 0.0035 max mem: 3951 +train: [9] [240/400] eta: 0:01:01 lr: 0.000236 loss: 1.4053 (1.4349) grad: 0.0258 (0.0268) time: 0.3887 data: 0.0034 max mem: 3951 +train: [9] [260/400] eta: 0:00:53 lr: 0.000234 loss: 1.3865 (1.4323) grad: 0.0260 (0.0268) time: 0.3687 data: 0.0034 max mem: 3951 +train: [9] [280/400] eta: 0:00:46 lr: 0.000233 loss: 1.4026 (1.4310) grad: 0.0271 (0.0269) time: 0.3713 data: 0.0035 max mem: 3951 +train: [9] [300/400] eta: 0:00:39 lr: 0.000232 loss: 1.4116 (1.4309) grad: 0.0258 (0.0269) time: 0.5659 data: 0.2059 max mem: 3951 +train: [9] [320/400] eta: 0:00:31 lr: 0.000230 loss: 1.3946 (1.4284) grad: 0.0258 (0.0269) time: 0.4080 data: 0.0035 max mem: 3951 +train: [9] [340/400] eta: 0:00:23 lr: 0.000229 loss: 1.3888 (1.4272) grad: 0.0262 (0.0269) time: 0.3926 data: 0.0033 max mem: 3951 +train: [9] [360/400] eta: 0:00:15 lr: 0.000228 loss: 1.3891 (1.4258) grad: 0.0263 (0.0269) time: 0.3834 data: 0.0034 max mem: 3951 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 1.3891 (1.4241) grad: 0.0268 (0.0269) time: 0.4140 data: 0.0033 max mem: 3951 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 1.4041 (1.4239) grad: 0.0260 (0.0270) time: 0.3843 data: 0.0033 max mem: 3951 +train: [9] Total time: 0:02:38 (0.3970 s / it) +train: [9] Summary: lr: 0.000225 loss: 1.4041 (1.4239) grad: 0.0260 (0.0270) +eval (validation): [9] [ 0/63] eta: 0:03:58 time: 3.7932 data: 3.4959 max mem: 3951 +eval (validation): [9] [20/63] eta: 0:00:24 time: 0.4100 data: 0.0052 max mem: 3951 +eval (validation): [9] [40/63] eta: 0:00:11 time: 0.3964 data: 0.0034 max mem: 3951 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3622 data: 0.0035 max mem: 3951 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3604 data: 0.0035 max mem: 3951 +eval (validation): [9] Total time: 0:00:28 (0.4459 s / it) +cv: [9] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.191 acc: 0.960 f1: 0.955 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:25:24 lr: nan time: 3.8125 data: 3.5103 max mem: 3951 +train: [10] [ 20/400] eta: 0:03:50 lr: 0.000224 loss: 1.3813 (1.3969) grad: 0.0275 (0.0278) time: 0.4465 data: 0.0025 max mem: 3951 +train: [10] [ 40/400] eta: 0:03:00 lr: 0.000222 loss: 1.3863 (1.4091) grad: 0.0262 (0.0266) time: 0.3932 data: 0.0034 max mem: 3951 +train: [10] [ 60/400] eta: 0:02:36 lr: 0.000221 loss: 1.3983 (1.4043) grad: 0.0262 (0.0269) time: 0.3693 data: 0.0036 max mem: 3951 +train: [10] [ 80/400] eta: 0:02:22 lr: 0.000220 loss: 1.3954 (1.3977) grad: 0.0266 (0.0269) time: 0.4102 data: 0.0035 max mem: 3951 +train: [10] [100/400] eta: 0:02:09 lr: 0.000218 loss: 1.3879 (1.3957) grad: 0.0263 (0.0268) time: 0.3700 data: 0.0032 max mem: 3951 +train: [10] [120/400] eta: 0:01:59 lr: 0.000217 loss: 1.3711 (1.3899) grad: 0.0266 (0.0268) time: 0.3988 data: 0.0032 max mem: 3951 +train: [10] [140/400] eta: 0:01:50 lr: 0.000215 loss: 1.3863 (1.3901) grad: 0.0266 (0.0269) time: 0.4059 data: 0.0034 max mem: 3951 +train: [10] [160/400] eta: 0:01:40 lr: 0.000214 loss: 1.4130 (1.3942) grad: 0.0262 (0.0268) time: 0.3970 data: 0.0035 max mem: 3951 +train: [10] [180/400] eta: 0:01:31 lr: 0.000213 loss: 1.4248 (1.3942) grad: 0.0254 (0.0267) time: 0.3647 data: 0.0032 max mem: 3951 +train: [10] [200/400] eta: 0:01:22 lr: 0.000211 loss: 1.3573 (1.3903) grad: 0.0264 (0.0267) time: 0.3821 data: 0.0033 max mem: 3951 +train: [10] [220/400] eta: 0:01:13 lr: 0.000210 loss: 1.3633 (1.3889) grad: 0.0264 (0.0268) time: 0.3952 data: 0.0034 max mem: 3951 +train: [10] [240/400] eta: 0:01:05 lr: 0.000208 loss: 1.3778 (1.3905) grad: 0.0254 (0.0266) time: 0.3924 data: 0.0036 max mem: 3951 +train: [10] [260/400] eta: 0:00:56 lr: 0.000207 loss: 1.3964 (1.3908) grad: 0.0250 (0.0265) time: 0.3801 data: 0.0036 max mem: 3951 +train: [10] [280/400] eta: 0:00:48 lr: 0.000205 loss: 1.3850 (1.3917) grad: 0.0257 (0.0265) time: 0.3847 data: 0.0035 max mem: 3951 +train: [10] [300/400] eta: 0:00:41 lr: 0.000204 loss: 1.3850 (1.3901) grad: 0.0254 (0.0264) time: 0.5889 data: 0.2041 max mem: 3951 +train: [10] [320/400] eta: 0:00:33 lr: 0.000202 loss: 1.3793 (1.3897) grad: 0.0254 (0.0265) time: 0.4108 data: 0.0033 max mem: 3951 +train: [10] [340/400] eta: 0:00:24 lr: 0.000201 loss: 1.3720 (1.3876) grad: 0.0262 (0.0264) time: 0.3837 data: 0.0034 max mem: 3951 +train: [10] [360/400] eta: 0:00:16 lr: 0.000199 loss: 1.3506 (1.3872) grad: 0.0262 (0.0264) time: 0.3768 data: 0.0033 max mem: 3951 +train: [10] [380/400] eta: 0:00:08 lr: 0.000198 loss: 1.3740 (1.3873) grad: 0.0249 (0.0263) time: 0.3768 data: 0.0033 max mem: 3951 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 1.3585 (1.3857) grad: 0.0244 (0.0263) time: 0.3649 data: 0.0035 max mem: 3951 +train: [10] Total time: 0:02:43 (0.4085 s / it) +train: [10] Summary: lr: 0.000196 loss: 1.3585 (1.3857) grad: 0.0244 (0.0263) +eval (validation): [10] [ 0/63] eta: 0:03:46 time: 3.5937 data: 3.2968 max mem: 3951 +eval (validation): [10] [20/63] eta: 0:00:23 time: 0.3905 data: 0.0044 max mem: 3951 +eval (validation): [10] [40/63] eta: 0:00:10 time: 0.3553 data: 0.0033 max mem: 3951 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3365 data: 0.0035 max mem: 3951 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3328 data: 0.0035 max mem: 3951 +eval (validation): [10] Total time: 0:00:26 (0.4180 s / it) +cv: [10] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.190 acc: 0.957 f1: 0.953 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:23:11 lr: nan time: 3.4787 data: 3.2288 max mem: 3951 +train: [11] [ 20/400] eta: 0:03:38 lr: 0.000195 loss: 1.3565 (1.3616) grad: 0.0242 (0.0256) time: 0.4289 data: 0.0033 max mem: 3951 +train: [11] [ 40/400] eta: 0:02:54 lr: 0.000193 loss: 1.3711 (1.3707) grad: 0.0257 (0.0261) time: 0.3931 data: 0.0033 max mem: 3951 +train: [11] [ 60/400] eta: 0:02:32 lr: 0.000192 loss: 1.3864 (1.3712) grad: 0.0253 (0.0260) time: 0.3716 data: 0.0034 max mem: 3951 +train: [11] [ 80/400] eta: 0:02:16 lr: 0.000190 loss: 1.3864 (1.3744) grad: 0.0252 (0.0259) time: 0.3650 data: 0.0033 max mem: 3951 +train: [11] [100/400] eta: 0:02:05 lr: 0.000189 loss: 1.3620 (1.3660) grad: 0.0256 (0.0261) time: 0.3852 data: 0.0033 max mem: 3951 +train: [11] [120/400] eta: 0:01:57 lr: 0.000187 loss: 1.3495 (1.3647) grad: 0.0258 (0.0261) time: 0.4127 data: 0.0040 max mem: 3951 +train: [11] [140/400] eta: 0:01:47 lr: 0.000186 loss: 1.3696 (1.3659) grad: 0.0260 (0.0262) time: 0.3867 data: 0.0033 max mem: 3951 +train: [11] [160/400] eta: 0:01:38 lr: 0.000184 loss: 1.3554 (1.3621) grad: 0.0258 (0.0261) time: 0.3764 data: 0.0034 max mem: 3951 +train: [11] [180/400] eta: 0:01:28 lr: 0.000183 loss: 1.3569 (1.3639) grad: 0.0253 (0.0260) time: 0.3538 data: 0.0036 max mem: 3951 +train: [11] [200/400] eta: 0:01:19 lr: 0.000181 loss: 1.3773 (1.3643) grad: 0.0253 (0.0259) time: 0.3658 data: 0.0034 max mem: 3951 +train: [11] [220/400] eta: 0:01:11 lr: 0.000180 loss: 1.3693 (1.3658) grad: 0.0249 (0.0259) time: 0.3686 data: 0.0037 max mem: 3951 +train: [11] [240/400] eta: 0:01:03 lr: 0.000178 loss: 1.3594 (1.3639) grad: 0.0262 (0.0260) time: 0.3642 data: 0.0033 max mem: 3951 +train: [11] [260/400] eta: 0:00:54 lr: 0.000177 loss: 1.3422 (1.3634) grad: 0.0261 (0.0259) time: 0.3743 data: 0.0033 max mem: 3951 +train: [11] [280/400] eta: 0:00:46 lr: 0.000175 loss: 1.3422 (1.3616) grad: 0.0259 (0.0260) time: 0.3711 data: 0.0034 max mem: 3951 +train: [11] [300/400] eta: 0:00:40 lr: 0.000174 loss: 1.3130 (1.3580) grad: 0.0261 (0.0260) time: 0.5289 data: 0.1902 max mem: 3951 +train: [11] [320/400] eta: 0:00:31 lr: 0.000172 loss: 1.3312 (1.3568) grad: 0.0253 (0.0259) time: 0.3753 data: 0.0120 max mem: 3951 +train: [11] [340/400] eta: 0:00:23 lr: 0.000170 loss: 1.3360 (1.3548) grad: 0.0242 (0.0259) time: 0.3716 data: 0.0043 max mem: 3951 +train: [11] [360/400] eta: 0:00:15 lr: 0.000169 loss: 1.3331 (1.3547) grad: 0.0243 (0.0259) time: 0.3553 data: 0.0034 max mem: 3951 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 1.3419 (1.3541) grad: 0.0259 (0.0259) time: 0.3851 data: 0.0034 max mem: 3951 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 1.3419 (1.3536) grad: 0.0259 (0.0259) time: 0.3670 data: 0.0034 max mem: 3951 +train: [11] Total time: 0:02:37 (0.3931 s / it) +train: [11] Summary: lr: 0.000166 loss: 1.3419 (1.3536) grad: 0.0259 (0.0259) +eval (validation): [11] [ 0/63] eta: 0:03:46 time: 3.5908 data: 3.3386 max mem: 3951 +eval (validation): [11] [20/63] eta: 0:00:23 time: 0.3861 data: 0.0039 max mem: 3951 +eval (validation): [11] [40/63] eta: 0:00:10 time: 0.3600 data: 0.0034 max mem: 3951 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3341 data: 0.0032 max mem: 3951 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3315 data: 0.0032 max mem: 3951 +eval (validation): [11] Total time: 0:00:26 (0.4145 s / it) +cv: [11] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.187 acc: 0.959 f1: 0.953 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:23:33 lr: nan time: 3.5339 data: 3.2893 max mem: 3951 +train: [12] [ 20/400] eta: 0:03:19 lr: 0.000164 loss: 1.3439 (1.3479) grad: 0.0251 (0.0255) time: 0.3740 data: 0.0047 max mem: 3951 +train: [12] [ 40/400] eta: 0:02:41 lr: 0.000163 loss: 1.3381 (1.3463) grad: 0.0252 (0.0254) time: 0.3702 data: 0.0034 max mem: 3951 +train: [12] [ 60/400] eta: 0:02:22 lr: 0.000161 loss: 1.3317 (1.3402) grad: 0.0248 (0.0254) time: 0.3544 data: 0.0030 max mem: 3951 +train: [12] [ 80/400] eta: 0:02:09 lr: 0.000160 loss: 1.3383 (1.3387) grad: 0.0248 (0.0253) time: 0.3599 data: 0.0035 max mem: 3951 +train: [12] [100/400] eta: 0:01:58 lr: 0.000158 loss: 1.3305 (1.3342) grad: 0.0254 (0.0256) time: 0.3610 data: 0.0036 max mem: 3951 +train: [12] [120/400] eta: 0:01:48 lr: 0.000156 loss: 1.3301 (1.3344) grad: 0.0263 (0.0257) time: 0.3507 data: 0.0032 max mem: 3951 +train: [12] [140/400] eta: 0:01:40 lr: 0.000155 loss: 1.3432 (1.3346) grad: 0.0246 (0.0255) time: 0.3794 data: 0.0033 max mem: 3951 +train: [12] [160/400] eta: 0:01:32 lr: 0.000153 loss: 1.3297 (1.3333) grad: 0.0251 (0.0257) time: 0.3785 data: 0.0034 max mem: 3951 +train: [12] [180/400] eta: 0:01:24 lr: 0.000152 loss: 1.3329 (1.3335) grad: 0.0252 (0.0256) time: 0.3533 data: 0.0032 max mem: 3951 +train: [12] [200/400] eta: 0:01:15 lr: 0.000150 loss: 1.3366 (1.3349) grad: 0.0246 (0.0256) time: 0.3567 data: 0.0033 max mem: 3951 +train: [12] [220/400] eta: 0:01:08 lr: 0.000149 loss: 1.3182 (1.3344) grad: 0.0250 (0.0256) time: 0.3611 data: 0.0036 max mem: 3951 +train: [12] [240/400] eta: 0:01:00 lr: 0.000147 loss: 1.3376 (1.3355) grad: 0.0246 (0.0255) time: 0.3684 data: 0.0031 max mem: 3951 +train: [12] [260/400] eta: 0:00:52 lr: 0.000145 loss: 1.3336 (1.3341) grad: 0.0247 (0.0255) time: 0.3854 data: 0.0034 max mem: 3951 +train: [12] [280/400] eta: 0:00:45 lr: 0.000144 loss: 1.3241 (1.3357) grad: 0.0251 (0.0255) time: 0.3883 data: 0.0034 max mem: 3951 +train: [12] [300/400] eta: 0:00:39 lr: 0.000142 loss: 1.3616 (1.3369) grad: 0.0247 (0.0254) time: 0.5550 data: 0.1969 max mem: 3951 +train: [12] [320/400] eta: 0:00:31 lr: 0.000141 loss: 1.3299 (1.3348) grad: 0.0248 (0.0254) time: 0.3816 data: 0.0040 max mem: 3951 +train: [12] [340/400] eta: 0:00:23 lr: 0.000139 loss: 1.3112 (1.3334) grad: 0.0253 (0.0254) time: 0.3953 data: 0.0021 max mem: 3951 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 1.3212 (1.3331) grad: 0.0254 (0.0254) time: 0.3626 data: 0.0032 max mem: 3951 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 1.3317 (1.3320) grad: 0.0261 (0.0255) time: 0.3703 data: 0.0034 max mem: 3951 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 1.3267 (1.3314) grad: 0.0252 (0.0254) time: 0.3767 data: 0.0036 max mem: 3951 +train: [12] Total time: 0:02:34 (0.3873 s / it) +train: [12] Summary: lr: 0.000134 loss: 1.3267 (1.3314) grad: 0.0252 (0.0254) +eval (validation): [12] [ 0/63] eta: 0:03:50 time: 3.6650 data: 3.3750 max mem: 3951 +eval (validation): [12] [20/63] eta: 0:00:23 time: 0.3815 data: 0.0029 max mem: 3951 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3576 data: 0.0039 max mem: 3951 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3407 data: 0.0034 max mem: 3951 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3393 data: 0.0033 max mem: 3951 +eval (validation): [12] Total time: 0:00:26 (0.4158 s / it) +cv: [12] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.178 acc: 0.963 f1: 0.958 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:23:30 lr: nan time: 3.5262 data: 3.2429 max mem: 3951 +train: [13] [ 20/400] eta: 0:03:33 lr: 0.000133 loss: 1.3395 (1.3411) grad: 0.0234 (0.0238) time: 0.4131 data: 0.0045 max mem: 3951 +train: [13] [ 40/400] eta: 0:02:48 lr: 0.000131 loss: 1.3395 (1.3246) grad: 0.0244 (0.0245) time: 0.3723 data: 0.0030 max mem: 3951 +train: [13] [ 60/400] eta: 0:02:28 lr: 0.000130 loss: 1.2849 (1.3148) grad: 0.0250 (0.0251) time: 0.3725 data: 0.0035 max mem: 3951 +train: [13] [ 80/400] eta: 0:02:13 lr: 0.000128 loss: 1.2849 (1.3101) grad: 0.0254 (0.0251) time: 0.3587 data: 0.0033 max mem: 3951 +train: [13] [100/400] eta: 0:02:03 lr: 0.000127 loss: 1.3265 (1.3131) grad: 0.0245 (0.0251) time: 0.3812 data: 0.0035 max mem: 3951 +train: [13] [120/400] eta: 0:01:52 lr: 0.000125 loss: 1.3008 (1.3107) grad: 0.0245 (0.0252) time: 0.3519 data: 0.0034 max mem: 3951 +train: [13] [140/400] eta: 0:01:43 lr: 0.000124 loss: 1.2983 (1.3106) grad: 0.0249 (0.0251) time: 0.3804 data: 0.0037 max mem: 3951 +train: [13] [160/400] eta: 0:01:34 lr: 0.000122 loss: 1.2988 (1.3094) grad: 0.0255 (0.0252) time: 0.3674 data: 0.0035 max mem: 3951 +train: [13] [180/400] eta: 0:01:26 lr: 0.000120 loss: 1.2803 (1.3073) grad: 0.0255 (0.0253) time: 0.3879 data: 0.0036 max mem: 3951 +train: [13] [200/400] eta: 0:01:18 lr: 0.000119 loss: 1.2798 (1.3041) grad: 0.0255 (0.0254) time: 0.3870 data: 0.0034 max mem: 3951 +train: [13] [220/400] eta: 0:01:10 lr: 0.000117 loss: 1.2965 (1.3072) grad: 0.0255 (0.0254) time: 0.3621 data: 0.0034 max mem: 3951 +train: [13] [240/400] eta: 0:01:02 lr: 0.000116 loss: 1.3106 (1.3077) grad: 0.0252 (0.0253) time: 0.3586 data: 0.0034 max mem: 3951 +train: [13] [260/400] eta: 0:00:53 lr: 0.000114 loss: 1.3045 (1.3082) grad: 0.0250 (0.0253) time: 0.3599 data: 0.0032 max mem: 3951 +train: [13] [280/400] eta: 0:00:46 lr: 0.000113 loss: 1.3045 (1.3085) grad: 0.0250 (0.0253) time: 0.3865 data: 0.0035 max mem: 3951 +train: [13] [300/400] eta: 0:00:39 lr: 0.000111 loss: 1.3075 (1.3094) grad: 0.0248 (0.0253) time: 0.5330 data: 0.1918 max mem: 3951 +train: [13] [320/400] eta: 0:00:31 lr: 0.000110 loss: 1.3265 (1.3101) grad: 0.0247 (0.0253) time: 0.3678 data: 0.0043 max mem: 3951 +train: [13] [340/400] eta: 0:00:23 lr: 0.000108 loss: 1.3112 (1.3107) grad: 0.0246 (0.0254) time: 0.3649 data: 0.0028 max mem: 3951 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 1.3041 (1.3108) grad: 0.0251 (0.0254) time: 0.3676 data: 0.0033 max mem: 3951 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 1.2798 (1.3092) grad: 0.0246 (0.0253) time: 0.3612 data: 0.0033 max mem: 3951 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 1.2849 (1.3082) grad: 0.0239 (0.0253) time: 0.3666 data: 0.0035 max mem: 3951 +train: [13] Total time: 0:02:35 (0.3882 s / it) +train: [13] Summary: lr: 0.000104 loss: 1.2849 (1.3082) grad: 0.0239 (0.0253) +eval (validation): [13] [ 0/63] eta: 0:03:43 time: 3.5539 data: 3.2655 max mem: 3951 +eval (validation): [13] [20/63] eta: 0:00:22 time: 0.3600 data: 0.0041 max mem: 3951 +eval (validation): [13] [40/63] eta: 0:00:10 time: 0.3751 data: 0.0039 max mem: 3951 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3534 data: 0.0034 max mem: 3951 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3510 data: 0.0036 max mem: 3951 +eval (validation): [13] Total time: 0:00:26 (0.4173 s / it) +cv: [13] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.176 acc: 0.964 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:23:36 lr: nan time: 3.5408 data: 3.2339 max mem: 3951 +train: [14] [ 20/400] eta: 0:03:42 lr: 0.000102 loss: 1.3254 (1.3344) grad: 0.0250 (0.0252) time: 0.4371 data: 0.0037 max mem: 3951 +train: [14] [ 40/400] eta: 0:02:52 lr: 0.000101 loss: 1.3072 (1.3154) grad: 0.0245 (0.0251) time: 0.3694 data: 0.0033 max mem: 3951 +train: [14] [ 60/400] eta: 0:02:29 lr: 0.000099 loss: 1.2860 (1.3046) grad: 0.0247 (0.0251) time: 0.3546 data: 0.0033 max mem: 3951 +train: [14] [ 80/400] eta: 0:02:14 lr: 0.000098 loss: 1.2983 (1.3060) grad: 0.0252 (0.0253) time: 0.3647 data: 0.0033 max mem: 3951 +train: [14] [100/400] eta: 0:02:03 lr: 0.000096 loss: 1.3178 (1.3082) grad: 0.0252 (0.0252) time: 0.3766 data: 0.0036 max mem: 3951 +train: [14] [120/400] eta: 0:01:53 lr: 0.000095 loss: 1.2860 (1.3026) grad: 0.0257 (0.0254) time: 0.3645 data: 0.0033 max mem: 3951 +train: [14] [140/400] eta: 0:01:43 lr: 0.000093 loss: 1.2558 (1.2960) grad: 0.0257 (0.0254) time: 0.3586 data: 0.0031 max mem: 3951 +train: [14] [160/400] eta: 0:01:34 lr: 0.000092 loss: 1.2713 (1.2964) grad: 0.0254 (0.0254) time: 0.3717 data: 0.0034 max mem: 3951 +train: [14] [180/400] eta: 0:01:25 lr: 0.000090 loss: 1.2650 (1.2941) grad: 0.0255 (0.0254) time: 0.3582 data: 0.0032 max mem: 3951 +train: [14] [200/400] eta: 0:01:17 lr: 0.000089 loss: 1.2927 (1.2964) grad: 0.0243 (0.0254) time: 0.3684 data: 0.0031 max mem: 3951 +train: [14] [220/400] eta: 0:01:09 lr: 0.000088 loss: 1.3010 (1.2968) grad: 0.0243 (0.0253) time: 0.3766 data: 0.0034 max mem: 3951 +train: [14] [240/400] eta: 0:01:01 lr: 0.000086 loss: 1.2721 (1.2944) grad: 0.0248 (0.0253) time: 0.3836 data: 0.0034 max mem: 3951 +train: [14] [260/400] eta: 0:00:54 lr: 0.000085 loss: 1.2832 (1.2956) grad: 0.0238 (0.0253) time: 0.3907 data: 0.0033 max mem: 3951 +train: [14] [280/400] eta: 0:00:46 lr: 0.000083 loss: 1.2876 (1.2951) grad: 0.0238 (0.0253) time: 0.3783 data: 0.0034 max mem: 3951 +train: [14] [300/400] eta: 0:00:39 lr: 0.000082 loss: 1.2876 (1.2953) grad: 0.0239 (0.0252) time: 0.5681 data: 0.1958 max mem: 3951 +train: [14] [320/400] eta: 0:00:31 lr: 0.000081 loss: 1.2892 (1.2947) grad: 0.0244 (0.0252) time: 0.3892 data: 0.0033 max mem: 3951 +train: [14] [340/400] eta: 0:00:23 lr: 0.000079 loss: 1.2813 (1.2948) grad: 0.0243 (0.0252) time: 0.3745 data: 0.0035 max mem: 3951 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 1.2813 (1.2939) grad: 0.0251 (0.0252) time: 0.3919 data: 0.0033 max mem: 3951 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 1.3000 (1.2949) grad: 0.0251 (0.0251) time: 0.3695 data: 0.0036 max mem: 3951 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 1.2754 (1.2935) grad: 0.0240 (0.0251) time: 0.3754 data: 0.0036 max mem: 3951 +train: [14] Total time: 0:02:37 (0.3942 s / it) +train: [14] Summary: lr: 0.000075 loss: 1.2754 (1.2935) grad: 0.0240 (0.0251) +eval (validation): [14] [ 0/63] eta: 0:03:56 time: 3.7488 data: 3.4278 max mem: 3951 +eval (validation): [14] [20/63] eta: 0:00:24 time: 0.4030 data: 0.0029 max mem: 3951 +eval (validation): [14] [40/63] eta: 0:00:10 time: 0.3779 data: 0.0032 max mem: 3951 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3455 data: 0.0032 max mem: 3951 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3423 data: 0.0031 max mem: 3951 +eval (validation): [14] Total time: 0:00:27 (0.4325 s / it) +cv: [14] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.174 acc: 0.962 f1: 0.958 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:44 lr: nan time: 3.5622 data: 3.3277 max mem: 3951 +train: [15] [ 20/400] eta: 0:03:21 lr: 0.000074 loss: 1.2844 (1.2946) grad: 0.0253 (0.0254) time: 0.3777 data: 0.0039 max mem: 3951 +train: [15] [ 40/400] eta: 0:02:43 lr: 0.000072 loss: 1.2918 (1.2961) grad: 0.0246 (0.0248) time: 0.3762 data: 0.0027 max mem: 3951 +train: [15] [ 60/400] eta: 0:02:25 lr: 0.000071 loss: 1.2946 (1.2933) grad: 0.0241 (0.0252) time: 0.3763 data: 0.0034 max mem: 3951 +train: [15] [ 80/400] eta: 0:02:12 lr: 0.000070 loss: 1.2946 (1.2914) grad: 0.0256 (0.0253) time: 0.3680 data: 0.0032 max mem: 3951 +train: [15] [100/400] eta: 0:02:02 lr: 0.000068 loss: 1.2810 (1.2876) grad: 0.0255 (0.0253) time: 0.3821 data: 0.0035 max mem: 3951 +train: [15] [120/400] eta: 0:01:52 lr: 0.000067 loss: 1.2810 (1.2871) grad: 0.0247 (0.0252) time: 0.3705 data: 0.0034 max mem: 3951 +train: [15] [140/400] eta: 0:01:43 lr: 0.000066 loss: 1.2713 (1.2862) grad: 0.0247 (0.0252) time: 0.3665 data: 0.0034 max mem: 3951 +train: [15] [160/400] eta: 0:01:34 lr: 0.000064 loss: 1.2853 (1.2893) grad: 0.0247 (0.0251) time: 0.3676 data: 0.0033 max mem: 3951 +train: [15] [180/400] eta: 0:01:25 lr: 0.000063 loss: 1.2960 (1.2885) grad: 0.0246 (0.0251) time: 0.3578 data: 0.0034 max mem: 3951 +train: [15] [200/400] eta: 0:01:17 lr: 0.000062 loss: 1.2903 (1.2898) grad: 0.0250 (0.0251) time: 0.3667 data: 0.0035 max mem: 3951 +train: [15] [220/400] eta: 0:01:09 lr: 0.000061 loss: 1.2923 (1.2889) grad: 0.0246 (0.0251) time: 0.3783 data: 0.0033 max mem: 3951 +train: [15] [240/400] eta: 0:01:01 lr: 0.000059 loss: 1.2923 (1.2899) grad: 0.0246 (0.0251) time: 0.3974 data: 0.0033 max mem: 3951 +train: [15] [260/400] eta: 0:00:54 lr: 0.000058 loss: 1.2794 (1.2902) grad: 0.0245 (0.0250) time: 0.3812 data: 0.0031 max mem: 3951 +train: [15] [280/400] eta: 0:00:46 lr: 0.000057 loss: 1.2615 (1.2898) grad: 0.0235 (0.0249) time: 0.3886 data: 0.0031 max mem: 3951 +train: [15] [300/400] eta: 0:00:39 lr: 0.000056 loss: 1.2750 (1.2905) grad: 0.0239 (0.0249) time: 0.5673 data: 0.1997 max mem: 3951 +train: [15] [320/400] eta: 0:00:31 lr: 0.000054 loss: 1.2622 (1.2885) grad: 0.0239 (0.0249) time: 0.3943 data: 0.0029 max mem: 3951 +train: [15] [340/400] eta: 0:00:23 lr: 0.000053 loss: 1.2678 (1.2879) grad: 0.0242 (0.0249) time: 0.3955 data: 0.0057 max mem: 3951 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 1.2763 (1.2879) grad: 0.0243 (0.0249) time: 0.4027 data: 0.0037 max mem: 3951 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 1.2753 (1.2872) grad: 0.0243 (0.0249) time: 0.3721 data: 0.0034 max mem: 3951 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 1.2785 (1.2874) grad: 0.0242 (0.0249) time: 0.3705 data: 0.0036 max mem: 3951 +train: [15] Total time: 0:02:38 (0.3961 s / it) +train: [15] Summary: lr: 0.000050 loss: 1.2785 (1.2874) grad: 0.0242 (0.0249) +eval (validation): [15] [ 0/63] eta: 0:03:53 time: 3.7003 data: 3.3946 max mem: 3951 +eval (validation): [15] [20/63] eta: 0:00:25 time: 0.4423 data: 0.0035 max mem: 3951 +eval (validation): [15] [40/63] eta: 0:00:11 time: 0.3685 data: 0.0036 max mem: 3951 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3358 data: 0.0033 max mem: 3951 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3329 data: 0.0032 max mem: 3951 +eval (validation): [15] Total time: 0:00:27 (0.4374 s / it) +cv: [15] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.173 acc: 0.965 f1: 0.960 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:23:56 lr: nan time: 3.5919 data: 3.3558 max mem: 3951 +train: [16] [ 20/400] eta: 0:03:27 lr: 0.000048 loss: 1.2907 (1.3079) grad: 0.0219 (0.0225) time: 0.3943 data: 0.0058 max mem: 3951 +train: [16] [ 40/400] eta: 0:02:47 lr: 0.000047 loss: 1.2851 (1.2838) grad: 0.0235 (0.0238) time: 0.3776 data: 0.0033 max mem: 3951 +train: [16] [ 60/400] eta: 0:02:28 lr: 0.000046 loss: 1.2850 (1.2789) grad: 0.0248 (0.0245) time: 0.3769 data: 0.0034 max mem: 3951 +train: [16] [ 80/400] eta: 0:02:12 lr: 0.000045 loss: 1.3037 (1.2909) grad: 0.0245 (0.0245) time: 0.3544 data: 0.0034 max mem: 3951 +train: [16] [100/400] eta: 0:02:01 lr: 0.000044 loss: 1.2907 (1.2872) grad: 0.0243 (0.0245) time: 0.3709 data: 0.0032 max mem: 3951 +train: [16] [120/400] eta: 0:01:52 lr: 0.000043 loss: 1.2654 (1.2811) grad: 0.0243 (0.0246) time: 0.3701 data: 0.0032 max mem: 3951 +train: [16] [140/400] eta: 0:01:43 lr: 0.000042 loss: 1.2654 (1.2818) grad: 0.0248 (0.0248) time: 0.3784 data: 0.0033 max mem: 3951 +train: [16] [160/400] eta: 0:01:34 lr: 0.000041 loss: 1.2937 (1.2826) grad: 0.0256 (0.0249) time: 0.3530 data: 0.0033 max mem: 3951 +train: [16] [180/400] eta: 0:01:25 lr: 0.000040 loss: 1.2937 (1.2824) grad: 0.0246 (0.0248) time: 0.3497 data: 0.0033 max mem: 3951 +train: [16] [200/400] eta: 0:01:17 lr: 0.000039 loss: 1.2653 (1.2820) grad: 0.0234 (0.0248) time: 0.3740 data: 0.0032 max mem: 3951 +train: [16] [220/400] eta: 0:01:09 lr: 0.000038 loss: 1.2583 (1.2811) grad: 0.0242 (0.0248) time: 0.3723 data: 0.0032 max mem: 3951 +train: [16] [240/400] eta: 0:01:01 lr: 0.000036 loss: 1.2608 (1.2820) grad: 0.0252 (0.0249) time: 0.3711 data: 0.0032 max mem: 3951 +train: [16] [260/400] eta: 0:00:53 lr: 0.000035 loss: 1.2666 (1.2805) grad: 0.0246 (0.0249) time: 0.3754 data: 0.0033 max mem: 3951 +train: [16] [280/400] eta: 0:00:45 lr: 0.000034 loss: 1.2532 (1.2791) grad: 0.0233 (0.0248) time: 0.3719 data: 0.0035 max mem: 3951 +train: [16] [300/400] eta: 0:00:39 lr: 0.000033 loss: 1.2590 (1.2788) grad: 0.0233 (0.0248) time: 0.5918 data: 0.1954 max mem: 3951 +train: [16] [320/400] eta: 0:00:31 lr: 0.000032 loss: 1.2935 (1.2796) grad: 0.0247 (0.0248) time: 0.3785 data: 0.0034 max mem: 3951 +train: [16] [340/400] eta: 0:00:23 lr: 0.000031 loss: 1.2864 (1.2794) grad: 0.0244 (0.0248) time: 0.3781 data: 0.0032 max mem: 3951 +train: [16] [360/400] eta: 0:00:15 lr: 0.000031 loss: 1.2850 (1.2789) grad: 0.0243 (0.0248) time: 0.4065 data: 0.0036 max mem: 3951 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 1.2877 (1.2791) grad: 0.0249 (0.0249) time: 0.3603 data: 0.0032 max mem: 3951 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 1.2877 (1.2800) grad: 0.0253 (0.0249) time: 0.3676 data: 0.0035 max mem: 3951 +train: [16] Total time: 0:02:36 (0.3919 s / it) +train: [16] Summary: lr: 0.000029 loss: 1.2877 (1.2800) grad: 0.0253 (0.0249) +eval (validation): [16] [ 0/63] eta: 0:03:49 time: 3.6350 data: 3.3586 max mem: 3951 +eval (validation): [16] [20/63] eta: 0:00:23 time: 0.3818 data: 0.0041 max mem: 3951 +eval (validation): [16] [40/63] eta: 0:00:10 time: 0.3754 data: 0.0033 max mem: 3951 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3571 data: 0.0033 max mem: 3951 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3385 data: 0.0032 max mem: 3951 +eval (validation): [16] Total time: 0:00:26 (0.4263 s / it) +cv: [16] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.171 acc: 0.964 f1: 0.960 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:24:13 lr: nan time: 3.6337 data: 3.3222 max mem: 3951 +train: [17] [ 20/400] eta: 0:03:30 lr: 0.000028 loss: 1.2646 (1.2776) grad: 0.0253 (0.0250) time: 0.3993 data: 0.0044 max mem: 3951 +train: [17] [ 40/400] eta: 0:02:46 lr: 0.000027 loss: 1.2582 (1.2656) grad: 0.0253 (0.0252) time: 0.3661 data: 0.0036 max mem: 3951 +train: [17] [ 60/400] eta: 0:02:28 lr: 0.000026 loss: 1.2568 (1.2665) grad: 0.0255 (0.0255) time: 0.3889 data: 0.0038 max mem: 3951 +train: [17] [ 80/400] eta: 0:02:12 lr: 0.000025 loss: 1.2880 (1.2751) grad: 0.0254 (0.0254) time: 0.3468 data: 0.0033 max mem: 3951 +train: [17] [100/400] eta: 0:02:02 lr: 0.000024 loss: 1.2917 (1.2758) grad: 0.0249 (0.0254) time: 0.3733 data: 0.0033 max mem: 3951 +train: [17] [120/400] eta: 0:01:51 lr: 0.000023 loss: 1.2807 (1.2759) grad: 0.0249 (0.0253) time: 0.3603 data: 0.0034 max mem: 3951 +train: [17] [140/400] eta: 0:01:42 lr: 0.000023 loss: 1.2918 (1.2779) grad: 0.0246 (0.0252) time: 0.3654 data: 0.0033 max mem: 3951 +train: [17] [160/400] eta: 0:01:33 lr: 0.000022 loss: 1.2953 (1.2792) grad: 0.0246 (0.0251) time: 0.3462 data: 0.0034 max mem: 3951 +train: [17] [180/400] eta: 0:01:25 lr: 0.000021 loss: 1.2728 (1.2797) grad: 0.0247 (0.0251) time: 0.3838 data: 0.0037 max mem: 3951 +train: [17] [200/400] eta: 0:01:17 lr: 0.000020 loss: 1.2606 (1.2768) grad: 0.0253 (0.0251) time: 0.3645 data: 0.0035 max mem: 3951 +train: [17] [220/400] eta: 0:01:09 lr: 0.000019 loss: 1.2607 (1.2786) grad: 0.0242 (0.0250) time: 0.3678 data: 0.0035 max mem: 3951 +train: [17] [240/400] eta: 0:01:01 lr: 0.000019 loss: 1.2776 (1.2773) grad: 0.0249 (0.0251) time: 0.3574 data: 0.0034 max mem: 3951 +train: [17] [260/400] eta: 0:00:53 lr: 0.000018 loss: 1.2632 (1.2759) grad: 0.0249 (0.0250) time: 0.3623 data: 0.0034 max mem: 3951 +train: [17] [280/400] eta: 0:00:45 lr: 0.000017 loss: 1.2850 (1.2778) grad: 0.0236 (0.0250) time: 0.3662 data: 0.0035 max mem: 3951 +train: [17] [300/400] eta: 0:00:39 lr: 0.000016 loss: 1.2961 (1.2808) grad: 0.0242 (0.0249) time: 0.5614 data: 0.1913 max mem: 3951 +train: [17] [320/400] eta: 0:00:31 lr: 0.000016 loss: 1.2779 (1.2797) grad: 0.0235 (0.0249) time: 0.3721 data: 0.0037 max mem: 3951 +train: [17] [340/400] eta: 0:00:23 lr: 0.000015 loss: 1.2673 (1.2799) grad: 0.0239 (0.0249) time: 0.3719 data: 0.0030 max mem: 3951 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 1.2649 (1.2792) grad: 0.0240 (0.0248) time: 0.3698 data: 0.0035 max mem: 3951 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 1.2586 (1.2794) grad: 0.0239 (0.0248) time: 0.3634 data: 0.0034 max mem: 3951 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 1.2810 (1.2792) grad: 0.0235 (0.0247) time: 0.3669 data: 0.0036 max mem: 3951 +train: [17] Total time: 0:02:34 (0.3861 s / it) +train: [17] Summary: lr: 0.000013 loss: 1.2810 (1.2792) grad: 0.0235 (0.0247) +eval (validation): [17] [ 0/63] eta: 0:03:49 time: 3.6473 data: 3.3547 max mem: 3951 +eval (validation): [17] [20/63] eta: 0:00:22 time: 0.3754 data: 0.0041 max mem: 3951 +eval (validation): [17] [40/63] eta: 0:00:10 time: 0.3667 data: 0.0029 max mem: 3951 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3370 data: 0.0035 max mem: 3951 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3344 data: 0.0034 max mem: 3951 +eval (validation): [17] Total time: 0:00:26 (0.4161 s / it) +cv: [17] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.170 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:24:16 lr: nan time: 3.6417 data: 3.3729 max mem: 3951 +train: [18] [ 20/400] eta: 0:03:26 lr: 0.000012 loss: 1.2820 (1.2852) grad: 0.0259 (0.0258) time: 0.3880 data: 0.0037 max mem: 3951 +train: [18] [ 40/400] eta: 0:02:48 lr: 0.000012 loss: 1.2914 (1.2904) grad: 0.0249 (0.0250) time: 0.3869 data: 0.0030 max mem: 3951 +train: [18] [ 60/400] eta: 0:02:29 lr: 0.000011 loss: 1.2602 (1.2754) grad: 0.0249 (0.0254) time: 0.3818 data: 0.0034 max mem: 3951 +train: [18] [ 80/400] eta: 0:02:14 lr: 0.000011 loss: 1.2498 (1.2686) grad: 0.0240 (0.0249) time: 0.3605 data: 0.0034 max mem: 3951 +train: [18] [100/400] eta: 0:02:02 lr: 0.000010 loss: 1.2501 (1.2658) grad: 0.0238 (0.0250) time: 0.3627 data: 0.0034 max mem: 3951 +train: [18] [120/400] eta: 0:01:52 lr: 0.000009 loss: 1.2570 (1.2681) grad: 0.0252 (0.0249) time: 0.3703 data: 0.0034 max mem: 3951 +train: [18] [140/400] eta: 0:01:43 lr: 0.000009 loss: 1.2754 (1.2695) grad: 0.0245 (0.0248) time: 0.3828 data: 0.0033 max mem: 3951 +train: [18] [160/400] eta: 0:01:35 lr: 0.000008 loss: 1.2794 (1.2719) grad: 0.0242 (0.0247) time: 0.3769 data: 0.0035 max mem: 3951 +train: [18] [180/400] eta: 0:01:26 lr: 0.000008 loss: 1.2692 (1.2712) grad: 0.0248 (0.0249) time: 0.3595 data: 0.0034 max mem: 3951 +train: [18] [200/400] eta: 0:01:18 lr: 0.000007 loss: 1.2677 (1.2744) grad: 0.0252 (0.0249) time: 0.3880 data: 0.0035 max mem: 3951 +train: [18] [220/400] eta: 0:01:10 lr: 0.000007 loss: 1.2915 (1.2761) grad: 0.0235 (0.0248) time: 0.3934 data: 0.0035 max mem: 3951 +train: [18] [240/400] eta: 0:01:02 lr: 0.000006 loss: 1.2766 (1.2768) grad: 0.0235 (0.0248) time: 0.3825 data: 0.0036 max mem: 3951 +train: [18] [260/400] eta: 0:00:54 lr: 0.000006 loss: 1.2568 (1.2742) grad: 0.0243 (0.0248) time: 0.3794 data: 0.0035 max mem: 3951 +train: [18] [280/400] eta: 0:00:46 lr: 0.000006 loss: 1.2644 (1.2749) grad: 0.0244 (0.0249) time: 0.3757 data: 0.0035 max mem: 3951 +train: [18] [300/400] eta: 0:00:40 lr: 0.000005 loss: 1.2821 (1.2766) grad: 0.0244 (0.0249) time: 0.5919 data: 0.2190 max mem: 3951 +train: [18] [320/400] eta: 0:00:32 lr: 0.000005 loss: 1.2821 (1.2778) grad: 0.0252 (0.0249) time: 0.3927 data: 0.0031 max mem: 3951 +train: [18] [340/400] eta: 0:00:24 lr: 0.000004 loss: 1.2633 (1.2761) grad: 0.0246 (0.0249) time: 0.4010 data: 0.0032 max mem: 3951 +train: [18] [360/400] eta: 0:00:16 lr: 0.000004 loss: 1.2691 (1.2764) grad: 0.0240 (0.0249) time: 0.3956 data: 0.0035 max mem: 3951 +train: [18] [380/400] eta: 0:00:08 lr: 0.000004 loss: 1.2691 (1.2759) grad: 0.0239 (0.0249) time: 0.3715 data: 0.0033 max mem: 3951 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 1.2571 (1.2752) grad: 0.0249 (0.0249) time: 0.3753 data: 0.0034 max mem: 3951 +train: [18] Total time: 0:02:39 (0.3992 s / it) +train: [18] Summary: lr: 0.000003 loss: 1.2571 (1.2752) grad: 0.0249 (0.0249) +eval (validation): [18] [ 0/63] eta: 0:04:08 time: 3.9431 data: 3.6964 max mem: 3951 +eval (validation): [18] [20/63] eta: 0:00:23 time: 0.3695 data: 0.0031 max mem: 3951 +eval (validation): [18] [40/63] eta: 0:00:10 time: 0.3712 data: 0.0031 max mem: 3951 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3354 data: 0.0034 max mem: 3951 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3302 data: 0.0034 max mem: 3951 +eval (validation): [18] Total time: 0:00:26 (0.4200 s / it) +cv: [18] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.170 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:24:33 lr: nan time: 3.6834 data: 3.3791 max mem: 3951 +train: [19] [ 20/400] eta: 0:03:20 lr: 0.000003 loss: 1.2595 (1.2736) grad: 0.0242 (0.0246) time: 0.3686 data: 0.0040 max mem: 3951 +train: [19] [ 40/400] eta: 0:02:42 lr: 0.000003 loss: 1.2703 (1.2736) grad: 0.0242 (0.0247) time: 0.3726 data: 0.0029 max mem: 3951 +train: [19] [ 60/400] eta: 0:02:23 lr: 0.000002 loss: 1.2838 (1.2814) grad: 0.0239 (0.0245) time: 0.3663 data: 0.0036 max mem: 3951 +train: [19] [ 80/400] eta: 0:02:10 lr: 0.000002 loss: 1.2847 (1.2810) grad: 0.0242 (0.0246) time: 0.3544 data: 0.0034 max mem: 3951 +train: [19] [100/400] eta: 0:01:59 lr: 0.000002 loss: 1.2555 (1.2724) grad: 0.0249 (0.0248) time: 0.3611 data: 0.0034 max mem: 3951 +train: [19] [120/400] eta: 0:01:50 lr: 0.000002 loss: 1.2656 (1.2733) grad: 0.0244 (0.0247) time: 0.3911 data: 0.0034 max mem: 3951 +train: [19] [140/400] eta: 0:01:41 lr: 0.000001 loss: 1.2830 (1.2722) grad: 0.0244 (0.0248) time: 0.3611 data: 0.0035 max mem: 3951 +train: [19] [160/400] eta: 0:01:33 lr: 0.000001 loss: 1.2643 (1.2709) grad: 0.0240 (0.0247) time: 0.3635 data: 0.0033 max mem: 3951 +train: [19] [180/400] eta: 0:01:24 lr: 0.000001 loss: 1.2646 (1.2708) grad: 0.0243 (0.0247) time: 0.3439 data: 0.0032 max mem: 3951 +train: [19] [200/400] eta: 0:01:16 lr: 0.000001 loss: 1.2646 (1.2702) grad: 0.0252 (0.0246) time: 0.3849 data: 0.0033 max mem: 3951 +train: [19] [220/400] eta: 0:01:08 lr: 0.000001 loss: 1.2655 (1.2704) grad: 0.0248 (0.0247) time: 0.3739 data: 0.0034 max mem: 3951 +train: [19] [240/400] eta: 0:01:00 lr: 0.000001 loss: 1.2492 (1.2671) grad: 0.0251 (0.0248) time: 0.3666 data: 0.0033 max mem: 3951 +train: [19] [260/400] eta: 0:00:53 lr: 0.000000 loss: 1.2671 (1.2697) grad: 0.0251 (0.0248) time: 0.3629 data: 0.0035 max mem: 3951 +train: [19] [280/400] eta: 0:00:45 lr: 0.000000 loss: 1.2818 (1.2681) grad: 0.0245 (0.0249) time: 0.3583 data: 0.0035 max mem: 3951 +train: [19] [300/400] eta: 0:00:38 lr: 0.000000 loss: 1.2536 (1.2697) grad: 0.0240 (0.0248) time: 0.5302 data: 0.1909 max mem: 3951 +train: [19] [320/400] eta: 0:00:30 lr: 0.000000 loss: 1.2655 (1.2696) grad: 0.0241 (0.0248) time: 0.3672 data: 0.0038 max mem: 3951 +train: [19] [340/400] eta: 0:00:23 lr: 0.000000 loss: 1.2519 (1.2686) grad: 0.0243 (0.0247) time: 0.3581 data: 0.0030 max mem: 3951 +train: [19] [360/400] eta: 0:00:15 lr: 0.000000 loss: 1.2444 (1.2691) grad: 0.0236 (0.0247) time: 0.3682 data: 0.0036 max mem: 3951 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 1.2420 (1.2687) grad: 0.0233 (0.0246) time: 0.3543 data: 0.0035 max mem: 3951 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 1.2420 (1.2689) grad: 0.0237 (0.0246) time: 0.3616 data: 0.0034 max mem: 3951 +train: [19] Total time: 0:02:32 (0.3820 s / it) +train: [19] Summary: lr: 0.000000 loss: 1.2420 (1.2689) grad: 0.0237 (0.0246) +eval (validation): [19] [ 0/63] eta: 0:03:52 time: 3.6857 data: 3.4086 max mem: 3951 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3431 data: 0.0034 max mem: 3951 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3486 data: 0.0033 max mem: 3951 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3216 data: 0.0031 max mem: 3951 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3193 data: 0.0031 max mem: 3951 +eval (validation): [19] Total time: 0:00:24 (0.3947 s / it) +cv: [19] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.170 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +eval model info: +{"score": 0.9625496031746031, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 19, "is_best": false, "best_score": 0.9645337301587301} +eval (train): [20] [ 0/297] eta: 0:17:29 time: 3.5353 data: 3.2946 max mem: 3951 +eval (train): [20] [ 20/297] eta: 0:02:31 time: 0.3975 data: 0.0052 max mem: 3951 +eval (train): [20] [ 40/297] eta: 0:01:57 time: 0.3632 data: 0.0033 max mem: 3951 +eval (train): [20] [ 60/297] eta: 0:01:41 time: 0.3659 data: 0.0038 max mem: 3951 +eval (train): [20] [ 80/297] eta: 0:01:29 time: 0.3673 data: 0.0037 max mem: 3951 +eval (train): [20] [100/297] eta: 0:01:18 time: 0.3378 data: 0.0030 max mem: 3951 +eval (train): [20] [120/297] eta: 0:01:09 time: 0.3638 data: 0.0035 max mem: 3951 +eval (train): [20] [140/297] eta: 0:01:00 time: 0.3629 data: 0.0036 max mem: 3951 +eval (train): [20] [160/297] eta: 0:00:52 time: 0.3579 data: 0.0036 max mem: 3951 +eval (train): [20] [180/297] eta: 0:00:44 time: 0.3440 data: 0.0035 max mem: 3951 +eval (train): [20] [200/297] eta: 0:00:36 time: 0.3472 data: 0.0035 max mem: 3951 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3722 data: 0.0036 max mem: 3951 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3596 data: 0.0034 max mem: 3951 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3726 data: 0.0035 max mem: 3951 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3674 data: 0.0037 max mem: 3951 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3492 data: 0.0034 max mem: 3951 +eval (train): [20] Total time: 0:01:51 (0.3739 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:39 time: 3.4830 data: 3.2061 max mem: 3951 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.3766 data: 0.0153 max mem: 3951 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3711 data: 0.0034 max mem: 3951 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3494 data: 0.0034 max mem: 3951 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3434 data: 0.0034 max mem: 3951 +eval (validation): [20] Total time: 0:00:26 (0.4199 s / it) +eval (test): [20] [ 0/79] eta: 0:04:51 time: 3.6860 data: 3.3868 max mem: 3951 +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3459 data: 0.0040 max mem: 3951 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3872 data: 0.0033 max mem: 3951 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3625 data: 0.0033 max mem: 3951 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3466 data: 0.0034 max mem: 3951 +eval (test): [20] Total time: 0:00:32 (0.4070 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +eval model info: +{"score": 0.9645337301587301, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 15, "is_best": true, "best_score": 0.9645337301587301} +eval (train): [20] [ 0/297] eta: 0:16:43 time: 3.3790 data: 3.1588 max mem: 3951 +eval (train): [20] [ 20/297] eta: 0:02:19 time: 0.3582 data: 0.0032 max mem: 3951 +eval (train): [20] [ 40/297] eta: 0:01:53 time: 0.3756 data: 0.0035 max mem: 3951 +eval (train): [20] [ 60/297] eta: 0:01:38 time: 0.3679 data: 0.0037 max mem: 3951 +eval (train): [20] [ 80/297] eta: 0:01:27 time: 0.3601 data: 0.0037 max mem: 3951 +eval (train): [20] [100/297] eta: 0:01:17 time: 0.3575 data: 0.0035 max mem: 3951 +eval (train): [20] [120/297] eta: 0:01:08 time: 0.3463 data: 0.0035 max mem: 3951 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3434 data: 0.0033 max mem: 3951 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3638 data: 0.0036 max mem: 3951 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3499 data: 0.0035 max mem: 3951 +eval (train): [20] [200/297] eta: 0:00:36 time: 0.3445 data: 0.0035 max mem: 3951 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3520 data: 0.0036 max mem: 3951 +eval (train): [20] [240/297] eta: 0:00:21 time: 0.3600 data: 0.0035 max mem: 3951 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3758 data: 0.0037 max mem: 3951 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3672 data: 0.0036 max mem: 3951 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3437 data: 0.0038 max mem: 3951 +eval (train): [20] Total time: 0:01:49 (0.3695 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:48 time: 3.6321 data: 3.3892 max mem: 3951 +eval (validation): [20] [20/63] eta: 0:00:22 time: 0.3657 data: 0.0044 max mem: 3951 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3839 data: 0.0036 max mem: 3951 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3465 data: 0.0033 max mem: 3951 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3430 data: 0.0033 max mem: 3951 +eval (validation): [20] Total time: 0:00:26 (0.4201 s / it) +eval (test): [20] [ 0/79] eta: 0:04:47 time: 3.6369 data: 3.3405 max mem: 3951 +eval (test): [20] [20/79] eta: 0:00:30 time: 0.3654 data: 0.0038 max mem: 3951 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3528 data: 0.0035 max mem: 3951 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3663 data: 0.0032 max mem: 3951 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3329 data: 0.0035 max mem: 3951 +eval (test): [20] Total time: 0:00:31 (0.4012 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|--------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | linear | hcpya_task21 | best | 15 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 0.13155 | 0.97879 | 0.0010432 | 0.97816 | 0.0011666 | +| flat_mae | patch | linear | hcpya_task21 | best | 15 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 0.17266 | 0.96453 | 0.0029036 | 0.96016 | 0.00364 | +| flat_mae | patch | linear | hcpya_task21 | best | 15 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 0.19017 | 0.95575 | 0.002821 | 0.94859 | 0.0036013 | + + +done! total time: 1:07:36 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/train_log.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..6359d115bd11cfda73331a4b492f09ad7a63a9c1 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__patch__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.930131013393402, "train/grad": 0.046667127162218096, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.0452783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.04520263671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.04506591796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.044918212890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.04477783203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.04459716796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.044388427734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.04414306640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.043802490234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.043460693359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0430615234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.042532958984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0420166015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.041190185546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.040399169921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0395751953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.038489990234375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.037115478515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.03553466796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.03392822265625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.03186279296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0294482421875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.026561279296875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.023306884765625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.019403076171875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0143115234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.009415283203125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.004488525390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.997239990234375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.98791015625, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.978709716796875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.96983154296875, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.956934814453125, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.94438720703125, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.928397216796875, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.911177978515625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.89101806640625, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.8702545166015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.84550048828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.8113079833984376, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7820172119140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.7541009521484376, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7141375732421875, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.676289367675781, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.628423767089844, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5721612548828126, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.519475555419922, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.4509483337402345, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.3879222869873047, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007081167777068913, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007080847970210016, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007080276352353394, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007079693623818457, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00707909939577803, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0070782566559501, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007077267547138035, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0070762061257846655, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007074880066793412, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007073247605003417, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007071710140444339, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007069246522150934, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007066772186663002, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007063050735741854, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007059220259543508, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007055331664159894, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007050446318462491, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007044071510899812, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0070362295885570345, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007028380404226482, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007018184431362897, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007007094563450664, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0069935817853547634, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006977667415048927, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006959418971091509, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006935059914831072, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006911135611589998, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006887512486428022, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006852883794344962, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0068082383857108655, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006764533331152052, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006722274487838149, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006660265550017357, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006601122375577688, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006525933265220374, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006445889824535697, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0063547933683730665, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00626388356089592, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006160109635675326, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006027723326114938, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00592444809502922, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005834313726518303, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0057185918430332095, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005619370368076488, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005505613890709356, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00538349180133082, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0052764572680462155, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005145670179044828, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005031365618342534, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.043304920196533, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.043053388595581, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.042640447616577, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.042205810546875, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0417890548706055, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0412003993988037, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.040539026260376, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.039769172668457, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0387754440307617, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0376839637756348, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0366146564483643, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0349321365356445, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0332765579223633, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.030770778656006, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.028308868408203, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.025867223739624, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.022576332092285, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.01851224899292, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0136823654174805, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.008875846862793, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0025343894958496, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.995486259460449, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9869863986968994, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9770634174346924, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.965851306915283, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.951213836669922, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9369094371795654, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9229815006256104, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.902665376663208, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.87666654586792, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.851731538772583, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8278391361236572, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7936837673187256, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7612955570220947, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.720564365386963, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.677611827850342, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.628316879272461, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5779945850372314, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.518885374069214, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4378457069396973, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.368509531021118, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.302410364151001, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.208470106124878, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.1200857162475586, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.010301113128662, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.8852617740631104, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.7726891040802002, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.6336469650268555, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.5134354829788208, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06820436507936507, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06870039682539683, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07043650793650794, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0716765873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0716765873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07217261904761904, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07514880952380952, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.078125, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08134920634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0835813492063492, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08556547619047619, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.09126984126984126, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.09821428571428571, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.10863095238095238, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1185515873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.13120039682539683, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.14583333333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.15773809523809523, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.16790674603174602, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17881944444444445, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.18898809523809523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.203125, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.21354166666666666, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.22544642857142858, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22941468253968253, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.23313492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.22817460317460317, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2269345238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.22495039682539683, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22172619047619047, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21726190476190477, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21378968253968253, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.21329365079365079, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2152777777777778, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21924603174603174, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22296626984126985, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22767857142857142, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.23635912698412698, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24776785714285715, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2693452380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.29538690476190477, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.32961309523809523, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.39384920634920634, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.4486607142857143, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.5171130952380952, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.5808531746031746, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6294642857142857, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6805555555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7266865079365079, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03349440035862266, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.033952419270049404, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03515265088651589, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03536882253946151, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03530718639592821, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0355707397859271, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03647565644191787, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.037656308115418285, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.039557470129891865, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0405075642714372, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04107331384193383, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.04252059862012577, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.04495241914336819, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0462301370795369, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04894013142524488, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.052164757917667066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.055721233048522875, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.05310108495806961, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.05084877458480483, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.05185108348835192, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05381889385023022, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05632113606968881, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.05727530352254512, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06074450224532714, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06178776739991529, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06458957711664312, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.06319598560973264, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06400428664726887, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.06394691125507997, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0635817334628587, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.06052026249760846, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.05670901074429255, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.055943805145981705, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.056622737731095475, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.058745265735297134, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.06094329719689403, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.06457491715514807, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.06992902174995373, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.07892220996167344, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.10008888270461756, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1290308735667008, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16937661184474292, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.23757166162711224, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.29064710568278745, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.35082885674250963, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.4077939624877997, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.4622398065458314, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.5308891819542316, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.6138356508168139, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.3879222869873047, "validation/loss_best": 1.5134354829788208, "validation/acc_best": 0.7266865079365079, "validation/f1_best": 0.6138356508168139} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.5634448301792143, "train/grad": 0.041677360497415064, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.040972900390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.040389404296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.03940185546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.038466796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.037481689453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.03606689453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.03450927734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.032796630859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.03046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0280322265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.025474853515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.021566162109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0178076171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.012276611328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.00670654296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.001217041015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.9938916015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.98498046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.97451904296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.964176025390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.950751953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.936007080078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.91849609375, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.898577880859375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.87652587890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.848250732421875, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.821495361328125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7959228515625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.75926513671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.71374267578125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.6709515380859377, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.630599365234375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.5735931396484375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.519820556640625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.4523809814453124, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.381117858886719, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.299402160644531, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2161961364746094, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.119539337158203, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9913600921630858, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8866957855224609, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7920844268798828, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6661632919311524, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.5565509414672851, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4312888717651366, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.301021432876587, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.1935738849639892, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0717164778709412, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.9745051717758179, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007164528674911708, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007161884000524878, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007157386175822467, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.007152905694674701, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007148544355295598, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007142404799815268, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0071352877770550546, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0071274359454400835, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007116434769704938, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007104435167275369, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007092399350367487, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007073866778519004, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007056180238723755, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007030271636322141, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007004238343797624, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006978470152243971, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006944154566153884, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0069026696379296485, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006853253559675068, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006804765113629401, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006741644542198628, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006673202523961664, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006591288107447326, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006497808259446174, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0063947818474844095, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006264427597634494, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006141540389508009, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006026153373531997, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0058662755182012916, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005677193228621036, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005512103589717298, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005369528729934245, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005189731230493635, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005042214590357617, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004881934354780242, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004736341492971406, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004591514100320637, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004459770395187661, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004319885995937511, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004145496286218986, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004007320301607251, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0038828333001583813, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003715698578162119, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0035677565715741366, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003394652873976156, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0032091071887407454, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0030509929009713234, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0028659671038622036, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002713142763241194, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0382111072540283, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.037208318710327, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.035543203353882, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0338525772094727, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0321860313415527, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.029874086380005, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0271897315979004, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.024219036102295, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0202910900115967, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0160562992095947, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0118539333343506, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0054502487182617, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.999086856842041, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9896960258483887, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9804601669311523, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.971351146697998, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.959459066390991, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.944904088973999, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9278957843780518, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9113714694976807, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8900623321533203, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.866994619369507, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.8399808406829834, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.809553384780884, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.7762465476989746, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.7345244884490967, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.695284605026245, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6582725048065186, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.606025218963623, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.541245698928833, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4806549549102783, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4232003688812256, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.341498851776123, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.264385938644409, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.1674976348876953, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.0658674240112305, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.9516894817352295, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.838791012763977, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.7128291130065918, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.5542348623275757, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.4327772855758667, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.3285166025161743, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.1982884407043457, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.0924700498580933, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.9793119430541992, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8703137636184692, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7867698073387146, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6985647082328796, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6328429579734802, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.08159722222222222, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0845734126984127, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.09052579365079365, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.09697420634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.10317460317460317, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.11284722222222222, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.12524801587301587, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.14012896825396826, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.15178571428571427, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1636904761904762, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17336309523809523, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.18427579365079366, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.19593253968253968, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.21180555555555555, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.22023809523809523, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2244543650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.22594246031746032, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22271825396825398, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.21999007936507936, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21825396825396826, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21279761904761904, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.20833333333333334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.20461309523809523, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2041170634920635, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.20634920634920634, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.20758928571428573, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.21205357142857142, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.21552579365079366, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.22371031746031747, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23387896825396826, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.251984126984127, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.27157738095238093, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.30654761904761907, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.35193452380952384, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.41865079365079366, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.4818948412698413, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5443948412698413, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6011904761904762, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6498015873015873, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.703125, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7462797619047619, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7810019841269841, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8139880952380952, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8370535714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.861359126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8797123015873016, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8898809523809523, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8968253968253969, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9030257936507936, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0392862631990956, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.04074560632112421, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.04221602059139077, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.04484540551814608, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.04464503115271711, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.04638307564160448, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.04975575285511925, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.053358041369972534, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05029095104061653, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05006190246992321, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.048804050013214646, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05055300649743941, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05176705882820306, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05468194704386232, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.054803801295108, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05723054893818641, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05699870449818158, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.05579737305228205, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.056681582507328715, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.056836339136089924, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05491547669689718, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.052258656582458964, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.04956577999156709, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04847577955055865, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04992634371477619, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.05032418441133507, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.053363497665948376, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.05697550764697087, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.06274401748100993, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.07059291407198864, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08793683625435789, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.10846660453536523, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.14803377763802908, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19902395527104835, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.26304944646948564, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.32169882133603583, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.3751595823190296, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.42638650037645576, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.47572913070585043, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5586248872867684, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6404498685373609, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7062674805924722, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.7657458997548283, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8024288847098924, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8400344656637667, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8640882493428743, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8771500331692899, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8852898076827035, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8933128700099928, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.9745051717758179, "validation/loss_best": 0.6328429579734802, "validation/acc_best": 0.9030257936507936, "validation/f1_best": 0.8933128700099928} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.2555999767780306, "train/grad": 0.037382756592705846, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.034688720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.03313720703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.030491943359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.027843017578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.025352783203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0216943359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.017674560546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.013114013671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0071923828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.000712890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.994378662109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.98478271484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.975225830078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.961356201171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.947691650390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.93454833984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.917408447265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.896572265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.872716064453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.849747314453125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.820499267578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.78930908203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.75310791015625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.7128656005859373, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.6692437744140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.6143994140625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.5632281494140625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.514559326171875, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4453945922851563, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.358814392089844, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2775439453125, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.200703125, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0932652282714845, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9942185974121094, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8740659332275391, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7533412170410156, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6240024185180664, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5021021270751953, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3728311920166016, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.2192557621002198, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.10773362159729, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0161710214614867, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9064811515808106, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8207942700386047, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7326420021057128, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6504588449001312, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5888101583719254, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5247635424137116, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.47746643841266634, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007034113833215088, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007026583740953356, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007014512456953526, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0070018628961406645, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0069892137963324785, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006971449533011764, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006951255460735411, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006929411892779172, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006901275038253516, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00687105399556458, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0068412920110858975, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0067954984260722995, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006750284202862531, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006683902794029564, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0066185888345353305, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006555378071498126, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006473908324260265, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006375187495723367, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006262324233539403, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006153859421610832, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006018170295283199, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005874884044751525, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005713202860206366, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005542005188763141, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005368276212830096, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005172978256596252, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005013833721168339, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004883516728878021, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004728251082124189, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004570835049962625, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004447540835244581, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004342848011292517, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004205651361262426, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004082100063096732, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003931891663232818, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0037784716091118753, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0036101092502940444, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003447737384121865, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0032707803649827836, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003053008266724646, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0028890130168292673, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.002749728971393779, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002576334896730259, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0024359273724257947, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002285857712267898, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.002140763210481964, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0020283125480636956, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001907289358205162, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00181513553194236, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0299315452575684, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.027675151824951, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0239715576171875, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0203094482421875, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0166475772857666, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.011579751968384, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0058205127716064, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9994375705718994, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9910097122192383, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.982034921646118, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9731686115264893, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9598042964935303, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.946756362915039, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.92771577835083, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.909247636795044, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.89137864112854, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8683907985687256, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.840820789337158, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8093626499176025, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.779461145401001, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7417213916778564, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.7017784118652344, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6558902263641357, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.605130672454834, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5501492023468018, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4815118312835693, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4167606830596924, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.355195999145508, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.267604351043701, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.1585958003997803, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.0574381351470947, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.963714361190796, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.835979700088501, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.7219687700271606, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.5888274908065796, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.4605015516281128, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.3290613889694214, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.210620641708374, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.0905557870864868, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9550037980079651, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.8613290786743164, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.7869673371315002, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.7011783123016357, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6363427639007568, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5713154673576355, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5120470523834229, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.468295693397522, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4230812191963196, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3899587094783783, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.11135912698412699, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.12276785714285714, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1416170634920635, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.15128968253968253, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.16170634920634921, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17336309523809523, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.18080357142857142, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.19543650793650794, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2088293650793651, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21999007936507936, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.22569444444444445, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22891865079365079, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22842261904761904, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22470238095238096, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.22247023809523808, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.22023809523809523, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.21651785714285715, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21378968253968253, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2113095238095238, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21180555555555555, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21378968253968253, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2177579365079365, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2244543650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23189484126984128, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2435515873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25967261904761907, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.28000992063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.30753968253968256, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.359375, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.435515873015873, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.4937996031746032, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5458829365079365, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6145833333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6587301587301587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7053571428571429, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7537202380952381, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7914186507936508, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8211805555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8487103174603174, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8747519841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8881448412698413, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8958333333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9025297619047619, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9087301587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9164186507936508, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9221230158730159, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9255952380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9305555555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9340277777777778, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.045981927202150254, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05001352143620487, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.053631649858278625, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05130618427504705, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05010546587800127, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.049298678674499365, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.049178796831036375, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.053028542076312496, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05498273124092632, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05591014770875079, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05759548764258662, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0580218730660432, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05816897201640604, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05868398969245425, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05884768081910337, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05895095471311428, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05750364985460807, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0564414468105979, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0539088978819821, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.05394630245469183, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05477002015329988, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.057246675230943456, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06146082898985069, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06752811893169228, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.07585500904653372, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.08860149400624666, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1115897911478179, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.14414883092840367, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2023059533591116, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.27754300016028527, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3286610794416571, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.3737733117333799, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4381779417102261, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.4900621617561072, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5671629719612727, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.6566638331450599, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7331441782575411, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.7805064390326277, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8237789406675515, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8597881743666291, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8742606948030724, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8839593401625274, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.893220039229597, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8999262969033995, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9076724207065248, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.914039009130092, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9181360102624877, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9231587115607354, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.926680628403815, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.47746643841266634, "validation/loss_best": 0.3899587094783783, "validation/acc_best": 0.9340277777777778, "validation/f1_best": 0.926680628403815} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.0278813928365707, "train/grad": 0.034916616547852754, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.025013427734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.02198974609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.017060546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.012110595703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.007232666015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.000462646484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.9928662109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.9843896484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.973310546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.961446533203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.94995361328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.93260498046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.915841064453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.891402587890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.868179931640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.845743408203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.817122802734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.783135986328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.744656982421875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7083758544921874, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6626849365234375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.61446533203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5589825439453127, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.497313232421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.430107421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3458590698242188, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.266304931640625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.191028747558594, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.085294189453125, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9567549133300781, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8408462524414062, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.73649658203125, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.5985918426513672, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.479943733215332, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.345887622833252, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.2215078735351563, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.0983502388000488, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9909877014160157, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8856211090087891, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.7704870104789734, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6930652523040771, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6329760789871216, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5644811481237412, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5134094327688217, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.462543762922287, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4165365406870842, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.38263796642422676, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3478416663408279, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.32228318266570566, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007041444240603596, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.007026621357072145, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.007002079563681036, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006977991149760783, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006955464887432754, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006924025823827833, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0068885813280940055, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006848044446669519, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006794636903796345, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006737984314095229, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006682833661325276, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006600084097590298, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006520175784826279, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00640441874274984, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006294327338691801, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006189283828716725, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006055271981749683, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005899257760029286, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00572721975389868, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005572281340137124, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005388908726163208, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005213422009255737, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005037297341041267, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004872447614325211, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004724996673176065, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004574408525368199, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004454329187283292, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004351106116082519, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004213911129627376, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004049505770672113, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003900374418590218, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003763960991054773, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003580194440437481, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00341906723799184, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003232559240423143, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0030543912027496843, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002871622977545485, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0027058514440432193, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002536326419794932, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0023421091737691312, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0022057510551530867, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.002096631337190047, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0019685426191426813, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001870762649923563, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0017711627733660862, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0016792363673448563, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0016096013539936393, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015360594767844305, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0014803882141131907, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0183918476104736, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0145106315612793, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0080811977386475, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0017404556274414, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.995445728302002, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9867498874664307, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9769859313964844, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.966167449951172, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9520652294158936, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.937173366546631, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.92264986038208, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9010000228881836, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.880141019821167, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8501763343811035, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.821660280227661, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7944416999816895, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.759958028793335, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.719325065612793, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.673675775527954, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.630749225616455, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.577012062072754, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5202622413635254, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4548068046569824, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3818912506103516, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.302391290664673, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.202711343765259, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.109675168991089, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.0227131843566895, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.902785301208496, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.7607766389846802, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.6366586685180664, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.527940273284912, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.3889166116714478, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.272887945175171, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.1463853120803833, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.0327446460723877, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.9238291382789612, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.8319227695465088, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7440254092216492, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.650554895401001, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5889976620674133, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5418261289596558, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4886128902435303, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.44932466745376587, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4104722738265991, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.3753184378147125, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3492741286754608, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.32225286960601807, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.30281394720077515, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1572420634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.16517857142857142, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1775793650793651, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.18973214285714285, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.20287698412698413, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2160218253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.22371031746031747, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22718253968253968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22817460317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.22544642857142858, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.22321428571428573, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22172619047619047, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.21899801587301587, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2152777777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21155753968253968, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.21106150793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2130456349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21552579365079366, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22172619047619047, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.22767857142857142, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23834325396825398, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24950396825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26959325396825395, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.294890873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.33630952380952384, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4027777777777778, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.46056547619047616, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5109126984126984, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5677083333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6324404761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6795634920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7209821428571429, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.767609126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7973710317460317, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.826140873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8531746031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8707837301587301, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8829365079365079, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8940972222222222, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9027777777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9072420634920635, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9139384920634921, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9176587301587301, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9233630952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9288194444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9322916666666666, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.935515873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9397321428571429, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.941468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.04955387426615636, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.048583784848064124, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.04892563441427874, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05116919383728655, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05342189500646476, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05622206841078848, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05564913947933021, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05741097411555319, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05657646258262573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05645396193113329, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05698996227947996, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05783977569431671, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.057656445743425336, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05635156436074203, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.053552495309388645, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05281354310583786, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05402274750191295, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.055176889893597814, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0590354873447136, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.06401660806092166, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07115471074679933, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07973061046556328, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.09909756211161909, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.12713582797906448, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1752668905826256, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.24343092261885457, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2967093054104396, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.3387958190325064, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.38956497795213446, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.45768397948250694, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5229693155788333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6030645770169228, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6877532204909876, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7401009251304641, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7882220497336304, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8287436777531912, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8530698954212383, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8687320958216372, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8823330905259708, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8921841897364874, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8985270649743055, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9053746474787161, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9096724248145013, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9151219237482474, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.921160283442393, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9243031169565287, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9277948268550918, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9319627783945075, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9335988258317497, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.32228318266570566, "validation/loss_best": 0.30281394720077515, "validation/acc_best": 0.941468253968254, "validation/f1_best": 0.9335988258317497} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.8523912382125856, "train/grad": 0.03287062275223434, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.0120361328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.00721923828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.999107666015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.99121337890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.983482666015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.972630615234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.960552978515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.94724365234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.930125732421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.91198486328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.894478759765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.868404541015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8436279296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8081494140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.774638671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7429150390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7028277587890623, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6558135986328124, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.602935791015625, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.553272705078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4907861328125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4243658447265624, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3475875854492188, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.2620819091796873, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.169295349121094, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0546788024902343, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9494216918945313, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8528472900390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7226636505126953, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5729862594604491, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4459207916259766, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3373777961730957, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.201938467025757, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0921442317962646, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9752975082397461, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8728771829605102, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7769672799110413, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.697400587797165, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6223710536956787, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5435670351982117, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.49201233506202696, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4525638209283352, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.40805599093437195, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3750229014456272, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3422166126221418, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3124167478084564, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2903775069117546, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.26783042699098586, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.2514387469738722, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.007010797478724271, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006988188477698713, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006951618250459432, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006915178552735597, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0068778440542519095, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006825675582513213, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006768459726590664, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006704904825892299, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006622849146369844, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006536628357134759, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006453770403750241, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006331142745912075, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0062140832049772145, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006047917380928993, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005893997736275196, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005751642032992095, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005578417079523206, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0053876828704960645, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005195304834051058, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005036960449069738, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004869012139970437, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004723304969957098, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004586313121253624, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0044576896680518984, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004332551632542163, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004185859577264636, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004052404295653105, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003928630547598004, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037588144035544248, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003558759355219081, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0033845316397491843, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003231807327829301, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0030357244063634425, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0028703682869672775, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0026874307135585696, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002519573421450332, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0023560060461750255, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0022146287671057506, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002076822883100249, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0019270186458015814, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.001826394847012125, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0017476933466969058, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0016571375413332134, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0015885548322694377, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0015178786555770784, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0014513157098554074, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0013999313689419068, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0013466272613732145, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0013096178040723316, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.003854990005493, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.997950553894043, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9881951808929443, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9785959720611572, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.969156503677368, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9562180042266846, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.941741466522217, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9258873462677, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9054276943206787, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8840298652648926, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.863403081893921, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.833012580871582, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8040711879730225, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7631590366363525, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.724735736846924, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6884350776672363, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.642843246459961, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.589430570602417, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.529489517211914, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4729132652282715, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4015839099884033, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.325817108154297, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.238294839859009, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.1413369178771973, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.037415027618408, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.9112138748168945, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.7976446151733398, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.695488452911377, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.560833215713501, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.4102928638458252, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2861454486846924, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.182562232017517, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.0566024780273438, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9570904970169067, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8535313010215759, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7647709846496582, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.6832247376441956, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6165968775749207, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.5544271469116211, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.48968833684921265, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.44746750593185425, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.41518595814704895, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.37866321206092834, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.3516212999820709, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.32477110624313354, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.30085399746894836, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.28340548276901245, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.26566189527511597, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.25270137190818787, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1865079365079365, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1984126984126984, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2130456349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.22420634920634921, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2261904761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.22991071428571427, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2269345238095238, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22544642857142858, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22321428571428573, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.22123015873015872, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.21750992063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21378968253968253, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.21180555555555555, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.21329365079365079, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.21726190476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2214781746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.22718253968253968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.23759920634920634, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.24950396825396826, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.26165674603174605, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2849702380952381, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.31994047619047616, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3742559523809524, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.43898809523809523, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.4990079365079365, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5691964285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6217757936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6547619047619048, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7013888888888888, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7534722222222222, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7916666666666666, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8184523809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8452380952380952, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8655753968253969, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8824404761904762, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8940972222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8995535714285714, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9084821428571429, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9161706349206349, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9206349206349206, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9231150793650794, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9288194444444444, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9317956349206349, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9347718253968254, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9407242063492064, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9427083333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9456845238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9471726190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9496527777777778, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.050658763122395666, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.052833757384169545, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05586807087726181, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.057248994065620326, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.057351055357844134, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.059658239606465324, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05746575466692271, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.059345435847056885, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05942958464431235, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0602541592532317, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05819944479730547, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05581730204979997, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05361071272291903, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.054037838667049094, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0559599616254267, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05877116908023631, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0629662438176974, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06987634313023122, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07875393033896361, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.08897669348483508, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1148396181888293, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15523377297326663, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.21529469869284137, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2804776527132399, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.33165059559567744, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.39047997259072026, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.4401283114139499, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.48288678155193226, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.559185911759803, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6609402946602748, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7315976032049735, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7780641068524252, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8212825588029318, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8492070386086733, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8683868613694694, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8827640857480781, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8893130197637331, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8987645056050836, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9066548293497763, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.912225244466002, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9148283984456872, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9217439141574921, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9248043462796334, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9277814859006901, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9349600926283449, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9369328172867084, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9401428017916971, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9421119796520434, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9444927853295584, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.2514387469738722, "validation/loss_best": 0.25270137190818787, "validation/acc_best": 0.9496527777777778, "validation/f1_best": 0.9444927853295584} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 1.7177051782608033, "train/grad": 0.03097497279755771, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.99625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9892529296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.9778564453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.9666259765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.95553955078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.940531005859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.92373291015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.905406494140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.88183349609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.85747314453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.833934326171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.799637451171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.76694091796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7211865234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.678345947265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6378765869140626, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.586978759765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5273333740234376, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.459951171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.3963262939453127, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3158856201171876, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.230399169921875, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1325137329101564, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.0253477478027344, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.912023468017578, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7769091796875, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.65780029296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5524474334716798, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.4164927673339844, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2677726745605469, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1478654861450195, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0496463108062744, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9323294830322265, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8413281631469727, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.7480414342880249, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.6691633152961731, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.5972853708267212, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5388351917266846, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4845384097099304, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.4279570090770721, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.39113283827900885, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.36284147411584855, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.3310967420786619, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.30746741227805613, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.28408189713954923, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2629720910638571, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.24761161558330058, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.23200350012630225, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.22075240425765513, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006904663164168596, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00687236754456535, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006817185909021646, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0067634713859297335, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006711985878646374, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006640403661876917, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006560992493759841, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006475156822707504, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006365446960553527, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006251731752417982, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006142123392783106, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0059832948399707675, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0058366968529298905, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005637429615017026, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005459788527805359, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005304880149196833, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005130024566315114, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0049547305447049435, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004792752813082188, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004668043958954513, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004537072278326377, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004416364441858604, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0042880146473180504, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004151233595330268, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004005902697099373, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038290388591121884, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0036702481110114605, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003526692242594436, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0033373958023730664, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003123724218457937, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002945020515471697, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0027927065966650844, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0026032043900340797, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0024492655642097817, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0022846387833124026, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002139574327156879, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0020024404185824095, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0018872389645548538, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0017770852404646576, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0016586307622492313, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0015791519032791258, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0015173682919703425, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0014464973463327623, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0013928019933518955, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0013390863555832765, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0012905490733101032, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0012564453892991879, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0012241343822097406, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0012027175797265954, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9883036613464355, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9802427291870117, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9670753479003906, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.95418643951416, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.941561460494995, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9243788719177246, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.905296564102173, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8846116065979004, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8580734729766846, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8306384086608887, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8043344020843506, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.766080141067505, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.730015516281128, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6793372631073, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6320929527282715, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5875561237335205, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5315473079681396, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.465691328048706, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3912353515625, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3206279277801514, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.231813430786133, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.1379542350769043, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.031559467315674, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9164315462112427, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7966374158859253, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.6563361883163452, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.5350631475448608, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.4296449422836304, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2959988117218018, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1530500650405884, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.040138840675354, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9491955041885376, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.8424552083015442, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.760953962802887, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.6784862875938416, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6095280647277832, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.5471405386924744, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.49661821126937866, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.4498172998428345, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.4012916088104248, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.36989182233810425, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3459022045135498, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3191416263580322, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.29941558837890625, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2798730134963989, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2622796297073364, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.24946057796478271, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2367710918188095, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2277471274137497, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2123015873015873, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22172619047619047, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22718253968253968, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.22991071428571427, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2279265873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2251984126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2234623015873016, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22098214285714285, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.21577380952380953, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21279761904761904, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.21155753968253968, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2130456349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2160218253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.22247023809523808, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.22842261904761904, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.23685515873015872, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24975198412698413, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26512896825396826, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29191468253968256, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3256448412698413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3814484126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4459325396825397, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5062003968253969, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5684523809523809, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6242559523809523, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6805555555555556, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7254464285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7606646825396826, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7971230158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8343253968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8566468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8740079365079365, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8898809523809523, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8958333333333334, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9032738095238095, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9084821428571429, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9161706349206349, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9206349206349206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9263392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9310515873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9340277777777778, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9372519841269841, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9402281746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9417162698412699, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9449404761904762, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9476686507936508, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9508928571428571, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9533730158730159, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.955109126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05542458761388221, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05701557841339834, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.058095630440502796, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0604119700382237, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.058992381484455084, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.059678577134175806, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05992788446730385, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.060176224668834044, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05717718303453746, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.054956749343019314, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05339764211093107, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0539824974279262, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05561564999391589, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05968756812670379, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06414416369970813, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06995338675539335, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07992630509303718, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.09422919911565102, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.12427887491672059, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1630218541336657, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2228519888442874, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.28678547191554393, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.33809295644489895, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3925210497105636, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.45024870045536486, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5296161761164593, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6093643142615972, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6729747147926168, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7386921256380573, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7986773289605363, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8317150610167051, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8567700993200971, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.876963654217303, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8840979694322528, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8938230444845784, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8998836555895661, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9072125328288898, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9118672800571845, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9176484567379747, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.923122862871366, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9272693236851006, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9308578552728922, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9342876869631334, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9363144776184029, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9393961488198135, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9420402063062641, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9448297770533438, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9464366964265797, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9480897633439604, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.22075240425765513, "validation/loss_best": 0.2277471274137497, "validation/acc_best": 0.955109126984127, "validation/f1_best": 0.9480897633439604} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 1.6174468910694122, "train/grad": 0.02948151683434844, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.982359619140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.97353271484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.95895263671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.94499267578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.9311572265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.912388916015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.89177001953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.869329833984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.840699462890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.811217041015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.782994384765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.741949462890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.703397216796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.649200439453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5984490966796874, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5505181884765626, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4899468994140626, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4181915283203126, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3369451904296876, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2598211669921877, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1629153442382814, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0612606811523437, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9468936157226562, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8246690368652343, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6991793823242187, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.554304962158203, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4308549499511718, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3251131057739258, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1927796936035155, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.053651638031006, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9454230976104736, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.859364161491394, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.7595711040496826, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6840480589866638, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.6082445335388184, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.5452153325080872, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.4883888345956802, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.44256359100341797, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.4002222281694412, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.3562041087448597, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3275147739052773, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.30557494193315504, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2809058255702257, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.26260638423264027, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.244554096609354, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2282383455336094, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.21641163788735868, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.20444675669074058, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.19596559688448906, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006792033556848764, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006748060535173863, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006679376268293708, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006611079131253064, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006544650811702013, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.006454982764553279, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006356515637598932, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006250994566362351, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006115288792643696, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005976692272815854, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005846976798493415, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005664858953095973, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005499468217603862, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005285935644060373, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005109427168499678, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004964511328143999, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00481138562085107, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004665876204380765, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004532678980613127, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004423976923571899, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0042986760498024525, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004171760480385273, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004028757871128619, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00387355147046037, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0037107519700657577, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003518568854779005, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0033507640205789357, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003203234615502879, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0030132365366443994, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0028042220266070216, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0026329152542166412, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0024909973324975, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0023187149362638593, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002182359649450518, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0020403559890110044, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0019177233683876694, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0018033621867652983, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0017081128765130415, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0016172949934843929, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0015198953147046268, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0014544303235015832, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0014035693666664883, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0013455311447614804, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0013019063274259679, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012585007125744596, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0012198914194596, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001192692085460294, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001166977746761404, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0011492648042622023, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.973466634750366, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.963434934616089, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9471099376678467, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9312584400177, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.915766954421997, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8948142528533936, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.871716022491455, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.846789836883545, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8150815963745117, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.782526731491089, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.75160551071167, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7067689895629883, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6647114753723145, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6058056354522705, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.550865411758423, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4989471435546875, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4333839416503906, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3559439182281494, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.268352746963501, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.185743570327759, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.082726001739502, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9756208658218384, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8566621541976929, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7311172485351562, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6040418148040771, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.4597009420394897, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.338626503944397, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.2362282276153564, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.109928846359253, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.979123055934906, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.878687858581543, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.8001067638397217, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.7094796895980835, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.6414849162101746, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.5737331509590149, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.517483651638031, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.46695297956466675, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.42625465989112854, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.3888508677482605, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3498467803001404, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3247162699699402, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.30559632182121277, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.28402459621429443, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.26821577548980713, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.25247377157211304, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.23837532103061676, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2281828075647354, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.21765176951885223, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2103092223405838, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22668650793650794, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22916666666666666, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22891865079365079, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2261904761904762, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.22321428571428573, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2222222222222222, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21850198412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2140376984126984, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2113095238095238, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21254960317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.21478174603174602, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21924603174603174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.22495039682539683, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.23487103174603174, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.24479166666666666, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2562003968253968, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2757936507936508, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3055555555555556, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.35788690476190477, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4124503968253968, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4771825396825397, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.5357142857142857, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5982142857142857, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.6493055555555556, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6971726190476191, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7507440476190477, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7916666666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8174603174603174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8452380952380952, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.871031746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8864087301587301, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8943452380952381, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9030257936507936, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9089781746031746, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9176587301587301, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.923859126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9278273809523809, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9317956349206349, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9370039682539683, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9392361111111112, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9424603174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9459325396825397, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9464285714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.949156746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9506448412698413, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9516369047619048, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9548611111111112, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9585813492063492, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.058308876525915175, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0590435752071555, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.059343427751597705, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.059330647540474755, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.059081952104796116, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.06040922577236435, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.058911984659883565, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.056314393086490645, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.053414988821372716, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.054055310790974274, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05521054312752074, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.057469000923593576, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06198151860626801, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06869411724422636, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07525572454681563, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08592514041180396, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10524097705813847, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1382850131147531, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.19783078017388747, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.2523343903926903, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.31254226063732515, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.364556206585367, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.4241645131530914, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4816953292419191, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5615451554653782, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6531943570423857, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7264084323599221, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.7733144103038683, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8155237736663232, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8534557523781477, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8730921154436834, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8830410776130255, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8916744826835379, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8996248778134088, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9095420020574995, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9163124587507613, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9200225872541855, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9246785625656835, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9304808606967049, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9328248228206425, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9362708575972705, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9403234983732118, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9412677526347945, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.943500467290784, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9447143154092685, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9459981793569356, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9489232181092814, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9500448158204184, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9519647991124417, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.19596559688448906, "validation/loss_best": 0.2103092223405838, "validation/acc_best": 0.9585813492063492, "validation/f1_best": 0.9519647991124417} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 1.5311995047330855, "train/grad": 0.028459213357418776, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.965849609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.954884033203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.936966552734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.919610595703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.90271240234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.879974365234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.85484619140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.827857666015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.79351806640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.758468017578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.725167236328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6770458984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6319232177734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5688134765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.509813232421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.45401611328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3834039306640626, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2057510375976563, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.117420654296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.007734527587891, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8949037170410157, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.770603485107422, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.6408599090576172, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.5111521148681641, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.365465850830078, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.2447764205932617, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.1437704467773437, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.0204867839813232, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.894476342201233, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.7990310335159302, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.7246734356880188, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.6398467803001404, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.5766934204101563, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.5138853257894516, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.46198411703109743, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.41550549000501635, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.3780520012974739, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.343443421125412, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.3075479957461357, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.2842053392529488, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.2664609970152378, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2463478308916092, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.23152330480515956, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.21684275731444358, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.20367685858160256, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.19414943601936102, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1846193043887615, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.17801644012331963, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00676207997603342, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0067112216958776115, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006625507804565132, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006544617479667067, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006465020882897079, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00635857576970011, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006242150729522109, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006115679638460278, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005957418635953218, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005799477226100862, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00565432844683528, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005451411579269916, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005277051953598857, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00506244071177207, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004893950660480186, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004761829065391794, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004625226694624871, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004492335234535858, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004362373864278197, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004248345472151413, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004109146718401462, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003965160301886499, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038034704141318796, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003631026321090758, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00345482743345201, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003251698852982372, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0030779773474205285, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002927986142458394, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002737294405233115, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0025321333459578455, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0023685414995998143, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0022357997338986026, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002078850289108232, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0019570822699461134, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0018323748791590332, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0017255597253097222, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0016267647745553404, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0015450727683492004, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0014674549794290214, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0013848095972207376, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0013293958333088086, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001286745481484104, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001237150853849016, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0011996329270186833, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0011621521497727372, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0011288486371631734, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0011050042699207552, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001083527031878475, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0010718943868414498, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.959547281265259, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.947718381881714, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9285457134246826, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.909977674484253, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.891984701156616, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.867680072784424, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.841097354888916, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8125014305114746, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.776393413543701, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7394962310791016, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.704559326171875, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6541295051574707, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6068999767303467, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5407559871673584, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.478855609893799, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.420217752456665, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3458597660064697, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.2581706047058105, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.1593892574310303, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.067065477371216, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.9534987211227417, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.8374769687652588, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.7108850479125977, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.5803910493850708, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4513722658157349, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.3082380294799805, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.191023588180542, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.093977451324463, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.9764838218688965, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.8578897714614868, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.7687861323356628, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6997765302658081, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6213318109512329, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.5630636215209961, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.5053846836090088, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.45762959122657776, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.4150236248970032, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.3806961178779602, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.34918004274368286, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3165704309940338, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.29555922746658325, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.279784232378006, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2619660198688507, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.24910639226436615, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2366265505552292, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2255081832408905, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.21780088543891907, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2103503942489624, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.20567995309829712, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.23040674603174602, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22891865079365079, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2261904761904762, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.22395833333333334, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.22123015873015872, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21676587301587302, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21378968253968253, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21106150793650794, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.21329365079365079, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21502976190476192, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.21899801587301587, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.22544642857142858, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2326388888888889, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.24677579365079366, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2594246031746032, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.2770337301587302, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.3072916666666667, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.35987103174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.42509920634920634, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.48313492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.542906746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6021825396825397, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6495535714285714, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7003968253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.748015873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7931547619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.826140873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.84375, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8670634920634921, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8864087301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8940972222222222, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9007936507936508, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9079861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9151785714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9216269841269841, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9270833333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9303075396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9340277777777778, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9389880952380952, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9437003968253969, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9446924603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9466765873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9481646825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9496527777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.953125, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.957093253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.957093253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06050161230957597, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.059042760205253515, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05976164014217062, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05949880738273343, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05939183378014992, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05749681010764843, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05597871606053588, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05311293136384935, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0545454427914576, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05533789417302259, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05776233112292056, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.062356684850791204, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06733924912843968, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07731828055285875, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0883733764774143, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10659180136477277, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1417083473462975, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.20055748145506036, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.2649657693806044, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.3173621994455155, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.3696567330037302, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4272191941250276, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.48193429374740965, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5665553344425736, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6520092532519046, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.7331289631713714, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.7859347379774594, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8153335173997843, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8488912801703682, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8727257854353193, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8821724194602257, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8906607597691987, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8993594417064037, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.907340029501419, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9128863194086352, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9180653121732644, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9222890651217484, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9261874309981185, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9322011895007947, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9375023905894304, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9383716000330637, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.940091276729517, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9416638467353747, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.942898114722701, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.947647444160005, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9493610766429929, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9516396860222045, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9519068622921745, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9518752345952893, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.1846193043887615, "validation/loss_best": 0.2103503942489624, "validation/acc_best": 0.957093253968254, "validation/f1_best": 0.9519068622921745} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 1.4736107540130616, "train/grad": 0.027835212387144564, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.95378662109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9411474609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.920643310546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.900849609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.881773681640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.855972900390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.827740478515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.797628173828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.75945068359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7205474853515623, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6837579345703126, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6306781005859374, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5809130859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.511181640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4457598876953126, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3837158203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3050503540039062, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.212324523925781, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.108226013183594, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.011611022949219, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.893145294189453, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.7730485534667968, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6431700134277343, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5102245330810546, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.3798417282104491, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.2365881156921388, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.1203145790100097, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.0246466159820558, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.9100715684890747, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.7952859687805176, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.7097187447547912, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.6437819170951843, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5693670225143432, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.5142421245574951, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.45969936937093736, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.4148241573572159, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.37454883962869645, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.34207928195595744, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.3121168123185635, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2809283743053675, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.26056725449860096, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.2450807949155569, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.22756131328642368, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.21465338487178087, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.20191545940935612, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.19062269523739814, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1825461572781205, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.17454817347228527, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.169030872695148, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006714450984727591, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006654032520018518, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006558308913372457, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0064652118412777786, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006376817193813622, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0062574709416367115, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.006126837278716266, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005988012382294983, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0058180760499089955, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005649865949526429, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005497213900089264, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005294754453934729, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0051270783552899955, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004929584953933954, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004781579617410898, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00466702196514234, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004544678857782856, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004418275785865262, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00428508042357862, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0041632787289563565, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004011934464797378, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038546996866352856, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0036806096974760292, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0034982838260475546, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003314969117054716, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003106639558682218, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0029307464289013295, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0027804879611358045, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002592450752854347, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0023941568902228027, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002239429321489297, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0021158573013963177, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001971535455668345, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001861027939012274, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0017481521028093994, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00165181863354519, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0015623580705141648, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0014879997371463104, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001416960986389313, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0013409098132979125, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0012900843226816504, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0012507018991163932, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001205411798437126, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0011721462506102398, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0011393081001006067, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0011110325090703554, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0010911615382065065, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0010732228675624355, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0010628304837155156, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.946829319000244, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9334025382995605, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9117093086242676, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.890778064727783, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8705708980560303, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8433918952941895, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8137691020965576, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.782042980194092, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.742164134979248, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.701580286026001, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.663245677947998, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.60796856880188, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5562267303466797, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.483513355255127, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4153189659118652, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.350492238998413, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.268440008163452, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.1719300746917725, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.064159631729126, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.9645094871520996, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.843316912651062, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.7216230630874634, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.5910801887512207, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.4588046073913574, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.3305656909942627, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.1908764839172363, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.0787538290023804, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.9873347878456116, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.8784654140472412, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.770344078540802, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6902377009391785, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6288945078849792, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.559775710105896, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.5085998177528381, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.45817363262176514, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.41662347316741943, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.3795628845691681, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.3498576879501343, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.322442889213562, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.29418447613716125, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2759127616882324, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.26201388239860535, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.24649809300899506, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2351510226726532, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2242545634508133, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2145196795463562, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.20777441561222076, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.20152971148490906, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.19753462076187134, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2286706349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22594246031746032, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22247023809523808, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.22073412698412698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2160218253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2130456349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2105654761904762, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21155753968253968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2140376984126984, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2177579365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.22321428571428573, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.23115079365079366, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.24231150793650794, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2562003968253968, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2777777777777778, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.30357142857142855, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.35193452380952384, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.41592261904761907, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.482390873015873, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5357142857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5969742063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6468253968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6974206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7467757936507936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7891865079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8278769841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8497023809523809, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8665674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8846726190476191, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8978174603174603, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9030257936507936, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9087301587301587, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9159226190476191, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9216269841269841, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9263392857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9305555555555556, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9342757936507936, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9377480158730159, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9427083333333334, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9446924603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9466765873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9508928571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9528769841269841, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9575892857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9588293650793651, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05882524840617043, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.058660798171222245, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05834186356191599, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.059398530538482215, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05699940604626069, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05555715702619935, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05280322547991243, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05333607353630136, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.054667020587752975, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.056493779418610286, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06044659328580765, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06660082726378788, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.07386729001461739, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.08554854205057838, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10731492014743307, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.13656660227524445, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.19219925556872, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.25562825298380026, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3167050101041224, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.36368135303252375, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.4210940902988389, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4777168097366407, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5621815484114593, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6499521463986662, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.7249135505447754, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.7912110840387182, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8240664082338617, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8488908890143249, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8713697202219909, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8863880396816474, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.89299531604818, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.900287935707879, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9079291621291112, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9124726208339518, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.917418404287201, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9221108405489903, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9266724499860195, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9312335868602284, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9341422898912148, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9360890630213712, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.93876432081101, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9404913754093837, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9448230959685573, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.947108244210662, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9496882707340436, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9527884745591451, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9536066054128938, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9533239570325692, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9535966623796083, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.17454817347228527, "validation/loss_best": 0.20152971148490906, "validation/acc_best": 0.9588293650793651, "validation/f1_best": 0.9533239570325692} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 1.4238558524847031, "train/grad": 0.02695688223466277, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.941531982421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9275732421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.90486328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.882978515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.861968994140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.833629150390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.802784423828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.769859619140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.728397216796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.686201171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.64640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.58883056640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5347088623046874, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4586767578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3870501708984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.3188897705078126, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2325634765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.1312026977539062, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.0184490966796873, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9146640014648437, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.789127960205078, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.6638890838623046, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.5305003356933593, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.3963593673706054, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.2672014617919922, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.1279713821411133, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.0169400310516357, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.9270124530792236, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.8208936643600464, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.7162365889549256, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.639178614616394, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5803206062316895, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5141408085823059, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.46540185242891313, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.4172391161322594, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.3775887762010097, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.34209263369441034, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.3134450854361057, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2869533683359623, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2593171942979097, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.241307957097888, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.22753970041871072, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.21203827776014805, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.20058426428586246, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.18924871768802404, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.17915188167244195, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.17185156024992465, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.16458109471946955, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.15959522183984517, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006619948286097497, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006553014987148344, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006445797521155328, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0063439066265709694, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006245148894377053, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0061125152953900395, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0059685313352383675, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00581899767043069, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00563728528097272, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005458981739357114, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005303245279937982, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005102358651347458, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004941930099157617, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0047593203920405355, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004624505614629015, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004518241321202368, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004399983595358208, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004271059003658592, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004130473040277138, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00399982645874843, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00383920238702558, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003674735244130716, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0034959635429549964, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0033117596618831156, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003128977724118158, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002924270782386884, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0027535804908256976, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0026089501148089766, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002430829069344327, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002245441690320149, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002102667479193769, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0019895268138498067, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001857789761852473, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0017572567670140415, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001655157112982124, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0015681764401961119, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0014877204986987636, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0014207912830170243, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001356848416326102, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0012881610429030842, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.001241996753087733, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0012057512105093338, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0011640390421962365, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001132873538590502, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001101425211818423, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010736936517059803, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0010542667485424317, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0010362170223379508, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0010261704231379553, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9354703426361084, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.92063570022583, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8967466354370117, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.873786687850952, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8516829013824463, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8220314979553223, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.789827823638916, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.755491256713867, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7124059200286865, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.668694257736206, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.627547264099121, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.567991018295288, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5121958255767822, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.4336979389190674, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.359764814376831, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.289546489715576, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.200854539871216, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.0971555709838867, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.9822441339492798, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.8771408796310425, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.7507483959197998, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.625533938407898, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.4932169914245605, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.36111581325531, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.2348686456680298, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.0997329950332642, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.9928017258644104, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.9065797924995422, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.805255115032196, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.7058974504470825, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.6330634951591492, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5774931311607361, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.5150986313819885, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.46912822127342224, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.4238314926624298, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.38676247000694275, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.35355421900749207, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.3269958198070526, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.302507221698761, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.27720171213150024, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2608422040939331, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.24842219054698944, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.23462964594364166, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.224538654088974, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2149784117937088, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.20653851330280304, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.20082442462444305, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.19512860476970673, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.19077876210212708, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22643849206349206, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22420634920634921, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22123015873015872, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2177579365079365, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21577380952380953, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21155753968253968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21279761904761904, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.21577380952380953, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.22271825396825398, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2279265873015873, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.23933531746031747, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.25124007936507936, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.27306547619047616, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.29985119047619047, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.3395337301587302, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.3968253968253968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.46106150793650796, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5265376984126984, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5798611111111112, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.638640873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6857638888888888, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7375992063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7819940476190477, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8149801587301587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8452380952380952, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8673115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8804563492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8931051587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9020337301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9077380952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9149305555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9213789682539683, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9265873015873016, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9317956349206349, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9367559523809523, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9466765873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9486607142857143, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9506448412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9536210317460317, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9575892857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9598214285714286, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9603174603174603, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.058369515614367984, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.058524452730288556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05870298879849746, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05818323395305583, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.057273319683828525, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05375411334776559, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05389024113783563, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05381270462253504, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.055328697309582606, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05994214572508265, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0640843889152457, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0717944005817633, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08070977560439241, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.10247345308606763, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1319275965231777, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1788027020537791, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.23804448847327633, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.29928036589015006, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.3543125988835749, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4055016413981306, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.4667078717664192, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5361077164235561, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6326009336399254, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.7109956639028098, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.7694176558055674, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8157674476712884, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.847841515131054, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8639843643217398, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8808265381164692, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8919785830079102, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8981695390996197, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.907036853381359, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9129993360826335, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9183407113520303, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9250057490211618, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9286560402033087, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9302978512666787, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9345596141024041, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9373141792218951, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9404939077849888, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9426175003230176, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9445454371481995, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9474409876799728, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9485667719754448, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9509123781784006, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9523784193717065, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9535555766778633, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9553369713980353, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9554637108422108, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.15959522183984517, "validation/loss_best": 0.19077876210212708, "validation/acc_best": 0.9603174603174603, "validation/f1_best": 0.9554637108422108} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 1.38572030544281, "train/grad": 0.026287357630208133, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.930487060546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.914993896484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.89005859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.866116943359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.84317138671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.812366943359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.778924560546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.743419189453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.698861083984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6535992431640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6109747314453124, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.5494342041015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4916510009765624, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.410087890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3333029174804687, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.26020751953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1681307983398437, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.0605978393554687, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.9419755554199218, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.8338807678222657, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.704548568725586, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.5771593475341796, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.4431912231445312, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.3103742027282714, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.1841472053527833, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.0499257469177246, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.9443816184997559, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.8598203325271606, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.7609561085700989, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.66442014336586, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5937934637069702, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5400042313337327, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.4797851863503456, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.4353118391335011, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.39142233893275263, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.35520253896713255, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.3226398733258247, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2964043435454369, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2719819002598524, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.24660887382924557, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.22996143102645875, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.2172563138604164, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.20292345814406873, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.19228585358709097, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.18183991719037296, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1724944196268916, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.16572328366339206, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.15906797271221876, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.15442237127572297, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00657472541090101, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00650244144257158, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006384293951559812, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006271673340816051, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0061633230792358515, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00601766505278647, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005862926258705556, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0057031991588883104, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005507472816389054, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005322535096202046, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0051636104471981525, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004963489861693233, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004807693760376423, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0046346196066588165, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004505457446211949, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004400416037533432, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004279246821533888, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004143185346620158, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003993346237111836, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003854592733550817, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0036847212712746115, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003513990771025419, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003330603140639141, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003144171582534909, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002961188912158832, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002758882362395525, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002592336316592991, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002453452134504914, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0022846586065134035, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0021125177218345925, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001981300142360851, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0018779703415930272, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001758691918803379, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0016673498385353014, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0015741230821004137, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0014946430135751143, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0014204364799661562, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0013587224067305214, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001299398387200199, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0012350553151918575, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0011921944370260461, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00115826916648075, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0011192522390047089, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0010899279688601383, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0010614550273749046, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010358125230413861, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001017664724495262, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0009999186717323028, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009879186516627669, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.925508737564087, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.909487724304199, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8837246894836426, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.85898494720459, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8353049755096436, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8035330772399902, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7692062854766846, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7326841354370117, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.686929941177368, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6405556201934814, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.596858501434326, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5338006019592285, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.474463701248169, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.390860080718994, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.31211256980896, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.2373249530792236, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.1432392597198486, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.0336554050445557, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.9133754968643188, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.8043309450149536, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.6746150255203247, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.5473644733428955, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.414535403251648, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2836676836013794, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.1599642038345337, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.0291833877563477, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.9269011616706848, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.8454528450965881, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.750322163105011, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6578448414802551, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.59040367603302, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5391916036605835, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4819062352180481, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.4399140477180481, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3984368145465851, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.36451655626296997, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.3342503607273102, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.3101150393486023, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2880318760871887, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2651014029979706, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2505815029144287, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.23964597284793854, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.22749367356300354, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2188860923051834, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.21047598123550415, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.20310188829898834, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19799724221229553, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.19339822232723236, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.19000516831874847, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2244543650793651, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2222222222222222, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2204861111111111, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21726190476190477, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21329365079365079, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2105654761904762, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21254960317460317, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21428571428571427, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.21924603174603174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.22544642857142858, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.23239087301587302, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.24578373015873015, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2571924603174603, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2847222222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.3229166666666667, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.3705357142857143, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4332837301587302, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4962797619047619, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5634920634920635, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6183035714285714, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6656746031746031, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7137896825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7569444444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.798859126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8298611111111112, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8578869047619048, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8762400793650794, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8891369047619048, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8975694444444444, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9037698412698413, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9117063492063492, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.917906746031746, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9246031746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9283234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9327876984126984, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9360119047619048, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9392361111111112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9427083333333334, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9489087301587301, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9508928571428571, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9516369047619048, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.953125, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9533730158730159, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9556051587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.957093253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9573412698412699, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05834664001492956, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05809672131758022, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05943296354342612, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05806758066827916, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05527279926814996, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05267987155544737, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05383434995631653, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05452087575554317, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05709461701454751, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06225934511249263, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06726740507687422, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07649139315426728, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0867395768741537, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.11622983685020172, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.15809499711310776, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.21103534586300718, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.27297522507070554, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.3274418094400605, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.38726463448093656, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4421911618380324, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5027196513779546, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5880440568399534, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6671245080553075, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.740968829807468, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.7938211357923034, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8349498978000875, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8588031554580827, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8757128458554262, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8859035364040301, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.893426956413243, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9032627758915874, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9101364829413742, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.916873818923389, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9208402281613097, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9255647427858574, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9294463274738438, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9330967768247573, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.936792611212512, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9398320389317302, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9443800148998692, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9458556211834981, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9463904698675573, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9472957327888762, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9476713275212416, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9507386736488959, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9520121756567816, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9528787444293702, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9531753733694011, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9530695350175361, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.15442237127572297, "validation/loss_best": 0.19000516831874847, "validation/acc_best": 0.9573412698412699, "validation/f1_best": 0.9530695350175361} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 1.3535894930362702, "train/grad": 0.025897682327777147, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.92172607421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.905235595703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8787548828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.853350830078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.828934326171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.79633056640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.76096435546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.723433837890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.676405029296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6286810302734374, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.583692626953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.518607177734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.457352294921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.370823974609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.2892105102539064, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2118719482421874, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1145220947265626, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.001435546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.8777182006835937, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.7659339904785156, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.633436279296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.504204330444336, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.3697611236572265, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.2379233169555663, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.1140668106079101, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.9838321685791016, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.882544813156128, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.8020897674560546, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.7088669109344482, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.6185188174247742, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5528954160213471, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5032342267036438, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.4477104890346527, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.4068933203816414, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.36672158151865003, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.33367410480976106, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.3040354424715042, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.280120435655117, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2579648210853338, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.23487594589591027, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.21975937023758887, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.20811241380870343, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.19504120737314223, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1853338509052992, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.17572963103652, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1671527974680066, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1609412243962288, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1548346409201622, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.1506261894106865, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006543032156769186, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006464194024447352, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006339312815107405, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006219525749329478, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0061040340014733374, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00595068623078987, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005789209420327097, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005621895480435342, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005419932610820979, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005233263969421387, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005075438139028847, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0048807581467553976, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004733068204950541, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004569738974096254, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004445700935320929, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0043415484973229465, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004217843976803124, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004077401326503605, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003921662028878927, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0037779687775764616, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0036044573644176126, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00343120060977526, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00324627568712458, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0030593010305892676, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0028767844743561, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0026751216349657626, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0025099055282771588, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00237299911910668, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002207415755256079, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0020396688929758965, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0019130484096240253, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0018142074631759897, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0017001928918762132, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0016139193635899573, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0015262616920517758, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001451825460535474, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0013828838625340723, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0013254637719364837, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001270321339543443, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0012109346175566316, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0011701235731015913, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0011379086307715626, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001100510302640032, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0010719689054531046, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0010430151014588773, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010170717141591012, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009986707827192732, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0009815762177458965, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009712570265401155, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9170613288879395, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9000346660614014, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.872704029083252, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8465702533721924, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8214776515960693, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.788048505783081, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7518773078918457, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.713521957397461, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.665621519088745, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6170477867126465, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5712673664093018, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5051188468933105, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.4428632259368896, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.3548810482025146, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.272029161453247, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.1935102939605713, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.0948688983917236, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.9809038639068604, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.8565576076507568, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.7446691989898682, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.61265230178833, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.4844133853912354, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.3518931865692139, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2222295999526978, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.101293683052063, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.9743689894676208, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.8762986660003662, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7982914447784424, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.708314061164856, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6212337613105774, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5581202507019043, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.5101185441017151, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4568927586078644, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.4176918566226959, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3790520429611206, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3475783169269562, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.3193531036376953, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.29675576090812683, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.276038259267807, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2548394203186035, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.241123765707016, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.23089009523391724, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.21954715251922607, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.21121466159820557, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.20320375263690948, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1963653415441513, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19168543815612793, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.18715275824069977, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.18389298021793365, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22247023809523808, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2222222222222222, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.21626984126984128, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21329365079365079, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21031746031746032, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21081349206349206, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21478174603174602, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2214781746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.22842261904761904, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.23685515873015872, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2507440476190476, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2681051587301587, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.29910714285714285, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.34598214285714285, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.39632936507936506, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4573412698412698, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5243055555555556, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5880456349206349, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6381448412698413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6899801587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7375992063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7814980158730159, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8172123015873016, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8444940476190477, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8690476190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8856646825396826, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8943452380952381, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9030257936507936, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9089781746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9169146825396826, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9223710317460317, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9250992063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9303075396825397, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9392361111111112, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9419642857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9513888888888888, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9528769841269841, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9538690476190477, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9558531746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.957093253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9583333333333334, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05784573199734581, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.059180423639708636, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.056919887042809654, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05556220320233677, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05269089307069494, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.052725765609133855, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.052819492043772155, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.054536915088904826, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05878164670208507, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0641973624751967, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.06994811007292914, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08051492174080786, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.09691587392387484, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1308924912549782, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.1862185799470592, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2368830761018548, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.2952099388518629, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.35305645507284, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4134584349239113, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4671438794922601, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5456293286382584, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6345883223366752, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7117863625144836, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.7742871766217673, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8151508637183567, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8514032080900458, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8720718574744682, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8829931912320655, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8921155592394147, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9010975731168832, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9090550445746244, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9143343189547202, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9168061437349845, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9228860127378137, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9278492340011045, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.933330349309882, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9363093592964611, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9384269208305163, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.942895460683951, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9454507648327538, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9463061681629864, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9474488025028517, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9507198899316643, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9517684771468785, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9513310791795998, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9524367590671294, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9529298363751619, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9534861031517944, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9525939371782153, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.1548346409201622, "validation/loss_best": 0.18715275824069977, "validation/acc_best": 0.9585813492063492, "validation/f1_best": 0.9534861031517944} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 1.3314272820949555, "train/grad": 0.02540752333588898, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.914803466796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.89749267578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.869561767578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.842926025390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8174169921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.783287353515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.746544189453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7075677490234376, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6588018798828124, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6092596435546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5626605224609373, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.495113525390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.431373291015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.3412261962890626, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.2562210083007814, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.175705871582031, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.074609680175781, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.9578207397460938, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.8308999633789063, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.7169300079345704, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.5829319763183594, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.453077049255371, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.3192940902709962, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.1891297721862792, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.0677555656433106, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.941278133392334, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.8436575412750245, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.7664974308013917, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6775019693374634, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5915893685817718, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.5293971002101898, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.48221602201461794, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.42955974727869034, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.3908864402770996, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.35277237117290494, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.32136041700839996, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.2932220255583525, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.27042480915784833, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.24935312516987324, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.22732279773801564, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.21293456062674523, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.20184609942138196, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.18939808096736668, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.18003475103527308, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.17080487743020056, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.16248255956918, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1564474431797862, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.15037818849086762, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.14616097915917636, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00648386990884319, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0063998181652277705, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006268165137153119, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006141040360089392, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006019242380280048, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0058595477347262205, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005692483123857528, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005519092443864793, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005316114579327405, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0051309230388142165, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0049777114926837385, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004793421928770841, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004655602276325226, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004502070547314361, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004382153183687478, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004278026978718117, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004151311697205529, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004004874585662037, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038421345804817973, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0036923411884345115, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003512765612686053, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0033344506577122957, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003145857782801613, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0029563258041162043, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002772229129914194, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002570547590148635, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0024069387634517627, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002272332731517963, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002111144483787939, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001948631385457702, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0018267701991135255, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0017316650331486016, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0016220353078097104, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001539261435973458, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0014551985636353493, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00138371039647609, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0013176060403930023, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001262720259546768, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001210201322392095, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0011540625395718962, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0011166996863903478, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0010872338761691936, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0010541803436353802, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0010290416987845674, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0010037513799034058, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0009806722213397735, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009638180705951526, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00094690306665143, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000936206904007122, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.910139322280884, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8922922611236572, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.863671064376831, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.836367130279541, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8102378845214844, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.775404453277588, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.737879991531372, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.698026418685913, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.6483287811279297, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.5980052947998047, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.550551652908325, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4818997383117676, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.4171717166900635, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.3255913257598877, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.239459991455078, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.158010482788086, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.0559654235839844, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.9384334087371826, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.811139464378357, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6973052024841309, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.563902735710144, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.4352186918258667, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.3030943870544434, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.1751123666763306, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.0562783479690552, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.9328703284263611, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.8379478454589844, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7631577849388123, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.67702317237854, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5941485166549683, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.53420090675354, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.48883095383644104, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4383202791213989, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.40135085582733154, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.36494767665863037, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.335122674703598, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.3084963262081146, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.2872145175933838, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.26752468943595886, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.24731546640396118, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.234267920255661, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.22439593076705933, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2134248912334442, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.20536451041698456, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.19756965339183807, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.19079673290252686, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.18603460490703583, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.18133136630058289, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.17812080681324005, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22296626984126985, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22098214285714285, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.21552579365079366, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21254960317460317, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.20982142857142858, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21106150793650794, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21329365079365079, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2160218253968254, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22321428571428573, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23139880952380953, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2408234126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.25471230158730157, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2757936507936508, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.31101190476190477, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.3635912698412698, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4184027777777778, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.48139880952380953, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5436507936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6111111111111112, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6525297619047619, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.705109126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7517361111111112, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7926587301587301, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.828125, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8516865079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8745039682539683, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8893849206349206, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8958333333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.904265873015873, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9124503968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9186507936507936, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9233630952380952, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9278273809523809, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9305555555555556, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9337797619047619, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9387400793650794, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.941468253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9441964285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9523809523809523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.957093253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9625496031746031, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05842468448457246, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.058921359969123704, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05645748106321745, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.054491770250698145, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05216849538287677, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05269910755910266, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05384530214912164, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05499874460238722, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06036941238364957, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06604262296835875, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07226318488915814, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0843782328946252, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10509595785749345, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1437638384660574, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.20321070049834833, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2575051447033816, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.31542843445074575, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.3708144193740436, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.43530973954353525, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.4853792975932638, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5750319183935947, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6555484156067072, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.731089594147113, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.7896516855673655, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.827581716136657, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8578753820267406, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8759968709217846, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8844405024976134, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8940346639545895, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9034023066083996, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9105966082132023, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9153263635000004, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9199897544284633, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9233764533187528, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.927656264609118, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9325915125576423, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9359223898104752, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9382014100483671, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9433240878983508, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9468887585411174, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9493575411586441, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9512715771753054, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9522740285271393, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9534613018185432, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.954157831692003, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9565349592303221, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9571077440196564, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9578076610222165, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9584010039038007, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.14616097915917636, "validation/loss_best": 0.17812080681324005, "validation/acc_best": 0.9625496031746031, "validation/f1_best": 0.9584010039038007} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 1.3082075184583664, "train/grad": 0.025321320388466118, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.906451416015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8883203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.85897216796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.831131591796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.804447021484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.768946533203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7306689453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6900732421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.639423828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5880609130859376, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.53970703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4695806884765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.4034857177734374, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.310069274902344, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.221968688964844, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.1387432861328124, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.034661865234375, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.9150163269042968, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.7855165100097656, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.6699332427978515, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.5348751831054688, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.4047467803955078, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.2716168022155763, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.1428778648376465, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.023765468597412, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.9003810405731201, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.805734031200409, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.73134343624115, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6457895076274872, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5637272983789444, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.504421808719635, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.45952163070440294, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.4095659238100052, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.37283653125166893, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3366397958993912, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.30683418035507204, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.280039090514183, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2583443181216717, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.23817882865667342, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.21712184719741345, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.20333933897316456, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1927046923339367, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.180715117380023, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1717801835760474, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1629642243310809, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.15499355416744948, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.14920422181487084, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.14345581706613303, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.13947240505367517, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006491002638358623, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006405170389916748, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006267016110941767, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006134405934717506, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.006008091925177723, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00584360416745767, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0056712535512633624, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0054932422982528805, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005288734307978302, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005103674742858857, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004952140960376709, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00477230288204737, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0046386004658415915, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0044875702017452565, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004366889436496422, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004260227475315332, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004129201234318316, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003977424966869876, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003810011084424332, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003657624690094963, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0034753941476810724, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003296244266675785, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0031078748765867204, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002919956137193367, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002738286758540198, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002541068565333262, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0023822765448130666, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002252313285134733, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002096701021655463, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0019404741964535789, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0018231803155504167, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0017311504512326791, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0016253355197841301, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0015448713779915124, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001462285118177533, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013917950459290296, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0013263673373148776, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0012710708568920382, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0012182106749969535, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001160574427631218, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0011218407738488167, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0010913638325291686, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001055978357908316, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0010291975372820161, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00100264617591165, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.000978938635380473, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009623219858622178, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0009468331281095743, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009379250704660081, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.904698133468628, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8861958980560303, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.856600761413574, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8283770084381104, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8013787269592285, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.76552152633667, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7268595695495605, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.6859514713287354, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.6348752975463867, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.58308744430542, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.534320592880249, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4637088775634766, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.3970448970794678, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.302722930908203, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.213996648788452, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.1301941871643066, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.025618076324463, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.9056035280227661, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.776200771331787, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6608421802520752, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.5265629291534424, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3977023363113403, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2662458419799805, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.1395525932312012, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.0226541757583618, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.9018909931182861, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.8095383644104004, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7370291948318481, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6537622809410095, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5740253925323486, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5163558721542358, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.4728393852710724, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.42442551255226135, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3889133632183075, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3540098965167999, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3255000114440918, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.29999467730522156, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.279545396566391, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.26085931062698364, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.24160358309745789, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.22926956415176392, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21981316804885864, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20944839715957642, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.201905757188797, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.19466571509838104, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1883758008480072, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1838606894016266, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.17942608892917633, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.17648498713970184, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22271825396825398, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21899801587301587, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2152777777777778, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21106150793650794, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2105654761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2113095238095238, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21453373015873015, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21750992063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22470238095238096, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23288690476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.24379960317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.25892857142857145, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.28000992063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3229166666666667, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.38070436507936506, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.43526785714285715, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4945436507936508, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5637400793650794, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6240079365079365, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6674107142857143, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7199900793650794, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7606646825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8018353174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8330853174603174, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8578869047619048, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8797123015873016, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.892609126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8983134920634921, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9047619047619048, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9141865079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9211309523809523, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9248511904761905, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9295634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9332837301587301, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9375, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9429563492063492, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9466765873015873, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9518849206349206, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.955109126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9578373015873016, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9595734126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9637896825396826, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05938057089079717, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.058317317079207745, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05673368162791422, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05337389712707287, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05264469908746878, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0525801263971207, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05456072142245727, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05568472834890017, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06144391309414473, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06715135230487483, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07483451197235251, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.08727603737549378, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.10995136465731696, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.15812730736790154, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.221013587712081, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2746355895902707, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3268374789644533, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.38777899583800846, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4473926533503275, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5058200375631723, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6008942992660143, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6737350681185557, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7477078220890073, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.7982383526505581, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.836542752866151, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.864173064263812, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8804045056532501, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8869162814927739, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8950274451057095, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9061225806417573, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9125310302420315, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9164116803819149, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9219061928339811, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9264223113177567, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9309596796824586, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9338201376004762, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9370766928825861, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9403101201824475, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9459125573930733, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.949139235671631, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.950257192045953, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9514697710623773, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9520824109293051, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9526596146818229, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.953794172347717, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9553918921159993, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9569289762597636, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9580034766432936, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9592275179413586, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.13947240505367517, "validation/loss_best": 0.17648498713970184, "validation/acc_best": 0.9637896825396826, "validation/f1_best": 0.9592275179413586} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 1.2934613931179046, "train/grad": 0.025117926578968764, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.902325439453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8835302734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.85345458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.824786376953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.79729248046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.76076416015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.721546630859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.679874267578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6279656982421873, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5753155517578126, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5257769775390626, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4537091064453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.3857196044921873, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.289408874511719, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.19881591796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.1133624267578126, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.006773681640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.8844998168945313, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.7528400421142578, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.6360282135009765, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.5000860595703125, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.36995304107666, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.237470359802246, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.1102719116210937, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.9929662227630616, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.8722782230377197, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7801249027252197, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.7079806852340699, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6252963256835937, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5461627244949341, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4890691694617271, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.445847914814949, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.39777642592787743, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.3624623830616474, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.32760763764381406, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.29883643448352815, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.27298263274133205, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.25209611386060715, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2326773461699486, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.21231767050921918, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.19900253232568502, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.18878230471163987, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.17719748493283988, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.16858566902577876, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.16012024123221635, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.15240481987595558, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1468604627251625, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.14127254918217658, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.1373292263969779, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006448595100082457, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0063608934846706685, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006220176185015589, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0060846815025433895, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005956786677706986, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005791145861148834, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005617621128913015, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00544100885745138, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0052396152727305885, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005060106017626822, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004915578737854958, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00474545604782179, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004619668329833075, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004475428320001811, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004356981351738795, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004250052542192862, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004117552394745871, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003962917748140171, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003791812430135906, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003636614314746112, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003451926421839744, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0032706438982859254, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0030807953735347837, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002890932058217004, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002707867642166093, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025092654681066052, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002349479582044296, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002219199036480859, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0020634425967000426, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0019077931198989973, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017908061109483241, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016990136180538684, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0015933855867478997, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0015129218023503198, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001430734747555107, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013602026924490929, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001294932525488548, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0012398787785787135, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0011871155866538174, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0011297634115908296, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.001090732721495442, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0010604112708824686, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0010250831430312247, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009985184742254205, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009721271364833228, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.000947965155064594, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009310540804290213, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0009142195514868945, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009031757959746756, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.900623083114624, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8816781044006348, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8513431549072266, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.822467803955078, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7948977947235107, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7582013607025146, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.718761444091797, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.677032709121704, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.624877452850342, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.572183847427368, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5223727226257324, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4502384662628174, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.3821048736572266, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.2857673168182373, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.1951255798339844, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.109609603881836, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.003126859664917, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.8813660144805908, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7503905296325684, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6340854167938232, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.499203085899353, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3703724145889282, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2393611669540405, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.113762378692627, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9983039498329163, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.8795737028121948, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.789015531539917, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7181860208511353, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.637000560760498, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5594492554664612, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5034563541412354, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.46134254336357117, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4143814146518707, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.38009196519851685, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.346324622631073, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.31875577569007874, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.29420754313468933, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.2744999825954437, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.25635337829589844, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2377682626247406, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.22562193870544434, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21656838059425354, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2064858376979828, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.19908224046230316, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.19203810393810272, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.18567855656147003, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.18121211230754852, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.17672015726566315, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.17360956966876984, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2222222222222222, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21875, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.21378968253968253, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21006944444444445, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21006944444444445, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21155753968253968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2140376984126984, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21899801587301587, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22594246031746032, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23561507936507936, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.24677579365079366, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2638888888888889, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2857142857142857, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.33308531746031744, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.3923611111111111, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4466765873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5119047619047619, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5739087301587301, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6339285714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6790674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7301587301587301, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7720734126984127, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.808531746031746, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8392857142857143, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8625992063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8836805555555556, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8928571428571429, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8988095238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9074900793650794, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9149305555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9221230158730159, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9255952380952381, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9300595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9342757936507936, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9367559523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9429563492063492, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9471726190476191, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9533730158730159, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9583333333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9578373015873016, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9615575396825397, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05947744705480996, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.058431877684003895, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05597401555653153, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05250228428236699, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05203537319533121, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.052576289534163365, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.053696883475131664, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.056854572038416235, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06272872695927961, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0687799490100248, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07716253394753826, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09187232134776367, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11643483634944943, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1703114048547258, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.23309839203260083, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.28524136144769796, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3422111135582034, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.3948753130287625, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4609608694987487, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.523715670907632, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6182063929694843, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6942466171662934, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7602310230717837, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8064893626071943, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8425340714689911, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8694710920075995, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8804064266335255, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8876033954390407, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8982902979237327, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9066746251447978, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9140289035000628, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9170210402054205, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9223644140353277, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.927233152241334, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9304430931339857, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9344958541065477, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9376954503927315, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9423601760420639, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9456020001905117, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.948170984833469, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9517868386135826, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9533259822219171, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9539790264482362, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9531228911262049, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.956404329550023, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9564983294956924, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9565544444535968, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9574536935931015, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.957990919385764, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.1373292263969779, "validation/loss_best": 0.17360956966876984, "validation/acc_best": 0.9615575396825397, "validation/f1_best": 0.957990919385764} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 1.2873907136917113, "train/grad": 0.02489203592762351, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.9016748046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8828759765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8527978515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.824090576171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.796702880859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.760272216796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7210400390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6795977783203124, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.62767578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5750543212890626, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5251312255859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4528057861328123, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.3840966796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.2866094970703124, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.194822082519531, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.10797119140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9997869873046874, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.875940704345703, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.74284423828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.624803466796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.4876825714111328, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.3567659759521484, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.2237748527526855, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.096362953186035, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.9793249130249023, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.8592079114913941, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7678017234802246, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6963665580749512, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6145898592472077, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.536534925699234, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4802465718984604, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.43771771490573885, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.39038244754076, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.35553073316812517, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.321188283264637, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2928483609110117, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.2673096542805433, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2466380412131548, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.22729762703180312, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2070729922503233, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1937677277997136, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1835207573324442, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1718766801059246, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.16314953304827212, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.15451691433787346, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.14671694681048394, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.14099174730479716, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13524457573890686, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.13112290155142545, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006419668318703771, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006330572094302624, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006187532218173146, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006049765255302191, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005920151006430388, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0057523896475322545, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005576515942811966, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00539854204049334, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005197510065045208, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005019557715859264, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004877112752292305, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004711510357446968, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004588915028143674, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004447387378895655, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004329625439131632, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004222159127239138, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0040882210398558525, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003931692279875279, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0037586911383550616, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003601255262037739, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0034137498505879193, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003230290076462552, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0030374540318734945, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0028453941841144114, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026604608667548744, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0024606125813443212, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002300653757993132, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0021707748383050784, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0020161543920403347, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001861796822049655, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017460618843324483, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.001655739831039682, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0015520136198028923, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0014728121313964948, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001392137081711553, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013232629394042306, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001259135248255916, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0012057645613094792, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0011541219972423277, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0010982575299567543, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0010607674831408075, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001030879762256518, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0009961532073793932, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009698134681093507, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009433430767967365, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0009191439047572203, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009010678800405003, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.000883607958239736, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000871077899064403, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.897834539413452, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8785598278045654, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8477039337158203, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8183701038360596, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.790346384048462, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.753156900405884, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.713120460510254, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.670797824859619, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.6180341243743896, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.5645108222961426, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5141115188598633, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4409055709838867, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.37174129486084, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.2739531993865967, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.181950092315674, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.095360517501831, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.987549901008606, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.8644816875457764, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7324315309524536, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6157137155532837, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.4803874492645264, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3515082597732544, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2209233045578003, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0958982706069946, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9814826846122742, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.8641616702079773, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7748759984970093, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.7051808834075928, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6254599690437317, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5493325591087341, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.4945623576641083, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.4532611668109894, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.40734076499938965, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.37375587224960327, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3407669961452484, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3137989342212677, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.28982678055763245, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.2705431878566742, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2529767155647278, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23480427265167236, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.22310002148151398, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21422520279884338, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20445427298545837, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.19730889797210693, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.19042710959911346, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.18431596457958221, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.18002864718437195, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.17568624019622803, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1726643443107605, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2222222222222222, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21850198412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2130456349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21031746031746032, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2105654761904762, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21453373015873015, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.2197420634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22743055555555555, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23685515873015872, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.24851190476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.26711309523809523, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.29092261904761907, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.341765873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.40029761904761907, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.45436507936507936, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5205853174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5835813492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6411210317460317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6860119047619048, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7366071428571429, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7787698412698413, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8132440476190477, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8425099206349206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8655753968253969, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8854166666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8950892857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9017857142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9092261904761905, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9161706349206349, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9233630952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9265873015873016, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9300595238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9345238095238095, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9387400793650794, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9441964285714286, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9575892857142857, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9578373015873016, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9595734126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9600694444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9645337301587301, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06004863497353727, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.058759916346743234, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.055537806409658344, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.052641886883025825, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0523082860858879, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05296768407581002, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05379548106371451, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0571893854731869, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06362770746807704, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0697842330991002, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0785205140026479, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09561932810111201, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12121859929324157, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1802967868770098, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.24025277771910358, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.2927370074768337, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.34994737811228427, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4060288148230557, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.46962269789735067, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5358971561657753, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6295682346218656, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7054721420290505, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7663381753015985, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8117991904966634, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8460837515983213, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8715743987006507, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8837550132249999, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8906933354104053, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9005415737742188, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9083558174426744, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.91521043867016, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9188369430415924, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9231134079983997, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9280760397011136, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9328446750284373, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9348419763239397, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9387236847223113, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9423006856526419, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9464248467851678, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.949364415435187, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.951112063790548, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9514570380659156, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.95256225093787, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9545367818669386, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9546286509170832, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.956538995325373, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9588203388992934, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9591424015531267, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9601560884172378, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.13112290155142545, "validation/loss_best": 0.1726643443107605, "validation/acc_best": 0.9645337301587301, "validation/f1_best": 0.9601560884172378} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 1.2800150501728058, "train/grad": 0.02486548911780119, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.899061279296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.87970947265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.848992919921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.819658203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.79174072265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.754599609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.71447509765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6721893310546876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6191790771484373, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.56557373046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5147918701171874, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.44130126953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.371602783203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.2730447387695314, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.180225830078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.092776184082031, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9839430236816407, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.8595814514160156, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.7260666656494141, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.6080689239501953, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.4712432861328124, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.3408746147155761, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.2087577438354493, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.0824529361724853, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.9665929698944091, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.8479408407211304, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7577514672279357, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6873378777503967, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6068196141719818, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5299195292592048, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.47443564742803573, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.43252703875303267, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.38583727955818176, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.3514839192479849, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3176644904911518, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.28969925925135614, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.26453698351979255, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.24418499052524567, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.22527773432433607, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.20541371893137694, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.19238299157470465, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1822919712588191, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.17084823593497275, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.16234306409955024, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.15381867676973343, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.14612449411302805, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.14044718645513057, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13465313494205475, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.13049476388841869, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006429709026124328, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006339334698859602, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006193775346037001, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006054658011998981, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005923610471654683, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005754324297886342, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00557565500959754, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005396577238570899, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005194189101457596, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005015200129710138, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004872475329320878, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004705975875258446, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004582530242623761, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004438802908407524, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0043186024902388456, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004208794212900102, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0040723153611179445, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003913198630325496, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003738274072529748, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003579801535233855, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003391872813226655, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0032082431763410567, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0030156840139534324, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0028236353141255677, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026391295180656017, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002440078661311418, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002281340918270871, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0021527263353345915, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0020005083968862893, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0018502003862522543, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017379518906818702, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016504553152481094, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001550191079149954, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0014738449099240825, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0013957673896220512, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013288232826744206, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0012662212137365713, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001213688306743279, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001162837824667804, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0011072758267982863, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0010692863463191316, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001039063218049705, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0010038760810857639, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009768658102257176, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009492823824984953, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0009242371231084689, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009056101075839251, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0008870728395413607, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0008736202004365623, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.896097183227539, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8765854835510254, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.845459222793579, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.815810441970825, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7875590324401855, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.750009536743164, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.709651470184326, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.666966438293457, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.613659143447876, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.559809446334839, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5089259147644043, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.435060739517212, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.3653032779693604, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.266568422317505, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.173762798309326, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.0864410400390625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.977784514427185, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.853985071182251, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7211769819259644, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6041126251220703, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.4685763120651245, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.339718222618103, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2094991207122803, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0848751068115234, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9710628986358643, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.8545077443122864, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7661740779876709, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6970338225364685, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6183449625968933, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.543046236038208, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.48894941806793213, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.4482184052467346, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.4028642773628235, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.369799941778183, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3372684419155121, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.31057360768318176, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.28692755103111267, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.26797571778297424, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.25044745206832886, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23254746198654175, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.22104907035827637, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21229179203510284, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20254041254520416, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1955428272485733, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18866829574108124, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1825398951768875, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1782250851392746, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1738925576210022, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.17077264189720154, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22098214285714285, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2177579365079365, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.21329365079365079, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.20982142857142858, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21031746031746032, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.21428571428571427, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21999007936507936, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2279265873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23735119047619047, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2490079365079365, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.26785714285714285, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.29365079365079366, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.34598214285714285, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.40575396825396826, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.46056547619047616, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5248015873015873, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5892857142857143, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6436011904761905, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6897321428571429, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7400793650793651, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7814980158730159, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8177083333333334, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8447420634920635, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8673115079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8869047619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8965773809523809, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9025297619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9084821428571429, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9171626984126984, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9231150793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9268353174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9312996031746031, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.935515873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9402281746031746, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9456845238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9486607142857143, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9533730158730159, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9635416666666666, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.058978479158806024, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.058269977952529285, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05576695386864069, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05224185177341386, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05219570085530487, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05304568454068313, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05350716769166927, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05745204891975461, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06388045091793994, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07028143604125778, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07874226065301387, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0962948173184891, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12446622984855886, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18495947460264617, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.24499072379913134, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.29828720733706876, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.35339894959611273, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.41374349786897663, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4726928986979266, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5438896058125906, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6372662682191415, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7114034468573304, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7736183288214907, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8156372812235925, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8491097348031109, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8728425425944621, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.885081000539329, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8916161442405485, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9001004603478299, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9093929907982076, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9149919996989456, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9191080871702842, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9243855009010996, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9292072560271152, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9342684317790173, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9347321163685443, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9400152304253194, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9434175865457236, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9478563595525158, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9495125847141126, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9499025556858994, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9515192677696895, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.954022168222511, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9555225505819299, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9560811584138588, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9574851584478549, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9578701159197307, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9592174088148915, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9597674254586794, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.13049476388841869, "validation/loss_best": 0.17077264189720154, "validation/acc_best": 0.9635416666666666, "validation/f1_best": 0.9597674254586794} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 1.2792203557491302, "train/grad": 0.02474680875428021, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.89742431640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.87805419921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.847159423828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.817886962890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7898095703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.752640380859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7125103759765623, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6700946044921876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6171099853515627, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.563370361328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5125799560546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4385968017578126, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.36861572265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.269331359863281, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.1758953857421877, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.087920837402344, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9783128356933595, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.8533428955078124, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.719466552734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.6010987091064453, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.4641887664794921, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.3341296195983887, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.2024257850646973, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.0767687702178954, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.9618134593963623, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.8442419242858886, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7549812531471253, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6853630292415619, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6057899677753449, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5299078148603439, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4752314367890358, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.43392317950725556, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.3879632578790188, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.35415897458791734, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3207620342075825, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.29324312388896945, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.268418942540884, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.24826679080724717, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2294577020406723, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2097155835852027, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.19665798190981149, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.18662409167736768, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.17517171163111925, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1665789770707488, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.15797683779150248, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.15010053664445877, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.14432931412011385, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13835941199213267, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.1340270446240902, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006395580007229, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006304394651670009, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006158407505135983, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006019069217145443, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005887378267943859, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005718476444017142, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0055400226777419445, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005361667277757078, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005161236883141101, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0049854620941914615, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0048456625896506015, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00468356120865792, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0045633295271545644, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004423146857880056, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0043045037891715765, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004195493614533916, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0040596835757605735, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0039010969654191285, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0037266795861069114, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003568692214321345, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033815479569602757, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003199043538188562, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003007474449696019, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0028168032434768976, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026333159219939263, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002435140546876937, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0022771917126374317, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0021490766713395714, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0019969814730575308, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0018458325421670451, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017327516950899735, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016449747286969795, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0015442844753852114, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001467931171064265, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0013897906488273292, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013234958625980653, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0012614427303196862, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0012093716007075272, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001159348716319073, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0011046714914846234, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0010671225824626163, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0010378358289017341, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0010030116126290524, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009764052566606551, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009491961705498397, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0009235024251393043, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009047391230706125, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0008849081824882887, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000870422026491724, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8951611518859863, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8755691051483154, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8442625999450684, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.814485549926758, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.786087989807129, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7483434677124023, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.707838535308838, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.664931535720825, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.611443519592285, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.5573017597198486, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5062015056610107, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4319937229156494, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.3619256019592285, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.2627508640289307, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.1694657802581787, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.0817859172821045, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.97274649143219, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.8484563827514648, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.715459942817688, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.597959280014038, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.462345838546753, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3334920406341553, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2033463716506958, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0791031122207642, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9655510187149048, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.8494721055030823, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7613862156867981, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.692794919013977, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6144517064094543, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5396867394447327, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.48609134554862976, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.44552481174468994, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.40053054690361023, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3676908314228058, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.33537557721138, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.30903539061546326, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.2855050563812256, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.26667025685310364, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.24937143921852112, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23164185881614685, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.22021088004112244, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21152007579803467, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2019251585006714, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.19490253925323486, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18808132410049438, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1821727603673935, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.17787955701351166, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.17354337871074677, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.17047588527202606, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22073412698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21676587301587302, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2130456349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.20982142857142858, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21006944444444445, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2123015873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2140376984126984, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21999007936507936, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22817460317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2378472222222222, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.24975198412698413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.2681051587301587, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.29464285714285715, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3482142857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.408234126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4632936507936508, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5270337301587301, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5912698412698413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6450892857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6909722222222222, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7413194444444444, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7844742063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8199404761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8472222222222222, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8680555555555556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8876488095238095, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8970734126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9032738095238095, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9087301587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9174107142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9233630952380952, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9273313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9308035714285714, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.935515873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9397321428571429, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9409722222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9595734126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9627976190476191, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05896184526088633, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.057566252244353085, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.055724436653571394, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.052114170076116316, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05176900422737839, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05311717375330468, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05336384067890611, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05732345360657851, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06417008714131385, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07041210019569541, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07937845005503134, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09666882452924808, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1252102777284276, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18781671987236245, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.24773331766013146, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.3008866460562318, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.35594609870245697, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.41558138007595696, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.475435761376705, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5460512279423587, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6391557448475472, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7164700083870793, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7766856579723923, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8186246121704702, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8498420836022641, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8741570898898627, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8853061513749875, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8925055526082294, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9001942494001953, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.909929620966387, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9152713039986983, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9189075170338343, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9239597954574575, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.929256962046277, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9338016257796301, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9351409027534472, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9393039427693504, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9431500113202254, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.947067589373743, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.94964446667993, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9506682492408032, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.951815564858608, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.953257416735045, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9548011507918481, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9568773538808552, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9578834056711296, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9586958922815405, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9588486961342431, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9593696105016323, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.1340270446240902, "validation/loss_best": 0.17047588527202606, "validation/acc_best": 0.9627976190476191, "validation/f1_best": 0.9593696105016323} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 1.2751686054468154, "train/grad": 0.024874162748456, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.896661376953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.877154541015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.846162109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.816650390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.78845458984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.751092529296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.710782470703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6681573486328123, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6150775146484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.561097412109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5101202392578124, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.43586181640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.3656402587890626, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.2660140991210938, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.172166748046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.0837725830078124, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9738331604003907, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.8483285522460937, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.7139307403564452, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.5952442169189454, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.4578938674926758, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.3275582695007324, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.1955358123779296, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.06965106010437, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.9545289039611816, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.8369442439079284, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7477990317344666, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6783376729488373, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.599171599149704, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5236737251281738, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4693355721235275, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.428342986702919, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.3826902829110622, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.34914915293455123, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3160613179206848, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2887411864846945, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.26415744319558143, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.24423023849725722, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.22562341079115866, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2061176074296236, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1932541996240616, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.18331371616572142, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1719429587572813, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.16338056091219186, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.15487415201961993, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1470783757045865, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.14127957623451948, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1353487579897046, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.13104480650275946, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.006423182121943682, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0063316115969792005, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0061853691865690055, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.006045231241732836, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005913590942509472, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005743809398263693, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005565077597275377, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005386995333246887, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005186386764980852, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005010450130794197, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004870393157470971, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0047088683745823805, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00458890448207967, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0044476292305625975, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004327814675634727, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004217606643214822, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0040802090393845, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003919556946493685, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0037424973945599047, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003582779343705624, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033939461805857717, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0032103123690467327, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003018528672400862, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002828248138539493, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026458582538180053, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002449746384518221, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002293671715888195, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002166946685756557, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0020164591708453374, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00186626901733689, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017536309361457824, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016657895315438508, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0015640440065180883, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0014866964722750709, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0014071248873369767, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013392542314250022, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0012759896015631966, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001222532136598602, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0011714442700031214, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0011154812388122083, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0010771624435437844, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001046762024925556, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0010110903874738142, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.000983470714709256, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009552422480192035, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0009286478512512985, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009087991387059447, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0008878914617525879, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0008724753378191963, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.894805908203125, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8751814365386963, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.843824625015259, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8139729499816895, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7855441570281982, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.747743844985962, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.707110643386841, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.664189100265503, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.610635757446289, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.556375026702881, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5051467418670654, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4308876991271973, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.3606486320495605, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.261291980743408, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.167778730392456, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.079986572265625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.9708760976791382, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.846340298652649, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7132384777069092, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5958106517791748, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.4600553512573242, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3311724662780762, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.200974702835083, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.076940655708313, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9634315967559814, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.847581148147583, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7597196102142334, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6911437511444092, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6130003929138184, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5383599996566772, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.4848736524581909, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.4446377158164978, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.39974144101142883, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3668938875198364, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3347332179546356, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3084581792354584, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.2849210798740387, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.26620930433273315, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.24895991384983063, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23120719194412231, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.21982872486114502, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2112114429473877, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20162993669509888, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.19463442265987396, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1879051774740219, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.18192288279533386, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.17756716907024384, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.173334538936615, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1703517585992813, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22123015873015872, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21676587301587302, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2123015873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.20982142857142858, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21006944444444445, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2140376984126984, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22023809523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22817460317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2378472222222222, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.24975198412698413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.26860119047619047, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.29464285714285715, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3492063492063492, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4089781746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4650297619047619, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5280257936507936, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5922619047619048, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6458333333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6922123015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7425595238095238, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.785218253968254, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8199404761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8459821428571429, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8687996031746031, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8871527777777778, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8968253968253969, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9027777777777778, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9089781746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.917906746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9231150793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9275793650793651, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9308035714285714, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9357638888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9412202380952381, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9526289682539683, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9595734126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9625496031746031, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05939319286907557, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05766332010344686, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05482204829749008, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05216849538287677, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0517827996172974, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05282450492798038, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05341043083900227, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05758611850088474, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06412084201377803, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07056702425015852, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07928646623824781, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0968648750658986, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12514344071780736, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.18886197713422712, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.2483475786734753, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.3021949560656973, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3567537973473498, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.41656026431329307, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.47610505866219294, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5487863205482348, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6416804105678493, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7182368249572727, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7766298722131746, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8171831972155849, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8511203375267083, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8733288136658862, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8850751559727603, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8917249652765911, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9007676282150257, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9100802848897881, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.915052231451098, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9194671018739755, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9239714268314424, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9294571383614103, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9340210363196152, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9353735525369776, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9393659565669978, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9431556291102124, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9474459366317745, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9504276922595619, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9506660959900863, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9513378807762236, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9542829375731372, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.954919732155555, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9560727826071811, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9570259976566083, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9579312319747353, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9583179827024173, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9589855807637898, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.13104480650275946, "validation/loss_best": 0.1703517585992813, "validation/acc_best": 0.9625496031746031, "validation/f1_best": 0.9589855807637898} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 1.2689196962118148, "train/grad": 0.024606087179854512, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.895152587890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8754443359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.84389404296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.813941650390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.78532958984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7473828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7065283203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.663331298828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.60944580078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5548016357421877, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.50330078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4283880615234374, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.35760498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.257273864746094, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.162962646484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.0743511962890624, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9640480041503907, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.838355712890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.7037790679931641, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.5850392913818359, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.4476746368408202, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.317256259918213, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.1854589653015137, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.059957628250122, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.9451316499710083, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.828055374622345, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7393281292915345, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6702971160411835, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5915523993968964, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5165944290161133, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4626682448387146, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.4220344358682632, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.37678856059908866, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.34350439690053464, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3107332322001457, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.28364181369543073, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.2592909698933363, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.23950733825564385, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.22104273363947868, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.20167614191770553, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.188899860419333, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.17898131936788558, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.16775235787034035, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.15926923621445893, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1507838084548712, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.14305341951549053, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.13730160992592574, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1313835310935974, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.12709088042378425, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0063716033357195554, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.006279673404060304, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.006132489291485399, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005991765533108265, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005859818703029305, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005689667798578739, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005510762620251626, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005333219282329082, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005133445321116596, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004958991827443242, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004820417917799204, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004662073359359056, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004543834188953042, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004405811377801001, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004288115713279694, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004179811464855448, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004044250238221139, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038851122942287473, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0037101362308021636, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0035513930628076197, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033632281760219485, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0031791649514343588, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0029864670406095683, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0027943644230253996, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026100021111778917, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0024115101573988795, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0022534750122576953, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0021254899393534287, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0019734534883173185, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0018227530003059656, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017103361623594538, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016231197572778911, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0015227963076904416, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001446870209183544, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00136990787810646, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013042777677765116, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0012431668135104701, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001192102969798725, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0011425419643637724, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0010886695547378622, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0010517177765723318, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0010221053787972778, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0009873608333873561, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009603833733126522, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009324548480799422, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0009062923182500527, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0008863123145420104, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0008652724226703867, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0008499120133637916, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8947601318359375, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8751323223114014, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8437724113464355, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8138997554779053, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7854487895965576, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.747664451599121, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7070207595825195, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.6640963554382324, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.6105244159698486, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.5562500953674316, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.505014181137085, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4307284355163574, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.3604736328125, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.261049509048462, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.1675713062286377, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.0797410011291504, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.970566987991333, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.8460180759429932, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7129250764846802, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5954793691635132, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.4597526788711548, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3308161497116089, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.2006689310073853, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0766311883926392, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9631659984588623, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.8472450375556946, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.7594018578529358, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6909990906715393, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.6127880215644836, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5381932258605957, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.48472321033477783, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.4444461762905121, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.3995732069015503, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3667849004268646, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3346218764781952, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.3083305358886719, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.2848605215549469, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.26616722345352173, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.24885781109333038, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2312079221010208, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2196470946073532, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2111232876777649, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.20152555406093597, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.19454635679721832, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.18781225383281708, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.18177153170108795, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1774396449327469, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.17326240241527557, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.17021863162517548, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22123015873015872, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.21676587301587302, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2095734126984127, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21006944444444445, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.21205357142857142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2140376984126984, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.22023809523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.22817460317460317, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.23759920634920634, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.24975198412698413, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.26884920634920634, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.29464285714285715, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3492063492063492, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.40922619047619047, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.4652777777777778, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5277777777777778, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5925099206349206, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6458333333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6924603174603174, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7423115079365079, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7849702380952381, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8204365079365079, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8459821428571429, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8687996031746031, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.886656746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8970734126984127, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9025297619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9087301587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9181547619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9236111111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9278273809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9310515873015873, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9357638888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9412202380952381, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9454365079365079, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9484126984126984, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9526289682539683, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.957093253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9595734126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9625496031746031, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0594457171634876, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.057688124240077576, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05453249863440299, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05187512819721585, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0517827996172974, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05282450492798038, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05341043083900227, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05758611850088474, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06412084201377803, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.07034696837293004, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07928646623824781, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.09732088991750786, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.12514344071780736, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.188903691750378, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.2485986471278412, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.3025678424061046, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3565170940964226, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.4167466818816015, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.47593681152167666, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5498323743535322, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.641529170059214, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7180416468587802, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7773840826197054, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8172932165958329, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8511203375267083, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8729143180266428, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8856410258155624, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8915815797822172, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9006650781589742, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9104463215941558, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9156723579153476, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9196873918789656, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9239629979392454, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9294571383614103, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9340210363196152, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9353635802643107, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9395434835029994, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9433341472541624, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9474146868731481, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9501983147356784, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9507078495627713, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9516744934345606, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9544608679016061, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9549870479308156, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9566149291017796, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9574371321818754, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9581017164472727, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9577602890644556, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9586458448009709, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.12709088042378425, "validation/loss_best": 0.17021863162517548, "validation/acc_best": 0.9625496031746031, "validation/f1_best": 0.9586458448009709} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/config.yaml b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0ee5f5d8bf43d086fcb8240cdaf526fbc78ec02f --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (hcpya_task21 reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..5ca28d3b6cd79440b3e0dac555f13059f45e032f --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 9, "eval/id_best": 46, "eval/lr_best": 0.010799999999999999, "eval/wd_best": 0.05, "eval/train/loss": 0.05801542103290558, "eval/train/acc": 0.9909995262908574, "eval/train/acc_std": 0.0006576577238066316, "eval/train/f1": 0.9916705701537704, "eval/train/f1_std": 0.0006625940860695853, "eval/validation/loss": 0.09630896896123886, "eval/validation/acc": 0.9784226190476191, "eval/validation/acc_std": 0.00227750311820554, "eval/validation/f1": 0.9753798237842884, "eval/validation/f1_std": 0.002933939106903534, "eval/test/loss": 0.10561123490333557, "eval/test/acc": 0.9751984126984127, "eval/test/acc_std": 0.0023470206477333843, "eval/test/f1": 0.969762860336247, "eval/test/f1_std": 0.00316471131903427} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log_best.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..0ea9e511db85b9305595814d7eb607f2f0d8fdf0 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 9, "eval/best/id_best": 46, "eval/best/lr_best": 0.010799999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.05801542103290558, "eval/best/train/acc": 0.9909995262908574, "eval/best/train/acc_std": 0.0006576577238066316, "eval/best/train/f1": 0.9916705701537704, "eval/best/train/f1_std": 0.0006625940860695853, "eval/best/validation/loss": 0.09630896896123886, "eval/best/validation/acc": 0.9784226190476191, "eval/best/validation/acc_std": 0.00227750311820554, "eval/best/validation/f1": 0.9753798237842884, "eval/best/validation/f1_std": 0.002933939106903534, "eval/best/test/loss": 0.10561123490333557, "eval/best/test/acc": 0.9751984126984127, "eval/best/test/acc_std": 0.0023470206477333843, "eval/best/test/f1": 0.969762860336247, "eval/best/test/f1_std": 0.00316471131903427} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log_last.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..f0290c9213371ca4b2f26522ce6b41cbad9b1c27 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 42, "eval/last/lr_best": 0.005699999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.058460135012865067, "eval/last/train/acc": 0.9909995262908574, "eval/last/train/acc_std": 0.0006634415881078099, "eval/last/train/f1": 0.9915768423105734, "eval/last/train/f1_std": 0.0006776967243167487, "eval/last/validation/loss": 0.09533528238534927, "eval/last/validation/acc": 0.9779265873015873, "eval/last/validation/acc_std": 0.0022677584117296815, "eval/last/validation/f1": 0.9748475707500636, "eval/last/validation/f1_std": 0.0029409891591324613, "eval/last/test/loss": 0.10370934009552002, "eval/last/test/acc": 0.9748015873015873, "eval/last/test/acc_std": 0.0023443583005849926, "eval/last/test/f1": 0.9688658638933164, "eval/last/test/f1_std": 0.0031750932032714356} diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..71d7eb3699be8b2deeb00a6e90edb9623f725f59 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,best,9,0.010799999999999999,0.05,46,"[36, 1.0]",train,0.05801542103290558,0.9909995262908574,0.0006576577238066316,0.9916705701537704,0.0006625940860695853 +flat_mae,reg,linear,hcpya_task21,best,9,0.010799999999999999,0.05,46,"[36, 1.0]",validation,0.09630896896123886,0.9784226190476191,0.00227750311820554,0.9753798237842884,0.002933939106903534 +flat_mae,reg,linear,hcpya_task21,best,9,0.010799999999999999,0.05,46,"[36, 1.0]",test,0.10561123490333557,0.9751984126984127,0.0023470206477333843,0.969762860336247,0.00316471131903427 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..71d7eb3699be8b2deeb00a6e90edb9623f725f59 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,best,9,0.010799999999999999,0.05,46,"[36, 1.0]",train,0.05801542103290558,0.9909995262908574,0.0006576577238066316,0.9916705701537704,0.0006625940860695853 +flat_mae,reg,linear,hcpya_task21,best,9,0.010799999999999999,0.05,46,"[36, 1.0]",validation,0.09630896896123886,0.9784226190476191,0.00227750311820554,0.9753798237842884,0.002933939106903534 +flat_mae,reg,linear,hcpya_task21,best,9,0.010799999999999999,0.05,46,"[36, 1.0]",test,0.10561123490333557,0.9751984126984127,0.0023470206477333843,0.969762860336247,0.00316471131903427 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..6baa6731547446616d26623c042b34360ba17043 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",train,0.058460135012865067,0.9909995262908574,0.0006634415881078099,0.9915768423105734,0.0006776967243167487 +flat_mae,reg,linear,hcpya_task21,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",validation,0.09533528238534927,0.9779265873015873,0.0022677584117296815,0.9748475707500636,0.0029409891591324613 +flat_mae,reg,linear,hcpya_task21,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",test,0.10370934009552002,0.9748015873015873,0.0023443583005849926,0.9688658638933164,0.0031750932032714356 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/log.txt b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..73b18fba2c4d386b108c3dcbe7f60ba9d7227d5c --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/log.txt @@ -0,0 +1,886 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: clean, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 21:11:35 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (hcpya_task21 reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 0.8M (0.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:21:24 lr: nan time: 3.2115 data: 2.8811 max mem: 3910 +train: [0] [ 20/400] eta: 0:02:50 lr: 0.000003 loss: 3.0429 (3.0419) grad: 0.0606 (0.0622) time: 0.3105 data: 0.0033 max mem: 3951 +train: [0] [ 40/400] eta: 0:02:22 lr: 0.000006 loss: 3.0369 (3.0372) grad: 0.0605 (0.0612) time: 0.3378 data: 0.0035 max mem: 3951 +train: [0] [ 60/400] eta: 0:02:07 lr: 0.000009 loss: 3.0309 (3.0341) grad: 0.0609 (0.0614) time: 0.3318 data: 0.0037 max mem: 3951 +train: [0] [ 80/400] eta: 0:01:55 lr: 0.000012 loss: 3.0185 (3.0291) grad: 0.0613 (0.0612) time: 0.3274 data: 0.0040 max mem: 3951 +train: [0] [100/400] eta: 0:01:48 lr: 0.000015 loss: 3.0082 (3.0228) grad: 0.0589 (0.0607) time: 0.3550 data: 0.0042 max mem: 3951 +train: [0] [120/400] eta: 0:01:40 lr: 0.000018 loss: 2.9855 (3.0160) grad: 0.0596 (0.0606) time: 0.3386 data: 0.0042 max mem: 3951 +train: [0] [140/400] eta: 0:01:31 lr: 0.000021 loss: 2.9637 (3.0069) grad: 0.0603 (0.0605) time: 0.3184 data: 0.0036 max mem: 3951 +train: [0] [160/400] eta: 0:01:23 lr: 0.000024 loss: 2.9448 (2.9980) grad: 0.0585 (0.0600) time: 0.3311 data: 0.0041 max mem: 3951 +train: [0] [180/400] eta: 0:01:16 lr: 0.000027 loss: 2.9231 (2.9872) grad: 0.0570 (0.0600) time: 0.3554 data: 0.0043 max mem: 3951 +train: [0] [200/400] eta: 0:01:09 lr: 0.000030 loss: 2.8866 (2.9759) grad: 0.0578 (0.0598) time: 0.3365 data: 0.0040 max mem: 3951 +train: [0] [220/400] eta: 0:01:02 lr: 0.000033 loss: 2.8538 (2.9630) grad: 0.0578 (0.0597) time: 0.3402 data: 0.0041 max mem: 3951 +train: [0] [240/400] eta: 0:00:55 lr: 0.000036 loss: 2.8197 (2.9504) grad: 0.0566 (0.0595) time: 0.3348 data: 0.0040 max mem: 3951 +train: [0] [260/400] eta: 0:00:48 lr: 0.000039 loss: 2.7889 (2.9367) grad: 0.0563 (0.0594) time: 0.3544 data: 0.0040 max mem: 3951 +train: [0] [280/400] eta: 0:00:41 lr: 0.000042 loss: 2.7537 (2.9228) grad: 0.0558 (0.0591) time: 0.3471 data: 0.0040 max mem: 3951 +train: [0] [300/400] eta: 0:00:35 lr: 0.000045 loss: 2.7190 (2.9078) grad: 0.0546 (0.0589) time: 0.5293 data: 0.1890 max mem: 3951 +train: [0] [320/400] eta: 0:00:28 lr: 0.000048 loss: 2.6825 (2.8929) grad: 0.0550 (0.0587) time: 0.3463 data: 0.0031 max mem: 3951 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 2.6420 (2.8779) grad: 0.0556 (0.0585) time: 0.3389 data: 0.0039 max mem: 3951 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 2.6146 (2.8624) grad: 0.0556 (0.0584) time: 0.3241 data: 0.0042 max mem: 3951 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 2.5736 (2.8469) grad: 0.0546 (0.0582) time: 0.3521 data: 0.0040 max mem: 3951 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.5454 (2.8305) grad: 0.0546 (0.0580) time: 0.3275 data: 0.0038 max mem: 3951 +train: [0] Total time: 0:02:21 (0.3547 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.5454 (2.8305) grad: 0.0546 (0.0580) +eval (validation): [0] [ 0/63] eta: 0:03:16 time: 3.1207 data: 2.9079 max mem: 3951 +eval (validation): [0] [20/63] eta: 0:00:18 time: 0.2935 data: 0.0032 max mem: 3951 +eval (validation): [0] [40/63] eta: 0:00:08 time: 0.3118 data: 0.0029 max mem: 3951 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3189 data: 0.0034 max mem: 3951 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3180 data: 0.0032 max mem: 3951 +eval (validation): [0] Total time: 0:00:22 (0.3584 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.643 acc: 0.942 f1: 0.932 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:20:57 lr: nan time: 3.1439 data: 2.9105 max mem: 3951 +train: [1] [ 20/400] eta: 0:02:56 lr: 0.000063 loss: 2.5008 (2.4944) grad: 0.0552 (0.0551) time: 0.3304 data: 0.0060 max mem: 3951 +train: [1] [ 40/400] eta: 0:02:24 lr: 0.000066 loss: 2.4841 (2.4858) grad: 0.0544 (0.0543) time: 0.3335 data: 0.0033 max mem: 3951 +train: [1] [ 60/400] eta: 0:02:07 lr: 0.000069 loss: 2.4648 (2.4754) grad: 0.0544 (0.0546) time: 0.3238 data: 0.0036 max mem: 3951 +train: [1] [ 80/400] eta: 0:01:56 lr: 0.000072 loss: 2.4421 (2.4611) grad: 0.0528 (0.0541) time: 0.3283 data: 0.0038 max mem: 3951 +train: [1] [100/400] eta: 0:01:49 lr: 0.000075 loss: 2.4086 (2.4484) grad: 0.0504 (0.0534) time: 0.3707 data: 0.0040 max mem: 3951 +train: [1] [120/400] eta: 0:01:41 lr: 0.000078 loss: 2.3806 (2.4356) grad: 0.0510 (0.0535) time: 0.3498 data: 0.0041 max mem: 3951 +train: [1] [140/400] eta: 0:01:34 lr: 0.000081 loss: 2.3601 (2.4219) grad: 0.0512 (0.0533) time: 0.3706 data: 0.0042 max mem: 3951 +train: [1] [160/400] eta: 0:01:26 lr: 0.000084 loss: 2.3344 (2.4103) grad: 0.0506 (0.0531) time: 0.3390 data: 0.0041 max mem: 3951 +train: [1] [180/400] eta: 0:01:18 lr: 0.000087 loss: 2.3075 (2.3974) grad: 0.0505 (0.0530) time: 0.3193 data: 0.0036 max mem: 3951 +train: [1] [200/400] eta: 0:01:11 lr: 0.000090 loss: 2.2825 (2.3854) grad: 0.0501 (0.0527) time: 0.3470 data: 0.0040 max mem: 3951 +train: [1] [220/400] eta: 0:01:03 lr: 0.000093 loss: 2.2485 (2.3719) grad: 0.0508 (0.0526) time: 0.3512 data: 0.0039 max mem: 3951 +train: [1] [240/400] eta: 0:00:56 lr: 0.000096 loss: 2.2351 (2.3600) grad: 0.0510 (0.0524) time: 0.3265 data: 0.0038 max mem: 3951 +train: [1] [260/400] eta: 0:00:49 lr: 0.000099 loss: 2.2022 (2.3468) grad: 0.0506 (0.0523) time: 0.3220 data: 0.0039 max mem: 3951 +train: [1] [280/400] eta: 0:00:41 lr: 0.000102 loss: 2.1948 (2.3359) grad: 0.0482 (0.0521) time: 0.3261 data: 0.0040 max mem: 3951 +train: [1] [300/400] eta: 0:00:35 lr: 0.000105 loss: 2.1758 (2.3238) grad: 0.0480 (0.0520) time: 0.5048 data: 0.1873 max mem: 3951 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 2.1589 (2.3138) grad: 0.0484 (0.0518) time: 0.3206 data: 0.0034 max mem: 3951 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 2.1273 (2.3014) grad: 0.0505 (0.0518) time: 0.2998 data: 0.0037 max mem: 3951 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 2.0899 (2.2890) grad: 0.0515 (0.0517) time: 0.3084 data: 0.0038 max mem: 3951 +train: [1] [380/400] eta: 0:00:06 lr: 0.000117 loss: 2.0745 (2.2778) grad: 0.0493 (0.0516) time: 0.3071 data: 0.0041 max mem: 3951 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.0712 (2.2675) grad: 0.0489 (0.0515) time: 0.3124 data: 0.0040 max mem: 3951 +train: [1] Total time: 0:02:18 (0.3472 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.0712 (2.2675) grad: 0.0489 (0.0515) +eval (validation): [1] [ 0/63] eta: 0:03:11 time: 3.0363 data: 2.7902 max mem: 3951 +eval (validation): [1] [20/63] eta: 0:00:18 time: 0.3102 data: 0.0049 max mem: 3951 +eval (validation): [1] [40/63] eta: 0:00:08 time: 0.3096 data: 0.0027 max mem: 3951 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.2873 data: 0.0030 max mem: 3951 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.2840 data: 0.0031 max mem: 3951 +eval (validation): [1] Total time: 0:00:21 (0.3487 s / it) +cv: [1] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.229 acc: 0.966 f1: 0.960 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:19:16 lr: nan time: 2.8905 data: 2.6915 max mem: 3951 +train: [2] [ 20/400] eta: 0:02:44 lr: 0.000123 loss: 2.0368 (2.0454) grad: 0.0481 (0.0489) time: 0.3106 data: 0.0056 max mem: 3951 +train: [2] [ 40/400] eta: 0:02:15 lr: 0.000126 loss: 2.0368 (2.0372) grad: 0.0489 (0.0489) time: 0.3145 data: 0.0027 max mem: 3951 +train: [2] [ 60/400] eta: 0:02:00 lr: 0.000129 loss: 2.0032 (2.0207) grad: 0.0482 (0.0485) time: 0.3105 data: 0.0036 max mem: 3951 +train: [2] [ 80/400] eta: 0:01:50 lr: 0.000132 loss: 1.9847 (2.0155) grad: 0.0474 (0.0482) time: 0.3202 data: 0.0038 max mem: 3951 +train: [2] [100/400] eta: 0:01:42 lr: 0.000135 loss: 1.9870 (2.0094) grad: 0.0467 (0.0480) time: 0.3324 data: 0.0040 max mem: 3951 +train: [2] [120/400] eta: 0:01:34 lr: 0.000138 loss: 1.9794 (2.0002) grad: 0.0471 (0.0481) time: 0.3188 data: 0.0038 max mem: 3951 +train: [2] [140/400] eta: 0:01:27 lr: 0.000141 loss: 1.9548 (1.9945) grad: 0.0477 (0.0480) time: 0.3183 data: 0.0039 max mem: 3951 +train: [2] [160/400] eta: 0:01:20 lr: 0.000144 loss: 1.9583 (1.9887) grad: 0.0461 (0.0476) time: 0.3390 data: 0.0037 max mem: 3951 +train: [2] [180/400] eta: 0:01:14 lr: 0.000147 loss: 1.9288 (1.9813) grad: 0.0450 (0.0474) time: 0.3625 data: 0.0042 max mem: 3951 +train: [2] [200/400] eta: 0:01:07 lr: 0.000150 loss: 1.9186 (1.9741) grad: 0.0452 (0.0473) time: 0.3419 data: 0.0039 max mem: 3951 +train: [2] [220/400] eta: 0:01:01 lr: 0.000153 loss: 1.8874 (1.9649) grad: 0.0456 (0.0472) time: 0.3379 data: 0.0041 max mem: 3951 +train: [2] [240/400] eta: 0:00:54 lr: 0.000156 loss: 1.8708 (1.9578) grad: 0.0456 (0.0472) time: 0.3545 data: 0.0042 max mem: 3951 +train: [2] [260/400] eta: 0:00:47 lr: 0.000159 loss: 1.8708 (1.9508) grad: 0.0460 (0.0472) time: 0.3304 data: 0.0042 max mem: 3951 +train: [2] [280/400] eta: 0:00:40 lr: 0.000162 loss: 1.8628 (1.9449) grad: 0.0458 (0.0470) time: 0.3456 data: 0.0040 max mem: 3951 +train: [2] [300/400] eta: 0:00:35 lr: 0.000165 loss: 1.8399 (1.9375) grad: 0.0458 (0.0470) time: 0.5052 data: 0.1847 max mem: 3951 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 1.8314 (1.9317) grad: 0.0446 (0.0467) time: 0.3370 data: 0.0039 max mem: 3951 +train: [2] [340/400] eta: 0:00:20 lr: 0.000171 loss: 1.8286 (1.9246) grad: 0.0428 (0.0465) time: 0.3379 data: 0.0037 max mem: 3951 +train: [2] [360/400] eta: 0:00:13 lr: 0.000174 loss: 1.7951 (1.9183) grad: 0.0439 (0.0464) time: 0.3211 data: 0.0040 max mem: 3951 +train: [2] [380/400] eta: 0:00:06 lr: 0.000177 loss: 1.7951 (1.9118) grad: 0.0447 (0.0464) time: 0.3567 data: 0.0043 max mem: 3951 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 1.7844 (1.9046) grad: 0.0453 (0.0463) time: 0.3422 data: 0.0041 max mem: 3951 +train: [2] Total time: 0:02:19 (0.3484 s / it) +train: [2] Summary: lr: 0.000180 loss: 1.7844 (1.9046) grad: 0.0453 (0.0463) +eval (validation): [2] [ 0/63] eta: 0:03:06 time: 2.9665 data: 2.7620 max mem: 3951 +eval (validation): [2] [20/63] eta: 0:00:20 time: 0.3402 data: 0.0039 max mem: 3951 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3473 data: 0.0032 max mem: 3951 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3338 data: 0.0033 max mem: 3951 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3316 data: 0.0032 max mem: 3951 +eval (validation): [2] Total time: 0:00:24 (0.3864 s / it) +cv: [2] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.154 acc: 0.969 f1: 0.964 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:20:44 lr: nan time: 3.1111 data: 2.8978 max mem: 3951 +train: [3] [ 20/400] eta: 0:02:55 lr: 0.000183 loss: 1.7391 (1.7441) grad: 0.0456 (0.0452) time: 0.3285 data: 0.0036 max mem: 3951 +train: [3] [ 40/400] eta: 0:02:21 lr: 0.000186 loss: 1.7409 (1.7431) grad: 0.0446 (0.0449) time: 0.3214 data: 0.0035 max mem: 3951 +train: [3] [ 60/400] eta: 0:02:05 lr: 0.000189 loss: 1.7300 (1.7398) grad: 0.0436 (0.0448) time: 0.3238 data: 0.0025 max mem: 3951 +train: [3] [ 80/400] eta: 0:01:55 lr: 0.000192 loss: 1.7281 (1.7367) grad: 0.0420 (0.0441) time: 0.3330 data: 0.0036 max mem: 3951 +train: [3] [100/400] eta: 0:01:46 lr: 0.000195 loss: 1.7187 (1.7345) grad: 0.0426 (0.0440) time: 0.3317 data: 0.0037 max mem: 3951 +train: [3] [120/400] eta: 0:01:37 lr: 0.000198 loss: 1.7049 (1.7291) grad: 0.0433 (0.0440) time: 0.3087 data: 0.0034 max mem: 3951 +train: [3] [140/400] eta: 0:01:29 lr: 0.000201 loss: 1.6772 (1.7220) grad: 0.0435 (0.0441) time: 0.3374 data: 0.0040 max mem: 3951 +train: [3] [160/400] eta: 0:01:22 lr: 0.000204 loss: 1.6793 (1.7185) grad: 0.0433 (0.0439) time: 0.3291 data: 0.0039 max mem: 3951 +train: [3] [180/400] eta: 0:01:16 lr: 0.000207 loss: 1.6863 (1.7137) grad: 0.0425 (0.0440) time: 0.3663 data: 0.0039 max mem: 3951 +train: [3] [200/400] eta: 0:01:09 lr: 0.000210 loss: 1.6655 (1.7083) grad: 0.0438 (0.0440) time: 0.3388 data: 0.0038 max mem: 3951 +train: [3] [220/400] eta: 0:01:01 lr: 0.000213 loss: 1.6424 (1.7023) grad: 0.0435 (0.0440) time: 0.3315 data: 0.0036 max mem: 3951 +train: [3] [240/400] eta: 0:00:54 lr: 0.000216 loss: 1.6406 (1.6969) grad: 0.0425 (0.0439) time: 0.3274 data: 0.0040 max mem: 3951 +train: [3] [260/400] eta: 0:00:47 lr: 0.000219 loss: 1.6259 (1.6917) grad: 0.0412 (0.0437) time: 0.3282 data: 0.0039 max mem: 3951 +train: [3] [280/400] eta: 0:00:40 lr: 0.000222 loss: 1.6259 (1.6877) grad: 0.0408 (0.0436) time: 0.3337 data: 0.0043 max mem: 3951 +train: [3] [300/400] eta: 0:00:35 lr: 0.000225 loss: 1.6218 (1.6840) grad: 0.0412 (0.0435) time: 0.5021 data: 0.1913 max mem: 3951 +train: [3] [320/400] eta: 0:00:28 lr: 0.000228 loss: 1.6143 (1.6784) grad: 0.0412 (0.0434) time: 0.3718 data: 0.0039 max mem: 3951 +train: [3] [340/400] eta: 0:00:21 lr: 0.000231 loss: 1.5847 (1.6734) grad: 0.0417 (0.0434) time: 0.3419 data: 0.0035 max mem: 3951 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 1.5962 (1.6691) grad: 0.0412 (0.0433) time: 0.3401 data: 0.0040 max mem: 3951 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 1.5653 (1.6631) grad: 0.0419 (0.0433) time: 0.3622 data: 0.0042 max mem: 3951 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 1.5691 (1.6591) grad: 0.0415 (0.0431) time: 0.3432 data: 0.0041 max mem: 3951 +train: [3] Total time: 0:02:21 (0.3525 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.5691 (1.6591) grad: 0.0415 (0.0431) +eval (validation): [3] [ 0/63] eta: 0:03:10 time: 3.0276 data: 2.7658 max mem: 3951 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3631 data: 0.0031 max mem: 3951 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3541 data: 0.0031 max mem: 3951 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3294 data: 0.0035 max mem: 3951 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3179 data: 0.0035 max mem: 3951 +eval (validation): [3] Total time: 0:00:24 (0.3956 s / it) +cv: [3] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.140 acc: 0.972 f1: 0.967 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:21:37 lr: nan time: 3.2437 data: 2.9546 max mem: 3951 +train: [4] [ 20/400] eta: 0:03:06 lr: 0.000243 loss: 1.5505 (1.5520) grad: 0.0411 (0.0419) time: 0.3529 data: 0.0046 max mem: 3951 +train: [4] [ 40/400] eta: 0:02:27 lr: 0.000246 loss: 1.5486 (1.5482) grad: 0.0406 (0.0411) time: 0.3228 data: 0.0036 max mem: 3951 +train: [4] [ 60/400] eta: 0:02:13 lr: 0.000249 loss: 1.5487 (1.5500) grad: 0.0413 (0.0414) time: 0.3555 data: 0.0044 max mem: 3951 +train: [4] [ 80/400] eta: 0:02:01 lr: 0.000252 loss: 1.5387 (1.5457) grad: 0.0416 (0.0413) time: 0.3458 data: 0.0039 max mem: 3951 +train: [4] [100/400] eta: 0:01:52 lr: 0.000255 loss: 1.5330 (1.5430) grad: 0.0406 (0.0414) time: 0.3462 data: 0.0041 max mem: 3951 +train: [4] [120/400] eta: 0:01:41 lr: 0.000258 loss: 1.5127 (1.5387) grad: 0.0406 (0.0412) time: 0.3151 data: 0.0040 max mem: 3951 +train: [4] [140/400] eta: 0:01:33 lr: 0.000261 loss: 1.5117 (1.5352) grad: 0.0411 (0.0412) time: 0.3226 data: 0.0041 max mem: 3951 +train: [4] [160/400] eta: 0:01:25 lr: 0.000264 loss: 1.4997 (1.5305) grad: 0.0399 (0.0410) time: 0.3511 data: 0.0038 max mem: 3951 +train: [4] [180/400] eta: 0:01:17 lr: 0.000267 loss: 1.4767 (1.5252) grad: 0.0396 (0.0411) time: 0.3291 data: 0.0038 max mem: 3951 +train: [4] [200/400] eta: 0:01:10 lr: 0.000270 loss: 1.4569 (1.5178) grad: 0.0407 (0.0411) time: 0.3283 data: 0.0042 max mem: 3951 +train: [4] [220/400] eta: 0:01:03 lr: 0.000273 loss: 1.4563 (1.5127) grad: 0.0404 (0.0410) time: 0.3358 data: 0.0042 max mem: 3951 +train: [4] [240/400] eta: 0:00:55 lr: 0.000276 loss: 1.4517 (1.5085) grad: 0.0397 (0.0409) time: 0.3475 data: 0.0042 max mem: 3951 +train: [4] [260/400] eta: 0:00:48 lr: 0.000279 loss: 1.4517 (1.5042) grad: 0.0394 (0.0408) time: 0.3505 data: 0.0042 max mem: 3951 +train: [4] [280/400] eta: 0:00:41 lr: 0.000282 loss: 1.4494 (1.4991) grad: 0.0393 (0.0407) time: 0.3352 data: 0.0043 max mem: 3951 +train: [4] [300/400] eta: 0:00:35 lr: 0.000285 loss: 1.4505 (1.4961) grad: 0.0385 (0.0406) time: 0.4882 data: 0.1785 max mem: 3951 +train: [4] [320/400] eta: 0:00:28 lr: 0.000288 loss: 1.4432 (1.4911) grad: 0.0400 (0.0406) time: 0.3268 data: 0.0041 max mem: 3951 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 1.4050 (1.4863) grad: 0.0403 (0.0405) time: 0.3289 data: 0.0036 max mem: 3951 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 1.4079 (1.4826) grad: 0.0384 (0.0405) time: 0.3316 data: 0.0034 max mem: 3951 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.4034 (1.4785) grad: 0.0396 (0.0404) time: 0.3295 data: 0.0039 max mem: 3951 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 1.3911 (1.4743) grad: 0.0401 (0.0405) time: 0.3403 data: 0.0041 max mem: 3951 +train: [4] Total time: 0:02:20 (0.3520 s / it) +train: [4] Summary: lr: 0.000300 loss: 1.3911 (1.4743) grad: 0.0401 (0.0405) +eval (validation): [4] [ 0/63] eta: 0:03:07 time: 2.9693 data: 2.7295 max mem: 3951 +eval (validation): [4] [20/63] eta: 0:00:19 time: 0.3290 data: 0.0046 max mem: 3951 +eval (validation): [4] [40/63] eta: 0:00:08 time: 0.3232 data: 0.0032 max mem: 3951 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3018 data: 0.0035 max mem: 3951 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.2990 data: 0.0035 max mem: 3951 +eval (validation): [4] Total time: 0:00:22 (0.3645 s / it) +cv: [4] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.112 acc: 0.975 f1: 0.971 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:20:43 lr: nan time: 3.1093 data: 2.8827 max mem: 3951 +train: [5] [ 20/400] eta: 0:03:03 lr: 0.000300 loss: 1.3895 (1.3846) grad: 0.0391 (0.0394) time: 0.3517 data: 0.0067 max mem: 3951 +train: [5] [ 40/400] eta: 0:02:27 lr: 0.000300 loss: 1.4019 (1.3941) grad: 0.0390 (0.0389) time: 0.3339 data: 0.0032 max mem: 3951 +train: [5] [ 60/400] eta: 0:02:11 lr: 0.000300 loss: 1.3934 (1.3943) grad: 0.0372 (0.0383) time: 0.3396 data: 0.0039 max mem: 3951 +train: [5] [ 80/400] eta: 0:02:00 lr: 0.000300 loss: 1.3921 (1.3948) grad: 0.0376 (0.0387) time: 0.3443 data: 0.0041 max mem: 3951 +train: [5] [100/400] eta: 0:01:54 lr: 0.000300 loss: 1.3689 (1.3839) grad: 0.0377 (0.0385) time: 0.3992 data: 0.0044 max mem: 3951 +train: [5] [120/400] eta: 0:01:46 lr: 0.000300 loss: 1.3477 (1.3816) grad: 0.0374 (0.0385) time: 0.3685 data: 0.0043 max mem: 3951 +train: [5] [140/400] eta: 0:01:36 lr: 0.000300 loss: 1.3465 (1.3746) grad: 0.0390 (0.0386) time: 0.3307 data: 0.0039 max mem: 3951 +train: [5] [160/400] eta: 0:01:28 lr: 0.000299 loss: 1.3367 (1.3720) grad: 0.0392 (0.0387) time: 0.3581 data: 0.0040 max mem: 3951 +train: [5] [180/400] eta: 0:01:21 lr: 0.000299 loss: 1.3475 (1.3681) grad: 0.0392 (0.0388) time: 0.3567 data: 0.0041 max mem: 3951 +train: [5] [200/400] eta: 0:01:13 lr: 0.000299 loss: 1.3229 (1.3631) grad: 0.0394 (0.0389) time: 0.3355 data: 0.0040 max mem: 3951 +train: [5] [220/400] eta: 0:01:05 lr: 0.000299 loss: 1.3235 (1.3600) grad: 0.0382 (0.0388) time: 0.3552 data: 0.0041 max mem: 3951 +train: [5] [240/400] eta: 0:00:58 lr: 0.000299 loss: 1.3285 (1.3581) grad: 0.0369 (0.0387) time: 0.3434 data: 0.0042 max mem: 3951 +train: [5] [260/400] eta: 0:00:50 lr: 0.000299 loss: 1.3170 (1.3545) grad: 0.0372 (0.0387) time: 0.3310 data: 0.0042 max mem: 3951 +train: [5] [280/400] eta: 0:00:43 lr: 0.000298 loss: 1.3118 (1.3531) grad: 0.0371 (0.0385) time: 0.3598 data: 0.0042 max mem: 3951 +train: [5] [300/400] eta: 0:00:36 lr: 0.000298 loss: 1.3034 (1.3492) grad: 0.0366 (0.0384) time: 0.4996 data: 0.1903 max mem: 3951 +train: [5] [320/400] eta: 0:00:29 lr: 0.000298 loss: 1.2801 (1.3455) grad: 0.0356 (0.0383) time: 0.3533 data: 0.0040 max mem: 3951 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 1.2811 (1.3422) grad: 0.0370 (0.0383) time: 0.3366 data: 0.0035 max mem: 3951 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 1.2826 (1.3386) grad: 0.0373 (0.0382) time: 0.3340 data: 0.0041 max mem: 3951 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.2826 (1.3358) grad: 0.0370 (0.0382) time: 0.3306 data: 0.0037 max mem: 3951 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 1.2794 (1.3330) grad: 0.0375 (0.0382) time: 0.3280 data: 0.0037 max mem: 3951 +train: [5] Total time: 0:02:24 (0.3620 s / it) +train: [5] Summary: lr: 0.000297 loss: 1.2794 (1.3330) grad: 0.0375 (0.0382) +eval (validation): [5] [ 0/63] eta: 0:03:06 time: 2.9655 data: 2.7260 max mem: 3951 +eval (validation): [5] [20/63] eta: 0:00:19 time: 0.3275 data: 0.0029 max mem: 3951 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3317 data: 0.0035 max mem: 3951 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3337 data: 0.0033 max mem: 3951 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3287 data: 0.0036 max mem: 3951 +eval (validation): [5] Total time: 0:00:23 (0.3770 s / it) +cv: [5] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.114 acc: 0.977 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:21:12 lr: nan time: 3.1819 data: 2.9644 max mem: 3951 +train: [6] [ 20/400] eta: 0:03:01 lr: 0.000296 loss: 1.2666 (1.2688) grad: 0.0371 (0.0376) time: 0.3422 data: 0.0166 max mem: 3951 +train: [6] [ 40/400] eta: 0:02:24 lr: 0.000296 loss: 1.2626 (1.2663) grad: 0.0380 (0.0382) time: 0.3220 data: 0.0028 max mem: 3951 +train: [6] [ 60/400] eta: 0:02:08 lr: 0.000296 loss: 1.2496 (1.2587) grad: 0.0372 (0.0379) time: 0.3330 data: 0.0039 max mem: 3951 +train: [6] [ 80/400] eta: 0:01:58 lr: 0.000295 loss: 1.2565 (1.2616) grad: 0.0355 (0.0370) time: 0.3473 data: 0.0032 max mem: 3951 +train: [6] [100/400] eta: 0:01:49 lr: 0.000295 loss: 1.2565 (1.2594) grad: 0.0355 (0.0370) time: 0.3353 data: 0.0038 max mem: 3951 +train: [6] [120/400] eta: 0:01:39 lr: 0.000295 loss: 1.2497 (1.2577) grad: 0.0371 (0.0371) time: 0.3213 data: 0.0037 max mem: 3951 +train: [6] [140/400] eta: 0:01:30 lr: 0.000294 loss: 1.2493 (1.2596) grad: 0.0377 (0.0371) time: 0.3048 data: 0.0035 max mem: 3951 +train: [6] [160/400] eta: 0:01:23 lr: 0.000294 loss: 1.2666 (1.2592) grad: 0.0365 (0.0370) time: 0.3503 data: 0.0043 max mem: 3951 +train: [6] [180/400] eta: 0:01:16 lr: 0.000293 loss: 1.2400 (1.2561) grad: 0.0356 (0.0369) time: 0.3329 data: 0.0041 max mem: 3951 +train: [6] [200/400] eta: 0:01:09 lr: 0.000293 loss: 1.2325 (1.2534) grad: 0.0355 (0.0368) time: 0.3283 data: 0.0039 max mem: 3951 +train: [6] [220/400] eta: 0:01:02 lr: 0.000292 loss: 1.2242 (1.2504) grad: 0.0357 (0.0367) time: 0.3460 data: 0.0041 max mem: 3951 +train: [6] [240/400] eta: 0:00:55 lr: 0.000292 loss: 1.2242 (1.2493) grad: 0.0361 (0.0368) time: 0.3254 data: 0.0041 max mem: 3951 +train: [6] [260/400] eta: 0:00:47 lr: 0.000291 loss: 1.2166 (1.2447) grad: 0.0368 (0.0368) time: 0.3230 data: 0.0038 max mem: 3951 +train: [6] [280/400] eta: 0:00:41 lr: 0.000291 loss: 1.2063 (1.2447) grad: 0.0346 (0.0366) time: 0.3357 data: 0.0044 max mem: 3951 +train: [6] [300/400] eta: 0:00:35 lr: 0.000290 loss: 1.2217 (1.2424) grad: 0.0347 (0.0366) time: 0.4924 data: 0.1781 max mem: 3951 +train: [6] [320/400] eta: 0:00:28 lr: 0.000290 loss: 1.2015 (1.2395) grad: 0.0356 (0.0365) time: 0.3635 data: 0.0035 max mem: 3951 +train: [6] [340/400] eta: 0:00:21 lr: 0.000289 loss: 1.1928 (1.2372) grad: 0.0349 (0.0364) time: 0.3546 data: 0.0040 max mem: 3951 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 1.1913 (1.2338) grad: 0.0352 (0.0364) time: 0.3189 data: 0.0043 max mem: 3951 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 1.1819 (1.2319) grad: 0.0351 (0.0364) time: 0.3500 data: 0.0043 max mem: 3951 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 1.1857 (1.2294) grad: 0.0349 (0.0363) time: 0.3488 data: 0.0044 max mem: 3951 +train: [6] Total time: 0:02:20 (0.3514 s / it) +train: [6] Summary: lr: 0.000287 loss: 1.1857 (1.2294) grad: 0.0349 (0.0363) +eval (validation): [6] [ 0/63] eta: 0:03:19 time: 3.1590 data: 2.9502 max mem: 3951 +eval (validation): [6] [20/63] eta: 0:00:20 time: 0.3345 data: 0.0039 max mem: 3951 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3672 data: 0.0036 max mem: 3951 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3058 data: 0.0034 max mem: 3951 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3066 data: 0.0032 max mem: 3951 +eval (validation): [6] Total time: 0:00:24 (0.3843 s / it) +cv: [6] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.107 acc: 0.977 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:21:40 lr: nan time: 3.2508 data: 2.9736 max mem: 3951 +train: [7] [ 20/400] eta: 0:03:01 lr: 0.000286 loss: 1.2022 (1.2016) grad: 0.0336 (0.0353) time: 0.3387 data: 0.0036 max mem: 3951 +train: [7] [ 40/400] eta: 0:02:25 lr: 0.000286 loss: 1.2022 (1.1934) grad: 0.0350 (0.0355) time: 0.3289 data: 0.0037 max mem: 3951 +train: [7] [ 60/400] eta: 0:02:07 lr: 0.000285 loss: 1.1598 (1.1777) grad: 0.0360 (0.0360) time: 0.3180 data: 0.0036 max mem: 3951 +train: [7] [ 80/400] eta: 0:01:58 lr: 0.000284 loss: 1.1660 (1.1807) grad: 0.0347 (0.0355) time: 0.3515 data: 0.0042 max mem: 3951 +train: [7] [100/400] eta: 0:01:48 lr: 0.000284 loss: 1.1718 (1.1778) grad: 0.0346 (0.0356) time: 0.3337 data: 0.0040 max mem: 3951 +train: [7] [120/400] eta: 0:01:39 lr: 0.000283 loss: 1.1490 (1.1750) grad: 0.0347 (0.0354) time: 0.3270 data: 0.0041 max mem: 3951 +train: [7] [140/400] eta: 0:01:31 lr: 0.000282 loss: 1.1428 (1.1704) grad: 0.0352 (0.0357) time: 0.3103 data: 0.0038 max mem: 3951 +train: [7] [160/400] eta: 0:01:24 lr: 0.000282 loss: 1.1492 (1.1694) grad: 0.0355 (0.0356) time: 0.3796 data: 0.0047 max mem: 3951 +train: [7] [180/400] eta: 0:01:17 lr: 0.000281 loss: 1.1526 (1.1666) grad: 0.0345 (0.0356) time: 0.3375 data: 0.0040 max mem: 3951 +train: [7] [200/400] eta: 0:01:09 lr: 0.000280 loss: 1.1496 (1.1651) grad: 0.0345 (0.0355) time: 0.3255 data: 0.0043 max mem: 3951 +train: [7] [220/400] eta: 0:01:02 lr: 0.000279 loss: 1.1432 (1.1625) grad: 0.0332 (0.0353) time: 0.3270 data: 0.0041 max mem: 3951 +train: [7] [240/400] eta: 0:00:55 lr: 0.000278 loss: 1.1366 (1.1603) grad: 0.0338 (0.0353) time: 0.3365 data: 0.0041 max mem: 3951 +train: [7] [260/400] eta: 0:00:48 lr: 0.000278 loss: 1.1367 (1.1591) grad: 0.0350 (0.0353) time: 0.3540 data: 0.0042 max mem: 3951 +train: [7] [280/400] eta: 0:00:41 lr: 0.000277 loss: 1.1203 (1.1553) grad: 0.0348 (0.0352) time: 0.3337 data: 0.0045 max mem: 3951 +train: [7] [300/400] eta: 0:00:35 lr: 0.000276 loss: 1.1220 (1.1539) grad: 0.0338 (0.0351) time: 0.4942 data: 0.1785 max mem: 3951 +train: [7] [320/400] eta: 0:00:28 lr: 0.000275 loss: 1.1292 (1.1512) grad: 0.0342 (0.0351) time: 0.3820 data: 0.0038 max mem: 3951 +train: [7] [340/400] eta: 0:00:21 lr: 0.000274 loss: 1.1046 (1.1502) grad: 0.0340 (0.0350) time: 0.3411 data: 0.0040 max mem: 3951 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 1.1154 (1.1479) grad: 0.0336 (0.0350) time: 0.3372 data: 0.0040 max mem: 3951 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 1.1013 (1.1460) grad: 0.0345 (0.0350) time: 0.3496 data: 0.0043 max mem: 3951 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 1.1013 (1.1449) grad: 0.0348 (0.0350) time: 0.3313 data: 0.0041 max mem: 3951 +train: [7] Total time: 0:02:21 (0.3547 s / it) +train: [7] Summary: lr: 0.000271 loss: 1.1013 (1.1449) grad: 0.0348 (0.0350) +eval (validation): [7] [ 0/63] eta: 0:02:56 time: 2.8039 data: 2.6102 max mem: 3951 +eval (validation): [7] [20/63] eta: 0:00:20 time: 0.3532 data: 0.0043 max mem: 3951 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3322 data: 0.0035 max mem: 3951 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3001 data: 0.0031 max mem: 3951 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.2962 data: 0.0030 max mem: 3951 +eval (validation): [7] Total time: 0:00:23 (0.3712 s / it) +cv: [7] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.104 acc: 0.976 f1: 0.972 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:23:12 lr: nan time: 3.4803 data: 3.2357 max mem: 3951 +train: [8] [ 20/400] eta: 0:03:18 lr: 0.000270 loss: 1.1039 (1.1187) grad: 0.0330 (0.0334) time: 0.3742 data: 0.0037 max mem: 3951 +train: [8] [ 40/400] eta: 0:02:32 lr: 0.000270 loss: 1.1006 (1.1023) grad: 0.0338 (0.0346) time: 0.3216 data: 0.0033 max mem: 3951 +train: [8] [ 60/400] eta: 0:02:13 lr: 0.000269 loss: 1.1043 (1.1029) grad: 0.0350 (0.0347) time: 0.3249 data: 0.0038 max mem: 3951 +train: [8] [ 80/400] eta: 0:02:04 lr: 0.000268 loss: 1.1045 (1.1005) grad: 0.0346 (0.0346) time: 0.3816 data: 0.0042 max mem: 3951 +train: [8] [100/400] eta: 0:01:52 lr: 0.000267 loss: 1.0855 (1.0976) grad: 0.0344 (0.0347) time: 0.3244 data: 0.0038 max mem: 3951 +train: [8] [120/400] eta: 0:01:42 lr: 0.000266 loss: 1.0759 (1.0962) grad: 0.0344 (0.0347) time: 0.3133 data: 0.0031 max mem: 3951 +train: [8] [140/400] eta: 0:01:33 lr: 0.000265 loss: 1.0939 (1.0976) grad: 0.0344 (0.0345) time: 0.3226 data: 0.0038 max mem: 3951 +train: [8] [160/400] eta: 0:01:25 lr: 0.000264 loss: 1.1062 (1.0982) grad: 0.0345 (0.0346) time: 0.3478 data: 0.0041 max mem: 3951 +train: [8] [180/400] eta: 0:01:17 lr: 0.000263 loss: 1.0938 (1.0975) grad: 0.0344 (0.0345) time: 0.3224 data: 0.0039 max mem: 3951 +train: [8] [200/400] eta: 0:01:10 lr: 0.000262 loss: 1.0852 (1.0964) grad: 0.0334 (0.0344) time: 0.3301 data: 0.0040 max mem: 3951 +train: [8] [220/400] eta: 0:01:02 lr: 0.000260 loss: 1.0757 (1.0946) grad: 0.0334 (0.0343) time: 0.3283 data: 0.0040 max mem: 3951 +train: [8] [240/400] eta: 0:00:55 lr: 0.000259 loss: 1.0787 (1.0929) grad: 0.0334 (0.0343) time: 0.3236 data: 0.0038 max mem: 3951 +train: [8] [260/400] eta: 0:00:48 lr: 0.000258 loss: 1.0848 (1.0921) grad: 0.0334 (0.0343) time: 0.3512 data: 0.0041 max mem: 3951 +train: [8] [280/400] eta: 0:00:41 lr: 0.000257 loss: 1.0714 (1.0903) grad: 0.0338 (0.0343) time: 0.3348 data: 0.0040 max mem: 3951 +train: [8] [300/400] eta: 0:00:35 lr: 0.000256 loss: 1.0662 (1.0897) grad: 0.0333 (0.0342) time: 0.5085 data: 0.1734 max mem: 3951 +train: [8] [320/400] eta: 0:00:28 lr: 0.000255 loss: 1.0744 (1.0888) grad: 0.0333 (0.0342) time: 0.3622 data: 0.0041 max mem: 3951 +train: [8] [340/400] eta: 0:00:21 lr: 0.000254 loss: 1.0680 (1.0878) grad: 0.0335 (0.0342) time: 0.3698 data: 0.0039 max mem: 3951 +train: [8] [360/400] eta: 0:00:14 lr: 0.000253 loss: 1.0598 (1.0864) grad: 0.0334 (0.0342) time: 0.3370 data: 0.0042 max mem: 3951 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 1.0614 (1.0857) grad: 0.0337 (0.0341) time: 0.3327 data: 0.0042 max mem: 3951 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 1.0679 (1.0848) grad: 0.0326 (0.0340) time: 0.3345 data: 0.0040 max mem: 3951 +train: [8] Total time: 0:02:22 (0.3556 s / it) +train: [8] Summary: lr: 0.000250 loss: 1.0679 (1.0848) grad: 0.0326 (0.0340) +eval (validation): [8] [ 0/63] eta: 0:03:16 time: 3.1136 data: 2.8516 max mem: 3951 +eval (validation): [8] [20/63] eta: 0:00:19 time: 0.3140 data: 0.0243 max mem: 3951 +eval (validation): [8] [40/63] eta: 0:00:08 time: 0.3173 data: 0.0080 max mem: 3951 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3023 data: 0.0027 max mem: 3951 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3004 data: 0.0029 max mem: 3951 +eval (validation): [8] Total time: 0:00:22 (0.3591 s / it) +cv: [8] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.100 acc: 0.976 f1: 0.972 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:21:26 lr: nan time: 3.2169 data: 2.9936 max mem: 3951 +train: [9] [ 20/400] eta: 0:03:03 lr: 0.000249 loss: 1.0412 (1.0534) grad: 0.0330 (0.0329) time: 0.3473 data: 0.0032 max mem: 3951 +train: [9] [ 40/400] eta: 0:02:27 lr: 0.000248 loss: 1.0501 (1.0558) grad: 0.0331 (0.0330) time: 0.3323 data: 0.0037 max mem: 3951 +train: [9] [ 60/400] eta: 0:02:13 lr: 0.000247 loss: 1.0501 (1.0505) grad: 0.0332 (0.0332) time: 0.3572 data: 0.0041 max mem: 3951 +train: [9] [ 80/400] eta: 0:02:01 lr: 0.000246 loss: 1.0616 (1.0580) grad: 0.0331 (0.0332) time: 0.3444 data: 0.0043 max mem: 3951 +train: [9] [100/400] eta: 0:01:51 lr: 0.000244 loss: 1.0563 (1.0527) grad: 0.0328 (0.0330) time: 0.3364 data: 0.0042 max mem: 3951 +train: [9] [120/400] eta: 0:01:41 lr: 0.000243 loss: 1.0381 (1.0517) grad: 0.0328 (0.0331) time: 0.3197 data: 0.0037 max mem: 3951 +train: [9] [140/400] eta: 0:01:33 lr: 0.000242 loss: 1.0503 (1.0514) grad: 0.0331 (0.0331) time: 0.3497 data: 0.0045 max mem: 3951 +train: [9] [160/400] eta: 0:01:25 lr: 0.000241 loss: 1.0346 (1.0492) grad: 0.0331 (0.0331) time: 0.3262 data: 0.0038 max mem: 3951 +train: [9] [180/400] eta: 0:01:18 lr: 0.000240 loss: 1.0346 (1.0489) grad: 0.0331 (0.0331) time: 0.3379 data: 0.0035 max mem: 3951 +train: [9] [200/400] eta: 0:01:10 lr: 0.000238 loss: 1.0455 (1.0479) grad: 0.0330 (0.0330) time: 0.3334 data: 0.0035 max mem: 3951 +train: [9] [220/400] eta: 0:01:03 lr: 0.000237 loss: 1.0294 (1.0462) grad: 0.0330 (0.0330) time: 0.3366 data: 0.0035 max mem: 3951 +train: [9] [240/400] eta: 0:00:56 lr: 0.000236 loss: 1.0179 (1.0439) grad: 0.0321 (0.0330) time: 0.3421 data: 0.0038 max mem: 3951 +train: [9] [260/400] eta: 0:00:49 lr: 0.000234 loss: 1.0078 (1.0419) grad: 0.0322 (0.0330) time: 0.3442 data: 0.0041 max mem: 3951 +train: [9] [280/400] eta: 0:00:41 lr: 0.000233 loss: 1.0205 (1.0406) grad: 0.0336 (0.0331) time: 0.3328 data: 0.0041 max mem: 3951 +train: [9] [300/400] eta: 0:00:35 lr: 0.000232 loss: 1.0261 (1.0404) grad: 0.0324 (0.0330) time: 0.4886 data: 0.1777 max mem: 3951 +train: [9] [320/400] eta: 0:00:28 lr: 0.000230 loss: 1.0208 (1.0385) grad: 0.0322 (0.0330) time: 0.3391 data: 0.0042 max mem: 3951 +train: [9] [340/400] eta: 0:00:21 lr: 0.000229 loss: 1.0119 (1.0373) grad: 0.0322 (0.0330) time: 0.3426 data: 0.0055 max mem: 3951 +train: [9] [360/400] eta: 0:00:14 lr: 0.000228 loss: 1.0089 (1.0361) grad: 0.0317 (0.0330) time: 0.3319 data: 0.0037 max mem: 3951 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 0.9954 (1.0343) grad: 0.0327 (0.0330) time: 0.4020 data: 0.0042 max mem: 3951 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 1.0073 (1.0341) grad: 0.0327 (0.0330) time: 0.3413 data: 0.0041 max mem: 3951 +train: [9] Total time: 0:02:22 (0.3571 s / it) +train: [9] Summary: lr: 0.000225 loss: 1.0073 (1.0341) grad: 0.0327 (0.0330) +eval (validation): [9] [ 0/63] eta: 0:03:13 time: 3.0687 data: 2.7965 max mem: 3951 +eval (validation): [9] [20/63] eta: 0:00:21 time: 0.3731 data: 0.0051 max mem: 3951 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3214 data: 0.0031 max mem: 3951 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3060 data: 0.0033 max mem: 3951 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3057 data: 0.0033 max mem: 3951 +eval (validation): [9] Total time: 0:00:23 (0.3807 s / it) +cv: [9] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.096 acc: 0.978 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:22:10 lr: nan time: 3.3252 data: 3.0285 max mem: 3951 +train: [10] [ 20/400] eta: 0:03:08 lr: 0.000224 loss: 0.9937 (1.0098) grad: 0.0333 (0.0335) time: 0.3543 data: 0.0125 max mem: 3951 +train: [10] [ 40/400] eta: 0:02:35 lr: 0.000222 loss: 1.0020 (1.0193) grad: 0.0324 (0.0325) time: 0.3628 data: 0.0023 max mem: 3951 +train: [10] [ 60/400] eta: 0:02:16 lr: 0.000221 loss: 1.0150 (1.0163) grad: 0.0324 (0.0328) time: 0.3422 data: 0.0037 max mem: 3951 +train: [10] [ 80/400] eta: 0:02:04 lr: 0.000220 loss: 1.0047 (1.0104) grad: 0.0331 (0.0329) time: 0.3510 data: 0.0035 max mem: 3951 +train: [10] [100/400] eta: 0:01:52 lr: 0.000218 loss: 0.9876 (1.0072) grad: 0.0327 (0.0327) time: 0.3187 data: 0.0035 max mem: 3951 +train: [10] [120/400] eta: 0:01:42 lr: 0.000217 loss: 0.9855 (1.0032) grad: 0.0328 (0.0327) time: 0.3121 data: 0.0036 max mem: 3951 +train: [10] [140/400] eta: 0:01:34 lr: 0.000215 loss: 0.9933 (1.0048) grad: 0.0328 (0.0328) time: 0.3619 data: 0.0042 max mem: 3951 +train: [10] [160/400] eta: 0:01:26 lr: 0.000214 loss: 1.0111 (1.0066) grad: 0.0324 (0.0327) time: 0.3344 data: 0.0040 max mem: 3951 +train: [10] [180/400] eta: 0:01:18 lr: 0.000213 loss: 1.0134 (1.0061) grad: 0.0319 (0.0326) time: 0.3383 data: 0.0040 max mem: 3951 +train: [10] [200/400] eta: 0:01:11 lr: 0.000211 loss: 0.9770 (1.0030) grad: 0.0324 (0.0326) time: 0.3430 data: 0.0043 max mem: 3951 +train: [10] [220/400] eta: 0:01:03 lr: 0.000210 loss: 0.9706 (1.0024) grad: 0.0328 (0.0326) time: 0.3362 data: 0.0044 max mem: 3951 +train: [10] [240/400] eta: 0:00:56 lr: 0.000208 loss: 0.9882 (1.0025) grad: 0.0319 (0.0325) time: 0.3318 data: 0.0041 max mem: 3951 +train: [10] [260/400] eta: 0:00:49 lr: 0.000207 loss: 0.9967 (1.0022) grad: 0.0310 (0.0324) time: 0.3488 data: 0.0041 max mem: 3951 +train: [10] [280/400] eta: 0:00:42 lr: 0.000205 loss: 0.9947 (1.0022) grad: 0.0311 (0.0324) time: 0.3247 data: 0.0041 max mem: 3951 +train: [10] [300/400] eta: 0:00:35 lr: 0.000204 loss: 0.9911 (1.0012) grad: 0.0311 (0.0323) time: 0.4854 data: 0.1755 max mem: 3951 +train: [10] [320/400] eta: 0:00:28 lr: 0.000202 loss: 0.9913 (1.0003) grad: 0.0315 (0.0324) time: 0.3692 data: 0.0067 max mem: 3951 +train: [10] [340/400] eta: 0:00:21 lr: 0.000201 loss: 0.9861 (0.9986) grad: 0.0321 (0.0323) time: 0.3480 data: 0.0055 max mem: 3951 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 0.9812 (0.9981) grad: 0.0324 (0.0323) time: 0.3398 data: 0.0040 max mem: 3951 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 0.9816 (0.9978) grad: 0.0311 (0.0322) time: 0.3198 data: 0.0037 max mem: 3951 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.9694 (0.9964) grad: 0.0310 (0.0322) time: 0.3463 data: 0.0041 max mem: 3951 +train: [10] Total time: 0:02:22 (0.3564 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.9694 (0.9964) grad: 0.0310 (0.0322) +eval (validation): [10] [ 0/63] eta: 0:03:17 time: 3.1313 data: 2.8969 max mem: 3951 +eval (validation): [10] [20/63] eta: 0:00:20 time: 0.3452 data: 0.0116 max mem: 3951 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3231 data: 0.0035 max mem: 3951 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3036 data: 0.0034 max mem: 3951 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3028 data: 0.0036 max mem: 3951 +eval (validation): [10] Total time: 0:00:23 (0.3724 s / it) +cv: [10] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.103 acc: 0.976 f1: 0.973 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:32 lr: nan time: 3.3823 data: 3.0939 max mem: 3951 +train: [11] [ 20/400] eta: 0:03:04 lr: 0.000195 loss: 0.9611 (0.9734) grad: 0.0309 (0.0315) time: 0.3403 data: 0.0032 max mem: 3951 +train: [11] [ 40/400] eta: 0:02:36 lr: 0.000193 loss: 0.9815 (0.9795) grad: 0.0318 (0.0320) time: 0.3817 data: 0.0034 max mem: 3951 +train: [11] [ 60/400] eta: 0:02:17 lr: 0.000192 loss: 0.9891 (0.9812) grad: 0.0315 (0.0318) time: 0.3382 data: 0.0039 max mem: 3951 +train: [11] [ 80/400] eta: 0:02:03 lr: 0.000190 loss: 0.9880 (0.9827) grad: 0.0311 (0.0317) time: 0.3354 data: 0.0040 max mem: 3951 +train: [11] [100/400] eta: 0:01:54 lr: 0.000189 loss: 0.9763 (0.9773) grad: 0.0314 (0.0319) time: 0.3550 data: 0.0038 max mem: 3951 +train: [11] [120/400] eta: 0:01:44 lr: 0.000187 loss: 0.9566 (0.9738) grad: 0.0317 (0.0319) time: 0.3411 data: 0.0040 max mem: 3951 +train: [11] [140/400] eta: 0:01:35 lr: 0.000186 loss: 0.9769 (0.9756) grad: 0.0318 (0.0320) time: 0.3385 data: 0.0034 max mem: 3951 +train: [11] [160/400] eta: 0:01:27 lr: 0.000184 loss: 0.9631 (0.9717) grad: 0.0317 (0.0319) time: 0.3274 data: 0.0037 max mem: 3951 +train: [11] [180/400] eta: 0:01:19 lr: 0.000183 loss: 0.9631 (0.9719) grad: 0.0313 (0.0318) time: 0.3500 data: 0.0041 max mem: 3951 +train: [11] [200/400] eta: 0:01:12 lr: 0.000181 loss: 0.9716 (0.9716) grad: 0.0314 (0.0317) time: 0.3538 data: 0.0040 max mem: 3951 +train: [11] [220/400] eta: 0:01:05 lr: 0.000180 loss: 0.9764 (0.9727) grad: 0.0312 (0.0317) time: 0.3651 data: 0.0039 max mem: 3951 +train: [11] [240/400] eta: 0:00:57 lr: 0.000178 loss: 0.9732 (0.9717) grad: 0.0320 (0.0318) time: 0.3506 data: 0.0044 max mem: 3951 +train: [11] [260/400] eta: 0:00:50 lr: 0.000177 loss: 0.9659 (0.9715) grad: 0.0320 (0.0317) time: 0.3387 data: 0.0037 max mem: 3951 +train: [11] [280/400] eta: 0:00:42 lr: 0.000175 loss: 0.9548 (0.9701) grad: 0.0314 (0.0318) time: 0.3423 data: 0.0038 max mem: 3951 +train: [11] [300/400] eta: 0:00:36 lr: 0.000174 loss: 0.9325 (0.9674) grad: 0.0319 (0.0318) time: 0.4939 data: 0.1802 max mem: 3951 +train: [11] [320/400] eta: 0:00:29 lr: 0.000172 loss: 0.9410 (0.9671) grad: 0.0315 (0.0317) time: 0.3478 data: 0.0040 max mem: 3951 +train: [11] [340/400] eta: 0:00:21 lr: 0.000170 loss: 0.9429 (0.9656) grad: 0.0306 (0.0317) time: 0.3540 data: 0.0031 max mem: 3951 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 0.9429 (0.9655) grad: 0.0308 (0.0317) time: 0.3593 data: 0.0043 max mem: 3951 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 0.9488 (0.9647) grad: 0.0314 (0.0317) time: 0.3357 data: 0.0036 max mem: 3951 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.9444 (0.9640) grad: 0.0313 (0.0317) time: 0.3443 data: 0.0038 max mem: 3951 +train: [11] Total time: 0:02:25 (0.3627 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.9444 (0.9640) grad: 0.0313 (0.0317) +eval (validation): [11] [ 0/63] eta: 0:03:15 time: 3.1020 data: 2.8435 max mem: 3951 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3747 data: 0.0049 max mem: 3951 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3210 data: 0.0034 max mem: 3951 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3130 data: 0.0035 max mem: 3951 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3145 data: 0.0033 max mem: 3951 +eval (validation): [11] Total time: 0:00:24 (0.3850 s / it) +cv: [11] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.101 acc: 0.977 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:17 lr: nan time: 3.3425 data: 3.0580 max mem: 3951 +train: [12] [ 20/400] eta: 0:03:09 lr: 0.000164 loss: 0.9428 (0.9573) grad: 0.0311 (0.0313) time: 0.3579 data: 0.0044 max mem: 3951 +train: [12] [ 40/400] eta: 0:02:34 lr: 0.000163 loss: 0.9356 (0.9483) grad: 0.0311 (0.0312) time: 0.3529 data: 0.0036 max mem: 3951 +train: [12] [ 60/400] eta: 0:02:16 lr: 0.000161 loss: 0.9405 (0.9497) grad: 0.0306 (0.0312) time: 0.3481 data: 0.0044 max mem: 3951 +train: [12] [ 80/400] eta: 0:02:03 lr: 0.000160 loss: 0.9544 (0.9490) grad: 0.0309 (0.0311) time: 0.3378 data: 0.0041 max mem: 3951 +train: [12] [100/400] eta: 0:01:54 lr: 0.000158 loss: 0.9453 (0.9476) grad: 0.0314 (0.0314) time: 0.3684 data: 0.0043 max mem: 3951 +train: [12] [120/400] eta: 0:01:45 lr: 0.000156 loss: 0.9362 (0.9473) grad: 0.0318 (0.0314) time: 0.3446 data: 0.0039 max mem: 3951 +train: [12] [140/400] eta: 0:01:36 lr: 0.000155 loss: 0.9368 (0.9465) grad: 0.0305 (0.0313) time: 0.3480 data: 0.0039 max mem: 3951 +train: [12] [160/400] eta: 0:01:28 lr: 0.000153 loss: 0.9432 (0.9446) grad: 0.0307 (0.0314) time: 0.3332 data: 0.0039 max mem: 3951 +train: [12] [180/400] eta: 0:01:20 lr: 0.000152 loss: 0.9438 (0.9441) grad: 0.0309 (0.0313) time: 0.3342 data: 0.0040 max mem: 3951 +train: [12] [200/400] eta: 0:01:12 lr: 0.000150 loss: 0.9432 (0.9447) grad: 0.0305 (0.0313) time: 0.3478 data: 0.0038 max mem: 3951 +train: [12] [220/400] eta: 0:01:05 lr: 0.000149 loss: 0.9461 (0.9450) grad: 0.0308 (0.0313) time: 0.3530 data: 0.0039 max mem: 3951 +train: [12] [240/400] eta: 0:00:57 lr: 0.000147 loss: 0.9500 (0.9454) grad: 0.0302 (0.0312) time: 0.3358 data: 0.0037 max mem: 3951 +train: [12] [260/400] eta: 0:00:50 lr: 0.000145 loss: 0.9413 (0.9440) grad: 0.0304 (0.0312) time: 0.3486 data: 0.0035 max mem: 3951 +train: [12] [280/400] eta: 0:00:42 lr: 0.000144 loss: 0.9263 (0.9450) grad: 0.0307 (0.0312) time: 0.3219 data: 0.0034 max mem: 3951 +train: [12] [300/400] eta: 0:00:36 lr: 0.000142 loss: 0.9492 (0.9458) grad: 0.0303 (0.0311) time: 0.5097 data: 0.1907 max mem: 3951 +train: [12] [320/400] eta: 0:00:29 lr: 0.000141 loss: 0.9293 (0.9442) grad: 0.0307 (0.0311) time: 0.3938 data: 0.0085 max mem: 3951 +train: [12] [340/400] eta: 0:00:21 lr: 0.000139 loss: 0.9210 (0.9429) grad: 0.0309 (0.0311) time: 0.3348 data: 0.0027 max mem: 3951 +train: [12] [360/400] eta: 0:00:14 lr: 0.000138 loss: 0.9278 (0.9428) grad: 0.0309 (0.0312) time: 0.3408 data: 0.0040 max mem: 3951 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 0.9360 (0.9422) grad: 0.0317 (0.0312) time: 0.3766 data: 0.0041 max mem: 3951 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.9356 (0.9422) grad: 0.0304 (0.0311) time: 0.3489 data: 0.0040 max mem: 3951 +train: [12] Total time: 0:02:25 (0.3647 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.9356 (0.9422) grad: 0.0304 (0.0311) +eval (validation): [12] [ 0/63] eta: 0:03:12 time: 3.0492 data: 2.7956 max mem: 3951 +eval (validation): [12] [20/63] eta: 0:00:20 time: 0.3582 data: 0.0041 max mem: 3951 +eval (validation): [12] [40/63] eta: 0:00:09 time: 0.3337 data: 0.0037 max mem: 3951 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3161 data: 0.0030 max mem: 3951 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3170 data: 0.0031 max mem: 3951 +eval (validation): [12] Total time: 0:00:24 (0.3837 s / it) +cv: [12] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.095 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:30 lr: nan time: 3.3759 data: 3.0908 max mem: 3951 +train: [13] [ 20/400] eta: 0:03:27 lr: 0.000133 loss: 0.9292 (0.9416) grad: 0.0292 (0.0297) time: 0.4036 data: 0.0040 max mem: 3951 +train: [13] [ 40/400] eta: 0:02:41 lr: 0.000131 loss: 0.9292 (0.9332) grad: 0.0295 (0.0302) time: 0.3467 data: 0.0035 max mem: 3951 +train: [13] [ 60/400] eta: 0:02:21 lr: 0.000130 loss: 0.9109 (0.9254) grad: 0.0304 (0.0307) time: 0.3502 data: 0.0040 max mem: 3951 +train: [13] [ 80/400] eta: 0:02:08 lr: 0.000128 loss: 0.8938 (0.9203) grad: 0.0306 (0.0307) time: 0.3532 data: 0.0043 max mem: 3951 +train: [13] [100/400] eta: 0:01:56 lr: 0.000127 loss: 0.9051 (0.9212) grad: 0.0304 (0.0307) time: 0.3326 data: 0.0039 max mem: 3951 +train: [13] [120/400] eta: 0:01:46 lr: 0.000125 loss: 0.9108 (0.9199) grad: 0.0304 (0.0308) time: 0.3441 data: 0.0041 max mem: 3951 +train: [13] [140/400] eta: 0:01:38 lr: 0.000124 loss: 0.9108 (0.9197) grad: 0.0308 (0.0307) time: 0.3642 data: 0.0040 max mem: 3951 +train: [13] [160/400] eta: 0:01:29 lr: 0.000122 loss: 0.9237 (0.9192) grad: 0.0308 (0.0308) time: 0.3366 data: 0.0041 max mem: 3951 +train: [13] [180/400] eta: 0:01:21 lr: 0.000120 loss: 0.9133 (0.9176) grad: 0.0308 (0.0308) time: 0.3525 data: 0.0044 max mem: 3951 +train: [13] [200/400] eta: 0:01:14 lr: 0.000119 loss: 0.9074 (0.9161) grad: 0.0310 (0.0309) time: 0.3676 data: 0.0046 max mem: 3951 +train: [13] [220/400] eta: 0:01:06 lr: 0.000117 loss: 0.9210 (0.9183) grad: 0.0310 (0.0309) time: 0.3512 data: 0.0042 max mem: 3951 +train: [13] [240/400] eta: 0:00:58 lr: 0.000116 loss: 0.9250 (0.9193) grad: 0.0303 (0.0309) time: 0.3456 data: 0.0044 max mem: 3951 +train: [13] [260/400] eta: 0:00:51 lr: 0.000114 loss: 0.9213 (0.9197) grad: 0.0303 (0.0309) time: 0.3433 data: 0.0043 max mem: 3951 +train: [13] [280/400] eta: 0:00:43 lr: 0.000113 loss: 0.9157 (0.9196) grad: 0.0306 (0.0309) time: 0.3488 data: 0.0045 max mem: 3951 +train: [13] [300/400] eta: 0:00:37 lr: 0.000111 loss: 0.9146 (0.9200) grad: 0.0311 (0.0309) time: 0.4896 data: 0.1818 max mem: 3951 +train: [13] [320/400] eta: 0:00:29 lr: 0.000110 loss: 0.9146 (0.9199) grad: 0.0303 (0.0309) time: 0.3410 data: 0.0045 max mem: 3951 +train: [13] [340/400] eta: 0:00:22 lr: 0.000108 loss: 0.9165 (0.9211) grad: 0.0300 (0.0309) time: 0.3357 data: 0.0030 max mem: 3951 +train: [13] [360/400] eta: 0:00:14 lr: 0.000107 loss: 0.9282 (0.9212) grad: 0.0310 (0.0309) time: 0.3540 data: 0.0042 max mem: 3951 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 0.9004 (0.9201) grad: 0.0310 (0.0309) time: 0.3429 data: 0.0038 max mem: 3951 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.9130 (0.9199) grad: 0.0293 (0.0309) time: 0.3452 data: 0.0039 max mem: 3951 +train: [13] Total time: 0:02:26 (0.3656 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.9130 (0.9199) grad: 0.0293 (0.0309) +eval (validation): [13] [ 0/63] eta: 0:03:13 time: 3.0739 data: 2.8620 max mem: 3951 +eval (validation): [13] [20/63] eta: 0:00:19 time: 0.3126 data: 0.0103 max mem: 3951 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3454 data: 0.0030 max mem: 3951 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3291 data: 0.0037 max mem: 3951 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3195 data: 0.0036 max mem: 3951 +eval (validation): [13] Total time: 0:00:23 (0.3769 s / it) +cv: [13] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.102 acc: 0.977 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:21:45 lr: nan time: 3.2634 data: 3.0449 max mem: 3951 +train: [14] [ 20/400] eta: 0:03:11 lr: 0.000102 loss: 0.9230 (0.9343) grad: 0.0301 (0.0304) time: 0.3652 data: 0.0038 max mem: 3951 +train: [14] [ 40/400] eta: 0:02:38 lr: 0.000101 loss: 0.9227 (0.9220) grad: 0.0301 (0.0305) time: 0.3716 data: 0.0035 max mem: 3951 +train: [14] [ 60/400] eta: 0:02:15 lr: 0.000099 loss: 0.8962 (0.9142) grad: 0.0303 (0.0305) time: 0.3176 data: 0.0040 max mem: 3951 +train: [14] [ 80/400] eta: 0:02:07 lr: 0.000098 loss: 0.9098 (0.9154) grad: 0.0308 (0.0306) time: 0.3985 data: 0.0045 max mem: 3951 +train: [14] [100/400] eta: 0:01:57 lr: 0.000096 loss: 0.9153 (0.9167) grad: 0.0304 (0.0306) time: 0.3650 data: 0.0043 max mem: 3951 +train: [14] [120/400] eta: 0:01:47 lr: 0.000095 loss: 0.9031 (0.9126) grad: 0.0308 (0.0307) time: 0.3366 data: 0.0042 max mem: 3951 +train: [14] [140/400] eta: 0:01:37 lr: 0.000093 loss: 0.8732 (0.9073) grad: 0.0314 (0.0308) time: 0.3376 data: 0.0040 max mem: 3951 +train: [14] [160/400] eta: 0:01:28 lr: 0.000092 loss: 0.8834 (0.9076) grad: 0.0308 (0.0308) time: 0.3092 data: 0.0039 max mem: 3951 +train: [14] [180/400] eta: 0:01:20 lr: 0.000090 loss: 0.8846 (0.9061) grad: 0.0309 (0.0308) time: 0.3275 data: 0.0041 max mem: 3951 +train: [14] [200/400] eta: 0:01:12 lr: 0.000089 loss: 0.9139 (0.9081) grad: 0.0303 (0.0307) time: 0.3292 data: 0.0041 max mem: 3951 +train: [14] [220/400] eta: 0:01:04 lr: 0.000088 loss: 0.9164 (0.9088) grad: 0.0303 (0.0307) time: 0.3155 data: 0.0042 max mem: 3951 +train: [14] [240/400] eta: 0:00:56 lr: 0.000086 loss: 0.8955 (0.9065) grad: 0.0303 (0.0307) time: 0.3230 data: 0.0040 max mem: 3951 +train: [14] [260/400] eta: 0:00:49 lr: 0.000085 loss: 0.8955 (0.9075) grad: 0.0300 (0.0307) time: 0.3172 data: 0.0040 max mem: 3951 +train: [14] [280/400] eta: 0:00:41 lr: 0.000083 loss: 0.9034 (0.9074) grad: 0.0300 (0.0307) time: 0.3176 data: 0.0042 max mem: 3951 +train: [14] [300/400] eta: 0:00:35 lr: 0.000082 loss: 0.8994 (0.9068) grad: 0.0299 (0.0306) time: 0.4685 data: 0.1614 max mem: 3951 +train: [14] [320/400] eta: 0:00:28 lr: 0.000081 loss: 0.8854 (0.9065) grad: 0.0300 (0.0306) time: 0.3156 data: 0.0032 max mem: 3951 +train: [14] [340/400] eta: 0:00:21 lr: 0.000079 loss: 0.8904 (0.9068) grad: 0.0300 (0.0306) time: 0.3184 data: 0.0034 max mem: 3951 +train: [14] [360/400] eta: 0:00:13 lr: 0.000078 loss: 0.8904 (0.9060) grad: 0.0301 (0.0306) time: 0.3186 data: 0.0040 max mem: 3951 +train: [14] [380/400] eta: 0:00:06 lr: 0.000076 loss: 0.8945 (0.9068) grad: 0.0306 (0.0306) time: 0.3219 data: 0.0037 max mem: 3951 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.8824 (0.9056) grad: 0.0300 (0.0305) time: 0.3102 data: 0.0036 max mem: 3951 +train: [14] Total time: 0:02:18 (0.3471 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.8824 (0.9056) grad: 0.0300 (0.0305) +eval (validation): [14] [ 0/63] eta: 0:03:11 time: 3.0360 data: 2.7999 max mem: 3951 +eval (validation): [14] [20/63] eta: 0:00:19 time: 0.3134 data: 0.0029 max mem: 3951 +eval (validation): [14] [40/63] eta: 0:00:08 time: 0.3250 data: 0.0032 max mem: 3951 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3043 data: 0.0034 max mem: 3951 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3040 data: 0.0034 max mem: 3951 +eval (validation): [14] Total time: 0:00:22 (0.3614 s / it) +cv: [14] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 0.099 acc: 0.978 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:19:35 lr: nan time: 2.9383 data: 2.7323 max mem: 3951 +train: [15] [ 20/400] eta: 0:02:49 lr: 0.000074 loss: 0.9052 (0.9106) grad: 0.0303 (0.0307) time: 0.3221 data: 0.0167 max mem: 3951 +train: [15] [ 40/400] eta: 0:02:21 lr: 0.000072 loss: 0.8920 (0.9017) grad: 0.0299 (0.0303) time: 0.3383 data: 0.0027 max mem: 3951 +train: [15] [ 60/400] eta: 0:02:08 lr: 0.000071 loss: 0.8968 (0.9009) grad: 0.0299 (0.0305) time: 0.3447 data: 0.0036 max mem: 3951 +train: [15] [ 80/400] eta: 0:01:58 lr: 0.000070 loss: 0.8968 (0.8994) grad: 0.0311 (0.0306) time: 0.3522 data: 0.0041 max mem: 3951 +train: [15] [100/400] eta: 0:01:50 lr: 0.000068 loss: 0.8846 (0.8975) grad: 0.0307 (0.0307) time: 0.3494 data: 0.0040 max mem: 3951 +train: [15] [120/400] eta: 0:01:42 lr: 0.000067 loss: 0.8913 (0.8970) grad: 0.0300 (0.0306) time: 0.3555 data: 0.0041 max mem: 3951 +train: [15] [140/400] eta: 0:01:33 lr: 0.000066 loss: 0.8821 (0.8956) grad: 0.0300 (0.0306) time: 0.3362 data: 0.0038 max mem: 3951 +train: [15] [160/400] eta: 0:01:25 lr: 0.000064 loss: 0.8889 (0.8974) grad: 0.0299 (0.0305) time: 0.3352 data: 0.0040 max mem: 3951 +train: [15] [180/400] eta: 0:01:18 lr: 0.000063 loss: 0.8975 (0.8972) grad: 0.0299 (0.0305) time: 0.3413 data: 0.0041 max mem: 3951 +train: [15] [200/400] eta: 0:01:11 lr: 0.000062 loss: 0.8977 (0.8986) grad: 0.0299 (0.0305) time: 0.3641 data: 0.0044 max mem: 3951 +train: [15] [220/400] eta: 0:01:03 lr: 0.000061 loss: 0.8951 (0.8972) grad: 0.0297 (0.0305) time: 0.3400 data: 0.0045 max mem: 3951 +train: [15] [240/400] eta: 0:00:56 lr: 0.000059 loss: 0.9001 (0.8982) grad: 0.0305 (0.0305) time: 0.3470 data: 0.0042 max mem: 3951 +train: [15] [260/400] eta: 0:00:49 lr: 0.000058 loss: 0.9020 (0.8985) grad: 0.0299 (0.0304) time: 0.3467 data: 0.0041 max mem: 3951 +train: [15] [280/400] eta: 0:00:42 lr: 0.000057 loss: 0.8899 (0.8983) grad: 0.0293 (0.0304) time: 0.3392 data: 0.0043 max mem: 3951 +train: [15] [300/400] eta: 0:00:36 lr: 0.000056 loss: 0.8899 (0.8989) grad: 0.0295 (0.0303) time: 0.5129 data: 0.1734 max mem: 3951 +train: [15] [320/400] eta: 0:00:28 lr: 0.000054 loss: 0.8894 (0.8981) grad: 0.0297 (0.0304) time: 0.3256 data: 0.0044 max mem: 3951 +train: [15] [340/400] eta: 0:00:21 lr: 0.000053 loss: 0.8869 (0.8977) grad: 0.0297 (0.0303) time: 0.3606 data: 0.0041 max mem: 3951 +train: [15] [360/400] eta: 0:00:14 lr: 0.000052 loss: 0.8931 (0.8973) grad: 0.0301 (0.0303) time: 0.3562 data: 0.0045 max mem: 3951 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 0.8728 (0.8962) grad: 0.0298 (0.0303) time: 0.3448 data: 0.0046 max mem: 3951 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.8816 (0.8963) grad: 0.0297 (0.0303) time: 0.3538 data: 0.0042 max mem: 3951 +train: [15] Total time: 0:02:24 (0.3601 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.8816 (0.8963) grad: 0.0297 (0.0303) +eval (validation): [15] [ 0/63] eta: 0:03:09 time: 3.0068 data: 2.7981 max mem: 3951 +eval (validation): [15] [20/63] eta: 0:00:19 time: 0.3285 data: 0.0074 max mem: 3951 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3298 data: 0.0035 max mem: 3951 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3072 data: 0.0024 max mem: 3951 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3099 data: 0.0027 max mem: 3951 +eval (validation): [15] Total time: 0:00:23 (0.3690 s / it) +cv: [15] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.094 acc: 0.978 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:08 lr: nan time: 3.3219 data: 3.0537 max mem: 3951 +train: [16] [ 20/400] eta: 0:03:06 lr: 0.000048 loss: 0.8984 (0.9134) grad: 0.0283 (0.0286) time: 0.3504 data: 0.0042 max mem: 3951 +train: [16] [ 40/400] eta: 0:02:32 lr: 0.000047 loss: 0.8975 (0.9017) grad: 0.0292 (0.0295) time: 0.3536 data: 0.0037 max mem: 3951 +train: [16] [ 60/400] eta: 0:02:17 lr: 0.000046 loss: 0.8875 (0.8976) grad: 0.0298 (0.0300) time: 0.3588 data: 0.0044 max mem: 3951 +train: [16] [ 80/400] eta: 0:02:05 lr: 0.000045 loss: 0.9043 (0.9013) grad: 0.0296 (0.0299) time: 0.3531 data: 0.0042 max mem: 3951 +train: [16] [100/400] eta: 0:01:54 lr: 0.000044 loss: 0.8892 (0.8968) grad: 0.0297 (0.0299) time: 0.3528 data: 0.0038 max mem: 3951 +train: [16] [120/400] eta: 0:01:47 lr: 0.000043 loss: 0.8749 (0.8927) grad: 0.0297 (0.0300) time: 0.3982 data: 0.0042 max mem: 3951 +train: [16] [140/400] eta: 0:01:39 lr: 0.000042 loss: 0.8781 (0.8938) grad: 0.0303 (0.0301) time: 0.3550 data: 0.0041 max mem: 3951 +train: [16] [160/400] eta: 0:01:29 lr: 0.000041 loss: 0.8890 (0.8931) grad: 0.0312 (0.0302) time: 0.3298 data: 0.0041 max mem: 3951 +train: [16] [180/400] eta: 0:01:21 lr: 0.000040 loss: 0.8830 (0.8926) grad: 0.0299 (0.0302) time: 0.3447 data: 0.0041 max mem: 3951 +train: [16] [200/400] eta: 0:01:13 lr: 0.000039 loss: 0.8740 (0.8919) grad: 0.0290 (0.0302) time: 0.3559 data: 0.0044 max mem: 3951 +train: [16] [220/400] eta: 0:01:06 lr: 0.000038 loss: 0.8758 (0.8921) grad: 0.0297 (0.0302) time: 0.3471 data: 0.0040 max mem: 3951 +train: [16] [240/400] eta: 0:00:58 lr: 0.000036 loss: 0.8847 (0.8928) grad: 0.0303 (0.0302) time: 0.3431 data: 0.0042 max mem: 3951 +train: [16] [260/400] eta: 0:00:51 lr: 0.000035 loss: 0.8846 (0.8917) grad: 0.0303 (0.0303) time: 0.3472 data: 0.0042 max mem: 3951 +train: [16] [280/400] eta: 0:00:43 lr: 0.000034 loss: 0.8616 (0.8902) grad: 0.0293 (0.0302) time: 0.3671 data: 0.0045 max mem: 3951 +train: [16] [300/400] eta: 0:00:37 lr: 0.000033 loss: 0.8763 (0.8904) grad: 0.0292 (0.0302) time: 0.5228 data: 0.1808 max mem: 3951 +train: [16] [320/400] eta: 0:00:29 lr: 0.000032 loss: 0.8875 (0.8906) grad: 0.0301 (0.0302) time: 0.3383 data: 0.0035 max mem: 3951 +train: [16] [340/400] eta: 0:00:22 lr: 0.000031 loss: 0.8915 (0.8907) grad: 0.0298 (0.0302) time: 0.3633 data: 0.0040 max mem: 3951 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 0.8925 (0.8901) grad: 0.0294 (0.0302) time: 0.3621 data: 0.0039 max mem: 3951 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 0.8893 (0.8901) grad: 0.0302 (0.0302) time: 0.3484 data: 0.0041 max mem: 3951 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.8725 (0.8907) grad: 0.0303 (0.0302) time: 0.3355 data: 0.0043 max mem: 3951 +train: [16] Total time: 0:02:27 (0.3693 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.8725 (0.8907) grad: 0.0303 (0.0302) +eval (validation): [16] [ 0/63] eta: 0:03:19 time: 3.1644 data: 2.8822 max mem: 3951 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3611 data: 0.0029 max mem: 3951 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3133 data: 0.0032 max mem: 3951 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3126 data: 0.0035 max mem: 3951 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3130 data: 0.0035 max mem: 3951 +eval (validation): [16] Total time: 0:00:23 (0.3784 s / it) +cv: [16] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 0.098 acc: 0.978 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:27:11 lr: nan time: 4.0781 data: 3.8462 max mem: 3951 +train: [17] [ 20/400] eta: 0:03:15 lr: 0.000028 loss: 0.8938 (0.8921) grad: 0.0307 (0.0303) time: 0.3363 data: 0.0029 max mem: 3951 +train: [17] [ 40/400] eta: 0:02:39 lr: 0.000027 loss: 0.8836 (0.8791) grad: 0.0307 (0.0306) time: 0.3695 data: 0.0030 max mem: 3951 +train: [17] [ 60/400] eta: 0:02:21 lr: 0.000026 loss: 0.8686 (0.8804) grad: 0.0307 (0.0307) time: 0.3614 data: 0.0038 max mem: 3951 +train: [17] [ 80/400] eta: 0:02:07 lr: 0.000025 loss: 0.8923 (0.8857) grad: 0.0305 (0.0306) time: 0.3435 data: 0.0043 max mem: 3951 +train: [17] [100/400] eta: 0:01:55 lr: 0.000024 loss: 0.8855 (0.8855) grad: 0.0299 (0.0306) time: 0.3334 data: 0.0034 max mem: 3951 +train: [17] [120/400] eta: 0:01:45 lr: 0.000023 loss: 0.8820 (0.8854) grad: 0.0301 (0.0305) time: 0.3244 data: 0.0043 max mem: 3951 +train: [17] [140/400] eta: 0:01:36 lr: 0.000023 loss: 0.8820 (0.8856) grad: 0.0302 (0.0304) time: 0.3473 data: 0.0039 max mem: 3951 +train: [17] [160/400] eta: 0:01:28 lr: 0.000022 loss: 0.8838 (0.8860) grad: 0.0303 (0.0304) time: 0.3323 data: 0.0037 max mem: 3951 +train: [17] [180/400] eta: 0:01:19 lr: 0.000021 loss: 0.8838 (0.8869) grad: 0.0301 (0.0303) time: 0.3355 data: 0.0040 max mem: 3951 +train: [17] [200/400] eta: 0:01:12 lr: 0.000020 loss: 0.8784 (0.8852) grad: 0.0300 (0.0303) time: 0.3453 data: 0.0045 max mem: 3951 +train: [17] [220/400] eta: 0:01:04 lr: 0.000019 loss: 0.8798 (0.8867) grad: 0.0295 (0.0303) time: 0.3381 data: 0.0044 max mem: 3951 +train: [17] [240/400] eta: 0:00:57 lr: 0.000019 loss: 0.8904 (0.8859) grad: 0.0302 (0.0303) time: 0.3575 data: 0.0041 max mem: 3951 +train: [17] [260/400] eta: 0:00:50 lr: 0.000018 loss: 0.8882 (0.8853) grad: 0.0305 (0.0303) time: 0.3331 data: 0.0040 max mem: 3951 +train: [17] [280/400] eta: 0:00:42 lr: 0.000017 loss: 0.8956 (0.8863) grad: 0.0294 (0.0303) time: 0.3406 data: 0.0037 max mem: 3951 +train: [17] [300/400] eta: 0:00:36 lr: 0.000016 loss: 0.9016 (0.8884) grad: 0.0295 (0.0302) time: 0.4878 data: 0.1815 max mem: 3951 +train: [17] [320/400] eta: 0:00:28 lr: 0.000016 loss: 0.8809 (0.8870) grad: 0.0291 (0.0302) time: 0.3251 data: 0.0032 max mem: 3951 +train: [17] [340/400] eta: 0:00:21 lr: 0.000015 loss: 0.8766 (0.8876) grad: 0.0291 (0.0302) time: 0.3547 data: 0.0033 max mem: 3951 +train: [17] [360/400] eta: 0:00:14 lr: 0.000014 loss: 0.8864 (0.8871) grad: 0.0300 (0.0301) time: 0.3390 data: 0.0043 max mem: 3951 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 0.8686 (0.8870) grad: 0.0296 (0.0301) time: 0.3481 data: 0.0040 max mem: 3951 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.8686 (0.8870) grad: 0.0288 (0.0301) time: 0.3418 data: 0.0038 max mem: 3951 +train: [17] Total time: 0:02:23 (0.3596 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.8686 (0.8870) grad: 0.0288 (0.0301) +eval (validation): [17] [ 0/63] eta: 0:03:08 time: 2.9911 data: 2.7817 max mem: 3951 +eval (validation): [17] [20/63] eta: 0:00:19 time: 0.3231 data: 0.0032 max mem: 3951 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3539 data: 0.0034 max mem: 3951 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.2994 data: 0.0033 max mem: 3951 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.2966 data: 0.0033 max mem: 3951 +eval (validation): [17] Total time: 0:00:23 (0.3720 s / it) +cv: [17] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.095 acc: 0.978 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:21:29 lr: nan time: 3.2235 data: 2.9492 max mem: 3951 +train: [18] [ 20/400] eta: 0:02:52 lr: 0.000012 loss: 0.8974 (0.9016) grad: 0.0302 (0.0309) time: 0.3168 data: 0.0031 max mem: 3951 +train: [18] [ 40/400] eta: 0:02:26 lr: 0.000012 loss: 0.8974 (0.8980) grad: 0.0299 (0.0303) time: 0.3565 data: 0.0034 max mem: 3951 +train: [18] [ 60/400] eta: 0:02:12 lr: 0.000011 loss: 0.8757 (0.8868) grad: 0.0299 (0.0306) time: 0.3564 data: 0.0044 max mem: 3951 +train: [18] [ 80/400] eta: 0:02:03 lr: 0.000011 loss: 0.8529 (0.8807) grad: 0.0299 (0.0303) time: 0.3722 data: 0.0042 max mem: 3951 +train: [18] [100/400] eta: 0:01:52 lr: 0.000010 loss: 0.8583 (0.8798) grad: 0.0294 (0.0303) time: 0.3364 data: 0.0041 max mem: 3951 +train: [18] [120/400] eta: 0:01:45 lr: 0.000009 loss: 0.8801 (0.8808) grad: 0.0300 (0.0303) time: 0.3786 data: 0.0044 max mem: 3951 +train: [18] [140/400] eta: 0:01:36 lr: 0.000009 loss: 0.8780 (0.8806) grad: 0.0300 (0.0302) time: 0.3432 data: 0.0037 max mem: 3951 +train: [18] [160/400] eta: 0:01:28 lr: 0.000008 loss: 0.8780 (0.8825) grad: 0.0295 (0.0301) time: 0.3450 data: 0.0040 max mem: 3951 +train: [18] [180/400] eta: 0:01:20 lr: 0.000008 loss: 0.8803 (0.8811) grad: 0.0300 (0.0303) time: 0.3322 data: 0.0041 max mem: 3951 +train: [18] [200/400] eta: 0:01:12 lr: 0.000007 loss: 0.8832 (0.8837) grad: 0.0305 (0.0302) time: 0.3482 data: 0.0039 max mem: 3951 +train: [18] [220/400] eta: 0:01:05 lr: 0.000007 loss: 0.8940 (0.8846) grad: 0.0290 (0.0302) time: 0.3568 data: 0.0040 max mem: 3951 +train: [18] [240/400] eta: 0:00:58 lr: 0.000006 loss: 0.8939 (0.8852) grad: 0.0290 (0.0301) time: 0.3707 data: 0.0042 max mem: 3951 +train: [18] [260/400] eta: 0:00:50 lr: 0.000006 loss: 0.8766 (0.8836) grad: 0.0299 (0.0301) time: 0.3458 data: 0.0040 max mem: 3951 +train: [18] [280/400] eta: 0:00:43 lr: 0.000006 loss: 0.8766 (0.8840) grad: 0.0300 (0.0302) time: 0.3503 data: 0.0042 max mem: 3951 +train: [18] [300/400] eta: 0:00:37 lr: 0.000005 loss: 0.8951 (0.8857) grad: 0.0300 (0.0302) time: 0.5004 data: 0.1831 max mem: 3951 +train: [18] [320/400] eta: 0:00:29 lr: 0.000005 loss: 0.8933 (0.8866) grad: 0.0299 (0.0302) time: 0.3254 data: 0.0032 max mem: 3951 +train: [18] [340/400] eta: 0:00:22 lr: 0.000004 loss: 0.8719 (0.8852) grad: 0.0298 (0.0302) time: 0.3632 data: 0.0033 max mem: 3951 +train: [18] [360/400] eta: 0:00:14 lr: 0.000004 loss: 0.8788 (0.8857) grad: 0.0293 (0.0301) time: 0.3461 data: 0.0039 max mem: 3951 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 0.8946 (0.8858) grad: 0.0293 (0.0301) time: 0.3398 data: 0.0044 max mem: 3951 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.8653 (0.8848) grad: 0.0304 (0.0301) time: 0.3206 data: 0.0042 max mem: 3951 +train: [18] Total time: 0:02:25 (0.3630 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.8653 (0.8848) grad: 0.0304 (0.0301) +eval (validation): [18] [ 0/63] eta: 0:03:22 time: 3.2070 data: 2.9965 max mem: 3951 +eval (validation): [18] [20/63] eta: 0:00:21 time: 0.3616 data: 0.0199 max mem: 3951 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3541 data: 0.0029 max mem: 3951 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.2929 data: 0.0031 max mem: 3951 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.2942 data: 0.0030 max mem: 3951 +eval (validation): [18] Total time: 0:00:24 (0.3862 s / it) +cv: [18] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.103 acc: 0.978 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:21:24 lr: nan time: 3.2100 data: 2.9927 max mem: 3951 +train: [19] [ 20/400] eta: 0:02:57 lr: 0.000003 loss: 0.8758 (0.8854) grad: 0.0298 (0.0300) time: 0.3299 data: 0.0037 max mem: 3951 +train: [19] [ 40/400] eta: 0:02:24 lr: 0.000003 loss: 0.8856 (0.8869) grad: 0.0298 (0.0301) time: 0.3304 data: 0.0034 max mem: 3951 +train: [19] [ 60/400] eta: 0:02:09 lr: 0.000002 loss: 0.8900 (0.8920) grad: 0.0295 (0.0300) time: 0.3375 data: 0.0033 max mem: 3951 +train: [19] [ 80/400] eta: 0:01:59 lr: 0.000002 loss: 0.8849 (0.8902) grad: 0.0297 (0.0300) time: 0.3531 data: 0.0041 max mem: 3951 +train: [19] [100/400] eta: 0:01:48 lr: 0.000002 loss: 0.8734 (0.8840) grad: 0.0299 (0.0302) time: 0.3159 data: 0.0040 max mem: 3951 +train: [19] [120/400] eta: 0:01:40 lr: 0.000002 loss: 0.8753 (0.8837) grad: 0.0298 (0.0301) time: 0.3341 data: 0.0037 max mem: 3951 +train: [19] [140/400] eta: 0:01:31 lr: 0.000001 loss: 0.8818 (0.8827) grad: 0.0295 (0.0301) time: 0.3291 data: 0.0037 max mem: 3951 +train: [19] [160/400] eta: 0:01:23 lr: 0.000001 loss: 0.8705 (0.8808) grad: 0.0294 (0.0300) time: 0.3225 data: 0.0043 max mem: 3951 +train: [19] [180/400] eta: 0:01:16 lr: 0.000001 loss: 0.8784 (0.8805) grad: 0.0301 (0.0300) time: 0.3251 data: 0.0040 max mem: 3951 +train: [19] [200/400] eta: 0:01:09 lr: 0.000001 loss: 0.8809 (0.8801) grad: 0.0302 (0.0300) time: 0.3325 data: 0.0041 max mem: 3951 +train: [19] [220/400] eta: 0:01:01 lr: 0.000001 loss: 0.8741 (0.8807) grad: 0.0301 (0.0300) time: 0.3300 data: 0.0037 max mem: 3951 +train: [19] [240/400] eta: 0:00:54 lr: 0.000001 loss: 0.8630 (0.8789) grad: 0.0306 (0.0301) time: 0.3288 data: 0.0040 max mem: 3951 +train: [19] [260/400] eta: 0:00:47 lr: 0.000000 loss: 0.8750 (0.8805) grad: 0.0305 (0.0301) time: 0.3255 data: 0.0042 max mem: 3951 +train: [19] [280/400] eta: 0:00:40 lr: 0.000000 loss: 0.8725 (0.8795) grad: 0.0296 (0.0302) time: 0.3355 data: 0.0042 max mem: 3951 +train: [19] [300/400] eta: 0:00:34 lr: 0.000000 loss: 0.8672 (0.8808) grad: 0.0291 (0.0301) time: 0.4688 data: 0.1674 max mem: 3951 +train: [19] [320/400] eta: 0:00:27 lr: 0.000000 loss: 0.8793 (0.8809) grad: 0.0296 (0.0301) time: 0.3169 data: 0.0031 max mem: 3951 +train: [19] [340/400] eta: 0:00:20 lr: 0.000000 loss: 0.8662 (0.8800) grad: 0.0298 (0.0300) time: 0.3305 data: 0.0034 max mem: 3951 +train: [19] [360/400] eta: 0:00:13 lr: 0.000000 loss: 0.8655 (0.8803) grad: 0.0294 (0.0300) time: 0.3372 data: 0.0042 max mem: 3951 +train: [19] [380/400] eta: 0:00:06 lr: 0.000000 loss: 0.8655 (0.8799) grad: 0.0293 (0.0300) time: 0.3159 data: 0.0042 max mem: 3951 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.8699 (0.8802) grad: 0.0296 (0.0300) time: 0.3247 data: 0.0042 max mem: 3951 +train: [19] Total time: 0:02:17 (0.3439 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.8699 (0.8802) grad: 0.0296 (0.0300) +eval (validation): [19] [ 0/63] eta: 0:03:15 time: 3.1075 data: 2.8959 max mem: 3951 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3780 data: 0.0041 max mem: 3951 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3487 data: 0.0036 max mem: 3951 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3086 data: 0.0033 max mem: 3951 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3071 data: 0.0034 max mem: 3951 +eval (validation): [19] Total time: 0:00:24 (0.3925 s / it) +cv: [19] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.095 acc: 0.978 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +eval model info: +{"score": 0.9779265873015873, "hparam": [19, 1.0], "hparam_id": 42, "epoch": 19, "is_best": false, "best_score": 0.9784226190476191} +eval (train): [20] [ 0/297] eta: 0:16:32 time: 3.3434 data: 3.0850 max mem: 3951 +eval (train): [20] [ 20/297] eta: 0:02:13 time: 0.3380 data: 0.0039 max mem: 3951 +eval (train): [20] [ 40/297] eta: 0:01:43 time: 0.3202 data: 0.0030 max mem: 3951 +eval (train): [20] [ 60/297] eta: 0:01:32 time: 0.3634 data: 0.0035 max mem: 3951 +eval (train): [20] [ 80/297] eta: 0:01:21 time: 0.3312 data: 0.0033 max mem: 3951 +eval (train): [20] [100/297] eta: 0:01:11 time: 0.3160 data: 0.0033 max mem: 3951 +eval (train): [20] [120/297] eta: 0:01:03 time: 0.3454 data: 0.0036 max mem: 3951 +eval (train): [20] [140/297] eta: 0:00:56 time: 0.3467 data: 0.0038 max mem: 3951 +eval (train): [20] [160/297] eta: 0:00:48 time: 0.3167 data: 0.0036 max mem: 3951 +eval (train): [20] [180/297] eta: 0:00:40 time: 0.3135 data: 0.0032 max mem: 3951 +eval (train): [20] [200/297] eta: 0:00:33 time: 0.3432 data: 0.0038 max mem: 3951 +eval (train): [20] [220/297] eta: 0:00:26 time: 0.3189 data: 0.0034 max mem: 3951 +eval (train): [20] [240/297] eta: 0:00:19 time: 0.3254 data: 0.0034 max mem: 3951 +eval (train): [20] [260/297] eta: 0:00:12 time: 0.3266 data: 0.0035 max mem: 3951 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3112 data: 0.0033 max mem: 3951 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.2955 data: 0.0031 max mem: 3951 +eval (train): [20] Total time: 0:01:41 (0.3402 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:14 time: 3.0848 data: 2.8226 max mem: 3951 +eval (validation): [20] [20/63] eta: 0:00:19 time: 0.3326 data: 0.0035 max mem: 3951 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3607 data: 0.0029 max mem: 3951 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3126 data: 0.0035 max mem: 3951 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3098 data: 0.0034 max mem: 3951 +eval (validation): [20] Total time: 0:00:24 (0.3829 s / it) +eval (test): [20] [ 0/79] eta: 0:04:07 time: 3.1311 data: 2.8765 max mem: 3951 +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3675 data: 0.0082 max mem: 3951 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3323 data: 0.0034 max mem: 3951 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3261 data: 0.0034 max mem: 3951 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3041 data: 0.0031 max mem: 3951 +eval (test): [20] Total time: 0:00:29 (0.3716 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +eval model info: +{"score": 0.9784226190476191, "hparam": [36, 1.0], "hparam_id": 46, "epoch": 9, "is_best": true, "best_score": 0.9784226190476191} +eval (train): [20] [ 0/297] eta: 0:14:38 time: 2.9578 data: 2.7512 max mem: 3951 +eval (train): [20] [ 20/297] eta: 0:02:07 time: 0.3348 data: 0.0169 max mem: 3951 +eval (train): [20] [ 40/297] eta: 0:01:45 time: 0.3563 data: 0.0033 max mem: 3951 +eval (train): [20] [ 60/297] eta: 0:01:32 time: 0.3531 data: 0.0031 max mem: 3951 +eval (train): [20] [ 80/297] eta: 0:01:21 time: 0.3336 data: 0.0035 max mem: 3951 +eval (train): [20] [100/297] eta: 0:01:12 time: 0.3454 data: 0.0032 max mem: 3951 +eval (train): [20] [120/297] eta: 0:01:03 time: 0.3104 data: 0.0034 max mem: 3951 +eval (train): [20] [140/297] eta: 0:00:56 time: 0.3693 data: 0.0034 max mem: 3951 +eval (train): [20] [160/297] eta: 0:00:49 time: 0.3391 data: 0.0037 max mem: 3951 +eval (train): [20] [180/297] eta: 0:00:41 time: 0.3288 data: 0.0033 max mem: 3951 +eval (train): [20] [200/297] eta: 0:00:34 time: 0.3278 data: 0.0036 max mem: 3951 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3594 data: 0.0035 max mem: 3951 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3365 data: 0.0034 max mem: 3951 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3472 data: 0.0037 max mem: 3951 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3182 data: 0.0034 max mem: 3951 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3000 data: 0.0036 max mem: 3951 +eval (train): [20] Total time: 0:01:43 (0.3487 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:12 time: 3.0477 data: 2.7932 max mem: 3951 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3404 data: 0.0103 max mem: 3951 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3123 data: 0.0032 max mem: 3951 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3056 data: 0.0032 max mem: 3951 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3077 data: 0.0032 max mem: 3951 +eval (validation): [20] Total time: 0:00:23 (0.3675 s / it) +eval (test): [20] [ 0/79] eta: 0:04:12 time: 3.1907 data: 2.9677 max mem: 3951 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3543 data: 0.0035 max mem: 3951 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3300 data: 0.0032 max mem: 3951 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3236 data: 0.0035 max mem: 3951 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.2948 data: 0.0034 max mem: 3951 +eval (test): [20] Total time: 0:00:28 (0.3666 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|---------:|--------:|-----------:|--------:|-----------:| +| flat_mae | reg | linear | hcpya_task21 | best | 9 | 0.0108 | 0.05 | 46 | [36, 1.0] | train | 0.058015 | 0.991 | 0.00065766 | 0.99167 | 0.00066259 | +| flat_mae | reg | linear | hcpya_task21 | best | 9 | 0.0108 | 0.05 | 46 | [36, 1.0] | validation | 0.096309 | 0.97842 | 0.0022775 | 0.97538 | 0.0029339 | +| flat_mae | reg | linear | hcpya_task21 | best | 9 | 0.0108 | 0.05 | 46 | [36, 1.0] | test | 0.10561 | 0.9752 | 0.002347 | 0.96976 | 0.0031647 | + + +done! total time: 1:01:56 diff --git a/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/train_log.json b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..fa9e62738f00212f481fad28d7e7b52bc2fdb752 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/hcpya_task21__reg__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.8305206310749056, "train/grad": 0.057987456507980824, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.039559326171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.039442138671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.039237060546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.039019775390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.03881103515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.038514404296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.03819580078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.037822265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.037333984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.036837158203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.03630859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.035452880859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.034642333984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.03340087890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.032110595703125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.030899658203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.029239501953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.027161865234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.02473876953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.022166748046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.01890869140625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.01518310546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.010711669921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.00532958984375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.99927978515625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.99119873046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.98312255859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.975064697265625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.963092041015625, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9472802734375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.931571044921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.91613525390625, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.893193359375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.870540771484375, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8408013916015626, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.808172607421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7690887451171875, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7277423095703126, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6777886962890625, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6078262329101562, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5477914428710937, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4907354736328124, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4107684326171874, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.336992645263672, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.247313003540039, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.14747932434082, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.059351463317871, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.9520435333251953, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.8601122856140138, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008634919854812325, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008634747781325131, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00863440855871886, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008634063443168997, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008633799140807242, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008633342492394148, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0086328838695772, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008632383956573904, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00863163530593738, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008630868270993233, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008630153122358025, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008628879515454173, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008627649580594152, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00862589012598619, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00862400142243132, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008622188121080399, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008619649664033203, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008616589605808259, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008613007578533142, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008609340330585837, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008604331463575364, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00859893009532243, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008592152965720743, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008584308912977576, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008574866382405162, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008562619707081467, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008550571773666889, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008538232094142586, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008520185274537653, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008495725926477462, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00847177712712437, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0084474782878533, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008411099382210524, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008374786791391671, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008326032157056034, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008270341651514173, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008201931293588132, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00812679948983714, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008031387797091156, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007890171732287853, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0077617424284107985, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007634596473071725, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007449372461996973, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0072725992836058136, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0070516149164177476, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006800044853007421, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0065733288147021085, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.006292437720112502, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0060478164243977514, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.035752058029175, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.035383939743042, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.034754514694214, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.034120798110962, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.033505439758301, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0326085090637207, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.031616449356079, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0304813385009766, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.028974771499634, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0273211002349854, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.025725841522217, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.023184299468994, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.020702600479126, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.016918897628784, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0131986141204834, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.009439706802368, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0044548511505127, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9982216358184814, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.990779399871826, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.983351230621338, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.973463773727417, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9623796939849854, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9489359855651855, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9330973625183105, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.914900302886963, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8908534049987793, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.867002487182617, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8433611392974854, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8082332611083984, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7621099948883057, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.71677827835083, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.672122001647949, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.606637477874756, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5427417755126953, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.460038661956787, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.37032413482666, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.265501022338867, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.1569457054138184, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.029651403427124, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.8592860698699951, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.7202552556991577, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.5954757928848267, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.4315482378005981, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.2921688556671143, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.1376328468322754, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9842219948768616, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8643462061882019, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.73725426197052, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6431695222854614, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.08333333333333333, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0845734126984127, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.08531746031746032, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0882936507936508, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08978174603174603, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.09250992063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.09375, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09846230158730158, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10416666666666667, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.109375, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1130952380952381, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.12251984126984126, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1324404761904762, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.14682539682539683, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16046626984126985, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1765873015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19915674603174602, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2234623015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.25818452380952384, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.28596230158730157, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.32043650793650796, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.35987103174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.40054563492063494, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.4419642857142857, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.48139880952380953, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5280257936507936, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5696924603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5989583333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6369047619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6750992063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6996527777777778, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7172619047619048, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7281746031746031, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7373511904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7485119047619048, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7589285714285714, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7690972222222222, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7805059523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7938988095238095, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8097718253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8244047619047619, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8410218253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8611111111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8787202380952381, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8973214285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9112103174603174, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9228670634920635, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9337797619047619, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9422123015873016, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.054410092647736205, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05493937311298399, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05509989821693314, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.056756253216765286, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05717436234058332, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05892276689343653, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0591622613569656, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.06251390078910889, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.06561038728254143, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06857142633146839, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07146600022492564, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07575113270817824, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08038543209823981, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.08926472638300081, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.09520975128935308, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10548223400219661, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12042377459485351, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1384431678397729, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16287370632612108, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.18122668101256498, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.2097687249054023, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.24134697626747273, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2759774970662533, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3107097343843829, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3428332452529145, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.3830488264232494, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.41977114741435384, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.4423013496223086, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.47513628149032977, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5028416763612533, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5228405475501313, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5363790716789557, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.5484916195448657, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.5576636236549517, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5716579187490024, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5866900124874656, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6040387634797756, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.622252563019247, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6439526094402075, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6757051957672958, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7078716139635959, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.746055221689488, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.7880954433619923, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8241969076517639, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8568502911301908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8830951895761568, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.904162469908117, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9196960081087937, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9320778348101516, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 1.8601122856140138, "validation/loss_best": 0.6431695222854614, "validation/acc_best": 0.9422123015873016, "validation/f1_best": 0.9320778348101516} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.2674589133262635, "train/grad": 0.05149967899546027, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.033272705078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.03235107421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.030867919921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0294091796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.027947998046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.02585205078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.02352783203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0209130859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.01740478515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0135693359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.009775390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.003865966796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.998111572265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.989451904296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.980732421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.972125244140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.960654296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.946419677734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.92932373046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.912432861328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.890106201171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.865252685546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.834996337890625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.799974365234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.76008544921875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.70798583984375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.6570489501953123, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.607242431640625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.5347393798828124, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.4417840576171876, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.353238525390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2690548706054687, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1502981567382813, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0403366088867188, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9064093017578125, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.771380615234375, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6260272979736328, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.4884942626953126, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.3422389221191406, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1682966995239257, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0423376846313477, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9392987537384033, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.816830358505249, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7222565507888794, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6262370204925537, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5385674226284027, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4744342851638794, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.40952223479747774, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3630049180984497, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008714084955863654, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008712759139016271, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008710624696686865, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008708365934435278, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008706168432254344, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008703102478757501, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008699614927172661, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008695617869962006, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008690175330266357, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008684648708440363, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008678732626140117, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008670064890757202, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008661493342369795, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008648397447541357, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008635672172531486, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008622446006629616, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008605191914830357, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008582922432105988, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008556879996322096, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008530989848077297, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008496863425243646, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008457786152139306, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008410819086711853, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008354739982169122, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008289565437007696, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008203051537275314, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00811511773383245, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008026763992384077, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007892777621746063, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007711296686902642, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007527447678148747, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007343267863616347, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00706881933612749, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006801452294457704, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006461752788163721, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006107318047434092, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005714891587849706, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005334623985690996, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004921445254003629, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0044187140476424245, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004046992167131975, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037385787861421702, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0033661348558962343, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0030736212711781263, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002771449841093272, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.002489750825916417, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002279930138611235, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0020637123961932957, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0019064703170442953, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.028167247772217, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0266711711883545, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0241451263427734, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0216338634490967, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.019113063812256, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0156126022338867, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.01157283782959, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0070815086364746, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0010759830474854, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9945857524871826, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.988128185272217, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9781830310821533, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9682817459106445, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.953509569168091, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9388318061828613, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.924208641052246, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.9047980308532715, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.880805730819702, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8522160053253174, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8239481449127197, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7867255210876465, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.745408058166504, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6957995891571045, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.638361692428589, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.573697090148926, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.49002742767334, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.409245729446411, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.3313796520233154, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.219844102859497, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.080775022506714, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.9523398876190186, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.8341338634490967, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.6746731996536255, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.5347886085510254, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.37436842918396, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.2238757610321045, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.0742098093032837, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9443596005439758, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.8184956312179565, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.684403657913208, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5971454381942749, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5314654111862183, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.45923739671707153, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.40718594193458557, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.35722842812538147, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.31345489621162415, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2823043167591095, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.25116944313049316, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2289278507232666, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.10689484126984126, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.11011904761904762, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.11805555555555555, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.13020833333333334, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.13938492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.15104166666666666, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.16865079365079366, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.18675595238095238, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.21478174603174602, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.24057539682539683, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.26785714285714285, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.30431547619047616, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3368055555555556, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3841765873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4243551587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.45709325396825395, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.49677579365079366, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5414186507936508, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5818452380952381, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6150793650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6507936507936508, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6780753968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7021329365079365, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7202380952380952, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7299107142857143, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.7410714285714286, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7497519841269841, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7599206349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7686011904761905, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7824900793650794, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7958829365079365, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8075396825396826, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8256448412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.84375, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8670634920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8871527777777778, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9055059523809523, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9156746031746031, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9283234126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9409722222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9469246031746031, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9489087301587301, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9523809523809523, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9558531746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9655257936507936, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06682437171979332, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.06856585379329826, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.07353003734418606, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07960697382735257, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.08443298648381312, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.09026826958637081, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.10012852297018592, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.11135586830417366, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.13097717138821294, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.14810697173490558, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.16791327311957702, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.19628808330036607, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.22117994656491338, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.2620447295441864, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.29530490332444803, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.32097490087025565, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.35746112029175137, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.3945243045618118, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.4295353748103577, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.45567292541099275, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.4839516794264823, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5077519451200048, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5254546136469037, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.5384624222131147, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5481718843190335, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5623688393725979, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5729161581904454, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5871350240519102, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6038960090494921, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6252115006008132, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6494595507369603, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6766462888155411, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.716932384685518, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7574346985738971, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8029854781584265, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8419934383749302, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8738645219161522, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8927489990972545, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9132549510356165, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.932641259289778, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9385442304444832, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9412570798026285, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9449580878894976, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9486881776692115, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9526542586498756, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9552183458673797, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.957275722850289, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9584009363211033, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9599498366289962, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.3630049180984497, "validation/loss_best": 0.2289278507232666, "validation/acc_best": 0.9655257936507936, "validation/f1_best": 0.9599498366289962} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.9045893663167954, "train/grad": 0.046324483063071964, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.023372802734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.021063232421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.0170654296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.013101806640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.009049072265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.003673095703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.997281494140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.99018798828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.980811767578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.97069091796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.96057373046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.945013427734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9296435546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.90666015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.88397216796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.861373291015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.831624755859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.794921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.75144775390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.70880615234375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.65301513671875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.59178466796875, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.518973388671875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.436009521484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3442059326171876, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2279483032226564, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1190121459960936, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.01673583984375, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.875704803466797, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7086166381835937, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5628907012939453, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.435524444580078, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.2739419555664062, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.1408146286010743, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9977809524536133, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8720588874816895, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7546940803527832, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6583284568786621, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.5690326261520385, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.4776892614364624, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4195761203765869, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.37637984156608584, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.32890865445137024, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.2947398459911346, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.26170134961605074, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.23250701725482942, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.21140508383512496, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1900301134586334, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.174535813331604, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008617527547758073, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008614062909036874, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008607757936697453, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008601847453974187, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008595661714207382, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008587370165623725, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008578244417440145, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008567940162029117, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008553765048272908, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008538740111980588, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008523490689694881, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008499708843883126, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008476190504152327, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008440686506219208, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008405942688696086, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008370940743479877, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008325106378179044, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008267341970931739, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008198088442441076, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008128620192874223, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008034839895553886, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00792842822847888, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007797235960606485, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0076403645076788965, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007456856013741344, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007209925299976021, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006962973640765995, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006718559777364135, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006363997186999768, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0059238325292244555, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005526999977882951, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005173426584806293, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00471711085177958, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004335250341100618, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003917761771008372, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003542920924955979, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00318504570517689, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0028840527136344465, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0025991186848841608, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00230128854571376, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0021091782732401043, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0019643906562123448, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001804734203615226, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0016891424352070317, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001576650668575894, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001477165184332989, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0014047336843213997, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0013305057777324692, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0012764997678459621, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0156588554382324, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0122742652893066, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0066540241241455, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0010485649108887, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.99541974067688, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9876132011413574, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.978693723678589, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9687044620513916, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.95544171333313, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.941120147705078, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9268879890441895, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9051320552825928, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.883547067642212, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8514912128448486, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.819772720336914, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.788468360900879, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.747234344482422, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6966099739074707, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6371145248413086, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5789895057678223, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.503615140914917, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4216082096099854, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.3252739906311035, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.2170536518096924, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.0993845462799072, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.9543719291687012, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.8221062421798706, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.702025055885315, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.5423429012298584, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.3626761436462402, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2145025730133057, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0915734767913818, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9440589547157288, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8300411701202393, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7147486805915833, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.619475245475769, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.535105288028717, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.46875250339508057, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.4091545045375824, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.3495883643627167, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3121836483478546, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.2844170928001404, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.25401872396469116, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23199526965618134, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.21062590181827545, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.19167359173297882, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.17777463793754578, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.16388873755931854, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1537957638502121, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.15004960317460317, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.16517857142857142, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18898809523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21502976190476192, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.23834325396825398, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2700892857142857, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3020833333333333, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.33705357142857145, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3792162698412698, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.41716269841269843, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.4503968253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.4957837301587302, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5374503968253969, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5860615079365079, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6215277777777778, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6532738095238095, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6788194444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7056051587301587, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7256944444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7371031746031746, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7462797619047619, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7547123015873016, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.7648809523809523, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7755456349206349, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7876984126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8005952380952381, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8149801587301587, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8288690476190477, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8501984126984127, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.8725198412698413, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8923611111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9060019841269841, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9169146825396826, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9298115079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9632936507936508, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9670138888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9689980158730159, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.09005128267100548, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.09833930237511551, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.11232856517600907, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.13150243031984593, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.14707275318126292, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.16994912461978184, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.19390533312709576, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.22165209234306626, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2584360699068608, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.2897328660842362, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.3165989192217296, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.3561722824384971, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.39408291975077736, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4336194900524755, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.46299496581804384, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.48930015261846466, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5100755591520837, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5315892392623306, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5487201064196464, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.56217948557944, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5711213518448008, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.5831444794414966, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5988369698691982, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6180961319663634, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6363885788584485, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.6589919916694831, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6921109007246096, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.7225741031830177, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7696378530513664, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8168604444351207, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8493730353460665, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8749824180573643, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.895048359567882, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9151419487451116, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9316156085291235, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.93838771027889, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.943134466887187, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9446572073634679, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.948125152731268, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9526133760097033, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9551752690508695, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9574002477654585, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9588917219768709, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9591371262471637, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9598834856585154, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9608562058197954, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9617267550834183, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9633135825150447, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.963578715398075, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.174535813331604, "validation/loss_best": 0.1537957638502121, "validation/acc_best": 0.9689980158730159, "validation/f1_best": 0.963578715398075} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 1.659110242128372, "train/grad": 0.043112281281501054, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.00825439453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.0037255859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.995902099609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.988323974609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.980645751953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.97005615234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.957852783203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.944285888671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.926220703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.906854248046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.88763916015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.85826416015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8292529296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7862744140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.743914794921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.702310791015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6478411865234377, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.581435546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.50409912109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4291790771484374, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3333123779296874, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2306634521484376, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1124176025390624, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9827346801757812, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.84597412109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6833433532714843, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5410304260253906, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4163343048095702, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2575595092773437, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0877321243286133, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9546519660949707, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8488455963134766, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.7271126651763916, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6364479827880859, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.5473709344863892, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.4754157614707947, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.41243518114089966, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.36338295698165896, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.31940704464912417, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.2752509945631027, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.24745612293481828, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.22664270609617232, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.20366350561380386, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.18687248438596726, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.17031186871230602, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.15539312563836574, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.14443778190761805, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.13313778653740882, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.12473255090415478, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008636186018120497, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008629261443857103, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008617866698186845, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008606521324254572, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00859545097220689, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008579144733957947, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008560840389691293, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008539510692935437, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008512145814020187, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008482008625287562, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008452137284912169, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008406992859672755, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008361897794529796, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008294870764948427, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008226819594856351, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00815854453947395, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00806661523412913, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007950987399090082, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007810772841330618, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007668985316995531, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007477745574433357, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007259800527244806, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0069917613849975165, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006677705876063556, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006326955505646765, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00588978343643248, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005495245750062168, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0051436829147860404, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004689699850277975, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004197321545798331, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003803451646817848, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003484079723712057, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003107414824189618, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002819782019359991, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0025309779332019387, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0022927447623806076, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0020818255009362476, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0019150022219400853, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0017647674132604152, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001612749551422894, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0015164572035428136, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0014446094137383625, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001363806322333403, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0013043025822844355, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0012451222323579714, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0011908807163126768, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0011505242774728685, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0011074979667318986, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0010749246520572343, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9981462955474854, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.992192268371582, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.982246160507202, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9723873138427734, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.962519645690918, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9487857818603516, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9331655502319336, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.915682792663574, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.892587184906006, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8677334785461426, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8431308269500732, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.805734395980835, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7687883377075195, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7143821716308594, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6610310077667236, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6087779998779297, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5408074855804443, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.458466053009033, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.363435983657837, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.272472620010376, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.157463550567627, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.0362749099731445, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.899756908416748, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7538657188415527, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6046264171600342, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.4334896802902222, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.28941011428833, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.1678621768951416, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.019148826599121, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.8677456378936768, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.7547383308410645, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6682324409484863, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.5722188949584961, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.5027374625205994, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.4358583688735962, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.38252609968185425, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.3362692892551422, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.3002723455429077, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.26807737350463867, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.23564806580543518, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2151968628168106, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.19989612698554993, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1829601526260376, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17063654959201813, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1586565375328064, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1479988396167755, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1404166966676712, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.133089080452919, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12810654938220978, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.22569444444444445, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.25148809523809523, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2876984126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.32242063492063494, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.35639880952380953, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3960813492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4367559523809524, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4742063492063492, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5181051587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5612599206349206, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5942460317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6324404761904762, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6651785714285714, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6961805555555556, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7157738095238095, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7289186507936508, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7408234126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7487599206349206, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7579365079365079, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.767609126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7814980158730159, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7916666666666666, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8075396825396826, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8246527777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8427579365079365, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8673115079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8834325396825397, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8958333333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9107142857142857, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9248511904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9365079365079365, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9437003968253969, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9528769841269841, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9610615079365079, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.964781746031746, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9657738095238095, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9675099206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.970734126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.970734126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.13792376775425233, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.15656448285565508, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.18105232968993962, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.20905135893557814, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.23883282034145487, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.2712968873916661, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.3045286230574411, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.3368416939432762, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.37406590851610566, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4136330364162762, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.43890313464805353, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.4692049786657939, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4960497566895971, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5225894448737913, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5362509245192121, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5504082084767222, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.5651262286760103, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5731402636881084, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.5907632320314125, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6040994561927328, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6274742043211057, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6446783642618162, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.6756876072718262, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.711735760944294, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.7514303651415412, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8030085831345483, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8332178159380306, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8561487986163799, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8819690443031744, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9072760786944536, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9259699781837486, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9353796850452356, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9405107449080584, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9434384419080818, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9463538092830148, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.950056013108864, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9531129588080897, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9551770353025779, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9570926265100924, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9596289715843117, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9603614490298304, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9619206423501743, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9629135038392024, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9638434043070444, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.965502293740454, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9659203386500295, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.966742806137579, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9670331314706696, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9661891473465604, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.14443778190761805, "validation/loss_best": 0.1404166966676712, "validation/acc_best": 0.9719742063492064, "validation/f1_best": 0.966742806137579} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.4742702662944793, "train/grad": 0.04047617200762033, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.988511962890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9809375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.96828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.95573974609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.94321533203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.92584716796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.9061474609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8841015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.8549462890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.823824462890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.79296142578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7462353515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.70025634765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.63289794921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.567293701171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.503487548828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4209332275390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.322037353515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.209461669921875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1033358764648438, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.9717282104492186, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.8363818359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.6879750061035157, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.5343087768554688, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.3821712493896485, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.2140943145751952, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.0776939392089844, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.9661100387573243, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.8338740158081055, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.7041909885406494, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.6100971508026123, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5395052337646484, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.4621871399879456, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.4068241763114929, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3537916398048401, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.3115244281291962, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.27482703924179075, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.24607886284589767, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2201036837697029, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.19364144027233124, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.17667486995458603, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1637592127919197, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.14920020282268523, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.13835283517837524, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.12747822102159262, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.11750081732869148, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.11004894757643342, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.10223176268860698, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.09643563644960523, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008631031808909029, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008620146880857646, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008601061811204999, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008581983589101583, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008562685996294022, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00853578516514972, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008505129835102708, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008471085741184652, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00842571167042479, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00837762163951993, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008329587399493903, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008254309773910791, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0081786451744847, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00806428745156154, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007948823829647154, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00783257391070947, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007675332424696535, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007476392581593245, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007234182415995747, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006990151659119874, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006667607724666596, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00631597415311262, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005912673231214285, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005482332699466496, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005049578638281673, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004565916846040637, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00416857190662995, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038381675141863523, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003438354235840961, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003035069648176432, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002734880230855197, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0025051751430146397, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0022492875106399877, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0020635862945346164, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0018837978655938058, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0017393634823383763, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0016130892350338399, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001513761705136858, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0014233574538957327, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0013300656204228288, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0012695621969760395, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001222633472061716, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0011690407816786319, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001128084227675572, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0010862826224183665, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0010467574713402428, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00101643960661022, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0009839407910476438, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0009596303984289989, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.975759506225586, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.966508388519287, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9511399269104004, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9358694553375244, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9206607341766357, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8995208740234375, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8755390644073486, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8488268852233887, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8136274814605713, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7760002613067627, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7388288974761963, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.682774305343628, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6277859210968018, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.547621488571167, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.470019578933716, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.394977331161499, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.2987852096557617, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.1847119331359863, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.0567233562469482, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.9379163980484009, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.7933908700942993, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.6482006311416626, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.4933347702026367, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.3376760482788086, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.1883952617645264, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.0293316841125488, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.9049540758132935, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.8063235878944397, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.693204402923584, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.5859183073043823, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5099866390228271, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.45378920435905457, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.3931516110897064, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3499189019203186, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3085620403289795, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.27561047673225403, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.2468576282262802, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.22441373765468597, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.20398969948291779, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.18337957561016083, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.17004479467868805, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.16005703806877136, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.14892731606960297, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.14083026349544525, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13287575542926788, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12584836781024933, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12080547213554382, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11578628420829773, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11224362254142761, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.31101190476190477, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.34226190476190477, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.392609126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.4305555555555556, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.4625496031746032, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5037202380952381, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.5458829365079365, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5855654761904762, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6222718253968254, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6577380952380952, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6817956349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.707093253968254, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7212301587301587, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7358630952380952, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7450396825396826, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.753968253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7643849206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7765376984126984, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7901785714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8015873015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8191964285714286, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8355654761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8583829365079365, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8764880952380952, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8940972222222222, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9089781746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9206349206349206, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9317956349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.941468253968254, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9489087301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9513888888888888, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9546130952380952, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9618055555555556, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9650297619047619, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.966765873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9704861111111112, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9714781746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9732142857142857, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9749503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.20045371331638911, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.22577316599710512, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.26787520475288473, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2986888076051129, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3259446857702931, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.3606602808141396, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.39840494991609915, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.432207262915277, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.45981609244150284, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4890374830081161, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5104582105807802, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.52830540005225, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5414328078904816, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5568214326501884, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.569524949789543, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5844723738559436, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6001559014456649, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6185509259104793, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6406956169328354, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.6636096910022199, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.7007011242127626, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.737215826114924, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7846791813901123, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8216039368162521, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8542176078184065, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8828144664241303, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9019637928992655, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9187571289556147, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9325842136024718, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9417288444728887, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9442634796747117, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.948028481403104, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9509183942413836, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9513254103097495, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9540873074969635, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9551068088291869, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9565684209535716, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9583918238142315, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9593965314761226, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9614041176031277, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9631064522363639, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9649958895181334, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9659236756558985, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9669255755133218, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9660118534791786, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.967201885519543, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9686989462596498, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9699365654622097, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9711274722047308, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.09643563644960523, "validation/loss_best": 0.11224362254142761, "validation/acc_best": 0.9749503968253969, "validation/f1_best": 0.9711274722047308} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 1.3329566717147827, "train/grad": 0.03816303510218859, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.964005126953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.952950439453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.934613037109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.916278076171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.898221435546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.872991943359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.844454345703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.81269775390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.77106201171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.72656494140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.682838134765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.61706298828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5528076171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.459847412109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3703546142578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.2844970703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.1756866455078123, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.048330993652344, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.9076791381835938, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.7798117065429688, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.6273487854003905, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.4780644226074218, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.322606887817383, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.170750274658203, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.0293906402587891, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.8830268096923828, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7717713832855224, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.6854146003723145, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.5881618356704712, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.4971661281585693, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.43338029623031615, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.38641675233840944, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.3355878901481628, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.2993025243282318, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.2645015025138855, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2366251140832901, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.21208425015211105, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.1926254850625992, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.17480887591838837, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.15630942568182946, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.14421961292624474, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1349233041703701, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1242505107074976, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.11624858934432268, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.10807074720039964, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10053220055997372, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09486151510849596, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.08898900171741843, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.08468284605070948, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008579639019444585, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008562770893331618, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00853410349227488, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008505981480702758, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008477774274069816, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008439043322578072, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00839520626468584, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00834608266595751, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008280958810355515, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008209019377827644, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008136390019208193, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008024257067590952, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007911621404346078, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00773981400532648, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007566241587046534, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007389596994034946, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007151831369847059, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00685328712919727, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006500196296256036, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006161369283217937, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005742009577807039, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005320777271408588, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004876826955005527, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00443814346450381, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004022543712053448, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0035825359239242973, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0032386262912768873, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0029656368063297124, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0026508329389616845, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0023499221744714303, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0021350210788659753, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0019750803482020273, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0018004484678385778, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001674704045872204, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0015534799336455762, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0014555189007660373, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0013686984326341189, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.001298791240551509, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0012338557885959744, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0011650367232505232, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0011191248503746466, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0010825809993548318, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0010401054989779368, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0010074106244428549, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009729087073355913, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0009405025294108782, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0009160898180562071, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.000889993562886957, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000871060606878018, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.951206684112549, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9383769035339355, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9171040058135986, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.896007776260376, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8750853538513184, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8460206985473633, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.813209056854248, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7767207622528076, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7288942337036133, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6779656410217285, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.628058910369873, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.5531487464904785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.4805285930633545, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.3756322860717773, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.275705099105835, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.1805782318115234, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.0609498023986816, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.9227365255355835, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.7727774381637573, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6388237476348877, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.482394814491272, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.3324872255325317, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.1803302764892578, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.0353076457977295, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.9037467837333679, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7712409496307373, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6730818748474121, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5982199907302856, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.5151137709617615, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.438291996717453, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3849213421344757, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.34574374556541443, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.30335336923599243, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2732904553413391, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.2442973256111145, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.2210787832736969, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.20078277587890625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.18466348946094513, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.17007030546665192, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1551012098789215, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14546474814414978, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1382811963558197, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13018006086349487, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.12429305166006088, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11853662878274918, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.11357183009386063, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.11002715677022934, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.10656047612428665, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.10440550744533539, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.3931051587301587, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.4243551587301587, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.470734126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5106646825396826, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.548859126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5912698412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6242559523809523, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.658234126984127, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6865079365079365, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7103174603174603, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.722718253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7361111111111112, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7445436507936508, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7581845238095238, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7683531746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7790178571428571, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7884424603174603, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8050595238095238, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8226686507936508, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8410218253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8606150793650794, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8782242063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8965773809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9092261904761905, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9236111111111112, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9362599206349206, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9441964285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9479166666666666, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9513888888888888, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9578373015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9630456349206349, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9769345238095238, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2689597933302908, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.29387222571912497, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3338008408393652, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.3666760446860544, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.40246699666409474, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4370748814826203, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.46329772582091727, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.4905382817240358, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5136742579590456, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5325260893410493, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5433616928502234, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5589447437444601, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5694969578333637, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5915925193363638, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6057106062492928, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6252742711424685, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6406685097593086, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.6720805863783421, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7103411250969351, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7475098950932713, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.7874232719714547, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8242844897390779, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8566325733257807, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.880919016859998, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9047386213004555, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9253965623013701, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9359654009625211, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9407597179735079, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.944312441271686, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9482388275994841, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9512386717652417, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9544637389762782, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9563805175144641, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.958029324131956, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.959318648295556, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9593624403888745, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9621869705405421, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9630436621299077, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9653243502310382, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9667490175800072, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9671973797823806, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9685403413395564, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9696918036176654, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9704203560417781, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9721808404105136, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9736786399523429, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.973774167428676, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9733186709579942, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9723682854098196, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.10053220055997372, "validation/loss_best": 0.11357183009386063, "validation/acc_best": 0.9771825396825397, "validation/f1_best": 0.9736786399523429} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 1.2293697971105575, "train/grad": 0.036299650054425, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.9401708984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.92555908203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.901519775390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.877796630859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.854180908203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.82139404296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.784471435546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.74358642578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.689857177734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.63301513671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.577314453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4940350341796873, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.413642578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.298201904296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.189012451171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.0858578491210937, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9574432373046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.8111758422851563, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.654942626953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.517611541748047, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.3599028015136718, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.2117449951171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.0642031478881835, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.9264948272705078, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.804106330871582, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.6832866668701172, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5949889659881592, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5282326412200927, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.4547016954421997, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.3870796823501587, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.3400854587554932, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.30559908628463744, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.26820278525352476, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.2414667111635208, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.21559003949165345, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.19472698092460633, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.17617498636245726, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.16124619528651238, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.147490251660347, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1330620114132762, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.12354750394821166, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11610119547694922, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10760073993355036, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10113784529268742, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09455844487994909, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08842481879517436, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08384392760694027, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0790648595802486, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.07566665027290582, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008501028607133776, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00847882336936891, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008441350576467811, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008404879907611757, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00836837959010154, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008318217811174691, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008260492370463907, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00819541464559734, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008106674533337355, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00801049250178039, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007914442997425795, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007764183159451932, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007611873252317309, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00738111010286957, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007146340827457607, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006909944666549563, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006597015361767262, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006218644918408245, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005795298893935978, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0054132452979683875, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004968432881869375, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0045458695606794206, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004119118562666699, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003712207443313673, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033409472263883798, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00296346194925718, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0026802441489417106, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0024618428153917195, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0022170383459888397, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00198857732815668, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001827854846487753, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0017087395064299927, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001578691543545574, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0014848100021481515, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001393068094039336, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0013180836255196483, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001250283176486846, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0011946277561946772, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0011419473981368355, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0010848517014528625, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0010458900412777439, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0010141943352937233, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.000976942960114684, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0009473674226319418, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0009163484291639179, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0008859850076260045, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0008631631183379795, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.000838984778674785, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0008218096806376706, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.927443504333496, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9111695289611816, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.884294033050537, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8576717376708984, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8313043117523193, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7947745323181152, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.753648042678833, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.70810604095459, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.6485793590545654, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.5856380462646484, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5242063999176025, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.432718276977539, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.344841480255127, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.2195329666137695, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.101935386657715, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.9919443130493164, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.8565146923065186, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.7042391300201416, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.54434072971344, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.4060144424438477, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.2500728368759155, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.1062270402908325, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.9659557938575745, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.837714433670044, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7258749008178711, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.617245078086853, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5389610528945923, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.4803900718688965, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.41614097356796265, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.35743507742881775, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3167279064655304, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.28694599866867065, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.25460556149482727, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.23154935240745544, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.20922064781188965, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.19120125472545624, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.17542321979999542, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.16286465525627136, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15130740404129028, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13961011171340942, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1319694072008133, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12625934183597565, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11989107728004456, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11533906310796738, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11093058437108994, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10706226527690887, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.10434141755104065, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.10163924843072891, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.0997069850564003, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.44915674603174605, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.482390873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5327380952380952, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5758928571428571, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6063988095238095, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6438492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6743551587301587, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.6976686507936508, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.71875, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7316468253968254, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7410714285714286, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7507440476190477, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7609126984126984, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7748015873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7857142857142857, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7981150793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8117559523809523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8298611111111112, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8524305555555556, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8697916666666666, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8888888888888888, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9032738095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9156746031746031, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9280753968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.939484126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.951140873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9583333333333334, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.964781746031746, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9670138888888888, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.96875, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9764384920634921, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3147643216622991, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.34537048447093416, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3883550315497472, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.42466468351694514, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.44955346665566914, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.48119839444519513, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.504613633960494, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.524006127038164, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5405910247083567, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5549168297486737, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5657018953369852, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5796684985659537, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5967257248991058, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6196102412273656, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6354520162499987, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6594976217729955, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6844489864359199, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7241395627322171, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7732830689091076, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8086268701790428, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8422267514709325, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8704307387436268, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8934071894501168, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.912278215843626, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9300204135183023, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9397913413895128, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9436244592048517, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.945149488912975, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.949038442351907, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9522495100235221, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9561177921234875, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9565039084224946, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9582546538764098, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9591221511599166, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.960947182459656, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9613644495324584, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9635873115406921, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9642586323222242, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9658076623436119, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9668262965713187, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9671947365864755, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9675116669520207, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9705775534615901, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9729303792305227, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9730871466757898, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9738009351423113, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9736566751913391, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9728298585971099, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9723047615612562, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.08842481879517436, "validation/loss_best": 0.10706226527690887, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.9738009351423113} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 1.1448573833703994, "train/grad": 0.03502399267628789, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.9152783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.897275390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.867506103515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.83800048828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.80883056640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.768447265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.723135986328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.67302001953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.60758544921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5386212158203123, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.4714617919921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.371895751953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.2766876220703125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.1418963623046876, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.016504211425781, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.90025146484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.7586337280273439, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.6016500854492188, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.4390939331054688, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.3007360076904297, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.147030029296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.0077759552001953, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.8743144416809082, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.7542362022399902, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.650913610458374, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5518603324890137, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4810138940811157, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.4281806564331055, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3704328942298889, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.31762969493865967, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.2809230661392212, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.2539737695455551, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.22459199905395508, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.20335181921720505, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.18272796839475633, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.16586363434791565, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.15077563911676406, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.13854325957596303, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.12708053670823574, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.11494506306946278, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.10680531181395053, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10048920180648566, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09318383179605007, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0876217820495367, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.08197362495586276, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.07679333372041583, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.07298784922808409, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0691066856868565, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.06637502761557698, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008496009439695626, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008467805981636047, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008422415803652257, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00837710834108293, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008332489165477455, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008269695409107953, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008196773242671042, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008113324190489948, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008002426440361888, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007881512981839478, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007758373692631722, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0075674188323318955, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007373374137096107, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007077834261581302, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006780787019524723, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006488284401129931, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00611309677362442, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005679966893512756, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005221153653692454, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004825780284591019, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0043819840531796215, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003972654064418748, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0035706407518591734, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003199002405162901, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0028700864012353123, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0025467563327401877, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0023103610979160294, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002131403946550563, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0019337176205590368, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001750939516350627, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0016228657978354022, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0015283988509327173, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0014246303954860194, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0013489796113572083, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00127437362622004, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0012123691613669507, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0011557507718680427, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0011086083203554154, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001062944571604021, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0010126367746852338, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.000977567617665045, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.000948822169448249, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0009144786515389569, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0008868991529743653, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.000857659780594986, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.000829232139949454, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0008077858996693977, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0007852832117350772, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0007699335740471724, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9048678874969482, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8853583335876465, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8532042503356934, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.821384906768799, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7899293899536133, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7465150356292725, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6977293491363525, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.6438539028167725, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.573805332183838, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.500087261199951, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.4285855293273926, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.322814464569092, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.222111701965332, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.0805599689483643, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.9499365091323853, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.8295390605926514, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.6845546960830688, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.525555968284607, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.3630776405334473, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2264628410339355, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.0767179727554321, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.9431891441345215, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.8167802095413208, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7047656178474426, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6095325946807861, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5189806222915649, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.4546882212162018, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.4069157838821411, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.35489001870155334, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.3074226677417755, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2744157910346985, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.250300794839859, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.22401462495326996, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2051587849855423, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.18686430156230927, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1720787137746811, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1590198427438736, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.14866593480110168, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13917246460914612, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1294928789138794, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1232401505112648, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11866562813520432, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11364821344614029, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11011435836553574, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.10678531974554062, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10406267642974854, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.10230478644371033, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.10075109452009201, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09992535412311554, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.4947916666666667, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5302579365079365, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5815972222222222, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6135912698412699, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6490575396825397, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.6785714285714286, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7028769841269841, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7202380952380952, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7328869047619048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7418154761904762, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7507440476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7624007936507936, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7738095238095238, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7876984126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8015873015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8147321428571429, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.832093253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8531746031746031, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8722718253968254, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8913690476190477, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9060019841269841, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9164186507936508, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9293154761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9402281746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9471726190476191, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9508928571428571, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9553571428571429, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9650297619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.966765873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.96875, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9747023809523809, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3554252901094447, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.3859696326759727, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4281527487008976, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4557050248763845, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4859940464521816, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.508141359197231, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5291740928935547, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5422920535077358, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5582998798157565, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5665029947073469, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5806197027896364, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5979366128997693, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6168130528613852, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6385300925903766, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6664376700754548, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.692349602653588, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7299707536961995, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7761616139851726, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8142069229214964, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8458763293600727, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8750848831757454, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8940542768983041, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9145308230249443, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9305766565911914, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9391294451812803, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9431343975818545, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9448411789586514, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9488218179094045, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9522974846841705, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9559016656039917, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9572212214727168, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9581524215426724, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9590954401543608, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9609713641214194, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9632933388568016, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9636678064504766, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9639575886743611, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9649292925522278, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9661029367433842, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9661813777679882, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9683065350068335, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9686555584121218, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9712447353705779, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9713023701937444, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9715855885193688, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9722365628977416, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9713458739391789, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.971306005771312, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9709150436331536, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.07679333372041583, "validation/loss_best": 0.10406267642974854, "validation/acc_best": 0.9761904761904762, "validation/f1_best": 0.9722365628977416} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 1.0847972649335862, "train/grad": 0.03401264233514666, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.894595947265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.873426513671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.838582763671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.804312744140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.770306396484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.72343017578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.6708447265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.61298095703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.537740478515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.4588018798828126, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.382281494140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.269832763671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.163232421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.0141311645507813, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.8777108764648438, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.7532269287109374, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.604507598876953, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.4431375122070313, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.2805073547363282, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.145331802368164, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.999155158996582, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.870394287109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.7502448272705078, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6449305820465088, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5562160682678222, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.472438702583313, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4131883382797241, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.36925712585449216, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.32142584800720214, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.27769526958465574, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.2473231989145279, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.22480375766754152, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.20026471883058547, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.18239419281482697, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.16488103285431863, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.15047278255224228, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.13745562352240084, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.12682635389268399, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.11683076549321413, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.10611008662730455, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09886950727552175, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.09322012737393379, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08665807651355863, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0816182678192854, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.07649804558604956, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.07180597698315978, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.06825284751132131, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.06471262679435313, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.06220051854848862, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008471291912719607, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00843868828844279, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008385696685872973, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00833293584175408, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008280137197580188, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008205161965452134, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008118077290710062, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008020214589778333, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007888916162773967, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007743828063830734, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007597172008827329, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007368790085893124, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007136643396224826, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006786397160030901, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006441934353206307, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006111143585294485, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00570128875784576, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005246141348034143, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00478125297697261, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0043904404924251135, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003959913915023208, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00357111988007091, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003198084415635094, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002861752155004069, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0025715462560765446, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002291562291793525, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0020905872603179886, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0019402554142288863, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001774755657534115, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0016221859824145212, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0015153719030786305, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.001435574444476515, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0013474238279741258, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0012824307929258795, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0012174837751081212, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0011626614493434318, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0011119264186709187, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0010691343978396616, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0010273359608254395, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0009807574495789594, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0009476342964626383, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.000920707605255302, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0008881560228473972, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0008622900767659302, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0008346399683796335, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0008088049219804816, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0007888353778980672, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0007687882267055101, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0007550078377244063, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.883939266204834, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.861499547958374, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8244779109954834, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.787903070449829, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.751861095428467, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.702179193496704, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6464853286743164, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.585237979888916, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.5058202743530273, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.4226787090301514, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.3424532413482666, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.224668025970459, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.1137194633483887, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.9595531225204468, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.819458246231079, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.692629098892212, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.5425699949264526, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.381318211555481, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2205702066421509, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.088456392288208, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9474733471870422, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.824406623840332, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7109020948410034, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6124408841133118, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5299279689788818, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.45262396335601807, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.39802640676498413, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.35766488313674927, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.31381404399871826, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.27376335859298706, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.24598410725593567, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2254869043827057, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.20320121943950653, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18715792894363403, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1715826392173767, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.15892450511455536, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.14768192172050476, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13878968358039856, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1306525468826294, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12249182164669037, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11722168326377869, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.11329104006290436, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.10894318670034409, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1058502197265625, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1029241532087326, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.10046321153640747, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09870483726263046, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.0972759872674942, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09648041427135468, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5324900793650794, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5704365079365079, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6106150793650794, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6500496031746031, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6748511904761905, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7008928571428571, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.71875, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7309027777777778, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7408234126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7512400793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7609126984126984, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7720734126984127, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7844742063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7998511904761905, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8147321428571429, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8293650793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8509424603174603, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8697916666666666, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8913690476190477, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9047619047619048, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9159226190476191, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9278273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9389880952380952, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9464285714285714, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9508928571428571, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9528769841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9732142857142857, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9742063492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9759424603174603, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.387837862011276, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.42018376266258156, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.45319536736454036, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.4874983521608711, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5061674198496248, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.527803430068528, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5421457429658835, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.555937867309529, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5654204939729981, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5816320491715468, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5964471166486041, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6137685368757071, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6337728918478633, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6634968935913773, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6946085975332196, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7247795592579952, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7727945859287099, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8099362968041854, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.846474991973819, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8735600209422503, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.894003465528052, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9122721612704092, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9290790268783321, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9384317471256187, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9434561805702097, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9460432556699785, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9488239468876342, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9525118928619075, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.95502343159303, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9562930928366422, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.958050304565773, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9594717219508906, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9604736787458396, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.961803288679397, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9640467274168179, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9650740799125908, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9656054598751964, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9667558570493489, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9681223104809439, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9688473350495551, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.970016975979726, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9705715607542913, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9711385054567794, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9700170039588409, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9715001066484235, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9722587896307398, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9722472701365332, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9718632229106238, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.971970430907904, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.07180597698315978, "validation/loss_best": 0.10046321153640747, "validation/acc_best": 0.9761904761904762, "validation/f1_best": 0.9722587896307398} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 1.0340972673892974, "train/grad": 0.03298655077815056, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.873602294921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.849698486328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.810245361328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.77129150390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7329931640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.680206298828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.621138916015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.55611328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.4721990966796876, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.3843182373046874, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.2998248291015626, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.1761962890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.0602490234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.8999899291992188, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.7556146240234376, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.6259121704101562, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.4734573364257812, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.3114778900146484, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.151583366394043, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.0217614364624024, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.884432601928711, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.766182861328125, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6580795574188233, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5650000524520874, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.48761563777923583, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.41517921924591067, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.36421454668045045, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.32650325059890745, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2854103434085846, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.24781871378421783, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.22159529626369476, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.20209676265716553, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1806994479894638, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.16504049092531203, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.14964963346719742, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1368457602709532, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.12519583772867918, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.11562405571341515, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.10654444895684718, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.09677478190511465, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09019434796646238, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.08499088874086738, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07899147933349013, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.07437477055937051, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06972732983529567, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06545110560953617, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.06235107065178454, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.059243413899093864, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.057065764013677835, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008411632056813688, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008375100044067949, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008314494187943637, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008254504930227995, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008193018820602447, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008106022882275283, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008006383744068445, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007893684492446483, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0077409504330717025, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007573430268093944, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0074035921995528045, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.007138730350416154, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006870556233916431, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006473019593395293, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006091628612484783, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005735876408871263, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005308718055021018, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004849211971741169, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004390619618352503, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00401228952105157, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003602276189485565, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0032394040958024562, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0028976576204877346, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002595514438580722, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00233923046849668, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002094754410791211, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0019208482769317926, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0017912319977767765, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001648646030225791, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0015176218538545073, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0014249913609819488, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0013557260832749308, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0012782032493851147, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0012201883443049156, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0011616301708272658, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00111126020521624, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0010638503418886102, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0010234897132613697, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0009832242954871616, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0009376908418198582, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.000905167215532856, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0008785306390200276, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0008464151190128177, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00082071181765059, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0007935508144146297, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0007677626592339948, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0007483450188010465, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0007289058261085302, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0007155341672478244, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8649773597717285, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8398663997650146, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.798496961593628, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7577266693115234, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7175776958465576, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6623120307922363, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6005136966705322, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.5327866077423096, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.4453301429748535, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.354135274887085, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.2666144371032715, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.13903546333313, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.019786834716797, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.8561805486679077, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.7097896337509155, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.5791594982147217, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.426629662513733, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2660390138626099, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.108963131904602, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.9823693633079529, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8498924970626831, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7365862727165222, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6339904069900513, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5461336374282837, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.4734078645706177, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.4056549668312073, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.35803359746932983, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3229128122329712, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.284720242023468, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.24988335371017456, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2255268096923828, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2076408714056015, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.18808604776859283, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.17398032546043396, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1602780818939209, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14909611642360687, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.13921546936035156, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13130220770835876, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12418333441019058, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11691883206367493, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11236528307199478, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10887795686721802, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1051231324672699, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.10241153836250305, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09991484135389328, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0977858304977417, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09630896896123886, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09507371485233307, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09448011219501495, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5657242063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.597718253968254, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6408730158730159, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6703869047619048, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6919642857142857, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.714781746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7286706349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7390873015873016, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7477678571428571, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7606646825396826, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.767609126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7814980158730159, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.792906746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8097718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8266369047619048, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8449900793650794, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8655753968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8856646825396826, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9012896825396826, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9126984126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9265873015873016, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9362599206349206, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9459325396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9506448412698413, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9528769841269841, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9650297619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9771825396825397, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4156676776492562, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4425312525987722, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4777037828554955, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5010605542748268, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5198054906753315, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5376737484290429, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5531818353608454, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5647473227664589, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5752913986181063, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5957160165286184, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6057078509961548, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.628861229185292, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6517718746885148, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6820794908358507, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7201447259782933, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7598377696758856, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8017550736177864, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.839296234965414, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8660816030519614, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.886708964415798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9100237829209513, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.924726077145139, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.937371145238528, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9434113637884968, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9461441648607072, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9507088403962245, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9537793320316216, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9552026371256601, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9573051280621618, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.959029941327071, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.961357343495587, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9617227086805452, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9624135656856391, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9639020347232652, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9638743039479575, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9654719672355057, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9662880083899521, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.96661889706668, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9676532622144629, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.969672989955926, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9712007890304196, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9721586269980713, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.972701855158222, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9729627687757688, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9731361242895845, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9745178769273056, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9753798237842884, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9745611903325165, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9741603384714091, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.06235107065178454, "validation/loss_best": 0.09630896896123886, "validation/acc_best": 0.9784226190476191, "validation/f1_best": 0.9753798237842884} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.9963653862476349, "train/grad": 0.032218590294942256, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.85671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.83027099609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.78676025390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.7439453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.701732177734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.643704833984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.579024658203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.5081268310546876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.4166845703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.32164306640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.2305328369140627, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.098260498046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.9752230834960938, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.8072415161132813, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.6579417419433593, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.5255764770507811, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.3722079467773438, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.2118683624267579, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.056518669128418, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.9325529479980469, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.803718318939209, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6945235633850098, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5961808395385743, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5122904300689697, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.443080358505249, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3785560727119446, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.33323933362960817, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.29976525068283083, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2631480622291565, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2295531713962555, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.20592847645282744, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.18834345936775207, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.16887427106499672, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.1545296311378479, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.14033176697790622, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1285359053313732, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1176806540414691, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.10871849358081817, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1002310724183917, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.09107754463329912, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08491309765726328, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.08006737979128957, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07445244755595923, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0702184678055346, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0658917224407196, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.06198146877810359, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05909619925543666, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.056217215955257416, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.05422458922490478, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008386136500630527, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008345204798970371, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008277682506013661, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008209608697798102, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008139920991379768, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008041852600872517, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007930390851106495, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007802365007810294, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007629334351513535, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007439727825112641, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007246623474638909, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00694602157222107, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006645548697561026, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006207671551965177, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0057980544492602345, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005426308088935912, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004990870882757008, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0045320190000347794, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004081991408020258, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0037159090721979736, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0033256099850405008, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0029859738040249797, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0026720450748689475, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002398454057984054, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002168755555758253, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0019516671425662934, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0017978810804197564, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0016832099977182225, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001557038176106289, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0014399497426347808, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001357020317518618, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0012941221636720002, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0012234861915931105, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0011697718262439593, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0011150339673622512, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001068113200890366, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0010230495341238565, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0009837026754394174, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0009447204464231618, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0008999121221131645, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0008676152020052541, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0008409079063858372, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0008086625693249516, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0007830332439334597, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0007561394450021908, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0007310272287577391, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0007122486145817675, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.000694151070638327, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006823052474646829, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.848262071609497, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.820812702178955, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7756853103637695, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.731184959411621, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.687473773956299, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6274094581604004, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.560454845428467, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.4871675968170166, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.392782211303711, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.2948625087738037, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.2013466358184814, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0658681392669678, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.94033682346344, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.7700139284133911, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.61929452419281, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.4864153861999512, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.3335267305374146, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1748408079147339, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.0222254991531372, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.9012885689735413, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7764692306518555, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6714628338813782, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5774881839752197, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4978320896625519, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.43236881494522095, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.371599018573761, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3291073441505432, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2977368235588074, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.263568639755249, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.23243212699890137, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2106771171092987, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.19460110366344452, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.17703156173229218, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.16428932547569275, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.15187643468379974, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.14180772006511688, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.13283486664295197, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1257709413766861, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11933641880750656, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11287156492471695, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10877390950918198, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10572869330644608, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.10263756662607193, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1003727987408638, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09828151762485504, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0967194065451622, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.0956932008266449, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.0950077474117279, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09460809826850891, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5882936507936508, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6135912698412699, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6589781746031746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6872519841269841, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7078373015873016, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.722718253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.734375, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7428075396825397, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7547123015873016, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7643849206349206, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7740575396825397, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7869543650793651, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.800843253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8206845238095238, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8390376984126984, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8576388888888888, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8759920634920635, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8955853174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9094742063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9196428571428571, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9325396825396826, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9429563492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9486607142857143, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9513888888888888, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9546130952380952, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9578373015873016, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.96875, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9744543650793651, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.43546099402044736, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.45557158844934587, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.49200412411132405, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5155571914355652, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5326835088981591, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5451206867716845, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5592522773848498, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.566981390741343, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5852230733761455, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6003671874529789, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6186796123767516, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6387339792966863, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6659942319803346, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7082026230158844, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7466936024655902, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7852118615132776, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8233925747359145, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8547457357195933, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8814914766462452, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.898783359184436, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9190073473524224, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9335902144427176, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9409138707483644, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9444412339773068, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9482584577471359, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9519470615594118, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.954993366309945, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9571083159086848, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9581394673769579, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9592422256875767, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9617573458839688, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9634720264161485, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9637546336666932, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9641647939919742, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9656816233748982, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9658280161143163, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9668531901230163, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9681798461607911, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9689109837732249, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9698664003706481, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.971705769577191, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9716562041512308, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9726286119310281, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.972422250896518, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9731778171272988, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9730137958880801, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9726554283549094, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9723045504479935, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9716193794747987, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 0.07445244755595923, "validation/loss_best": 0.10263756662607193, "validation/acc_best": 0.9761904761904762, "validation/f1_best": 0.9726286119310281} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.9640243878960609, "train/grad": 0.031704715238884094, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.840281982421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.811529541015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.76440185546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.71805419921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.672510986328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.6099951171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.5402532958984376, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.4641143798828127, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.366168212890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.264600830078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.1679327392578127, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.028255615234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.899281005859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.725140380859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.5721409606933594, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.4380926513671874, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.2847016906738282, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.1266301727294923, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.9758737564086915, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8574480628967285, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.7361108779907226, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6346972465515137, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5443619060516357, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4680836343765259, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.4056140208244324, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.34773405313491823, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.30715988397598265, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2772201597690582, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.24452946543693543, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.21450401484966278, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.19333670020103455, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.17755059763789177, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.16000665321946145, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.14703554898500443, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.13410741373896598, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.12321554485708475, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.11324724182486534, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.10492400186136365, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09697433829307556, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08835403479635716, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.08248051561415196, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07784628735855222, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07248881403356791, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06838090476579964, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06424658821895718, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.060454541854560374, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05759463148191571, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.05476952339522541, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.05275940335355699, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008383765865582973, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008339567556977272, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008266294579952956, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008191066631115972, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008114951164461672, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008008718185592442, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007885856924112887, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007745304491836577, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007555294695775956, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007345663728192449, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.007132748852018267, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006802426364738494, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00647540605161339, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006007340797223151, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005579850689973682, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005198747951071709, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004759718489367515, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004303647322813049, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038608923822175713, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003504539196146652, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0031299437046982347, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0028079322958365085, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002514519800897688, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0022619940497679634, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002051840726053342, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018550680147018284, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0017159264377551154, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0016122699371771887, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0014983039966318756, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001391896950372029, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0013158134496188722, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0012578123397543094, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001191705091332551, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0011416107285185718, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00108991312852595, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.001044630687974859, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.001001471962663345, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0009636777777632233, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0009260129474569112, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0008824704999278765, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0008514371325145475, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0008256938021804672, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0007945622122497298, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0007699379335099365, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0007440950501768384, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0007196375205239747, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0007004058270831592, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006809264949697535, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000666869134947774, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8339521884918213, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8045475482940674, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7561120986938477, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.708547830581665, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.661785840988159, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.597628116607666, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.5262463092803955, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.4483535289764404, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.348358392715454, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.244932174682617, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.1465766429901123, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0048725605010986, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.8745923042297363, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.6991959810256958, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.5460530519485474, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.412062406539917, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2597235441207886, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1034773588180542, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9550687074661255, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.8391898274421692, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7210313677787781, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6228523254394531, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5356143712997437, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4622778594493866, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.40214022994041443, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.34669068455696106, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3079286813735962, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2793421447277069, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.24812613427639008, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.2196359932422638, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.199695885181427, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.18495388329029083, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16878889501094818, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.15708081424236298, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1456792652606964, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.13640421628952026, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12826816737651825, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.12166909128427505, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1158001646399498, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10989517718553543, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10618814826011658, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10347961634397507, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.10056829452514648, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09864279627799988, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09676443040370941, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.095256008207798, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09424768388271332, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09331545978784561, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09274307638406754, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6019345238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6344246031746031, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6706349206349206, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6964285714285714, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7145337301587301, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7274305555555556, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.738343253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7470238095238095, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7601686507936508, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7693452380952381, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7795138888888888, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7926587301587301, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8065476190476191, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8273809523809523, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8497023809523809, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8663194444444444, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8864087301587301, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9010416666666666, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9144345238095238, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9263392857142857, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9377480158730159, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9459325396825397, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9503968253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9523809523809523, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9553571428571429, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9595734126984127, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9620535714285714, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9630456349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9637896825396826, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9742063492063492, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.44537480144588837, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.47212940800111125, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5013675077353922, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5221602720953618, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5364946452263677, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5503697222634836, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5622866677087792, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5733864842829696, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5952229316404535, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6085664897606571, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6265062931142138, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.651002180639121, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6766627595283947, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7220170625853614, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7707143872364925, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8034687347264191, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8403509871675384, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8652651339678814, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8913202480292094, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.909882776423056, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9270484483536792, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9374695050414937, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9430618570730277, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.945470653233775, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9486189189973999, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9537732826143943, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9559281767894043, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9570218835876722, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.957864302398247, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.960686674755011, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.961936225685521, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9635727623922512, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.96360422507594, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9644859279278846, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9658860210601079, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9668139634365618, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.967989763368333, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9689291293594634, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9702319429471651, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9724802842119348, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.972839400416939, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9731737506957882, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.974160208660624, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9730341117143269, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9728258072721303, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9727918069187154, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9722065527496458, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9711892870029124, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9711904137937566, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 0.07248881403356791, "validation/loss_best": 0.10056829452514648, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.974160208660624} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.9421660149097443, "train/grad": 0.031120880423113704, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.828631591796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.798363037109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.748546142578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.699615478515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.65147216796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.585562744140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.512310791015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.432301025390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.3298284912109377, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.2239874267578124, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.1233935546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.9788775634765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.846328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.6686416625976563, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.513995361328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.3794548034667968, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.2268553924560548, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.0712609100341797, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.9244639205932618, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8103262519836426, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6946606159210205, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5988796043395996, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5139125442504883, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.44260173082351684, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.38433189630508424, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.33035882472991945, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.29247828722000124, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2645224153995514, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2338957178592682, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.20562269985675813, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.18563608199357987, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.17067095428705215, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.15391040325164795, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.14153861247003077, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1291083312779665, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11871306374669074, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1089971861988306, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.10095871493220329, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09320957673713565, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08480672079138457, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07909407997503877, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07460670687258243, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06933865999802948, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06527807871811092, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0612189590651542, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.05742481111548841, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.054674006290733816, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.05179649651050568, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04967369263060391, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008339529149234295, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0082927125855349, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008213394419290126, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008132387055084109, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008051231584977359, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007937569532077759, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00780468086944893, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007653698669746518, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007449612994678318, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007224211893044412, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006995537008624524, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006642990671098232, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006298025846481323, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005810710384976119, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005374090338591486, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0049901265394873915, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004551745082717389, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0040997040178626775, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0036648656998295335, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0033183460927102715, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002958197247935459, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0026527998119127007, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0023767708224477248, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002141222762875259, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0019467454217374325, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0017653375875670463, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0016370040026959032, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001541886161430739, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0014367707871133463, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0013389151799492538, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001268336336943321, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0012145298370160162, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0011528841013205239, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0011059220158495008, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001056903207791038, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0010141672860481776, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009723845127155073, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0009363048517843708, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008993124177504797, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0008572255517356098, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0008267239537963178, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0008018596276815515, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0007716272371180821, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0007479068703833036, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0007232628505153116, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0007000941451406106, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0006830949897994287, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006655000800674316, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006519199634931283, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.82214093208313, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.791034460067749, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.740016222000122, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6898536682128906, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6406140327453613, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5732147693634033, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4982757568359375, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.416640281677246, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.312098264694214, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.204303741455078, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.102079391479492, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.9557539224624634, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.8218029737472534, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.643053650856018, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.488075852394104, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.353886604309082, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2022466659545898, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.048416256904602, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9040553569793701, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7923985719680786, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6796015501022339, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.586596667766571, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5046289563179016, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.43596890568733215, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3799843490123749, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3282887935638428, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.292224645614624, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.26564645767211914, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.23661112785339355, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.21005848050117493, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.191554456949234, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.17774443328380585, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.16263322532176971, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.15168534219264984, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.14096108078956604, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.13227002322673798, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12452490627765656, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1185128465294838, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11306190490722656, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10753053426742554, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10410956293344498, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10158996284008026, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09893117845058441, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09696117043495178, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09529384970664978, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.09385738521814346, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.0928260087966919, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09192800521850586, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09132070094347, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6121031746031746, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6475694444444444, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6822916666666666, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7058531746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7194940476190477, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7318948412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7408234126984127, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7504960317460317, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7628968253968254, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7723214285714286, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7834821428571429, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7996031746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8134920634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8350694444444444, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8561507936507936, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8717757936507936, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8923611111111112, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9069940476190477, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9186507936507936, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9290674603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9412202380952381, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9481646825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.951140873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9533730158730159, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9610615079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9627976190476191, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.964781746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9774305555555556, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4542922056409925, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4852178797264883, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5117296361445222, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5298200197979008, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5412235984361347, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5551465495770825, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5651887311080951, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5798009080364082, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5978130658002615, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6154586395566846, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6328661000456404, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6630880277259975, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6926632518626148, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.740371534622159, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7832880664542978, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8149253126681779, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8497114320707643, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8779996198823599, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.898232313091689, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9146653840983946, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9321826463768013, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.940624379076501, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9437370459958371, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9464410310170508, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9509319647702326, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.954853473079608, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9564967160018967, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9568645469818448, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.958930378382574, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9611757298012723, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9634154708730271, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9627014607221395, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9630598335019562, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9654576072595646, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9662068632349801, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9666377552232932, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.967625077859148, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9687100115038701, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9716951938002031, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9731029639832955, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9733758328408555, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9733768163168697, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9737712631983412, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9743300636271582, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9746954891182193, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9739869390046338, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9737057873866414, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9737057873866414, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9743343246471251, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0612189590651542, "validation/loss_best": 0.09529384970664978, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.9746954891182193} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.9198577666282653, "train/grad": 0.030873216483742, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.816295166015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.78442138671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.73205078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.680548095703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.62988037109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5607611083984376, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.483902587890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.4002313232421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.293216552734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.18305419921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.0788421630859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.9297238159179688, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.7938275146484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.6129721069335938, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.4568722534179688, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.3221662902832032, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.1706593322753907, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.0175323486328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8746118927001953, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7645795249938965, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6539537620544433, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5630115222930908, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.482993950843811, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4161798071861267, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3616130304336548, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3112945294380188, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.27607054948806764, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.24993825495243072, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2214465880393982, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.19504889219999313, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.17633980512619019, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.16226943463087082, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.14654117308557033, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13490901567041874, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.12313778102397918, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1132042045891285, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10398898500949144, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09627064513042569, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0888635153695941, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.08070355217903852, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07513072182424367, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07068796616978944, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06552044338546693, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06150968462228775, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05744252239353955, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.053734885789453984, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.05091389901936054, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.04809569926001132, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.046067796368151906, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008353204089216889, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008303567639086396, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008219742765650153, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008133334727026521, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008047570185735821, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007926402608864009, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007785415237303823, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007624599505215883, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007407377089839429, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007166659708600491, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006923662580084056, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006551151447929442, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006190175460651517, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005687429690733552, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0052438310720026495, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004858174677938223, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004421961582265794, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003975229115458206, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0035491291037760674, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003212728362996131, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0028658924216870218, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0025743907096330075, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0023129913897719234, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.002090757232508622, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0019073365710210056, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0017358707985840737, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0016147498961072415, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0015238786721602081, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0014235669834306464, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0013288768651545978, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0012599340410088188, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0012069614793290384, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0011460551162599587, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0010989534389227629, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0010498654964612797, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0010064783561392688, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009643556889204774, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0009272266103653237, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008899482013657689, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0008465676763444208, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0008149469565250911, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.000789225489133969, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0007575134426588192, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0007318452336767222, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0007053165194520261, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0006800003640819341, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.000660504040424712, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006406071328819963, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006267195930558955, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.812798023223877, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.780418634414673, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.727290630340576, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6751339435577393, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6239888668060303, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.553947687149048, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4762368202209473, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.391716957092285, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.283648729324341, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.1725220680236816, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.067439079284668, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.9174821376800537, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7810958623886108, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5998486280441284, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.4439133405685425, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.3096834421157837, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.1589537858963013, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.007218599319458, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.866051435470581, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.757716715335846, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.649030864238739, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5599526166915894, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4817896783351898, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4166863262653351, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.36365994811058044, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3148057758808136, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.28064262866973877, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2555820047855377, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.22807656228542328, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.20299309492111206, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.18542328476905823, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.17231513559818268, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1580127626657486, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.14752300083637238, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1374032348394394, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.12913697957992554, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12186367064714432, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11606749147176743, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11084260046482086, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10565900802612305, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10240175575017929, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1000417098402977, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.0975605770945549, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09580633044242859, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.0942092016339302, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.09287606924772263, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09196589887142181, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09121187776327133, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09061036258935928, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6240079365079365, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6550099206349206, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6867559523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7115575396825397, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7232142857142857, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7338789682539683, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7435515873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7532242063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7648809523809523, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7767857142857143, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.785218253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8023313492063492, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8179563492063492, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8402777777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8611111111111112, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8767361111111112, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8960813492063492, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9092261904761905, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9228670634920635, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9322916666666666, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9434523809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.949156746031746, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9516369047619048, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9538690476190477, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9580853174603174, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9670138888888888, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.96875, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9759424603174603, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4633252274020319, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4889223004937671, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5141137045820631, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5333938185308041, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5451307951801199, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5578162906122658, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.567930008106936, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.583699886344635, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6011610910425258, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6240897793533958, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6354948826563748, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6680463831732363, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7034310829381472, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7495365911902114, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7935052297743008, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8239111345141678, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8566349773437268, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8816241848313459, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9047215328248687, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9198400738722798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9347749794129966, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9418405400867061, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9443802375207316, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9466021932339094, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9518148195388136, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9552299498275997, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9565939971290557, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.957244554280615, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9585208200036641, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9617563152375583, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9635649602303424, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9633254935821478, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9654133237636978, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9658007702851938, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9668163662866588, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9682074906416951, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9691698110102632, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9706015592363276, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9722363115475045, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9721598240554115, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9739671376617585, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.973778533293577, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.973885775065247, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9740871737120012, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9742677931257636, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9738778209950903, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9729266987442092, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9719482663711745, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9725830883300152, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 0.07513072182424367, "validation/loss_best": 0.10240175575017929, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.9739671376617585} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.9055513831973075, "train/grad": 0.030549104074016214, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.808770751953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.775670166015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.72135498046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.668072509765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.615810546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5442938232421874, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4650738525390623, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.378819580078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2687493896484376, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1555523681640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.048807373046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8965933227539062, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.758367919921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.5752989196777343, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.4183013916015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.2835700988769532, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.1328318786621094, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.981683235168457, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8416900634765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7346768760681153, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6276560115814209, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5402449226379394, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.46356107234954835, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.39966544866561887, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3477114307880402, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2997209763526916, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.26613854110240937, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.241316619515419, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.21408138871192933, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.18886930838227273, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.1709641008079052, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15749489165842534, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.14239520378410817, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.13112890623509885, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.11980390626937151, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11020116411149501, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.10124759316444397, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09377547543495894, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08655868362635374, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07864039113745093, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07327310942113399, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0689542505517602, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06393486177548766, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06008581794798374, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.056139046596363186, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.052493397872895003, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04980008214712143, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.04706710129976273, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.045106116058304904, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008322372583206743, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008270832665730268, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008183247130364179, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008094363063573837, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008005769527517258, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007880776999518274, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007734477715566754, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007568398118019104, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0073431907664053145, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00709433572832495, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0068435569270513955, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006460965219885111, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006092909341678023, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0055848896061070265, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0051402677898295225, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004756050240248441, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004322183467447758, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003879164890386164, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0034578001778572797, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003126279693096876, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002785700202221051, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0025004594179335983, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0022452857479220256, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0020290932263014837, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018516646843636409, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0016861293360125275, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015692851744825021, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0014823791699018329, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013861952733714134, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012953301714151166, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0012297703663352877, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011787422207999044, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001120184671599418, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0010750083037419245, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0010274650491192007, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0009849280107300728, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009436179001932033, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.000907048391236458, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008698774980439339, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0008268138259882107, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007956083233875688, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0007693816501705441, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0007380089814250823, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0007127053810108919, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0006854843557812274, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0006593374216754455, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0006392923768726177, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006184349539398681, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006031834565510507, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8058505058288574, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.772465467453003, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.717815637588501, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.664135217666626, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6115262508392334, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5396361351013184, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4598426818847656, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.373103618621826, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.262467384338379, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.148963451385498, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.041860342025757, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8892626762390137, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7510454654693604, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.568131685256958, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.4115405082702637, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2773033380508423, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.1273969411849976, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9773308634757996, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8385610580444336, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7327048778533936, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6270638704299927, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5408536195755005, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.46558159589767456, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.40282395482063293, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.351922869682312, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3050732910633087, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.27237316966056824, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2482590228319168, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.22199194133281708, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19787289202213287, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1809925138950348, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.1684289425611496, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.15468910336494446, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1446554809808731, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.13501612842082977, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.127054363489151, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12002500146627426, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11452583223581314, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10956545174121857, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10459332168102264, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10160528123378754, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09933392703533173, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.0969543606042862, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09543411433696747, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09386841207742691, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0926002711057663, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.0918617844581604, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09102082997560501, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.09046352654695511, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6324404761904762, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6609623015873016, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6924603174603174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7142857142857143, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7251984126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.736359126984127, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7450396825396826, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7564484126984127, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7653769841269841, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7787698412698413, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7881944444444444, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8048115079365079, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8199404761904762, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8435019841269841, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8653273809523809, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8814484126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8975694444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9109623015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9250992063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9357638888888888, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9441964285714286, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9501488095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9518849206349206, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.955109126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9588293650793651, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9630456349206349, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9637896825396826, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.964781746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9749503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.47002980531180977, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4923492490709396, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5198640192469283, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5360646281854538, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5470113569197458, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5591999031458061, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5697361781333304, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5895489832761976, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6014635521990905, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6258282561244158, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6410611967247452, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6723003267941743, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7071541591839635, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7564735333351232, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.802009883832165, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8307164594909265, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8592481112463091, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8854530885265449, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9085436326823904, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9247335494572023, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9353471585009181, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9429691135046173, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9447595621222298, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9481128894778401, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9527013972379211, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9562209440043861, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9569323152038607, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9578141659787088, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9592490907504224, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9625312305220428, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9633170029021259, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9629343743628499, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9650496970365985, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9664243549435686, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9668139634365618, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9674449270838569, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9691570892327872, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9705739205545663, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9725079019723705, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9732721177596265, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9735917728621514, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9741354213971476, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.973837788912787, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9745745993934033, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9736807029731649, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9723739297537177, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9721427637615621, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9715133765100074, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9707793388405148, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 0.0689542505517602, "validation/loss_best": 0.09933392703533173, "validation/acc_best": 0.9776785714285714, "validation/f1_best": 0.9741354213971476} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.8963180416822434, "train/grad": 0.030310852527618407, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.804771728515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.77129150390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.71607421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.661983642578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.608905029296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5364886474609376, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4560888671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.36857177734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2571636962890627, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1425830078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.034598693847656, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8809323120117187, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.7414785766601562, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.5572442626953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.3994373321533202, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.264295654296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.1134763336181641, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9626631546020508, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8235867881774902, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7176556301116943, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6121720504760743, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5262588357925415, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4510943365097046, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3886387300491333, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.33785861372947695, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.291036012172699, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.25823206305503843, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.23391305327415465, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.20722117096185685, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.18246175229549408, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16480893209576608, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15154334142804146, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.13663965545594692, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.1254815848916769, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1142244440689683, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.10465012107044458, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0957853827625513, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.08835012944415212, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08116490010172128, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07340315056964755, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0680549681186676, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06386643077246845, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.059017020594328645, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05527674870565533, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05151504273526371, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.04807206935249269, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04553066812455654, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.04294660515151918, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.041075941454619166, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00830658125691116, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00825412777485326, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008163941737730057, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00807257356122136, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007981575794983655, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0078527092654258, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007702666795812547, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007531700397375971, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0072996275126934055, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007043414865620434, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006785507970489562, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006393534417729825, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006017844642046839, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005504192041698843, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005056726483162493, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0046714503807015716, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00423805957660079, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0037969682400580494, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00337985651451163, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003053558630635962, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0027203086100053044, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00244253164390102, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002194858200382441, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019854956190101802, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0018128095217980445, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0016511775652179495, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015372618468245491, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0014514371159020812, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013561914468300529, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012662270627333784, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0012005665432661772, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011500133530353196, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001091502901399508, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001046180226840079, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.000998408814193681, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.000956203095120145, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.000914867644169135, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0008780715045577381, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008408663103182335, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0007975325977895408, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007659384592261631, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0007399341424752493, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0007082999742851825, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0006827048037666828, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0006560688307217788, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0006302255432819948, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0006105942004069221, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005898636308120331, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0005745673056662781, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.800973892211914, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.766969680786133, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7111778259277344, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.656520366668701, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6028904914855957, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5296413898468018, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.448425769805908, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.3602545261383057, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.247847557067871, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.1325273513793945, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.024104356765747, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8698220252990723, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7302945852279663, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5463474988937378, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3892676830291748, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2551647424697876, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.1057565212249756, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.956975519657135, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8198733925819397, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7156214118003845, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.612173318862915, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5279366374015808, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.45445653796195984, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3934325575828552, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3439732491970062, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2985113859176636, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2666388154029846, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.24327319860458374, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.21777263283729553, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19428622722625732, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.17788653075695038, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.16572755575180054, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.15228262543678284, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.14263442158699036, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.13308870792388916, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.12533941864967346, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11853445321321487, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11317718029022217, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10834944993257523, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10357023030519485, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10057689994573593, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09843116998672485, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09608697146177292, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09448300302028656, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09302300214767456, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.09178364276885986, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09095502644777298, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09009549766778946, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.08946218341588974, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6393849206349206, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6641865079365079, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6966765873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7155257936507936, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7269345238095238, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7373511904761905, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7457837301587301, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7576884920634921, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7666170634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7805059523809523, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7901785714285714, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8067956349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8226686507936508, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8469742063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8665674603174603, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8841765873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8993055555555556, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9117063492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9265873015873016, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9367559523809523, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9449404761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9501488095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9528769841269841, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.96875, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.96875, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.972718253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9759424603174603, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4764357863361365, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4952122265902537, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5223034256308823, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5371204731693927, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5491304513230981, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5603578309230669, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5710695718937876, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5916358016911488, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.604640988925942, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6271332557684574, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6476076610532493, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6760843723522212, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7119924653020212, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7645571189895851, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8043085492117276, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8357460952293804, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8627170568963947, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.887017059528966, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9104085721876265, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9255690657586247, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9363731632875353, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9429691135046173, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9458455077369531, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9495877037903954, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9538796919135254, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9563958611672939, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9572066126908956, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9583565476841791, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9604657339639123, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9628929899639164, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9635569006481559, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9634870378549264, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9648741685380215, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9666019041815572, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9670453878323871, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9674276697964663, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.969273348286285, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9709218324646223, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9731350690850645, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9731697335503026, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9737788504670235, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9741085409838584, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9742803917512937, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9746696343599575, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9737298684813254, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9736843616848037, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9731135345862608, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9729326952033691, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9727546249581364, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.05527674870565533, "validation/loss_best": 0.09448300302028656, "validation/acc_best": 0.9776785714285714, "validation/f1_best": 0.9746696343599575} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.8907363051176072, "train/grad": 0.030229482473805545, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.80067138671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.766571044921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7104541015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.655419921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.60158447265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5277923583984374, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.446151123046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.3573809814453126, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2442694091796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1282989501953127, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.01908203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8637850952148438, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.7236203002929686, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.5387518310546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.381021499633789, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.2463874053955077, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0965905380249024, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9473188400268555, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8100829887390136, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7058094215393066, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6022640705108643, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.518064579963684, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.444567654132843, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3835076570510864, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3339064109325409, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.28812991857528686, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.2560801714658737, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2323296296596527, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.20631372421979904, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1820798000693321, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16483381763100624, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15181228421628476, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1371644039452076, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.126173399053514, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.11510055363178254, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.10566979171708227, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.09690280323848129, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.08950096790678799, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.08240316136740149, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07460809404961764, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06929676365107298, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06504945303313434, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06015318041667342, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05631231201812625, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.052498841974884275, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.04891085399314761, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.046274330886080864, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.04354250667616725, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04158496647141874, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008315892301034182, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00826212388696149, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008170149512588978, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008077333765104413, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007984865105245263, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007852836898528039, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00769945117412135, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007524821986444294, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007287013062741607, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007024300883058459, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006759861069731414, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006358800253365189, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005975826398935169, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005454864539206028, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0050039151310920715, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0046175779635086655, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004183766266796738, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003743516057729721, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003328282185830176, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003004442601231858, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0026750697463285176, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.002401723931543529, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0021595175098627806, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001956013139570132, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017891608126228676, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0016342998383333906, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015252094285096974, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001443554668512661, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013531910092569887, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012673195189563558, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0012046009209007024, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011561218276619912, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0010995901603018865, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0010554416768718512, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0010089163755765186, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0009672178965411149, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009260391069983597, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0008894766126468312, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008519059141690377, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0008080460519704502, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007763062465528491, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0007495316298445686, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0007172840156999882, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0006904964517161716, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0006625170626648469, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0006353410104202339, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.000614243480595178, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005918733154248912, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0005753694318264024, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7979376316070557, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7635507583618164, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7071022987365723, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.651759624481201, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.59749698638916, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.523428201675415, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4413580894470215, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.352268934249878, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.23865008354187, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.12237548828125, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.012979030609131, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8576550483703613, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7172982692718506, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5326696634292603, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.375484585762024, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2413616180419922, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.092332124710083, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9441637992858887, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8081861734390259, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7050608396530151, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6027398109436035, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5198370218276978, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4474887251853943, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.38754281401634216, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.33900362253189087, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2943221926689148, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.26315563917160034, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.24013730883598328, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.2150854915380478, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1921837329864502, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1759970784187317, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.16398219764232635, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1508636325597763, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.14130337536334991, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.13193649053573608, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.12439482659101486, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11768819391727448, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11240607500076294, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10772508382797241, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1029815599322319, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10002211481332779, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.0979718416929245, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09563814103603363, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09404924511909485, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09261544793844223, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.09136448055505753, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09052667021751404, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.08961275219917297, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.08903654664754868, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6413690476190477, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6651785714285714, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6974206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7172619047619048, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7276785714285714, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.738343253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.746031746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7594246031746031, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.767609126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7797619047619048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7909226190476191, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8072916666666666, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8234126984126984, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8499503968253969, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8680555555555556, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8864087301587301, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9000496031746031, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9139384920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9270833333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9377480158730159, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9469246031746031, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9503968253968254, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.953125, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9556051587301587, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9595734126984127, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9627976190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9774305555555556, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.47848495472275393, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.49625209362666967, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.522936095031799, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5381012246574417, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5496075161907736, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5622128915413829, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5725774942251235, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5944866965040345, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6073605153206602, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6266443871575087, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6488334673257525, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6778919223126558, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7146808721956115, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7712657633699853, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8068381036476466, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8398052212886313, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8642373849056232, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8912606449786109, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9114081029386728, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9271287836147417, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9390927167628897, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9429892729269637, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9460177532923478, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9490261875213017, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9537636179162619, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9567709641309738, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9572066126908956, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9585311442361327, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9608582998362054, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9631667954935287, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9632029319431584, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9638282463177645, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9654150608995806, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9664269134216669, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9670438974739155, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.968049464666835, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9687592027604058, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9718226762740683, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9733089874360425, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.972921341004872, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9739109663047585, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9746419265319091, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9746984721544736, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9742664945156223, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9740886799392198, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9735145649813859, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9736923548890686, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9740497261319143, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9743189234152337, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 0.06504945303313434, "validation/loss_best": 0.0979718416929245, "validation/acc_best": 0.9779265873015873, "validation/f1_best": 0.9746419265319091} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.8869506576657296, "train/grad": 0.03008883900940418, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.797518310546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.763037109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.706295166015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6506201171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5962841796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5216937255859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4392767333984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.3497381591796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2356024169921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.118802490234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.0088040161132814, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.85275146484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.7117117309570313, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.526332550048828, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.3683904266357423, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.2337859344482422, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0844374465942384, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9360758590698243, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8002288818359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6973817062377929, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5953786373138428, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5125845909118653, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4403938555717468, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.380462327003479, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.33169520378112793, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.28671945571899415, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.2552227538824081, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.23187101244926453, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.206145544052124, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.18231128841638566, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.1652706963568926, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15240161709487438, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1378987354040146, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.12700151436030865, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.11594947434961796, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.10657052412629127, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.09777809090912343, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.09035686181858182, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0832181053981185, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07539469918236136, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07001578448340297, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06573397235944867, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.060715158060193064, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05687418210320175, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.05295060127042234, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.049243472842499615, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04650771098211408, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.043626874899491665, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0415219755936414, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008286767404060811, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008232469612266868, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008139724796637892, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008046140973456205, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007953042357694357, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007820038441568613, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0076655152696184815, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007489511913154274, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007250622001010925, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006986340000294149, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006720945683773607, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006319781502243132, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005937315477058292, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005418409446720034, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004970411348622293, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004586545326747, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0041562580515164885, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0037199596932623535, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003308775854529813, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.002988566665444523, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0026633902755565943, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0023936988692730664, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0021548262296710165, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001953659359132871, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017883593623992055, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0016348233906319364, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001526241714018397, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0014449952979339287, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013546151286573148, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012688285185140558, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001206078419345431, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011576028398121707, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001100928855012171, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0010570214132894762, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0010101241583470254, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0009681193699361757, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009268290190084372, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0008898935756587889, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008521811148966662, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0008079427135817241, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007756089733447879, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0007483997629606165, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0007151808342314326, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0006881576258456335, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0006593366836023051, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0006311931108939461, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0006094639853108674, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005858664085099008, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0005682927426096285, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7963576316833496, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7617452144622803, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.704927444458008, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6492245197296143, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.594716787338257, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.520184278488159, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4376237392425537, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.3480212688446045, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.233910083770752, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.116946220397949, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.0071237087249756, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8512320518493652, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.710503101348877, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5255141258239746, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3681024312973022, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2340002059936523, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0852346420288086, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9373548626899719, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8019973039627075, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6994466185569763, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5978487133979797, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5154693722724915, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4438294768333435, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.3843630850315094, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.33629846572875977, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.29201292991638184, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.261208713054657, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.23844924569129944, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.21365922689437866, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19089458882808685, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.17496657371520996, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.1630735546350479, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1500655561685562, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.14052161574363708, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1313207447528839, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.12387555837631226, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11720170080661774, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11197182536125183, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10738816112279892, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10265684127807617, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09975524246692657, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09768908470869064, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09541747719049454, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09384993463754654, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09240730851888657, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0911998450756073, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09026338905096054, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.08947840332984924, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.08879393339157104, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6436011904761905, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6666666666666666, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6976686507936508, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.716765873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7279265873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7390873015873016, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7475198412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7586805555555556, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7681051587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7810019841269841, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7916666666666666, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8075396825396826, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.824156746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8499503968253969, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8690476190476191, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8871527777777778, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9005456349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9149305555555556, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9275793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9387400793650794, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9469246031746031, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9501488095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9536210317460317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9561011904761905, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.970734126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9764384920634921, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.48098648916206216, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.49715021710065554, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.522987983583905, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5377523189234713, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.549629927679965, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.56303801314809, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5742213133761795, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5937695011570293, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.607938472806987, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6281073634643182, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6493311834200589, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.678298223806901, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7168474321572865, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7715293735829418, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8085942792559219, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8410509934728064, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8651523300514867, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.892457296237775, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9119788398224286, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9287465774079285, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9390897270705028, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9430489297115917, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9464137715785997, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9495927674341768, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9542087414761065, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9565957618252018, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9575541956985031, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9587069043659634, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9604657339639123, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9633943114883039, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9629803916117579, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9640054121246008, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9655905893981576, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9664269134216669, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9670438974739155, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9682744446860136, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9687592027604058, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9712813900866321, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.973414393189911, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.973423626236784, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9743829299642518, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9744817520570004, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9748475707500636, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9744450585326344, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.974084528716678, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9738700970336687, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9738700970336687, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.973687597802238, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9733903123480767, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 0.060715158060193064, "validation/loss_best": 0.09541747719049454, "validation/acc_best": 0.9779265873015873, "validation/f1_best": 0.9748475707500636} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.8848196867108346, "train/grad": 0.030146805765107275, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.79685546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.762144775390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.705159912109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.649345703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.594632568359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5197967529296874, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.437191162109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.347344970703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2328582763671876, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.115745849609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.0054132080078126, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8490078735351563, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.7079098510742188, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.5222543334960938, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.3641266632080078, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.229413299560547, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0800452041625976, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9317138671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7958090782165528, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6929551887512208, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5910862827301026, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5085468721389771, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4366027474403381, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3769827127456665, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.3285841941833496, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.2839440667629242, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.2526832509040833, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.22956239461898803, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.20412898898124696, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.18051837652921676, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.16363927811384202, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.15091325379908085, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.13660751316696407, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.12585421830415724, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.11499006651341916, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.10571583528071642, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.09703840240836144, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.08973142478615045, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0826722332648933, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07490386083722114, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06952206199988722, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06524209769442678, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.06021884832531214, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.056341158738359806, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.052344443621113894, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.04863476794213056, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04582417204044759, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0428830938693136, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.04072490588761866, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008307823431678116, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008253364886622877, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008160269218496979, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0080659382045269, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.007972491611726583, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007838731138035656, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007683482125867158, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007506182654760778, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0072655882430262865, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0069995687832124535, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006732581921387464, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006328341520857066, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005944202528335154, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005422493801452219, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004972845155280083, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004587624582927674, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004156557230744511, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0037202048557810484, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003309426186606288, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0029897320130839945, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002665310436859727, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0023960213537793608, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.002157326136948541, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.001956019451608881, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0017909278260776773, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0016369757533539087, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015279571176506578, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001446292462933343, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013552000161143952, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012691532750613986, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0012058690306730568, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011568756695487536, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0010998569056391717, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.001055432590219425, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001008355086960364, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0009662408832809888, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009246778579836245, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0008876672107726336, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008498124063044088, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00080529611230304, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007724282778508496, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0007452893009030958, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.000711552941284026, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0006843360034690704, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0006550765554857208, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0006266938198677963, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0006041907177132089, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005800417668433511, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000561558131921629, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7957730293273926, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7610392570495605, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.704097032546997, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.648314952850342, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.593658924102783, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5189428329467773, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4361627101898193, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.346442461013794, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.2320759296417236, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.1150403022766113, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.0049123764038086, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8487575054168701, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7079401016235352, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5228692293167114, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.365293025970459, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.23123300075531, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0824379920959473, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9348322153091431, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7995961904525757, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.697252631187439, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5959416627883911, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.513806164264679, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.44232606887817383, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.38321906328201294, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.33523836731910706, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.29114678502082825, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2604755461215973, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.23775748908519745, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.2131160944700241, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19040177762508392, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.17455384135246277, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.1627252846956253, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.14974793791770935, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.14024485647678375, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.13115447759628296, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.12367106229066849, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11697874963283539, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11186018586158752, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1072247251868248, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10252130776643753, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09963624179363251, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.0976024717092514, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09535533934831619, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09376910328865051, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09231407940387726, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.09103203564882278, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09020785987377167, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.0893554538488388, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.08870383352041245, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6448412698412699, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6674107142857143, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6974206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7172619047619048, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7279265873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7393353174603174, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7477678571428571, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7594246031746031, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7690972222222222, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7817460317460317, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7921626984126984, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8077876984126984, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8246527777777778, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8504464285714286, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8692956349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8876488095238095, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9017857142857143, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9151785714285714, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9275793650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9384920634920635, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9469246031746031, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9513888888888888, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9533730158730159, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9627976190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9657738095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9759424603174603, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4820453591754469, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4979154489964303, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5227533981271935, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5380732900022355, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.5496947631462437, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.5627551857658479, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5750695061498055, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5944603665973992, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6090705206677969, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.629449470993854, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6503586012512672, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6785796425943471, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7172192264194829, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7723644161593199, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8088364712824443, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8412250058125077, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8675451944796349, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8933658164616403, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.912350731339492, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9282509808376121, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9390897270705028, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.944208783726255, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9461413138340854, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9493855592450028, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9542087414761065, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9567693468310742, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9574223875369848, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9585311442361327, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9602413618881284, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9633943114883039, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9631551974276562, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9641806612402055, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9654150608995806, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9664257033586827, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9670438974739155, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9682744446860136, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9687592027604058, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9707434789797137, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9729664906633243, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9743529305222883, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9743829299642518, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9744817520570004, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9746689871247924, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9742664945156223, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.974084528716678, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9740477951706388, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.973690428959614, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9731525545994136, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9728947839843558, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.07490386083722114, "validation/loss_best": 0.10252130776643753, "validation/acc_best": 0.9779265873015873, "validation/f1_best": 0.9743529305222883} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.8802165353298187, "train/grad": 0.029961600387468933, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.79570068359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7607666015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7034814453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.647230224609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.592210693359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.51685791015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.43374755859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.343306884765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2280340576171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1102081298828126, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.999190673828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8417767333984374, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.7000527954101563, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.51352783203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.354884719848633, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.2199382781982422, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0704208374023438, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9221946716308593, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7865407752990723, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6841022777557373, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.5828227615356445, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5007731819152832, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4295321393013001, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.3704654550552368, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.32259342074394226, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.27857172369956973, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.24773166656494142, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.22490856647491456, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.1998664531111717, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.17658385425806045, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.15998225897550583, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.14743534564971925, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.13329166945070028, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.12271116498857737, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.11192389290779829, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.10273385586217046, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.09412777438759803, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0869210953079164, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.07988776268437504, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07219860427081586, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06689815871417522, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06268884082324803, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.05773821350187063, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.05394057735800743, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0500840711966157, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.046463760826736686, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04376089854165912, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0409237246029079, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.03887642839923501, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00826691705500707, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008211943162605167, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008118790658190846, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008024797760881483, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00793121951399371, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.007797392883803695, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007642334557604044, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007465424740221351, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.007225762468297034, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006960533317178488, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006695293004158884, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006293222510721535, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005912018027156591, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005393611874897033, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004946212181821465, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004562771595083177, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004132236770819872, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003696063043316826, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0032842308189719917, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0029637171176727863, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.002638478062581271, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.002368586511583999, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0021299896109849216, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0019290938053745776, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.001764693561126478, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001611882168217562, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0015041860163910313, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001423557378584519, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0013338080557878129, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012495385942747816, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.001187466406263411, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011396546836476772, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0010837027942761778, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0010400586514151655, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0009936483777710236, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0009522933745756745, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009110745147336275, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.000874266651662765, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008368186076404527, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.000792295867431676, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007595717094955035, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0007324201859591994, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0006984457409998868, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0006708961984259077, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0006414267526270123, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0006122479045734508, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0005892842573666712, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005641346947959391, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0005449757527094335, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7956736087799072, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7609164714813232, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7039847373962402, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6481854915618896, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5934946537017822, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5187740325927734, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4360055923461914, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.3462138175964355, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.2318053245544434, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.114781618118286, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.004560947418213, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8484148979187012, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7075824737548828, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.522528052330017, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3648980855941772, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.230830430984497, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0820835828781128, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9344574809074402, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7992464303970337, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.6969637274742126, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5956794023513794, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5135772824287415, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.44217798113822937, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.38306552171707153, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3350847363471985, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.2910110354423523, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.26037853956222534, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.23769813776016235, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.2130129039287567, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.19035114347934723, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.17450620234012604, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.16267025470733643, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.14971914887428284, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.14022335410118103, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.13109317421913147, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.12364078313112259, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11697044968605042, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11182159185409546, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.107200987637043, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10251425206661224, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09965511411428452, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09759054332971573, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09533528238534927, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09377685189247131, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09230291843414307, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.09109438210725784, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.0901988074183464, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.08930455148220062, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.08866079896688461, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.644593253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6674107142857143, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6974206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7175099206349206, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7276785714285714, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7390873015873016, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.7475198412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7596726190476191, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.7690972222222222, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7819940476190477, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7919146825396826, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8077876984126984, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8246527777777778, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8504464285714286, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8690476190476191, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8876488095238095, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9015376984126984, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9151785714285714, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9280753968253969, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9384920634920635, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9469246031746031, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9513888888888888, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9536210317460317, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9627976190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9769345238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9761904761904762, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4818085307760559, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4979154489964303, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.5227112696339015, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.538323963419613, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.549533670389358, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.562657047240702, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5749218296957559, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.5948089023451012, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.6090705206677969, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.6295269302579564, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6498536269905616, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6785796425943471, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7171829441245465, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7723644161593199, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.808585840186266, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8412250058125077, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8672100121586565, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8933658164616403, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9129223226183087, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9282509808376121, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9390897270705028, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.944194493806247, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9464137715785997, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9493855592450028, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9539380274527636, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9567693468310742, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9574223875369848, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9585311442361327, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9600556810567275, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9631230002499791, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9631551974276562, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9641806612402055, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9654150608995806, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9664257033586827, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9670438974739155, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9682744446860136, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9687592027604058, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9709214291777877, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9729664906633243, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.974145384137705, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9743829299642518, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9744817520570004, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9748475707500636, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9742664945156223, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.974084528716678, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9740477951706388, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9738700970336687, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9731525545994136, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9730748105718644, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 0.05773821350187063, "validation/loss_best": 0.09533528238534927, "validation/acc_best": 0.9779265873015873, "validation/f1_best": 0.9748475707500636} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/config.yaml b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..adc396131c766c5ea426b4c95c9abce13e9695d3 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..a2cedb394ac0fb08ed1867d69b408e83fc7c061b --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 10, "eval/id_best": 26, "eval/lr_best": 0.00041999999999999996, "eval/wd_best": 0.05, "eval/train/loss": 2.2605645656585693, "eval/train/acc": 0.3197701220074372, "eval/train/acc_std": 0.002298118062558802, "eval/train/f1": 0.26337077778657175, "eval/train/f1_std": 0.002306882492623809, "eval/validation/loss": 2.427823066711426, "eval/validation/acc": 0.2739018087855297, "eval/validation/acc_std": 0.0055456699499999654, "eval/validation/f1": 0.20107671791720697, "eval/validation/f1_std": 0.00487686697323598, "eval/test/loss": 2.3020825386047363, "eval/test/acc": 0.2907235621521336, "eval/test/acc_std": 0.005013393360799736, "eval/test/f1": 0.22086432780826984, "eval/test/f1_std": 0.005086535840965432, "eval/testid/loss": 2.4446189403533936, "eval/testid/acc": 0.26527858106805474, "eval/testid/acc_std": 0.005133250314781336, "eval/testid/f1": 0.20384687486539307, "eval/testid/f1_std": 0.004845466837976695} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..ad35bd318daf5019398b6c9026ee791cb48d49b8 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 10, "eval/best/id_best": 26, "eval/best/lr_best": 0.00041999999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.2605645656585693, "eval/best/train/acc": 0.3197701220074372, "eval/best/train/acc_std": 0.002298118062558802, "eval/best/train/f1": 0.26337077778657175, "eval/best/train/f1_std": 0.002306882492623809, "eval/best/validation/loss": 2.427823066711426, "eval/best/validation/acc": 0.2739018087855297, "eval/best/validation/acc_std": 0.0055456699499999654, "eval/best/validation/f1": 0.20107671791720697, "eval/best/validation/f1_std": 0.00487686697323598, "eval/best/test/loss": 2.3020825386047363, "eval/best/test/acc": 0.2907235621521336, "eval/best/test/acc_std": 0.005013393360799736, "eval/best/test/f1": 0.22086432780826984, "eval/best/test/f1_std": 0.005086535840965432, "eval/best/testid/loss": 2.4446189403533936, "eval/best/testid/acc": 0.26527858106805474, "eval/best/testid/acc_std": 0.005133250314781336, "eval/best/testid/f1": 0.20384687486539307, "eval/best/testid/f1_std": 0.004845466837976695} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..c8a87823e6c06c4fcd2145e2775a53ed00734ca8 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 25, "eval/last/lr_best": 0.00035999999999999997, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.214479684829712, "eval/last/train/acc": 0.333538215679646, "eval/last/train/acc_std": 0.0024347813380314284, "eval/last/train/f1": 0.27807483689039497, "eval/last/train/f1_std": 0.0024488567666694854, "eval/last/validation/loss": 2.433335542678833, "eval/last/validation/acc": 0.2713178294573643, "eval/last/validation/acc_std": 0.005475532417090575, "eval/last/validation/f1": 0.2045602904745525, "eval/last/validation/f1_std": 0.004761130683286945, "eval/last/test/loss": 2.2954249382019043, "eval/last/test/acc": 0.29313543599257885, "eval/last/test/acc_std": 0.005160856470291994, "eval/last/test/f1": 0.22741334745801298, "eval/last/test/f1_std": 0.0050700306975071776, "eval/last/testid/loss": 2.4195709228515625, "eval/last/testid/acc": 0.26855600539811064, "eval/last/testid/acc_std": 0.005510115868940855, "eval/last/testid/f1": 0.20973811093119385, "eval/last/testid/f1_std": 0.005026214708323616} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..be2290b151e683f2c277d3f9e25d34725e4a5184 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",train,2.2605645656585693,0.3197701220074372,0.002298118062558802,0.26337077778657175,0.002306882492623809 +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",validation,2.427823066711426,0.2739018087855297,0.0055456699499999654,0.20107671791720697,0.00487686697323598 +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",test,2.3020825386047363,0.2907235621521336,0.005013393360799736,0.22086432780826984,0.005086535840965432 +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",testid,2.4446189403533936,0.26527858106805474,0.005133250314781336,0.20384687486539307,0.004845466837976695 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..be2290b151e683f2c277d3f9e25d34725e4a5184 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",train,2.2605645656585693,0.3197701220074372,0.002298118062558802,0.26337077778657175,0.002306882492623809 +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",validation,2.427823066711426,0.2739018087855297,0.0055456699499999654,0.20107671791720697,0.00487686697323598 +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",test,2.3020825386047363,0.2907235621521336,0.005013393360799736,0.22086432780826984,0.005086535840965432 +flat_mae,patch,attn,nsd_cococlip,best,10,0.00041999999999999996,0.05,26,"[1.4, 1.0]",testid,2.4446189403533936,0.26527858106805474,0.005133250314781336,0.20384687486539307,0.004845466837976695 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..f2c1e5e1a412c0a25f6b38ad8cdf09e0470c9617 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,0.00035999999999999997,0.05,25,"[1.2, 1.0]",train,2.214479684829712,0.333538215679646,0.0024347813380314284,0.27807483689039497,0.0024488567666694854 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00035999999999999997,0.05,25,"[1.2, 1.0]",validation,2.433335542678833,0.2713178294573643,0.005475532417090575,0.2045602904745525,0.004761130683286945 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00035999999999999997,0.05,25,"[1.2, 1.0]",test,2.2954249382019043,0.29313543599257885,0.005160856470291994,0.22741334745801298,0.0050700306975071776 +flat_mae,patch,attn,nsd_cococlip,last,19,0.00035999999999999997,0.05,25,"[1.2, 1.0]",testid,2.4195709228515625,0.26855600539811064,0.005510115868940855,0.20973811093119385,0.005026214708323616 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/log.txt b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..201af17ef78681506206428c144927744462c7ea --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,957 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 22:21:36 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:58 lr: nan time: 3.7459 data: 3.1011 max mem: 21740 +train: [0] [ 20/400] eta: 0:04:02 lr: 0.000003 loss: 3.1771 (3.1770) grad: 0.0277 (0.0277) time: 0.4837 data: 0.0026 max mem: 22448 +train: [0] [ 40/400] eta: 0:03:18 lr: 0.000006 loss: 3.1774 (3.1772) grad: 0.0271 (0.0270) time: 0.4620 data: 0.0046 max mem: 22448 +train: [0] [ 60/400] eta: 0:02:59 lr: 0.000009 loss: 3.1723 (3.1750) grad: 0.0260 (0.0266) time: 0.4764 data: 0.0049 max mem: 22448 +train: [0] [ 80/400] eta: 0:02:44 lr: 0.000012 loss: 3.1690 (3.1724) grad: 0.0265 (0.0269) time: 0.4664 data: 0.0048 max mem: 22448 +train: [0] [100/400] eta: 0:02:30 lr: 0.000015 loss: 3.1634 (3.1702) grad: 0.0280 (0.0271) time: 0.4616 data: 0.0047 max mem: 22448 +train: [0] [120/400] eta: 0:02:19 lr: 0.000018 loss: 3.1596 (3.1686) grad: 0.0274 (0.0273) time: 0.4722 data: 0.0050 max mem: 22448 +train: [0] [140/400] eta: 0:02:08 lr: 0.000021 loss: 3.1583 (3.1671) grad: 0.0271 (0.0274) time: 0.4642 data: 0.0047 max mem: 22448 +train: [0] [160/400] eta: 0:01:56 lr: 0.000024 loss: 3.1547 (3.1652) grad: 0.0285 (0.0276) time: 0.4469 data: 0.0045 max mem: 22448 +train: [0] [180/400] eta: 0:01:46 lr: 0.000027 loss: 3.1522 (3.1636) grad: 0.0285 (0.0278) time: 0.4552 data: 0.0048 max mem: 22448 +train: [0] [200/400] eta: 0:01:36 lr: 0.000030 loss: 3.1510 (3.1618) grad: 0.0277 (0.0278) time: 0.4673 data: 0.0046 max mem: 22448 +train: [0] [220/400] eta: 0:01:26 lr: 0.000033 loss: 3.1339 (3.1588) grad: 0.0288 (0.0280) time: 0.4690 data: 0.0049 max mem: 22448 +train: [0] [240/400] eta: 0:01:16 lr: 0.000036 loss: 3.1305 (3.1566) grad: 0.0301 (0.0281) time: 0.4605 data: 0.0048 max mem: 22448 +train: [0] [260/400] eta: 0:01:07 lr: 0.000039 loss: 3.1366 (3.1547) grad: 0.0290 (0.0282) time: 0.4811 data: 0.0050 max mem: 22448 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 3.1271 (3.1526) grad: 0.0291 (0.0283) time: 0.4647 data: 0.0047 max mem: 22448 +train: [0] [300/400] eta: 0:00:47 lr: 0.000045 loss: 3.1192 (3.1496) grad: 0.0299 (0.0285) time: 0.4694 data: 0.0050 max mem: 22448 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 3.1033 (3.1465) grad: 0.0313 (0.0288) time: 0.4717 data: 0.0049 max mem: 22448 +train: [0] [340/400] eta: 0:00:28 lr: 0.000051 loss: 3.1006 (3.1436) grad: 0.0299 (0.0289) time: 0.4716 data: 0.0050 max mem: 22448 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 3.0875 (3.1399) grad: 0.0316 (0.0291) time: 0.4616 data: 0.0047 max mem: 22448 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.0863 (3.1370) grad: 0.0349 (0.0295) time: 0.4631 data: 0.0047 max mem: 22448 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.0777 (3.1339) grad: 0.0363 (0.0298) time: 0.4543 data: 0.0048 max mem: 22448 +train: [0] Total time: 0:03:09 (0.4749 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.0777 (3.1339) grad: 0.0363 (0.0298) +eval (validation): [0] [ 0/85] eta: 0:04:34 time: 3.2287 data: 2.9207 max mem: 22448 +eval (validation): [0] [20/85] eta: 0:00:34 time: 0.3910 data: 0.0046 max mem: 22448 +eval (validation): [0] [40/85] eta: 0:00:19 time: 0.3516 data: 0.0032 max mem: 22448 +eval (validation): [0] [60/85] eta: 0:00:10 time: 0.3529 data: 0.0043 max mem: 22448 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3431 data: 0.0043 max mem: 22448 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3358 data: 0.0043 max mem: 22448 +eval (validation): [0] Total time: 0:00:33 (0.3947 s / it) +cv: [0] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.697 acc: 0.200 f1: 0.121 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:01 lr: nan time: 3.3048 data: 2.8924 max mem: 22448 +train: [1] [ 20/400] eta: 0:03:46 lr: 0.000063 loss: 3.0543 (3.0648) grad: 0.0346 (0.0352) time: 0.4609 data: 0.0044 max mem: 22448 +train: [1] [ 40/400] eta: 0:03:13 lr: 0.000066 loss: 3.0523 (3.0515) grad: 0.0344 (0.0347) time: 0.4738 data: 0.0048 max mem: 22448 +train: [1] [ 60/400] eta: 0:02:54 lr: 0.000069 loss: 3.0482 (3.0512) grad: 0.0345 (0.0350) time: 0.4637 data: 0.0049 max mem: 22448 +train: [1] [ 80/400] eta: 0:02:39 lr: 0.000072 loss: 3.0493 (3.0529) grad: 0.0357 (0.0356) time: 0.4501 data: 0.0044 max mem: 22448 +train: [1] [100/400] eta: 0:02:28 lr: 0.000075 loss: 3.0439 (3.0479) grad: 0.0380 (0.0361) time: 0.4780 data: 0.0048 max mem: 22448 +train: [1] [120/400] eta: 0:02:16 lr: 0.000078 loss: 3.0228 (3.0447) grad: 0.0380 (0.0366) time: 0.4606 data: 0.0047 max mem: 22448 +train: [1] [140/400] eta: 0:02:05 lr: 0.000081 loss: 3.0302 (3.0428) grad: 0.0369 (0.0366) time: 0.4615 data: 0.0050 max mem: 22448 +train: [1] [160/400] eta: 0:01:55 lr: 0.000084 loss: 3.0298 (3.0391) grad: 0.0371 (0.0370) time: 0.4487 data: 0.0047 max mem: 22448 +train: [1] [180/400] eta: 0:01:45 lr: 0.000087 loss: 3.0253 (3.0364) grad: 0.0399 (0.0374) time: 0.4574 data: 0.0047 max mem: 22448 +train: [1] [200/400] eta: 0:01:35 lr: 0.000090 loss: 3.0016 (3.0333) grad: 0.0391 (0.0376) time: 0.4711 data: 0.0049 max mem: 22448 +train: [1] [220/400] eta: 0:01:25 lr: 0.000093 loss: 2.9991 (3.0302) grad: 0.0392 (0.0379) time: 0.4552 data: 0.0047 max mem: 22448 +train: [1] [240/400] eta: 0:01:16 lr: 0.000096 loss: 3.0035 (3.0284) grad: 0.0406 (0.0382) time: 0.4788 data: 0.0049 max mem: 22448 +train: [1] [260/400] eta: 0:01:06 lr: 0.000099 loss: 2.9792 (3.0256) grad: 0.0407 (0.0385) time: 0.4628 data: 0.0050 max mem: 22448 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 2.9777 (3.0225) grad: 0.0416 (0.0388) time: 0.4639 data: 0.0049 max mem: 22448 +train: [1] [300/400] eta: 0:00:47 lr: 0.000105 loss: 2.9843 (3.0211) grad: 0.0416 (0.0390) time: 0.4656 data: 0.0048 max mem: 22448 +train: [1] [320/400] eta: 0:00:37 lr: 0.000108 loss: 3.0072 (3.0194) grad: 0.0414 (0.0392) time: 0.4624 data: 0.0050 max mem: 22448 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 2.9735 (3.0154) grad: 0.0421 (0.0395) time: 0.4659 data: 0.0050 max mem: 22448 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 2.9685 (3.0133) grad: 0.0421 (0.0396) time: 0.4719 data: 0.0050 max mem: 22448 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 2.9599 (3.0101) grad: 0.0420 (0.0398) time: 0.4686 data: 0.0049 max mem: 22448 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.9715 (3.0086) grad: 0.0430 (0.0400) time: 0.4613 data: 0.0048 max mem: 22448 +train: [1] Total time: 0:03:08 (0.4719 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.9715 (3.0086) grad: 0.0430 (0.0400) +eval (validation): [1] [ 0/85] eta: 0:04:46 time: 3.3690 data: 3.1045 max mem: 22448 +eval (validation): [1] [20/85] eta: 0:00:33 time: 0.3758 data: 0.0047 max mem: 22448 +eval (validation): [1] [40/85] eta: 0:00:19 time: 0.3411 data: 0.0035 max mem: 22448 +eval (validation): [1] [60/85] eta: 0:00:10 time: 0.3437 data: 0.0040 max mem: 22448 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3400 data: 0.0040 max mem: 22448 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3306 data: 0.0039 max mem: 22448 +eval (validation): [1] Total time: 0:00:32 (0.3869 s / it) +cv: [1] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.572 acc: 0.227 f1: 0.154 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:38 lr: nan time: 3.3969 data: 3.0248 max mem: 22448 +train: [2] [ 20/400] eta: 0:03:56 lr: 0.000123 loss: 2.9729 (2.9601) grad: 0.0452 (0.0457) time: 0.4841 data: 0.0038 max mem: 22448 +train: [2] [ 40/400] eta: 0:03:16 lr: 0.000126 loss: 2.9495 (2.9477) grad: 0.0456 (0.0464) time: 0.4671 data: 0.0045 max mem: 22448 +train: [2] [ 60/400] eta: 0:02:56 lr: 0.000129 loss: 2.9394 (2.9406) grad: 0.0494 (0.0474) time: 0.4658 data: 0.0047 max mem: 22448 +train: [2] [ 80/400] eta: 0:02:41 lr: 0.000132 loss: 2.9394 (2.9425) grad: 0.0483 (0.0472) time: 0.4559 data: 0.0047 max mem: 22448 +train: [2] [100/400] eta: 0:02:30 lr: 0.000135 loss: 2.9452 (2.9421) grad: 0.0478 (0.0475) time: 0.4836 data: 0.0050 max mem: 22448 +train: [2] [120/400] eta: 0:02:18 lr: 0.000138 loss: 2.9446 (2.9388) grad: 0.0467 (0.0474) time: 0.4634 data: 0.0051 max mem: 22448 +train: [2] [140/400] eta: 0:02:07 lr: 0.000141 loss: 2.9255 (2.9373) grad: 0.0467 (0.0477) time: 0.4714 data: 0.0046 max mem: 22448 +train: [2] [160/400] eta: 0:01:56 lr: 0.000144 loss: 2.9208 (2.9336) grad: 0.0501 (0.0482) time: 0.4550 data: 0.0046 max mem: 22448 +train: [2] [180/400] eta: 0:01:46 lr: 0.000147 loss: 2.9024 (2.9314) grad: 0.0522 (0.0487) time: 0.4613 data: 0.0049 max mem: 22448 +train: [2] [200/400] eta: 0:01:36 lr: 0.000150 loss: 2.9098 (2.9326) grad: 0.0525 (0.0492) time: 0.4620 data: 0.0049 max mem: 22448 +train: [2] [220/400] eta: 0:01:26 lr: 0.000153 loss: 2.8993 (2.9295) grad: 0.0532 (0.0496) time: 0.4634 data: 0.0049 max mem: 22448 +train: [2] [240/400] eta: 0:01:16 lr: 0.000156 loss: 2.8928 (2.9267) grad: 0.0530 (0.0499) time: 0.4707 data: 0.0052 max mem: 22448 +train: [2] [260/400] eta: 0:01:06 lr: 0.000159 loss: 2.8901 (2.9243) grad: 0.0520 (0.0500) time: 0.4690 data: 0.0050 max mem: 22448 +train: [2] [280/400] eta: 0:00:57 lr: 0.000162 loss: 2.8875 (2.9231) grad: 0.0511 (0.0501) time: 0.4630 data: 0.0045 max mem: 22448 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 2.9183 (2.9235) grad: 0.0518 (0.0502) time: 0.4641 data: 0.0047 max mem: 22448 +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 2.8809 (2.9198) grad: 0.0518 (0.0503) time: 0.4678 data: 0.0047 max mem: 22448 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 2.8674 (2.9179) grad: 0.0519 (0.0505) time: 0.4701 data: 0.0046 max mem: 22448 +train: [2] [360/400] eta: 0:00:19 lr: 0.000174 loss: 2.8761 (2.9166) grad: 0.0522 (0.0506) time: 0.4739 data: 0.0048 max mem: 22448 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.8843 (2.9161) grad: 0.0522 (0.0507) time: 0.4634 data: 0.0047 max mem: 22448 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.8915 (2.9154) grad: 0.0531 (0.0509) time: 0.4779 data: 0.0050 max mem: 22448 +train: [2] Total time: 0:03:10 (0.4756 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.8915 (2.9154) grad: 0.0531 (0.0509) +eval (validation): [2] [ 0/85] eta: 0:04:25 time: 3.1231 data: 2.8827 max mem: 22448 +eval (validation): [2] [20/85] eta: 0:00:31 time: 0.3605 data: 0.0053 max mem: 22448 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3394 data: 0.0037 max mem: 22448 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3397 data: 0.0042 max mem: 22448 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3335 data: 0.0039 max mem: 22448 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3288 data: 0.0039 max mem: 22448 +eval (validation): [2] Total time: 0:00:32 (0.3787 s / it) +cv: [2] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.595 acc: 0.234 f1: 0.163 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:21:58 lr: nan time: 3.2973 data: 2.9022 max mem: 22448 +train: [3] [ 20/400] eta: 0:03:58 lr: 0.000183 loss: 2.8385 (2.8546) grad: 0.0535 (0.0560) time: 0.4933 data: 0.0046 max mem: 22448 +train: [3] [ 40/400] eta: 0:03:18 lr: 0.000186 loss: 2.8529 (2.8624) grad: 0.0578 (0.0575) time: 0.4732 data: 0.0048 max mem: 22448 +train: [3] [ 60/400] eta: 0:02:56 lr: 0.000189 loss: 2.8529 (2.8540) grad: 0.0574 (0.0565) time: 0.4510 data: 0.0047 max mem: 22448 +train: [3] [ 80/400] eta: 0:02:42 lr: 0.000192 loss: 2.8229 (2.8500) grad: 0.0557 (0.0571) time: 0.4781 data: 0.0049 max mem: 22448 +train: [3] [100/400] eta: 0:02:30 lr: 0.000195 loss: 2.8456 (2.8548) grad: 0.0580 (0.0569) time: 0.4652 data: 0.0048 max mem: 22448 +train: [3] [120/400] eta: 0:02:18 lr: 0.000198 loss: 2.8649 (2.8534) grad: 0.0583 (0.0574) time: 0.4604 data: 0.0050 max mem: 22448 +train: [3] [140/400] eta: 0:02:06 lr: 0.000201 loss: 2.8447 (2.8552) grad: 0.0580 (0.0572) time: 0.4438 data: 0.0047 max mem: 22448 +train: [3] [160/400] eta: 0:01:56 lr: 0.000204 loss: 2.8594 (2.8570) grad: 0.0560 (0.0572) time: 0.4642 data: 0.0049 max mem: 22448 +train: [3] [180/400] eta: 0:01:45 lr: 0.000207 loss: 2.8774 (2.8583) grad: 0.0563 (0.0573) time: 0.4647 data: 0.0050 max mem: 22448 +train: [3] [200/400] eta: 0:01:35 lr: 0.000210 loss: 2.8626 (2.8602) grad: 0.0584 (0.0574) time: 0.4645 data: 0.0050 max mem: 22448 +train: [3] [220/400] eta: 0:01:26 lr: 0.000213 loss: 2.8553 (2.8585) grad: 0.0586 (0.0578) time: 0.4648 data: 0.0049 max mem: 22448 +train: [3] [240/400] eta: 0:01:16 lr: 0.000216 loss: 2.8303 (2.8558) grad: 0.0597 (0.0579) time: 0.4575 data: 0.0048 max mem: 22448 +train: [3] [260/400] eta: 0:01:06 lr: 0.000219 loss: 2.8504 (2.8565) grad: 0.0599 (0.0582) time: 0.4642 data: 0.0049 max mem: 22448 +train: [3] [280/400] eta: 0:00:56 lr: 0.000222 loss: 2.8692 (2.8565) grad: 0.0614 (0.0584) time: 0.4593 data: 0.0047 max mem: 22448 +train: [3] [300/400] eta: 0:00:47 lr: 0.000225 loss: 2.8698 (2.8568) grad: 0.0599 (0.0586) time: 0.4615 data: 0.0047 max mem: 22448 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 2.8079 (2.8550) grad: 0.0591 (0.0586) time: 0.4653 data: 0.0048 max mem: 22448 +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 2.8110 (2.8531) grad: 0.0601 (0.0588) time: 0.4593 data: 0.0045 max mem: 22448 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 2.8384 (2.8520) grad: 0.0625 (0.0589) time: 0.4565 data: 0.0046 max mem: 22448 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 2.8389 (2.8522) grad: 0.0620 (0.0591) time: 0.4615 data: 0.0049 max mem: 22448 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.8254 (2.8490) grad: 0.0631 (0.0593) time: 0.4685 data: 0.0047 max mem: 22448 +train: [3] Total time: 0:03:08 (0.4714 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.8254 (2.8490) grad: 0.0631 (0.0593) +eval (validation): [3] [ 0/85] eta: 0:04:25 time: 3.1233 data: 2.8888 max mem: 22448 +eval (validation): [3] [20/85] eta: 0:00:30 time: 0.3318 data: 0.0041 max mem: 22448 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3632 data: 0.0035 max mem: 22448 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3575 data: 0.0040 max mem: 22448 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3430 data: 0.0043 max mem: 22448 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3350 data: 0.0043 max mem: 22448 +eval (validation): [3] Total time: 0:00:32 (0.3836 s / it) +cv: [3] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 2.499 acc: 0.245 f1: 0.172 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:21:49 lr: nan time: 3.2733 data: 2.8709 max mem: 22448 +train: [4] [ 20/400] eta: 0:03:48 lr: 0.000243 loss: 2.8411 (2.8204) grad: 0.0629 (0.0637) time: 0.4679 data: 0.0046 max mem: 22448 +train: [4] [ 40/400] eta: 0:03:12 lr: 0.000246 loss: 2.8060 (2.8123) grad: 0.0628 (0.0633) time: 0.4635 data: 0.0048 max mem: 22448 +train: [4] [ 60/400] eta: 0:02:52 lr: 0.000249 loss: 2.8007 (2.8154) grad: 0.0634 (0.0641) time: 0.4496 data: 0.0050 max mem: 22448 +train: [4] [ 80/400] eta: 0:02:39 lr: 0.000252 loss: 2.7819 (2.8071) grad: 0.0640 (0.0641) time: 0.4752 data: 0.0048 max mem: 22448 +train: [4] [100/400] eta: 0:02:27 lr: 0.000255 loss: 2.7556 (2.7933) grad: 0.0638 (0.0641) time: 0.4707 data: 0.0049 max mem: 22448 +train: [4] [120/400] eta: 0:02:16 lr: 0.000258 loss: 2.7704 (2.7953) grad: 0.0655 (0.0645) time: 0.4662 data: 0.0049 max mem: 22448 +train: [4] [140/400] eta: 0:02:05 lr: 0.000261 loss: 2.8268 (2.8015) grad: 0.0670 (0.0649) time: 0.4471 data: 0.0047 max mem: 22448 +train: [4] [160/400] eta: 0:01:55 lr: 0.000264 loss: 2.8212 (2.8014) grad: 0.0651 (0.0650) time: 0.4737 data: 0.0050 max mem: 22448 +train: [4] [180/400] eta: 0:01:45 lr: 0.000267 loss: 2.7884 (2.8009) grad: 0.0634 (0.0648) time: 0.4631 data: 0.0050 max mem: 22448 +train: [4] [200/400] eta: 0:01:35 lr: 0.000270 loss: 2.7946 (2.8003) grad: 0.0647 (0.0650) time: 0.4647 data: 0.0048 max mem: 22448 +train: [4] [220/400] eta: 0:01:25 lr: 0.000273 loss: 2.8022 (2.8003) grad: 0.0671 (0.0654) time: 0.4618 data: 0.0046 max mem: 22448 +train: [4] [240/400] eta: 0:01:16 lr: 0.000276 loss: 2.8074 (2.8021) grad: 0.0682 (0.0656) time: 0.4672 data: 0.0049 max mem: 22448 +train: [4] [260/400] eta: 0:01:06 lr: 0.000279 loss: 2.7965 (2.7994) grad: 0.0672 (0.0658) time: 0.4666 data: 0.0049 max mem: 22448 +train: [4] [280/400] eta: 0:00:56 lr: 0.000282 loss: 2.7516 (2.7974) grad: 0.0682 (0.0661) time: 0.4682 data: 0.0047 max mem: 22448 +train: [4] [300/400] eta: 0:00:47 lr: 0.000285 loss: 2.7317 (2.7957) grad: 0.0696 (0.0663) time: 0.4748 data: 0.0048 max mem: 22448 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 2.7782 (2.7975) grad: 0.0692 (0.0664) time: 0.4730 data: 0.0048 max mem: 22448 +train: [4] [340/400] eta: 0:00:28 lr: 0.000291 loss: 2.7717 (2.7958) grad: 0.0670 (0.0664) time: 0.4647 data: 0.0046 max mem: 22448 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 2.7742 (2.7960) grad: 0.0661 (0.0664) time: 0.4549 data: 0.0044 max mem: 22448 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.8053 (2.7969) grad: 0.0665 (0.0664) time: 0.4739 data: 0.0047 max mem: 22448 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.8053 (2.7968) grad: 0.0662 (0.0665) time: 0.4647 data: 0.0049 max mem: 22448 +train: [4] Total time: 0:03:09 (0.4732 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.8053 (2.7968) grad: 0.0662 (0.0665) +eval (validation): [4] [ 0/85] eta: 0:04:26 time: 3.1318 data: 2.8882 max mem: 22448 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3527 data: 0.0036 max mem: 22448 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3412 data: 0.0039 max mem: 22448 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3502 data: 0.0044 max mem: 22448 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3488 data: 0.0043 max mem: 22448 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3444 data: 0.0043 max mem: 22448 +eval (validation): [4] Total time: 0:00:32 (0.3828 s / it) +cv: [4] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.464 acc: 0.270 f1: 0.197 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:43 lr: nan time: 3.4080 data: 3.0069 max mem: 22448 +train: [5] [ 20/400] eta: 0:03:58 lr: 0.000300 loss: 2.7475 (2.7467) grad: 0.0697 (0.0696) time: 0.4882 data: 0.0031 max mem: 22448 +train: [5] [ 40/400] eta: 0:03:15 lr: 0.000300 loss: 2.7475 (2.7538) grad: 0.0697 (0.0695) time: 0.4533 data: 0.0041 max mem: 22448 +train: [5] [ 60/400] eta: 0:02:57 lr: 0.000300 loss: 2.7629 (2.7704) grad: 0.0702 (0.0706) time: 0.4764 data: 0.0052 max mem: 22448 +train: [5] [ 80/400] eta: 0:02:42 lr: 0.000300 loss: 2.7372 (2.7551) grad: 0.0690 (0.0702) time: 0.4725 data: 0.0049 max mem: 22448 +train: [5] [100/400] eta: 0:02:30 lr: 0.000300 loss: 2.7406 (2.7617) grad: 0.0706 (0.0704) time: 0.4683 data: 0.0048 max mem: 22448 +train: [5] [120/400] eta: 0:02:18 lr: 0.000300 loss: 2.7297 (2.7520) grad: 0.0722 (0.0715) time: 0.4578 data: 0.0049 max mem: 22448 +train: [5] [140/400] eta: 0:02:07 lr: 0.000300 loss: 2.7196 (2.7586) grad: 0.0745 (0.0721) time: 0.4750 data: 0.0048 max mem: 22448 +train: [5] [160/400] eta: 0:01:56 lr: 0.000299 loss: 2.8189 (2.7664) grad: 0.0744 (0.0725) time: 0.4611 data: 0.0049 max mem: 22448 +train: [5] [180/400] eta: 0:01:46 lr: 0.000299 loss: 2.7378 (2.7599) grad: 0.0720 (0.0723) time: 0.4694 data: 0.0048 max mem: 22448 +train: [5] [200/400] eta: 0:01:36 lr: 0.000299 loss: 2.6947 (2.7580) grad: 0.0725 (0.0726) time: 0.4669 data: 0.0051 max mem: 22448 +train: [5] [220/400] eta: 0:01:26 lr: 0.000299 loss: 2.7223 (2.7556) grad: 0.0729 (0.0727) time: 0.4648 data: 0.0048 max mem: 22448 +train: [5] [240/400] eta: 0:01:16 lr: 0.000299 loss: 2.7374 (2.7577) grad: 0.0718 (0.0726) time: 0.4713 data: 0.0051 max mem: 22448 +train: [5] [260/400] eta: 0:01:07 lr: 0.000299 loss: 2.7557 (2.7582) grad: 0.0696 (0.0724) time: 0.4646 data: 0.0047 max mem: 22448 +train: [5] [280/400] eta: 0:00:57 lr: 0.000298 loss: 2.7557 (2.7578) grad: 0.0696 (0.0723) time: 0.4645 data: 0.0046 max mem: 22448 +train: [5] [300/400] eta: 0:00:47 lr: 0.000298 loss: 2.7427 (2.7573) grad: 0.0713 (0.0723) time: 0.4631 data: 0.0050 max mem: 22448 +train: [5] [320/400] eta: 0:00:38 lr: 0.000298 loss: 2.7427 (2.7573) grad: 0.0708 (0.0722) time: 0.4646 data: 0.0049 max mem: 22448 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 2.7126 (2.7560) grad: 0.0706 (0.0722) time: 0.4648 data: 0.0049 max mem: 22448 +train: [5] [360/400] eta: 0:00:19 lr: 0.000297 loss: 2.6370 (2.7492) grad: 0.0706 (0.0721) time: 0.4689 data: 0.0049 max mem: 22448 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.6465 (2.7474) grad: 0.0699 (0.0720) time: 0.4832 data: 0.0050 max mem: 22448 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.7472 (2.7473) grad: 0.0699 (0.0720) time: 0.4682 data: 0.0049 max mem: 22448 +train: [5] Total time: 0:03:10 (0.4764 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.7472 (2.7473) grad: 0.0699 (0.0720) +eval (validation): [5] [ 0/85] eta: 0:04:37 time: 3.2663 data: 2.9773 max mem: 22448 +eval (validation): [5] [20/85] eta: 0:00:32 time: 0.3552 data: 0.0056 max mem: 22448 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3495 data: 0.0036 max mem: 22448 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3474 data: 0.0041 max mem: 22448 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3371 data: 0.0042 max mem: 22448 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3341 data: 0.0042 max mem: 22448 +eval (validation): [5] Total time: 0:00:32 (0.3840 s / it) +cv: [5] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 2.466 acc: 0.260 f1: 0.200 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:22:10 lr: nan time: 3.3266 data: 2.9691 max mem: 22448 +train: [6] [ 20/400] eta: 0:03:49 lr: 0.000296 loss: 2.6946 (2.6809) grad: 0.0678 (0.0692) time: 0.4670 data: 0.0038 max mem: 22448 +train: [6] [ 40/400] eta: 0:03:10 lr: 0.000296 loss: 2.6946 (2.6912) grad: 0.0699 (0.0698) time: 0.4502 data: 0.0042 max mem: 22448 +train: [6] [ 60/400] eta: 0:02:55 lr: 0.000296 loss: 2.6642 (2.6807) grad: 0.0699 (0.0699) time: 0.4949 data: 0.0052 max mem: 22448 +train: [6] [ 80/400] eta: 0:02:40 lr: 0.000295 loss: 2.6474 (2.6812) grad: 0.0711 (0.0706) time: 0.4521 data: 0.0050 max mem: 22448 +train: [6] [100/400] eta: 0:02:27 lr: 0.000295 loss: 2.6474 (2.6794) grad: 0.0718 (0.0711) time: 0.4576 data: 0.0048 max mem: 22448 +train: [6] [120/400] eta: 0:02:15 lr: 0.000295 loss: 2.6651 (2.6770) grad: 0.0713 (0.0711) time: 0.4482 data: 0.0048 max mem: 22448 +train: [6] [140/400] eta: 0:02:05 lr: 0.000294 loss: 2.6387 (2.6745) grad: 0.0714 (0.0714) time: 0.4649 data: 0.0050 max mem: 22448 +train: [6] [160/400] eta: 0:01:55 lr: 0.000294 loss: 2.6466 (2.6758) grad: 0.0728 (0.0715) time: 0.4588 data: 0.0049 max mem: 22448 +train: [6] [180/400] eta: 0:01:45 lr: 0.000293 loss: 2.6684 (2.6741) grad: 0.0728 (0.0716) time: 0.4672 data: 0.0052 max mem: 22448 +train: [6] [200/400] eta: 0:01:35 lr: 0.000293 loss: 2.6590 (2.6746) grad: 0.0716 (0.0717) time: 0.4624 data: 0.0049 max mem: 22448 +train: [6] [220/400] eta: 0:01:25 lr: 0.000292 loss: 2.6766 (2.6739) grad: 0.0730 (0.0718) time: 0.4538 data: 0.0048 max mem: 22448 +train: [6] [240/400] eta: 0:01:15 lr: 0.000292 loss: 2.7013 (2.6747) grad: 0.0729 (0.0719) time: 0.4627 data: 0.0047 max mem: 22448 +train: [6] [260/400] eta: 0:01:06 lr: 0.000291 loss: 2.7115 (2.6764) grad: 0.0729 (0.0722) time: 0.4716 data: 0.0049 max mem: 22448 +train: [6] [280/400] eta: 0:00:56 lr: 0.000291 loss: 2.6833 (2.6779) grad: 0.0739 (0.0722) time: 0.4615 data: 0.0049 max mem: 22448 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 2.6432 (2.6756) grad: 0.0732 (0.0725) time: 0.4579 data: 0.0045 max mem: 22448 +train: [6] [320/400] eta: 0:00:37 lr: 0.000290 loss: 2.6187 (2.6738) grad: 0.0742 (0.0726) time: 0.4653 data: 0.0047 max mem: 22448 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 2.6665 (2.6748) grad: 0.0730 (0.0726) time: 0.4574 data: 0.0048 max mem: 22448 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 2.6595 (2.6739) grad: 0.0739 (0.0727) time: 0.4679 data: 0.0048 max mem: 22448 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 2.6595 (2.6750) grad: 0.0734 (0.0726) time: 0.4733 data: 0.0049 max mem: 22448 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.6467 (2.6733) grad: 0.0712 (0.0726) time: 0.4633 data: 0.0050 max mem: 22448 +train: [6] Total time: 0:03:08 (0.4706 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.6467 (2.6733) grad: 0.0712 (0.0726) +eval (validation): [6] [ 0/85] eta: 0:04:26 time: 3.1358 data: 2.8948 max mem: 22448 +eval (validation): [6] [20/85] eta: 0:00:30 time: 0.3293 data: 0.0045 max mem: 22448 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3417 data: 0.0037 max mem: 22448 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3431 data: 0.0042 max mem: 22448 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3540 data: 0.0043 max mem: 22448 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3495 data: 0.0042 max mem: 22448 +eval (validation): [6] Total time: 0:00:32 (0.3768 s / it) +cv: [6] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.477 acc: 0.269 f1: 0.200 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:28:44 lr: nan time: 4.3102 data: 3.9213 max mem: 22448 +train: [7] [ 20/400] eta: 0:04:02 lr: 0.000286 loss: 2.5902 (2.6308) grad: 0.0713 (0.0724) time: 0.4538 data: 0.0025 max mem: 22448 +train: [7] [ 40/400] eta: 0:03:18 lr: 0.000286 loss: 2.6679 (2.6449) grad: 0.0735 (0.0737) time: 0.4620 data: 0.0045 max mem: 22448 +train: [7] [ 60/400] eta: 0:02:59 lr: 0.000285 loss: 2.6840 (2.6456) grad: 0.0737 (0.0735) time: 0.4799 data: 0.0050 max mem: 22448 +train: [7] [ 80/400] eta: 0:02:43 lr: 0.000284 loss: 2.6459 (2.6380) grad: 0.0715 (0.0731) time: 0.4600 data: 0.0048 max mem: 22448 +train: [7] [100/400] eta: 0:02:30 lr: 0.000284 loss: 2.6459 (2.6412) grad: 0.0715 (0.0735) time: 0.4652 data: 0.0048 max mem: 22448 +train: [7] [120/400] eta: 0:02:18 lr: 0.000283 loss: 2.6492 (2.6423) grad: 0.0748 (0.0738) time: 0.4479 data: 0.0046 max mem: 22448 +train: [7] [140/400] eta: 0:02:07 lr: 0.000282 loss: 2.6301 (2.6383) grad: 0.0725 (0.0736) time: 0.4657 data: 0.0045 max mem: 22448 +train: [7] [160/400] eta: 0:01:56 lr: 0.000282 loss: 2.6334 (2.6431) grad: 0.0720 (0.0735) time: 0.4613 data: 0.0048 max mem: 22448 +train: [7] [180/400] eta: 0:01:46 lr: 0.000281 loss: 2.6678 (2.6481) grad: 0.0727 (0.0735) time: 0.4633 data: 0.0044 max mem: 22448 +train: [7] [200/400] eta: 0:01:36 lr: 0.000280 loss: 2.6402 (2.6453) grad: 0.0725 (0.0734) time: 0.4701 data: 0.0046 max mem: 22448 +train: [7] [220/400] eta: 0:01:26 lr: 0.000279 loss: 2.6194 (2.6489) grad: 0.0725 (0.0734) time: 0.4654 data: 0.0047 max mem: 22448 +train: [7] [240/400] eta: 0:01:16 lr: 0.000278 loss: 2.6602 (2.6482) grad: 0.0706 (0.0732) time: 0.4597 data: 0.0047 max mem: 22448 +train: [7] [260/400] eta: 0:01:06 lr: 0.000278 loss: 2.6404 (2.6510) grad: 0.0714 (0.0733) time: 0.4623 data: 0.0047 max mem: 22448 +train: [7] [280/400] eta: 0:00:57 lr: 0.000277 loss: 2.5967 (2.6481) grad: 0.0726 (0.0732) time: 0.4564 data: 0.0045 max mem: 22448 +train: [7] [300/400] eta: 0:00:47 lr: 0.000276 loss: 2.5818 (2.6446) grad: 0.0730 (0.0734) time: 0.4525 data: 0.0047 max mem: 22448 +train: [7] [320/400] eta: 0:00:37 lr: 0.000275 loss: 2.5795 (2.6434) grad: 0.0728 (0.0735) time: 0.4610 data: 0.0047 max mem: 22448 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 2.6187 (2.6422) grad: 0.0727 (0.0736) time: 0.4481 data: 0.0044 max mem: 22448 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 2.6197 (2.6385) grad: 0.0752 (0.0737) time: 0.4727 data: 0.0050 max mem: 22448 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 2.6220 (2.6384) grad: 0.0742 (0.0736) time: 0.4663 data: 0.0049 max mem: 22448 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.6095 (2.6383) grad: 0.0728 (0.0736) time: 0.4594 data: 0.0047 max mem: 22448 +train: [7] Total time: 0:03:08 (0.4718 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.6095 (2.6383) grad: 0.0728 (0.0736) +eval (validation): [7] [ 0/85] eta: 0:04:26 time: 3.1318 data: 2.8938 max mem: 22448 +eval (validation): [7] [20/85] eta: 0:00:32 time: 0.3754 data: 0.0044 max mem: 22448 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3413 data: 0.0035 max mem: 22448 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3472 data: 0.0043 max mem: 22448 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3590 data: 0.0041 max mem: 22448 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3473 data: 0.0040 max mem: 22448 +eval (validation): [7] Total time: 0:00:33 (0.3901 s / it) +cv: [7] best hparam: (2.7, 1.0) (030) ('030_lr2.7e+00_wd1.0e+00') loss: 2.460 acc: 0.266 f1: 0.204 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:23:05 lr: nan time: 3.4643 data: 3.0466 max mem: 22448 +train: [8] [ 20/400] eta: 0:03:45 lr: 0.000270 loss: 2.5330 (2.5594) grad: 0.0706 (0.0719) time: 0.4507 data: 0.0042 max mem: 22448 +train: [8] [ 40/400] eta: 0:03:10 lr: 0.000270 loss: 2.5677 (2.5860) grad: 0.0747 (0.0737) time: 0.4581 data: 0.0041 max mem: 22448 +train: [8] [ 60/400] eta: 0:02:52 lr: 0.000269 loss: 2.5798 (2.5908) grad: 0.0750 (0.0738) time: 0.4666 data: 0.0052 max mem: 22448 +train: [8] [ 80/400] eta: 0:02:38 lr: 0.000268 loss: 2.5908 (2.5921) grad: 0.0745 (0.0741) time: 0.4616 data: 0.0047 max mem: 22448 +train: [8] [100/400] eta: 0:02:26 lr: 0.000267 loss: 2.5989 (2.6005) grad: 0.0734 (0.0739) time: 0.4642 data: 0.0050 max mem: 22448 +train: [8] [120/400] eta: 0:02:15 lr: 0.000266 loss: 2.5555 (2.5884) grad: 0.0722 (0.0736) time: 0.4508 data: 0.0046 max mem: 22448 +train: [8] [140/400] eta: 0:02:04 lr: 0.000265 loss: 2.5497 (2.5831) grad: 0.0726 (0.0737) time: 0.4635 data: 0.0050 max mem: 22448 +train: [8] [160/400] eta: 0:01:54 lr: 0.000264 loss: 2.5567 (2.5818) grad: 0.0754 (0.0740) time: 0.4684 data: 0.0048 max mem: 22448 +train: [8] [180/400] eta: 0:01:44 lr: 0.000263 loss: 2.5381 (2.5765) grad: 0.0742 (0.0738) time: 0.4555 data: 0.0047 max mem: 22448 +train: [8] [200/400] eta: 0:01:35 lr: 0.000262 loss: 2.5287 (2.5744) grad: 0.0727 (0.0739) time: 0.4657 data: 0.0048 max mem: 22448 +train: [8] [220/400] eta: 0:01:25 lr: 0.000260 loss: 2.5674 (2.5756) grad: 0.0729 (0.0739) time: 0.4570 data: 0.0045 max mem: 22448 +train: [8] [240/400] eta: 0:01:15 lr: 0.000259 loss: 2.5676 (2.5742) grad: 0.0749 (0.0743) time: 0.4547 data: 0.0047 max mem: 22448 +train: [8] [260/400] eta: 0:01:05 lr: 0.000258 loss: 2.5744 (2.5760) grad: 0.0758 (0.0744) time: 0.4421 data: 0.0046 max mem: 22448 +train: [8] [280/400] eta: 0:00:56 lr: 0.000257 loss: 2.6201 (2.5784) grad: 0.0753 (0.0744) time: 0.4431 data: 0.0049 max mem: 22448 +train: [8] [300/400] eta: 0:00:46 lr: 0.000256 loss: 2.6201 (2.5821) grad: 0.0768 (0.0747) time: 0.4439 data: 0.0046 max mem: 22448 +train: [8] [320/400] eta: 0:00:37 lr: 0.000255 loss: 2.5931 (2.5824) grad: 0.0770 (0.0748) time: 0.4406 data: 0.0047 max mem: 22448 +train: [8] [340/400] eta: 0:00:27 lr: 0.000254 loss: 2.6014 (2.5837) grad: 0.0752 (0.0748) time: 0.4543 data: 0.0047 max mem: 22448 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 2.6076 (2.5844) grad: 0.0748 (0.0749) time: 0.4490 data: 0.0047 max mem: 22448 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 2.5897 (2.5842) grad: 0.0771 (0.0751) time: 0.4403 data: 0.0047 max mem: 22448 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.5891 (2.5849) grad: 0.0761 (0.0752) time: 0.4408 data: 0.0044 max mem: 22448 +train: [8] Total time: 0:03:04 (0.4617 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.5891 (2.5849) grad: 0.0761 (0.0752) +eval (validation): [8] [ 0/85] eta: 0:04:08 time: 2.9217 data: 2.6893 max mem: 22448 +eval (validation): [8] [20/85] eta: 0:00:29 time: 0.3261 data: 0.0036 max mem: 22448 +eval (validation): [8] [40/85] eta: 0:00:17 time: 0.3190 data: 0.0035 max mem: 22448 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3317 data: 0.0038 max mem: 22448 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3278 data: 0.0039 max mem: 22448 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3176 data: 0.0038 max mem: 22448 +eval (validation): [8] Total time: 0:00:30 (0.3585 s / it) +cv: [8] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.508 acc: 0.264 f1: 0.200 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:20:11 lr: nan time: 3.0279 data: 2.6957 max mem: 22448 +train: [9] [ 20/400] eta: 0:03:33 lr: 0.000249 loss: 2.5090 (2.5290) grad: 0.0730 (0.0739) time: 0.4380 data: 0.0034 max mem: 22448 +train: [9] [ 40/400] eta: 0:03:03 lr: 0.000248 loss: 2.5090 (2.5241) grad: 0.0730 (0.0751) time: 0.4540 data: 0.0047 max mem: 22448 +train: [9] [ 60/400] eta: 0:02:48 lr: 0.000247 loss: 2.5254 (2.5383) grad: 0.0751 (0.0753) time: 0.4716 data: 0.0049 max mem: 22448 +train: [9] [ 80/400] eta: 0:02:35 lr: 0.000246 loss: 2.5133 (2.5288) grad: 0.0744 (0.0748) time: 0.4520 data: 0.0051 max mem: 22448 +train: [9] [100/400] eta: 0:02:23 lr: 0.000244 loss: 2.4752 (2.5191) grad: 0.0731 (0.0749) time: 0.4500 data: 0.0046 max mem: 22448 +train: [9] [120/400] eta: 0:02:12 lr: 0.000243 loss: 2.5127 (2.5229) grad: 0.0739 (0.0748) time: 0.4525 data: 0.0048 max mem: 22448 +train: [9] [140/400] eta: 0:02:02 lr: 0.000242 loss: 2.5299 (2.5294) grad: 0.0747 (0.0751) time: 0.4559 data: 0.0050 max mem: 22448 +train: [9] [160/400] eta: 0:01:52 lr: 0.000241 loss: 2.5144 (2.5300) grad: 0.0750 (0.0752) time: 0.4580 data: 0.0049 max mem: 22448 +train: [9] [180/400] eta: 0:01:43 lr: 0.000240 loss: 2.5498 (2.5370) grad: 0.0740 (0.0750) time: 0.4556 data: 0.0049 max mem: 22448 +train: [9] [200/400] eta: 0:01:33 lr: 0.000238 loss: 2.5795 (2.5420) grad: 0.0740 (0.0751) time: 0.4558 data: 0.0046 max mem: 22448 +train: [9] [220/400] eta: 0:01:23 lr: 0.000237 loss: 2.5743 (2.5393) grad: 0.0756 (0.0752) time: 0.4617 data: 0.0048 max mem: 22448 +train: [9] [240/400] eta: 0:01:14 lr: 0.000236 loss: 2.5185 (2.5380) grad: 0.0756 (0.0754) time: 0.4643 data: 0.0050 max mem: 22448 +train: [9] [260/400] eta: 0:01:05 lr: 0.000234 loss: 2.5007 (2.5375) grad: 0.0762 (0.0755) time: 0.4567 data: 0.0048 max mem: 22448 +train: [9] [280/400] eta: 0:00:55 lr: 0.000233 loss: 2.5109 (2.5421) grad: 0.0763 (0.0758) time: 0.4549 data: 0.0049 max mem: 22448 +train: [9] [300/400] eta: 0:00:46 lr: 0.000232 loss: 2.5109 (2.5406) grad: 0.0773 (0.0758) time: 0.4677 data: 0.0049 max mem: 22448 +train: [9] [320/400] eta: 0:00:37 lr: 0.000230 loss: 2.5051 (2.5407) grad: 0.0773 (0.0761) time: 0.4593 data: 0.0047 max mem: 22448 +train: [9] [340/400] eta: 0:00:27 lr: 0.000229 loss: 2.5363 (2.5403) grad: 0.0784 (0.0762) time: 0.4583 data: 0.0046 max mem: 22448 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 2.5503 (2.5441) grad: 0.0805 (0.0765) time: 0.4591 data: 0.0047 max mem: 22448 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 2.5537 (2.5460) grad: 0.0786 (0.0765) time: 0.4545 data: 0.0048 max mem: 22448 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.5325 (2.5458) grad: 0.0755 (0.0764) time: 0.4623 data: 0.0048 max mem: 22448 +train: [9] Total time: 0:03:05 (0.4641 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.5325 (2.5458) grad: 0.0755 (0.0764) +eval (validation): [9] [ 0/85] eta: 0:04:23 time: 3.0977 data: 2.8294 max mem: 22448 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3549 data: 0.0076 max mem: 22448 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3465 data: 0.0034 max mem: 22448 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3632 data: 0.0045 max mem: 22448 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3410 data: 0.0042 max mem: 22448 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3296 data: 0.0040 max mem: 22448 +eval (validation): [9] Total time: 0:00:32 (0.3857 s / it) +cv: [9] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 2.437 acc: 0.269 f1: 0.203 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:20:27 lr: nan time: 3.0685 data: 2.7302 max mem: 22448 +train: [10] [ 20/400] eta: 0:03:34 lr: 0.000224 loss: 2.4668 (2.4752) grad: 0.0722 (0.0725) time: 0.4388 data: 0.0041 max mem: 22448 +train: [10] [ 40/400] eta: 0:03:04 lr: 0.000222 loss: 2.4909 (2.4864) grad: 0.0736 (0.0741) time: 0.4564 data: 0.0046 max mem: 22448 +train: [10] [ 60/400] eta: 0:02:49 lr: 0.000221 loss: 2.4738 (2.4874) grad: 0.0737 (0.0739) time: 0.4708 data: 0.0049 max mem: 22448 +train: [10] [ 80/400] eta: 0:02:36 lr: 0.000220 loss: 2.4815 (2.4954) grad: 0.0725 (0.0741) time: 0.4585 data: 0.0047 max mem: 22448 +train: [10] [100/400] eta: 0:02:23 lr: 0.000218 loss: 2.4981 (2.4969) grad: 0.0757 (0.0745) time: 0.4366 data: 0.0045 max mem: 22448 +train: [10] [120/400] eta: 0:02:12 lr: 0.000217 loss: 2.4895 (2.4992) grad: 0.0764 (0.0748) time: 0.4497 data: 0.0046 max mem: 22448 +train: [10] [140/400] eta: 0:02:02 lr: 0.000215 loss: 2.4714 (2.4938) grad: 0.0760 (0.0748) time: 0.4537 data: 0.0047 max mem: 22448 +train: [10] [160/400] eta: 0:01:52 lr: 0.000214 loss: 2.4718 (2.4941) grad: 0.0733 (0.0746) time: 0.4611 data: 0.0048 max mem: 22448 +train: [10] [180/400] eta: 0:01:42 lr: 0.000213 loss: 2.4761 (2.4926) grad: 0.0736 (0.0747) time: 0.4562 data: 0.0048 max mem: 22448 +train: [10] [200/400] eta: 0:01:33 lr: 0.000211 loss: 2.4612 (2.4911) grad: 0.0755 (0.0748) time: 0.4642 data: 0.0050 max mem: 22448 +train: [10] [220/400] eta: 0:01:23 lr: 0.000210 loss: 2.4612 (2.4892) grad: 0.0756 (0.0750) time: 0.4569 data: 0.0048 max mem: 22448 +train: [10] [240/400] eta: 0:01:14 lr: 0.000208 loss: 2.4405 (2.4879) grad: 0.0769 (0.0750) time: 0.4810 data: 0.0048 max mem: 22448 +train: [10] [260/400] eta: 0:01:05 lr: 0.000207 loss: 2.5118 (2.4960) grad: 0.0763 (0.0751) time: 0.4763 data: 0.0047 max mem: 22448 +train: [10] [280/400] eta: 0:00:56 lr: 0.000205 loss: 2.5435 (2.4979) grad: 0.0762 (0.0752) time: 0.4599 data: 0.0046 max mem: 22448 +train: [10] [300/400] eta: 0:00:46 lr: 0.000204 loss: 2.4939 (2.4979) grad: 0.0769 (0.0755) time: 0.4664 data: 0.0047 max mem: 22448 +train: [10] [320/400] eta: 0:00:37 lr: 0.000202 loss: 2.4845 (2.4994) grad: 0.0786 (0.0756) time: 0.4514 data: 0.0046 max mem: 22448 +train: [10] [340/400] eta: 0:00:28 lr: 0.000201 loss: 2.4852 (2.4986) grad: 0.0771 (0.0756) time: 0.4696 data: 0.0048 max mem: 22448 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.5028 (2.5009) grad: 0.0776 (0.0758) time: 0.4651 data: 0.0047 max mem: 22448 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 2.5184 (2.4992) grad: 0.0778 (0.0759) time: 0.4641 data: 0.0048 max mem: 22448 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.5248 (2.5016) grad: 0.0772 (0.0761) time: 0.4661 data: 0.0048 max mem: 22448 +train: [10] Total time: 0:03:06 (0.4672 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.5248 (2.5016) grad: 0.0772 (0.0761) +eval (validation): [10] [ 0/85] eta: 0:04:23 time: 3.0999 data: 2.8616 max mem: 22448 +eval (validation): [10] [20/85] eta: 0:00:32 time: 0.3768 data: 0.0042 max mem: 22448 +eval (validation): [10] [40/85] eta: 0:00:19 time: 0.3534 data: 0.0039 max mem: 22448 +eval (validation): [10] [60/85] eta: 0:00:10 time: 0.3712 data: 0.0048 max mem: 22448 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3600 data: 0.0044 max mem: 22448 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3495 data: 0.0043 max mem: 22448 +eval (validation): [10] Total time: 0:00:33 (0.3984 s / it) +cv: [10] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.428 acc: 0.274 f1: 0.201 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:21:56 lr: nan time: 3.2908 data: 2.8856 max mem: 22448 +train: [11] [ 20/400] eta: 0:03:49 lr: 0.000195 loss: 2.4146 (2.4420) grad: 0.0781 (0.0787) time: 0.4699 data: 0.0030 max mem: 22448 +train: [11] [ 40/400] eta: 0:03:10 lr: 0.000193 loss: 2.4146 (2.4327) grad: 0.0781 (0.0784) time: 0.4489 data: 0.0049 max mem: 22448 +train: [11] [ 60/400] eta: 0:02:52 lr: 0.000192 loss: 2.3894 (2.4386) grad: 0.0771 (0.0776) time: 0.4666 data: 0.0050 max mem: 22448 +train: [11] [ 80/400] eta: 0:02:38 lr: 0.000190 loss: 2.5066 (2.4536) grad: 0.0774 (0.0780) time: 0.4522 data: 0.0047 max mem: 22448 +train: [11] [100/400] eta: 0:02:25 lr: 0.000189 loss: 2.4458 (2.4436) grad: 0.0761 (0.0774) time: 0.4501 data: 0.0048 max mem: 22448 +train: [11] [120/400] eta: 0:02:14 lr: 0.000187 loss: 2.3998 (2.4406) grad: 0.0749 (0.0770) time: 0.4629 data: 0.0046 max mem: 22448 +train: [11] [140/400] eta: 0:02:04 lr: 0.000186 loss: 2.4654 (2.4431) grad: 0.0763 (0.0773) time: 0.4658 data: 0.0047 max mem: 22448 +train: [11] [160/400] eta: 0:01:54 lr: 0.000184 loss: 2.4574 (2.4438) grad: 0.0778 (0.0773) time: 0.4709 data: 0.0049 max mem: 22448 +train: [11] [180/400] eta: 0:01:44 lr: 0.000183 loss: 2.4394 (2.4456) grad: 0.0769 (0.0773) time: 0.4655 data: 0.0051 max mem: 22448 +train: [11] [200/400] eta: 0:01:35 lr: 0.000181 loss: 2.4449 (2.4477) grad: 0.0766 (0.0773) time: 0.4636 data: 0.0048 max mem: 22448 +train: [11] [220/400] eta: 0:01:25 lr: 0.000180 loss: 2.4369 (2.4463) grad: 0.0773 (0.0773) time: 0.4534 data: 0.0047 max mem: 22448 +train: [11] [240/400] eta: 0:01:15 lr: 0.000178 loss: 2.4547 (2.4512) grad: 0.0781 (0.0776) time: 0.4654 data: 0.0047 max mem: 22448 +train: [11] [260/400] eta: 0:01:06 lr: 0.000177 loss: 2.4796 (2.4540) grad: 0.0793 (0.0779) time: 0.4606 data: 0.0047 max mem: 22448 +train: [11] [280/400] eta: 0:00:56 lr: 0.000175 loss: 2.4443 (2.4537) grad: 0.0779 (0.0777) time: 0.4546 data: 0.0047 max mem: 22448 +train: [11] [300/400] eta: 0:00:46 lr: 0.000174 loss: 2.4443 (2.4531) grad: 0.0763 (0.0776) time: 0.4587 data: 0.0044 max mem: 22448 +train: [11] [320/400] eta: 0:00:37 lr: 0.000172 loss: 2.4606 (2.4553) grad: 0.0773 (0.0776) time: 0.4613 data: 0.0048 max mem: 22448 +train: [11] [340/400] eta: 0:00:28 lr: 0.000170 loss: 2.4448 (2.4544) grad: 0.0774 (0.0775) time: 0.4639 data: 0.0044 max mem: 22448 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 2.4565 (2.4553) grad: 0.0771 (0.0776) time: 0.4645 data: 0.0048 max mem: 22448 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 2.4624 (2.4570) grad: 0.0770 (0.0775) time: 0.4661 data: 0.0048 max mem: 22448 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.4621 (2.4566) grad: 0.0765 (0.0775) time: 0.4597 data: 0.0046 max mem: 22448 +train: [11] Total time: 0:03:07 (0.4689 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.4621 (2.4566) grad: 0.0765 (0.0775) +eval (validation): [11] [ 0/85] eta: 0:04:24 time: 3.1079 data: 2.8321 max mem: 22448 +eval (validation): [11] [20/85] eta: 0:00:32 time: 0.3671 data: 0.0043 max mem: 22448 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3537 data: 0.0043 max mem: 22448 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3424 data: 0.0042 max mem: 22448 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3344 data: 0.0044 max mem: 22448 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3276 data: 0.0043 max mem: 22448 +eval (validation): [11] Total time: 0:00:32 (0.3831 s / it) +cv: [11] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.433 acc: 0.271 f1: 0.201 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:05 lr: nan time: 3.3130 data: 2.9420 max mem: 22448 +train: [12] [ 20/400] eta: 0:03:51 lr: 0.000164 loss: 2.3837 (2.4178) grad: 0.0741 (0.0751) time: 0.4745 data: 0.0047 max mem: 22448 +train: [12] [ 40/400] eta: 0:03:11 lr: 0.000163 loss: 2.3837 (2.3999) grad: 0.0741 (0.0755) time: 0.4481 data: 0.0047 max mem: 22448 +train: [12] [ 60/400] eta: 0:02:52 lr: 0.000161 loss: 2.4389 (2.4245) grad: 0.0747 (0.0758) time: 0.4602 data: 0.0051 max mem: 22448 +train: [12] [ 80/400] eta: 0:02:37 lr: 0.000160 loss: 2.4229 (2.4157) grad: 0.0753 (0.0761) time: 0.4458 data: 0.0047 max mem: 22448 +train: [12] [100/400] eta: 0:02:25 lr: 0.000158 loss: 2.3978 (2.4096) grad: 0.0785 (0.0764) time: 0.4632 data: 0.0047 max mem: 22448 +train: [12] [120/400] eta: 0:02:14 lr: 0.000156 loss: 2.4367 (2.4220) grad: 0.0791 (0.0767) time: 0.4595 data: 0.0048 max mem: 22448 +train: [12] [140/400] eta: 0:02:04 lr: 0.000155 loss: 2.4719 (2.4279) grad: 0.0780 (0.0769) time: 0.4543 data: 0.0048 max mem: 22448 +train: [12] [160/400] eta: 0:01:54 lr: 0.000153 loss: 2.4326 (2.4305) grad: 0.0780 (0.0771) time: 0.4619 data: 0.0049 max mem: 22448 +train: [12] [180/400] eta: 0:01:44 lr: 0.000152 loss: 2.3995 (2.4261) grad: 0.0781 (0.0774) time: 0.4559 data: 0.0046 max mem: 22448 +train: [12] [200/400] eta: 0:01:34 lr: 0.000150 loss: 2.4101 (2.4277) grad: 0.0783 (0.0774) time: 0.4617 data: 0.0049 max mem: 22448 +train: [12] [220/400] eta: 0:01:24 lr: 0.000149 loss: 2.4356 (2.4262) grad: 0.0786 (0.0776) time: 0.4610 data: 0.0050 max mem: 22448 +train: [12] [240/400] eta: 0:01:15 lr: 0.000147 loss: 2.4057 (2.4232) grad: 0.0778 (0.0775) time: 0.4589 data: 0.0049 max mem: 22448 +train: [12] [260/400] eta: 0:01:05 lr: 0.000145 loss: 2.3717 (2.4191) grad: 0.0757 (0.0775) time: 0.4512 data: 0.0047 max mem: 22448 +train: [12] [280/400] eta: 0:00:56 lr: 0.000144 loss: 2.4070 (2.4234) grad: 0.0759 (0.0775) time: 0.4470 data: 0.0046 max mem: 22448 +train: [12] [300/400] eta: 0:00:46 lr: 0.000142 loss: 2.4414 (2.4246) grad: 0.0768 (0.0774) time: 0.4594 data: 0.0048 max mem: 22448 +train: [12] [320/400] eta: 0:00:37 lr: 0.000141 loss: 2.3969 (2.4270) grad: 0.0784 (0.0776) time: 0.4566 data: 0.0047 max mem: 22448 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 2.4396 (2.4277) grad: 0.0791 (0.0776) time: 0.4568 data: 0.0047 max mem: 22448 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 2.4093 (2.4252) grad: 0.0781 (0.0777) time: 0.4613 data: 0.0047 max mem: 22448 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 2.4148 (2.4283) grad: 0.0792 (0.0778) time: 0.4600 data: 0.0047 max mem: 22448 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.4703 (2.4302) grad: 0.0794 (0.0779) time: 0.4561 data: 0.0048 max mem: 22448 +train: [12] Total time: 0:03:06 (0.4654 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.4703 (2.4302) grad: 0.0794 (0.0779) +eval (validation): [12] [ 0/85] eta: 0:04:37 time: 3.2682 data: 2.9732 max mem: 22448 +eval (validation): [12] [20/85] eta: 0:00:35 time: 0.4078 data: 0.0062 max mem: 22448 +eval (validation): [12] [40/85] eta: 0:00:20 time: 0.3426 data: 0.0034 max mem: 22448 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3575 data: 0.0043 max mem: 22448 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3398 data: 0.0040 max mem: 22448 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3306 data: 0.0039 max mem: 22448 +eval (validation): [12] Total time: 0:00:33 (0.3973 s / it) +cv: [12] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 2.436 acc: 0.270 f1: 0.205 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:22:36 lr: nan time: 3.3920 data: 3.0359 max mem: 22448 +train: [13] [ 20/400] eta: 0:03:47 lr: 0.000133 loss: 2.3725 (2.4061) grad: 0.0745 (0.0755) time: 0.4591 data: 0.0038 max mem: 22448 +train: [13] [ 40/400] eta: 0:03:09 lr: 0.000131 loss: 2.3119 (2.3466) grad: 0.0730 (0.0744) time: 0.4505 data: 0.0046 max mem: 22448 +train: [13] [ 60/400] eta: 0:02:51 lr: 0.000130 loss: 2.3147 (2.3579) grad: 0.0756 (0.0752) time: 0.4582 data: 0.0049 max mem: 22448 +train: [13] [ 80/400] eta: 0:02:37 lr: 0.000128 loss: 2.3585 (2.3586) grad: 0.0780 (0.0761) time: 0.4560 data: 0.0050 max mem: 22448 +train: [13] [100/400] eta: 0:02:25 lr: 0.000127 loss: 2.4069 (2.3724) grad: 0.0769 (0.0762) time: 0.4609 data: 0.0049 max mem: 22448 +train: [13] [120/400] eta: 0:02:14 lr: 0.000125 loss: 2.4012 (2.3654) grad: 0.0763 (0.0763) time: 0.4538 data: 0.0049 max mem: 22448 +train: [13] [140/400] eta: 0:02:04 lr: 0.000124 loss: 2.3198 (2.3609) grad: 0.0763 (0.0764) time: 0.4593 data: 0.0049 max mem: 22448 +train: [13] [160/400] eta: 0:01:54 lr: 0.000122 loss: 2.3453 (2.3669) grad: 0.0760 (0.0766) time: 0.4568 data: 0.0047 max mem: 22448 +train: [13] [180/400] eta: 0:01:44 lr: 0.000120 loss: 2.4238 (2.3734) grad: 0.0778 (0.0768) time: 0.4551 data: 0.0050 max mem: 22448 +train: [13] [200/400] eta: 0:01:34 lr: 0.000119 loss: 2.3939 (2.3721) grad: 0.0773 (0.0769) time: 0.4575 data: 0.0049 max mem: 22448 +train: [13] [220/400] eta: 0:01:24 lr: 0.000117 loss: 2.3943 (2.3751) grad: 0.0773 (0.0769) time: 0.4576 data: 0.0048 max mem: 22448 +train: [13] [240/400] eta: 0:01:15 lr: 0.000116 loss: 2.4063 (2.3773) grad: 0.0772 (0.0770) time: 0.4560 data: 0.0051 max mem: 22448 +train: [13] [260/400] eta: 0:01:05 lr: 0.000114 loss: 2.4135 (2.3799) grad: 0.0771 (0.0769) time: 0.4448 data: 0.0046 max mem: 22448 +train: [13] [280/400] eta: 0:00:55 lr: 0.000113 loss: 2.3779 (2.3781) grad: 0.0770 (0.0770) time: 0.4448 data: 0.0046 max mem: 22448 +train: [13] [300/400] eta: 0:00:46 lr: 0.000111 loss: 2.3536 (2.3761) grad: 0.0764 (0.0770) time: 0.4717 data: 0.0049 max mem: 22448 +train: [13] [320/400] eta: 0:00:37 lr: 0.000110 loss: 2.3395 (2.3775) grad: 0.0773 (0.0772) time: 0.4564 data: 0.0048 max mem: 22448 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 2.3593 (2.3772) grad: 0.0803 (0.0774) time: 0.4447 data: 0.0047 max mem: 22448 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 2.3983 (2.3793) grad: 0.0803 (0.0774) time: 0.4567 data: 0.0048 max mem: 22448 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 2.3983 (2.3790) grad: 0.0787 (0.0775) time: 0.4527 data: 0.0047 max mem: 22448 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.3721 (2.3810) grad: 0.0788 (0.0775) time: 0.4646 data: 0.0047 max mem: 22448 +train: [13] Total time: 0:03:05 (0.4637 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.3721 (2.3810) grad: 0.0788 (0.0775) +eval (validation): [13] [ 0/85] eta: 0:04:48 time: 3.3956 data: 3.0875 max mem: 22448 +eval (validation): [13] [20/85] eta: 0:00:34 time: 0.3839 data: 0.0035 max mem: 22448 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3332 data: 0.0037 max mem: 22448 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3405 data: 0.0042 max mem: 22448 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3545 data: 0.0044 max mem: 22448 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3401 data: 0.0044 max mem: 22448 +eval (validation): [13] Total time: 0:00:33 (0.3914 s / it) +cv: [13] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.428 acc: 0.271 f1: 0.208 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:23:07 lr: nan time: 3.4682 data: 3.0551 max mem: 22448 +train: [14] [ 20/400] eta: 0:03:50 lr: 0.000102 loss: 2.2833 (2.3062) grad: 0.0753 (0.0748) time: 0.4628 data: 0.0040 max mem: 22448 +train: [14] [ 40/400] eta: 0:03:07 lr: 0.000101 loss: 2.3630 (2.3456) grad: 0.0752 (0.0753) time: 0.4320 data: 0.0042 max mem: 22448 +train: [14] [ 60/400] eta: 0:02:50 lr: 0.000099 loss: 2.3715 (2.3467) grad: 0.0757 (0.0761) time: 0.4608 data: 0.0047 max mem: 22448 +train: [14] [ 80/400] eta: 0:02:36 lr: 0.000098 loss: 2.3555 (2.3513) grad: 0.0780 (0.0767) time: 0.4472 data: 0.0048 max mem: 22448 +train: [14] [100/400] eta: 0:02:23 lr: 0.000096 loss: 2.3555 (2.3513) grad: 0.0780 (0.0768) time: 0.4463 data: 0.0050 max mem: 22448 +train: [14] [120/400] eta: 0:02:13 lr: 0.000095 loss: 2.3271 (2.3462) grad: 0.0764 (0.0768) time: 0.4520 data: 0.0048 max mem: 22448 +train: [14] [140/400] eta: 0:02:02 lr: 0.000093 loss: 2.3279 (2.3439) grad: 0.0771 (0.0772) time: 0.4551 data: 0.0049 max mem: 22448 +train: [14] [160/400] eta: 0:01:52 lr: 0.000092 loss: 2.3429 (2.3413) grad: 0.0773 (0.0771) time: 0.4540 data: 0.0047 max mem: 22448 +train: [14] [180/400] eta: 0:01:42 lr: 0.000090 loss: 2.3145 (2.3353) grad: 0.0771 (0.0772) time: 0.4501 data: 0.0053 max mem: 22448 +train: [14] [200/400] eta: 0:01:33 lr: 0.000089 loss: 2.2757 (2.3317) grad: 0.0777 (0.0773) time: 0.4499 data: 0.0043 max mem: 22448 +train: [14] [220/400] eta: 0:01:23 lr: 0.000088 loss: 2.3385 (2.3368) grad: 0.0774 (0.0774) time: 0.4572 data: 0.0051 max mem: 22448 +train: [14] [240/400] eta: 0:01:14 lr: 0.000086 loss: 2.3422 (2.3370) grad: 0.0774 (0.0775) time: 0.4616 data: 0.0048 max mem: 22448 +train: [14] [260/400] eta: 0:01:04 lr: 0.000085 loss: 2.2935 (2.3339) grad: 0.0775 (0.0775) time: 0.4541 data: 0.0047 max mem: 22448 +train: [14] [280/400] eta: 0:00:55 lr: 0.000083 loss: 2.3034 (2.3376) grad: 0.0783 (0.0777) time: 0.4566 data: 0.0050 max mem: 22448 +train: [14] [300/400] eta: 0:00:46 lr: 0.000082 loss: 2.3524 (2.3405) grad: 0.0781 (0.0777) time: 0.4555 data: 0.0049 max mem: 22448 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 2.3524 (2.3433) grad: 0.0784 (0.0778) time: 0.4622 data: 0.0049 max mem: 22448 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 2.3464 (2.3421) grad: 0.0787 (0.0778) time: 0.4623 data: 0.0048 max mem: 22448 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 2.3163 (2.3405) grad: 0.0771 (0.0778) time: 0.4581 data: 0.0049 max mem: 22448 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 2.3163 (2.3420) grad: 0.0764 (0.0777) time: 0.4506 data: 0.0047 max mem: 22448 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.3525 (2.3433) grad: 0.0777 (0.0778) time: 0.4658 data: 0.0047 max mem: 22448 +train: [14] Total time: 0:03:05 (0.4629 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.3525 (2.3433) grad: 0.0777 (0.0778) +eval (validation): [14] [ 0/85] eta: 0:04:26 time: 3.1309 data: 2.8843 max mem: 22448 +eval (validation): [14] [20/85] eta: 0:00:30 time: 0.3412 data: 0.0043 max mem: 22448 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3301 data: 0.0035 max mem: 22448 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3498 data: 0.0043 max mem: 22448 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3628 data: 0.0043 max mem: 22448 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3470 data: 0.0040 max mem: 22448 +eval (validation): [14] Total time: 0:00:32 (0.3801 s / it) +cv: [14] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.427 acc: 0.271 f1: 0.204 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:46 lr: nan time: 3.4164 data: 3.0469 max mem: 22448 +train: [15] [ 20/400] eta: 0:03:56 lr: 0.000074 loss: 2.2063 (2.2770) grad: 0.0750 (0.0751) time: 0.4834 data: 0.0030 max mem: 22448 +train: [15] [ 40/400] eta: 0:03:13 lr: 0.000072 loss: 2.2915 (2.3005) grad: 0.0751 (0.0758) time: 0.4465 data: 0.0047 max mem: 22448 +train: [15] [ 60/400] eta: 0:02:55 lr: 0.000071 loss: 2.3571 (2.3185) grad: 0.0778 (0.0763) time: 0.4733 data: 0.0050 max mem: 22448 +train: [15] [ 80/400] eta: 0:02:40 lr: 0.000070 loss: 2.3563 (2.3178) grad: 0.0778 (0.0770) time: 0.4557 data: 0.0049 max mem: 22448 +train: [15] [100/400] eta: 0:02:28 lr: 0.000068 loss: 2.2613 (2.3087) grad: 0.0784 (0.0772) time: 0.4624 data: 0.0048 max mem: 22448 +train: [15] [120/400] eta: 0:02:16 lr: 0.000067 loss: 2.3051 (2.3110) grad: 0.0784 (0.0772) time: 0.4533 data: 0.0048 max mem: 22448 +train: [15] [140/400] eta: 0:02:05 lr: 0.000066 loss: 2.3128 (2.3121) grad: 0.0774 (0.0773) time: 0.4683 data: 0.0049 max mem: 22448 +train: [15] [160/400] eta: 0:01:55 lr: 0.000064 loss: 2.3128 (2.3160) grad: 0.0787 (0.0777) time: 0.4646 data: 0.0048 max mem: 22448 +train: [15] [180/400] eta: 0:01:45 lr: 0.000063 loss: 2.3089 (2.3127) grad: 0.0787 (0.0777) time: 0.4606 data: 0.0049 max mem: 22448 +train: [15] [200/400] eta: 0:01:35 lr: 0.000062 loss: 2.3089 (2.3126) grad: 0.0780 (0.0777) time: 0.4583 data: 0.0048 max mem: 22448 +train: [15] [220/400] eta: 0:01:25 lr: 0.000061 loss: 2.3554 (2.3169) grad: 0.0793 (0.0778) time: 0.4620 data: 0.0049 max mem: 22448 +train: [15] [240/400] eta: 0:01:15 lr: 0.000059 loss: 2.3020 (2.3151) grad: 0.0779 (0.0779) time: 0.4547 data: 0.0045 max mem: 22448 +train: [15] [260/400] eta: 0:01:06 lr: 0.000058 loss: 2.2935 (2.3169) grad: 0.0774 (0.0780) time: 0.4528 data: 0.0046 max mem: 22448 +train: [15] [280/400] eta: 0:00:56 lr: 0.000057 loss: 2.3222 (2.3198) grad: 0.0808 (0.0782) time: 0.4543 data: 0.0046 max mem: 22448 +train: [15] [300/400] eta: 0:00:47 lr: 0.000056 loss: 2.3364 (2.3205) grad: 0.0780 (0.0781) time: 0.4627 data: 0.0045 max mem: 22448 +train: [15] [320/400] eta: 0:00:37 lr: 0.000054 loss: 2.3231 (2.3211) grad: 0.0779 (0.0782) time: 0.4516 data: 0.0046 max mem: 22448 +train: [15] [340/400] eta: 0:00:28 lr: 0.000053 loss: 2.3237 (2.3248) grad: 0.0805 (0.0784) time: 0.4513 data: 0.0048 max mem: 22448 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 2.3665 (2.3258) grad: 0.0785 (0.0784) time: 0.4584 data: 0.0047 max mem: 22448 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.3606 (2.3254) grad: 0.0775 (0.0783) time: 0.4675 data: 0.0049 max mem: 22448 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.3120 (2.3237) grad: 0.0776 (0.0783) time: 0.4645 data: 0.0048 max mem: 22448 +train: [15] Total time: 0:03:07 (0.4683 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.3120 (2.3237) grad: 0.0776 (0.0783) +eval (validation): [15] [ 0/85] eta: 0:04:23 time: 3.0973 data: 2.8405 max mem: 22448 +eval (validation): [15] [20/85] eta: 0:00:30 time: 0.3420 data: 0.0042 max mem: 22448 +eval (validation): [15] [40/85] eta: 0:00:18 time: 0.3446 data: 0.0037 max mem: 22448 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3648 data: 0.0045 max mem: 22448 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3420 data: 0.0042 max mem: 22448 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3325 data: 0.0042 max mem: 22448 +eval (validation): [15] Total time: 0:00:32 (0.3823 s / it) +cv: [15] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 2.452 acc: 0.270 f1: 0.208 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:54 lr: nan time: 3.4372 data: 3.0163 max mem: 22448 +train: [16] [ 20/400] eta: 0:03:53 lr: 0.000048 loss: 2.2578 (2.2678) grad: 0.0790 (0.0788) time: 0.4733 data: 0.0028 max mem: 22448 +train: [16] [ 40/400] eta: 0:03:14 lr: 0.000047 loss: 2.2854 (2.2921) grad: 0.0798 (0.0794) time: 0.4642 data: 0.0048 max mem: 22448 +train: [16] [ 60/400] eta: 0:02:55 lr: 0.000046 loss: 2.2854 (2.2912) grad: 0.0784 (0.0789) time: 0.4607 data: 0.0050 max mem: 22448 +train: [16] [ 80/400] eta: 0:02:40 lr: 0.000045 loss: 2.2725 (2.2911) grad: 0.0777 (0.0789) time: 0.4644 data: 0.0050 max mem: 22448 +train: [16] [100/400] eta: 0:02:27 lr: 0.000044 loss: 2.2915 (2.2921) grad: 0.0769 (0.0783) time: 0.4506 data: 0.0046 max mem: 22448 +train: [16] [120/400] eta: 0:02:16 lr: 0.000043 loss: 2.2741 (2.2898) grad: 0.0769 (0.0786) time: 0.4587 data: 0.0048 max mem: 22448 +train: [16] [140/400] eta: 0:02:05 lr: 0.000042 loss: 2.2640 (2.2829) grad: 0.0784 (0.0784) time: 0.4588 data: 0.0049 max mem: 22448 +train: [16] [160/400] eta: 0:01:55 lr: 0.000041 loss: 2.2308 (2.2815) grad: 0.0768 (0.0782) time: 0.4598 data: 0.0049 max mem: 22448 +train: [16] [180/400] eta: 0:01:44 lr: 0.000040 loss: 2.2409 (2.2784) grad: 0.0765 (0.0782) time: 0.4468 data: 0.0047 max mem: 22448 +train: [16] [200/400] eta: 0:01:34 lr: 0.000039 loss: 2.2409 (2.2747) grad: 0.0771 (0.0781) time: 0.4605 data: 0.0050 max mem: 22448 +train: [16] [220/400] eta: 0:01:25 lr: 0.000038 loss: 2.2512 (2.2794) grad: 0.0775 (0.0782) time: 0.4678 data: 0.0051 max mem: 22448 +train: [16] [240/400] eta: 0:01:15 lr: 0.000036 loss: 2.3145 (2.2834) grad: 0.0769 (0.0781) time: 0.4507 data: 0.0045 max mem: 22448 +train: [16] [260/400] eta: 0:01:05 lr: 0.000035 loss: 2.2974 (2.2807) grad: 0.0769 (0.0781) time: 0.4560 data: 0.0050 max mem: 22448 +train: [16] [280/400] eta: 0:00:56 lr: 0.000034 loss: 2.3017 (2.2832) grad: 0.0778 (0.0782) time: 0.4593 data: 0.0050 max mem: 22448 +train: [16] [300/400] eta: 0:00:46 lr: 0.000033 loss: 2.3016 (2.2825) grad: 0.0790 (0.0782) time: 0.4535 data: 0.0052 max mem: 22448 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 2.2664 (2.2821) grad: 0.0784 (0.0782) time: 0.4619 data: 0.0049 max mem: 22448 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 2.2977 (2.2838) grad: 0.0765 (0.0780) time: 0.4574 data: 0.0049 max mem: 22448 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 2.3215 (2.2852) grad: 0.0770 (0.0780) time: 0.4600 data: 0.0047 max mem: 22448 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 2.2463 (2.2820) grad: 0.0780 (0.0779) time: 0.4597 data: 0.0049 max mem: 22448 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.2463 (2.2816) grad: 0.0765 (0.0779) time: 0.4620 data: 0.0048 max mem: 22448 +train: [16] Total time: 0:03:06 (0.4673 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.2463 (2.2816) grad: 0.0765 (0.0779) +eval (validation): [16] [ 0/85] eta: 0:04:29 time: 3.1692 data: 2.8927 max mem: 22448 +eval (validation): [16] [20/85] eta: 0:00:35 time: 0.4156 data: 0.0057 max mem: 22448 +eval (validation): [16] [40/85] eta: 0:00:21 time: 0.3928 data: 0.0041 max mem: 22448 +eval (validation): [16] [60/85] eta: 0:00:10 time: 0.3736 data: 0.0044 max mem: 22448 +eval (validation): [16] [80/85] eta: 0:00:02 time: 0.3545 data: 0.0047 max mem: 22448 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3324 data: 0.0045 max mem: 22448 +eval (validation): [16] Total time: 0:00:35 (0.4173 s / it) +cv: [16] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.435 acc: 0.270 f1: 0.203 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:20:59 lr: nan time: 3.1480 data: 2.7669 max mem: 22448 +train: [17] [ 20/400] eta: 0:03:45 lr: 0.000028 loss: 2.2001 (2.2109) grad: 0.0756 (0.0777) time: 0.4664 data: 0.0226 max mem: 22448 +train: [17] [ 40/400] eta: 0:03:10 lr: 0.000027 loss: 2.2197 (2.2403) grad: 0.0772 (0.0776) time: 0.4601 data: 0.0044 max mem: 22448 +train: [17] [ 60/400] eta: 0:02:50 lr: 0.000026 loss: 2.2890 (2.2586) grad: 0.0772 (0.0777) time: 0.4497 data: 0.0046 max mem: 22448 +train: [17] [ 80/400] eta: 0:02:37 lr: 0.000025 loss: 2.2452 (2.2441) grad: 0.0767 (0.0775) time: 0.4592 data: 0.0047 max mem: 22448 +train: [17] [100/400] eta: 0:02:25 lr: 0.000024 loss: 2.1972 (2.2509) grad: 0.0759 (0.0772) time: 0.4626 data: 0.0047 max mem: 22448 +train: [17] [120/400] eta: 0:02:14 lr: 0.000023 loss: 2.2763 (2.2511) grad: 0.0757 (0.0770) time: 0.4519 data: 0.0048 max mem: 22448 +train: [17] [140/400] eta: 0:02:04 lr: 0.000023 loss: 2.2763 (2.2617) grad: 0.0773 (0.0774) time: 0.4577 data: 0.0047 max mem: 22448 +train: [17] [160/400] eta: 0:01:53 lr: 0.000022 loss: 2.2707 (2.2612) grad: 0.0790 (0.0775) time: 0.4540 data: 0.0048 max mem: 22448 +train: [17] [180/400] eta: 0:01:43 lr: 0.000021 loss: 2.2430 (2.2631) grad: 0.0777 (0.0773) time: 0.4514 data: 0.0047 max mem: 22448 +train: [17] [200/400] eta: 0:01:33 lr: 0.000020 loss: 2.2554 (2.2639) grad: 0.0752 (0.0772) time: 0.4410 data: 0.0047 max mem: 22448 +train: [17] [220/400] eta: 0:01:23 lr: 0.000019 loss: 2.2762 (2.2647) grad: 0.0759 (0.0773) time: 0.4372 data: 0.0045 max mem: 22448 +train: [17] [240/400] eta: 0:01:14 lr: 0.000019 loss: 2.2293 (2.2630) grad: 0.0789 (0.0773) time: 0.4324 data: 0.0047 max mem: 22448 +train: [17] [260/400] eta: 0:01:04 lr: 0.000018 loss: 2.2554 (2.2619) grad: 0.0780 (0.0773) time: 0.4338 data: 0.0046 max mem: 22448 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 2.2241 (2.2590) grad: 0.0762 (0.0773) time: 0.4371 data: 0.0046 max mem: 22448 +train: [17] [300/400] eta: 0:00:45 lr: 0.000016 loss: 2.2390 (2.2591) grad: 0.0765 (0.0774) time: 0.4503 data: 0.0046 max mem: 22448 +train: [17] [320/400] eta: 0:00:36 lr: 0.000016 loss: 2.2502 (2.2577) grad: 0.0770 (0.0773) time: 0.4470 data: 0.0048 max mem: 22448 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 2.2308 (2.2595) grad: 0.0758 (0.0773) time: 0.4433 data: 0.0047 max mem: 22448 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 2.2830 (2.2596) grad: 0.0771 (0.0773) time: 0.4415 data: 0.0048 max mem: 22448 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 2.2591 (2.2597) grad: 0.0773 (0.0773) time: 0.4413 data: 0.0048 max mem: 22448 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.2311 (2.2599) grad: 0.0779 (0.0773) time: 0.4400 data: 0.0047 max mem: 22448 +train: [17] Total time: 0:03:02 (0.4552 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.2311 (2.2599) grad: 0.0779 (0.0773) +eval (validation): [17] [ 0/85] eta: 0:04:18 time: 3.0459 data: 2.8115 max mem: 22448 +eval (validation): [17] [20/85] eta: 0:00:30 time: 0.3461 data: 0.0032 max mem: 22448 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3530 data: 0.0035 max mem: 22448 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3617 data: 0.0043 max mem: 22448 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3397 data: 0.0043 max mem: 22448 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3258 data: 0.0041 max mem: 22448 +eval (validation): [17] Total time: 0:00:32 (0.3827 s / it) +cv: [17] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.434 acc: 0.271 f1: 0.204 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:20:04 lr: nan time: 3.0115 data: 2.6829 max mem: 22448 +train: [18] [ 20/400] eta: 0:03:33 lr: 0.000012 loss: 2.2560 (2.2737) grad: 0.0760 (0.0771) time: 0.4401 data: 0.0038 max mem: 22448 +train: [18] [ 40/400] eta: 0:03:02 lr: 0.000012 loss: 2.2560 (2.2576) grad: 0.0766 (0.0771) time: 0.4485 data: 0.0047 max mem: 22448 +train: [18] [ 60/400] eta: 0:02:46 lr: 0.000011 loss: 2.2353 (2.2629) grad: 0.0767 (0.0772) time: 0.4504 data: 0.0048 max mem: 22448 +train: [18] [ 80/400] eta: 0:02:32 lr: 0.000011 loss: 2.2271 (2.2580) grad: 0.0767 (0.0771) time: 0.4465 data: 0.0047 max mem: 22448 +train: [18] [100/400] eta: 0:02:22 lr: 0.000010 loss: 2.2222 (2.2578) grad: 0.0753 (0.0766) time: 0.4553 data: 0.0047 max mem: 22448 +train: [18] [120/400] eta: 0:02:12 lr: 0.000009 loss: 2.2222 (2.2520) grad: 0.0753 (0.0764) time: 0.4633 data: 0.0050 max mem: 22448 +train: [18] [140/400] eta: 0:02:01 lr: 0.000009 loss: 2.2163 (2.2461) grad: 0.0766 (0.0765) time: 0.4512 data: 0.0048 max mem: 22448 +train: [18] [160/400] eta: 0:01:52 lr: 0.000008 loss: 2.2024 (2.2454) grad: 0.0766 (0.0767) time: 0.4563 data: 0.0047 max mem: 22448 +train: [18] [180/400] eta: 0:01:42 lr: 0.000008 loss: 2.2200 (2.2478) grad: 0.0760 (0.0766) time: 0.4507 data: 0.0049 max mem: 22448 +train: [18] [200/400] eta: 0:01:32 lr: 0.000007 loss: 2.2200 (2.2416) grad: 0.0747 (0.0765) time: 0.4554 data: 0.0051 max mem: 22448 +train: [18] [220/400] eta: 0:01:23 lr: 0.000007 loss: 2.2065 (2.2393) grad: 0.0755 (0.0765) time: 0.4615 data: 0.0048 max mem: 22448 +train: [18] [240/400] eta: 0:01:14 lr: 0.000006 loss: 2.2082 (2.2400) grad: 0.0756 (0.0764) time: 0.4502 data: 0.0048 max mem: 22448 +train: [18] [260/400] eta: 0:01:04 lr: 0.000006 loss: 2.2414 (2.2420) grad: 0.0755 (0.0765) time: 0.4575 data: 0.0048 max mem: 22448 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 2.2555 (2.2419) grad: 0.0755 (0.0766) time: 0.4533 data: 0.0050 max mem: 22448 +train: [18] [300/400] eta: 0:00:46 lr: 0.000005 loss: 2.2453 (2.2410) grad: 0.0759 (0.0766) time: 0.4544 data: 0.0049 max mem: 22448 +train: [18] [320/400] eta: 0:00:36 lr: 0.000005 loss: 2.2319 (2.2393) grad: 0.0762 (0.0766) time: 0.4576 data: 0.0047 max mem: 22448 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 2.1990 (2.2372) grad: 0.0779 (0.0766) time: 0.4576 data: 0.0049 max mem: 22448 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 2.2004 (2.2335) grad: 0.0747 (0.0765) time: 0.4605 data: 0.0048 max mem: 22448 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 2.2208 (2.2360) grad: 0.0735 (0.0764) time: 0.4634 data: 0.0050 max mem: 22448 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.2306 (2.2339) grad: 0.0751 (0.0765) time: 0.4787 data: 0.0050 max mem: 22448 +train: [18] Total time: 0:03:05 (0.4625 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.2306 (2.2339) grad: 0.0751 (0.0765) +eval (validation): [18] [ 0/85] eta: 0:04:24 time: 3.1155 data: 2.8772 max mem: 22448 +eval (validation): [18] [20/85] eta: 0:00:30 time: 0.3306 data: 0.0039 max mem: 22448 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3481 data: 0.0032 max mem: 22448 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3570 data: 0.0039 max mem: 22448 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3315 data: 0.0042 max mem: 22448 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3213 data: 0.0042 max mem: 22448 +eval (validation): [18] Total time: 0:00:31 (0.3753 s / it) +cv: [18] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.434 acc: 0.272 f1: 0.204 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:20:40 lr: nan time: 3.1016 data: 2.7143 max mem: 22448 +train: [19] [ 20/400] eta: 0:03:37 lr: 0.000003 loss: 2.2118 (2.2141) grad: 0.0752 (0.0759) time: 0.4457 data: 0.0038 max mem: 22448 +train: [19] [ 40/400] eta: 0:03:06 lr: 0.000003 loss: 2.2139 (2.2278) grad: 0.0756 (0.0762) time: 0.4591 data: 0.0049 max mem: 22448 +train: [19] [ 60/400] eta: 0:02:49 lr: 0.000002 loss: 2.2501 (2.2265) grad: 0.0758 (0.0764) time: 0.4562 data: 0.0050 max mem: 22448 +train: [19] [ 80/400] eta: 0:02:34 lr: 0.000002 loss: 2.2487 (2.2240) grad: 0.0764 (0.0768) time: 0.4437 data: 0.0050 max mem: 22448 +train: [19] [100/400] eta: 0:02:23 lr: 0.000002 loss: 2.2414 (2.2232) grad: 0.0763 (0.0767) time: 0.4544 data: 0.0051 max mem: 22448 +train: [19] [120/400] eta: 0:02:12 lr: 0.000002 loss: 2.2466 (2.2347) grad: 0.0763 (0.0766) time: 0.4565 data: 0.0049 max mem: 22448 +train: [19] [140/400] eta: 0:02:02 lr: 0.000001 loss: 2.2294 (2.2356) grad: 0.0768 (0.0768) time: 0.4613 data: 0.0051 max mem: 22448 +train: [19] [160/400] eta: 0:01:52 lr: 0.000001 loss: 2.2225 (2.2333) grad: 0.0767 (0.0767) time: 0.4489 data: 0.0046 max mem: 22448 +train: [19] [180/400] eta: 0:01:42 lr: 0.000001 loss: 2.2617 (2.2403) grad: 0.0763 (0.0765) time: 0.4533 data: 0.0050 max mem: 22448 +train: [19] [200/400] eta: 0:01:33 lr: 0.000001 loss: 2.2006 (2.2329) grad: 0.0754 (0.0767) time: 0.4593 data: 0.0048 max mem: 22448 +train: [19] [220/400] eta: 0:01:23 lr: 0.000001 loss: 2.1787 (2.2320) grad: 0.0775 (0.0770) time: 0.4618 data: 0.0049 max mem: 22448 +train: [19] [240/400] eta: 0:01:14 lr: 0.000001 loss: 2.2509 (2.2362) grad: 0.0768 (0.0770) time: 0.4532 data: 0.0048 max mem: 22448 +train: [19] [260/400] eta: 0:01:05 lr: 0.000000 loss: 2.2445 (2.2350) grad: 0.0763 (0.0770) time: 0.4585 data: 0.0047 max mem: 22448 +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 2.1849 (2.2322) grad: 0.0763 (0.0768) time: 0.4602 data: 0.0049 max mem: 22448 +train: [19] [300/400] eta: 0:00:46 lr: 0.000000 loss: 2.2224 (2.2316) grad: 0.0761 (0.0769) time: 0.4573 data: 0.0049 max mem: 22448 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 2.2217 (2.2302) grad: 0.0763 (0.0768) time: 0.4554 data: 0.0047 max mem: 22448 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 2.1944 (2.2272) grad: 0.0753 (0.0767) time: 0.4576 data: 0.0047 max mem: 22448 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.2152 (2.2307) grad: 0.0770 (0.0767) time: 0.4592 data: 0.0049 max mem: 22448 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 2.2152 (2.2296) grad: 0.0763 (0.0767) time: 0.4640 data: 0.0047 max mem: 22448 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.2146 (2.2301) grad: 0.0751 (0.0767) time: 0.4651 data: 0.0047 max mem: 22448 +train: [19] Total time: 0:03:05 (0.4637 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.2146 (2.2301) grad: 0.0751 (0.0767) +eval (validation): [19] [ 0/85] eta: 0:04:53 time: 3.4541 data: 3.1942 max mem: 22448 +eval (validation): [19] [20/85] eta: 0:00:34 time: 0.3854 data: 0.0039 max mem: 22448 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3328 data: 0.0035 max mem: 22448 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3731 data: 0.0045 max mem: 22448 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3534 data: 0.0044 max mem: 22448 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3433 data: 0.0044 max mem: 22448 +eval (validation): [19] Total time: 0:00:33 (0.3982 s / it) +cv: [19] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.433 acc: 0.271 f1: 0.205 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.2713178294573643, "hparam": [1.2, 1.0], "hparam_id": 25, "epoch": 19, "is_best": false, "best_score": 0.2739018087855297} +eval (train): [20] [ 0/509] eta: 0:25:46 time: 3.0378 data: 2.7933 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:04:04 time: 0.3741 data: 0.0043 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:20 time: 0.3503 data: 0.0035 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:03:02 time: 0.3645 data: 0.0038 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:47 time: 0.3366 data: 0.0037 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:35 time: 0.3438 data: 0.0040 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:26 time: 0.3526 data: 0.0040 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:18 time: 0.3655 data: 0.0041 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:09 time: 0.3592 data: 0.0044 max mem: 22448 +eval (train): [20] [180/509] eta: 0:02:01 time: 0.3501 data: 0.0040 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:53 time: 0.3455 data: 0.0040 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:46 time: 0.3793 data: 0.0040 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:38 time: 0.3464 data: 0.0040 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:30 time: 0.3283 data: 0.0039 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:22 time: 0.3375 data: 0.0037 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:15 time: 0.3416 data: 0.0039 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:08 time: 0.3853 data: 0.0046 max mem: 22448 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3429 data: 0.0038 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:53 time: 0.3631 data: 0.0041 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:46 time: 0.3424 data: 0.0040 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3233 data: 0.0036 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3218 data: 0.0038 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3287 data: 0.0036 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3352 data: 0.0037 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3459 data: 0.0038 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3475 data: 0.0041 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3298 data: 0.0041 max mem: 22448 +eval (train): [20] Total time: 0:03:00 (0.3548 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:01 time: 2.8413 data: 2.5860 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:29 time: 0.3338 data: 0.0074 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:17 time: 0.3329 data: 0.0038 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3357 data: 0.0030 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3226 data: 0.0041 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3177 data: 0.0040 max mem: 22448 +eval (validation): [20] Total time: 0:00:30 (0.3627 s / it) +eval (test): [20] [ 0/85] eta: 0:04:04 time: 2.8814 data: 2.5946 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3639 data: 0.0034 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3288 data: 0.0036 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3312 data: 0.0041 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3470 data: 0.0042 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3369 data: 0.0041 max mem: 22448 +eval (test): [20] Total time: 0:00:31 (0.3733 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:17 time: 3.1461 data: 2.8882 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3561 data: 0.0035 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3621 data: 0.0034 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3607 data: 0.0042 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3596 data: 0.0042 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3437 data: 0.0040 max mem: 22448 +eval (testid): [20] Total time: 0:00:32 (0.3942 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.2739018087855297, "hparam": [1.4, 1.0], "hparam_id": 26, "epoch": 10, "is_best": true, "best_score": 0.2739018087855297} +eval (train): [20] [ 0/509] eta: 0:26:03 time: 3.0727 data: 2.8264 max mem: 22448 +eval (train): [20] [ 20/509] eta: 0:03:48 time: 0.3381 data: 0.0048 max mem: 22448 +eval (train): [20] [ 40/509] eta: 0:03:14 time: 0.3563 data: 0.0035 max mem: 22448 +eval (train): [20] [ 60/509] eta: 0:02:56 time: 0.3499 data: 0.0039 max mem: 22448 +eval (train): [20] [ 80/509] eta: 0:02:43 time: 0.3461 data: 0.0041 max mem: 22448 +eval (train): [20] [100/509] eta: 0:02:32 time: 0.3398 data: 0.0038 max mem: 22448 +eval (train): [20] [120/509] eta: 0:02:22 time: 0.3389 data: 0.0038 max mem: 22448 +eval (train): [20] [140/509] eta: 0:02:13 time: 0.3316 data: 0.0040 max mem: 22448 +eval (train): [20] [160/509] eta: 0:02:04 time: 0.3288 data: 0.0038 max mem: 22448 +eval (train): [20] [180/509] eta: 0:01:57 time: 0.3547 data: 0.0039 max mem: 22448 +eval (train): [20] [200/509] eta: 0:01:49 time: 0.3366 data: 0.0039 max mem: 22448 +eval (train): [20] [220/509] eta: 0:01:42 time: 0.3401 data: 0.0039 max mem: 22448 +eval (train): [20] [240/509] eta: 0:01:35 time: 0.3424 data: 0.0040 max mem: 22448 +eval (train): [20] [260/509] eta: 0:01:27 time: 0.3487 data: 0.0040 max mem: 22448 +eval (train): [20] [280/509] eta: 0:01:20 time: 0.3259 data: 0.0038 max mem: 22448 +eval (train): [20] [300/509] eta: 0:01:13 time: 0.3432 data: 0.0038 max mem: 22448 +eval (train): [20] [320/509] eta: 0:01:06 time: 0.3306 data: 0.0037 max mem: 22448 +eval (train): [20] [340/509] eta: 0:00:58 time: 0.3244 data: 0.0036 max mem: 22448 +eval (train): [20] [360/509] eta: 0:00:51 time: 0.3334 data: 0.0037 max mem: 22448 +eval (train): [20] [380/509] eta: 0:00:44 time: 0.3428 data: 0.0040 max mem: 22448 +eval (train): [20] [400/509] eta: 0:00:37 time: 0.3340 data: 0.0038 max mem: 22448 +eval (train): [20] [420/509] eta: 0:00:30 time: 0.3215 data: 0.0038 max mem: 22448 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3359 data: 0.0039 max mem: 22448 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3831 data: 0.0043 max mem: 22448 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3460 data: 0.0040 max mem: 22448 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3564 data: 0.0042 max mem: 22448 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3290 data: 0.0040 max mem: 22448 +eval (train): [20] Total time: 0:02:56 (0.3477 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:21 time: 3.0794 data: 2.8159 max mem: 22448 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3825 data: 0.0049 max mem: 22448 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3557 data: 0.0036 max mem: 22448 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3764 data: 0.0042 max mem: 22448 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3500 data: 0.0044 max mem: 22448 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3384 data: 0.0042 max mem: 22448 +eval (validation): [20] Total time: 0:00:33 (0.3989 s / it) +eval (test): [20] [ 0/85] eta: 0:04:27 time: 3.1455 data: 2.8308 max mem: 22448 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3746 data: 0.0032 max mem: 22448 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3469 data: 0.0038 max mem: 22448 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3745 data: 0.0042 max mem: 22448 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3615 data: 0.0045 max mem: 22448 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3435 data: 0.0041 max mem: 22448 +eval (test): [20] Total time: 0:00:33 (0.3974 s / it) +eval (testid): [20] [ 0/82] eta: 0:03:50 time: 2.8086 data: 2.5442 max mem: 22448 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3809 data: 0.0053 max mem: 22448 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3532 data: 0.0035 max mem: 22448 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3669 data: 0.0042 max mem: 22448 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3345 data: 0.0039 max mem: 22448 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3234 data: 0.0039 max mem: 22448 +eval (testid): [20] Total time: 0:00:31 (0.3891 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 10 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | train | 2.2606 | 0.31977 | 0.0022981 | 0.26337 | 0.0023069 | +| flat_mae | patch | attn | nsd_cococlip | best | 10 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | validation | 2.4278 | 0.2739 | 0.0055457 | 0.20108 | 0.0048769 | +| flat_mae | patch | attn | nsd_cococlip | best | 10 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | test | 2.3021 | 0.29072 | 0.0050134 | 0.22086 | 0.0050865 | +| flat_mae | patch | attn | nsd_cococlip | best | 10 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | testid | 2.4446 | 0.26528 | 0.0051333 | 0.20385 | 0.0048455 | + + +done! total time: 1:25:37 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/train_log.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..c9ac8503970a8d7e9c6d3080712cefa89a5b7309 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1338812530040743, "train/grad": 0.02984202534891665, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.176650390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.176590576171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.176488037109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.17640380859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.176309814453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.17615478515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.175997314453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.175789794921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.175533447265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.175257568359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.175009765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.174637451171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.174195556640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.173662109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1730517578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.172529296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.171798095703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.17085693359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.169755859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.168668212890625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.167220458984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.16568359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.16383544921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.161790771484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.159534912109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.156798095703125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1543505859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.15207275390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.149176025390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1459912109375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.14332275390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.140877685546875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.137645263671875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.134632568359375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.13081298828125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.126534423828125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1210894775390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.11496826171875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1069384765625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.09497802734375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0844232177734376, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0743563842773436, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0604379272460935, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0474484252929686, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.030914001464844, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0122015380859377, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.996091613769531, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9781643676757814, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.962552947998047, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0038406146015040575, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0038402257417328657, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.003839599676430225, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0038390534068457782, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0038384242309257386, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00383763327030465, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003836750444024801, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0038358650845475495, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0038346232858020813, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003833490597316995, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0038324141141492874, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038308341382071375, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0038294668216258287, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003827792340889573, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038264851458370687, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038255505077540875, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003824952645227313, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038249086902942507, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038260099955368786, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003828428731067106, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038331140752416106, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003840000149793923, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003850718855392188, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038653828878886997, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003884106770856306, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003911314700962976, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003939851190662012, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0039689763856586065, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004011077869217843, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004062338607618585, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004106006472138688, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004142922190949321, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00418863816303201, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004226952926255762, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004271247747819871, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004315480472287163, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004364348162198439, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004415301911067217, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004476572714047507, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004562199221691116, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004636732954531908, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004708165471674875, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004828080638544634, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004930813381215557, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00506230748607777, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005285542317433283, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00553474422194995, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0058874201320577415, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006142112560337409, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.176257848739624, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1760571002960205, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.175726890563965, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1753976345062256, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1750681400299072, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1746063232421875, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.174088716506958, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1735079288482666, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.172732353210449, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.171905755996704, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.171076774597168, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1698296070098877, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.168593168258667, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.166757583618164, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.164952278137207, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1631698608398438, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.160829544067383, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1579694747924805, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1545989513397217, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1513216495513916, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.147077798843384, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.142526865005493, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.137315273284912, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1317570209503174, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1262404918670654, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.120398998260498, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1160953044891357, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.112854480743408, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.109147787094116, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.104921579360962, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1006782054901123, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0961451530456543, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0885283946990967, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0798585414886475, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0665688514709473, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0494673252105713, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0262198448181152, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9992294311523438, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9645543098449707, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9195144176483154, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.887347459793091, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.862558364868164, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8283965587615967, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.811384916305542, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.791804790496826, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7373528480529785, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.710012912750244, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6965200901031494, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.724534749984741, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05832410483573274, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05998523440383906, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.060723514211886306, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.067921742340347, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0784422296050203, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0754891103728313, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08545588778146918, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09837578442229605, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.10760428202288667, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1197858988556663, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1273532668881506, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.12919896640826872, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.13399778516057587, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1378737541528239, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.14544112218530822, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.15356220007382798, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.16076042820228867, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.15891472868217055, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.15946843853820597, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18032484311554078, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19047619047619047, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19952011812476927, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.19102990033222592, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.024525706402214447, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.024975170062849637, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.024895665987310345, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.024517990791432128, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.023352344980383213, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02456103362392542, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0232496829132586, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.020973709857066574, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02079152206053711, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.019249020316160954, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.018388218363858108, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01643244207000639, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015963894698725178, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015901683886476715, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.015262564183479576, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014766911546636364, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.015428208511796672, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014700779957961596, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014155572296122276, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013375772647578279, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013141208957969447, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.011663266347671973, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010942113649366923, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01022007302627123, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.00967087937816176, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.008297397858360207, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.007276211461130327, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0061365041200864626, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005745067960071585, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.007644049967854003, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.01235257853194873, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.015991217338381093, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.022535080177520997, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0315602561409356, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03645955863803015, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04482144714598923, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05107036593990413, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.052705865166026065, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05671484836446619, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.061237485094704315, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06744317744635057, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.07360022700992182, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.07847307859484275, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.08033670012035739, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.08442597001737866, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.10297999398146129, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.11066280477086123, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1209017321080069, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1198763227416994, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.9781643676757814, "validation/loss_best": 2.6965200901031494, "validation/acc_best": 0.19952011812476927, "validation/f1_best": 0.1209017321080069} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.0085564613342286, "train/grad": 0.0400247897952795, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.174224853515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.173798828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17302490234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.172347412109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.171632080078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.170662841796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.16958251953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.168470458984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.166871337890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1652197265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.163682861328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.16113525390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.158736572265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.155252685546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.15196533203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.148804931640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1448388671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.14051513671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.135994873046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.13213134765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12791259765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.123828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.119666748046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.115423583984375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.110869140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.105032958984375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0990673828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.092554931640625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0819183349609376, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0662664794921874, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0495111083984376, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0323284912109374, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0071795654296873, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9831170654296875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9524224853515624, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.918062438964844, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.876812973022461, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.8367070007324218, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.796969146728516, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7531121826171874, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7244295120239257, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.703156280517578, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.680179500579834, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6634629821777343, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6472655868530275, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6368821048736573, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.633954782485962, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6366603851318358, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6456227588653562, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00377327173249796, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.003771347509464249, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0037684731115587055, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0037659712473396213, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.003763873904244974, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003761369310086593, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003759365949081257, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0037580621941015126, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0037576356902718545, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003758835095213726, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003761909822933376, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0037693981127813457, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00377976123127155, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003799693473847583, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00382372057181783, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038505700009409337, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0038887864409480246, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003939389284932986, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004001570917898789, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004061607848852873, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004135532334912568, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004206284893443808, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004276677899761125, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004340750563424081, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004397328209597618, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004454899579286575, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00450116274645552, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0045411154220346365, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00459580009104684, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004666044323239475, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004734605704434216, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004801960639888421, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0049075885687489065, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005031952981371432, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005247792247682809, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005539015505928546, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005893680066801608, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006274943847674876, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006703415005467832, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0072109796619042755, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007605411659460515, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007936772692482918, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008369471437763423, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00873440480325371, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009167647005524486, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00966989622451365, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010089316542726011, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010546329850330948, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01101222803350538, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1723642349243164, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1716041564941406, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1703450679779053, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.169111967086792, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.167886257171631, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1661901473999023, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.164278030395508, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.162160873413086, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1593873500823975, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1564393043518066, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.153568983078003, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1492557525634766, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1451189517974854, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1392710208892822, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1339516639709473, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1292357444763184, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1239185333251953, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1187384128570557, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1141297817230225, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.110572576522827, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1065635681152344, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1023635864257812, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.09704852104187, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0902163982391357, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0813307762145996, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.067610025405884, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.051732301712036, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0340325832366943, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0052456855773926, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9665727615356445, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9312498569488525, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.900102138519287, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8587164878845215, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8207476139068604, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7674124240875244, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7096080780029297, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.664844036102295, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6306824684143066, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6120426654815674, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5924041271209717, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.577789306640625, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5725045204162598, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5718884468078613, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.572755813598633, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.583427667617798, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6034226417541504, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6291558742523193, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6535098552703857, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6836466789245605, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07788851974898486, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07715023994093761, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07918050941306755, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0784422296050203, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07438169066076043, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.08564045773348099, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.10003691399040236, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.11720191952750092, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.12679955703211518, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.1330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.13528977482465854, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.13935031376891843, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.14156515319306018, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1461794019933555, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.14987080103359174, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.15928386858619417, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1760797342192691, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1891842008121078, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20062753783684018, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.20985603543743078, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2115171650055371, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21853082318198597, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22517534145441123, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22665190107050573, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22093023255813954, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.21428571428571427, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2131782945736434, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02006485046213734, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.019080666576164716, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01681158114072172, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01603736519490656, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01590188721766624, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015225803231732138, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014309439603843349, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.015075517770839075, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.015363540000260198, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014250541788333277, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013879738549158213, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013501201771537297, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012997002319669354, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0123675979620798, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.011745254491161816, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011070106402881244, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010221082831309868, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00942640398295288, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008866986094010536, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008888557320318319, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.00954928200569504, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010884010252148453, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.015499666697144601, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.022694286899475672, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03566087771141125, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.046941681241202404, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.051704208547753455, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.054014629904980384, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.05448320940200852, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.056537968050259506, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.05842919996579928, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.06293485310335, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.07005477569629177, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.08148947515455067, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.09706478998628314, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.11387248079346905, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.12813625822756694, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.13561438902847653, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1374964883002299, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14562354568170013, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15353819448687275, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1534390825796811, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15412298261431104, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15505907962621376, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1552651326533809, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15630654764876076, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15850451608796745, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15369206808705815, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1509955758424026, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.680179500579834, "validation/loss_best": 2.5718884468078613, "validation/acc_best": 0.22665190107050573, "validation/f1_best": 0.15412298261431104} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.9153818225860597, "train/grad": 0.05088853420689702, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1694580078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.168441162109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.166629638671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.16473388671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.16301513671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.160665283203125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.157889404296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.154974365234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.151190185546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.14733154296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.143646240234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13842529296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.13400634765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128323974609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12389892578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.120511474609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.116658935546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.112623291015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.108226318359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.103828125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0976123046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.08992919921875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.079400634765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0652490234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.047139892578125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0213916015625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.995230712890625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.96980712890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9336343383789063, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.887908935546875, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.843372650146484, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.800849838256836, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7451666259765624, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6998172760009767, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.655134372711182, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6203691482543947, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.5940928268432617, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5768598175048827, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.562192039489746, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5487944412231447, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.544116048812866, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5430343437194822, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5431535816192627, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.54508620262146, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5526747608184817, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.570607581138611, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5906617522239683, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.629027943611145, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6669193363189696, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0038161787285935136, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0038147097639739513, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0038141890265978875, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0038153996085748074, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.003818823639303446, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0038261099450755866, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0038375974388327448, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0038545614248141646, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003881338955834508, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003914643318857998, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003950607503065839, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0040088249859400096, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0040683045738842336, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004156571849016473, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004238022008212283, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004310453658690676, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004390550086973235, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004465786939254031, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004528727902797982, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004572238745167851, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004614198440685868, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004652789091924205, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004698625514283777, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004755559653276577, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004825823414139449, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004921076550381258, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005017504540737718, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00511523486347869, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0052755016554147, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005554891629144549, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005932446604128927, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006352852422278375, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006968235850799829, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007497511261608452, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00805893279844895, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008505098668392748, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008819226957857609, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009091697663534433, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009400528552941979, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009832924462389201, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010206538981292397, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010562790848780423, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010995786138810217, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011415665447711944, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011921981908380985, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01250020473729819, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013066081297583878, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013802911946550011, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014518178496509791, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1660776138305664, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1644527912139893, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.161782741546631, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1591544151306152, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.156567335128784, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.153028726577759, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1491007804870605, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1448404788970947, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1394715309143066, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.134145975112915, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1294076442718506, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1233201026916504, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1185848712921143, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1133718490600586, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1094913482666016, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.106191873550415, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1020123958587646, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.096605062484741, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.089493989944458, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.081512451171875, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.069316864013672, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.053420066833496, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.031301259994507, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0028111934661865, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.969489574432373, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.928527355194092, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.892962694168091, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8613195419311523, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.815883159637451, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.753910541534424, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.704400062561035, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6564807891845703, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.611525774002075, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.589884042739868, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.577049970626831, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5682036876678467, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5598394870758057, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5605716705322266, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.561880588531494, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5604357719421387, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5707616806030273, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.585895299911499, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5966975688934326, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.595107316970825, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6127498149871826, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6348471641540527, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.651857376098633, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7046961784362793, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7751379013061523, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07438169066076043, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07567368032484312, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07659653008490218, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07659653008490218, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0784422296050203, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0784422296050203, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07751937984496124, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.067921742340347, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.09099298634182355, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.10428202288667406, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.11720191952750092, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1256921373200443, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.12809154669619785, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.132890365448505, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.13676633444075303, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1421188630490956, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.14673311184939092, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15762273901808785, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.16980435585086748, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1878922111480251, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20155038759689922, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22388335179032853, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22609819121447028, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22665190107050573, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22868217054263565, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22683647102251753, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23034330011074197, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23145071982281284, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23274270948689554, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23403469915097821, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22572905131044665, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21391657438169065, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20339608711701734, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.18512366186784793, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.015132057719600668, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01434992030830464, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014836996955099097, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014645576359400586, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01363835324064725, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013446889347133286, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013136339921047178, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012309220778360023, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011591840125735468, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010895174046439917, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010603908759448189, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00900714472423107, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008660357700989755, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007806809157053239, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006899499920006993, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007209599638321513, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.00978977813507308, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013488263443501217, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.017838003929914737, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02794487662138211, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03844826485523383, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.048743212312205124, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.054679263909461706, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.054838047160506304, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.05863025335290146, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06119399056700455, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.06488033492399832, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06955052923976944, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07908447904122241, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.09243794886246469, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.11340309437634617, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1330622809550811, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.14604427500408987, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15164613431372018, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1523356534634787, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.153306712200209, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.15347783642241142, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.152670124724801, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15018711798418502, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15303451664452994, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15265783406891886, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15128829735579066, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15721485894011847, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16294645066075167, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1563509555931936, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.16077994717777572, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15593232812489977, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15492797902178776, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.14189443013054728, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.54508620262146, "validation/loss_best": 2.595107316970825, "validation/acc_best": 0.23403469915097821, "validation/f1_best": 0.16294645066075167} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.8489762461185455, "train/grad": 0.05931318478658795, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.16200927734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1600146484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.156591796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.15329833984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1501220703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.145811767578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.14117919921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1364892578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.130927734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126064453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12210693359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1174169921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1138525390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.109381103515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.105316162109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.10107177734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0951953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0868914794921873, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0755718994140624, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0626727294921876, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.04388916015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0209246826171876, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9921368408203124, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9591302490234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9231756591796874, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.87727783203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8309112548828126, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7852782440185546, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7229150390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.658741302490234, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.6150809478759767, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5862207794189453, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.5592385864257814, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.5401741600036623, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.5211315155029297, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.5056411933898928, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.492611331939697, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.484569969177246, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.478195104598999, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4737533950805664, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4746068954467773, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4772307872772217, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4878153562545777, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5045013093948363, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5348295068740843, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5762069606781006, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6137258768081666, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6749979972839357, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.7329412746429442, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0038476526946760715, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.003853770042769611, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.003868480332894251, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.003887713322183117, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.003910307047190145, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003945472784107551, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00398929476737976, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004040348912822083, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004108392536872998, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004181079671252519, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00424974033376202, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004345327864866704, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004423218732699752, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004507761392742396, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004562335988739505, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0045991120825055985, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004634360645432025, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004672121223993599, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004719064880628138, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004771049665287137, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0048465371574275195, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004935034090885892, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005042221802286803, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005165991554968059, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005313846529461443, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005555869936943054, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005908474733587354, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006360039813444018, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007067892283666879, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007801717934198677, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008235409439075738, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00851136542391032, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008805525300558656, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009044562336057424, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009327981888782233, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009645275396760553, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010059075877070427, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010466759777627885, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010921459309756756, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011491233445703984, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01189499834086746, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012257726155221462, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01277209997177124, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.013335875016637147, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.014028601404279471, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014888276597484946, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015550835011526942, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.016451380285434424, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01701711849309504, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.157649517059326, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.154902458190918, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1504228115081787, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.146106481552124, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1419787406921387, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.136563301086426, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.131009340286255, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1256518363952637, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1199653148651123, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1153292655944824, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1118288040161133, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1075351238250732, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.103745937347412, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0980260372161865, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.091872215270996, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0850489139556885, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0748205184936523, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.060027837753296, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0396413803100586, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0171005725860596, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9858648777008057, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9520788192749023, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9152092933654785, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.878176689147949, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8393635749816895, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.780486583709717, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.71260666847229, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.6539034843444824, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6042895317077637, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5763509273529053, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.557615041732788, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.544063091278076, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.527641534805298, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.511997938156128, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4989476203918457, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.502239465713501, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.520188808441162, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5386712551116943, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5641255378723145, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5785677433013916, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5830373764038086, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5862598419189453, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6104769706726074, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6379036903381348, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6749985218048096, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.737705945968628, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.788299798965454, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.8274893760681152, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.893155097961426, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07715023994093761, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07733480989294943, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.08102620893318568, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07954964931709117, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07862679955703211, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0754891103728313, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0843484680693983, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09523809523809523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.10889627168696936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11941675895164268, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1242155777039498, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12827611664820968, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.132890365448505, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13676633444075303, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.14377999261720192, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.15171650055370986, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.16555924695459578, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18290882244370615, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2026578073089701, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2220376522702104, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22905131044665927, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.23163528977482467, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23883351790328536, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23994093761535623, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23385012919896642, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2248062015503876, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2188999630860096, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2072720561092654, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20081210778885197, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20191952750092285, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1969361387966039, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013864740907417468, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01379872378934748, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013028324989982088, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01362668955614646, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012818196865940462, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.012023980373310863, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011214619289833659, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01099436066358072, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009983070441585027, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009390807485849076, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008967217343613576, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009110603273273225, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009238352397840155, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011969556133465481, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.016757685339236893, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01952793041487957, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.027080279072549302, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.036577946548177726, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04355063010827171, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.04757483066365029, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05050035981465633, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05394745058478648, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.05821634529979947, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06451850582328235, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.07192574609108486, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.08512490269231315, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10283675556662715, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.12444380611689, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.14528506955556722, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.15472099338319434, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.15918656383568006, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.16744292894577514, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17080642865154325, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1697812011642391, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17209392069539095, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16761880227528558, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1637489066513146, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1569707147573749, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1567776821130072, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15941385749978812, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16270564753113956, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16568602510931815, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1664891121729629, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16446924522262515, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1649707430830363, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15582269898887377, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.14483265198388415, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1532520615051092, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.14990543287460378, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 2.5211315155029297, "validation/loss_best": 2.4989476203918457, "validation/acc_best": 0.24510889627168697, "validation/f1_best": 0.17209392069539095} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.7967839217185975, "train/grad": 0.06645752051845193, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.154466552734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1514501953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.146607666015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14229248046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.138265380859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.133380126953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.124744873046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120760498046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.117432861328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1144775390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.110167236328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.10559814453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.098082275390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.089605712890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0801654052734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0659149169921873, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.04588134765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0199017333984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9933056640625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.958920593261719, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.922669219970703, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8804656982421877, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.828726959228516, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.7663545989990235, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.6924563598632814, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.6393109512329103, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.602937698364258, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.5679914474487306, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.538133544921875, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.516007537841797, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.4979769515991213, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.474416217803955, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4543257331848145, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.4344264602661134, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.4204048919677734, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.4097813034057616, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.405815391540527, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.4063274097442626, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4113000297546385, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.419570384025574, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.433151669502258, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.465885558128357, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4940840864181517, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5343227899074554, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.583257031440735, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6446892690658568, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7308333241939544, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.8266210627555846, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.003847395844059065, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0038704820082057266, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.003914202814921736, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.003962763393064961, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0040130428061820565, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004084194726310671, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0041640341479796915, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004250203247647732, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004351406438509002, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004438816303154454, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004503435345832259, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004568809791235254, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004609201038256287, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004650561242597178, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004686451075831428, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004724747758591548, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004782305462285876, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004862568533280864, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004963960198219866, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00506381690967828, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00518893662141636, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005324878836981952, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005519312403630465, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00586792791262269, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006465329201892018, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0073177776834927495, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007957272008061409, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008332388112321495, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008651885304134339, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008935161149129272, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009188288049772382, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009442985542118549, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00981065814383328, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01013910926412791, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010545146614313126, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01096594745758921, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.011453882060013711, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011878248546272516, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012323245024308562, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.012860812041908502, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.013271683375351132, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.013682940225116909, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.014277868433855473, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015007312651723623, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015648884545080365, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.016345757334493102, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0172585931699723, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01827198117505759, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01925346417352557, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1478426456451416, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.143953323364258, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.137875556945801, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1324007511138916, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.127617835998535, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1220922470092773, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1172566413879395, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1130990982055664, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.108834743499756, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.104820489883423, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1009247303009033, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0946500301361084, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.087775945663452, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0759263038635254, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.062129497528076, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.046398401260376, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0230655670166016, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9919257164001465, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9550657272338867, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.921283721923828, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8816792964935303, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.840806007385254, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7889468669891357, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.7195889949798584, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.643258810043335, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5810024738311768, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.553323745727539, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.535904884338379, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5164895057678223, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4956767559051514, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.482084035873413, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.474182605743408, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.464263677597046, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4588541984558105, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.464953660964966, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4779765605926514, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4899888038635254, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.511288642883301, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5354816913604736, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.550967216491699, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5605356693267822, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5710694789886475, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6053102016448975, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.63504695892334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6536970138549805, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.688477039337158, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.747898817062378, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.86676287651062, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.949697971343994, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07825765965300849, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.08010335917312661, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07825765965300849, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07807308970099668, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07604282022886674, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.08102620893318568, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.09800664451827243, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.11295681063122924, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.12403100775193798, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.12919896640826872, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.13695090439276486, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.13953488372093023, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.14599483204134367, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.15485418973791068, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.165374677002584, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.18180140273163528, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.20653377630121816, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.22905131044665927, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2482465854558878, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2698412698412698, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24787744555186417, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24787744555186417, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24603174603174602, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23938722775932078, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2264673311184939, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23015873015873015, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2264673311184939, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2115171650055371, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1984126984126984, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.18604651162790697, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01301784702517736, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012926677828063409, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012240131256116818, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.011883041905563942, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.011344285636651777, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010052098350502052, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009487493475678453, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008991370030970102, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008695085396656078, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008857829291406402, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009691959165982957, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015041181966023975, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018201947807352913, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03277153345160264, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04426764236381042, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05086575766731363, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05415241283806357, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.057720890850285374, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06053550980285003, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.06350520650201345, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.06841420750011155, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07576903949032535, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08606482242896489, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.10398839018921117, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1293963904519427, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.15196817772654467, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16178063244288485, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16727424793556825, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1736941360157643, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17507959175111984, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1829860662903576, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1875331032493853, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19668490197269864, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19729815260958086, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19408934873752193, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19037304221633058, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19039387069321875, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18671736410305936, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17420810477642443, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17122339582296078, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17339940942458207, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17245392509970706, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17272681694274414, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16076592125895242, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16183798643963584, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1667171009273859, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1642223891720001, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.16610188302277243, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15271856302745035, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.474416217803955, "validation/loss_best": 2.464263677597046, "validation/acc_best": 0.2698412698412698, "validation/f1_best": 0.19668490197269864} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.747284564971924, "train/grad": 0.07202210251241922, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.145042724609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14114990234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.135350341796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1304736328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126444091796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12217529296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.11839111328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.115093994140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.111085205078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.106759033203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.102181396484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.09446044921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.085880126953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0710003662109373, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0539404296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0351483154296877, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0087042236328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9754092407226564, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9377252197265626, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9027615356445313, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8577008056640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.8031182861328126, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.7333431243896484, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.6621829223632814, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.606275749206543, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5623629188537596, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.534382019042969, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.513356189727783, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4879845428466796, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.4604146480560303, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.437561559677124, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.4181511545181276, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3951129150390624, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.378352613449097, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3635279369354247, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.354165515899658, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3459626722335813, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.343795027732849, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.34819207906723, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3635297656059264, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.378495287895203, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4007577228546144, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4416765069961546, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4734751343727113, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5217162549495695, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5826088404655456, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.657315574884415, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7717434895038604, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.900508986711502, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0039622596895787865, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004004285340197384, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00407579310820438, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004145093396073207, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004213405592599884, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00430233696824871, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004389083245769143, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004464538756292313, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004533593325177208, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004580876658437773, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004612593344645575, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004650128266075626, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004686106233857572, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004746970518026501, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00481611873023212, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0048901164054404945, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0049889520462602375, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005106873740442097, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005240856215823442, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0053750889888033275, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005594144873321057, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00599625896429643, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006719818857964128, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0075124872010201215, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008043962104711682, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00840264868689701, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008630570713430643, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008832663351204246, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00913591469405219, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009530276767909527, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009886681279167532, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010224791276268661, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010688908910378814, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.011061882907524705, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.011475798254832626, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.011853884612210095, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.012326139612123371, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.012782530980184675, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.013256158865988254, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.013881713515147567, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.014388857269659638, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.014883721964433789, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015483560650609433, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016161225847899915, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.016734941117465495, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.017466769381426276, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01877976777497679, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0198006949480623, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.021237292718142273, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1378657817840576, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.133225202560425, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1265645027160645, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1212618350982666, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1171281337738037, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1126821041107178, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1087377071380615, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1048521995544434, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0998451709747314, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0941131114959717, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0878491401672363, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0768983364105225, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0642504692077637, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0421957969665527, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0173373222351074, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.9910857677459717, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.95658540725708, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9170520305633545, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.875805616378784, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8381717205047607, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7848212718963623, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.717559337615967, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6453394889831543, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5943174362182617, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.565863847732544, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.543046236038208, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.527008056640625, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5132575035095215, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.495572566986084, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.47989821434021, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.474583387374878, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.470829963684082, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4678032398223877, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.466413974761963, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.484806776046753, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.51961350440979, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5535502433776855, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.563957929611206, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.578446626663208, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5772287845611572, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5974998474121094, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6250417232513428, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.641369104385376, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6839165687561035, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.696903944015503, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.755039930343628, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8047854900360107, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.842986583709717, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.93831467628479, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0784422296050203, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07825765965300849, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07659653008490218, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0784422296050203, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08877814691768181, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1035437430786268, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11960132890365449, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12827611664820968, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1315983757844223, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.135843484680694, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1421188630490956, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14544112218530822, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15411590992986343, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.16352897748246586, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.18161683277962348, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.20468807678110004, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.22129937246216316, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24215577703949798, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2500922849760059, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2571059431524548, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24640088593576967, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23791066814322628, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23458840900701367, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23421926910299004, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23385012919896642, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23034330011074197, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22148394241417496, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2157622739018088, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20431893687707642, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20191952750092285, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012039461760866302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011789006760998805, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011190624516615705, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01032782165264172, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00948729143107981, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008956757025876913, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008883344923658101, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008796415327620308, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009437483516626745, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012071118074481803, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0160087914017668, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.026207684278696172, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03886017642019164, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.048036256622273704, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05341551001458889, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.054919181586082305, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05799670507521159, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.062495572487555856, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06567489500974462, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07223079317105463, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.08054213532564376, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.09831803453114313, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.12560125649465304, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14616282353987886, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15493188727723553, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1640775669846634, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16882965010776707, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17269368981610964, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17987428980495676, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18896449642065818, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19396904046845287, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19786722884112484, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19854315737047734, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2001128539505598, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19803666804489037, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19596399421544042, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1846722666534015, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18498272793146897, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18797531186333813, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19439733203495743, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19069070557741677, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18463862224702834, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18296051445081396, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1785095598973158, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1739531466176134, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17373224539703694, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.16843876935001148, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15513438489834938, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1570901837004102, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 2.378352613449097, "validation/loss_best": 2.466413974761963, "validation/acc_best": 0.2596899224806202, "validation/f1_best": 0.2001128539505598} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.673299260139465, "train/grad": 0.07258342418819666, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.134091796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129483642578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123199462890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.118480224609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.114854736328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1107763671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.10696533203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.10276611328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.097144775390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.09047119140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.08317626953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0703179931640623, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.055841064453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0309515380859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.004119873046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.977095947265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.94232177734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9023577880859377, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.8576170349121095, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.811098175048828, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.7410834503173827, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.663296127319336, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5943516540527343, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5481712341308596, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.515778007507324, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4844330596923827, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4585837364196776, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.4359542655944826, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.405707359313965, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3719970321655275, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.345125217437744, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3220488166809083, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.294780912399292, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.276413164138794, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.260981764793396, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2515461444854736, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2414293241500856, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.240518128871918, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2484891271591185, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.266063189506531, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2853210878372194, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.311435008049011, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.354009360074997, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.383057248592377, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.4331981325149536, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4914754951000213, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.54438662648201, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6392860436439514, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.7196143817901612, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004054982220986858, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004111587312072515, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004203682146035135, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004291353551670909, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004368822921533138, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004455638515064492, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004526134900515899, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004577891821973026, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004621679716510698, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004655840018531307, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004687247540568933, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00473903268110007, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0047980942437425254, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0048950956377666445, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004992970474995672, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00508590891957283, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005202126756776124, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0053467444493435325, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005548433365765959, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005840442443732172, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006477846975903958, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007282893883530051, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007928705720696599, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0083152966783382, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008576507149264216, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008856372127775103, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009131576213985682, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00939640789758414, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009753008633852004, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010174112464301287, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010531171881593764, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010828535663895309, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01119696888141334, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.011510670725256205, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.011876870994456112, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012218786692246795, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01269680084194988, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.013069667727686465, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.013481043712235987, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.014105060999281705, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01459740178193897, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.014949074420146645, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015579968616366386, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016110448758117856, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.016493435502052307, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01706036933232099, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.017984944437630476, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01883147245272994, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.019363008616492153, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.129495620727539, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124809741973877, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1186623573303223, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1141481399536133, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.110629081726074, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.106532096862793, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.102199077606201, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.097261905670166, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0900986194610596, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.081395387649536, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0714991092681885, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0540475845336914, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0340819358825684, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.001251697540283, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9678640365600586, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.9363670349121094, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.898925304412842, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.858102560043335, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.810943126678467, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.75705885887146, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6786510944366455, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.611755609512329, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5724034309387207, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5493972301483154, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.531139612197876, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.509976625442505, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.490750789642334, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4747531414031982, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4566781520843506, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4471070766448975, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4504947662353516, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4613795280456543, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4772841930389404, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4870412349700928, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5009119510650635, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5239439010620117, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5545403957366943, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5744292736053467, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.58807110786438, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.593881607055664, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6077136993408203, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.636495590209961, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6893420219421387, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7190499305725098, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.711238145828247, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7431540489196777, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7989273071289062, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.885249137878418, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.9211249351501465, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07179771133259505, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07788851974898486, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08416389811738649, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09837578442229605, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11664820967146548, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.12495385751199704, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.13122923588039867, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.13602805463270579, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1421188630490956, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.14470284237726097, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.15337763012181616, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.16076042820228867, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1716500553709856, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.19933554817275748, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22148394241417496, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.23237356958287192, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24012550756736803, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26578073089701, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26799557032115173, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2412329272794389, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24381690660760427, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24012550756736803, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23145071982281284, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23108157991878922, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2307124400147656, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21908453303802142, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.21686969361387967, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20985603543743078, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011322960633868203, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01111851955830058, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009777043712806648, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009102347288589987, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00889389842225114, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008706104568316749, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009062535275791784, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.011502491080459231, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01629284261444693, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.021269888736685148, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03222034496721494, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.044544402686429195, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.049772195666776355, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05376909528348687, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05666609507002123, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06176715795940869, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06425258576564073, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07192862658461292, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07965386471359408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.09051589155462379, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.11784927093291679, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.14300124603533057, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1542247083972347, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.16263265570003257, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.17341373698513296, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.17982640207166775, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18308920801952486, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.18732658822917236, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1908292360569673, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19525472241803674, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19752518923392767, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19855386916169682, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19955142047168764, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19922426218641412, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1993783818763063, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19611007669412284, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19283879223462164, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19566681081413242, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18646593562965053, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1830104922995706, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18269676971866633, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17937878916469097, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17199462522457554, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17120095707023011, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.17099354736527184, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1673545000824195, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.16089741180129372, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15814292222843418, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15811647174983778, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.294780912399292, "validation/loss_best": 2.4772841930389404, "validation/acc_best": 0.26947212993724623, "validation/f1_best": 0.19955142047168764} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.6382838249206544, "train/grad": 0.07364647388458252, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128795166015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124735107421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.119478759765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.11566162109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.112591552734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.108721923828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1043017578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.099066162109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.091219482421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.081854248046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.07133544921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.05267578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.032020263671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9988818359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9659503173828123, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.934810791015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8968569946289064, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8523184204101564, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7947796630859374, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.731098480224609, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6537415313720705, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5945494842529295, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5528900718688963, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5206824684143068, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.49198748588562, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.459537763595581, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.430451998710632, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.404273052215576, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3686857843399047, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3307723689079283, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.302129814624786, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.279509117603302, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2534956097602845, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2355470991134645, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.219441921710968, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2086603832244873, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1968151259422304, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1946285653114317, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2011401295661925, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.220527231693268, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.238498339653015, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2680572843551636, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.307480490207672, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.336795666217804, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.386054747104645, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4480564153194426, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.4953065955638887, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.592634401321411, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6664056253433226, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004096484255278483, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00416460873442702, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00427086376468651, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004360140945063904, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00442984372493811, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0044978686526883395, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004547013421542943, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004583022259175777, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004619846021523699, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004658141209511087, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004700495169963688, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00477314465562813, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004851910773431882, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004970065882662311, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005080159683711827, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005184500087052584, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005325404773466289, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00553102666977793, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005911909104324878, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006543480139225721, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007395160614978522, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007960005898494273, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008310561489779503, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008571632204111666, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008832908647600562, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009175023671705276, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009503144756890833, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009785053925588727, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010141705321148038, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010542345782741904, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010905214017257095, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.011231742356903851, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01165066028945148, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.011988014141097665, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.012375270747579634, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012733256774954498, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.013242504829540848, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01366463084705174, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01408836321439594, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.014649195335805417, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.015047465334646404, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015356457992456853, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015712226727046072, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015997055061161516, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01620278342626989, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.016764438250102102, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.017516496288590134, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.018237985488958657, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.018461242578923703, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1231918334960938, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.118863821029663, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1134402751922607, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.109361410140991, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1058735847473145, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.101285219192505, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0958986282348633, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.089329957962036, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0795071125030518, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.067253828048706, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.053321361541748, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.029181957244873, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.002962350845337, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9633843898773193, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9268555641174316, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.894249439239502, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.855441093444824, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.80816650390625, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.742347478866577, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.668663501739502, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5928735733032227, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5518991947174072, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5271384716033936, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.508751630783081, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4918792247772217, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.473024368286133, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.458686590194702, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.44858980178833, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.440093755722046, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.446132183074951, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.459660530090332, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4766392707824707, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.508103132247925, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.54679274559021, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5884745121002197, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.622046709060669, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6381163597106934, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6402175426483154, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6490318775177, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6802775859832764, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.703321695327759, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6958765983581543, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7170066833496094, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7678823471069336, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.786006212234497, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.816457986831665, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8444881439208984, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.868826389312744, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.896836280822754, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07438169066076043, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0799187892211148, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09228497600590624, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.10723514211886305, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.11830933923957179, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.12624584717607973, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1315983757844223, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1362126245847176, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.14008859357696568, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.14747139165743817, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.15227021040974528, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1638981173864895, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1805094130675526, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.20376522702104097, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.22369878183831673, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.23624953857511996, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24326319675156885, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25083056478405313, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26448874123292726, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2571059431524548, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23754152823920266, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23477297895902546, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23108157991878922, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23458840900701367, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22868217054263565, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22517534145441123, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22093023255813954, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20764119601328904, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2072720561092654, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.19859726836471023, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010739591198206236, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00977715425964513, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009071130659824617, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008868238687879783, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009074705021659432, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010097046075430903, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01302842832553345, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017347502530465426, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02533947130093038, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.036559867346059115, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0443927821283008, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05094174262140263, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.052930391761070485, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0567930718514833, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.060727866144194474, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06654989159854628, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07161297787994152, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08285355369914871, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.10096519139401859, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.12689888851986564, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.15039629750573447, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16352554846785852, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17235698648353248, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18167836721462327, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18556675816418486, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18781279702036388, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1950837763270347, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19402758583017288, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19683710760007553, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2010066519991608, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20368342268323336, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20152711065393492, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1974793172585141, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19067717111248217, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18427354436158602, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18401912906338488, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18577323108779722, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19183129676038135, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18829753130263263, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19007270500253026, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18878481094401575, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18520850032691513, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1890850296458451, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18235047878815858, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.17887364406232723, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17937119076596844, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1730286463775135, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.17479287699337123, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.16893721385024127, "id_best": 30, "lr_best": 0.00081, "wd_best": 0.05, "train/loss_best": 2.302129814624786, "validation/loss_best": 2.459660530090332, "validation/acc_best": 0.26559616094499816, "validation/f1_best": 0.20368342268323336} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.5849139380455015, "train/grad": 0.07519369695335626, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12389404296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.120103759765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.115465087890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.111768798828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.10849853515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.10388916015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.098216552734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.091416015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.08119140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.06856689453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.054405517578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.029954833984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.00389892578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.964640808105469, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.927673645019531, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8937396240234374, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.851133117675781, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7948504638671876, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.718122863769531, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6459041595458985, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.579275665283203, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.536740417480469, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5026533889770506, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4716140747070314, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4402521324157713, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4030240631103514, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3701885414123534, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3416152000427246, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3049565410614012, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.266690731048584, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2366431522369385, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2118583965301513, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.182641000747681, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1623038053512573, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.143294358253479, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.130387315750122, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.115434091091156, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.113413623571396, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1154431438446046, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1379179227352143, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1581667470932007, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.182855256795883, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.23064026594162, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.260457834005356, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.311511214971542, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.3656118547916414, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.412605607509613, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.4965679478645324, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.568687440156937, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0041919231007341295, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0042656359844841065, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004368840771494433, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004444860465591774, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004497405036818236, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0045450580201577395, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004579737408785149, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004610824178671464, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004652088843286038, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004703786289319396, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0047620386374183, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0048600414174143226, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004957376023521647, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005092765400186181, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005218413134571165, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00534495415398851, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005536869489587843, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0058842613361775875, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006595031563192606, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0073443996021524075, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00793948766309768, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008284549182280897, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008557853524107486, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008834930290468036, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00915119833080098, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009552831479813903, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009920478332787752, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010244036358781159, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01067987507674843, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.011150827161036431, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011509264265187084, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01178979404270649, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.012115450915880501, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.012423506109043955, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01281859019305557, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.013185351015999913, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.013654819736257196, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01404640576802194, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.014476128998212516, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015047749178484083, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.015375776118598878, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015610017278231681, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015933188665658234, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016345931738615035, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.016490701930597425, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.016724841948598624, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.017352928519248963, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.017838232843205334, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01782661380711943, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1187074184417725, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1148219108581543, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1098883152008057, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.105876922607422, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1020843982696533, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0967113971710205, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0900325775146484, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.081660032272339, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0688841342926025, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0528717041015625, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.034924030303955, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.004927396774292, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9742980003356934, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.931273937225342, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8935048580169678, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8600122928619385, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8175830841064453, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.758960247039795, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.677645206451416, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6083292961120605, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5601160526275635, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.534402370452881, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.516054153442383, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5007405281066895, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.486490249633789, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.471005916595459, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4608559608459473, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4585282802581787, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4649195671081543, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.474740743637085, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.481215715408325, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.489672899246216, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.507505178451538, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.51749849319458, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5164201259613037, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5272128582000732, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5615320205688477, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5813305377960205, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6180458068847656, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.638235092163086, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6506807804107666, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.658507823944092, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.657864570617676, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6712136268615723, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6728200912475586, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6907036304473877, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.71512508392334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7589073181152344, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7890710830688477, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08822443706164636, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.10409745293466224, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.11424880029531193, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12070874861572536, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.12772240679217423, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.13381321520856404, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1389811738648948, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.14691768180140274, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.15430047988187523, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1626061277224068, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17257290513104467, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19767441860465115, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2207456626061277, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23255813953488372, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24289405684754523, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24787744555186417, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24953857511997046, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25396825396825395, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26375046142488, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25544481358434845, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24603174603174602, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24437061646363972, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2511997046880768, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23274270948689554, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23477297895902546, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2292358803986711, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22978959025470652, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22111480251015134, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009206698677975831, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008881836768117999, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008590332314072996, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008292564741140642, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009153834587962728, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013146312515884504, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015923195681228998, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.022832527934070677, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03397839164676047, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.040681282576153444, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04515771235624553, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.049885546378300255, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.054007899759322776, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05827446133767591, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06431756719441332, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.07030585722169778, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07868557971298991, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08970687020458139, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11822258192633861, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.14191774762836473, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1546946034119763, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16474615005886203, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.16987186912823082, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.17485329986728693, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1802332676098772, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1842717977666732, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18786132513260143, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.189687490153724, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19351452261737045, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1949982373797924, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1976343155154272, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19579148363975293, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1997266270998442, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19539773166538865, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19859623560665085, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2012677425211926, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19693074872475322, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19652976499937003, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19021536562285354, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19323867136946435, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1853959047893312, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1867869819342571, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19563625542366492, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1856783681360029, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18284935265321559, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.17643163319374686, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.17996390408670435, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.17513782364413133, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1613779937874212, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.182641000747681, "validation/loss_best": 2.507505178451538, "validation/acc_best": 0.26375046142488, "validation/f1_best": 0.1997266270998442} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.545808707475662, "train/grad": 0.07642267771065235, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.119029541015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1155322265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.111055908203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.107144775390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.103482666015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0980078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0912548828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.08275146484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.06989501953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0540216064453123, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.03638671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.007305908203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9778045654296874, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9361453247070313, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8984945678710936, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8635943603515623, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.816358184814453, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.748861541748047, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.665736618041992, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6017358779907225, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.551100006103516, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5149953460693357, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4818229484558105, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.448492393493652, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4138038253784178, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.373065376281738, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3375957870483397, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3072833442687988, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2682135486602784, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2255587196350097, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.192209072113037, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1652637052536012, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1351918315887453, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1129347825050355, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.088063181638718, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0727759552001954, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0541574466228485, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.049503483772278, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.047752032279968, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.05782124876976, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0810823941230776, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1155457961559296, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.162922822237015, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.1979812383651733, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.249817726612091, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.299285504817963, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.3313073682785035, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.415551664829254, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.48893120765686, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004278821568004787, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004355541745899245, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004454295255709439, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004520193899516016, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00456309016328305, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004602109638508409, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004635132382391021, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0046700182219501585, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004720974751980975, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00478439626051113, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004852886233711615, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004958295314572751, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005056670178892091, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005192323981318623, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005326257199048996, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005474626757204532, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005736789959482849, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006300740246661008, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0071853158343583344, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007782559404149652, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008194914748892189, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008475598925724626, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008752474370412528, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009070560911204666, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009434046768583358, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009873008308932184, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010255207545123995, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010589151144959032, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011041795178316533, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0115424139611423, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011947982502169907, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012268053144216537, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.012649549343623221, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.012952791531570257, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0132978405803442, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.013602595864795149, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.014147653859108687, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.014508352009579539, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.014887374755926431, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015428297291509806, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01580569882877171, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016069570402614773, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01624809399712831, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01638506774790585, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01638642663601786, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.016538972146809102, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.017042826656252147, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.017220612154342233, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01709010127466172, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1154117584228516, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.111818313598633, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1070284843444824, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1027657985687256, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0984816551208496, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0921030044555664, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0839922428131104, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0736753940582275, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0577847957611084, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.038126230239868, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0165798664093018, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9821181297302246, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.948772430419922, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9040989875793457, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.865630626678467, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.830411672592163, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7815639972686768, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7101447582244873, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6258912086486816, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5733535289764404, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.539766550064087, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.517974615097046, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4988458156585693, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4810242652893066, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4666202068328857, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.452674627304077, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.441171646118164, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.434842586517334, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.437154531478882, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.455500364303589, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4770164489746094, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4927361011505127, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5099706649780273, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.529766082763672, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5609800815582275, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.599632740020752, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.636368989944458, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6558470726013184, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6963002681732178, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.730330467224121, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.735201358795166, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7137458324432373, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7028584480285645, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6993985176086426, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6847715377807617, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6896395683288574, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6875240802764893, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7232682704925537, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.728133201599121, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0784422296050203, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08564045773348099, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09966777408637874, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1153562200073828, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12255444813584349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.12938353636028055, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.13473606496862311, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.13935031376891843, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1463639719453673, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15282392026578073, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.15799187892211147, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1642672572905131, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1877076411960133, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2159468438538206, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23181985972683647, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24160206718346253, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24898486526393504, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2528608342561831, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2567368032484312, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24437061646363972, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22683647102251753, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2355112587670727, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23661867847914358, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23403469915097821, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23772609819121446, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2427094868955334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2353266888150609, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23255813953488372, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.23661867847914358, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009027239594477208, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008802779818277082, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008803440270689881, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009744388153067045, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01152975629660516, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.016784087250109044, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.021443415526466156, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.031221910201239298, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.041998828873864684, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.04707452371253156, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.051121878264462545, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05439210879379853, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.058447327549378036, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06335913018134672, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06896999320095099, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.07484863428255538, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.08268877513845811, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10640685877098666, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13764450218942184, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15348022459415536, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1621932635322492, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16938352559219916, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17504208235346297, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1786018955527827, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18463333882224978, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18596717865642778, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19087631752685966, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1978396071635571, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20302439959755736, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20218773435481022, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20361493192853772, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20490735537225502, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21331567239474425, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.21484661025616272, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2069377170875085, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20117940942003013, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19828504679879422, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19561417195900666, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1935044625032055, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18603654515495072, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17488438582566682, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18985867179651905, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19241201766786595, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18532007404237472, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18605891323703058, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19193572162628988, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1804040240812094, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.17170564002543678, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.17677975474274543, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 2.2682135486602784, "validation/loss_best": 2.437154531478882, "validation/acc_best": 0.26854928017718716, "validation/f1_best": 0.20302439959755736} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.501584885120392, "train/grad": 0.07605475060641766, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11802734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11475341796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.110308837890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.106033935546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.101920166015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.095379638671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.08721435546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.076904296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0611224365234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0418212890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0208575439453127, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.987545166015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.954992370605469, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9104983520507814, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8706015014648436, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8320082092285155, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.77603515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6964094543457033, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6114317321777345, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5572357177734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.513505706787109, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4788643646240236, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.444551582336426, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.409243354797363, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3728009414672853, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.331058368682861, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2949146938323977, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.263942584991455, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.223480577468872, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.17850257396698, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.142849955558777, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.112636823654175, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.077409949302673, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0514308786392212, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.0233222031593323, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.001177290678024, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9775002539157867, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9686260628700256, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9674786746501922, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9806107264757156, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.000014590024948, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.030152084827423, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0778761422634124, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.113592120409012, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.169218221902847, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.2235645604133607, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.2665151453018186, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.3446588599681855, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.407061072587967, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004296691101044417, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0043682221276685595, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004454465525923297, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004508185356389732, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004543043787125498, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00457761611440219, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004612171407788992, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004653314413735643, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004715806784806773, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004791345167905092, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004869487362448126, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0049834189517423515, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005087740563321858, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005234399158507585, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005387622525449842, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005571159245446325, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005937736807391047, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006685892320238054, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007501593823544681, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007948478450998664, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00827590218745172, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00853752528084442, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008829038897529244, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00916846758686006, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009550322364084422, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01001481163315475, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010421221069991589, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010776190222240984, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01124797213356942, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.011758943293243647, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.012150847031734883, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012447877023369074, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.012789523932151497, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.013063591411337257, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.013451740792952478, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.013753788857720793, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.014260501633398235, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.014578775335103274, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01491542178671807, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015456496574915945, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.015682660043239594, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0158394265267998, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015975311556831004, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01618113210424781, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.016060182726942002, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.016095113130286335, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.016488899788819254, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01652756521012634, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01601676023565233, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1129672527313232, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.109537124633789, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1046619415283203, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.100005626678467, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.095149040222168, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.087759017944336, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.078223705291748, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0659873485565186, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0472285747528076, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.024388074874878, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0001437664031982, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.962937593460083, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.928525924682617, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8837356567382812, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8448398113250732, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8070034980773926, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.750094175338745, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6684038639068604, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.590282917022705, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5506677627563477, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5222530364990234, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5010154247283936, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.480342149734497, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4611573219299316, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.445671558380127, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4330883026123047, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.427823066711426, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4293243885040283, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.442451238632202, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4668374061584473, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.490110397338867, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.510972738265991, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.540191650390625, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.566534996032715, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5972723960876465, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.627593517303467, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.661313772201538, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.674960136413574, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.71234393119812, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7353925704956055, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.780035972595215, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.766798734664917, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7608931064605713, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7418856620788574, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7296254634857178, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.721264123916626, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.723465919494629, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7224485874176025, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.726860284805298, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.073827980804725, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08028792912513842, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.09136212624584718, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.10612772240679218, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1184939091915836, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12495385751199704, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13049095607235142, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.13602805463270579, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.14027316352897748, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.14839424141749724, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15596160944998155, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.16279069767441862, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17700258397932817, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.20191952750092285, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22425249169435216, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23791066814322628, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24861572535991142, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2532299741602067, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2572905131044666, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26264304171280917, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2692875599852344, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2739018087855297, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.271686969361388, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2397563676633444, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2351421188630491, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23237356958287192, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2368032484311554, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2410483573274271, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2336655592469546, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2307124400147656, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22277593207825766, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008907833182394563, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008543580218773807, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008671695052152777, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010292200563594726, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01465492880000406, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.017754591642321595, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.025102560875506608, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03447991892381836, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04408619135317846, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.047552341765658875, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.051091835895055504, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05452859071671987, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05819407439487297, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.06537063745464029, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07223566333867944, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.07979547612423675, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.09547013648108482, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12320219663577638, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14726032669502329, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16172649771862743, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1714404223431343, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17570796930044094, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18146028151249527, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18633965700203478, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19283556983531894, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.197457028672724, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20107671791720697, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2037775230806913, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20785114866032403, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2060968010888904, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2067622587575445, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2064770554324309, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20572440612624732, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20555951978316334, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20341729904430328, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20303490871084165, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20068472361862133, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2037956432967213, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19940941468962955, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19479436456231558, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18986122237392475, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19305677314196168, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18694831716839108, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19040924166567405, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18377979812253697, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.18662456058665278, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.18545353958207345, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.18319027313000377, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.17422180099585163, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.2949146938323977, "validation/loss_best": 2.427823066711426, "validation/acc_best": 0.2739018087855297, "validation/f1_best": 0.20107671791720697} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.456556978225708, "train/grad": 0.07752097584307194, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11428955078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11111572265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1063818359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.10184814453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.097021484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.089664306640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.080296630859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.068262939453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0501263427734373, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0281060791015624, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.004676513671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.96861083984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9344552612304686, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8886138916015627, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8471383666992187, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8052024841308594, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.741324462890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.65638916015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5794245910644533, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5350264358520507, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.496102142333984, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4622196102142335, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.426179676055908, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3874079895019533, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.346574912071228, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2991150712966917, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2586654114723204, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2240731322765352, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.1777825379371643, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.126328568458557, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0860198509693144, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.053982799053192, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.016637386083603, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9875202071666718, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.954197416305542, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9312746196985244, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8979999428987504, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8801554667949676, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8752142953872681, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8810046869516373, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8926026850938797, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9222675251960755, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9745985156297683, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0111777639389037, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.083383782505989, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.139821739792824, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.1803123462200165, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.2560079979896543, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.3346910393238067, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004418069387320429, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004488871560897678, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004568114320281893, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004614958838792518, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00464593107579276, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004679775056429207, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004717131429351866, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004764108029194176, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004835875595454127, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004919910577591509, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005003962086047978, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005123588619753718, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0052332114987075325, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005393077714834362, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005570737989619374, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0058028561272658406, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0063093563262373205, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00718178934417665, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007901102511677891, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008270316619891672, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008568195956759155, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00883802075870335, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009159264515619724, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009530899412930012, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0099443049589172, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010423473287373782, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01082487597130239, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011168987317942082, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01162725483532995, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012133423951454461, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.012559186848811806, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012921642162837088, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01333024725317955, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.013645673636347055, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.013993135215714573, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014270542608574032, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.014663247857242823, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.014951934330165386, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015334030999802052, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015846090917475523, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016074791783466935, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01613398297689855, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.016224600211717188, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016242538150399922, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.016029962138272822, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01594215755816549, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.016095245387405158, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.015885229404084385, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.015619531758129596, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1112051010131836, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1078176498413086, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1027567386627197, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0976853370666504, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0923171043395996, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.083949089050293, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0730831623077393, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0590858459472656, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0377936363220215, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.012383222579956, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9860196113586426, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.946934223175049, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.9118521213531494, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.866755723953247, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8267107009887695, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7857460975646973, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.722327470779419, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.638826847076416, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.573432445526123, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.542440891265869, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.51859712600708, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4996402263641357, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4812326431274414, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4651074409484863, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4506304264068604, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4369592666625977, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.433241844177246, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.437777519226074, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.454500198364258, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4803645610809326, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5034923553466797, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5244293212890625, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5517866611480713, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5797383785247803, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.617408275604248, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6581344604492188, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.704843759536743, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7261102199554443, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7583861351013184, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.818044900894165, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8034048080444336, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.783541202545166, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8002254962921143, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.779855728149414, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.746612071990967, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6984152793884277, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6898796558380127, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.67822003364563, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6809916496276855, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08471760797342193, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.09856035437430787, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.11074197120708748, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1212624584717608, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1288298265042451, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1345514950166113, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.13971945367294206, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.14248800295311922, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15208564045773348, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15928386858619417, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.165374677002584, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18383167220376523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2115171650055371, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2262827611664821, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23735695828719083, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24713916574381692, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25193798449612403, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2532299741602067, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25692137320044295, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2707641196013289, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26799557032115173, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.262827611664821, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2264673311184939, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2320044296788483, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2334809892949428, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23477297895902546, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2364341085271318, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.24067921742340348, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23938722775932078, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23274270948689554, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.23920265780730898, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00848371230446702, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008459266715256568, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009118333033456313, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01231015320395581, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015037304491034922, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.021399146380703078, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.030311076679926195, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03822903585336682, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04541744331379913, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05024915483797201, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.052886560467089144, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05732589034902059, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06056143840854605, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.068313352124559, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07532639986903784, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08146024762788857, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.10080499388071378, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13268302885191152, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.15121339877487563, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16378613914706566, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17352955339219042, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17800899094371014, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17900049358131565, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18318997737782192, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18789013068191074, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19489153974108286, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20086683866800778, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2011494995883781, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19946149515114883, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20526614570606494, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20813289929754442, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20660261695172863, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20452636548384476, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20691390497595766, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20011392104131423, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1953111703951992, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19383604032112134, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19441284663078992, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18879117090344158, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17678046540448078, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18163021488392891, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1880715706110705, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1882880968724323, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18318327068931453, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.179398452874855, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.18625704470056073, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.18571533737651427, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.17550163803287133, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.18173779883192773, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.2586654114723204, "validation/loss_best": 2.433241844177246, "validation/acc_best": 0.2707641196013289, "validation/f1_best": 0.20086683866800778} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.430168423652649, "train/grad": 0.07789480179548264, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.11506591796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.11207763671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.107216796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.102354736328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.096895751953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.088758544921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.07815673828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.064803466796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.044490966796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0204144287109376, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.995335693359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.957720947265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9228802490234376, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8765155029296876, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.833715515136719, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7883267211914062, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7192121887207032, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.633892288208008, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.564341812133789, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.523412094116211, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.485473213195801, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4512234115600586, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.414354820251465, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3751923561096193, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3343634510040285, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.287093467712402, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2472156429290773, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.212424325942993, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.1641128730773924, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1101165199279786, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.067528657913208, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.03366512298584, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9932482242584229, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9612736928462982, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9196301651000978, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8865035235881806, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8439205604791642, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.8238440024852753, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8151780372858048, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8140082329511642, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.818803580403328, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.841687119603157, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9076073801517486, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9422230941057206, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.0136012917757036, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.0731232953071594, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.12111230134964, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.198242634534836, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.2758960449695587, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004434609772870317, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004497942054877057, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004565844993339852, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004605780174024403, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0046334817935712634, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004667158519150689, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004707405293593183, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004759639203548431, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004838699158281088, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004928960998076945, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005016870847903192, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005141879762522877, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005259007585700601, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005436832779087126, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005644137908238918, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005931188513059169, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006556030851788819, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007434022577945143, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008048519385047257, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00837186431279406, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0086591315548867, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008945323845837265, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009289564150385558, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009684222140349448, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010112089337781072, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010592737044207752, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010999660156667233, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0113464274443686, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01181748750153929, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012341357944533228, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0127522095432505, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013095322730951011, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013501061056740583, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.013798353765159845, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014173907954245805, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014495838657021523, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.014951091031543911, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.015238512051291763, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015512364823371172, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01591455557849258, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01622242555953562, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01623953538481146, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.016219371724873782, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016293558864854275, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015914752916432916, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01565585517324507, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015774919907562433, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.015579466759227216, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014993129996582866, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1098806858062744, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1064870357513428, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.101177453994751, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.095747470855713, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0898430347442627, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0806422233581543, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0686135292053223, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.053126573562622, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0297791957855225, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.002392292022705, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9746627807617188, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9345321655273438, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8991165161132812, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.853667974472046, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.81207275390625, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7676427364349365, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6981096267700195, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.614799976348877, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.558943510055542, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5315887928009033, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.509343385696411, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4905154705047607, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.472053050994873, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.456204891204834, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4430885314941406, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.433150053024292, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4317147731781006, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4359638690948486, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4503581523895264, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.471797227859497, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4922831058502197, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.516723394393921, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5519983768463135, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5812883377075195, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.615915536880493, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.656881093978882, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6950342655181885, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7201220989227295, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.787496328353882, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.828458547592163, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.809669017791748, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8210690021514893, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.788093090057373, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7536191940307617, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7006120681762695, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.681567668914795, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6575281620025635, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6498725414276123, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.622560501098633, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07585825027685493, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08822443706164636, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.10483573274270949, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.11664820967146548, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1256921373200443, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1314138058324105, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13528977482465854, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.13953488372093023, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.14599483204134367, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15485418973791068, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1640826873385013, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1688815060908084, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1939830195644149, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21963824289405684, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2334809892949428, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24473975636766335, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25230712440014763, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2541528239202658, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25655223329641935, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.266703580657069, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2703949796973053, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2692875599852344, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26891842008121075, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24473975636766335, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23606496862310816, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23920265780730898, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2351421188630491, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2410483573274271, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.24289405684754523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.24381690660760427, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2469545957918051, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2410483573274271, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008285321538103014, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008390592502072091, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010021441028853757, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013994566924929489, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015905178163953673, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.02393989159364257, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03573558337666926, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.043661483723130286, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.04895886562642731, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05208210011995556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0543773959963308, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05856831057681903, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06332508804673082, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07004000467438763, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08010545340439122, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08566036403428819, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11264903842014563, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1418355544966198, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1562815732101392, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16780351786872008, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1751197877154335, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17709005562284078, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1812430239309187, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18686301610972858, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19279241180140314, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1950060042656173, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19839212423873653, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2046347321240077, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20729453526685496, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21232742043265462, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20907985208214963, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20766751810077003, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2132538223344376, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2134897124069968, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20810732279528443, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2045829339096835, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20522532073054656, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20241119518805686, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1954394495226447, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1893302469454329, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19242406130838718, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19380589829748926, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1898772911134516, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19578454314795932, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19687886519553588, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19494802005651704, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.19713391053425247, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.19643297135198393, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.18502748313153194, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 2.212424325942993, "validation/loss_best": 2.4359638690948486, "validation/acc_best": 0.2703949796973053, "validation/f1_best": 0.2046347321240077} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.3810491859912872, "train/grad": 0.07754158314317465, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1126220703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1093603515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.10419921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.098892822265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.093065185546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.084158935546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.07251708984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.05770751953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0355718994140624, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0095562744140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.98301513671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.943431396484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.907421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.859468688964844, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8138002014160155, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7637760925292967, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6877406311035155, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6008362579345703, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5371499633789063, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4985214996337892, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.460752487182617, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4247432708740235, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3853141403198244, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3434957313537597, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.299933605194092, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.249867362976074, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2075729465484617, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1702365016937257, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.1184315061569214, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0607435274124146, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.015515661239624, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9786083459854127, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9310272073745727, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8960209238529204, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8511182951927185, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8124332892894746, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.7618204486370086, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.7330908346176148, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.7095633798837662, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.699637776017189, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.701152695417404, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7212088429927825, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.779484840631485, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.8118175292015075, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.8987749725580216, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.9723978579044341, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.015482017993927, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.100565881729126, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.187787218093872, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004387361409608275, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004446975828614086, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00450920163304545, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004546775011112914, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004574283132096752, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00461040862952359, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004655612917849794, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0047143550566397605, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004801043833140284, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00489749277359806, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0049886427819728855, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005116695563774556, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00523694264004007, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005423180244397372, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005649362669792026, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005980280730873346, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006674764936324209, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007504291816148907, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008033392000943423, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008325507869012655, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008608993112575262, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00890968054300174, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00927120953798294, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009682542467489839, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010123835001140833, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010613454887643457, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011030543078668416, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011393299223855138, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011879226467572153, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012404476744122803, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.012826361753977835, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013177798730321228, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013569295136258007, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.013860035282559692, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014238579072989524, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014576487173326314, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.015030201491899788, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0153114825906232, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015556080802343785, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015841089077293872, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016119111231528222, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016158486790955065, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.016087607089430092, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016088770739734172, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015773155181668698, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015581229659728706, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015358197847381233, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.015021301750093698, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014415671373717487, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.108832359313965, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1053855419158936, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0998458862304688, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0940420627593994, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0877089500427246, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.077761650085449, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.064732074737549, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0480284690856934, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0230841636657715, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9942541122436523, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9656176567077637, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.924931764602661, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.889582633972168, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8440842628479004, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8013968467712402, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.754028558731079, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6802852153778076, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5998358726501465, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5513477325439453, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5267510414123535, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.505539894104004, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4865529537200928, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4676074981689453, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.451381206512451, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.437483310699463, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4281482696533203, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.428344964981079, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.434566020965576, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4525883197784424, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4825403690338135, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.514068126678467, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.543684244155884, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5816702842712402, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.610391855239868, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6420581340789795, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.67427396774292, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.715157985687256, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7415735721588135, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7907907962799072, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.842881679534912, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.840688705444336, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8553476333618164, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.848276376724243, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.816593647003174, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.751601219177246, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7032642364501953, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6854660511016846, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.639235258102417, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6141507625579834, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08010335917312661, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.09246954595791805, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.10815799187892211, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.11997046880767812, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1288298265042451, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.13233665559246954, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13842746400885936, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1421188630490956, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.14950166112956811, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15706902916205243, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1642672572905131, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17257290513104467, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20081210778885197, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22369878183831673, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2355112587670727, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24363233665559247, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25064599483204136, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25341454411221853, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25655223329641935, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2606127722406792, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.266703580657069, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2692875599852344, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.27113325950535255, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.268733850129199, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23994093761535623, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23883351790328536, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23181985972683647, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23403469915097821, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23569582871908454, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2369878183831672, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2395717977113326, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.24234034699150978, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2425249169435216, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.24086378737541528, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008277023623619767, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008291513833986167, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010398653889204926, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014706162133953588, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01771699652847294, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.027136384908145714, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.037891830526979725, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.045602043645034056, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.050831771973068984, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.052710842762232285, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.056750797853823816, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.060369252840614444, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0653975027826852, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07270746396515745, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08040384100872211, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08968373518571811, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11967116319494416, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.14678969181194138, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.15926349706848308, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16796045060277276, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17466399909248476, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17985492388659693, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1842041117822523, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19052895114083712, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19906755490310515, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2034954618530419, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20827559885412372, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20858008449476462, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20872698520742783, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2118414043439821, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2126466897804887, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21020212543292313, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2073864663042029, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2121517921073941, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20960261543736633, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20685896764617254, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20445950789026449, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20304943211993678, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19349359592343926, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19234058078915284, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19400556874980243, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19389335916158723, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19065662427645017, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19443290240942054, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19539471502423342, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19594064227697405, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.19474196666984878, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.19339131646409694, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1902055655142192, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.2075729465484617, "validation/loss_best": 2.428344964981079, "validation/acc_best": 0.2713178294573643, "validation/f1_best": 0.20827559885412372} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.3432770693302154, "train/grad": 0.07779950831085443, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.111624755859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1082666015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1027685546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.097078857421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.090799560546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.081187744140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.068641357421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.05262451171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0289312744140626, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0014068603515627, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.97352783203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9329043579101564, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.896211853027344, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.847352294921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7997227478027344, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.746562652587891, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.667983093261719, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5836863708496094, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5245932006835936, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.488176784515381, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.451547050476074, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4158139991760255, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.375961194038391, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3327745723724367, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2872281098365783, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.234194931983948, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1891671657562255, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.149498974084854, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0953773415088652, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.034470626115799, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.984546856880188, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9431234860420228, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.89054094851017, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8471796894073487, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7905775606632233, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.7438086771965027, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6872291618585586, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6517713433504104, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.6298217153549195, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.601977590918541, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.597113670706749, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.6092931401729584, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.656997231245041, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.715527861714363, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.8008131474256515, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.8755428159236909, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.9157186180353165, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.0042342150211336, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.104675762653351, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004481037346413359, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004536634044488892, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004593712235800922, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004627860133768991, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004654794376110658, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00469173212419264, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004739318710053339, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00480122487177141, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0048916652053594585, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004989712887909264, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0050816158507950605, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005209134856704623, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005330213962588459, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005522139584645629, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005764530056621879, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0061365649034269155, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006885223763529211, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007677264849189669, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008162596852052957, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008440799044910819, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008725074524991215, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009037573176901787, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00941408123355359, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009839358921162784, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010288752410560846, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010784161123447121, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011202305438928306, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011564592346549035, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012059669219888746, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01259931446518749, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013008844703435898, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013322261380963027, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013647567410953344, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.013884454723447561, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014227084359154105, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014590070224367082, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.015050350283272564, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01531952727586031, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015561723206192256, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015824762643314897, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016039333981461824, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016051418078131974, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0161041760770604, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01613445996772498, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015775322178378702, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015384968360885978, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01527415337972343, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014812643523328006, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014078988702967763, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1080613136291504, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.104545831680298, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0988335609436035, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.092738389968872, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.086064338684082, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.075547456741333, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0617733001708984, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0441508293151855, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.018019199371338, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9882571697235107, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.958994150161743, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.917999505996704, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8825883865356445, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8367393016815186, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7928788661956787, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7433054447174072, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.667233467102051, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5898404121398926, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.545283794403076, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.521916151046753, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.501105785369873, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4822773933410645, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.463690996170044, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4477057456970215, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4342851638793945, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.426023244857788, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4270834922790527, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.433832883834839, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4521560668945312, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4813754558563232, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5112507343292236, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.539552688598633, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.575352907180786, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6076114177703857, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6491589546203613, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6884355545043945, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.743926763534546, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.777174711227417, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8264544010162354, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8627843856811523, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.8895821571350098, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9023590087890625, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.878305435180664, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.834778308868408, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.782961130142212, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.75312876701355, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7222657203674316, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6599936485290527, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.620737075805664, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07401255075673681, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08176448874123293, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.09486895533407161, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.11037283130306386, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.12089331856773718, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12809154669619785, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1343669250645995, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1378737541528239, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1435954226651901, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1509782207456626, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15873015873015872, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1642672572905131, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17792543373938724, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20450350682908822, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22720561092654115, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.23883351790328536, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24861572535991142, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2532299741602067, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2567368032484312, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2587670727205611, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26301218161683276, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2692875599852344, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2709486895533407, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2705795496493171, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2336655592469546, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23477297895902546, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2351421188630491, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24160206718346253, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23864894795127353, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.24049464747139165, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.24234034699150978, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.24658545588778147, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.24732373569582872, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008502990833586604, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008709202028604443, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01057940559280686, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015308078172447783, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.019033141382164127, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.029007697558913945, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.039416346136693765, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04534887695430095, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0501757529788233, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05426645177066477, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05677501109421318, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06200339481715419, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06747097862982694, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07548356068888189, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08150426898174555, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09610486687455166, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12253070156822005, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1491384552845941, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16175958781678043, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17053525993519866, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17702993633709696, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18004329962072316, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18429548194313664, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19131835487168805, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19896246221324457, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20140473165283104, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2043294690357789, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20735268038448273, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20867488246720725, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21153725533135323, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21427637334803454, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21121770427641798, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.21052635058338853, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.2124761979043166, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20833819555284708, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20371478940183066, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2033664649467697, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20071890622077282, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19775605379066197, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19095733942543638, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1951187284043607, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19518764866383562, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19807203477671387, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.20067084009745426, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19664971350626914, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1982822738581159, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.20042848410157635, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.2032423592621535, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1947938087490305, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.1891671657562255, "validation/loss_best": 2.4270834922790527, "validation/acc_best": 0.2709486895533407, "validation/f1_best": 0.2043294690357789} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.323650384545326, "train/grad": 0.0783447015285492, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.112342529296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.10917236328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1038134765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.098111572265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.09180908203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.082109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.06953369140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.05356201171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.029891357421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0026373291015624, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.97541259765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9357614135742187, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.9000399780273436, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.85216552734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.804978790283203, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.751849365234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6745294952392578, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5957304763793947, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5412516593933105, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5059037971496583, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4690106868743897, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.432418565750122, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3917920541763307, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.347856254577637, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.302080502510071, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2484364795684812, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2022448527812957, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.160529339313507, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.1026095724105835, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0365302062034605, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9816820013523102, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9366693496704102, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8778753930330276, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8306187617778777, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7730669128894805, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.725860407948494, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6573554062843323, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6116892093420028, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.5739196562767028, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.5263609075546265, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.5014683401584625, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.5103249508142471, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.5470419889688491, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.5885679602622986, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.6823486131429672, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.76330539226532, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.8243245923519134, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.92646781206131, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.035809665322304, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0044727341493126, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004528250546427443, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004584115520119667, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004618342405883595, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0046456767024938015, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004683931486215443, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0047335454472340645, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004797620601020753, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0048897223372478035, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0049888338765595105, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005081446452531963, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005213034187909216, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005340873068198562, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005547674752306193, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005813106191344559, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0062249232199974355, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007010801988653839, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007774302044417709, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008230575732886792, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008502072875853629, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00879121241858229, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009113013090100139, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009497097020503133, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00992731812875718, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010375737431459128, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01087291853968054, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011295662680640816, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011662618876434862, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012159309927374124, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012694565253332258, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013111152183264495, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013433645153418184, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013792259143665433, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014077218691818416, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01449157718103379, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014846495632082225, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.015319006778299808, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01557966370601207, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01576589062344283, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015940544647164642, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016068795979954302, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016048601139336826, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.016085562920197846, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016039959639310836, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01582378304563463, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015523454090580344, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015247096484526991, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014833131982013583, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014070026073604823, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.107574462890625, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1040232181549072, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0981569290161133, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.091891050338745, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.084979772567749, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0740857124328613, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.059807062149048, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0415515899658203, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.014683485031128, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9843220710754395, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9547934532165527, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.913719415664673, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8784022331237793, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8325536251068115, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.788087844848633, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.737159490585327, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.660017728805542, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.585476875305176, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5438694953918457, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.52164626121521, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.501408338546753, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4831125736236572, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4659605026245117, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4516351222991943, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.440814971923828, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4366981983184814, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4414775371551514, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.452043056488037, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4750607013702393, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5077931880950928, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.539231300354004, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.568938970565796, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.611074686050415, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.646000862121582, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.686899185180664, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.727445363998413, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.790788173675537, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8302698135375977, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.880833148956299, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9525601863861084, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.96946120262146, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0049283504486084, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9882678985595703, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.9393603801727295, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8892221450805664, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8398947715759277, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7853024005889893, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.73750376701355, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6484193801879883, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0754891103728313, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0828719084533038, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.09819121447028424, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.11166482096714656, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.12015503875968993, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12809154669619785, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13861203396087118, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1435954226651901, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15171650055370986, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15909929863418235, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16463639719453674, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18161683277962348, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20487264673311184, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22868217054263565, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.23791066814322628, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24732373569582872, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2532299741602067, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25544481358434845, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.25655223329641935, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.262827611664821, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26578073089701, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2702104097452935, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26836471022517533, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22905131044665927, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23624953857511996, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2201919527500923, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22369878183831673, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2321889996308601, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.23403469915097821, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23661867847914358, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2368032484311554, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.24381690660760427, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008492832686033501, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008990696937594323, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.011583100322199608, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0158183263078742, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0204456179068611, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03165054498042636, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03980907288209552, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.045722965668531707, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.050143977041160144, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.054884686043641655, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05799022720760689, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.062499757573185155, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06838752313150669, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0763610984857719, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.082597902998026, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10003587046088219, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12472132193799373, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.15125840138188285, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16171935990766603, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17178828488184947, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17797196621155345, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1800633078529235, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18551566264158115, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19360836397920336, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19838123614400704, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20387621563662517, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20548260281195677, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20798780390160487, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.21075559110516306, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20870562453889918, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20720045736540815, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2054294180401576, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20338415700585288, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20091190962404426, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19853361501679379, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.195942403265173, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19618064983296604, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1961458622207525, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1918998883386085, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18818549370075374, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2005508379078588, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19059801198256313, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18877784237127235, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19405630377837188, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19238061612774549, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19277614080317687, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.19700010506438762, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.19476727618742182, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.19726389991521742, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 2.160529339313507, "validation/loss_best": 2.452043056488037, "validation/acc_best": 0.2702104097452935, "validation/f1_best": 0.20798780390160487} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.281551686525345, "train/grad": 0.07786541130393744, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.113392333984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1101318359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.10452392578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.098643798828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.09211669921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0819677734375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.068919677734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.052305908203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0278253173828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.999801025390625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9719805908203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9319989013671877, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8960751342773436, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8478712463378906, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7998907470703127, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.744841766357422, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6635145568847656, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.580587387084961, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.523411293029785, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4865838050842286, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.448500156402588, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4104955768585206, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.368313374519348, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3226811933517455, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2748979353904724, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2198543643951414, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1722779440879822, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1294960868358612, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0700228929519655, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0021868562698364, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.946604917049408, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8999059104919434, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8376745569705963, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.787083957195282, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.722548320889473, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6652550321817399, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.588422423005104, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5317731153964997, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4879082214832307, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4359439241886138, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3949530094861984, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3919531846046447, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.4215581905841828, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.462805339694023, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.5438878065347672, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.6354649132490158, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.6983684700727464, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.799582332968712, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.9292309427261352, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004435796766774729, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004487160723656416, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00453939687460661, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004572167611913755, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004599159506615252, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004638226282550022, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004689172324724496, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004754507692996413, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0048482858017086985, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004947623594198376, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005039770749863237, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005171621085610241, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005300649246200919, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005512049091048538, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005787755409255624, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0062184434058144685, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007020263173617422, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007765663180034608, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008202049494720996, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008464011268224568, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008750169333070516, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009073367840610445, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009458974038716405, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009891332476399839, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010340308272279799, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01083628648892045, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011255071638152004, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0116155386576429, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012111697983928025, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012646167282946407, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013060893341898918, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013389300093986095, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013763159518130124, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014036335735581815, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01440834510140121, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014720759065821766, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01513575178105384, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.015349020073190332, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015534030310809611, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015686226268298922, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.015873446026816965, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015844627395272256, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015815647966228426, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015869693369604646, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015753677235916256, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015500292503274978, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015318181868642568, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014964261939749122, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014245174848474563, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1072583198547363, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1036815643310547, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0977132320404053, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.091322422027588, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.084277391433716, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0731430053710938, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.058506488800049, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0399057865142822, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.012568712234497, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.981825351715088, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.952117681503296, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9109489917755127, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8756141662597656, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.829697370529175, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.784550666809082, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.732656478881836, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.654543161392212, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5817184448242188, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5418283939361572, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.520416021347046, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.501058340072632, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.48313570022583, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4661641120910645, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4516892433166504, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.440089464187622, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4348158836364746, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4388506412506104, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4483509063720703, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4693760871887207, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.499955654144287, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.530649423599243, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5599582195281982, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5996134281158447, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6347880363464355, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6746606826782227, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7191579341888428, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.776522636413574, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8089382648468018, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.867793083190918, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.953120231628418, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.991427421569824, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.01029896736145, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.997408151626587, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.9443199634552, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.906085968017578, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8413238525390625, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.813555955886841, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7681896686553955, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6825644969940186, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08397932816537468, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.10022148394241417, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.11369509043927649, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.12144702842377261, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1286452565522333, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.13602805463270579, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13842746400885936, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14414913252122555, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15153193060169803, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15928386858619417, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16519010705057216, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1821705426356589, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20801033591731266, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22665190107050573, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.23938722775932078, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24787744555186417, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25230712440014763, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25249169435215946, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2572905131044666, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26208933185677374, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26578073089701, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26836471022517533, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26375046142488, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24713916574381692, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22886674049464747, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2336655592469546, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2249907715023994, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22591362126245848, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23440383905500184, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2320044296788483, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23735695828719083, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.24012550756736803, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23661867847914358, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.24160206718346253, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008369352122434589, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009211104327656884, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0123642973147385, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01586950461652548, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02118286947121247, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03237176170215224, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.041398268547455055, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.046364083299712124, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05034895178874013, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.054806284366721726, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0575906931386781, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06264597050717487, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06811630600188598, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07615200424506365, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08289197894631699, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10076330239316189, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12784218771323627, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1500688885791839, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16269933411535528, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17126655278342884, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17604814201264687, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1763890448268575, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1852984732841909, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19149544342432545, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1974616992869295, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20284415316238, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20372773308407352, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2061787031874278, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2070366920879397, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2113022711274902, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2104786111527153, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.207129000577666, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2053372925993425, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20674971282959365, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20303505567844574, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20380590969203385, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20268929743417885, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20502532980402796, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1949754577969737, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1885976084035664, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19634416376389421, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19170684981759786, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19156982546374124, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19937992822532716, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19549431074600418, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1981959927374156, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.20016162330735562, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.19578002375167813, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1951813562786191, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.2198543643951414, "validation/loss_best": 2.4348158836364746, "validation/acc_best": 0.27002583979328165, "validation/f1_best": 0.20284415316238} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.259935847520828, "train/grad": 0.07733772631734609, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1118408203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.108536376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.102957763671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0968603515625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.090286865234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.080072021484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0667626953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.04991943359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.025133056640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9968609619140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9689544677734374, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9286654663085936, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8927597045898437, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.844513244628906, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7959715270996095, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.740548095703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6608145141601565, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5823059844970704, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5282600212097166, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4925797462463377, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.454924478530884, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4168122673034667, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3737031412124634, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.327101764678955, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.27833211183548, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.222249755859375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.173417887687683, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1287002003192903, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0665627682209013, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9965409171581268, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9398773539066314, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.8925865906476975, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8318451815843582, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7805669862031936, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7114042526483535, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6458210104703903, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5592261153459548, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5000319093465806, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.449863811135292, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3853194922208787, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3425601923465729, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.320524959564209, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.3467426258325577, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.3787536239624023, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4461871016025543, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.527821160554886, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.584975609779358, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.6772146821022034, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.8125875222682952, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004463799860095605, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004513768918113783, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004564809702569619, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004597148030297831, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00462428905419074, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004664338307920843, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004716991607565433, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004784839430358261, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004881208555307239, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0049838056846056135, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005079420042457059, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0052152928360737864, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005347689443733543, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005563218130264431, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005843601890373975, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00628055039094761, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0070822026114910844, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007815162336919456, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008247155412100256, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008510390862356871, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008798278279136866, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009121678399387746, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00950445566792041, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009935021908022463, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010381428678520023, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010872658644802868, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011289354851469398, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011651291940361262, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012143821148201823, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012670695027336478, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013076549749821425, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013391544409096241, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013757168417796492, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014016850320622325, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014352208357304335, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014639351363293827, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.015017825313843786, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.015220937263220548, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01533021745737642, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015421544113196432, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.015533457030542194, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015503097297623754, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015534447943791748, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01552140252199024, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015379571891389787, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01522441531997174, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015068190060555936, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014832843355834483, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014256990146823228, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.10709285736084, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1034910678863525, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0974881649017334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0910158157348633, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0839033126831055, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.072614908218384, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0578296184539795, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.039036512374878, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.0114498138427734, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9805455207824707, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9507296085357666, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9095046520233154, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.874166488647461, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.828129529953003, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7827792167663574, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7303624153137207, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.652010202407837, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5800371170043945, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.540552854537964, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5190670490264893, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.499131917953491, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.480898380279541, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.463391065597534, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4488604068756104, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.43790340423584, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.433797836303711, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4385273456573486, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4483954906463623, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.469346761703491, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4997997283935547, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.531038284301758, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5613083839416504, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6042520999908447, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6390888690948486, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.681436538696289, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7289745807647705, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.791116952896118, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.83124041557312, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9011917114257812, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.983666181564331, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.024122714996338, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0530052185058594, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0466766357421875, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.9904277324676514, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.9610989093780518, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.9085211753845215, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.876197576522827, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.8268399238586426, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.744194269180298, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0769656699889258, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08471760797342193, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.10077519379844961, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.11351052048726468, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.1212624584717608, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12938353636028055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1363971945367294, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13879660391288298, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1448874123292728, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15227021040974528, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1596530084902178, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.16482096714654854, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18235511258767073, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2085640457733481, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22849760059062385, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.23901808785529716, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2502768549280177, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25359911406423036, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25378368401624213, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2587670727205611, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2646733111849391, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27113325950535255, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25452196382428943, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22868217054263565, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2321889996308601, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22425249169435216, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22535991140642303, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23089700996677742, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22905131044665927, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2349575489110373, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23735695828719083, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.23809523809523808, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00843829962530506, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009140744866998235, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01244144561288566, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016266531142860752, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021535430713976414, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03256974430281947, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.040982057344620106, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.046012331214629894, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05081433795464363, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0549659500677555, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.057751902100981335, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06313556128710657, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06810400345703015, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07596538604725964, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08283290094689065, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10055556447151874, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12832957300076223, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.15068434271274678, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16198783195810562, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1723678708306493, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17583039111299517, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1772485500546641, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18557845597325717, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19332462566865918, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1967485369211789, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20410763020642234, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20249947881329733, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20466954572069504, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20782091142984704, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2109609013752715, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21048396895028545, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2047388577413517, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20497697847186602, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20742586976372165, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20550751827295685, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2023489479508308, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2008654245770989, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20421408247601613, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19209817729525888, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18837008577095596, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19456924043814564, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18973993750927787, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18754380762095038, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19350417659472804, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.18865757421713122, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19775275799136213, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.19968131682331156, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.19902549678030526, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.18998159763063163, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.222249755859375, "validation/loss_best": 2.433797836303711, "validation/acc_best": 0.27113325950535255, "validation/f1_best": 0.20410763020642234} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.2338778442144394, "train/grad": 0.07650299690663814, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.108974609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.105361328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.09960693359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0933447265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.086612548828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.076004638671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.062232666015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.044822998046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0190850830078126, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9898321533203127, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.960792236328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.919380798339844, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8824081420898438, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8328485107421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7829518127441406, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7255357360839843, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6431292724609374, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5649024200439454, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.51230504989624, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.477306594848633, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4397093296051025, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.401332197189331, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.357705760002136, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3101809644699096, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.26066992521286, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.203862726688385, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1549570763111117, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.111190826892853, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0507012724876406, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9822844123840333, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9257929348945617, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.876877417564392, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8114886182546615, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7571285796165466, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.688834638595581, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6213717198371886, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5323015469312669, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.467285760641098, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4072086507081984, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3378073346614838, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2984318029880524, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.2757054793834686, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2857909822463989, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.31103047311306, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3686039972305297, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.4431611996889115, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.4985900968313217, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.5833645832538605, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.709207854270935, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00440380961401388, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004453413803130388, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004504595617763698, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00453845510375686, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004567468921886757, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004609807946253568, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004665495882509276, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004736230053240433, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0048361336649395525, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004941499083070084, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005039303516969085, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005177693222649395, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005312484512105584, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005531862645875662, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005817539866548031, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00626110538141802, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007066626399755478, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007798900469206274, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008229222921654582, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008490268578752876, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00877685496583581, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0090997307584621, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009481557160615921, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00990691252052784, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010343595673330128, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010826177764683961, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011234948863275349, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011590869496576488, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012077085487544537, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012602594206109643, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013006751034408808, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013322527543641627, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.013666697926819325, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.013914528083987535, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014241924863308669, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014538654396310448, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01489142346661538, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.015057594534009695, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015132822073064744, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015247117462567985, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01532487710006535, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01527864213567227, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01517639529891312, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015146059892140329, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015023122448474169, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014946896168403327, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01480008235666901, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014592814790084958, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014111241856589914, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1070218086242676, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1034154891967773, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0973987579345703, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0908944606781006, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.083759069442749, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0724234580993652, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.0575904846191406, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.038705348968506, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.01102614402771, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9800760746002197, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9502193927764893, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.909011125564575, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.873704195022583, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8276572227478027, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7823190689086914, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.729712963104248, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6511857509613037, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.579549551010132, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.540268659591675, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5188636779785156, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4990296363830566, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.480769634246826, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4635322093963623, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.449099540710449, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4380273818969727, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.43367338180542, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4381847381591797, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4479217529296875, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4685845375061035, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4983060359954834, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5292136669158936, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5586957931518555, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.600023031234741, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6356749534606934, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.679769277572632, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.72994327545166, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7921063899993896, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8345189094543457, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9028382301330566, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.982442855834961, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0211071968078613, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0504026412963867, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.049715995788574, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0098609924316406, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.9684481620788574, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.913100481033325, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.879234790802002, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.833130359649658, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7535369396209717, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0769656699889258, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08508674787744555, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.10077519379844961, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.11406423034330011, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.1212624584717608, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12956810631229235, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1362126245847176, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13861203396087118, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.14470284237726097, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.15208564045773348, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15909929863418235, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.165374677002584, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18272425249169436, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20801033591731266, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22886674049464747, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.23883351790328536, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2499077150239941, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2526762643041713, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25489110372831303, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2576596530084902, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26411960132890366, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26651901070505724, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27150239940937615, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2691029900332226, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.262827611664821, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2528608342561831, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22960502030269472, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2321889996308601, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22591362126245848, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2307124400147656, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22886674049464747, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23661867847914358, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.23920265780730898, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008417905437195162, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009142659434623621, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012627350571873731, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016348246238269432, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021641687174224003, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03255971887244513, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.041226369950302794, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04605809742992035, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05093420597868462, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.054626840121924015, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05767669156894938, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.06313177395276677, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06804345338950477, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.07565754480605448, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08316449730436044, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10127406563084397, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1281200647711387, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.15144601680172376, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16225361563938318, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17266355803151426, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17541411111640914, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1785461469814823, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18508883067737136, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19248315967902138, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19781453600912755, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20415910830504344, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2038769432634472, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20619572281162044, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20830291076835725, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2135115034659866, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2094658741401613, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20505936416863046, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20630209099161056, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20504996384626464, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20439994077464227, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20232523852408313, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20199256975154714, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20412398348852576, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19490021812340177, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19094254021413556, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19680837559418932, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19327809867852633, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19093477906703618, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19477098465328693, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1916233426862376, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19501013034961645, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.19929128501760995, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.20130719112228487, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.19830862930376045, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.203862726688385, "validation/loss_best": 2.43367338180542, "validation/acc_best": 0.27150239940937615, "validation/f1_best": 0.20415910830504344} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.2300677901506423, "train/grad": 0.07665639162063599, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.110224609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.106842041015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.101090087890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.09500732421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.088389892578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.078082275390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0647027587890623, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0478173828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0229461669921873, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9947503662109374, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.9667626953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9264324951171874, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.890455322265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.842002258300781, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.793185577392578, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.73736572265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6563265991210936, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5767861938476564, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5225829315185546, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.486345024108887, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.447365989685059, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4074080657958983, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.363041343688965, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.315610046386719, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.266128339767456, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.209192771911621, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1599711990356445, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.115803985595703, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.054869918823242, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9839990663528442, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9255817413330079, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.875159900188446, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8071789360046386, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.751920907497406, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.6818645644187926, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.6139024543762206, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.5224609273672103, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.45880701482296, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4045835942029954, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3370813286304475, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.286650367975235, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.258141713142395, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2674604612588882, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.2856367635726929, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.3360909360647202, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.4001247262954712, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.4490438324213029, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.5218475866317749, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.6582975107431412, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004467031371314078, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00451574761653319, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00456514090532437, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00459666465758346, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004623617336619645, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004663001626031473, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004715116200968623, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004781418303027749, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004875817454885692, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004975740311201662, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005068704378791153, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005200474844314158, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00532924312632531, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005540426187217236, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00581980749964714, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006261949392501265, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007071213533636183, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007807498029433191, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008247946936171502, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008517827168107032, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008813587853219361, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00914398186141625, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009536728356033563, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009974948219023646, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01042309906333685, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010915618645958603, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011332456823438405, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011694851075299084, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012185579305514694, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012716414164751768, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.013115587732754648, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.013426516223698854, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01377291850745678, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.013998842281289399, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014329125341027975, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014618516750633716, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.014953311700373888, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.015126495799049735, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015203911233693362, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.015265702111646533, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.015259074862115085, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.015180970532819629, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015106516610831022, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015094389799050987, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.014962498717941343, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014823390170931816, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014665310485288501, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014474822389893234, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014030413748696447, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1070151329040527, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1034059524536133, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.097384452819824, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0908827781677246, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0837366580963135, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.072397470474243, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.05755615234375, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0386576652526855, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.010974407196045, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9800052642822266, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.950162887573242, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9089362621307373, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8736395835876465, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.827582359313965, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.78218674659729, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7295684814453125, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6510229110717773, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5793862342834473, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.540123462677002, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.518723487854004, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.498865842819214, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4807229042053223, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4633030891418457, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.448920965194702, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4377682209014893, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.433335542678833, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4377293586730957, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4474055767059326, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.467780351638794, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.497504234313965, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.528076171875, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.557281732559204, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.598717212677002, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6338722705841064, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6765968799591064, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7250730991363525, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7880008220672607, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8299498558044434, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8994338512420654, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.977837324142456, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.017622232437134, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.049055337905884, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.045480966567993, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.005587100982666, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.965353488922119, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.9107797145843506, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.880434036254883, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.832493305206299, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7557713985443115, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0769656699889258, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08508674787744555, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.10095976375046142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.1138796603912883, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.1212624584717608, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.12938353636028055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1362126245847176, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.13861203396087118, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1448874123292728, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1524547803617571, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.15891472868217055, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1657438169066076, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18290882244370615, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2081949058693245, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22868217054263565, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.23883351790328536, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2499077150239941, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2532299741602067, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25507567368032485, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2582133628645257, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26448874123292726, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2692875599852344, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26947212993724623, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24437061646363972, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22849760059062385, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23292727943890734, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22609819121447028, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22535991140642303, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23163528977482467, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2279438907345884, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.23237356958287192, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2355112587670727, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.23864894795127353, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.23994093761535623, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0084155404956808, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009142659434623621, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012689419676616777, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016345603147689413, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.021641687174224003, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03261761401792083, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.041162845502363175, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04605243335802515, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05084317074220953, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.054619925942211156, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.05769175559364576, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0632164600326469, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.06831474344238268, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0756856080651393, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.08330508918212041, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10141554826810033, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1282890356328712, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1511244153807216, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16224694249279717, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1725230045706565, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17601915795080655, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17877526524181162, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18571667546805418, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1928202980166496, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19772147437392085, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2045602904745525, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20349385394091557, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2063961527428115, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20900193174343776, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21330908559006753, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20990861791652052, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2062807059950167, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20831163689425625, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20699434755889842, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20369032699481307, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20259334903306112, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20153286803051096, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2040320026770225, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19584466577886303, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1889032081041202, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19754867136373644, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19258465154963123, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18975624026637358, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19658253992244226, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.19102990019221314, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19511889793463177, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.19811533591870223, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.202133903497122, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.19775357379924965, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.209192771911621, "validation/loss_best": 2.433335542678833, "validation/acc_best": 0.2713178294573643, "validation/f1_best": 0.2045602904745525} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/config.yaml b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9f975778ed409062413eef54fa4260923f152cf1 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (nsd_cococlip patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..83b84ac14a5841c90a6121b2cfafe9262e10e316 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 19, "eval/id_best": 47, "eval/lr_best": 0.012899999999999998, "eval/wd_best": 0.05, "eval/train/loss": 2.6421639919281006, "eval/train/acc": 0.23040044254586803, "eval/train/acc_std": 0.0021191913989343724, "eval/train/f1": 0.16953420992493587, "eval/train/f1_std": 0.0020270705260694074, "eval/validation/loss": 2.7155017852783203, "eval/validation/acc": 0.2024732373569583, "eval/validation/acc_std": 0.004934505885757396, "eval/validation/f1": 0.1357424119482108, "eval/validation/f1_std": 0.004218270105620033, "eval/test/loss": 2.6492323875427246, "eval/test/acc": 0.21929499072356215, "eval/test/acc_std": 0.00466207156531081, "eval/test/f1": 0.14367467984267523, "eval/test/f1_std": 0.004186820206192118, "eval/testid/loss": 2.793358564376831, "eval/testid/acc": 0.17910160015423174, "eval/testid/acc_std": 0.004677208127250881, "eval/testid/f1": 0.12332880335157931, "eval/testid/f1_std": 0.004086355416255143} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..e6d542d956b7472852ae9503f345eefaff33fdbe --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 19, "eval/best/id_best": 47, "eval/best/lr_best": 0.012899999999999998, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.6421639919281006, "eval/best/train/acc": 0.23040044254586803, "eval/best/train/acc_std": 0.0021191913989343724, "eval/best/train/f1": 0.16953420992493587, "eval/best/train/f1_std": 0.0020270705260694074, "eval/best/validation/loss": 2.7155017852783203, "eval/best/validation/acc": 0.2024732373569583, "eval/best/validation/acc_std": 0.004934505885757396, "eval/best/validation/f1": 0.1357424119482108, "eval/best/validation/f1_std": 0.004218270105620033, "eval/best/test/loss": 2.6492323875427246, "eval/best/test/acc": 0.21929499072356215, "eval/best/test/acc_std": 0.00466207156531081, "eval/best/test/f1": 0.14367467984267523, "eval/best/test/f1_std": 0.004186820206192118, "eval/best/testid/loss": 2.793358564376831, "eval/best/testid/acc": 0.17910160015423174, "eval/best/testid/acc_std": 0.004677208127250881, "eval/best/testid/f1": 0.12332880335157931, "eval/best/testid/f1_std": 0.004086355416255143} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..fc5d4ae4db292020050875e38987e727485b0051 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 47, "eval/last/lr_best": 0.012899999999999998, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.6421639919281006, "eval/last/train/acc": 0.23040044254586803, "eval/last/train/acc_std": 0.0021191913989343724, "eval/last/train/f1": 0.16953420992493587, "eval/last/train/f1_std": 0.0020270705260694074, "eval/last/validation/loss": 2.7155017852783203, "eval/last/validation/acc": 0.2024732373569583, "eval/last/validation/acc_std": 0.004934505885757396, "eval/last/validation/f1": 0.1357424119482108, "eval/last/validation/f1_std": 0.004218270105620033, "eval/last/test/loss": 2.6492323875427246, "eval/last/test/acc": 0.21929499072356215, "eval/last/test/acc_std": 0.00466207156531081, "eval/last/test/f1": 0.14367467984267523, "eval/last/test/f1_std": 0.004186820206192118, "eval/last/testid/loss": 2.793358564376831, "eval/last/testid/acc": 0.17910160015423174, "eval/last/testid/acc_std": 0.004677208127250881, "eval/last/testid/f1": 0.12332880335157931, "eval/last/testid/f1_std": 0.004086355416255143} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..802c85b32f068b3745a630d52a1177b8c7bec5dd --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",train,2.6421639919281006,0.23040044254586803,0.0021191913989343724,0.16953420992493587,0.0020270705260694074 +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",validation,2.7155017852783203,0.2024732373569583,0.004934505885757396,0.1357424119482108,0.004218270105620033 +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",test,2.6492323875427246,0.21929499072356215,0.00466207156531081,0.14367467984267523,0.004186820206192118 +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",testid,2.793358564376831,0.17910160015423174,0.004677208127250881,0.12332880335157931,0.004086355416255143 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..802c85b32f068b3745a630d52a1177b8c7bec5dd --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",train,2.6421639919281006,0.23040044254586803,0.0021191913989343724,0.16953420992493587,0.0020270705260694074 +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",validation,2.7155017852783203,0.2024732373569583,0.004934505885757396,0.1357424119482108,0.004218270105620033 +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",test,2.6492323875427246,0.21929499072356215,0.00466207156531081,0.14367467984267523,0.004186820206192118 +flat_mae,patch,linear,nsd_cococlip,best,19,0.012899999999999998,0.05,47,"[43, 1.0]",testid,2.793358564376831,0.17910160015423174,0.004677208127250881,0.12332880335157931,0.004086355416255143 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..0e2e062d20ae162559ef9e205b0ee4c8b48941cb --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",train,2.6421639919281006,0.23040044254586803,0.0021191913989343724,0.16953420992493587,0.0020270705260694074 +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",validation,2.7155017852783203,0.2024732373569583,0.004934505885757396,0.1357424119482108,0.004218270105620033 +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",test,2.6492323875427246,0.21929499072356215,0.00466207156531081,0.14367467984267523,0.004186820206192118 +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",testid,2.793358564376831,0.17910160015423174,0.004677208127250881,0.12332880335157931,0.004086355416255143 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/log.txt b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..713db5a1f25079d4a0739a28ba5e890070f5bb56 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/log.txt @@ -0,0 +1,966 @@ +fMRI foundation model probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 23:03:52 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (nsd_cococlip patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:21:36 lr: nan time: 3.2421 data: 2.8642 max mem: 3910 +train: [0] [ 20/400] eta: 0:02:58 lr: 0.000003 loss: 3.1794 (3.1797) grad: 0.0315 (0.0321) time: 0.3312 data: 0.0072 max mem: 3953 +train: [0] [ 40/400] eta: 0:02:22 lr: 0.000006 loss: 3.1808 (3.1798) grad: 0.0315 (0.0313) time: 0.3178 data: 0.0039 max mem: 3953 +train: [0] [ 60/400] eta: 0:02:05 lr: 0.000009 loss: 3.1776 (3.1794) grad: 0.0303 (0.0308) time: 0.3175 data: 0.0037 max mem: 3953 +train: [0] [ 80/400] eta: 0:01:54 lr: 0.000012 loss: 3.1769 (3.1795) grad: 0.0293 (0.0304) time: 0.3230 data: 0.0043 max mem: 3953 +train: [0] [100/400] eta: 0:01:45 lr: 0.000015 loss: 3.1784 (3.1794) grad: 0.0289 (0.0303) time: 0.3227 data: 0.0043 max mem: 3953 +train: [0] [120/400] eta: 0:01:37 lr: 0.000018 loss: 3.1768 (3.1786) grad: 0.0296 (0.0303) time: 0.3279 data: 0.0038 max mem: 3953 +train: [0] [140/400] eta: 0:01:29 lr: 0.000021 loss: 3.1718 (3.1775) grad: 0.0306 (0.0305) time: 0.3272 data: 0.0040 max mem: 3953 +train: [0] [160/400] eta: 0:01:22 lr: 0.000024 loss: 3.1722 (3.1771) grad: 0.0306 (0.0304) time: 0.3297 data: 0.0040 max mem: 3953 +train: [0] [180/400] eta: 0:01:15 lr: 0.000027 loss: 3.1722 (3.1760) grad: 0.0297 (0.0304) time: 0.3335 data: 0.0041 max mem: 3953 +train: [0] [200/400] eta: 0:01:08 lr: 0.000030 loss: 3.1657 (3.1752) grad: 0.0297 (0.0302) time: 0.3285 data: 0.0041 max mem: 3953 +train: [0] [220/400] eta: 0:01:01 lr: 0.000033 loss: 3.1657 (3.1743) grad: 0.0297 (0.0301) time: 0.3432 data: 0.0043 max mem: 3953 +train: [0] [240/400] eta: 0:00:54 lr: 0.000036 loss: 3.1625 (3.1736) grad: 0.0292 (0.0301) time: 0.3265 data: 0.0042 max mem: 3953 +train: [0] [260/400] eta: 0:00:47 lr: 0.000039 loss: 3.1625 (3.1727) grad: 0.0289 (0.0300) time: 0.3285 data: 0.0039 max mem: 3953 +train: [0] [280/400] eta: 0:00:40 lr: 0.000042 loss: 3.1607 (3.1716) grad: 0.0283 (0.0300) time: 0.3300 data: 0.0043 max mem: 3953 +train: [0] [300/400] eta: 0:00:33 lr: 0.000045 loss: 3.1587 (3.1707) grad: 0.0301 (0.0300) time: 0.3328 data: 0.0042 max mem: 3953 +train: [0] [320/400] eta: 0:00:26 lr: 0.000048 loss: 3.1555 (3.1696) grad: 0.0302 (0.0300) time: 0.3328 data: 0.0038 max mem: 3953 +train: [0] [340/400] eta: 0:00:20 lr: 0.000051 loss: 3.1583 (3.1693) grad: 0.0296 (0.0299) time: 0.3402 data: 0.0040 max mem: 3953 +train: [0] [360/400] eta: 0:00:13 lr: 0.000054 loss: 3.1614 (3.1685) grad: 0.0291 (0.0299) time: 0.3279 data: 0.0045 max mem: 3953 +train: [0] [380/400] eta: 0:00:06 lr: 0.000057 loss: 3.1485 (3.1676) grad: 0.0291 (0.0299) time: 0.3282 data: 0.0045 max mem: 3953 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1482 (3.1667) grad: 0.0299 (0.0300) time: 0.3271 data: 0.0043 max mem: 3953 +train: [0] Total time: 0:02:14 (0.3364 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1482 (3.1667) grad: 0.0299 (0.0300) +eval (validation): [0] [ 0/85] eta: 0:04:36 time: 3.2532 data: 3.0292 max mem: 3953 +eval (validation): [0] [20/85] eta: 0:00:34 time: 0.3907 data: 0.0412 max mem: 3953 +eval (validation): [0] [40/85] eta: 0:00:19 time: 0.3392 data: 0.0031 max mem: 3953 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3260 data: 0.0167 max mem: 3953 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.2998 data: 0.0032 max mem: 3953 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.2889 data: 0.0037 max mem: 3953 +eval (validation): [0] Total time: 0:00:31 (0.3727 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.042 acc: 0.114 f1: 0.051 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:21:09 lr: nan time: 3.1739 data: 2.8993 max mem: 3953 +train: [1] [ 20/400] eta: 0:03:03 lr: 0.000063 loss: 3.1423 (3.1469) grad: 0.0275 (0.0286) time: 0.3485 data: 0.0042 max mem: 3953 +train: [1] [ 40/400] eta: 0:02:29 lr: 0.000066 loss: 3.1465 (3.1474) grad: 0.0279 (0.0285) time: 0.3436 data: 0.0041 max mem: 3953 +train: [1] [ 60/400] eta: 0:02:12 lr: 0.000069 loss: 3.1473 (3.1477) grad: 0.0290 (0.0288) time: 0.3419 data: 0.0039 max mem: 3953 +train: [1] [ 80/400] eta: 0:02:00 lr: 0.000072 loss: 3.1328 (3.1435) grad: 0.0297 (0.0292) time: 0.3355 data: 0.0040 max mem: 3953 +train: [1] [100/400] eta: 0:01:50 lr: 0.000075 loss: 3.1325 (3.1439) grad: 0.0290 (0.0291) time: 0.3379 data: 0.0040 max mem: 3953 +train: [1] [120/400] eta: 0:01:42 lr: 0.000078 loss: 3.1353 (3.1418) grad: 0.0282 (0.0289) time: 0.3583 data: 0.0043 max mem: 3953 +train: [1] [140/400] eta: 0:01:35 lr: 0.000081 loss: 3.1309 (3.1404) grad: 0.0284 (0.0290) time: 0.3607 data: 0.0043 max mem: 3953 +train: [1] [160/400] eta: 0:01:27 lr: 0.000084 loss: 3.1368 (3.1412) grad: 0.0284 (0.0288) time: 0.3479 data: 0.0043 max mem: 3953 +train: [1] [180/400] eta: 0:01:19 lr: 0.000087 loss: 3.1390 (3.1407) grad: 0.0278 (0.0288) time: 0.3528 data: 0.0044 max mem: 3953 +train: [1] [200/400] eta: 0:01:12 lr: 0.000090 loss: 3.1368 (3.1397) grad: 0.0280 (0.0287) time: 0.3432 data: 0.0042 max mem: 3953 +train: [1] [220/400] eta: 0:01:05 lr: 0.000093 loss: 3.1252 (3.1388) grad: 0.0290 (0.0288) time: 0.3632 data: 0.0045 max mem: 3953 +train: [1] [240/400] eta: 0:00:57 lr: 0.000096 loss: 3.1269 (3.1376) grad: 0.0297 (0.0288) time: 0.3469 data: 0.0045 max mem: 3953 +train: [1] [260/400] eta: 0:00:50 lr: 0.000099 loss: 3.1275 (3.1375) grad: 0.0286 (0.0288) time: 0.3444 data: 0.0041 max mem: 3953 +train: [1] [280/400] eta: 0:00:43 lr: 0.000102 loss: 3.1230 (3.1358) grad: 0.0286 (0.0288) time: 0.3582 data: 0.0037 max mem: 3953 +train: [1] [300/400] eta: 0:00:35 lr: 0.000105 loss: 3.1220 (3.1351) grad: 0.0286 (0.0288) time: 0.3515 data: 0.0043 max mem: 3953 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 3.1239 (3.1350) grad: 0.0277 (0.0287) time: 0.3506 data: 0.0036 max mem: 3953 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 3.1208 (3.1338) grad: 0.0282 (0.0287) time: 0.3538 data: 0.0043 max mem: 3953 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 3.1147 (3.1331) grad: 0.0282 (0.0287) time: 0.3499 data: 0.0037 max mem: 3953 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 3.1127 (3.1322) grad: 0.0283 (0.0287) time: 0.3656 data: 0.0047 max mem: 3953 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.1142 (3.1314) grad: 0.0295 (0.0287) time: 0.3404 data: 0.0039 max mem: 3953 +train: [1] Total time: 0:02:22 (0.3571 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.1142 (3.1314) grad: 0.0295 (0.0287) +eval (validation): [1] [ 0/85] eta: 0:04:44 time: 3.3477 data: 3.0784 max mem: 3953 +eval (validation): [1] [20/85] eta: 0:00:31 time: 0.3374 data: 0.0075 max mem: 3953 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3521 data: 0.0270 max mem: 3953 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3471 data: 0.0039 max mem: 3953 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3114 data: 0.0038 max mem: 3953 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.2998 data: 0.0039 max mem: 3953 +eval (validation): [1] Total time: 0:00:31 (0.3733 s / it) +cv: [1] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.930 acc: 0.140 f1: 0.072 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:27 lr: nan time: 3.3695 data: 3.0763 max mem: 3953 +train: [2] [ 20/400] eta: 0:03:13 lr: 0.000123 loss: 3.0971 (3.1054) grad: 0.0269 (0.0275) time: 0.3675 data: 0.0258 max mem: 3953 +train: [2] [ 40/400] eta: 0:02:36 lr: 0.000126 loss: 3.1018 (3.1069) grad: 0.0274 (0.0281) time: 0.3538 data: 0.0043 max mem: 3953 +train: [2] [ 60/400] eta: 0:02:19 lr: 0.000129 loss: 3.1061 (3.1073) grad: 0.0277 (0.0280) time: 0.3600 data: 0.0036 max mem: 3953 +train: [2] [ 80/400] eta: 0:02:06 lr: 0.000132 loss: 3.1022 (3.1055) grad: 0.0275 (0.0281) time: 0.3460 data: 0.0043 max mem: 3953 +train: [2] [100/400] eta: 0:01:54 lr: 0.000135 loss: 3.1018 (3.1054) grad: 0.0282 (0.0283) time: 0.3392 data: 0.0042 max mem: 3953 +train: [2] [120/400] eta: 0:01:45 lr: 0.000138 loss: 3.1124 (3.1065) grad: 0.0282 (0.0282) time: 0.3420 data: 0.0037 max mem: 3953 +train: [2] [140/400] eta: 0:01:37 lr: 0.000141 loss: 3.1124 (3.1073) grad: 0.0276 (0.0282) time: 0.3570 data: 0.0041 max mem: 3953 +train: [2] [160/400] eta: 0:01:28 lr: 0.000144 loss: 3.1061 (3.1086) grad: 0.0278 (0.0281) time: 0.3348 data: 0.0041 max mem: 3953 +train: [2] [180/400] eta: 0:01:20 lr: 0.000147 loss: 3.1036 (3.1074) grad: 0.0278 (0.0282) time: 0.3345 data: 0.0038 max mem: 3953 +train: [2] [200/400] eta: 0:01:12 lr: 0.000150 loss: 3.0918 (3.1059) grad: 0.0289 (0.0282) time: 0.3350 data: 0.0038 max mem: 3953 +train: [2] [220/400] eta: 0:01:05 lr: 0.000153 loss: 3.0856 (3.1043) grad: 0.0290 (0.0284) time: 0.3661 data: 0.0041 max mem: 3953 +train: [2] [240/400] eta: 0:00:57 lr: 0.000156 loss: 3.0906 (3.1040) grad: 0.0286 (0.0284) time: 0.3626 data: 0.0045 max mem: 3953 +train: [2] [260/400] eta: 0:00:50 lr: 0.000159 loss: 3.1030 (3.1046) grad: 0.0272 (0.0283) time: 0.3374 data: 0.0040 max mem: 3953 +train: [2] [280/400] eta: 0:00:43 lr: 0.000162 loss: 3.1005 (3.1030) grad: 0.0279 (0.0283) time: 0.3527 data: 0.0043 max mem: 3953 +train: [2] [300/400] eta: 0:00:35 lr: 0.000165 loss: 3.0885 (3.1031) grad: 0.0278 (0.0283) time: 0.3577 data: 0.0043 max mem: 3953 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 3.0885 (3.1019) grad: 0.0276 (0.0283) time: 0.3699 data: 0.0048 max mem: 3953 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 3.0862 (3.1015) grad: 0.0278 (0.0283) time: 0.3707 data: 0.0046 max mem: 3953 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 3.0943 (3.1009) grad: 0.0273 (0.0282) time: 0.3670 data: 0.0046 max mem: 3953 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 3.0953 (3.1010) grad: 0.0269 (0.0282) time: 0.3613 data: 0.0041 max mem: 3953 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.1034 (3.1017) grad: 0.0279 (0.0282) time: 0.3519 data: 0.0045 max mem: 3953 +train: [2] Total time: 0:02:24 (0.3612 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.1034 (3.1017) grad: 0.0279 (0.0282) +eval (validation): [2] [ 0/85] eta: 0:04:52 time: 3.4449 data: 3.1613 max mem: 3953 +eval (validation): [2] [20/85] eta: 0:00:31 time: 0.3301 data: 0.0058 max mem: 3953 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3382 data: 0.0044 max mem: 3953 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3291 data: 0.0041 max mem: 3953 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3054 data: 0.0042 max mem: 3953 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3024 data: 0.0039 max mem: 3953 +eval (validation): [2] Total time: 0:00:31 (0.3653 s / it) +cv: [2] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.865 acc: 0.159 f1: 0.094 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:23 lr: nan time: 3.3593 data: 3.0902 max mem: 3953 +train: [3] [ 20/400] eta: 0:03:11 lr: 0.000183 loss: 3.0790 (3.0843) grad: 0.0281 (0.0286) time: 0.3618 data: 0.0044 max mem: 3953 +train: [3] [ 40/400] eta: 0:02:32 lr: 0.000186 loss: 3.0790 (3.0778) grad: 0.0281 (0.0282) time: 0.3414 data: 0.0039 max mem: 3953 +train: [3] [ 60/400] eta: 0:02:15 lr: 0.000189 loss: 3.0804 (3.0812) grad: 0.0274 (0.0281) time: 0.3468 data: 0.0041 max mem: 3953 +train: [3] [ 80/400] eta: 0:02:03 lr: 0.000192 loss: 3.0865 (3.0829) grad: 0.0286 (0.0285) time: 0.3476 data: 0.0037 max mem: 3953 +train: [3] [100/400] eta: 0:01:53 lr: 0.000195 loss: 3.0865 (3.0840) grad: 0.0283 (0.0283) time: 0.3505 data: 0.0043 max mem: 3953 +train: [3] [120/400] eta: 0:01:45 lr: 0.000198 loss: 3.0814 (3.0831) grad: 0.0276 (0.0282) time: 0.3644 data: 0.0041 max mem: 3953 +train: [3] [140/400] eta: 0:01:37 lr: 0.000201 loss: 3.0752 (3.0820) grad: 0.0275 (0.0282) time: 0.3603 data: 0.0043 max mem: 3953 +train: [3] [160/400] eta: 0:01:29 lr: 0.000204 loss: 3.0567 (3.0788) grad: 0.0278 (0.0282) time: 0.3503 data: 0.0039 max mem: 3953 +train: [3] [180/400] eta: 0:01:21 lr: 0.000207 loss: 3.0567 (3.0781) grad: 0.0291 (0.0283) time: 0.3414 data: 0.0040 max mem: 3953 +train: [3] [200/400] eta: 0:01:13 lr: 0.000210 loss: 3.0778 (3.0788) grad: 0.0284 (0.0282) time: 0.3638 data: 0.0046 max mem: 3953 +train: [3] [220/400] eta: 0:01:06 lr: 0.000213 loss: 3.0722 (3.0779) grad: 0.0276 (0.0282) time: 0.3686 data: 0.0045 max mem: 3953 +train: [3] [240/400] eta: 0:00:58 lr: 0.000216 loss: 3.0722 (3.0789) grad: 0.0280 (0.0283) time: 0.3603 data: 0.0045 max mem: 3953 +train: [3] [260/400] eta: 0:00:51 lr: 0.000219 loss: 3.0759 (3.0779) grad: 0.0280 (0.0282) time: 0.3489 data: 0.0042 max mem: 3953 +train: [3] [280/400] eta: 0:00:43 lr: 0.000222 loss: 3.0722 (3.0776) grad: 0.0281 (0.0283) time: 0.3605 data: 0.0040 max mem: 3953 +train: [3] [300/400] eta: 0:00:36 lr: 0.000225 loss: 3.0600 (3.0761) grad: 0.0281 (0.0282) time: 0.3451 data: 0.0040 max mem: 3953 +train: [3] [320/400] eta: 0:00:29 lr: 0.000228 loss: 3.0600 (3.0762) grad: 0.0276 (0.0282) time: 0.3464 data: 0.0040 max mem: 3953 +train: [3] [340/400] eta: 0:00:21 lr: 0.000231 loss: 3.0687 (3.0752) grad: 0.0276 (0.0282) time: 0.3506 data: 0.0040 max mem: 3953 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 3.0711 (3.0751) grad: 0.0275 (0.0281) time: 0.3478 data: 0.0041 max mem: 3953 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 3.0706 (3.0743) grad: 0.0277 (0.0281) time: 0.3615 data: 0.0040 max mem: 3953 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.0508 (3.0734) grad: 0.0279 (0.0281) time: 0.3558 data: 0.0040 max mem: 3953 +train: [3] Total time: 0:02:24 (0.3615 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.0508 (3.0734) grad: 0.0279 (0.0281) +eval (validation): [3] [ 0/85] eta: 0:04:46 time: 3.3742 data: 3.1590 max mem: 3953 +eval (validation): [3] [20/85] eta: 0:00:31 time: 0.3347 data: 0.0061 max mem: 3953 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3505 data: 0.0039 max mem: 3953 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3432 data: 0.0042 max mem: 3953 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3452 data: 0.0042 max mem: 3953 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3341 data: 0.0037 max mem: 3953 +eval (validation): [3] Total time: 0:00:32 (0.3817 s / it) +cv: [3] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.810 acc: 0.170 f1: 0.108 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:20 lr: nan time: 3.3507 data: 3.0842 max mem: 3953 +train: [4] [ 20/400] eta: 0:03:04 lr: 0.000243 loss: 3.0380 (3.0530) grad: 0.0266 (0.0272) time: 0.3419 data: 0.0041 max mem: 3953 +train: [4] [ 40/400] eta: 0:02:29 lr: 0.000246 loss: 3.0372 (3.0470) grad: 0.0266 (0.0268) time: 0.3425 data: 0.0050 max mem: 3953 +train: [4] [ 60/400] eta: 0:02:13 lr: 0.000249 loss: 3.0470 (3.0482) grad: 0.0267 (0.0270) time: 0.3414 data: 0.0042 max mem: 3953 +train: [4] [ 80/400] eta: 0:02:01 lr: 0.000252 loss: 3.0473 (3.0450) grad: 0.0273 (0.0271) time: 0.3482 data: 0.0043 max mem: 3953 +train: [4] [100/400] eta: 0:01:51 lr: 0.000255 loss: 3.0360 (3.0438) grad: 0.0278 (0.0274) time: 0.3414 data: 0.0037 max mem: 3953 +train: [4] [120/400] eta: 0:01:43 lr: 0.000258 loss: 3.0314 (3.0418) grad: 0.0278 (0.0276) time: 0.3510 data: 0.0040 max mem: 3953 +train: [4] [140/400] eta: 0:01:35 lr: 0.000261 loss: 3.0232 (3.0408) grad: 0.0279 (0.0277) time: 0.3552 data: 0.0043 max mem: 3953 +train: [4] [160/400] eta: 0:01:27 lr: 0.000264 loss: 3.0549 (3.0424) grad: 0.0274 (0.0276) time: 0.3570 data: 0.0042 max mem: 3953 +train: [4] [180/400] eta: 0:01:20 lr: 0.000267 loss: 3.0419 (3.0426) grad: 0.0279 (0.0276) time: 0.3477 data: 0.0042 max mem: 3953 +train: [4] [200/400] eta: 0:01:12 lr: 0.000270 loss: 3.0419 (3.0427) grad: 0.0280 (0.0277) time: 0.3579 data: 0.0042 max mem: 3953 +train: [4] [220/400] eta: 0:01:05 lr: 0.000273 loss: 3.0424 (3.0434) grad: 0.0279 (0.0277) time: 0.3689 data: 0.0044 max mem: 3953 +train: [4] [240/400] eta: 0:00:58 lr: 0.000276 loss: 3.0489 (3.0432) grad: 0.0283 (0.0278) time: 0.3706 data: 0.0044 max mem: 3953 +train: [4] [260/400] eta: 0:00:50 lr: 0.000279 loss: 3.0489 (3.0439) grad: 0.0283 (0.0277) time: 0.3496 data: 0.0039 max mem: 3953 +train: [4] [280/400] eta: 0:00:43 lr: 0.000282 loss: 3.0469 (3.0451) grad: 0.0275 (0.0277) time: 0.3686 data: 0.0042 max mem: 3953 +train: [4] [300/400] eta: 0:00:36 lr: 0.000285 loss: 3.0406 (3.0450) grad: 0.0275 (0.0277) time: 0.3614 data: 0.0042 max mem: 3953 +train: [4] [320/400] eta: 0:00:29 lr: 0.000288 loss: 3.0569 (3.0460) grad: 0.0275 (0.0277) time: 0.3623 data: 0.0041 max mem: 3953 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 3.0626 (3.0458) grad: 0.0277 (0.0277) time: 0.3663 data: 0.0041 max mem: 3953 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 3.0463 (3.0457) grad: 0.0275 (0.0277) time: 0.3691 data: 0.0043 max mem: 3953 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.0344 (3.0454) grad: 0.0275 (0.0277) time: 0.3663 data: 0.0045 max mem: 3953 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.0281 (3.0449) grad: 0.0277 (0.0277) time: 0.3619 data: 0.0043 max mem: 3953 +train: [4] Total time: 0:02:25 (0.3641 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.0281 (3.0449) grad: 0.0277 (0.0277) +eval (validation): [4] [ 0/85] eta: 0:04:55 time: 3.4807 data: 3.2003 max mem: 3953 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3512 data: 0.0041 max mem: 3953 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3272 data: 0.0039 max mem: 3953 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3562 data: 0.0045 max mem: 3953 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3193 data: 0.0042 max mem: 3953 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3107 data: 0.0042 max mem: 3953 +eval (validation): [4] Total time: 0:00:32 (0.3765 s / it) +cv: [4] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.797 acc: 0.178 f1: 0.118 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:21:45 lr: nan time: 3.2649 data: 3.0340 max mem: 3953 +train: [5] [ 20/400] eta: 0:03:17 lr: 0.000300 loss: 3.0100 (3.0054) grad: 0.0269 (0.0276) time: 0.3819 data: 0.0308 max mem: 3953 +train: [5] [ 40/400] eta: 0:02:37 lr: 0.000300 loss: 3.0132 (3.0208) grad: 0.0274 (0.0274) time: 0.3516 data: 0.0055 max mem: 3953 +train: [5] [ 60/400] eta: 0:02:18 lr: 0.000300 loss: 3.0256 (3.0222) grad: 0.0274 (0.0274) time: 0.3467 data: 0.0036 max mem: 3953 +train: [5] [ 80/400] eta: 0:02:05 lr: 0.000300 loss: 3.0147 (3.0216) grad: 0.0274 (0.0272) time: 0.3454 data: 0.0046 max mem: 3953 +train: [5] [100/400] eta: 0:01:54 lr: 0.000300 loss: 3.0109 (3.0180) grad: 0.0274 (0.0273) time: 0.3338 data: 0.0040 max mem: 3953 +train: [5] [120/400] eta: 0:01:45 lr: 0.000300 loss: 3.0163 (3.0218) grad: 0.0274 (0.0273) time: 0.3543 data: 0.0039 max mem: 3953 +train: [5] [140/400] eta: 0:01:37 lr: 0.000300 loss: 3.0478 (3.0254) grad: 0.0271 (0.0273) time: 0.3591 data: 0.0046 max mem: 3953 +train: [5] [160/400] eta: 0:01:29 lr: 0.000299 loss: 3.0329 (3.0228) grad: 0.0278 (0.0275) time: 0.3509 data: 0.0041 max mem: 3953 +train: [5] [180/400] eta: 0:01:20 lr: 0.000299 loss: 3.0032 (3.0230) grad: 0.0279 (0.0275) time: 0.3346 data: 0.0043 max mem: 3953 +train: [5] [200/400] eta: 0:01:12 lr: 0.000299 loss: 3.0032 (3.0208) grad: 0.0278 (0.0275) time: 0.3417 data: 0.0037 max mem: 3953 +train: [5] [220/400] eta: 0:01:05 lr: 0.000299 loss: 3.0124 (3.0203) grad: 0.0269 (0.0275) time: 0.3658 data: 0.0041 max mem: 3953 +train: [5] [240/400] eta: 0:00:58 lr: 0.000299 loss: 3.0207 (3.0222) grad: 0.0269 (0.0275) time: 0.3418 data: 0.0042 max mem: 3953 +train: [5] [260/400] eta: 0:00:50 lr: 0.000299 loss: 3.0296 (3.0235) grad: 0.0278 (0.0275) time: 0.3557 data: 0.0042 max mem: 3953 +train: [5] [280/400] eta: 0:00:43 lr: 0.000298 loss: 3.0294 (3.0245) grad: 0.0275 (0.0276) time: 0.3702 data: 0.0045 max mem: 3953 +train: [5] [300/400] eta: 0:00:36 lr: 0.000298 loss: 3.0399 (3.0255) grad: 0.0268 (0.0275) time: 0.3850 data: 0.0045 max mem: 3953 +train: [5] [320/400] eta: 0:00:29 lr: 0.000298 loss: 3.0251 (3.0257) grad: 0.0264 (0.0275) time: 0.3544 data: 0.0046 max mem: 3953 +train: [5] [340/400] eta: 0:00:21 lr: 0.000298 loss: 3.0154 (3.0247) grad: 0.0267 (0.0275) time: 0.3667 data: 0.0044 max mem: 3953 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 3.0006 (3.0237) grad: 0.0279 (0.0275) time: 0.3561 data: 0.0045 max mem: 3953 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.0244 (3.0245) grad: 0.0273 (0.0275) time: 0.3629 data: 0.0046 max mem: 3953 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 3.0321 (3.0247) grad: 0.0273 (0.0275) time: 0.3580 data: 0.0044 max mem: 3953 +train: [5] Total time: 0:02:25 (0.3635 s / it) +train: [5] Summary: lr: 0.000297 loss: 3.0321 (3.0247) grad: 0.0273 (0.0275) +eval (validation): [5] [ 0/85] eta: 0:05:04 time: 3.5776 data: 3.2638 max mem: 3953 +eval (validation): [5] [20/85] eta: 0:00:34 time: 0.3839 data: 0.0044 max mem: 3953 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3475 data: 0.0043 max mem: 3953 +eval (validation): [5] [60/85] eta: 0:00:10 time: 0.3442 data: 0.0047 max mem: 3953 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3363 data: 0.0046 max mem: 3953 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3181 data: 0.0043 max mem: 3953 +eval (validation): [5] Total time: 0:00:33 (0.3911 s / it) +cv: [5] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.803 acc: 0.181 f1: 0.114 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:20 lr: nan time: 3.3512 data: 3.0584 max mem: 3953 +train: [6] [ 20/400] eta: 0:03:30 lr: 0.000296 loss: 2.9873 (2.9986) grad: 0.0268 (0.0275) time: 0.4152 data: 0.0059 max mem: 3953 +train: [6] [ 40/400] eta: 0:02:45 lr: 0.000296 loss: 3.0067 (3.0048) grad: 0.0268 (0.0273) time: 0.3569 data: 0.0041 max mem: 3953 +train: [6] [ 60/400] eta: 0:02:24 lr: 0.000296 loss: 3.0091 (3.0121) grad: 0.0270 (0.0273) time: 0.3586 data: 0.0039 max mem: 3953 +train: [6] [ 80/400] eta: 0:02:10 lr: 0.000295 loss: 2.9911 (3.0087) grad: 0.0274 (0.0275) time: 0.3489 data: 0.0039 max mem: 3953 +train: [6] [100/400] eta: 0:01:58 lr: 0.000295 loss: 2.9874 (3.0028) grad: 0.0273 (0.0274) time: 0.3526 data: 0.0037 max mem: 3953 +train: [6] [120/400] eta: 0:01:49 lr: 0.000295 loss: 3.0027 (3.0063) grad: 0.0265 (0.0273) time: 0.3599 data: 0.0037 max mem: 3953 +train: [6] [140/400] eta: 0:01:40 lr: 0.000294 loss: 3.0254 (3.0092) grad: 0.0274 (0.0274) time: 0.3664 data: 0.0043 max mem: 3953 +train: [6] [160/400] eta: 0:01:32 lr: 0.000294 loss: 3.0233 (3.0067) grad: 0.0274 (0.0274) time: 0.3638 data: 0.0044 max mem: 3953 +train: [6] [180/400] eta: 0:01:23 lr: 0.000293 loss: 2.9940 (3.0069) grad: 0.0272 (0.0274) time: 0.3418 data: 0.0040 max mem: 3953 +train: [6] [200/400] eta: 0:01:15 lr: 0.000293 loss: 2.9981 (3.0054) grad: 0.0270 (0.0274) time: 0.3603 data: 0.0043 max mem: 3953 +train: [6] [220/400] eta: 0:01:08 lr: 0.000292 loss: 2.9981 (3.0043) grad: 0.0271 (0.0274) time: 0.3902 data: 0.0043 max mem: 3953 +train: [6] [240/400] eta: 0:01:00 lr: 0.000292 loss: 2.9957 (3.0045) grad: 0.0277 (0.0274) time: 0.3671 data: 0.0042 max mem: 3953 +train: [6] [260/400] eta: 0:00:52 lr: 0.000291 loss: 2.9938 (3.0039) grad: 0.0272 (0.0274) time: 0.3518 data: 0.0043 max mem: 3953 +train: [6] [280/400] eta: 0:00:44 lr: 0.000291 loss: 2.9921 (3.0037) grad: 0.0272 (0.0274) time: 0.3663 data: 0.0042 max mem: 3953 +train: [6] [300/400] eta: 0:00:37 lr: 0.000290 loss: 3.0014 (3.0043) grad: 0.0274 (0.0274) time: 0.3629 data: 0.0045 max mem: 3953 +train: [6] [320/400] eta: 0:00:29 lr: 0.000290 loss: 3.0170 (3.0054) grad: 0.0273 (0.0274) time: 0.3656 data: 0.0046 max mem: 3953 +train: [6] [340/400] eta: 0:00:22 lr: 0.000289 loss: 3.0180 (3.0059) grad: 0.0273 (0.0274) time: 0.3711 data: 0.0041 max mem: 3953 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 3.0132 (3.0054) grad: 0.0265 (0.0273) time: 0.3809 data: 0.0043 max mem: 3953 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 2.9995 (3.0045) grad: 0.0270 (0.0274) time: 0.3791 data: 0.0042 max mem: 3953 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 3.0111 (3.0050) grad: 0.0261 (0.0273) time: 0.3681 data: 0.0042 max mem: 3953 +train: [6] Total time: 0:02:29 (0.3741 s / it) +train: [6] Summary: lr: 0.000287 loss: 3.0111 (3.0050) grad: 0.0261 (0.0273) +eval (validation): [6] [ 0/85] eta: 0:05:13 time: 3.6857 data: 3.4560 max mem: 3953 +eval (validation): [6] [20/85] eta: 0:00:32 time: 0.3443 data: 0.0041 max mem: 3953 +eval (validation): [6] [40/85] eta: 0:00:19 time: 0.3696 data: 0.0040 max mem: 3953 +eval (validation): [6] [60/85] eta: 0:00:10 time: 0.3629 data: 0.0046 max mem: 3953 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3177 data: 0.0044 max mem: 3953 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3145 data: 0.0042 max mem: 3953 +eval (validation): [6] Total time: 0:00:33 (0.3890 s / it) +cv: [6] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.770 acc: 0.186 f1: 0.117 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:23:40 lr: nan time: 3.5519 data: 3.2477 max mem: 3953 +train: [7] [ 20/400] eta: 0:03:18 lr: 0.000286 loss: 2.9619 (2.9757) grad: 0.0266 (0.0270) time: 0.3709 data: 0.0036 max mem: 3953 +train: [7] [ 40/400] eta: 0:02:39 lr: 0.000286 loss: 2.9774 (2.9695) grad: 0.0270 (0.0275) time: 0.3613 data: 0.0042 max mem: 3953 +train: [7] [ 60/400] eta: 0:02:20 lr: 0.000285 loss: 2.9770 (2.9690) grad: 0.0271 (0.0274) time: 0.3490 data: 0.0038 max mem: 3953 +train: [7] [ 80/400] eta: 0:02:07 lr: 0.000284 loss: 2.9806 (2.9758) grad: 0.0268 (0.0274) time: 0.3546 data: 0.0041 max mem: 3953 +train: [7] [100/400] eta: 0:01:56 lr: 0.000284 loss: 2.9909 (2.9783) grad: 0.0275 (0.0274) time: 0.3547 data: 0.0039 max mem: 3953 +train: [7] [120/400] eta: 0:01:47 lr: 0.000283 loss: 2.9717 (2.9786) grad: 0.0277 (0.0275) time: 0.3624 data: 0.0043 max mem: 3953 +train: [7] [140/400] eta: 0:01:39 lr: 0.000282 loss: 2.9894 (2.9820) grad: 0.0274 (0.0274) time: 0.3645 data: 0.0041 max mem: 3953 +train: [7] [160/400] eta: 0:01:30 lr: 0.000282 loss: 2.9894 (2.9845) grad: 0.0274 (0.0274) time: 0.3528 data: 0.0039 max mem: 3953 +train: [7] [180/400] eta: 0:01:22 lr: 0.000281 loss: 2.9813 (2.9810) grad: 0.0275 (0.0274) time: 0.3487 data: 0.0040 max mem: 3953 +train: [7] [200/400] eta: 0:01:14 lr: 0.000280 loss: 2.9708 (2.9836) grad: 0.0275 (0.0274) time: 0.3712 data: 0.0042 max mem: 3953 +train: [7] [220/400] eta: 0:01:07 lr: 0.000279 loss: 2.9969 (2.9852) grad: 0.0270 (0.0274) time: 0.3789 data: 0.0043 max mem: 3953 +train: [7] [240/400] eta: 0:00:59 lr: 0.000278 loss: 2.9969 (2.9864) grad: 0.0276 (0.0275) time: 0.3668 data: 0.0045 max mem: 3953 +train: [7] [260/400] eta: 0:00:52 lr: 0.000278 loss: 3.0129 (2.9894) grad: 0.0277 (0.0275) time: 0.3594 data: 0.0040 max mem: 3953 +train: [7] [280/400] eta: 0:00:44 lr: 0.000277 loss: 3.0158 (2.9928) grad: 0.0268 (0.0275) time: 0.3768 data: 0.0043 max mem: 3953 +train: [7] [300/400] eta: 0:00:37 lr: 0.000276 loss: 3.0053 (2.9927) grad: 0.0269 (0.0275) time: 0.3791 data: 0.0045 max mem: 3953 +train: [7] [320/400] eta: 0:00:29 lr: 0.000275 loss: 3.0053 (2.9948) grad: 0.0273 (0.0275) time: 0.3614 data: 0.0045 max mem: 3953 +train: [7] [340/400] eta: 0:00:22 lr: 0.000274 loss: 2.9994 (2.9934) grad: 0.0272 (0.0275) time: 0.3722 data: 0.0040 max mem: 3953 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 2.9863 (2.9936) grad: 0.0272 (0.0275) time: 0.3750 data: 0.0042 max mem: 3953 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 2.9853 (2.9934) grad: 0.0273 (0.0275) time: 0.3701 data: 0.0043 max mem: 3953 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.9561 (2.9916) grad: 0.0272 (0.0276) time: 0.3654 data: 0.0041 max mem: 3953 +train: [7] Total time: 0:02:29 (0.3729 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.9561 (2.9916) grad: 0.0272 (0.0276) +eval (validation): [7] [ 0/85] eta: 0:04:45 time: 3.3613 data: 3.1307 max mem: 3953 +eval (validation): [7] [20/85] eta: 0:00:33 time: 0.3811 data: 0.0051 max mem: 3953 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3558 data: 0.0039 max mem: 3953 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3467 data: 0.0046 max mem: 3953 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3447 data: 0.0042 max mem: 3953 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3401 data: 0.0041 max mem: 3953 +eval (validation): [7] Total time: 0:00:33 (0.3944 s / it) +cv: [7] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.763 acc: 0.188 f1: 0.116 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:23:19 lr: nan time: 3.4995 data: 3.2061 max mem: 3953 +train: [8] [ 20/400] eta: 0:03:26 lr: 0.000270 loss: 2.9798 (2.9823) grad: 0.0266 (0.0270) time: 0.3962 data: 0.0067 max mem: 3953 +train: [8] [ 40/400] eta: 0:02:45 lr: 0.000270 loss: 2.9789 (2.9786) grad: 0.0266 (0.0269) time: 0.3687 data: 0.0040 max mem: 3953 +train: [8] [ 60/400] eta: 0:02:25 lr: 0.000269 loss: 2.9788 (2.9833) grad: 0.0269 (0.0271) time: 0.3663 data: 0.0045 max mem: 3953 +train: [8] [ 80/400] eta: 0:02:12 lr: 0.000268 loss: 2.9714 (2.9781) grad: 0.0264 (0.0270) time: 0.3663 data: 0.0044 max mem: 3953 +train: [8] [100/400] eta: 0:02:00 lr: 0.000267 loss: 2.9670 (2.9789) grad: 0.0264 (0.0271) time: 0.3518 data: 0.0041 max mem: 3953 +train: [8] [120/400] eta: 0:01:51 lr: 0.000266 loss: 2.9640 (2.9744) grad: 0.0271 (0.0270) time: 0.3838 data: 0.0043 max mem: 3953 +train: [8] [140/400] eta: 0:01:42 lr: 0.000265 loss: 2.9475 (2.9729) grad: 0.0262 (0.0270) time: 0.3827 data: 0.0041 max mem: 3953 +train: [8] [160/400] eta: 0:01:33 lr: 0.000264 loss: 2.9655 (2.9739) grad: 0.0269 (0.0270) time: 0.3470 data: 0.0041 max mem: 3953 +train: [8] [180/400] eta: 0:01:25 lr: 0.000263 loss: 2.9729 (2.9738) grad: 0.0269 (0.0270) time: 0.3759 data: 0.0039 max mem: 3953 +train: [8] [200/400] eta: 0:01:17 lr: 0.000262 loss: 2.9683 (2.9736) grad: 0.0267 (0.0270) time: 0.3763 data: 0.0044 max mem: 3953 +train: [8] [220/400] eta: 0:01:09 lr: 0.000260 loss: 2.9712 (2.9741) grad: 0.0270 (0.0270) time: 0.3812 data: 0.0046 max mem: 3953 +train: [8] [240/400] eta: 0:01:01 lr: 0.000259 loss: 2.9892 (2.9751) grad: 0.0272 (0.0270) time: 0.3753 data: 0.0044 max mem: 3953 +train: [8] [260/400] eta: 0:00:53 lr: 0.000258 loss: 2.9822 (2.9741) grad: 0.0272 (0.0271) time: 0.3546 data: 0.0038 max mem: 3953 +train: [8] [280/400] eta: 0:00:45 lr: 0.000257 loss: 2.9765 (2.9754) grad: 0.0267 (0.0271) time: 0.3699 data: 0.0041 max mem: 3953 +train: [8] [300/400] eta: 0:00:38 lr: 0.000256 loss: 2.9890 (2.9762) grad: 0.0261 (0.0270) time: 0.3758 data: 0.0043 max mem: 3953 +train: [8] [320/400] eta: 0:00:30 lr: 0.000255 loss: 2.9951 (2.9779) grad: 0.0265 (0.0270) time: 0.3722 data: 0.0041 max mem: 3953 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 2.9880 (2.9785) grad: 0.0273 (0.0270) time: 0.3655 data: 0.0046 max mem: 3953 +train: [8] [360/400] eta: 0:00:15 lr: 0.000253 loss: 2.9880 (2.9783) grad: 0.0267 (0.0270) time: 0.3698 data: 0.0046 max mem: 3953 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 2.9606 (2.9768) grad: 0.0272 (0.0270) time: 0.3772 data: 0.0043 max mem: 3953 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.9490 (2.9759) grad: 0.0269 (0.0270) time: 0.3660 data: 0.0041 max mem: 3953 +train: [8] Total time: 0:02:31 (0.3792 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.9490 (2.9759) grad: 0.0269 (0.0270) +eval (validation): [8] [ 0/85] eta: 0:04:56 time: 3.4857 data: 3.2438 max mem: 3953 +eval (validation): [8] [20/85] eta: 0:00:37 time: 0.4260 data: 0.0051 max mem: 3953 +eval (validation): [8] [40/85] eta: 0:00:21 time: 0.3657 data: 0.0047 max mem: 3953 +eval (validation): [8] [60/85] eta: 0:00:10 time: 0.3476 data: 0.0042 max mem: 3953 +eval (validation): [8] [80/85] eta: 0:00:02 time: 0.3510 data: 0.0043 max mem: 3953 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3383 data: 0.0040 max mem: 3953 +eval (validation): [8] Total time: 0:00:34 (0.4107 s / it) +cv: [8] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.756 acc: 0.184 f1: 0.122 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:23:20 lr: nan time: 3.5004 data: 3.1894 max mem: 3953 +train: [9] [ 20/400] eta: 0:03:20 lr: 0.000249 loss: 2.9839 (2.9897) grad: 0.0265 (0.0268) time: 0.3780 data: 0.0041 max mem: 3953 +train: [9] [ 40/400] eta: 0:02:43 lr: 0.000248 loss: 2.9695 (2.9742) grad: 0.0266 (0.0267) time: 0.3757 data: 0.0041 max mem: 3953 +train: [9] [ 60/400] eta: 0:02:24 lr: 0.000247 loss: 2.9670 (2.9697) grad: 0.0265 (0.0267) time: 0.3639 data: 0.0043 max mem: 3953 +train: [9] [ 80/400] eta: 0:02:11 lr: 0.000246 loss: 2.9733 (2.9676) grad: 0.0267 (0.0269) time: 0.3675 data: 0.0043 max mem: 3953 +train: [9] [100/400] eta: 0:02:00 lr: 0.000244 loss: 2.9616 (2.9686) grad: 0.0271 (0.0270) time: 0.3637 data: 0.0042 max mem: 3953 +train: [9] [120/400] eta: 0:01:51 lr: 0.000243 loss: 2.9473 (2.9651) grad: 0.0272 (0.0270) time: 0.3913 data: 0.0045 max mem: 3953 +train: [9] [140/400] eta: 0:01:42 lr: 0.000242 loss: 2.9645 (2.9673) grad: 0.0267 (0.0269) time: 0.3672 data: 0.0046 max mem: 3953 +train: [9] [160/400] eta: 0:01:33 lr: 0.000241 loss: 2.9592 (2.9660) grad: 0.0259 (0.0268) time: 0.3529 data: 0.0041 max mem: 3953 +train: [9] [180/400] eta: 0:01:25 lr: 0.000240 loss: 2.9592 (2.9684) grad: 0.0257 (0.0267) time: 0.3839 data: 0.0043 max mem: 3953 +train: [9] [200/400] eta: 0:01:17 lr: 0.000238 loss: 2.9666 (2.9673) grad: 0.0263 (0.0268) time: 0.3839 data: 0.0041 max mem: 3953 +train: [9] [220/400] eta: 0:01:09 lr: 0.000237 loss: 2.9635 (2.9670) grad: 0.0274 (0.0269) time: 0.3886 data: 0.0044 max mem: 3953 +train: [9] [240/400] eta: 0:01:02 lr: 0.000236 loss: 2.9593 (2.9657) grad: 0.0288 (0.0271) time: 0.3785 data: 0.0042 max mem: 3953 +train: [9] [260/400] eta: 0:00:53 lr: 0.000234 loss: 2.9653 (2.9663) grad: 0.0280 (0.0271) time: 0.3521 data: 0.0041 max mem: 3953 +train: [9] [280/400] eta: 0:00:46 lr: 0.000233 loss: 2.9635 (2.9655) grad: 0.0265 (0.0271) time: 0.3878 data: 0.0042 max mem: 3953 +train: [9] [300/400] eta: 0:00:38 lr: 0.000232 loss: 2.9654 (2.9670) grad: 0.0268 (0.0271) time: 0.3747 data: 0.0044 max mem: 3953 +train: [9] [320/400] eta: 0:00:30 lr: 0.000230 loss: 2.9807 (2.9687) grad: 0.0274 (0.0271) time: 0.3778 data: 0.0042 max mem: 3953 +train: [9] [340/400] eta: 0:00:23 lr: 0.000229 loss: 2.9640 (2.9679) grad: 0.0269 (0.0271) time: 0.3785 data: 0.0042 max mem: 3953 +train: [9] [360/400] eta: 0:00:15 lr: 0.000228 loss: 2.9602 (2.9685) grad: 0.0266 (0.0271) time: 0.3653 data: 0.0041 max mem: 3953 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 2.9790 (2.9682) grad: 0.0268 (0.0271) time: 0.3770 data: 0.0042 max mem: 3953 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.9605 (2.9679) grad: 0.0267 (0.0271) time: 0.3804 data: 0.0045 max mem: 3953 +train: [9] Total time: 0:02:32 (0.3824 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.9605 (2.9679) grad: 0.0267 (0.0271) +eval (validation): [9] [ 0/85] eta: 0:05:06 time: 3.6048 data: 3.3127 max mem: 3953 +eval (validation): [9] [20/85] eta: 0:00:36 time: 0.4053 data: 0.0197 max mem: 3953 +eval (validation): [9] [40/85] eta: 0:00:20 time: 0.3568 data: 0.0040 max mem: 3953 +eval (validation): [9] [60/85] eta: 0:00:10 time: 0.3841 data: 0.0046 max mem: 3953 +eval (validation): [9] [80/85] eta: 0:00:02 time: 0.3739 data: 0.0046 max mem: 3953 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3447 data: 0.0044 max mem: 3953 +eval (validation): [9] Total time: 0:00:35 (0.4178 s / it) +cv: [9] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.766 acc: 0.188 f1: 0.127 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:23:13 lr: nan time: 3.4837 data: 3.1885 max mem: 3953 +train: [10] [ 20/400] eta: 0:03:33 lr: 0.000224 loss: 2.9541 (2.9702) grad: 0.0269 (0.0265) time: 0.4163 data: 0.0050 max mem: 3953 +train: [10] [ 40/400] eta: 0:02:45 lr: 0.000222 loss: 2.9541 (2.9648) grad: 0.0269 (0.0269) time: 0.3513 data: 0.0041 max mem: 3953 +train: [10] [ 60/400] eta: 0:02:24 lr: 0.000221 loss: 2.9295 (2.9554) grad: 0.0274 (0.0272) time: 0.3509 data: 0.0041 max mem: 3953 +train: [10] [ 80/400] eta: 0:02:10 lr: 0.000220 loss: 2.9430 (2.9588) grad: 0.0272 (0.0270) time: 0.3580 data: 0.0041 max mem: 3953 +train: [10] [100/400] eta: 0:01:59 lr: 0.000218 loss: 2.9776 (2.9610) grad: 0.0266 (0.0272) time: 0.3669 data: 0.0042 max mem: 3953 +train: [10] [120/400] eta: 0:01:50 lr: 0.000217 loss: 2.9785 (2.9651) grad: 0.0271 (0.0272) time: 0.3612 data: 0.0039 max mem: 3953 +train: [10] [140/400] eta: 0:01:40 lr: 0.000215 loss: 2.9712 (2.9643) grad: 0.0272 (0.0273) time: 0.3351 data: 0.0040 max mem: 3953 +train: [10] [160/400] eta: 0:01:31 lr: 0.000214 loss: 2.9548 (2.9648) grad: 0.0275 (0.0272) time: 0.3545 data: 0.0040 max mem: 3953 +train: [10] [180/400] eta: 0:01:23 lr: 0.000213 loss: 2.9613 (2.9652) grad: 0.0273 (0.0273) time: 0.3671 data: 0.0045 max mem: 3953 +train: [10] [200/400] eta: 0:01:15 lr: 0.000211 loss: 2.9708 (2.9662) grad: 0.0273 (0.0273) time: 0.3587 data: 0.0039 max mem: 3953 +train: [10] [220/400] eta: 0:01:07 lr: 0.000210 loss: 2.9601 (2.9640) grad: 0.0267 (0.0272) time: 0.3576 data: 0.0042 max mem: 3953 +train: [10] [240/400] eta: 0:00:59 lr: 0.000208 loss: 2.9374 (2.9626) grad: 0.0265 (0.0272) time: 0.3455 data: 0.0038 max mem: 3953 +train: [10] [260/400] eta: 0:00:51 lr: 0.000207 loss: 2.9464 (2.9626) grad: 0.0266 (0.0271) time: 0.3348 data: 0.0040 max mem: 3953 +train: [10] [280/400] eta: 0:00:44 lr: 0.000205 loss: 2.9527 (2.9619) grad: 0.0260 (0.0271) time: 0.3551 data: 0.0042 max mem: 3953 +train: [10] [300/400] eta: 0:00:36 lr: 0.000204 loss: 2.9715 (2.9621) grad: 0.0260 (0.0271) time: 0.3582 data: 0.0039 max mem: 3953 +train: [10] [320/400] eta: 0:00:29 lr: 0.000202 loss: 2.9767 (2.9619) grad: 0.0268 (0.0271) time: 0.3555 data: 0.0040 max mem: 3953 +train: [10] [340/400] eta: 0:00:22 lr: 0.000201 loss: 2.9552 (2.9617) grad: 0.0268 (0.0271) time: 0.3568 data: 0.0042 max mem: 3953 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 2.9580 (2.9618) grad: 0.0265 (0.0270) time: 0.3430 data: 0.0043 max mem: 3953 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 2.9502 (2.9607) grad: 0.0267 (0.0270) time: 0.3543 data: 0.0041 max mem: 3953 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.9446 (2.9616) grad: 0.0276 (0.0271) time: 0.3645 data: 0.0040 max mem: 3953 +train: [10] Total time: 0:02:26 (0.3653 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.9446 (2.9616) grad: 0.0276 (0.0271) +eval (validation): [10] [ 0/85] eta: 0:05:23 time: 3.8094 data: 3.5813 max mem: 3953 +eval (validation): [10] [20/85] eta: 0:00:36 time: 0.3941 data: 0.0163 max mem: 3953 +eval (validation): [10] [40/85] eta: 0:00:20 time: 0.3477 data: 0.0062 max mem: 3953 +eval (validation): [10] [60/85] eta: 0:00:10 time: 0.3773 data: 0.0045 max mem: 3953 +eval (validation): [10] [80/85] eta: 0:00:02 time: 0.3449 data: 0.0042 max mem: 3953 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3351 data: 0.0041 max mem: 3953 +eval (validation): [10] Total time: 0:00:34 (0.4088 s / it) +cv: [10] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 2.741 acc: 0.188 f1: 0.124 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:25:10 lr: nan time: 3.7766 data: 3.4852 max mem: 3953 +train: [11] [ 20/400] eta: 0:03:29 lr: 0.000195 loss: 2.9491 (2.9552) grad: 0.0271 (0.0270) time: 0.3905 data: 0.0119 max mem: 3953 +train: [11] [ 40/400] eta: 0:02:51 lr: 0.000193 loss: 2.9529 (2.9591) grad: 0.0271 (0.0273) time: 0.3959 data: 0.0039 max mem: 3953 +train: [11] [ 60/400] eta: 0:02:30 lr: 0.000192 loss: 2.9686 (2.9629) grad: 0.0276 (0.0276) time: 0.3765 data: 0.0042 max mem: 3953 +train: [11] [ 80/400] eta: 0:02:16 lr: 0.000190 loss: 2.9523 (2.9563) grad: 0.0270 (0.0274) time: 0.3720 data: 0.0042 max mem: 3953 +train: [11] [100/400] eta: 0:02:04 lr: 0.000189 loss: 2.9402 (2.9572) grad: 0.0268 (0.0274) time: 0.3764 data: 0.0041 max mem: 3953 +train: [11] [120/400] eta: 0:01:54 lr: 0.000187 loss: 2.9420 (2.9545) grad: 0.0268 (0.0274) time: 0.3807 data: 0.0040 max mem: 3953 +train: [11] [140/400] eta: 0:01:44 lr: 0.000186 loss: 2.9402 (2.9538) grad: 0.0272 (0.0273) time: 0.3655 data: 0.0040 max mem: 3953 +train: [11] [160/400] eta: 0:01:36 lr: 0.000184 loss: 2.9402 (2.9553) grad: 0.0273 (0.0274) time: 0.3971 data: 0.0043 max mem: 3953 +train: [11] [180/400] eta: 0:01:27 lr: 0.000183 loss: 2.9596 (2.9566) grad: 0.0273 (0.0273) time: 0.3703 data: 0.0043 max mem: 3953 +train: [11] [200/400] eta: 0:01:20 lr: 0.000181 loss: 2.9443 (2.9548) grad: 0.0268 (0.0274) time: 0.4073 data: 0.0039 max mem: 3953 +train: [11] [220/400] eta: 0:01:11 lr: 0.000180 loss: 2.9443 (2.9551) grad: 0.0267 (0.0273) time: 0.3852 data: 0.0044 max mem: 3953 +train: [11] [240/400] eta: 0:01:03 lr: 0.000178 loss: 2.9580 (2.9560) grad: 0.0264 (0.0272) time: 0.3694 data: 0.0046 max mem: 3953 +train: [11] [260/400] eta: 0:00:55 lr: 0.000177 loss: 2.9577 (2.9560) grad: 0.0264 (0.0272) time: 0.3735 data: 0.0044 max mem: 3953 +train: [11] [280/400] eta: 0:00:47 lr: 0.000175 loss: 2.9489 (2.9550) grad: 0.0262 (0.0271) time: 0.3959 data: 0.0045 max mem: 3953 +train: [11] [300/400] eta: 0:00:39 lr: 0.000174 loss: 2.9515 (2.9545) grad: 0.0262 (0.0272) time: 0.3757 data: 0.0040 max mem: 3953 +train: [11] [320/400] eta: 0:00:31 lr: 0.000172 loss: 2.9659 (2.9566) grad: 0.0269 (0.0271) time: 0.3737 data: 0.0040 max mem: 3953 +train: [11] [340/400] eta: 0:00:23 lr: 0.000170 loss: 2.9815 (2.9579) grad: 0.0265 (0.0271) time: 0.4007 data: 0.0039 max mem: 3953 +train: [11] [360/400] eta: 0:00:15 lr: 0.000169 loss: 2.9529 (2.9567) grad: 0.0258 (0.0271) time: 0.4282 data: 0.0045 max mem: 3953 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 2.9429 (2.9571) grad: 0.0267 (0.0271) time: 0.3812 data: 0.0045 max mem: 3953 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.9472 (2.9569) grad: 0.0276 (0.0272) time: 0.3774 data: 0.0041 max mem: 3953 +train: [11] Total time: 0:02:37 (0.3933 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.9472 (2.9569) grad: 0.0276 (0.0272) +eval (validation): [11] [ 0/85] eta: 0:05:15 time: 3.7108 data: 3.3912 max mem: 3953 +eval (validation): [11] [20/85] eta: 0:00:33 time: 0.3624 data: 0.0037 max mem: 3953 +eval (validation): [11] [40/85] eta: 0:00:20 time: 0.3758 data: 0.0040 max mem: 3953 +eval (validation): [11] [60/85] eta: 0:00:10 time: 0.3720 data: 0.0043 max mem: 3953 +eval (validation): [11] [80/85] eta: 0:00:02 time: 0.3384 data: 0.0042 max mem: 3953 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3307 data: 0.0040 max mem: 3953 +eval (validation): [11] Total time: 0:00:34 (0.4028 s / it) +cv: [11] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.739 acc: 0.193 f1: 0.125 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:22:04 lr: nan time: 3.3122 data: 3.0892 max mem: 3953 +train: [12] [ 20/400] eta: 0:03:17 lr: 0.000164 loss: 2.9401 (2.9309) grad: 0.0269 (0.0267) time: 0.3789 data: 0.0152 max mem: 3953 +train: [12] [ 40/400] eta: 0:02:44 lr: 0.000163 loss: 2.9401 (2.9388) grad: 0.0264 (0.0264) time: 0.3932 data: 0.0042 max mem: 3953 +train: [12] [ 60/400] eta: 0:02:25 lr: 0.000161 loss: 2.9608 (2.9473) grad: 0.0264 (0.0265) time: 0.3648 data: 0.0039 max mem: 3953 +train: [12] [ 80/400] eta: 0:02:14 lr: 0.000160 loss: 2.9209 (2.9357) grad: 0.0269 (0.0268) time: 0.3980 data: 0.0042 max mem: 3953 +train: [12] [100/400] eta: 0:02:03 lr: 0.000158 loss: 2.9207 (2.9406) grad: 0.0268 (0.0269) time: 0.3829 data: 0.0041 max mem: 3953 +train: [12] [120/400] eta: 0:01:54 lr: 0.000156 loss: 2.9419 (2.9423) grad: 0.0266 (0.0270) time: 0.3832 data: 0.0043 max mem: 3953 +train: [12] [140/400] eta: 0:01:44 lr: 0.000155 loss: 2.9448 (2.9438) grad: 0.0259 (0.0268) time: 0.3715 data: 0.0042 max mem: 3953 +train: [12] [160/400] eta: 0:01:36 lr: 0.000153 loss: 2.9393 (2.9418) grad: 0.0270 (0.0270) time: 0.3832 data: 0.0044 max mem: 3953 +train: [12] [180/400] eta: 0:01:27 lr: 0.000152 loss: 2.9442 (2.9458) grad: 0.0273 (0.0269) time: 0.3695 data: 0.0039 max mem: 3953 +train: [12] [200/400] eta: 0:01:19 lr: 0.000150 loss: 2.9479 (2.9455) grad: 0.0263 (0.0270) time: 0.3924 data: 0.0042 max mem: 3953 +train: [12] [220/400] eta: 0:01:11 lr: 0.000149 loss: 2.9270 (2.9441) grad: 0.0263 (0.0268) time: 0.3861 data: 0.0041 max mem: 3953 +train: [12] [240/400] eta: 0:01:02 lr: 0.000147 loss: 2.9454 (2.9451) grad: 0.0265 (0.0269) time: 0.3695 data: 0.0043 max mem: 3953 +train: [12] [260/400] eta: 0:00:55 lr: 0.000145 loss: 2.9486 (2.9435) grad: 0.0265 (0.0268) time: 0.4046 data: 0.0038 max mem: 3953 +train: [12] [280/400] eta: 0:00:47 lr: 0.000144 loss: 2.9511 (2.9448) grad: 0.0262 (0.0268) time: 0.3963 data: 0.0042 max mem: 3953 +train: [12] [300/400] eta: 0:00:39 lr: 0.000142 loss: 2.9400 (2.9429) grad: 0.0262 (0.0268) time: 0.3679 data: 0.0042 max mem: 3953 +train: [12] [320/400] eta: 0:00:31 lr: 0.000141 loss: 2.9400 (2.9438) grad: 0.0267 (0.0268) time: 0.3782 data: 0.0044 max mem: 3953 +train: [12] [340/400] eta: 0:00:23 lr: 0.000139 loss: 2.9634 (2.9462) grad: 0.0268 (0.0268) time: 0.3812 data: 0.0041 max mem: 3953 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 3.0036 (2.9488) grad: 0.0266 (0.0267) time: 0.3720 data: 0.0046 max mem: 3953 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 2.9713 (2.9490) grad: 0.0266 (0.0268) time: 0.3794 data: 0.0044 max mem: 3953 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.9495 (2.9490) grad: 0.0275 (0.0269) time: 0.3720 data: 0.0044 max mem: 3953 +train: [12] Total time: 0:02:35 (0.3889 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.9495 (2.9490) grad: 0.0275 (0.0269) +eval (validation): [12] [ 0/85] eta: 0:05:04 time: 3.5840 data: 3.3688 max mem: 3953 +eval (validation): [12] [20/85] eta: 0:00:35 time: 0.3949 data: 0.0054 max mem: 3953 +eval (validation): [12] [40/85] eta: 0:00:21 time: 0.3850 data: 0.0043 max mem: 3953 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3717 data: 0.0050 max mem: 3953 +eval (validation): [12] [80/85] eta: 0:00:02 time: 0.3476 data: 0.0044 max mem: 3953 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3375 data: 0.0043 max mem: 3953 +eval (validation): [12] Total time: 0:00:35 (0.4130 s / it) +cv: [12] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 2.741 acc: 0.191 f1: 0.128 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:23:23 lr: nan time: 3.5090 data: 3.2647 max mem: 3953 +train: [13] [ 20/400] eta: 0:03:21 lr: 0.000133 loss: 2.9312 (2.9382) grad: 0.0267 (0.0265) time: 0.3810 data: 0.0044 max mem: 3953 +train: [13] [ 40/400] eta: 0:02:43 lr: 0.000131 loss: 2.9301 (2.9306) grad: 0.0262 (0.0265) time: 0.3757 data: 0.0042 max mem: 3953 +train: [13] [ 60/400] eta: 0:02:26 lr: 0.000130 loss: 2.9301 (2.9346) grad: 0.0266 (0.0268) time: 0.3840 data: 0.0038 max mem: 3953 +train: [13] [ 80/400] eta: 0:02:13 lr: 0.000128 loss: 2.9538 (2.9358) grad: 0.0271 (0.0269) time: 0.3707 data: 0.0042 max mem: 3953 +train: [13] [100/400] eta: 0:02:03 lr: 0.000127 loss: 2.9538 (2.9388) grad: 0.0267 (0.0269) time: 0.3904 data: 0.0041 max mem: 3953 +train: [13] [120/400] eta: 0:01:53 lr: 0.000125 loss: 2.9337 (2.9399) grad: 0.0262 (0.0269) time: 0.3731 data: 0.0041 max mem: 3953 +train: [13] [140/400] eta: 0:01:44 lr: 0.000124 loss: 2.9409 (2.9412) grad: 0.0272 (0.0269) time: 0.3911 data: 0.0043 max mem: 3953 +train: [13] [160/400] eta: 0:01:35 lr: 0.000122 loss: 2.9538 (2.9414) grad: 0.0270 (0.0269) time: 0.3740 data: 0.0042 max mem: 3953 +train: [13] [180/400] eta: 0:01:27 lr: 0.000120 loss: 2.9396 (2.9403) grad: 0.0270 (0.0269) time: 0.3756 data: 0.0040 max mem: 3953 +train: [13] [200/400] eta: 0:01:19 lr: 0.000119 loss: 2.9411 (2.9419) grad: 0.0276 (0.0269) time: 0.3959 data: 0.0044 max mem: 3953 +train: [13] [220/400] eta: 0:01:11 lr: 0.000117 loss: 2.9443 (2.9410) grad: 0.0277 (0.0270) time: 0.3966 data: 0.0040 max mem: 3953 +train: [13] [240/400] eta: 0:01:03 lr: 0.000116 loss: 2.9443 (2.9401) grad: 0.0280 (0.0270) time: 0.3641 data: 0.0041 max mem: 3953 +train: [13] [260/400] eta: 0:00:55 lr: 0.000114 loss: 2.9592 (2.9422) grad: 0.0259 (0.0269) time: 0.3875 data: 0.0042 max mem: 3953 +train: [13] [280/400] eta: 0:00:47 lr: 0.000113 loss: 2.9592 (2.9418) grad: 0.0262 (0.0269) time: 0.3798 data: 0.0043 max mem: 3953 +train: [13] [300/400] eta: 0:00:39 lr: 0.000111 loss: 2.9321 (2.9410) grad: 0.0269 (0.0269) time: 0.3798 data: 0.0041 max mem: 3953 +train: [13] [320/400] eta: 0:00:31 lr: 0.000110 loss: 2.9414 (2.9422) grad: 0.0259 (0.0268) time: 0.3793 data: 0.0045 max mem: 3953 +train: [13] [340/400] eta: 0:00:23 lr: 0.000108 loss: 2.9511 (2.9409) grad: 0.0259 (0.0268) time: 0.3846 data: 0.0043 max mem: 3953 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 2.9256 (2.9416) grad: 0.0260 (0.0268) time: 0.3763 data: 0.0043 max mem: 3953 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 2.9499 (2.9426) grad: 0.0272 (0.0268) time: 0.3793 data: 0.0044 max mem: 3953 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.9506 (2.9419) grad: 0.0273 (0.0269) time: 0.3713 data: 0.0043 max mem: 3953 +train: [13] Total time: 0:02:35 (0.3886 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.9506 (2.9419) grad: 0.0273 (0.0269) +eval (validation): [13] [ 0/85] eta: 0:04:50 time: 3.4189 data: 3.1213 max mem: 3953 +eval (validation): [13] [20/85] eta: 0:00:36 time: 0.4114 data: 0.0056 max mem: 3953 +eval (validation): [13] [40/85] eta: 0:00:21 time: 0.3826 data: 0.0041 max mem: 3953 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3592 data: 0.0046 max mem: 3953 +eval (validation): [13] [80/85] eta: 0:00:02 time: 0.3495 data: 0.0046 max mem: 3953 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3376 data: 0.0043 max mem: 3953 +eval (validation): [13] Total time: 0:00:35 (0.4129 s / it) +cv: [13] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.729 acc: 0.198 f1: 0.133 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:24:20 lr: nan time: 3.6524 data: 3.3574 max mem: 3953 +train: [14] [ 20/400] eta: 0:03:30 lr: 0.000102 loss: 2.9293 (2.9463) grad: 0.0265 (0.0275) time: 0.3981 data: 0.0203 max mem: 3953 +train: [14] [ 40/400] eta: 0:02:46 lr: 0.000101 loss: 2.9392 (2.9540) grad: 0.0268 (0.0273) time: 0.3652 data: 0.0037 max mem: 3953 +train: [14] [ 60/400] eta: 0:02:29 lr: 0.000099 loss: 2.9505 (2.9570) grad: 0.0268 (0.0270) time: 0.3920 data: 0.0038 max mem: 3953 +train: [14] [ 80/400] eta: 0:02:14 lr: 0.000098 loss: 2.9687 (2.9616) grad: 0.0256 (0.0267) time: 0.3700 data: 0.0043 max mem: 3953 +train: [14] [100/400] eta: 0:02:04 lr: 0.000096 loss: 2.9425 (2.9563) grad: 0.0254 (0.0267) time: 0.3807 data: 0.0040 max mem: 3953 +train: [14] [120/400] eta: 0:01:55 lr: 0.000095 loss: 2.9320 (2.9492) grad: 0.0262 (0.0266) time: 0.3992 data: 0.0042 max mem: 3953 +train: [14] [140/400] eta: 0:01:46 lr: 0.000093 loss: 2.9426 (2.9496) grad: 0.0266 (0.0267) time: 0.3895 data: 0.0041 max mem: 3953 +train: [14] [160/400] eta: 0:01:37 lr: 0.000092 loss: 2.9514 (2.9507) grad: 0.0274 (0.0268) time: 0.3853 data: 0.0041 max mem: 3953 +train: [14] [180/400] eta: 0:01:28 lr: 0.000090 loss: 2.9332 (2.9487) grad: 0.0273 (0.0269) time: 0.3858 data: 0.0042 max mem: 3953 +train: [14] [200/400] eta: 0:01:20 lr: 0.000089 loss: 2.9211 (2.9476) grad: 0.0266 (0.0268) time: 0.3914 data: 0.0043 max mem: 3953 +train: [14] [220/400] eta: 0:01:12 lr: 0.000088 loss: 2.9238 (2.9472) grad: 0.0270 (0.0269) time: 0.3856 data: 0.0042 max mem: 3953 +train: [14] [240/400] eta: 0:01:03 lr: 0.000086 loss: 2.9340 (2.9466) grad: 0.0272 (0.0269) time: 0.3621 data: 0.0040 max mem: 3953 +train: [14] [260/400] eta: 0:00:55 lr: 0.000085 loss: 2.9501 (2.9462) grad: 0.0269 (0.0269) time: 0.3813 data: 0.0040 max mem: 3953 +train: [14] [280/400] eta: 0:00:47 lr: 0.000083 loss: 2.9446 (2.9459) grad: 0.0264 (0.0269) time: 0.3926 data: 0.0040 max mem: 3953 +train: [14] [300/400] eta: 0:00:39 lr: 0.000082 loss: 2.9494 (2.9472) grad: 0.0258 (0.0268) time: 0.3955 data: 0.0044 max mem: 3953 +train: [14] [320/400] eta: 0:00:31 lr: 0.000081 loss: 2.9461 (2.9459) grad: 0.0267 (0.0268) time: 0.3932 data: 0.0045 max mem: 3953 +train: [14] [340/400] eta: 0:00:23 lr: 0.000079 loss: 2.9590 (2.9476) grad: 0.0269 (0.0268) time: 0.3790 data: 0.0046 max mem: 3953 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 2.9595 (2.9477) grad: 0.0263 (0.0268) time: 0.3852 data: 0.0042 max mem: 3953 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 2.9465 (2.9466) grad: 0.0267 (0.0268) time: 0.3744 data: 0.0042 max mem: 3953 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.9530 (2.9463) grad: 0.0266 (0.0268) time: 0.3755 data: 0.0044 max mem: 3953 +train: [14] Total time: 0:02:37 (0.3926 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.9530 (2.9463) grad: 0.0266 (0.0268) +eval (validation): [14] [ 0/85] eta: 0:04:48 time: 3.3895 data: 3.1493 max mem: 3953 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3603 data: 0.0047 max mem: 3953 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3540 data: 0.0035 max mem: 3953 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3632 data: 0.0043 max mem: 3953 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3402 data: 0.0042 max mem: 3953 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3385 data: 0.0043 max mem: 3953 +eval (validation): [14] Total time: 0:00:33 (0.3929 s / it) +cv: [14] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.732 acc: 0.196 f1: 0.130 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:26 lr: nan time: 3.5173 data: 3.2798 max mem: 3953 +train: [15] [ 20/400] eta: 0:03:23 lr: 0.000074 loss: 2.9253 (2.9301) grad: 0.0275 (0.0278) time: 0.3870 data: 0.0048 max mem: 3953 +train: [15] [ 40/400] eta: 0:02:48 lr: 0.000072 loss: 2.9138 (2.9237) grad: 0.0265 (0.0270) time: 0.3940 data: 0.0029 max mem: 3953 +train: [15] [ 60/400] eta: 0:02:29 lr: 0.000071 loss: 2.9138 (2.9257) grad: 0.0254 (0.0268) time: 0.3867 data: 0.0040 max mem: 3953 +train: [15] [ 80/400] eta: 0:02:16 lr: 0.000070 loss: 2.9112 (2.9197) grad: 0.0258 (0.0266) time: 0.3889 data: 0.0044 max mem: 3953 +train: [15] [100/400] eta: 0:02:05 lr: 0.000068 loss: 2.9186 (2.9245) grad: 0.0258 (0.0265) time: 0.3717 data: 0.0042 max mem: 3953 +train: [15] [120/400] eta: 0:01:55 lr: 0.000067 loss: 2.9289 (2.9235) grad: 0.0263 (0.0268) time: 0.3966 data: 0.0044 max mem: 3953 +train: [15] [140/400] eta: 0:01:45 lr: 0.000066 loss: 2.9127 (2.9230) grad: 0.0271 (0.0268) time: 0.3700 data: 0.0045 max mem: 3953 +train: [15] [160/400] eta: 0:01:36 lr: 0.000064 loss: 2.9185 (2.9250) grad: 0.0271 (0.0269) time: 0.3498 data: 0.0043 max mem: 3953 +train: [15] [180/400] eta: 0:01:26 lr: 0.000063 loss: 2.9387 (2.9280) grad: 0.0274 (0.0269) time: 0.3535 data: 0.0042 max mem: 3953 +train: [15] [200/400] eta: 0:01:18 lr: 0.000062 loss: 2.9567 (2.9303) grad: 0.0269 (0.0269) time: 0.3744 data: 0.0042 max mem: 3953 +train: [15] [220/400] eta: 0:01:10 lr: 0.000061 loss: 2.9499 (2.9311) grad: 0.0260 (0.0269) time: 0.3589 data: 0.0041 max mem: 3953 +train: [15] [240/400] eta: 0:01:01 lr: 0.000059 loss: 2.9499 (2.9331) grad: 0.0264 (0.0269) time: 0.3485 data: 0.0042 max mem: 3953 +train: [15] [260/400] eta: 0:00:53 lr: 0.000058 loss: 2.9373 (2.9334) grad: 0.0264 (0.0268) time: 0.3499 data: 0.0041 max mem: 3953 +train: [15] [280/400] eta: 0:00:45 lr: 0.000057 loss: 2.9367 (2.9361) grad: 0.0266 (0.0269) time: 0.3773 data: 0.0042 max mem: 3953 +train: [15] [300/400] eta: 0:00:38 lr: 0.000056 loss: 2.9257 (2.9368) grad: 0.0266 (0.0269) time: 0.3456 data: 0.0041 max mem: 3953 +train: [15] [320/400] eta: 0:00:30 lr: 0.000054 loss: 2.9414 (2.9389) grad: 0.0273 (0.0269) time: 0.3531 data: 0.0040 max mem: 3953 +train: [15] [340/400] eta: 0:00:22 lr: 0.000053 loss: 2.9414 (2.9380) grad: 0.0268 (0.0269) time: 0.3519 data: 0.0044 max mem: 3953 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 2.9299 (2.9387) grad: 0.0261 (0.0268) time: 0.3556 data: 0.0045 max mem: 3953 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 2.9230 (2.9377) grad: 0.0263 (0.0268) time: 0.3497 data: 0.0043 max mem: 3953 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.9271 (2.9384) grad: 0.0267 (0.0269) time: 0.3395 data: 0.0041 max mem: 3953 +train: [15] Total time: 0:02:29 (0.3733 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.9271 (2.9384) grad: 0.0267 (0.0269) +eval (validation): [15] [ 0/85] eta: 0:04:47 time: 3.3773 data: 3.1006 max mem: 3953 +eval (validation): [15] [20/85] eta: 0:00:33 time: 0.3697 data: 0.0103 max mem: 3953 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3507 data: 0.0035 max mem: 3953 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3687 data: 0.0046 max mem: 3953 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3484 data: 0.0046 max mem: 3953 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3320 data: 0.0046 max mem: 3953 +eval (validation): [15] Total time: 0:00:33 (0.3966 s / it) +cv: [15] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.719 acc: 0.200 f1: 0.134 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:21:34 lr: nan time: 3.2373 data: 3.0065 max mem: 3953 +train: [16] [ 20/400] eta: 0:03:10 lr: 0.000048 loss: 2.9169 (2.9319) grad: 0.0257 (0.0260) time: 0.3647 data: 0.0063 max mem: 3953 +train: [16] [ 40/400] eta: 0:02:37 lr: 0.000047 loss: 2.9302 (2.9302) grad: 0.0260 (0.0264) time: 0.3719 data: 0.0036 max mem: 3953 +train: [16] [ 60/400] eta: 0:02:20 lr: 0.000046 loss: 2.9354 (2.9431) grad: 0.0271 (0.0268) time: 0.3610 data: 0.0044 max mem: 3953 +train: [16] [ 80/400] eta: 0:02:07 lr: 0.000045 loss: 2.9509 (2.9362) grad: 0.0264 (0.0267) time: 0.3575 data: 0.0040 max mem: 3953 +train: [16] [100/400] eta: 0:02:00 lr: 0.000044 loss: 2.9621 (2.9433) grad: 0.0264 (0.0270) time: 0.4192 data: 0.0043 max mem: 3953 +train: [16] [120/400] eta: 0:01:52 lr: 0.000043 loss: 2.9596 (2.9431) grad: 0.0269 (0.0269) time: 0.3920 data: 0.0045 max mem: 3953 +train: [16] [140/400] eta: 0:01:43 lr: 0.000042 loss: 2.9393 (2.9435) grad: 0.0265 (0.0269) time: 0.3753 data: 0.0044 max mem: 3953 +train: [16] [160/400] eta: 0:01:34 lr: 0.000041 loss: 2.9248 (2.9433) grad: 0.0268 (0.0269) time: 0.3596 data: 0.0044 max mem: 3953 +train: [16] [180/400] eta: 0:01:26 lr: 0.000040 loss: 2.9551 (2.9453) grad: 0.0268 (0.0269) time: 0.3988 data: 0.0041 max mem: 3953 +train: [16] [200/400] eta: 0:01:19 lr: 0.000039 loss: 2.9551 (2.9454) grad: 0.0265 (0.0269) time: 0.4085 data: 0.0045 max mem: 3953 +train: [16] [220/400] eta: 0:01:10 lr: 0.000038 loss: 2.9334 (2.9440) grad: 0.0268 (0.0269) time: 0.3624 data: 0.0045 max mem: 3953 +train: [16] [240/400] eta: 0:01:02 lr: 0.000036 loss: 2.9334 (2.9427) grad: 0.0268 (0.0270) time: 0.3757 data: 0.0047 max mem: 3953 +train: [16] [260/400] eta: 0:00:54 lr: 0.000035 loss: 2.9388 (2.9433) grad: 0.0271 (0.0270) time: 0.3869 data: 0.0045 max mem: 3953 +train: [16] [280/400] eta: 0:00:46 lr: 0.000034 loss: 2.9151 (2.9399) grad: 0.0267 (0.0270) time: 0.3936 data: 0.0044 max mem: 3953 +train: [16] [300/400] eta: 0:00:39 lr: 0.000033 loss: 2.9312 (2.9409) grad: 0.0263 (0.0270) time: 0.3885 data: 0.0044 max mem: 3953 +train: [16] [320/400] eta: 0:00:31 lr: 0.000032 loss: 2.9401 (2.9408) grad: 0.0266 (0.0270) time: 0.3787 data: 0.0044 max mem: 3953 +train: [16] [340/400] eta: 0:00:23 lr: 0.000031 loss: 2.9212 (2.9387) grad: 0.0259 (0.0269) time: 0.3837 data: 0.0045 max mem: 3953 +train: [16] [360/400] eta: 0:00:15 lr: 0.000031 loss: 2.8969 (2.9387) grad: 0.0259 (0.0269) time: 0.3880 data: 0.0047 max mem: 3953 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 2.9381 (2.9383) grad: 0.0265 (0.0269) time: 0.3802 data: 0.0045 max mem: 3953 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.9221 (2.9377) grad: 0.0267 (0.0269) time: 0.3837 data: 0.0041 max mem: 3953 +train: [16] Total time: 0:02:35 (0.3890 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.9221 (2.9377) grad: 0.0267 (0.0269) +eval (validation): [16] [ 0/85] eta: 0:05:09 time: 3.6372 data: 3.3819 max mem: 3953 +eval (validation): [16] [20/85] eta: 0:00:36 time: 0.4146 data: 0.0041 max mem: 3953 +eval (validation): [16] [40/85] eta: 0:00:21 time: 0.3913 data: 0.0046 max mem: 3953 +eval (validation): [16] [60/85] eta: 0:00:11 time: 0.4014 data: 0.0047 max mem: 3953 +eval (validation): [16] [80/85] eta: 0:00:02 time: 0.3663 data: 0.0047 max mem: 3953 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3460 data: 0.0044 max mem: 3953 +eval (validation): [16] Total time: 0:00:36 (0.4323 s / it) +cv: [16] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.720 acc: 0.200 f1: 0.133 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [17] [ 0/400] eta: 0:23:39 lr: nan time: 3.5480 data: 3.1951 max mem: 3953 +train: [17] [ 20/400] eta: 0:03:41 lr: 0.000028 loss: 2.9365 (2.9344) grad: 0.0265 (0.0266) time: 0.4346 data: 0.0044 max mem: 3953 +train: [17] [ 40/400] eta: 0:02:59 lr: 0.000027 loss: 2.9365 (2.9407) grad: 0.0273 (0.0272) time: 0.4087 data: 0.0046 max mem: 3953 +train: [17] [ 60/400] eta: 0:02:37 lr: 0.000026 loss: 2.9357 (2.9432) grad: 0.0273 (0.0270) time: 0.3898 data: 0.0039 max mem: 3953 +train: [17] [ 80/400] eta: 0:02:23 lr: 0.000025 loss: 2.9306 (2.9391) grad: 0.0266 (0.0270) time: 0.4108 data: 0.0045 max mem: 3953 +train: [17] [100/400] eta: 0:02:12 lr: 0.000024 loss: 2.9288 (2.9375) grad: 0.0266 (0.0270) time: 0.4058 data: 0.0044 max mem: 3953 +train: [17] [120/400] eta: 0:02:01 lr: 0.000023 loss: 2.9215 (2.9342) grad: 0.0267 (0.0270) time: 0.4077 data: 0.0046 max mem: 3953 +train: [17] [140/400] eta: 0:01:51 lr: 0.000023 loss: 2.9089 (2.9354) grad: 0.0269 (0.0271) time: 0.3900 data: 0.0045 max mem: 3953 +train: [17] [160/400] eta: 0:01:40 lr: 0.000022 loss: 2.9077 (2.9342) grad: 0.0284 (0.0272) time: 0.3579 data: 0.0040 max mem: 3953 +train: [17] [180/400] eta: 0:01:31 lr: 0.000021 loss: 2.9401 (2.9356) grad: 0.0274 (0.0272) time: 0.3968 data: 0.0044 max mem: 3953 +train: [17] [200/400] eta: 0:01:22 lr: 0.000020 loss: 2.9383 (2.9334) grad: 0.0276 (0.0273) time: 0.3850 data: 0.0046 max mem: 3953 +train: [17] [220/400] eta: 0:01:14 lr: 0.000019 loss: 2.9134 (2.9317) grad: 0.0276 (0.0273) time: 0.3825 data: 0.0044 max mem: 3953 +train: [17] [240/400] eta: 0:01:05 lr: 0.000019 loss: 2.9223 (2.9311) grad: 0.0261 (0.0273) time: 0.3608 data: 0.0042 max mem: 3953 +train: [17] [260/400] eta: 0:00:56 lr: 0.000018 loss: 2.9247 (2.9318) grad: 0.0261 (0.0272) time: 0.3809 data: 0.0044 max mem: 3953 +train: [17] [280/400] eta: 0:00:48 lr: 0.000017 loss: 2.9263 (2.9311) grad: 0.0262 (0.0271) time: 0.3950 data: 0.0045 max mem: 3953 +train: [17] [300/400] eta: 0:00:40 lr: 0.000016 loss: 2.9310 (2.9320) grad: 0.0267 (0.0271) time: 0.3978 data: 0.0041 max mem: 3953 +train: [17] [320/400] eta: 0:00:32 lr: 0.000016 loss: 2.9310 (2.9314) grad: 0.0268 (0.0272) time: 0.3764 data: 0.0044 max mem: 3953 +train: [17] [340/400] eta: 0:00:24 lr: 0.000015 loss: 2.9227 (2.9304) grad: 0.0268 (0.0271) time: 0.3836 data: 0.0044 max mem: 3953 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 2.9217 (2.9313) grad: 0.0271 (0.0271) time: 0.3680 data: 0.0044 max mem: 3953 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 2.8999 (2.9311) grad: 0.0274 (0.0271) time: 0.3732 data: 0.0042 max mem: 3953 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.9355 (2.9315) grad: 0.0263 (0.0271) time: 0.4105 data: 0.0048 max mem: 3953 +train: [17] Total time: 0:02:39 (0.3989 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.9355 (2.9315) grad: 0.0263 (0.0271) +eval (validation): [17] [ 0/85] eta: 0:04:59 time: 3.5234 data: 3.2301 max mem: 3953 +eval (validation): [17] [20/85] eta: 0:00:34 time: 0.3805 data: 0.0048 max mem: 3953 +eval (validation): [17] [40/85] eta: 0:00:20 time: 0.3798 data: 0.0049 max mem: 3953 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.3759 data: 0.0049 max mem: 3953 +eval (validation): [17] [80/85] eta: 0:00:02 time: 0.3431 data: 0.0042 max mem: 3953 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3305 data: 0.0040 max mem: 3953 +eval (validation): [17] Total time: 0:00:34 (0.4076 s / it) +cv: [17] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 2.721 acc: 0.199 f1: 0.133 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:23:54 lr: nan time: 3.5852 data: 3.2838 max mem: 3953 +train: [18] [ 20/400] eta: 0:03:27 lr: 0.000012 loss: 2.8966 (2.9200) grad: 0.0270 (0.0269) time: 0.3952 data: 0.0038 max mem: 3953 +train: [18] [ 40/400] eta: 0:02:48 lr: 0.000012 loss: 2.9338 (2.9459) grad: 0.0266 (0.0270) time: 0.3868 data: 0.0035 max mem: 3953 +train: [18] [ 60/400] eta: 0:02:28 lr: 0.000011 loss: 2.9488 (2.9412) grad: 0.0265 (0.0268) time: 0.3718 data: 0.0041 max mem: 3953 +train: [18] [ 80/400] eta: 0:02:17 lr: 0.000011 loss: 2.9229 (2.9369) grad: 0.0264 (0.0269) time: 0.4076 data: 0.0043 max mem: 3953 +train: [18] [100/400] eta: 0:02:06 lr: 0.000010 loss: 2.9291 (2.9378) grad: 0.0269 (0.0270) time: 0.3852 data: 0.0044 max mem: 3953 +train: [18] [120/400] eta: 0:01:55 lr: 0.000009 loss: 2.9291 (2.9363) grad: 0.0269 (0.0268) time: 0.3686 data: 0.0045 max mem: 3953 +train: [18] [140/400] eta: 0:01:46 lr: 0.000009 loss: 2.9250 (2.9301) grad: 0.0267 (0.0268) time: 0.3816 data: 0.0041 max mem: 3953 +train: [18] [160/400] eta: 0:01:36 lr: 0.000008 loss: 2.9203 (2.9320) grad: 0.0262 (0.0267) time: 0.3610 data: 0.0041 max mem: 3953 +train: [18] [180/400] eta: 0:01:28 lr: 0.000008 loss: 2.9242 (2.9315) grad: 0.0257 (0.0267) time: 0.4183 data: 0.0041 max mem: 3953 +train: [18] [200/400] eta: 0:01:20 lr: 0.000007 loss: 2.9462 (2.9336) grad: 0.0273 (0.0268) time: 0.3791 data: 0.0044 max mem: 3953 +train: [18] [220/400] eta: 0:01:11 lr: 0.000007 loss: 2.9603 (2.9353) grad: 0.0268 (0.0268) time: 0.3845 data: 0.0042 max mem: 3953 +train: [18] [240/400] eta: 0:01:03 lr: 0.000006 loss: 2.9240 (2.9339) grad: 0.0259 (0.0267) time: 0.3622 data: 0.0040 max mem: 3953 +train: [18] [260/400] eta: 0:00:55 lr: 0.000006 loss: 2.9116 (2.9330) grad: 0.0263 (0.0268) time: 0.3747 data: 0.0044 max mem: 3953 +train: [18] [280/400] eta: 0:00:47 lr: 0.000006 loss: 2.9257 (2.9316) grad: 0.0268 (0.0267) time: 0.3922 data: 0.0045 max mem: 3953 +train: [18] [300/400] eta: 0:00:39 lr: 0.000005 loss: 2.9290 (2.9322) grad: 0.0266 (0.0267) time: 0.3752 data: 0.0042 max mem: 3953 +train: [18] [320/400] eta: 0:00:31 lr: 0.000005 loss: 2.9422 (2.9336) grad: 0.0266 (0.0268) time: 0.3606 data: 0.0042 max mem: 3953 +train: [18] [340/400] eta: 0:00:23 lr: 0.000004 loss: 2.9422 (2.9329) grad: 0.0268 (0.0267) time: 0.3880 data: 0.0044 max mem: 3953 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 2.9323 (2.9329) grad: 0.0262 (0.0268) time: 0.3706 data: 0.0040 max mem: 3953 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 2.9414 (2.9334) grad: 0.0267 (0.0268) time: 0.4004 data: 0.0046 max mem: 3953 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.9621 (2.9340) grad: 0.0261 (0.0267) time: 0.4005 data: 0.0041 max mem: 3953 +train: [18] Total time: 0:02:36 (0.3915 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.9621 (2.9340) grad: 0.0261 (0.0267) +eval (validation): [18] [ 0/85] eta: 0:05:13 time: 3.6927 data: 3.3600 max mem: 3953 +eval (validation): [18] [20/85] eta: 0:00:37 time: 0.4190 data: 0.0113 max mem: 3953 +eval (validation): [18] [40/85] eta: 0:00:21 time: 0.3932 data: 0.0048 max mem: 3953 +eval (validation): [18] [60/85] eta: 0:00:11 time: 0.3787 data: 0.0037 max mem: 3953 +eval (validation): [18] [80/85] eta: 0:00:02 time: 0.3770 data: 0.0041 max mem: 3953 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3683 data: 0.0040 max mem: 3953 +eval (validation): [18] Total time: 0:00:36 (0.4351 s / it) +cv: [18] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.716 acc: 0.201 f1: 0.134 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [19] [ 0/400] eta: 0:25:30 lr: nan time: 3.8271 data: 3.5148 max mem: 3953 +train: [19] [ 20/400] eta: 0:03:37 lr: 0.000003 loss: 2.9317 (2.9343) grad: 0.0270 (0.0271) time: 0.4093 data: 0.0041 max mem: 3953 +train: [19] [ 40/400] eta: 0:02:51 lr: 0.000003 loss: 2.9221 (2.9222) grad: 0.0270 (0.0268) time: 0.3739 data: 0.0043 max mem: 3953 +train: [19] [ 60/400] eta: 0:02:32 lr: 0.000002 loss: 2.9164 (2.9278) grad: 0.0262 (0.0266) time: 0.3925 data: 0.0043 max mem: 3953 +train: [19] [ 80/400] eta: 0:02:20 lr: 0.000002 loss: 2.9217 (2.9229) grad: 0.0262 (0.0265) time: 0.4104 data: 0.0045 max mem: 3953 +train: [19] [100/400] eta: 0:02:07 lr: 0.000002 loss: 2.9086 (2.9204) grad: 0.0265 (0.0266) time: 0.3715 data: 0.0044 max mem: 3953 +train: [19] [120/400] eta: 0:01:56 lr: 0.000002 loss: 2.9119 (2.9233) grad: 0.0269 (0.0266) time: 0.3713 data: 0.0044 max mem: 3953 +train: [19] [140/400] eta: 0:01:47 lr: 0.000001 loss: 2.9364 (2.9252) grad: 0.0265 (0.0267) time: 0.3938 data: 0.0042 max mem: 3953 +train: [19] [160/400] eta: 0:01:38 lr: 0.000001 loss: 2.9531 (2.9297) grad: 0.0269 (0.0267) time: 0.3738 data: 0.0040 max mem: 3953 +train: [19] [180/400] eta: 0:01:29 lr: 0.000001 loss: 2.9648 (2.9347) grad: 0.0265 (0.0267) time: 0.4001 data: 0.0045 max mem: 3953 +train: [19] [200/400] eta: 0:01:21 lr: 0.000001 loss: 2.9455 (2.9337) grad: 0.0264 (0.0267) time: 0.3930 data: 0.0046 max mem: 3953 +train: [19] [220/400] eta: 0:01:12 lr: 0.000001 loss: 2.9296 (2.9340) grad: 0.0266 (0.0268) time: 0.3965 data: 0.0045 max mem: 3953 +train: [19] [240/400] eta: 0:01:04 lr: 0.000001 loss: 2.9343 (2.9351) grad: 0.0269 (0.0268) time: 0.3760 data: 0.0046 max mem: 3953 +train: [19] [260/400] eta: 0:00:56 lr: 0.000000 loss: 2.9354 (2.9340) grad: 0.0271 (0.0269) time: 0.3997 data: 0.0043 max mem: 3953 +train: [19] [280/400] eta: 0:00:48 lr: 0.000000 loss: 2.9395 (2.9348) grad: 0.0268 (0.0268) time: 0.4027 data: 0.0044 max mem: 3953 +train: [19] [300/400] eta: 0:00:40 lr: 0.000000 loss: 2.9637 (2.9366) grad: 0.0269 (0.0268) time: 0.4119 data: 0.0046 max mem: 3953 +train: [19] [320/400] eta: 0:00:32 lr: 0.000000 loss: 2.9493 (2.9366) grad: 0.0274 (0.0269) time: 0.4041 data: 0.0042 max mem: 3953 +train: [19] [340/400] eta: 0:00:24 lr: 0.000000 loss: 2.9205 (2.9355) grad: 0.0277 (0.0269) time: 0.4001 data: 0.0043 max mem: 3953 +train: [19] [360/400] eta: 0:00:16 lr: 0.000000 loss: 2.9156 (2.9349) grad: 0.0271 (0.0270) time: 0.3971 data: 0.0042 max mem: 3953 +train: [19] [380/400] eta: 0:00:08 lr: 0.000000 loss: 2.9156 (2.9360) grad: 0.0269 (0.0270) time: 0.4387 data: 0.0047 max mem: 3953 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.9188 (2.9356) grad: 0.0264 (0.0269) time: 0.3890 data: 0.0044 max mem: 3953 +train: [19] Total time: 0:02:41 (0.4042 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.9188 (2.9356) grad: 0.0264 (0.0269) +eval (validation): [19] [ 0/85] eta: 0:04:52 time: 3.4406 data: 3.1605 max mem: 3953 +eval (validation): [19] [20/85] eta: 0:00:35 time: 0.4088 data: 0.0044 max mem: 3953 +eval (validation): [19] [40/85] eta: 0:00:21 time: 0.3779 data: 0.0043 max mem: 3953 +eval (validation): [19] [60/85] eta: 0:00:11 time: 0.3950 data: 0.0045 max mem: 3953 +eval (validation): [19] [80/85] eta: 0:00:02 time: 0.3597 data: 0.0045 max mem: 3953 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3462 data: 0.0044 max mem: 3953 +eval (validation): [19] Total time: 0:00:35 (0.4205 s / it) +cv: [19] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.716 acc: 0.202 f1: 0.136 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +eval model info: +{"score": 0.2024732373569583, "hparam": [43, 1.0], "hparam_id": 47, "epoch": 19, "is_best": true, "best_score": 0.2024732373569583} +eval (train): [20] [ 0/509] eta: 0:29:25 time: 3.4691 data: 3.2374 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:04:17 time: 0.3792 data: 0.0139 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:03:33 time: 0.3785 data: 0.0046 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:03:07 time: 0.3448 data: 0.0037 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:58 time: 0.4054 data: 0.0049 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:46 time: 0.3779 data: 0.0043 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:35 time: 0.3585 data: 0.0044 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:24 time: 0.3516 data: 0.0048 max mem: 3953 +eval (train): [20] [160/509] eta: 0:02:14 time: 0.3432 data: 0.0045 max mem: 3953 +eval (train): [20] [180/509] eta: 0:02:06 time: 0.3538 data: 0.0048 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:57 time: 0.3419 data: 0.0046 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:48 time: 0.3480 data: 0.0040 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:40 time: 0.3428 data: 0.0043 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:32 time: 0.3340 data: 0.0044 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3480 data: 0.0043 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:17 time: 0.3637 data: 0.0044 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3503 data: 0.0045 max mem: 3953 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3322 data: 0.0044 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3531 data: 0.0044 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:46 time: 0.3576 data: 0.0042 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3640 data: 0.0049 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3388 data: 0.0046 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3531 data: 0.0046 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3443 data: 0.0046 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3332 data: 0.0044 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3286 data: 0.0041 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3134 data: 0.0040 max mem: 3953 +eval (train): [20] Total time: 0:03:03 (0.3599 s / it) +eval (validation): [20] [ 0/85] eta: 0:05:09 time: 3.6446 data: 3.4167 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3238 data: 0.0102 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3303 data: 0.0038 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3456 data: 0.0043 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3354 data: 0.0042 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3204 data: 0.0040 max mem: 3953 +eval (validation): [20] Total time: 0:00:31 (0.3747 s / it) +eval (test): [20] [ 0/85] eta: 0:04:39 time: 3.2911 data: 3.0668 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3286 data: 0.0045 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:17 time: 0.3210 data: 0.0040 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3531 data: 0.0046 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3358 data: 0.0040 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3221 data: 0.0040 max mem: 3953 +eval (test): [20] Total time: 0:00:31 (0.3704 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:42 time: 3.4511 data: 3.1630 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:32 time: 0.3733 data: 0.0047 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3224 data: 0.0036 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3455 data: 0.0040 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3258 data: 0.0043 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3157 data: 0.0039 max mem: 3953 +eval (testid): [20] Total time: 0:00:31 (0.3811 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +eval model info: +{"score": 0.2024732373569583, "hparam": [43, 1.0], "hparam_id": 47, "epoch": 19, "is_best": true, "best_score": 0.2024732373569583} +eval (train): [20] [ 0/509] eta: 0:29:02 time: 3.4235 data: 3.1444 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:04:07 time: 0.3604 data: 0.0057 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:03:19 time: 0.3424 data: 0.0047 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:02:58 time: 0.3376 data: 0.0038 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:45 time: 0.3544 data: 0.0044 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:34 time: 0.3363 data: 0.0041 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:24 time: 0.3444 data: 0.0047 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:14 time: 0.3178 data: 0.0040 max mem: 3953 +eval (train): [20] [160/509] eta: 0:02:06 time: 0.3613 data: 0.0044 max mem: 3953 +eval (train): [20] [180/509] eta: 0:01:59 time: 0.3576 data: 0.0047 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:51 time: 0.3432 data: 0.0044 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:43 time: 0.3409 data: 0.0045 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:36 time: 0.3613 data: 0.0049 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:29 time: 0.3392 data: 0.0048 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:22 time: 0.3665 data: 0.0044 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:14 time: 0.3524 data: 0.0043 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:07 time: 0.3586 data: 0.0045 max mem: 3953 +eval (train): [20] [340/509] eta: 0:01:00 time: 0.3473 data: 0.0046 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:53 time: 0.3471 data: 0.0046 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:45 time: 0.3277 data: 0.0044 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:38 time: 0.3612 data: 0.0048 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3657 data: 0.0046 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3700 data: 0.0045 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3472 data: 0.0045 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3392 data: 0.0043 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3527 data: 0.0045 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3148 data: 0.0041 max mem: 3953 +eval (train): [20] Total time: 0:03:01 (0.3560 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:50 time: 3.4130 data: 3.1707 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3397 data: 0.0039 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3552 data: 0.0045 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3271 data: 0.0040 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3198 data: 0.0037 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3122 data: 0.0035 max mem: 3953 +eval (validation): [20] Total time: 0:00:31 (0.3732 s / it) +eval (test): [20] [ 0/85] eta: 0:04:22 time: 3.0888 data: 2.8328 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:31 time: 0.3576 data: 0.0038 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3343 data: 0.0040 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3496 data: 0.0040 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3231 data: 0.0041 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3108 data: 0.0039 max mem: 3953 +eval (test): [20] Total time: 0:00:31 (0.3739 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:24 time: 3.2273 data: 2.9522 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3422 data: 0.0059 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3356 data: 0.0032 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3754 data: 0.0045 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3233 data: 0.0042 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3126 data: 0.0041 max mem: 3953 +eval (testid): [20] Total time: 0:00:31 (0.3811 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.0129 | 0.05 | 47 | [43, 1.0] | train | 2.6422 | 0.2304 | 0.0021192 | 0.16953 | 0.0020271 | +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.0129 | 0.05 | 47 | [43, 1.0] | validation | 2.7155 | 0.20247 | 0.0049345 | 0.13574 | 0.0042183 | +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.0129 | 0.05 | 47 | [43, 1.0] | test | 2.6492 | 0.21929 | 0.0046621 | 0.14367 | 0.0041868 | +| flat_mae | patch | linear | nsd_cococlip | best | 19 | 0.0129 | 0.05 | 47 | [43, 1.0] | testid | 2.7934 | 0.1791 | 0.0046772 | 0.12333 | 0.0040864 | + + +done! total time: 1:12:27 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/train_log.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..d151a7308178f751b57b409b3e392ddc5e10fd17 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__patch__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1666651797294616, "train/grad": 0.029969326527789233, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.182032470703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.182010498046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.181978759765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.18197265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.18194091796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.181904296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.18183837890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.181798095703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.181722412109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.181651611328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1815869140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1814990234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.181387939453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.181246337890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.181077880859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.18087158203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.18060791015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.18031494140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.17998046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1796484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.179267578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.17876953125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.178221435546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.177542724609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1768115234375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.175806884765625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.174830322265625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.17390869140625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.172518310546875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.170892333984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1692333984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1676513671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.16553955078125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.16358154296875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.161114501953125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.158623046875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.156043701171875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.15340087890625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.150743408203125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.147196044921875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.14448486328125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.142093505859375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.138878173828125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.13604736328125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.132730712890625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.128984375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1256005859375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.121473388671875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.117535400390625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004383054360514507, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004382921056821943, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0043827121832873675, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004382489119889215, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004382285024039447, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004381961053004488, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004381612855941058, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004381209083367139, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004380657108267769, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004380106466123834, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0043795531999785454, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004378662675153464, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004377743635559455, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004376410822151229, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004375094170682132, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00437383504002355, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004372094592545181, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004370035630417987, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004367556241340935, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00436508348910138, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004361765237990767, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004358030987204984, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004353687373222784, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004348571960581467, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004342707180185244, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0043350209959317, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004327735044062138, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0043204160663299265, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004310069625498727, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004296767971245572, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004284412816632539, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004272771046962589, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004256519360933453, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004241673938231542, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004223835495067761, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0042059346218593415, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004187004944542423, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004169448046013713, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004151237920159474, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0041302231058944015, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00411534734419547, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004103196192299947, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0040888558002188805, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004077536178519949, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004065856526140123, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004054999864893034, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0040466712403576825, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004038253137841821, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004032098230673, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1819510459899902, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1818954944610596, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1817967891693115, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.181704044342041, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1816108226776123, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.181475877761841, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1813180446624756, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1811444759368896, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.180917739868164, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1806716918945312, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.180421829223633, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1800479888916016, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.179673910140991, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1791131496429443, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.178558349609375, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.178006172180176, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.177271842956543, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1763792037963867, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.175309658050537, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1742541790008545, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1728782653808594, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1713616847991943, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1695473194122314, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.167466163635254, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.165156841278076, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1621947288513184, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.159376621246338, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.156687021255493, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1529083251953125, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1482789516448975, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1440632343292236, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1402342319488525, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.135119676589966, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1306586265563965, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1255557537078857, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1207475662231445, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1158862113952637, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.111506462097168, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1069529056549072, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.101423978805542, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0970561504364014, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.093043327331543, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0874321460723877, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0821003913879395, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0753960609436035, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.067492723464966, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0601186752319336, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0506796836853027, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.042142868041992, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.03617571059431524, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.03599114064230343, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.036544850498338874, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.036729420450350686, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0369139904023625, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.036360280546327055, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.03617571059431524, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.035622000738279806, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.036729420450350686, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.03765227021040975, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.03820598006644518, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.039313399778516056, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.039313399778516056, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.041343669250646, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.04226651901070506, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.04152823920265781, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.04263565891472868, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.04688076781100037, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.05057216685123662, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.05260243632336656, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.054078995939461055, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.05555555555555555, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.058693244739756366, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06921373200442968, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07179771133259505, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08213362864525656, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08194905869324474, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0828719084533038, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08748615725359911, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08988556662975268, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09431524547803617, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.10077519379844961, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.10668143226282761, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11184939091915837, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1138796603912883, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.029824389208691238, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.029591559858094276, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.029902549151683194, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03002743035234153, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02986143234822249, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.029376924290200414, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.028490461476468, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.028285251716004545, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0282579952397046, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.028484413104534506, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.02908186719645876, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.029778123688216012, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.029459606789529896, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.030264482061890696, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0299708284524258, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.027786735801860096, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.02829954942030768, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.030535592088715216, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.03034019148733697, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.029447244145657556, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02846315025928084, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.026755413254953755, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.027577402273554066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.02704971160070006, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.02567442532177688, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.02439984452941832, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.02365860944037612, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.022625383266805715, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02171852562778782, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.019991379170061992, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.019126759792484713, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.017746718626218547, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.015191521481104184, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01482889823016411, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.014293004398381715, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.012511784205633479, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.012306945714038986, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.012467028514247384, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.014079371682047483, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.015684713487692025, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.016298617094487374, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.018539901057131325, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.025014750553680385, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03100477707581493, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03818104099267635, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.042435458868891406, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.046828858694232596, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04963730123342707, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05122718187807198, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.117535400390625, "validation/loss_best": 3.042142868041992, "validation/acc_best": 0.1138796603912883, "validation/f1_best": 0.05122718187807198} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.1313791918754577, "train/grad": 0.028733252603560685, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.18079345703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1806591796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.180413818359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1802294921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.18001220703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.17976806640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.179476318359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.179144287109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1786669921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.178134765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.17763427734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.176824951171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.176024169921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.174886474609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.173797607421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.172650146484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.171231689453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.169432373046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.167540283203125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.165474853515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.163089599609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1604248046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.15748046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.154168701171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1507470703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.146541748046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.142813720703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.139578857421875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.135225830078125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.13037353515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12625244140625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1227392578125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.118275146484375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1144384765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.109891357421875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.105438232421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.100667724609375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.095743408203125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0900244140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.082388916015625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0758599853515625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0696923828125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0609527587890626, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0531256103515627, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0433978271484374, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0324688720703126, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0226068115234375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0103973388671874, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.99998291015625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0043406258011236785, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004339679996483028, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004338075335836038, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004336464195512235, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00433490275987424, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00433272136724554, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004330235120141879, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00432754143839702, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004323772852076218, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004319799190852791, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00431587724830024, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004309823085786774, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00430389626766555, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004295130360405892, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004286487080389634, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004278041938086972, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.004267084794119001, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004253689491888508, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004238193223718554, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004223238556878641, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0042041421483736486, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004184103495208547, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0041610761021729555, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004136069878004491, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00411000786582008, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004079212438082323, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0040524401597213, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004029311477206647, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004000098541146144, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003969575251685456, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003946326320292428, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003928494183346629, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003909036564873531, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003895829588873312, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003884189872769639, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003876232458278537, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0038704687112476677, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0038672515284270048, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003865321739576757, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003865120500558987, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003865653600078076, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0038669174967799337, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003869222162757069, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00387174507137388, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0038755487580783665, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0038804124388843774, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003885477150324732, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0038927255873568356, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003900080929743126, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1807775497436523, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1805484294891357, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.180166244506836, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1797826290130615, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1794042587280273, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.178877830505371, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1782729625701904, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1776061058044434, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1767241954803467, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.17578125, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.174849271774292, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1734437942504883, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1720635890960693, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1700401306152344, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1680848598480225, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1661739349365234, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1637279987335205, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.160808801651001, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1574862003326416, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1543660163879395, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1504786014556885, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.14646053314209, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.14201283454895, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.137319326400757, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1325666904449463, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1271440982818604, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1225879192352295, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1187069416046143, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1138460636138916, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1085708141326904, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.104214906692505, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1003823280334473, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0952835083007812, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.090609312057495, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0847413539886475, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0785138607025146, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0712382793426514, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.06369686126709, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0547986030578613, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.04266095161438, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.032470703125, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0229880809783936, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0099167823791504, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.998152494430542, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.9841935634613037, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.969214916229248, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.956559419631958, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.941781520843506, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.929609537124634, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.037467700258397935, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.03857511997046881, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.03968253968253968, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.039128829826504244, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.03875968992248062, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.04060538944259875, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.04245108896271687, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.043004798818752306, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.04614248800295312, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.049464747139165745, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05204872646733112, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.053156146179401995, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.056109265411590996, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.059616094499815434, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.067921742340347, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07179771133259505, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07567368032484312, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07954964931709117, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08748615725359911, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09653008490217793, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.10446659283868587, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.11406423034330011, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.12015503875968993, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.12624584717607973, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1273532668881506, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.13104466592838687, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.132890365448505, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.13528977482465854, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.13528977482465854, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.13732004429678848, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.13805832410483573, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1391657438169066, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.13990402362495385, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.028649795243638726, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02925932043622634, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03033240682304525, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.029504348680622322, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02865694897650645, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.029358179554001256, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02968796376389075, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02887828330286434, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.030436974154381787, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03108086821697392, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03008166322639905, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.02857134291288432, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.028691237838728696, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.028101924155595547, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02672779290930601, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02488313605493014, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.024855605939849913, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.023011557540591834, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.020370185880735064, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01886164292340616, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.018466456115773706, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01782949414832367, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.016095239057802094, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.014854510053120246, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013223308003914353, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013183407326448777, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.011997135039345115, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.011905870009041197, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.011760003023320795, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.012955789009257439, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.013968464924077391, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.014488709082054588, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.016434628596079907, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.019125056523939588, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.02817357682594024, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03561053632811073, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04304706560964652, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.05077921848152143, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.05575702673987337, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06062024299051568, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06117773233619824, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06336100684124148, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.06523546964569099, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.06626082031986628, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06664004284150148, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06786496715851593, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0685862285665589, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0697404782435797, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.07165225722446622, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.99998291015625, "validation/loss_best": 2.929609537124634, "validation/acc_best": 0.13990402362495385, "validation/f1_best": 0.07165225722446622} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.101729382276535, "train/grad": 0.028183418130502104, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.17958251953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.179229736328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17863037109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.17816162109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.177701416015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1769970703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.17622802734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.17522705078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.17402099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1728173828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.17162841796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.169754638671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.167962646484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.165440673828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.16308837890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.16085693359375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.157908935546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.154674072265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1511083984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.147857666015625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1439892578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.140111083984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.136064453125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.131993408203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.128079833984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.123743896484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.119923095703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.116788330078125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.112642822265625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.107562255859375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.102767333984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.098388671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.091971435546875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.08586669921875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.078111572265625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.069906005859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0604736328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0507940673828124, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0396282958984373, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.025107421875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.013143310546875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0024127197265624, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.988013916015625, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9754608154296873, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9609521484375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9456167602539063, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9327511596679687, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.917816162109375, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9057852172851564, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004311962109059095, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0043093845061957835, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0043052036711014804, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0043011936533730475, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004297116883099079, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004291428066790104, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004285014907363802, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004277864980977029, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004268623243551701, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004258751820307225, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004249005598248914, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004234608071856201, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004220547099830583, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00420021136989817, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.004180970543529838, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.004162743458291516, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00413993520080112, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004113700892776251, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0040854413202032445, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004060293830698356, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004030933199683204, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004002756697591394, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003974322584690526, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003947673463262618, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003924195287982002, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0039020707015879454, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0038874040672089907, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038774059840943663, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038678859476931394, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003861104587558657, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0038574249914381654, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0038552779227029534, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038533670944161714, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003851988021051511, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0038505553686991336, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003849378484301269, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003847965627210215, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003846836828161031, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0038457760692108423, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003844592657405883, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003844068153994158, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003843624024884775, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003844190927920863, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0038453355222009124, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003847980524878949, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0038525859266519548, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0038580959546379743, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003866477777482942, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003875525291077793, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1788930892944336, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.178396224975586, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1775596141815186, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1767418384552, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1759254932403564, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.174809455871582, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1735479831695557, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.172163486480713, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.170349359512329, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.168447732925415, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.166597366333008, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1638598442077637, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1612462997436523, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1575446128845215, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.154083490371704, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.150852680206299, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1468653678894043, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1423513889312744, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.137529134750366, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1332664489746094, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.128347873687744, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1236257553100586, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1187899112701416, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.114021062850952, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.109440565109253, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.104304790496826, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.099858522415161, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0958073139190674, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.090219497680664, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0832810401916504, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0767507553100586, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0705270767211914, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.061645746231079, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0533454418182373, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0429861545562744, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.032217502593994, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.020200729370117, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0083019733428955, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9949331283569336, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9777352809906006, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.964094400405884, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.952044725418091, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.936305284500122, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.922900676727295, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.907731294631958, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8922674655914307, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.879535675048828, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.865330457687378, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.8545870780944824, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04097452934662237, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.04245108896271687, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04263565891472868, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.04595791805094131, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.048726467331118496, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05204872646733112, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.053156146179401995, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.05537098560354374, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05906238464377999, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06183093392395718, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.067921742340347, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07715023994093761, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.08102620893318568, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.08619416758951642, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09542266519010704, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10280546327057954, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1079734219269103, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.11775562938353636, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.11886304909560723, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.12366186784791436, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.12495385751199704, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.12919896640826872, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.13325950535252862, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1376891842008121, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.13935031376891843, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1421188630490956, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.14470284237726097, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1493170911775563, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.15319306016980436, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.15614617940199335, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.15503875968992248, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.15633074935400518, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.15891472868217055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1583610188261351, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.029444990439483062, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.029745463194947752, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.028749207468248408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.030192222483566376, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.030590431053864952, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.030238161104630828, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.027832518727534866, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.028087829614689072, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.027926953685633502, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.027407506329000866, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.025433634723586836, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.025064522470850514, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02352942920045847, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.020919324308289782, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.019898637150273627, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01930746271283425, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.019691939784140484, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.017157097256091516, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.016915178605760466, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01536790106205182, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.014561449650180336, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.014469316479333388, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014597134251103953, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.014732867169208774, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.015346523816547114, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.015799855017561353, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.017850210840211937, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.019965813341250402, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02252007834611454, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.028838728982608235, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03413792500057368, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03880565470359743, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04584966131073468, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.04811649764720338, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05245838532525874, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.055682233620420594, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.06025758577653259, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.06435043473169715, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06817344282803726, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06995824592906726, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.07304292491170628, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.07608293248012139, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.08045821953367141, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.08475567518578826, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.08840902043221222, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.08967601271278347, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.09149656741311078, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.09410818721945254, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.09537535535323087, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.917816162109375, "validation/loss_best": 2.865330457687378, "validation/acc_best": 0.15891472868217055, "validation/f1_best": 0.09410818721945254} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.0734116756916046, "train/grad": 0.028108417689800262, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.177127685546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.176544189453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17561767578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.174581298828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.173602294921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1724072265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.170791015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.169263916015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.167193603515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.16508544921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.162933349609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.160084228515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.157208251953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.15347900390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.149830322265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.146715087890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.142930908203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.138851318359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1345654296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.13097900390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.126942138671875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1231201171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.119178466796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11531494140625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.111175537109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.106331787109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.101873779296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.097532958984375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.09128662109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.083336181640625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.07571044921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0685693359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0582708740234374, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.048719482421875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0370123291015627, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.024833984375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.011407470703125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9981964111328123, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.983431396484375, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.964752197265625, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.9501171875, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.937391357421875, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.920920104980469, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9071295166015627, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8921075439453126, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8771710205078125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.8657334899902343, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.854044189453125, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.845773010253906, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004322685721563175, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004317978697363287, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004310365116689354, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0043027525802608576, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0042952459363732485, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004285179807338863, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004273617037106305, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004260836424073204, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004244533834280446, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004227595268748701, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004211179340491072, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004187281783670187, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.004165131154004484, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004134727094788104, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00410779228201136, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0040835726412478835, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0040553117950912565, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.004024994423380121, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003995222558733076, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003971432709367946, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003947392327245325, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003928203519899398, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003912416533567011, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0039005334279499948, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038925398094579577, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003886684727622196, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0038834937138017265, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038817439670674504, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003880062948446721, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0038785686355549843, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003877391588175669, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003876540057826787, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038752852426841857, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0038743620947934688, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003873392187524587, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0038724054244812576, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0038716645142994823, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0038711647561285646, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003870783197926357, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00387127336114645, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0038719633384607733, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003873054636642337, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0038753392186481506, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003878261619247496, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003883102663094178, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00389021365554072, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0038989167369436473, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003913250009063631, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0039301555207930505, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.176363706588745, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.175510883331299, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1741011142730713, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.172736644744873, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1713907718658447, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.169551372528076, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.167515993118286, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1653010845184326, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1624717712402344, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.159555435180664, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1567976474761963, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1528196334838867, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1491494178771973, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1441519260406494, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1397109031677246, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.135725498199463, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1310489177703857, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1260406970977783, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1210217475891113, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1167750358581543, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1120505332946777, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.107597827911377, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1029000282287598, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0980560779571533, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.093010187149048, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0867490768432617, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0808773040771484, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0752792358398438, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0672991275787354, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.057326316833496, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.047974109649658, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.039246082305908, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.027097225189209, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0159103870391846, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.002342462539673, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.9885644912719727, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.9735026359558105, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9589436054229736, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.9430131912231445, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9231677055358887, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.907953977584839, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.894800901412964, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8779284954071045, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8640382289886475, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8490889072418213, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.835045099258423, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8248167037963867, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.815316677093506, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.810140609741211, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.047619047619047616, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05094130675526024, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05260243632336656, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05518641565153193, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05647840531561462, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.067921742340347, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.073827980804725, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07954964931709117, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.09246954595791805, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0976375046142488, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.10612772240679218, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.11498708010335917, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.12033960871170174, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.12384643779992617, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.12827611664820968, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.13086009597637505, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.13270579549649317, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.135843484680694, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1389811738648948, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.14101144333702473, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1450719822812846, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.14820967146548542, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1509782207456626, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.15227021040974528, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.15633074935400518, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1583610188261351, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.16002214839424142, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.16223698781838317, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.16482096714654854, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1688815060908084, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.17035806570690293, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03126069141887181, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03121078803573075, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.028485984160151023, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.028425447714138793, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.027429173071849295, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.027518984897302434, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.026195165262698775, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.024469687916417293, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.023969252823047054, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02127844090746615, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.020069005137320628, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.018080840219330468, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.018490256543712908, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01705556940086884, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.016103367494884384, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.015554469976849209, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014268367045409675, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013834281914883761, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013297780383236089, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013492866437430327, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.014098734526780976, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01436860404438881, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.015256429541317437, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.017367793167018957, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.018780371953607437, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.022069371120149128, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03018841890181714, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.033865652541535125, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.04108939920915899, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.04712337582938312, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.05128886277753352, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.053301800343660645, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.055788697211619914, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05724561656473789, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.05819800772939285, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.059954176672924374, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.0623813000133174, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.06345994949811097, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.06627301315705163, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.06867887611406041, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.07159943791162283, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.07391556901773148, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.07969011993133414, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.08374766419286238, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.08790953695441066, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.09319106533919404, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.09836082329784564, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.10432062170589744, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.10829442030291352, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.845773010253906, "validation/loss_best": 2.810140609741211, "validation/acc_best": 0.17035806570690293, "validation/f1_best": 0.10829442030291352} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.0448711359500886, "train/grad": 0.027715711584314705, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.17470458984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.17377197265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17209228515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.170572509765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.169061279296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.16701171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.164761962890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.16239501953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.15936279296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.156361083984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.153426513671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.149364013671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1456591796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1408984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.136666259765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.133011474609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.128795166015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124361572265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.120032958984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1163525390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11197509765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.10776123046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.103021240234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.097818603515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0922021484375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.08496826171875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.078126220703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.071480712890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.062080078125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0503179931640627, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0393914794921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0293109130859377, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.015386962890625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0026202392578125, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9874053955078126, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9722119140625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9558636474609377, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.940203857421875, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.9234384155273436, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.903048400878906, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.8878543090820314, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.8750210571289063, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.8593438720703124, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.8469744873046876, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.83419677734375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.8225953674316404, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.81447509765625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.807395477294922, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.803536224365234, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004287523132516072, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00428002405562438, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004267816354986281, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004255800683749839, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004244198112282902, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004228243757970631, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004210880366154015, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00419196413946338, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004168100227834657, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.004144087417516857, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004121837296988815, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0040909632307011634, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00406360459048301, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.004028486756142229, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003998688613064587, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003973793732002378, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00394691176712513, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003921757808420807, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003900723895058036, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038862772088032217, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038741061300970616, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038659022690262644, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003859949806937948, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003856219021836296, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038534472323954105, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00385104289278388, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003849019529297948, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003847457976080477, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038449845381546767, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003842173549346626, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003839629293652251, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003837447118712589, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038346161448862405, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003832114337710664, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0038299780304078012, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0038278343703132124, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0038257886364590375, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0038246412831358613, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0038239645946305245, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0038243920227978376, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0038259442197158934, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0038281684054527433, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0038326503382995723, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0038385570584796368, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00384750418481417, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0038606293930206446, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0038753568509127946, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0038971195870544763, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003919281427515671, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1731839179992676, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.171910285949707, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1698360443115234, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.167829990386963, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.165886640548706, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1632702350616455, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1604208946228027, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1573731899261475, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1535747051239014, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.149775743484497, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1462690830230713, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1413705348968506, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1370158195495605, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.13136625289917, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.126560926437378, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1224427223205566, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1177704334259033, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.112924337387085, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1080687046051025, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1039140224456787, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0990517139434814, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0941145420074463, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0885283946990967, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.082369327545166, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0755996704101562, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.067136287689209, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.059095621109009, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.051508665084839, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0408201217651367, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0277163982391357, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.015777826309204, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.004817485809326, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9899697303771973, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9767043590545654, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9610700607299805, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.945758819580078, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.9296059608459473, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.914628505706787, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.898836851119995, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8801193237304688, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.86660099029541, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.8557093143463135, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8428518772125244, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8330304622650146, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8232529163360596, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.814749002456665, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.808422565460205, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.8015191555023193, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7968175411224365, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05426356589147287, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.056109265411590996, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08084163898117387, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09191583610188261, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09837578442229605, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.10575858250276855, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.11277224067921743, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.11812476928755998, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.12366186784791436, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1301218161683278, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1301218161683278, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.13658176448874124, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.14008859357696568, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.14285714285714285, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.14525655223329642, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.15005537098560354, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.15282392026578073, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.15651531930601698, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1581764488741233, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.16020671834625322, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1642672572905131, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.16906607604282023, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1699889258028793, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17128091546696197, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1758951642672573, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1760797342192691, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1760797342192691, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.17829457364341086, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02885708831664209, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.028225010391255453, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02724915427146303, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.026039168862376134, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.025010101877067065, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.024048264359465592, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.023259169396621565, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.02043558388747117, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.019182090414769006, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.019212998779773175, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.019062807492283642, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.017089332672831716, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015886503830307142, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014671875039700034, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014655984969060168, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014499268544094548, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013495210926900446, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014797182718465189, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014850674484564806, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.015480670748053038, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01720363233851731, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.01894644854872702, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.02094833429914922, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0282345620452229, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.033701577219067864, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.04053321662495018, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0475603796561884, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.05185195564586656, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.056252024136543816, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.061449779898810675, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.06227858156773634, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.06403376646891969, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.06713189903364163, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.06978063687275204, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.07118489954944363, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.07280318026425868, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.07592044955774689, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0774989638551817, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.08134821268404578, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.0832152966369923, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.08617500056926024, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.09099047565958802, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.09654599233301393, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.09978388910348594, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.10417973234400664, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.11159257015020935, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.11362387851784221, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.11553674971464466, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.11782573908383527, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.803536224365234, "validation/loss_best": 2.7968175411224365, "validation/acc_best": 0.17829457364341086, "validation/f1_best": 0.11782573908383527} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 3.0247373640537263, "train/grad": 0.027500603329390288, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.171431884765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.170067138671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.16778564453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.165640869140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.163529052734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.160791015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1577734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.154561767578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.150745849609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.146839599609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.143394775390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.138658447265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1344921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.129227294921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125042724609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.121177978515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1169775390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.112578125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10803466796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.10406982421875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0991015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0939208984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.087869873046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.081187744140625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.07371337890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0643603515625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0555474853515623, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0471240234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0353662109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0211578369140626, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.00808349609375, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9962646484375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9801580810546877, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9660235595703126, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9492779541015626, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9329452514648438, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9159884643554688, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.9002239990234373, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.8838385009765624, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.8646395874023436, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.8507931518554686, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.8396401977539063, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.8264776611328126, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.8165155029296876, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8067137145996095, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.798578338623047, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.793553924560547, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7903187561035154, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.7899295043945314, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004255680502392351, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004245022831019014, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004227709255646914, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004210913513088599, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004194877478294074, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004173269995953887, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004150004453258589, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004125693888636306, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004096173826837912, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0040677881496958435, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.004042739931028336, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.004009122079005465, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.003980396076804027, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003945965943858027, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003920335030416027, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0039012652018573135, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003883095413912088, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038685873162467035, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003857967497315258, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038519934157375244, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003847413961775601, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003844293395522982, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003842215873301029, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038404153019655496, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038385313260369002, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003836373992962763, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003834548903396353, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003832732926821336, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038301732705440373, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0038272218278143557, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003824627649737522, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0038223344075959177, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038196121901273726, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003817214583978057, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0038147874816786497, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0038127246289514005, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003811420213896781, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003811069790972397, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0038116708805318923, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003814600231125951, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0038184995611663906, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0038231643312610685, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003831101349787787, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0038400079833809287, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0038527876592706887, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0038706639292649925, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003888399364659563, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003912676078034565, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003937134428415447, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1698224544525146, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.168134927749634, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1654136180877686, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.162813425064087, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1603293418884277, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1570281982421875, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.153494358062744, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1497983932495117, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.145313262939453, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1409311294555664, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.136996269226074, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1316797733306885, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1271305084228516, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1214442253112793, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1167354583740234, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.112769365310669, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.108240842819214, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1034367084503174, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.098419427871704, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.093864679336548, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.088233709335327, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0822925567626953, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.075403928756714, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.067657470703125, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.059232234954834, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0486741065979004, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0388317108154297, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.0296437740325928, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.016881227493286, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0015721321105957, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.987910747528076, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.975619316101074, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.959218978881836, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9448647499084473, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9282965660095215, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.9122560024261475, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8956704139709473, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8803951740264893, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8645167350769043, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8461480140686035, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.833204746246338, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.822991371154785, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8114733695983887, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8032312393188477, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.795783519744873, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.790225028991699, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.787283420562744, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7862722873687744, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.788440227508545, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0799187892211148, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08379475821336287, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0917312661498708, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1005906238464378, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.10889627168696936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.11701734957548911, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.12532299741602068, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.13233665559246954, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.13252122554448137, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.13805832410483573, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.14082687338501293, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.14174972314507198, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.14451827242524917, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.14802510151347362, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.150609080841639, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.15319306016980436, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.15651531930601698, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1583610188261351, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.16205241786637137, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.16500553709856036, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.17183462532299743, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17497231450719822, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1758951642672573, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.17811000369139904, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1806939830195644, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17700258397932817, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18032484311554078, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.17995570321151716, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1805094130675526, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1773717238833518, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.027086029296715605, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.025887270358819478, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.024670774653437675, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02405700110046233, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.02291245229223711, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020717492098877997, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.018454453501176495, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01952126046492036, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01818123906001268, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015892409388108247, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.015235393667608945, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01444793723661489, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013999775869294427, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013081393584416035, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013262640377913568, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014203809357661816, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014433841083991062, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.014672214964541732, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01718825867095444, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.018601930896372448, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.020927338359824844, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.029233854095212036, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.035426124041099176, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04263978626504686, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0484529082008307, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.05486597434767846, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.05985677638356091, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06147285090434749, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0646729178759701, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.06662482433566685, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.06722239857568649, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.06895489980877485, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.07083359790641748, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.07197206135648304, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.07401569109403335, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.07774371218623632, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.08087597144616102, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0841972830627311, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.08930730841801393, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.09624728951610718, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1019648200354654, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.10517164789509859, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.10916703964452586, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.11374894615889743, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11410755268458894, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1186227416208999, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.11779331047077064, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.11780702577771436, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.11684399784379262, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.8165155029296876, "validation/loss_best": 2.8032312393188477, "validation/acc_best": 0.1806939830195644, "validation/f1_best": 0.11374894615889743} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 3.0050498104095458, "train/grad": 0.027291177920997143, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.16868408203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1668701171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.164117431640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.161553955078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.158963623046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1556005859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.15210205078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.14837890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.14419677734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.139951171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.136142578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.131357421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12703369140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121995849609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11767333984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1139794921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.109708251953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.105081787109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.10001220703125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.095186767578125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0890625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0826025390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.075054931640625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.066484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0570001220703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0453814697265624, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0344439697265626, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.024285888671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.010159912109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9932568359375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.978065185546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9644805908203127, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9462542724609375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9304437255859375, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.912107238769531, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8945147705078127, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.876500549316406, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.8601651000976562, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.843492126464844, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.824432067871094, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.811212463378906, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.800809020996094, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7891294860839846, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7808087158203123, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7733074951171877, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.7678790283203125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.765499038696289, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7650694274902343, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.766951141357422, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004215432036435231, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00420206003007479, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004180506332777441, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004160079265711829, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00414077251800336, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004115515345474705, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0040889535448513925, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.004062189913820475, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.004030827536480501, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00400153381866403, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003976110643707216, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00394358214456588, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.003918492191005498, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0038914949994068595, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038734251062851398, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003861193178454414, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0038507957314141096, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038433856167830525, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038386357412673535, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003836003871401772, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003833845657063648, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038318660703953356, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003829895684029907, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003827731389319524, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038254750706255437, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038229394133668395, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003820365011924878, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038181770616210996, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038152265944518147, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0038116541085764766, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0038085827277973294, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003805934801930562, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038026958494447173, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0038000699039548638, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003797218628460541, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003794809292303398, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037928584520705044, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0037916611309628933, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003791476975893602, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0037933510483708233, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003796931792749092, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003801509566837922, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0038104024901986122, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0038208415056578816, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0038363059936091302, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0038570183946285397, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003877591248601675, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0039035711972974243, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003926559543469921, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1667120456695557, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1646595001220703, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.16139554977417, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1583094596862793, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.155400037765503, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1515839099884033, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1475744247436523, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1434686183929443, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.138564348220825, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1339025497436523, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.129819631576538, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124445676803589, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1199567317962646, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1143887042999268, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1098127365112305, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1058919429779053, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.101318359375, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0962374210357666, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0906646251678467, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0854716300964355, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0789172649383545, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.071856737136841, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.063723564147949, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0546741485595703, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.044835329055786, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0327200889587402, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0215556621551514, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.011235237121582, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9971606731414795, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9804792404174805, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9658095836639404, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9527769088745117, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9355926513671875, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9208145141601562, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.903916597366333, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8879106044769287, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.871701240539551, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.85709285736084, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8422012329101562, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8248860836029053, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.812566041946411, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.802589178085327, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7911953926086426, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7831404209136963, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7757318019866943, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.769965887069702, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7667934894561768, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.767582654953003, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.774263858795166, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07032115171650055, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07788851974898486, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.08213362864525656, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.08656330749354005, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0946843853820598, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.10169804355850867, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.11000369139904023, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.11480251015134736, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.12236987818383167, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.12809154669619785, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.13049095607235142, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.13122923588039867, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1363971945367294, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.13935031376891843, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1419342930970838, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.14544112218530822, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1491325212255445, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1511627906976744, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.15079365079365079, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.15559246954595793, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.16002214839424142, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1626061277224068, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1672203765227021, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1716500553709856, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17626430417128092, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1790328534514581, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18124769287559986, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.18124769287559986, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18290882244370615, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18586194167589518, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.18420081210778885, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.18549280177187155, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.18512366186784793, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0255952996971112, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.024158035540014833, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.023115434489089013, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02092143130455512, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.019652226262869662, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.018925680386579904, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.018732621076370512, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.016952154614835024, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.015425735663984955, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01497770058875209, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013831543262695284, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0137575596425755, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014058506743994057, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013750805583919425, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014659202091789615, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014981745884260808, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.016491620977774808, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.017625203580844937, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01982064691688308, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02395153041610457, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.030700147524436307, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.036571484862536405, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.04370562403752922, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.04744768753800177, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.05305089477984413, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.05753071817243524, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.060839286096932434, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06237268246869693, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.06519031498820173, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.06699121890561999, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.06842767065158419, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.07098041831445617, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.07409040663236711, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.07695374259448928, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.07693917522053945, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.08186107241299215, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.08647890354423254, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.08933860741929683, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.09330818403746888, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.09862428634717539, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.10352990906861832, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.10677255848780719, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.10966832944909038, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.11026853848978115, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11286022042568822, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.11711955215179459, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.11705423708797169, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.12008641709071356, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.11945741402140946, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.7678790283203125, "validation/loss_best": 2.769965887069702, "validation/acc_best": 0.18586194167589518, "validation/f1_best": 0.11711955215179459} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.991574590206146, "train/grad": 0.027586139431223275, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.165721435546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.163681640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1603759765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.157369384765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.15447998046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1506884765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.146722412109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.142752685546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.138118896484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13372802734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129837646484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124923095703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.120809326171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1156298828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11128662109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1075244140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10309326171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.097957763671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0922216796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.08665283203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.07958251953125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.072108154296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.06329345703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.053531494140625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0428509521484375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0297357177734376, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.01766357421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.00642578125, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9910626220703125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9728619384765627, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9567730712890623, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.942384033203125, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9235760498046877, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.907186279296875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8886468505859373, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8711212158203123, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.8532525634765626, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.837297058105469, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.8212037658691407, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.8030540466308596, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.790338592529297, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.780592956542969, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7695684814453125, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7616326904296873, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7546005249023438, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.749494934082031, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.747117462158203, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7471192932128905, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.7495063018798827, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004251538114622235, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004235692438669503, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0042106583202257755, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004187276443699375, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004165352075360716, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004137351528042927, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00410883104428649, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00408060330315493, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0040481223701499406, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00401827652938664, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003993539256043732, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00396452107001096, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.003943648997228592, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003922530548879877, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003909411348868162, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0039011695329099895, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003894584629451856, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038900352164637298, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038868312165141108, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003884732665028423, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038824729062616825, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038803792372345924, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038782221998553724, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038757304195314647, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038733671768568455, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038701670919544994, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003867566389963031, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038652284897398204, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003861956603359431, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0038585750432685016, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0038557558308821172, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0038532488222699614, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0038508216093759984, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003848679753718898, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003846753592370078, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0038455647171940655, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0038451065158005802, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0038453107816167178, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0038467067247256637, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003849914890015498, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003854043416213244, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00385883686481975, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003867054030997679, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0038760699378326533, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003889374325517565, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0039076678908895705, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003927041975548491, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003955525732599199, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00398436511750333, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1638505458831787, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1614973545074463, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.15777850151062, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1543030738830566, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1510684490203857, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.146867275238037, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.14253306388855, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.138153553009033, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1330373287200928, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1282732486724854, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1241705417633057, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.118861198425293, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1144471168518066, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1089928150177, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1044135093688965, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.100383996963501, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0955440998077393, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0899810791015625, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0837514400482178, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0778355598449707, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0703582763671875, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0623562335968018, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.053178071975708, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.042965888977051, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.032010555267334, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0186288356781006, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.006422758102417, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.995222806930542, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.980069398880005, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9623095989227295, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.946807384490967, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.933112859725952, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.915316581726074, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9000983238220215, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8829128742218018, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8668437004089355, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.850696086883545, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8364412784576416, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8221757411956787, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.8063344955444336, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.795551061630249, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7871124744415283, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7776401042938232, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7707936763763428, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.764740467071533, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7603299617767334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7583868503570557, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.758723020553589, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7627151012420654, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07807308970099668, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.08250276854928018, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.08896271686969362, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.09708379475821337, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.10612772240679218, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.11332595053525286, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1197858988556663, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.12495385751199704, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.12956810631229235, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.13325950535252862, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.13750461424880028, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.14156515319306018, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.14248800295311922, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.14599483204134367, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1491325212255445, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.14876338132152087, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1511627906976744, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.15411590992986343, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.15799187892211147, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.16020671834625322, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.16500553709856036, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.16906607604282023, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1714654854189738, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.17368032484311555, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17663344407530454, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.17681801402731634, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.17977113325950536, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.18180140273163528, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18253968253968253, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18383167220376523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.18604651162790697, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.18549280177187155, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.18752307124400147, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02458030327915309, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022541742136201345, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.021271012873574732, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01910898794062685, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.019138068109607314, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.018088066150489326, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.016972592498962043, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0152943711277345, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013934095721750228, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013975870476519705, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013241945607417469, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012425771260263578, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013551842970084202, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014526099383602692, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014689254466426672, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01593111505697246, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.017622354091918965, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01977512689881643, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.026085426891888447, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.032137309962938725, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03879671707780293, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0448201617285336, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.04805578981202291, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.05261187497210215, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.056666196324143235, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06078846859148532, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.06364671431955791, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06623882012314108, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.06728594675888698, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0701242530160509, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.07326026215232052, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.07396006072981333, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.07662903379349241, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.07916775195512074, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.082814064059289, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.08516402663210375, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.08944820452380077, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0951584502336138, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.09921959361602366, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1022256941366161, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.10454883532267929, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.10453096381220421, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.10680538029798776, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.10840520102898839, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.10866734130708589, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.11085256878599718, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.11326455999587874, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.11373313513648092, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.11572032645544966, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.7495063018798827, "validation/loss_best": 2.7627151012420654, "validation/acc_best": 0.18752307124400147, "validation/f1_best": 0.11572032645544966} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.975940021276474, "train/grad": 0.027009636983275413, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1631787109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.160684814453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.156890869140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.153460693359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.15020263671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.146025390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.141729736328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.137467041015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13248291015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1278564453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12391845703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.118800048828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11453369140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.109267578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.10474365234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.10063232421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.095521240234375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.08970458984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.083057861328125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.076636962890625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.068450927734375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.059749755859375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.049736328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.03849365234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0265887451171873, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.011845703125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9984423828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.9861883544921874, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9694268798828123, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9499200439453124, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9326861572265623, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9176007080078126, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.897910461425781, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.881114196777344, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.862027587890625, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8443228149414064, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.8264645385742186, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.810537109375, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7946241760253905, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.776721649169922, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7645663452148437, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.755124053955078, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7445916748046875, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.737154846191406, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7305288696289063, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.725679931640625, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.723558349609375, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.723818817138672, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.7263933563232423, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004175830205203965, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004157609940739349, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004129423334961757, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004103064093505963, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004079317194409669, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0040493158949539065, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004019448461476714, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003990249235648662, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00395724753732793, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003928095385199413, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0039055948867462577, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038805880502332003, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.003863473791861907, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0038472849305253476, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038379748177248983, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003832457527751103, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003828077535144985, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038247650593984874, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038223094609566035, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003820071049267426, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038176998123526573, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038151731190737338, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003812334821559489, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038093125936575233, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003806135532213375, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038023259944748133, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003799012469826266, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0037957828375510872, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037917466158978643, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003786640439648181, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003782400154741481, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0037788706773426383, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00377451517037116, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0037709675717633217, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0037675235886126756, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003764562665019184, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003762088300427422, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0037605309032369403, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003759710150770843, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003760376119753346, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037625565961934625, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003765845774905756, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0037721691257320343, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0037792309897486122, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003788531390018761, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003799753290368244, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003811660927021876, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0038307902798987927, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0038527983566746114, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1613171100616455, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1587064266204834, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.154625654220581, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1508545875549316, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1473701000213623, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1429147720336914, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1383605003356934, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1338484287261963, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1286401748657227, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1238882541656494, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1198315620422363, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1146364212036133, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1103010177612305, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.104887008666992, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.100231885910034, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.096062183380127, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0908877849578857, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0848848819732666, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.078029155731201, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0715460777282715, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0633034706115723, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.054574966430664, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.044529676437378, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.033513069152832, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0217528343200684, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0074822902679443, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9945645332336426, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.982837200164795, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9670121669769287, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9486701488494873, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9327993392944336, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9188883304595947, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9009199142456055, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.885687828063965, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8686866760253906, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8529839515686035, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8375563621520996, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8241539001464844, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8111042976379395, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7969720363616943, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.787423610687256, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.780024290084839, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7717201709747314, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7657742500305176, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7606186866760254, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7570624351501465, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.755526542663574, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.755540370941162, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7580716609954834, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.08748615725359911, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.09413067552602436, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.10391288298265043, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.11074197120708748, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.11590992986341823, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.12181616832779624, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1271686969361388, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.13215208564045774, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.13399778516057587, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.13510520487264674, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.1391657438169066, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.14248800295311922, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.14654854189737912, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15134736064968624, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.15633074935400518, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.15873015873015872, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.16297526762643041, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.16758951642672573, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.16943521594684385, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.17109634551495018, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.17128091546696197, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.17423403469915097, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.17829457364341086, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17977113325950536, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1777408637873754, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.17958656330749354, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.17995570321151716, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18032484311554078, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18106312292358803, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1821705426356589, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.18438538205980065, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1819859726836471, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02231507417482086, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.020339164351494368, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.019795919707053515, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01896465290514318, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018035037602770296, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01702801227213128, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015013111384457283, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014091394635299787, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013706481552154303, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012540403901648308, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.012454496789520887, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012802363431203001, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013825170771357044, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015258073802126848, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.016138908430773317, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.01725929698393835, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.019347793852469205, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.02591767543627557, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.031112238305059114, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03911596730285202, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04495048374269695, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.04836599859773789, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.053213443761001546, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.057811652043083576, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06224753741726036, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06474429849305438, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.06591305916882928, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0690845704297806, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07184721250685164, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0754505747273979, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.07986926425393755, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.08555104683112057, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.08887423312746572, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.09272627161863306, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.09782352171885672, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10022681974775476, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.10344883000509873, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.10493257246043093, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.10759410009376004, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11171128631002385, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1125121278677708, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11162480417419844, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1118640019297565, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.11275645572124815, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11434988566314754, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1160690035853895, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.11809793187239143, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.12213745786277169, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.12211207691443288, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.723818817138672, "validation/loss_best": 2.755540370941162, "validation/acc_best": 0.18438538205980065, "validation/f1_best": 0.12213745786277169} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.9678819620609285, "train/grad": 0.027076325584203004, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1607958984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.15833251953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.154356689453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.150643310546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14724853515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.142965087890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.138626708984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.134293212890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129486083984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1250537109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.121195068359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116326904296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11226806640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.106986083984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.102215576171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.098021240234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.092557373046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.086181640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.078831787109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.071756591796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.062835693359375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.053309326171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.042340087890625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.030321044921875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0173406982421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0016558837890623, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9874835205078125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.974549560546875, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.956898193359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9364385986328125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.91861328125, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9031475830078124, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8829833984375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.86595703125, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8467901611328124, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.829036865234375, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.8113327026367188, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.795778961181641, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7803048706054687, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7632958984375, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.751706848144531, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.742867431640625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7330091857910155, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.726111068725586, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7199751281738282, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.7157862091064455, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.714416961669922, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7153446960449217, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.718446273803711, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0041762207204010336, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00415644078864716, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004125815080478787, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004098237077705562, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004073406865354627, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00404268400860019, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004012267366051674, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0039826893364079295, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003950583302648738, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00392397245625034, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003904209471074864, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.003883129528257996, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0038692309719044714, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0038569900998845696, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003850301287602633, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038462886889465155, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003842954532010481, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003840128694428131, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038375998882111163, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038353707839269193, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038328544690739365, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038301738328300416, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038268938427791, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038234827457927167, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003819931468460709, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038156082364730537, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003811841860879213, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003808452715165913, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038037825911305845, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003798424022970721, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0037938752141781153, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0037901613337453454, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003785376736195758, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003781439911108464, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0037776628555729985, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0037746132258325814, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003772195738274604, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003771068110363558, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003771205354714766, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0037736247235443444, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037772021477576346, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037814781768247484, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0037890691205393523, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003797425979282707, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003808345349971205, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003822170435450971, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0038356562773697077, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0038544552540406584, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003872264977544546, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.159069776535034, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1562535762786865, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1518747806549072, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.147859573364258, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1441895961761475, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.139538526535034, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.134861469268799, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1302638053894043, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.125049114227295, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120319366455078, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1163294315338135, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1111903190612793, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1068999767303467, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.101393699645996, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.096583127975464, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0921552181243896, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.086622476577759, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.08009934425354, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.072669744491577, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0655994415283203, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0566933155059814, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.047266960144043, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0365123748779297, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0247483253479004, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.012317180633545, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9973738193511963, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.983954429626465, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9718494415283203, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9556920528411865, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.937157392501831, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9213273525238037, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.9075753688812256, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.890099287033081, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.875568389892578, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8594729900360107, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.845020294189453, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8308770656585693, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8188633918762207, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.807249069213867, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7947261333465576, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.786391258239746, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7799782752990723, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.772651433944702, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7671937942504883, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7620158195495605, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.758316993713379, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7573001384735107, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7598071098327637, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.766414165496826, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.073827980804725, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07973421926910298, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0858250276854928, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.09339239571797711, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.10280546327057954, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.11018826135105204, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1153562200073828, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.12089331856773718, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.12606127722406793, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13086009597637505, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1345514950166113, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1363971945367294, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1376891842008121, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.14138058324104835, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1450719822812846, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.14710225175341454, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15208564045773348, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.15430047988187523, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1568844592100406, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.16020671834625322, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.16371354743447766, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.165374677002584, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.16961978589885568, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.17275747508305647, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.17681801402731634, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.17792543373938724, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.17977113325950536, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18106312292358803, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18272425249169436, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1834625322997416, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18327796234772978, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18567737172388335, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.18604651162790697, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.18678479143595422, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1878922111480251, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02101662934344466, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.020024852900752357, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.018564341080888228, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0183156459748095, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01684185116199677, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015316945261702014, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01456523413001607, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013963004668465008, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013068611817188961, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013088148903748736, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01260084739905558, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013767099659391616, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014855295468860203, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01574923706519984, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01739978753741311, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.018797209932577472, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.024236562297415994, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.030414769172667666, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.038163001090218834, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.043757935424410845, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04848914360736276, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.052304529973120774, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.05682543535729978, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06020814221978019, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06313957075017017, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06520422953250152, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.06606890350356932, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06887665024796888, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07180074152345603, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.07351776886700213, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.07790661192965379, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.08029926215095798, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.08207335395879185, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.08486966364983982, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.08870018456832529, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.09082221202883695, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.0958018584021203, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.09960543796446457, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.10472102050059567, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.10774880454170654, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.11032139409577406, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1120265862999012, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.11603562455847717, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.11963408721342061, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12014066768860403, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1229074594125361, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.12445817784458273, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.12623906869164683, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.12710394514838605, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.718446273803711, "validation/loss_best": 2.766414165496826, "validation/acc_best": 0.1878922111480251, "validation/f1_best": 0.12710394514838605} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.9616285490989687, "train/grad": 0.027100140769034622, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15854736328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.155865478515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.15162841796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.147713623046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14424560546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.139693603515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.135352783203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.131109619140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126165771484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.121798095703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11802978515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.113199462890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.10916259765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.103759765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.09898193359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.09439697265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.088675537109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.081849365234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.073970947265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.06654296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.057049560546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.047108154296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.03552001953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0228643798828125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0094793701171874, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.993212890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9785638427734376, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.9652099609375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.947169189453125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.926417236328125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9084906005859374, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.89278564453125, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8726547241210936, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.855566101074219, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8364627075195314, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8189407348632813, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.801463623046875, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7861309814453126, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7710392761230467, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.754327697753906, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7431684875488282, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.734504852294922, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.725243148803711, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7188715362548828, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7135499572753905, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.7101470947265627, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.709116134643555, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.710395584106445, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.713658561706543, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004159241170855239, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004138836896745488, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004107771054841578, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004080209721578285, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004055666198255494, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004025923667941242, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003996545320842415, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003968884245259687, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003940440755104646, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003918033208465204, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003902077543316409, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038858895539306106, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00387601193622686, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0038677463796921076, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038635966333094986, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038610436220187696, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003858721958240494, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038563984516076745, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038540942722465844, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003851584199583158, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038488134858198466, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038457961892709135, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003842384150484577, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038386165082920343, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038346242997795345, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038301227742340415, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003825939524685964, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038221164944116028, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038171338802203535, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003811330884927884, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0038063963351305575, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0038023108104243875, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003797022388316691, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0037926501221954823, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0037879268836695703, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003784104575170204, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037807004037313163, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003778417621506378, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003777016729582101, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0037770501198247076, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037786453554872423, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037811611243523655, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003786681401543319, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0037934046005830167, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0038034700776916, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003817189767723903, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0038318721111863852, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0038537708728108556, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0038774721033405513, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.157184362411499, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.154202699661255, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.149597644805908, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.145420551300049, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1416189670562744, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.136847734451294, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1320858001708984, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1274664402008057, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122265338897705, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1175854206085205, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1136302947998047, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.108513355255127, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.104198694229126, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0985658168792725, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.093522787094116, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.088839054107666, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.08292818069458, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.075918197631836, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0679335594177246, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.060353994369507, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.050809383392334, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0407276153564453, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0293068885803223, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.016841173171997, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0037286281585693, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.987980604171753, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.973926067352295, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.961242914199829, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.944399118423462, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9251599311828613, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.908834457397461, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8948302268981934, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8770525455474854, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8623299598693848, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.846230983734131, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8318185806274414, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.817875385284424, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8059885501861572, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.794584035873413, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.782182216644287, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.773926019668579, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7676050662994385, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.760427474975586, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7549800872802734, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.749432325363159, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.744234800338745, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7405006885528564, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.738011598587036, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7381339073181152, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08453303802141011, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09136212624584718, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1005906238464378, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.10981912144702842, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.11406423034330011, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.11941675895164268, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.12679955703211518, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1315983757844223, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13362864525655224, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.13510520487264674, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.13953488372093023, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1450719822812846, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.14728682170542637, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15134736064968624, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1526393503137689, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15411590992986343, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.15614617940199335, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16002214839424142, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1640826873385013, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.16685123661867848, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.16980435585086748, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.17404946474713917, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1773717238833518, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.17940199335548174, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18143226282761166, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1847545219638243, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18420081210778885, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18512366186784793, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1864156515319306, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1864156515319306, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.18752307124400147, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.18826135105204872, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1878922111480251, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.18549280177187155, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.020696267741743202, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.019534793199627132, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.018721591216038207, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01781261511581319, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.017061260728344692, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015275662793156161, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0146118598821264, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01350434190523543, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01322030390763843, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01271696115545389, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013803974490815168, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015337653600306651, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015035348654981871, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.017600795122184005, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.019049543464319717, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.021920457129959308, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.028486805608037704, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03552334017478318, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.042852130219281165, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.046744814192806565, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05097848656777334, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05673840983586703, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06155195469434291, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06435931596531996, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06516193996265769, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06840096078626075, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07141821382614276, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07376034209759359, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07850729922048814, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0794655926651579, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08116685626956738, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.08297375564604988, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.08867206606529014, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.09287207437255156, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.09560243345739972, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.09947943300351146, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.10420854931539066, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.10717229018071539, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.108929966150634, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11075508836764765, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.11441145919530127, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11556667895679934, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.11691127369023357, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1199456629249676, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1207419867364304, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.12316366617536377, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.12376292817644356, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1261633989038176, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.12659428601905523, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.709116134643555, "validation/loss_best": 2.7405006885528564, "validation/acc_best": 0.18826135105204872, "validation/f1_best": 0.12376292817644356} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.9568767130374907, "train/grad": 0.027163036121055483, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15709228515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1543310546875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14994140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.146080322265625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.142525634765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.138072509765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.133787841796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.129547119140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12488525390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12067626953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11705810546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.112442626953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.108248291015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1029541015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.09798583984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.093267822265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0872509765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.079993896484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.071695556640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.06384765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.053865966796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0433001708984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.03126708984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0181390380859376, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0043121337890626, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9875921630859374, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9725714111328125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.95892578125, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.94068359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.91966064453125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9016403198242187, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.885850830078125, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8656802368164063, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.848631591796875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8296548461914064, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8121041870117187, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7946881103515624, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7794010925292967, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.764205017089844, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.747357940673828, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.735943603515625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.7270069885253907, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7171554565429688, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7102687835693358, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7041594696044924, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.700131530761719, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6986777496337893, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6996817779541016, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.702719879150391, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004171802829951048, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004150225151097402, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004117762397509068, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004088991768658162, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004063638744410128, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004032704769633711, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.004002634175121784, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003974872558610514, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00394741103402339, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003925865739583969, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003910872283158824, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.003895902324002236, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.003886839672923088, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003879308708710596, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003875256945611909, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003872726318659261, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003870291234925389, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038676890125498176, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003865033835172653, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003862689209636301, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003859698224114254, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038566685304977, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003853111028438434, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003849402110790834, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003845403081504628, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003840779036981985, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0038366394746117295, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038329636352136733, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0038281783019192515, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0038227355561684818, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00381805315380916, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0038142291468102486, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003809525896795094, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003805437599075958, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003801394475158304, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0037978052953258155, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037946955091319977, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0037922460318077357, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003790255578933284, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003789185609202832, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003789456579834223, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037903944123536346, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0037932306074071674, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003797326056519523, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003804266188526526, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0038151321792975067, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0038282694679219274, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003849270158680156, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0038716072042006998, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.155613422393799, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1524977684020996, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.147731304168701, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1434152126312256, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.139514446258545, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.134669065475464, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.129868507385254, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1252381801605225, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120072603225708, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1154282093048096, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1114957332611084, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.106400966644287, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1020348072052, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0962605476379395, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0910379886627197, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0861141681671143, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0799107551574707, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.072535514831543, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0641403198242188, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.056215286254883, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0462541580200195, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.035773754119873, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.023959159851074, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0111355781555176, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9977235794067383, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9817240238189697, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.967524528503418, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9547860622406006, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9379630088806152, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.918801784515381, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9025614261627197, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.88864803314209, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.870976686477661, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.856358766555786, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.840299129486084, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8258183002471924, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8116989135742188, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.799542188644409, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7877066135406494, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7748329639434814, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.766028642654419, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.759286880493164, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7517969608306885, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7465641498565674, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7421352863311768, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7393383979797363, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.738416910171509, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7386293411254883, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.74017333984375, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08250276854928018, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08748615725359911, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09542266519010704, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.10465116279069768, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11295681063122924, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.11720191952750092, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12181616832779624, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.12901439645625692, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13473606496862311, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13473606496862311, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1363971945367294, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1421188630490956, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.14433370247323735, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.14820967146548542, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15171650055370986, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1526393503137689, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15227021040974528, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1554078995939461, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16094499815430047, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.16611295681063123, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.16943521594684385, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1744186046511628, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1786637135474345, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18180140273163528, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1834625322997416, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18660022148394242, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1878922111480251, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18881506090808417, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18807678110003692, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1906607604282023, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19176818014027316, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19306016980435586, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19102990033222592, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1908453303802141, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.19010705057216684, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.020336107064549077, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01941020568210961, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.018428764285258165, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01706935579037527, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.016010884759731905, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015304237041241056, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.014444270485269672, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013721043720311084, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013296162177396069, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013211793136943671, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014429284645060603, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014920803949677578, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01602252380934809, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0181073660387376, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0199568614046212, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.024644917558556512, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.030922687990359427, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03819250786892034, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04492764184115685, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.04820280002829427, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.051626996073080154, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.056691052975276934, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.061684239719211637, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06320054226174691, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06370323386666274, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06728589046598717, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0688635393339237, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0719172595151401, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.075400763216059, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.07708439507769589, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.07846252109006706, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0833049839278986, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.08723107386877003, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.09244155350491719, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.09694979437591371, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10043716964598264, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.10606719953675636, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1092113581563353, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1123951526797501, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11582691911959621, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.11761349738130349, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1189489997488159, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.11862956908416282, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12135927162638242, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12309725707155321, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1251524296692623, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1235286439543305, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1242566373238271, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.12488277006745524, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.700131530761719, "validation/loss_best": 2.7393383979797363, "validation/acc_best": 0.19306016980435586, "validation/f1_best": 0.1251524296692623} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.949023184776306, "train/grad": 0.026864953758195042, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1563671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.15341064453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1489599609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.144912109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.141285400390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.136861572265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.132430419921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12821044921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12342529296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11923828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.115606689453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.110677490234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.106571044921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.10098388671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.09566162109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.09066162109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.084171142578125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.07640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.06754638671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.059085693359375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0484539794921877, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0371343994140627, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0243487548828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0105181884765626, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9957843017578125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9780999755859376, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9622723388671877, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.9479974365234374, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.92891357421875, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9070928955078124, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.888411560058594, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8721878051757814, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8515335083007813, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8341220092773436, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.815082550048828, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7975025939941407, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7803135681152344, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.765292053222656, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.750463104248047, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7341545104980467, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7230625915527344, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.7144955444335936, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.70505859375, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.698359069824219, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6923695373535157, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6879991912841796, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.685976104736328, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6855645751953126, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.687101821899414, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004134739215951413, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004111983042676002, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004077935270033777, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004048019042238593, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004021769330138341, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003989975025178865, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003959091916913167, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003931806520558894, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003904714998789132, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003884217219892889, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003870004714699462, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.003855875466251746, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0038477142713963988, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003840828271349892, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00383708355599083, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038344539108220487, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003831734681734815, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003829167342046276, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003826372668845579, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038235657522454856, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038204212777782232, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038168749515898525, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038130132120568305, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003808824198786169, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038045466237235813, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0037993613793514667, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003794744483893737, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003790473815752193, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037850041477940975, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0037788600206840784, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003773720486788079, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0037691774452105163, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003763635486830026, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003759288495639339, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0037546238431241364, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003751057835761458, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037479282333515583, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0037460117344744505, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003744651768356562, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0037449198274407537, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037462552345823496, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003748512796591967, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003752697615418583, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0037572168244514614, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0037638561672065406, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0037725321447942407, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0037813423399347813, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003794157578377053, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003806991084711626, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1543266773223877, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.151113748550415, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.146202802658081, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.141794443130493, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.137838125228882, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.132941246032715, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.128117084503174, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123502254486084, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1183741092681885, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1137712001800537, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.109877586364746, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1047909259796143, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1003901958465576, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0944948196411133, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.089124917984009, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0840351581573486, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0775978565216064, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0699515342712402, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.061281442642212, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0530991554260254, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.042832374572754, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.032097101211548, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.019988536834717, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0069291591644287, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.993307590484619, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9770851135253906, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.962716579437256, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9499127864837646, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9329309463500977, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.91377854347229, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.897585153579712, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8837177753448486, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8662052154541016, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.851771116256714, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8360321521759033, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.821791648864746, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.80800724029541, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7962446212768555, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7847580909729004, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7723991870880127, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7641260623931885, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.757735013961792, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.750471591949463, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7453465461730957, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7408154010772705, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.737844228744507, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.737053394317627, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7384419441223145, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7413852214813232, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07050572166851236, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07585825027685493, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08822443706164636, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09745293466223699, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1064968623108158, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1138796603912883, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.11886304909560723, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1242155777039498, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1286452565522333, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1349206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13732004429678848, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.13861203396087118, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.14248800295311922, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.14747139165743817, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.14987080103359174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1511627906976744, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.15448504983388706, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15799187892211147, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16002214839424142, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1642672572905131, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.165374677002584, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.16980435585086748, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.17220376522702105, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.17571059431524547, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1790328534514581, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18124769287559986, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1821705426356589, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.18530823181985973, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18586194167589518, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18899963086009597, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1906607604282023, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19139904023624954, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1906607604282023, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19047619047619047, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19029162052417867, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.18992248062015504, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019597828134769325, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.019262046799819434, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.018490275169139144, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01694970129400081, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015242005599437941, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014748181138716327, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013559869222651887, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013290917484664285, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012382848804828081, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013595256120528997, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014443189348012066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014715436036417805, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01681471816593606, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.017722949480241522, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.020364344319917304, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02547041200602285, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03301643650360059, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.039051229871521174, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04526259895046095, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.04886278876829411, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05246150323867047, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05667745435528287, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06168149953736091, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06387049552666908, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06506823710290391, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0671403671530562, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07042318294392219, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07287392897649225, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07453576822241657, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.07793062152838208, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08148079419144368, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.08593411682072344, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09137423275860444, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0937431723972116, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.09930999562329218, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1029954029601805, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.10762822527402371, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11151954408709008, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.114970371872136, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11640802069586438, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12050332139797558, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12197963581878214, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1250705798506695, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12677106033385957, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12835471318152214, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.12884647666567378, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.12904093585983742, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.12859875733786516, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.12728153689821112, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 2.6923695373535157, "validation/loss_best": 2.7408154010772705, "validation/acc_best": 0.19139904023624954, "validation/f1_best": 0.12835471318152214} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.9419073712825776, "train/grad": 0.02687412497587502, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.154617919921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.151500244140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1468115234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.142667236328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13888671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.134285888671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129703369140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.125401611328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120545654296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.116187744140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1125048828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.107547607421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.10319091796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0973681640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.09179443359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.086502685546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.07992431640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.071824951171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.062686767578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.053953857421875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0431109619140626, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0315924072265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.01845947265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.004354248046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9893280029296876, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.971385498046875, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9552777099609373, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.940855712890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9215582275390624, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8994317626953126, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.880484924316406, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8640240478515624, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8431585693359374, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8256015014648437, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8060890197753907, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.788192138671875, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.770615692138672, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7551531982421875, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.739865264892578, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.722899932861328, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7113645935058592, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.702445068359375, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6923937225341796, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6852479553222657, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.678568115234375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.673473358154297, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.670736770629883, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6695668792724607, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6703226470947268, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004128773616394028, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004105636228341609, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004071306856349111, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004041440614964813, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004015376861207187, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003983755214139819, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003953686956083402, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003927727810805664, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003902195863192901, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0038834009505808354, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003870576380286366, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038583419471979142, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0038512814592104403, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0038456025475170465, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038423015747684986, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038400653924327345, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00383782348013483, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038351355318445714, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038322486251126976, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038296399987302722, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003826461220160127, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038232840702403337, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003819500358076766, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038155016838572918, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038113473961129784, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038066193787381053, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0038020834745839237, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0037981268367730083, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003793010066729039, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003787162252701819, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003782123712589964, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0037777575792279096, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0037723187310621143, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003767852229066193, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003762883439194411, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003758713733404875, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00375488564488478, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003751987681025639, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0037495555635541676, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003747621963266283, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037474703730549664, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037478462746366858, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003749249706743285, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003751733604585752, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00375605923240073, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0037625768210273235, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003770045305136591, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003780943953897804, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0037926878640428185, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.15334153175354, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1500556468963623, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1450538635253906, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1405856609344482, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.136587619781494, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.131650686264038, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.126826286315918, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1222307682037354, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.117128849029541, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.112563133239746, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1086835861206055, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1035985946655273, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0991439819335938, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0931577682495117, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0876457691192627, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.082427501678467, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.075828790664673, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.067945957183838, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0590438842773438, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0506114959716797, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.04012131690979, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0291435718536377, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.01678729057312, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.003434419631958, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9895732402801514, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9730541706085205, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9584619998931885, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9454052448272705, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9281978607177734, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9087212085723877, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.892322063446045, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8782920837402344, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.860645294189453, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.846109390258789, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8302431106567383, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8160548210144043, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.8023626804351807, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.790574550628662, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7791554927825928, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7668094635009766, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.758579969406128, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7522451877593994, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.745389699935913, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.740445852279663, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7360332012176514, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.732377529144287, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7303059101104736, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.729095697402954, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.728976249694824, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.067921742340347, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0843484680693983, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08988556662975268, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09819121447028424, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1079734219269103, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11480251015134736, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.11886304909560723, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12458471760797342, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.12938353636028055, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1343669250645995, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1376891842008121, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1378737541528239, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.14248800295311922, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.14728682170542637, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15171650055370986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15466961978589885, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.15614617940199335, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15909929863418235, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16279069767441862, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1657438169066076, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.16906607604282023, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17220376522702105, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1777408637873754, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18143226282761166, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18272425249169436, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18327796234772978, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18826135105204872, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19047619047619047, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19176818014027316, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1937984496124031, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19601328903654486, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19601328903654486, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19619785898855666, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19712070874861573, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1982281284606866, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.19509043927648578, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019162144789455385, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.018973564467210536, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016730271528905532, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015896436634701968, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014884520846335703, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01405007051239416, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013407261898335639, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012873834292525732, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012208904449354496, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013268193097307292, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01427791717842373, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.014807339624630043, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01666413421503769, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.018085694767036902, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02156886133021768, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.028078089901023003, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03351839964687986, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.04032993089026649, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04638559390438745, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.04915823326039556, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0531352425963858, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05682639599431747, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.060888129193847264, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06366546087739579, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06415660533771932, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06711575849074038, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07088529155513777, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07440710267563462, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0770922086465792, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08073849232400913, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08475489607842329, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0890186347784299, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09270207566562937, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.09566278622028486, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.10036903425724301, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1066836184526949, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11039115273663291, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11248296408336624, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.11328084534294929, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.11819780603721891, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1204999692713471, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12351783358463823, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12560261761535665, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1284312019081146, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12840614299348088, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.12879797339829072, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13199925176277238, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.13303297122541716, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13104032447839745, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.6695668792724607, "validation/loss_best": 2.729095697402954, "validation/acc_best": 0.1982281284606866, "validation/f1_best": 0.13303297122541716} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.946299811601639, "train/grad": 0.026828049113973976, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1546435546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.151575927734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1469873046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14296630859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1392919921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13485595703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13041748046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12629638671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121754150390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.117607421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1140087890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.109320068359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.105042724609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.099361572265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.09380615234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.08861572265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.081888427734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.073843994140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.06460693359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.055838623046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.044951171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.033460693359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0204144287109376, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0063055419921874, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9915093994140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.973787841796875, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9578619384765625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.943585205078125, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9247369384765625, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.90311767578125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8847918701171875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8688253784179687, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.848577575683594, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8317413330078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8129733276367186, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.795948181152344, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7789447021484377, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.764158935546875, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.749525299072266, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.73322509765625, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7221279907226563, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.713468017578125, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.703571624755859, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6964460754394532, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.689589538574219, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6842350006103515, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6810265350341798, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6788072967529297, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6782493591308594, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004119344366481528, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004095983114093542, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004061385482782498, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004031775539042428, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0040057794947642835, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003974226877326146, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003945107632316649, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003920003721723333, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0038959861849434674, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0038784828525967895, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0038666287472005935, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038555541704408825, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0038492195459548383, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00384417601628229, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038411971123423426, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003838767110137269, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003836415457772091, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038337207946460695, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003830650890013203, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003827778652776033, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003824456579750404, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003820945945335552, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003816945926519111, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038125437300186604, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003808051533997059, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038028420007321984, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003798197294818237, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0037941730301827192, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037887525756377725, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003782803607173264, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0037776485166978093, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003773246416822076, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003767650156514719, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0037631446600425987, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003758356301113963, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0037538797652814536, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037498922541271897, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0037464671034831555, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0037434626859612764, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003740870667388663, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037395730754360558, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037390030617825685, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003739460407523438, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0037406804703641683, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003743257386377081, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003747338637476787, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00375198669382371, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0037586840067524462, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0037656356871593744, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1526169776916504, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1492762565612793, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1442060470581055, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1396989822387695, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1356656551361084, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1307199001312256, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.125894784927368, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1213014125823975, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1162290573120117, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1116654872894287, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1077959537506104, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1026811599731445, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0981807708740234, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0921037197113037, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.086484670639038, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.081151008605957, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.074369430541992, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0663230419158936, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0572030544281006, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0486111640930176, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0378682613372803, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0266664028167725, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.014072895050049, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0004990100860596, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9863791465759277, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.969644069671631, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9548370838165283, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9416708946228027, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9243485927581787, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9048211574554443, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8883657455444336, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8744122982025146, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.856919050216675, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.842583417892456, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.827008008956909, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.813091278076172, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.799640655517578, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7882683277130127, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7772207260131836, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7653005123138428, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.757441759109497, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7514538764953613, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7447874546051025, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7400856018066406, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.735755205154419, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.732231616973877, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7301061153411865, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.728430986404419, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7279510498046875, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0695828719084533, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.073827980804725, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07622739018087855, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08508674787744555, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09228497600590624, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10077519379844961, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1094499815430048, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11627906976744186, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.12144702842377261, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12606127722406793, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1315983757844223, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13473606496862311, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13695090439276486, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.13990402362495385, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1461794019933555, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1509782207456626, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15319306016980436, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15596160944998155, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.15725359911406422, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.16057585825027684, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1638981173864895, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16832779623477298, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1714654854189738, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17644887412329271, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1788482834994463, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18290882244370615, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1836471022517534, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18604651162790697, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18733850129198967, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.18844592100406055, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19102990033222592, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1921373200442968, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19601328903654486, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19601328903654486, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19619785898855666, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19601328903654486, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19619785898855666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1954595791805094, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019279434698408683, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01888398544427186, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01684053872826836, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015588042618650171, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0152798600666198, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014249420151199699, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013149787180842013, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012672034664733609, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012775531103524357, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013867749284102943, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014321675469297886, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015396141723646997, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017068499395351478, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.018853940723837382, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02236184926882151, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02927414459041965, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.034239249268172865, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0416788641873976, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04679749570773312, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.05008831028555805, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05376960231595466, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05839349701791016, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06173842556621371, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06426247402306912, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06550448327708151, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06969353653930806, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07393688210003418, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07614365757370205, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.08027072452444566, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08255987496541715, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08753356961202348, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09086130966976357, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0951911391020452, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.09889964555432153, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.10443755265526707, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10830871603652252, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11361975419591135, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11526903559246045, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.11752607929421814, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12082380648504588, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12257584772076564, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12479592299575577, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12614269031950812, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12911761069310326, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12907646154526126, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1295607151821027, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13018579391804685, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.13094078477794546, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13039189717862837, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.6842350006103515, "validation/loss_best": 2.732231616973877, "validation/acc_best": 0.19619785898855666, "validation/f1_best": 0.1295607151821027} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.938387460708618, "train/grad": 0.026858068527653812, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15320556640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.149932861328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1450244140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1406494140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.136790771484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.132041015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12744140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122974853515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1180419921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.113680419921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1098583984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1047900390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.10031982421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.094326171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.088590087890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0832275390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.076199951171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.067864990234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.05843994140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.04953857421875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0382611083984377, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.026424560546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0130609130859374, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.998665771484375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.983531494140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.96540283203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9493524169921876, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.934859619140625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9157305908203126, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.893875732421875, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8751654052734374, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8592108154296874, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.838581848144531, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8215237426757813, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8026727294921874, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7854013061523437, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.768250274658203, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7532142639160155, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.738328399658203, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7216864013671875, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.710190887451172, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.7012164306640627, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6910049438476564, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6834283447265626, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6761619567871096, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6701724243164064, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6664146423339843, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6636446380615233, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.662615432739258, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0041264218906871975, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004102765290299431, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004068026369204745, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00403803291846998, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004011911550769583, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003980229254812002, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003951325501548126, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003926758321467787, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0039032186137046665, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0038861740939319135, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0038748593535274265, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038642905047163367, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.003858261466957629, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003853107200702652, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003850187420612201, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038479389145504683, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0038453046302311124, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003842489501694217, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038393102027475833, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038364664791151882, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003832778767682612, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038289768469985577, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003824576229089871, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038200889190193265, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038154829444829374, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038099167705513536, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0038047728105448184, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038002388167660685, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037942617549560965, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0037876728642731905, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0037819214537739756, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0037771652347873895, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0037712296028621496, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0037661474256310613, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003760902100475505, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003756178569747135, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003751607135636732, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003747802416328341, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00374442421249114, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0037409305130131545, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00373908898094669, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037380493921227755, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003737580452580005, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003737772598396987, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003739177822135389, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.003741995565360412, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0037453861557878556, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00375105511629954, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0037575159524567427, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1521177291870117, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1487417221069336, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1436257362365723, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1390795707702637, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.135025978088379, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1300714015960693, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.125253438949585, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1206753253936768, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1156117916107178, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1110548973083496, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1071937084198, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1020615100860596, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0975353717803955, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0913820266723633, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.085688829421997, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0802736282348633, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0734012126922607, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.065232038497925, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0559780597686768, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.047255754470825, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0363850593566895, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.02502179145813, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0122945308685303, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9986133575439453, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9843590259552, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9675257205963135, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9526615142822266, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.939432144165039, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9220759868621826, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9025752544403076, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8861610889434814, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.872243642807007, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8547637462615967, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.840428352355957, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8249008655548096, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.810908317565918, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7974116802215576, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7858645915985107, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.774714708328247, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.762451171875, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.754167079925537, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7476553916931152, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7403712272644043, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7348334789276123, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7293848991394043, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.724839925765991, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7218143939971924, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7194159030914307, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.718533992767334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.073827980804725, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08102620893318568, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08619416758951642, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09376153562200074, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10169804355850867, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.11018826135105204, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11738648947951273, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.12200073827980805, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12679955703211518, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.13252122554448137, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13547434477667036, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13805832410483573, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.14119601328903655, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.14747139165743817, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.15134736064968624, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15430047988187523, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15466961978589885, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.15633074935400518, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1596530084902178, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16223698781838317, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16851236618678478, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.16980435585086748, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17423403469915097, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.17811000369139904, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18106312292358803, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18235511258767073, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18512366186784793, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18733850129198967, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19010705057216684, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19287559985234404, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19490586932447398, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1967515688445921, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19933554817275748, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19915097822074565, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19896640826873385, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19915097822074565, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.19952011812476927, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019377759212717845, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01867416134076488, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016879277628592367, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015244125260161237, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014848848157502878, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013706754898269434, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013445834163053581, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012330044151122052, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012714520625348716, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01385146285784022, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014544990947074973, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015430897284556317, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017132228934304914, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.019281192198108883, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02276372472513585, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.029898826308341148, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03519348135190792, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.042254967787663, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04750817658622652, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.050240757999644316, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05450367010240861, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.059242645528515124, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06260743468125374, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06485526515842775, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0669882795252957, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.07131900773273475, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07403318742805401, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07651600857619914, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07982403725347496, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08184253444327903, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08711460061331822, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09028779566166982, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09662787739760216, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0993787618490136, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.10362969293777526, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10780069382481254, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1120941395483961, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11439377301061443, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.11848479790674364, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12128440593865618, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12431182234634723, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1271045331821183, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12908630848368471, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13088111285911078, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13431458742301053, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.13448908174829022, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13395193959315335, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.13392256084885432, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13428715137797892, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.662615432739258, "validation/loss_best": 2.718533992767334, "validation/acc_best": 0.19952011812476927, "validation/f1_best": 0.13428715137797892} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.9376612651348113, "train/grad": 0.026900116009637712, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15283935546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14953369140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1448388671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1404931640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13673095703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13208251953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127611083984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12331298828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11863525390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.114307861328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.110693359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10572998046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.101334228515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0953955078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.089658203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.084205322265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.077200927734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.06890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.059449462890625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.050430908203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0392144775390624, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.027288818359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.013953857421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9994354248046875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.984266357421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.966202392578125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.95, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.935452880859375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9161260986328124, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8942578125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.875441589355469, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8591378784179686, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8385183715820315, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8213296508789063, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8022195434570314, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.784684295654297, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7672824096679687, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7519790649414064, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7367298889160154, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.719670715332031, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.707769012451172, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6983211517333983, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6875168609619142, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.679390411376953, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6713470458984374, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.664560470581055, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.659999008178711, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6560104370117186, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.653909378051758, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004128641952993348, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004105217406759038, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004070630783680826, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0040409950457979, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004014872793341055, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003983858615392819, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003955651267897337, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0039318451564759015, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0039092935808002945, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003893208340741694, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0038826146093197166, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038728147104848177, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.003867210306925699, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003862615152029321, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038597427133936434, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0038576336111873387, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003854870609939098, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003852211073972285, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038490947964601218, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003846197911771014, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003842519533354789, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003838784002000466, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003834577320376411, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003830058833118528, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038253640523180366, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0038196408131625503, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0038146607752423734, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003810162922600284, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003804201934253797, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003797337035648525, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0037916733184829355, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0037867390154860915, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003780564871849492, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0037752564228139816, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00376979588996619, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003764752510469407, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0037596405739896, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003755304266232997, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003751361691392958, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003746836696518585, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003743903909344226, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037418921978678555, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003739810368278995, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003738754701334983, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0037383624992799016, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00373873412492685, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003740174841368571, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0037428628688212485, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0037459619413129984, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1518101692199707, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.148409128189087, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.143265962600708, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.138704299926758, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1346471309661865, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1296794414520264, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1248536109924316, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1202757358551025, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1152379512786865, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.110687255859375, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1068217754364014, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.101682424545288, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0971262454986572, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0909411907196045, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.085195302963257, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0797371864318848, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.072781562805176, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0645458698272705, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0552005767822266, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0464041233062744, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.035463333129883, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0240318775177, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.011216640472412, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.997454881668091, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.983139753341675, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.966243267059326, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.951352834701538, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.938086748123169, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.920684337615967, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.901181936264038, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.884756326675415, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8707544803619385, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8532426357269287, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8389194011688232, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.82327938079834, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8093583583831787, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7958831787109375, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.784388303756714, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.773287057876587, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.76137638092041, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.753389596939087, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.74727725982666, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7404873371124268, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.735520362854004, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.730682134628296, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.726560354232788, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7237889766693115, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7212376594543457, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.719651937484741, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.073827980804725, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08176448874123293, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08656330749354005, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0946843853820598, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1035437430786268, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.11037283130306386, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11775562938353636, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1227390180878553, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12661498708010335, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1343669250645995, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13750461424880028, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1434108527131783, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1461794019933555, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.150609080841639, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.1526393503137689, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15374677002583978, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.15577703949796973, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1596530084902178, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16334440753045404, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16814322628276115, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17054263565891473, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17571059431524547, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.18032484311554078, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18401624215577703, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18512366186784793, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18678479143595422, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1877076411960133, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19047619047619047, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1921373200442968, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19361387966039129, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19619785898855666, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1982281284606866, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19804355850867478, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19859726836471023, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19952011812476927, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1997046880767811, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019257877082281244, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.018776456061682156, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01698250513442359, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015147327656103313, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014881331167747579, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013749513048364402, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013522598814360619, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01224186501561051, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012750040896281447, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014038402264273582, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01461068153096711, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015532592064773136, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01705638219460266, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.019509405361229793, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.023663014708806315, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.030605168752826956, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.037010795279619584, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.04251417996857432, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04793085849018358, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.050710397968462585, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05496459583684608, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.06010747914176808, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.062397166845759404, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06458657977308689, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06914477600835849, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.070729123075, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07456221018352538, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07632101176827234, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07989326436861424, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08298010022478793, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08775934991463774, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09094190517078533, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09636377739704327, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.10010733897331182, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1051267865323283, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10965416848316656, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11327642350934088, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11641033523677656, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1183562740953089, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12017605106521774, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12177064653285104, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12372383641396574, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12622560556352394, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12908357500972392, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13085296091468523, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.13065855822421155, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13140022081489292, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.13169703835878513, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13277974463961215, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.653909378051758, "validation/loss_best": 2.719651937484741, "validation/acc_best": 0.1997046880767811, "validation/f1_best": 0.13277974463961215} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.9315158128738403, "train/grad": 0.02709432021714747, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.152464599609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14929443359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.144296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.140042724609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1360888671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.131328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126666259765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122271728515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.117369384765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1130029296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.10914306640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10396240234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.09947021484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.09313720703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.087159423828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0814453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.074200439453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.065570068359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0556829833984374, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.046309814453125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0345440673828126, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0223260498046876, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.008463134765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9935101318359374, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9777301025390623, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9591070556640626, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.942484130859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.9276132202148437, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9079684448242187, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.885433349609375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8665234375, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.850153503417969, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8292730712890624, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8119187927246094, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7926104736328123, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.775044250488281, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.757621002197266, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7422421264648436, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7269140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7096302795410154, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6976589965820312, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6880416870117188, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6769384765625, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.668496322631836, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6601163482666017, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.652705307006836, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.647577667236328, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.642761993408203, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.639963607788086, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004152295074891299, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00412910740240477, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004094835976138711, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004065594627754763, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004039832993876189, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.004009121638955548, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003981532469624654, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003958151510450989, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003936387038556859, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003920846896944568, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003910615218337625, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0039013338985387238, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0038961259357165544, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003891902102623135, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038890582195017487, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003887050000485033, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0038846211216878148, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038819407892879097, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003878881015116349, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038760859065223485, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.003872495439136401, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003868818216724321, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003864604578120634, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038599992578383533, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003855450863484293, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003849851022241637, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0038448550552129747, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003840392407728359, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003834317692089826, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003827851371606812, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003822073570918292, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003817158790770918, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003810912516200915, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003805641180370003, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003799961538752541, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0037947335897479204, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003789526766631752, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003785158983664587, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0037805898918304593, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0037758492736611514, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0037726661702618004, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003770211172522977, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0037673395790625364, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003765327404253185, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0037635407550260427, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0037623776867985723, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003761743367649615, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003761609921930358, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0037621342251077296, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1516408920288086, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.14823842048645, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1430821418762207, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1385037899017334, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.134443759918213, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.129486560821533, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1246604919433594, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120084285736084, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1150295734405518, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.110508680343628, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.106623411178589, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1014857292175293, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.096930980682373, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0907204151153564, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.084937572479248, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0794436931610107, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0724825859069824, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0642037391662598, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.054807424545288, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0459911823272705, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.034987211227417, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.023545742034912, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0106546878814697, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.996907949447632, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9825363159179688, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.965611219406128, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9507248401641846, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.937450408935547, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9200456142425537, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.900503158569336, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.884093999862671, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8701517581939697, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8526623249053955, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8382906913757324, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8227291107177734, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.808800458908081, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7953672409057617, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7838006019592285, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7726895809173584, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7605135440826416, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7523694038391113, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7459981441497803, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7388482093811035, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7335710525512695, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7285656929016113, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7240779399871826, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7211596965789795, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7183635234832764, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7167232036590576, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08711701734957548, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09394610557401255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10409745293466224, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.11129568106312292, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11830933923957179, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.12181616832779624, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12679955703211518, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.13270579549649317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13473606496862311, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13824289405684753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1434108527131783, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.14599483204134367, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.15079365079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15208564045773348, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15319306016980436, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.15559246954595793, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15928386858619417, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1626061277224068, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16758951642672573, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17128091546696197, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17515688445921004, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.17958656330749354, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18272425249169436, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18420081210778885, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1847545219638243, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18881506090808417, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19176818014027316, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19306016980435586, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19416758951642674, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19582871908453303, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19638242894056848, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19859726836471023, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19878183831672203, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1982281284606866, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.1984126984126984, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01941814698664027, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01867421256212159, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016672872209856675, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015175646601305394, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01458226779534747, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013772183438514213, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013264395515119355, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01224047072947104, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012659604075415144, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014105541683132432, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01452178910778345, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015437261122709656, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017082378324900914, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01936873103238121, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02442786181608805, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.030269338548312954, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0373011266746473, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.04313594543579242, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.048461987106690106, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.050815382530733144, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05513923991994282, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.060074310283720754, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0626505614505141, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06512741355668383, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0690963537936693, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0709285385884419, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07456782919806783, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07624126903255257, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07965698619467178, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08332594378187184, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08758529067343261, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09089703756039019, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09621405974617188, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.10098435475685204, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1049941891058878, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10954726466512148, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11288454825315476, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11598295141478303, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.11709749969015924, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12145882276341387, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12479022454857008, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1271394211915705, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1283980316045883, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13099370512178649, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13137839418170508, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.13316510134594298, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13290578529826122, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.13265166132067704, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1330128063250454, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.647577667236328, "validation/loss_best": 2.7211596965789795, "validation/acc_best": 0.19878183831672203, "validation/f1_best": 0.13290578529826122} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.9340092039108274, "train/grad": 0.02670742335729301, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.152850341796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.149617919921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1447802734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14043701171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.136593017578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.131905517578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127318115234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1230029296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.118135986328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.113856201171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11013671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10505126953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.10051025390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.09433349609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.08849365234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0828173828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.07564697265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.067125244140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0573297119140626, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.048128662109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.03654541015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.024521484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.01077392578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.996060791015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.980594482421875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.962183837890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.94574951171875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.9310061645507814, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9116867065429686, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8893756103515624, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8706231689453126, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.854232177734375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8336563110351562, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8163304138183594, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.797231903076172, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7795716857910158, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7620610046386718, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.746831359863281, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7313471984863282, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7139515686035156, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.701823425292969, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.692049255371094, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.680887451171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6722062683105468, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6635862731933595, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.655863494873047, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.650465087890625, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6452286529541014, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6419388580322267, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004102988876402378, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004079322110628709, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004044314165366813, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004014337923144921, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.003988301136996597, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003957096140366048, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0039290459360927345, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0039053725020494314, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003883085527922958, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.003867240846157074, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003856758688343689, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038473055488429963, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00384194208541885, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0038375876273494215, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0038349041622132065, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003832803600234911, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0038304832798894493, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.003827750711934641, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.003824635435594246, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0038216571416705846, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038181909965351226, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003814463444286957, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038102984137367455, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038058897200971844, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038011406909208745, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0037955388298723846, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003790412397356704, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003785902466624975, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003780005960725248, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0037731367826927455, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003767141751013696, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00376212396658957, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0037554420833475887, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0037498305644840003, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0037437565706204623, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0037378607341088353, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003732557031325996, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0037272247567307205, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0037222804070916027, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003716944658663124, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003713222126243636, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037103289586957544, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0037070588732603937, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003704812165815383, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0037025662732776254, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00370085810078308, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003699859151383862, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00369925492326729, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.003699261761503294, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.151585340499878, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1481754779815674, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1430187225341797, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1384360790252686, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.134369134902954, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.129399299621582, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1245791912078857, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.12001371383667, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1149611473083496, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1104204654693604, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1065549850463867, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1013998985290527, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0968494415283203, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.090632200241089, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0848350524902344, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0793442726135254, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.072361469268799, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0640664100646973, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.054659128189087, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0458173751831055, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0348048210144043, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.023320436477661, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0104355812072754, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.996642589569092, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.982274293899536, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.965327739715576, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9503955841064453, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9371337890625, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9196975231170654, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.900127410888672, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.883751630783081, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8697400093078613, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.852234363555908, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8378419876098633, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8222713470458984, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8083317279815674, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.794786214828491, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7832443714141846, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7719995975494385, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7597460746765137, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7514984607696533, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7451202869415283, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.737752914428711, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7323849201202393, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.727058172225952, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7223641872406006, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7190589904785156, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7160120010375977, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7140133380889893, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08157991878922112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0873015873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09431524547803617, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10428202288667406, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1111111111111111, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11794019933554817, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.12200073827980805, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12698412698412698, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.13252122554448137, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13565891472868216, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13842746400885936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.14396456256921372, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.14581026208933184, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.150609080841639, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15227021040974528, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15282392026578073, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1554078995939461, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15928386858619417, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16371354743447766, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16758951642672573, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1714654854189738, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17552602436323367, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.17940199335548174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18290882244370615, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18456995201181248, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18530823181985973, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18881506090808417, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19121447028423771, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1925064599483204, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1954595791805094, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19767441860465115, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.20007382798080472, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20007382798080472, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20044296788482835, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20081210778885197, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20025839793281655, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019314355952130453, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.018505689641179334, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016828283463448345, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01516117822373394, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014595425085526359, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013573289591933836, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013167781818367226, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01225576819131023, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012737088997133878, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01401822622670567, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01460321664166077, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01566898812118098, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017011026727022902, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.019414895297087977, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.024498568976605153, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.030388463552720988, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03755619110215133, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.04342240253321572, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.048109694035124384, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.051034054057024554, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.055548271107237174, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.060133839029898606, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06324498334263055, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06537974926205513, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06955818029658908, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.07082238992052749, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0747777691275347, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07629949136055675, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07954492661990761, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0833349057833821, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08735239791877863, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09146708919529893, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09621775469877729, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1004389886276565, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.10522302538746871, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10977944666951822, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11323502126178779, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11598850914068404, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.11757073173904707, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12166522749319564, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12445439038130686, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12579331584771117, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1292221400868976, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13170166509399792, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13402877547534994, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.13402863085046238, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13351337001554966, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1343820874711027, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13406240645894305, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.6452286529541014, "validation/loss_best": 2.7160120010375977, "validation/acc_best": 0.20081210778885197, "validation/f1_best": 0.1343820874711027} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.9355909538269045, "train/grad": 0.026946014082059263, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.153690185546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.150537109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1459375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14173095703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1380859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.133663330078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129273681640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1252099609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120704345703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11656982421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.112962646484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.108116455078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.103687744140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.097498779296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.091754150390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0861572265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.078955078125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.070316162109375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.060443115234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.051214599609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0394586181640624, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0272308349609376, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0135223388671877, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.998616943359375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9829827880859376, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9644195556640627, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9479248046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.9330517578125, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.91339599609375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8910736083984374, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8720492553710937, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.855702209472656, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8347232055664064, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8172988891601562, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.798084411621094, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.780391845703125, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7627906799316406, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7473223876953123, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.731836242675781, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.714369659423828, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.70215087890625, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6923478698730468, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.680986785888672, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6721754455566407, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.663368835449219, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.655519561767578, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.64982421875, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6442279052734374, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.640602874755859, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.004138852491742, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.004115349150961265, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.004080580337904394, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.004050890075741336, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.004024763104971498, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.003993722551967949, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.003965897593880072, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.003942418888909742, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.003920288410736248, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0039044870575889947, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.003894121797056869, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0038847708608955147, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00387940380605869, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.003874830453423783, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.003871954744681716, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.003869884826708585, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.003867326172767207, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0038644540682435035, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0038612410402856768, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.003858331523369998, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0038545599253848196, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003850628293585032, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038462359574623407, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003841535138199106, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038366728858090938, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003830820986768231, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003825546356383711, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003820808231830597, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003814679078059271, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.003807459461968392, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0038014357502106576, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003796110049588606, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0037891887477599084, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003783370681339875, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003777014994993806, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003771094981348142, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003765062647871673, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003759710694430396, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0037543428130447864, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003748482760274783, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.003744205069961026, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0037408558675087987, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0037368735659401866, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0037338908575475214, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0037309147545602174, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0037282883888110517, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.003726343585876748, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003724637314444408, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0037236421497073026, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1515743732452393, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1481637954711914, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1430070400238037, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.138429641723633, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1343588829040527, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1293866634368896, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1245691776275635, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1200053691864014, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1149497032165527, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.110412836074829, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1065468788146973, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1013829708099365, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.096836805343628, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0906105041503906, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0848264694213867, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0793275833129883, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0723488330841064, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0640392303466797, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.054631233215332, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.045790910720825, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0347719192504883, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.023286819458008, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0103931427001953, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9966061115264893, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.982248544692993, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9652621746063232, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.950345754623413, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9370710849761963, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.91965389251709, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9000535011291504, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8836727142333984, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.869663953781128, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8521406650543213, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.837743043899536, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.8221867084503174, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8082141876220703, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7946507930755615, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7831244468688965, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7718558311462402, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7595467567443848, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7512967586517334, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7448456287384033, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7374448776245117, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.732117176055908, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7267823219299316, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.722032070159912, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7186942100524902, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7155017852783203, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7133398056030273, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07290513104466592, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07401255075673681, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07641196013289037, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08139534883720931, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0873015873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09394610557401255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10428202288667406, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1111111111111111, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11812476928755998, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.12218530823181986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12698412698412698, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13528977482465854, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13842746400885936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.14433370247323735, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.14599483204134367, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.150609080841639, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15208564045773348, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1524547803617571, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1554078995939461, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1596530084902178, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16371354743447766, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16795865633074936, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17109634551495018, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1760797342192691, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.17940199335548174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.18272425249169436, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.18456995201181248, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18586194167589518, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1893687707641196, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19121447028423771, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19195275009228496, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19582871908453303, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19785898855666298, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.20044296788482835, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20155038759689922, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20155038759689922, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2024732373569583, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20191952750092285, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.019299393839753706, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01850948443293261, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016717117459047127, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015162339983707362, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014586345387642934, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01357323374360161, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013166189674881283, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012247159086360272, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.012737088997133878, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.01401822622670567, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01460321664166077, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015657203120365584, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.017009176854249276, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.019348794551538796, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.024479708648157395, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.030265004730379606, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.037541461485411244, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.043420749085568096, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.048127225536133966, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.05111026927615004, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05551034107788232, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0606779443514267, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06320012999492507, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06540174380412017, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06974364249822836, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.07083081478369534, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0747518360210357, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07604728062709275, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07939766805192891, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0832778746424888, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08764980304103609, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09146262049491534, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09636315395617874, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.10017098367013512, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.10591449412322078, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10979171481184313, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11308763307684555, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11608061924399775, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.11791331947232382, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12172565950244767, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.124486454164066, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12529487680347837, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12975195351585986, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13171382708282864, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13429919247747324, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.134470587244127, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13418148442328656, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1357424119482108, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1348441306032652, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.6442279052734374, "validation/loss_best": 2.7155017852783203, "validation/acc_best": 0.2024732373569583, "validation/f1_best": 0.1357424119482108} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/config.yaml b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..13e93014ebef2e1b76736959b8cbe050f1e1cd92 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..fb70e50e3797c44db32348f49e87cf765b74af5f --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 13, "eval/id_best": 46, "eval/lr_best": 0.010799999999999999, "eval/wd_best": 0.05, "eval/train/loss": 2.5178704261779785, "eval/train/acc": 0.2596576415993116, "eval/train/acc_std": 0.002257672534609239, "eval/train/f1": 0.2029632124295865, "eval/train/f1_std": 0.0022149603122320945, "eval/validation/loss": 2.6562340259552, "eval/validation/acc": 0.2279438907345884, "eval/validation/acc_std": 0.005136612417732463, "eval/validation/f1": 0.16052493317747382, "eval/validation/f1_std": 0.004388670403550095, "eval/test/loss": 2.5494439601898193, "eval/test/acc": 0.24211502782931354, "eval/test/acc_std": 0.004949267704219595, "eval/test/f1": 0.1725306096578186, "eval/test/f1_std": 0.004842893743188471, "eval/testid/loss": 2.716172456741333, "eval/testid/acc": 0.19857335646809332, "eval/testid/acc_std": 0.004670155535636598, "eval/testid/f1": 0.14422362054770904, "eval/testid/f1_std": 0.00414261587233872} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..8e56fc9869f08e296d11957e70518ded59145399 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 13, "eval/best/id_best": 46, "eval/best/lr_best": 0.010799999999999999, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.5178704261779785, "eval/best/train/acc": 0.2596576415993116, "eval/best/train/acc_std": 0.002257672534609239, "eval/best/train/f1": 0.2029632124295865, "eval/best/train/f1_std": 0.0022149603122320945, "eval/best/validation/loss": 2.6562340259552, "eval/best/validation/acc": 0.2279438907345884, "eval/best/validation/acc_std": 0.005136612417732463, "eval/best/validation/f1": 0.16052493317747382, "eval/best/validation/f1_std": 0.004388670403550095, "eval/best/test/loss": 2.5494439601898193, "eval/best/test/acc": 0.24211502782931354, "eval/best/test/acc_std": 0.004949267704219595, "eval/best/test/f1": 0.1725306096578186, "eval/best/test/f1_std": 0.004842893743188471, "eval/best/testid/loss": 2.716172456741333, "eval/best/testid/acc": 0.19857335646809332, "eval/best/testid/acc_std": 0.004670155535636598, "eval/best/testid/f1": 0.14422362054770904, "eval/best/testid/f1_std": 0.00414261587233872} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..0c222f9f6dea92173eea14ef77c918fc991a584c --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 42, "eval/last/lr_best": 0.005699999999999999, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.5318148136138916, "eval/last/train/acc": 0.2582746857617013, "eval/last/train/acc_std": 0.0023477989423760707, "eval/last/train/f1": 0.1993047035636926, "eval/last/train/f1_std": 0.0022620852799214285, "eval/last/validation/loss": 2.648336410522461, "eval/last/validation/acc": 0.22443706164636398, "eval/last/validation/acc_std": 0.005114792652912888, "eval/last/validation/f1": 0.1598170258403817, "eval/last/validation/f1_std": 0.00439607170301734, "eval/last/test/loss": 2.5524418354034424, "eval/last/test/acc": 0.24230055658627087, "eval/last/test/acc_std": 0.005000401276747439, "eval/last/test/f1": 0.1682596369628707, "eval/last/test/f1_std": 0.004705707525518391, "eval/last/testid/loss": 2.7144618034362793, "eval/last/testid/acc": 0.19818777713514554, "eval/last/testid/acc_std": 0.004792177683957179, "eval/last/testid/f1": 0.1452834300869232, "eval/last/testid/f1_std": 0.00428279526778641} diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..77b20bb7058d8cf9f2fd7a70a21eeb5b8dbb9549 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",train,2.5178704261779785,0.2596576415993116,0.002257672534609239,0.2029632124295865,0.0022149603122320945 +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",validation,2.6562340259552,0.2279438907345884,0.005136612417732463,0.16052493317747382,0.004388670403550095 +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",test,2.5494439601898193,0.24211502782931354,0.004949267704219595,0.1725306096578186,0.004842893743188471 +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",testid,2.716172456741333,0.19857335646809332,0.004670155535636598,0.14422362054770904,0.00414261587233872 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..77b20bb7058d8cf9f2fd7a70a21eeb5b8dbb9549 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",train,2.5178704261779785,0.2596576415993116,0.002257672534609239,0.2029632124295865,0.0022149603122320945 +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",validation,2.6562340259552,0.2279438907345884,0.005136612417732463,0.16052493317747382,0.004388670403550095 +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",test,2.5494439601898193,0.24211502782931354,0.004949267704219595,0.1725306096578186,0.004842893743188471 +flat_mae,reg,linear,nsd_cococlip,best,13,0.010799999999999999,0.05,46,"[36, 1.0]",testid,2.716172456741333,0.19857335646809332,0.004670155535636598,0.14422362054770904,0.00414261587233872 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..b35aa05e648e59bf42206d42b4caeb6a34c10c73 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",train,2.5318148136138916,0.2582746857617013,0.0023477989423760707,0.1993047035636926,0.0022620852799214285 +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",validation,2.648336410522461,0.22443706164636398,0.005114792652912888,0.1598170258403817,0.00439607170301734 +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",test,2.5524418354034424,0.24230055658627087,0.005000401276747439,0.1682596369628707,0.004705707525518391 +flat_mae,reg,linear,nsd_cococlip,last,19,0.005699999999999999,0.05,42,"[19, 1.0]",testid,2.7144618034362793,0.19818777713514554,0.004792177683957179,0.1452834300869232,0.00428279526778641 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/log.txt b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..dc5cdc0e186a8a41c645ae6c745d87d8ccec8008 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/log.txt @@ -0,0 +1,960 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: clean, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 21:13:09 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:23:37 lr: nan time: 3.5433 data: 3.1009 max mem: 3910 +train: [0] [ 20/400] eta: 0:03:05 lr: 0.000003 loss: 3.1766 (3.1772) grad: 0.0388 (0.0393) time: 0.3343 data: 0.0072 max mem: 3953 +train: [0] [ 40/400] eta: 0:02:30 lr: 0.000006 loss: 3.1783 (3.1785) grad: 0.0387 (0.0388) time: 0.3458 data: 0.0051 max mem: 3953 +train: [0] [ 60/400] eta: 0:02:13 lr: 0.000009 loss: 3.1754 (3.1782) grad: 0.0382 (0.0384) time: 0.3423 data: 0.0043 max mem: 3953 +train: [0] [ 80/400] eta: 0:02:00 lr: 0.000012 loss: 3.1767 (3.1783) grad: 0.0371 (0.0382) time: 0.3262 data: 0.0042 max mem: 3953 +train: [0] [100/400] eta: 0:01:49 lr: 0.000015 loss: 3.1778 (3.1785) grad: 0.0368 (0.0381) time: 0.3223 data: 0.0040 max mem: 3953 +train: [0] [120/400] eta: 0:01:41 lr: 0.000018 loss: 3.1766 (3.1775) grad: 0.0374 (0.0381) time: 0.3351 data: 0.0040 max mem: 3953 +train: [0] [140/400] eta: 0:01:32 lr: 0.000021 loss: 3.1704 (3.1763) grad: 0.0385 (0.0383) time: 0.3284 data: 0.0039 max mem: 3953 +train: [0] [160/400] eta: 0:01:24 lr: 0.000024 loss: 3.1691 (3.1758) grad: 0.0386 (0.0382) time: 0.3209 data: 0.0036 max mem: 3953 +train: [0] [180/400] eta: 0:01:17 lr: 0.000027 loss: 3.1683 (3.1746) grad: 0.0375 (0.0382) time: 0.3352 data: 0.0042 max mem: 3953 +train: [0] [200/400] eta: 0:01:09 lr: 0.000030 loss: 3.1633 (3.1735) grad: 0.0375 (0.0381) time: 0.3373 data: 0.0041 max mem: 3953 +train: [0] [220/400] eta: 0:01:02 lr: 0.000033 loss: 3.1622 (3.1724) grad: 0.0374 (0.0380) time: 0.3316 data: 0.0042 max mem: 3953 +train: [0] [240/400] eta: 0:00:55 lr: 0.000036 loss: 3.1616 (3.1716) grad: 0.0372 (0.0380) time: 0.3313 data: 0.0044 max mem: 3953 +train: [0] [260/400] eta: 0:00:48 lr: 0.000039 loss: 3.1623 (3.1708) grad: 0.0371 (0.0379) time: 0.3210 data: 0.0041 max mem: 3953 +train: [0] [280/400] eta: 0:00:41 lr: 0.000042 loss: 3.1562 (3.1694) grad: 0.0368 (0.0379) time: 0.3285 data: 0.0040 max mem: 3953 +train: [0] [300/400] eta: 0:00:34 lr: 0.000045 loss: 3.1521 (3.1684) grad: 0.0379 (0.0379) time: 0.3409 data: 0.0040 max mem: 3953 +train: [0] [320/400] eta: 0:00:27 lr: 0.000048 loss: 3.1493 (3.1669) grad: 0.0378 (0.0379) time: 0.3391 data: 0.0041 max mem: 3953 +train: [0] [340/400] eta: 0:00:20 lr: 0.000051 loss: 3.1516 (3.1663) grad: 0.0371 (0.0378) time: 0.3450 data: 0.0041 max mem: 3953 +train: [0] [360/400] eta: 0:00:13 lr: 0.000054 loss: 3.1535 (3.1652) grad: 0.0371 (0.0378) time: 0.3543 data: 0.0045 max mem: 3953 +train: [0] [380/400] eta: 0:00:06 lr: 0.000057 loss: 3.1463 (3.1642) grad: 0.0374 (0.0378) time: 0.3345 data: 0.0038 max mem: 3953 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1419 (3.1628) grad: 0.0380 (0.0378) time: 0.3373 data: 0.0040 max mem: 3953 +train: [0] Total time: 0:02:17 (0.3429 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1419 (3.1628) grad: 0.0380 (0.0378) +eval (validation): [0] [ 0/85] eta: 0:04:39 time: 3.2920 data: 3.0780 max mem: 3953 +eval (validation): [0] [20/85] eta: 0:00:30 time: 0.3354 data: 0.0272 max mem: 3953 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3371 data: 0.0050 max mem: 3953 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3313 data: 0.0043 max mem: 3953 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.2961 data: 0.0041 max mem: 3953 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.2907 data: 0.0040 max mem: 3953 +eval (validation): [0] Total time: 0:00:30 (0.3617 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.963 acc: 0.150 f1: 0.074 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:12 lr: nan time: 3.3312 data: 3.0767 max mem: 3953 +train: [1] [ 20/400] eta: 0:02:58 lr: 0.000063 loss: 3.1347 (3.1392) grad: 0.0359 (0.0366) time: 0.3261 data: 0.0049 max mem: 3953 +train: [1] [ 40/400] eta: 0:02:22 lr: 0.000066 loss: 3.1339 (3.1365) grad: 0.0365 (0.0367) time: 0.3176 data: 0.0045 max mem: 3953 +train: [1] [ 60/400] eta: 0:02:06 lr: 0.000069 loss: 3.1347 (3.1357) grad: 0.0371 (0.0369) time: 0.3249 data: 0.0038 max mem: 3953 +train: [1] [ 80/400] eta: 0:01:55 lr: 0.000072 loss: 3.1219 (3.1310) grad: 0.0376 (0.0372) time: 0.3227 data: 0.0042 max mem: 3953 +train: [1] [100/400] eta: 0:01:46 lr: 0.000075 loss: 3.1166 (3.1311) grad: 0.0371 (0.0371) time: 0.3356 data: 0.0040 max mem: 3953 +train: [1] [120/400] eta: 0:01:38 lr: 0.000078 loss: 3.1199 (3.1284) grad: 0.0363 (0.0370) time: 0.3314 data: 0.0040 max mem: 3953 +train: [1] [140/400] eta: 0:01:30 lr: 0.000081 loss: 3.1169 (3.1268) grad: 0.0369 (0.0371) time: 0.3230 data: 0.0040 max mem: 3953 +train: [1] [160/400] eta: 0:01:22 lr: 0.000084 loss: 3.1223 (3.1271) grad: 0.0365 (0.0370) time: 0.3327 data: 0.0038 max mem: 3953 +train: [1] [180/400] eta: 0:01:15 lr: 0.000087 loss: 3.1264 (3.1264) grad: 0.0364 (0.0369) time: 0.3224 data: 0.0038 max mem: 3953 +train: [1] [200/400] eta: 0:01:08 lr: 0.000090 loss: 3.1154 (3.1246) grad: 0.0368 (0.0369) time: 0.3359 data: 0.0039 max mem: 3953 +train: [1] [220/400] eta: 0:01:01 lr: 0.000093 loss: 3.1054 (3.1229) grad: 0.0370 (0.0370) time: 0.3258 data: 0.0040 max mem: 3953 +train: [1] [240/400] eta: 0:00:54 lr: 0.000096 loss: 3.1056 (3.1212) grad: 0.0376 (0.0370) time: 0.3253 data: 0.0040 max mem: 3953 +train: [1] [260/400] eta: 0:00:47 lr: 0.000099 loss: 3.1033 (3.1207) grad: 0.0365 (0.0369) time: 0.3196 data: 0.0041 max mem: 3953 +train: [1] [280/400] eta: 0:00:40 lr: 0.000102 loss: 3.0985 (3.1185) grad: 0.0367 (0.0370) time: 0.3228 data: 0.0038 max mem: 3953 +train: [1] [300/400] eta: 0:00:33 lr: 0.000105 loss: 3.0945 (3.1173) grad: 0.0368 (0.0369) time: 0.3332 data: 0.0043 max mem: 3953 +train: [1] [320/400] eta: 0:00:26 lr: 0.000108 loss: 3.0986 (3.1166) grad: 0.0360 (0.0369) time: 0.3241 data: 0.0043 max mem: 3953 +train: [1] [340/400] eta: 0:00:20 lr: 0.000111 loss: 3.0915 (3.1148) grad: 0.0363 (0.0369) time: 0.3303 data: 0.0041 max mem: 3953 +train: [1] [360/400] eta: 0:00:13 lr: 0.000114 loss: 3.0840 (3.1135) grad: 0.0363 (0.0368) time: 0.3384 data: 0.0041 max mem: 3953 +train: [1] [380/400] eta: 0:00:06 lr: 0.000117 loss: 3.0984 (3.1123) grad: 0.0363 (0.0369) time: 0.3519 data: 0.0047 max mem: 3953 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.0861 (3.1113) grad: 0.0374 (0.0369) time: 0.3472 data: 0.0044 max mem: 3953 +train: [1] Total time: 0:02:14 (0.3371 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.0861 (3.1113) grad: 0.0374 (0.0369) +eval (validation): [1] [ 0/85] eta: 0:04:36 time: 3.2484 data: 3.0529 max mem: 3953 +eval (validation): [1] [20/85] eta: 0:00:29 time: 0.3158 data: 0.0125 max mem: 3953 +eval (validation): [1] [40/85] eta: 0:00:17 time: 0.3218 data: 0.0048 max mem: 3953 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3433 data: 0.0049 max mem: 3953 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3075 data: 0.0043 max mem: 3953 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3024 data: 0.0043 max mem: 3953 +eval (validation): [1] Total time: 0:00:30 (0.3604 s / it) +cv: [1] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.814 acc: 0.180 f1: 0.105 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:32 lr: nan time: 3.3811 data: 3.1705 max mem: 3953 +train: [2] [ 20/400] eta: 0:03:03 lr: 0.000123 loss: 3.0637 (3.0693) grad: 0.0355 (0.0361) time: 0.3369 data: 0.0036 max mem: 3953 +train: [2] [ 40/400] eta: 0:02:27 lr: 0.000126 loss: 3.0643 (3.0705) grad: 0.0359 (0.0364) time: 0.3345 data: 0.0053 max mem: 3953 +train: [2] [ 60/400] eta: 0:02:09 lr: 0.000129 loss: 3.0682 (3.0711) grad: 0.0360 (0.0363) time: 0.3213 data: 0.0035 max mem: 3953 +train: [2] [ 80/400] eta: 0:01:58 lr: 0.000132 loss: 3.0664 (3.0695) grad: 0.0358 (0.0363) time: 0.3365 data: 0.0043 max mem: 3953 +train: [2] [100/400] eta: 0:01:48 lr: 0.000135 loss: 3.0586 (3.0697) grad: 0.0362 (0.0365) time: 0.3260 data: 0.0042 max mem: 3953 +train: [2] [120/400] eta: 0:01:40 lr: 0.000138 loss: 3.0738 (3.0710) grad: 0.0362 (0.0364) time: 0.3499 data: 0.0047 max mem: 3953 +train: [2] [140/400] eta: 0:01:32 lr: 0.000141 loss: 3.0800 (3.0712) grad: 0.0363 (0.0364) time: 0.3291 data: 0.0043 max mem: 3953 +train: [2] [160/400] eta: 0:01:24 lr: 0.000144 loss: 3.0664 (3.0722) grad: 0.0362 (0.0364) time: 0.3385 data: 0.0045 max mem: 3953 +train: [2] [180/400] eta: 0:01:16 lr: 0.000147 loss: 3.0630 (3.0710) grad: 0.0362 (0.0364) time: 0.3211 data: 0.0042 max mem: 3953 +train: [2] [200/400] eta: 0:01:09 lr: 0.000150 loss: 3.0593 (3.0694) grad: 0.0364 (0.0364) time: 0.3267 data: 0.0045 max mem: 3953 +train: [2] [220/400] eta: 0:01:02 lr: 0.000153 loss: 3.0470 (3.0675) grad: 0.0369 (0.0365) time: 0.3321 data: 0.0043 max mem: 3953 +train: [2] [240/400] eta: 0:00:55 lr: 0.000156 loss: 3.0547 (3.0670) grad: 0.0368 (0.0366) time: 0.3337 data: 0.0041 max mem: 3953 +train: [2] [260/400] eta: 0:00:48 lr: 0.000159 loss: 3.0679 (3.0674) grad: 0.0358 (0.0365) time: 0.3521 data: 0.0041 max mem: 3953 +train: [2] [280/400] eta: 0:00:41 lr: 0.000162 loss: 3.0625 (3.0659) grad: 0.0361 (0.0365) time: 0.3313 data: 0.0038 max mem: 3953 +train: [2] [300/400] eta: 0:00:34 lr: 0.000165 loss: 3.0546 (3.0659) grad: 0.0358 (0.0365) time: 0.3459 data: 0.0041 max mem: 3953 +train: [2] [320/400] eta: 0:00:27 lr: 0.000168 loss: 3.0517 (3.0644) grad: 0.0357 (0.0365) time: 0.3506 data: 0.0042 max mem: 3953 +train: [2] [340/400] eta: 0:00:20 lr: 0.000171 loss: 3.0408 (3.0636) grad: 0.0363 (0.0365) time: 0.3254 data: 0.0039 max mem: 3953 +train: [2] [360/400] eta: 0:00:13 lr: 0.000174 loss: 3.0437 (3.0628) grad: 0.0359 (0.0365) time: 0.3411 data: 0.0041 max mem: 3953 +train: [2] [380/400] eta: 0:00:06 lr: 0.000177 loss: 3.0572 (3.0626) grad: 0.0354 (0.0364) time: 0.3408 data: 0.0042 max mem: 3953 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.0590 (3.0632) grad: 0.0365 (0.0365) time: 0.3343 data: 0.0042 max mem: 3953 +train: [2] Total time: 0:02:17 (0.3432 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.0590 (3.0632) grad: 0.0365 (0.0365) +eval (validation): [2] [ 0/85] eta: 0:04:46 time: 3.3696 data: 3.1219 max mem: 3953 +eval (validation): [2] [20/85] eta: 0:00:32 time: 0.3610 data: 0.0043 max mem: 3953 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3528 data: 0.0045 max mem: 3953 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3141 data: 0.0043 max mem: 3953 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3085 data: 0.0043 max mem: 3953 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3076 data: 0.0040 max mem: 3953 +eval (validation): [2] Total time: 0:00:31 (0.3733 s / it) +cv: [2] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.736 acc: 0.199 f1: 0.138 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:16 lr: nan time: 3.3401 data: 3.0849 max mem: 3953 +train: [3] [ 20/400] eta: 0:03:17 lr: 0.000183 loss: 3.0316 (3.0386) grad: 0.0361 (0.0365) time: 0.3781 data: 0.0060 max mem: 3953 +train: [3] [ 40/400] eta: 0:02:36 lr: 0.000186 loss: 3.0316 (3.0315) grad: 0.0359 (0.0362) time: 0.3471 data: 0.0034 max mem: 3953 +train: [3] [ 60/400] eta: 0:02:16 lr: 0.000189 loss: 3.0294 (3.0328) grad: 0.0358 (0.0363) time: 0.3277 data: 0.0041 max mem: 3953 +train: [3] [ 80/400] eta: 0:02:02 lr: 0.000192 loss: 3.0333 (3.0346) grad: 0.0366 (0.0366) time: 0.3258 data: 0.0042 max mem: 3953 +train: [3] [100/400] eta: 0:01:51 lr: 0.000195 loss: 3.0397 (3.0356) grad: 0.0364 (0.0364) time: 0.3287 data: 0.0042 max mem: 3953 +train: [3] [120/400] eta: 0:01:41 lr: 0.000198 loss: 3.0349 (3.0345) grad: 0.0358 (0.0364) time: 0.3267 data: 0.0040 max mem: 3953 +train: [3] [140/400] eta: 0:01:33 lr: 0.000201 loss: 3.0254 (3.0332) grad: 0.0358 (0.0364) time: 0.3275 data: 0.0039 max mem: 3953 +train: [3] [160/400] eta: 0:01:25 lr: 0.000204 loss: 3.0106 (3.0299) grad: 0.0362 (0.0364) time: 0.3453 data: 0.0042 max mem: 3953 +train: [3] [180/400] eta: 0:01:18 lr: 0.000207 loss: 3.0106 (3.0299) grad: 0.0368 (0.0365) time: 0.3400 data: 0.0039 max mem: 3953 +train: [3] [200/400] eta: 0:01:10 lr: 0.000210 loss: 3.0347 (3.0308) grad: 0.0365 (0.0364) time: 0.3406 data: 0.0042 max mem: 3953 +train: [3] [220/400] eta: 0:01:03 lr: 0.000213 loss: 3.0240 (3.0296) grad: 0.0358 (0.0364) time: 0.3429 data: 0.0040 max mem: 3953 +train: [3] [240/400] eta: 0:00:56 lr: 0.000216 loss: 3.0266 (3.0312) grad: 0.0361 (0.0364) time: 0.3382 data: 0.0042 max mem: 3953 +train: [3] [260/400] eta: 0:00:48 lr: 0.000219 loss: 3.0315 (3.0300) grad: 0.0361 (0.0364) time: 0.3237 data: 0.0039 max mem: 3953 +train: [3] [280/400] eta: 0:00:41 lr: 0.000222 loss: 3.0117 (3.0294) grad: 0.0364 (0.0364) time: 0.3306 data: 0.0041 max mem: 3953 +train: [3] [300/400] eta: 0:00:34 lr: 0.000225 loss: 3.0095 (3.0277) grad: 0.0362 (0.0364) time: 0.3339 data: 0.0040 max mem: 3953 +train: [3] [320/400] eta: 0:00:27 lr: 0.000228 loss: 3.0095 (3.0275) grad: 0.0357 (0.0364) time: 0.3264 data: 0.0039 max mem: 3953 +train: [3] [340/400] eta: 0:00:20 lr: 0.000231 loss: 3.0162 (3.0263) grad: 0.0360 (0.0364) time: 0.3227 data: 0.0042 max mem: 3953 +train: [3] [360/400] eta: 0:00:13 lr: 0.000234 loss: 3.0114 (3.0257) grad: 0.0355 (0.0363) time: 0.3208 data: 0.0044 max mem: 3953 +train: [3] [380/400] eta: 0:00:06 lr: 0.000237 loss: 3.0031 (3.0244) grad: 0.0357 (0.0363) time: 0.3246 data: 0.0040 max mem: 3953 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.0004 (3.0237) grad: 0.0362 (0.0363) time: 0.3469 data: 0.0043 max mem: 3953 +train: [3] Total time: 0:02:17 (0.3428 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.0004 (3.0237) grad: 0.0362 (0.0363) +eval (validation): [3] [ 0/85] eta: 0:04:44 time: 3.3494 data: 3.1336 max mem: 3953 +eval (validation): [3] [20/85] eta: 0:00:30 time: 0.3208 data: 0.0044 max mem: 3953 +eval (validation): [3] [40/85] eta: 0:00:18 time: 0.3570 data: 0.0052 max mem: 3953 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3337 data: 0.0038 max mem: 3953 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3001 data: 0.0037 max mem: 3953 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.2957 data: 0.0038 max mem: 3953 +eval (validation): [3] Total time: 0:00:30 (0.3647 s / it) +cv: [3] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.707 acc: 0.208 f1: 0.138 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:37 lr: nan time: 3.3947 data: 3.1234 max mem: 3953 +train: [4] [ 20/400] eta: 0:03:14 lr: 0.000243 loss: 2.9879 (2.9957) grad: 0.0353 (0.0357) time: 0.3672 data: 0.0051 max mem: 3953 +train: [4] [ 40/400] eta: 0:02:31 lr: 0.000246 loss: 2.9852 (2.9885) grad: 0.0351 (0.0353) time: 0.3274 data: 0.0036 max mem: 3953 +train: [4] [ 60/400] eta: 0:02:12 lr: 0.000249 loss: 2.9831 (2.9864) grad: 0.0351 (0.0355) time: 0.3220 data: 0.0042 max mem: 3953 +train: [4] [ 80/400] eta: 0:01:59 lr: 0.000252 loss: 2.9861 (2.9839) grad: 0.0356 (0.0355) time: 0.3249 data: 0.0042 max mem: 3953 +train: [4] [100/400] eta: 0:01:49 lr: 0.000255 loss: 2.9861 (2.9827) grad: 0.0358 (0.0357) time: 0.3374 data: 0.0041 max mem: 3953 +train: [4] [120/400] eta: 0:01:40 lr: 0.000258 loss: 2.9773 (2.9818) grad: 0.0363 (0.0359) time: 0.3210 data: 0.0043 max mem: 3953 +train: [4] [140/400] eta: 0:01:32 lr: 0.000261 loss: 2.9666 (2.9813) grad: 0.0360 (0.0359) time: 0.3470 data: 0.0042 max mem: 3953 +train: [4] [160/400] eta: 0:01:25 lr: 0.000264 loss: 2.9961 (2.9831) grad: 0.0355 (0.0358) time: 0.3346 data: 0.0040 max mem: 3953 +train: [4] [180/400] eta: 0:01:17 lr: 0.000267 loss: 2.9845 (2.9826) grad: 0.0359 (0.0359) time: 0.3312 data: 0.0042 max mem: 3953 +train: [4] [200/400] eta: 0:01:10 lr: 0.000270 loss: 2.9753 (2.9832) grad: 0.0363 (0.0359) time: 0.3462 data: 0.0044 max mem: 3953 +train: [4] [220/400] eta: 0:01:02 lr: 0.000273 loss: 2.9879 (2.9842) grad: 0.0363 (0.0359) time: 0.3328 data: 0.0041 max mem: 3953 +train: [4] [240/400] eta: 0:00:55 lr: 0.000276 loss: 2.9863 (2.9836) grad: 0.0364 (0.0360) time: 0.3501 data: 0.0043 max mem: 3953 +train: [4] [260/400] eta: 0:00:48 lr: 0.000279 loss: 2.9920 (2.9854) grad: 0.0364 (0.0360) time: 0.3209 data: 0.0040 max mem: 3953 +train: [4] [280/400] eta: 0:00:41 lr: 0.000282 loss: 2.9920 (2.9864) grad: 0.0360 (0.0360) time: 0.3348 data: 0.0040 max mem: 3953 +train: [4] [300/400] eta: 0:00:34 lr: 0.000285 loss: 2.9918 (2.9864) grad: 0.0358 (0.0360) time: 0.3458 data: 0.0041 max mem: 3953 +train: [4] [320/400] eta: 0:00:27 lr: 0.000288 loss: 2.9955 (2.9870) grad: 0.0358 (0.0359) time: 0.3334 data: 0.0040 max mem: 3953 +train: [4] [340/400] eta: 0:00:20 lr: 0.000291 loss: 2.9887 (2.9869) grad: 0.0358 (0.0359) time: 0.3365 data: 0.0039 max mem: 3953 +train: [4] [360/400] eta: 0:00:13 lr: 0.000294 loss: 2.9834 (2.9867) grad: 0.0355 (0.0359) time: 0.3295 data: 0.0039 max mem: 3953 +train: [4] [380/400] eta: 0:00:06 lr: 0.000297 loss: 2.9737 (2.9866) grad: 0.0355 (0.0359) time: 0.3340 data: 0.0040 max mem: 3953 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.9738 (2.9861) grad: 0.0359 (0.0359) time: 0.3312 data: 0.0040 max mem: 3953 +train: [4] Total time: 0:02:17 (0.3433 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.9738 (2.9861) grad: 0.0359 (0.0359) +eval (validation): [4] [ 0/85] eta: 0:04:48 time: 3.3997 data: 3.1417 max mem: 3953 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3456 data: 0.0043 max mem: 3953 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3484 data: 0.0045 max mem: 3953 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3619 data: 0.0048 max mem: 3953 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3062 data: 0.0041 max mem: 3953 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.2958 data: 0.0038 max mem: 3953 +eval (validation): [4] Total time: 0:00:32 (0.3773 s / it) +cv: [4] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 2.713 acc: 0.207 f1: 0.144 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:21:28 lr: nan time: 3.2219 data: 3.0214 max mem: 3953 +train: [5] [ 20/400] eta: 0:02:59 lr: 0.000300 loss: 2.9428 (2.9359) grad: 0.0351 (0.0358) time: 0.3340 data: 0.0229 max mem: 3953 +train: [5] [ 40/400] eta: 0:02:23 lr: 0.000300 loss: 2.9536 (2.9518) grad: 0.0355 (0.0357) time: 0.3227 data: 0.0044 max mem: 3953 +train: [5] [ 60/400] eta: 0:02:10 lr: 0.000300 loss: 2.9630 (2.9539) grad: 0.0355 (0.0357) time: 0.3519 data: 0.0034 max mem: 3953 +train: [5] [ 80/400] eta: 0:01:59 lr: 0.000300 loss: 2.9485 (2.9533) grad: 0.0353 (0.0355) time: 0.3397 data: 0.0039 max mem: 3953 +train: [5] [100/400] eta: 0:01:49 lr: 0.000300 loss: 2.9438 (2.9504) grad: 0.0357 (0.0356) time: 0.3370 data: 0.0040 max mem: 3953 +train: [5] [120/400] eta: 0:01:41 lr: 0.000300 loss: 2.9602 (2.9554) grad: 0.0353 (0.0356) time: 0.3442 data: 0.0041 max mem: 3953 +train: [5] [140/400] eta: 0:01:32 lr: 0.000300 loss: 2.9781 (2.9589) grad: 0.0354 (0.0357) time: 0.3282 data: 0.0037 max mem: 3953 +train: [5] [160/400] eta: 0:01:25 lr: 0.000299 loss: 2.9751 (2.9574) grad: 0.0360 (0.0357) time: 0.3541 data: 0.0037 max mem: 3953 +train: [5] [180/400] eta: 0:01:18 lr: 0.000299 loss: 2.9384 (2.9576) grad: 0.0360 (0.0357) time: 0.3368 data: 0.0038 max mem: 3953 +train: [5] [200/400] eta: 0:01:11 lr: 0.000299 loss: 2.9384 (2.9558) grad: 0.0356 (0.0357) time: 0.3694 data: 0.0044 max mem: 3953 +train: [5] [220/400] eta: 0:01:03 lr: 0.000299 loss: 2.9507 (2.9551) grad: 0.0353 (0.0357) time: 0.3190 data: 0.0041 max mem: 3953 +train: [5] [240/400] eta: 0:00:56 lr: 0.000299 loss: 2.9527 (2.9566) grad: 0.0356 (0.0357) time: 0.3229 data: 0.0043 max mem: 3953 +train: [5] [260/400] eta: 0:00:48 lr: 0.000299 loss: 2.9550 (2.9579) grad: 0.0361 (0.0357) time: 0.3217 data: 0.0038 max mem: 3953 +train: [5] [280/400] eta: 0:00:41 lr: 0.000298 loss: 2.9599 (2.9592) grad: 0.0361 (0.0357) time: 0.3227 data: 0.0041 max mem: 3953 +train: [5] [300/400] eta: 0:00:34 lr: 0.000298 loss: 2.9807 (2.9604) grad: 0.0354 (0.0357) time: 0.3639 data: 0.0043 max mem: 3953 +train: [5] [320/400] eta: 0:00:27 lr: 0.000298 loss: 2.9616 (2.9599) grad: 0.0349 (0.0357) time: 0.3390 data: 0.0042 max mem: 3953 +train: [5] [340/400] eta: 0:00:20 lr: 0.000298 loss: 2.9258 (2.9583) grad: 0.0352 (0.0357) time: 0.3307 data: 0.0043 max mem: 3953 +train: [5] [360/400] eta: 0:00:13 lr: 0.000297 loss: 2.9238 (2.9574) grad: 0.0357 (0.0357) time: 0.3372 data: 0.0042 max mem: 3953 +train: [5] [380/400] eta: 0:00:06 lr: 0.000297 loss: 2.9516 (2.9585) grad: 0.0352 (0.0357) time: 0.3303 data: 0.0043 max mem: 3953 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.9774 (2.9590) grad: 0.0356 (0.0357) time: 0.3241 data: 0.0041 max mem: 3953 +train: [5] Total time: 0:02:17 (0.3440 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.9774 (2.9590) grad: 0.0356 (0.0357) +eval (validation): [5] [ 0/85] eta: 0:04:40 time: 3.3016 data: 3.0990 max mem: 3953 +eval (validation): [5] [20/85] eta: 0:00:31 time: 0.3473 data: 0.0171 max mem: 3953 +eval (validation): [5] [40/85] eta: 0:00:18 time: 0.3184 data: 0.0037 max mem: 3953 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3222 data: 0.0042 max mem: 3953 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3013 data: 0.0046 max mem: 3953 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.2939 data: 0.0040 max mem: 3953 +eval (validation): [5] Total time: 0:00:30 (0.3590 s / it) +cv: [5] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.698 acc: 0.209 f1: 0.148 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:21:22 lr: nan time: 3.2069 data: 3.0071 max mem: 3953 +train: [6] [ 20/400] eta: 0:02:57 lr: 0.000296 loss: 2.9362 (2.9348) grad: 0.0351 (0.0355) time: 0.3291 data: 0.0052 max mem: 3953 +train: [6] [ 40/400] eta: 0:02:30 lr: 0.000296 loss: 2.9345 (2.9342) grad: 0.0354 (0.0354) time: 0.3652 data: 0.0037 max mem: 3953 +train: [6] [ 60/400] eta: 0:02:12 lr: 0.000296 loss: 2.9345 (2.9436) grad: 0.0354 (0.0354) time: 0.3364 data: 0.0041 max mem: 3953 +train: [6] [ 80/400] eta: 0:02:00 lr: 0.000295 loss: 2.9268 (2.9404) grad: 0.0357 (0.0357) time: 0.3356 data: 0.0041 max mem: 3953 +train: [6] [100/400] eta: 0:01:50 lr: 0.000295 loss: 2.9205 (2.9340) grad: 0.0355 (0.0355) time: 0.3391 data: 0.0042 max mem: 3953 +train: [6] [120/400] eta: 0:01:41 lr: 0.000295 loss: 2.9304 (2.9385) grad: 0.0350 (0.0355) time: 0.3276 data: 0.0042 max mem: 3953 +train: [6] [140/400] eta: 0:01:33 lr: 0.000294 loss: 2.9652 (2.9421) grad: 0.0357 (0.0356) time: 0.3364 data: 0.0042 max mem: 3953 +train: [6] [160/400] eta: 0:01:25 lr: 0.000294 loss: 2.9426 (2.9382) grad: 0.0357 (0.0356) time: 0.3326 data: 0.0042 max mem: 3953 +train: [6] [180/400] eta: 0:01:18 lr: 0.000293 loss: 2.9222 (2.9384) grad: 0.0358 (0.0356) time: 0.3469 data: 0.0041 max mem: 3953 +train: [6] [200/400] eta: 0:01:10 lr: 0.000293 loss: 2.9229 (2.9362) grad: 0.0357 (0.0356) time: 0.3388 data: 0.0041 max mem: 3953 +train: [6] [220/400] eta: 0:01:03 lr: 0.000292 loss: 2.9163 (2.9337) grad: 0.0357 (0.0356) time: 0.3425 data: 0.0040 max mem: 3953 +train: [6] [240/400] eta: 0:00:56 lr: 0.000292 loss: 2.9157 (2.9339) grad: 0.0357 (0.0356) time: 0.3413 data: 0.0040 max mem: 3953 +train: [6] [260/400] eta: 0:00:48 lr: 0.000291 loss: 2.9272 (2.9336) grad: 0.0355 (0.0356) time: 0.3308 data: 0.0042 max mem: 3953 +train: [6] [280/400] eta: 0:00:41 lr: 0.000291 loss: 2.9302 (2.9337) grad: 0.0354 (0.0356) time: 0.3381 data: 0.0042 max mem: 3953 +train: [6] [300/400] eta: 0:00:34 lr: 0.000290 loss: 2.9345 (2.9341) grad: 0.0355 (0.0356) time: 0.3379 data: 0.0043 max mem: 3953 +train: [6] [320/400] eta: 0:00:27 lr: 0.000290 loss: 2.9447 (2.9354) grad: 0.0355 (0.0356) time: 0.3354 data: 0.0045 max mem: 3953 +train: [6] [340/400] eta: 0:00:20 lr: 0.000289 loss: 2.9447 (2.9362) grad: 0.0351 (0.0356) time: 0.3497 data: 0.0039 max mem: 3953 +train: [6] [360/400] eta: 0:00:13 lr: 0.000288 loss: 2.9372 (2.9355) grad: 0.0350 (0.0356) time: 0.3216 data: 0.0040 max mem: 3953 +train: [6] [380/400] eta: 0:00:06 lr: 0.000288 loss: 2.9302 (2.9349) grad: 0.0351 (0.0356) time: 0.3232 data: 0.0042 max mem: 3953 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.9374 (2.9353) grad: 0.0346 (0.0355) time: 0.3243 data: 0.0044 max mem: 3953 +train: [6] Total time: 0:02:17 (0.3441 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.9374 (2.9353) grad: 0.0346 (0.0355) +eval (validation): [6] [ 0/85] eta: 0:04:41 time: 3.3097 data: 3.1027 max mem: 3953 +eval (validation): [6] [20/85] eta: 0:00:30 time: 0.3318 data: 0.0048 max mem: 3953 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3276 data: 0.0043 max mem: 3953 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3227 data: 0.0044 max mem: 3953 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3148 data: 0.0042 max mem: 3953 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3056 data: 0.0041 max mem: 3953 +eval (validation): [6] Total time: 0:00:30 (0.3610 s / it) +cv: [6] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.680 acc: 0.210 f1: 0.145 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:22:09 lr: nan time: 3.3229 data: 3.0645 max mem: 3953 +train: [7] [ 20/400] eta: 0:03:00 lr: 0.000286 loss: 2.8824 (2.8928) grad: 0.0349 (0.0353) time: 0.3324 data: 0.0040 max mem: 3953 +train: [7] [ 40/400] eta: 0:02:25 lr: 0.000286 loss: 2.8895 (2.8885) grad: 0.0351 (0.0357) time: 0.3286 data: 0.0038 max mem: 3953 +train: [7] [ 60/400] eta: 0:02:08 lr: 0.000285 loss: 2.9010 (2.8903) grad: 0.0352 (0.0355) time: 0.3257 data: 0.0041 max mem: 3953 +train: [7] [ 80/400] eta: 0:01:57 lr: 0.000284 loss: 2.9099 (2.8964) grad: 0.0352 (0.0355) time: 0.3288 data: 0.0041 max mem: 3953 +train: [7] [100/400] eta: 0:01:47 lr: 0.000284 loss: 2.8921 (2.8980) grad: 0.0353 (0.0355) time: 0.3252 data: 0.0041 max mem: 3953 +train: [7] [120/400] eta: 0:01:39 lr: 0.000283 loss: 2.8908 (2.8987) grad: 0.0356 (0.0356) time: 0.3420 data: 0.0039 max mem: 3953 +train: [7] [140/400] eta: 0:01:31 lr: 0.000282 loss: 2.9048 (2.9036) grad: 0.0355 (0.0355) time: 0.3306 data: 0.0041 max mem: 3953 +train: [7] [160/400] eta: 0:01:23 lr: 0.000282 loss: 2.9233 (2.9059) grad: 0.0353 (0.0355) time: 0.3289 data: 0.0040 max mem: 3953 +train: [7] [180/400] eta: 0:01:16 lr: 0.000281 loss: 2.8873 (2.9015) grad: 0.0355 (0.0356) time: 0.3242 data: 0.0041 max mem: 3953 +train: [7] [200/400] eta: 0:01:09 lr: 0.000280 loss: 2.8870 (2.9046) grad: 0.0354 (0.0356) time: 0.3578 data: 0.0042 max mem: 3953 +train: [7] [220/400] eta: 0:01:02 lr: 0.000279 loss: 2.9157 (2.9052) grad: 0.0351 (0.0355) time: 0.3385 data: 0.0040 max mem: 3953 +train: [7] [240/400] eta: 0:00:55 lr: 0.000278 loss: 2.9157 (2.9078) grad: 0.0357 (0.0356) time: 0.3300 data: 0.0042 max mem: 3953 +train: [7] [260/400] eta: 0:00:48 lr: 0.000278 loss: 2.9399 (2.9111) grad: 0.0358 (0.0356) time: 0.3218 data: 0.0041 max mem: 3953 +train: [7] [280/400] eta: 0:00:41 lr: 0.000277 loss: 2.9399 (2.9149) grad: 0.0349 (0.0356) time: 0.3307 data: 0.0042 max mem: 3953 +train: [7] [300/400] eta: 0:00:34 lr: 0.000276 loss: 2.9269 (2.9150) grad: 0.0350 (0.0356) time: 0.3323 data: 0.0042 max mem: 3953 +train: [7] [320/400] eta: 0:00:27 lr: 0.000275 loss: 2.9223 (2.9169) grad: 0.0353 (0.0356) time: 0.3468 data: 0.0043 max mem: 3953 +train: [7] [340/400] eta: 0:00:20 lr: 0.000274 loss: 2.9316 (2.9158) grad: 0.0355 (0.0356) time: 0.3439 data: 0.0042 max mem: 3953 +train: [7] [360/400] eta: 0:00:13 lr: 0.000273 loss: 2.9021 (2.9160) grad: 0.0353 (0.0356) time: 0.3339 data: 0.0041 max mem: 3953 +train: [7] [380/400] eta: 0:00:06 lr: 0.000272 loss: 2.9176 (2.9165) grad: 0.0355 (0.0356) time: 0.3401 data: 0.0043 max mem: 3953 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.9173 (2.9148) grad: 0.0355 (0.0356) time: 0.3495 data: 0.0039 max mem: 3953 +train: [7] Total time: 0:02:16 (0.3422 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.9173 (2.9148) grad: 0.0355 (0.0356) +eval (validation): [7] [ 0/85] eta: 0:04:49 time: 3.4068 data: 3.1506 max mem: 3953 +eval (validation): [7] [20/85] eta: 0:00:32 time: 0.3489 data: 0.0053 max mem: 3953 +eval (validation): [7] [40/85] eta: 0:00:18 time: 0.3067 data: 0.0037 max mem: 3953 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3321 data: 0.0045 max mem: 3953 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3191 data: 0.0041 max mem: 3953 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3089 data: 0.0039 max mem: 3953 +eval (validation): [7] Total time: 0:00:31 (0.3655 s / it) +cv: [7] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.670 acc: 0.212 f1: 0.148 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:22:01 lr: nan time: 3.3027 data: 3.0917 max mem: 3953 +train: [8] [ 20/400] eta: 0:02:59 lr: 0.000270 loss: 2.8787 (2.8972) grad: 0.0355 (0.0353) time: 0.3296 data: 0.0043 max mem: 3953 +train: [8] [ 40/400] eta: 0:02:25 lr: 0.000270 loss: 2.8842 (2.8946) grad: 0.0353 (0.0353) time: 0.3333 data: 0.0047 max mem: 3953 +train: [8] [ 60/400] eta: 0:02:10 lr: 0.000269 loss: 2.9007 (2.9020) grad: 0.0352 (0.0354) time: 0.3385 data: 0.0032 max mem: 3953 +train: [8] [ 80/400] eta: 0:01:57 lr: 0.000268 loss: 2.8865 (2.8968) grad: 0.0348 (0.0352) time: 0.3259 data: 0.0036 max mem: 3953 +train: [8] [100/400] eta: 0:01:47 lr: 0.000267 loss: 2.8801 (2.8973) grad: 0.0349 (0.0354) time: 0.3242 data: 0.0039 max mem: 3953 +train: [8] [120/400] eta: 0:01:40 lr: 0.000266 loss: 2.8588 (2.8913) grad: 0.0349 (0.0353) time: 0.3547 data: 0.0043 max mem: 3953 +train: [8] [140/400] eta: 0:01:33 lr: 0.000265 loss: 2.8558 (2.8890) grad: 0.0345 (0.0353) time: 0.3518 data: 0.0040 max mem: 3953 +train: [8] [160/400] eta: 0:01:24 lr: 0.000264 loss: 2.8766 (2.8909) grad: 0.0350 (0.0352) time: 0.3255 data: 0.0043 max mem: 3953 +train: [8] [180/400] eta: 0:01:17 lr: 0.000263 loss: 2.8772 (2.8903) grad: 0.0352 (0.0352) time: 0.3307 data: 0.0042 max mem: 3953 +train: [8] [200/400] eta: 0:01:10 lr: 0.000262 loss: 2.8821 (2.8905) grad: 0.0352 (0.0352) time: 0.3412 data: 0.0040 max mem: 3953 +train: [8] [220/400] eta: 0:01:02 lr: 0.000260 loss: 2.8952 (2.8917) grad: 0.0353 (0.0352) time: 0.3275 data: 0.0042 max mem: 3953 +train: [8] [240/400] eta: 0:00:55 lr: 0.000259 loss: 2.9084 (2.8928) grad: 0.0353 (0.0353) time: 0.3289 data: 0.0043 max mem: 3953 +train: [8] [260/400] eta: 0:00:48 lr: 0.000258 loss: 2.8958 (2.8921) grad: 0.0351 (0.0353) time: 0.3197 data: 0.0041 max mem: 3953 +train: [8] [280/400] eta: 0:00:41 lr: 0.000257 loss: 2.8898 (2.8941) grad: 0.0350 (0.0353) time: 0.3533 data: 0.0040 max mem: 3953 +train: [8] [300/400] eta: 0:00:34 lr: 0.000256 loss: 2.9117 (2.8953) grad: 0.0345 (0.0352) time: 0.3424 data: 0.0043 max mem: 3953 +train: [8] [320/400] eta: 0:00:27 lr: 0.000255 loss: 2.9177 (2.8976) grad: 0.0348 (0.0353) time: 0.3298 data: 0.0038 max mem: 3953 +train: [8] [340/400] eta: 0:00:20 lr: 0.000254 loss: 2.9148 (2.8987) grad: 0.0354 (0.0353) time: 0.3216 data: 0.0039 max mem: 3953 +train: [8] [360/400] eta: 0:00:13 lr: 0.000253 loss: 2.9140 (2.8989) grad: 0.0351 (0.0353) time: 0.3384 data: 0.0041 max mem: 3953 +train: [8] [380/400] eta: 0:00:06 lr: 0.000252 loss: 2.8803 (2.8974) grad: 0.0352 (0.0353) time: 0.3347 data: 0.0039 max mem: 3953 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.8790 (2.8969) grad: 0.0350 (0.0352) time: 0.3234 data: 0.0041 max mem: 3953 +train: [8] Total time: 0:02:16 (0.3415 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.8790 (2.8969) grad: 0.0350 (0.0352) +eval (validation): [8] [ 0/85] eta: 0:04:34 time: 3.2301 data: 3.0160 max mem: 3953 +eval (validation): [8] [20/85] eta: 0:00:29 time: 0.3170 data: 0.0052 max mem: 3953 +eval (validation): [8] [40/85] eta: 0:00:17 time: 0.3261 data: 0.0037 max mem: 3953 +eval (validation): [8] [60/85] eta: 0:00:09 time: 0.3146 data: 0.0040 max mem: 3953 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3052 data: 0.0043 max mem: 3953 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3009 data: 0.0042 max mem: 3953 +eval (validation): [8] Total time: 0:00:29 (0.3526 s / it) +cv: [8] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.669 acc: 0.217 f1: 0.151 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:22:07 lr: nan time: 3.3187 data: 3.1135 max mem: 3953 +train: [9] [ 20/400] eta: 0:02:59 lr: 0.000249 loss: 2.8928 (2.9208) grad: 0.0348 (0.0351) time: 0.3298 data: 0.0041 max mem: 3953 +train: [9] [ 40/400] eta: 0:02:31 lr: 0.000248 loss: 2.8828 (2.8946) grad: 0.0351 (0.0350) time: 0.3661 data: 0.0036 max mem: 3953 +train: [9] [ 60/400] eta: 0:02:13 lr: 0.000247 loss: 2.8723 (2.8886) grad: 0.0349 (0.0351) time: 0.3360 data: 0.0042 max mem: 3953 +train: [9] [ 80/400] eta: 0:02:02 lr: 0.000246 loss: 2.8688 (2.8869) grad: 0.0349 (0.0352) time: 0.3512 data: 0.0041 max mem: 3953 +train: [9] [100/400] eta: 0:01:51 lr: 0.000244 loss: 2.8718 (2.8868) grad: 0.0351 (0.0352) time: 0.3259 data: 0.0041 max mem: 3953 +train: [9] [120/400] eta: 0:01:41 lr: 0.000243 loss: 2.8683 (2.8826) grad: 0.0351 (0.0352) time: 0.3241 data: 0.0041 max mem: 3953 +train: [9] [140/400] eta: 0:01:33 lr: 0.000242 loss: 2.8683 (2.8853) grad: 0.0346 (0.0352) time: 0.3370 data: 0.0042 max mem: 3953 +train: [9] [160/400] eta: 0:01:25 lr: 0.000241 loss: 2.8689 (2.8833) grad: 0.0345 (0.0351) time: 0.3210 data: 0.0042 max mem: 3953 +train: [9] [180/400] eta: 0:01:17 lr: 0.000240 loss: 2.8689 (2.8861) grad: 0.0344 (0.0350) time: 0.3363 data: 0.0044 max mem: 3953 +train: [9] [200/400] eta: 0:01:10 lr: 0.000238 loss: 2.8833 (2.8843) grad: 0.0350 (0.0351) time: 0.3355 data: 0.0042 max mem: 3953 +train: [9] [220/400] eta: 0:01:02 lr: 0.000237 loss: 2.8823 (2.8840) grad: 0.0357 (0.0352) time: 0.3313 data: 0.0043 max mem: 3953 +train: [9] [240/400] eta: 0:00:55 lr: 0.000236 loss: 2.8623 (2.8818) grad: 0.0364 (0.0353) time: 0.3261 data: 0.0040 max mem: 3953 +train: [9] [260/400] eta: 0:00:48 lr: 0.000234 loss: 2.8528 (2.8818) grad: 0.0356 (0.0353) time: 0.3204 data: 0.0041 max mem: 3953 +train: [9] [280/400] eta: 0:00:41 lr: 0.000233 loss: 2.8720 (2.8812) grad: 0.0348 (0.0353) time: 0.3335 data: 0.0040 max mem: 3953 +train: [9] [300/400] eta: 0:00:34 lr: 0.000232 loss: 2.8951 (2.8833) grad: 0.0355 (0.0353) time: 0.3635 data: 0.0043 max mem: 3953 +train: [9] [320/400] eta: 0:00:27 lr: 0.000230 loss: 2.9032 (2.8858) grad: 0.0355 (0.0353) time: 0.3401 data: 0.0040 max mem: 3953 +train: [9] [340/400] eta: 0:00:20 lr: 0.000229 loss: 2.8828 (2.8857) grad: 0.0351 (0.0353) time: 0.3291 data: 0.0041 max mem: 3953 +train: [9] [360/400] eta: 0:00:13 lr: 0.000228 loss: 2.8903 (2.8863) grad: 0.0351 (0.0353) time: 0.3283 data: 0.0041 max mem: 3953 +train: [9] [380/400] eta: 0:00:06 lr: 0.000226 loss: 2.8821 (2.8855) grad: 0.0354 (0.0353) time: 0.3273 data: 0.0041 max mem: 3953 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.8672 (2.8850) grad: 0.0355 (0.0353) time: 0.3257 data: 0.0041 max mem: 3953 +train: [9] Total time: 0:02:16 (0.3421 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.8672 (2.8850) grad: 0.0355 (0.0353) +eval (validation): [9] [ 0/85] eta: 0:04:47 time: 3.3774 data: 3.1690 max mem: 3953 +eval (validation): [9] [20/85] eta: 0:00:31 time: 0.3338 data: 0.0042 max mem: 3953 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3342 data: 0.0040 max mem: 3953 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3207 data: 0.0042 max mem: 3953 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3299 data: 0.0044 max mem: 3953 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3244 data: 0.0043 max mem: 3953 +eval (validation): [9] Total time: 0:00:31 (0.3672 s / it) +cv: [9] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 2.675 acc: 0.216 f1: 0.150 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:21:15 lr: nan time: 3.1877 data: 2.9744 max mem: 3953 +train: [10] [ 20/400] eta: 0:03:03 lr: 0.000224 loss: 2.8736 (2.8816) grad: 0.0348 (0.0347) time: 0.3485 data: 0.0077 max mem: 3953 +train: [10] [ 40/400] eta: 0:02:29 lr: 0.000222 loss: 2.8736 (2.8820) grad: 0.0350 (0.0351) time: 0.3452 data: 0.0039 max mem: 3953 +train: [10] [ 60/400] eta: 0:02:14 lr: 0.000221 loss: 2.8482 (2.8706) grad: 0.0355 (0.0353) time: 0.3492 data: 0.0040 max mem: 3953 +train: [10] [ 80/400] eta: 0:02:01 lr: 0.000220 loss: 2.8576 (2.8723) grad: 0.0353 (0.0352) time: 0.3295 data: 0.0040 max mem: 3953 +train: [10] [100/400] eta: 0:01:50 lr: 0.000218 loss: 2.8764 (2.8749) grad: 0.0351 (0.0353) time: 0.3226 data: 0.0041 max mem: 3953 +train: [10] [120/400] eta: 0:01:41 lr: 0.000217 loss: 2.9096 (2.8802) grad: 0.0351 (0.0353) time: 0.3369 data: 0.0040 max mem: 3953 +train: [10] [140/400] eta: 0:01:32 lr: 0.000215 loss: 2.8913 (2.8795) grad: 0.0356 (0.0354) time: 0.3274 data: 0.0041 max mem: 3953 +train: [10] [160/400] eta: 0:01:24 lr: 0.000214 loss: 2.8682 (2.8807) grad: 0.0356 (0.0353) time: 0.3299 data: 0.0039 max mem: 3953 +train: [10] [180/400] eta: 0:01:17 lr: 0.000213 loss: 2.8777 (2.8817) grad: 0.0355 (0.0354) time: 0.3413 data: 0.0041 max mem: 3953 +train: [10] [200/400] eta: 0:01:10 lr: 0.000211 loss: 2.8876 (2.8833) grad: 0.0355 (0.0354) time: 0.3501 data: 0.0039 max mem: 3953 +train: [10] [220/400] eta: 0:01:03 lr: 0.000210 loss: 2.8813 (2.8809) grad: 0.0354 (0.0354) time: 0.3404 data: 0.0041 max mem: 3953 +train: [10] [240/400] eta: 0:00:55 lr: 0.000208 loss: 2.8546 (2.8792) grad: 0.0346 (0.0353) time: 0.3356 data: 0.0043 max mem: 3953 +train: [10] [260/400] eta: 0:00:48 lr: 0.000207 loss: 2.8615 (2.8787) grad: 0.0348 (0.0353) time: 0.3293 data: 0.0041 max mem: 3953 +train: [10] [280/400] eta: 0:00:41 lr: 0.000205 loss: 2.8615 (2.8779) grad: 0.0347 (0.0352) time: 0.3364 data: 0.0038 max mem: 3953 +train: [10] [300/400] eta: 0:00:34 lr: 0.000204 loss: 2.8794 (2.8782) grad: 0.0347 (0.0353) time: 0.3621 data: 0.0041 max mem: 3953 +train: [10] [320/400] eta: 0:00:27 lr: 0.000202 loss: 2.9049 (2.8784) grad: 0.0350 (0.0353) time: 0.3429 data: 0.0041 max mem: 3953 +train: [10] [340/400] eta: 0:00:20 lr: 0.000201 loss: 2.8728 (2.8781) grad: 0.0349 (0.0352) time: 0.3373 data: 0.0040 max mem: 3953 +train: [10] [360/400] eta: 0:00:13 lr: 0.000199 loss: 2.8727 (2.8785) grad: 0.0346 (0.0352) time: 0.3332 data: 0.0040 max mem: 3953 +train: [10] [380/400] eta: 0:00:06 lr: 0.000198 loss: 2.8708 (2.8776) grad: 0.0346 (0.0352) time: 0.3336 data: 0.0040 max mem: 3953 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.8708 (2.8785) grad: 0.0355 (0.0353) time: 0.3296 data: 0.0041 max mem: 3953 +train: [10] Total time: 0:02:18 (0.3455 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.8708 (2.8785) grad: 0.0355 (0.0353) +eval (validation): [10] [ 0/85] eta: 0:04:38 time: 3.2786 data: 3.0106 max mem: 3953 +eval (validation): [10] [20/85] eta: 0:00:31 time: 0.3466 data: 0.0040 max mem: 3953 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3170 data: 0.0039 max mem: 3953 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3173 data: 0.0042 max mem: 3953 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3253 data: 0.0040 max mem: 3953 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3202 data: 0.0040 max mem: 3953 +eval (validation): [10] Total time: 0:00:30 (0.3627 s / it) +cv: [10] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 2.662 acc: 0.223 f1: 0.162 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:21:59 lr: nan time: 3.3000 data: 3.0995 max mem: 3953 +train: [11] [ 20/400] eta: 0:03:08 lr: 0.000195 loss: 2.8287 (2.8388) grad: 0.0357 (0.0352) time: 0.3545 data: 0.0042 max mem: 3953 +train: [11] [ 40/400] eta: 0:02:29 lr: 0.000193 loss: 2.8411 (2.8572) grad: 0.0357 (0.0354) time: 0.3333 data: 0.0032 max mem: 3953 +train: [11] [ 60/400] eta: 0:02:11 lr: 0.000192 loss: 2.8813 (2.8713) grad: 0.0357 (0.0357) time: 0.3278 data: 0.0042 max mem: 3953 +train: [11] [ 80/400] eta: 0:02:00 lr: 0.000190 loss: 2.8761 (2.8647) grad: 0.0353 (0.0355) time: 0.3398 data: 0.0043 max mem: 3953 +train: [11] [100/400] eta: 0:01:51 lr: 0.000189 loss: 2.8570 (2.8676) grad: 0.0350 (0.0355) time: 0.3535 data: 0.0040 max mem: 3953 +train: [11] [120/400] eta: 0:01:42 lr: 0.000187 loss: 2.8570 (2.8655) grad: 0.0348 (0.0355) time: 0.3386 data: 0.0041 max mem: 3953 +train: [11] [140/400] eta: 0:01:34 lr: 0.000186 loss: 2.8549 (2.8643) grad: 0.0348 (0.0354) time: 0.3393 data: 0.0043 max mem: 3953 +train: [11] [160/400] eta: 0:01:26 lr: 0.000184 loss: 2.8414 (2.8655) grad: 0.0354 (0.0355) time: 0.3353 data: 0.0040 max mem: 3953 +train: [11] [180/400] eta: 0:01:18 lr: 0.000183 loss: 2.8563 (2.8670) grad: 0.0354 (0.0354) time: 0.3410 data: 0.0040 max mem: 3953 +train: [11] [200/400] eta: 0:01:11 lr: 0.000181 loss: 2.8666 (2.8661) grad: 0.0350 (0.0355) time: 0.3569 data: 0.0042 max mem: 3953 +train: [11] [220/400] eta: 0:01:04 lr: 0.000180 loss: 2.8666 (2.8661) grad: 0.0353 (0.0354) time: 0.3523 data: 0.0042 max mem: 3953 +train: [11] [240/400] eta: 0:00:56 lr: 0.000178 loss: 2.8644 (2.8677) grad: 0.0346 (0.0354) time: 0.3304 data: 0.0044 max mem: 3953 +train: [11] [260/400] eta: 0:00:49 lr: 0.000177 loss: 2.8582 (2.8685) grad: 0.0347 (0.0353) time: 0.3235 data: 0.0038 max mem: 3953 +train: [11] [280/400] eta: 0:00:42 lr: 0.000175 loss: 2.8546 (2.8673) grad: 0.0347 (0.0353) time: 0.3294 data: 0.0039 max mem: 3953 +train: [11] [300/400] eta: 0:00:34 lr: 0.000174 loss: 2.8748 (2.8669) grad: 0.0351 (0.0354) time: 0.3405 data: 0.0040 max mem: 3953 +train: [11] [320/400] eta: 0:00:27 lr: 0.000172 loss: 2.8853 (2.8690) grad: 0.0351 (0.0353) time: 0.3419 data: 0.0037 max mem: 3953 +train: [11] [340/400] eta: 0:00:21 lr: 0.000170 loss: 2.8861 (2.8705) grad: 0.0349 (0.0353) time: 0.3659 data: 0.0046 max mem: 3953 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 2.8651 (2.8695) grad: 0.0345 (0.0353) time: 0.3661 data: 0.0047 max mem: 3953 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 2.8591 (2.8700) grad: 0.0349 (0.0353) time: 0.3772 data: 0.0040 max mem: 3953 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.8617 (2.8700) grad: 0.0356 (0.0353) time: 0.3661 data: 0.0042 max mem: 3953 +train: [11] Total time: 0:02:21 (0.3531 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.8617 (2.8700) grad: 0.0356 (0.0353) +eval (validation): [11] [ 0/85] eta: 0:04:43 time: 3.3328 data: 3.0826 max mem: 3953 +eval (validation): [11] [20/85] eta: 0:00:30 time: 0.3266 data: 0.0042 max mem: 3953 +eval (validation): [11] [40/85] eta: 0:00:18 time: 0.3606 data: 0.0044 max mem: 3953 +eval (validation): [11] [60/85] eta: 0:00:10 time: 0.3666 data: 0.0051 max mem: 3953 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3287 data: 0.0041 max mem: 3953 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3009 data: 0.0039 max mem: 3953 +eval (validation): [11] Total time: 0:00:32 (0.3805 s / it) +cv: [11] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.659 acc: 0.223 f1: 0.155 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:21:32 lr: nan time: 3.2320 data: 3.0203 max mem: 3953 +train: [12] [ 20/400] eta: 0:02:59 lr: 0.000164 loss: 2.8309 (2.8413) grad: 0.0347 (0.0349) time: 0.3349 data: 0.0049 max mem: 3953 +train: [12] [ 40/400] eta: 0:02:25 lr: 0.000163 loss: 2.8381 (2.8526) grad: 0.0347 (0.0348) time: 0.3333 data: 0.0037 max mem: 3953 +train: [12] [ 60/400] eta: 0:02:09 lr: 0.000161 loss: 2.8627 (2.8587) grad: 0.0347 (0.0348) time: 0.3348 data: 0.0045 max mem: 3953 +train: [12] [ 80/400] eta: 0:01:58 lr: 0.000160 loss: 2.8517 (2.8504) grad: 0.0352 (0.0351) time: 0.3309 data: 0.0037 max mem: 3953 +train: [12] [100/400] eta: 0:01:49 lr: 0.000158 loss: 2.8517 (2.8573) grad: 0.0352 (0.0352) time: 0.3464 data: 0.0042 max mem: 3953 +train: [12] [120/400] eta: 0:01:41 lr: 0.000156 loss: 2.8770 (2.8597) grad: 0.0350 (0.0352) time: 0.3448 data: 0.0043 max mem: 3953 +train: [12] [140/400] eta: 0:01:34 lr: 0.000155 loss: 2.8599 (2.8602) grad: 0.0343 (0.0351) time: 0.3651 data: 0.0045 max mem: 3953 +train: [12] [160/400] eta: 0:01:27 lr: 0.000153 loss: 2.8385 (2.8574) grad: 0.0350 (0.0352) time: 0.3690 data: 0.0040 max mem: 3953 +train: [12] [180/400] eta: 0:01:19 lr: 0.000152 loss: 2.8568 (2.8609) grad: 0.0350 (0.0351) time: 0.3330 data: 0.0041 max mem: 3953 +train: [12] [200/400] eta: 0:01:12 lr: 0.000150 loss: 2.8685 (2.8617) grad: 0.0348 (0.0352) time: 0.3747 data: 0.0042 max mem: 3953 +train: [12] [220/400] eta: 0:01:04 lr: 0.000149 loss: 2.8397 (2.8592) grad: 0.0350 (0.0351) time: 0.3314 data: 0.0040 max mem: 3953 +train: [12] [240/400] eta: 0:00:56 lr: 0.000147 loss: 2.8504 (2.8605) grad: 0.0348 (0.0351) time: 0.3305 data: 0.0040 max mem: 3953 +train: [12] [260/400] eta: 0:00:49 lr: 0.000145 loss: 2.8618 (2.8577) grad: 0.0348 (0.0351) time: 0.3312 data: 0.0039 max mem: 3953 +train: [12] [280/400] eta: 0:00:42 lr: 0.000144 loss: 2.8618 (2.8589) grad: 0.0347 (0.0351) time: 0.3689 data: 0.0053 max mem: 3953 +train: [12] [300/400] eta: 0:00:35 lr: 0.000142 loss: 2.8349 (2.8563) grad: 0.0347 (0.0350) time: 0.3364 data: 0.0036 max mem: 3953 +train: [12] [320/400] eta: 0:00:28 lr: 0.000141 loss: 2.8349 (2.8565) grad: 0.0349 (0.0350) time: 0.3443 data: 0.0040 max mem: 3953 +train: [12] [340/400] eta: 0:00:21 lr: 0.000139 loss: 2.8753 (2.8591) grad: 0.0350 (0.0350) time: 0.3335 data: 0.0039 max mem: 3953 +train: [12] [360/400] eta: 0:00:14 lr: 0.000138 loss: 2.9103 (2.8621) grad: 0.0347 (0.0350) time: 0.3353 data: 0.0040 max mem: 3953 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 2.8852 (2.8624) grad: 0.0348 (0.0350) time: 0.3460 data: 0.0038 max mem: 3953 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.8503 (2.8621) grad: 0.0358 (0.0351) time: 0.3475 data: 0.0040 max mem: 3953 +train: [12] Total time: 0:02:20 (0.3510 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.8503 (2.8621) grad: 0.0358 (0.0351) +eval (validation): [12] [ 0/85] eta: 0:04:44 time: 3.3499 data: 3.0977 max mem: 3953 +eval (validation): [12] [20/85] eta: 0:00:31 time: 0.3411 data: 0.0206 max mem: 3953 +eval (validation): [12] [40/85] eta: 0:00:18 time: 0.3347 data: 0.0199 max mem: 3953 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3389 data: 0.0134 max mem: 3953 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3232 data: 0.0042 max mem: 3953 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3104 data: 0.0028 max mem: 3953 +eval (validation): [12] Total time: 0:00:31 (0.3702 s / it) +cv: [12] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.662 acc: 0.216 f1: 0.155 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:21:26 lr: nan time: 3.2172 data: 3.0083 max mem: 3953 +train: [13] [ 20/400] eta: 0:03:08 lr: 0.000133 loss: 2.8093 (2.8481) grad: 0.0343 (0.0348) time: 0.3608 data: 0.0048 max mem: 3953 +train: [13] [ 40/400] eta: 0:02:31 lr: 0.000131 loss: 2.8211 (2.8410) grad: 0.0343 (0.0348) time: 0.3431 data: 0.0041 max mem: 3953 +train: [13] [ 60/400] eta: 0:02:13 lr: 0.000130 loss: 2.8375 (2.8456) grad: 0.0349 (0.0351) time: 0.3344 data: 0.0041 max mem: 3953 +train: [13] [ 80/400] eta: 0:02:02 lr: 0.000128 loss: 2.8496 (2.8484) grad: 0.0353 (0.0351) time: 0.3450 data: 0.0043 max mem: 3953 +train: [13] [100/400] eta: 0:01:51 lr: 0.000127 loss: 2.8496 (2.8508) grad: 0.0351 (0.0351) time: 0.3274 data: 0.0041 max mem: 3953 +train: [13] [120/400] eta: 0:01:42 lr: 0.000125 loss: 2.8621 (2.8524) grad: 0.0347 (0.0352) time: 0.3401 data: 0.0041 max mem: 3953 +train: [13] [140/400] eta: 0:01:34 lr: 0.000124 loss: 2.8649 (2.8538) grad: 0.0348 (0.0351) time: 0.3616 data: 0.0046 max mem: 3953 +train: [13] [160/400] eta: 0:01:26 lr: 0.000122 loss: 2.8649 (2.8545) grad: 0.0349 (0.0351) time: 0.3312 data: 0.0042 max mem: 3953 +train: [13] [180/400] eta: 0:01:18 lr: 0.000120 loss: 2.8540 (2.8526) grad: 0.0352 (0.0351) time: 0.3334 data: 0.0044 max mem: 3953 +train: [13] [200/400] eta: 0:01:10 lr: 0.000119 loss: 2.8355 (2.8544) grad: 0.0354 (0.0352) time: 0.3269 data: 0.0041 max mem: 3953 +train: [13] [220/400] eta: 0:01:03 lr: 0.000117 loss: 2.8487 (2.8530) grad: 0.0357 (0.0352) time: 0.3322 data: 0.0039 max mem: 3953 +train: [13] [240/400] eta: 0:00:56 lr: 0.000116 loss: 2.8467 (2.8520) grad: 0.0363 (0.0352) time: 0.3232 data: 0.0040 max mem: 3953 +train: [13] [260/400] eta: 0:00:48 lr: 0.000114 loss: 2.8625 (2.8540) grad: 0.0344 (0.0351) time: 0.3373 data: 0.0041 max mem: 3953 +train: [13] [280/400] eta: 0:00:41 lr: 0.000113 loss: 2.8625 (2.8535) grad: 0.0344 (0.0351) time: 0.3357 data: 0.0040 max mem: 3953 +train: [13] [300/400] eta: 0:00:34 lr: 0.000111 loss: 2.8481 (2.8533) grad: 0.0352 (0.0351) time: 0.3286 data: 0.0042 max mem: 3953 +train: [13] [320/400] eta: 0:00:27 lr: 0.000110 loss: 2.8474 (2.8540) grad: 0.0344 (0.0351) time: 0.3278 data: 0.0043 max mem: 3953 +train: [13] [340/400] eta: 0:00:20 lr: 0.000108 loss: 2.8508 (2.8516) grad: 0.0345 (0.0351) time: 0.3315 data: 0.0041 max mem: 3953 +train: [13] [360/400] eta: 0:00:13 lr: 0.000107 loss: 2.8464 (2.8525) grad: 0.0346 (0.0351) time: 0.3235 data: 0.0040 max mem: 3953 +train: [13] [380/400] eta: 0:00:06 lr: 0.000105 loss: 2.8682 (2.8535) grad: 0.0351 (0.0351) time: 0.3250 data: 0.0043 max mem: 3953 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.8587 (2.8527) grad: 0.0354 (0.0351) time: 0.3366 data: 0.0041 max mem: 3953 +train: [13] Total time: 0:02:17 (0.3428 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.8587 (2.8527) grad: 0.0354 (0.0351) +eval (validation): [13] [ 0/85] eta: 0:04:44 time: 3.3528 data: 3.1464 max mem: 3953 +eval (validation): [13] [20/85] eta: 0:00:32 time: 0.3579 data: 0.0151 max mem: 3953 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3441 data: 0.0062 max mem: 3953 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3705 data: 0.0035 max mem: 3953 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3192 data: 0.0036 max mem: 3953 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.2980 data: 0.0026 max mem: 3953 +eval (validation): [13] Total time: 0:00:32 (0.3843 s / it) +cv: [13] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 2.656 acc: 0.228 f1: 0.161 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:27:45 lr: nan time: 4.1647 data: 3.9076 max mem: 3953 +train: [14] [ 20/400] eta: 0:03:31 lr: 0.000102 loss: 2.8296 (2.8481) grad: 0.0350 (0.0355) time: 0.3765 data: 0.0046 max mem: 3953 +train: [14] [ 40/400] eta: 0:02:41 lr: 0.000101 loss: 2.8493 (2.8707) grad: 0.0349 (0.0354) time: 0.3345 data: 0.0041 max mem: 3953 +train: [14] [ 60/400] eta: 0:02:19 lr: 0.000099 loss: 2.8816 (2.8728) grad: 0.0349 (0.0352) time: 0.3361 data: 0.0040 max mem: 3953 +train: [14] [ 80/400] eta: 0:02:06 lr: 0.000098 loss: 2.8786 (2.8771) grad: 0.0341 (0.0348) time: 0.3440 data: 0.0043 max mem: 3953 +train: [14] [100/400] eta: 0:01:55 lr: 0.000096 loss: 2.8499 (2.8707) grad: 0.0338 (0.0349) time: 0.3453 data: 0.0039 max mem: 3953 +train: [14] [120/400] eta: 0:01:46 lr: 0.000095 loss: 2.8372 (2.8635) grad: 0.0346 (0.0348) time: 0.3510 data: 0.0038 max mem: 3953 +train: [14] [140/400] eta: 0:01:37 lr: 0.000093 loss: 2.8600 (2.8621) grad: 0.0349 (0.0349) time: 0.3502 data: 0.0038 max mem: 3953 +train: [14] [160/400] eta: 0:01:29 lr: 0.000092 loss: 2.8626 (2.8637) grad: 0.0352 (0.0350) time: 0.3534 data: 0.0045 max mem: 3953 +train: [14] [180/400] eta: 0:01:21 lr: 0.000090 loss: 2.8448 (2.8613) grad: 0.0351 (0.0350) time: 0.3475 data: 0.0040 max mem: 3953 +train: [14] [200/400] eta: 0:01:13 lr: 0.000089 loss: 2.8413 (2.8599) grad: 0.0349 (0.0350) time: 0.3444 data: 0.0036 max mem: 3953 +train: [14] [220/400] eta: 0:01:05 lr: 0.000088 loss: 2.8395 (2.8582) grad: 0.0351 (0.0350) time: 0.3413 data: 0.0039 max mem: 3953 +train: [14] [240/400] eta: 0:00:58 lr: 0.000086 loss: 2.8418 (2.8574) grad: 0.0352 (0.0350) time: 0.3367 data: 0.0040 max mem: 3953 +train: [14] [260/400] eta: 0:00:50 lr: 0.000085 loss: 2.8718 (2.8576) grad: 0.0352 (0.0350) time: 0.3725 data: 0.0041 max mem: 3953 +train: [14] [280/400] eta: 0:00:43 lr: 0.000083 loss: 2.8524 (2.8568) grad: 0.0343 (0.0350) time: 0.3430 data: 0.0044 max mem: 3953 +train: [14] [300/400] eta: 0:00:36 lr: 0.000082 loss: 2.8548 (2.8579) grad: 0.0343 (0.0350) time: 0.3541 data: 0.0044 max mem: 3953 +train: [14] [320/400] eta: 0:00:28 lr: 0.000081 loss: 2.8548 (2.8570) grad: 0.0347 (0.0350) time: 0.3422 data: 0.0043 max mem: 3953 +train: [14] [340/400] eta: 0:00:21 lr: 0.000079 loss: 2.8795 (2.8591) grad: 0.0353 (0.0350) time: 0.3358 data: 0.0041 max mem: 3953 +train: [14] [360/400] eta: 0:00:14 lr: 0.000078 loss: 2.8786 (2.8593) grad: 0.0350 (0.0350) time: 0.3327 data: 0.0039 max mem: 3953 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 2.8595 (2.8583) grad: 0.0350 (0.0350) time: 0.3297 data: 0.0038 max mem: 3953 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.8539 (2.8579) grad: 0.0350 (0.0350) time: 0.3438 data: 0.0043 max mem: 3953 +train: [14] Total time: 0:02:22 (0.3555 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.8539 (2.8579) grad: 0.0350 (0.0350) +eval (validation): [14] [ 0/85] eta: 0:04:41 time: 3.3072 data: 3.0916 max mem: 3953 +eval (validation): [14] [20/85] eta: 0:00:31 time: 0.3356 data: 0.0129 max mem: 3953 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3668 data: 0.0084 max mem: 3953 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3229 data: 0.0043 max mem: 3953 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3104 data: 0.0036 max mem: 3953 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3046 data: 0.0038 max mem: 3953 +eval (validation): [14] Total time: 0:00:31 (0.3706 s / it) +cv: [14] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.652 acc: 0.226 f1: 0.161 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:22:52 lr: nan time: 3.4314 data: 3.2187 max mem: 3953 +train: [15] [ 20/400] eta: 0:02:59 lr: 0.000074 loss: 2.8604 (2.8384) grad: 0.0350 (0.0354) time: 0.3241 data: 0.0044 max mem: 3953 +train: [15] [ 40/400] eta: 0:02:27 lr: 0.000072 loss: 2.8344 (2.8302) grad: 0.0347 (0.0351) time: 0.3446 data: 0.0038 max mem: 3953 +train: [15] [ 60/400] eta: 0:02:11 lr: 0.000071 loss: 2.8131 (2.8308) grad: 0.0340 (0.0350) time: 0.3409 data: 0.0041 max mem: 3953 +train: [15] [ 80/400] eta: 0:01:59 lr: 0.000070 loss: 2.8011 (2.8229) grad: 0.0343 (0.0348) time: 0.3318 data: 0.0043 max mem: 3953 +train: [15] [100/400] eta: 0:01:49 lr: 0.000068 loss: 2.8123 (2.8286) grad: 0.0343 (0.0348) time: 0.3346 data: 0.0037 max mem: 3953 +train: [15] [120/400] eta: 0:01:40 lr: 0.000067 loss: 2.8334 (2.8282) grad: 0.0349 (0.0349) time: 0.3306 data: 0.0039 max mem: 3953 +train: [15] [140/400] eta: 0:01:32 lr: 0.000066 loss: 2.8290 (2.8287) grad: 0.0352 (0.0350) time: 0.3278 data: 0.0038 max mem: 3953 +train: [15] [160/400] eta: 0:01:24 lr: 0.000064 loss: 2.8336 (2.8300) grad: 0.0354 (0.0350) time: 0.3439 data: 0.0042 max mem: 3953 +train: [15] [180/400] eta: 0:01:17 lr: 0.000063 loss: 2.8486 (2.8331) grad: 0.0354 (0.0351) time: 0.3448 data: 0.0040 max mem: 3953 +train: [15] [200/400] eta: 0:01:10 lr: 0.000062 loss: 2.8611 (2.8360) grad: 0.0351 (0.0351) time: 0.3328 data: 0.0045 max mem: 3953 +train: [15] [220/400] eta: 0:01:03 lr: 0.000061 loss: 2.8534 (2.8383) grad: 0.0347 (0.0350) time: 0.3544 data: 0.0042 max mem: 3953 +train: [15] [240/400] eta: 0:00:55 lr: 0.000059 loss: 2.8682 (2.8411) grad: 0.0347 (0.0351) time: 0.3338 data: 0.0041 max mem: 3953 +train: [15] [260/400] eta: 0:00:48 lr: 0.000058 loss: 2.8690 (2.8419) grad: 0.0346 (0.0350) time: 0.3498 data: 0.0042 max mem: 3953 +train: [15] [280/400] eta: 0:00:41 lr: 0.000057 loss: 2.8563 (2.8448) grad: 0.0351 (0.0350) time: 0.3420 data: 0.0037 max mem: 3953 +train: [15] [300/400] eta: 0:00:34 lr: 0.000056 loss: 2.8558 (2.8460) grad: 0.0352 (0.0351) time: 0.3589 data: 0.0040 max mem: 3953 +train: [15] [320/400] eta: 0:00:27 lr: 0.000054 loss: 2.8773 (2.8482) grad: 0.0356 (0.0351) time: 0.3373 data: 0.0043 max mem: 3953 +train: [15] [340/400] eta: 0:00:20 lr: 0.000053 loss: 2.8422 (2.8475) grad: 0.0355 (0.0351) time: 0.3416 data: 0.0043 max mem: 3953 +train: [15] [360/400] eta: 0:00:13 lr: 0.000052 loss: 2.8422 (2.8485) grad: 0.0346 (0.0351) time: 0.3255 data: 0.0044 max mem: 3953 +train: [15] [380/400] eta: 0:00:06 lr: 0.000051 loss: 2.8290 (2.8471) grad: 0.0346 (0.0351) time: 0.3221 data: 0.0038 max mem: 3953 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.8386 (2.8485) grad: 0.0349 (0.0351) time: 0.3661 data: 0.0043 max mem: 3953 +train: [15] Total time: 0:02:18 (0.3473 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.8386 (2.8485) grad: 0.0349 (0.0351) +eval (validation): [15] [ 0/85] eta: 0:04:50 time: 3.4146 data: 3.1544 max mem: 3953 +eval (validation): [15] [20/85] eta: 0:00:36 time: 0.4217 data: 0.0080 max mem: 3953 +eval (validation): [15] [40/85] eta: 0:00:20 time: 0.3468 data: 0.0040 max mem: 3953 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3248 data: 0.0045 max mem: 3953 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3168 data: 0.0045 max mem: 3953 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3103 data: 0.0040 max mem: 3953 +eval (validation): [15] Total time: 0:00:33 (0.3896 s / it) +cv: [15] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.652 acc: 0.225 f1: 0.160 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:26 lr: nan time: 3.3665 data: 3.1440 max mem: 3953 +train: [16] [ 20/400] eta: 0:03:21 lr: 0.000048 loss: 2.8195 (2.8376) grad: 0.0343 (0.0345) time: 0.3894 data: 0.0167 max mem: 3953 +train: [16] [ 40/400] eta: 0:02:36 lr: 0.000047 loss: 2.8372 (2.8387) grad: 0.0344 (0.0347) time: 0.3306 data: 0.0035 max mem: 3953 +train: [16] [ 60/400] eta: 0:02:20 lr: 0.000046 loss: 2.8491 (2.8506) grad: 0.0352 (0.0350) time: 0.3733 data: 0.0044 max mem: 3953 +train: [16] [ 80/400] eta: 0:02:09 lr: 0.000045 loss: 2.8482 (2.8438) grad: 0.0345 (0.0349) time: 0.3817 data: 0.0045 max mem: 3953 +train: [16] [100/400] eta: 0:01:59 lr: 0.000044 loss: 2.8670 (2.8520) grad: 0.0345 (0.0351) time: 0.3610 data: 0.0043 max mem: 3953 +train: [16] [120/400] eta: 0:01:48 lr: 0.000043 loss: 2.8568 (2.8523) grad: 0.0351 (0.0350) time: 0.3379 data: 0.0042 max mem: 3953 +train: [16] [140/400] eta: 0:01:38 lr: 0.000042 loss: 2.8493 (2.8519) grad: 0.0344 (0.0350) time: 0.3363 data: 0.0043 max mem: 3953 +train: [16] [160/400] eta: 0:01:30 lr: 0.000041 loss: 2.8400 (2.8505) grad: 0.0350 (0.0350) time: 0.3561 data: 0.0036 max mem: 3953 +train: [16] [180/400] eta: 0:01:21 lr: 0.000040 loss: 2.8611 (2.8538) grad: 0.0350 (0.0350) time: 0.3373 data: 0.0042 max mem: 3953 +train: [16] [200/400] eta: 0:01:13 lr: 0.000039 loss: 2.8611 (2.8549) grad: 0.0350 (0.0351) time: 0.3366 data: 0.0040 max mem: 3953 +train: [16] [220/400] eta: 0:01:06 lr: 0.000038 loss: 2.8424 (2.8523) grad: 0.0349 (0.0350) time: 0.3439 data: 0.0041 max mem: 3953 +train: [16] [240/400] eta: 0:00:58 lr: 0.000036 loss: 2.8227 (2.8510) grad: 0.0356 (0.0351) time: 0.3477 data: 0.0041 max mem: 3953 +train: [16] [260/400] eta: 0:00:50 lr: 0.000035 loss: 2.8515 (2.8517) grad: 0.0355 (0.0351) time: 0.3502 data: 0.0042 max mem: 3953 +train: [16] [280/400] eta: 0:00:43 lr: 0.000034 loss: 2.8314 (2.8486) grad: 0.0350 (0.0351) time: 0.3461 data: 0.0039 max mem: 3953 +train: [16] [300/400] eta: 0:00:36 lr: 0.000033 loss: 2.8526 (2.8499) grad: 0.0348 (0.0351) time: 0.3471 data: 0.0041 max mem: 3953 +train: [16] [320/400] eta: 0:00:28 lr: 0.000032 loss: 2.8625 (2.8505) grad: 0.0351 (0.0351) time: 0.3389 data: 0.0040 max mem: 3953 +train: [16] [340/400] eta: 0:00:21 lr: 0.000031 loss: 2.8276 (2.8476) grad: 0.0344 (0.0351) time: 0.3474 data: 0.0042 max mem: 3953 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 2.8100 (2.8474) grad: 0.0346 (0.0351) time: 0.3406 data: 0.0041 max mem: 3953 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 2.8374 (2.8469) grad: 0.0349 (0.0351) time: 0.3489 data: 0.0042 max mem: 3953 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.8312 (2.8460) grad: 0.0350 (0.0351) time: 0.3518 data: 0.0041 max mem: 3953 +train: [16] Total time: 0:02:23 (0.3579 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.8312 (2.8460) grad: 0.0350 (0.0351) +eval (validation): [16] [ 0/85] eta: 0:04:38 time: 3.2796 data: 3.0323 max mem: 3953 +eval (validation): [16] [20/85] eta: 0:00:31 time: 0.3496 data: 0.0054 max mem: 3953 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3355 data: 0.0042 max mem: 3953 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3377 data: 0.0041 max mem: 3953 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3115 data: 0.0044 max mem: 3953 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3046 data: 0.0041 max mem: 3953 +eval (validation): [16] Total time: 0:00:31 (0.3705 s / it) +cv: [16] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.651 acc: 0.224 f1: 0.158 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:40 lr: nan time: 3.4023 data: 3.1806 max mem: 3953 +train: [17] [ 20/400] eta: 0:03:08 lr: 0.000028 loss: 2.8473 (2.8475) grad: 0.0353 (0.0349) time: 0.3505 data: 0.0126 max mem: 3953 +train: [17] [ 40/400] eta: 0:02:32 lr: 0.000027 loss: 2.8494 (2.8542) grad: 0.0353 (0.0352) time: 0.3476 data: 0.0041 max mem: 3953 +train: [17] [ 60/400] eta: 0:02:15 lr: 0.000026 loss: 2.8594 (2.8536) grad: 0.0351 (0.0351) time: 0.3483 data: 0.0038 max mem: 3953 +train: [17] [ 80/400] eta: 0:02:03 lr: 0.000025 loss: 2.8311 (2.8496) grad: 0.0349 (0.0351) time: 0.3469 data: 0.0037 max mem: 3953 +train: [17] [100/400] eta: 0:01:53 lr: 0.000024 loss: 2.8254 (2.8483) grad: 0.0350 (0.0351) time: 0.3458 data: 0.0038 max mem: 3953 +train: [17] [120/400] eta: 0:01:45 lr: 0.000023 loss: 2.8339 (2.8456) grad: 0.0351 (0.0351) time: 0.3606 data: 0.0043 max mem: 3953 +train: [17] [140/400] eta: 0:01:35 lr: 0.000023 loss: 2.8339 (2.8446) grad: 0.0354 (0.0352) time: 0.3247 data: 0.0039 max mem: 3953 +train: [17] [160/400] eta: 0:01:27 lr: 0.000022 loss: 2.7979 (2.8428) grad: 0.0359 (0.0353) time: 0.3567 data: 0.0043 max mem: 3953 +train: [17] [180/400] eta: 0:01:20 lr: 0.000021 loss: 2.8624 (2.8446) grad: 0.0355 (0.0353) time: 0.3454 data: 0.0040 max mem: 3953 +train: [17] [200/400] eta: 0:01:12 lr: 0.000020 loss: 2.8443 (2.8421) grad: 0.0355 (0.0354) time: 0.3469 data: 0.0040 max mem: 3953 +train: [17] [220/400] eta: 0:01:04 lr: 0.000019 loss: 2.8265 (2.8397) grad: 0.0355 (0.0354) time: 0.3412 data: 0.0040 max mem: 3953 +train: [17] [240/400] eta: 0:00:57 lr: 0.000019 loss: 2.8284 (2.8390) grad: 0.0344 (0.0354) time: 0.3325 data: 0.0040 max mem: 3953 +train: [17] [260/400] eta: 0:00:50 lr: 0.000018 loss: 2.8395 (2.8398) grad: 0.0344 (0.0353) time: 0.3553 data: 0.0045 max mem: 3953 +train: [17] [280/400] eta: 0:00:42 lr: 0.000017 loss: 2.8429 (2.8388) grad: 0.0346 (0.0353) time: 0.3546 data: 0.0040 max mem: 3953 +train: [17] [300/400] eta: 0:00:35 lr: 0.000016 loss: 2.8391 (2.8393) grad: 0.0348 (0.0353) time: 0.3468 data: 0.0042 max mem: 3953 +train: [17] [320/400] eta: 0:00:28 lr: 0.000016 loss: 2.8462 (2.8389) grad: 0.0353 (0.0353) time: 0.3451 data: 0.0046 max mem: 3953 +train: [17] [340/400] eta: 0:00:21 lr: 0.000015 loss: 2.8414 (2.8377) grad: 0.0349 (0.0352) time: 0.3373 data: 0.0037 max mem: 3953 +train: [17] [360/400] eta: 0:00:14 lr: 0.000014 loss: 2.8141 (2.8387) grad: 0.0349 (0.0353) time: 0.3298 data: 0.0041 max mem: 3953 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 2.8277 (2.8385) grad: 0.0350 (0.0352) time: 0.3512 data: 0.0039 max mem: 3953 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.8402 (2.8392) grad: 0.0348 (0.0352) time: 0.3352 data: 0.0042 max mem: 3953 +train: [17] Total time: 0:02:21 (0.3530 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.8402 (2.8392) grad: 0.0348 (0.0352) +eval (validation): [17] [ 0/85] eta: 0:04:52 time: 3.4412 data: 3.1734 max mem: 3953 +eval (validation): [17] [20/85] eta: 0:00:32 time: 0.3489 data: 0.0041 max mem: 3953 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3322 data: 0.0038 max mem: 3953 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3430 data: 0.0040 max mem: 3953 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3176 data: 0.0044 max mem: 3953 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3132 data: 0.0033 max mem: 3953 +eval (validation): [17] Total time: 0:00:31 (0.3744 s / it) +cv: [17] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.647 acc: 0.224 f1: 0.160 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:46 lr: nan time: 3.4171 data: 3.1962 max mem: 3953 +train: [18] [ 20/400] eta: 0:03:14 lr: 0.000012 loss: 2.8209 (2.8440) grad: 0.0353 (0.0351) time: 0.3666 data: 0.0117 max mem: 3953 +train: [18] [ 40/400] eta: 0:02:37 lr: 0.000012 loss: 2.8527 (2.8611) grad: 0.0347 (0.0351) time: 0.3618 data: 0.0038 max mem: 3953 +train: [18] [ 60/400] eta: 0:02:17 lr: 0.000011 loss: 2.8565 (2.8535) grad: 0.0350 (0.0350) time: 0.3353 data: 0.0043 max mem: 3953 +train: [18] [ 80/400] eta: 0:02:05 lr: 0.000011 loss: 2.8346 (2.8470) grad: 0.0351 (0.0350) time: 0.3560 data: 0.0038 max mem: 3953 +train: [18] [100/400] eta: 0:01:55 lr: 0.000010 loss: 2.8481 (2.8476) grad: 0.0350 (0.0351) time: 0.3497 data: 0.0044 max mem: 3953 +train: [18] [120/400] eta: 0:01:45 lr: 0.000009 loss: 2.8461 (2.8454) grad: 0.0348 (0.0350) time: 0.3470 data: 0.0043 max mem: 3953 +train: [18] [140/400] eta: 0:01:36 lr: 0.000009 loss: 2.8029 (2.8379) grad: 0.0347 (0.0350) time: 0.3409 data: 0.0041 max mem: 3953 +train: [18] [160/400] eta: 0:01:28 lr: 0.000008 loss: 2.8247 (2.8397) grad: 0.0343 (0.0349) time: 0.3474 data: 0.0044 max mem: 3953 +train: [18] [180/400] eta: 0:01:20 lr: 0.000008 loss: 2.8272 (2.8389) grad: 0.0343 (0.0349) time: 0.3420 data: 0.0044 max mem: 3953 +train: [18] [200/400] eta: 0:01:12 lr: 0.000007 loss: 2.8351 (2.8410) grad: 0.0352 (0.0350) time: 0.3448 data: 0.0041 max mem: 3953 +train: [18] [220/400] eta: 0:01:05 lr: 0.000007 loss: 2.8553 (2.8439) grad: 0.0354 (0.0350) time: 0.3358 data: 0.0044 max mem: 3953 +train: [18] [240/400] eta: 0:00:57 lr: 0.000006 loss: 2.8483 (2.8424) grad: 0.0345 (0.0349) time: 0.3425 data: 0.0040 max mem: 3953 +train: [18] [260/400] eta: 0:00:50 lr: 0.000006 loss: 2.8180 (2.8421) grad: 0.0346 (0.0349) time: 0.3515 data: 0.0042 max mem: 3953 +train: [18] [280/400] eta: 0:00:43 lr: 0.000006 loss: 2.8338 (2.8403) grad: 0.0349 (0.0349) time: 0.3427 data: 0.0041 max mem: 3953 +train: [18] [300/400] eta: 0:00:35 lr: 0.000005 loss: 2.8458 (2.8407) grad: 0.0349 (0.0350) time: 0.3302 data: 0.0043 max mem: 3953 +train: [18] [320/400] eta: 0:00:28 lr: 0.000005 loss: 2.8503 (2.8423) grad: 0.0349 (0.0350) time: 0.3306 data: 0.0038 max mem: 3953 +train: [18] [340/400] eta: 0:00:21 lr: 0.000004 loss: 2.8363 (2.8411) grad: 0.0348 (0.0349) time: 0.3517 data: 0.0040 max mem: 3953 +train: [18] [360/400] eta: 0:00:14 lr: 0.000004 loss: 2.8283 (2.8410) grad: 0.0344 (0.0350) time: 0.3360 data: 0.0041 max mem: 3953 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 2.8400 (2.8416) grad: 0.0347 (0.0350) time: 0.3619 data: 0.0040 max mem: 3953 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.8561 (2.8419) grad: 0.0343 (0.0349) time: 0.3505 data: 0.0040 max mem: 3953 +train: [18] Total time: 0:02:21 (0.3542 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.8561 (2.8419) grad: 0.0343 (0.0349) +eval (validation): [18] [ 0/85] eta: 0:04:38 time: 3.2729 data: 3.0569 max mem: 3953 +eval (validation): [18] [20/85] eta: 0:00:32 time: 0.3551 data: 0.0058 max mem: 3953 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3440 data: 0.0040 max mem: 3953 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3482 data: 0.0046 max mem: 3953 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3326 data: 0.0041 max mem: 3953 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3297 data: 0.0043 max mem: 3953 +eval (validation): [18] Total time: 0:00:32 (0.3804 s / it) +cv: [18] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.648 acc: 0.224 f1: 0.159 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:16 lr: nan time: 3.3424 data: 3.1251 max mem: 3953 +train: [19] [ 20/400] eta: 0:02:58 lr: 0.000003 loss: 2.8262 (2.8239) grad: 0.0349 (0.0350) time: 0.3258 data: 0.0051 max mem: 3953 +train: [19] [ 40/400] eta: 0:02:28 lr: 0.000003 loss: 2.8252 (2.8189) grad: 0.0349 (0.0349) time: 0.3546 data: 0.0041 max mem: 3953 +train: [19] [ 60/400] eta: 0:02:12 lr: 0.000002 loss: 2.8252 (2.8257) grad: 0.0341 (0.0348) time: 0.3427 data: 0.0047 max mem: 3953 +train: [19] [ 80/400] eta: 0:02:03 lr: 0.000002 loss: 2.8398 (2.8207) grad: 0.0341 (0.0347) time: 0.3781 data: 0.0032 max mem: 3953 +train: [19] [100/400] eta: 0:01:54 lr: 0.000002 loss: 2.8158 (2.8221) grad: 0.0347 (0.0348) time: 0.3546 data: 0.0045 max mem: 3953 +train: [19] [120/400] eta: 0:01:44 lr: 0.000002 loss: 2.8112 (2.8255) grad: 0.0350 (0.0348) time: 0.3343 data: 0.0035 max mem: 3953 +train: [19] [140/400] eta: 0:01:35 lr: 0.000001 loss: 2.8468 (2.8285) grad: 0.0349 (0.0349) time: 0.3348 data: 0.0041 max mem: 3953 +train: [19] [160/400] eta: 0:01:27 lr: 0.000001 loss: 2.8509 (2.8316) grad: 0.0349 (0.0349) time: 0.3379 data: 0.0039 max mem: 3953 +train: [19] [180/400] eta: 0:01:19 lr: 0.000001 loss: 2.8634 (2.8383) grad: 0.0349 (0.0349) time: 0.3306 data: 0.0039 max mem: 3953 +train: [19] [200/400] eta: 0:01:11 lr: 0.000001 loss: 2.8629 (2.8379) grad: 0.0349 (0.0349) time: 0.3335 data: 0.0042 max mem: 3953 +train: [19] [220/400] eta: 0:01:03 lr: 0.000001 loss: 2.8419 (2.8394) grad: 0.0351 (0.0350) time: 0.3289 data: 0.0040 max mem: 3953 +train: [19] [240/400] eta: 0:00:56 lr: 0.000001 loss: 2.8512 (2.8405) grad: 0.0350 (0.0350) time: 0.3373 data: 0.0043 max mem: 3953 +train: [19] [260/400] eta: 0:00:49 lr: 0.000000 loss: 2.8456 (2.8398) grad: 0.0354 (0.0350) time: 0.3339 data: 0.0041 max mem: 3953 +train: [19] [280/400] eta: 0:00:42 lr: 0.000000 loss: 2.8456 (2.8417) grad: 0.0350 (0.0350) time: 0.3272 data: 0.0039 max mem: 3953 +train: [19] [300/400] eta: 0:00:34 lr: 0.000000 loss: 2.8761 (2.8438) grad: 0.0348 (0.0350) time: 0.3284 data: 0.0042 max mem: 3953 +train: [19] [320/400] eta: 0:00:27 lr: 0.000000 loss: 2.8611 (2.8435) grad: 0.0357 (0.0350) time: 0.3440 data: 0.0039 max mem: 3953 +train: [19] [340/400] eta: 0:00:20 lr: 0.000000 loss: 2.8278 (2.8426) grad: 0.0357 (0.0351) time: 0.3423 data: 0.0045 max mem: 3953 +train: [19] [360/400] eta: 0:00:13 lr: 0.000000 loss: 2.8192 (2.8422) grad: 0.0352 (0.0351) time: 0.3230 data: 0.0035 max mem: 3953 +train: [19] [380/400] eta: 0:00:06 lr: 0.000000 loss: 2.8368 (2.8434) grad: 0.0349 (0.0351) time: 0.3287 data: 0.0044 max mem: 3953 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.8391 (2.8427) grad: 0.0348 (0.0351) time: 0.3400 data: 0.0038 max mem: 3953 +train: [19] Total time: 0:02:18 (0.3458 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.8391 (2.8427) grad: 0.0348 (0.0351) +eval (validation): [19] [ 0/85] eta: 0:04:46 time: 3.3653 data: 3.1555 max mem: 3953 +eval (validation): [19] [20/85] eta: 0:00:30 time: 0.3211 data: 0.0037 max mem: 3953 +eval (validation): [19] [40/85] eta: 0:00:18 time: 0.3542 data: 0.0046 max mem: 3953 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3632 data: 0.0046 max mem: 3953 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3156 data: 0.0044 max mem: 3953 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3104 data: 0.0042 max mem: 3953 +eval (validation): [19] Total time: 0:00:31 (0.3756 s / it) +cv: [19] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.648 acc: 0.224 f1: 0.160 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +eval model info: +{"score": 0.22443706164636398, "hparam": [19, 1.0], "hparam_id": 42, "epoch": 19, "is_best": false, "best_score": 0.2279438907345884} +eval (train): [20] [ 0/509] eta: 0:28:00 time: 3.3013 data: 3.0969 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:03:41 time: 0.3116 data: 0.0048 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:03:04 time: 0.3288 data: 0.0046 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:02:48 time: 0.3414 data: 0.0050 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:36 time: 0.3343 data: 0.0041 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:30 time: 0.3732 data: 0.0051 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:19 time: 0.3198 data: 0.0042 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:10 time: 0.3191 data: 0.0040 max mem: 3953 +eval (train): [20] [160/509] eta: 0:02:03 time: 0.3536 data: 0.0045 max mem: 3953 +eval (train): [20] [180/509] eta: 0:01:55 time: 0.3253 data: 0.0043 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:47 time: 0.3181 data: 0.0043 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:39 time: 0.3271 data: 0.0046 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:32 time: 0.3422 data: 0.0047 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:26 time: 0.3676 data: 0.0047 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:19 time: 0.3246 data: 0.0045 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:11 time: 0.3323 data: 0.0045 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:05 time: 0.3400 data: 0.0048 max mem: 3953 +eval (train): [20] [340/509] eta: 0:00:58 time: 0.3305 data: 0.0039 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:51 time: 0.3488 data: 0.0049 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:44 time: 0.3186 data: 0.0043 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:37 time: 0.3685 data: 0.0047 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:30 time: 0.3323 data: 0.0043 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3412 data: 0.0049 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3271 data: 0.0049 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3625 data: 0.0046 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3127 data: 0.0043 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3098 data: 0.0040 max mem: 3953 +eval (train): [20] Total time: 0:02:54 (0.3432 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:49 time: 3.4063 data: 3.1360 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:30 time: 0.3252 data: 0.0036 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3256 data: 0.0045 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3350 data: 0.0036 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3031 data: 0.0040 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2971 data: 0.0039 max mem: 3953 +eval (validation): [20] Total time: 0:00:30 (0.3606 s / it) +eval (test): [20] [ 0/85] eta: 0:04:40 time: 3.2977 data: 3.0413 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:29 time: 0.3177 data: 0.0045 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:17 time: 0.3221 data: 0.0042 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3271 data: 0.0058 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3163 data: 0.0033 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3080 data: 0.0039 max mem: 3953 +eval (test): [20] Total time: 0:00:30 (0.3580 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:26 time: 3.2445 data: 3.0443 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3320 data: 0.0050 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3546 data: 0.0044 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3403 data: 0.0044 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3282 data: 0.0045 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3145 data: 0.0043 max mem: 3953 +eval (testid): [20] Total time: 0:00:30 (0.3761 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +eval model info: +{"score": 0.2279438907345884, "hparam": [36, 1.0], "hparam_id": 46, "epoch": 13, "is_best": true, "best_score": 0.2279438907345884} +eval (train): [20] [ 0/509] eta: 0:28:25 time: 3.3503 data: 3.0945 max mem: 3953 +eval (train): [20] [ 20/509] eta: 0:04:05 time: 0.3586 data: 0.0059 max mem: 3953 +eval (train): [20] [ 40/509] eta: 0:03:15 time: 0.3303 data: 0.0038 max mem: 3953 +eval (train): [20] [ 60/509] eta: 0:02:52 time: 0.3177 data: 0.0043 max mem: 3953 +eval (train): [20] [ 80/509] eta: 0:02:40 time: 0.3385 data: 0.0046 max mem: 3953 +eval (train): [20] [100/509] eta: 0:02:30 time: 0.3443 data: 0.0042 max mem: 3953 +eval (train): [20] [120/509] eta: 0:02:21 time: 0.3422 data: 0.0044 max mem: 3953 +eval (train): [20] [140/509] eta: 0:02:13 time: 0.3435 data: 0.0044 max mem: 3953 +eval (train): [20] [160/509] eta: 0:02:04 time: 0.3343 data: 0.0047 max mem: 3953 +eval (train): [20] [180/509] eta: 0:01:56 time: 0.3309 data: 0.0049 max mem: 3953 +eval (train): [20] [200/509] eta: 0:01:48 time: 0.3341 data: 0.0043 max mem: 3953 +eval (train): [20] [220/509] eta: 0:01:40 time: 0.3186 data: 0.0044 max mem: 3953 +eval (train): [20] [240/509] eta: 0:01:33 time: 0.3252 data: 0.0048 max mem: 3953 +eval (train): [20] [260/509] eta: 0:01:26 time: 0.3266 data: 0.0042 max mem: 3953 +eval (train): [20] [280/509] eta: 0:01:19 time: 0.3523 data: 0.0046 max mem: 3953 +eval (train): [20] [300/509] eta: 0:01:12 time: 0.3357 data: 0.0047 max mem: 3953 +eval (train): [20] [320/509] eta: 0:01:05 time: 0.3388 data: 0.0047 max mem: 3953 +eval (train): [20] [340/509] eta: 0:00:58 time: 0.3332 data: 0.0047 max mem: 3953 +eval (train): [20] [360/509] eta: 0:00:51 time: 0.3371 data: 0.0048 max mem: 3953 +eval (train): [20] [380/509] eta: 0:00:44 time: 0.3308 data: 0.0045 max mem: 3953 +eval (train): [20] [400/509] eta: 0:00:37 time: 0.3337 data: 0.0045 max mem: 3953 +eval (train): [20] [420/509] eta: 0:00:30 time: 0.3311 data: 0.0045 max mem: 3953 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3153 data: 0.0041 max mem: 3953 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3114 data: 0.0044 max mem: 3953 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3612 data: 0.0048 max mem: 3953 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3313 data: 0.0042 max mem: 3953 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3228 data: 0.0040 max mem: 3953 +eval (train): [20] Total time: 0:02:53 (0.3414 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:37 time: 3.2620 data: 3.0169 max mem: 3953 +eval (validation): [20] [20/85] eta: 0:00:32 time: 0.3549 data: 0.0039 max mem: 3953 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3169 data: 0.0039 max mem: 3953 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3329 data: 0.0044 max mem: 3953 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3191 data: 0.0040 max mem: 3953 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3071 data: 0.0037 max mem: 3953 +eval (validation): [20] Total time: 0:00:31 (0.3671 s / it) +eval (test): [20] [ 0/85] eta: 0:04:41 time: 3.3173 data: 3.0708 max mem: 3953 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3293 data: 0.0036 max mem: 3953 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3264 data: 0.0041 max mem: 3953 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3602 data: 0.0046 max mem: 3953 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3355 data: 0.0047 max mem: 3953 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3212 data: 0.0044 max mem: 3953 +eval (test): [20] Total time: 0:00:31 (0.3735 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:30 time: 3.2968 data: 3.0921 max mem: 3953 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3449 data: 0.0233 max mem: 3953 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3202 data: 0.0038 max mem: 3953 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3183 data: 0.0045 max mem: 3953 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3154 data: 0.0042 max mem: 3953 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2987 data: 0.0036 max mem: 3953 +eval (testid): [20] Total time: 0:00:29 (0.3626 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | reg | linear | nsd_cococlip | best | 13 | 0.0108 | 0.05 | 46 | [36, 1.0] | train | 2.5179 | 0.25966 | 0.0022577 | 0.20296 | 0.002215 | +| flat_mae | reg | linear | nsd_cococlip | best | 13 | 0.0108 | 0.05 | 46 | [36, 1.0] | validation | 2.6562 | 0.22794 | 0.0051366 | 0.16052 | 0.0043887 | +| flat_mae | reg | linear | nsd_cococlip | best | 13 | 0.0108 | 0.05 | 46 | [36, 1.0] | test | 2.5494 | 0.24212 | 0.0049493 | 0.17253 | 0.0048429 | +| flat_mae | reg | linear | nsd_cococlip | best | 13 | 0.0108 | 0.05 | 46 | [36, 1.0] | testid | 2.7162 | 0.19857 | 0.0046702 | 0.14422 | 0.0041426 | + + +done! total time: 1:07:10 diff --git a/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/train_log.json b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..e035c965807c2053fe65fa8027132d4cfc3cc3aa --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/nsd_cococlip__reg__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1628155183792113, "train/grad": 0.03784413650631904, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.180748291015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.18072265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.180706787109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.180673828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.18064208984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.18059814453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.180548095703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.180504150390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.18044677734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.180386962890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.18031005859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1802197265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.180120849609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1799560546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.179835205078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1797119140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.17955078125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.179239501953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1788818359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1785546875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.178216552734375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.17783203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.177286376953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.17667724609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.175928955078125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.174993896484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.174134521484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.173162841796875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.171856689453125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.170185546875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.168575439453125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.166981201171875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.16465576171875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.162567138671875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1598486328125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.157025146484375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.153812255859375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.150513916015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.146800537109375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.14182861328125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1379150390625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.13414306640625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.129075927734375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.12442626953125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.11873779296875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.112193603515625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1062603759765626, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.098475341796875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.091494140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005472673571202904, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005472609912976623, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005472488985396921, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00547237355960533, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005472237772773951, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005472068511880934, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005471862023696304, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005471640678588301, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0054713490372523665, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005471049752086401, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005470737228170037, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0054702894273214045, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005469843740575016, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0054691653419286015, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005468412574846298, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005467702266760171, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0054666965641081335, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00546547875739634, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005464060271624476, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005462634172290564, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005460781857836991, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0054586982214823365, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005456244205124677, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00545331043889746, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005449932285118848, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005445637195371091, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0054413517098873855, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0054371797922067346, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005431006110738963, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005423231541644782, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005415920501109213, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005408912727143615, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005398937556892633, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00538960189325735, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0053781671659089625, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005366439933422953, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005353521346114576, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005340944710187614, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005327674462459981, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005311531038023532, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005299518641550094, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0052893432695418595, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005276754305232317, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005266535626724363, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005255692049395293, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005245061167515814, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00523667668690905, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005227013777475804, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005219496877398342, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1811838150024414, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1811330318450928, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.181049108505249, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.180962085723877, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.180875778198242, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1807541847229004, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.18061900138855, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1804654598236084, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1802585124969482, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.180042266845703, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1798150539398193, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1794769763946533, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.179138422012329, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1786320209503174, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.178123712539673, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1776251792907715, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1769626140594482, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1761298179626465, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1751537322998047, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.174180269241333, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.172893762588501, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1714723110198975, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1697604656219482, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.16776967048645, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1655311584472656, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1626219749450684, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.159794569015503, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1570653915405273, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.153116226196289, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1481151580810547, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1434004306793213, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1389541625976562, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.132737159729004, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1269969940185547, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.119999647140503, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.112905263900757, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1051342487335205, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0975570678710938, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0891473293304443, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0782909393310547, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0694382190704346, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.061330556869507, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0500307083129883, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0395047664642334, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0264339447021484, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.011256217956543, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.99725604057312, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.979283094406128, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.96315336227417, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.036544850498338874, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.036544850498338874, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.036544850498338874, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.036360280546327055, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.036729420450350686, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.03617571059431524, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.03599114064230343, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.03580657069029162, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.036360280546327055, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0369139904023625, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.03709856035437431, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.03783684016242156, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.03765227021040975, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.039313399778516056, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.040051679586563305, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.04023624953857512, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.041159099298634184, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.043004798818752306, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.04540420819490587, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.045773348098929495, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.04688076781100037, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.04817275747508306, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.051310446659283866, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.05334071613141381, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.05721668512366187, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.067921742340347, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0754891103728313, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08767072720561092, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08914728682170543, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0932078257659653, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.09486895533407161, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.09782207456626062, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.10391288298265043, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.11037283130306386, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.11406423034330011, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.12089331856773718, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1273532668881506, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.13695090439276486, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.14304171280915468, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.14544112218530822, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1496862310815799, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.15005537098560354, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03189222082937857, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0318911970737912, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03186923896348328, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03173474657451662, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03206391843036754, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03140595656461809, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03125287028538262, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.031129143005513654, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03125787756534818, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.031788911849575496, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03188773022776195, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0323474411901748, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.032185877911251104, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0334215655587322, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.03382477239378836, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03378894039806147, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03465313557033171, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.035804801457793634, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.036904029750770895, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03679961311896282, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03600249895655979, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03639601287124358, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.037085255024758186, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03651036218663156, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.036704986298654624, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03756624062768244, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.033741315399654255, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03532154044433041, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0344981370788797, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03368604551558507, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03378629833921775, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03383820273555656, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03380015013308932, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.033947844647065364, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.034785023141752094, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.034432305508853296, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03615329877697123, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.035628566014287356, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.037629134649383174, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04192739901307862, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04886643067691492, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05231255573396404, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.05774859735944212, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.061652161538833794, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.06664596237223795, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.07030226920593775, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0720074524457288, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.07412997143998297, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0739883119619455, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.091494140625, "validation/loss_best": 2.96315336227417, "validation/acc_best": 0.15005537098560354, "validation/f1_best": 0.0739883119619455} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.1112782526016236, "train/grad": 0.036874718051403764, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1799755859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.17984619140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.179654541015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.179471435546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.17930419921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.179072265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.178795166015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.178470458984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.177984619140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.177525634765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.177012939453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.176265869140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.175616455078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.17455810546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1735400390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.172545166015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1711328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1693603515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.16745849609375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1656005859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1632080078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.160574951171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1574072265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.153953857421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.15012939453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.145230712890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.140816650390625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1366259765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1308935546875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12392333984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.117855224609375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.11216796875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.104466552734375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.09759521484375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0893115234375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0807452392578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0712445068359373, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0617059326171874, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0505914306640625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.03567138671875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.023289794921875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0117364501953126, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.99593017578125, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.9815594482421877, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.96447265625, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.9456854248046875, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9292922973632813, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.909876403808594, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.893485107421875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0054402797133661805, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005439759676810354, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005438894010148942, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005438053540419787, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005437184539623559, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005435932292602957, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005434567607007921, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005432958425953985, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0054308624658733606, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005428670500405133, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005426546896342188, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005423092013224959, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005419781585223973, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005414881135802716, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005409816566389054, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005405050835106522, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005398723983671516, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00539091233164072, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005381849019322545, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0053731107804924245, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005361997550353408, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005349903893657029, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0053359266160987314, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005320546408183873, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0053039611876010894, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005283904967363924, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005265647666528821, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005249310787767172, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005227918331511319, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005204057693481446, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005184773255605251, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0051686737150885165, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005149606543127448, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0051351347658783195, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0051207401533611115, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005108978322241455, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005098340210970491, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005090251509100199, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005082764197140932, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005074866372160614, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0050694741262122985, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00506518344162032, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005059884127695114, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005055650332942605, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005050908918492496, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005046351985074579, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005042885064613074, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005039593873079866, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00503756832331419, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1801345348358154, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.179921865463257, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1795873641967773, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1792356967926025, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1788947582244873, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.178410768508911, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.177865505218506, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.177257776260376, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1764466762542725, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.175586223602295, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.174720048904419, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.173414707183838, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1721208095550537, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.170217752456665, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1683452129364014, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1665139198303223, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.164113759994507, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1612095832824707, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.157851219177246, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1546032428741455, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.15047025680542, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1460466384887695, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1409595012664795, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1353325843811035, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.129343271255493, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1220591068267822, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1154675483703613, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1094677448272705, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.10137939453125, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0918850898742676, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0834736824035645, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.075866222381592, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0655126571655273, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.056061029434204, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.044355869293213, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0321364402770996, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0182626247406006, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0041451454162598, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.987868547439575, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.9663665294647217, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.948805332183838, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.9329795837402344, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.9119107723236084, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.893585681915283, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.87252140045166, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.850834608078003, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8330636024475098, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.813505172729492, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.798773765563965, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.036729420450350686, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.03765227021040975, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.03783684016242156, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.037467700258397935, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.03857511997046881, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.039313399778516056, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.04023624953857512, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.04097452934662237, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.04245108896271687, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.04466592838685862, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.045773348098929495, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.04688076781100037, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.04780361757105943, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.05057216685123662, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.05334071613141381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.056847545219638244, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0753045404208195, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07973421926910298, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.08637873754152824, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.08785529715762273, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.09210040605389443, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.09376153562200074, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.09985234403839055, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.10391288298265043, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.10686600221483943, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1124031007751938, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.11997046880767812, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.12772240679217423, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.13196751568844592, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1404577334809893, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.14765596160945, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.15374677002583978, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1581764488741233, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1598375784422296, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.16315983757844224, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.1688815060908084, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.16832779623477298, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17331118493909192, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1758951642672573, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.17700258397932817, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.18032484311554078, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.17811000369139904, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0315728738484831, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03226159281782614, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03234722429154855, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03202783213675977, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03285883661432882, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03316417912404518, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03369088497687206, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.034385886840039896, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03524459225942669, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.036411363019902276, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03643749509534921, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03594772868915738, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.036116651797215814, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03666544031566905, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.03656382095683513, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.036517089370315094, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03655433986734962, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03431545534368349, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.033965191008043454, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.033440729393623074, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.034007638057431455, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03324512556432842, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03266724223794828, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03234205600439664, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.032776371718416374, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03366225871692922, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03249111798935636, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.03376390553906524, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.03322262386471083, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03717040308192023, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03929194963135479, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.04151290179049322, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.04773048420141934, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.05447324638385176, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0600309996148291, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.06209049352978601, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.06717338364321387, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.07160182454991364, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.07565727397544893, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.07761395481925333, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.07913736013485986, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.08244115252981372, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.08707998443103497, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0884840560317756, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.09446066113512776, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0982719769318901, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.09974136950394608, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.10474429740587049, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.10539556143683561, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.909876403808594, "validation/loss_best": 2.813505172729492, "validation/acc_best": 0.18032484311554078, "validation/f1_best": 0.10474429740587049} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.0632355105876923, "train/grad": 0.03645824499428272, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.17903564453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.178677978515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17823974609375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1777880859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.177384033203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.176649169921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.175887451171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.175076904296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1739306640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.172730712890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.171590576171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.16977294921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.168092041015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.165567626953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.16315185546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1608349609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.157822265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.154193115234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.15002685546875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.14613525390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1413037109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.13643798828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.130760498046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.124703369140625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.118450927734375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.110943603515625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1042236328125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.09803466796875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.089583740234375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.07933837890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0698046875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0610064697265624, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.048470458984375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.036632080078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0219580078125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.00662841796875, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.9894183349609373, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.972308349609375, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.95297119140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.928333435058594, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.908978271484375, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.891931457519531, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.869919738769531, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.851521301269531, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.831241455078125, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.811036376953125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.7953163146972657, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.778492431640625, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.7662059020996095, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005430489117279649, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005429077146109193, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005426767216995358, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005424461776856333, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005422159677837044, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00541903605684638, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005415492290630937, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005411462986376137, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005406193640083074, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005400597958359867, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005395050952211022, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0053867326816543935, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005378686534240842, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005366927688010037, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005355523293837905, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00534471936058253, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005330807829741388, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005314807151444256, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005296879292000085, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00528045704588294, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00526071056490764, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005241026040166617, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005220026820898056, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0051989198988303545, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005179066346026957, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005158150140196085, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005142437496688217, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005130267187487334, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005116713817697019, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005104255718179047, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005095756959635764, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005089320817496627, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005082159293815494, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0050761192315258085, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005069552150089294, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005062927075196058, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005055719178635627, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005048766115214676, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005040851354133338, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0050311510707251724, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005023843771778047, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00501752249430865, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005009783955756575, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005003833447117359, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004997774919029325, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004993158834986388, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004990560233127325, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00498975571943447, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004990792777389288, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1784307956695557, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.177973985671997, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1772146224975586, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1764614582061768, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.175722122192383, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1746721267700195, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1735072135925293, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.172213077545166, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.170496940612793, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1686835289001465, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1669068336486816, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1642308235168457, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.161632537841797, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1578636169433594, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.154261827468872, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1508052349090576, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.146411895751953, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1412436962127686, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1354591846466064, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.130091905593872, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1235127449035645, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1167750358581543, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1093547344207764, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1015210151672363, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.093425989151001, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.083833694458008, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.075228452682495, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.067295551300049, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0563337802886963, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0429024696350098, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.0304508209228516, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.0187900066375732, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.002492904663086, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.987410306930542, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.9690089225769043, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.950340747833252, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.92997670173645, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.9103806018829346, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.8890717029571533, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.862957239151001, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.843369483947754, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.826871156692505, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.806506633758545, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.790318727493286, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7734363079071045, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.757807493209839, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.746509313583374, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7357912063598633, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7291040420532227, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.03875968992248062, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.040051679586563305, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04097452934662237, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.04245108896271687, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.04448135843484681, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.04521963824289406, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.04688076781100037, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.047434477667035804, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05075673680324843, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.052417866371354746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05555555555555555, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07308970099667775, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07438169066076043, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07751937984496124, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.08010335917312661, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08600959763750461, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.09043927648578812, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.09413067552602436, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09505352528608342, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.09689922480620156, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.10299003322259136, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.10834256183093392, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.11351052048726468, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.11886304909560723, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.12901439645625692, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.13510520487264674, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1421188630490956, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1493170911775563, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.15596160944998155, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1598375784422296, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.16279069767441862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1657438169066076, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1716500553709856, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.17663344407530454, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18420081210778885, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1878922111480251, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19121447028423771, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19564414913252123, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1984126984126984, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.19804355850867478, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19767441860465115, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.19712070874861573, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.19933554817275748, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.19804355850867478, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03281996583103857, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03366159129850066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03437012938761308, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03547655262980665, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0363059194903269, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03593660519823252, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03654812399182358, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.035814278500651026, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03729719495485682, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0367233778194865, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03644127353801422, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03720037527361438, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03470009929478325, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03465828521174358, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.033812309603087794, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.034022005994081096, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.032998749645579785, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03339999229035747, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.03310551470751363, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03259936128096986, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03373935705151231, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03494420398232132, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.034833328505483735, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.03403145695924468, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.03552895115854741, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03833122486427067, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04107449292236889, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.045160266810251704, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.05055610008671348, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0582138443121644, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.06226958711783347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.06824501650289906, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.07330071335688783, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0775978445968893, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.08009805019949415, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.0824589307112872, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.08688912397772404, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.09248080993691547, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.09846677166634817, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.10611501302176014, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.11108381829346196, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11603761727326933, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12323877172806326, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12735376026929177, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12901641315609233, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1320047609807411, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13287990492192986, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1378114223216554, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13765943991260196, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.778492431640625, "validation/loss_best": 2.7357912063598633, "validation/acc_best": 0.19933554817275748, "validation/f1_best": 0.1378114223216554} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.0236708068847657, "train/grad": 0.03629376288503408, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.176973876953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.17636962890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.175469970703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.174598388671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1736767578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.17240966796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.170997314453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.169461669921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.167369384765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1652978515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.163209228515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.160189208984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.157237548828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.152967529296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.148985595703125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1452197265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.14059326171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.13511962890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1292041015625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.123831787109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11728759765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.110723876953125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.103548583984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.095770263671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.08773681640625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0778662109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.068851318359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0601416015625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0479833984375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.03279296875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.01862060546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.005380859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.98699462890625, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.9700567626953127, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.94989990234375, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.9296697998046874, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.90793701171875, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.8874240112304688, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.86529541015625, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.838692626953125, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.8190350341796875, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.802595672607422, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7826976013183593, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.767122955322266, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7510931396484377, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.736694793701172, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.7268663024902344, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.7181722640991213, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.713738784790039, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005435863898601383, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005433143363334238, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005428735532332212, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005424433532170952, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005420275258366018, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00541443356545642, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005407975846901536, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005400664242915809, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005391261042095721, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00538131324807182, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005371648864820599, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005357589377090335, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005344205475412309, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005325561997015029, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005308306843508035, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005292600775137543, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005273577293846757, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005252208772581071, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005230008743237704, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005211480802390724, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005190910748206079, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00517268483992666, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005155510967597365, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0051406623120419685, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0051285202475264665, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005117346092592925, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005109610436484217, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005103782927617431, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005096995423082262, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005089707926381379, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005083552848082036, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0050779043301008644, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00507037068484351, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005063629210926592, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005055462655145675, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0050477359001524745, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005039353335741907, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005031679631210864, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005023771706037223, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005014483735430985, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005008130266796798, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00500323994550854, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00499798335134983, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0049943318357691165, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004992107418365777, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0049920648825354874, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004994274398777634, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004999888862948864, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005007823626510799, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.176116466522217, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1753220558166504, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.174025058746338, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.172740936279297, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.171482801437378, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1697311401367188, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1677749156951904, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1656248569488525, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1628332138061523, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.159904956817627, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1570651531219482, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1528849601745605, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.148900270462036, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.14326810836792, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.138012170791626, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.133118152618408, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1270406246185303, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1201205253601074, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1126468181610107, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1058876514434814, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.097811222076416, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.089672088623047, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0807442665100098, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.071214199066162, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.061174154281616, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0488979816436768, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.0375113487243652, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.026808023452759, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.0118346214294434, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9934768676757812, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9767298698425293, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.961390972137451, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.9406495094299316, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.922184944152832, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.900574207305908, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.8796749114990234, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.857964038848877, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8380696773529053, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.817512273788452, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7938785552978516, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7771973609924316, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7639641761779785, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.748628616333008, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7372305393218994, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7260894775390625, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7166712284088135, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.710733413696289, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.706712484359741, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.706058979034424, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.043743078626799554, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.04540420819490587, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04595791805094131, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.046511627906976744, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.048726467331118496, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05149501661129568, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05334071613141381, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07511997046880768, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07659653008490218, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07862679955703211, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08250276854928018, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.08785529715762273, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.09154669619785899, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.09376153562200074, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.09726836471022518, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.10151347360649686, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.10723514211886305, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.11203396087117018, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1197858988556663, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.12679955703211518, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.13196751568844592, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.13750461424880028, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.14138058324104835, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1493170911775563, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.15356220007382798, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.15946843853820597, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.16297526762643041, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1657438169066076, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17035806570690293, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.1731266149870801, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.17626430417128092, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1806939830195644, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.18309339239571798, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.18826135105204872, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19158361018826134, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19472129937246216, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19767441860465115, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2011812476928756, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.20302694721299372, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2024732373569583, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20450350682908822, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20782576596530086, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20505721668512367, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.036166669529800605, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.036857696916336224, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.036001203406709203, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03557315098255427, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03625355583834842, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03719126774171086, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.035912966742518405, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.037618195870579484, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.035323671116069134, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03314802240509767, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.034202266416890253, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0335848994446799, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03419839799265449, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03320147760573578, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.03326904672853187, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03247105231826793, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.032565917899335786, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03334056879444005, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.034266377413536345, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03327813490688318, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.033620224119284906, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.03539693417604871, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.03969651123812834, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.043646548254375826, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04979521645564335, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.056451643158047536, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.05998194100564631, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06369930557037477, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.06548007442928654, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.07079439805652457, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.07352519147195073, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.07684304600341808, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.07928728006661918, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.08241468178339756, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.08690084553909581, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.09007691935288094, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.09568945747384207, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.10077265078382419, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.10398497730893268, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1095854484066932, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1125103198623257, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11614529725494427, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12003394527251303, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12521336238614245, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.12754612686045594, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.12919905125334655, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13249101005534283, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.13793148972393363, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.13762149479824415, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.7181722640991213, "validation/loss_best": 2.706712484359741, "validation/acc_best": 0.20782576596530086, "validation/f1_best": 0.13793148972393363} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.986107420921326, "train/grad": 0.035920347813516856, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.174781494140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.173812255859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1723095703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.170799560546875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.169366455078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.16735595703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.165167236328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.162705078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.159613037109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1562841796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.153187255859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.148660888671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.144327392578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.138319091796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.132860107421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1278564453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.121658935546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.114681396484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.107193603515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1004638671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.09233154296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.084019775390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0746240234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.064364013671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.05338623046875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.03962646484375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0267529296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0146173095703124, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.997554931640625, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.97676513671875, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9579925537109375, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.94086669921875, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.917969970703125, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.897734375, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8744076538085936, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.8519711303710937, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.8288134765625, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.8077798461914063, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7862368774414064, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7616007995605467, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.744252166748047, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.730613098144531, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.7149726867675783, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7034310913085937, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.6928164672851564, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6844915771484374, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.680048828125, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6781124114990233, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6797088623046874, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005409622436854988, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005405316925607622, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0053984142979606985, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005391528366599232, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005384876027237624, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005375785515643656, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0053654342191293836, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0053544140118174256, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00534033716423437, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005325861023738981, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005312098658178002, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005292663527652622, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0052749107894487675, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005250970874913037, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005230002659372985, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00521156019764021, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005190424032043665, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005169009929522872, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005148769270163029, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005133263003081083, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005117838364094495, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00510526935569942, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005094707852695137, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005085795409977436, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005078362487256527, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005070682682562619, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0050642300955951215, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005058496142737567, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005050795127172023, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005041424292139709, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00503286775900051, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00502557955449447, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0050155359460040926, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0050069662439636885, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0049970864527858795, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004987978802528232, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004978777859359979, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0049708553217351435, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004963243759702891, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004955606765579432, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004950945356395096, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004948009063955396, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004946115599013865, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00494622923899442, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004948900954332203, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004954523695632815, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004962260995525867, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004975660576019436, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004991320436820388, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1731698513031006, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.171969175338745, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1700127124786377, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.168090581893921, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.166213274002075, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1636314392089844, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1607863903045654, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1576805114746094, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1537017822265625, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.149606943130493, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1457033157348633, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.140052080154419, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1347808837890625, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1275291442871094, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.120948076248169, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1149308681488037, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1076438426971436, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0994951725006104, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.090797185897827, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0829718112945557, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.073499917984009, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0638115406036377, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.052903890609741, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.0409727096557617, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.0281577110290527, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.0123114585876465, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.997619867324829, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.983975410461426, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9651851654052734, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.9428775310516357, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.923140525817871, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.905599594116211, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8827426433563232, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.8631112575531006, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.841099739074707, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.820669651031494, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.800408363342285, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.7827646732330322, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.7655656337738037, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7471022605895996, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.7352802753448486, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.726806402206421, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7185654640197754, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.714064598083496, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7114155292510986, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.711437225341797, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.713427782058716, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.717982769012451, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.7233564853668213, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04632705795496493, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.04724990771502399, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.051125876707272054, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05334071613141381, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.058508674787744554, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07438169066076043, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07825765965300849, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0812107788851975, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08545588778146918, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08951642672572906, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0932078257659653, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.09413067552602436, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.09708379475821337, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.10095976375046142, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.10594315245478036, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.11129568106312292, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.11794019933554817, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.12532299741602068, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13067552602436322, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.13602805463270579, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.14119601328903655, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.14562569213732005, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15042451088962716, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.15706902916205243, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.16334440753045404, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.16685123661867848, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.16851236618678478, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.17257290513104467, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17497231450719822, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.18106312292358803, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.18327796234772978, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1847545219638243, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1878922111480251, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1925064599483204, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.19785898855666298, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1997046880767811, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20191952750092285, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20210409745293467, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20450350682908822, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.20450350682908822, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20487264673311184, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2070874861572536, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2026578073089701, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20062753783684018, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03568172511248134, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03548205985549114, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03708851669238845, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.036159053452958, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03706076975359724, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03585375559886241, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03490367156637737, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03445971367582765, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03326411932181955, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03357606720437487, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.032457815528438336, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03325096986750512, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03239262745915161, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.032897986670629015, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.03361238057630908, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03472348803167212, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03283358230507892, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.033563700345773835, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.03502203537729641, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.03759890513693096, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04125461277243687, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.047360209156526716, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.05525271198075912, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.059002117340303716, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06334783728621922, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.06756858615810303, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.06996030540920799, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07348994668892572, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.07826390198741266, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0826565233892751, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.08597341228591616, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0880563520964463, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.09350358634318932, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.09856917386122031, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.10579292416996193, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10883575479003345, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11133580407565564, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11450072775788482, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.11821390045238989, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12576444880524723, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1284980070394208, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1315163122082855, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.13391041510806595, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1378892818549718, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.13967469566882362, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1409906239681182, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1443995690235699, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.14194145465182487, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1426835581960972, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.680048828125, "validation/loss_best": 2.713427782058716, "validation/acc_best": 0.2070874861572536, "validation/f1_best": 0.1443995690235699} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.959005401134491, "train/grad": 0.035699917171150446, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1710546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.169715576171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.16755859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.165445556640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1634423828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.160557861328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.15741455078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1541064453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.149825439453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.14541015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.14135009765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1353955078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.13011474609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.122733154296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1160791015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.110057373046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10288818359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.094727783203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0860205078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.078067626953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.068211669921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.05808349609375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.046339111328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0334112548828127, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.0194525146484374, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.0021124267578125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.986175537109375, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.9712994384765623, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9509808349609377, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.926922607421875, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9057342529296877, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.887012634277344, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8624563598632813, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.8415298461914062, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8180108642578126, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7961102294921876, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7744476318359377, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7553428649902343, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.7367230224609376, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7162380981445313, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.7028509521484376, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6928584289550783, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.682255325317383, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6753900909423827, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.670207977294922, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6678585815429687, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6685564422607424, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.672978973388672, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.679750709533691, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005389836120884866, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00538377454970032, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005373904663138092, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005364244459196925, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00535484901163727, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00534211857477203, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005328307070303708, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005313592453021556, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005295254562515766, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005277175849769265, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005260406930465251, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005237361716572195, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0052171097113750875, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005191004367079585, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0051696780696511265, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005152414897456765, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0051340109808370475, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005116732979658991, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005102008744142949, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005091662062332034, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005081709753721952, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005073864734731615, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0050668152328580615, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005059938647318632, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0050533644924871625, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005045548824127764, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005038451564032585, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005031895509455353, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005023052939213813, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005012380769476295, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005003155074082315, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0049951929366216065, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004984556077979505, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004975571730174124, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004965927402954548, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0049569510109722615, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004948386996984482, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004941282740328461, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00493493938120082, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004929518222343177, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00492720813723281, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004926745847333222, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004928537711966783, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004931845283135772, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004938608647789806, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004949023060034961, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00496137412963435, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004980345293879509, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004999456442892552, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1700048446655273, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1683895587921143, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.165753126144409, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1631901264190674, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.160698890686035, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.157335042953491, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.15364146232605, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1496548652648926, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1446373462677, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1395511627197266, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1347768306732178, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.127990245819092, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121783971786499, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1133975982666016, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.105955123901367, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.099201202392578, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.09110689163208, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0820207595825195, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0722410678863525, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.063274621963501, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0522563457489014, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.040743827819824, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.027639389038086, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.01322078704834, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9977939128875732, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9789576530456543, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9618279933929443, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9461824893951416, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.9250857830047607, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.900700330734253, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8798093795776367, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8616983890533447, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8386988639831543, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.819662094116211, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.798882246017456, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7803099155426025, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.762540578842163, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.747621774673462, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.733556032180786, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.719304323196411, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.710538864135742, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7045538425445557, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6990609169006348, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.696432113647461, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.695882797241211, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6981284618377686, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.7026665210723877, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.7112138271331787, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.721794605255127, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05167958656330749, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.052417866371354746, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.059800664451827246, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07032115171650055, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0754891103728313, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07881136950904392, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0812107788851975, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08490217792543374, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.08803986710963455, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.09228497600590624, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.09616094499815431, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.09782207456626062, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10114433370247324, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.10575858250276855, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.10981912144702842, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.11794019933554817, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.12550756736803248, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1314138058324105, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.13528977482465854, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13953488372093023, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1461794019933555, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.15356220007382798, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.15946843853820597, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.1626061277224068, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.16629752676264303, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17128091546696197, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17478774455518642, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.17958656330749354, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.18567737172388335, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.18733850129198967, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.19232188999630861, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.19269102990033224, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.19656699889258028, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.1982281284606866, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2011812476928756, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20191952750092285, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20431893687707642, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20505721668512367, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20671834625322996, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20579549649317092, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2041343669250646, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20948689553340716, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2087486157253599, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2085640457733481, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20616463639719454, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03773264005604283, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03588940039031325, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03741985802647988, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0345603863978016, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03524432496580781, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03406779900578483, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03281880670188633, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.033209034026797014, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03240177086678911, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.033642246236425366, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03194071522777002, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03255402605065605, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03331903083594757, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.033910847959300904, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0340351207970478, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.034528820736524364, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03604629982340672, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03940523056829441, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04225801541260327, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.04857653275115739, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05586931957385884, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.06040027254489708, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0625959951524991, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06535670785045565, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.06957467966784253, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.07474409321444128, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07789818879802972, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.07906850629226764, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.08317404163410379, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.08847145735019919, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.09168319988211547, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.09695220209171124, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.10265965347950362, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.10540667197558062, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1125954278587498, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1159311134680156, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11962810921938755, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.12333798727913448, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1277333322811294, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12975132672360576, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.13333091988192478, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.13597956102458356, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1390776542720755, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14108850767628953, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.14126278397524547, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14790894112866257, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.14895441592240022, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15011239824760758, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.14984175954704373, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.6678585815429687, "validation/loss_best": 2.6981284618377686, "validation/acc_best": 0.20948689553340716, "validation/f1_best": 0.14790894112866257} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.935299913883209, "train/grad": 0.03552872000262141, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1687353515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.16701904296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.164249267578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.161610107421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.158990478515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.15544921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.15169189453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.147613525390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.142425537109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.137225341796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.132423095703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125809326171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.119566650390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1113671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.104002685546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.097352294921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.089332275390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.08017822265625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.07018310546875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0608984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.049332275390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.036973876953125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0228131103515623, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.0072802734375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.990379638671875, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9700341796875, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.9514599609375, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.934447021484375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9116082763671876, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.885015869140625, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8622613525390626, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8424728393554686, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8171295166015624, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.795843200683594, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7724977111816407, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7513058471679686, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.7306676483154297, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7129672241210936, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6959203338623046, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6780419540405274, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6666513442993165, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.658362865447998, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6501119041442873, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.645433864593506, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.642713108062744, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6428929138183594, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6457871341705324, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.652367172241211, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6608031511306764, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005367634228896349, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005360011162701994, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005347617969382554, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005335507288109511, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005324208938982338, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005308922168333083, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00529261669376865, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0052757796412333845, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005255394799169153, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005235249646939337, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00521737739443779, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005193331826012582, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005173289722297341, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005149201075546443, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005130950675811619, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00511680593714118, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005102795788552612, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005090227834880352, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005080110868439078, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00507295171963051, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005065696293022484, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005059322067536414, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005052481235470623, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005045449519529939, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005037856160197407, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005028889065142721, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005020730125252158, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0050131576904095705, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0050030712666921315, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004991576366592199, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00498168796300888, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004973232401534915, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00496234628604725, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004953226449433714, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00494364025304094, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004934950417373329, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0049268494732677935, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00492042870959267, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004914535442367196, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004909393759444356, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004907329974230379, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004907107171602547, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004909334110561758, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004913627726491541, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004922007618006319, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0049344462784938516, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004948575526941568, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004969944956246764, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0049909337237477305, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.16701602935791, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1650164127349854, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.161780595779419, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1586642265319824, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1556396484375, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.151596784591675, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1472060680389404, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.142526865005493, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.136715888977051, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1308846473693848, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1254751682281494, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.117917776107788, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.111093044281006, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1019911766052246, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.093919515609741, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.086634635925293, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.077820062637329, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0678369998931885, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.05688214302063, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0467307567596436, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0341100692749023, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.0208685398101807, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0058345794677734, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9894001483917236, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9720168113708496, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9511256217956543, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9324259757995605, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.9156363010406494, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8934075832366943, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.868274211883545, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.847186803817749, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8292834758758545, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.8069143295288086, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7887229919433594, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7693228721618652, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.752260208129883, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.736243724822998, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.723123550415039, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.711117744445801, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.699204206466675, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6919708251953125, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.687065839767456, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6821436882019043, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6795740127563477, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6783690452575684, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6793510913848877, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6822147369384766, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6876659393310547, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.694767713546753, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.055924695459579184, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.060538944259874494, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07364341085271318, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07881136950904392, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08342561830933924, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08545588778146918, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.09080841638981174, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.09339239571797711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.09542266519010704, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.09892949427833149, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.10317460317460317, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1064968623108158, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.11166482096714656, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1197858988556663, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.12790697674418605, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.13233665559246954, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1362126245847176, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.14285714285714285, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.14950166112956811, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1554078995939461, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.16020671834625322, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.16500553709856036, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.16666666666666666, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1716500553709856, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17663344407530454, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1806939830195644, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1834625322997416, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1864156515319306, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.19102990033222592, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1937984496124031, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.19269102990033224, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.1967515688445921, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2009966777408638, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2041343669250646, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20468807678110004, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.20487264673311184, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20837947582133629, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20985603543743078, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2087486157253599, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20579549649317092, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20524178663713546, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20450350682908822, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03671069596189047, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03655085918987556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03424585860567895, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03377605493250804, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03364772175478628, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.033681432132607575, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.032304721517558956, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03261120144450801, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03220678428718916, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03199927619039149, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03247528707597167, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03435736795267909, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.034537155039176044, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03214249094312194, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0339915657851821, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03634045409837512, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.038955355763716594, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.04211298788592261, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.05014024998657544, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.05761615248329483, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0615958057709334, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.064526030364336, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06815108720106175, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.07213802191098333, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.075917834148517, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.07857675075580169, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.08343230261828176, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.08378529649187309, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.09001262842538094, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0968293633883539, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.10175014218481386, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1042486444152092, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.10857234392592262, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.11413147111488213, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.11824260256807946, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.11989676428294677, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.12601810450092527, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.13046988461542117, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.13513342545850668, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1365092498427673, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.13716471774910458, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1391202716143357, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14324833653670063, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14505990490802242, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.14472062054580798, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14422406469919802, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.14607532358117178, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.14747909710651622, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1483965538232976, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.645433864593506, "validation/loss_best": 2.6795740127563477, "validation/acc_best": 0.20985603543743078, "validation/f1_best": 0.14505990490802242} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.9148306119441987, "train/grad": 0.03564260317012668, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.165848388671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.163758544921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.16045654296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.157188720703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.154127197265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.15008056640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.145531005859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.140814208984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.134981689453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129239501953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123785400390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.116363525390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1096875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.100714111328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0926123046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.08536376953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.07659912109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.06627685546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.054874267578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0442333984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.030721435546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.01650634765625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0002703857421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.98256103515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9636871337890627, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9410076904296876, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.920771484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.902376708984375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.8779010009765624, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8501318359375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.8265570068359374, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8064389038085937, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.78095458984375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.760069580078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7373696899414064, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.717057342529297, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.697646179199219, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.681201629638672, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6657196044921876, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.649466552734375, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.639474334716797, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6322522735595704, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6252017974853517, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6210890197753907, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.61904052734375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.619684143066406, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.622455062866211, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6291210556030276, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.637431640625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0053911951347254215, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005381864926312119, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00536705878097564, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005353092378936708, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005339693662244826, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005322088359389454, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0053038660250604155, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005285091393161565, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005262617424596101, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005241257683373988, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005222594067454338, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00519851328805089, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0051795265334658325, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005157556012272834, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005141468376386911, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005129751299973577, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005118440252263099, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005108535960316658, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005099835409782827, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005093372697010636, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005086423431057483, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005079406390432268, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005071843252517283, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005063731845002622, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00505520632956177, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005044991970062256, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005035971282050014, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005027999670710414, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005017191397491842, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005005073600914329, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00499485656619072, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0049862094945274296, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004975577048026025, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004966978603042662, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00495810167863965, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00495029263664037, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004943407708778978, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004938151794485748, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004933855643030256, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004930830011144281, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004930249452590942, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004931029581930488, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004933736294042319, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004938248894177377, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004945875487755984, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004957007779739797, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004969717534258962, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004989189913030714, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005009836698882282, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1642274856567383, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.161881923675537, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1581201553344727, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1545116901397705, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.151048421859741, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.146425247192383, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.141464948654175, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.136219024658203, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1297757625579834, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123385429382324, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.117537260055542, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1093955039978027, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.102121353149414, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0924265384674072, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0838422775268555, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0760247707366943, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0664830207824707, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0555381774902344, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0434298515319824, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0321238040924072, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0180275440216064, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.003312587738037, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.986666679382324, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9686806201934814, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9499166011810303, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.9276468753814697, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.9079744815826416, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.890578031539917, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.867823600769043, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8425395488739014, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8216617107391357, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.8041913509368896, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.782698631286621, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.76552152633667, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.747408390045166, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.731621503829956, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7170631885528564, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.705202579498291, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.694427728652954, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6837880611419678, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.677398920059204, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6734957695007324, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6700451374053955, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6687488555908203, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6692023277282715, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.671632766723633, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6756162643432617, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.683345079421997, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6928212642669678, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0664451827242525, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07456626061277224, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07659653008490218, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07973421926910298, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08416389811738649, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08748615725359911, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09154669619785899, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.09394610557401255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.09560723514211886, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1005906238464378, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.10465116279069768, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.10631229235880399, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.11221853082318199, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.12052417866371355, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.12938353636028055, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.13418235511258766, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.13990402362495385, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.14451827242524917, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.15079365079365079, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.15633074935400518, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.16002214839424142, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1642672572905131, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.16703580657069028, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17331118493909192, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17718715393134, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.18290882244370615, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.18567737172388335, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1893687707641196, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.19195275009228496, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1954595791805094, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20210409745293467, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20468807678110004, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.20671834625322996, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2072720561092654, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20930232558139536, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2115171650055371, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21188630490956073, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21207087486157253, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21114802510151348, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2117017349575489, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21096345514950166, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.20985603543743078, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.20967146548541898, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20893318567737174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03602710677401429, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.034385756634613546, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.033975319262227445, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.033215391555795566, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03283389874325463, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.032599919475834564, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03290118250955556, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.032613860023232785, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03214610982742425, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03336564774156254, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03465192818825579, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.033824527741863765, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03239919625648769, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.035353822166095845, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.03751998582588444, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0386581510134544, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0435320380027884, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.05010210764695994, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0580115155088241, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.061602017922971986, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.06607365313890101, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.06810942321610175, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.07272866107213043, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.07572326801230962, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.07802249324085078, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.08213758435891366, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.08482666979163683, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.09165243480817355, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.09632395214233991, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.10322884697339933, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.10705676091946488, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.11207525228611966, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1158147620370736, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.12137138927230347, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1275992858775952, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1311467659963865, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.13430020330152861, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1378315302885473, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1393032260185917, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14157783567637036, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.14459082144849156, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.14582871752926002, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14785000206670287, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1472618002994299, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.14776464178978546, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14787832723467031, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.14714914224631723, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1468451008608844, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.14633886274111294, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.6252017974853517, "validation/loss_best": 2.6700451374053955, "validation/acc_best": 0.21207087486157253, "validation/f1_best": 0.14785000206670287} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.896927614212036, "train/grad": 0.03523359261453152, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.163438720703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1609716796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.157091064453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.15341796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.149892578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.145140380859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.14013671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.134827880859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.128355712890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1219287109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.116068115234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10800048828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1007421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.090914306640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.082176513671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.07427978515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.064432373046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.05296142578125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.040205078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.028194580078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.0130023193359374, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.997266845703125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.979251708984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9597686767578124, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.939345703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9151141357421877, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.89345703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8743060302734373, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.849056396484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.82058349609375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7968521118164062, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7766244506835935, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7515679931640626, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7311720275878906, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7091299438476564, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.689636688232422, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.671053009033203, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6554876708984376, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6408119583129883, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.625540351867676, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.616018829345703, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6092342567443847, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6027290344238283, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5991625785827637, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5974816703796386, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5982458877563475, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.6011859512329103, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.6075579833984377, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6156347942352296, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005342056362424046, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005331358464900404, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005314477800857276, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005298622106201947, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005283836235757917, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005264644287526607, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005244774578604847, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005224663286935538, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005200973085593432, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00517915102886036, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005160651337355375, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005137837452348321, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00512002209899947, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005100631886161864, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0050869035930372775, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00507715875050053, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0050675565632991495, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005059047709219158, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0050514017650857565, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005045129139907658, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0050375740206800405, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005030067751649767, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005021723296958953, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005012778327800334, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005003420552238822, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004992137292865664, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004982205582782626, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004973436705768108, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00496185933239758, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004948851440567523, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004937896565534175, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004928683086764068, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0049172549019567665, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0049080868321470916, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004898522803559899, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004890182781964541, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004882818774785846, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004876985868904739, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0048723151558078825, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004868280803784728, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004866439453326166, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0048666881304234265, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004868299381341785, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00487191527383402, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00487817568005994, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004887086341623217, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004896525731310248, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004910555561073124, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004925434363540262, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.161720037460327, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1590847969055176, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.154865026473999, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.150841236114502, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1470046043395996, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.141925573348999, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.136504650115967, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.130840301513672, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123931407928467, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1171436309814453, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.110956907272339, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1024248600006104, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0948221683502197, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0846784114837646, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0756402015686035, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0673646926879883, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.057164430618286, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.045384645462036, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0322651863098145, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0200376510620117, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0048208236694336, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9889731407165527, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.971280336380005, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.95227313041687, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9326484203338623, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.909636974334717, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.8896472454071045, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8720388412475586, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.849393606185913, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.82450795173645, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.8042683601379395, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.787419319152832, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7670412063598633, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7508130073547363, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7339396476745605, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7194631099700928, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.706324577331543, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6957764625549316, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.686574697494507, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.678112030029297, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.673581838607788, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.671125650405884, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.669405221939087, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.669219732284546, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.670484781265259, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.673628330230713, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.677884340286255, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6851351261138916, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.693007469177246, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06589147286821706, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07493540051679587, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0769656699889258, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07862679955703211, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08324104835732743, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08508674787744555, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0902547065337763, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0917312661498708, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.09413067552602436, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.09800664451827243, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.10299003322259136, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.10557401255075674, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.11166482096714656, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.11775562938353636, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.12772240679217423, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.13270579549649317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.13805832410483573, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.14267257290513105, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1491325212255445, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1552233296419343, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.15946843853820597, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1644518272425249, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.16758951642672573, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17257290513104467, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17515688445921004, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.1805094130675526, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.18456995201181248, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1906607604282023, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.19435215946843853, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1997046880767811, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2026578073089701, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20376522702104097, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.20524178663713546, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20948689553340716, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21133259505352528, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2131782945736434, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21502399409376152, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21539313399778517, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2174234034699151, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.21410114433370248, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2146548541897379, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21502399409376152, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.21040974529346623, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.20764119601328904, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03449005858878759, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0339744474347597, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03295261604471763, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03302354589985052, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03293110314134121, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03333580340616448, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0323559272888848, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.032225110459747235, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.032782806149121414, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03467550165844425, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03433337556544716, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03241260618968757, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0342544266416527, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03683474932154459, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.039613788119295876, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.04354049705990063, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.05031766671785757, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.05850922697592579, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06253130892311477, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0668492625040544, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.06875996199684857, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07287045458198946, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.07695811745348091, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.07979984767702843, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.08239061925750704, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.08679180279970156, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.09309686278637798, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.09726259131964492, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.10389718898368971, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.10949829935495621, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.11620393223115204, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.11981113013600458, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.12681939328577863, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1302815804159265, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.13351063579423308, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1358588992462201, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14051839295990776, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1433055151553472, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.14550027620096043, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14766296843151674, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.14854482329145505, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.14991501839169222, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.151131905799656, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1513544312851363, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1506226519242944, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15140405808763294, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15187917155358846, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1482848790619736, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1494935363361114, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.6027290344238283, "validation/loss_best": 2.669405221939087, "validation/acc_best": 0.2174234034699151, "validation/f1_best": 0.151131905799656} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.8849716114997865, "train/grad": 0.03532270012423396, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.161146240234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1584814453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.154296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1502783203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.146356201171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.141397705078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13601318359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13039306640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.116888427734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11087158203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.102425537109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.095015869140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.084840087890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0756396484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.06712158203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.056533203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.044129638671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0302008056640624, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0170501708984374, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.00060791015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9834375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9641375732421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.943262939453125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.921651611328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.896090087890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8736480712890624, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.853895568847656, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.82802001953125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.7993194580078127, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7755998229980468, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.755704650878906, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7309526062011718, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7110359191894533, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6897816467285156, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6710807037353517, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.653504180908203, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6387853240966797, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6249739646911623, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6109385681152344, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6021153640747072, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.596001396179199, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5901979541778566, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5869876766204833, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.585497455596924, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.586350984573364, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.589114990234375, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.595223431587219, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6030213403701783, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005353699072729796, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005341988506261259, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005323587614111602, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005306344532873482, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0052905012830160554, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005270253650378436, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0052493362640962, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005228369852993638, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005204472972545773, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005182840246707201, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0051649772236123685, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005143742284271866, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005127628699410707, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005110405886080116, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005098627470433712, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005090208356268704, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005082005858421326, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005074006046634168, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005066444284748286, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005059953725431114, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005052208893466741, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005043991142883897, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005035060262307525, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005025648071896285, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0050156593206338584, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005003897941205651, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004993592000100761, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004984567484352737, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004972769238520414, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004959657553117722, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004948812536895275, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0049396840669214724, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004928587810136378, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004919719591271132, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004910472941119224, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00490278244484216, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004895952739752829, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004890739936381578, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004886841981206089, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004884262562263757, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004883861388079822, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004884947051759809, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004888390586711466, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004893224325496703, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0049007111042737965, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0049109502066858116, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004921593570616096, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004936600395012647, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0049517095857299865, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.159466028213501, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.156567335128784, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.151942253112793, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1475729942321777, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.143420696258545, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1379616260528564, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.132169485092163, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.126166582107544, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1188759803771973, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.11177659034729, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.105347156524658, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.096479654312134, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0885651111602783, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.078001022338867, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0684945583343506, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.059749126434326, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.048894166946411, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0363011360168457, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0222694873809814, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0091452598571777, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9929022789001465, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9761247634887695, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.957495927810669, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9376821517944336, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.917423963546753, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.893866777420044, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.873645544052124, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.856050491333008, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.833672285079956, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.809473991394043, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7900474071502686, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7741973400115967, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7552895545959473, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.740633010864258, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7257769107818604, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.713242530822754, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7021539211273193, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.693596839904785, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.686067581176758, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6790151596069336, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.675279140472412, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6729273796081543, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6710808277130127, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.67031192779541, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6704370975494385, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6719536781311035, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6746344566345215, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6807188987731934, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.689155101776123, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.067921742340347, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07622739018087855, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07899593946105574, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08213362864525656, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08416389811738649, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08970099667774087, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0932078257659653, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0932078257659653, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.09616094499815431, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10132890365448505, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.10409745293466224, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.11055740125507567, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.11590992986341823, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1273532668881506, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.13270579549649317, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.13824289405684753, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1435954226651901, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1496862310815799, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.15614617940199335, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.16002214839424142, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1626061277224068, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.16629752676264303, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1714654854189738, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1744186046511628, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.1788482834994463, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.18106312292358803, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1878922111480251, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.18992248062015504, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.19509043927648578, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.1969361387966039, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20191952750092285, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20431893687707642, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2069029162052418, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20893318567737174, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.20985603543743078, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21280915466961978, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21557770394979697, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21631598375784422, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21410114433370248, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2131782945736434, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21114802510151348, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.21336286452565523, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21354743447766703, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21354743447766703, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.21207087486157253, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2100406053894426, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03380845603716709, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.033819816433141706, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.033437122767127854, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03223561579486959, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03302683186810909, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.033174224928607506, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.031730192187461766, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03263511427960461, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03455304104015459, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0351402203082956, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03275578046849539, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03327102108292873, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03605060211543012, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03809213176133692, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04267481135852396, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.04846474653407557, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.057952988083664864, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06198487288045774, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0664525231756672, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.06924940484556884, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07239237103022916, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0768886681961934, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.07887941880362269, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0803134878401238, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.08379078394959254, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09040883027822337, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.09427154310053287, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.09936927809527966, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.10283824802414804, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.11046991014995254, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.11406110024894721, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.11939330963103724, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.12122550067860106, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.12708400762838584, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1296408889857376, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.13458150897700313, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.13853849786396236, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14060500384100452, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.14334661848383634, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14653180581763453, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.14959386028965016, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.14893232012124802, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14820745555517464, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14734680803173653, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15090429424138077, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15316640831267425, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15421877959370212, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15412678726251935, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15297064318589246, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 2.6021153640747072, "validation/loss_best": 2.675279140472412, "validation/acc_best": 0.21631598375784422, "validation/f1_best": 0.14959386028965016} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.878480026721954, "train/grad": 0.035274369213730096, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.159053955078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.156175537109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.151641845703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.147276611328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.143193359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.137813720703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.132161865234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126348876953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.119202880859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.112288818359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.10605224609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.097376708984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0896044921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0791455078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.069571533203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0607470703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.049541015625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0364190673828126, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.02166748046875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.00788818359375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9906439208984374, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9726800537109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.95268310546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.931270751953125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9091546630859373, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.883212890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.860675964355469, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.840784912109375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.81505859375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.786813049316406, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7634820556640625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7441595458984374, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7203697967529297, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7012198638916014, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6810237121582032, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6634552764892576, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6468340301513673, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6331080627441406, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6202462005615232, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6071111297607423, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5990741539001463, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.593397560119629, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.587922306060791, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.584945487976074, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.583779697418213, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.584847650527954, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.587919445037842, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.5943339443206788, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.602145528793335, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00533762427046895, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0053253001742996275, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005306222627405077, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005288764534052462, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005272774496115744, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005252124525140971, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005231504088733345, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005211180236656219, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005188494988251477, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005168439205735922, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005152495428919792, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0051338846841827036, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0051203844021074476, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005106445294804871, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005096996878273785, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005090092595200986, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005083195387851447, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005076172633562237, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005068951596040278, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005062320225406438, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005054208240471781, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005045908633619547, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005036367438733578, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005026420715730637, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0050157981365919115, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005003537395969033, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004992703939788044, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0049832566361874345, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004970922460779547, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004957223543897271, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004946067577693611, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00493651922326535, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004925157043617219, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004916038736701012, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004906638152897358, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004898646275978536, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004891381680499763, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004886000312399119, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004881370500661433, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0048776527214795355, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004876397766638547, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004876610478386283, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004878730121999979, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004882175913080573, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004888544878922403, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004898387619759887, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004909215450752526, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004925457346253097, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004942032352555543, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.157538414001465, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.15443754196167, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.149487257003784, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.144836902618408, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.140441417694092, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1346704959869385, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.128610610961914, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1223418712615967, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.114776849746704, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1074323654174805, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1007866859436035, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.091641902923584, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0834767818450928, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0725035667419434, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0625882148742676, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.05336594581604, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0419225692749023, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0285887718200684, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0137133598327637, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.999866008758545, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9827985763549805, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9652605056762695, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9458162784576416, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9253406524658203, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.9044740200042725, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8804843425750732, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.8599419593811035, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.842219829559326, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.819763660430908, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.795639753341675, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7764649391174316, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7608296871185303, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.74242901802063, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7282276153564453, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7138664722442627, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7019588947296143, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.691484212875366, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.683323860168457, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6763062477111816, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6698086261749268, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6661903858184814, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6639535427093506, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.661940097808838, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.660992383956909, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.660573959350586, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.660639762878418, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6609814167022705, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.661871910095215, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6634018421173096, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0753045404208195, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07770394979697305, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0799187892211148, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08379475821336287, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08674787744555186, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09062384643779993, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09339239571797711, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09560723514211886, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10022148394241417, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.1037283130306386, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1094499815430048, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.11590992986341823, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.12236987818383167, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.12993724621631597, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1362126245847176, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14304171280915468, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.14710225175341454, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.15430047988187523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.15946843853820597, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.16334440753045404, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.16648209671465486, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17109634551495018, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17700258397932817, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17847914359542266, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18106312292358803, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.18512366186784793, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1906607604282023, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.19472129937246216, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.19804355850867478, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.20284237726098192, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20505721668512367, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2081949058693245, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21040974529346623, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21354743447766703, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2144702842377261, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2174234034699151, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22056109265411591, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22148394241417496, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22148394241417496, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22111480251015134, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2222222222222222, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03430436138714361, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.032989245011391215, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03298587579567094, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.032548758097105265, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03297655631393261, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0324294796055409, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.032392655580568405, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03365748687954426, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03471084486350726, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0334562764996264, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03261883224107418, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03519066388945629, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03717035495209858, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04171362372946832, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04733076773357525, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05348238499018679, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.060332016600523695, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06465676624396294, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06927189012421493, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07096275898462501, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07571839234214835, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07913133663512437, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08079112569216433, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08318745888964632, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0874935170733921, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09573139947531457, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0993482968113527, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10450649114696782, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.10938033971360595, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.11461463319208252, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12030378859855434, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12437821517831922, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13048244860491098, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13284117202276347, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.13631650200515524, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.13959761777119298, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1439288458920037, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14546414811916616, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.14915332640996906, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15354263949778948, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1546755767489375, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15455093936541664, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15573023493008978, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15676537580258293, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.155863840328581, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15636529102934515, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1576534995294678, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.16218636093270636, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.16418943674148878, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 2.5943339443206788, "validation/loss_best": 2.661871910095215, "validation/acc_best": 0.22314507198228128, "validation/f1_best": 0.16218636093270636} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.86999192237854, "train/grad": 0.03534729352220893, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15726806640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.154329833984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.149588623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1450439453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1408642578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.135306396484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129483642578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1235595703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.116231689453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.10927490234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.102952880859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.09413330078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0861962890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.075390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0655078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.056165771484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.044407958984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.03065185546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.015107421875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.000650634765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.982576904296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9637921142578123, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9431011962890623, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.920943603515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8982080078125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8718856811523437, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.84894775390625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8289569091796873, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.8031842041015627, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.774705810546875, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.751675872802734, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7323992919921873, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7088062286376955, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6899067687988283, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.66996208190918, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6525253677368164, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.636021041870117, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6224066543579103, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6096144485473634, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.596295928955078, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.587965793609619, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5818419456481934, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5758860015869143, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.572359495162964, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5701959419250486, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.570202569961548, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5721983242034914, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.5771416664123534, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.583783974647522, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0053532747109420594, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005340050568338484, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005319872726686299, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00530138225061819, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005284422074910253, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005262963112909347, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005241269099060446, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005220507518388331, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005197468250989914, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0051775712193921205, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005161888049915433, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005143634979613125, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0051304923463612795, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0051170578994788225, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005107961934991181, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005101098755840212, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005093787210062146, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005086656047496945, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005078784129582345, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0050718993018381295, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005063227971550077, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00505448455689475, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005044745067134499, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005034501408226788, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005023900517262519, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005011598560959101, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005001056047622115, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0049917868478223685, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004979824314359576, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004966788713354617, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004956254162825644, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004947545581962913, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004936980134807527, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004928612464573235, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004919807151891291, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004912706222385168, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004906211316119879, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004900930325966328, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00489689337555319, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004893245913553983, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004891676225233823, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00489117075689137, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004892061350401491, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0048943444294855, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0048986040335148575, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004905376585666091, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004913324667140842, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004926177232991904, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00494102586293593, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1559126377105713, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.152623176574707, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1474242210388184, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.14254093170166, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1379458904266357, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.131951332092285, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.125669002532959, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1191837787628174, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1114161014556885, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1038832664489746, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0970823764801025, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0877151489257812, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.079329490661621, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.068004608154297, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0576910972595215, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.048126220703125, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0361673831939697, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0222666263580322, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0067713260650635, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9923951625823975, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9747393131256104, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9566359519958496, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.936795949935913, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.9159953594207764, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8949332237243652, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.870882749557495, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.8504748344421387, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.833035945892334, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.811022996902466, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7876150608062744, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7691924571990967, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.754281997680664, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.736732244491577, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7233104705810547, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7097108364105225, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.698478937149048, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.688542604446411, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.680781602859497, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.674062490463257, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6678006649017334, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.664355516433716, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.66219162940979, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.660245180130005, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6592562198638916, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.659287929534912, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.660518169403076, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.662700891494751, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6669139862060547, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.672125816345215, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0769656699889258, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07881136950904392, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08194905869324474, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08508674787744555, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08951642672572906, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09339239571797711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09486895533407161, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09726836471022518, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1020671834625323, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10668143226282761, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11184939091915837, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.11904761904761904, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1273532668881506, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.13344407530454042, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1391657438169066, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1448874123292728, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15153193060169803, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1583610188261351, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.16039128829826504, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.16352897748246586, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.16777408637873753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1716500553709856, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17534145441122184, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1806939830195644, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18309339239571798, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.18807678110003692, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.19269102990033224, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.19416758951642674, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1984126984126984, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.20191952750092285, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20487264673311184, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2070874861572536, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21096345514950166, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2131782945736434, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21520856404577335, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21613141380583242, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21926910299003322, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2222222222222222, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22056109265411591, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21853082318198597, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.21816168327796234, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.21539313399778517, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.033160536610151475, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03340847176243449, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03214562610515479, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03329920673207636, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03311239224146085, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03163064662020868, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03291607912021452, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03408612862197769, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03475944854759296, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03270442742955034, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.033091431243954327, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03611567313751655, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.038560238127978284, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.042722238050902556, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.049316185522923744, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05672702464855477, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.061823839567142325, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06628341763740174, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06908114425625587, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07284687032446242, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07675215241418527, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07780930791433825, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08002204069001136, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08460303802681356, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.08874637611600282, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09456355331819415, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10137511040274821, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10488620968618075, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1105558380271305, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.11488693538667281, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.11787222886207178, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12272053882819434, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.12697072229966927, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13050188540821905, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.13409933365769133, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.13840188266693967, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14164020740981081, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14340539619072232, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1445502948973679, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14704278069663915, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.14760017541642798, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.150552056482356, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1534421458605215, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15504627770040055, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1542608939221398, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1534730676455124, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1529471124705841, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15364581579934852, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1520416960952324, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.572359495162964, "validation/loss_best": 2.6592562198638916, "validation/acc_best": 0.22277593207825766, "validation/f1_best": 0.15504627770040055} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.862084939479828, "train/grad": 0.03508766004815698, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.156290283203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1531494140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.148116455078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.143411865234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13909423828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1333447265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127362060546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121065673828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.113699951171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1065380859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.100013427734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.090965576171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.082728271484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.071363525390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.060985107421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.051180419921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.03882568359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.024332275390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.007958984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9927264404296876, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.973890380859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.95437744140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9327056884765623, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9098602294921876, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8866168212890626, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8596151733398436, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.836212158203125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.81590087890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.789836730957031, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.7614486694335936, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7384263610839845, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7193190002441407, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6960681915283202, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6776187896728514, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.658079299926758, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6409578704833985, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6252217864990235, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.612008171081543, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.599714984893799, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5870136642456054, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5790804481506346, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5732013511657716, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.567460536956787, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.563815402984619, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.56152982711792, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.560899143218994, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.56209397315979, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.565561237335205, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.570478105545044, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0053235755558125675, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005309586536604911, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005288411695510149, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005268977920059115, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005251171239651739, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005228948348667472, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005206527148839086, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00518533700844273, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0051620027329772715, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0051422888482920825, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005126926107332111, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0051093032630160455, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005096522024832666, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0050834890571422875, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005074712217319757, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005067852614447474, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0050607092166319485, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005053005581721663, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005044982994440943, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005037582425866276, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00502878851024434, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005019535745959729, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0050094086211174725, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00499866854865104, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004987690772395581, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004974933550693094, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004963771479669959, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004954156421590596, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004941669474355877, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004928117557428777, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004916944294236601, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004907818485517055, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004896772289648652, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004887942143250256, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004879047556314618, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004871258544735611, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004864629933144897, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00485923032509163, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004854929826688021, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004851308830548078, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004850177515763789, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004850020797457546, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004851358199957758, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004853889304213226, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004858198876027018, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004864850086160004, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004871547322254628, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004882106119766832, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004892759490758181, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.154576301574707, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.151151180267334, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.145737886428833, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1406772136688232, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.135918378829956, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1297504901885986, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1232857704162598, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.116670608520508, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1087253093719482, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.101069450378418, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0941450595855713, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.084613800048828, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0760438442230225, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0644378662109375, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0538434982299805, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0439605712890625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.031625747680664, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.017274856567383, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.0013160705566406, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9865520000457764, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9684650897979736, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.950045585632324, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.929884433746338, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.908876895904541, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8877320289611816, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8637282848358154, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.8435163497924805, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8262135982513428, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.804607629776001, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.781735420227051, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.763859748840332, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.74945068359375, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.732550621032715, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.719848871231079, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7069244384765625, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6963322162628174, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.687098503112793, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6799349784851074, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.67391037940979, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6683452129364014, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6654560565948486, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.663630723953247, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.662205934524536, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6617488861083984, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6618518829345703, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6628916263580322, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6647698879241943, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.668613910675049, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6735501289367676, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06902916205241787, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07493540051679587, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07715023994093761, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07954964931709117, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08324104835732743, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08656330749354005, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09099298634182355, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09339239571797711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09542266519010704, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.09837578442229605, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10428202288667406, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10594315245478036, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11480251015134736, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12200073827980805, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.12975267626430417, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1362126245847176, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14138058324104835, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14544112218530822, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1524547803617571, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.15928386858619417, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.16039128829826504, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1626061277224068, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1674049464747139, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17331118493909192, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17681801402731634, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1821705426356589, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18272425249169436, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.18881506090808417, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.19139904023624954, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.19878183831672203, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.19933554817275748, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.20302694721299372, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20505721668512367, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.20782576596530086, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21040974529346623, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.20985603543743078, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2115171650055371, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21133259505352528, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21373200442967885, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2159468438538206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21557770394979697, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2144702842377261, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21631598375784422, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.21502399409376152, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.21336286452565523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21428571428571427, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.21354743447766703, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2144702842377261, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03295411685092967, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03332066196873775, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.032453480836484645, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03278240466274642, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03251290730929577, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.031856552227796854, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03349203893786228, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03450110969037006, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03375443638018164, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03265182253220892, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.033961353930676154, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.037271303164321846, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.038974371516318426, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04544815648365011, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.052326085920289395, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0590334292752078, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06377664657136, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06699661331056474, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06909437671288267, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07320559902730572, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07680785244775086, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07784785728903326, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.07961436690103663, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08372710304404342, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0909827537392951, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09556435034509847, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10270505309038543, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10355159427670836, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1114080025674332, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.11460834381471206, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12169569549365251, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12392416500284652, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.12892587126985108, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13249398472327767, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.136504333330996, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.13998990615634302, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1405528698160319, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14400576031703807, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1451943310696707, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14887000838457695, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15298122905580314, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.153914657823451, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15293512430654685, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1553978001905131, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15530160523913744, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1538999561221656, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15564988589345405, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1564345221465854, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15729010432190474, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.563815402984619, "validation/loss_best": 2.6617488861083984, "validation/acc_best": 0.21631598375784422, "validation/f1_best": 0.1553978001905131} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.85273265004158, "train/grad": 0.03512077739462256, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15461181640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1512255859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14599853515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.14107177734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1364892578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130511474609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.117862548828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.110146484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.102664794921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.09587158203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.086436767578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.077982177734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.066292724609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.05547119140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0452764892578124, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.032557373046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.017548828125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0006951904296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.98494873046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9656634521484375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.945797119140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.923758544921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.90053955078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.876900634765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.849645080566406, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.82623779296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8057492065429686, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7796560668945314, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.7512762451171877, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7281666564941407, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7090023040771483, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6857365417480468, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6670781707763673, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6474383544921873, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6300587463378906, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6137927627563475, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.6002022552490236, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.5872092056274414, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.573521366119385, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5648875427246094, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5582956314086913, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5515973281860354, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5469793701171874, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.543452043533325, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.541532440185547, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5415153217315676, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.543465805053711, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.5468647146224974, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005324195146095008, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0053100221301428975, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005288439337164164, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005268940881360322, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005251117115840316, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005228919347282499, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0052069648797623816, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005186076655518263, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005163584921974689, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005144939245656133, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005130441985093057, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005113841493148356, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005102514026220888, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005090696583501995, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005082642284687609, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005076348094735295, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005069451180752367, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00506204481702298, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005054082369897514, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005046797338873148, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005037973632570356, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005028765904717148, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005018579286988825, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005008111107163132, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004997169061098248, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0049846111913211645, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004973591896705329, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004964043113868683, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004951767609454692, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0049382660700939595, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00492728469427675, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004918142028618604, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004906993249896914, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004898146835621446, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004888697618152946, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004880461662542075, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004873015142511577, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004866980691440403, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004861721589695662, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004856799114495516, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004854485276155174, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0048530377889983356, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004852740233764053, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004853611423168331, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004855580001603812, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0048592272191308435, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004864024501293898, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004871558686718344, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004879742295015603, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.153534173965454, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1500158309936523, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1444458961486816, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1392407417297363, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.134376287460327, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1280643939971924, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12148118019104, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1147563457489014, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1067116260528564, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0989251136779785, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0919177532196045, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.082230567932129, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.07352614402771, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.061716318130493, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0508742332458496, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.040745258331299, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0281245708465576, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.013406991958618, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9970943927764893, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.982025623321533, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.963629722595215, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9449360370635986, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9245595932006836, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.903325080871582, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8820958137512207, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.858060359954834, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.837846040725708, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.820556879043579, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.799076557159424, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7763328552246094, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7585256099700928, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.744234323501587, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7275590896606445, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.714789390563965, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7020394802093506, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.69156551361084, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.682356595993042, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6752474308013916, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.669095754623413, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6633455753326416, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6600403785705566, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6579363346099854, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6560165882110596, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.655081272125244, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.654780387878418, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.655224084854126, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6562340259552, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.658134698867798, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6604387760162354, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07087486157253599, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07475083056478406, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07807308970099668, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08047249907715023, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08324104835732743, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08803986710963455, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09080841638981174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09357696566998892, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09653008490217793, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0991140642303433, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10391288298265043, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10741971207087486, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11517165005537099, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12513842746400886, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.13086009597637505, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1362126245847176, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14138058324104835, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14728682170542637, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15559246954595793, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.15909929863418235, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.16076042820228867, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1638981173864895, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.16925064599483206, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17331118493909192, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17755629383536362, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1806939830195644, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18290882244370615, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.18881506090808417, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1934293097083795, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.19952011812476927, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2011812476928756, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20653377630121816, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21096345514950166, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2131782945736434, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21483942414174972, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22406792174234036, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22443706164636398, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22609819121447028, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22739018087855298, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22720561092654115, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22609819121447028, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.2279438907345884, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22683647102251753, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22517534145441123, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03295497465924411, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03272829784084591, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.032220516273440324, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03287333061750875, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03194259731689862, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03171155743757075, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0335976709504991, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03366335405421091, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03290336985833182, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.032940954451781836, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.034041301296949086, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03709008447132871, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.040020907061114476, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04637356414507398, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.055434837098295275, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.059397448588208245, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06358663662334463, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06684533609516904, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06976605574903036, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07490691053205001, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07629642966538093, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07744009077128182, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08041441942367315, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08552756235574953, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.09119072992946077, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09701305738502906, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10186364629219048, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10539922676254543, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11242080998994464, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.11681132581001209, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12365632269065323, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12570764142447693, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13174965467559926, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1342052663953434, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1389974002556509, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14197771013571844, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14391290506919255, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14640216396399633, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1483083213401696, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15393341509222092, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15647205807014392, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1572650572558919, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1589339797875881, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1598184473697735, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15978700454481595, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1590900442902586, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.16052493317747382, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1600924270757074, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.16009311860491474, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 2.5415153217315676, "validation/loss_best": 2.6562340259552, "validation/acc_best": 0.2279438907345884, "validation/f1_best": 0.16052493317747382} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.8579206323623656, "train/grad": 0.035020997598767284, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1544873046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.151153564453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.145928955078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.141121826171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.136488037109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130555419921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1243505859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.118070068359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.110489501953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1032763671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0965869140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0873876953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0789306640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.06735107421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.056627197265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.046533203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0337615966796876, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0186322021484373, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.0019549560546874, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9862506103515627, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9669482421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9471893310546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.925364990234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.9025091552734374, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.879173583984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.852408752441406, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.829403991699219, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.809517517089844, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7842169189453125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.756653137207031, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.734392547607422, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.715989990234375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6936566162109377, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.676014709472656, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6573429107666016, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.640857849121094, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6255326080322265, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.612724380493164, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6003974151611327, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5874345397949217, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.578929901123047, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.572560386657715, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5657313537597655, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5609792709350585, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5568511581420896, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5541214752197265, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.552972412109375, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.553339729309082, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.5549609375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005308464039117098, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005294092658441513, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00527208510786295, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0052524172747507696, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005234384743962437, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005212116211187095, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005190351193305105, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005169795977417379, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0051478778361342846, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005129622863605619, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005115685563068837, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005099955350160599, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005089027381036431, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005077866844367236, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005070068917702884, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0050639865756966175, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005057029705494642, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0050493226619437335, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005041349597740918, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0050337981549091635, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005024667074903846, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005015380540862679, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005004980892408639, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004994335202500224, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004983159457333386, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004970565598923713, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004959722612984479, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004950161660090089, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004938071093056351, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004924844149500131, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004914075371343643, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0049051856435835366, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004894290918018669, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004885542683769018, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00487643331522122, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0048687024367973205, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004861479350365698, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004855634700506925, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004850318697281182, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0048451673449017105, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004842150721233338, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004840332099702209, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004839119669049978, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004839064059779048, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004840015752706677, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004842578272800892, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0048460906045511365, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0048516028583981095, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004857513592578471, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1527740955352783, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.149160385131836, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.143481492996216, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.138179063796997, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.133242130279541, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1268348693847656, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1201634407043457, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1133410930633545, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.105217933654785, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.097379446029663, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0902788639068604, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.080493450164795, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0716748237609863, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.059647560119629, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0486202239990234, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.038342237472534, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0254454612731934, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.010463237762451, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.993884563446045, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.978562593460083, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9598844051361084, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9409339427948, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.920320510864258, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.898918628692627, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8775622844696045, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8533897399902344, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.833116054534912, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.815876007080078, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7943716049194336, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.771751880645752, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7541251182556152, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.740018367767334, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7235262393951416, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7111217975616455, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.698758125305176, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6885969638824463, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6797847747802734, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6727802753448486, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.666896343231201, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6612226963043213, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6577939987182617, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.655606746673584, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.653395175933838, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.652071475982666, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6511244773864746, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6507956981658936, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6509814262390137, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.651815891265869, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6531434059143066, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07899593946105574, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08084163898117387, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08324104835732743, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08951642672572906, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0917312661498708, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09431524547803617, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09745293466223699, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.1005906238464378, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10465116279069768, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10908084163898117, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11646363971945367, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12606127722406793, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1314138058324105, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.13750461424880028, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14248800295311922, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14839424141749724, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15633074935400518, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.16020671834625322, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.16094499815430047, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.165374677002584, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.1699889258028793, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17423403469915097, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1792174234034699, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18235511258767073, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18733850129198967, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19010705057216684, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.1952750092284976, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.20062753783684018, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20228866740494647, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.20524178663713546, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2081949058693245, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21133259505352528, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2144702842377261, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21779254337393872, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2203765227021041, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22259136212624583, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22406792174234036, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22517534145441123, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2262827611664821, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22535991140642303, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22443706164636398, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22388335179032853, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.033052884753109274, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.032662844893978235, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.032884209650805456, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03313753160591917, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.031208657925228617, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03161079031263677, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03404272352370492, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.033858907667317355, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0326216433760161, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.032604530151817766, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03469035013573323, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03712298862310268, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.04093823657223286, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04660037518041999, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0558151799889793, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.059432730837894375, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06398452456639407, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0670325197611437, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07008107574377574, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07529111322138883, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07657493742572351, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07720364400389185, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08168976483120996, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08641763790160717, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.09343488490124278, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09931710302336473, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10383307500118731, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10942486292142811, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11344474690196821, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.11906799397292367, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1246477330264744, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12827710663726344, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13280868264658985, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1357746897678143, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.13980209223941656, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14242315691825358, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14461182187916247, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1462787377003089, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1493341004132598, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15347891967463698, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15609284695222275, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1582842413242199, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15952591609447808, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16056920896694704, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.16016700237250978, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15896283154580668, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1575509641426566, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15670069514665366, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15791075436782012, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.5609792709350585, "validation/loss_best": 2.652071475982666, "validation/acc_best": 0.2262827611664821, "validation/f1_best": 0.16056920896694704} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.8484988915920257, "train/grad": 0.03506535310298205, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15365966796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1501953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1445703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.139407958984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.134586181640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128409423828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.122003173828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.115377197265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1074365234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.09976318359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.09291015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.083267822265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.074625244140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.062568359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0515966796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.041163330078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.028011474609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.01260009765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9955548095703124, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.979495849609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.959888916015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.939732666015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.91765869140625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.894454345703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8708932495117185, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.843691711425781, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8205450439453124, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.800337219238281, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7746340942382814, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.746743469238281, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7241383361816407, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7053672790527346, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.682622375488281, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.664353332519531, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6451029205322265, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6281229400634767, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.612006301879883, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.598530502319336, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.585491180419922, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.571558532714844, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5623555755615235, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5553985595703126, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5477074813842773, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5422402954101564, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5373151397705076, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5336519622802736, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.531841812133789, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.531037712097168, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.531824378967285, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005319355851970613, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005304790469817817, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005282573143485934, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005262545184232295, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005244360400829464, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005221648283768445, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005199635766912252, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005179070848971606, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005157284857705236, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005139156940858811, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005125324490945786, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005109723936766386, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005099108149297535, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005088042379356921, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005080208091530949, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005073986197821796, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005066954814828932, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005059220846742391, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00505103068659082, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005043197951745242, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005033790012821555, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005024279574863613, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005013736709952354, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005002762826625258, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0049913449748419225, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004978465633466839, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004967342305462807, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0049576493469066915, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004945173503365367, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004931590214837343, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004920514049008489, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004911441954318434, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0049003859446384015, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0048914597602561114, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004882045602425933, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004873959326650947, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00486632289364934, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00486003827303648, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004854228335898369, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004848062451928854, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004844458212610334, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004841882174368948, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004839617011602968, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004838301411364227, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004837925736792386, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004838859594892711, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004840576329734177, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004844091690611094, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004848660100251436, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.15224289894104, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1485838890075684, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.142824649810791, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1374564170837402, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1324450969696045, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1259758472442627, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1192498207092285, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.112380027770996, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.104179620742798, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0962722301483154, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0891621112823486, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0792882442474365, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0703792572021484, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0582387447357178, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.047097682952881, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0366687774658203, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.023622512817383, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0084550380706787, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.991668939590454, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9761931896209717, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9573628902435303, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9382810592651367, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9175357818603516, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.896066904067993, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8746132850646973, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8504388332366943, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.830181121826172, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.812974214553833, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.791644334793091, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7692506313323975, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.751791000366211, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.737841844558716, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7216897010803223, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7094826698303223, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.697322368621826, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6872475147247314, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.678476572036743, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6716740131378174, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6655635833740234, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6599669456481934, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.65643572807312, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6541543006896973, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.651632785797119, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.649872064590454, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6485791206359863, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.647385358810425, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6468698978424072, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.646926164627075, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6474063396453857, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07235142118863049, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07862679955703211, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08194905869324474, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08453303802141011, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08988556662975268, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09246954595791805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09486895533407161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09745293466223699, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10114433370247324, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10483573274270949, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.10963455149501661, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11720191952750092, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12643041712809155, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.13178294573643412, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.13805832410483573, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14377999261720192, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.14987080103359174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15614617940199335, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.16039128829826504, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.16223698781838317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.16629752676264303, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17109634551495018, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17497231450719822, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1786637135474345, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18309339239571798, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.1864156515319306, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19047619047619047, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.19619785898855666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.20136581764488742, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20228866740494647, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20764119601328904, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21207087486157253, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2187153931339978, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22000738279808046, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22517534145441123, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2248062015503876, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22388335179032853, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21963824289405684, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22056109265411591, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22093023255813954, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.033557658500741765, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03257042627413634, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03289620447978254, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03238690578424296, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03160015132821961, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.032411293566706724, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03418384741549447, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03400358917373305, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03219490019671766, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03289149531644777, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.034703832887931454, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03713406494899172, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0410710996137498, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.047183811307242085, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05591779693547624, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.05953037657701129, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06442209991207722, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06781158129627966, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07105693472749298, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07521686989842717, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07676808071135505, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07825385366581734, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08274470201444625, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0872654027661031, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.09424245593637703, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.10024100942854747, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10438820291641426, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10908107397912366, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11401631903032068, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.12010449789540063, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12566257823894292, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12785526041416118, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13248519702635023, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13567549156017364, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.14016883904189872, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14241456795827195, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14580111508550722, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14856205376720177, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15227272220405116, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15358811801649697, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15673493048872306, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15844655869771682, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16019965471098582, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16039917716850202, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15947822457669528, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15815967856807542, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1559523580904276, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15680124154755212, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1571196353789258, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.5477074813842773, "validation/loss_best": 2.651632785797119, "validation/acc_best": 0.22517534145441123, "validation/f1_best": 0.16019965471098582} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.846019830703735, "train/grad": 0.035056432150304316, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15294189453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14951416015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1439306640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.138828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.134068603515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127957763671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12156005859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.115020751953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.107279052734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.099735107421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.09275390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.083255615234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.074608154296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.062554931640625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.051534423828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0409918212890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0278118896484374, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.01234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.994913330078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.978865966796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9589837646484374, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9386187744140626, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.916435546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.892957763671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8691806030273437, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.841719055175781, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8183026123046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7980743408203126, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7721820068359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.7440061950683594, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7214620971679686, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.702534484863281, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6796258544921874, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6614370727539063, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.642087936401367, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.625062484741211, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6088842010498046, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.595185317993164, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.5819906997680664, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5678089904785155, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.558175163269043, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5507983779907226, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.54245548248291, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5364757537841798, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.530745620727539, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5258452606201174, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.522906532287598, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.5206292343139647, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.519933204650879, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005318646980449557, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005304174807388335, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0052818228397518395, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005261522585060447, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005243452885188162, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0052210578694939615, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005199221952352673, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005178884421475231, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005157476738095284, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0051398342521861195, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005126339034177363, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0051114216516725715, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005101096762809902, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005090477224439382, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005082982266321779, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005076767592690885, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005069745606742799, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005062050563283265, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005053623975254595, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005045802358072251, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0050362278940156106, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005026539040263742, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005015887492336332, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005004666950553655, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004993141309823841, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004979878144804388, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004968421333469451, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004958437492605299, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004945751132909209, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00493175073293969, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004920615823939442, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004911106834188103, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0048996793711557985, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004890497515443713, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004880830184556544, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004872373815160245, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004864538686815649, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004857839012984187, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004851483299862593, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004844542925711721, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004840189765673131, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004836926748976111, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00483353303745389, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004831248016562313, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004829487393144518, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004828737350180745, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004828853812068701, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004830040200613439, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004832097752951086, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1519126892089844, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1482179164886475, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.14241623878479, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1370086669921875, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.131969690322876, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1254525184631348, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.118680715560913, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1117970943450928, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.10355806350708, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.095616579055786, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.088465929031372, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.078551769256592, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0695979595184326, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0573573112487793, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0461411476135254, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0356357097625732, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0225107669830322, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.007215976715088, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9902946949005127, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9747188091278076, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.955796480178833, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9366202354431152, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9158246517181396, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.8942713737487793, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.872842311859131, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8486626148223877, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.8284196853637695, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.81126070022583, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7899248600006104, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.767622947692871, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7502853870391846, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.736433744430542, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7203519344329834, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.708217144012451, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.69602108001709, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.686002254486084, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6772332191467285, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.670339345932007, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6643548011779785, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.658663511276245, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6553032398223877, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.652925968170166, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6505963802337646, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6491432189941406, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.647958517074585, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6469743251800537, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6464853286743164, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.646010398864746, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.645923376083374, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07272056109265411, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07604282022886674, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0784422296050203, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08231819859726837, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08471760797342193, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0902547065337763, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09228497600590624, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0946843853820598, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09745293466223699, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10151347360649686, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10520487264673312, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11037283130306386, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11812476928755998, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1271686969361388, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.132890365448505, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.13824289405684753, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14470284237726097, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.15079365079365079, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15725359911406422, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.16076042820228867, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1611295681063123, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.16703580657069028, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17183462532299743, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17515688445921004, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.1790328534514581, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18420081210778885, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18715393133997785, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19158361018826134, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.19712070874861573, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1998892580287929, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20210409745293467, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20930232558139536, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21040974529346623, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21336286452565523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21650055370985605, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21853082318198597, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22425249169435216, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22406792174234036, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2222222222222222, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22259136212624583, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03365584648368523, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03198019509674455, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.032680276079213165, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.032317324588685845, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03166080737871794, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.032483352446183666, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03424327303981837, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03407242309555746, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.032107903200874345, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.032800364535641516, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03513092436429629, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0376707942309431, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.041243077434956484, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.048152668947184486, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05676878293317137, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.060810722008045305, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06451707487345114, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06860625697416031, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07151030350256547, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07596101750569728, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07767258017377483, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07774055137720554, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0832844810007546, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08992739682232048, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.09437642690287186, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.10108646322061286, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10585612596520037, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.11012659029157656, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11518824267476162, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.12078350845928237, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1252380590517658, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.12814588346181294, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13255327020772686, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13717030448455533, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1390955803450843, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14305762173121025, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1448754253768514, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14853991224863608, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15158620967044908, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15483101993704815, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15654058170936017, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15691097715710295, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15835612963630388, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.158300687376666, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15766509617765737, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1573615886562696, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15753578671379392, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15728773263628057, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.15772313651220723, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.54245548248291, "validation/loss_best": 2.6505963802337646, "validation/acc_best": 0.22425249169435216, "validation/f1_best": 0.15835612963630388} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.8391684710979463, "train/grad": 0.03523512415587902, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.152384033203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.148897705078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.143153076171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13798828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13308837890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126778564453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1201708984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.113453369140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10543212890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.09771728515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.090499267578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0806494140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.071678466796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.059405517578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.047989501953125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0370941162109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0234552001953126, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.007547607421875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9896795654296877, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9731048583984374, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9527789306640626, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9320587158203124, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9093096923828123, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.8854119873046873, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8611520385742186, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.833402099609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8097845458984376, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7892355346679687, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7631903076171875, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.7350198364257814, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.712247619628906, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.6933811950683593, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6704885864257815, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6522476196289064, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6328690338134764, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.615818099975586, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.599531707763672, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.585804672241211, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.5724003601074217, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5579276275634766, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.548122901916504, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.540386848449707, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.531616516113281, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.52497745513916, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.518411865234375, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5128461837768556, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5090618896484376, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.5057354736328126, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.503871078491211, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005340989083051682, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005326532498002052, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005304345837794244, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005284364910330623, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005266329210717231, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005244321143254638, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005222750252578408, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005202679336071015, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005181717616505921, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005164506435394287, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005151251913048327, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005136985103599727, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00512687447713688, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00511664406163618, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005109274755232036, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005103269133251161, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005096542118117213, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0050889206700958315, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005080735282972455, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00507298359181732, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005063662661705166, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005054138817358762, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005043530664406717, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005032507465220988, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005021261456422507, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005008188060019165, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00499701067339629, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004987167029175907, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004974749251268804, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004960819054394961, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004949700841680169, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004940298651345074, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00492856181692332, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004919265271164477, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004909070851281286, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004900380002800376, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004891898212954402, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004884883309714496, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004877953880932182, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004870504576247186, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004865619002375751, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0048619081359356645, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004857682243455202, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004854713366366923, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004851941394153982, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0048499157885089515, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004848935473710299, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004848333748523146, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0048486392875202, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.151742935180664, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1480300426483154, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1421964168548584, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1367666721343994, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.131714105606079, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.125187873840332, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1184005737304688, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.111475944519043, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.103238105773926, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0952770709991455, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.0881032943725586, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.078179121017456, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.069200277328491, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0569257736206055, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0456299781799316, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0350944995880127, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0218966007232666, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0065555572509766, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9896023273468018, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.973994016647339, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9549920558929443, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9357805252075195, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9149599075317383, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.8934175968170166, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8719074726104736, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.847733736038208, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.827519655227661, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8104026317596436, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.789100170135498, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7668678760528564, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7495338916778564, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7357072830200195, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7197306156158447, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.707571506500244, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.695424795150757, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6854426860809326, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6766610145568848, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.66982364654541, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6638388633728027, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.657878875732422, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6543850898742676, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6518545150756836, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.649238109588623, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6474974155426025, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6457908153533936, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.644441604614258, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6436073780059814, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6428327560424805, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.642408609390259, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07327427094868956, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07641196013289037, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07918050941306755, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08342561830933924, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08527131782945736, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.09062384643779993, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09246954595791805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09505352528608342, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09745293466223699, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10169804355850867, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10538944259874493, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11055740125507567, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11794019933554817, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12753783684016243, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.13344407530454042, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.13861203396087118, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14470284237726097, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.15134736064968624, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15762273901808785, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.16039128829826504, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1613141380583241, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.16703580657069028, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17220376522702105, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17423403469915097, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17940199335548174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1836471022517534, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18733850129198967, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19158361018826134, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.19730527870062753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.20136581764488742, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20284237726098192, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2054263565891473, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2100406053894426, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21336286452565523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21391657438169065, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2159468438538206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2187153931339978, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2235142118863049, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22406792174234036, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2220376522702104, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22093023255813954, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.033254909116651264, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.032195453040205456, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03269181788264092, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.03248540268908525, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03201091307264883, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03265676888825713, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03436744885459827, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.03353140705011701, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0319969400077921, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.032812983015820744, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03516632530398578, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03782920386818287, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.04150119863626692, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.048552662157894604, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05682587214152316, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06116291001019128, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06460128936646363, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06867070798738542, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07223975944598572, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07625938798056013, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07724274909001826, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07797884264090531, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08331471165003923, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0900506589970664, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.09394420643545638, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1015327630784056, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10613276452871612, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.11037430719527998, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11536604472404698, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.12162578046052404, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12629823653194647, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1291276905820666, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13261743678083124, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13780301286553676, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1405216244420259, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14335220990961142, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14547026414706318, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14804551825195134, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15142844542180564, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15461679344712598, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15645072266299742, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15826675885331823, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15869691502852284, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15966751844925187, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.1595725975535454, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15836599560258724, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.1577115904697464, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1585034256326038, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1574770690227186, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.52497745513916, "validation/loss_best": 2.6474974155426025, "validation/acc_best": 0.22406792174234036, "validation/f1_best": 0.15966751844925187} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.8418563294410704, "train/grad": 0.03491413623094559, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.152742919921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.149208984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.143577880859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.138428955078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13364013671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12732421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1207861328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.114168701171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.10627197265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.09859130859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0916259765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0819677734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.073052978515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.06086669921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.049603271484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0387945556640625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.025418701171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.009644775390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9920263671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.975718994140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.955657958984375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.93518798828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9127032470703127, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.889097900390625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8652191162109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.837857360839844, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8144326782226563, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7940911865234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.7683416748046876, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.7402497863769533, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7176678466796873, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.6987225341796877, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6758761596679688, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.657645416259766, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6381424713134765, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.620950698852539, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6046190643310547, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5905657958984376, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.576865997314453, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.562114944458008, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5519525146484376, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.543928375244141, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.534710235595703, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5277691650390626, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.520542411804199, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5143509674072266, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5099114608764648, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.505501708984375, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.502825126647949, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.005298797939904034, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005284082046709954, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005261543665546924, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0052413461147807535, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.005223263481166213, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005200715796090663, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005178973632864654, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005158753276336938, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.005137607150245458, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00512014115229249, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0051069293823093175, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005092394666280598, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00508226994657889, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005071985288523138, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005064546328503639, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005058503544423729, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00505163508001715, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00504393809242174, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005035823334474117, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005028057491872459, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005018747234717011, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0050090740877203645, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004998439503833651, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004987351598683745, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004976063608191908, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004962915778160095, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004951459083240479, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004941570344381034, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004928942676633597, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004914778890088201, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004903646288439632, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004893857131246477, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004881958190817386, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004872568792197853, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004862394866067916, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004853324887808413, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004844708635937422, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004837316344492137, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00483025731286034, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004822451691143215, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004817331593949347, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004813323391135782, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004808698922861367, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004805532358586788, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0048024425818584855, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004799943526741117, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004798481112811714, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0047970551904290915, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004796474629547447, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.15167498588562, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.147963047027588, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1421127319335938, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1366848945617676, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1316206455230713, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.125070571899414, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1182732582092285, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.111356496810913, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1031105518341064, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.09515118598938, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.087970018386841, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0780234336853027, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.069009304046631, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.05674409866333, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.045469045639038, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0348899364471436, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0216739177703857, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.0063257217407227, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9893417358398438, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.973682403564453, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9546844959259033, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9354476928710938, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9146056175231934, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.893014669418335, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.871546983718872, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8473470211029053, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.8271243572235107, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.810035228729248, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.788759708404541, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7664546966552734, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7491767406463623, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.735325574874878, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.719339370727539, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7071783542633057, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6950430870056152, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6850647926330566, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6761958599090576, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6693453788757324, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.663247585296631, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6574339866638184, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6538732051849365, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.651289224624634, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6484808921813965, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.646656036376953, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6448426246643066, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.643361806869507, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6423139572143555, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.641395330429077, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6405396461486816, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07308970099667775, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07678110003691399, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07918050941306755, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08305647840531562, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08490217792543374, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0902547065337763, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09283868586194167, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09486895533407161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0976375046142488, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10132890365448505, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10520487264673312, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11055740125507567, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11830933923957179, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.12753783684016243, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.132890365448505, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1389811738648948, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14470284237726097, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.15153193060169803, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15780730897009967, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1598375784422296, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1613141380583241, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1674049464747139, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17238833517903285, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1746031746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.18032484311554078, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18383167220376523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18660022148394242, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19176818014027316, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.19767441860465115, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.20025839793281655, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20302694721299372, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2059800664451827, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20967146548541898, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21816168327796234, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22406792174234036, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22148394241417496, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.2222222222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.2233296419342931, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.03342858442805324, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03209837367530018, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.032979878183680096, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.032222150180763715, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.03194170011659237, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.032580290473984135, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.034230070275580476, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.034039067899426685, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.031905604031649555, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.032988928700785895, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03500694962157647, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.037780184823260565, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.041602660388669825, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.048467004593468345, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.056853502045664146, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06086424617401707, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06491875689707173, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06843027675273673, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07261219147162441, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0762806415496108, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0770953202769656, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07800163460182825, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08368887050167967, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.09016331307634123, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0942673799234901, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.10221631223191086, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10595887176139217, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10991704796305361, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11570611488367553, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.12205476163964017, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12553639703081762, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1291434295764775, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1330495829472323, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13767878754348767, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1406008535985299, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14380432774279156, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1454897640822644, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1469892957035629, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15137198468178567, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15505693646122187, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1571760217488901, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1584809075250563, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15938726944645887, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15891682464467302, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15925811293408285, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15803997183175608, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15825034442946137, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.15910906437756314, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1601816230232255, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.534710235595703, "validation/loss_best": 2.6484808921813965, "validation/acc_best": 0.22406792174234036, "validation/f1_best": 0.15938726944645887} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.842721185684204, "train/grad": 0.03509074406698346, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.152977294921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.14956787109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14416748046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13914794921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.134361572265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12833984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.121978759765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.115540771484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1077978515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.100301513671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.09343994140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.083951416015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.075250244140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0631591796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.051917724609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0412109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.0277374267578123, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.01187744140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.994134521484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.977598876953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.957391357421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9367596435546877, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.9140338134765624, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.8902142333984373, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.866125183105469, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.838456726074219, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.814844970703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.7944403076171875, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.768415832519531, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.740245056152344, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7175425720214843, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.698679656982422, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.6758128356933595, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6576397705078123, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.638294982910156, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6211561584472656, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.604849090576172, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5909407043457033, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.577387390136719, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5626397705078126, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.552492141723633, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.5443959045410156, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.535189971923828, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.528124008178711, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.5210234832763674, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.514522171020508, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.5098123931884766, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.505265121459961, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.5021871185302733, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00532641323748976, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.005311765915248543, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.005289301266893745, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.005269057822879404, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00525094942888245, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.005228505758568644, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.005206774005200714, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.005186614992562681, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0051653633546084165, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005147947461809963, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00513473070692271, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005120226335711777, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005110007820185274, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005099591882899403, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005092132641002536, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0050859211571514604, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0050790068204514685, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005071239261887968, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005062824846245349, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005055026174522937, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005045410313177854, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005035744500346482, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005024927023332566, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005013809504453093, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0050022435234859585, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004989041665103286, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004977594681549818, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004967616782523692, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004954785597510636, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004940545943100005, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004929079057183117, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0049192780116572975, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00490705156698823, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0048972905334085225, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0048868457833305, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004877452391665429, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004868467769119889, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004860775314737112, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004853252137545496, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00484505713917315, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004839410902932286, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004835168314166367, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00483005864545703, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0048262137616984545, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00482264417456463, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004819170807022602, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004816933230031282, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004814714817330241, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0048132043681107465, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1516644954681396, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1479525566101074, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.142104148864746, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.136672258377075, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1316022872924805, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1250579357147217, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.118256092071533, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.111340045928955, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1030948162078857, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.09513258934021, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.087946891784668, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.078007459640503, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0689854621887207, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.056718587875366, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0454423427581787, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0348527431488037, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.021641492843628, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.006291389465332, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.989292621612549, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9736435413360596, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9546396732330322, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.935413122177124, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.9145290851593018, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.89296293258667, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.8714823722839355, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8472678661346436, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.8270716667175293, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.8099746704101562, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.7887282371520996, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.7663936614990234, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.749089241027832, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.7352707386016846, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.71923565864563, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.707127571105957, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6949729919433594, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.684964418411255, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.676114082336426, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.66926646232605, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6632015705108643, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6572253704071045, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6536641120910645, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6511523723602295, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.648336410522461, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6464290618896484, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.6446640491485596, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6431546211242676, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.641976833343506, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.6408751010894775, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.6402428150177, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07290513104466592, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07659653008490218, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07918050941306755, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08305647840531562, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08508674787744555, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0902547065337763, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.09302325581395349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0946843853820598, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0976375046142488, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10132890365448505, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.10520487264673312, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11074197120708748, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.11794019933554817, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1273532668881506, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.132890365448505, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1389811738648948, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.14470284237726097, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.15153193060169803, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15780730897009967, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.1598375784422296, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1613141380583241, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.1674049464747139, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17220376522702105, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1744186046511628, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.18014027316352899, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18383167220376523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.18660022148394242, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19121447028423771, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.19730527870062753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.20044296788482835, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20302694721299372, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2056109265411591, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.20948689553340716, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21520856404577335, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2188999630860096, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22185308231819859, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22296050203026946, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22443706164636398, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2233296419342931, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2235142118863049, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2216685123661868, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.22129937246216316, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.22369878183831673, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.22443706164636398, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.033437449487741924, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03203118660670738, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03287999899059576, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.032221096916350264, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0319891141856263, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.032595989552557776, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.034222814802862045, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0340581970979442, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.03187649084623709, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.03297941688360249, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03500694962157647, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.037778049650028005, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.04167362995185563, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04834171870247722, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.05679063130291822, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.060855710219828274, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06491249581740029, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0684490598482792, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07257357834944714, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07627575227793139, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07707820178066548, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07799863826889851, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08371381206500451, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.09009840402000634, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.09420298017674476, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1020663121757142, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.10595245759439542, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10992018825467607, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11515735201984467, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.12171247991269947, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.12585604039854273, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1291411590904426, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13282954354781704, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13746514482272384, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.14064052812291186, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1438705470664674, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14554963288407666, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14757193732034232, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.152037851964534, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15594605962090427, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.15739016755323573, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1583026299780547, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1598170258403817, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15884873424909546, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.15939092579552036, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.15803057306850735, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15813688861633446, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.1605526047939031, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1614273702068336, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.535189971923828, "validation/loss_best": 2.648336410522461, "validation/acc_best": 0.22443706164636398, "validation/f1_best": 0.1598170258403817} diff --git a/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..52e5d8951b86abb39b0fc1c6f26985ee787a01e8 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..148c5c6db5d122761820de7e6fd3268d58715ac8 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,train,0.8469750889679716,0.013713431589130883,0.8323482073482074,0.01567838028755565,0.822360248447205,0.016075532825095943 +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,test,0.56,0.042283065167984205,0.47619047619047616,0.04918532913052271,0.48906048906048905,0.043752060719324706 +flat_mae,patch,logistic,ppmi_dx,1,0.000774263682681127,train,0.6868327402135231,0.013289277866743776,0.5891812865497076,0.021592291513289886,0.6065082423463927,0.015810376589471428 +flat_mae,patch,logistic,ppmi_dx,1,0.000774263682681127,test,0.65,0.030047236145775542,0.5269631031220435,0.050366175561861064,0.5598471986417657,0.03487706277047915 +flat_mae,patch,logistic,ppmi_dx,2,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,2,10000.0,test,0.59,0.0487274050201732,0.5626666666666666,0.051663229156721564,0.5623938879456706,0.05163961351456658 +flat_mae,patch,logistic,ppmi_dx,3,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,3,21.54434690031882,test,0.55,0.0474564684737497,0.52,0.04962095090073551,0.5199490662139219,0.049217176743732015 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,train,0.7615658362989324,0.015837689970495217,0.7253817990868912,0.019861897085760635,0.7159066581031899,0.01848471726424222 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,test,0.61,0.0403300136374884,0.5311936530833032,0.05041720075836507,0.5428692699490663,0.04302166336439922 +flat_mae,patch,logistic,ppmi_dx,5,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,5,2.782559402207126,test,0.56,0.04546124063419298,0.5098039215686274,0.049875637176166256,0.5127334465195246,0.04736400453910402 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,train,0.8469750889679716,0.014460207645357126,0.8331077348066298,0.01631109736837477,0.8244085848854634,0.01667358054473454 +flat_mae,patch,logistic,ppmi_dx,6,0.046415888336127774,test,0.6,0.04469080889847486,0.5659722222222222,0.04848190550698252,0.565365025466893,0.04716693658372838 +flat_mae,patch,logistic,ppmi_dx,7,0.3593813663804626,train,0.9626334519572953,0.007900436022805253,0.9601233938026037,0.008514981397054215,0.9557375294369514,0.00942608866946112 +flat_mae,patch,logistic,ppmi_dx,7,0.3593813663804626,test,0.56,0.0496826086271645,0.537620849096259,0.050143496789799395,0.5382003395585738,0.05048385466641547 +flat_mae,patch,logistic,ppmi_dx,8,0.005994842503189409,train,0.7633451957295374,0.015954817014470057,0.7270240560370171,0.019919376682673157,0.7173517448083921,0.01848864067775276 +flat_mae,patch,logistic,ppmi_dx,8,0.005994842503189409,test,0.67,0.03901988723715125,0.6033177064551027,0.051985269638431385,0.6065365025466893,0.04429139426403994 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,train,0.7508896797153025,0.016918336608555375,0.7122249531835206,0.021120834433650166,0.703757225433526,0.019391415180281764 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,test,0.61,0.044749721786844665,0.5741893219783819,0.05096163825484755,0.5734295415959253,0.048981297972940076 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,train,0.7580071174377224,0.01575268381186214,0.7221058755090168,0.019701327593604073,0.7130164846927853,0.018329653787562183 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,test,0.6,0.04257368201130835,0.5238095238095238,0.05246173679414779,0.5348047538200339,0.04552946911762569 +flat_mae,patch,logistic,ppmi_dx,11,0.005994842503189409,train,0.7686832740213523,0.015878529800193896,0.7343659104130308,0.019660005687683214,0.7242961892528367,0.018416674849136998 +flat_mae,patch,logistic,ppmi_dx,11,0.005994842503189409,test,0.59,0.04104862969698257,0.516452411841019,0.04997595745541942,0.5267402376910016,0.043575720686815055 +flat_mae,patch,logistic,ppmi_dx,12,0.000774263682681127,train,0.6921708185053381,0.01373123775327456,0.5952609910123678,0.02228883485703906,0.6117132305716121,0.016330875098030002 +flat_mae,patch,logistic,ppmi_dx,12,0.000774263682681127,test,0.6,0.025614644248944787,0.435347261434218,0.037887568854848896,0.499151103565365,0.026610587397851743 +flat_mae,patch,logistic,ppmi_dx,13,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,13,10000.0,test,0.54,0.04685061792548738,0.5166036149642708,0.0484553058888356,0.5169779286926994,0.048648669950036874 +flat_mae,patch,logistic,ppmi_dx,14,0.000774263682681127,train,0.6814946619217082,0.013413594113253857,0.5792902996466136,0.021917856382195698,0.5995637979019482,0.01588801735382857 +flat_mae,patch,logistic,ppmi_dx,14,0.000774263682681127,test,0.66,0.033274013884711885,0.5582120582120582,0.050510830024439686,0.5780984719864176,0.038064229540214156 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,train,0.7704626334519573,0.015087349674851562,0.7352338588629714,0.018994882782369226,0.7248715478484264,0.017668491711863504 +flat_mae,patch,logistic,ppmi_dx,15,0.005994842503189409,test,0.59,0.03667964558171193,0.5071523019593701,0.047536478697451104,0.5216468590831919,0.039796991870535856 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,train,0.8451957295373665,0.015575596121467594,0.8313552219037468,0.017570869355999365,0.8229634981802612,0.017982630893932355 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,test,0.6,0.04490382611760383,0.554367201426025,0.05011128706493877,0.5551782682512734,0.04727118574597413 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,train,0.7758007117437722,0.015499793588029285,0.7447553959946365,0.019093148016921222,0.7344251766217085,0.018162589364311803 +flat_mae,patch,logistic,ppmi_dx,17,0.005994842503189409,test,0.62,0.043211160595383234,0.5634191176470589,0.04999655663546582,0.566213921901528,0.04573238119519254 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,train,0.7740213523131673,0.015617303007888625,0.743091725187982,0.019008608916022515,0.7329800899165061,0.018069874672702973 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,test,0.57,0.03987919256955937,0.483110950835437,0.046204191148494576,0.5004244482173175,0.04057528757395148 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,train,0.9501779359430605,0.009248630380567915,0.946780303030303,0.009974908844759421,0.9421430100620852,0.010750499391808934 +flat_mae,patch,logistic,ppmi_dx,19,0.3593813663804626,test,0.61,0.047967701633495015,0.5793334052421529,0.05070520943727189,0.5785229202037352,0.05009307057441223 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,train,0.7651245551601423,0.016798003476872093,0.7294805782049973,0.021089533225841003,0.719666559623207,0.01959737092257138 +flat_mae,patch,logistic,ppmi_dx,20,0.005994842503189409,test,0.67,0.04153423166497726,0.6108031607500884,0.05231375861741512,0.6116298811544991,0.045962706904358275 +flat_mae,patch,logistic,ppmi_dx,21,0.005994842503189409,train,0.7366548042704626,0.016606394269805893,0.6929641934293097,0.0209224000812861,0.68610843502462,0.01891953734891421 +flat_mae,patch,logistic,ppmi_dx,21,0.005994842503189409,test,0.66,0.038997558897961804,0.5783730158730158,0.0540581406928642,0.5882852292020373,0.04370382127383393 +flat_mae,patch,logistic,ppmi_dx,22,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,22,21.54434690031882,test,0.56,0.04812502051947614,0.5225694444444444,0.05156168290941722,0.5229202037351443,0.05009472203565616 +flat_mae,patch,logistic,ppmi_dx,23,0.046415888336127774,train,0.8380782918149466,0.01503345222686976,0.82198041652308,0.017117061265176103,0.8119647827017769,0.017250417772944285 +flat_mae,patch,logistic,ppmi_dx,23,0.046415888336127774,test,0.63,0.045872885237359995,0.5906626839252129,0.05159926941045855,0.5895585738539898,0.04925213367548716 +flat_mae,patch,logistic,ppmi_dx,24,0.3593813663804626,train,0.9626334519572953,0.007863608390924882,0.9601987029673921,0.008434273814904464,0.9566072575465638,0.009097907954158475 +flat_mae,patch,logistic,ppmi_dx,24,0.3593813663804626,test,0.55,0.04680801213467625,0.5021573182874212,0.05104238811828223,0.5046689303904923,0.048657828461887334 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.8540925266903915,0.014504113516493524,0.8393972343035575,0.01644894692238689,0.8284494754870477,0.016625877459984298 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.62,0.04683069079140303,0.5703301673450927,0.05260827130863967,0.5713073005093379,0.04896954235633102 +flat_mae,patch,logistic,ppmi_dx,26,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,26,1291.5496650148827,test,0.5,0.049247436481506326,0.4791666666666667,0.04990538264546153,0.47962648556876064,0.05068598130449204 +flat_mae,patch,logistic,ppmi_dx,27,0.3593813663804626,train,0.9572953736654805,0.008386531564235418,0.9542946988898979,0.0090926031914658,0.948793084992507,0.010062719244885752 +flat_mae,patch,logistic,ppmi_dx,27,0.3593813663804626,test,0.63,0.0457994934469804,0.6093337556752191,0.04790517685611169,0.6099320882852293,0.0482225918347251 +flat_mae,patch,logistic,ppmi_dx,28,0.046415888336127774,train,0.8505338078291815,0.014511254245964963,0.8350869838608258,0.01671442046183708,0.8238198458574182,0.017081848685012297 +flat_mae,patch,logistic,ppmi_dx,28,0.046415888336127774,test,0.59,0.04305473725387254,0.5327635327635327,0.050388598423025295,0.5369269949066213,0.045753569292401985 +flat_mae,patch,logistic,ppmi_dx,29,0.3593813663804626,train,0.9590747330960854,0.00811427232611017,0.9562416425464209,0.008789933236503625,0.9511078998073217,0.009788731778936948 +flat_mae,patch,logistic,ppmi_dx,29,0.3593813663804626,test,0.56,0.047124732359982685,0.5280995280995281,0.050036550730670086,0.5280135823429541,0.049581103683298995 +flat_mae,patch,logistic,ppmi_dx,30,0.046415888336127774,train,0.8523131672597865,0.01321761267731341,0.8380094111927211,0.015183523753053254,0.8278741168914578,0.01570534474664229 +flat_mae,patch,logistic,ppmi_dx,30,0.046415888336127774,test,0.57,0.04936386937832163,0.5501621508525996,0.05046048012484104,0.551358234295416,0.051168398956059534 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,train,0.7562277580071174,0.015899761280726305,0.7179655305042216,0.019679844050746766,0.7089622136587455,0.01817815572279996 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,test,0.64,0.043979317866469914,0.5863970588235294,0.05209059957069275,0.5874363327674024,0.04748389855049405 +flat_mae,patch,logistic,ppmi_dx,32,0.046415888336127774,train,0.8487544483985765,0.014434970882973576,0.834487680991203,0.01635195969827293,0.8249839434810533,0.01668881790241361 +flat_mae,patch,logistic,ppmi_dx,32,0.046415888336127774,test,0.59,0.04799151591687847,0.5626666666666666,0.05076913782366488,0.5623938879456706,0.050295808053657486 +flat_mae,patch,logistic,ppmi_dx,33,0.005994842503189409,train,0.7580071174377224,0.016334215644680985,0.7212830199687851,0.02033283242152268,0.7121467565831727,0.018854717715959396 +flat_mae,patch,logistic,ppmi_dx,33,0.005994842503189409,test,0.64,0.045163808519654326,0.592944369063772,0.051367134810385,0.5925297113752122,0.047714389844199026 +flat_mae,patch,logistic,ppmi_dx,34,0.000774263682681127,train,0.6743772241992882,0.011584540583341903,0.5505355761540781,0.021594135435286644,0.5842164418754014,0.01424499383439276 +flat_mae,patch,logistic,ppmi_dx,34,0.000774263682681127,test,0.68,0.024667581965000112,0.5482778091473743,0.04765962669720731,0.5840407470288624,0.03072319455633551 +flat_mae,patch,logistic,ppmi_dx,35,0.046415888336127774,train,0.8683274021352313,0.013668971973881597,0.8560709885515733,0.015251826781716132,0.8460982658959537,0.0155142090101759 +flat_mae,patch,logistic,ppmi_dx,35,0.046415888336127774,test,0.6,0.04848205853715372,0.5755517826825127,0.05013528081879025,0.5755517826825127,0.05004905640978035 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,train,0.7669039145907474,0.01630160314720245,0.7327142094734664,0.02033628380161164,0.7228511025476343,0.019068516380702987 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,test,0.6,0.03687567762089261,0.503968253968254,0.04805341212110805,0.5246179966044142,0.03921953904757598 +flat_mae,patch,logistic,ppmi_dx,37,0.3593813663804626,train,0.9661921708185054,0.007737594353764254,0.9641864131072764,0.008214195073203027,0.9629763433954186,0.008599682599668415 +flat_mae,patch,logistic,ppmi_dx,37,0.3593813663804626,test,0.56,0.04616424590524576,0.5280995280995281,0.04877488419090629,0.5280135823429541,0.04785346735929977 +flat_mae,patch,logistic,ppmi_dx,38,0.046415888336127774,train,0.8505338078291815,0.014751756367569133,0.835866768653084,0.01679324869414022,0.8255593020766431,0.017038520109081825 +flat_mae,patch,logistic,ppmi_dx,38,0.046415888336127774,test,0.63,0.04482626016075845,0.6161427533976553,0.045967648966750964,0.6201188455008488,0.04688511490578909 +flat_mae,patch,logistic,ppmi_dx,39,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,39,2.782559402207126,test,0.56,0.04893684092787355,0.5280995280995281,0.051530234263042304,0.5280135823429541,0.050785923206491716 +flat_mae,patch,logistic,ppmi_dx,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,40,166.81005372000556,test,0.59,0.047855093772763625,0.5746446726838883,0.04864335423205851,0.5776740237691002,0.049370986673114924 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,train,0.8416370106761566,0.01371368647529525,0.8250598954234649,0.01585684013994739,0.813985228002569,0.016065243387797825 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,test,0.62,0.043666788294996005,0.5766488413547237,0.04964518794068216,0.5764006791171477,0.0468184266290451 +flat_mae,patch,logistic,ppmi_dx,42,0.046415888336127774,train,0.8523131672597865,0.014205617619117386,0.8380094111927211,0.016169906877292452,0.8278741168914578,0.016491833918817228 +flat_mae,patch,logistic,ppmi_dx,42,0.046415888336127774,test,0.6,0.04157000841953246,0.5404411764705883,0.048733502233366706,0.5449915110356536,0.044142618551651906 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,train,0.7544483985765125,0.01665298641111738,0.7204463860893637,0.02019949376244201,0.7118657675016057,0.018983244124777372 +flat_mae,patch,logistic,ppmi_dx,43,0.005994842503189409,test,0.59,0.044208863364714544,0.5327635327635327,0.051338815372829145,0.5369269949066213,0.046948873114374685 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,train,0.7597864768683275,0.015347471341711086,0.72291915462404,0.019326601009316612,0.713591843288375,0.017938316484141147 +flat_mae,patch,logistic,ppmi_dx,44,0.005994842503189409,test,0.58,0.04588139492212502,0.5174632352941176,0.05239136589706526,0.5237691001697793,0.04785574277968042 +flat_mae,patch,logistic,ppmi_dx,45,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,45,10000.0,test,0.63,0.04642938293796289,0.6093337556752191,0.048469641110641226,0.6099320882852293,0.04879700572567455 +flat_mae,patch,logistic,ppmi_dx,46,0.3593813663804626,train,0.9501779359430605,0.009204861435358406,0.946780303030303,0.00993147344384316,0.9421430100620852,0.010662583201098324 +flat_mae,patch,logistic,ppmi_dx,46,0.3593813663804626,test,0.57,0.04874197780148031,0.5361881134721174,0.05238487015427173,0.5360780984719864,0.05128559385356686 +flat_mae,patch,logistic,ppmi_dx,47,0.046415888336127774,train,0.8540925266903915,0.013493814916283741,0.8393972343035575,0.015403477106201498,0.8284494754870477,0.015633404044313574 +flat_mae,patch,logistic,ppmi_dx,47,0.046415888336127774,test,0.64,0.044437187129700274,0.592944369063772,0.05138972756329716,0.5925297113752122,0.04784935709344889 +flat_mae,patch,logistic,ppmi_dx,48,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,48,2.782559402207126,test,0.58,0.048776629649864074,0.565936337329475,0.04952393936579981,0.5696095076400679,0.050503535776952546 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,train,0.7597864768683275,0.015462074039080271,0.7261356868265743,0.018915823729593294,0.7170707557268251,0.017769891120687494 +flat_mae,patch,logistic,ppmi_dx,49,0.005994842503189409,test,0.59,0.04134239470567712,0.516452411841019,0.048474750413794385,0.5267402376910016,0.04301206676722522 +flat_mae,patch,logistic,ppmi_dx,50,0.3593813663804626,train,0.9697508896797153,0.007407070453046494,0.9678985548637687,0.007895119065360256,0.9658665168058231,0.008455760748398275 +flat_mae,patch,logistic,ppmi_dx,50,0.3593813663804626,test,0.53,0.04873853095857527,0.49304282170208175,0.050781438341929906,0.4936332767402377,0.05006338845984606 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,train,0.8523131672597865,0.013924249180446633,0.8368536103387371,0.016123645179416685,0.8252649325626205,0.01643636032486679 +flat_mae,patch,logistic,ppmi_dx,51,0.046415888336127774,test,0.55,0.046571562138283486,0.52,0.0493273823227316,0.5199490662139219,0.048832230798010044 +flat_mae,patch,logistic,ppmi_dx,52,0.005994842503189409,train,0.7740213523131673,0.016174944886663437,0.7423646831627773,0.01997804178243051,0.7321103618068936,0.01899419733847627 +flat_mae,patch,logistic,ppmi_dx,52,0.005994842503189409,test,0.54,0.04322156406239829,0.47987336047037543,0.04785678956116182,0.4864176570458404,0.044541719134023175 +flat_mae,patch,logistic,ppmi_dx,53,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,53,2.782559402207126,test,0.53,0.04838956499081181,0.4800309768779732,0.05166826621678807,0.483446519524618,0.049675133686322245 +flat_mae,patch,logistic,ppmi_dx,54,0.046415888336127774,train,0.8416370106761566,0.015155453471002727,0.8278583302072184,0.0170141219347075,0.8200733247698566,0.01738101799940209 +flat_mae,patch,logistic,ppmi_dx,54,0.046415888336127774,test,0.55,0.04512231820285832,0.52,0.04622701014076199,0.5199490662139219,0.045846470980162535 +flat_mae,patch,logistic,ppmi_dx,55,0.046415888336127774,train,0.8469750889679716,0.014454040148169863,0.8315629530500726,0.016427902594844446,0.8209296724470134,0.016503931762444836 +flat_mae,patch,logistic,ppmi_dx,55,0.046415888336127774,test,0.6,0.0470892769109911,0.554367201426025,0.05265875603005206,0.5551782682512734,0.04954898103565885 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,train,0.7686832740213523,0.016224114593804753,0.7319685963753761,0.020457306113743183,0.7216870049239992,0.018995902426436805 +flat_mae,patch,logistic,ppmi_dx,56,0.005994842503189409,test,0.62,0.045612151889600654,0.5766488413547237,0.05177256230897252,0.5764006791171477,0.04893519482033321 +flat_mae,patch,logistic,ppmi_dx,57,0.005994842503189409,train,0.7544483985765125,0.01463169802344563,0.7163360252808989,0.01844711874312502,0.7075171269535432,0.01703397311452522 +flat_mae,patch,logistic,ppmi_dx,57,0.005994842503189409,test,0.63,0.045990759941536084,0.5783475783475784,0.05265820316363649,0.5793718166383701,0.04854310425849429 +flat_mae,patch,logistic,ppmi_dx,58,0.046415888336127774,train,0.8451957295373665,0.015144570804341393,0.8298054531594281,0.017344862652196445,0.8194845857418112,0.017657338851108064 +flat_mae,patch,logistic,ppmi_dx,58,0.046415888336127774,test,0.63,0.04650375898784957,0.5906626839252129,0.051614197804140755,0.5895585738539898,0.04929707974333597 +flat_mae,patch,logistic,ppmi_dx,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,59,166.81005372000556,test,0.59,0.04995698549752577,0.5746446726838883,0.050715567436354934,0.5776740237691002,0.051542316208525486 +flat_mae,patch,logistic,ppmi_dx,60,0.005994842503189409,train,0.7562277580071174,0.015525356732225066,0.7188142532110628,0.019282847054733106,0.709831941768358,0.017834422925158043 +flat_mae,patch,logistic,ppmi_dx,60,0.005994842503189409,test,0.63,0.03821007197062053,0.5552350042072365,0.04987238422041501,0.5640916808149405,0.04219072786072208 +flat_mae,patch,logistic,ppmi_dx,61,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,61,1291.5496650148827,test,0.56,0.04654623078187963,0.5225694444444444,0.0497727750417674,0.5229202037351443,0.04857185483614281 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,train,0.7562277580071174,0.0157402243851457,0.7179655305042216,0.019957669026006836,0.7089622136587455,0.01841037034897521 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,test,0.63,0.04208199615037291,0.5552350042072365,0.05320429874750593,0.5640916808149405,0.04536945784315508 +flat_mae,patch,logistic,ppmi_dx,63,0.046415888336127774,train,0.8647686832740213,0.013716700422029314,0.8540957846553255,0.015065575456468108,0.8475567330336116,0.015477981871442396 +flat_mae,patch,logistic,ppmi_dx,63,0.046415888336127774,test,0.51,0.044536093227852847,0.4415954415954416,0.047892874648637264,0.45203735144312396,0.0447579507984783 +flat_mae,patch,logistic,ppmi_dx,64,0.3593813663804626,train,0.9697508896797153,0.007164082033101578,0.9677799024021745,0.007702838143773647,0.9641270605865981,0.008634951573344223 +flat_mae,patch,logistic,ppmi_dx,64,0.3593813663804626,test,0.55,0.04883410283807822,0.529239460194581,0.04932696672231545,0.5301358234295416,0.04978203623901016 +flat_mae,patch,logistic,ppmi_dx,65,0.3593813663804626,train,0.9661921708185054,0.006993146065503453,0.9639211658214033,0.007536969085699094,0.9594974309569686,0.00840198657189258 +flat_mae,patch,logistic,ppmi_dx,65,0.3593813663804626,test,0.57,0.046861920575238906,0.5501621508525996,0.04906579644340615,0.551358234295416,0.04968516682371925 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,train,0.7651245551601423,0.016671820777417985,0.7348146877144819,0.020167240193672994,0.7257546563904946,0.019263094299264105 +flat_mae,patch,logistic,ppmi_dx,66,0.005994842503189409,test,0.52,0.0386440163544112,0.4171928120446819,0.042621336469192035,0.44482173174872663,0.037869339558129295 +flat_mae,patch,logistic,ppmi_dx,67,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,67,21.54434690031882,test,0.53,0.049205024133720326,0.5242433444680635,0.048700773537173926,0.5343803056027165,0.05030552309834309 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,train,0.7740213523131673,0.016289245983378334,0.7385519881316508,0.020507324883405568,0.7277617212588311,0.01906430157358431 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,test,0.61,0.04098516316912744,0.5400400990682863,0.04977241333151689,0.547962648556876,0.043723794213069954 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,train,0.8612099644128114,0.01409011086809735,0.8502562000409921,0.015409862976205743,0.8437968315135945,0.01578501778188466 +flat_mae,patch,logistic,ppmi_dx,69,0.046415888336127774,test,0.6,0.04606994682002574,0.5477159656264134,0.05184201354502542,0.5500848896434635,0.048247907660562646 +flat_mae,patch,logistic,ppmi_dx,70,0.046415888336127774,train,0.8558718861209964,0.014428197490177598,0.8433317387279179,0.016103069118042303,0.835112930849925,0.016487326975405066 +flat_mae,patch,logistic,ppmi_dx,70,0.046415888336127774,test,0.53,0.04570284455042158,0.4725620020199753,0.049434398589855995,0.47835314091680814,0.04646888066385927 +flat_mae,patch,logistic,ppmi_dx,71,0.000774263682681127,train,0.6868327402135231,0.014535911190038771,0.5946561757233013,0.022862834646135533,0.6091174266752302,0.017189315125684064 +flat_mae,patch,logistic,ppmi_dx,71,0.000774263682681127,test,0.61,0.03519645436688191,0.48677457560205295,0.04729523625610396,0.5224957555178268,0.036818166586864175 +flat_mae,patch,logistic,ppmi_dx,72,0.046415888336127774,train,0.8540925266903915,0.013807654454630629,0.838623375168086,0.015969768178778692,0.8267100192678227,0.016254303760625425 +flat_mae,patch,logistic,ppmi_dx,72,0.046415888336127774,test,0.6,0.04204635061453015,0.5477159656264134,0.048109626565484856,0.5500848896434635,0.04459811574806294 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,train,0.7615658362989324,0.016302428567202456,0.7245581694756554,0.020450840489763623,0.7150369299935774,0.01894420185444264 +flat_mae,patch,logistic,ppmi_dx,73,0.005994842503189409,test,0.6,0.04400756298637769,0.5477159656264134,0.04955542677943155,0.5500848896434635,0.04607594008504673 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7669039145907474,0.016430579931643013,0.7342501849946758,0.020330141566391013,0.7245905587668593,0.019256445399378208 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.55,0.04555739676496013,0.4950061721467849,0.04979825695800772,0.49957555178268254,0.04672621608479725 +flat_mae,patch,logistic,ppmi_dx,75,0.000774263682681127,train,0.693950177935943,0.01402354653423862,0.6021140674394099,0.022318893407187804,0.6157675016056519,0.01668733289492568 +flat_mae,patch,logistic,ppmi_dx,75,0.000774263682681127,test,0.62,0.030200258277041286,0.4791666666666667,0.04613837041470895,0.5254668930390493,0.03261887804278316 +flat_mae,patch,logistic,ppmi_dx,76,0.046415888336127774,train,0.8416370106761566,0.015099831582445352,0.8278583302072184,0.016815424988419668,0.8200733247698566,0.017110256473364137 +flat_mae,patch,logistic,ppmi_dx,76,0.046415888336127774,test,0.6,0.04892197870078438,0.5659722222222222,0.05274968030730707,0.565365025466893,0.051170311988565996 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,train,0.8469750889679716,0.014409489094704773,0.8307513446884804,0.016633073656771982,0.8191902162277884,0.016877524909978184 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,test,0.66,0.04317840200841156,0.6212121212121212,0.04925184981254044,0.6188455008488964,0.046689928997204644 +flat_mae,patch,logistic,ppmi_dx,78,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,78,1291.5496650148827,test,0.54,0.04779948116873236,0.5066495066495067,0.04840839302304163,0.5067911714770797,0.04795791235235949 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,train,0.7544483985765125,0.016381628314338932,0.7154743561523222,0.020363679930052857,0.7066473988439306,0.018754414342048394 +flat_mae,patch,logistic,ppmi_dx,79,0.005994842503189409,test,0.63,0.03711497810857499,0.5360501567398119,0.049795827557103566,0.5539049235993209,0.040242786600766196 +flat_mae,patch,logistic,ppmi_dx,80,0.005994842503189409,train,0.7473309608540926,0.015575281042958038,0.7054115909929863,0.02017725892340405,0.6973881395846714,0.018296985754075363 +flat_mae,patch,logistic,ppmi_dx,80,0.005994842503189409,test,0.61,0.0415020915135611,0.5400400990682863,0.050752661363583806,0.547962648556876,0.044514136727785085 +flat_mae,patch,logistic,ppmi_dx,81,0.000774263682681127,train,0.6779359430604982,0.014407238938573836,0.5803599790431637,0.02240713636407196,0.5984130807107686,0.016697548392862704 +flat_mae,patch,logistic,ppmi_dx,81,0.000774263682681127,test,0.66,0.02699999259259157,0.5200451722190853,0.04798913485275384,0.5628183361629882,0.03168790051137242 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,train,0.8576512455516014,0.014769324687010508,0.844044844044844,0.01683309519054845,0.8339488332262899,0.01740919864715706 +flat_mae,patch,logistic,ppmi_dx,82,0.046415888336127774,test,0.68,0.04276868012927216,0.64349376114082,0.049308222274909226,0.6400679117147707,0.046977412694595204 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,train,0.7686832740213523,0.01704195036039654,0.736652392692879,0.02082772814397486,0.7269053735816742,0.01968894921706045 +flat_mae,patch,logistic,ppmi_dx,83,0.005994842503189409,test,0.54,0.04746500184346357,0.5008680555555556,0.050597269784281564,0.50169779286927,0.04936542553501477 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,train,0.8398576512455516,0.014627157071362992,0.824951202292454,0.01642627387967888,0.8160190537358167,0.016581131051200636 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,test,0.59,0.04584870336225442,0.5523528769516323,0.04977991645094833,0.5522071307300509,0.04820728418381723 +flat_mae,patch,logistic,ppmi_dx,85,0.000774263682681127,train,0.6779359430604982,0.013177018121059614,0.5784679775397302,0.020945168625441324,0.5975433526011561,0.015386659017938929 +flat_mae,patch,logistic,ppmi_dx,85,0.000774263682681127,test,0.65,0.030229813098992194,0.539413080668509,0.04720727387978017,0.5649405772495755,0.03443535700189057 +flat_mae,patch,logistic,ppmi_dx,86,0.046415888336127774,train,0.8451957295373665,0.014864667297353817,0.8305932734851136,0.016828262078611912,0.8212240419610362,0.017130178602020273 +flat_mae,patch,logistic,ppmi_dx,86,0.046415888336127774,test,0.57,0.046373423423335905,0.5361881134721174,0.04999668342221381,0.5360780984719864,0.04886210060721715 +flat_mae,patch,logistic,ppmi_dx,87,0.3593813663804626,train,0.9626334519572953,0.0076652020356734185,0.9601233938026037,0.008273386686105885,0.9557375294369514,0.009244924209183427 +flat_mae,patch,logistic,ppmi_dx,87,0.3593813663804626,test,0.56,0.048554859694988295,0.537620849096259,0.05008713203005423,0.5382003395585738,0.05037173981445745 +flat_mae,patch,logistic,ppmi_dx,88,0.3593813663804626,train,0.9555160142348754,0.008682062659801707,0.95243656798524,0.009421755470392278,0.9473479982873046,0.010551063560793605 +flat_mae,patch,logistic,ppmi_dx,88,0.3593813663804626,test,0.63,0.047130537870896404,0.6053333333333333,0.04984526921924103,0.6048387096774194,0.049569086164361426 +flat_mae,patch,logistic,ppmi_dx,89,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,89,21.54434690031882,test,0.59,0.049593047899882094,0.5670995670995671,0.05253010513677805,0.5674872665534805,0.05269496224505331 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,train,0.7722419928825622,0.015035294907559435,0.7392149185771668,0.018649646942967894,0.7289258188824663,0.017489913794338435 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,test,0.57,0.046490304365534106,0.5242836596968692,0.04987197503820543,0.5258913412563667,0.047920642655449264 +flat_mae,patch,logistic,ppmi_dx,91,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,91,1291.5496650148827,test,0.58,0.04643677852736987,0.5586380832282472,0.04809045432021896,0.5594227504244482,0.048449465360040626 +flat_mae,patch,logistic,ppmi_dx,92,0.046415888336127774,train,0.8202846975088968,0.015334872632781922,0.8019490375187978,0.01772721102364473,0.7922955469920787,0.01789079082596796 +flat_mae,patch,logistic,ppmi_dx,92,0.046415888336127774,test,0.68,0.04499608427407878,0.6483516483516483,0.049963533806217,0.6451612903225806,0.048542093062049714 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,train,0.7669039145907474,0.016669055860633285,0.7342501849946758,0.02056058627932845,0.7245905587668593,0.019455826713300112 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,test,0.61,0.04640628836698751,0.5623386825272135,0.05189092402687307,0.5632427843803056,0.04900553943395027 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,train,0.7508896797153025,0.01593798335210255,0.7147663171937761,0.01949504420378673,0.7063664097623634,0.018211705679519734 +flat_mae,patch,logistic,ppmi_dx,94,0.005994842503189409,test,0.66,0.04031612580593527,0.609375,0.04933164548376999,0.6086587436332768,0.044721179551901066 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,train,0.7651245551601423,0.0164614948687202,0.7348146877144819,0.019444172569967146,0.7257546563904946,0.018510030839648504 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,test,0.59,0.04553523470895917,0.539894512400404,0.0507136366184342,0.5420203735144312,0.047556380679542175 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,train,0.7615658362989324,0.016204845846628957,0.7261925538103549,0.020095894124981088,0.7167763862128024,0.018774238624649803 +flat_mae,patch,logistic,ppmi_dx,96,0.005994842503189409,test,0.56,0.04127668106812852,0.47619047619047616,0.04888690551928722,0.4923599320882852,0.04266529640876891 +flat_mae,patch,logistic,ppmi_dx,97,0.046415888336127774,train,0.8629893238434164,0.013763464700992769,0.8500653110155603,0.015478275553539521,0.8400235495611218,0.01576463677146108 +flat_mae,patch,logistic,ppmi_dx,97,0.046415888336127774,test,0.63,0.04196479953484826,0.5847828526540231,0.047776030622713926,0.5844651952461799,0.04485246537093719 +flat_mae,patch,logistic,ppmi_dx,98,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,98,166.81005372000556,test,0.54,0.04911105374556729,0.5118845500848896,0.050198425578294986,0.5118845500848896,0.05003868908088707 +flat_mae,patch,logistic,ppmi_dx,99,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,99,166.81005372000556,test,0.56,0.048124604933443345,0.548440065681445,0.04884441608083412,0.5534804753820034,0.05033754849584416 +flat_mae,patch,logistic,ppmi_dx,100,0.005994842503189409,train,0.7615658362989324,0.016335280919463777,0.7269906178854715,0.020164921193872,0.7176461143224149,0.018873164787982514 +flat_mae,patch,logistic,ppmi_dx,100,0.005994842503189409,test,0.62,0.040239781311533,0.5558672276764843,0.04986051904347404,0.5611205432937181,0.04371166579326239 diff --git a/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..fa49a6fdafe7e27a8331537c8eab3a7ffe32cbcb --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:44:43 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:16:55 time: 4.3792 data: 3.4674 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:24 time: 0.2006 data: 0.0708 max mem: 3005 +extract (train) [ 40/232] eta: 0:00:57 time: 0.1967 data: 0.0712 max mem: 3005 +extract (train) [ 60/232] eta: 0:00:44 time: 0.1675 data: 0.0541 max mem: 3005 +extract (train) [ 80/232] eta: 0:00:36 time: 0.1841 data: 0.0634 max mem: 3005 +extract (train) [100/232] eta: 0:00:30 time: 0.1925 data: 0.0698 max mem: 3005 +extract (train) [120/232] eta: 0:00:24 time: 0.1784 data: 0.0598 max mem: 3005 +extract (train) [140/232] eta: 0:00:19 time: 0.1753 data: 0.0599 max mem: 3005 +extract (train) [160/232] eta: 0:00:15 time: 0.1773 data: 0.0600 max mem: 3005 +extract (train) [180/232] eta: 0:00:10 time: 0.1662 data: 0.0542 max mem: 3005 +extract (train) [200/232] eta: 0:00:06 time: 0.1858 data: 0.0653 max mem: 3005 +extract (train) [220/232] eta: 0:00:02 time: 0.1559 data: 0.0479 max mem: 3005 +extract (train) [231/232] eta: 0:00:00 time: 0.1519 data: 0.0472 max mem: 3005 +extract (train) Total time: 0:00:45 (0.1982 s / it) +extract (validation) [ 0/50] eta: 0:03:03 time: 3.6719 data: 3.4193 max mem: 3005 +extract (validation) [20/50] eta: 0:00:11 time: 0.2247 data: 0.0855 max mem: 3005 +extract (validation) [40/50] eta: 0:00:02 time: 0.1479 data: 0.0419 max mem: 3005 +extract (validation) [49/50] eta: 0:00:00 time: 0.1515 data: 0.0455 max mem: 3005 +extract (validation) Total time: 0:00:12 (0.2542 s / it) +extract (test) [ 0/50] eta: 0:02:51 time: 3.4200 data: 3.2778 max mem: 3005 +extract (test) [20/50] eta: 0:00:10 time: 0.2123 data: 0.0789 max mem: 3005 +extract (test) [40/50] eta: 0:00:02 time: 0.1454 data: 0.0398 max mem: 3005 +extract (test) [49/50] eta: 0:00:00 time: 0.1508 data: 0.0434 max mem: 3005 +extract (test) Total time: 0:00:12 (0.2441 s / it) +feature extraction time: 0:01:10 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | train | 0.84698 | 0.013713 | 0.83235 | 0.015678 | 0.82236 | 0.016076 | +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | test | 0.56 | 0.042283 | 0.47619 | 0.049185 | 0.48906 | 0.043752 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 0.000774263682681127, "split": "test", "acc": 0.65, "acc_std": 0.030047236145775542, "f1": 0.5269631031220435, "f1_std": 0.050366175561861064, "bacc": 0.5598471986417657, "bacc_std": 0.03487706277047915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 10000.0, "split": "test", "acc": 0.59, "acc_std": 0.0487274050201732, "f1": 0.5626666666666666, "f1_std": 0.051663229156721564, "bacc": 0.5623938879456706, "bacc_std": 0.05163961351456658} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 21.54434690031882, "split": "test", "acc": 0.55, "acc_std": 0.0474564684737497, "f1": 0.52, "f1_std": 0.04962095090073551, "bacc": 0.5199490662139219, "bacc_std": 0.049217176743732015} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.0403300136374884, "f1": 0.5311936530833032, "f1_std": 0.05041720075836507, "bacc": 0.5428692699490663, "bacc_std": 0.04302166336439922} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.04546124063419298, "f1": 0.5098039215686274, "f1_std": 0.049875637176166256, "bacc": 0.5127334465195246, "bacc_std": 0.04736400453910402} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04469080889847486, "f1": 0.5659722222222222, "f1_std": 0.04848190550698252, "bacc": 0.565365025466893, "bacc_std": 0.04716693658372838} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.0496826086271645, "f1": 0.537620849096259, "f1_std": 0.050143496789799395, "bacc": 0.5382003395585738, "bacc_std": 0.05048385466641547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.03901988723715125, "f1": 0.6033177064551027, "f1_std": 0.051985269638431385, "bacc": 0.6065365025466893, "bacc_std": 0.04429139426403994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.044749721786844665, "f1": 0.5741893219783819, "f1_std": 0.05096163825484755, "bacc": 0.5734295415959253, "bacc_std": 0.048981297972940076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04257368201130835, "f1": 0.5238095238095238, "f1_std": 0.05246173679414779, "bacc": 0.5348047538200339, "bacc_std": 0.04552946911762569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.04104862969698257, "f1": 0.516452411841019, "f1_std": 0.04997595745541942, "bacc": 0.5267402376910016, "bacc_std": 0.043575720686815055} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.025614644248944787, "f1": 0.435347261434218, "f1_std": 0.037887568854848896, "bacc": 0.499151103565365, "bacc_std": 0.026610587397851743} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 10000.0, "split": "test", "acc": 0.54, "acc_std": 0.04685061792548738, "f1": 0.5166036149642708, "f1_std": 0.0484553058888356, "bacc": 0.5169779286926994, "bacc_std": 0.048648669950036874} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.000774263682681127, "split": "test", "acc": 0.66, "acc_std": 0.033274013884711885, "f1": 0.5582120582120582, "f1_std": 0.050510830024439686, "bacc": 0.5780984719864176, "bacc_std": 0.038064229540214156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.03667964558171193, "f1": 0.5071523019593701, "f1_std": 0.047536478697451104, "bacc": 0.5216468590831919, "bacc_std": 0.039796991870535856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04490382611760383, "f1": 0.554367201426025, "f1_std": 0.05011128706493877, "bacc": 0.5551782682512734, "bacc_std": 0.04727118574597413} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.043211160595383234, "f1": 0.5634191176470589, "f1_std": 0.04999655663546582, "bacc": 0.566213921901528, "bacc_std": 0.04573238119519254} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.03987919256955937, "f1": 0.483110950835437, "f1_std": 0.046204191148494576, "bacc": 0.5004244482173175, "bacc_std": 0.04057528757395148} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.047967701633495015, "f1": 0.5793334052421529, "f1_std": 0.05070520943727189, "bacc": 0.5785229202037352, "bacc_std": 0.05009307057441223} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04153423166497726, "f1": 0.6108031607500884, "f1_std": 0.05231375861741512, "bacc": 0.6116298811544991, "bacc_std": 0.045962706904358275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.038997558897961804, "f1": 0.5783730158730158, "f1_std": 0.0540581406928642, "bacc": 0.5882852292020373, "bacc_std": 0.04370382127383393} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 21.54434690031882, "split": "test", "acc": 0.56, "acc_std": 0.04812502051947614, "f1": 0.5225694444444444, "f1_std": 0.05156168290941722, "bacc": 0.5229202037351443, "bacc_std": 0.05009472203565616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.045872885237359995, "f1": 0.5906626839252129, "f1_std": 0.05159926941045855, "bacc": 0.5895585738539898, "bacc_std": 0.04925213367548716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.55, "acc_std": 0.04680801213467625, "f1": 0.5021573182874212, "f1_std": 0.05104238811828223, "bacc": 0.5046689303904923, "bacc_std": 0.048657828461887334} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04683069079140303, "f1": 0.5703301673450927, "f1_std": 0.05260827130863967, "bacc": 0.5713073005093379, "bacc_std": 0.04896954235633102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 1291.5496650148827, "split": "test", "acc": 0.5, "acc_std": 0.049247436481506326, "f1": 0.4791666666666667, "f1_std": 0.04990538264546153, "bacc": 0.47962648556876064, "bacc_std": 0.05068598130449204} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.0457994934469804, "f1": 0.6093337556752191, "f1_std": 0.04790517685611169, "bacc": 0.6099320882852293, "bacc_std": 0.0482225918347251} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04305473725387254, "f1": 0.5327635327635327, "f1_std": 0.050388598423025295, "bacc": 0.5369269949066213, "bacc_std": 0.045753569292401985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.047124732359982685, "f1": 0.5280995280995281, "f1_std": 0.050036550730670086, "bacc": 0.5280135823429541, "bacc_std": 0.049581103683298995} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.04936386937832163, "f1": 0.5501621508525996, "f1_std": 0.05046048012484104, "bacc": 0.551358234295416, "bacc_std": 0.051168398956059534} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.043979317866469914, "f1": 0.5863970588235294, "f1_std": 0.05209059957069275, "bacc": 0.5874363327674024, "bacc_std": 0.04748389855049405} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04799151591687847, "f1": 0.5626666666666666, "f1_std": 0.05076913782366488, "bacc": 0.5623938879456706, "bacc_std": 0.050295808053657486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.045163808519654326, "f1": 0.592944369063772, "f1_std": 0.051367134810385, "bacc": 0.5925297113752122, "bacc_std": 0.047714389844199026} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.000774263682681127, "split": "test", "acc": 0.68, "acc_std": 0.024667581965000112, "f1": 0.5482778091473743, "f1_std": 0.04765962669720731, "bacc": 0.5840407470288624, "bacc_std": 0.03072319455633551} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04848205853715372, "f1": 0.5755517826825127, "f1_std": 0.05013528081879025, "bacc": 0.5755517826825127, "bacc_std": 0.05004905640978035} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.03687567762089261, "f1": 0.503968253968254, "f1_std": 0.04805341212110805, "bacc": 0.5246179966044142, "bacc_std": 0.03921953904757598} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.04616424590524576, "f1": 0.5280995280995281, "f1_std": 0.04877488419090629, "bacc": 0.5280135823429541, "bacc_std": 0.04785346735929977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04482626016075845, "f1": 0.6161427533976553, "f1_std": 0.045967648966750964, "bacc": 0.6201188455008488, "bacc_std": 0.04688511490578909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.04893684092787355, "f1": 0.5280995280995281, "f1_std": 0.051530234263042304, "bacc": 0.5280135823429541, "bacc_std": 0.050785923206491716} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.59, "acc_std": 0.047855093772763625, "f1": 0.5746446726838883, "f1_std": 0.04864335423205851, "bacc": 0.5776740237691002, "bacc_std": 0.049370986673114924} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.043666788294996005, "f1": 0.5766488413547237, "f1_std": 0.04964518794068216, "bacc": 0.5764006791171477, "bacc_std": 0.0468184266290451} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04157000841953246, "f1": 0.5404411764705883, "f1_std": 0.048733502233366706, "bacc": 0.5449915110356536, "bacc_std": 0.044142618551651906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.044208863364714544, "f1": 0.5327635327635327, "f1_std": 0.051338815372829145, "bacc": 0.5369269949066213, "bacc_std": 0.046948873114374685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04588139492212502, "f1": 0.5174632352941176, "f1_std": 0.05239136589706526, "bacc": 0.5237691001697793, "bacc_std": 0.04785574277968042} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 10000.0, "split": "test", "acc": 0.63, "acc_std": 0.04642938293796289, "f1": 0.6093337556752191, "f1_std": 0.048469641110641226, "bacc": 0.6099320882852293, "bacc_std": 0.04879700572567455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.04874197780148031, "f1": 0.5361881134721174, "f1_std": 0.05238487015427173, "bacc": 0.5360780984719864, "bacc_std": 0.05128559385356686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.044437187129700274, "f1": 0.592944369063772, "f1_std": 0.05138972756329716, "bacc": 0.5925297113752122, "bacc_std": 0.04784935709344889} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 2.782559402207126, "split": "test", "acc": 0.58, "acc_std": 0.048776629649864074, "f1": 0.565936337329475, "f1_std": 0.04952393936579981, "bacc": 0.5696095076400679, "bacc_std": 0.050503535776952546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.04134239470567712, "f1": 0.516452411841019, "f1_std": 0.048474750413794385, "bacc": 0.5267402376910016, "bacc_std": 0.04301206676722522} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.53, "acc_std": 0.04873853095857527, "f1": 0.49304282170208175, "f1_std": 0.050781438341929906, "bacc": 0.4936332767402377, "bacc_std": 0.05006338845984606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.046571562138283486, "f1": 0.52, "f1_std": 0.0493273823227316, "bacc": 0.5199490662139219, "bacc_std": 0.048832230798010044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.54, "acc_std": 0.04322156406239829, "f1": 0.47987336047037543, "f1_std": 0.04785678956116182, "bacc": 0.4864176570458404, "bacc_std": 0.044541719134023175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.53, "acc_std": 0.04838956499081181, "f1": 0.4800309768779732, "f1_std": 0.05166826621678807, "bacc": 0.483446519524618, "bacc_std": 0.049675133686322245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.04512231820285832, "f1": 0.52, "f1_std": 0.04622701014076199, "bacc": 0.5199490662139219, "bacc_std": 0.045846470980162535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.0470892769109911, "f1": 0.554367201426025, "f1_std": 0.05265875603005206, "bacc": 0.5551782682512734, "bacc_std": 0.04954898103565885} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.045612151889600654, "f1": 0.5766488413547237, "f1_std": 0.05177256230897252, "bacc": 0.5764006791171477, "bacc_std": 0.04893519482033321} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.045990759941536084, "f1": 0.5783475783475784, "f1_std": 0.05265820316363649, "bacc": 0.5793718166383701, "bacc_std": 0.04854310425849429} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04650375898784957, "f1": 0.5906626839252129, "f1_std": 0.051614197804140755, "bacc": 0.5895585738539898, "bacc_std": 0.04929707974333597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.59, "acc_std": 0.04995698549752577, "f1": 0.5746446726838883, "f1_std": 0.050715567436354934, "bacc": 0.5776740237691002, "bacc_std": 0.051542316208525486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.03821007197062053, "f1": 0.5552350042072365, "f1_std": 0.04987238422041501, "bacc": 0.5640916808149405, "bacc_std": 0.04219072786072208} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 1291.5496650148827, "split": "test", "acc": 0.56, "acc_std": 0.04654623078187963, "f1": 0.5225694444444444, "f1_std": 0.0497727750417674, "bacc": 0.5229202037351443, "bacc_std": 0.04857185483614281} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04208199615037291, "f1": 0.5552350042072365, "f1_std": 0.05320429874750593, "bacc": 0.5640916808149405, "bacc_std": 0.04536945784315508} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.51, "acc_std": 0.044536093227852847, "f1": 0.4415954415954416, "f1_std": 0.047892874648637264, "bacc": 0.45203735144312396, "bacc_std": 0.0447579507984783} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.55, "acc_std": 0.04883410283807822, "f1": 0.529239460194581, "f1_std": 0.04932696672231545, "bacc": 0.5301358234295416, "bacc_std": 0.04978203623901016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.046861920575238906, "f1": 0.5501621508525996, "f1_std": 0.04906579644340615, "bacc": 0.551358234295416, "bacc_std": 0.04968516682371925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.52, "acc_std": 0.0386440163544112, "f1": 0.4171928120446819, "f1_std": 0.042621336469192035, "bacc": 0.44482173174872663, "bacc_std": 0.037869339558129295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 21.54434690031882, "split": "test", "acc": 0.53, "acc_std": 0.049205024133720326, "f1": 0.5242433444680635, "f1_std": 0.048700773537173926, "bacc": 0.5343803056027165, "bacc_std": 0.05030552309834309} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04098516316912744, "f1": 0.5400400990682863, "f1_std": 0.04977241333151689, "bacc": 0.547962648556876, "bacc_std": 0.043723794213069954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04606994682002574, "f1": 0.5477159656264134, "f1_std": 0.05184201354502542, "bacc": 0.5500848896434635, "bacc_std": 0.048247907660562646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.53, "acc_std": 0.04570284455042158, "f1": 0.4725620020199753, "f1_std": 0.049434398589855995, "bacc": 0.47835314091680814, "bacc_std": 0.04646888066385927} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.000774263682681127, "split": "test", "acc": 0.61, "acc_std": 0.03519645436688191, "f1": 0.48677457560205295, "f1_std": 0.04729523625610396, "bacc": 0.5224957555178268, "bacc_std": 0.036818166586864175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04204635061453015, "f1": 0.5477159656264134, "f1_std": 0.048109626565484856, "bacc": 0.5500848896434635, "bacc_std": 0.04459811574806294} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04400756298637769, "f1": 0.5477159656264134, "f1_std": 0.04955542677943155, "bacc": 0.5500848896434635, "bacc_std": 0.04607594008504673} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.55, "acc_std": 0.04555739676496013, "f1": 0.4950061721467849, "f1_std": 0.04979825695800772, "bacc": 0.49957555178268254, "bacc_std": 0.04672621608479725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.000774263682681127, "split": "test", "acc": 0.62, "acc_std": 0.030200258277041286, "f1": 0.4791666666666667, "f1_std": 0.04613837041470895, "bacc": 0.5254668930390493, "bacc_std": 0.03261887804278316} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04892197870078438, "f1": 0.5659722222222222, "f1_std": 0.05274968030730707, "bacc": 0.565365025466893, "bacc_std": 0.051170311988565996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04317840200841156, "f1": 0.6212121212121212, "f1_std": 0.04925184981254044, "bacc": 0.6188455008488964, "bacc_std": 0.046689928997204644} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 1291.5496650148827, "split": "test", "acc": 0.54, "acc_std": 0.04779948116873236, "f1": 0.5066495066495067, "f1_std": 0.04840839302304163, "bacc": 0.5067911714770797, "bacc_std": 0.04795791235235949} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.03711497810857499, "f1": 0.5360501567398119, "f1_std": 0.049795827557103566, "bacc": 0.5539049235993209, "bacc_std": 0.040242786600766196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.0415020915135611, "f1": 0.5400400990682863, "f1_std": 0.050752661363583806, "bacc": 0.547962648556876, "bacc_std": 0.044514136727785085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.000774263682681127, "split": "test", "acc": 0.66, "acc_std": 0.02699999259259157, "f1": 0.5200451722190853, "f1_std": 0.04798913485275384, "bacc": 0.5628183361629882, "bacc_std": 0.03168790051137242} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04276868012927216, "f1": 0.64349376114082, "f1_std": 0.049308222274909226, "bacc": 0.6400679117147707, "bacc_std": 0.046977412694595204} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.54, "acc_std": 0.04746500184346357, "f1": 0.5008680555555556, "f1_std": 0.050597269784281564, "bacc": 0.50169779286927, "bacc_std": 0.04936542553501477} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04584870336225442, "f1": 0.5523528769516323, "f1_std": 0.04977991645094833, "bacc": 0.5522071307300509, "bacc_std": 0.04820728418381723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.000774263682681127, "split": "test", "acc": 0.65, "acc_std": 0.030229813098992194, "f1": 0.539413080668509, "f1_std": 0.04720727387978017, "bacc": 0.5649405772495755, "bacc_std": 0.03443535700189057} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.046373423423335905, "f1": 0.5361881134721174, "f1_std": 0.04999668342221381, "bacc": 0.5360780984719864, "bacc_std": 0.04886210060721715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.048554859694988295, "f1": 0.537620849096259, "f1_std": 0.05008713203005423, "bacc": 0.5382003395585738, "bacc_std": 0.05037173981445745} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.047130537870896404, "f1": 0.6053333333333333, "f1_std": 0.04984526921924103, "bacc": 0.6048387096774194, "bacc_std": 0.049569086164361426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 21.54434690031882, "split": "test", "acc": 0.59, "acc_std": 0.049593047899882094, "f1": 0.5670995670995671, "f1_std": 0.05253010513677805, "bacc": 0.5674872665534805, "bacc_std": 0.05269496224505331} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.046490304365534106, "f1": 0.5242836596968692, "f1_std": 0.04987197503820543, "bacc": 0.5258913412563667, "bacc_std": 0.047920642655449264} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 1291.5496650148827, "split": "test", "acc": 0.58, "acc_std": 0.04643677852736987, "f1": 0.5586380832282472, "f1_std": 0.04809045432021896, "bacc": 0.5594227504244482, "bacc_std": 0.048449465360040626} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04499608427407878, "f1": 0.6483516483516483, "f1_std": 0.049963533806217, "bacc": 0.6451612903225806, "bacc_std": 0.048542093062049714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04640628836698751, "f1": 0.5623386825272135, "f1_std": 0.05189092402687307, "bacc": 0.5632427843803056, "bacc_std": 0.04900553943395027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04031612580593527, "f1": 0.609375, "f1_std": 0.04933164548376999, "bacc": 0.6086587436332768, "bacc_std": 0.044721179551901066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.04553523470895917, "f1": 0.539894512400404, "f1_std": 0.0507136366184342, "bacc": 0.5420203735144312, "bacc_std": 0.047556380679542175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.56, "acc_std": 0.04127668106812852, "f1": 0.47619047619047616, "f1_std": 0.04888690551928722, "bacc": 0.4923599320882852, "bacc_std": 0.04266529640876891} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04196479953484826, "f1": 0.5847828526540231, "f1_std": 0.047776030622713926, "bacc": 0.5844651952461799, "bacc_std": 0.04485246537093719} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 166.81005372000556, "split": "test", "acc": 0.54, "acc_std": 0.04911105374556729, "f1": 0.5118845500848896, "f1_std": 0.050198425578294986, "bacc": 0.5118845500848896, "bacc_std": 0.05003868908088707} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 166.81005372000556, "split": "test", "acc": 0.56, "acc_std": 0.048124604933443345, "f1": 0.548440065681445, "f1_std": 0.04884441608083412, "bacc": 0.5534804753820034, "bacc_std": 0.05033754849584416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.040239781311533, "f1": 0.5558672276764843, "f1_std": 0.04986051904347404, "bacc": 0.5611205432937181, "bacc_std": 0.04371166579326239} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 359.37 | 1722.9 | 0.84849 | 0.10373 | 0.82423 | 0.12726 | 0.81946 | 0.12626 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 359.37 | 1722.9 | 0.5951 | 0.041231 | 0.54321 | 0.042659 | 0.54929 | 0.038376 | + + +done! total time: 0:05:24 diff --git a/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/config.yaml b/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ba7283c4a86029aa3b0450ca6b777097011dbe01 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..9cd66ba11cc11e22209ddb7bbc5f1e907d0c7e26 --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,ppmi_dx,,0.005994842503189409,train,0.7882562277580071,0.015775403331183692,0.7557583659278575,0.0198577100478623,0.743758765778401,0.018654707488784505 +flat_mae,reg,logistic,ppmi_dx,,0.005994842503189409,test,0.62,0.03554138995593731,0.5062370062370062,0.04930734997036736,0.5311025311025311,0.038604307063025145 +flat_mae,reg,logistic,ppmi_dx,1,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,1,2.782559402207126,test,0.54,0.04764288404368484,0.5118845500848896,0.0493115406410543,0.5118845500848896,0.04900838276395242 +flat_mae,reg,logistic,ppmi_dx,2,0.005994842503189409,train,0.7935943060498221,0.015649275913862882,0.7636635199605575,0.019374846332391747,0.751485228002569,0.018423256932341522 +flat_mae,reg,logistic,ppmi_dx,2,0.005994842503189409,test,0.6,0.03957647786248796,0.5143273433705683,0.049255099633857574,0.5297113752122241,0.04162440880563508 +flat_mae,reg,logistic,ppmi_dx,3,0.046415888336127774,train,0.9110320284697508,0.01154553707278527,0.90380928907876,0.012782812669477067,0.8955657246842218,0.013660740803565235 +flat_mae,reg,logistic,ppmi_dx,3,0.046415888336127774,test,0.57,0.04788016290699103,0.5361881134721174,0.05096673234724016,0.5360780984719864,0.04991830992222761 +flat_mae,reg,logistic,ppmi_dx,4,0.005994842503189409,train,0.7882562277580071,0.015288618639547624,0.7579015576865296,0.018860902444584993,0.7462802397773496,0.01794879987362899 +flat_mae,reg,logistic,ppmi_dx,4,0.005994842503189409,test,0.66,0.04241687871590742,0.609375,0.049619890843987095,0.6086587436332768,0.04535992877588278 +flat_mae,reg,logistic,ppmi_dx,5,0.005994842503189409,train,0.7953736654804271,0.016067329539548262,0.7705055411744236,0.019310589771334354,0.7598881395846714,0.01883843065704229 +flat_mae,reg,logistic,ppmi_dx,5,0.005994842503189409,test,0.55,0.045853087137072895,0.5021573182874212,0.049927596527497585,0.5046689303904923,0.04745487027089342 +flat_mae,reg,logistic,ppmi_dx,6,0.046415888336127774,train,0.902135231316726,0.012684449722039698,0.8938511993681211,0.014161771043656826,0.8848613787197602,0.015021170129190617 +flat_mae,reg,logistic,ppmi_dx,6,0.046415888336127774,test,0.57,0.04615997833621675,0.5305164319248826,0.05035164970709522,0.5309847198641766,0.04882228964933279 +flat_mae,reg,logistic,ppmi_dx,7,0.3593813663804626,train,0.99644128113879,0.0023430184461532017,0.9962334964144495,0.002485621021976695,0.9953703703703703,0.003048093441523376 +flat_mae,reg,logistic,ppmi_dx,7,0.3593813663804626,test,0.58,0.049660330244572476,0.5689655172413793,0.04971039982892561,0.5747028862478778,0.05081812512250601 +flat_mae,reg,logistic,ppmi_dx,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,8,166.81005372000556,test,0.63,0.04775327842148641,0.6053333333333333,0.05046597912106882,0.6048387096774194,0.05033019747504857 +flat_mae,reg,logistic,ppmi_dx,9,0.046415888336127774,train,0.902135231316726,0.01285534717987451,0.8943012977242806,0.014152650503448634,0.8866008349389852,0.014768713207267505 +flat_mae,reg,logistic,ppmi_dx,9,0.046415888336127774,test,0.61,0.047673825103509364,0.584,0.05129804060463981,0.583616298811545,0.05094055122021549 +flat_mae,reg,logistic,ppmi_dx,10,0.046415888336127774,train,0.9199288256227758,0.01150197480102439,0.9140482947304025,0.012559706320011578,0.9080095268679084,0.013382624355792537 +flat_mae,reg,logistic,ppmi_dx,10,0.046415888336127774,test,0.59,0.04758300536956446,0.5464100011063171,0.051992629292488254,0.5471137521222411,0.04935292504917706 +flat_mae,reg,logistic,ppmi_dx,11,0.005994842503189409,train,0.7864768683274022,0.015751341548516012,0.7540732529136339,0.019743490181485503,0.7422259687433097,0.018590441197820433 +flat_mae,reg,logistic,ppmi_dx,11,0.005994842503189409,test,0.64,0.03991957414602516,0.5714285714285714,0.050374918057164535,0.5772495755517827,0.04367569990644279 +flat_mae,reg,logistic,ppmi_dx,12,0.000774263682681127,train,0.708185053380783,0.012995716264521473,0.6171916533758639,0.02146175962468602,0.6290676514664953,0.015805698805269563 +flat_mae,reg,logistic,ppmi_dx,12,0.000774263682681127,test,0.57,0.030672098069744087,0.4188403838356535,0.03831677288037553,0.47495755517826826,0.030391175547897487 +flat_mae,reg,logistic,ppmi_dx,13,0.046415888336127774,train,0.9163701067615658,0.0115433885636394,0.9094849889828969,0.012783137038035115,0.9007707129094413,0.01373518462286312 +flat_mae,reg,logistic,ppmi_dx,13,0.046415888336127774,test,0.58,0.04788591024508148,0.5543293718166383,0.04942330861778958,0.5543293718166383,0.04934404146848294 +flat_mae,reg,logistic,ppmi_dx,14,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,14,21.54434690031882,test,0.56,0.050899131623240876,0.5452666391070691,0.05158724605274322,0.5483870967741935,0.05274913890226157 +flat_mae,reg,logistic,ppmi_dx,15,0.005994842503189409,train,0.7935943060498221,0.015455300916329835,0.7656717276282494,0.018836031777449865,0.7540944123314066,0.018150916698703903 +flat_mae,reg,logistic,ppmi_dx,15,0.005994842503189409,test,0.62,0.03519551675995113,0.5287698412698413,0.04844726862196129,0.5458404074702886,0.03869833043228537 +flat_mae,reg,logistic,ppmi_dx,16,0.3593813663804626,train,0.998220640569395,0.0016615825665379034,0.9981184064710746,0.0017596775211224625,0.9976851851851851,0.0021615958388756964 +flat_mae,reg,logistic,ppmi_dx,16,0.3593813663804626,test,0.61,0.04819063809496612,0.5741893219783819,0.051960930610530746,0.5734295415959253,0.05035406419556085 +flat_mae,reg,logistic,ppmi_dx,17,0.046415888336127774,train,0.9110320284697508,0.012241940639630312,0.90380928907876,0.01359559663979743,0.8955657246842218,0.014587846310151366 +flat_mae,reg,logistic,ppmi_dx,17,0.046415888336127774,test,0.58,0.047123565230147844,0.5442708333333334,0.04984158304077198,0.5441426146010186,0.0485267251184681 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,train,0.7935943060498221,0.015199875670958917,0.7629726585223968,0.019114071113381984,0.7506154998929565,0.01814757526929549 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,test,0.59,0.0408129195231118,0.516452411841019,0.04768034893928743,0.5267402376910016,0.042310065847541684 +flat_mae,reg,logistic,ppmi_dx,19,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,19,2.782559402207126,test,0.55,0.0487405539566386,0.529239460194581,0.05027374918464897,0.5301358234295416,0.05086046720633029 +flat_mae,reg,logistic,ppmi_dx,20,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,20,21.54434690031882,test,0.6,0.0449921726525848,0.5659722222222222,0.04904223062682838,0.565365025466893,0.04777205904913215 +flat_mae,reg,logistic,ppmi_dx,21,0.005994842503189409,train,0.7846975088967971,0.0170453405793375,0.7538326763031099,0.020940273622172115,0.7425203382573324,0.019872768472296066 +flat_mae,reg,logistic,ppmi_dx,21,0.005994842503189409,test,0.67,0.04095414020584487,0.6108031607500884,0.05238226515635606,0.6116298811544991,0.04574288828473311 +flat_mae,reg,logistic,ppmi_dx,22,0.3593813663804626,train,0.998220640569395,0.0018299256278874426,0.9981184064710746,0.001938768103335671,0.9976851851851851,0.002380597691835051 +flat_mae,reg,logistic,ppmi_dx,22,0.3593813663804626,test,0.51,0.04960088305665536,0.48263118994826315,0.05121234879450136,0.482597623089983,0.05108492157334616 +flat_mae,reg,logistic,ppmi_dx,23,0.046415888336127774,train,0.896797153024911,0.012530496732446389,0.8879400440044004,0.013998251021294079,0.8787866623849283,0.014732286972329783 +flat_mae,reg,logistic,ppmi_dx,23,0.046415888336127774,test,0.64,0.04334178122781758,0.592944369063772,0.050988231138931056,0.5925297113752122,0.04724573119548986 +flat_mae,reg,logistic,ppmi_dx,24,0.046415888336127774,train,0.902135231316726,0.01242925548922026,0.8949479157816032,0.013535373315231993,0.8892100192678227,0.014149563118864998 +flat_mae,reg,logistic,ppmi_dx,24,0.046415888336127774,test,0.66,0.04735599222907277,0.6212121212121212,0.05480576065687998,0.6188455008488964,0.05175631304848321 +flat_mae,reg,logistic,ppmi_dx,25,0.005994842503189409,train,0.7935943060498221,0.016136396060480677,0.7636635199605575,0.019833222872039924,0.751485228002569,0.018866929455207022 +flat_mae,reg,logistic,ppmi_dx,25,0.005994842503189409,test,0.62,0.04068255645851181,0.5386109762020399,0.05165693087209284,0.5509337860780985,0.04364482875756256 +flat_mae,reg,logistic,ppmi_dx,26,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,26,166.81005372000556,test,0.52,0.04879220839437378,0.5104039167686658,0.04879418558885745,0.5161290322580645,0.05037260243154183 +flat_mae,reg,logistic,ppmi_dx,27,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,27,21.54434690031882,test,0.65,0.04658289814942818,0.6368917937545389,0.047506227814465514,0.6413412563667232,0.04819474916613959 +flat_mae,reg,logistic,ppmi_dx,28,0.3593813663804626,train,0.998220640569395,0.001868984802152337,0.9981184064710746,0.0019802879184783193,0.9976851851851851,0.002431410784281514 +flat_mae,reg,logistic,ppmi_dx,28,0.3593813663804626,test,0.48,0.04389031783890383,0.4120307553143374,0.04547360628315206,0.4227504244482173,0.043227342806824116 +flat_mae,reg,logistic,ppmi_dx,29,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,29,166.81005372000556,test,0.6,0.04535405163819436,0.570999570999571,0.04797354349117997,0.5704584040747029,0.04753394974781696 +flat_mae,reg,logistic,ppmi_dx,30,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,30,2.782559402207126,test,0.54,0.046421869846011155,0.5245969408846631,0.04723852862109287,0.5271646859083192,0.04847645651354544 +flat_mae,reg,logistic,ppmi_dx,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,31,166.81005372000556,test,0.63,0.04687039150679243,0.6254681647940075,0.046739035677887286,0.6404923599320883,0.04836343212458863 +flat_mae,reg,logistic,ppmi_dx,32,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,32,21.54434690031882,test,0.63,0.04873407021786709,0.6129302228266555,0.04984186032317263,0.615025466893039,0.05045381745475584 +flat_mae,reg,logistic,ppmi_dx,33,0.046415888336127774,train,0.900355871886121,0.012389363729952377,0.8927129922548271,0.013625900908143885,0.8860254763433955,0.01436083249351421 +flat_mae,reg,logistic,ppmi_dx,33,0.046415888336127774,test,0.67,0.045567988764043554,0.648,0.04847160818398622,0.6472835314091681,0.04824561820405694 +flat_mae,reg,logistic,ppmi_dx,34,0.046415888336127774,train,0.905693950177936,0.011431023223735985,0.8977111557547348,0.012746854930539068,0.8886212802397773,0.013586343808367086 +flat_mae,reg,logistic,ppmi_dx,34,0.046415888336127774,test,0.69,0.04111709620097216,0.6467236467236468,0.04872688853556702,0.6430390492359932,0.04517027696786742 +flat_mae,reg,logistic,ppmi_dx,35,0.005994842503189409,train,0.8096085409252669,0.014564326395288197,0.7841526229831834,0.017719385214133545,0.7714488332262899,0.017205125301555067 +flat_mae,reg,logistic,ppmi_dx,35,0.005994842503189409,test,0.59,0.04961562253967998,0.5464100011063171,0.05382101131551028,0.5471137521222411,0.05150952397886852 +flat_mae,reg,logistic,ppmi_dx,36,0.046415888336127774,train,0.9110320284697508,0.012113876389928249,0.9042080287989528,0.013291620893260105,0.8973051809034468,0.014040357389438011 +flat_mae,reg,logistic,ppmi_dx,36,0.046415888336127774,test,0.62,0.043854760288935576,0.5634191176470589,0.05119703890324886,0.566213921901528,0.04654560262575569 +flat_mae,reg,logistic,ppmi_dx,37,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,37,166.81005372000556,test,0.56,0.049559576269375016,0.548440065681445,0.04989225364807276,0.5534804753820034,0.05126969018419432 +flat_mae,reg,logistic,ppmi_dx,38,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,38,2.782559402207126,test,0.63,0.047078470663350996,0.6093337556752191,0.04867204700138565,0.6099320882852293,0.04878254371340434 +flat_mae,reg,logistic,ppmi_dx,39,0.046415888336127774,train,0.9074733096085409,0.01199344011713866,0.9005783493229911,0.013127756468701977,0.8944150074930421,0.013854333082415607 +flat_mae,reg,logistic,ppmi_dx,39,0.046415888336127774,test,0.6,0.04809567132289558,0.5604395604395604,0.052879156756433815,0.5602716468590832,0.050685455007485516 +flat_mae,reg,logistic,ppmi_dx,40,0.046415888336127774,train,0.905693950177936,0.011847621819561376,0.8979298811934795,0.013108773156121294,0.8894910083493899,0.013867342023527619 +flat_mae,reg,logistic,ppmi_dx,40,0.046415888336127774,test,0.58,0.05037289350434418,0.5586380832282472,0.051983194158654565,0.5594227504244482,0.05225983797768699 +flat_mae,reg,logistic,ppmi_dx,41,0.005994842503189409,train,0.7900355871886121,0.015466198312186699,0.7595887530633256,0.01896208841915538,0.7477253264825519,0.018009399260444304 +flat_mae,reg,logistic,ppmi_dx,41,0.005994842503189409,test,0.67,0.04293425671884864,0.6296711929076422,0.049139695397906025,0.6269100169779287,0.046143288328387114 +flat_mae,reg,logistic,ppmi_dx,42,0.005994842503189409,train,0.8113879003558719,0.013908627932998435,0.7840373544467163,0.017349632367565183,0.7702847356026546,0.01670531323449236 +flat_mae,reg,logistic,ppmi_dx,42,0.005994842503189409,test,0.67,0.0345750140997802,0.5862068965517242,0.04909578632541204,0.5963497453310695,0.039256675439193825 +flat_mae,reg,logistic,ppmi_dx,43,0.3593813663804626,train,0.99644128113879,0.0023472954597213024,0.9962465771722434,0.002470017181529299,0.9971098265895953,0.0019063295496580728 +flat_mae,reg,logistic,ppmi_dx,43,0.3593813663804626,test,0.64,0.04481685397258491,0.6043956043956044,0.04978921638015068,0.6027164685908319,0.047985720490077974 +flat_mae,reg,logistic,ppmi_dx,44,0.046415888336127774,train,0.9234875444839857,0.010475226038503592,0.9173628327662557,0.0115700176321047,0.909160244059088,0.012486569378232885 +flat_mae,reg,logistic,ppmi_dx,44,0.046415888336127774,test,0.54,0.05008792269599529,0.5066495066495067,0.05259924632602734,0.5067911714770797,0.05194900573299815 +flat_mae,reg,logistic,ppmi_dx,45,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,45,21.54434690031882,test,0.63,0.05342198423870083,0.6189887756152817,0.05384174436371583,0.6252122241086587,0.054796992830504786 +flat_mae,reg,logistic,ppmi_dx,46,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,46,166.81005372000556,test,0.6,0.04869199112790521,0.5796553173602353,0.05132879245282865,0.5806451612903225,0.051836061851132556 +flat_mae,reg,logistic,ppmi_dx,47,0.005994842503189409,train,0.800711743772242,0.014213194788395795,0.7704683693860583,0.01780181451762171,0.7572655748233783,0.016876701415478517 +flat_mae,reg,logistic,ppmi_dx,47,0.005994842503189409,test,0.64,0.040125059501513516,0.5714285714285714,0.050632324836548115,0.5772495755517827,0.04392969640126528 +flat_mae,reg,logistic,ppmi_dx,48,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,48,2.782559402207126,test,0.68,0.04591286965546806,0.6604414261460102,0.04840193939698929,0.6604414261460102,0.048369648620440256 +flat_mae,reg,logistic,ppmi_dx,49,0.046415888336127774,train,0.9252669039145908,0.010832784054419073,0.9190279512054558,0.012028269424956335,0.9097356026546778,0.013024338500272516 +flat_mae,reg,logistic,ppmi_dx,49,0.046415888336127774,test,0.64,0.04214703311029141,0.5863970588235294,0.05124170091354092,0.5874363327674024,0.04608884869929445 +flat_mae,reg,logistic,ppmi_dx,50,0.046415888336127774,train,0.9092526690391459,0.01183469333411235,0.9019884760716057,0.013051658435547476,0.8941206379790194,0.013800211083703016 +flat_mae,reg,logistic,ppmi_dx,50,0.046415888336127774,test,0.57,0.047401312218123236,0.5242836596968692,0.05177476756360297,0.5258913412563667,0.04946647111655059 +flat_mae,reg,logistic,ppmi_dx,51,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,51,166.81005372000556,test,0.61,0.048823678681557785,0.5920075321686369,0.050893322616953944,0.5938030560271647,0.05162843163860421 +flat_mae,reg,logistic,ppmi_dx,52,0.005994842503189409,train,0.797153024911032,0.015491646852402976,0.7690644058999092,0.019019295091855633,0.7569845857418112,0.018280997987045387 +flat_mae,reg,logistic,ppmi_dx,52,0.005994842503189409,test,0.6,0.045600877184545474,0.554367201426025,0.051156126213831,0.5551782682512734,0.04841577995947277 +flat_mae,reg,logistic,ppmi_dx,53,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,53,2.782559402207126,test,0.56,0.045572342489716276,0.5098039215686274,0.05039140911928061,0.5127334465195246,0.0477305531186235 +flat_mae,reg,logistic,ppmi_dx,54,0.046415888336127774,train,0.9128113879003559,0.011680665123017938,0.9060274430714946,0.012881649857054964,0.8987502676086491,0.013796911684980434 +flat_mae,reg,logistic,ppmi_dx,54,0.046415888336127774,test,0.52,0.04809272710088294,0.5,0.048507125121926,0.5008488964346349,0.04940196022024757 +flat_mae,reg,logistic,ppmi_dx,55,0.3593813663804626,train,0.998220640569395,0.0018490412814937181,0.9981184064710746,0.0019590073326530314,0.9976851851851851,0.002405465741202476 +flat_mae,reg,logistic,ppmi_dx,55,0.3593813663804626,test,0.57,0.04503706917640178,0.5361881134721174,0.04863074238570459,0.5360780984719864,0.047409247091664344 +flat_mae,reg,logistic,ppmi_dx,56,0.005994842503189409,train,0.7953736654804271,0.015025052216919197,0.7632557372845656,0.019309304936843057,0.7503211303789339,0.018251179844435084 +flat_mae,reg,logistic,ppmi_dx,56,0.005994842503189409,test,0.58,0.04537620521815371,0.5320855614973261,0.049946763651716373,0.533955857385399,0.047321220649247826 +flat_mae,reg,logistic,ppmi_dx,57,0.046415888336127774,train,0.9092526690391459,0.01175739261920399,0.9015711121413486,0.013073150244982337,0.8923811817597944,0.013895610566169137 +flat_mae,reg,logistic,ppmi_dx,57,0.046415888336127774,test,0.61,0.04927332341135516,0.584,0.051988358134296926,0.583616298811545,0.05166974309511503 +flat_mae,reg,logistic,ppmi_dx,58,0.000774263682681127,train,0.6832740213523132,0.013394284095010518,0.5845128920786815,0.022047012050771597,0.6027483408263755,0.01605412049833905 +flat_mae,reg,logistic,ppmi_dx,58,0.000774263682681127,test,0.62,0.033527874969941064,0.5062370062370062,0.048160411377523006,0.5356536502546689,0.03644764592519959 +flat_mae,reg,logistic,ppmi_dx,59,0.3593813663804626,train,0.998220640569395,0.0017609582330387241,0.9981184064710746,0.0018651813149161642,0.9976851851851851,0.0022908762198327833 +flat_mae,reg,logistic,ppmi_dx,59,0.3593813663804626,test,0.6,0.04624896106941214,0.570999570999571,0.050008848359092556,0.5704584040747029,0.049486961627823386 +flat_mae,reg,logistic,ppmi_dx,60,0.3593813663804626,train,0.9928825622775801,0.0036633912437548937,0.9924669928288989,0.0038880909758625625,0.9916104688503533,0.004436103345515827 +flat_mae,reg,logistic,ppmi_dx,60,0.3593813663804626,test,0.6,0.04755346885349165,0.5659722222222222,0.051156330966597545,0.565365025466893,0.04996143435454387 +flat_mae,reg,logistic,ppmi_dx,61,0.005994842503189409,train,0.7935943060498221,0.016237816075081034,0.7615578183520599,0.020278242359690557,0.7488760436737316,0.019049230462242602 +flat_mae,reg,logistic,ppmi_dx,61,0.005994842503189409,test,0.6,0.04269037830706118,0.5324918186068257,0.04978138117074226,0.5398981324278438,0.044500530976119015 +flat_mae,reg,logistic,ppmi_dx,62,0.046415888336127774,train,0.9181494661921709,0.010645585530185998,0.910930113973071,0.011944549285145387,0.9004763433954186,0.01291326383019507 +flat_mae,reg,logistic,ppmi_dx,62,0.046415888336127774,test,0.54,0.04485326743950768,0.4945054945054945,0.04828548731566969,0.49660441426146007,0.046151624953092274 +flat_mae,reg,logistic,ppmi_dx,63,0.046415888336127774,train,0.9145907473309609,0.011708306200630137,0.9084093872229465,0.012782254425103903,0.902804538642689,0.013653540749355205 +flat_mae,reg,logistic,ppmi_dx,63,0.046415888336127774,test,0.5,0.04586981578336674,0.4429590017825312,0.04764112487947692,0.4490662139219015,0.045792745422552225 +flat_mae,reg,logistic,ppmi_dx,64,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,64,166.81005372000556,test,0.48,0.04738192060269403,0.4422994422994423,0.048011015445325864,0.4431239388794567,0.047816422980700275 +flat_mae,reg,logistic,ppmi_dx,65,0.046415888336127774,train,0.9181494661921709,0.010704775402157349,0.9115045459524591,0.011847212109087926,0.903085527724256,0.01273362935144811 +flat_mae,reg,logistic,ppmi_dx,65,0.046415888336127774,test,0.62,0.04546620283243368,0.5924495924495925,0.04945304661813686,0.5916808149405772,0.048639124683485455 +flat_mae,reg,logistic,ppmi_dx,66,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,66,21.54434690031882,test,0.45,0.04826218395389915,0.41333333333333333,0.04772765618309145,0.41383701188455013,0.04775857741376698 +flat_mae,reg,logistic,ppmi_dx,67,0.3593813663804626,train,0.998220640569395,0.001927666392729838,0.9981216765874674,0.0020309558666608534,0.9985549132947977,0.0015655325328239465 +flat_mae,reg,logistic,ppmi_dx,67,0.3593813663804626,test,0.57,0.04705949850986514,0.562608076492727,0.04654027637479382,0.5717317487266553,0.047942710002943874 +flat_mae,reg,logistic,ppmi_dx,68,0.005994842503189409,train,0.7864768683274022,0.01685889303267882,0.7575914423740511,0.020538583013438787,0.7465746092913723,0.019656681977027062 +flat_mae,reg,logistic,ppmi_dx,68,0.005994842503189409,test,0.59,0.041768887943061155,0.5249681381068243,0.04967918829363481,0.5318336162988115,0.04416184392451689 +flat_mae,reg,logistic,ppmi_dx,69,0.046415888336127774,train,0.9288256227758007,0.010223050970242842,0.9232083077133293,0.011297357227719807,0.9152349603939199,0.012421871822651562 +flat_mae,reg,logistic,ppmi_dx,69,0.046415888336127774,test,0.6,0.045832193925231204,0.5659722222222222,0.049030445871899656,0.565365025466893,0.0479393366352834 +flat_mae,reg,logistic,ppmi_dx,70,0.046415888336127774,train,0.9039145907473309,0.011749175937854208,0.8958930801213003,0.013031679305376579,0.887176193534575,0.013765216915386094 +flat_mae,reg,logistic,ppmi_dx,70,0.046415888336127774,test,0.54,0.045997808643456047,0.4945054945054945,0.05007249625403731,0.49660441426146007,0.04767624856349193 +flat_mae,reg,logistic,ppmi_dx,71,0.3593813663804626,train,0.998220640569395,0.0016704157796151467,0.9981184064710746,0.0017690977648605714,0.9976851851851851,0.002173087194777116 +flat_mae,reg,logistic,ppmi_dx,71,0.3593813663804626,test,0.61,0.04778801523394752,0.5793334052421529,0.0514973135284971,0.5785229202037352,0.05039171251937784 +flat_mae,reg,logistic,ppmi_dx,72,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,72,166.81005372000556,test,0.57,0.04681869711984731,0.5459824728117411,0.048626370889368074,0.5462648556876061,0.04876330992385192 +flat_mae,reg,logistic,ppmi_dx,73,0.005994842503189409,train,0.7900355871886121,0.015466973333280176,0.7622912036705141,0.018923604314415327,0.751204238921002,0.01828122418103704 +flat_mae,reg,logistic,ppmi_dx,73,0.005994842503189409,test,0.58,0.04677833259106185,0.5384615384615385,0.05073267349314522,0.5390492359932089,0.04855823435804258 +flat_mae,reg,logistic,ppmi_dx,74,0.046415888336127774,train,0.9074733096085409,0.011654223451339244,0.9003763499509109,0.012814557342503714,0.8935452793834298,0.013657568599806264 +flat_mae,reg,logistic,ppmi_dx,74,0.046415888336127774,test,0.63,0.048592225715643034,0.6093337556752191,0.05044784280265885,0.6099320882852293,0.05043092527413005 +flat_mae,reg,logistic,ppmi_dx,75,0.005994842503189409,train,0.7935943060498221,0.015467049891629227,0.7650129042490303,0.018762653113861466,0.753224684221794,0.01789650139561091 +flat_mae,reg,logistic,ppmi_dx,75,0.005994842503189409,test,0.6,0.040788017848382874,0.5143273433705683,0.04906635048069404,0.5297113752122241,0.04225159211453286 +flat_mae,reg,logistic,ppmi_dx,76,0.046415888336127774,train,0.905693950177936,0.011742553047896943,0.8983562139344738,0.012875501210262041,0.8912304645686149,0.013503300008699827 +flat_mae,reg,logistic,ppmi_dx,76,0.046415888336127774,test,0.55,0.04900969291885024,0.52,0.05151411549271526,0.5199490662139219,0.05112581426426387 +flat_mae,reg,logistic,ppmi_dx,77,0.046415888336127774,train,0.8896797153024911,0.012967695638708877,0.8807235184576624,0.014295806022827722,0.873006315564119,0.014874322213895763 +flat_mae,reg,logistic,ppmi_dx,77,0.046415888336127774,test,0.59,0.047041071416369755,0.5523528769516323,0.051658568030857735,0.5522071307300509,0.04957855187215168 +flat_mae,reg,logistic,ppmi_dx,78,0.046415888336127774,train,0.8861209964412812,0.01269150064111602,0.8758011049723757,0.014280629752820321,0.8657675016056519,0.014949052660317565 +flat_mae,reg,logistic,ppmi_dx,78,0.046415888336127774,test,0.65,0.04399244935213314,0.6011396011396011,0.05255637044384299,0.6005942275042444,0.04847515897877285 +flat_mae,reg,logistic,ppmi_dx,79,0.000774263682681127,train,0.6797153024911032,0.012560884259327594,0.5719363574813812,0.020816635659465052,0.5955095268679084,0.014796955988591928 +flat_mae,reg,logistic,ppmi_dx,79,0.000774263682681127,test,0.61,0.02948542012588596,0.45765540258656656,0.04452901620588249,0.5123089983022071,0.031537897756522326 +flat_mae,reg,logistic,ppmi_dx,80,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,80,166.81005372000556,test,0.53,0.05081968122686328,0.5083167695365624,0.051919965593242016,0.5089134125636672,0.052489899507988456 +flat_mae,reg,logistic,ppmi_dx,81,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,81,2.782559402207126,test,0.55,0.04284575124793589,0.4950061721467849,0.04818122242065944,0.49957555178268254,0.04470391152117604 +flat_mae,reg,logistic,ppmi_dx,82,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,82,21.54434690031882,test,0.58,0.04729661298655538,0.5495495495495495,0.04968083452990254,0.5492359932088284,0.048965338700798916 +flat_mae,reg,logistic,ppmi_dx,83,0.046415888336127774,train,0.905693950177936,0.011908442717918993,0.8987679915713631,0.013001949716462213,0.8929699207878399,0.013718920808708034 +flat_mae,reg,logistic,ppmi_dx,83,0.046415888336127774,test,0.54,0.05176901003496203,0.5118845500848896,0.05412152773261562,0.5118845500848896,0.054033650050021476 +flat_mae,reg,logistic,ppmi_dx,84,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,84,21.54434690031882,test,0.61,0.04858343339040582,0.5983935742971888,0.04894392251960316,0.6039898132427843,0.050085753287423054 +flat_mae,reg,logistic,ppmi_dx,85,0.005994842503189409,train,0.800711743772242,0.014619317571132209,0.771813053755021,0.01810456708424672,0.7590050310426033,0.0172980623507396 +flat_mae,reg,logistic,ppmi_dx,85,0.005994842503189409,test,0.62,0.04062832017201795,0.5476190476190476,0.05085748966778338,0.5560271646859083,0.04397567632955119 +flat_mae,reg,logistic,ppmi_dx,86,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,86,0.3593813663804626,test,0.58,0.04396934841454896,0.5320855614973261,0.04856836650760864,0.533955857385399,0.04574162036046841 +flat_mae,reg,logistic,ppmi_dx,87,0.005994842503189409,train,0.8078291814946619,0.015987993921878624,0.7824360169187755,0.019536258345647456,0.7700037465210876,0.019010240974245432 +flat_mae,reg,logistic,ppmi_dx,87,0.005994842503189409,test,0.64,0.045730095123452344,0.5863970588235294,0.053869501415995724,0.5874363327674024,0.04936485408738001 +flat_mae,reg,logistic,ppmi_dx,88,0.005994842503189409,train,0.791814946619217,0.01576973133851767,0.7612791031175234,0.019674079270969206,0.7491704131877541,0.018693887628705285 +flat_mae,reg,logistic,ppmi_dx,88,0.005994842503189409,test,0.68,0.04136955402225167,0.6259934548854604,0.0525234832328131,0.6247877758913413,0.046699490353516955 +flat_mae,reg,logistic,ppmi_dx,89,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,89,166.81005372000556,test,0.57,0.04797484340776945,0.5501621508525996,0.0497413085604683,0.551358234295416,0.05039185523786308 +flat_mae,reg,logistic,ppmi_dx,90,0.046415888336127774,train,0.9128113879003559,0.011513792570605223,0.9054310685279623,0.01281230097112188,0.8961410832798116,0.013750961121718442 +flat_mae,reg,logistic,ppmi_dx,90,0.046415888336127774,test,0.56,0.04413841410834783,0.5164835164835164,0.04782618259357257,0.5178268251273345,0.04592866385325775 +flat_mae,reg,logistic,ppmi_dx,91,0.046415888336127774,train,0.896797153024911,0.012269647238639197,0.8876944915312633,0.013749495931915231,0.8779169342753157,0.014478307179082325 +flat_mae,reg,logistic,ppmi_dx,91,0.046415888336127774,test,0.65,0.044620044822926835,0.6224786970121885,0.048606025983929074,0.6209677419354839,0.047902974514094955 +flat_mae,reg,logistic,ppmi_dx,92,0.3593813663804626,train,0.998220640569395,0.0018007926219300592,0.9981216765874674,0.001897734499477782,0.9985549132947977,0.0014624934299489827 +flat_mae,reg,logistic,ppmi_dx,92,0.3593813663804626,test,0.59,0.04939755459534408,0.5670995670995671,0.050998516355750985,0.5674872665534805,0.05130228177467836 +flat_mae,reg,logistic,ppmi_dx,93,0.046415888336127774,train,0.9145907473309609,0.011377096187098257,0.9080397076469946,0.012482948140839174,0.9010650824234638,0.013259863345725778 +flat_mae,reg,logistic,ppmi_dx,93,0.046415888336127774,test,0.58,0.047964899666318485,0.5625,0.04969441700914221,0.564516129032258,0.05069886522185111 +flat_mae,reg,logistic,ppmi_dx,94,0.005994842503189409,train,0.7953736654804271,0.015742082886074083,0.766039320453369,0.01926822866043379,0.7538000428173839,0.018329335827476853 +flat_mae,reg,logistic,ppmi_dx,94,0.005994842503189409,test,0.68,0.04089891930112578,0.6259934548854604,0.05108085085520882,0.6247877758913413,0.045529901369088126 +flat_mae,reg,logistic,ppmi_dx,95,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,95,21.54434690031882,test,0.56,0.04904179442067755,0.5331069609507639,0.051204563333448784,0.5331069609507639,0.05101623021973129 +flat_mae,reg,logistic,ppmi_dx,96,0.005994842503189409,train,0.8096085409252669,0.014561847953225907,0.7847460114617899,0.017443881606668647,0.7723185613359024,0.01700027778969286 +flat_mae,reg,logistic,ppmi_dx,96,0.005994842503189409,test,0.63,0.040562228735610675,0.5636277862955537,0.05057534794829756,0.5691850594227504,0.04406234405324586 +flat_mae,reg,logistic,ppmi_dx,97,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,97,2.782559402207126,test,0.56,0.04411745686233511,0.5164835164835164,0.04755621520507605,0.5178268251273345,0.04580994664073254 +flat_mae,reg,logistic,ppmi_dx,98,0.005994842503189409,train,0.7953736654804271,0.015650230822606134,0.7646694703879695,0.01953576396091866,0.7520605865981589,0.01851349225385302 +flat_mae,reg,logistic,ppmi_dx,98,0.005994842503189409,test,0.65,0.03997449186668919,0.5792763553311696,0.05238613842233354,0.5853140916808149,0.044470840227418686 +flat_mae,reg,logistic,ppmi_dx,99,0.000774263682681127,train,0.6797153024911032,0.011573056054841345,0.5677809680065627,0.02014307275553277,0.5937700706486834,0.013935076607382284 +flat_mae,reg,logistic,ppmi_dx,99,0.000774263682681127,test,0.61,0.030048460859085625,0.4729017434788485,0.04413491832250589,0.517402376910017,0.03194475462033669 +flat_mae,reg,logistic,ppmi_dx,100,0.046415888336127774,train,0.9234875444839857,0.010849060148372893,0.9173628327662557,0.01198650381104277,0.909160244059088,0.012922450290610411 +flat_mae,reg,logistic,ppmi_dx,100,0.046415888336127774,test,0.59,0.04686174986062727,0.5577607593571352,0.0495953240337669,0.5573005093378608,0.04862919267158898 diff --git a/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/log.txt b/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2ac8d4867a6801db05ccd3f0bcbd06968c2d21df --- /dev/null +++ b/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:18:34 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg1; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg1/eval_v2/ppmi_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:17:39 time: 4.5662 data: 3.5437 max mem: 2698 +extract (train) [ 20/232] eta: 0:01:24 time: 0.1906 data: 0.0697 max mem: 3005 +extract (train) [ 40/232] eta: 0:00:54 time: 0.1621 data: 0.0522 max mem: 3005 +extract (train) [ 60/232] eta: 0:00:41 time: 0.1566 data: 0.0492 max mem: 3005 +extract (train) [ 80/232] eta: 0:00:33 time: 0.1651 data: 0.0557 max mem: 3005 +extract (train) [100/232] eta: 0:00:28 time: 0.1768 data: 0.0592 max mem: 3005 +extract (train) [120/232] eta: 0:00:23 time: 0.1640 data: 0.0542 max mem: 3005 +extract (train) [140/232] eta: 0:00:18 time: 0.1770 data: 0.0591 max mem: 3005 +extract (train) [160/232] eta: 0:00:14 time: 0.1665 data: 0.0521 max mem: 3005 +extract (train) [180/232] eta: 0:00:10 time: 0.1575 data: 0.0517 max mem: 3005 +extract (train) [200/232] eta: 0:00:06 time: 0.1706 data: 0.0573 max mem: 3005 +extract (train) [220/232] eta: 0:00:02 time: 0.1611 data: 0.0513 max mem: 3005 +extract (train) [231/232] eta: 0:00:00 time: 0.1628 data: 0.0542 max mem: 3005 +extract (train) Total time: 0:00:43 (0.1889 s / it) +extract (validation) [ 0/50] eta: 0:03:21 time: 4.0325 data: 3.8933 max mem: 3005 +extract (validation) [20/50] eta: 0:00:12 time: 0.2320 data: 0.0759 max mem: 3005 +extract (validation) [40/50] eta: 0:00:02 time: 0.1579 data: 0.0456 max mem: 3005 +extract (validation) [49/50] eta: 0:00:00 time: 0.1544 data: 0.0451 max mem: 3005 +extract (validation) Total time: 0:00:13 (0.2730 s / it) +extract (test) [ 0/50] eta: 0:03:38 time: 4.3685 data: 4.2172 max mem: 3005 +extract (test) [20/50] eta: 0:00:13 time: 0.2576 data: 0.0933 max mem: 3005 +extract (test) [40/50] eta: 0:00:03 time: 0.1632 data: 0.0478 max mem: 3005 +extract (test) [49/50] eta: 0:00:00 time: 0.1665 data: 0.0508 max mem: 3005 +extract (test) Total time: 0:00:14 (0.2924 s / it) +feature extraction time: 0:01:12 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | | 0.0059948 | train | 0.78826 | 0.015775 | 0.75576 | 0.019858 | 0.74376 | 0.018655 | +| flat_mae | reg | logistic | ppmi_dx | | 0.0059948 | test | 0.62 | 0.035541 | 0.50624 | 0.049307 | 0.5311 | 0.038604 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.54, "acc_std": 0.04764288404368484, "f1": 0.5118845500848896, "f1_std": 0.0493115406410543, "bacc": 0.5118845500848896, "bacc_std": 0.04900838276395242} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.03957647786248796, "f1": 0.5143273433705683, "f1_std": 0.049255099633857574, "bacc": 0.5297113752122241, "bacc_std": 0.04162440880563508} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.04788016290699103, "f1": 0.5361881134721174, "f1_std": 0.05096673234724016, "bacc": 0.5360780984719864, "bacc_std": 0.04991830992222761} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04241687871590742, "f1": 0.609375, "f1_std": 0.049619890843987095, "bacc": 0.6086587436332768, "bacc_std": 0.04535992877588278} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.55, "acc_std": 0.045853087137072895, "f1": 0.5021573182874212, "f1_std": 0.049927596527497585, "bacc": 0.5046689303904923, "bacc_std": 0.04745487027089342} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.04615997833621675, "f1": 0.5305164319248826, "f1_std": 0.05035164970709522, "bacc": 0.5309847198641766, "bacc_std": 0.04882228964933279} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.049660330244572476, "f1": 0.5689655172413793, "f1_std": 0.04971039982892561, "bacc": 0.5747028862478778, "bacc_std": 0.05081812512250601} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.63, "acc_std": 0.04775327842148641, "f1": 0.6053333333333333, "f1_std": 0.05046597912106882, "bacc": 0.6048387096774194, "bacc_std": 0.05033019747504857} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.047673825103509364, "f1": 0.584, "f1_std": 0.05129804060463981, "bacc": 0.583616298811545, "bacc_std": 0.05094055122021549} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04758300536956446, "f1": 0.5464100011063171, "f1_std": 0.051992629292488254, "bacc": 0.5471137521222411, "bacc_std": 0.04935292504917706} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.03991957414602516, "f1": 0.5714285714285714, "f1_std": 0.050374918057164535, "bacc": 0.5772495755517827, "bacc_std": 0.04367569990644279} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.000774263682681127, "split": "test", "acc": 0.57, "acc_std": 0.030672098069744087, "f1": 0.4188403838356535, "f1_std": 0.03831677288037553, "bacc": 0.47495755517826826, "bacc_std": 0.030391175547897487} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04788591024508148, "f1": 0.5543293718166383, "f1_std": 0.04942330861778958, "bacc": 0.5543293718166383, "bacc_std": 0.04934404146848294} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 21.54434690031882, "split": "test", "acc": 0.56, "acc_std": 0.050899131623240876, "f1": 0.5452666391070691, "f1_std": 0.05158724605274322, "bacc": 0.5483870967741935, "bacc_std": 0.05274913890226157} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03519551675995113, "f1": 0.5287698412698413, "f1_std": 0.04844726862196129, "bacc": 0.5458404074702886, "bacc_std": 0.03869833043228537} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04819063809496612, "f1": 0.5741893219783819, "f1_std": 0.051960930610530746, "bacc": 0.5734295415959253, "bacc_std": 0.05035406419556085} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.047123565230147844, "f1": 0.5442708333333334, "f1_std": 0.04984158304077198, "bacc": 0.5441426146010186, "bacc_std": 0.0485267251184681} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.0408129195231118, "f1": 0.516452411841019, "f1_std": 0.04768034893928743, "bacc": 0.5267402376910016, "bacc_std": 0.042310065847541684} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 2.782559402207126, "split": "test", "acc": 0.55, "acc_std": 0.0487405539566386, "f1": 0.529239460194581, "f1_std": 0.05027374918464897, "bacc": 0.5301358234295416, "bacc_std": 0.05086046720633029} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 21.54434690031882, "split": "test", "acc": 0.6, "acc_std": 0.0449921726525848, "f1": 0.5659722222222222, "f1_std": 0.04904223062682838, "bacc": 0.565365025466893, "bacc_std": 0.04777205904913215} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04095414020584487, "f1": 0.6108031607500884, "f1_std": 0.05238226515635606, "bacc": 0.6116298811544991, "bacc_std": 0.04574288828473311} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.51, "acc_std": 0.04960088305665536, "f1": 0.48263118994826315, "f1_std": 0.05121234879450136, "bacc": 0.482597623089983, "bacc_std": 0.05108492157334616} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04334178122781758, "f1": 0.592944369063772, "f1_std": 0.050988231138931056, "bacc": 0.5925297113752122, "bacc_std": 0.04724573119548986} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04735599222907277, "f1": 0.6212121212121212, "f1_std": 0.05480576065687998, "bacc": 0.6188455008488964, "bacc_std": 0.05175631304848321} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04068255645851181, "f1": 0.5386109762020399, "f1_std": 0.05165693087209284, "bacc": 0.5509337860780985, "bacc_std": 0.04364482875756256} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 166.81005372000556, "split": "test", "acc": 0.52, "acc_std": 0.04879220839437378, "f1": 0.5104039167686658, "f1_std": 0.04879418558885745, "bacc": 0.5161290322580645, "bacc_std": 0.05037260243154183} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 21.54434690031882, "split": "test", "acc": 0.65, "acc_std": 0.04658289814942818, "f1": 0.6368917937545389, "f1_std": 0.047506227814465514, "bacc": 0.6413412563667232, "bacc_std": 0.04819474916613959} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.48, "acc_std": 0.04389031783890383, "f1": 0.4120307553143374, "f1_std": 0.04547360628315206, "bacc": 0.4227504244482173, "bacc_std": 0.043227342806824116} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.04535405163819436, "f1": 0.570999570999571, "f1_std": 0.04797354349117997, "bacc": 0.5704584040747029, "bacc_std": 0.04753394974781696} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 2.782559402207126, "split": "test", "acc": 0.54, "acc_std": 0.046421869846011155, "f1": 0.5245969408846631, "f1_std": 0.04723852862109287, "bacc": 0.5271646859083192, "bacc_std": 0.04847645651354544} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.63, "acc_std": 0.04687039150679243, "f1": 0.6254681647940075, "f1_std": 0.046739035677887286, "bacc": 0.6404923599320883, "bacc_std": 0.04836343212458863} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.04873407021786709, "f1": 0.6129302228266555, "f1_std": 0.04984186032317263, "bacc": 0.615025466893039, "bacc_std": 0.05045381745475584} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.045567988764043554, "f1": 0.648, "f1_std": 0.04847160818398622, "bacc": 0.6472835314091681, "bacc_std": 0.04824561820405694} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.69, "acc_std": 0.04111709620097216, "f1": 0.6467236467236468, "f1_std": 0.04872688853556702, "bacc": 0.6430390492359932, "bacc_std": 0.04517027696786742} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.04961562253967998, "f1": 0.5464100011063171, "f1_std": 0.05382101131551028, "bacc": 0.5471137521222411, "bacc_std": 0.05150952397886852} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.043854760288935576, "f1": 0.5634191176470589, "f1_std": 0.05119703890324886, "bacc": 0.566213921901528, "bacc_std": 0.04654560262575569} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 166.81005372000556, "split": "test", "acc": 0.56, "acc_std": 0.049559576269375016, "f1": 0.548440065681445, "f1_std": 0.04989225364807276, "bacc": 0.5534804753820034, "bacc_std": 0.05126969018419432} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.63, "acc_std": 0.047078470663350996, "f1": 0.6093337556752191, "f1_std": 0.04867204700138565, "bacc": 0.6099320882852293, "bacc_std": 0.04878254371340434} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.04809567132289558, "f1": 0.5604395604395604, "f1_std": 0.052879156756433815, "bacc": 0.5602716468590832, "bacc_std": 0.050685455007485516} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.05037289350434418, "f1": 0.5586380832282472, "f1_std": 0.051983194158654565, "bacc": 0.5594227504244482, "bacc_std": 0.05225983797768699} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04293425671884864, "f1": 0.6296711929076422, "f1_std": 0.049139695397906025, "bacc": 0.6269100169779287, "bacc_std": 0.046143288328387114} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.0345750140997802, "f1": 0.5862068965517242, "f1_std": 0.04909578632541204, "bacc": 0.5963497453310695, "bacc_std": 0.039256675439193825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04481685397258491, "f1": 0.6043956043956044, "f1_std": 0.04978921638015068, "bacc": 0.6027164685908319, "bacc_std": 0.047985720490077974} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.54, "acc_std": 0.05008792269599529, "f1": 0.5066495066495067, "f1_std": 0.05259924632602734, "bacc": 0.5067911714770797, "bacc_std": 0.05194900573299815} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.05342198423870083, "f1": 0.6189887756152817, "f1_std": 0.05384174436371583, "bacc": 0.6252122241086587, "bacc_std": 0.054796992830504786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.04869199112790521, "f1": 0.5796553173602353, "f1_std": 0.05132879245282865, "bacc": 0.5806451612903225, "bacc_std": 0.051836061851132556} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.040125059501513516, "f1": 0.5714285714285714, "f1_std": 0.050632324836548115, "bacc": 0.5772495755517827, "bacc_std": 0.04392969640126528} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 2.782559402207126, "split": "test", "acc": 0.68, "acc_std": 0.04591286965546806, "f1": 0.6604414261460102, "f1_std": 0.04840193939698929, "bacc": 0.6604414261460102, "bacc_std": 0.048369648620440256} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04214703311029141, "f1": 0.5863970588235294, "f1_std": 0.05124170091354092, "bacc": 0.5874363327674024, "bacc_std": 0.04608884869929445} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.047401312218123236, "f1": 0.5242836596968692, "f1_std": 0.05177476756360297, "bacc": 0.5258913412563667, "bacc_std": 0.04946647111655059} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 166.81005372000556, "split": "test", "acc": 0.61, "acc_std": 0.048823678681557785, "f1": 0.5920075321686369, "f1_std": 0.050893322616953944, "bacc": 0.5938030560271647, "bacc_std": 0.05162843163860421} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.045600877184545474, "f1": 0.554367201426025, "f1_std": 0.051156126213831, "bacc": 0.5551782682512734, "bacc_std": 0.04841577995947277} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.045572342489716276, "f1": 0.5098039215686274, "f1_std": 0.05039140911928061, "bacc": 0.5127334465195246, "bacc_std": 0.0477305531186235} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.52, "acc_std": 0.04809272710088294, "f1": 0.5, "f1_std": 0.048507125121926, "bacc": 0.5008488964346349, "bacc_std": 0.04940196022024757} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.04503706917640178, "f1": 0.5361881134721174, "f1_std": 0.04863074238570459, "bacc": 0.5360780984719864, "bacc_std": 0.047409247091664344} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04537620521815371, "f1": 0.5320855614973261, "f1_std": 0.049946763651716373, "bacc": 0.533955857385399, "bacc_std": 0.047321220649247826} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04927332341135516, "f1": 0.584, "f1_std": 0.051988358134296926, "bacc": 0.583616298811545, "bacc_std": 0.05166974309511503} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.000774263682681127, "split": "test", "acc": 0.62, "acc_std": 0.033527874969941064, "f1": 0.5062370062370062, "f1_std": 0.048160411377523006, "bacc": 0.5356536502546689, "bacc_std": 0.03644764592519959} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04624896106941214, "f1": 0.570999570999571, "f1_std": 0.050008848359092556, "bacc": 0.5704584040747029, "bacc_std": 0.049486961627823386} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.04755346885349165, "f1": 0.5659722222222222, "f1_std": 0.051156330966597545, "bacc": 0.565365025466893, "bacc_std": 0.04996143435454387} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04269037830706118, "f1": 0.5324918186068257, "f1_std": 0.04978138117074226, "bacc": 0.5398981324278438, "bacc_std": 0.044500530976119015} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.54, "acc_std": 0.04485326743950768, "f1": 0.4945054945054945, "f1_std": 0.04828548731566969, "bacc": 0.49660441426146007, "bacc_std": 0.046151624953092274} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.04586981578336674, "f1": 0.4429590017825312, "f1_std": 0.04764112487947692, "bacc": 0.4490662139219015, "bacc_std": 0.045792745422552225} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 166.81005372000556, "split": "test", "acc": 0.48, "acc_std": 0.04738192060269403, "f1": 0.4422994422994423, "f1_std": 0.048011015445325864, "bacc": 0.4431239388794567, "bacc_std": 0.047816422980700275} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04546620283243368, "f1": 0.5924495924495925, "f1_std": 0.04945304661813686, "bacc": 0.5916808149405772, "bacc_std": 0.048639124683485455} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 21.54434690031882, "split": "test", "acc": 0.45, "acc_std": 0.04826218395389915, "f1": 0.41333333333333333, "f1_std": 0.04772765618309145, "bacc": 0.41383701188455013, "bacc_std": 0.04775857741376698} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.04705949850986514, "f1": 0.562608076492727, "f1_std": 0.04654027637479382, "bacc": 0.5717317487266553, "bacc_std": 0.047942710002943874} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.041768887943061155, "f1": 0.5249681381068243, "f1_std": 0.04967918829363481, "bacc": 0.5318336162988115, "bacc_std": 0.04416184392451689} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.045832193925231204, "f1": 0.5659722222222222, "f1_std": 0.049030445871899656, "bacc": 0.565365025466893, "bacc_std": 0.0479393366352834} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.54, "acc_std": 0.045997808643456047, "f1": 0.4945054945054945, "f1_std": 0.05007249625403731, "bacc": 0.49660441426146007, "bacc_std": 0.04767624856349193} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.04778801523394752, "f1": 0.5793334052421529, "f1_std": 0.0514973135284971, "bacc": 0.5785229202037352, "bacc_std": 0.05039171251937784} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 166.81005372000556, "split": "test", "acc": 0.57, "acc_std": 0.04681869711984731, "f1": 0.5459824728117411, "f1_std": 0.048626370889368074, "bacc": 0.5462648556876061, "bacc_std": 0.04876330992385192} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04677833259106185, "f1": 0.5384615384615385, "f1_std": 0.05073267349314522, "bacc": 0.5390492359932089, "bacc_std": 0.04855823435804258} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.048592225715643034, "f1": 0.6093337556752191, "f1_std": 0.05044784280265885, "bacc": 0.6099320882852293, "bacc_std": 0.05043092527413005} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.040788017848382874, "f1": 0.5143273433705683, "f1_std": 0.04906635048069404, "bacc": 0.5297113752122241, "bacc_std": 0.04225159211453286} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.04900969291885024, "f1": 0.52, "f1_std": 0.05151411549271526, "bacc": 0.5199490662139219, "bacc_std": 0.05112581426426387} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.047041071416369755, "f1": 0.5523528769516323, "f1_std": 0.051658568030857735, "bacc": 0.5522071307300509, "bacc_std": 0.04957855187215168} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04399244935213314, "f1": 0.6011396011396011, "f1_std": 0.05255637044384299, "bacc": 0.6005942275042444, "bacc_std": 0.04847515897877285} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.000774263682681127, "split": "test", "acc": 0.61, "acc_std": 0.02948542012588596, "f1": 0.45765540258656656, "f1_std": 0.04452901620588249, "bacc": 0.5123089983022071, "bacc_std": 0.031537897756522326} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 166.81005372000556, "split": "test", "acc": 0.53, "acc_std": 0.05081968122686328, "f1": 0.5083167695365624, "f1_std": 0.051919965593242016, "bacc": 0.5089134125636672, "bacc_std": 0.052489899507988456} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.55, "acc_std": 0.04284575124793589, "f1": 0.4950061721467849, "f1_std": 0.04818122242065944, "bacc": 0.49957555178268254, "bacc_std": 0.04470391152117604} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 21.54434690031882, "split": "test", "acc": 0.58, "acc_std": 0.04729661298655538, "f1": 0.5495495495495495, "f1_std": 0.04968083452990254, "bacc": 0.5492359932088284, "bacc_std": 0.048965338700798916} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.54, "acc_std": 0.05176901003496203, "f1": 0.5118845500848896, "f1_std": 0.05412152773261562, "bacc": 0.5118845500848896, "bacc_std": 0.054033650050021476} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 21.54434690031882, "split": "test", "acc": 0.61, "acc_std": 0.04858343339040582, "f1": 0.5983935742971888, "f1_std": 0.04894392251960316, "bacc": 0.6039898132427843, "bacc_std": 0.050085753287423054} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04062832017201795, "f1": 0.5476190476190476, "f1_std": 0.05085748966778338, "bacc": 0.5560271646859083, "bacc_std": 0.04397567632955119} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04396934841454896, "f1": 0.5320855614973261, "f1_std": 0.04856836650760864, "bacc": 0.533955857385399, "bacc_std": 0.04574162036046841} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.045730095123452344, "f1": 0.5863970588235294, "f1_std": 0.053869501415995724, "bacc": 0.5874363327674024, "bacc_std": 0.04936485408738001} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04136955402225167, "f1": 0.6259934548854604, "f1_std": 0.0525234832328131, "bacc": 0.6247877758913413, "bacc_std": 0.046699490353516955} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 166.81005372000556, "split": "test", "acc": 0.57, "acc_std": 0.04797484340776945, "f1": 0.5501621508525996, "f1_std": 0.0497413085604683, "bacc": 0.551358234295416, "bacc_std": 0.05039185523786308} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.04413841410834783, "f1": 0.5164835164835164, "f1_std": 0.04782618259357257, "bacc": 0.5178268251273345, "bacc_std": 0.04592866385325775} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.044620044822926835, "f1": 0.6224786970121885, "f1_std": 0.048606025983929074, "bacc": 0.6209677419354839, "bacc_std": 0.047902974514094955} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04939755459534408, "f1": 0.5670995670995671, "f1_std": 0.050998516355750985, "bacc": 0.5674872665534805, "bacc_std": 0.05130228177467836} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.047964899666318485, "f1": 0.5625, "f1_std": 0.04969441700914221, "bacc": 0.564516129032258, "bacc_std": 0.05069886522185111} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04089891930112578, "f1": 0.6259934548854604, "f1_std": 0.05108085085520882, "bacc": 0.6247877758913413, "bacc_std": 0.045529901369088126} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 21.54434690031882, "split": "test", "acc": 0.56, "acc_std": 0.04904179442067755, "f1": 0.5331069609507639, "f1_std": 0.051204563333448784, "bacc": 0.5331069609507639, "bacc_std": 0.05101623021973129} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.040562228735610675, "f1": 0.5636277862955537, "f1_std": 0.05057534794829756, "bacc": 0.5691850594227504, "bacc_std": 0.04406234405324586} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 2.782559402207126, "split": "test", "acc": 0.56, "acc_std": 0.04411745686233511, "f1": 0.5164835164835164, "f1_std": 0.04755621520507605, "bacc": 0.5178268251273345, "bacc_std": 0.04580994664073254} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.03997449186668919, "f1": 0.5792763553311696, "f1_std": 0.05238613842233354, "bacc": 0.5853140916808149, "bacc_std": 0.044470840227418686} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.61, "acc_std": 0.030048460859085625, "f1": 0.4729017434788485, "f1_std": 0.04413491832250589, "bacc": 0.517402376910017, "bacc_std": 0.03194475462033669} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04686174986062727, "f1": 0.5577607593571352, "f1_std": 0.0495953240337669, "bacc": 0.5573005093378608, "bacc_std": 0.04862919267158898} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | train | 100 | 20.57 | 52.03 | 0.90918 | 0.091823 | 0.89575 | 0.1111 | 0.89106 | 0.11229 | +| flat_mae | reg | logistic | ppmi_dx | test | 100 | 20.57 | 52.03 | 0.5948 | 0.047172 | 0.55206 | 0.051226 | 0.55618 | 0.047806 | + + +done! total time: 0:05:21 diff --git a/decoders/crossreg_reg1/pretrain/config.yaml b/decoders/crossreg_reg1/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..feaf6e9da3ca195254216e75ae1981890a7fb284 --- /dev/null +++ b/decoders/crossreg_reg1/pretrain/config.yaml @@ -0,0 +1,99 @@ +name: decoders/crossreg_reg1/pretrain +notes: decoder ablations crossreg_reg1 (model_kwargs.decoding=crossreg model_kwargs.reg_tokens=1) +output_dir: experiments/decoders/output/decoders/crossreg_reg1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: crossreg + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + class_token: false + reg_tokens: 1 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/decoders/crossreg_reg1/pretrain/log.json b/decoders/crossreg_reg1/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..835a7167dfc4e03a9a74d8179fc668ce0f12d34d --- /dev/null +++ b/decoders/crossreg_reg1/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.013120476552546024, "train/loss": 0.9958403291893005, "eval/hcp-train-subset/loss": 0.995976984500885, "eval/hcp-val/loss": 0.9957742527607949} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.04677892064624719, "train/loss": 0.9944411948013305, "eval/hcp-train-subset/loss": 0.9936109906242739, "eval/hcp-val/loss": 0.9932837938108752} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.043054675917364844, "train/loss": 0.9922343576908111, "eval/hcp-train-subset/loss": 0.9922349674086417, "eval/hcp-val/loss": 0.990951923593398} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.12104469703422728, "train/loss": 0.987658240032196, "eval/hcp-train-subset/loss": 0.9852502451788995, "eval/hcp-val/loss": 0.9829819221650401} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.1436905354936447, "train/loss": 0.9832307527732849, "eval/hcp-train-subset/loss": 0.982552981184375, "eval/hcp-val/loss": 0.9803499637111541} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.16041621939122924, "train/loss": 0.9768645949077607, "eval/hcp-train-subset/loss": 0.9766131591412329, "eval/hcp-val/loss": 0.9740175191433199} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.19164537453830777, "train/loss": 0.9689482814502716, "eval/hcp-train-subset/loss": 0.9667357542822438, "eval/hcp-val/loss": 0.9637274597921679} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.2018469996524941, "train/loss": 0.9599459889030456, "eval/hcp-train-subset/loss": 0.9579398122525984, "eval/hcp-val/loss": 0.9551404656902436} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.20499155594193116, "train/loss": 0.9526728638839722, "eval/hcp-train-subset/loss": 0.9504610742292097, "eval/hcp-val/loss": 0.9461706280708313} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.19934792776088323, "train/loss": 0.9459312986564636, "eval/hcp-train-subset/loss": 0.9448111711009857, "eval/hcp-val/loss": 0.9408756532976704} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.2005795965554696, "train/loss": 0.9390890504741669, "eval/hcp-train-subset/loss": 0.9405156585478014, "eval/hcp-val/loss": 0.9359766139138129} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.19068752996693883, "train/loss": 0.9352394065666199, "eval/hcp-train-subset/loss": 0.9354004273491521, "eval/hcp-val/loss": 0.9316035768678111} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.1794845464969681, "train/loss": 0.9320327891254425, "eval/hcp-train-subset/loss": 0.9318915826659049, "eval/hcp-val/loss": 0.9272315944394758} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.1745731973156216, "train/loss": 0.9281847089004517, "eval/hcp-train-subset/loss": 0.928462169824108, "eval/hcp-val/loss": 0.9242466765065347} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.17004517560646745, "train/loss": 0.923158945350647, "eval/hcp-train-subset/loss": 0.9249561775115228, "eval/hcp-val/loss": 0.9213091625321296} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.16305373512117835, "train/loss": 0.9216287209701538, "eval/hcp-train-subset/loss": 0.9231832633095403, "eval/hcp-val/loss": 0.9189702849234304} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.1588896900062448, "train/loss": 0.9178319258594513, "eval/hcp-train-subset/loss": 0.9211664988148597, "eval/hcp-val/loss": 0.9174524882147389} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.1564349259472149, "train/loss": 0.9148847919178009, "eval/hcp-train-subset/loss": 0.9179284678351495, "eval/hcp-val/loss": 0.9139107994494899} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.1495411235161803, "train/loss": 0.9136725032424927, "eval/hcp-train-subset/loss": 0.9166816386484331, "eval/hcp-val/loss": 0.9128635256521164} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.1438215781401523, "train/loss": 0.9126153063678741, "eval/hcp-train-subset/loss": 0.9156851999221309, "eval/hcp-val/loss": 0.9107417079710192} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.13935327484466675, "train/loss": 0.9108825247955322, "eval/hcp-train-subset/loss": 0.9142169827415098, "eval/hcp-val/loss": 0.9099383008095526} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.13621483028664938, "train/loss": 0.9083364165210724, "eval/hcp-train-subset/loss": 0.9124709983025828, "eval/hcp-val/loss": 0.9080367838182757} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.1345747858214344, "train/loss": 0.9058385415554047, "eval/hcp-train-subset/loss": 0.9116830220145564, "eval/hcp-val/loss": 0.9072384055583708} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.12970467472584016, "train/loss": 0.9057866615867615, "eval/hcp-train-subset/loss": 0.9109559222575156, "eval/hcp-val/loss": 0.9060026916765398} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.12968774631378535, "train/loss": 0.9025007299423218, "eval/hcp-train-subset/loss": 0.9082744602234133, "eval/hcp-val/loss": 0.9039622199150824} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.1257154951873742, "train/loss": 0.9035641800689698, "eval/hcp-train-subset/loss": 0.908488699505406, "eval/hcp-val/loss": 0.9036838979490341} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.12459449486501964, "train/loss": 0.9023755426502228, "eval/hcp-train-subset/loss": 0.9077684590893407, "eval/hcp-val/loss": 0.9030899809252831} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.12094844504296351, "train/loss": 0.9011662386894226, "eval/hcp-train-subset/loss": 0.90678850489278, "eval/hcp-val/loss": 0.9025785855708583} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.11986093855803921, "train/loss": 0.900511413488388, "eval/hcp-train-subset/loss": 0.9059360190745323, "eval/hcp-val/loss": 0.9018988407427265} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.12172040418887489, "train/loss": 0.8972087801265717, "eval/hcp-train-subset/loss": 0.9051587427816083, "eval/hcp-val/loss": 0.9011791175411593} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.11495883468653001, "train/loss": 0.899097623796463, "eval/hcp-train-subset/loss": 0.9050051512256745, "eval/hcp-val/loss": 0.9006540333071062} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.11880312495114861, "train/loss": 0.8964911277198792, "eval/hcp-train-subset/loss": 0.9041092068918289, "eval/hcp-val/loss": 0.900403174661821} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.11306062263451673, "train/loss": 0.8980442223548889, "eval/hcp-train-subset/loss": 0.9038139975840046, "eval/hcp-val/loss": 0.8993190113575228} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.114167865044968, "train/loss": 0.8950316997814178, "eval/hcp-train-subset/loss": 0.9029499388510182, "eval/hcp-val/loss": 0.8988510437550083} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.11444639417888337, "train/loss": 0.8952050615024567, "eval/hcp-train-subset/loss": 0.9033526009128939, "eval/hcp-val/loss": 0.8995546025614585} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.11665250570006507, "train/loss": 0.8926357818031311, "eval/hcp-train-subset/loss": 0.9021992837229083, "eval/hcp-val/loss": 0.898071954327245} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.11438673359094591, "train/loss": 0.8947206095409393, "eval/hcp-train-subset/loss": 0.9016728035865291, "eval/hcp-val/loss": 0.897558928497376} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.11273299311925675, "train/loss": 0.8941395057296753, "eval/hcp-train-subset/loss": 0.9014354127068673, "eval/hcp-val/loss": 0.8972060343911571} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.11603496084645601, "train/loss": 0.8918262758541107, "eval/hcp-train-subset/loss": 0.9007069978021807, "eval/hcp-val/loss": 0.896689768760435} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.1157737531237903, "train/loss": 0.8907784888458252, "eval/hcp-train-subset/loss": 0.8997298902080905, "eval/hcp-val/loss": 0.8960627769270251} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.11579183666285953, "train/loss": 0.892945302476883, "eval/hcp-train-subset/loss": 0.9002787778454442, "eval/hcp-val/loss": 0.895994471926843} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.11766059703590699, "train/loss": 0.8903988942527771, "eval/hcp-train-subset/loss": 0.8988191139313483, "eval/hcp-val/loss": 0.8959122973103677} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.11562576552705993, "train/loss": 0.8912456320381165, "eval/hcp-train-subset/loss": 0.8991868457486553, "eval/hcp-val/loss": 0.8951814126583838} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.11961052324613927, "train/loss": 0.8892447493267059, "eval/hcp-train-subset/loss": 0.8982526544601687, "eval/hcp-val/loss": 0.8948057563074173} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.11708666802063183, "train/loss": 0.8878465418338776, "eval/hcp-train-subset/loss": 0.8973066066541979, "eval/hcp-val/loss": 0.8935292555439857} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.1205049966437656, "train/loss": 0.8878355521488189, "eval/hcp-train-subset/loss": 0.897930827832991, "eval/hcp-val/loss": 0.8942081197615592} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.11921873635385673, "train/loss": 0.8885330288505554, "eval/hcp-train-subset/loss": 0.896527559526505, "eval/hcp-val/loss": 0.8931001895858396} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.11861994390217313, "train/loss": 0.888475731973648, "eval/hcp-train-subset/loss": 0.8963369650225486, "eval/hcp-val/loss": 0.893388512634462} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.12256136546614992, "train/loss": 0.886841855506897, "eval/hcp-train-subset/loss": 0.8968271093983804, "eval/hcp-val/loss": 0.8933012235549188} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.12144122597067508, "train/loss": 0.8876157729911804, "eval/hcp-train-subset/loss": 0.8957311357221296, "eval/hcp-val/loss": 0.8930989907633874} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.12316548050752103, "train/loss": 0.8869433226680755, "eval/hcp-train-subset/loss": 0.8949369961215604, "eval/hcp-val/loss": 0.8924670334785215} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.11998408383161555, "train/loss": 0.8871764406776428, "eval/hcp-train-subset/loss": 0.894437147725013, "eval/hcp-val/loss": 0.891028405197205} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.12128359752024233, "train/loss": 0.8857182938957214, "eval/hcp-train-subset/loss": 0.8954589107344227, "eval/hcp-val/loss": 0.8916249880867619} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.12520806321658687, "train/loss": 0.8835849066352844, "eval/hcp-train-subset/loss": 0.8930383536123461, "eval/hcp-val/loss": 0.8916639541426012} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.12560868352203225, "train/loss": 0.8843005979537963, "eval/hcp-train-subset/loss": 0.8918812851752004, "eval/hcp-val/loss": 0.8913137633954326} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.12539189510171453, "train/loss": 0.8857234201240539, "eval/hcp-train-subset/loss": 0.8923250840556237, "eval/hcp-val/loss": 0.8899423854966317} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.1269081744128501, "train/loss": 0.8850894048690796, "eval/hcp-train-subset/loss": 0.8924112089218632, "eval/hcp-val/loss": 0.8903738173746294} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.12691795418782292, "train/loss": 0.883670255613327, "eval/hcp-train-subset/loss": 0.8920943592825243, "eval/hcp-val/loss": 0.891206669230615} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.13062026672227434, "train/loss": 0.8839191403102875, "eval/hcp-train-subset/loss": 0.8922182946435867, "eval/hcp-val/loss": 0.8897463910041317} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.12932165160002462, "train/loss": 0.8820280857181549, "eval/hcp-train-subset/loss": 0.8921519835149089, "eval/hcp-val/loss": 0.8896420165415733} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.13184618961578257, "train/loss": 0.8825875285625457, "eval/hcp-train-subset/loss": 0.891822938957522, "eval/hcp-val/loss": 0.8886859128552098} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.13055009475614632, "train/loss": 0.88227265209198, "eval/hcp-train-subset/loss": 0.8909372350861949, "eval/hcp-val/loss": 0.8886029470351434} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.12938850857770587, "train/loss": 0.8824621554279327, "eval/hcp-train-subset/loss": 0.8909408305921862, "eval/hcp-val/loss": 0.8883338339867131} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.13589051663493987, "train/loss": 0.8798403162288666, "eval/hcp-train-subset/loss": 0.8904913413909173, "eval/hcp-val/loss": 0.8879872675864927} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.13707342722882684, "train/loss": 0.8804466211223603, "eval/hcp-train-subset/loss": 0.889985719996114, "eval/hcp-val/loss": 0.8877322750706826} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.13403354790786257, "train/loss": 0.8814954561042786, "eval/hcp-train-subset/loss": 0.889909868278811, "eval/hcp-val/loss": 0.8881203993674247} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.1371859470047003, "train/loss": 0.8797313052177429, "eval/hcp-train-subset/loss": 0.8887425334222855, "eval/hcp-val/loss": 0.8873186745951253} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.13863283158030948, "train/loss": 0.8797030834388733, "eval/hcp-train-subset/loss": 0.8875919282436371, "eval/hcp-val/loss": 0.8872163641837335} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.13922246985934036, "train/loss": 0.8807426215553283, "eval/hcp-train-subset/loss": 0.888751128027516, "eval/hcp-val/loss": 0.8867072136171402} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.13851728621469608, "train/loss": 0.8809453124141693, "eval/hcp-train-subset/loss": 0.8880492448806763, "eval/hcp-val/loss": 0.8859088891936887} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.14378025168315953, "train/loss": 0.8792123316478729, "eval/hcp-train-subset/loss": 0.8871683805219589, "eval/hcp-val/loss": 0.8857245714433731} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.14257066498812235, "train/loss": 0.8791571943664551, "eval/hcp-train-subset/loss": 0.8877083034284653, "eval/hcp-val/loss": 0.8853444562804315} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.141194343757721, "train/loss": 0.8794018990325928, "eval/hcp-train-subset/loss": 0.8869334526600376, "eval/hcp-val/loss": 0.8852546772649211} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.1445288872155486, "train/loss": 0.880023350276947, "eval/hcp-train-subset/loss": 0.8866587088954064, "eval/hcp-val/loss": 0.8847267329692841} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.14361626164200822, "train/loss": 0.8804099445247651, "eval/hcp-train-subset/loss": 0.8862746002212647, "eval/hcp-val/loss": 0.8849177062511444} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.14417558186299975, "train/loss": 0.8786344333934784, "eval/hcp-train-subset/loss": 0.885548307049659, "eval/hcp-val/loss": 0.8840562393588405} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.15156868986316693, "train/loss": 0.8769770639705659, "eval/hcp-train-subset/loss": 0.885352889376302, "eval/hcp-val/loss": 0.8841741046597881} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.14742811437196054, "train/loss": 0.8802793583488464, "eval/hcp-train-subset/loss": 0.8854841263063492, "eval/hcp-val/loss": 0.8838051653677418} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.15002498487811175, "train/loss": 0.878726280822754, "eval/hcp-train-subset/loss": 0.8845429564675977, "eval/hcp-val/loss": 0.8835270433656631} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.1536891035952707, "train/loss": 0.8767983042430878, "eval/hcp-train-subset/loss": 0.8845732029407255, "eval/hcp-val/loss": 0.8833299452258695} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.15109405553322788, "train/loss": 0.8781260886669159, "eval/hcp-train-subset/loss": 0.8845864880469537, "eval/hcp-val/loss": 0.8836553077543935} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.1535500566377742, "train/loss": 0.8785548809146881, "eval/hcp-train-subset/loss": 0.883107413207331, "eval/hcp-val/loss": 0.8825883663469746} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.15623253449635455, "train/loss": 0.8770041329097747, "eval/hcp-train-subset/loss": 0.882690756551681, "eval/hcp-val/loss": 0.8826046912900863} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.15456709802203195, "train/loss": 0.8766005696582794, "eval/hcp-train-subset/loss": 0.8823669139415987, "eval/hcp-val/loss": 0.8823474145704701} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.15888622347089565, "train/loss": 0.8765854595088959, "eval/hcp-train-subset/loss": 0.8826555532793845, "eval/hcp-val/loss": 0.8824851080294578} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.15755714283404673, "train/loss": 0.876001187171936, "eval/hcp-train-subset/loss": 0.8817946160993269, "eval/hcp-val/loss": 0.8816071691051606} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.15774297931263756, "train/loss": 0.8788074966049194, "eval/hcp-train-subset/loss": 0.8824863453065196, "eval/hcp-val/loss": 0.8817465516828722} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.1618421022540552, "train/loss": 0.8760194149303436, "eval/hcp-train-subset/loss": 0.8816285690953655, "eval/hcp-val/loss": 0.8814886106598762} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.1558759570329289, "train/loss": 0.8786246121406556, "eval/hcp-train-subset/loss": 0.8812465744633828, "eval/hcp-val/loss": 0.8811618512676608} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.16172266613059336, "train/loss": 0.8788426070785522, "eval/hcp-train-subset/loss": 0.8806796794937503, "eval/hcp-val/loss": 0.8808353716327298} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.16073694029314953, "train/loss": 0.8780821794509888, "eval/hcp-train-subset/loss": 0.880037349077963, "eval/hcp-val/loss": 0.8806407076697196} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.16041316280306034, "train/loss": 0.8780720603561402, "eval/hcp-train-subset/loss": 0.8802283213984582, "eval/hcp-val/loss": 0.8805071346221431} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.15953288774156793, "train/loss": 0.8789937506866455, "eval/hcp-train-subset/loss": 0.880322185254866, "eval/hcp-val/loss": 0.880322995685762} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.1600452758661555, "train/loss": 0.8795108302974701, "eval/hcp-train-subset/loss": 0.8799951278394268, "eval/hcp-val/loss": 0.880145271939616} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.16339069008302437, "train/loss": 0.8783884255599975, "eval/hcp-train-subset/loss": 0.8798880134859393, "eval/hcp-val/loss": 0.8801282067452708} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.1639466934892097, "train/loss": 0.8790581334781646, "eval/hcp-train-subset/loss": 0.879908908759394, "eval/hcp-val/loss": 0.8800330306253126} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.16513911808097154, "train/loss": 0.8771445495510102, "eval/hcp-train-subset/loss": 0.8800083639160279, "eval/hcp-val/loss": 0.8798602127259777} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.16456333725060657, "train/loss": 0.8779545384597778, "eval/hcp-train-subset/loss": 0.8797709797659228, "eval/hcp-val/loss": 0.8797889409526702} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.16181667467406663, "train/loss": 0.8795447197341919, "eval/hcp-train-subset/loss": 0.8792772687250568, "eval/hcp-val/loss": 0.8800789175495025} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.16814345351604937, "train/loss": 0.8777064585399628, "eval/hcp-train-subset/loss": 0.8795197740677865, "eval/hcp-val/loss": 0.8798019366879617} diff --git a/decoders/crossreg_reg1/pretrain/log.txt b/decoders/crossreg_reg1/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7d53b275f7ee8e658484df065f86cb77f3ae9ecf --- /dev/null +++ b/decoders/crossreg_reg1/pretrain/log.txt @@ -0,0 +1,7774 @@ +pretraining fmri mae +start: 2026-01-16 00:34:08 +cwd: /admin/home/connor/fmri-fm +sha: f9ef1eebbc1a5292e462bf6c7741545659511885, status: has uncommitted changes, branch: dev/clane9 +config: +name: decoders/crossreg_reg1/pretrain +notes: decoder ablations crossreg_reg1 (model_kwargs.decoding=crossreg model_kwargs.reg_tokens=1) +output_dir: experiments/decoders/output/decoders/crossreg_reg1/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: crossreg + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + class_token: false + reg_tokens: 1 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +val transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=crossreg, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=False, reg_tokens=1, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=True, class_token=False, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Identity() + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=768, out_features=512, bias=True) + (v): Linear(in_features=768, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 100.4M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 10:39:23 lr: 0.000000 grad: 0.0264 (0.0264) loss: 0.9980 (0.9980) time: 6.1382 data: 4.9625 max mem: 7436 +Train: [0] [ 100/6250] eta: 0:20:57 lr: 0.000000 grad: 0.0140 (0.0160) loss: 0.9954 (0.9960) time: 0.1346 data: 0.0572 max mem: 8233 +Train: [0] [ 200/6250] eta: 0:20:42 lr: 0.000001 grad: 0.0135 (0.0151) loss: 0.9950 (0.9958) time: 0.2585 data: 0.1328 max mem: 8233 +Train: [0] [ 300/6250] eta: 0:19:35 lr: 0.000001 grad: 0.0127 (0.0145) loss: 0.9960 (0.9958) time: 0.1818 data: 0.0737 max mem: 8233 +Train: [0] [ 400/6250] eta: 0:19:29 lr: 0.000002 grad: 0.0128 (0.0141) loss: 0.9959 (0.9958) time: 0.2033 data: 0.0725 max mem: 8233 +Train: [0] [ 500/6250] eta: 0:19:17 lr: 0.000002 grad: 0.0128 (0.0139) loss: 0.9957 (0.9958) time: 0.1896 data: 0.0783 max mem: 8233 +Train: [0] [ 600/6250] eta: 0:18:29 lr: 0.000002 grad: 0.0123 (0.0137) loss: 0.9957 (0.9958) time: 0.1715 data: 0.0826 max mem: 8233 +Train: [0] [ 700/6250] eta: 0:18:08 lr: 0.000003 grad: 0.0127 (0.0135) loss: 0.9958 (0.9958) time: 0.2004 data: 0.1111 max mem: 8233 +Train: [0] [ 800/6250] eta: 0:17:37 lr: 0.000003 grad: 0.0127 (0.0134) loss: 0.9963 (0.9958) time: 0.1961 data: 0.1117 max mem: 8233 +Train: [0] [ 900/6250] eta: 0:17:11 lr: 0.000004 grad: 0.0124 (0.0133) loss: 0.9960 (0.9958) time: 0.1407 data: 0.0496 max mem: 8233 +Train: [0] [1000/6250] eta: 0:16:43 lr: 0.000004 grad: 0.0127 (0.0133) loss: 0.9952 (0.9958) time: 0.1736 data: 0.1000 max mem: 8233 +Train: [0] [1100/6250] eta: 0:16:13 lr: 0.000004 grad: 0.0125 (0.0132) loss: 0.9959 (0.9958) time: 0.1729 data: 0.0948 max mem: 8233 +Train: [0] [1200/6250] eta: 0:15:40 lr: 0.000005 grad: 0.0123 (0.0132) loss: 0.9955 (0.9958) time: 0.1394 data: 0.0570 max mem: 8233 +Train: [0] [1300/6250] eta: 0:15:10 lr: 0.000005 grad: 0.0125 (0.0131) loss: 0.9959 (0.9958) time: 0.1602 data: 0.0824 max mem: 8233 +Train: [0] [1400/6250] eta: 0:14:41 lr: 0.000006 grad: 0.0125 (0.0131) loss: 0.9958 (0.9958) time: 0.1640 data: 0.0812 max mem: 8233 +Train: [0] [1500/6250] eta: 0:14:15 lr: 0.000006 grad: 0.0130 (0.0131) loss: 0.9957 (0.9958) time: 0.1573 data: 0.0786 max mem: 8233 +Train: [0] [1600/6250] eta: 0:13:50 lr: 0.000006 grad: 0.0124 (0.0130) loss: 0.9955 (0.9958) time: 0.1720 data: 0.0922 max mem: 8233 +Train: [0] [1700/6250] eta: 0:13:26 lr: 0.000007 grad: 0.0129 (0.0130) loss: 0.9954 (0.9958) time: 0.1359 data: 0.0490 max mem: 8233 +Train: [0] [1800/6250] eta: 0:13:04 lr: 0.000007 grad: 0.0131 (0.0130) loss: 0.9962 (0.9958) time: 0.1553 data: 0.0729 max mem: 8233 +Train: [0] [1900/6250] eta: 0:12:42 lr: 0.000008 grad: 0.0130 (0.0130) loss: 0.9959 (0.9958) time: 0.1647 data: 0.0818 max mem: 8233 +Train: [0] [2000/6250] eta: 0:12:24 lr: 0.000008 grad: 0.0138 (0.0131) loss: 0.9953 (0.9958) time: 0.1697 data: 0.0938 max mem: 8233 +Train: [0] [2100/6250] eta: 0:12:03 lr: 0.000008 grad: 0.0127 (0.0131) loss: 0.9962 (0.9958) time: 0.1759 data: 0.0980 max mem: 8233 +Train: [0] [2200/6250] eta: 0:11:43 lr: 0.000009 grad: 0.0131 (0.0131) loss: 0.9957 (0.9958) time: 0.1529 data: 0.0661 max mem: 8233 +Train: [0] [2300/6250] eta: 0:11:26 lr: 0.000009 grad: 0.0130 (0.0131) loss: 0.9960 (0.9958) time: 0.1478 data: 0.0545 max mem: 8233 +Train: [0] [2400/6250] eta: 0:11:07 lr: 0.000010 grad: 0.0131 (0.0131) loss: 0.9955 (0.9958) time: 0.1588 data: 0.0820 max mem: 8233 +Train: [0] [2500/6250] eta: 0:10:49 lr: 0.000010 grad: 0.0130 (0.0131) loss: 0.9957 (0.9958) time: 0.1476 data: 0.0664 max mem: 8233 +Train: [0] [2600/6250] eta: 0:10:29 lr: 0.000010 grad: 0.0136 (0.0131) loss: 0.9960 (0.9958) time: 0.1661 data: 0.0900 max mem: 8233 +Train: [0] [2700/6250] eta: 0:10:11 lr: 0.000011 grad: 0.0127 (0.0131) loss: 0.9962 (0.9958) time: 0.1607 data: 0.0694 max mem: 8233 +Train: [0] [2800/6250] eta: 0:09:52 lr: 0.000011 grad: 0.0127 (0.0131) loss: 0.9960 (0.9958) time: 0.1579 data: 0.0898 max mem: 8233 +Train: [0] [2900/6250] eta: 0:09:35 lr: 0.000012 grad: 0.0130 (0.0131) loss: 0.9956 (0.9958) time: 0.1528 data: 0.0861 max mem: 8233 +Train: [0] [3000/6250] eta: 0:09:16 lr: 0.000012 grad: 0.0131 (0.0131) loss: 0.9957 (0.9958) time: 0.1644 data: 0.0772 max mem: 8233 +Train: [0] [3100/6250] eta: 0:08:58 lr: 0.000012 grad: 0.0125 (0.0131) loss: 0.9963 (0.9958) time: 0.1775 data: 0.0986 max mem: 8233 +Train: [0] [3200/6250] eta: 0:08:40 lr: 0.000013 grad: 0.0134 (0.0131) loss: 0.9961 (0.9958) time: 0.1510 data: 0.0657 max mem: 8233 +Train: [0] [3300/6250] eta: 0:08:22 lr: 0.000013 grad: 0.0130 (0.0131) loss: 0.9956 (0.9958) time: 0.1552 data: 0.0801 max mem: 8233 +Train: [0] [3400/6250] eta: 0:08:04 lr: 0.000014 grad: 0.0127 (0.0131) loss: 0.9956 (0.9958) time: 0.1344 data: 0.0565 max mem: 8233 +Train: [0] [3500/6250] eta: 0:07:46 lr: 0.000014 grad: 0.0131 (0.0131) loss: 0.9960 (0.9958) time: 0.1465 data: 0.0605 max mem: 8233 +Train: [0] [3600/6250] eta: 0:07:29 lr: 0.000014 grad: 0.0130 (0.0131) loss: 0.9959 (0.9958) time: 0.1509 data: 0.0741 max mem: 8233 +Train: [0] [3700/6250] eta: 0:07:11 lr: 0.000015 grad: 0.0125 (0.0131) loss: 0.9963 (0.9958) time: 0.1551 data: 0.0667 max mem: 8233 +Train: [0] [3800/6250] eta: 0:06:53 lr: 0.000015 grad: 0.0123 (0.0131) loss: 0.9957 (0.9958) time: 0.1430 data: 0.0533 max mem: 8233 +Train: [0] [3900/6250] eta: 0:06:36 lr: 0.000016 grad: 0.0138 (0.0131) loss: 0.9958 (0.9958) time: 0.1738 data: 0.1001 max mem: 8233 +Train: [0] [4000/6250] eta: 0:06:18 lr: 0.000016 grad: 0.0135 (0.0131) loss: 0.9959 (0.9958) time: 0.1419 data: 0.0588 max mem: 8233 +Train: [0] [4100/6250] eta: 0:06:01 lr: 0.000016 grad: 0.0138 (0.0132) loss: 0.9963 (0.9958) time: 0.1532 data: 0.0779 max mem: 8233 +Train: [0] [4200/6250] eta: 0:05:44 lr: 0.000017 grad: 0.0135 (0.0132) loss: 0.9958 (0.9958) time: 0.1574 data: 0.0747 max mem: 8233 +Train: [0] [4300/6250] eta: 0:05:27 lr: 0.000017 grad: 0.0125 (0.0132) loss: 0.9956 (0.9958) time: 0.1760 data: 0.0989 max mem: 8233 +Train: [0] [4400/6250] eta: 0:05:09 lr: 0.000018 grad: 0.0129 (0.0132) loss: 0.9958 (0.9958) time: 0.1339 data: 0.0539 max mem: 8233 +Train: [0] [4500/6250] eta: 0:04:52 lr: 0.000018 grad: 0.0128 (0.0132) loss: 0.9957 (0.9958) time: 0.1678 data: 0.0904 max mem: 8233 +Train: [0] [4600/6250] eta: 0:04:35 lr: 0.000018 grad: 0.0126 (0.0132) loss: 0.9954 (0.9958) time: 0.1620 data: 0.0853 max mem: 8233 +Train: [0] [4700/6250] eta: 0:04:18 lr: 0.000019 grad: 0.0124 (0.0132) loss: 0.9959 (0.9958) time: 0.1669 data: 0.0882 max mem: 8233 +Train: [0] [4800/6250] eta: 0:04:01 lr: 0.000019 grad: 0.0128 (0.0132) loss: 0.9957 (0.9958) time: 0.1721 data: 0.0913 max mem: 8233 +Train: [0] [4900/6250] eta: 0:03:44 lr: 0.000020 grad: 0.0133 (0.0132) loss: 0.9958 (0.9958) time: 0.1214 data: 0.0371 max mem: 8233 +Train: [0] [5000/6250] eta: 0:03:28 lr: 0.000020 grad: 0.0134 (0.0132) loss: 0.9960 (0.9958) time: 0.1635 data: 0.0885 max mem: 8233 +Train: [0] [5100/6250] eta: 0:03:11 lr: 0.000020 grad: 0.0124 (0.0132) loss: 0.9958 (0.9958) time: 0.1540 data: 0.0694 max mem: 8233 +Train: [0] [5200/6250] eta: 0:02:54 lr: 0.000021 grad: 0.0134 (0.0132) loss: 0.9958 (0.9958) time: 0.1547 data: 0.0727 max mem: 8233 +Train: [0] [5300/6250] eta: 0:02:37 lr: 0.000021 grad: 0.0126 (0.0132) loss: 0.9961 (0.9958) time: 0.1679 data: 0.0850 max mem: 8233 +Train: [0] [5400/6250] eta: 0:02:21 lr: 0.000022 grad: 0.0134 (0.0132) loss: 0.9959 (0.9958) time: 0.1415 data: 0.0529 max mem: 8233 +Train: [0] [5500/6250] eta: 0:02:04 lr: 0.000022 grad: 0.0131 (0.0132) loss: 0.9958 (0.9958) time: 0.1826 data: 0.1028 max mem: 8233 +Train: [0] [5600/6250] eta: 0:01:47 lr: 0.000022 grad: 0.0119 (0.0132) loss: 0.9955 (0.9958) time: 0.1623 data: 0.0766 max mem: 8233 +Train: [0] [5700/6250] eta: 0:01:31 lr: 0.000023 grad: 0.0120 (0.0131) loss: 0.9956 (0.9958) time: 0.1741 data: 0.0942 max mem: 8233 +Train: [0] [5800/6250] eta: 0:01:14 lr: 0.000023 grad: 0.0119 (0.0131) loss: 0.9955 (0.9958) time: 0.1689 data: 0.0940 max mem: 8233 +Train: [0] [5900/6250] eta: 0:00:58 lr: 0.000024 grad: 0.0123 (0.0131) loss: 0.9958 (0.9958) time: 0.1773 data: 0.0942 max mem: 8233 +Train: [0] [6000/6250] eta: 0:00:41 lr: 0.000024 grad: 0.0128 (0.0131) loss: 0.9952 (0.9958) time: 0.1465 data: 0.0642 max mem: 8233 +Train: [0] [6100/6250] eta: 0:00:24 lr: 0.000024 grad: 0.0127 (0.0131) loss: 0.9956 (0.9958) time: 0.1852 data: 0.1116 max mem: 8233 +Train: [0] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.0123 (0.0131) loss: 0.9956 (0.9958) time: 0.1388 data: 0.0607 max mem: 8233 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0139 (0.0131) loss: 0.9955 (0.9958) time: 0.1715 data: 0.1037 max mem: 8233 +Train: [0] Total time: 0:17:21 (0.1667 s / it) +Averaged stats: lr: 0.000025 grad: 0.0139 (0.0131) loss: 0.9955 (0.9958) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:04:02 loss: 0.9969 (0.9969) time: 3.9175 data: 3.7897 max mem: 8233 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9961 (0.9960) time: 0.0790 data: 0.0586 max mem: 8233 +Eval (hcp-train-subset): [0] Total time: 0:00:14 (0.2331 s / it) +Averaged stats (hcp-train-subset): loss: 0.9961 (0.9960) +Eval (hcp-val): [0] [ 0/62] eta: 0:08:06 loss: 0.9959 (0.9959) time: 7.8404 data: 7.8147 max mem: 8233 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9955 (0.9958) time: 0.1565 data: 0.1348 max mem: 8233 +Eval (hcp-val): [0] Total time: 0:00:18 (0.2957 s / it) +Averaged stats (hcp-val): loss: 0.9955 (0.9958) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 10:25:31 lr: 0.000025 grad: 0.0280 (0.0280) loss: 0.9965 (0.9965) time: 6.0050 data: 5.9275 max mem: 8233 +Train: [1] [ 100/6250] eta: 0:21:21 lr: 0.000025 grad: 0.0182 (0.0207) loss: 0.9952 (0.9958) time: 0.1683 data: 0.0846 max mem: 8233 +Train: [1] [ 200/6250] eta: 0:18:43 lr: 0.000026 grad: 0.0202 (0.0216) loss: 0.9952 (0.9957) time: 0.1636 data: 0.0709 max mem: 8233 +Train: [1] [ 300/6250] eta: 0:17:40 lr: 0.000026 grad: 0.0128 (0.0239) loss: 0.9956 (0.9958) time: 0.1746 data: 0.0885 max mem: 8233 +Train: [1] [ 400/6250] eta: 0:16:55 lr: 0.000027 grad: 0.0190 (0.0219) loss: 0.9961 (0.9958) time: 0.1553 data: 0.0541 max mem: 8233 +Train: [1] [ 500/6250] eta: 0:16:19 lr: 0.000027 grad: 0.0240 (0.0277) loss: 0.9955 (0.9957) time: 0.1623 data: 0.0604 max mem: 8233 +Train: [1] [ 600/6250] eta: 0:15:52 lr: 0.000027 grad: 0.0231 (0.0330) loss: 0.9951 (0.9956) time: 0.1504 data: 0.0553 max mem: 8233 +Train: [1] [ 700/6250] eta: 0:15:29 lr: 0.000028 grad: 0.0320 (0.0366) loss: 0.9954 (0.9956) time: 0.1519 data: 0.0580 max mem: 8233 +Train: [1] [ 800/6250] eta: 0:15:14 lr: 0.000028 grad: 0.0150 (0.0399) loss: 0.9958 (0.9955) time: 0.1849 data: 0.1029 max mem: 8233 +Train: [1] [ 900/6250] eta: 0:15:06 lr: 0.000029 grad: 0.0199 (0.0413) loss: 0.9952 (0.9955) time: 0.1669 data: 0.0828 max mem: 8233 +Train: [1] [1000/6250] eta: 0:14:46 lr: 0.000029 grad: 0.0406 (0.0419) loss: 0.9952 (0.9955) time: 0.1664 data: 0.0900 max mem: 8233 +Train: [1] [1100/6250] eta: 0:14:32 lr: 0.000029 grad: 0.0452 (0.0441) loss: 0.9946 (0.9954) time: 0.1902 data: 0.1155 max mem: 8233 +Train: [1] [1200/6250] eta: 0:14:13 lr: 0.000030 grad: 0.0198 (0.0462) loss: 0.9948 (0.9954) time: 0.1473 data: 0.0624 max mem: 8233 +Train: [1] [1300/6250] eta: 0:13:56 lr: 0.000030 grad: 0.0227 (0.0470) loss: 0.9947 (0.9954) time: 0.1679 data: 0.0910 max mem: 8233 +Train: [1] [1400/6250] eta: 0:13:38 lr: 0.000031 grad: 0.0381 (0.0484) loss: 0.9954 (0.9953) time: 0.1649 data: 0.0768 max mem: 8233 +Train: [1] [1500/6250] eta: 0:13:20 lr: 0.000031 grad: 0.0325 (0.0483) loss: 0.9954 (0.9953) time: 0.1435 data: 0.0631 max mem: 8233 +Train: [1] [1600/6250] eta: 0:13:02 lr: 0.000031 grad: 0.0475 (0.0480) loss: 0.9955 (0.9953) time: 0.1673 data: 0.0875 max mem: 8233 +Train: [1] [1700/6250] eta: 0:12:41 lr: 0.000032 grad: 0.0377 (0.0476) loss: 0.9946 (0.9953) time: 0.1389 data: 0.0449 max mem: 8233 +Train: [1] [1800/6250] eta: 0:12:23 lr: 0.000032 grad: 0.0263 (0.0472) loss: 0.9943 (0.9953) time: 0.1819 data: 0.1159 max mem: 8233 +Train: [1] [1900/6250] eta: 0:12:05 lr: 0.000033 grad: 0.0314 (0.0470) loss: 0.9948 (0.9953) time: 0.1613 data: 0.0759 max mem: 8233 +Train: [1] [2000/6250] eta: 0:11:46 lr: 0.000033 grad: 0.0308 (0.0465) loss: 0.9952 (0.9952) time: 0.1560 data: 0.0751 max mem: 8233 +Train: [1] [2100/6250] eta: 0:11:26 lr: 0.000033 grad: 0.0330 (0.0463) loss: 0.9952 (0.9952) time: 0.1456 data: 0.0593 max mem: 8233 +Train: [1] [2200/6250] eta: 0:11:09 lr: 0.000034 grad: 0.0257 (0.0457) loss: 0.9948 (0.9952) time: 0.1645 data: 0.0860 max mem: 8233 +Train: [1] [2300/6250] eta: 0:10:49 lr: 0.000034 grad: 0.0280 (0.0455) loss: 0.9948 (0.9952) time: 0.1374 data: 0.0648 max mem: 8233 +Train: [1] [2400/6250] eta: 0:10:33 lr: 0.000035 grad: 0.0336 (0.0450) loss: 0.9942 (0.9952) time: 0.1490 data: 0.0722 max mem: 8233 +Train: [1] [2500/6250] eta: 0:10:17 lr: 0.000035 grad: 0.0249 (0.0444) loss: 0.9955 (0.9952) time: 0.1492 data: 0.0598 max mem: 8233 +Train: [1] [2600/6250] eta: 0:10:01 lr: 0.000035 grad: 0.0353 (0.0441) loss: 0.9948 (0.9952) time: 0.1775 data: 0.1071 max mem: 8233 +Train: [1] [2700/6250] eta: 0:09:44 lr: 0.000036 grad: 0.0326 (0.0437) loss: 0.9945 (0.9952) time: 0.1743 data: 0.0968 max mem: 8233 +Train: [1] [2800/6250] eta: 0:09:26 lr: 0.000036 grad: 0.0244 (0.0431) loss: 0.9958 (0.9952) time: 0.1347 data: 0.0527 max mem: 8233 +Train: [1] [2900/6250] eta: 0:09:09 lr: 0.000037 grad: 0.0331 (0.0429) loss: 0.9950 (0.9952) time: 0.1552 data: 0.0754 max mem: 8233 +Train: [1] [3000/6250] eta: 0:08:52 lr: 0.000037 grad: 0.0237 (0.0424) loss: 0.9952 (0.9952) time: 0.1729 data: 0.0955 max mem: 8233 +Train: [1] [3100/6250] eta: 0:08:35 lr: 0.000037 grad: 0.0222 (0.0419) loss: 0.9948 (0.9952) time: 0.1782 data: 0.0999 max mem: 8233 +Train: [1] [3200/6250] eta: 0:08:18 lr: 0.000038 grad: 0.0235 (0.0415) loss: 0.9951 (0.9952) time: 0.1822 data: 0.1057 max mem: 8233 +Train: [1] [3300/6250] eta: 0:08:02 lr: 0.000038 grad: 0.0250 (0.0412) loss: 0.9952 (0.9951) time: 0.1532 data: 0.0710 max mem: 8233 +Train: [1] [3400/6250] eta: 0:07:46 lr: 0.000039 grad: 0.0250 (0.0408) loss: 0.9947 (0.9951) time: 0.1630 data: 0.0766 max mem: 8233 +Train: [1] [3500/6250] eta: 0:07:28 lr: 0.000039 grad: 0.0255 (0.0405) loss: 0.9944 (0.9951) time: 0.1380 data: 0.0510 max mem: 8233 +Train: [1] [3600/6250] eta: 0:07:12 lr: 0.000039 grad: 0.0281 (0.0402) loss: 0.9947 (0.9951) time: 0.1850 data: 0.1075 max mem: 8233 +Train: [1] [3700/6250] eta: 0:06:55 lr: 0.000040 grad: 0.0445 (0.0412) loss: 0.9944 (0.9951) time: 0.1482 data: 0.0701 max mem: 8233 +Train: [1] [3800/6250] eta: 0:06:38 lr: 0.000040 grad: 0.0342 (0.0421) loss: 0.9941 (0.9951) time: 0.1589 data: 0.0791 max mem: 8233 +Train: [1] [3900/6250] eta: 0:06:22 lr: 0.000041 grad: 0.0430 (0.0429) loss: 0.9946 (0.9950) time: 0.1878 data: 0.1152 max mem: 8233 +Train: [1] [4000/6250] eta: 0:06:06 lr: 0.000041 grad: 0.0438 (0.0449) loss: 0.9936 (0.9950) time: 0.1849 data: 0.1124 max mem: 8233 +Train: [1] [4100/6250] eta: 0:05:50 lr: 0.000041 grad: 0.0408 (0.0464) loss: 0.9937 (0.9950) time: 0.1582 data: 0.0751 max mem: 8233 +Train: [1] [4200/6250] eta: 0:05:34 lr: 0.000042 grad: 0.0393 (0.0464) loss: 0.9940 (0.9950) time: 0.1838 data: 0.1076 max mem: 8233 +Train: [1] [4300/6250] eta: 0:05:17 lr: 0.000042 grad: 0.0326 (0.0479) loss: 0.9946 (0.9950) time: 0.1657 data: 0.0828 max mem: 8233 +Train: [1] [4400/6250] eta: 0:05:01 lr: 0.000043 grad: 0.0415 (0.0480) loss: 0.9935 (0.9949) time: 0.1713 data: 0.0948 max mem: 8233 +Train: [1] [4500/6250] eta: 0:04:45 lr: 0.000043 grad: 0.0417 (0.0479) loss: 0.9938 (0.9949) time: 0.1452 data: 0.0598 max mem: 8233 +Train: [1] [4600/6250] eta: 0:04:29 lr: 0.000043 grad: 0.0505 (0.0480) loss: 0.9926 (0.9949) time: 0.1727 data: 0.0904 max mem: 8233 +Train: [1] [4700/6250] eta: 0:04:13 lr: 0.000044 grad: 0.0489 (0.0481) loss: 0.9937 (0.9949) time: 0.1674 data: 0.0817 max mem: 8233 +Train: [1] [4800/6250] eta: 0:03:56 lr: 0.000044 grad: 0.0483 (0.0480) loss: 0.9924 (0.9948) time: 0.1591 data: 0.0807 max mem: 8233 +Train: [1] [4900/6250] eta: 0:03:40 lr: 0.000045 grad: 0.0387 (0.0479) loss: 0.9940 (0.9948) time: 0.1643 data: 0.0889 max mem: 8233 +Train: [1] [5000/6250] eta: 0:03:24 lr: 0.000045 grad: 0.0413 (0.0478) loss: 0.9921 (0.9948) time: 0.1858 data: 0.1113 max mem: 8233 +Train: [1] [5100/6250] eta: 0:03:07 lr: 0.000045 grad: 0.0474 (0.0478) loss: 0.9934 (0.9947) time: 0.1476 data: 0.0647 max mem: 8233 +Train: [1] [5200/6250] eta: 0:02:51 lr: 0.000046 grad: 0.0427 (0.0477) loss: 0.9930 (0.9947) time: 0.1851 data: 0.1119 max mem: 8233 +Train: [1] [5300/6250] eta: 0:02:35 lr: 0.000046 grad: 0.0354 (0.0477) loss: 0.9937 (0.9947) time: 0.1835 data: 0.1051 max mem: 8233 +Train: [1] [5400/6250] eta: 0:02:18 lr: 0.000047 grad: 0.0406 (0.0476) loss: 0.9924 (0.9946) time: 0.1688 data: 0.0901 max mem: 8233 +Train: [1] [5500/6250] eta: 0:02:02 lr: 0.000047 grad: 0.0400 (0.0475) loss: 0.9924 (0.9946) time: 0.1564 data: 0.0784 max mem: 8233 +Train: [1] [5600/6250] eta: 0:01:46 lr: 0.000047 grad: 0.0431 (0.0475) loss: 0.9937 (0.9946) time: 0.1630 data: 0.0867 max mem: 8233 +Train: [1] [5700/6250] eta: 0:01:29 lr: 0.000048 grad: 0.0415 (0.0474) loss: 0.9932 (0.9946) time: 0.1476 data: 0.0673 max mem: 8233 +Train: [1] [5800/6250] eta: 0:01:13 lr: 0.000048 grad: 0.0411 (0.0473) loss: 0.9925 (0.9945) time: 0.1667 data: 0.0897 max mem: 8233 +Train: [1] [5900/6250] eta: 0:00:57 lr: 0.000049 grad: 0.0358 (0.0472) loss: 0.9933 (0.9945) time: 0.1671 data: 0.0795 max mem: 8233 +Train: [1] [6000/6250] eta: 0:00:40 lr: 0.000049 grad: 0.0312 (0.0470) loss: 0.9938 (0.9945) time: 0.1628 data: 0.0793 max mem: 8233 +Train: [1] [6100/6250] eta: 0:00:24 lr: 0.000049 grad: 0.0412 (0.0469) loss: 0.9924 (0.9945) time: 0.1536 data: 0.0694 max mem: 8233 +Train: [1] [6200/6250] eta: 0:00:08 lr: 0.000050 grad: 0.0440 (0.0468) loss: 0.9935 (0.9945) time: 0.1605 data: 0.0815 max mem: 8233 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.0426 (0.0468) loss: 0.9920 (0.9944) time: 0.1357 data: 0.0741 max mem: 8233 +Train: [1] Total time: 0:17:08 (0.1646 s / it) +Averaged stats: lr: 0.000050 grad: 0.0426 (0.0468) loss: 0.9920 (0.9944) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:03:40 loss: 0.9944 (0.9944) time: 3.5491 data: 3.4878 max mem: 8233 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9941 (0.9936) time: 0.1295 data: 0.1071 max mem: 8233 +Eval (hcp-train-subset): [1] Total time: 0:00:14 (0.2320 s / it) +Averaged stats (hcp-train-subset): loss: 0.9941 (0.9936) +Eval (hcp-val): [1] [ 0/62] eta: 0:04:21 loss: 0.9906 (0.9906) time: 4.2189 data: 4.1026 max mem: 8233 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9935 (0.9933) time: 0.1584 data: 0.1366 max mem: 8233 +Eval (hcp-val): [1] Total time: 0:00:16 (0.2603 s / it) +Averaged stats (hcp-val): loss: 0.9935 (0.9933) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 9:30:13 lr: 0.000050 grad: 0.0457 (0.0457) loss: 0.9919 (0.9919) time: 5.4741 data: 5.3132 max mem: 8233 +Train: [2] [ 100/6250] eta: 0:24:50 lr: 0.000050 grad: 0.0401 (0.0539) loss: 0.9935 (0.9922) time: 0.1745 data: 0.0858 max mem: 8233 +Train: [2] [ 200/6250] eta: 0:20:41 lr: 0.000051 grad: 0.0342 (0.0486) loss: 0.9934 (0.9926) time: 0.1782 data: 0.0778 max mem: 8233 +Train: [2] [ 300/6250] eta: 0:19:15 lr: 0.000051 grad: 0.0427 (0.0476) loss: 0.9919 (0.9926) time: 0.1533 data: 0.0352 max mem: 8233 +Train: [2] [ 400/6250] eta: 0:18:08 lr: 0.000052 grad: 0.0438 (0.0469) loss: 0.9915 (0.9927) time: 0.1723 data: 0.0861 max mem: 8233 +Train: [2] [ 500/6250] eta: 0:17:13 lr: 0.000052 grad: 0.0464 (0.0478) loss: 0.9934 (0.9926) time: 0.1535 data: 0.0515 max mem: 8233 +Train: [2] [ 600/6250] eta: 0:16:36 lr: 0.000052 grad: 0.0416 (0.0478) loss: 0.9920 (0.9925) time: 0.1250 data: 0.0256 max mem: 8233 +Train: [2] [ 700/6250] eta: 0:16:05 lr: 0.000053 grad: 0.0458 (0.0475) loss: 0.9930 (0.9925) time: 0.1708 data: 0.0782 max mem: 8233 +Train: [2] [ 800/6250] eta: 0:15:45 lr: 0.000053 grad: 0.0446 (0.0481) loss: 0.9918 (0.9924) time: 0.1768 data: 0.0926 max mem: 8233 +Train: [2] [ 900/6250] eta: 0:15:21 lr: 0.000054 grad: 0.0319 (0.0477) loss: 0.9931 (0.9924) time: 0.1251 data: 0.0349 max mem: 8233 +Train: [2] [1000/6250] eta: 0:15:03 lr: 0.000054 grad: 0.0382 (0.0475) loss: 0.9928 (0.9924) time: 0.1760 data: 0.1013 max mem: 8233 +Train: [2] [1100/6250] eta: 0:14:46 lr: 0.000054 grad: 0.0455 (0.0476) loss: 0.9925 (0.9924) time: 0.1825 data: 0.0816 max mem: 8233 +Train: [2] [1200/6250] eta: 0:14:32 lr: 0.000055 grad: 0.0401 (0.0472) loss: 0.9928 (0.9924) time: 0.2206 data: 0.1510 max mem: 8233 +Train: [2] [1300/6250] eta: 0:14:08 lr: 0.000055 grad: 0.0423 (0.0468) loss: 0.9921 (0.9924) time: 0.1615 data: 0.0789 max mem: 8233 +Train: [2] [1400/6250] eta: 0:13:46 lr: 0.000056 grad: 0.0485 (0.0465) loss: 0.9924 (0.9924) time: 0.1683 data: 0.0919 max mem: 8233 +Train: [2] [1500/6250] eta: 0:13:25 lr: 0.000056 grad: 0.0318 (0.0462) loss: 0.9928 (0.9924) time: 0.1537 data: 0.0743 max mem: 8233 +Train: [2] [1600/6250] eta: 0:13:06 lr: 0.000056 grad: 0.0370 (0.0463) loss: 0.9925 (0.9924) time: 0.1685 data: 0.0946 max mem: 8233 +Train: [2] [1700/6250] eta: 0:12:46 lr: 0.000057 grad: 0.0357 (0.0460) loss: 0.9922 (0.9924) time: 0.1727 data: 0.0943 max mem: 8233 +Train: [2] [1800/6250] eta: 0:12:27 lr: 0.000057 grad: 0.0371 (0.0458) loss: 0.9932 (0.9924) time: 0.1355 data: 0.0426 max mem: 8233 +Train: [2] [1900/6250] eta: 0:12:08 lr: 0.000058 grad: 0.0380 (0.0456) loss: 0.9929 (0.9924) time: 0.1494 data: 0.0751 max mem: 8233 +Train: [2] [2000/6250] eta: 0:11:48 lr: 0.000058 grad: 0.0393 (0.0455) loss: 0.9929 (0.9924) time: 0.1784 data: 0.1016 max mem: 8233 +Train: [2] [2100/6250] eta: 0:11:32 lr: 0.000058 grad: 0.0391 (0.0454) loss: 0.9920 (0.9924) time: 0.1433 data: 0.0620 max mem: 8233 +Train: [2] [2200/6250] eta: 0:11:14 lr: 0.000059 grad: 0.0433 (0.0452) loss: 0.9928 (0.9924) time: 0.1616 data: 0.0760 max mem: 8233 +Train: [2] [2300/6250] eta: 0:10:55 lr: 0.000059 grad: 0.0376 (0.0448) loss: 0.9933 (0.9924) time: 0.1610 data: 0.0773 max mem: 8233 +Train: [2] [2400/6250] eta: 0:10:38 lr: 0.000060 grad: 0.0400 (0.0445) loss: 0.9924 (0.9925) time: 0.1905 data: 0.1061 max mem: 8233 +Train: [2] [2500/6250] eta: 0:10:20 lr: 0.000060 grad: 0.0314 (0.0444) loss: 0.9936 (0.9925) time: 0.1474 data: 0.0593 max mem: 8233 +Train: [2] [2600/6250] eta: 0:10:03 lr: 0.000060 grad: 0.0389 (0.0440) loss: 0.9930 (0.9925) time: 0.1587 data: 0.0773 max mem: 8233 +Train: [2] [2700/6250] eta: 0:09:46 lr: 0.000061 grad: 0.0325 (0.0439) loss: 0.9929 (0.9925) time: 0.1837 data: 0.1057 max mem: 8233 +Train: [2] [2800/6250] eta: 0:09:27 lr: 0.000061 grad: 0.0335 (0.0436) loss: 0.9927 (0.9926) time: 0.1561 data: 0.0665 max mem: 8233 +Train: [2] [2900/6250] eta: 0:09:11 lr: 0.000062 grad: 0.0364 (0.0434) loss: 0.9930 (0.9926) time: 0.1884 data: 0.1167 max mem: 8233 +Train: [2] [3000/6250] eta: 0:08:53 lr: 0.000062 grad: 0.0362 (0.0432) loss: 0.9927 (0.9926) time: 0.1318 data: 0.0529 max mem: 8233 +Train: [2] [3100/6250] eta: 0:08:36 lr: 0.000062 grad: 0.0363 (0.0430) loss: 0.9932 (0.9926) time: 0.1506 data: 0.0757 max mem: 8233 +Train: [2] [3200/6250] eta: 0:08:20 lr: 0.000063 grad: 0.0285 (0.0427) loss: 0.9936 (0.9926) time: 0.1670 data: 0.0880 max mem: 8233 +Train: [2] [3300/6250] eta: 0:08:03 lr: 0.000063 grad: 0.0317 (0.0426) loss: 0.9939 (0.9926) time: 0.1570 data: 0.0721 max mem: 8233 +Train: [2] [3400/6250] eta: 0:07:46 lr: 0.000064 grad: 0.0396 (0.0424) loss: 0.9926 (0.9926) time: 0.1889 data: 0.1009 max mem: 8233 +Train: [2] [3500/6250] eta: 0:07:29 lr: 0.000064 grad: 0.0447 (0.0424) loss: 0.9922 (0.9926) time: 0.1459 data: 0.0540 max mem: 8233 +Train: [2] [3600/6250] eta: 0:07:12 lr: 0.000064 grad: 0.0359 (0.0423) loss: 0.9923 (0.9926) time: 0.1535 data: 0.0714 max mem: 8233 +Train: [2] [3700/6250] eta: 0:06:56 lr: 0.000065 grad: 0.0316 (0.0421) loss: 0.9932 (0.9926) time: 0.1363 data: 0.0504 max mem: 8233 +Train: [2] [3800/6250] eta: 0:06:39 lr: 0.000065 grad: 0.0329 (0.0421) loss: 0.9923 (0.9926) time: 0.1480 data: 0.0614 max mem: 8233 +Train: [2] [3900/6250] eta: 0:06:23 lr: 0.000066 grad: 0.0377 (0.0421) loss: 0.9931 (0.9926) time: 0.1553 data: 0.0754 max mem: 8233 +Train: [2] [4000/6250] eta: 0:06:07 lr: 0.000066 grad: 0.0395 (0.0422) loss: 0.9927 (0.9926) time: 0.1449 data: 0.0615 max mem: 8233 +Train: [2] [4100/6250] eta: 0:05:50 lr: 0.000066 grad: 0.0347 (0.0422) loss: 0.9920 (0.9926) time: 0.1666 data: 0.0837 max mem: 8233 +Train: [2] [4200/6250] eta: 0:05:34 lr: 0.000067 grad: 0.0405 (0.0422) loss: 0.9909 (0.9926) time: 0.1647 data: 0.0846 max mem: 8233 +Train: [2] [4300/6250] eta: 0:05:18 lr: 0.000067 grad: 0.0406 (0.0423) loss: 0.9925 (0.9926) time: 0.2040 data: 0.1231 max mem: 8233 +Train: [2] [4400/6250] eta: 0:05:01 lr: 0.000068 grad: 0.0401 (0.0423) loss: 0.9930 (0.9925) time: 0.1777 data: 0.1032 max mem: 8233 +Train: [2] [4500/6250] eta: 0:04:45 lr: 0.000068 grad: 0.0474 (0.0423) loss: 0.9919 (0.9925) time: 0.1872 data: 0.1039 max mem: 8233 +Train: [2] [4600/6250] eta: 0:04:28 lr: 0.000068 grad: 0.0413 (0.0424) loss: 0.9912 (0.9925) time: 0.1583 data: 0.0723 max mem: 8233 +Train: [2] [4700/6250] eta: 0:04:12 lr: 0.000069 grad: 0.0333 (0.0424) loss: 0.9922 (0.9925) time: 0.1342 data: 0.0451 max mem: 8233 +Train: [2] [4800/6250] eta: 0:03:56 lr: 0.000069 grad: 0.0417 (0.0425) loss: 0.9917 (0.9925) time: 0.1759 data: 0.0916 max mem: 8233 +Train: [2] [4900/6250] eta: 0:03:39 lr: 0.000070 grad: 0.0359 (0.0425) loss: 0.9914 (0.9925) time: 0.1375 data: 0.0521 max mem: 8233 +Train: [2] [5000/6250] eta: 0:03:23 lr: 0.000070 grad: 0.0409 (0.0426) loss: 0.9921 (0.9924) time: 0.1545 data: 0.0745 max mem: 8233 +Train: [2] [5100/6250] eta: 0:03:07 lr: 0.000070 grad: 0.0444 (0.0426) loss: 0.9902 (0.9924) time: 0.1713 data: 0.0873 max mem: 8233 +Train: [2] [5200/6250] eta: 0:02:50 lr: 0.000071 grad: 0.0335 (0.0427) loss: 0.9921 (0.9924) time: 0.1587 data: 0.0798 max mem: 8233 +Train: [2] [5300/6250] eta: 0:02:34 lr: 0.000071 grad: 0.0376 (0.0427) loss: 0.9916 (0.9924) time: 0.1574 data: 0.0837 max mem: 8233 +Train: [2] [5400/6250] eta: 0:02:17 lr: 0.000072 grad: 0.0408 (0.0428) loss: 0.9911 (0.9924) time: 0.1682 data: 0.0762 max mem: 8233 +Train: [2] [5500/6250] eta: 0:02:01 lr: 0.000072 grad: 0.0443 (0.0428) loss: 0.9909 (0.9924) time: 0.1511 data: 0.0702 max mem: 8233 +Train: [2] [5600/6250] eta: 0:01:46 lr: 0.000072 grad: 0.0428 (0.0429) loss: 0.9919 (0.9924) time: 0.1603 data: 0.0665 max mem: 8233 +Train: [2] [5700/6250] eta: 0:01:29 lr: 0.000073 grad: 0.0433 (0.0429) loss: 0.9900 (0.9923) time: 0.1756 data: 0.1086 max mem: 8233 +Train: [2] [5800/6250] eta: 0:01:13 lr: 0.000073 grad: 0.0407 (0.0429) loss: 0.9907 (0.9923) time: 0.1650 data: 0.0838 max mem: 8233 +Train: [2] [5900/6250] eta: 0:00:57 lr: 0.000074 grad: 0.0432 (0.0430) loss: 0.9921 (0.9923) time: 0.1434 data: 0.0577 max mem: 8233 +Train: [2] [6000/6250] eta: 0:00:40 lr: 0.000074 grad: 0.0380 (0.0430) loss: 0.9920 (0.9923) time: 0.1726 data: 0.0711 max mem: 8233 +Train: [2] [6100/6250] eta: 0:00:24 lr: 0.000074 grad: 0.0474 (0.0430) loss: 0.9904 (0.9923) time: 0.2536 data: 0.1920 max mem: 8233 +Train: [2] [6200/6250] eta: 0:00:08 lr: 0.000075 grad: 0.0388 (0.0430) loss: 0.9918 (0.9922) time: 0.1967 data: 0.1154 max mem: 8233 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.0446 (0.0431) loss: 0.9921 (0.9922) time: 0.1908 data: 0.1205 max mem: 8233 +Train: [2] Total time: 0:17:15 (0.1656 s / it) +Averaged stats: lr: 0.000075 grad: 0.0446 (0.0431) loss: 0.9921 (0.9922) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:04:17 loss: 0.9900 (0.9900) time: 4.1541 data: 4.1271 max mem: 8233 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9928 (0.9922) time: 0.1866 data: 0.1650 max mem: 8233 +Eval (hcp-train-subset): [2] Total time: 0:00:15 (0.2535 s / it) +Averaged stats (hcp-train-subset): loss: 0.9928 (0.9922) +Eval (hcp-val): [2] [ 0/62] eta: 0:03:14 loss: 0.9850 (0.9850) time: 3.1381 data: 3.0460 max mem: 8233 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9904 (0.9910) time: 0.0906 data: 0.0694 max mem: 8233 +Eval (hcp-val): [2] Total time: 0:00:15 (0.2475 s / it) +Averaged stats (hcp-val): loss: 0.9904 (0.9910) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 9:45:46 lr: 0.000075 grad: 0.0263 (0.0263) loss: 0.9961 (0.9961) time: 5.6234 data: 5.4245 max mem: 8233 +Train: [3] [ 100/6250] eta: 0:21:02 lr: 0.000075 grad: 0.0455 (0.0471) loss: 0.9909 (0.9922) time: 0.1654 data: 0.0742 max mem: 8233 +Train: [3] [ 200/6250] eta: 0:19:17 lr: 0.000076 grad: 0.0540 (0.0520) loss: 0.9916 (0.9915) time: 0.1860 data: 0.0826 max mem: 8233 +Train: [3] [ 300/6250] eta: 0:18:22 lr: 0.000076 grad: 0.0458 (0.0534) loss: 0.9919 (0.9913) time: 0.1786 data: 0.0751 max mem: 8233 +Train: [3] [ 400/6250] eta: 0:17:25 lr: 0.000077 grad: 0.0498 (0.0518) loss: 0.9908 (0.9913) time: 0.1574 data: 0.0704 max mem: 8233 +Train: [3] [ 500/6250] eta: 0:16:43 lr: 0.000077 grad: 0.0402 (0.0501) loss: 0.9926 (0.9914) time: 0.1482 data: 0.0600 max mem: 8233 +Train: [3] [ 600/6250] eta: 0:16:11 lr: 0.000077 grad: 0.0419 (0.0486) loss: 0.9914 (0.9916) time: 0.1348 data: 0.0305 max mem: 8233 +Train: [3] [ 700/6250] eta: 0:15:42 lr: 0.000078 grad: 0.0424 (0.0479) loss: 0.9918 (0.9916) time: 0.1589 data: 0.0546 max mem: 8233 +Train: [3] [ 800/6250] eta: 0:15:38 lr: 0.000078 grad: 0.0397 (0.0478) loss: 0.9916 (0.9916) time: 0.2617 data: 0.1916 max mem: 8233 +Train: [3] [ 900/6250] eta: 0:15:24 lr: 0.000079 grad: 0.0466 (0.0480) loss: 0.9920 (0.9915) time: 0.2034 data: 0.1315 max mem: 8233 +Train: [3] [1000/6250] eta: 0:15:03 lr: 0.000079 grad: 0.0390 (0.0482) loss: 0.9923 (0.9915) time: 0.1598 data: 0.0742 max mem: 8233 +Train: [3] [1100/6250] eta: 0:14:43 lr: 0.000079 grad: 0.0336 (0.0487) loss: 0.9914 (0.9915) time: 0.1352 data: 0.0371 max mem: 8233 +Train: [3] [1200/6250] eta: 0:14:22 lr: 0.000080 grad: 0.0497 (0.0491) loss: 0.9910 (0.9914) time: 0.1537 data: 0.0745 max mem: 8233 +Train: [3] [1300/6250] eta: 0:14:02 lr: 0.000080 grad: 0.0455 (0.0500) loss: 0.9918 (0.9914) time: 0.1802 data: 0.0951 max mem: 8233 +Train: [3] [1400/6250] eta: 0:13:41 lr: 0.000081 grad: 0.0572 (0.0502) loss: 0.9904 (0.9914) time: 0.1553 data: 0.0705 max mem: 8233 +Train: [3] [1500/6250] eta: 0:13:23 lr: 0.000081 grad: 0.0517 (0.0510) loss: 0.9925 (0.9914) time: 0.1863 data: 0.1098 max mem: 8233 +Train: [3] [1600/6250] eta: 0:13:06 lr: 0.000081 grad: 0.0594 (0.0518) loss: 0.9898 (0.9913) time: 0.1529 data: 0.0621 max mem: 8233 +Train: [3] [1700/6250] eta: 0:12:55 lr: 0.000082 grad: 0.1138 (0.0538) loss: 0.9909 (0.9913) time: 0.3050 data: 0.2267 max mem: 8233 +Train: [3] [1800/6250] eta: 0:12:43 lr: 0.000082 grad: 0.0718 (0.0558) loss: 0.9902 (0.9912) time: 0.2893 data: 0.1844 max mem: 8233 +Train: [3] [1900/6250] eta: 0:12:22 lr: 0.000083 grad: 0.0606 (0.0579) loss: 0.9903 (0.9911) time: 0.1787 data: 0.0985 max mem: 8233 +Train: [3] [2000/6250] eta: 0:12:02 lr: 0.000083 grad: 0.0841 (0.0598) loss: 0.9895 (0.9911) time: 0.1765 data: 0.0966 max mem: 8233 +Train: [3] [2100/6250] eta: 0:11:46 lr: 0.000083 grad: 0.0869 (0.0624) loss: 0.9894 (0.9910) time: 0.1295 data: 0.0487 max mem: 8233 +Train: [3] [2200/6250] eta: 0:11:27 lr: 0.000084 grad: 0.1343 (0.0657) loss: 0.9896 (0.9909) time: 0.1487 data: 0.0753 max mem: 8233 +Train: [3] [2300/6250] eta: 0:11:08 lr: 0.000084 grad: 0.1212 (0.0688) loss: 0.9885 (0.9908) time: 0.1519 data: 0.0724 max mem: 8233 +Train: [3] [2400/6250] eta: 0:10:51 lr: 0.000085 grad: 0.1236 (0.0720) loss: 0.9889 (0.9907) time: 0.1718 data: 0.0817 max mem: 8233 +Train: [3] [2500/6250] eta: 0:10:31 lr: 0.000085 grad: 0.0783 (0.0741) loss: 0.9882 (0.9907) time: 0.1280 data: 0.0332 max mem: 8233 +Train: [3] [2600/6250] eta: 0:10:14 lr: 0.000085 grad: 0.0685 (0.0765) loss: 0.9876 (0.9906) time: 0.1538 data: 0.0761 max mem: 8233 +Train: [3] [2700/6250] eta: 0:09:55 lr: 0.000086 grad: 0.1115 (0.0794) loss: 0.9889 (0.9905) time: 0.1630 data: 0.0872 max mem: 8233 +Train: [3] [2800/6250] eta: 0:09:38 lr: 0.000086 grad: 0.1338 (0.0823) loss: 0.9888 (0.9903) time: 0.1708 data: 0.0785 max mem: 8233 +Train: [3] [2900/6250] eta: 0:09:21 lr: 0.000087 grad: 0.0793 (0.0841) loss: 0.9861 (0.9902) time: 0.1646 data: 0.0834 max mem: 8233 +Train: [3] [3000/6250] eta: 0:09:04 lr: 0.000087 grad: 0.1038 (0.0868) loss: 0.9854 (0.9902) time: 0.1609 data: 0.0808 max mem: 8233 +Train: [3] [3100/6250] eta: 0:08:47 lr: 0.000087 grad: 0.0917 (0.0889) loss: 0.9871 (0.9901) time: 0.1459 data: 0.0584 max mem: 8233 +Train: [3] [3200/6250] eta: 0:08:30 lr: 0.000088 grad: 0.1167 (0.0909) loss: 0.9880 (0.9900) time: 0.1427 data: 0.0527 max mem: 8233 +Train: [3] [3300/6250] eta: 0:08:12 lr: 0.000088 grad: 0.1096 (0.0924) loss: 0.9879 (0.9899) time: 0.1728 data: 0.1000 max mem: 8233 +Train: [3] [3400/6250] eta: 0:07:55 lr: 0.000089 grad: 0.1263 (0.0942) loss: 0.9864 (0.9898) time: 0.1652 data: 0.0776 max mem: 8233 +Train: [3] [3500/6250] eta: 0:07:38 lr: 0.000089 grad: 0.1387 (0.0958) loss: 0.9875 (0.9897) time: 0.1158 data: 0.0355 max mem: 8233 +Train: [3] [3600/6250] eta: 0:07:21 lr: 0.000089 grad: 0.0868 (0.0971) loss: 0.9852 (0.9896) time: 0.1756 data: 0.0884 max mem: 8233 +Train: [3] [3700/6250] eta: 0:07:03 lr: 0.000090 grad: 0.0862 (0.0987) loss: 0.9863 (0.9895) time: 0.1701 data: 0.0942 max mem: 8233 +Train: [3] [3800/6250] eta: 0:06:46 lr: 0.000090 grad: 0.1225 (0.1007) loss: 0.9857 (0.9894) time: 0.1561 data: 0.0808 max mem: 8233 +Train: [3] [3900/6250] eta: 0:06:29 lr: 0.000091 grad: 0.1099 (0.1020) loss: 0.9869 (0.9893) time: 0.1634 data: 0.0788 max mem: 8233 +Train: [3] [4000/6250] eta: 0:06:14 lr: 0.000091 grad: 0.1697 (0.1037) loss: 0.9866 (0.9893) time: 0.2792 data: 0.1469 max mem: 8233 +Train: [3] [4100/6250] eta: 0:05:56 lr: 0.000091 grad: 0.1014 (0.1049) loss: 0.9839 (0.9892) time: 0.1535 data: 0.0800 max mem: 8233 +Train: [3] [4200/6250] eta: 0:05:39 lr: 0.000092 grad: 0.1428 (0.1065) loss: 0.9879 (0.9891) time: 0.1562 data: 0.0662 max mem: 8233 +Train: [3] [4300/6250] eta: 0:05:23 lr: 0.000092 grad: 0.0982 (0.1076) loss: 0.9850 (0.9890) time: 0.1700 data: 0.0823 max mem: 8233 +Train: [3] [4400/6250] eta: 0:05:05 lr: 0.000093 grad: 0.1452 (0.1089) loss: 0.9853 (0.9889) time: 0.1537 data: 0.0774 max mem: 8233 +Train: [3] [4500/6250] eta: 0:04:49 lr: 0.000093 grad: 0.0942 (0.1098) loss: 0.9848 (0.9888) time: 0.1573 data: 0.0802 max mem: 8233 +Train: [3] [4600/6250] eta: 0:04:32 lr: 0.000093 grad: 0.0903 (0.1109) loss: 0.9832 (0.9888) time: 0.1400 data: 0.0562 max mem: 8233 +Train: [3] [4700/6250] eta: 0:04:15 lr: 0.000094 grad: 0.1492 (0.1116) loss: 0.9842 (0.9887) time: 0.1705 data: 0.0874 max mem: 8233 +Train: [3] [4800/6250] eta: 0:03:59 lr: 0.000094 grad: 0.1338 (0.1123) loss: 0.9870 (0.9886) time: 0.1643 data: 0.0757 max mem: 8233 +Train: [3] [4900/6250] eta: 0:03:43 lr: 0.000095 grad: 0.1596 (0.1132) loss: 0.9836 (0.9885) time: 0.2503 data: 0.1487 max mem: 8233 +Train: [3] [5000/6250] eta: 0:03:26 lr: 0.000095 grad: 0.1724 (0.1142) loss: 0.9855 (0.9884) time: 0.1362 data: 0.0580 max mem: 8233 +Train: [3] [5100/6250] eta: 0:03:10 lr: 0.000095 grad: 0.0975 (0.1150) loss: 0.9857 (0.9884) time: 0.1619 data: 0.0795 max mem: 8233 +Train: [3] [5200/6250] eta: 0:02:53 lr: 0.000096 grad: 0.1245 (0.1156) loss: 0.9843 (0.9883) time: 0.1598 data: 0.0798 max mem: 8233 +Train: [3] [5300/6250] eta: 0:02:36 lr: 0.000096 grad: 0.0817 (0.1157) loss: 0.9849 (0.9882) time: 0.1598 data: 0.0742 max mem: 8233 +Train: [3] [5400/6250] eta: 0:02:20 lr: 0.000097 grad: 0.0995 (0.1162) loss: 0.9846 (0.9882) time: 0.1723 data: 0.0908 max mem: 8233 +Train: [3] [5500/6250] eta: 0:02:03 lr: 0.000097 grad: 0.1102 (0.1167) loss: 0.9836 (0.9881) time: 0.1796 data: 0.1011 max mem: 8233 +Train: [3] [5600/6250] eta: 0:01:47 lr: 0.000097 grad: 0.2297 (0.1176) loss: 0.9854 (0.9880) time: 0.1823 data: 0.0912 max mem: 8233 +Train: [3] [5700/6250] eta: 0:01:30 lr: 0.000098 grad: 0.0998 (0.1185) loss: 0.9852 (0.9879) time: 0.1706 data: 0.0864 max mem: 8233 +Train: [3] [5800/6250] eta: 0:01:14 lr: 0.000098 grad: 0.1134 (0.1187) loss: 0.9851 (0.9879) time: 0.1687 data: 0.0829 max mem: 8233 +Train: [3] [5900/6250] eta: 0:00:57 lr: 0.000099 grad: 0.1443 (0.1190) loss: 0.9833 (0.9878) time: 0.1623 data: 0.0765 max mem: 8233 +Train: [3] [6000/6250] eta: 0:00:41 lr: 0.000099 grad: 0.1627 (0.1198) loss: 0.9850 (0.9878) time: 0.1772 data: 0.0910 max mem: 8233 +Train: [3] [6100/6250] eta: 0:00:24 lr: 0.000099 grad: 0.0996 (0.1204) loss: 0.9845 (0.9877) time: 0.1701 data: 0.0982 max mem: 8233 +Train: [3] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.1035 (0.1210) loss: 0.9850 (0.9877) time: 0.1990 data: 0.1260 max mem: 8233 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1335 (0.1210) loss: 0.9853 (0.9877) time: 0.1807 data: 0.1043 max mem: 8233 +Train: [3] Total time: 0:17:18 (0.1661 s / it) +Averaged stats: lr: 0.000100 grad: 0.1335 (0.1210) loss: 0.9853 (0.9877) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:03:17 loss: 0.9847 (0.9847) time: 3.1879 data: 3.1058 max mem: 8233 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9855 (0.9853) time: 0.1185 data: 0.0975 max mem: 8233 +Eval (hcp-train-subset): [3] Total time: 0:00:14 (0.2307 s / it) +Averaged stats (hcp-train-subset): loss: 0.9855 (0.9853) +Eval (hcp-val): [3] [ 0/62] eta: 0:03:47 loss: 0.9767 (0.9767) time: 3.6721 data: 3.6125 max mem: 8233 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9816 (0.9830) time: 0.1976 data: 0.1757 max mem: 8233 +Eval (hcp-val): [3] Total time: 0:00:14 (0.2360 s / it) +Averaged stats (hcp-val): loss: 0.9816 (0.9830) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 7:53:27 lr: 0.000100 grad: 0.1571 (0.1571) loss: 0.9743 (0.9743) time: 4.5452 data: 4.1902 max mem: 8233 +Train: [4] [ 100/6250] eta: 0:22:20 lr: 0.000100 grad: 0.1135 (0.1730) loss: 0.9855 (0.9856) time: 0.1675 data: 0.0809 max mem: 8233 +Train: [4] [ 200/6250] eta: 0:19:10 lr: 0.000101 grad: 0.1132 (0.1527) loss: 0.9876 (0.9859) time: 0.1683 data: 0.0786 max mem: 8233 +Train: [4] [ 300/6250] eta: 0:18:34 lr: 0.000101 grad: 0.1300 (0.1476) loss: 0.9855 (0.9856) time: 0.2243 data: 0.1241 max mem: 8233 +Train: [4] [ 400/6250] eta: 0:17:43 lr: 0.000102 grad: 0.0920 (0.1488) loss: 0.9806 (0.9851) time: 0.1517 data: 0.0437 max mem: 8233 +Train: [4] [ 500/6250] eta: 0:16:57 lr: 0.000102 grad: 0.1396 (0.1488) loss: 0.9852 (0.9850) time: 0.1786 data: 0.0716 max mem: 8233 +Train: [4] [ 600/6250] eta: 0:16:18 lr: 0.000102 grad: 0.1079 (0.1446) loss: 0.9822 (0.9847) time: 0.1466 data: 0.0450 max mem: 8233 +Train: [4] [ 700/6250] eta: 0:15:56 lr: 0.000103 grad: 0.1828 (0.1454) loss: 0.9827 (0.9845) time: 0.1600 data: 0.0753 max mem: 8233 +Train: [4] [ 800/6250] eta: 0:15:40 lr: 0.000103 grad: 0.0821 (0.1433) loss: 0.9834 (0.9845) time: 0.1890 data: 0.1078 max mem: 8233 +Train: [4] [ 900/6250] eta: 0:15:55 lr: 0.000104 grad: 0.1053 (0.1423) loss: 0.9838 (0.9845) time: 0.2260 data: 0.1389 max mem: 8233 +Train: [4] [1000/6250] eta: 0:15:48 lr: 0.000104 grad: 0.1004 (0.1417) loss: 0.9854 (0.9845) time: 0.2338 data: 0.1668 max mem: 8233 +Train: [4] [1100/6250] eta: 0:15:25 lr: 0.000104 grad: 0.1110 (0.1399) loss: 0.9857 (0.9845) time: 0.2000 data: 0.1177 max mem: 8233 +Train: [4] [1200/6250] eta: 0:14:54 lr: 0.000105 grad: 0.1374 (0.1420) loss: 0.9851 (0.9845) time: 0.1462 data: 0.0622 max mem: 8233 +Train: [4] [1300/6250] eta: 0:14:30 lr: 0.000105 grad: 0.1227 (0.1413) loss: 0.9844 (0.9845) time: 0.1502 data: 0.0639 max mem: 8233 +Train: [4] [1400/6250] eta: 0:14:08 lr: 0.000106 grad: 0.1007 (0.1399) loss: 0.9845 (0.9845) time: 0.1749 data: 0.0985 max mem: 8233 +Train: [4] [1500/6250] eta: 0:13:43 lr: 0.000106 grad: 0.0736 (0.1391) loss: 0.9853 (0.9844) time: 0.1621 data: 0.0853 max mem: 8233 +Train: [4] [1600/6250] eta: 0:13:20 lr: 0.000106 grad: 0.1112 (0.1392) loss: 0.9841 (0.9844) time: 0.1524 data: 0.0696 max mem: 8233 +Train: [4] [1700/6250] eta: 0:13:00 lr: 0.000107 grad: 0.1583 (0.1393) loss: 0.9857 (0.9844) time: 0.1719 data: 0.0843 max mem: 8233 +Train: [4] [1800/6250] eta: 0:12:44 lr: 0.000107 grad: 0.1345 (0.1394) loss: 0.9837 (0.9844) time: 0.1630 data: 0.0500 max mem: 8233 +Train: [4] [1900/6250] eta: 0:12:25 lr: 0.000108 grad: 0.1342 (0.1394) loss: 0.9822 (0.9844) time: 0.1198 data: 0.0395 max mem: 8233 +Train: [4] [2000/6250] eta: 0:12:11 lr: 0.000108 grad: 0.1099 (0.1398) loss: 0.9842 (0.9844) time: 0.1783 data: 0.1064 max mem: 8233 +Train: [4] [2100/6250] eta: 0:11:53 lr: 0.000108 grad: 0.0863 (0.1387) loss: 0.9839 (0.9843) time: 0.1922 data: 0.0999 max mem: 8233 +Train: [4] [2200/6250] eta: 0:11:37 lr: 0.000109 grad: 0.2096 (0.1388) loss: 0.9865 (0.9843) time: 0.1151 data: 0.0222 max mem: 8233 +Train: [4] [2300/6250] eta: 0:11:20 lr: 0.000109 grad: 0.1998 (0.1398) loss: 0.9843 (0.9843) time: 0.1508 data: 0.0667 max mem: 8233 +Train: [4] [2400/6250] eta: 0:11:04 lr: 0.000110 grad: 0.1139 (0.1401) loss: 0.9832 (0.9843) time: 0.2628 data: 0.1790 max mem: 8233 +Train: [4] [2500/6250] eta: 0:10:45 lr: 0.000110 grad: 0.1185 (0.1405) loss: 0.9836 (0.9843) time: 0.1836 data: 0.0979 max mem: 8233 +Train: [4] [2600/6250] eta: 0:10:28 lr: 0.000110 grad: 0.1103 (0.1396) loss: 0.9834 (0.9842) time: 0.1722 data: 0.0923 max mem: 8233 +Train: [4] [2700/6250] eta: 0:10:13 lr: 0.000111 grad: 0.0853 (0.1403) loss: 0.9827 (0.9842) time: 0.1907 data: 0.1089 max mem: 8233 +Train: [4] [2800/6250] eta: 0:09:53 lr: 0.000111 grad: 0.0797 (0.1404) loss: 0.9832 (0.9842) time: 0.1662 data: 0.0765 max mem: 8233 +Train: [4] [2900/6250] eta: 0:09:36 lr: 0.000112 grad: 0.1748 (0.1402) loss: 0.9847 (0.9842) time: 0.1611 data: 0.0647 max mem: 8233 +Train: [4] [3000/6250] eta: 0:09:16 lr: 0.000112 grad: 0.0941 (0.1400) loss: 0.9835 (0.9842) time: 0.1532 data: 0.0769 max mem: 8233 +Train: [4] [3100/6250] eta: 0:08:58 lr: 0.000112 grad: 0.1164 (0.1397) loss: 0.9846 (0.9842) time: 0.1594 data: 0.0893 max mem: 8233 +Train: [4] [3200/6250] eta: 0:08:40 lr: 0.000113 grad: 0.1359 (0.1393) loss: 0.9846 (0.9842) time: 0.1735 data: 0.0843 max mem: 8233 +Train: [4] [3300/6250] eta: 0:08:22 lr: 0.000113 grad: 0.1155 (0.1391) loss: 0.9820 (0.9841) time: 0.1252 data: 0.0463 max mem: 8233 +Train: [4] [3400/6250] eta: 0:08:04 lr: 0.000114 grad: 0.1343 (0.1393) loss: 0.9820 (0.9841) time: 0.1419 data: 0.0472 max mem: 8233 +Train: [4] [3500/6250] eta: 0:07:46 lr: 0.000114 grad: 0.0860 (0.1388) loss: 0.9828 (0.9841) time: 0.1445 data: 0.0655 max mem: 8233 +Train: [4] [3600/6250] eta: 0:07:28 lr: 0.000114 grad: 0.1571 (0.1390) loss: 0.9835 (0.9840) time: 0.1571 data: 0.0800 max mem: 8233 +Train: [4] [3700/6250] eta: 0:07:11 lr: 0.000115 grad: 0.1362 (0.1391) loss: 0.9842 (0.9839) time: 0.1499 data: 0.0657 max mem: 8233 +Train: [4] [3800/6250] eta: 0:06:54 lr: 0.000115 grad: 0.0897 (0.1392) loss: 0.9825 (0.9839) time: 0.1563 data: 0.0809 max mem: 8233 +Train: [4] [3900/6250] eta: 0:06:37 lr: 0.000116 grad: 0.1695 (0.1396) loss: 0.9814 (0.9839) time: 0.1850 data: 0.1083 max mem: 8233 +Train: [4] [4000/6250] eta: 0:06:19 lr: 0.000116 grad: 0.0862 (0.1398) loss: 0.9821 (0.9839) time: 0.1555 data: 0.0671 max mem: 8233 +Train: [4] [4100/6250] eta: 0:06:02 lr: 0.000116 grad: 0.1056 (0.1397) loss: 0.9830 (0.9838) time: 0.1247 data: 0.0304 max mem: 8233 +Train: [4] [4200/6250] eta: 0:05:45 lr: 0.000117 grad: 0.1255 (0.1403) loss: 0.9827 (0.9838) time: 0.1405 data: 0.0612 max mem: 8233 +Train: [4] [4300/6250] eta: 0:05:28 lr: 0.000117 grad: 0.0906 (0.1403) loss: 0.9835 (0.9838) time: 0.1494 data: 0.0724 max mem: 8233 +Train: [4] [4400/6250] eta: 0:05:10 lr: 0.000118 grad: 0.1189 (0.1404) loss: 0.9849 (0.9838) time: 0.1480 data: 0.0612 max mem: 8233 +Train: [4] [4500/6250] eta: 0:04:53 lr: 0.000118 grad: 0.1057 (0.1407) loss: 0.9827 (0.9838) time: 0.1974 data: 0.1242 max mem: 8233 +Train: [4] [4600/6250] eta: 0:04:36 lr: 0.000118 grad: 0.1090 (0.1408) loss: 0.9822 (0.9837) time: 0.1399 data: 0.0609 max mem: 8233 +Train: [4] [4700/6250] eta: 0:04:19 lr: 0.000119 grad: 0.1397 (0.1405) loss: 0.9823 (0.9837) time: 0.1545 data: 0.0681 max mem: 8233 +Train: [4] [4800/6250] eta: 0:04:03 lr: 0.000119 grad: 0.1821 (0.1411) loss: 0.9839 (0.9837) time: 0.1594 data: 0.0896 max mem: 8233 +Train: [4] [4900/6250] eta: 0:03:46 lr: 0.000120 grad: 0.1249 (0.1412) loss: 0.9823 (0.9837) time: 0.1975 data: 0.1232 max mem: 8233 +Train: [4] [5000/6250] eta: 0:03:29 lr: 0.000120 grad: 0.1390 (0.1413) loss: 0.9825 (0.9836) time: 0.1462 data: 0.0456 max mem: 8233 +Train: [4] [5100/6250] eta: 0:03:12 lr: 0.000120 grad: 0.1150 (0.1414) loss: 0.9814 (0.9836) time: 0.1611 data: 0.0741 max mem: 8233 +Train: [4] [5200/6250] eta: 0:02:55 lr: 0.000121 grad: 0.1094 (0.1413) loss: 0.9812 (0.9836) time: 0.1423 data: 0.0655 max mem: 8233 +Train: [4] [5300/6250] eta: 0:02:38 lr: 0.000121 grad: 0.1537 (0.1416) loss: 0.9835 (0.9835) time: 0.1662 data: 0.0866 max mem: 8233 +Train: [4] [5400/6250] eta: 0:02:22 lr: 0.000122 grad: 0.1370 (0.1419) loss: 0.9828 (0.9835) time: 0.1630 data: 0.0885 max mem: 8233 +Train: [4] [5500/6250] eta: 0:02:05 lr: 0.000122 grad: 0.1303 (0.1419) loss: 0.9815 (0.9835) time: 0.1287 data: 0.0296 max mem: 8233 +Train: [4] [5600/6250] eta: 0:01:48 lr: 0.000122 grad: 0.1254 (0.1419) loss: 0.9834 (0.9835) time: 0.1773 data: 0.1092 max mem: 8233 +Train: [4] [5700/6250] eta: 0:01:31 lr: 0.000123 grad: 0.1548 (0.1421) loss: 0.9832 (0.9834) time: 0.1644 data: 0.0846 max mem: 8233 +Train: [4] [5800/6250] eta: 0:01:15 lr: 0.000123 grad: 0.1535 (0.1425) loss: 0.9816 (0.9834) time: 0.1700 data: 0.0966 max mem: 8233 +Train: [4] [5900/6250] eta: 0:00:58 lr: 0.000124 grad: 0.1252 (0.1429) loss: 0.9811 (0.9834) time: 0.1386 data: 0.0548 max mem: 8233 +Train: [4] [6000/6250] eta: 0:00:41 lr: 0.000124 grad: 0.1393 (0.1430) loss: 0.9789 (0.9833) time: 0.1927 data: 0.1050 max mem: 8233 +Train: [4] [6100/6250] eta: 0:00:25 lr: 0.000124 grad: 0.1208 (0.1433) loss: 0.9811 (0.9833) time: 0.1616 data: 0.0794 max mem: 8233 +Train: [4] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1236 (0.1435) loss: 0.9796 (0.9833) time: 0.1701 data: 0.0910 max mem: 8233 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1238 (0.1437) loss: 0.9811 (0.9832) time: 0.1473 data: 0.0681 max mem: 8233 +Train: [4] Total time: 0:17:34 (0.1687 s / it) +Averaged stats: lr: 0.000125 grad: 0.1238 (0.1437) loss: 0.9811 (0.9832) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:04:15 loss: 0.9825 (0.9825) time: 4.1201 data: 4.0425 max mem: 8233 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9835 (0.9826) time: 0.1083 data: 0.0876 max mem: 8233 +Eval (hcp-train-subset): [4] Total time: 0:00:15 (0.2532 s / it) +Averaged stats (hcp-train-subset): loss: 0.9835 (0.9826) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [4] [ 0/62] eta: 0:05:51 loss: 0.9758 (0.9758) time: 5.6661 data: 5.6374 max mem: 8233 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9806 (0.9803) time: 0.1327 data: 0.1119 max mem: 8233 +Eval (hcp-val): [4] Total time: 0:00:14 (0.2262 s / it) +Averaged stats (hcp-val): loss: 0.9806 (0.9803) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 9:40:28 lr: 0.000125 grad: 0.1995 (0.1995) loss: 0.9718 (0.9718) time: 5.5725 data: 5.4196 max mem: 8233 +Train: [5] [ 100/6250] eta: 0:22:31 lr: 0.000125 grad: 0.1148 (0.1597) loss: 0.9840 (0.9827) time: 0.1333 data: 0.0435 max mem: 8233 +Train: [5] [ 200/6250] eta: 0:19:16 lr: 0.000125 grad: 0.1043 (0.1573) loss: 0.9823 (0.9815) time: 0.1631 data: 0.0775 max mem: 8233 +Train: [5] [ 300/6250] eta: 0:18:11 lr: 0.000125 grad: 0.1055 (0.1502) loss: 0.9820 (0.9814) time: 0.1857 data: 0.0986 max mem: 8233 +Train: [5] [ 400/6250] eta: 0:17:20 lr: 0.000125 grad: 0.1604 (0.1545) loss: 0.9806 (0.9811) time: 0.1479 data: 0.0550 max mem: 8233 +Train: [5] [ 500/6250] eta: 0:16:42 lr: 0.000125 grad: 0.1333 (0.1549) loss: 0.9806 (0.9807) time: 0.1411 data: 0.0408 max mem: 8233 +Train: [5] [ 600/6250] eta: 0:16:13 lr: 0.000125 grad: 0.1720 (0.1565) loss: 0.9793 (0.9804) time: 0.1693 data: 0.0800 max mem: 8233 +Train: [5] [ 700/6250] eta: 0:15:41 lr: 0.000125 grad: 0.1503 (0.1553) loss: 0.9781 (0.9801) time: 0.1414 data: 0.0410 max mem: 8233 +Train: [5] [ 800/6250] eta: 0:15:17 lr: 0.000125 grad: 0.1799 (0.1580) loss: 0.9793 (0.9799) time: 0.1653 data: 0.0647 max mem: 8233 +Train: [5] [ 900/6250] eta: 0:14:59 lr: 0.000125 grad: 0.1282 (0.1574) loss: 0.9774 (0.9799) time: 0.1660 data: 0.0744 max mem: 8233 +Train: [5] [1000/6250] eta: 0:14:40 lr: 0.000125 grad: 0.1295 (0.1573) loss: 0.9823 (0.9799) time: 0.1676 data: 0.0827 max mem: 8233 +Train: [5] [1100/6250] eta: 0:14:20 lr: 0.000125 grad: 0.1699 (0.1579) loss: 0.9810 (0.9798) time: 0.1511 data: 0.0733 max mem: 8233 +Train: [5] [1200/6250] eta: 0:14:05 lr: 0.000125 grad: 0.1393 (0.1570) loss: 0.9790 (0.9798) time: 0.1580 data: 0.0819 max mem: 8233 +Train: [5] [1300/6250] eta: 0:13:48 lr: 0.000125 grad: 0.1488 (0.1567) loss: 0.9778 (0.9796) time: 0.1750 data: 0.1013 max mem: 8233 +Train: [5] [1400/6250] eta: 0:13:38 lr: 0.000125 grad: 0.1303 (0.1565) loss: 0.9758 (0.9794) time: 0.2053 data: 0.1362 max mem: 8233 +Train: [5] [1500/6250] eta: 0:13:25 lr: 0.000125 grad: 0.1421 (0.1568) loss: 0.9780 (0.9793) time: 0.1594 data: 0.0698 max mem: 8233 +Train: [5] [1600/6250] eta: 0:13:10 lr: 0.000125 grad: 0.1841 (0.1579) loss: 0.9796 (0.9792) time: 0.1746 data: 0.1049 max mem: 8233 +Train: [5] [1700/6250] eta: 0:12:55 lr: 0.000125 grad: 0.1257 (0.1581) loss: 0.9782 (0.9791) time: 0.1620 data: 0.0896 max mem: 8233 +Train: [5] [1800/6250] eta: 0:12:42 lr: 0.000125 grad: 0.1334 (0.1575) loss: 0.9786 (0.9791) time: 0.1667 data: 0.0906 max mem: 8233 +Train: [5] [1900/6250] eta: 0:12:22 lr: 0.000125 grad: 0.1236 (0.1577) loss: 0.9806 (0.9791) time: 0.1846 data: 0.1131 max mem: 8233 +Train: [5] [2000/6250] eta: 0:12:01 lr: 0.000125 grad: 0.1051 (0.1571) loss: 0.9785 (0.9790) time: 0.1685 data: 0.0893 max mem: 8233 +Train: [5] [2100/6250] eta: 0:11:42 lr: 0.000125 grad: 0.1088 (0.1575) loss: 0.9792 (0.9790) time: 0.1799 data: 0.1081 max mem: 8233 +Train: [5] [2200/6250] eta: 0:11:23 lr: 0.000125 grad: 0.1638 (0.1584) loss: 0.9779 (0.9790) time: 0.1418 data: 0.0640 max mem: 8233 +Train: [5] [2300/6250] eta: 0:11:05 lr: 0.000125 grad: 0.1689 (0.1581) loss: 0.9776 (0.9790) time: 0.1434 data: 0.0668 max mem: 8233 +Train: [5] [2400/6250] eta: 0:10:48 lr: 0.000125 grad: 0.1533 (0.1577) loss: 0.9774 (0.9789) time: 0.1742 data: 0.0915 max mem: 8233 +Train: [5] [2500/6250] eta: 0:10:31 lr: 0.000125 grad: 0.1284 (0.1575) loss: 0.9786 (0.9788) time: 0.1806 data: 0.1116 max mem: 8233 +Train: [5] [2600/6250] eta: 0:10:13 lr: 0.000125 grad: 0.1110 (0.1577) loss: 0.9768 (0.9787) time: 0.1447 data: 0.0645 max mem: 8233 +Train: [5] [2700/6250] eta: 0:09:56 lr: 0.000125 grad: 0.1478 (0.1577) loss: 0.9762 (0.9787) time: 0.1867 data: 0.1067 max mem: 8233 +Train: [5] [2800/6250] eta: 0:09:40 lr: 0.000125 grad: 0.1490 (0.1574) loss: 0.9775 (0.9786) time: 0.1927 data: 0.1085 max mem: 8233 +Train: [5] [2900/6250] eta: 0:09:24 lr: 0.000125 grad: 0.1573 (0.1573) loss: 0.9800 (0.9786) time: 0.1554 data: 0.0543 max mem: 8233 +Train: [5] [3000/6250] eta: 0:09:07 lr: 0.000125 grad: 0.1534 (0.1579) loss: 0.9791 (0.9785) time: 0.1520 data: 0.0728 max mem: 8233 +Train: [5] [3100/6250] eta: 0:08:50 lr: 0.000125 grad: 0.1493 (0.1575) loss: 0.9785 (0.9785) time: 0.1893 data: 0.1130 max mem: 8233 +Train: [5] [3200/6250] eta: 0:08:33 lr: 0.000125 grad: 0.1327 (0.1580) loss: 0.9781 (0.9784) time: 0.1451 data: 0.0644 max mem: 8233 +Train: [5] [3300/6250] eta: 0:08:16 lr: 0.000125 grad: 0.1415 (0.1585) loss: 0.9767 (0.9784) time: 0.1962 data: 0.1251 max mem: 8233 +Train: [5] [3400/6250] eta: 0:07:58 lr: 0.000125 grad: 0.1406 (0.1586) loss: 0.9753 (0.9784) time: 0.1373 data: 0.0537 max mem: 8233 +Train: [5] [3500/6250] eta: 0:07:40 lr: 0.000125 grad: 0.1352 (0.1584) loss: 0.9765 (0.9783) time: 0.1470 data: 0.0646 max mem: 8233 +Train: [5] [3600/6250] eta: 0:07:24 lr: 0.000125 grad: 0.1179 (0.1579) loss: 0.9760 (0.9782) time: 0.1634 data: 0.0773 max mem: 8233 +Train: [5] [3700/6250] eta: 0:07:07 lr: 0.000125 grad: 0.1265 (0.1577) loss: 0.9772 (0.9782) time: 0.1662 data: 0.0970 max mem: 8233 +Train: [5] [3800/6250] eta: 0:06:49 lr: 0.000125 grad: 0.1113 (0.1581) loss: 0.9776 (0.9781) time: 0.1619 data: 0.0792 max mem: 8233 +Train: [5] [3900/6250] eta: 0:06:32 lr: 0.000125 grad: 0.1204 (0.1579) loss: 0.9759 (0.9780) time: 0.1638 data: 0.0903 max mem: 8233 +Train: [5] [4000/6250] eta: 0:06:15 lr: 0.000125 grad: 0.1166 (0.1579) loss: 0.9777 (0.9780) time: 0.1611 data: 0.0816 max mem: 8233 +Train: [5] [4100/6250] eta: 0:05:57 lr: 0.000125 grad: 0.2050 (0.1580) loss: 0.9764 (0.9779) time: 0.1501 data: 0.0704 max mem: 8233 +Train: [5] [4200/6250] eta: 0:05:40 lr: 0.000125 grad: 0.1819 (0.1584) loss: 0.9751 (0.9779) time: 0.1798 data: 0.0927 max mem: 8233 +Train: [5] [4300/6250] eta: 0:05:23 lr: 0.000125 grad: 0.1716 (0.1587) loss: 0.9757 (0.9778) time: 0.1487 data: 0.0633 max mem: 8233 +Train: [5] [4400/6250] eta: 0:05:06 lr: 0.000125 grad: 0.1774 (0.1589) loss: 0.9752 (0.9778) time: 0.1527 data: 0.0655 max mem: 8233 +Train: [5] [4500/6250] eta: 0:04:50 lr: 0.000125 grad: 0.1405 (0.1589) loss: 0.9735 (0.9777) time: 0.1532 data: 0.0644 max mem: 8233 +Train: [5] [4600/6250] eta: 0:04:33 lr: 0.000125 grad: 0.1529 (0.1593) loss: 0.9747 (0.9777) time: 0.1579 data: 0.0679 max mem: 8233 +Train: [5] [4700/6250] eta: 0:04:16 lr: 0.000125 grad: 0.1454 (0.1594) loss: 0.9750 (0.9776) time: 0.1189 data: 0.0257 max mem: 8233 +Train: [5] [4800/6250] eta: 0:03:59 lr: 0.000125 grad: 0.1449 (0.1591) loss: 0.9765 (0.9776) time: 0.1498 data: 0.0690 max mem: 8233 +Train: [5] [4900/6250] eta: 0:03:43 lr: 0.000125 grad: 0.1582 (0.1594) loss: 0.9756 (0.9775) time: 0.1567 data: 0.0731 max mem: 8233 +Train: [5] [5000/6250] eta: 0:03:26 lr: 0.000125 grad: 0.1186 (0.1590) loss: 0.9799 (0.9775) time: 0.1684 data: 0.0943 max mem: 8233 +Train: [5] [5100/6250] eta: 0:03:10 lr: 0.000125 grad: 0.1506 (0.1589) loss: 0.9750 (0.9775) time: 0.1665 data: 0.0858 max mem: 8233 +Train: [5] [5200/6250] eta: 0:02:53 lr: 0.000125 grad: 0.1300 (0.1586) loss: 0.9737 (0.9774) time: 0.1754 data: 0.1027 max mem: 8233 +Train: [5] [5300/6250] eta: 0:02:36 lr: 0.000125 grad: 0.1400 (0.1585) loss: 0.9774 (0.9774) time: 0.1339 data: 0.0588 max mem: 8233 +Train: [5] [5400/6250] eta: 0:02:20 lr: 0.000125 grad: 0.1386 (0.1585) loss: 0.9758 (0.9774) time: 0.1417 data: 0.0676 max mem: 8233 +Train: [5] [5500/6250] eta: 0:02:03 lr: 0.000125 grad: 0.1575 (0.1587) loss: 0.9744 (0.9773) time: 0.1829 data: 0.0986 max mem: 8233 +Train: [5] [5600/6250] eta: 0:01:47 lr: 0.000125 grad: 0.1782 (0.1591) loss: 0.9727 (0.9772) time: 0.1525 data: 0.0790 max mem: 8233 +Train: [5] [5700/6250] eta: 0:01:30 lr: 0.000125 grad: 0.1652 (0.1596) loss: 0.9743 (0.9772) time: 0.1568 data: 0.0763 max mem: 8233 +Train: [5] [5800/6250] eta: 0:01:14 lr: 0.000125 grad: 0.1550 (0.1596) loss: 0.9750 (0.9771) time: 0.1848 data: 0.1112 max mem: 8233 +Train: [5] [5900/6250] eta: 0:00:57 lr: 0.000125 grad: 0.1691 (0.1598) loss: 0.9719 (0.9771) time: 0.1696 data: 0.0892 max mem: 8233 +Train: [5] [6000/6250] eta: 0:00:41 lr: 0.000125 grad: 0.1427 (0.1601) loss: 0.9722 (0.9770) time: 0.1482 data: 0.0686 max mem: 8233 +Train: [5] [6100/6250] eta: 0:00:24 lr: 0.000125 grad: 0.1826 (0.1602) loss: 0.9716 (0.9769) time: 0.1790 data: 0.0939 max mem: 8233 +Train: [5] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1524 (0.1603) loss: 0.9742 (0.9769) time: 0.1954 data: 0.1322 max mem: 8233 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1822 (0.1604) loss: 0.9756 (0.9769) time: 0.1366 data: 0.0655 max mem: 8233 +Train: [5] Total time: 0:17:17 (0.1661 s / it) +Averaged stats: lr: 0.000125 grad: 0.1822 (0.1604) loss: 0.9756 (0.9769) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:04:20 loss: 0.9762 (0.9762) time: 4.1949 data: 4.1462 max mem: 8233 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.9781 (0.9766) time: 0.1193 data: 0.0991 max mem: 8233 +Eval (hcp-train-subset): [5] Total time: 0:00:17 (0.2819 s / it) +Averaged stats (hcp-train-subset): loss: 0.9781 (0.9766) +Eval (hcp-val): [5] [ 0/62] eta: 0:05:03 loss: 0.9708 (0.9708) time: 4.8988 data: 4.8461 max mem: 8233 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.9736 (0.9740) time: 0.1276 data: 0.1070 max mem: 8233 +Eval (hcp-val): [5] Total time: 0:00:13 (0.2258 s / it) +Averaged stats (hcp-val): loss: 0.9736 (0.9740) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 11:48:39 lr: 0.000125 grad: 0.1546 (0.1546) loss: 0.9786 (0.9786) time: 6.8030 data: 6.7105 max mem: 8233 +Train: [6] [ 100/6250] eta: 0:23:07 lr: 0.000125 grad: 0.1516 (0.1782) loss: 0.9754 (0.9748) time: 0.1799 data: 0.0861 max mem: 8233 +Train: [6] [ 200/6250] eta: 0:19:55 lr: 0.000125 grad: 0.1565 (0.1882) loss: 0.9747 (0.9741) time: 0.1740 data: 0.0914 max mem: 8233 +Train: [6] [ 300/6250] eta: 0:18:17 lr: 0.000125 grad: 0.1490 (0.1806) loss: 0.9775 (0.9747) time: 0.1570 data: 0.0660 max mem: 8233 +Train: [6] [ 400/6250] eta: 0:17:34 lr: 0.000125 grad: 0.1763 (0.1775) loss: 0.9768 (0.9747) time: 0.1633 data: 0.0755 max mem: 8233 +Train: [6] [ 500/6250] eta: 0:16:54 lr: 0.000125 grad: 0.1595 (0.1787) loss: 0.9754 (0.9745) time: 0.1794 data: 0.0726 max mem: 8233 +Train: [6] [ 600/6250] eta: 0:16:24 lr: 0.000125 grad: 0.1675 (0.1786) loss: 0.9744 (0.9743) time: 0.1944 data: 0.1045 max mem: 8233 +Train: [6] [ 700/6250] eta: 0:15:58 lr: 0.000125 grad: 0.1567 (0.1776) loss: 0.9736 (0.9741) time: 0.1644 data: 0.0742 max mem: 8233 +Train: [6] [ 800/6250] eta: 0:15:52 lr: 0.000125 grad: 0.1384 (0.1776) loss: 0.9711 (0.9740) time: 0.1461 data: 0.0583 max mem: 8233 +Train: [6] [ 900/6250] eta: 0:15:33 lr: 0.000125 grad: 0.1378 (0.1775) loss: 0.9738 (0.9737) time: 0.1546 data: 0.0602 max mem: 8233 +Train: [6] [1000/6250] eta: 0:15:18 lr: 0.000125 grad: 0.1941 (0.1771) loss: 0.9742 (0.9736) time: 0.1580 data: 0.0725 max mem: 8233 +Train: [6] [1100/6250] eta: 0:15:02 lr: 0.000125 grad: 0.1494 (0.1762) loss: 0.9714 (0.9735) time: 0.1066 data: 0.0131 max mem: 8233 +Train: [6] [1200/6250] eta: 0:14:35 lr: 0.000125 grad: 0.1867 (0.1764) loss: 0.9726 (0.9734) time: 0.1430 data: 0.0507 max mem: 8233 +Train: [6] [1300/6250] eta: 0:14:22 lr: 0.000125 grad: 0.1603 (0.1768) loss: 0.9709 (0.9733) time: 0.2919 data: 0.1982 max mem: 8233 +Train: [6] [1400/6250] eta: 0:13:51 lr: 0.000125 grad: 0.1454 (0.1759) loss: 0.9732 (0.9733) time: 0.1363 data: 0.0506 max mem: 8233 +Train: [6] [1500/6250] eta: 0:13:28 lr: 0.000125 grad: 0.1546 (0.1751) loss: 0.9736 (0.9732) time: 0.1423 data: 0.0568 max mem: 8233 +Train: [6] [1600/6250] eta: 0:13:08 lr: 0.000125 grad: 0.1618 (0.1747) loss: 0.9717 (0.9732) time: 0.1688 data: 0.0911 max mem: 8233 +Train: [6] [1700/6250] eta: 0:12:53 lr: 0.000125 grad: 0.1439 (0.1749) loss: 0.9724 (0.9732) time: 0.1943 data: 0.1221 max mem: 8233 +Train: [6] [1800/6250] eta: 0:12:35 lr: 0.000125 grad: 0.1607 (0.1744) loss: 0.9745 (0.9731) time: 0.1604 data: 0.0832 max mem: 8233 +Train: [6] [1900/6250] eta: 0:12:18 lr: 0.000125 grad: 0.1489 (0.1753) loss: 0.9739 (0.9730) time: 0.1715 data: 0.0966 max mem: 8233 +Train: [6] [2000/6250] eta: 0:12:04 lr: 0.000125 grad: 0.2096 (0.1766) loss: 0.9681 (0.9729) time: 0.2096 data: 0.1445 max mem: 8233 +Train: [6] [2100/6250] eta: 0:11:49 lr: 0.000125 grad: 0.2351 (0.1775) loss: 0.9708 (0.9727) time: 0.1983 data: 0.1313 max mem: 8233 +Train: [6] [2200/6250] eta: 0:11:34 lr: 0.000125 grad: 0.1508 (0.1779) loss: 0.9706 (0.9726) time: 0.1792 data: 0.1002 max mem: 8233 +Train: [6] [2300/6250] eta: 0:11:13 lr: 0.000125 grad: 0.1477 (0.1786) loss: 0.9691 (0.9725) time: 0.1361 data: 0.0497 max mem: 8233 +Train: [6] [2400/6250] eta: 0:10:55 lr: 0.000125 grad: 0.1959 (0.1797) loss: 0.9687 (0.9724) time: 0.1476 data: 0.0697 max mem: 8233 +Train: [6] [2500/6250] eta: 0:10:35 lr: 0.000125 grad: 0.1642 (0.1802) loss: 0.9688 (0.9722) time: 0.1413 data: 0.0554 max mem: 8233 +Train: [6] [2600/6250] eta: 0:10:20 lr: 0.000125 grad: 0.1633 (0.1806) loss: 0.9708 (0.9721) time: 0.1045 data: 0.0003 max mem: 8233 +Train: [6] [2700/6250] eta: 0:10:01 lr: 0.000125 grad: 0.1938 (0.1820) loss: 0.9691 (0.9719) time: 0.1187 data: 0.0493 max mem: 8233 +Train: [6] [2800/6250] eta: 0:09:43 lr: 0.000125 grad: 0.1815 (0.1826) loss: 0.9655 (0.9718) time: 0.1446 data: 0.0633 max mem: 8233 +Train: [6] [2900/6250] eta: 0:09:25 lr: 0.000125 grad: 0.1850 (0.1829) loss: 0.9684 (0.9716) time: 0.1467 data: 0.0692 max mem: 8233 +Train: [6] [3000/6250] eta: 0:09:09 lr: 0.000125 grad: 0.2262 (0.1833) loss: 0.9698 (0.9715) time: 0.2244 data: 0.1463 max mem: 8233 +Train: [6] [3100/6250] eta: 0:08:53 lr: 0.000125 grad: 0.1919 (0.1835) loss: 0.9671 (0.9714) time: 0.2143 data: 0.1316 max mem: 8233 +Train: [6] [3200/6250] eta: 0:08:35 lr: 0.000125 grad: 0.2159 (0.1846) loss: 0.9690 (0.9713) time: 0.1518 data: 0.0761 max mem: 8233 +Train: [6] [3300/6250] eta: 0:08:18 lr: 0.000125 grad: 0.2070 (0.1852) loss: 0.9719 (0.9712) time: 0.1636 data: 0.0885 max mem: 8233 +Train: [6] [3400/6250] eta: 0:08:01 lr: 0.000125 grad: 0.1918 (0.1856) loss: 0.9685 (0.9711) time: 0.2053 data: 0.1284 max mem: 8233 +Train: [6] [3500/6250] eta: 0:07:46 lr: 0.000125 grad: 0.1745 (0.1862) loss: 0.9648 (0.9709) time: 0.2135 data: 0.1276 max mem: 8233 +Train: [6] [3600/6250] eta: 0:07:30 lr: 0.000125 grad: 0.1832 (0.1868) loss: 0.9666 (0.9708) time: 0.1535 data: 0.0391 max mem: 8233 +Train: [6] [3700/6250] eta: 0:07:12 lr: 0.000125 grad: 0.1744 (0.1872) loss: 0.9698 (0.9707) time: 0.1757 data: 0.1003 max mem: 8233 +Train: [6] [3800/6250] eta: 0:06:54 lr: 0.000125 grad: 0.2061 (0.1879) loss: 0.9684 (0.9707) time: 0.1481 data: 0.0777 max mem: 8233 +Train: [6] [3900/6250] eta: 0:06:37 lr: 0.000125 grad: 0.1716 (0.1881) loss: 0.9660 (0.9706) time: 0.1429 data: 0.0660 max mem: 8233 +Train: [6] [4000/6250] eta: 0:06:19 lr: 0.000125 grad: 0.1740 (0.1886) loss: 0.9681 (0.9705) time: 0.1362 data: 0.0583 max mem: 8233 +Train: [6] [4100/6250] eta: 0:06:02 lr: 0.000125 grad: 0.1767 (0.1886) loss: 0.9682 (0.9704) time: 0.1778 data: 0.0927 max mem: 8233 +Train: [6] [4200/6250] eta: 0:05:46 lr: 0.000125 grad: 0.1700 (0.1884) loss: 0.9679 (0.9704) time: 0.1097 data: 0.0003 max mem: 8233 +Train: [6] [4300/6250] eta: 0:05:29 lr: 0.000125 grad: 0.2008 (0.1887) loss: 0.9662 (0.9703) time: 0.1601 data: 0.0547 max mem: 8233 +Train: [6] [4400/6250] eta: 0:05:12 lr: 0.000125 grad: 0.1984 (0.1891) loss: 0.9665 (0.9702) time: 0.1617 data: 0.0794 max mem: 8233 +Train: [6] [4500/6250] eta: 0:04:55 lr: 0.000125 grad: 0.1869 (0.1891) loss: 0.9681 (0.9702) time: 0.1768 data: 0.0892 max mem: 8233 +Train: [6] [4600/6250] eta: 0:04:38 lr: 0.000125 grad: 0.2033 (0.1896) loss: 0.9683 (0.9701) time: 0.1348 data: 0.0502 max mem: 8233 +Train: [6] [4700/6250] eta: 0:04:21 lr: 0.000125 grad: 0.1756 (0.1896) loss: 0.9698 (0.9700) time: 0.1660 data: 0.0868 max mem: 8233 +Train: [6] [4800/6250] eta: 0:04:04 lr: 0.000125 grad: 0.2048 (0.1895) loss: 0.9670 (0.9700) time: 0.1476 data: 0.0681 max mem: 8233 +Train: [6] [4900/6250] eta: 0:03:48 lr: 0.000125 grad: 0.1604 (0.1896) loss: 0.9672 (0.9699) time: 0.1487 data: 0.0257 max mem: 8233 +Train: [6] [5000/6250] eta: 0:03:31 lr: 0.000125 grad: 0.1647 (0.1895) loss: 0.9684 (0.9699) time: 0.1647 data: 0.0775 max mem: 8233 +Train: [6] [5100/6250] eta: 0:03:14 lr: 0.000125 grad: 0.1812 (0.1895) loss: 0.9659 (0.9698) time: 0.0910 data: 0.0002 max mem: 8233 +Train: [6] [5200/6250] eta: 0:02:57 lr: 0.000125 grad: 0.1748 (0.1897) loss: 0.9671 (0.9697) time: 0.1542 data: 0.0800 max mem: 8233 +Train: [6] [5300/6250] eta: 0:02:40 lr: 0.000125 grad: 0.1994 (0.1901) loss: 0.9657 (0.9697) time: 0.1849 data: 0.1045 max mem: 8233 +Train: [6] [5400/6250] eta: 0:02:23 lr: 0.000125 grad: 0.1465 (0.1902) loss: 0.9666 (0.9696) time: 0.1156 data: 0.0068 max mem: 8233 +Train: [6] [5500/6250] eta: 0:02:06 lr: 0.000125 grad: 0.1550 (0.1901) loss: 0.9657 (0.9695) time: 0.1660 data: 0.0742 max mem: 8233 +Train: [6] [5600/6250] eta: 0:01:49 lr: 0.000125 grad: 0.2143 (0.1904) loss: 0.9654 (0.9694) time: 0.1282 data: 0.0007 max mem: 8233 +Train: [6] [5700/6250] eta: 0:01:32 lr: 0.000125 grad: 0.1708 (0.1906) loss: 0.9650 (0.9693) time: 0.1465 data: 0.0630 max mem: 8233 +Train: [6] [5800/6250] eta: 0:01:16 lr: 0.000125 grad: 0.1805 (0.1909) loss: 0.9643 (0.9693) time: 0.1128 data: 0.0246 max mem: 8233 +Train: [6] [5900/6250] eta: 0:00:59 lr: 0.000125 grad: 0.1654 (0.1910) loss: 0.9672 (0.9692) time: 0.1801 data: 0.1057 max mem: 8233 +Train: [6] [6000/6250] eta: 0:00:42 lr: 0.000125 grad: 0.1801 (0.1911) loss: 0.9654 (0.9691) time: 0.1461 data: 0.0713 max mem: 8233 +Train: [6] [6100/6250] eta: 0:00:25 lr: 0.000125 grad: 0.1709 (0.1913) loss: 0.9653 (0.9690) time: 0.1104 data: 0.0252 max mem: 8233 +Train: [6] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1769 (0.1914) loss: 0.9665 (0.9690) time: 0.1603 data: 0.0806 max mem: 8233 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1984 (0.1916) loss: 0.9678 (0.9689) time: 0.1722 data: 0.0910 max mem: 8233 +Train: [6] Total time: 0:17:43 (0.1702 s / it) +Averaged stats: lr: 0.000125 grad: 0.1984 (0.1916) loss: 0.9678 (0.9689) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:04:06 loss: 0.9668 (0.9668) time: 3.9833 data: 3.9210 max mem: 8233 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.9683 (0.9667) time: 0.1073 data: 0.0869 max mem: 8233 +Eval (hcp-train-subset): [6] Total time: 0:00:13 (0.2224 s / it) +Averaged stats (hcp-train-subset): loss: 0.9683 (0.9667) +Eval (hcp-val): [6] [ 0/62] eta: 0:05:01 loss: 0.9617 (0.9617) time: 4.8629 data: 4.8354 max mem: 8233 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.9639 (0.9637) time: 0.1495 data: 0.1275 max mem: 8233 +Eval (hcp-val): [6] Total time: 0:00:14 (0.2313 s / it) +Averaged stats (hcp-val): loss: 0.9639 (0.9637) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 11:36:06 lr: 0.000125 grad: 0.1314 (0.1314) loss: 0.9716 (0.9716) time: 6.6826 data: 6.5447 max mem: 8233 +Train: [7] [ 100/6250] eta: 0:22:40 lr: 0.000125 grad: 0.1769 (0.1860) loss: 0.9669 (0.9690) time: 0.1907 data: 0.0953 max mem: 8233 +Train: [7] [ 200/6250] eta: 0:20:05 lr: 0.000125 grad: 0.1777 (0.1880) loss: 0.9655 (0.9674) time: 0.1606 data: 0.0699 max mem: 8233 +Train: [7] [ 300/6250] eta: 0:18:30 lr: 0.000125 grad: 0.2014 (0.1947) loss: 0.9639 (0.9665) time: 0.1542 data: 0.0670 max mem: 8233 +Train: [7] [ 400/6250] eta: 0:17:45 lr: 0.000125 grad: 0.1710 (0.1934) loss: 0.9648 (0.9661) time: 0.1665 data: 0.0768 max mem: 8233 +Train: [7] [ 500/6250] eta: 0:17:07 lr: 0.000125 grad: 0.1748 (0.1936) loss: 0.9657 (0.9658) time: 0.1669 data: 0.0789 max mem: 8233 +Train: [7] [ 600/6250] eta: 0:16:34 lr: 0.000125 grad: 0.1824 (0.1912) loss: 0.9651 (0.9654) time: 0.1722 data: 0.0691 max mem: 8233 +Train: [7] [ 700/6250] eta: 0:16:02 lr: 0.000125 grad: 0.1668 (0.1912) loss: 0.9643 (0.9653) time: 0.1435 data: 0.0457 max mem: 8233 +Train: [7] [ 800/6250] eta: 0:15:36 lr: 0.000125 grad: 0.1584 (0.1907) loss: 0.9653 (0.9652) time: 0.1669 data: 0.0445 max mem: 8233 +Train: [7] [ 900/6250] eta: 0:15:17 lr: 0.000125 grad: 0.1724 (0.1899) loss: 0.9626 (0.9651) time: 0.1428 data: 0.0463 max mem: 8233 +Train: [7] [1000/6250] eta: 0:14:56 lr: 0.000125 grad: 0.1927 (0.1899) loss: 0.9656 (0.9650) time: 0.1865 data: 0.1007 max mem: 8233 +Train: [7] [1100/6250] eta: 0:14:34 lr: 0.000125 grad: 0.1787 (0.1910) loss: 0.9629 (0.9649) time: 0.1622 data: 0.0821 max mem: 8233 +Train: [7] [1200/6250] eta: 0:14:12 lr: 0.000125 grad: 0.1702 (0.1920) loss: 0.9627 (0.9648) time: 0.1580 data: 0.0736 max mem: 8233 +Train: [7] [1300/6250] eta: 0:13:53 lr: 0.000125 grad: 0.1667 (0.1919) loss: 0.9624 (0.9646) time: 0.1367 data: 0.0590 max mem: 8233 +Train: [7] [1400/6250] eta: 0:13:42 lr: 0.000125 grad: 0.2149 (0.1927) loss: 0.9635 (0.9644) time: 0.1824 data: 0.1021 max mem: 8233 +Train: [7] [1500/6250] eta: 0:13:18 lr: 0.000125 grad: 0.1850 (0.1928) loss: 0.9594 (0.9644) time: 0.1516 data: 0.0819 max mem: 8233 +Train: [7] [1600/6250] eta: 0:13:06 lr: 0.000125 grad: 0.1798 (0.1929) loss: 0.9634 (0.9642) time: 0.1613 data: 0.0767 max mem: 8233 +Train: [7] [1700/6250] eta: 0:12:47 lr: 0.000125 grad: 0.1640 (0.1929) loss: 0.9632 (0.9641) time: 0.1511 data: 0.0670 max mem: 8233 +Train: [7] [1800/6250] eta: 0:12:28 lr: 0.000125 grad: 0.1905 (0.1922) loss: 0.9590 (0.9639) time: 0.1306 data: 0.0465 max mem: 8233 +Train: [7] [1900/6250] eta: 0:12:11 lr: 0.000125 grad: 0.1903 (0.1921) loss: 0.9603 (0.9639) time: 0.1365 data: 0.0521 max mem: 8233 +Train: [7] [2000/6250] eta: 0:11:55 lr: 0.000125 grad: 0.2107 (0.1923) loss: 0.9623 (0.9637) time: 0.1664 data: 0.0747 max mem: 8233 +Train: [7] [2100/6250] eta: 0:11:38 lr: 0.000125 grad: 0.1885 (0.1926) loss: 0.9594 (0.9636) time: 0.1561 data: 0.0781 max mem: 8233 +Train: [7] [2200/6250] eta: 0:11:21 lr: 0.000125 grad: 0.1816 (0.1927) loss: 0.9625 (0.9635) time: 0.1633 data: 0.0859 max mem: 8233 +Train: [7] [2300/6250] eta: 0:11:07 lr: 0.000125 grad: 0.2405 (0.1938) loss: 0.9622 (0.9634) time: 0.1596 data: 0.0845 max mem: 8233 +Train: [7] [2400/6250] eta: 0:10:50 lr: 0.000125 grad: 0.1845 (0.1945) loss: 0.9582 (0.9633) time: 0.1442 data: 0.0617 max mem: 8233 +Train: [7] [2500/6250] eta: 0:10:35 lr: 0.000125 grad: 0.1733 (0.1948) loss: 0.9602 (0.9631) time: 0.1739 data: 0.0957 max mem: 8233 +Train: [7] [2600/6250] eta: 0:10:17 lr: 0.000125 grad: 0.2107 (0.1955) loss: 0.9604 (0.9630) time: 0.1493 data: 0.0709 max mem: 8233 +Train: [7] [2700/6250] eta: 0:09:59 lr: 0.000125 grad: 0.1800 (0.1966) loss: 0.9627 (0.9628) time: 0.1595 data: 0.0723 max mem: 8233 +Train: [7] [2800/6250] eta: 0:09:41 lr: 0.000125 grad: 0.1872 (0.1968) loss: 0.9577 (0.9627) time: 0.1967 data: 0.1201 max mem: 8233 +Train: [7] [2900/6250] eta: 0:09:24 lr: 0.000125 grad: 0.1843 (0.1968) loss: 0.9601 (0.9626) time: 0.1686 data: 0.0817 max mem: 8233 +Train: [7] [3000/6250] eta: 0:09:08 lr: 0.000125 grad: 0.2311 (0.1976) loss: 0.9567 (0.9624) time: 0.1713 data: 0.0767 max mem: 8233 +Train: [7] [3100/6250] eta: 0:08:49 lr: 0.000125 grad: 0.2049 (0.1978) loss: 0.9605 (0.9623) time: 0.1332 data: 0.0599 max mem: 8233 +Train: [7] [3200/6250] eta: 0:08:31 lr: 0.000125 grad: 0.1943 (0.1978) loss: 0.9602 (0.9622) time: 0.1526 data: 0.0707 max mem: 8233 +Train: [7] [3300/6250] eta: 0:08:14 lr: 0.000125 grad: 0.1672 (0.1977) loss: 0.9582 (0.9621) time: 0.1883 data: 0.1038 max mem: 8233 +Train: [7] [3400/6250] eta: 0:07:56 lr: 0.000125 grad: 0.1754 (0.1976) loss: 0.9619 (0.9621) time: 0.1541 data: 0.0738 max mem: 8233 +Train: [7] [3500/6250] eta: 0:07:39 lr: 0.000125 grad: 0.1877 (0.1980) loss: 0.9594 (0.9619) time: 0.1260 data: 0.0462 max mem: 8233 +Train: [7] [3600/6250] eta: 0:07:22 lr: 0.000125 grad: 0.1744 (0.1983) loss: 0.9605 (0.9619) time: 0.1845 data: 0.1029 max mem: 8233 +Train: [7] [3700/6250] eta: 0:07:06 lr: 0.000125 grad: 0.1929 (0.1987) loss: 0.9584 (0.9618) time: 0.1602 data: 0.0918 max mem: 8233 +Train: [7] [3800/6250] eta: 0:06:52 lr: 0.000125 grad: 0.2606 (0.1991) loss: 0.9550 (0.9617) time: 0.3385 data: 0.2367 max mem: 8233 +Train: [7] [3900/6250] eta: 0:06:34 lr: 0.000125 grad: 0.2175 (0.1992) loss: 0.9614 (0.9616) time: 0.1387 data: 0.0519 max mem: 8233 +Train: [7] [4000/6250] eta: 0:06:18 lr: 0.000125 grad: 0.1865 (0.1995) loss: 0.9608 (0.9615) time: 0.1372 data: 0.0286 max mem: 8233 +Train: [7] [4100/6250] eta: 0:06:00 lr: 0.000125 grad: 0.1966 (0.1995) loss: 0.9619 (0.9615) time: 0.1650 data: 0.0666 max mem: 8233 +Train: [7] [4200/6250] eta: 0:05:43 lr: 0.000125 grad: 0.2137 (0.1997) loss: 0.9591 (0.9614) time: 0.1943 data: 0.1112 max mem: 8233 +Train: [7] [4300/6250] eta: 0:05:27 lr: 0.000125 grad: 0.2122 (0.1998) loss: 0.9606 (0.9613) time: 0.1424 data: 0.0483 max mem: 8233 +Train: [7] [4400/6250] eta: 0:05:10 lr: 0.000125 grad: 0.1811 (0.1998) loss: 0.9558 (0.9612) time: 0.1447 data: 0.0641 max mem: 8233 +Train: [7] [4500/6250] eta: 0:04:53 lr: 0.000125 grad: 0.1945 (0.2000) loss: 0.9596 (0.9611) time: 0.1826 data: 0.1045 max mem: 8233 +Train: [7] [4600/6250] eta: 0:04:37 lr: 0.000125 grad: 0.1836 (0.2001) loss: 0.9583 (0.9611) time: 0.1129 data: 0.0080 max mem: 8233 +Train: [7] [4700/6250] eta: 0:04:20 lr: 0.000125 grad: 0.1971 (0.2003) loss: 0.9613 (0.9610) time: 0.1545 data: 0.0844 max mem: 8233 +Train: [7] [4800/6250] eta: 0:04:04 lr: 0.000125 grad: 0.1846 (0.2001) loss: 0.9578 (0.9610) time: 0.2315 data: 0.1237 max mem: 8233 +Train: [7] [4900/6250] eta: 0:03:47 lr: 0.000125 grad: 0.2160 (0.2004) loss: 0.9577 (0.9609) time: 0.2284 data: 0.1486 max mem: 8233 +Train: [7] [5000/6250] eta: 0:03:30 lr: 0.000125 grad: 0.1746 (0.2005) loss: 0.9600 (0.9608) time: 0.1645 data: 0.0727 max mem: 8233 +Train: [7] [5100/6250] eta: 0:03:13 lr: 0.000125 grad: 0.2048 (0.2008) loss: 0.9562 (0.9607) time: 0.1814 data: 0.0873 max mem: 8233 +Train: [7] [5200/6250] eta: 0:02:56 lr: 0.000125 grad: 0.1979 (0.2010) loss: 0.9585 (0.9607) time: 0.1473 data: 0.0527 max mem: 8233 +Train: [7] [5300/6250] eta: 0:02:39 lr: 0.000125 grad: 0.1850 (0.2009) loss: 0.9579 (0.9606) time: 0.1326 data: 0.0350 max mem: 8233 +Train: [7] [5400/6250] eta: 0:02:22 lr: 0.000125 grad: 0.1841 (0.2011) loss: 0.9577 (0.9606) time: 0.1445 data: 0.0563 max mem: 8233 +Train: [7] [5500/6250] eta: 0:02:05 lr: 0.000125 grad: 0.1991 (0.2013) loss: 0.9557 (0.9605) time: 0.1545 data: 0.0714 max mem: 8233 +Train: [7] [5600/6250] eta: 0:01:48 lr: 0.000125 grad: 0.2072 (0.2014) loss: 0.9567 (0.9604) time: 0.1610 data: 0.0758 max mem: 8233 +Train: [7] [5700/6250] eta: 0:01:31 lr: 0.000125 grad: 0.1743 (0.2015) loss: 0.9552 (0.9603) time: 0.1271 data: 0.0555 max mem: 8233 +Train: [7] [5800/6250] eta: 0:01:15 lr: 0.000125 grad: 0.1974 (0.2017) loss: 0.9537 (0.9603) time: 0.2172 data: 0.1432 max mem: 8233 +Train: [7] [5900/6250] eta: 0:00:58 lr: 0.000125 grad: 0.1861 (0.2017) loss: 0.9563 (0.9602) time: 0.1942 data: 0.1138 max mem: 8233 +Train: [7] [6000/6250] eta: 0:00:41 lr: 0.000125 grad: 0.1889 (0.2018) loss: 0.9561 (0.9601) time: 0.1632 data: 0.0877 max mem: 8233 +Train: [7] [6100/6250] eta: 0:00:25 lr: 0.000125 grad: 0.2180 (0.2017) loss: 0.9565 (0.9600) time: 0.1416 data: 0.0499 max mem: 8233 +Train: [7] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1867 (0.2019) loss: 0.9568 (0.9600) time: 0.1683 data: 0.0904 max mem: 8233 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1862 (0.2018) loss: 0.9562 (0.9599) time: 0.1652 data: 0.0789 max mem: 8233 +Train: [7] Total time: 0:17:30 (0.1680 s / it) +Averaged stats: lr: 0.000125 grad: 0.1862 (0.2018) loss: 0.9562 (0.9599) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:03:26 loss: 0.9586 (0.9586) time: 3.3364 data: 3.2799 max mem: 8233 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.9595 (0.9579) time: 0.1247 data: 0.1038 max mem: 8233 +Eval (hcp-train-subset): [7] Total time: 0:00:13 (0.2143 s / it) +Averaged stats (hcp-train-subset): loss: 0.9595 (0.9579) +Eval (hcp-val): [7] [ 0/62] eta: 0:03:44 loss: 0.9525 (0.9525) time: 3.6156 data: 3.4885 max mem: 8233 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.9566 (0.9551) time: 0.1416 data: 0.1208 max mem: 8233 +Eval (hcp-val): [7] Total time: 0:00:15 (0.2442 s / it) +Averaged stats (hcp-val): loss: 0.9566 (0.9551) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 10:35:59 lr: 0.000125 grad: 0.0988 (0.0988) loss: 0.9751 (0.9751) time: 6.1055 data: 5.9741 max mem: 8233 +Train: [8] [ 100/6250] eta: 0:29:51 lr: 0.000125 grad: 0.1664 (0.2011) loss: 0.9645 (0.9621) time: 0.1829 data: 0.0728 max mem: 8233 +Train: [8] [ 200/6250] eta: 0:24:01 lr: 0.000125 grad: 0.1769 (0.1961) loss: 0.9577 (0.9618) time: 0.1902 data: 0.1174 max mem: 8233 +Train: [8] [ 300/6250] eta: 0:21:24 lr: 0.000125 grad: 0.1733 (0.1945) loss: 0.9599 (0.9610) time: 0.1839 data: 0.0887 max mem: 8233 +Train: [8] [ 400/6250] eta: 0:19:59 lr: 0.000125 grad: 0.1759 (0.1967) loss: 0.9558 (0.9603) time: 0.1511 data: 0.0671 max mem: 8233 +Train: [8] [ 500/6250] eta: 0:19:20 lr: 0.000125 grad: 0.1817 (0.1966) loss: 0.9547 (0.9597) time: 0.1858 data: 0.0748 max mem: 8233 +Train: [8] [ 600/6250] eta: 0:18:39 lr: 0.000125 grad: 0.1913 (0.1973) loss: 0.9563 (0.9593) time: 0.1963 data: 0.0869 max mem: 8233 +Train: [8] [ 700/6250] eta: 0:17:52 lr: 0.000125 grad: 0.1860 (0.1991) loss: 0.9568 (0.9591) time: 0.1743 data: 0.0704 max mem: 8233 +Train: [8] [ 800/6250] eta: 0:17:17 lr: 0.000125 grad: 0.1761 (0.1985) loss: 0.9566 (0.9588) time: 0.1805 data: 0.0915 max mem: 8233 +Train: [8] [ 900/6250] eta: 0:16:48 lr: 0.000125 grad: 0.2451 (0.2000) loss: 0.9520 (0.9583) time: 0.2048 data: 0.1127 max mem: 8233 +Train: [8] [1000/6250] eta: 0:16:20 lr: 0.000125 grad: 0.2131 (0.2009) loss: 0.9566 (0.9581) time: 0.1730 data: 0.0941 max mem: 8233 +Train: [8] [1100/6250] eta: 0:15:53 lr: 0.000125 grad: 0.2088 (0.2026) loss: 0.9545 (0.9577) time: 0.1801 data: 0.1002 max mem: 8233 +Train: [8] [1200/6250] eta: 0:15:28 lr: 0.000125 grad: 0.1843 (0.2041) loss: 0.9547 (0.9574) time: 0.1581 data: 0.0612 max mem: 8233 +Train: [8] [1300/6250] eta: 0:15:08 lr: 0.000125 grad: 0.1871 (0.2058) loss: 0.9531 (0.9571) time: 0.1895 data: 0.1038 max mem: 8233 +Train: [8] [1400/6250] eta: 0:14:49 lr: 0.000125 grad: 0.1924 (0.2060) loss: 0.9513 (0.9568) time: 0.1826 data: 0.1002 max mem: 8233 +Train: [8] [1500/6250] eta: 0:14:24 lr: 0.000125 grad: 0.2346 (0.2065) loss: 0.9550 (0.9566) time: 0.1502 data: 0.0604 max mem: 8233 +Train: [8] [1600/6250] eta: 0:13:59 lr: 0.000125 grad: 0.1997 (0.2066) loss: 0.9537 (0.9563) time: 0.1661 data: 0.0853 max mem: 8233 +Train: [8] [1700/6250] eta: 0:13:36 lr: 0.000125 grad: 0.1829 (0.2061) loss: 0.9503 (0.9561) time: 0.1411 data: 0.0556 max mem: 8233 +Train: [8] [1800/6250] eta: 0:13:14 lr: 0.000125 grad: 0.1882 (0.2066) loss: 0.9524 (0.9560) time: 0.1335 data: 0.0421 max mem: 8233 +Train: [8] [1900/6250] eta: 0:12:57 lr: 0.000125 grad: 0.2028 (0.2067) loss: 0.9520 (0.9558) time: 0.2262 data: 0.1286 max mem: 8233 +Train: [8] [2000/6250] eta: 0:12:36 lr: 0.000125 grad: 0.2197 (0.2068) loss: 0.9514 (0.9556) time: 0.2036 data: 0.1315 max mem: 8233 +Train: [8] [2100/6250] eta: 0:12:14 lr: 0.000125 grad: 0.2085 (0.2069) loss: 0.9504 (0.9555) time: 0.2007 data: 0.1219 max mem: 8233 +Train: [8] [2200/6250] eta: 0:11:52 lr: 0.000125 grad: 0.1894 (0.2065) loss: 0.9535 (0.9554) time: 0.1629 data: 0.0749 max mem: 8233 +Train: [8] [2300/6250] eta: 0:11:39 lr: 0.000125 grad: 0.1945 (0.2069) loss: 0.9528 (0.9553) time: 0.3134 data: 0.2124 max mem: 8233 +Train: [8] [2400/6250] eta: 0:11:18 lr: 0.000125 grad: 0.1844 (0.2071) loss: 0.9513 (0.9552) time: 0.1627 data: 0.0786 max mem: 8233 +Train: [8] [2500/6250] eta: 0:11:00 lr: 0.000125 grad: 0.2128 (0.2073) loss: 0.9490 (0.9551) time: 0.1771 data: 0.1003 max mem: 8233 +Train: [8] [2600/6250] eta: 0:10:42 lr: 0.000125 grad: 0.2211 (0.2080) loss: 0.9532 (0.9550) time: 0.1436 data: 0.0644 max mem: 8233 +Train: [8] [2700/6250] eta: 0:10:23 lr: 0.000125 grad: 0.2167 (0.2078) loss: 0.9514 (0.9549) time: 0.1647 data: 0.0951 max mem: 8233 +Train: [8] [2800/6250] eta: 0:10:05 lr: 0.000125 grad: 0.2104 (0.2077) loss: 0.9510 (0.9547) time: 0.1636 data: 0.0958 max mem: 8233 +Train: [8] [2900/6250] eta: 0:09:47 lr: 0.000125 grad: 0.1826 (0.2079) loss: 0.9506 (0.9546) time: 0.1221 data: 0.0542 max mem: 8233 +Train: [8] [3000/6250] eta: 0:09:30 lr: 0.000125 grad: 0.1813 (0.2082) loss: 0.9525 (0.9545) time: 0.1758 data: 0.1071 max mem: 8233 +Train: [8] [3100/6250] eta: 0:09:12 lr: 0.000125 grad: 0.2042 (0.2081) loss: 0.9492 (0.9544) time: 0.1693 data: 0.0814 max mem: 8233 +Train: [8] [3200/6250] eta: 0:08:54 lr: 0.000125 grad: 0.2003 (0.2081) loss: 0.9500 (0.9543) time: 0.1684 data: 0.0965 max mem: 8233 +Train: [8] [3300/6250] eta: 0:08:37 lr: 0.000125 grad: 0.1792 (0.2081) loss: 0.9549 (0.9543) time: 0.1402 data: 0.0694 max mem: 8233 +Train: [8] [3400/6250] eta: 0:08:20 lr: 0.000125 grad: 0.1955 (0.2083) loss: 0.9524 (0.9542) time: 0.1847 data: 0.1019 max mem: 8233 +Train: [8] [3500/6250] eta: 0:08:02 lr: 0.000125 grad: 0.1853 (0.2081) loss: 0.9529 (0.9542) time: 0.1753 data: 0.1117 max mem: 8233 +Train: [8] [3600/6250] eta: 0:07:46 lr: 0.000125 grad: 0.1959 (0.2080) loss: 0.9523 (0.9541) time: 0.1360 data: 0.0375 max mem: 8233 +Train: [8] [3700/6250] eta: 0:07:30 lr: 0.000125 grad: 0.1799 (0.2075) loss: 0.9536 (0.9541) time: 0.2064 data: 0.1432 max mem: 8233 +Train: [8] [3800/6250] eta: 0:07:12 lr: 0.000125 grad: 0.1916 (0.2072) loss: 0.9539 (0.9541) time: 0.1771 data: 0.0964 max mem: 8233 +Train: [8] [3900/6250] eta: 0:06:54 lr: 0.000125 grad: 0.1814 (0.2067) loss: 0.9502 (0.9540) time: 0.1092 data: 0.0037 max mem: 8233 +Train: [8] [4000/6250] eta: 0:06:36 lr: 0.000125 grad: 0.2178 (0.2065) loss: 0.9555 (0.9540) time: 0.1470 data: 0.0654 max mem: 8233 +Train: [8] [4100/6250] eta: 0:06:19 lr: 0.000125 grad: 0.1765 (0.2064) loss: 0.9492 (0.9539) time: 0.1795 data: 0.0979 max mem: 8233 +Train: [8] [4200/6250] eta: 0:06:02 lr: 0.000125 grad: 0.1910 (0.2062) loss: 0.9533 (0.9539) time: 0.3063 data: 0.1663 max mem: 8233 +Train: [8] [4300/6250] eta: 0:05:43 lr: 0.000125 grad: 0.1923 (0.2061) loss: 0.9541 (0.9538) time: 0.1496 data: 0.0663 max mem: 8233 +Train: [8] [4400/6250] eta: 0:05:26 lr: 0.000125 grad: 0.1851 (0.2058) loss: 0.9537 (0.9538) time: 0.1101 data: 0.0159 max mem: 8233 +Train: [8] [4500/6250] eta: 0:05:08 lr: 0.000125 grad: 0.1759 (0.2058) loss: 0.9511 (0.9537) time: 0.2295 data: 0.1419 max mem: 8233 +Train: [8] [4600/6250] eta: 0:04:50 lr: 0.000125 grad: 0.2056 (0.2055) loss: 0.9511 (0.9537) time: 0.1593 data: 0.0569 max mem: 8233 +Train: [8] [4700/6250] eta: 0:04:32 lr: 0.000125 grad: 0.1827 (0.2052) loss: 0.9536 (0.9537) time: 0.1723 data: 0.0882 max mem: 8233 +Train: [8] [4800/6250] eta: 0:04:14 lr: 0.000125 grad: 0.1843 (0.2053) loss: 0.9543 (0.9536) time: 0.1064 data: 0.0057 max mem: 8233 +Train: [8] [4900/6250] eta: 0:03:56 lr: 0.000125 grad: 0.2002 (0.2051) loss: 0.9491 (0.9536) time: 0.1363 data: 0.0572 max mem: 8233 +Train: [8] [5000/6250] eta: 0:03:39 lr: 0.000125 grad: 0.1496 (0.2048) loss: 0.9527 (0.9535) time: 0.1407 data: 0.0633 max mem: 8233 +Train: [8] [5100/6250] eta: 0:03:21 lr: 0.000125 grad: 0.1917 (0.2046) loss: 0.9488 (0.9535) time: 0.1398 data: 0.0598 max mem: 8233 +Train: [8] [5200/6250] eta: 0:03:03 lr: 0.000124 grad: 0.1948 (0.2046) loss: 0.9503 (0.9535) time: 0.1565 data: 0.0708 max mem: 8233 +Train: [8] [5300/6250] eta: 0:02:46 lr: 0.000124 grad: 0.2219 (0.2047) loss: 0.9499 (0.9534) time: 0.1204 data: 0.0003 max mem: 8233 +Train: [8] [5400/6250] eta: 0:02:28 lr: 0.000124 grad: 0.2022 (0.2047) loss: 0.9526 (0.9534) time: 0.1920 data: 0.1119 max mem: 8233 +Train: [8] [5500/6250] eta: 0:02:10 lr: 0.000124 grad: 0.2043 (0.2046) loss: 0.9484 (0.9533) time: 0.1683 data: 0.0930 max mem: 8233 +Train: [8] [5600/6250] eta: 0:01:53 lr: 0.000124 grad: 0.1977 (0.2047) loss: 0.9483 (0.9532) time: 0.1574 data: 0.0672 max mem: 8233 +Train: [8] [5700/6250] eta: 0:01:35 lr: 0.000124 grad: 0.1830 (0.2047) loss: 0.9476 (0.9531) time: 0.1355 data: 0.0392 max mem: 8233 +Train: [8] [5800/6250] eta: 0:01:18 lr: 0.000124 grad: 0.1777 (0.2048) loss: 0.9500 (0.9531) time: 0.1617 data: 0.0708 max mem: 8233 +Train: [8] [5900/6250] eta: 0:01:00 lr: 0.000124 grad: 0.2012 (0.2049) loss: 0.9447 (0.9530) time: 0.1393 data: 0.0541 max mem: 8233 +Train: [8] [6000/6250] eta: 0:00:43 lr: 0.000124 grad: 0.1862 (0.2047) loss: 0.9503 (0.9529) time: 0.1923 data: 0.0981 max mem: 8233 +Train: [8] [6100/6250] eta: 0:00:26 lr: 0.000124 grad: 0.1984 (0.2050) loss: 0.9468 (0.9528) time: 0.1711 data: 0.0908 max mem: 8233 +Train: [8] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.2136 (0.2049) loss: 0.9485 (0.9527) time: 0.1675 data: 0.0843 max mem: 8233 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.1734 (0.2050) loss: 0.9465 (0.9527) time: 0.1728 data: 0.0972 max mem: 8233 +Train: [8] Total time: 0:18:13 (0.1749 s / it) +Averaged stats: lr: 0.000124 grad: 0.1734 (0.2050) loss: 0.9465 (0.9527) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:07:28 loss: 0.9530 (0.9530) time: 7.2313 data: 7.1986 max mem: 8233 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.9521 (0.9505) time: 0.1501 data: 0.1294 max mem: 8233 +Eval (hcp-train-subset): [8] Total time: 0:00:14 (0.2379 s / it) +Averaged stats (hcp-train-subset): loss: 0.9521 (0.9505) +Eval (hcp-val): [8] [ 0/62] eta: 0:05:49 loss: 0.9416 (0.9416) time: 5.6412 data: 5.6121 max mem: 8233 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.9478 (0.9462) time: 0.1382 data: 0.1133 max mem: 8233 +Eval (hcp-val): [8] Total time: 0:00:14 (0.2360 s / it) +Averaged stats (hcp-val): loss: 0.9478 (0.9462) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 7:37:47 lr: 0.000124 grad: 0.1420 (0.1420) loss: 0.9517 (0.9517) time: 4.3948 data: 4.1357 max mem: 8233 +Train: [9] [ 100/6250] eta: 0:23:31 lr: 0.000124 grad: 0.1913 (0.2153) loss: 0.9455 (0.9482) time: 0.1875 data: 0.0832 max mem: 8233 +Train: [9] [ 200/6250] eta: 0:20:20 lr: 0.000124 grad: 0.2042 (0.2143) loss: 0.9496 (0.9488) time: 0.1846 data: 0.1066 max mem: 8233 +Train: [9] [ 300/6250] eta: 0:19:43 lr: 0.000124 grad: 0.2227 (0.2135) loss: 0.9535 (0.9488) time: 0.1627 data: 0.0844 max mem: 8233 +Train: [9] [ 400/6250] eta: 0:18:35 lr: 0.000124 grad: 0.2086 (0.2109) loss: 0.9533 (0.9493) time: 0.1513 data: 0.0799 max mem: 8233 +Train: [9] [ 500/6250] eta: 0:17:41 lr: 0.000124 grad: 0.1795 (0.2083) loss: 0.9507 (0.9495) time: 0.1812 data: 0.0951 max mem: 8233 +Train: [9] [ 600/6250] eta: 0:17:18 lr: 0.000124 grad: 0.2072 (0.2057) loss: 0.9513 (0.9496) time: 0.1803 data: 0.0911 max mem: 8233 +Train: [9] [ 700/6250] eta: 0:16:45 lr: 0.000124 grad: 0.1862 (0.2038) loss: 0.9510 (0.9498) time: 0.1497 data: 0.0713 max mem: 8233 +Train: [9] [ 800/6250] eta: 0:16:12 lr: 0.000124 grad: 0.1878 (0.2019) loss: 0.9495 (0.9499) time: 0.1625 data: 0.0714 max mem: 8233 +Train: [9] [ 900/6250] eta: 0:15:41 lr: 0.000124 grad: 0.2093 (0.2015) loss: 0.9505 (0.9498) time: 0.1450 data: 0.0310 max mem: 8233 +Train: [9] [1000/6250] eta: 0:15:10 lr: 0.000124 grad: 0.2007 (0.2015) loss: 0.9484 (0.9497) time: 0.1500 data: 0.0637 max mem: 8233 +Train: [9] [1100/6250] eta: 0:14:47 lr: 0.000124 grad: 0.2000 (0.2019) loss: 0.9486 (0.9497) time: 0.1677 data: 0.1012 max mem: 8233 +Train: [9] [1200/6250] eta: 0:14:33 lr: 0.000124 grad: 0.1881 (0.2010) loss: 0.9517 (0.9496) time: 0.1983 data: 0.1134 max mem: 8233 +Train: [9] [1300/6250] eta: 0:14:21 lr: 0.000124 grad: 0.1828 (0.2007) loss: 0.9493 (0.9496) time: 0.1178 data: 0.0003 max mem: 8233 +Train: [9] [1400/6250] eta: 0:14:05 lr: 0.000124 grad: 0.2037 (0.2002) loss: 0.9454 (0.9495) time: 0.1627 data: 0.0682 max mem: 8233 +Train: [9] [1500/6250] eta: 0:13:48 lr: 0.000124 grad: 0.2025 (0.2000) loss: 0.9506 (0.9494) time: 0.1844 data: 0.1078 max mem: 8233 +Train: [9] [1600/6250] eta: 0:13:30 lr: 0.000124 grad: 0.1808 (0.1998) loss: 0.9528 (0.9493) time: 0.2094 data: 0.1248 max mem: 8233 +Train: [9] [1700/6250] eta: 0:13:14 lr: 0.000124 grad: 0.1731 (0.1996) loss: 0.9504 (0.9493) time: 0.2105 data: 0.1363 max mem: 8233 +Train: [9] [1800/6250] eta: 0:12:55 lr: 0.000124 grad: 0.1983 (0.1996) loss: 0.9436 (0.9491) time: 0.1675 data: 0.0884 max mem: 8233 +Train: [9] [1900/6250] eta: 0:12:37 lr: 0.000124 grad: 0.1915 (0.1992) loss: 0.9460 (0.9491) time: 0.1150 data: 0.0003 max mem: 8233 +Train: [9] [2000/6250] eta: 0:12:16 lr: 0.000124 grad: 0.2026 (0.1995) loss: 0.9454 (0.9490) time: 0.1710 data: 0.0902 max mem: 8233 +Train: [9] [2100/6250] eta: 0:11:57 lr: 0.000124 grad: 0.1701 (0.1994) loss: 0.9476 (0.9489) time: 0.1665 data: 0.0939 max mem: 8233 +Train: [9] [2200/6250] eta: 0:11:41 lr: 0.000124 grad: 0.1852 (0.1997) loss: 0.9481 (0.9488) time: 0.1598 data: 0.0848 max mem: 8233 +Train: [9] [2300/6250] eta: 0:11:22 lr: 0.000124 grad: 0.1862 (0.1997) loss: 0.9433 (0.9486) time: 0.2278 data: 0.1470 max mem: 8233 +Train: [9] [2400/6250] eta: 0:11:00 lr: 0.000124 grad: 0.1942 (0.2000) loss: 0.9454 (0.9484) time: 0.1647 data: 0.0858 max mem: 8233 +Train: [9] [2500/6250] eta: 0:10:43 lr: 0.000124 grad: 0.1865 (0.2000) loss: 0.9446 (0.9483) time: 0.1983 data: 0.0960 max mem: 8233 +Train: [9] [2600/6250] eta: 0:10:24 lr: 0.000124 grad: 0.1724 (0.2000) loss: 0.9455 (0.9482) time: 0.1640 data: 0.0965 max mem: 8233 +Train: [9] [2700/6250] eta: 0:10:06 lr: 0.000124 grad: 0.1981 (0.1998) loss: 0.9467 (0.9481) time: 0.1551 data: 0.0654 max mem: 8233 +Train: [9] [2800/6250] eta: 0:09:47 lr: 0.000124 grad: 0.1931 (0.2003) loss: 0.9474 (0.9480) time: 0.1686 data: 0.0851 max mem: 8233 +Train: [9] [2900/6250] eta: 0:09:28 lr: 0.000124 grad: 0.2018 (0.2002) loss: 0.9494 (0.9479) time: 0.1557 data: 0.0821 max mem: 8233 +Train: [9] [3000/6250] eta: 0:09:09 lr: 0.000124 grad: 0.1921 (0.2001) loss: 0.9462 (0.9478) time: 0.1760 data: 0.0973 max mem: 8233 +Train: [9] [3100/6250] eta: 0:08:54 lr: 0.000124 grad: 0.1830 (0.2001) loss: 0.9453 (0.9478) time: 0.1393 data: 0.0628 max mem: 8233 +Train: [9] [3200/6250] eta: 0:08:36 lr: 0.000124 grad: 0.1844 (0.1998) loss: 0.9467 (0.9477) time: 0.1724 data: 0.0966 max mem: 8233 +Train: [9] [3300/6250] eta: 0:08:20 lr: 0.000124 grad: 0.1924 (0.1998) loss: 0.9470 (0.9476) time: 0.1726 data: 0.0824 max mem: 8233 +Train: [9] [3400/6250] eta: 0:08:02 lr: 0.000124 grad: 0.2060 (0.1996) loss: 0.9466 (0.9475) time: 0.1630 data: 0.0884 max mem: 8233 +Train: [9] [3500/6250] eta: 0:07:44 lr: 0.000124 grad: 0.1891 (0.1999) loss: 0.9437 (0.9474) time: 0.1484 data: 0.0670 max mem: 8233 +Train: [9] [3600/6250] eta: 0:07:27 lr: 0.000124 grad: 0.1895 (0.1999) loss: 0.9504 (0.9474) time: 0.1609 data: 0.0864 max mem: 8233 +Train: [9] [3700/6250] eta: 0:07:09 lr: 0.000124 grad: 0.1714 (0.1997) loss: 0.9456 (0.9473) time: 0.1713 data: 0.0824 max mem: 8233 +Train: [9] [3800/6250] eta: 0:06:53 lr: 0.000124 grad: 0.1919 (0.1998) loss: 0.9448 (0.9473) time: 0.1227 data: 0.0618 max mem: 8233 +Train: [9] [3900/6250] eta: 0:06:36 lr: 0.000124 grad: 0.1968 (0.2000) loss: 0.9456 (0.9472) time: 0.1639 data: 0.0845 max mem: 8233 +Train: [9] [4000/6250] eta: 0:06:20 lr: 0.000124 grad: 0.1836 (0.1997) loss: 0.9442 (0.9471) time: 0.0980 data: 0.0002 max mem: 8233 +Train: [9] [4100/6250] eta: 0:06:03 lr: 0.000124 grad: 0.2165 (0.2000) loss: 0.9472 (0.9470) time: 0.1865 data: 0.1007 max mem: 8233 +Train: [9] [4200/6250] eta: 0:05:46 lr: 0.000124 grad: 0.1938 (0.1998) loss: 0.9485 (0.9470) time: 0.1537 data: 0.0730 max mem: 8233 +Train: [9] [4300/6250] eta: 0:05:28 lr: 0.000124 grad: 0.2015 (0.1999) loss: 0.9456 (0.9470) time: 0.1554 data: 0.0740 max mem: 8233 +Train: [9] [4400/6250] eta: 0:05:11 lr: 0.000124 grad: 0.1815 (0.1998) loss: 0.9474 (0.9470) time: 0.1623 data: 0.0737 max mem: 8233 +Train: [9] [4500/6250] eta: 0:04:54 lr: 0.000124 grad: 0.1780 (0.1998) loss: 0.9410 (0.9469) time: 0.1482 data: 0.0677 max mem: 8233 +Train: [9] [4600/6250] eta: 0:04:37 lr: 0.000124 grad: 0.1735 (0.1997) loss: 0.9416 (0.9469) time: 0.1462 data: 0.0618 max mem: 8233 +Train: [9] [4700/6250] eta: 0:04:20 lr: 0.000124 grad: 0.2022 (0.1998) loss: 0.9424 (0.9468) time: 0.1555 data: 0.0707 max mem: 8233 +Train: [9] [4800/6250] eta: 0:04:03 lr: 0.000124 grad: 0.1864 (0.1997) loss: 0.9443 (0.9468) time: 0.1680 data: 0.0900 max mem: 8233 +Train: [9] [4900/6250] eta: 0:03:46 lr: 0.000124 grad: 0.1947 (0.1997) loss: 0.9472 (0.9467) time: 0.1536 data: 0.0711 max mem: 8233 +Train: [9] [5000/6250] eta: 0:03:29 lr: 0.000124 grad: 0.1682 (0.1994) loss: 0.9475 (0.9467) time: 0.1678 data: 0.0948 max mem: 8233 +Train: [9] [5100/6250] eta: 0:03:12 lr: 0.000124 grad: 0.1965 (0.1994) loss: 0.9447 (0.9466) time: 0.1706 data: 0.1012 max mem: 8233 +Train: [9] [5200/6250] eta: 0:02:55 lr: 0.000124 grad: 0.2403 (0.1996) loss: 0.9449 (0.9466) time: 0.1637 data: 0.0784 max mem: 8233 +Train: [9] [5300/6250] eta: 0:02:39 lr: 0.000124 grad: 0.1998 (0.1995) loss: 0.9428 (0.9466) time: 0.2342 data: 0.1316 max mem: 8233 +Train: [9] [5400/6250] eta: 0:02:22 lr: 0.000124 grad: 0.1634 (0.1993) loss: 0.9420 (0.9465) time: 0.1867 data: 0.0902 max mem: 8233 +Train: [9] [5500/6250] eta: 0:02:05 lr: 0.000124 grad: 0.1850 (0.1992) loss: 0.9391 (0.9465) time: 0.1993 data: 0.1169 max mem: 8233 +Train: [9] [5600/6250] eta: 0:01:49 lr: 0.000124 grad: 0.1993 (0.1991) loss: 0.9385 (0.9464) time: 0.2403 data: 0.1559 max mem: 8233 +Train: [9] [5700/6250] eta: 0:01:32 lr: 0.000124 grad: 0.1872 (0.1991) loss: 0.9448 (0.9463) time: 0.1467 data: 0.0582 max mem: 8233 +Train: [9] [5800/6250] eta: 0:01:15 lr: 0.000124 grad: 0.1876 (0.1991) loss: 0.9446 (0.9463) time: 0.1511 data: 0.0662 max mem: 8233 +Train: [9] [5900/6250] eta: 0:00:58 lr: 0.000124 grad: 0.2179 (0.1992) loss: 0.9408 (0.9462) time: 0.2077 data: 0.0688 max mem: 8233 +Train: [9] [6000/6250] eta: 0:00:41 lr: 0.000124 grad: 0.1821 (0.1992) loss: 0.9370 (0.9461) time: 0.1367 data: 0.0509 max mem: 8233 +Train: [9] [6100/6250] eta: 0:00:25 lr: 0.000124 grad: 0.1807 (0.1992) loss: 0.9396 (0.9461) time: 0.1498 data: 0.0720 max mem: 8233 +Train: [9] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.1982 (0.1994) loss: 0.9389 (0.9460) time: 0.2068 data: 0.1323 max mem: 8233 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.1884 (0.1993) loss: 0.9415 (0.9459) time: 0.1609 data: 0.0874 max mem: 8233 +Train: [9] Total time: 0:17:36 (0.1691 s / it) +Averaged stats: lr: 0.000124 grad: 0.1884 (0.1993) loss: 0.9415 (0.9459) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:06:02 loss: 0.9490 (0.9490) time: 5.8397 data: 5.8118 max mem: 8233 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.9461 (0.9448) time: 0.1295 data: 0.1076 max mem: 8233 +Eval (hcp-train-subset): [9] Total time: 0:00:14 (0.2305 s / it) +Averaged stats (hcp-train-subset): loss: 0.9461 (0.9448) +Making plots (hcp-train-subset): example=54 +Eval (hcp-val): [9] [ 0/62] eta: 0:05:40 loss: 0.9399 (0.9399) time: 5.4922 data: 5.4569 max mem: 8233 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.9408 (0.9409) time: 0.1181 data: 0.0967 max mem: 8233 +Eval (hcp-val): [9] Total time: 0:00:14 (0.2392 s / it) +Averaged stats (hcp-val): loss: 0.9408 (0.9409) +Making plots (hcp-val): example=9 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 8:59:42 lr: 0.000124 grad: 0.1281 (0.1281) loss: 0.9752 (0.9752) time: 5.1811 data: 4.9058 max mem: 8233 +Train: [10] [ 100/6250] eta: 0:22:31 lr: 0.000124 grad: 0.1909 (0.2326) loss: 0.9513 (0.9473) time: 0.1549 data: 0.0604 max mem: 8233 +Train: [10] [ 200/6250] eta: 0:19:49 lr: 0.000124 grad: 0.2179 (0.2164) loss: 0.9462 (0.9460) time: 0.1716 data: 0.0856 max mem: 8233 +Train: [10] [ 300/6250] eta: 0:18:35 lr: 0.000124 grad: 0.1994 (0.2103) loss: 0.9432 (0.9455) time: 0.1839 data: 0.0991 max mem: 8233 +Train: [10] [ 400/6250] eta: 0:18:15 lr: 0.000124 grad: 0.1812 (0.2077) loss: 0.9381 (0.9447) time: 0.1942 data: 0.1141 max mem: 8233 +Train: [10] [ 500/6250] eta: 0:17:36 lr: 0.000124 grad: 0.1892 (0.2074) loss: 0.9388 (0.9439) time: 0.2027 data: 0.1288 max mem: 8233 +Train: [10] [ 600/6250] eta: 0:16:54 lr: 0.000124 grad: 0.2027 (0.2077) loss: 0.9360 (0.9433) time: 0.1293 data: 0.0428 max mem: 8233 +Train: [10] [ 700/6250] eta: 0:16:26 lr: 0.000124 grad: 0.1771 (0.2075) loss: 0.9377 (0.9428) time: 0.1586 data: 0.0644 max mem: 8233 +Train: [10] [ 800/6250] eta: 0:16:09 lr: 0.000124 grad: 0.1818 (0.2070) loss: 0.9412 (0.9425) time: 0.1492 data: 0.0534 max mem: 8233 +Train: [10] [ 900/6250] eta: 0:15:45 lr: 0.000124 grad: 0.1914 (0.2062) loss: 0.9418 (0.9424) time: 0.1626 data: 0.0620 max mem: 8233 +Train: [10] [1000/6250] eta: 0:15:19 lr: 0.000124 grad: 0.2017 (0.2067) loss: 0.9385 (0.9422) time: 0.1689 data: 0.0851 max mem: 8233 +Train: [10] [1100/6250] eta: 0:14:54 lr: 0.000124 grad: 0.1980 (0.2068) loss: 0.9412 (0.9419) time: 0.1630 data: 0.0746 max mem: 8233 +Train: [10] [1200/6250] eta: 0:14:29 lr: 0.000124 grad: 0.1911 (0.2061) loss: 0.9388 (0.9417) time: 0.1533 data: 0.0540 max mem: 8233 +Train: [10] [1300/6250] eta: 0:14:06 lr: 0.000124 grad: 0.1779 (0.2053) loss: 0.9412 (0.9416) time: 0.1468 data: 0.0557 max mem: 8233 +Train: [10] [1400/6250] eta: 0:13:41 lr: 0.000124 grad: 0.2020 (0.2052) loss: 0.9399 (0.9415) time: 0.1537 data: 0.0643 max mem: 8233 +Train: [10] [1500/6250] eta: 0:13:22 lr: 0.000124 grad: 0.1909 (0.2052) loss: 0.9429 (0.9414) time: 0.1572 data: 0.0689 max mem: 8233 +Train: [10] [1600/6250] eta: 0:13:03 lr: 0.000124 grad: 0.1982 (0.2053) loss: 0.9405 (0.9414) time: 0.1220 data: 0.0511 max mem: 8233 +Train: [10] [1700/6250] eta: 0:12:42 lr: 0.000124 grad: 0.1909 (0.2049) loss: 0.9439 (0.9413) time: 0.1350 data: 0.0526 max mem: 8233 +Train: [10] [1800/6250] eta: 0:12:26 lr: 0.000124 grad: 0.1827 (0.2053) loss: 0.9432 (0.9412) time: 0.1767 data: 0.1115 max mem: 8233 +Train: [10] [1900/6250] eta: 0:12:08 lr: 0.000124 grad: 0.1766 (0.2047) loss: 0.9422 (0.9411) time: 0.1702 data: 0.0855 max mem: 8233 +Train: [10] [2000/6250] eta: 0:11:48 lr: 0.000124 grad: 0.1869 (0.2043) loss: 0.9389 (0.9411) time: 0.1356 data: 0.0482 max mem: 8233 +Train: [10] [2100/6250] eta: 0:11:31 lr: 0.000124 grad: 0.2026 (0.2042) loss: 0.9402 (0.9411) time: 0.1660 data: 0.0834 max mem: 8233 +Train: [10] [2200/6250] eta: 0:11:12 lr: 0.000124 grad: 0.1857 (0.2037) loss: 0.9403 (0.9410) time: 0.1584 data: 0.0860 max mem: 8233 +Train: [10] [2300/6250] eta: 0:10:58 lr: 0.000124 grad: 0.1894 (0.2036) loss: 0.9413 (0.9410) time: 0.1945 data: 0.1127 max mem: 8233 +Train: [10] [2400/6250] eta: 0:10:43 lr: 0.000124 grad: 0.1884 (0.2034) loss: 0.9364 (0.9409) time: 0.0901 data: 0.0084 max mem: 8233 +Train: [10] [2500/6250] eta: 0:10:24 lr: 0.000124 grad: 0.1842 (0.2029) loss: 0.9401 (0.9408) time: 0.1357 data: 0.0592 max mem: 8233 +Train: [10] [2600/6250] eta: 0:10:06 lr: 0.000124 grad: 0.2056 (0.2029) loss: 0.9405 (0.9408) time: 0.1619 data: 0.0799 max mem: 8233 +Train: [10] [2700/6250] eta: 0:09:49 lr: 0.000124 grad: 0.1825 (0.2027) loss: 0.9398 (0.9407) time: 0.1753 data: 0.0972 max mem: 8233 +Train: [10] [2800/6250] eta: 0:09:31 lr: 0.000124 grad: 0.1904 (0.2024) loss: 0.9374 (0.9407) time: 0.1537 data: 0.0675 max mem: 8233 +Train: [10] [2900/6250] eta: 0:09:15 lr: 0.000124 grad: 0.2016 (0.2020) loss: 0.9416 (0.9407) time: 0.1434 data: 0.0557 max mem: 8233 +Train: [10] [3000/6250] eta: 0:08:57 lr: 0.000124 grad: 0.2090 (0.2020) loss: 0.9396 (0.9407) time: 0.1363 data: 0.0652 max mem: 8233 +Train: [10] [3100/6250] eta: 0:08:42 lr: 0.000124 grad: 0.2027 (0.2018) loss: 0.9407 (0.9406) time: 0.1556 data: 0.0937 max mem: 8233 +Train: [10] [3200/6250] eta: 0:08:28 lr: 0.000124 grad: 0.1756 (0.2017) loss: 0.9410 (0.9406) time: 0.2751 data: 0.1983 max mem: 8233 +Train: [10] [3300/6250] eta: 0:08:10 lr: 0.000124 grad: 0.1877 (0.2013) loss: 0.9399 (0.9406) time: 0.1762 data: 0.1046 max mem: 8233 +Train: [10] [3400/6250] eta: 0:07:54 lr: 0.000124 grad: 0.2064 (0.2013) loss: 0.9402 (0.9406) time: 0.1732 data: 0.0936 max mem: 8233 +Train: [10] [3500/6250] eta: 0:07:38 lr: 0.000124 grad: 0.1851 (0.2012) loss: 0.9383 (0.9406) time: 0.1546 data: 0.0760 max mem: 8233 +Train: [10] [3600/6250] eta: 0:07:21 lr: 0.000124 grad: 0.2096 (0.2012) loss: 0.9393 (0.9405) time: 0.1622 data: 0.0785 max mem: 8233 +Train: [10] [3700/6250] eta: 0:07:06 lr: 0.000124 grad: 0.1861 (0.2015) loss: 0.9382 (0.9405) time: 0.2496 data: 0.1647 max mem: 8233 +Train: [10] [3800/6250] eta: 0:06:48 lr: 0.000124 grad: 0.1933 (0.2012) loss: 0.9381 (0.9404) time: 0.1618 data: 0.0864 max mem: 8233 +Train: [10] [3900/6250] eta: 0:06:31 lr: 0.000124 grad: 0.1940 (0.2013) loss: 0.9399 (0.9404) time: 0.1989 data: 0.1228 max mem: 8233 +Train: [10] [4000/6250] eta: 0:06:16 lr: 0.000124 grad: 0.1811 (0.2011) loss: 0.9376 (0.9403) time: 0.2035 data: 0.1057 max mem: 8233 +Train: [10] [4100/6250] eta: 0:05:59 lr: 0.000124 grad: 0.1959 (0.2010) loss: 0.9374 (0.9402) time: 0.2330 data: 0.1530 max mem: 8233 +Train: [10] [4200/6250] eta: 0:05:42 lr: 0.000124 grad: 0.1928 (0.2011) loss: 0.9387 (0.9402) time: 0.1700 data: 0.0801 max mem: 8233 +Train: [10] [4300/6250] eta: 0:05:26 lr: 0.000124 grad: 0.1925 (0.2009) loss: 0.9386 (0.9402) time: 0.1562 data: 0.0698 max mem: 8233 +Train: [10] [4400/6250] eta: 0:05:09 lr: 0.000124 grad: 0.1886 (0.2009) loss: 0.9361 (0.9402) time: 0.1830 data: 0.1013 max mem: 8233 +Train: [10] [4500/6250] eta: 0:04:52 lr: 0.000124 grad: 0.1862 (0.2008) loss: 0.9380 (0.9401) time: 0.1699 data: 0.0810 max mem: 8233 +Train: [10] [4600/6250] eta: 0:04:35 lr: 0.000124 grad: 0.1928 (0.2009) loss: 0.9355 (0.9401) time: 0.1400 data: 0.0389 max mem: 8233 +Train: [10] [4700/6250] eta: 0:04:19 lr: 0.000124 grad: 0.1859 (0.2009) loss: 0.9365 (0.9400) time: 0.1742 data: 0.1057 max mem: 8233 +Train: [10] [4800/6250] eta: 0:04:02 lr: 0.000124 grad: 0.1853 (0.2010) loss: 0.9387 (0.9399) time: 0.1289 data: 0.0484 max mem: 8233 +Train: [10] [4900/6250] eta: 0:03:45 lr: 0.000124 grad: 0.1936 (0.2009) loss: 0.9347 (0.9399) time: 0.1513 data: 0.0759 max mem: 8233 +Train: [10] [5000/6250] eta: 0:03:28 lr: 0.000124 grad: 0.1713 (0.2008) loss: 0.9392 (0.9398) time: 0.1821 data: 0.1035 max mem: 8233 +Train: [10] [5100/6250] eta: 0:03:11 lr: 0.000124 grad: 0.2193 (0.2009) loss: 0.9379 (0.9398) time: 0.2090 data: 0.1367 max mem: 8233 +Train: [10] [5200/6250] eta: 0:02:54 lr: 0.000124 grad: 0.2077 (0.2009) loss: 0.9368 (0.9397) time: 0.1430 data: 0.0612 max mem: 8233 +Train: [10] [5300/6250] eta: 0:02:38 lr: 0.000124 grad: 0.2103 (0.2010) loss: 0.9385 (0.9397) time: 0.1828 data: 0.1153 max mem: 8233 +Train: [10] [5400/6250] eta: 0:02:21 lr: 0.000124 grad: 0.1691 (0.2009) loss: 0.9367 (0.9396) time: 0.1678 data: 0.0939 max mem: 8233 +Train: [10] [5500/6250] eta: 0:02:05 lr: 0.000124 grad: 0.1986 (0.2010) loss: 0.9338 (0.9395) time: 0.2130 data: 0.1114 max mem: 8233 +Train: [10] [5600/6250] eta: 0:01:48 lr: 0.000124 grad: 0.1859 (0.2011) loss: 0.9343 (0.9394) time: 0.1528 data: 0.0756 max mem: 8233 +Train: [10] [5700/6250] eta: 0:01:31 lr: 0.000124 grad: 0.1912 (0.2010) loss: 0.9362 (0.9394) time: 0.1504 data: 0.0695 max mem: 8233 +Train: [10] [5800/6250] eta: 0:01:14 lr: 0.000124 grad: 0.1798 (0.2010) loss: 0.9359 (0.9393) time: 0.1789 data: 0.1006 max mem: 8233 +Train: [10] [5900/6250] eta: 0:00:58 lr: 0.000124 grad: 0.2216 (0.2010) loss: 0.9341 (0.9392) time: 0.1547 data: 0.0758 max mem: 8233 +Train: [10] [6000/6250] eta: 0:00:41 lr: 0.000124 grad: 0.1928 (0.2009) loss: 0.9353 (0.9392) time: 0.1503 data: 0.0729 max mem: 8233 +Train: [10] [6100/6250] eta: 0:00:24 lr: 0.000124 grad: 0.1771 (0.2008) loss: 0.9341 (0.9391) time: 0.1309 data: 0.0292 max mem: 8233 +Train: [10] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.1894 (0.2006) loss: 0.9376 (0.9391) time: 0.1923 data: 0.1042 max mem: 8233 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.1836 (0.2006) loss: 0.9380 (0.9391) time: 0.1682 data: 0.0784 max mem: 8233 +Train: [10] Total time: 0:17:22 (0.1668 s / it) +Averaged stats: lr: 0.000124 grad: 0.1836 (0.2006) loss: 0.9380 (0.9391) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:06:09 loss: 0.9456 (0.9456) time: 5.9571 data: 5.9311 max mem: 8233 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.9437 (0.9405) time: 0.0917 data: 0.0700 max mem: 8233 +Eval (hcp-train-subset): [10] Total time: 0:00:15 (0.2462 s / it) +Averaged stats (hcp-train-subset): loss: 0.9437 (0.9405) +Eval (hcp-val): [10] [ 0/62] eta: 0:06:44 loss: 0.9362 (0.9362) time: 6.5298 data: 6.4823 max mem: 8233 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.9357 (0.9360) time: 0.1064 data: 0.0860 max mem: 8233 +Eval (hcp-val): [10] Total time: 0:00:17 (0.2791 s / it) +Averaged stats (hcp-val): loss: 0.9357 (0.9360) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 10:00:04 lr: 0.000124 grad: 0.1449 (0.1449) loss: 0.9405 (0.9405) time: 5.7607 data: 5.5778 max mem: 8233 +Train: [11] [ 100/6250] eta: 0:22:58 lr: 0.000124 grad: 0.2151 (0.2016) loss: 0.9408 (0.9408) time: 0.1657 data: 0.0802 max mem: 8233 +Train: [11] [ 200/6250] eta: 0:20:49 lr: 0.000124 grad: 0.1826 (0.2054) loss: 0.9381 (0.9388) time: 0.1838 data: 0.1054 max mem: 8233 +Train: [11] [ 300/6250] eta: 0:19:06 lr: 0.000124 grad: 0.2093 (0.2026) loss: 0.9406 (0.9386) time: 0.1800 data: 0.0975 max mem: 8233 +Train: [11] [ 400/6250] eta: 0:18:21 lr: 0.000124 grad: 0.1913 (0.2019) loss: 0.9348 (0.9377) time: 0.1913 data: 0.0970 max mem: 8233 +Train: [11] [ 500/6250] eta: 0:17:53 lr: 0.000124 grad: 0.1825 (0.2019) loss: 0.9374 (0.9375) time: 0.2168 data: 0.1379 max mem: 8233 +Train: [11] [ 600/6250] eta: 0:17:14 lr: 0.000124 grad: 0.1841 (0.2002) loss: 0.9367 (0.9374) time: 0.1712 data: 0.0865 max mem: 8233 +Train: [11] [ 700/6250] eta: 0:16:29 lr: 0.000124 grad: 0.1754 (0.1987) loss: 0.9363 (0.9373) time: 0.1527 data: 0.0713 max mem: 8233 +Train: [11] [ 800/6250] eta: 0:16:12 lr: 0.000124 grad: 0.1844 (0.1968) loss: 0.9369 (0.9373) time: 0.1792 data: 0.0703 max mem: 8233 +Train: [11] [ 900/6250] eta: 0:15:45 lr: 0.000124 grad: 0.1789 (0.1977) loss: 0.9372 (0.9373) time: 0.1724 data: 0.0713 max mem: 8233 +Train: [11] [1000/6250] eta: 0:15:17 lr: 0.000124 grad: 0.1879 (0.1978) loss: 0.9369 (0.9373) time: 0.1665 data: 0.0724 max mem: 8233 +Train: [11] [1100/6250] eta: 0:14:58 lr: 0.000124 grad: 0.1820 (0.1969) loss: 0.9399 (0.9372) time: 0.2161 data: 0.1378 max mem: 8233 +Train: [11] [1200/6250] eta: 0:14:32 lr: 0.000124 grad: 0.1774 (0.1966) loss: 0.9344 (0.9372) time: 0.1724 data: 0.0859 max mem: 8233 +Train: [11] [1300/6250] eta: 0:14:21 lr: 0.000124 grad: 0.1800 (0.1964) loss: 0.9392 (0.9372) time: 0.1615 data: 0.0564 max mem: 8233 +Train: [11] [1400/6250] eta: 0:14:02 lr: 0.000124 grad: 0.1789 (0.1961) loss: 0.9366 (0.9372) time: 0.1489 data: 0.0623 max mem: 8233 +Train: [11] [1500/6250] eta: 0:13:56 lr: 0.000124 grad: 0.1875 (0.1959) loss: 0.9357 (0.9372) time: 0.2885 data: 0.2057 max mem: 8233 +Train: [11] [1600/6250] eta: 0:13:42 lr: 0.000124 grad: 0.2036 (0.1957) loss: 0.9375 (0.9371) time: 0.1819 data: 0.0851 max mem: 8233 +Train: [11] [1700/6250] eta: 0:13:23 lr: 0.000124 grad: 0.2034 (0.1958) loss: 0.9348 (0.9371) time: 0.1919 data: 0.0784 max mem: 8233 +Train: [11] [1800/6250] eta: 0:13:03 lr: 0.000124 grad: 0.1902 (0.1958) loss: 0.9381 (0.9369) time: 0.1727 data: 0.1011 max mem: 8233 +Train: [11] [1900/6250] eta: 0:12:44 lr: 0.000124 grad: 0.1889 (0.1960) loss: 0.9312 (0.9368) time: 0.1542 data: 0.0691 max mem: 8233 +Train: [11] [2000/6250] eta: 0:12:23 lr: 0.000124 grad: 0.2068 (0.1957) loss: 0.9351 (0.9368) time: 0.1433 data: 0.0495 max mem: 8233 +Train: [11] [2100/6250] eta: 0:12:05 lr: 0.000124 grad: 0.1831 (0.1955) loss: 0.9371 (0.9368) time: 0.2009 data: 0.1169 max mem: 8233 +Train: [11] [2200/6250] eta: 0:11:47 lr: 0.000124 grad: 0.1830 (0.1953) loss: 0.9376 (0.9367) time: 0.1759 data: 0.0883 max mem: 8233 +Train: [11] [2300/6250] eta: 0:11:27 lr: 0.000124 grad: 0.1838 (0.1951) loss: 0.9355 (0.9366) time: 0.1706 data: 0.0927 max mem: 8233 +Train: [11] [2400/6250] eta: 0:11:07 lr: 0.000124 grad: 0.1747 (0.1946) loss: 0.9364 (0.9366) time: 0.1434 data: 0.0596 max mem: 8233 +Train: [11] [2500/6250] eta: 0:10:50 lr: 0.000124 grad: 0.1796 (0.1943) loss: 0.9381 (0.9366) time: 0.1888 data: 0.1127 max mem: 8233 +Train: [11] [2600/6250] eta: 0:10:32 lr: 0.000124 grad: 0.2152 (0.1942) loss: 0.9350 (0.9366) time: 0.1672 data: 0.0873 max mem: 8233 +Train: [11] [2700/6250] eta: 0:10:12 lr: 0.000124 grad: 0.1731 (0.1939) loss: 0.9352 (0.9366) time: 0.1876 data: 0.1058 max mem: 8233 +Train: [11] [2800/6250] eta: 0:09:55 lr: 0.000124 grad: 0.1815 (0.1936) loss: 0.9374 (0.9366) time: 0.1388 data: 0.0574 max mem: 8233 +Train: [11] [2900/6250] eta: 0:09:38 lr: 0.000124 grad: 0.1840 (0.1934) loss: 0.9376 (0.9366) time: 0.1894 data: 0.1019 max mem: 8233 +Train: [11] [3000/6250] eta: 0:09:19 lr: 0.000124 grad: 0.1935 (0.1933) loss: 0.9318 (0.9365) time: 0.1840 data: 0.1056 max mem: 8233 +Train: [11] [3100/6250] eta: 0:09:04 lr: 0.000124 grad: 0.1808 (0.1931) loss: 0.9374 (0.9365) time: 0.2775 data: 0.1885 max mem: 8233 +Train: [11] [3200/6250] eta: 0:08:45 lr: 0.000124 grad: 0.1781 (0.1932) loss: 0.9365 (0.9365) time: 0.1760 data: 0.0969 max mem: 8233 +Train: [11] [3300/6250] eta: 0:08:26 lr: 0.000124 grad: 0.1836 (0.1928) loss: 0.9346 (0.9365) time: 0.1606 data: 0.0839 max mem: 8233 +Train: [11] [3400/6250] eta: 0:08:11 lr: 0.000124 grad: 0.1849 (0.1928) loss: 0.9372 (0.9365) time: 0.2654 data: 0.1870 max mem: 8233 +Train: [11] [3500/6250] eta: 0:07:52 lr: 0.000124 grad: 0.1733 (0.1925) loss: 0.9359 (0.9364) time: 0.1490 data: 0.0716 max mem: 8233 +Train: [11] [3600/6250] eta: 0:07:34 lr: 0.000124 grad: 0.1781 (0.1925) loss: 0.9367 (0.9364) time: 0.1599 data: 0.0845 max mem: 8233 +Train: [11] [3700/6250] eta: 0:07:16 lr: 0.000124 grad: 0.1782 (0.1922) loss: 0.9354 (0.9364) time: 0.1603 data: 0.0814 max mem: 8233 +Train: [11] [3800/6250] eta: 0:07:00 lr: 0.000124 grad: 0.1977 (0.1922) loss: 0.9317 (0.9363) time: 0.2210 data: 0.1439 max mem: 8233 +Train: [11] [3900/6250] eta: 0:06:45 lr: 0.000124 grad: 0.1871 (0.1922) loss: 0.9376 (0.9363) time: 0.1902 data: 0.0947 max mem: 8233 +Train: [11] [4000/6250] eta: 0:06:28 lr: 0.000123 grad: 0.1733 (0.1921) loss: 0.9336 (0.9363) time: 0.2124 data: 0.1489 max mem: 8233 +Train: [11] [4100/6250] eta: 0:06:11 lr: 0.000123 grad: 0.2015 (0.1922) loss: 0.9347 (0.9362) time: 0.1673 data: 0.0959 max mem: 8233 +Train: [11] [4200/6250] eta: 0:05:56 lr: 0.000123 grad: 0.1938 (0.1922) loss: 0.9320 (0.9361) time: 0.2054 data: 0.1240 max mem: 8233 +Train: [11] [4300/6250] eta: 0:05:38 lr: 0.000123 grad: 0.1896 (0.1922) loss: 0.9346 (0.9360) time: 0.1866 data: 0.1179 max mem: 8233 +Train: [11] [4400/6250] eta: 0:05:21 lr: 0.000123 grad: 0.1957 (0.1922) loss: 0.9332 (0.9359) time: 0.1402 data: 0.0681 max mem: 8233 +Train: [11] [4500/6250] eta: 0:05:04 lr: 0.000123 grad: 0.1690 (0.1923) loss: 0.9351 (0.9358) time: 0.2289 data: 0.1503 max mem: 8233 +Train: [11] [4600/6250] eta: 0:04:46 lr: 0.000123 grad: 0.1772 (0.1922) loss: 0.9338 (0.9358) time: 0.1610 data: 0.0697 max mem: 8233 +Train: [11] [4700/6250] eta: 0:04:29 lr: 0.000123 grad: 0.1827 (0.1921) loss: 0.9321 (0.9357) time: 0.1474 data: 0.0643 max mem: 8233 +Train: [11] [4800/6250] eta: 0:04:11 lr: 0.000123 grad: 0.1845 (0.1920) loss: 0.9329 (0.9357) time: 0.1751 data: 0.0879 max mem: 8233 +Train: [11] [4900/6250] eta: 0:03:54 lr: 0.000123 grad: 0.1734 (0.1919) loss: 0.9333 (0.9357) time: 0.1546 data: 0.0747 max mem: 8233 +Train: [11] [5000/6250] eta: 0:03:37 lr: 0.000123 grad: 0.1736 (0.1918) loss: 0.9366 (0.9356) time: 0.3386 data: 0.2086 max mem: 8233 +Train: [11] [5100/6250] eta: 0:03:19 lr: 0.000123 grad: 0.1904 (0.1918) loss: 0.9314 (0.9356) time: 0.1731 data: 0.0943 max mem: 8233 +Train: [11] [5200/6250] eta: 0:03:01 lr: 0.000123 grad: 0.1817 (0.1917) loss: 0.9330 (0.9356) time: 0.1750 data: 0.0988 max mem: 8233 +Train: [11] [5300/6250] eta: 0:02:44 lr: 0.000123 grad: 0.1790 (0.1914) loss: 0.9309 (0.9355) time: 0.1217 data: 0.0334 max mem: 8233 +Train: [11] [5400/6250] eta: 0:02:26 lr: 0.000123 grad: 0.1830 (0.1914) loss: 0.9307 (0.9355) time: 0.1740 data: 0.0975 max mem: 8233 +Train: [11] [5500/6250] eta: 0:02:09 lr: 0.000123 grad: 0.1668 (0.1911) loss: 0.9353 (0.9355) time: 0.1579 data: 0.0688 max mem: 8233 +Train: [11] [5600/6250] eta: 0:01:52 lr: 0.000123 grad: 0.1709 (0.1910) loss: 0.9329 (0.9355) time: 0.2243 data: 0.1459 max mem: 8233 +Train: [11] [5700/6250] eta: 0:01:34 lr: 0.000123 grad: 0.1826 (0.1909) loss: 0.9295 (0.9354) time: 0.1345 data: 0.0479 max mem: 8233 +Train: [11] [5800/6250] eta: 0:01:17 lr: 0.000123 grad: 0.1940 (0.1909) loss: 0.9346 (0.9354) time: 0.1770 data: 0.0936 max mem: 8233 +Train: [11] [5900/6250] eta: 0:01:00 lr: 0.000123 grad: 0.1714 (0.1908) loss: 0.9331 (0.9354) time: 0.1875 data: 0.1200 max mem: 8233 +Train: [11] [6000/6250] eta: 0:00:43 lr: 0.000123 grad: 0.1838 (0.1908) loss: 0.9333 (0.9353) time: 0.1675 data: 0.0674 max mem: 8233 +Train: [11] [6100/6250] eta: 0:00:25 lr: 0.000123 grad: 0.1721 (0.1906) loss: 0.9318 (0.9353) time: 0.1046 data: 0.0003 max mem: 8233 +Train: [11] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.1886 (0.1907) loss: 0.9324 (0.9352) time: 0.1654 data: 0.0793 max mem: 8233 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.1660 (0.1907) loss: 0.9363 (0.9352) time: 0.1541 data: 0.0733 max mem: 8233 +Train: [11] Total time: 0:18:11 (0.1747 s / it) +Averaged stats: lr: 0.000123 grad: 0.1660 (0.1907) loss: 0.9363 (0.9352) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:04:39 loss: 0.9434 (0.9434) time: 4.5159 data: 4.4645 max mem: 8233 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.9355 (0.9354) time: 0.1330 data: 0.1113 max mem: 8233 +Eval (hcp-train-subset): [11] Total time: 0:00:15 (0.2455 s / it) +Averaged stats (hcp-train-subset): loss: 0.9355 (0.9354) +Eval (hcp-val): [11] [ 0/62] eta: 0:06:54 loss: 0.9277 (0.9277) time: 6.6826 data: 6.6552 max mem: 8233 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.9314 (0.9316) time: 0.1629 data: 0.1422 max mem: 8233 +Eval (hcp-val): [11] Total time: 0:00:16 (0.2617 s / it) +Averaged stats (hcp-val): loss: 0.9314 (0.9316) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 13:03:37 lr: 0.000123 grad: 0.1942 (0.1942) loss: 0.9492 (0.9492) time: 7.5227 data: 7.4161 max mem: 8233 +Train: [12] [ 100/6250] eta: 0:24:45 lr: 0.000123 grad: 0.2018 (0.1824) loss: 0.9412 (0.9415) time: 0.1634 data: 0.0680 max mem: 8233 +Train: [12] [ 200/6250] eta: 0:22:05 lr: 0.000123 grad: 0.1918 (0.1859) loss: 0.9329 (0.9390) time: 0.2226 data: 0.1325 max mem: 8233 +Train: [12] [ 300/6250] eta: 0:21:01 lr: 0.000123 grad: 0.1667 (0.1865) loss: 0.9401 (0.9372) time: 0.2180 data: 0.1316 max mem: 8233 +Train: [12] [ 400/6250] eta: 0:20:14 lr: 0.000123 grad: 0.1875 (0.1889) loss: 0.9338 (0.9361) time: 0.2342 data: 0.1333 max mem: 8233 +Train: [12] [ 500/6250] eta: 0:19:32 lr: 0.000123 grad: 0.1840 (0.1902) loss: 0.9335 (0.9356) time: 0.2106 data: 0.1352 max mem: 8233 +Train: [12] [ 600/6250] eta: 0:18:44 lr: 0.000123 grad: 0.1621 (0.1903) loss: 0.9326 (0.9350) time: 0.1779 data: 0.1054 max mem: 8233 +Train: [12] [ 700/6250] eta: 0:18:07 lr: 0.000123 grad: 0.1730 (0.1898) loss: 0.9335 (0.9347) time: 0.1415 data: 0.0643 max mem: 8233 +Train: [12] [ 800/6250] eta: 0:17:29 lr: 0.000123 grad: 0.1931 (0.1887) loss: 0.9324 (0.9344) time: 0.1488 data: 0.0747 max mem: 8233 +Train: [12] [ 900/6250] eta: 0:16:54 lr: 0.000123 grad: 0.1675 (0.1882) loss: 0.9345 (0.9343) time: 0.1628 data: 0.0652 max mem: 8233 +Train: [12] [1000/6250] eta: 0:16:19 lr: 0.000123 grad: 0.1828 (0.1878) loss: 0.9373 (0.9340) time: 0.1560 data: 0.0622 max mem: 8233 +Train: [12] [1100/6250] eta: 0:15:48 lr: 0.000123 grad: 0.1838 (0.1879) loss: 0.9296 (0.9337) time: 0.1639 data: 0.0555 max mem: 8233 +Train: [12] [1200/6250] eta: 0:15:16 lr: 0.000123 grad: 0.1829 (0.1878) loss: 0.9307 (0.9335) time: 0.1549 data: 0.0675 max mem: 8233 +Train: [12] [1300/6250] eta: 0:14:47 lr: 0.000123 grad: 0.1826 (0.1875) loss: 0.9350 (0.9334) time: 0.1781 data: 0.0855 max mem: 8233 +Train: [12] [1400/6250] eta: 0:14:24 lr: 0.000123 grad: 0.1753 (0.1880) loss: 0.9329 (0.9332) time: 0.1053 data: 0.0006 max mem: 8233 +Train: [12] [1500/6250] eta: 0:14:04 lr: 0.000123 grad: 0.1811 (0.1876) loss: 0.9322 (0.9330) time: 0.1505 data: 0.0690 max mem: 8233 +Train: [12] [1600/6250] eta: 0:13:45 lr: 0.000123 grad: 0.1778 (0.1877) loss: 0.9304 (0.9329) time: 0.1703 data: 0.0704 max mem: 8233 +Train: [12] [1700/6250] eta: 0:13:37 lr: 0.000123 grad: 0.1918 (0.1877) loss: 0.9311 (0.9328) time: 0.3768 data: 0.2845 max mem: 8233 +Train: [12] [1800/6250] eta: 0:13:11 lr: 0.000123 grad: 0.1574 (0.1874) loss: 0.9344 (0.9328) time: 0.1543 data: 0.0565 max mem: 8233 +Train: [12] [1900/6250] eta: 0:12:57 lr: 0.000123 grad: 0.1860 (0.1873) loss: 0.9278 (0.9328) time: 0.1123 data: 0.0003 max mem: 8233 +Train: [12] [2000/6250] eta: 0:12:36 lr: 0.000123 grad: 0.1721 (0.1869) loss: 0.9316 (0.9327) time: 0.1758 data: 0.1067 max mem: 8233 +Train: [12] [2100/6250] eta: 0:12:13 lr: 0.000123 grad: 0.1734 (0.1863) loss: 0.9337 (0.9327) time: 0.1385 data: 0.0537 max mem: 8233 +Train: [12] [2200/6250] eta: 0:11:54 lr: 0.000123 grad: 0.1707 (0.1858) loss: 0.9324 (0.9327) time: 0.2017 data: 0.1156 max mem: 8233 +Train: [12] [2300/6250] eta: 0:11:35 lr: 0.000123 grad: 0.1699 (0.1857) loss: 0.9301 (0.9326) time: 0.1332 data: 0.0003 max mem: 8233 +Train: [12] [2400/6250] eta: 0:11:16 lr: 0.000123 grad: 0.1817 (0.1855) loss: 0.9356 (0.9326) time: 0.1667 data: 0.0865 max mem: 8233 +Train: [12] [2500/6250] eta: 0:10:58 lr: 0.000123 grad: 0.1755 (0.1851) loss: 0.9354 (0.9326) time: 0.1374 data: 0.0564 max mem: 8233 +Train: [12] [2600/6250] eta: 0:10:39 lr: 0.000123 grad: 0.1784 (0.1849) loss: 0.9326 (0.9326) time: 0.1489 data: 0.0630 max mem: 8233 +Train: [12] [2700/6250] eta: 0:10:22 lr: 0.000123 grad: 0.1698 (0.1848) loss: 0.9302 (0.9326) time: 0.2362 data: 0.1517 max mem: 8233 +Train: [12] [2800/6250] eta: 0:10:01 lr: 0.000123 grad: 0.1864 (0.1847) loss: 0.9323 (0.9325) time: 0.1397 data: 0.0453 max mem: 8233 +Train: [12] [2900/6250] eta: 0:09:42 lr: 0.000123 grad: 0.1694 (0.1845) loss: 0.9308 (0.9324) time: 0.1766 data: 0.1032 max mem: 8233 +Train: [12] [3000/6250] eta: 0:09:24 lr: 0.000123 grad: 0.1715 (0.1844) loss: 0.9334 (0.9324) time: 0.1573 data: 0.0722 max mem: 8233 +Train: [12] [3100/6250] eta: 0:09:04 lr: 0.000123 grad: 0.1724 (0.1843) loss: 0.9308 (0.9324) time: 0.1562 data: 0.0778 max mem: 8233 +Train: [12] [3200/6250] eta: 0:08:46 lr: 0.000123 grad: 0.1571 (0.1840) loss: 0.9321 (0.9324) time: 0.1693 data: 0.0609 max mem: 8233 +Train: [12] [3300/6250] eta: 0:08:28 lr: 0.000123 grad: 0.1676 (0.1839) loss: 0.9312 (0.9323) time: 0.1182 data: 0.0332 max mem: 8233 +Train: [12] [3400/6250] eta: 0:08:10 lr: 0.000123 grad: 0.1560 (0.1835) loss: 0.9334 (0.9324) time: 0.1538 data: 0.0768 max mem: 8233 +Train: [12] [3500/6250] eta: 0:07:52 lr: 0.000123 grad: 0.1807 (0.1835) loss: 0.9284 (0.9324) time: 0.1664 data: 0.0672 max mem: 8233 +Train: [12] [3600/6250] eta: 0:07:36 lr: 0.000123 grad: 0.1609 (0.1834) loss: 0.9307 (0.9323) time: 0.1761 data: 0.0799 max mem: 8233 +Train: [12] [3700/6250] eta: 0:07:18 lr: 0.000123 grad: 0.1773 (0.1831) loss: 0.9317 (0.9323) time: 0.1875 data: 0.1037 max mem: 8233 +Train: [12] [3800/6250] eta: 0:07:00 lr: 0.000123 grad: 0.1736 (0.1829) loss: 0.9290 (0.9323) time: 0.1695 data: 0.0936 max mem: 8233 +Train: [12] [3900/6250] eta: 0:06:44 lr: 0.000123 grad: 0.1767 (0.1829) loss: 0.9334 (0.9323) time: 0.1117 data: 0.0214 max mem: 8233 +Train: [12] [4000/6250] eta: 0:06:25 lr: 0.000123 grad: 0.1706 (0.1826) loss: 0.9321 (0.9323) time: 0.1613 data: 0.0755 max mem: 8233 +Train: [12] [4100/6250] eta: 0:06:08 lr: 0.000123 grad: 0.1663 (0.1823) loss: 0.9292 (0.9324) time: 0.1626 data: 0.0934 max mem: 8233 +Train: [12] [4200/6250] eta: 0:05:51 lr: 0.000123 grad: 0.1650 (0.1820) loss: 0.9295 (0.9324) time: 0.1834 data: 0.1097 max mem: 8233 +Train: [12] [4300/6250] eta: 0:05:34 lr: 0.000123 grad: 0.1614 (0.1818) loss: 0.9333 (0.9324) time: 0.1721 data: 0.0954 max mem: 8233 +Train: [12] [4400/6250] eta: 0:05:17 lr: 0.000123 grad: 0.1757 (0.1816) loss: 0.9342 (0.9324) time: 0.1542 data: 0.0724 max mem: 8233 +Train: [12] [4500/6250] eta: 0:05:00 lr: 0.000123 grad: 0.1707 (0.1814) loss: 0.9314 (0.9324) time: 0.1741 data: 0.1004 max mem: 8233 +Train: [12] [4600/6250] eta: 0:04:43 lr: 0.000123 grad: 0.1716 (0.1814) loss: 0.9323 (0.9323) time: 0.2047 data: 0.1444 max mem: 8233 +Train: [12] [4700/6250] eta: 0:04:26 lr: 0.000123 grad: 0.1832 (0.1813) loss: 0.9306 (0.9323) time: 0.1213 data: 0.0003 max mem: 8233 +Train: [12] [4800/6250] eta: 0:04:08 lr: 0.000123 grad: 0.1711 (0.1812) loss: 0.9295 (0.9323) time: 0.1654 data: 0.0821 max mem: 8233 +Train: [12] [4900/6250] eta: 0:03:51 lr: 0.000123 grad: 0.1613 (0.1811) loss: 0.9298 (0.9323) time: 0.1733 data: 0.0835 max mem: 8233 +Train: [12] [5000/6250] eta: 0:03:35 lr: 0.000123 grad: 0.1611 (0.1809) loss: 0.9293 (0.9322) time: 0.2859 data: 0.1852 max mem: 8233 +Train: [12] [5100/6250] eta: 0:03:17 lr: 0.000123 grad: 0.1592 (0.1807) loss: 0.9344 (0.9323) time: 0.1574 data: 0.0737 max mem: 8233 +Train: [12] [5200/6250] eta: 0:03:00 lr: 0.000123 grad: 0.1643 (0.1805) loss: 0.9300 (0.9323) time: 0.1218 data: 0.0218 max mem: 8233 +Train: [12] [5300/6250] eta: 0:02:43 lr: 0.000123 grad: 0.1696 (0.1803) loss: 0.9308 (0.9323) time: 0.1548 data: 0.0728 max mem: 8233 +Train: [12] [5400/6250] eta: 0:02:26 lr: 0.000123 grad: 0.1579 (0.1802) loss: 0.9344 (0.9322) time: 0.0930 data: 0.0136 max mem: 8233 +Train: [12] [5500/6250] eta: 0:02:09 lr: 0.000123 grad: 0.1755 (0.1801) loss: 0.9287 (0.9322) time: 0.1473 data: 0.0684 max mem: 8233 +Train: [12] [5600/6250] eta: 0:01:51 lr: 0.000123 grad: 0.1546 (0.1799) loss: 0.9280 (0.9322) time: 0.1648 data: 0.0794 max mem: 8233 +Train: [12] [5700/6250] eta: 0:01:34 lr: 0.000123 grad: 0.1792 (0.1798) loss: 0.9307 (0.9322) time: 0.1566 data: 0.0734 max mem: 8233 +Train: [12] [5800/6250] eta: 0:01:17 lr: 0.000123 grad: 0.1610 (0.1797) loss: 0.9295 (0.9321) time: 0.1770 data: 0.1013 max mem: 8233 +Train: [12] [5900/6250] eta: 0:01:00 lr: 0.000123 grad: 0.1648 (0.1797) loss: 0.9314 (0.9321) time: 0.1588 data: 0.0887 max mem: 8233 +Train: [12] [6000/6250] eta: 0:00:42 lr: 0.000123 grad: 0.1797 (0.1796) loss: 0.9273 (0.9321) time: 0.1496 data: 0.0738 max mem: 8233 +Train: [12] [6100/6250] eta: 0:00:25 lr: 0.000123 grad: 0.1677 (0.1796) loss: 0.9289 (0.9321) time: 0.1087 data: 0.0003 max mem: 8233 +Train: [12] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.1671 (0.1795) loss: 0.9324 (0.9321) time: 0.1714 data: 0.1014 max mem: 8233 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.1784 (0.1795) loss: 0.9290 (0.9320) time: 0.1558 data: 0.0760 max mem: 8233 +Train: [12] Total time: 0:17:58 (0.1725 s / it) +Averaged stats: lr: 0.000123 grad: 0.1784 (0.1795) loss: 0.9290 (0.9320) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:03:25 loss: 0.9347 (0.9347) time: 3.3071 data: 3.2151 max mem: 8233 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.9347 (0.9319) time: 0.1265 data: 0.1059 max mem: 8233 +Eval (hcp-train-subset): [12] Total time: 0:00:13 (0.2217 s / it) +Averaged stats (hcp-train-subset): loss: 0.9347 (0.9319) +Eval (hcp-val): [12] [ 0/62] eta: 0:03:05 loss: 0.9215 (0.9215) time: 2.9970 data: 2.9368 max mem: 8233 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.9276 (0.9272) time: 0.1504 data: 0.1297 max mem: 8233 +Eval (hcp-val): [12] Total time: 0:00:14 (0.2268 s / it) +Averaged stats (hcp-val): loss: 0.9276 (0.9272) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 9:04:21 lr: 0.000123 grad: 0.1458 (0.1458) loss: 0.9527 (0.9527) time: 5.2259 data: 4.9359 max mem: 8233 +Train: [13] [ 100/6250] eta: 0:23:33 lr: 0.000123 grad: 0.1940 (0.2043) loss: 0.9297 (0.9324) time: 0.1685 data: 0.0691 max mem: 8233 +Train: [13] [ 200/6250] eta: 0:20:27 lr: 0.000123 grad: 0.1787 (0.1990) loss: 0.9299 (0.9305) time: 0.1422 data: 0.0502 max mem: 8233 +Train: [13] [ 300/6250] eta: 0:19:44 lr: 0.000123 grad: 0.1688 (0.1916) loss: 0.9324 (0.9307) time: 0.2016 data: 0.1039 max mem: 8233 +Train: [13] [ 400/6250] eta: 0:19:18 lr: 0.000123 grad: 0.1935 (0.1900) loss: 0.9281 (0.9304) time: 0.2191 data: 0.1204 max mem: 8233 +Train: [13] [ 500/6250] eta: 0:18:26 lr: 0.000123 grad: 0.1677 (0.1869) loss: 0.9316 (0.9303) time: 0.1898 data: 0.1059 max mem: 8233 +Train: [13] [ 600/6250] eta: 0:18:06 lr: 0.000123 grad: 0.1676 (0.1860) loss: 0.9306 (0.9304) time: 0.2354 data: 0.1607 max mem: 8233 +Train: [13] [ 700/6250] eta: 0:17:37 lr: 0.000123 grad: 0.1727 (0.1842) loss: 0.9313 (0.9304) time: 0.1793 data: 0.0864 max mem: 8233 +Train: [13] [ 800/6250] eta: 0:17:06 lr: 0.000123 grad: 0.1581 (0.1831) loss: 0.9300 (0.9301) time: 0.1627 data: 0.0745 max mem: 8233 +Train: [13] [ 900/6250] eta: 0:16:38 lr: 0.000123 grad: 0.1741 (0.1824) loss: 0.9285 (0.9299) time: 0.1762 data: 0.0966 max mem: 8233 +Train: [13] [1000/6250] eta: 0:16:07 lr: 0.000123 grad: 0.1673 (0.1817) loss: 0.9299 (0.9297) time: 0.1532 data: 0.0764 max mem: 8233 +Train: [13] [1100/6250] eta: 0:15:38 lr: 0.000123 grad: 0.1752 (0.1814) loss: 0.9274 (0.9296) time: 0.1669 data: 0.0806 max mem: 8233 +Train: [13] [1200/6250] eta: 0:15:13 lr: 0.000123 grad: 0.1713 (0.1813) loss: 0.9264 (0.9294) time: 0.1685 data: 0.0755 max mem: 8233 +Train: [13] [1300/6250] eta: 0:14:47 lr: 0.000123 grad: 0.1568 (0.1813) loss: 0.9275 (0.9293) time: 0.1600 data: 0.0610 max mem: 8233 +Train: [13] [1400/6250] eta: 0:14:22 lr: 0.000123 grad: 0.1661 (0.1813) loss: 0.9306 (0.9292) time: 0.1458 data: 0.0526 max mem: 8233 +Train: [13] [1500/6250] eta: 0:14:00 lr: 0.000123 grad: 0.1705 (0.1811) loss: 0.9273 (0.9291) time: 0.1700 data: 0.0831 max mem: 8233 +Train: [13] [1600/6250] eta: 0:13:42 lr: 0.000123 grad: 0.1643 (0.1806) loss: 0.9280 (0.9289) time: 0.1647 data: 0.0901 max mem: 8233 +Train: [13] [1700/6250] eta: 0:13:20 lr: 0.000123 grad: 0.1703 (0.1804) loss: 0.9255 (0.9288) time: 0.1531 data: 0.0674 max mem: 8233 +Train: [13] [1800/6250] eta: 0:13:03 lr: 0.000123 grad: 0.1638 (0.1802) loss: 0.9273 (0.9288) time: 0.1590 data: 0.0819 max mem: 8233 +Train: [13] [1900/6250] eta: 0:12:49 lr: 0.000123 grad: 0.1569 (0.1798) loss: 0.9285 (0.9287) time: 0.1762 data: 0.0873 max mem: 8233 +Train: [13] [2000/6250] eta: 0:12:31 lr: 0.000123 grad: 0.1714 (0.1799) loss: 0.9271 (0.9287) time: 0.1105 data: 0.0003 max mem: 8233 +Train: [13] [2100/6250] eta: 0:12:19 lr: 0.000123 grad: 0.1681 (0.1795) loss: 0.9268 (0.9288) time: 0.0973 data: 0.0004 max mem: 8233 +Train: [13] [2200/6250] eta: 0:11:58 lr: 0.000123 grad: 0.1600 (0.1792) loss: 0.9293 (0.9287) time: 0.1717 data: 0.0966 max mem: 8233 +Train: [13] [2300/6250] eta: 0:11:36 lr: 0.000123 grad: 0.1771 (0.1792) loss: 0.9265 (0.9286) time: 0.1755 data: 0.0982 max mem: 8233 +Train: [13] [2400/6250] eta: 0:11:17 lr: 0.000123 grad: 0.1540 (0.1787) loss: 0.9283 (0.9286) time: 0.1529 data: 0.0723 max mem: 8233 +Train: [13] [2500/6250] eta: 0:10:57 lr: 0.000123 grad: 0.1715 (0.1785) loss: 0.9260 (0.9286) time: 0.1618 data: 0.0920 max mem: 8233 +Train: [13] [2600/6250] eta: 0:10:39 lr: 0.000123 grad: 0.1669 (0.1783) loss: 0.9286 (0.9285) time: 0.1681 data: 0.0903 max mem: 8233 +Train: [13] [2700/6250] eta: 0:10:22 lr: 0.000123 grad: 0.1634 (0.1781) loss: 0.9309 (0.9286) time: 0.2096 data: 0.1246 max mem: 8233 +Train: [13] [2800/6250] eta: 0:10:04 lr: 0.000123 grad: 0.1708 (0.1778) loss: 0.9286 (0.9286) time: 0.1648 data: 0.0850 max mem: 8233 +Train: [13] [2900/6250] eta: 0:09:46 lr: 0.000123 grad: 0.1642 (0.1776) loss: 0.9280 (0.9285) time: 0.1981 data: 0.1048 max mem: 8233 +Train: [13] [3000/6250] eta: 0:09:28 lr: 0.000123 grad: 0.1610 (0.1773) loss: 0.9295 (0.9285) time: 0.1597 data: 0.0696 max mem: 8233 +Train: [13] [3100/6250] eta: 0:09:09 lr: 0.000123 grad: 0.1746 (0.1771) loss: 0.9279 (0.9286) time: 0.1547 data: 0.0745 max mem: 8233 +Train: [13] [3200/6250] eta: 0:08:51 lr: 0.000123 grad: 0.1684 (0.1771) loss: 0.9302 (0.9286) time: 0.2360 data: 0.1635 max mem: 8233 +Train: [13] [3300/6250] eta: 0:08:34 lr: 0.000123 grad: 0.1703 (0.1768) loss: 0.9298 (0.9286) time: 0.2367 data: 0.1444 max mem: 8233 +Train: [13] [3400/6250] eta: 0:08:17 lr: 0.000123 grad: 0.1631 (0.1766) loss: 0.9322 (0.9286) time: 0.2462 data: 0.1507 max mem: 8233 +Train: [13] [3500/6250] eta: 0:07:58 lr: 0.000123 grad: 0.1796 (0.1767) loss: 0.9291 (0.9286) time: 0.1605 data: 0.0736 max mem: 8233 +Train: [13] [3600/6250] eta: 0:07:40 lr: 0.000123 grad: 0.1693 (0.1766) loss: 0.9262 (0.9286) time: 0.1373 data: 0.0514 max mem: 8233 +Train: [13] [3700/6250] eta: 0:07:21 lr: 0.000122 grad: 0.1789 (0.1765) loss: 0.9290 (0.9286) time: 0.1493 data: 0.0700 max mem: 8233 +Train: [13] [3800/6250] eta: 0:07:04 lr: 0.000122 grad: 0.1657 (0.1765) loss: 0.9279 (0.9286) time: 0.1761 data: 0.0723 max mem: 8233 +Train: [13] [3900/6250] eta: 0:06:46 lr: 0.000122 grad: 0.1603 (0.1764) loss: 0.9292 (0.9286) time: 0.1604 data: 0.0798 max mem: 8233 +Train: [13] [4000/6250] eta: 0:06:28 lr: 0.000122 grad: 0.1717 (0.1764) loss: 0.9288 (0.9286) time: 0.1275 data: 0.0479 max mem: 8233 +Train: [13] [4100/6250] eta: 0:06:11 lr: 0.000122 grad: 0.1650 (0.1764) loss: 0.9301 (0.9285) time: 0.1106 data: 0.0005 max mem: 8233 +Train: [13] [4200/6250] eta: 0:05:54 lr: 0.000122 grad: 0.1713 (0.1764) loss: 0.9291 (0.9285) time: 0.1741 data: 0.0845 max mem: 8233 +Train: [13] [4300/6250] eta: 0:05:36 lr: 0.000122 grad: 0.1460 (0.1763) loss: 0.9255 (0.9285) time: 0.1759 data: 0.0753 max mem: 8233 +Train: [13] [4400/6250] eta: 0:05:19 lr: 0.000122 grad: 0.1780 (0.1763) loss: 0.9247 (0.9284) time: 0.1383 data: 0.0549 max mem: 8233 +Train: [13] [4500/6250] eta: 0:05:01 lr: 0.000122 grad: 0.1750 (0.1763) loss: 0.9261 (0.9284) time: 0.1525 data: 0.0769 max mem: 8233 +Train: [13] [4600/6250] eta: 0:04:44 lr: 0.000122 grad: 0.1636 (0.1762) loss: 0.9275 (0.9284) time: 0.1426 data: 0.0573 max mem: 8233 +Train: [13] [4700/6250] eta: 0:04:27 lr: 0.000122 grad: 0.1912 (0.1762) loss: 0.9253 (0.9284) time: 0.2201 data: 0.1452 max mem: 8233 +Train: [13] [4800/6250] eta: 0:04:09 lr: 0.000122 grad: 0.1789 (0.1761) loss: 0.9284 (0.9283) time: 0.1703 data: 0.0870 max mem: 8233 +Train: [13] [4900/6250] eta: 0:03:51 lr: 0.000122 grad: 0.1795 (0.1760) loss: 0.9277 (0.9283) time: 0.1646 data: 0.0843 max mem: 8233 +Train: [13] [5000/6250] eta: 0:03:34 lr: 0.000122 grad: 0.1608 (0.1759) loss: 0.9281 (0.9283) time: 0.1802 data: 0.0984 max mem: 8233 +Train: [13] [5100/6250] eta: 0:03:17 lr: 0.000122 grad: 0.1678 (0.1758) loss: 0.9269 (0.9282) time: 0.2104 data: 0.1315 max mem: 8233 +Train: [13] [5200/6250] eta: 0:03:00 lr: 0.000122 grad: 0.1650 (0.1758) loss: 0.9255 (0.9282) time: 0.1005 data: 0.0003 max mem: 8233 +Train: [13] [5300/6250] eta: 0:02:43 lr: 0.000122 grad: 0.1520 (0.1757) loss: 0.9277 (0.9282) time: 0.1337 data: 0.0431 max mem: 8233 +Train: [13] [5400/6250] eta: 0:02:26 lr: 0.000122 grad: 0.1736 (0.1755) loss: 0.9294 (0.9282) time: 0.1040 data: 0.0003 max mem: 8233 +Train: [13] [5500/6250] eta: 0:02:09 lr: 0.000122 grad: 0.1689 (0.1754) loss: 0.9306 (0.9282) time: 0.1792 data: 0.0998 max mem: 8233 +Train: [13] [5600/6250] eta: 0:01:51 lr: 0.000122 grad: 0.1579 (0.1752) loss: 0.9288 (0.9282) time: 0.1199 data: 0.0427 max mem: 8233 +Train: [13] [5700/6250] eta: 0:01:34 lr: 0.000122 grad: 0.1622 (0.1751) loss: 0.9290 (0.9282) time: 0.1929 data: 0.1036 max mem: 8233 +Train: [13] [5800/6250] eta: 0:01:17 lr: 0.000122 grad: 0.1616 (0.1749) loss: 0.9266 (0.9282) time: 0.1609 data: 0.0794 max mem: 8233 +Train: [13] [5900/6250] eta: 0:01:00 lr: 0.000122 grad: 0.1671 (0.1748) loss: 0.9274 (0.9282) time: 0.2027 data: 0.1244 max mem: 8233 +Train: [13] [6000/6250] eta: 0:00:43 lr: 0.000122 grad: 0.1776 (0.1748) loss: 0.9271 (0.9282) time: 0.1425 data: 0.0564 max mem: 8233 +Train: [13] [6100/6250] eta: 0:00:25 lr: 0.000122 grad: 0.1583 (0.1748) loss: 0.9297 (0.9282) time: 0.2889 data: 0.2171 max mem: 8233 +Train: [13] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.1464 (0.1747) loss: 0.9247 (0.9282) time: 0.1457 data: 0.0632 max mem: 8233 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.1631 (0.1746) loss: 0.9283 (0.9282) time: 0.1734 data: 0.0949 max mem: 8233 +Train: [13] Total time: 0:18:04 (0.1736 s / it) +Averaged stats: lr: 0.000122 grad: 0.1631 (0.1746) loss: 0.9283 (0.9282) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:03:22 loss: 0.9346 (0.9346) time: 3.2723 data: 3.2163 max mem: 8233 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.9305 (0.9285) time: 0.1309 data: 0.1091 max mem: 8233 +Eval (hcp-train-subset): [13] Total time: 0:00:13 (0.2185 s / it) +Averaged stats (hcp-train-subset): loss: 0.9305 (0.9285) +Eval (hcp-val): [13] [ 0/62] eta: 0:04:34 loss: 0.9213 (0.9213) time: 4.4325 data: 4.4026 max mem: 8233 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.9230 (0.9242) time: 0.0942 data: 0.0731 max mem: 8233 +Eval (hcp-val): [13] Total time: 0:00:13 (0.2172 s / it) +Averaged stats (hcp-val): loss: 0.9230 (0.9242) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 8:35:01 lr: 0.000122 grad: 0.1335 (0.1335) loss: 0.9511 (0.9511) time: 4.9442 data: 4.6603 max mem: 8233 +Train: [14] [ 100/6250] eta: 0:23:49 lr: 0.000122 grad: 0.1753 (0.1812) loss: 0.9278 (0.9286) time: 0.2004 data: 0.1013 max mem: 8233 +Train: [14] [ 200/6250] eta: 0:20:22 lr: 0.000122 grad: 0.1783 (0.1817) loss: 0.9277 (0.9273) time: 0.1726 data: 0.0860 max mem: 8233 +Train: [14] [ 300/6250] eta: 0:18:57 lr: 0.000122 grad: 0.1752 (0.1776) loss: 0.9240 (0.9275) time: 0.1692 data: 0.0753 max mem: 8233 +Train: [14] [ 400/6250] eta: 0:18:08 lr: 0.000122 grad: 0.1556 (0.1757) loss: 0.9264 (0.9271) time: 0.1722 data: 0.0907 max mem: 8233 +Train: [14] [ 500/6250] eta: 0:17:21 lr: 0.000122 grad: 0.1758 (0.1744) loss: 0.9258 (0.9270) time: 0.1567 data: 0.0647 max mem: 8233 +Train: [14] [ 600/6250] eta: 0:16:40 lr: 0.000122 grad: 0.1633 (0.1734) loss: 0.9282 (0.9267) time: 0.1632 data: 0.0835 max mem: 8233 +Train: [14] [ 700/6250] eta: 0:16:20 lr: 0.000122 grad: 0.1667 (0.1740) loss: 0.9242 (0.9265) time: 0.2329 data: 0.1645 max mem: 8233 +Train: [14] [ 800/6250] eta: 0:15:54 lr: 0.000122 grad: 0.1669 (0.1736) loss: 0.9241 (0.9263) time: 0.1547 data: 0.0681 max mem: 8233 +Train: [14] [ 900/6250] eta: 0:15:28 lr: 0.000122 grad: 0.1828 (0.1727) loss: 0.9227 (0.9261) time: 0.1694 data: 0.0885 max mem: 8233 +Train: [14] [1000/6250] eta: 0:15:11 lr: 0.000122 grad: 0.1769 (0.1727) loss: 0.9291 (0.9261) time: 0.1674 data: 0.0904 max mem: 8233 +Train: [14] [1100/6250] eta: 0:14:48 lr: 0.000122 grad: 0.1614 (0.1728) loss: 0.9248 (0.9260) time: 0.1674 data: 0.0906 max mem: 8233 +Train: [14] [1200/6250] eta: 0:14:27 lr: 0.000122 grad: 0.1668 (0.1727) loss: 0.9217 (0.9258) time: 0.1502 data: 0.0725 max mem: 8233 +Train: [14] [1300/6250] eta: 0:14:16 lr: 0.000122 grad: 0.1723 (0.1729) loss: 0.9242 (0.9257) time: 0.1731 data: 0.0863 max mem: 8233 +Train: [14] [1400/6250] eta: 0:14:02 lr: 0.000122 grad: 0.1546 (0.1725) loss: 0.9264 (0.9256) time: 0.1473 data: 0.0365 max mem: 8233 +Train: [14] [1500/6250] eta: 0:13:47 lr: 0.000122 grad: 0.1713 (0.1723) loss: 0.9232 (0.9255) time: 0.1348 data: 0.0526 max mem: 8233 +Train: [14] [1600/6250] eta: 0:13:27 lr: 0.000122 grad: 0.1566 (0.1719) loss: 0.9228 (0.9254) time: 0.1811 data: 0.1057 max mem: 8233 +Train: [14] [1700/6250] eta: 0:13:06 lr: 0.000122 grad: 0.1635 (0.1717) loss: 0.9227 (0.9253) time: 0.1646 data: 0.0881 max mem: 8233 +Train: [14] [1800/6250] eta: 0:12:48 lr: 0.000122 grad: 0.1559 (0.1718) loss: 0.9245 (0.9251) time: 0.1540 data: 0.0667 max mem: 8233 +Train: [14] [1900/6250] eta: 0:12:37 lr: 0.000122 grad: 0.1744 (0.1718) loss: 0.9192 (0.9249) time: 0.1588 data: 0.0564 max mem: 8233 +Train: [14] [2000/6250] eta: 0:12:19 lr: 0.000122 grad: 0.1777 (0.1722) loss: 0.9179 (0.9248) time: 0.1381 data: 0.0541 max mem: 8233 +Train: [14] [2100/6250] eta: 0:12:02 lr: 0.000122 grad: 0.1583 (0.1722) loss: 0.9258 (0.9247) time: 0.2160 data: 0.1155 max mem: 8233 +Train: [14] [2200/6250] eta: 0:11:44 lr: 0.000122 grad: 0.1593 (0.1719) loss: 0.9244 (0.9246) time: 0.1492 data: 0.0707 max mem: 8233 +Train: [14] [2300/6250] eta: 0:11:31 lr: 0.000122 grad: 0.1613 (0.1718) loss: 0.9273 (0.9246) time: 0.1611 data: 0.0756 max mem: 8233 +Train: [14] [2400/6250] eta: 0:11:10 lr: 0.000122 grad: 0.1668 (0.1717) loss: 0.9251 (0.9245) time: 0.1816 data: 0.1030 max mem: 8233 +Train: [14] [2500/6250] eta: 0:10:50 lr: 0.000122 grad: 0.1740 (0.1715) loss: 0.9278 (0.9245) time: 0.1488 data: 0.0451 max mem: 8233 +Train: [14] [2600/6250] eta: 0:10:33 lr: 0.000122 grad: 0.1840 (0.1715) loss: 0.9229 (0.9245) time: 0.1682 data: 0.0948 max mem: 8233 +Train: [14] [2700/6250] eta: 0:10:16 lr: 0.000122 grad: 0.1537 (0.1714) loss: 0.9280 (0.9245) time: 0.2311 data: 0.1468 max mem: 8233 +Train: [14] [2800/6250] eta: 0:09:55 lr: 0.000122 grad: 0.1627 (0.1713) loss: 0.9226 (0.9244) time: 0.1678 data: 0.0812 max mem: 8233 +Train: [14] [2900/6250] eta: 0:09:38 lr: 0.000122 grad: 0.1760 (0.1713) loss: 0.9230 (0.9244) time: 0.2454 data: 0.1573 max mem: 8233 +Train: [14] [3000/6250] eta: 0:09:19 lr: 0.000122 grad: 0.1600 (0.1712) loss: 0.9206 (0.9243) time: 0.1227 data: 0.0299 max mem: 8233 +Train: [14] [3100/6250] eta: 0:09:01 lr: 0.000122 grad: 0.1637 (0.1710) loss: 0.9288 (0.9243) time: 0.1055 data: 0.0178 max mem: 8233 +Train: [14] [3200/6250] eta: 0:08:42 lr: 0.000122 grad: 0.1595 (0.1708) loss: 0.9224 (0.9243) time: 0.1303 data: 0.0495 max mem: 8233 +Train: [14] [3300/6250] eta: 0:08:25 lr: 0.000122 grad: 0.1641 (0.1709) loss: 0.9248 (0.9243) time: 0.1655 data: 0.0712 max mem: 8233 +Train: [14] [3400/6250] eta: 0:08:08 lr: 0.000122 grad: 0.1537 (0.1707) loss: 0.9278 (0.9243) time: 0.1083 data: 0.0003 max mem: 8233 +Train: [14] [3500/6250] eta: 0:07:51 lr: 0.000122 grad: 0.1618 (0.1706) loss: 0.9228 (0.9243) time: 0.1643 data: 0.0742 max mem: 8233 +Train: [14] [3600/6250] eta: 0:07:33 lr: 0.000122 grad: 0.1760 (0.1706) loss: 0.9220 (0.9243) time: 0.1652 data: 0.0789 max mem: 8233 +Train: [14] [3700/6250] eta: 0:07:15 lr: 0.000122 grad: 0.1629 (0.1705) loss: 0.9245 (0.9243) time: 0.1663 data: 0.0722 max mem: 8233 +Train: [14] [3800/6250] eta: 0:06:57 lr: 0.000122 grad: 0.1517 (0.1703) loss: 0.9264 (0.9243) time: 0.1765 data: 0.0920 max mem: 8233 +Train: [14] [3900/6250] eta: 0:06:40 lr: 0.000122 grad: 0.1665 (0.1701) loss: 0.9248 (0.9242) time: 0.1341 data: 0.0556 max mem: 8233 +Train: [14] [4000/6250] eta: 0:06:23 lr: 0.000122 grad: 0.1677 (0.1700) loss: 0.9229 (0.9242) time: 0.1520 data: 0.0733 max mem: 8233 +Train: [14] [4100/6250] eta: 0:06:06 lr: 0.000122 grad: 0.1675 (0.1699) loss: 0.9245 (0.9242) time: 0.1777 data: 0.0988 max mem: 8233 +Train: [14] [4200/6250] eta: 0:05:49 lr: 0.000122 grad: 0.1720 (0.1699) loss: 0.9198 (0.9241) time: 0.2096 data: 0.1259 max mem: 8233 +Train: [14] [4300/6250] eta: 0:05:32 lr: 0.000122 grad: 0.1621 (0.1698) loss: 0.9219 (0.9241) time: 0.1578 data: 0.0830 max mem: 8233 +Train: [14] [4400/6250] eta: 0:05:15 lr: 0.000122 grad: 0.1610 (0.1698) loss: 0.9224 (0.9241) time: 0.2379 data: 0.1383 max mem: 8233 +Train: [14] [4500/6250] eta: 0:04:58 lr: 0.000122 grad: 0.1575 (0.1698) loss: 0.9243 (0.9240) time: 0.1645 data: 0.0691 max mem: 8233 +Train: [14] [4600/6250] eta: 0:04:42 lr: 0.000122 grad: 0.1723 (0.1698) loss: 0.9250 (0.9240) time: 0.1505 data: 0.0448 max mem: 8233 +Train: [14] [4700/6250] eta: 0:04:25 lr: 0.000122 grad: 0.1704 (0.1699) loss: 0.9161 (0.9239) time: 0.1458 data: 0.0457 max mem: 8233 +Train: [14] [4800/6250] eta: 0:04:07 lr: 0.000122 grad: 0.1683 (0.1698) loss: 0.9198 (0.9239) time: 0.1759 data: 0.0798 max mem: 8233 +Train: [14] [4900/6250] eta: 0:03:50 lr: 0.000122 grad: 0.1646 (0.1697) loss: 0.9219 (0.9238) time: 0.2176 data: 0.1398 max mem: 8233 +Train: [14] [5000/6250] eta: 0:03:33 lr: 0.000122 grad: 0.1676 (0.1698) loss: 0.9200 (0.9238) time: 0.1734 data: 0.0951 max mem: 8233 +Train: [14] [5100/6250] eta: 0:03:16 lr: 0.000122 grad: 0.1702 (0.1698) loss: 0.9205 (0.9237) time: 0.1867 data: 0.1087 max mem: 8233 +Train: [14] [5200/6250] eta: 0:02:58 lr: 0.000122 grad: 0.1755 (0.1699) loss: 0.9189 (0.9236) time: 0.1604 data: 0.0734 max mem: 8233 +Train: [14] [5300/6250] eta: 0:02:41 lr: 0.000122 grad: 0.1615 (0.1699) loss: 0.9226 (0.9235) time: 0.1950 data: 0.0948 max mem: 8233 +Train: [14] [5400/6250] eta: 0:02:24 lr: 0.000122 grad: 0.1633 (0.1699) loss: 0.9196 (0.9235) time: 0.1246 data: 0.0305 max mem: 8233 +Train: [14] [5500/6250] eta: 0:02:07 lr: 0.000122 grad: 0.1731 (0.1699) loss: 0.9211 (0.9234) time: 0.1862 data: 0.1070 max mem: 8233 +Train: [14] [5600/6250] eta: 0:01:50 lr: 0.000122 grad: 0.1649 (0.1699) loss: 0.9204 (0.9234) time: 0.1520 data: 0.0592 max mem: 8233 +Train: [14] [5700/6250] eta: 0:01:33 lr: 0.000122 grad: 0.1523 (0.1699) loss: 0.9228 (0.9233) time: 0.2098 data: 0.1348 max mem: 8233 +Train: [14] [5800/6250] eta: 0:01:16 lr: 0.000122 grad: 0.1643 (0.1699) loss: 0.9204 (0.9233) time: 0.2429 data: 0.1692 max mem: 8233 +Train: [14] [5900/6250] eta: 0:00:59 lr: 0.000122 grad: 0.1544 (0.1700) loss: 0.9250 (0.9233) time: 0.1524 data: 0.0712 max mem: 8233 +Train: [14] [6000/6250] eta: 0:00:42 lr: 0.000122 grad: 0.1825 (0.1700) loss: 0.9184 (0.9232) time: 0.2009 data: 0.1153 max mem: 8233 +Train: [14] [6100/6250] eta: 0:00:25 lr: 0.000122 grad: 0.1547 (0.1700) loss: 0.9212 (0.9232) time: 0.1732 data: 0.0939 max mem: 8233 +Train: [14] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.1696 (0.1700) loss: 0.9224 (0.9232) time: 0.1456 data: 0.0646 max mem: 8233 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.1761 (0.1700) loss: 0.9223 (0.9232) time: 0.2250 data: 0.1444 max mem: 8233 +Train: [14] Total time: 0:17:55 (0.1720 s / it) +Averaged stats: lr: 0.000122 grad: 0.1761 (0.1700) loss: 0.9223 (0.9232) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:06:15 loss: 0.9323 (0.9323) time: 6.0613 data: 6.0336 max mem: 8233 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.9250 (0.9250) time: 0.1224 data: 0.1005 max mem: 8233 +Eval (hcp-train-subset): [14] Total time: 0:00:14 (0.2332 s / it) +Averaged stats (hcp-train-subset): loss: 0.9250 (0.9250) +Making plots (hcp-train-subset): example=46 +Eval (hcp-val): [14] [ 0/62] eta: 0:04:59 loss: 0.9181 (0.9181) time: 4.8247 data: 4.7683 max mem: 8233 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.9204 (0.9213) time: 0.1394 data: 0.1177 max mem: 8233 +Eval (hcp-val): [14] Total time: 0:00:14 (0.2359 s / it) +Averaged stats (hcp-val): loss: 0.9204 (0.9213) +Making plots (hcp-val): example=55 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 10:46:41 lr: 0.000122 grad: 0.1722 (0.1722) loss: 0.9320 (0.9320) time: 6.2082 data: 6.0606 max mem: 8233 +Train: [15] [ 100/6250] eta: 0:24:05 lr: 0.000122 grad: 0.1536 (0.1661) loss: 0.9341 (0.9298) time: 0.1948 data: 0.1085 max mem: 8233 +Train: [15] [ 200/6250] eta: 0:20:26 lr: 0.000122 grad: 0.1569 (0.1693) loss: 0.9275 (0.9271) time: 0.1528 data: 0.0457 max mem: 8233 +Train: [15] [ 300/6250] eta: 0:19:19 lr: 0.000122 grad: 0.1449 (0.1668) loss: 0.9316 (0.9269) time: 0.1892 data: 0.0929 max mem: 8233 +Train: [15] [ 400/6250] eta: 0:18:17 lr: 0.000122 grad: 0.1450 (0.1650) loss: 0.9258 (0.9263) time: 0.1528 data: 0.0607 max mem: 8233 +Train: [15] [ 500/6250] eta: 0:17:29 lr: 0.000122 grad: 0.1500 (0.1645) loss: 0.9224 (0.9257) time: 0.1372 data: 0.0490 max mem: 8233 +Train: [15] [ 600/6250] eta: 0:16:51 lr: 0.000122 grad: 0.1458 (0.1632) loss: 0.9224 (0.9251) time: 0.1423 data: 0.0334 max mem: 8233 +Train: [15] [ 700/6250] eta: 0:16:15 lr: 0.000122 grad: 0.1624 (0.1628) loss: 0.9201 (0.9247) time: 0.1522 data: 0.0546 max mem: 8233 +Train: [15] [ 800/6250] eta: 0:15:55 lr: 0.000122 grad: 0.1583 (0.1627) loss: 0.9211 (0.9244) time: 0.1462 data: 0.0638 max mem: 8233 +Train: [15] [ 900/6250] eta: 0:15:32 lr: 0.000122 grad: 0.1591 (0.1625) loss: 0.9216 (0.9243) time: 0.1730 data: 0.0813 max mem: 8233 +Train: [15] [1000/6250] eta: 0:15:03 lr: 0.000122 grad: 0.1588 (0.1625) loss: 0.9233 (0.9243) time: 0.1396 data: 0.0596 max mem: 8233 +Train: [15] [1100/6250] eta: 0:15:03 lr: 0.000121 grad: 0.1636 (0.1629) loss: 0.9227 (0.9241) time: 0.1804 data: 0.0878 max mem: 8233 +Train: [15] [1200/6250] eta: 0:14:51 lr: 0.000121 grad: 0.1617 (0.1636) loss: 0.9235 (0.9239) time: 0.1844 data: 0.1094 max mem: 8233 +Train: [15] [1300/6250] eta: 0:14:35 lr: 0.000121 grad: 0.1540 (0.1637) loss: 0.9231 (0.9238) time: 0.1946 data: 0.0990 max mem: 8233 +Train: [15] [1400/6250] eta: 0:14:26 lr: 0.000121 grad: 0.1640 (0.1641) loss: 0.9192 (0.9237) time: 0.1545 data: 0.0423 max mem: 8233 +Train: [15] [1500/6250] eta: 0:14:07 lr: 0.000121 grad: 0.1675 (0.1640) loss: 0.9200 (0.9234) time: 0.1758 data: 0.0757 max mem: 8233 +Train: [15] [1600/6250] eta: 0:13:50 lr: 0.000121 grad: 0.1665 (0.1644) loss: 0.9202 (0.9232) time: 0.1911 data: 0.1068 max mem: 8233 +Train: [15] [1700/6250] eta: 0:13:30 lr: 0.000121 grad: 0.1624 (0.1645) loss: 0.9219 (0.9230) time: 0.1795 data: 0.1003 max mem: 8233 +Train: [15] [1800/6250] eta: 0:13:11 lr: 0.000121 grad: 0.1603 (0.1646) loss: 0.9211 (0.9230) time: 0.1693 data: 0.0880 max mem: 8233 +Train: [15] [1900/6250] eta: 0:12:56 lr: 0.000121 grad: 0.1649 (0.1646) loss: 0.9196 (0.9229) time: 0.1624 data: 0.0679 max mem: 8233 +Train: [15] [2000/6250] eta: 0:12:37 lr: 0.000121 grad: 0.1552 (0.1645) loss: 0.9216 (0.9229) time: 0.1550 data: 0.0728 max mem: 8233 +Train: [15] [2100/6250] eta: 0:12:19 lr: 0.000121 grad: 0.1539 (0.1646) loss: 0.9244 (0.9228) time: 0.1918 data: 0.1284 max mem: 8233 +Train: [15] [2200/6250] eta: 0:12:01 lr: 0.000121 grad: 0.1522 (0.1647) loss: 0.9185 (0.9228) time: 0.1693 data: 0.0986 max mem: 8233 +Train: [15] [2300/6250] eta: 0:11:43 lr: 0.000121 grad: 0.1705 (0.1647) loss: 0.9252 (0.9227) time: 0.2016 data: 0.1300 max mem: 8233 +Train: [15] [2400/6250] eta: 0:11:23 lr: 0.000121 grad: 0.1624 (0.1649) loss: 0.9254 (0.9227) time: 0.1550 data: 0.0828 max mem: 8233 +Train: [15] [2500/6250] eta: 0:11:09 lr: 0.000121 grad: 0.1517 (0.1647) loss: 0.9223 (0.9226) time: 0.1068 data: 0.0005 max mem: 8233 +Train: [15] [2600/6250] eta: 0:10:47 lr: 0.000121 grad: 0.1574 (0.1648) loss: 0.9238 (0.9226) time: 0.1577 data: 0.0800 max mem: 8233 +Train: [15] [2700/6250] eta: 0:10:26 lr: 0.000121 grad: 0.1494 (0.1647) loss: 0.9195 (0.9225) time: 0.1466 data: 0.0555 max mem: 8233 +Train: [15] [2800/6250] eta: 0:10:09 lr: 0.000121 grad: 0.1521 (0.1647) loss: 0.9197 (0.9225) time: 0.1514 data: 0.0499 max mem: 8233 +Train: [15] [2900/6250] eta: 0:09:52 lr: 0.000121 grad: 0.1514 (0.1645) loss: 0.9209 (0.9225) time: 0.1654 data: 0.0699 max mem: 8233 +Train: [15] [3000/6250] eta: 0:09:33 lr: 0.000121 grad: 0.1651 (0.1646) loss: 0.9216 (0.9224) time: 0.1568 data: 0.0747 max mem: 8233 +Train: [15] [3100/6250] eta: 0:09:15 lr: 0.000121 grad: 0.1600 (0.1646) loss: 0.9197 (0.9224) time: 0.1572 data: 0.0704 max mem: 8233 +Train: [15] [3200/6250] eta: 0:08:55 lr: 0.000121 grad: 0.1655 (0.1645) loss: 0.9231 (0.9224) time: 0.1434 data: 0.0567 max mem: 8233 +Train: [15] [3300/6250] eta: 0:08:37 lr: 0.000121 grad: 0.1787 (0.1646) loss: 0.9197 (0.9223) time: 0.1663 data: 0.0821 max mem: 8233 +Train: [15] [3400/6250] eta: 0:08:18 lr: 0.000121 grad: 0.1555 (0.1647) loss: 0.9174 (0.9223) time: 0.1449 data: 0.0547 max mem: 8233 +Train: [15] [3500/6250] eta: 0:08:01 lr: 0.000121 grad: 0.1487 (0.1647) loss: 0.9217 (0.9223) time: 0.1179 data: 0.0003 max mem: 8233 +Train: [15] [3600/6250] eta: 0:07:42 lr: 0.000121 grad: 0.1560 (0.1645) loss: 0.9229 (0.9223) time: 0.1453 data: 0.0618 max mem: 8233 +Train: [15] [3700/6250] eta: 0:07:23 lr: 0.000121 grad: 0.1650 (0.1647) loss: 0.9250 (0.9223) time: 0.1361 data: 0.0461 max mem: 8233 +Train: [15] [3800/6250] eta: 0:07:06 lr: 0.000121 grad: 0.1493 (0.1645) loss: 0.9209 (0.9223) time: 0.0949 data: 0.0002 max mem: 8233 +Train: [15] [3900/6250] eta: 0:06:47 lr: 0.000121 grad: 0.1488 (0.1643) loss: 0.9166 (0.9223) time: 0.1394 data: 0.0641 max mem: 8233 +Train: [15] [4000/6250] eta: 0:06:31 lr: 0.000121 grad: 0.1529 (0.1642) loss: 0.9205 (0.9223) time: 0.1701 data: 0.1015 max mem: 8233 +Train: [15] [4100/6250] eta: 0:06:13 lr: 0.000121 grad: 0.1670 (0.1641) loss: 0.9240 (0.9224) time: 0.1292 data: 0.0451 max mem: 8233 +Train: [15] [4200/6250] eta: 0:05:55 lr: 0.000121 grad: 0.1427 (0.1639) loss: 0.9236 (0.9224) time: 0.1582 data: 0.0711 max mem: 8233 +Train: [15] [4300/6250] eta: 0:05:37 lr: 0.000121 grad: 0.1479 (0.1637) loss: 0.9224 (0.9224) time: 0.1210 data: 0.0336 max mem: 8233 +Train: [15] [4400/6250] eta: 0:05:19 lr: 0.000121 grad: 0.1623 (0.1636) loss: 0.9193 (0.9223) time: 0.1679 data: 0.0878 max mem: 8233 +Train: [15] [4500/6250] eta: 0:05:02 lr: 0.000121 grad: 0.1569 (0.1635) loss: 0.9241 (0.9223) time: 0.1627 data: 0.0809 max mem: 8233 +Train: [15] [4600/6250] eta: 0:04:44 lr: 0.000121 grad: 0.1461 (0.1634) loss: 0.9179 (0.9223) time: 0.1758 data: 0.0882 max mem: 8233 +Train: [15] [4700/6250] eta: 0:04:27 lr: 0.000121 grad: 0.1592 (0.1633) loss: 0.9187 (0.9223) time: 0.1706 data: 0.1047 max mem: 8233 +Train: [15] [4800/6250] eta: 0:04:09 lr: 0.000121 grad: 0.1622 (0.1634) loss: 0.9212 (0.9222) time: 0.1527 data: 0.0718 max mem: 8233 +Train: [15] [4900/6250] eta: 0:03:52 lr: 0.000121 grad: 0.1558 (0.1632) loss: 0.9232 (0.9222) time: 0.1517 data: 0.0590 max mem: 8233 +Train: [15] [5000/6250] eta: 0:03:34 lr: 0.000121 grad: 0.1524 (0.1632) loss: 0.9170 (0.9222) time: 0.1619 data: 0.0810 max mem: 8233 +Train: [15] [5100/6250] eta: 0:03:17 lr: 0.000121 grad: 0.1532 (0.1631) loss: 0.9250 (0.9222) time: 0.2119 data: 0.1383 max mem: 8233 +Train: [15] [5200/6250] eta: 0:03:00 lr: 0.000121 grad: 0.1489 (0.1629) loss: 0.9203 (0.9222) time: 0.1722 data: 0.0959 max mem: 8233 +Train: [15] [5300/6250] eta: 0:02:43 lr: 0.000121 grad: 0.1516 (0.1628) loss: 0.9190 (0.9221) time: 0.1743 data: 0.0839 max mem: 8233 +Train: [15] [5400/6250] eta: 0:02:25 lr: 0.000121 grad: 0.1566 (0.1627) loss: 0.9185 (0.9221) time: 0.1733 data: 0.0889 max mem: 8233 +Train: [15] [5500/6250] eta: 0:02:08 lr: 0.000121 grad: 0.1571 (0.1628) loss: 0.9145 (0.9220) time: 0.1396 data: 0.0560 max mem: 8233 +Train: [15] [5600/6250] eta: 0:01:51 lr: 0.000121 grad: 0.1697 (0.1629) loss: 0.9214 (0.9220) time: 0.2178 data: 0.1490 max mem: 8233 +Train: [15] [5700/6250] eta: 0:01:34 lr: 0.000121 grad: 0.1615 (0.1629) loss: 0.9197 (0.9219) time: 0.1684 data: 0.0872 max mem: 8233 +Train: [15] [5800/6250] eta: 0:01:17 lr: 0.000121 grad: 0.1731 (0.1630) loss: 0.9223 (0.9219) time: 0.1863 data: 0.1156 max mem: 8233 +Train: [15] [5900/6250] eta: 0:01:00 lr: 0.000121 grad: 0.1525 (0.1629) loss: 0.9197 (0.9218) time: 0.1157 data: 0.0003 max mem: 8233 +Train: [15] [6000/6250] eta: 0:00:43 lr: 0.000121 grad: 0.1573 (0.1629) loss: 0.9191 (0.9218) time: 0.2865 data: 0.1599 max mem: 8233 +Train: [15] [6100/6250] eta: 0:00:25 lr: 0.000121 grad: 0.1555 (0.1630) loss: 0.9171 (0.9217) time: 0.1357 data: 0.0208 max mem: 8233 +Train: [15] [6200/6250] eta: 0:00:08 lr: 0.000121 grad: 0.1668 (0.1631) loss: 0.9235 (0.9216) time: 0.2190 data: 0.1460 max mem: 8233 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.1517 (0.1631) loss: 0.9210 (0.9216) time: 0.2031 data: 0.1332 max mem: 8233 +Train: [15] Total time: 0:18:03 (0.1734 s / it) +Averaged stats: lr: 0.000121 grad: 0.1517 (0.1631) loss: 0.9210 (0.9216) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:04:35 loss: 0.9285 (0.9285) time: 4.4428 data: 4.3502 max mem: 8233 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.9255 (0.9232) time: 0.1418 data: 0.1210 max mem: 8233 +Eval (hcp-train-subset): [15] Total time: 0:00:15 (0.2469 s / it) +Averaged stats (hcp-train-subset): loss: 0.9255 (0.9232) +Eval (hcp-val): [15] [ 0/62] eta: 0:03:51 loss: 0.9141 (0.9141) time: 3.7376 data: 3.6747 max mem: 8233 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.9188 (0.9190) time: 0.1458 data: 0.1241 max mem: 8233 +Eval (hcp-val): [15] Total time: 0:00:14 (0.2364 s / it) +Averaged stats (hcp-val): loss: 0.9188 (0.9190) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 11:53:52 lr: 0.000121 grad: 0.2178 (0.2178) loss: 0.9176 (0.9176) time: 6.8533 data: 6.7057 max mem: 8233 +Train: [16] [ 100/6250] eta: 0:22:58 lr: 0.000121 grad: 0.1555 (0.1713) loss: 0.9270 (0.9240) time: 0.1587 data: 0.0770 max mem: 8233 +Train: [16] [ 200/6250] eta: 0:19:51 lr: 0.000121 grad: 0.1659 (0.1662) loss: 0.9219 (0.9221) time: 0.1796 data: 0.0912 max mem: 8233 +Train: [16] [ 300/6250] eta: 0:18:40 lr: 0.000121 grad: 0.1457 (0.1659) loss: 0.9217 (0.9218) time: 0.1650 data: 0.0695 max mem: 8233 +Train: [16] [ 400/6250] eta: 0:18:03 lr: 0.000121 grad: 0.1631 (0.1660) loss: 0.9209 (0.9210) time: 0.2022 data: 0.1061 max mem: 8233 +Train: [16] [ 500/6250] eta: 0:17:28 lr: 0.000121 grad: 0.1608 (0.1649) loss: 0.9188 (0.9205) time: 0.1540 data: 0.0592 max mem: 8233 +Train: [16] [ 600/6250] eta: 0:16:44 lr: 0.000121 grad: 0.1489 (0.1645) loss: 0.9165 (0.9200) time: 0.1410 data: 0.0410 max mem: 8233 +Train: [16] [ 700/6250] eta: 0:16:14 lr: 0.000121 grad: 0.1547 (0.1636) loss: 0.9206 (0.9201) time: 0.1723 data: 0.0839 max mem: 8233 +Train: [16] [ 800/6250] eta: 0:15:49 lr: 0.000121 grad: 0.1591 (0.1634) loss: 0.9183 (0.9202) time: 0.1891 data: 0.1180 max mem: 8233 +Train: [16] [ 900/6250] eta: 0:15:46 lr: 0.000121 grad: 0.1527 (0.1628) loss: 0.9182 (0.9203) time: 0.1679 data: 0.0664 max mem: 8233 +Train: [16] [1000/6250] eta: 0:15:20 lr: 0.000121 grad: 0.1502 (0.1622) loss: 0.9204 (0.9204) time: 0.1633 data: 0.0791 max mem: 8233 +Train: [16] [1100/6250] eta: 0:14:50 lr: 0.000121 grad: 0.1592 (0.1621) loss: 0.9218 (0.9202) time: 0.1403 data: 0.0652 max mem: 8233 +Train: [16] [1200/6250] eta: 0:14:30 lr: 0.000121 grad: 0.1553 (0.1617) loss: 0.9172 (0.9200) time: 0.1901 data: 0.1177 max mem: 8233 +Train: [16] [1300/6250] eta: 0:14:14 lr: 0.000121 grad: 0.1607 (0.1616) loss: 0.9234 (0.9200) time: 0.1692 data: 0.1031 max mem: 8233 +Train: [16] [1400/6250] eta: 0:13:54 lr: 0.000121 grad: 0.1693 (0.1616) loss: 0.9216 (0.9199) time: 0.1721 data: 0.0990 max mem: 8233 +Train: [16] [1500/6250] eta: 0:13:42 lr: 0.000121 grad: 0.1500 (0.1616) loss: 0.9210 (0.9197) time: 0.2108 data: 0.1200 max mem: 8233 +Train: [16] [1600/6250] eta: 0:13:28 lr: 0.000121 grad: 0.1621 (0.1618) loss: 0.9185 (0.9197) time: 0.2157 data: 0.1190 max mem: 8233 +Train: [16] [1700/6250] eta: 0:13:11 lr: 0.000121 grad: 0.1437 (0.1616) loss: 0.9186 (0.9195) time: 0.1629 data: 0.0743 max mem: 8233 +Train: [16] [1800/6250] eta: 0:12:51 lr: 0.000121 grad: 0.1600 (0.1617) loss: 0.9154 (0.9193) time: 0.1449 data: 0.0450 max mem: 8233 +Train: [16] [1900/6250] eta: 0:12:34 lr: 0.000121 grad: 0.1433 (0.1617) loss: 0.9177 (0.9192) time: 0.1712 data: 0.0836 max mem: 8233 +Train: [16] [2000/6250] eta: 0:12:25 lr: 0.000121 grad: 0.1600 (0.1618) loss: 0.9194 (0.9191) time: 0.2344 data: 0.1272 max mem: 8233 +Train: [16] [2100/6250] eta: 0:12:07 lr: 0.000121 grad: 0.1539 (0.1617) loss: 0.9190 (0.9190) time: 0.2312 data: 0.1390 max mem: 8233 +Train: [16] [2200/6250] eta: 0:11:49 lr: 0.000121 grad: 0.1481 (0.1615) loss: 0.9210 (0.9190) time: 0.1181 data: 0.0007 max mem: 8233 +Train: [16] [2300/6250] eta: 0:11:32 lr: 0.000121 grad: 0.1584 (0.1612) loss: 0.9186 (0.9189) time: 0.2314 data: 0.1430 max mem: 8233 +Train: [16] [2400/6250] eta: 0:11:11 lr: 0.000121 grad: 0.1571 (0.1611) loss: 0.9161 (0.9188) time: 0.1648 data: 0.0755 max mem: 8233 +Train: [16] [2500/6250] eta: 0:10:51 lr: 0.000121 grad: 0.1557 (0.1609) loss: 0.9156 (0.9188) time: 0.1501 data: 0.0738 max mem: 8233 +Train: [16] [2600/6250] eta: 0:10:35 lr: 0.000121 grad: 0.1499 (0.1607) loss: 0.9168 (0.9187) time: 0.1906 data: 0.1010 max mem: 8233 +Train: [16] [2700/6250] eta: 0:10:16 lr: 0.000121 grad: 0.1585 (0.1608) loss: 0.9187 (0.9187) time: 0.1613 data: 0.0774 max mem: 8233 +Train: [16] [2800/6250] eta: 0:09:57 lr: 0.000121 grad: 0.1502 (0.1605) loss: 0.9172 (0.9187) time: 0.1605 data: 0.0741 max mem: 8233 +Train: [16] [2900/6250] eta: 0:09:38 lr: 0.000121 grad: 0.1484 (0.1603) loss: 0.9210 (0.9187) time: 0.1142 data: 0.0258 max mem: 8233 +Train: [16] [3000/6250] eta: 0:09:20 lr: 0.000121 grad: 0.1616 (0.1602) loss: 0.9136 (0.9188) time: 0.1612 data: 0.0667 max mem: 8233 +Train: [16] [3100/6250] eta: 0:09:03 lr: 0.000121 grad: 0.1562 (0.1600) loss: 0.9194 (0.9187) time: 0.1570 data: 0.0690 max mem: 8233 +Train: [16] [3200/6250] eta: 0:08:45 lr: 0.000121 grad: 0.1543 (0.1598) loss: 0.9149 (0.9187) time: 0.1694 data: 0.0956 max mem: 8233 +Train: [16] [3300/6250] eta: 0:08:28 lr: 0.000121 grad: 0.1623 (0.1597) loss: 0.9202 (0.9187) time: 0.1852 data: 0.0869 max mem: 8233 +Train: [16] [3400/6250] eta: 0:08:10 lr: 0.000121 grad: 0.1590 (0.1597) loss: 0.9190 (0.9187) time: 0.1719 data: 0.0943 max mem: 8233 +Train: [16] [3500/6250] eta: 0:07:52 lr: 0.000120 grad: 0.1582 (0.1598) loss: 0.9145 (0.9186) time: 0.1217 data: 0.0462 max mem: 8233 +Train: [16] [3600/6250] eta: 0:07:34 lr: 0.000120 grad: 0.1484 (0.1597) loss: 0.9147 (0.9186) time: 0.1948 data: 0.1160 max mem: 8233 +Train: [16] [3700/6250] eta: 0:07:16 lr: 0.000120 grad: 0.1584 (0.1597) loss: 0.9191 (0.9185) time: 0.1422 data: 0.0576 max mem: 8233 +Train: [16] [3800/6250] eta: 0:06:58 lr: 0.000120 grad: 0.1544 (0.1598) loss: 0.9183 (0.9185) time: 0.1737 data: 0.0995 max mem: 8233 +Train: [16] [3900/6250] eta: 0:06:40 lr: 0.000120 grad: 0.1541 (0.1597) loss: 0.9183 (0.9184) time: 0.1656 data: 0.0915 max mem: 8233 +Train: [16] [4000/6250] eta: 0:06:22 lr: 0.000120 grad: 0.1508 (0.1597) loss: 0.9120 (0.9183) time: 0.1591 data: 0.0823 max mem: 8233 +Train: [16] [4100/6250] eta: 0:06:05 lr: 0.000120 grad: 0.1654 (0.1597) loss: 0.9209 (0.9184) time: 0.1410 data: 0.0635 max mem: 8233 +Train: [16] [4200/6250] eta: 0:05:49 lr: 0.000120 grad: 0.1510 (0.1595) loss: 0.9140 (0.9183) time: 0.1016 data: 0.0003 max mem: 8233 +Train: [16] [4300/6250] eta: 0:05:32 lr: 0.000120 grad: 0.1568 (0.1596) loss: 0.9205 (0.9183) time: 0.1833 data: 0.1032 max mem: 8233 +Train: [16] [4400/6250] eta: 0:05:15 lr: 0.000120 grad: 0.1509 (0.1595) loss: 0.9190 (0.9183) time: 0.2055 data: 0.1121 max mem: 8233 +Train: [16] [4500/6250] eta: 0:04:58 lr: 0.000120 grad: 0.1552 (0.1595) loss: 0.9176 (0.9183) time: 0.1581 data: 0.0728 max mem: 8233 +Train: [16] [4600/6250] eta: 0:04:41 lr: 0.000120 grad: 0.1606 (0.1595) loss: 0.9166 (0.9183) time: 0.1343 data: 0.0635 max mem: 8233 +Train: [16] [4700/6250] eta: 0:04:25 lr: 0.000120 grad: 0.1548 (0.1594) loss: 0.9161 (0.9183) time: 0.1215 data: 0.0422 max mem: 8233 +Train: [16] [4800/6250] eta: 0:04:07 lr: 0.000120 grad: 0.1553 (0.1593) loss: 0.9195 (0.9183) time: 0.1522 data: 0.0747 max mem: 8233 +Train: [16] [4900/6250] eta: 0:03:50 lr: 0.000120 grad: 0.1565 (0.1593) loss: 0.9171 (0.9182) time: 0.1610 data: 0.0592 max mem: 8233 +Train: [16] [5000/6250] eta: 0:03:34 lr: 0.000120 grad: 0.1603 (0.1592) loss: 0.9192 (0.9182) time: 0.2849 data: 0.1952 max mem: 8233 +Train: [16] [5100/6250] eta: 0:03:16 lr: 0.000120 grad: 0.1530 (0.1593) loss: 0.9172 (0.9182) time: 0.1682 data: 0.0828 max mem: 8233 +Train: [16] [5200/6250] eta: 0:03:00 lr: 0.000120 grad: 0.1461 (0.1592) loss: 0.9137 (0.9182) time: 0.3452 data: 0.2537 max mem: 8233 +Train: [16] [5300/6250] eta: 0:02:42 lr: 0.000120 grad: 0.1517 (0.1591) loss: 0.9175 (0.9181) time: 0.2089 data: 0.1171 max mem: 8233 +Train: [16] [5400/6250] eta: 0:02:25 lr: 0.000120 grad: 0.1460 (0.1590) loss: 0.9180 (0.9181) time: 0.1624 data: 0.0785 max mem: 8233 +Train: [16] [5500/6250] eta: 0:02:08 lr: 0.000120 grad: 0.1557 (0.1590) loss: 0.9208 (0.9181) time: 0.1549 data: 0.0769 max mem: 8233 +Train: [16] [5600/6250] eta: 0:01:50 lr: 0.000120 grad: 0.1479 (0.1589) loss: 0.9170 (0.9180) time: 0.1482 data: 0.0682 max mem: 8233 +Train: [16] [5700/6250] eta: 0:01:33 lr: 0.000120 grad: 0.1559 (0.1589) loss: 0.9171 (0.9180) time: 0.1789 data: 0.0935 max mem: 8233 +Train: [16] [5800/6250] eta: 0:01:16 lr: 0.000120 grad: 0.1558 (0.1589) loss: 0.9177 (0.9179) time: 0.1650 data: 0.0854 max mem: 8233 +Train: [16] [5900/6250] eta: 0:00:59 lr: 0.000120 grad: 0.1512 (0.1589) loss: 0.9170 (0.9179) time: 0.1542 data: 0.0755 max mem: 8233 +Train: [16] [6000/6250] eta: 0:00:42 lr: 0.000120 grad: 0.1535 (0.1589) loss: 0.9184 (0.9179) time: 0.1274 data: 0.0427 max mem: 8233 +Train: [16] [6100/6250] eta: 0:00:25 lr: 0.000120 grad: 0.1659 (0.1589) loss: 0.9194 (0.9179) time: 0.1487 data: 0.0629 max mem: 8233 +Train: [16] [6200/6250] eta: 0:00:08 lr: 0.000120 grad: 0.1558 (0.1589) loss: 0.9172 (0.9179) time: 0.1110 data: 0.0005 max mem: 8233 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.1568 (0.1589) loss: 0.9146 (0.9178) time: 0.1609 data: 0.0680 max mem: 8233 +Train: [16] Total time: 0:17:50 (0.1713 s / it) +Averaged stats: lr: 0.000120 grad: 0.1568 (0.1589) loss: 0.9146 (0.9178) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:04:08 loss: 0.9283 (0.9283) time: 4.0045 data: 3.9305 max mem: 8233 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.9236 (0.9212) time: 0.1913 data: 0.1709 max mem: 8233 +Eval (hcp-train-subset): [16] Total time: 0:00:16 (0.2710 s / it) +Averaged stats (hcp-train-subset): loss: 0.9236 (0.9212) +Eval (hcp-val): [16] [ 0/62] eta: 0:04:47 loss: 0.9147 (0.9147) time: 4.6402 data: 4.5799 max mem: 8233 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.9175 (0.9175) time: 0.1459 data: 0.1256 max mem: 8233 +Eval (hcp-val): [16] Total time: 0:00:14 (0.2297 s / it) +Averaged stats (hcp-val): loss: 0.9175 (0.9175) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 13:04:55 lr: 0.000120 grad: nan (nan) loss: 0.9053 (0.9053) time: 7.5352 data: 7.4417 max mem: 8233 +Train: [17] [ 100/6250] eta: 0:23:22 lr: 0.000120 grad: 0.1374 (0.1719) loss: 0.9230 (0.9174) time: 0.1896 data: 0.0926 max mem: 8233 +Train: [17] [ 200/6250] eta: 0:20:06 lr: 0.000120 grad: 0.1556 (0.1686) loss: 0.9106 (0.9160) time: 0.1882 data: 0.0995 max mem: 8233 +Train: [17] [ 300/6250] eta: 0:18:58 lr: 0.000120 grad: 0.1501 (0.1654) loss: 0.9198 (0.9159) time: 0.1787 data: 0.0860 max mem: 8233 +Train: [17] [ 400/6250] eta: 0:18:14 lr: 0.000120 grad: 0.1504 (0.1641) loss: 0.9136 (0.9157) time: 0.1736 data: 0.0864 max mem: 8233 +Train: [17] [ 500/6250] eta: 0:17:34 lr: 0.000120 grad: 0.1511 (0.1626) loss: 0.9152 (0.9155) time: 0.1577 data: 0.0679 max mem: 8233 +Train: [17] [ 600/6250] eta: 0:16:56 lr: 0.000120 grad: 0.1465 (0.1620) loss: 0.9171 (0.9155) time: 0.1546 data: 0.0573 max mem: 8233 +Train: [17] [ 700/6250] eta: 0:16:25 lr: 0.000120 grad: 0.1424 (0.1618) loss: 0.9199 (0.9155) time: 0.1669 data: 0.0677 max mem: 8233 +Train: [17] [ 800/6250] eta: 0:16:10 lr: 0.000120 grad: 0.1566 (0.1607) loss: 0.9128 (0.9156) time: 0.2040 data: 0.1198 max mem: 8233 +Train: [17] [ 900/6250] eta: 0:15:48 lr: 0.000120 grad: 0.1579 (0.1605) loss: 0.9181 (0.9159) time: 0.1458 data: 0.0345 max mem: 8233 +Train: [17] [1000/6250] eta: 0:15:37 lr: 0.000120 grad: 0.1521 (0.1601) loss: 0.9185 (0.9161) time: 0.2332 data: 0.1611 max mem: 8233 +Train: [17] [1100/6250] eta: 0:15:11 lr: 0.000120 grad: 0.1487 (0.1595) loss: 0.9172 (0.9161) time: 0.1427 data: 0.0521 max mem: 8233 +Train: [17] [1200/6250] eta: 0:14:48 lr: 0.000120 grad: 0.1521 (0.1592) loss: 0.9177 (0.9161) time: 0.1759 data: 0.0979 max mem: 8233 +Train: [17] [1300/6250] eta: 0:14:24 lr: 0.000120 grad: 0.1570 (0.1590) loss: 0.9173 (0.9160) time: 0.1821 data: 0.1042 max mem: 8233 +Train: [17] [1400/6250] eta: 0:14:06 lr: 0.000120 grad: 0.1420 (0.1585) loss: 0.9200 (0.9161) time: 0.2180 data: 0.1524 max mem: 8233 +Train: [17] [1500/6250] eta: 0:13:50 lr: 0.000120 grad: 0.1564 (0.1584) loss: 0.9145 (0.9161) time: 0.2013 data: 0.1170 max mem: 8233 +Train: [17] [1600/6250] eta: 0:13:26 lr: 0.000120 grad: 0.1493 (0.1581) loss: 0.9167 (0.9161) time: 0.1576 data: 0.0818 max mem: 8233 +Train: [17] [1700/6250] eta: 0:13:08 lr: 0.000120 grad: 0.1635 (0.1579) loss: 0.9184 (0.9161) time: 0.1649 data: 0.0744 max mem: 8233 +Train: [17] [1800/6250] eta: 0:12:47 lr: 0.000120 grad: 0.1524 (0.1578) loss: 0.9181 (0.9161) time: 0.1730 data: 0.0833 max mem: 8233 +Train: [17] [1900/6250] eta: 0:12:26 lr: 0.000120 grad: 0.1478 (0.1575) loss: 0.9144 (0.9160) time: 0.1504 data: 0.0615 max mem: 8233 +Train: [17] [2000/6250] eta: 0:12:06 lr: 0.000120 grad: 0.1488 (0.1572) loss: 0.9175 (0.9160) time: 0.1603 data: 0.0587 max mem: 8233 +Train: [17] [2100/6250] eta: 0:11:49 lr: 0.000120 grad: 0.1454 (0.1571) loss: 0.9179 (0.9160) time: 0.1868 data: 0.0980 max mem: 8233 +Train: [17] [2200/6250] eta: 0:11:32 lr: 0.000120 grad: 0.1490 (0.1569) loss: 0.9145 (0.9160) time: 0.2026 data: 0.1172 max mem: 8233 +Train: [17] [2300/6250] eta: 0:11:15 lr: 0.000120 grad: 0.1584 (0.1568) loss: 0.9122 (0.9160) time: 0.2404 data: 0.1589 max mem: 8233 +Train: [17] [2400/6250] eta: 0:10:56 lr: 0.000120 grad: 0.1494 (0.1567) loss: 0.9178 (0.9160) time: 0.1687 data: 0.0790 max mem: 8233 +Train: [17] [2500/6250] eta: 0:10:44 lr: 0.000120 grad: 0.1574 (0.1567) loss: 0.9103 (0.9159) time: 0.3514 data: 0.2470 max mem: 8233 +Train: [17] [2600/6250] eta: 0:10:24 lr: 0.000120 grad: 0.1509 (0.1566) loss: 0.9126 (0.9159) time: 0.1498 data: 0.0647 max mem: 8233 +Train: [17] [2700/6250] eta: 0:10:04 lr: 0.000120 grad: 0.1541 (0.1567) loss: 0.9138 (0.9159) time: 0.1287 data: 0.0645 max mem: 8233 +Train: [17] [2800/6250] eta: 0:09:47 lr: 0.000120 grad: 0.1509 (0.1566) loss: 0.9145 (0.9158) time: 0.1394 data: 0.0667 max mem: 8233 +Train: [17] [2900/6250] eta: 0:09:29 lr: 0.000120 grad: 0.1581 (0.1567) loss: 0.9109 (0.9157) time: 0.1551 data: 0.0757 max mem: 8233 +Train: [17] [3000/6250] eta: 0:09:11 lr: 0.000120 grad: 0.1547 (0.1570) loss: 0.9137 (0.9156) time: 0.1534 data: 0.0751 max mem: 8233 +Train: [17] [3100/6250] eta: 0:08:53 lr: 0.000120 grad: 0.1733 (0.1573) loss: 0.9149 (0.9156) time: 0.1678 data: 0.0853 max mem: 8233 +Train: [17] [3200/6250] eta: 0:08:35 lr: 0.000120 grad: 0.1469 (0.1573) loss: 0.9130 (0.9155) time: 0.1534 data: 0.0684 max mem: 8233 +Train: [17] [3300/6250] eta: 0:08:18 lr: 0.000120 grad: 0.1470 (0.1574) loss: 0.9154 (0.9155) time: 0.1912 data: 0.1133 max mem: 8233 +Train: [17] [3400/6250] eta: 0:08:01 lr: 0.000120 grad: 0.1548 (0.1575) loss: 0.9140 (0.9154) time: 0.2465 data: 0.1645 max mem: 8233 +Train: [17] [3500/6250] eta: 0:07:44 lr: 0.000120 grad: 0.1513 (0.1576) loss: 0.9156 (0.9154) time: 0.1131 data: 0.0003 max mem: 8233 +Train: [17] [3600/6250] eta: 0:07:26 lr: 0.000120 grad: 0.1541 (0.1577) loss: 0.9138 (0.9153) time: 0.1330 data: 0.0531 max mem: 8233 +Train: [17] [3700/6250] eta: 0:07:09 lr: 0.000120 grad: 0.1537 (0.1578) loss: 0.9148 (0.9153) time: 0.1460 data: 0.0695 max mem: 8233 +Train: [17] [3800/6250] eta: 0:06:54 lr: 0.000120 grad: 0.1520 (0.1579) loss: 0.9152 (0.9153) time: 0.3468 data: 0.2640 max mem: 8233 +Train: [17] [3900/6250] eta: 0:06:35 lr: 0.000120 grad: 0.1465 (0.1578) loss: 0.9168 (0.9153) time: 0.1709 data: 0.0837 max mem: 8233 +Train: [17] [4000/6250] eta: 0:06:18 lr: 0.000120 grad: 0.1406 (0.1577) loss: 0.9169 (0.9153) time: 0.1520 data: 0.0780 max mem: 8233 +Train: [17] [4100/6250] eta: 0:06:01 lr: 0.000120 grad: 0.1527 (0.1576) loss: 0.9199 (0.9153) time: 0.2163 data: 0.1433 max mem: 8233 +Train: [17] [4200/6250] eta: 0:05:44 lr: 0.000120 grad: 0.1507 (0.1574) loss: 0.9144 (0.9154) time: 0.1473 data: 0.0567 max mem: 8233 +Train: [17] [4300/6250] eta: 0:05:27 lr: 0.000120 grad: 0.1536 (0.1574) loss: 0.9148 (0.9153) time: 0.1473 data: 0.0575 max mem: 8233 +Train: [17] [4400/6250] eta: 0:05:10 lr: 0.000120 grad: 0.1455 (0.1573) loss: 0.9161 (0.9154) time: 0.1390 data: 0.0547 max mem: 8233 +Train: [17] [4500/6250] eta: 0:04:53 lr: 0.000120 grad: 0.1479 (0.1571) loss: 0.9158 (0.9153) time: 0.1438 data: 0.0650 max mem: 8233 +Train: [17] [4600/6250] eta: 0:04:36 lr: 0.000120 grad: 0.1528 (0.1570) loss: 0.9080 (0.9153) time: 0.1643 data: 0.0769 max mem: 8233 +Train: [17] [4700/6250] eta: 0:04:19 lr: 0.000120 grad: 0.1506 (0.1570) loss: 0.9119 (0.9152) time: 0.1427 data: 0.0352 max mem: 8233 +Train: [17] [4800/6250] eta: 0:04:03 lr: 0.000120 grad: 0.1459 (0.1570) loss: 0.9129 (0.9152) time: 0.2377 data: 0.1571 max mem: 8233 +Train: [17] [4900/6250] eta: 0:03:46 lr: 0.000119 grad: 0.1577 (0.1570) loss: 0.9166 (0.9152) time: 0.1697 data: 0.0843 max mem: 8233 +Train: [17] [5000/6250] eta: 0:03:29 lr: 0.000119 grad: 0.1426 (0.1570) loss: 0.9093 (0.9151) time: 0.1113 data: 0.0003 max mem: 8233 +Train: [17] [5100/6250] eta: 0:03:13 lr: 0.000119 grad: 0.1452 (0.1569) loss: 0.9119 (0.9151) time: 0.1312 data: 0.0458 max mem: 8233 +Train: [17] [5200/6250] eta: 0:02:56 lr: 0.000119 grad: 0.1445 (0.1569) loss: 0.9184 (0.9151) time: 0.1650 data: 0.0909 max mem: 8233 +Train: [17] [5300/6250] eta: 0:02:39 lr: 0.000119 grad: 0.1417 (0.1568) loss: 0.9174 (0.9151) time: 0.1893 data: 0.1034 max mem: 8233 +Train: [17] [5400/6250] eta: 0:02:22 lr: 0.000119 grad: 0.1580 (0.1568) loss: 0.9142 (0.9151) time: 0.1204 data: 0.0461 max mem: 8233 +Train: [17] [5500/6250] eta: 0:02:05 lr: 0.000119 grad: 0.1553 (0.1568) loss: 0.9172 (0.9150) time: 0.1315 data: 0.0492 max mem: 8233 +Train: [17] [5600/6250] eta: 0:01:48 lr: 0.000119 grad: 0.1450 (0.1567) loss: 0.9102 (0.9150) time: 0.1557 data: 0.0783 max mem: 8233 +Train: [17] [5700/6250] eta: 0:01:31 lr: 0.000119 grad: 0.1517 (0.1567) loss: 0.9131 (0.9150) time: 0.1753 data: 0.1042 max mem: 8233 +Train: [17] [5800/6250] eta: 0:01:15 lr: 0.000119 grad: 0.1392 (0.1566) loss: 0.9128 (0.9150) time: 0.1030 data: 0.0003 max mem: 8233 +Train: [17] [5900/6250] eta: 0:00:58 lr: 0.000119 grad: 0.1738 (0.1567) loss: 0.9142 (0.9149) time: 0.1733 data: 0.0929 max mem: 8233 +Train: [17] [6000/6250] eta: 0:00:41 lr: 0.000119 grad: 0.1539 (0.1566) loss: 0.9152 (0.9149) time: 0.2338 data: 0.1648 max mem: 8233 +Train: [17] [6100/6250] eta: 0:00:25 lr: 0.000119 grad: 0.1596 (0.1565) loss: 0.9147 (0.9149) time: 0.1460 data: 0.0656 max mem: 8233 +Train: [17] [6200/6250] eta: 0:00:08 lr: 0.000119 grad: 0.1477 (0.1565) loss: 0.9177 (0.9149) time: 0.1341 data: 0.0428 max mem: 8233 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.1475 (0.1564) loss: 0.9146 (0.9149) time: 0.1600 data: 0.0895 max mem: 8233 +Train: [17] Total time: 0:17:33 (0.1686 s / it) +Averaged stats: lr: 0.000119 grad: 0.1475 (0.1564) loss: 0.9146 (0.9149) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:04:10 loss: 0.9270 (0.9270) time: 4.0480 data: 3.9808 max mem: 8233 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.9204 (0.9179) time: 0.1372 data: 0.1165 max mem: 8233 +Eval (hcp-train-subset): [17] Total time: 0:00:14 (0.2362 s / it) +Averaged stats (hcp-train-subset): loss: 0.9204 (0.9179) +Eval (hcp-val): [17] [ 0/62] eta: 0:06:25 loss: 0.9086 (0.9086) time: 6.2236 data: 6.1980 max mem: 8233 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.9129 (0.9139) time: 0.1053 data: 0.0849 max mem: 8233 +Eval (hcp-val): [17] Total time: 0:00:15 (0.2436 s / it) +Averaged stats (hcp-val): loss: 0.9129 (0.9139) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 10:37:58 lr: 0.000119 grad: 0.1617 (0.1617) loss: 0.9082 (0.9082) time: 6.1246 data: 6.0133 max mem: 8233 +Train: [18] [ 100/6250] eta: 0:22:24 lr: 0.000119 grad: 0.1749 (0.1682) loss: 0.9060 (0.9156) time: 0.1677 data: 0.0882 max mem: 8233 +Train: [18] [ 200/6250] eta: 0:21:16 lr: 0.000119 grad: 0.1525 (0.1639) loss: 0.9142 (0.9139) time: 0.2104 data: 0.1036 max mem: 8233 +Train: [18] [ 300/6250] eta: 0:20:31 lr: 0.000119 grad: 0.1528 (0.1615) loss: 0.9134 (0.9144) time: 0.1924 data: 0.0958 max mem: 8233 +Train: [18] [ 400/6250] eta: 0:19:53 lr: 0.000119 grad: 0.1482 (0.1587) loss: 0.9167 (0.9152) time: 0.2189 data: 0.1178 max mem: 8233 +Train: [18] [ 500/6250] eta: 0:19:23 lr: 0.000119 grad: 0.1453 (0.1564) loss: 0.9155 (0.9155) time: 0.1727 data: 0.0757 max mem: 8233 +Train: [18] [ 600/6250] eta: 0:18:38 lr: 0.000119 grad: 0.1598 (0.1561) loss: 0.9178 (0.9158) time: 0.1371 data: 0.0468 max mem: 8233 +Train: [18] [ 700/6250] eta: 0:18:32 lr: 0.000119 grad: 0.1418 (0.1547) loss: 0.9198 (0.9160) time: 0.3187 data: 0.2313 max mem: 8233 +Train: [18] [ 800/6250] eta: 0:17:49 lr: 0.000119 grad: 0.1444 (0.1537) loss: 0.9151 (0.9160) time: 0.1752 data: 0.0820 max mem: 8233 +Train: [18] [ 900/6250] eta: 0:17:39 lr: 0.000119 grad: 0.1545 (0.1534) loss: 0.9163 (0.9159) time: 0.1358 data: 0.0395 max mem: 8233 +Train: [18] [1000/6250] eta: 0:17:11 lr: 0.000119 grad: 0.1572 (0.1533) loss: 0.9156 (0.9158) time: 0.1656 data: 0.0662 max mem: 8233 +Train: [18] [1100/6250] eta: 0:16:38 lr: 0.000119 grad: 0.1595 (0.1535) loss: 0.9136 (0.9158) time: 0.1669 data: 0.0821 max mem: 8233 +Train: [18] [1200/6250] eta: 0:16:26 lr: 0.000119 grad: 0.1463 (0.1535) loss: 0.9100 (0.9155) time: 0.2036 data: 0.1219 max mem: 8233 +Train: [18] [1300/6250] eta: 0:15:52 lr: 0.000119 grad: 0.1413 (0.1530) loss: 0.9128 (0.9154) time: 0.1510 data: 0.0677 max mem: 8233 +Train: [18] [1400/6250] eta: 0:15:23 lr: 0.000119 grad: 0.1571 (0.1529) loss: 0.9128 (0.9152) time: 0.1722 data: 0.0807 max mem: 8233 +Train: [18] [1500/6250] eta: 0:14:59 lr: 0.000119 grad: 0.1524 (0.1529) loss: 0.9088 (0.9149) time: 0.1796 data: 0.0975 max mem: 8233 +Train: [18] [1600/6250] eta: 0:14:40 lr: 0.000119 grad: 0.1447 (0.1531) loss: 0.9151 (0.9147) time: 0.2554 data: 0.1840 max mem: 8233 +Train: [18] [1700/6250] eta: 0:14:15 lr: 0.000119 grad: 0.1400 (0.1532) loss: 0.9193 (0.9146) time: 0.1545 data: 0.0700 max mem: 8233 +Train: [18] [1800/6250] eta: 0:13:51 lr: 0.000119 grad: 0.1479 (0.1531) loss: 0.9181 (0.9146) time: 0.1836 data: 0.1061 max mem: 8233 +Train: [18] [1900/6250] eta: 0:13:27 lr: 0.000119 grad: 0.1529 (0.1531) loss: 0.9153 (0.9145) time: 0.1839 data: 0.1005 max mem: 8233 +Train: [18] [2000/6250] eta: 0:13:03 lr: 0.000119 grad: 0.1407 (0.1531) loss: 0.9132 (0.9145) time: 0.1631 data: 0.0767 max mem: 8233 +Train: [18] [2100/6250] eta: 0:12:39 lr: 0.000119 grad: 0.1401 (0.1528) loss: 0.9172 (0.9145) time: 0.1407 data: 0.0578 max mem: 8233 +Train: [18] [2200/6250] eta: 0:12:15 lr: 0.000119 grad: 0.1512 (0.1527) loss: 0.9147 (0.9145) time: 0.1383 data: 0.0282 max mem: 8233 +Train: [18] [2300/6250] eta: 0:11:51 lr: 0.000119 grad: 0.1457 (0.1525) loss: 0.9220 (0.9146) time: 0.1597 data: 0.0774 max mem: 8233 +Train: [18] [2400/6250] eta: 0:11:30 lr: 0.000119 grad: 0.1481 (0.1522) loss: 0.9138 (0.9146) time: 0.1500 data: 0.0741 max mem: 8233 +Train: [18] [2500/6250] eta: 0:11:11 lr: 0.000119 grad: 0.1482 (0.1520) loss: 0.9160 (0.9146) time: 0.1713 data: 0.1010 max mem: 8233 +Train: [18] [2600/6250] eta: 0:10:51 lr: 0.000119 grad: 0.1428 (0.1519) loss: 0.9137 (0.9147) time: 0.1584 data: 0.0838 max mem: 8233 +Train: [18] [2700/6250] eta: 0:10:33 lr: 0.000119 grad: 0.1463 (0.1519) loss: 0.9119 (0.9146) time: 0.1870 data: 0.1057 max mem: 8233 +Train: [18] [2800/6250] eta: 0:10:17 lr: 0.000119 grad: 0.1503 (0.1518) loss: 0.9176 (0.9147) time: 0.2709 data: 0.1704 max mem: 8233 +Train: [18] [2900/6250] eta: 0:09:56 lr: 0.000119 grad: 0.1563 (0.1518) loss: 0.9174 (0.9147) time: 0.1792 data: 0.0918 max mem: 8233 +Train: [18] [3000/6250] eta: 0:09:38 lr: 0.000119 grad: 0.1450 (0.1517) loss: 0.9143 (0.9147) time: 0.2148 data: 0.1449 max mem: 8233 +Train: [18] [3100/6250] eta: 0:09:18 lr: 0.000119 grad: 0.1417 (0.1516) loss: 0.9152 (0.9147) time: 0.1587 data: 0.0764 max mem: 8233 +Train: [18] [3200/6250] eta: 0:08:59 lr: 0.000119 grad: 0.1426 (0.1514) loss: 0.9143 (0.9147) time: 0.1692 data: 0.0663 max mem: 8233 +Train: [18] [3300/6250] eta: 0:08:41 lr: 0.000119 grad: 0.1361 (0.1515) loss: 0.9164 (0.9146) time: 0.0946 data: 0.0096 max mem: 8233 +Train: [18] [3400/6250] eta: 0:08:23 lr: 0.000119 grad: 0.1454 (0.1513) loss: 0.9147 (0.9146) time: 0.2201 data: 0.1362 max mem: 8233 +Train: [18] [3500/6250] eta: 0:08:04 lr: 0.000119 grad: 0.1486 (0.1513) loss: 0.9121 (0.9146) time: 0.1248 data: 0.0170 max mem: 8233 +Train: [18] [3600/6250] eta: 0:07:46 lr: 0.000119 grad: 0.1403 (0.1512) loss: 0.9143 (0.9146) time: 0.1566 data: 0.0775 max mem: 8233 +Train: [18] [3700/6250] eta: 0:07:28 lr: 0.000119 grad: 0.1428 (0.1510) loss: 0.9147 (0.9146) time: 0.1854 data: 0.1047 max mem: 8233 +Train: [18] [3800/6250] eta: 0:07:09 lr: 0.000119 grad: 0.1424 (0.1508) loss: 0.9127 (0.9146) time: 0.1408 data: 0.0548 max mem: 8233 +Train: [18] [3900/6250] eta: 0:06:51 lr: 0.000119 grad: 0.1525 (0.1508) loss: 0.9090 (0.9146) time: 0.1825 data: 0.1033 max mem: 8233 +Train: [18] [4000/6250] eta: 0:06:33 lr: 0.000119 grad: 0.1383 (0.1507) loss: 0.9152 (0.9145) time: 0.1188 data: 0.0412 max mem: 8233 +Train: [18] [4100/6250] eta: 0:06:15 lr: 0.000119 grad: 0.1417 (0.1507) loss: 0.9114 (0.9145) time: 0.1678 data: 0.0770 max mem: 8233 +Train: [18] [4200/6250] eta: 0:05:57 lr: 0.000119 grad: 0.1399 (0.1506) loss: 0.9131 (0.9145) time: 0.1807 data: 0.0908 max mem: 8233 +Train: [18] [4300/6250] eta: 0:05:40 lr: 0.000119 grad: 0.1373 (0.1504) loss: 0.9134 (0.9144) time: 0.1572 data: 0.0707 max mem: 8233 +Train: [18] [4400/6250] eta: 0:05:22 lr: 0.000119 grad: 0.1445 (0.1502) loss: 0.9134 (0.9144) time: 0.1581 data: 0.0763 max mem: 8233 +Train: [18] [4500/6250] eta: 0:05:04 lr: 0.000119 grad: 0.1436 (0.1502) loss: 0.9144 (0.9144) time: 0.1659 data: 0.0823 max mem: 8233 +Train: [18] [4600/6250] eta: 0:04:46 lr: 0.000119 grad: 0.1496 (0.1502) loss: 0.9111 (0.9144) time: 0.1715 data: 0.0819 max mem: 8233 +Train: [18] [4700/6250] eta: 0:04:29 lr: 0.000119 grad: 0.1433 (0.1502) loss: 0.9133 (0.9143) time: 0.1296 data: 0.0455 max mem: 8233 +Train: [18] [4800/6250] eta: 0:04:11 lr: 0.000119 grad: 0.1520 (0.1501) loss: 0.9093 (0.9143) time: 0.1384 data: 0.0513 max mem: 8233 +Train: [18] [4900/6250] eta: 0:03:53 lr: 0.000119 grad: 0.1419 (0.1500) loss: 0.9159 (0.9142) time: 0.1649 data: 0.0904 max mem: 8233 +Train: [18] [5000/6250] eta: 0:03:36 lr: 0.000119 grad: 0.1344 (0.1499) loss: 0.9142 (0.9142) time: 0.1584 data: 0.0776 max mem: 8233 +Train: [18] [5100/6250] eta: 0:03:18 lr: 0.000119 grad: 0.1416 (0.1498) loss: 0.9122 (0.9141) time: 0.1916 data: 0.1186 max mem: 8233 +Train: [18] [5200/6250] eta: 0:03:01 lr: 0.000119 grad: 0.1487 (0.1498) loss: 0.9139 (0.9141) time: 0.1518 data: 0.0745 max mem: 8233 +Train: [18] [5300/6250] eta: 0:02:44 lr: 0.000119 grad: 0.1437 (0.1499) loss: 0.9135 (0.9141) time: 0.1754 data: 0.0978 max mem: 8233 +Train: [18] [5400/6250] eta: 0:02:27 lr: 0.000119 grad: 0.1446 (0.1499) loss: 0.9122 (0.9140) time: 0.1352 data: 0.0453 max mem: 8233 +Train: [18] [5500/6250] eta: 0:02:09 lr: 0.000119 grad: 0.1408 (0.1498) loss: 0.9102 (0.9140) time: 0.1593 data: 0.0783 max mem: 8233 +Train: [18] [5600/6250] eta: 0:01:52 lr: 0.000119 grad: 0.1381 (0.1497) loss: 0.9066 (0.9139) time: 0.1602 data: 0.0770 max mem: 8233 +Train: [18] [5700/6250] eta: 0:01:34 lr: 0.000119 grad: 0.1499 (0.1497) loss: 0.9114 (0.9139) time: 0.1297 data: 0.0430 max mem: 8233 +Train: [18] [5800/6250] eta: 0:01:17 lr: 0.000118 grad: 0.1403 (0.1496) loss: 0.9133 (0.9138) time: 0.1218 data: 0.0296 max mem: 8233 +Train: [18] [5900/6250] eta: 0:01:00 lr: 0.000118 grad: 0.1540 (0.1496) loss: 0.9135 (0.9138) time: 0.3459 data: 0.2513 max mem: 8233 +Train: [18] [6000/6250] eta: 0:00:43 lr: 0.000118 grad: 0.1462 (0.1496) loss: 0.9150 (0.9138) time: 0.1137 data: 0.0081 max mem: 8233 +Train: [18] [6100/6250] eta: 0:00:25 lr: 0.000118 grad: 0.1503 (0.1496) loss: 0.9125 (0.9137) time: 0.1447 data: 0.0531 max mem: 8233 +Train: [18] [6200/6250] eta: 0:00:08 lr: 0.000118 grad: 0.1483 (0.1495) loss: 0.9085 (0.9137) time: 0.1638 data: 0.0818 max mem: 8233 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.1488 (0.1495) loss: 0.9141 (0.9137) time: 0.1540 data: 0.0683 max mem: 8233 +Train: [18] Total time: 0:18:01 (0.1731 s / it) +Averaged stats: lr: 0.000118 grad: 0.1488 (0.1495) loss: 0.9141 (0.9137) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:03:55 loss: 0.9270 (0.9270) time: 3.7979 data: 3.7075 max mem: 8233 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.9158 (0.9167) time: 0.1528 data: 0.1320 max mem: 8233 +Eval (hcp-train-subset): [18] Total time: 0:00:14 (0.2301 s / it) +Averaged stats (hcp-train-subset): loss: 0.9158 (0.9167) +Eval (hcp-val): [18] [ 0/62] eta: 0:05:34 loss: 0.9098 (0.9098) time: 5.3924 data: 5.3648 max mem: 8233 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.9128 (0.9129) time: 0.1074 data: 0.0867 max mem: 8233 +Eval (hcp-val): [18] Total time: 0:00:14 (0.2365 s / it) +Averaged stats (hcp-val): loss: 0.9128 (0.9129) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 9:55:30 lr: 0.000118 grad: 0.1344 (0.1344) loss: 0.9187 (0.9187) time: 5.7169 data: 5.5532 max mem: 8233 +Train: [19] [ 100/6250] eta: 0:22:32 lr: 0.000118 grad: 0.1346 (0.1324) loss: 0.9196 (0.9251) time: 0.1647 data: 0.0685 max mem: 8233 +Train: [19] [ 200/6250] eta: 0:19:44 lr: 0.000118 grad: 0.1390 (0.1357) loss: 0.9149 (0.9220) time: 0.1853 data: 0.0851 max mem: 8233 +Train: [19] [ 300/6250] eta: 0:18:34 lr: 0.000118 grad: 0.1410 (0.1369) loss: 0.9122 (0.9196) time: 0.1638 data: 0.0721 max mem: 8233 +Train: [19] [ 400/6250] eta: 0:17:49 lr: 0.000118 grad: 0.1403 (0.1377) loss: 0.9140 (0.9184) time: 0.1727 data: 0.0715 max mem: 8233 +Train: [19] [ 500/6250] eta: 0:17:11 lr: 0.000118 grad: 0.1455 (0.1389) loss: 0.9123 (0.9174) time: 0.1488 data: 0.0504 max mem: 8233 +Train: [19] [ 600/6250] eta: 0:16:39 lr: 0.000118 grad: 0.1365 (0.1386) loss: 0.9123 (0.9167) time: 0.1708 data: 0.0854 max mem: 8233 +Train: [19] [ 700/6250] eta: 0:16:02 lr: 0.000118 grad: 0.1445 (0.1398) loss: 0.9116 (0.9163) time: 0.1497 data: 0.0627 max mem: 8233 +Train: [19] [ 800/6250] eta: 0:15:35 lr: 0.000118 grad: 0.1434 (0.1402) loss: 0.9144 (0.9159) time: 0.1782 data: 0.0906 max mem: 8233 +Train: [19] [ 900/6250] eta: 0:15:13 lr: 0.000118 grad: 0.1492 (0.1408) loss: 0.9112 (0.9157) time: 0.1356 data: 0.0486 max mem: 8233 +Train: [19] [1000/6250] eta: 0:14:56 lr: 0.000118 grad: 0.1408 (0.1411) loss: 0.9155 (0.9155) time: 0.1659 data: 0.0970 max mem: 8233 +Train: [19] [1100/6250] eta: 0:14:42 lr: 0.000118 grad: 0.1444 (0.1412) loss: 0.9113 (0.9152) time: 0.2252 data: 0.1527 max mem: 8233 +Train: [19] [1200/6250] eta: 0:14:27 lr: 0.000118 grad: 0.1533 (0.1417) loss: 0.9172 (0.9151) time: 0.1516 data: 0.0486 max mem: 8233 +Train: [19] [1300/6250] eta: 0:14:24 lr: 0.000118 grad: 0.1320 (0.1418) loss: 0.9100 (0.9148) time: 0.1962 data: 0.1104 max mem: 8233 +Train: [19] [1400/6250] eta: 0:14:05 lr: 0.000118 grad: 0.1427 (0.1419) loss: 0.9135 (0.9146) time: 0.1779 data: 0.1105 max mem: 8233 +Train: [19] [1500/6250] eta: 0:13:43 lr: 0.000118 grad: 0.1436 (0.1423) loss: 0.9151 (0.9146) time: 0.1647 data: 0.0786 max mem: 8233 +Train: [19] [1600/6250] eta: 0:13:25 lr: 0.000118 grad: 0.1382 (0.1421) loss: 0.9161 (0.9145) time: 0.1597 data: 0.0759 max mem: 8233 +Train: [19] [1700/6250] eta: 0:13:07 lr: 0.000118 grad: 0.1377 (0.1420) loss: 0.9116 (0.9144) time: 0.1845 data: 0.1035 max mem: 8233 +Train: [19] [1800/6250] eta: 0:12:50 lr: 0.000118 grad: 0.1502 (0.1420) loss: 0.9133 (0.9143) time: 0.1772 data: 0.1090 max mem: 8233 +Train: [19] [1900/6250] eta: 0:12:32 lr: 0.000118 grad: 0.1469 (0.1420) loss: 0.9098 (0.9142) time: 0.1735 data: 0.0831 max mem: 8233 +Train: [19] [2000/6250] eta: 0:12:09 lr: 0.000118 grad: 0.1427 (0.1423) loss: 0.9119 (0.9140) time: 0.1581 data: 0.0815 max mem: 8233 +Train: [19] [2100/6250] eta: 0:11:51 lr: 0.000118 grad: 0.1543 (0.1426) loss: 0.9091 (0.9139) time: 0.1672 data: 0.0864 max mem: 8233 +Train: [19] [2200/6250] eta: 0:11:32 lr: 0.000118 grad: 0.1390 (0.1426) loss: 0.9158 (0.9138) time: 0.1261 data: 0.0478 max mem: 8233 +Train: [19] [2300/6250] eta: 0:11:13 lr: 0.000118 grad: 0.1380 (0.1428) loss: 0.9098 (0.9137) time: 0.1538 data: 0.0680 max mem: 8233 +Train: [19] [2400/6250] eta: 0:10:53 lr: 0.000118 grad: 0.1418 (0.1430) loss: 0.9135 (0.9137) time: 0.1553 data: 0.0678 max mem: 8233 +Train: [19] [2500/6250] eta: 0:10:34 lr: 0.000118 grad: 0.1444 (0.1432) loss: 0.9096 (0.9136) time: 0.1787 data: 0.0934 max mem: 8233 +Train: [19] [2600/6250] eta: 0:10:17 lr: 0.000118 grad: 0.1469 (0.1434) loss: 0.9113 (0.9136) time: 0.1779 data: 0.1032 max mem: 8233 +Train: [19] [2700/6250] eta: 0:09:59 lr: 0.000118 grad: 0.1378 (0.1434) loss: 0.9129 (0.9136) time: 0.1531 data: 0.0871 max mem: 8233 +Train: [19] [2800/6250] eta: 0:09:44 lr: 0.000118 grad: 0.1396 (0.1434) loss: 0.9096 (0.9135) time: 0.2439 data: 0.1721 max mem: 8233 +Train: [19] [2900/6250] eta: 0:09:27 lr: 0.000118 grad: 0.1473 (0.1435) loss: 0.9121 (0.9135) time: 0.1676 data: 0.0862 max mem: 8233 +Train: [19] [3000/6250] eta: 0:09:11 lr: 0.000118 grad: 0.1470 (0.1437) loss: 0.9124 (0.9134) time: 0.1875 data: 0.1026 max mem: 8233 +Train: [19] [3100/6250] eta: 0:08:55 lr: 0.000118 grad: 0.1448 (0.1437) loss: 0.9114 (0.9134) time: 0.1537 data: 0.0722 max mem: 8233 +Train: [19] [3200/6250] eta: 0:08:39 lr: 0.000118 grad: 0.1438 (0.1437) loss: 0.9104 (0.9133) time: 0.1751 data: 0.1077 max mem: 8233 +Train: [19] [3300/6250] eta: 0:08:23 lr: 0.000118 grad: 0.1462 (0.1440) loss: 0.9100 (0.9133) time: 0.1320 data: 0.0419 max mem: 8233 +Train: [19] [3400/6250] eta: 0:08:08 lr: 0.000118 grad: 0.1362 (0.1440) loss: 0.9121 (0.9132) time: 0.1264 data: 0.0215 max mem: 8233 +Train: [19] [3500/6250] eta: 0:07:50 lr: 0.000118 grad: 0.1325 (0.1440) loss: 0.9139 (0.9132) time: 0.1582 data: 0.0583 max mem: 8233 +Train: [19] [3600/6250] eta: 0:07:33 lr: 0.000118 grad: 0.1451 (0.1441) loss: 0.9115 (0.9132) time: 0.1530 data: 0.0651 max mem: 8233 +Train: [19] [3700/6250] eta: 0:07:16 lr: 0.000118 grad: 0.1459 (0.1441) loss: 0.9109 (0.9131) time: 0.2308 data: 0.1358 max mem: 8233 +Train: [19] [3800/6250] eta: 0:06:59 lr: 0.000118 grad: 0.1541 (0.1442) loss: 0.9125 (0.9131) time: 0.1779 data: 0.0885 max mem: 8233 +Train: [19] [3900/6250] eta: 0:06:41 lr: 0.000118 grad: 0.1438 (0.1442) loss: 0.9122 (0.9131) time: 0.1635 data: 0.0647 max mem: 8233 +Train: [19] [4000/6250] eta: 0:06:23 lr: 0.000118 grad: 0.1419 (0.1442) loss: 0.9132 (0.9131) time: 0.1413 data: 0.0606 max mem: 8233 +Train: [19] [4100/6250] eta: 0:06:05 lr: 0.000118 grad: 0.1394 (0.1441) loss: 0.9112 (0.9130) time: 0.1558 data: 0.0599 max mem: 8233 +Train: [19] [4200/6250] eta: 0:05:48 lr: 0.000118 grad: 0.1401 (0.1441) loss: 0.9121 (0.9130) time: 0.1523 data: 0.0697 max mem: 8233 +Train: [19] [4300/6250] eta: 0:05:31 lr: 0.000118 grad: 0.1417 (0.1441) loss: 0.9129 (0.9130) time: 0.1415 data: 0.0576 max mem: 8233 +Train: [19] [4400/6250] eta: 0:05:14 lr: 0.000118 grad: 0.1413 (0.1441) loss: 0.9100 (0.9130) time: 0.1705 data: 0.0826 max mem: 8233 +Train: [19] [4500/6250] eta: 0:04:57 lr: 0.000118 grad: 0.1467 (0.1441) loss: 0.9124 (0.9130) time: 0.1826 data: 0.0942 max mem: 8233 +Train: [19] [4600/6250] eta: 0:04:41 lr: 0.000118 grad: 0.1355 (0.1441) loss: 0.9106 (0.9130) time: 0.3062 data: 0.2007 max mem: 8233 +Train: [19] [4700/6250] eta: 0:04:24 lr: 0.000118 grad: 0.1376 (0.1441) loss: 0.9116 (0.9130) time: 0.1528 data: 0.0719 max mem: 8233 +Train: [19] [4800/6250] eta: 0:04:06 lr: 0.000118 grad: 0.1375 (0.1441) loss: 0.9086 (0.9129) time: 0.1712 data: 0.0923 max mem: 8233 +Train: [19] [4900/6250] eta: 0:03:49 lr: 0.000118 grad: 0.1429 (0.1441) loss: 0.9096 (0.9129) time: 0.1596 data: 0.0688 max mem: 8233 +Train: [19] [5000/6250] eta: 0:03:32 lr: 0.000118 grad: 0.1356 (0.1441) loss: 0.9132 (0.9129) time: 0.2290 data: 0.1431 max mem: 8233 +Train: [19] [5100/6250] eta: 0:03:15 lr: 0.000118 grad: 0.1386 (0.1442) loss: 0.9129 (0.9129) time: 0.1625 data: 0.0710 max mem: 8233 +Train: [19] [5200/6250] eta: 0:02:58 lr: 0.000118 grad: 0.1479 (0.1442) loss: 0.9104 (0.9128) time: 0.1549 data: 0.0793 max mem: 8233 +Train: [19] [5300/6250] eta: 0:02:41 lr: 0.000118 grad: 0.1420 (0.1443) loss: 0.9104 (0.9128) time: 0.1650 data: 0.0808 max mem: 8233 +Train: [19] [5400/6250] eta: 0:02:24 lr: 0.000118 grad: 0.1516 (0.1443) loss: 0.9169 (0.9128) time: 0.1427 data: 0.0562 max mem: 8233 +Train: [19] [5500/6250] eta: 0:02:07 lr: 0.000118 grad: 0.1408 (0.1443) loss: 0.9087 (0.9128) time: 0.1683 data: 0.0886 max mem: 8233 +Train: [19] [5600/6250] eta: 0:01:50 lr: 0.000118 grad: 0.1384 (0.1442) loss: 0.9114 (0.9127) time: 0.1550 data: 0.0491 max mem: 8233 +Train: [19] [5700/6250] eta: 0:01:33 lr: 0.000118 grad: 0.1405 (0.1443) loss: 0.9092 (0.9127) time: 0.1439 data: 0.0573 max mem: 8233 +Train: [19] [5800/6250] eta: 0:01:16 lr: 0.000118 grad: 0.1330 (0.1442) loss: 0.9109 (0.9127) time: 0.1747 data: 0.0979 max mem: 8233 +Train: [19] [5900/6250] eta: 0:00:59 lr: 0.000118 grad: 0.1369 (0.1442) loss: 0.9146 (0.9126) time: 0.1478 data: 0.0655 max mem: 8233 +Train: [19] [6000/6250] eta: 0:00:42 lr: 0.000118 grad: 0.1389 (0.1442) loss: 0.9137 (0.9126) time: 0.1597 data: 0.0896 max mem: 8233 +Train: [19] [6100/6250] eta: 0:00:25 lr: 0.000117 grad: 0.1356 (0.1440) loss: 0.9109 (0.9126) time: 0.1615 data: 0.0711 max mem: 8233 +Train: [19] [6200/6250] eta: 0:00:08 lr: 0.000117 grad: 0.1297 (0.1439) loss: 0.9149 (0.9126) time: 0.1424 data: 0.0594 max mem: 8233 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.1361 (0.1438) loss: 0.9110 (0.9126) time: 0.1814 data: 0.0969 max mem: 8233 +Train: [19] Total time: 0:17:40 (0.1697 s / it) +Averaged stats: lr: 0.000117 grad: 0.1361 (0.1438) loss: 0.9110 (0.9126) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:06:37 loss: 0.9213 (0.9213) time: 6.4061 data: 6.3794 max mem: 8233 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.9165 (0.9157) time: 0.1359 data: 0.1148 max mem: 8233 +Eval (hcp-train-subset): [19] Total time: 0:00:14 (0.2390 s / it) +Averaged stats (hcp-train-subset): loss: 0.9165 (0.9157) +Making plots (hcp-train-subset): example=6 +Eval (hcp-val): [19] [ 0/62] eta: 0:04:52 loss: 0.9060 (0.9060) time: 4.7202 data: 4.6901 max mem: 8233 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.9097 (0.9107) time: 0.1515 data: 0.1291 max mem: 8233 +Eval (hcp-val): [19] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-val): loss: 0.9097 (0.9107) +Making plots (hcp-val): example=51 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-00019.pth +Train: [20] [ 0/6250] eta: 8:42:45 lr: 0.000117 grad: 0.1735 (0.1735) loss: 0.9150 (0.9150) time: 5.0185 data: 4.8017 max mem: 8233 +Train: [20] [ 100/6250] eta: 0:22:39 lr: 0.000117 grad: 0.1357 (0.1463) loss: 0.9173 (0.9151) time: 0.1613 data: 0.0734 max mem: 8233 +Train: [20] [ 200/6250] eta: 0:19:21 lr: 0.000117 grad: 0.1281 (0.1440) loss: 0.9193 (0.9151) time: 0.1693 data: 0.0871 max mem: 8233 +Train: [20] [ 300/6250] eta: 0:18:17 lr: 0.000117 grad: 0.1401 (0.1431) loss: 0.9064 (0.9138) time: 0.1682 data: 0.0759 max mem: 8233 +Train: [20] [ 400/6250] eta: 0:17:30 lr: 0.000117 grad: 0.1400 (0.1427) loss: 0.9104 (0.9131) time: 0.1780 data: 0.0776 max mem: 8233 +Train: [20] [ 500/6250] eta: 0:16:54 lr: 0.000117 grad: 0.1332 (0.1416) loss: 0.9136 (0.9131) time: 0.1553 data: 0.0606 max mem: 8233 +Train: [20] [ 600/6250] eta: 0:16:27 lr: 0.000117 grad: 0.1371 (0.1413) loss: 0.9099 (0.9128) time: 0.1563 data: 0.0618 max mem: 8233 +Train: [20] [ 700/6250] eta: 0:15:58 lr: 0.000117 grad: 0.1459 (0.1412) loss: 0.9142 (0.9126) time: 0.1419 data: 0.0437 max mem: 8233 +Train: [20] [ 800/6250] eta: 0:15:36 lr: 0.000117 grad: 0.1310 (0.1405) loss: 0.9097 (0.9124) time: 0.1766 data: 0.0731 max mem: 8233 +Train: [20] [ 900/6250] eta: 0:15:14 lr: 0.000117 grad: 0.1484 (0.1409) loss: 0.9090 (0.9122) time: 0.1653 data: 0.0864 max mem: 8233 +Train: [20] [1000/6250] eta: 0:14:53 lr: 0.000117 grad: 0.1355 (0.1408) loss: 0.9089 (0.9120) time: 0.1678 data: 0.0821 max mem: 8233 +Train: [20] [1100/6250] eta: 0:14:33 lr: 0.000117 grad: 0.1282 (0.1405) loss: 0.9079 (0.9118) time: 0.1756 data: 0.0896 max mem: 8233 +Train: [20] [1200/6250] eta: 0:14:18 lr: 0.000117 grad: 0.1460 (0.1403) loss: 0.9094 (0.9117) time: 0.1597 data: 0.0695 max mem: 8233 +Train: [20] [1300/6250] eta: 0:14:05 lr: 0.000117 grad: 0.1375 (0.1403) loss: 0.9043 (0.9114) time: 0.1628 data: 0.0926 max mem: 8233 +Train: [20] [1400/6250] eta: 0:13:48 lr: 0.000117 grad: 0.1373 (0.1403) loss: 0.9124 (0.9114) time: 0.1698 data: 0.0932 max mem: 8233 +Train: [20] [1500/6250] eta: 0:13:27 lr: 0.000117 grad: 0.1390 (0.1401) loss: 0.9090 (0.9112) time: 0.1539 data: 0.0714 max mem: 8233 +Train: [20] [1600/6250] eta: 0:13:07 lr: 0.000117 grad: 0.1413 (0.1402) loss: 0.9065 (0.9111) time: 0.1888 data: 0.1019 max mem: 8233 +Train: [20] [1700/6250] eta: 0:12:49 lr: 0.000117 grad: 0.1463 (0.1403) loss: 0.9020 (0.9111) time: 0.1509 data: 0.0706 max mem: 8233 +Train: [20] [1800/6250] eta: 0:12:34 lr: 0.000117 grad: 0.1359 (0.1403) loss: 0.9107 (0.9111) time: 0.1960 data: 0.1176 max mem: 8233 +Train: [20] [1900/6250] eta: 0:12:15 lr: 0.000117 grad: 0.1338 (0.1401) loss: 0.9133 (0.9111) time: 0.1660 data: 0.1024 max mem: 8233 +Train: [20] [2000/6250] eta: 0:11:58 lr: 0.000117 grad: 0.1428 (0.1401) loss: 0.9118 (0.9110) time: 0.1342 data: 0.0646 max mem: 8233 +Train: [20] [2100/6250] eta: 0:11:40 lr: 0.000117 grad: 0.1384 (0.1401) loss: 0.9139 (0.9111) time: 0.1704 data: 0.0915 max mem: 8233 +Train: [20] [2200/6250] eta: 0:11:21 lr: 0.000117 grad: 0.1411 (0.1402) loss: 0.9101 (0.9111) time: 0.1774 data: 0.0942 max mem: 8233 +Train: [20] [2300/6250] eta: 0:11:03 lr: 0.000117 grad: 0.1356 (0.1404) loss: 0.9095 (0.9110) time: 0.1557 data: 0.0623 max mem: 8233 +Train: [20] [2400/6250] eta: 0:10:45 lr: 0.000117 grad: 0.1445 (0.1404) loss: 0.9091 (0.9110) time: 0.1583 data: 0.0798 max mem: 8233 +Train: [20] [2500/6250] eta: 0:10:27 lr: 0.000117 grad: 0.1335 (0.1403) loss: 0.9142 (0.9110) time: 0.1321 data: 0.0364 max mem: 8233 +Train: [20] [2600/6250] eta: 0:10:08 lr: 0.000117 grad: 0.1342 (0.1402) loss: 0.9083 (0.9110) time: 0.1494 data: 0.0626 max mem: 8233 +Train: [20] [2700/6250] eta: 0:09:48 lr: 0.000117 grad: 0.1312 (0.1401) loss: 0.9134 (0.9111) time: 0.1144 data: 0.0153 max mem: 8233 +Train: [20] [2800/6250] eta: 0:09:30 lr: 0.000117 grad: 0.1375 (0.1400) loss: 0.9130 (0.9111) time: 0.1627 data: 0.0796 max mem: 8233 +Train: [20] [2900/6250] eta: 0:09:11 lr: 0.000117 grad: 0.1349 (0.1401) loss: 0.9094 (0.9111) time: 0.1495 data: 0.0668 max mem: 8233 +Train: [20] [3000/6250] eta: 0:08:53 lr: 0.000117 grad: 0.1419 (0.1402) loss: 0.9095 (0.9111) time: 0.1476 data: 0.0618 max mem: 8233 +Train: [20] [3100/6250] eta: 0:08:36 lr: 0.000117 grad: 0.1400 (0.1402) loss: 0.9100 (0.9111) time: 0.1725 data: 0.0872 max mem: 8233 +Train: [20] [3200/6250] eta: 0:08:20 lr: 0.000117 grad: 0.1354 (0.1403) loss: 0.9131 (0.9110) time: 0.1685 data: 0.0844 max mem: 8233 +Train: [20] [3300/6250] eta: 0:08:06 lr: 0.000117 grad: 0.1356 (0.1403) loss: 0.9153 (0.9110) time: 0.2144 data: 0.1166 max mem: 8233 +Train: [20] [3400/6250] eta: 0:07:49 lr: 0.000117 grad: 0.1383 (0.1403) loss: 0.9140 (0.9109) time: 0.1773 data: 0.0964 max mem: 8233 +Train: [20] [3500/6250] eta: 0:07:34 lr: 0.000117 grad: 0.1406 (0.1403) loss: 0.9113 (0.9109) time: 0.1307 data: 0.0395 max mem: 8233 +Train: [20] [3600/6250] eta: 0:07:19 lr: 0.000117 grad: 0.1363 (0.1405) loss: 0.9064 (0.9109) time: 0.1699 data: 0.0777 max mem: 8233 +Train: [20] [3700/6250] eta: 0:07:02 lr: 0.000117 grad: 0.1311 (0.1405) loss: 0.9103 (0.9108) time: 0.1641 data: 0.0813 max mem: 8233 +Train: [20] [3800/6250] eta: 0:06:45 lr: 0.000117 grad: 0.1448 (0.1406) loss: 0.9070 (0.9108) time: 0.1669 data: 0.0956 max mem: 8233 +Train: [20] [3900/6250] eta: 0:06:28 lr: 0.000117 grad: 0.1392 (0.1405) loss: 0.9096 (0.9108) time: 0.1325 data: 0.0470 max mem: 8233 +Train: [20] [4000/6250] eta: 0:06:11 lr: 0.000117 grad: 0.1361 (0.1405) loss: 0.9100 (0.9108) time: 0.1474 data: 0.0747 max mem: 8233 +Train: [20] [4100/6250] eta: 0:05:55 lr: 0.000117 grad: 0.1337 (0.1404) loss: 0.9112 (0.9108) time: 0.2023 data: 0.1383 max mem: 8233 +Train: [20] [4200/6250] eta: 0:05:39 lr: 0.000117 grad: 0.1449 (0.1404) loss: 0.9131 (0.9108) time: 0.1725 data: 0.0942 max mem: 8233 +Train: [20] [4300/6250] eta: 0:05:24 lr: 0.000117 grad: 0.1279 (0.1404) loss: 0.9128 (0.9108) time: 0.1607 data: 0.0579 max mem: 8233 +Train: [20] [4400/6250] eta: 0:05:09 lr: 0.000117 grad: 0.1239 (0.1404) loss: 0.9084 (0.9108) time: 0.2163 data: 0.0850 max mem: 8233 +Train: [20] [4500/6250] eta: 0:04:52 lr: 0.000117 grad: 0.1291 (0.1404) loss: 0.9103 (0.9107) time: 0.1758 data: 0.0942 max mem: 8233 +Train: [20] [4600/6250] eta: 0:04:36 lr: 0.000117 grad: 0.1354 (0.1404) loss: 0.9108 (0.9108) time: 0.2082 data: 0.1248 max mem: 8233 +Train: [20] [4700/6250] eta: 0:04:19 lr: 0.000117 grad: 0.1331 (0.1404) loss: 0.9108 (0.9108) time: 0.1357 data: 0.0535 max mem: 8233 +Train: [20] [4800/6250] eta: 0:04:03 lr: 0.000117 grad: 0.1375 (0.1403) loss: 0.9127 (0.9108) time: 0.2849 data: 0.1443 max mem: 8233 +Train: [20] [4900/6250] eta: 0:03:46 lr: 0.000117 grad: 0.1252 (0.1402) loss: 0.9113 (0.9109) time: 0.1256 data: 0.0381 max mem: 8233 +Train: [20] [5000/6250] eta: 0:03:30 lr: 0.000117 grad: 0.1365 (0.1400) loss: 0.9128 (0.9109) time: 0.1761 data: 0.0913 max mem: 8233 +Train: [20] [5100/6250] eta: 0:03:13 lr: 0.000117 grad: 0.1350 (0.1399) loss: 0.9143 (0.9109) time: 0.1432 data: 0.0595 max mem: 8233 +Train: [20] [5200/6250] eta: 0:02:56 lr: 0.000117 grad: 0.1411 (0.1398) loss: 0.9111 (0.9110) time: 0.1644 data: 0.0765 max mem: 8233 +Train: [20] [5300/6250] eta: 0:02:39 lr: 0.000117 grad: 0.1348 (0.1397) loss: 0.9118 (0.9110) time: 0.1466 data: 0.0661 max mem: 8233 +Train: [20] [5400/6250] eta: 0:02:22 lr: 0.000117 grad: 0.1362 (0.1397) loss: 0.9128 (0.9110) time: 0.2056 data: 0.1254 max mem: 8233 +Train: [20] [5500/6250] eta: 0:02:05 lr: 0.000117 grad: 0.1243 (0.1396) loss: 0.9112 (0.9110) time: 0.1609 data: 0.0789 max mem: 8233 +Train: [20] [5600/6250] eta: 0:01:48 lr: 0.000117 grad: 0.1331 (0.1395) loss: 0.9094 (0.9110) time: 0.1526 data: 0.0713 max mem: 8233 +Train: [20] [5700/6250] eta: 0:01:31 lr: 0.000117 grad: 0.1369 (0.1395) loss: 0.9105 (0.9110) time: 0.1755 data: 0.0934 max mem: 8233 +Train: [20] [5800/6250] eta: 0:01:15 lr: 0.000117 grad: 0.1315 (0.1395) loss: 0.9102 (0.9110) time: 0.2910 data: 0.1975 max mem: 8233 +Train: [20] [5900/6250] eta: 0:00:58 lr: 0.000117 grad: 0.1393 (0.1394) loss: 0.9119 (0.9110) time: 0.1603 data: 0.0829 max mem: 8233 +Train: [20] [6000/6250] eta: 0:00:41 lr: 0.000116 grad: 0.1325 (0.1394) loss: 0.9113 (0.9110) time: 0.1738 data: 0.0952 max mem: 8233 +Train: [20] [6100/6250] eta: 0:00:25 lr: 0.000116 grad: 0.1380 (0.1394) loss: 0.9109 (0.9109) time: 0.1215 data: 0.0003 max mem: 8233 +Train: [20] [6200/6250] eta: 0:00:08 lr: 0.000116 grad: 0.1386 (0.1394) loss: 0.9074 (0.9109) time: 0.1554 data: 0.0587 max mem: 8233 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.1370 (0.1394) loss: 0.9107 (0.9109) time: 0.1506 data: 0.0755 max mem: 8233 +Train: [20] Total time: 0:17:32 (0.1685 s / it) +Averaged stats: lr: 0.000116 grad: 0.1370 (0.1394) loss: 0.9107 (0.9109) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:05:54 loss: 0.9225 (0.9225) time: 5.7145 data: 5.6870 max mem: 8233 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.9153 (0.9142) time: 0.1432 data: 0.1221 max mem: 8233 +Eval (hcp-train-subset): [20] Total time: 0:00:14 (0.2390 s / it) +Averaged stats (hcp-train-subset): loss: 0.9153 (0.9142) +Eval (hcp-val): [20] [ 0/62] eta: 0:03:34 loss: 0.9065 (0.9065) time: 3.4663 data: 3.3897 max mem: 8233 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.9091 (0.9099) time: 0.1333 data: 0.1126 max mem: 8233 +Eval (hcp-val): [20] Total time: 0:00:14 (0.2315 s / it) +Averaged stats (hcp-val): loss: 0.9091 (0.9099) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 9:33:16 lr: 0.000116 grad: 0.1150 (0.1150) loss: 0.9242 (0.9242) time: 5.5035 data: 5.2503 max mem: 8233 +Train: [21] [ 100/6250] eta: 0:22:32 lr: 0.000116 grad: 0.1310 (0.1357) loss: 0.9105 (0.9113) time: 0.1819 data: 0.0859 max mem: 8233 +Train: [21] [ 200/6250] eta: 0:19:44 lr: 0.000116 grad: 0.1231 (0.1351) loss: 0.9140 (0.9110) time: 0.1804 data: 0.0926 max mem: 8233 +Train: [21] [ 300/6250] eta: 0:18:40 lr: 0.000116 grad: 0.1446 (0.1356) loss: 0.9131 (0.9109) time: 0.1646 data: 0.0755 max mem: 8233 +Train: [21] [ 400/6250] eta: 0:17:56 lr: 0.000116 grad: 0.1309 (0.1357) loss: 0.9023 (0.9105) time: 0.1530 data: 0.0525 max mem: 8233 +Train: [21] [ 500/6250] eta: 0:17:16 lr: 0.000116 grad: 0.1443 (0.1363) loss: 0.9091 (0.9096) time: 0.1734 data: 0.0809 max mem: 8233 +Train: [21] [ 600/6250] eta: 0:16:43 lr: 0.000116 grad: 0.1413 (0.1372) loss: 0.9092 (0.9091) time: 0.1580 data: 0.0618 max mem: 8233 +Train: [21] [ 700/6250] eta: 0:16:10 lr: 0.000116 grad: 0.1328 (0.1385) loss: 0.9067 (0.9089) time: 0.1685 data: 0.0773 max mem: 8233 +Train: [21] [ 800/6250] eta: 0:15:47 lr: 0.000116 grad: 0.1341 (0.1384) loss: 0.9039 (0.9087) time: 0.1842 data: 0.1034 max mem: 8233 +Train: [21] [ 900/6250] eta: 0:15:24 lr: 0.000116 grad: 0.1294 (0.1381) loss: 0.9094 (0.9086) time: 0.1400 data: 0.0437 max mem: 8233 +Train: [21] [1000/6250] eta: 0:15:14 lr: 0.000116 grad: 0.1340 (0.1379) loss: 0.9066 (0.9086) time: 0.2498 data: 0.1714 max mem: 8233 +Train: [21] [1100/6250] eta: 0:14:50 lr: 0.000116 grad: 0.1304 (0.1375) loss: 0.9107 (0.9086) time: 0.1608 data: 0.0805 max mem: 8233 +Train: [21] [1200/6250] eta: 0:14:45 lr: 0.000116 grad: 0.1307 (0.1372) loss: 0.9109 (0.9085) time: 0.2175 data: 0.1275 max mem: 8233 +Train: [21] [1300/6250] eta: 0:14:20 lr: 0.000116 grad: 0.1266 (0.1369) loss: 0.9083 (0.9086) time: 0.1719 data: 0.0860 max mem: 8233 +Train: [21] [1400/6250] eta: 0:14:06 lr: 0.000116 grad: 0.1383 (0.1370) loss: 0.9082 (0.9084) time: 0.1779 data: 0.1041 max mem: 8233 +Train: [21] [1500/6250] eta: 0:13:47 lr: 0.000116 grad: 0.1296 (0.1369) loss: 0.9118 (0.9084) time: 0.1858 data: 0.1127 max mem: 8233 +Train: [21] [1600/6250] eta: 0:13:27 lr: 0.000116 grad: 0.1309 (0.1368) loss: 0.9097 (0.9085) time: 0.1776 data: 0.0958 max mem: 8233 +Train: [21] [1700/6250] eta: 0:13:09 lr: 0.000116 grad: 0.1338 (0.1367) loss: 0.9090 (0.9085) time: 0.1482 data: 0.0592 max mem: 8233 +Train: [21] [1800/6250] eta: 0:12:51 lr: 0.000116 grad: 0.1332 (0.1364) loss: 0.9048 (0.9086) time: 0.1609 data: 0.0756 max mem: 8233 +Train: [21] [1900/6250] eta: 0:12:31 lr: 0.000116 grad: 0.1361 (0.1363) loss: 0.9070 (0.9086) time: 0.1646 data: 0.0887 max mem: 8233 +Train: [21] [2000/6250] eta: 0:12:11 lr: 0.000116 grad: 0.1372 (0.1365) loss: 0.9089 (0.9086) time: 0.1532 data: 0.0679 max mem: 8233 +Train: [21] [2100/6250] eta: 0:11:52 lr: 0.000116 grad: 0.1324 (0.1365) loss: 0.9112 (0.9087) time: 0.2091 data: 0.1449 max mem: 8233 +Train: [21] [2200/6250] eta: 0:11:34 lr: 0.000116 grad: 0.1268 (0.1365) loss: 0.9117 (0.9086) time: 0.1744 data: 0.1030 max mem: 8233 +Train: [21] [2300/6250] eta: 0:11:15 lr: 0.000116 grad: 0.1364 (0.1365) loss: 0.9081 (0.9086) time: 0.1560 data: 0.0807 max mem: 8233 +Train: [21] [2400/6250] eta: 0:10:56 lr: 0.000116 grad: 0.1285 (0.1363) loss: 0.9108 (0.9086) time: 0.1690 data: 0.0876 max mem: 8233 +Train: [21] [2500/6250] eta: 0:10:39 lr: 0.000116 grad: 0.1362 (0.1365) loss: 0.9092 (0.9086) time: 0.1631 data: 0.0760 max mem: 8233 +Train: [21] [2600/6250] eta: 0:10:19 lr: 0.000116 grad: 0.1264 (0.1364) loss: 0.9122 (0.9086) time: 0.1317 data: 0.0428 max mem: 8233 +Train: [21] [2700/6250] eta: 0:10:02 lr: 0.000116 grad: 0.1292 (0.1362) loss: 0.9075 (0.9087) time: 0.1723 data: 0.0951 max mem: 8233 +Train: [21] [2800/6250] eta: 0:09:45 lr: 0.000116 grad: 0.1320 (0.1361) loss: 0.9073 (0.9087) time: 0.2016 data: 0.1396 max mem: 8233 +Train: [21] [2900/6250] eta: 0:09:30 lr: 0.000116 grad: 0.1270 (0.1360) loss: 0.9101 (0.9087) time: 0.1796 data: 0.1012 max mem: 8233 +Train: [21] [3000/6250] eta: 0:09:14 lr: 0.000116 grad: 0.1310 (0.1360) loss: 0.9082 (0.9087) time: 0.1948 data: 0.1142 max mem: 8233 +Train: [21] [3100/6250] eta: 0:08:59 lr: 0.000116 grad: 0.1342 (0.1359) loss: 0.9088 (0.9087) time: 0.1980 data: 0.1306 max mem: 8233 +Train: [21] [3200/6250] eta: 0:08:47 lr: 0.000116 grad: 0.1336 (0.1359) loss: 0.9087 (0.9087) time: 0.1884 data: 0.1161 max mem: 8233 +Train: [21] [3300/6250] eta: 0:08:32 lr: 0.000116 grad: 0.1290 (0.1358) loss: 0.9102 (0.9087) time: 0.1841 data: 0.1117 max mem: 8233 +Train: [21] [3400/6250] eta: 0:08:17 lr: 0.000116 grad: 0.1313 (0.1359) loss: 0.9054 (0.9087) time: 0.1784 data: 0.1073 max mem: 8233 +Train: [21] [3500/6250] eta: 0:08:00 lr: 0.000116 grad: 0.1334 (0.1359) loss: 0.9111 (0.9086) time: 0.1899 data: 0.1186 max mem: 8233 +Train: [21] [3600/6250] eta: 0:07:44 lr: 0.000116 grad: 0.1346 (0.1359) loss: 0.9107 (0.9086) time: 0.1171 data: 0.0003 max mem: 8233 +Train: [21] [3700/6250] eta: 0:07:26 lr: 0.000116 grad: 0.1288 (0.1360) loss: 0.9051 (0.9086) time: 0.1246 data: 0.0396 max mem: 8233 +Train: [21] [3800/6250] eta: 0:07:10 lr: 0.000116 grad: 0.1393 (0.1360) loss: 0.9086 (0.9085) time: 0.1164 data: 0.0003 max mem: 8233 +Train: [21] [3900/6250] eta: 0:06:52 lr: 0.000116 grad: 0.1388 (0.1359) loss: 0.9039 (0.9085) time: 0.1625 data: 0.0814 max mem: 8233 +Train: [21] [4000/6250] eta: 0:06:34 lr: 0.000116 grad: 0.1330 (0.1360) loss: 0.9044 (0.9084) time: 0.1644 data: 0.0844 max mem: 8233 +Train: [21] [4100/6250] eta: 0:06:16 lr: 0.000116 grad: 0.1239 (0.1360) loss: 0.9041 (0.9083) time: 0.1097 data: 0.0196 max mem: 8233 +Train: [21] [4200/6250] eta: 0:05:58 lr: 0.000116 grad: 0.1345 (0.1360) loss: 0.9067 (0.9083) time: 0.1860 data: 0.0984 max mem: 8233 +Train: [21] [4300/6250] eta: 0:05:42 lr: 0.000116 grad: 0.1375 (0.1361) loss: 0.9042 (0.9083) time: 0.1581 data: 0.0881 max mem: 8233 +Train: [21] [4400/6250] eta: 0:05:24 lr: 0.000116 grad: 0.1372 (0.1361) loss: 0.9034 (0.9082) time: 0.1871 data: 0.0920 max mem: 8233 +Train: [21] [4500/6250] eta: 0:05:06 lr: 0.000116 grad: 0.1318 (0.1362) loss: 0.9086 (0.9081) time: 0.1618 data: 0.0825 max mem: 8233 +Train: [21] [4600/6250] eta: 0:04:49 lr: 0.000116 grad: 0.1418 (0.1365) loss: 0.9091 (0.9081) time: 0.1075 data: 0.0003 max mem: 8233 +Train: [21] [4700/6250] eta: 0:04:31 lr: 0.000116 grad: 0.1434 (0.1366) loss: 0.9086 (0.9081) time: 0.1740 data: 0.0995 max mem: 8233 +Train: [21] [4800/6250] eta: 0:04:13 lr: 0.000116 grad: 0.1356 (0.1367) loss: 0.9084 (0.9080) time: 0.1123 data: 0.0003 max mem: 8233 +Train: [21] [4900/6250] eta: 0:03:55 lr: 0.000116 grad: 0.1295 (0.1367) loss: 0.9081 (0.9080) time: 0.1320 data: 0.0354 max mem: 8233 +Train: [21] [5000/6250] eta: 0:03:38 lr: 0.000116 grad: 0.1286 (0.1367) loss: 0.9070 (0.9080) time: 0.1033 data: 0.0003 max mem: 8233 +Train: [21] [5100/6250] eta: 0:03:20 lr: 0.000116 grad: 0.1325 (0.1367) loss: 0.9066 (0.9080) time: 0.1673 data: 0.0679 max mem: 8233 +Train: [21] [5200/6250] eta: 0:03:03 lr: 0.000116 grad: 0.1306 (0.1366) loss: 0.9071 (0.9080) time: 0.1808 data: 0.1044 max mem: 8233 +Train: [21] [5300/6250] eta: 0:02:45 lr: 0.000116 grad: 0.1321 (0.1365) loss: 0.9126 (0.9080) time: 0.1714 data: 0.0957 max mem: 8233 +Train: [21] [5400/6250] eta: 0:02:27 lr: 0.000116 grad: 0.1304 (0.1365) loss: 0.9110 (0.9081) time: 0.1793 data: 0.1116 max mem: 8233 +Train: [21] [5500/6250] eta: 0:02:10 lr: 0.000116 grad: 0.1284 (0.1364) loss: 0.9108 (0.9081) time: 0.1929 data: 0.1186 max mem: 8233 +Train: [21] [5600/6250] eta: 0:01:52 lr: 0.000115 grad: 0.1405 (0.1365) loss: 0.9044 (0.9081) time: 0.1787 data: 0.1102 max mem: 8233 +Train: [21] [5700/6250] eta: 0:01:35 lr: 0.000115 grad: 0.1342 (0.1364) loss: 0.9076 (0.9081) time: 0.1770 data: 0.1015 max mem: 8233 +Train: [21] [5800/6250] eta: 0:01:18 lr: 0.000115 grad: 0.1349 (0.1364) loss: 0.9069 (0.9082) time: 0.1949 data: 0.1131 max mem: 8233 +Train: [21] [5900/6250] eta: 0:01:00 lr: 0.000115 grad: 0.1418 (0.1365) loss: 0.9105 (0.9082) time: 0.1679 data: 0.0978 max mem: 8233 +Train: [21] [6000/6250] eta: 0:00:43 lr: 0.000115 grad: 0.1217 (0.1364) loss: 0.9126 (0.9082) time: 0.2020 data: 0.1241 max mem: 8233 +Train: [21] [6100/6250] eta: 0:00:26 lr: 0.000115 grad: 0.1248 (0.1363) loss: 0.9119 (0.9083) time: 0.1542 data: 0.0743 max mem: 8233 +Train: [21] [6200/6250] eta: 0:00:08 lr: 0.000115 grad: 0.1307 (0.1362) loss: 0.9093 (0.9083) time: 0.1703 data: 0.0890 max mem: 8233 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.1277 (0.1362) loss: 0.9115 (0.9083) time: 0.1830 data: 0.1048 max mem: 8233 +Train: [21] Total time: 0:18:13 (0.1750 s / it) +Averaged stats: lr: 0.000115 grad: 0.1277 (0.1362) loss: 0.9115 (0.9083) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:04:56 loss: 0.9204 (0.9204) time: 4.7753 data: 4.7087 max mem: 8233 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.9141 (0.9125) time: 0.1385 data: 0.1176 max mem: 8233 +Eval (hcp-train-subset): [21] Total time: 0:00:15 (0.2435 s / it) +Averaged stats (hcp-train-subset): loss: 0.9141 (0.9125) +Eval (hcp-val): [21] [ 0/62] eta: 0:06:04 loss: 0.9019 (0.9019) time: 5.8726 data: 5.8447 max mem: 8233 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.9089 (0.9080) time: 0.1072 data: 0.0863 max mem: 8233 +Eval (hcp-val): [21] Total time: 0:00:14 (0.2386 s / it) +Averaged stats (hcp-val): loss: 0.9089 (0.9080) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 10:54:30 lr: 0.000115 grad: 0.1097 (0.1097) loss: 0.9473 (0.9473) time: 6.2833 data: 6.1394 max mem: 8233 +Train: [22] [ 100/6250] eta: 0:23:24 lr: 0.000115 grad: 0.1349 (0.1464) loss: 0.9092 (0.9116) time: 0.1591 data: 0.0656 max mem: 8233 +Train: [22] [ 200/6250] eta: 0:20:00 lr: 0.000115 grad: 0.1304 (0.1395) loss: 0.9090 (0.9107) time: 0.1641 data: 0.0725 max mem: 8233 +Train: [22] [ 300/6250] eta: 0:18:28 lr: 0.000115 grad: 0.1307 (0.1373) loss: 0.9040 (0.9101) time: 0.1879 data: 0.0985 max mem: 8233 +Train: [22] [ 400/6250] eta: 0:17:43 lr: 0.000115 grad: 0.1331 (0.1376) loss: 0.9077 (0.9094) time: 0.1477 data: 0.0534 max mem: 8233 +Train: [22] [ 500/6250] eta: 0:17:00 lr: 0.000115 grad: 0.1288 (0.1366) loss: 0.9065 (0.9085) time: 0.1660 data: 0.0729 max mem: 8233 +Train: [22] [ 600/6250] eta: 0:16:28 lr: 0.000115 grad: 0.1263 (0.1361) loss: 0.9078 (0.9083) time: 0.1456 data: 0.0562 max mem: 8233 +Train: [22] [ 700/6250] eta: 0:15:52 lr: 0.000115 grad: 0.1265 (0.1354) loss: 0.9075 (0.9082) time: 0.1321 data: 0.0427 max mem: 8233 +Train: [22] [ 800/6250] eta: 0:15:29 lr: 0.000115 grad: 0.1338 (0.1351) loss: 0.9065 (0.9080) time: 0.1482 data: 0.0585 max mem: 8233 +Train: [22] [ 900/6250] eta: 0:15:17 lr: 0.000115 grad: 0.1276 (0.1347) loss: 0.9041 (0.9078) time: 0.2150 data: 0.1389 max mem: 8233 +Train: [22] [1000/6250] eta: 0:15:08 lr: 0.000115 grad: 0.1224 (0.1344) loss: 0.9076 (0.9079) time: 0.1294 data: 0.0345 max mem: 8233 +Train: [22] [1100/6250] eta: 0:14:53 lr: 0.000115 grad: 0.1274 (0.1341) loss: 0.9074 (0.9079) time: 0.1719 data: 0.0876 max mem: 8233 +Train: [22] [1200/6250] eta: 0:14:49 lr: 0.000115 grad: 0.1224 (0.1338) loss: 0.9123 (0.9079) time: 0.2880 data: 0.2063 max mem: 8233 +Train: [22] [1300/6250] eta: 0:14:24 lr: 0.000115 grad: 0.1233 (0.1336) loss: 0.9051 (0.9077) time: 0.1736 data: 0.1022 max mem: 8233 +Train: [22] [1400/6250] eta: 0:14:17 lr: 0.000115 grad: 0.1323 (0.1337) loss: 0.9045 (0.9076) time: 0.3230 data: 0.2473 max mem: 8233 +Train: [22] [1500/6250] eta: 0:13:59 lr: 0.000115 grad: 0.1356 (0.1337) loss: 0.9046 (0.9075) time: 0.2080 data: 0.1392 max mem: 8233 +Train: [22] [1600/6250] eta: 0:13:43 lr: 0.000115 grad: 0.1359 (0.1336) loss: 0.9054 (0.9073) time: 0.1667 data: 0.0907 max mem: 8233 +Train: [22] [1700/6250] eta: 0:13:27 lr: 0.000115 grad: 0.1330 (0.1338) loss: 0.9019 (0.9071) time: 0.1730 data: 0.0894 max mem: 8233 +Train: [22] [1800/6250] eta: 0:13:10 lr: 0.000115 grad: 0.1320 (0.1338) loss: 0.9035 (0.9070) time: 0.1596 data: 0.0777 max mem: 8233 +Train: [22] [1900/6250] eta: 0:12:52 lr: 0.000115 grad: 0.1255 (0.1339) loss: 0.9057 (0.9068) time: 0.1639 data: 0.0799 max mem: 8233 +Train: [22] [2000/6250] eta: 0:12:33 lr: 0.000115 grad: 0.1256 (0.1338) loss: 0.9078 (0.9068) time: 0.1757 data: 0.0886 max mem: 8233 +Train: [22] [2100/6250] eta: 0:12:14 lr: 0.000115 grad: 0.1275 (0.1336) loss: 0.9098 (0.9068) time: 0.1684 data: 0.0891 max mem: 8233 +Train: [22] [2200/6250] eta: 0:11:55 lr: 0.000115 grad: 0.1426 (0.1337) loss: 0.9084 (0.9069) time: 0.1347 data: 0.0479 max mem: 8233 +Train: [22] [2300/6250] eta: 0:11:39 lr: 0.000115 grad: 0.1325 (0.1337) loss: 0.9088 (0.9068) time: 0.1774 data: 0.1003 max mem: 8233 +Train: [22] [2400/6250] eta: 0:11:20 lr: 0.000115 grad: 0.1321 (0.1337) loss: 0.9075 (0.9068) time: 0.1784 data: 0.1002 max mem: 8233 +Train: [22] [2500/6250] eta: 0:11:00 lr: 0.000115 grad: 0.1342 (0.1337) loss: 0.9089 (0.9068) time: 0.1595 data: 0.0724 max mem: 8233 +Train: [22] [2600/6250] eta: 0:10:42 lr: 0.000115 grad: 0.1287 (0.1337) loss: 0.9071 (0.9068) time: 0.1766 data: 0.0963 max mem: 8233 +Train: [22] [2700/6250] eta: 0:10:23 lr: 0.000115 grad: 0.1326 (0.1336) loss: 0.9044 (0.9068) time: 0.1715 data: 0.0868 max mem: 8233 +Train: [22] [2800/6250] eta: 0:10:03 lr: 0.000115 grad: 0.1178 (0.1335) loss: 0.9096 (0.9068) time: 0.1745 data: 0.0897 max mem: 8233 +Train: [22] [2900/6250] eta: 0:09:43 lr: 0.000115 grad: 0.1303 (0.1334) loss: 0.9114 (0.9068) time: 0.1877 data: 0.1095 max mem: 8233 +Train: [22] [3000/6250] eta: 0:09:24 lr: 0.000115 grad: 0.1317 (0.1335) loss: 0.9085 (0.9068) time: 0.1658 data: 0.0874 max mem: 8233 +Train: [22] [3100/6250] eta: 0:09:11 lr: 0.000115 grad: 0.1312 (0.1335) loss: 0.9105 (0.9068) time: 0.3383 data: 0.2466 max mem: 8233 +Train: [22] [3200/6250] eta: 0:08:51 lr: 0.000115 grad: 0.1335 (0.1336) loss: 0.9058 (0.9068) time: 0.1491 data: 0.0614 max mem: 8233 +Train: [22] [3300/6250] eta: 0:08:33 lr: 0.000115 grad: 0.1329 (0.1336) loss: 0.9007 (0.9068) time: 0.1750 data: 0.0905 max mem: 8233 +Train: [22] [3400/6250] eta: 0:08:15 lr: 0.000115 grad: 0.1264 (0.1335) loss: 0.9069 (0.9068) time: 0.1530 data: 0.0743 max mem: 8233 +Train: [22] [3500/6250] eta: 0:07:58 lr: 0.000115 grad: 0.1308 (0.1335) loss: 0.9043 (0.9068) time: 0.1554 data: 0.0873 max mem: 8233 +Train: [22] [3600/6250] eta: 0:07:40 lr: 0.000115 grad: 0.1275 (0.1335) loss: 0.9107 (0.9068) time: 0.1975 data: 0.1252 max mem: 8233 +Train: [22] [3700/6250] eta: 0:07:24 lr: 0.000115 grad: 0.1282 (0.1335) loss: 0.9097 (0.9067) time: 0.1946 data: 0.1345 max mem: 8233 +Train: [22] [3800/6250] eta: 0:07:10 lr: 0.000115 grad: 0.1319 (0.1335) loss: 0.9097 (0.9067) time: 0.3284 data: 0.2662 max mem: 8233 +Train: [22] [3900/6250] eta: 0:06:51 lr: 0.000115 grad: 0.1331 (0.1336) loss: 0.9067 (0.9067) time: 0.1712 data: 0.0732 max mem: 8233 +Train: [22] [4000/6250] eta: 0:06:36 lr: 0.000115 grad: 0.1380 (0.1336) loss: 0.9069 (0.9067) time: 0.3469 data: 0.2570 max mem: 8233 +Train: [22] [4100/6250] eta: 0:06:18 lr: 0.000115 grad: 0.1335 (0.1336) loss: 0.9055 (0.9067) time: 0.1890 data: 0.1154 max mem: 8233 +Train: [22] [4200/6250] eta: 0:05:59 lr: 0.000115 grad: 0.1282 (0.1337) loss: 0.9068 (0.9067) time: 0.1881 data: 0.1037 max mem: 8233 +Train: [22] [4300/6250] eta: 0:05:42 lr: 0.000115 grad: 0.1381 (0.1337) loss: 0.9018 (0.9067) time: 0.1220 data: 0.0005 max mem: 8233 +Train: [22] [4400/6250] eta: 0:05:24 lr: 0.000115 grad: 0.1343 (0.1338) loss: 0.9031 (0.9066) time: 0.1638 data: 0.0798 max mem: 8233 +Train: [22] [4500/6250] eta: 0:05:07 lr: 0.000115 grad: 0.1312 (0.1337) loss: 0.9088 (0.9066) time: 0.0952 data: 0.0002 max mem: 8233 +Train: [22] [4600/6250] eta: 0:04:49 lr: 0.000115 grad: 0.1280 (0.1337) loss: 0.9048 (0.9066) time: 0.1449 data: 0.0530 max mem: 8233 +Train: [22] [4700/6250] eta: 0:04:33 lr: 0.000115 grad: 0.1369 (0.1338) loss: 0.9059 (0.9066) time: 0.2457 data: 0.1652 max mem: 8233 +Train: [22] [4800/6250] eta: 0:04:15 lr: 0.000115 grad: 0.1273 (0.1338) loss: 0.9049 (0.9066) time: 0.1383 data: 0.0281 max mem: 8233 +Train: [22] [4900/6250] eta: 0:03:57 lr: 0.000114 grad: 0.1305 (0.1338) loss: 0.9070 (0.9066) time: 0.1878 data: 0.1080 max mem: 8233 +Train: [22] [5000/6250] eta: 0:03:39 lr: 0.000114 grad: 0.1274 (0.1338) loss: 0.9044 (0.9065) time: 0.1614 data: 0.0817 max mem: 8233 +Train: [22] [5100/6250] eta: 0:03:21 lr: 0.000114 grad: 0.1331 (0.1338) loss: 0.9020 (0.9065) time: 0.1536 data: 0.0679 max mem: 8233 +Train: [22] [5200/6250] eta: 0:03:03 lr: 0.000114 grad: 0.1336 (0.1339) loss: 0.9008 (0.9065) time: 0.1751 data: 0.1047 max mem: 8233 +Train: [22] [5300/6250] eta: 0:02:45 lr: 0.000114 grad: 0.1330 (0.1339) loss: 0.9004 (0.9064) time: 0.1490 data: 0.0754 max mem: 8233 +Train: [22] [5400/6250] eta: 0:02:28 lr: 0.000114 grad: 0.1327 (0.1340) loss: 0.9013 (0.9063) time: 0.1880 data: 0.1078 max mem: 8233 +Train: [22] [5500/6250] eta: 0:02:11 lr: 0.000114 grad: 0.1328 (0.1341) loss: 0.9036 (0.9063) time: 0.1974 data: 0.1093 max mem: 8233 +Train: [22] [5600/6250] eta: 0:01:53 lr: 0.000114 grad: 0.1373 (0.1342) loss: 0.9006 (0.9062) time: 0.1527 data: 0.0760 max mem: 8233 +Train: [22] [5700/6250] eta: 0:01:36 lr: 0.000114 grad: 0.1312 (0.1343) loss: 0.9026 (0.9061) time: 0.1910 data: 0.0648 max mem: 8233 +Train: [22] [5800/6250] eta: 0:01:18 lr: 0.000114 grad: 0.1331 (0.1343) loss: 0.9058 (0.9060) time: 0.1811 data: 0.0818 max mem: 8233 +Train: [22] [5900/6250] eta: 0:01:01 lr: 0.000114 grad: 0.1333 (0.1344) loss: 0.9053 (0.9060) time: 0.1678 data: 0.0938 max mem: 8233 +Train: [22] [6000/6250] eta: 0:00:43 lr: 0.000114 grad: 0.1345 (0.1344) loss: 0.9032 (0.9060) time: 0.1665 data: 0.0330 max mem: 8233 +Train: [22] [6100/6250] eta: 0:00:26 lr: 0.000114 grad: 0.1323 (0.1345) loss: 0.9049 (0.9059) time: 0.1391 data: 0.0506 max mem: 8233 +Train: [22] [6200/6250] eta: 0:00:08 lr: 0.000114 grad: 0.1305 (0.1346) loss: 0.9081 (0.9059) time: 0.1833 data: 0.0991 max mem: 8233 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.1361 (0.1346) loss: 0.9003 (0.9058) time: 0.1978 data: 0.0757 max mem: 8233 +Train: [22] Total time: 0:18:21 (0.1762 s / it) +Averaged stats: lr: 0.000114 grad: 0.1361 (0.1346) loss: 0.9003 (0.9058) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:04:37 loss: 0.9203 (0.9203) time: 4.4694 data: 4.3916 max mem: 8233 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.9131 (0.9117) time: 0.1398 data: 0.1191 max mem: 8233 +Eval (hcp-train-subset): [22] Total time: 0:00:14 (0.2388 s / it) +Averaged stats (hcp-train-subset): loss: 0.9131 (0.9117) +Eval (hcp-val): [22] [ 0/62] eta: 0:04:50 loss: 0.9023 (0.9023) time: 4.6849 data: 4.6192 max mem: 8233 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.9068 (0.9072) time: 0.1434 data: 0.1231 max mem: 8233 +Eval (hcp-val): [22] Total time: 0:00:14 (0.2392 s / it) +Averaged stats (hcp-val): loss: 0.9068 (0.9072) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 12:39:07 lr: 0.000114 grad: 0.1196 (0.1196) loss: 0.9070 (0.9070) time: 7.2876 data: 7.1885 max mem: 8233 +Train: [23] [ 100/6250] eta: 0:24:17 lr: 0.000114 grad: 0.1260 (0.1353) loss: 0.9064 (0.9053) time: 0.1918 data: 0.0874 max mem: 8233 +Train: [23] [ 200/6250] eta: 0:20:56 lr: 0.000114 grad: 0.1368 (0.1338) loss: 0.9036 (0.9049) time: 0.1725 data: 0.0750 max mem: 8233 +Train: [23] [ 300/6250] eta: 0:19:16 lr: 0.000114 grad: 0.1286 (0.1325) loss: 0.9126 (0.9048) time: 0.1250 data: 0.0327 max mem: 8233 +Train: [23] [ 400/6250] eta: 0:18:17 lr: 0.000114 grad: 0.1244 (0.1322) loss: 0.9025 (0.9048) time: 0.1568 data: 0.0568 max mem: 8233 +Train: [23] [ 500/6250] eta: 0:17:37 lr: 0.000114 grad: 0.1346 (0.1317) loss: 0.9058 (0.9051) time: 0.1696 data: 0.0709 max mem: 8233 +Train: [23] [ 600/6250] eta: 0:17:00 lr: 0.000114 grad: 0.1308 (0.1319) loss: 0.9045 (0.9050) time: 0.1468 data: 0.0538 max mem: 8233 +Train: [23] [ 700/6250] eta: 0:16:32 lr: 0.000114 grad: 0.1260 (0.1315) loss: 0.9072 (0.9050) time: 0.1664 data: 0.0783 max mem: 8233 +Train: [23] [ 800/6250] eta: 0:16:00 lr: 0.000114 grad: 0.1236 (0.1309) loss: 0.9083 (0.9051) time: 0.1444 data: 0.0604 max mem: 8233 +Train: [23] [ 900/6250] eta: 0:15:38 lr: 0.000114 grad: 0.1149 (0.1303) loss: 0.9053 (0.9052) time: 0.2028 data: 0.1310 max mem: 8233 +Train: [23] [1000/6250] eta: 0:15:25 lr: 0.000114 grad: 0.1263 (0.1297) loss: 0.9064 (0.9054) time: 0.2196 data: 0.1452 max mem: 8233 +Train: [23] [1100/6250] eta: 0:15:13 lr: 0.000114 grad: 0.1185 (0.1297) loss: 0.9091 (0.9056) time: 0.1523 data: 0.0786 max mem: 8233 +Train: [23] [1200/6250] eta: 0:15:03 lr: 0.000114 grad: 0.1221 (0.1293) loss: 0.9077 (0.9057) time: 0.1234 data: 0.0211 max mem: 8233 +Train: [23] [1300/6250] eta: 0:14:38 lr: 0.000114 grad: 0.1186 (0.1292) loss: 0.9102 (0.9059) time: 0.1741 data: 0.1055 max mem: 8233 +Train: [23] [1400/6250] eta: 0:14:16 lr: 0.000114 grad: 0.1210 (0.1289) loss: 0.9072 (0.9059) time: 0.1687 data: 0.0963 max mem: 8233 +Train: [23] [1500/6250] eta: 0:14:03 lr: 0.000114 grad: 0.1228 (0.1289) loss: 0.9061 (0.9061) time: 0.1975 data: 0.1220 max mem: 8233 +Train: [23] [1600/6250] eta: 0:13:53 lr: 0.000114 grad: 0.1299 (0.1290) loss: 0.9040 (0.9060) time: 0.2078 data: 0.1239 max mem: 8233 +Train: [23] [1700/6250] eta: 0:13:34 lr: 0.000114 grad: 0.1211 (0.1289) loss: 0.9099 (0.9061) time: 0.1828 data: 0.1011 max mem: 8233 +Train: [23] [1800/6250] eta: 0:13:21 lr: 0.000114 grad: 0.1227 (0.1289) loss: 0.9048 (0.9061) time: 0.1846 data: 0.1044 max mem: 8233 +Train: [23] [1900/6250] eta: 0:13:06 lr: 0.000114 grad: 0.1239 (0.1288) loss: 0.9075 (0.9061) time: 0.1641 data: 0.0797 max mem: 8233 +Train: [23] [2000/6250] eta: 0:12:46 lr: 0.000114 grad: 0.1223 (0.1289) loss: 0.9034 (0.9061) time: 0.1654 data: 0.0759 max mem: 8233 +Train: [23] [2100/6250] eta: 0:12:25 lr: 0.000114 grad: 0.1231 (0.1287) loss: 0.9064 (0.9062) time: 0.1609 data: 0.0695 max mem: 8233 +Train: [23] [2200/6250] eta: 0:12:06 lr: 0.000114 grad: 0.1287 (0.1287) loss: 0.9034 (0.9062) time: 0.1952 data: 0.1161 max mem: 8233 +Train: [23] [2300/6250] eta: 0:11:49 lr: 0.000114 grad: 0.1311 (0.1287) loss: 0.9079 (0.9062) time: 0.1692 data: 0.0911 max mem: 8233 +Train: [23] [2400/6250] eta: 0:11:33 lr: 0.000114 grad: 0.1245 (0.1287) loss: 0.9074 (0.9062) time: 0.1546 data: 0.0589 max mem: 8233 +Train: [23] [2500/6250] eta: 0:11:13 lr: 0.000114 grad: 0.1247 (0.1285) loss: 0.9065 (0.9062) time: 0.1269 data: 0.0548 max mem: 8233 +Train: [23] [2600/6250] eta: 0:10:54 lr: 0.000114 grad: 0.1199 (0.1286) loss: 0.9083 (0.9063) time: 0.1653 data: 0.0910 max mem: 8233 +Train: [23] [2700/6250] eta: 0:10:34 lr: 0.000114 grad: 0.1218 (0.1284) loss: 0.9044 (0.9063) time: 0.1763 data: 0.0912 max mem: 8233 +Train: [23] [2800/6250] eta: 0:10:15 lr: 0.000114 grad: 0.1225 (0.1284) loss: 0.9137 (0.9063) time: 0.1792 data: 0.0901 max mem: 8233 +Train: [23] [2900/6250] eta: 0:09:55 lr: 0.000114 grad: 0.1206 (0.1283) loss: 0.9079 (0.9064) time: 0.1737 data: 0.0821 max mem: 8233 +Train: [23] [3000/6250] eta: 0:09:36 lr: 0.000114 grad: 0.1226 (0.1283) loss: 0.9077 (0.9064) time: 0.1858 data: 0.1003 max mem: 8233 +Train: [23] [3100/6250] eta: 0:09:17 lr: 0.000114 grad: 0.1203 (0.1283) loss: 0.9101 (0.9065) time: 0.1561 data: 0.0557 max mem: 8233 +Train: [23] [3200/6250] eta: 0:08:58 lr: 0.000114 grad: 0.1298 (0.1282) loss: 0.9088 (0.9065) time: 0.1525 data: 0.0850 max mem: 8233 +Train: [23] [3300/6250] eta: 0:08:40 lr: 0.000114 grad: 0.1231 (0.1281) loss: 0.9071 (0.9066) time: 0.1975 data: 0.1110 max mem: 8233 +Train: [23] [3400/6250] eta: 0:08:24 lr: 0.000114 grad: 0.1289 (0.1281) loss: 0.9102 (0.9065) time: 0.2260 data: 0.1368 max mem: 8233 +Train: [23] [3500/6250] eta: 0:08:06 lr: 0.000114 grad: 0.1264 (0.1281) loss: 0.9051 (0.9066) time: 0.1399 data: 0.0408 max mem: 8233 +Train: [23] [3600/6250] eta: 0:07:49 lr: 0.000114 grad: 0.1219 (0.1282) loss: 0.9097 (0.9065) time: 0.2724 data: 0.1684 max mem: 8233 +Train: [23] [3700/6250] eta: 0:07:29 lr: 0.000114 grad: 0.1220 (0.1282) loss: 0.9053 (0.9065) time: 0.1488 data: 0.0742 max mem: 8233 +Train: [23] [3800/6250] eta: 0:07:11 lr: 0.000114 grad: 0.1381 (0.1284) loss: 0.9022 (0.9065) time: 0.1295 data: 0.0322 max mem: 8233 +Train: [23] [3900/6250] eta: 0:06:53 lr: 0.000114 grad: 0.1275 (0.1285) loss: 0.9028 (0.9064) time: 0.1460 data: 0.0576 max mem: 8233 +Train: [23] [4000/6250] eta: 0:06:36 lr: 0.000113 grad: 0.1301 (0.1286) loss: 0.9073 (0.9064) time: 0.1579 data: 0.0791 max mem: 8233 +Train: [23] [4100/6250] eta: 0:06:17 lr: 0.000113 grad: 0.1303 (0.1288) loss: 0.9038 (0.9064) time: 0.1519 data: 0.0681 max mem: 8233 +Train: [23] [4200/6250] eta: 0:05:59 lr: 0.000113 grad: 0.1228 (0.1288) loss: 0.9051 (0.9063) time: 0.1863 data: 0.1070 max mem: 8233 +Train: [23] [4300/6250] eta: 0:05:41 lr: 0.000113 grad: 0.1277 (0.1289) loss: 0.9035 (0.9063) time: 0.1816 data: 0.1114 max mem: 8233 +Train: [23] [4400/6250] eta: 0:05:23 lr: 0.000113 grad: 0.1283 (0.1290) loss: 0.9066 (0.9063) time: 0.1508 data: 0.0641 max mem: 8233 +Train: [23] [4500/6250] eta: 0:05:06 lr: 0.000113 grad: 0.1215 (0.1290) loss: 0.9046 (0.9062) time: 0.2032 data: 0.1303 max mem: 8233 +Train: [23] [4600/6250] eta: 0:04:48 lr: 0.000113 grad: 0.1285 (0.1290) loss: 0.9056 (0.9062) time: 0.1817 data: 0.1058 max mem: 8233 +Train: [23] [4700/6250] eta: 0:04:30 lr: 0.000113 grad: 0.1227 (0.1291) loss: 0.9063 (0.9062) time: 0.1453 data: 0.0482 max mem: 8233 +Train: [23] [4800/6250] eta: 0:04:13 lr: 0.000113 grad: 0.1331 (0.1292) loss: 0.9056 (0.9061) time: 0.1700 data: 0.0908 max mem: 8233 +Train: [23] [4900/6250] eta: 0:03:55 lr: 0.000113 grad: 0.1421 (0.1293) loss: 0.9017 (0.9061) time: 0.1958 data: 0.1114 max mem: 8233 +Train: [23] [5000/6250] eta: 0:03:38 lr: 0.000113 grad: 0.1206 (0.1293) loss: 0.9049 (0.9061) time: 0.1409 data: 0.0525 max mem: 8233 +Train: [23] [5100/6250] eta: 0:03:20 lr: 0.000113 grad: 0.1267 (0.1293) loss: 0.9088 (0.9061) time: 0.1526 data: 0.0676 max mem: 8233 +Train: [23] [5200/6250] eta: 0:03:03 lr: 0.000113 grad: 0.1318 (0.1293) loss: 0.9044 (0.9060) time: 0.1847 data: 0.1090 max mem: 8233 +Train: [23] [5300/6250] eta: 0:02:45 lr: 0.000113 grad: 0.1284 (0.1294) loss: 0.9042 (0.9060) time: 0.1268 data: 0.0387 max mem: 8233 +Train: [23] [5400/6250] eta: 0:02:28 lr: 0.000113 grad: 0.1274 (0.1295) loss: 0.9061 (0.9060) time: 0.2406 data: 0.1625 max mem: 8233 +Train: [23] [5500/6250] eta: 0:02:10 lr: 0.000113 grad: 0.1254 (0.1295) loss: 0.9058 (0.9059) time: 0.2523 data: 0.1525 max mem: 8233 +Train: [23] [5600/6250] eta: 0:01:53 lr: 0.000113 grad: 0.1171 (0.1295) loss: 0.9035 (0.9059) time: 0.1547 data: 0.0644 max mem: 8233 +Train: [23] [5700/6250] eta: 0:01:36 lr: 0.000113 grad: 0.1200 (0.1295) loss: 0.9029 (0.9058) time: 0.0936 data: 0.0002 max mem: 8233 +Train: [23] [5800/6250] eta: 0:01:18 lr: 0.000113 grad: 0.1257 (0.1296) loss: 0.9075 (0.9058) time: 0.0984 data: 0.0002 max mem: 8233 +Train: [23] [5900/6250] eta: 0:01:01 lr: 0.000113 grad: 0.1275 (0.1297) loss: 0.9059 (0.9058) time: 0.1380 data: 0.0201 max mem: 8233 +Train: [23] [6000/6250] eta: 0:00:43 lr: 0.000113 grad: 0.1254 (0.1297) loss: 0.9084 (0.9058) time: 0.1610 data: 0.0776 max mem: 8233 +Train: [23] [6100/6250] eta: 0:00:26 lr: 0.000113 grad: 0.1131 (0.1297) loss: 0.9107 (0.9058) time: 0.1415 data: 0.0615 max mem: 8233 +Train: [23] [6200/6250] eta: 0:00:08 lr: 0.000113 grad: 0.1191 (0.1297) loss: 0.9102 (0.9058) time: 0.1297 data: 0.0419 max mem: 8233 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.1197 (0.1297) loss: 0.9041 (0.9058) time: 0.1419 data: 0.0470 max mem: 8233 +Train: [23] Total time: 0:18:18 (0.1758 s / it) +Averaged stats: lr: 0.000113 grad: 0.1197 (0.1297) loss: 0.9041 (0.9058) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:06:28 loss: 0.9173 (0.9173) time: 6.2735 data: 6.2468 max mem: 8233 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.9108 (0.9110) time: 0.1236 data: 0.1031 max mem: 8233 +Eval (hcp-train-subset): [23] Total time: 0:00:14 (0.2366 s / it) +Averaged stats (hcp-train-subset): loss: 0.9108 (0.9110) +Eval (hcp-val): [23] [ 0/62] eta: 0:05:27 loss: 0.9040 (0.9040) time: 5.2750 data: 5.2491 max mem: 8233 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.9065 (0.9060) time: 0.1421 data: 0.1195 max mem: 8233 +Eval (hcp-val): [23] Total time: 0:00:14 (0.2342 s / it) +Averaged stats (hcp-val): loss: 0.9065 (0.9060) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 8:41:29 lr: 0.000113 grad: 0.1322 (0.1322) loss: 0.8932 (0.8932) time: 5.0063 data: 4.6754 max mem: 8233 +Train: [24] [ 100/6250] eta: 0:23:10 lr: 0.000113 grad: 0.1156 (0.1248) loss: 0.9083 (0.9117) time: 0.1727 data: 0.0697 max mem: 8233 +Train: [24] [ 200/6250] eta: 0:20:46 lr: 0.000113 grad: 0.1312 (0.1281) loss: 0.9001 (0.9084) time: 0.1721 data: 0.0881 max mem: 8233 +Train: [24] [ 300/6250] eta: 0:19:13 lr: 0.000113 grad: 0.1284 (0.1299) loss: 0.9039 (0.9066) time: 0.1578 data: 0.0722 max mem: 8233 +Train: [24] [ 400/6250] eta: 0:18:11 lr: 0.000113 grad: 0.1348 (0.1307) loss: 0.9014 (0.9057) time: 0.1694 data: 0.0886 max mem: 8233 +Train: [24] [ 500/6250] eta: 0:17:35 lr: 0.000113 grad: 0.1260 (0.1315) loss: 0.9034 (0.9048) time: 0.1557 data: 0.0676 max mem: 8233 +Train: [24] [ 600/6250] eta: 0:17:02 lr: 0.000113 grad: 0.1185 (0.1320) loss: 0.9040 (0.9041) time: 0.1686 data: 0.0802 max mem: 8233 +Train: [24] [ 700/6250] eta: 0:16:24 lr: 0.000113 grad: 0.1326 (0.1325) loss: 0.8990 (0.9038) time: 0.1258 data: 0.0431 max mem: 8233 +Train: [24] [ 800/6250] eta: 0:15:56 lr: 0.000113 grad: 0.1204 (0.1319) loss: 0.9058 (0.9037) time: 0.1773 data: 0.0726 max mem: 8233 +Train: [24] [ 900/6250] eta: 0:15:29 lr: 0.000113 grad: 0.1251 (0.1314) loss: 0.9047 (0.9037) time: 0.1719 data: 0.0799 max mem: 8233 +Train: [24] [1000/6250] eta: 0:15:11 lr: 0.000113 grad: 0.1252 (0.1313) loss: 0.9041 (0.9035) time: 0.2078 data: 0.1426 max mem: 8233 +Train: [24] [1100/6250] eta: 0:14:48 lr: 0.000113 grad: 0.1384 (0.1312) loss: 0.8961 (0.9032) time: 0.1702 data: 0.0954 max mem: 8233 +Train: [24] [1200/6250] eta: 0:14:38 lr: 0.000113 grad: 0.1213 (0.1309) loss: 0.9057 (0.9032) time: 0.2599 data: 0.1517 max mem: 8233 +Train: [24] [1300/6250] eta: 0:14:18 lr: 0.000113 grad: 0.1417 (0.1312) loss: 0.9038 (0.9030) time: 0.1756 data: 0.0910 max mem: 8233 +Train: [24] [1400/6250] eta: 0:13:55 lr: 0.000113 grad: 0.1252 (0.1312) loss: 0.9012 (0.9028) time: 0.1475 data: 0.0607 max mem: 8233 +Train: [24] [1500/6250] eta: 0:13:34 lr: 0.000113 grad: 0.1277 (0.1310) loss: 0.8972 (0.9028) time: 0.1379 data: 0.0592 max mem: 8233 +Train: [24] [1600/6250] eta: 0:13:20 lr: 0.000113 grad: 0.1244 (0.1308) loss: 0.9043 (0.9027) time: 0.1576 data: 0.0936 max mem: 8233 +Train: [24] [1700/6250] eta: 0:13:03 lr: 0.000113 grad: 0.1245 (0.1307) loss: 0.9009 (0.9026) time: 0.1665 data: 0.0872 max mem: 8233 +Train: [24] [1800/6250] eta: 0:12:42 lr: 0.000113 grad: 0.1327 (0.1305) loss: 0.9015 (0.9026) time: 0.1351 data: 0.0514 max mem: 8233 +Train: [24] [1900/6250] eta: 0:12:22 lr: 0.000113 grad: 0.1247 (0.1303) loss: 0.9026 (0.9027) time: 0.1607 data: 0.0844 max mem: 8233 +Train: [24] [2000/6250] eta: 0:12:06 lr: 0.000113 grad: 0.1218 (0.1302) loss: 0.9029 (0.9027) time: 0.1578 data: 0.0767 max mem: 8233 +Train: [24] [2100/6250] eta: 0:11:48 lr: 0.000113 grad: 0.1320 (0.1301) loss: 0.9007 (0.9027) time: 0.1559 data: 0.0482 max mem: 8233 +Train: [24] [2200/6250] eta: 0:11:29 lr: 0.000113 grad: 0.1232 (0.1300) loss: 0.9036 (0.9027) time: 0.1586 data: 0.0761 max mem: 8233 +Train: [24] [2300/6250] eta: 0:11:10 lr: 0.000113 grad: 0.1273 (0.1300) loss: 0.9026 (0.9028) time: 0.1692 data: 0.0925 max mem: 8233 +Train: [24] [2400/6250] eta: 0:10:55 lr: 0.000113 grad: 0.1246 (0.1300) loss: 0.9006 (0.9028) time: 0.2081 data: 0.1239 max mem: 8233 +Train: [24] [2500/6250] eta: 0:10:40 lr: 0.000113 grad: 0.1233 (0.1300) loss: 0.9047 (0.9028) time: 0.2580 data: 0.1786 max mem: 8233 +Train: [24] [2600/6250] eta: 0:10:24 lr: 0.000113 grad: 0.1267 (0.1302) loss: 0.9023 (0.9027) time: 0.2259 data: 0.1355 max mem: 8233 +Train: [24] [2700/6250] eta: 0:10:08 lr: 0.000113 grad: 0.1211 (0.1301) loss: 0.9022 (0.9027) time: 0.2391 data: 0.1657 max mem: 8233 +Train: [24] [2800/6250] eta: 0:09:50 lr: 0.000113 grad: 0.1285 (0.1302) loss: 0.9035 (0.9027) time: 0.1756 data: 0.0948 max mem: 8233 +Train: [24] [2900/6250] eta: 0:09:32 lr: 0.000112 grad: 0.1279 (0.1300) loss: 0.9042 (0.9028) time: 0.1732 data: 0.0869 max mem: 8233 +Train: [24] [3000/6250] eta: 0:09:15 lr: 0.000112 grad: 0.1274 (0.1299) loss: 0.9035 (0.9028) time: 0.1800 data: 0.0858 max mem: 8233 +Train: [24] [3100/6250] eta: 0:08:57 lr: 0.000112 grad: 0.1246 (0.1300) loss: 0.9027 (0.9028) time: 0.1590 data: 0.0605 max mem: 8233 +Train: [24] [3200/6250] eta: 0:08:41 lr: 0.000112 grad: 0.1280 (0.1300) loss: 0.9002 (0.9028) time: 0.1534 data: 0.0644 max mem: 8233 +Train: [24] [3300/6250] eta: 0:08:22 lr: 0.000112 grad: 0.1269 (0.1301) loss: 0.9036 (0.9028) time: 0.1401 data: 0.0490 max mem: 8233 +Train: [24] [3400/6250] eta: 0:08:05 lr: 0.000112 grad: 0.1278 (0.1301) loss: 0.9074 (0.9028) time: 0.1740 data: 0.0957 max mem: 8233 +Train: [24] [3500/6250] eta: 0:07:47 lr: 0.000112 grad: 0.1209 (0.1301) loss: 0.9036 (0.9028) time: 0.1860 data: 0.0954 max mem: 8233 +Train: [24] [3600/6250] eta: 0:07:30 lr: 0.000112 grad: 0.1270 (0.1300) loss: 0.9002 (0.9028) time: 0.2109 data: 0.1303 max mem: 8233 +Train: [24] [3700/6250] eta: 0:07:13 lr: 0.000112 grad: 0.1247 (0.1299) loss: 0.9063 (0.9029) time: 0.1168 data: 0.0124 max mem: 8233 +Train: [24] [3800/6250] eta: 0:06:57 lr: 0.000112 grad: 0.1300 (0.1299) loss: 0.9030 (0.9029) time: 0.1273 data: 0.0253 max mem: 8233 +Train: [24] [3900/6250] eta: 0:06:41 lr: 0.000112 grad: 0.1261 (0.1298) loss: 0.9045 (0.9029) time: 0.1662 data: 0.0701 max mem: 8233 +Train: [24] [4000/6250] eta: 0:06:25 lr: 0.000112 grad: 0.1204 (0.1298) loss: 0.9021 (0.9029) time: 0.1436 data: 0.0609 max mem: 8233 +Train: [24] [4100/6250] eta: 0:06:07 lr: 0.000112 grad: 0.1153 (0.1298) loss: 0.9083 (0.9029) time: 0.1586 data: 0.0786 max mem: 8233 +Train: [24] [4200/6250] eta: 0:05:50 lr: 0.000112 grad: 0.1258 (0.1298) loss: 0.9091 (0.9029) time: 0.1458 data: 0.0497 max mem: 8233 +Train: [24] [4300/6250] eta: 0:05:33 lr: 0.000112 grad: 0.1299 (0.1298) loss: 0.9026 (0.9028) time: 0.1215 data: 0.0248 max mem: 8233 +Train: [24] [4400/6250] eta: 0:05:16 lr: 0.000112 grad: 0.1336 (0.1299) loss: 0.9038 (0.9028) time: 0.1435 data: 0.0715 max mem: 8233 +Train: [24] [4500/6250] eta: 0:04:58 lr: 0.000112 grad: 0.1209 (0.1299) loss: 0.9021 (0.9028) time: 0.1038 data: 0.0066 max mem: 8233 +Train: [24] [4600/6250] eta: 0:04:41 lr: 0.000112 grad: 0.1176 (0.1298) loss: 0.9045 (0.9028) time: 0.1819 data: 0.1039 max mem: 8233 +Train: [24] [4700/6250] eta: 0:04:23 lr: 0.000112 grad: 0.1287 (0.1299) loss: 0.8992 (0.9028) time: 0.1576 data: 0.0812 max mem: 8233 +Train: [24] [4800/6250] eta: 0:04:07 lr: 0.000112 grad: 0.1314 (0.1299) loss: 0.9017 (0.9028) time: 0.1766 data: 0.0978 max mem: 8233 +Train: [24] [4900/6250] eta: 0:03:49 lr: 0.000112 grad: 0.1226 (0.1299) loss: 0.9020 (0.9027) time: 0.1693 data: 0.0980 max mem: 8233 +Train: [24] [5000/6250] eta: 0:03:33 lr: 0.000112 grad: 0.1245 (0.1299) loss: 0.8989 (0.9027) time: 0.1959 data: 0.1245 max mem: 8233 +Train: [24] [5100/6250] eta: 0:03:16 lr: 0.000112 grad: 0.1209 (0.1299) loss: 0.9004 (0.9027) time: 0.1454 data: 0.0627 max mem: 8233 +Train: [24] [5200/6250] eta: 0:02:59 lr: 0.000112 grad: 0.1243 (0.1298) loss: 0.8983 (0.9027) time: 0.1473 data: 0.0701 max mem: 8233 +Train: [24] [5300/6250] eta: 0:02:41 lr: 0.000112 grad: 0.1236 (0.1298) loss: 0.9005 (0.9026) time: 0.1741 data: 0.0818 max mem: 8233 +Train: [24] [5400/6250] eta: 0:02:25 lr: 0.000112 grad: 0.1221 (0.1298) loss: 0.9066 (0.9027) time: 0.1723 data: 0.0903 max mem: 8233 +Train: [24] [5500/6250] eta: 0:02:08 lr: 0.000112 grad: 0.1299 (0.1297) loss: 0.8984 (0.9027) time: 0.2157 data: 0.0950 max mem: 8233 +Train: [24] [5600/6250] eta: 0:01:51 lr: 0.000112 grad: 0.1265 (0.1297) loss: 0.9009 (0.9026) time: 0.1455 data: 0.0528 max mem: 8233 +Train: [24] [5700/6250] eta: 0:01:33 lr: 0.000112 grad: 0.1271 (0.1298) loss: 0.9005 (0.9026) time: 0.1610 data: 0.0771 max mem: 8233 +Train: [24] [5800/6250] eta: 0:01:16 lr: 0.000112 grad: 0.1353 (0.1298) loss: 0.9022 (0.9026) time: 0.1266 data: 0.0392 max mem: 8233 +Train: [24] [5900/6250] eta: 0:00:59 lr: 0.000112 grad: 0.1345 (0.1298) loss: 0.9016 (0.9026) time: 0.1123 data: 0.0207 max mem: 8233 +Train: [24] [6000/6250] eta: 0:00:42 lr: 0.000112 grad: 0.1268 (0.1298) loss: 0.8994 (0.9025) time: 0.1502 data: 0.0726 max mem: 8233 +Train: [24] [6100/6250] eta: 0:00:25 lr: 0.000112 grad: 0.1198 (0.1297) loss: 0.9067 (0.9025) time: 0.1761 data: 0.0916 max mem: 8233 +Train: [24] [6200/6250] eta: 0:00:08 lr: 0.000112 grad: 0.1232 (0.1297) loss: 0.9021 (0.9025) time: 0.1680 data: 0.0804 max mem: 8233 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.1288 (0.1297) loss: 0.9028 (0.9025) time: 0.1630 data: 0.0780 max mem: 8233 +Train: [24] Total time: 0:17:54 (0.1719 s / it) +Averaged stats: lr: 0.000112 grad: 0.1288 (0.1297) loss: 0.9028 (0.9025) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:03:19 loss: 0.9147 (0.9147) time: 3.2225 data: 3.1487 max mem: 8233 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.9081 (0.9083) time: 0.1580 data: 0.1369 max mem: 8233 +Eval (hcp-train-subset): [24] Total time: 0:00:14 (0.2354 s / it) +Averaged stats (hcp-train-subset): loss: 0.9081 (0.9083) +Making plots (hcp-train-subset): example=34 +Eval (hcp-val): [24] [ 0/62] eta: 0:03:34 loss: 0.8984 (0.8984) time: 3.4652 data: 3.3796 max mem: 8233 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.9039 (0.9040) time: 0.1368 data: 0.1161 max mem: 8233 +Eval (hcp-val): [24] Total time: 0:00:14 (0.2385 s / it) +Averaged stats (hcp-val): loss: 0.9039 (0.9040) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 8:13:44 lr: 0.000112 grad: 0.1245 (0.1245) loss: 0.9128 (0.9128) time: 4.7400 data: 4.5281 max mem: 8233 +Train: [25] [ 100/6250] eta: 0:22:14 lr: 0.000112 grad: 0.1293 (0.1394) loss: 0.9059 (0.9103) time: 0.1388 data: 0.0398 max mem: 8233 +Train: [25] [ 200/6250] eta: 0:20:15 lr: 0.000112 grad: 0.1136 (0.1310) loss: 0.9082 (0.9093) time: 0.1906 data: 0.1086 max mem: 8233 +Train: [25] [ 300/6250] eta: 0:18:48 lr: 0.000112 grad: 0.1402 (0.1310) loss: 0.9023 (0.9075) time: 0.1558 data: 0.0658 max mem: 8233 +Train: [25] [ 400/6250] eta: 0:18:05 lr: 0.000112 grad: 0.1166 (0.1309) loss: 0.9044 (0.9063) time: 0.1637 data: 0.0854 max mem: 8233 +Train: [25] [ 500/6250] eta: 0:17:18 lr: 0.000112 grad: 0.1253 (0.1305) loss: 0.9061 (0.9052) time: 0.1506 data: 0.0651 max mem: 8233 +Train: [25] [ 600/6250] eta: 0:16:56 lr: 0.000112 grad: 0.1334 (0.1304) loss: 0.9027 (0.9047) time: 0.1777 data: 0.0818 max mem: 8233 +Train: [25] [ 700/6250] eta: 0:16:33 lr: 0.000112 grad: 0.1270 (0.1302) loss: 0.9023 (0.9044) time: 0.1702 data: 0.0800 max mem: 8233 +Train: [25] [ 800/6250] eta: 0:16:05 lr: 0.000112 grad: 0.1164 (0.1296) loss: 0.9062 (0.9046) time: 0.1648 data: 0.0777 max mem: 8233 +Train: [25] [ 900/6250] eta: 0:15:42 lr: 0.000112 grad: 0.1230 (0.1288) loss: 0.9071 (0.9048) time: 0.1507 data: 0.0723 max mem: 8233 +Train: [25] [1000/6250] eta: 0:15:17 lr: 0.000112 grad: 0.1156 (0.1280) loss: 0.9094 (0.9050) time: 0.1581 data: 0.0638 max mem: 8233 +Train: [25] [1100/6250] eta: 0:14:51 lr: 0.000112 grad: 0.1197 (0.1278) loss: 0.9045 (0.9051) time: 0.1436 data: 0.0650 max mem: 8233 +Train: [25] [1200/6250] eta: 0:14:26 lr: 0.000112 grad: 0.1256 (0.1272) loss: 0.9067 (0.9052) time: 0.1415 data: 0.0641 max mem: 8233 +Train: [25] [1300/6250] eta: 0:14:11 lr: 0.000112 grad: 0.1242 (0.1272) loss: 0.9074 (0.9054) time: 0.1835 data: 0.1005 max mem: 8233 +Train: [25] [1400/6250] eta: 0:13:52 lr: 0.000112 grad: 0.1198 (0.1272) loss: 0.9016 (0.9054) time: 0.1289 data: 0.0212 max mem: 8233 +Train: [25] [1500/6250] eta: 0:13:38 lr: 0.000112 grad: 0.1193 (0.1269) loss: 0.9071 (0.9055) time: 0.2381 data: 0.1530 max mem: 8233 +Train: [25] [1600/6250] eta: 0:13:11 lr: 0.000111 grad: 0.1193 (0.1268) loss: 0.9032 (0.9056) time: 0.1535 data: 0.0707 max mem: 8233 +Train: [25] [1700/6250] eta: 0:12:52 lr: 0.000111 grad: 0.1234 (0.1267) loss: 0.9029 (0.9056) time: 0.1857 data: 0.1044 max mem: 8233 +Train: [25] [1800/6250] eta: 0:12:35 lr: 0.000111 grad: 0.1212 (0.1266) loss: 0.9078 (0.9056) time: 0.1697 data: 0.0928 max mem: 8233 +Train: [25] [1900/6250] eta: 0:12:16 lr: 0.000111 grad: 0.1215 (0.1265) loss: 0.9070 (0.9056) time: 0.1418 data: 0.0661 max mem: 8233 +Train: [25] [2000/6250] eta: 0:11:54 lr: 0.000111 grad: 0.1244 (0.1264) loss: 0.9043 (0.9055) time: 0.1655 data: 0.0921 max mem: 8233 +Train: [25] [2100/6250] eta: 0:11:39 lr: 0.000111 grad: 0.1282 (0.1264) loss: 0.9044 (0.9055) time: 0.1715 data: 0.0846 max mem: 8233 +Train: [25] [2200/6250] eta: 0:11:21 lr: 0.000111 grad: 0.1230 (0.1263) loss: 0.8982 (0.9054) time: 0.1807 data: 0.1026 max mem: 8233 +Train: [25] [2300/6250] eta: 0:11:03 lr: 0.000111 grad: 0.1210 (0.1262) loss: 0.9016 (0.9053) time: 0.1566 data: 0.0664 max mem: 8233 +Train: [25] [2400/6250] eta: 0:10:45 lr: 0.000111 grad: 0.1189 (0.1261) loss: 0.9016 (0.9051) time: 0.1587 data: 0.0688 max mem: 8233 +Train: [25] [2500/6250] eta: 0:10:26 lr: 0.000111 grad: 0.1205 (0.1261) loss: 0.9018 (0.9050) time: 0.1656 data: 0.0812 max mem: 8233 +Train: [25] [2600/6250] eta: 0:10:08 lr: 0.000111 grad: 0.1190 (0.1262) loss: 0.9000 (0.9048) time: 0.1542 data: 0.0653 max mem: 8233 +Train: [25] [2700/6250] eta: 0:09:50 lr: 0.000111 grad: 0.1175 (0.1263) loss: 0.9031 (0.9047) time: 0.1607 data: 0.0811 max mem: 8233 +Train: [25] [2800/6250] eta: 0:09:36 lr: 0.000111 grad: 0.1223 (0.1262) loss: 0.9048 (0.9047) time: 0.1882 data: 0.0997 max mem: 8233 +Train: [25] [2900/6250] eta: 0:09:19 lr: 0.000111 grad: 0.1297 (0.1262) loss: 0.8993 (0.9046) time: 0.1565 data: 0.0904 max mem: 8233 +Train: [25] [3000/6250] eta: 0:09:02 lr: 0.000111 grad: 0.1290 (0.1262) loss: 0.9040 (0.9046) time: 0.1429 data: 0.0641 max mem: 8233 +Train: [25] [3100/6250] eta: 0:08:44 lr: 0.000111 grad: 0.1218 (0.1263) loss: 0.9041 (0.9044) time: 0.1691 data: 0.0975 max mem: 8233 +Train: [25] [3200/6250] eta: 0:08:27 lr: 0.000111 grad: 0.1174 (0.1262) loss: 0.9009 (0.9044) time: 0.1780 data: 0.0907 max mem: 8233 +Train: [25] [3300/6250] eta: 0:08:10 lr: 0.000111 grad: 0.1171 (0.1262) loss: 0.9034 (0.9043) time: 0.1603 data: 0.0721 max mem: 8233 +Train: [25] [3400/6250] eta: 0:07:53 lr: 0.000111 grad: 0.1194 (0.1262) loss: 0.9045 (0.9042) time: 0.1241 data: 0.0354 max mem: 8233 +Train: [25] [3500/6250] eta: 0:07:35 lr: 0.000111 grad: 0.1154 (0.1262) loss: 0.9039 (0.9042) time: 0.1575 data: 0.0738 max mem: 8233 +Train: [25] [3600/6250] eta: 0:07:17 lr: 0.000111 grad: 0.1160 (0.1262) loss: 0.9042 (0.9042) time: 0.1482 data: 0.0584 max mem: 8233 +Train: [25] [3700/6250] eta: 0:07:01 lr: 0.000111 grad: 0.1211 (0.1262) loss: 0.9054 (0.9041) time: 0.1337 data: 0.0374 max mem: 8233 +Train: [25] [3800/6250] eta: 0:06:45 lr: 0.000111 grad: 0.1241 (0.1262) loss: 0.8985 (0.9040) time: 0.1719 data: 0.0797 max mem: 8233 +Train: [25] [3900/6250] eta: 0:06:29 lr: 0.000111 grad: 0.1198 (0.1263) loss: 0.8973 (0.9040) time: 0.1664 data: 0.0580 max mem: 8233 +Train: [25] [4000/6250] eta: 0:06:13 lr: 0.000111 grad: 0.1246 (0.1263) loss: 0.8997 (0.9040) time: 0.1262 data: 0.0245 max mem: 8233 +Train: [25] [4100/6250] eta: 0:05:57 lr: 0.000111 grad: 0.1234 (0.1263) loss: 0.9019 (0.9039) time: 0.1110 data: 0.0274 max mem: 8233 +Train: [25] [4200/6250] eta: 0:05:40 lr: 0.000111 grad: 0.1191 (0.1262) loss: 0.9007 (0.9039) time: 0.1634 data: 0.0702 max mem: 8233 +Train: [25] [4300/6250] eta: 0:05:24 lr: 0.000111 grad: 0.1214 (0.1262) loss: 0.9028 (0.9039) time: 0.1741 data: 0.0808 max mem: 8233 +Train: [25] [4400/6250] eta: 0:05:07 lr: 0.000111 grad: 0.1285 (0.1262) loss: 0.9034 (0.9038) time: 0.1640 data: 0.0837 max mem: 8233 +Train: [25] [4500/6250] eta: 0:04:52 lr: 0.000111 grad: 0.1241 (0.1262) loss: 0.8975 (0.9037) time: 0.1777 data: 0.0951 max mem: 8233 +Train: [25] [4600/6250] eta: 0:04:35 lr: 0.000111 grad: 0.1212 (0.1262) loss: 0.9008 (0.9036) time: 0.1786 data: 0.0934 max mem: 8233 +Train: [25] [4700/6250] eta: 0:04:19 lr: 0.000111 grad: 0.1199 (0.1262) loss: 0.9013 (0.9036) time: 0.1288 data: 0.0111 max mem: 8233 +Train: [25] [4800/6250] eta: 0:04:02 lr: 0.000111 grad: 0.1293 (0.1261) loss: 0.9032 (0.9035) time: 0.1370 data: 0.0683 max mem: 8233 +Train: [25] [4900/6250] eta: 0:03:45 lr: 0.000111 grad: 0.1199 (0.1261) loss: 0.9020 (0.9035) time: 0.1502 data: 0.0729 max mem: 8233 +Train: [25] [5000/6250] eta: 0:03:28 lr: 0.000111 grad: 0.1192 (0.1261) loss: 0.9030 (0.9035) time: 0.1470 data: 0.0667 max mem: 8233 +Train: [25] [5100/6250] eta: 0:03:11 lr: 0.000111 grad: 0.1210 (0.1261) loss: 0.9024 (0.9035) time: 0.1635 data: 0.0814 max mem: 8233 +Train: [25] [5200/6250] eta: 0:02:55 lr: 0.000111 grad: 0.1229 (0.1260) loss: 0.9010 (0.9035) time: 0.1716 data: 0.0901 max mem: 8233 +Train: [25] [5300/6250] eta: 0:02:38 lr: 0.000111 grad: 0.1207 (0.1260) loss: 0.9028 (0.9035) time: 0.1875 data: 0.1179 max mem: 8233 +Train: [25] [5400/6250] eta: 0:02:22 lr: 0.000111 grad: 0.1289 (0.1260) loss: 0.9037 (0.9035) time: 0.1464 data: 0.0720 max mem: 8233 +Train: [25] [5500/6250] eta: 0:02:05 lr: 0.000111 grad: 0.1195 (0.1260) loss: 0.8996 (0.9035) time: 0.1728 data: 0.0885 max mem: 8233 +Train: [25] [5600/6250] eta: 0:01:48 lr: 0.000111 grad: 0.1223 (0.1259) loss: 0.9033 (0.9035) time: 0.1761 data: 0.0984 max mem: 8233 +Train: [25] [5700/6250] eta: 0:01:32 lr: 0.000111 grad: 0.1153 (0.1258) loss: 0.9067 (0.9035) time: 0.1489 data: 0.0689 max mem: 8233 +Train: [25] [5800/6250] eta: 0:01:15 lr: 0.000111 grad: 0.1193 (0.1258) loss: 0.9080 (0.9035) time: 0.3047 data: 0.2226 max mem: 8233 +Train: [25] [5900/6250] eta: 0:00:58 lr: 0.000111 grad: 0.1110 (0.1257) loss: 0.9043 (0.9035) time: 0.1534 data: 0.0739 max mem: 8233 +Train: [25] [6000/6250] eta: 0:00:42 lr: 0.000111 grad: 0.1142 (0.1257) loss: 0.9046 (0.9036) time: 0.2998 data: 0.1909 max mem: 8233 +Train: [25] [6100/6250] eta: 0:00:25 lr: 0.000111 grad: 0.1222 (0.1257) loss: 0.9000 (0.9036) time: 0.1831 data: 0.1046 max mem: 8233 +Train: [25] [6200/6250] eta: 0:00:08 lr: 0.000111 grad: 0.1202 (0.1257) loss: 0.9042 (0.9036) time: 0.1222 data: 0.0003 max mem: 8233 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.1265 (0.1257) loss: 0.9031 (0.9036) time: 0.1945 data: 0.1104 max mem: 8233 +Train: [25] Total time: 0:17:40 (0.1697 s / it) +Averaged stats: lr: 0.000111 grad: 0.1265 (0.1257) loss: 0.9031 (0.9036) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:04:07 loss: 0.9154 (0.9154) time: 3.9843 data: 3.8844 max mem: 8233 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.9104 (0.9085) time: 0.1262 data: 0.1040 max mem: 8233 +Eval (hcp-train-subset): [25] Total time: 0:00:15 (0.2502 s / it) +Averaged stats (hcp-train-subset): loss: 0.9104 (0.9085) +Eval (hcp-val): [25] [ 0/62] eta: 0:05:24 loss: 0.9019 (0.9019) time: 5.2355 data: 5.2079 max mem: 8233 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.9022 (0.9037) time: 0.1448 data: 0.1236 max mem: 8233 +Eval (hcp-val): [25] Total time: 0:00:15 (0.2477 s / it) +Averaged stats (hcp-val): loss: 0.9022 (0.9037) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 10:00:20 lr: 0.000111 grad: 0.0985 (0.0985) loss: 0.9208 (0.9208) time: 5.7633 data: 5.5281 max mem: 8233 +Train: [26] [ 100/6250] eta: 0:23:32 lr: 0.000111 grad: 0.1292 (0.1439) loss: 0.8989 (0.9025) time: 0.1995 data: 0.1015 max mem: 8233 +Train: [26] [ 200/6250] eta: 0:20:16 lr: 0.000110 grad: 0.1161 (0.1350) loss: 0.9021 (0.9017) time: 0.1769 data: 0.0817 max mem: 8233 +Train: [26] [ 300/6250] eta: 0:18:55 lr: 0.000110 grad: 0.1207 (0.1324) loss: 0.9015 (0.9015) time: 0.1733 data: 0.1003 max mem: 8233 +Train: [26] [ 400/6250] eta: 0:17:57 lr: 0.000110 grad: 0.1235 (0.1301) loss: 0.9094 (0.9022) time: 0.1642 data: 0.0799 max mem: 8233 +Train: [26] [ 500/6250] eta: 0:17:07 lr: 0.000110 grad: 0.1198 (0.1286) loss: 0.9059 (0.9027) time: 0.1585 data: 0.0725 max mem: 8233 +Train: [26] [ 600/6250] eta: 0:16:41 lr: 0.000110 grad: 0.1272 (0.1280) loss: 0.9024 (0.9029) time: 0.1603 data: 0.0711 max mem: 8233 +Train: [26] [ 700/6250] eta: 0:16:16 lr: 0.000110 grad: 0.1215 (0.1282) loss: 0.9008 (0.9030) time: 0.1650 data: 0.0632 max mem: 8233 +Train: [26] [ 800/6250] eta: 0:15:54 lr: 0.000110 grad: 0.1205 (0.1286) loss: 0.9016 (0.9028) time: 0.1777 data: 0.0986 max mem: 8233 +Train: [26] [ 900/6250] eta: 0:15:33 lr: 0.000110 grad: 0.1200 (0.1283) loss: 0.9071 (0.9029) time: 0.1336 data: 0.0296 max mem: 8233 +Train: [26] [1000/6250] eta: 0:15:33 lr: 0.000110 grad: 0.1147 (0.1278) loss: 0.9051 (0.9030) time: 0.1144 data: 0.0005 max mem: 8233 +Train: [26] [1100/6250] eta: 0:15:12 lr: 0.000110 grad: 0.1184 (0.1273) loss: 0.9008 (0.9030) time: 0.1898 data: 0.1018 max mem: 8233 +Train: [26] [1200/6250] eta: 0:15:01 lr: 0.000110 grad: 0.1193 (0.1273) loss: 0.9081 (0.9031) time: 0.1959 data: 0.1275 max mem: 8233 +Train: [26] [1300/6250] eta: 0:14:38 lr: 0.000110 grad: 0.1095 (0.1268) loss: 0.9077 (0.9032) time: 0.1533 data: 0.0590 max mem: 8233 +Train: [26] [1400/6250] eta: 0:14:28 lr: 0.000110 grad: 0.1187 (0.1266) loss: 0.9075 (0.9032) time: 0.1503 data: 0.0614 max mem: 8233 +Train: [26] [1500/6250] eta: 0:14:06 lr: 0.000110 grad: 0.1179 (0.1266) loss: 0.9063 (0.9033) time: 0.1824 data: 0.1072 max mem: 8233 +Train: [26] [1600/6250] eta: 0:13:50 lr: 0.000110 grad: 0.1273 (0.1266) loss: 0.9028 (0.9032) time: 0.1837 data: 0.0897 max mem: 8233 +Train: [26] [1700/6250] eta: 0:13:28 lr: 0.000110 grad: 0.1211 (0.1266) loss: 0.9059 (0.9032) time: 0.1441 data: 0.0566 max mem: 8233 +Train: [26] [1800/6250] eta: 0:13:09 lr: 0.000110 grad: 0.1163 (0.1267) loss: 0.9024 (0.9032) time: 0.1324 data: 0.0488 max mem: 8233 +Train: [26] [1900/6250] eta: 0:12:49 lr: 0.000110 grad: 0.1192 (0.1266) loss: 0.9030 (0.9032) time: 0.1765 data: 0.1078 max mem: 8233 +Train: [26] [2000/6250] eta: 0:12:27 lr: 0.000110 grad: 0.1171 (0.1263) loss: 0.9057 (0.9032) time: 0.1451 data: 0.0675 max mem: 8233 +Train: [26] [2100/6250] eta: 0:12:05 lr: 0.000110 grad: 0.1217 (0.1262) loss: 0.9046 (0.9033) time: 0.1457 data: 0.0792 max mem: 8233 +Train: [26] [2200/6250] eta: 0:11:47 lr: 0.000110 grad: 0.1138 (0.1260) loss: 0.9055 (0.9033) time: 0.1664 data: 0.0885 max mem: 8233 +Train: [26] [2300/6250] eta: 0:11:28 lr: 0.000110 grad: 0.1179 (0.1259) loss: 0.9053 (0.9034) time: 0.1600 data: 0.0836 max mem: 8233 +Train: [26] [2400/6250] eta: 0:11:10 lr: 0.000110 grad: 0.1264 (0.1257) loss: 0.9067 (0.9033) time: 0.1709 data: 0.0918 max mem: 8233 +Train: [26] [2500/6250] eta: 0:10:50 lr: 0.000110 grad: 0.1343 (0.1257) loss: 0.9070 (0.9034) time: 0.1327 data: 0.0458 max mem: 8233 +Train: [26] [2600/6250] eta: 0:10:31 lr: 0.000110 grad: 0.1170 (0.1256) loss: 0.9041 (0.9034) time: 0.1721 data: 0.0943 max mem: 8233 +Train: [26] [2700/6250] eta: 0:10:13 lr: 0.000110 grad: 0.1207 (0.1257) loss: 0.9014 (0.9033) time: 0.2031 data: 0.1306 max mem: 8233 +Train: [26] [2800/6250] eta: 0:10:04 lr: 0.000110 grad: 0.1178 (0.1255) loss: 0.9011 (0.9033) time: 0.3999 data: 0.3171 max mem: 8233 +Train: [26] [2900/6250] eta: 0:09:44 lr: 0.000110 grad: 0.1249 (0.1256) loss: 0.8995 (0.9032) time: 0.1706 data: 0.0785 max mem: 8233 +Train: [26] [3000/6250] eta: 0:09:26 lr: 0.000110 grad: 0.1157 (0.1257) loss: 0.9052 (0.9032) time: 0.1367 data: 0.0552 max mem: 8233 +Train: [26] [3100/6250] eta: 0:09:08 lr: 0.000110 grad: 0.1236 (0.1257) loss: 0.9001 (0.9032) time: 0.1690 data: 0.0876 max mem: 8233 +Train: [26] [3200/6250] eta: 0:08:49 lr: 0.000110 grad: 0.1273 (0.1256) loss: 0.9048 (0.9032) time: 0.1672 data: 0.0917 max mem: 8233 +Train: [26] [3300/6250] eta: 0:08:31 lr: 0.000110 grad: 0.1236 (0.1256) loss: 0.9045 (0.9033) time: 0.1569 data: 0.0708 max mem: 8233 +Train: [26] [3400/6250] eta: 0:08:13 lr: 0.000110 grad: 0.1199 (0.1255) loss: 0.9070 (0.9033) time: 0.1790 data: 0.0915 max mem: 8233 +Train: [26] [3500/6250] eta: 0:07:55 lr: 0.000110 grad: 0.1260 (0.1255) loss: 0.9007 (0.9033) time: 0.1698 data: 0.0890 max mem: 8233 +Train: [26] [3600/6250] eta: 0:07:36 lr: 0.000110 grad: 0.1169 (0.1255) loss: 0.9045 (0.9034) time: 0.1494 data: 0.0637 max mem: 8233 +Train: [26] [3700/6250] eta: 0:07:17 lr: 0.000110 grad: 0.1220 (0.1253) loss: 0.9005 (0.9034) time: 0.1608 data: 0.0749 max mem: 8233 +Train: [26] [3800/6250] eta: 0:07:00 lr: 0.000110 grad: 0.1160 (0.1252) loss: 0.9026 (0.9034) time: 0.1790 data: 0.1025 max mem: 8233 +Train: [26] [3900/6250] eta: 0:06:47 lr: 0.000110 grad: 0.1173 (0.1251) loss: 0.8985 (0.9033) time: 0.4302 data: 0.3590 max mem: 8233 +Train: [26] [4000/6250] eta: 0:06:29 lr: 0.000110 grad: 0.1253 (0.1250) loss: 0.9016 (0.9033) time: 0.1657 data: 0.0582 max mem: 8233 +Train: [26] [4100/6250] eta: 0:06:13 lr: 0.000110 grad: 0.1247 (0.1250) loss: 0.9012 (0.9032) time: 0.2399 data: 0.1408 max mem: 8233 +Train: [26] [4200/6250] eta: 0:05:56 lr: 0.000110 grad: 0.1207 (0.1250) loss: 0.8994 (0.9032) time: 0.2191 data: 0.1336 max mem: 8233 +Train: [26] [4300/6250] eta: 0:05:37 lr: 0.000110 grad: 0.1189 (0.1250) loss: 0.9059 (0.9032) time: 0.1604 data: 0.0779 max mem: 8233 +Train: [26] [4400/6250] eta: 0:05:20 lr: 0.000110 grad: 0.1213 (0.1249) loss: 0.8980 (0.9031) time: 0.1442 data: 0.0644 max mem: 8233 +Train: [26] [4500/6250] eta: 0:05:03 lr: 0.000110 grad: 0.1264 (0.1249) loss: 0.9064 (0.9031) time: 0.3499 data: 0.2787 max mem: 8233 +Train: [26] [4600/6250] eta: 0:04:47 lr: 0.000110 grad: 0.1136 (0.1248) loss: 0.9011 (0.9031) time: 0.1245 data: 0.0214 max mem: 8233 +Train: [26] [4700/6250] eta: 0:04:29 lr: 0.000110 grad: 0.1151 (0.1248) loss: 0.9060 (0.9031) time: 0.1423 data: 0.0588 max mem: 8233 +Train: [26] [4800/6250] eta: 0:04:12 lr: 0.000109 grad: 0.1203 (0.1247) loss: 0.9018 (0.9031) time: 0.2386 data: 0.1635 max mem: 8233 +Train: [26] [4900/6250] eta: 0:03:54 lr: 0.000109 grad: 0.1271 (0.1247) loss: 0.9008 (0.9031) time: 0.1740 data: 0.1003 max mem: 8233 +Train: [26] [5000/6250] eta: 0:03:36 lr: 0.000109 grad: 0.1244 (0.1247) loss: 0.8999 (0.9030) time: 0.1664 data: 0.0870 max mem: 8233 +Train: [26] [5100/6250] eta: 0:03:19 lr: 0.000109 grad: 0.1228 (0.1247) loss: 0.9030 (0.9030) time: 0.1658 data: 0.0762 max mem: 8233 +Train: [26] [5200/6250] eta: 0:03:02 lr: 0.000109 grad: 0.1264 (0.1248) loss: 0.8978 (0.9029) time: 0.1558 data: 0.0525 max mem: 8233 +Train: [26] [5300/6250] eta: 0:02:44 lr: 0.000109 grad: 0.1225 (0.1248) loss: 0.9001 (0.9029) time: 0.1661 data: 0.0753 max mem: 8233 +Train: [26] [5400/6250] eta: 0:02:26 lr: 0.000109 grad: 0.1208 (0.1248) loss: 0.8998 (0.9028) time: 0.1225 data: 0.0357 max mem: 8233 +Train: [26] [5500/6250] eta: 0:02:09 lr: 0.000109 grad: 0.1190 (0.1247) loss: 0.8992 (0.9027) time: 0.1682 data: 0.0906 max mem: 8233 +Train: [26] [5600/6250] eta: 0:01:52 lr: 0.000109 grad: 0.1308 (0.1247) loss: 0.9031 (0.9027) time: 0.1556 data: 0.0751 max mem: 8233 +Train: [26] [5700/6250] eta: 0:01:34 lr: 0.000109 grad: 0.1210 (0.1247) loss: 0.9021 (0.9026) time: 0.1558 data: 0.0784 max mem: 8233 +Train: [26] [5800/6250] eta: 0:01:17 lr: 0.000109 grad: 0.1227 (0.1247) loss: 0.8991 (0.9026) time: 0.1245 data: 0.0320 max mem: 8233 +Train: [26] [5900/6250] eta: 0:01:00 lr: 0.000109 grad: 0.1242 (0.1247) loss: 0.8998 (0.9025) time: 0.1124 data: 0.0003 max mem: 8233 +Train: [26] [6000/6250] eta: 0:00:43 lr: 0.000109 grad: 0.1224 (0.1247) loss: 0.8979 (0.9025) time: 0.1577 data: 0.0712 max mem: 8233 +Train: [26] [6100/6250] eta: 0:00:25 lr: 0.000109 grad: 0.1256 (0.1247) loss: 0.9006 (0.9025) time: 0.1476 data: 0.0756 max mem: 8233 +Train: [26] [6200/6250] eta: 0:00:08 lr: 0.000109 grad: 0.1207 (0.1246) loss: 0.8926 (0.9024) time: 0.1212 data: 0.0164 max mem: 8233 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.1153 (0.1246) loss: 0.9014 (0.9024) time: 0.1752 data: 0.0614 max mem: 8233 +Train: [26] Total time: 0:18:05 (0.1737 s / it) +Averaged stats: lr: 0.000109 grad: 0.1153 (0.1246) loss: 0.9014 (0.9024) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:06:14 loss: 0.9173 (0.9173) time: 6.0360 data: 6.0074 max mem: 8233 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.9099 (0.9078) time: 0.1218 data: 0.0998 max mem: 8233 +Eval (hcp-train-subset): [26] Total time: 0:00:14 (0.2398 s / it) +Averaged stats (hcp-train-subset): loss: 0.9099 (0.9078) +Eval (hcp-val): [26] [ 0/62] eta: 0:05:19 loss: 0.8997 (0.8997) time: 5.1562 data: 5.1291 max mem: 8233 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.9030 (0.9031) time: 0.1587 data: 0.1364 max mem: 8233 +Eval (hcp-val): [26] Total time: 0:00:15 (0.2470 s / it) +Averaged stats (hcp-val): loss: 0.9030 (0.9031) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 10:57:27 lr: 0.000109 grad: 0.0999 (0.0999) loss: 0.9083 (0.9083) time: 6.3116 data: 6.1896 max mem: 8233 +Train: [27] [ 100/6250] eta: 0:24:34 lr: 0.000109 grad: 0.1150 (0.1173) loss: 0.9097 (0.9095) time: 0.1714 data: 0.0713 max mem: 8233 +Train: [27] [ 200/6250] eta: 0:21:31 lr: 0.000109 grad: 0.1112 (0.1198) loss: 0.9074 (0.9056) time: 0.1668 data: 0.0707 max mem: 8233 +Train: [27] [ 300/6250] eta: 0:20:03 lr: 0.000109 grad: 0.1256 (0.1215) loss: 0.8990 (0.9035) time: 0.1583 data: 0.0654 max mem: 8233 +Train: [27] [ 400/6250] eta: 0:19:33 lr: 0.000109 grad: 0.1141 (0.1229) loss: 0.9038 (0.9021) time: 0.1951 data: 0.1136 max mem: 8233 +Train: [27] [ 500/6250] eta: 0:19:02 lr: 0.000109 grad: 0.1278 (0.1235) loss: 0.9029 (0.9016) time: 0.1800 data: 0.0903 max mem: 8233 +Train: [27] [ 600/6250] eta: 0:18:25 lr: 0.000109 grad: 0.1167 (0.1233) loss: 0.9015 (0.9014) time: 0.1737 data: 0.0908 max mem: 8233 +Train: [27] [ 700/6250] eta: 0:17:55 lr: 0.000109 grad: 0.1185 (0.1236) loss: 0.8997 (0.9011) time: 0.1857 data: 0.0908 max mem: 8233 +Train: [27] [ 800/6250] eta: 0:17:29 lr: 0.000109 grad: 0.1129 (0.1234) loss: 0.9006 (0.9010) time: 0.2044 data: 0.1224 max mem: 8233 +Train: [27] [ 900/6250] eta: 0:16:55 lr: 0.000109 grad: 0.1215 (0.1236) loss: 0.8965 (0.9008) time: 0.1629 data: 0.0785 max mem: 8233 +Train: [27] [1000/6250] eta: 0:16:36 lr: 0.000109 grad: 0.1200 (0.1234) loss: 0.8994 (0.9007) time: 0.1711 data: 0.0566 max mem: 8233 +Train: [27] [1100/6250] eta: 0:16:07 lr: 0.000109 grad: 0.1220 (0.1235) loss: 0.9031 (0.9006) time: 0.1725 data: 0.0823 max mem: 8233 +Train: [27] [1200/6250] eta: 0:15:38 lr: 0.000109 grad: 0.1145 (0.1234) loss: 0.8971 (0.9004) time: 0.1719 data: 0.0820 max mem: 8233 +Train: [27] [1300/6250] eta: 0:15:28 lr: 0.000109 grad: 0.1286 (0.1233) loss: 0.9012 (0.9003) time: 0.3083 data: 0.1831 max mem: 8233 +Train: [27] [1400/6250] eta: 0:14:59 lr: 0.000109 grad: 0.1179 (0.1232) loss: 0.9035 (0.9003) time: 0.2136 data: 0.1243 max mem: 8233 +Train: [27] [1500/6250] eta: 0:14:37 lr: 0.000109 grad: 0.1165 (0.1232) loss: 0.8999 (0.9004) time: 0.1908 data: 0.1208 max mem: 8233 +Train: [27] [1600/6250] eta: 0:14:30 lr: 0.000109 grad: 0.1201 (0.1231) loss: 0.8992 (0.9003) time: 0.3944 data: 0.3054 max mem: 8233 +Train: [27] [1700/6250] eta: 0:14:07 lr: 0.000109 grad: 0.1157 (0.1230) loss: 0.8985 (0.9003) time: 0.2250 data: 0.1426 max mem: 8233 +Train: [27] [1800/6250] eta: 0:13:45 lr: 0.000109 grad: 0.1214 (0.1229) loss: 0.8972 (0.9004) time: 0.1621 data: 0.0798 max mem: 8233 +Train: [27] [1900/6250] eta: 0:13:22 lr: 0.000109 grad: 0.1160 (0.1228) loss: 0.9012 (0.9005) time: 0.2051 data: 0.1343 max mem: 8233 +Train: [27] [2000/6250] eta: 0:13:02 lr: 0.000109 grad: 0.1201 (0.1226) loss: 0.8981 (0.9005) time: 0.1302 data: 0.0424 max mem: 8233 +Train: [27] [2100/6250] eta: 0:12:41 lr: 0.000109 grad: 0.1140 (0.1224) loss: 0.8996 (0.9005) time: 0.1635 data: 0.0874 max mem: 8233 +Train: [27] [2200/6250] eta: 0:12:19 lr: 0.000109 grad: 0.1200 (0.1223) loss: 0.8945 (0.9006) time: 0.1821 data: 0.1164 max mem: 8233 +Train: [27] [2300/6250] eta: 0:11:58 lr: 0.000109 grad: 0.1126 (0.1223) loss: 0.9034 (0.9007) time: 0.1410 data: 0.0629 max mem: 8233 +Train: [27] [2400/6250] eta: 0:11:38 lr: 0.000109 grad: 0.1247 (0.1222) loss: 0.9011 (0.9008) time: 0.1819 data: 0.0995 max mem: 8233 +Train: [27] [2500/6250] eta: 0:11:16 lr: 0.000109 grad: 0.1233 (0.1222) loss: 0.9014 (0.9008) time: 0.1654 data: 0.0901 max mem: 8233 +Train: [27] [2600/6250] eta: 0:10:55 lr: 0.000109 grad: 0.1216 (0.1221) loss: 0.9061 (0.9009) time: 0.1507 data: 0.0576 max mem: 8233 +Train: [27] [2700/6250] eta: 0:10:35 lr: 0.000109 grad: 0.1140 (0.1218) loss: 0.9034 (0.9010) time: 0.1635 data: 0.0660 max mem: 8233 +Train: [27] [2800/6250] eta: 0:10:13 lr: 0.000109 grad: 0.1146 (0.1217) loss: 0.9009 (0.9010) time: 0.1347 data: 0.0367 max mem: 8233 +Train: [27] [2900/6250] eta: 0:09:52 lr: 0.000109 grad: 0.1236 (0.1217) loss: 0.9009 (0.9011) time: 0.1497 data: 0.0781 max mem: 8233 +Train: [27] [3000/6250] eta: 0:09:32 lr: 0.000109 grad: 0.1140 (0.1216) loss: 0.9018 (0.9012) time: 0.1501 data: 0.0632 max mem: 8233 +Train: [27] [3100/6250] eta: 0:09:16 lr: 0.000108 grad: 0.1153 (0.1215) loss: 0.9031 (0.9012) time: 0.1820 data: 0.0935 max mem: 8233 +Train: [27] [3200/6250] eta: 0:09:00 lr: 0.000108 grad: 0.1193 (0.1215) loss: 0.9022 (0.9013) time: 0.2174 data: 0.1352 max mem: 8233 +Train: [27] [3300/6250] eta: 0:08:42 lr: 0.000108 grad: 0.1110 (0.1213) loss: 0.9070 (0.9014) time: 0.1621 data: 0.0774 max mem: 8233 +Train: [27] [3400/6250] eta: 0:08:22 lr: 0.000108 grad: 0.1129 (0.1211) loss: 0.9064 (0.9015) time: 0.1507 data: 0.0739 max mem: 8233 +Train: [27] [3500/6250] eta: 0:08:04 lr: 0.000108 grad: 0.1104 (0.1210) loss: 0.9072 (0.9015) time: 0.1662 data: 0.0756 max mem: 8233 +Train: [27] [3600/6250] eta: 0:07:46 lr: 0.000108 grad: 0.1240 (0.1211) loss: 0.9018 (0.9015) time: 0.1639 data: 0.0803 max mem: 8233 +Train: [27] [3700/6250] eta: 0:07:29 lr: 0.000108 grad: 0.1250 (0.1212) loss: 0.8972 (0.9015) time: 0.2035 data: 0.1198 max mem: 8233 +Train: [27] [3800/6250] eta: 0:07:10 lr: 0.000108 grad: 0.1158 (0.1211) loss: 0.9016 (0.9015) time: 0.1540 data: 0.0677 max mem: 8233 +Train: [27] [3900/6250] eta: 0:06:52 lr: 0.000108 grad: 0.1148 (0.1210) loss: 0.9036 (0.9015) time: 0.1772 data: 0.0922 max mem: 8233 +Train: [27] [4000/6250] eta: 0:06:34 lr: 0.000108 grad: 0.1116 (0.1210) loss: 0.8992 (0.9015) time: 0.1885 data: 0.1073 max mem: 8233 +Train: [27] [4100/6250] eta: 0:06:16 lr: 0.000108 grad: 0.1094 (0.1209) loss: 0.9027 (0.9015) time: 0.2144 data: 0.1186 max mem: 8233 +Train: [27] [4200/6250] eta: 0:05:58 lr: 0.000108 grad: 0.1208 (0.1209) loss: 0.9007 (0.9015) time: 0.1507 data: 0.0576 max mem: 8233 +Train: [27] [4300/6250] eta: 0:05:40 lr: 0.000108 grad: 0.1087 (0.1209) loss: 0.8975 (0.9014) time: 0.1398 data: 0.0554 max mem: 8233 +Train: [27] [4400/6250] eta: 0:05:23 lr: 0.000108 grad: 0.1230 (0.1209) loss: 0.9013 (0.9014) time: 0.1620 data: 0.0758 max mem: 8233 +Train: [27] [4500/6250] eta: 0:05:06 lr: 0.000108 grad: 0.1197 (0.1209) loss: 0.9042 (0.9014) time: 0.0893 data: 0.0002 max mem: 8233 +Train: [27] [4600/6250] eta: 0:04:48 lr: 0.000108 grad: 0.1271 (0.1208) loss: 0.8945 (0.9014) time: 0.1572 data: 0.0767 max mem: 8233 +Train: [27] [4700/6250] eta: 0:04:30 lr: 0.000108 grad: 0.1136 (0.1209) loss: 0.9053 (0.9014) time: 0.1841 data: 0.0960 max mem: 8233 +Train: [27] [4800/6250] eta: 0:04:13 lr: 0.000108 grad: 0.1224 (0.1209) loss: 0.9006 (0.9014) time: 0.1709 data: 0.1063 max mem: 8233 +Train: [27] [4900/6250] eta: 0:03:55 lr: 0.000108 grad: 0.1074 (0.1208) loss: 0.9046 (0.9014) time: 0.1843 data: 0.1124 max mem: 8233 +Train: [27] [5000/6250] eta: 0:03:37 lr: 0.000108 grad: 0.1224 (0.1208) loss: 0.9037 (0.9014) time: 0.1438 data: 0.0662 max mem: 8233 +Train: [27] [5100/6250] eta: 0:03:19 lr: 0.000108 grad: 0.1112 (0.1207) loss: 0.9043 (0.9014) time: 0.1527 data: 0.0778 max mem: 8233 +Train: [27] [5200/6250] eta: 0:03:01 lr: 0.000108 grad: 0.1162 (0.1207) loss: 0.9015 (0.9014) time: 0.1509 data: 0.0680 max mem: 8233 +Train: [27] [5300/6250] eta: 0:02:44 lr: 0.000108 grad: 0.1190 (0.1208) loss: 0.8983 (0.9014) time: 0.1754 data: 0.1084 max mem: 8233 +Train: [27] [5400/6250] eta: 0:02:26 lr: 0.000108 grad: 0.1145 (0.1208) loss: 0.9032 (0.9014) time: 0.1398 data: 0.0671 max mem: 8233 +Train: [27] [5500/6250] eta: 0:02:09 lr: 0.000108 grad: 0.1147 (0.1207) loss: 0.9048 (0.9014) time: 0.1794 data: 0.1017 max mem: 8233 +Train: [27] [5600/6250] eta: 0:01:52 lr: 0.000108 grad: 0.1128 (0.1207) loss: 0.8962 (0.9014) time: 0.1426 data: 0.0639 max mem: 8233 +Train: [27] [5700/6250] eta: 0:01:34 lr: 0.000108 grad: 0.1147 (0.1208) loss: 0.8979 (0.9013) time: 0.1416 data: 0.0649 max mem: 8233 +Train: [27] [5800/6250] eta: 0:01:17 lr: 0.000108 grad: 0.1211 (0.1208) loss: 0.9008 (0.9013) time: 0.1711 data: 0.1151 max mem: 8233 +Train: [27] [5900/6250] eta: 0:01:00 lr: 0.000108 grad: 0.1189 (0.1207) loss: 0.8991 (0.9013) time: 0.1462 data: 0.0756 max mem: 8233 +Train: [27] [6000/6250] eta: 0:00:42 lr: 0.000108 grad: 0.1162 (0.1208) loss: 0.8972 (0.9012) time: 0.1699 data: 0.0855 max mem: 8233 +Train: [27] [6100/6250] eta: 0:00:25 lr: 0.000108 grad: 0.1168 (0.1208) loss: 0.8999 (0.9012) time: 0.1474 data: 0.0768 max mem: 8233 +Train: [27] [6200/6250] eta: 0:00:08 lr: 0.000108 grad: 0.1186 (0.1209) loss: 0.9014 (0.9012) time: 0.1707 data: 0.0929 max mem: 8233 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.1176 (0.1209) loss: 0.8966 (0.9012) time: 0.1696 data: 0.1064 max mem: 8233 +Train: [27] Total time: 0:17:59 (0.1728 s / it) +Averaged stats: lr: 0.000108 grad: 0.1176 (0.1209) loss: 0.8966 (0.9012) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:04:55 loss: 0.9120 (0.9120) time: 4.7621 data: 4.7272 max mem: 8233 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.9081 (0.9068) time: 0.1316 data: 0.1111 max mem: 8233 +Eval (hcp-train-subset): [27] Total time: 0:00:14 (0.2278 s / it) +Averaged stats (hcp-train-subset): loss: 0.9081 (0.9068) +Eval (hcp-val): [27] [ 0/62] eta: 0:03:54 loss: 0.9028 (0.9028) time: 3.7749 data: 3.7047 max mem: 8233 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.9022 (0.9026) time: 0.1341 data: 0.1123 max mem: 8233 +Eval (hcp-val): [27] Total time: 0:00:13 (0.2232 s / it) +Averaged stats (hcp-val): loss: 0.9022 (0.9026) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 12:03:43 lr: 0.000108 grad: 0.1622 (0.1622) loss: 0.9113 (0.9113) time: 6.9477 data: 6.8464 max mem: 8233 +Train: [28] [ 100/6250] eta: 0:23:13 lr: 0.000108 grad: 0.1222 (0.1379) loss: 0.8992 (0.9008) time: 0.1803 data: 0.0783 max mem: 8233 +Train: [28] [ 200/6250] eta: 0:19:36 lr: 0.000108 grad: 0.1156 (0.1298) loss: 0.8930 (0.8997) time: 0.1767 data: 0.0880 max mem: 8233 +Train: [28] [ 300/6250] eta: 0:18:29 lr: 0.000108 grad: 0.1175 (0.1263) loss: 0.8970 (0.8984) time: 0.1755 data: 0.0884 max mem: 8233 +Train: [28] [ 400/6250] eta: 0:17:36 lr: 0.000108 grad: 0.1145 (0.1247) loss: 0.8958 (0.8977) time: 0.1629 data: 0.0795 max mem: 8233 +Train: [28] [ 500/6250] eta: 0:17:05 lr: 0.000108 grad: 0.1154 (0.1242) loss: 0.9010 (0.8978) time: 0.1573 data: 0.0717 max mem: 8233 +Train: [28] [ 600/6250] eta: 0:16:31 lr: 0.000108 grad: 0.1153 (0.1236) loss: 0.9027 (0.8980) time: 0.1539 data: 0.0752 max mem: 8233 +Train: [28] [ 700/6250] eta: 0:16:08 lr: 0.000108 grad: 0.1133 (0.1226) loss: 0.9010 (0.8982) time: 0.1731 data: 0.0941 max mem: 8233 +Train: [28] [ 800/6250] eta: 0:15:49 lr: 0.000108 grad: 0.1225 (0.1224) loss: 0.9002 (0.8985) time: 0.1707 data: 0.0600 max mem: 8233 +Train: [28] [ 900/6250] eta: 0:15:23 lr: 0.000108 grad: 0.1170 (0.1220) loss: 0.9028 (0.8989) time: 0.1353 data: 0.0306 max mem: 8233 +Train: [28] [1000/6250] eta: 0:15:02 lr: 0.000108 grad: 0.1099 (0.1219) loss: 0.9015 (0.8991) time: 0.1637 data: 0.0902 max mem: 8233 +Train: [28] [1100/6250] eta: 0:14:36 lr: 0.000108 grad: 0.1154 (0.1217) loss: 0.9047 (0.8993) time: 0.1566 data: 0.0770 max mem: 8233 +Train: [28] [1200/6250] eta: 0:14:13 lr: 0.000108 grad: 0.1105 (0.1216) loss: 0.8999 (0.8995) time: 0.1723 data: 0.0949 max mem: 8233 +Train: [28] [1300/6250] eta: 0:13:55 lr: 0.000107 grad: 0.1152 (0.1214) loss: 0.9024 (0.8996) time: 0.1556 data: 0.0805 max mem: 8233 +Train: [28] [1400/6250] eta: 0:13:37 lr: 0.000107 grad: 0.1207 (0.1215) loss: 0.8957 (0.8996) time: 0.1666 data: 0.0793 max mem: 8233 +Train: [28] [1500/6250] eta: 0:13:27 lr: 0.000107 grad: 0.1204 (0.1216) loss: 0.9020 (0.8996) time: 0.2829 data: 0.2077 max mem: 8233 +Train: [28] [1600/6250] eta: 0:13:13 lr: 0.000107 grad: 0.1163 (0.1217) loss: 0.8996 (0.8997) time: 0.1268 data: 0.0480 max mem: 8233 +Train: [28] [1700/6250] eta: 0:12:56 lr: 0.000107 grad: 0.1228 (0.1217) loss: 0.8973 (0.8998) time: 0.2393 data: 0.1779 max mem: 8233 +Train: [28] [1800/6250] eta: 0:12:35 lr: 0.000107 grad: 0.1263 (0.1219) loss: 0.8976 (0.8998) time: 0.1750 data: 0.0937 max mem: 8233 +Train: [28] [1900/6250] eta: 0:12:18 lr: 0.000107 grad: 0.1121 (0.1217) loss: 0.9018 (0.8999) time: 0.2139 data: 0.1426 max mem: 8233 +Train: [28] [2000/6250] eta: 0:12:02 lr: 0.000107 grad: 0.1138 (0.1215) loss: 0.9042 (0.9000) time: 0.1522 data: 0.0696 max mem: 8233 +Train: [28] [2100/6250] eta: 0:11:44 lr: 0.000107 grad: 0.1174 (0.1215) loss: 0.9012 (0.9001) time: 0.1841 data: 0.1164 max mem: 8233 +Train: [28] [2200/6250] eta: 0:11:25 lr: 0.000107 grad: 0.1116 (0.1215) loss: 0.9019 (0.9002) time: 0.1495 data: 0.0768 max mem: 8233 +Train: [28] [2300/6250] eta: 0:11:08 lr: 0.000107 grad: 0.1198 (0.1215) loss: 0.9017 (0.9003) time: 0.1700 data: 0.0953 max mem: 8233 +Train: [28] [2400/6250] eta: 0:10:50 lr: 0.000107 grad: 0.1241 (0.1214) loss: 0.9043 (0.9004) time: 0.1617 data: 0.0795 max mem: 8233 +Train: [28] [2500/6250] eta: 0:10:33 lr: 0.000107 grad: 0.1193 (0.1214) loss: 0.9032 (0.9005) time: 0.1903 data: 0.0903 max mem: 8233 +Train: [28] [2600/6250] eta: 0:10:15 lr: 0.000107 grad: 0.1106 (0.1217) loss: 0.9004 (0.9005) time: 0.1526 data: 0.0615 max mem: 8233 +Train: [28] [2700/6250] eta: 0:09:58 lr: 0.000107 grad: 0.1145 (0.1215) loss: 0.9008 (0.9005) time: 0.1558 data: 0.0700 max mem: 8233 +Train: [28] [2800/6250] eta: 0:09:40 lr: 0.000107 grad: 0.1220 (0.1215) loss: 0.8981 (0.9006) time: 0.1516 data: 0.0586 max mem: 8233 +Train: [28] [2900/6250] eta: 0:09:23 lr: 0.000107 grad: 0.1207 (0.1215) loss: 0.8971 (0.9006) time: 0.1932 data: 0.1110 max mem: 8233 +Train: [28] [3000/6250] eta: 0:09:05 lr: 0.000107 grad: 0.1161 (0.1213) loss: 0.8986 (0.9006) time: 0.1486 data: 0.0646 max mem: 8233 +Train: [28] [3100/6250] eta: 0:08:48 lr: 0.000107 grad: 0.1217 (0.1212) loss: 0.9028 (0.9006) time: 0.1659 data: 0.0934 max mem: 8233 +Train: [28] [3200/6250] eta: 0:08:31 lr: 0.000107 grad: 0.1142 (0.1211) loss: 0.9005 (0.9006) time: 0.1525 data: 0.0596 max mem: 8233 +Train: [28] [3300/6250] eta: 0:08:18 lr: 0.000107 grad: 0.1218 (0.1210) loss: 0.9009 (0.9007) time: 0.0974 data: 0.0002 max mem: 8233 +Train: [28] [3400/6250] eta: 0:08:00 lr: 0.000107 grad: 0.1218 (0.1209) loss: 0.9050 (0.9008) time: 0.1643 data: 0.0933 max mem: 8233 +Train: [28] [3500/6250] eta: 0:07:42 lr: 0.000107 grad: 0.1186 (0.1209) loss: 0.8976 (0.9008) time: 0.1614 data: 0.0846 max mem: 8233 +Train: [28] [3600/6250] eta: 0:07:26 lr: 0.000107 grad: 0.1139 (0.1207) loss: 0.8994 (0.9008) time: 0.1864 data: 0.1149 max mem: 8233 +Train: [28] [3700/6250] eta: 0:07:09 lr: 0.000107 grad: 0.1097 (0.1206) loss: 0.9014 (0.9008) time: 0.1926 data: 0.1255 max mem: 8233 +Train: [28] [3800/6250] eta: 0:06:53 lr: 0.000107 grad: 0.1160 (0.1206) loss: 0.8968 (0.9008) time: 0.2261 data: 0.1152 max mem: 8233 +Train: [28] [3900/6250] eta: 0:06:35 lr: 0.000107 grad: 0.1217 (0.1205) loss: 0.8937 (0.9008) time: 0.1677 data: 0.0956 max mem: 8233 +Train: [28] [4000/6250] eta: 0:06:17 lr: 0.000107 grad: 0.1144 (0.1204) loss: 0.9016 (0.9007) time: 0.1492 data: 0.0727 max mem: 8233 +Train: [28] [4100/6250] eta: 0:06:00 lr: 0.000107 grad: 0.1120 (0.1204) loss: 0.9040 (0.9007) time: 0.1729 data: 0.0994 max mem: 8233 +Train: [28] [4200/6250] eta: 0:05:43 lr: 0.000107 grad: 0.1113 (0.1203) loss: 0.8998 (0.9007) time: 0.1267 data: 0.0406 max mem: 8233 +Train: [28] [4300/6250] eta: 0:05:26 lr: 0.000107 grad: 0.1176 (0.1204) loss: 0.9019 (0.9007) time: 0.1625 data: 0.0526 max mem: 8233 +Train: [28] [4400/6250] eta: 0:05:10 lr: 0.000107 grad: 0.1063 (0.1203) loss: 0.9031 (0.9007) time: 0.1613 data: 0.0736 max mem: 8233 +Train: [28] [4500/6250] eta: 0:04:53 lr: 0.000107 grad: 0.1127 (0.1202) loss: 0.8996 (0.9007) time: 0.1778 data: 0.0966 max mem: 8233 +Train: [28] [4600/6250] eta: 0:04:36 lr: 0.000107 grad: 0.1142 (0.1202) loss: 0.9010 (0.9007) time: 0.1537 data: 0.0754 max mem: 8233 +Train: [28] [4700/6250] eta: 0:04:19 lr: 0.000107 grad: 0.1195 (0.1201) loss: 0.9043 (0.9007) time: 0.1737 data: 0.0956 max mem: 8233 +Train: [28] [4800/6250] eta: 0:04:02 lr: 0.000107 grad: 0.1172 (0.1201) loss: 0.8957 (0.9007) time: 0.1506 data: 0.0814 max mem: 8233 +Train: [28] [4900/6250] eta: 0:03:45 lr: 0.000107 grad: 0.1153 (0.1201) loss: 0.8956 (0.9007) time: 0.1290 data: 0.0451 max mem: 8233 +Train: [28] [5000/6250] eta: 0:03:28 lr: 0.000107 grad: 0.1162 (0.1201) loss: 0.9032 (0.9007) time: 0.1602 data: 0.0798 max mem: 8233 +Train: [28] [5100/6250] eta: 0:03:11 lr: 0.000107 grad: 0.1089 (0.1200) loss: 0.9024 (0.9007) time: 0.1719 data: 0.0867 max mem: 8233 +Train: [28] [5200/6250] eta: 0:02:55 lr: 0.000107 grad: 0.1132 (0.1199) loss: 0.8974 (0.9007) time: 0.1729 data: 0.0963 max mem: 8233 +Train: [28] [5300/6250] eta: 0:02:38 lr: 0.000107 grad: 0.1126 (0.1198) loss: 0.9054 (0.9007) time: 0.1547 data: 0.0790 max mem: 8233 +Train: [28] [5400/6250] eta: 0:02:21 lr: 0.000107 grad: 0.1082 (0.1198) loss: 0.8977 (0.9007) time: 0.1541 data: 0.0664 max mem: 8233 +Train: [28] [5500/6250] eta: 0:02:04 lr: 0.000107 grad: 0.1150 (0.1197) loss: 0.9026 (0.9007) time: 0.1397 data: 0.0587 max mem: 8233 +Train: [28] [5600/6250] eta: 0:01:47 lr: 0.000106 grad: 0.1187 (0.1197) loss: 0.8998 (0.9006) time: 0.1782 data: 0.1032 max mem: 8233 +Train: [28] [5700/6250] eta: 0:01:31 lr: 0.000106 grad: 0.1150 (0.1197) loss: 0.9019 (0.9006) time: 0.1960 data: 0.1029 max mem: 8233 +Train: [28] [5800/6250] eta: 0:01:14 lr: 0.000106 grad: 0.1136 (0.1198) loss: 0.8970 (0.9006) time: 0.1121 data: 0.0204 max mem: 8233 +Train: [28] [5900/6250] eta: 0:00:57 lr: 0.000106 grad: 0.1242 (0.1197) loss: 0.8961 (0.9005) time: 0.1322 data: 0.0435 max mem: 8233 +Train: [28] [6000/6250] eta: 0:00:41 lr: 0.000106 grad: 0.1144 (0.1198) loss: 0.9000 (0.9005) time: 0.1554 data: 0.0747 max mem: 8233 +Train: [28] [6100/6250] eta: 0:00:24 lr: 0.000106 grad: 0.1157 (0.1198) loss: 0.9020 (0.9005) time: 0.1689 data: 0.0856 max mem: 8233 +Train: [28] [6200/6250] eta: 0:00:08 lr: 0.000106 grad: 0.1218 (0.1199) loss: 0.8978 (0.9005) time: 0.1679 data: 0.0906 max mem: 8233 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.1171 (0.1199) loss: 0.9002 (0.9005) time: 0.1416 data: 0.0599 max mem: 8233 +Train: [28] Total time: 0:17:17 (0.1660 s / it) +Averaged stats: lr: 0.000106 grad: 0.1171 (0.1199) loss: 0.9002 (0.9005) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:04:05 loss: 0.9145 (0.9145) time: 3.9601 data: 3.8904 max mem: 8233 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.9065 (0.9059) time: 0.1380 data: 0.1175 max mem: 8233 +Eval (hcp-train-subset): [28] Total time: 0:00:14 (0.2260 s / it) +Averaged stats (hcp-train-subset): loss: 0.9065 (0.9059) +Eval (hcp-val): [28] [ 0/62] eta: 0:03:31 loss: 0.8982 (0.8982) time: 3.4154 data: 3.3245 max mem: 8233 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.9018 (0.9019) time: 0.1508 data: 0.1299 max mem: 8233 +Eval (hcp-val): [28] Total time: 0:00:14 (0.2330 s / it) +Averaged stats (hcp-val): loss: 0.9018 (0.9019) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 8:58:04 lr: 0.000106 grad: 0.0866 (0.0866) loss: 0.9275 (0.9275) time: 5.1655 data: 4.9498 max mem: 8233 +Train: [29] [ 100/6250] eta: 0:22:30 lr: 0.000106 grad: 0.1043 (0.1102) loss: 0.9024 (0.9077) time: 0.1676 data: 0.0714 max mem: 8233 +Train: [29] [ 200/6250] eta: 0:19:55 lr: 0.000106 grad: 0.1188 (0.1126) loss: 0.8965 (0.9031) time: 0.1577 data: 0.0761 max mem: 8233 +Train: [29] [ 300/6250] eta: 0:18:41 lr: 0.000106 grad: 0.1163 (0.1159) loss: 0.8946 (0.9005) time: 0.1688 data: 0.0930 max mem: 8233 +Train: [29] [ 400/6250] eta: 0:18:15 lr: 0.000106 grad: 0.1210 (0.1189) loss: 0.8899 (0.8986) time: 0.1923 data: 0.1130 max mem: 8233 +Train: [29] [ 500/6250] eta: 0:17:41 lr: 0.000106 grad: 0.1202 (0.1205) loss: 0.8912 (0.8975) time: 0.1874 data: 0.1021 max mem: 8233 +Train: [29] [ 600/6250] eta: 0:17:09 lr: 0.000106 grad: 0.1174 (0.1203) loss: 0.8999 (0.8972) time: 0.1702 data: 0.0791 max mem: 8233 +Train: [29] [ 700/6250] eta: 0:16:39 lr: 0.000106 grad: 0.1155 (0.1202) loss: 0.9016 (0.8974) time: 0.1736 data: 0.0768 max mem: 8233 +Train: [29] [ 800/6250] eta: 0:16:19 lr: 0.000106 grad: 0.1193 (0.1205) loss: 0.8925 (0.8972) time: 0.1822 data: 0.0968 max mem: 8233 +Train: [29] [ 900/6250] eta: 0:15:55 lr: 0.000106 grad: 0.1110 (0.1202) loss: 0.9003 (0.8974) time: 0.1949 data: 0.1014 max mem: 8233 +Train: [29] [1000/6250] eta: 0:15:30 lr: 0.000106 grad: 0.1159 (0.1203) loss: 0.8948 (0.8974) time: 0.1832 data: 0.1009 max mem: 8233 +Train: [29] [1100/6250] eta: 0:15:05 lr: 0.000106 grad: 0.1162 (0.1207) loss: 0.8976 (0.8974) time: 0.1835 data: 0.1042 max mem: 8233 +Train: [29] [1200/6250] eta: 0:14:41 lr: 0.000106 grad: 0.1225 (0.1210) loss: 0.8971 (0.8972) time: 0.1567 data: 0.0783 max mem: 8233 +Train: [29] [1300/6250] eta: 0:14:24 lr: 0.000106 grad: 0.1241 (0.1209) loss: 0.8968 (0.8971) time: 0.1588 data: 0.0869 max mem: 8233 +Train: [29] [1400/6250] eta: 0:14:10 lr: 0.000106 grad: 0.1200 (0.1211) loss: 0.8971 (0.8971) time: 0.1686 data: 0.0997 max mem: 8233 +Train: [29] [1500/6250] eta: 0:13:53 lr: 0.000106 grad: 0.1144 (0.1211) loss: 0.9016 (0.8972) time: 0.1657 data: 0.0875 max mem: 8233 +Train: [29] [1600/6250] eta: 0:13:36 lr: 0.000106 grad: 0.1127 (0.1215) loss: 0.8986 (0.8971) time: 0.1722 data: 0.0942 max mem: 8233 +Train: [29] [1700/6250] eta: 0:13:15 lr: 0.000106 grad: 0.1202 (0.1217) loss: 0.8993 (0.8972) time: 0.1461 data: 0.0686 max mem: 8233 +Train: [29] [1800/6250] eta: 0:12:56 lr: 0.000106 grad: 0.1230 (0.1219) loss: 0.8990 (0.8971) time: 0.1716 data: 0.0922 max mem: 8233 +Train: [29] [1900/6250] eta: 0:12:43 lr: 0.000106 grad: 0.1229 (0.1224) loss: 0.8946 (0.8970) time: 0.3614 data: 0.2193 max mem: 8233 +Train: [29] [2000/6250] eta: 0:12:21 lr: 0.000106 grad: 0.1143 (0.1227) loss: 0.8927 (0.8969) time: 0.1976 data: 0.1171 max mem: 8233 +Train: [29] [2100/6250] eta: 0:12:02 lr: 0.000106 grad: 0.1183 (0.1229) loss: 0.8939 (0.8968) time: 0.1257 data: 0.0366 max mem: 8233 +Train: [29] [2200/6250] eta: 0:11:45 lr: 0.000106 grad: 0.1264 (0.1232) loss: 0.8950 (0.8967) time: 0.1654 data: 0.0902 max mem: 8233 +Train: [29] [2300/6250] eta: 0:11:28 lr: 0.000106 grad: 0.1159 (0.1232) loss: 0.8948 (0.8966) time: 0.1737 data: 0.0898 max mem: 8233 +Train: [29] [2400/6250] eta: 0:11:09 lr: 0.000106 grad: 0.1217 (0.1232) loss: 0.8916 (0.8965) time: 0.1487 data: 0.0727 max mem: 8233 +Train: [29] [2500/6250] eta: 0:10:52 lr: 0.000106 grad: 0.1141 (0.1232) loss: 0.8895 (0.8965) time: 0.1506 data: 0.0727 max mem: 8233 +Train: [29] [2600/6250] eta: 0:10:35 lr: 0.000106 grad: 0.1194 (0.1232) loss: 0.8942 (0.8964) time: 0.1796 data: 0.1059 max mem: 8233 +Train: [29] [2700/6250] eta: 0:10:16 lr: 0.000106 grad: 0.1266 (0.1233) loss: 0.8939 (0.8963) time: 0.1512 data: 0.0691 max mem: 8233 +Train: [29] [2800/6250] eta: 0:09:57 lr: 0.000106 grad: 0.1129 (0.1233) loss: 0.8938 (0.8962) time: 0.1456 data: 0.0753 max mem: 8233 +Train: [29] [2900/6250] eta: 0:09:38 lr: 0.000106 grad: 0.1210 (0.1232) loss: 0.8944 (0.8963) time: 0.1580 data: 0.0616 max mem: 8233 +Train: [29] [3000/6250] eta: 0:09:19 lr: 0.000106 grad: 0.1101 (0.1231) loss: 0.8964 (0.8963) time: 0.1428 data: 0.0488 max mem: 8233 +Train: [29] [3100/6250] eta: 0:09:02 lr: 0.000106 grad: 0.1136 (0.1230) loss: 0.8979 (0.8963) time: 0.1346 data: 0.0414 max mem: 8233 +Train: [29] [3200/6250] eta: 0:08:44 lr: 0.000106 grad: 0.1178 (0.1230) loss: 0.8989 (0.8963) time: 0.1390 data: 0.0615 max mem: 8233 +Train: [29] [3300/6250] eta: 0:08:28 lr: 0.000106 grad: 0.1140 (0.1230) loss: 0.8941 (0.8963) time: 0.1236 data: 0.0327 max mem: 8233 +Train: [29] [3400/6250] eta: 0:08:10 lr: 0.000106 grad: 0.1167 (0.1229) loss: 0.8981 (0.8963) time: 0.1947 data: 0.1200 max mem: 8233 +Train: [29] [3500/6250] eta: 0:07:53 lr: 0.000105 grad: 0.1160 (0.1228) loss: 0.9022 (0.8963) time: 0.1523 data: 0.0800 max mem: 8233 +Train: [29] [3600/6250] eta: 0:07:35 lr: 0.000105 grad: 0.1241 (0.1227) loss: 0.8976 (0.8963) time: 0.1535 data: 0.0866 max mem: 8233 +Train: [29] [3700/6250] eta: 0:07:18 lr: 0.000105 grad: 0.1089 (0.1226) loss: 0.8996 (0.8964) time: 0.1897 data: 0.1073 max mem: 8233 +Train: [29] [3800/6250] eta: 0:07:00 lr: 0.000105 grad: 0.1159 (0.1225) loss: 0.9003 (0.8964) time: 0.1556 data: 0.0885 max mem: 8233 +Train: [29] [3900/6250] eta: 0:06:43 lr: 0.000105 grad: 0.1192 (0.1224) loss: 0.8970 (0.8965) time: 0.1584 data: 0.0692 max mem: 8233 +Train: [29] [4000/6250] eta: 0:06:25 lr: 0.000105 grad: 0.1139 (0.1223) loss: 0.8965 (0.8965) time: 0.1575 data: 0.0814 max mem: 8233 +Train: [29] [4100/6250] eta: 0:06:07 lr: 0.000105 grad: 0.1159 (0.1223) loss: 0.9001 (0.8966) time: 0.1601 data: 0.0719 max mem: 8233 +Train: [29] [4200/6250] eta: 0:05:49 lr: 0.000105 grad: 0.1142 (0.1222) loss: 0.8940 (0.8966) time: 0.1438 data: 0.0515 max mem: 8233 +Train: [29] [4300/6250] eta: 0:05:32 lr: 0.000105 grad: 0.1242 (0.1222) loss: 0.8985 (0.8966) time: 0.1587 data: 0.0822 max mem: 8233 +Train: [29] [4400/6250] eta: 0:05:14 lr: 0.000105 grad: 0.1154 (0.1222) loss: 0.9004 (0.8966) time: 0.1724 data: 0.0880 max mem: 8233 +Train: [29] [4500/6250] eta: 0:04:57 lr: 0.000105 grad: 0.1266 (0.1223) loss: 0.8989 (0.8967) time: 0.1569 data: 0.0714 max mem: 8233 +Train: [29] [4600/6250] eta: 0:04:41 lr: 0.000105 grad: 0.1178 (0.1224) loss: 0.9029 (0.8967) time: 0.1641 data: 0.0473 max mem: 8233 +Train: [29] [4700/6250] eta: 0:04:23 lr: 0.000105 grad: 0.1206 (0.1224) loss: 0.8948 (0.8967) time: 0.1684 data: 0.0922 max mem: 8233 +Train: [29] [4800/6250] eta: 0:04:06 lr: 0.000105 grad: 0.1124 (0.1224) loss: 0.9000 (0.8968) time: 0.1536 data: 0.0689 max mem: 8233 +Train: [29] [4900/6250] eta: 0:03:49 lr: 0.000105 grad: 0.1192 (0.1224) loss: 0.8984 (0.8968) time: 0.1704 data: 0.0885 max mem: 8233 +Train: [29] [5000/6250] eta: 0:03:32 lr: 0.000105 grad: 0.1179 (0.1223) loss: 0.9034 (0.8968) time: 0.1607 data: 0.0849 max mem: 8233 +Train: [29] [5100/6250] eta: 0:03:15 lr: 0.000105 grad: 0.1181 (0.1222) loss: 0.8971 (0.8969) time: 0.1531 data: 0.0682 max mem: 8233 +Train: [29] [5200/6250] eta: 0:02:57 lr: 0.000105 grad: 0.1180 (0.1222) loss: 0.8987 (0.8969) time: 0.1664 data: 0.0889 max mem: 8233 +Train: [29] [5300/6250] eta: 0:02:40 lr: 0.000105 grad: 0.1192 (0.1222) loss: 0.8977 (0.8969) time: 0.1503 data: 0.0830 max mem: 8233 +Train: [29] [5400/6250] eta: 0:02:23 lr: 0.000105 grad: 0.1120 (0.1223) loss: 0.8977 (0.8969) time: 0.1759 data: 0.0937 max mem: 8233 +Train: [29] [5500/6250] eta: 0:02:06 lr: 0.000105 grad: 0.1145 (0.1222) loss: 0.8988 (0.8970) time: 0.2158 data: 0.1318 max mem: 8233 +Train: [29] [5600/6250] eta: 0:01:49 lr: 0.000105 grad: 0.1183 (0.1222) loss: 0.8991 (0.8970) time: 0.1354 data: 0.0496 max mem: 8233 +Train: [29] [5700/6250] eta: 0:01:32 lr: 0.000105 grad: 0.1180 (0.1222) loss: 0.8965 (0.8970) time: 0.1357 data: 0.0566 max mem: 8233 +Train: [29] [5800/6250] eta: 0:01:15 lr: 0.000105 grad: 0.1224 (0.1222) loss: 0.8944 (0.8970) time: 0.1783 data: 0.0948 max mem: 8233 +Train: [29] [5900/6250] eta: 0:00:59 lr: 0.000105 grad: 0.1157 (0.1221) loss: 0.8955 (0.8970) time: 0.2166 data: 0.1480 max mem: 8233 +Train: [29] [6000/6250] eta: 0:00:42 lr: 0.000105 grad: 0.1129 (0.1220) loss: 0.8966 (0.8971) time: 0.1493 data: 0.0662 max mem: 8233 +Train: [29] [6100/6250] eta: 0:00:25 lr: 0.000105 grad: 0.1114 (0.1219) loss: 0.9051 (0.8971) time: 0.1293 data: 0.0273 max mem: 8233 +Train: [29] [6200/6250] eta: 0:00:08 lr: 0.000105 grad: 0.1152 (0.1218) loss: 0.9048 (0.8972) time: 0.1684 data: 0.0642 max mem: 8233 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.1033 (0.1217) loss: 0.9033 (0.8972) time: 0.1631 data: 0.0554 max mem: 8233 +Train: [29] Total time: 0:17:44 (0.1703 s / it) +Averaged stats: lr: 0.000105 grad: 0.1033 (0.1217) loss: 0.9033 (0.8972) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:06:37 loss: 0.9151 (0.9151) time: 6.4108 data: 6.3787 max mem: 8233 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.9057 (0.9052) time: 0.1501 data: 0.1294 max mem: 8233 +Eval (hcp-train-subset): [29] Total time: 0:00:14 (0.2363 s / it) +Averaged stats (hcp-train-subset): loss: 0.9057 (0.9052) +Making plots (hcp-train-subset): example=10 +Eval (hcp-val): [29] [ 0/62] eta: 0:05:09 loss: 0.9008 (0.9008) time: 4.9880 data: 4.9611 max mem: 8233 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8994 (0.9012) time: 0.1434 data: 0.1213 max mem: 8233 +Eval (hcp-val): [29] Total time: 0:00:14 (0.2287 s / it) +Averaged stats (hcp-val): loss: 0.8994 (0.9012) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 10:58:17 lr: 0.000105 grad: 0.2006 (0.2006) loss: 0.8574 (0.8574) time: 6.3195 data: 6.1548 max mem: 8233 +Train: [30] [ 100/6250] eta: 0:22:26 lr: 0.000105 grad: 0.1002 (0.1071) loss: 0.9081 (0.9080) time: 0.1851 data: 0.0887 max mem: 8233 +Train: [30] [ 200/6250] eta: 0:19:58 lr: 0.000105 grad: 0.1135 (0.1101) loss: 0.9035 (0.9049) time: 0.1609 data: 0.0714 max mem: 8233 +Train: [30] [ 300/6250] eta: 0:18:51 lr: 0.000105 grad: 0.1108 (0.1116) loss: 0.9026 (0.9040) time: 0.1672 data: 0.0733 max mem: 8233 +Train: [30] [ 400/6250] eta: 0:17:44 lr: 0.000105 grad: 0.1099 (0.1123) loss: 0.8998 (0.9026) time: 0.1420 data: 0.0500 max mem: 8233 +Train: [30] [ 500/6250] eta: 0:17:08 lr: 0.000105 grad: 0.1123 (0.1130) loss: 0.9005 (0.9016) time: 0.1859 data: 0.1069 max mem: 8233 +Train: [30] [ 600/6250] eta: 0:16:40 lr: 0.000105 grad: 0.1131 (0.1133) loss: 0.8977 (0.9014) time: 0.1595 data: 0.0779 max mem: 8233 +Train: [30] [ 700/6250] eta: 0:16:12 lr: 0.000105 grad: 0.1035 (0.1133) loss: 0.9060 (0.9012) time: 0.1363 data: 0.0608 max mem: 8233 +Train: [30] [ 800/6250] eta: 0:15:45 lr: 0.000105 grad: 0.1043 (0.1131) loss: 0.9052 (0.9015) time: 0.1535 data: 0.0668 max mem: 8233 +Train: [30] [ 900/6250] eta: 0:15:20 lr: 0.000105 grad: 0.1091 (0.1132) loss: 0.9025 (0.9015) time: 0.1522 data: 0.0776 max mem: 8233 +Train: [30] [1000/6250] eta: 0:14:56 lr: 0.000105 grad: 0.1119 (0.1130) loss: 0.8993 (0.9014) time: 0.1714 data: 0.0829 max mem: 8233 +Train: [30] [1100/6250] eta: 0:14:30 lr: 0.000105 grad: 0.1161 (0.1133) loss: 0.9015 (0.9015) time: 0.1512 data: 0.0619 max mem: 8233 +Train: [30] [1200/6250] eta: 0:14:04 lr: 0.000105 grad: 0.1129 (0.1135) loss: 0.8995 (0.9015) time: 0.1400 data: 0.0552 max mem: 8233 +Train: [30] [1300/6250] eta: 0:13:40 lr: 0.000105 grad: 0.1085 (0.1134) loss: 0.9073 (0.9015) time: 0.1270 data: 0.0375 max mem: 8233 +Train: [30] [1400/6250] eta: 0:13:16 lr: 0.000104 grad: 0.1117 (0.1135) loss: 0.8969 (0.9015) time: 0.1381 data: 0.0430 max mem: 8233 +Train: [30] [1500/6250] eta: 0:12:56 lr: 0.000104 grad: 0.1079 (0.1134) loss: 0.9004 (0.9015) time: 0.1565 data: 0.0792 max mem: 8233 +Train: [30] [1600/6250] eta: 0:12:40 lr: 0.000104 grad: 0.1114 (0.1135) loss: 0.9060 (0.9015) time: 0.1760 data: 0.0923 max mem: 8233 +Train: [30] [1700/6250] eta: 0:12:26 lr: 0.000104 grad: 0.1034 (0.1133) loss: 0.9049 (0.9015) time: 0.1920 data: 0.1091 max mem: 8233 +Train: [30] [1800/6250] eta: 0:12:08 lr: 0.000104 grad: 0.1051 (0.1133) loss: 0.9019 (0.9014) time: 0.1510 data: 0.0766 max mem: 8233 +Train: [30] [1900/6250] eta: 0:11:52 lr: 0.000104 grad: 0.1087 (0.1133) loss: 0.9003 (0.9014) time: 0.1614 data: 0.0724 max mem: 8233 +Train: [30] [2000/6250] eta: 0:11:35 lr: 0.000104 grad: 0.1099 (0.1133) loss: 0.8999 (0.9013) time: 0.1617 data: 0.0793 max mem: 8233 +Train: [30] [2100/6250] eta: 0:11:23 lr: 0.000104 grad: 0.1067 (0.1133) loss: 0.8997 (0.9012) time: 0.2663 data: 0.1833 max mem: 8233 +Train: [30] [2200/6250] eta: 0:11:06 lr: 0.000104 grad: 0.1122 (0.1134) loss: 0.8976 (0.9011) time: 0.2003 data: 0.1316 max mem: 8233 +Train: [30] [2300/6250] eta: 0:10:51 lr: 0.000104 grad: 0.1087 (0.1135) loss: 0.9023 (0.9010) time: 0.1942 data: 0.1131 max mem: 8233 +Train: [30] [2400/6250] eta: 0:10:32 lr: 0.000104 grad: 0.1072 (0.1136) loss: 0.9028 (0.9010) time: 0.1472 data: 0.0756 max mem: 8233 +Train: [30] [2500/6250] eta: 0:10:17 lr: 0.000104 grad: 0.1098 (0.1138) loss: 0.9024 (0.9010) time: 0.1879 data: 0.1205 max mem: 8233 +Train: [30] [2600/6250] eta: 0:09:59 lr: 0.000104 grad: 0.1086 (0.1139) loss: 0.9038 (0.9010) time: 0.1720 data: 0.0919 max mem: 8233 +Train: [30] [2700/6250] eta: 0:09:44 lr: 0.000104 grad: 0.1185 (0.1141) loss: 0.8966 (0.9009) time: 0.1736 data: 0.0962 max mem: 8233 +Train: [30] [2800/6250] eta: 0:09:29 lr: 0.000104 grad: 0.1155 (0.1144) loss: 0.8958 (0.9008) time: 0.1885 data: 0.1022 max mem: 8233 +Train: [30] [2900/6250] eta: 0:09:14 lr: 0.000104 grad: 0.1154 (0.1144) loss: 0.8982 (0.9007) time: 0.1715 data: 0.0896 max mem: 8233 +Train: [30] [3000/6250] eta: 0:08:58 lr: 0.000104 grad: 0.1077 (0.1145) loss: 0.9013 (0.9006) time: 0.1673 data: 0.0949 max mem: 8233 +Train: [30] [3100/6250] eta: 0:08:41 lr: 0.000104 grad: 0.1091 (0.1145) loss: 0.9004 (0.9005) time: 0.1890 data: 0.1152 max mem: 8233 +Train: [30] [3200/6250] eta: 0:08:24 lr: 0.000104 grad: 0.1139 (0.1145) loss: 0.8967 (0.9004) time: 0.1468 data: 0.0619 max mem: 8233 +Train: [30] [3300/6250] eta: 0:08:07 lr: 0.000104 grad: 0.1093 (0.1145) loss: 0.8968 (0.9003) time: 0.1034 data: 0.0003 max mem: 8233 +Train: [30] [3400/6250] eta: 0:07:51 lr: 0.000104 grad: 0.1166 (0.1146) loss: 0.8968 (0.9002) time: 0.1352 data: 0.0402 max mem: 8233 +Train: [30] [3500/6250] eta: 0:07:34 lr: 0.000104 grad: 0.1160 (0.1147) loss: 0.8932 (0.9002) time: 0.1558 data: 0.0846 max mem: 8233 +Train: [30] [3600/6250] eta: 0:07:18 lr: 0.000104 grad: 0.1146 (0.1147) loss: 0.8998 (0.9001) time: 0.1732 data: 0.1001 max mem: 8233 +Train: [30] [3700/6250] eta: 0:07:01 lr: 0.000104 grad: 0.1067 (0.1147) loss: 0.8979 (0.9001) time: 0.1691 data: 0.0903 max mem: 8233 +Train: [30] [3800/6250] eta: 0:06:44 lr: 0.000104 grad: 0.1182 (0.1147) loss: 0.8990 (0.9000) time: 0.1632 data: 0.0890 max mem: 8233 +Train: [30] [3900/6250] eta: 0:06:28 lr: 0.000104 grad: 0.1078 (0.1146) loss: 0.8961 (0.8999) time: 0.1695 data: 0.0872 max mem: 8233 +Train: [30] [4000/6250] eta: 0:06:11 lr: 0.000104 grad: 0.1138 (0.1146) loss: 0.8988 (0.8999) time: 0.1813 data: 0.0990 max mem: 8233 +Train: [30] [4100/6250] eta: 0:05:55 lr: 0.000104 grad: 0.1049 (0.1146) loss: 0.8950 (0.8999) time: 0.1613 data: 0.0749 max mem: 8233 +Train: [30] [4200/6250] eta: 0:05:38 lr: 0.000104 grad: 0.1158 (0.1147) loss: 0.9000 (0.8998) time: 0.1775 data: 0.1040 max mem: 8233 +Train: [30] [4300/6250] eta: 0:05:21 lr: 0.000104 grad: 0.1099 (0.1147) loss: 0.9010 (0.8997) time: 0.1478 data: 0.0453 max mem: 8233 +Train: [30] [4400/6250] eta: 0:05:04 lr: 0.000104 grad: 0.1182 (0.1149) loss: 0.8972 (0.8997) time: 0.1394 data: 0.0439 max mem: 8233 +Train: [30] [4500/6250] eta: 0:04:47 lr: 0.000104 grad: 0.1087 (0.1149) loss: 0.9014 (0.8996) time: 0.1555 data: 0.0796 max mem: 8233 +Train: [30] [4600/6250] eta: 0:04:30 lr: 0.000104 grad: 0.1096 (0.1148) loss: 0.8943 (0.8996) time: 0.1389 data: 0.0511 max mem: 8233 +Train: [30] [4700/6250] eta: 0:04:13 lr: 0.000104 grad: 0.1110 (0.1148) loss: 0.8943 (0.8995) time: 0.1542 data: 0.0755 max mem: 8233 +Train: [30] [4800/6250] eta: 0:03:57 lr: 0.000104 grad: 0.1090 (0.1149) loss: 0.8963 (0.8995) time: 0.1532 data: 0.0638 max mem: 8233 +Train: [30] [4900/6250] eta: 0:03:40 lr: 0.000104 grad: 0.1096 (0.1149) loss: 0.8979 (0.8994) time: 0.1352 data: 0.0587 max mem: 8233 +Train: [30] [5000/6250] eta: 0:03:23 lr: 0.000104 grad: 0.1106 (0.1148) loss: 0.8955 (0.8994) time: 0.1604 data: 0.0720 max mem: 8233 +Train: [30] [5100/6250] eta: 0:03:07 lr: 0.000104 grad: 0.1117 (0.1147) loss: 0.9003 (0.8994) time: 0.1875 data: 0.1123 max mem: 8233 +Train: [30] [5200/6250] eta: 0:02:51 lr: 0.000104 grad: 0.1028 (0.1146) loss: 0.9018 (0.8994) time: 0.2497 data: 0.1698 max mem: 8233 +Train: [30] [5300/6250] eta: 0:02:35 lr: 0.000104 grad: 0.1088 (0.1146) loss: 0.8981 (0.8994) time: 0.1625 data: 0.0790 max mem: 8233 +Train: [30] [5400/6250] eta: 0:02:19 lr: 0.000103 grad: 0.1186 (0.1146) loss: 0.9039 (0.8994) time: 0.1649 data: 0.0859 max mem: 8233 +Train: [30] [5500/6250] eta: 0:02:02 lr: 0.000103 grad: 0.1178 (0.1146) loss: 0.8939 (0.8993) time: 0.2074 data: 0.1415 max mem: 8233 +Train: [30] [5600/6250] eta: 0:01:46 lr: 0.000103 grad: 0.1078 (0.1147) loss: 0.8977 (0.8993) time: 0.1603 data: 0.0784 max mem: 8233 +Train: [30] [5700/6250] eta: 0:01:30 lr: 0.000103 grad: 0.1162 (0.1147) loss: 0.8963 (0.8992) time: 0.1540 data: 0.0764 max mem: 8233 +Train: [30] [5800/6250] eta: 0:01:13 lr: 0.000103 grad: 0.1102 (0.1147) loss: 0.9016 (0.8992) time: 0.1777 data: 0.0972 max mem: 8233 +Train: [30] [5900/6250] eta: 0:00:57 lr: 0.000103 grad: 0.1245 (0.1148) loss: 0.8922 (0.8992) time: 0.1604 data: 0.0755 max mem: 8233 +Train: [30] [6000/6250] eta: 0:00:40 lr: 0.000103 grad: 0.1078 (0.1149) loss: 0.9016 (0.8991) time: 0.1650 data: 0.0857 max mem: 8233 +Train: [30] [6100/6250] eta: 0:00:24 lr: 0.000103 grad: 0.1112 (0.1149) loss: 0.9009 (0.8991) time: 0.3154 data: 0.2017 max mem: 8233 +Train: [30] [6200/6250] eta: 0:00:08 lr: 0.000103 grad: 0.1156 (0.1149) loss: 0.8974 (0.8991) time: 0.1598 data: 0.0847 max mem: 8233 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.1131 (0.1150) loss: 0.8942 (0.8991) time: 0.1526 data: 0.0781 max mem: 8233 +Train: [30] Total time: 0:17:11 (0.1650 s / it) +Averaged stats: lr: 0.000103 grad: 0.1131 (0.1150) loss: 0.8942 (0.8991) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:05:00 loss: 0.9119 (0.9119) time: 4.8426 data: 4.8064 max mem: 8233 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.9060 (0.9050) time: 0.1431 data: 0.1213 max mem: 8233 +Eval (hcp-train-subset): [30] Total time: 0:00:14 (0.2267 s / it) +Averaged stats (hcp-train-subset): loss: 0.9060 (0.9050) +Eval (hcp-val): [30] [ 0/62] eta: 0:03:41 loss: 0.8967 (0.8967) time: 3.5663 data: 3.4898 max mem: 8233 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8999 (0.9007) time: 0.1160 data: 0.0955 max mem: 8233 +Eval (hcp-val): [30] Total time: 0:00:14 (0.2313 s / it) +Averaged stats (hcp-val): loss: 0.8999 (0.9007) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 8:37:36 lr: 0.000103 grad: nan (nan) loss: 0.8398 (0.8398) time: 4.9690 data: 4.8443 max mem: 8233 +Train: [31] [ 100/6250] eta: 0:23:29 lr: 0.000103 grad: 0.1167 (0.1293) loss: 0.8975 (0.8940) time: 0.2062 data: 0.1072 max mem: 8233 +Train: [31] [ 200/6250] eta: 0:19:49 lr: 0.000103 grad: 0.1122 (0.1275) loss: 0.8892 (0.8926) time: 0.1580 data: 0.0686 max mem: 8233 +Train: [31] [ 300/6250] eta: 0:18:20 lr: 0.000103 grad: 0.1162 (0.1247) loss: 0.8991 (0.8924) time: 0.1319 data: 0.0449 max mem: 8233 +Train: [31] [ 400/6250] eta: 0:17:29 lr: 0.000103 grad: 0.1114 (0.1230) loss: 0.8952 (0.8928) time: 0.1621 data: 0.0781 max mem: 8233 +Train: [31] [ 500/6250] eta: 0:16:38 lr: 0.000103 grad: 0.1176 (0.1214) loss: 0.8998 (0.8939) time: 0.1509 data: 0.0537 max mem: 8233 +Train: [31] [ 600/6250] eta: 0:16:19 lr: 0.000103 grad: 0.1219 (0.1210) loss: 0.8976 (0.8945) time: 0.1874 data: 0.1008 max mem: 8233 +Train: [31] [ 700/6250] eta: 0:15:50 lr: 0.000103 grad: 0.1137 (0.1203) loss: 0.8987 (0.8948) time: 0.1609 data: 0.0762 max mem: 8233 +Train: [31] [ 800/6250] eta: 0:15:22 lr: 0.000103 grad: 0.1135 (0.1201) loss: 0.8983 (0.8951) time: 0.1602 data: 0.0742 max mem: 8233 +Train: [31] [ 900/6250] eta: 0:15:05 lr: 0.000103 grad: 0.1142 (0.1194) loss: 0.9001 (0.8954) time: 0.1939 data: 0.0970 max mem: 8233 +Train: [31] [1000/6250] eta: 0:14:43 lr: 0.000103 grad: 0.1080 (0.1187) loss: 0.9005 (0.8957) time: 0.1339 data: 0.0430 max mem: 8233 +Train: [31] [1100/6250] eta: 0:14:19 lr: 0.000103 grad: 0.1112 (0.1183) loss: 0.8972 (0.8960) time: 0.1724 data: 0.0895 max mem: 8233 +Train: [31] [1200/6250] eta: 0:13:59 lr: 0.000103 grad: 0.1192 (0.1183) loss: 0.8983 (0.8961) time: 0.1675 data: 0.0888 max mem: 8233 +Train: [31] [1300/6250] eta: 0:13:44 lr: 0.000103 grad: 0.1148 (0.1179) loss: 0.8934 (0.8962) time: 0.1831 data: 0.1068 max mem: 8233 +Train: [31] [1400/6250] eta: 0:13:33 lr: 0.000103 grad: 0.1147 (0.1178) loss: 0.8994 (0.8962) time: 0.2453 data: 0.1619 max mem: 8233 +Train: [31] [1500/6250] eta: 0:13:13 lr: 0.000103 grad: 0.1196 (0.1177) loss: 0.8989 (0.8963) time: 0.1893 data: 0.1160 max mem: 8233 +Train: [31] [1600/6250] eta: 0:12:55 lr: 0.000103 grad: 0.1128 (0.1176) loss: 0.8977 (0.8963) time: 0.1779 data: 0.0919 max mem: 8233 +Train: [31] [1700/6250] eta: 0:12:43 lr: 0.000103 grad: 0.1085 (0.1175) loss: 0.8970 (0.8964) time: 0.1283 data: 0.0157 max mem: 8233 +Train: [31] [1800/6250] eta: 0:12:33 lr: 0.000103 grad: 0.1131 (0.1174) loss: 0.8989 (0.8965) time: 0.2936 data: 0.2149 max mem: 8233 +Train: [31] [1900/6250] eta: 0:12:18 lr: 0.000103 grad: 0.1061 (0.1172) loss: 0.8985 (0.8965) time: 0.3238 data: 0.2191 max mem: 8233 +Train: [31] [2000/6250] eta: 0:11:54 lr: 0.000103 grad: 0.1177 (0.1172) loss: 0.8995 (0.8966) time: 0.1599 data: 0.0772 max mem: 8233 +Train: [31] [2100/6250] eta: 0:11:39 lr: 0.000103 grad: 0.1107 (0.1173) loss: 0.8969 (0.8966) time: 0.1578 data: 0.0839 max mem: 8233 +Train: [31] [2200/6250] eta: 0:11:21 lr: 0.000103 grad: 0.1229 (0.1171) loss: 0.8962 (0.8967) time: 0.1647 data: 0.0808 max mem: 8233 +Train: [31] [2300/6250] eta: 0:11:03 lr: 0.000103 grad: 0.1095 (0.1171) loss: 0.8944 (0.8967) time: 0.1597 data: 0.0856 max mem: 8233 +Train: [31] [2400/6250] eta: 0:10:46 lr: 0.000103 grad: 0.1117 (0.1170) loss: 0.8974 (0.8967) time: 0.1537 data: 0.0841 max mem: 8233 +Train: [31] [2500/6250] eta: 0:10:28 lr: 0.000103 grad: 0.1177 (0.1170) loss: 0.8951 (0.8967) time: 0.1425 data: 0.0625 max mem: 8233 +Train: [31] [2600/6250] eta: 0:10:09 lr: 0.000103 grad: 0.1055 (0.1170) loss: 0.8968 (0.8967) time: 0.1529 data: 0.0806 max mem: 8233 +Train: [31] [2700/6250] eta: 0:09:52 lr: 0.000103 grad: 0.1157 (0.1170) loss: 0.8952 (0.8967) time: 0.1657 data: 0.0860 max mem: 8233 +Train: [31] [2800/6250] eta: 0:09:37 lr: 0.000103 grad: 0.1166 (0.1170) loss: 0.8944 (0.8967) time: 0.1841 data: 0.1037 max mem: 8233 +Train: [31] [2900/6250] eta: 0:09:19 lr: 0.000103 grad: 0.1090 (0.1170) loss: 0.8955 (0.8968) time: 0.1474 data: 0.0662 max mem: 8233 +Train: [31] [3000/6250] eta: 0:09:01 lr: 0.000103 grad: 0.1229 (0.1171) loss: 0.8967 (0.8967) time: 0.1599 data: 0.0727 max mem: 8233 +Train: [31] [3100/6250] eta: 0:08:43 lr: 0.000103 grad: 0.1088 (0.1170) loss: 0.8933 (0.8967) time: 0.1527 data: 0.0622 max mem: 8233 +Train: [31] [3200/6250] eta: 0:08:26 lr: 0.000102 grad: 0.1237 (0.1172) loss: 0.8955 (0.8967) time: 0.1812 data: 0.1008 max mem: 8233 +Train: [31] [3300/6250] eta: 0:08:09 lr: 0.000102 grad: 0.1121 (0.1173) loss: 0.8989 (0.8967) time: 0.1853 data: 0.0980 max mem: 8233 +Train: [31] [3400/6250] eta: 0:07:52 lr: 0.000102 grad: 0.1117 (0.1175) loss: 0.9025 (0.8967) time: 0.1717 data: 0.0924 max mem: 8233 +Train: [31] [3500/6250] eta: 0:07:36 lr: 0.000102 grad: 0.1133 (0.1175) loss: 0.8927 (0.8967) time: 0.1664 data: 0.0928 max mem: 8233 +Train: [31] [3600/6250] eta: 0:07:21 lr: 0.000102 grad: 0.1065 (0.1175) loss: 0.8931 (0.8966) time: 0.1807 data: 0.0897 max mem: 8233 +Train: [31] [3700/6250] eta: 0:07:04 lr: 0.000102 grad: 0.1131 (0.1175) loss: 0.8992 (0.8967) time: 0.2095 data: 0.1377 max mem: 8233 +Train: [31] [3800/6250] eta: 0:06:47 lr: 0.000102 grad: 0.1150 (0.1174) loss: 0.9003 (0.8967) time: 0.1433 data: 0.0670 max mem: 8233 +Train: [31] [3900/6250] eta: 0:06:30 lr: 0.000102 grad: 0.1171 (0.1175) loss: 0.8968 (0.8967) time: 0.1564 data: 0.0798 max mem: 8233 +Train: [31] [4000/6250] eta: 0:06:13 lr: 0.000102 grad: 0.1209 (0.1176) loss: 0.8994 (0.8967) time: 0.1486 data: 0.0557 max mem: 8233 +Train: [31] [4100/6250] eta: 0:05:57 lr: 0.000102 grad: 0.1108 (0.1175) loss: 0.8983 (0.8968) time: 0.1632 data: 0.0700 max mem: 8233 +Train: [31] [4200/6250] eta: 0:05:40 lr: 0.000102 grad: 0.1208 (0.1177) loss: 0.9002 (0.8968) time: 0.1498 data: 0.0589 max mem: 8233 +Train: [31] [4300/6250] eta: 0:05:23 lr: 0.000102 grad: 0.1088 (0.1177) loss: 0.9016 (0.8969) time: 0.1564 data: 0.0676 max mem: 8233 +Train: [31] [4400/6250] eta: 0:05:05 lr: 0.000102 grad: 0.1212 (0.1178) loss: 0.9023 (0.8969) time: 0.1412 data: 0.0643 max mem: 8233 +Train: [31] [4500/6250] eta: 0:04:48 lr: 0.000102 grad: 0.1172 (0.1180) loss: 0.9020 (0.8970) time: 0.1338 data: 0.0557 max mem: 8233 +Train: [31] [4600/6250] eta: 0:04:31 lr: 0.000102 grad: 0.1218 (0.1181) loss: 0.8962 (0.8970) time: 0.1620 data: 0.0759 max mem: 8233 +Train: [31] [4700/6250] eta: 0:04:15 lr: 0.000102 grad: 0.1124 (0.1181) loss: 0.9010 (0.8970) time: 0.1389 data: 0.0560 max mem: 8233 +Train: [31] [4800/6250] eta: 0:03:58 lr: 0.000102 grad: 0.1143 (0.1181) loss: 0.8973 (0.8971) time: 0.0944 data: 0.0160 max mem: 8233 +Train: [31] [4900/6250] eta: 0:03:43 lr: 0.000102 grad: 0.1222 (0.1181) loss: 0.8909 (0.8970) time: 0.2703 data: 0.1531 max mem: 8233 +Train: [31] [5000/6250] eta: 0:03:26 lr: 0.000102 grad: 0.1162 (0.1182) loss: 0.8988 (0.8970) time: 0.2384 data: 0.1608 max mem: 8233 +Train: [31] [5100/6250] eta: 0:03:10 lr: 0.000102 grad: 0.1107 (0.1181) loss: 0.8959 (0.8970) time: 0.1699 data: 0.0917 max mem: 8233 +Train: [31] [5200/6250] eta: 0:02:53 lr: 0.000102 grad: 0.1177 (0.1182) loss: 0.8951 (0.8970) time: 0.1457 data: 0.0609 max mem: 8233 +Train: [31] [5300/6250] eta: 0:02:36 lr: 0.000102 grad: 0.1157 (0.1183) loss: 0.8947 (0.8970) time: 0.1899 data: 0.0985 max mem: 8233 +Train: [31] [5400/6250] eta: 0:02:20 lr: 0.000102 grad: 0.1197 (0.1183) loss: 0.8948 (0.8969) time: 0.1785 data: 0.0892 max mem: 8233 +Train: [31] [5500/6250] eta: 0:02:03 lr: 0.000102 grad: 0.1248 (0.1184) loss: 0.8971 (0.8968) time: 0.1619 data: 0.0848 max mem: 8233 +Train: [31] [5600/6250] eta: 0:01:47 lr: 0.000102 grad: 0.1221 (0.1185) loss: 0.8969 (0.8968) time: 0.1375 data: 0.0701 max mem: 8233 +Train: [31] [5700/6250] eta: 0:01:30 lr: 0.000102 grad: 0.1154 (0.1187) loss: 0.8918 (0.8967) time: 0.1676 data: 0.0846 max mem: 8233 +Train: [31] [5800/6250] eta: 0:01:14 lr: 0.000102 grad: 0.1136 (0.1187) loss: 0.8929 (0.8967) time: 0.1269 data: 0.0494 max mem: 8233 +Train: [31] [5900/6250] eta: 0:00:57 lr: 0.000102 grad: 0.1150 (0.1187) loss: 0.8919 (0.8966) time: 0.1692 data: 0.0957 max mem: 8233 +Train: [31] [6000/6250] eta: 0:00:41 lr: 0.000102 grad: 0.1106 (0.1187) loss: 0.8951 (0.8966) time: 0.1839 data: 0.1088 max mem: 8233 +Train: [31] [6100/6250] eta: 0:00:24 lr: 0.000102 grad: 0.1127 (0.1188) loss: 0.8983 (0.8966) time: 0.1593 data: 0.0785 max mem: 8233 +Train: [31] [6200/6250] eta: 0:00:08 lr: 0.000102 grad: 0.1143 (0.1188) loss: 0.8910 (0.8965) time: 0.2404 data: 0.1705 max mem: 8233 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.1021 (0.1188) loss: 0.8985 (0.8965) time: 0.1716 data: 0.0930 max mem: 8233 +Train: [31] Total time: 0:17:14 (0.1656 s / it) +Averaged stats: lr: 0.000102 grad: 0.1021 (0.1188) loss: 0.8985 (0.8965) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:05:21 loss: 0.9135 (0.9135) time: 5.1909 data: 5.1641 max mem: 8233 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.9052 (0.9041) time: 0.1274 data: 0.1053 max mem: 8233 +Eval (hcp-train-subset): [31] Total time: 0:00:14 (0.2341 s / it) +Averaged stats (hcp-train-subset): loss: 0.9052 (0.9041) +Eval (hcp-val): [31] [ 0/62] eta: 0:03:37 loss: 0.9001 (0.9001) time: 3.5015 data: 3.4086 max mem: 8233 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.9000 (0.9004) time: 0.1372 data: 0.1154 max mem: 8233 +Eval (hcp-val): [31] Total time: 0:00:13 (0.2251 s / it) +Averaged stats (hcp-val): loss: 0.9000 (0.9004) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 7:46:33 lr: 0.000102 grad: 0.0763 (0.0763) loss: 0.9178 (0.9178) time: 4.4790 data: 4.1243 max mem: 8233 +Train: [32] [ 100/6250] eta: 0:22:28 lr: 0.000102 grad: 0.1123 (0.1271) loss: 0.9039 (0.9005) time: 0.1712 data: 0.0762 max mem: 8233 +Train: [32] [ 200/6250] eta: 0:20:25 lr: 0.000102 grad: 0.1317 (0.1260) loss: 0.8898 (0.8970) time: 0.1854 data: 0.1029 max mem: 8233 +Train: [32] [ 300/6250] eta: 0:19:38 lr: 0.000102 grad: 0.1202 (0.1236) loss: 0.8970 (0.8960) time: 0.1737 data: 0.0783 max mem: 8233 +Train: [32] [ 400/6250] eta: 0:18:46 lr: 0.000102 grad: 0.1166 (0.1223) loss: 0.8968 (0.8961) time: 0.1467 data: 0.0535 max mem: 8233 +Train: [32] [ 500/6250] eta: 0:18:02 lr: 0.000102 grad: 0.1025 (0.1209) loss: 0.8976 (0.8961) time: 0.1685 data: 0.0862 max mem: 8233 +Train: [32] [ 600/6250] eta: 0:17:38 lr: 0.000102 grad: 0.1066 (0.1200) loss: 0.8970 (0.8963) time: 0.2297 data: 0.1412 max mem: 8233 +Train: [32] [ 700/6250] eta: 0:17:03 lr: 0.000102 grad: 0.1046 (0.1192) loss: 0.9034 (0.8962) time: 0.1362 data: 0.0568 max mem: 8233 +Train: [32] [ 800/6250] eta: 0:16:33 lr: 0.000101 grad: 0.1093 (0.1182) loss: 0.8950 (0.8964) time: 0.1479 data: 0.0759 max mem: 8233 +Train: [32] [ 900/6250] eta: 0:16:06 lr: 0.000101 grad: 0.1066 (0.1173) loss: 0.9035 (0.8967) time: 0.1579 data: 0.0748 max mem: 8233 +Train: [32] [1000/6250] eta: 0:15:35 lr: 0.000101 grad: 0.1100 (0.1169) loss: 0.9032 (0.8970) time: 0.1612 data: 0.0694 max mem: 8233 +Train: [32] [1100/6250] eta: 0:15:04 lr: 0.000101 grad: 0.1048 (0.1162) loss: 0.9003 (0.8972) time: 0.1395 data: 0.0535 max mem: 8233 +Train: [32] [1200/6250] eta: 0:14:36 lr: 0.000101 grad: 0.1063 (0.1155) loss: 0.8980 (0.8973) time: 0.1537 data: 0.0622 max mem: 8233 +Train: [32] [1300/6250] eta: 0:14:12 lr: 0.000101 grad: 0.1098 (0.1152) loss: 0.8930 (0.8973) time: 0.1594 data: 0.0838 max mem: 8233 +Train: [32] [1400/6250] eta: 0:13:49 lr: 0.000101 grad: 0.1042 (0.1148) loss: 0.9011 (0.8975) time: 0.1512 data: 0.0651 max mem: 8233 +Train: [32] [1500/6250] eta: 0:13:31 lr: 0.000101 grad: 0.1006 (0.1142) loss: 0.9049 (0.8977) time: 0.2222 data: 0.1555 max mem: 8233 +Train: [32] [1600/6250] eta: 0:13:14 lr: 0.000101 grad: 0.1109 (0.1140) loss: 0.8950 (0.8978) time: 0.2298 data: 0.1559 max mem: 8233 +Train: [32] [1700/6250] eta: 0:12:52 lr: 0.000101 grad: 0.1087 (0.1138) loss: 0.9008 (0.8978) time: 0.1562 data: 0.0944 max mem: 8233 +Train: [32] [1800/6250] eta: 0:12:32 lr: 0.000101 grad: 0.1057 (0.1136) loss: 0.9030 (0.8979) time: 0.1617 data: 0.0806 max mem: 8233 +Train: [32] [1900/6250] eta: 0:12:13 lr: 0.000101 grad: 0.1076 (0.1136) loss: 0.8942 (0.8980) time: 0.1641 data: 0.0954 max mem: 8233 +Train: [32] [2000/6250] eta: 0:11:52 lr: 0.000101 grad: 0.1088 (0.1134) loss: 0.8984 (0.8980) time: 0.1511 data: 0.0852 max mem: 8233 +Train: [32] [2100/6250] eta: 0:11:32 lr: 0.000101 grad: 0.1137 (0.1134) loss: 0.8983 (0.8980) time: 0.1413 data: 0.0613 max mem: 8233 +Train: [32] [2200/6250] eta: 0:11:14 lr: 0.000101 grad: 0.1069 (0.1132) loss: 0.8969 (0.8980) time: 0.1640 data: 0.0861 max mem: 8233 +Train: [32] [2300/6250] eta: 0:10:54 lr: 0.000101 grad: 0.1085 (0.1133) loss: 0.8948 (0.8980) time: 0.1489 data: 0.0653 max mem: 8233 +Train: [32] [2400/6250] eta: 0:10:36 lr: 0.000101 grad: 0.1131 (0.1131) loss: 0.8991 (0.8979) time: 0.1615 data: 0.0823 max mem: 8233 +Train: [32] [2500/6250] eta: 0:10:20 lr: 0.000101 grad: 0.1083 (0.1131) loss: 0.8953 (0.8979) time: 0.1953 data: 0.1327 max mem: 8233 +Train: [32] [2600/6250] eta: 0:10:02 lr: 0.000101 grad: 0.1116 (0.1130) loss: 0.8961 (0.8978) time: 0.1457 data: 0.0742 max mem: 8233 +Train: [32] [2700/6250] eta: 0:09:45 lr: 0.000101 grad: 0.1086 (0.1131) loss: 0.8911 (0.8977) time: 0.1534 data: 0.0778 max mem: 8233 +Train: [32] [2800/6250] eta: 0:09:28 lr: 0.000101 grad: 0.1088 (0.1131) loss: 0.8957 (0.8976) time: 0.1484 data: 0.0536 max mem: 8233 +Train: [32] [2900/6250] eta: 0:09:11 lr: 0.000101 grad: 0.1166 (0.1132) loss: 0.8958 (0.8976) time: 0.1341 data: 0.0422 max mem: 8233 +Train: [32] [3000/6250] eta: 0:08:54 lr: 0.000101 grad: 0.1119 (0.1133) loss: 0.8994 (0.8975) time: 0.1334 data: 0.0547 max mem: 8233 +Train: [32] [3100/6250] eta: 0:08:37 lr: 0.000101 grad: 0.1111 (0.1133) loss: 0.8962 (0.8975) time: 0.1047 data: 0.0197 max mem: 8233 +Train: [32] [3200/6250] eta: 0:08:19 lr: 0.000101 grad: 0.1073 (0.1133) loss: 0.8995 (0.8976) time: 0.1331 data: 0.0335 max mem: 8233 +Train: [32] [3300/6250] eta: 0:08:02 lr: 0.000101 grad: 0.1153 (0.1133) loss: 0.8955 (0.8976) time: 0.1628 data: 0.0862 max mem: 8233 +Train: [32] [3400/6250] eta: 0:07:45 lr: 0.000101 grad: 0.1096 (0.1134) loss: 0.8999 (0.8976) time: 0.1125 data: 0.0395 max mem: 8233 +Train: [32] [3500/6250] eta: 0:07:29 lr: 0.000101 grad: 0.1072 (0.1134) loss: 0.9019 (0.8976) time: 0.1213 data: 0.0418 max mem: 8233 +Train: [32] [3600/6250] eta: 0:07:13 lr: 0.000101 grad: 0.1128 (0.1134) loss: 0.8979 (0.8976) time: 0.1445 data: 0.0651 max mem: 8233 +Train: [32] [3700/6250] eta: 0:06:56 lr: 0.000101 grad: 0.1077 (0.1134) loss: 0.8987 (0.8976) time: 0.1327 data: 0.0501 max mem: 8233 +Train: [32] [3800/6250] eta: 0:06:38 lr: 0.000101 grad: 0.1162 (0.1134) loss: 0.8957 (0.8976) time: 0.1106 data: 0.0311 max mem: 8233 +Train: [32] [3900/6250] eta: 0:06:22 lr: 0.000101 grad: 0.1057 (0.1134) loss: 0.8976 (0.8976) time: 0.1646 data: 0.0924 max mem: 8233 +Train: [32] [4000/6250] eta: 0:06:06 lr: 0.000101 grad: 0.1128 (0.1134) loss: 0.8941 (0.8976) time: 0.1761 data: 0.0974 max mem: 8233 +Train: [32] [4100/6250] eta: 0:05:50 lr: 0.000101 grad: 0.1083 (0.1133) loss: 0.9021 (0.8977) time: 0.1552 data: 0.0843 max mem: 8233 +Train: [32] [4200/6250] eta: 0:05:34 lr: 0.000101 grad: 0.1035 (0.1134) loss: 0.8982 (0.8977) time: 0.1912 data: 0.1130 max mem: 8233 +Train: [32] [4300/6250] eta: 0:05:18 lr: 0.000101 grad: 0.1134 (0.1134) loss: 0.8956 (0.8977) time: 0.1494 data: 0.0657 max mem: 8233 +Train: [32] [4400/6250] eta: 0:05:02 lr: 0.000101 grad: 0.1080 (0.1134) loss: 0.8959 (0.8977) time: 0.1809 data: 0.0953 max mem: 8233 +Train: [32] [4500/6250] eta: 0:04:45 lr: 0.000101 grad: 0.1063 (0.1133) loss: 0.9016 (0.8977) time: 0.1404 data: 0.0567 max mem: 8233 +Train: [32] [4600/6250] eta: 0:04:29 lr: 0.000101 grad: 0.1085 (0.1133) loss: 0.8984 (0.8977) time: 0.1394 data: 0.0420 max mem: 8233 +Train: [32] [4700/6250] eta: 0:04:12 lr: 0.000100 grad: 0.1168 (0.1133) loss: 0.8960 (0.8978) time: 0.1630 data: 0.0802 max mem: 8233 +Train: [32] [4800/6250] eta: 0:03:57 lr: 0.000100 grad: 0.1120 (0.1133) loss: 0.8996 (0.8978) time: 0.1705 data: 0.0881 max mem: 8233 +Train: [32] [4900/6250] eta: 0:03:40 lr: 0.000100 grad: 0.1125 (0.1133) loss: 0.8998 (0.8979) time: 0.1558 data: 0.0836 max mem: 8233 +Train: [32] [5000/6250] eta: 0:03:24 lr: 0.000100 grad: 0.0997 (0.1133) loss: 0.9009 (0.8979) time: 0.2969 data: 0.2134 max mem: 8233 +Train: [32] [5100/6250] eta: 0:03:08 lr: 0.000100 grad: 0.1136 (0.1133) loss: 0.8948 (0.8979) time: 0.3065 data: 0.2272 max mem: 8233 +Train: [32] [5200/6250] eta: 0:02:52 lr: 0.000100 grad: 0.1045 (0.1133) loss: 0.8969 (0.8979) time: 0.1002 data: 0.0002 max mem: 8233 +Train: [32] [5300/6250] eta: 0:02:35 lr: 0.000100 grad: 0.1138 (0.1133) loss: 0.8949 (0.8979) time: 0.1586 data: 0.0922 max mem: 8233 +Train: [32] [5400/6250] eta: 0:02:19 lr: 0.000100 grad: 0.1128 (0.1132) loss: 0.9018 (0.8979) time: 0.1494 data: 0.0745 max mem: 8233 +Train: [32] [5500/6250] eta: 0:02:02 lr: 0.000100 grad: 0.1069 (0.1133) loss: 0.8999 (0.8979) time: 0.1483 data: 0.0828 max mem: 8233 +Train: [32] [5600/6250] eta: 0:01:46 lr: 0.000100 grad: 0.1048 (0.1133) loss: 0.8970 (0.8979) time: 0.1989 data: 0.1214 max mem: 8233 +Train: [32] [5700/6250] eta: 0:01:29 lr: 0.000100 grad: 0.1068 (0.1132) loss: 0.8980 (0.8979) time: 0.1380 data: 0.0435 max mem: 8233 +Train: [32] [5800/6250] eta: 0:01:13 lr: 0.000100 grad: 0.1080 (0.1132) loss: 0.8976 (0.8979) time: 0.1435 data: 0.0604 max mem: 8233 +Train: [32] [5900/6250] eta: 0:00:56 lr: 0.000100 grad: 0.1088 (0.1131) loss: 0.9007 (0.8980) time: 0.1296 data: 0.0468 max mem: 8233 +Train: [32] [6000/6250] eta: 0:00:40 lr: 0.000100 grad: 0.1111 (0.1131) loss: 0.9001 (0.8980) time: 0.1732 data: 0.0907 max mem: 8233 +Train: [32] [6100/6250] eta: 0:00:24 lr: 0.000100 grad: 0.1093 (0.1131) loss: 0.8967 (0.8980) time: 0.1662 data: 0.0840 max mem: 8233 +Train: [32] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.1076 (0.1131) loss: 0.9001 (0.8981) time: 0.1772 data: 0.0926 max mem: 8233 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.1100 (0.1131) loss: 0.8916 (0.8980) time: 0.1649 data: 0.0863 max mem: 8233 +Train: [32] Total time: 0:17:02 (0.1636 s / it) +Averaged stats: lr: 0.000100 grad: 0.1100 (0.1131) loss: 0.8916 (0.8980) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:04:31 loss: 0.9138 (0.9138) time: 4.3711 data: 4.2688 max mem: 8233 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.9043 (0.9038) time: 0.1374 data: 0.1167 max mem: 8233 +Eval (hcp-train-subset): [32] Total time: 0:00:14 (0.2306 s / it) +Averaged stats (hcp-train-subset): loss: 0.9043 (0.9038) +Eval (hcp-val): [32] [ 0/62] eta: 0:03:54 loss: 0.8951 (0.8951) time: 3.7811 data: 3.6939 max mem: 8233 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8993 (0.8993) time: 0.1522 data: 0.1315 max mem: 8233 +Eval (hcp-val): [32] Total time: 0:00:14 (0.2339 s / it) +Averaged stats (hcp-val): loss: 0.8993 (0.8993) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 7:12:30 lr: 0.000100 grad: 0.0976 (0.0976) loss: 0.9142 (0.9142) time: 4.1521 data: 3.8590 max mem: 8233 +Train: [33] [ 100/6250] eta: 0:22:52 lr: 0.000100 grad: 0.1161 (0.1130) loss: 0.8986 (0.9000) time: 0.1912 data: 0.0952 max mem: 8233 +Train: [33] [ 200/6250] eta: 0:19:55 lr: 0.000100 grad: 0.1079 (0.1149) loss: 0.8996 (0.8978) time: 0.1488 data: 0.0491 max mem: 8233 +Train: [33] [ 300/6250] eta: 0:18:31 lr: 0.000100 grad: 0.1166 (0.1133) loss: 0.8975 (0.8967) time: 0.1539 data: 0.0554 max mem: 8233 +Train: [33] [ 400/6250] eta: 0:17:44 lr: 0.000100 grad: 0.1129 (0.1128) loss: 0.8977 (0.8965) time: 0.1598 data: 0.0677 max mem: 8233 +Train: [33] [ 500/6250] eta: 0:16:53 lr: 0.000100 grad: 0.1094 (0.1127) loss: 0.8952 (0.8963) time: 0.1388 data: 0.0404 max mem: 8233 +Train: [33] [ 600/6250] eta: 0:16:18 lr: 0.000100 grad: 0.1110 (0.1129) loss: 0.8934 (0.8957) time: 0.1454 data: 0.0585 max mem: 8233 +Train: [33] [ 700/6250] eta: 0:15:50 lr: 0.000100 grad: 0.1097 (0.1128) loss: 0.8946 (0.8957) time: 0.1500 data: 0.0717 max mem: 8233 +Train: [33] [ 800/6250] eta: 0:15:32 lr: 0.000100 grad: 0.1102 (0.1127) loss: 0.8913 (0.8954) time: 0.1316 data: 0.0506 max mem: 8233 +Train: [33] [ 900/6250] eta: 0:15:12 lr: 0.000100 grad: 0.1071 (0.1125) loss: 0.8976 (0.8954) time: 0.1739 data: 0.1001 max mem: 8233 +Train: [33] [1000/6250] eta: 0:14:47 lr: 0.000100 grad: 0.1085 (0.1125) loss: 0.8942 (0.8953) time: 0.1584 data: 0.0700 max mem: 8233 +Train: [33] [1100/6250] eta: 0:14:27 lr: 0.000100 grad: 0.1107 (0.1125) loss: 0.8926 (0.8953) time: 0.1805 data: 0.1023 max mem: 8233 +Train: [33] [1200/6250] eta: 0:14:08 lr: 0.000100 grad: 0.1049 (0.1123) loss: 0.8990 (0.8954) time: 0.1437 data: 0.0553 max mem: 8233 +Train: [33] [1300/6250] eta: 0:13:44 lr: 0.000100 grad: 0.1052 (0.1124) loss: 0.8989 (0.8954) time: 0.1375 data: 0.0529 max mem: 8233 +Train: [33] [1400/6250] eta: 0:13:22 lr: 0.000100 grad: 0.1104 (0.1127) loss: 0.9022 (0.8952) time: 0.1517 data: 0.0697 max mem: 8233 +Train: [33] [1500/6250] eta: 0:13:03 lr: 0.000100 grad: 0.1156 (0.1128) loss: 0.8901 (0.8950) time: 0.1554 data: 0.0704 max mem: 8233 +Train: [33] [1600/6250] eta: 0:12:41 lr: 0.000100 grad: 0.1201 (0.1132) loss: 0.8925 (0.8948) time: 0.1591 data: 0.0773 max mem: 8233 +Train: [33] [1700/6250] eta: 0:12:22 lr: 0.000100 grad: 0.1130 (0.1138) loss: 0.8943 (0.8946) time: 0.1330 data: 0.0547 max mem: 8233 +Train: [33] [1800/6250] eta: 0:12:05 lr: 0.000100 grad: 0.1092 (0.1139) loss: 0.8961 (0.8946) time: 0.1766 data: 0.0970 max mem: 8233 +Train: [33] [1900/6250] eta: 0:11:49 lr: 0.000100 grad: 0.1148 (0.1140) loss: 0.8904 (0.8946) time: 0.1590 data: 0.0664 max mem: 8233 +Train: [33] [2000/6250] eta: 0:11:36 lr: 0.000100 grad: 0.1128 (0.1143) loss: 0.8998 (0.8946) time: 0.1353 data: 0.0243 max mem: 8233 +Train: [33] [2100/6250] eta: 0:11:18 lr: 0.000100 grad: 0.1284 (0.1147) loss: 0.8953 (0.8947) time: 0.1387 data: 0.0579 max mem: 8233 +Train: [33] [2200/6250] eta: 0:11:00 lr: 0.000099 grad: 0.1157 (0.1149) loss: 0.8892 (0.8947) time: 0.1585 data: 0.0682 max mem: 8233 +Train: [33] [2300/6250] eta: 0:10:43 lr: 0.000099 grad: 0.1090 (0.1152) loss: 0.8974 (0.8947) time: 0.1587 data: 0.0822 max mem: 8233 +Train: [33] [2400/6250] eta: 0:10:28 lr: 0.000099 grad: 0.1109 (0.1152) loss: 0.8908 (0.8946) time: 0.1697 data: 0.0835 max mem: 8233 +Train: [33] [2500/6250] eta: 0:10:08 lr: 0.000099 grad: 0.1079 (0.1154) loss: 0.8996 (0.8946) time: 0.1455 data: 0.0673 max mem: 8233 +Train: [33] [2600/6250] eta: 0:09:51 lr: 0.000099 grad: 0.1116 (0.1154) loss: 0.8970 (0.8947) time: 0.1594 data: 0.0770 max mem: 8233 +Train: [33] [2700/6250] eta: 0:09:36 lr: 0.000099 grad: 0.1080 (0.1154) loss: 0.8960 (0.8947) time: 0.1517 data: 0.0716 max mem: 8233 +Train: [33] [2800/6250] eta: 0:09:19 lr: 0.000099 grad: 0.1039 (0.1154) loss: 0.8973 (0.8947) time: 0.1639 data: 0.0886 max mem: 8233 +Train: [33] [2900/6250] eta: 0:09:02 lr: 0.000099 grad: 0.1198 (0.1155) loss: 0.8925 (0.8947) time: 0.1906 data: 0.1058 max mem: 8233 +Train: [33] [3000/6250] eta: 0:08:46 lr: 0.000099 grad: 0.1059 (0.1156) loss: 0.8977 (0.8946) time: 0.1783 data: 0.0993 max mem: 8233 +Train: [33] [3100/6250] eta: 0:08:31 lr: 0.000099 grad: 0.1069 (0.1156) loss: 0.8922 (0.8946) time: 0.1492 data: 0.0612 max mem: 8233 +Train: [33] [3200/6250] eta: 0:08:14 lr: 0.000099 grad: 0.1175 (0.1154) loss: 0.8956 (0.8946) time: 0.1654 data: 0.0957 max mem: 8233 +Train: [33] [3300/6250] eta: 0:07:57 lr: 0.000099 grad: 0.1154 (0.1155) loss: 0.8937 (0.8946) time: 0.1830 data: 0.1007 max mem: 8233 +Train: [33] [3400/6250] eta: 0:07:40 lr: 0.000099 grad: 0.1061 (0.1153) loss: 0.8999 (0.8946) time: 0.1647 data: 0.0882 max mem: 8233 +Train: [33] [3500/6250] eta: 0:07:23 lr: 0.000099 grad: 0.1122 (0.1153) loss: 0.8994 (0.8946) time: 0.1394 data: 0.0545 max mem: 8233 +Train: [33] [3600/6250] eta: 0:07:06 lr: 0.000099 grad: 0.1041 (0.1153) loss: 0.8946 (0.8946) time: 0.0972 data: 0.0122 max mem: 8233 +Train: [33] [3700/6250] eta: 0:06:50 lr: 0.000099 grad: 0.1065 (0.1152) loss: 0.8959 (0.8946) time: 0.1611 data: 0.0832 max mem: 8233 +Train: [33] [3800/6250] eta: 0:06:33 lr: 0.000099 grad: 0.1066 (0.1152) loss: 0.8966 (0.8946) time: 0.1283 data: 0.0514 max mem: 8233 +Train: [33] [3900/6250] eta: 0:06:17 lr: 0.000099 grad: 0.1033 (0.1151) loss: 0.8950 (0.8947) time: 0.1775 data: 0.1004 max mem: 8233 +Train: [33] [4000/6250] eta: 0:06:00 lr: 0.000099 grad: 0.1091 (0.1151) loss: 0.8945 (0.8947) time: 0.1469 data: 0.0554 max mem: 8233 +Train: [33] [4100/6250] eta: 0:05:45 lr: 0.000099 grad: 0.1116 (0.1150) loss: 0.8897 (0.8947) time: 0.1638 data: 0.0783 max mem: 8233 +Train: [33] [4200/6250] eta: 0:05:28 lr: 0.000099 grad: 0.1066 (0.1149) loss: 0.8976 (0.8948) time: 0.1717 data: 0.0817 max mem: 8233 +Train: [33] [4300/6250] eta: 0:05:12 lr: 0.000099 grad: 0.1064 (0.1148) loss: 0.8959 (0.8948) time: 0.1510 data: 0.0775 max mem: 8233 +Train: [33] [4400/6250] eta: 0:04:56 lr: 0.000099 grad: 0.1129 (0.1147) loss: 0.8956 (0.8948) time: 0.1563 data: 0.0732 max mem: 8233 +Train: [33] [4500/6250] eta: 0:04:40 lr: 0.000099 grad: 0.1109 (0.1146) loss: 0.8977 (0.8949) time: 0.1413 data: 0.0570 max mem: 8233 +Train: [33] [4600/6250] eta: 0:04:24 lr: 0.000099 grad: 0.1105 (0.1145) loss: 0.9005 (0.8949) time: 0.1381 data: 0.0553 max mem: 8233 +Train: [33] [4700/6250] eta: 0:04:08 lr: 0.000099 grad: 0.1050 (0.1144) loss: 0.8971 (0.8949) time: 0.1607 data: 0.0763 max mem: 8233 +Train: [33] [4800/6250] eta: 0:03:52 lr: 0.000099 grad: 0.1007 (0.1143) loss: 0.9004 (0.8949) time: 0.1446 data: 0.0478 max mem: 8233 +Train: [33] [4900/6250] eta: 0:03:36 lr: 0.000099 grad: 0.1114 (0.1143) loss: 0.8950 (0.8949) time: 0.1445 data: 0.0624 max mem: 8233 +Train: [33] [5000/6250] eta: 0:03:19 lr: 0.000099 grad: 0.1131 (0.1143) loss: 0.9009 (0.8950) time: 0.1399 data: 0.0497 max mem: 8233 +Train: [33] [5100/6250] eta: 0:03:03 lr: 0.000099 grad: 0.1118 (0.1142) loss: 0.8937 (0.8949) time: 0.1592 data: 0.0813 max mem: 8233 +Train: [33] [5200/6250] eta: 0:02:47 lr: 0.000099 grad: 0.1198 (0.1142) loss: 0.8862 (0.8949) time: 0.1598 data: 0.0774 max mem: 8233 +Train: [33] [5300/6250] eta: 0:02:31 lr: 0.000099 grad: 0.1094 (0.1141) loss: 0.8958 (0.8950) time: 0.1446 data: 0.0590 max mem: 8233 +Train: [33] [5400/6250] eta: 0:02:15 lr: 0.000099 grad: 0.1054 (0.1141) loss: 0.8976 (0.8950) time: 0.1381 data: 0.0552 max mem: 8233 +Train: [33] [5500/6250] eta: 0:01:59 lr: 0.000099 grad: 0.1102 (0.1140) loss: 0.8970 (0.8950) time: 0.1696 data: 0.0927 max mem: 8233 +Train: [33] [5600/6250] eta: 0:01:43 lr: 0.000099 grad: 0.1141 (0.1140) loss: 0.8963 (0.8950) time: 0.2099 data: 0.1308 max mem: 8233 +Train: [33] [5700/6250] eta: 0:01:27 lr: 0.000099 grad: 0.1027 (0.1140) loss: 0.8975 (0.8951) time: 0.1360 data: 0.0143 max mem: 8233 +Train: [33] [5800/6250] eta: 0:01:11 lr: 0.000099 grad: 0.1037 (0.1140) loss: 0.8975 (0.8951) time: 0.1605 data: 0.0778 max mem: 8233 +Train: [33] [5900/6250] eta: 0:00:55 lr: 0.000098 grad: 0.1128 (0.1141) loss: 0.8944 (0.8951) time: 0.1484 data: 0.0550 max mem: 8233 +Train: [33] [6000/6250] eta: 0:00:39 lr: 0.000098 grad: 0.1090 (0.1141) loss: 0.8971 (0.8951) time: 0.1420 data: 0.0615 max mem: 8233 +Train: [33] [6100/6250] eta: 0:00:23 lr: 0.000098 grad: 0.1118 (0.1142) loss: 0.8944 (0.8951) time: 0.1622 data: 0.0836 max mem: 8233 +Train: [33] [6200/6250] eta: 0:00:07 lr: 0.000098 grad: 0.1070 (0.1142) loss: 0.8944 (0.8950) time: 0.1483 data: 0.0730 max mem: 8233 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.1128 (0.1142) loss: 0.8899 (0.8950) time: 0.1556 data: 0.0802 max mem: 8233 +Train: [33] Total time: 0:16:40 (0.1600 s / it) +Averaged stats: lr: 0.000098 grad: 0.1128 (0.1142) loss: 0.8899 (0.8950) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:05:17 loss: 0.9107 (0.9107) time: 5.1146 data: 5.0882 max mem: 8233 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.9028 (0.9029) time: 0.1438 data: 0.1235 max mem: 8233 +Eval (hcp-train-subset): [33] Total time: 0:00:13 (0.2258 s / it) +Averaged stats (hcp-train-subset): loss: 0.9028 (0.9029) +Eval (hcp-val): [33] [ 0/62] eta: 0:04:23 loss: 0.8929 (0.8929) time: 4.2488 data: 4.1750 max mem: 8233 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8980 (0.8989) time: 0.1607 data: 0.1388 max mem: 8233 +Eval (hcp-val): [33] Total time: 0:00:14 (0.2352 s / it) +Averaged stats (hcp-val): loss: 0.8980 (0.8989) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 11:16:29 lr: 0.000098 grad: 0.2168 (0.2168) loss: 0.9119 (0.9119) time: 6.4942 data: 6.3497 max mem: 8233 +Train: [34] [ 100/6250] eta: 0:23:28 lr: 0.000098 grad: 0.1106 (0.1182) loss: 0.8961 (0.8977) time: 0.2125 data: 0.1180 max mem: 8233 +Train: [34] [ 200/6250] eta: 0:20:32 lr: 0.000098 grad: 0.1073 (0.1154) loss: 0.8948 (0.8985) time: 0.1887 data: 0.0881 max mem: 8233 +Train: [34] [ 300/6250] eta: 0:19:14 lr: 0.000098 grad: 0.1083 (0.1142) loss: 0.8967 (0.8979) time: 0.1620 data: 0.0741 max mem: 8233 +Train: [34] [ 400/6250] eta: 0:18:11 lr: 0.000098 grad: 0.1118 (0.1141) loss: 0.8963 (0.8971) time: 0.1418 data: 0.0528 max mem: 8233 +Train: [34] [ 500/6250] eta: 0:17:30 lr: 0.000098 grad: 0.1053 (0.1138) loss: 0.8983 (0.8972) time: 0.1441 data: 0.0529 max mem: 8233 +Train: [34] [ 600/6250] eta: 0:16:48 lr: 0.000098 grad: 0.1057 (0.1134) loss: 0.8985 (0.8973) time: 0.1395 data: 0.0533 max mem: 8233 +Train: [34] [ 700/6250] eta: 0:16:18 lr: 0.000098 grad: 0.1038 (0.1128) loss: 0.9000 (0.8975) time: 0.1363 data: 0.0520 max mem: 8233 +Train: [34] [ 800/6250] eta: 0:15:55 lr: 0.000098 grad: 0.1042 (0.1119) loss: 0.8951 (0.8974) time: 0.1981 data: 0.1118 max mem: 8233 +Train: [34] [ 900/6250] eta: 0:15:38 lr: 0.000098 grad: 0.1168 (0.1120) loss: 0.9006 (0.8973) time: 0.1515 data: 0.0771 max mem: 8233 +Train: [34] [1000/6250] eta: 0:15:12 lr: 0.000098 grad: 0.1108 (0.1119) loss: 0.8960 (0.8973) time: 0.1665 data: 0.1012 max mem: 8233 +Train: [34] [1100/6250] eta: 0:14:52 lr: 0.000098 grad: 0.1008 (0.1115) loss: 0.9013 (0.8974) time: 0.1976 data: 0.1104 max mem: 8233 +Train: [34] [1200/6250] eta: 0:14:32 lr: 0.000098 grad: 0.1053 (0.1114) loss: 0.8965 (0.8974) time: 0.1583 data: 0.0801 max mem: 8233 +Train: [34] [1300/6250] eta: 0:14:10 lr: 0.000098 grad: 0.1042 (0.1116) loss: 0.8986 (0.8975) time: 0.1572 data: 0.0722 max mem: 8233 +Train: [34] [1400/6250] eta: 0:13:48 lr: 0.000098 grad: 0.1137 (0.1115) loss: 0.9027 (0.8975) time: 0.1564 data: 0.0731 max mem: 8233 +Train: [34] [1500/6250] eta: 0:13:27 lr: 0.000098 grad: 0.1110 (0.1116) loss: 0.8965 (0.8974) time: 0.1735 data: 0.0949 max mem: 8233 +Train: [34] [1600/6250] eta: 0:13:05 lr: 0.000098 grad: 0.1105 (0.1117) loss: 0.8956 (0.8974) time: 0.1689 data: 0.0902 max mem: 8233 +Train: [34] [1700/6250] eta: 0:12:43 lr: 0.000098 grad: 0.1117 (0.1118) loss: 0.8971 (0.8974) time: 0.1561 data: 0.0854 max mem: 8233 +Train: [34] [1800/6250] eta: 0:12:24 lr: 0.000098 grad: 0.1089 (0.1120) loss: 0.8977 (0.8974) time: 0.1620 data: 0.0905 max mem: 8233 +Train: [34] [1900/6250] eta: 0:12:07 lr: 0.000098 grad: 0.1157 (0.1122) loss: 0.8937 (0.8972) time: 0.1553 data: 0.0836 max mem: 8233 +Train: [34] [2000/6250] eta: 0:11:48 lr: 0.000098 grad: 0.1169 (0.1123) loss: 0.8991 (0.8971) time: 0.1542 data: 0.0773 max mem: 8233 +Train: [34] [2100/6250] eta: 0:11:29 lr: 0.000098 grad: 0.1120 (0.1122) loss: 0.8956 (0.8971) time: 0.1434 data: 0.0673 max mem: 8233 +Train: [34] [2200/6250] eta: 0:11:10 lr: 0.000098 grad: 0.1175 (0.1122) loss: 0.8930 (0.8970) time: 0.1495 data: 0.0722 max mem: 8233 +Train: [34] [2300/6250] eta: 0:10:52 lr: 0.000098 grad: 0.1078 (0.1121) loss: 0.8974 (0.8970) time: 0.1540 data: 0.0882 max mem: 8233 +Train: [34] [2400/6250] eta: 0:10:35 lr: 0.000098 grad: 0.1063 (0.1123) loss: 0.9033 (0.8970) time: 0.1464 data: 0.0741 max mem: 8233 +Train: [34] [2500/6250] eta: 0:10:20 lr: 0.000098 grad: 0.1157 (0.1122) loss: 0.8989 (0.8970) time: 0.2515 data: 0.1556 max mem: 8233 +Train: [34] [2600/6250] eta: 0:10:04 lr: 0.000098 grad: 0.1092 (0.1123) loss: 0.8984 (0.8970) time: 0.1629 data: 0.0920 max mem: 8233 +Train: [34] [2700/6250] eta: 0:09:48 lr: 0.000098 grad: 0.1209 (0.1125) loss: 0.8908 (0.8969) time: 0.1719 data: 0.0896 max mem: 8233 +Train: [34] [2800/6250] eta: 0:09:33 lr: 0.000098 grad: 0.1072 (0.1127) loss: 0.8947 (0.8968) time: 0.1651 data: 0.0824 max mem: 8233 +Train: [34] [2900/6250] eta: 0:09:15 lr: 0.000098 grad: 0.1078 (0.1127) loss: 0.9001 (0.8967) time: 0.1505 data: 0.0768 max mem: 8233 +Train: [34] [3000/6250] eta: 0:08:58 lr: 0.000098 grad: 0.1109 (0.1127) loss: 0.8961 (0.8966) time: 0.1642 data: 0.0865 max mem: 8233 +Train: [34] [3100/6250] eta: 0:08:42 lr: 0.000098 grad: 0.1119 (0.1127) loss: 0.8915 (0.8966) time: 0.1531 data: 0.0713 max mem: 8233 +Train: [34] [3200/6250] eta: 0:08:26 lr: 0.000098 grad: 0.1086 (0.1128) loss: 0.8946 (0.8965) time: 0.1593 data: 0.0767 max mem: 8233 +Train: [34] [3300/6250] eta: 0:08:09 lr: 0.000097 grad: 0.1065 (0.1128) loss: 0.8944 (0.8964) time: 0.1632 data: 0.0876 max mem: 8233 +Train: [34] [3400/6250] eta: 0:07:51 lr: 0.000097 grad: 0.1123 (0.1128) loss: 0.8920 (0.8963) time: 0.1513 data: 0.0640 max mem: 8233 +Train: [34] [3500/6250] eta: 0:07:34 lr: 0.000097 grad: 0.1126 (0.1128) loss: 0.8913 (0.8962) time: 0.1671 data: 0.0803 max mem: 8233 +Train: [34] [3600/6250] eta: 0:07:16 lr: 0.000097 grad: 0.1032 (0.1128) loss: 0.8964 (0.8962) time: 0.1289 data: 0.0433 max mem: 8233 +Train: [34] [3700/6250] eta: 0:06:58 lr: 0.000097 grad: 0.1093 (0.1128) loss: 0.8953 (0.8962) time: 0.1514 data: 0.0674 max mem: 8233 +Train: [34] [3800/6250] eta: 0:06:40 lr: 0.000097 grad: 0.1159 (0.1129) loss: 0.8899 (0.8961) time: 0.1121 data: 0.0231 max mem: 8233 +Train: [34] [3900/6250] eta: 0:06:23 lr: 0.000097 grad: 0.1032 (0.1129) loss: 0.8943 (0.8960) time: 0.1370 data: 0.0517 max mem: 8233 +Train: [34] [4000/6250] eta: 0:06:07 lr: 0.000097 grad: 0.1124 (0.1131) loss: 0.8950 (0.8959) time: 0.1894 data: 0.1114 max mem: 8233 +Train: [34] [4100/6250] eta: 0:05:50 lr: 0.000097 grad: 0.1090 (0.1131) loss: 0.8964 (0.8959) time: 0.1651 data: 0.0837 max mem: 8233 +Train: [34] [4200/6250] eta: 0:05:36 lr: 0.000097 grad: 0.1156 (0.1133) loss: 0.8943 (0.8958) time: 0.3338 data: 0.2652 max mem: 8233 +Train: [34] [4300/6250] eta: 0:05:19 lr: 0.000097 grad: 0.1072 (0.1134) loss: 0.8916 (0.8958) time: 0.1569 data: 0.0836 max mem: 8233 +Train: [34] [4400/6250] eta: 0:05:03 lr: 0.000097 grad: 0.1214 (0.1134) loss: 0.8877 (0.8957) time: 0.1964 data: 0.0706 max mem: 8233 +Train: [34] [4500/6250] eta: 0:04:47 lr: 0.000097 grad: 0.1147 (0.1135) loss: 0.8948 (0.8957) time: 0.1783 data: 0.0977 max mem: 8233 +Train: [34] [4600/6250] eta: 0:04:31 lr: 0.000097 grad: 0.1161 (0.1136) loss: 0.8917 (0.8956) time: 0.2000 data: 0.1078 max mem: 8233 +Train: [34] [4700/6250] eta: 0:04:14 lr: 0.000097 grad: 0.1082 (0.1136) loss: 0.8973 (0.8956) time: 0.1633 data: 0.0764 max mem: 8233 +Train: [34] [4800/6250] eta: 0:03:58 lr: 0.000097 grad: 0.1161 (0.1137) loss: 0.8954 (0.8956) time: 0.1795 data: 0.0949 max mem: 8233 +Train: [34] [4900/6250] eta: 0:03:42 lr: 0.000097 grad: 0.1164 (0.1138) loss: 0.8933 (0.8956) time: 0.1420 data: 0.0527 max mem: 8233 +Train: [34] [5000/6250] eta: 0:03:25 lr: 0.000097 grad: 0.1089 (0.1140) loss: 0.8979 (0.8956) time: 0.1295 data: 0.0414 max mem: 8233 +Train: [34] [5100/6250] eta: 0:03:09 lr: 0.000097 grad: 0.1085 (0.1140) loss: 0.8961 (0.8956) time: 0.1119 data: 0.0232 max mem: 8233 +Train: [34] [5200/6250] eta: 0:02:52 lr: 0.000097 grad: 0.1051 (0.1141) loss: 0.8974 (0.8956) time: 0.1545 data: 0.0714 max mem: 8233 +Train: [34] [5300/6250] eta: 0:02:36 lr: 0.000097 grad: 0.1055 (0.1141) loss: 0.8953 (0.8956) time: 0.2579 data: 0.1796 max mem: 8233 +Train: [34] [5400/6250] eta: 0:02:19 lr: 0.000097 grad: 0.1089 (0.1141) loss: 0.8943 (0.8956) time: 0.1518 data: 0.0726 max mem: 8233 +Train: [34] [5500/6250] eta: 0:02:02 lr: 0.000097 grad: 0.1157 (0.1142) loss: 0.8898 (0.8955) time: 0.1485 data: 0.0618 max mem: 8233 +Train: [34] [5600/6250] eta: 0:01:46 lr: 0.000097 grad: 0.1135 (0.1141) loss: 0.8954 (0.8955) time: 0.1542 data: 0.0722 max mem: 8233 +Train: [34] [5700/6250] eta: 0:01:30 lr: 0.000097 grad: 0.1126 (0.1142) loss: 0.8910 (0.8955) time: 0.2202 data: 0.1175 max mem: 8233 +Train: [34] [5800/6250] eta: 0:01:13 lr: 0.000097 grad: 0.1148 (0.1142) loss: 0.8938 (0.8954) time: 0.1426 data: 0.0577 max mem: 8233 +Train: [34] [5900/6250] eta: 0:00:57 lr: 0.000097 grad: 0.1193 (0.1143) loss: 0.8897 (0.8953) time: 0.1478 data: 0.0617 max mem: 8233 +Train: [34] [6000/6250] eta: 0:00:40 lr: 0.000097 grad: 0.1220 (0.1144) loss: 0.8874 (0.8953) time: 0.1775 data: 0.0995 max mem: 8233 +Train: [34] [6100/6250] eta: 0:00:24 lr: 0.000097 grad: 0.1100 (0.1145) loss: 0.8915 (0.8953) time: 0.1567 data: 0.0679 max mem: 8233 +Train: [34] [6200/6250] eta: 0:00:08 lr: 0.000097 grad: 0.1138 (0.1145) loss: 0.8930 (0.8952) time: 0.2915 data: 0.2058 max mem: 8233 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.1073 (0.1144) loss: 0.8927 (0.8952) time: 0.1986 data: 0.1136 max mem: 8233 +Train: [34] Total time: 0:17:08 (0.1645 s / it) +Averaged stats: lr: 0.000097 grad: 0.1073 (0.1144) loss: 0.8927 (0.8952) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:06:17 loss: 0.9126 (0.9126) time: 6.0943 data: 6.0670 max mem: 8233 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.9030 (0.9034) time: 0.1261 data: 0.1054 max mem: 8233 +Eval (hcp-train-subset): [34] Total time: 0:00:14 (0.2326 s / it) +Averaged stats (hcp-train-subset): loss: 0.9030 (0.9034) +Making plots (hcp-train-subset): example=16 +Eval (hcp-val): [34] [ 0/62] eta: 0:06:25 loss: 0.8987 (0.8987) time: 6.2159 data: 6.1770 max mem: 8233 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8998 (0.8996) time: 0.1122 data: 0.0906 max mem: 8233 +Eval (hcp-val): [34] Total time: 0:00:14 (0.2331 s / it) +Averaged stats (hcp-val): loss: 0.8998 (0.8996) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 8:48:55 lr: 0.000097 grad: 0.1195 (0.1195) loss: 0.9173 (0.9173) time: 5.0776 data: 4.7807 max mem: 8233 +Train: [35] [ 100/6250] eta: 0:22:34 lr: 0.000097 grad: 0.1165 (0.1258) loss: 0.8929 (0.8981) time: 0.1458 data: 0.0395 max mem: 8233 +Train: [35] [ 200/6250] eta: 0:19:46 lr: 0.000097 grad: 0.1166 (0.1228) loss: 0.8949 (0.8958) time: 0.1788 data: 0.0670 max mem: 8233 +Train: [35] [ 300/6250] eta: 0:18:32 lr: 0.000097 grad: 0.1216 (0.1210) loss: 0.8948 (0.8947) time: 0.1615 data: 0.0641 max mem: 8233 +Train: [35] [ 400/6250] eta: 0:17:52 lr: 0.000097 grad: 0.1049 (0.1194) loss: 0.8952 (0.8938) time: 0.1577 data: 0.0800 max mem: 8233 +Train: [35] [ 500/6250] eta: 0:17:14 lr: 0.000097 grad: 0.1111 (0.1191) loss: 0.8943 (0.8933) time: 0.1677 data: 0.0758 max mem: 8233 +Train: [35] [ 600/6250] eta: 0:16:38 lr: 0.000097 grad: 0.1122 (0.1190) loss: 0.8967 (0.8928) time: 0.1715 data: 0.0855 max mem: 8233 +Train: [35] [ 700/6250] eta: 0:16:11 lr: 0.000096 grad: 0.1208 (0.1190) loss: 0.8877 (0.8922) time: 0.1576 data: 0.0715 max mem: 8233 +Train: [35] [ 800/6250] eta: 0:15:46 lr: 0.000096 grad: 0.1233 (0.1194) loss: 0.8898 (0.8919) time: 0.1763 data: 0.0941 max mem: 8233 +Train: [35] [ 900/6250] eta: 0:15:34 lr: 0.000096 grad: 0.1145 (0.1194) loss: 0.8937 (0.8917) time: 0.2075 data: 0.1231 max mem: 8233 +Train: [35] [1000/6250] eta: 0:15:05 lr: 0.000096 grad: 0.1154 (0.1193) loss: 0.8894 (0.8917) time: 0.1407 data: 0.0603 max mem: 8233 +Train: [35] [1100/6250] eta: 0:14:40 lr: 0.000096 grad: 0.1163 (0.1193) loss: 0.8890 (0.8917) time: 0.1943 data: 0.1145 max mem: 8233 +Train: [35] [1200/6250] eta: 0:14:26 lr: 0.000096 grad: 0.1242 (0.1193) loss: 0.8877 (0.8916) time: 0.1689 data: 0.0833 max mem: 8233 +Train: [35] [1300/6250] eta: 0:14:04 lr: 0.000096 grad: 0.1139 (0.1191) loss: 0.8940 (0.8916) time: 0.1470 data: 0.0598 max mem: 8233 +Train: [35] [1400/6250] eta: 0:13:43 lr: 0.000096 grad: 0.1170 (0.1190) loss: 0.8885 (0.8916) time: 0.1334 data: 0.0407 max mem: 8233 +Train: [35] [1500/6250] eta: 0:13:20 lr: 0.000096 grad: 0.1215 (0.1188) loss: 0.8883 (0.8917) time: 0.1503 data: 0.0615 max mem: 8233 +Train: [35] [1600/6250] eta: 0:12:59 lr: 0.000096 grad: 0.1118 (0.1187) loss: 0.8921 (0.8917) time: 0.1246 data: 0.0360 max mem: 8233 +Train: [35] [1700/6250] eta: 0:12:39 lr: 0.000096 grad: 0.1108 (0.1187) loss: 0.8935 (0.8916) time: 0.1603 data: 0.0655 max mem: 8233 +Train: [35] [1800/6250] eta: 0:12:20 lr: 0.000096 grad: 0.1089 (0.1189) loss: 0.8880 (0.8916) time: 0.1574 data: 0.0737 max mem: 8233 +Train: [35] [1900/6250] eta: 0:12:06 lr: 0.000096 grad: 0.1225 (0.1189) loss: 0.8951 (0.8916) time: 0.0955 data: 0.0002 max mem: 8233 +Train: [35] [2000/6250] eta: 0:11:45 lr: 0.000096 grad: 0.1161 (0.1189) loss: 0.8878 (0.8915) time: 0.1504 data: 0.0733 max mem: 8233 +Train: [35] [2100/6250] eta: 0:11:26 lr: 0.000096 grad: 0.1149 (0.1191) loss: 0.8896 (0.8915) time: 0.1654 data: 0.0846 max mem: 8233 +Train: [35] [2200/6250] eta: 0:11:09 lr: 0.000096 grad: 0.1120 (0.1190) loss: 0.8923 (0.8915) time: 0.1604 data: 0.0897 max mem: 8233 +Train: [35] [2300/6250] eta: 0:10:50 lr: 0.000096 grad: 0.1140 (0.1191) loss: 0.8947 (0.8915) time: 0.1402 data: 0.0627 max mem: 8233 +Train: [35] [2400/6250] eta: 0:10:32 lr: 0.000096 grad: 0.1138 (0.1190) loss: 0.8928 (0.8915) time: 0.1256 data: 0.0304 max mem: 8233 +Train: [35] [2500/6250] eta: 0:10:12 lr: 0.000096 grad: 0.1143 (0.1191) loss: 0.8962 (0.8916) time: 0.1340 data: 0.0631 max mem: 8233 +Train: [35] [2600/6250] eta: 0:09:53 lr: 0.000096 grad: 0.1117 (0.1191) loss: 0.8968 (0.8917) time: 0.1332 data: 0.0532 max mem: 8233 +Train: [35] [2700/6250] eta: 0:09:39 lr: 0.000096 grad: 0.1130 (0.1190) loss: 0.8968 (0.8918) time: 0.1944 data: 0.1302 max mem: 8233 +Train: [35] [2800/6250] eta: 0:09:23 lr: 0.000096 grad: 0.1150 (0.1190) loss: 0.8958 (0.8920) time: 0.1552 data: 0.0818 max mem: 8233 +Train: [35] [2900/6250] eta: 0:09:07 lr: 0.000096 grad: 0.1107 (0.1189) loss: 0.8925 (0.8920) time: 0.1524 data: 0.0787 max mem: 8233 +Train: [35] [3000/6250] eta: 0:08:53 lr: 0.000096 grad: 0.1158 (0.1188) loss: 0.8886 (0.8920) time: 0.1877 data: 0.1073 max mem: 8233 +Train: [35] [3100/6250] eta: 0:08:38 lr: 0.000096 grad: 0.1099 (0.1188) loss: 0.8932 (0.8921) time: 0.1753 data: 0.0905 max mem: 8233 +Train: [35] [3200/6250] eta: 0:08:24 lr: 0.000096 grad: 0.1145 (0.1188) loss: 0.8941 (0.8921) time: 0.1848 data: 0.1051 max mem: 8233 +Train: [35] [3300/6250] eta: 0:08:07 lr: 0.000096 grad: 0.1085 (0.1187) loss: 0.8941 (0.8922) time: 0.1586 data: 0.0770 max mem: 8233 +Train: [35] [3400/6250] eta: 0:07:52 lr: 0.000096 grad: 0.1086 (0.1186) loss: 0.8917 (0.8922) time: 0.2159 data: 0.1420 max mem: 8233 +Train: [35] [3500/6250] eta: 0:07:35 lr: 0.000096 grad: 0.1136 (0.1186) loss: 0.8914 (0.8922) time: 0.1526 data: 0.0571 max mem: 8233 +Train: [35] [3600/6250] eta: 0:07:18 lr: 0.000096 grad: 0.1100 (0.1188) loss: 0.8886 (0.8922) time: 0.1621 data: 0.0822 max mem: 8233 +Train: [35] [3700/6250] eta: 0:07:01 lr: 0.000096 grad: 0.1067 (0.1188) loss: 0.8948 (0.8922) time: 0.1456 data: 0.0739 max mem: 8233 +Train: [35] [3800/6250] eta: 0:06:45 lr: 0.000096 grad: 0.1111 (0.1189) loss: 0.8913 (0.8922) time: 0.1907 data: 0.1122 max mem: 8233 +Train: [35] [3900/6250] eta: 0:06:28 lr: 0.000096 grad: 0.1109 (0.1188) loss: 0.8935 (0.8922) time: 0.1366 data: 0.0547 max mem: 8233 +Train: [35] [4000/6250] eta: 0:06:11 lr: 0.000096 grad: 0.1069 (0.1188) loss: 0.8957 (0.8922) time: 0.1552 data: 0.0763 max mem: 8233 +Train: [35] [4100/6250] eta: 0:05:56 lr: 0.000096 grad: 0.1099 (0.1188) loss: 0.8907 (0.8922) time: 0.0916 data: 0.0002 max mem: 8233 +Train: [35] [4200/6250] eta: 0:05:39 lr: 0.000096 grad: 0.1069 (0.1187) loss: 0.8988 (0.8922) time: 0.1860 data: 0.1202 max mem: 8233 +Train: [35] [4300/6250] eta: 0:05:22 lr: 0.000095 grad: 0.1109 (0.1185) loss: 0.8948 (0.8922) time: 0.1257 data: 0.0548 max mem: 8233 +Train: [35] [4400/6250] eta: 0:05:06 lr: 0.000095 grad: 0.1148 (0.1184) loss: 0.8933 (0.8923) time: 0.1434 data: 0.0727 max mem: 8233 +Train: [35] [4500/6250] eta: 0:04:49 lr: 0.000095 grad: 0.1147 (0.1183) loss: 0.8915 (0.8923) time: 0.1570 data: 0.0688 max mem: 8233 +Train: [35] [4600/6250] eta: 0:04:33 lr: 0.000095 grad: 0.1064 (0.1181) loss: 0.8918 (0.8923) time: 0.1970 data: 0.1170 max mem: 8233 +Train: [35] [4700/6250] eta: 0:04:16 lr: 0.000095 grad: 0.1068 (0.1180) loss: 0.8931 (0.8923) time: 0.1682 data: 0.0896 max mem: 8233 +Train: [35] [4800/6250] eta: 0:04:00 lr: 0.000095 grad: 0.1125 (0.1179) loss: 0.8927 (0.8923) time: 0.1532 data: 0.0657 max mem: 8233 +Train: [35] [4900/6250] eta: 0:03:43 lr: 0.000095 grad: 0.1060 (0.1177) loss: 0.8937 (0.8923) time: 0.1643 data: 0.0783 max mem: 8233 +Train: [35] [5000/6250] eta: 0:03:26 lr: 0.000095 grad: 0.1053 (0.1176) loss: 0.8960 (0.8922) time: 0.1582 data: 0.0777 max mem: 8233 +Train: [35] [5100/6250] eta: 0:03:10 lr: 0.000095 grad: 0.1114 (0.1175) loss: 0.8957 (0.8923) time: 0.1305 data: 0.0508 max mem: 8233 +Train: [35] [5200/6250] eta: 0:02:53 lr: 0.000095 grad: 0.1077 (0.1174) loss: 0.8943 (0.8923) time: 0.1533 data: 0.0704 max mem: 8233 +Train: [35] [5300/6250] eta: 0:02:36 lr: 0.000095 grad: 0.1056 (0.1172) loss: 0.8965 (0.8923) time: 0.1546 data: 0.0658 max mem: 8233 +Train: [35] [5400/6250] eta: 0:02:20 lr: 0.000095 grad: 0.1076 (0.1172) loss: 0.8927 (0.8924) time: 0.1538 data: 0.0646 max mem: 8233 +Train: [35] [5500/6250] eta: 0:02:03 lr: 0.000095 grad: 0.1120 (0.1171) loss: 0.8919 (0.8924) time: 0.1437 data: 0.0622 max mem: 8233 +Train: [35] [5600/6250] eta: 0:01:46 lr: 0.000095 grad: 0.1079 (0.1170) loss: 0.8972 (0.8925) time: 0.1225 data: 0.0384 max mem: 8233 +Train: [35] [5700/6250] eta: 0:01:30 lr: 0.000095 grad: 0.1152 (0.1169) loss: 0.8930 (0.8925) time: 0.1240 data: 0.0205 max mem: 8233 +Train: [35] [5800/6250] eta: 0:01:13 lr: 0.000095 grad: 0.1117 (0.1168) loss: 0.8919 (0.8925) time: 0.1567 data: 0.0781 max mem: 8233 +Train: [35] [5900/6250] eta: 0:00:57 lr: 0.000095 grad: 0.1042 (0.1168) loss: 0.8979 (0.8926) time: 0.1226 data: 0.0257 max mem: 8233 +Train: [35] [6000/6250] eta: 0:00:40 lr: 0.000095 grad: 0.1138 (0.1167) loss: 0.8973 (0.8926) time: 0.1718 data: 0.0938 max mem: 8233 +Train: [35] [6100/6250] eta: 0:00:24 lr: 0.000095 grad: 0.1030 (0.1166) loss: 0.8919 (0.8926) time: 0.1635 data: 0.0865 max mem: 8233 +Train: [35] [6200/6250] eta: 0:00:08 lr: 0.000095 grad: 0.1107 (0.1166) loss: 0.8915 (0.8926) time: 0.1625 data: 0.0862 max mem: 8233 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.1194 (0.1167) loss: 0.8929 (0.8926) time: 0.1493 data: 0.0658 max mem: 8233 +Train: [35] Total time: 0:17:07 (0.1644 s / it) +Averaged stats: lr: 0.000095 grad: 0.1194 (0.1167) loss: 0.8929 (0.8926) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:06:02 loss: 0.9090 (0.9090) time: 5.8455 data: 5.8186 max mem: 8233 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.9029 (0.9022) time: 0.1236 data: 0.1031 max mem: 8233 +Eval (hcp-train-subset): [35] Total time: 0:00:14 (0.2301 s / it) +Averaged stats (hcp-train-subset): loss: 0.9029 (0.9022) +Eval (hcp-val): [35] [ 0/62] eta: 0:04:17 loss: 0.8937 (0.8937) time: 4.1529 data: 4.0539 max mem: 8233 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8973 (0.8981) time: 0.1438 data: 0.1231 max mem: 8233 +Eval (hcp-val): [35] Total time: 0:00:14 (0.2269 s / it) +Averaged stats (hcp-val): loss: 0.8973 (0.8981) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 9:53:15 lr: 0.000095 grad: 0.1073 (0.1073) loss: 0.9178 (0.9178) time: 5.6953 data: 5.3811 max mem: 8233 +Train: [36] [ 100/6250] eta: 0:23:38 lr: 0.000095 grad: 0.1131 (0.1321) loss: 0.8926 (0.8970) time: 0.1975 data: 0.1081 max mem: 8233 +Train: [36] [ 200/6250] eta: 0:20:21 lr: 0.000095 grad: 0.1069 (0.1251) loss: 0.8998 (0.8964) time: 0.1650 data: 0.0902 max mem: 8233 +Train: [36] [ 300/6250] eta: 0:18:50 lr: 0.000095 grad: 0.1084 (0.1209) loss: 0.8972 (0.8959) time: 0.1851 data: 0.1090 max mem: 8233 +Train: [36] [ 400/6250] eta: 0:17:41 lr: 0.000095 grad: 0.1055 (0.1182) loss: 0.8946 (0.8962) time: 0.1632 data: 0.0707 max mem: 8233 +Train: [36] [ 500/6250] eta: 0:16:49 lr: 0.000095 grad: 0.1046 (0.1170) loss: 0.8953 (0.8962) time: 0.1580 data: 0.0728 max mem: 8233 +Train: [36] [ 600/6250] eta: 0:16:12 lr: 0.000095 grad: 0.1007 (0.1168) loss: 0.8978 (0.8962) time: 0.1522 data: 0.0657 max mem: 8233 +Train: [36] [ 700/6250] eta: 0:15:37 lr: 0.000095 grad: 0.1051 (0.1154) loss: 0.8961 (0.8963) time: 0.1314 data: 0.0317 max mem: 8233 +Train: [36] [ 800/6250] eta: 0:15:15 lr: 0.000095 grad: 0.1029 (0.1150) loss: 0.8957 (0.8962) time: 0.1727 data: 0.0918 max mem: 8233 +Train: [36] [ 900/6250] eta: 0:15:05 lr: 0.000095 grad: 0.1087 (0.1145) loss: 0.8943 (0.8961) time: 0.1771 data: 0.0943 max mem: 8233 +Train: [36] [1000/6250] eta: 0:14:37 lr: 0.000095 grad: 0.1148 (0.1143) loss: 0.9002 (0.8961) time: 0.1416 data: 0.0625 max mem: 8233 +Train: [36] [1100/6250] eta: 0:14:12 lr: 0.000095 grad: 0.1026 (0.1149) loss: 0.8951 (0.8962) time: 0.1631 data: 0.0679 max mem: 8233 +Train: [36] [1200/6250] eta: 0:13:50 lr: 0.000095 grad: 0.1039 (0.1145) loss: 0.8921 (0.8961) time: 0.1543 data: 0.0758 max mem: 8233 +Train: [36] [1300/6250] eta: 0:13:31 lr: 0.000095 grad: 0.1133 (0.1147) loss: 0.8929 (0.8959) time: 0.1487 data: 0.0714 max mem: 8233 +Train: [36] [1400/6250] eta: 0:13:13 lr: 0.000095 grad: 0.1056 (0.1143) loss: 0.8961 (0.8959) time: 0.1229 data: 0.0287 max mem: 8233 +Train: [36] [1500/6250] eta: 0:12:53 lr: 0.000095 grad: 0.1138 (0.1143) loss: 0.8921 (0.8957) time: 0.1592 data: 0.0744 max mem: 8233 +Train: [36] [1600/6250] eta: 0:12:33 lr: 0.000094 grad: 0.1109 (0.1142) loss: 0.8895 (0.8956) time: 0.1453 data: 0.0561 max mem: 8233 +Train: [36] [1700/6250] eta: 0:12:17 lr: 0.000094 grad: 0.1051 (0.1140) loss: 0.9046 (0.8957) time: 0.1656 data: 0.0888 max mem: 8233 +Train: [36] [1800/6250] eta: 0:12:03 lr: 0.000094 grad: 0.1104 (0.1140) loss: 0.8986 (0.8957) time: 0.1892 data: 0.1027 max mem: 8233 +Train: [36] [1900/6250] eta: 0:11:47 lr: 0.000094 grad: 0.1079 (0.1140) loss: 0.8961 (0.8956) time: 0.1677 data: 0.0864 max mem: 8233 +Train: [36] [2000/6250] eta: 0:11:31 lr: 0.000094 grad: 0.1150 (0.1142) loss: 0.8999 (0.8957) time: 0.1569 data: 0.0846 max mem: 8233 +Train: [36] [2100/6250] eta: 0:11:19 lr: 0.000094 grad: 0.1109 (0.1142) loss: 0.8977 (0.8957) time: 0.2613 data: 0.1803 max mem: 8233 +Train: [36] [2200/6250] eta: 0:11:00 lr: 0.000094 grad: 0.1121 (0.1140) loss: 0.8987 (0.8958) time: 0.1717 data: 0.0914 max mem: 8233 +Train: [36] [2300/6250] eta: 0:10:46 lr: 0.000094 grad: 0.1174 (0.1142) loss: 0.8927 (0.8958) time: 0.1350 data: 0.0335 max mem: 8233 +Train: [36] [2400/6250] eta: 0:10:29 lr: 0.000094 grad: 0.1039 (0.1139) loss: 0.8941 (0.8957) time: 0.1704 data: 0.0888 max mem: 8233 +Train: [36] [2500/6250] eta: 0:10:12 lr: 0.000094 grad: 0.1067 (0.1139) loss: 0.8958 (0.8957) time: 0.1547 data: 0.0708 max mem: 8233 +Train: [36] [2600/6250] eta: 0:09:54 lr: 0.000094 grad: 0.1095 (0.1139) loss: 0.8933 (0.8957) time: 0.0990 data: 0.0037 max mem: 8233 +Train: [36] [2700/6250] eta: 0:09:37 lr: 0.000094 grad: 0.1123 (0.1138) loss: 0.8925 (0.8956) time: 0.1639 data: 0.0845 max mem: 8233 +Train: [36] [2800/6250] eta: 0:09:22 lr: 0.000094 grad: 0.1139 (0.1139) loss: 0.8898 (0.8956) time: 0.1664 data: 0.0878 max mem: 8233 +Train: [36] [2900/6250] eta: 0:09:06 lr: 0.000094 grad: 0.1073 (0.1140) loss: 0.8953 (0.8955) time: 0.1737 data: 0.0939 max mem: 8233 +Train: [36] [3000/6250] eta: 0:08:50 lr: 0.000094 grad: 0.1084 (0.1141) loss: 0.8941 (0.8955) time: 0.1734 data: 0.0868 max mem: 8233 +Train: [36] [3100/6250] eta: 0:08:36 lr: 0.000094 grad: 0.1185 (0.1142) loss: 0.8918 (0.8954) time: 0.2230 data: 0.1501 max mem: 8233 +Train: [36] [3200/6250] eta: 0:08:19 lr: 0.000094 grad: 0.1040 (0.1143) loss: 0.8867 (0.8953) time: 0.1518 data: 0.0678 max mem: 8233 +Train: [36] [3300/6250] eta: 0:08:02 lr: 0.000094 grad: 0.1128 (0.1144) loss: 0.8904 (0.8952) time: 0.1603 data: 0.0777 max mem: 8233 +Train: [36] [3400/6250] eta: 0:07:46 lr: 0.000094 grad: 0.1179 (0.1145) loss: 0.8939 (0.8951) time: 0.1738 data: 0.0867 max mem: 8233 +Train: [36] [3500/6250] eta: 0:07:28 lr: 0.000094 grad: 0.1114 (0.1146) loss: 0.8994 (0.8951) time: 0.1529 data: 0.0693 max mem: 8233 +Train: [36] [3600/6250] eta: 0:07:11 lr: 0.000094 grad: 0.1151 (0.1146) loss: 0.8890 (0.8950) time: 0.1525 data: 0.0673 max mem: 8233 +Train: [36] [3700/6250] eta: 0:06:55 lr: 0.000094 grad: 0.1144 (0.1148) loss: 0.8953 (0.8949) time: 0.1712 data: 0.0940 max mem: 8233 +Train: [36] [3800/6250] eta: 0:06:38 lr: 0.000094 grad: 0.1116 (0.1147) loss: 0.8921 (0.8949) time: 0.1578 data: 0.0754 max mem: 8233 +Train: [36] [3900/6250] eta: 0:06:22 lr: 0.000094 grad: 0.1180 (0.1148) loss: 0.8916 (0.8948) time: 0.1426 data: 0.0591 max mem: 8233 +Train: [36] [4000/6250] eta: 0:06:05 lr: 0.000094 grad: 0.1139 (0.1149) loss: 0.8921 (0.8948) time: 0.1319 data: 0.0458 max mem: 8233 +Train: [36] [4100/6250] eta: 0:05:49 lr: 0.000094 grad: 0.1159 (0.1150) loss: 0.8941 (0.8947) time: 0.2170 data: 0.1307 max mem: 8233 +Train: [36] [4200/6250] eta: 0:05:32 lr: 0.000094 grad: 0.1139 (0.1149) loss: 0.8924 (0.8947) time: 0.1786 data: 0.0980 max mem: 8233 +Train: [36] [4300/6250] eta: 0:05:16 lr: 0.000094 grad: 0.1114 (0.1150) loss: 0.8938 (0.8947) time: 0.1733 data: 0.0868 max mem: 8233 +Train: [36] [4400/6250] eta: 0:05:00 lr: 0.000094 grad: 0.1129 (0.1150) loss: 0.8951 (0.8947) time: 0.1790 data: 0.1036 max mem: 8233 +Train: [36] [4500/6250] eta: 0:04:44 lr: 0.000094 grad: 0.1063 (0.1149) loss: 0.9009 (0.8947) time: 0.1952 data: 0.1175 max mem: 8233 +Train: [36] [4600/6250] eta: 0:04:27 lr: 0.000094 grad: 0.1163 (0.1148) loss: 0.8901 (0.8947) time: 0.1606 data: 0.0775 max mem: 8233 +Train: [36] [4700/6250] eta: 0:04:11 lr: 0.000094 grad: 0.1074 (0.1147) loss: 0.8976 (0.8947) time: 0.1637 data: 0.0761 max mem: 8233 +Train: [36] [4800/6250] eta: 0:03:55 lr: 0.000094 grad: 0.1060 (0.1148) loss: 0.8949 (0.8946) time: 0.1300 data: 0.0504 max mem: 8233 +Train: [36] [4900/6250] eta: 0:03:39 lr: 0.000094 grad: 0.1140 (0.1148) loss: 0.8970 (0.8946) time: 0.1579 data: 0.0713 max mem: 8233 +Train: [36] [5000/6250] eta: 0:03:23 lr: 0.000094 grad: 0.1142 (0.1148) loss: 0.8936 (0.8946) time: 0.1645 data: 0.0832 max mem: 8233 +Train: [36] [5100/6250] eta: 0:03:06 lr: 0.000093 grad: 0.1090 (0.1148) loss: 0.8940 (0.8946) time: 0.1704 data: 0.0956 max mem: 8233 +Train: [36] [5200/6250] eta: 0:02:50 lr: 0.000093 grad: 0.1052 (0.1147) loss: 0.8921 (0.8946) time: 0.1329 data: 0.0407 max mem: 8233 +Train: [36] [5300/6250] eta: 0:02:33 lr: 0.000093 grad: 0.1153 (0.1147) loss: 0.8975 (0.8946) time: 0.1490 data: 0.0570 max mem: 8233 +Train: [36] [5400/6250] eta: 0:02:17 lr: 0.000093 grad: 0.1094 (0.1147) loss: 0.8935 (0.8946) time: 0.1612 data: 0.0771 max mem: 8233 +Train: [36] [5500/6250] eta: 0:02:01 lr: 0.000093 grad: 0.1042 (0.1146) loss: 0.8931 (0.8946) time: 0.1539 data: 0.0691 max mem: 8233 +Train: [36] [5600/6250] eta: 0:01:45 lr: 0.000093 grad: 0.1042 (0.1145) loss: 0.8931 (0.8946) time: 0.1585 data: 0.0950 max mem: 8233 +Train: [36] [5700/6250] eta: 0:01:29 lr: 0.000093 grad: 0.1149 (0.1146) loss: 0.8991 (0.8946) time: 0.1415 data: 0.0555 max mem: 8233 +Train: [36] [5800/6250] eta: 0:01:12 lr: 0.000093 grad: 0.1061 (0.1145) loss: 0.8915 (0.8946) time: 0.1423 data: 0.0581 max mem: 8233 +Train: [36] [5900/6250] eta: 0:00:56 lr: 0.000093 grad: 0.1089 (0.1145) loss: 0.8998 (0.8947) time: 0.1722 data: 0.1088 max mem: 8233 +Train: [36] [6000/6250] eta: 0:00:40 lr: 0.000093 grad: 0.1087 (0.1145) loss: 0.8937 (0.8947) time: 0.1500 data: 0.0692 max mem: 8233 +Train: [36] [6100/6250] eta: 0:00:24 lr: 0.000093 grad: 0.1005 (0.1144) loss: 0.8942 (0.8947) time: 0.1520 data: 0.0933 max mem: 8233 +Train: [36] [6200/6250] eta: 0:00:08 lr: 0.000093 grad: 0.1040 (0.1144) loss: 0.8950 (0.8947) time: 0.1380 data: 0.0671 max mem: 8233 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.1008 (0.1144) loss: 0.8987 (0.8947) time: 0.1498 data: 0.0744 max mem: 8233 +Train: [36] Total time: 0:16:52 (0.1620 s / it) +Averaged stats: lr: 0.000093 grad: 0.1008 (0.1144) loss: 0.8987 (0.8947) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:05:29 loss: 0.9094 (0.9094) time: 5.3113 data: 5.2846 max mem: 8233 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.9017 (0.9017) time: 0.1305 data: 0.1098 max mem: 8233 +Eval (hcp-train-subset): [36] Total time: 0:00:14 (0.2264 s / it) +Averaged stats (hcp-train-subset): loss: 0.9017 (0.9017) +Eval (hcp-val): [36] [ 0/62] eta: 0:06:05 loss: 0.8921 (0.8921) time: 5.8977 data: 5.8707 max mem: 8233 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8974 (0.8976) time: 0.1246 data: 0.0995 max mem: 8233 +Eval (hcp-val): [36] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-val): loss: 0.8974 (0.8976) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 7:17:55 lr: 0.000093 grad: 0.1798 (0.1798) loss: 0.9340 (0.9340) time: 4.2041 data: 3.8665 max mem: 8233 +Train: [37] [ 100/6250] eta: 0:22:47 lr: 0.000093 grad: 0.1125 (0.1209) loss: 0.9028 (0.9005) time: 0.1509 data: 0.0550 max mem: 8233 +Train: [37] [ 200/6250] eta: 0:20:03 lr: 0.000093 grad: 0.1030 (0.1157) loss: 0.9020 (0.8995) time: 0.1630 data: 0.0741 max mem: 8233 +Train: [37] [ 300/6250] eta: 0:18:40 lr: 0.000093 grad: 0.1121 (0.1145) loss: 0.8950 (0.8982) time: 0.1588 data: 0.0696 max mem: 8233 +Train: [37] [ 400/6250] eta: 0:17:39 lr: 0.000093 grad: 0.1037 (0.1130) loss: 0.8946 (0.8977) time: 0.1440 data: 0.0520 max mem: 8233 +Train: [37] [ 500/6250] eta: 0:17:00 lr: 0.000093 grad: 0.1032 (0.1120) loss: 0.8945 (0.8971) time: 0.1852 data: 0.0970 max mem: 8233 +Train: [37] [ 600/6250] eta: 0:16:23 lr: 0.000093 grad: 0.1048 (0.1118) loss: 0.8963 (0.8965) time: 0.1397 data: 0.0475 max mem: 8233 +Train: [37] [ 700/6250] eta: 0:15:56 lr: 0.000093 grad: 0.1073 (0.1116) loss: 0.8929 (0.8963) time: 0.1446 data: 0.0557 max mem: 8233 +Train: [37] [ 800/6250] eta: 0:15:31 lr: 0.000093 grad: 0.1019 (0.1112) loss: 0.8940 (0.8960) time: 0.1604 data: 0.0762 max mem: 8233 +Train: [37] [ 900/6250] eta: 0:15:20 lr: 0.000093 grad: 0.0993 (0.1109) loss: 0.8945 (0.8961) time: 0.1273 data: 0.0416 max mem: 8233 +Train: [37] [1000/6250] eta: 0:14:58 lr: 0.000093 grad: 0.1016 (0.1109) loss: 0.8982 (0.8961) time: 0.1958 data: 0.1227 max mem: 8233 +Train: [37] [1100/6250] eta: 0:14:28 lr: 0.000093 grad: 0.1202 (0.1105) loss: 0.8946 (0.8961) time: 0.1473 data: 0.0778 max mem: 8233 +Train: [37] [1200/6250] eta: 0:14:13 lr: 0.000093 grad: 0.1047 (0.1104) loss: 0.8933 (0.8959) time: 0.1664 data: 0.0721 max mem: 8233 +Train: [37] [1300/6250] eta: 0:13:53 lr: 0.000093 grad: 0.1107 (0.1102) loss: 0.8947 (0.8958) time: 0.1531 data: 0.0682 max mem: 8233 +Train: [37] [1400/6250] eta: 0:13:37 lr: 0.000093 grad: 0.1129 (0.1104) loss: 0.8918 (0.8957) time: 0.1572 data: 0.0687 max mem: 8233 +Train: [37] [1500/6250] eta: 0:13:18 lr: 0.000093 grad: 0.1140 (0.1107) loss: 0.8913 (0.8956) time: 0.1520 data: 0.0678 max mem: 8233 +Train: [37] [1600/6250] eta: 0:12:57 lr: 0.000093 grad: 0.1071 (0.1107) loss: 0.8938 (0.8956) time: 0.1497 data: 0.0634 max mem: 8233 +Train: [37] [1700/6250] eta: 0:12:37 lr: 0.000093 grad: 0.1067 (0.1107) loss: 0.8949 (0.8955) time: 0.1646 data: 0.0808 max mem: 8233 +Train: [37] [1800/6250] eta: 0:12:18 lr: 0.000093 grad: 0.1078 (0.1109) loss: 0.8894 (0.8954) time: 0.1494 data: 0.0753 max mem: 8233 +Train: [37] [1900/6250] eta: 0:12:00 lr: 0.000093 grad: 0.1059 (0.1110) loss: 0.8926 (0.8953) time: 0.1844 data: 0.0897 max mem: 8233 +Train: [37] [2000/6250] eta: 0:11:44 lr: 0.000093 grad: 0.1058 (0.1111) loss: 0.8957 (0.8952) time: 0.1654 data: 0.0887 max mem: 8233 +Train: [37] [2100/6250] eta: 0:11:28 lr: 0.000093 grad: 0.1079 (0.1113) loss: 0.8900 (0.8950) time: 0.2118 data: 0.1356 max mem: 8233 +Train: [37] [2200/6250] eta: 0:11:08 lr: 0.000093 grad: 0.1095 (0.1115) loss: 0.8940 (0.8949) time: 0.1551 data: 0.0805 max mem: 8233 +Train: [37] [2300/6250] eta: 0:10:50 lr: 0.000092 grad: 0.1074 (0.1117) loss: 0.8936 (0.8948) time: 0.1483 data: 0.0636 max mem: 8233 +Train: [37] [2400/6250] eta: 0:10:33 lr: 0.000092 grad: 0.1197 (0.1120) loss: 0.8870 (0.8947) time: 0.1490 data: 0.0617 max mem: 8233 +Train: [37] [2500/6250] eta: 0:10:16 lr: 0.000092 grad: 0.1059 (0.1120) loss: 0.8910 (0.8946) time: 0.1253 data: 0.0452 max mem: 8233 +Train: [37] [2600/6250] eta: 0:09:59 lr: 0.000092 grad: 0.1185 (0.1121) loss: 0.8926 (0.8945) time: 0.1529 data: 0.0737 max mem: 8233 +Train: [37] [2700/6250] eta: 0:09:41 lr: 0.000092 grad: 0.1105 (0.1123) loss: 0.8896 (0.8944) time: 0.1578 data: 0.0783 max mem: 8233 +Train: [37] [2800/6250] eta: 0:09:26 lr: 0.000092 grad: 0.1157 (0.1123) loss: 0.8952 (0.8944) time: 0.1598 data: 0.0845 max mem: 8233 +Train: [37] [2900/6250] eta: 0:09:08 lr: 0.000092 grad: 0.1071 (0.1124) loss: 0.8980 (0.8944) time: 0.1528 data: 0.0786 max mem: 8233 +Train: [37] [3000/6250] eta: 0:08:51 lr: 0.000092 grad: 0.1080 (0.1124) loss: 0.8913 (0.8944) time: 0.1760 data: 0.0826 max mem: 8233 +Train: [37] [3100/6250] eta: 0:08:35 lr: 0.000092 grad: 0.1096 (0.1125) loss: 0.8960 (0.8943) time: 0.1459 data: 0.0664 max mem: 8233 +Train: [37] [3200/6250] eta: 0:08:20 lr: 0.000092 grad: 0.1045 (0.1124) loss: 0.8988 (0.8944) time: 0.1948 data: 0.1066 max mem: 8233 +Train: [37] [3300/6250] eta: 0:08:04 lr: 0.000092 grad: 0.1105 (0.1123) loss: 0.9016 (0.8944) time: 0.1610 data: 0.0785 max mem: 8233 +Train: [37] [3400/6250] eta: 0:07:47 lr: 0.000092 grad: 0.1063 (0.1123) loss: 0.8987 (0.8945) time: 0.1482 data: 0.0601 max mem: 8233 +Train: [37] [3500/6250] eta: 0:07:29 lr: 0.000092 grad: 0.1181 (0.1124) loss: 0.8948 (0.8945) time: 0.1281 data: 0.0406 max mem: 8233 +Train: [37] [3600/6250] eta: 0:07:12 lr: 0.000092 grad: 0.1092 (0.1123) loss: 0.8927 (0.8945) time: 0.1490 data: 0.0654 max mem: 8233 +Train: [37] [3700/6250] eta: 0:06:55 lr: 0.000092 grad: 0.1130 (0.1124) loss: 0.8939 (0.8946) time: 0.1474 data: 0.0531 max mem: 8233 +Train: [37] [3800/6250] eta: 0:06:39 lr: 0.000092 grad: 0.1048 (0.1124) loss: 0.8977 (0.8946) time: 0.1593 data: 0.0724 max mem: 8233 +Train: [37] [3900/6250] eta: 0:06:23 lr: 0.000092 grad: 0.1029 (0.1123) loss: 0.9011 (0.8946) time: 0.2482 data: 0.1762 max mem: 8233 +Train: [37] [4000/6250] eta: 0:06:06 lr: 0.000092 grad: 0.1026 (0.1122) loss: 0.8949 (0.8946) time: 0.1447 data: 0.0644 max mem: 8233 +Train: [37] [4100/6250] eta: 0:05:49 lr: 0.000092 grad: 0.1086 (0.1122) loss: 0.8927 (0.8946) time: 0.1413 data: 0.0551 max mem: 8233 +Train: [37] [4200/6250] eta: 0:05:33 lr: 0.000092 grad: 0.1103 (0.1122) loss: 0.8979 (0.8946) time: 0.1790 data: 0.1010 max mem: 8233 +Train: [37] [4300/6250] eta: 0:05:16 lr: 0.000092 grad: 0.1040 (0.1122) loss: 0.8983 (0.8946) time: 0.1419 data: 0.0588 max mem: 8233 +Train: [37] [4400/6250] eta: 0:04:59 lr: 0.000092 grad: 0.1102 (0.1122) loss: 0.8958 (0.8945) time: 0.1674 data: 0.0892 max mem: 8233 +Train: [37] [4500/6250] eta: 0:04:44 lr: 0.000092 grad: 0.0970 (0.1122) loss: 0.8941 (0.8946) time: 0.1517 data: 0.0817 max mem: 8233 +Train: [37] [4600/6250] eta: 0:04:27 lr: 0.000092 grad: 0.1081 (0.1122) loss: 0.8927 (0.8945) time: 0.1364 data: 0.0657 max mem: 8233 +Train: [37] [4700/6250] eta: 0:04:11 lr: 0.000092 grad: 0.1062 (0.1122) loss: 0.8954 (0.8945) time: 0.1430 data: 0.0610 max mem: 8233 +Train: [37] [4800/6250] eta: 0:03:54 lr: 0.000092 grad: 0.1022 (0.1121) loss: 0.8908 (0.8945) time: 0.1540 data: 0.0625 max mem: 8233 +Train: [37] [4900/6250] eta: 0:03:38 lr: 0.000092 grad: 0.1090 (0.1121) loss: 0.8974 (0.8945) time: 0.1626 data: 0.0901 max mem: 8233 +Train: [37] [5000/6250] eta: 0:03:22 lr: 0.000092 grad: 0.1034 (0.1121) loss: 0.9019 (0.8945) time: 0.1973 data: 0.1016 max mem: 8233 +Train: [37] [5100/6250] eta: 0:03:06 lr: 0.000092 grad: 0.1086 (0.1120) loss: 0.8913 (0.8945) time: 0.1560 data: 0.0673 max mem: 8233 +Train: [37] [5200/6250] eta: 0:02:49 lr: 0.000092 grad: 0.1077 (0.1120) loss: 0.8932 (0.8945) time: 0.1599 data: 0.0713 max mem: 8233 +Train: [37] [5300/6250] eta: 0:02:33 lr: 0.000092 grad: 0.1079 (0.1121) loss: 0.8938 (0.8945) time: 0.1401 data: 0.0512 max mem: 8233 +Train: [37] [5400/6250] eta: 0:02:17 lr: 0.000092 grad: 0.1076 (0.1121) loss: 0.8998 (0.8945) time: 0.1613 data: 0.0829 max mem: 8233 +Train: [37] [5500/6250] eta: 0:02:01 lr: 0.000092 grad: 0.1147 (0.1123) loss: 0.8892 (0.8945) time: 0.1364 data: 0.0599 max mem: 8233 +Train: [37] [5600/6250] eta: 0:01:44 lr: 0.000092 grad: 0.1107 (0.1124) loss: 0.8897 (0.8944) time: 0.1306 data: 0.0559 max mem: 8233 +Train: [37] [5700/6250] eta: 0:01:28 lr: 0.000091 grad: 0.1183 (0.1124) loss: 0.8947 (0.8944) time: 0.1621 data: 0.0841 max mem: 8233 +Train: [37] [5800/6250] eta: 0:01:12 lr: 0.000091 grad: 0.1091 (0.1125) loss: 0.8922 (0.8943) time: 0.1310 data: 0.0503 max mem: 8233 +Train: [37] [5900/6250] eta: 0:00:56 lr: 0.000091 grad: 0.1116 (0.1126) loss: 0.8914 (0.8943) time: 0.1514 data: 0.0641 max mem: 8233 +Train: [37] [6000/6250] eta: 0:00:40 lr: 0.000091 grad: 0.1163 (0.1126) loss: 0.8984 (0.8942) time: 0.1662 data: 0.0956 max mem: 8233 +Train: [37] [6100/6250] eta: 0:00:24 lr: 0.000091 grad: 0.1092 (0.1127) loss: 0.8924 (0.8942) time: 0.1447 data: 0.0635 max mem: 8233 +Train: [37] [6200/6250] eta: 0:00:08 lr: 0.000091 grad: 0.1123 (0.1127) loss: 0.8931 (0.8942) time: 0.1826 data: 0.1028 max mem: 8233 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.1093 (0.1127) loss: 0.8902 (0.8941) time: 0.2604 data: 0.1969 max mem: 8233 +Train: [37] Total time: 0:16:54 (0.1623 s / it) +Averaged stats: lr: 0.000091 grad: 0.1093 (0.1127) loss: 0.8902 (0.8941) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:04:34 loss: 0.9109 (0.9109) time: 4.4329 data: 4.3274 max mem: 8233 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.9015 (0.9014) time: 0.1365 data: 0.1145 max mem: 8233 +Eval (hcp-train-subset): [37] Total time: 0:00:15 (0.2493 s / it) +Averaged stats (hcp-train-subset): loss: 0.9015 (0.9014) +Eval (hcp-val): [37] [ 0/62] eta: 0:03:49 loss: 0.8925 (0.8925) time: 3.6978 data: 3.6160 max mem: 8233 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8962 (0.8972) time: 0.1480 data: 0.1274 max mem: 8233 +Eval (hcp-val): [37] Total time: 0:00:14 (0.2329 s / it) +Averaged stats (hcp-val): loss: 0.8962 (0.8972) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 10:46:24 lr: 0.000091 grad: 0.2054 (0.2054) loss: 0.9115 (0.9115) time: 6.2055 data: 6.0332 max mem: 8233 +Train: [38] [ 100/6250] eta: 0:24:21 lr: 0.000091 grad: 0.1105 (0.1121) loss: 0.9009 (0.9021) time: 0.1917 data: 0.0796 max mem: 8233 +Train: [38] [ 200/6250] eta: 0:21:00 lr: 0.000091 grad: 0.1178 (0.1155) loss: 0.8886 (0.8963) time: 0.1604 data: 0.0735 max mem: 8233 +Train: [38] [ 300/6250] eta: 0:19:46 lr: 0.000091 grad: 0.1049 (0.1157) loss: 0.8988 (0.8947) time: 0.1763 data: 0.0750 max mem: 8233 +Train: [38] [ 400/6250] eta: 0:18:54 lr: 0.000091 grad: 0.1116 (0.1172) loss: 0.8928 (0.8942) time: 0.1917 data: 0.1071 max mem: 8233 +Train: [38] [ 500/6250] eta: 0:18:00 lr: 0.000091 grad: 0.1102 (0.1170) loss: 0.8908 (0.8937) time: 0.1590 data: 0.0696 max mem: 8233 +Train: [38] [ 600/6250] eta: 0:17:27 lr: 0.000091 grad: 0.1080 (0.1172) loss: 0.8893 (0.8933) time: 0.1872 data: 0.0975 max mem: 8233 +Train: [38] [ 700/6250] eta: 0:16:49 lr: 0.000091 grad: 0.1057 (0.1167) loss: 0.8941 (0.8933) time: 0.1596 data: 0.0670 max mem: 8233 +Train: [38] [ 800/6250] eta: 0:16:31 lr: 0.000091 grad: 0.1078 (0.1165) loss: 0.8965 (0.8932) time: 0.1064 data: 0.0234 max mem: 8233 +Train: [38] [ 900/6250] eta: 0:16:06 lr: 0.000091 grad: 0.1127 (0.1165) loss: 0.8894 (0.8930) time: 0.1683 data: 0.0823 max mem: 8233 +Train: [38] [1000/6250] eta: 0:15:49 lr: 0.000091 grad: 0.1059 (0.1163) loss: 0.8865 (0.8925) time: 0.1629 data: 0.0808 max mem: 8233 +Train: [38] [1100/6250] eta: 0:15:19 lr: 0.000091 grad: 0.1201 (0.1162) loss: 0.8873 (0.8923) time: 0.1436 data: 0.0630 max mem: 8233 +Train: [38] [1200/6250] eta: 0:14:54 lr: 0.000091 grad: 0.1109 (0.1164) loss: 0.8906 (0.8923) time: 0.1729 data: 0.0909 max mem: 8233 +Train: [38] [1300/6250] eta: 0:14:34 lr: 0.000091 grad: 0.1203 (0.1167) loss: 0.8891 (0.8921) time: 0.1646 data: 0.0805 max mem: 8233 +Train: [38] [1400/6250] eta: 0:14:14 lr: 0.000091 grad: 0.1127 (0.1169) loss: 0.8905 (0.8921) time: 0.1622 data: 0.0826 max mem: 8233 +Train: [38] [1500/6250] eta: 0:13:56 lr: 0.000091 grad: 0.1114 (0.1171) loss: 0.8910 (0.8922) time: 0.1947 data: 0.1116 max mem: 8233 +Train: [38] [1600/6250] eta: 0:13:33 lr: 0.000091 grad: 0.1093 (0.1169) loss: 0.8929 (0.8921) time: 0.1776 data: 0.0868 max mem: 8233 +Train: [38] [1700/6250] eta: 0:13:13 lr: 0.000091 grad: 0.1103 (0.1171) loss: 0.8959 (0.8920) time: 0.1682 data: 0.0792 max mem: 8233 +Train: [38] [1800/6250] eta: 0:12:51 lr: 0.000091 grad: 0.1170 (0.1171) loss: 0.8908 (0.8920) time: 0.1495 data: 0.0628 max mem: 8233 +Train: [38] [1900/6250] eta: 0:12:29 lr: 0.000091 grad: 0.1133 (0.1171) loss: 0.8897 (0.8920) time: 0.1410 data: 0.0635 max mem: 8233 +Train: [38] [2000/6250] eta: 0:12:10 lr: 0.000091 grad: 0.1142 (0.1171) loss: 0.8960 (0.8919) time: 0.1436 data: 0.0562 max mem: 8233 +Train: [38] [2100/6250] eta: 0:11:49 lr: 0.000091 grad: 0.1031 (0.1171) loss: 0.8882 (0.8919) time: 0.1399 data: 0.0713 max mem: 8233 +Train: [38] [2200/6250] eta: 0:11:29 lr: 0.000091 grad: 0.1177 (0.1172) loss: 0.8957 (0.8919) time: 0.1466 data: 0.0648 max mem: 8233 +Train: [38] [2300/6250] eta: 0:11:11 lr: 0.000091 grad: 0.1212 (0.1171) loss: 0.8921 (0.8918) time: 0.1729 data: 0.1033 max mem: 8233 +Train: [38] [2400/6250] eta: 0:10:53 lr: 0.000091 grad: 0.1132 (0.1171) loss: 0.8886 (0.8917) time: 0.1528 data: 0.0625 max mem: 8233 +Train: [38] [2500/6250] eta: 0:10:39 lr: 0.000091 grad: 0.1067 (0.1171) loss: 0.8839 (0.8917) time: 0.3113 data: 0.2343 max mem: 8233 +Train: [38] [2600/6250] eta: 0:10:19 lr: 0.000091 grad: 0.1075 (0.1172) loss: 0.8819 (0.8915) time: 0.1435 data: 0.0625 max mem: 8233 +Train: [38] [2700/6250] eta: 0:10:00 lr: 0.000091 grad: 0.1130 (0.1172) loss: 0.8911 (0.8914) time: 0.1222 data: 0.0320 max mem: 8233 +Train: [38] [2800/6250] eta: 0:09:43 lr: 0.000091 grad: 0.1079 (0.1170) loss: 0.8887 (0.8914) time: 0.2072 data: 0.1353 max mem: 8233 +Train: [38] [2900/6250] eta: 0:09:25 lr: 0.000090 grad: 0.1190 (0.1170) loss: 0.8946 (0.8914) time: 0.1467 data: 0.0771 max mem: 8233 +Train: [38] [3000/6250] eta: 0:09:08 lr: 0.000090 grad: 0.1153 (0.1170) loss: 0.8912 (0.8914) time: 0.1523 data: 0.0837 max mem: 8233 +Train: [38] [3100/6250] eta: 0:08:50 lr: 0.000090 grad: 0.1038 (0.1169) loss: 0.8962 (0.8914) time: 0.1746 data: 0.0948 max mem: 8233 +Train: [38] [3200/6250] eta: 0:08:34 lr: 0.000090 grad: 0.1083 (0.1168) loss: 0.8905 (0.8915) time: 0.1869 data: 0.1070 max mem: 8233 +Train: [38] [3300/6250] eta: 0:08:18 lr: 0.000090 grad: 0.1123 (0.1167) loss: 0.8920 (0.8914) time: 0.1659 data: 0.0784 max mem: 8233 +Train: [38] [3400/6250] eta: 0:08:01 lr: 0.000090 grad: 0.1048 (0.1165) loss: 0.8894 (0.8914) time: 0.1724 data: 0.0889 max mem: 8233 +Train: [38] [3500/6250] eta: 0:07:44 lr: 0.000090 grad: 0.1116 (0.1164) loss: 0.8883 (0.8915) time: 0.1609 data: 0.0858 max mem: 8233 +Train: [38] [3600/6250] eta: 0:07:26 lr: 0.000090 grad: 0.1015 (0.1163) loss: 0.8919 (0.8915) time: 0.1544 data: 0.0749 max mem: 8233 +Train: [38] [3700/6250] eta: 0:07:08 lr: 0.000090 grad: 0.1215 (0.1163) loss: 0.8917 (0.8915) time: 0.1593 data: 0.0675 max mem: 8233 +Train: [38] [3800/6250] eta: 0:06:51 lr: 0.000090 grad: 0.1096 (0.1162) loss: 0.8949 (0.8916) time: 0.1718 data: 0.1002 max mem: 8233 +Train: [38] [3900/6250] eta: 0:06:33 lr: 0.000090 grad: 0.1120 (0.1161) loss: 0.8952 (0.8916) time: 0.1548 data: 0.0868 max mem: 8233 +Train: [38] [4000/6250] eta: 0:06:16 lr: 0.000090 grad: 0.1143 (0.1163) loss: 0.8965 (0.8917) time: 0.1711 data: 0.0963 max mem: 8233 +Train: [38] [4100/6250] eta: 0:05:59 lr: 0.000090 grad: 0.1058 (0.1163) loss: 0.8929 (0.8918) time: 0.1412 data: 0.0659 max mem: 8233 +Train: [38] [4200/6250] eta: 0:05:41 lr: 0.000090 grad: 0.1049 (0.1162) loss: 0.8911 (0.8918) time: 0.1507 data: 0.0676 max mem: 8233 +Train: [38] [4300/6250] eta: 0:05:24 lr: 0.000090 grad: 0.1092 (0.1162) loss: 0.8900 (0.8918) time: 0.1376 data: 0.0497 max mem: 8233 +Train: [38] [4400/6250] eta: 0:05:07 lr: 0.000090 grad: 0.1092 (0.1162) loss: 0.8915 (0.8918) time: 0.1652 data: 0.0910 max mem: 8233 +Train: [38] [4500/6250] eta: 0:04:51 lr: 0.000090 grad: 0.1136 (0.1161) loss: 0.8909 (0.8918) time: 0.1853 data: 0.1056 max mem: 8233 +Train: [38] [4600/6250] eta: 0:04:34 lr: 0.000090 grad: 0.1076 (0.1161) loss: 0.8951 (0.8918) time: 0.2118 data: 0.1373 max mem: 8233 +Train: [38] [4700/6250] eta: 0:04:18 lr: 0.000090 grad: 0.1150 (0.1161) loss: 0.8910 (0.8918) time: 0.1695 data: 0.0911 max mem: 8233 +Train: [38] [4800/6250] eta: 0:04:00 lr: 0.000090 grad: 0.1173 (0.1161) loss: 0.8886 (0.8918) time: 0.1606 data: 0.0909 max mem: 8233 +Train: [38] [4900/6250] eta: 0:03:44 lr: 0.000090 grad: 0.1121 (0.1160) loss: 0.8944 (0.8918) time: 0.1725 data: 0.0938 max mem: 8233 +Train: [38] [5000/6250] eta: 0:03:27 lr: 0.000090 grad: 0.1110 (0.1160) loss: 0.8926 (0.8918) time: 0.1732 data: 0.0863 max mem: 8233 +Train: [38] [5100/6250] eta: 0:03:10 lr: 0.000090 grad: 0.1093 (0.1159) loss: 0.8901 (0.8918) time: 0.1577 data: 0.0845 max mem: 8233 +Train: [38] [5200/6250] eta: 0:02:54 lr: 0.000090 grad: 0.1119 (0.1160) loss: 0.8947 (0.8918) time: 0.1544 data: 0.0691 max mem: 8233 +Train: [38] [5300/6250] eta: 0:02:37 lr: 0.000090 grad: 0.1145 (0.1160) loss: 0.8909 (0.8918) time: 0.1405 data: 0.0478 max mem: 8233 +Train: [38] [5400/6250] eta: 0:02:20 lr: 0.000090 grad: 0.1144 (0.1160) loss: 0.8879 (0.8918) time: 0.1739 data: 0.0933 max mem: 8233 +Train: [38] [5500/6250] eta: 0:02:03 lr: 0.000090 grad: 0.1142 (0.1159) loss: 0.8935 (0.8919) time: 0.1416 data: 0.0556 max mem: 8233 +Train: [38] [5600/6250] eta: 0:01:47 lr: 0.000090 grad: 0.1107 (0.1159) loss: 0.8940 (0.8919) time: 0.1451 data: 0.0624 max mem: 8233 +Train: [38] [5700/6250] eta: 0:01:30 lr: 0.000090 grad: 0.1111 (0.1159) loss: 0.8949 (0.8919) time: 0.1712 data: 0.0957 max mem: 8233 +Train: [38] [5800/6250] eta: 0:01:14 lr: 0.000090 grad: 0.1103 (0.1159) loss: 0.8909 (0.8919) time: 0.1605 data: 0.0883 max mem: 8233 +Train: [38] [5900/6250] eta: 0:00:57 lr: 0.000090 grad: 0.1065 (0.1159) loss: 0.8945 (0.8919) time: 0.1377 data: 0.0532 max mem: 8233 +Train: [38] [6000/6250] eta: 0:00:41 lr: 0.000090 grad: 0.1138 (0.1159) loss: 0.8951 (0.8919) time: 0.1520 data: 0.0783 max mem: 8233 +Train: [38] [6100/6250] eta: 0:00:24 lr: 0.000090 grad: 0.1123 (0.1160) loss: 0.8890 (0.8919) time: 0.1234 data: 0.0519 max mem: 8233 +Train: [38] [6200/6250] eta: 0:00:08 lr: 0.000089 grad: 0.1155 (0.1160) loss: 0.8903 (0.8918) time: 0.1496 data: 0.0711 max mem: 8233 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.1176 (0.1160) loss: 0.8882 (0.8918) time: 0.1594 data: 0.0794 max mem: 8233 +Train: [38] Total time: 0:17:14 (0.1655 s / it) +Averaged stats: lr: 0.000089 grad: 0.1176 (0.1160) loss: 0.8882 (0.8918) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:05:08 loss: 0.9112 (0.9112) time: 4.9728 data: 4.9451 max mem: 8233 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.9030 (0.9007) time: 0.1287 data: 0.1079 max mem: 8233 +Eval (hcp-train-subset): [38] Total time: 0:00:13 (0.2244 s / it) +Averaged stats (hcp-train-subset): loss: 0.9030 (0.9007) +Eval (hcp-val): [38] [ 0/62] eta: 0:05:28 loss: 0.8943 (0.8943) time: 5.3028 data: 5.2764 max mem: 8233 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8971 (0.8967) time: 0.1318 data: 0.1101 max mem: 8233 +Eval (hcp-val): [38] Total time: 0:00:14 (0.2268 s / it) +Averaged stats (hcp-val): loss: 0.8971 (0.8967) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 11:23:09 lr: 0.000089 grad: 0.0917 (0.0917) loss: 0.9009 (0.9009) time: 6.5583 data: 6.3968 max mem: 8233 +Train: [39] [ 100/6250] eta: 0:22:20 lr: 0.000089 grad: 0.1085 (0.1023) loss: 0.8980 (0.9081) time: 0.1586 data: 0.0524 max mem: 8233 +Train: [39] [ 200/6250] eta: 0:19:53 lr: 0.000089 grad: 0.1121 (0.1070) loss: 0.8889 (0.9014) time: 0.1832 data: 0.0804 max mem: 8233 +Train: [39] [ 300/6250] eta: 0:18:26 lr: 0.000089 grad: 0.1123 (0.1094) loss: 0.8951 (0.8985) time: 0.1721 data: 0.0800 max mem: 8233 +Train: [39] [ 400/6250] eta: 0:17:38 lr: 0.000089 grad: 0.1064 (0.1095) loss: 0.8979 (0.8973) time: 0.1334 data: 0.0240 max mem: 8233 +Train: [39] [ 500/6250] eta: 0:16:54 lr: 0.000089 grad: 0.0998 (0.1088) loss: 0.8896 (0.8962) time: 0.1546 data: 0.0671 max mem: 8233 +Train: [39] [ 600/6250] eta: 0:16:24 lr: 0.000089 grad: 0.1028 (0.1089) loss: 0.8909 (0.8953) time: 0.1848 data: 0.0984 max mem: 8233 +Train: [39] [ 700/6250] eta: 0:15:57 lr: 0.000089 grad: 0.1138 (0.1085) loss: 0.8977 (0.8953) time: 0.1639 data: 0.0844 max mem: 8233 +Train: [39] [ 800/6250] eta: 0:15:32 lr: 0.000089 grad: 0.1035 (0.1083) loss: 0.8937 (0.8951) time: 0.1428 data: 0.0513 max mem: 8233 +Train: [39] [ 900/6250] eta: 0:15:09 lr: 0.000089 grad: 0.1234 (0.1089) loss: 0.8898 (0.8949) time: 0.1722 data: 0.0797 max mem: 8233 +Train: [39] [1000/6250] eta: 0:14:54 lr: 0.000089 grad: 0.1125 (0.1091) loss: 0.8891 (0.8946) time: 0.2457 data: 0.1684 max mem: 8233 +Train: [39] [1100/6250] eta: 0:14:32 lr: 0.000089 grad: 0.1073 (0.1093) loss: 0.8958 (0.8945) time: 0.1496 data: 0.0785 max mem: 8233 +Train: [39] [1200/6250] eta: 0:14:13 lr: 0.000089 grad: 0.1150 (0.1095) loss: 0.8967 (0.8943) time: 0.1284 data: 0.0503 max mem: 8233 +Train: [39] [1300/6250] eta: 0:13:54 lr: 0.000089 grad: 0.1160 (0.1095) loss: 0.8885 (0.8942) time: 0.2021 data: 0.1355 max mem: 8233 +Train: [39] [1400/6250] eta: 0:13:36 lr: 0.000089 grad: 0.1063 (0.1096) loss: 0.8894 (0.8940) time: 0.1721 data: 0.0854 max mem: 8233 +Train: [39] [1500/6250] eta: 0:13:19 lr: 0.000089 grad: 0.1066 (0.1098) loss: 0.8938 (0.8940) time: 0.1740 data: 0.0925 max mem: 8233 +Train: [39] [1600/6250] eta: 0:13:02 lr: 0.000089 grad: 0.1106 (0.1103) loss: 0.8959 (0.8939) time: 0.2119 data: 0.1429 max mem: 8233 +Train: [39] [1700/6250] eta: 0:12:39 lr: 0.000089 grad: 0.1081 (0.1106) loss: 0.8969 (0.8937) time: 0.1470 data: 0.0597 max mem: 8233 +Train: [39] [1800/6250] eta: 0:12:20 lr: 0.000089 grad: 0.1176 (0.1108) loss: 0.8901 (0.8936) time: 0.1528 data: 0.0582 max mem: 8233 +Train: [39] [1900/6250] eta: 0:12:00 lr: 0.000089 grad: 0.1158 (0.1110) loss: 0.8896 (0.8934) time: 0.1434 data: 0.0640 max mem: 8233 +Train: [39] [2000/6250] eta: 0:11:42 lr: 0.000089 grad: 0.1126 (0.1115) loss: 0.8887 (0.8932) time: 0.1586 data: 0.0823 max mem: 8233 +Train: [39] [2100/6250] eta: 0:11:22 lr: 0.000089 grad: 0.1098 (0.1117) loss: 0.8907 (0.8931) time: 0.1427 data: 0.0646 max mem: 8233 +Train: [39] [2200/6250] eta: 0:11:06 lr: 0.000089 grad: 0.1091 (0.1117) loss: 0.8813 (0.8929) time: 0.1346 data: 0.0413 max mem: 8233 +Train: [39] [2300/6250] eta: 0:10:47 lr: 0.000089 grad: 0.1177 (0.1119) loss: 0.8929 (0.8928) time: 0.1494 data: 0.0649 max mem: 8233 +Train: [39] [2400/6250] eta: 0:10:31 lr: 0.000089 grad: 0.1176 (0.1121) loss: 0.8885 (0.8926) time: 0.1789 data: 0.0944 max mem: 8233 +Train: [39] [2500/6250] eta: 0:10:18 lr: 0.000089 grad: 0.1106 (0.1123) loss: 0.8893 (0.8924) time: 0.2588 data: 0.1569 max mem: 8233 +Train: [39] [2600/6250] eta: 0:09:57 lr: 0.000089 grad: 0.1182 (0.1125) loss: 0.8829 (0.8923) time: 0.1603 data: 0.0854 max mem: 8233 +Train: [39] [2700/6250] eta: 0:09:38 lr: 0.000089 grad: 0.1154 (0.1127) loss: 0.8912 (0.8922) time: 0.1500 data: 0.0668 max mem: 8233 +Train: [39] [2800/6250] eta: 0:09:21 lr: 0.000089 grad: 0.1116 (0.1128) loss: 0.8875 (0.8920) time: 0.1445 data: 0.0550 max mem: 8233 +Train: [39] [2900/6250] eta: 0:09:05 lr: 0.000089 grad: 0.1144 (0.1130) loss: 0.8863 (0.8919) time: 0.1604 data: 0.0784 max mem: 8233 +Train: [39] [3000/6250] eta: 0:08:49 lr: 0.000089 grad: 0.1040 (0.1131) loss: 0.8895 (0.8918) time: 0.1644 data: 0.0996 max mem: 8233 +Train: [39] [3100/6250] eta: 0:08:33 lr: 0.000089 grad: 0.1111 (0.1131) loss: 0.8916 (0.8917) time: 0.1595 data: 0.0644 max mem: 8233 +Train: [39] [3200/6250] eta: 0:08:17 lr: 0.000089 grad: 0.1092 (0.1132) loss: 0.8866 (0.8917) time: 0.1529 data: 0.0801 max mem: 8233 +Train: [39] [3300/6250] eta: 0:08:02 lr: 0.000088 grad: 0.1106 (0.1133) loss: 0.8921 (0.8917) time: 0.1774 data: 0.0959 max mem: 8233 +Train: [39] [3400/6250] eta: 0:07:44 lr: 0.000088 grad: 0.1141 (0.1134) loss: 0.8896 (0.8917) time: 0.1453 data: 0.0508 max mem: 8233 +Train: [39] [3500/6250] eta: 0:07:28 lr: 0.000088 grad: 0.1179 (0.1138) loss: 0.8940 (0.8917) time: 0.1539 data: 0.0729 max mem: 8233 +Train: [39] [3600/6250] eta: 0:07:11 lr: 0.000088 grad: 0.1167 (0.1139) loss: 0.8890 (0.8917) time: 0.1921 data: 0.1003 max mem: 8233 +Train: [39] [3700/6250] eta: 0:06:54 lr: 0.000088 grad: 0.1125 (0.1141) loss: 0.8887 (0.8916) time: 0.1524 data: 0.0638 max mem: 8233 +Train: [39] [3800/6250] eta: 0:06:37 lr: 0.000088 grad: 0.1222 (0.1142) loss: 0.8931 (0.8916) time: 0.1548 data: 0.0633 max mem: 8233 +Train: [39] [3900/6250] eta: 0:06:20 lr: 0.000088 grad: 0.1135 (0.1143) loss: 0.8915 (0.8916) time: 0.1400 data: 0.0569 max mem: 8233 +Train: [39] [4000/6250] eta: 0:06:02 lr: 0.000088 grad: 0.1177 (0.1145) loss: 0.8938 (0.8916) time: 0.1265 data: 0.0390 max mem: 8233 +Train: [39] [4100/6250] eta: 0:05:45 lr: 0.000088 grad: 0.1078 (0.1147) loss: 0.8931 (0.8916) time: 0.1388 data: 0.0479 max mem: 8233 +Train: [39] [4200/6250] eta: 0:05:28 lr: 0.000088 grad: 0.1121 (0.1150) loss: 0.8876 (0.8916) time: 0.1454 data: 0.0526 max mem: 8233 +Train: [39] [4300/6250] eta: 0:05:12 lr: 0.000088 grad: 0.1162 (0.1151) loss: 0.8890 (0.8915) time: 0.1391 data: 0.0641 max mem: 8233 +Train: [39] [4400/6250] eta: 0:04:56 lr: 0.000088 grad: 0.1178 (0.1152) loss: 0.8889 (0.8915) time: 0.1859 data: 0.1148 max mem: 8233 +Train: [39] [4500/6250] eta: 0:04:40 lr: 0.000088 grad: 0.1180 (0.1153) loss: 0.8915 (0.8914) time: 0.1852 data: 0.1006 max mem: 8233 +Train: [39] [4600/6250] eta: 0:04:24 lr: 0.000088 grad: 0.1165 (0.1154) loss: 0.8892 (0.8914) time: 0.1200 data: 0.0301 max mem: 8233 +Train: [39] [4700/6250] eta: 0:04:09 lr: 0.000088 grad: 0.1095 (0.1154) loss: 0.8888 (0.8913) time: 0.1689 data: 0.1010 max mem: 8233 +Train: [39] [4800/6250] eta: 0:03:53 lr: 0.000088 grad: 0.1131 (0.1155) loss: 0.8876 (0.8913) time: 0.1854 data: 0.1072 max mem: 8233 +Train: [39] [4900/6250] eta: 0:03:37 lr: 0.000088 grad: 0.1167 (0.1155) loss: 0.8861 (0.8912) time: 0.1670 data: 0.0867 max mem: 8233 +Train: [39] [5000/6250] eta: 0:03:21 lr: 0.000088 grad: 0.1098 (0.1155) loss: 0.8932 (0.8911) time: 0.1695 data: 0.0801 max mem: 8233 +Train: [39] [5100/6250] eta: 0:03:05 lr: 0.000088 grad: 0.1169 (0.1155) loss: 0.8824 (0.8911) time: 0.1711 data: 0.0868 max mem: 8233 +Train: [39] [5200/6250] eta: 0:02:49 lr: 0.000088 grad: 0.1179 (0.1156) loss: 0.8934 (0.8910) time: 0.1798 data: 0.0921 max mem: 8233 +Train: [39] [5300/6250] eta: 0:02:33 lr: 0.000088 grad: 0.1154 (0.1157) loss: 0.8871 (0.8910) time: 0.1595 data: 0.0707 max mem: 8233 +Train: [39] [5400/6250] eta: 0:02:17 lr: 0.000088 grad: 0.1146 (0.1157) loss: 0.8891 (0.8909) time: 0.1790 data: 0.0916 max mem: 8233 +Train: [39] [5500/6250] eta: 0:02:01 lr: 0.000088 grad: 0.1095 (0.1157) loss: 0.8949 (0.8909) time: 0.1570 data: 0.0748 max mem: 8233 +Train: [39] [5600/6250] eta: 0:01:45 lr: 0.000088 grad: 0.1074 (0.1158) loss: 0.8931 (0.8908) time: 0.1500 data: 0.0599 max mem: 8233 +Train: [39] [5700/6250] eta: 0:01:28 lr: 0.000088 grad: 0.1078 (0.1158) loss: 0.8897 (0.8908) time: 0.1460 data: 0.0668 max mem: 8233 +Train: [39] [5800/6250] eta: 0:01:12 lr: 0.000088 grad: 0.1115 (0.1158) loss: 0.8915 (0.8908) time: 0.1493 data: 0.0626 max mem: 8233 +Train: [39] [5900/6250] eta: 0:00:56 lr: 0.000088 grad: 0.1138 (0.1158) loss: 0.8912 (0.8908) time: 0.1840 data: 0.1039 max mem: 8233 +Train: [39] [6000/6250] eta: 0:00:40 lr: 0.000088 grad: 0.1095 (0.1157) loss: 0.8914 (0.8907) time: 0.1322 data: 0.0502 max mem: 8233 +Train: [39] [6100/6250] eta: 0:00:24 lr: 0.000088 grad: 0.1222 (0.1158) loss: 0.8909 (0.8907) time: 0.1372 data: 0.0507 max mem: 8233 +Train: [39] [6200/6250] eta: 0:00:08 lr: 0.000088 grad: 0.1071 (0.1158) loss: 0.8905 (0.8908) time: 0.1883 data: 0.1093 max mem: 8233 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.1102 (0.1158) loss: 0.8926 (0.8908) time: 0.1755 data: 0.0919 max mem: 8233 +Train: [39] Total time: 0:16:53 (0.1621 s / it) +Averaged stats: lr: 0.000088 grad: 0.1102 (0.1158) loss: 0.8926 (0.8908) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:04:36 loss: 0.9063 (0.9063) time: 4.4623 data: 4.4097 max mem: 8233 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.9004 (0.8997) time: 0.1433 data: 0.1226 max mem: 8233 +Eval (hcp-train-subset): [39] Total time: 0:00:14 (0.2336 s / it) +Averaged stats (hcp-train-subset): loss: 0.9004 (0.8997) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [39] [ 0/62] eta: 0:04:36 loss: 0.8933 (0.8933) time: 4.4670 data: 4.3957 max mem: 8233 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8952 (0.8961) time: 0.1418 data: 0.1208 max mem: 8233 +Eval (hcp-val): [39] Total time: 0:00:14 (0.2301 s / it) +Averaged stats (hcp-val): loss: 0.8952 (0.8961) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-00039.pth +Train: [40] [ 0/6250] eta: 7:48:37 lr: 0.000088 grad: 0.1021 (0.1021) loss: 0.9159 (0.9159) time: 4.4988 data: 4.2944 max mem: 8233 +Train: [40] [ 100/6250] eta: 0:23:49 lr: 0.000088 grad: 0.1126 (0.1121) loss: 0.8891 (0.9018) time: 0.1743 data: 0.0758 max mem: 8233 +Train: [40] [ 200/6250] eta: 0:20:30 lr: 0.000088 grad: 0.1197 (0.1150) loss: 0.8906 (0.8969) time: 0.1996 data: 0.1096 max mem: 8233 +Train: [40] [ 300/6250] eta: 0:18:57 lr: 0.000088 grad: 0.1043 (0.1136) loss: 0.8961 (0.8959) time: 0.1615 data: 0.0648 max mem: 8233 +Train: [40] [ 400/6250] eta: 0:18:00 lr: 0.000087 grad: 0.1120 (0.1138) loss: 0.8923 (0.8954) time: 0.1623 data: 0.0647 max mem: 8233 +Train: [40] [ 500/6250] eta: 0:17:18 lr: 0.000087 grad: 0.1116 (0.1140) loss: 0.8971 (0.8945) time: 0.1792 data: 0.0856 max mem: 8233 +Train: [40] [ 600/6250] eta: 0:16:42 lr: 0.000087 grad: 0.1076 (0.1143) loss: 0.9012 (0.8941) time: 0.1842 data: 0.1054 max mem: 8233 +Train: [40] [ 700/6250] eta: 0:16:09 lr: 0.000087 grad: 0.1148 (0.1143) loss: 0.8975 (0.8939) time: 0.1621 data: 0.0730 max mem: 8233 +Train: [40] [ 800/6250] eta: 0:15:41 lr: 0.000087 grad: 0.1145 (0.1147) loss: 0.8980 (0.8939) time: 0.1210 data: 0.0351 max mem: 8233 +Train: [40] [ 900/6250] eta: 0:15:15 lr: 0.000087 grad: 0.1109 (0.1148) loss: 0.8931 (0.8938) time: 0.1443 data: 0.0533 max mem: 8233 +Train: [40] [1000/6250] eta: 0:15:01 lr: 0.000087 grad: 0.1203 (0.1150) loss: 0.8862 (0.8935) time: 0.1676 data: 0.0957 max mem: 8233 +Train: [40] [1100/6250] eta: 0:14:38 lr: 0.000087 grad: 0.1112 (0.1155) loss: 0.8921 (0.8935) time: 0.1479 data: 0.0713 max mem: 8233 +Train: [40] [1200/6250] eta: 0:14:14 lr: 0.000087 grad: 0.1166 (0.1156) loss: 0.8906 (0.8935) time: 0.1667 data: 0.0876 max mem: 8233 +Train: [40] [1300/6250] eta: 0:13:58 lr: 0.000087 grad: 0.1094 (0.1158) loss: 0.8918 (0.8934) time: 0.1972 data: 0.1128 max mem: 8233 +Train: [40] [1400/6250] eta: 0:13:42 lr: 0.000087 grad: 0.1142 (0.1161) loss: 0.8964 (0.8935) time: 0.1828 data: 0.0970 max mem: 8233 +Train: [40] [1500/6250] eta: 0:13:24 lr: 0.000087 grad: 0.1031 (0.1162) loss: 0.8937 (0.8934) time: 0.1701 data: 0.0957 max mem: 8233 +Train: [40] [1600/6250] eta: 0:13:04 lr: 0.000087 grad: 0.1137 (0.1164) loss: 0.8957 (0.8933) time: 0.1596 data: 0.0698 max mem: 8233 +Train: [40] [1700/6250] eta: 0:12:46 lr: 0.000087 grad: 0.1085 (0.1166) loss: 0.8950 (0.8933) time: 0.1670 data: 0.0898 max mem: 8233 +Train: [40] [1800/6250] eta: 0:12:24 lr: 0.000087 grad: 0.1054 (0.1168) loss: 0.8994 (0.8933) time: 0.1496 data: 0.0718 max mem: 8233 +Train: [40] [1900/6250] eta: 0:12:05 lr: 0.000087 grad: 0.1097 (0.1169) loss: 0.8957 (0.8933) time: 0.1311 data: 0.0431 max mem: 8233 +Train: [40] [2000/6250] eta: 0:11:47 lr: 0.000087 grad: 0.1080 (0.1171) loss: 0.8943 (0.8934) time: 0.1713 data: 0.0943 max mem: 8233 +Train: [40] [2100/6250] eta: 0:11:28 lr: 0.000087 grad: 0.1165 (0.1173) loss: 0.8888 (0.8934) time: 0.1685 data: 0.0896 max mem: 8233 +Train: [40] [2200/6250] eta: 0:11:10 lr: 0.000087 grad: 0.1077 (0.1173) loss: 0.8923 (0.8933) time: 0.1963 data: 0.1136 max mem: 8233 +Train: [40] [2300/6250] eta: 0:10:52 lr: 0.000087 grad: 0.1093 (0.1173) loss: 0.8948 (0.8933) time: 0.1416 data: 0.0656 max mem: 8233 +Train: [40] [2400/6250] eta: 0:10:34 lr: 0.000087 grad: 0.1081 (0.1172) loss: 0.8957 (0.8933) time: 0.1697 data: 0.0995 max mem: 8233 +Train: [40] [2500/6250] eta: 0:10:17 lr: 0.000087 grad: 0.1042 (0.1169) loss: 0.8880 (0.8933) time: 0.1336 data: 0.0646 max mem: 8233 +Train: [40] [2600/6250] eta: 0:10:01 lr: 0.000087 grad: 0.1068 (0.1169) loss: 0.8947 (0.8933) time: 0.1782 data: 0.1055 max mem: 8233 +Train: [40] [2700/6250] eta: 0:09:42 lr: 0.000087 grad: 0.1117 (0.1167) loss: 0.8938 (0.8932) time: 0.1608 data: 0.0839 max mem: 8233 +Train: [40] [2800/6250] eta: 0:09:24 lr: 0.000087 grad: 0.1049 (0.1166) loss: 0.8952 (0.8933) time: 0.1771 data: 0.0914 max mem: 8233 +Train: [40] [2900/6250] eta: 0:09:07 lr: 0.000087 grad: 0.1118 (0.1166) loss: 0.8900 (0.8933) time: 0.1615 data: 0.0890 max mem: 8233 +Train: [40] [3000/6250] eta: 0:08:50 lr: 0.000087 grad: 0.1163 (0.1167) loss: 0.8924 (0.8933) time: 0.1704 data: 0.0892 max mem: 8233 +Train: [40] [3100/6250] eta: 0:08:32 lr: 0.000087 grad: 0.1183 (0.1167) loss: 0.8918 (0.8932) time: 0.1639 data: 0.0952 max mem: 8233 +Train: [40] [3200/6250] eta: 0:08:17 lr: 0.000087 grad: 0.1039 (0.1166) loss: 0.8919 (0.8932) time: 0.2001 data: 0.1154 max mem: 8233 +Train: [40] [3300/6250] eta: 0:08:03 lr: 0.000087 grad: 0.1106 (0.1165) loss: 0.8947 (0.8932) time: 0.1734 data: 0.0837 max mem: 8233 +Train: [40] [3400/6250] eta: 0:07:48 lr: 0.000087 grad: 0.1115 (0.1164) loss: 0.8925 (0.8932) time: 0.1778 data: 0.0997 max mem: 8233 +Train: [40] [3500/6250] eta: 0:07:32 lr: 0.000087 grad: 0.1091 (0.1163) loss: 0.8936 (0.8932) time: 0.1662 data: 0.0848 max mem: 8233 +Train: [40] [3600/6250] eta: 0:07:16 lr: 0.000087 grad: 0.1111 (0.1163) loss: 0.8920 (0.8932) time: 0.1777 data: 0.0943 max mem: 8233 +Train: [40] [3700/6250] eta: 0:07:00 lr: 0.000086 grad: 0.1212 (0.1163) loss: 0.8907 (0.8932) time: 0.1705 data: 0.1047 max mem: 8233 +Train: [40] [3800/6250] eta: 0:06:44 lr: 0.000086 grad: 0.1183 (0.1163) loss: 0.8904 (0.8931) time: 0.1738 data: 0.0987 max mem: 8233 +Train: [40] [3900/6250] eta: 0:06:28 lr: 0.000086 grad: 0.1114 (0.1163) loss: 0.8903 (0.8931) time: 0.2081 data: 0.1359 max mem: 8233 +Train: [40] [4000/6250] eta: 0:06:11 lr: 0.000086 grad: 0.1096 (0.1163) loss: 0.8945 (0.8931) time: 0.1547 data: 0.0577 max mem: 8233 +Train: [40] [4100/6250] eta: 0:05:54 lr: 0.000086 grad: 0.1044 (0.1162) loss: 0.8957 (0.8931) time: 0.1585 data: 0.0863 max mem: 8233 +Train: [40] [4200/6250] eta: 0:05:37 lr: 0.000086 grad: 0.1110 (0.1162) loss: 0.8947 (0.8932) time: 0.1683 data: 0.0939 max mem: 8233 +Train: [40] [4300/6250] eta: 0:05:21 lr: 0.000086 grad: 0.1110 (0.1161) loss: 0.8978 (0.8932) time: 0.1543 data: 0.0663 max mem: 8233 +Train: [40] [4400/6250] eta: 0:05:05 lr: 0.000086 grad: 0.1039 (0.1161) loss: 0.9015 (0.8932) time: 0.1245 data: 0.0351 max mem: 8233 +Train: [40] [4500/6250] eta: 0:04:48 lr: 0.000086 grad: 0.1035 (0.1159) loss: 0.8938 (0.8933) time: 0.1653 data: 0.0853 max mem: 8233 +Train: [40] [4600/6250] eta: 0:04:32 lr: 0.000086 grad: 0.1133 (0.1160) loss: 0.8959 (0.8933) time: 0.1520 data: 0.0792 max mem: 8233 +Train: [40] [4700/6250] eta: 0:04:15 lr: 0.000086 grad: 0.1077 (0.1160) loss: 0.8924 (0.8933) time: 0.1771 data: 0.0985 max mem: 8233 +Train: [40] [4800/6250] eta: 0:03:59 lr: 0.000086 grad: 0.1208 (0.1160) loss: 0.8930 (0.8933) time: 0.1640 data: 0.0853 max mem: 8233 +Train: [40] [4900/6250] eta: 0:03:42 lr: 0.000086 grad: 0.1032 (0.1159) loss: 0.8941 (0.8933) time: 0.1583 data: 0.0787 max mem: 8233 +Train: [40] [5000/6250] eta: 0:03:26 lr: 0.000086 grad: 0.1069 (0.1158) loss: 0.8945 (0.8933) time: 0.1724 data: 0.0879 max mem: 8233 +Train: [40] [5100/6250] eta: 0:03:09 lr: 0.000086 grad: 0.1050 (0.1158) loss: 0.8908 (0.8932) time: 0.1802 data: 0.1020 max mem: 8233 +Train: [40] [5200/6250] eta: 0:02:53 lr: 0.000086 grad: 0.1136 (0.1158) loss: 0.8882 (0.8932) time: 0.1648 data: 0.0858 max mem: 8233 +Train: [40] [5300/6250] eta: 0:02:36 lr: 0.000086 grad: 0.1157 (0.1159) loss: 0.8925 (0.8932) time: 0.1522 data: 0.0690 max mem: 8233 +Train: [40] [5400/6250] eta: 0:02:20 lr: 0.000086 grad: 0.1105 (0.1158) loss: 0.8933 (0.8932) time: 0.1587 data: 0.0698 max mem: 8233 +Train: [40] [5500/6250] eta: 0:02:03 lr: 0.000086 grad: 0.1015 (0.1157) loss: 0.8947 (0.8932) time: 0.1413 data: 0.0569 max mem: 8233 +Train: [40] [5600/6250] eta: 0:01:46 lr: 0.000086 grad: 0.1123 (0.1157) loss: 0.8933 (0.8932) time: 0.1544 data: 0.0694 max mem: 8233 +Train: [40] [5700/6250] eta: 0:01:30 lr: 0.000086 grad: 0.1104 (0.1158) loss: 0.8899 (0.8931) time: 0.1624 data: 0.0736 max mem: 8233 +Train: [40] [5800/6250] eta: 0:01:13 lr: 0.000086 grad: 0.1119 (0.1158) loss: 0.8898 (0.8931) time: 0.1571 data: 0.0791 max mem: 8233 +Train: [40] [5900/6250] eta: 0:00:57 lr: 0.000086 grad: 0.1060 (0.1158) loss: 0.8897 (0.8931) time: 0.1518 data: 0.0650 max mem: 8233 +Train: [40] [6000/6250] eta: 0:00:41 lr: 0.000086 grad: 0.1076 (0.1158) loss: 0.8885 (0.8931) time: 0.1316 data: 0.0608 max mem: 8233 +Train: [40] [6100/6250] eta: 0:00:24 lr: 0.000086 grad: 0.1053 (0.1158) loss: 0.8831 (0.8930) time: 0.1497 data: 0.0691 max mem: 8233 +Train: [40] [6200/6250] eta: 0:00:08 lr: 0.000086 grad: 0.1087 (0.1158) loss: 0.8941 (0.8930) time: 0.1382 data: 0.0597 max mem: 8233 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.1162 (0.1158) loss: 0.8888 (0.8929) time: 0.1941 data: 0.1152 max mem: 8233 +Train: [40] Total time: 0:17:11 (0.1650 s / it) +Averaged stats: lr: 0.000086 grad: 0.1162 (0.1158) loss: 0.8888 (0.8929) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:05:12 loss: 0.9100 (0.9100) time: 5.0436 data: 5.0161 max mem: 8233 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.9013 (0.9003) time: 0.1357 data: 0.1148 max mem: 8233 +Eval (hcp-train-subset): [40] Total time: 0:00:14 (0.2327 s / it) +Averaged stats (hcp-train-subset): loss: 0.9013 (0.9003) +Eval (hcp-val): [40] [ 0/62] eta: 0:05:50 loss: 0.8920 (0.8920) time: 5.6501 data: 5.6224 max mem: 8233 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8957 (0.8960) time: 0.1245 data: 0.1029 max mem: 8233 +Eval (hcp-val): [40] Total time: 0:00:13 (0.2254 s / it) +Averaged stats (hcp-val): loss: 0.8957 (0.8960) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 11:03:53 lr: 0.000086 grad: 0.0999 (0.0999) loss: 0.9080 (0.9080) time: 6.3733 data: 6.2806 max mem: 8233 +Train: [41] [ 100/6250] eta: 0:22:10 lr: 0.000086 grad: 0.1110 (0.1143) loss: 0.8930 (0.8973) time: 0.1592 data: 0.0587 max mem: 8233 +Train: [41] [ 200/6250] eta: 0:19:36 lr: 0.000086 grad: 0.1077 (0.1167) loss: 0.8888 (0.8947) time: 0.1673 data: 0.0711 max mem: 8233 +Train: [41] [ 300/6250] eta: 0:18:22 lr: 0.000086 grad: 0.1109 (0.1174) loss: 0.8909 (0.8927) time: 0.1637 data: 0.0726 max mem: 8233 +Train: [41] [ 400/6250] eta: 0:17:22 lr: 0.000086 grad: 0.1196 (0.1184) loss: 0.8861 (0.8912) time: 0.1384 data: 0.0453 max mem: 8233 +Train: [41] [ 500/6250] eta: 0:16:44 lr: 0.000086 grad: 0.1101 (0.1184) loss: 0.8902 (0.8910) time: 0.1518 data: 0.0656 max mem: 8233 +Train: [41] [ 600/6250] eta: 0:16:12 lr: 0.000086 grad: 0.1091 (0.1176) loss: 0.8968 (0.8911) time: 0.1508 data: 0.0652 max mem: 8233 +Train: [41] [ 700/6250] eta: 0:15:45 lr: 0.000085 grad: 0.1139 (0.1171) loss: 0.8875 (0.8913) time: 0.1931 data: 0.1096 max mem: 8233 +Train: [41] [ 800/6250] eta: 0:15:19 lr: 0.000085 grad: 0.1143 (0.1174) loss: 0.8879 (0.8914) time: 0.1739 data: 0.0859 max mem: 8233 +Train: [41] [ 900/6250] eta: 0:14:54 lr: 0.000085 grad: 0.1059 (0.1175) loss: 0.8936 (0.8914) time: 0.1642 data: 0.0808 max mem: 8233 +Train: [41] [1000/6250] eta: 0:14:35 lr: 0.000085 grad: 0.1152 (0.1181) loss: 0.8900 (0.8913) time: 0.1681 data: 0.0883 max mem: 8233 +Train: [41] [1100/6250] eta: 0:14:24 lr: 0.000085 grad: 0.1214 (0.1185) loss: 0.8865 (0.8910) time: 0.1722 data: 0.0845 max mem: 8233 +Train: [41] [1200/6250] eta: 0:14:07 lr: 0.000085 grad: 0.1073 (0.1188) loss: 0.8886 (0.8907) time: 0.1592 data: 0.0713 max mem: 8233 +Train: [41] [1300/6250] eta: 0:13:43 lr: 0.000085 grad: 0.1136 (0.1192) loss: 0.8909 (0.8905) time: 0.1607 data: 0.0717 max mem: 8233 +Train: [41] [1400/6250] eta: 0:13:27 lr: 0.000085 grad: 0.1099 (0.1192) loss: 0.8855 (0.8903) time: 0.1859 data: 0.1060 max mem: 8233 +Train: [41] [1500/6250] eta: 0:13:11 lr: 0.000085 grad: 0.1136 (0.1192) loss: 0.8898 (0.8902) time: 0.1637 data: 0.0893 max mem: 8233 +Train: [41] [1600/6250] eta: 0:12:53 lr: 0.000085 grad: 0.1168 (0.1192) loss: 0.8884 (0.8900) time: 0.1686 data: 0.0899 max mem: 8233 +Train: [41] [1700/6250] eta: 0:12:35 lr: 0.000085 grad: 0.1054 (0.1190) loss: 0.8904 (0.8900) time: 0.2147 data: 0.1346 max mem: 8233 +Train: [41] [1800/6250] eta: 0:12:12 lr: 0.000085 grad: 0.1118 (0.1189) loss: 0.8898 (0.8899) time: 0.1408 data: 0.0483 max mem: 8233 +Train: [41] [1900/6250] eta: 0:11:53 lr: 0.000085 grad: 0.1262 (0.1193) loss: 0.8863 (0.8898) time: 0.1467 data: 0.0601 max mem: 8233 +Train: [41] [2000/6250] eta: 0:11:34 lr: 0.000085 grad: 0.1109 (0.1194) loss: 0.8910 (0.8897) time: 0.1451 data: 0.0603 max mem: 8233 +Train: [41] [2100/6250] eta: 0:11:16 lr: 0.000085 grad: 0.1083 (0.1195) loss: 0.8902 (0.8897) time: 0.1682 data: 0.0946 max mem: 8233 +Train: [41] [2200/6250] eta: 0:10:59 lr: 0.000085 grad: 0.1169 (0.1194) loss: 0.8880 (0.8897) time: 0.1603 data: 0.0788 max mem: 8233 +Train: [41] [2300/6250] eta: 0:10:43 lr: 0.000085 grad: 0.1078 (0.1192) loss: 0.8912 (0.8897) time: 0.1679 data: 0.0907 max mem: 8233 +Train: [41] [2400/6250] eta: 0:10:26 lr: 0.000085 grad: 0.1131 (0.1191) loss: 0.8931 (0.8897) time: 0.1482 data: 0.0668 max mem: 8233 +Train: [41] [2500/6250] eta: 0:10:08 lr: 0.000085 grad: 0.1207 (0.1191) loss: 0.8885 (0.8898) time: 0.1641 data: 0.0814 max mem: 8233 +Train: [41] [2600/6250] eta: 0:09:51 lr: 0.000085 grad: 0.1252 (0.1192) loss: 0.8889 (0.8898) time: 0.1573 data: 0.0849 max mem: 8233 +Train: [41] [2700/6250] eta: 0:09:36 lr: 0.000085 grad: 0.1251 (0.1193) loss: 0.8897 (0.8898) time: 0.1618 data: 0.0800 max mem: 8233 +Train: [41] [2800/6250] eta: 0:09:19 lr: 0.000085 grad: 0.1106 (0.1191) loss: 0.8914 (0.8898) time: 0.1637 data: 0.0939 max mem: 8233 +Train: [41] [2900/6250] eta: 0:09:02 lr: 0.000085 grad: 0.1215 (0.1191) loss: 0.8873 (0.8898) time: 0.1366 data: 0.0545 max mem: 8233 +Train: [41] [3000/6250] eta: 0:08:48 lr: 0.000085 grad: 0.1083 (0.1189) loss: 0.8883 (0.8898) time: 0.1878 data: 0.1121 max mem: 8233 +Train: [41] [3100/6250] eta: 0:08:31 lr: 0.000085 grad: 0.1160 (0.1190) loss: 0.8893 (0.8898) time: 0.1492 data: 0.0728 max mem: 8233 +Train: [41] [3200/6250] eta: 0:08:16 lr: 0.000085 grad: 0.1127 (0.1190) loss: 0.8918 (0.8898) time: 0.1911 data: 0.1157 max mem: 8233 +Train: [41] [3300/6250] eta: 0:08:00 lr: 0.000085 grad: 0.1269 (0.1191) loss: 0.8891 (0.8898) time: 0.1602 data: 0.0690 max mem: 8233 +Train: [41] [3400/6250] eta: 0:07:44 lr: 0.000085 grad: 0.1096 (0.1190) loss: 0.8922 (0.8898) time: 0.1670 data: 0.0851 max mem: 8233 +Train: [41] [3500/6250] eta: 0:07:29 lr: 0.000085 grad: 0.1143 (0.1190) loss: 0.8871 (0.8898) time: 0.1678 data: 0.0928 max mem: 8233 +Train: [41] [3600/6250] eta: 0:07:13 lr: 0.000085 grad: 0.1106 (0.1189) loss: 0.8917 (0.8899) time: 0.1518 data: 0.0642 max mem: 8233 +Train: [41] [3700/6250] eta: 0:06:56 lr: 0.000085 grad: 0.1113 (0.1189) loss: 0.8911 (0.8900) time: 0.1410 data: 0.0583 max mem: 8233 +Train: [41] [3800/6250] eta: 0:06:39 lr: 0.000085 grad: 0.1150 (0.1188) loss: 0.8917 (0.8900) time: 0.1437 data: 0.0617 max mem: 8233 +Train: [41] [3900/6250] eta: 0:06:23 lr: 0.000084 grad: 0.1077 (0.1188) loss: 0.8921 (0.8900) time: 0.1549 data: 0.0784 max mem: 8233 +Train: [41] [4000/6250] eta: 0:06:06 lr: 0.000084 grad: 0.1166 (0.1188) loss: 0.8947 (0.8900) time: 0.1579 data: 0.0736 max mem: 8233 +Train: [41] [4100/6250] eta: 0:05:49 lr: 0.000084 grad: 0.1094 (0.1187) loss: 0.8911 (0.8901) time: 0.2000 data: 0.1302 max mem: 8233 +Train: [41] [4200/6250] eta: 0:05:33 lr: 0.000084 grad: 0.1120 (0.1186) loss: 0.8956 (0.8902) time: 0.1681 data: 0.0826 max mem: 8233 +Train: [41] [4300/6250] eta: 0:05:16 lr: 0.000084 grad: 0.1128 (0.1185) loss: 0.8921 (0.8902) time: 0.1563 data: 0.0697 max mem: 8233 +Train: [41] [4400/6250] eta: 0:05:00 lr: 0.000084 grad: 0.1052 (0.1185) loss: 0.8925 (0.8903) time: 0.1445 data: 0.0627 max mem: 8233 +Train: [41] [4500/6250] eta: 0:04:43 lr: 0.000084 grad: 0.1087 (0.1183) loss: 0.8922 (0.8903) time: 0.1621 data: 0.0897 max mem: 8233 +Train: [41] [4600/6250] eta: 0:04:27 lr: 0.000084 grad: 0.1103 (0.1182) loss: 0.8927 (0.8904) time: 0.1612 data: 0.0774 max mem: 8233 +Train: [41] [4700/6250] eta: 0:04:11 lr: 0.000084 grad: 0.1090 (0.1181) loss: 0.8878 (0.8904) time: 0.1734 data: 0.0989 max mem: 8233 +Train: [41] [4800/6250] eta: 0:03:55 lr: 0.000084 grad: 0.1045 (0.1180) loss: 0.8914 (0.8904) time: 0.1125 data: 0.0264 max mem: 8233 +Train: [41] [4900/6250] eta: 0:03:39 lr: 0.000084 grad: 0.1090 (0.1180) loss: 0.8913 (0.8904) time: 0.1605 data: 0.0779 max mem: 8233 +Train: [41] [5000/6250] eta: 0:03:22 lr: 0.000084 grad: 0.1119 (0.1181) loss: 0.8937 (0.8905) time: 0.1462 data: 0.0729 max mem: 8233 +Train: [41] [5100/6250] eta: 0:03:06 lr: 0.000084 grad: 0.1125 (0.1180) loss: 0.8886 (0.8905) time: 0.1724 data: 0.0924 max mem: 8233 +Train: [41] [5200/6250] eta: 0:02:50 lr: 0.000084 grad: 0.1153 (0.1180) loss: 0.8878 (0.8904) time: 0.1538 data: 0.0886 max mem: 8233 +Train: [41] [5300/6250] eta: 0:02:34 lr: 0.000084 grad: 0.1155 (0.1180) loss: 0.8893 (0.8904) time: 0.1595 data: 0.0718 max mem: 8233 +Train: [41] [5400/6250] eta: 0:02:18 lr: 0.000084 grad: 0.1095 (0.1180) loss: 0.8901 (0.8904) time: 0.1593 data: 0.0665 max mem: 8233 +Train: [41] [5500/6250] eta: 0:02:01 lr: 0.000084 grad: 0.1091 (0.1179) loss: 0.8894 (0.8904) time: 0.1393 data: 0.0494 max mem: 8233 +Train: [41] [5600/6250] eta: 0:01:45 lr: 0.000084 grad: 0.1094 (0.1178) loss: 0.8911 (0.8904) time: 0.1256 data: 0.0393 max mem: 8233 +Train: [41] [5700/6250] eta: 0:01:29 lr: 0.000084 grad: 0.1086 (0.1178) loss: 0.8896 (0.8904) time: 0.1661 data: 0.0895 max mem: 8233 +Train: [41] [5800/6250] eta: 0:01:12 lr: 0.000084 grad: 0.1169 (0.1178) loss: 0.8899 (0.8904) time: 0.1582 data: 0.0805 max mem: 8233 +Train: [41] [5900/6250] eta: 0:00:56 lr: 0.000084 grad: 0.1158 (0.1177) loss: 0.8909 (0.8904) time: 0.1596 data: 0.0857 max mem: 8233 +Train: [41] [6000/6250] eta: 0:00:40 lr: 0.000084 grad: 0.1061 (0.1177) loss: 0.8885 (0.8904) time: 0.1611 data: 0.0830 max mem: 8233 +Train: [41] [6100/6250] eta: 0:00:24 lr: 0.000084 grad: 0.1108 (0.1177) loss: 0.8871 (0.8904) time: 0.1358 data: 0.0524 max mem: 8233 +Train: [41] [6200/6250] eta: 0:00:08 lr: 0.000084 grad: 0.1074 (0.1177) loss: 0.8894 (0.8904) time: 0.1523 data: 0.0727 max mem: 8233 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.1079 (0.1177) loss: 0.8959 (0.8904) time: 0.1580 data: 0.0917 max mem: 8233 +Train: [41] Total time: 0:16:57 (0.1627 s / it) +Averaged stats: lr: 0.000084 grad: 0.1079 (0.1177) loss: 0.8959 (0.8904) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:05:02 loss: 0.9086 (0.9086) time: 4.8726 data: 4.8448 max mem: 8233 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8985 (0.8988) time: 0.1491 data: 0.1274 max mem: 8233 +Eval (hcp-train-subset): [41] Total time: 0:00:13 (0.2252 s / it) +Averaged stats (hcp-train-subset): loss: 0.8985 (0.8988) +Eval (hcp-val): [41] [ 0/62] eta: 0:04:54 loss: 0.8910 (0.8910) time: 4.7536 data: 4.6903 max mem: 8233 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8947 (0.8959) time: 0.1144 data: 0.0925 max mem: 8233 +Eval (hcp-val): [41] Total time: 0:00:14 (0.2281 s / it) +Averaged stats (hcp-val): loss: 0.8947 (0.8959) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 8:16:25 lr: 0.000084 grad: 0.0775 (0.0775) loss: 0.9039 (0.9039) time: 4.7656 data: 4.4915 max mem: 8233 +Train: [42] [ 100/6250] eta: 0:22:30 lr: 0.000084 grad: 0.1097 (0.1124) loss: 0.8969 (0.8955) time: 0.1675 data: 0.0721 max mem: 8233 +Train: [42] [ 200/6250] eta: 0:19:52 lr: 0.000084 grad: 0.1089 (0.1153) loss: 0.8923 (0.8922) time: 0.1733 data: 0.0778 max mem: 8233 +Train: [42] [ 300/6250] eta: 0:18:20 lr: 0.000084 grad: 0.1170 (0.1147) loss: 0.8931 (0.8915) time: 0.1678 data: 0.0738 max mem: 8233 +Train: [42] [ 400/6250] eta: 0:17:23 lr: 0.000084 grad: 0.1133 (0.1148) loss: 0.8852 (0.8904) time: 0.1383 data: 0.0487 max mem: 8233 +Train: [42] [ 500/6250] eta: 0:16:42 lr: 0.000084 grad: 0.1126 (0.1155) loss: 0.8977 (0.8909) time: 0.1450 data: 0.0422 max mem: 8233 +Train: [42] [ 600/6250] eta: 0:16:08 lr: 0.000084 grad: 0.1114 (0.1154) loss: 0.8848 (0.8907) time: 0.1550 data: 0.0657 max mem: 8233 +Train: [42] [ 700/6250] eta: 0:15:33 lr: 0.000084 grad: 0.1156 (0.1158) loss: 0.8901 (0.8904) time: 0.1663 data: 0.0756 max mem: 8233 +Train: [42] [ 800/6250] eta: 0:15:06 lr: 0.000084 grad: 0.1118 (0.1156) loss: 0.8940 (0.8904) time: 0.1687 data: 0.0797 max mem: 8233 +Train: [42] [ 900/6250] eta: 0:14:35 lr: 0.000083 grad: 0.1096 (0.1154) loss: 0.8913 (0.8905) time: 0.1248 data: 0.0376 max mem: 8233 +Train: [42] [1000/6250] eta: 0:14:11 lr: 0.000083 grad: 0.1090 (0.1152) loss: 0.8849 (0.8903) time: 0.1456 data: 0.0656 max mem: 8233 +Train: [42] [1100/6250] eta: 0:14:04 lr: 0.000083 grad: 0.1119 (0.1154) loss: 0.8914 (0.8903) time: 0.1684 data: 0.0900 max mem: 8233 +Train: [42] [1200/6250] eta: 0:13:51 lr: 0.000083 grad: 0.1098 (0.1151) loss: 0.8908 (0.8901) time: 0.1690 data: 0.0885 max mem: 8233 +Train: [42] [1300/6250] eta: 0:13:37 lr: 0.000083 grad: 0.1170 (0.1154) loss: 0.8867 (0.8899) time: 0.1725 data: 0.0952 max mem: 8233 +Train: [42] [1400/6250] eta: 0:13:29 lr: 0.000083 grad: 0.1115 (0.1154) loss: 0.8868 (0.8898) time: 0.1994 data: 0.1147 max mem: 8233 +Train: [42] [1500/6250] eta: 0:13:12 lr: 0.000083 grad: 0.1075 (0.1155) loss: 0.8954 (0.8899) time: 0.1823 data: 0.0918 max mem: 8233 +Train: [42] [1600/6250] eta: 0:12:59 lr: 0.000083 grad: 0.1101 (0.1156) loss: 0.8926 (0.8900) time: 0.1889 data: 0.1077 max mem: 8233 +Train: [42] [1700/6250] eta: 0:12:44 lr: 0.000083 grad: 0.1047 (0.1154) loss: 0.8952 (0.8900) time: 0.1702 data: 0.0847 max mem: 8233 +Train: [42] [1800/6250] eta: 0:12:27 lr: 0.000083 grad: 0.1091 (0.1152) loss: 0.8911 (0.8901) time: 0.1619 data: 0.0906 max mem: 8233 +Train: [42] [1900/6250] eta: 0:12:09 lr: 0.000083 grad: 0.1082 (0.1151) loss: 0.8928 (0.8902) time: 0.1602 data: 0.0734 max mem: 8233 +Train: [42] [2000/6250] eta: 0:11:51 lr: 0.000083 grad: 0.1122 (0.1150) loss: 0.8904 (0.8903) time: 0.1591 data: 0.0844 max mem: 8233 +Train: [42] [2100/6250] eta: 0:11:35 lr: 0.000083 grad: 0.1071 (0.1151) loss: 0.8921 (0.8903) time: 0.1535 data: 0.0674 max mem: 8233 +Train: [42] [2200/6250] eta: 0:11:20 lr: 0.000083 grad: 0.1196 (0.1151) loss: 0.8918 (0.8902) time: 0.1360 data: 0.0471 max mem: 8233 +Train: [42] [2300/6250] eta: 0:11:01 lr: 0.000083 grad: 0.1095 (0.1151) loss: 0.8918 (0.8903) time: 0.1374 data: 0.0346 max mem: 8233 +Train: [42] [2400/6250] eta: 0:10:46 lr: 0.000083 grad: 0.1143 (0.1153) loss: 0.8920 (0.8902) time: 0.1598 data: 0.0694 max mem: 8233 +Train: [42] [2500/6250] eta: 0:10:30 lr: 0.000083 grad: 0.1159 (0.1152) loss: 0.8870 (0.8902) time: 0.1736 data: 0.1013 max mem: 8233 +Train: [42] [2600/6250] eta: 0:10:12 lr: 0.000083 grad: 0.1128 (0.1153) loss: 0.8927 (0.8902) time: 0.1121 data: 0.0205 max mem: 8233 +Train: [42] [2700/6250] eta: 0:09:54 lr: 0.000083 grad: 0.1119 (0.1153) loss: 0.8953 (0.8902) time: 0.1593 data: 0.0794 max mem: 8233 +Train: [42] [2800/6250] eta: 0:09:37 lr: 0.000083 grad: 0.1149 (0.1152) loss: 0.8851 (0.8902) time: 0.0980 data: 0.0003 max mem: 8233 +Train: [42] [2900/6250] eta: 0:09:20 lr: 0.000083 grad: 0.1078 (0.1152) loss: 0.8891 (0.8901) time: 0.1422 data: 0.0671 max mem: 8233 +Train: [42] [3000/6250] eta: 0:09:03 lr: 0.000083 grad: 0.1080 (0.1151) loss: 0.8897 (0.8901) time: 0.1457 data: 0.0765 max mem: 8233 +Train: [42] [3100/6250] eta: 0:08:45 lr: 0.000083 grad: 0.1143 (0.1152) loss: 0.8936 (0.8901) time: 0.1526 data: 0.0689 max mem: 8233 +Train: [42] [3200/6250] eta: 0:08:29 lr: 0.000083 grad: 0.1043 (0.1152) loss: 0.8835 (0.8901) time: 0.1576 data: 0.0791 max mem: 8233 +Train: [42] [3300/6250] eta: 0:08:13 lr: 0.000083 grad: 0.1130 (0.1152) loss: 0.8908 (0.8900) time: 0.1954 data: 0.1173 max mem: 8233 +Train: [42] [3400/6250] eta: 0:07:56 lr: 0.000083 grad: 0.1137 (0.1154) loss: 0.8917 (0.8901) time: 0.1813 data: 0.1043 max mem: 8233 +Train: [42] [3500/6250] eta: 0:07:40 lr: 0.000083 grad: 0.1072 (0.1152) loss: 0.8951 (0.8902) time: 0.1523 data: 0.0706 max mem: 8233 +Train: [42] [3600/6250] eta: 0:07:23 lr: 0.000083 grad: 0.1107 (0.1153) loss: 0.8936 (0.8902) time: 0.1637 data: 0.0827 max mem: 8233 +Train: [42] [3700/6250] eta: 0:07:06 lr: 0.000083 grad: 0.1143 (0.1153) loss: 0.8881 (0.8902) time: 0.1812 data: 0.1006 max mem: 8233 +Train: [42] [3800/6250] eta: 0:06:49 lr: 0.000083 grad: 0.1134 (0.1153) loss: 0.8939 (0.8903) time: 0.1367 data: 0.0545 max mem: 8233 +Train: [42] [3900/6250] eta: 0:06:32 lr: 0.000083 grad: 0.1051 (0.1153) loss: 0.8926 (0.8903) time: 0.1724 data: 0.0933 max mem: 8233 +Train: [42] [4000/6250] eta: 0:06:14 lr: 0.000083 grad: 0.1072 (0.1153) loss: 0.8918 (0.8902) time: 0.1626 data: 0.0784 max mem: 8233 +Train: [42] [4100/6250] eta: 0:05:57 lr: 0.000082 grad: 0.1162 (0.1152) loss: 0.8930 (0.8903) time: 0.1495 data: 0.0789 max mem: 8233 +Train: [42] [4200/6250] eta: 0:05:40 lr: 0.000082 grad: 0.1012 (0.1152) loss: 0.8923 (0.8903) time: 0.1624 data: 0.0782 max mem: 8233 +Train: [42] [4300/6250] eta: 0:05:23 lr: 0.000082 grad: 0.1122 (0.1152) loss: 0.8926 (0.8904) time: 0.1564 data: 0.0711 max mem: 8233 +Train: [42] [4400/6250] eta: 0:05:06 lr: 0.000082 grad: 0.1122 (0.1151) loss: 0.8951 (0.8904) time: 0.1703 data: 0.0936 max mem: 8233 +Train: [42] [4500/6250] eta: 0:04:50 lr: 0.000082 grad: 0.1066 (0.1151) loss: 0.8939 (0.8905) time: 0.1821 data: 0.1020 max mem: 8233 +Train: [42] [4600/6250] eta: 0:04:33 lr: 0.000082 grad: 0.1104 (0.1151) loss: 0.8938 (0.8905) time: 0.1824 data: 0.0919 max mem: 8233 +Train: [42] [4700/6250] eta: 0:04:16 lr: 0.000082 grad: 0.1081 (0.1150) loss: 0.8981 (0.8906) time: 0.1533 data: 0.0667 max mem: 8233 +Train: [42] [4800/6250] eta: 0:03:59 lr: 0.000082 grad: 0.1056 (0.1150) loss: 0.8971 (0.8907) time: 0.1652 data: 0.0812 max mem: 8233 +Train: [42] [4900/6250] eta: 0:03:43 lr: 0.000082 grad: 0.1065 (0.1149) loss: 0.8964 (0.8908) time: 0.1250 data: 0.0310 max mem: 8233 +Train: [42] [5000/6250] eta: 0:03:27 lr: 0.000082 grad: 0.1111 (0.1149) loss: 0.8921 (0.8909) time: 0.1574 data: 0.0765 max mem: 8233 +Train: [42] [5100/6250] eta: 0:03:10 lr: 0.000082 grad: 0.1145 (0.1149) loss: 0.8929 (0.8910) time: 0.1651 data: 0.0769 max mem: 8233 +Train: [42] [5200/6250] eta: 0:02:54 lr: 0.000082 grad: 0.1106 (0.1150) loss: 0.8954 (0.8911) time: 0.1911 data: 0.1050 max mem: 8233 +Train: [42] [5300/6250] eta: 0:02:37 lr: 0.000082 grad: 0.1027 (0.1151) loss: 0.8986 (0.8912) time: 0.1781 data: 0.0894 max mem: 8233 +Train: [42] [5400/6250] eta: 0:02:20 lr: 0.000082 grad: 0.1164 (0.1151) loss: 0.8952 (0.8912) time: 0.1884 data: 0.1057 max mem: 8233 +Train: [42] [5500/6250] eta: 0:02:04 lr: 0.000082 grad: 0.1135 (0.1151) loss: 0.8870 (0.8913) time: 0.1492 data: 0.0599 max mem: 8233 +Train: [42] [5600/6250] eta: 0:01:47 lr: 0.000082 grad: 0.1133 (0.1152) loss: 0.8963 (0.8913) time: 0.1813 data: 0.1011 max mem: 8233 +Train: [42] [5700/6250] eta: 0:01:30 lr: 0.000082 grad: 0.1079 (0.1152) loss: 0.8892 (0.8913) time: 0.1421 data: 0.0484 max mem: 8233 +Train: [42] [5800/6250] eta: 0:01:14 lr: 0.000082 grad: 0.1127 (0.1153) loss: 0.8918 (0.8913) time: 0.1428 data: 0.0605 max mem: 8233 +Train: [42] [5900/6250] eta: 0:00:57 lr: 0.000082 grad: 0.1156 (0.1153) loss: 0.8919 (0.8913) time: 0.1316 data: 0.0445 max mem: 8233 +Train: [42] [6000/6250] eta: 0:00:41 lr: 0.000082 grad: 0.1216 (0.1154) loss: 0.8880 (0.8913) time: 0.1560 data: 0.0711 max mem: 8233 +Train: [42] [6100/6250] eta: 0:00:24 lr: 0.000082 grad: 0.1200 (0.1156) loss: 0.8927 (0.8913) time: 0.1577 data: 0.0782 max mem: 8233 +Train: [42] [6200/6250] eta: 0:00:08 lr: 0.000082 grad: 0.1095 (0.1156) loss: 0.8902 (0.8913) time: 0.1660 data: 0.0893 max mem: 8233 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.1113 (0.1156) loss: 0.8883 (0.8912) time: 0.1419 data: 0.0650 max mem: 8233 +Train: [42] Total time: 0:17:12 (0.1652 s / it) +Averaged stats: lr: 0.000082 grad: 0.1113 (0.1156) loss: 0.8883 (0.8912) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:05:39 loss: 0.9079 (0.9079) time: 5.4826 data: 5.4554 max mem: 8233 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8978 (0.8992) time: 0.1404 data: 0.1197 max mem: 8233 +Eval (hcp-train-subset): [42] Total time: 0:00:14 (0.2365 s / it) +Averaged stats (hcp-train-subset): loss: 0.8978 (0.8992) +Eval (hcp-val): [42] [ 0/62] eta: 0:03:54 loss: 0.8902 (0.8902) time: 3.7842 data: 3.7016 max mem: 8233 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8947 (0.8952) time: 0.1430 data: 0.1211 max mem: 8233 +Eval (hcp-val): [42] Total time: 0:00:14 (0.2356 s / it) +Averaged stats (hcp-val): loss: 0.8947 (0.8952) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 11:23:47 lr: 0.000082 grad: 0.0851 (0.0851) loss: 0.8995 (0.8995) time: 6.5645 data: 6.4515 max mem: 8233 +Train: [43] [ 100/6250] eta: 0:23:04 lr: 0.000082 grad: 0.1131 (0.1227) loss: 0.8882 (0.8953) time: 0.1675 data: 0.0730 max mem: 8233 +Train: [43] [ 200/6250] eta: 0:20:35 lr: 0.000082 grad: 0.1191 (0.1222) loss: 0.8949 (0.8932) time: 0.1761 data: 0.0811 max mem: 8233 +Train: [43] [ 300/6250] eta: 0:18:54 lr: 0.000082 grad: 0.1179 (0.1203) loss: 0.8940 (0.8928) time: 0.1514 data: 0.0479 max mem: 8233 +Train: [43] [ 400/6250] eta: 0:18:14 lr: 0.000082 grad: 0.1136 (0.1189) loss: 0.8870 (0.8923) time: 0.1750 data: 0.0808 max mem: 8233 +Train: [43] [ 500/6250] eta: 0:17:44 lr: 0.000082 grad: 0.1113 (0.1187) loss: 0.8881 (0.8917) time: 0.1789 data: 0.0918 max mem: 8233 +Train: [43] [ 600/6250] eta: 0:17:05 lr: 0.000082 grad: 0.1142 (0.1185) loss: 0.8897 (0.8914) time: 0.1681 data: 0.0971 max mem: 8233 +Train: [43] [ 700/6250] eta: 0:16:32 lr: 0.000082 grad: 0.1072 (0.1182) loss: 0.8942 (0.8914) time: 0.1551 data: 0.0722 max mem: 8233 +Train: [43] [ 800/6250] eta: 0:16:05 lr: 0.000082 grad: 0.1024 (0.1179) loss: 0.8960 (0.8918) time: 0.1769 data: 0.0941 max mem: 8233 +Train: [43] [ 900/6250] eta: 0:16:03 lr: 0.000082 grad: 0.1104 (0.1176) loss: 0.8952 (0.8919) time: 0.1662 data: 0.0614 max mem: 8233 +Train: [43] [1000/6250] eta: 0:15:31 lr: 0.000081 grad: 0.1076 (0.1174) loss: 0.8863 (0.8917) time: 0.1286 data: 0.0447 max mem: 8233 +Train: [43] [1100/6250] eta: 0:15:10 lr: 0.000081 grad: 0.1187 (0.1173) loss: 0.8886 (0.8913) time: 0.1626 data: 0.0907 max mem: 8233 +Train: [43] [1200/6250] eta: 0:14:51 lr: 0.000081 grad: 0.1097 (0.1172) loss: 0.8890 (0.8912) time: 0.1768 data: 0.0935 max mem: 8233 +Train: [43] [1300/6250] eta: 0:14:24 lr: 0.000081 grad: 0.1089 (0.1173) loss: 0.8929 (0.8912) time: 0.1708 data: 0.0902 max mem: 8233 +Train: [43] [1400/6250] eta: 0:14:02 lr: 0.000081 grad: 0.1202 (0.1171) loss: 0.8875 (0.8913) time: 0.1743 data: 0.0738 max mem: 8233 +Train: [43] [1500/6250] eta: 0:13:45 lr: 0.000081 grad: 0.1145 (0.1172) loss: 0.8888 (0.8912) time: 0.1979 data: 0.1129 max mem: 8233 +Train: [43] [1600/6250] eta: 0:13:23 lr: 0.000081 grad: 0.1071 (0.1172) loss: 0.8961 (0.8912) time: 0.1434 data: 0.0457 max mem: 8233 +Train: [43] [1700/6250] eta: 0:13:04 lr: 0.000081 grad: 0.1152 (0.1173) loss: 0.8916 (0.8911) time: 0.1578 data: 0.0752 max mem: 8233 +Train: [43] [1800/6250] eta: 0:12:43 lr: 0.000081 grad: 0.1081 (0.1172) loss: 0.8939 (0.8911) time: 0.1507 data: 0.0604 max mem: 8233 +Train: [43] [1900/6250] eta: 0:12:22 lr: 0.000081 grad: 0.1116 (0.1172) loss: 0.8905 (0.8911) time: 0.1418 data: 0.0703 max mem: 8233 +Train: [43] [2000/6250] eta: 0:12:02 lr: 0.000081 grad: 0.1113 (0.1173) loss: 0.8914 (0.8911) time: 0.1644 data: 0.0908 max mem: 8233 +Train: [43] [2100/6250] eta: 0:11:42 lr: 0.000081 grad: 0.1136 (0.1172) loss: 0.8889 (0.8912) time: 0.1515 data: 0.0690 max mem: 8233 +Train: [43] [2200/6250] eta: 0:11:25 lr: 0.000081 grad: 0.1041 (0.1171) loss: 0.8906 (0.8912) time: 0.1690 data: 0.0804 max mem: 8233 +Train: [43] [2300/6250] eta: 0:11:12 lr: 0.000081 grad: 0.1035 (0.1170) loss: 0.8951 (0.8914) time: 0.3295 data: 0.2559 max mem: 8233 +Train: [43] [2400/6250] eta: 0:10:50 lr: 0.000081 grad: 0.1090 (0.1168) loss: 0.8983 (0.8915) time: 0.1352 data: 0.0510 max mem: 8233 +Train: [43] [2500/6250] eta: 0:10:32 lr: 0.000081 grad: 0.1105 (0.1169) loss: 0.8942 (0.8916) time: 0.1660 data: 0.0924 max mem: 8233 +Train: [43] [2600/6250] eta: 0:10:14 lr: 0.000081 grad: 0.1053 (0.1167) loss: 0.8926 (0.8916) time: 0.1455 data: 0.0485 max mem: 8233 +Train: [43] [2700/6250] eta: 0:09:56 lr: 0.000081 grad: 0.1134 (0.1166) loss: 0.8938 (0.8916) time: 0.1374 data: 0.0483 max mem: 8233 +Train: [43] [2800/6250] eta: 0:09:39 lr: 0.000081 grad: 0.1131 (0.1165) loss: 0.8890 (0.8917) time: 0.1602 data: 0.0809 max mem: 8233 +Train: [43] [2900/6250] eta: 0:09:21 lr: 0.000081 grad: 0.1097 (0.1164) loss: 0.8915 (0.8916) time: 0.1537 data: 0.0753 max mem: 8233 +Train: [43] [3000/6250] eta: 0:09:05 lr: 0.000081 grad: 0.1110 (0.1166) loss: 0.8933 (0.8916) time: 0.1350 data: 0.0618 max mem: 8233 +Train: [43] [3100/6250] eta: 0:08:48 lr: 0.000081 grad: 0.1121 (0.1170) loss: 0.8888 (0.8915) time: 0.1777 data: 0.1120 max mem: 8233 +Train: [43] [3200/6250] eta: 0:08:30 lr: 0.000081 grad: 0.1217 (0.1171) loss: 0.8883 (0.8914) time: 0.1521 data: 0.0769 max mem: 8233 +Train: [43] [3300/6250] eta: 0:08:14 lr: 0.000081 grad: 0.1280 (0.1172) loss: 0.8887 (0.8913) time: 0.1648 data: 0.0820 max mem: 8233 +Train: [43] [3400/6250] eta: 0:07:57 lr: 0.000081 grad: 0.1148 (0.1172) loss: 0.8864 (0.8912) time: 0.1751 data: 0.0842 max mem: 8233 +Train: [43] [3500/6250] eta: 0:07:41 lr: 0.000081 grad: 0.1203 (0.1173) loss: 0.8838 (0.8911) time: 0.1708 data: 0.0975 max mem: 8233 +Train: [43] [3600/6250] eta: 0:07:24 lr: 0.000081 grad: 0.1099 (0.1173) loss: 0.8897 (0.8910) time: 0.1734 data: 0.0955 max mem: 8233 +Train: [43] [3700/6250] eta: 0:07:07 lr: 0.000081 grad: 0.1205 (0.1174) loss: 0.8835 (0.8909) time: 0.1466 data: 0.0670 max mem: 8233 +Train: [43] [3800/6250] eta: 0:06:49 lr: 0.000081 grad: 0.1217 (0.1175) loss: 0.8890 (0.8908) time: 0.1665 data: 0.0813 max mem: 8233 +Train: [43] [3900/6250] eta: 0:06:32 lr: 0.000081 grad: 0.1204 (0.1176) loss: 0.8846 (0.8907) time: 0.1822 data: 0.0889 max mem: 8233 +Train: [43] [4000/6250] eta: 0:06:15 lr: 0.000081 grad: 0.1171 (0.1177) loss: 0.8877 (0.8906) time: 0.1465 data: 0.0568 max mem: 8233 +Train: [43] [4100/6250] eta: 0:05:58 lr: 0.000081 grad: 0.1182 (0.1178) loss: 0.8845 (0.8905) time: 0.1652 data: 0.0798 max mem: 8233 +Train: [43] [4200/6250] eta: 0:05:41 lr: 0.000080 grad: 0.1163 (0.1179) loss: 0.8867 (0.8904) time: 0.1635 data: 0.0836 max mem: 8233 +Train: [43] [4300/6250] eta: 0:05:23 lr: 0.000080 grad: 0.1105 (0.1180) loss: 0.8872 (0.8904) time: 0.1398 data: 0.0513 max mem: 8233 +Train: [43] [4400/6250] eta: 0:05:06 lr: 0.000080 grad: 0.1165 (0.1180) loss: 0.8868 (0.8903) time: 0.1654 data: 0.0859 max mem: 8233 +Train: [43] [4500/6250] eta: 0:04:49 lr: 0.000080 grad: 0.1114 (0.1180) loss: 0.8862 (0.8902) time: 0.1506 data: 0.0804 max mem: 8233 +Train: [43] [4600/6250] eta: 0:04:32 lr: 0.000080 grad: 0.1141 (0.1182) loss: 0.8880 (0.8901) time: 0.1481 data: 0.0628 max mem: 8233 +Train: [43] [4700/6250] eta: 0:04:15 lr: 0.000080 grad: 0.1144 (0.1182) loss: 0.8861 (0.8900) time: 0.1423 data: 0.0581 max mem: 8233 +Train: [43] [4800/6250] eta: 0:03:58 lr: 0.000080 grad: 0.1172 (0.1183) loss: 0.8898 (0.8900) time: 0.1248 data: 0.0401 max mem: 8233 +Train: [43] [4900/6250] eta: 0:03:42 lr: 0.000080 grad: 0.1177 (0.1184) loss: 0.8919 (0.8899) time: 0.1848 data: 0.1213 max mem: 8233 +Train: [43] [5000/6250] eta: 0:03:25 lr: 0.000080 grad: 0.1224 (0.1185) loss: 0.8843 (0.8899) time: 0.1696 data: 0.0941 max mem: 8233 +Train: [43] [5100/6250] eta: 0:03:09 lr: 0.000080 grad: 0.1135 (0.1185) loss: 0.8881 (0.8899) time: 0.1805 data: 0.1059 max mem: 8233 +Train: [43] [5200/6250] eta: 0:02:52 lr: 0.000080 grad: 0.1160 (0.1186) loss: 0.8849 (0.8898) time: 0.1731 data: 0.0914 max mem: 8233 +Train: [43] [5300/6250] eta: 0:02:36 lr: 0.000080 grad: 0.1150 (0.1187) loss: 0.8858 (0.8897) time: 0.2032 data: 0.1331 max mem: 8233 +Train: [43] [5400/6250] eta: 0:02:19 lr: 0.000080 grad: 0.1288 (0.1188) loss: 0.8854 (0.8896) time: 0.1556 data: 0.0696 max mem: 8233 +Train: [43] [5500/6250] eta: 0:02:03 lr: 0.000080 grad: 0.1161 (0.1189) loss: 0.8839 (0.8896) time: 0.1676 data: 0.0829 max mem: 8233 +Train: [43] [5600/6250] eta: 0:01:46 lr: 0.000080 grad: 0.1065 (0.1189) loss: 0.8892 (0.8895) time: 0.1507 data: 0.0754 max mem: 8233 +Train: [43] [5700/6250] eta: 0:01:30 lr: 0.000080 grad: 0.1318 (0.1191) loss: 0.8881 (0.8895) time: 0.1909 data: 0.1071 max mem: 8233 +Train: [43] [5800/6250] eta: 0:01:13 lr: 0.000080 grad: 0.1160 (0.1192) loss: 0.8854 (0.8894) time: 0.1370 data: 0.0482 max mem: 8233 +Train: [43] [5900/6250] eta: 0:00:57 lr: 0.000080 grad: 0.1160 (0.1193) loss: 0.8854 (0.8894) time: 0.1663 data: 0.0883 max mem: 8233 +Train: [43] [6000/6250] eta: 0:00:40 lr: 0.000080 grad: 0.1205 (0.1194) loss: 0.8898 (0.8893) time: 0.1763 data: 0.0989 max mem: 8233 +Train: [43] [6100/6250] eta: 0:00:24 lr: 0.000080 grad: 0.1292 (0.1195) loss: 0.8865 (0.8893) time: 0.1829 data: 0.0917 max mem: 8233 +Train: [43] [6200/6250] eta: 0:00:08 lr: 0.000080 grad: 0.1141 (0.1196) loss: 0.8871 (0.8892) time: 0.1629 data: 0.0887 max mem: 8233 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.1232 (0.1196) loss: 0.8923 (0.8892) time: 0.1656 data: 0.0838 max mem: 8233 +Train: [43] Total time: 0:17:09 (0.1647 s / it) +Averaged stats: lr: 0.000080 grad: 0.1232 (0.1196) loss: 0.8923 (0.8892) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:05:10 loss: 0.9069 (0.9069) time: 5.0075 data: 4.9779 max mem: 8233 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8968 (0.8983) time: 0.1474 data: 0.1257 max mem: 8233 +Eval (hcp-train-subset): [43] Total time: 0:00:14 (0.2329 s / it) +Averaged stats (hcp-train-subset): loss: 0.8968 (0.8983) +Eval (hcp-val): [43] [ 0/62] eta: 0:04:40 loss: 0.8923 (0.8923) time: 4.5225 data: 4.4403 max mem: 8233 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8942 (0.8948) time: 0.1152 data: 0.0935 max mem: 8233 +Eval (hcp-val): [43] Total time: 0:00:14 (0.2320 s / it) +Averaged stats (hcp-val): loss: 0.8942 (0.8948) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 9:39:30 lr: 0.000080 grad: 0.1859 (0.1859) loss: 0.9180 (0.9180) time: 5.5633 data: 5.2497 max mem: 8233 +Train: [44] [ 100/6250] eta: 0:23:24 lr: 0.000080 grad: 0.1075 (0.1194) loss: 0.8963 (0.8932) time: 0.2088 data: 0.1025 max mem: 8233 +Train: [44] [ 200/6250] eta: 0:20:05 lr: 0.000080 grad: 0.1137 (0.1188) loss: 0.8895 (0.8918) time: 0.1702 data: 0.0571 max mem: 8233 +Train: [44] [ 300/6250] eta: 0:18:33 lr: 0.000080 grad: 0.1074 (0.1191) loss: 0.8932 (0.8896) time: 0.1483 data: 0.0531 max mem: 8233 +Train: [44] [ 400/6250] eta: 0:17:32 lr: 0.000080 grad: 0.1080 (0.1184) loss: 0.8948 (0.8890) time: 0.1665 data: 0.0699 max mem: 8233 +Train: [44] [ 500/6250] eta: 0:16:56 lr: 0.000080 grad: 0.1117 (0.1179) loss: 0.8940 (0.8896) time: 0.1861 data: 0.0944 max mem: 8233 +Train: [44] [ 600/6250] eta: 0:16:15 lr: 0.000080 grad: 0.1144 (0.1176) loss: 0.8910 (0.8898) time: 0.1530 data: 0.0682 max mem: 8233 +Train: [44] [ 700/6250] eta: 0:15:58 lr: 0.000080 grad: 0.1078 (0.1165) loss: 0.8925 (0.8902) time: 0.2104 data: 0.1167 max mem: 8233 +Train: [44] [ 800/6250] eta: 0:15:30 lr: 0.000080 grad: 0.1077 (0.1160) loss: 0.8962 (0.8906) time: 0.1868 data: 0.0985 max mem: 8233 +Train: [44] [ 900/6250] eta: 0:15:11 lr: 0.000080 grad: 0.1088 (0.1154) loss: 0.8954 (0.8908) time: 0.1414 data: 0.0638 max mem: 8233 +Train: [44] [1000/6250] eta: 0:14:45 lr: 0.000080 grad: 0.1107 (0.1150) loss: 0.8925 (0.8910) time: 0.1611 data: 0.0761 max mem: 8233 +Train: [44] [1100/6250] eta: 0:14:30 lr: 0.000079 grad: 0.1078 (0.1149) loss: 0.8929 (0.8910) time: 0.1761 data: 0.0987 max mem: 8233 +Train: [44] [1200/6250] eta: 0:14:08 lr: 0.000079 grad: 0.1056 (0.1145) loss: 0.8936 (0.8911) time: 0.1669 data: 0.0869 max mem: 8233 +Train: [44] [1300/6250] eta: 0:13:45 lr: 0.000079 grad: 0.1118 (0.1145) loss: 0.8916 (0.8912) time: 0.1436 data: 0.0741 max mem: 8233 +Train: [44] [1400/6250] eta: 0:13:30 lr: 0.000079 grad: 0.1061 (0.1141) loss: 0.8909 (0.8914) time: 0.1798 data: 0.0957 max mem: 8233 +Train: [44] [1500/6250] eta: 0:13:11 lr: 0.000079 grad: 0.1168 (0.1142) loss: 0.8914 (0.8914) time: 0.1560 data: 0.0565 max mem: 8233 +Train: [44] [1600/6250] eta: 0:12:56 lr: 0.000079 grad: 0.1078 (0.1141) loss: 0.8915 (0.8913) time: 0.1850 data: 0.1161 max mem: 8233 +Train: [44] [1700/6250] eta: 0:12:36 lr: 0.000079 grad: 0.1188 (0.1142) loss: 0.8937 (0.8914) time: 0.1538 data: 0.0774 max mem: 8233 +Train: [44] [1800/6250] eta: 0:12:17 lr: 0.000079 grad: 0.1172 (0.1144) loss: 0.8892 (0.8912) time: 0.1597 data: 0.0643 max mem: 8233 +Train: [44] [1900/6250] eta: 0:11:58 lr: 0.000079 grad: 0.1116 (0.1144) loss: 0.8941 (0.8912) time: 0.1653 data: 0.0810 max mem: 8233 +Train: [44] [2000/6250] eta: 0:11:39 lr: 0.000079 grad: 0.1114 (0.1145) loss: 0.8908 (0.8910) time: 0.1484 data: 0.0699 max mem: 8233 +Train: [44] [2100/6250] eta: 0:11:20 lr: 0.000079 grad: 0.1085 (0.1146) loss: 0.8920 (0.8908) time: 0.1383 data: 0.0581 max mem: 8233 +Train: [44] [2200/6250] eta: 0:11:04 lr: 0.000079 grad: 0.1143 (0.1147) loss: 0.8854 (0.8907) time: 0.1667 data: 0.0909 max mem: 8233 +Train: [44] [2300/6250] eta: 0:10:45 lr: 0.000079 grad: 0.1138 (0.1148) loss: 0.8887 (0.8905) time: 0.1590 data: 0.0730 max mem: 8233 +Train: [44] [2400/6250] eta: 0:10:28 lr: 0.000079 grad: 0.1151 (0.1149) loss: 0.8882 (0.8905) time: 0.1619 data: 0.0817 max mem: 8233 +Train: [44] [2500/6250] eta: 0:10:13 lr: 0.000079 grad: 0.1158 (0.1151) loss: 0.8830 (0.8903) time: 0.1489 data: 0.0454 max mem: 8233 +Train: [44] [2600/6250] eta: 0:09:55 lr: 0.000079 grad: 0.1141 (0.1152) loss: 0.8891 (0.8901) time: 0.1505 data: 0.0577 max mem: 8233 +Train: [44] [2700/6250] eta: 0:09:38 lr: 0.000079 grad: 0.1105 (0.1153) loss: 0.8866 (0.8900) time: 0.1681 data: 0.0915 max mem: 8233 +Train: [44] [2800/6250] eta: 0:09:21 lr: 0.000079 grad: 0.1182 (0.1154) loss: 0.8851 (0.8898) time: 0.1578 data: 0.0679 max mem: 8233 +Train: [44] [2900/6250] eta: 0:09:04 lr: 0.000079 grad: 0.1125 (0.1155) loss: 0.8838 (0.8896) time: 0.1633 data: 0.0790 max mem: 8233 +Train: [44] [3000/6250] eta: 0:08:48 lr: 0.000079 grad: 0.1186 (0.1156) loss: 0.8849 (0.8895) time: 0.2081 data: 0.1435 max mem: 8233 +Train: [44] [3100/6250] eta: 0:08:31 lr: 0.000079 grad: 0.1161 (0.1157) loss: 0.8798 (0.8893) time: 0.1449 data: 0.0612 max mem: 8233 +Train: [44] [3200/6250] eta: 0:08:15 lr: 0.000079 grad: 0.1080 (0.1158) loss: 0.8797 (0.8891) time: 0.1497 data: 0.0792 max mem: 8233 +Train: [44] [3300/6250] eta: 0:07:58 lr: 0.000079 grad: 0.1105 (0.1161) loss: 0.8834 (0.8889) time: 0.1757 data: 0.0967 max mem: 8233 +Train: [44] [3400/6250] eta: 0:07:42 lr: 0.000079 grad: 0.1093 (0.1163) loss: 0.8861 (0.8888) time: 0.1614 data: 0.0767 max mem: 8233 +Train: [44] [3500/6250] eta: 0:07:26 lr: 0.000079 grad: 0.1068 (0.1163) loss: 0.8830 (0.8886) time: 0.1332 data: 0.0589 max mem: 8233 +Train: [44] [3600/6250] eta: 0:07:09 lr: 0.000079 grad: 0.1198 (0.1164) loss: 0.8858 (0.8885) time: 0.1512 data: 0.0734 max mem: 8233 +Train: [44] [3700/6250] eta: 0:06:52 lr: 0.000079 grad: 0.1113 (0.1164) loss: 0.8883 (0.8884) time: 0.1470 data: 0.0549 max mem: 8233 +Train: [44] [3800/6250] eta: 0:06:35 lr: 0.000079 grad: 0.1194 (0.1165) loss: 0.8850 (0.8884) time: 0.1475 data: 0.0562 max mem: 8233 +Train: [44] [3900/6250] eta: 0:06:18 lr: 0.000079 grad: 0.1109 (0.1165) loss: 0.8857 (0.8883) time: 0.1501 data: 0.0691 max mem: 8233 +Train: [44] [4000/6250] eta: 0:06:02 lr: 0.000079 grad: 0.1122 (0.1165) loss: 0.8884 (0.8882) time: 0.1557 data: 0.0744 max mem: 8233 +Train: [44] [4100/6250] eta: 0:05:46 lr: 0.000079 grad: 0.1113 (0.1166) loss: 0.8892 (0.8882) time: 0.1321 data: 0.0544 max mem: 8233 +Train: [44] [4200/6250] eta: 0:05:29 lr: 0.000078 grad: 0.1268 (0.1166) loss: 0.8801 (0.8882) time: 0.1607 data: 0.0831 max mem: 8233 +Train: [44] [4300/6250] eta: 0:05:13 lr: 0.000078 grad: 0.1128 (0.1166) loss: 0.8840 (0.8881) time: 0.1557 data: 0.0736 max mem: 8233 +Train: [44] [4400/6250] eta: 0:04:57 lr: 0.000078 grad: 0.1187 (0.1167) loss: 0.8873 (0.8881) time: 0.1440 data: 0.0582 max mem: 8233 +Train: [44] [4500/6250] eta: 0:04:40 lr: 0.000078 grad: 0.1165 (0.1168) loss: 0.8852 (0.8880) time: 0.1490 data: 0.0707 max mem: 8233 +Train: [44] [4600/6250] eta: 0:04:24 lr: 0.000078 grad: 0.1233 (0.1169) loss: 0.8841 (0.8879) time: 0.1572 data: 0.0719 max mem: 8233 +Train: [44] [4700/6250] eta: 0:04:08 lr: 0.000078 grad: 0.1168 (0.1169) loss: 0.8865 (0.8879) time: 0.1931 data: 0.1148 max mem: 8233 +Train: [44] [4800/6250] eta: 0:03:52 lr: 0.000078 grad: 0.1074 (0.1170) loss: 0.8841 (0.8878) time: 0.2000 data: 0.1192 max mem: 8233 +Train: [44] [4900/6250] eta: 0:03:36 lr: 0.000078 grad: 0.1168 (0.1170) loss: 0.8869 (0.8877) time: 0.1615 data: 0.0773 max mem: 8233 +Train: [44] [5000/6250] eta: 0:03:20 lr: 0.000078 grad: 0.1170 (0.1170) loss: 0.8872 (0.8877) time: 0.1593 data: 0.0792 max mem: 8233 +Train: [44] [5100/6250] eta: 0:03:05 lr: 0.000078 grad: 0.1169 (0.1171) loss: 0.8828 (0.8877) time: 0.1916 data: 0.1133 max mem: 8233 +Train: [44] [5200/6250] eta: 0:02:49 lr: 0.000078 grad: 0.1119 (0.1171) loss: 0.8870 (0.8877) time: 0.1717 data: 0.0865 max mem: 8233 +Train: [44] [5300/6250] eta: 0:02:33 lr: 0.000078 grad: 0.1149 (0.1170) loss: 0.8896 (0.8877) time: 0.1754 data: 0.0883 max mem: 8233 +Train: [44] [5400/6250] eta: 0:02:17 lr: 0.000078 grad: 0.1080 (0.1171) loss: 0.8871 (0.8877) time: 0.1955 data: 0.1031 max mem: 8233 +Train: [44] [5500/6250] eta: 0:02:01 lr: 0.000078 grad: 0.1114 (0.1171) loss: 0.8870 (0.8877) time: 0.1790 data: 0.0979 max mem: 8233 +Train: [44] [5600/6250] eta: 0:01:45 lr: 0.000078 grad: 0.1173 (0.1171) loss: 0.8897 (0.8877) time: 0.1808 data: 0.0942 max mem: 8233 +Train: [44] [5700/6250] eta: 0:01:29 lr: 0.000078 grad: 0.1126 (0.1172) loss: 0.8886 (0.8877) time: 0.1751 data: 0.0928 max mem: 8233 +Train: [44] [5800/6250] eta: 0:01:12 lr: 0.000078 grad: 0.1141 (0.1172) loss: 0.8898 (0.8877) time: 0.1686 data: 0.0681 max mem: 8233 +Train: [44] [5900/6250] eta: 0:00:56 lr: 0.000078 grad: 0.1103 (0.1171) loss: 0.8881 (0.8877) time: 0.1601 data: 0.0851 max mem: 8233 +Train: [44] [6000/6250] eta: 0:00:40 lr: 0.000078 grad: 0.1139 (0.1171) loss: 0.8905 (0.8878) time: 0.2124 data: 0.1330 max mem: 8233 +Train: [44] [6100/6250] eta: 0:00:24 lr: 0.000078 grad: 0.1083 (0.1171) loss: 0.8910 (0.8878) time: 0.1042 data: 0.0003 max mem: 8233 +Train: [44] [6200/6250] eta: 0:00:08 lr: 0.000078 grad: 0.1116 (0.1171) loss: 0.8871 (0.8878) time: 0.3718 data: 0.3030 max mem: 8233 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.1107 (0.1171) loss: 0.8920 (0.8878) time: 0.1706 data: 0.0764 max mem: 8233 +Train: [44] Total time: 0:17:04 (0.1639 s / it) +Averaged stats: lr: 0.000078 grad: 0.1107 (0.1171) loss: 0.8920 (0.8878) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:05:04 loss: 0.9061 (0.9061) time: 4.9036 data: 4.8759 max mem: 8233 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8982 (0.8973) time: 0.1266 data: 0.1061 max mem: 8233 +Eval (hcp-train-subset): [44] Total time: 0:00:14 (0.2270 s / it) +Averaged stats (hcp-train-subset): loss: 0.8982 (0.8973) +Making plots (hcp-train-subset): example=14 +Eval (hcp-val): [44] [ 0/62] eta: 0:06:10 loss: 0.8931 (0.8931) time: 5.9744 data: 5.9480 max mem: 8233 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8928 (0.8935) time: 0.1541 data: 0.1321 max mem: 8233 +Eval (hcp-val): [44] Total time: 0:00:14 (0.2408 s / it) +Averaged stats (hcp-val): loss: 0.8928 (0.8935) +Making plots (hcp-val): example=45 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 11:15:30 lr: 0.000078 grad: 0.1296 (0.1296) loss: 0.8952 (0.8952) time: 6.4849 data: 6.3335 max mem: 8233 +Train: [45] [ 100/6250] eta: 0:23:29 lr: 0.000078 grad: 0.1033 (0.1159) loss: 0.8973 (0.8915) time: 0.1867 data: 0.0816 max mem: 8233 +Train: [45] [ 200/6250] eta: 0:20:33 lr: 0.000078 grad: 0.1095 (0.1179) loss: 0.8910 (0.8902) time: 0.1742 data: 0.0673 max mem: 8233 +Train: [45] [ 300/6250] eta: 0:19:31 lr: 0.000078 grad: 0.1131 (0.1175) loss: 0.8844 (0.8883) time: 0.1692 data: 0.0688 max mem: 8233 +Train: [45] [ 400/6250] eta: 0:18:33 lr: 0.000078 grad: 0.1090 (0.1165) loss: 0.8872 (0.8887) time: 0.1590 data: 0.0521 max mem: 8233 +Train: [45] [ 500/6250] eta: 0:17:43 lr: 0.000078 grad: 0.1143 (0.1166) loss: 0.8844 (0.8888) time: 0.1773 data: 0.0912 max mem: 8233 +Train: [45] [ 600/6250] eta: 0:17:13 lr: 0.000078 grad: 0.1148 (0.1170) loss: 0.8904 (0.8886) time: 0.1879 data: 0.1085 max mem: 8233 +Train: [45] [ 700/6250] eta: 0:16:36 lr: 0.000078 grad: 0.1261 (0.1181) loss: 0.8895 (0.8881) time: 0.1651 data: 0.0816 max mem: 8233 +Train: [45] [ 800/6250] eta: 0:16:09 lr: 0.000078 grad: 0.1119 (0.1182) loss: 0.8856 (0.8880) time: 0.1779 data: 0.0989 max mem: 8233 +Train: [45] [ 900/6250] eta: 0:15:44 lr: 0.000078 grad: 0.1221 (0.1184) loss: 0.8911 (0.8881) time: 0.1568 data: 0.0695 max mem: 8233 +Train: [45] [1000/6250] eta: 0:15:16 lr: 0.000078 grad: 0.1177 (0.1188) loss: 0.8935 (0.8882) time: 0.1476 data: 0.0612 max mem: 8233 +Train: [45] [1100/6250] eta: 0:14:57 lr: 0.000077 grad: 0.1089 (0.1189) loss: 0.8879 (0.8881) time: 0.1758 data: 0.1026 max mem: 8233 +Train: [45] [1200/6250] eta: 0:14:35 lr: 0.000077 grad: 0.1094 (0.1189) loss: 0.8848 (0.8881) time: 0.1663 data: 0.0933 max mem: 8233 +Train: [45] [1300/6250] eta: 0:14:11 lr: 0.000077 grad: 0.1078 (0.1188) loss: 0.8923 (0.8882) time: 0.1535 data: 0.0866 max mem: 8233 +Train: [45] [1400/6250] eta: 0:13:47 lr: 0.000077 grad: 0.1187 (0.1188) loss: 0.8871 (0.8882) time: 0.1470 data: 0.0574 max mem: 8233 +Train: [45] [1500/6250] eta: 0:13:32 lr: 0.000077 grad: 0.1146 (0.1191) loss: 0.8903 (0.8881) time: 0.1859 data: 0.0992 max mem: 8233 +Train: [45] [1600/6250] eta: 0:13:15 lr: 0.000077 grad: 0.1122 (0.1190) loss: 0.8872 (0.8880) time: 0.1681 data: 0.0845 max mem: 8233 +Train: [45] [1700/6250] eta: 0:12:55 lr: 0.000077 grad: 0.1180 (0.1194) loss: 0.8830 (0.8878) time: 0.1766 data: 0.1182 max mem: 8233 +Train: [45] [1800/6250] eta: 0:12:36 lr: 0.000077 grad: 0.1131 (0.1195) loss: 0.8810 (0.8877) time: 0.1562 data: 0.0698 max mem: 8233 +Train: [45] [1900/6250] eta: 0:12:18 lr: 0.000077 grad: 0.1218 (0.1196) loss: 0.8799 (0.8875) time: 0.1560 data: 0.0702 max mem: 8233 +Train: [45] [2000/6250] eta: 0:11:57 lr: 0.000077 grad: 0.1279 (0.1198) loss: 0.8803 (0.8873) time: 0.1582 data: 0.0710 max mem: 8233 +Train: [45] [2100/6250] eta: 0:11:36 lr: 0.000077 grad: 0.1189 (0.1202) loss: 0.8876 (0.8873) time: 0.1490 data: 0.0617 max mem: 8233 +Train: [45] [2200/6250] eta: 0:11:17 lr: 0.000077 grad: 0.1191 (0.1202) loss: 0.8870 (0.8873) time: 0.1551 data: 0.0669 max mem: 8233 +Train: [45] [2300/6250] eta: 0:10:57 lr: 0.000077 grad: 0.1110 (0.1204) loss: 0.8868 (0.8873) time: 0.1612 data: 0.0795 max mem: 8233 +Train: [45] [2400/6250] eta: 0:10:38 lr: 0.000077 grad: 0.1245 (0.1207) loss: 0.8874 (0.8872) time: 0.1692 data: 0.1027 max mem: 8233 +Train: [45] [2500/6250] eta: 0:10:19 lr: 0.000077 grad: 0.1141 (0.1207) loss: 0.8879 (0.8871) time: 0.1799 data: 0.1028 max mem: 8233 +Train: [45] [2600/6250] eta: 0:09:59 lr: 0.000077 grad: 0.1215 (0.1210) loss: 0.8888 (0.8871) time: 0.1459 data: 0.0713 max mem: 8233 +Train: [45] [2700/6250] eta: 0:09:41 lr: 0.000077 grad: 0.1202 (0.1210) loss: 0.8829 (0.8871) time: 0.1609 data: 0.0773 max mem: 8233 +Train: [45] [2800/6250] eta: 0:09:24 lr: 0.000077 grad: 0.1142 (0.1209) loss: 0.8876 (0.8871) time: 0.1459 data: 0.0605 max mem: 8233 +Train: [45] [2900/6250] eta: 0:09:10 lr: 0.000077 grad: 0.1221 (0.1208) loss: 0.8865 (0.8872) time: 0.1406 data: 0.0493 max mem: 8233 +Train: [45] [3000/6250] eta: 0:08:56 lr: 0.000077 grad: 0.1138 (0.1208) loss: 0.8816 (0.8873) time: 0.1670 data: 0.0869 max mem: 8233 +Train: [45] [3100/6250] eta: 0:08:40 lr: 0.000077 grad: 0.1131 (0.1207) loss: 0.8869 (0.8873) time: 0.1088 data: 0.0215 max mem: 8233 +Train: [45] [3200/6250] eta: 0:08:22 lr: 0.000077 grad: 0.1154 (0.1207) loss: 0.8855 (0.8873) time: 0.1438 data: 0.0693 max mem: 8233 +Train: [45] [3300/6250] eta: 0:08:06 lr: 0.000077 grad: 0.1106 (0.1206) loss: 0.8921 (0.8874) time: 0.1589 data: 0.0741 max mem: 8233 +Train: [45] [3400/6250] eta: 0:07:49 lr: 0.000077 grad: 0.1086 (0.1205) loss: 0.8922 (0.8875) time: 0.1509 data: 0.0713 max mem: 8233 +Train: [45] [3500/6250] eta: 0:07:33 lr: 0.000077 grad: 0.1031 (0.1203) loss: 0.8982 (0.8876) time: 0.1978 data: 0.1359 max mem: 8233 +Train: [45] [3600/6250] eta: 0:07:17 lr: 0.000077 grad: 0.1076 (0.1200) loss: 0.8865 (0.8877) time: 0.1715 data: 0.0909 max mem: 8233 +Train: [45] [3700/6250] eta: 0:06:59 lr: 0.000077 grad: 0.1107 (0.1198) loss: 0.8943 (0.8878) time: 0.1477 data: 0.0628 max mem: 8233 +Train: [45] [3800/6250] eta: 0:06:42 lr: 0.000077 grad: 0.1145 (0.1198) loss: 0.8939 (0.8879) time: 0.1191 data: 0.0369 max mem: 8233 +Train: [45] [3900/6250] eta: 0:06:25 lr: 0.000077 grad: 0.1144 (0.1197) loss: 0.8893 (0.8880) time: 0.1568 data: 0.0668 max mem: 8233 +Train: [45] [4000/6250] eta: 0:06:08 lr: 0.000077 grad: 0.1166 (0.1198) loss: 0.8912 (0.8881) time: 0.1467 data: 0.0602 max mem: 8233 +Train: [45] [4100/6250] eta: 0:05:52 lr: 0.000077 grad: 0.1160 (0.1198) loss: 0.8890 (0.8881) time: 0.1670 data: 0.0774 max mem: 8233 +Train: [45] [4200/6250] eta: 0:05:35 lr: 0.000076 grad: 0.1088 (0.1198) loss: 0.8939 (0.8882) time: 0.1761 data: 0.0945 max mem: 8233 +Train: [45] [4300/6250] eta: 0:05:19 lr: 0.000076 grad: 0.1210 (0.1198) loss: 0.8858 (0.8882) time: 0.1476 data: 0.0589 max mem: 8233 +Train: [45] [4400/6250] eta: 0:05:02 lr: 0.000076 grad: 0.1164 (0.1198) loss: 0.8914 (0.8883) time: 0.1442 data: 0.0614 max mem: 8233 +Train: [45] [4500/6250] eta: 0:04:45 lr: 0.000076 grad: 0.1192 (0.1198) loss: 0.8916 (0.8883) time: 0.1352 data: 0.0525 max mem: 8233 +Train: [45] [4600/6250] eta: 0:04:29 lr: 0.000076 grad: 0.1255 (0.1198) loss: 0.8877 (0.8883) time: 0.1353 data: 0.0531 max mem: 8233 +Train: [45] [4700/6250] eta: 0:04:12 lr: 0.000076 grad: 0.1089 (0.1198) loss: 0.8885 (0.8882) time: 0.1605 data: 0.0722 max mem: 8233 +Train: [45] [4800/6250] eta: 0:03:56 lr: 0.000076 grad: 0.1175 (0.1198) loss: 0.8855 (0.8882) time: 0.1771 data: 0.0962 max mem: 8233 +Train: [45] [4900/6250] eta: 0:03:39 lr: 0.000076 grad: 0.1144 (0.1198) loss: 0.8850 (0.8882) time: 0.1578 data: 0.0683 max mem: 8233 +Train: [45] [5000/6250] eta: 0:03:23 lr: 0.000076 grad: 0.1276 (0.1199) loss: 0.8839 (0.8881) time: 0.1562 data: 0.0926 max mem: 8233 +Train: [45] [5100/6250] eta: 0:03:07 lr: 0.000076 grad: 0.1136 (0.1200) loss: 0.8840 (0.8881) time: 0.1645 data: 0.0810 max mem: 8233 +Train: [45] [5200/6250] eta: 0:02:50 lr: 0.000076 grad: 0.1141 (0.1200) loss: 0.8857 (0.8881) time: 0.1549 data: 0.0856 max mem: 8233 +Train: [45] [5300/6250] eta: 0:02:34 lr: 0.000076 grad: 0.1174 (0.1200) loss: 0.8867 (0.8880) time: 0.1690 data: 0.0886 max mem: 8233 +Train: [45] [5400/6250] eta: 0:02:18 lr: 0.000076 grad: 0.1177 (0.1200) loss: 0.8862 (0.8880) time: 0.1532 data: 0.0727 max mem: 8233 +Train: [45] [5500/6250] eta: 0:02:02 lr: 0.000076 grad: 0.1184 (0.1201) loss: 0.8863 (0.8880) time: 0.1541 data: 0.0631 max mem: 8233 +Train: [45] [5600/6250] eta: 0:01:46 lr: 0.000076 grad: 0.1111 (0.1201) loss: 0.8934 (0.8880) time: 0.1918 data: 0.1148 max mem: 8233 +Train: [45] [5700/6250] eta: 0:01:29 lr: 0.000076 grad: 0.1114 (0.1201) loss: 0.8824 (0.8880) time: 0.1762 data: 0.0961 max mem: 8233 +Train: [45] [5800/6250] eta: 0:01:13 lr: 0.000076 grad: 0.1169 (0.1202) loss: 0.8832 (0.8879) time: 0.1575 data: 0.0746 max mem: 8233 +Train: [45] [5900/6250] eta: 0:00:57 lr: 0.000076 grad: 0.1174 (0.1203) loss: 0.8827 (0.8879) time: 0.1887 data: 0.1130 max mem: 8233 +Train: [45] [6000/6250] eta: 0:00:40 lr: 0.000076 grad: 0.1168 (0.1204) loss: 0.8901 (0.8879) time: 0.1704 data: 0.0995 max mem: 8233 +Train: [45] [6100/6250] eta: 0:00:24 lr: 0.000076 grad: 0.1173 (0.1205) loss: 0.8843 (0.8878) time: 0.1610 data: 0.0663 max mem: 8233 +Train: [45] [6200/6250] eta: 0:00:08 lr: 0.000076 grad: 0.1177 (0.1205) loss: 0.8847 (0.8878) time: 0.1506 data: 0.0656 max mem: 8233 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.1122 (0.1205) loss: 0.8863 (0.8878) time: 0.1651 data: 0.0868 max mem: 8233 +Train: [45] Total time: 0:17:06 (0.1642 s / it) +Averaged stats: lr: 0.000076 grad: 0.1122 (0.1205) loss: 0.8863 (0.8878) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:04:11 loss: 0.9049 (0.9049) time: 4.0569 data: 3.9783 max mem: 8233 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8981 (0.8979) time: 0.1373 data: 0.1164 max mem: 8233 +Eval (hcp-train-subset): [45] Total time: 0:00:14 (0.2341 s / it) +Averaged stats (hcp-train-subset): loss: 0.8981 (0.8979) +Eval (hcp-val): [45] [ 0/62] eta: 0:04:40 loss: 0.8879 (0.8879) time: 4.5314 data: 4.4355 max mem: 8233 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8942 (0.8942) time: 0.1409 data: 0.1193 max mem: 8233 +Eval (hcp-val): [45] Total time: 0:00:14 (0.2291 s / it) +Averaged stats (hcp-val): loss: 0.8942 (0.8942) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 11:47:44 lr: 0.000076 grad: 0.1172 (0.1172) loss: 0.8882 (0.8882) time: 6.7943 data: 6.6959 max mem: 8233 +Train: [46] [ 100/6250] eta: 0:23:04 lr: 0.000076 grad: 0.1089 (0.1201) loss: 0.8919 (0.8876) time: 0.1404 data: 0.0382 max mem: 8233 +Train: [46] [ 200/6250] eta: 0:20:16 lr: 0.000076 grad: 0.1163 (0.1253) loss: 0.8924 (0.8878) time: 0.1613 data: 0.0659 max mem: 8233 +Train: [46] [ 300/6250] eta: 0:18:40 lr: 0.000076 grad: 0.1105 (0.1239) loss: 0.8912 (0.8875) time: 0.1486 data: 0.0597 max mem: 8233 +Train: [46] [ 400/6250] eta: 0:17:47 lr: 0.000076 grad: 0.1207 (0.1255) loss: 0.8887 (0.8885) time: 0.1236 data: 0.0272 max mem: 8233 +Train: [46] [ 500/6250] eta: 0:17:04 lr: 0.000076 grad: 0.1135 (0.1244) loss: 0.8880 (0.8887) time: 0.1566 data: 0.0589 max mem: 8233 +Train: [46] [ 600/6250] eta: 0:16:40 lr: 0.000076 grad: 0.1252 (0.1238) loss: 0.8838 (0.8882) time: 0.1715 data: 0.0856 max mem: 8233 +Train: [46] [ 700/6250] eta: 0:16:07 lr: 0.000076 grad: 0.1129 (0.1236) loss: 0.8966 (0.8880) time: 0.1625 data: 0.0739 max mem: 8233 +Train: [46] [ 800/6250] eta: 0:15:41 lr: 0.000076 grad: 0.1127 (0.1223) loss: 0.8881 (0.8883) time: 0.1719 data: 0.0851 max mem: 8233 +Train: [46] [ 900/6250] eta: 0:15:20 lr: 0.000076 grad: 0.1092 (0.1215) loss: 0.8935 (0.8885) time: 0.1810 data: 0.1055 max mem: 8233 +Train: [46] [1000/6250] eta: 0:14:52 lr: 0.000076 grad: 0.1100 (0.1206) loss: 0.8888 (0.8887) time: 0.1454 data: 0.0701 max mem: 8233 +Train: [46] [1100/6250] eta: 0:14:27 lr: 0.000075 grad: 0.1080 (0.1197) loss: 0.8915 (0.8890) time: 0.1309 data: 0.0407 max mem: 8233 +Train: [46] [1200/6250] eta: 0:14:07 lr: 0.000075 grad: 0.1175 (0.1192) loss: 0.8911 (0.8893) time: 0.1564 data: 0.0773 max mem: 8233 +Train: [46] [1300/6250] eta: 0:13:48 lr: 0.000075 grad: 0.1142 (0.1193) loss: 0.8895 (0.8895) time: 0.1518 data: 0.0619 max mem: 8233 +Train: [46] [1400/6250] eta: 0:13:25 lr: 0.000075 grad: 0.1152 (0.1190) loss: 0.8908 (0.8895) time: 0.1498 data: 0.0731 max mem: 8233 +Train: [46] [1500/6250] eta: 0:13:08 lr: 0.000075 grad: 0.1069 (0.1185) loss: 0.8888 (0.8896) time: 0.1337 data: 0.0441 max mem: 8233 +Train: [46] [1600/6250] eta: 0:12:49 lr: 0.000075 grad: 0.1148 (0.1184) loss: 0.8866 (0.8896) time: 0.1537 data: 0.0619 max mem: 8233 +Train: [46] [1700/6250] eta: 0:12:32 lr: 0.000075 grad: 0.1150 (0.1184) loss: 0.8922 (0.8897) time: 0.1620 data: 0.0750 max mem: 8233 +Train: [46] [1800/6250] eta: 0:12:18 lr: 0.000075 grad: 0.1098 (0.1182) loss: 0.8924 (0.8897) time: 0.1974 data: 0.1126 max mem: 8233 +Train: [46] [1900/6250] eta: 0:12:03 lr: 0.000075 grad: 0.1088 (0.1181) loss: 0.8891 (0.8896) time: 0.2155 data: 0.1439 max mem: 8233 +Train: [46] [2000/6250] eta: 0:11:47 lr: 0.000075 grad: 0.1113 (0.1179) loss: 0.8917 (0.8896) time: 0.1944 data: 0.1040 max mem: 8233 +Train: [46] [2100/6250] eta: 0:11:30 lr: 0.000075 grad: 0.1203 (0.1179) loss: 0.8930 (0.8896) time: 0.1872 data: 0.1089 max mem: 8233 +Train: [46] [2200/6250] eta: 0:11:13 lr: 0.000075 grad: 0.1140 (0.1180) loss: 0.8849 (0.8895) time: 0.1698 data: 0.0581 max mem: 8233 +Train: [46] [2300/6250] eta: 0:10:58 lr: 0.000075 grad: 0.1127 (0.1179) loss: 0.8909 (0.8894) time: 0.0964 data: 0.0004 max mem: 8233 +Train: [46] [2400/6250] eta: 0:10:41 lr: 0.000075 grad: 0.1114 (0.1178) loss: 0.8863 (0.8894) time: 0.1764 data: 0.0964 max mem: 8233 +Train: [46] [2500/6250] eta: 0:10:22 lr: 0.000075 grad: 0.1171 (0.1178) loss: 0.8859 (0.8894) time: 0.1548 data: 0.0673 max mem: 8233 +Train: [46] [2600/6250] eta: 0:10:04 lr: 0.000075 grad: 0.1073 (0.1178) loss: 0.8877 (0.8894) time: 0.1111 data: 0.0253 max mem: 8233 +Train: [46] [2700/6250] eta: 0:09:46 lr: 0.000075 grad: 0.1108 (0.1178) loss: 0.8888 (0.8894) time: 0.1561 data: 0.0737 max mem: 8233 +Train: [46] [2800/6250] eta: 0:09:29 lr: 0.000075 grad: 0.1176 (0.1178) loss: 0.8899 (0.8895) time: 0.1319 data: 0.0597 max mem: 8233 +Train: [46] [2900/6250] eta: 0:09:12 lr: 0.000075 grad: 0.1142 (0.1178) loss: 0.8890 (0.8895) time: 0.1702 data: 0.0911 max mem: 8233 +Train: [46] [3000/6250] eta: 0:08:53 lr: 0.000075 grad: 0.1127 (0.1180) loss: 0.8880 (0.8895) time: 0.1413 data: 0.0708 max mem: 8233 +Train: [46] [3100/6250] eta: 0:08:37 lr: 0.000075 grad: 0.1199 (0.1181) loss: 0.8907 (0.8895) time: 0.1728 data: 0.0875 max mem: 8233 +Train: [46] [3200/6250] eta: 0:08:20 lr: 0.000075 grad: 0.1127 (0.1181) loss: 0.8885 (0.8894) time: 0.1599 data: 0.0834 max mem: 8233 +Train: [46] [3300/6250] eta: 0:08:03 lr: 0.000075 grad: 0.1071 (0.1181) loss: 0.8912 (0.8894) time: 0.1810 data: 0.1012 max mem: 8233 +Train: [46] [3400/6250] eta: 0:07:48 lr: 0.000075 grad: 0.1096 (0.1181) loss: 0.8953 (0.8894) time: 0.1901 data: 0.0958 max mem: 8233 +Train: [46] [3500/6250] eta: 0:07:33 lr: 0.000075 grad: 0.1192 (0.1181) loss: 0.8892 (0.8895) time: 0.1673 data: 0.0917 max mem: 8233 +Train: [46] [3600/6250] eta: 0:07:16 lr: 0.000075 grad: 0.1136 (0.1181) loss: 0.8907 (0.8895) time: 0.1803 data: 0.0928 max mem: 8233 +Train: [46] [3700/6250] eta: 0:07:00 lr: 0.000075 grad: 0.1096 (0.1182) loss: 0.8896 (0.8895) time: 0.1590 data: 0.0742 max mem: 8233 +Train: [46] [3800/6250] eta: 0:06:44 lr: 0.000075 grad: 0.1137 (0.1182) loss: 0.8874 (0.8895) time: 0.1869 data: 0.1099 max mem: 8233 +Train: [46] [3900/6250] eta: 0:06:28 lr: 0.000075 grad: 0.1179 (0.1183) loss: 0.8917 (0.8894) time: 0.2234 data: 0.1495 max mem: 8233 +Train: [46] [4000/6250] eta: 0:06:13 lr: 0.000075 grad: 0.1206 (0.1183) loss: 0.8890 (0.8894) time: 0.3389 data: 0.2134 max mem: 8233 +Train: [46] [4100/6250] eta: 0:05:55 lr: 0.000075 grad: 0.1095 (0.1184) loss: 0.8892 (0.8893) time: 0.1440 data: 0.0538 max mem: 8233 +Train: [46] [4200/6250] eta: 0:05:38 lr: 0.000074 grad: 0.1153 (0.1186) loss: 0.8912 (0.8893) time: 0.1219 data: 0.0353 max mem: 8233 +Train: [46] [4300/6250] eta: 0:05:23 lr: 0.000074 grad: 0.1109 (0.1186) loss: 0.8897 (0.8892) time: 0.1820 data: 0.0920 max mem: 8233 +Train: [46] [4400/6250] eta: 0:05:06 lr: 0.000074 grad: 0.1104 (0.1187) loss: 0.8908 (0.8892) time: 0.1402 data: 0.0640 max mem: 8233 +Train: [46] [4500/6250] eta: 0:04:49 lr: 0.000074 grad: 0.1093 (0.1187) loss: 0.8875 (0.8891) time: 0.2090 data: 0.1358 max mem: 8233 +Train: [46] [4600/6250] eta: 0:04:32 lr: 0.000074 grad: 0.1083 (0.1187) loss: 0.8892 (0.8891) time: 0.1873 data: 0.1100 max mem: 8233 +Train: [46] [4700/6250] eta: 0:04:15 lr: 0.000074 grad: 0.1160 (0.1188) loss: 0.8894 (0.8891) time: 0.1132 data: 0.0255 max mem: 8233 +Train: [46] [4800/6250] eta: 0:03:59 lr: 0.000074 grad: 0.1157 (0.1187) loss: 0.8877 (0.8891) time: 0.1578 data: 0.0710 max mem: 8233 +Train: [46] [4900/6250] eta: 0:03:42 lr: 0.000074 grad: 0.1209 (0.1188) loss: 0.8884 (0.8890) time: 0.1718 data: 0.0855 max mem: 8233 +Train: [46] [5000/6250] eta: 0:03:25 lr: 0.000074 grad: 0.1126 (0.1188) loss: 0.8872 (0.8889) time: 0.1836 data: 0.1036 max mem: 8233 +Train: [46] [5100/6250] eta: 0:03:09 lr: 0.000074 grad: 0.1203 (0.1189) loss: 0.8879 (0.8888) time: 0.2587 data: 0.1879 max mem: 8233 +Train: [46] [5200/6250] eta: 0:02:53 lr: 0.000074 grad: 0.1074 (0.1189) loss: 0.8908 (0.8888) time: 0.1874 data: 0.1107 max mem: 8233 +Train: [46] [5300/6250] eta: 0:02:36 lr: 0.000074 grad: 0.1152 (0.1189) loss: 0.8839 (0.8887) time: 0.1605 data: 0.0970 max mem: 8233 +Train: [46] [5400/6250] eta: 0:02:20 lr: 0.000074 grad: 0.1107 (0.1189) loss: 0.8910 (0.8887) time: 0.1608 data: 0.0766 max mem: 8233 +Train: [46] [5500/6250] eta: 0:02:03 lr: 0.000074 grad: 0.1200 (0.1190) loss: 0.8883 (0.8886) time: 0.1661 data: 0.0745 max mem: 8233 +Train: [46] [5600/6250] eta: 0:01:47 lr: 0.000074 grad: 0.1155 (0.1189) loss: 0.8868 (0.8886) time: 0.1547 data: 0.0735 max mem: 8233 +Train: [46] [5700/6250] eta: 0:01:30 lr: 0.000074 grad: 0.1174 (0.1189) loss: 0.8873 (0.8886) time: 0.1638 data: 0.0781 max mem: 8233 +Train: [46] [5800/6250] eta: 0:01:14 lr: 0.000074 grad: 0.1145 (0.1190) loss: 0.8852 (0.8886) time: 0.1894 data: 0.1157 max mem: 8233 +Train: [46] [5900/6250] eta: 0:00:57 lr: 0.000074 grad: 0.1124 (0.1190) loss: 0.8888 (0.8885) time: 0.1352 data: 0.0512 max mem: 8233 +Train: [46] [6000/6250] eta: 0:00:41 lr: 0.000074 grad: 0.1105 (0.1191) loss: 0.8896 (0.8885) time: 0.1524 data: 0.0694 max mem: 8233 +Train: [46] [6100/6250] eta: 0:00:24 lr: 0.000074 grad: 0.1202 (0.1192) loss: 0.8838 (0.8885) time: 0.1616 data: 0.0894 max mem: 8233 +Train: [46] [6200/6250] eta: 0:00:08 lr: 0.000074 grad: 0.1152 (0.1192) loss: 0.8896 (0.8885) time: 0.1637 data: 0.0750 max mem: 8233 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.1159 (0.1192) loss: 0.8881 (0.8885) time: 0.1740 data: 0.0926 max mem: 8233 +Train: [46] Total time: 0:17:12 (0.1652 s / it) +Averaged stats: lr: 0.000074 grad: 0.1159 (0.1192) loss: 0.8881 (0.8885) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:39 loss: 0.9078 (0.9078) time: 3.5376 data: 3.4238 max mem: 8233 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8967 (0.8965) time: 0.1349 data: 0.1143 max mem: 8233 +Eval (hcp-train-subset): [46] Total time: 0:00:14 (0.2340 s / it) +Averaged stats (hcp-train-subset): loss: 0.8967 (0.8965) +Eval (hcp-val): [46] [ 0/62] eta: 0:05:29 loss: 0.8931 (0.8931) time: 5.3207 data: 5.2945 max mem: 8233 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8928 (0.8931) time: 0.1424 data: 0.1217 max mem: 8233 +Eval (hcp-val): [46] Total time: 0:00:14 (0.2273 s / it) +Averaged stats (hcp-val): loss: 0.8928 (0.8931) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 7:36:54 lr: 0.000074 grad: 0.1054 (0.1054) loss: 0.9025 (0.9025) time: 4.3862 data: 4.1525 max mem: 8233 +Train: [47] [ 100/6250] eta: 0:23:08 lr: 0.000074 grad: 0.1044 (0.1189) loss: 0.8942 (0.8945) time: 0.2122 data: 0.1184 max mem: 8233 +Train: [47] [ 200/6250] eta: 0:19:41 lr: 0.000074 grad: 0.1165 (0.1186) loss: 0.8934 (0.8920) time: 0.1708 data: 0.0650 max mem: 8233 +Train: [47] [ 300/6250] eta: 0:18:08 lr: 0.000074 grad: 0.1057 (0.1171) loss: 0.8913 (0.8926) time: 0.1454 data: 0.0590 max mem: 8233 +Train: [47] [ 400/6250] eta: 0:17:22 lr: 0.000074 grad: 0.1057 (0.1160) loss: 0.8907 (0.8924) time: 0.1487 data: 0.0498 max mem: 8233 +Train: [47] [ 500/6250] eta: 0:16:34 lr: 0.000074 grad: 0.1080 (0.1155) loss: 0.8963 (0.8923) time: 0.1431 data: 0.0501 max mem: 8233 +Train: [47] [ 600/6250] eta: 0:16:04 lr: 0.000074 grad: 0.1026 (0.1146) loss: 0.8910 (0.8921) time: 0.1677 data: 0.0881 max mem: 8233 +Train: [47] [ 700/6250] eta: 0:15:38 lr: 0.000074 grad: 0.1058 (0.1144) loss: 0.8907 (0.8921) time: 0.1298 data: 0.0401 max mem: 8233 +Train: [47] [ 800/6250] eta: 0:15:21 lr: 0.000074 grad: 0.1139 (0.1147) loss: 0.8856 (0.8917) time: 0.1635 data: 0.0802 max mem: 8233 +Train: [47] [ 900/6250] eta: 0:15:03 lr: 0.000074 grad: 0.1065 (0.1148) loss: 0.8860 (0.8913) time: 0.1600 data: 0.0770 max mem: 8233 +Train: [47] [1000/6250] eta: 0:14:35 lr: 0.000073 grad: 0.1077 (0.1149) loss: 0.8880 (0.8908) time: 0.1584 data: 0.0758 max mem: 8233 +Train: [47] [1100/6250] eta: 0:14:09 lr: 0.000073 grad: 0.1103 (0.1151) loss: 0.8883 (0.8905) time: 0.1343 data: 0.0468 max mem: 8233 +Train: [47] [1200/6250] eta: 0:14:02 lr: 0.000073 grad: 0.1119 (0.1154) loss: 0.8831 (0.8901) time: 0.2709 data: 0.1899 max mem: 8233 +Train: [47] [1300/6250] eta: 0:13:39 lr: 0.000073 grad: 0.1151 (0.1157) loss: 0.8863 (0.8895) time: 0.1369 data: 0.0573 max mem: 8233 +Train: [47] [1400/6250] eta: 0:13:17 lr: 0.000073 grad: 0.1153 (0.1159) loss: 0.8915 (0.8893) time: 0.1419 data: 0.0633 max mem: 8233 +Train: [47] [1500/6250] eta: 0:13:01 lr: 0.000073 grad: 0.1146 (0.1162) loss: 0.8894 (0.8891) time: 0.1804 data: 0.0928 max mem: 8233 +Train: [47] [1600/6250] eta: 0:12:46 lr: 0.000073 grad: 0.1156 (0.1167) loss: 0.8851 (0.8889) time: 0.1722 data: 0.0889 max mem: 8233 +Train: [47] [1700/6250] eta: 0:12:29 lr: 0.000073 grad: 0.1164 (0.1170) loss: 0.8827 (0.8885) time: 0.1642 data: 0.0900 max mem: 8233 +Train: [47] [1800/6250] eta: 0:12:10 lr: 0.000073 grad: 0.1278 (0.1175) loss: 0.8822 (0.8882) time: 0.1480 data: 0.0611 max mem: 8233 +Train: [47] [1900/6250] eta: 0:11:52 lr: 0.000073 grad: 0.1122 (0.1178) loss: 0.8889 (0.8880) time: 0.1419 data: 0.0563 max mem: 8233 +Train: [47] [2000/6250] eta: 0:11:33 lr: 0.000073 grad: 0.1232 (0.1184) loss: 0.8848 (0.8878) time: 0.1297 data: 0.0378 max mem: 8233 +Train: [47] [2100/6250] eta: 0:11:15 lr: 0.000073 grad: 0.1188 (0.1188) loss: 0.8836 (0.8877) time: 0.1634 data: 0.0880 max mem: 8233 +Train: [47] [2200/6250] eta: 0:10:57 lr: 0.000073 grad: 0.1185 (0.1188) loss: 0.8899 (0.8876) time: 0.1517 data: 0.0633 max mem: 8233 +Train: [47] [2300/6250] eta: 0:10:41 lr: 0.000073 grad: 0.1198 (0.1191) loss: 0.8840 (0.8875) time: 0.1719 data: 0.0854 max mem: 8233 +Train: [47] [2400/6250] eta: 0:10:24 lr: 0.000073 grad: 0.1081 (0.1191) loss: 0.8902 (0.8874) time: 0.1628 data: 0.0807 max mem: 8233 +Train: [47] [2500/6250] eta: 0:10:06 lr: 0.000073 grad: 0.1126 (0.1191) loss: 0.8878 (0.8874) time: 0.1430 data: 0.0742 max mem: 8233 +Train: [47] [2600/6250] eta: 0:09:54 lr: 0.000073 grad: 0.1191 (0.1193) loss: 0.8882 (0.8875) time: 0.2180 data: 0.1171 max mem: 8233 +Train: [47] [2700/6250] eta: 0:09:37 lr: 0.000073 grad: 0.1166 (0.1194) loss: 0.8915 (0.8875) time: 0.1874 data: 0.1051 max mem: 8233 +Train: [47] [2800/6250] eta: 0:09:20 lr: 0.000073 grad: 0.1280 (0.1196) loss: 0.8859 (0.8874) time: 0.1452 data: 0.0742 max mem: 8233 +Train: [47] [2900/6250] eta: 0:09:05 lr: 0.000073 grad: 0.1160 (0.1195) loss: 0.8896 (0.8875) time: 0.1903 data: 0.1168 max mem: 8233 +Train: [47] [3000/6250] eta: 0:08:47 lr: 0.000073 grad: 0.1181 (0.1195) loss: 0.8895 (0.8875) time: 0.1665 data: 0.0762 max mem: 8233 +Train: [47] [3100/6250] eta: 0:08:35 lr: 0.000073 grad: 0.1121 (0.1195) loss: 0.8883 (0.8875) time: 0.3621 data: 0.2938 max mem: 8233 +Train: [47] [3200/6250] eta: 0:08:16 lr: 0.000073 grad: 0.1170 (0.1195) loss: 0.8903 (0.8875) time: 0.1496 data: 0.0757 max mem: 8233 +Train: [47] [3300/6250] eta: 0:08:00 lr: 0.000073 grad: 0.1044 (0.1194) loss: 0.8916 (0.8875) time: 0.1483 data: 0.0584 max mem: 8233 +Train: [47] [3400/6250] eta: 0:07:44 lr: 0.000073 grad: 0.1143 (0.1194) loss: 0.8885 (0.8874) time: 0.2016 data: 0.1308 max mem: 8233 +Train: [47] [3500/6250] eta: 0:07:28 lr: 0.000073 grad: 0.1162 (0.1194) loss: 0.8860 (0.8874) time: 0.1647 data: 0.0796 max mem: 8233 +Train: [47] [3600/6250] eta: 0:07:11 lr: 0.000073 grad: 0.1111 (0.1192) loss: 0.8885 (0.8874) time: 0.1720 data: 0.0844 max mem: 8233 +Train: [47] [3700/6250] eta: 0:06:55 lr: 0.000073 grad: 0.1124 (0.1193) loss: 0.8902 (0.8874) time: 0.1719 data: 0.0923 max mem: 8233 +Train: [47] [3800/6250] eta: 0:06:39 lr: 0.000073 grad: 0.1118 (0.1192) loss: 0.8895 (0.8874) time: 0.1747 data: 0.0948 max mem: 8233 +Train: [47] [3900/6250] eta: 0:06:23 lr: 0.000073 grad: 0.1222 (0.1192) loss: 0.8884 (0.8874) time: 0.1796 data: 0.0907 max mem: 8233 +Train: [47] [4000/6250] eta: 0:06:06 lr: 0.000073 grad: 0.1081 (0.1191) loss: 0.8882 (0.8875) time: 0.1652 data: 0.0788 max mem: 8233 +Train: [47] [4100/6250] eta: 0:05:49 lr: 0.000072 grad: 0.1181 (0.1191) loss: 0.8870 (0.8875) time: 0.1467 data: 0.0665 max mem: 8233 +Train: [47] [4200/6250] eta: 0:05:34 lr: 0.000072 grad: 0.1106 (0.1191) loss: 0.8897 (0.8875) time: 0.1106 data: 0.0037 max mem: 8233 +Train: [47] [4300/6250] eta: 0:05:17 lr: 0.000072 grad: 0.1146 (0.1192) loss: 0.8870 (0.8875) time: 0.1413 data: 0.0571 max mem: 8233 +Train: [47] [4400/6250] eta: 0:05:00 lr: 0.000072 grad: 0.1146 (0.1192) loss: 0.8915 (0.8875) time: 0.1371 data: 0.0439 max mem: 8233 +Train: [47] [4500/6250] eta: 0:04:44 lr: 0.000072 grad: 0.1174 (0.1192) loss: 0.8882 (0.8876) time: 0.1464 data: 0.0558 max mem: 8233 +Train: [47] [4600/6250] eta: 0:04:28 lr: 0.000072 grad: 0.1127 (0.1192) loss: 0.8917 (0.8876) time: 0.1438 data: 0.0660 max mem: 8233 +Train: [47] [4700/6250] eta: 0:04:12 lr: 0.000072 grad: 0.1106 (0.1191) loss: 0.8912 (0.8876) time: 0.1951 data: 0.1107 max mem: 8233 +Train: [47] [4800/6250] eta: 0:03:55 lr: 0.000072 grad: 0.1088 (0.1191) loss: 0.8913 (0.8877) time: 0.2123 data: 0.1327 max mem: 8233 +Train: [47] [4900/6250] eta: 0:03:39 lr: 0.000072 grad: 0.1153 (0.1191) loss: 0.8891 (0.8877) time: 0.1622 data: 0.0710 max mem: 8233 +Train: [47] [5000/6250] eta: 0:03:22 lr: 0.000072 grad: 0.1137 (0.1191) loss: 0.8919 (0.8878) time: 0.1177 data: 0.0183 max mem: 8233 +Train: [47] [5100/6250] eta: 0:03:06 lr: 0.000072 grad: 0.1055 (0.1189) loss: 0.8882 (0.8878) time: 0.1724 data: 0.0859 max mem: 8233 +Train: [47] [5200/6250] eta: 0:02:50 lr: 0.000072 grad: 0.1140 (0.1189) loss: 0.8878 (0.8878) time: 0.1544 data: 0.0712 max mem: 8233 +Train: [47] [5300/6250] eta: 0:02:34 lr: 0.000072 grad: 0.1112 (0.1189) loss: 0.8931 (0.8879) time: 0.1465 data: 0.0557 max mem: 8233 +Train: [47] [5400/6250] eta: 0:02:17 lr: 0.000072 grad: 0.1156 (0.1188) loss: 0.8891 (0.8879) time: 0.2082 data: 0.1277 max mem: 8233 +Train: [47] [5500/6250] eta: 0:02:01 lr: 0.000072 grad: 0.1140 (0.1187) loss: 0.8901 (0.8880) time: 0.1472 data: 0.0550 max mem: 8233 +Train: [47] [5600/6250] eta: 0:01:45 lr: 0.000072 grad: 0.1123 (0.1187) loss: 0.8893 (0.8880) time: 0.1491 data: 0.0676 max mem: 8233 +Train: [47] [5700/6250] eta: 0:01:29 lr: 0.000072 grad: 0.1105 (0.1186) loss: 0.8969 (0.8881) time: 0.1774 data: 0.0843 max mem: 8233 +Train: [47] [5800/6250] eta: 0:01:12 lr: 0.000072 grad: 0.1118 (0.1185) loss: 0.8896 (0.8882) time: 0.1627 data: 0.0798 max mem: 8233 +Train: [47] [5900/6250] eta: 0:00:56 lr: 0.000072 grad: 0.1112 (0.1184) loss: 0.8953 (0.8883) time: 0.1670 data: 0.0874 max mem: 8233 +Train: [47] [6000/6250] eta: 0:00:40 lr: 0.000072 grad: 0.1115 (0.1184) loss: 0.8946 (0.8883) time: 0.1389 data: 0.0550 max mem: 8233 +Train: [47] [6100/6250] eta: 0:00:24 lr: 0.000072 grad: 0.1136 (0.1185) loss: 0.8893 (0.8884) time: 0.1514 data: 0.0634 max mem: 8233 +Train: [47] [6200/6250] eta: 0:00:08 lr: 0.000072 grad: 0.1140 (0.1185) loss: 0.8894 (0.8885) time: 0.1307 data: 0.0405 max mem: 8233 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.1101 (0.1186) loss: 0.8943 (0.8885) time: 0.1454 data: 0.0650 max mem: 8233 +Train: [47] Total time: 0:16:56 (0.1627 s / it) +Averaged stats: lr: 0.000072 grad: 0.1101 (0.1186) loss: 0.8943 (0.8885) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:05:29 loss: 0.9036 (0.9036) time: 5.3090 data: 5.2821 max mem: 8233 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8948 (0.8963) time: 0.1360 data: 0.1154 max mem: 8233 +Eval (hcp-train-subset): [47] Total time: 0:00:14 (0.2344 s / it) +Averaged stats (hcp-train-subset): loss: 0.8948 (0.8963) +Eval (hcp-val): [47] [ 0/62] eta: 0:05:49 loss: 0.8907 (0.8907) time: 5.6339 data: 5.6079 max mem: 8233 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8923 (0.8934) time: 0.1382 data: 0.1164 max mem: 8233 +Eval (hcp-val): [47] Total time: 0:00:13 (0.2249 s / it) +Averaged stats (hcp-val): loss: 0.8923 (0.8934) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 11:57:56 lr: 0.000072 grad: 0.1494 (0.1494) loss: 0.8915 (0.8915) time: 6.8923 data: 6.7960 max mem: 8233 +Train: [48] [ 100/6250] eta: 0:23:00 lr: 0.000072 grad: 0.1174 (0.1254) loss: 0.8937 (0.8942) time: 0.1904 data: 0.0794 max mem: 8233 +Train: [48] [ 200/6250] eta: 0:20:02 lr: 0.000072 grad: 0.1082 (0.1230) loss: 0.8971 (0.8923) time: 0.1761 data: 0.0842 max mem: 8233 +Train: [48] [ 300/6250] eta: 0:18:47 lr: 0.000072 grad: 0.1106 (0.1198) loss: 0.8940 (0.8926) time: 0.1840 data: 0.1010 max mem: 8233 +Train: [48] [ 400/6250] eta: 0:17:37 lr: 0.000072 grad: 0.1125 (0.1189) loss: 0.8897 (0.8925) time: 0.1469 data: 0.0485 max mem: 8233 +Train: [48] [ 500/6250] eta: 0:16:46 lr: 0.000072 grad: 0.1233 (0.1181) loss: 0.8844 (0.8921) time: 0.1489 data: 0.0633 max mem: 8233 +Train: [48] [ 600/6250] eta: 0:16:04 lr: 0.000072 grad: 0.1112 (0.1181) loss: 0.8917 (0.8921) time: 0.1393 data: 0.0486 max mem: 8233 +Train: [48] [ 700/6250] eta: 0:15:38 lr: 0.000072 grad: 0.1146 (0.1181) loss: 0.8947 (0.8920) time: 0.1650 data: 0.0766 max mem: 8233 +Train: [48] [ 800/6250] eta: 0:15:09 lr: 0.000072 grad: 0.1206 (0.1188) loss: 0.8867 (0.8918) time: 0.1613 data: 0.0719 max mem: 8233 +Train: [48] [ 900/6250] eta: 0:14:45 lr: 0.000071 grad: 0.1156 (0.1187) loss: 0.8951 (0.8919) time: 0.1673 data: 0.0813 max mem: 8233 +Train: [48] [1000/6250] eta: 0:14:23 lr: 0.000071 grad: 0.1133 (0.1187) loss: 0.8943 (0.8918) time: 0.1611 data: 0.0739 max mem: 8233 +Train: [48] [1100/6250] eta: 0:14:05 lr: 0.000071 grad: 0.1179 (0.1188) loss: 0.8909 (0.8916) time: 0.1690 data: 0.0946 max mem: 8233 +Train: [48] [1200/6250] eta: 0:13:51 lr: 0.000071 grad: 0.1171 (0.1188) loss: 0.8867 (0.8914) time: 0.1292 data: 0.0221 max mem: 8233 +Train: [48] [1300/6250] eta: 0:13:48 lr: 0.000071 grad: 0.1222 (0.1188) loss: 0.8872 (0.8912) time: 0.1972 data: 0.1191 max mem: 8233 +Train: [48] [1400/6250] eta: 0:13:36 lr: 0.000071 grad: 0.1128 (0.1185) loss: 0.8859 (0.8910) time: 0.1911 data: 0.1139 max mem: 8233 +Train: [48] [1500/6250] eta: 0:13:21 lr: 0.000071 grad: 0.1134 (0.1187) loss: 0.8863 (0.8908) time: 0.1784 data: 0.0922 max mem: 8233 +Train: [48] [1600/6250] eta: 0:13:09 lr: 0.000071 grad: 0.1215 (0.1190) loss: 0.8812 (0.8906) time: 0.1683 data: 0.0830 max mem: 8233 +Train: [48] [1700/6250] eta: 0:12:54 lr: 0.000071 grad: 0.1185 (0.1191) loss: 0.8889 (0.8903) time: 0.1759 data: 0.0899 max mem: 8233 +Train: [48] [1800/6250] eta: 0:12:38 lr: 0.000071 grad: 0.1098 (0.1191) loss: 0.8897 (0.8902) time: 0.1567 data: 0.0670 max mem: 8233 +Train: [48] [1900/6250] eta: 0:12:20 lr: 0.000071 grad: 0.1129 (0.1191) loss: 0.8866 (0.8900) time: 0.1440 data: 0.0668 max mem: 8233 +Train: [48] [2000/6250] eta: 0:12:02 lr: 0.000071 grad: 0.1158 (0.1193) loss: 0.8844 (0.8897) time: 0.1656 data: 0.0822 max mem: 8233 +Train: [48] [2100/6250] eta: 0:11:43 lr: 0.000071 grad: 0.1187 (0.1197) loss: 0.8877 (0.8895) time: 0.1287 data: 0.0597 max mem: 8233 +Train: [48] [2200/6250] eta: 0:11:25 lr: 0.000071 grad: 0.1145 (0.1197) loss: 0.8851 (0.8894) time: 0.1441 data: 0.0489 max mem: 8233 +Train: [48] [2300/6250] eta: 0:11:13 lr: 0.000071 grad: 0.1139 (0.1198) loss: 0.8876 (0.8893) time: 0.1288 data: 0.0243 max mem: 8233 +Train: [48] [2400/6250] eta: 0:10:55 lr: 0.000071 grad: 0.1137 (0.1198) loss: 0.8894 (0.8892) time: 0.1679 data: 0.0723 max mem: 8233 +Train: [48] [2500/6250] eta: 0:10:36 lr: 0.000071 grad: 0.1175 (0.1200) loss: 0.8852 (0.8890) time: 0.1463 data: 0.0603 max mem: 8233 +Train: [48] [2600/6250] eta: 0:10:17 lr: 0.000071 grad: 0.1161 (0.1201) loss: 0.8884 (0.8889) time: 0.1804 data: 0.0960 max mem: 8233 +Train: [48] [2700/6250] eta: 0:09:58 lr: 0.000071 grad: 0.1223 (0.1203) loss: 0.8850 (0.8888) time: 0.1721 data: 0.0864 max mem: 8233 +Train: [48] [2800/6250] eta: 0:09:40 lr: 0.000071 grad: 0.1181 (0.1203) loss: 0.8861 (0.8887) time: 0.1657 data: 0.0933 max mem: 8233 +Train: [48] [2900/6250] eta: 0:09:20 lr: 0.000071 grad: 0.1084 (0.1203) loss: 0.8902 (0.8886) time: 0.1377 data: 0.0529 max mem: 8233 +Train: [48] [3000/6250] eta: 0:09:02 lr: 0.000071 grad: 0.1302 (0.1205) loss: 0.8855 (0.8885) time: 0.1481 data: 0.0652 max mem: 8233 +Train: [48] [3100/6250] eta: 0:08:44 lr: 0.000071 grad: 0.1172 (0.1205) loss: 0.8798 (0.8884) time: 0.1469 data: 0.0689 max mem: 8233 +Train: [48] [3200/6250] eta: 0:08:29 lr: 0.000071 grad: 0.1076 (0.1204) loss: 0.8818 (0.8882) time: 0.1676 data: 0.0927 max mem: 8233 +Train: [48] [3300/6250] eta: 0:08:11 lr: 0.000071 grad: 0.1088 (0.1204) loss: 0.8881 (0.8881) time: 0.1424 data: 0.0669 max mem: 8233 +Train: [48] [3400/6250] eta: 0:07:54 lr: 0.000071 grad: 0.1097 (0.1204) loss: 0.8881 (0.8880) time: 0.1486 data: 0.0671 max mem: 8233 +Train: [48] [3500/6250] eta: 0:07:38 lr: 0.000071 grad: 0.1204 (0.1204) loss: 0.8831 (0.8879) time: 0.2042 data: 0.1135 max mem: 8233 +Train: [48] [3600/6250] eta: 0:07:21 lr: 0.000071 grad: 0.1229 (0.1207) loss: 0.8893 (0.8878) time: 0.1522 data: 0.0594 max mem: 8233 +Train: [48] [3700/6250] eta: 0:07:04 lr: 0.000071 grad: 0.1137 (0.1209) loss: 0.8856 (0.8877) time: 0.1416 data: 0.0533 max mem: 8233 +Train: [48] [3800/6250] eta: 0:06:47 lr: 0.000071 grad: 0.1083 (0.1208) loss: 0.8856 (0.8876) time: 0.1651 data: 0.0707 max mem: 8233 +Train: [48] [3900/6250] eta: 0:06:30 lr: 0.000070 grad: 0.1166 (0.1209) loss: 0.8859 (0.8876) time: 0.1427 data: 0.0631 max mem: 8233 +Train: [48] [4000/6250] eta: 0:06:13 lr: 0.000070 grad: 0.1250 (0.1209) loss: 0.8914 (0.8876) time: 0.2046 data: 0.1170 max mem: 8233 +Train: [48] [4100/6250] eta: 0:05:56 lr: 0.000070 grad: 0.1125 (0.1210) loss: 0.8935 (0.8875) time: 0.1624 data: 0.0884 max mem: 8233 +Train: [48] [4200/6250] eta: 0:05:39 lr: 0.000070 grad: 0.1189 (0.1212) loss: 0.8893 (0.8874) time: 0.1930 data: 0.1214 max mem: 8233 +Train: [48] [4300/6250] eta: 0:05:22 lr: 0.000070 grad: 0.1272 (0.1213) loss: 0.8826 (0.8874) time: 0.1524 data: 0.0789 max mem: 8233 +Train: [48] [4400/6250] eta: 0:05:05 lr: 0.000070 grad: 0.1214 (0.1213) loss: 0.8840 (0.8873) time: 0.1434 data: 0.0645 max mem: 8233 +Train: [48] [4500/6250] eta: 0:04:48 lr: 0.000070 grad: 0.1259 (0.1214) loss: 0.8803 (0.8872) time: 0.1664 data: 0.0890 max mem: 8233 +Train: [48] [4600/6250] eta: 0:04:31 lr: 0.000070 grad: 0.1199 (0.1215) loss: 0.8864 (0.8871) time: 0.1626 data: 0.0802 max mem: 8233 +Train: [48] [4700/6250] eta: 0:04:14 lr: 0.000070 grad: 0.1162 (0.1216) loss: 0.8841 (0.8871) time: 0.1541 data: 0.0769 max mem: 8233 +Train: [48] [4800/6250] eta: 0:03:58 lr: 0.000070 grad: 0.1138 (0.1216) loss: 0.8881 (0.8871) time: 0.1570 data: 0.0759 max mem: 8233 +Train: [48] [4900/6250] eta: 0:03:41 lr: 0.000070 grad: 0.1142 (0.1218) loss: 0.8865 (0.8870) time: 0.1575 data: 0.0746 max mem: 8233 +Train: [48] [5000/6250] eta: 0:03:25 lr: 0.000070 grad: 0.1220 (0.1218) loss: 0.8877 (0.8870) time: 0.1970 data: 0.1161 max mem: 8233 +Train: [48] [5100/6250] eta: 0:03:09 lr: 0.000070 grad: 0.1273 (0.1219) loss: 0.8835 (0.8870) time: 0.1071 data: 0.0062 max mem: 8233 +Train: [48] [5200/6250] eta: 0:02:53 lr: 0.000070 grad: 0.1211 (0.1220) loss: 0.8889 (0.8870) time: 0.1044 data: 0.0081 max mem: 8233 +Train: [48] [5300/6250] eta: 0:02:37 lr: 0.000070 grad: 0.1223 (0.1221) loss: 0.8825 (0.8870) time: 0.1794 data: 0.1054 max mem: 8233 +Train: [48] [5400/6250] eta: 0:02:20 lr: 0.000070 grad: 0.1194 (0.1223) loss: 0.8882 (0.8870) time: 0.1826 data: 0.1035 max mem: 8233 +Train: [48] [5500/6250] eta: 0:02:04 lr: 0.000070 grad: 0.1251 (0.1223) loss: 0.8869 (0.8870) time: 0.1727 data: 0.0830 max mem: 8233 +Train: [48] [5600/6250] eta: 0:01:47 lr: 0.000070 grad: 0.1206 (0.1222) loss: 0.8859 (0.8870) time: 0.1990 data: 0.1179 max mem: 8233 +Train: [48] [5700/6250] eta: 0:01:31 lr: 0.000070 grad: 0.1215 (0.1223) loss: 0.8903 (0.8870) time: 0.1668 data: 0.0752 max mem: 8233 +Train: [48] [5800/6250] eta: 0:01:14 lr: 0.000070 grad: 0.1222 (0.1224) loss: 0.8906 (0.8870) time: 0.1696 data: 0.0919 max mem: 8233 +Train: [48] [5900/6250] eta: 0:00:58 lr: 0.000070 grad: 0.1247 (0.1224) loss: 0.8877 (0.8870) time: 0.1600 data: 0.0745 max mem: 8233 +Train: [48] [6000/6250] eta: 0:00:41 lr: 0.000070 grad: 0.1156 (0.1224) loss: 0.8878 (0.8870) time: 0.1740 data: 0.0877 max mem: 8233 +Train: [48] [6100/6250] eta: 0:00:24 lr: 0.000070 grad: 0.1206 (0.1225) loss: 0.8828 (0.8869) time: 0.1494 data: 0.0587 max mem: 8233 +Train: [48] [6200/6250] eta: 0:00:08 lr: 0.000070 grad: 0.1189 (0.1226) loss: 0.8856 (0.8869) time: 0.1480 data: 0.0666 max mem: 8233 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.1149 (0.1226) loss: 0.8846 (0.8868) time: 0.1514 data: 0.0714 max mem: 8233 +Train: [48] Total time: 0:17:21 (0.1666 s / it) +Averaged stats: lr: 0.000070 grad: 0.1149 (0.1226) loss: 0.8846 (0.8868) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:05:35 loss: 0.9105 (0.9105) time: 5.4075 data: 5.3807 max mem: 8233 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8975 (0.8968) time: 0.1156 data: 0.0945 max mem: 8233 +Eval (hcp-train-subset): [48] Total time: 0:00:14 (0.2282 s / it) +Averaged stats (hcp-train-subset): loss: 0.8975 (0.8968) +Eval (hcp-val): [48] [ 0/62] eta: 0:04:29 loss: 0.8897 (0.8897) time: 4.3519 data: 4.2720 max mem: 8233 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8926 (0.8933) time: 0.1279 data: 0.1071 max mem: 8233 +Eval (hcp-val): [48] Total time: 0:00:14 (0.2288 s / it) +Averaged stats (hcp-val): loss: 0.8926 (0.8933) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 10:08:43 lr: 0.000070 grad: 0.2102 (0.2102) loss: 0.8946 (0.8946) time: 5.8438 data: 5.5558 max mem: 8233 +Train: [49] [ 100/6250] eta: 0:22:34 lr: 0.000070 grad: 0.1103 (0.1181) loss: 0.8889 (0.8971) time: 0.1868 data: 0.0795 max mem: 8233 +Train: [49] [ 200/6250] eta: 0:19:40 lr: 0.000070 grad: 0.1194 (0.1162) loss: 0.8841 (0.8928) time: 0.1568 data: 0.0518 max mem: 8233 +Train: [49] [ 300/6250] eta: 0:17:58 lr: 0.000070 grad: 0.1175 (0.1171) loss: 0.8921 (0.8916) time: 0.1489 data: 0.0634 max mem: 8233 +Train: [49] [ 400/6250] eta: 0:17:05 lr: 0.000070 grad: 0.1140 (0.1170) loss: 0.8885 (0.8915) time: 0.1393 data: 0.0516 max mem: 8233 +Train: [49] [ 500/6250] eta: 0:16:34 lr: 0.000070 grad: 0.1132 (0.1171) loss: 0.8990 (0.8916) time: 0.1504 data: 0.0649 max mem: 8233 +Train: [49] [ 600/6250] eta: 0:16:05 lr: 0.000070 grad: 0.1115 (0.1173) loss: 0.8944 (0.8913) time: 0.1564 data: 0.0725 max mem: 8233 +Train: [49] [ 700/6250] eta: 0:15:39 lr: 0.000069 grad: 0.1133 (0.1176) loss: 0.8895 (0.8910) time: 0.1423 data: 0.0474 max mem: 8233 +Train: [49] [ 800/6250] eta: 0:15:21 lr: 0.000069 grad: 0.1112 (0.1174) loss: 0.8916 (0.8910) time: 0.1904 data: 0.1078 max mem: 8233 +Train: [49] [ 900/6250] eta: 0:15:03 lr: 0.000069 grad: 0.1118 (0.1171) loss: 0.8871 (0.8909) time: 0.1697 data: 0.0826 max mem: 8233 +Train: [49] [1000/6250] eta: 0:14:46 lr: 0.000069 grad: 0.1186 (0.1179) loss: 0.8864 (0.8908) time: 0.1880 data: 0.1133 max mem: 8233 +Train: [49] [1100/6250] eta: 0:14:29 lr: 0.000069 grad: 0.1121 (0.1185) loss: 0.8868 (0.8905) time: 0.2245 data: 0.1452 max mem: 8233 +Train: [49] [1200/6250] eta: 0:14:04 lr: 0.000069 grad: 0.1204 (0.1191) loss: 0.8918 (0.8903) time: 0.1875 data: 0.1034 max mem: 8233 +Train: [49] [1300/6250] eta: 0:13:49 lr: 0.000069 grad: 0.1165 (0.1196) loss: 0.8805 (0.8901) time: 0.2084 data: 0.1253 max mem: 8233 +Train: [49] [1400/6250] eta: 0:13:29 lr: 0.000069 grad: 0.1122 (0.1200) loss: 0.8876 (0.8898) time: 0.1607 data: 0.0723 max mem: 8233 +Train: [49] [1500/6250] eta: 0:13:09 lr: 0.000069 grad: 0.1173 (0.1204) loss: 0.8915 (0.8897) time: 0.1577 data: 0.0865 max mem: 8233 +Train: [49] [1600/6250] eta: 0:12:52 lr: 0.000069 grad: 0.1132 (0.1208) loss: 0.8842 (0.8895) time: 0.1499 data: 0.0678 max mem: 8233 +Train: [49] [1700/6250] eta: 0:12:36 lr: 0.000069 grad: 0.1138 (0.1208) loss: 0.8831 (0.8893) time: 0.1203 data: 0.0351 max mem: 8233 +Train: [49] [1800/6250] eta: 0:12:18 lr: 0.000069 grad: 0.1133 (0.1207) loss: 0.8858 (0.8891) time: 0.1592 data: 0.0689 max mem: 8233 +Train: [49] [1900/6250] eta: 0:12:01 lr: 0.000069 grad: 0.1188 (0.1208) loss: 0.8885 (0.8889) time: 0.1553 data: 0.0655 max mem: 8233 +Train: [49] [2000/6250] eta: 0:11:43 lr: 0.000069 grad: 0.1215 (0.1208) loss: 0.8824 (0.8888) time: 0.1436 data: 0.0526 max mem: 8233 +Train: [49] [2100/6250] eta: 0:11:24 lr: 0.000069 grad: 0.1139 (0.1211) loss: 0.8873 (0.8886) time: 0.1562 data: 0.0595 max mem: 8233 +Train: [49] [2200/6250] eta: 0:11:07 lr: 0.000069 grad: 0.1199 (0.1210) loss: 0.8841 (0.8886) time: 0.1688 data: 0.0857 max mem: 8233 +Train: [49] [2300/6250] eta: 0:10:49 lr: 0.000069 grad: 0.1098 (0.1209) loss: 0.8876 (0.8886) time: 0.1528 data: 0.0641 max mem: 8233 +Train: [49] [2400/6250] eta: 0:10:32 lr: 0.000069 grad: 0.1179 (0.1208) loss: 0.8891 (0.8885) time: 0.1623 data: 0.0851 max mem: 8233 +Train: [49] [2500/6250] eta: 0:10:17 lr: 0.000069 grad: 0.1182 (0.1208) loss: 0.8899 (0.8885) time: 0.2353 data: 0.1663 max mem: 8233 +Train: [49] [2600/6250] eta: 0:09:57 lr: 0.000069 grad: 0.1131 (0.1208) loss: 0.8892 (0.8885) time: 0.1671 data: 0.0828 max mem: 8233 +Train: [49] [2700/6250] eta: 0:09:40 lr: 0.000069 grad: 0.1259 (0.1208) loss: 0.8849 (0.8885) time: 0.1524 data: 0.0770 max mem: 8233 +Train: [49] [2800/6250] eta: 0:09:23 lr: 0.000069 grad: 0.1206 (0.1208) loss: 0.8897 (0.8885) time: 0.1070 data: 0.0128 max mem: 8233 +Train: [49] [2900/6250] eta: 0:09:06 lr: 0.000069 grad: 0.1168 (0.1208) loss: 0.8843 (0.8885) time: 0.1639 data: 0.0767 max mem: 8233 +Train: [49] [3000/6250] eta: 0:08:50 lr: 0.000069 grad: 0.1099 (0.1207) loss: 0.8890 (0.8885) time: 0.1429 data: 0.0608 max mem: 8233 +Train: [49] [3100/6250] eta: 0:08:33 lr: 0.000069 grad: 0.1084 (0.1206) loss: 0.8903 (0.8886) time: 0.1657 data: 0.0932 max mem: 8233 +Train: [49] [3200/6250] eta: 0:08:17 lr: 0.000069 grad: 0.1152 (0.1207) loss: 0.8822 (0.8885) time: 0.1625 data: 0.0838 max mem: 8233 +Train: [49] [3300/6250] eta: 0:08:00 lr: 0.000069 grad: 0.1112 (0.1207) loss: 0.8952 (0.8886) time: 0.1687 data: 0.0780 max mem: 8233 +Train: [49] [3400/6250] eta: 0:07:43 lr: 0.000069 grad: 0.1144 (0.1206) loss: 0.8896 (0.8886) time: 0.1554 data: 0.0660 max mem: 8233 +Train: [49] [3500/6250] eta: 0:07:26 lr: 0.000069 grad: 0.1217 (0.1206) loss: 0.8856 (0.8886) time: 0.1466 data: 0.0651 max mem: 8233 +Train: [49] [3600/6250] eta: 0:07:11 lr: 0.000069 grad: 0.1181 (0.1208) loss: 0.8852 (0.8885) time: 0.1618 data: 0.0721 max mem: 8233 +Train: [49] [3700/6250] eta: 0:06:54 lr: 0.000069 grad: 0.1156 (0.1208) loss: 0.8862 (0.8885) time: 0.1384 data: 0.0584 max mem: 8233 +Train: [49] [3800/6250] eta: 0:06:37 lr: 0.000068 grad: 0.1160 (0.1209) loss: 0.8874 (0.8885) time: 0.1485 data: 0.0647 max mem: 8233 +Train: [49] [3900/6250] eta: 0:06:20 lr: 0.000068 grad: 0.1141 (0.1210) loss: 0.8859 (0.8885) time: 0.1290 data: 0.0390 max mem: 8233 +Train: [49] [4000/6250] eta: 0:06:03 lr: 0.000068 grad: 0.1130 (0.1210) loss: 0.8895 (0.8884) time: 0.1772 data: 0.0900 max mem: 8233 +Train: [49] [4100/6250] eta: 0:05:47 lr: 0.000068 grad: 0.1147 (0.1211) loss: 0.8838 (0.8884) time: 0.1594 data: 0.0724 max mem: 8233 +Train: [49] [4200/6250] eta: 0:05:30 lr: 0.000068 grad: 0.1181 (0.1209) loss: 0.8895 (0.8884) time: 0.1393 data: 0.0533 max mem: 8233 +Train: [49] [4300/6250] eta: 0:05:14 lr: 0.000068 grad: 0.1168 (0.1211) loss: 0.8864 (0.8883) time: 0.1618 data: 0.0838 max mem: 8233 +Train: [49] [4400/6250] eta: 0:04:58 lr: 0.000068 grad: 0.1152 (0.1210) loss: 0.8854 (0.8882) time: 0.1569 data: 0.0745 max mem: 8233 +Train: [49] [4500/6250] eta: 0:04:42 lr: 0.000068 grad: 0.1165 (0.1211) loss: 0.8829 (0.8881) time: 0.1613 data: 0.0836 max mem: 8233 +Train: [49] [4600/6250] eta: 0:04:25 lr: 0.000068 grad: 0.1162 (0.1211) loss: 0.8825 (0.8881) time: 0.1580 data: 0.0926 max mem: 8233 +Train: [49] [4700/6250] eta: 0:04:09 lr: 0.000068 grad: 0.1155 (0.1211) loss: 0.8870 (0.8880) time: 0.1509 data: 0.0785 max mem: 8233 +Train: [49] [4800/6250] eta: 0:03:53 lr: 0.000068 grad: 0.1146 (0.1210) loss: 0.8853 (0.8879) time: 0.1498 data: 0.0645 max mem: 8233 +Train: [49] [4900/6250] eta: 0:03:37 lr: 0.000068 grad: 0.1152 (0.1211) loss: 0.8857 (0.8878) time: 0.1602 data: 0.0616 max mem: 8233 +Train: [49] [5000/6250] eta: 0:03:20 lr: 0.000068 grad: 0.1109 (0.1210) loss: 0.8898 (0.8878) time: 0.1606 data: 0.0721 max mem: 8233 +Train: [49] [5100/6250] eta: 0:03:04 lr: 0.000068 grad: 0.1171 (0.1211) loss: 0.8919 (0.8878) time: 0.1385 data: 0.0561 max mem: 8233 +Train: [49] [5200/6250] eta: 0:02:48 lr: 0.000068 grad: 0.1170 (0.1211) loss: 0.8915 (0.8878) time: 0.1756 data: 0.0966 max mem: 8233 +Train: [49] [5300/6250] eta: 0:02:32 lr: 0.000068 grad: 0.1163 (0.1211) loss: 0.8909 (0.8878) time: 0.2165 data: 0.1518 max mem: 8233 +Train: [49] [5400/6250] eta: 0:02:16 lr: 0.000068 grad: 0.1123 (0.1210) loss: 0.8892 (0.8878) time: 0.1376 data: 0.0651 max mem: 8233 +Train: [49] [5500/6250] eta: 0:02:00 lr: 0.000068 grad: 0.1135 (0.1210) loss: 0.8863 (0.8878) time: 0.1489 data: 0.0718 max mem: 8233 +Train: [49] [5600/6250] eta: 0:01:44 lr: 0.000068 grad: 0.1198 (0.1210) loss: 0.8840 (0.8878) time: 0.1657 data: 0.0756 max mem: 8233 +Train: [49] [5700/6250] eta: 0:01:28 lr: 0.000068 grad: 0.1267 (0.1211) loss: 0.8847 (0.8878) time: 0.1475 data: 0.0558 max mem: 8233 +Train: [49] [5800/6250] eta: 0:01:12 lr: 0.000068 grad: 0.1137 (0.1211) loss: 0.8859 (0.8878) time: 0.1729 data: 0.0892 max mem: 8233 +Train: [49] [5900/6250] eta: 0:00:56 lr: 0.000068 grad: 0.1178 (0.1212) loss: 0.8872 (0.8877) time: 0.1525 data: 0.0631 max mem: 8233 +Train: [49] [6000/6250] eta: 0:00:40 lr: 0.000068 grad: 0.1117 (0.1213) loss: 0.8865 (0.8877) time: 0.1844 data: 0.1007 max mem: 8233 +Train: [49] [6100/6250] eta: 0:00:24 lr: 0.000068 grad: 0.1122 (0.1213) loss: 0.8912 (0.8877) time: 0.1421 data: 0.0561 max mem: 8233 +Train: [49] [6200/6250] eta: 0:00:08 lr: 0.000068 grad: 0.1219 (0.1214) loss: 0.8899 (0.8876) time: 0.1485 data: 0.0621 max mem: 8233 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.1186 (0.1214) loss: 0.8862 (0.8876) time: 0.1356 data: 0.0494 max mem: 8233 +Train: [49] Total time: 0:16:51 (0.1618 s / it) +Averaged stats: lr: 0.000068 grad: 0.1186 (0.1214) loss: 0.8862 (0.8876) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:05:07 loss: 0.9079 (0.9079) time: 4.9530 data: 4.9262 max mem: 8233 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8967 (0.8957) time: 0.1370 data: 0.1162 max mem: 8233 +Eval (hcp-train-subset): [49] Total time: 0:00:14 (0.2365 s / it) +Averaged stats (hcp-train-subset): loss: 0.8967 (0.8957) +Making plots (hcp-train-subset): example=33 +Eval (hcp-val): [49] [ 0/62] eta: 0:06:04 loss: 0.8894 (0.8894) time: 5.8860 data: 5.8590 max mem: 8233 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8925 (0.8931) time: 0.1410 data: 0.1189 max mem: 8233 +Eval (hcp-val): [49] Total time: 0:00:14 (0.2306 s / it) +Averaged stats (hcp-val): loss: 0.8925 (0.8931) +Making plots (hcp-val): example=47 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 12:16:48 lr: 0.000068 grad: 0.2270 (0.2270) loss: 0.8533 (0.8533) time: 7.0733 data: 6.9430 max mem: 8233 +Train: [50] [ 100/6250] eta: 0:22:51 lr: 0.000068 grad: 0.1201 (0.1275) loss: 0.8814 (0.8879) time: 0.1630 data: 0.0494 max mem: 8233 +Train: [50] [ 200/6250] eta: 0:19:30 lr: 0.000068 grad: 0.1148 (0.1220) loss: 0.8885 (0.8868) time: 0.1624 data: 0.0544 max mem: 8233 +Train: [50] [ 300/6250] eta: 0:18:28 lr: 0.000068 grad: 0.1222 (0.1192) loss: 0.8952 (0.8883) time: 0.2025 data: 0.1195 max mem: 8233 +Train: [50] [ 400/6250] eta: 0:17:24 lr: 0.000068 grad: 0.1129 (0.1191) loss: 0.8886 (0.8885) time: 0.1516 data: 0.0582 max mem: 8233 +Train: [50] [ 500/6250] eta: 0:16:45 lr: 0.000067 grad: 0.1202 (0.1194) loss: 0.8904 (0.8890) time: 0.1379 data: 0.0399 max mem: 8233 +Train: [50] [ 600/6250] eta: 0:16:18 lr: 0.000067 grad: 0.1186 (0.1204) loss: 0.8934 (0.8892) time: 0.1724 data: 0.0861 max mem: 8233 +Train: [50] [ 700/6250] eta: 0:15:52 lr: 0.000067 grad: 0.1182 (0.1199) loss: 0.8956 (0.8896) time: 0.1703 data: 0.0818 max mem: 8233 +Train: [50] [ 800/6250] eta: 0:15:30 lr: 0.000067 grad: 0.1386 (0.1215) loss: 0.8806 (0.8895) time: 0.1811 data: 0.1029 max mem: 8233 +Train: [50] [ 900/6250] eta: 0:15:11 lr: 0.000067 grad: 0.1218 (0.1226) loss: 0.8886 (0.8896) time: 0.1768 data: 0.0958 max mem: 8233 +Train: [50] [1000/6250] eta: 0:14:47 lr: 0.000067 grad: 0.1179 (0.1223) loss: 0.8943 (0.8898) time: 0.1383 data: 0.0554 max mem: 8233 +Train: [50] [1100/6250] eta: 0:14:24 lr: 0.000067 grad: 0.1101 (0.1223) loss: 0.8923 (0.8900) time: 0.1695 data: 0.0897 max mem: 8233 +Train: [50] [1200/6250] eta: 0:14:03 lr: 0.000067 grad: 0.1092 (0.1221) loss: 0.8901 (0.8901) time: 0.1676 data: 0.0878 max mem: 8233 +Train: [50] [1300/6250] eta: 0:13:52 lr: 0.000067 grad: 0.1259 (0.1218) loss: 0.8883 (0.8901) time: 0.1559 data: 0.0770 max mem: 8233 +Train: [50] [1400/6250] eta: 0:13:32 lr: 0.000067 grad: 0.1258 (0.1218) loss: 0.8890 (0.8899) time: 0.1595 data: 0.0784 max mem: 8233 +Train: [50] [1500/6250] eta: 0:13:12 lr: 0.000067 grad: 0.1165 (0.1219) loss: 0.8886 (0.8899) time: 0.1555 data: 0.0818 max mem: 8233 +Train: [50] [1600/6250] eta: 0:12:55 lr: 0.000067 grad: 0.1228 (0.1221) loss: 0.8897 (0.8898) time: 0.1767 data: 0.1020 max mem: 8233 +Train: [50] [1700/6250] eta: 0:12:41 lr: 0.000067 grad: 0.1130 (0.1220) loss: 0.8868 (0.8896) time: 0.1587 data: 0.0718 max mem: 8233 +Train: [50] [1800/6250] eta: 0:12:21 lr: 0.000067 grad: 0.1126 (0.1219) loss: 0.8869 (0.8895) time: 0.1506 data: 0.0608 max mem: 8233 +Train: [50] [1900/6250] eta: 0:12:02 lr: 0.000067 grad: 0.1188 (0.1222) loss: 0.8797 (0.8893) time: 0.1566 data: 0.0674 max mem: 8233 +Train: [50] [2000/6250] eta: 0:11:43 lr: 0.000067 grad: 0.1235 (0.1225) loss: 0.8861 (0.8891) time: 0.1456 data: 0.0466 max mem: 8233 +Train: [50] [2100/6250] eta: 0:11:23 lr: 0.000067 grad: 0.1177 (0.1227) loss: 0.8896 (0.8890) time: 0.1468 data: 0.0615 max mem: 8233 +Train: [50] [2200/6250] eta: 0:11:04 lr: 0.000067 grad: 0.1186 (0.1226) loss: 0.8898 (0.8889) time: 0.1601 data: 0.0769 max mem: 8233 +Train: [50] [2300/6250] eta: 0:10:45 lr: 0.000067 grad: 0.1140 (0.1225) loss: 0.8911 (0.8889) time: 0.1501 data: 0.0708 max mem: 8233 +Train: [50] [2400/6250] eta: 0:10:26 lr: 0.000067 grad: 0.1224 (0.1226) loss: 0.8903 (0.8889) time: 0.1519 data: 0.0660 max mem: 8233 +Train: [50] [2500/6250] eta: 0:10:09 lr: 0.000067 grad: 0.1215 (0.1225) loss: 0.8867 (0.8888) time: 0.1189 data: 0.0304 max mem: 8233 +Train: [50] [2600/6250] eta: 0:09:52 lr: 0.000067 grad: 0.1112 (0.1224) loss: 0.8894 (0.8888) time: 0.1575 data: 0.0773 max mem: 8233 +Train: [50] [2700/6250] eta: 0:09:35 lr: 0.000067 grad: 0.1112 (0.1223) loss: 0.8827 (0.8887) time: 0.1607 data: 0.0821 max mem: 8233 +Train: [50] [2800/6250] eta: 0:09:18 lr: 0.000067 grad: 0.1215 (0.1224) loss: 0.8899 (0.8886) time: 0.1634 data: 0.0948 max mem: 8233 +Train: [50] [2900/6250] eta: 0:09:02 lr: 0.000067 grad: 0.1141 (0.1225) loss: 0.8887 (0.8886) time: 0.1755 data: 0.0912 max mem: 8233 +Train: [50] [3000/6250] eta: 0:08:45 lr: 0.000067 grad: 0.1223 (0.1225) loss: 0.8874 (0.8885) time: 0.1673 data: 0.0874 max mem: 8233 +Train: [50] [3100/6250] eta: 0:08:28 lr: 0.000067 grad: 0.1205 (0.1225) loss: 0.8914 (0.8884) time: 0.1540 data: 0.0729 max mem: 8233 +Train: [50] [3200/6250] eta: 0:08:14 lr: 0.000067 grad: 0.1206 (0.1227) loss: 0.8852 (0.8884) time: 0.1809 data: 0.1119 max mem: 8233 +Train: [50] [3300/6250] eta: 0:07:57 lr: 0.000067 grad: 0.1191 (0.1226) loss: 0.8896 (0.8883) time: 0.1596 data: 0.0873 max mem: 8233 +Train: [50] [3400/6250] eta: 0:07:40 lr: 0.000067 grad: 0.1074 (0.1226) loss: 0.8873 (0.8883) time: 0.1352 data: 0.0656 max mem: 8233 +Train: [50] [3500/6250] eta: 0:07:24 lr: 0.000067 grad: 0.1143 (0.1226) loss: 0.8878 (0.8882) time: 0.1638 data: 0.0814 max mem: 8233 +Train: [50] [3600/6250] eta: 0:07:09 lr: 0.000066 grad: 0.1173 (0.1226) loss: 0.8839 (0.8881) time: 0.2032 data: 0.1209 max mem: 8233 +Train: [50] [3700/6250] eta: 0:06:52 lr: 0.000066 grad: 0.1204 (0.1225) loss: 0.8913 (0.8881) time: 0.1528 data: 0.0709 max mem: 8233 +Train: [50] [3800/6250] eta: 0:06:36 lr: 0.000066 grad: 0.1157 (0.1224) loss: 0.8883 (0.8881) time: 0.1716 data: 0.0850 max mem: 8233 +Train: [50] [3900/6250] eta: 0:06:20 lr: 0.000066 grad: 0.1159 (0.1224) loss: 0.8874 (0.8881) time: 0.1470 data: 0.0585 max mem: 8233 +Train: [50] [4000/6250] eta: 0:06:04 lr: 0.000066 grad: 0.1115 (0.1224) loss: 0.8904 (0.8880) time: 0.1624 data: 0.0706 max mem: 8233 +Train: [50] [4100/6250] eta: 0:05:48 lr: 0.000066 grad: 0.1174 (0.1224) loss: 0.8906 (0.8880) time: 0.1864 data: 0.1021 max mem: 8233 +Train: [50] [4200/6250] eta: 0:05:32 lr: 0.000066 grad: 0.1168 (0.1225) loss: 0.8861 (0.8879) time: 0.1546 data: 0.0772 max mem: 8233 +Train: [50] [4300/6250] eta: 0:05:15 lr: 0.000066 grad: 0.1194 (0.1224) loss: 0.8826 (0.8878) time: 0.1307 data: 0.0450 max mem: 8233 +Train: [50] [4400/6250] eta: 0:04:59 lr: 0.000066 grad: 0.1166 (0.1224) loss: 0.8867 (0.8877) time: 0.1699 data: 0.0842 max mem: 8233 +Train: [50] [4500/6250] eta: 0:04:42 lr: 0.000066 grad: 0.1215 (0.1224) loss: 0.8864 (0.8876) time: 0.1388 data: 0.0605 max mem: 8233 +Train: [50] [4600/6250] eta: 0:04:26 lr: 0.000066 grad: 0.1193 (0.1225) loss: 0.8832 (0.8876) time: 0.1602 data: 0.0927 max mem: 8233 +Train: [50] [4700/6250] eta: 0:04:09 lr: 0.000066 grad: 0.1265 (0.1226) loss: 0.8837 (0.8875) time: 0.1424 data: 0.0570 max mem: 8233 +Train: [50] [4800/6250] eta: 0:03:52 lr: 0.000066 grad: 0.1196 (0.1226) loss: 0.8871 (0.8874) time: 0.1434 data: 0.0691 max mem: 8233 +Train: [50] [4900/6250] eta: 0:03:36 lr: 0.000066 grad: 0.1210 (0.1227) loss: 0.8869 (0.8873) time: 0.1396 data: 0.0584 max mem: 8233 +Train: [50] [5000/6250] eta: 0:03:20 lr: 0.000066 grad: 0.1197 (0.1227) loss: 0.8815 (0.8873) time: 0.1430 data: 0.0668 max mem: 8233 +Train: [50] [5100/6250] eta: 0:03:04 lr: 0.000066 grad: 0.1189 (0.1228) loss: 0.8812 (0.8872) time: 0.1282 data: 0.0502 max mem: 8233 +Train: [50] [5200/6250] eta: 0:02:49 lr: 0.000066 grad: 0.1249 (0.1229) loss: 0.8887 (0.8872) time: 0.1864 data: 0.1054 max mem: 8233 +Train: [50] [5300/6250] eta: 0:02:33 lr: 0.000066 grad: 0.1098 (0.1229) loss: 0.8840 (0.8871) time: 0.1254 data: 0.0003 max mem: 8233 +Train: [50] [5400/6250] eta: 0:02:17 lr: 0.000066 grad: 0.1131 (0.1230) loss: 0.8880 (0.8871) time: 0.1565 data: 0.0696 max mem: 8233 +Train: [50] [5500/6250] eta: 0:02:01 lr: 0.000066 grad: 0.1202 (0.1230) loss: 0.8833 (0.8871) time: 0.1445 data: 0.0575 max mem: 8233 +Train: [50] [5600/6250] eta: 0:01:45 lr: 0.000066 grad: 0.1149 (0.1230) loss: 0.8834 (0.8871) time: 0.1675 data: 0.0898 max mem: 8233 +Train: [50] [5700/6250] eta: 0:01:29 lr: 0.000066 grad: 0.1195 (0.1231) loss: 0.8852 (0.8870) time: 0.1492 data: 0.0747 max mem: 8233 +Train: [50] [5800/6250] eta: 0:01:13 lr: 0.000066 grad: 0.1150 (0.1230) loss: 0.8846 (0.8870) time: 0.1681 data: 0.0826 max mem: 8233 +Train: [50] [5900/6250] eta: 0:00:56 lr: 0.000066 grad: 0.1156 (0.1230) loss: 0.8866 (0.8870) time: 0.1928 data: 0.1059 max mem: 8233 +Train: [50] [6000/6250] eta: 0:00:40 lr: 0.000066 grad: 0.1200 (0.1230) loss: 0.8845 (0.8869) time: 0.1799 data: 0.1062 max mem: 8233 +Train: [50] [6100/6250] eta: 0:00:24 lr: 0.000066 grad: 0.1204 (0.1231) loss: 0.8886 (0.8869) time: 0.1562 data: 0.0665 max mem: 8233 +Train: [50] [6200/6250] eta: 0:00:08 lr: 0.000066 grad: 0.1178 (0.1231) loss: 0.8830 (0.8869) time: 0.1540 data: 0.0742 max mem: 8233 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.1262 (0.1232) loss: 0.8857 (0.8869) time: 0.1771 data: 0.0912 max mem: 8233 +Train: [50] Total time: 0:17:05 (0.1640 s / it) +Averaged stats: lr: 0.000066 grad: 0.1262 (0.1232) loss: 0.8857 (0.8869) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:05:13 loss: 0.9036 (0.9036) time: 5.0609 data: 5.0289 max mem: 8233 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8940 (0.8949) time: 0.1430 data: 0.1223 max mem: 8233 +Eval (hcp-train-subset): [50] Total time: 0:00:14 (0.2401 s / it) +Averaged stats (hcp-train-subset): loss: 0.8940 (0.8949) +Eval (hcp-val): [50] [ 0/62] eta: 0:03:46 loss: 0.8873 (0.8873) time: 3.6587 data: 3.5825 max mem: 8233 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8916 (0.8925) time: 0.1645 data: 0.1430 max mem: 8233 +Eval (hcp-val): [50] Total time: 0:00:15 (0.2563 s / it) +Averaged stats (hcp-val): loss: 0.8916 (0.8925) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 11:38:28 lr: 0.000066 grad: 0.0939 (0.0939) loss: 0.9251 (0.9251) time: 6.7053 data: 6.6011 max mem: 8233 +Train: [51] [ 100/6250] eta: 0:23:01 lr: 0.000066 grad: 0.1075 (0.1118) loss: 0.8944 (0.8972) time: 0.1752 data: 0.0778 max mem: 8233 +Train: [51] [ 200/6250] eta: 0:19:57 lr: 0.000066 grad: 0.1028 (0.1106) loss: 0.8946 (0.8960) time: 0.1656 data: 0.0798 max mem: 8233 +Train: [51] [ 300/6250] eta: 0:18:42 lr: 0.000065 grad: 0.1073 (0.1113) loss: 0.8939 (0.8959) time: 0.1679 data: 0.0658 max mem: 8233 +Train: [51] [ 400/6250] eta: 0:17:55 lr: 0.000065 grad: 0.1057 (0.1113) loss: 0.8883 (0.8952) time: 0.1770 data: 0.0849 max mem: 8233 +Train: [51] [ 500/6250] eta: 0:17:17 lr: 0.000065 grad: 0.1115 (0.1119) loss: 0.8835 (0.8938) time: 0.1757 data: 0.0853 max mem: 8233 +Train: [51] [ 600/6250] eta: 0:16:48 lr: 0.000065 grad: 0.1073 (0.1123) loss: 0.8860 (0.8927) time: 0.1795 data: 0.0965 max mem: 8233 +Train: [51] [ 700/6250] eta: 0:16:18 lr: 0.000065 grad: 0.1114 (0.1124) loss: 0.8899 (0.8921) time: 0.1686 data: 0.0787 max mem: 8233 +Train: [51] [ 800/6250] eta: 0:15:51 lr: 0.000065 grad: 0.1112 (0.1128) loss: 0.8881 (0.8914) time: 0.1673 data: 0.0828 max mem: 8233 +Train: [51] [ 900/6250] eta: 0:15:24 lr: 0.000065 grad: 0.1138 (0.1125) loss: 0.8928 (0.8911) time: 0.1635 data: 0.0793 max mem: 8233 +Train: [51] [1000/6250] eta: 0:15:05 lr: 0.000065 grad: 0.1115 (0.1128) loss: 0.8897 (0.8909) time: 0.1866 data: 0.1117 max mem: 8233 +Train: [51] [1100/6250] eta: 0:14:41 lr: 0.000065 grad: 0.1128 (0.1128) loss: 0.8894 (0.8906) time: 0.1541 data: 0.0802 max mem: 8233 +Train: [51] [1200/6250] eta: 0:14:18 lr: 0.000065 grad: 0.1076 (0.1130) loss: 0.8908 (0.8904) time: 0.1603 data: 0.0808 max mem: 8233 +Train: [51] [1300/6250] eta: 0:13:55 lr: 0.000065 grad: 0.1082 (0.1131) loss: 0.8877 (0.8901) time: 0.1573 data: 0.0727 max mem: 8233 +Train: [51] [1400/6250] eta: 0:13:36 lr: 0.000065 grad: 0.1121 (0.1131) loss: 0.8875 (0.8898) time: 0.1811 data: 0.1027 max mem: 8233 +Train: [51] [1500/6250] eta: 0:13:15 lr: 0.000065 grad: 0.1091 (0.1131) loss: 0.8865 (0.8897) time: 0.1591 data: 0.0835 max mem: 8233 +Train: [51] [1600/6250] eta: 0:12:56 lr: 0.000065 grad: 0.1155 (0.1135) loss: 0.8805 (0.8895) time: 0.1807 data: 0.0970 max mem: 8233 +Train: [51] [1700/6250] eta: 0:12:39 lr: 0.000065 grad: 0.1154 (0.1138) loss: 0.8855 (0.8893) time: 0.1880 data: 0.1129 max mem: 8233 +Train: [51] [1800/6250] eta: 0:12:27 lr: 0.000065 grad: 0.1101 (0.1139) loss: 0.8942 (0.8892) time: 0.1701 data: 0.0828 max mem: 8233 +Train: [51] [1900/6250] eta: 0:12:10 lr: 0.000065 grad: 0.1090 (0.1142) loss: 0.8845 (0.8891) time: 0.1500 data: 0.0720 max mem: 8233 +Train: [51] [2000/6250] eta: 0:11:52 lr: 0.000065 grad: 0.1162 (0.1145) loss: 0.8880 (0.8890) time: 0.1683 data: 0.0743 max mem: 8233 +Train: [51] [2100/6250] eta: 0:11:34 lr: 0.000065 grad: 0.1133 (0.1147) loss: 0.8874 (0.8889) time: 0.1555 data: 0.0809 max mem: 8233 +Train: [51] [2200/6250] eta: 0:11:16 lr: 0.000065 grad: 0.1135 (0.1151) loss: 0.8903 (0.8888) time: 0.1681 data: 0.0812 max mem: 8233 +Train: [51] [2300/6250] eta: 0:10:57 lr: 0.000065 grad: 0.1222 (0.1152) loss: 0.8889 (0.8887) time: 0.1732 data: 0.1050 max mem: 8233 +Train: [51] [2400/6250] eta: 0:10:42 lr: 0.000065 grad: 0.1175 (0.1154) loss: 0.8793 (0.8885) time: 0.1145 data: 0.0034 max mem: 8233 +Train: [51] [2500/6250] eta: 0:10:26 lr: 0.000065 grad: 0.1162 (0.1156) loss: 0.8893 (0.8885) time: 0.1911 data: 0.1082 max mem: 8233 +Train: [51] [2600/6250] eta: 0:10:08 lr: 0.000065 grad: 0.1135 (0.1156) loss: 0.8911 (0.8884) time: 0.1256 data: 0.0411 max mem: 8233 +Train: [51] [2700/6250] eta: 0:09:54 lr: 0.000065 grad: 0.1172 (0.1157) loss: 0.8906 (0.8883) time: 0.0961 data: 0.0211 max mem: 8233 +Train: [51] [2800/6250] eta: 0:09:36 lr: 0.000065 grad: 0.1163 (0.1158) loss: 0.8800 (0.8882) time: 0.1465 data: 0.0613 max mem: 8233 +Train: [51] [2900/6250] eta: 0:09:18 lr: 0.000065 grad: 0.1117 (0.1158) loss: 0.8881 (0.8881) time: 0.1779 data: 0.0901 max mem: 8233 +Train: [51] [3000/6250] eta: 0:09:02 lr: 0.000065 grad: 0.1167 (0.1160) loss: 0.8860 (0.8880) time: 0.1547 data: 0.0750 max mem: 8233 +Train: [51] [3100/6250] eta: 0:08:45 lr: 0.000065 grad: 0.1129 (0.1161) loss: 0.8859 (0.8880) time: 0.1704 data: 0.0925 max mem: 8233 +Train: [51] [3200/6250] eta: 0:08:27 lr: 0.000065 grad: 0.1168 (0.1161) loss: 0.8886 (0.8879) time: 0.1687 data: 0.0886 max mem: 8233 +Train: [51] [3300/6250] eta: 0:08:14 lr: 0.000065 grad: 0.1173 (0.1162) loss: 0.8913 (0.8879) time: 0.3030 data: 0.2179 max mem: 8233 +Train: [51] [3400/6250] eta: 0:07:56 lr: 0.000064 grad: 0.1083 (0.1162) loss: 0.8914 (0.8879) time: 0.1775 data: 0.1087 max mem: 8233 +Train: [51] [3500/6250] eta: 0:07:38 lr: 0.000064 grad: 0.1139 (0.1164) loss: 0.8904 (0.8879) time: 0.1545 data: 0.0836 max mem: 8233 +Train: [51] [3600/6250] eta: 0:07:22 lr: 0.000064 grad: 0.1137 (0.1164) loss: 0.8932 (0.8879) time: 0.1586 data: 0.0720 max mem: 8233 +Train: [51] [3700/6250] eta: 0:07:06 lr: 0.000064 grad: 0.1177 (0.1165) loss: 0.8902 (0.8880) time: 0.1595 data: 0.0870 max mem: 8233 +Train: [51] [3800/6250] eta: 0:06:49 lr: 0.000064 grad: 0.1116 (0.1167) loss: 0.8856 (0.8879) time: 0.1625 data: 0.0748 max mem: 8233 +Train: [51] [3900/6250] eta: 0:06:32 lr: 0.000064 grad: 0.1202 (0.1170) loss: 0.8894 (0.8879) time: 0.1550 data: 0.0790 max mem: 8233 +Train: [51] [4000/6250] eta: 0:06:15 lr: 0.000064 grad: 0.1144 (0.1170) loss: 0.8895 (0.8879) time: 0.1567 data: 0.0667 max mem: 8233 +Train: [51] [4100/6250] eta: 0:05:57 lr: 0.000064 grad: 0.1148 (0.1172) loss: 0.8890 (0.8879) time: 0.1532 data: 0.0659 max mem: 8233 +Train: [51] [4200/6250] eta: 0:05:40 lr: 0.000064 grad: 0.1222 (0.1173) loss: 0.8835 (0.8878) time: 0.1089 data: 0.0095 max mem: 8233 +Train: [51] [4300/6250] eta: 0:05:23 lr: 0.000064 grad: 0.1198 (0.1175) loss: 0.8877 (0.8878) time: 0.1463 data: 0.0649 max mem: 8233 +Train: [51] [4400/6250] eta: 0:05:06 lr: 0.000064 grad: 0.1208 (0.1176) loss: 0.8812 (0.8877) time: 0.1588 data: 0.0811 max mem: 8233 +Train: [51] [4500/6250] eta: 0:04:49 lr: 0.000064 grad: 0.1155 (0.1177) loss: 0.8876 (0.8877) time: 0.2252 data: 0.1480 max mem: 8233 +Train: [51] [4600/6250] eta: 0:04:32 lr: 0.000064 grad: 0.1237 (0.1179) loss: 0.8880 (0.8877) time: 0.1535 data: 0.0789 max mem: 8233 +Train: [51] [4700/6250] eta: 0:04:15 lr: 0.000064 grad: 0.1229 (0.1181) loss: 0.8862 (0.8876) time: 0.1364 data: 0.0531 max mem: 8233 +Train: [51] [4800/6250] eta: 0:03:58 lr: 0.000064 grad: 0.1219 (0.1183) loss: 0.8838 (0.8875) time: 0.1866 data: 0.1130 max mem: 8233 +Train: [51] [4900/6250] eta: 0:03:42 lr: 0.000064 grad: 0.1166 (0.1184) loss: 0.8890 (0.8875) time: 0.1676 data: 0.0812 max mem: 8233 +Train: [51] [5000/6250] eta: 0:03:25 lr: 0.000064 grad: 0.1196 (0.1186) loss: 0.8813 (0.8875) time: 0.1264 data: 0.0337 max mem: 8233 +Train: [51] [5100/6250] eta: 0:03:09 lr: 0.000064 grad: 0.1252 (0.1188) loss: 0.8881 (0.8875) time: 0.1473 data: 0.0434 max mem: 8233 +Train: [51] [5200/6250] eta: 0:02:52 lr: 0.000064 grad: 0.1166 (0.1189) loss: 0.8872 (0.8874) time: 0.1838 data: 0.1086 max mem: 8233 +Train: [51] [5300/6250] eta: 0:02:36 lr: 0.000064 grad: 0.1195 (0.1189) loss: 0.8861 (0.8874) time: 0.1635 data: 0.0881 max mem: 8233 +Train: [51] [5400/6250] eta: 0:02:19 lr: 0.000064 grad: 0.1206 (0.1191) loss: 0.8881 (0.8874) time: 0.1382 data: 0.0567 max mem: 8233 +Train: [51] [5500/6250] eta: 0:02:03 lr: 0.000064 grad: 0.1225 (0.1193) loss: 0.8882 (0.8874) time: 0.1522 data: 0.0710 max mem: 8233 +Train: [51] [5600/6250] eta: 0:01:46 lr: 0.000064 grad: 0.1219 (0.1194) loss: 0.8885 (0.8873) time: 0.1727 data: 0.0972 max mem: 8233 +Train: [51] [5700/6250] eta: 0:01:30 lr: 0.000064 grad: 0.1134 (0.1195) loss: 0.8876 (0.8873) time: 0.1671 data: 0.0942 max mem: 8233 +Train: [51] [5800/6250] eta: 0:01:13 lr: 0.000064 grad: 0.1302 (0.1196) loss: 0.8916 (0.8873) time: 0.1665 data: 0.0872 max mem: 8233 +Train: [51] [5900/6250] eta: 0:00:57 lr: 0.000064 grad: 0.1151 (0.1197) loss: 0.8880 (0.8873) time: 0.1540 data: 0.0643 max mem: 8233 +Train: [51] [6000/6250] eta: 0:00:41 lr: 0.000064 grad: 0.1184 (0.1198) loss: 0.8843 (0.8873) time: 0.1833 data: 0.1106 max mem: 8233 +Train: [51] [6100/6250] eta: 0:00:24 lr: 0.000064 grad: 0.1207 (0.1199) loss: 0.8873 (0.8872) time: 0.1680 data: 0.0779 max mem: 8233 +Train: [51] [6200/6250] eta: 0:00:08 lr: 0.000064 grad: 0.1252 (0.1200) loss: 0.8818 (0.8872) time: 0.1416 data: 0.0564 max mem: 8233 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.1168 (0.1200) loss: 0.8876 (0.8872) time: 0.1610 data: 0.0733 max mem: 8233 +Train: [51] Total time: 0:17:11 (0.1650 s / it) +Averaged stats: lr: 0.000064 grad: 0.1168 (0.1200) loss: 0.8876 (0.8872) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:05:49 loss: 0.9028 (0.9028) time: 5.6301 data: 5.6028 max mem: 8233 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8937 (0.8944) time: 0.1401 data: 0.1183 max mem: 8233 +Eval (hcp-train-subset): [51] Total time: 0:00:13 (0.2254 s / it) +Averaged stats (hcp-train-subset): loss: 0.8937 (0.8944) +Eval (hcp-val): [51] [ 0/62] eta: 0:05:23 loss: 0.8877 (0.8877) time: 5.2173 data: 5.1915 max mem: 8233 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8911 (0.8910) time: 0.1176 data: 0.0968 max mem: 8233 +Eval (hcp-val): [51] Total time: 0:00:13 (0.2250 s / it) +Averaged stats (hcp-val): loss: 0.8911 (0.8910) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 8:42:11 lr: 0.000064 grad: 0.0725 (0.0725) loss: 0.9155 (0.9155) time: 5.0130 data: 4.7322 max mem: 8233 +Train: [52] [ 100/6250] eta: 0:22:56 lr: 0.000063 grad: 0.1185 (0.1253) loss: 0.8916 (0.8926) time: 0.1933 data: 0.0690 max mem: 8233 +Train: [52] [ 200/6250] eta: 0:19:50 lr: 0.000063 grad: 0.1190 (0.1247) loss: 0.8832 (0.8888) time: 0.1574 data: 0.0575 max mem: 8233 +Train: [52] [ 300/6250] eta: 0:18:06 lr: 0.000063 grad: 0.1199 (0.1238) loss: 0.8779 (0.8862) time: 0.1530 data: 0.0500 max mem: 8233 +Train: [52] [ 400/6250] eta: 0:17:07 lr: 0.000063 grad: 0.1176 (0.1234) loss: 0.8791 (0.8846) time: 0.1707 data: 0.0783 max mem: 8233 +Train: [52] [ 500/6250] eta: 0:16:25 lr: 0.000063 grad: 0.1203 (0.1227) loss: 0.8812 (0.8839) time: 0.1419 data: 0.0453 max mem: 8233 +Train: [52] [ 600/6250] eta: 0:16:02 lr: 0.000063 grad: 0.1202 (0.1221) loss: 0.8777 (0.8835) time: 0.1514 data: 0.0606 max mem: 8233 +Train: [52] [ 700/6250] eta: 0:15:41 lr: 0.000063 grad: 0.1143 (0.1215) loss: 0.8768 (0.8833) time: 0.1655 data: 0.0774 max mem: 8233 +Train: [52] [ 800/6250] eta: 0:15:18 lr: 0.000063 grad: 0.1081 (0.1208) loss: 0.8873 (0.8833) time: 0.1657 data: 0.0803 max mem: 8233 +Train: [52] [ 900/6250] eta: 0:14:59 lr: 0.000063 grad: 0.1090 (0.1201) loss: 0.8834 (0.8838) time: 0.1074 data: 0.0002 max mem: 8233 +Train: [52] [1000/6250] eta: 0:14:52 lr: 0.000063 grad: 0.1116 (0.1200) loss: 0.8856 (0.8839) time: 0.2327 data: 0.1589 max mem: 8233 +Train: [52] [1100/6250] eta: 0:14:24 lr: 0.000063 grad: 0.1102 (0.1198) loss: 0.8864 (0.8841) time: 0.2083 data: 0.1335 max mem: 8233 +Train: [52] [1200/6250] eta: 0:14:00 lr: 0.000063 grad: 0.1159 (0.1195) loss: 0.8855 (0.8842) time: 0.1476 data: 0.0630 max mem: 8233 +Train: [52] [1300/6250] eta: 0:13:39 lr: 0.000063 grad: 0.1160 (0.1195) loss: 0.8884 (0.8843) time: 0.1401 data: 0.0679 max mem: 8233 +Train: [52] [1400/6250] eta: 0:13:27 lr: 0.000063 grad: 0.1214 (0.1197) loss: 0.8840 (0.8843) time: 0.1734 data: 0.0896 max mem: 8233 +Train: [52] [1500/6250] eta: 0:13:06 lr: 0.000063 grad: 0.1279 (0.1200) loss: 0.8828 (0.8842) time: 0.1652 data: 0.0825 max mem: 8233 +Train: [52] [1600/6250] eta: 0:12:48 lr: 0.000063 grad: 0.1202 (0.1200) loss: 0.8847 (0.8843) time: 0.1717 data: 0.0893 max mem: 8233 +Train: [52] [1700/6250] eta: 0:12:31 lr: 0.000063 grad: 0.1178 (0.1198) loss: 0.8822 (0.8844) time: 0.1714 data: 0.1021 max mem: 8233 +Train: [52] [1800/6250] eta: 0:12:16 lr: 0.000063 grad: 0.1126 (0.1197) loss: 0.8826 (0.8844) time: 0.1652 data: 0.0790 max mem: 8233 +Train: [52] [1900/6250] eta: 0:11:56 lr: 0.000063 grad: 0.1194 (0.1197) loss: 0.8823 (0.8845) time: 0.1468 data: 0.0501 max mem: 8233 +Train: [52] [2000/6250] eta: 0:11:39 lr: 0.000063 grad: 0.1142 (0.1195) loss: 0.8853 (0.8845) time: 0.1398 data: 0.0565 max mem: 8233 +Train: [52] [2100/6250] eta: 0:11:22 lr: 0.000063 grad: 0.1082 (0.1194) loss: 0.8895 (0.8845) time: 0.1658 data: 0.0814 max mem: 8233 +Train: [52] [2200/6250] eta: 0:11:03 lr: 0.000063 grad: 0.1236 (0.1194) loss: 0.8814 (0.8844) time: 0.1389 data: 0.0469 max mem: 8233 +Train: [52] [2300/6250] eta: 0:10:44 lr: 0.000063 grad: 0.1151 (0.1194) loss: 0.8846 (0.8844) time: 0.1370 data: 0.0575 max mem: 8233 +Train: [52] [2400/6250] eta: 0:10:25 lr: 0.000063 grad: 0.1119 (0.1193) loss: 0.8874 (0.8845) time: 0.1543 data: 0.0708 max mem: 8233 +Train: [52] [2500/6250] eta: 0:10:08 lr: 0.000063 grad: 0.1233 (0.1197) loss: 0.8831 (0.8845) time: 0.1561 data: 0.0770 max mem: 8233 +Train: [52] [2600/6250] eta: 0:09:50 lr: 0.000063 grad: 0.1199 (0.1198) loss: 0.8850 (0.8845) time: 0.1338 data: 0.0483 max mem: 8233 +Train: [52] [2700/6250] eta: 0:09:33 lr: 0.000063 grad: 0.1224 (0.1199) loss: 0.8839 (0.8845) time: 0.1302 data: 0.0463 max mem: 8233 +Train: [52] [2800/6250] eta: 0:09:17 lr: 0.000063 grad: 0.1143 (0.1199) loss: 0.8859 (0.8846) time: 0.2153 data: 0.1394 max mem: 8233 +Train: [52] [2900/6250] eta: 0:08:59 lr: 0.000063 grad: 0.1136 (0.1199) loss: 0.8897 (0.8846) time: 0.1431 data: 0.0668 max mem: 8233 +Train: [52] [3000/6250] eta: 0:08:42 lr: 0.000063 grad: 0.1153 (0.1199) loss: 0.8871 (0.8847) time: 0.1491 data: 0.0692 max mem: 8233 +Train: [52] [3100/6250] eta: 0:08:25 lr: 0.000063 grad: 0.1116 (0.1200) loss: 0.8856 (0.8847) time: 0.1488 data: 0.0708 max mem: 8233 +Train: [52] [3200/6250] eta: 0:08:08 lr: 0.000062 grad: 0.1151 (0.1201) loss: 0.8877 (0.8847) time: 0.1583 data: 0.0787 max mem: 8233 +Train: [52] [3300/6250] eta: 0:07:51 lr: 0.000062 grad: 0.1205 (0.1202) loss: 0.8874 (0.8847) time: 0.1499 data: 0.0599 max mem: 8233 +Train: [52] [3400/6250] eta: 0:07:37 lr: 0.000062 grad: 0.1222 (0.1203) loss: 0.8869 (0.8847) time: 0.1493 data: 0.0751 max mem: 8233 +Train: [52] [3500/6250] eta: 0:07:22 lr: 0.000062 grad: 0.1186 (0.1203) loss: 0.8847 (0.8848) time: 0.1910 data: 0.1103 max mem: 8233 +Train: [52] [3600/6250] eta: 0:07:06 lr: 0.000062 grad: 0.1190 (0.1203) loss: 0.8883 (0.8849) time: 0.2137 data: 0.1341 max mem: 8233 +Train: [52] [3700/6250] eta: 0:06:51 lr: 0.000062 grad: 0.1137 (0.1204) loss: 0.8884 (0.8849) time: 0.1583 data: 0.0709 max mem: 8233 +Train: [52] [3800/6250] eta: 0:06:37 lr: 0.000062 grad: 0.1178 (0.1205) loss: 0.8860 (0.8850) time: 0.2536 data: 0.1574 max mem: 8233 +Train: [52] [3900/6250] eta: 0:06:20 lr: 0.000062 grad: 0.1122 (0.1205) loss: 0.8905 (0.8851) time: 0.1670 data: 0.0845 max mem: 8233 +Train: [52] [4000/6250] eta: 0:06:05 lr: 0.000062 grad: 0.1169 (0.1205) loss: 0.8925 (0.8851) time: 0.1894 data: 0.1082 max mem: 8233 +Train: [52] [4100/6250] eta: 0:05:49 lr: 0.000062 grad: 0.1220 (0.1206) loss: 0.8869 (0.8852) time: 0.1658 data: 0.0835 max mem: 8233 +Train: [52] [4200/6250] eta: 0:05:33 lr: 0.000062 grad: 0.1136 (0.1206) loss: 0.8884 (0.8853) time: 0.1636 data: 0.0800 max mem: 8233 +Train: [52] [4300/6250] eta: 0:05:17 lr: 0.000062 grad: 0.1153 (0.1205) loss: 0.8881 (0.8853) time: 0.1567 data: 0.0623 max mem: 8233 +Train: [52] [4400/6250] eta: 0:05:01 lr: 0.000062 grad: 0.1150 (0.1206) loss: 0.8862 (0.8854) time: 0.1399 data: 0.0571 max mem: 8233 +Train: [52] [4500/6250] eta: 0:04:45 lr: 0.000062 grad: 0.1169 (0.1206) loss: 0.8889 (0.8854) time: 0.1461 data: 0.0696 max mem: 8233 +Train: [52] [4600/6250] eta: 0:04:29 lr: 0.000062 grad: 0.1157 (0.1206) loss: 0.8863 (0.8855) time: 0.1438 data: 0.0567 max mem: 8233 +Train: [52] [4700/6250] eta: 0:04:13 lr: 0.000062 grad: 0.1166 (0.1206) loss: 0.8895 (0.8856) time: 0.1842 data: 0.0959 max mem: 8233 +Train: [52] [4800/6250] eta: 0:03:56 lr: 0.000062 grad: 0.1208 (0.1206) loss: 0.8879 (0.8856) time: 0.1599 data: 0.0831 max mem: 8233 +Train: [52] [4900/6250] eta: 0:03:40 lr: 0.000062 grad: 0.1187 (0.1207) loss: 0.8853 (0.8856) time: 0.1816 data: 0.1086 max mem: 8233 +Train: [52] [5000/6250] eta: 0:03:23 lr: 0.000062 grad: 0.1147 (0.1208) loss: 0.8879 (0.8856) time: 0.1334 data: 0.0439 max mem: 8233 +Train: [52] [5100/6250] eta: 0:03:07 lr: 0.000062 grad: 0.1170 (0.1209) loss: 0.8843 (0.8856) time: 0.1688 data: 0.0724 max mem: 8233 +Train: [52] [5200/6250] eta: 0:02:51 lr: 0.000062 grad: 0.1104 (0.1209) loss: 0.8849 (0.8856) time: 0.3277 data: 0.2214 max mem: 8233 +Train: [52] [5300/6250] eta: 0:02:35 lr: 0.000062 grad: 0.1238 (0.1209) loss: 0.8823 (0.8856) time: 0.1717 data: 0.0978 max mem: 8233 +Train: [52] [5400/6250] eta: 0:02:18 lr: 0.000062 grad: 0.1197 (0.1210) loss: 0.8881 (0.8856) time: 0.1549 data: 0.0758 max mem: 8233 +Train: [52] [5500/6250] eta: 0:02:02 lr: 0.000062 grad: 0.1154 (0.1210) loss: 0.8819 (0.8856) time: 0.1741 data: 0.0967 max mem: 8233 +Train: [52] [5600/6250] eta: 0:01:45 lr: 0.000062 grad: 0.1172 (0.1210) loss: 0.8856 (0.8856) time: 0.1589 data: 0.0862 max mem: 8233 +Train: [52] [5700/6250] eta: 0:01:29 lr: 0.000062 grad: 0.1187 (0.1210) loss: 0.8796 (0.8856) time: 0.1761 data: 0.0911 max mem: 8233 +Train: [52] [5800/6250] eta: 0:01:13 lr: 0.000062 grad: 0.1207 (0.1210) loss: 0.8835 (0.8856) time: 0.1571 data: 0.0637 max mem: 8233 +Train: [52] [5900/6250] eta: 0:00:57 lr: 0.000062 grad: 0.1156 (0.1210) loss: 0.8874 (0.8857) time: 0.1420 data: 0.0709 max mem: 8233 +Train: [52] [6000/6250] eta: 0:00:40 lr: 0.000062 grad: 0.1354 (0.1211) loss: 0.8838 (0.8857) time: 0.1393 data: 0.0528 max mem: 8233 +Train: [52] [6100/6250] eta: 0:00:24 lr: 0.000062 grad: 0.1197 (0.1212) loss: 0.8854 (0.8857) time: 0.1500 data: 0.0630 max mem: 8233 +Train: [52] [6200/6250] eta: 0:00:08 lr: 0.000061 grad: 0.1190 (0.1212) loss: 0.8891 (0.8857) time: 0.2003 data: 0.1130 max mem: 8233 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.1239 (0.1213) loss: 0.8876 (0.8857) time: 0.1730 data: 0.0861 max mem: 8233 +Train: [52] Total time: 0:17:11 (0.1651 s / it) +Averaged stats: lr: 0.000061 grad: 0.1239 (0.1213) loss: 0.8876 (0.8857) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:05:38 loss: 0.9086 (0.9086) time: 5.4534 data: 5.4252 max mem: 8233 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8950 (0.8955) time: 0.1575 data: 0.1352 max mem: 8233 +Eval (hcp-train-subset): [52] Total time: 0:00:15 (0.2517 s / it) +Averaged stats (hcp-train-subset): loss: 0.8950 (0.8955) +Eval (hcp-val): [52] [ 0/62] eta: 0:06:05 loss: 0.8904 (0.8904) time: 5.8907 data: 5.8636 max mem: 8233 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8909 (0.8916) time: 0.1410 data: 0.1200 max mem: 8233 +Eval (hcp-val): [52] Total time: 0:00:15 (0.2456 s / it) +Averaged stats (hcp-val): loss: 0.8909 (0.8916) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 12:04:29 lr: 0.000061 grad: 0.1294 (0.1294) loss: 0.9014 (0.9014) time: 6.9551 data: 6.8563 max mem: 8233 +Train: [53] [ 100/6250] eta: 0:24:25 lr: 0.000061 grad: 0.1070 (0.1121) loss: 0.8947 (0.9004) time: 0.1935 data: 0.0946 max mem: 8233 +Train: [53] [ 200/6250] eta: 0:21:16 lr: 0.000061 grad: 0.1154 (0.1142) loss: 0.8965 (0.8952) time: 0.1874 data: 0.0835 max mem: 8233 +Train: [53] [ 300/6250] eta: 0:19:48 lr: 0.000061 grad: 0.1114 (0.1136) loss: 0.8897 (0.8934) time: 0.1699 data: 0.0759 max mem: 8233 +Train: [53] [ 400/6250] eta: 0:18:45 lr: 0.000061 grad: 0.1091 (0.1140) loss: 0.8888 (0.8918) time: 0.1657 data: 0.0659 max mem: 8233 +Train: [53] [ 500/6250] eta: 0:17:57 lr: 0.000061 grad: 0.1129 (0.1145) loss: 0.8852 (0.8907) time: 0.1722 data: 0.0763 max mem: 8233 +Train: [53] [ 600/6250] eta: 0:17:17 lr: 0.000061 grad: 0.1151 (0.1156) loss: 0.8813 (0.8897) time: 0.1767 data: 0.0988 max mem: 8233 +Train: [53] [ 700/6250] eta: 0:16:54 lr: 0.000061 grad: 0.1118 (0.1166) loss: 0.8865 (0.8891) time: 0.1143 data: 0.0233 max mem: 8233 +Train: [53] [ 800/6250] eta: 0:16:25 lr: 0.000061 grad: 0.1144 (0.1167) loss: 0.8895 (0.8888) time: 0.1578 data: 0.0710 max mem: 8233 +Train: [53] [ 900/6250] eta: 0:16:01 lr: 0.000061 grad: 0.1144 (0.1169) loss: 0.8829 (0.8882) time: 0.1919 data: 0.1007 max mem: 8233 +Train: [53] [1000/6250] eta: 0:15:41 lr: 0.000061 grad: 0.1190 (0.1169) loss: 0.8824 (0.8879) time: 0.1387 data: 0.0591 max mem: 8233 +Train: [53] [1100/6250] eta: 0:15:13 lr: 0.000061 grad: 0.1162 (0.1172) loss: 0.8841 (0.8877) time: 0.1789 data: 0.0925 max mem: 8233 +Train: [53] [1200/6250] eta: 0:14:46 lr: 0.000061 grad: 0.1147 (0.1175) loss: 0.8837 (0.8875) time: 0.1574 data: 0.0809 max mem: 8233 +Train: [53] [1300/6250] eta: 0:14:27 lr: 0.000061 grad: 0.1166 (0.1179) loss: 0.8795 (0.8871) time: 0.0980 data: 0.0033 max mem: 8233 +Train: [53] [1400/6250] eta: 0:14:05 lr: 0.000061 grad: 0.1149 (0.1181) loss: 0.8808 (0.8868) time: 0.1339 data: 0.0662 max mem: 8233 +Train: [53] [1500/6250] eta: 0:13:50 lr: 0.000061 grad: 0.1111 (0.1181) loss: 0.8887 (0.8867) time: 0.1446 data: 0.0643 max mem: 8233 +Train: [53] [1600/6250] eta: 0:13:31 lr: 0.000061 grad: 0.1131 (0.1183) loss: 0.8854 (0.8866) time: 0.1743 data: 0.0826 max mem: 8233 +Train: [53] [1700/6250] eta: 0:13:11 lr: 0.000061 grad: 0.1151 (0.1185) loss: 0.8852 (0.8864) time: 0.1731 data: 0.0856 max mem: 8233 +Train: [53] [1800/6250] eta: 0:12:54 lr: 0.000061 grad: 0.1158 (0.1187) loss: 0.8793 (0.8863) time: 0.1642 data: 0.0843 max mem: 8233 +Train: [53] [1900/6250] eta: 0:12:35 lr: 0.000061 grad: 0.1237 (0.1188) loss: 0.8835 (0.8862) time: 0.1421 data: 0.0579 max mem: 8233 +Train: [53] [2000/6250] eta: 0:12:15 lr: 0.000061 grad: 0.1275 (0.1193) loss: 0.8806 (0.8860) time: 0.1611 data: 0.0765 max mem: 8233 +Train: [53] [2100/6250] eta: 0:11:54 lr: 0.000061 grad: 0.1183 (0.1196) loss: 0.8792 (0.8857) time: 0.1566 data: 0.0758 max mem: 8233 +Train: [53] [2200/6250] eta: 0:11:34 lr: 0.000061 grad: 0.1194 (0.1198) loss: 0.8814 (0.8856) time: 0.1553 data: 0.0712 max mem: 8233 +Train: [53] [2300/6250] eta: 0:11:13 lr: 0.000061 grad: 0.1243 (0.1202) loss: 0.8836 (0.8855) time: 0.1389 data: 0.0527 max mem: 8233 +Train: [53] [2400/6250] eta: 0:10:52 lr: 0.000061 grad: 0.1238 (0.1205) loss: 0.8797 (0.8855) time: 0.1311 data: 0.0381 max mem: 8233 +Train: [53] [2500/6250] eta: 0:10:32 lr: 0.000061 grad: 0.1265 (0.1207) loss: 0.8796 (0.8854) time: 0.1410 data: 0.0565 max mem: 8233 +Train: [53] [2600/6250] eta: 0:10:13 lr: 0.000061 grad: 0.1270 (0.1212) loss: 0.8763 (0.8853) time: 0.1559 data: 0.0777 max mem: 8233 +Train: [53] [2700/6250] eta: 0:09:55 lr: 0.000061 grad: 0.1190 (0.1215) loss: 0.8861 (0.8852) time: 0.1705 data: 0.0941 max mem: 8233 +Train: [53] [2800/6250] eta: 0:09:36 lr: 0.000061 grad: 0.1228 (0.1218) loss: 0.8799 (0.8850) time: 0.1553 data: 0.0787 max mem: 8233 +Train: [53] [2900/6250] eta: 0:09:21 lr: 0.000061 grad: 0.1247 (0.1219) loss: 0.8791 (0.8849) time: 0.2171 data: 0.1397 max mem: 8233 +Train: [53] [3000/6250] eta: 0:09:02 lr: 0.000060 grad: 0.1202 (0.1221) loss: 0.8763 (0.8847) time: 0.1848 data: 0.1017 max mem: 8233 +Train: [53] [3100/6250] eta: 0:08:44 lr: 0.000060 grad: 0.1193 (0.1222) loss: 0.8868 (0.8845) time: 0.1710 data: 0.0897 max mem: 8233 +Train: [53] [3200/6250] eta: 0:08:25 lr: 0.000060 grad: 0.1301 (0.1225) loss: 0.8788 (0.8844) time: 0.1477 data: 0.0678 max mem: 8233 +Train: [53] [3300/6250] eta: 0:08:08 lr: 0.000060 grad: 0.1328 (0.1227) loss: 0.8778 (0.8842) time: 0.1324 data: 0.0511 max mem: 8233 +Train: [53] [3400/6250] eta: 0:07:51 lr: 0.000060 grad: 0.1215 (0.1229) loss: 0.8823 (0.8840) time: 0.1373 data: 0.0521 max mem: 8233 +Train: [53] [3500/6250] eta: 0:07:35 lr: 0.000060 grad: 0.1290 (0.1232) loss: 0.8798 (0.8839) time: 0.1634 data: 0.0926 max mem: 8233 +Train: [53] [3600/6250] eta: 0:07:18 lr: 0.000060 grad: 0.1218 (0.1234) loss: 0.8792 (0.8838) time: 0.1779 data: 0.1008 max mem: 8233 +Train: [53] [3700/6250] eta: 0:07:02 lr: 0.000060 grad: 0.1249 (0.1236) loss: 0.8789 (0.8836) time: 0.1551 data: 0.0713 max mem: 8233 +Train: [53] [3800/6250] eta: 0:06:45 lr: 0.000060 grad: 0.1246 (0.1237) loss: 0.8788 (0.8835) time: 0.1703 data: 0.0885 max mem: 8233 +Train: [53] [3900/6250] eta: 0:06:30 lr: 0.000060 grad: 0.1265 (0.1239) loss: 0.8800 (0.8835) time: 0.1715 data: 0.0824 max mem: 8233 +Train: [53] [4000/6250] eta: 0:06:13 lr: 0.000060 grad: 0.1233 (0.1240) loss: 0.8883 (0.8834) time: 0.1697 data: 0.0866 max mem: 8233 +Train: [53] [4100/6250] eta: 0:05:55 lr: 0.000060 grad: 0.1252 (0.1241) loss: 0.8823 (0.8835) time: 0.1527 data: 0.0758 max mem: 8233 +Train: [53] [4200/6250] eta: 0:05:38 lr: 0.000060 grad: 0.1389 (0.1242) loss: 0.8863 (0.8835) time: 0.1440 data: 0.0600 max mem: 8233 +Train: [53] [4300/6250] eta: 0:05:21 lr: 0.000060 grad: 0.1148 (0.1241) loss: 0.8897 (0.8835) time: 0.1444 data: 0.0635 max mem: 8233 +Train: [53] [4400/6250] eta: 0:05:04 lr: 0.000060 grad: 0.1176 (0.1242) loss: 0.8872 (0.8835) time: 0.1493 data: 0.0714 max mem: 8233 +Train: [53] [4500/6250] eta: 0:04:47 lr: 0.000060 grad: 0.1179 (0.1243) loss: 0.8803 (0.8835) time: 0.1707 data: 0.0914 max mem: 8233 +Train: [53] [4600/6250] eta: 0:04:30 lr: 0.000060 grad: 0.1233 (0.1249) loss: 0.8861 (0.8835) time: 0.1605 data: 0.0685 max mem: 8233 +Train: [53] [4700/6250] eta: 0:04:13 lr: 0.000060 grad: 0.1190 (0.1249) loss: 0.8843 (0.8835) time: 0.1457 data: 0.0684 max mem: 8233 +Train: [53] [4800/6250] eta: 0:03:57 lr: 0.000060 grad: 0.1160 (0.1248) loss: 0.8877 (0.8835) time: 0.1774 data: 0.0975 max mem: 8233 +Train: [53] [4900/6250] eta: 0:03:40 lr: 0.000060 grad: 0.1207 (0.1249) loss: 0.8855 (0.8835) time: 0.1478 data: 0.0665 max mem: 8233 +Train: [53] [5000/6250] eta: 0:03:24 lr: 0.000060 grad: 0.1257 (0.1250) loss: 0.8808 (0.8835) time: 0.2078 data: 0.1199 max mem: 8233 +Train: [53] [5100/6250] eta: 0:03:09 lr: 0.000060 grad: 0.1154 (0.1249) loss: 0.8850 (0.8835) time: 0.1157 data: 0.0005 max mem: 8233 +Train: [53] [5200/6250] eta: 0:02:52 lr: 0.000060 grad: 0.1202 (0.1249) loss: 0.8845 (0.8836) time: 0.1307 data: 0.0384 max mem: 8233 +Train: [53] [5300/6250] eta: 0:02:36 lr: 0.000060 grad: 0.1183 (0.1250) loss: 0.8831 (0.8835) time: 0.1866 data: 0.1083 max mem: 8233 +Train: [53] [5400/6250] eta: 0:02:19 lr: 0.000060 grad: 0.1188 (0.1250) loss: 0.8867 (0.8836) time: 0.1575 data: 0.0735 max mem: 8233 +Train: [53] [5500/6250] eta: 0:02:02 lr: 0.000060 grad: 0.1205 (0.1250) loss: 0.8839 (0.8836) time: 0.1486 data: 0.0537 max mem: 8233 +Train: [53] [5600/6250] eta: 0:01:46 lr: 0.000060 grad: 0.1185 (0.1250) loss: 0.8781 (0.8835) time: 0.1259 data: 0.0310 max mem: 8233 +Train: [53] [5700/6250] eta: 0:01:30 lr: 0.000060 grad: 0.1260 (0.1251) loss: 0.8807 (0.8835) time: 0.1653 data: 0.0778 max mem: 8233 +Train: [53] [5800/6250] eta: 0:01:13 lr: 0.000060 grad: 0.1187 (0.1251) loss: 0.8827 (0.8835) time: 0.1510 data: 0.0716 max mem: 8233 +Train: [53] [5900/6250] eta: 0:00:57 lr: 0.000060 grad: 0.1270 (0.1251) loss: 0.8835 (0.8835) time: 0.1484 data: 0.0689 max mem: 8233 +Train: [53] [6000/6250] eta: 0:00:40 lr: 0.000059 grad: 0.1283 (0.1251) loss: 0.8836 (0.8836) time: 0.1464 data: 0.0707 max mem: 8233 +Train: [53] [6100/6250] eta: 0:00:24 lr: 0.000059 grad: 0.1233 (0.1252) loss: 0.8828 (0.8836) time: 0.1546 data: 0.0609 max mem: 8233 +Train: [53] [6200/6250] eta: 0:00:08 lr: 0.000059 grad: 0.1207 (0.1252) loss: 0.8866 (0.8836) time: 0.1625 data: 0.0764 max mem: 8233 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.1170 (0.1252) loss: 0.8875 (0.8836) time: 0.1549 data: 0.0741 max mem: 8233 +Train: [53] Total time: 0:17:09 (0.1647 s / it) +Averaged stats: lr: 0.000059 grad: 0.1170 (0.1252) loss: 0.8875 (0.8836) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:06:44 loss: 0.8993 (0.8993) time: 6.5253 data: 6.4997 max mem: 8233 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8917 (0.8930) time: 0.1048 data: 0.0842 max mem: 8233 +Eval (hcp-train-subset): [53] Total time: 0:00:15 (0.2499 s / it) +Averaged stats (hcp-train-subset): loss: 0.8917 (0.8930) +Eval (hcp-val): [53] [ 0/62] eta: 0:06:48 loss: 0.8868 (0.8868) time: 6.5840 data: 6.5342 max mem: 8233 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8900 (0.8917) time: 0.1041 data: 0.0834 max mem: 8233 +Eval (hcp-val): [53] Total time: 0:00:15 (0.2431 s / it) +Averaged stats (hcp-val): loss: 0.8900 (0.8917) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 11:09:44 lr: 0.000059 grad: 0.1871 (0.1871) loss: 0.9358 (0.9358) time: 6.4296 data: 6.2786 max mem: 8233 +Train: [54] [ 100/6250] eta: 0:23:08 lr: 0.000059 grad: 0.1235 (0.1392) loss: 0.8807 (0.8851) time: 0.1654 data: 0.0575 max mem: 8233 +Train: [54] [ 200/6250] eta: 0:20:10 lr: 0.000059 grad: 0.1225 (0.1329) loss: 0.8855 (0.8836) time: 0.1692 data: 0.0725 max mem: 8233 +Train: [54] [ 300/6250] eta: 0:18:45 lr: 0.000059 grad: 0.1130 (0.1301) loss: 0.8841 (0.8832) time: 0.1296 data: 0.0391 max mem: 8233 +Train: [54] [ 400/6250] eta: 0:17:54 lr: 0.000059 grad: 0.1197 (0.1287) loss: 0.8814 (0.8830) time: 0.1685 data: 0.0606 max mem: 8233 +Train: [54] [ 500/6250] eta: 0:17:13 lr: 0.000059 grad: 0.1262 (0.1275) loss: 0.8781 (0.8831) time: 0.1960 data: 0.1124 max mem: 8233 +Train: [54] [ 600/6250] eta: 0:16:33 lr: 0.000059 grad: 0.1163 (0.1269) loss: 0.8822 (0.8829) time: 0.1512 data: 0.0517 max mem: 8233 +Train: [54] [ 700/6250] eta: 0:16:02 lr: 0.000059 grad: 0.1181 (0.1266) loss: 0.8879 (0.8830) time: 0.1302 data: 0.0317 max mem: 8233 +Train: [54] [ 800/6250] eta: 0:15:38 lr: 0.000059 grad: 0.1216 (0.1271) loss: 0.8782 (0.8828) time: 0.1899 data: 0.1063 max mem: 8233 +Train: [54] [ 900/6250] eta: 0:15:15 lr: 0.000059 grad: 0.1243 (0.1267) loss: 0.8758 (0.8827) time: 0.1696 data: 0.0845 max mem: 8233 +Train: [54] [1000/6250] eta: 0:14:52 lr: 0.000059 grad: 0.1183 (0.1263) loss: 0.8766 (0.8826) time: 0.1701 data: 0.0905 max mem: 8233 +Train: [54] [1100/6250] eta: 0:14:31 lr: 0.000059 grad: 0.1155 (0.1261) loss: 0.8832 (0.8825) time: 0.1469 data: 0.0661 max mem: 8233 +Train: [54] [1200/6250] eta: 0:14:10 lr: 0.000059 grad: 0.1189 (0.1260) loss: 0.8864 (0.8825) time: 0.1734 data: 0.0833 max mem: 8233 +Train: [54] [1300/6250] eta: 0:13:42 lr: 0.000059 grad: 0.1276 (0.1258) loss: 0.8778 (0.8824) time: 0.1298 data: 0.0324 max mem: 8233 +Train: [54] [1400/6250] eta: 0:13:20 lr: 0.000059 grad: 0.1182 (0.1258) loss: 0.8773 (0.8823) time: 0.1203 data: 0.0333 max mem: 8233 +Train: [54] [1500/6250] eta: 0:13:03 lr: 0.000059 grad: 0.1151 (0.1255) loss: 0.8823 (0.8824) time: 0.1687 data: 0.0856 max mem: 8233 +Train: [54] [1600/6250] eta: 0:12:46 lr: 0.000059 grad: 0.1251 (0.1252) loss: 0.8832 (0.8825) time: 0.1662 data: 0.0830 max mem: 8233 +Train: [54] [1700/6250] eta: 0:12:29 lr: 0.000059 grad: 0.1125 (0.1249) loss: 0.8892 (0.8826) time: 0.1528 data: 0.0821 max mem: 8233 +Train: [54] [1800/6250] eta: 0:12:16 lr: 0.000059 grad: 0.1139 (0.1248) loss: 0.8802 (0.8827) time: 0.1792 data: 0.0925 max mem: 8233 +Train: [54] [1900/6250] eta: 0:12:03 lr: 0.000059 grad: 0.1199 (0.1247) loss: 0.8855 (0.8829) time: 0.1776 data: 0.0946 max mem: 8233 +Train: [54] [2000/6250] eta: 0:11:46 lr: 0.000059 grad: 0.1239 (0.1247) loss: 0.8819 (0.8831) time: 0.1611 data: 0.0853 max mem: 8233 +Train: [54] [2100/6250] eta: 0:11:29 lr: 0.000059 grad: 0.1173 (0.1245) loss: 0.8821 (0.8832) time: 0.1413 data: 0.0545 max mem: 8233 +Train: [54] [2200/6250] eta: 0:11:14 lr: 0.000059 grad: 0.1170 (0.1244) loss: 0.8855 (0.8833) time: 0.1779 data: 0.1063 max mem: 8233 +Train: [54] [2300/6250] eta: 0:10:56 lr: 0.000059 grad: 0.1212 (0.1244) loss: 0.8865 (0.8833) time: 0.1533 data: 0.0659 max mem: 8233 +Train: [54] [2400/6250] eta: 0:10:40 lr: 0.000059 grad: 0.1167 (0.1248) loss: 0.8876 (0.8834) time: 0.1445 data: 0.0603 max mem: 8233 +Train: [54] [2500/6250] eta: 0:10:23 lr: 0.000059 grad: 0.1131 (0.1248) loss: 0.8876 (0.8835) time: 0.1573 data: 0.0759 max mem: 8233 +Train: [54] [2600/6250] eta: 0:10:10 lr: 0.000059 grad: 0.1221 (0.1247) loss: 0.8817 (0.8836) time: 0.1618 data: 0.0525 max mem: 8233 +Train: [54] [2700/6250] eta: 0:09:55 lr: 0.000059 grad: 0.1269 (0.1249) loss: 0.8822 (0.8837) time: 0.1805 data: 0.1066 max mem: 8233 +Train: [54] [2800/6250] eta: 0:09:37 lr: 0.000058 grad: 0.1140 (0.1248) loss: 0.8875 (0.8838) time: 0.1746 data: 0.0960 max mem: 8233 +Train: [54] [2900/6250] eta: 0:09:20 lr: 0.000058 grad: 0.1155 (0.1248) loss: 0.8873 (0.8839) time: 0.1425 data: 0.0625 max mem: 8233 +Train: [54] [3000/6250] eta: 0:09:02 lr: 0.000058 grad: 0.1156 (0.1247) loss: 0.8825 (0.8839) time: 0.1233 data: 0.0295 max mem: 8233 +Train: [54] [3100/6250] eta: 0:08:45 lr: 0.000058 grad: 0.1187 (0.1248) loss: 0.8859 (0.8840) time: 0.1821 data: 0.1114 max mem: 8233 +Train: [54] [3200/6250] eta: 0:08:27 lr: 0.000058 grad: 0.1147 (0.1248) loss: 0.8934 (0.8841) time: 0.1527 data: 0.0685 max mem: 8233 +Train: [54] [3300/6250] eta: 0:08:09 lr: 0.000058 grad: 0.1285 (0.1249) loss: 0.8827 (0.8841) time: 0.1812 data: 0.1077 max mem: 8233 +Train: [54] [3400/6250] eta: 0:07:52 lr: 0.000058 grad: 0.1142 (0.1249) loss: 0.8845 (0.8841) time: 0.1700 data: 0.0963 max mem: 8233 +Train: [54] [3500/6250] eta: 0:07:35 lr: 0.000058 grad: 0.1139 (0.1249) loss: 0.8829 (0.8841) time: 0.1483 data: 0.0678 max mem: 8233 +Train: [54] [3600/6250] eta: 0:07:18 lr: 0.000058 grad: 0.1082 (0.1248) loss: 0.8907 (0.8842) time: 0.2016 data: 0.1394 max mem: 8233 +Train: [54] [3700/6250] eta: 0:07:01 lr: 0.000058 grad: 0.1249 (0.1249) loss: 0.8856 (0.8843) time: 0.1522 data: 0.0840 max mem: 8233 +Train: [54] [3800/6250] eta: 0:06:45 lr: 0.000058 grad: 0.1210 (0.1249) loss: 0.8814 (0.8844) time: 0.1710 data: 0.0797 max mem: 8233 +Train: [54] [3900/6250] eta: 0:06:29 lr: 0.000058 grad: 0.1205 (0.1249) loss: 0.8879 (0.8844) time: 0.1802 data: 0.0972 max mem: 8233 +Train: [54] [4000/6250] eta: 0:06:12 lr: 0.000058 grad: 0.1170 (0.1249) loss: 0.8915 (0.8845) time: 0.1815 data: 0.0982 max mem: 8233 +Train: [54] [4100/6250] eta: 0:05:56 lr: 0.000058 grad: 0.1180 (0.1248) loss: 0.8798 (0.8845) time: 0.2065 data: 0.1134 max mem: 8233 +Train: [54] [4200/6250] eta: 0:05:39 lr: 0.000058 grad: 0.1233 (0.1249) loss: 0.8835 (0.8844) time: 0.1429 data: 0.0640 max mem: 8233 +Train: [54] [4300/6250] eta: 0:05:22 lr: 0.000058 grad: 0.1168 (0.1248) loss: 0.8864 (0.8845) time: 0.1552 data: 0.0775 max mem: 8233 +Train: [54] [4400/6250] eta: 0:05:05 lr: 0.000058 grad: 0.1114 (0.1247) loss: 0.8851 (0.8845) time: 0.1470 data: 0.0521 max mem: 8233 +Train: [54] [4500/6250] eta: 0:04:49 lr: 0.000058 grad: 0.1275 (0.1247) loss: 0.8843 (0.8845) time: 0.1315 data: 0.0521 max mem: 8233 +Train: [54] [4600/6250] eta: 0:04:32 lr: 0.000058 grad: 0.1222 (0.1248) loss: 0.8837 (0.8845) time: 0.1505 data: 0.0714 max mem: 8233 +Train: [54] [4700/6250] eta: 0:04:15 lr: 0.000058 grad: 0.1146 (0.1248) loss: 0.8854 (0.8845) time: 0.1481 data: 0.0720 max mem: 8233 +Train: [54] [4800/6250] eta: 0:03:59 lr: 0.000058 grad: 0.1200 (0.1248) loss: 0.8815 (0.8845) time: 0.1612 data: 0.0686 max mem: 8233 +Train: [54] [4900/6250] eta: 0:03:42 lr: 0.000058 grad: 0.1190 (0.1248) loss: 0.8842 (0.8845) time: 0.1637 data: 0.0829 max mem: 8233 +Train: [54] [5000/6250] eta: 0:03:25 lr: 0.000058 grad: 0.1332 (0.1249) loss: 0.8798 (0.8845) time: 0.1665 data: 0.0847 max mem: 8233 +Train: [54] [5100/6250] eta: 0:03:09 lr: 0.000058 grad: 0.1264 (0.1249) loss: 0.8860 (0.8844) time: 0.1535 data: 0.0791 max mem: 8233 +Train: [54] [5200/6250] eta: 0:02:52 lr: 0.000058 grad: 0.1255 (0.1251) loss: 0.8840 (0.8844) time: 0.1395 data: 0.0607 max mem: 8233 +Train: [54] [5300/6250] eta: 0:02:36 lr: 0.000058 grad: 0.1242 (0.1251) loss: 0.8852 (0.8844) time: 0.1508 data: 0.0640 max mem: 8233 +Train: [54] [5400/6250] eta: 0:02:19 lr: 0.000058 grad: 0.1229 (0.1251) loss: 0.8863 (0.8844) time: 0.1568 data: 0.0837 max mem: 8233 +Train: [54] [5500/6250] eta: 0:02:03 lr: 0.000058 grad: 0.1305 (0.1251) loss: 0.8855 (0.8844) time: 0.1736 data: 0.0900 max mem: 8233 +Train: [54] [5600/6250] eta: 0:01:46 lr: 0.000058 grad: 0.1245 (0.1252) loss: 0.8853 (0.8845) time: 0.1443 data: 0.0400 max mem: 8233 +Train: [54] [5700/6250] eta: 0:01:30 lr: 0.000058 grad: 0.1252 (0.1253) loss: 0.8823 (0.8844) time: 0.1382 data: 0.0535 max mem: 8233 +Train: [54] [5800/6250] eta: 0:01:13 lr: 0.000057 grad: 0.1171 (0.1253) loss: 0.8822 (0.8844) time: 0.1552 data: 0.0732 max mem: 8233 +Train: [54] [5900/6250] eta: 0:00:57 lr: 0.000057 grad: 0.1284 (0.1254) loss: 0.8808 (0.8844) time: 0.1644 data: 0.0894 max mem: 8233 +Train: [54] [6000/6250] eta: 0:00:40 lr: 0.000057 grad: 0.1279 (0.1254) loss: 0.8823 (0.8844) time: 0.1676 data: 0.0974 max mem: 8233 +Train: [54] [6100/6250] eta: 0:00:24 lr: 0.000057 grad: 0.1246 (0.1255) loss: 0.8793 (0.8843) time: 0.1741 data: 0.0980 max mem: 8233 +Train: [54] [6200/6250] eta: 0:00:08 lr: 0.000057 grad: 0.1262 (0.1256) loss: 0.8866 (0.8843) time: 0.1569 data: 0.0899 max mem: 8233 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.1236 (0.1256) loss: 0.8818 (0.8843) time: 0.1369 data: 0.0597 max mem: 8233 +Train: [54] Total time: 0:17:12 (0.1652 s / it) +Averaged stats: lr: 0.000057 grad: 0.1236 (0.1256) loss: 0.8818 (0.8843) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:05:35 loss: 0.9010 (0.9010) time: 5.4144 data: 5.3885 max mem: 8233 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8915 (0.8919) time: 0.0935 data: 0.0729 max mem: 8233 +Eval (hcp-train-subset): [54] Total time: 0:00:15 (0.2428 s / it) +Averaged stats (hcp-train-subset): loss: 0.8915 (0.8919) +Making plots (hcp-train-subset): example=12 +Eval (hcp-val): [54] [ 0/62] eta: 0:03:56 loss: 0.8867 (0.8867) time: 3.8224 data: 3.7483 max mem: 8233 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8907 (0.8913) time: 0.1345 data: 0.1133 max mem: 8233 +Eval (hcp-val): [54] Total time: 0:00:13 (0.2235 s / it) +Averaged stats (hcp-val): loss: 0.8907 (0.8913) +Making plots (hcp-val): example=36 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 11:50:13 lr: 0.000057 grad: 0.1423 (0.1423) loss: 0.9234 (0.9234) time: 6.8181 data: 6.6638 max mem: 8233 +Train: [55] [ 100/6250] eta: 0:22:40 lr: 0.000057 grad: 0.1128 (0.1272) loss: 0.8907 (0.8943) time: 0.1610 data: 0.0433 max mem: 8233 +Train: [55] [ 200/6250] eta: 0:19:46 lr: 0.000057 grad: 0.1152 (0.1273) loss: 0.8932 (0.8908) time: 0.1715 data: 0.0650 max mem: 8233 +Train: [55] [ 300/6250] eta: 0:18:11 lr: 0.000057 grad: 0.1113 (0.1251) loss: 0.8873 (0.8889) time: 0.1434 data: 0.0485 max mem: 8233 +Train: [55] [ 400/6250] eta: 0:17:21 lr: 0.000057 grad: 0.1139 (0.1238) loss: 0.8896 (0.8879) time: 0.1699 data: 0.0896 max mem: 8233 +Train: [55] [ 500/6250] eta: 0:16:36 lr: 0.000057 grad: 0.1189 (0.1231) loss: 0.8891 (0.8874) time: 0.1724 data: 0.0877 max mem: 8233 +Train: [55] [ 600/6250] eta: 0:15:58 lr: 0.000057 grad: 0.1142 (0.1225) loss: 0.8869 (0.8876) time: 0.1507 data: 0.0593 max mem: 8233 +Train: [55] [ 700/6250] eta: 0:15:34 lr: 0.000057 grad: 0.1229 (0.1226) loss: 0.8835 (0.8874) time: 0.1807 data: 0.0950 max mem: 8233 +Train: [55] [ 800/6250] eta: 0:15:10 lr: 0.000057 grad: 0.1229 (0.1230) loss: 0.8861 (0.8869) time: 0.1815 data: 0.0925 max mem: 8233 +Train: [55] [ 900/6250] eta: 0:14:50 lr: 0.000057 grad: 0.1147 (0.1230) loss: 0.8901 (0.8868) time: 0.1338 data: 0.0503 max mem: 8233 +Train: [55] [1000/6250] eta: 0:14:30 lr: 0.000057 grad: 0.1126 (0.1236) loss: 0.8880 (0.8867) time: 0.1873 data: 0.1171 max mem: 8233 +Train: [55] [1100/6250] eta: 0:14:03 lr: 0.000057 grad: 0.1182 (0.1237) loss: 0.8915 (0.8867) time: 0.1472 data: 0.0612 max mem: 8233 +Train: [55] [1200/6250] eta: 0:13:41 lr: 0.000057 grad: 0.1180 (0.1237) loss: 0.8846 (0.8866) time: 0.1637 data: 0.0831 max mem: 8233 +Train: [55] [1300/6250] eta: 0:13:20 lr: 0.000057 grad: 0.1222 (0.1237) loss: 0.8871 (0.8864) time: 0.1370 data: 0.0507 max mem: 8233 +Train: [55] [1400/6250] eta: 0:13:02 lr: 0.000057 grad: 0.1153 (0.1235) loss: 0.8893 (0.8863) time: 0.1509 data: 0.0711 max mem: 8233 +Train: [55] [1500/6250] eta: 0:12:52 lr: 0.000057 grad: 0.1175 (0.1234) loss: 0.8833 (0.8863) time: 0.1588 data: 0.0754 max mem: 8233 +Train: [55] [1600/6250] eta: 0:12:33 lr: 0.000057 grad: 0.1141 (0.1234) loss: 0.8884 (0.8863) time: 0.1447 data: 0.0639 max mem: 8233 +Train: [55] [1700/6250] eta: 0:12:17 lr: 0.000057 grad: 0.1263 (0.1238) loss: 0.8889 (0.8864) time: 0.1722 data: 0.1100 max mem: 8233 +Train: [55] [1800/6250] eta: 0:12:03 lr: 0.000057 grad: 0.1125 (0.1236) loss: 0.8902 (0.8864) time: 0.1598 data: 0.0789 max mem: 8233 +Train: [55] [1900/6250] eta: 0:11:48 lr: 0.000057 grad: 0.1229 (0.1238) loss: 0.8826 (0.8864) time: 0.1619 data: 0.0837 max mem: 8233 +Train: [55] [2000/6250] eta: 0:11:31 lr: 0.000057 grad: 0.1132 (0.1235) loss: 0.8881 (0.8865) time: 0.1519 data: 0.0853 max mem: 8233 +Train: [55] [2100/6250] eta: 0:11:14 lr: 0.000057 grad: 0.1184 (0.1234) loss: 0.8866 (0.8865) time: 0.1521 data: 0.0669 max mem: 8233 +Train: [55] [2200/6250] eta: 0:10:56 lr: 0.000057 grad: 0.1190 (0.1234) loss: 0.8813 (0.8864) time: 0.1563 data: 0.0749 max mem: 8233 +Train: [55] [2300/6250] eta: 0:10:38 lr: 0.000057 grad: 0.1187 (0.1234) loss: 0.8847 (0.8864) time: 0.1101 data: 0.0158 max mem: 8233 +Train: [55] [2400/6250] eta: 0:10:19 lr: 0.000057 grad: 0.1192 (0.1235) loss: 0.8897 (0.8864) time: 0.1398 data: 0.0486 max mem: 8233 +Train: [55] [2500/6250] eta: 0:10:01 lr: 0.000057 grad: 0.1237 (0.1236) loss: 0.8849 (0.8863) time: 0.1429 data: 0.0589 max mem: 8233 +Train: [55] [2600/6250] eta: 0:09:43 lr: 0.000056 grad: 0.1167 (0.1237) loss: 0.8851 (0.8863) time: 0.1441 data: 0.0574 max mem: 8233 +Train: [55] [2700/6250] eta: 0:09:25 lr: 0.000056 grad: 0.1230 (0.1236) loss: 0.8837 (0.8863) time: 0.1616 data: 0.0760 max mem: 8233 +Train: [55] [2800/6250] eta: 0:09:08 lr: 0.000056 grad: 0.1188 (0.1238) loss: 0.8858 (0.8863) time: 0.1468 data: 0.0676 max mem: 8233 +Train: [55] [2900/6250] eta: 0:08:51 lr: 0.000056 grad: 0.1192 (0.1239) loss: 0.8850 (0.8862) time: 0.1391 data: 0.0615 max mem: 8233 +Train: [55] [3000/6250] eta: 0:08:35 lr: 0.000056 grad: 0.1210 (0.1240) loss: 0.8866 (0.8860) time: 0.1838 data: 0.1065 max mem: 8233 +Train: [55] [3100/6250] eta: 0:08:20 lr: 0.000056 grad: 0.1171 (0.1241) loss: 0.8799 (0.8859) time: 0.1521 data: 0.0797 max mem: 8233 +Train: [55] [3200/6250] eta: 0:08:05 lr: 0.000056 grad: 0.1302 (0.1244) loss: 0.8827 (0.8858) time: 0.1510 data: 0.0668 max mem: 8233 +Train: [55] [3300/6250] eta: 0:07:50 lr: 0.000056 grad: 0.1214 (0.1244) loss: 0.8755 (0.8856) time: 0.1760 data: 0.0976 max mem: 8233 +Train: [55] [3400/6250] eta: 0:07:34 lr: 0.000056 grad: 0.1217 (0.1247) loss: 0.8862 (0.8856) time: 0.1848 data: 0.1151 max mem: 8233 +Train: [55] [3500/6250] eta: 0:07:20 lr: 0.000056 grad: 0.1202 (0.1249) loss: 0.8874 (0.8856) time: 0.2023 data: 0.1122 max mem: 8233 +Train: [55] [3600/6250] eta: 0:07:04 lr: 0.000056 grad: 0.1225 (0.1251) loss: 0.8864 (0.8856) time: 0.1784 data: 0.0967 max mem: 8233 +Train: [55] [3700/6250] eta: 0:06:48 lr: 0.000056 grad: 0.1305 (0.1252) loss: 0.8855 (0.8855) time: 0.1423 data: 0.0749 max mem: 8233 +Train: [55] [3800/6250] eta: 0:06:33 lr: 0.000056 grad: 0.1296 (0.1252) loss: 0.8872 (0.8855) time: 0.1677 data: 0.0835 max mem: 8233 +Train: [55] [3900/6250] eta: 0:06:17 lr: 0.000056 grad: 0.1268 (0.1252) loss: 0.8836 (0.8855) time: 0.1671 data: 0.0718 max mem: 8233 +Train: [55] [4000/6250] eta: 0:06:02 lr: 0.000056 grad: 0.1176 (0.1253) loss: 0.8915 (0.8856) time: 0.1412 data: 0.0603 max mem: 8233 +Train: [55] [4100/6250] eta: 0:05:46 lr: 0.000056 grad: 0.1195 (0.1253) loss: 0.8887 (0.8856) time: 0.1458 data: 0.0693 max mem: 8233 +Train: [55] [4200/6250] eta: 0:05:30 lr: 0.000056 grad: 0.1189 (0.1253) loss: 0.8885 (0.8856) time: 0.1534 data: 0.0760 max mem: 8233 +Train: [55] [4300/6250] eta: 0:05:14 lr: 0.000056 grad: 0.1154 (0.1253) loss: 0.8865 (0.8856) time: 0.1673 data: 0.0848 max mem: 8233 +Train: [55] [4400/6250] eta: 0:04:58 lr: 0.000056 grad: 0.1187 (0.1253) loss: 0.8852 (0.8856) time: 0.1588 data: 0.0770 max mem: 8233 +Train: [55] [4500/6250] eta: 0:04:42 lr: 0.000056 grad: 0.1187 (0.1254) loss: 0.8849 (0.8857) time: 0.1500 data: 0.0654 max mem: 8233 +Train: [55] [4600/6250] eta: 0:04:26 lr: 0.000056 grad: 0.1246 (0.1255) loss: 0.8866 (0.8857) time: 0.1654 data: 0.0869 max mem: 8233 +Train: [55] [4700/6250] eta: 0:04:09 lr: 0.000056 grad: 0.1180 (0.1256) loss: 0.8862 (0.8857) time: 0.1504 data: 0.0768 max mem: 8233 +Train: [55] [4800/6250] eta: 0:03:53 lr: 0.000056 grad: 0.1200 (0.1256) loss: 0.8869 (0.8858) time: 0.1517 data: 0.0708 max mem: 8233 +Train: [55] [4900/6250] eta: 0:03:37 lr: 0.000056 grad: 0.1169 (0.1255) loss: 0.8867 (0.8858) time: 0.1417 data: 0.0565 max mem: 8233 +Train: [55] [5000/6250] eta: 0:03:20 lr: 0.000056 grad: 0.1202 (0.1255) loss: 0.8850 (0.8858) time: 0.1509 data: 0.0636 max mem: 8233 +Train: [55] [5100/6250] eta: 0:03:05 lr: 0.000056 grad: 0.1188 (0.1254) loss: 0.8893 (0.8858) time: 0.1492 data: 0.0675 max mem: 8233 +Train: [55] [5200/6250] eta: 0:02:48 lr: 0.000056 grad: 0.1134 (0.1254) loss: 0.8846 (0.8859) time: 0.1442 data: 0.0631 max mem: 8233 +Train: [55] [5300/6250] eta: 0:02:32 lr: 0.000056 grad: 0.1197 (0.1253) loss: 0.8887 (0.8859) time: 0.1626 data: 0.0709 max mem: 8233 +Train: [55] [5400/6250] eta: 0:02:17 lr: 0.000056 grad: 0.1167 (0.1253) loss: 0.8860 (0.8859) time: 0.2823 data: 0.2135 max mem: 8233 +Train: [55] [5500/6250] eta: 0:02:00 lr: 0.000056 grad: 0.1170 (0.1252) loss: 0.8896 (0.8859) time: 0.1544 data: 0.0677 max mem: 8233 +Train: [55] [5600/6250] eta: 0:01:44 lr: 0.000055 grad: 0.1226 (0.1252) loss: 0.8845 (0.8859) time: 0.1625 data: 0.0797 max mem: 8233 +Train: [55] [5700/6250] eta: 0:01:28 lr: 0.000055 grad: 0.1188 (0.1252) loss: 0.8849 (0.8859) time: 0.1396 data: 0.0546 max mem: 8233 +Train: [55] [5800/6250] eta: 0:01:12 lr: 0.000055 grad: 0.1195 (0.1252) loss: 0.8827 (0.8858) time: 0.1368 data: 0.0476 max mem: 8233 +Train: [55] [5900/6250] eta: 0:00:56 lr: 0.000055 grad: 0.1215 (0.1252) loss: 0.8866 (0.8858) time: 0.2015 data: 0.1376 max mem: 8233 +Train: [55] [6000/6250] eta: 0:00:40 lr: 0.000055 grad: 0.1172 (0.1253) loss: 0.8832 (0.8858) time: 0.1568 data: 0.0787 max mem: 8233 +Train: [55] [6100/6250] eta: 0:00:24 lr: 0.000055 grad: 0.1128 (0.1253) loss: 0.8878 (0.8858) time: 0.1620 data: 0.0845 max mem: 8233 +Train: [55] [6200/6250] eta: 0:00:08 lr: 0.000055 grad: 0.1372 (0.1254) loss: 0.8796 (0.8857) time: 0.1847 data: 0.1077 max mem: 8233 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.1211 (0.1254) loss: 0.8799 (0.8857) time: 0.1669 data: 0.0742 max mem: 8233 +Train: [55] Total time: 0:16:48 (0.1614 s / it) +Averaged stats: lr: 0.000055 grad: 0.1211 (0.1254) loss: 0.8799 (0.8857) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:06:30 loss: 0.9017 (0.9017) time: 6.3054 data: 6.2794 max mem: 8233 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8909 (0.8923) time: 0.1817 data: 0.1602 max mem: 8233 +Eval (hcp-train-subset): [55] Total time: 0:00:16 (0.2623 s / it) +Averaged stats (hcp-train-subset): loss: 0.8909 (0.8923) +Eval (hcp-val): [55] [ 0/62] eta: 0:06:30 loss: 0.8863 (0.8863) time: 6.3063 data: 6.2703 max mem: 8233 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8878 (0.8899) time: 0.1646 data: 0.1423 max mem: 8233 +Eval (hcp-val): [55] Total time: 0:00:15 (0.2478 s / it) +Averaged stats (hcp-val): loss: 0.8878 (0.8899) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 10:47:54 lr: 0.000055 grad: 0.0950 (0.0950) loss: 0.9362 (0.9362) time: 6.2200 data: 6.0167 max mem: 8233 +Train: [56] [ 100/6250] eta: 0:24:30 lr: 0.000055 grad: 0.1148 (0.1231) loss: 0.8898 (0.8935) time: 0.1997 data: 0.0763 max mem: 8233 +Train: [56] [ 200/6250] eta: 0:21:20 lr: 0.000055 grad: 0.1209 (0.1238) loss: 0.8849 (0.8925) time: 0.1761 data: 0.0758 max mem: 8233 +Train: [56] [ 300/6250] eta: 0:19:37 lr: 0.000055 grad: 0.1161 (0.1251) loss: 0.8899 (0.8907) time: 0.1896 data: 0.0858 max mem: 8233 +Train: [56] [ 400/6250] eta: 0:18:41 lr: 0.000055 grad: 0.1227 (0.1254) loss: 0.8813 (0.8892) time: 0.1902 data: 0.0928 max mem: 8233 +Train: [56] [ 500/6250] eta: 0:17:57 lr: 0.000055 grad: 0.1178 (0.1253) loss: 0.8834 (0.8880) time: 0.1639 data: 0.0777 max mem: 8233 +Train: [56] [ 600/6250] eta: 0:17:22 lr: 0.000055 grad: 0.1327 (0.1262) loss: 0.8810 (0.8871) time: 0.1419 data: 0.0496 max mem: 8233 +Train: [56] [ 700/6250] eta: 0:16:54 lr: 0.000055 grad: 0.1258 (0.1268) loss: 0.8788 (0.8861) time: 0.1701 data: 0.0868 max mem: 8233 +Train: [56] [ 800/6250] eta: 0:16:30 lr: 0.000055 grad: 0.1295 (0.1276) loss: 0.8791 (0.8854) time: 0.1566 data: 0.0737 max mem: 8233 +Train: [56] [ 900/6250] eta: 0:16:01 lr: 0.000055 grad: 0.1155 (0.1274) loss: 0.8775 (0.8847) time: 0.1658 data: 0.0729 max mem: 8233 +Train: [56] [1000/6250] eta: 0:15:33 lr: 0.000055 grad: 0.1182 (0.1271) loss: 0.8756 (0.8843) time: 0.1382 data: 0.0641 max mem: 8233 +Train: [56] [1100/6250] eta: 0:15:09 lr: 0.000055 grad: 0.1281 (0.1272) loss: 0.8798 (0.8842) time: 0.1522 data: 0.0638 max mem: 8233 +Train: [56] [1200/6250] eta: 0:14:45 lr: 0.000055 grad: 0.1239 (0.1273) loss: 0.8833 (0.8839) time: 0.1161 data: 0.0313 max mem: 8233 +Train: [56] [1300/6250] eta: 0:14:22 lr: 0.000055 grad: 0.1207 (0.1272) loss: 0.8851 (0.8840) time: 0.1764 data: 0.0997 max mem: 8233 +Train: [56] [1400/6250] eta: 0:13:57 lr: 0.000055 grad: 0.1216 (0.1274) loss: 0.8822 (0.8839) time: 0.1492 data: 0.0634 max mem: 8233 +Train: [56] [1500/6250] eta: 0:13:40 lr: 0.000055 grad: 0.1181 (0.1274) loss: 0.8817 (0.8839) time: 0.1557 data: 0.0746 max mem: 8233 +Train: [56] [1600/6250] eta: 0:13:18 lr: 0.000055 grad: 0.1203 (0.1275) loss: 0.8865 (0.8841) time: 0.1664 data: 0.0827 max mem: 8233 +Train: [56] [1700/6250] eta: 0:12:55 lr: 0.000055 grad: 0.1193 (0.1275) loss: 0.8867 (0.8841) time: 0.1253 data: 0.0511 max mem: 8233 +Train: [56] [1800/6250] eta: 0:12:37 lr: 0.000055 grad: 0.1273 (0.1275) loss: 0.8833 (0.8841) time: 0.1417 data: 0.0586 max mem: 8233 +Train: [56] [1900/6250] eta: 0:12:20 lr: 0.000055 grad: 0.1242 (0.1275) loss: 0.8813 (0.8840) time: 0.1686 data: 0.0753 max mem: 8233 +Train: [56] [2000/6250] eta: 0:12:01 lr: 0.000055 grad: 0.1264 (0.1276) loss: 0.8863 (0.8841) time: 0.1662 data: 0.0818 max mem: 8233 +Train: [56] [2100/6250] eta: 0:11:42 lr: 0.000055 grad: 0.1215 (0.1275) loss: 0.8812 (0.8841) time: 0.1749 data: 0.0903 max mem: 8233 +Train: [56] [2200/6250] eta: 0:11:21 lr: 0.000055 grad: 0.1239 (0.1276) loss: 0.8818 (0.8840) time: 0.1334 data: 0.0502 max mem: 8233 +Train: [56] [2300/6250] eta: 0:11:02 lr: 0.000055 grad: 0.1253 (0.1277) loss: 0.8840 (0.8839) time: 0.1380 data: 0.0474 max mem: 8233 +Train: [56] [2400/6250] eta: 0:10:43 lr: 0.000054 grad: 0.1211 (0.1277) loss: 0.8835 (0.8840) time: 0.1684 data: 0.0820 max mem: 8233 +Train: [56] [2500/6250] eta: 0:10:25 lr: 0.000054 grad: 0.1265 (0.1278) loss: 0.8818 (0.8839) time: 0.1561 data: 0.0760 max mem: 8233 +Train: [56] [2600/6250] eta: 0:10:06 lr: 0.000054 grad: 0.1226 (0.1279) loss: 0.8859 (0.8839) time: 0.1588 data: 0.0808 max mem: 8233 +Train: [56] [2700/6250] eta: 0:09:49 lr: 0.000054 grad: 0.1158 (0.1278) loss: 0.8882 (0.8840) time: 0.1625 data: 0.0912 max mem: 8233 +Train: [56] [2800/6250] eta: 0:09:31 lr: 0.000054 grad: 0.1235 (0.1277) loss: 0.8837 (0.8840) time: 0.1585 data: 0.0706 max mem: 8233 +Train: [56] [2900/6250] eta: 0:09:14 lr: 0.000054 grad: 0.1202 (0.1276) loss: 0.8891 (0.8841) time: 0.1704 data: 0.0856 max mem: 8233 +Train: [56] [3000/6250] eta: 0:08:56 lr: 0.000054 grad: 0.1178 (0.1277) loss: 0.8879 (0.8842) time: 0.1623 data: 0.0699 max mem: 8233 +Train: [56] [3100/6250] eta: 0:08:39 lr: 0.000054 grad: 0.1240 (0.1276) loss: 0.8878 (0.8842) time: 0.1216 data: 0.0028 max mem: 8233 +Train: [56] [3200/6250] eta: 0:08:22 lr: 0.000054 grad: 0.1213 (0.1275) loss: 0.8895 (0.8842) time: 0.1499 data: 0.0662 max mem: 8233 +Train: [56] [3300/6250] eta: 0:08:05 lr: 0.000054 grad: 0.1120 (0.1274) loss: 0.8881 (0.8842) time: 0.1526 data: 0.0619 max mem: 8233 +Train: [56] [3400/6250] eta: 0:07:47 lr: 0.000054 grad: 0.1150 (0.1273) loss: 0.8895 (0.8842) time: 0.1284 data: 0.0414 max mem: 8233 +Train: [56] [3500/6250] eta: 0:07:30 lr: 0.000054 grad: 0.1244 (0.1274) loss: 0.8866 (0.8842) time: 0.1462 data: 0.0461 max mem: 8233 +Train: [56] [3600/6250] eta: 0:07:15 lr: 0.000054 grad: 0.1183 (0.1273) loss: 0.8831 (0.8842) time: 0.1639 data: 0.0808 max mem: 8233 +Train: [56] [3700/6250] eta: 0:06:59 lr: 0.000054 grad: 0.1275 (0.1272) loss: 0.8831 (0.8842) time: 0.1630 data: 0.0761 max mem: 8233 +Train: [56] [3800/6250] eta: 0:06:42 lr: 0.000054 grad: 0.1217 (0.1270) loss: 0.8891 (0.8843) time: 0.1588 data: 0.0843 max mem: 8233 +Train: [56] [3900/6250] eta: 0:06:26 lr: 0.000054 grad: 0.1168 (0.1270) loss: 0.8892 (0.8843) time: 0.1650 data: 0.0886 max mem: 8233 +Train: [56] [4000/6250] eta: 0:06:11 lr: 0.000054 grad: 0.1153 (0.1268) loss: 0.8879 (0.8843) time: 0.1835 data: 0.1020 max mem: 8233 +Train: [56] [4100/6250] eta: 0:05:54 lr: 0.000054 grad: 0.1220 (0.1268) loss: 0.8851 (0.8844) time: 0.1831 data: 0.1002 max mem: 8233 +Train: [56] [4200/6250] eta: 0:05:38 lr: 0.000054 grad: 0.1187 (0.1268) loss: 0.8864 (0.8843) time: 0.1748 data: 0.0846 max mem: 8233 +Train: [56] [4300/6250] eta: 0:05:21 lr: 0.000054 grad: 0.1266 (0.1268) loss: 0.8851 (0.8843) time: 0.1615 data: 0.0711 max mem: 8233 +Train: [56] [4400/6250] eta: 0:05:05 lr: 0.000054 grad: 0.1261 (0.1268) loss: 0.8836 (0.8844) time: 0.1633 data: 0.0757 max mem: 8233 +Train: [56] [4500/6250] eta: 0:04:48 lr: 0.000054 grad: 0.1244 (0.1268) loss: 0.8837 (0.8844) time: 0.1523 data: 0.0692 max mem: 8233 +Train: [56] [4600/6250] eta: 0:04:31 lr: 0.000054 grad: 0.1231 (0.1269) loss: 0.8844 (0.8845) time: 0.1249 data: 0.0450 max mem: 8233 +Train: [56] [4700/6250] eta: 0:04:14 lr: 0.000054 grad: 0.1234 (0.1268) loss: 0.8829 (0.8845) time: 0.1585 data: 0.0917 max mem: 8233 +Train: [56] [4800/6250] eta: 0:03:58 lr: 0.000054 grad: 0.1232 (0.1267) loss: 0.8862 (0.8845) time: 0.1098 data: 0.0280 max mem: 8233 +Train: [56] [4900/6250] eta: 0:03:41 lr: 0.000054 grad: 0.1234 (0.1268) loss: 0.8857 (0.8845) time: 0.1682 data: 0.0923 max mem: 8233 +Train: [56] [5000/6250] eta: 0:03:24 lr: 0.000054 grad: 0.1206 (0.1268) loss: 0.8864 (0.8846) time: 0.1443 data: 0.0612 max mem: 8233 +Train: [56] [5100/6250] eta: 0:03:08 lr: 0.000054 grad: 0.1200 (0.1268) loss: 0.8860 (0.8846) time: 0.1791 data: 0.1049 max mem: 8233 +Train: [56] [5200/6250] eta: 0:02:51 lr: 0.000054 grad: 0.1266 (0.1269) loss: 0.8844 (0.8847) time: 0.1485 data: 0.0727 max mem: 8233 +Train: [56] [5300/6250] eta: 0:02:35 lr: 0.000054 grad: 0.1259 (0.1269) loss: 0.8919 (0.8847) time: 0.1604 data: 0.0877 max mem: 8233 +Train: [56] [5400/6250] eta: 0:02:18 lr: 0.000054 grad: 0.1209 (0.1269) loss: 0.8829 (0.8848) time: 0.1592 data: 0.0773 max mem: 8233 +Train: [56] [5500/6250] eta: 0:02:02 lr: 0.000053 grad: 0.1246 (0.1270) loss: 0.8860 (0.8848) time: 0.1336 data: 0.0464 max mem: 8233 +Train: [56] [5600/6250] eta: 0:01:46 lr: 0.000053 grad: 0.1192 (0.1270) loss: 0.8828 (0.8848) time: 0.1702 data: 0.0820 max mem: 8233 +Train: [56] [5700/6250] eta: 0:01:29 lr: 0.000053 grad: 0.1249 (0.1270) loss: 0.8853 (0.8849) time: 0.1766 data: 0.0875 max mem: 8233 +Train: [56] [5800/6250] eta: 0:01:13 lr: 0.000053 grad: 0.1238 (0.1270) loss: 0.8902 (0.8849) time: 0.1622 data: 0.0815 max mem: 8233 +Train: [56] [5900/6250] eta: 0:00:57 lr: 0.000053 grad: 0.1217 (0.1269) loss: 0.8862 (0.8850) time: 0.1709 data: 0.0935 max mem: 8233 +Train: [56] [6000/6250] eta: 0:00:40 lr: 0.000053 grad: 0.1218 (0.1269) loss: 0.8890 (0.8850) time: 0.1662 data: 0.0962 max mem: 8233 +Train: [56] [6100/6250] eta: 0:00:24 lr: 0.000053 grad: 0.1207 (0.1269) loss: 0.8886 (0.8851) time: 0.2029 data: 0.1193 max mem: 8233 +Train: [56] [6200/6250] eta: 0:00:08 lr: 0.000053 grad: 0.1249 (0.1269) loss: 0.8885 (0.8851) time: 0.1795 data: 0.1124 max mem: 8233 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.1262 (0.1269) loss: 0.8782 (0.8851) time: 0.1893 data: 0.1062 max mem: 8233 +Train: [56] Total time: 0:17:08 (0.1646 s / it) +Averaged stats: lr: 0.000053 grad: 0.1262 (0.1269) loss: 0.8782 (0.8851) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:04:29 loss: 0.9026 (0.9026) time: 4.3485 data: 4.2571 max mem: 8233 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8913 (0.8924) time: 0.1257 data: 0.1052 max mem: 8233 +Eval (hcp-train-subset): [56] Total time: 0:00:14 (0.2345 s / it) +Averaged stats (hcp-train-subset): loss: 0.8913 (0.8924) +Eval (hcp-val): [56] [ 0/62] eta: 0:05:41 loss: 0.8904 (0.8904) time: 5.5110 data: 5.4846 max mem: 8233 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8892 (0.8904) time: 0.1353 data: 0.1146 max mem: 8233 +Eval (hcp-val): [56] Total time: 0:00:14 (0.2399 s / it) +Averaged stats (hcp-val): loss: 0.8892 (0.8904) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 10:42:15 lr: 0.000053 grad: 0.1133 (0.1133) loss: 0.8942 (0.8942) time: 6.1656 data: 6.0025 max mem: 8233 +Train: [57] [ 100/6250] eta: 0:22:25 lr: 0.000053 grad: 0.1221 (0.1299) loss: 0.8949 (0.8920) time: 0.1637 data: 0.0480 max mem: 8233 +Train: [57] [ 200/6250] eta: 0:19:23 lr: 0.000053 grad: 0.1144 (0.1251) loss: 0.8864 (0.8912) time: 0.1604 data: 0.0609 max mem: 8233 +Train: [57] [ 300/6250] eta: 0:18:21 lr: 0.000053 grad: 0.1148 (0.1232) loss: 0.8873 (0.8895) time: 0.1883 data: 0.0962 max mem: 8233 +Train: [57] [ 400/6250] eta: 0:17:22 lr: 0.000053 grad: 0.1212 (0.1232) loss: 0.8849 (0.8881) time: 0.1394 data: 0.0581 max mem: 8233 +Train: [57] [ 500/6250] eta: 0:16:35 lr: 0.000053 grad: 0.1211 (0.1223) loss: 0.8855 (0.8871) time: 0.1549 data: 0.0674 max mem: 8233 +Train: [57] [ 600/6250] eta: 0:16:02 lr: 0.000053 grad: 0.1146 (0.1225) loss: 0.8837 (0.8863) time: 0.1696 data: 0.0747 max mem: 8233 +Train: [57] [ 700/6250] eta: 0:15:35 lr: 0.000053 grad: 0.1188 (0.1226) loss: 0.8781 (0.8858) time: 0.1688 data: 0.0765 max mem: 8233 +Train: [57] [ 800/6250] eta: 0:15:12 lr: 0.000053 grad: 0.1204 (0.1229) loss: 0.8843 (0.8855) time: 0.1647 data: 0.0768 max mem: 8233 +Train: [57] [ 900/6250] eta: 0:14:52 lr: 0.000053 grad: 0.1257 (0.1232) loss: 0.8817 (0.8852) time: 0.1589 data: 0.0762 max mem: 8233 +Train: [57] [1000/6250] eta: 0:14:34 lr: 0.000053 grad: 0.1235 (0.1232) loss: 0.8870 (0.8849) time: 0.1377 data: 0.0581 max mem: 8233 +Train: [57] [1100/6250] eta: 0:14:19 lr: 0.000053 grad: 0.1155 (0.1234) loss: 0.8848 (0.8847) time: 0.2138 data: 0.1407 max mem: 8233 +Train: [57] [1200/6250] eta: 0:13:57 lr: 0.000053 grad: 0.1182 (0.1236) loss: 0.8849 (0.8846) time: 0.1501 data: 0.0528 max mem: 8233 +Train: [57] [1300/6250] eta: 0:13:42 lr: 0.000053 grad: 0.1238 (0.1238) loss: 0.8857 (0.8846) time: 0.2032 data: 0.1194 max mem: 8233 +Train: [57] [1400/6250] eta: 0:13:21 lr: 0.000053 grad: 0.1244 (0.1241) loss: 0.8865 (0.8845) time: 0.1491 data: 0.0621 max mem: 8233 +Train: [57] [1500/6250] eta: 0:13:06 lr: 0.000053 grad: 0.1256 (0.1241) loss: 0.8810 (0.8843) time: 0.2244 data: 0.1360 max mem: 8233 +Train: [57] [1600/6250] eta: 0:12:48 lr: 0.000053 grad: 0.1215 (0.1242) loss: 0.8871 (0.8842) time: 0.1262 data: 0.0398 max mem: 8233 +Train: [57] [1700/6250] eta: 0:12:30 lr: 0.000053 grad: 0.1289 (0.1243) loss: 0.8876 (0.8841) time: 0.1545 data: 0.0698 max mem: 8233 +Train: [57] [1800/6250] eta: 0:12:15 lr: 0.000053 grad: 0.1175 (0.1244) loss: 0.8838 (0.8841) time: 0.1792 data: 0.0817 max mem: 8233 +Train: [57] [1900/6250] eta: 0:12:00 lr: 0.000053 grad: 0.1246 (0.1246) loss: 0.8816 (0.8839) time: 0.1706 data: 0.0841 max mem: 8233 +Train: [57] [2000/6250] eta: 0:11:44 lr: 0.000053 grad: 0.1316 (0.1250) loss: 0.8786 (0.8839) time: 0.1745 data: 0.0902 max mem: 8233 +Train: [57] [2100/6250] eta: 0:11:29 lr: 0.000053 grad: 0.1229 (0.1251) loss: 0.8822 (0.8837) time: 0.1989 data: 0.1135 max mem: 8233 +Train: [57] [2200/6250] eta: 0:11:11 lr: 0.000053 grad: 0.1219 (0.1254) loss: 0.8776 (0.8835) time: 0.1647 data: 0.0879 max mem: 8233 +Train: [57] [2300/6250] eta: 0:10:52 lr: 0.000052 grad: 0.1203 (0.1256) loss: 0.8765 (0.8833) time: 0.1531 data: 0.0704 max mem: 8233 +Train: [57] [2400/6250] eta: 0:10:34 lr: 0.000052 grad: 0.1264 (0.1257) loss: 0.8821 (0.8832) time: 0.1467 data: 0.0452 max mem: 8233 +Train: [57] [2500/6250] eta: 0:10:17 lr: 0.000052 grad: 0.1224 (0.1259) loss: 0.8832 (0.8830) time: 0.1660 data: 0.0781 max mem: 8233 +Train: [57] [2600/6250] eta: 0:09:59 lr: 0.000052 grad: 0.1277 (0.1260) loss: 0.8800 (0.8830) time: 0.1403 data: 0.0662 max mem: 8233 +Train: [57] [2700/6250] eta: 0:09:46 lr: 0.000052 grad: 0.1267 (0.1260) loss: 0.8824 (0.8829) time: 0.2107 data: 0.1154 max mem: 8233 +Train: [57] [2800/6250] eta: 0:09:29 lr: 0.000052 grad: 0.1244 (0.1261) loss: 0.8815 (0.8829) time: 0.1717 data: 0.0909 max mem: 8233 +Train: [57] [2900/6250] eta: 0:09:11 lr: 0.000052 grad: 0.1188 (0.1261) loss: 0.8831 (0.8828) time: 0.1254 data: 0.0388 max mem: 8233 +Train: [57] [3000/6250] eta: 0:08:53 lr: 0.000052 grad: 0.1212 (0.1260) loss: 0.8873 (0.8828) time: 0.1566 data: 0.0761 max mem: 8233 +Train: [57] [3100/6250] eta: 0:08:36 lr: 0.000052 grad: 0.1203 (0.1259) loss: 0.8851 (0.8828) time: 0.1204 data: 0.0320 max mem: 8233 +Train: [57] [3200/6250] eta: 0:08:19 lr: 0.000052 grad: 0.1231 (0.1259) loss: 0.8800 (0.8828) time: 0.1481 data: 0.0771 max mem: 8233 +Train: [57] [3300/6250] eta: 0:08:02 lr: 0.000052 grad: 0.1142 (0.1260) loss: 0.8820 (0.8827) time: 0.1582 data: 0.0774 max mem: 8233 +Train: [57] [3400/6250] eta: 0:07:45 lr: 0.000052 grad: 0.1231 (0.1259) loss: 0.8843 (0.8828) time: 0.1644 data: 0.0788 max mem: 8233 +Train: [57] [3500/6250] eta: 0:07:29 lr: 0.000052 grad: 0.1155 (0.1259) loss: 0.8852 (0.8828) time: 0.1584 data: 0.0707 max mem: 8233 +Train: [57] [3600/6250] eta: 0:07:13 lr: 0.000052 grad: 0.1162 (0.1259) loss: 0.8847 (0.8828) time: 0.1620 data: 0.0919 max mem: 8233 +Train: [57] [3700/6250] eta: 0:06:57 lr: 0.000052 grad: 0.1208 (0.1259) loss: 0.8811 (0.8829) time: 0.1458 data: 0.0701 max mem: 8233 +Train: [57] [3800/6250] eta: 0:06:41 lr: 0.000052 grad: 0.1231 (0.1259) loss: 0.8862 (0.8829) time: 0.1857 data: 0.1079 max mem: 8233 +Train: [57] [3900/6250] eta: 0:06:24 lr: 0.000052 grad: 0.1209 (0.1259) loss: 0.8850 (0.8830) time: 0.1664 data: 0.0823 max mem: 8233 +Train: [57] [4000/6250] eta: 0:06:08 lr: 0.000052 grad: 0.1145 (0.1258) loss: 0.8898 (0.8831) time: 0.1305 data: 0.0189 max mem: 8233 +Train: [57] [4100/6250] eta: 0:05:52 lr: 0.000052 grad: 0.1209 (0.1258) loss: 0.8813 (0.8831) time: 0.1495 data: 0.0652 max mem: 8233 +Train: [57] [4200/6250] eta: 0:05:35 lr: 0.000052 grad: 0.1212 (0.1259) loss: 0.8852 (0.8831) time: 0.1563 data: 0.0664 max mem: 8233 +Train: [57] [4300/6250] eta: 0:05:19 lr: 0.000052 grad: 0.1211 (0.1260) loss: 0.8852 (0.8831) time: 0.1632 data: 0.0657 max mem: 8233 +Train: [57] [4400/6250] eta: 0:05:02 lr: 0.000052 grad: 0.1267 (0.1261) loss: 0.8836 (0.8831) time: 0.1577 data: 0.0717 max mem: 8233 +Train: [57] [4500/6250] eta: 0:04:45 lr: 0.000052 grad: 0.1220 (0.1263) loss: 0.8844 (0.8831) time: 0.1649 data: 0.0862 max mem: 8233 +Train: [57] [4600/6250] eta: 0:04:29 lr: 0.000052 grad: 0.1192 (0.1264) loss: 0.8824 (0.8831) time: 0.1528 data: 0.0695 max mem: 8233 +Train: [57] [4700/6250] eta: 0:04:12 lr: 0.000052 grad: 0.1202 (0.1264) loss: 0.8857 (0.8831) time: 0.1683 data: 0.0856 max mem: 8233 +Train: [57] [4800/6250] eta: 0:03:55 lr: 0.000052 grad: 0.1193 (0.1264) loss: 0.8871 (0.8832) time: 0.1285 data: 0.0356 max mem: 8233 +Train: [57] [4900/6250] eta: 0:03:39 lr: 0.000052 grad: 0.1257 (0.1265) loss: 0.8801 (0.8832) time: 0.1960 data: 0.1149 max mem: 8233 +Train: [57] [5000/6250] eta: 0:03:23 lr: 0.000052 grad: 0.1303 (0.1266) loss: 0.8891 (0.8832) time: 0.1749 data: 0.0923 max mem: 8233 +Train: [57] [5100/6250] eta: 0:03:07 lr: 0.000052 grad: 0.1188 (0.1266) loss: 0.8849 (0.8833) time: 0.1348 data: 0.0570 max mem: 8233 +Train: [57] [5200/6250] eta: 0:02:51 lr: 0.000052 grad: 0.1262 (0.1266) loss: 0.8831 (0.8833) time: 0.1698 data: 0.0845 max mem: 8233 +Train: [57] [5300/6250] eta: 0:02:35 lr: 0.000052 grad: 0.1310 (0.1267) loss: 0.8862 (0.8833) time: 0.2072 data: 0.1302 max mem: 8233 +Train: [57] [5400/6250] eta: 0:02:18 lr: 0.000051 grad: 0.1242 (0.1267) loss: 0.8883 (0.8834) time: 0.1596 data: 0.0739 max mem: 8233 +Train: [57] [5500/6250] eta: 0:02:02 lr: 0.000051 grad: 0.1190 (0.1267) loss: 0.8837 (0.8834) time: 0.1774 data: 0.0950 max mem: 8233 +Train: [57] [5600/6250] eta: 0:01:46 lr: 0.000051 grad: 0.1232 (0.1268) loss: 0.8860 (0.8835) time: 0.1399 data: 0.0495 max mem: 8233 +Train: [57] [5700/6250] eta: 0:01:29 lr: 0.000051 grad: 0.1172 (0.1268) loss: 0.8833 (0.8835) time: 0.1715 data: 0.0956 max mem: 8233 +Train: [57] [5800/6250] eta: 0:01:13 lr: 0.000051 grad: 0.1164 (0.1267) loss: 0.8861 (0.8836) time: 0.1420 data: 0.0662 max mem: 8233 +Train: [57] [5900/6250] eta: 0:00:57 lr: 0.000051 grad: 0.1231 (0.1267) loss: 0.8825 (0.8836) time: 0.1646 data: 0.0873 max mem: 8233 +Train: [57] [6000/6250] eta: 0:00:40 lr: 0.000051 grad: 0.1253 (0.1268) loss: 0.8833 (0.8836) time: 0.1853 data: 0.1186 max mem: 8233 +Train: [57] [6100/6250] eta: 0:00:24 lr: 0.000051 grad: 0.1285 (0.1269) loss: 0.8809 (0.8837) time: 0.1536 data: 0.0777 max mem: 8233 +Train: [57] [6200/6250] eta: 0:00:08 lr: 0.000051 grad: 0.1233 (0.1269) loss: 0.8856 (0.8837) time: 0.1508 data: 0.0779 max mem: 8233 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.1299 (0.1269) loss: 0.8805 (0.8837) time: 0.1830 data: 0.1023 max mem: 8233 +Train: [57] Total time: 0:17:05 (0.1640 s / it) +Averaged stats: lr: 0.000051 grad: 0.1299 (0.1269) loss: 0.8805 (0.8837) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:04:42 loss: 0.9052 (0.9052) time: 4.5622 data: 4.4577 max mem: 8233 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8915 (0.8921) time: 0.1349 data: 0.1131 max mem: 8233 +Eval (hcp-train-subset): [57] Total time: 0:00:15 (0.2420 s / it) +Averaged stats (hcp-train-subset): loss: 0.8915 (0.8921) +Eval (hcp-val): [57] [ 0/62] eta: 0:06:55 loss: 0.8866 (0.8866) time: 6.7026 data: 6.6746 max mem: 8233 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8912 (0.8912) time: 0.1388 data: 0.1165 max mem: 8233 +Eval (hcp-val): [57] Total time: 0:00:15 (0.2446 s / it) +Averaged stats (hcp-val): loss: 0.8912 (0.8912) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 11:01:48 lr: 0.000051 grad: 0.2605 (0.2605) loss: 0.8737 (0.8737) time: 6.3534 data: 5.9576 max mem: 8233 +Train: [58] [ 100/6250] eta: 0:25:50 lr: 0.000051 grad: 0.1164 (0.1254) loss: 0.8899 (0.8936) time: 0.2001 data: 0.0792 max mem: 8233 +Train: [58] [ 200/6250] eta: 0:22:21 lr: 0.000051 grad: 0.1227 (0.1269) loss: 0.8804 (0.8891) time: 0.2015 data: 0.0984 max mem: 8233 +Train: [58] [ 300/6250] eta: 0:20:50 lr: 0.000051 grad: 0.1155 (0.1267) loss: 0.8891 (0.8881) time: 0.1982 data: 0.0820 max mem: 8233 +Train: [58] [ 400/6250] eta: 0:19:47 lr: 0.000051 grad: 0.1157 (0.1260) loss: 0.8906 (0.8879) time: 0.1893 data: 0.0695 max mem: 8233 +Train: [58] [ 500/6250] eta: 0:18:50 lr: 0.000051 grad: 0.1101 (0.1267) loss: 0.8840 (0.8874) time: 0.1785 data: 0.0806 max mem: 8233 +Train: [58] [ 600/6250] eta: 0:18:04 lr: 0.000051 grad: 0.1154 (0.1264) loss: 0.8882 (0.8873) time: 0.1876 data: 0.0862 max mem: 8233 +Train: [58] [ 700/6250] eta: 0:17:24 lr: 0.000051 grad: 0.1214 (0.1269) loss: 0.8854 (0.8868) time: 0.1437 data: 0.0679 max mem: 8233 +Train: [58] [ 800/6250] eta: 0:16:49 lr: 0.000051 grad: 0.1176 (0.1271) loss: 0.8894 (0.8865) time: 0.1576 data: 0.0617 max mem: 8233 +Train: [58] [ 900/6250] eta: 0:16:22 lr: 0.000051 grad: 0.1400 (0.1276) loss: 0.8882 (0.8863) time: 0.1874 data: 0.0866 max mem: 8233 +Train: [58] [1000/6250] eta: 0:15:51 lr: 0.000051 grad: 0.1212 (0.1282) loss: 0.8826 (0.8859) time: 0.1215 data: 0.0247 max mem: 8233 +Train: [58] [1100/6250] eta: 0:15:21 lr: 0.000051 grad: 0.1244 (0.1281) loss: 0.8826 (0.8857) time: 0.1571 data: 0.0774 max mem: 8233 +Train: [58] [1200/6250] eta: 0:14:55 lr: 0.000051 grad: 0.1224 (0.1277) loss: 0.8819 (0.8856) time: 0.1720 data: 0.0857 max mem: 8233 +Train: [58] [1300/6250] eta: 0:14:30 lr: 0.000051 grad: 0.1267 (0.1280) loss: 0.8792 (0.8854) time: 0.1572 data: 0.0717 max mem: 8233 +Train: [58] [1400/6250] eta: 0:14:07 lr: 0.000051 grad: 0.1213 (0.1281) loss: 0.8823 (0.8852) time: 0.1643 data: 0.0838 max mem: 8233 +Train: [58] [1500/6250] eta: 0:13:45 lr: 0.000051 grad: 0.1288 (0.1281) loss: 0.8881 (0.8850) time: 0.1601 data: 0.0734 max mem: 8233 +Train: [58] [1600/6250] eta: 0:13:29 lr: 0.000051 grad: 0.1268 (0.1281) loss: 0.8874 (0.8849) time: 0.1800 data: 0.1002 max mem: 8233 +Train: [58] [1700/6250] eta: 0:13:09 lr: 0.000051 grad: 0.1248 (0.1281) loss: 0.8866 (0.8849) time: 0.1977 data: 0.1235 max mem: 8233 +Train: [58] [1800/6250] eta: 0:12:49 lr: 0.000051 grad: 0.1246 (0.1283) loss: 0.8856 (0.8849) time: 0.1481 data: 0.0770 max mem: 8233 +Train: [58] [1900/6250] eta: 0:12:32 lr: 0.000051 grad: 0.1291 (0.1288) loss: 0.8837 (0.8848) time: 0.1731 data: 0.0900 max mem: 8233 +Train: [58] [2000/6250] eta: 0:12:16 lr: 0.000051 grad: 0.1323 (0.1291) loss: 0.8848 (0.8847) time: 0.2025 data: 0.1052 max mem: 8233 +Train: [58] [2100/6250] eta: 0:11:58 lr: 0.000051 grad: 0.1223 (0.1291) loss: 0.8840 (0.8847) time: 0.1792 data: 0.0906 max mem: 8233 +Train: [58] [2200/6250] eta: 0:11:38 lr: 0.000050 grad: 0.1243 (0.1291) loss: 0.8827 (0.8846) time: 0.1370 data: 0.0554 max mem: 8233 +Train: [58] [2300/6250] eta: 0:11:18 lr: 0.000050 grad: 0.1258 (0.1291) loss: 0.8869 (0.8846) time: 0.1482 data: 0.0659 max mem: 8233 +Train: [58] [2400/6250] eta: 0:10:58 lr: 0.000050 grad: 0.1245 (0.1293) loss: 0.8822 (0.8846) time: 0.1544 data: 0.0623 max mem: 8233 +Train: [58] [2500/6250] eta: 0:10:39 lr: 0.000050 grad: 0.1196 (0.1294) loss: 0.8871 (0.8846) time: 0.1698 data: 0.0869 max mem: 8233 +Train: [58] [2600/6250] eta: 0:10:19 lr: 0.000050 grad: 0.1358 (0.1297) loss: 0.8817 (0.8845) time: 0.1442 data: 0.0705 max mem: 8233 +Train: [58] [2700/6250] eta: 0:10:02 lr: 0.000050 grad: 0.1336 (0.1298) loss: 0.8824 (0.8845) time: 0.1348 data: 0.0653 max mem: 8233 +Train: [58] [2800/6250] eta: 0:09:44 lr: 0.000050 grad: 0.1247 (0.1299) loss: 0.8811 (0.8845) time: 0.1574 data: 0.0752 max mem: 8233 +Train: [58] [2900/6250] eta: 0:09:27 lr: 0.000050 grad: 0.1148 (0.1299) loss: 0.8914 (0.8844) time: 0.1740 data: 0.0847 max mem: 8233 +Train: [58] [3000/6250] eta: 0:09:07 lr: 0.000050 grad: 0.1247 (0.1299) loss: 0.8798 (0.8844) time: 0.1426 data: 0.0614 max mem: 8233 +Train: [58] [3100/6250] eta: 0:08:50 lr: 0.000050 grad: 0.1183 (0.1299) loss: 0.8855 (0.8844) time: 0.0877 data: 0.0002 max mem: 8233 +Train: [58] [3200/6250] eta: 0:08:31 lr: 0.000050 grad: 0.1260 (0.1298) loss: 0.8817 (0.8844) time: 0.1364 data: 0.0576 max mem: 8233 +Train: [58] [3300/6250] eta: 0:08:13 lr: 0.000050 grad: 0.1223 (0.1298) loss: 0.8852 (0.8844) time: 0.1561 data: 0.0784 max mem: 8233 +Train: [58] [3400/6250] eta: 0:07:56 lr: 0.000050 grad: 0.1311 (0.1298) loss: 0.8833 (0.8844) time: 0.1669 data: 0.0865 max mem: 8233 +Train: [58] [3500/6250] eta: 0:07:38 lr: 0.000050 grad: 0.1232 (0.1299) loss: 0.8826 (0.8844) time: 0.1432 data: 0.0553 max mem: 8233 +Train: [58] [3600/6250] eta: 0:07:22 lr: 0.000050 grad: 0.1295 (0.1300) loss: 0.8764 (0.8844) time: 0.1756 data: 0.0994 max mem: 8233 +Train: [58] [3700/6250] eta: 0:07:05 lr: 0.000050 grad: 0.1263 (0.1301) loss: 0.8854 (0.8844) time: 0.1874 data: 0.1000 max mem: 8233 +Train: [58] [3800/6250] eta: 0:06:49 lr: 0.000050 grad: 0.1195 (0.1302) loss: 0.8843 (0.8844) time: 0.1882 data: 0.1091 max mem: 8233 +Train: [58] [3900/6250] eta: 0:06:32 lr: 0.000050 grad: 0.1157 (0.1302) loss: 0.8819 (0.8844) time: 0.2434 data: 0.1655 max mem: 8233 +Train: [58] [4000/6250] eta: 0:06:15 lr: 0.000050 grad: 0.1145 (0.1301) loss: 0.8844 (0.8843) time: 0.1811 data: 0.1013 max mem: 8233 +Train: [58] [4100/6250] eta: 0:05:59 lr: 0.000050 grad: 0.1307 (0.1301) loss: 0.8792 (0.8843) time: 0.1724 data: 0.0789 max mem: 8233 +Train: [58] [4200/6250] eta: 0:05:43 lr: 0.000050 grad: 0.1286 (0.1300) loss: 0.8803 (0.8843) time: 0.1685 data: 0.0821 max mem: 8233 +Train: [58] [4300/6250] eta: 0:05:26 lr: 0.000050 grad: 0.1332 (0.1302) loss: 0.8855 (0.8843) time: 0.1565 data: 0.0706 max mem: 8233 +Train: [58] [4400/6250] eta: 0:05:09 lr: 0.000050 grad: 0.1315 (0.1303) loss: 0.8826 (0.8842) time: 0.1800 data: 0.0994 max mem: 8233 +Train: [58] [4500/6250] eta: 0:04:52 lr: 0.000050 grad: 0.1339 (0.1304) loss: 0.8815 (0.8842) time: 0.1719 data: 0.0906 max mem: 8233 +Train: [58] [4600/6250] eta: 0:04:35 lr: 0.000050 grad: 0.1197 (0.1304) loss: 0.8874 (0.8842) time: 0.1724 data: 0.0936 max mem: 8233 +Train: [58] [4700/6250] eta: 0:04:18 lr: 0.000050 grad: 0.1272 (0.1304) loss: 0.8885 (0.8842) time: 0.1521 data: 0.0698 max mem: 8233 +Train: [58] [4800/6250] eta: 0:04:01 lr: 0.000050 grad: 0.1274 (0.1303) loss: 0.8804 (0.8842) time: 0.1680 data: 0.1053 max mem: 8233 +Train: [58] [4900/6250] eta: 0:03:45 lr: 0.000050 grad: 0.1278 (0.1303) loss: 0.8824 (0.8841) time: 0.1897 data: 0.1026 max mem: 8233 +Train: [58] [5000/6250] eta: 0:03:28 lr: 0.000050 grad: 0.1281 (0.1304) loss: 0.8861 (0.8841) time: 0.1690 data: 0.0897 max mem: 8233 +Train: [58] [5100/6250] eta: 0:03:11 lr: 0.000050 grad: 0.1323 (0.1305) loss: 0.8823 (0.8841) time: 0.1699 data: 0.0849 max mem: 8233 +Train: [58] [5200/6250] eta: 0:02:55 lr: 0.000050 grad: 0.1302 (0.1305) loss: 0.8857 (0.8841) time: 0.1899 data: 0.1079 max mem: 8233 +Train: [58] [5300/6250] eta: 0:02:38 lr: 0.000049 grad: 0.1215 (0.1304) loss: 0.8872 (0.8841) time: 0.2312 data: 0.1543 max mem: 8233 +Train: [58] [5400/6250] eta: 0:02:21 lr: 0.000049 grad: 0.1241 (0.1304) loss: 0.8862 (0.8841) time: 0.2042 data: 0.1288 max mem: 8233 +Train: [58] [5500/6250] eta: 0:02:04 lr: 0.000049 grad: 0.1186 (0.1304) loss: 0.8873 (0.8841) time: 0.1683 data: 0.0922 max mem: 8233 +Train: [58] [5600/6250] eta: 0:01:48 lr: 0.000049 grad: 0.1386 (0.1305) loss: 0.8804 (0.8841) time: 0.1910 data: 0.1147 max mem: 8233 +Train: [58] [5700/6250] eta: 0:01:31 lr: 0.000049 grad: 0.1259 (0.1305) loss: 0.8811 (0.8840) time: 0.1349 data: 0.0544 max mem: 8233 +Train: [58] [5800/6250] eta: 0:01:14 lr: 0.000049 grad: 0.1295 (0.1306) loss: 0.8850 (0.8840) time: 0.1663 data: 0.0914 max mem: 8233 +Train: [58] [5900/6250] eta: 0:00:58 lr: 0.000049 grad: 0.1206 (0.1306) loss: 0.8856 (0.8840) time: 0.1697 data: 0.0883 max mem: 8233 +Train: [58] [6000/6250] eta: 0:00:41 lr: 0.000049 grad: 0.1243 (0.1306) loss: 0.8739 (0.8840) time: 0.1991 data: 0.1185 max mem: 8233 +Train: [58] [6100/6250] eta: 0:00:24 lr: 0.000049 grad: 0.1238 (0.1306) loss: 0.8808 (0.8840) time: 0.1539 data: 0.0796 max mem: 8233 +Train: [58] [6200/6250] eta: 0:00:08 lr: 0.000049 grad: 0.1286 (0.1306) loss: 0.8782 (0.8839) time: 0.2121 data: 0.1315 max mem: 8233 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.1216 (0.1306) loss: 0.8854 (0.8839) time: 0.1713 data: 0.0836 max mem: 8233 +Train: [58] Total time: 0:17:31 (0.1683 s / it) +Averaged stats: lr: 0.000049 grad: 0.1216 (0.1306) loss: 0.8854 (0.8839) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:03:56 loss: 0.9059 (0.9059) time: 3.8113 data: 3.7414 max mem: 8233 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8933 (0.8922) time: 0.1880 data: 0.1662 max mem: 8233 +Eval (hcp-train-subset): [58] Total time: 0:00:16 (0.2660 s / it) +Averaged stats (hcp-train-subset): loss: 0.8933 (0.8922) +Eval (hcp-val): [58] [ 0/62] eta: 0:05:36 loss: 0.8844 (0.8844) time: 5.4234 data: 5.3394 max mem: 8233 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8883 (0.8897) time: 0.1573 data: 0.1364 max mem: 8233 +Eval (hcp-val): [58] Total time: 0:00:16 (0.2721 s / it) +Averaged stats (hcp-val): loss: 0.8883 (0.8897) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 8:50:22 lr: 0.000049 grad: 0.0823 (0.0823) loss: 0.8977 (0.8977) time: 5.0917 data: 4.8797 max mem: 8233 +Train: [59] [ 100/6250] eta: 0:26:01 lr: 0.000049 grad: 0.1146 (0.1244) loss: 0.8913 (0.8880) time: 0.1807 data: 0.0558 max mem: 8233 +Train: [59] [ 200/6250] eta: 0:22:51 lr: 0.000049 grad: 0.1169 (0.1241) loss: 0.8793 (0.8875) time: 0.1928 data: 0.0740 max mem: 8233 +Train: [59] [ 300/6250] eta: 0:21:07 lr: 0.000049 grad: 0.1224 (0.1245) loss: 0.8880 (0.8868) time: 0.1874 data: 0.0725 max mem: 8233 +Train: [59] [ 400/6250] eta: 0:20:14 lr: 0.000049 grad: 0.1249 (0.1259) loss: 0.8834 (0.8859) time: 0.1774 data: 0.0810 max mem: 8233 +Train: [59] [ 500/6250] eta: 0:19:11 lr: 0.000049 grad: 0.1173 (0.1264) loss: 0.8818 (0.8854) time: 0.1719 data: 0.0689 max mem: 8233 +Train: [59] [ 600/6250] eta: 0:18:31 lr: 0.000049 grad: 0.1232 (0.1271) loss: 0.8829 (0.8847) time: 0.1502 data: 0.0520 max mem: 8233 +Train: [59] [ 700/6250] eta: 0:17:50 lr: 0.000049 grad: 0.1258 (0.1269) loss: 0.8784 (0.8840) time: 0.1769 data: 0.0801 max mem: 8233 +Train: [59] [ 800/6250] eta: 0:17:11 lr: 0.000049 grad: 0.1264 (0.1272) loss: 0.8818 (0.8836) time: 0.1643 data: 0.0724 max mem: 8233 +Train: [59] [ 900/6250] eta: 0:16:49 lr: 0.000049 grad: 0.1279 (0.1275) loss: 0.8807 (0.8832) time: 0.1430 data: 0.0548 max mem: 8233 +Train: [59] [1000/6250] eta: 0:16:08 lr: 0.000049 grad: 0.1210 (0.1272) loss: 0.8806 (0.8831) time: 0.1248 data: 0.0462 max mem: 8233 +Train: [59] [1100/6250] eta: 0:16:01 lr: 0.000049 grad: 0.1258 (0.1272) loss: 0.8805 (0.8830) time: 0.3045 data: 0.2302 max mem: 8233 +Train: [59] [1200/6250] eta: 0:15:23 lr: 0.000049 grad: 0.1214 (0.1272) loss: 0.8768 (0.8828) time: 0.1429 data: 0.0579 max mem: 8233 +Train: [59] [1300/6250] eta: 0:14:58 lr: 0.000049 grad: 0.1255 (0.1272) loss: 0.8816 (0.8826) time: 0.1701 data: 0.1002 max mem: 8233 +Train: [59] [1400/6250] eta: 0:14:34 lr: 0.000049 grad: 0.1238 (0.1273) loss: 0.8832 (0.8825) time: 0.1524 data: 0.0779 max mem: 8233 +Train: [59] [1500/6250] eta: 0:14:16 lr: 0.000049 grad: 0.1283 (0.1275) loss: 0.8856 (0.8824) time: 0.1796 data: 0.0948 max mem: 8233 +Train: [59] [1600/6250] eta: 0:13:56 lr: 0.000049 grad: 0.1176 (0.1273) loss: 0.8816 (0.8824) time: 0.1841 data: 0.1053 max mem: 8233 +Train: [59] [1700/6250] eta: 0:13:33 lr: 0.000049 grad: 0.1244 (0.1272) loss: 0.8803 (0.8824) time: 0.1605 data: 0.0791 max mem: 8233 +Train: [59] [1800/6250] eta: 0:13:11 lr: 0.000049 grad: 0.1234 (0.1271) loss: 0.8839 (0.8824) time: 0.1344 data: 0.0593 max mem: 8233 +Train: [59] [1900/6250] eta: 0:12:51 lr: 0.000049 grad: 0.1208 (0.1269) loss: 0.8827 (0.8824) time: 0.1599 data: 0.0835 max mem: 8233 +Train: [59] [2000/6250] eta: 0:12:30 lr: 0.000049 grad: 0.1185 (0.1270) loss: 0.8798 (0.8824) time: 0.1618 data: 0.0786 max mem: 8233 +Train: [59] [2100/6250] eta: 0:12:12 lr: 0.000048 grad: 0.1280 (0.1273) loss: 0.8760 (0.8823) time: 0.1652 data: 0.0761 max mem: 8233 +Train: [59] [2200/6250] eta: 0:11:51 lr: 0.000048 grad: 0.1225 (0.1275) loss: 0.8800 (0.8822) time: 0.1446 data: 0.0622 max mem: 8233 +Train: [59] [2300/6250] eta: 0:11:31 lr: 0.000048 grad: 0.1302 (0.1276) loss: 0.8824 (0.8821) time: 0.1521 data: 0.0673 max mem: 8233 +Train: [59] [2400/6250] eta: 0:11:10 lr: 0.000048 grad: 0.1217 (0.1278) loss: 0.8791 (0.8820) time: 0.1559 data: 0.0733 max mem: 8233 +Train: [59] [2500/6250] eta: 0:10:49 lr: 0.000048 grad: 0.1286 (0.1280) loss: 0.8802 (0.8819) time: 0.1387 data: 0.0279 max mem: 8233 +Train: [59] [2600/6250] eta: 0:10:28 lr: 0.000048 grad: 0.1192 (0.1281) loss: 0.8806 (0.8820) time: 0.1430 data: 0.0615 max mem: 8233 +Train: [59] [2700/6250] eta: 0:10:10 lr: 0.000048 grad: 0.1323 (0.1283) loss: 0.8833 (0.8819) time: 0.1645 data: 0.0895 max mem: 8233 +Train: [59] [2800/6250] eta: 0:09:50 lr: 0.000048 grad: 0.1230 (0.1283) loss: 0.8825 (0.8819) time: 0.1529 data: 0.0667 max mem: 8233 +Train: [59] [2900/6250] eta: 0:09:33 lr: 0.000048 grad: 0.1250 (0.1283) loss: 0.8845 (0.8820) time: 0.1351 data: 0.0328 max mem: 8233 +Train: [59] [3000/6250] eta: 0:09:16 lr: 0.000048 grad: 0.1239 (0.1283) loss: 0.8778 (0.8820) time: 0.1211 data: 0.0365 max mem: 8233 +Train: [59] [3100/6250] eta: 0:08:57 lr: 0.000048 grad: 0.1234 (0.1282) loss: 0.8855 (0.8820) time: 0.1613 data: 0.0866 max mem: 8233 +Train: [59] [3200/6250] eta: 0:08:39 lr: 0.000048 grad: 0.1261 (0.1281) loss: 0.8855 (0.8820) time: 0.1910 data: 0.1056 max mem: 8233 +Train: [59] [3300/6250] eta: 0:08:21 lr: 0.000048 grad: 0.1276 (0.1281) loss: 0.8822 (0.8821) time: 0.1670 data: 0.0831 max mem: 8233 +Train: [59] [3400/6250] eta: 0:08:05 lr: 0.000048 grad: 0.1243 (0.1280) loss: 0.8837 (0.8821) time: 0.2321 data: 0.1539 max mem: 8233 +Train: [59] [3500/6250] eta: 0:07:47 lr: 0.000048 grad: 0.1260 (0.1281) loss: 0.8863 (0.8821) time: 0.1498 data: 0.0654 max mem: 8233 +Train: [59] [3600/6250] eta: 0:07:29 lr: 0.000048 grad: 0.1321 (0.1281) loss: 0.8854 (0.8821) time: 0.1750 data: 0.1038 max mem: 8233 +Train: [59] [3700/6250] eta: 0:07:16 lr: 0.000048 grad: 0.1170 (0.1282) loss: 0.8824 (0.8821) time: 0.1917 data: 0.1156 max mem: 8233 +Train: [59] [3800/6250] eta: 0:07:00 lr: 0.000048 grad: 0.1127 (0.1282) loss: 0.8870 (0.8822) time: 0.1955 data: 0.1160 max mem: 8233 +Train: [59] [3900/6250] eta: 0:06:45 lr: 0.000048 grad: 0.1319 (0.1285) loss: 0.8847 (0.8822) time: 0.2312 data: 0.1557 max mem: 8233 +Train: [59] [4000/6250] eta: 0:06:29 lr: 0.000048 grad: 0.1290 (0.1286) loss: 0.8828 (0.8822) time: 0.1983 data: 0.0947 max mem: 8233 +Train: [59] [4100/6250] eta: 0:06:12 lr: 0.000048 grad: 0.1262 (0.1287) loss: 0.8866 (0.8823) time: 0.1478 data: 0.0517 max mem: 8233 +Train: [59] [4200/6250] eta: 0:05:55 lr: 0.000048 grad: 0.1255 (0.1287) loss: 0.8859 (0.8823) time: 0.1775 data: 0.0973 max mem: 8233 +Train: [59] [4300/6250] eta: 0:05:37 lr: 0.000048 grad: 0.1194 (0.1288) loss: 0.8845 (0.8822) time: 0.1699 data: 0.0841 max mem: 8233 +Train: [59] [4400/6250] eta: 0:05:20 lr: 0.000048 grad: 0.1323 (0.1288) loss: 0.8757 (0.8822) time: 0.1958 data: 0.1013 max mem: 8233 +Train: [59] [4500/6250] eta: 0:05:02 lr: 0.000048 grad: 0.1250 (0.1288) loss: 0.8793 (0.8822) time: 0.1420 data: 0.0593 max mem: 8233 +Train: [59] [4600/6250] eta: 0:04:44 lr: 0.000048 grad: 0.1194 (0.1288) loss: 0.8836 (0.8822) time: 0.1630 data: 0.0889 max mem: 8233 +Train: [59] [4700/6250] eta: 0:04:26 lr: 0.000048 grad: 0.1274 (0.1289) loss: 0.8802 (0.8822) time: 0.1710 data: 0.0988 max mem: 8233 +Train: [59] [4800/6250] eta: 0:04:10 lr: 0.000048 grad: 0.1333 (0.1289) loss: 0.8818 (0.8821) time: 0.1679 data: 0.0779 max mem: 8233 +Train: [59] [4900/6250] eta: 0:03:53 lr: 0.000048 grad: 0.1193 (0.1290) loss: 0.8763 (0.8821) time: 0.1890 data: 0.1206 max mem: 8233 +Train: [59] [5000/6250] eta: 0:03:35 lr: 0.000048 grad: 0.1152 (0.1290) loss: 0.8810 (0.8821) time: 0.1878 data: 0.1165 max mem: 8233 +Train: [59] [5100/6250] eta: 0:03:18 lr: 0.000048 grad: 0.1296 (0.1291) loss: 0.8830 (0.8820) time: 0.1230 data: 0.0316 max mem: 8233 +Train: [59] [5200/6250] eta: 0:03:00 lr: 0.000047 grad: 0.1231 (0.1291) loss: 0.8809 (0.8820) time: 0.1912 data: 0.1121 max mem: 8233 +Train: [59] [5300/6250] eta: 0:02:43 lr: 0.000047 grad: 0.1208 (0.1290) loss: 0.8841 (0.8820) time: 0.1071 data: 0.0003 max mem: 8233 +Train: [59] [5400/6250] eta: 0:02:26 lr: 0.000047 grad: 0.1267 (0.1290) loss: 0.8860 (0.8820) time: 0.1374 data: 0.0553 max mem: 8233 +Train: [59] [5500/6250] eta: 0:02:09 lr: 0.000047 grad: 0.1211 (0.1290) loss: 0.8812 (0.8820) time: 0.1809 data: 0.0491 max mem: 8233 +Train: [59] [5600/6250] eta: 0:01:52 lr: 0.000047 grad: 0.1304 (0.1291) loss: 0.8800 (0.8820) time: 0.1782 data: 0.0928 max mem: 8233 +Train: [59] [5700/6250] eta: 0:01:35 lr: 0.000047 grad: 0.1275 (0.1291) loss: 0.8840 (0.8820) time: 0.2472 data: 0.1629 max mem: 8233 +Train: [59] [5800/6250] eta: 0:01:17 lr: 0.000047 grad: 0.1196 (0.1290) loss: 0.8849 (0.8821) time: 0.1521 data: 0.0606 max mem: 8233 +Train: [59] [5900/6250] eta: 0:01:00 lr: 0.000047 grad: 0.1172 (0.1290) loss: 0.8863 (0.8821) time: 0.1768 data: 0.0984 max mem: 8233 +Train: [59] [6000/6250] eta: 0:00:43 lr: 0.000047 grad: 0.1252 (0.1290) loss: 0.8762 (0.8821) time: 0.1664 data: 0.0908 max mem: 8233 +Train: [59] [6100/6250] eta: 0:00:25 lr: 0.000047 grad: 0.1154 (0.1291) loss: 0.8810 (0.8821) time: 0.1804 data: 0.1061 max mem: 8233 +Train: [59] [6200/6250] eta: 0:00:08 lr: 0.000047 grad: 0.1187 (0.1292) loss: 0.8832 (0.8820) time: 0.1561 data: 0.0623 max mem: 8233 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.1363 (0.1293) loss: 0.8837 (0.8820) time: 0.1673 data: 0.0852 max mem: 8233 +Train: [59] Total time: 0:18:05 (0.1737 s / it) +Averaged stats: lr: 0.000047 grad: 0.1363 (0.1293) loss: 0.8837 (0.8820) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:05:30 loss: 0.9028 (0.9028) time: 5.3328 data: 5.2699 max mem: 8233 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8928 (0.8922) time: 0.1413 data: 0.1206 max mem: 8233 +Eval (hcp-train-subset): [59] Total time: 0:00:14 (0.2367 s / it) +Averaged stats (hcp-train-subset): loss: 0.8928 (0.8922) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [59] [ 0/62] eta: 0:06:09 loss: 0.8858 (0.8858) time: 5.9674 data: 5.9408 max mem: 8233 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8884 (0.8896) time: 0.1452 data: 0.1228 max mem: 8233 +Eval (hcp-val): [59] Total time: 0:00:15 (0.2482 s / it) +Averaged stats (hcp-val): loss: 0.8884 (0.8896) +Making plots (hcp-val): example=59 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-00059.pth +Train: [60] [ 0/6250] eta: 13:23:03 lr: 0.000047 grad: 0.0941 (0.0941) loss: 0.9275 (0.9275) time: 7.7093 data: 7.6130 max mem: 8233 +Train: [60] [ 100/6250] eta: 0:23:52 lr: 0.000047 grad: 0.1332 (0.1335) loss: 0.8875 (0.8888) time: 0.1723 data: 0.0623 max mem: 8233 +Train: [60] [ 200/6250] eta: 0:20:36 lr: 0.000047 grad: 0.1170 (0.1280) loss: 0.8857 (0.8880) time: 0.1577 data: 0.0471 max mem: 8233 +Train: [60] [ 300/6250] eta: 0:19:08 lr: 0.000047 grad: 0.1182 (0.1269) loss: 0.8838 (0.8872) time: 0.1790 data: 0.0766 max mem: 8233 +Train: [60] [ 400/6250] eta: 0:18:08 lr: 0.000047 grad: 0.1185 (0.1265) loss: 0.8791 (0.8869) time: 0.1651 data: 0.0655 max mem: 8233 +Train: [60] [ 500/6250] eta: 0:17:19 lr: 0.000047 grad: 0.1223 (0.1260) loss: 0.8843 (0.8864) time: 0.1628 data: 0.0688 max mem: 8233 +Train: [60] [ 600/6250] eta: 0:16:44 lr: 0.000047 grad: 0.1208 (0.1261) loss: 0.8878 (0.8865) time: 0.1074 data: 0.0026 max mem: 8233 +Train: [60] [ 700/6250] eta: 0:16:30 lr: 0.000047 grad: 0.1143 (0.1254) loss: 0.8885 (0.8863) time: 0.1866 data: 0.1027 max mem: 8233 +Train: [60] [ 800/6250] eta: 0:16:02 lr: 0.000047 grad: 0.1203 (0.1258) loss: 0.8850 (0.8862) time: 0.1642 data: 0.0711 max mem: 8233 +Train: [60] [ 900/6250] eta: 0:15:46 lr: 0.000047 grad: 0.1167 (0.1254) loss: 0.8873 (0.8865) time: 0.1613 data: 0.0674 max mem: 8233 +Train: [60] [1000/6250] eta: 0:15:21 lr: 0.000047 grad: 0.1209 (0.1250) loss: 0.8854 (0.8864) time: 0.1500 data: 0.0669 max mem: 8233 +Train: [60] [1100/6250] eta: 0:15:02 lr: 0.000047 grad: 0.1197 (0.1250) loss: 0.8904 (0.8864) time: 0.1487 data: 0.0718 max mem: 8233 +Train: [60] [1200/6250] eta: 0:14:40 lr: 0.000047 grad: 0.1249 (0.1253) loss: 0.8842 (0.8862) time: 0.1620 data: 0.0694 max mem: 8233 +Train: [60] [1300/6250] eta: 0:14:18 lr: 0.000047 grad: 0.1209 (0.1252) loss: 0.8818 (0.8862) time: 0.1758 data: 0.0924 max mem: 8233 +Train: [60] [1400/6250] eta: 0:14:03 lr: 0.000047 grad: 0.1209 (0.1254) loss: 0.8854 (0.8862) time: 0.1629 data: 0.0938 max mem: 8233 +Train: [60] [1500/6250] eta: 0:13:39 lr: 0.000047 grad: 0.1258 (0.1258) loss: 0.8799 (0.8860) time: 0.1269 data: 0.0380 max mem: 8233 +Train: [60] [1600/6250] eta: 0:13:21 lr: 0.000047 grad: 0.1219 (0.1260) loss: 0.8818 (0.8858) time: 0.1616 data: 0.0806 max mem: 8233 +Train: [60] [1700/6250] eta: 0:13:04 lr: 0.000047 grad: 0.1205 (0.1260) loss: 0.8843 (0.8857) time: 0.1761 data: 0.0970 max mem: 8233 +Train: [60] [1800/6250] eta: 0:12:43 lr: 0.000047 grad: 0.1273 (0.1263) loss: 0.8815 (0.8855) time: 0.1562 data: 0.0859 max mem: 8233 +Train: [60] [1900/6250] eta: 0:12:24 lr: 0.000047 grad: 0.1292 (0.1263) loss: 0.8779 (0.8853) time: 0.1669 data: 0.0924 max mem: 8233 +Train: [60] [2000/6250] eta: 0:12:07 lr: 0.000047 grad: 0.1244 (0.1265) loss: 0.8762 (0.8851) time: 0.1698 data: 0.0929 max mem: 8233 +Train: [60] [2100/6250] eta: 0:11:49 lr: 0.000046 grad: 0.1198 (0.1267) loss: 0.8835 (0.8850) time: 0.1834 data: 0.0947 max mem: 8233 +Train: [60] [2200/6250] eta: 0:11:30 lr: 0.000046 grad: 0.1197 (0.1267) loss: 0.8883 (0.8849) time: 0.1501 data: 0.0589 max mem: 8233 +Train: [60] [2300/6250] eta: 0:11:11 lr: 0.000046 grad: 0.1386 (0.1271) loss: 0.8832 (0.8848) time: 0.1219 data: 0.0438 max mem: 8233 +Train: [60] [2400/6250] eta: 0:10:52 lr: 0.000046 grad: 0.1264 (0.1271) loss: 0.8784 (0.8848) time: 0.1618 data: 0.0716 max mem: 8233 +Train: [60] [2500/6250] eta: 0:10:33 lr: 0.000046 grad: 0.1269 (0.1273) loss: 0.8830 (0.8847) time: 0.1577 data: 0.0679 max mem: 8233 +Train: [60] [2600/6250] eta: 0:10:15 lr: 0.000046 grad: 0.1229 (0.1274) loss: 0.8875 (0.8846) time: 0.1527 data: 0.0825 max mem: 8233 +Train: [60] [2700/6250] eta: 0:09:56 lr: 0.000046 grad: 0.1294 (0.1277) loss: 0.8788 (0.8845) time: 0.1549 data: 0.0652 max mem: 8233 +Train: [60] [2800/6250] eta: 0:09:40 lr: 0.000046 grad: 0.1211 (0.1279) loss: 0.8845 (0.8845) time: 0.1791 data: 0.1038 max mem: 8233 +Train: [60] [2900/6250] eta: 0:09:25 lr: 0.000046 grad: 0.1278 (0.1280) loss: 0.8830 (0.8844) time: 0.1742 data: 0.1061 max mem: 8233 +Train: [60] [3000/6250] eta: 0:09:10 lr: 0.000046 grad: 0.1188 (0.1280) loss: 0.8828 (0.8843) time: 0.1772 data: 0.1032 max mem: 8233 +Train: [60] [3100/6250] eta: 0:08:54 lr: 0.000046 grad: 0.1298 (0.1281) loss: 0.8841 (0.8843) time: 0.1894 data: 0.1122 max mem: 8233 +Train: [60] [3200/6250] eta: 0:08:37 lr: 0.000046 grad: 0.1294 (0.1283) loss: 0.8792 (0.8842) time: 0.1552 data: 0.0788 max mem: 8233 +Train: [60] [3300/6250] eta: 0:08:19 lr: 0.000046 grad: 0.1333 (0.1284) loss: 0.8835 (0.8841) time: 0.1418 data: 0.0605 max mem: 8233 +Train: [60] [3400/6250] eta: 0:08:02 lr: 0.000046 grad: 0.1224 (0.1284) loss: 0.8829 (0.8841) time: 0.1810 data: 0.0980 max mem: 8233 +Train: [60] [3500/6250] eta: 0:07:44 lr: 0.000046 grad: 0.1283 (0.1285) loss: 0.8849 (0.8841) time: 0.1620 data: 0.0854 max mem: 8233 +Train: [60] [3600/6250] eta: 0:07:28 lr: 0.000046 grad: 0.1261 (0.1285) loss: 0.8842 (0.8841) time: 0.1954 data: 0.0867 max mem: 8233 +Train: [60] [3700/6250] eta: 0:07:12 lr: 0.000046 grad: 0.1325 (0.1285) loss: 0.8826 (0.8840) time: 0.1717 data: 0.0925 max mem: 8233 +Train: [60] [3800/6250] eta: 0:06:55 lr: 0.000046 grad: 0.1251 (0.1286) loss: 0.8825 (0.8840) time: 0.2061 data: 0.1146 max mem: 8233 +Train: [60] [3900/6250] eta: 0:06:39 lr: 0.000046 grad: 0.1311 (0.1288) loss: 0.8839 (0.8840) time: 0.1779 data: 0.0972 max mem: 8233 +Train: [60] [4000/6250] eta: 0:06:21 lr: 0.000046 grad: 0.1233 (0.1291) loss: 0.8842 (0.8839) time: 0.1490 data: 0.0730 max mem: 8233 +Train: [60] [4100/6250] eta: 0:06:05 lr: 0.000046 grad: 0.1326 (0.1292) loss: 0.8828 (0.8839) time: 0.1920 data: 0.1075 max mem: 8233 +Train: [60] [4200/6250] eta: 0:05:47 lr: 0.000046 grad: 0.1378 (0.1293) loss: 0.8830 (0.8839) time: 0.1643 data: 0.0777 max mem: 8233 +Train: [60] [4300/6250] eta: 0:05:30 lr: 0.000046 grad: 0.1339 (0.1294) loss: 0.8793 (0.8838) time: 0.1499 data: 0.0568 max mem: 8233 +Train: [60] [4400/6250] eta: 0:05:13 lr: 0.000046 grad: 0.1216 (0.1295) loss: 0.8838 (0.8838) time: 0.1670 data: 0.0860 max mem: 8233 +Train: [60] [4500/6250] eta: 0:04:55 lr: 0.000046 grad: 0.1314 (0.1295) loss: 0.8815 (0.8837) time: 0.1399 data: 0.0391 max mem: 8233 +Train: [60] [4600/6250] eta: 0:04:38 lr: 0.000046 grad: 0.1357 (0.1297) loss: 0.8751 (0.8836) time: 0.1526 data: 0.0734 max mem: 8233 +Train: [60] [4700/6250] eta: 0:04:21 lr: 0.000046 grad: 0.1188 (0.1298) loss: 0.8834 (0.8835) time: 0.1249 data: 0.0500 max mem: 8233 +Train: [60] [4800/6250] eta: 0:04:03 lr: 0.000046 grad: 0.1263 (0.1298) loss: 0.8832 (0.8834) time: 0.1417 data: 0.0542 max mem: 8233 +Train: [60] [4900/6250] eta: 0:03:46 lr: 0.000046 grad: 0.1262 (0.1299) loss: 0.8833 (0.8834) time: 0.1745 data: 0.1091 max mem: 8233 +Train: [60] [5000/6250] eta: 0:03:29 lr: 0.000046 grad: 0.1330 (0.1301) loss: 0.8850 (0.8834) time: 0.1849 data: 0.1107 max mem: 8233 +Train: [60] [5100/6250] eta: 0:03:13 lr: 0.000046 grad: 0.1393 (0.1303) loss: 0.8784 (0.8833) time: 0.2589 data: 0.1897 max mem: 8233 +Train: [60] [5200/6250] eta: 0:02:56 lr: 0.000045 grad: 0.1242 (0.1304) loss: 0.8800 (0.8833) time: 0.1431 data: 0.0457 max mem: 8233 +Train: [60] [5300/6250] eta: 0:02:39 lr: 0.000045 grad: 0.1253 (0.1306) loss: 0.8813 (0.8833) time: 0.1565 data: 0.0617 max mem: 8233 +Train: [60] [5400/6250] eta: 0:02:23 lr: 0.000045 grad: 0.1241 (0.1307) loss: 0.8852 (0.8832) time: 0.1201 data: 0.0003 max mem: 8233 +Train: [60] [5500/6250] eta: 0:02:06 lr: 0.000045 grad: 0.1291 (0.1309) loss: 0.8799 (0.8832) time: 0.2029 data: 0.1220 max mem: 8233 +Train: [60] [5600/6250] eta: 0:01:49 lr: 0.000045 grad: 0.1295 (0.1310) loss: 0.8793 (0.8831) time: 0.1620 data: 0.0732 max mem: 8233 +Train: [60] [5700/6250] eta: 0:01:32 lr: 0.000045 grad: 0.1335 (0.1313) loss: 0.8812 (0.8830) time: 0.1727 data: 0.0936 max mem: 8233 +Train: [60] [5800/6250] eta: 0:01:15 lr: 0.000045 grad: 0.1330 (0.1313) loss: 0.8831 (0.8830) time: 0.1249 data: 0.0420 max mem: 8233 +Train: [60] [5900/6250] eta: 0:00:58 lr: 0.000045 grad: 0.1379 (0.1315) loss: 0.8785 (0.8829) time: 0.1452 data: 0.0580 max mem: 8233 +Train: [60] [6000/6250] eta: 0:00:42 lr: 0.000045 grad: 0.1259 (0.1316) loss: 0.8847 (0.8828) time: 0.1728 data: 0.1001 max mem: 8233 +Train: [60] [6100/6250] eta: 0:00:25 lr: 0.000045 grad: 0.1341 (0.1318) loss: 0.8774 (0.8827) time: 0.1699 data: 0.0928 max mem: 8233 +Train: [60] [6200/6250] eta: 0:00:08 lr: 0.000045 grad: 0.1261 (0.1318) loss: 0.8767 (0.8826) time: 0.2225 data: 0.1611 max mem: 8233 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1266 (0.1318) loss: 0.8873 (0.8826) time: 0.1981 data: 0.1250 max mem: 8233 +Train: [60] Total time: 0:17:38 (0.1693 s / it) +Averaged stats: lr: 0.000045 grad: 0.1266 (0.1318) loss: 0.8873 (0.8826) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:06:22 loss: 0.9015 (0.9015) time: 6.1635 data: 6.1370 max mem: 8233 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8897 (0.8918) time: 0.1616 data: 0.1410 max mem: 8233 +Eval (hcp-train-subset): [60] Total time: 0:00:15 (0.2498 s / it) +Averaged stats (hcp-train-subset): loss: 0.8897 (0.8918) +Eval (hcp-val): [60] [ 0/62] eta: 0:04:56 loss: 0.8838 (0.8838) time: 4.7901 data: 4.7302 max mem: 8233 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8869 (0.8887) time: 0.1396 data: 0.1192 max mem: 8233 +Eval (hcp-val): [60] Total time: 0:00:14 (0.2341 s / it) +Averaged stats (hcp-val): loss: 0.8869 (0.8887) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 12:27:02 lr: 0.000045 grad: 0.1756 (0.1756) loss: 0.8515 (0.8515) time: 7.1717 data: 7.0550 max mem: 8233 +Train: [61] [ 100/6250] eta: 0:23:45 lr: 0.000045 grad: 0.1186 (0.1281) loss: 0.8861 (0.8910) time: 0.1855 data: 0.0821 max mem: 8233 +Train: [61] [ 200/6250] eta: 0:20:23 lr: 0.000045 grad: 0.1243 (0.1280) loss: 0.8811 (0.8866) time: 0.1724 data: 0.0660 max mem: 8233 +Train: [61] [ 300/6250] eta: 0:19:15 lr: 0.000045 grad: 0.1250 (0.1280) loss: 0.8763 (0.8830) time: 0.1821 data: 0.0800 max mem: 8233 +Train: [61] [ 400/6250] eta: 0:18:34 lr: 0.000045 grad: 0.1181 (0.1276) loss: 0.8759 (0.8821) time: 0.1959 data: 0.1126 max mem: 8233 +Train: [61] [ 500/6250] eta: 0:17:43 lr: 0.000045 grad: 0.1322 (0.1277) loss: 0.8786 (0.8821) time: 0.1733 data: 0.0620 max mem: 8233 +Train: [61] [ 600/6250] eta: 0:17:09 lr: 0.000045 grad: 0.1235 (0.1272) loss: 0.8848 (0.8821) time: 0.1558 data: 0.0602 max mem: 8233 +Train: [61] [ 700/6250] eta: 0:16:32 lr: 0.000045 grad: 0.1247 (0.1273) loss: 0.8836 (0.8823) time: 0.1371 data: 0.0536 max mem: 8233 +Train: [61] [ 800/6250] eta: 0:16:02 lr: 0.000045 grad: 0.1203 (0.1280) loss: 0.8835 (0.8823) time: 0.1520 data: 0.0508 max mem: 8233 +Train: [61] [ 900/6250] eta: 0:15:38 lr: 0.000045 grad: 0.1238 (0.1285) loss: 0.8825 (0.8824) time: 0.1423 data: 0.0454 max mem: 8233 +Train: [61] [1000/6250] eta: 0:15:11 lr: 0.000045 grad: 0.1250 (0.1287) loss: 0.8875 (0.8826) time: 0.1471 data: 0.0601 max mem: 8233 +Train: [61] [1100/6250] eta: 0:14:48 lr: 0.000045 grad: 0.1234 (0.1290) loss: 0.8771 (0.8825) time: 0.1377 data: 0.0448 max mem: 8233 +Train: [61] [1200/6250] eta: 0:14:42 lr: 0.000045 grad: 0.1215 (0.1290) loss: 0.8808 (0.8826) time: 0.3498 data: 0.2630 max mem: 8233 +Train: [61] [1300/6250] eta: 0:14:14 lr: 0.000045 grad: 0.1311 (0.1294) loss: 0.8853 (0.8826) time: 0.1513 data: 0.0547 max mem: 8233 +Train: [61] [1400/6250] eta: 0:13:53 lr: 0.000045 grad: 0.1284 (0.1299) loss: 0.8848 (0.8827) time: 0.1824 data: 0.1037 max mem: 8233 +Train: [61] [1500/6250] eta: 0:13:35 lr: 0.000045 grad: 0.1190 (0.1301) loss: 0.8855 (0.8827) time: 0.1370 data: 0.0412 max mem: 8233 +Train: [61] [1600/6250] eta: 0:13:14 lr: 0.000045 grad: 0.1239 (0.1304) loss: 0.8771 (0.8826) time: 0.1686 data: 0.0875 max mem: 8233 +Train: [61] [1700/6250] eta: 0:13:00 lr: 0.000045 grad: 0.1201 (0.1303) loss: 0.8828 (0.8827) time: 0.1659 data: 0.0871 max mem: 8233 +Train: [61] [1800/6250] eta: 0:12:43 lr: 0.000045 grad: 0.1348 (0.1304) loss: 0.8778 (0.8826) time: 0.1742 data: 0.0947 max mem: 8233 +Train: [61] [1900/6250] eta: 0:12:26 lr: 0.000045 grad: 0.1302 (0.1309) loss: 0.8875 (0.8827) time: 0.1925 data: 0.0959 max mem: 8233 +Train: [61] [2000/6250] eta: 0:12:08 lr: 0.000045 grad: 0.1281 (0.1312) loss: 0.8808 (0.8827) time: 0.1682 data: 0.0752 max mem: 8233 +Train: [61] [2100/6250] eta: 0:11:52 lr: 0.000044 grad: 0.1261 (0.1312) loss: 0.8786 (0.8828) time: 0.1677 data: 0.0731 max mem: 8233 +Train: [61] [2200/6250] eta: 0:11:35 lr: 0.000044 grad: 0.1229 (0.1311) loss: 0.8859 (0.8828) time: 0.1678 data: 0.0666 max mem: 8233 +Train: [61] [2300/6250] eta: 0:11:16 lr: 0.000044 grad: 0.1295 (0.1312) loss: 0.8781 (0.8827) time: 0.1499 data: 0.0713 max mem: 8233 +Train: [61] [2400/6250] eta: 0:10:56 lr: 0.000044 grad: 0.1212 (0.1311) loss: 0.8826 (0.8827) time: 0.1412 data: 0.0564 max mem: 8233 +Train: [61] [2500/6250] eta: 0:10:36 lr: 0.000044 grad: 0.1182 (0.1309) loss: 0.8855 (0.8828) time: 0.1465 data: 0.0548 max mem: 8233 +Train: [61] [2600/6250] eta: 0:10:17 lr: 0.000044 grad: 0.1206 (0.1307) loss: 0.8838 (0.8828) time: 0.1510 data: 0.0612 max mem: 8233 +Train: [61] [2700/6250] eta: 0:09:59 lr: 0.000044 grad: 0.1205 (0.1306) loss: 0.8836 (0.8828) time: 0.1500 data: 0.0690 max mem: 8233 +Train: [61] [2800/6250] eta: 0:09:43 lr: 0.000044 grad: 0.1147 (0.1304) loss: 0.8867 (0.8828) time: 0.1762 data: 0.0993 max mem: 8233 +Train: [61] [2900/6250] eta: 0:09:26 lr: 0.000044 grad: 0.1131 (0.1305) loss: 0.8835 (0.8828) time: 0.1568 data: 0.0859 max mem: 8233 +Train: [61] [3000/6250] eta: 0:09:12 lr: 0.000044 grad: 0.1217 (0.1305) loss: 0.8853 (0.8828) time: 0.1173 data: 0.0003 max mem: 8233 +Train: [61] [3100/6250] eta: 0:08:55 lr: 0.000044 grad: 0.1194 (0.1304) loss: 0.8844 (0.8829) time: 0.1586 data: 0.0591 max mem: 8233 +Train: [61] [3200/6250] eta: 0:08:39 lr: 0.000044 grad: 0.1208 (0.1304) loss: 0.8833 (0.8829) time: 0.1316 data: 0.0426 max mem: 8233 +Train: [61] [3300/6250] eta: 0:08:23 lr: 0.000044 grad: 0.1184 (0.1303) loss: 0.8841 (0.8829) time: 0.2046 data: 0.1223 max mem: 8233 +Train: [61] [3400/6250] eta: 0:08:06 lr: 0.000044 grad: 0.1178 (0.1302) loss: 0.8870 (0.8830) time: 0.1250 data: 0.0352 max mem: 8233 +Train: [61] [3500/6250] eta: 0:07:48 lr: 0.000044 grad: 0.1155 (0.1300) loss: 0.8856 (0.8831) time: 0.1604 data: 0.0833 max mem: 8233 +Train: [61] [3600/6250] eta: 0:07:31 lr: 0.000044 grad: 0.1213 (0.1299) loss: 0.8785 (0.8832) time: 0.1546 data: 0.0701 max mem: 8233 +Train: [61] [3700/6250] eta: 0:07:15 lr: 0.000044 grad: 0.1244 (0.1298) loss: 0.8788 (0.8831) time: 0.2391 data: 0.1557 max mem: 8233 +Train: [61] [3800/6250] eta: 0:06:57 lr: 0.000044 grad: 0.1280 (0.1299) loss: 0.8857 (0.8831) time: 0.1964 data: 0.1239 max mem: 8233 +Train: [61] [3900/6250] eta: 0:06:41 lr: 0.000044 grad: 0.1289 (0.1300) loss: 0.8813 (0.8830) time: 0.1370 data: 0.0563 max mem: 8233 +Train: [61] [4000/6250] eta: 0:06:24 lr: 0.000044 grad: 0.1266 (0.1300) loss: 0.8780 (0.8830) time: 0.1500 data: 0.0617 max mem: 8233 +Train: [61] [4100/6250] eta: 0:06:06 lr: 0.000044 grad: 0.1289 (0.1301) loss: 0.8860 (0.8830) time: 0.1561 data: 0.0762 max mem: 8233 +Train: [61] [4200/6250] eta: 0:05:49 lr: 0.000044 grad: 0.1254 (0.1301) loss: 0.8805 (0.8830) time: 0.1677 data: 0.0765 max mem: 8233 +Train: [61] [4300/6250] eta: 0:05:32 lr: 0.000044 grad: 0.1225 (0.1302) loss: 0.8831 (0.8830) time: 0.1376 data: 0.0576 max mem: 8233 +Train: [61] [4400/6250] eta: 0:05:15 lr: 0.000044 grad: 0.1190 (0.1303) loss: 0.8835 (0.8829) time: 0.1560 data: 0.0760 max mem: 8233 +Train: [61] [4500/6250] eta: 0:04:57 lr: 0.000044 grad: 0.1300 (0.1302) loss: 0.8884 (0.8830) time: 0.1420 data: 0.0564 max mem: 8233 +Train: [61] [4600/6250] eta: 0:04:39 lr: 0.000044 grad: 0.1271 (0.1302) loss: 0.8800 (0.8829) time: 0.1457 data: 0.0381 max mem: 8233 +Train: [61] [4700/6250] eta: 0:04:22 lr: 0.000044 grad: 0.1189 (0.1302) loss: 0.8840 (0.8829) time: 0.1560 data: 0.0763 max mem: 8233 +Train: [61] [4800/6250] eta: 0:04:04 lr: 0.000044 grad: 0.1238 (0.1301) loss: 0.8789 (0.8829) time: 0.1675 data: 0.0843 max mem: 8233 +Train: [61] [4900/6250] eta: 0:03:47 lr: 0.000044 grad: 0.1188 (0.1302) loss: 0.8743 (0.8829) time: 0.1641 data: 0.0837 max mem: 8233 +Train: [61] [5000/6250] eta: 0:03:31 lr: 0.000044 grad: 0.1219 (0.1301) loss: 0.8879 (0.8829) time: 0.1370 data: 0.0475 max mem: 8233 +Train: [61] [5100/6250] eta: 0:03:14 lr: 0.000044 grad: 0.1280 (0.1300) loss: 0.8865 (0.8829) time: 0.1704 data: 0.0941 max mem: 8233 +Train: [61] [5200/6250] eta: 0:02:57 lr: 0.000044 grad: 0.1298 (0.1300) loss: 0.8811 (0.8829) time: 0.1786 data: 0.0929 max mem: 8233 +Train: [61] [5300/6250] eta: 0:02:40 lr: 0.000043 grad: 0.1297 (0.1300) loss: 0.8808 (0.8829) time: 0.1897 data: 0.0802 max mem: 8233 +Train: [61] [5400/6250] eta: 0:02:23 lr: 0.000043 grad: 0.1369 (0.1301) loss: 0.8845 (0.8829) time: 0.1576 data: 0.0755 max mem: 8233 +Train: [61] [5500/6250] eta: 0:02:06 lr: 0.000043 grad: 0.1284 (0.1302) loss: 0.8812 (0.8828) time: 0.1526 data: 0.0727 max mem: 8233 +Train: [61] [5600/6250] eta: 0:01:49 lr: 0.000043 grad: 0.1234 (0.1301) loss: 0.8807 (0.8828) time: 0.1498 data: 0.0700 max mem: 8233 +Train: [61] [5700/6250] eta: 0:01:32 lr: 0.000043 grad: 0.1334 (0.1301) loss: 0.8800 (0.8827) time: 0.1632 data: 0.0773 max mem: 8233 +Train: [61] [5800/6250] eta: 0:01:15 lr: 0.000043 grad: 0.1248 (0.1302) loss: 0.8823 (0.8827) time: 0.1381 data: 0.0537 max mem: 8233 +Train: [61] [5900/6250] eta: 0:00:58 lr: 0.000043 grad: 0.1299 (0.1303) loss: 0.8728 (0.8826) time: 0.1387 data: 0.0576 max mem: 8233 +Train: [61] [6000/6250] eta: 0:00:41 lr: 0.000043 grad: 0.1213 (0.1303) loss: 0.8746 (0.8825) time: 0.1471 data: 0.0638 max mem: 8233 +Train: [61] [6100/6250] eta: 0:00:25 lr: 0.000043 grad: 0.1230 (0.1304) loss: 0.8806 (0.8824) time: 0.1690 data: 0.1044 max mem: 8233 +Train: [61] [6200/6250] eta: 0:00:08 lr: 0.000043 grad: 0.1366 (0.1305) loss: 0.8830 (0.8823) time: 0.1244 data: 0.0004 max mem: 8233 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.1364 (0.1306) loss: 0.8756 (0.8823) time: 0.1646 data: 0.0806 max mem: 8233 +Train: [61] Total time: 0:17:37 (0.1691 s / it) +Averaged stats: lr: 0.000043 grad: 0.1364 (0.1306) loss: 0.8756 (0.8823) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:04:56 loss: 0.8983 (0.8983) time: 4.7897 data: 4.7489 max mem: 8233 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8929 (0.8909) time: 0.1941 data: 0.1737 max mem: 8233 +Eval (hcp-train-subset): [61] Total time: 0:00:17 (0.2803 s / it) +Averaged stats (hcp-train-subset): loss: 0.8929 (0.8909) +Eval (hcp-val): [61] [ 0/62] eta: 0:05:33 loss: 0.8852 (0.8852) time: 5.3715 data: 5.3404 max mem: 8233 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8876 (0.8886) time: 0.0899 data: 0.0694 max mem: 8233 +Eval (hcp-val): [61] Total time: 0:00:15 (0.2562 s / it) +Averaged stats (hcp-val): loss: 0.8876 (0.8886) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 12:17:33 lr: 0.000043 grad: 0.1277 (0.1277) loss: 0.9226 (0.9226) time: 7.0806 data: 6.9653 max mem: 8233 +Train: [62] [ 100/6250] eta: 0:23:33 lr: 0.000043 grad: 0.1265 (0.1356) loss: 0.8939 (0.8851) time: 0.1828 data: 0.0809 max mem: 8233 +Train: [62] [ 200/6250] eta: 0:20:18 lr: 0.000043 grad: 0.1177 (0.1325) loss: 0.8831 (0.8835) time: 0.1674 data: 0.0565 max mem: 8233 +Train: [62] [ 300/6250] eta: 0:19:36 lr: 0.000043 grad: 0.1150 (0.1284) loss: 0.8889 (0.8852) time: 0.2070 data: 0.0974 max mem: 8233 +Train: [62] [ 400/6250] eta: 0:18:27 lr: 0.000043 grad: 0.1199 (0.1279) loss: 0.8810 (0.8852) time: 0.1683 data: 0.0628 max mem: 8233 +Train: [62] [ 500/6250] eta: 0:17:40 lr: 0.000043 grad: 0.1347 (0.1271) loss: 0.8888 (0.8848) time: 0.1624 data: 0.0677 max mem: 8233 +Train: [62] [ 600/6250] eta: 0:17:01 lr: 0.000043 grad: 0.1279 (0.1271) loss: 0.8923 (0.8848) time: 0.1445 data: 0.0466 max mem: 8233 +Train: [62] [ 700/6250] eta: 0:16:31 lr: 0.000043 grad: 0.1199 (0.1270) loss: 0.8920 (0.8848) time: 0.1507 data: 0.0549 max mem: 8233 +Train: [62] [ 800/6250] eta: 0:16:05 lr: 0.000043 grad: 0.1214 (0.1265) loss: 0.8826 (0.8846) time: 0.1714 data: 0.0802 max mem: 8233 +Train: [62] [ 900/6250] eta: 0:15:41 lr: 0.000043 grad: 0.1209 (0.1261) loss: 0.8863 (0.8848) time: 0.1587 data: 0.0767 max mem: 8233 +Train: [62] [1000/6250] eta: 0:15:31 lr: 0.000043 grad: 0.1177 (0.1259) loss: 0.8812 (0.8845) time: 0.2774 data: 0.1999 max mem: 8233 +Train: [62] [1100/6250] eta: 0:15:01 lr: 0.000043 grad: 0.1196 (0.1256) loss: 0.8843 (0.8844) time: 0.1479 data: 0.0628 max mem: 8233 +Train: [62] [1200/6250] eta: 0:14:43 lr: 0.000043 grad: 0.1192 (0.1253) loss: 0.8813 (0.8844) time: 0.1702 data: 0.0866 max mem: 8233 +Train: [62] [1300/6250] eta: 0:14:23 lr: 0.000043 grad: 0.1216 (0.1255) loss: 0.8828 (0.8844) time: 0.1728 data: 0.0950 max mem: 8233 +Train: [62] [1400/6250] eta: 0:14:03 lr: 0.000043 grad: 0.1221 (0.1254) loss: 0.8848 (0.8843) time: 0.1739 data: 0.0853 max mem: 8233 +Train: [62] [1500/6250] eta: 0:13:40 lr: 0.000043 grad: 0.1256 (0.1256) loss: 0.8846 (0.8842) time: 0.1392 data: 0.0649 max mem: 8233 +Train: [62] [1600/6250] eta: 0:13:22 lr: 0.000043 grad: 0.1201 (0.1259) loss: 0.8781 (0.8839) time: 0.1774 data: 0.0979 max mem: 8233 +Train: [62] [1700/6250] eta: 0:13:05 lr: 0.000043 grad: 0.1221 (0.1259) loss: 0.8787 (0.8837) time: 0.1795 data: 0.1030 max mem: 8233 +Train: [62] [1800/6250] eta: 0:12:48 lr: 0.000043 grad: 0.1231 (0.1260) loss: 0.8868 (0.8836) time: 0.1500 data: 0.0741 max mem: 8233 +Train: [62] [1900/6250] eta: 0:12:28 lr: 0.000043 grad: 0.1229 (0.1262) loss: 0.8796 (0.8833) time: 0.1772 data: 0.0979 max mem: 8233 +Train: [62] [2000/6250] eta: 0:12:10 lr: 0.000043 grad: 0.1234 (0.1265) loss: 0.8789 (0.8831) time: 0.1730 data: 0.0894 max mem: 8233 +Train: [62] [2100/6250] eta: 0:11:53 lr: 0.000043 grad: 0.1269 (0.1265) loss: 0.8788 (0.8829) time: 0.1873 data: 0.1058 max mem: 8233 +Train: [62] [2200/6250] eta: 0:11:32 lr: 0.000042 grad: 0.1203 (0.1266) loss: 0.8852 (0.8828) time: 0.1506 data: 0.0692 max mem: 8233 +Train: [62] [2300/6250] eta: 0:11:12 lr: 0.000042 grad: 0.1192 (0.1267) loss: 0.8839 (0.8827) time: 0.1354 data: 0.0539 max mem: 8233 +Train: [62] [2400/6250] eta: 0:10:52 lr: 0.000042 grad: 0.1234 (0.1268) loss: 0.8779 (0.8826) time: 0.1524 data: 0.0705 max mem: 8233 +Train: [62] [2500/6250] eta: 0:10:33 lr: 0.000042 grad: 0.1234 (0.1269) loss: 0.8810 (0.8826) time: 0.1358 data: 0.0465 max mem: 8233 +Train: [62] [2600/6250] eta: 0:10:16 lr: 0.000042 grad: 0.1304 (0.1270) loss: 0.8829 (0.8825) time: 0.1988 data: 0.1269 max mem: 8233 +Train: [62] [2700/6250] eta: 0:10:01 lr: 0.000042 grad: 0.1201 (0.1271) loss: 0.8816 (0.8824) time: 0.1809 data: 0.1084 max mem: 8233 +Train: [62] [2800/6250] eta: 0:09:45 lr: 0.000042 grad: 0.1261 (0.1272) loss: 0.8797 (0.8824) time: 0.1649 data: 0.0897 max mem: 8233 +Train: [62] [2900/6250] eta: 0:09:29 lr: 0.000042 grad: 0.1229 (0.1271) loss: 0.8823 (0.8824) time: 0.1838 data: 0.1072 max mem: 8233 +Train: [62] [3000/6250] eta: 0:09:13 lr: 0.000042 grad: 0.1280 (0.1272) loss: 0.8791 (0.8824) time: 0.1482 data: 0.0722 max mem: 8233 +Train: [62] [3100/6250] eta: 0:08:54 lr: 0.000042 grad: 0.1297 (0.1272) loss: 0.8796 (0.8823) time: 0.1464 data: 0.0501 max mem: 8233 +Train: [62] [3200/6250] eta: 0:08:35 lr: 0.000042 grad: 0.1239 (0.1273) loss: 0.8806 (0.8823) time: 0.1412 data: 0.0498 max mem: 8233 +Train: [62] [3300/6250] eta: 0:08:18 lr: 0.000042 grad: 0.1263 (0.1274) loss: 0.8812 (0.8823) time: 0.1467 data: 0.0661 max mem: 8233 +Train: [62] [3400/6250] eta: 0:08:00 lr: 0.000042 grad: 0.1337 (0.1275) loss: 0.8801 (0.8822) time: 0.1554 data: 0.0732 max mem: 8233 +Train: [62] [3500/6250] eta: 0:07:44 lr: 0.000042 grad: 0.1279 (0.1277) loss: 0.8835 (0.8822) time: 0.1394 data: 0.0500 max mem: 8233 +Train: [62] [3600/6250] eta: 0:07:26 lr: 0.000042 grad: 0.1203 (0.1278) loss: 0.8826 (0.8822) time: 0.1417 data: 0.0565 max mem: 8233 +Train: [62] [3700/6250] eta: 0:07:08 lr: 0.000042 grad: 0.1273 (0.1279) loss: 0.8777 (0.8821) time: 0.1593 data: 0.0738 max mem: 8233 +Train: [62] [3800/6250] eta: 0:06:52 lr: 0.000042 grad: 0.1268 (0.1279) loss: 0.8724 (0.8821) time: 0.1278 data: 0.0162 max mem: 8233 +Train: [62] [3900/6250] eta: 0:06:35 lr: 0.000042 grad: 0.1299 (0.1281) loss: 0.8846 (0.8821) time: 0.1324 data: 0.0496 max mem: 8233 +Train: [62] [4000/6250] eta: 0:06:18 lr: 0.000042 grad: 0.1261 (0.1282) loss: 0.8837 (0.8821) time: 0.1803 data: 0.1049 max mem: 8233 +Train: [62] [4100/6250] eta: 0:06:00 lr: 0.000042 grad: 0.1306 (0.1283) loss: 0.8793 (0.8821) time: 0.1696 data: 0.0855 max mem: 8233 +Train: [62] [4200/6250] eta: 0:05:43 lr: 0.000042 grad: 0.1242 (0.1284) loss: 0.8830 (0.8821) time: 0.1618 data: 0.0703 max mem: 8233 +Train: [62] [4300/6250] eta: 0:05:26 lr: 0.000042 grad: 0.1304 (0.1285) loss: 0.8810 (0.8821) time: 0.1413 data: 0.0642 max mem: 8233 +Train: [62] [4400/6250] eta: 0:05:09 lr: 0.000042 grad: 0.1228 (0.1286) loss: 0.8829 (0.8821) time: 0.1836 data: 0.1071 max mem: 8233 +Train: [62] [4500/6250] eta: 0:04:52 lr: 0.000042 grad: 0.1340 (0.1287) loss: 0.8834 (0.8821) time: 0.1406 data: 0.0460 max mem: 8233 +Train: [62] [4600/6250] eta: 0:04:35 lr: 0.000042 grad: 0.1281 (0.1287) loss: 0.8834 (0.8822) time: 0.1398 data: 0.0425 max mem: 8233 +Train: [62] [4700/6250] eta: 0:04:18 lr: 0.000042 grad: 0.1332 (0.1288) loss: 0.8820 (0.8822) time: 0.1516 data: 0.0700 max mem: 8233 +Train: [62] [4800/6250] eta: 0:04:01 lr: 0.000042 grad: 0.1204 (0.1289) loss: 0.8855 (0.8822) time: 0.1456 data: 0.0563 max mem: 8233 +Train: [62] [4900/6250] eta: 0:03:45 lr: 0.000042 grad: 0.1299 (0.1289) loss: 0.8812 (0.8822) time: 0.1545 data: 0.0806 max mem: 8233 +Train: [62] [5000/6250] eta: 0:03:28 lr: 0.000042 grad: 0.1235 (0.1289) loss: 0.8834 (0.8822) time: 0.1418 data: 0.0502 max mem: 8233 +Train: [62] [5100/6250] eta: 0:03:12 lr: 0.000042 grad: 0.1247 (0.1288) loss: 0.8820 (0.8822) time: 0.1522 data: 0.0349 max mem: 8233 +Train: [62] [5200/6250] eta: 0:02:56 lr: 0.000042 grad: 0.1299 (0.1289) loss: 0.8844 (0.8823) time: 0.1714 data: 0.0662 max mem: 8233 +Train: [62] [5300/6250] eta: 0:02:39 lr: 0.000042 grad: 0.1175 (0.1289) loss: 0.8837 (0.8823) time: 0.1201 data: 0.0303 max mem: 8233 +Train: [62] [5400/6250] eta: 0:02:22 lr: 0.000041 grad: 0.1260 (0.1288) loss: 0.8841 (0.8823) time: 0.1478 data: 0.0664 max mem: 8233 +Train: [62] [5500/6250] eta: 0:02:05 lr: 0.000041 grad: 0.1208 (0.1289) loss: 0.8816 (0.8823) time: 0.1735 data: 0.1014 max mem: 8233 +Train: [62] [5600/6250] eta: 0:01:48 lr: 0.000041 grad: 0.1218 (0.1289) loss: 0.8840 (0.8824) time: 0.1731 data: 0.0909 max mem: 8233 +Train: [62] [5700/6250] eta: 0:01:32 lr: 0.000041 grad: 0.1266 (0.1289) loss: 0.8836 (0.8824) time: 0.1560 data: 0.0615 max mem: 8233 +Train: [62] [5800/6250] eta: 0:01:15 lr: 0.000041 grad: 0.1378 (0.1289) loss: 0.8794 (0.8824) time: 0.1878 data: 0.0548 max mem: 8233 +Train: [62] [5900/6250] eta: 0:00:58 lr: 0.000041 grad: 0.1364 (0.1291) loss: 0.8861 (0.8824) time: 0.1371 data: 0.0495 max mem: 8233 +Train: [62] [6000/6250] eta: 0:00:41 lr: 0.000041 grad: 0.1241 (0.1292) loss: 0.8808 (0.8824) time: 0.1439 data: 0.0563 max mem: 8233 +Train: [62] [6100/6250] eta: 0:00:25 lr: 0.000041 grad: 0.1316 (0.1293) loss: 0.8841 (0.8824) time: 0.1756 data: 0.0921 max mem: 8233 +Train: [62] [6200/6250] eta: 0:00:08 lr: 0.000041 grad: 0.1294 (0.1294) loss: 0.8837 (0.8825) time: 0.1637 data: 0.0779 max mem: 8233 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1232 (0.1294) loss: 0.8837 (0.8825) time: 0.2345 data: 0.1446 max mem: 8233 +Train: [62] Total time: 0:17:29 (0.1679 s / it) +Averaged stats: lr: 0.000041 grad: 0.1232 (0.1294) loss: 0.8837 (0.8825) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:04:28 loss: 0.9011 (0.9011) time: 4.3311 data: 4.2512 max mem: 8233 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8897 (0.8909) time: 0.1131 data: 0.0924 max mem: 8233 +Eval (hcp-train-subset): [62] Total time: 0:00:14 (0.2402 s / it) +Averaged stats (hcp-train-subset): loss: 0.8897 (0.8909) +Eval (hcp-val): [62] [ 0/62] eta: 0:05:45 loss: 0.8853 (0.8853) time: 5.5781 data: 5.5525 max mem: 8233 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8875 (0.8883) time: 0.1314 data: 0.1107 max mem: 8233 +Eval (hcp-val): [62] Total time: 0:00:15 (0.2434 s / it) +Averaged stats (hcp-val): loss: 0.8875 (0.8883) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 12:00:22 lr: 0.000041 grad: 0.1593 (0.1593) loss: 0.8519 (0.8519) time: 6.9156 data: 6.7349 max mem: 8233 +Train: [63] [ 100/6250] eta: 0:24:21 lr: 0.000041 grad: 0.1344 (0.1501) loss: 0.8789 (0.8839) time: 0.1926 data: 0.0718 max mem: 8233 +Train: [63] [ 200/6250] eta: 0:20:43 lr: 0.000041 grad: 0.1393 (0.1450) loss: 0.8739 (0.8814) time: 0.1881 data: 0.0902 max mem: 8233 +Train: [63] [ 300/6250] eta: 0:19:50 lr: 0.000041 grad: 0.1270 (0.1422) loss: 0.8766 (0.8797) time: 0.1570 data: 0.0482 max mem: 8233 +Train: [63] [ 400/6250] eta: 0:18:47 lr: 0.000041 grad: 0.1245 (0.1403) loss: 0.8804 (0.8790) time: 0.1764 data: 0.0818 max mem: 8233 +Train: [63] [ 500/6250] eta: 0:17:53 lr: 0.000041 grad: 0.1270 (0.1389) loss: 0.8793 (0.8790) time: 0.1669 data: 0.0761 max mem: 8233 +Train: [63] [ 600/6250] eta: 0:17:11 lr: 0.000041 grad: 0.1303 (0.1385) loss: 0.8773 (0.8797) time: 0.1445 data: 0.0522 max mem: 8233 +Train: [63] [ 700/6250] eta: 0:16:40 lr: 0.000041 grad: 0.1380 (0.1380) loss: 0.8839 (0.8800) time: 0.1785 data: 0.0851 max mem: 8233 +Train: [63] [ 800/6250] eta: 0:16:14 lr: 0.000041 grad: 0.1178 (0.1375) loss: 0.8850 (0.8802) time: 0.1560 data: 0.0620 max mem: 8233 +Train: [63] [ 900/6250] eta: 0:15:51 lr: 0.000041 grad: 0.1296 (0.1367) loss: 0.8784 (0.8802) time: 0.1814 data: 0.0865 max mem: 8233 +Train: [63] [1000/6250] eta: 0:15:27 lr: 0.000041 grad: 0.1273 (0.1359) loss: 0.8835 (0.8804) time: 0.1898 data: 0.1043 max mem: 8233 +Train: [63] [1100/6250] eta: 0:15:02 lr: 0.000041 grad: 0.1242 (0.1359) loss: 0.8816 (0.8802) time: 0.1163 data: 0.0004 max mem: 8233 +Train: [63] [1200/6250] eta: 0:14:40 lr: 0.000041 grad: 0.1363 (0.1358) loss: 0.8750 (0.8802) time: 0.1358 data: 0.0594 max mem: 8233 +Train: [63] [1300/6250] eta: 0:14:18 lr: 0.000041 grad: 0.1305 (0.1355) loss: 0.8805 (0.8801) time: 0.1725 data: 0.0818 max mem: 8233 +Train: [63] [1400/6250] eta: 0:13:56 lr: 0.000041 grad: 0.1297 (0.1352) loss: 0.8814 (0.8802) time: 0.1755 data: 0.0942 max mem: 8233 +Train: [63] [1500/6250] eta: 0:13:35 lr: 0.000041 grad: 0.1290 (0.1350) loss: 0.8824 (0.8803) time: 0.1506 data: 0.0683 max mem: 8233 +Train: [63] [1600/6250] eta: 0:13:21 lr: 0.000041 grad: 0.1339 (0.1349) loss: 0.8862 (0.8804) time: 0.2413 data: 0.1602 max mem: 8233 +Train: [63] [1700/6250] eta: 0:13:04 lr: 0.000041 grad: 0.1268 (0.1351) loss: 0.8825 (0.8804) time: 0.1100 data: 0.0169 max mem: 8233 +Train: [63] [1800/6250] eta: 0:12:46 lr: 0.000041 grad: 0.1374 (0.1353) loss: 0.8822 (0.8805) time: 0.1754 data: 0.0941 max mem: 8233 +Train: [63] [1900/6250] eta: 0:12:25 lr: 0.000041 grad: 0.1359 (0.1353) loss: 0.8807 (0.8806) time: 0.1470 data: 0.0696 max mem: 8233 +Train: [63] [2000/6250] eta: 0:12:06 lr: 0.000041 grad: 0.1250 (0.1351) loss: 0.8845 (0.8806) time: 0.1812 data: 0.1115 max mem: 8233 +Train: [63] [2100/6250] eta: 0:11:49 lr: 0.000041 grad: 0.1281 (0.1351) loss: 0.8788 (0.8807) time: 0.2078 data: 0.1144 max mem: 8233 +Train: [63] [2200/6250] eta: 0:11:31 lr: 0.000041 grad: 0.1283 (0.1350) loss: 0.8823 (0.8808) time: 0.1693 data: 0.0908 max mem: 8233 +Train: [63] [2300/6250] eta: 0:11:11 lr: 0.000041 grad: 0.1298 (0.1351) loss: 0.8836 (0.8808) time: 0.1585 data: 0.0738 max mem: 8233 +Train: [63] [2400/6250] eta: 0:10:51 lr: 0.000040 grad: 0.1310 (0.1350) loss: 0.8817 (0.8809) time: 0.1440 data: 0.0686 max mem: 8233 +Train: [63] [2500/6250] eta: 0:10:33 lr: 0.000040 grad: 0.1320 (0.1350) loss: 0.8839 (0.8810) time: 0.1671 data: 0.0897 max mem: 8233 +Train: [63] [2600/6250] eta: 0:10:18 lr: 0.000040 grad: 0.1269 (0.1351) loss: 0.8830 (0.8810) time: 0.1733 data: 0.0829 max mem: 8233 +Train: [63] [2700/6250] eta: 0:10:01 lr: 0.000040 grad: 0.1221 (0.1350) loss: 0.8844 (0.8811) time: 0.1795 data: 0.1107 max mem: 8233 +Train: [63] [2800/6250] eta: 0:09:45 lr: 0.000040 grad: 0.1235 (0.1350) loss: 0.8836 (0.8813) time: 0.1725 data: 0.0970 max mem: 8233 +Train: [63] [2900/6250] eta: 0:09:32 lr: 0.000040 grad: 0.1329 (0.1350) loss: 0.8840 (0.8813) time: 0.2031 data: 0.1408 max mem: 8233 +Train: [63] [3000/6250] eta: 0:09:17 lr: 0.000040 grad: 0.1281 (0.1350) loss: 0.8804 (0.8814) time: 0.1479 data: 0.0695 max mem: 8233 +Train: [63] [3100/6250] eta: 0:09:00 lr: 0.000040 grad: 0.1349 (0.1349) loss: 0.8872 (0.8814) time: 0.1171 data: 0.0350 max mem: 8233 +Train: [63] [3200/6250] eta: 0:08:43 lr: 0.000040 grad: 0.1209 (0.1349) loss: 0.8829 (0.8814) time: 0.1670 data: 0.0913 max mem: 8233 +Train: [63] [3300/6250] eta: 0:08:26 lr: 0.000040 grad: 0.1247 (0.1350) loss: 0.8734 (0.8814) time: 0.1440 data: 0.0657 max mem: 8233 +Train: [63] [3400/6250] eta: 0:08:09 lr: 0.000040 grad: 0.1310 (0.1351) loss: 0.8832 (0.8814) time: 0.2031 data: 0.1191 max mem: 8233 +Train: [63] [3500/6250] eta: 0:07:53 lr: 0.000040 grad: 0.1339 (0.1351) loss: 0.8833 (0.8814) time: 0.2147 data: 0.0974 max mem: 8233 +Train: [63] [3600/6250] eta: 0:07:41 lr: 0.000040 grad: 0.1328 (0.1352) loss: 0.8797 (0.8813) time: 0.1288 data: 0.0319 max mem: 8233 +Train: [63] [3700/6250] eta: 0:07:22 lr: 0.000040 grad: 0.1229 (0.1351) loss: 0.8799 (0.8813) time: 0.1580 data: 0.0607 max mem: 8233 +Train: [63] [3800/6250] eta: 0:07:03 lr: 0.000040 grad: 0.1408 (0.1353) loss: 0.8758 (0.8811) time: 0.1035 data: 0.0096 max mem: 8233 +Train: [63] [3900/6250] eta: 0:06:45 lr: 0.000040 grad: 0.1341 (0.1352) loss: 0.8855 (0.8811) time: 0.1674 data: 0.0917 max mem: 8233 +Train: [63] [4000/6250] eta: 0:06:28 lr: 0.000040 grad: 0.1264 (0.1352) loss: 0.8843 (0.8811) time: 0.1516 data: 0.0710 max mem: 8233 +Train: [63] [4100/6250] eta: 0:06:10 lr: 0.000040 grad: 0.1240 (0.1352) loss: 0.8798 (0.8810) time: 0.1488 data: 0.0664 max mem: 8233 +Train: [63] [4200/6250] eta: 0:05:52 lr: 0.000040 grad: 0.1222 (0.1352) loss: 0.8831 (0.8809) time: 0.1747 data: 0.0874 max mem: 8233 +Train: [63] [4300/6250] eta: 0:05:35 lr: 0.000040 grad: 0.1314 (0.1353) loss: 0.8806 (0.8808) time: 0.1659 data: 0.0739 max mem: 8233 +Train: [63] [4400/6250] eta: 0:05:17 lr: 0.000040 grad: 0.1357 (0.1355) loss: 0.8747 (0.8807) time: 0.1516 data: 0.0575 max mem: 8233 +Train: [63] [4500/6250] eta: 0:04:59 lr: 0.000040 grad: 0.1286 (0.1355) loss: 0.8693 (0.8806) time: 0.1391 data: 0.0483 max mem: 8233 +Train: [63] [4600/6250] eta: 0:04:42 lr: 0.000040 grad: 0.1336 (0.1356) loss: 0.8766 (0.8805) time: 0.1251 data: 0.0315 max mem: 8233 +Train: [63] [4700/6250] eta: 0:04:24 lr: 0.000040 grad: 0.1362 (0.1357) loss: 0.8695 (0.8804) time: 0.1549 data: 0.0565 max mem: 8233 +Train: [63] [4800/6250] eta: 0:04:08 lr: 0.000040 grad: 0.1311 (0.1358) loss: 0.8788 (0.8803) time: 0.1738 data: 0.0990 max mem: 8233 +Train: [63] [4900/6250] eta: 0:03:50 lr: 0.000040 grad: 0.1288 (0.1357) loss: 0.8752 (0.8803) time: 0.2041 data: 0.1263 max mem: 8233 +Train: [63] [5000/6250] eta: 0:03:34 lr: 0.000040 grad: 0.1319 (0.1358) loss: 0.8753 (0.8802) time: 0.2240 data: 0.1353 max mem: 8233 +Train: [63] [5100/6250] eta: 0:03:17 lr: 0.000040 grad: 0.1312 (0.1358) loss: 0.8773 (0.8802) time: 0.3351 data: 0.2469 max mem: 8233 +Train: [63] [5200/6250] eta: 0:03:00 lr: 0.000040 grad: 0.1400 (0.1359) loss: 0.8705 (0.8801) time: 0.1372 data: 0.0219 max mem: 8233 +Train: [63] [5300/6250] eta: 0:02:43 lr: 0.000040 grad: 0.1306 (0.1359) loss: 0.8767 (0.8800) time: 0.2471 data: 0.1305 max mem: 8233 +Train: [63] [5400/6250] eta: 0:02:25 lr: 0.000040 grad: 0.1297 (0.1360) loss: 0.8718 (0.8799) time: 0.1797 data: 0.0933 max mem: 8233 +Train: [63] [5500/6250] eta: 0:02:08 lr: 0.000040 grad: 0.1348 (0.1361) loss: 0.8766 (0.8799) time: 0.1493 data: 0.0602 max mem: 8233 +Train: [63] [5600/6250] eta: 0:01:51 lr: 0.000039 grad: 0.1339 (0.1360) loss: 0.8793 (0.8799) time: 0.1357 data: 0.0523 max mem: 8233 +Train: [63] [5700/6250] eta: 0:01:33 lr: 0.000039 grad: 0.1322 (0.1360) loss: 0.8750 (0.8799) time: 0.1667 data: 0.0861 max mem: 8233 +Train: [63] [5800/6250] eta: 0:01:16 lr: 0.000039 grad: 0.1382 (0.1361) loss: 0.8843 (0.8798) time: 0.1782 data: 0.0830 max mem: 8233 +Train: [63] [5900/6250] eta: 0:00:59 lr: 0.000039 grad: 0.1309 (0.1361) loss: 0.8833 (0.8799) time: 0.0958 data: 0.0003 max mem: 8233 +Train: [63] [6000/6250] eta: 0:00:42 lr: 0.000039 grad: 0.1302 (0.1360) loss: 0.8834 (0.8799) time: 0.1725 data: 0.0969 max mem: 8233 +Train: [63] [6100/6250] eta: 0:00:25 lr: 0.000039 grad: 0.1289 (0.1360) loss: 0.8769 (0.8799) time: 0.1585 data: 0.0766 max mem: 8233 +Train: [63] [6200/6250] eta: 0:00:08 lr: 0.000039 grad: 0.1268 (0.1360) loss: 0.8819 (0.8798) time: 0.1450 data: 0.0697 max mem: 8233 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1230 (0.1359) loss: 0.8785 (0.8798) time: 0.1695 data: 0.0926 max mem: 8233 +Train: [63] Total time: 0:17:50 (0.1713 s / it) +Averaged stats: lr: 0.000039 grad: 0.1230 (0.1359) loss: 0.8785 (0.8798) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:03:51 loss: 0.9004 (0.9004) time: 3.7395 data: 3.6593 max mem: 8233 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8893 (0.8905) time: 0.1133 data: 0.0927 max mem: 8233 +Eval (hcp-train-subset): [63] Total time: 0:00:15 (0.2453 s / it) +Averaged stats (hcp-train-subset): loss: 0.8893 (0.8905) +Eval (hcp-val): [63] [ 0/62] eta: 0:06:18 loss: 0.8853 (0.8853) time: 6.1043 data: 6.0788 max mem: 8233 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8862 (0.8880) time: 0.0997 data: 0.0763 max mem: 8233 +Eval (hcp-val): [63] Total time: 0:00:14 (0.2401 s / it) +Averaged stats (hcp-val): loss: 0.8862 (0.8880) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 12:13:09 lr: 0.000039 grad: 0.1632 (0.1632) loss: 0.9037 (0.9037) time: 7.0383 data: 6.9357 max mem: 8233 +Train: [64] [ 100/6250] eta: 0:23:07 lr: 0.000039 grad: 0.1327 (0.1462) loss: 0.8820 (0.8830) time: 0.1823 data: 0.0844 max mem: 8233 +Train: [64] [ 200/6250] eta: 0:20:31 lr: 0.000039 grad: 0.1328 (0.1425) loss: 0.8808 (0.8809) time: 0.2025 data: 0.0966 max mem: 8233 +Train: [64] [ 300/6250] eta: 0:19:11 lr: 0.000039 grad: 0.1266 (0.1402) loss: 0.8781 (0.8797) time: 0.1674 data: 0.0722 max mem: 8233 +Train: [64] [ 400/6250] eta: 0:18:33 lr: 0.000039 grad: 0.1283 (0.1384) loss: 0.8851 (0.8800) time: 0.1736 data: 0.0798 max mem: 8233 +Train: [64] [ 500/6250] eta: 0:17:57 lr: 0.000039 grad: 0.1258 (0.1368) loss: 0.8820 (0.8809) time: 0.1793 data: 0.0773 max mem: 8233 +Train: [64] [ 600/6250] eta: 0:17:13 lr: 0.000039 grad: 0.1193 (0.1358) loss: 0.8811 (0.8812) time: 0.1722 data: 0.0650 max mem: 8233 +Train: [64] [ 700/6250] eta: 0:16:39 lr: 0.000039 grad: 0.1266 (0.1353) loss: 0.8827 (0.8813) time: 0.1578 data: 0.0603 max mem: 8233 +Train: [64] [ 800/6250] eta: 0:16:08 lr: 0.000039 grad: 0.1210 (0.1342) loss: 0.8885 (0.8820) time: 0.1636 data: 0.0777 max mem: 8233 +Train: [64] [ 900/6250] eta: 0:15:42 lr: 0.000039 grad: 0.1262 (0.1339) loss: 0.8872 (0.8824) time: 0.1648 data: 0.0762 max mem: 8233 +Train: [64] [1000/6250] eta: 0:15:35 lr: 0.000039 grad: 0.1177 (0.1334) loss: 0.8827 (0.8826) time: 0.2007 data: 0.1132 max mem: 8233 +Train: [64] [1100/6250] eta: 0:15:24 lr: 0.000039 grad: 0.1306 (0.1331) loss: 0.8789 (0.8828) time: 0.1681 data: 0.0620 max mem: 8233 +Train: [64] [1200/6250] eta: 0:15:04 lr: 0.000039 grad: 0.1221 (0.1329) loss: 0.8875 (0.8829) time: 0.1528 data: 0.0537 max mem: 8233 +Train: [64] [1300/6250] eta: 0:14:45 lr: 0.000039 grad: 0.1219 (0.1325) loss: 0.8875 (0.8829) time: 0.2350 data: 0.1595 max mem: 8233 +Train: [64] [1400/6250] eta: 0:14:25 lr: 0.000039 grad: 0.1204 (0.1325) loss: 0.8853 (0.8830) time: 0.1140 data: 0.0005 max mem: 8233 +Train: [64] [1500/6250] eta: 0:14:01 lr: 0.000039 grad: 0.1197 (0.1323) loss: 0.8866 (0.8830) time: 0.1083 data: 0.0004 max mem: 8233 +Train: [64] [1600/6250] eta: 0:13:40 lr: 0.000039 grad: 0.1236 (0.1321) loss: 0.8851 (0.8831) time: 0.1772 data: 0.0979 max mem: 8233 +Train: [64] [1700/6250] eta: 0:13:23 lr: 0.000039 grad: 0.1332 (0.1323) loss: 0.8835 (0.8832) time: 0.2452 data: 0.1599 max mem: 8233 +Train: [64] [1800/6250] eta: 0:13:04 lr: 0.000039 grad: 0.1267 (0.1325) loss: 0.8869 (0.8833) time: 0.1709 data: 0.0933 max mem: 8233 +Train: [64] [1900/6250] eta: 0:12:43 lr: 0.000039 grad: 0.1282 (0.1328) loss: 0.8876 (0.8833) time: 0.1328 data: 0.0509 max mem: 8233 +Train: [64] [2000/6250] eta: 0:12:24 lr: 0.000039 grad: 0.1271 (0.1329) loss: 0.8855 (0.8834) time: 0.1347 data: 0.0441 max mem: 8233 +Train: [64] [2100/6250] eta: 0:12:06 lr: 0.000039 grad: 0.1220 (0.1330) loss: 0.8806 (0.8833) time: 0.1546 data: 0.0732 max mem: 8233 +Train: [64] [2200/6250] eta: 0:11:48 lr: 0.000039 grad: 0.1296 (0.1330) loss: 0.8853 (0.8833) time: 0.1645 data: 0.0890 max mem: 8233 +Train: [64] [2300/6250] eta: 0:11:29 lr: 0.000039 grad: 0.1285 (0.1330) loss: 0.8842 (0.8833) time: 0.1630 data: 0.0798 max mem: 8233 +Train: [64] [2400/6250] eta: 0:11:09 lr: 0.000039 grad: 0.1262 (0.1330) loss: 0.8862 (0.8833) time: 0.1397 data: 0.0426 max mem: 8233 +Train: [64] [2500/6250] eta: 0:10:50 lr: 0.000039 grad: 0.1338 (0.1332) loss: 0.8821 (0.8833) time: 0.1474 data: 0.0702 max mem: 8233 +Train: [64] [2600/6250] eta: 0:10:32 lr: 0.000039 grad: 0.1317 (0.1332) loss: 0.8817 (0.8833) time: 0.1752 data: 0.0899 max mem: 8233 +Train: [64] [2700/6250] eta: 0:10:15 lr: 0.000038 grad: 0.1291 (0.1332) loss: 0.8803 (0.8832) time: 0.1700 data: 0.0998 max mem: 8233 +Train: [64] [2800/6250] eta: 0:09:58 lr: 0.000038 grad: 0.1252 (0.1334) loss: 0.8837 (0.8832) time: 0.1758 data: 0.1038 max mem: 8233 +Train: [64] [2900/6250] eta: 0:09:39 lr: 0.000038 grad: 0.1266 (0.1335) loss: 0.8820 (0.8832) time: 0.1356 data: 0.0549 max mem: 8233 +Train: [64] [3000/6250] eta: 0:09:22 lr: 0.000038 grad: 0.1284 (0.1336) loss: 0.8798 (0.8832) time: 0.1494 data: 0.0576 max mem: 8233 +Train: [64] [3100/6250] eta: 0:09:08 lr: 0.000038 grad: 0.1284 (0.1336) loss: 0.8759 (0.8831) time: 0.2204 data: 0.1339 max mem: 8233 +Train: [64] [3200/6250] eta: 0:08:49 lr: 0.000038 grad: 0.1263 (0.1336) loss: 0.8824 (0.8830) time: 0.1235 data: 0.0246 max mem: 8233 +Train: [64] [3300/6250] eta: 0:08:33 lr: 0.000038 grad: 0.1275 (0.1339) loss: 0.8803 (0.8829) time: 0.1525 data: 0.0327 max mem: 8233 +Train: [64] [3400/6250] eta: 0:08:16 lr: 0.000038 grad: 0.1393 (0.1341) loss: 0.8764 (0.8827) time: 0.1515 data: 0.0479 max mem: 8233 +Train: [64] [3500/6250] eta: 0:07:58 lr: 0.000038 grad: 0.1355 (0.1344) loss: 0.8815 (0.8826) time: 0.1792 data: 0.0960 max mem: 8233 +Train: [64] [3600/6250] eta: 0:07:40 lr: 0.000038 grad: 0.1308 (0.1344) loss: 0.8757 (0.8824) time: 0.1800 data: 0.0992 max mem: 8233 +Train: [64] [3700/6250] eta: 0:07:21 lr: 0.000038 grad: 0.1400 (0.1345) loss: 0.8717 (0.8822) time: 0.1618 data: 0.0861 max mem: 8233 +Train: [64] [3800/6250] eta: 0:07:04 lr: 0.000038 grad: 0.1308 (0.1346) loss: 0.8763 (0.8821) time: 0.1378 data: 0.0003 max mem: 8233 +Train: [64] [3900/6250] eta: 0:06:47 lr: 0.000038 grad: 0.1383 (0.1348) loss: 0.8759 (0.8819) time: 0.1811 data: 0.0975 max mem: 8233 +Train: [64] [4000/6250] eta: 0:06:30 lr: 0.000038 grad: 0.1372 (0.1350) loss: 0.8760 (0.8817) time: 0.1446 data: 0.0491 max mem: 8233 +Train: [64] [4100/6250] eta: 0:06:12 lr: 0.000038 grad: 0.1359 (0.1352) loss: 0.8771 (0.8816) time: 0.1670 data: 0.0821 max mem: 8233 +Train: [64] [4200/6250] eta: 0:05:54 lr: 0.000038 grad: 0.1387 (0.1353) loss: 0.8770 (0.8815) time: 0.1726 data: 0.1022 max mem: 8233 +Train: [64] [4300/6250] eta: 0:05:37 lr: 0.000038 grad: 0.1387 (0.1354) loss: 0.8770 (0.8814) time: 0.1919 data: 0.1115 max mem: 8233 +Train: [64] [4400/6250] eta: 0:05:20 lr: 0.000038 grad: 0.1320 (0.1356) loss: 0.8763 (0.8813) time: 0.2006 data: 0.1039 max mem: 8233 +Train: [64] [4500/6250] eta: 0:05:03 lr: 0.000038 grad: 0.1381 (0.1356) loss: 0.8759 (0.8812) time: 0.1208 data: 0.0030 max mem: 8233 +Train: [64] [4600/6250] eta: 0:04:46 lr: 0.000038 grad: 0.1423 (0.1356) loss: 0.8774 (0.8811) time: 0.1847 data: 0.1004 max mem: 8233 +Train: [64] [4700/6250] eta: 0:04:29 lr: 0.000038 grad: 0.1259 (0.1359) loss: 0.8764 (0.8811) time: 0.1543 data: 0.0818 max mem: 8233 +Train: [64] [4800/6250] eta: 0:04:12 lr: 0.000038 grad: 0.1438 (0.1359) loss: 0.8832 (0.8810) time: 0.1659 data: 0.0684 max mem: 8233 +Train: [64] [4900/6250] eta: 0:03:54 lr: 0.000038 grad: 0.1323 (0.1359) loss: 0.8811 (0.8810) time: 0.1536 data: 0.0661 max mem: 8233 +Train: [64] [5000/6250] eta: 0:03:36 lr: 0.000038 grad: 0.1262 (0.1361) loss: 0.8835 (0.8810) time: 0.2086 data: 0.1316 max mem: 8233 +Train: [64] [5100/6250] eta: 0:03:20 lr: 0.000038 grad: 0.1262 (0.1360) loss: 0.8866 (0.8810) time: 0.1701 data: 0.0674 max mem: 8233 +Train: [64] [5200/6250] eta: 0:03:03 lr: 0.000038 grad: 0.1322 (0.1361) loss: 0.8821 (0.8810) time: 0.3910 data: 0.2722 max mem: 8233 +Train: [64] [5300/6250] eta: 0:02:46 lr: 0.000038 grad: 0.1363 (0.1361) loss: 0.8809 (0.8810) time: 0.1179 data: 0.0133 max mem: 8233 +Train: [64] [5400/6250] eta: 0:02:28 lr: 0.000038 grad: 0.1404 (0.1361) loss: 0.8781 (0.8809) time: 0.0936 data: 0.0003 max mem: 8233 +Train: [64] [5500/6250] eta: 0:02:11 lr: 0.000038 grad: 0.1333 (0.1361) loss: 0.8762 (0.8809) time: 0.1814 data: 0.1078 max mem: 8233 +Train: [64] [5600/6250] eta: 0:01:53 lr: 0.000038 grad: 0.1281 (0.1363) loss: 0.8823 (0.8808) time: 0.1731 data: 0.0797 max mem: 8233 +Train: [64] [5700/6250] eta: 0:01:36 lr: 0.000038 grad: 0.1410 (0.1365) loss: 0.8773 (0.8808) time: 0.1256 data: 0.0286 max mem: 8233 +Train: [64] [5800/6250] eta: 0:01:18 lr: 0.000038 grad: 0.1408 (0.1366) loss: 0.8785 (0.8807) time: 0.1538 data: 0.0645 max mem: 8233 +Train: [64] [5900/6250] eta: 0:01:01 lr: 0.000037 grad: 0.1341 (0.1368) loss: 0.8720 (0.8806) time: 0.1732 data: 0.0914 max mem: 8233 +Train: [64] [6000/6250] eta: 0:00:43 lr: 0.000037 grad: 0.1275 (0.1368) loss: 0.8824 (0.8806) time: 0.1643 data: 0.0919 max mem: 8233 +Train: [64] [6100/6250] eta: 0:00:26 lr: 0.000037 grad: 0.1368 (0.1369) loss: 0.8781 (0.8805) time: 0.1595 data: 0.0815 max mem: 8233 +Train: [64] [6200/6250] eta: 0:00:08 lr: 0.000037 grad: 0.1322 (0.1370) loss: 0.8762 (0.8805) time: 0.1575 data: 0.0816 max mem: 8233 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1329 (0.1371) loss: 0.8755 (0.8804) time: 0.1690 data: 0.0943 max mem: 8233 +Train: [64] Total time: 0:18:13 (0.1750 s / it) +Averaged stats: lr: 0.000037 grad: 0.1329 (0.1371) loss: 0.8755 (0.8804) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:05:28 loss: 0.9005 (0.9005) time: 5.3028 data: 5.2763 max mem: 8233 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8889 (0.8900) time: 0.1324 data: 0.1117 max mem: 8233 +Eval (hcp-train-subset): [64] Total time: 0:00:14 (0.2388 s / it) +Averaged stats (hcp-train-subset): loss: 0.8889 (0.8900) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [64] [ 0/62] eta: 0:04:35 loss: 0.8842 (0.8842) time: 4.4392 data: 4.3805 max mem: 8233 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8864 (0.8877) time: 0.1343 data: 0.1124 max mem: 8233 +Eval (hcp-val): [64] Total time: 0:00:14 (0.2387 s / it) +Averaged stats (hcp-val): loss: 0.8864 (0.8877) +Making plots (hcp-val): example=43 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 10:48:42 lr: 0.000037 grad: nan (nan) loss: 0.8424 (0.8424) time: 6.2275 data: 6.1058 max mem: 8233 +Train: [65] [ 100/6250] eta: 0:23:32 lr: 0.000037 grad: 0.1122 (0.1280) loss: 0.8927 (0.8897) time: 0.1777 data: 0.0719 max mem: 8233 +Train: [65] [ 200/6250] eta: 0:20:32 lr: 0.000037 grad: 0.1109 (0.1239) loss: 0.8903 (0.8886) time: 0.1507 data: 0.0334 max mem: 8233 +Train: [65] [ 300/6250] eta: 0:19:48 lr: 0.000037 grad: 0.1174 (0.1249) loss: 0.8820 (0.8874) time: 0.1817 data: 0.0791 max mem: 8233 +Train: [65] [ 400/6250] eta: 0:19:03 lr: 0.000037 grad: 0.1191 (0.1241) loss: 0.8832 (0.8868) time: 0.1853 data: 0.1020 max mem: 8233 +Train: [65] [ 500/6250] eta: 0:18:02 lr: 0.000037 grad: 0.1185 (0.1251) loss: 0.8851 (0.8865) time: 0.1781 data: 0.0905 max mem: 8233 +Train: [65] [ 600/6250] eta: 0:17:37 lr: 0.000037 grad: 0.1259 (0.1254) loss: 0.8842 (0.8863) time: 0.1665 data: 0.0712 max mem: 8233 +Train: [65] [ 700/6250] eta: 0:17:03 lr: 0.000037 grad: 0.1314 (0.1263) loss: 0.8851 (0.8858) time: 0.1816 data: 0.0884 max mem: 8233 +Train: [65] [ 800/6250] eta: 0:16:35 lr: 0.000037 grad: 0.1283 (0.1275) loss: 0.8829 (0.8855) time: 0.1657 data: 0.0790 max mem: 8233 +Train: [65] [ 900/6250] eta: 0:16:08 lr: 0.000037 grad: 0.1315 (0.1280) loss: 0.8861 (0.8853) time: 0.1728 data: 0.0854 max mem: 8233 +Train: [65] [1000/6250] eta: 0:15:52 lr: 0.000037 grad: 0.1350 (0.1287) loss: 0.8772 (0.8851) time: 0.2561 data: 0.1782 max mem: 8233 +Train: [65] [1100/6250] eta: 0:15:59 lr: 0.000037 grad: 0.1282 (0.1290) loss: 0.8821 (0.8849) time: 0.1023 data: 0.0003 max mem: 8233 +Train: [65] [1200/6250] eta: 0:15:26 lr: 0.000037 grad: 0.1336 (0.1298) loss: 0.8756 (0.8845) time: 0.1613 data: 0.0660 max mem: 8233 +Train: [65] [1300/6250] eta: 0:15:15 lr: 0.000037 grad: 0.1267 (0.1301) loss: 0.8803 (0.8842) time: 0.2702 data: 0.1998 max mem: 8233 +Train: [65] [1400/6250] eta: 0:14:50 lr: 0.000037 grad: 0.1193 (0.1302) loss: 0.8779 (0.8839) time: 0.1706 data: 0.0873 max mem: 8233 +Train: [65] [1500/6250] eta: 0:14:24 lr: 0.000037 grad: 0.1354 (0.1302) loss: 0.8783 (0.8836) time: 0.1339 data: 0.0366 max mem: 8233 +Train: [65] [1600/6250] eta: 0:14:11 lr: 0.000037 grad: 0.1341 (0.1307) loss: 0.8781 (0.8833) time: 0.1895 data: 0.1177 max mem: 8233 +Train: [65] [1700/6250] eta: 0:13:59 lr: 0.000037 grad: 0.1272 (0.1308) loss: 0.8763 (0.8831) time: 0.3688 data: 0.2910 max mem: 8233 +Train: [65] [1800/6250] eta: 0:13:40 lr: 0.000037 grad: 0.1296 (0.1311) loss: 0.8817 (0.8830) time: 0.1513 data: 0.0529 max mem: 8233 +Train: [65] [1900/6250] eta: 0:13:15 lr: 0.000037 grad: 0.1289 (0.1312) loss: 0.8806 (0.8829) time: 0.1731 data: 0.0952 max mem: 8233 +Train: [65] [2000/6250] eta: 0:12:52 lr: 0.000037 grad: 0.1327 (0.1312) loss: 0.8799 (0.8828) time: 0.1556 data: 0.0758 max mem: 8233 +Train: [65] [2100/6250] eta: 0:12:34 lr: 0.000037 grad: 0.1252 (0.1315) loss: 0.8756 (0.8826) time: 0.1852 data: 0.0993 max mem: 8233 +Train: [65] [2200/6250] eta: 0:12:13 lr: 0.000037 grad: 0.1359 (0.1317) loss: 0.8774 (0.8825) time: 0.1704 data: 0.0979 max mem: 8233 +Train: [65] [2300/6250] eta: 0:11:53 lr: 0.000037 grad: 0.1278 (0.1318) loss: 0.8823 (0.8824) time: 0.1857 data: 0.0967 max mem: 8233 +Train: [65] [2400/6250] eta: 0:11:31 lr: 0.000037 grad: 0.1247 (0.1318) loss: 0.8790 (0.8824) time: 0.1497 data: 0.0734 max mem: 8233 +Train: [65] [2500/6250] eta: 0:11:10 lr: 0.000037 grad: 0.1231 (0.1319) loss: 0.8827 (0.8823) time: 0.1543 data: 0.0583 max mem: 8233 +Train: [65] [2600/6250] eta: 0:10:48 lr: 0.000037 grad: 0.1291 (0.1320) loss: 0.8790 (0.8821) time: 0.1702 data: 0.0848 max mem: 8233 +Train: [65] [2700/6250] eta: 0:10:29 lr: 0.000037 grad: 0.1269 (0.1320) loss: 0.8788 (0.8821) time: 0.1721 data: 0.1004 max mem: 8233 +Train: [65] [2800/6250] eta: 0:10:08 lr: 0.000037 grad: 0.1256 (0.1321) loss: 0.8837 (0.8820) time: 0.1615 data: 0.0829 max mem: 8233 +Train: [65] [2900/6250] eta: 0:09:51 lr: 0.000037 grad: 0.1355 (0.1324) loss: 0.8842 (0.8819) time: 0.1406 data: 0.0568 max mem: 8233 +Train: [65] [3000/6250] eta: 0:09:31 lr: 0.000036 grad: 0.1282 (0.1325) loss: 0.8771 (0.8819) time: 0.1398 data: 0.0688 max mem: 8233 +Train: [65] [3100/6250] eta: 0:09:13 lr: 0.000036 grad: 0.1257 (0.1326) loss: 0.8825 (0.8818) time: 0.1692 data: 0.0864 max mem: 8233 +Train: [65] [3200/6250] eta: 0:08:56 lr: 0.000036 grad: 0.1290 (0.1327) loss: 0.8801 (0.8817) time: 0.1187 data: 0.0007 max mem: 8233 +Train: [65] [3300/6250] eta: 0:08:37 lr: 0.000036 grad: 0.1346 (0.1327) loss: 0.8796 (0.8817) time: 0.1550 data: 0.0787 max mem: 8233 +Train: [65] [3400/6250] eta: 0:08:18 lr: 0.000036 grad: 0.1258 (0.1326) loss: 0.8872 (0.8816) time: 0.0955 data: 0.0002 max mem: 8233 +Train: [65] [3500/6250] eta: 0:08:00 lr: 0.000036 grad: 0.1280 (0.1326) loss: 0.8759 (0.8816) time: 0.1406 data: 0.0556 max mem: 8233 +Train: [65] [3600/6250] eta: 0:07:42 lr: 0.000036 grad: 0.1267 (0.1325) loss: 0.8786 (0.8814) time: 0.1489 data: 0.0658 max mem: 8233 +Train: [65] [3700/6250] eta: 0:07:23 lr: 0.000036 grad: 0.1258 (0.1326) loss: 0.8788 (0.8814) time: 0.1465 data: 0.0699 max mem: 8233 +Train: [65] [3800/6250] eta: 0:07:06 lr: 0.000036 grad: 0.1263 (0.1327) loss: 0.8812 (0.8813) time: 0.1376 data: 0.0481 max mem: 8233 +Train: [65] [3900/6250] eta: 0:06:48 lr: 0.000036 grad: 0.1321 (0.1327) loss: 0.8793 (0.8812) time: 0.1345 data: 0.0620 max mem: 8233 +Train: [65] [4000/6250] eta: 0:06:30 lr: 0.000036 grad: 0.1244 (0.1328) loss: 0.8832 (0.8812) time: 0.1918 data: 0.1121 max mem: 8233 +Train: [65] [4100/6250] eta: 0:06:13 lr: 0.000036 grad: 0.1357 (0.1328) loss: 0.8824 (0.8812) time: 0.1467 data: 0.0603 max mem: 8233 +Train: [65] [4200/6250] eta: 0:05:56 lr: 0.000036 grad: 0.1328 (0.1329) loss: 0.8841 (0.8812) time: 0.1897 data: 0.1104 max mem: 8233 +Train: [65] [4300/6250] eta: 0:05:39 lr: 0.000036 grad: 0.1272 (0.1329) loss: 0.8854 (0.8812) time: 0.1966 data: 0.1297 max mem: 8233 +Train: [65] [4400/6250] eta: 0:05:21 lr: 0.000036 grad: 0.1279 (0.1330) loss: 0.8888 (0.8813) time: 0.1515 data: 0.0854 max mem: 8233 +Train: [65] [4500/6250] eta: 0:05:03 lr: 0.000036 grad: 0.1346 (0.1329) loss: 0.8776 (0.8813) time: 0.1677 data: 0.0809 max mem: 8233 +Train: [65] [4600/6250] eta: 0:04:47 lr: 0.000036 grad: 0.1311 (0.1330) loss: 0.8827 (0.8813) time: 0.1647 data: 0.0682 max mem: 8233 +Train: [65] [4700/6250] eta: 0:04:29 lr: 0.000036 grad: 0.1263 (0.1330) loss: 0.8836 (0.8813) time: 0.2031 data: 0.1246 max mem: 8233 +Train: [65] [4800/6250] eta: 0:04:11 lr: 0.000036 grad: 0.1246 (0.1331) loss: 0.8828 (0.8814) time: 0.1534 data: 0.0531 max mem: 8233 +Train: [65] [4900/6250] eta: 0:03:54 lr: 0.000036 grad: 0.1315 (0.1331) loss: 0.8834 (0.8814) time: 0.1366 data: 0.0489 max mem: 8233 +Train: [65] [5000/6250] eta: 0:03:36 lr: 0.000036 grad: 0.1360 (0.1332) loss: 0.8834 (0.8814) time: 0.1429 data: 0.0497 max mem: 8233 +Train: [65] [5100/6250] eta: 0:03:19 lr: 0.000036 grad: 0.1306 (0.1332) loss: 0.8791 (0.8815) time: 0.2484 data: 0.1213 max mem: 8233 +Train: [65] [5200/6250] eta: 0:03:02 lr: 0.000036 grad: 0.1327 (0.1332) loss: 0.8768 (0.8815) time: 0.1636 data: 0.0804 max mem: 8233 +Train: [65] [5300/6250] eta: 0:02:44 lr: 0.000036 grad: 0.1246 (0.1333) loss: 0.8798 (0.8815) time: 0.1826 data: 0.1040 max mem: 8233 +Train: [65] [5400/6250] eta: 0:02:27 lr: 0.000036 grad: 0.1309 (0.1335) loss: 0.8753 (0.8815) time: 0.1617 data: 0.0718 max mem: 8233 +Train: [65] [5500/6250] eta: 0:02:11 lr: 0.000036 grad: 0.1307 (0.1336) loss: 0.8797 (0.8815) time: 0.1079 data: 0.0045 max mem: 8233 +Train: [65] [5600/6250] eta: 0:01:53 lr: 0.000036 grad: 0.1340 (0.1337) loss: 0.8783 (0.8815) time: 0.2428 data: 0.1589 max mem: 8233 +Train: [65] [5700/6250] eta: 0:01:36 lr: 0.000036 grad: 0.1440 (0.1338) loss: 0.8785 (0.8814) time: 0.1155 data: 0.0003 max mem: 8233 +Train: [65] [5800/6250] eta: 0:01:18 lr: 0.000036 grad: 0.1245 (0.1338) loss: 0.8788 (0.8814) time: 0.1572 data: 0.0719 max mem: 8233 +Train: [65] [5900/6250] eta: 0:01:01 lr: 0.000036 grad: 0.1365 (0.1339) loss: 0.8757 (0.8814) time: 0.1465 data: 0.0619 max mem: 8233 +Train: [65] [6000/6250] eta: 0:00:43 lr: 0.000036 grad: 0.1310 (0.1340) loss: 0.8793 (0.8814) time: 0.2198 data: 0.1459 max mem: 8233 +Train: [65] [6100/6250] eta: 0:00:26 lr: 0.000036 grad: 0.1317 (0.1340) loss: 0.8858 (0.8815) time: 0.1254 data: 0.0380 max mem: 8233 +Train: [65] [6200/6250] eta: 0:00:08 lr: 0.000036 grad: 0.1240 (0.1340) loss: 0.8850 (0.8815) time: 0.1748 data: 0.0964 max mem: 8233 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1286 (0.1340) loss: 0.8837 (0.8815) time: 0.1757 data: 0.1054 max mem: 8233 +Train: [65] Total time: 0:18:12 (0.1749 s / it) +Averaged stats: lr: 0.000036 grad: 0.1286 (0.1340) loss: 0.8837 (0.8815) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:03:51 loss: 0.8972 (0.8972) time: 3.7340 data: 3.6871 max mem: 8233 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8893 (0.8899) time: 0.1113 data: 0.0897 max mem: 8233 +Eval (hcp-train-subset): [65] Total time: 0:00:14 (0.2370 s / it) +Averaged stats (hcp-train-subset): loss: 0.8893 (0.8899) +Eval (hcp-val): [65] [ 0/62] eta: 0:05:31 loss: 0.8840 (0.8840) time: 5.3471 data: 5.3211 max mem: 8233 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8869 (0.8881) time: 0.1026 data: 0.0818 max mem: 8233 +Eval (hcp-val): [65] Total time: 0:00:15 (0.2420 s / it) +Averaged stats (hcp-val): loss: 0.8869 (0.8881) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 11:14:11 lr: 0.000036 grad: 0.1891 (0.1891) loss: 0.8506 (0.8506) time: 6.4723 data: 6.2559 max mem: 8233 +Train: [66] [ 100/6250] eta: 0:23:31 lr: 0.000035 grad: 0.1370 (0.1658) loss: 0.8719 (0.8734) time: 0.1553 data: 0.0600 max mem: 8233 +Train: [66] [ 200/6250] eta: 0:20:20 lr: 0.000035 grad: 0.1255 (0.1511) loss: 0.8774 (0.8741) time: 0.1679 data: 0.0575 max mem: 8233 +Train: [66] [ 300/6250] eta: 0:18:41 lr: 0.000035 grad: 0.1331 (0.1447) loss: 0.8776 (0.8756) time: 0.1589 data: 0.0581 max mem: 8233 +Train: [66] [ 400/6250] eta: 0:18:04 lr: 0.000035 grad: 0.1276 (0.1424) loss: 0.8752 (0.8759) time: 0.2515 data: 0.1750 max mem: 8233 +Train: [66] [ 500/6250] eta: 0:17:26 lr: 0.000035 grad: 0.1290 (0.1412) loss: 0.8792 (0.8761) time: 0.1815 data: 0.1010 max mem: 8233 +Train: [66] [ 600/6250] eta: 0:16:49 lr: 0.000035 grad: 0.1314 (0.1410) loss: 0.8731 (0.8758) time: 0.1689 data: 0.0857 max mem: 8233 +Train: [66] [ 700/6250] eta: 0:16:11 lr: 0.000035 grad: 0.1307 (0.1411) loss: 0.8810 (0.8758) time: 0.1597 data: 0.0640 max mem: 8233 +Train: [66] [ 800/6250] eta: 0:15:55 lr: 0.000035 grad: 0.1320 (0.1405) loss: 0.8711 (0.8759) time: 0.2095 data: 0.1203 max mem: 8233 +Train: [66] [ 900/6250] eta: 0:15:32 lr: 0.000035 grad: 0.1284 (0.1405) loss: 0.8801 (0.8762) time: 0.1738 data: 0.0824 max mem: 8233 +Train: [66] [1000/6250] eta: 0:15:03 lr: 0.000035 grad: 0.1354 (0.1403) loss: 0.8811 (0.8763) time: 0.1418 data: 0.0612 max mem: 8233 +Train: [66] [1100/6250] eta: 0:14:37 lr: 0.000035 grad: 0.1336 (0.1400) loss: 0.8743 (0.8766) time: 0.1572 data: 0.0713 max mem: 8233 +Train: [66] [1200/6250] eta: 0:14:22 lr: 0.000035 grad: 0.1336 (0.1399) loss: 0.8785 (0.8769) time: 0.1933 data: 0.1118 max mem: 8233 +Train: [66] [1300/6250] eta: 0:14:04 lr: 0.000035 grad: 0.1314 (0.1400) loss: 0.8802 (0.8771) time: 0.1672 data: 0.0785 max mem: 8233 +Train: [66] [1400/6250] eta: 0:13:48 lr: 0.000035 grad: 0.1378 (0.1399) loss: 0.8725 (0.8771) time: 0.2111 data: 0.1201 max mem: 8233 +Train: [66] [1500/6250] eta: 0:13:25 lr: 0.000035 grad: 0.1334 (0.1400) loss: 0.8755 (0.8771) time: 0.1649 data: 0.0901 max mem: 8233 +Train: [66] [1600/6250] eta: 0:13:13 lr: 0.000035 grad: 0.1327 (0.1397) loss: 0.8832 (0.8773) time: 0.1726 data: 0.0837 max mem: 8233 +Train: [66] [1700/6250] eta: 0:12:50 lr: 0.000035 grad: 0.1301 (0.1395) loss: 0.8807 (0.8774) time: 0.1531 data: 0.0642 max mem: 8233 +Train: [66] [1800/6250] eta: 0:12:31 lr: 0.000035 grad: 0.1388 (0.1397) loss: 0.8745 (0.8773) time: 0.1601 data: 0.0863 max mem: 8233 +Train: [66] [1900/6250] eta: 0:12:17 lr: 0.000035 grad: 0.1328 (0.1395) loss: 0.8823 (0.8774) time: 0.1684 data: 0.0841 max mem: 8233 +Train: [66] [2000/6250] eta: 0:11:57 lr: 0.000035 grad: 0.1276 (0.1393) loss: 0.8730 (0.8774) time: 0.1415 data: 0.0580 max mem: 8233 +Train: [66] [2100/6250] eta: 0:11:38 lr: 0.000035 grad: 0.1341 (0.1392) loss: 0.8823 (0.8774) time: 0.1425 data: 0.0690 max mem: 8233 +Train: [66] [2200/6250] eta: 0:11:21 lr: 0.000035 grad: 0.1342 (0.1391) loss: 0.8749 (0.8775) time: 0.1703 data: 0.0951 max mem: 8233 +Train: [66] [2300/6250] eta: 0:11:03 lr: 0.000035 grad: 0.1393 (0.1392) loss: 0.8738 (0.8775) time: 0.1372 data: 0.0515 max mem: 8233 +Train: [66] [2400/6250] eta: 0:10:45 lr: 0.000035 grad: 0.1328 (0.1391) loss: 0.8789 (0.8775) time: 0.1435 data: 0.0602 max mem: 8233 +Train: [66] [2500/6250] eta: 0:10:27 lr: 0.000035 grad: 0.1370 (0.1392) loss: 0.8745 (0.8776) time: 0.1545 data: 0.0739 max mem: 8233 +Train: [66] [2600/6250] eta: 0:10:08 lr: 0.000035 grad: 0.1388 (0.1391) loss: 0.8810 (0.8778) time: 0.1545 data: 0.0804 max mem: 8233 +Train: [66] [2700/6250] eta: 0:09:50 lr: 0.000035 grad: 0.1289 (0.1389) loss: 0.8798 (0.8779) time: 0.1449 data: 0.0641 max mem: 8233 +Train: [66] [2800/6250] eta: 0:09:32 lr: 0.000035 grad: 0.1245 (0.1392) loss: 0.8857 (0.8780) time: 0.1567 data: 0.0812 max mem: 8233 +Train: [66] [2900/6250] eta: 0:09:17 lr: 0.000035 grad: 0.1303 (0.1392) loss: 0.8742 (0.8780) time: 0.1641 data: 0.0919 max mem: 8233 +Train: [66] [3000/6250] eta: 0:09:02 lr: 0.000035 grad: 0.1359 (0.1392) loss: 0.8840 (0.8781) time: 0.1806 data: 0.1106 max mem: 8233 +Train: [66] [3100/6250] eta: 0:08:44 lr: 0.000035 grad: 0.1337 (0.1391) loss: 0.8762 (0.8781) time: 0.1570 data: 0.0758 max mem: 8233 +Train: [66] [3200/6250] eta: 0:08:27 lr: 0.000035 grad: 0.1302 (0.1390) loss: 0.8790 (0.8782) time: 0.1494 data: 0.0624 max mem: 8233 +Train: [66] [3300/6250] eta: 0:08:09 lr: 0.000035 grad: 0.1330 (0.1389) loss: 0.8812 (0.8782) time: 0.1553 data: 0.0806 max mem: 8233 +Train: [66] [3400/6250] eta: 0:07:54 lr: 0.000035 grad: 0.1290 (0.1389) loss: 0.8821 (0.8783) time: 0.1680 data: 0.0836 max mem: 8233 +Train: [66] [3500/6250] eta: 0:07:39 lr: 0.000034 grad: 0.1444 (0.1387) loss: 0.8845 (0.8785) time: 0.2492 data: 0.1631 max mem: 8233 +Train: [66] [3600/6250] eta: 0:07:22 lr: 0.000034 grad: 0.1324 (0.1387) loss: 0.8825 (0.8785) time: 0.1644 data: 0.0886 max mem: 8233 +Train: [66] [3700/6250] eta: 0:07:05 lr: 0.000034 grad: 0.1304 (0.1385) loss: 0.8787 (0.8787) time: 0.1887 data: 0.1025 max mem: 8233 +Train: [66] [3800/6250] eta: 0:06:51 lr: 0.000034 grad: 0.1312 (0.1384) loss: 0.8801 (0.8788) time: 0.1974 data: 0.0775 max mem: 8233 +Train: [66] [3900/6250] eta: 0:06:34 lr: 0.000034 grad: 0.1292 (0.1382) loss: 0.8837 (0.8789) time: 0.1661 data: 0.0905 max mem: 8233 +Train: [66] [4000/6250] eta: 0:06:17 lr: 0.000034 grad: 0.1334 (0.1382) loss: 0.8794 (0.8790) time: 0.1572 data: 0.0726 max mem: 8233 +Train: [66] [4100/6250] eta: 0:06:00 lr: 0.000034 grad: 0.1392 (0.1382) loss: 0.8871 (0.8791) time: 0.1649 data: 0.0802 max mem: 8233 +Train: [66] [4200/6250] eta: 0:05:42 lr: 0.000034 grad: 0.1254 (0.1382) loss: 0.8857 (0.8791) time: 0.1484 data: 0.0684 max mem: 8233 +Train: [66] [4300/6250] eta: 0:05:26 lr: 0.000034 grad: 0.1340 (0.1381) loss: 0.8745 (0.8792) time: 0.1611 data: 0.0929 max mem: 8233 +Train: [66] [4400/6250] eta: 0:05:09 lr: 0.000034 grad: 0.1249 (0.1381) loss: 0.8792 (0.8792) time: 0.1741 data: 0.0905 max mem: 8233 +Train: [66] [4500/6250] eta: 0:04:52 lr: 0.000034 grad: 0.1252 (0.1381) loss: 0.8796 (0.8792) time: 0.1664 data: 0.0895 max mem: 8233 +Train: [66] [4600/6250] eta: 0:04:35 lr: 0.000034 grad: 0.1214 (0.1380) loss: 0.8767 (0.8792) time: 0.1795 data: 0.0937 max mem: 8233 +Train: [66] [4700/6250] eta: 0:04:19 lr: 0.000034 grad: 0.1308 (0.1380) loss: 0.8788 (0.8792) time: 0.1918 data: 0.1068 max mem: 8233 +Train: [66] [4800/6250] eta: 0:04:02 lr: 0.000034 grad: 0.1275 (0.1379) loss: 0.8823 (0.8792) time: 0.1563 data: 0.0595 max mem: 8233 +Train: [66] [4900/6250] eta: 0:03:45 lr: 0.000034 grad: 0.1272 (0.1378) loss: 0.8818 (0.8793) time: 0.1722 data: 0.0937 max mem: 8233 +Train: [66] [5000/6250] eta: 0:03:28 lr: 0.000034 grad: 0.1267 (0.1378) loss: 0.8861 (0.8793) time: 0.1710 data: 0.0863 max mem: 8233 +Train: [66] [5100/6250] eta: 0:03:11 lr: 0.000034 grad: 0.1246 (0.1377) loss: 0.8805 (0.8794) time: 0.1575 data: 0.0700 max mem: 8233 +Train: [66] [5200/6250] eta: 0:02:54 lr: 0.000034 grad: 0.1318 (0.1376) loss: 0.8791 (0.8794) time: 0.1331 data: 0.0433 max mem: 8233 +Train: [66] [5300/6250] eta: 0:02:37 lr: 0.000034 grad: 0.1311 (0.1376) loss: 0.8811 (0.8795) time: 0.1749 data: 0.0888 max mem: 8233 +Train: [66] [5400/6250] eta: 0:02:21 lr: 0.000034 grad: 0.1274 (0.1375) loss: 0.8815 (0.8796) time: 0.1578 data: 0.0758 max mem: 8233 +Train: [66] [5500/6250] eta: 0:02:04 lr: 0.000034 grad: 0.1273 (0.1374) loss: 0.8831 (0.8796) time: 0.1929 data: 0.1109 max mem: 8233 +Train: [66] [5600/6250] eta: 0:01:48 lr: 0.000034 grad: 0.1355 (0.1374) loss: 0.8759 (0.8796) time: 0.1677 data: 0.0842 max mem: 8233 +Train: [66] [5700/6250] eta: 0:01:31 lr: 0.000034 grad: 0.1318 (0.1374) loss: 0.8866 (0.8796) time: 0.1866 data: 0.1126 max mem: 8233 +Train: [66] [5800/6250] eta: 0:01:14 lr: 0.000034 grad: 0.1305 (0.1373) loss: 0.8830 (0.8796) time: 0.1611 data: 0.0795 max mem: 8233 +Train: [66] [5900/6250] eta: 0:00:58 lr: 0.000034 grad: 0.1321 (0.1373) loss: 0.8810 (0.8797) time: 0.1403 data: 0.0520 max mem: 8233 +Train: [66] [6000/6250] eta: 0:00:41 lr: 0.000034 grad: 0.1365 (0.1373) loss: 0.8757 (0.8797) time: 0.1609 data: 0.0878 max mem: 8233 +Train: [66] [6100/6250] eta: 0:00:24 lr: 0.000034 grad: 0.1265 (0.1373) loss: 0.8806 (0.8797) time: 0.1620 data: 0.0919 max mem: 8233 +Train: [66] [6200/6250] eta: 0:00:08 lr: 0.000034 grad: 0.1322 (0.1372) loss: 0.8851 (0.8797) time: 0.1221 data: 0.0454 max mem: 8233 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1376 (0.1372) loss: 0.8757 (0.8797) time: 0.1581 data: 0.0635 max mem: 8233 +Train: [66] Total time: 0:17:22 (0.1669 s / it) +Averaged stats: lr: 0.000034 grad: 0.1376 (0.1372) loss: 0.8757 (0.8797) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:05:17 loss: 0.9012 (0.9012) time: 5.1259 data: 5.0551 max mem: 8233 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8879 (0.8887) time: 0.1366 data: 0.1161 max mem: 8233 +Eval (hcp-train-subset): [66] Total time: 0:00:14 (0.2411 s / it) +Averaged stats (hcp-train-subset): loss: 0.8879 (0.8887) +Eval (hcp-val): [66] [ 0/62] eta: 0:05:16 loss: 0.8849 (0.8849) time: 5.1082 data: 5.0812 max mem: 8233 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8859 (0.8873) time: 0.1158 data: 0.0929 max mem: 8233 +Eval (hcp-val): [66] Total time: 0:00:14 (0.2303 s / it) +Averaged stats (hcp-val): loss: 0.8859 (0.8873) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 11:00:48 lr: 0.000034 grad: 0.1819 (0.1819) loss: 0.8759 (0.8759) time: 6.3438 data: 6.2234 max mem: 8233 +Train: [67] [ 100/6250] eta: 0:23:36 lr: 0.000034 grad: 0.1277 (0.1413) loss: 0.8851 (0.8901) time: 0.1693 data: 0.0631 max mem: 8233 +Train: [67] [ 200/6250] eta: 0:20:12 lr: 0.000034 grad: 0.1246 (0.1402) loss: 0.8876 (0.8852) time: 0.1638 data: 0.0653 max mem: 8233 +Train: [67] [ 300/6250] eta: 0:19:04 lr: 0.000034 grad: 0.1216 (0.1387) loss: 0.8810 (0.8836) time: 0.1804 data: 0.0763 max mem: 8233 +Train: [67] [ 400/6250] eta: 0:18:00 lr: 0.000034 grad: 0.1238 (0.1372) loss: 0.8859 (0.8829) time: 0.1679 data: 0.0804 max mem: 8233 +Train: [67] [ 500/6250] eta: 0:17:18 lr: 0.000034 grad: 0.1210 (0.1366) loss: 0.8808 (0.8832) time: 0.1679 data: 0.0767 max mem: 8233 +Train: [67] [ 600/6250] eta: 0:16:54 lr: 0.000033 grad: 0.1332 (0.1367) loss: 0.8774 (0.8828) time: 0.1673 data: 0.0752 max mem: 8233 +Train: [67] [ 700/6250] eta: 0:16:30 lr: 0.000033 grad: 0.1214 (0.1359) loss: 0.8838 (0.8829) time: 0.2028 data: 0.1287 max mem: 8233 +Train: [67] [ 800/6250] eta: 0:15:53 lr: 0.000033 grad: 0.1284 (0.1352) loss: 0.8825 (0.8829) time: 0.1487 data: 0.0679 max mem: 8233 +Train: [67] [ 900/6250] eta: 0:15:42 lr: 0.000033 grad: 0.1303 (0.1344) loss: 0.8792 (0.8829) time: 0.2279 data: 0.1504 max mem: 8233 +Train: [67] [1000/6250] eta: 0:15:09 lr: 0.000033 grad: 0.1275 (0.1343) loss: 0.8827 (0.8827) time: 0.1414 data: 0.0432 max mem: 8233 +Train: [67] [1100/6250] eta: 0:14:47 lr: 0.000033 grad: 0.1299 (0.1340) loss: 0.8856 (0.8828) time: 0.1629 data: 0.0748 max mem: 8233 +Train: [67] [1200/6250] eta: 0:14:32 lr: 0.000033 grad: 0.1206 (0.1339) loss: 0.8824 (0.8826) time: 0.1974 data: 0.1117 max mem: 8233 +Train: [67] [1300/6250] eta: 0:14:09 lr: 0.000033 grad: 0.1276 (0.1339) loss: 0.8805 (0.8824) time: 0.1678 data: 0.0854 max mem: 8233 +Train: [67] [1400/6250] eta: 0:13:52 lr: 0.000033 grad: 0.1302 (0.1339) loss: 0.8832 (0.8823) time: 0.1298 data: 0.0004 max mem: 8233 +Train: [67] [1500/6250] eta: 0:13:31 lr: 0.000033 grad: 0.1321 (0.1341) loss: 0.8792 (0.8820) time: 0.1484 data: 0.0592 max mem: 8233 +Train: [67] [1600/6250] eta: 0:13:14 lr: 0.000033 grad: 0.1252 (0.1340) loss: 0.8809 (0.8819) time: 0.2282 data: 0.1441 max mem: 8233 +Train: [67] [1700/6250] eta: 0:12:52 lr: 0.000033 grad: 0.1370 (0.1340) loss: 0.8771 (0.8817) time: 0.1565 data: 0.0602 max mem: 8233 +Train: [67] [1800/6250] eta: 0:12:32 lr: 0.000033 grad: 0.1281 (0.1344) loss: 0.8799 (0.8816) time: 0.1125 data: 0.0328 max mem: 8233 +Train: [67] [1900/6250] eta: 0:12:16 lr: 0.000033 grad: 0.1428 (0.1347) loss: 0.8752 (0.8813) time: 0.1988 data: 0.1155 max mem: 8233 +Train: [67] [2000/6250] eta: 0:12:01 lr: 0.000033 grad: 0.1243 (0.1348) loss: 0.8808 (0.8812) time: 0.1534 data: 0.0787 max mem: 8233 +Train: [67] [2100/6250] eta: 0:11:41 lr: 0.000033 grad: 0.1317 (0.1349) loss: 0.8761 (0.8811) time: 0.1304 data: 0.0495 max mem: 8233 +Train: [67] [2200/6250] eta: 0:11:23 lr: 0.000033 grad: 0.1287 (0.1351) loss: 0.8794 (0.8810) time: 0.1468 data: 0.0699 max mem: 8233 +Train: [67] [2300/6250] eta: 0:11:06 lr: 0.000033 grad: 0.1411 (0.1352) loss: 0.8787 (0.8810) time: 0.1718 data: 0.0871 max mem: 8233 +Train: [67] [2400/6250] eta: 0:10:47 lr: 0.000033 grad: 0.1333 (0.1353) loss: 0.8788 (0.8809) time: 0.1584 data: 0.0755 max mem: 8233 +Train: [67] [2500/6250] eta: 0:10:30 lr: 0.000033 grad: 0.1367 (0.1356) loss: 0.8757 (0.8808) time: 0.1615 data: 0.0709 max mem: 8233 +Train: [67] [2600/6250] eta: 0:10:11 lr: 0.000033 grad: 0.1264 (0.1356) loss: 0.8800 (0.8807) time: 0.1688 data: 0.0837 max mem: 8233 +Train: [67] [2700/6250] eta: 0:09:53 lr: 0.000033 grad: 0.1360 (0.1357) loss: 0.8797 (0.8806) time: 0.1586 data: 0.0813 max mem: 8233 +Train: [67] [2800/6250] eta: 0:09:35 lr: 0.000033 grad: 0.1385 (0.1359) loss: 0.8835 (0.8805) time: 0.1632 data: 0.0798 max mem: 8233 +Train: [67] [2900/6250] eta: 0:09:18 lr: 0.000033 grad: 0.1329 (0.1361) loss: 0.8790 (0.8803) time: 0.1557 data: 0.0731 max mem: 8233 +Train: [67] [3000/6250] eta: 0:09:01 lr: 0.000033 grad: 0.1283 (0.1364) loss: 0.8755 (0.8802) time: 0.1582 data: 0.0733 max mem: 8233 +Train: [67] [3100/6250] eta: 0:08:45 lr: 0.000033 grad: 0.1358 (0.1366) loss: 0.8754 (0.8801) time: 0.2015 data: 0.1179 max mem: 8233 +Train: [67] [3200/6250] eta: 0:08:30 lr: 0.000033 grad: 0.1343 (0.1367) loss: 0.8794 (0.8801) time: 0.1663 data: 0.0891 max mem: 8233 +Train: [67] [3300/6250] eta: 0:08:12 lr: 0.000033 grad: 0.1395 (0.1370) loss: 0.8760 (0.8799) time: 0.1697 data: 0.0749 max mem: 8233 +Train: [67] [3400/6250] eta: 0:07:55 lr: 0.000033 grad: 0.1307 (0.1369) loss: 0.8775 (0.8799) time: 0.2036 data: 0.1283 max mem: 8233 +Train: [67] [3500/6250] eta: 0:07:38 lr: 0.000033 grad: 0.1305 (0.1370) loss: 0.8739 (0.8798) time: 0.1142 data: 0.0239 max mem: 8233 +Train: [67] [3600/6250] eta: 0:07:20 lr: 0.000033 grad: 0.1311 (0.1371) loss: 0.8783 (0.8797) time: 0.1519 data: 0.0719 max mem: 8233 +Train: [67] [3700/6250] eta: 0:07:03 lr: 0.000033 grad: 0.1326 (0.1371) loss: 0.8765 (0.8797) time: 0.1703 data: 0.0860 max mem: 8233 +Train: [67] [3800/6250] eta: 0:06:46 lr: 0.000033 grad: 0.1328 (0.1370) loss: 0.8771 (0.8796) time: 0.1515 data: 0.0755 max mem: 8233 +Train: [67] [3900/6250] eta: 0:06:29 lr: 0.000033 grad: 0.1553 (0.1372) loss: 0.8759 (0.8795) time: 0.1612 data: 0.0789 max mem: 8233 +Train: [67] [4000/6250] eta: 0:06:12 lr: 0.000032 grad: 0.1342 (0.1372) loss: 0.8818 (0.8795) time: 0.1589 data: 0.0814 max mem: 8233 +Train: [67] [4100/6250] eta: 0:05:57 lr: 0.000032 grad: 0.1279 (0.1373) loss: 0.8759 (0.8795) time: 0.1166 data: 0.0201 max mem: 8233 +Train: [67] [4200/6250] eta: 0:05:39 lr: 0.000032 grad: 0.1423 (0.1374) loss: 0.8824 (0.8794) time: 0.1482 data: 0.0677 max mem: 8233 +Train: [67] [4300/6250] eta: 0:05:22 lr: 0.000032 grad: 0.1237 (0.1374) loss: 0.8798 (0.8795) time: 0.1637 data: 0.0845 max mem: 8233 +Train: [67] [4400/6250] eta: 0:05:06 lr: 0.000032 grad: 0.1265 (0.1374) loss: 0.8842 (0.8795) time: 0.1615 data: 0.0882 max mem: 8233 +Train: [67] [4500/6250] eta: 0:04:50 lr: 0.000032 grad: 0.1256 (0.1374) loss: 0.8816 (0.8795) time: 0.1622 data: 0.0797 max mem: 8233 +Train: [67] [4600/6250] eta: 0:04:33 lr: 0.000032 grad: 0.1320 (0.1373) loss: 0.8778 (0.8796) time: 0.1758 data: 0.0971 max mem: 8233 +Train: [67] [4700/6250] eta: 0:04:17 lr: 0.000032 grad: 0.1326 (0.1373) loss: 0.8824 (0.8796) time: 0.2025 data: 0.1253 max mem: 8233 +Train: [67] [4800/6250] eta: 0:04:00 lr: 0.000032 grad: 0.1341 (0.1372) loss: 0.8804 (0.8796) time: 0.1810 data: 0.0866 max mem: 8233 +Train: [67] [4900/6250] eta: 0:03:44 lr: 0.000032 grad: 0.1383 (0.1374) loss: 0.8819 (0.8796) time: 0.1771 data: 0.0956 max mem: 8233 +Train: [67] [5000/6250] eta: 0:03:27 lr: 0.000032 grad: 0.1347 (0.1374) loss: 0.8793 (0.8796) time: 0.1514 data: 0.0599 max mem: 8233 +Train: [67] [5100/6250] eta: 0:03:10 lr: 0.000032 grad: 0.1341 (0.1375) loss: 0.8771 (0.8797) time: 0.1676 data: 0.0847 max mem: 8233 +Train: [67] [5200/6250] eta: 0:02:53 lr: 0.000032 grad: 0.1268 (0.1375) loss: 0.8813 (0.8797) time: 0.1396 data: 0.0589 max mem: 8233 +Train: [67] [5300/6250] eta: 0:02:37 lr: 0.000032 grad: 0.1363 (0.1376) loss: 0.8797 (0.8797) time: 0.1556 data: 0.0740 max mem: 8233 +Train: [67] [5400/6250] eta: 0:02:20 lr: 0.000032 grad: 0.1296 (0.1377) loss: 0.8848 (0.8797) time: 0.1405 data: 0.0533 max mem: 8233 +Train: [67] [5500/6250] eta: 0:02:04 lr: 0.000032 grad: 0.1399 (0.1378) loss: 0.8766 (0.8798) time: 0.1670 data: 0.0917 max mem: 8233 +Train: [67] [5600/6250] eta: 0:01:47 lr: 0.000032 grad: 0.1325 (0.1379) loss: 0.8776 (0.8798) time: 0.1726 data: 0.0943 max mem: 8233 +Train: [67] [5700/6250] eta: 0:01:31 lr: 0.000032 grad: 0.1365 (0.1381) loss: 0.8809 (0.8797) time: 0.1332 data: 0.0286 max mem: 8233 +Train: [67] [5800/6250] eta: 0:01:14 lr: 0.000032 grad: 0.1374 (0.1382) loss: 0.8754 (0.8797) time: 0.2359 data: 0.1542 max mem: 8233 +Train: [67] [5900/6250] eta: 0:00:57 lr: 0.000032 grad: 0.1349 (0.1384) loss: 0.8786 (0.8797) time: 0.1661 data: 0.0944 max mem: 8233 +Train: [67] [6000/6250] eta: 0:00:41 lr: 0.000032 grad: 0.1350 (0.1384) loss: 0.8824 (0.8797) time: 0.1432 data: 0.0587 max mem: 8233 +Train: [67] [6100/6250] eta: 0:00:24 lr: 0.000032 grad: 0.1405 (0.1385) loss: 0.8827 (0.8797) time: 0.1278 data: 0.0429 max mem: 8233 +Train: [67] [6200/6250] eta: 0:00:08 lr: 0.000032 grad: 0.1299 (0.1386) loss: 0.8825 (0.8797) time: 0.1533 data: 0.0727 max mem: 8233 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1371 (0.1386) loss: 0.8804 (0.8797) time: 0.1615 data: 0.0927 max mem: 8233 +Train: [67] Total time: 0:17:19 (0.1663 s / it) +Averaged stats: lr: 0.000032 grad: 0.1371 (0.1386) loss: 0.8804 (0.8797) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:06:14 loss: 0.9022 (0.9022) time: 6.0468 data: 6.0209 max mem: 8233 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8876 (0.8876) time: 0.1337 data: 0.1129 max mem: 8233 +Eval (hcp-train-subset): [67] Total time: 0:00:14 (0.2411 s / it) +Averaged stats (hcp-train-subset): loss: 0.8876 (0.8876) +Eval (hcp-val): [67] [ 0/62] eta: 0:06:34 loss: 0.8824 (0.8824) time: 6.3617 data: 6.3359 max mem: 8233 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8868 (0.8872) time: 0.1204 data: 0.0972 max mem: 8233 +Eval (hcp-val): [67] Total time: 0:00:15 (0.2428 s / it) +Averaged stats (hcp-val): loss: 0.8868 (0.8872) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 11:48:17 lr: 0.000032 grad: 0.1430 (0.1430) loss: 0.8856 (0.8856) time: 6.7996 data: 6.6540 max mem: 8233 +Train: [68] [ 100/6250] eta: 0:22:57 lr: 0.000032 grad: 0.1372 (0.1340) loss: 0.8833 (0.8858) time: 0.1610 data: 0.0541 max mem: 8233 +Train: [68] [ 200/6250] eta: 0:20:55 lr: 0.000032 grad: 0.1351 (0.1358) loss: 0.8773 (0.8824) time: 0.2241 data: 0.1307 max mem: 8233 +Train: [68] [ 300/6250] eta: 0:19:00 lr: 0.000032 grad: 0.1342 (0.1357) loss: 0.8813 (0.8813) time: 0.1641 data: 0.0759 max mem: 8233 +Train: [68] [ 400/6250] eta: 0:17:59 lr: 0.000032 grad: 0.1326 (0.1352) loss: 0.8841 (0.8815) time: 0.1471 data: 0.0611 max mem: 8233 +Train: [68] [ 500/6250] eta: 0:17:14 lr: 0.000032 grad: 0.1349 (0.1354) loss: 0.8765 (0.8810) time: 0.1851 data: 0.0936 max mem: 8233 +Train: [68] [ 600/6250] eta: 0:16:45 lr: 0.000032 grad: 0.1300 (0.1346) loss: 0.8853 (0.8814) time: 0.1951 data: 0.1104 max mem: 8233 +Train: [68] [ 700/6250] eta: 0:16:22 lr: 0.000032 grad: 0.1296 (0.1341) loss: 0.8849 (0.8817) time: 0.2270 data: 0.1403 max mem: 8233 +Train: [68] [ 800/6250] eta: 0:16:12 lr: 0.000032 grad: 0.1326 (0.1338) loss: 0.8833 (0.8818) time: 0.1829 data: 0.1020 max mem: 8233 +Train: [68] [ 900/6250] eta: 0:15:48 lr: 0.000032 grad: 0.1299 (0.1341) loss: 0.8818 (0.8816) time: 0.1756 data: 0.1033 max mem: 8233 +Train: [68] [1000/6250] eta: 0:15:20 lr: 0.000032 grad: 0.1378 (0.1343) loss: 0.8828 (0.8815) time: 0.1336 data: 0.0528 max mem: 8233 +Train: [68] [1100/6250] eta: 0:14:57 lr: 0.000032 grad: 0.1286 (0.1344) loss: 0.8825 (0.8814) time: 0.1797 data: 0.0928 max mem: 8233 +Train: [68] [1200/6250] eta: 0:14:36 lr: 0.000032 grad: 0.1289 (0.1348) loss: 0.8759 (0.8813) time: 0.1732 data: 0.0876 max mem: 8233 +Train: [68] [1300/6250] eta: 0:14:13 lr: 0.000031 grad: 0.1390 (0.1351) loss: 0.8780 (0.8811) time: 0.1650 data: 0.0632 max mem: 8233 +Train: [68] [1400/6250] eta: 0:13:50 lr: 0.000031 grad: 0.1282 (0.1351) loss: 0.8787 (0.8811) time: 0.1540 data: 0.0665 max mem: 8233 +Train: [68] [1500/6250] eta: 0:13:23 lr: 0.000031 grad: 0.1310 (0.1357) loss: 0.8814 (0.8809) time: 0.1320 data: 0.0381 max mem: 8233 +Train: [68] [1600/6250] eta: 0:12:58 lr: 0.000031 grad: 0.1424 (0.1360) loss: 0.8746 (0.8808) time: 0.1376 data: 0.0466 max mem: 8233 +Train: [68] [1700/6250] eta: 0:12:40 lr: 0.000031 grad: 0.1428 (0.1365) loss: 0.8748 (0.8807) time: 0.1707 data: 0.0862 max mem: 8233 +Train: [68] [1800/6250] eta: 0:12:25 lr: 0.000031 grad: 0.1365 (0.1369) loss: 0.8723 (0.8805) time: 0.2063 data: 0.1231 max mem: 8233 +Train: [68] [1900/6250] eta: 0:12:12 lr: 0.000031 grad: 0.1282 (0.1372) loss: 0.8868 (0.8806) time: 0.2133 data: 0.1303 max mem: 8233 +Train: [68] [2000/6250] eta: 0:11:52 lr: 0.000031 grad: 0.1278 (0.1375) loss: 0.8850 (0.8806) time: 0.0918 data: 0.0002 max mem: 8233 +Train: [68] [2100/6250] eta: 0:11:43 lr: 0.000031 grad: 0.1357 (0.1377) loss: 0.8806 (0.8806) time: 0.1876 data: 0.1056 max mem: 8233 +Train: [68] [2200/6250] eta: 0:11:26 lr: 0.000031 grad: 0.1375 (0.1379) loss: 0.8809 (0.8805) time: 0.1864 data: 0.1052 max mem: 8233 +Train: [68] [2300/6250] eta: 0:11:09 lr: 0.000031 grad: 0.1302 (0.1382) loss: 0.8796 (0.8803) time: 0.1778 data: 0.0893 max mem: 8233 +Train: [68] [2400/6250] eta: 0:10:52 lr: 0.000031 grad: 0.1356 (0.1385) loss: 0.8865 (0.8803) time: 0.1982 data: 0.1160 max mem: 8233 +Train: [68] [2500/6250] eta: 0:10:37 lr: 0.000031 grad: 0.1346 (0.1384) loss: 0.8871 (0.8803) time: 0.2158 data: 0.1366 max mem: 8233 +Train: [68] [2600/6250] eta: 0:10:20 lr: 0.000031 grad: 0.1273 (0.1383) loss: 0.8824 (0.8804) time: 0.1600 data: 0.0779 max mem: 8233 +Train: [68] [2700/6250] eta: 0:10:02 lr: 0.000031 grad: 0.1287 (0.1382) loss: 0.8828 (0.8804) time: 0.1446 data: 0.0617 max mem: 8233 +Train: [68] [2800/6250] eta: 0:09:44 lr: 0.000031 grad: 0.1377 (0.1382) loss: 0.8788 (0.8804) time: 0.1238 data: 0.0201 max mem: 8233 +Train: [68] [2900/6250] eta: 0:09:26 lr: 0.000031 grad: 0.1339 (0.1381) loss: 0.8773 (0.8805) time: 0.1599 data: 0.0739 max mem: 8233 +Train: [68] [3000/6250] eta: 0:09:11 lr: 0.000031 grad: 0.1338 (0.1382) loss: 0.8826 (0.8805) time: 0.3046 data: 0.2182 max mem: 8233 +Train: [68] [3100/6250] eta: 0:08:53 lr: 0.000031 grad: 0.1383 (0.1382) loss: 0.8851 (0.8805) time: 0.1750 data: 0.1019 max mem: 8233 +Train: [68] [3200/6250] eta: 0:08:36 lr: 0.000031 grad: 0.1375 (0.1381) loss: 0.8828 (0.8805) time: 0.1097 data: 0.0003 max mem: 8233 +Train: [68] [3300/6250] eta: 0:08:21 lr: 0.000031 grad: 0.1388 (0.1381) loss: 0.8821 (0.8805) time: 0.2757 data: 0.1931 max mem: 8233 +Train: [68] [3400/6250] eta: 0:08:02 lr: 0.000031 grad: 0.1359 (0.1381) loss: 0.8868 (0.8806) time: 0.1534 data: 0.0731 max mem: 8233 +Train: [68] [3500/6250] eta: 0:07:44 lr: 0.000031 grad: 0.1247 (0.1379) loss: 0.8831 (0.8807) time: 0.1585 data: 0.0784 max mem: 8233 +Train: [68] [3600/6250] eta: 0:07:27 lr: 0.000031 grad: 0.1366 (0.1380) loss: 0.8810 (0.8807) time: 0.1691 data: 0.0924 max mem: 8233 +Train: [68] [3700/6250] eta: 0:07:10 lr: 0.000031 grad: 0.1252 (0.1381) loss: 0.8826 (0.8807) time: 0.1984 data: 0.1089 max mem: 8233 +Train: [68] [3800/6250] eta: 0:06:52 lr: 0.000031 grad: 0.1298 (0.1381) loss: 0.8773 (0.8808) time: 0.1403 data: 0.0671 max mem: 8233 +Train: [68] [3900/6250] eta: 0:06:34 lr: 0.000031 grad: 0.1268 (0.1381) loss: 0.8851 (0.8809) time: 0.1483 data: 0.0752 max mem: 8233 +Train: [68] [4000/6250] eta: 0:06:17 lr: 0.000031 grad: 0.1299 (0.1379) loss: 0.8826 (0.8809) time: 0.1007 data: 0.0191 max mem: 8233 +Train: [68] [4100/6250] eta: 0:06:01 lr: 0.000031 grad: 0.1392 (0.1378) loss: 0.8770 (0.8810) time: 0.1591 data: 0.0797 max mem: 8233 +Train: [68] [4200/6250] eta: 0:05:44 lr: 0.000031 grad: 0.1281 (0.1378) loss: 0.8864 (0.8811) time: 0.1683 data: 0.0836 max mem: 8233 +Train: [68] [4300/6250] eta: 0:05:28 lr: 0.000031 grad: 0.1280 (0.1379) loss: 0.8801 (0.8812) time: 0.2013 data: 0.1084 max mem: 8233 +Train: [68] [4400/6250] eta: 0:05:11 lr: 0.000031 grad: 0.1370 (0.1379) loss: 0.8884 (0.8813) time: 0.1685 data: 0.0859 max mem: 8233 +Train: [68] [4500/6250] eta: 0:04:54 lr: 0.000031 grad: 0.1337 (0.1379) loss: 0.8834 (0.8813) time: 0.1837 data: 0.1015 max mem: 8233 +Train: [68] [4600/6250] eta: 0:04:37 lr: 0.000031 grad: 0.1321 (0.1379) loss: 0.8762 (0.8813) time: 0.1809 data: 0.1064 max mem: 8233 +Train: [68] [4700/6250] eta: 0:04:20 lr: 0.000031 grad: 0.1334 (0.1379) loss: 0.8825 (0.8813) time: 0.1338 data: 0.0599 max mem: 8233 +Train: [68] [4800/6250] eta: 0:04:03 lr: 0.000030 grad: 0.1357 (0.1379) loss: 0.8822 (0.8813) time: 0.1507 data: 0.0693 max mem: 8233 +Train: [68] [4900/6250] eta: 0:03:47 lr: 0.000030 grad: 0.1352 (0.1379) loss: 0.8799 (0.8813) time: 0.1793 data: 0.0992 max mem: 8233 +Train: [68] [5000/6250] eta: 0:03:30 lr: 0.000030 grad: 0.1346 (0.1380) loss: 0.8857 (0.8813) time: 0.1698 data: 0.0929 max mem: 8233 +Train: [68] [5100/6250] eta: 0:03:13 lr: 0.000030 grad: 0.1394 (0.1381) loss: 0.8771 (0.8813) time: 0.1548 data: 0.0636 max mem: 8233 +Train: [68] [5200/6250] eta: 0:02:56 lr: 0.000030 grad: 0.1328 (0.1381) loss: 0.8771 (0.8812) time: 0.1513 data: 0.0561 max mem: 8233 +Train: [68] [5300/6250] eta: 0:02:39 lr: 0.000030 grad: 0.1354 (0.1383) loss: 0.8774 (0.8812) time: 0.1779 data: 0.0890 max mem: 8233 +Train: [68] [5400/6250] eta: 0:02:22 lr: 0.000030 grad: 0.1265 (0.1383) loss: 0.8766 (0.8811) time: 0.1783 data: 0.0913 max mem: 8233 +Train: [68] [5500/6250] eta: 0:02:05 lr: 0.000030 grad: 0.1364 (0.1384) loss: 0.8850 (0.8810) time: 0.1548 data: 0.0721 max mem: 8233 +Train: [68] [5600/6250] eta: 0:01:49 lr: 0.000030 grad: 0.1448 (0.1385) loss: 0.8733 (0.8810) time: 0.1633 data: 0.0554 max mem: 8233 +Train: [68] [5700/6250] eta: 0:01:32 lr: 0.000030 grad: 0.1301 (0.1387) loss: 0.8781 (0.8810) time: 0.1400 data: 0.0539 max mem: 8233 +Train: [68] [5800/6250] eta: 0:01:15 lr: 0.000030 grad: 0.1312 (0.1387) loss: 0.8774 (0.8809) time: 0.1588 data: 0.0672 max mem: 8233 +Train: [68] [5900/6250] eta: 0:00:58 lr: 0.000030 grad: 0.1442 (0.1389) loss: 0.8742 (0.8809) time: 0.1564 data: 0.0725 max mem: 8233 +Train: [68] [6000/6250] eta: 0:00:41 lr: 0.000030 grad: 0.1432 (0.1390) loss: 0.8773 (0.8808) time: 0.1703 data: 0.0898 max mem: 8233 +Train: [68] [6100/6250] eta: 0:00:25 lr: 0.000030 grad: 0.1328 (0.1391) loss: 0.8784 (0.8808) time: 0.1603 data: 0.0924 max mem: 8233 +Train: [68] [6200/6250] eta: 0:00:08 lr: 0.000030 grad: 0.1428 (0.1392) loss: 0.8823 (0.8808) time: 0.1681 data: 0.0994 max mem: 8233 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1389 (0.1392) loss: 0.8770 (0.8807) time: 0.1717 data: 0.0888 max mem: 8233 +Train: [68] Total time: 0:17:30 (0.1680 s / it) +Averaged stats: lr: 0.000030 grad: 0.1389 (0.1392) loss: 0.8770 (0.8807) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:05:19 loss: 0.9008 (0.9008) time: 5.1553 data: 5.1277 max mem: 8233 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8893 (0.8888) time: 0.1295 data: 0.1089 max mem: 8233 +Eval (hcp-train-subset): [68] Total time: 0:00:14 (0.2355 s / it) +Averaged stats (hcp-train-subset): loss: 0.8893 (0.8888) +Eval (hcp-val): [68] [ 0/62] eta: 0:04:27 loss: 0.8833 (0.8833) time: 4.3068 data: 4.2229 max mem: 8233 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8847 (0.8867) time: 0.1209 data: 0.0998 max mem: 8233 +Eval (hcp-val): [68] Total time: 0:00:14 (0.2333 s / it) +Averaged stats (hcp-val): loss: 0.8847 (0.8867) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 9:41:08 lr: 0.000030 grad: 0.5913 (0.5913) loss: 0.8538 (0.8538) time: 5.5789 data: 5.2901 max mem: 8233 +Train: [69] [ 100/6250] eta: 0:24:58 lr: 0.000030 grad: 0.1315 (0.1434) loss: 0.8863 (0.8838) time: 0.1628 data: 0.0345 max mem: 8233 +Train: [69] [ 200/6250] eta: 0:20:50 lr: 0.000030 grad: 0.1286 (0.1411) loss: 0.8858 (0.8835) time: 0.1547 data: 0.0419 max mem: 8233 +Train: [69] [ 300/6250] eta: 0:19:18 lr: 0.000030 grad: 0.1300 (0.1409) loss: 0.8819 (0.8825) time: 0.1258 data: 0.0212 max mem: 8233 +Train: [69] [ 400/6250] eta: 0:18:00 lr: 0.000030 grad: 0.1225 (0.1395) loss: 0.8857 (0.8820) time: 0.1479 data: 0.0495 max mem: 8233 +Train: [69] [ 500/6250] eta: 0:17:16 lr: 0.000030 grad: 0.1319 (0.1383) loss: 0.8798 (0.8820) time: 0.1759 data: 0.0875 max mem: 8233 +Train: [69] [ 600/6250] eta: 0:16:35 lr: 0.000030 grad: 0.1211 (0.1376) loss: 0.8840 (0.8824) time: 0.1115 data: 0.0048 max mem: 8233 +Train: [69] [ 700/6250] eta: 0:16:07 lr: 0.000030 grad: 0.1264 (0.1366) loss: 0.8896 (0.8826) time: 0.1564 data: 0.0595 max mem: 8233 +Train: [69] [ 800/6250] eta: 0:15:40 lr: 0.000030 grad: 0.1298 (0.1356) loss: 0.8883 (0.8830) time: 0.1838 data: 0.0941 max mem: 8233 +Train: [69] [ 900/6250] eta: 0:15:20 lr: 0.000030 grad: 0.1338 (0.1351) loss: 0.8839 (0.8831) time: 0.1602 data: 0.0567 max mem: 8233 +Train: [69] [1000/6250] eta: 0:15:02 lr: 0.000030 grad: 0.1332 (0.1351) loss: 0.8808 (0.8831) time: 0.1687 data: 0.0901 max mem: 8233 +Train: [69] [1100/6250] eta: 0:14:36 lr: 0.000030 grad: 0.1279 (0.1351) loss: 0.8863 (0.8832) time: 0.1555 data: 0.0766 max mem: 8233 +Train: [69] [1200/6250] eta: 0:14:14 lr: 0.000030 grad: 0.1302 (0.1348) loss: 0.8837 (0.8832) time: 0.1605 data: 0.0675 max mem: 8233 +Train: [69] [1300/6250] eta: 0:13:55 lr: 0.000030 grad: 0.1259 (0.1347) loss: 0.8839 (0.8833) time: 0.1615 data: 0.0693 max mem: 8233 +Train: [69] [1400/6250] eta: 0:13:35 lr: 0.000030 grad: 0.1263 (0.1348) loss: 0.8793 (0.8831) time: 0.1632 data: 0.0858 max mem: 8233 +Train: [69] [1500/6250] eta: 0:13:14 lr: 0.000030 grad: 0.1314 (0.1349) loss: 0.8831 (0.8830) time: 0.1253 data: 0.0380 max mem: 8233 +Train: [69] [1600/6250] eta: 0:12:52 lr: 0.000030 grad: 0.1256 (0.1350) loss: 0.8822 (0.8829) time: 0.1332 data: 0.0519 max mem: 8233 +Train: [69] [1700/6250] eta: 0:12:31 lr: 0.000030 grad: 0.1285 (0.1350) loss: 0.8791 (0.8828) time: 0.1605 data: 0.0625 max mem: 8233 +Train: [69] [1800/6250] eta: 0:12:07 lr: 0.000030 grad: 0.1243 (0.1352) loss: 0.8841 (0.8827) time: 0.1338 data: 0.0533 max mem: 8233 +Train: [69] [1900/6250] eta: 0:11:47 lr: 0.000030 grad: 0.1334 (0.1353) loss: 0.8756 (0.8826) time: 0.1479 data: 0.0541 max mem: 8233 +Train: [69] [2000/6250] eta: 0:11:26 lr: 0.000030 grad: 0.1476 (0.1355) loss: 0.8778 (0.8824) time: 0.1673 data: 0.0835 max mem: 8233 +Train: [69] [2100/6250] eta: 0:11:09 lr: 0.000029 grad: 0.1323 (0.1358) loss: 0.8790 (0.8823) time: 0.2016 data: 0.1378 max mem: 8233 +Train: [69] [2200/6250] eta: 0:10:51 lr: 0.000029 grad: 0.1317 (0.1360) loss: 0.8802 (0.8822) time: 0.1283 data: 0.0453 max mem: 8233 +Train: [69] [2300/6250] eta: 0:10:34 lr: 0.000029 grad: 0.1373 (0.1363) loss: 0.8801 (0.8820) time: 0.1596 data: 0.0826 max mem: 8233 +Train: [69] [2400/6250] eta: 0:10:17 lr: 0.000029 grad: 0.1322 (0.1365) loss: 0.8792 (0.8819) time: 0.1699 data: 0.0856 max mem: 8233 +Train: [69] [2500/6250] eta: 0:10:02 lr: 0.000029 grad: 0.1390 (0.1365) loss: 0.8817 (0.8818) time: 0.1735 data: 0.0952 max mem: 8233 +Train: [69] [2600/6250] eta: 0:09:47 lr: 0.000029 grad: 0.1378 (0.1366) loss: 0.8789 (0.8817) time: 0.1146 data: 0.0290 max mem: 8233 +Train: [69] [2700/6250] eta: 0:09:29 lr: 0.000029 grad: 0.1307 (0.1366) loss: 0.8839 (0.8816) time: 0.1497 data: 0.0569 max mem: 8233 +Train: [69] [2800/6250] eta: 0:09:11 lr: 0.000029 grad: 0.1361 (0.1368) loss: 0.8809 (0.8815) time: 0.1403 data: 0.0551 max mem: 8233 +Train: [69] [2900/6250] eta: 0:08:54 lr: 0.000029 grad: 0.1251 (0.1369) loss: 0.8866 (0.8815) time: 0.1218 data: 0.0311 max mem: 8233 +Train: [69] [3000/6250] eta: 0:08:36 lr: 0.000029 grad: 0.1337 (0.1371) loss: 0.8801 (0.8814) time: 0.1604 data: 0.0701 max mem: 8233 +Train: [69] [3100/6250] eta: 0:08:20 lr: 0.000029 grad: 0.1243 (0.1372) loss: 0.8833 (0.8814) time: 0.1690 data: 0.0973 max mem: 8233 +Train: [69] [3200/6250] eta: 0:08:04 lr: 0.000029 grad: 0.1300 (0.1375) loss: 0.8813 (0.8813) time: 0.1732 data: 0.0992 max mem: 8233 +Train: [69] [3300/6250] eta: 0:07:47 lr: 0.000029 grad: 0.1253 (0.1376) loss: 0.8855 (0.8814) time: 0.1407 data: 0.0663 max mem: 8233 +Train: [69] [3400/6250] eta: 0:07:31 lr: 0.000029 grad: 0.1388 (0.1378) loss: 0.8806 (0.8813) time: 0.1532 data: 0.0748 max mem: 8233 +Train: [69] [3500/6250] eta: 0:07:15 lr: 0.000029 grad: 0.1345 (0.1379) loss: 0.8799 (0.8812) time: 0.1362 data: 0.0644 max mem: 8233 +Train: [69] [3600/6250] eta: 0:06:59 lr: 0.000029 grad: 0.1263 (0.1382) loss: 0.8835 (0.8812) time: 0.1528 data: 0.0647 max mem: 8233 +Train: [69] [3700/6250] eta: 0:06:43 lr: 0.000029 grad: 0.1419 (0.1383) loss: 0.8769 (0.8812) time: 0.1707 data: 0.0923 max mem: 8233 +Train: [69] [3800/6250] eta: 0:06:28 lr: 0.000029 grad: 0.1353 (0.1384) loss: 0.8775 (0.8811) time: 0.1303 data: 0.0142 max mem: 8233 +Train: [69] [3900/6250] eta: 0:06:12 lr: 0.000029 grad: 0.1321 (0.1383) loss: 0.8779 (0.8811) time: 0.1630 data: 0.0910 max mem: 8233 +Train: [69] [4000/6250] eta: 0:05:56 lr: 0.000029 grad: 0.1367 (0.1384) loss: 0.8807 (0.8811) time: 0.1739 data: 0.0963 max mem: 8233 +Train: [69] [4100/6250] eta: 0:05:41 lr: 0.000029 grad: 0.1304 (0.1384) loss: 0.8800 (0.8811) time: 0.1882 data: 0.1151 max mem: 8233 +Train: [69] [4200/6250] eta: 0:05:25 lr: 0.000029 grad: 0.1287 (0.1384) loss: 0.8840 (0.8811) time: 0.2132 data: 0.1263 max mem: 8233 +Train: [69] [4300/6250] eta: 0:05:09 lr: 0.000029 grad: 0.1400 (0.1385) loss: 0.8791 (0.8810) time: 0.1794 data: 0.1041 max mem: 8233 +Train: [69] [4400/6250] eta: 0:04:53 lr: 0.000029 grad: 0.1283 (0.1386) loss: 0.8828 (0.8810) time: 0.1655 data: 0.0849 max mem: 8233 +Train: [69] [4500/6250] eta: 0:04:38 lr: 0.000029 grad: 0.1416 (0.1386) loss: 0.8793 (0.8810) time: 0.1039 data: 0.0003 max mem: 8233 +Train: [69] [4600/6250] eta: 0:04:23 lr: 0.000029 grad: 0.1455 (0.1387) loss: 0.8773 (0.8810) time: 0.1743 data: 0.0953 max mem: 8233 +Train: [69] [4700/6250] eta: 0:04:06 lr: 0.000029 grad: 0.1386 (0.1388) loss: 0.8763 (0.8809) time: 0.1476 data: 0.0674 max mem: 8233 +Train: [69] [4800/6250] eta: 0:03:50 lr: 0.000029 grad: 0.1409 (0.1388) loss: 0.8771 (0.8808) time: 0.1889 data: 0.1015 max mem: 8233 +Train: [69] [4900/6250] eta: 0:03:35 lr: 0.000029 grad: 0.1240 (0.1388) loss: 0.8823 (0.8808) time: 0.1755 data: 0.0938 max mem: 8233 +Train: [69] [5000/6250] eta: 0:03:19 lr: 0.000029 grad: 0.1302 (0.1388) loss: 0.8794 (0.8808) time: 0.1791 data: 0.0970 max mem: 8233 +Train: [69] [5100/6250] eta: 0:03:03 lr: 0.000029 grad: 0.1284 (0.1388) loss: 0.8844 (0.8809) time: 0.1595 data: 0.0500 max mem: 8233 +Train: [69] [5200/6250] eta: 0:02:47 lr: 0.000029 grad: 0.1301 (0.1388) loss: 0.8821 (0.8808) time: 0.1451 data: 0.0550 max mem: 8233 +Train: [69] [5300/6250] eta: 0:02:31 lr: 0.000029 grad: 0.1246 (0.1388) loss: 0.8852 (0.8808) time: 0.1516 data: 0.0682 max mem: 8233 +Train: [69] [5400/6250] eta: 0:02:15 lr: 0.000029 grad: 0.1353 (0.1388) loss: 0.8782 (0.8808) time: 0.1642 data: 0.0924 max mem: 8233 +Train: [69] [5500/6250] eta: 0:01:59 lr: 0.000029 grad: 0.1259 (0.1387) loss: 0.8788 (0.8808) time: 0.1580 data: 0.0904 max mem: 8233 +Train: [69] [5600/6250] eta: 0:01:43 lr: 0.000028 grad: 0.1255 (0.1387) loss: 0.8843 (0.8808) time: 0.2107 data: 0.1369 max mem: 8233 +Train: [69] [5700/6250] eta: 0:01:27 lr: 0.000028 grad: 0.1292 (0.1387) loss: 0.8834 (0.8809) time: 0.1796 data: 0.1082 max mem: 8233 +Train: [69] [5800/6250] eta: 0:01:11 lr: 0.000028 grad: 0.1277 (0.1386) loss: 0.8827 (0.8809) time: 0.2183 data: 0.1539 max mem: 8233 +Train: [69] [5900/6250] eta: 0:00:55 lr: 0.000028 grad: 0.1310 (0.1385) loss: 0.8771 (0.8809) time: 0.1240 data: 0.0467 max mem: 8233 +Train: [69] [6000/6250] eta: 0:00:39 lr: 0.000028 grad: 0.1308 (0.1386) loss: 0.8827 (0.8809) time: 0.1469 data: 0.0717 max mem: 8233 +Train: [69] [6100/6250] eta: 0:00:23 lr: 0.000028 grad: 0.1322 (0.1385) loss: 0.8829 (0.8810) time: 0.1779 data: 0.1010 max mem: 8233 +Train: [69] [6200/6250] eta: 0:00:07 lr: 0.000028 grad: 0.1325 (0.1385) loss: 0.8789 (0.8809) time: 0.1384 data: 0.0462 max mem: 8233 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1346 (0.1385) loss: 0.8816 (0.8809) time: 0.1754 data: 0.0949 max mem: 8233 +Train: [69] Total time: 0:16:41 (0.1602 s / it) +Averaged stats: lr: 0.000028 grad: 0.1346 (0.1385) loss: 0.8816 (0.8809) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:05:05 loss: 0.8942 (0.8942) time: 4.9222 data: 4.8524 max mem: 8233 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8872 (0.8880) time: 0.1321 data: 0.1099 max mem: 8233 +Eval (hcp-train-subset): [69] Total time: 0:00:15 (0.2550 s / it) +Averaged stats (hcp-train-subset): loss: 0.8872 (0.8880) +Making plots (hcp-train-subset): example=47 +Eval (hcp-val): [69] [ 0/62] eta: 0:04:35 loss: 0.8791 (0.8791) time: 4.4471 data: 4.3557 max mem: 8233 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8866 (0.8859) time: 0.1458 data: 0.1234 max mem: 8233 +Eval (hcp-val): [69] Total time: 0:00:16 (0.2675 s / it) +Averaged stats (hcp-val): loss: 0.8866 (0.8859) +Making plots (hcp-val): example=54 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 14:26:13 lr: 0.000028 grad: 0.0951 (0.0951) loss: 0.8982 (0.8982) time: 8.3158 data: 8.2154 max mem: 8233 +Train: [70] [ 100/6250] eta: 0:26:55 lr: 0.000028 grad: 0.1317 (0.1472) loss: 0.8809 (0.8855) time: 0.1300 data: 0.0111 max mem: 8233 +Train: [70] [ 200/6250] eta: 0:23:11 lr: 0.000028 grad: 0.1277 (0.1490) loss: 0.8814 (0.8810) time: 0.2181 data: 0.1169 max mem: 8233 +Train: [70] [ 300/6250] eta: 0:20:51 lr: 0.000028 grad: 0.1343 (0.1492) loss: 0.8799 (0.8790) time: 0.1648 data: 0.0485 max mem: 8233 +Train: [70] [ 400/6250] eta: 0:20:25 lr: 0.000028 grad: 0.1367 (0.1472) loss: 0.8821 (0.8785) time: 0.1430 data: 0.0211 max mem: 8233 +Train: [70] [ 500/6250] eta: 0:19:12 lr: 0.000028 grad: 0.1320 (0.1475) loss: 0.8822 (0.8783) time: 0.1673 data: 0.0594 max mem: 8233 +Train: [70] [ 600/6250] eta: 0:19:02 lr: 0.000028 grad: 0.1324 (0.1466) loss: 0.8793 (0.8780) time: 0.3201 data: 0.2029 max mem: 8233 +Train: [70] [ 700/6250] eta: 0:18:14 lr: 0.000028 grad: 0.1358 (0.1460) loss: 0.8783 (0.8782) time: 0.1587 data: 0.0779 max mem: 8233 +Train: [70] [ 800/6250] eta: 0:17:53 lr: 0.000028 grad: 0.1441 (0.1456) loss: 0.8781 (0.8784) time: 0.2099 data: 0.1210 max mem: 8233 +Train: [70] [ 900/6250] eta: 0:17:15 lr: 0.000028 grad: 0.1365 (0.1450) loss: 0.8805 (0.8787) time: 0.1514 data: 0.0397 max mem: 8233 +Train: [70] [1000/6250] eta: 0:16:51 lr: 0.000028 grad: 0.1430 (0.1446) loss: 0.8765 (0.8788) time: 0.1759 data: 0.0937 max mem: 8233 +Train: [70] [1100/6250] eta: 0:16:20 lr: 0.000028 grad: 0.1399 (0.1444) loss: 0.8719 (0.8787) time: 0.1343 data: 0.0614 max mem: 8233 +Train: [70] [1200/6250] eta: 0:15:46 lr: 0.000028 grad: 0.1489 (0.1442) loss: 0.8687 (0.8787) time: 0.1518 data: 0.0765 max mem: 8233 +Train: [70] [1300/6250] eta: 0:15:16 lr: 0.000028 grad: 0.1371 (0.1442) loss: 0.8814 (0.8787) time: 0.1460 data: 0.0620 max mem: 8233 +Train: [70] [1400/6250] eta: 0:14:54 lr: 0.000028 grad: 0.1380 (0.1444) loss: 0.8752 (0.8787) time: 0.1618 data: 0.0614 max mem: 8233 +Train: [70] [1500/6250] eta: 0:14:31 lr: 0.000028 grad: 0.1337 (0.1443) loss: 0.8762 (0.8785) time: 0.1970 data: 0.1149 max mem: 8233 +Train: [70] [1600/6250] eta: 0:14:05 lr: 0.000028 grad: 0.1464 (0.1442) loss: 0.8797 (0.8786) time: 0.1646 data: 0.0854 max mem: 8233 +Train: [70] [1700/6250] eta: 0:13:44 lr: 0.000028 grad: 0.1349 (0.1441) loss: 0.8828 (0.8787) time: 0.1868 data: 0.1015 max mem: 8233 +Train: [70] [1800/6250] eta: 0:13:20 lr: 0.000028 grad: 0.1377 (0.1440) loss: 0.8786 (0.8787) time: 0.1541 data: 0.0591 max mem: 8233 +Train: [70] [1900/6250] eta: 0:12:56 lr: 0.000028 grad: 0.1380 (0.1441) loss: 0.8776 (0.8788) time: 0.1464 data: 0.0682 max mem: 8233 +Train: [70] [2000/6250] eta: 0:12:38 lr: 0.000028 grad: 0.1463 (0.1439) loss: 0.8785 (0.8788) time: 0.2057 data: 0.1165 max mem: 8233 +Train: [70] [2100/6250] eta: 0:12:18 lr: 0.000028 grad: 0.1301 (0.1438) loss: 0.8810 (0.8789) time: 0.1452 data: 0.0564 max mem: 8233 +Train: [70] [2200/6250] eta: 0:12:00 lr: 0.000028 grad: 0.1300 (0.1436) loss: 0.8753 (0.8789) time: 0.1840 data: 0.1065 max mem: 8233 +Train: [70] [2300/6250] eta: 0:11:41 lr: 0.000028 grad: 0.1432 (0.1436) loss: 0.8790 (0.8789) time: 0.1924 data: 0.1048 max mem: 8233 +Train: [70] [2400/6250] eta: 0:11:18 lr: 0.000028 grad: 0.1414 (0.1436) loss: 0.8828 (0.8789) time: 0.1478 data: 0.0762 max mem: 8233 +Train: [70] [2500/6250] eta: 0:10:59 lr: 0.000028 grad: 0.1390 (0.1435) loss: 0.8778 (0.8790) time: 0.1513 data: 0.0579 max mem: 8233 +Train: [70] [2600/6250] eta: 0:10:41 lr: 0.000028 grad: 0.1324 (0.1435) loss: 0.8818 (0.8791) time: 0.1683 data: 0.0846 max mem: 8233 +Train: [70] [2700/6250] eta: 0:10:23 lr: 0.000028 grad: 0.1477 (0.1435) loss: 0.8763 (0.8791) time: 0.1693 data: 0.0837 max mem: 8233 +Train: [70] [2800/6250] eta: 0:10:03 lr: 0.000028 grad: 0.1343 (0.1434) loss: 0.8851 (0.8791) time: 0.1908 data: 0.1012 max mem: 8233 +Train: [70] [2900/6250] eta: 0:09:43 lr: 0.000028 grad: 0.1329 (0.1431) loss: 0.8879 (0.8792) time: 0.1639 data: 0.0732 max mem: 8233 +Train: [70] [3000/6250] eta: 0:09:24 lr: 0.000027 grad: 0.1445 (0.1432) loss: 0.8817 (0.8793) time: 0.1700 data: 0.0820 max mem: 8233 +Train: [70] [3100/6250] eta: 0:09:04 lr: 0.000027 grad: 0.1447 (0.1434) loss: 0.8822 (0.8793) time: 0.1520 data: 0.0601 max mem: 8233 +Train: [70] [3200/6250] eta: 0:08:45 lr: 0.000027 grad: 0.1390 (0.1434) loss: 0.8842 (0.8793) time: 0.1544 data: 0.0734 max mem: 8233 +Train: [70] [3300/6250] eta: 0:08:26 lr: 0.000027 grad: 0.1399 (0.1435) loss: 0.8803 (0.8793) time: 0.1602 data: 0.0813 max mem: 8233 +Train: [70] [3400/6250] eta: 0:08:08 lr: 0.000027 grad: 0.1468 (0.1438) loss: 0.8807 (0.8793) time: 0.1456 data: 0.0638 max mem: 8233 +Train: [70] [3500/6250] eta: 0:07:51 lr: 0.000027 grad: 0.1307 (0.1438) loss: 0.8837 (0.8794) time: 0.1773 data: 0.0924 max mem: 8233 +Train: [70] [3600/6250] eta: 0:07:33 lr: 0.000027 grad: 0.1330 (0.1437) loss: 0.8839 (0.8794) time: 0.1450 data: 0.0640 max mem: 8233 +Train: [70] [3700/6250] eta: 0:07:15 lr: 0.000027 grad: 0.1340 (0.1437) loss: 0.8778 (0.8794) time: 0.1750 data: 0.0964 max mem: 8233 +Train: [70] [3800/6250] eta: 0:06:57 lr: 0.000027 grad: 0.1359 (0.1437) loss: 0.8844 (0.8795) time: 0.1476 data: 0.0511 max mem: 8233 +Train: [70] [3900/6250] eta: 0:06:39 lr: 0.000027 grad: 0.1399 (0.1438) loss: 0.8852 (0.8795) time: 0.1472 data: 0.0635 max mem: 8233 +Train: [70] [4000/6250] eta: 0:06:23 lr: 0.000027 grad: 0.1307 (0.1438) loss: 0.8820 (0.8795) time: 0.3217 data: 0.2191 max mem: 8233 +Train: [70] [4100/6250] eta: 0:06:05 lr: 0.000027 grad: 0.1424 (0.1438) loss: 0.8785 (0.8796) time: 0.1578 data: 0.0832 max mem: 8233 +Train: [70] [4200/6250] eta: 0:05:48 lr: 0.000027 grad: 0.1386 (0.1439) loss: 0.8779 (0.8796) time: 0.1217 data: 0.0003 max mem: 8233 +Train: [70] [4300/6250] eta: 0:05:31 lr: 0.000027 grad: 0.1407 (0.1440) loss: 0.8734 (0.8796) time: 0.1474 data: 0.0686 max mem: 8233 +Train: [70] [4400/6250] eta: 0:05:13 lr: 0.000027 grad: 0.1395 (0.1439) loss: 0.8853 (0.8796) time: 0.1901 data: 0.1045 max mem: 8233 +Train: [70] [4500/6250] eta: 0:04:56 lr: 0.000027 grad: 0.1315 (0.1439) loss: 0.8822 (0.8796) time: 0.1542 data: 0.0755 max mem: 8233 +Train: [70] [4600/6250] eta: 0:04:39 lr: 0.000027 grad: 0.1380 (0.1439) loss: 0.8788 (0.8796) time: 0.2225 data: 0.1428 max mem: 8233 +Train: [70] [4700/6250] eta: 0:04:21 lr: 0.000027 grad: 0.1372 (0.1439) loss: 0.8768 (0.8796) time: 0.1654 data: 0.0822 max mem: 8233 +Train: [70] [4800/6250] eta: 0:04:04 lr: 0.000027 grad: 0.1338 (0.1438) loss: 0.8820 (0.8796) time: 0.1872 data: 0.1137 max mem: 8233 +Train: [70] [4900/6250] eta: 0:03:47 lr: 0.000027 grad: 0.1317 (0.1438) loss: 0.8801 (0.8796) time: 0.1158 data: 0.0374 max mem: 8233 +Train: [70] [5000/6250] eta: 0:03:30 lr: 0.000027 grad: 0.1349 (0.1437) loss: 0.8750 (0.8796) time: 0.1477 data: 0.0641 max mem: 8233 +Train: [70] [5100/6250] eta: 0:03:13 lr: 0.000027 grad: 0.1414 (0.1437) loss: 0.8735 (0.8796) time: 0.1673 data: 0.0867 max mem: 8233 +Train: [70] [5200/6250] eta: 0:02:56 lr: 0.000027 grad: 0.1317 (0.1438) loss: 0.8744 (0.8795) time: 0.1645 data: 0.0843 max mem: 8233 +Train: [70] [5300/6250] eta: 0:02:39 lr: 0.000027 grad: 0.1422 (0.1437) loss: 0.8751 (0.8794) time: 0.1822 data: 0.0871 max mem: 8233 +Train: [70] [5400/6250] eta: 0:02:23 lr: 0.000027 grad: 0.1302 (0.1437) loss: 0.8738 (0.8794) time: 0.2134 data: 0.1243 max mem: 8233 +Train: [70] [5500/6250] eta: 0:02:06 lr: 0.000027 grad: 0.1332 (0.1437) loss: 0.8770 (0.8793) time: 0.1472 data: 0.0569 max mem: 8233 +Train: [70] [5600/6250] eta: 0:01:49 lr: 0.000027 grad: 0.1366 (0.1437) loss: 0.8723 (0.8793) time: 0.1666 data: 0.0935 max mem: 8233 +Train: [70] [5700/6250] eta: 0:01:32 lr: 0.000027 grad: 0.1432 (0.1437) loss: 0.8732 (0.8793) time: 0.1806 data: 0.1083 max mem: 8233 +Train: [70] [5800/6250] eta: 0:01:15 lr: 0.000027 grad: 0.1344 (0.1437) loss: 0.8789 (0.8793) time: 0.1885 data: 0.0913 max mem: 8233 +Train: [70] [5900/6250] eta: 0:00:58 lr: 0.000027 grad: 0.1338 (0.1437) loss: 0.8828 (0.8793) time: 0.1366 data: 0.0480 max mem: 8233 +Train: [70] [6000/6250] eta: 0:00:42 lr: 0.000027 grad: 0.1286 (0.1437) loss: 0.8811 (0.8793) time: 0.1848 data: 0.1096 max mem: 8233 +Train: [70] [6100/6250] eta: 0:00:25 lr: 0.000027 grad: 0.1429 (0.1437) loss: 0.8799 (0.8793) time: 0.3244 data: 0.2290 max mem: 8233 +Train: [70] [6200/6250] eta: 0:00:08 lr: 0.000027 grad: 0.1397 (0.1437) loss: 0.8771 (0.8792) time: 0.1574 data: 0.0793 max mem: 8233 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1459 (0.1438) loss: 0.8748 (0.8792) time: 0.1468 data: 0.0520 max mem: 8233 +Train: [70] Total time: 0:17:41 (0.1699 s / it) +Averaged stats: lr: 0.000027 grad: 0.1459 (0.1438) loss: 0.8748 (0.8792) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:06:40 loss: 0.8964 (0.8964) time: 6.4630 data: 6.4337 max mem: 8233 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8861 (0.8872) time: 0.1417 data: 0.1205 max mem: 8233 +Eval (hcp-train-subset): [70] Total time: 0:00:15 (0.2576 s / it) +Averaged stats (hcp-train-subset): loss: 0.8861 (0.8872) +Eval (hcp-val): [70] [ 0/62] eta: 0:04:19 loss: 0.8797 (0.8797) time: 4.1894 data: 4.1162 max mem: 8233 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8851 (0.8857) time: 0.1248 data: 0.1027 max mem: 8233 +Eval (hcp-val): [70] Total time: 0:00:14 (0.2393 s / it) +Averaged stats (hcp-val): loss: 0.8851 (0.8857) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 12:49:49 lr: 0.000027 grad: 0.1529 (0.1529) loss: 0.8883 (0.8883) time: 7.3903 data: 7.2769 max mem: 8233 +Train: [71] [ 100/6250] eta: 0:24:44 lr: 0.000027 grad: 0.1280 (0.1504) loss: 0.8756 (0.8860) time: 0.2011 data: 0.0964 max mem: 8233 +Train: [71] [ 200/6250] eta: 0:21:51 lr: 0.000027 grad: 0.1362 (0.1484) loss: 0.8759 (0.8818) time: 0.1970 data: 0.0818 max mem: 8233 +Train: [71] [ 300/6250] eta: 0:20:01 lr: 0.000027 grad: 0.1542 (0.1494) loss: 0.8740 (0.8797) time: 0.1565 data: 0.0405 max mem: 8233 +Train: [71] [ 400/6250] eta: 0:19:02 lr: 0.000026 grad: 0.1459 (0.1484) loss: 0.8709 (0.8781) time: 0.1772 data: 0.0778 max mem: 8233 +Train: [71] [ 500/6250] eta: 0:18:11 lr: 0.000026 grad: 0.1355 (0.1470) loss: 0.8794 (0.8773) time: 0.1456 data: 0.0488 max mem: 8233 +Train: [71] [ 600/6250] eta: 0:17:27 lr: 0.000026 grad: 0.1363 (0.1472) loss: 0.8758 (0.8768) time: 0.1645 data: 0.0678 max mem: 8233 +Train: [71] [ 700/6250] eta: 0:17:01 lr: 0.000026 grad: 0.1341 (0.1461) loss: 0.8761 (0.8767) time: 0.1420 data: 0.0449 max mem: 8233 +Train: [71] [ 800/6250] eta: 0:16:28 lr: 0.000026 grad: 0.1370 (0.1447) loss: 0.8790 (0.8771) time: 0.1745 data: 0.0785 max mem: 8233 +Train: [71] [ 900/6250] eta: 0:16:14 lr: 0.000026 grad: 0.1294 (0.1435) loss: 0.8836 (0.8774) time: 0.2381 data: 0.1369 max mem: 8233 +Train: [71] [1000/6250] eta: 0:15:39 lr: 0.000026 grad: 0.1319 (0.1425) loss: 0.8852 (0.8778) time: 0.1579 data: 0.0774 max mem: 8233 +Train: [71] [1100/6250] eta: 0:15:09 lr: 0.000026 grad: 0.1315 (0.1418) loss: 0.8770 (0.8778) time: 0.1380 data: 0.0612 max mem: 8233 +Train: [71] [1200/6250] eta: 0:14:50 lr: 0.000026 grad: 0.1329 (0.1414) loss: 0.8791 (0.8781) time: 0.1474 data: 0.0616 max mem: 8233 +Train: [71] [1300/6250] eta: 0:14:23 lr: 0.000026 grad: 0.1305 (0.1409) loss: 0.8792 (0.8783) time: 0.1504 data: 0.0709 max mem: 8233 +Train: [71] [1400/6250] eta: 0:13:59 lr: 0.000026 grad: 0.1240 (0.1404) loss: 0.8790 (0.8783) time: 0.1733 data: 0.1041 max mem: 8233 +Train: [71] [1500/6250] eta: 0:13:41 lr: 0.000026 grad: 0.1344 (0.1405) loss: 0.8746 (0.8783) time: 0.1630 data: 0.0854 max mem: 8233 +Train: [71] [1600/6250] eta: 0:13:24 lr: 0.000026 grad: 0.1300 (0.1401) loss: 0.8821 (0.8783) time: 0.1751 data: 0.0825 max mem: 8233 +Train: [71] [1700/6250] eta: 0:13:04 lr: 0.000026 grad: 0.1321 (0.1401) loss: 0.8778 (0.8784) time: 0.1676 data: 0.0904 max mem: 8233 +Train: [71] [1800/6250] eta: 0:12:43 lr: 0.000026 grad: 0.1388 (0.1403) loss: 0.8811 (0.8784) time: 0.1453 data: 0.0601 max mem: 8233 +Train: [71] [1900/6250] eta: 0:12:23 lr: 0.000026 grad: 0.1288 (0.1401) loss: 0.8872 (0.8784) time: 0.1437 data: 0.0505 max mem: 8233 +Train: [71] [2000/6250] eta: 0:12:04 lr: 0.000026 grad: 0.1331 (0.1402) loss: 0.8817 (0.8786) time: 0.1572 data: 0.0765 max mem: 8233 +Train: [71] [2100/6250] eta: 0:11:44 lr: 0.000026 grad: 0.1270 (0.1402) loss: 0.8827 (0.8787) time: 0.1625 data: 0.0687 max mem: 8233 +Train: [71] [2200/6250] eta: 0:11:25 lr: 0.000026 grad: 0.1401 (0.1400) loss: 0.8798 (0.8788) time: 0.1699 data: 0.0765 max mem: 8233 +Train: [71] [2300/6250] eta: 0:11:09 lr: 0.000026 grad: 0.1311 (0.1400) loss: 0.8788 (0.8789) time: 0.1921 data: 0.1197 max mem: 8233 +Train: [71] [2400/6250] eta: 0:10:51 lr: 0.000026 grad: 0.1246 (0.1400) loss: 0.8798 (0.8790) time: 0.1678 data: 0.0820 max mem: 8233 +Train: [71] [2500/6250] eta: 0:10:33 lr: 0.000026 grad: 0.1346 (0.1399) loss: 0.8800 (0.8792) time: 0.1421 data: 0.0398 max mem: 8233 +Train: [71] [2600/6250] eta: 0:10:14 lr: 0.000026 grad: 0.1333 (0.1399) loss: 0.8814 (0.8793) time: 0.1387 data: 0.0363 max mem: 8233 +Train: [71] [2700/6250] eta: 0:09:56 lr: 0.000026 grad: 0.1406 (0.1400) loss: 0.8800 (0.8794) time: 0.1567 data: 0.0702 max mem: 8233 +Train: [71] [2800/6250] eta: 0:09:38 lr: 0.000026 grad: 0.1334 (0.1399) loss: 0.8824 (0.8795) time: 0.1335 data: 0.0500 max mem: 8233 +Train: [71] [2900/6250] eta: 0:09:20 lr: 0.000026 grad: 0.1402 (0.1400) loss: 0.8785 (0.8796) time: 0.1305 data: 0.0535 max mem: 8233 +Train: [71] [3000/6250] eta: 0:09:02 lr: 0.000026 grad: 0.1343 (0.1401) loss: 0.8854 (0.8797) time: 0.1593 data: 0.0692 max mem: 8233 +Train: [71] [3100/6250] eta: 0:08:45 lr: 0.000026 grad: 0.1335 (0.1403) loss: 0.8851 (0.8797) time: 0.1163 data: 0.0224 max mem: 8233 +Train: [71] [3200/6250] eta: 0:08:33 lr: 0.000026 grad: 0.1375 (0.1406) loss: 0.8866 (0.8798) time: 0.4172 data: 0.3331 max mem: 8233 +Train: [71] [3300/6250] eta: 0:08:14 lr: 0.000026 grad: 0.1260 (0.1407) loss: 0.8778 (0.8799) time: 0.1692 data: 0.0869 max mem: 8233 +Train: [71] [3400/6250] eta: 0:07:58 lr: 0.000026 grad: 0.1371 (0.1408) loss: 0.8798 (0.8799) time: 0.1945 data: 0.1008 max mem: 8233 +Train: [71] [3500/6250] eta: 0:07:41 lr: 0.000026 grad: 0.1426 (0.1409) loss: 0.8756 (0.8799) time: 0.1005 data: 0.0227 max mem: 8233 +Train: [71] [3600/6250] eta: 0:07:26 lr: 0.000026 grad: 0.1426 (0.1411) loss: 0.8814 (0.8799) time: 0.1640 data: 0.0764 max mem: 8233 +Train: [71] [3700/6250] eta: 0:07:08 lr: 0.000026 grad: 0.1372 (0.1413) loss: 0.8844 (0.8798) time: 0.1293 data: 0.0270 max mem: 8233 +Train: [71] [3800/6250] eta: 0:06:51 lr: 0.000026 grad: 0.1438 (0.1415) loss: 0.8759 (0.8797) time: 0.1240 data: 0.0399 max mem: 8233 +Train: [71] [3900/6250] eta: 0:06:34 lr: 0.000026 grad: 0.1406 (0.1417) loss: 0.8830 (0.8797) time: 0.1892 data: 0.1217 max mem: 8233 +Train: [71] [4000/6250] eta: 0:06:18 lr: 0.000026 grad: 0.1378 (0.1417) loss: 0.8803 (0.8797) time: 0.1667 data: 0.0887 max mem: 8233 +Train: [71] [4100/6250] eta: 0:06:01 lr: 0.000026 grad: 0.1395 (0.1418) loss: 0.8780 (0.8797) time: 0.1811 data: 0.1101 max mem: 8233 +Train: [71] [4200/6250] eta: 0:05:44 lr: 0.000025 grad: 0.1322 (0.1418) loss: 0.8781 (0.8797) time: 0.1511 data: 0.0821 max mem: 8233 +Train: [71] [4300/6250] eta: 0:05:27 lr: 0.000025 grad: 0.1325 (0.1419) loss: 0.8815 (0.8797) time: 0.1688 data: 0.0879 max mem: 8233 +Train: [71] [4400/6250] eta: 0:05:10 lr: 0.000025 grad: 0.1399 (0.1419) loss: 0.8770 (0.8797) time: 0.1544 data: 0.0797 max mem: 8233 +Train: [71] [4500/6250] eta: 0:04:53 lr: 0.000025 grad: 0.1423 (0.1420) loss: 0.8790 (0.8797) time: 0.1716 data: 0.0975 max mem: 8233 +Train: [71] [4600/6250] eta: 0:04:36 lr: 0.000025 grad: 0.1248 (0.1419) loss: 0.8799 (0.8797) time: 0.1551 data: 0.0650 max mem: 8233 +Train: [71] [4700/6250] eta: 0:04:19 lr: 0.000025 grad: 0.1322 (0.1419) loss: 0.8830 (0.8798) time: 0.1333 data: 0.0501 max mem: 8233 +Train: [71] [4800/6250] eta: 0:04:02 lr: 0.000025 grad: 0.1364 (0.1420) loss: 0.8746 (0.8797) time: 0.1778 data: 0.1016 max mem: 8233 +Train: [71] [4900/6250] eta: 0:03:45 lr: 0.000025 grad: 0.1311 (0.1420) loss: 0.8803 (0.8797) time: 0.1455 data: 0.0704 max mem: 8233 +Train: [71] [5000/6250] eta: 0:03:28 lr: 0.000025 grad: 0.1422 (0.1419) loss: 0.8794 (0.8796) time: 0.1387 data: 0.0710 max mem: 8233 +Train: [71] [5100/6250] eta: 0:03:12 lr: 0.000025 grad: 0.1357 (0.1420) loss: 0.8816 (0.8796) time: 0.1671 data: 0.0858 max mem: 8233 +Train: [71] [5200/6250] eta: 0:02:55 lr: 0.000025 grad: 0.1422 (0.1420) loss: 0.8736 (0.8796) time: 0.2024 data: 0.1245 max mem: 8233 +Train: [71] [5300/6250] eta: 0:02:39 lr: 0.000025 grad: 0.1438 (0.1420) loss: 0.8737 (0.8796) time: 0.1472 data: 0.0552 max mem: 8233 +Train: [71] [5400/6250] eta: 0:02:22 lr: 0.000025 grad: 0.1351 (0.1420) loss: 0.8770 (0.8796) time: 0.1514 data: 0.0590 max mem: 8233 +Train: [71] [5500/6250] eta: 0:02:05 lr: 0.000025 grad: 0.1425 (0.1420) loss: 0.8797 (0.8795) time: 0.1950 data: 0.1050 max mem: 8233 +Train: [71] [5600/6250] eta: 0:01:48 lr: 0.000025 grad: 0.1427 (0.1422) loss: 0.8773 (0.8795) time: 0.1859 data: 0.1047 max mem: 8233 +Train: [71] [5700/6250] eta: 0:01:32 lr: 0.000025 grad: 0.1391 (0.1422) loss: 0.8829 (0.8794) time: 0.1535 data: 0.0610 max mem: 8233 +Train: [71] [5800/6250] eta: 0:01:15 lr: 0.000025 grad: 0.1436 (0.1423) loss: 0.8711 (0.8794) time: 0.1036 data: 0.0003 max mem: 8233 +Train: [71] [5900/6250] eta: 0:00:58 lr: 0.000025 grad: 0.1468 (0.1424) loss: 0.8777 (0.8793) time: 0.1654 data: 0.0816 max mem: 8233 +Train: [71] [6000/6250] eta: 0:00:41 lr: 0.000025 grad: 0.1338 (0.1424) loss: 0.8805 (0.8793) time: 0.1026 data: 0.0002 max mem: 8233 +Train: [71] [6100/6250] eta: 0:00:25 lr: 0.000025 grad: 0.1406 (0.1425) loss: 0.8807 (0.8792) time: 0.1503 data: 0.0613 max mem: 8233 +Train: [71] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.1438 (0.1425) loss: 0.8752 (0.8792) time: 0.1405 data: 0.0645 max mem: 8233 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1552 (0.1426) loss: 0.8734 (0.8792) time: 0.1221 data: 0.0505 max mem: 8233 +Train: [71] Total time: 0:17:34 (0.1687 s / it) +Averaged stats: lr: 0.000025 grad: 0.1552 (0.1426) loss: 0.8734 (0.8792) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:06:01 loss: 0.8988 (0.8988) time: 5.8280 data: 5.7849 max mem: 8233 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8857 (0.8877) time: 0.1440 data: 0.1222 max mem: 8233 +Eval (hcp-train-subset): [71] Total time: 0:00:15 (0.2473 s / it) +Averaged stats (hcp-train-subset): loss: 0.8857 (0.8877) +Eval (hcp-val): [71] [ 0/62] eta: 0:05:04 loss: 0.8819 (0.8819) time: 4.9191 data: 4.8689 max mem: 8233 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8840 (0.8853) time: 0.1353 data: 0.1148 max mem: 8233 +Eval (hcp-val): [71] Total time: 0:00:15 (0.2449 s / it) +Averaged stats (hcp-val): loss: 0.8840 (0.8853) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 10:44:59 lr: 0.000025 grad: 0.1628 (0.1628) loss: 0.9257 (0.9257) time: 6.1919 data: 5.9765 max mem: 8233 +Train: [72] [ 100/6250] eta: 0:24:00 lr: 0.000025 grad: 0.1257 (0.1425) loss: 0.8859 (0.8826) time: 0.1464 data: 0.0324 max mem: 8233 +Train: [72] [ 200/6250] eta: 0:20:19 lr: 0.000025 grad: 0.1290 (0.1375) loss: 0.8758 (0.8808) time: 0.1616 data: 0.0500 max mem: 8233 +Train: [72] [ 300/6250] eta: 0:18:58 lr: 0.000025 grad: 0.1246 (0.1359) loss: 0.8810 (0.8804) time: 0.1625 data: 0.0602 max mem: 8233 +Train: [72] [ 400/6250] eta: 0:18:04 lr: 0.000025 grad: 0.1318 (0.1362) loss: 0.8820 (0.8807) time: 0.1356 data: 0.0399 max mem: 8233 +Train: [72] [ 500/6250] eta: 0:17:20 lr: 0.000025 grad: 0.1212 (0.1362) loss: 0.8838 (0.8805) time: 0.1608 data: 0.0674 max mem: 8233 +Train: [72] [ 600/6250] eta: 0:16:41 lr: 0.000025 grad: 0.1259 (0.1355) loss: 0.8817 (0.8804) time: 0.1588 data: 0.0693 max mem: 8233 +Train: [72] [ 700/6250] eta: 0:16:32 lr: 0.000025 grad: 0.1256 (0.1354) loss: 0.8758 (0.8801) time: 0.1233 data: 0.0004 max mem: 8233 +Train: [72] [ 800/6250] eta: 0:16:10 lr: 0.000025 grad: 0.1313 (0.1359) loss: 0.8852 (0.8801) time: 0.1131 data: 0.0215 max mem: 8233 +Train: [72] [ 900/6250] eta: 0:15:48 lr: 0.000025 grad: 0.1312 (0.1365) loss: 0.8797 (0.8801) time: 0.1783 data: 0.0963 max mem: 8233 +Train: [72] [1000/6250] eta: 0:15:33 lr: 0.000025 grad: 0.1284 (0.1365) loss: 0.8769 (0.8801) time: 0.1348 data: 0.0241 max mem: 8233 +Train: [72] [1100/6250] eta: 0:15:11 lr: 0.000025 grad: 0.1416 (0.1368) loss: 0.8813 (0.8800) time: 0.1071 data: 0.0137 max mem: 8233 +Train: [72] [1200/6250] eta: 0:14:52 lr: 0.000025 grad: 0.1422 (0.1368) loss: 0.8713 (0.8800) time: 0.2313 data: 0.1540 max mem: 8233 +Train: [72] [1300/6250] eta: 0:14:21 lr: 0.000025 grad: 0.1361 (0.1370) loss: 0.8772 (0.8800) time: 0.1901 data: 0.0947 max mem: 8233 +Train: [72] [1400/6250] eta: 0:14:04 lr: 0.000025 grad: 0.1362 (0.1373) loss: 0.8839 (0.8800) time: 0.1558 data: 0.0757 max mem: 8233 +Train: [72] [1500/6250] eta: 0:13:46 lr: 0.000025 grad: 0.1316 (0.1372) loss: 0.8759 (0.8801) time: 0.1741 data: 0.0995 max mem: 8233 +Train: [72] [1600/6250] eta: 0:13:23 lr: 0.000025 grad: 0.1365 (0.1373) loss: 0.8788 (0.8802) time: 0.1706 data: 0.0936 max mem: 8233 +Train: [72] [1700/6250] eta: 0:13:03 lr: 0.000024 grad: 0.1355 (0.1373) loss: 0.8790 (0.8803) time: 0.1153 data: 0.0262 max mem: 8233 +Train: [72] [1800/6250] eta: 0:12:45 lr: 0.000024 grad: 0.1476 (0.1377) loss: 0.8814 (0.8803) time: 0.1402 data: 0.0489 max mem: 8233 +Train: [72] [1900/6250] eta: 0:12:26 lr: 0.000024 grad: 0.1330 (0.1377) loss: 0.8756 (0.8803) time: 0.1723 data: 0.0870 max mem: 8233 +Train: [72] [2000/6250] eta: 0:12:08 lr: 0.000024 grad: 0.1402 (0.1378) loss: 0.8781 (0.8803) time: 0.1768 data: 0.0897 max mem: 8233 +Train: [72] [2100/6250] eta: 0:11:49 lr: 0.000024 grad: 0.1359 (0.1379) loss: 0.8769 (0.8802) time: 0.1653 data: 0.0840 max mem: 8233 +Train: [72] [2200/6250] eta: 0:11:30 lr: 0.000024 grad: 0.1417 (0.1381) loss: 0.8747 (0.8801) time: 0.1531 data: 0.0691 max mem: 8233 +Train: [72] [2300/6250] eta: 0:11:14 lr: 0.000024 grad: 0.1299 (0.1381) loss: 0.8799 (0.8801) time: 0.2181 data: 0.1486 max mem: 8233 +Train: [72] [2400/6250] eta: 0:10:57 lr: 0.000024 grad: 0.1381 (0.1383) loss: 0.8811 (0.8801) time: 0.1164 data: 0.0427 max mem: 8233 +Train: [72] [2500/6250] eta: 0:10:38 lr: 0.000024 grad: 0.1391 (0.1384) loss: 0.8776 (0.8801) time: 0.1274 data: 0.0540 max mem: 8233 +Train: [72] [2600/6250] eta: 0:10:20 lr: 0.000024 grad: 0.1384 (0.1385) loss: 0.8846 (0.8802) time: 0.1409 data: 0.0562 max mem: 8233 +Train: [72] [2700/6250] eta: 0:10:03 lr: 0.000024 grad: 0.1363 (0.1388) loss: 0.8817 (0.8802) time: 0.1784 data: 0.0922 max mem: 8233 +Train: [72] [2800/6250] eta: 0:09:46 lr: 0.000024 grad: 0.1442 (0.1392) loss: 0.8757 (0.8802) time: 0.1869 data: 0.0987 max mem: 8233 +Train: [72] [2900/6250] eta: 0:09:27 lr: 0.000024 grad: 0.1312 (0.1394) loss: 0.8803 (0.8802) time: 0.1432 data: 0.0587 max mem: 8233 +Train: [72] [3000/6250] eta: 0:09:09 lr: 0.000024 grad: 0.1387 (0.1394) loss: 0.8786 (0.8801) time: 0.1514 data: 0.0851 max mem: 8233 +Train: [72] [3100/6250] eta: 0:08:50 lr: 0.000024 grad: 0.1322 (0.1395) loss: 0.8770 (0.8801) time: 0.1347 data: 0.0537 max mem: 8233 +Train: [72] [3200/6250] eta: 0:08:33 lr: 0.000024 grad: 0.1350 (0.1395) loss: 0.8771 (0.8800) time: 0.1798 data: 0.1084 max mem: 8233 +Train: [72] [3300/6250] eta: 0:08:16 lr: 0.000024 grad: 0.1439 (0.1396) loss: 0.8805 (0.8800) time: 0.1449 data: 0.0565 max mem: 8233 +Train: [72] [3400/6250] eta: 0:07:59 lr: 0.000024 grad: 0.1383 (0.1397) loss: 0.8843 (0.8800) time: 0.1864 data: 0.1140 max mem: 8233 +Train: [72] [3500/6250] eta: 0:07:42 lr: 0.000024 grad: 0.1430 (0.1398) loss: 0.8780 (0.8800) time: 0.2039 data: 0.1140 max mem: 8233 +Train: [72] [3600/6250] eta: 0:07:28 lr: 0.000024 grad: 0.1398 (0.1400) loss: 0.8734 (0.8800) time: 0.3615 data: 0.2380 max mem: 8233 +Train: [72] [3700/6250] eta: 0:07:12 lr: 0.000024 grad: 0.1474 (0.1401) loss: 0.8775 (0.8799) time: 0.2642 data: 0.1786 max mem: 8233 +Train: [72] [3800/6250] eta: 0:06:54 lr: 0.000024 grad: 0.1451 (0.1403) loss: 0.8800 (0.8799) time: 0.1768 data: 0.0936 max mem: 8233 +Train: [72] [3900/6250] eta: 0:06:38 lr: 0.000024 grad: 0.1434 (0.1405) loss: 0.8721 (0.8797) time: 0.1664 data: 0.0828 max mem: 8233 +Train: [72] [4000/6250] eta: 0:06:20 lr: 0.000024 grad: 0.1391 (0.1407) loss: 0.8757 (0.8797) time: 0.1008 data: 0.0099 max mem: 8233 +Train: [72] [4100/6250] eta: 0:06:03 lr: 0.000024 grad: 0.1366 (0.1408) loss: 0.8821 (0.8796) time: 0.1601 data: 0.0880 max mem: 8233 +Train: [72] [4200/6250] eta: 0:05:46 lr: 0.000024 grad: 0.1345 (0.1407) loss: 0.8765 (0.8796) time: 0.1653 data: 0.0915 max mem: 8233 +Train: [72] [4300/6250] eta: 0:05:28 lr: 0.000024 grad: 0.1439 (0.1408) loss: 0.8750 (0.8796) time: 0.1534 data: 0.0701 max mem: 8233 +Train: [72] [4400/6250] eta: 0:05:11 lr: 0.000024 grad: 0.1528 (0.1410) loss: 0.8700 (0.8795) time: 0.1411 data: 0.0525 max mem: 8233 +Train: [72] [4500/6250] eta: 0:04:53 lr: 0.000024 grad: 0.1385 (0.1409) loss: 0.8773 (0.8795) time: 0.1360 data: 0.0520 max mem: 8233 +Train: [72] [4600/6250] eta: 0:04:36 lr: 0.000024 grad: 0.1410 (0.1410) loss: 0.8771 (0.8795) time: 0.1598 data: 0.0880 max mem: 8233 +Train: [72] [4700/6250] eta: 0:04:19 lr: 0.000024 grad: 0.1377 (0.1409) loss: 0.8875 (0.8795) time: 0.1605 data: 0.0786 max mem: 8233 +Train: [72] [4800/6250] eta: 0:04:02 lr: 0.000024 grad: 0.1303 (0.1410) loss: 0.8775 (0.8795) time: 0.1616 data: 0.0837 max mem: 8233 +Train: [72] [4900/6250] eta: 0:03:45 lr: 0.000024 grad: 0.1311 (0.1410) loss: 0.8768 (0.8795) time: 0.1667 data: 0.0794 max mem: 8233 +Train: [72] [5000/6250] eta: 0:03:29 lr: 0.000024 grad: 0.1378 (0.1410) loss: 0.8807 (0.8795) time: 0.1580 data: 0.0755 max mem: 8233 +Train: [72] [5100/6250] eta: 0:03:12 lr: 0.000024 grad: 0.1427 (0.1410) loss: 0.8749 (0.8795) time: 0.1565 data: 0.0757 max mem: 8233 +Train: [72] [5200/6250] eta: 0:02:55 lr: 0.000024 grad: 0.1422 (0.1411) loss: 0.8820 (0.8795) time: 0.2044 data: 0.1267 max mem: 8233 +Train: [72] [5300/6250] eta: 0:02:39 lr: 0.000024 grad: 0.1355 (0.1410) loss: 0.8822 (0.8795) time: 0.1100 data: 0.0202 max mem: 8233 +Train: [72] [5400/6250] eta: 0:02:22 lr: 0.000024 grad: 0.1382 (0.1410) loss: 0.8712 (0.8795) time: 0.1687 data: 0.0866 max mem: 8233 +Train: [72] [5500/6250] eta: 0:02:06 lr: 0.000023 grad: 0.1463 (0.1411) loss: 0.8811 (0.8794) time: 0.2043 data: 0.1158 max mem: 8233 +Train: [72] [5600/6250] eta: 0:01:49 lr: 0.000023 grad: 0.1334 (0.1411) loss: 0.8811 (0.8794) time: 0.1751 data: 0.0834 max mem: 8233 +Train: [72] [5700/6250] eta: 0:01:32 lr: 0.000023 grad: 0.1369 (0.1412) loss: 0.8792 (0.8794) time: 0.1522 data: 0.0720 max mem: 8233 +Train: [72] [5800/6250] eta: 0:01:15 lr: 0.000023 grad: 0.1327 (0.1412) loss: 0.8776 (0.8794) time: 0.2209 data: 0.1355 max mem: 8233 +Train: [72] [5900/6250] eta: 0:00:58 lr: 0.000023 grad: 0.1376 (0.1412) loss: 0.8794 (0.8794) time: 0.1960 data: 0.1056 max mem: 8233 +Train: [72] [6000/6250] eta: 0:00:42 lr: 0.000023 grad: 0.1443 (0.1413) loss: 0.8729 (0.8794) time: 0.2204 data: 0.1450 max mem: 8233 +Train: [72] [6100/6250] eta: 0:00:25 lr: 0.000023 grad: 0.1312 (0.1413) loss: 0.8790 (0.8794) time: 0.1711 data: 0.0883 max mem: 8233 +Train: [72] [6200/6250] eta: 0:00:08 lr: 0.000023 grad: 0.1359 (0.1412) loss: 0.8724 (0.8794) time: 0.1624 data: 0.0766 max mem: 8233 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1328 (0.1412) loss: 0.8752 (0.8794) time: 0.2284 data: 0.1325 max mem: 8233 +Train: [72] Total time: 0:17:39 (0.1695 s / it) +Averaged stats: lr: 0.000023 grad: 0.1328 (0.1412) loss: 0.8752 (0.8794) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:05:33 loss: 0.8929 (0.8929) time: 5.3802 data: 5.2886 max mem: 8233 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8829 (0.8869) time: 0.1504 data: 0.1294 max mem: 8233 +Eval (hcp-train-subset): [72] Total time: 0:00:16 (0.2644 s / it) +Averaged stats (hcp-train-subset): loss: 0.8829 (0.8869) +Eval (hcp-val): [72] [ 0/62] eta: 0:04:20 loss: 0.8800 (0.8800) time: 4.2027 data: 4.1451 max mem: 8233 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8839 (0.8853) time: 0.1214 data: 0.1000 max mem: 8233 +Eval (hcp-val): [72] Total time: 0:00:15 (0.2464 s / it) +Averaged stats (hcp-val): loss: 0.8839 (0.8853) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 13:40:52 lr: 0.000023 grad: 0.4632 (0.4632) loss: 0.8693 (0.8693) time: 7.8803 data: 7.7777 max mem: 8233 +Train: [73] [ 100/6250] eta: 0:24:38 lr: 0.000023 grad: 0.1309 (0.1531) loss: 0.8785 (0.8821) time: 0.1690 data: 0.0583 max mem: 8233 +Train: [73] [ 200/6250] eta: 0:21:11 lr: 0.000023 grad: 0.1233 (0.1490) loss: 0.8856 (0.8806) time: 0.1692 data: 0.0540 max mem: 8233 +Train: [73] [ 300/6250] eta: 0:19:52 lr: 0.000023 grad: 0.1451 (0.1493) loss: 0.8779 (0.8791) time: 0.1729 data: 0.0647 max mem: 8233 +Train: [73] [ 400/6250] eta: 0:19:07 lr: 0.000023 grad: 0.1468 (0.1501) loss: 0.8771 (0.8789) time: 0.1804 data: 0.0676 max mem: 8233 +Train: [73] [ 500/6250] eta: 0:18:22 lr: 0.000023 grad: 0.1344 (0.1487) loss: 0.8816 (0.8792) time: 0.2011 data: 0.1105 max mem: 8233 +Train: [73] [ 600/6250] eta: 0:17:38 lr: 0.000023 grad: 0.1316 (0.1477) loss: 0.8800 (0.8793) time: 0.1802 data: 0.0886 max mem: 8233 +Train: [73] [ 700/6250] eta: 0:17:11 lr: 0.000023 grad: 0.1318 (0.1469) loss: 0.8829 (0.8796) time: 0.2205 data: 0.1156 max mem: 8233 +Train: [73] [ 800/6250] eta: 0:16:50 lr: 0.000023 grad: 0.1377 (0.1465) loss: 0.8808 (0.8796) time: 0.1675 data: 0.0691 max mem: 8233 +Train: [73] [ 900/6250] eta: 0:16:22 lr: 0.000023 grad: 0.1288 (0.1458) loss: 0.8834 (0.8800) time: 0.1898 data: 0.0911 max mem: 8233 +Train: [73] [1000/6250] eta: 0:15:59 lr: 0.000023 grad: 0.1314 (0.1452) loss: 0.8831 (0.8800) time: 0.1704 data: 0.0873 max mem: 8233 +Train: [73] [1100/6250] eta: 0:15:36 lr: 0.000023 grad: 0.1247 (0.1451) loss: 0.8810 (0.8802) time: 0.1747 data: 0.0852 max mem: 8233 +Train: [73] [1200/6250] eta: 0:15:17 lr: 0.000023 grad: 0.1272 (0.1450) loss: 0.8864 (0.8802) time: 0.1296 data: 0.0315 max mem: 8233 +Train: [73] [1300/6250] eta: 0:14:59 lr: 0.000023 grad: 0.1369 (0.1447) loss: 0.8802 (0.8802) time: 0.2422 data: 0.1727 max mem: 8233 +Train: [73] [1400/6250] eta: 0:14:30 lr: 0.000023 grad: 0.1364 (0.1446) loss: 0.8809 (0.8802) time: 0.1426 data: 0.0502 max mem: 8233 +Train: [73] [1500/6250] eta: 0:14:12 lr: 0.000023 grad: 0.1419 (0.1444) loss: 0.8812 (0.8801) time: 0.1418 data: 0.0447 max mem: 8233 +Train: [73] [1600/6250] eta: 0:13:54 lr: 0.000023 grad: 0.1337 (0.1441) loss: 0.8821 (0.8802) time: 0.2436 data: 0.1659 max mem: 8233 +Train: [73] [1700/6250] eta: 0:13:31 lr: 0.000023 grad: 0.1434 (0.1444) loss: 0.8806 (0.8801) time: 0.1711 data: 0.1023 max mem: 8233 +Train: [73] [1800/6250] eta: 0:13:11 lr: 0.000023 grad: 0.1319 (0.1444) loss: 0.8835 (0.8800) time: 0.1646 data: 0.0887 max mem: 8233 +Train: [73] [1900/6250] eta: 0:12:53 lr: 0.000023 grad: 0.1343 (0.1444) loss: 0.8860 (0.8799) time: 0.2007 data: 0.1209 max mem: 8233 +Train: [73] [2000/6250] eta: 0:12:36 lr: 0.000023 grad: 0.1387 (0.1447) loss: 0.8816 (0.8799) time: 0.1913 data: 0.0888 max mem: 8233 +Train: [73] [2100/6250] eta: 0:12:15 lr: 0.000023 grad: 0.1339 (0.1447) loss: 0.8830 (0.8799) time: 0.1500 data: 0.0741 max mem: 8233 +Train: [73] [2200/6250] eta: 0:11:55 lr: 0.000023 grad: 0.1528 (0.1448) loss: 0.8785 (0.8799) time: 0.1706 data: 0.0951 max mem: 8233 +Train: [73] [2300/6250] eta: 0:11:35 lr: 0.000023 grad: 0.1387 (0.1451) loss: 0.8815 (0.8798) time: 0.1797 data: 0.0982 max mem: 8233 +Train: [73] [2400/6250] eta: 0:11:23 lr: 0.000023 grad: 0.1464 (0.1455) loss: 0.8808 (0.8798) time: 0.0929 data: 0.0002 max mem: 8233 +Train: [73] [2500/6250] eta: 0:11:01 lr: 0.000023 grad: 0.1381 (0.1456) loss: 0.8813 (0.8797) time: 0.1387 data: 0.0653 max mem: 8233 +Train: [73] [2600/6250] eta: 0:10:41 lr: 0.000023 grad: 0.1442 (0.1457) loss: 0.8751 (0.8797) time: 0.1625 data: 0.0968 max mem: 8233 +Train: [73] [2700/6250] eta: 0:10:21 lr: 0.000023 grad: 0.1493 (0.1459) loss: 0.8800 (0.8797) time: 0.1582 data: 0.0710 max mem: 8233 +Train: [73] [2800/6250] eta: 0:10:02 lr: 0.000023 grad: 0.1402 (0.1459) loss: 0.8799 (0.8798) time: 0.1598 data: 0.0723 max mem: 8233 +Train: [73] [2900/6250] eta: 0:09:43 lr: 0.000023 grad: 0.1457 (0.1460) loss: 0.8730 (0.8798) time: 0.1599 data: 0.0711 max mem: 8233 +Train: [73] [3000/6250] eta: 0:09:23 lr: 0.000023 grad: 0.1378 (0.1459) loss: 0.8787 (0.8798) time: 0.1541 data: 0.0801 max mem: 8233 +Train: [73] [3100/6250] eta: 0:09:04 lr: 0.000023 grad: 0.1364 (0.1459) loss: 0.8787 (0.8798) time: 0.1408 data: 0.0484 max mem: 8233 +Train: [73] [3200/6250] eta: 0:08:46 lr: 0.000022 grad: 0.1350 (0.1458) loss: 0.8868 (0.8799) time: 0.1386 data: 0.0573 max mem: 8233 +Train: [73] [3300/6250] eta: 0:08:26 lr: 0.000022 grad: 0.1371 (0.1459) loss: 0.8845 (0.8800) time: 0.1640 data: 0.0803 max mem: 8233 +Train: [73] [3400/6250] eta: 0:08:09 lr: 0.000022 grad: 0.1404 (0.1458) loss: 0.8812 (0.8800) time: 0.1398 data: 0.0460 max mem: 8233 +Train: [73] [3500/6250] eta: 0:07:58 lr: 0.000022 grad: 0.1397 (0.1458) loss: 0.8809 (0.8800) time: 0.5347 data: 0.4243 max mem: 8233 +Train: [73] [3600/6250] eta: 0:07:41 lr: 0.000022 grad: 0.1357 (0.1457) loss: 0.8823 (0.8801) time: 0.2053 data: 0.1164 max mem: 8233 +Train: [73] [3700/6250] eta: 0:07:26 lr: 0.000022 grad: 0.1347 (0.1455) loss: 0.8814 (0.8801) time: 0.1734 data: 0.0673 max mem: 8233 +Train: [73] [3800/6250] eta: 0:07:07 lr: 0.000022 grad: 0.1445 (0.1455) loss: 0.8749 (0.8801) time: 0.1672 data: 0.0770 max mem: 8233 +Train: [73] [3900/6250] eta: 0:06:49 lr: 0.000022 grad: 0.1464 (0.1454) loss: 0.8813 (0.8801) time: 0.1389 data: 0.0569 max mem: 8233 +Train: [73] [4000/6250] eta: 0:06:31 lr: 0.000022 grad: 0.1387 (0.1453) loss: 0.8781 (0.8801) time: 0.1529 data: 0.0631 max mem: 8233 +Train: [73] [4100/6250] eta: 0:06:13 lr: 0.000022 grad: 0.1400 (0.1452) loss: 0.8793 (0.8801) time: 0.1717 data: 0.0966 max mem: 8233 +Train: [73] [4200/6250] eta: 0:05:55 lr: 0.000022 grad: 0.1420 (0.1450) loss: 0.8771 (0.8802) time: 0.1940 data: 0.1067 max mem: 8233 +Train: [73] [4300/6250] eta: 0:05:37 lr: 0.000022 grad: 0.1451 (0.1451) loss: 0.8803 (0.8802) time: 0.1977 data: 0.1188 max mem: 8233 +Train: [73] [4400/6250] eta: 0:05:19 lr: 0.000022 grad: 0.1433 (0.1450) loss: 0.8781 (0.8802) time: 0.1528 data: 0.0827 max mem: 8233 +Train: [73] [4500/6250] eta: 0:05:01 lr: 0.000022 grad: 0.1414 (0.1450) loss: 0.8775 (0.8803) time: 0.1351 data: 0.0614 max mem: 8233 +Train: [73] [4600/6250] eta: 0:04:44 lr: 0.000022 grad: 0.1368 (0.1450) loss: 0.8776 (0.8803) time: 0.2411 data: 0.1696 max mem: 8233 +Train: [73] [4700/6250] eta: 0:04:27 lr: 0.000022 grad: 0.1426 (0.1450) loss: 0.8805 (0.8803) time: 0.1465 data: 0.0359 max mem: 8233 +Train: [73] [4800/6250] eta: 0:04:10 lr: 0.000022 grad: 0.1348 (0.1450) loss: 0.8792 (0.8803) time: 0.1764 data: 0.0930 max mem: 8233 +Train: [73] [4900/6250] eta: 0:03:53 lr: 0.000022 grad: 0.1372 (0.1450) loss: 0.8790 (0.8802) time: 0.1022 data: 0.0002 max mem: 8233 +Train: [73] [5000/6250] eta: 0:03:36 lr: 0.000022 grad: 0.1421 (0.1450) loss: 0.8802 (0.8802) time: 0.2143 data: 0.1340 max mem: 8233 +Train: [73] [5100/6250] eta: 0:03:20 lr: 0.000022 grad: 0.1372 (0.1450) loss: 0.8765 (0.8802) time: 0.1375 data: 0.0670 max mem: 8233 +Train: [73] [5200/6250] eta: 0:03:02 lr: 0.000022 grad: 0.1409 (0.1449) loss: 0.8835 (0.8803) time: 0.1913 data: 0.1176 max mem: 8233 +Train: [73] [5300/6250] eta: 0:02:45 lr: 0.000022 grad: 0.1452 (0.1448) loss: 0.8787 (0.8802) time: 0.1448 data: 0.0717 max mem: 8233 +Train: [73] [5400/6250] eta: 0:02:28 lr: 0.000022 grad: 0.1419 (0.1448) loss: 0.8801 (0.8802) time: 0.1853 data: 0.0996 max mem: 8233 +Train: [73] [5500/6250] eta: 0:02:10 lr: 0.000022 grad: 0.1393 (0.1447) loss: 0.8751 (0.8802) time: 0.1931 data: 0.1010 max mem: 8233 +Train: [73] [5600/6250] eta: 0:01:53 lr: 0.000022 grad: 0.1410 (0.1447) loss: 0.8784 (0.8802) time: 0.1703 data: 0.0873 max mem: 8233 +Train: [73] [5700/6250] eta: 0:01:36 lr: 0.000022 grad: 0.1375 (0.1447) loss: 0.8798 (0.8802) time: 0.2054 data: 0.1314 max mem: 8233 +Train: [73] [5800/6250] eta: 0:01:18 lr: 0.000022 grad: 0.1373 (0.1447) loss: 0.8789 (0.8802) time: 0.1340 data: 0.0458 max mem: 8233 +Train: [73] [5900/6250] eta: 0:01:01 lr: 0.000022 grad: 0.1307 (0.1446) loss: 0.8810 (0.8801) time: 0.1878 data: 0.0688 max mem: 8233 +Train: [73] [6000/6250] eta: 0:00:43 lr: 0.000022 grad: 0.1375 (0.1446) loss: 0.8770 (0.8801) time: 0.1504 data: 0.0580 max mem: 8233 +Train: [73] [6100/6250] eta: 0:00:26 lr: 0.000022 grad: 0.1381 (0.1445) loss: 0.8770 (0.8801) time: 0.1739 data: 0.0922 max mem: 8233 +Train: [73] [6200/6250] eta: 0:00:08 lr: 0.000022 grad: 0.1402 (0.1445) loss: 0.8791 (0.8800) time: 0.1707 data: 0.0834 max mem: 8233 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1426 (0.1445) loss: 0.8836 (0.8800) time: 0.1664 data: 0.0822 max mem: 8233 +Train: [73] Total time: 0:18:19 (0.1759 s / it) +Averaged stats: lr: 0.000022 grad: 0.1426 (0.1445) loss: 0.8836 (0.8800) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:05:15 loss: 0.8971 (0.8971) time: 5.0917 data: 5.0273 max mem: 8233 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8857 (0.8867) time: 0.1401 data: 0.1193 max mem: 8233 +Eval (hcp-train-subset): [73] Total time: 0:00:15 (0.2422 s / it) +Averaged stats (hcp-train-subset): loss: 0.8857 (0.8867) +Eval (hcp-val): [73] [ 0/62] eta: 0:05:53 loss: 0.8792 (0.8792) time: 5.6963 data: 5.6677 max mem: 8233 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8837 (0.8847) time: 0.1545 data: 0.1337 max mem: 8233 +Eval (hcp-val): [73] Total time: 0:00:15 (0.2425 s / it) +Averaged stats (hcp-val): loss: 0.8837 (0.8847) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 11:21:41 lr: 0.000022 grad: 0.1547 (0.1547) loss: 0.8895 (0.8895) time: 6.5443 data: 6.4161 max mem: 8233 +Train: [74] [ 100/6250] eta: 0:23:37 lr: 0.000022 grad: 0.1427 (0.1524) loss: 0.8875 (0.8870) time: 0.1696 data: 0.0568 max mem: 8233 +Train: [74] [ 200/6250] eta: 0:20:45 lr: 0.000022 grad: 0.1413 (0.1508) loss: 0.8820 (0.8832) time: 0.1670 data: 0.0562 max mem: 8233 +Train: [74] [ 300/6250] eta: 0:19:33 lr: 0.000022 grad: 0.1415 (0.1477) loss: 0.8772 (0.8824) time: 0.2446 data: 0.1394 max mem: 8233 +Train: [74] [ 400/6250] eta: 0:18:34 lr: 0.000022 grad: 0.1367 (0.1447) loss: 0.8838 (0.8820) time: 0.1939 data: 0.1075 max mem: 8233 +Train: [74] [ 500/6250] eta: 0:17:57 lr: 0.000022 grad: 0.1337 (0.1431) loss: 0.8804 (0.8822) time: 0.1133 data: 0.0004 max mem: 8233 +Train: [74] [ 600/6250] eta: 0:17:13 lr: 0.000022 grad: 0.1371 (0.1420) loss: 0.8864 (0.8826) time: 0.1723 data: 0.0923 max mem: 8233 +Train: [74] [ 700/6250] eta: 0:17:50 lr: 0.000022 grad: 0.1339 (0.1413) loss: 0.8808 (0.8827) time: 0.1889 data: 0.0781 max mem: 8233 +Train: [74] [ 800/6250] eta: 0:17:27 lr: 0.000022 grad: 0.1321 (0.1413) loss: 0.8780 (0.8824) time: 0.2566 data: 0.1554 max mem: 8233 +Train: [74] [ 900/6250] eta: 0:17:06 lr: 0.000021 grad: 0.1267 (0.1411) loss: 0.8779 (0.8821) time: 0.1467 data: 0.0488 max mem: 8233 +Train: [74] [1000/6250] eta: 0:16:47 lr: 0.000021 grad: 0.1403 (0.1411) loss: 0.8780 (0.8819) time: 0.3062 data: 0.1933 max mem: 8233 +Train: [74] [1100/6250] eta: 0:16:04 lr: 0.000021 grad: 0.1297 (0.1409) loss: 0.8812 (0.8819) time: 0.1857 data: 0.1122 max mem: 8233 +Train: [74] [1200/6250] eta: 0:15:35 lr: 0.000021 grad: 0.1394 (0.1407) loss: 0.8797 (0.8817) time: 0.1985 data: 0.1117 max mem: 8233 +Train: [74] [1300/6250] eta: 0:15:06 lr: 0.000021 grad: 0.1368 (0.1405) loss: 0.8781 (0.8815) time: 0.1709 data: 0.0872 max mem: 8233 +Train: [74] [1400/6250] eta: 0:14:40 lr: 0.000021 grad: 0.1382 (0.1406) loss: 0.8793 (0.8814) time: 0.1566 data: 0.0752 max mem: 8233 +Train: [74] [1500/6250] eta: 0:14:22 lr: 0.000021 grad: 0.1406 (0.1410) loss: 0.8808 (0.8813) time: 0.2069 data: 0.1252 max mem: 8233 +Train: [74] [1600/6250] eta: 0:13:59 lr: 0.000021 grad: 0.1359 (0.1411) loss: 0.8726 (0.8810) time: 0.1812 data: 0.0963 max mem: 8233 +Train: [74] [1700/6250] eta: 0:13:44 lr: 0.000021 grad: 0.1499 (0.1413) loss: 0.8716 (0.8808) time: 0.3161 data: 0.2013 max mem: 8233 +Train: [74] [1800/6250] eta: 0:13:24 lr: 0.000021 grad: 0.1359 (0.1412) loss: 0.8812 (0.8807) time: 0.1494 data: 0.0657 max mem: 8233 +Train: [74] [1900/6250] eta: 0:13:02 lr: 0.000021 grad: 0.1448 (0.1413) loss: 0.8828 (0.8807) time: 0.1443 data: 0.0641 max mem: 8233 +Train: [74] [2000/6250] eta: 0:12:40 lr: 0.000021 grad: 0.1336 (0.1415) loss: 0.8829 (0.8806) time: 0.1655 data: 0.0825 max mem: 8233 +Train: [74] [2100/6250] eta: 0:12:20 lr: 0.000021 grad: 0.1337 (0.1415) loss: 0.8848 (0.8806) time: 0.1636 data: 0.0701 max mem: 8233 +Train: [74] [2200/6250] eta: 0:12:01 lr: 0.000021 grad: 0.1402 (0.1415) loss: 0.8787 (0.8805) time: 0.1752 data: 0.0849 max mem: 8233 +Train: [74] [2300/6250] eta: 0:11:43 lr: 0.000021 grad: 0.1393 (0.1414) loss: 0.8819 (0.8805) time: 0.1716 data: 0.0973 max mem: 8233 +Train: [74] [2400/6250] eta: 0:11:22 lr: 0.000021 grad: 0.1359 (0.1413) loss: 0.8800 (0.8804) time: 0.1817 data: 0.0921 max mem: 8233 +Train: [74] [2500/6250] eta: 0:11:03 lr: 0.000021 grad: 0.1408 (0.1414) loss: 0.8785 (0.8803) time: 0.1706 data: 0.0973 max mem: 8233 +Train: [74] [2600/6250] eta: 0:10:43 lr: 0.000021 grad: 0.1339 (0.1415) loss: 0.8793 (0.8803) time: 0.1521 data: 0.0741 max mem: 8233 +Train: [74] [2700/6250] eta: 0:10:23 lr: 0.000021 grad: 0.1395 (0.1416) loss: 0.8754 (0.8803) time: 0.1808 data: 0.1013 max mem: 8233 +Train: [74] [2800/6250] eta: 0:10:04 lr: 0.000021 grad: 0.1432 (0.1416) loss: 0.8809 (0.8803) time: 0.1740 data: 0.0902 max mem: 8233 +Train: [74] [2900/6250] eta: 0:09:45 lr: 0.000021 grad: 0.1384 (0.1418) loss: 0.8823 (0.8804) time: 0.1681 data: 0.0795 max mem: 8233 +Train: [74] [3000/6250] eta: 0:09:26 lr: 0.000021 grad: 0.1385 (0.1418) loss: 0.8822 (0.8804) time: 0.1727 data: 0.0839 max mem: 8233 +Train: [74] [3100/6250] eta: 0:09:06 lr: 0.000021 grad: 0.1388 (0.1419) loss: 0.8825 (0.8805) time: 0.1563 data: 0.0762 max mem: 8233 +Train: [74] [3200/6250] eta: 0:08:47 lr: 0.000021 grad: 0.1351 (0.1419) loss: 0.8792 (0.8804) time: 0.1890 data: 0.1102 max mem: 8233 +Train: [74] [3300/6250] eta: 0:08:30 lr: 0.000021 grad: 0.1374 (0.1420) loss: 0.8743 (0.8804) time: 0.1639 data: 0.0858 max mem: 8233 +Train: [74] [3400/6250] eta: 0:08:12 lr: 0.000021 grad: 0.1406 (0.1423) loss: 0.8770 (0.8804) time: 0.1592 data: 0.0818 max mem: 8233 +Train: [74] [3500/6250] eta: 0:07:54 lr: 0.000021 grad: 0.1315 (0.1423) loss: 0.8769 (0.8804) time: 0.1391 data: 0.0585 max mem: 8233 +Train: [74] [3600/6250] eta: 0:07:37 lr: 0.000021 grad: 0.1338 (0.1425) loss: 0.8760 (0.8803) time: 0.1519 data: 0.0760 max mem: 8233 +Train: [74] [3700/6250] eta: 0:07:20 lr: 0.000021 grad: 0.1424 (0.1427) loss: 0.8826 (0.8803) time: 0.1755 data: 0.1038 max mem: 8233 +Train: [74] [3800/6250] eta: 0:07:04 lr: 0.000021 grad: 0.1368 (0.1427) loss: 0.8772 (0.8803) time: 0.1434 data: 0.0695 max mem: 8233 +Train: [74] [3900/6250] eta: 0:06:46 lr: 0.000021 grad: 0.1402 (0.1428) loss: 0.8793 (0.8802) time: 0.1465 data: 0.0656 max mem: 8233 +Train: [74] [4000/6250] eta: 0:06:29 lr: 0.000021 grad: 0.1385 (0.1427) loss: 0.8790 (0.8802) time: 0.1253 data: 0.0517 max mem: 8233 +Train: [74] [4100/6250] eta: 0:06:12 lr: 0.000021 grad: 0.1327 (0.1426) loss: 0.8774 (0.8802) time: 0.1205 data: 0.0005 max mem: 8233 +Train: [74] [4200/6250] eta: 0:05:57 lr: 0.000021 grad: 0.1333 (0.1426) loss: 0.8814 (0.8802) time: 0.2929 data: 0.2068 max mem: 8233 +Train: [74] [4300/6250] eta: 0:05:39 lr: 0.000021 grad: 0.1377 (0.1427) loss: 0.8778 (0.8801) time: 0.1553 data: 0.0599 max mem: 8233 +Train: [74] [4400/6250] eta: 0:05:22 lr: 0.000021 grad: 0.1434 (0.1427) loss: 0.8746 (0.8801) time: 0.2878 data: 0.1664 max mem: 8233 +Train: [74] [4500/6250] eta: 0:05:06 lr: 0.000021 grad: 0.1402 (0.1428) loss: 0.8810 (0.8801) time: 0.1975 data: 0.1199 max mem: 8233 +Train: [74] [4600/6250] eta: 0:04:48 lr: 0.000021 grad: 0.1461 (0.1429) loss: 0.8789 (0.8801) time: 0.1570 data: 0.0377 max mem: 8233 +Train: [74] [4700/6250] eta: 0:04:31 lr: 0.000021 grad: 0.1320 (0.1429) loss: 0.8791 (0.8801) time: 0.1694 data: 0.0846 max mem: 8233 +Train: [74] [4800/6250] eta: 0:04:14 lr: 0.000021 grad: 0.1382 (0.1429) loss: 0.8818 (0.8802) time: 0.1672 data: 0.0951 max mem: 8233 +Train: [74] [4900/6250] eta: 0:03:56 lr: 0.000020 grad: 0.1463 (0.1430) loss: 0.8813 (0.8802) time: 0.1720 data: 0.0766 max mem: 8233 +Train: [74] [5000/6250] eta: 0:03:38 lr: 0.000020 grad: 0.1409 (0.1430) loss: 0.8788 (0.8802) time: 0.1631 data: 0.0717 max mem: 8233 +Train: [74] [5100/6250] eta: 0:03:21 lr: 0.000020 grad: 0.1428 (0.1430) loss: 0.8813 (0.8802) time: 0.3068 data: 0.2383 max mem: 8233 +Train: [74] [5200/6250] eta: 0:03:03 lr: 0.000020 grad: 0.1370 (0.1432) loss: 0.8771 (0.8802) time: 0.1849 data: 0.1124 max mem: 8233 +Train: [74] [5300/6250] eta: 0:02:46 lr: 0.000020 grad: 0.1420 (0.1432) loss: 0.8831 (0.8802) time: 0.1741 data: 0.1019 max mem: 8233 +Train: [74] [5400/6250] eta: 0:02:28 lr: 0.000020 grad: 0.1483 (0.1432) loss: 0.8804 (0.8802) time: 0.1824 data: 0.0990 max mem: 8233 +Train: [74] [5500/6250] eta: 0:02:11 lr: 0.000020 grad: 0.1338 (0.1433) loss: 0.8852 (0.8802) time: 0.1685 data: 0.0911 max mem: 8233 +Train: [74] [5600/6250] eta: 0:01:53 lr: 0.000020 grad: 0.1437 (0.1434) loss: 0.8796 (0.8803) time: 0.1704 data: 0.0862 max mem: 8233 +Train: [74] [5700/6250] eta: 0:01:36 lr: 0.000020 grad: 0.1322 (0.1434) loss: 0.8843 (0.8803) time: 0.1650 data: 0.0791 max mem: 8233 +Train: [74] [5800/6250] eta: 0:01:18 lr: 0.000020 grad: 0.1342 (0.1434) loss: 0.8794 (0.8804) time: 0.1099 data: 0.0213 max mem: 8233 +Train: [74] [5900/6250] eta: 0:01:00 lr: 0.000020 grad: 0.1354 (0.1434) loss: 0.8861 (0.8804) time: 0.1565 data: 0.0747 max mem: 8233 +Train: [74] [6000/6250] eta: 0:00:43 lr: 0.000020 grad: 0.1372 (0.1435) loss: 0.8824 (0.8804) time: 0.1671 data: 0.0803 max mem: 8233 +Train: [74] [6100/6250] eta: 0:00:26 lr: 0.000020 grad: 0.1436 (0.1436) loss: 0.8854 (0.8804) time: 0.1831 data: 0.0952 max mem: 8233 +Train: [74] [6200/6250] eta: 0:00:08 lr: 0.000020 grad: 0.1486 (0.1436) loss: 0.8838 (0.8804) time: 0.2911 data: 0.1908 max mem: 8233 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1403 (0.1436) loss: 0.8864 (0.8804) time: 0.2558 data: 0.1734 max mem: 8233 +Train: [74] Total time: 0:18:16 (0.1755 s / it) +Averaged stats: lr: 0.000020 grad: 0.1403 (0.1436) loss: 0.8864 (0.8804) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:06:23 loss: 0.8934 (0.8934) time: 6.1899 data: 6.1625 max mem: 8233 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8837 (0.8863) time: 0.1443 data: 0.1236 max mem: 8233 +Eval (hcp-train-subset): [74] Total time: 0:00:15 (0.2517 s / it) +Averaged stats (hcp-train-subset): loss: 0.8837 (0.8863) +Making plots (hcp-train-subset): example=30 +Eval (hcp-val): [74] [ 0/62] eta: 0:04:35 loss: 0.8812 (0.8812) time: 4.4394 data: 4.3408 max mem: 8233 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8839 (0.8849) time: 0.1120 data: 0.0904 max mem: 8233 +Eval (hcp-val): [74] Total time: 0:00:14 (0.2414 s / it) +Averaged stats (hcp-val): loss: 0.8839 (0.8849) +Making plots (hcp-val): example=48 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 8:59:42 lr: 0.000020 grad: 0.0794 (0.0794) loss: 0.9105 (0.9105) time: 5.1812 data: 5.0109 max mem: 8233 +Train: [75] [ 100/6250] eta: 0:23:31 lr: 0.000020 grad: 0.1181 (0.1329) loss: 0.8871 (0.8925) time: 0.1659 data: 0.0471 max mem: 8233 +Train: [75] [ 200/6250] eta: 0:21:23 lr: 0.000020 grad: 0.1314 (0.1429) loss: 0.8770 (0.8872) time: 0.2199 data: 0.1099 max mem: 8233 +Train: [75] [ 300/6250] eta: 0:20:21 lr: 0.000020 grad: 0.1362 (0.1442) loss: 0.8815 (0.8847) time: 0.1899 data: 0.0757 max mem: 8233 +Train: [75] [ 400/6250] eta: 0:19:13 lr: 0.000020 grad: 0.1331 (0.1431) loss: 0.8866 (0.8839) time: 0.1723 data: 0.0789 max mem: 8233 +Train: [75] [ 500/6250] eta: 0:18:48 lr: 0.000020 grad: 0.1361 (0.1421) loss: 0.8720 (0.8830) time: 0.2042 data: 0.1036 max mem: 8233 +Train: [75] [ 600/6250] eta: 0:18:07 lr: 0.000020 grad: 0.1282 (0.1416) loss: 0.8828 (0.8823) time: 0.1640 data: 0.0700 max mem: 8233 +Train: [75] [ 700/6250] eta: 0:18:24 lr: 0.000020 grad: 0.1311 (0.1411) loss: 0.8735 (0.8818) time: 0.4206 data: 0.2966 max mem: 8233 +Train: [75] [ 800/6250] eta: 0:17:45 lr: 0.000020 grad: 0.1346 (0.1411) loss: 0.8855 (0.8815) time: 0.1738 data: 0.0772 max mem: 8233 +Train: [75] [ 900/6250] eta: 0:17:13 lr: 0.000020 grad: 0.1340 (0.1415) loss: 0.8745 (0.8811) time: 0.1426 data: 0.0417 max mem: 8233 +Train: [75] [1000/6250] eta: 0:16:50 lr: 0.000020 grad: 0.1417 (0.1418) loss: 0.8794 (0.8808) time: 0.1144 data: 0.0004 max mem: 8233 +Train: [75] [1100/6250] eta: 0:16:21 lr: 0.000020 grad: 0.1377 (0.1425) loss: 0.8791 (0.8803) time: 0.2440 data: 0.1702 max mem: 8233 +Train: [75] [1200/6250] eta: 0:15:40 lr: 0.000020 grad: 0.1456 (0.1428) loss: 0.8782 (0.8800) time: 0.1321 data: 0.0410 max mem: 8233 +Train: [75] [1300/6250] eta: 0:15:12 lr: 0.000020 grad: 0.1402 (0.1430) loss: 0.8721 (0.8796) time: 0.1701 data: 0.0972 max mem: 8233 +Train: [75] [1400/6250] eta: 0:14:45 lr: 0.000020 grad: 0.1363 (0.1431) loss: 0.8822 (0.8794) time: 0.1749 data: 0.0889 max mem: 8233 +Train: [75] [1500/6250] eta: 0:14:19 lr: 0.000020 grad: 0.1417 (0.1430) loss: 0.8813 (0.8793) time: 0.1276 data: 0.0389 max mem: 8233 +Train: [75] [1600/6250] eta: 0:13:54 lr: 0.000020 grad: 0.1368 (0.1431) loss: 0.8779 (0.8791) time: 0.1530 data: 0.0776 max mem: 8233 +Train: [75] [1700/6250] eta: 0:13:30 lr: 0.000020 grad: 0.1375 (0.1433) loss: 0.8821 (0.8791) time: 0.1082 data: 0.0242 max mem: 8233 +Train: [75] [1800/6250] eta: 0:13:11 lr: 0.000020 grad: 0.1339 (0.1431) loss: 0.8771 (0.8790) time: 0.2020 data: 0.1324 max mem: 8233 +Train: [75] [1900/6250] eta: 0:12:51 lr: 0.000020 grad: 0.1329 (0.1430) loss: 0.8743 (0.8789) time: 0.1656 data: 0.0921 max mem: 8233 +Train: [75] [2000/6250] eta: 0:12:31 lr: 0.000020 grad: 0.1383 (0.1429) loss: 0.8775 (0.8789) time: 0.1489 data: 0.0746 max mem: 8233 +Train: [75] [2100/6250] eta: 0:12:14 lr: 0.000020 grad: 0.1275 (0.1428) loss: 0.8812 (0.8789) time: 0.1982 data: 0.1059 max mem: 8233 +Train: [75] [2200/6250] eta: 0:11:57 lr: 0.000020 grad: 0.1373 (0.1429) loss: 0.8810 (0.8789) time: 0.1744 data: 0.0837 max mem: 8233 +Train: [75] [2300/6250] eta: 0:11:39 lr: 0.000020 grad: 0.1336 (0.1428) loss: 0.8795 (0.8790) time: 0.1647 data: 0.0909 max mem: 8233 +Train: [75] [2400/6250] eta: 0:11:22 lr: 0.000020 grad: 0.1371 (0.1427) loss: 0.8799 (0.8791) time: 0.2082 data: 0.1332 max mem: 8233 +Train: [75] [2500/6250] eta: 0:11:05 lr: 0.000020 grad: 0.1444 (0.1426) loss: 0.8842 (0.8792) time: 0.1705 data: 0.0935 max mem: 8233 +Train: [75] [2600/6250] eta: 0:10:46 lr: 0.000020 grad: 0.1383 (0.1426) loss: 0.8827 (0.8792) time: 0.1596 data: 0.0701 max mem: 8233 +Train: [75] [2700/6250] eta: 0:10:24 lr: 0.000020 grad: 0.1348 (0.1425) loss: 0.8856 (0.8794) time: 0.1355 data: 0.0653 max mem: 8233 +Train: [75] [2800/6250] eta: 0:10:07 lr: 0.000019 grad: 0.1373 (0.1424) loss: 0.8773 (0.8796) time: 0.1762 data: 0.0955 max mem: 8233 +Train: [75] [2900/6250] eta: 0:09:47 lr: 0.000019 grad: 0.1373 (0.1425) loss: 0.8841 (0.8796) time: 0.1234 data: 0.0360 max mem: 8233 +Train: [75] [3000/6250] eta: 0:09:28 lr: 0.000019 grad: 0.1326 (0.1424) loss: 0.8794 (0.8796) time: 0.1785 data: 0.0938 max mem: 8233 +Train: [75] [3100/6250] eta: 0:09:08 lr: 0.000019 grad: 0.1358 (0.1425) loss: 0.8816 (0.8796) time: 0.1452 data: 0.0549 max mem: 8233 +Train: [75] [3200/6250] eta: 0:08:49 lr: 0.000019 grad: 0.1449 (0.1427) loss: 0.8819 (0.8796) time: 0.1420 data: 0.0574 max mem: 8233 +Train: [75] [3300/6250] eta: 0:08:30 lr: 0.000019 grad: 0.1387 (0.1426) loss: 0.8824 (0.8796) time: 0.1343 data: 0.0520 max mem: 8233 +Train: [75] [3400/6250] eta: 0:08:12 lr: 0.000019 grad: 0.1328 (0.1426) loss: 0.8771 (0.8796) time: 0.1568 data: 0.0835 max mem: 8233 +Train: [75] [3500/6250] eta: 0:07:56 lr: 0.000019 grad: 0.1371 (0.1426) loss: 0.8754 (0.8796) time: 0.1502 data: 0.0364 max mem: 8233 +Train: [75] [3600/6250] eta: 0:07:43 lr: 0.000019 grad: 0.1414 (0.1428) loss: 0.8759 (0.8795) time: 0.5138 data: 0.3710 max mem: 8233 +Train: [75] [3700/6250] eta: 0:07:26 lr: 0.000019 grad: 0.1386 (0.1428) loss: 0.8802 (0.8795) time: 0.2008 data: 0.1131 max mem: 8233 +Train: [75] [3800/6250] eta: 0:07:10 lr: 0.000019 grad: 0.1453 (0.1429) loss: 0.8746 (0.8794) time: 0.1527 data: 0.0696 max mem: 8233 +Train: [75] [3900/6250] eta: 0:06:51 lr: 0.000019 grad: 0.1279 (0.1429) loss: 0.8766 (0.8793) time: 0.1488 data: 0.0652 max mem: 8233 +Train: [75] [4000/6250] eta: 0:06:34 lr: 0.000019 grad: 0.1358 (0.1428) loss: 0.8768 (0.8793) time: 0.2004 data: 0.1031 max mem: 8233 +Train: [75] [4100/6250] eta: 0:06:16 lr: 0.000019 grad: 0.1390 (0.1429) loss: 0.8789 (0.8792) time: 0.1899 data: 0.1126 max mem: 8233 +Train: [75] [4200/6250] eta: 0:06:00 lr: 0.000019 grad: 0.1411 (0.1429) loss: 0.8803 (0.8792) time: 0.2334 data: 0.1448 max mem: 8233 +Train: [75] [4300/6250] eta: 0:05:42 lr: 0.000019 grad: 0.1361 (0.1429) loss: 0.8780 (0.8791) time: 0.1187 data: 0.0236 max mem: 8233 +Train: [75] [4400/6250] eta: 0:05:26 lr: 0.000019 grad: 0.1440 (0.1431) loss: 0.8762 (0.8791) time: 0.1031 data: 0.0003 max mem: 8233 +Train: [75] [4500/6250] eta: 0:05:08 lr: 0.000019 grad: 0.1422 (0.1431) loss: 0.8732 (0.8790) time: 0.1433 data: 0.0574 max mem: 8233 +Train: [75] [4600/6250] eta: 0:04:50 lr: 0.000019 grad: 0.1353 (0.1431) loss: 0.8800 (0.8789) time: 0.1800 data: 0.0954 max mem: 8233 +Train: [75] [4700/6250] eta: 0:04:32 lr: 0.000019 grad: 0.1373 (0.1432) loss: 0.8799 (0.8789) time: 0.1718 data: 0.0755 max mem: 8233 +Train: [75] [4800/6250] eta: 0:04:14 lr: 0.000019 grad: 0.1404 (0.1433) loss: 0.8816 (0.8788) time: 0.1465 data: 0.0682 max mem: 8233 +Train: [75] [4900/6250] eta: 0:03:57 lr: 0.000019 grad: 0.1407 (0.1434) loss: 0.8721 (0.8788) time: 0.2400 data: 0.1418 max mem: 8233 +Train: [75] [5000/6250] eta: 0:03:39 lr: 0.000019 grad: 0.1400 (0.1434) loss: 0.8733 (0.8787) time: 0.2104 data: 0.1278 max mem: 8233 +Train: [75] [5100/6250] eta: 0:03:22 lr: 0.000019 grad: 0.1418 (0.1434) loss: 0.8759 (0.8787) time: 0.1455 data: 0.0564 max mem: 8233 +Train: [75] [5200/6250] eta: 0:03:05 lr: 0.000019 grad: 0.1443 (0.1434) loss: 0.8752 (0.8787) time: 0.1050 data: 0.0002 max mem: 8233 +Train: [75] [5300/6250] eta: 0:02:47 lr: 0.000019 grad: 0.1473 (0.1435) loss: 0.8753 (0.8786) time: 0.1595 data: 0.0684 max mem: 8233 +Train: [75] [5400/6250] eta: 0:02:29 lr: 0.000019 grad: 0.1387 (0.1436) loss: 0.8793 (0.8786) time: 0.1554 data: 0.0825 max mem: 8233 +Train: [75] [5500/6250] eta: 0:02:11 lr: 0.000019 grad: 0.1371 (0.1437) loss: 0.8804 (0.8786) time: 0.1830 data: 0.0950 max mem: 8233 +Train: [75] [5600/6250] eta: 0:01:54 lr: 0.000019 grad: 0.1490 (0.1439) loss: 0.8752 (0.8785) time: 0.1806 data: 0.1096 max mem: 8233 +Train: [75] [5700/6250] eta: 0:01:36 lr: 0.000019 grad: 0.1418 (0.1439) loss: 0.8808 (0.8786) time: 0.1789 data: 0.0898 max mem: 8233 +Train: [75] [5800/6250] eta: 0:01:18 lr: 0.000019 grad: 0.1401 (0.1440) loss: 0.8763 (0.8786) time: 0.1608 data: 0.0689 max mem: 8233 +Train: [75] [5900/6250] eta: 0:01:01 lr: 0.000019 grad: 0.1378 (0.1440) loss: 0.8819 (0.8786) time: 0.1652 data: 0.0834 max mem: 8233 +Train: [75] [6000/6250] eta: 0:00:43 lr: 0.000019 grad: 0.1481 (0.1440) loss: 0.8794 (0.8786) time: 0.1426 data: 0.0613 max mem: 8233 +Train: [75] [6100/6250] eta: 0:00:26 lr: 0.000019 grad: 0.1387 (0.1441) loss: 0.8796 (0.8786) time: 0.1706 data: 0.0844 max mem: 8233 +Train: [75] [6200/6250] eta: 0:00:08 lr: 0.000019 grad: 0.1455 (0.1442) loss: 0.8790 (0.8786) time: 0.1649 data: 0.0708 max mem: 8233 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1476 (0.1442) loss: 0.8791 (0.8786) time: 0.2025 data: 0.1206 max mem: 8233 +Train: [75] Total time: 0:18:19 (0.1758 s / it) +Averaged stats: lr: 0.000019 grad: 0.1476 (0.1442) loss: 0.8791 (0.8786) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:04:08 loss: 0.8948 (0.8948) time: 4.0034 data: 3.9161 max mem: 8233 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8857 (0.8855) time: 0.1587 data: 0.1369 max mem: 8233 +Eval (hcp-train-subset): [75] Total time: 0:00:15 (0.2558 s / it) +Averaged stats (hcp-train-subset): loss: 0.8857 (0.8855) +Eval (hcp-val): [75] [ 0/62] eta: 0:04:23 loss: 0.8799 (0.8799) time: 4.2481 data: 4.1612 max mem: 8233 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8834 (0.8841) time: 0.1349 data: 0.1140 max mem: 8233 +Eval (hcp-val): [75] Total time: 0:00:14 (0.2398 s / it) +Averaged stats (hcp-val): loss: 0.8834 (0.8841) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 15:24:06 lr: 0.000019 grad: 0.1287 (0.1287) loss: 0.9108 (0.9108) time: 8.8715 data: 8.7708 max mem: 8233 +Train: [76] [ 100/6250] eta: 0:24:09 lr: 0.000019 grad: 0.1494 (0.1597) loss: 0.8818 (0.8866) time: 0.1427 data: 0.0499 max mem: 8233 +Train: [76] [ 200/6250] eta: 0:20:53 lr: 0.000019 grad: 0.1342 (0.1563) loss: 0.8839 (0.8831) time: 0.1768 data: 0.0590 max mem: 8233 +Train: [76] [ 300/6250] eta: 0:19:15 lr: 0.000019 grad: 0.1355 (0.1541) loss: 0.8809 (0.8819) time: 0.1603 data: 0.0844 max mem: 8233 +Train: [76] [ 400/6250] eta: 0:18:12 lr: 0.000019 grad: 0.1411 (0.1525) loss: 0.8757 (0.8805) time: 0.1542 data: 0.0588 max mem: 8233 +Train: [76] [ 500/6250] eta: 0:17:53 lr: 0.000019 grad: 0.1387 (0.1512) loss: 0.8829 (0.8800) time: 0.2325 data: 0.1313 max mem: 8233 +Train: [76] [ 600/6250] eta: 0:17:29 lr: 0.000019 grad: 0.1464 (0.1515) loss: 0.8757 (0.8799) time: 0.2186 data: 0.1230 max mem: 8233 +Train: [76] [ 700/6250] eta: 0:17:10 lr: 0.000019 grad: 0.1500 (0.1519) loss: 0.8779 (0.8792) time: 0.1721 data: 0.0832 max mem: 8233 +Train: [76] [ 800/6250] eta: 0:16:47 lr: 0.000018 grad: 0.1386 (0.1517) loss: 0.8789 (0.8791) time: 0.1870 data: 0.0975 max mem: 8233 +Train: [76] [ 900/6250] eta: 0:16:28 lr: 0.000018 grad: 0.1413 (0.1516) loss: 0.8778 (0.8788) time: 0.1106 data: 0.0002 max mem: 8233 +Train: [76] [1000/6250] eta: 0:16:01 lr: 0.000018 grad: 0.1430 (0.1516) loss: 0.8798 (0.8786) time: 0.1525 data: 0.0800 max mem: 8233 +Train: [76] [1100/6250] eta: 0:15:36 lr: 0.000018 grad: 0.1424 (0.1516) loss: 0.8790 (0.8783) time: 0.1884 data: 0.1047 max mem: 8233 +Train: [76] [1200/6250] eta: 0:15:10 lr: 0.000018 grad: 0.1363 (0.1511) loss: 0.8817 (0.8782) time: 0.1522 data: 0.0664 max mem: 8233 +Train: [76] [1300/6250] eta: 0:14:47 lr: 0.000018 grad: 0.1462 (0.1510) loss: 0.8752 (0.8779) time: 0.1731 data: 0.0780 max mem: 8233 +Train: [76] [1400/6250] eta: 0:14:29 lr: 0.000018 grad: 0.1333 (0.1508) loss: 0.8817 (0.8779) time: 0.1898 data: 0.1106 max mem: 8233 +Train: [76] [1500/6250] eta: 0:14:30 lr: 0.000018 grad: 0.1378 (0.1509) loss: 0.8800 (0.8780) time: 0.2917 data: 0.1924 max mem: 8233 +Train: [76] [1600/6250] eta: 0:14:03 lr: 0.000018 grad: 0.1412 (0.1509) loss: 0.8768 (0.8779) time: 0.1736 data: 0.0865 max mem: 8233 +Train: [76] [1700/6250] eta: 0:13:55 lr: 0.000018 grad: 0.1514 (0.1508) loss: 0.8789 (0.8779) time: 0.2141 data: 0.1133 max mem: 8233 +Train: [76] [1800/6250] eta: 0:13:25 lr: 0.000018 grad: 0.1491 (0.1507) loss: 0.8797 (0.8778) time: 0.1544 data: 0.0732 max mem: 8233 +Train: [76] [1900/6250] eta: 0:13:01 lr: 0.000018 grad: 0.1360 (0.1506) loss: 0.8721 (0.8777) time: 0.1446 data: 0.0522 max mem: 8233 +Train: [76] [2000/6250] eta: 0:12:45 lr: 0.000018 grad: 0.1532 (0.1506) loss: 0.8802 (0.8777) time: 0.1701 data: 0.0878 max mem: 8233 +Train: [76] [2100/6250] eta: 0:12:24 lr: 0.000018 grad: 0.1429 (0.1507) loss: 0.8726 (0.8776) time: 0.1743 data: 0.0874 max mem: 8233 +Train: [76] [2200/6250] eta: 0:12:03 lr: 0.000018 grad: 0.1455 (0.1510) loss: 0.8722 (0.8774) time: 0.1368 data: 0.0554 max mem: 8233 +Train: [76] [2300/6250] eta: 0:11:44 lr: 0.000018 grad: 0.1489 (0.1509) loss: 0.8805 (0.8773) time: 0.1522 data: 0.0657 max mem: 8233 +Train: [76] [2400/6250] eta: 0:11:26 lr: 0.000018 grad: 0.1589 (0.1513) loss: 0.8768 (0.8771) time: 0.1869 data: 0.1156 max mem: 8233 +Train: [76] [2500/6250] eta: 0:11:07 lr: 0.000018 grad: 0.1537 (0.1515) loss: 0.8808 (0.8770) time: 0.1687 data: 0.0760 max mem: 8233 +Train: [76] [2600/6250] eta: 0:10:50 lr: 0.000018 grad: 0.1503 (0.1519) loss: 0.8681 (0.8769) time: 0.1801 data: 0.0992 max mem: 8233 +Train: [76] [2700/6250] eta: 0:10:30 lr: 0.000018 grad: 0.1418 (0.1520) loss: 0.8754 (0.8768) time: 0.1652 data: 0.0957 max mem: 8233 +Train: [76] [2800/6250] eta: 0:10:09 lr: 0.000018 grad: 0.1533 (0.1523) loss: 0.8745 (0.8767) time: 0.1638 data: 0.0850 max mem: 8233 +Train: [76] [2900/6250] eta: 0:09:50 lr: 0.000018 grad: 0.1607 (0.1524) loss: 0.8717 (0.8766) time: 0.1655 data: 0.0827 max mem: 8233 +Train: [76] [3000/6250] eta: 0:09:30 lr: 0.000018 grad: 0.1427 (0.1526) loss: 0.8739 (0.8765) time: 0.1570 data: 0.0633 max mem: 8233 +Train: [76] [3100/6250] eta: 0:09:10 lr: 0.000018 grad: 0.1452 (0.1527) loss: 0.8806 (0.8765) time: 0.1281 data: 0.0444 max mem: 8233 +Train: [76] [3200/6250] eta: 0:08:51 lr: 0.000018 grad: 0.1419 (0.1528) loss: 0.8705 (0.8764) time: 0.1801 data: 0.0940 max mem: 8233 +Train: [76] [3300/6250] eta: 0:08:31 lr: 0.000018 grad: 0.1447 (0.1529) loss: 0.8715 (0.8763) time: 0.1666 data: 0.0895 max mem: 8233 +Train: [76] [3400/6250] eta: 0:08:13 lr: 0.000018 grad: 0.1372 (0.1529) loss: 0.8738 (0.8763) time: 0.1762 data: 0.0920 max mem: 8233 +Train: [76] [3500/6250] eta: 0:07:55 lr: 0.000018 grad: 0.1389 (0.1529) loss: 0.8783 (0.8763) time: 0.1548 data: 0.0750 max mem: 8233 +Train: [76] [3600/6250] eta: 0:07:37 lr: 0.000018 grad: 0.1471 (0.1529) loss: 0.8788 (0.8763) time: 0.1498 data: 0.0687 max mem: 8233 +Train: [76] [3700/6250] eta: 0:07:21 lr: 0.000018 grad: 0.1379 (0.1528) loss: 0.8812 (0.8763) time: 0.2530 data: 0.1795 max mem: 8233 +Train: [76] [3800/6250] eta: 0:07:03 lr: 0.000018 grad: 0.1482 (0.1529) loss: 0.8752 (0.8763) time: 0.1588 data: 0.0716 max mem: 8233 +Train: [76] [3900/6250] eta: 0:06:45 lr: 0.000018 grad: 0.1386 (0.1528) loss: 0.8826 (0.8763) time: 0.1497 data: 0.0499 max mem: 8233 +Train: [76] [4000/6250] eta: 0:06:28 lr: 0.000018 grad: 0.1391 (0.1526) loss: 0.8790 (0.8764) time: 0.1924 data: 0.1082 max mem: 8233 +Train: [76] [4100/6250] eta: 0:06:11 lr: 0.000018 grad: 0.1467 (0.1525) loss: 0.8734 (0.8763) time: 0.2223 data: 0.1385 max mem: 8233 +Train: [76] [4200/6250] eta: 0:05:52 lr: 0.000018 grad: 0.1463 (0.1524) loss: 0.8772 (0.8764) time: 0.1556 data: 0.0584 max mem: 8233 +Train: [76] [4300/6250] eta: 0:05:35 lr: 0.000018 grad: 0.1536 (0.1524) loss: 0.8782 (0.8764) time: 0.1738 data: 0.0918 max mem: 8233 +Train: [76] [4400/6250] eta: 0:05:17 lr: 0.000018 grad: 0.1438 (0.1525) loss: 0.8772 (0.8765) time: 0.1547 data: 0.0801 max mem: 8233 +Train: [76] [4500/6250] eta: 0:05:01 lr: 0.000018 grad: 0.1446 (0.1524) loss: 0.8787 (0.8765) time: 0.1492 data: 0.0267 max mem: 8233 +Train: [76] [4600/6250] eta: 0:04:43 lr: 0.000018 grad: 0.1479 (0.1522) loss: 0.8829 (0.8766) time: 0.1929 data: 0.1143 max mem: 8233 +Train: [76] [4700/6250] eta: 0:04:26 lr: 0.000018 grad: 0.1433 (0.1522) loss: 0.8789 (0.8766) time: 0.1696 data: 0.0799 max mem: 8233 +Train: [76] [4800/6250] eta: 0:04:08 lr: 0.000018 grad: 0.1376 (0.1522) loss: 0.8834 (0.8767) time: 0.1890 data: 0.1073 max mem: 8233 +Train: [76] [4900/6250] eta: 0:03:51 lr: 0.000018 grad: 0.1483 (0.1522) loss: 0.8761 (0.8767) time: 0.2510 data: 0.1800 max mem: 8233 +Train: [76] [5000/6250] eta: 0:03:34 lr: 0.000018 grad: 0.1526 (0.1522) loss: 0.8723 (0.8767) time: 0.2389 data: 0.1529 max mem: 8233 +Train: [76] [5100/6250] eta: 0:03:16 lr: 0.000017 grad: 0.1372 (0.1521) loss: 0.8768 (0.8767) time: 0.1647 data: 0.0875 max mem: 8233 +Train: [76] [5200/6250] eta: 0:02:59 lr: 0.000017 grad: 0.1378 (0.1521) loss: 0.8740 (0.8767) time: 0.1363 data: 0.0645 max mem: 8233 +Train: [76] [5300/6250] eta: 0:02:42 lr: 0.000017 grad: 0.1420 (0.1521) loss: 0.8785 (0.8768) time: 0.1640 data: 0.0928 max mem: 8233 +Train: [76] [5400/6250] eta: 0:02:25 lr: 0.000017 grad: 0.1449 (0.1520) loss: 0.8765 (0.8768) time: 0.1595 data: 0.0802 max mem: 8233 +Train: [76] [5500/6250] eta: 0:02:07 lr: 0.000017 grad: 0.1486 (0.1519) loss: 0.8764 (0.8768) time: 0.1542 data: 0.0812 max mem: 8233 +Train: [76] [5600/6250] eta: 0:01:50 lr: 0.000017 grad: 0.1392 (0.1518) loss: 0.8770 (0.8769) time: 0.1451 data: 0.0643 max mem: 8233 +Train: [76] [5700/6250] eta: 0:01:33 lr: 0.000017 grad: 0.1537 (0.1518) loss: 0.8758 (0.8769) time: 0.1856 data: 0.1072 max mem: 8233 +Train: [76] [5800/6250] eta: 0:01:16 lr: 0.000017 grad: 0.1426 (0.1517) loss: 0.8763 (0.8769) time: 0.1890 data: 0.1052 max mem: 8233 +Train: [76] [5900/6250] eta: 0:00:59 lr: 0.000017 grad: 0.1407 (0.1517) loss: 0.8701 (0.8769) time: 0.1681 data: 0.0746 max mem: 8233 +Train: [76] [6000/6250] eta: 0:00:42 lr: 0.000017 grad: 0.1457 (0.1516) loss: 0.8820 (0.8769) time: 0.1774 data: 0.0939 max mem: 8233 +Train: [76] [6100/6250] eta: 0:00:25 lr: 0.000017 grad: 0.1474 (0.1517) loss: 0.8788 (0.8770) time: 0.2122 data: 0.1418 max mem: 8233 +Train: [76] [6200/6250] eta: 0:00:08 lr: 0.000017 grad: 0.1412 (0.1516) loss: 0.8794 (0.8770) time: 0.2087 data: 0.1263 max mem: 8233 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1521 (0.1516) loss: 0.8766 (0.8770) time: 0.1252 data: 0.0003 max mem: 8233 +Train: [76] Total time: 0:17:53 (0.1717 s / it) +Averaged stats: lr: 0.000017 grad: 0.1521 (0.1516) loss: 0.8766 (0.8770) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:06:49 loss: 0.8941 (0.8941) time: 6.5989 data: 6.5718 max mem: 8233 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8831 (0.8854) time: 0.1241 data: 0.1033 max mem: 8233 +Eval (hcp-train-subset): [76] Total time: 0:00:15 (0.2535 s / it) +Averaged stats (hcp-train-subset): loss: 0.8831 (0.8854) +Eval (hcp-val): [76] [ 0/62] eta: 0:06:30 loss: 0.8820 (0.8820) time: 6.2920 data: 6.2643 max mem: 8233 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8837 (0.8842) time: 0.1288 data: 0.1082 max mem: 8233 +Eval (hcp-val): [76] Total time: 0:00:14 (0.2400 s / it) +Averaged stats (hcp-val): loss: 0.8837 (0.8842) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 11:58:21 lr: 0.000017 grad: 0.0967 (0.0967) loss: 0.9102 (0.9102) time: 6.8963 data: 6.7513 max mem: 8233 +Train: [77] [ 100/6250] eta: 0:25:25 lr: 0.000017 grad: 0.1601 (0.1546) loss: 0.8852 (0.8845) time: 0.2682 data: 0.1678 max mem: 8233 +Train: [77] [ 200/6250] eta: 0:20:16 lr: 0.000017 grad: 0.1428 (0.1507) loss: 0.8788 (0.8831) time: 0.1680 data: 0.0679 max mem: 8233 +Train: [77] [ 300/6250] eta: 0:18:35 lr: 0.000017 grad: 0.1416 (0.1508) loss: 0.8799 (0.8821) time: 0.1553 data: 0.0397 max mem: 8233 +Train: [77] [ 400/6250] eta: 0:17:36 lr: 0.000017 grad: 0.1407 (0.1493) loss: 0.8766 (0.8813) time: 0.1599 data: 0.0677 max mem: 8233 +Train: [77] [ 500/6250] eta: 0:17:03 lr: 0.000017 grad: 0.1440 (0.1489) loss: 0.8719 (0.8805) time: 0.1783 data: 0.0830 max mem: 8233 +Train: [77] [ 600/6250] eta: 0:17:00 lr: 0.000017 grad: 0.1408 (0.1482) loss: 0.8796 (0.8801) time: 0.1811 data: 0.0746 max mem: 8233 +Train: [77] [ 700/6250] eta: 0:16:30 lr: 0.000017 grad: 0.1376 (0.1482) loss: 0.8826 (0.8800) time: 0.1742 data: 0.0832 max mem: 8233 +Train: [77] [ 800/6250] eta: 0:16:12 lr: 0.000017 grad: 0.1396 (0.1484) loss: 0.8779 (0.8798) time: 0.1784 data: 0.0979 max mem: 8233 +Train: [77] [ 900/6250] eta: 0:15:56 lr: 0.000017 grad: 0.1373 (0.1488) loss: 0.8806 (0.8797) time: 0.1663 data: 0.0824 max mem: 8233 +Train: [77] [1000/6250] eta: 0:15:35 lr: 0.000017 grad: 0.1393 (0.1485) loss: 0.8806 (0.8796) time: 0.1742 data: 0.0842 max mem: 8233 +Train: [77] [1100/6250] eta: 0:15:37 lr: 0.000017 grad: 0.1367 (0.1485) loss: 0.8883 (0.8799) time: 0.3352 data: 0.2432 max mem: 8233 +Train: [77] [1200/6250] eta: 0:15:08 lr: 0.000017 grad: 0.1488 (0.1481) loss: 0.8776 (0.8798) time: 0.2080 data: 0.1244 max mem: 8233 +Train: [77] [1300/6250] eta: 0:14:48 lr: 0.000017 grad: 0.1452 (0.1481) loss: 0.8780 (0.8799) time: 0.2541 data: 0.1759 max mem: 8233 +Train: [77] [1400/6250] eta: 0:14:18 lr: 0.000017 grad: 0.1448 (0.1478) loss: 0.8817 (0.8801) time: 0.1374 data: 0.0441 max mem: 8233 +Train: [77] [1500/6250] eta: 0:14:02 lr: 0.000017 grad: 0.1400 (0.1476) loss: 0.8825 (0.8802) time: 0.1230 data: 0.0003 max mem: 8233 +Train: [77] [1600/6250] eta: 0:13:41 lr: 0.000017 grad: 0.1410 (0.1477) loss: 0.8753 (0.8801) time: 0.1600 data: 0.0735 max mem: 8233 +Train: [77] [1700/6250] eta: 0:13:24 lr: 0.000017 grad: 0.1402 (0.1478) loss: 0.8762 (0.8801) time: 0.1755 data: 0.0755 max mem: 8233 +Train: [77] [1800/6250] eta: 0:13:09 lr: 0.000017 grad: 0.1540 (0.1476) loss: 0.8786 (0.8801) time: 0.2617 data: 0.1801 max mem: 8233 +Train: [77] [1900/6250] eta: 0:12:47 lr: 0.000017 grad: 0.1593 (0.1477) loss: 0.8848 (0.8801) time: 0.1269 data: 0.0394 max mem: 8233 +Train: [77] [2000/6250] eta: 0:12:25 lr: 0.000017 grad: 0.1418 (0.1480) loss: 0.8783 (0.8801) time: 0.1665 data: 0.0821 max mem: 8233 +Train: [77] [2100/6250] eta: 0:12:06 lr: 0.000017 grad: 0.1369 (0.1479) loss: 0.8813 (0.8801) time: 0.1807 data: 0.1051 max mem: 8233 +Train: [77] [2200/6250] eta: 0:11:48 lr: 0.000017 grad: 0.1421 (0.1478) loss: 0.8775 (0.8801) time: 0.1605 data: 0.0767 max mem: 8233 +Train: [77] [2300/6250] eta: 0:11:29 lr: 0.000017 grad: 0.1413 (0.1478) loss: 0.8797 (0.8800) time: 0.1414 data: 0.0757 max mem: 8233 +Train: [77] [2400/6250] eta: 0:11:11 lr: 0.000017 grad: 0.1481 (0.1479) loss: 0.8720 (0.8800) time: 0.1717 data: 0.0906 max mem: 8233 +Train: [77] [2500/6250] eta: 0:10:53 lr: 0.000017 grad: 0.1405 (0.1478) loss: 0.8742 (0.8800) time: 0.1485 data: 0.0537 max mem: 8233 +Train: [77] [2600/6250] eta: 0:10:38 lr: 0.000017 grad: 0.1561 (0.1479) loss: 0.8756 (0.8799) time: 0.1789 data: 0.0966 max mem: 8233 +Train: [77] [2700/6250] eta: 0:10:20 lr: 0.000017 grad: 0.1439 (0.1478) loss: 0.8798 (0.8798) time: 0.1487 data: 0.0640 max mem: 8233 +Train: [77] [2800/6250] eta: 0:10:01 lr: 0.000017 grad: 0.1407 (0.1479) loss: 0.8734 (0.8797) time: 0.1690 data: 0.0844 max mem: 8233 +Train: [77] [2900/6250] eta: 0:09:42 lr: 0.000017 grad: 0.1424 (0.1479) loss: 0.8766 (0.8797) time: 0.1569 data: 0.0680 max mem: 8233 +Train: [77] [3000/6250] eta: 0:09:23 lr: 0.000017 grad: 0.1456 (0.1480) loss: 0.8767 (0.8796) time: 0.1300 data: 0.0341 max mem: 8233 +Train: [77] [3100/6250] eta: 0:09:03 lr: 0.000017 grad: 0.1386 (0.1479) loss: 0.8756 (0.8795) time: 0.1525 data: 0.0473 max mem: 8233 +Train: [77] [3200/6250] eta: 0:08:43 lr: 0.000017 grad: 0.1421 (0.1479) loss: 0.8789 (0.8794) time: 0.1567 data: 0.0761 max mem: 8233 +Train: [77] [3300/6250] eta: 0:08:25 lr: 0.000016 grad: 0.1461 (0.1480) loss: 0.8777 (0.8794) time: 0.1541 data: 0.0760 max mem: 8233 +Train: [77] [3400/6250] eta: 0:08:07 lr: 0.000016 grad: 0.1465 (0.1480) loss: 0.8781 (0.8794) time: 0.1738 data: 0.0991 max mem: 8233 +Train: [77] [3500/6250] eta: 0:07:49 lr: 0.000016 grad: 0.1389 (0.1480) loss: 0.8790 (0.8794) time: 0.1635 data: 0.1027 max mem: 8233 +Train: [77] [3600/6250] eta: 0:07:32 lr: 0.000016 grad: 0.1448 (0.1479) loss: 0.8830 (0.8795) time: 0.1487 data: 0.0682 max mem: 8233 +Train: [77] [3700/6250] eta: 0:07:15 lr: 0.000016 grad: 0.1388 (0.1479) loss: 0.8818 (0.8794) time: 0.1624 data: 0.0897 max mem: 8233 +Train: [77] [3800/6250] eta: 0:06:57 lr: 0.000016 grad: 0.1356 (0.1478) loss: 0.8868 (0.8795) time: 0.1647 data: 0.0749 max mem: 8233 +Train: [77] [3900/6250] eta: 0:06:42 lr: 0.000016 grad: 0.1520 (0.1480) loss: 0.8792 (0.8795) time: 0.2280 data: 0.1390 max mem: 8233 +Train: [77] [4000/6250] eta: 0:06:23 lr: 0.000016 grad: 0.1391 (0.1481) loss: 0.8803 (0.8796) time: 0.1545 data: 0.0717 max mem: 8233 +Train: [77] [4100/6250] eta: 0:06:06 lr: 0.000016 grad: 0.1390 (0.1481) loss: 0.8820 (0.8796) time: 0.1990 data: 0.1236 max mem: 8233 +Train: [77] [4200/6250] eta: 0:05:49 lr: 0.000016 grad: 0.1444 (0.1481) loss: 0.8762 (0.8796) time: 0.1009 data: 0.0025 max mem: 8233 +Train: [77] [4300/6250] eta: 0:05:32 lr: 0.000016 grad: 0.1425 (0.1481) loss: 0.8795 (0.8796) time: 0.1736 data: 0.0937 max mem: 8233 +Train: [77] [4400/6250] eta: 0:05:14 lr: 0.000016 grad: 0.1322 (0.1481) loss: 0.8804 (0.8796) time: 0.1540 data: 0.0650 max mem: 8233 +Train: [77] [4500/6250] eta: 0:04:56 lr: 0.000016 grad: 0.1406 (0.1481) loss: 0.8796 (0.8797) time: 0.1580 data: 0.0772 max mem: 8233 +Train: [77] [4600/6250] eta: 0:04:39 lr: 0.000016 grad: 0.1472 (0.1481) loss: 0.8789 (0.8797) time: 0.1569 data: 0.0835 max mem: 8233 +Train: [77] [4700/6250] eta: 0:04:22 lr: 0.000016 grad: 0.1400 (0.1481) loss: 0.8810 (0.8797) time: 0.1518 data: 0.0649 max mem: 8233 +Train: [77] [4800/6250] eta: 0:04:04 lr: 0.000016 grad: 0.1344 (0.1482) loss: 0.8807 (0.8798) time: 0.1639 data: 0.0866 max mem: 8233 +Train: [77] [4900/6250] eta: 0:03:47 lr: 0.000016 grad: 0.1395 (0.1481) loss: 0.8790 (0.8799) time: 0.1416 data: 0.0480 max mem: 8233 +Train: [77] [5000/6250] eta: 0:03:30 lr: 0.000016 grad: 0.1489 (0.1481) loss: 0.8853 (0.8799) time: 0.1736 data: 0.0962 max mem: 8233 +Train: [77] [5100/6250] eta: 0:03:13 lr: 0.000016 grad: 0.1428 (0.1480) loss: 0.8802 (0.8800) time: 0.1588 data: 0.0876 max mem: 8233 +Train: [77] [5200/6250] eta: 0:02:56 lr: 0.000016 grad: 0.1440 (0.1480) loss: 0.8806 (0.8800) time: 0.1673 data: 0.0904 max mem: 8233 +Train: [77] [5300/6250] eta: 0:02:39 lr: 0.000016 grad: 0.1375 (0.1479) loss: 0.8833 (0.8801) time: 0.1578 data: 0.0699 max mem: 8233 +Train: [77] [5400/6250] eta: 0:02:23 lr: 0.000016 grad: 0.1366 (0.1478) loss: 0.8842 (0.8801) time: 0.1837 data: 0.1173 max mem: 8233 +Train: [77] [5500/6250] eta: 0:02:06 lr: 0.000016 grad: 0.1396 (0.1478) loss: 0.8866 (0.8802) time: 0.1559 data: 0.0774 max mem: 8233 +Train: [77] [5600/6250] eta: 0:01:49 lr: 0.000016 grad: 0.1424 (0.1477) loss: 0.8781 (0.8802) time: 0.1504 data: 0.0676 max mem: 8233 +Train: [77] [5700/6250] eta: 0:01:32 lr: 0.000016 grad: 0.1310 (0.1476) loss: 0.8831 (0.8803) time: 0.1690 data: 0.0878 max mem: 8233 +Train: [77] [5800/6250] eta: 0:01:15 lr: 0.000016 grad: 0.1402 (0.1476) loss: 0.8812 (0.8803) time: 0.1491 data: 0.0698 max mem: 8233 +Train: [77] [5900/6250] eta: 0:00:58 lr: 0.000016 grad: 0.1365 (0.1475) loss: 0.8805 (0.8803) time: 0.1537 data: 0.0714 max mem: 8233 +Train: [77] [6000/6250] eta: 0:00:41 lr: 0.000016 grad: 0.1348 (0.1475) loss: 0.8796 (0.8803) time: 0.1491 data: 0.0625 max mem: 8233 +Train: [77] [6100/6250] eta: 0:00:25 lr: 0.000016 grad: 0.1435 (0.1475) loss: 0.8777 (0.8803) time: 0.1594 data: 0.0813 max mem: 8233 +Train: [77] [6200/6250] eta: 0:00:08 lr: 0.000016 grad: 0.1341 (0.1474) loss: 0.8797 (0.8803) time: 0.1596 data: 0.0762 max mem: 8233 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1450 (0.1474) loss: 0.8725 (0.8803) time: 0.1689 data: 0.0877 max mem: 8233 +Train: [77] Total time: 0:17:32 (0.1685 s / it) +Averaged stats: lr: 0.000016 grad: 0.1450 (0.1474) loss: 0.8725 (0.8803) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:06:48 loss: 0.8935 (0.8935) time: 6.5936 data: 6.5483 max mem: 8233 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8829 (0.8855) time: 0.1420 data: 0.1198 max mem: 8233 +Eval (hcp-train-subset): [77] Total time: 0:00:14 (0.2415 s / it) +Averaged stats (hcp-train-subset): loss: 0.8829 (0.8855) +Eval (hcp-val): [77] [ 0/62] eta: 0:06:11 loss: 0.8752 (0.8752) time: 5.9844 data: 5.9573 max mem: 8233 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8838 (0.8838) time: 0.1143 data: 0.0915 max mem: 8233 +Eval (hcp-val): [77] Total time: 0:00:14 (0.2296 s / it) +Averaged stats (hcp-val): loss: 0.8838 (0.8838) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 12:20:53 lr: 0.000016 grad: 0.1947 (0.1947) loss: 0.8836 (0.8836) time: 7.1125 data: 6.9510 max mem: 8233 +Train: [78] [ 100/6250] eta: 0:23:38 lr: 0.000016 grad: 0.1513 (0.1521) loss: 0.8712 (0.8856) time: 0.1545 data: 0.0338 max mem: 8233 +Train: [78] [ 200/6250] eta: 0:20:02 lr: 0.000016 grad: 0.1483 (0.1593) loss: 0.8695 (0.8787) time: 0.1072 data: 0.0003 max mem: 8233 +Train: [78] [ 300/6250] eta: 0:18:27 lr: 0.000016 grad: 0.1499 (0.1592) loss: 0.8809 (0.8774) time: 0.1815 data: 0.0801 max mem: 8233 +Train: [78] [ 400/6250] eta: 0:17:31 lr: 0.000016 grad: 0.1327 (0.1551) loss: 0.8793 (0.8782) time: 0.1631 data: 0.0551 max mem: 8233 +Train: [78] [ 500/6250] eta: 0:17:04 lr: 0.000016 grad: 0.1370 (0.1527) loss: 0.8823 (0.8790) time: 0.1242 data: 0.0387 max mem: 8233 +Train: [78] [ 600/6250] eta: 0:16:40 lr: 0.000016 grad: 0.1435 (0.1510) loss: 0.8848 (0.8796) time: 0.2004 data: 0.1177 max mem: 8233 +Train: [78] [ 700/6250] eta: 0:16:33 lr: 0.000016 grad: 0.1362 (0.1500) loss: 0.8809 (0.8804) time: 0.2123 data: 0.1117 max mem: 8233 +Train: [78] [ 800/6250] eta: 0:16:16 lr: 0.000016 grad: 0.1446 (0.1488) loss: 0.8844 (0.8808) time: 0.2249 data: 0.1357 max mem: 8233 +Train: [78] [ 900/6250] eta: 0:17:00 lr: 0.000016 grad: 0.1381 (0.1480) loss: 0.8825 (0.8810) time: 0.2186 data: 0.1081 max mem: 8233 +Train: [78] [1000/6250] eta: 0:17:05 lr: 0.000016 grad: 0.1412 (0.1480) loss: 0.8791 (0.8811) time: 0.2188 data: 0.0935 max mem: 8233 +Train: [78] [1100/6250] eta: 0:16:39 lr: 0.000016 grad: 0.1460 (0.1479) loss: 0.8767 (0.8811) time: 0.1183 data: 0.0005 max mem: 8233 +Train: [78] [1200/6250] eta: 0:16:04 lr: 0.000016 grad: 0.1338 (0.1476) loss: 0.8827 (0.8813) time: 0.1530 data: 0.0665 max mem: 8233 +Train: [78] [1300/6250] eta: 0:15:46 lr: 0.000016 grad: 0.1444 (0.1470) loss: 0.8784 (0.8813) time: 0.2827 data: 0.1905 max mem: 8233 +Train: [78] [1400/6250] eta: 0:15:15 lr: 0.000016 grad: 0.1438 (0.1468) loss: 0.8850 (0.8814) time: 0.1621 data: 0.0779 max mem: 8233 +Train: [78] [1500/6250] eta: 0:14:48 lr: 0.000015 grad: 0.1408 (0.1468) loss: 0.8816 (0.8814) time: 0.1719 data: 0.0887 max mem: 8233 +Train: [78] [1600/6250] eta: 0:14:26 lr: 0.000015 grad: 0.1380 (0.1470) loss: 0.8827 (0.8813) time: 0.1974 data: 0.1250 max mem: 8233 +Train: [78] [1700/6250] eta: 0:13:57 lr: 0.000015 grad: 0.1339 (0.1468) loss: 0.8839 (0.8813) time: 0.1371 data: 0.0509 max mem: 8233 +Train: [78] [1800/6250] eta: 0:13:32 lr: 0.000015 grad: 0.1456 (0.1467) loss: 0.8761 (0.8813) time: 0.1745 data: 0.1027 max mem: 8233 +Train: [78] [1900/6250] eta: 0:13:08 lr: 0.000015 grad: 0.1384 (0.1466) loss: 0.8810 (0.8813) time: 0.1480 data: 0.0633 max mem: 8233 +Train: [78] [2000/6250] eta: 0:12:46 lr: 0.000015 grad: 0.1353 (0.1466) loss: 0.8808 (0.8812) time: 0.1602 data: 0.0814 max mem: 8233 +Train: [78] [2100/6250] eta: 0:12:26 lr: 0.000015 grad: 0.1390 (0.1466) loss: 0.8811 (0.8812) time: 0.1310 data: 0.0480 max mem: 8233 +Train: [78] [2200/6250] eta: 0:12:06 lr: 0.000015 grad: 0.1394 (0.1464) loss: 0.8793 (0.8812) time: 0.1285 data: 0.0310 max mem: 8233 +Train: [78] [2300/6250] eta: 0:11:47 lr: 0.000015 grad: 0.1361 (0.1464) loss: 0.8814 (0.8813) time: 0.1685 data: 0.0828 max mem: 8233 +Train: [78] [2400/6250] eta: 0:11:26 lr: 0.000015 grad: 0.1403 (0.1464) loss: 0.8842 (0.8813) time: 0.1483 data: 0.0768 max mem: 8233 +Train: [78] [2500/6250] eta: 0:11:05 lr: 0.000015 grad: 0.1325 (0.1465) loss: 0.8834 (0.8813) time: 0.1746 data: 0.0926 max mem: 8233 +Train: [78] [2600/6250] eta: 0:10:47 lr: 0.000015 grad: 0.1466 (0.1467) loss: 0.8786 (0.8812) time: 0.1555 data: 0.0665 max mem: 8233 +Train: [78] [2700/6250] eta: 0:10:30 lr: 0.000015 grad: 0.1479 (0.1466) loss: 0.8761 (0.8813) time: 0.1767 data: 0.0930 max mem: 8233 +Train: [78] [2800/6250] eta: 0:10:10 lr: 0.000015 grad: 0.1402 (0.1467) loss: 0.8763 (0.8813) time: 0.1639 data: 0.0887 max mem: 8233 +Train: [78] [2900/6250] eta: 0:09:53 lr: 0.000015 grad: 0.1409 (0.1467) loss: 0.8787 (0.8813) time: 0.1873 data: 0.1136 max mem: 8233 +Train: [78] [3000/6250] eta: 0:09:37 lr: 0.000015 grad: 0.1450 (0.1469) loss: 0.8820 (0.8811) time: 0.2098 data: 0.1174 max mem: 8233 +Train: [78] [3100/6250] eta: 0:09:18 lr: 0.000015 grad: 0.1387 (0.1469) loss: 0.8778 (0.8811) time: 0.1837 data: 0.1039 max mem: 8233 +Train: [78] [3200/6250] eta: 0:09:00 lr: 0.000015 grad: 0.1366 (0.1469) loss: 0.8819 (0.8810) time: 0.1719 data: 0.0851 max mem: 8233 +Train: [78] [3300/6250] eta: 0:08:41 lr: 0.000015 grad: 0.1478 (0.1471) loss: 0.8787 (0.8809) time: 0.1797 data: 0.0916 max mem: 8233 +Train: [78] [3400/6250] eta: 0:08:26 lr: 0.000015 grad: 0.1486 (0.1472) loss: 0.8760 (0.8808) time: 0.3435 data: 0.2438 max mem: 8233 +Train: [78] [3500/6250] eta: 0:08:07 lr: 0.000015 grad: 0.1494 (0.1474) loss: 0.8804 (0.8808) time: 0.1738 data: 0.1000 max mem: 8233 +Train: [78] [3600/6250] eta: 0:07:51 lr: 0.000015 grad: 0.1451 (0.1475) loss: 0.8809 (0.8808) time: 0.2007 data: 0.1116 max mem: 8233 +Train: [78] [3700/6250] eta: 0:07:32 lr: 0.000015 grad: 0.1562 (0.1476) loss: 0.8748 (0.8807) time: 0.1616 data: 0.0788 max mem: 8233 +Train: [78] [3800/6250] eta: 0:07:15 lr: 0.000015 grad: 0.1410 (0.1477) loss: 0.8753 (0.8807) time: 0.1370 data: 0.0498 max mem: 8233 +Train: [78] [3900/6250] eta: 0:06:56 lr: 0.000015 grad: 0.1433 (0.1480) loss: 0.8790 (0.8806) time: 0.1532 data: 0.0697 max mem: 8233 +Train: [78] [4000/6250] eta: 0:06:38 lr: 0.000015 grad: 0.1377 (0.1482) loss: 0.8782 (0.8805) time: 0.1731 data: 0.0867 max mem: 8233 +Train: [78] [4100/6250] eta: 0:06:19 lr: 0.000015 grad: 0.1400 (0.1482) loss: 0.8782 (0.8805) time: 0.1578 data: 0.0836 max mem: 8233 +Train: [78] [4200/6250] eta: 0:06:01 lr: 0.000015 grad: 0.1504 (0.1482) loss: 0.8750 (0.8803) time: 0.1659 data: 0.0762 max mem: 8233 +Train: [78] [4300/6250] eta: 0:05:44 lr: 0.000015 grad: 0.1451 (0.1482) loss: 0.8736 (0.8802) time: 0.1623 data: 0.0624 max mem: 8233 +Train: [78] [4400/6250] eta: 0:05:25 lr: 0.000015 grad: 0.1486 (0.1484) loss: 0.8733 (0.8801) time: 0.1838 data: 0.0943 max mem: 8233 +Train: [78] [4500/6250] eta: 0:05:07 lr: 0.000015 grad: 0.1441 (0.1484) loss: 0.8766 (0.8800) time: 0.1337 data: 0.0343 max mem: 8233 +Train: [78] [4600/6250] eta: 0:04:49 lr: 0.000015 grad: 0.1461 (0.1487) loss: 0.8730 (0.8798) time: 0.1494 data: 0.0710 max mem: 8233 +Train: [78] [4700/6250] eta: 0:04:31 lr: 0.000015 grad: 0.1573 (0.1490) loss: 0.8711 (0.8797) time: 0.1517 data: 0.0771 max mem: 8233 +Train: [78] [4800/6250] eta: 0:04:13 lr: 0.000015 grad: 0.1481 (0.1490) loss: 0.8740 (0.8796) time: 0.1606 data: 0.0764 max mem: 8233 +Train: [78] [4900/6250] eta: 0:03:55 lr: 0.000015 grad: 0.1486 (0.1491) loss: 0.8788 (0.8795) time: 0.1613 data: 0.0827 max mem: 8233 +Train: [78] [5000/6250] eta: 0:03:38 lr: 0.000015 grad: 0.1475 (0.1491) loss: 0.8714 (0.8794) time: 0.1775 data: 0.1053 max mem: 8233 +Train: [78] [5100/6250] eta: 0:03:20 lr: 0.000015 grad: 0.1465 (0.1494) loss: 0.8768 (0.8793) time: 0.1520 data: 0.0579 max mem: 8233 +Train: [78] [5200/6250] eta: 0:03:03 lr: 0.000015 grad: 0.1499 (0.1494) loss: 0.8724 (0.8792) time: 0.1005 data: 0.0002 max mem: 8233 +Train: [78] [5300/6250] eta: 0:02:45 lr: 0.000015 grad: 0.1414 (0.1495) loss: 0.8781 (0.8791) time: 0.1653 data: 0.0972 max mem: 8233 +Train: [78] [5400/6250] eta: 0:02:28 lr: 0.000015 grad: 0.1478 (0.1495) loss: 0.8765 (0.8791) time: 0.1880 data: 0.1245 max mem: 8233 +Train: [78] [5500/6250] eta: 0:02:10 lr: 0.000015 grad: 0.1426 (0.1495) loss: 0.8743 (0.8791) time: 0.1534 data: 0.0800 max mem: 8233 +Train: [78] [5600/6250] eta: 0:01:53 lr: 0.000015 grad: 0.1450 (0.1495) loss: 0.8822 (0.8791) time: 0.1508 data: 0.0732 max mem: 8233 +Train: [78] [5700/6250] eta: 0:01:35 lr: 0.000015 grad: 0.1482 (0.1495) loss: 0.8728 (0.8791) time: 0.1665 data: 0.0783 max mem: 8233 +Train: [78] [5800/6250] eta: 0:01:18 lr: 0.000015 grad: 0.1525 (0.1496) loss: 0.8731 (0.8790) time: 0.1667 data: 0.0878 max mem: 8233 +Train: [78] [5900/6250] eta: 0:01:00 lr: 0.000015 grad: 0.1525 (0.1497) loss: 0.8719 (0.8789) time: 0.1331 data: 0.0400 max mem: 8233 +Train: [78] [6000/6250] eta: 0:00:43 lr: 0.000015 grad: 0.1466 (0.1497) loss: 0.8752 (0.8789) time: 0.1661 data: 0.0956 max mem: 8233 +Train: [78] [6100/6250] eta: 0:00:26 lr: 0.000015 grad: 0.1479 (0.1498) loss: 0.8741 (0.8788) time: 0.1424 data: 0.0602 max mem: 8233 +Train: [78] [6200/6250] eta: 0:00:08 lr: 0.000014 grad: 0.1552 (0.1500) loss: 0.8781 (0.8788) time: 0.1432 data: 0.0576 max mem: 8233 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1534 (0.1500) loss: 0.8758 (0.8787) time: 0.1552 data: 0.0783 max mem: 8233 +Train: [78] Total time: 0:18:09 (0.1743 s / it) +Averaged stats: lr: 0.000014 grad: 0.1534 (0.1500) loss: 0.8758 (0.8787) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:06:40 loss: 0.8959 (0.8959) time: 6.4675 data: 6.4407 max mem: 8233 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8841 (0.8845) time: 0.1294 data: 0.1085 max mem: 8233 +Eval (hcp-train-subset): [78] Total time: 0:00:14 (0.2394 s / it) +Averaged stats (hcp-train-subset): loss: 0.8841 (0.8845) +Eval (hcp-val): [78] [ 0/62] eta: 0:05:55 loss: 0.8811 (0.8811) time: 5.7312 data: 5.7037 max mem: 8233 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8829 (0.8835) time: 0.1231 data: 0.0993 max mem: 8233 +Eval (hcp-val): [78] Total time: 0:00:14 (0.2384 s / it) +Averaged stats (hcp-val): loss: 0.8829 (0.8835) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 11:50:25 lr: 0.000014 grad: 0.1027 (0.1027) loss: 0.9121 (0.9121) time: 6.8202 data: 6.6376 max mem: 8233 +Train: [79] [ 100/6250] eta: 0:24:17 lr: 0.000014 grad: 0.1428 (0.1722) loss: 0.8763 (0.8783) time: 0.1706 data: 0.0460 max mem: 8233 +Train: [79] [ 200/6250] eta: 0:19:56 lr: 0.000014 grad: 0.1521 (0.1664) loss: 0.8816 (0.8779) time: 0.1546 data: 0.0631 max mem: 8233 +Train: [79] [ 300/6250] eta: 0:18:33 lr: 0.000014 grad: 0.1515 (0.1653) loss: 0.8769 (0.8770) time: 0.1556 data: 0.0504 max mem: 8233 +Train: [79] [ 400/6250] eta: 0:17:58 lr: 0.000014 grad: 0.1513 (0.1633) loss: 0.8788 (0.8771) time: 0.1646 data: 0.0615 max mem: 8233 +Train: [79] [ 500/6250] eta: 0:17:20 lr: 0.000014 grad: 0.1469 (0.1613) loss: 0.8743 (0.8773) time: 0.1651 data: 0.0833 max mem: 8233 +Train: [79] [ 600/6250] eta: 0:17:17 lr: 0.000014 grad: 0.1492 (0.1606) loss: 0.8792 (0.8770) time: 0.1058 data: 0.0040 max mem: 8233 +Train: [79] [ 700/6250] eta: 0:16:54 lr: 0.000014 grad: 0.1542 (0.1604) loss: 0.8785 (0.8770) time: 0.2262 data: 0.1288 max mem: 8233 +Train: [79] [ 800/6250] eta: 0:16:32 lr: 0.000014 grad: 0.1447 (0.1601) loss: 0.8730 (0.8768) time: 0.2511 data: 0.1500 max mem: 8233 +Train: [79] [ 900/6250] eta: 0:16:01 lr: 0.000014 grad: 0.1432 (0.1591) loss: 0.8719 (0.8766) time: 0.1222 data: 0.0180 max mem: 8233 +Train: [79] [1000/6250] eta: 0:15:59 lr: 0.000014 grad: 0.1432 (0.1580) loss: 0.8769 (0.8767) time: 0.1267 data: 0.0004 max mem: 8233 +Train: [79] [1100/6250] eta: 0:15:38 lr: 0.000014 grad: 0.1466 (0.1570) loss: 0.8812 (0.8767) time: 0.1489 data: 0.0373 max mem: 8233 +Train: [79] [1200/6250] eta: 0:15:20 lr: 0.000014 grad: 0.1444 (0.1564) loss: 0.8783 (0.8767) time: 0.1179 data: 0.0173 max mem: 8233 +Train: [79] [1300/6250] eta: 0:14:58 lr: 0.000014 grad: 0.1462 (0.1559) loss: 0.8801 (0.8767) time: 0.1108 data: 0.0002 max mem: 8233 +Train: [79] [1400/6250] eta: 0:14:33 lr: 0.000014 grad: 0.1472 (0.1560) loss: 0.8758 (0.8767) time: 0.1631 data: 0.0691 max mem: 8233 +Train: [79] [1500/6250] eta: 0:14:11 lr: 0.000014 grad: 0.1417 (0.1556) loss: 0.8794 (0.8768) time: 0.1476 data: 0.0584 max mem: 8233 +Train: [79] [1600/6250] eta: 0:13:54 lr: 0.000014 grad: 0.1420 (0.1556) loss: 0.8809 (0.8768) time: 0.2260 data: 0.1245 max mem: 8233 +Train: [79] [1700/6250] eta: 0:13:36 lr: 0.000014 grad: 0.1462 (0.1553) loss: 0.8769 (0.8769) time: 0.2102 data: 0.1246 max mem: 8233 +Train: [79] [1800/6250] eta: 0:13:15 lr: 0.000014 grad: 0.1471 (0.1549) loss: 0.8784 (0.8769) time: 0.1996 data: 0.1170 max mem: 8233 +Train: [79] [1900/6250] eta: 0:12:49 lr: 0.000014 grad: 0.1531 (0.1545) loss: 0.8764 (0.8769) time: 0.1371 data: 0.0538 max mem: 8233 +Train: [79] [2000/6250] eta: 0:12:28 lr: 0.000014 grad: 0.1449 (0.1545) loss: 0.8754 (0.8769) time: 0.1705 data: 0.0854 max mem: 8233 +Train: [79] [2100/6250] eta: 0:12:10 lr: 0.000014 grad: 0.1572 (0.1545) loss: 0.8693 (0.8768) time: 0.2139 data: 0.1308 max mem: 8233 +Train: [79] [2200/6250] eta: 0:11:50 lr: 0.000014 grad: 0.1439 (0.1543) loss: 0.8764 (0.8768) time: 0.1256 data: 0.0477 max mem: 8233 +Train: [79] [2300/6250] eta: 0:11:29 lr: 0.000014 grad: 0.1502 (0.1542) loss: 0.8774 (0.8768) time: 0.1684 data: 0.0868 max mem: 8233 +Train: [79] [2400/6250] eta: 0:11:10 lr: 0.000014 grad: 0.1449 (0.1541) loss: 0.8731 (0.8768) time: 0.1578 data: 0.0706 max mem: 8233 +Train: [79] [2500/6250] eta: 0:10:52 lr: 0.000014 grad: 0.1418 (0.1540) loss: 0.8762 (0.8768) time: 0.1643 data: 0.0877 max mem: 8233 +Train: [79] [2600/6250] eta: 0:10:35 lr: 0.000014 grad: 0.1442 (0.1539) loss: 0.8769 (0.8769) time: 0.1367 data: 0.0516 max mem: 8233 +Train: [79] [2700/6250] eta: 0:10:19 lr: 0.000014 grad: 0.1441 (0.1538) loss: 0.8756 (0.8769) time: 0.2017 data: 0.1216 max mem: 8233 +Train: [79] [2800/6250] eta: 0:10:01 lr: 0.000014 grad: 0.1451 (0.1537) loss: 0.8785 (0.8769) time: 0.1752 data: 0.0765 max mem: 8233 +Train: [79] [2900/6250] eta: 0:09:45 lr: 0.000014 grad: 0.1395 (0.1533) loss: 0.8770 (0.8770) time: 0.1877 data: 0.0957 max mem: 8233 +Train: [79] [3000/6250] eta: 0:09:27 lr: 0.000014 grad: 0.1402 (0.1531) loss: 0.8826 (0.8771) time: 0.1747 data: 0.0878 max mem: 8233 +Train: [79] [3100/6250] eta: 0:09:08 lr: 0.000014 grad: 0.1380 (0.1529) loss: 0.8773 (0.8772) time: 0.1644 data: 0.0652 max mem: 8233 +Train: [79] [3200/6250] eta: 0:08:51 lr: 0.000014 grad: 0.1550 (0.1530) loss: 0.8777 (0.8772) time: 0.1501 data: 0.0764 max mem: 8233 +Train: [79] [3300/6250] eta: 0:08:33 lr: 0.000014 grad: 0.1461 (0.1530) loss: 0.8671 (0.8772) time: 0.1635 data: 0.0743 max mem: 8233 +Train: [79] [3400/6250] eta: 0:08:16 lr: 0.000014 grad: 0.1488 (0.1531) loss: 0.8827 (0.8771) time: 0.2298 data: 0.1400 max mem: 8233 +Train: [79] [3500/6250] eta: 0:08:00 lr: 0.000014 grad: 0.1454 (0.1533) loss: 0.8739 (0.8771) time: 0.2588 data: 0.1746 max mem: 8233 +Train: [79] [3600/6250] eta: 0:07:44 lr: 0.000014 grad: 0.1497 (0.1533) loss: 0.8733 (0.8770) time: 0.1225 data: 0.0005 max mem: 8233 +Train: [79] [3700/6250] eta: 0:07:29 lr: 0.000014 grad: 0.1427 (0.1532) loss: 0.8804 (0.8770) time: 0.3151 data: 0.2205 max mem: 8233 +Train: [79] [3800/6250] eta: 0:07:11 lr: 0.000014 grad: 0.1424 (0.1531) loss: 0.8784 (0.8770) time: 0.1377 data: 0.0339 max mem: 8233 +Train: [79] [3900/6250] eta: 0:06:54 lr: 0.000014 grad: 0.1484 (0.1531) loss: 0.8743 (0.8770) time: 0.2348 data: 0.1260 max mem: 8233 +Train: [79] [4000/6250] eta: 0:06:38 lr: 0.000014 grad: 0.1482 (0.1530) loss: 0.8758 (0.8770) time: 0.1240 data: 0.0004 max mem: 8233 +Train: [79] [4100/6250] eta: 0:06:19 lr: 0.000014 grad: 0.1541 (0.1530) loss: 0.8801 (0.8770) time: 0.1380 data: 0.0620 max mem: 8233 +Train: [79] [4200/6250] eta: 0:06:01 lr: 0.000014 grad: 0.1474 (0.1531) loss: 0.8748 (0.8770) time: 0.1128 data: 0.0003 max mem: 8233 +Train: [79] [4300/6250] eta: 0:05:42 lr: 0.000014 grad: 0.1513 (0.1530) loss: 0.8725 (0.8770) time: 0.1347 data: 0.0439 max mem: 8233 +Train: [79] [4400/6250] eta: 0:05:24 lr: 0.000014 grad: 0.1328 (0.1530) loss: 0.8819 (0.8770) time: 0.1815 data: 0.0951 max mem: 8233 +Train: [79] [4500/6250] eta: 0:05:06 lr: 0.000014 grad: 0.1539 (0.1530) loss: 0.8739 (0.8770) time: 0.1521 data: 0.0681 max mem: 8233 +Train: [79] [4600/6250] eta: 0:04:48 lr: 0.000014 grad: 0.1434 (0.1530) loss: 0.8801 (0.8770) time: 0.1478 data: 0.0661 max mem: 8233 +Train: [79] [4700/6250] eta: 0:04:30 lr: 0.000013 grad: 0.1548 (0.1531) loss: 0.8791 (0.8770) time: 0.1645 data: 0.0660 max mem: 8233 +Train: [79] [4800/6250] eta: 0:04:13 lr: 0.000013 grad: 0.1457 (0.1531) loss: 0.8771 (0.8770) time: 0.1824 data: 0.1047 max mem: 8233 +Train: [79] [4900/6250] eta: 0:03:55 lr: 0.000013 grad: 0.1441 (0.1530) loss: 0.8793 (0.8770) time: 0.1994 data: 0.0863 max mem: 8233 +Train: [79] [5000/6250] eta: 0:03:38 lr: 0.000013 grad: 0.1453 (0.1529) loss: 0.8775 (0.8769) time: 0.1634 data: 0.0856 max mem: 8233 +Train: [79] [5100/6250] eta: 0:03:21 lr: 0.000013 grad: 0.1512 (0.1530) loss: 0.8721 (0.8769) time: 0.3059 data: 0.2153 max mem: 8233 +Train: [79] [5200/6250] eta: 0:03:03 lr: 0.000013 grad: 0.1523 (0.1530) loss: 0.8725 (0.8769) time: 0.1510 data: 0.0708 max mem: 8233 +Train: [79] [5300/6250] eta: 0:02:45 lr: 0.000013 grad: 0.1424 (0.1530) loss: 0.8791 (0.8769) time: 0.1268 data: 0.0003 max mem: 8233 +Train: [79] [5400/6250] eta: 0:02:28 lr: 0.000013 grad: 0.1460 (0.1531) loss: 0.8773 (0.8768) time: 0.1621 data: 0.0764 max mem: 8233 +Train: [79] [5500/6250] eta: 0:02:10 lr: 0.000013 grad: 0.1535 (0.1531) loss: 0.8759 (0.8768) time: 0.1661 data: 0.0801 max mem: 8233 +Train: [79] [5600/6250] eta: 0:01:53 lr: 0.000013 grad: 0.1543 (0.1531) loss: 0.8732 (0.8768) time: 0.1574 data: 0.0728 max mem: 8233 +Train: [79] [5700/6250] eta: 0:01:35 lr: 0.000013 grad: 0.1460 (0.1533) loss: 0.8764 (0.8768) time: 0.1295 data: 0.0627 max mem: 8233 +Train: [79] [5800/6250] eta: 0:01:18 lr: 0.000013 grad: 0.1539 (0.1533) loss: 0.8729 (0.8768) time: 0.2165 data: 0.1324 max mem: 8233 +Train: [79] [5900/6250] eta: 0:01:00 lr: 0.000013 grad: 0.1439 (0.1532) loss: 0.8727 (0.8768) time: 0.1712 data: 0.0948 max mem: 8233 +Train: [79] [6000/6250] eta: 0:00:43 lr: 0.000013 grad: 0.1610 (0.1534) loss: 0.8733 (0.8768) time: 0.1554 data: 0.0636 max mem: 8233 +Train: [79] [6100/6250] eta: 0:00:25 lr: 0.000013 grad: 0.1534 (0.1535) loss: 0.8730 (0.8768) time: 0.1662 data: 0.0744 max mem: 8233 +Train: [79] [6200/6250] eta: 0:00:08 lr: 0.000013 grad: 0.1454 (0.1535) loss: 0.8790 (0.8768) time: 0.1584 data: 0.0704 max mem: 8233 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1441 (0.1537) loss: 0.8782 (0.8768) time: 0.1847 data: 0.0994 max mem: 8233 +Train: [79] Total time: 0:18:08 (0.1742 s / it) +Averaged stats: lr: 0.000013 grad: 0.1441 (0.1537) loss: 0.8782 (0.8768) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:05:50 loss: 0.8930 (0.8930) time: 5.6538 data: 5.6278 max mem: 8233 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8842 (0.8846) time: 0.1529 data: 0.1323 max mem: 8233 +Eval (hcp-train-subset): [79] Total time: 0:00:15 (0.2554 s / it) +Averaged stats (hcp-train-subset): loss: 0.8842 (0.8846) +Making plots (hcp-train-subset): example=26 +Eval (hcp-val): [79] [ 0/62] eta: 0:07:30 loss: 0.8784 (0.8784) time: 7.2686 data: 7.2115 max mem: 8233 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8827 (0.8833) time: 0.1520 data: 0.1308 max mem: 8233 +Eval (hcp-val): [79] Total time: 0:00:16 (0.2602 s / it) +Averaged stats (hcp-val): loss: 0.8827 (0.8833) +Making plots (hcp-val): example=1 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-00079.pth +Train: [80] [ 0/6250] eta: 12:56:38 lr: 0.000013 grad: 0.1021 (0.1021) loss: 0.8885 (0.8885) time: 7.4558 data: 7.3047 max mem: 8233 +Train: [80] [ 100/6250] eta: 0:22:34 lr: 0.000013 grad: 0.1465 (0.1563) loss: 0.8900 (0.8876) time: 0.1570 data: 0.0503 max mem: 8233 +Train: [80] [ 200/6250] eta: 0:21:08 lr: 0.000013 grad: 0.1345 (0.1502) loss: 0.8804 (0.8857) time: 0.2883 data: 0.1512 max mem: 8233 +Train: [80] [ 300/6250] eta: 0:19:15 lr: 0.000013 grad: 0.1360 (0.1470) loss: 0.8773 (0.8838) time: 0.1763 data: 0.0805 max mem: 8233 +Train: [80] [ 400/6250] eta: 0:18:26 lr: 0.000013 grad: 0.1392 (0.1468) loss: 0.8796 (0.8828) time: 0.1394 data: 0.0430 max mem: 8233 +Train: [80] [ 500/6250] eta: 0:17:57 lr: 0.000013 grad: 0.1317 (0.1456) loss: 0.8779 (0.8822) time: 0.2060 data: 0.1069 max mem: 8233 +Train: [80] [ 600/6250] eta: 0:17:51 lr: 0.000013 grad: 0.1525 (0.1462) loss: 0.8773 (0.8813) time: 0.2664 data: 0.1705 max mem: 8233 +Train: [80] [ 700/6250] eta: 0:17:12 lr: 0.000013 grad: 0.1451 (0.1465) loss: 0.8808 (0.8808) time: 0.1636 data: 0.0712 max mem: 8233 +Train: [80] [ 800/6250] eta: 0:17:38 lr: 0.000013 grad: 0.1447 (0.1468) loss: 0.8720 (0.8801) time: 0.1194 data: 0.0002 max mem: 8233 +Train: [80] [ 900/6250] eta: 0:17:25 lr: 0.000013 grad: 0.1380 (0.1471) loss: 0.8746 (0.8799) time: 0.2556 data: 0.1829 max mem: 8233 +Train: [80] [1000/6250] eta: 0:17:36 lr: 0.000013 grad: 0.1395 (0.1473) loss: 0.8776 (0.8799) time: 0.5266 data: 0.4165 max mem: 8233 +Train: [80] [1100/6250] eta: 0:16:53 lr: 0.000013 grad: 0.1464 (0.1472) loss: 0.8828 (0.8798) time: 0.1302 data: 0.0395 max mem: 8233 +Train: [80] [1200/6250] eta: 0:16:17 lr: 0.000013 grad: 0.1412 (0.1481) loss: 0.8752 (0.8793) time: 0.1539 data: 0.0725 max mem: 8233 +Train: [80] [1300/6250] eta: 0:15:45 lr: 0.000013 grad: 0.1474 (0.1487) loss: 0.8712 (0.8788) time: 0.1514 data: 0.0682 max mem: 8233 +Train: [80] [1400/6250] eta: 0:15:21 lr: 0.000013 grad: 0.1438 (0.1496) loss: 0.8682 (0.8784) time: 0.1236 data: 0.0418 max mem: 8233 +Train: [80] [1500/6250] eta: 0:14:54 lr: 0.000013 grad: 0.1517 (0.1497) loss: 0.8746 (0.8782) time: 0.2082 data: 0.1333 max mem: 8233 +Train: [80] [1600/6250] eta: 0:14:25 lr: 0.000013 grad: 0.1589 (0.1501) loss: 0.8705 (0.8778) time: 0.1616 data: 0.0737 max mem: 8233 +Train: [80] [1700/6250] eta: 0:13:59 lr: 0.000013 grad: 0.1519 (0.1504) loss: 0.8688 (0.8775) time: 0.1617 data: 0.0702 max mem: 8233 +Train: [80] [1800/6250] eta: 0:13:34 lr: 0.000013 grad: 0.1560 (0.1511) loss: 0.8756 (0.8772) time: 0.1696 data: 0.0863 max mem: 8233 +Train: [80] [1900/6250] eta: 0:13:09 lr: 0.000013 grad: 0.1581 (0.1517) loss: 0.8696 (0.8769) time: 0.1654 data: 0.0700 max mem: 8233 +Train: [80] [2000/6250] eta: 0:12:48 lr: 0.000013 grad: 0.1645 (0.1519) loss: 0.8734 (0.8765) time: 0.1566 data: 0.0816 max mem: 8233 +Train: [80] [2100/6250] eta: 0:12:27 lr: 0.000013 grad: 0.1555 (0.1522) loss: 0.8694 (0.8763) time: 0.1841 data: 0.0976 max mem: 8233 +Train: [80] [2200/6250] eta: 0:12:05 lr: 0.000013 grad: 0.1666 (0.1525) loss: 0.8714 (0.8761) time: 0.1610 data: 0.0771 max mem: 8233 +Train: [80] [2300/6250] eta: 0:11:43 lr: 0.000013 grad: 0.1437 (0.1526) loss: 0.8783 (0.8759) time: 0.1654 data: 0.0955 max mem: 8233 +Train: [80] [2400/6250] eta: 0:11:25 lr: 0.000013 grad: 0.1542 (0.1526) loss: 0.8704 (0.8758) time: 0.1772 data: 0.0885 max mem: 8233 +Train: [80] [2500/6250] eta: 0:11:11 lr: 0.000013 grad: 0.1519 (0.1527) loss: 0.8729 (0.8758) time: 0.1118 data: 0.0089 max mem: 8233 +Train: [80] [2600/6250] eta: 0:10:50 lr: 0.000013 grad: 0.1412 (0.1526) loss: 0.8769 (0.8758) time: 0.1697 data: 0.0880 max mem: 8233 +Train: [80] [2700/6250] eta: 0:10:31 lr: 0.000013 grad: 0.1367 (0.1524) loss: 0.8771 (0.8758) time: 0.1533 data: 0.0802 max mem: 8233 +Train: [80] [2800/6250] eta: 0:10:13 lr: 0.000013 grad: 0.1407 (0.1524) loss: 0.8746 (0.8758) time: 0.2182 data: 0.1409 max mem: 8233 +Train: [80] [2900/6250] eta: 0:09:55 lr: 0.000013 grad: 0.1496 (0.1525) loss: 0.8793 (0.8759) time: 0.1605 data: 0.0841 max mem: 8233 +Train: [80] [3000/6250] eta: 0:09:39 lr: 0.000013 grad: 0.1441 (0.1526) loss: 0.8784 (0.8760) time: 0.1443 data: 0.0538 max mem: 8233 +Train: [80] [3100/6250] eta: 0:09:22 lr: 0.000013 grad: 0.1466 (0.1526) loss: 0.8776 (0.8761) time: 0.1708 data: 0.0872 max mem: 8233 +Train: [80] [3200/6250] eta: 0:09:02 lr: 0.000013 grad: 0.1428 (0.1525) loss: 0.8720 (0.8761) time: 0.1620 data: 0.0732 max mem: 8233 +Train: [80] [3300/6250] eta: 0:08:43 lr: 0.000013 grad: 0.1433 (0.1524) loss: 0.8774 (0.8762) time: 0.1475 data: 0.0587 max mem: 8233 +Train: [80] [3400/6250] eta: 0:08:24 lr: 0.000012 grad: 0.1436 (0.1524) loss: 0.8785 (0.8763) time: 0.2029 data: 0.1181 max mem: 8233 +Train: [80] [3500/6250] eta: 0:08:06 lr: 0.000012 grad: 0.1431 (0.1523) loss: 0.8813 (0.8764) time: 0.1966 data: 0.1129 max mem: 8233 +Train: [80] [3600/6250] eta: 0:07:50 lr: 0.000012 grad: 0.1441 (0.1522) loss: 0.8765 (0.8766) time: 0.2637 data: 0.1588 max mem: 8233 +Train: [80] [3700/6250] eta: 0:07:32 lr: 0.000012 grad: 0.1535 (0.1522) loss: 0.8768 (0.8767) time: 0.1251 data: 0.0203 max mem: 8233 +Train: [80] [3800/6250] eta: 0:07:15 lr: 0.000012 grad: 0.1435 (0.1521) loss: 0.8794 (0.8768) time: 0.1151 data: 0.0003 max mem: 8233 +Train: [80] [3900/6250] eta: 0:06:56 lr: 0.000012 grad: 0.1447 (0.1519) loss: 0.8826 (0.8769) time: 0.1522 data: 0.0813 max mem: 8233 +Train: [80] [4000/6250] eta: 0:06:41 lr: 0.000012 grad: 0.1459 (0.1519) loss: 0.8812 (0.8770) time: 0.2936 data: 0.2122 max mem: 8233 +Train: [80] [4100/6250] eta: 0:06:27 lr: 0.000012 grad: 0.1410 (0.1518) loss: 0.8775 (0.8770) time: 0.1368 data: 0.0257 max mem: 8233 +Train: [80] [4200/6250] eta: 0:06:08 lr: 0.000012 grad: 0.1501 (0.1517) loss: 0.8795 (0.8770) time: 0.1741 data: 0.0814 max mem: 8233 +Train: [80] [4300/6250] eta: 0:05:53 lr: 0.000012 grad: 0.1391 (0.1517) loss: 0.8809 (0.8771) time: 0.2094 data: 0.1224 max mem: 8233 +Train: [80] [4400/6250] eta: 0:05:33 lr: 0.000012 grad: 0.1486 (0.1517) loss: 0.8784 (0.8770) time: 0.1401 data: 0.0487 max mem: 8233 +Train: [80] [4500/6250] eta: 0:05:14 lr: 0.000012 grad: 0.1438 (0.1517) loss: 0.8753 (0.8770) time: 0.1096 data: 0.0009 max mem: 8233 +Train: [80] [4600/6250] eta: 0:04:55 lr: 0.000012 grad: 0.1436 (0.1517) loss: 0.8797 (0.8770) time: 0.1381 data: 0.0574 max mem: 8233 +Train: [80] [4700/6250] eta: 0:04:37 lr: 0.000012 grad: 0.1438 (0.1516) loss: 0.8792 (0.8771) time: 0.1635 data: 0.0750 max mem: 8233 +Train: [80] [4800/6250] eta: 0:04:19 lr: 0.000012 grad: 0.1390 (0.1516) loss: 0.8870 (0.8772) time: 0.2269 data: 0.1402 max mem: 8233 +Train: [80] [4900/6250] eta: 0:04:00 lr: 0.000012 grad: 0.1511 (0.1515) loss: 0.8798 (0.8773) time: 0.1529 data: 0.0664 max mem: 8233 +Train: [80] [5000/6250] eta: 0:03:41 lr: 0.000012 grad: 0.1438 (0.1515) loss: 0.8804 (0.8774) time: 0.1396 data: 0.0665 max mem: 8233 +Train: [80] [5100/6250] eta: 0:03:23 lr: 0.000012 grad: 0.1455 (0.1514) loss: 0.8790 (0.8775) time: 0.1567 data: 0.0848 max mem: 8233 +Train: [80] [5200/6250] eta: 0:03:05 lr: 0.000012 grad: 0.1438 (0.1513) loss: 0.8792 (0.8775) time: 0.1713 data: 0.0861 max mem: 8233 +Train: [80] [5300/6250] eta: 0:02:47 lr: 0.000012 grad: 0.1372 (0.1512) loss: 0.8829 (0.8776) time: 0.1463 data: 0.0682 max mem: 8233 +Train: [80] [5400/6250] eta: 0:02:30 lr: 0.000012 grad: 0.1467 (0.1512) loss: 0.8782 (0.8776) time: 0.1647 data: 0.0866 max mem: 8233 +Train: [80] [5500/6250] eta: 0:02:12 lr: 0.000012 grad: 0.1499 (0.1512) loss: 0.8812 (0.8776) time: 0.1546 data: 0.0808 max mem: 8233 +Train: [80] [5600/6250] eta: 0:01:54 lr: 0.000012 grad: 0.1391 (0.1512) loss: 0.8849 (0.8777) time: 0.1632 data: 0.0875 max mem: 8233 +Train: [80] [5700/6250] eta: 0:01:36 lr: 0.000012 grad: 0.1469 (0.1512) loss: 0.8831 (0.8778) time: 0.1393 data: 0.0595 max mem: 8233 +Train: [80] [5800/6250] eta: 0:01:19 lr: 0.000012 grad: 0.1465 (0.1512) loss: 0.8815 (0.8778) time: 0.1702 data: 0.0963 max mem: 8233 +Train: [80] [5900/6250] eta: 0:01:01 lr: 0.000012 grad: 0.1418 (0.1512) loss: 0.8832 (0.8779) time: 0.1738 data: 0.0772 max mem: 8233 +Train: [80] [6000/6250] eta: 0:00:43 lr: 0.000012 grad: 0.1483 (0.1511) loss: 0.8797 (0.8780) time: 0.1638 data: 0.0855 max mem: 8233 +Train: [80] [6100/6250] eta: 0:00:26 lr: 0.000012 grad: 0.1403 (0.1511) loss: 0.8832 (0.8780) time: 0.1802 data: 0.0899 max mem: 8233 +Train: [80] [6200/6250] eta: 0:00:08 lr: 0.000012 grad: 0.1523 (0.1511) loss: 0.8806 (0.8781) time: 0.1719 data: 0.0817 max mem: 8233 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1427 (0.1511) loss: 0.8808 (0.8781) time: 0.1633 data: 0.0778 max mem: 8233 +Train: [80] Total time: 0:18:22 (0.1763 s / it) +Averaged stats: lr: 0.000012 grad: 0.1427 (0.1511) loss: 0.8808 (0.8781) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:06:56 loss: 0.8949 (0.8949) time: 6.7193 data: 6.6925 max mem: 8233 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8842 (0.8846) time: 0.1487 data: 0.1269 max mem: 8233 +Eval (hcp-train-subset): [80] Total time: 0:00:15 (0.2510 s / it) +Averaged stats (hcp-train-subset): loss: 0.8842 (0.8846) +Eval (hcp-val): [80] [ 0/62] eta: 0:07:15 loss: 0.8821 (0.8821) time: 7.0163 data: 6.9893 max mem: 8233 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8829 (0.8837) time: 0.1132 data: 0.0914 max mem: 8233 +Eval (hcp-val): [80] Total time: 0:00:15 (0.2523 s / it) +Averaged stats (hcp-val): loss: 0.8829 (0.8837) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 11:18:07 lr: 0.000012 grad: 0.1220 (0.1220) loss: 0.8977 (0.8977) time: 6.5100 data: 6.3420 max mem: 8233 +Train: [81] [ 100/6250] eta: 0:22:38 lr: 0.000012 grad: 0.1605 (0.1794) loss: 0.8789 (0.8742) time: 0.1550 data: 0.0523 max mem: 8233 +Train: [81] [ 200/6250] eta: 0:20:10 lr: 0.000012 grad: 0.1533 (0.1755) loss: 0.8729 (0.8720) time: 0.1860 data: 0.0889 max mem: 8233 +Train: [81] [ 300/6250] eta: 0:18:36 lr: 0.000012 grad: 0.1396 (0.1678) loss: 0.8808 (0.8738) time: 0.1757 data: 0.0803 max mem: 8233 +Train: [81] [ 400/6250] eta: 0:17:38 lr: 0.000012 grad: 0.1395 (0.1641) loss: 0.8775 (0.8752) time: 0.1343 data: 0.0312 max mem: 8233 +Train: [81] [ 500/6250] eta: 0:17:55 lr: 0.000012 grad: 0.1467 (0.1609) loss: 0.8841 (0.8765) time: 0.3319 data: 0.2551 max mem: 8233 +Train: [81] [ 600/6250] eta: 0:17:37 lr: 0.000012 grad: 0.1423 (0.1583) loss: 0.8809 (0.8775) time: 0.1753 data: 0.0831 max mem: 8233 +Train: [81] [ 700/6250] eta: 0:17:12 lr: 0.000012 grad: 0.1333 (0.1560) loss: 0.8831 (0.8783) time: 0.1740 data: 0.0783 max mem: 8233 +Train: [81] [ 800/6250] eta: 0:16:45 lr: 0.000012 grad: 0.1407 (0.1549) loss: 0.8796 (0.8789) time: 0.1794 data: 0.0813 max mem: 8233 +Train: [81] [ 900/6250] eta: 0:16:21 lr: 0.000012 grad: 0.1359 (0.1539) loss: 0.8769 (0.8791) time: 0.1968 data: 0.1124 max mem: 8233 +Train: [81] [1000/6250] eta: 0:15:59 lr: 0.000012 grad: 0.1471 (0.1534) loss: 0.8783 (0.8793) time: 0.1664 data: 0.0785 max mem: 8233 +Train: [81] [1100/6250] eta: 0:15:31 lr: 0.000012 grad: 0.1482 (0.1529) loss: 0.8797 (0.8793) time: 0.1734 data: 0.0922 max mem: 8233 +Train: [81] [1200/6250] eta: 0:15:07 lr: 0.000012 grad: 0.1423 (0.1530) loss: 0.8832 (0.8794) time: 0.1563 data: 0.0695 max mem: 8233 +Train: [81] [1300/6250] eta: 0:14:41 lr: 0.000012 grad: 0.1435 (0.1529) loss: 0.8826 (0.8795) time: 0.1539 data: 0.0771 max mem: 8233 +Train: [81] [1400/6250] eta: 0:14:19 lr: 0.000012 grad: 0.1486 (0.1525) loss: 0.8809 (0.8796) time: 0.1542 data: 0.0744 max mem: 8233 +Train: [81] [1500/6250] eta: 0:13:54 lr: 0.000012 grad: 0.1454 (0.1522) loss: 0.8795 (0.8796) time: 0.1632 data: 0.0799 max mem: 8233 +Train: [81] [1600/6250] eta: 0:13:32 lr: 0.000012 grad: 0.1415 (0.1518) loss: 0.8823 (0.8796) time: 0.1324 data: 0.0477 max mem: 8233 +Train: [81] [1700/6250] eta: 0:13:13 lr: 0.000012 grad: 0.1464 (0.1516) loss: 0.8777 (0.8797) time: 0.1505 data: 0.0721 max mem: 8233 +Train: [81] [1800/6250] eta: 0:12:51 lr: 0.000012 grad: 0.1425 (0.1516) loss: 0.8798 (0.8797) time: 0.1646 data: 0.0800 max mem: 8233 +Train: [81] [1900/6250] eta: 0:12:30 lr: 0.000012 grad: 0.1515 (0.1513) loss: 0.8787 (0.8798) time: 0.1174 data: 0.0327 max mem: 8233 +Train: [81] [2000/6250] eta: 0:12:11 lr: 0.000012 grad: 0.1387 (0.1511) loss: 0.8801 (0.8798) time: 0.1679 data: 0.0941 max mem: 8233 +Train: [81] [2100/6250] eta: 0:11:53 lr: 0.000012 grad: 0.1469 (0.1512) loss: 0.8801 (0.8797) time: 0.1871 data: 0.1137 max mem: 8233 +Train: [81] [2200/6250] eta: 0:11:35 lr: 0.000012 grad: 0.1521 (0.1515) loss: 0.8806 (0.8796) time: 0.1810 data: 0.0893 max mem: 8233 +Train: [81] [2300/6250] eta: 0:11:19 lr: 0.000011 grad: 0.1571 (0.1519) loss: 0.8739 (0.8794) time: 0.1585 data: 0.0701 max mem: 8233 +Train: [81] [2400/6250] eta: 0:11:08 lr: 0.000011 grad: 0.1540 (0.1521) loss: 0.8761 (0.8793) time: 0.1126 data: 0.0115 max mem: 8233 +Train: [81] [2500/6250] eta: 0:10:48 lr: 0.000011 grad: 0.1522 (0.1523) loss: 0.8760 (0.8792) time: 0.1054 data: 0.0164 max mem: 8233 +Train: [81] [2600/6250] eta: 0:10:37 lr: 0.000011 grad: 0.1499 (0.1523) loss: 0.8823 (0.8791) time: 0.2757 data: 0.2184 max mem: 8233 +Train: [81] [2700/6250] eta: 0:10:17 lr: 0.000011 grad: 0.1472 (0.1524) loss: 0.8743 (0.8790) time: 0.1537 data: 0.0890 max mem: 8233 +Train: [81] [2800/6250] eta: 0:09:57 lr: 0.000011 grad: 0.1479 (0.1527) loss: 0.8774 (0.8789) time: 0.1593 data: 0.0900 max mem: 8233 +Train: [81] [2900/6250] eta: 0:09:38 lr: 0.000011 grad: 0.1392 (0.1528) loss: 0.8800 (0.8788) time: 0.1524 data: 0.0735 max mem: 8233 +Train: [81] [3000/6250] eta: 0:09:20 lr: 0.000011 grad: 0.1501 (0.1531) loss: 0.8790 (0.8787) time: 0.1712 data: 0.0948 max mem: 8233 +Train: [81] [3100/6250] eta: 0:09:02 lr: 0.000011 grad: 0.1482 (0.1532) loss: 0.8747 (0.8786) time: 0.1598 data: 0.0807 max mem: 8233 +Train: [81] [3200/6250] eta: 0:08:44 lr: 0.000011 grad: 0.1551 (0.1533) loss: 0.8750 (0.8786) time: 0.1437 data: 0.0550 max mem: 8233 +Train: [81] [3300/6250] eta: 0:08:26 lr: 0.000011 grad: 0.1465 (0.1535) loss: 0.8832 (0.8785) time: 0.1702 data: 0.1012 max mem: 8233 +Train: [81] [3400/6250] eta: 0:08:09 lr: 0.000011 grad: 0.1392 (0.1536) loss: 0.8871 (0.8786) time: 0.1773 data: 0.0877 max mem: 8233 +Train: [81] [3500/6250] eta: 0:07:50 lr: 0.000011 grad: 0.1472 (0.1537) loss: 0.8745 (0.8785) time: 0.1610 data: 0.0801 max mem: 8233 +Train: [81] [3600/6250] eta: 0:07:31 lr: 0.000011 grad: 0.1463 (0.1538) loss: 0.8786 (0.8784) time: 0.1532 data: 0.0688 max mem: 8233 +Train: [81] [3700/6250] eta: 0:07:13 lr: 0.000011 grad: 0.1479 (0.1539) loss: 0.8763 (0.8784) time: 0.1351 data: 0.0404 max mem: 8233 +Train: [81] [3800/6250] eta: 0:06:55 lr: 0.000011 grad: 0.1421 (0.1542) loss: 0.8772 (0.8785) time: 0.1448 data: 0.0646 max mem: 8233 +Train: [81] [3900/6250] eta: 0:06:39 lr: 0.000011 grad: 0.1418 (0.1541) loss: 0.8816 (0.8785) time: 0.0885 data: 0.0002 max mem: 8233 +Train: [81] [4000/6250] eta: 0:06:22 lr: 0.000011 grad: 0.1458 (0.1540) loss: 0.8817 (0.8785) time: 0.1211 data: 0.0002 max mem: 8233 +Train: [81] [4100/6250] eta: 0:06:04 lr: 0.000011 grad: 0.1367 (0.1540) loss: 0.8820 (0.8785) time: 0.1496 data: 0.0690 max mem: 8233 +Train: [81] [4200/6250] eta: 0:05:48 lr: 0.000011 grad: 0.1507 (0.1540) loss: 0.8814 (0.8785) time: 0.2630 data: 0.1871 max mem: 8233 +Train: [81] [4300/6250] eta: 0:05:30 lr: 0.000011 grad: 0.1453 (0.1540) loss: 0.8768 (0.8785) time: 0.1546 data: 0.0680 max mem: 8233 +Train: [81] [4400/6250] eta: 0:05:12 lr: 0.000011 grad: 0.1370 (0.1539) loss: 0.8800 (0.8785) time: 0.1729 data: 0.0982 max mem: 8233 +Train: [81] [4500/6250] eta: 0:04:55 lr: 0.000011 grad: 0.1388 (0.1538) loss: 0.8816 (0.8785) time: 0.1531 data: 0.0794 max mem: 8233 +Train: [81] [4600/6250] eta: 0:04:38 lr: 0.000011 grad: 0.1478 (0.1538) loss: 0.8800 (0.8785) time: 0.1684 data: 0.0899 max mem: 8233 +Train: [81] [4700/6250] eta: 0:04:21 lr: 0.000011 grad: 0.1473 (0.1536) loss: 0.8839 (0.8785) time: 0.1593 data: 0.0801 max mem: 8233 +Train: [81] [4800/6250] eta: 0:04:03 lr: 0.000011 grad: 0.1478 (0.1535) loss: 0.8850 (0.8786) time: 0.1890 data: 0.1102 max mem: 8233 +Train: [81] [4900/6250] eta: 0:03:46 lr: 0.000011 grad: 0.1475 (0.1534) loss: 0.8802 (0.8786) time: 0.1664 data: 0.0898 max mem: 8233 +Train: [81] [5000/6250] eta: 0:03:29 lr: 0.000011 grad: 0.1491 (0.1534) loss: 0.8740 (0.8786) time: 0.1835 data: 0.1072 max mem: 8233 +Train: [81] [5100/6250] eta: 0:03:13 lr: 0.000011 grad: 0.1451 (0.1534) loss: 0.8795 (0.8786) time: 0.1041 data: 0.0003 max mem: 8233 +Train: [81] [5200/6250] eta: 0:02:56 lr: 0.000011 grad: 0.1453 (0.1534) loss: 0.8828 (0.8787) time: 0.1945 data: 0.1157 max mem: 8233 +Train: [81] [5300/6250] eta: 0:02:39 lr: 0.000011 grad: 0.1398 (0.1534) loss: 0.8812 (0.8787) time: 0.1916 data: 0.1026 max mem: 8233 +Train: [81] [5400/6250] eta: 0:02:23 lr: 0.000011 grad: 0.1484 (0.1533) loss: 0.8805 (0.8787) time: 0.1250 data: 0.0443 max mem: 8233 +Train: [81] [5500/6250] eta: 0:02:06 lr: 0.000011 grad: 0.1474 (0.1533) loss: 0.8823 (0.8787) time: 0.1545 data: 0.0634 max mem: 8233 +Train: [81] [5600/6250] eta: 0:01:49 lr: 0.000011 grad: 0.1499 (0.1532) loss: 0.8792 (0.8787) time: 0.1574 data: 0.0742 max mem: 8233 +Train: [81] [5700/6250] eta: 0:01:32 lr: 0.000011 grad: 0.1484 (0.1533) loss: 0.8722 (0.8787) time: 0.1542 data: 0.0711 max mem: 8233 +Train: [81] [5800/6250] eta: 0:01:15 lr: 0.000011 grad: 0.1475 (0.1532) loss: 0.8765 (0.8787) time: 0.1883 data: 0.1015 max mem: 8233 +Train: [81] [5900/6250] eta: 0:00:59 lr: 0.000011 grad: 0.1454 (0.1533) loss: 0.8808 (0.8787) time: 0.1792 data: 0.1005 max mem: 8233 +Train: [81] [6000/6250] eta: 0:00:42 lr: 0.000011 grad: 0.1593 (0.1535) loss: 0.8737 (0.8786) time: 0.1830 data: 0.0995 max mem: 8233 +Train: [81] [6100/6250] eta: 0:00:25 lr: 0.000011 grad: 0.1489 (0.1535) loss: 0.8765 (0.8786) time: 0.1462 data: 0.0575 max mem: 8233 +Train: [81] [6200/6250] eta: 0:00:08 lr: 0.000011 grad: 0.1594 (0.1536) loss: 0.8704 (0.8786) time: 0.1804 data: 0.1020 max mem: 8233 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1516 (0.1536) loss: 0.8737 (0.8786) time: 0.1599 data: 0.0781 max mem: 8233 +Train: [81] Total time: 0:17:42 (0.1700 s / it) +Averaged stats: lr: 0.000011 grad: 0.1516 (0.1536) loss: 0.8737 (0.8786) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:06:40 loss: 0.8934 (0.8934) time: 6.4629 data: 6.4361 max mem: 8233 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8825 (0.8831) time: 0.1265 data: 0.1062 max mem: 8233 +Eval (hcp-train-subset): [81] Total time: 0:00:15 (0.2446 s / it) +Averaged stats (hcp-train-subset): loss: 0.8825 (0.8831) +Eval (hcp-val): [81] [ 0/62] eta: 0:06:04 loss: 0.8791 (0.8791) time: 5.8799 data: 5.8321 max mem: 8233 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8816 (0.8826) time: 0.1555 data: 0.1346 max mem: 8233 +Eval (hcp-val): [81] Total time: 0:00:15 (0.2532 s / it) +Averaged stats (hcp-val): loss: 0.8816 (0.8826) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 12:51:25 lr: 0.000011 grad: 0.1402 (0.1402) loss: 0.9018 (0.9018) time: 7.4056 data: 7.3108 max mem: 8233 +Train: [82] [ 100/6250] eta: 0:24:19 lr: 0.000011 grad: 0.1376 (0.1553) loss: 0.8894 (0.8858) time: 0.1770 data: 0.0870 max mem: 8233 +Train: [82] [ 200/6250] eta: 0:20:40 lr: 0.000011 grad: 0.1499 (0.1659) loss: 0.8801 (0.8808) time: 0.1760 data: 0.0603 max mem: 8233 +Train: [82] [ 300/6250] eta: 0:19:17 lr: 0.000011 grad: 0.1436 (0.1667) loss: 0.8774 (0.8781) time: 0.1899 data: 0.0924 max mem: 8233 +Train: [82] [ 400/6250] eta: 0:18:07 lr: 0.000011 grad: 0.1515 (0.1661) loss: 0.8681 (0.8770) time: 0.1615 data: 0.0641 max mem: 8233 +Train: [82] [ 500/6250] eta: 0:17:18 lr: 0.000011 grad: 0.1540 (0.1647) loss: 0.8793 (0.8766) time: 0.1469 data: 0.0303 max mem: 8233 +Train: [82] [ 600/6250] eta: 0:16:42 lr: 0.000011 grad: 0.1444 (0.1636) loss: 0.8804 (0.8764) time: 0.1683 data: 0.0770 max mem: 8233 +Train: [82] [ 700/6250] eta: 0:16:24 lr: 0.000011 grad: 0.1517 (0.1622) loss: 0.8786 (0.8765) time: 0.1137 data: 0.0268 max mem: 8233 +Train: [82] [ 800/6250] eta: 0:16:16 lr: 0.000011 grad: 0.1505 (0.1618) loss: 0.8793 (0.8761) time: 0.2168 data: 0.1411 max mem: 8233 +Train: [82] [ 900/6250] eta: 0:15:51 lr: 0.000011 grad: 0.1431 (0.1608) loss: 0.8801 (0.8762) time: 0.1638 data: 0.0800 max mem: 8233 +Train: [82] [1000/6250] eta: 0:15:23 lr: 0.000011 grad: 0.1442 (0.1603) loss: 0.8824 (0.8762) time: 0.1345 data: 0.0539 max mem: 8233 +Train: [82] [1100/6250] eta: 0:15:02 lr: 0.000011 grad: 0.1432 (0.1599) loss: 0.8846 (0.8763) time: 0.1102 data: 0.0065 max mem: 8233 +Train: [82] [1200/6250] eta: 0:14:40 lr: 0.000011 grad: 0.1545 (0.1594) loss: 0.8778 (0.8762) time: 0.1720 data: 0.0838 max mem: 8233 +Train: [82] [1300/6250] eta: 0:14:28 lr: 0.000011 grad: 0.1421 (0.1588) loss: 0.8781 (0.8762) time: 0.1496 data: 0.0659 max mem: 8233 +Train: [82] [1400/6250] eta: 0:14:10 lr: 0.000010 grad: 0.1464 (0.1583) loss: 0.8776 (0.8763) time: 0.2110 data: 0.1334 max mem: 8233 +Train: [82] [1500/6250] eta: 0:13:55 lr: 0.000010 grad: 0.1305 (0.1578) loss: 0.8830 (0.8764) time: 0.2141 data: 0.1251 max mem: 8233 +Train: [82] [1600/6250] eta: 0:13:42 lr: 0.000010 grad: 0.1400 (0.1573) loss: 0.8766 (0.8765) time: 0.1104 data: 0.0014 max mem: 8233 +Train: [82] [1700/6250] eta: 0:13:21 lr: 0.000010 grad: 0.1481 (0.1571) loss: 0.8768 (0.8767) time: 0.1274 data: 0.0355 max mem: 8233 +Train: [82] [1800/6250] eta: 0:13:21 lr: 0.000010 grad: 0.1455 (0.1568) loss: 0.8774 (0.8768) time: 0.1370 data: 0.0323 max mem: 8233 +Train: [82] [1900/6250] eta: 0:12:57 lr: 0.000010 grad: 0.1450 (0.1565) loss: 0.8748 (0.8769) time: 0.1550 data: 0.0677 max mem: 8233 +Train: [82] [2000/6250] eta: 0:12:34 lr: 0.000010 grad: 0.1400 (0.1561) loss: 0.8822 (0.8771) time: 0.1259 data: 0.0403 max mem: 8233 +Train: [82] [2100/6250] eta: 0:12:13 lr: 0.000010 grad: 0.1442 (0.1559) loss: 0.8774 (0.8773) time: 0.1330 data: 0.0397 max mem: 8233 +Train: [82] [2200/6250] eta: 0:11:51 lr: 0.000010 grad: 0.1443 (0.1557) loss: 0.8807 (0.8774) time: 0.1762 data: 0.1018 max mem: 8233 +Train: [82] [2300/6250] eta: 0:11:30 lr: 0.000010 grad: 0.1394 (0.1555) loss: 0.8832 (0.8776) time: 0.1394 data: 0.0581 max mem: 8233 +Train: [82] [2400/6250] eta: 0:11:09 lr: 0.000010 grad: 0.1412 (0.1552) loss: 0.8803 (0.8777) time: 0.1373 data: 0.0440 max mem: 8233 +Train: [82] [2500/6250] eta: 0:10:49 lr: 0.000010 grad: 0.1500 (0.1552) loss: 0.8813 (0.8778) time: 0.1676 data: 0.0849 max mem: 8233 +Train: [82] [2600/6250] eta: 0:10:30 lr: 0.000010 grad: 0.1497 (0.1550) loss: 0.8758 (0.8779) time: 0.1691 data: 0.0938 max mem: 8233 +Train: [82] [2700/6250] eta: 0:10:13 lr: 0.000010 grad: 0.1493 (0.1548) loss: 0.8805 (0.8779) time: 0.1582 data: 0.0754 max mem: 8233 +Train: [82] [2800/6250] eta: 0:09:56 lr: 0.000010 grad: 0.1490 (0.1548) loss: 0.8742 (0.8780) time: 0.2232 data: 0.1568 max mem: 8233 +Train: [82] [2900/6250] eta: 0:09:37 lr: 0.000010 grad: 0.1508 (0.1547) loss: 0.8798 (0.8780) time: 0.1381 data: 0.0596 max mem: 8233 +Train: [82] [3000/6250] eta: 0:09:19 lr: 0.000010 grad: 0.1493 (0.1546) loss: 0.8805 (0.8781) time: 0.1359 data: 0.0554 max mem: 8233 +Train: [82] [3100/6250] eta: 0:09:01 lr: 0.000010 grad: 0.1410 (0.1546) loss: 0.8791 (0.8782) time: 0.1699 data: 0.0815 max mem: 8233 +Train: [82] [3200/6250] eta: 0:08:44 lr: 0.000010 grad: 0.1449 (0.1545) loss: 0.8812 (0.8782) time: 0.1772 data: 0.0866 max mem: 8233 +Train: [82] [3300/6250] eta: 0:08:26 lr: 0.000010 grad: 0.1595 (0.1546) loss: 0.8743 (0.8782) time: 0.1963 data: 0.1046 max mem: 8233 +Train: [82] [3400/6250] eta: 0:08:08 lr: 0.000010 grad: 0.1455 (0.1546) loss: 0.8782 (0.8782) time: 0.1655 data: 0.0670 max mem: 8233 +Train: [82] [3500/6250] eta: 0:07:50 lr: 0.000010 grad: 0.1498 (0.1545) loss: 0.8706 (0.8781) time: 0.1746 data: 0.0836 max mem: 8233 +Train: [82] [3600/6250] eta: 0:07:32 lr: 0.000010 grad: 0.1402 (0.1543) loss: 0.8790 (0.8781) time: 0.1427 data: 0.0643 max mem: 8233 +Train: [82] [3700/6250] eta: 0:07:13 lr: 0.000010 grad: 0.1464 (0.1542) loss: 0.8762 (0.8781) time: 0.1452 data: 0.0629 max mem: 8233 +Train: [82] [3800/6250] eta: 0:06:55 lr: 0.000010 grad: 0.1448 (0.1541) loss: 0.8749 (0.8781) time: 0.1898 data: 0.1057 max mem: 8233 +Train: [82] [3900/6250] eta: 0:06:37 lr: 0.000010 grad: 0.1590 (0.1544) loss: 0.8727 (0.8780) time: 0.1610 data: 0.0821 max mem: 8233 +Train: [82] [4000/6250] eta: 0:06:20 lr: 0.000010 grad: 0.1560 (0.1547) loss: 0.8748 (0.8779) time: 0.1617 data: 0.0803 max mem: 8233 +Train: [82] [4100/6250] eta: 0:06:03 lr: 0.000010 grad: 0.1526 (0.1547) loss: 0.8736 (0.8778) time: 0.2106 data: 0.1323 max mem: 8233 +Train: [82] [4200/6250] eta: 0:05:48 lr: 0.000010 grad: 0.1511 (0.1548) loss: 0.8740 (0.8777) time: 0.3075 data: 0.2272 max mem: 8233 +Train: [82] [4300/6250] eta: 0:05:33 lr: 0.000010 grad: 0.1470 (0.1549) loss: 0.8693 (0.8777) time: 0.1986 data: 0.1100 max mem: 8233 +Train: [82] [4400/6250] eta: 0:05:18 lr: 0.000010 grad: 0.1471 (0.1549) loss: 0.8735 (0.8776) time: 0.1593 data: 0.0566 max mem: 8233 +Train: [82] [4500/6250] eta: 0:05:00 lr: 0.000010 grad: 0.1519 (0.1551) loss: 0.8760 (0.8775) time: 0.1579 data: 0.0822 max mem: 8233 +Train: [82] [4600/6250] eta: 0:04:43 lr: 0.000010 grad: 0.1428 (0.1553) loss: 0.8839 (0.8775) time: 0.1422 data: 0.0628 max mem: 8233 +Train: [82] [4700/6250] eta: 0:04:26 lr: 0.000010 grad: 0.1473 (0.1554) loss: 0.8728 (0.8774) time: 0.1478 data: 0.0609 max mem: 8233 +Train: [82] [4800/6250] eta: 0:04:09 lr: 0.000010 grad: 0.1597 (0.1555) loss: 0.8681 (0.8773) time: 0.2677 data: 0.1831 max mem: 8233 +Train: [82] [4900/6250] eta: 0:03:51 lr: 0.000010 grad: 0.1520 (0.1557) loss: 0.8740 (0.8772) time: 0.1698 data: 0.0860 max mem: 8233 +Train: [82] [5000/6250] eta: 0:03:35 lr: 0.000010 grad: 0.1501 (0.1557) loss: 0.8769 (0.8772) time: 0.2418 data: 0.1342 max mem: 8233 +Train: [82] [5100/6250] eta: 0:03:18 lr: 0.000010 grad: 0.1484 (0.1556) loss: 0.8800 (0.8772) time: 0.1454 data: 0.0716 max mem: 8233 +Train: [82] [5200/6250] eta: 0:03:00 lr: 0.000010 grad: 0.1510 (0.1556) loss: 0.8762 (0.8772) time: 0.1148 data: 0.0364 max mem: 8233 +Train: [82] [5300/6250] eta: 0:02:43 lr: 0.000010 grad: 0.1490 (0.1557) loss: 0.8794 (0.8772) time: 0.1408 data: 0.0483 max mem: 8233 +Train: [82] [5400/6250] eta: 0:02:26 lr: 0.000010 grad: 0.1575 (0.1558) loss: 0.8752 (0.8771) time: 0.1283 data: 0.0246 max mem: 8233 +Train: [82] [5500/6250] eta: 0:02:08 lr: 0.000010 grad: 0.1620 (0.1560) loss: 0.8750 (0.8771) time: 0.1695 data: 0.0914 max mem: 8233 +Train: [82] [5600/6250] eta: 0:01:51 lr: 0.000010 grad: 0.1500 (0.1560) loss: 0.8780 (0.8771) time: 0.1535 data: 0.0821 max mem: 8233 +Train: [82] [5700/6250] eta: 0:01:34 lr: 0.000010 grad: 0.1469 (0.1561) loss: 0.8750 (0.8770) time: 0.1795 data: 0.1064 max mem: 8233 +Train: [82] [5800/6250] eta: 0:01:17 lr: 0.000010 grad: 0.1510 (0.1561) loss: 0.8857 (0.8771) time: 0.1677 data: 0.0926 max mem: 8233 +Train: [82] [5900/6250] eta: 0:01:00 lr: 0.000010 grad: 0.1525 (0.1561) loss: 0.8753 (0.8770) time: 0.1660 data: 0.0757 max mem: 8233 +Train: [82] [6000/6250] eta: 0:00:42 lr: 0.000010 grad: 0.1551 (0.1562) loss: 0.8755 (0.8770) time: 0.1644 data: 0.0921 max mem: 8233 +Train: [82] [6100/6250] eta: 0:00:25 lr: 0.000010 grad: 0.1567 (0.1563) loss: 0.8777 (0.8770) time: 0.1817 data: 0.1077 max mem: 8233 +Train: [82] [6200/6250] eta: 0:00:08 lr: 0.000010 grad: 0.1547 (0.1562) loss: 0.8741 (0.8770) time: 0.1542 data: 0.0659 max mem: 8233 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1525 (0.1562) loss: 0.8758 (0.8770) time: 0.1702 data: 0.0877 max mem: 8233 +Train: [82] Total time: 0:18:00 (0.1729 s / it) +Averaged stats: lr: 0.000010 grad: 0.1525 (0.1562) loss: 0.8758 (0.8770) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:06:49 loss: 0.8915 (0.8915) time: 6.6013 data: 6.5734 max mem: 8233 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8814 (0.8827) time: 0.1220 data: 0.1005 max mem: 8233 +Eval (hcp-train-subset): [82] Total time: 0:00:15 (0.2507 s / it) +Averaged stats (hcp-train-subset): loss: 0.8814 (0.8827) +Eval (hcp-val): [82] [ 0/62] eta: 0:05:52 loss: 0.8780 (0.8780) time: 5.6902 data: 5.6571 max mem: 8233 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8825 (0.8826) time: 0.1183 data: 0.0974 max mem: 8233 +Eval (hcp-val): [82] Total time: 0:00:14 (0.2350 s / it) +Averaged stats (hcp-val): loss: 0.8825 (0.8826) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 9:23:35 lr: 0.000010 grad: 0.1493 (0.1493) loss: 0.8690 (0.8690) time: 5.4105 data: 5.1096 max mem: 8233 +Train: [83] [ 100/6250] eta: 0:23:06 lr: 0.000010 grad: 0.1454 (0.1534) loss: 0.8890 (0.8783) time: 0.1644 data: 0.0676 max mem: 8233 +Train: [83] [ 200/6250] eta: 0:19:57 lr: 0.000010 grad: 0.1368 (0.1473) loss: 0.8906 (0.8810) time: 0.1381 data: 0.0142 max mem: 8233 +Train: [83] [ 300/6250] eta: 0:18:30 lr: 0.000010 grad: 0.1395 (0.1470) loss: 0.8895 (0.8819) time: 0.1666 data: 0.0633 max mem: 8233 +Train: [83] [ 400/6250] eta: 0:17:30 lr: 0.000010 grad: 0.1434 (0.1467) loss: 0.8854 (0.8823) time: 0.1664 data: 0.0688 max mem: 8233 +Train: [83] [ 500/6250] eta: 0:16:42 lr: 0.000010 grad: 0.1377 (0.1470) loss: 0.8800 (0.8824) time: 0.1435 data: 0.0472 max mem: 8233 +Train: [83] [ 600/6250] eta: 0:16:15 lr: 0.000010 grad: 0.1491 (0.1474) loss: 0.8823 (0.8823) time: 0.1680 data: 0.0819 max mem: 8233 +Train: [83] [ 700/6250] eta: 0:15:59 lr: 0.000009 grad: 0.1452 (0.1476) loss: 0.8790 (0.8819) time: 0.1309 data: 0.0009 max mem: 8233 +Train: [83] [ 800/6250] eta: 0:15:49 lr: 0.000009 grad: 0.1327 (0.1479) loss: 0.8768 (0.8815) time: 0.1839 data: 0.0571 max mem: 8233 +Train: [83] [ 900/6250] eta: 0:16:16 lr: 0.000009 grad: 0.1475 (0.1483) loss: 0.8781 (0.8812) time: 0.2774 data: 0.1509 max mem: 8233 +Train: [83] [1000/6250] eta: 0:15:49 lr: 0.000009 grad: 0.1443 (0.1490) loss: 0.8794 (0.8810) time: 0.1162 data: 0.0138 max mem: 8233 +Train: [83] [1100/6250] eta: 0:15:26 lr: 0.000009 grad: 0.1520 (0.1492) loss: 0.8775 (0.8807) time: 0.1345 data: 0.0237 max mem: 8233 +Train: [83] [1200/6250] eta: 0:15:18 lr: 0.000009 grad: 0.1445 (0.1493) loss: 0.8801 (0.8804) time: 0.2976 data: 0.2073 max mem: 8233 +Train: [83] [1300/6250] eta: 0:14:48 lr: 0.000009 grad: 0.1492 (0.1494) loss: 0.8817 (0.8803) time: 0.1288 data: 0.0245 max mem: 8233 +Train: [83] [1400/6250] eta: 0:14:31 lr: 0.000009 grad: 0.1412 (0.1496) loss: 0.8798 (0.8801) time: 0.1248 data: 0.0066 max mem: 8233 +Train: [83] [1500/6250] eta: 0:14:08 lr: 0.000009 grad: 0.1392 (0.1495) loss: 0.8806 (0.8799) time: 0.1732 data: 0.0806 max mem: 8233 +Train: [83] [1600/6250] eta: 0:13:44 lr: 0.000009 grad: 0.1463 (0.1496) loss: 0.8772 (0.8798) time: 0.1801 data: 0.1006 max mem: 8233 +Train: [83] [1700/6250] eta: 0:13:22 lr: 0.000009 grad: 0.1542 (0.1498) loss: 0.8748 (0.8795) time: 0.1315 data: 0.0379 max mem: 8233 +Train: [83] [1800/6250] eta: 0:13:01 lr: 0.000009 grad: 0.1418 (0.1498) loss: 0.8718 (0.8793) time: 0.1621 data: 0.0735 max mem: 8233 +Train: [83] [1900/6250] eta: 0:12:40 lr: 0.000009 grad: 0.1658 (0.1502) loss: 0.8739 (0.8790) time: 0.1412 data: 0.0558 max mem: 8233 +Train: [83] [2000/6250] eta: 0:12:20 lr: 0.000009 grad: 0.1475 (0.1506) loss: 0.8781 (0.8788) time: 0.1471 data: 0.0682 max mem: 8233 +Train: [83] [2100/6250] eta: 0:12:01 lr: 0.000009 grad: 0.1546 (0.1510) loss: 0.8732 (0.8785) time: 0.1449 data: 0.0614 max mem: 8233 +Train: [83] [2200/6250] eta: 0:11:44 lr: 0.000009 grad: 0.1456 (0.1512) loss: 0.8732 (0.8783) time: 0.2400 data: 0.1502 max mem: 8233 +Train: [83] [2300/6250] eta: 0:11:22 lr: 0.000009 grad: 0.1511 (0.1513) loss: 0.8754 (0.8782) time: 0.1519 data: 0.0669 max mem: 8233 +Train: [83] [2400/6250] eta: 0:11:02 lr: 0.000009 grad: 0.1542 (0.1515) loss: 0.8754 (0.8781) time: 0.1516 data: 0.0723 max mem: 8233 +Train: [83] [2500/6250] eta: 0:10:44 lr: 0.000009 grad: 0.1470 (0.1515) loss: 0.8773 (0.8780) time: 0.1434 data: 0.0493 max mem: 8233 +Train: [83] [2600/6250] eta: 0:10:24 lr: 0.000009 grad: 0.1447 (0.1515) loss: 0.8765 (0.8780) time: 0.1417 data: 0.0585 max mem: 8233 +Train: [83] [2700/6250] eta: 0:10:07 lr: 0.000009 grad: 0.1447 (0.1515) loss: 0.8752 (0.8779) time: 0.1554 data: 0.0723 max mem: 8233 +Train: [83] [2800/6250] eta: 0:09:48 lr: 0.000009 grad: 0.1441 (0.1514) loss: 0.8807 (0.8779) time: 0.1525 data: 0.0758 max mem: 8233 +Train: [83] [2900/6250] eta: 0:09:29 lr: 0.000009 grad: 0.1452 (0.1514) loss: 0.8771 (0.8778) time: 0.1640 data: 0.0830 max mem: 8233 +Train: [83] [3000/6250] eta: 0:09:12 lr: 0.000009 grad: 0.1531 (0.1516) loss: 0.8719 (0.8777) time: 0.1691 data: 0.0986 max mem: 8233 +Train: [83] [3100/6250] eta: 0:08:57 lr: 0.000009 grad: 0.1553 (0.1517) loss: 0.8729 (0.8776) time: 0.1765 data: 0.0972 max mem: 8233 +Train: [83] [3200/6250] eta: 0:08:40 lr: 0.000009 grad: 0.1559 (0.1519) loss: 0.8747 (0.8775) time: 0.1814 data: 0.0885 max mem: 8233 +Train: [83] [3300/6250] eta: 0:08:26 lr: 0.000009 grad: 0.1478 (0.1519) loss: 0.8762 (0.8775) time: 0.1960 data: 0.1101 max mem: 8233 +Train: [83] [3400/6250] eta: 0:08:09 lr: 0.000009 grad: 0.1591 (0.1520) loss: 0.8756 (0.8775) time: 0.1720 data: 0.0902 max mem: 8233 +Train: [83] [3500/6250] eta: 0:07:53 lr: 0.000009 grad: 0.1510 (0.1521) loss: 0.8780 (0.8775) time: 0.1828 data: 0.0933 max mem: 8233 +Train: [83] [3600/6250] eta: 0:07:35 lr: 0.000009 grad: 0.1430 (0.1521) loss: 0.8747 (0.8774) time: 0.1754 data: 0.0826 max mem: 8233 +Train: [83] [3700/6250] eta: 0:07:18 lr: 0.000009 grad: 0.1554 (0.1522) loss: 0.8768 (0.8774) time: 0.1712 data: 0.0775 max mem: 8233 +Train: [83] [3800/6250] eta: 0:07:00 lr: 0.000009 grad: 0.1542 (0.1524) loss: 0.8736 (0.8773) time: 0.1829 data: 0.0929 max mem: 8233 +Train: [83] [3900/6250] eta: 0:06:44 lr: 0.000009 grad: 0.1468 (0.1526) loss: 0.8831 (0.8771) time: 0.1948 data: 0.0714 max mem: 8233 +Train: [83] [4000/6250] eta: 0:06:27 lr: 0.000009 grad: 0.1607 (0.1529) loss: 0.8730 (0.8770) time: 0.1371 data: 0.0446 max mem: 8233 +Train: [83] [4100/6250] eta: 0:06:10 lr: 0.000009 grad: 0.1496 (0.1532) loss: 0.8751 (0.8768) time: 0.1806 data: 0.1019 max mem: 8233 +Train: [83] [4200/6250] eta: 0:05:53 lr: 0.000009 grad: 0.1611 (0.1533) loss: 0.8734 (0.8767) time: 0.1169 data: 0.0003 max mem: 8233 +Train: [83] [4300/6250] eta: 0:05:35 lr: 0.000009 grad: 0.1483 (0.1535) loss: 0.8734 (0.8766) time: 0.1597 data: 0.0709 max mem: 8233 +Train: [83] [4400/6250] eta: 0:05:18 lr: 0.000009 grad: 0.1463 (0.1536) loss: 0.8797 (0.8765) time: 0.1057 data: 0.0295 max mem: 8233 +Train: [83] [4500/6250] eta: 0:05:00 lr: 0.000009 grad: 0.1514 (0.1538) loss: 0.8671 (0.8764) time: 0.1709 data: 0.0748 max mem: 8233 +Train: [83] [4600/6250] eta: 0:04:43 lr: 0.000009 grad: 0.1559 (0.1539) loss: 0.8687 (0.8763) time: 0.2266 data: 0.1452 max mem: 8233 +Train: [83] [4700/6250] eta: 0:04:25 lr: 0.000009 grad: 0.1459 (0.1541) loss: 0.8754 (0.8762) time: 0.1276 data: 0.0445 max mem: 8233 +Train: [83] [4800/6250] eta: 0:04:08 lr: 0.000009 grad: 0.1513 (0.1542) loss: 0.8805 (0.8762) time: 0.1395 data: 0.0532 max mem: 8233 +Train: [83] [4900/6250] eta: 0:03:51 lr: 0.000009 grad: 0.1507 (0.1543) loss: 0.8745 (0.8762) time: 0.1941 data: 0.1101 max mem: 8233 +Train: [83] [5000/6250] eta: 0:03:34 lr: 0.000009 grad: 0.1550 (0.1543) loss: 0.8764 (0.8763) time: 0.0987 data: 0.0133 max mem: 8233 +Train: [83] [5100/6250] eta: 0:03:17 lr: 0.000009 grad: 0.1509 (0.1543) loss: 0.8851 (0.8763) time: 0.1448 data: 0.0548 max mem: 8233 +Train: [83] [5200/6250] eta: 0:02:59 lr: 0.000009 grad: 0.1577 (0.1543) loss: 0.8796 (0.8763) time: 0.1684 data: 0.0881 max mem: 8233 +Train: [83] [5300/6250] eta: 0:02:42 lr: 0.000009 grad: 0.1539 (0.1544) loss: 0.8756 (0.8764) time: 0.1387 data: 0.0574 max mem: 8233 +Train: [83] [5400/6250] eta: 0:02:25 lr: 0.000009 grad: 0.1464 (0.1544) loss: 0.8781 (0.8764) time: 0.1644 data: 0.0828 max mem: 8233 +Train: [83] [5500/6250] eta: 0:02:07 lr: 0.000009 grad: 0.1456 (0.1544) loss: 0.8829 (0.8765) time: 0.1425 data: 0.0601 max mem: 8233 +Train: [83] [5600/6250] eta: 0:01:50 lr: 0.000009 grad: 0.1492 (0.1544) loss: 0.8779 (0.8765) time: 0.1611 data: 0.0728 max mem: 8233 +Train: [83] [5700/6250] eta: 0:01:33 lr: 0.000009 grad: 0.1509 (0.1544) loss: 0.8775 (0.8765) time: 0.1582 data: 0.0770 max mem: 8233 +Train: [83] [5800/6250] eta: 0:01:16 lr: 0.000009 grad: 0.1442 (0.1545) loss: 0.8741 (0.8765) time: 0.1675 data: 0.0967 max mem: 8233 +Train: [83] [5900/6250] eta: 0:00:59 lr: 0.000009 grad: 0.1423 (0.1545) loss: 0.8784 (0.8765) time: 0.1282 data: 0.0509 max mem: 8233 +Train: [83] [6000/6250] eta: 0:00:42 lr: 0.000009 grad: 0.1512 (0.1545) loss: 0.8790 (0.8765) time: 0.1452 data: 0.0515 max mem: 8233 +Train: [83] [6100/6250] eta: 0:00:25 lr: 0.000009 grad: 0.1537 (0.1545) loss: 0.8765 (0.8765) time: 0.1279 data: 0.0386 max mem: 8233 +Train: [83] [6200/6250] eta: 0:00:08 lr: 0.000009 grad: 0.1491 (0.1546) loss: 0.8787 (0.8766) time: 0.1674 data: 0.0862 max mem: 8233 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1443 (0.1546) loss: 0.8786 (0.8766) time: 0.1517 data: 0.0647 max mem: 8233 +Train: [83] Total time: 0:17:47 (0.1708 s / it) +Averaged stats: lr: 0.000009 grad: 0.1443 (0.1546) loss: 0.8786 (0.8766) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:06:22 loss: 0.8912 (0.8912) time: 6.1669 data: 6.1392 max mem: 8233 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8811 (0.8824) time: 0.1025 data: 0.0816 max mem: 8233 +Eval (hcp-train-subset): [83] Total time: 0:00:16 (0.2611 s / it) +Averaged stats (hcp-train-subset): loss: 0.8811 (0.8824) +Eval (hcp-val): [83] [ 0/62] eta: 0:04:28 loss: 0.8779 (0.8779) time: 4.3228 data: 4.2292 max mem: 8233 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8811 (0.8823) time: 0.1574 data: 0.1353 max mem: 8233 +Eval (hcp-val): [83] Total time: 0:00:15 (0.2543 s / it) +Averaged stats (hcp-val): loss: 0.8811 (0.8823) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 13:58:30 lr: 0.000009 grad: 0.1263 (0.1263) loss: 0.9020 (0.9020) time: 8.0497 data: 7.9141 max mem: 8233 +Train: [84] [ 100/6250] eta: 0:24:52 lr: 0.000009 grad: 0.1557 (0.1891) loss: 0.8747 (0.8646) time: 0.1710 data: 0.0624 max mem: 8233 +Train: [84] [ 200/6250] eta: 0:21:29 lr: 0.000009 grad: 0.1438 (0.1767) loss: 0.8725 (0.8683) time: 0.1615 data: 0.0512 max mem: 8233 +Train: [84] [ 300/6250] eta: 0:20:12 lr: 0.000008 grad: 0.1442 (0.1703) loss: 0.8746 (0.8700) time: 0.1633 data: 0.0587 max mem: 8233 +Train: [84] [ 400/6250] eta: 0:19:03 lr: 0.000008 grad: 0.1614 (0.1668) loss: 0.8744 (0.8715) time: 0.1625 data: 0.0553 max mem: 8233 +Train: [84] [ 500/6250] eta: 0:18:17 lr: 0.000008 grad: 0.1495 (0.1637) loss: 0.8738 (0.8727) time: 0.1589 data: 0.0575 max mem: 8233 +Train: [84] [ 600/6250] eta: 0:17:42 lr: 0.000008 grad: 0.1588 (0.1633) loss: 0.8790 (0.8735) time: 0.1826 data: 0.0784 max mem: 8233 +Train: [84] [ 700/6250] eta: 0:17:09 lr: 0.000008 grad: 0.1438 (0.1624) loss: 0.8741 (0.8737) time: 0.1831 data: 0.1014 max mem: 8233 +Train: [84] [ 800/6250] eta: 0:16:37 lr: 0.000008 grad: 0.1445 (0.1617) loss: 0.8813 (0.8744) time: 0.1391 data: 0.0388 max mem: 8233 +Train: [84] [ 900/6250] eta: 0:16:16 lr: 0.000008 grad: 0.1449 (0.1608) loss: 0.8817 (0.8748) time: 0.1428 data: 0.0420 max mem: 8233 +Train: [84] [1000/6250] eta: 0:16:07 lr: 0.000008 grad: 0.1503 (0.1604) loss: 0.8793 (0.8754) time: 0.2984 data: 0.2047 max mem: 8233 +Train: [84] [1100/6250] eta: 0:15:31 lr: 0.000008 grad: 0.1414 (0.1600) loss: 0.8799 (0.8759) time: 0.1578 data: 0.0817 max mem: 8233 +Train: [84] [1200/6250] eta: 0:15:06 lr: 0.000008 grad: 0.1568 (0.1601) loss: 0.8793 (0.8761) time: 0.1649 data: 0.0758 max mem: 8233 +Train: [84] [1300/6250] eta: 0:14:41 lr: 0.000008 grad: 0.1513 (0.1597) loss: 0.8743 (0.8760) time: 0.1819 data: 0.0928 max mem: 8233 +Train: [84] [1400/6250] eta: 0:14:16 lr: 0.000008 grad: 0.1554 (0.1596) loss: 0.8770 (0.8759) time: 0.1569 data: 0.0872 max mem: 8233 +Train: [84] [1500/6250] eta: 0:13:51 lr: 0.000008 grad: 0.1559 (0.1594) loss: 0.8682 (0.8759) time: 0.1383 data: 0.0541 max mem: 8233 +Train: [84] [1600/6250] eta: 0:13:30 lr: 0.000008 grad: 0.1490 (0.1592) loss: 0.8764 (0.8759) time: 0.1770 data: 0.0952 max mem: 8233 +Train: [84] [1700/6250] eta: 0:13:07 lr: 0.000008 grad: 0.1429 (0.1589) loss: 0.8834 (0.8759) time: 0.1436 data: 0.0526 max mem: 8233 +Train: [84] [1800/6250] eta: 0:12:46 lr: 0.000008 grad: 0.1567 (0.1587) loss: 0.8759 (0.8759) time: 0.1641 data: 0.0807 max mem: 8233 +Train: [84] [1900/6250] eta: 0:12:27 lr: 0.000008 grad: 0.1631 (0.1586) loss: 0.8781 (0.8759) time: 0.1630 data: 0.0742 max mem: 8233 +Train: [84] [2000/6250] eta: 0:12:08 lr: 0.000008 grad: 0.1609 (0.1588) loss: 0.8779 (0.8760) time: 0.1017 data: 0.0149 max mem: 8233 +Train: [84] [2100/6250] eta: 0:12:00 lr: 0.000008 grad: 0.1446 (0.1588) loss: 0.8756 (0.8760) time: 0.0884 data: 0.0002 max mem: 8233 +Train: [84] [2200/6250] eta: 0:11:51 lr: 0.000008 grad: 0.1467 (0.1587) loss: 0.8819 (0.8761) time: 0.2167 data: 0.1243 max mem: 8233 +Train: [84] [2300/6250] eta: 0:11:31 lr: 0.000008 grad: 0.1587 (0.1589) loss: 0.8780 (0.8761) time: 0.1863 data: 0.0966 max mem: 8233 +Train: [84] [2400/6250] eta: 0:11:12 lr: 0.000008 grad: 0.1533 (0.1590) loss: 0.8768 (0.8761) time: 0.1727 data: 0.0846 max mem: 8233 +Train: [84] [2500/6250] eta: 0:10:56 lr: 0.000008 grad: 0.1552 (0.1590) loss: 0.8789 (0.8763) time: 0.2390 data: 0.1381 max mem: 8233 +Train: [84] [2600/6250] eta: 0:10:35 lr: 0.000008 grad: 0.1476 (0.1590) loss: 0.8809 (0.8764) time: 0.1664 data: 0.0789 max mem: 8233 +Train: [84] [2700/6250] eta: 0:10:19 lr: 0.000008 grad: 0.1463 (0.1589) loss: 0.8827 (0.8764) time: 0.2475 data: 0.1804 max mem: 8233 +Train: [84] [2800/6250] eta: 0:09:58 lr: 0.000008 grad: 0.1614 (0.1590) loss: 0.8771 (0.8764) time: 0.1349 data: 0.0712 max mem: 8233 +Train: [84] [2900/6250] eta: 0:09:40 lr: 0.000008 grad: 0.1520 (0.1590) loss: 0.8724 (0.8764) time: 0.1612 data: 0.0876 max mem: 8233 +Train: [84] [3000/6250] eta: 0:09:21 lr: 0.000008 grad: 0.1463 (0.1590) loss: 0.8747 (0.8764) time: 0.1663 data: 0.0796 max mem: 8233 +Train: [84] [3100/6250] eta: 0:09:04 lr: 0.000008 grad: 0.1566 (0.1589) loss: 0.8779 (0.8764) time: 0.1781 data: 0.0940 max mem: 8233 +Train: [84] [3200/6250] eta: 0:08:49 lr: 0.000008 grad: 0.1469 (0.1590) loss: 0.8743 (0.8764) time: 0.1814 data: 0.1003 max mem: 8233 +Train: [84] [3300/6250] eta: 0:08:32 lr: 0.000008 grad: 0.1564 (0.1589) loss: 0.8797 (0.8764) time: 0.1932 data: 0.1102 max mem: 8233 +Train: [84] [3400/6250] eta: 0:08:15 lr: 0.000008 grad: 0.1633 (0.1589) loss: 0.8799 (0.8765) time: 0.1602 data: 0.0851 max mem: 8233 +Train: [84] [3500/6250] eta: 0:07:57 lr: 0.000008 grad: 0.1539 (0.1591) loss: 0.8839 (0.8765) time: 0.1588 data: 0.0809 max mem: 8233 +Train: [84] [3600/6250] eta: 0:07:40 lr: 0.000008 grad: 0.1519 (0.1591) loss: 0.8779 (0.8764) time: 0.1790 data: 0.0806 max mem: 8233 +Train: [84] [3700/6250] eta: 0:07:22 lr: 0.000008 grad: 0.1501 (0.1592) loss: 0.8803 (0.8764) time: 0.1660 data: 0.0681 max mem: 8233 +Train: [84] [3800/6250] eta: 0:07:04 lr: 0.000008 grad: 0.1537 (0.1592) loss: 0.8758 (0.8764) time: 0.1605 data: 0.0741 max mem: 8233 +Train: [84] [3900/6250] eta: 0:06:46 lr: 0.000008 grad: 0.1426 (0.1593) loss: 0.8755 (0.8763) time: 0.1670 data: 0.0686 max mem: 8233 +Train: [84] [4000/6250] eta: 0:06:28 lr: 0.000008 grad: 0.1549 (0.1593) loss: 0.8736 (0.8762) time: 0.1603 data: 0.0815 max mem: 8233 +Train: [84] [4100/6250] eta: 0:06:10 lr: 0.000008 grad: 0.1547 (0.1593) loss: 0.8808 (0.8762) time: 0.1643 data: 0.0847 max mem: 8233 +Train: [84] [4200/6250] eta: 0:05:52 lr: 0.000008 grad: 0.1588 (0.1594) loss: 0.8761 (0.8762) time: 0.1449 data: 0.0570 max mem: 8233 +Train: [84] [4300/6250] eta: 0:05:34 lr: 0.000008 grad: 0.1548 (0.1595) loss: 0.8732 (0.8762) time: 0.1858 data: 0.1092 max mem: 8233 +Train: [84] [4400/6250] eta: 0:05:18 lr: 0.000008 grad: 0.1479 (0.1596) loss: 0.8792 (0.8762) time: 0.2628 data: 0.1816 max mem: 8233 +Train: [84] [4500/6250] eta: 0:05:00 lr: 0.000008 grad: 0.1480 (0.1596) loss: 0.8810 (0.8763) time: 0.1578 data: 0.0758 max mem: 8233 +Train: [84] [4600/6250] eta: 0:04:43 lr: 0.000008 grad: 0.1506 (0.1594) loss: 0.8776 (0.8763) time: 0.2070 data: 0.1140 max mem: 8233 +Train: [84] [4700/6250] eta: 0:04:25 lr: 0.000008 grad: 0.1580 (0.1593) loss: 0.8747 (0.8763) time: 0.1645 data: 0.0931 max mem: 8233 +Train: [84] [4800/6250] eta: 0:04:08 lr: 0.000008 grad: 0.1539 (0.1592) loss: 0.8783 (0.8764) time: 0.2025 data: 0.1216 max mem: 8233 +Train: [84] [4900/6250] eta: 0:03:50 lr: 0.000008 grad: 0.1515 (0.1591) loss: 0.8812 (0.8764) time: 0.1332 data: 0.0426 max mem: 8233 +Train: [84] [5000/6250] eta: 0:03:32 lr: 0.000008 grad: 0.1476 (0.1591) loss: 0.8745 (0.8764) time: 0.1715 data: 0.0929 max mem: 8233 +Train: [84] [5100/6250] eta: 0:03:15 lr: 0.000008 grad: 0.1475 (0.1590) loss: 0.8775 (0.8764) time: 0.1183 data: 0.0359 max mem: 8233 +Train: [84] [5200/6250] eta: 0:02:58 lr: 0.000008 grad: 0.1507 (0.1590) loss: 0.8823 (0.8765) time: 0.1473 data: 0.0613 max mem: 8233 +Train: [84] [5300/6250] eta: 0:02:40 lr: 0.000008 grad: 0.1488 (0.1590) loss: 0.8835 (0.8765) time: 0.1525 data: 0.0617 max mem: 8233 +Train: [84] [5400/6250] eta: 0:02:23 lr: 0.000008 grad: 0.1484 (0.1590) loss: 0.8784 (0.8765) time: 0.1415 data: 0.0550 max mem: 8233 +Train: [84] [5500/6250] eta: 0:02:06 lr: 0.000008 grad: 0.1447 (0.1589) loss: 0.8815 (0.8765) time: 0.1715 data: 0.0991 max mem: 8233 +Train: [84] [5600/6250] eta: 0:01:49 lr: 0.000008 grad: 0.1528 (0.1588) loss: 0.8759 (0.8766) time: 0.1544 data: 0.0698 max mem: 8233 +Train: [84] [5700/6250] eta: 0:01:33 lr: 0.000008 grad: 0.1493 (0.1588) loss: 0.8793 (0.8766) time: 0.3891 data: 0.3256 max mem: 8233 +Train: [84] [5800/6250] eta: 0:01:16 lr: 0.000008 grad: 0.1467 (0.1587) loss: 0.8745 (0.8766) time: 0.1600 data: 0.0867 max mem: 8233 +Train: [84] [5900/6250] eta: 0:00:59 lr: 0.000008 grad: 0.1520 (0.1587) loss: 0.8779 (0.8765) time: 0.1589 data: 0.0840 max mem: 8233 +Train: [84] [6000/6250] eta: 0:00:42 lr: 0.000008 grad: 0.1630 (0.1588) loss: 0.8788 (0.8766) time: 0.1900 data: 0.1230 max mem: 8233 +Train: [84] [6100/6250] eta: 0:00:25 lr: 0.000008 grad: 0.1534 (0.1587) loss: 0.8766 (0.8766) time: 0.1656 data: 0.0774 max mem: 8233 +Train: [84] [6200/6250] eta: 0:00:08 lr: 0.000008 grad: 0.1625 (0.1589) loss: 0.8719 (0.8766) time: 0.1645 data: 0.0891 max mem: 8233 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1530 (0.1589) loss: 0.8741 (0.8766) time: 0.1767 data: 0.0871 max mem: 8233 +Train: [84] Total time: 0:17:50 (0.1713 s / it) +Averaged stats: lr: 0.000008 grad: 0.1530 (0.1589) loss: 0.8741 (0.8766) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:07:22 loss: 0.8912 (0.8912) time: 7.1386 data: 7.1111 max mem: 8233 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8823 (0.8827) time: 0.1318 data: 0.1110 max mem: 8233 +Eval (hcp-train-subset): [84] Total time: 0:00:16 (0.2644 s / it) +Averaged stats (hcp-train-subset): loss: 0.8823 (0.8827) +Making plots (hcp-train-subset): example=9 +Eval (hcp-val): [84] [ 0/62] eta: 0:04:55 loss: 0.8803 (0.8803) time: 4.7626 data: 4.6599 max mem: 8233 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8800 (0.8825) time: 0.1483 data: 0.1273 max mem: 8233 +Eval (hcp-val): [84] Total time: 0:00:16 (0.2603 s / it) +Averaged stats (hcp-val): loss: 0.8800 (0.8825) +Making plots (hcp-val): example=39 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 10:48:54 lr: 0.000008 grad: 0.2887 (0.2887) loss: 0.9110 (0.9110) time: 6.2295 data: 5.9341 max mem: 8233 +Train: [85] [ 100/6250] eta: 0:24:48 lr: 0.000008 grad: 0.1640 (0.1771) loss: 0.8776 (0.8788) time: 0.1773 data: 0.0575 max mem: 8233 +Train: [85] [ 200/6250] eta: 0:21:05 lr: 0.000008 grad: 0.1579 (0.1719) loss: 0.8840 (0.8799) time: 0.1664 data: 0.0521 max mem: 8233 +Train: [85] [ 300/6250] eta: 0:19:06 lr: 0.000007 grad: 0.1528 (0.1715) loss: 0.8759 (0.8778) time: 0.1484 data: 0.0321 max mem: 8233 +Train: [85] [ 400/6250] eta: 0:17:58 lr: 0.000007 grad: 0.1562 (0.1691) loss: 0.8719 (0.8764) time: 0.1517 data: 0.0447 max mem: 8233 +Train: [85] [ 500/6250] eta: 0:17:08 lr: 0.000007 grad: 0.1538 (0.1681) loss: 0.8700 (0.8761) time: 0.1684 data: 0.0748 max mem: 8233 +Train: [85] [ 600/6250] eta: 0:16:35 lr: 0.000007 grad: 0.1567 (0.1675) loss: 0.8741 (0.8761) time: 0.1625 data: 0.0650 max mem: 8233 +Train: [85] [ 700/6250] eta: 0:16:00 lr: 0.000007 grad: 0.1527 (0.1664) loss: 0.8731 (0.8758) time: 0.1478 data: 0.0555 max mem: 8233 +Train: [85] [ 800/6250] eta: 0:15:35 lr: 0.000007 grad: 0.1501 (0.1655) loss: 0.8740 (0.8753) time: 0.1408 data: 0.0511 max mem: 8233 +Train: [85] [ 900/6250] eta: 0:15:16 lr: 0.000007 grad: 0.1425 (0.1647) loss: 0.8753 (0.8751) time: 0.1854 data: 0.0911 max mem: 8233 +Train: [85] [1000/6250] eta: 0:15:04 lr: 0.000007 grad: 0.1448 (0.1637) loss: 0.8779 (0.8751) time: 0.1197 data: 0.0004 max mem: 8233 +Train: [85] [1100/6250] eta: 0:14:47 lr: 0.000007 grad: 0.1561 (0.1628) loss: 0.8692 (0.8750) time: 0.1079 data: 0.0280 max mem: 8233 +Train: [85] [1200/6250] eta: 0:14:34 lr: 0.000007 grad: 0.1533 (0.1623) loss: 0.8739 (0.8749) time: 0.1853 data: 0.0929 max mem: 8233 +Train: [85] [1300/6250] eta: 0:14:12 lr: 0.000007 grad: 0.1523 (0.1616) loss: 0.8759 (0.8749) time: 0.1640 data: 0.0888 max mem: 8233 +Train: [85] [1400/6250] eta: 0:13:50 lr: 0.000007 grad: 0.1556 (0.1610) loss: 0.8779 (0.8749) time: 0.1350 data: 0.0486 max mem: 8233 +Train: [85] [1500/6250] eta: 0:13:29 lr: 0.000007 grad: 0.1570 (0.1606) loss: 0.8758 (0.8749) time: 0.1513 data: 0.0670 max mem: 8233 +Train: [85] [1600/6250] eta: 0:13:11 lr: 0.000007 grad: 0.1510 (0.1601) loss: 0.8731 (0.8749) time: 0.1602 data: 0.0793 max mem: 8233 +Train: [85] [1700/6250] eta: 0:12:51 lr: 0.000007 grad: 0.1466 (0.1600) loss: 0.8771 (0.8749) time: 0.1731 data: 0.0881 max mem: 8233 +Train: [85] [1800/6250] eta: 0:12:31 lr: 0.000007 grad: 0.1472 (0.1598) loss: 0.8754 (0.8749) time: 0.1478 data: 0.0538 max mem: 8233 +Train: [85] [1900/6250] eta: 0:12:11 lr: 0.000007 grad: 0.1600 (0.1596) loss: 0.8751 (0.8749) time: 0.1446 data: 0.0712 max mem: 8233 +Train: [85] [2000/6250] eta: 0:11:54 lr: 0.000007 grad: 0.1436 (0.1594) loss: 0.8773 (0.8748) time: 0.1893 data: 0.1040 max mem: 8233 +Train: [85] [2100/6250] eta: 0:11:34 lr: 0.000007 grad: 0.1512 (0.1593) loss: 0.8777 (0.8749) time: 0.1569 data: 0.0698 max mem: 8233 +Train: [85] [2200/6250] eta: 0:11:16 lr: 0.000007 grad: 0.1503 (0.1595) loss: 0.8774 (0.8749) time: 0.1512 data: 0.0750 max mem: 8233 +Train: [85] [2300/6250] eta: 0:10:57 lr: 0.000007 grad: 0.1580 (0.1594) loss: 0.8675 (0.8749) time: 0.1564 data: 0.0814 max mem: 8233 +Train: [85] [2400/6250] eta: 0:10:39 lr: 0.000007 grad: 0.1467 (0.1593) loss: 0.8748 (0.8749) time: 0.1683 data: 0.0906 max mem: 8233 +Train: [85] [2500/6250] eta: 0:10:26 lr: 0.000007 grad: 0.1374 (0.1591) loss: 0.8798 (0.8750) time: 0.3305 data: 0.2280 max mem: 8233 +Train: [85] [2600/6250] eta: 0:10:07 lr: 0.000007 grad: 0.1444 (0.1589) loss: 0.8768 (0.8751) time: 0.1674 data: 0.0862 max mem: 8233 +Train: [85] [2700/6250] eta: 0:09:51 lr: 0.000007 grad: 0.1520 (0.1588) loss: 0.8776 (0.8751) time: 0.2138 data: 0.1462 max mem: 8233 +Train: [85] [2800/6250] eta: 0:09:34 lr: 0.000007 grad: 0.1439 (0.1586) loss: 0.8774 (0.8752) time: 0.1612 data: 0.0947 max mem: 8233 +Train: [85] [2900/6250] eta: 0:09:18 lr: 0.000007 grad: 0.1474 (0.1585) loss: 0.8751 (0.8753) time: 0.1588 data: 0.0897 max mem: 8233 +Train: [85] [3000/6250] eta: 0:09:02 lr: 0.000007 grad: 0.1494 (0.1585) loss: 0.8785 (0.8753) time: 0.1795 data: 0.1055 max mem: 8233 +Train: [85] [3100/6250] eta: 0:08:46 lr: 0.000007 grad: 0.1476 (0.1583) loss: 0.8811 (0.8754) time: 0.1686 data: 0.0782 max mem: 8233 +Train: [85] [3200/6250] eta: 0:08:31 lr: 0.000007 grad: 0.1442 (0.1581) loss: 0.8753 (0.8754) time: 0.1827 data: 0.0997 max mem: 8233 +Train: [85] [3300/6250] eta: 0:08:16 lr: 0.000007 grad: 0.1604 (0.1581) loss: 0.8725 (0.8754) time: 0.1615 data: 0.0790 max mem: 8233 +Train: [85] [3400/6250] eta: 0:08:00 lr: 0.000007 grad: 0.1628 (0.1581) loss: 0.8698 (0.8754) time: 0.1872 data: 0.1070 max mem: 8233 +Train: [85] [3500/6250] eta: 0:07:43 lr: 0.000007 grad: 0.1626 (0.1581) loss: 0.8762 (0.8754) time: 0.1902 data: 0.1126 max mem: 8233 +Train: [85] [3600/6250] eta: 0:07:26 lr: 0.000007 grad: 0.1541 (0.1581) loss: 0.8786 (0.8755) time: 0.1512 data: 0.0643 max mem: 8233 +Train: [85] [3700/6250] eta: 0:07:09 lr: 0.000007 grad: 0.1467 (0.1580) loss: 0.8795 (0.8755) time: 0.1651 data: 0.0728 max mem: 8233 +Train: [85] [3800/6250] eta: 0:06:51 lr: 0.000007 grad: 0.1500 (0.1580) loss: 0.8726 (0.8756) time: 0.1601 data: 0.0626 max mem: 8233 +Train: [85] [3900/6250] eta: 0:06:34 lr: 0.000007 grad: 0.1471 (0.1580) loss: 0.8783 (0.8756) time: 0.1477 data: 0.0559 max mem: 8233 +Train: [85] [4000/6250] eta: 0:06:17 lr: 0.000007 grad: 0.1461 (0.1580) loss: 0.8802 (0.8756) time: 0.1595 data: 0.0774 max mem: 8233 +Train: [85] [4100/6250] eta: 0:05:59 lr: 0.000007 grad: 0.1454 (0.1578) loss: 0.8781 (0.8757) time: 0.1460 data: 0.0675 max mem: 8233 +Train: [85] [4200/6250] eta: 0:05:42 lr: 0.000007 grad: 0.1488 (0.1577) loss: 0.8758 (0.8757) time: 0.1698 data: 0.0897 max mem: 8233 +Train: [85] [4300/6250] eta: 0:05:26 lr: 0.000007 grad: 0.1494 (0.1577) loss: 0.8759 (0.8758) time: 0.1751 data: 0.0992 max mem: 8233 +Train: [85] [4400/6250] eta: 0:05:09 lr: 0.000007 grad: 0.1486 (0.1577) loss: 0.8780 (0.8758) time: 0.1582 data: 0.0750 max mem: 8233 +Train: [85] [4500/6250] eta: 0:04:52 lr: 0.000007 grad: 0.1555 (0.1576) loss: 0.8741 (0.8758) time: 0.1587 data: 0.0760 max mem: 8233 +Train: [85] [4600/6250] eta: 0:04:36 lr: 0.000007 grad: 0.1508 (0.1577) loss: 0.8731 (0.8758) time: 0.2905 data: 0.2092 max mem: 8233 +Train: [85] [4700/6250] eta: 0:04:18 lr: 0.000007 grad: 0.1521 (0.1577) loss: 0.8747 (0.8758) time: 0.1820 data: 0.1096 max mem: 8233 +Train: [85] [4800/6250] eta: 0:04:02 lr: 0.000007 grad: 0.1498 (0.1576) loss: 0.8788 (0.8759) time: 0.2995 data: 0.2168 max mem: 8233 +Train: [85] [4900/6250] eta: 0:03:45 lr: 0.000007 grad: 0.1432 (0.1575) loss: 0.8754 (0.8759) time: 0.2698 data: 0.1848 max mem: 8233 +Train: [85] [5000/6250] eta: 0:03:29 lr: 0.000007 grad: 0.1523 (0.1574) loss: 0.8781 (0.8760) time: 0.1354 data: 0.0323 max mem: 8233 +Train: [85] [5100/6250] eta: 0:03:12 lr: 0.000007 grad: 0.1594 (0.1575) loss: 0.8748 (0.8760) time: 0.1592 data: 0.0826 max mem: 8233 +Train: [85] [5200/6250] eta: 0:02:56 lr: 0.000007 grad: 0.1624 (0.1575) loss: 0.8717 (0.8759) time: 0.1340 data: 0.0003 max mem: 8233 +Train: [85] [5300/6250] eta: 0:02:39 lr: 0.000007 grad: 0.1470 (0.1576) loss: 0.8799 (0.8760) time: 0.1665 data: 0.0847 max mem: 8233 +Train: [85] [5400/6250] eta: 0:02:22 lr: 0.000007 grad: 0.1499 (0.1575) loss: 0.8762 (0.8760) time: 0.1276 data: 0.0411 max mem: 8233 +Train: [85] [5500/6250] eta: 0:02:05 lr: 0.000007 grad: 0.1497 (0.1575) loss: 0.8823 (0.8760) time: 0.1660 data: 0.0870 max mem: 8233 +Train: [85] [5600/6250] eta: 0:01:48 lr: 0.000007 grad: 0.1482 (0.1574) loss: 0.8721 (0.8760) time: 0.1777 data: 0.0970 max mem: 8233 +Train: [85] [5700/6250] eta: 0:01:31 lr: 0.000007 grad: 0.1550 (0.1574) loss: 0.8787 (0.8760) time: 0.1385 data: 0.0680 max mem: 8233 +Train: [85] [5800/6250] eta: 0:01:15 lr: 0.000007 grad: 0.1615 (0.1574) loss: 0.8799 (0.8760) time: 0.1481 data: 0.0723 max mem: 8233 +Train: [85] [5900/6250] eta: 0:00:58 lr: 0.000007 grad: 0.1519 (0.1575) loss: 0.8770 (0.8760) time: 0.1534 data: 0.0686 max mem: 8233 +Train: [85] [6000/6250] eta: 0:00:41 lr: 0.000007 grad: 0.1633 (0.1575) loss: 0.8763 (0.8760) time: 0.1713 data: 0.0926 max mem: 8233 +Train: [85] [6100/6250] eta: 0:00:25 lr: 0.000007 grad: 0.1576 (0.1576) loss: 0.8702 (0.8760) time: 0.1451 data: 0.0552 max mem: 8233 +Train: [85] [6200/6250] eta: 0:00:08 lr: 0.000007 grad: 0.1543 (0.1576) loss: 0.8744 (0.8760) time: 0.1672 data: 0.0805 max mem: 8233 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1484 (0.1576) loss: 0.8776 (0.8760) time: 0.1681 data: 0.0856 max mem: 8233 +Train: [85] Total time: 0:17:30 (0.1681 s / it) +Averaged stats: lr: 0.000007 grad: 0.1484 (0.1576) loss: 0.8776 (0.8760) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:06:09 loss: 0.8931 (0.8931) time: 5.9517 data: 5.9251 max mem: 8233 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8807 (0.8818) time: 0.1346 data: 0.1138 max mem: 8233 +Eval (hcp-train-subset): [85] Total time: 0:00:14 (0.2398 s / it) +Averaged stats (hcp-train-subset): loss: 0.8807 (0.8818) +Eval (hcp-val): [85] [ 0/62] eta: 0:05:10 loss: 0.8786 (0.8786) time: 5.0035 data: 4.9253 max mem: 8233 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8809 (0.8816) time: 0.1262 data: 0.1043 max mem: 8233 +Eval (hcp-val): [85] Total time: 0:00:14 (0.2384 s / it) +Averaged stats (hcp-val): loss: 0.8809 (0.8816) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 12:16:17 lr: 0.000007 grad: 0.2193 (0.2193) loss: 0.8519 (0.8519) time: 7.0683 data: 6.9612 max mem: 8233 +Train: [86] [ 100/6250] eta: 0:22:45 lr: 0.000007 grad: 0.1436 (0.1532) loss: 0.8824 (0.8820) time: 0.1821 data: 0.0717 max mem: 8233 +Train: [86] [ 200/6250] eta: 0:20:12 lr: 0.000007 grad: 0.1330 (0.1479) loss: 0.8855 (0.8833) time: 0.1769 data: 0.0559 max mem: 8233 +Train: [86] [ 300/6250] eta: 0:19:00 lr: 0.000007 grad: 0.1512 (0.1484) loss: 0.8773 (0.8830) time: 0.1733 data: 0.0647 max mem: 8233 +Train: [86] [ 400/6250] eta: 0:18:27 lr: 0.000007 grad: 0.1422 (0.1489) loss: 0.8847 (0.8835) time: 0.2167 data: 0.1126 max mem: 8233 +Train: [86] [ 500/6250] eta: 0:17:40 lr: 0.000007 grad: 0.1487 (0.1493) loss: 0.8793 (0.8833) time: 0.1869 data: 0.1012 max mem: 8233 +Train: [86] [ 600/6250] eta: 0:17:03 lr: 0.000006 grad: 0.1410 (0.1488) loss: 0.8869 (0.8837) time: 0.1711 data: 0.0885 max mem: 8233 +Train: [86] [ 700/6250] eta: 0:16:45 lr: 0.000006 grad: 0.1424 (0.1494) loss: 0.8817 (0.8839) time: 0.1457 data: 0.0342 max mem: 8233 +Train: [86] [ 800/6250] eta: 0:16:16 lr: 0.000006 grad: 0.1507 (0.1494) loss: 0.8801 (0.8836) time: 0.1486 data: 0.0584 max mem: 8233 +Train: [86] [ 900/6250] eta: 0:16:06 lr: 0.000006 grad: 0.1451 (0.1497) loss: 0.8793 (0.8831) time: 0.1917 data: 0.0657 max mem: 8233 +Train: [86] [1000/6250] eta: 0:15:40 lr: 0.000006 grad: 0.1456 (0.1500) loss: 0.8767 (0.8827) time: 0.1800 data: 0.0897 max mem: 8233 +Train: [86] [1100/6250] eta: 0:15:11 lr: 0.000006 grad: 0.1558 (0.1510) loss: 0.8719 (0.8822) time: 0.1638 data: 0.0817 max mem: 8233 +Train: [86] [1200/6250] eta: 0:14:42 lr: 0.000006 grad: 0.1546 (0.1518) loss: 0.8711 (0.8818) time: 0.1523 data: 0.0662 max mem: 8233 +Train: [86] [1300/6250] eta: 0:14:20 lr: 0.000006 grad: 0.1551 (0.1524) loss: 0.8725 (0.8813) time: 0.1686 data: 0.0916 max mem: 8233 +Train: [86] [1400/6250] eta: 0:14:02 lr: 0.000006 grad: 0.1502 (0.1523) loss: 0.8793 (0.8811) time: 0.2180 data: 0.1277 max mem: 8233 +Train: [86] [1500/6250] eta: 0:13:36 lr: 0.000006 grad: 0.1518 (0.1528) loss: 0.8790 (0.8809) time: 0.1406 data: 0.0495 max mem: 8233 +Train: [86] [1600/6250] eta: 0:13:16 lr: 0.000006 grad: 0.1420 (0.1531) loss: 0.8805 (0.8807) time: 0.1861 data: 0.0968 max mem: 8233 +Train: [86] [1700/6250] eta: 0:12:59 lr: 0.000006 grad: 0.1489 (0.1533) loss: 0.8783 (0.8805) time: 0.1977 data: 0.1266 max mem: 8233 +Train: [86] [1800/6250] eta: 0:12:39 lr: 0.000006 grad: 0.1549 (0.1536) loss: 0.8768 (0.8804) time: 0.1518 data: 0.0689 max mem: 8233 +Train: [86] [1900/6250] eta: 0:12:17 lr: 0.000006 grad: 0.1452 (0.1536) loss: 0.8781 (0.8803) time: 0.1315 data: 0.0362 max mem: 8233 +Train: [86] [2000/6250] eta: 0:11:58 lr: 0.000006 grad: 0.1557 (0.1538) loss: 0.8799 (0.8802) time: 0.1743 data: 0.0886 max mem: 8233 +Train: [86] [2100/6250] eta: 0:11:38 lr: 0.000006 grad: 0.1507 (0.1540) loss: 0.8776 (0.8801) time: 0.1440 data: 0.0533 max mem: 8233 +Train: [86] [2200/6250] eta: 0:11:25 lr: 0.000006 grad: 0.1562 (0.1542) loss: 0.8777 (0.8800) time: 0.2812 data: 0.2058 max mem: 8233 +Train: [86] [2300/6250] eta: 0:11:05 lr: 0.000006 grad: 0.1498 (0.1542) loss: 0.8797 (0.8801) time: 0.1413 data: 0.0474 max mem: 8233 +Train: [86] [2400/6250] eta: 0:10:47 lr: 0.000006 grad: 0.1574 (0.1543) loss: 0.8800 (0.8800) time: 0.1665 data: 0.0799 max mem: 8233 +Train: [86] [2500/6250] eta: 0:10:29 lr: 0.000006 grad: 0.1545 (0.1545) loss: 0.8775 (0.8800) time: 0.1425 data: 0.0612 max mem: 8233 +Train: [86] [2600/6250] eta: 0:10:11 lr: 0.000006 grad: 0.1536 (0.1545) loss: 0.8760 (0.8799) time: 0.1636 data: 0.0870 max mem: 8233 +Train: [86] [2700/6250] eta: 0:09:57 lr: 0.000006 grad: 0.1551 (0.1544) loss: 0.8823 (0.8799) time: 0.2365 data: 0.1627 max mem: 8233 +Train: [86] [2800/6250] eta: 0:09:38 lr: 0.000006 grad: 0.1550 (0.1546) loss: 0.8789 (0.8798) time: 0.1540 data: 0.0808 max mem: 8233 +Train: [86] [2900/6250] eta: 0:09:21 lr: 0.000006 grad: 0.1554 (0.1547) loss: 0.8804 (0.8798) time: 0.1521 data: 0.0941 max mem: 8233 +Train: [86] [3000/6250] eta: 0:09:05 lr: 0.000006 grad: 0.1468 (0.1549) loss: 0.8816 (0.8797) time: 0.1717 data: 0.0878 max mem: 8233 +Train: [86] [3100/6250] eta: 0:08:49 lr: 0.000006 grad: 0.1502 (0.1549) loss: 0.8814 (0.8797) time: 0.1627 data: 0.0781 max mem: 8233 +Train: [86] [3200/6250] eta: 0:08:32 lr: 0.000006 grad: 0.1454 (0.1550) loss: 0.8852 (0.8797) time: 0.1771 data: 0.0989 max mem: 8233 +Train: [86] [3300/6250] eta: 0:08:15 lr: 0.000006 grad: 0.1457 (0.1551) loss: 0.8817 (0.8797) time: 0.1668 data: 0.0875 max mem: 8233 +Train: [86] [3400/6250] eta: 0:07:59 lr: 0.000006 grad: 0.1617 (0.1551) loss: 0.8805 (0.8797) time: 0.1794 data: 0.1011 max mem: 8233 +Train: [86] [3500/6250] eta: 0:07:41 lr: 0.000006 grad: 0.1494 (0.1553) loss: 0.8729 (0.8796) time: 0.1739 data: 0.0873 max mem: 8233 +Train: [86] [3600/6250] eta: 0:07:23 lr: 0.000006 grad: 0.1504 (0.1555) loss: 0.8788 (0.8796) time: 0.1339 data: 0.0605 max mem: 8233 +Train: [86] [3700/6250] eta: 0:07:06 lr: 0.000006 grad: 0.1534 (0.1555) loss: 0.8821 (0.8796) time: 0.1651 data: 0.0827 max mem: 8233 +Train: [86] [3800/6250] eta: 0:06:48 lr: 0.000006 grad: 0.1497 (0.1555) loss: 0.8826 (0.8796) time: 0.1421 data: 0.0637 max mem: 8233 +Train: [86] [3900/6250] eta: 0:06:31 lr: 0.000006 grad: 0.1498 (0.1556) loss: 0.8807 (0.8796) time: 0.1585 data: 0.0801 max mem: 8233 +Train: [86] [4000/6250] eta: 0:06:14 lr: 0.000006 grad: 0.1512 (0.1556) loss: 0.8780 (0.8795) time: 0.1598 data: 0.0825 max mem: 8233 +Train: [86] [4100/6250] eta: 0:05:57 lr: 0.000006 grad: 0.1487 (0.1556) loss: 0.8803 (0.8795) time: 0.1803 data: 0.0992 max mem: 8233 +Train: [86] [4200/6250] eta: 0:05:40 lr: 0.000006 grad: 0.1433 (0.1555) loss: 0.8794 (0.8796) time: 0.2032 data: 0.1134 max mem: 8233 +Train: [86] [4300/6250] eta: 0:05:24 lr: 0.000006 grad: 0.1549 (0.1555) loss: 0.8744 (0.8796) time: 0.1789 data: 0.0982 max mem: 8233 +Train: [86] [4400/6250] eta: 0:05:07 lr: 0.000006 grad: 0.1590 (0.1556) loss: 0.8771 (0.8796) time: 0.1242 data: 0.0299 max mem: 8233 +Train: [86] [4500/6250] eta: 0:04:51 lr: 0.000006 grad: 0.1423 (0.1557) loss: 0.8891 (0.8796) time: 0.1710 data: 0.0923 max mem: 8233 +Train: [86] [4600/6250] eta: 0:04:34 lr: 0.000006 grad: 0.1548 (0.1559) loss: 0.8798 (0.8796) time: 0.1603 data: 0.0609 max mem: 8233 +Train: [86] [4700/6250] eta: 0:04:17 lr: 0.000006 grad: 0.1547 (0.1560) loss: 0.8752 (0.8795) time: 0.1534 data: 0.0655 max mem: 8233 +Train: [86] [4800/6250] eta: 0:04:01 lr: 0.000006 grad: 0.1606 (0.1562) loss: 0.8788 (0.8795) time: 0.1735 data: 0.0954 max mem: 8233 +Train: [86] [4900/6250] eta: 0:03:44 lr: 0.000006 grad: 0.1482 (0.1563) loss: 0.8783 (0.8795) time: 0.1615 data: 0.0692 max mem: 8233 +Train: [86] [5000/6250] eta: 0:03:27 lr: 0.000006 grad: 0.1502 (0.1563) loss: 0.8742 (0.8794) time: 0.1469 data: 0.0658 max mem: 8233 +Train: [86] [5100/6250] eta: 0:03:10 lr: 0.000006 grad: 0.1752 (0.1566) loss: 0.8738 (0.8793) time: 0.1616 data: 0.0920 max mem: 8233 +Train: [86] [5200/6250] eta: 0:02:53 lr: 0.000006 grad: 0.1557 (0.1567) loss: 0.8746 (0.8792) time: 0.1512 data: 0.0672 max mem: 8233 +Train: [86] [5300/6250] eta: 0:02:37 lr: 0.000006 grad: 0.1494 (0.1568) loss: 0.8781 (0.8791) time: 0.1474 data: 0.0544 max mem: 8233 +Train: [86] [5400/6250] eta: 0:02:20 lr: 0.000006 grad: 0.1653 (0.1570) loss: 0.8758 (0.8791) time: 0.1612 data: 0.0791 max mem: 8233 +Train: [86] [5500/6250] eta: 0:02:03 lr: 0.000006 grad: 0.1635 (0.1573) loss: 0.8717 (0.8790) time: 0.1786 data: 0.1009 max mem: 8233 +Train: [86] [5600/6250] eta: 0:01:47 lr: 0.000006 grad: 0.1498 (0.1575) loss: 0.8743 (0.8789) time: 0.1533 data: 0.0616 max mem: 8233 +Train: [86] [5700/6250] eta: 0:01:30 lr: 0.000006 grad: 0.1589 (0.1575) loss: 0.8756 (0.8789) time: 0.1572 data: 0.0806 max mem: 8233 +Train: [86] [5800/6250] eta: 0:01:14 lr: 0.000006 grad: 0.1581 (0.1575) loss: 0.8781 (0.8789) time: 0.1335 data: 0.0619 max mem: 8233 +Train: [86] [5900/6250] eta: 0:00:58 lr: 0.000006 grad: 0.1510 (0.1576) loss: 0.8794 (0.8789) time: 0.1886 data: 0.1090 max mem: 8233 +Train: [86] [6000/6250] eta: 0:00:41 lr: 0.000006 grad: 0.1495 (0.1576) loss: 0.8806 (0.8789) time: 0.1547 data: 0.0846 max mem: 8233 +Train: [86] [6100/6250] eta: 0:00:24 lr: 0.000006 grad: 0.1584 (0.1577) loss: 0.8784 (0.8788) time: 0.1753 data: 0.0869 max mem: 8233 +Train: [86] [6200/6250] eta: 0:00:08 lr: 0.000006 grad: 0.1619 (0.1577) loss: 0.8803 (0.8788) time: 0.1656 data: 0.0993 max mem: 8233 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1556 (0.1577) loss: 0.8743 (0.8788) time: 0.1548 data: 0.0594 max mem: 8233 +Train: [86] Total time: 0:17:29 (0.1680 s / it) +Averaged stats: lr: 0.000006 grad: 0.1556 (0.1577) loss: 0.8743 (0.8788) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:07:13 loss: 0.8935 (0.8935) time: 6.9859 data: 6.9584 max mem: 8233 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8834 (0.8825) time: 0.1560 data: 0.1344 max mem: 8233 +Eval (hcp-train-subset): [86] Total time: 0:00:16 (0.2633 s / it) +Averaged stats (hcp-train-subset): loss: 0.8834 (0.8825) +Eval (hcp-val): [86] [ 0/62] eta: 0:05:26 loss: 0.8785 (0.8785) time: 5.2693 data: 5.1710 max mem: 8233 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8800 (0.8817) time: 0.1301 data: 0.1092 max mem: 8233 +Eval (hcp-val): [86] Total time: 0:00:16 (0.2624 s / it) +Averaged stats (hcp-val): loss: 0.8800 (0.8817) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 10:54:20 lr: 0.000006 grad: 0.1055 (0.1055) loss: 0.8872 (0.8872) time: 6.2816 data: 6.0884 max mem: 8233 +Train: [87] [ 100/6250] eta: 0:24:20 lr: 0.000006 grad: 0.1360 (0.1602) loss: 0.8903 (0.8877) time: 0.1751 data: 0.0718 max mem: 8233 +Train: [87] [ 200/6250] eta: 0:20:39 lr: 0.000006 grad: 0.1362 (0.1548) loss: 0.8873 (0.8859) time: 0.1394 data: 0.0291 max mem: 8233 +Train: [87] [ 300/6250] eta: 0:19:07 lr: 0.000006 grad: 0.1514 (0.1551) loss: 0.8804 (0.8848) time: 0.1736 data: 0.0581 max mem: 8233 +Train: [87] [ 400/6250] eta: 0:18:17 lr: 0.000006 grad: 0.1447 (0.1548) loss: 0.8818 (0.8833) time: 0.1675 data: 0.0656 max mem: 8233 +Train: [87] [ 500/6250] eta: 0:17:43 lr: 0.000006 grad: 0.1424 (0.1552) loss: 0.8811 (0.8823) time: 0.1868 data: 0.1077 max mem: 8233 +Train: [87] [ 600/6250] eta: 0:17:20 lr: 0.000006 grad: 0.1563 (0.1561) loss: 0.8788 (0.8819) time: 0.1807 data: 0.0962 max mem: 8233 +Train: [87] [ 700/6250] eta: 0:16:47 lr: 0.000006 grad: 0.1635 (0.1579) loss: 0.8729 (0.8812) time: 0.1819 data: 0.0832 max mem: 8233 +Train: [87] [ 800/6250] eta: 0:16:29 lr: 0.000006 grad: 0.1427 (0.1581) loss: 0.8792 (0.8807) time: 0.2066 data: 0.1172 max mem: 8233 +Train: [87] [ 900/6250] eta: 0:16:27 lr: 0.000006 grad: 0.1574 (0.1585) loss: 0.8798 (0.8803) time: 0.1354 data: 0.0160 max mem: 8233 +Train: [87] [1000/6250] eta: 0:15:59 lr: 0.000006 grad: 0.1550 (0.1587) loss: 0.8752 (0.8800) time: 0.1863 data: 0.1133 max mem: 8233 +Train: [87] [1100/6250] eta: 0:15:34 lr: 0.000006 grad: 0.1496 (0.1590) loss: 0.8802 (0.8795) time: 0.2097 data: 0.1261 max mem: 8233 +Train: [87] [1200/6250] eta: 0:15:15 lr: 0.000006 grad: 0.1513 (0.1592) loss: 0.8753 (0.8792) time: 0.2731 data: 0.1948 max mem: 8233 +Train: [87] [1300/6250] eta: 0:14:43 lr: 0.000006 grad: 0.1532 (0.1591) loss: 0.8783 (0.8790) time: 0.1652 data: 0.0784 max mem: 8233 +Train: [87] [1400/6250] eta: 0:14:18 lr: 0.000005 grad: 0.1503 (0.1593) loss: 0.8733 (0.8785) time: 0.1547 data: 0.0704 max mem: 8233 +Train: [87] [1500/6250] eta: 0:13:51 lr: 0.000005 grad: 0.1468 (0.1595) loss: 0.8781 (0.8783) time: 0.1506 data: 0.0762 max mem: 8233 +Train: [87] [1600/6250] eta: 0:13:31 lr: 0.000005 grad: 0.1516 (0.1595) loss: 0.8724 (0.8780) time: 0.2092 data: 0.1303 max mem: 8233 +Train: [87] [1700/6250] eta: 0:13:06 lr: 0.000005 grad: 0.1545 (0.1594) loss: 0.8799 (0.8779) time: 0.1484 data: 0.0633 max mem: 8233 +Train: [87] [1800/6250] eta: 0:12:53 lr: 0.000005 grad: 0.1588 (0.1594) loss: 0.8744 (0.8778) time: 0.1442 data: 0.0503 max mem: 8233 +Train: [87] [1900/6250] eta: 0:12:30 lr: 0.000005 grad: 0.1568 (0.1591) loss: 0.8755 (0.8777) time: 0.1590 data: 0.0726 max mem: 8233 +Train: [87] [2000/6250] eta: 0:12:10 lr: 0.000005 grad: 0.1516 (0.1591) loss: 0.8759 (0.8776) time: 0.1774 data: 0.0943 max mem: 8233 +Train: [87] [2100/6250] eta: 0:11:50 lr: 0.000005 grad: 0.1576 (0.1588) loss: 0.8701 (0.8775) time: 0.1539 data: 0.0633 max mem: 8233 +Train: [87] [2200/6250] eta: 0:11:32 lr: 0.000005 grad: 0.1509 (0.1586) loss: 0.8709 (0.8774) time: 0.1843 data: 0.1054 max mem: 8233 +Train: [87] [2300/6250] eta: 0:11:12 lr: 0.000005 grad: 0.1530 (0.1584) loss: 0.8775 (0.8774) time: 0.1637 data: 0.0813 max mem: 8233 +Train: [87] [2400/6250] eta: 0:10:55 lr: 0.000005 grad: 0.1468 (0.1583) loss: 0.8754 (0.8773) time: 0.1766 data: 0.1028 max mem: 8233 +Train: [87] [2500/6250] eta: 0:10:36 lr: 0.000005 grad: 0.1531 (0.1581) loss: 0.8763 (0.8773) time: 0.1655 data: 0.0918 max mem: 8233 +Train: [87] [2600/6250] eta: 0:10:17 lr: 0.000005 grad: 0.1440 (0.1579) loss: 0.8754 (0.8772) time: 0.1654 data: 0.0793 max mem: 8233 +Train: [87] [2700/6250] eta: 0:10:00 lr: 0.000005 grad: 0.1498 (0.1578) loss: 0.8813 (0.8773) time: 0.1627 data: 0.0797 max mem: 8233 +Train: [87] [2800/6250] eta: 0:09:43 lr: 0.000005 grad: 0.1520 (0.1578) loss: 0.8747 (0.8773) time: 0.1616 data: 0.0777 max mem: 8233 +Train: [87] [2900/6250] eta: 0:09:25 lr: 0.000005 grad: 0.1471 (0.1577) loss: 0.8821 (0.8773) time: 0.1728 data: 0.0881 max mem: 8233 +Train: [87] [3000/6250] eta: 0:09:08 lr: 0.000005 grad: 0.1499 (0.1578) loss: 0.8782 (0.8773) time: 0.1842 data: 0.1035 max mem: 8233 +Train: [87] [3100/6250] eta: 0:08:51 lr: 0.000005 grad: 0.1608 (0.1578) loss: 0.8746 (0.8772) time: 0.1836 data: 0.1007 max mem: 8233 +Train: [87] [3200/6250] eta: 0:08:35 lr: 0.000005 grad: 0.1528 (0.1580) loss: 0.8733 (0.8771) time: 0.1913 data: 0.1084 max mem: 8233 +Train: [87] [3300/6250] eta: 0:08:16 lr: 0.000005 grad: 0.1538 (0.1581) loss: 0.8765 (0.8771) time: 0.1717 data: 0.0732 max mem: 8233 +Train: [87] [3400/6250] eta: 0:07:59 lr: 0.000005 grad: 0.1562 (0.1584) loss: 0.8743 (0.8770) time: 0.1439 data: 0.0618 max mem: 8233 +Train: [87] [3500/6250] eta: 0:07:43 lr: 0.000005 grad: 0.1569 (0.1585) loss: 0.8734 (0.8770) time: 0.1820 data: 0.1024 max mem: 8233 +Train: [87] [3600/6250] eta: 0:07:26 lr: 0.000005 grad: 0.1569 (0.1588) loss: 0.8789 (0.8770) time: 0.1614 data: 0.0794 max mem: 8233 +Train: [87] [3700/6250] eta: 0:07:08 lr: 0.000005 grad: 0.1565 (0.1590) loss: 0.8769 (0.8770) time: 0.1649 data: 0.0799 max mem: 8233 +Train: [87] [3800/6250] eta: 0:06:51 lr: 0.000005 grad: 0.1566 (0.1591) loss: 0.8732 (0.8769) time: 0.1709 data: 0.0797 max mem: 8233 +Train: [87] [3900/6250] eta: 0:06:33 lr: 0.000005 grad: 0.1591 (0.1594) loss: 0.8750 (0.8769) time: 0.1379 data: 0.0573 max mem: 8233 +Train: [87] [4000/6250] eta: 0:06:16 lr: 0.000005 grad: 0.1562 (0.1595) loss: 0.8696 (0.8767) time: 0.1528 data: 0.0734 max mem: 8233 +Train: [87] [4100/6250] eta: 0:05:59 lr: 0.000005 grad: 0.1624 (0.1599) loss: 0.8685 (0.8766) time: 0.1561 data: 0.0732 max mem: 8233 +Train: [87] [4200/6250] eta: 0:05:41 lr: 0.000005 grad: 0.1629 (0.1601) loss: 0.8729 (0.8765) time: 0.1483 data: 0.0669 max mem: 8233 +Train: [87] [4300/6250] eta: 0:05:24 lr: 0.000005 grad: 0.1554 (0.1603) loss: 0.8815 (0.8765) time: 0.1439 data: 0.0642 max mem: 8233 +Train: [87] [4400/6250] eta: 0:05:08 lr: 0.000005 grad: 0.1663 (0.1605) loss: 0.8708 (0.8765) time: 0.1019 data: 0.0004 max mem: 8233 +Train: [87] [4500/6250] eta: 0:04:51 lr: 0.000005 grad: 0.1595 (0.1607) loss: 0.8701 (0.8764) time: 0.1284 data: 0.0503 max mem: 8233 +Train: [87] [4600/6250] eta: 0:04:35 lr: 0.000005 grad: 0.1592 (0.1608) loss: 0.8783 (0.8764) time: 0.2081 data: 0.1321 max mem: 8233 +Train: [87] [4700/6250] eta: 0:04:19 lr: 0.000005 grad: 0.1588 (0.1609) loss: 0.8744 (0.8764) time: 0.1582 data: 0.0810 max mem: 8233 +Train: [87] [4800/6250] eta: 0:04:02 lr: 0.000005 grad: 0.1588 (0.1610) loss: 0.8785 (0.8764) time: 0.1717 data: 0.0949 max mem: 8233 +Train: [87] [4900/6250] eta: 0:03:45 lr: 0.000005 grad: 0.1645 (0.1611) loss: 0.8803 (0.8764) time: 0.1364 data: 0.0541 max mem: 8233 +Train: [87] [5000/6250] eta: 0:03:28 lr: 0.000005 grad: 0.1504 (0.1613) loss: 0.8752 (0.8764) time: 0.1508 data: 0.0704 max mem: 8233 +Train: [87] [5100/6250] eta: 0:03:11 lr: 0.000005 grad: 0.1594 (0.1614) loss: 0.8799 (0.8764) time: 0.1440 data: 0.0634 max mem: 8233 +Train: [87] [5200/6250] eta: 0:02:54 lr: 0.000005 grad: 0.1482 (0.1615) loss: 0.8763 (0.8764) time: 0.1476 data: 0.0643 max mem: 8233 +Train: [87] [5300/6250] eta: 0:02:38 lr: 0.000005 grad: 0.1579 (0.1616) loss: 0.8736 (0.8763) time: 0.1470 data: 0.0759 max mem: 8233 +Train: [87] [5400/6250] eta: 0:02:21 lr: 0.000005 grad: 0.1716 (0.1617) loss: 0.8674 (0.8762) time: 0.2597 data: 0.1722 max mem: 8233 +Train: [87] [5500/6250] eta: 0:02:04 lr: 0.000005 grad: 0.1535 (0.1618) loss: 0.8738 (0.8762) time: 0.1560 data: 0.0781 max mem: 8233 +Train: [87] [5600/6250] eta: 0:01:48 lr: 0.000005 grad: 0.1619 (0.1618) loss: 0.8743 (0.8761) time: 0.1690 data: 0.0873 max mem: 8233 +Train: [87] [5700/6250] eta: 0:01:31 lr: 0.000005 grad: 0.1480 (0.1618) loss: 0.8740 (0.8761) time: 0.1250 data: 0.0571 max mem: 8233 +Train: [87] [5800/6250] eta: 0:01:14 lr: 0.000005 grad: 0.1585 (0.1618) loss: 0.8753 (0.8761) time: 0.1562 data: 0.0663 max mem: 8233 +Train: [87] [5900/6250] eta: 0:00:58 lr: 0.000005 grad: 0.1480 (0.1617) loss: 0.8766 (0.8761) time: 0.1651 data: 0.0817 max mem: 8233 +Train: [87] [6000/6250] eta: 0:00:41 lr: 0.000005 grad: 0.1546 (0.1617) loss: 0.8746 (0.8761) time: 0.1660 data: 0.0650 max mem: 8233 +Train: [87] [6100/6250] eta: 0:00:25 lr: 0.000005 grad: 0.1544 (0.1618) loss: 0.8770 (0.8760) time: 0.2002 data: 0.1265 max mem: 8233 +Train: [87] [6200/6250] eta: 0:00:08 lr: 0.000005 grad: 0.1593 (0.1618) loss: 0.8718 (0.8760) time: 0.1686 data: 0.0855 max mem: 8233 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1502 (0.1618) loss: 0.8741 (0.8760) time: 0.1775 data: 0.0904 max mem: 8233 +Train: [87] Total time: 0:17:31 (0.1683 s / it) +Averaged stats: lr: 0.000005 grad: 0.1502 (0.1618) loss: 0.8741 (0.8760) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:04:24 loss: 0.8909 (0.8909) time: 4.2666 data: 4.1581 max mem: 8233 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8800 (0.8816) time: 0.1467 data: 0.1259 max mem: 8233 +Eval (hcp-train-subset): [87] Total time: 0:00:16 (0.2629 s / it) +Averaged stats (hcp-train-subset): loss: 0.8800 (0.8816) +Eval (hcp-val): [87] [ 0/62] eta: 0:06:06 loss: 0.8752 (0.8752) time: 5.9070 data: 5.8806 max mem: 8233 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8803 (0.8815) time: 0.1518 data: 0.1304 max mem: 8233 +Eval (hcp-val): [87] Total time: 0:00:15 (0.2497 s / it) +Averaged stats (hcp-val): loss: 0.8803 (0.8815) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 11:01:00 lr: 0.000005 grad: 0.1332 (0.1332) loss: 0.9005 (0.9005) time: 6.3457 data: 6.0370 max mem: 8233 +Train: [88] [ 100/6250] eta: 0:24:36 lr: 0.000005 grad: 0.1593 (0.1641) loss: 0.8828 (0.8809) time: 0.2006 data: 0.1034 max mem: 8233 +Train: [88] [ 200/6250] eta: 0:21:00 lr: 0.000005 grad: 0.1505 (0.1615) loss: 0.8840 (0.8801) time: 0.1725 data: 0.0729 max mem: 8233 +Train: [88] [ 300/6250] eta: 0:19:42 lr: 0.000005 grad: 0.1423 (0.1584) loss: 0.8711 (0.8791) time: 0.1771 data: 0.0841 max mem: 8233 +Train: [88] [ 400/6250] eta: 0:18:31 lr: 0.000005 grad: 0.1531 (0.1572) loss: 0.8760 (0.8784) time: 0.1807 data: 0.0849 max mem: 8233 +Train: [88] [ 500/6250] eta: 0:17:44 lr: 0.000005 grad: 0.1439 (0.1561) loss: 0.8781 (0.8782) time: 0.1739 data: 0.0963 max mem: 8233 +Train: [88] [ 600/6250] eta: 0:17:11 lr: 0.000005 grad: 0.1481 (0.1554) loss: 0.8783 (0.8781) time: 0.1594 data: 0.0417 max mem: 8233 +Train: [88] [ 700/6250] eta: 0:16:42 lr: 0.000005 grad: 0.1420 (0.1547) loss: 0.8783 (0.8778) time: 0.1710 data: 0.0797 max mem: 8233 +Train: [88] [ 800/6250] eta: 0:16:21 lr: 0.000005 grad: 0.1503 (0.1547) loss: 0.8683 (0.8775) time: 0.1943 data: 0.0969 max mem: 8233 +Train: [88] [ 900/6250] eta: 0:15:50 lr: 0.000005 grad: 0.1481 (0.1544) loss: 0.8811 (0.8774) time: 0.1766 data: 0.0906 max mem: 8233 +Train: [88] [1000/6250] eta: 0:15:24 lr: 0.000005 grad: 0.1540 (0.1542) loss: 0.8738 (0.8773) time: 0.1711 data: 0.0917 max mem: 8233 +Train: [88] [1100/6250] eta: 0:15:13 lr: 0.000005 grad: 0.1438 (0.1540) loss: 0.8786 (0.8772) time: 0.1138 data: 0.0003 max mem: 8233 +Train: [88] [1200/6250] eta: 0:14:51 lr: 0.000005 grad: 0.1451 (0.1534) loss: 0.8746 (0.8772) time: 0.1887 data: 0.0862 max mem: 8233 +Train: [88] [1300/6250] eta: 0:14:28 lr: 0.000005 grad: 0.1553 (0.1533) loss: 0.8789 (0.8772) time: 0.1386 data: 0.0465 max mem: 8233 +Train: [88] [1400/6250] eta: 0:14:05 lr: 0.000005 grad: 0.1409 (0.1530) loss: 0.8786 (0.8773) time: 0.1591 data: 0.0712 max mem: 8233 +Train: [88] [1500/6250] eta: 0:13:45 lr: 0.000005 grad: 0.1431 (0.1527) loss: 0.8754 (0.8772) time: 0.1864 data: 0.1089 max mem: 8233 +Train: [88] [1600/6250] eta: 0:13:20 lr: 0.000005 grad: 0.1463 (0.1525) loss: 0.8712 (0.8771) time: 0.1335 data: 0.0344 max mem: 8233 +Train: [88] [1700/6250] eta: 0:12:59 lr: 0.000005 grad: 0.1451 (0.1523) loss: 0.8757 (0.8771) time: 0.1475 data: 0.0626 max mem: 8233 +Train: [88] [1800/6250] eta: 0:12:38 lr: 0.000005 grad: 0.1496 (0.1526) loss: 0.8713 (0.8771) time: 0.1287 data: 0.0404 max mem: 8233 +Train: [88] [1900/6250] eta: 0:12:19 lr: 0.000005 grad: 0.1502 (0.1528) loss: 0.8778 (0.8770) time: 0.1765 data: 0.0859 max mem: 8233 +Train: [88] [2000/6250] eta: 0:11:59 lr: 0.000005 grad: 0.1512 (0.1529) loss: 0.8739 (0.8771) time: 0.1589 data: 0.0772 max mem: 8233 +Train: [88] [2100/6250] eta: 0:11:38 lr: 0.000005 grad: 0.1462 (0.1530) loss: 0.8817 (0.8771) time: 0.1555 data: 0.0717 max mem: 8233 +Train: [88] [2200/6250] eta: 0:11:19 lr: 0.000005 grad: 0.1452 (0.1531) loss: 0.8786 (0.8772) time: 0.1526 data: 0.0617 max mem: 8233 +Train: [88] [2300/6250] eta: 0:10:59 lr: 0.000005 grad: 0.1484 (0.1531) loss: 0.8796 (0.8773) time: 0.1569 data: 0.0756 max mem: 8233 +Train: [88] [2400/6250] eta: 0:10:41 lr: 0.000005 grad: 0.1456 (0.1531) loss: 0.8774 (0.8774) time: 0.1679 data: 0.0859 max mem: 8233 +Train: [88] [2500/6250] eta: 0:10:22 lr: 0.000005 grad: 0.1390 (0.1531) loss: 0.8766 (0.8775) time: 0.1617 data: 0.0784 max mem: 8233 +Train: [88] [2600/6250] eta: 0:10:05 lr: 0.000005 grad: 0.1501 (0.1532) loss: 0.8787 (0.8775) time: 0.1588 data: 0.0738 max mem: 8233 +Train: [88] [2700/6250] eta: 0:09:54 lr: 0.000005 grad: 0.1465 (0.1532) loss: 0.8791 (0.8776) time: 0.2182 data: 0.1455 max mem: 8233 +Train: [88] [2800/6250] eta: 0:09:38 lr: 0.000005 grad: 0.1565 (0.1532) loss: 0.8804 (0.8776) time: 0.1727 data: 0.0862 max mem: 8233 +Train: [88] [2900/6250] eta: 0:09:20 lr: 0.000004 grad: 0.1442 (0.1534) loss: 0.8785 (0.8777) time: 0.1621 data: 0.0724 max mem: 8233 +Train: [88] [3000/6250] eta: 0:09:03 lr: 0.000004 grad: 0.1437 (0.1534) loss: 0.8794 (0.8777) time: 0.1622 data: 0.0799 max mem: 8233 +Train: [88] [3100/6250] eta: 0:08:46 lr: 0.000004 grad: 0.1432 (0.1534) loss: 0.8834 (0.8778) time: 0.1607 data: 0.0773 max mem: 8233 +Train: [88] [3200/6250] eta: 0:08:29 lr: 0.000004 grad: 0.1440 (0.1534) loss: 0.8851 (0.8779) time: 0.1400 data: 0.0499 max mem: 8233 +Train: [88] [3300/6250] eta: 0:08:12 lr: 0.000004 grad: 0.1484 (0.1534) loss: 0.8759 (0.8780) time: 0.1592 data: 0.0713 max mem: 8233 +Train: [88] [3400/6250] eta: 0:07:55 lr: 0.000004 grad: 0.1495 (0.1534) loss: 0.8803 (0.8780) time: 0.1570 data: 0.0607 max mem: 8233 +Train: [88] [3500/6250] eta: 0:07:37 lr: 0.000004 grad: 0.1563 (0.1538) loss: 0.8795 (0.8780) time: 0.1458 data: 0.0499 max mem: 8233 +Train: [88] [3600/6250] eta: 0:07:22 lr: 0.000004 grad: 0.1585 (0.1540) loss: 0.8812 (0.8781) time: 0.1883 data: 0.1012 max mem: 8233 +Train: [88] [3700/6250] eta: 0:07:05 lr: 0.000004 grad: 0.1515 (0.1541) loss: 0.8804 (0.8780) time: 0.1981 data: 0.1070 max mem: 8233 +Train: [88] [3800/6250] eta: 0:06:49 lr: 0.000004 grad: 0.1512 (0.1543) loss: 0.8787 (0.8780) time: 0.1822 data: 0.1004 max mem: 8233 +Train: [88] [3900/6250] eta: 0:06:33 lr: 0.000004 grad: 0.1453 (0.1544) loss: 0.8760 (0.8781) time: 0.1315 data: 0.0423 max mem: 8233 +Train: [88] [4000/6250] eta: 0:06:16 lr: 0.000004 grad: 0.1516 (0.1544) loss: 0.8753 (0.8781) time: 0.1645 data: 0.0746 max mem: 8233 +Train: [88] [4100/6250] eta: 0:06:00 lr: 0.000004 grad: 0.1458 (0.1545) loss: 0.8826 (0.8781) time: 0.1902 data: 0.1004 max mem: 8233 +Train: [88] [4200/6250] eta: 0:05:42 lr: 0.000004 grad: 0.1541 (0.1545) loss: 0.8732 (0.8782) time: 0.1515 data: 0.0619 max mem: 8233 +Train: [88] [4300/6250] eta: 0:05:26 lr: 0.000004 grad: 0.1564 (0.1546) loss: 0.8783 (0.8782) time: 0.1401 data: 0.0528 max mem: 8233 +Train: [88] [4400/6250] eta: 0:05:10 lr: 0.000004 grad: 0.1528 (0.1548) loss: 0.8825 (0.8782) time: 0.1229 data: 0.0003 max mem: 8233 +Train: [88] [4500/6250] eta: 0:04:54 lr: 0.000004 grad: 0.1553 (0.1548) loss: 0.8809 (0.8782) time: 0.1687 data: 0.0676 max mem: 8233 +Train: [88] [4600/6250] eta: 0:04:37 lr: 0.000004 grad: 0.1632 (0.1549) loss: 0.8722 (0.8782) time: 0.1136 data: 0.0003 max mem: 8233 +Train: [88] [4700/6250] eta: 0:04:20 lr: 0.000004 grad: 0.1469 (0.1550) loss: 0.8782 (0.8782) time: 0.1531 data: 0.0717 max mem: 8233 +Train: [88] [4800/6250] eta: 0:04:03 lr: 0.000004 grad: 0.1535 (0.1551) loss: 0.8815 (0.8782) time: 0.1663 data: 0.0914 max mem: 8233 +Train: [88] [4900/6250] eta: 0:03:46 lr: 0.000004 grad: 0.1574 (0.1552) loss: 0.8788 (0.8782) time: 0.1948 data: 0.1103 max mem: 8233 +Train: [88] [5000/6250] eta: 0:03:29 lr: 0.000004 grad: 0.1595 (0.1553) loss: 0.8760 (0.8782) time: 0.1416 data: 0.0612 max mem: 8233 +Train: [88] [5100/6250] eta: 0:03:12 lr: 0.000004 grad: 0.1513 (0.1555) loss: 0.8810 (0.8783) time: 0.1792 data: 0.1027 max mem: 8233 +Train: [88] [5200/6250] eta: 0:02:55 lr: 0.000004 grad: 0.1420 (0.1555) loss: 0.8836 (0.8783) time: 0.1445 data: 0.0374 max mem: 8233 +Train: [88] [5300/6250] eta: 0:02:39 lr: 0.000004 grad: 0.1530 (0.1555) loss: 0.8825 (0.8784) time: 0.1102 data: 0.0002 max mem: 8233 +Train: [88] [5400/6250] eta: 0:02:22 lr: 0.000004 grad: 0.1635 (0.1556) loss: 0.8866 (0.8784) time: 0.1360 data: 0.0637 max mem: 8233 +Train: [88] [5500/6250] eta: 0:02:05 lr: 0.000004 grad: 0.1439 (0.1556) loss: 0.8821 (0.8785) time: 0.1787 data: 0.1039 max mem: 8233 +Train: [88] [5600/6250] eta: 0:01:48 lr: 0.000004 grad: 0.1434 (0.1556) loss: 0.8791 (0.8785) time: 0.1690 data: 0.0881 max mem: 8233 +Train: [88] [5700/6250] eta: 0:01:31 lr: 0.000004 grad: 0.1409 (0.1557) loss: 0.8812 (0.8785) time: 0.1759 data: 0.0841 max mem: 8233 +Train: [88] [5800/6250] eta: 0:01:15 lr: 0.000004 grad: 0.1584 (0.1557) loss: 0.8738 (0.8785) time: 0.1586 data: 0.0907 max mem: 8233 +Train: [88] [5900/6250] eta: 0:00:58 lr: 0.000004 grad: 0.1540 (0.1557) loss: 0.8766 (0.8785) time: 0.1654 data: 0.0945 max mem: 8233 +Train: [88] [6000/6250] eta: 0:00:41 lr: 0.000004 grad: 0.1445 (0.1558) loss: 0.8775 (0.8786) time: 0.1844 data: 0.1078 max mem: 8233 +Train: [88] [6100/6250] eta: 0:00:25 lr: 0.000004 grad: 0.1526 (0.1558) loss: 0.8789 (0.8786) time: 0.1807 data: 0.0929 max mem: 8233 +Train: [88] [6200/6250] eta: 0:00:08 lr: 0.000004 grad: 0.1562 (0.1559) loss: 0.8802 (0.8786) time: 0.1983 data: 0.1213 max mem: 8233 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1573 (0.1559) loss: 0.8830 (0.8786) time: 0.1825 data: 0.1011 max mem: 8233 +Train: [88] Total time: 0:17:31 (0.1683 s / it) +Averaged stats: lr: 0.000004 grad: 0.1573 (0.1559) loss: 0.8830 (0.8786) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:07:01 loss: 0.8904 (0.8904) time: 6.7917 data: 6.7648 max mem: 8233 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8797 (0.8812) time: 0.1294 data: 0.1074 max mem: 8233 +Eval (hcp-train-subset): [88] Total time: 0:00:15 (0.2526 s / it) +Averaged stats (hcp-train-subset): loss: 0.8797 (0.8812) +Eval (hcp-val): [88] [ 0/62] eta: 0:04:54 loss: 0.8787 (0.8787) time: 4.7488 data: 4.6592 max mem: 8233 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8803 (0.8812) time: 0.1478 data: 0.1269 max mem: 8233 +Eval (hcp-val): [88] Total time: 0:00:15 (0.2552 s / it) +Averaged stats (hcp-val): loss: 0.8803 (0.8812) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 14:27:09 lr: 0.000004 grad: 0.2101 (0.2101) loss: 0.8446 (0.8446) time: 8.3247 data: 8.2274 max mem: 8233 +Train: [89] [ 100/6250] eta: 0:23:20 lr: 0.000004 grad: 0.1603 (0.1624) loss: 0.8843 (0.8795) time: 0.1512 data: 0.0389 max mem: 8233 +Train: [89] [ 200/6250] eta: 0:20:23 lr: 0.000004 grad: 0.1533 (0.1593) loss: 0.8841 (0.8781) time: 0.1771 data: 0.0695 max mem: 8233 +Train: [89] [ 300/6250] eta: 0:18:55 lr: 0.000004 grad: 0.1558 (0.1603) loss: 0.8769 (0.8787) time: 0.1654 data: 0.0621 max mem: 8233 +Train: [89] [ 400/6250] eta: 0:18:03 lr: 0.000004 grad: 0.1445 (0.1601) loss: 0.8890 (0.8791) time: 0.1713 data: 0.0701 max mem: 8233 +Train: [89] [ 500/6250] eta: 0:17:12 lr: 0.000004 grad: 0.1437 (0.1607) loss: 0.8809 (0.8794) time: 0.1482 data: 0.0486 max mem: 8233 +Train: [89] [ 600/6250] eta: 0:16:34 lr: 0.000004 grad: 0.1558 (0.1603) loss: 0.8828 (0.8800) time: 0.1416 data: 0.0505 max mem: 8233 +Train: [89] [ 700/6250] eta: 0:16:12 lr: 0.000004 grad: 0.1431 (0.1593) loss: 0.8823 (0.8806) time: 0.1406 data: 0.0352 max mem: 8233 +Train: [89] [ 800/6250] eta: 0:15:47 lr: 0.000004 grad: 0.1591 (0.1584) loss: 0.8820 (0.8812) time: 0.1659 data: 0.0826 max mem: 8233 +Train: [89] [ 900/6250] eta: 0:15:27 lr: 0.000004 grad: 0.1437 (0.1577) loss: 0.8848 (0.8816) time: 0.1841 data: 0.0878 max mem: 8233 +Train: [89] [1000/6250] eta: 0:15:05 lr: 0.000004 grad: 0.1485 (0.1574) loss: 0.8855 (0.8817) time: 0.1607 data: 0.0757 max mem: 8233 +Train: [89] [1100/6250] eta: 0:14:45 lr: 0.000004 grad: 0.1527 (0.1570) loss: 0.8820 (0.8816) time: 0.1603 data: 0.0729 max mem: 8233 +Train: [89] [1200/6250] eta: 0:14:25 lr: 0.000004 grad: 0.1477 (0.1572) loss: 0.8811 (0.8813) time: 0.1696 data: 0.0904 max mem: 8233 +Train: [89] [1300/6250] eta: 0:14:04 lr: 0.000004 grad: 0.1527 (0.1574) loss: 0.8775 (0.8812) time: 0.1402 data: 0.0587 max mem: 8233 +Train: [89] [1400/6250] eta: 0:13:42 lr: 0.000004 grad: 0.1565 (0.1576) loss: 0.8792 (0.8810) time: 0.1438 data: 0.0500 max mem: 8233 +Train: [89] [1500/6250] eta: 0:13:21 lr: 0.000004 grad: 0.1599 (0.1576) loss: 0.8796 (0.8808) time: 0.1654 data: 0.0727 max mem: 8233 +Train: [89] [1600/6250] eta: 0:13:00 lr: 0.000004 grad: 0.1556 (0.1581) loss: 0.8755 (0.8806) time: 0.1438 data: 0.0575 max mem: 8233 +Train: [89] [1700/6250] eta: 0:12:40 lr: 0.000004 grad: 0.1488 (0.1580) loss: 0.8776 (0.8804) time: 0.1780 data: 0.0919 max mem: 8233 +Train: [89] [1800/6250] eta: 0:12:22 lr: 0.000004 grad: 0.1537 (0.1580) loss: 0.8782 (0.8803) time: 0.1247 data: 0.0386 max mem: 8233 +Train: [89] [1900/6250] eta: 0:12:04 lr: 0.000004 grad: 0.1478 (0.1581) loss: 0.8777 (0.8801) time: 0.1563 data: 0.0785 max mem: 8233 +Train: [89] [2000/6250] eta: 0:11:46 lr: 0.000004 grad: 0.1472 (0.1580) loss: 0.8764 (0.8800) time: 0.1198 data: 0.0314 max mem: 8233 +Train: [89] [2100/6250] eta: 0:11:27 lr: 0.000004 grad: 0.1618 (0.1582) loss: 0.8725 (0.8798) time: 0.1393 data: 0.0518 max mem: 8233 +Train: [89] [2200/6250] eta: 0:11:09 lr: 0.000004 grad: 0.1503 (0.1584) loss: 0.8782 (0.8797) time: 0.1571 data: 0.0795 max mem: 8233 +Train: [89] [2300/6250] eta: 0:10:50 lr: 0.000004 grad: 0.1560 (0.1585) loss: 0.8770 (0.8795) time: 0.1509 data: 0.0659 max mem: 8233 +Train: [89] [2400/6250] eta: 0:10:32 lr: 0.000004 grad: 0.1554 (0.1587) loss: 0.8823 (0.8794) time: 0.1345 data: 0.0482 max mem: 8233 +Train: [89] [2500/6250] eta: 0:10:15 lr: 0.000004 grad: 0.1524 (0.1588) loss: 0.8756 (0.8793) time: 0.1611 data: 0.0795 max mem: 8233 +Train: [89] [2600/6250] eta: 0:10:01 lr: 0.000004 grad: 0.1715 (0.1588) loss: 0.8781 (0.8793) time: 0.1466 data: 0.0253 max mem: 8233 +Train: [89] [2700/6250] eta: 0:09:46 lr: 0.000004 grad: 0.1579 (0.1589) loss: 0.8763 (0.8793) time: 0.1996 data: 0.1309 max mem: 8233 +Train: [89] [2800/6250] eta: 0:09:31 lr: 0.000004 grad: 0.1531 (0.1590) loss: 0.8785 (0.8792) time: 0.1560 data: 0.0755 max mem: 8233 +Train: [89] [2900/6250] eta: 0:09:16 lr: 0.000004 grad: 0.1591 (0.1592) loss: 0.8816 (0.8792) time: 0.1720 data: 0.0943 max mem: 8233 +Train: [89] [3000/6250] eta: 0:09:00 lr: 0.000004 grad: 0.1458 (0.1593) loss: 0.8771 (0.8791) time: 0.1710 data: 0.0893 max mem: 8233 +Train: [89] [3100/6250] eta: 0:08:46 lr: 0.000004 grad: 0.1634 (0.1594) loss: 0.8739 (0.8791) time: 0.1548 data: 0.0732 max mem: 8233 +Train: [89] [3200/6250] eta: 0:08:29 lr: 0.000004 grad: 0.1545 (0.1596) loss: 0.8795 (0.8790) time: 0.1875 data: 0.1021 max mem: 8233 +Train: [89] [3300/6250] eta: 0:08:13 lr: 0.000004 grad: 0.1613 (0.1595) loss: 0.8778 (0.8790) time: 0.1991 data: 0.1127 max mem: 8233 +Train: [89] [3400/6250] eta: 0:07:57 lr: 0.000004 grad: 0.1562 (0.1597) loss: 0.8746 (0.8790) time: 0.1630 data: 0.0819 max mem: 8233 +Train: [89] [3500/6250] eta: 0:07:40 lr: 0.000004 grad: 0.1465 (0.1596) loss: 0.8813 (0.8789) time: 0.1762 data: 0.0961 max mem: 8233 +Train: [89] [3600/6250] eta: 0:07:23 lr: 0.000004 grad: 0.1627 (0.1595) loss: 0.8767 (0.8789) time: 0.1885 data: 0.1054 max mem: 8233 +Train: [89] [3700/6250] eta: 0:07:07 lr: 0.000004 grad: 0.1560 (0.1596) loss: 0.8778 (0.8789) time: 0.1757 data: 0.0987 max mem: 8233 +Train: [89] [3800/6250] eta: 0:06:50 lr: 0.000004 grad: 0.1571 (0.1596) loss: 0.8778 (0.8789) time: 0.1531 data: 0.0755 max mem: 8233 +Train: [89] [3900/6250] eta: 0:06:33 lr: 0.000004 grad: 0.1603 (0.1596) loss: 0.8746 (0.8789) time: 0.1464 data: 0.0705 max mem: 8233 +Train: [89] [4000/6250] eta: 0:06:16 lr: 0.000004 grad: 0.1506 (0.1596) loss: 0.8767 (0.8789) time: 0.1624 data: 0.0718 max mem: 8233 +Train: [89] [4100/6250] eta: 0:05:59 lr: 0.000004 grad: 0.1559 (0.1597) loss: 0.8797 (0.8789) time: 0.1513 data: 0.0590 max mem: 8233 +Train: [89] [4200/6250] eta: 0:05:43 lr: 0.000004 grad: 0.1531 (0.1597) loss: 0.8798 (0.8789) time: 0.1604 data: 0.0815 max mem: 8233 +Train: [89] [4300/6250] eta: 0:05:25 lr: 0.000004 grad: 0.1679 (0.1600) loss: 0.8776 (0.8790) time: 0.1472 data: 0.0605 max mem: 8233 +Train: [89] [4400/6250] eta: 0:05:08 lr: 0.000004 grad: 0.1499 (0.1601) loss: 0.8779 (0.8790) time: 0.1495 data: 0.0615 max mem: 8233 +Train: [89] [4500/6250] eta: 0:04:51 lr: 0.000004 grad: 0.1668 (0.1602) loss: 0.8793 (0.8790) time: 0.1494 data: 0.0809 max mem: 8233 +Train: [89] [4600/6250] eta: 0:04:35 lr: 0.000004 grad: 0.1560 (0.1602) loss: 0.8764 (0.8789) time: 0.1445 data: 0.0699 max mem: 8233 +Train: [89] [4700/6250] eta: 0:04:18 lr: 0.000004 grad: 0.1546 (0.1603) loss: 0.8812 (0.8789) time: 0.1748 data: 0.0883 max mem: 8233 +Train: [89] [4800/6250] eta: 0:04:01 lr: 0.000004 grad: 0.1622 (0.1605) loss: 0.8777 (0.8789) time: 0.2153 data: 0.0805 max mem: 8233 +Train: [89] [4900/6250] eta: 0:03:45 lr: 0.000004 grad: 0.1687 (0.1605) loss: 0.8818 (0.8789) time: 0.2121 data: 0.1182 max mem: 8233 +Train: [89] [5000/6250] eta: 0:03:28 lr: 0.000004 grad: 0.1543 (0.1607) loss: 0.8778 (0.8789) time: 0.1043 data: 0.0003 max mem: 8233 +Train: [89] [5100/6250] eta: 0:03:11 lr: 0.000004 grad: 0.1590 (0.1607) loss: 0.8797 (0.8789) time: 0.1578 data: 0.0783 max mem: 8233 +Train: [89] [5200/6250] eta: 0:02:54 lr: 0.000003 grad: 0.1458 (0.1606) loss: 0.8810 (0.8789) time: 0.1661 data: 0.0855 max mem: 8233 +Train: [89] [5300/6250] eta: 0:02:38 lr: 0.000003 grad: 0.1647 (0.1608) loss: 0.8808 (0.8789) time: 0.1762 data: 0.1015 max mem: 8233 +Train: [89] [5400/6250] eta: 0:02:21 lr: 0.000003 grad: 0.1612 (0.1610) loss: 0.8836 (0.8789) time: 0.1763 data: 0.0782 max mem: 8233 +Train: [89] [5500/6250] eta: 0:02:04 lr: 0.000003 grad: 0.1549 (0.1611) loss: 0.8800 (0.8789) time: 0.1402 data: 0.0572 max mem: 8233 +Train: [89] [5600/6250] eta: 0:01:48 lr: 0.000003 grad: 0.1552 (0.1612) loss: 0.8810 (0.8789) time: 0.1589 data: 0.0830 max mem: 8233 +Train: [89] [5700/6250] eta: 0:01:31 lr: 0.000003 grad: 0.1550 (0.1613) loss: 0.8724 (0.8789) time: 0.1126 data: 0.0002 max mem: 8233 +Train: [89] [5800/6250] eta: 0:01:14 lr: 0.000003 grad: 0.1538 (0.1614) loss: 0.8785 (0.8789) time: 0.1697 data: 0.0821 max mem: 8233 +Train: [89] [5900/6250] eta: 0:00:58 lr: 0.000003 grad: 0.1589 (0.1614) loss: 0.8822 (0.8789) time: 0.1584 data: 0.0787 max mem: 8233 +Train: [89] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1548 (0.1615) loss: 0.8768 (0.8789) time: 0.1589 data: 0.0845 max mem: 8233 +Train: [89] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1534 (0.1616) loss: 0.8787 (0.8788) time: 0.1792 data: 0.1094 max mem: 8233 +Train: [89] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1728 (0.1616) loss: 0.8826 (0.8788) time: 0.1713 data: 0.0963 max mem: 8233 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1583 (0.1617) loss: 0.8811 (0.8788) time: 0.1734 data: 0.0862 max mem: 8233 +Train: [89] Total time: 0:17:28 (0.1677 s / it) +Averaged stats: lr: 0.000003 grad: 0.1583 (0.1617) loss: 0.8811 (0.8788) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:04:50 loss: 0.8923 (0.8923) time: 4.6908 data: 4.5944 max mem: 8233 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8781 (0.8807) time: 0.1538 data: 0.1314 max mem: 8233 +Eval (hcp-train-subset): [89] Total time: 0:00:15 (0.2566 s / it) +Averaged stats (hcp-train-subset): loss: 0.8781 (0.8807) +Making plots (hcp-train-subset): example=55 +Eval (hcp-val): [89] [ 0/62] eta: 0:04:39 loss: 0.8780 (0.8780) time: 4.5146 data: 4.4102 max mem: 8233 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8802 (0.8808) time: 0.1416 data: 0.1207 max mem: 8233 +Eval (hcp-val): [89] Total time: 0:00:15 (0.2466 s / it) +Averaged stats (hcp-val): loss: 0.8802 (0.8808) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 9:08:11 lr: 0.000003 grad: 0.1032 (0.1032) loss: 0.9087 (0.9087) time: 5.2626 data: 4.8725 max mem: 8233 +Train: [90] [ 100/6250] eta: 0:23:54 lr: 0.000003 grad: 0.1577 (0.1597) loss: 0.8845 (0.8841) time: 0.1822 data: 0.0740 max mem: 8233 +Train: [90] [ 200/6250] eta: 0:20:15 lr: 0.000003 grad: 0.1585 (0.1620) loss: 0.8704 (0.8811) time: 0.1663 data: 0.0603 max mem: 8233 +Train: [90] [ 300/6250] eta: 0:18:41 lr: 0.000003 grad: 0.1739 (0.1701) loss: 0.8686 (0.8775) time: 0.1890 data: 0.0949 max mem: 8233 +Train: [90] [ 400/6250] eta: 0:17:33 lr: 0.000003 grad: 0.1644 (0.1706) loss: 0.8686 (0.8757) time: 0.1560 data: 0.0529 max mem: 8233 +Train: [90] [ 500/6250] eta: 0:16:42 lr: 0.000003 grad: 0.1466 (0.1703) loss: 0.8816 (0.8763) time: 0.1596 data: 0.0549 max mem: 8233 +Train: [90] [ 600/6250] eta: 0:16:06 lr: 0.000003 grad: 0.1564 (0.1687) loss: 0.8814 (0.8768) time: 0.1454 data: 0.0428 max mem: 8233 +Train: [90] [ 700/6250] eta: 0:15:37 lr: 0.000003 grad: 0.1517 (0.1683) loss: 0.8837 (0.8771) time: 0.1599 data: 0.0690 max mem: 8233 +Train: [90] [ 800/6250] eta: 0:15:13 lr: 0.000003 grad: 0.1549 (0.1682) loss: 0.8779 (0.8772) time: 0.1629 data: 0.0747 max mem: 8233 +Train: [90] [ 900/6250] eta: 0:14:59 lr: 0.000003 grad: 0.1584 (0.1680) loss: 0.8774 (0.8771) time: 0.1696 data: 0.0827 max mem: 8233 +Train: [90] [1000/6250] eta: 0:14:44 lr: 0.000003 grad: 0.1576 (0.1669) loss: 0.8782 (0.8772) time: 0.1773 data: 0.0947 max mem: 8233 +Train: [90] [1100/6250] eta: 0:14:24 lr: 0.000003 grad: 0.1541 (0.1668) loss: 0.8804 (0.8773) time: 0.1520 data: 0.0690 max mem: 8233 +Train: [90] [1200/6250] eta: 0:14:06 lr: 0.000003 grad: 0.1732 (0.1670) loss: 0.8766 (0.8771) time: 0.1485 data: 0.0591 max mem: 8233 +Train: [90] [1300/6250] eta: 0:13:44 lr: 0.000003 grad: 0.1621 (0.1669) loss: 0.8745 (0.8770) time: 0.1686 data: 0.0803 max mem: 8233 +Train: [90] [1400/6250] eta: 0:13:26 lr: 0.000003 grad: 0.1626 (0.1666) loss: 0.8760 (0.8770) time: 0.1596 data: 0.0733 max mem: 8233 +Train: [90] [1500/6250] eta: 0:13:11 lr: 0.000003 grad: 0.1555 (0.1664) loss: 0.8738 (0.8770) time: 0.1523 data: 0.0517 max mem: 8233 +Train: [90] [1600/6250] eta: 0:12:54 lr: 0.000003 grad: 0.1525 (0.1662) loss: 0.8816 (0.8771) time: 0.1555 data: 0.0809 max mem: 8233 +Train: [90] [1700/6250] eta: 0:12:43 lr: 0.000003 grad: 0.1468 (0.1658) loss: 0.8811 (0.8771) time: 0.1245 data: 0.0004 max mem: 8233 +Train: [90] [1800/6250] eta: 0:12:28 lr: 0.000003 grad: 0.1534 (0.1655) loss: 0.8763 (0.8771) time: 0.1772 data: 0.1030 max mem: 8233 +Train: [90] [1900/6250] eta: 0:12:11 lr: 0.000003 grad: 0.1458 (0.1652) loss: 0.8780 (0.8772) time: 0.1846 data: 0.0895 max mem: 8233 +Train: [90] [2000/6250] eta: 0:11:55 lr: 0.000003 grad: 0.1556 (0.1650) loss: 0.8768 (0.8772) time: 0.1513 data: 0.0869 max mem: 8233 +Train: [90] [2100/6250] eta: 0:11:39 lr: 0.000003 grad: 0.1559 (0.1648) loss: 0.8803 (0.8772) time: 0.2146 data: 0.1306 max mem: 8233 +Train: [90] [2200/6250] eta: 0:11:21 lr: 0.000003 grad: 0.1584 (0.1646) loss: 0.8778 (0.8773) time: 0.1600 data: 0.0787 max mem: 8233 +Train: [90] [2300/6250] eta: 0:11:03 lr: 0.000003 grad: 0.1586 (0.1645) loss: 0.8832 (0.8773) time: 0.1707 data: 0.0961 max mem: 8233 +Train: [90] [2400/6250] eta: 0:10:46 lr: 0.000003 grad: 0.1510 (0.1645) loss: 0.8766 (0.8773) time: 0.1939 data: 0.1009 max mem: 8233 +Train: [90] [2500/6250] eta: 0:10:28 lr: 0.000003 grad: 0.1577 (0.1646) loss: 0.8768 (0.8774) time: 0.1591 data: 0.0730 max mem: 8233 +Train: [90] [2600/6250] eta: 0:10:09 lr: 0.000003 grad: 0.1580 (0.1646) loss: 0.8797 (0.8774) time: 0.1638 data: 0.0808 max mem: 8233 +Train: [90] [2700/6250] eta: 0:09:53 lr: 0.000003 grad: 0.1403 (0.1645) loss: 0.8786 (0.8773) time: 0.1485 data: 0.0668 max mem: 8233 +Train: [90] [2800/6250] eta: 0:09:36 lr: 0.000003 grad: 0.1554 (0.1642) loss: 0.8761 (0.8773) time: 0.1590 data: 0.0888 max mem: 8233 +Train: [90] [2900/6250] eta: 0:09:19 lr: 0.000003 grad: 0.1498 (0.1641) loss: 0.8791 (0.8774) time: 0.1602 data: 0.0862 max mem: 8233 +Train: [90] [3000/6250] eta: 0:09:02 lr: 0.000003 grad: 0.1534 (0.1638) loss: 0.8764 (0.8774) time: 0.1690 data: 0.0923 max mem: 8233 +Train: [90] [3100/6250] eta: 0:08:45 lr: 0.000003 grad: 0.1429 (0.1637) loss: 0.8809 (0.8775) time: 0.1821 data: 0.0996 max mem: 8233 +Train: [90] [3200/6250] eta: 0:08:29 lr: 0.000003 grad: 0.1496 (0.1636) loss: 0.8802 (0.8775) time: 0.1416 data: 0.0446 max mem: 8233 +Train: [90] [3300/6250] eta: 0:08:12 lr: 0.000003 grad: 0.1596 (0.1638) loss: 0.8796 (0.8775) time: 0.1659 data: 0.0797 max mem: 8233 +Train: [90] [3400/6250] eta: 0:07:54 lr: 0.000003 grad: 0.1493 (0.1638) loss: 0.8763 (0.8775) time: 0.1761 data: 0.1001 max mem: 8233 +Train: [90] [3500/6250] eta: 0:07:37 lr: 0.000003 grad: 0.1570 (0.1637) loss: 0.8775 (0.8776) time: 0.1593 data: 0.0780 max mem: 8233 +Train: [90] [3600/6250] eta: 0:07:20 lr: 0.000003 grad: 0.1609 (0.1635) loss: 0.8773 (0.8776) time: 0.1527 data: 0.0688 max mem: 8233 +Train: [90] [3700/6250] eta: 0:07:03 lr: 0.000003 grad: 0.1547 (0.1634) loss: 0.8775 (0.8776) time: 0.1611 data: 0.0710 max mem: 8233 +Train: [90] [3800/6250] eta: 0:06:47 lr: 0.000003 grad: 0.1661 (0.1636) loss: 0.8732 (0.8775) time: 0.1196 data: 0.0505 max mem: 8233 +Train: [90] [3900/6250] eta: 0:06:30 lr: 0.000003 grad: 0.1474 (0.1635) loss: 0.8774 (0.8775) time: 0.1324 data: 0.0500 max mem: 8233 +Train: [90] [4000/6250] eta: 0:06:13 lr: 0.000003 grad: 0.1518 (0.1634) loss: 0.8767 (0.8774) time: 0.1448 data: 0.0723 max mem: 8233 +Train: [90] [4100/6250] eta: 0:05:57 lr: 0.000003 grad: 0.1456 (0.1633) loss: 0.8746 (0.8774) time: 0.1689 data: 0.0811 max mem: 8233 +Train: [90] [4200/6250] eta: 0:05:40 lr: 0.000003 grad: 0.1539 (0.1632) loss: 0.8795 (0.8774) time: 0.1549 data: 0.0739 max mem: 8233 +Train: [90] [4300/6250] eta: 0:05:24 lr: 0.000003 grad: 0.1357 (0.1630) loss: 0.8815 (0.8774) time: 0.1333 data: 0.0509 max mem: 8233 +Train: [90] [4400/6250] eta: 0:05:07 lr: 0.000003 grad: 0.1520 (0.1628) loss: 0.8731 (0.8774) time: 0.1683 data: 0.0867 max mem: 8233 +Train: [90] [4500/6250] eta: 0:04:50 lr: 0.000003 grad: 0.1411 (0.1626) loss: 0.8736 (0.8774) time: 0.1808 data: 0.1026 max mem: 8233 +Train: [90] [4600/6250] eta: 0:04:33 lr: 0.000003 grad: 0.1519 (0.1625) loss: 0.8693 (0.8774) time: 0.1416 data: 0.0620 max mem: 8233 +Train: [90] [4700/6250] eta: 0:04:17 lr: 0.000003 grad: 0.1417 (0.1623) loss: 0.8791 (0.8774) time: 0.2222 data: 0.1266 max mem: 8233 +Train: [90] [4800/6250] eta: 0:04:00 lr: 0.000003 grad: 0.1492 (0.1622) loss: 0.8790 (0.8774) time: 0.1605 data: 0.0848 max mem: 8233 +Train: [90] [4900/6250] eta: 0:03:43 lr: 0.000003 grad: 0.1499 (0.1620) loss: 0.8784 (0.8774) time: 0.1797 data: 0.0997 max mem: 8233 +Train: [90] [5000/6250] eta: 0:03:26 lr: 0.000003 grad: 0.1428 (0.1618) loss: 0.8801 (0.8774) time: 0.1803 data: 0.1089 max mem: 8233 +Train: [90] [5100/6250] eta: 0:03:10 lr: 0.000003 grad: 0.1477 (0.1617) loss: 0.8823 (0.8775) time: 0.1441 data: 0.0565 max mem: 8233 +Train: [90] [5200/6250] eta: 0:02:53 lr: 0.000003 grad: 0.1441 (0.1614) loss: 0.8816 (0.8775) time: 0.1482 data: 0.0696 max mem: 8233 +Train: [90] [5300/6250] eta: 0:02:36 lr: 0.000003 grad: 0.1486 (0.1613) loss: 0.8821 (0.8776) time: 0.1565 data: 0.0784 max mem: 8233 +Train: [90] [5400/6250] eta: 0:02:20 lr: 0.000003 grad: 0.1549 (0.1611) loss: 0.8735 (0.8776) time: 0.1316 data: 0.0495 max mem: 8233 +Train: [90] [5500/6250] eta: 0:02:03 lr: 0.000003 grad: 0.1441 (0.1610) loss: 0.8841 (0.8777) time: 0.1456 data: 0.0690 max mem: 8233 +Train: [90] [5600/6250] eta: 0:01:47 lr: 0.000003 grad: 0.1529 (0.1609) loss: 0.8853 (0.8778) time: 0.1397 data: 0.0621 max mem: 8233 +Train: [90] [5700/6250] eta: 0:01:30 lr: 0.000003 grad: 0.1574 (0.1609) loss: 0.8776 (0.8778) time: 0.1708 data: 0.0942 max mem: 8233 +Train: [90] [5800/6250] eta: 0:01:14 lr: 0.000003 grad: 0.1521 (0.1608) loss: 0.8792 (0.8779) time: 0.1099 data: 0.0042 max mem: 8233 +Train: [90] [5900/6250] eta: 0:00:57 lr: 0.000003 grad: 0.1553 (0.1609) loss: 0.8779 (0.8779) time: 0.1635 data: 0.0969 max mem: 8233 +Train: [90] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1542 (0.1609) loss: 0.8828 (0.8780) time: 0.1393 data: 0.0641 max mem: 8233 +Train: [90] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1461 (0.1608) loss: 0.8813 (0.8780) time: 0.1497 data: 0.0732 max mem: 8233 +Train: [90] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1448 (0.1608) loss: 0.8847 (0.8781) time: 0.1821 data: 0.1011 max mem: 8233 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1623 (0.1607) loss: 0.8806 (0.8781) time: 0.1771 data: 0.0878 max mem: 8233 +Train: [90] Total time: 0:17:13 (0.1654 s / it) +Averaged stats: lr: 0.000003 grad: 0.1623 (0.1607) loss: 0.8806 (0.8781) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:04:19 loss: 0.8914 (0.8914) time: 4.1843 data: 4.0682 max mem: 8233 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8778 (0.8800) time: 0.1369 data: 0.1159 max mem: 8233 +Eval (hcp-train-subset): [90] Total time: 0:00:15 (0.2563 s / it) +Averaged stats (hcp-train-subset): loss: 0.8778 (0.8800) +Eval (hcp-val): [90] [ 0/62] eta: 0:04:05 loss: 0.8801 (0.8801) time: 3.9592 data: 3.8511 max mem: 8233 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8814 (0.8806) time: 0.1370 data: 0.1158 max mem: 8233 +Eval (hcp-val): [90] Total time: 0:00:14 (0.2416 s / it) +Averaged stats (hcp-val): loss: 0.8814 (0.8806) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 11:32:35 lr: 0.000003 grad: 0.1731 (0.1731) loss: 0.8797 (0.8797) time: 6.6488 data: 6.4772 max mem: 8233 +Train: [91] [ 100/6250] eta: 0:23:13 lr: 0.000003 grad: 0.1851 (0.1935) loss: 0.8639 (0.8734) time: 0.1747 data: 0.0760 max mem: 8233 +Train: [91] [ 200/6250] eta: 0:19:42 lr: 0.000003 grad: 0.1712 (0.1872) loss: 0.8705 (0.8725) time: 0.1542 data: 0.0587 max mem: 8233 +Train: [91] [ 300/6250] eta: 0:18:21 lr: 0.000003 grad: 0.1658 (0.1816) loss: 0.8765 (0.8741) time: 0.1641 data: 0.0591 max mem: 8233 +Train: [91] [ 400/6250] eta: 0:17:09 lr: 0.000003 grad: 0.1633 (0.1783) loss: 0.8786 (0.8753) time: 0.1372 data: 0.0281 max mem: 8233 +Train: [91] [ 500/6250] eta: 0:16:38 lr: 0.000003 grad: 0.1464 (0.1746) loss: 0.8832 (0.8763) time: 0.1649 data: 0.0752 max mem: 8233 +Train: [91] [ 600/6250] eta: 0:16:05 lr: 0.000003 grad: 0.1595 (0.1726) loss: 0.8752 (0.8763) time: 0.1478 data: 0.0503 max mem: 8233 +Train: [91] [ 700/6250] eta: 0:15:43 lr: 0.000003 grad: 0.1527 (0.1713) loss: 0.8768 (0.8764) time: 0.1552 data: 0.0783 max mem: 8233 +Train: [91] [ 800/6250] eta: 0:15:27 lr: 0.000003 grad: 0.1559 (0.1701) loss: 0.8777 (0.8766) time: 0.2062 data: 0.1234 max mem: 8233 +Train: [91] [ 900/6250] eta: 0:15:06 lr: 0.000003 grad: 0.1563 (0.1700) loss: 0.8792 (0.8764) time: 0.1482 data: 0.0583 max mem: 8233 +Train: [91] [1000/6250] eta: 0:15:09 lr: 0.000003 grad: 0.1488 (0.1689) loss: 0.8816 (0.8766) time: 0.3019 data: 0.2159 max mem: 8233 +Train: [91] [1100/6250] eta: 0:14:42 lr: 0.000003 grad: 0.1503 (0.1679) loss: 0.8791 (0.8767) time: 0.1607 data: 0.0829 max mem: 8233 +Train: [91] [1200/6250] eta: 0:14:27 lr: 0.000003 grad: 0.1561 (0.1673) loss: 0.8808 (0.8768) time: 0.2377 data: 0.1572 max mem: 8233 +Train: [91] [1300/6250] eta: 0:14:02 lr: 0.000003 grad: 0.1624 (0.1668) loss: 0.8855 (0.8770) time: 0.1804 data: 0.0987 max mem: 8233 +Train: [91] [1400/6250] eta: 0:13:39 lr: 0.000003 grad: 0.1493 (0.1662) loss: 0.8748 (0.8771) time: 0.1694 data: 0.0819 max mem: 8233 +Train: [91] [1500/6250] eta: 0:13:18 lr: 0.000003 grad: 0.1590 (0.1658) loss: 0.8802 (0.8772) time: 0.1384 data: 0.0545 max mem: 8233 +Train: [91] [1600/6250] eta: 0:13:00 lr: 0.000003 grad: 0.1538 (0.1655) loss: 0.8757 (0.8773) time: 0.1626 data: 0.0845 max mem: 8233 +Train: [91] [1700/6250] eta: 0:12:42 lr: 0.000003 grad: 0.1576 (0.1652) loss: 0.8774 (0.8772) time: 0.1637 data: 0.0730 max mem: 8233 +Train: [91] [1800/6250] eta: 0:12:23 lr: 0.000003 grad: 0.1451 (0.1650) loss: 0.8801 (0.8772) time: 0.1426 data: 0.0570 max mem: 8233 +Train: [91] [1900/6250] eta: 0:12:07 lr: 0.000003 grad: 0.1589 (0.1646) loss: 0.8872 (0.8773) time: 0.1844 data: 0.0881 max mem: 8233 +Train: [91] [2000/6250] eta: 0:11:48 lr: 0.000003 grad: 0.1547 (0.1646) loss: 0.8793 (0.8773) time: 0.1811 data: 0.1002 max mem: 8233 +Train: [91] [2100/6250] eta: 0:11:30 lr: 0.000003 grad: 0.1463 (0.1644) loss: 0.8771 (0.8773) time: 0.1526 data: 0.0759 max mem: 8233 +Train: [91] [2200/6250] eta: 0:11:12 lr: 0.000003 grad: 0.1711 (0.1642) loss: 0.8768 (0.8773) time: 0.1509 data: 0.0717 max mem: 8233 +Train: [91] [2300/6250] eta: 0:10:54 lr: 0.000003 grad: 0.1519 (0.1642) loss: 0.8791 (0.8773) time: 0.1378 data: 0.0517 max mem: 8233 +Train: [91] [2400/6250] eta: 0:10:36 lr: 0.000003 grad: 0.1565 (0.1641) loss: 0.8790 (0.8773) time: 0.1756 data: 0.0922 max mem: 8233 +Train: [91] [2500/6250] eta: 0:10:19 lr: 0.000003 grad: 0.1533 (0.1641) loss: 0.8765 (0.8772) time: 0.1710 data: 0.0979 max mem: 8233 +Train: [91] [2600/6250] eta: 0:10:02 lr: 0.000003 grad: 0.1584 (0.1640) loss: 0.8770 (0.8772) time: 0.1480 data: 0.0745 max mem: 8233 +Train: [91] [2700/6250] eta: 0:09:44 lr: 0.000002 grad: 0.1549 (0.1637) loss: 0.8812 (0.8772) time: 0.1668 data: 0.0937 max mem: 8233 +Train: [91] [2800/6250] eta: 0:09:28 lr: 0.000002 grad: 0.1434 (0.1635) loss: 0.8792 (0.8772) time: 0.1599 data: 0.0739 max mem: 8233 +Train: [91] [2900/6250] eta: 0:09:12 lr: 0.000002 grad: 0.1596 (0.1633) loss: 0.8771 (0.8772) time: 0.1694 data: 0.0875 max mem: 8233 +Train: [91] [3000/6250] eta: 0:08:55 lr: 0.000002 grad: 0.1436 (0.1630) loss: 0.8781 (0.8773) time: 0.1868 data: 0.1213 max mem: 8233 +Train: [91] [3100/6250] eta: 0:08:39 lr: 0.000002 grad: 0.1469 (0.1628) loss: 0.8803 (0.8774) time: 0.1694 data: 0.0894 max mem: 8233 +Train: [91] [3200/6250] eta: 0:08:24 lr: 0.000002 grad: 0.1509 (0.1626) loss: 0.8804 (0.8774) time: 0.1630 data: 0.0696 max mem: 8233 +Train: [91] [3300/6250] eta: 0:08:08 lr: 0.000002 grad: 0.1529 (0.1625) loss: 0.8802 (0.8775) time: 0.1528 data: 0.0632 max mem: 8233 +Train: [91] [3400/6250] eta: 0:07:51 lr: 0.000002 grad: 0.1505 (0.1625) loss: 0.8776 (0.8775) time: 0.1781 data: 0.1041 max mem: 8233 +Train: [91] [3500/6250] eta: 0:07:33 lr: 0.000002 grad: 0.1463 (0.1626) loss: 0.8748 (0.8775) time: 0.1490 data: 0.0679 max mem: 8233 +Train: [91] [3600/6250] eta: 0:07:16 lr: 0.000002 grad: 0.1457 (0.1625) loss: 0.8799 (0.8774) time: 0.1420 data: 0.0549 max mem: 8233 +Train: [91] [3700/6250] eta: 0:07:00 lr: 0.000002 grad: 0.1603 (0.1624) loss: 0.8739 (0.8774) time: 0.1359 data: 0.0458 max mem: 8233 +Train: [91] [3800/6250] eta: 0:06:43 lr: 0.000002 grad: 0.1515 (0.1623) loss: 0.8764 (0.8775) time: 0.1454 data: 0.0693 max mem: 8233 +Train: [91] [3900/6250] eta: 0:06:27 lr: 0.000002 grad: 0.1525 (0.1623) loss: 0.8698 (0.8774) time: 0.2632 data: 0.1789 max mem: 8233 +Train: [91] [4000/6250] eta: 0:06:10 lr: 0.000002 grad: 0.1445 (0.1621) loss: 0.8784 (0.8774) time: 0.1384 data: 0.0473 max mem: 8233 +Train: [91] [4100/6250] eta: 0:05:53 lr: 0.000002 grad: 0.1468 (0.1620) loss: 0.8764 (0.8774) time: 0.1524 data: 0.0671 max mem: 8233 +Train: [91] [4200/6250] eta: 0:05:36 lr: 0.000002 grad: 0.1518 (0.1620) loss: 0.8763 (0.8774) time: 0.1507 data: 0.0752 max mem: 8233 +Train: [91] [4300/6250] eta: 0:05:19 lr: 0.000002 grad: 0.1606 (0.1619) loss: 0.8721 (0.8774) time: 0.1764 data: 0.0938 max mem: 8233 +Train: [91] [4400/6250] eta: 0:05:03 lr: 0.000002 grad: 0.1577 (0.1619) loss: 0.8809 (0.8775) time: 0.1723 data: 0.0849 max mem: 8233 +Train: [91] [4500/6250] eta: 0:04:46 lr: 0.000002 grad: 0.1438 (0.1618) loss: 0.8820 (0.8775) time: 0.1614 data: 0.0750 max mem: 8233 +Train: [91] [4600/6250] eta: 0:04:30 lr: 0.000002 grad: 0.1489 (0.1616) loss: 0.8780 (0.8775) time: 0.1804 data: 0.0911 max mem: 8233 +Train: [91] [4700/6250] eta: 0:04:13 lr: 0.000002 grad: 0.1497 (0.1615) loss: 0.8768 (0.8776) time: 0.1866 data: 0.1032 max mem: 8233 +Train: [91] [4800/6250] eta: 0:03:57 lr: 0.000002 grad: 0.1555 (0.1614) loss: 0.8800 (0.8777) time: 0.1470 data: 0.0650 max mem: 8233 +Train: [91] [4900/6250] eta: 0:03:40 lr: 0.000002 grad: 0.1492 (0.1613) loss: 0.8774 (0.8777) time: 0.1446 data: 0.0568 max mem: 8233 +Train: [91] [5000/6250] eta: 0:03:24 lr: 0.000002 grad: 0.1527 (0.1613) loss: 0.8834 (0.8778) time: 0.2277 data: 0.1390 max mem: 8233 +Train: [91] [5100/6250] eta: 0:03:07 lr: 0.000002 grad: 0.1481 (0.1612) loss: 0.8791 (0.8778) time: 0.1463 data: 0.0575 max mem: 8233 +Train: [91] [5200/6250] eta: 0:02:51 lr: 0.000002 grad: 0.1455 (0.1611) loss: 0.8848 (0.8778) time: 0.1453 data: 0.0887 max mem: 8233 +Train: [91] [5300/6250] eta: 0:02:34 lr: 0.000002 grad: 0.1461 (0.1610) loss: 0.8818 (0.8778) time: 0.1316 data: 0.0475 max mem: 8233 +Train: [91] [5400/6250] eta: 0:02:18 lr: 0.000002 grad: 0.1457 (0.1608) loss: 0.8834 (0.8779) time: 0.1700 data: 0.0857 max mem: 8233 +Train: [91] [5500/6250] eta: 0:02:02 lr: 0.000002 grad: 0.1476 (0.1607) loss: 0.8782 (0.8779) time: 0.1513 data: 0.0730 max mem: 8233 +Train: [91] [5600/6250] eta: 0:01:46 lr: 0.000002 grad: 0.1509 (0.1606) loss: 0.8744 (0.8779) time: 0.1815 data: 0.1072 max mem: 8233 +Train: [91] [5700/6250] eta: 0:01:30 lr: 0.000002 grad: 0.1541 (0.1606) loss: 0.8789 (0.8780) time: 0.1997 data: 0.1287 max mem: 8233 +Train: [91] [5800/6250] eta: 0:01:13 lr: 0.000002 grad: 0.1637 (0.1606) loss: 0.8778 (0.8780) time: 0.1435 data: 0.0659 max mem: 8233 +Train: [91] [5900/6250] eta: 0:00:57 lr: 0.000002 grad: 0.1574 (0.1606) loss: 0.8827 (0.8780) time: 0.1594 data: 0.0767 max mem: 8233 +Train: [91] [6000/6250] eta: 0:00:40 lr: 0.000002 grad: 0.1543 (0.1605) loss: 0.8748 (0.8780) time: 0.1655 data: 0.0972 max mem: 8233 +Train: [91] [6100/6250] eta: 0:00:24 lr: 0.000002 grad: 0.1550 (0.1605) loss: 0.8741 (0.8780) time: 0.1624 data: 0.0842 max mem: 8233 +Train: [91] [6200/6250] eta: 0:00:08 lr: 0.000002 grad: 0.1502 (0.1605) loss: 0.8766 (0.8780) time: 0.1668 data: 0.0977 max mem: 8233 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1546 (0.1604) loss: 0.8813 (0.8781) time: 0.1503 data: 0.0693 max mem: 8233 +Train: [91] Total time: 0:17:02 (0.1636 s / it) +Averaged stats: lr: 0.000002 grad: 0.1546 (0.1604) loss: 0.8813 (0.8781) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:05:43 loss: 0.8898 (0.8898) time: 5.5469 data: 5.5197 max mem: 8233 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8815 (0.8802) time: 0.1439 data: 0.1231 max mem: 8233 +Eval (hcp-train-subset): [91] Total time: 0:00:14 (0.2408 s / it) +Averaged stats (hcp-train-subset): loss: 0.8815 (0.8802) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:09 loss: 0.8769 (0.8769) time: 4.0287 data: 3.9479 max mem: 8233 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8799 (0.8805) time: 0.1297 data: 0.1074 max mem: 8233 +Eval (hcp-val): [91] Total time: 0:00:14 (0.2372 s / it) +Averaged stats (hcp-val): loss: 0.8799 (0.8805) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 9:53:41 lr: 0.000002 grad: 0.2267 (0.2267) loss: 0.8824 (0.8824) time: 5.6994 data: 5.4078 max mem: 8233 +Train: [92] [ 100/6250] eta: 0:23:25 lr: 0.000002 grad: 0.1542 (0.1681) loss: 0.8844 (0.8824) time: 0.1787 data: 0.0675 max mem: 8233 +Train: [92] [ 200/6250] eta: 0:19:49 lr: 0.000002 grad: 0.1738 (0.1715) loss: 0.8804 (0.8811) time: 0.1796 data: 0.0686 max mem: 8233 +Train: [92] [ 300/6250] eta: 0:18:13 lr: 0.000002 grad: 0.1563 (0.1688) loss: 0.8788 (0.8802) time: 0.1456 data: 0.0216 max mem: 8233 +Train: [92] [ 400/6250] eta: 0:17:17 lr: 0.000002 grad: 0.1579 (0.1678) loss: 0.8835 (0.8801) time: 0.1541 data: 0.0579 max mem: 8233 +Train: [92] [ 500/6250] eta: 0:16:24 lr: 0.000002 grad: 0.1482 (0.1656) loss: 0.8852 (0.8800) time: 0.1497 data: 0.0520 max mem: 8233 +Train: [92] [ 600/6250] eta: 0:15:43 lr: 0.000002 grad: 0.1467 (0.1643) loss: 0.8779 (0.8798) time: 0.1554 data: 0.0469 max mem: 8233 +Train: [92] [ 700/6250] eta: 0:15:10 lr: 0.000002 grad: 0.1549 (0.1633) loss: 0.8770 (0.8796) time: 0.1360 data: 0.0360 max mem: 8233 +Train: [92] [ 800/6250] eta: 0:14:48 lr: 0.000002 grad: 0.1544 (0.1634) loss: 0.8806 (0.8792) time: 0.1438 data: 0.0346 max mem: 8233 +Train: [92] [ 900/6250] eta: 0:14:22 lr: 0.000002 grad: 0.1485 (0.1629) loss: 0.8767 (0.8791) time: 0.1530 data: 0.0512 max mem: 8233 +Train: [92] [1000/6250] eta: 0:14:00 lr: 0.000002 grad: 0.1565 (0.1630) loss: 0.8733 (0.8789) time: 0.1426 data: 0.0441 max mem: 8233 +Train: [92] [1100/6250] eta: 0:13:39 lr: 0.000002 grad: 0.1544 (0.1630) loss: 0.8704 (0.8786) time: 0.1655 data: 0.0683 max mem: 8233 +Train: [92] [1200/6250] eta: 0:13:15 lr: 0.000002 grad: 0.1525 (0.1626) loss: 0.8753 (0.8786) time: 0.1434 data: 0.0580 max mem: 8233 +Train: [92] [1300/6250] eta: 0:12:53 lr: 0.000002 grad: 0.1658 (0.1632) loss: 0.8777 (0.8784) time: 0.1489 data: 0.0663 max mem: 8233 +Train: [92] [1400/6250] eta: 0:12:33 lr: 0.000002 grad: 0.1563 (0.1633) loss: 0.8792 (0.8784) time: 0.1398 data: 0.0492 max mem: 8233 +Train: [92] [1500/6250] eta: 0:12:13 lr: 0.000002 grad: 0.1571 (0.1636) loss: 0.8743 (0.8784) time: 0.1544 data: 0.0717 max mem: 8233 +Train: [92] [1600/6250] eta: 0:11:57 lr: 0.000002 grad: 0.1594 (0.1635) loss: 0.8761 (0.8784) time: 0.1543 data: 0.0661 max mem: 8233 +Train: [92] [1700/6250] eta: 0:11:39 lr: 0.000002 grad: 0.1607 (0.1635) loss: 0.8769 (0.8783) time: 0.1556 data: 0.0683 max mem: 8233 +Train: [92] [1800/6250] eta: 0:11:24 lr: 0.000002 grad: 0.1520 (0.1635) loss: 0.8786 (0.8783) time: 0.1687 data: 0.0942 max mem: 8233 +Train: [92] [1900/6250] eta: 0:11:06 lr: 0.000002 grad: 0.1543 (0.1635) loss: 0.8773 (0.8782) time: 0.1508 data: 0.0488 max mem: 8233 +Train: [92] [2000/6250] eta: 0:10:49 lr: 0.000002 grad: 0.1516 (0.1637) loss: 0.8788 (0.8782) time: 0.1448 data: 0.0528 max mem: 8233 +Train: [92] [2100/6250] eta: 0:10:34 lr: 0.000002 grad: 0.1635 (0.1636) loss: 0.8782 (0.8781) time: 0.1813 data: 0.1072 max mem: 8233 +Train: [92] [2200/6250] eta: 0:10:17 lr: 0.000002 grad: 0.1513 (0.1634) loss: 0.8795 (0.8781) time: 0.1676 data: 0.0802 max mem: 8233 +Train: [92] [2300/6250] eta: 0:10:07 lr: 0.000002 grad: 0.1593 (0.1635) loss: 0.8720 (0.8780) time: 0.1010 data: 0.0003 max mem: 8233 +Train: [92] [2400/6250] eta: 0:09:51 lr: 0.000002 grad: 0.1492 (0.1636) loss: 0.8766 (0.8779) time: 0.1561 data: 0.0649 max mem: 8233 +Train: [92] [2500/6250] eta: 0:09:37 lr: 0.000002 grad: 0.1604 (0.1635) loss: 0.8800 (0.8780) time: 0.1745 data: 0.0750 max mem: 8233 +Train: [92] [2600/6250] eta: 0:09:22 lr: 0.000002 grad: 0.1487 (0.1635) loss: 0.8780 (0.8780) time: 0.1413 data: 0.0574 max mem: 8233 +Train: [92] [2700/6250] eta: 0:09:06 lr: 0.000002 grad: 0.1477 (0.1632) loss: 0.8812 (0.8780) time: 0.1661 data: 0.0838 max mem: 8233 +Train: [92] [2800/6250] eta: 0:08:53 lr: 0.000002 grad: 0.1474 (0.1629) loss: 0.8777 (0.8780) time: 0.2675 data: 0.2000 max mem: 8233 +Train: [92] [2900/6250] eta: 0:08:37 lr: 0.000002 grad: 0.1524 (0.1627) loss: 0.8808 (0.8780) time: 0.1366 data: 0.0521 max mem: 8233 +Train: [92] [3000/6250] eta: 0:08:21 lr: 0.000002 grad: 0.1483 (0.1625) loss: 0.8823 (0.8781) time: 0.1354 data: 0.0514 max mem: 8233 +Train: [92] [3100/6250] eta: 0:08:05 lr: 0.000002 grad: 0.1492 (0.1623) loss: 0.8820 (0.8781) time: 0.1464 data: 0.0593 max mem: 8233 +Train: [92] [3200/6250] eta: 0:07:51 lr: 0.000002 grad: 0.1475 (0.1620) loss: 0.8824 (0.8782) time: 0.1779 data: 0.0848 max mem: 8233 +Train: [92] [3300/6250] eta: 0:07:36 lr: 0.000002 grad: 0.1466 (0.1618) loss: 0.8852 (0.8783) time: 0.1979 data: 0.1140 max mem: 8233 +Train: [92] [3400/6250] eta: 0:07:21 lr: 0.000002 grad: 0.1508 (0.1617) loss: 0.8776 (0.8783) time: 0.1613 data: 0.0713 max mem: 8233 +Train: [92] [3500/6250] eta: 0:07:05 lr: 0.000002 grad: 0.1514 (0.1616) loss: 0.8795 (0.8784) time: 0.1531 data: 0.0586 max mem: 8233 +Train: [92] [3600/6250] eta: 0:06:50 lr: 0.000002 grad: 0.1484 (0.1614) loss: 0.8837 (0.8784) time: 0.1604 data: 0.0776 max mem: 8233 +Train: [92] [3700/6250] eta: 0:06:33 lr: 0.000002 grad: 0.1472 (0.1612) loss: 0.8833 (0.8785) time: 0.1501 data: 0.0713 max mem: 8233 +Train: [92] [3800/6250] eta: 0:06:18 lr: 0.000002 grad: 0.1478 (0.1610) loss: 0.8826 (0.8786) time: 0.1711 data: 0.0929 max mem: 8233 +Train: [92] [3900/6250] eta: 0:06:02 lr: 0.000002 grad: 0.1451 (0.1608) loss: 0.8860 (0.8787) time: 0.1311 data: 0.0400 max mem: 8233 +Train: [92] [4000/6250] eta: 0:05:47 lr: 0.000002 grad: 0.1460 (0.1607) loss: 0.8744 (0.8787) time: 0.1555 data: 0.0778 max mem: 8233 +Train: [92] [4100/6250] eta: 0:05:32 lr: 0.000002 grad: 0.1467 (0.1605) loss: 0.8865 (0.8788) time: 0.1391 data: 0.0579 max mem: 8233 +Train: [92] [4200/6250] eta: 0:05:16 lr: 0.000002 grad: 0.1476 (0.1605) loss: 0.8799 (0.8789) time: 0.1478 data: 0.0706 max mem: 8233 +Train: [92] [4300/6250] eta: 0:05:01 lr: 0.000002 grad: 0.1549 (0.1606) loss: 0.8806 (0.8789) time: 0.1372 data: 0.0641 max mem: 8233 +Train: [92] [4400/6250] eta: 0:04:46 lr: 0.000002 grad: 0.1540 (0.1604) loss: 0.8784 (0.8789) time: 0.1572 data: 0.0730 max mem: 8233 +Train: [92] [4500/6250] eta: 0:04:31 lr: 0.000002 grad: 0.1411 (0.1602) loss: 0.8789 (0.8790) time: 0.1751 data: 0.0872 max mem: 8233 +Train: [92] [4600/6250] eta: 0:04:15 lr: 0.000002 grad: 0.1471 (0.1601) loss: 0.8824 (0.8790) time: 0.2229 data: 0.1424 max mem: 8233 +Train: [92] [4700/6250] eta: 0:03:59 lr: 0.000002 grad: 0.1487 (0.1601) loss: 0.8816 (0.8790) time: 0.1452 data: 0.0578 max mem: 8233 +Train: [92] [4800/6250] eta: 0:03:44 lr: 0.000002 grad: 0.1490 (0.1599) loss: 0.8784 (0.8790) time: 0.1600 data: 0.0783 max mem: 8233 +Train: [92] [4900/6250] eta: 0:03:28 lr: 0.000002 grad: 0.1579 (0.1599) loss: 0.8758 (0.8790) time: 0.1789 data: 0.0969 max mem: 8233 +Train: [92] [5000/6250] eta: 0:03:13 lr: 0.000002 grad: 0.1582 (0.1599) loss: 0.8788 (0.8790) time: 0.1570 data: 0.0839 max mem: 8233 +Train: [92] [5100/6250] eta: 0:02:58 lr: 0.000002 grad: 0.1637 (0.1600) loss: 0.8759 (0.8789) time: 0.2360 data: 0.1587 max mem: 8233 +Train: [92] [5200/6250] eta: 0:02:43 lr: 0.000002 grad: 0.1492 (0.1600) loss: 0.8794 (0.8789) time: 0.1812 data: 0.0964 max mem: 8233 +Train: [92] [5300/6250] eta: 0:02:27 lr: 0.000002 grad: 0.1580 (0.1599) loss: 0.8836 (0.8789) time: 0.1110 data: 0.0003 max mem: 8233 +Train: [92] [5400/6250] eta: 0:02:12 lr: 0.000002 grad: 0.1499 (0.1598) loss: 0.8819 (0.8790) time: 0.1496 data: 0.0688 max mem: 8233 +Train: [92] [5500/6250] eta: 0:01:56 lr: 0.000002 grad: 0.1492 (0.1598) loss: 0.8800 (0.8790) time: 0.1482 data: 0.0700 max mem: 8233 +Train: [92] [5600/6250] eta: 0:01:41 lr: 0.000002 grad: 0.1544 (0.1598) loss: 0.8737 (0.8790) time: 0.1647 data: 0.0877 max mem: 8233 +Train: [92] [5700/6250] eta: 0:01:25 lr: 0.000002 grad: 0.1535 (0.1598) loss: 0.8782 (0.8789) time: 0.1552 data: 0.0715 max mem: 8233 +Train: [92] [5800/6250] eta: 0:01:09 lr: 0.000002 grad: 0.1485 (0.1597) loss: 0.8852 (0.8790) time: 0.1498 data: 0.0825 max mem: 8233 +Train: [92] [5900/6250] eta: 0:00:54 lr: 0.000002 grad: 0.1530 (0.1596) loss: 0.8790 (0.8790) time: 0.1650 data: 0.0805 max mem: 8233 +Train: [92] [6000/6250] eta: 0:00:38 lr: 0.000002 grad: 0.1486 (0.1597) loss: 0.8739 (0.8790) time: 0.1356 data: 0.0520 max mem: 8233 +Train: [92] [6100/6250] eta: 0:00:23 lr: 0.000002 grad: 0.1535 (0.1596) loss: 0.8779 (0.8790) time: 0.1469 data: 0.0755 max mem: 8233 +Train: [92] [6200/6250] eta: 0:00:07 lr: 0.000002 grad: 0.1481 (0.1596) loss: 0.8805 (0.8790) time: 0.1819 data: 0.1021 max mem: 8233 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1487 (0.1595) loss: 0.8760 (0.8790) time: 0.1385 data: 0.0603 max mem: 8233 +Train: [92] Total time: 0:16:19 (0.1567 s / it) +Averaged stats: lr: 0.000002 grad: 0.1487 (0.1595) loss: 0.8760 (0.8790) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:04:36 loss: 0.8897 (0.8897) time: 4.4526 data: 4.3919 max mem: 8233 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8787 (0.8803) time: 0.1377 data: 0.1172 max mem: 8233 +Eval (hcp-train-subset): [92] Total time: 0:00:14 (0.2367 s / it) +Averaged stats (hcp-train-subset): loss: 0.8787 (0.8803) +Eval (hcp-val): [92] [ 0/62] eta: 0:06:52 loss: 0.8728 (0.8728) time: 6.6611 data: 6.6353 max mem: 8233 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8799 (0.8803) time: 0.1084 data: 0.0878 max mem: 8233 +Eval (hcp-val): [92] Total time: 0:00:14 (0.2416 s / it) +Averaged stats (hcp-val): loss: 0.8799 (0.8803) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 10:45:51 lr: 0.000002 grad: 0.1479 (0.1479) loss: 0.9009 (0.9009) time: 6.2002 data: 5.8346 max mem: 8233 +Train: [93] [ 100/6250] eta: 0:23:46 lr: 0.000002 grad: 0.1362 (0.1585) loss: 0.8904 (0.8900) time: 0.1712 data: 0.0582 max mem: 8233 +Train: [93] [ 200/6250] eta: 0:20:20 lr: 0.000002 grad: 0.1596 (0.1580) loss: 0.8887 (0.8894) time: 0.1832 data: 0.0768 max mem: 8233 +Train: [93] [ 300/6250] eta: 0:18:37 lr: 0.000002 grad: 0.1374 (0.1578) loss: 0.8886 (0.8890) time: 0.1597 data: 0.0524 max mem: 8233 +Train: [93] [ 400/6250] eta: 0:17:35 lr: 0.000002 grad: 0.1488 (0.1581) loss: 0.8843 (0.8879) time: 0.1731 data: 0.0714 max mem: 8233 +Train: [93] [ 500/6250] eta: 0:16:38 lr: 0.000002 grad: 0.1482 (0.1589) loss: 0.8818 (0.8865) time: 0.1361 data: 0.0391 max mem: 8233 +Train: [93] [ 600/6250] eta: 0:16:01 lr: 0.000002 grad: 0.1511 (0.1588) loss: 0.8865 (0.8861) time: 0.1566 data: 0.0518 max mem: 8233 +Train: [93] [ 700/6250] eta: 0:15:29 lr: 0.000002 grad: 0.1519 (0.1587) loss: 0.8801 (0.8858) time: 0.1344 data: 0.0331 max mem: 8233 +Train: [93] [ 800/6250] eta: 0:15:03 lr: 0.000002 grad: 0.1558 (0.1584) loss: 0.8796 (0.8856) time: 0.1567 data: 0.0634 max mem: 8233 +Train: [93] [ 900/6250] eta: 0:14:36 lr: 0.000002 grad: 0.1465 (0.1579) loss: 0.8814 (0.8856) time: 0.1519 data: 0.0689 max mem: 8233 +Train: [93] [1000/6250] eta: 0:14:15 lr: 0.000002 grad: 0.1434 (0.1572) loss: 0.8888 (0.8858) time: 0.1267 data: 0.0389 max mem: 8233 +Train: [93] [1100/6250] eta: 0:13:52 lr: 0.000002 grad: 0.1494 (0.1569) loss: 0.8846 (0.8855) time: 0.1374 data: 0.0535 max mem: 8233 +Train: [93] [1200/6250] eta: 0:13:35 lr: 0.000002 grad: 0.1476 (0.1564) loss: 0.8853 (0.8854) time: 0.1477 data: 0.0582 max mem: 8233 +Train: [93] [1300/6250] eta: 0:13:15 lr: 0.000002 grad: 0.1415 (0.1565) loss: 0.8851 (0.8852) time: 0.1594 data: 0.0808 max mem: 8233 +Train: [93] [1400/6250] eta: 0:12:56 lr: 0.000002 grad: 0.1428 (0.1560) loss: 0.8834 (0.8852) time: 0.1735 data: 0.0980 max mem: 8233 +Train: [93] [1500/6250] eta: 0:12:44 lr: 0.000002 grad: 0.1603 (0.1557) loss: 0.8837 (0.8851) time: 0.2165 data: 0.1407 max mem: 8233 +Train: [93] [1600/6250] eta: 0:12:24 lr: 0.000002 grad: 0.1441 (0.1553) loss: 0.8845 (0.8850) time: 0.1266 data: 0.0321 max mem: 8233 +Train: [93] [1700/6250] eta: 0:12:09 lr: 0.000002 grad: 0.1569 (0.1555) loss: 0.8809 (0.8848) time: 0.1578 data: 0.0808 max mem: 8233 +Train: [93] [1800/6250] eta: 0:11:50 lr: 0.000002 grad: 0.1487 (0.1556) loss: 0.8773 (0.8845) time: 0.1464 data: 0.0623 max mem: 8233 +Train: [93] [1900/6250] eta: 0:11:34 lr: 0.000002 grad: 0.1542 (0.1555) loss: 0.8794 (0.8843) time: 0.1671 data: 0.0994 max mem: 8233 +Train: [93] [2000/6250] eta: 0:11:26 lr: 0.000002 grad: 0.1509 (0.1557) loss: 0.8752 (0.8841) time: 0.1218 data: 0.0003 max mem: 8233 +Train: [93] [2100/6250] eta: 0:11:09 lr: 0.000002 grad: 0.1502 (0.1558) loss: 0.8832 (0.8839) time: 0.1548 data: 0.0673 max mem: 8233 +Train: [93] [2200/6250] eta: 0:10:51 lr: 0.000002 grad: 0.1559 (0.1560) loss: 0.8745 (0.8837) time: 0.1558 data: 0.0686 max mem: 8233 +Train: [93] [2300/6250] eta: 0:10:34 lr: 0.000001 grad: 0.1522 (0.1562) loss: 0.8807 (0.8835) time: 0.1486 data: 0.0640 max mem: 8233 +Train: [93] [2400/6250] eta: 0:10:18 lr: 0.000001 grad: 0.1483 (0.1564) loss: 0.8772 (0.8834) time: 0.1165 data: 0.0302 max mem: 8233 +Train: [93] [2500/6250] eta: 0:10:01 lr: 0.000001 grad: 0.1517 (0.1565) loss: 0.8804 (0.8832) time: 0.1325 data: 0.0393 max mem: 8233 +Train: [93] [2600/6250] eta: 0:09:44 lr: 0.000001 grad: 0.1458 (0.1566) loss: 0.8817 (0.8830) time: 0.1717 data: 0.0861 max mem: 8233 +Train: [93] [2700/6250] eta: 0:09:28 lr: 0.000001 grad: 0.1517 (0.1569) loss: 0.8796 (0.8828) time: 0.1371 data: 0.0601 max mem: 8233 +Train: [93] [2800/6250] eta: 0:09:12 lr: 0.000001 grad: 0.1518 (0.1570) loss: 0.8809 (0.8827) time: 0.1808 data: 0.0959 max mem: 8233 +Train: [93] [2900/6250] eta: 0:08:57 lr: 0.000001 grad: 0.1606 (0.1571) loss: 0.8729 (0.8825) time: 0.1720 data: 0.0861 max mem: 8233 +Train: [93] [3000/6250] eta: 0:08:40 lr: 0.000001 grad: 0.1557 (0.1573) loss: 0.8790 (0.8823) time: 0.1685 data: 0.0944 max mem: 8233 +Train: [93] [3100/6250] eta: 0:08:25 lr: 0.000001 grad: 0.1492 (0.1575) loss: 0.8757 (0.8821) time: 0.1650 data: 0.0762 max mem: 8233 +Train: [93] [3200/6250] eta: 0:08:09 lr: 0.000001 grad: 0.1535 (0.1577) loss: 0.8802 (0.8820) time: 0.1412 data: 0.0503 max mem: 8233 +Train: [93] [3300/6250] eta: 0:07:54 lr: 0.000001 grad: 0.1541 (0.1578) loss: 0.8780 (0.8818) time: 0.1727 data: 0.0889 max mem: 8233 +Train: [93] [3400/6250] eta: 0:07:37 lr: 0.000001 grad: 0.1597 (0.1579) loss: 0.8745 (0.8816) time: 0.1539 data: 0.0659 max mem: 8233 +Train: [93] [3500/6250] eta: 0:07:21 lr: 0.000001 grad: 0.1568 (0.1583) loss: 0.8747 (0.8814) time: 0.1601 data: 0.0704 max mem: 8233 +Train: [93] [3600/6250] eta: 0:07:05 lr: 0.000001 grad: 0.1684 (0.1586) loss: 0.8777 (0.8812) time: 0.1789 data: 0.0905 max mem: 8233 +Train: [93] [3700/6250] eta: 0:06:47 lr: 0.000001 grad: 0.1527 (0.1587) loss: 0.8748 (0.8810) time: 0.1396 data: 0.0548 max mem: 8233 +Train: [93] [3800/6250] eta: 0:06:31 lr: 0.000001 grad: 0.1490 (0.1588) loss: 0.8804 (0.8809) time: 0.1580 data: 0.0605 max mem: 8233 +Train: [93] [3900/6250] eta: 0:06:14 lr: 0.000001 grad: 0.1644 (0.1589) loss: 0.8797 (0.8808) time: 0.1502 data: 0.0582 max mem: 8233 +Train: [93] [4000/6250] eta: 0:05:58 lr: 0.000001 grad: 0.1645 (0.1590) loss: 0.8776 (0.8807) time: 0.1387 data: 0.0596 max mem: 8233 +Train: [93] [4100/6250] eta: 0:05:42 lr: 0.000001 grad: 0.1511 (0.1592) loss: 0.8762 (0.8806) time: 0.1750 data: 0.0865 max mem: 8233 +Train: [93] [4200/6250] eta: 0:05:26 lr: 0.000001 grad: 0.1486 (0.1594) loss: 0.8763 (0.8804) time: 0.1663 data: 0.0752 max mem: 8233 +Train: [93] [4300/6250] eta: 0:05:10 lr: 0.000001 grad: 0.1527 (0.1594) loss: 0.8760 (0.8804) time: 0.1689 data: 0.0790 max mem: 8233 +Train: [93] [4400/6250] eta: 0:04:54 lr: 0.000001 grad: 0.1433 (0.1593) loss: 0.8768 (0.8803) time: 0.1546 data: 0.0779 max mem: 8233 +Train: [93] [4500/6250] eta: 0:04:38 lr: 0.000001 grad: 0.1474 (0.1594) loss: 0.8823 (0.8803) time: 0.1527 data: 0.0694 max mem: 8233 +Train: [93] [4600/6250] eta: 0:04:22 lr: 0.000001 grad: 0.1543 (0.1594) loss: 0.8763 (0.8802) time: 0.1555 data: 0.0708 max mem: 8233 +Train: [93] [4700/6250] eta: 0:04:06 lr: 0.000001 grad: 0.1661 (0.1595) loss: 0.8783 (0.8802) time: 0.1581 data: 0.0764 max mem: 8233 +Train: [93] [4800/6250] eta: 0:03:50 lr: 0.000001 grad: 0.1546 (0.1596) loss: 0.8753 (0.8801) time: 0.1570 data: 0.0815 max mem: 8233 +Train: [93] [4900/6250] eta: 0:03:34 lr: 0.000001 grad: 0.1491 (0.1596) loss: 0.8761 (0.8800) time: 0.1499 data: 0.0621 max mem: 8233 +Train: [93] [5000/6250] eta: 0:03:18 lr: 0.000001 grad: 0.1529 (0.1596) loss: 0.8769 (0.8800) time: 0.1633 data: 0.0742 max mem: 8233 +Train: [93] [5100/6250] eta: 0:03:02 lr: 0.000001 grad: 0.1506 (0.1597) loss: 0.8761 (0.8800) time: 0.1504 data: 0.0727 max mem: 8233 +Train: [93] [5200/6250] eta: 0:02:46 lr: 0.000001 grad: 0.1514 (0.1598) loss: 0.8785 (0.8799) time: 0.1470 data: 0.0602 max mem: 8233 +Train: [93] [5300/6250] eta: 0:02:30 lr: 0.000001 grad: 0.1515 (0.1597) loss: 0.8751 (0.8799) time: 0.1685 data: 0.0803 max mem: 8233 +Train: [93] [5400/6250] eta: 0:02:14 lr: 0.000001 grad: 0.1465 (0.1597) loss: 0.8837 (0.8799) time: 0.1598 data: 0.0839 max mem: 8233 +Train: [93] [5500/6250] eta: 0:01:58 lr: 0.000001 grad: 0.1492 (0.1597) loss: 0.8797 (0.8798) time: 0.1117 data: 0.0312 max mem: 8233 +Train: [93] [5600/6250] eta: 0:01:43 lr: 0.000001 grad: 0.1466 (0.1596) loss: 0.8789 (0.8798) time: 0.1670 data: 0.0868 max mem: 8233 +Train: [93] [5700/6250] eta: 0:01:27 lr: 0.000001 grad: 0.1587 (0.1597) loss: 0.8809 (0.8797) time: 0.1643 data: 0.0691 max mem: 8233 +Train: [93] [5800/6250] eta: 0:01:11 lr: 0.000001 grad: 0.1491 (0.1597) loss: 0.8778 (0.8797) time: 0.1511 data: 0.0579 max mem: 8233 +Train: [93] [5900/6250] eta: 0:00:55 lr: 0.000001 grad: 0.1596 (0.1598) loss: 0.8798 (0.8796) time: 0.1594 data: 0.0728 max mem: 8233 +Train: [93] [6000/6250] eta: 0:00:39 lr: 0.000001 grad: 0.1611 (0.1598) loss: 0.8764 (0.8796) time: 0.1310 data: 0.0547 max mem: 8233 +Train: [93] [6100/6250] eta: 0:00:23 lr: 0.000001 grad: 0.1581 (0.1599) loss: 0.8789 (0.8795) time: 0.1836 data: 0.1047 max mem: 8233 +Train: [93] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1604 (0.1600) loss: 0.8785 (0.8795) time: 0.1462 data: 0.0643 max mem: 8233 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1574 (0.1600) loss: 0.8753 (0.8795) time: 0.1380 data: 0.0565 max mem: 8233 +Train: [93] Total time: 0:16:36 (0.1595 s / it) +Averaged stats: lr: 0.000001 grad: 0.1574 (0.1600) loss: 0.8753 (0.8795) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:05:46 loss: 0.8902 (0.8902) time: 5.5918 data: 5.5658 max mem: 8233 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8788 (0.8800) time: 0.1445 data: 0.1240 max mem: 8233 +Eval (hcp-train-subset): [93] Total time: 0:00:13 (0.2257 s / it) +Averaged stats (hcp-train-subset): loss: 0.8788 (0.8800) +Eval (hcp-val): [93] [ 0/62] eta: 0:06:44 loss: 0.8759 (0.8759) time: 6.5216 data: 6.4956 max mem: 8233 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8798 (0.8801) time: 0.1344 data: 0.1134 max mem: 8233 +Eval (hcp-val): [93] Total time: 0:00:14 (0.2419 s / it) +Averaged stats (hcp-val): loss: 0.8798 (0.8801) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 12:31:14 lr: 0.000001 grad: 0.1640 (0.1640) loss: 0.8961 (0.8961) time: 7.2120 data: 7.0751 max mem: 8233 +Train: [94] [ 100/6250] eta: 0:24:17 lr: 0.000001 grad: 0.1698 (0.1728) loss: 0.8775 (0.8750) time: 0.1802 data: 0.0746 max mem: 8233 +Train: [94] [ 200/6250] eta: 0:19:53 lr: 0.000001 grad: 0.1786 (0.1722) loss: 0.8770 (0.8765) time: 0.1494 data: 0.0361 max mem: 8233 +Train: [94] [ 300/6250] eta: 0:18:48 lr: 0.000001 grad: 0.1578 (0.1724) loss: 0.8787 (0.8762) time: 0.1872 data: 0.0907 max mem: 8233 +Train: [94] [ 400/6250] eta: 0:17:41 lr: 0.000001 grad: 0.1672 (0.1721) loss: 0.8720 (0.8759) time: 0.1574 data: 0.0535 max mem: 8233 +Train: [94] [ 500/6250] eta: 0:16:52 lr: 0.000001 grad: 0.1721 (0.1729) loss: 0.8786 (0.8755) time: 0.1549 data: 0.0447 max mem: 8233 +Train: [94] [ 600/6250] eta: 0:16:16 lr: 0.000001 grad: 0.1674 (0.1731) loss: 0.8804 (0.8753) time: 0.1438 data: 0.0502 max mem: 8233 +Train: [94] [ 700/6250] eta: 0:15:45 lr: 0.000001 grad: 0.1565 (0.1728) loss: 0.8777 (0.8754) time: 0.1500 data: 0.0522 max mem: 8233 +Train: [94] [ 800/6250] eta: 0:15:21 lr: 0.000001 grad: 0.1658 (0.1724) loss: 0.8710 (0.8752) time: 0.1719 data: 0.0833 max mem: 8233 +Train: [94] [ 900/6250] eta: 0:15:03 lr: 0.000001 grad: 0.1572 (0.1715) loss: 0.8748 (0.8754) time: 0.1913 data: 0.1153 max mem: 8233 +Train: [94] [1000/6250] eta: 0:14:39 lr: 0.000001 grad: 0.1531 (0.1706) loss: 0.8783 (0.8757) time: 0.1897 data: 0.0358 max mem: 8233 +Train: [94] [1100/6250] eta: 0:14:24 lr: 0.000001 grad: 0.1526 (0.1696) loss: 0.8728 (0.8760) time: 0.1857 data: 0.1174 max mem: 8233 +Train: [94] [1200/6250] eta: 0:13:57 lr: 0.000001 grad: 0.1508 (0.1687) loss: 0.8835 (0.8763) time: 0.1537 data: 0.0624 max mem: 8233 +Train: [94] [1300/6250] eta: 0:13:36 lr: 0.000001 grad: 0.1538 (0.1679) loss: 0.8789 (0.8765) time: 0.1496 data: 0.0650 max mem: 8233 +Train: [94] [1400/6250] eta: 0:13:19 lr: 0.000001 grad: 0.1548 (0.1676) loss: 0.8840 (0.8768) time: 0.1235 data: 0.0393 max mem: 8233 +Train: [94] [1500/6250] eta: 0:13:02 lr: 0.000001 grad: 0.1462 (0.1670) loss: 0.8861 (0.8770) time: 0.1449 data: 0.0703 max mem: 8233 +Train: [94] [1600/6250] eta: 0:12:43 lr: 0.000001 grad: 0.1448 (0.1661) loss: 0.8806 (0.8772) time: 0.1402 data: 0.0677 max mem: 8233 +Train: [94] [1700/6250] eta: 0:12:23 lr: 0.000001 grad: 0.1477 (0.1655) loss: 0.8830 (0.8774) time: 0.1392 data: 0.0502 max mem: 8233 +Train: [94] [1800/6250] eta: 0:12:03 lr: 0.000001 grad: 0.1570 (0.1648) loss: 0.8757 (0.8776) time: 0.1504 data: 0.0721 max mem: 8233 +Train: [94] [1900/6250] eta: 0:11:45 lr: 0.000001 grad: 0.1577 (0.1644) loss: 0.8753 (0.8777) time: 0.1508 data: 0.0649 max mem: 8233 +Train: [94] [2000/6250] eta: 0:11:28 lr: 0.000001 grad: 0.1505 (0.1639) loss: 0.8775 (0.8778) time: 0.1574 data: 0.0806 max mem: 8233 +Train: [94] [2100/6250] eta: 0:11:11 lr: 0.000001 grad: 0.1515 (0.1635) loss: 0.8792 (0.8779) time: 0.1897 data: 0.1183 max mem: 8233 +Train: [94] [2200/6250] eta: 0:10:52 lr: 0.000001 grad: 0.1495 (0.1631) loss: 0.8734 (0.8778) time: 0.1506 data: 0.0706 max mem: 8233 +Train: [94] [2300/6250] eta: 0:10:35 lr: 0.000001 grad: 0.1537 (0.1629) loss: 0.8775 (0.8778) time: 0.1369 data: 0.0488 max mem: 8233 +Train: [94] [2400/6250] eta: 0:10:18 lr: 0.000001 grad: 0.1613 (0.1628) loss: 0.8770 (0.8777) time: 0.1727 data: 0.0969 max mem: 8233 +Train: [94] [2500/6250] eta: 0:10:02 lr: 0.000001 grad: 0.1612 (0.1627) loss: 0.8809 (0.8778) time: 0.1916 data: 0.1078 max mem: 8233 +Train: [94] [2600/6250] eta: 0:09:45 lr: 0.000001 grad: 0.1447 (0.1624) loss: 0.8793 (0.8778) time: 0.1898 data: 0.1240 max mem: 8233 +Train: [94] [2700/6250] eta: 0:09:28 lr: 0.000001 grad: 0.1539 (0.1623) loss: 0.8792 (0.8779) time: 0.1594 data: 0.0767 max mem: 8233 +Train: [94] [2800/6250] eta: 0:09:11 lr: 0.000001 grad: 0.1487 (0.1622) loss: 0.8809 (0.8779) time: 0.1294 data: 0.0460 max mem: 8233 +Train: [94] [2900/6250] eta: 0:08:55 lr: 0.000001 grad: 0.1489 (0.1621) loss: 0.8767 (0.8779) time: 0.1562 data: 0.0736 max mem: 8233 +Train: [94] [3000/6250] eta: 0:08:37 lr: 0.000001 grad: 0.1547 (0.1620) loss: 0.8817 (0.8780) time: 0.1468 data: 0.0634 max mem: 8233 +Train: [94] [3100/6250] eta: 0:08:22 lr: 0.000001 grad: 0.1506 (0.1618) loss: 0.8780 (0.8780) time: 0.1980 data: 0.1201 max mem: 8233 +Train: [94] [3200/6250] eta: 0:08:05 lr: 0.000001 grad: 0.1497 (0.1617) loss: 0.8733 (0.8780) time: 0.1379 data: 0.0532 max mem: 8233 +Train: [94] [3300/6250] eta: 0:07:50 lr: 0.000001 grad: 0.1510 (0.1617) loss: 0.8724 (0.8779) time: 0.1953 data: 0.1119 max mem: 8233 +Train: [94] [3400/6250] eta: 0:07:33 lr: 0.000001 grad: 0.1535 (0.1616) loss: 0.8753 (0.8780) time: 0.1485 data: 0.0592 max mem: 8233 +Train: [94] [3500/6250] eta: 0:07:17 lr: 0.000001 grad: 0.1469 (0.1615) loss: 0.8782 (0.8780) time: 0.1600 data: 0.0757 max mem: 8233 +Train: [94] [3600/6250] eta: 0:07:00 lr: 0.000001 grad: 0.1528 (0.1615) loss: 0.8730 (0.8780) time: 0.1436 data: 0.0607 max mem: 8233 +Train: [94] [3700/6250] eta: 0:06:44 lr: 0.000001 grad: 0.1514 (0.1615) loss: 0.8804 (0.8780) time: 0.1292 data: 0.0475 max mem: 8233 +Train: [94] [3800/6250] eta: 0:06:28 lr: 0.000001 grad: 0.1561 (0.1616) loss: 0.8767 (0.8779) time: 0.1632 data: 0.0861 max mem: 8233 +Train: [94] [3900/6250] eta: 0:06:11 lr: 0.000001 grad: 0.1461 (0.1615) loss: 0.8803 (0.8779) time: 0.1252 data: 0.0468 max mem: 8233 +Train: [94] [4000/6250] eta: 0:05:54 lr: 0.000001 grad: 0.1513 (0.1615) loss: 0.8788 (0.8780) time: 0.1697 data: 0.0828 max mem: 8233 +Train: [94] [4100/6250] eta: 0:05:38 lr: 0.000001 grad: 0.1586 (0.1616) loss: 0.8705 (0.8779) time: 0.1586 data: 0.0725 max mem: 8233 +Train: [94] [4200/6250] eta: 0:05:21 lr: 0.000001 grad: 0.1596 (0.1617) loss: 0.8794 (0.8779) time: 0.1526 data: 0.0659 max mem: 8233 +Train: [94] [4300/6250] eta: 0:05:05 lr: 0.000001 grad: 0.1496 (0.1618) loss: 0.8809 (0.8779) time: 0.1573 data: 0.0793 max mem: 8233 +Train: [94] [4400/6250] eta: 0:04:50 lr: 0.000001 grad: 0.1677 (0.1620) loss: 0.8806 (0.8779) time: 0.1662 data: 0.0847 max mem: 8233 +Train: [94] [4500/6250] eta: 0:04:34 lr: 0.000001 grad: 0.1634 (0.1621) loss: 0.8774 (0.8779) time: 0.1711 data: 0.0927 max mem: 8233 +Train: [94] [4600/6250] eta: 0:04:18 lr: 0.000001 grad: 0.1582 (0.1621) loss: 0.8750 (0.8780) time: 0.1477 data: 0.0577 max mem: 8233 +Train: [94] [4700/6250] eta: 0:04:02 lr: 0.000001 grad: 0.1557 (0.1621) loss: 0.8775 (0.8780) time: 0.1513 data: 0.0622 max mem: 8233 +Train: [94] [4800/6250] eta: 0:03:46 lr: 0.000001 grad: 0.1603 (0.1623) loss: 0.8835 (0.8781) time: 0.1424 data: 0.0630 max mem: 8233 +Train: [94] [4900/6250] eta: 0:03:30 lr: 0.000001 grad: 0.1617 (0.1624) loss: 0.8802 (0.8781) time: 0.1390 data: 0.0655 max mem: 8233 +Train: [94] [5000/6250] eta: 0:03:15 lr: 0.000001 grad: 0.1674 (0.1626) loss: 0.8804 (0.8782) time: 0.1445 data: 0.0674 max mem: 8233 +Train: [94] [5100/6250] eta: 0:02:59 lr: 0.000001 grad: 0.1542 (0.1627) loss: 0.8813 (0.8783) time: 0.1691 data: 0.1053 max mem: 8233 +Train: [94] [5200/6250] eta: 0:02:43 lr: 0.000001 grad: 0.1627 (0.1626) loss: 0.8766 (0.8783) time: 0.1378 data: 0.0565 max mem: 8233 +Train: [94] [5300/6250] eta: 0:02:27 lr: 0.000001 grad: 0.1607 (0.1627) loss: 0.8782 (0.8783) time: 0.1260 data: 0.0436 max mem: 8233 +Train: [94] [5400/6250] eta: 0:02:11 lr: 0.000001 grad: 0.1634 (0.1628) loss: 0.8802 (0.8783) time: 0.1518 data: 0.0675 max mem: 8233 +Train: [94] [5500/6250] eta: 0:01:55 lr: 0.000001 grad: 0.1601 (0.1630) loss: 0.8786 (0.8783) time: 0.1476 data: 0.0685 max mem: 8233 +Train: [94] [5600/6250] eta: 0:01:40 lr: 0.000001 grad: 0.1568 (0.1632) loss: 0.8794 (0.8783) time: 0.1381 data: 0.0361 max mem: 8233 +Train: [94] [5700/6250] eta: 0:01:24 lr: 0.000001 grad: 0.1585 (0.1632) loss: 0.8862 (0.8784) time: 0.1264 data: 0.0407 max mem: 8233 +Train: [94] [5800/6250] eta: 0:01:09 lr: 0.000001 grad: 0.1528 (0.1633) loss: 0.8745 (0.8784) time: 0.1421 data: 0.0546 max mem: 8233 +Train: [94] [5900/6250] eta: 0:00:53 lr: 0.000001 grad: 0.1705 (0.1634) loss: 0.8776 (0.8784) time: 0.1246 data: 0.0413 max mem: 8233 +Train: [94] [6000/6250] eta: 0:00:38 lr: 0.000001 grad: 0.1646 (0.1635) loss: 0.8747 (0.8784) time: 0.1336 data: 0.0480 max mem: 8233 +Train: [94] [6100/6250] eta: 0:00:22 lr: 0.000001 grad: 0.1541 (0.1634) loss: 0.8737 (0.8784) time: 0.1282 data: 0.0410 max mem: 8233 +Train: [94] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1504 (0.1634) loss: 0.8860 (0.8784) time: 0.1546 data: 0.0741 max mem: 8233 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1566 (0.1634) loss: 0.8795 (0.8784) time: 0.1430 data: 0.0596 max mem: 8233 +Train: [94] Total time: 0:15:58 (0.1533 s / it) +Averaged stats: lr: 0.000001 grad: 0.1566 (0.1634) loss: 0.8795 (0.8784) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:05:17 loss: 0.8895 (0.8895) time: 5.1194 data: 5.0913 max mem: 8233 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8769 (0.8799) time: 0.1091 data: 0.0889 max mem: 8233 +Eval (hcp-train-subset): [94] Total time: 0:00:13 (0.2150 s / it) +Averaged stats (hcp-train-subset): loss: 0.8769 (0.8799) +Making plots (hcp-train-subset): example=2 +Eval (hcp-val): [94] [ 0/62] eta: 0:04:33 loss: 0.8778 (0.8778) time: 4.4041 data: 4.3143 max mem: 8233 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8804 (0.8801) time: 0.1263 data: 0.1045 max mem: 8233 +Eval (hcp-val): [94] Total time: 0:00:14 (0.2415 s / it) +Averaged stats (hcp-val): loss: 0.8804 (0.8801) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 10:25:00 lr: 0.000001 grad: 0.1289 (0.1289) loss: 0.9091 (0.9091) time: 6.0001 data: 5.6211 max mem: 8233 +Train: [95] [ 100/6250] eta: 0:22:56 lr: 0.000001 grad: 0.1673 (0.1688) loss: 0.8878 (0.8872) time: 0.1717 data: 0.0678 max mem: 8233 +Train: [95] [ 200/6250] eta: 0:19:29 lr: 0.000001 grad: 0.1522 (0.1727) loss: 0.8756 (0.8804) time: 0.1726 data: 0.0660 max mem: 8233 +Train: [95] [ 300/6250] eta: 0:17:46 lr: 0.000001 grad: 0.1600 (0.1734) loss: 0.8724 (0.8797) time: 0.1491 data: 0.0466 max mem: 8233 +Train: [95] [ 400/6250] eta: 0:16:46 lr: 0.000001 grad: 0.1511 (0.1723) loss: 0.8807 (0.8799) time: 0.1765 data: 0.0752 max mem: 8233 +Train: [95] [ 500/6250] eta: 0:15:59 lr: 0.000001 grad: 0.1470 (0.1712) loss: 0.8854 (0.8803) time: 0.1499 data: 0.0616 max mem: 8233 +Train: [95] [ 600/6250] eta: 0:15:24 lr: 0.000001 grad: 0.1574 (0.1685) loss: 0.8796 (0.8802) time: 0.1319 data: 0.0377 max mem: 8233 +Train: [95] [ 700/6250] eta: 0:14:58 lr: 0.000001 grad: 0.1541 (0.1676) loss: 0.8829 (0.8802) time: 0.1429 data: 0.0552 max mem: 8233 +Train: [95] [ 800/6250] eta: 0:14:31 lr: 0.000001 grad: 0.1515 (0.1669) loss: 0.8790 (0.8804) time: 0.1441 data: 0.0380 max mem: 8233 +Train: [95] [ 900/6250] eta: 0:14:03 lr: 0.000001 grad: 0.1421 (0.1663) loss: 0.8799 (0.8802) time: 0.1474 data: 0.0551 max mem: 8233 +Train: [95] [1000/6250] eta: 0:13:45 lr: 0.000001 grad: 0.1437 (0.1655) loss: 0.8815 (0.8800) time: 0.1500 data: 0.0686 max mem: 8233 +Train: [95] [1100/6250] eta: 0:13:22 lr: 0.000001 grad: 0.1523 (0.1651) loss: 0.8794 (0.8798) time: 0.1461 data: 0.0602 max mem: 8233 +Train: [95] [1200/6250] eta: 0:13:05 lr: 0.000001 grad: 0.1521 (0.1646) loss: 0.8780 (0.8797) time: 0.1635 data: 0.0957 max mem: 8233 +Train: [95] [1300/6250] eta: 0:12:47 lr: 0.000001 grad: 0.1464 (0.1643) loss: 0.8795 (0.8796) time: 0.1618 data: 0.0834 max mem: 8233 +Train: [95] [1400/6250] eta: 0:12:26 lr: 0.000001 grad: 0.1535 (0.1643) loss: 0.8744 (0.8794) time: 0.1184 data: 0.0267 max mem: 8233 +Train: [95] [1500/6250] eta: 0:12:08 lr: 0.000001 grad: 0.1618 (0.1649) loss: 0.8779 (0.8793) time: 0.1221 data: 0.0396 max mem: 8233 +Train: [95] [1600/6250] eta: 0:11:50 lr: 0.000001 grad: 0.1584 (0.1650) loss: 0.8825 (0.8792) time: 0.1519 data: 0.0701 max mem: 8233 +Train: [95] [1700/6250] eta: 0:11:33 lr: 0.000001 grad: 0.1573 (0.1654) loss: 0.8745 (0.8790) time: 0.1626 data: 0.0901 max mem: 8233 +Train: [95] [1800/6250] eta: 0:11:16 lr: 0.000001 grad: 0.1590 (0.1654) loss: 0.8762 (0.8789) time: 0.1369 data: 0.0417 max mem: 8233 +Train: [95] [1900/6250] eta: 0:11:00 lr: 0.000001 grad: 0.1634 (0.1656) loss: 0.8779 (0.8788) time: 0.1547 data: 0.0696 max mem: 8233 +Train: [95] [2000/6250] eta: 0:10:44 lr: 0.000001 grad: 0.1551 (0.1656) loss: 0.8770 (0.8786) time: 0.1488 data: 0.0659 max mem: 8233 +Train: [95] [2100/6250] eta: 0:10:27 lr: 0.000001 grad: 0.1652 (0.1658) loss: 0.8746 (0.8785) time: 0.1170 data: 0.0241 max mem: 8233 +Train: [95] [2200/6250] eta: 0:10:12 lr: 0.000001 grad: 0.1599 (0.1662) loss: 0.8771 (0.8784) time: 0.1529 data: 0.0803 max mem: 8233 +Train: [95] [2300/6250] eta: 0:09:56 lr: 0.000001 grad: 0.1534 (0.1661) loss: 0.8802 (0.8784) time: 0.1323 data: 0.0547 max mem: 8233 +Train: [95] [2400/6250] eta: 0:09:41 lr: 0.000001 grad: 0.1518 (0.1663) loss: 0.8850 (0.8784) time: 0.1587 data: 0.0770 max mem: 8233 +Train: [95] [2500/6250] eta: 0:09:26 lr: 0.000001 grad: 0.1561 (0.1662) loss: 0.8789 (0.8783) time: 0.1513 data: 0.0774 max mem: 8233 +Train: [95] [2600/6250] eta: 0:09:10 lr: 0.000001 grad: 0.1658 (0.1664) loss: 0.8763 (0.8783) time: 0.1274 data: 0.0410 max mem: 8233 +Train: [95] [2700/6250] eta: 0:08:55 lr: 0.000001 grad: 0.1577 (0.1667) loss: 0.8815 (0.8783) time: 0.1072 data: 0.0251 max mem: 8233 +Train: [95] [2800/6250] eta: 0:08:39 lr: 0.000001 grad: 0.1674 (0.1668) loss: 0.8761 (0.8783) time: 0.1489 data: 0.0830 max mem: 8233 +Train: [95] [2900/6250] eta: 0:08:26 lr: 0.000001 grad: 0.1530 (0.1668) loss: 0.8765 (0.8782) time: 0.1616 data: 0.0827 max mem: 8233 +Train: [95] [3000/6250] eta: 0:08:11 lr: 0.000001 grad: 0.1544 (0.1667) loss: 0.8763 (0.8783) time: 0.1556 data: 0.0734 max mem: 8233 +Train: [95] [3100/6250] eta: 0:07:56 lr: 0.000001 grad: 0.1607 (0.1668) loss: 0.8822 (0.8783) time: 0.1471 data: 0.0734 max mem: 8233 +Train: [95] [3200/6250] eta: 0:07:41 lr: 0.000001 grad: 0.1562 (0.1667) loss: 0.8765 (0.8783) time: 0.1536 data: 0.0653 max mem: 8233 +Train: [95] [3300/6250] eta: 0:07:26 lr: 0.000001 grad: 0.1619 (0.1667) loss: 0.8811 (0.8783) time: 0.1475 data: 0.0714 max mem: 8233 +Train: [95] [3400/6250] eta: 0:07:11 lr: 0.000001 grad: 0.1511 (0.1666) loss: 0.8827 (0.8783) time: 0.1543 data: 0.0734 max mem: 8233 +Train: [95] [3500/6250] eta: 0:06:56 lr: 0.000001 grad: 0.1552 (0.1663) loss: 0.8847 (0.8785) time: 0.1569 data: 0.0879 max mem: 8233 +Train: [95] [3600/6250] eta: 0:06:41 lr: 0.000001 grad: 0.1548 (0.1663) loss: 0.8834 (0.8785) time: 0.1525 data: 0.0709 max mem: 8233 +Train: [95] [3700/6250] eta: 0:06:26 lr: 0.000001 grad: 0.1574 (0.1660) loss: 0.8786 (0.8786) time: 0.1440 data: 0.0620 max mem: 8233 +Train: [95] [3800/6250] eta: 0:06:11 lr: 0.000001 grad: 0.1585 (0.1660) loss: 0.8775 (0.8786) time: 0.1619 data: 0.0888 max mem: 8233 +Train: [95] [3900/6250] eta: 0:05:55 lr: 0.000001 grad: 0.1598 (0.1659) loss: 0.8830 (0.8787) time: 0.1458 data: 0.0581 max mem: 8233 +Train: [95] [4000/6250] eta: 0:05:39 lr: 0.000001 grad: 0.1572 (0.1658) loss: 0.8830 (0.8788) time: 0.1393 data: 0.0606 max mem: 8233 +Train: [95] [4100/6250] eta: 0:05:23 lr: 0.000001 grad: 0.1558 (0.1656) loss: 0.8866 (0.8789) time: 0.1421 data: 0.0558 max mem: 8233 +Train: [95] [4200/6250] eta: 0:05:08 lr: 0.000001 grad: 0.1618 (0.1656) loss: 0.8797 (0.8790) time: 0.1498 data: 0.0679 max mem: 8233 +Train: [95] [4300/6250] eta: 0:04:53 lr: 0.000001 grad: 0.1562 (0.1656) loss: 0.8818 (0.8790) time: 0.1302 data: 0.0535 max mem: 8233 +Train: [95] [4400/6250] eta: 0:04:38 lr: 0.000001 grad: 0.1665 (0.1655) loss: 0.8784 (0.8790) time: 0.1217 data: 0.0421 max mem: 8233 +Train: [95] [4500/6250] eta: 0:04:23 lr: 0.000001 grad: 0.1475 (0.1654) loss: 0.8781 (0.8790) time: 0.1627 data: 0.0883 max mem: 8233 +Train: [95] [4600/6250] eta: 0:04:08 lr: 0.000001 grad: 0.1546 (0.1654) loss: 0.8844 (0.8790) time: 0.1511 data: 0.0778 max mem: 8233 +Train: [95] [4700/6250] eta: 0:03:53 lr: 0.000001 grad: 0.1509 (0.1652) loss: 0.8732 (0.8790) time: 0.1673 data: 0.0930 max mem: 8233 +Train: [95] [4800/6250] eta: 0:03:38 lr: 0.000001 grad: 0.1573 (0.1652) loss: 0.8795 (0.8790) time: 0.1511 data: 0.0609 max mem: 8233 +Train: [95] [4900/6250] eta: 0:03:24 lr: 0.000001 grad: 0.1560 (0.1650) loss: 0.8742 (0.8790) time: 0.1806 data: 0.0898 max mem: 8233 +Train: [95] [5000/6250] eta: 0:03:08 lr: 0.000001 grad: 0.1585 (0.1649) loss: 0.8760 (0.8790) time: 0.1539 data: 0.0642 max mem: 8233 +Train: [95] [5100/6250] eta: 0:02:53 lr: 0.000001 grad: 0.1543 (0.1649) loss: 0.8793 (0.8790) time: 0.1611 data: 0.0868 max mem: 8233 +Train: [95] [5200/6250] eta: 0:02:38 lr: 0.000001 grad: 0.1647 (0.1649) loss: 0.8753 (0.8790) time: 0.1647 data: 0.0874 max mem: 8233 +Train: [95] [5300/6250] eta: 0:02:23 lr: 0.000001 grad: 0.1662 (0.1648) loss: 0.8824 (0.8790) time: 0.1179 data: 0.0300 max mem: 8233 +Train: [95] [5400/6250] eta: 0:02:08 lr: 0.000001 grad: 0.1583 (0.1647) loss: 0.8777 (0.8790) time: 0.1512 data: 0.0789 max mem: 8233 +Train: [95] [5500/6250] eta: 0:01:52 lr: 0.000001 grad: 0.1486 (0.1646) loss: 0.8816 (0.8790) time: 0.1461 data: 0.0533 max mem: 8233 +Train: [95] [5600/6250] eta: 0:01:37 lr: 0.000001 grad: 0.1479 (0.1645) loss: 0.8809 (0.8790) time: 0.1593 data: 0.0793 max mem: 8233 +Train: [95] [5700/6250] eta: 0:01:22 lr: 0.000001 grad: 0.1500 (0.1644) loss: 0.8831 (0.8790) time: 0.1339 data: 0.0542 max mem: 8233 +Train: [95] [5800/6250] eta: 0:01:07 lr: 0.000001 grad: 0.1547 (0.1644) loss: 0.8773 (0.8790) time: 0.1437 data: 0.0661 max mem: 8233 +Train: [95] [5900/6250] eta: 0:00:52 lr: 0.000001 grad: 0.1547 (0.1643) loss: 0.8780 (0.8790) time: 0.1438 data: 0.0591 max mem: 8233 +Train: [95] [6000/6250] eta: 0:00:37 lr: 0.000001 grad: 0.1452 (0.1641) loss: 0.8822 (0.8791) time: 0.1509 data: 0.0766 max mem: 8233 +Train: [95] [6100/6250] eta: 0:00:22 lr: 0.000001 grad: 0.1517 (0.1640) loss: 0.8812 (0.8791) time: 0.1748 data: 0.0996 max mem: 8233 +Train: [95] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1559 (0.1640) loss: 0.8793 (0.8791) time: 0.1521 data: 0.0790 max mem: 8233 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1506 (0.1639) loss: 0.8815 (0.8791) time: 0.1320 data: 0.0628 max mem: 8233 +Train: [95] Total time: 0:15:42 (0.1508 s / it) +Averaged stats: lr: 0.000001 grad: 0.1506 (0.1639) loss: 0.8815 (0.8791) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:06:26 loss: 0.8907 (0.8907) time: 6.2377 data: 6.2111 max mem: 8233 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8759 (0.8799) time: 0.1114 data: 0.0907 max mem: 8233 +Eval (hcp-train-subset): [95] Total time: 0:00:14 (0.2282 s / it) +Averaged stats (hcp-train-subset): loss: 0.8759 (0.8799) +Eval (hcp-val): [95] [ 0/62] eta: 0:05:14 loss: 0.8747 (0.8747) time: 5.0795 data: 5.0508 max mem: 8233 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8800 (0.8800) time: 0.1226 data: 0.1019 max mem: 8233 +Eval (hcp-val): [95] Total time: 0:00:14 (0.2324 s / it) +Averaged stats (hcp-val): loss: 0.8800 (0.8800) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 8:59:11 lr: 0.000001 grad: 0.1060 (0.1060) loss: 0.9079 (0.9079) time: 5.1763 data: 4.8317 max mem: 8233 +Train: [96] [ 100/6250] eta: 0:22:52 lr: 0.000001 grad: 0.1486 (0.1798) loss: 0.8908 (0.8869) time: 0.1555 data: 0.0503 max mem: 8233 +Train: [96] [ 200/6250] eta: 0:19:27 lr: 0.000001 grad: 0.1474 (0.1694) loss: 0.8796 (0.8844) time: 0.1639 data: 0.0632 max mem: 8233 +Train: [96] [ 300/6250] eta: 0:17:55 lr: 0.000001 grad: 0.1504 (0.1693) loss: 0.8809 (0.8808) time: 0.1604 data: 0.0637 max mem: 8233 +Train: [96] [ 400/6250] eta: 0:17:06 lr: 0.000001 grad: 0.1590 (0.1706) loss: 0.8728 (0.8786) time: 0.1631 data: 0.0540 max mem: 8233 +Train: [96] [ 500/6250] eta: 0:16:20 lr: 0.000001 grad: 0.1602 (0.1729) loss: 0.8667 (0.8773) time: 0.1588 data: 0.0600 max mem: 8233 +Train: [96] [ 600/6250] eta: 0:15:44 lr: 0.000001 grad: 0.1595 (0.1738) loss: 0.8771 (0.8765) time: 0.1785 data: 0.1017 max mem: 8233 +Train: [96] [ 700/6250] eta: 0:15:09 lr: 0.000001 grad: 0.1632 (0.1735) loss: 0.8684 (0.8760) time: 0.1365 data: 0.0498 max mem: 8233 +Train: [96] [ 800/6250] eta: 0:14:42 lr: 0.000001 grad: 0.1665 (0.1738) loss: 0.8742 (0.8757) time: 0.1472 data: 0.0532 max mem: 8233 +Train: [96] [ 900/6250] eta: 0:14:20 lr: 0.000001 grad: 0.1604 (0.1738) loss: 0.8768 (0.8753) time: 0.1524 data: 0.0544 max mem: 8233 +Train: [96] [1000/6250] eta: 0:13:58 lr: 0.000001 grad: 0.1796 (0.1738) loss: 0.8750 (0.8752) time: 0.1586 data: 0.0815 max mem: 8233 +Train: [96] [1100/6250] eta: 0:13:36 lr: 0.000000 grad: 0.1567 (0.1730) loss: 0.8774 (0.8751) time: 0.1257 data: 0.0415 max mem: 8233 +Train: [96] [1200/6250] eta: 0:13:18 lr: 0.000000 grad: 0.1530 (0.1726) loss: 0.8764 (0.8751) time: 0.1380 data: 0.0589 max mem: 8233 +Train: [96] [1300/6250] eta: 0:12:58 lr: 0.000000 grad: 0.1652 (0.1720) loss: 0.8717 (0.8752) time: 0.1307 data: 0.0415 max mem: 8233 +Train: [96] [1400/6250] eta: 0:12:40 lr: 0.000000 grad: 0.1554 (0.1715) loss: 0.8786 (0.8752) time: 0.1511 data: 0.0786 max mem: 8233 +Train: [96] [1500/6250] eta: 0:12:22 lr: 0.000000 grad: 0.1673 (0.1714) loss: 0.8746 (0.8753) time: 0.1429 data: 0.0539 max mem: 8233 +Train: [96] [1600/6250] eta: 0:12:05 lr: 0.000000 grad: 0.1655 (0.1713) loss: 0.8812 (0.8753) time: 0.1537 data: 0.0791 max mem: 8233 +Train: [96] [1700/6250] eta: 0:11:52 lr: 0.000000 grad: 0.1506 (0.1711) loss: 0.8746 (0.8753) time: 0.1495 data: 0.0602 max mem: 8233 +Train: [96] [1800/6250] eta: 0:11:33 lr: 0.000000 grad: 0.1624 (0.1709) loss: 0.8796 (0.8753) time: 0.1458 data: 0.0680 max mem: 8233 +Train: [96] [1900/6250] eta: 0:11:16 lr: 0.000000 grad: 0.1608 (0.1710) loss: 0.8825 (0.8754) time: 0.1324 data: 0.0556 max mem: 8233 +Train: [96] [2000/6250] eta: 0:10:59 lr: 0.000000 grad: 0.1593 (0.1712) loss: 0.8731 (0.8755) time: 0.1459 data: 0.0688 max mem: 8233 +Train: [96] [2100/6250] eta: 0:10:42 lr: 0.000000 grad: 0.1659 (0.1708) loss: 0.8809 (0.8756) time: 0.1350 data: 0.0447 max mem: 8233 +Train: [96] [2200/6250] eta: 0:10:27 lr: 0.000000 grad: 0.1493 (0.1704) loss: 0.8833 (0.8757) time: 0.1310 data: 0.0462 max mem: 8233 +Train: [96] [2300/6250] eta: 0:10:10 lr: 0.000000 grad: 0.1683 (0.1702) loss: 0.8760 (0.8759) time: 0.1516 data: 0.0576 max mem: 8233 +Train: [96] [2400/6250] eta: 0:09:54 lr: 0.000000 grad: 0.1603 (0.1699) loss: 0.8766 (0.8759) time: 0.1718 data: 0.0884 max mem: 8233 +Train: [96] [2500/6250] eta: 0:09:38 lr: 0.000000 grad: 0.1544 (0.1698) loss: 0.8767 (0.8760) time: 0.1269 data: 0.0396 max mem: 8233 +Train: [96] [2600/6250] eta: 0:09:22 lr: 0.000000 grad: 0.1513 (0.1696) loss: 0.8759 (0.8760) time: 0.1431 data: 0.0535 max mem: 8233 +Train: [96] [2700/6250] eta: 0:09:06 lr: 0.000000 grad: 0.1602 (0.1695) loss: 0.8727 (0.8759) time: 0.1760 data: 0.0951 max mem: 8233 +Train: [96] [2800/6250] eta: 0:08:50 lr: 0.000000 grad: 0.1496 (0.1692) loss: 0.8786 (0.8760) time: 0.1386 data: 0.0451 max mem: 8233 +Train: [96] [2900/6250] eta: 0:08:37 lr: 0.000000 grad: 0.1519 (0.1691) loss: 0.8742 (0.8760) time: 0.1712 data: 0.0889 max mem: 8233 +Train: [96] [3000/6250] eta: 0:08:21 lr: 0.000000 grad: 0.1498 (0.1689) loss: 0.8809 (0.8761) time: 0.1727 data: 0.0915 max mem: 8233 +Train: [96] [3100/6250] eta: 0:08:06 lr: 0.000000 grad: 0.1520 (0.1687) loss: 0.8734 (0.8761) time: 0.1527 data: 0.0800 max mem: 8233 +Train: [96] [3200/6250] eta: 0:07:51 lr: 0.000000 grad: 0.1516 (0.1685) loss: 0.8800 (0.8761) time: 0.1399 data: 0.0612 max mem: 8233 +Train: [96] [3300/6250] eta: 0:07:36 lr: 0.000000 grad: 0.1529 (0.1683) loss: 0.8778 (0.8761) time: 0.1550 data: 0.0741 max mem: 8233 +Train: [96] [3400/6250] eta: 0:07:21 lr: 0.000000 grad: 0.1572 (0.1681) loss: 0.8789 (0.8762) time: 0.1651 data: 0.0899 max mem: 8233 +Train: [96] [3500/6250] eta: 0:07:05 lr: 0.000000 grad: 0.1499 (0.1679) loss: 0.8795 (0.8762) time: 0.1547 data: 0.0691 max mem: 8233 +Train: [96] [3600/6250] eta: 0:06:50 lr: 0.000000 grad: 0.1548 (0.1675) loss: 0.8762 (0.8763) time: 0.1391 data: 0.0482 max mem: 8233 +Train: [96] [3700/6250] eta: 0:06:34 lr: 0.000000 grad: 0.1417 (0.1672) loss: 0.8797 (0.8764) time: 0.1404 data: 0.0518 max mem: 8233 +Train: [96] [3800/6250] eta: 0:06:17 lr: 0.000000 grad: 0.1517 (0.1669) loss: 0.8795 (0.8764) time: 0.1398 data: 0.0538 max mem: 8233 +Train: [96] [3900/6250] eta: 0:06:01 lr: 0.000000 grad: 0.1496 (0.1668) loss: 0.8791 (0.8764) time: 0.1430 data: 0.0503 max mem: 8233 +Train: [96] [4000/6250] eta: 0:05:45 lr: 0.000000 grad: 0.1550 (0.1666) loss: 0.8813 (0.8764) time: 0.1423 data: 0.0573 max mem: 8233 +Train: [96] [4100/6250] eta: 0:05:30 lr: 0.000000 grad: 0.1442 (0.1665) loss: 0.8793 (0.8764) time: 0.1280 data: 0.0365 max mem: 8233 +Train: [96] [4200/6250] eta: 0:05:14 lr: 0.000000 grad: 0.1650 (0.1665) loss: 0.8766 (0.8764) time: 0.1484 data: 0.0707 max mem: 8233 +Train: [96] [4300/6250] eta: 0:04:58 lr: 0.000000 grad: 0.1594 (0.1665) loss: 0.8752 (0.8764) time: 0.1341 data: 0.0547 max mem: 8233 +Train: [96] [4400/6250] eta: 0:04:43 lr: 0.000000 grad: 0.1560 (0.1664) loss: 0.8760 (0.8764) time: 0.1446 data: 0.0656 max mem: 8233 +Train: [96] [4500/6250] eta: 0:04:28 lr: 0.000000 grad: 0.1635 (0.1665) loss: 0.8715 (0.8763) time: 0.1692 data: 0.0874 max mem: 8233 +Train: [96] [4600/6250] eta: 0:04:12 lr: 0.000000 grad: 0.1524 (0.1664) loss: 0.8789 (0.8764) time: 0.1411 data: 0.0492 max mem: 8233 +Train: [96] [4700/6250] eta: 0:03:57 lr: 0.000000 grad: 0.1653 (0.1664) loss: 0.8758 (0.8764) time: 0.1547 data: 0.0756 max mem: 8233 +Train: [96] [4800/6250] eta: 0:03:42 lr: 0.000000 grad: 0.1655 (0.1664) loss: 0.8789 (0.8764) time: 0.1695 data: 0.0850 max mem: 8233 +Train: [96] [4900/6250] eta: 0:03:27 lr: 0.000000 grad: 0.1640 (0.1665) loss: 0.8788 (0.8764) time: 0.1602 data: 0.0778 max mem: 8233 +Train: [96] [5000/6250] eta: 0:03:11 lr: 0.000000 grad: 0.1452 (0.1664) loss: 0.8800 (0.8765) time: 0.1635 data: 0.0749 max mem: 8233 +Train: [96] [5100/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1578 (0.1664) loss: 0.8813 (0.8765) time: 0.1333 data: 0.0435 max mem: 8233 +Train: [96] [5200/6250] eta: 0:02:40 lr: 0.000000 grad: 0.1564 (0.1663) loss: 0.8819 (0.8766) time: 0.1526 data: 0.0674 max mem: 8233 +Train: [96] [5300/6250] eta: 0:02:25 lr: 0.000000 grad: 0.1538 (0.1662) loss: 0.8821 (0.8767) time: 0.1500 data: 0.0713 max mem: 8233 +Train: [96] [5400/6250] eta: 0:02:10 lr: 0.000000 grad: 0.1597 (0.1661) loss: 0.8768 (0.8768) time: 0.1600 data: 0.0764 max mem: 8233 +Train: [96] [5500/6250] eta: 0:01:54 lr: 0.000000 grad: 0.1487 (0.1660) loss: 0.8738 (0.8768) time: 0.1350 data: 0.0602 max mem: 8233 +Train: [96] [5600/6250] eta: 0:01:39 lr: 0.000000 grad: 0.1564 (0.1659) loss: 0.8774 (0.8769) time: 0.1517 data: 0.0719 max mem: 8233 +Train: [96] [5700/6250] eta: 0:01:23 lr: 0.000000 grad: 0.1546 (0.1657) loss: 0.8778 (0.8769) time: 0.1304 data: 0.0374 max mem: 8233 +Train: [96] [5800/6250] eta: 0:01:08 lr: 0.000000 grad: 0.1544 (0.1657) loss: 0.8843 (0.8770) time: 0.1521 data: 0.0661 max mem: 8233 +Train: [96] [5900/6250] eta: 0:00:53 lr: 0.000000 grad: 0.1541 (0.1656) loss: 0.8797 (0.8770) time: 0.1792 data: 0.1057 max mem: 8233 +Train: [96] [6000/6250] eta: 0:00:38 lr: 0.000000 grad: 0.1560 (0.1654) loss: 0.8838 (0.8771) time: 0.1532 data: 0.0670 max mem: 8233 +Train: [96] [6100/6250] eta: 0:00:22 lr: 0.000000 grad: 0.1586 (0.1653) loss: 0.8789 (0.8771) time: 0.1429 data: 0.0549 max mem: 8233 +Train: [96] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1464 (0.1652) loss: 0.8779 (0.8771) time: 0.1816 data: 0.1126 max mem: 8233 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1515 (0.1651) loss: 0.8752 (0.8771) time: 0.1623 data: 0.0842 max mem: 8233 +Train: [96] Total time: 0:15:59 (0.1535 s / it) +Averaged stats: lr: 0.000000 grad: 0.1515 (0.1651) loss: 0.8752 (0.8771) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:05:42 loss: 0.8883 (0.8883) time: 5.5311 data: 5.5056 max mem: 8233 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8778 (0.8800) time: 0.1010 data: 0.0793 max mem: 8233 +Eval (hcp-train-subset): [96] Total time: 0:00:14 (0.2282 s / it) +Averaged stats (hcp-train-subset): loss: 0.8778 (0.8800) +Eval (hcp-val): [96] [ 0/62] eta: 0:06:06 loss: 0.8773 (0.8773) time: 5.9114 data: 5.8856 max mem: 8233 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8787 (0.8799) time: 0.1164 data: 0.0959 max mem: 8233 +Eval (hcp-val): [96] Total time: 0:00:14 (0.2310 s / it) +Averaged stats (hcp-val): loss: 0.8787 (0.8799) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 10:19:31 lr: 0.000000 grad: 0.3927 (0.3927) loss: 0.8660 (0.8660) time: 5.9475 data: 5.5889 max mem: 8233 +Train: [97] [ 100/6250] eta: 0:23:16 lr: 0.000000 grad: 0.1468 (0.1821) loss: 0.8876 (0.8864) time: 0.1683 data: 0.0621 max mem: 8233 +Train: [97] [ 200/6250] eta: 0:19:52 lr: 0.000000 grad: 0.1603 (0.1782) loss: 0.8795 (0.8844) time: 0.1708 data: 0.0573 max mem: 8233 +Train: [97] [ 300/6250] eta: 0:18:21 lr: 0.000000 grad: 0.1694 (0.1772) loss: 0.8749 (0.8825) time: 0.1604 data: 0.0529 max mem: 8233 +Train: [97] [ 400/6250] eta: 0:17:22 lr: 0.000000 grad: 0.1566 (0.1760) loss: 0.8809 (0.8819) time: 0.1584 data: 0.0583 max mem: 8233 +Train: [97] [ 500/6250] eta: 0:16:29 lr: 0.000000 grad: 0.1679 (0.1752) loss: 0.8788 (0.8811) time: 0.1608 data: 0.0598 max mem: 8233 +Train: [97] [ 600/6250] eta: 0:15:46 lr: 0.000000 grad: 0.1505 (0.1740) loss: 0.8773 (0.8808) time: 0.1533 data: 0.0448 max mem: 8233 +Train: [97] [ 700/6250] eta: 0:15:14 lr: 0.000000 grad: 0.1564 (0.1728) loss: 0.8819 (0.8804) time: 0.1449 data: 0.0456 max mem: 8233 +Train: [97] [ 800/6250] eta: 0:14:47 lr: 0.000000 grad: 0.1557 (0.1721) loss: 0.8812 (0.8803) time: 0.1190 data: 0.0295 max mem: 8233 +Train: [97] [ 900/6250] eta: 0:14:30 lr: 0.000000 grad: 0.1530 (0.1717) loss: 0.8764 (0.8797) time: 0.1697 data: 0.0861 max mem: 8233 +Train: [97] [1000/6250] eta: 0:14:13 lr: 0.000000 grad: 0.1565 (0.1707) loss: 0.8747 (0.8793) time: 0.1916 data: 0.1083 max mem: 8233 +Train: [97] [1100/6250] eta: 0:13:45 lr: 0.000000 grad: 0.1585 (0.1699) loss: 0.8757 (0.8790) time: 0.1204 data: 0.0433 max mem: 8233 +Train: [97] [1200/6250] eta: 0:13:25 lr: 0.000000 grad: 0.1622 (0.1695) loss: 0.8771 (0.8789) time: 0.1342 data: 0.0557 max mem: 8233 +Train: [97] [1300/6250] eta: 0:13:08 lr: 0.000000 grad: 0.1624 (0.1694) loss: 0.8729 (0.8786) time: 0.1543 data: 0.0833 max mem: 8233 +Train: [97] [1400/6250] eta: 0:12:48 lr: 0.000000 grad: 0.1643 (0.1693) loss: 0.8762 (0.8785) time: 0.1564 data: 0.0784 max mem: 8233 +Train: [97] [1500/6250] eta: 0:12:29 lr: 0.000000 grad: 0.1608 (0.1695) loss: 0.8783 (0.8784) time: 0.1447 data: 0.0608 max mem: 8233 +Train: [97] [1600/6250] eta: 0:12:09 lr: 0.000000 grad: 0.1556 (0.1695) loss: 0.8777 (0.8783) time: 0.1370 data: 0.0590 max mem: 8233 +Train: [97] [1700/6250] eta: 0:11:52 lr: 0.000000 grad: 0.1493 (0.1691) loss: 0.8736 (0.8782) time: 0.1537 data: 0.0702 max mem: 8233 +Train: [97] [1800/6250] eta: 0:11:34 lr: 0.000000 grad: 0.1607 (0.1689) loss: 0.8749 (0.8782) time: 0.1358 data: 0.0380 max mem: 8233 +Train: [97] [1900/6250] eta: 0:11:18 lr: 0.000000 grad: 0.1555 (0.1686) loss: 0.8821 (0.8782) time: 0.1700 data: 0.0935 max mem: 8233 +Train: [97] [2000/6250] eta: 0:11:01 lr: 0.000000 grad: 0.1500 (0.1684) loss: 0.8728 (0.8781) time: 0.1504 data: 0.0606 max mem: 8233 +Train: [97] [2100/6250] eta: 0:10:45 lr: 0.000000 grad: 0.1567 (0.1680) loss: 0.8775 (0.8781) time: 0.1243 data: 0.0402 max mem: 8233 +Train: [97] [2200/6250] eta: 0:10:27 lr: 0.000000 grad: 0.1542 (0.1677) loss: 0.8823 (0.8782) time: 0.1515 data: 0.0589 max mem: 8233 +Train: [97] [2300/6250] eta: 0:10:10 lr: 0.000000 grad: 0.1489 (0.1671) loss: 0.8828 (0.8784) time: 0.1485 data: 0.0691 max mem: 8233 +Train: [97] [2400/6250] eta: 0:09:55 lr: 0.000000 grad: 0.1602 (0.1668) loss: 0.8787 (0.8785) time: 0.1779 data: 0.1005 max mem: 8233 +Train: [97] [2500/6250] eta: 0:09:38 lr: 0.000000 grad: 0.1556 (0.1666) loss: 0.8806 (0.8786) time: 0.1503 data: 0.0625 max mem: 8233 +Train: [97] [2600/6250] eta: 0:09:23 lr: 0.000000 grad: 0.1580 (0.1663) loss: 0.8759 (0.8786) time: 0.1915 data: 0.1098 max mem: 8233 +Train: [97] [2700/6250] eta: 0:09:06 lr: 0.000000 grad: 0.1549 (0.1661) loss: 0.8834 (0.8787) time: 0.1334 data: 0.0457 max mem: 8233 +Train: [97] [2800/6250] eta: 0:08:50 lr: 0.000000 grad: 0.1547 (0.1658) loss: 0.8774 (0.8787) time: 0.1440 data: 0.0819 max mem: 8233 +Train: [97] [2900/6250] eta: 0:08:36 lr: 0.000000 grad: 0.1557 (0.1657) loss: 0.8778 (0.8788) time: 0.1352 data: 0.0584 max mem: 8233 +Train: [97] [3000/6250] eta: 0:08:21 lr: 0.000000 grad: 0.1599 (0.1658) loss: 0.8732 (0.8787) time: 0.1676 data: 0.0853 max mem: 8233 +Train: [97] [3100/6250] eta: 0:08:05 lr: 0.000000 grad: 0.1548 (0.1656) loss: 0.8864 (0.8788) time: 0.1461 data: 0.0551 max mem: 8233 +Train: [97] [3200/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1492 (0.1655) loss: 0.8754 (0.8787) time: 0.1515 data: 0.0630 max mem: 8233 +Train: [97] [3300/6250] eta: 0:07:35 lr: 0.000000 grad: 0.1525 (0.1656) loss: 0.8744 (0.8786) time: 0.1588 data: 0.0797 max mem: 8233 +Train: [97] [3400/6250] eta: 0:07:20 lr: 0.000000 grad: 0.1539 (0.1659) loss: 0.8752 (0.8785) time: 0.1387 data: 0.0407 max mem: 8233 +Train: [97] [3500/6250] eta: 0:07:04 lr: 0.000000 grad: 0.1672 (0.1660) loss: 0.8779 (0.8785) time: 0.1513 data: 0.0439 max mem: 8233 +Train: [97] [3600/6250] eta: 0:06:48 lr: 0.000000 grad: 0.1554 (0.1660) loss: 0.8790 (0.8784) time: 0.1559 data: 0.0723 max mem: 8233 +Train: [97] [3700/6250] eta: 0:06:32 lr: 0.000000 grad: 0.1638 (0.1661) loss: 0.8794 (0.8784) time: 0.1359 data: 0.0616 max mem: 8233 +Train: [97] [3800/6250] eta: 0:06:16 lr: 0.000000 grad: 0.1630 (0.1663) loss: 0.8785 (0.8784) time: 0.1530 data: 0.0762 max mem: 8233 +Train: [97] [3900/6250] eta: 0:06:00 lr: 0.000000 grad: 0.1611 (0.1663) loss: 0.8817 (0.8784) time: 0.1317 data: 0.0455 max mem: 8233 +Train: [97] [4000/6250] eta: 0:05:44 lr: 0.000000 grad: 0.1551 (0.1663) loss: 0.8727 (0.8783) time: 0.1195 data: 0.0398 max mem: 8233 +Train: [97] [4100/6250] eta: 0:05:29 lr: 0.000000 grad: 0.1660 (0.1663) loss: 0.8753 (0.8782) time: 0.1376 data: 0.0623 max mem: 8233 +Train: [97] [4200/6250] eta: 0:05:13 lr: 0.000000 grad: 0.1544 (0.1664) loss: 0.8814 (0.8782) time: 0.1356 data: 0.0521 max mem: 8233 +Train: [97] [4300/6250] eta: 0:04:58 lr: 0.000000 grad: 0.1680 (0.1664) loss: 0.8735 (0.8781) time: 0.1643 data: 0.0902 max mem: 8233 +Train: [97] [4400/6250] eta: 0:04:43 lr: 0.000000 grad: 0.1605 (0.1663) loss: 0.8728 (0.8781) time: 0.1701 data: 0.0896 max mem: 8233 +Train: [97] [4500/6250] eta: 0:04:27 lr: 0.000000 grad: 0.1679 (0.1661) loss: 0.8790 (0.8781) time: 0.1385 data: 0.0577 max mem: 8233 +Train: [97] [4600/6250] eta: 0:04:12 lr: 0.000000 grad: 0.1501 (0.1660) loss: 0.8753 (0.8780) time: 0.1624 data: 0.0926 max mem: 8233 +Train: [97] [4700/6250] eta: 0:03:58 lr: 0.000000 grad: 0.1545 (0.1661) loss: 0.8793 (0.8780) time: 0.2050 data: 0.1297 max mem: 8233 +Train: [97] [4800/6250] eta: 0:03:42 lr: 0.000000 grad: 0.1566 (0.1661) loss: 0.8788 (0.8780) time: 0.1482 data: 0.0613 max mem: 8233 +Train: [97] [4900/6250] eta: 0:03:27 lr: 0.000000 grad: 0.1511 (0.1661) loss: 0.8747 (0.8780) time: 0.1513 data: 0.0712 max mem: 8233 +Train: [97] [5000/6250] eta: 0:03:11 lr: 0.000000 grad: 0.1546 (0.1660) loss: 0.8720 (0.8780) time: 0.1501 data: 0.0637 max mem: 8233 +Train: [97] [5100/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1589 (0.1659) loss: 0.8775 (0.8779) time: 0.1518 data: 0.0641 max mem: 8233 +Train: [97] [5200/6250] eta: 0:02:40 lr: 0.000000 grad: 0.1530 (0.1659) loss: 0.8728 (0.8778) time: 0.1450 data: 0.0421 max mem: 8233 +Train: [97] [5300/6250] eta: 0:02:25 lr: 0.000000 grad: 0.1580 (0.1658) loss: 0.8802 (0.8778) time: 0.1651 data: 0.0750 max mem: 8233 +Train: [97] [5400/6250] eta: 0:02:09 lr: 0.000000 grad: 0.1530 (0.1657) loss: 0.8762 (0.8778) time: 0.1263 data: 0.0424 max mem: 8233 +Train: [97] [5500/6250] eta: 0:01:54 lr: 0.000000 grad: 0.1505 (0.1655) loss: 0.8832 (0.8778) time: 0.1344 data: 0.0432 max mem: 8233 +Train: [97] [5600/6250] eta: 0:01:39 lr: 0.000000 grad: 0.1534 (0.1653) loss: 0.8794 (0.8778) time: 0.1584 data: 0.0801 max mem: 8233 +Train: [97] [5700/6250] eta: 0:01:24 lr: 0.000000 grad: 0.1413 (0.1651) loss: 0.8803 (0.8778) time: 0.1790 data: 0.0950 max mem: 8233 +Train: [97] [5800/6250] eta: 0:01:08 lr: 0.000000 grad: 0.1524 (0.1649) loss: 0.8815 (0.8779) time: 0.1678 data: 0.0832 max mem: 8233 +Train: [97] [5900/6250] eta: 0:00:53 lr: 0.000000 grad: 0.1565 (0.1649) loss: 0.8806 (0.8779) time: 0.1563 data: 0.0743 max mem: 8233 +Train: [97] [6000/6250] eta: 0:00:38 lr: 0.000000 grad: 0.1530 (0.1648) loss: 0.8775 (0.8779) time: 0.1969 data: 0.1185 max mem: 8233 +Train: [97] [6100/6250] eta: 0:00:22 lr: 0.000000 grad: 0.1552 (0.1647) loss: 0.8806 (0.8779) time: 0.1378 data: 0.0571 max mem: 8233 +Train: [97] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1545 (0.1646) loss: 0.8768 (0.8779) time: 0.1034 data: 0.0208 max mem: 8233 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1443 (0.1646) loss: 0.8795 (0.8780) time: 0.2739 data: 0.1853 max mem: 8233 +Train: [97] Total time: 0:16:00 (0.1537 s / it) +Averaged stats: lr: 0.000000 grad: 0.1443 (0.1646) loss: 0.8795 (0.8780) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:05:42 loss: 0.8897 (0.8897) time: 5.5321 data: 5.5053 max mem: 8233 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8782 (0.8798) time: 0.1339 data: 0.1133 max mem: 8233 +Eval (hcp-train-subset): [97] Total time: 0:00:14 (0.2312 s / it) +Averaged stats (hcp-train-subset): loss: 0.8782 (0.8798) +Eval (hcp-val): [97] [ 0/62] eta: 0:05:29 loss: 0.8741 (0.8741) time: 5.3183 data: 5.2696 max mem: 8233 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8790 (0.8798) time: 0.1172 data: 0.0969 max mem: 8233 +Eval (hcp-val): [97] Total time: 0:00:14 (0.2288 s / it) +Averaged stats (hcp-val): loss: 0.8790 (0.8798) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 12:23:01 lr: 0.000000 grad: 0.1936 (0.1936) loss: 0.9010 (0.9010) time: 7.1331 data: 7.0380 max mem: 8233 +Train: [98] [ 100/6250] eta: 0:23:05 lr: 0.000000 grad: 0.1730 (0.1818) loss: 0.8809 (0.8900) time: 0.1919 data: 0.0752 max mem: 8233 +Train: [98] [ 200/6250] eta: 0:19:46 lr: 0.000000 grad: 0.1575 (0.1784) loss: 0.8814 (0.8855) time: 0.1660 data: 0.0485 max mem: 8233 +Train: [98] [ 300/6250] eta: 0:18:21 lr: 0.000000 grad: 0.1476 (0.1710) loss: 0.8795 (0.8846) time: 0.1665 data: 0.0674 max mem: 8233 +Train: [98] [ 400/6250] eta: 0:17:27 lr: 0.000000 grad: 0.1435 (0.1671) loss: 0.8837 (0.8842) time: 0.1700 data: 0.0627 max mem: 8233 +Train: [98] [ 500/6250] eta: 0:16:49 lr: 0.000000 grad: 0.1518 (0.1650) loss: 0.8857 (0.8837) time: 0.1499 data: 0.0546 max mem: 8233 +Train: [98] [ 600/6250] eta: 0:16:08 lr: 0.000000 grad: 0.1464 (0.1643) loss: 0.8791 (0.8831) time: 0.1390 data: 0.0439 max mem: 8233 +Train: [98] [ 700/6250] eta: 0:15:34 lr: 0.000000 grad: 0.1534 (0.1632) loss: 0.8780 (0.8824) time: 0.1533 data: 0.0641 max mem: 8233 +Train: [98] [ 800/6250] eta: 0:15:02 lr: 0.000000 grad: 0.1569 (0.1626) loss: 0.8848 (0.8822) time: 0.1470 data: 0.0616 max mem: 8233 +Train: [98] [ 900/6250] eta: 0:14:40 lr: 0.000000 grad: 0.1499 (0.1626) loss: 0.8842 (0.8822) time: 0.1554 data: 0.0662 max mem: 8233 +Train: [98] [1000/6250] eta: 0:14:15 lr: 0.000000 grad: 0.1634 (0.1628) loss: 0.8822 (0.8820) time: 0.1351 data: 0.0504 max mem: 8233 +Train: [98] [1100/6250] eta: 0:13:51 lr: 0.000000 grad: 0.1560 (0.1633) loss: 0.8805 (0.8818) time: 0.1351 data: 0.0521 max mem: 8233 +Train: [98] [1200/6250] eta: 0:13:29 lr: 0.000000 grad: 0.1565 (0.1635) loss: 0.8856 (0.8816) time: 0.1574 data: 0.0811 max mem: 8233 +Train: [98] [1300/6250] eta: 0:13:07 lr: 0.000000 grad: 0.1563 (0.1634) loss: 0.8854 (0.8816) time: 0.1511 data: 0.0627 max mem: 8233 +Train: [98] [1400/6250] eta: 0:12:53 lr: 0.000000 grad: 0.1436 (0.1631) loss: 0.8819 (0.8816) time: 0.2150 data: 0.1370 max mem: 8233 +Train: [98] [1500/6250] eta: 0:12:32 lr: 0.000000 grad: 0.1502 (0.1629) loss: 0.8766 (0.8815) time: 0.1575 data: 0.0816 max mem: 8233 +Train: [98] [1600/6250] eta: 0:12:13 lr: 0.000000 grad: 0.1550 (0.1629) loss: 0.8846 (0.8816) time: 0.1355 data: 0.0571 max mem: 8233 +Train: [98] [1700/6250] eta: 0:11:55 lr: 0.000000 grad: 0.1515 (0.1630) loss: 0.8768 (0.8815) time: 0.1642 data: 0.0811 max mem: 8233 +Train: [98] [1800/6250] eta: 0:11:38 lr: 0.000000 grad: 0.1482 (0.1630) loss: 0.8809 (0.8814) time: 0.1557 data: 0.0737 max mem: 8233 +Train: [98] [1900/6250] eta: 0:11:19 lr: 0.000000 grad: 0.1540 (0.1630) loss: 0.8821 (0.8813) time: 0.1455 data: 0.0632 max mem: 8233 +Train: [98] [2000/6250] eta: 0:11:02 lr: 0.000000 grad: 0.1507 (0.1629) loss: 0.8817 (0.8812) time: 0.1328 data: 0.0497 max mem: 8233 +Train: [98] [2100/6250] eta: 0:10:47 lr: 0.000000 grad: 0.1608 (0.1629) loss: 0.8779 (0.8811) time: 0.1193 data: 0.0158 max mem: 8233 +Train: [98] [2200/6250] eta: 0:10:30 lr: 0.000000 grad: 0.1562 (0.1628) loss: 0.8798 (0.8810) time: 0.1493 data: 0.0680 max mem: 8233 +Train: [98] [2300/6250] eta: 0:10:14 lr: 0.000000 grad: 0.1587 (0.1627) loss: 0.8777 (0.8809) time: 0.1478 data: 0.0634 max mem: 8233 +Train: [98] [2400/6250] eta: 0:09:59 lr: 0.000000 grad: 0.1542 (0.1626) loss: 0.8769 (0.8808) time: 0.1419 data: 0.0618 max mem: 8233 +Train: [98] [2500/6250] eta: 0:09:43 lr: 0.000000 grad: 0.1517 (0.1625) loss: 0.8785 (0.8808) time: 0.1677 data: 0.0817 max mem: 8233 +Train: [98] [2600/6250] eta: 0:09:27 lr: 0.000000 grad: 0.1536 (0.1624) loss: 0.8817 (0.8808) time: 0.1426 data: 0.0670 max mem: 8233 +Train: [98] [2700/6250] eta: 0:09:11 lr: 0.000000 grad: 0.1532 (0.1622) loss: 0.8755 (0.8807) time: 0.1484 data: 0.0797 max mem: 8233 +Train: [98] [2800/6250] eta: 0:08:54 lr: 0.000000 grad: 0.1699 (0.1625) loss: 0.8784 (0.8806) time: 0.1458 data: 0.0653 max mem: 8233 +Train: [98] [2900/6250] eta: 0:08:39 lr: 0.000000 grad: 0.1583 (0.1625) loss: 0.8776 (0.8805) time: 0.1155 data: 0.0388 max mem: 8233 +Train: [98] [3000/6250] eta: 0:08:24 lr: 0.000000 grad: 0.1576 (0.1626) loss: 0.8785 (0.8803) time: 0.1554 data: 0.0660 max mem: 8233 +Train: [98] [3100/6250] eta: 0:08:09 lr: 0.000000 grad: 0.1523 (0.1626) loss: 0.8817 (0.8803) time: 0.1344 data: 0.0612 max mem: 8233 +Train: [98] [3200/6250] eta: 0:07:54 lr: 0.000000 grad: 0.1543 (0.1625) loss: 0.8796 (0.8802) time: 0.1511 data: 0.0708 max mem: 8233 +Train: [98] [3300/6250] eta: 0:07:39 lr: 0.000000 grad: 0.1586 (0.1625) loss: 0.8818 (0.8802) time: 0.1663 data: 0.0794 max mem: 8233 +Train: [98] [3400/6250] eta: 0:07:23 lr: 0.000000 grad: 0.1577 (0.1625) loss: 0.8756 (0.8802) time: 0.1294 data: 0.0451 max mem: 8233 +Train: [98] [3500/6250] eta: 0:07:08 lr: 0.000000 grad: 0.1538 (0.1624) loss: 0.8804 (0.8802) time: 0.1622 data: 0.0773 max mem: 8233 +Train: [98] [3600/6250] eta: 0:06:52 lr: 0.000000 grad: 0.1544 (0.1623) loss: 0.8787 (0.8801) time: 0.1489 data: 0.0620 max mem: 8233 +Train: [98] [3700/6250] eta: 0:06:36 lr: 0.000000 grad: 0.1542 (0.1624) loss: 0.8827 (0.8802) time: 0.1579 data: 0.0747 max mem: 8233 +Train: [98] [3800/6250] eta: 0:06:20 lr: 0.000000 grad: 0.1568 (0.1623) loss: 0.8760 (0.8802) time: 0.1584 data: 0.0791 max mem: 8233 +Train: [98] [3900/6250] eta: 0:06:04 lr: 0.000000 grad: 0.1574 (0.1624) loss: 0.8815 (0.8802) time: 0.1637 data: 0.0770 max mem: 8233 +Train: [98] [4000/6250] eta: 0:05:48 lr: 0.000000 grad: 0.1516 (0.1624) loss: 0.8764 (0.8802) time: 0.1339 data: 0.0466 max mem: 8233 +Train: [98] [4100/6250] eta: 0:05:32 lr: 0.000000 grad: 0.1459 (0.1623) loss: 0.8843 (0.8801) time: 0.1507 data: 0.0706 max mem: 8233 +Train: [98] [4200/6250] eta: 0:05:16 lr: 0.000000 grad: 0.1490 (0.1623) loss: 0.8785 (0.8801) time: 0.1552 data: 0.0736 max mem: 8233 +Train: [98] [4300/6250] eta: 0:05:01 lr: 0.000000 grad: 0.1535 (0.1622) loss: 0.8757 (0.8801) time: 0.1571 data: 0.0769 max mem: 8233 +Train: [98] [4400/6250] eta: 0:04:45 lr: 0.000000 grad: 0.1503 (0.1621) loss: 0.8783 (0.8801) time: 0.1532 data: 0.0775 max mem: 8233 +Train: [98] [4500/6250] eta: 0:04:30 lr: 0.000000 grad: 0.1530 (0.1620) loss: 0.8762 (0.8801) time: 0.1550 data: 0.0719 max mem: 8233 +Train: [98] [4600/6250] eta: 0:04:15 lr: 0.000000 grad: 0.1484 (0.1619) loss: 0.8793 (0.8801) time: 0.1664 data: 0.0976 max mem: 8233 +Train: [98] [4700/6250] eta: 0:03:59 lr: 0.000000 grad: 0.1545 (0.1619) loss: 0.8800 (0.8801) time: 0.1372 data: 0.0607 max mem: 8233 +Train: [98] [4800/6250] eta: 0:03:43 lr: 0.000000 grad: 0.1587 (0.1619) loss: 0.8805 (0.8801) time: 0.1357 data: 0.0594 max mem: 8233 +Train: [98] [4900/6250] eta: 0:03:28 lr: 0.000000 grad: 0.1511 (0.1618) loss: 0.8792 (0.8801) time: 0.1665 data: 0.0920 max mem: 8233 +Train: [98] [5000/6250] eta: 0:03:13 lr: 0.000000 grad: 0.1465 (0.1617) loss: 0.8816 (0.8800) time: 0.1618 data: 0.0767 max mem: 8233 +Train: [98] [5100/6250] eta: 0:02:57 lr: 0.000000 grad: 0.1538 (0.1617) loss: 0.8782 (0.8800) time: 0.0997 data: 0.0120 max mem: 8233 +Train: [98] [5200/6250] eta: 0:02:42 lr: 0.000000 grad: 0.1498 (0.1616) loss: 0.8788 (0.8800) time: 0.1222 data: 0.0434 max mem: 8233 +Train: [98] [5300/6250] eta: 0:02:26 lr: 0.000000 grad: 0.1499 (0.1615) loss: 0.8840 (0.8800) time: 0.1252 data: 0.0386 max mem: 8233 +Train: [98] [5400/6250] eta: 0:02:11 lr: 0.000000 grad: 0.1505 (0.1615) loss: 0.8770 (0.8800) time: 0.1532 data: 0.0633 max mem: 8233 +Train: [98] [5500/6250] eta: 0:01:55 lr: 0.000000 grad: 0.1502 (0.1615) loss: 0.8760 (0.8800) time: 0.1580 data: 0.0608 max mem: 8233 +Train: [98] [5600/6250] eta: 0:01:40 lr: 0.000000 grad: 0.1505 (0.1616) loss: 0.8775 (0.8799) time: 0.1586 data: 0.0762 max mem: 8233 +Train: [98] [5700/6250] eta: 0:01:24 lr: 0.000000 grad: 0.1599 (0.1617) loss: 0.8765 (0.8799) time: 0.1313 data: 0.0368 max mem: 8233 +Train: [98] [5800/6250] eta: 0:01:09 lr: 0.000000 grad: 0.1631 (0.1619) loss: 0.8725 (0.8798) time: 0.1374 data: 0.0583 max mem: 8233 +Train: [98] [5900/6250] eta: 0:00:53 lr: 0.000000 grad: 0.1563 (0.1619) loss: 0.8741 (0.8797) time: 0.1519 data: 0.0645 max mem: 8233 +Train: [98] [6000/6250] eta: 0:00:38 lr: 0.000000 grad: 0.1520 (0.1619) loss: 0.8750 (0.8797) time: 0.1451 data: 0.0632 max mem: 8233 +Train: [98] [6100/6250] eta: 0:00:23 lr: 0.000000 grad: 0.1559 (0.1619) loss: 0.8807 (0.8796) time: 0.1490 data: 0.0711 max mem: 8233 +Train: [98] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1560 (0.1619) loss: 0.8767 (0.8796) time: 0.1518 data: 0.0711 max mem: 8233 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1545 (0.1618) loss: 0.8791 (0.8795) time: 0.1696 data: 0.0880 max mem: 8233 +Train: [98] Total time: 0:16:07 (0.1547 s / it) +Averaged stats: lr: 0.000000 grad: 0.1545 (0.1618) loss: 0.8791 (0.8795) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:05:27 loss: 0.8862 (0.8862) time: 5.2786 data: 5.2454 max mem: 8233 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8770 (0.8793) time: 0.1225 data: 0.1023 max mem: 8233 +Eval (hcp-train-subset): [98] Total time: 0:00:14 (0.2303 s / it) +Averaged stats (hcp-train-subset): loss: 0.8770 (0.8793) +Eval (hcp-val): [98] [ 0/62] eta: 0:06:37 loss: 0.8771 (0.8771) time: 6.4172 data: 6.3901 max mem: 8233 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8793 (0.8801) time: 0.1282 data: 0.1075 max mem: 8233 +Eval (hcp-val): [98] Total time: 0:00:14 (0.2386 s / it) +Averaged stats (hcp-val): loss: 0.8793 (0.8801) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 10:37:55 lr: 0.000000 grad: 0.1579 (0.1579) loss: 0.8850 (0.8850) time: 6.1240 data: 5.9564 max mem: 8233 +Train: [99] [ 100/6250] eta: 0:23:19 lr: 0.000000 grad: 0.1583 (0.1871) loss: 0.8706 (0.8785) time: 0.1604 data: 0.0364 max mem: 8233 +Train: [99] [ 200/6250] eta: 0:20:18 lr: 0.000000 grad: 0.1855 (0.2025) loss: 0.8674 (0.8718) time: 0.1783 data: 0.0610 max mem: 8233 +Train: [99] [ 300/6250] eta: 0:18:33 lr: 0.000000 grad: 0.1733 (0.2036) loss: 0.8659 (0.8693) time: 0.1525 data: 0.0535 max mem: 8233 +Train: [99] [ 400/6250] eta: 0:17:37 lr: 0.000000 grad: 0.1897 (0.2032) loss: 0.8758 (0.8688) time: 0.1615 data: 0.0546 max mem: 8233 +Train: [99] [ 500/6250] eta: 0:16:47 lr: 0.000000 grad: 0.1591 (0.1989) loss: 0.8738 (0.8695) time: 0.1375 data: 0.0400 max mem: 8233 +Train: [99] [ 600/6250] eta: 0:16:09 lr: 0.000000 grad: 0.1637 (0.1952) loss: 0.8792 (0.8703) time: 0.1629 data: 0.0708 max mem: 8233 +Train: [99] [ 700/6250] eta: 0:15:32 lr: 0.000000 grad: 0.1600 (0.1915) loss: 0.8739 (0.8708) time: 0.1464 data: 0.0596 max mem: 8233 +Train: [99] [ 800/6250] eta: 0:15:03 lr: 0.000000 grad: 0.1683 (0.1884) loss: 0.8819 (0.8714) time: 0.1156 data: 0.0155 max mem: 8233 +Train: [99] [ 900/6250] eta: 0:14:38 lr: 0.000000 grad: 0.1563 (0.1864) loss: 0.8764 (0.8721) time: 0.1289 data: 0.0435 max mem: 8233 +Train: [99] [1000/6250] eta: 0:14:12 lr: 0.000000 grad: 0.1563 (0.1844) loss: 0.8719 (0.8726) time: 0.1423 data: 0.0554 max mem: 8233 +Train: [99] [1100/6250] eta: 0:13:49 lr: 0.000000 grad: 0.1590 (0.1825) loss: 0.8742 (0.8731) time: 0.1241 data: 0.0482 max mem: 8233 +Train: [99] [1200/6250] eta: 0:13:25 lr: 0.000000 grad: 0.1491 (0.1809) loss: 0.8800 (0.8736) time: 0.1275 data: 0.0425 max mem: 8233 +Train: [99] [1300/6250] eta: 0:13:04 lr: 0.000000 grad: 0.1464 (0.1792) loss: 0.8802 (0.8741) time: 0.1483 data: 0.0682 max mem: 8233 +Train: [99] [1400/6250] eta: 0:12:44 lr: 0.000000 grad: 0.1495 (0.1778) loss: 0.8783 (0.8745) time: 0.1184 data: 0.0432 max mem: 8233 +Train: [99] [1500/6250] eta: 0:12:27 lr: 0.000000 grad: 0.1538 (0.1766) loss: 0.8822 (0.8748) time: 0.1590 data: 0.0724 max mem: 8233 +Train: [99] [1600/6250] eta: 0:12:06 lr: 0.000000 grad: 0.1546 (0.1756) loss: 0.8837 (0.8751) time: 0.1308 data: 0.0432 max mem: 8233 +Train: [99] [1700/6250] eta: 0:11:50 lr: 0.000000 grad: 0.1611 (0.1749) loss: 0.8806 (0.8754) time: 0.1581 data: 0.0736 max mem: 8233 +Train: [99] [1800/6250] eta: 0:11:32 lr: 0.000000 grad: 0.1534 (0.1741) loss: 0.8828 (0.8758) time: 0.1613 data: 0.0805 max mem: 8233 +Train: [99] [1900/6250] eta: 0:11:14 lr: 0.000000 grad: 0.1507 (0.1735) loss: 0.8816 (0.8760) time: 0.1576 data: 0.0780 max mem: 8233 +Train: [99] [2000/6250] eta: 0:10:56 lr: 0.000000 grad: 0.1486 (0.1727) loss: 0.8798 (0.8762) time: 0.1415 data: 0.0590 max mem: 8233 +Train: [99] [2100/6250] eta: 0:10:40 lr: 0.000000 grad: 0.1504 (0.1721) loss: 0.8843 (0.8765) time: 0.1385 data: 0.0619 max mem: 8233 +Train: [99] [2200/6250] eta: 0:10:25 lr: 0.000000 grad: 0.1527 (0.1716) loss: 0.8796 (0.8767) time: 0.1552 data: 0.0719 max mem: 8233 +Train: [99] [2300/6250] eta: 0:10:09 lr: 0.000000 grad: 0.1523 (0.1713) loss: 0.8777 (0.8768) time: 0.1706 data: 0.0877 max mem: 8233 +Train: [99] [2400/6250] eta: 0:09:54 lr: 0.000000 grad: 0.1695 (0.1711) loss: 0.8847 (0.8769) time: 0.1527 data: 0.0751 max mem: 8233 +Train: [99] [2500/6250] eta: 0:09:39 lr: 0.000000 grad: 0.1549 (0.1709) loss: 0.8825 (0.8770) time: 0.1577 data: 0.0695 max mem: 8233 +Train: [99] [2600/6250] eta: 0:09:22 lr: 0.000000 grad: 0.1566 (0.1707) loss: 0.8783 (0.8771) time: 0.1413 data: 0.0636 max mem: 8233 +Train: [99] [2700/6250] eta: 0:09:06 lr: 0.000000 grad: 0.1534 (0.1704) loss: 0.8815 (0.8772) time: 0.1665 data: 0.0871 max mem: 8233 +Train: [99] [2800/6250] eta: 0:08:49 lr: 0.000000 grad: 0.1648 (0.1705) loss: 0.8742 (0.8772) time: 0.1342 data: 0.0492 max mem: 8233 +Train: [99] [2900/6250] eta: 0:08:35 lr: 0.000000 grad: 0.1616 (0.1703) loss: 0.8828 (0.8773) time: 0.1839 data: 0.1216 max mem: 8233 +Train: [99] [3000/6250] eta: 0:08:19 lr: 0.000000 grad: 0.1608 (0.1701) loss: 0.8772 (0.8773) time: 0.1247 data: 0.0382 max mem: 8233 +Train: [99] [3100/6250] eta: 0:08:04 lr: 0.000000 grad: 0.1518 (0.1700) loss: 0.8770 (0.8773) time: 0.1458 data: 0.0781 max mem: 8233 +Train: [99] [3200/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1551 (0.1699) loss: 0.8806 (0.8773) time: 0.1513 data: 0.0589 max mem: 8233 +Train: [99] [3300/6250] eta: 0:07:34 lr: 0.000000 grad: 0.1610 (0.1698) loss: 0.8765 (0.8773) time: 0.1738 data: 0.0836 max mem: 8233 +Train: [99] [3400/6250] eta: 0:07:20 lr: 0.000000 grad: 0.1555 (0.1699) loss: 0.8792 (0.8773) time: 0.1526 data: 0.0691 max mem: 8233 +Train: [99] [3500/6250] eta: 0:07:04 lr: 0.000000 grad: 0.1592 (0.1699) loss: 0.8802 (0.8774) time: 0.1575 data: 0.0679 max mem: 8233 +Train: [99] [3600/6250] eta: 0:06:48 lr: 0.000000 grad: 0.1690 (0.1699) loss: 0.8767 (0.8774) time: 0.1416 data: 0.0504 max mem: 8233 +Train: [99] [3700/6250] eta: 0:06:33 lr: 0.000000 grad: 0.1532 (0.1700) loss: 0.8755 (0.8774) time: 0.1576 data: 0.0883 max mem: 8233 +Train: [99] [3800/6250] eta: 0:06:16 lr: 0.000000 grad: 0.1619 (0.1699) loss: 0.8759 (0.8775) time: 0.1446 data: 0.0533 max mem: 8233 +Train: [99] [3900/6250] eta: 0:06:01 lr: 0.000000 grad: 0.1610 (0.1698) loss: 0.8780 (0.8775) time: 0.1513 data: 0.0702 max mem: 8233 +Train: [99] [4000/6250] eta: 0:05:46 lr: 0.000000 grad: 0.1538 (0.1697) loss: 0.8770 (0.8775) time: 0.1683 data: 0.0967 max mem: 8233 +Train: [99] [4100/6250] eta: 0:05:30 lr: 0.000000 grad: 0.1601 (0.1695) loss: 0.8772 (0.8775) time: 0.1439 data: 0.0513 max mem: 8233 +Train: [99] [4200/6250] eta: 0:05:15 lr: 0.000000 grad: 0.1576 (0.1694) loss: 0.8740 (0.8775) time: 0.1450 data: 0.0592 max mem: 8233 +Train: [99] [4300/6250] eta: 0:04:59 lr: 0.000000 grad: 0.1608 (0.1692) loss: 0.8779 (0.8775) time: 0.1276 data: 0.0513 max mem: 8233 +Train: [99] [4400/6250] eta: 0:04:43 lr: 0.000000 grad: 0.1601 (0.1690) loss: 0.8729 (0.8775) time: 0.1381 data: 0.0528 max mem: 8233 +Train: [99] [4500/6250] eta: 0:04:28 lr: 0.000000 grad: 0.1609 (0.1688) loss: 0.8766 (0.8775) time: 0.1517 data: 0.0679 max mem: 8233 +Train: [99] [4600/6250] eta: 0:04:13 lr: 0.000000 grad: 0.1539 (0.1687) loss: 0.8805 (0.8775) time: 0.1569 data: 0.0746 max mem: 8233 +Train: [99] [4700/6250] eta: 0:03:57 lr: 0.000000 grad: 0.1561 (0.1685) loss: 0.8728 (0.8776) time: 0.1445 data: 0.0672 max mem: 8233 +Train: [99] [4800/6250] eta: 0:03:42 lr: 0.000000 grad: 0.1428 (0.1684) loss: 0.8815 (0.8776) time: 0.1474 data: 0.0792 max mem: 8233 +Train: [99] [4900/6250] eta: 0:03:27 lr: 0.000000 grad: 0.1610 (0.1683) loss: 0.8760 (0.8776) time: 0.1440 data: 0.0635 max mem: 8233 +Train: [99] [5000/6250] eta: 0:03:11 lr: 0.000000 grad: 0.1606 (0.1683) loss: 0.8751 (0.8776) time: 0.1604 data: 0.0926 max mem: 8233 +Train: [99] [5100/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1592 (0.1684) loss: 0.8782 (0.8776) time: 0.1650 data: 0.0786 max mem: 8233 +Train: [99] [5200/6250] eta: 0:02:41 lr: 0.000000 grad: 0.1711 (0.1685) loss: 0.8790 (0.8776) time: 0.1664 data: 0.0900 max mem: 8233 +Train: [99] [5300/6250] eta: 0:02:26 lr: 0.000000 grad: 0.1588 (0.1685) loss: 0.8774 (0.8776) time: 0.1579 data: 0.0735 max mem: 8233 +Train: [99] [5400/6250] eta: 0:02:10 lr: 0.000000 grad: 0.1567 (0.1685) loss: 0.8781 (0.8775) time: 0.1374 data: 0.0505 max mem: 8233 +Train: [99] [5500/6250] eta: 0:01:55 lr: 0.000000 grad: 0.1592 (0.1684) loss: 0.8782 (0.8776) time: 0.1462 data: 0.0622 max mem: 8233 +Train: [99] [5600/6250] eta: 0:01:39 lr: 0.000000 grad: 0.1517 (0.1684) loss: 0.8817 (0.8776) time: 0.1390 data: 0.0545 max mem: 8233 +Train: [99] [5700/6250] eta: 0:01:24 lr: 0.000000 grad: 0.1593 (0.1683) loss: 0.8779 (0.8776) time: 0.1427 data: 0.0650 max mem: 8233 +Train: [99] [5800/6250] eta: 0:01:08 lr: 0.000000 grad: 0.1531 (0.1683) loss: 0.8795 (0.8777) time: 0.1593 data: 0.0814 max mem: 8233 +Train: [99] [5900/6250] eta: 0:00:53 lr: 0.000000 grad: 0.1629 (0.1683) loss: 0.8780 (0.8776) time: 0.1495 data: 0.0723 max mem: 8233 +Train: [99] [6000/6250] eta: 0:00:38 lr: 0.000000 grad: 0.1507 (0.1682) loss: 0.8808 (0.8777) time: 0.1515 data: 0.0661 max mem: 8233 +Train: [99] [6100/6250] eta: 0:00:22 lr: 0.000000 grad: 0.1610 (0.1682) loss: 0.8799 (0.8777) time: 0.1291 data: 0.0494 max mem: 8233 +Train: [99] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1612 (0.1681) loss: 0.8806 (0.8777) time: 0.1743 data: 0.0940 max mem: 8233 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1589 (0.1681) loss: 0.8732 (0.8777) time: 0.1632 data: 0.0933 max mem: 8233 +Train: [99] Total time: 0:16:04 (0.1543 s / it) +Averaged stats: lr: 0.000000 grad: 0.1589 (0.1681) loss: 0.8732 (0.8777) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:06:24 loss: 0.8877 (0.8877) time: 6.1942 data: 6.1630 max mem: 8233 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8766 (0.8795) time: 0.1217 data: 0.1002 max mem: 8233 +Eval (hcp-train-subset): [99] Total time: 0:00:14 (0.2368 s / it) +Averaged stats (hcp-train-subset): loss: 0.8766 (0.8795) +Making plots (hcp-train-subset): example=56 +Eval (hcp-val): [99] [ 0/62] eta: 0:05:01 loss: 0.8767 (0.8767) time: 4.8678 data: 4.7694 max mem: 8233 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8784 (0.8798) time: 0.1069 data: 0.0836 max mem: 8233 +Eval (hcp-val): [99] Total time: 0:00:14 (0.2358 s / it) +Averaged stats (hcp-val): loss: 0.8784 (0.8798) +Making plots (hcp-val): example=50 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg1/pretrain/checkpoint-00099.pth +done! training time: 1 day, 6:03:06 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8135c9e5736a085abec15cdd1cf0301a210f321a --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..c9efe385265cd3ca09cef5d6aef57f24cb19d43b --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,0.046415888336127774,train,0.8641732283464567,0.015819900474987256,0.8654686954110568,0.015752422601597774,0.8666046119795852,0.015629575456753964 +flat_mae,patch,logistic,aabc_age,,0.046415888336127774,test,0.38461538461538464,0.06547102887004125,0.3925591951907741,0.0661921745579023,0.3814102564102564,0.06512556793879488 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,train,0.702755905511811,0.02012294770569284,0.7020930156008214,0.020280603374881946,0.7047462403311155,0.02012690637518408 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,test,0.46153846153846156,0.05732306195548754,0.44545454545454544,0.05455103831483217,0.46062271062271065,0.057419639636338185 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,train,0.5787401574803149,0.02064416883440488,0.5732921969131609,0.02117882387857465,0.5800791251829249,0.020718399533591617 +flat_mae,patch,logistic,aabc_age,2,0.000774263682681127,test,0.5192307692307693,0.06487652131358061,0.5165747633489568,0.06589383712925383,0.5173992673992673,0.06482785454968076 +flat_mae,patch,logistic,aabc_age,3,0.3593813663804626,train,0.9980314960629921,0.001935150508258974,0.9980917969033418,0.00187755047338689,0.997983870967742,0.0019819686657168633 +flat_mae,patch,logistic,aabc_age,3,0.3593813663804626,test,0.5576923076923077,0.06989911369019321,0.5568273555529928,0.07117929012026565,0.5563186813186813,0.06998645695734333 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,train,0.9980314960629921,0.0018475057040655222,0.9980686663398256,0.0018110621652815578,0.9982014388489209,0.0016880088087505058 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,test,0.4230769230769231,0.06210274936981406,0.4237037037037037,0.059992711634596414,0.4253663003663004,0.06268092835411916 +flat_mae,patch,logistic,aabc_age,5,0.005994842503189409,train,0.6948818897637795,0.019467791759463417,0.6939361159910642,0.019698043010945788,0.6959466684183977,0.019359657215334336 +flat_mae,patch,logistic,aabc_age,5,0.005994842503189409,test,0.40384615384615385,0.05791407377165246,0.3779647435897436,0.061852179975398845,0.4015567765567766,0.05749469334937588 +flat_mae,patch,logistic,aabc_age,6,0.046415888336127774,train,0.860236220472441,0.01536027343102979,0.8612900620270334,0.015228001625384856,0.8614618835456828,0.015242943566387886 +flat_mae,patch,logistic,aabc_age,6,0.046415888336127774,test,0.5192307692307693,0.07050765831919824,0.5283216783216783,0.0698157170797877,0.5222069597069596,0.07050473923025546 +flat_mae,patch,logistic,aabc_age,7,0.005994842503189409,train,0.6929133858267716,0.020131846936695147,0.6916054138674427,0.020461993741932086,0.6943656751484976,0.020135907996588216 +flat_mae,patch,logistic,aabc_age,7,0.005994842503189409,test,0.5192307692307693,0.0687476304056404,0.5184392419175028,0.06924501654576293,0.5176282051282051,0.06885234374656442 +flat_mae,patch,logistic,aabc_age,8,0.046415888336127774,train,0.8562992125984252,0.01530062483097473,0.8569039552619269,0.015286362844780703,0.8574296254811666,0.015222144263789317 +flat_mae,patch,logistic,aabc_age,8,0.046415888336127774,test,0.5384615384615384,0.06857557486055528,0.5385878489326765,0.06838114188870789,0.5396062271062272,0.06883203125024837 +flat_mae,patch,logistic,aabc_age,9,0.046415888336127774,train,0.8622047244094488,0.0152557485386895,0.8624192488878827,0.015307913204231197,0.864448257443099,0.015086955091283785 +flat_mae,patch,logistic,aabc_age,9,0.046415888336127774,test,0.46153846153846156,0.060356436345132436,0.4285714285714286,0.058855040103377214,0.45489926739926734,0.05934587185952785 +flat_mae,patch,logistic,aabc_age,10,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,10,21.54434690031882,test,0.5384615384615384,0.06608371730091832,0.531080532370855,0.06795873546666426,0.5396062271062272,0.06612247148783797 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,train,0.8582677165354331,0.0159734380238396,0.858780933744515,0.016035213626890907,0.8603160260381404,0.015811121649148503 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,test,0.6153846153846154,0.06772921852066593,0.6218617614269788,0.06660374689728135,0.6156135531135531,0.06794337938477127 +flat_mae,patch,logistic,aabc_age,12,0.000774263682681127,train,0.562992125984252,0.02000518370109981,0.5526860431675661,0.02063530516287435,0.5633826183521324,0.01997542383087942 +flat_mae,patch,logistic,aabc_age,12,0.000774263682681127,test,0.4807692307692308,0.06695113249237711,0.4757519169283875,0.06925403562359222,0.47619047619047616,0.06689848624741762 +flat_mae,patch,logistic,aabc_age,13,0.046415888336127774,train,0.8681102362204725,0.01441415094743685,0.867872543828869,0.014533704316256198,0.8685061681393356,0.01442438592117582 +flat_mae,patch,logistic,aabc_age,13,0.046415888336127774,test,0.5384615384615384,0.06380688087767085,0.5436883969492665,0.05851050880914986,0.5455586080586081,0.06475416142557727 +flat_mae,patch,logistic,aabc_age,14,0.005994842503189409,train,0.6791338582677166,0.020253255797247526,0.67686765794888,0.02054277884040408,0.6808554888960067,0.020219736289081292 +flat_mae,patch,logistic,aabc_age,14,0.005994842503189409,test,0.5769230769230769,0.06792464498582017,0.5728205128205128,0.07150427676100875,0.5796703296703297,0.06804363196584426 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,train,0.6909448818897638,0.020741004577371398,0.6895260467323994,0.021153098657075296,0.6914292879213025,0.020713773844552873 +flat_mae,patch,logistic,aabc_age,15,0.005994842503189409,test,0.4807692307692308,0.06542220638863686,0.49286422112509065,0.06245756288940119,0.4832875457875458,0.06571122146958143 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,train,0.6751968503937008,0.01963624622132069,0.6723442151853067,0.019908805938420124,0.6764057162694265,0.019543358038931896 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,test,0.4423076923076923,0.06265850905819935,0.4452157038363934,0.06483964213138288,0.443452380952381,0.06287850300694996 +flat_mae,patch,logistic,aabc_age,17,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,17,0.3593813663804626,test,0.5,0.06671509459000899,0.4956709956709956,0.06571136406521819,0.5009157509157509,0.06689078126064082 +flat_mae,patch,logistic,aabc_age,18,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,18,21.54434690031882,test,0.38461538461538464,0.06285942803038931,0.38450549450549454,0.06022467560404086,0.3882783882783883,0.063717093239232 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,train,0.8622047244094488,0.01606302059206988,0.8625972266869528,0.016156372086438393,0.8640807295512565,0.015913375268725865 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,test,0.4423076923076923,0.06460864204747639,0.43777237255498125,0.06578170602795239,0.4391025641025641,0.06452022132063853 +flat_mae,patch,logistic,aabc_age,20,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,20,21.54434690031882,test,0.46153846153846156,0.061273600694033266,0.4433140572570857,0.061235336290872515,0.4592490842490843,0.06119259422182373 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,train,0.8543307086614174,0.015573729790327026,0.8544212158103861,0.015656126761970205,0.8548960085464021,0.01554715578133718 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,test,0.4423076923076923,0.05851054373196895,0.42559523809523814,0.05429222576162201,0.4473443223443223,0.059412823189761765 +flat_mae,patch,logistic,aabc_age,22,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,22,21.54434690031882,test,0.3269230769230769,0.06229129651325115,0.3318939393939394,0.06171263239570974,0.3278388278388278,0.0624298827441985 +flat_mae,patch,logistic,aabc_age,23,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,23,0.3593813663804626,test,0.5,0.05838096674522022,0.47716608518815645,0.06305094034211331,0.49793956043956045,0.058330975773372346 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.8779527559055118,0.014552120052706946,0.8779093559826077,0.014626003228354917,0.878569192100332,0.014534437551266976 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.4423076923076923,0.06351949567936561,0.4341666666666667,0.06256784261370761,0.44459706959706957,0.0639289104217791 +flat_mae,patch,logistic,aabc_age,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,25,2.782559402207126,test,0.34615384615384615,0.05575777070582037,0.31544542414107635,0.05065906020823648,0.3463827838827839,0.05572808874631347 +flat_mae,patch,logistic,aabc_age,26,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,26,21.54434690031882,test,0.46153846153846156,0.07143063627615652,0.4735353535353535,0.07048029813415116,0.46130952380952384,0.07161773966333038 +flat_mae,patch,logistic,aabc_age,27,0.3593813663804626,train,0.9980314960629921,0.001924693588312385,0.9980686663398256,0.0018866835844875691,0.9982014388489209,0.001758532990760229 +flat_mae,patch,logistic,aabc_age,27,0.3593813663804626,test,0.4423076923076923,0.061881866363381326,0.4277851458885942,0.06366104259378189,0.44047619047619047,0.061686944183019586 +flat_mae,patch,logistic,aabc_age,28,0.046415888336127774,train,0.860236220472441,0.015133499795012125,0.8610251544786649,0.015150929541406195,0.8613619102052402,0.015031625062790646 +flat_mae,patch,logistic,aabc_age,28,0.046415888336127774,test,0.5,0.0661770419977651,0.48266899766899773,0.06835020555409277,0.49793956043956045,0.06598185885332529 +flat_mae,patch,logistic,aabc_age,29,0.005994842503189409,train,0.6929133858267716,0.02007711086488195,0.6905752072720968,0.02040848834530846,0.6945332563594553,0.019897578888261203 +flat_mae,patch,logistic,aabc_age,29,0.005994842503189409,test,0.46153846153846156,0.06229547601038896,0.46200828157349894,0.06060759154350523,0.4608516483516484,0.06254646104142936 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,train,0.6909448818897638,0.020569640169925022,0.6906972085399985,0.020702406967542154,0.6925494927971245,0.02050535715389879 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,test,0.5576923076923077,0.06707863221181752,0.5515826702033599,0.06762267222254109,0.5634157509157509,0.0671941879170224 +flat_mae,patch,logistic,aabc_age,31,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,31,0.3593813663804626,test,0.5192307692307693,0.06912175177212551,0.5183856582874815,0.06887174253704709,0.5146520146520146,0.06890905616371647 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,train,0.6673228346456693,0.019968082831074797,0.6656003378216405,0.020276314332351816,0.6679060643780363,0.019970478926098705 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,test,0.5192307692307693,0.06348549664312053,0.49993480150680963,0.06733372119606879,0.5171703296703297,0.06337139987838036 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,train,0.7007874015748031,0.020114373198686013,0.6988954796526796,0.020455990636206227,0.7025301646179724,0.019992569728457366 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,test,0.5192307692307693,0.05841855707436539,0.4772435897435897,0.057982003609924865,0.5112179487179487,0.057700302768520104 +flat_mae,patch,logistic,aabc_age,34,0.046415888336127774,train,0.8641732283464567,0.015616130689997286,0.8648384440477709,0.01559512075107348,0.8655441282804202,0.015552905856183803 +flat_mae,patch,logistic,aabc_age,34,0.046415888336127774,test,0.4230769230769231,0.06794179330946828,0.44159090909090903,0.06730889965212955,0.42719780219780223,0.06810112135599566 +flat_mae,patch,logistic,aabc_age,35,0.005994842503189409,train,0.6811023622047244,0.020471282144672445,0.6807902790855238,0.02075065947323353,0.6829715912687073,0.020468775114956546 +flat_mae,patch,logistic,aabc_age,35,0.005994842503189409,test,0.4423076923076923,0.0689707081294781,0.43966329966329964,0.06839796306762136,0.44024725274725274,0.06889588568468362 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,train,0.8622047244094488,0.014751867110137833,0.8627678553235081,0.014720762986591786,0.864180702891699,0.014573318295717598 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,test,0.4807692307692308,0.06489527293805106,0.4683228840125392,0.06573484910539011,0.48168498168498164,0.06515094283099387 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,train,0.6830708661417323,0.02090801622082507,0.6807569569815943,0.0212498263634934,0.6853228827228807,0.02096019752065608 +flat_mae,patch,logistic,aabc_age,37,0.005994842503189409,test,0.5,0.05941310595957186,0.47633928571428574,0.05932672174388613,0.4908424908424909,0.05890013310484917 +flat_mae,patch,logistic,aabc_age,38,0.005994842503189409,train,0.6791338582677166,0.019724138728555347,0.6763433178048908,0.02017497978250039,0.6797852706904058,0.019758645763932527 +flat_mae,patch,logistic,aabc_age,38,0.005994842503189409,test,0.6153846153846154,0.06331768077105204,0.6034798534798534,0.06746614279646086,0.6151556776556777,0.06336209842593629 +flat_mae,patch,logistic,aabc_age,39,0.046415888336127774,train,0.8661417322834646,0.01463877314146776,0.8667972577002133,0.014592822220987426,0.8678777985342998,0.014554990003139002 +flat_mae,patch,logistic,aabc_age,39,0.046415888336127774,test,0.5384615384615384,0.06648863185297524,0.5326923076923076,0.0682968796098759,0.5338827838827839,0.06650901386971134 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,train,0.6712598425196851,0.020159545215964733,0.668950248372029,0.02047201428966299,0.6730761485186684,0.02010737169696483 +flat_mae,patch,logistic,aabc_age,40,0.005994842503189409,test,0.5192307692307693,0.06175270398698458,0.49215686274509807,0.06468532339261669,0.5128205128205128,0.06149991826033366 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,train,0.8681102362204725,0.015550234198222443,0.8685839271124589,0.015635944098733236,0.8702790766586943,0.015411019298028947 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,test,0.46153846153846156,0.059980223565229494,0.4571360153256705,0.05796902771246942,0.46222527472527475,0.06007633370001463 +flat_mae,patch,logistic,aabc_age,42,0.000774263682681127,train,0.5590551181102362,0.019749051826609187,0.5489990632430423,0.020415481960638793,0.5597355093797529,0.01965926630274712 +flat_mae,patch,logistic,aabc_age,42,0.000774263682681127,test,0.5,0.05479357443000564,0.47377091377091374,0.0640613482394553,0.5038919413919414,0.055192764456703174 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6811023622047244,0.02036908305003169,0.6803549036202465,0.02064121108088945,0.6829715912687073,0.020323086294864103 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.5192307692307693,0.06963848957845963,0.5188426710165841,0.07179408697050242,0.5178571428571428,0.06997869713224837 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,train,0.6791338582677166,0.02036596478306498,0.6776335436938254,0.020543583986402464,0.6813905979988071,0.02033552635385427 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,test,0.5,0.0681327888984219,0.49512987012987014,0.06996777685389484,0.4954212454212454,0.06809391740329489 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,train,0.6732283464566929,0.019992738467233116,0.6700343946230791,0.02050348742687881,0.6746071551183473,0.019962852950175823 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,test,0.4807692307692308,0.06051469331087183,0.4666666666666667,0.06154260237599659,0.4860347985347986,0.061211926904026166 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,train,0.5531496062992126,0.021668314217577745,0.5451542360488855,0.02267051951436991,0.5530844053096633,0.021667237628379354 +flat_mae,patch,logistic,aabc_age,46,0.000774263682681127,test,0.5,0.06276672082085816,0.486588788741303,0.06772616838524576,0.49793956043956045,0.06274695834841308 +flat_mae,patch,logistic,aabc_age,47,0.000774263682681127,train,0.5649606299212598,0.020535237955572744,0.5582403640217286,0.020784212412171287,0.5664689655899913,0.020467423026030333 +flat_mae,patch,logistic,aabc_age,47,0.000774263682681127,test,0.40384615384615385,0.06283418349421448,0.37337009803921567,0.061530830003955844,0.3985805860805861,0.061715475061707756 +flat_mae,patch,logistic,aabc_age,48,0.046415888336127774,train,0.8661417322834646,0.015649432970862052,0.866302421231812,0.015721798418199148,0.867510270642457,0.01550917131867767 +flat_mae,patch,logistic,aabc_age,48,0.046415888336127774,test,0.40384615384615385,0.06327595241358407,0.39785214785214784,0.06201757261769053,0.40453296703296704,0.06342794223010993 +flat_mae,patch,logistic,aabc_age,49,0.000774263682681127,train,0.5688976377952756,0.02128837542861964,0.5629583664733111,0.022170533664467734,0.5699484933514132,0.02131955959855026 +flat_mae,patch,logistic,aabc_age,49,0.000774263682681127,test,0.38461538461538464,0.06122046444018691,0.3815422322775264,0.06073447121207202,0.38095238095238093,0.06098058504994892 +flat_mae,patch,logistic,aabc_age,50,0.005994842503189409,train,0.6948818897637795,0.019666849469855,0.6921426875165935,0.020158916600134424,0.695094018093976,0.01962588564993141 +flat_mae,patch,logistic,aabc_age,50,0.005994842503189409,test,0.38461538461538464,0.06434893552311942,0.38675324675324674,0.06689127369270624,0.38278388278388276,0.06456184643077816 +flat_mae,patch,logistic,aabc_age,51,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,51,166.81005372000556,test,0.4807692307692308,0.06667212009253295,0.4783176593521421,0.06703923044613078,0.4789377289377289,0.06634600137250318 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,train,0.8779527559055118,0.014641035165582416,0.878307286179197,0.014641713539286928,0.878569192100332,0.014590359802710314 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,test,0.4807692307692308,0.06699000852816449,0.49403702305174957,0.0652463262897533,0.48351648351648346,0.0672779042800141 +flat_mae,patch,logistic,aabc_age,53,0.046415888336127774,train,0.8641732283464567,0.014778218136550237,0.8645711857176619,0.014823648804834685,0.8650090191776199,0.01476019514652734 +flat_mae,patch,logistic,aabc_age,53,0.046415888336127774,test,0.5,0.06740405190355955,0.5127125326225777,0.06452290355446086,0.5011446886446886,0.06756171196260823 +flat_mae,patch,logistic,aabc_age,54,0.005994842503189409,train,0.6791338582677166,0.019957116201319618,0.6788567580094595,0.020235485632592583,0.6807378943552702,0.01997356165977024 +flat_mae,patch,logistic,aabc_age,54,0.005994842503189409,test,0.40384615384615385,0.06273236096645841,0.38727938727938727,0.06501406869769912,0.4017857142857143,0.06247848040714631 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,train,0.6614173228346457,0.019426361400608064,0.6584186566490973,0.01980234976908794,0.662795556676493,0.019372143848655918 +flat_mae,patch,logistic,aabc_age,55,0.005994842503189409,test,0.5576923076923077,0.06341227691784396,0.5495337995337995,0.06340408417027192,0.5602106227106227,0.06376680951182409 +flat_mae,patch,logistic,aabc_age,56,0.005994842503189409,train,0.7007874015748031,0.019591226853679658,0.6994036685965705,0.0198982845116723,0.7026801246286363,0.019552312664377826 +flat_mae,patch,logistic,aabc_age,56,0.005994842503189409,test,0.5192307692307693,0.05786967606859419,0.49686592045725175,0.06191566317538818,0.5171703296703297,0.05776104714099856 +flat_mae,patch,logistic,aabc_age,57,0.005994842503189409,train,0.6948818897637795,0.019584032196374522,0.693794242438834,0.0197956858430085,0.6963141963102405,0.019505386196779693 +flat_mae,patch,logistic,aabc_age,57,0.005994842503189409,test,0.4807692307692308,0.06463754198853423,0.47489316239316237,0.06289048939374234,0.4787087912087912,0.06457038199719749 +flat_mae,patch,logistic,aabc_age,58,0.005994842503189409,train,0.6751968503937008,0.021373607829803163,0.6722401579930114,0.021788311523871253,0.6754854580744896,0.021364128455749334 +flat_mae,patch,logistic,aabc_age,58,0.005994842503189409,test,0.4423076923076923,0.05623802962703584,0.4128113553113553,0.059023983746775525,0.4413919413919414,0.056066235207758816 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,train,0.8799212598425197,0.014138677813162734,0.8801886379551821,0.0142130930814994,0.8815555659977483,0.01398289429440577 +flat_mae,patch,logistic,aabc_age,59,0.046415888336127774,test,0.4230769230769231,0.0644335353164234,0.42583333333333334,0.06301145632013407,0.42101648351648346,0.06462440477473529 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,train,0.6653543307086615,0.021484369926909712,0.6627383362929955,0.021846230353794942,0.6664426656488724,0.02149359825278121 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,test,0.4807692307692308,0.06552988387349219,0.4801587301587301,0.0671409541019889,0.48328754578754585,0.06611535005655347 +flat_mae,patch,logistic,aabc_age,61,0.005994842503189409,train,0.687007874015748,0.02008812348292915,0.6857627609286641,0.02037687102710637,0.6877645577486291,0.02005865069420883 +flat_mae,patch,logistic,aabc_age,61,0.005994842503189409,test,0.36538461538461536,0.06398570245252604,0.3563011063011063,0.06174588876537783,0.3644688644688645,0.06384144914696574 +flat_mae,patch,logistic,aabc_age,62,0.000774263682681127,train,0.562992125984252,0.021219513732306065,0.557185940826761,0.021843387183056538,0.5633150104816174,0.021189670617519446 +flat_mae,patch,logistic,aabc_age,62,0.000774263682681127,test,0.5384615384615384,0.061291041074339164,0.5245320197044335,0.0622949924267881,0.5322802197802198,0.061125703599996306 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.6889763779527559,0.019346320491510333,0.6873442513853473,0.019694069117035525,0.6906009716353816,0.019287713314736245 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.5192307692307693,0.06449415137925436,0.5152343059239611,0.06404483323641064,0.5187728937728938,0.06462804227416798 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,train,0.8759842519685039,0.013598220024075765,0.8769356839121192,0.013573942641085057,0.8782259982469902,0.013430409592644453 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,test,0.38461538461538464,0.06456206591358107,0.389231078904992,0.06365675104363641,0.3839285714285714,0.06457568088349235 +flat_mae,patch,logistic,aabc_age,65,0.005994842503189409,train,0.6811023622047244,0.020188627433814194,0.6794258030894544,0.020543319547959474,0.6831391724796648,0.020028940784660422 +flat_mae,patch,logistic,aabc_age,65,0.005994842503189409,test,0.5384615384615384,0.06576921952316593,0.5191638370118845,0.06364231573182046,0.5306776556776557,0.06499187640243498 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,train,0.6830708661417323,0.018911258214919863,0.6826615009852914,0.019100014581592606,0.6848201390900077,0.01881019730113909 +flat_mae,patch,logistic,aabc_age,66,0.005994842503189409,test,0.5192307692307693,0.061685353530937036,0.5105820105820106,0.06286284527065365,0.5201465201465201,0.06218965613276734 +flat_mae,patch,logistic,aabc_age,67,0.3593813663804626,train,0.9980314960629921,0.0019901019875905425,0.9980686663398256,0.0019505893917000582,0.9982014388489209,0.0018182946217553799 +flat_mae,patch,logistic,aabc_age,67,0.3593813663804626,test,0.5192307692307693,0.05978089926690433,0.487453007518797,0.061652164803589864,0.5155677655677656,0.05923424013900034 +flat_mae,patch,logistic,aabc_age,68,0.005994842503189409,train,0.687007874015748,0.019863825503742397,0.6870564427493933,0.019987146527881937,0.6886348292733449,0.0198184820573066 +flat_mae,patch,logistic,aabc_age,68,0.005994842503189409,test,0.4423076923076923,0.06118014673919626,0.42839105339105343,0.05896574825619569,0.4413919413919414,0.06114544964960499 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,train,0.6771653543307087,0.021048329578956047,0.67636567486762,0.021333248082484928,0.6795420501775067,0.020978042132759295 +flat_mae,patch,logistic,aabc_age,69,0.005994842503189409,test,0.46153846153846156,0.0697279052405188,0.46115904555802256,0.06959887700953259,0.45673076923076916,0.06961542449426568 +flat_mae,patch,logistic,aabc_age,70,0.005994842503189409,train,0.6732283464566929,0.02018731605626313,0.6734358748023097,0.02012355299078891,0.6744219527070958,0.020075576605053613 +flat_mae,patch,logistic,aabc_age,70,0.005994842503189409,test,0.38461538461538464,0.0656499142619665,0.3854395604395604,0.06615663481869333,0.3857600732600733,0.06597806814654253 +flat_mae,patch,logistic,aabc_age,71,0.046415888336127774,train,0.8720472440944882,0.0154815665020631,0.8725936093411469,0.015495359467538723,0.8732734819875371,0.015348641010514525 +flat_mae,patch,logistic,aabc_age,71,0.046415888336127774,test,0.5,0.06562891013992116,0.5145798494983278,0.06376004883038347,0.5027472527472527,0.06603493931341392 +flat_mae,patch,logistic,aabc_age,72,0.000774263682681127,train,0.5551181102362205,0.02161151648115627,0.5470633407289033,0.02225635238057235,0.5555356701042792,0.02152000893506137 +flat_mae,patch,logistic,aabc_age,72,0.000774263682681127,test,0.6153846153846154,0.05757437947210229,0.5909944581280788,0.06557139751908261,0.6078296703296704,0.05781649233080081 +flat_mae,patch,logistic,aabc_age,73,0.005994842503189409,train,0.6830708661417323,0.020311677998839137,0.6813551087992029,0.020625174181617006,0.6841850566467647,0.020313301128759932 +flat_mae,patch,logistic,aabc_age,73,0.005994842503189409,test,0.4807692307692308,0.06193736098987858,0.47241379310344833,0.06187111828423953,0.4846611721611722,0.06261614128623451 +flat_mae,patch,logistic,aabc_age,74,0.000774263682681127,train,0.5649606299212598,0.021590884287878722,0.5552710613686224,0.02232271203566149,0.5651811795032116,0.021585839881814384 +flat_mae,patch,logistic,aabc_age,74,0.000774263682681127,test,0.46153846153846156,0.06124520268617784,0.4464285714285714,0.06219214859891357,0.46222527472527475,0.06173859189663165 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,train,0.6850393700787402,0.020663852302743153,0.6835833683121345,0.021016891573219818,0.686033604468065,0.020683701013401386 +flat_mae,patch,logistic,aabc_age,75,0.005994842503189409,test,0.5384615384615384,0.06692599463135716,0.5257294429708222,0.07058467414313702,0.5366300366300366,0.06708041356135265 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,train,0.860236220472441,0.01533689904905633,0.8607061754992786,0.015371528762748908,0.8625997096217988,0.015167352282165748 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,test,0.5576923076923077,0.0653812668825834,0.5588739217771477,0.06578853370889313,0.5560897435897436,0.06553474609574043 +flat_mae,patch,logistic,aabc_age,77,0.3593813663804626,train,0.9980314960629921,0.0018949894938944522,0.9980934568599307,0.0018341150381984076,0.9982014388489209,0.001731393278594204 +flat_mae,patch,logistic,aabc_age,77,0.3593813663804626,test,0.4230769230769231,0.06431850295587739,0.42061386888973096,0.0644423603074305,0.4223901098901099,0.06455882173141142 +flat_mae,patch,logistic,aabc_age,78,0.005994842503189409,train,0.6732283464566929,0.020464112479162126,0.6719523318409709,0.020707419761587877,0.674271992696432,0.020490722023506398 +flat_mae,patch,logistic,aabc_age,78,0.005994842503189409,test,0.5192307692307693,0.06591656910701767,0.5248432601880878,0.06487422879415483,0.5203754578754579,0.06619834488865105 +flat_mae,patch,logistic,aabc_age,79,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,79,0.3593813663804626,test,0.4423076923076923,0.06890456267473476,0.439793956043956,0.06906913300464397,0.43887362637362637,0.06877828709653112 +flat_mae,patch,logistic,aabc_age,80,0.000774263682681127,train,0.5669291338582677,0.0213328667127136,0.558810605342019,0.022080857532985255,0.5677324176382701,0.021202231820170857 +flat_mae,patch,logistic,aabc_age,80,0.000774263682681127,test,0.4807692307692308,0.05890865208049517,0.4608630952380952,0.05990059275603261,0.4844322344322344,0.059496408098426184 +flat_mae,patch,logistic,aabc_age,81,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,81,21.54434690031882,test,0.38461538461538464,0.06238949995104955,0.3841234221598878,0.061038237412370744,0.38095238095238093,0.0622533951636916 +flat_mae,patch,logistic,aabc_age,82,0.000774263682681127,train,0.5610236220472441,0.021835633803253957,0.5560114508995944,0.02244501628193865,0.5615664360007595,0.021810094746003955 +flat_mae,patch,logistic,aabc_age,82,0.000774263682681127,test,0.5961538461538461,0.06285255593038559,0.5825054466230937,0.06872540066038478,0.592948717948718,0.063243708518475 +flat_mae,patch,logistic,aabc_age,83,0.046415888336127774,train,0.8562992125984252,0.016094262830294286,0.8565883301306435,0.016201460319673074,0.8583498836761037,0.015948796532907046 +flat_mae,patch,logistic,aabc_age,83,0.046415888336127774,test,0.5192307692307693,0.05904671703743916,0.4985057471264368,0.06199052019881835,0.5215201465201466,0.05937187154508616 +flat_mae,patch,logistic,aabc_age,84,0.046415888336127774,train,0.8700787401574803,0.015133737412153535,0.8709547469541135,0.015118830425349299,0.8727127202530164,0.014933371076932656 +flat_mae,patch,logistic,aabc_age,84,0.046415888336127774,test,0.4807692307692308,0.06180580151241238,0.46020108923334724,0.06256626879259987,0.47298534798534797,0.06139889240537474 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,train,0.8759842519685039,0.014627823349577046,0.8762093628549927,0.01463996260366426,0.8772057667116107,0.014528765710139913 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,test,0.5,0.06717083889332584,0.5072089761570828,0.06591889642579875,0.49977106227106227,0.06718001313970322 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,train,0.8622047244094488,0.014927345381925083,0.8624658237658145,0.014907334760350235,0.8632104580265407,0.014905428434381215 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,test,0.46153846153846156,0.06414845024347084,0.44907407407407407,0.06510703046600784,0.459478021978022,0.06390125617666317 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,train,0.6712598425196851,0.018675090508964366,0.6670056201659975,0.019217760211544838,0.6727086206268257,0.018657644157270673 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,test,0.5192307692307693,0.0695306645560753,0.5259350483488414,0.06995657115678955,0.5206043956043955,0.06976855334458691 +flat_mae,patch,logistic,aabc_age,88,0.046415888336127774,train,0.860236220472441,0.01474335122123903,0.8606625222777095,0.01478357417695546,0.8621145871892195,0.014641785310880524 +flat_mae,patch,logistic,aabc_age,88,0.046415888336127774,test,0.5384615384615384,0.06478914365921712,0.5259986494208093,0.06850993600414562,0.5409798534798534,0.06510194489184823 +flat_mae,patch,logistic,aabc_age,89,0.000774263682681127,train,0.5767716535433071,0.02126480111319014,0.5694465367846484,0.021869903683256083,0.5772103458262449,0.0212596660813926 +flat_mae,patch,logistic,aabc_age,89,0.000774263682681127,test,0.40384615384615385,0.06536533652429942,0.4082693471078226,0.06561903981374909,0.40613553113553114,0.06577575814149471 +flat_mae,patch,logistic,aabc_age,90,0.000774263682681127,train,0.5570866141732284,0.020671645535221862,0.5506082171135602,0.020807788007776315,0.557701759147201,0.02068611377836286 +flat_mae,patch,logistic,aabc_age,90,0.000774263682681127,test,0.5,0.0633210449513257,0.49799482127068334,0.0628133769058468,0.5009157509157509,0.06347893580017887 +flat_mae,patch,logistic,aabc_age,91,0.000774263682681127,train,0.5708661417322834,0.022021462358108933,0.5632064259511722,0.022600478728236954,0.5718646490432288,0.02188586481629887 +flat_mae,patch,logistic,aabc_age,91,0.000774263682681127,test,0.5192307692307693,0.0619861002743271,0.4884648617511521,0.06798929299629375,0.5215201465201466,0.06251306613813291 +flat_mae,patch,logistic,aabc_age,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,92,21.54434690031882,test,0.4230769230769231,0.0654305155631828,0.42652895774335053,0.06067276331776289,0.4194139194139194,0.0648527723392605 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,train,0.8622047244094488,0.01550170490964494,0.8627044031902631,0.015505951942770116,0.8636955804591198,0.015409315807597548 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,test,0.46153846153846156,0.06617535428535988,0.45755681818181815,0.06598440209275677,0.4567307692307693,0.06615452129486252 +flat_mae,patch,logistic,aabc_age,94,0.046415888336127774,train,0.860236220472441,0.013820453846017103,0.8603079350240926,0.01395803399878948,0.8612119501945765,0.013727320660684125 +flat_mae,patch,logistic,aabc_age,94,0.046415888336127774,test,0.46153846153846156,0.06881725865476913,0.46403133903133903,0.06894528992227958,0.46565934065934067,0.06923469273070253 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,train,0.8661417322834646,0.015186155512131375,0.8669312401808886,0.015206372836336163,0.8685305021778366,0.015012386235418729 +flat_mae,patch,logistic,aabc_age,95,0.046415888336127774,test,0.4807692307692308,0.06454180792644564,0.4662800162800163,0.06250399925132476,0.4743589743589744,0.06405106067252782 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,train,0.8523622047244095,0.01544019801684648,0.8534920306987936,0.015409773577452983,0.8533473807464294,0.015373175688215057 +flat_mae,patch,logistic,aabc_age,96,0.046415888336127774,test,0.6538461538461539,0.06616157155249457,0.645275140207674,0.06967465876471424,0.6538461538461539,0.06629604571728184 +flat_mae,patch,logistic,aabc_age,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,97,166.81005372000556,test,0.34615384615384615,0.0627335871649301,0.34751168371858027,0.062228591104699776,0.34684065934065933,0.06273603622004384 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,train,0.6830708661417323,0.02097412964411702,0.6814968548767131,0.021302055428459952,0.6847201657495652,0.020896143107219153 +flat_mae,patch,logistic,aabc_age,98,0.005994842503189409,test,0.4230769230769231,0.06268352935238256,0.40236175115207373,0.06401627141190638,0.4194139194139194,0.062449947237282914 +flat_mae,patch,logistic,aabc_age,99,0.000774263682681127,train,0.5708661417322834,0.020897927060996038,0.5635815774607584,0.021225308116397938,0.5709443908482917,0.020882027818940836 +flat_mae,patch,logistic,aabc_age,99,0.000774263682681127,test,0.5,0.06226997908991128,0.4683760683760684,0.06385789959565841,0.49633699633699635,0.061688860743914914 +flat_mae,patch,logistic,aabc_age,100,0.046415888336127774,train,0.8582677165354331,0.015562060880727773,0.8584778403834833,0.015621691250881689,0.859295794502761,0.015433005057201651 +flat_mae,patch,logistic,aabc_age,100,0.046415888336127774,test,0.5,0.06936845283355186,0.5025349047088178,0.06946145310212624,0.5013736263736264,0.06936621185340752 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..76e9bfeb6dd5a183cca75953d33ea490ceecab05 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:52:08 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:20:59 time: 5.5221 data: 4.5227 max mem: 3219 +extract (train) [ 20/228] eta: 0:01:48 time: 0.2693 data: 0.1017 max mem: 3409 +extract (train) [ 40/228] eta: 0:01:11 time: 0.2291 data: 0.0797 max mem: 3409 +extract (train) [ 60/228] eta: 0:00:55 time: 0.2346 data: 0.0813 max mem: 3409 +extract (train) [ 80/228] eta: 0:00:46 time: 0.2546 data: 0.0927 max mem: 3409 +extract (train) [100/228] eta: 0:00:38 time: 0.2645 data: 0.0988 max mem: 3409 +extract (train) [120/228] eta: 0:00:31 time: 0.2160 data: 0.0722 max mem: 3409 +extract (train) [140/228] eta: 0:00:24 time: 0.2146 data: 0.0726 max mem: 3409 +extract (train) [160/228] eta: 0:00:18 time: 0.2318 data: 0.0784 max mem: 3409 +extract (train) [180/228] eta: 0:00:12 time: 0.2415 data: 0.0853 max mem: 3409 +extract (train) [200/228] eta: 0:00:07 time: 0.2351 data: 0.0823 max mem: 3409 +extract (train) [220/228] eta: 0:00:02 time: 0.1986 data: 0.0637 max mem: 3409 +extract (train) [227/228] eta: 0:00:00 time: 0.1918 data: 0.0623 max mem: 3409 +extract (train) Total time: 0:00:59 (0.2592 s / it) +extract (validation) [ 0/27] eta: 0:02:13 time: 4.9495 data: 4.7876 max mem: 3409 +extract (validation) [20/27] eta: 0:00:02 time: 0.1945 data: 0.0612 max mem: 3409 +extract (validation) [26/27] eta: 0:00:00 time: 0.1867 data: 0.0591 max mem: 3409 +extract (validation) Total time: 0:00:10 (0.3785 s / it) +extract (test) [ 0/26] eta: 0:01:57 time: 4.5269 data: 4.3617 max mem: 3409 +extract (test) [20/26] eta: 0:00:02 time: 0.2251 data: 0.0772 max mem: 3409 +extract (test) [25/26] eta: 0:00:00 time: 0.1998 data: 0.0648 max mem: 3409 +extract (test) Total time: 0:00:10 (0.3950 s / it) +feature extraction time: 0:01:19 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.046416 | train | 0.86417 | 0.01582 | 0.86547 | 0.015752 | 0.8666 | 0.01563 | +| flat_mae | patch | logistic | aabc_age | | 0.046416 | test | 0.38462 | 0.065471 | 0.39256 | 0.066192 | 0.38141 | 0.065126 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05732306195548754, "f1": 0.44545454545454544, "f1_std": 0.05455103831483217, "bacc": 0.46062271062271065, "bacc_std": 0.057419639636338185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06487652131358061, "f1": 0.5165747633489568, "f1_std": 0.06589383712925383, "bacc": 0.5173992673992673, "bacc_std": 0.06482785454968076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06989911369019321, "f1": 0.5568273555529928, "f1_std": 0.07117929012026565, "bacc": 0.5563186813186813, "bacc_std": 0.06998645695734333} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06210274936981406, "f1": 0.4237037037037037, "f1_std": 0.059992711634596414, "bacc": 0.4253663003663004, "bacc_std": 0.06268092835411916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05791407377165246, "f1": 0.3779647435897436, "f1_std": 0.061852179975398845, "bacc": 0.4015567765567766, "bacc_std": 0.05749469334937588} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.07050765831919824, "f1": 0.5283216783216783, "f1_std": 0.0698157170797877, "bacc": 0.5222069597069596, "bacc_std": 0.07050473923025546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0687476304056404, "f1": 0.5184392419175028, "f1_std": 0.06924501654576293, "bacc": 0.5176282051282051, "bacc_std": 0.06885234374656442} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06857557486055528, "f1": 0.5385878489326765, "f1_std": 0.06838114188870789, "bacc": 0.5396062271062272, "bacc_std": 0.06883203125024837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.060356436345132436, "f1": 0.4285714285714286, "f1_std": 0.058855040103377214, "bacc": 0.45489926739926734, "bacc_std": 0.05934587185952785} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 21.54434690031882, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06608371730091832, "f1": 0.531080532370855, "f1_std": 0.06795873546666426, "bacc": 0.5396062271062272, "bacc_std": 0.06612247148783797} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06772921852066593, "f1": 0.6218617614269788, "f1_std": 0.06660374689728135, "bacc": 0.6156135531135531, "bacc_std": 0.06794337938477127} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06695113249237711, "f1": 0.4757519169283875, "f1_std": 0.06925403562359222, "bacc": 0.47619047619047616, "bacc_std": 0.06689848624741762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06380688087767085, "f1": 0.5436883969492665, "f1_std": 0.05851050880914986, "bacc": 0.5455586080586081, "bacc_std": 0.06475416142557727} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06792464498582017, "f1": 0.5728205128205128, "f1_std": 0.07150427676100875, "bacc": 0.5796703296703297, "bacc_std": 0.06804363196584426} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06542220638863686, "f1": 0.49286422112509065, "f1_std": 0.06245756288940119, "bacc": 0.4832875457875458, "bacc_std": 0.06571122146958143} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06265850905819935, "f1": 0.4452157038363934, "f1_std": 0.06483964213138288, "bacc": 0.443452380952381, "bacc_std": 0.06287850300694996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.06671509459000899, "f1": 0.4956709956709956, "f1_std": 0.06571136406521819, "bacc": 0.5009157509157509, "bacc_std": 0.06689078126064082} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 21.54434690031882, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06285942803038931, "f1": 0.38450549450549454, "f1_std": 0.06022467560404086, "bacc": 0.3882783882783883, "bacc_std": 0.063717093239232} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06460864204747639, "f1": 0.43777237255498125, "f1_std": 0.06578170602795239, "bacc": 0.4391025641025641, "bacc_std": 0.06452022132063853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 21.54434690031882, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.061273600694033266, "f1": 0.4433140572570857, "f1_std": 0.061235336290872515, "bacc": 0.4592490842490843, "bacc_std": 0.06119259422182373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05851054373196895, "f1": 0.42559523809523814, "f1_std": 0.05429222576162201, "bacc": 0.4473443223443223, "bacc_std": 0.059412823189761765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 21.54434690031882, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.06229129651325115, "f1": 0.3318939393939394, "f1_std": 0.06171263239570974, "bacc": 0.3278388278388278, "bacc_std": 0.0624298827441985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.05838096674522022, "f1": 0.47716608518815645, "f1_std": 0.06305094034211331, "bacc": 0.49793956043956045, "bacc_std": 0.058330975773372346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06351949567936561, "f1": 0.4341666666666667, "f1_std": 0.06256784261370761, "bacc": 0.44459706959706957, "bacc_std": 0.0639289104217791} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.05575777070582037, "f1": 0.31544542414107635, "f1_std": 0.05065906020823648, "bacc": 0.3463827838827839, "bacc_std": 0.05572808874631347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 21.54434690031882, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.07143063627615652, "f1": 0.4735353535353535, "f1_std": 0.07048029813415116, "bacc": 0.46130952380952384, "bacc_std": 0.07161773966333038} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.061881866363381326, "f1": 0.4277851458885942, "f1_std": 0.06366104259378189, "bacc": 0.44047619047619047, "bacc_std": 0.061686944183019586} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.0661770419977651, "f1": 0.48266899766899773, "f1_std": 0.06835020555409277, "bacc": 0.49793956043956045, "bacc_std": 0.06598185885332529} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06229547601038896, "f1": 0.46200828157349894, "f1_std": 0.06060759154350523, "bacc": 0.4608516483516484, "bacc_std": 0.06254646104142936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06707863221181752, "f1": 0.5515826702033599, "f1_std": 0.06762267222254109, "bacc": 0.5634157509157509, "bacc_std": 0.0671941879170224} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06912175177212551, "f1": 0.5183856582874815, "f1_std": 0.06887174253704709, "bacc": 0.5146520146520146, "bacc_std": 0.06890905616371647} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06348549664312053, "f1": 0.49993480150680963, "f1_std": 0.06733372119606879, "bacc": 0.5171703296703297, "bacc_std": 0.06337139987838036} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05841855707436539, "f1": 0.4772435897435897, "f1_std": 0.057982003609924865, "bacc": 0.5112179487179487, "bacc_std": 0.057700302768520104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06794179330946828, "f1": 0.44159090909090903, "f1_std": 0.06730889965212955, "bacc": 0.42719780219780223, "bacc_std": 0.06810112135599566} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0689707081294781, "f1": 0.43966329966329964, "f1_std": 0.06839796306762136, "bacc": 0.44024725274725274, "bacc_std": 0.06889588568468362} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06489527293805106, "f1": 0.4683228840125392, "f1_std": 0.06573484910539011, "bacc": 0.48168498168498164, "bacc_std": 0.06515094283099387} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.05941310595957186, "f1": 0.47633928571428574, "f1_std": 0.05932672174388613, "bacc": 0.4908424908424909, "bacc_std": 0.05890013310484917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06331768077105204, "f1": 0.6034798534798534, "f1_std": 0.06746614279646086, "bacc": 0.6151556776556777, "bacc_std": 0.06336209842593629} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06648863185297524, "f1": 0.5326923076923076, "f1_std": 0.0682968796098759, "bacc": 0.5338827838827839, "bacc_std": 0.06650901386971134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06175270398698458, "f1": 0.49215686274509807, "f1_std": 0.06468532339261669, "bacc": 0.5128205128205128, "bacc_std": 0.06149991826033366} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.059980223565229494, "f1": 0.4571360153256705, "f1_std": 0.05796902771246942, "bacc": 0.46222527472527475, "bacc_std": 0.06007633370001463} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.05479357443000564, "f1": 0.47377091377091374, "f1_std": 0.0640613482394553, "bacc": 0.5038919413919414, "bacc_std": 0.055192764456703174} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06963848957845963, "f1": 0.5188426710165841, "f1_std": 0.07179408697050242, "bacc": 0.5178571428571428, "bacc_std": 0.06997869713224837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.0681327888984219, "f1": 0.49512987012987014, "f1_std": 0.06996777685389484, "bacc": 0.4954212454212454, "bacc_std": 0.06809391740329489} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06051469331087183, "f1": 0.4666666666666667, "f1_std": 0.06154260237599659, "bacc": 0.4860347985347986, "bacc_std": 0.061211926904026166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06276672082085816, "f1": 0.486588788741303, "f1_std": 0.06772616838524576, "bacc": 0.49793956043956045, "bacc_std": 0.06274695834841308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06283418349421448, "f1": 0.37337009803921567, "f1_std": 0.061530830003955844, "bacc": 0.3985805860805861, "bacc_std": 0.061715475061707756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06327595241358407, "f1": 0.39785214785214784, "f1_std": 0.06201757261769053, "bacc": 0.40453296703296704, "bacc_std": 0.06342794223010993} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06122046444018691, "f1": 0.3815422322775264, "f1_std": 0.06073447121207202, "bacc": 0.38095238095238093, "bacc_std": 0.06098058504994892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06434893552311942, "f1": 0.38675324675324674, "f1_std": 0.06689127369270624, "bacc": 0.38278388278388276, "bacc_std": 0.06456184643077816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 166.81005372000556, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06667212009253295, "f1": 0.4783176593521421, "f1_std": 0.06703923044613078, "bacc": 0.4789377289377289, "bacc_std": 0.06634600137250318} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06699000852816449, "f1": 0.49403702305174957, "f1_std": 0.0652463262897533, "bacc": 0.48351648351648346, "bacc_std": 0.0672779042800141} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06740405190355955, "f1": 0.5127125326225777, "f1_std": 0.06452290355446086, "bacc": 0.5011446886446886, "bacc_std": 0.06756171196260823} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06273236096645841, "f1": 0.38727938727938727, "f1_std": 0.06501406869769912, "bacc": 0.4017857142857143, "bacc_std": 0.06247848040714631} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06341227691784396, "f1": 0.5495337995337995, "f1_std": 0.06340408417027192, "bacc": 0.5602106227106227, "bacc_std": 0.06376680951182409} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05786967606859419, "f1": 0.49686592045725175, "f1_std": 0.06191566317538818, "bacc": 0.5171703296703297, "bacc_std": 0.05776104714099856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06463754198853423, "f1": 0.47489316239316237, "f1_std": 0.06289048939374234, "bacc": 0.4787087912087912, "bacc_std": 0.06457038199719749} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05623802962703584, "f1": 0.4128113553113553, "f1_std": 0.059023983746775525, "bacc": 0.4413919413919414, "bacc_std": 0.056066235207758816} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0644335353164234, "f1": 0.42583333333333334, "f1_std": 0.06301145632013407, "bacc": 0.42101648351648346, "bacc_std": 0.06462440477473529} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06552988387349219, "f1": 0.4801587301587301, "f1_std": 0.0671409541019889, "bacc": 0.48328754578754585, "bacc_std": 0.06611535005655347} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06398570245252604, "f1": 0.3563011063011063, "f1_std": 0.06174588876537783, "bacc": 0.3644688644688645, "bacc_std": 0.06384144914696574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.061291041074339164, "f1": 0.5245320197044335, "f1_std": 0.0622949924267881, "bacc": 0.5322802197802198, "bacc_std": 0.061125703599996306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06449415137925436, "f1": 0.5152343059239611, "f1_std": 0.06404483323641064, "bacc": 0.5187728937728938, "bacc_std": 0.06462804227416798} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06456206591358107, "f1": 0.389231078904992, "f1_std": 0.06365675104363641, "bacc": 0.3839285714285714, "bacc_std": 0.06457568088349235} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06576921952316593, "f1": 0.5191638370118845, "f1_std": 0.06364231573182046, "bacc": 0.5306776556776557, "bacc_std": 0.06499187640243498} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.061685353530937036, "f1": 0.5105820105820106, "f1_std": 0.06286284527065365, "bacc": 0.5201465201465201, "bacc_std": 0.06218965613276734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05978089926690433, "f1": 0.487453007518797, "f1_std": 0.061652164803589864, "bacc": 0.5155677655677656, "bacc_std": 0.05923424013900034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06118014673919626, "f1": 0.42839105339105343, "f1_std": 0.05896574825619569, "bacc": 0.4413919413919414, "bacc_std": 0.06114544964960499} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0697279052405188, "f1": 0.46115904555802256, "f1_std": 0.06959887700953259, "bacc": 0.45673076923076916, "bacc_std": 0.06961542449426568} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.0656499142619665, "f1": 0.3854395604395604, "f1_std": 0.06615663481869333, "bacc": 0.3857600732600733, "bacc_std": 0.06597806814654253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06562891013992116, "f1": 0.5145798494983278, "f1_std": 0.06376004883038347, "bacc": 0.5027472527472527, "bacc_std": 0.06603493931341392} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05757437947210229, "f1": 0.5909944581280788, "f1_std": 0.06557139751908261, "bacc": 0.6078296703296704, "bacc_std": 0.05781649233080081} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06193736098987858, "f1": 0.47241379310344833, "f1_std": 0.06187111828423953, "bacc": 0.4846611721611722, "bacc_std": 0.06261614128623451} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06124520268617784, "f1": 0.4464285714285714, "f1_std": 0.06219214859891357, "bacc": 0.46222527472527475, "bacc_std": 0.06173859189663165} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06692599463135716, "f1": 0.5257294429708222, "f1_std": 0.07058467414313702, "bacc": 0.5366300366300366, "bacc_std": 0.06708041356135265} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.0653812668825834, "f1": 0.5588739217771477, "f1_std": 0.06578853370889313, "bacc": 0.5560897435897436, "bacc_std": 0.06553474609574043} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06431850295587739, "f1": 0.42061386888973096, "f1_std": 0.0644423603074305, "bacc": 0.4223901098901099, "bacc_std": 0.06455882173141142} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06591656910701767, "f1": 0.5248432601880878, "f1_std": 0.06487422879415483, "bacc": 0.5203754578754579, "bacc_std": 0.06619834488865105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06890456267473476, "f1": 0.439793956043956, "f1_std": 0.06906913300464397, "bacc": 0.43887362637362637, "bacc_std": 0.06877828709653112} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05890865208049517, "f1": 0.4608630952380952, "f1_std": 0.05990059275603261, "bacc": 0.4844322344322344, "bacc_std": 0.059496408098426184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 21.54434690031882, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06238949995104955, "f1": 0.3841234221598878, "f1_std": 0.061038237412370744, "bacc": 0.38095238095238093, "bacc_std": 0.0622533951636916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.000774263682681127, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06285255593038559, "f1": 0.5825054466230937, "f1_std": 0.06872540066038478, "bacc": 0.592948717948718, "bacc_std": 0.063243708518475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05904671703743916, "f1": 0.4985057471264368, "f1_std": 0.06199052019881835, "bacc": 0.5215201465201466, "bacc_std": 0.05937187154508616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06180580151241238, "f1": 0.46020108923334724, "f1_std": 0.06256626879259987, "bacc": 0.47298534798534797, "bacc_std": 0.06139889240537474} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06717083889332584, "f1": 0.5072089761570828, "f1_std": 0.06591889642579875, "bacc": 0.49977106227106227, "bacc_std": 0.06718001313970322} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06414845024347084, "f1": 0.44907407407407407, "f1_std": 0.06510703046600784, "bacc": 0.459478021978022, "bacc_std": 0.06390125617666317} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0695306645560753, "f1": 0.5259350483488414, "f1_std": 0.06995657115678955, "bacc": 0.5206043956043955, "bacc_std": 0.06976855334458691} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06478914365921712, "f1": 0.5259986494208093, "f1_std": 0.06850993600414562, "bacc": 0.5409798534798534, "bacc_std": 0.06510194489184823} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06536533652429942, "f1": 0.4082693471078226, "f1_std": 0.06561903981374909, "bacc": 0.40613553113553114, "bacc_std": 0.06577575814149471} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.0633210449513257, "f1": 0.49799482127068334, "f1_std": 0.0628133769058468, "bacc": 0.5009157509157509, "bacc_std": 0.06347893580017887} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0619861002743271, "f1": 0.4884648617511521, "f1_std": 0.06798929299629375, "bacc": 0.5215201465201466, "bacc_std": 0.06251306613813291} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0654305155631828, "f1": 0.42652895774335053, "f1_std": 0.06067276331776289, "bacc": 0.4194139194139194, "bacc_std": 0.0648527723392605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06617535428535988, "f1": 0.45755681818181815, "f1_std": 0.06598440209275677, "bacc": 0.4567307692307693, "bacc_std": 0.06615452129486252} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06881725865476913, "f1": 0.46403133903133903, "f1_std": 0.06894528992227958, "bacc": 0.46565934065934067, "bacc_std": 0.06923469273070253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06454180792644564, "f1": 0.4662800162800163, "f1_std": 0.06250399925132476, "bacc": 0.4743589743589744, "bacc_std": 0.06405106067252782} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.6538461538461539, "acc_std": 0.06616157155249457, "f1": 0.645275140207674, "f1_std": 0.06967465876471424, "bacc": 0.6538461538461539, "bacc_std": 0.06629604571728184} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.0627335871649301, "f1": 0.34751168371858027, "f1_std": 0.062228591104699776, "bacc": 0.34684065934065933, "bacc_std": 0.06273603622004384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06268352935238256, "f1": 0.40236175115207373, "f1_std": 0.06401627141190638, "bacc": 0.4194139194139194, "bacc_std": 0.062449947237282914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06226997908991128, "f1": 0.4683760683760684, "f1_std": 0.06385789959565841, "bacc": 0.49633699633699635, "bacc_std": 0.061688860743914914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06936845283355186, "f1": 0.5025349047088178, "f1_std": 0.06946145310212624, "bacc": 0.5013736263736264, "bacc_std": 0.06936621185340752} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 4.9207 | 23.887 | 0.77986 | 0.14806 | 0.7783 | 0.15019 | 0.78092 | 0.14786 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 4.9207 | 23.887 | 0.48096 | 0.062059 | 0.47302 | 0.062154 | 0.48015 | 0.062031 | + + +done! total time: 0:05:51 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d8eedb63e9c2e881fadefaf3db2818f33e26644e --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_age reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..54cb6cc65ae25dc6ccbb3f4a372b187589d02274 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,aabc_age,,0.005994842503189409,train,0.6673228346456693,0.021494610360193768,0.6641779013763779,0.021770416141757117,0.668078005369687,0.021491776628648818 +flat_mae,reg,logistic,aabc_age,,0.005994842503189409,test,0.4807692307692308,0.062147229274593374,0.4517657600674679,0.06754706340479319,0.47046703296703296,0.062234684501671106 +flat_mae,reg,logistic,aabc_age,1,0.046415888336127774,train,0.8346456692913385,0.01582425646955287,0.8355133305752181,0.015803325198492712,0.8359225309701586,0.01585318999551209 +flat_mae,reg,logistic,aabc_age,1,0.046415888336127774,test,0.4807692307692308,0.06079808224552587,0.4636872010644802,0.06166621405382305,0.4800824175824176,0.060858918061514826 +flat_mae,reg,logistic,aabc_age,2,9.999999999999999e-05,train,0.49803149606299213,0.020632503820438942,0.48510471783628817,0.021574482454747666,0.49874374027837187,0.020650965270631424 +flat_mae,reg,logistic,aabc_age,2,9.999999999999999e-05,test,0.5,0.0594296859655551,0.46489862707535123,0.0639588838236542,0.49633699633699635,0.058796003835472455 +flat_mae,reg,logistic,aabc_age,3,0.005994842503189409,train,0.6732283464566929,0.019452823633722034,0.671677310116099,0.019760114065469018,0.674271992696432,0.01956430878720012 +flat_mae,reg,logistic,aabc_age,3,0.005994842503189409,test,0.4230769230769231,0.06716599370261093,0.4065772669220945,0.06689519199174516,0.4194139194139194,0.06679561844501888 +flat_mae,reg,logistic,aabc_age,4,0.3593813663804626,train,0.9862204724409449,0.005417322834645661,0.9863837385368486,0.005352173099778703,0.986707381628688,0.005234762074386386 +flat_mae,reg,logistic,aabc_age,4,0.3593813663804626,test,0.4807692307692308,0.06324193940264865,0.4712121212121212,0.06305948728158037,0.4878663003663004,0.06400326003078455 +flat_mae,reg,logistic,aabc_age,5,0.3593813663804626,train,0.9881889763779528,0.004581154873387263,0.9883187700710512,0.004518171769628287,0.988238388228367,0.004552270024284277 +flat_mae,reg,logistic,aabc_age,5,0.3593813663804626,test,0.38461538461538464,0.06554346089635632,0.3924548836692765,0.06478927026028977,0.3841575091575091,0.06574948120125342 +flat_mae,reg,logistic,aabc_age,6,0.046415888336127774,train,0.8287401574803149,0.016893411771300746,0.8286592524427184,0.017043689770396345,0.8291890747599201,0.01687729898965411 +flat_mae,reg,logistic,aabc_age,6,0.046415888336127774,test,0.5,0.06724910637095713,0.4971428571428571,0.0669703778305033,0.4981684981684981,0.06703419009347804 +flat_mae,reg,logistic,aabc_age,7,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,7,2.782559402207126,test,0.40384615384615385,0.06512249495460402,0.4146273291925466,0.06322521879998214,0.4033882783882784,0.06508756288092243 +flat_mae,reg,logistic,aabc_age,8,0.005994842503189409,train,0.6476377952755905,0.020871517284099583,0.6457707291974673,0.021116113141798083,0.6479123552664133,0.020827470134255403 +flat_mae,reg,logistic,aabc_age,8,0.005994842503189409,test,0.4807692307692308,0.0694157677805846,0.48283844189016606,0.069897013409641,0.4848901098901099,0.06971072391062516 +flat_mae,reg,logistic,aabc_age,9,0.046415888336127774,train,0.8366141732283464,0.016579664781610298,0.8375691087548118,0.016580661288636545,0.8376534842507226,0.01650254492583189 +flat_mae,reg,logistic,aabc_age,9,0.046415888336127774,test,0.46153846153846156,0.06641513693580088,0.4467072683753817,0.06624435365817392,0.4537545787545788,0.06592593175016968 +flat_mae,reg,logistic,aabc_age,10,0.005994842503189409,train,0.6633858267716536,0.019617794988626033,0.6624825167678771,0.01991797482521844,0.6657466881733216,0.019582754598466413 +flat_mae,reg,logistic,aabc_age,10,0.005994842503189409,test,0.5,0.06378044579863165,0.5000798212005109,0.0623417500587251,0.5009157509157509,0.06393419272588227 +flat_mae,reg,logistic,aabc_age,11,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,11,166.81005372000556,test,0.46153846153846156,0.06790369093505558,0.4874218374218374,0.0653471390796774,0.4642857142857143,0.06811061157111241 +flat_mae,reg,logistic,aabc_age,12,0.005994842503189409,train,0.65748031496063,0.02105702910661782,0.6546872795847001,0.02132138675789608,0.6591808131740409,0.020983716464700042 +flat_mae,reg,logistic,aabc_age,12,0.005994842503189409,test,0.5,0.06491244672360587,0.49921837421837423,0.06576284646711313,0.5043498168498168,0.06525305586943199 +flat_mae,reg,logistic,aabc_age,13,0.046415888336127774,train,0.8307086614173228,0.016830605055628074,0.8306865488941684,0.016920027135929678,0.831137595921663,0.016863007205775278 +flat_mae,reg,logistic,aabc_age,13,0.046415888336127774,test,0.4807692307692308,0.06391581000997147,0.4855555555555556,0.060912278230620454,0.48626373626373626,0.06470508585723983 +flat_mae,reg,logistic,aabc_age,14,0.046415888336127774,train,0.8287401574803149,0.016403282861530408,0.8288678922230908,0.01648840159623323,0.8303592663059636,0.01628527142526332 +flat_mae,reg,logistic,aabc_age,14,0.046415888336127774,test,0.5576923076923077,0.0675689873191635,0.5602020202020203,0.06816234630515244,0.5606684981684982,0.067319450762057 +flat_mae,reg,logistic,aabc_age,15,0.000774263682681127,train,0.5570866141732284,0.02194387006812761,0.5509768177064231,0.022396227131418967,0.5566139197413064,0.02194027920291079 +flat_mae,reg,logistic,aabc_age,15,0.000774263682681127,test,0.5,0.06269078572952021,0.4984065934065934,0.06065921703445822,0.5038919413919414,0.06349848210807552 +flat_mae,reg,logistic,aabc_age,16,0.046415888336127774,train,0.8248031496062992,0.016963730899667438,0.8254241168436084,0.017054748584005453,0.8255743312574679,0.017026568071133726 +flat_mae,reg,logistic,aabc_age,16,0.046415888336127774,test,0.4423076923076923,0.069195065579792,0.4465886287625418,0.06909632817710641,0.44207875457875456,0.06909506416612443 +flat_mae,reg,logistic,aabc_age,17,0.005994842503189409,train,0.6476377952755905,0.02159923719843123,0.6455156626916297,0.022026875290956413,0.6499704395374664,0.021564886968682025 +flat_mae,reg,logistic,aabc_age,17,0.005994842503189409,test,0.5384615384615384,0.0629733084247961,0.5216276477146042,0.06370973816255238,0.5364010989010989,0.0626927223203718 +flat_mae,reg,logistic,aabc_age,18,9.999999999999999e-05,train,0.49803149606299213,0.02081998869941717,0.48308788654957135,0.021725412376084385,0.4982086311755714,0.020789695949983766 +flat_mae,reg,logistic,aabc_age,18,9.999999999999999e-05,test,0.46153846153846156,0.06262266069991033,0.42296466973886326,0.062326421294590886,0.4548992673992674,0.06164507788113102 +flat_mae,reg,logistic,aabc_age,19,0.046415888336127774,train,0.8346456692913385,0.017016108297606816,0.8353696013763736,0.017006835567154314,0.8360225043106011,0.016984370556290672 +flat_mae,reg,logistic,aabc_age,19,0.046415888336127774,test,0.46153846153846156,0.06741885326188758,0.4627926421404682,0.067909960517878,0.4569597069597069,0.06749092681411574 +flat_mae,reg,logistic,aabc_age,20,0.3593813663804626,train,0.984251968503937,0.005532148923279574,0.984462804893692,0.005464534708835027,0.9844236980450297,0.00551952662526342 +flat_mae,reg,logistic,aabc_age,20,0.3593813663804626,test,0.5192307692307693,0.06889099313343684,0.5268920734437976,0.06793211389773102,0.5190018315018315,0.06898727162107603 +flat_mae,reg,logistic,aabc_age,21,0.005994842503189409,train,0.6476377952755905,0.019545757252489693,0.6446930364901595,0.01991295891722064,0.649217762553487,0.01951492078182403 +flat_mae,reg,logistic,aabc_age,21,0.005994842503189409,test,0.5384615384615384,0.06014327076033925,0.512808591527127,0.06627684705647481,0.5407509157509157,0.060580111292661935 +flat_mae,reg,logistic,aabc_age,22,0.005994842503189409,train,0.6712598425196851,0.020168194664177356,0.6687676393144556,0.020347539560651055,0.6729085673077106,0.020108097936280916 +flat_mae,reg,logistic,aabc_age,22,0.005994842503189409,test,0.38461538461538464,0.06537532739461167,0.3943840579710145,0.06336702843233422,0.38713369963369965,0.06572446573011298 +flat_mae,reg,logistic,aabc_age,23,0.046415888336127774,train,0.8228346456692913,0.01706836900990956,0.8232927552781706,0.01716068638556849,0.8236258100957251,0.017147339224930707 +flat_mae,reg,logistic,aabc_age,23,0.046415888336127774,test,0.4230769230769231,0.06063611271907587,0.41228070175438597,0.06266856286689018,0.42239010989010994,0.06066869274970524 +flat_mae,reg,logistic,aabc_age,24,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,24,166.81005372000556,test,0.4423076923076923,0.06306772916110474,0.42884510125889436,0.06141296405958855,0.43864468864468864,0.06236322940254331 +flat_mae,reg,logistic,aabc_age,25,9.999999999999999e-05,train,0.5,0.021054659842832942,0.4870618938897297,0.021427024305044586,0.5007598693106299,0.021023963713018748 +flat_mae,reg,logistic,aabc_age,25,9.999999999999999e-05,test,0.3269230769230769,0.061148512104092764,0.30933434381710245,0.05783460542629339,0.3244047619047619,0.060679850862608825 +flat_mae,reg,logistic,aabc_age,26,0.046415888336127774,train,0.844488188976378,0.015601135753235214,0.8446783564724193,0.015656750094114245,0.8460531628016702,0.015463775463836371 +flat_mae,reg,logistic,aabc_age,26,0.046415888336127774,test,0.46153846153846156,0.0611196687272227,0.4463812050018946,0.06228192635791265,0.46382783882783885,0.06127057706644027 +flat_mae,reg,logistic,aabc_age,27,0.046415888336127774,train,0.8248031496062992,0.017406862683945572,0.825038790804473,0.017449885786602844,0.8264446027821838,0.017349904954200378 +flat_mae,reg,logistic,aabc_age,27,0.046415888336127774,test,0.36538461538461536,0.06483318375628588,0.3606896551724138,0.061999801532850715,0.3630952380952381,0.06448789665452263 +flat_mae,reg,logistic,aabc_age,28,0.005994842503189409,train,0.6692913385826772,0.020717660315366163,0.6683367949452509,0.02099612413753317,0.6716951019296533,0.02069046640837449 +flat_mae,reg,logistic,aabc_age,28,0.005994842503189409,test,0.40384615384615385,0.06259869131097034,0.3941628242615085,0.06319913664060066,0.40453296703296704,0.06276200783991688 +flat_mae,reg,logistic,aabc_age,29,0.046415888336127774,train,0.8326771653543307,0.018020617011780565,0.8328022153821087,0.01802149035462056,0.8336888340567216,0.017924846343886462 +flat_mae,reg,logistic,aabc_age,29,0.046415888336127774,test,0.36538461538461536,0.06176222539066335,0.3639910813823858,0.05981245246892284,0.36309523809523814,0.061624021390559926 +flat_mae,reg,logistic,aabc_age,30,0.046415888336127774,train,0.8346456692913385,0.017438445635972622,0.8347484646010941,0.017524124125756588,0.8354374085375795,0.017381494575503396 +flat_mae,reg,logistic,aabc_age,30,0.046415888336127774,test,0.5192307692307693,0.0672098189501624,0.510576923076923,0.06856379871582646,0.5217490842490842,0.06734589745732507 +flat_mae,reg,logistic,aabc_age,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,31,166.81005372000556,test,0.5576923076923077,0.06545538025810962,0.5499194847020934,0.06568933349916388,0.5544871794871795,0.06524154911128721 +flat_mae,reg,logistic,aabc_age,32,0.005994842503189409,train,0.6535433070866141,0.021377300203204525,0.6499515246116361,0.021809474967505044,0.6540283502337026,0.021324259330877227 +flat_mae,reg,logistic,aabc_age,32,0.005994842503189409,test,0.5192307692307693,0.0646984242054979,0.5029582056147521,0.06796569233996617,0.5157967032967032,0.06438129394351907 +flat_mae,reg,logistic,aabc_age,33,0.005994842503189409,train,0.6594488188976378,0.020894623259837986,0.6584481264751717,0.021132778398570622,0.6609117664546049,0.020788843167966788 +flat_mae,reg,logistic,aabc_age,33,0.005994842503189409,test,0.5192307692307693,0.05550659644151053,0.4883972594885907,0.060094725636533695,0.5199175824175825,0.05581435365168408 +flat_mae,reg,logistic,aabc_age,34,0.005994842503189409,train,0.6653543307086615,0.020591121775867194,0.6617275165425234,0.02100945421556822,0.6671953426328519,0.020496592921859118 +flat_mae,reg,logistic,aabc_age,34,0.005994842503189409,test,0.40384615384615385,0.06541785354266967,0.40823529411764703,0.06687905946747194,0.4052197802197802,0.0657502775025906 +flat_mae,reg,logistic,aabc_age,35,0.000774263682681127,train,0.5551181102362205,0.021025557653678275,0.5494405506614477,0.0214667657518488,0.5557856034553854,0.021111822966676626 +flat_mae,reg,logistic,aabc_age,35,0.000774263682681127,test,0.4423076923076923,0.06076410640517094,0.4359066859066859,0.060020113016838655,0.4416208791208791,0.060726029229078084 +flat_mae,reg,logistic,aabc_age,36,0.046415888336127774,train,0.8326771653543307,0.01637188097247758,0.8334316955061141,0.01629065733893371,0.8341239698190794,0.01623701455339677 +flat_mae,reg,logistic,aabc_age,36,0.046415888336127774,test,0.46153846153846156,0.0667329749136692,0.4535714285714285,0.06602399623148913,0.4608516483516483,0.06671217122156585 +flat_mae,reg,logistic,aabc_age,37,0.046415888336127774,train,0.8346456692913385,0.0174289430986539,0.8351576278252131,0.0175593594748432,0.8355550030783158,0.017447247365912244 +flat_mae,reg,logistic,aabc_age,37,0.046415888336127774,test,0.5,0.06527270966658988,0.4889064558629776,0.0678025137084713,0.4926739926739927,0.06566429855452084 +flat_mae,reg,logistic,aabc_age,38,0.046415888336127774,train,0.8208661417322834,0.017089779361393664,0.8202905777506553,0.017268189875916398,0.8208070174092663,0.01710387326796935 +flat_mae,reg,logistic,aabc_age,38,0.046415888336127774,test,0.5576923076923077,0.0694677141815496,0.5659600815850816,0.06863578304854873,0.5560897435897436,0.06959255587559715 +flat_mae,reg,logistic,aabc_age,39,0.005994842503189409,train,0.6515748031496063,0.020034805646346434,0.6471859077659783,0.02048469997443601,0.651912247861002,0.020004797708899846 +flat_mae,reg,logistic,aabc_age,39,0.005994842503189409,test,0.5,0.06412509732163277,0.49424242424242426,0.0643127352043717,0.4967948717948718,0.06407042348843499 +flat_mae,reg,logistic,aabc_age,40,0.000774263682681127,train,0.5492125984251969,0.020343556675778116,0.5406695966430051,0.020782223828184947,0.5494372963372837,0.02024991527387485 +flat_mae,reg,logistic,aabc_age,40,0.000774263682681127,test,0.5,0.06347435767961923,0.48974358974358967,0.06571324774298376,0.49793956043956045,0.06364187726022416 +flat_mae,reg,logistic,aabc_age,41,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,41,21.54434690031882,test,0.4230769230769231,0.06136798502312763,0.4137875028197609,0.06067959730484982,0.4267399267399267,0.06215274264071985 +flat_mae,reg,logistic,aabc_age,42,0.005994842503189409,train,0.655511811023622,0.0201201807184564,0.6536771198226726,0.02033252575867529,0.6574822253634043,0.020101526451727518 +flat_mae,reg,logistic,aabc_age,42,0.005994842503189409,test,0.4807692307692308,0.05404188327518753,0.44783834586466165,0.06469293446750023,0.48305860805860806,0.05433087277196184 +flat_mae,reg,logistic,aabc_age,43,0.046415888336127774,train,0.8405511811023622,0.015467226285607205,0.8412240927879029,0.01544849199495008,0.8422884592885542,0.015384327586489095 +flat_mae,reg,logistic,aabc_age,43,0.046415888336127774,test,0.5384615384615384,0.07443549886394435,0.5354634190841088,0.07654819267306086,0.5430402930402931,0.07443051069820195 +flat_mae,reg,logistic,aabc_age,44,0.000774263682681127,train,0.5413385826771654,0.02039985618351916,0.5335179396034483,0.02075720898771644,0.5427781608357676,0.020423590927158102 +flat_mae,reg,logistic,aabc_age,44,0.000774263682681127,test,0.40384615384615385,0.06773437285656515,0.3956671982987772,0.07054982715712536,0.3976648351648352,0.06754795098975022 +flat_mae,reg,logistic,aabc_age,45,0.005994842503189409,train,0.6633858267716536,0.02025063673509,0.6610880716259661,0.02062253777793159,0.6639237929837416,0.020224510906243363 +flat_mae,reg,logistic,aabc_age,45,0.005994842503189409,test,0.46153846153846156,0.05933761591707147,0.4439412238325282,0.059329527955156204,0.4668040293040293,0.060182481592089485 +flat_mae,reg,logistic,aabc_age,46,0.000774263682681127,train,0.5354330708661418,0.02218737245730087,0.5291390596958211,0.022772452378850686,0.5356419343330987,0.022195989957529045 +flat_mae,reg,logistic,aabc_age,46,0.000774263682681127,test,0.5,0.062495857850906486,0.49017077798861486,0.06633923406646756,0.49793956043956045,0.06249446432568868 +flat_mae,reg,logistic,aabc_age,47,0.005994842503189409,train,0.6692913385826772,0.019881452790083784,0.6679078184174325,0.020191085666031876,0.6719626564810535,0.019796010602026487 +flat_mae,reg,logistic,aabc_age,47,0.005994842503189409,test,0.4423076923076923,0.0631303244869095,0.43026618542747574,0.06492569894762056,0.4416208791208791,0.06297559671338762 +flat_mae,reg,logistic,aabc_age,48,0.005994842503189409,train,0.6614173228346457,0.021550893412617816,0.6596146678528302,0.022074354222304388,0.6623927863840626,0.02147385116020739 +flat_mae,reg,logistic,aabc_age,48,0.005994842503189409,test,0.46153846153846156,0.06596272705814055,0.4630875576036867,0.06618161141697047,0.4624542124542125,0.06624849720589296 +flat_mae,reg,logistic,aabc_age,49,9.999999999999999e-05,train,0.5039370078740157,0.02032172108716916,0.48858478652284815,0.021010428153501192,0.5038718691802091,0.02026274977099854 +flat_mae,reg,logistic,aabc_age,49,9.999999999999999e-05,test,0.4423076923076923,0.06452570470787078,0.425182976416373,0.06425126713017841,0.4386446886446887,0.06403308828400184 +flat_mae,reg,logistic,aabc_age,50,0.005994842503189409,train,0.6751968503937008,0.020522019011455197,0.672142135611982,0.020909021460793206,0.6764557029396477,0.020449678274330273 +flat_mae,reg,logistic,aabc_age,50,0.005994842503189409,test,0.46153846153846156,0.06500199132134064,0.4579310344827586,0.06738048285409066,0.4597069597069597,0.06506012547359015 +flat_mae,reg,logistic,aabc_age,51,0.005994842503189409,train,0.6614173228346457,0.019715917121320432,0.6584569713853068,0.02012428347388565,0.6637481803413574,0.01959489757674101 +flat_mae,reg,logistic,aabc_age,51,0.005994842503189409,test,0.46153846153846156,0.05955270898900397,0.43363745210727966,0.06261643142351078,0.45787545787545786,0.05909540193136704 +flat_mae,reg,logistic,aabc_age,52,0.046415888336127774,train,0.8307086614173228,0.016748947699915303,0.8301278262466999,0.016890524344676954,0.830937649240778,0.016658921166158462 +flat_mae,reg,logistic,aabc_age,52,0.046415888336127774,test,0.46153846153846156,0.06853600099183393,0.46484949832775924,0.06923231305959544,0.46130952380952384,0.06858733893729338 +flat_mae,reg,logistic,aabc_age,53,0.005994842503189409,train,0.6653543307086615,0.020145528875774584,0.6619630081779009,0.02056489410423686,0.666542638989315,0.02013403362535031 +flat_mae,reg,logistic,aabc_age,53,0.005994842503189409,test,0.5384615384615384,0.06963794789468057,0.534555219337828,0.06943901544991202,0.5366300366300366,0.06948504360382732 +flat_mae,reg,logistic,aabc_age,54,0.046415888336127774,train,0.8228346456692913,0.016668758987850658,0.8233426067921972,0.01669761143426406,0.8243285004094831,0.016641452338672133 +flat_mae,reg,logistic,aabc_age,54,0.046415888336127774,test,0.4423076923076923,0.06321161744396087,0.4325757575757575,0.0638431855864915,0.4432234432234432,0.063390332039222 +flat_mae,reg,logistic,aabc_age,55,0.005994842503189409,train,0.6515748031496063,0.020283918097218474,0.6490227144442918,0.02056541703217998,0.6530324527368241,0.020211919819603658 +flat_mae,reg,logistic,aabc_age,55,0.005994842503189409,test,0.5384615384615384,0.07040735235948152,0.5375878147617278,0.07129422080984721,0.5412087912087913,0.07064209573428236 +flat_mae,reg,logistic,aabc_age,56,0.005994842503189409,train,0.6732283464566929,0.01961856927190463,0.6726475832939145,0.01969933940459339,0.6750070484801176,0.019669421846759128 +flat_mae,reg,logistic,aabc_age,56,0.005994842503189409,test,0.38461538461538464,0.06600560313314631,0.3860249189281447,0.06576918505632008,0.3855311355311355,0.0663174984869096 +flat_mae,reg,logistic,aabc_age,57,0.046415888336127774,train,0.84251968503937,0.015781693845203112,0.8431151677178756,0.015763052055297565,0.8434843034663179,0.01569213083122562 +flat_mae,reg,logistic,aabc_age,57,0.046415888336127774,test,0.4807692307692308,0.0639116786097963,0.4620507206714103,0.06229018756219902,0.47710622710622713,0.06349514768971937 +flat_mae,reg,logistic,aabc_age,58,0.005994842503189409,train,0.6653543307086615,0.02006842215977968,0.6640499673282922,0.020327658353489975,0.6666426123297576,0.02008404975326158 +flat_mae,reg,logistic,aabc_age,58,0.005994842503189409,test,0.46153846153846156,0.05253259061690254,0.4161019246408241,0.04880617611635784,0.4532967032967033,0.05100493664707068 +flat_mae,reg,logistic,aabc_age,59,0.3593813663804626,train,0.9862204724409449,0.005337740625297362,0.9863508463701893,0.005305016173451756,0.9864398270772878,0.005292878108261246 +flat_mae,reg,logistic,aabc_age,59,0.3593813663804626,test,0.4230769230769231,0.06562625034030065,0.4317860300618921,0.06456752725516178,0.42559523809523814,0.06580339349999566 +flat_mae,reg,logistic,aabc_age,60,0.000774263682681127,train,0.5413385826771654,0.021676770291368146,0.5338052465461895,0.022114730988557096,0.5422930384031884,0.02169177650355649 +flat_mae,reg,logistic,aabc_age,60,0.000774263682681127,test,0.46153846153846156,0.06691798168048219,0.45432240996757123,0.06924742351293386,0.45947802197802196,0.06694929981027288 +flat_mae,reg,logistic,aabc_age,61,0.005994842503189409,train,0.65748031496063,0.020127062433382692,0.6553083602895242,0.0204460907376123,0.6590132319630833,0.020069618285546785 +flat_mae,reg,logistic,aabc_age,61,0.005994842503189409,test,0.46153846153846156,0.06082621476277201,0.43530178230722694,0.062140657715511964,0.4592490842490843,0.06058269799207421 +flat_mae,reg,logistic,aabc_age,62,0.000774263682681127,train,0.5492125984251969,0.02116712466525232,0.5440310743595416,0.021535462308115594,0.5510926103159062,0.021157297658925354 +flat_mae,reg,logistic,aabc_age,62,0.000774263682681127,test,0.5,0.05430796469750822,0.46287762416794676,0.052428852453131086,0.49336080586080583,0.05343339476172293 +flat_mae,reg,logistic,aabc_age,63,0.005994842503189409,train,0.6751968503937008,0.02032464824253183,0.675555178481649,0.02038395289361792,0.6776082732853972,0.020283212915564862 +flat_mae,reg,logistic,aabc_age,63,0.005994842503189409,test,0.4423076923076923,0.06010684520282766,0.4268544120157023,0.05925379367543282,0.44597069597069594,0.06089821940853479 +flat_mae,reg,logistic,aabc_age,64,0.046415888336127774,train,0.8405511811023622,0.015818160288996644,0.8412279539227477,0.01577010815761502,0.8418533235261964,0.01571671328946646 +flat_mae,reg,logistic,aabc_age,64,0.046415888336127774,test,0.40384615384615385,0.06429126584463342,0.41380317905563346,0.06422493403915741,0.4036172161172161,0.06426513122370014 +flat_mae,reg,logistic,aabc_age,65,0.005994842503189409,train,0.6515748031496063,0.019200394665483077,0.6503766214908053,0.019274939548517212,0.6542026442828675,0.019091500926448665 +flat_mae,reg,logistic,aabc_age,65,0.005994842503189409,test,0.5384615384615384,0.06503129651657899,0.5311054150344183,0.06441768599257436,0.5322802197802198,0.06481844711329901 +flat_mae,reg,logistic,aabc_age,66,0.005994842503189409,train,0.6515748031496063,0.01988788831314686,0.6489486749417236,0.020132785891402105,0.6535675618396246,0.01989807185722098 +flat_mae,reg,logistic,aabc_age,66,0.005994842503189409,test,0.4230769230769231,0.0635463768584356,0.42620910698496905,0.06370235785469322,0.4255952380952381,0.06395988029185722 +flat_mae,reg,logistic,aabc_age,67,0.046415888336127774,train,0.8287401574803149,0.015856596257182366,0.8298299013670252,0.0157979030712366,0.8296565759922054,0.015810117498425345 +flat_mae,reg,logistic,aabc_age,67,0.046415888336127774,test,0.5,0.0676146845154969,0.4845238095238095,0.07002488315214395,0.49793956043956045,0.06768772540059989 +flat_mae,reg,logistic,aabc_age,68,0.005994842503189409,train,0.6653543307086615,0.020741784757905238,0.6624923033833156,0.021090038485833053,0.6658399486755571,0.020772404233104422 +flat_mae,reg,logistic,aabc_age,68,0.005994842503189409,test,0.5,0.06418827475002437,0.48722860791826306,0.06624839961620763,0.5009157509157509,0.0644165736633932 +flat_mae,reg,logistic,aabc_age,69,0.3593813663804626,train,0.9862204724409449,0.0052217415708908825,0.9862915705963804,0.005193349167999149,0.9861722725258876,0.005266043064115588 +flat_mae,reg,logistic,aabc_age,69,0.3593813663804626,test,0.5,0.07214641383731972,0.5031385281385281,0.07435550679527836,0.49565018315018317,0.07235370278563255 +flat_mae,reg,logistic,aabc_age,70,0.046415888336127774,train,0.8326771653543307,0.016427752120788765,0.8324259247704284,0.016577097992002496,0.8339240231381944,0.01635634541547106 +flat_mae,reg,logistic,aabc_age,70,0.046415888336127774,test,0.4807692307692308,0.0676201538529793,0.4822222222222222,0.06801833737616042,0.48511904761904767,0.06794283808439702 +flat_mae,reg,logistic,aabc_age,71,0.005994842503189409,train,0.6594488188976378,0.0205502850741403,0.6563424813147214,0.020812421064196493,0.6607118197737198,0.02053857647379036 +flat_mae,reg,logistic,aabc_age,71,0.005994842503189409,test,0.46153846153846156,0.05964515385761215,0.46054945054945057,0.05836358621184717,0.46382783882783885,0.060035153116939605 +flat_mae,reg,logistic,aabc_age,72,0.005994842503189409,train,0.6456692913385826,0.020214385106718698,0.6425930544516616,0.020603409009137805,0.6461814019858494,0.020250402963387693 +flat_mae,reg,logistic,aabc_age,72,0.005994842503189409,test,0.5769230769230769,0.06509404893767626,0.579294670846395,0.06562236511713344,0.5769230769230769,0.06523022816258871 +flat_mae,reg,logistic,aabc_age,73,0.005994842503189409,train,0.6515748031496063,0.020926526798278017,0.65098557576511,0.021160616803567074,0.6537175218502884,0.020884321001564416 +flat_mae,reg,logistic,aabc_age,73,0.005994842503189409,test,0.5192307692307693,0.06452012208486708,0.514994425863991,0.06541495200662967,0.5203754578754579,0.06473959612231543 +flat_mae,reg,logistic,aabc_age,74,0.000774263682681127,train,0.5452755905511811,0.020691311479960412,0.5384458977297354,0.02114963619723883,0.5450198891806309,0.020672920926712628 +flat_mae,reg,logistic,aabc_age,74,0.000774263682681127,test,0.5,0.06623947945940739,0.49572649572649574,0.06884022296945513,0.49954212454212454,0.06633552747851452 +flat_mae,reg,logistic,aabc_age,75,9.999999999999999e-05,train,0.484251968503937,0.021012580780501524,0.46313928669876625,0.02161624085832399,0.4853687697669111,0.02085546408752319 +flat_mae,reg,logistic,aabc_age,75,9.999999999999999e-05,test,0.5576923076923077,0.06502616678587095,0.5381548276285117,0.06785990768583017,0.5487637362637363,0.06499571380121424 +flat_mae,reg,logistic,aabc_age,76,0.000774263682681127,train,0.5511811023622047,0.02015659600668538,0.5422651181301209,0.020691938696322423,0.5510182896071839,0.02014280499149868 +flat_mae,reg,logistic,aabc_age,76,0.000774263682681127,test,0.4807692307692308,0.061928702563378735,0.47385878489326766,0.06411786857938939,0.4789377289377289,0.062087917828238366 +flat_mae,reg,logistic,aabc_age,77,9.999999999999999e-05,train,0.5,0.020483904649277667,0.4794090217552296,0.02121326853172217,0.49980724564576545,0.0204096378417534 +flat_mae,reg,logistic,aabc_age,77,9.999999999999999e-05,test,0.4230769230769231,0.061361476263456775,0.39268333863022403,0.0592817945814038,0.4178113553113553,0.06050129856122617 +flat_mae,reg,logistic,aabc_age,78,0.046415888336127774,train,0.8248031496062992,0.016329617120826517,0.825351641066723,0.016368454654512494,0.826009467019826,0.016319190499160526 +flat_mae,reg,logistic,aabc_age,78,0.046415888336127774,test,0.5769230769230769,0.06726482151182557,0.5689102564102564,0.06963636661562196,0.5796703296703296,0.06760678855889948 +flat_mae,reg,logistic,aabc_age,79,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,79,21.54434690031882,test,0.36538461538461536,0.06437835416665373,0.37106643356643354,0.06306057339671119,0.36469780219780223,0.06421772736691415 +flat_mae,reg,logistic,aabc_age,80,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,80,166.81005372000556,test,0.3269230769230769,0.054453973290298954,0.2918049199084668,0.04884120624972822,0.32715201465201466,0.054639627692183175 +flat_mae,reg,logistic,aabc_age,81,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,81,2.782559402207126,test,0.40384615384615385,0.06341555443563274,0.39674242424242423,0.06351748747948807,0.39903846153846156,0.06316889732471435 +flat_mae,reg,logistic,aabc_age,82,0.046415888336127774,train,0.8248031496062992,0.01651838782128184,0.8254518520728483,0.016568043940625814,0.8256419391279831,0.016515540055123627 +flat_mae,reg,logistic,aabc_age,82,0.046415888336127774,test,0.46153846153846156,0.05850676388348909,0.42366332497911446,0.062287763803514085,0.46062271062271065,0.05851114900812336 +flat_mae,reg,logistic,aabc_age,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,83,166.81005372000556,test,0.4423076923076923,0.06243486546822619,0.42411796583098027,0.06499318982295021,0.44299450549450553,0.06261319132031365 +flat_mae,reg,logistic,aabc_age,84,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,84,2.782559402207126,test,0.5384615384615384,0.06559103164269231,0.5313628899835796,0.06580459680352746,0.5325091575091575,0.06547313604104113 +flat_mae,reg,logistic,aabc_age,85,0.000774263682681127,train,0.5393700787401575,0.020800489497142294,0.5317320388005995,0.021220270600014517,0.5393566511759933,0.02074429426991904 +flat_mae,reg,logistic,aabc_age,85,0.000774263682681127,test,0.5192307692307693,0.060477635359678414,0.49306483957219255,0.0677123822922464,0.5144230769230769,0.06019865502276275 +flat_mae,reg,logistic,aabc_age,86,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,86,166.81005372000556,test,0.4423076923076923,0.052079877202883804,0.39732142857142855,0.052834098874846684,0.4384157509157509,0.05118048759047198 +flat_mae,reg,logistic,aabc_age,87,0.005994842503189409,train,0.6732283464566929,0.01995866365006709,0.6714079380950231,0.020395239182857246,0.6755097921129904,0.01996321673173766 +flat_mae,reg,logistic,aabc_age,87,0.005994842503189409,test,0.5384615384615384,0.06572936263517268,0.53001628001628,0.06741953252389994,0.5396062271062272,0.06577955925114269 +flat_mae,reg,logistic,aabc_age,88,0.000774263682681127,train,0.5433070866141733,0.020083525753612424,0.5336972564689589,0.020565600551641312,0.5451794389601622,0.020000469625145775 +flat_mae,reg,logistic,aabc_age,88,0.000774263682681127,test,0.5192307692307693,0.06405058790246103,0.5179676645193887,0.06604505456762462,0.5190018315018315,0.06421382677937684 +flat_mae,reg,logistic,aabc_age,89,9.999999999999999e-05,train,0.5059055118110236,0.020617795243113687,0.48761235001963377,0.02121322333488267,0.5057380382018033,0.02055552229760285 +flat_mae,reg,logistic,aabc_age,89,9.999999999999999e-05,test,0.4230769230769231,0.0598951129576781,0.39474921630094045,0.06394996835889986,0.4251373626373626,0.060446437786858626 +flat_mae,reg,logistic,aabc_age,90,0.005994842503189409,train,0.6535433070866141,0.020676145845055706,0.6501772314867,0.021107990753453057,0.6535932144713448,0.02071023529484053 +flat_mae,reg,logistic,aabc_age,90,0.005994842503189409,test,0.5,0.06283372440876732,0.5009990009990011,0.06069595990062417,0.5038919413919414,0.06335985398854957 +flat_mae,reg,logistic,aabc_age,91,0.005994842503189409,train,0.65748031496063,0.02097357981561805,0.6571288936578564,0.021085532185497486,0.6604509780605268,0.020864855831692012 +flat_mae,reg,logistic,aabc_age,91,0.005994842503189409,test,0.5192307692307693,0.06677989767682944,0.50625,0.07008379373361985,0.5173992673992673,0.06684419809921148 +flat_mae,reg,logistic,aabc_age,92,0.046415888336127774,train,0.8267716535433071,0.01549282582537169,0.8266177656677693,0.01562169408337846,0.8274405002790622,0.015459207976528862 +flat_mae,reg,logistic,aabc_age,92,0.046415888336127774,test,0.5384615384615384,0.062299275309926454,0.5179652255639098,0.06670666964219657,0.5350274725274725,0.06220251707622947 +flat_mae,reg,logistic,aabc_age,93,0.005994842503189409,train,0.6692913385826772,0.020416961470910197,0.6674860237596086,0.020696080055462186,0.6709924116158953,0.020427360562925507 +flat_mae,reg,logistic,aabc_age,93,0.005994842503189409,test,0.34615384615384615,0.0591195759487078,0.3353494623655914,0.05604885380197565,0.34226190476190477,0.05851947704972028 +flat_mae,reg,logistic,aabc_age,94,0.046415888336127774,train,0.8366141732283464,0.015603308925561245,0.836901420265568,0.015688110795479826,0.8385913636459534,0.015410246729151839 +flat_mae,reg,logistic,aabc_age,94,0.046415888336127774,test,0.4423076923076923,0.06477265658763827,0.43820512820512825,0.064207073658606,0.4461996336996337,0.06522094044831928 +flat_mae,reg,logistic,aabc_age,95,0.3593813663804626,train,0.9862204724409449,0.005268315291465757,0.9863673514080018,0.005210112319909275,0.986707381628688,0.005072540164409344 +flat_mae,reg,logistic,aabc_age,95,0.3593813663804626,test,0.40384615384615385,0.06308127330214665,0.3899440214957457,0.05850746486156186,0.3985805860805861,0.062146279232476405 +flat_mae,reg,logistic,aabc_age,96,0.005994842503189409,train,0.6456692913385826,0.020019946343497113,0.6445652060051218,0.02022809578786077,0.6469164577695349,0.019925513619550816 +flat_mae,reg,logistic,aabc_age,96,0.005994842503189409,test,0.4807692307692308,0.06483500907971605,0.4789746543778802,0.06314982759316491,0.4759615384615385,0.06424672924724227 +flat_mae,reg,logistic,aabc_age,97,0.005994842503189409,train,0.655511811023622,0.020585003995257794,0.6524015865220686,0.02091891454228787,0.6559944925957395,0.020573490767704747 +flat_mae,reg,logistic,aabc_age,97,0.005994842503189409,test,0.4230769230769231,0.0644840583941663,0.41905957038458697,0.06654047578169472,0.4223901098901099,0.064552303625443 +flat_mae,reg,logistic,aabc_age,98,0.046415888336127774,train,0.8385826771653543,0.0155574611061443,0.8389635471753958,0.015578124610789532,0.8399547890346747,0.015406012356299873 +flat_mae,reg,logistic,aabc_age,98,0.046415888336127774,test,0.46153846153846156,0.06175273991956927,0.4381932773109244,0.0657294544862225,0.4608516483516484,0.06192228498713 +flat_mae,reg,logistic,aabc_age,99,9.999999999999999e-05,train,0.5039370078740157,0.020565506215021595,0.484612529649596,0.021221474739213726,0.5039394770507242,0.02039803849276559 +flat_mae,reg,logistic,aabc_age,99,9.999999999999999e-05,test,0.46153846153846156,0.05921608209513886,0.4356129826791673,0.061221602362902625,0.4592490842490843,0.05913199484663096 +flat_mae,reg,logistic,aabc_age,100,0.005994842503189409,train,0.65748031496063,0.02079833135473071,0.6532903120383634,0.02122047843834821,0.6587632986119769,0.020736383141887773 +flat_mae,reg,logistic,aabc_age,100,0.005994842503189409,test,0.38461538461538464,0.06395953787518403,0.36085568326947637,0.06219265573800337,0.3928571428571428,0.06490908098708799 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..3c10da87eedb0e7016a909e12d031f18f4f9db05 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:24:44 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_age reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_age__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:25:40 time: 6.7566 data: 5.6351 max mem: 3219 +extract (train) [ 20/228] eta: 0:02:04 time: 0.2894 data: 0.1099 max mem: 3409 +extract (train) [ 40/228] eta: 0:01:19 time: 0.2397 data: 0.0823 max mem: 3409 +extract (train) [ 60/228] eta: 0:01:01 time: 0.2405 data: 0.0851 max mem: 3409 +extract (train) [ 80/228] eta: 0:00:47 time: 0.1920 data: 0.0601 max mem: 3409 +extract (train) [100/228] eta: 0:00:38 time: 0.2323 data: 0.0858 max mem: 3409 +extract (train) [120/228] eta: 0:00:31 time: 0.2489 data: 0.0886 max mem: 3409 +extract (train) [140/228] eta: 0:00:25 time: 0.2481 data: 0.0929 max mem: 3409 +extract (train) [160/228] eta: 0:00:19 time: 0.2216 data: 0.0790 max mem: 3409 +extract (train) [180/228] eta: 0:00:13 time: 0.2233 data: 0.0785 max mem: 3409 +extract (train) [200/228] eta: 0:00:07 time: 0.2268 data: 0.0805 max mem: 3409 +extract (train) [220/228] eta: 0:00:02 time: 0.1859 data: 0.0584 max mem: 3409 +extract (train) [227/228] eta: 0:00:00 time: 0.1890 data: 0.0592 max mem: 3409 +extract (train) Total time: 0:00:59 (0.2611 s / it) +extract (validation) [ 0/27] eta: 0:02:18 time: 5.1286 data: 4.9631 max mem: 3409 +extract (validation) [20/27] eta: 0:00:03 time: 0.2180 data: 0.0739 max mem: 3409 +extract (validation) [26/27] eta: 0:00:00 time: 0.1970 data: 0.0638 max mem: 3409 +extract (validation) Total time: 0:00:10 (0.4068 s / it) +extract (test) [ 0/26] eta: 0:02:31 time: 5.8380 data: 5.6421 max mem: 3409 +extract (test) [20/26] eta: 0:00:03 time: 0.2492 data: 0.0844 max mem: 3409 +extract (test) [25/26] eta: 0:00:00 time: 0.2295 data: 0.0766 max mem: 3409 +extract (test) Total time: 0:00:12 (0.4736 s / it) +feature extraction time: 0:01:22 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_age | | 0.0059948 | train | 0.66732 | 0.021495 | 0.66418 | 0.02177 | 0.66808 | 0.021492 | +| flat_mae | reg | logistic | aabc_age | | 0.0059948 | test | 0.48077 | 0.062147 | 0.45177 | 0.067547 | 0.47047 | 0.062235 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06079808224552587, "f1": 0.4636872010644802, "f1_std": 0.06166621405382305, "bacc": 0.4800824175824176, "bacc_std": 0.060858918061514826} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5, "acc_std": 0.0594296859655551, "f1": 0.46489862707535123, "f1_std": 0.0639588838236542, "bacc": 0.49633699633699635, "bacc_std": 0.058796003835472455} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06716599370261093, "f1": 0.4065772669220945, "f1_std": 0.06689519199174516, "bacc": 0.4194139194139194, "bacc_std": 0.06679561844501888} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06324193940264865, "f1": 0.4712121212121212, "f1_std": 0.06305948728158037, "bacc": 0.4878663003663004, "bacc_std": 0.06400326003078455} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06554346089635632, "f1": 0.3924548836692765, "f1_std": 0.06478927026028977, "bacc": 0.3841575091575091, "bacc_std": 0.06574948120125342} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06724910637095713, "f1": 0.4971428571428571, "f1_std": 0.0669703778305033, "bacc": 0.4981684981684981, "bacc_std": 0.06703419009347804} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06512249495460402, "f1": 0.4146273291925466, "f1_std": 0.06322521879998214, "bacc": 0.4033882783882784, "bacc_std": 0.06508756288092243} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0694157677805846, "f1": 0.48283844189016606, "f1_std": 0.069897013409641, "bacc": 0.4848901098901099, "bacc_std": 0.06971072391062516} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06641513693580088, "f1": 0.4467072683753817, "f1_std": 0.06624435365817392, "bacc": 0.4537545787545788, "bacc_std": 0.06592593175016968} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06378044579863165, "f1": 0.5000798212005109, "f1_std": 0.0623417500587251, "bacc": 0.5009157509157509, "bacc_std": 0.06393419272588227} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 166.81005372000556, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06790369093505558, "f1": 0.4874218374218374, "f1_std": 0.0653471390796774, "bacc": 0.4642857142857143, "bacc_std": 0.06811061157111241} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06491244672360587, "f1": 0.49921837421837423, "f1_std": 0.06576284646711313, "bacc": 0.5043498168498168, "bacc_std": 0.06525305586943199} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06391581000997147, "f1": 0.4855555555555556, "f1_std": 0.060912278230620454, "bacc": 0.48626373626373626, "bacc_std": 0.06470508585723983} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.0675689873191635, "f1": 0.5602020202020203, "f1_std": 0.06816234630515244, "bacc": 0.5606684981684982, "bacc_std": 0.067319450762057} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06269078572952021, "f1": 0.4984065934065934, "f1_std": 0.06065921703445822, "bacc": 0.5038919413919414, "bacc_std": 0.06349848210807552} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.069195065579792, "f1": 0.4465886287625418, "f1_std": 0.06909632817710641, "bacc": 0.44207875457875456, "bacc_std": 0.06909506416612443} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0629733084247961, "f1": 0.5216276477146042, "f1_std": 0.06370973816255238, "bacc": 0.5364010989010989, "bacc_std": 0.0626927223203718} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06262266069991033, "f1": 0.42296466973886326, "f1_std": 0.062326421294590886, "bacc": 0.4548992673992674, "bacc_std": 0.06164507788113102} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06741885326188758, "f1": 0.4627926421404682, "f1_std": 0.067909960517878, "bacc": 0.4569597069597069, "bacc_std": 0.06749092681411574} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06889099313343684, "f1": 0.5268920734437976, "f1_std": 0.06793211389773102, "bacc": 0.5190018315018315, "bacc_std": 0.06898727162107603} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06014327076033925, "f1": 0.512808591527127, "f1_std": 0.06627684705647481, "bacc": 0.5407509157509157, "bacc_std": 0.060580111292661935} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06537532739461167, "f1": 0.3943840579710145, "f1_std": 0.06336702843233422, "bacc": 0.38713369963369965, "bacc_std": 0.06572446573011298} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06063611271907587, "f1": 0.41228070175438597, "f1_std": 0.06266856286689018, "bacc": 0.42239010989010994, "bacc_std": 0.06066869274970524} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 166.81005372000556, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06306772916110474, "f1": 0.42884510125889436, "f1_std": 0.06141296405958855, "bacc": 0.43864468864468864, "bacc_std": 0.06236322940254331} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 9.999999999999999e-05, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.061148512104092764, "f1": 0.30933434381710245, "f1_std": 0.05783460542629339, "bacc": 0.3244047619047619, "bacc_std": 0.060679850862608825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0611196687272227, "f1": 0.4463812050018946, "f1_std": 0.06228192635791265, "bacc": 0.46382783882783885, "bacc_std": 0.06127057706644027} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06483318375628588, "f1": 0.3606896551724138, "f1_std": 0.061999801532850715, "bacc": 0.3630952380952381, "bacc_std": 0.06448789665452263} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06259869131097034, "f1": 0.3941628242615085, "f1_std": 0.06319913664060066, "bacc": 0.40453296703296704, "bacc_std": 0.06276200783991688} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06176222539066335, "f1": 0.3639910813823858, "f1_std": 0.05981245246892284, "bacc": 0.36309523809523814, "bacc_std": 0.061624021390559926} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0672098189501624, "f1": 0.510576923076923, "f1_std": 0.06856379871582646, "bacc": 0.5217490842490842, "bacc_std": 0.06734589745732507} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06545538025810962, "f1": 0.5499194847020934, "f1_std": 0.06568933349916388, "bacc": 0.5544871794871795, "bacc_std": 0.06524154911128721} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0646984242054979, "f1": 0.5029582056147521, "f1_std": 0.06796569233996617, "bacc": 0.5157967032967032, "bacc_std": 0.06438129394351907} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05550659644151053, "f1": 0.4883972594885907, "f1_std": 0.060094725636533695, "bacc": 0.5199175824175825, "bacc_std": 0.05581435365168408} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06541785354266967, "f1": 0.40823529411764703, "f1_std": 0.06687905946747194, "bacc": 0.4052197802197802, "bacc_std": 0.0657502775025906} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06076410640517094, "f1": 0.4359066859066859, "f1_std": 0.060020113016838655, "bacc": 0.4416208791208791, "bacc_std": 0.060726029229078084} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0667329749136692, "f1": 0.4535714285714285, "f1_std": 0.06602399623148913, "bacc": 0.4608516483516483, "bacc_std": 0.06671217122156585} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06527270966658988, "f1": 0.4889064558629776, "f1_std": 0.0678025137084713, "bacc": 0.4926739926739927, "bacc_std": 0.06566429855452084} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.0694677141815496, "f1": 0.5659600815850816, "f1_std": 0.06863578304854873, "bacc": 0.5560897435897436, "bacc_std": 0.06959255587559715} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06412509732163277, "f1": 0.49424242424242426, "f1_std": 0.0643127352043717, "bacc": 0.4967948717948718, "bacc_std": 0.06407042348843499} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06347435767961923, "f1": 0.48974358974358967, "f1_std": 0.06571324774298376, "bacc": 0.49793956043956045, "bacc_std": 0.06364187726022416} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 21.54434690031882, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06136798502312763, "f1": 0.4137875028197609, "f1_std": 0.06067959730484982, "bacc": 0.4267399267399267, "bacc_std": 0.06215274264071985} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05404188327518753, "f1": 0.44783834586466165, "f1_std": 0.06469293446750023, "bacc": 0.48305860805860806, "bacc_std": 0.05433087277196184} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.07443549886394435, "f1": 0.5354634190841088, "f1_std": 0.07654819267306086, "bacc": 0.5430402930402931, "bacc_std": 0.07443051069820195} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06773437285656515, "f1": 0.3956671982987772, "f1_std": 0.07054982715712536, "bacc": 0.3976648351648352, "bacc_std": 0.06754795098975022} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05933761591707147, "f1": 0.4439412238325282, "f1_std": 0.059329527955156204, "bacc": 0.4668040293040293, "bacc_std": 0.060182481592089485} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.062495857850906486, "f1": 0.49017077798861486, "f1_std": 0.06633923406646756, "bacc": 0.49793956043956045, "bacc_std": 0.06249446432568868} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.0631303244869095, "f1": 0.43026618542747574, "f1_std": 0.06492569894762056, "bacc": 0.4416208791208791, "bacc_std": 0.06297559671338762} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06596272705814055, "f1": 0.4630875576036867, "f1_std": 0.06618161141697047, "bacc": 0.4624542124542125, "bacc_std": 0.06624849720589296} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06452570470787078, "f1": 0.425182976416373, "f1_std": 0.06425126713017841, "bacc": 0.4386446886446887, "bacc_std": 0.06403308828400184} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06500199132134064, "f1": 0.4579310344827586, "f1_std": 0.06738048285409066, "bacc": 0.4597069597069597, "bacc_std": 0.06506012547359015} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05955270898900397, "f1": 0.43363745210727966, "f1_std": 0.06261643142351078, "bacc": 0.45787545787545786, "bacc_std": 0.05909540193136704} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06853600099183393, "f1": 0.46484949832775924, "f1_std": 0.06923231305959544, "bacc": 0.46130952380952384, "bacc_std": 0.06858733893729338} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06963794789468057, "f1": 0.534555219337828, "f1_std": 0.06943901544991202, "bacc": 0.5366300366300366, "bacc_std": 0.06948504360382732} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06321161744396087, "f1": 0.4325757575757575, "f1_std": 0.0638431855864915, "bacc": 0.4432234432234432, "bacc_std": 0.063390332039222} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.07040735235948152, "f1": 0.5375878147617278, "f1_std": 0.07129422080984721, "bacc": 0.5412087912087913, "bacc_std": 0.07064209573428236} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06600560313314631, "f1": 0.3860249189281447, "f1_std": 0.06576918505632008, "bacc": 0.3855311355311355, "bacc_std": 0.0663174984869096} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0639116786097963, "f1": 0.4620507206714103, "f1_std": 0.06229018756219902, "bacc": 0.47710622710622713, "bacc_std": 0.06349514768971937} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05253259061690254, "f1": 0.4161019246408241, "f1_std": 0.04880617611635784, "bacc": 0.4532967032967033, "bacc_std": 0.05100493664707068} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06562625034030065, "f1": 0.4317860300618921, "f1_std": 0.06456752725516178, "bacc": 0.42559523809523814, "bacc_std": 0.06580339349999566} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.000774263682681127, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06691798168048219, "f1": 0.45432240996757123, "f1_std": 0.06924742351293386, "bacc": 0.45947802197802196, "bacc_std": 0.06694929981027288} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06082621476277201, "f1": 0.43530178230722694, "f1_std": 0.062140657715511964, "bacc": 0.4592490842490843, "bacc_std": 0.06058269799207421} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.05430796469750822, "f1": 0.46287762416794676, "f1_std": 0.052428852453131086, "bacc": 0.49336080586080583, "bacc_std": 0.05343339476172293} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06010684520282766, "f1": 0.4268544120157023, "f1_std": 0.05925379367543282, "bacc": 0.44597069597069594, "bacc_std": 0.06089821940853479} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06429126584463342, "f1": 0.41380317905563346, "f1_std": 0.06422493403915741, "bacc": 0.4036172161172161, "bacc_std": 0.06426513122370014} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06503129651657899, "f1": 0.5311054150344183, "f1_std": 0.06441768599257436, "bacc": 0.5322802197802198, "bacc_std": 0.06481844711329901} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0635463768584356, "f1": 0.42620910698496905, "f1_std": 0.06370235785469322, "bacc": 0.4255952380952381, "bacc_std": 0.06395988029185722} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.0676146845154969, "f1": 0.4845238095238095, "f1_std": 0.07002488315214395, "bacc": 0.49793956043956045, "bacc_std": 0.06768772540059989} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06418827475002437, "f1": 0.48722860791826306, "f1_std": 0.06624839961620763, "bacc": 0.5009157509157509, "bacc_std": 0.0644165736633932} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.07214641383731972, "f1": 0.5031385281385281, "f1_std": 0.07435550679527836, "bacc": 0.49565018315018317, "bacc_std": 0.07235370278563255} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0676201538529793, "f1": 0.4822222222222222, "f1_std": 0.06801833737616042, "bacc": 0.48511904761904767, "bacc_std": 0.06794283808439702} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05964515385761215, "f1": 0.46054945054945057, "f1_std": 0.05836358621184717, "bacc": 0.46382783882783885, "bacc_std": 0.060035153116939605} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06509404893767626, "f1": 0.579294670846395, "f1_std": 0.06562236511713344, "bacc": 0.5769230769230769, "bacc_std": 0.06523022816258871} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06452012208486708, "f1": 0.514994425863991, "f1_std": 0.06541495200662967, "bacc": 0.5203754578754579, "bacc_std": 0.06473959612231543} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06623947945940739, "f1": 0.49572649572649574, "f1_std": 0.06884022296945513, "bacc": 0.49954212454212454, "bacc_std": 0.06633552747851452} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06502616678587095, "f1": 0.5381548276285117, "f1_std": 0.06785990768583017, "bacc": 0.5487637362637363, "bacc_std": 0.06499571380121424} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.061928702563378735, "f1": 0.47385878489326766, "f1_std": 0.06411786857938939, "bacc": 0.4789377289377289, "bacc_std": 0.062087917828238366} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.061361476263456775, "f1": 0.39268333863022403, "f1_std": 0.0592817945814038, "bacc": 0.4178113553113553, "bacc_std": 0.06050129856122617} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06726482151182557, "f1": 0.5689102564102564, "f1_std": 0.06963636661562196, "bacc": 0.5796703296703296, "bacc_std": 0.06760678855889948} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 21.54434690031882, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06437835416665373, "f1": 0.37106643356643354, "f1_std": 0.06306057339671119, "bacc": 0.36469780219780223, "bacc_std": 0.06421772736691415} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 166.81005372000556, "split": "test", "acc": 0.3269230769230769, "acc_std": 0.054453973290298954, "f1": 0.2918049199084668, "f1_std": 0.04884120624972822, "bacc": 0.32715201465201466, "bacc_std": 0.054639627692183175} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06341555443563274, "f1": 0.39674242424242423, "f1_std": 0.06351748747948807, "bacc": 0.39903846153846156, "bacc_std": 0.06316889732471435} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05850676388348909, "f1": 0.42366332497911446, "f1_std": 0.062287763803514085, "bacc": 0.46062271062271065, "bacc_std": 0.05851114900812336} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06243486546822619, "f1": 0.42411796583098027, "f1_std": 0.06499318982295021, "bacc": 0.44299450549450553, "bacc_std": 0.06261319132031365} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 2.782559402207126, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06559103164269231, "f1": 0.5313628899835796, "f1_std": 0.06580459680352746, "bacc": 0.5325091575091575, "bacc_std": 0.06547313604104113} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.060477635359678414, "f1": 0.49306483957219255, "f1_std": 0.0677123822922464, "bacc": 0.5144230769230769, "bacc_std": 0.06019865502276275} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 166.81005372000556, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.052079877202883804, "f1": 0.39732142857142855, "f1_std": 0.052834098874846684, "bacc": 0.4384157509157509, "bacc_std": 0.05118048759047198} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06572936263517268, "f1": 0.53001628001628, "f1_std": 0.06741953252389994, "bacc": 0.5396062271062272, "bacc_std": 0.06577955925114269} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06405058790246103, "f1": 0.5179676645193887, "f1_std": 0.06604505456762462, "bacc": 0.5190018315018315, "bacc_std": 0.06421382677937684} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0598951129576781, "f1": 0.39474921630094045, "f1_std": 0.06394996835889986, "bacc": 0.4251373626373626, "bacc_std": 0.060446437786858626} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06283372440876732, "f1": 0.5009990009990011, "f1_std": 0.06069595990062417, "bacc": 0.5038919413919414, "bacc_std": 0.06335985398854957} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06677989767682944, "f1": 0.50625, "f1_std": 0.07008379373361985, "bacc": 0.5173992673992673, "bacc_std": 0.06684419809921148} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.062299275309926454, "f1": 0.5179652255639098, "f1_std": 0.06670666964219657, "bacc": 0.5350274725274725, "bacc_std": 0.06220251707622947} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.0591195759487078, "f1": 0.3353494623655914, "f1_std": 0.05604885380197565, "bacc": 0.34226190476190477, "bacc_std": 0.05851947704972028} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06477265658763827, "f1": 0.43820512820512825, "f1_std": 0.064207073658606, "bacc": 0.4461996336996337, "bacc_std": 0.06522094044831928} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06308127330214665, "f1": 0.3899440214957457, "f1_std": 0.05850746486156186, "bacc": 0.3985805860805861, "bacc_std": 0.062146279232476405} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06483500907971605, "f1": 0.4789746543778802, "f1_std": 0.06314982759316491, "bacc": 0.4759615384615385, "bacc_std": 0.06424672924724227} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.0644840583941663, "f1": 0.41905957038458697, "f1_std": 0.06654047578169472, "bacc": 0.4223901098901099, "bacc_std": 0.064552303625443} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06175273991956927, "f1": 0.4381932773109244, "f1_std": 0.0657294544862225, "bacc": 0.4608516483516484, "bacc_std": 0.06192228498713} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05921608209513886, "f1": 0.4356129826791673, "f1_std": 0.061221602362902625, "bacc": 0.4592490842490843, "bacc_std": 0.05913199484663096} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06395953787518403, "f1": 0.36085568326947637, "f1_std": 0.06219265573800337, "bacc": 0.3928571428571428, "bacc_std": 0.06490908098708799} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_age | train | 100 | 10.559 | 39.792 | 0.73795 | 0.1574 | 0.73509 | 0.16098 | 0.7389 | 0.15721 | +| flat_mae | reg | logistic | aabc_age | test | 100 | 10.559 | 39.792 | 0.46788 | 0.055484 | 0.45791 | 0.05709 | 0.46712 | 0.055511 | + + +done! total time: 0:06:16 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..63f7745a39f6ad90150bbc9e1504e13794e79bf5 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..eef5d90a79733f85b5044a2256e2de2092666317 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.3593813663804626,train,0.998109640831758,0.0019095434856974628,0.9980653961915003,0.0019519750021900987,0.9983606557377049,0.0016559811539900641 +flat_mae,patch,logistic,aabc_sex,,0.3593813663804626,test,0.9090909090909091,0.039712204340148625,0.9071259709557582,0.040047074450271586,0.9166666666666667,0.037051808961116775 +flat_mae,patch,logistic,aabc_sex,1,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,1,21.54434690031882,test,0.8,0.055545677726080406,0.795677136102668,0.05685754102636625,0.7975543478260869,0.05684427094407075 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,train,0.998109640831758,0.0019372483394619702,0.9980631011617731,0.0019826079282856813,0.9983660130718954,0.0016745169470185814 +flat_mae,patch,logistic,aabc_sex,2,0.3593813663804626,test,0.8909090909090909,0.043970298013977754,0.8879076086956521,0.04530922378960111,0.8879076086956521,0.045544170797208176 +flat_mae,patch,logistic,aabc_sex,3,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,3,166.81005372000556,test,0.8,0.05533962458841562,0.7931623931623932,0.057754725710885295,0.7914402173913043,0.05794035342320279 +flat_mae,patch,logistic,aabc_sex,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,4,166.81005372000556,test,0.9272727272727272,0.035898847791082,0.9252717391304348,0.03696366931149015,0.9252717391304348,0.037003399476776486 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,train,0.9640831758034026,0.008357028810048498,0.9631541323753139,0.008568577998026216,0.9628725929833817,0.008632324131035894 +flat_mae,patch,logistic,aabc_sex,5,0.046415888336127774,test,0.8545454545454545,0.04668303530324442,0.8484848484848485,0.04948759803727418,0.8444293478260869,0.049756352301842256 +flat_mae,patch,logistic,aabc_sex,6,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,6,21.54434690031882,test,0.8545454545454545,0.04940189710948889,0.8505434782608696,0.05084945459514111,0.8505434782608696,0.05092912751421961 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,train,0.998109640831758,0.0019467542460676213,0.998060743809227,0.001999845874718282,0.9977578475336323,0.0023090425923088997 +flat_mae,patch,logistic,aabc_sex,7,0.3593813663804626,test,0.8727272727272727,0.04443182538944372,0.8699763593380614,0.04538297596688734,0.8722826086956521,0.04509113745744727 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,8,2.782559402207126,test,0.8181818181818182,0.04843028899936465,0.8131793478260869,0.049996088190895065,0.8131793478260869,0.05020006045933123 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,train,0.9565217391304348,0.008765948293186034,0.9554513267207827,0.008974298780750766,0.9557284797327003,0.009016373008906127 +flat_mae,patch,logistic,aabc_sex,9,0.046415888336127774,test,0.8909090909090909,0.042126280052650976,0.8863636363636364,0.044493520962427646,0.8817934782608696,0.04536479520923887 +flat_mae,patch,logistic,aabc_sex,10,0.3593813663804626,train,0.998109640831758,0.001961646393972089,0.998060743809227,0.002014877826435538,0.9977578475336323,0.0023267061489041048 +flat_mae,patch,logistic,aabc_sex,10,0.3593813663804626,test,0.8727272727272727,0.04395164886573116,0.8699763593380614,0.04476068417326131,0.8722826086956521,0.04437677673148388 +flat_mae,patch,logistic,aabc_sex,11,0.3593813663804626,train,0.998109640831758,0.0019527364458632199,0.998060743809227,0.002006143128410086,0.9977578475336323,0.0023161380714386537 +flat_mae,patch,logistic,aabc_sex,11,0.3593813663804626,test,0.9090909090909091,0.04008709526283453,0.905982905982906,0.041648567481165716,0.9035326086956521,0.04207945361683397 +flat_mae,patch,logistic,aabc_sex,12,0.046415888336127774,train,0.9565217391304348,0.008851161454536426,0.9553971076122221,0.009084502051907814,0.9551203141944371,0.009208835659830916 +flat_mae,patch,logistic,aabc_sex,12,0.046415888336127774,test,0.8363636363636363,0.0495129468000688,0.8307692307692308,0.05182082515569783,0.8288043478260869,0.05217681326503837 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,train,0.998109640831758,0.001978309414982629,0.9980631011617731,0.002024382585090262,0.9983660130718954,0.0017100092819049045 +flat_mae,patch,logistic,aabc_sex,13,0.3593813663804626,test,0.9272727272727272,0.03460280407115553,0.9242424242424243,0.03665187430916721,0.9191576086956521,0.03823710476886646 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,train,0.9508506616257089,0.008876472089044254,0.9494843391902215,0.00914760879192093,0.9483938567953341,0.009386872236732204 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,test,0.9272727272727272,0.03550273647932877,0.9252717391304348,0.03664522233668814,0.9252717391304348,0.03709078061780021 +flat_mae,patch,logistic,aabc_sex,15,0.046415888336127774,train,0.9546313799621928,0.008943082046220572,0.9533701592525121,0.009229479099397222,0.9522699961898062,0.009581616795351513 +flat_mae,patch,logistic,aabc_sex,15,0.046415888336127774,test,0.8727272727272727,0.044174021010446894,0.8699763593380614,0.04503006956727032,0.8722826086956521,0.04456571397522908 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,train,0.9508506616257089,0.00940760634237716,0.9495480822842386,0.009659938618528518,0.9490020223335971,0.009751409914965484 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,test,0.8545454545454545,0.04786206075279385,0.8533333333333333,0.048019281458844404,0.8627717391304348,0.04687122170894431 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,train,0.9527410207939508,0.009039712564195293,0.9515185952306762,0.009288869944232656,0.9512441747999649,0.009490964335948471 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,test,0.8909090909090909,0.040053451889499644,0.884453781512605,0.044285793593732824,0.8756793478260869,0.04534047762101824 +flat_mae,patch,logistic,aabc_sex,18,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,18,0.3593813663804626,test,0.8363636363636363,0.047042797465588995,0.8307692307692308,0.04942761169518995,0.8288043478260869,0.04995589863020505 +flat_mae,patch,logistic,aabc_sex,19,0.3593813663804626,train,0.996219281663516,0.002657110795183556,0.9961238606055277,0.0027248168702683905,0.9961238606055277,0.002791510427272268 +flat_mae,patch,logistic,aabc_sex,19,0.3593813663804626,test,0.8545454545454545,0.04499901192670972,0.8521505376344086,0.045502625199916075,0.8566576086956521,0.044787784631235256 +flat_mae,patch,logistic,aabc_sex,20,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,20,0.3593813663804626,test,0.8545454545454545,0.04666603698906155,0.8484848484848485,0.04971311014991755,0.8444293478260869,0.04992181009744147 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,train,0.9640831758034026,0.008122379514734945,0.9631541323753139,0.008342390217229012,0.9628725929833817,0.008497516289065775 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,test,0.8181818181818182,0.050992386403014886,0.8131793478260869,0.05284604188768158,0.8131793478260869,0.053286442673780424 +flat_mae,patch,logistic,aabc_sex,22,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,22,21.54434690031882,test,0.9272727272727272,0.03391493490952556,0.9260752688172043,0.03422762024442099,0.9313858695652174,0.032438174474914656 +flat_mae,patch,logistic,aabc_sex,23,0.046415888336127774,train,0.9508506616257089,0.009324109169029723,0.9494189467490438,0.009634583940443097,0.9477856912570708,0.010037771584235383 +flat_mae,patch,logistic,aabc_sex,23,0.046415888336127774,test,0.8727272727272727,0.04486823316231024,0.8711943793911007,0.04500858678587805,0.8783967391304348,0.04346320924503253 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,train,0.9527410207939508,0.009313108024827934,0.9515185952306762,0.009557458378579846,0.9512441747999649,0.009663230132771792 +flat_mae,patch,logistic,aabc_sex,24,0.046415888336127774,test,0.8181818181818182,0.05552548666532771,0.8106060606060606,0.0586234900542526,0.8070652173913043,0.05838243497298046 +flat_mae,patch,logistic,aabc_sex,25,0.3593813663804626,train,0.998109640831758,0.0019120532117240972,0.9980631011617731,0.001956855670371989,0.9983660130718954,0.0016527388055588854 +flat_mae,patch,logistic,aabc_sex,25,0.3593813663804626,test,0.9090909090909091,0.03777709306352963,0.9071259709557582,0.03850443746280451,0.9096467391304348,0.03817150613806454 +flat_mae,patch,logistic,aabc_sex,26,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,26,0.3593813663804626,test,0.8545454545454545,0.04483039110851195,0.8484848484848485,0.04782164287359455,0.8444293478260869,0.04841654876479196 +flat_mae,patch,logistic,aabc_sex,27,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,27,2.782559402207126,test,0.9636363636363636,0.025285124493685165,0.9626358695652174,0.02607369779271476,0.9626358695652174,0.026542112992565484 +flat_mae,patch,logistic,aabc_sex,28,0.046415888336127774,train,0.9565217391304348,0.00907298673753301,0.9552843287504089,0.009355633040352772,0.9539039831179108,0.009675315608121437 +flat_mae,patch,logistic,aabc_sex,28,0.046415888336127774,test,0.8545454545454545,0.04703233984967721,0.84593837535014,0.05186361353340904,0.8383152173913043,0.052191983732967996 +flat_mae,patch,logistic,aabc_sex,29,0.3593813663804626,train,0.998109640831758,0.001902700733678166,0.998060743809227,0.00195438371567798,0.9977578475336323,0.0022567907805285774 +flat_mae,patch,logistic,aabc_sex,29,0.3593813663804626,test,0.8909090909090909,0.04206684959336442,0.8879076086956521,0.043301426617399975,0.8879076086956521,0.04330573640425172 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,train,0.9489603024574669,0.009082066108554504,0.947507690272219,0.009377078554724541,0.9461517043289662,0.009697602698806908 +flat_mae,patch,logistic,aabc_sex,30,0.046415888336127774,test,0.8545454545454545,0.04982549382304948,0.8521505376344086,0.05046727866183209,0.8566576086956521,0.049909741682399804 +flat_mae,patch,logistic,aabc_sex,31,0.046415888336127774,train,0.9546313799621928,0.008885843145768717,0.9533701592525121,0.009154992638294477,0.9522699961898062,0.009431399838134924 +flat_mae,patch,logistic,aabc_sex,31,0.046415888336127774,test,0.8181818181818182,0.05046218124038226,0.8131793478260869,0.051685388047205426,0.8131793478260869,0.05127315777327244 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,train,0.9527410207939508,0.008598367614215882,0.9514580924590283,0.008854244073858729,0.9506360092617017,0.009105194511765306 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,test,0.8727272727272727,0.04374076903797025,0.8683760683760684,0.04564555700262949,0.8661684782608696,0.04623060735934749 +flat_mae,patch,logistic,aabc_sex,33,0.3593813663804626,train,0.996219281663516,0.002689055684127725,0.9961238606055277,0.0027573301223083094,0.9961238606055277,0.0028068313048470787 +flat_mae,patch,logistic,aabc_sex,33,0.3593813663804626,test,0.8727272727272727,0.04490240656916372,0.8699763593380614,0.0456716004995731,0.8722826086956521,0.0450853490812822 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,train,0.9546313799621928,0.009236755287218694,0.9534289990316049,0.00949956225396909,0.9528781617280695,0.00971380339304752 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,test,0.8545454545454545,0.04968942884400034,0.8505434782608696,0.05119954573990153,0.8505434782608696,0.05138667606438929 +flat_mae,patch,logistic,aabc_sex,35,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,35,2.782559402207126,test,0.8363636363636363,0.051624518487739,0.8328267477203647,0.05249239268094122,0.8349184782608696,0.051773467120423196 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,train,0.9489603024574669,0.00893675688902045,0.9476400828491303,0.0091736883270683,0.9473680354054925,0.009316728751671093 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,test,0.9636363636363636,0.02637554589932887,0.9630376344086022,0.026524694549674082,0.96875,0.022666484757235733 +flat_mae,patch,logistic,aabc_sex,37,0.3593813663804626,train,0.996219281663516,0.0025557879664796445,0.9961238606055277,0.0026214192795416913,0.9961238606055277,0.0027039149756076693 +flat_mae,patch,logistic,aabc_sex,37,0.3593813663804626,test,0.8363636363636363,0.0515185724354346,0.8307692307692308,0.053888210685652846,0.8288043478260869,0.054012511428529135 +flat_mae,patch,logistic,aabc_sex,38,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,38,2.782559402207126,test,0.8363636363636363,0.04703430785822703,0.8281846581048247,0.05076197120810574,0.8226902173913043,0.05084525347121735 +flat_mae,patch,logistic,aabc_sex,39,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,39,2.782559402207126,test,0.8727272727272727,0.04320347399560891,0.8683760683760684,0.0452604713751759,0.8661684782608696,0.04568964517030784 +flat_mae,patch,logistic,aabc_sex,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,40,21.54434690031882,test,0.9090909090909091,0.038698427157480314,0.9071259709557582,0.03943590595312746,0.9096467391304348,0.03877512200932932 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,train,0.9546313799621928,0.009272303250927455,0.9534289990316049,0.009521658092668932,0.9528781617280695,0.009652563197005658 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,test,0.8727272727272727,0.04524028045013216,0.8683760683760684,0.04727557271208694,0.8661684782608696,0.047538110018885395 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,42,0.3593813663804626,test,0.8363636363636363,0.051122914595064045,0.8343927735028438,0.05157833436345624,0.8410326086956521,0.05083537403936008 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,train,0.9508506616257089,0.009590748743929818,0.9495480822842386,0.009853214218191596,0.9490020223335971,0.010045177053987947 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,test,0.9090909090909091,0.03770079684362956,0.9071259709557582,0.03850495601352627,0.9096467391304348,0.03808222432489397 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,train,0.9565217391304348,0.008863829434458148,0.9553971076122221,0.00910878378267796,0.9551203141944371,0.009299658582119796 +flat_mae,patch,logistic,aabc_sex,44,0.046415888336127774,test,0.8181818181818182,0.05036660312889683,0.8106060606060606,0.05386528373210446,0.8070652173913043,0.05377539851684119 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,train,0.9546313799621928,0.009211055881098367,0.9534863272663325,0.009447311424878401,0.9534863272663325,0.009560363784776 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,test,0.9272727272727272,0.034506216950927315,0.9266666666666667,0.03439735271827876,0.9375,0.029653780192203154 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,train,0.9546313799621928,0.009319945386055848,0.9534289990316049,0.009579216850865916,0.9528781617280695,0.009768788078628065 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,test,0.9272727272727272,0.03507189310474149,0.9252717391304348,0.0360820820501194,0.9252717391304348,0.03609269110714443 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,train,0.9527410207939508,0.009297101572057844,0.951396009511314,0.009594878044952048,0.9500278437234386,0.009927329665405018 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,test,0.9090909090909091,0.03855607057925376,0.905982905982906,0.04025776235737081,0.9035326086956521,0.04123633691616066 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,train,0.9546313799621928,0.009094349588758854,0.9534289990316049,0.009344409607675276,0.9528781617280695,0.009509712952373664 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,test,0.8727272727272727,0.0447496027038091,0.8699763593380614,0.04565821934424626,0.8722826086956521,0.04552717137876866 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,train,0.996219281663516,0.0024471617579690103,0.9961238606055277,0.002509051547141568,0.9961238606055277,0.002558188705325346 +flat_mae,patch,logistic,aabc_sex,49,0.3593813663804626,test,0.8909090909090909,0.042411210119515014,0.8879076086956521,0.04362146411991292,0.8879076086956521,0.04363094403663936 +flat_mae,patch,logistic,aabc_sex,50,0.005994842503189409,train,0.9092627599243857,0.012097767001549943,0.9064958020327,0.012555420392550877,0.9045399923796125,0.012907739372434623 +flat_mae,patch,logistic,aabc_sex,50,0.005994842503189409,test,0.8909090909090909,0.04323965122450144,0.8879076086956521,0.04435367947873587,0.8879076086956521,0.044255169712690424 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,train,0.9508506616257089,0.008702614948886838,0.9496101878718604,0.008934898648456892,0.9496101878718604,0.009136817461571597 +flat_mae,patch,logistic,aabc_sex,51,0.046415888336127774,test,0.8727272727272727,0.042230003825958796,0.8639095086603039,0.04792332333618021,0.8539402173913043,0.048416049506693475 +flat_mae,patch,logistic,aabc_sex,52,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,52,2.782559402207126,test,0.8181818181818182,0.051598898059859115,0.8106060606060606,0.05484228685978499,0.8070652173913043,0.05489476250608612 +flat_mae,patch,logistic,aabc_sex,53,0.3593813663804626,train,0.998109640831758,0.0018960179951242827,0.998060743809227,0.0019473651470028473,0.9977578475336323,0.002248864393320048 +flat_mae,patch,logistic,aabc_sex,53,0.3593813663804626,test,0.8545454545454545,0.048173186190749236,0.8505434782608696,0.04958581480642769,0.8505434782608696,0.04950875436945977 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,train,0.9603024574669187,0.00879871446836554,0.9592247976655839,0.00906128149546109,0.9583882880506462,0.009363234723643818 +flat_mae,patch,logistic,aabc_sex,54,0.046415888336127774,test,0.8545454545454545,0.047618580997320206,0.8521505376344086,0.04811393712032087,0.8566576086956521,0.047202912028087386 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,train,0.998109640831758,0.0018926262398160903,0.998060743809227,0.0019439147759160464,0.9977578475336323,0.0022448414369119034 +flat_mae,patch,logistic,aabc_sex,55,0.3593813663804626,test,0.8363636363636363,0.04855833673135541,0.8328267477203647,0.049621239363186916,0.8349184782608696,0.0497087835126028 +flat_mae,patch,logistic,aabc_sex,56,0.046415888336127774,train,0.9546313799621928,0.009111687281487396,0.9533701592525121,0.009387578148014783,0.9522699961898062,0.009654133204550004 +flat_mae,patch,logistic,aabc_sex,56,0.046415888336127774,test,0.8181818181818182,0.04964310310557158,0.8131793478260869,0.051485263957843044,0.8131793478260869,0.05156293089626337 +flat_mae,patch,logistic,aabc_sex,57,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,57,21.54434690031882,test,0.8363636363636363,0.045599057551519356,0.8250265111346766,0.05134768838175725,0.8165760869565217,0.050967508567413354 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,58,0.3593813663804626,test,0.8,0.05311332030092289,0.795677136102668,0.05416334243226097,0.7975543478260869,0.05417562535732104 +flat_mae,patch,logistic,aabc_sex,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,59,166.81005372000556,test,0.8727272727272727,0.041031719236111396,0.8639095086603039,0.04695391264275241,0.8539402173913043,0.04747043652680443 +flat_mae,patch,logistic,aabc_sex,60,0.005994842503189409,train,0.9073724007561437,0.012270513424240624,0.904352318222911,0.01275244222622289,0.9016896743749816,0.013056104764909737 +flat_mae,patch,logistic,aabc_sex,60,0.005994842503189409,test,0.8545454545454545,0.0468496310965657,0.84593837535014,0.05127841312099915,0.8383152173913043,0.05149619596692247 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,train,0.9489603024574669,0.009723780451092841,0.9475747398557507,0.01000946599370982,0.9467598698672295,0.010214924416137194 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,test,0.9454545454545454,0.029911163232987342,0.9447975911676145,0.02992294191247988,0.953125,0.025704905903348486 +flat_mae,patch,logistic,aabc_sex,62,0.046415888336127774,train,0.945179584120983,0.010424778086659484,0.943691387252473,0.01075695159705787,0.9428837304727571,0.011117638376008706 +flat_mae,patch,logistic,aabc_sex,62,0.046415888336127774,test,0.9090909090909091,0.03693972754466904,0.9079959852793577,0.03709456819605891,0.9157608695652174,0.035002578341222744 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,train,0.945179584120983,0.01002760545168473,0.943691387252473,0.01031577810019327,0.9428837304727571,0.010523859681014916 +flat_mae,patch,logistic,aabc_sex,63,0.046415888336127774,test,0.9636363636363636,0.023900620691134526,0.9630376344086022,0.02404021258342928,0.96875,0.02053959590644373 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,64,0.3593813663804626,test,0.8181818181818182,0.050242177138698524,0.8151881720430108,0.05082915942644486,0.8192934782608696,0.05060763465251348 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,train,0.9054820415879017,0.012677974747561823,0.9025997937840624,0.013190323389499704,0.9006638529851403,0.013627958861892393 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,test,0.8727272727272727,0.04368595666707271,0.8639095086603039,0.04917183662842551,0.8539402173913043,0.04954903798534853 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,train,0.9621928166351607,0.008152767354636327,0.9611908325263374,0.008376876836540283,0.960630440517014,0.008558546858791434 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,test,0.8909090909090909,0.039314792286898624,0.8879076086956521,0.04069510572466014,0.8879076086956521,0.04128729935899808 +flat_mae,patch,logistic,aabc_sex,67,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,67,166.81005372000556,test,0.8909090909090909,0.04120529533490039,0.89,0.04119662961842159,0.9001358695652174,0.03863432093362383 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,test,0.8727272727272727,0.04406030427973846,0.8663658451926415,0.04760142514449367,0.8600543478260869,0.04827937692514401 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,train,0.947069943289225,0.009981987128726826,0.9456671655368724,0.010258176469777799,0.9451258829391249,0.010441459180346425 +flat_mae,patch,logistic,aabc_sex,69,0.046415888336127774,test,0.9818181818181818,0.018124236091054922,0.9811965811965813,0.019033310260698953,0.9782608695652174,0.02167028228278305 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,train,0.998109640831758,0.0019759055502986296,0.9980631011617731,0.0020217577076651044,0.9983660130718954,0.0017079314315489632 +flat_mae,patch,logistic,aabc_sex,70,0.3593813663804626,test,0.9272727272727272,0.03443626763930174,0.9252717391304348,0.03550305823827617,0.9252717391304348,0.03587168685569101 +flat_mae,patch,logistic,aabc_sex,71,0.046415888336127774,train,0.9603024574669187,0.00856614332937582,0.9593251243972363,0.008777728616275692,0.9596046191271725,0.008887950773957884 +flat_mae,patch,logistic,aabc_sex,71,0.046415888336127774,test,0.8909090909090909,0.03779948838693521,0.8863636363636364,0.03987514074950978,0.8817934782608696,0.04049240893040475 +flat_mae,patch,logistic,aabc_sex,72,0.046415888336127774,train,0.947069943289225,0.009418636731073897,0.9456671655368724,0.009693101779316949,0.9451258829391249,0.009939439012570757 +flat_mae,patch,logistic,aabc_sex,72,0.046415888336127774,test,0.9272727272727272,0.03477808752506134,0.9252717391304348,0.035761751674160236,0.9252717391304348,0.035871101411233335 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,train,0.9489603024574669,0.008970435274662318,0.9475747398557507,0.009251476810454481,0.9467598698672295,0.009626197425232073 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,test,0.9636363636363636,0.025649023308777573,0.9621212121212122,0.02738407179098347,0.9565217391304348,0.030667310477886227 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,train,0.9527410207939508,0.008957178433331789,0.9515185952306762,0.009199710157082718,0.9512441747999649,0.009424875300229637 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,test,0.8727272727272727,0.0450084877211193,0.8683760683760684,0.04687781241902098,0.8661684782608696,0.047518657783364324 +flat_mae,patch,logistic,aabc_sex,75,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,75,2.782559402207126,test,0.9090909090909091,0.03634492245733581,0.9071259709557582,0.037104363956088945,0.9096467391304348,0.03678715775118489 +flat_mae,patch,logistic,aabc_sex,76,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,76,0.3593813663804626,test,0.9272727272727272,0.0348243478993013,0.9252717391304348,0.03585686355615123,0.9252717391304348,0.03609528882492067 +flat_mae,patch,logistic,aabc_sex,77,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,77,2.782559402207126,test,0.8727272727272727,0.04621164391209049,0.8663658451926415,0.04988195492973766,0.8600543478260869,0.05061448340190723 +flat_mae,patch,logistic,aabc_sex,78,0.046415888336127774,train,0.943289224952741,0.00968599894426268,0.9417126990656403,0.00999607253005429,0.9406415780063895,0.010324621262472246 +flat_mae,patch,logistic,aabc_sex,78,0.046415888336127774,test,0.9454545454545454,0.031974287190214494,0.9442755825734549,0.032487563467902936,0.9470108695652174,0.03135800602413087 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,train,0.947069943289225,0.009763117848886851,0.9456671655368724,0.010044138700402534,0.9451258829391249,0.010265461199131782 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,test,0.9090909090909091,0.0366154734034941,0.9027925061859314,0.04175030728071112,0.8913043478260869,0.043779370373742944 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,train,0.9489603024574669,0.009484383143254432,0.947507690272219,0.009793949968340756,0.9461517043289662,0.010113960113885642 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,test,0.8545454545454545,0.04883764974953083,0.8484848484848485,0.05186675672956636,0.8444293478260869,0.05257988432738683 +flat_mae,patch,logistic,aabc_sex,81,0.3593813663804626,train,0.996219281663516,0.0027121219560621444,0.9961238606055277,0.0027808567614958867,0.9961238606055277,0.002812085420563384 +flat_mae,patch,logistic,aabc_sex,81,0.3593813663804626,test,0.9272727272727272,0.032211922232060264,0.9229691876750701,0.03561559772124731,0.9130434782608696,0.038514254842680735 +flat_mae,patch,logistic,aabc_sex,82,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,82,2.782559402207126,test,0.8909090909090909,0.041051872044367325,0.8863636363636364,0.04324528591513215,0.8817934782608696,0.044170963929386985 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,train,0.998109640831758,0.0018919426260339117,0.998060743809227,0.0019431709263222916,0.9977578475336323,0.0022440306035245165 +flat_mae,patch,logistic,aabc_sex,83,0.3593813663804626,test,0.8727272727272727,0.040373315792725926,0.8609606356085229,0.04853180712733903,0.8478260869565217,0.04827244279565058 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,train,0.9565217391304348,0.009110837771384956,0.9553971076122221,0.009348750022805774,0.9551203141944371,0.009426608204673866 +flat_mae,patch,logistic,aabc_sex,84,0.046415888336127774,test,0.8545454545454545,0.04880590670119363,0.8505434782608696,0.050101887263818305,0.8505434782608696,0.04996443131726087 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,train,0.947069943289225,0.00984812250003002,0.9455985191279309,0.010169953228342571,0.9445177174008617,0.0105659712914264 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,test,0.8909090909090909,0.04109462573698427,0.8863636363636364,0.043493979920730806,0.8817934782608696,0.04451271535812307 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,train,0.9527410207939508,0.009562634797088713,0.9515185952306762,0.00980898546321916,0.9512441747999649,0.009870756523545098 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,test,0.9272727272727272,0.03626989736055859,0.9252717391304348,0.03741219636045619,0.9252717391304348,0.037677305979260216 +flat_mae,patch,logistic,aabc_sex,87,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,87,2.782559402207126,test,0.8727272727272727,0.042201312109952836,0.8663658451926415,0.045573420218709915,0.8600543478260869,0.04627126396751769 +flat_mae,patch,logistic,aabc_sex,88,0.046415888336127774,train,0.9527410207939508,0.00897269767112116,0.9515185952306762,0.009207951107180382,0.9512441747999649,0.009338812540050761 +flat_mae,patch,logistic,aabc_sex,88,0.046415888336127774,test,0.9090909090909091,0.03982772820390711,0.9045470322804582,0.042893741659459604,0.8974184782608696,0.04467382717449169 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,train,0.9508506616257089,0.009501915509392467,0.9496101878718604,0.009749324088814279,0.9496101878718604,0.009909062008173255 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,test,0.8727272727272727,0.03911434392683131,0.8609606356085229,0.04664748928434424,0.8478260869565217,0.046767150347298315 +flat_mae,patch,logistic,aabc_sex,90,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,90,166.81005372000556,test,0.8181818181818182,0.05270846059392947,0.8151881720430108,0.0535994479199408,0.8192934782608696,0.05363743039387181 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,train,0.9527410207939508,0.008952881519359414,0.951396009511314,0.009244947076325335,0.9500278437234386,0.00960525921539464 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,test,0.9090909090909091,0.038714739756069205,0.9071259709557582,0.0393426621427502,0.9096467391304348,0.03849996554830382 +flat_mae,patch,logistic,aabc_sex,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,92,21.54434690031882,test,0.8909090909090909,0.039491160220195984,0.884453781512605,0.043686354740888424,0.8756793478260869,0.044879934503244075 +flat_mae,patch,logistic,aabc_sex,93,0.3593813663804626,train,0.998109640831758,0.00194412756919842,0.9980631011617731,0.0019897717804882808,0.9983660130718954,0.0016804632093234532 +flat_mae,patch,logistic,aabc_sex,93,0.3593813663804626,test,0.8909090909090909,0.03762346726786618,0.8821428571428571,0.043833119862641545,0.8695652173913043,0.04498458042897044 +flat_mae,patch,logistic,aabc_sex,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,94,2.782559402207126,test,0.9454545454545454,0.030113921439473976,0.9427282193682749,0.03291751756764983,0.9347826086956521,0.036005775634153664 +flat_mae,patch,logistic,aabc_sex,95,0.3593813663804626,train,0.996219281663516,0.0026115405982341786,0.9961238606055277,0.0026779867214890623,0.9961238606055277,0.0027239711693361904 +flat_mae,patch,logistic,aabc_sex,95,0.3593813663804626,test,0.8909090909090909,0.041744108308986505,0.8879076086956521,0.043012019517635905,0.8879076086956521,0.04324584353268938 +flat_mae,patch,logistic,aabc_sex,96,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,96,0.3593813663804626,test,0.9272727272727272,0.032765634082976405,0.9242424242424243,0.03465742060929422,0.9191576086956521,0.03616219920976261 +flat_mae,patch,logistic,aabc_sex,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,97,166.81005372000556,test,0.9272727272727272,0.0325119990564196,0.9242424242424243,0.03445643340295057,0.9191576086956521,0.036065106418703925 +flat_mae,patch,logistic,aabc_sex,98,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,98,2.782559402207126,test,0.8,0.05284469683394041,0.7861435136090491,0.05921950422359447,0.7792119565217391,0.05780370877827094 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,train,0.9527410207939508,0.009467114995821193,0.9515185952306762,0.009714999182467689,0.9512441747999649,0.009819539482256402 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,test,0.9090909090909091,0.038207281552557024,0.9045470322804582,0.041662992607520793,0.8974184782608696,0.04344355569707023 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,train,0.996219281663516,0.0025808325420027902,0.9961238606055277,0.002646216899870157,0.9961238606055277,0.0026996448812896283 +flat_mae,patch,logistic,aabc_sex,100,0.3593813663804626,test,0.9090909090909091,0.03745509267031853,0.9079959852793577,0.03754301409686839,0.9157608695652174,0.035206404808892096 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..ae884916533f02c8e1ba4f38daff0b33a49fefbf --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:52:08 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:25:56 time: 6.5956 data: 5.3922 max mem: 3219 +extract (train) [ 20/236] eta: 0:02:04 time: 0.2755 data: 0.1021 max mem: 3409 +extract (train) [ 40/236] eta: 0:01:19 time: 0.2249 data: 0.0763 max mem: 3409 +extract (train) [ 60/236] eta: 0:01:02 time: 0.2457 data: 0.0873 max mem: 3409 +extract (train) [ 80/236] eta: 0:00:50 time: 0.2468 data: 0.0899 max mem: 3409 +extract (train) [100/236] eta: 0:00:42 time: 0.2483 data: 0.0917 max mem: 3409 +extract (train) [120/236] eta: 0:00:34 time: 0.2452 data: 0.0863 max mem: 3409 +extract (train) [140/236] eta: 0:00:28 time: 0.2468 data: 0.0903 max mem: 3409 +extract (train) [160/236] eta: 0:00:21 time: 0.2012 data: 0.0644 max mem: 3409 +extract (train) [180/236] eta: 0:00:15 time: 0.2193 data: 0.0785 max mem: 3409 +extract (train) [200/236] eta: 0:00:09 time: 0.2372 data: 0.0854 max mem: 3409 +extract (train) [220/236] eta: 0:00:04 time: 0.1988 data: 0.0654 max mem: 3409 +extract (train) [235/236] eta: 0:00:00 time: 0.1934 data: 0.0633 max mem: 3409 +extract (train) Total time: 0:01:01 (0.2624 s / it) +extract (validation) [ 0/29] eta: 0:02:17 time: 4.7353 data: 4.5870 max mem: 3409 +extract (validation) [20/29] eta: 0:00:03 time: 0.2122 data: 0.0702 max mem: 3409 +extract (validation) [28/29] eta: 0:00:00 time: 0.1909 data: 0.0594 max mem: 3409 +extract (validation) Total time: 0:00:10 (0.3782 s / it) +extract (test) [ 0/28] eta: 0:02:08 time: 4.5844 data: 4.4390 max mem: 3409 +extract (test) [20/28] eta: 0:00:03 time: 0.2058 data: 0.0661 max mem: 3409 +extract (test) [27/28] eta: 0:00:00 time: 0.1758 data: 0.0523 max mem: 3409 +extract (test) Total time: 0:00:10 (0.3656 s / it) +feature extraction time: 0:01:23 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.35938 | train | 0.99811 | 0.0019095 | 0.99807 | 0.001952 | 0.99836 | 0.001656 | +| flat_mae | patch | logistic | aabc_sex | | 0.35938 | test | 0.90909 | 0.039712 | 0.90713 | 0.040047 | 0.91667 | 0.037052 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 21.54434690031882, "split": "test", "acc": 0.8, "acc_std": 0.055545677726080406, "f1": 0.795677136102668, "f1_std": 0.05685754102636625, "bacc": 0.7975543478260869, "bacc_std": 0.05684427094407075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.043970298013977754, "f1": 0.8879076086956521, "f1_std": 0.04530922378960111, "bacc": 0.8879076086956521, "bacc_std": 0.045544170797208176} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 166.81005372000556, "split": "test", "acc": 0.8, "acc_std": 0.05533962458841562, "f1": 0.7931623931623932, "f1_std": 0.057754725710885295, "bacc": 0.7914402173913043, "bacc_std": 0.05794035342320279} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.035898847791082, "f1": 0.9252717391304348, "f1_std": 0.03696366931149015, "bacc": 0.9252717391304348, "bacc_std": 0.037003399476776486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04668303530324442, "f1": 0.8484848484848485, "f1_std": 0.04948759803727418, "bacc": 0.8444293478260869, "bacc_std": 0.049756352301842256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04940189710948889, "f1": 0.8505434782608696, "f1_std": 0.05084945459514111, "bacc": 0.8505434782608696, "bacc_std": 0.05092912751421961} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04443182538944372, "f1": 0.8699763593380614, "f1_std": 0.04538297596688734, "bacc": 0.8722826086956521, "bacc_std": 0.04509113745744727} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04843028899936465, "f1": 0.8131793478260869, "f1_std": 0.049996088190895065, "bacc": 0.8131793478260869, "bacc_std": 0.05020006045933123} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042126280052650976, "f1": 0.8863636363636364, "f1_std": 0.044493520962427646, "bacc": 0.8817934782608696, "bacc_std": 0.04536479520923887} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04395164886573116, "f1": 0.8699763593380614, "f1_std": 0.04476068417326131, "bacc": 0.8722826086956521, "bacc_std": 0.04437677673148388} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.04008709526283453, "f1": 0.905982905982906, "f1_std": 0.041648567481165716, "bacc": 0.9035326086956521, "bacc_std": 0.04207945361683397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.0495129468000688, "f1": 0.8307692307692308, "f1_std": 0.05182082515569783, "bacc": 0.8288043478260869, "bacc_std": 0.05217681326503837} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03460280407115553, "f1": 0.9242424242424243, "f1_std": 0.03665187430916721, "bacc": 0.9191576086956521, "bacc_std": 0.03823710476886646} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03550273647932877, "f1": 0.9252717391304348, "f1_std": 0.03664522233668814, "bacc": 0.9252717391304348, "bacc_std": 0.03709078061780021} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044174021010446894, "f1": 0.8699763593380614, "f1_std": 0.04503006956727032, "bacc": 0.8722826086956521, "bacc_std": 0.04456571397522908} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04786206075279385, "f1": 0.8533333333333333, "f1_std": 0.048019281458844404, "bacc": 0.8627717391304348, "bacc_std": 0.04687122170894431} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.040053451889499644, "f1": 0.884453781512605, "f1_std": 0.044285793593732824, "bacc": 0.8756793478260869, "bacc_std": 0.04534047762101824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.047042797465588995, "f1": 0.8307692307692308, "f1_std": 0.04942761169518995, "bacc": 0.8288043478260869, "bacc_std": 0.04995589863020505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04499901192670972, "f1": 0.8521505376344086, "f1_std": 0.045502625199916075, "bacc": 0.8566576086956521, "bacc_std": 0.044787784631235256} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04666603698906155, "f1": 0.8484848484848485, "f1_std": 0.04971311014991755, "bacc": 0.8444293478260869, "bacc_std": 0.04992181009744147} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.050992386403014886, "f1": 0.8131793478260869, "f1_std": 0.05284604188768158, "bacc": 0.8131793478260869, "bacc_std": 0.053286442673780424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 21.54434690031882, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03391493490952556, "f1": 0.9260752688172043, "f1_std": 0.03422762024442099, "bacc": 0.9313858695652174, "bacc_std": 0.032438174474914656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04486823316231024, "f1": 0.8711943793911007, "f1_std": 0.04500858678587805, "bacc": 0.8783967391304348, "bacc_std": 0.04346320924503253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05552548666532771, "f1": 0.8106060606060606, "f1_std": 0.0586234900542526, "bacc": 0.8070652173913043, "bacc_std": 0.05838243497298046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03777709306352963, "f1": 0.9071259709557582, "f1_std": 0.03850443746280451, "bacc": 0.9096467391304348, "bacc_std": 0.03817150613806454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04483039110851195, "f1": 0.8484848484848485, "f1_std": 0.04782164287359455, "bacc": 0.8444293478260869, "bacc_std": 0.04841654876479196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025285124493685165, "f1": 0.9626358695652174, "f1_std": 0.02607369779271476, "bacc": 0.9626358695652174, "bacc_std": 0.026542112992565484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04703233984967721, "f1": 0.84593837535014, "f1_std": 0.05186361353340904, "bacc": 0.8383152173913043, "bacc_std": 0.052191983732967996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04206684959336442, "f1": 0.8879076086956521, "f1_std": 0.043301426617399975, "bacc": 0.8879076086956521, "bacc_std": 0.04330573640425172} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04982549382304948, "f1": 0.8521505376344086, "f1_std": 0.05046727866183209, "bacc": 0.8566576086956521, "bacc_std": 0.049909741682399804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05046218124038226, "f1": 0.8131793478260869, "f1_std": 0.051685388047205426, "bacc": 0.8131793478260869, "bacc_std": 0.05127315777327244} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04374076903797025, "f1": 0.8683760683760684, "f1_std": 0.04564555700262949, "bacc": 0.8661684782608696, "bacc_std": 0.04623060735934749} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04490240656916372, "f1": 0.8699763593380614, "f1_std": 0.0456716004995731, "bacc": 0.8722826086956521, "bacc_std": 0.0450853490812822} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04968942884400034, "f1": 0.8505434782608696, "f1_std": 0.05119954573990153, "bacc": 0.8505434782608696, "bacc_std": 0.05138667606438929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.051624518487739, "f1": 0.8328267477203647, "f1_std": 0.05249239268094122, "bacc": 0.8349184782608696, "bacc_std": 0.051773467120423196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02637554589932887, "f1": 0.9630376344086022, "f1_std": 0.026524694549674082, "bacc": 0.96875, "bacc_std": 0.022666484757235733} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.0515185724354346, "f1": 0.8307692307692308, "f1_std": 0.053888210685652846, "bacc": 0.8288043478260869, "bacc_std": 0.054012511428529135} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04703430785822703, "f1": 0.8281846581048247, "f1_std": 0.05076197120810574, "bacc": 0.8226902173913043, "bacc_std": 0.05084525347121735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04320347399560891, "f1": 0.8683760683760684, "f1_std": 0.0452604713751759, "bacc": 0.8661684782608696, "bacc_std": 0.04568964517030784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038698427157480314, "f1": 0.9071259709557582, "f1_std": 0.03943590595312746, "bacc": 0.9096467391304348, "bacc_std": 0.03877512200932932} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04524028045013216, "f1": 0.8683760683760684, "f1_std": 0.04727557271208694, "bacc": 0.8661684782608696, "bacc_std": 0.047538110018885395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.051122914595064045, "f1": 0.8343927735028438, "f1_std": 0.05157833436345624, "bacc": 0.8410326086956521, "bacc_std": 0.05083537403936008} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03770079684362956, "f1": 0.9071259709557582, "f1_std": 0.03850495601352627, "bacc": 0.9096467391304348, "bacc_std": 0.03808222432489397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05036660312889683, "f1": 0.8106060606060606, "f1_std": 0.05386528373210446, "bacc": 0.8070652173913043, "bacc_std": 0.05377539851684119} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034506216950927315, "f1": 0.9266666666666667, "f1_std": 0.03439735271827876, "bacc": 0.9375, "bacc_std": 0.029653780192203154} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03507189310474149, "f1": 0.9252717391304348, "f1_std": 0.0360820820501194, "bacc": 0.9252717391304348, "bacc_std": 0.03609269110714443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03855607057925376, "f1": 0.905982905982906, "f1_std": 0.04025776235737081, "bacc": 0.9035326086956521, "bacc_std": 0.04123633691616066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0447496027038091, "f1": 0.8699763593380614, "f1_std": 0.04565821934424626, "bacc": 0.8722826086956521, "bacc_std": 0.04552717137876866} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042411210119515014, "f1": 0.8879076086956521, "f1_std": 0.04362146411991292, "bacc": 0.8879076086956521, "bacc_std": 0.04363094403663936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04323965122450144, "f1": 0.8879076086956521, "f1_std": 0.04435367947873587, "bacc": 0.8879076086956521, "bacc_std": 0.044255169712690424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042230003825958796, "f1": 0.8639095086603039, "f1_std": 0.04792332333618021, "bacc": 0.8539402173913043, "bacc_std": 0.048416049506693475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.051598898059859115, "f1": 0.8106060606060606, "f1_std": 0.05484228685978499, "bacc": 0.8070652173913043, "bacc_std": 0.05489476250608612} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.048173186190749236, "f1": 0.8505434782608696, "f1_std": 0.04958581480642769, "bacc": 0.8505434782608696, "bacc_std": 0.04950875436945977} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047618580997320206, "f1": 0.8521505376344086, "f1_std": 0.04811393712032087, "bacc": 0.8566576086956521, "bacc_std": 0.047202912028087386} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04855833673135541, "f1": 0.8328267477203647, "f1_std": 0.049621239363186916, "bacc": 0.8349184782608696, "bacc_std": 0.0497087835126028} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04964310310557158, "f1": 0.8131793478260869, "f1_std": 0.051485263957843044, "bacc": 0.8131793478260869, "bacc_std": 0.05156293089626337} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.045599057551519356, "f1": 0.8250265111346766, "f1_std": 0.05134768838175725, "bacc": 0.8165760869565217, "bacc_std": 0.050967508567413354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.05311332030092289, "f1": 0.795677136102668, "f1_std": 0.05416334243226097, "bacc": 0.7975543478260869, "bacc_std": 0.05417562535732104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.041031719236111396, "f1": 0.8639095086603039, "f1_std": 0.04695391264275241, "bacc": 0.8539402173913043, "bacc_std": 0.04747043652680443} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0468496310965657, "f1": 0.84593837535014, "f1_std": 0.05127841312099915, "bacc": 0.8383152173913043, "bacc_std": 0.05149619596692247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029911163232987342, "f1": 0.9447975911676145, "f1_std": 0.02992294191247988, "bacc": 0.953125, "bacc_std": 0.025704905903348486} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03693972754466904, "f1": 0.9079959852793577, "f1_std": 0.03709456819605891, "bacc": 0.9157608695652174, "bacc_std": 0.035002578341222744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.023900620691134526, "f1": 0.9630376344086022, "f1_std": 0.02404021258342928, "bacc": 0.96875, "bacc_std": 0.02053959590644373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.050242177138698524, "f1": 0.8151881720430108, "f1_std": 0.05082915942644486, "bacc": 0.8192934782608696, "bacc_std": 0.05060763465251348} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04368595666707271, "f1": 0.8639095086603039, "f1_std": 0.04917183662842551, "bacc": 0.8539402173913043, "bacc_std": 0.04954903798534853} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.039314792286898624, "f1": 0.8879076086956521, "f1_std": 0.04069510572466014, "bacc": 0.8879076086956521, "bacc_std": 0.04128729935899808} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 166.81005372000556, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04120529533490039, "f1": 0.89, "f1_std": 0.04119662961842159, "bacc": 0.9001358695652174, "bacc_std": 0.03863432093362383} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 21.54434690031882, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04406030427973846, "f1": 0.8663658451926415, "f1_std": 0.04760142514449367, "bacc": 0.8600543478260869, "bacc_std": 0.04827937692514401} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.018124236091054922, "f1": 0.9811965811965813, "f1_std": 0.019033310260698953, "bacc": 0.9782608695652174, "bacc_std": 0.02167028228278305} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03443626763930174, "f1": 0.9252717391304348, "f1_std": 0.03550305823827617, "bacc": 0.9252717391304348, "bacc_std": 0.03587168685569101} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03779948838693521, "f1": 0.8863636363636364, "f1_std": 0.03987514074950978, "bacc": 0.8817934782608696, "bacc_std": 0.04049240893040475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03477808752506134, "f1": 0.9252717391304348, "f1_std": 0.035761751674160236, "bacc": 0.9252717391304348, "bacc_std": 0.035871101411233335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025649023308777573, "f1": 0.9621212121212122, "f1_std": 0.02738407179098347, "bacc": 0.9565217391304348, "bacc_std": 0.030667310477886227} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0450084877211193, "f1": 0.8683760683760684, "f1_std": 0.04687781241902098, "bacc": 0.8661684782608696, "bacc_std": 0.047518657783364324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03634492245733581, "f1": 0.9071259709557582, "f1_std": 0.037104363956088945, "bacc": 0.9096467391304348, "bacc_std": 0.03678715775118489} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.0348243478993013, "f1": 0.9252717391304348, "f1_std": 0.03585686355615123, "bacc": 0.9252717391304348, "bacc_std": 0.03609528882492067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04621164391209049, "f1": 0.8663658451926415, "f1_std": 0.04988195492973766, "bacc": 0.8600543478260869, "bacc_std": 0.05061448340190723} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.031974287190214494, "f1": 0.9442755825734549, "f1_std": 0.032487563467902936, "bacc": 0.9470108695652174, "bacc_std": 0.03135800602413087} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0366154734034941, "f1": 0.9027925061859314, "f1_std": 0.04175030728071112, "bacc": 0.8913043478260869, "bacc_std": 0.043779370373742944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04883764974953083, "f1": 0.8484848484848485, "f1_std": 0.05186675672956636, "bacc": 0.8444293478260869, "bacc_std": 0.05257988432738683} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.032211922232060264, "f1": 0.9229691876750701, "f1_std": 0.03561559772124731, "bacc": 0.9130434782608696, "bacc_std": 0.038514254842680735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041051872044367325, "f1": 0.8863636363636364, "f1_std": 0.04324528591513215, "bacc": 0.8817934782608696, "bacc_std": 0.044170963929386985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.040373315792725926, "f1": 0.8609606356085229, "f1_std": 0.04853180712733903, "bacc": 0.8478260869565217, "bacc_std": 0.04827244279565058} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04880590670119363, "f1": 0.8505434782608696, "f1_std": 0.050101887263818305, "bacc": 0.8505434782608696, "bacc_std": 0.04996443131726087} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04109462573698427, "f1": 0.8863636363636364, "f1_std": 0.043493979920730806, "bacc": 0.8817934782608696, "bacc_std": 0.04451271535812307} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03626989736055859, "f1": 0.9252717391304348, "f1_std": 0.03741219636045619, "bacc": 0.9252717391304348, "bacc_std": 0.037677305979260216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042201312109952836, "f1": 0.8663658451926415, "f1_std": 0.045573420218709915, "bacc": 0.8600543478260869, "bacc_std": 0.04627126396751769} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03982772820390711, "f1": 0.9045470322804582, "f1_std": 0.042893741659459604, "bacc": 0.8974184782608696, "bacc_std": 0.04467382717449169} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.03911434392683131, "f1": 0.8609606356085229, "f1_std": 0.04664748928434424, "bacc": 0.8478260869565217, "bacc_std": 0.046767150347298315} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 166.81005372000556, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05270846059392947, "f1": 0.8151881720430108, "f1_std": 0.0535994479199408, "bacc": 0.8192934782608696, "bacc_std": 0.05363743039387181} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038714739756069205, "f1": 0.9071259709557582, "f1_std": 0.0393426621427502, "bacc": 0.9096467391304348, "bacc_std": 0.03849996554830382} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.039491160220195984, "f1": 0.884453781512605, "f1_std": 0.043686354740888424, "bacc": 0.8756793478260869, "bacc_std": 0.044879934503244075} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03762346726786618, "f1": 0.8821428571428571, "f1_std": 0.043833119862641545, "bacc": 0.8695652173913043, "bacc_std": 0.04498458042897044} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030113921439473976, "f1": 0.9427282193682749, "f1_std": 0.03291751756764983, "bacc": 0.9347826086956521, "bacc_std": 0.036005775634153664} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041744108308986505, "f1": 0.8879076086956521, "f1_std": 0.043012019517635905, "bacc": 0.8879076086956521, "bacc_std": 0.04324584353268938} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.032765634082976405, "f1": 0.9242424242424243, "f1_std": 0.03465742060929422, "bacc": 0.9191576086956521, "bacc_std": 0.03616219920976261} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.0325119990564196, "f1": 0.9242424242424243, "f1_std": 0.03445643340295057, "bacc": 0.9191576086956521, "bacc_std": 0.036065106418703925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 2.782559402207126, "split": "test", "acc": 0.8, "acc_std": 0.05284469683394041, "f1": 0.7861435136090491, "f1_std": 0.05921950422359447, "bacc": 0.7792119565217391, "bacc_std": 0.05780370877827094} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038207281552557024, "f1": 0.9045470322804582, "f1_std": 0.041662992607520793, "bacc": 0.8974184782608696, "bacc_std": 0.04344355569707023} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03745509267031853, "f1": 0.9079959852793577, "f1_std": 0.03754301409686839, "bacc": 0.9157608695652174, "bacc_std": 0.035206404808892096} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 11.969 | 39.693 | 0.9755 | 0.026015 | 0.97483 | 0.026745 | 0.97448 | 0.027176 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 11.969 | 39.693 | 0.88036 | 0.04232 | 0.87615 | 0.043869 | 0.87481 | 0.044699 | + + +done! total time: 0:05:21 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..145717993e5f70272efa9f3db1a422c3440f0ca6 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_sex reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..aa239e6503aa0521c52c5cd4e6bd96f1cdc5cdc7 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,aabc_sex,,0.005994842503189409,train,0.8865784499054821,0.013817031253657519,0.8829611492964394,0.014354685042013393,0.8802985948477752,0.014579253676272866 +flat_mae,reg,logistic,aabc_sex,,0.005994842503189409,test,0.9272727272727272,0.036699161158697716,0.9242424242424243,0.038536766581790324,0.9242424242424243,0.03932845372916755 +flat_mae,reg,logistic,aabc_sex,1,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,1,2.782559402207126,test,0.8181818181818182,0.053222986396779096,0.8106060606060606,0.05643769746699359,0.8070652173913043,0.05650308573365163 +flat_mae,reg,logistic,aabc_sex,2,0.046415888336127774,train,0.9262759924385633,0.011622474229951604,0.9239766081871346,0.012066593045025206,0.9216785368856062,0.012452912641058304 +flat_mae,reg,logistic,aabc_sex,2,0.046415888336127774,test,0.9454545454545454,0.03144022795534883,0.9442755825734549,0.03190057281850923,0.9470108695652174,0.03055835897153896 +flat_mae,reg,logistic,aabc_sex,3,0.3593813663804626,train,0.9829867674858223,0.0053051440615988045,0.9825885657235016,0.00541673805303052,0.9834696210322693,0.005172878576541912 +flat_mae,reg,logistic,aabc_sex,3,0.3593813663804626,test,0.8,0.05500177607951241,0.790003471017008,0.05900656717252356,0.7853260869565217,0.058734313455016535 +flat_mae,reg,logistic,aabc_sex,4,0.046415888336127774,train,0.9338374291115312,0.010645317938660777,0.9317738791423003,0.011055515046963598,0.9294308156745509,0.011485301775717834 +flat_mae,reg,logistic,aabc_sex,4,0.046415888336127774,test,0.8,0.05520180857020434,0.795677136102668,0.056197365685708,0.7975543478260869,0.05595791715270819 +flat_mae,reg,logistic,aabc_sex,5,0.046415888336127774,train,0.9395085066162571,0.010428794067999618,0.9378268790033496,0.010746663299989705,0.9367654386119171,0.010998555946194467 +flat_mae,reg,logistic,aabc_sex,5,0.046415888336127774,test,0.8363636363636363,0.04931397133262579,0.8281846581048247,0.0531419292519252,0.8226902173913043,0.0531212444984994 +flat_mae,reg,logistic,aabc_sex,6,0.3593813663804626,train,0.9886578449905482,0.004346208296041284,0.9883855386416862,0.004444551317530606,0.9889797473548463,0.00427369917478197 +flat_mae,reg,logistic,aabc_sex,6,0.3593813663804626,test,0.8909090909090909,0.03943017261434058,0.884453781512605,0.043732451540602145,0.8756793478260869,0.04502440385574885 +flat_mae,reg,logistic,aabc_sex,7,0.3593813663804626,train,0.9810964083175804,0.005792825468838608,0.9806425644028103,0.005924387509022983,0.9812274685659017,0.005828029590290521 +flat_mae,reg,logistic,aabc_sex,7,0.3593813663804626,test,0.8363636363636363,0.05043586550189872,0.8328267477203647,0.051538525642100715,0.8349184782608696,0.05153539772917681 +flat_mae,reg,logistic,aabc_sex,8,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,8,21.54434690031882,test,0.7818181818181819,0.0538571235034523,0.7782258064516129,0.05467933750891791,0.7819293478260869,0.054714885865105936 +flat_mae,reg,logistic,aabc_sex,9,0.005994842503189409,train,0.8846880907372401,0.01368281402298602,0.8810916179337231,0.014158237500240383,0.8790410035464111,0.014333218242785006 +flat_mae,reg,logistic,aabc_sex,9,0.005994842503189409,test,0.8545454545454545,0.04950386578109558,0.8505434782608696,0.051100039024539815,0.8505434782608696,0.051474012385593064 +flat_mae,reg,logistic,aabc_sex,10,0.3593813663804626,train,0.9848771266540642,0.0051522452648515285,0.9845140515222482,0.0052723235960690125,0.9851036079603739,0.00521236329160055 +flat_mae,reg,logistic,aabc_sex,10,0.3593813663804626,test,0.8909090909090909,0.04298820134112911,0.8891129032258065,0.04346138414649903,0.8940217391304348,0.04245773421246041 +flat_mae,reg,logistic,aabc_sex,11,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,11,21.54434690031882,test,0.8909090909090909,0.041392233870538905,0.884453781512605,0.04545452727209712,0.8756793478260869,0.04667310987071823 +flat_mae,reg,logistic,aabc_sex,12,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,12,166.81005372000556,test,0.8363636363636363,0.0502682260026604,0.8307692307692308,0.05239193819414586,0.8288043478260869,0.05259271751595481 +flat_mae,reg,logistic,aabc_sex,13,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,13,166.81005372000556,test,0.8727272727272727,0.04654545454545453,0.8711943793911007,0.04663055464948849,0.8783967391304348,0.044548254410187636 +flat_mae,reg,logistic,aabc_sex,14,0.046415888336127774,train,0.9300567107750473,0.010852267982766617,0.9279718555536338,0.011232814872487774,0.9261628418183416,0.011589393114259517 +flat_mae,reg,logistic,aabc_sex,14,0.046415888336127774,test,0.8545454545454545,0.049121485427239577,0.8505434782608696,0.05068689470239224,0.8505434782608696,0.05081451353485448 +flat_mae,reg,logistic,aabc_sex,15,0.046415888336127774,train,0.9319470699432892,0.010891130739518027,0.929871851524525,0.011294555177126417,0.9277968287464463,0.011702419652626283 +flat_mae,reg,logistic,aabc_sex,15,0.046415888336127774,test,0.8727272727272727,0.04334258684839592,0.8711943793911007,0.04357594918443374,0.8783967391304348,0.04228430100628678 +flat_mae,reg,logistic,aabc_sex,16,0.3593813663804626,train,0.9867674858223062,0.005108727041482728,0.9864577733405013,0.005218836919582428,0.9873457604267417,0.004987953928978869 +flat_mae,reg,logistic,aabc_sex,16,0.3593813663804626,test,0.8909090909090909,0.044378224129177406,0.8863636363636364,0.04726546026250132,0.8817934782608696,0.04831437519134406 +flat_mae,reg,logistic,aabc_sex,17,0.046415888336127774,train,0.9357277882797732,0.010565505388959283,0.9339410589410589,0.010915318807539745,0.9328892992174448,0.011274283724321788 +flat_mae,reg,logistic,aabc_sex,17,0.046415888336127774,test,0.8727272727272727,0.04270057192796375,0.8639095086603039,0.048128933941479705,0.8539402173913043,0.04856021467883373 +flat_mae,reg,logistic,aabc_sex,18,0.046415888336127774,train,0.9281663516068053,0.010988055404537199,0.9261694188164776,0.011326825000399363,0.9251370204285002,0.011596588600191013 +flat_mae,reg,logistic,aabc_sex,18,0.046415888336127774,test,0.8909090909090909,0.04189676411102898,0.8879076086956521,0.04320853274271461,0.8879076086956521,0.04381651866181505 +flat_mae,reg,logistic,aabc_sex,19,0.046415888336127774,train,0.9376181474480151,0.010259155979406909,0.9357586819802679,0.010628190315382981,0.9339151206072862,0.011044572438178498 +flat_mae,reg,logistic,aabc_sex,19,0.046415888336127774,test,0.8363636363636363,0.04884788329579222,0.8343927735028438,0.04900749017351836,0.8410326086956521,0.04775226784749395 +flat_mae,reg,logistic,aabc_sex,20,0.046415888336127774,train,0.943289224952741,0.010377048441213538,0.9416372462488967,0.010727729007513153,0.9400334124681262,0.01110079126165885 +flat_mae,reg,logistic,aabc_sex,20,0.046415888336127774,test,0.8545454545454545,0.04631939422090636,0.8505434782608696,0.04802139861366552,0.8505434782608696,0.048322132088063664 +flat_mae,reg,logistic,aabc_sex,21,0.005994842503189409,train,0.8941398865784499,0.013111341499533746,0.8906120760959471,0.013610865687523037,0.8878191037251971,0.01377331186716219 +flat_mae,reg,logistic,aabc_sex,21,0.005994842503189409,test,0.7818181818181819,0.05635594082362304,0.7782258064516129,0.05725088283733767,0.7819293478260869,0.0572068841138336 +flat_mae,reg,logistic,aabc_sex,22,0.3593813663804626,train,0.9848771266540642,0.005273085659319852,0.9844954424221108,0.0054074920030713295,0.9844954424221108,0.0054797496006888605 +flat_mae,reg,logistic,aabc_sex,22,0.3593813663804626,test,0.8909090909090909,0.04288745217099062,0.8879076086956521,0.0443488709000987,0.8879076086956521,0.04497260300992225 +flat_mae,reg,logistic,aabc_sex,23,0.046415888336127774,train,0.9300567107750473,0.010655818311366281,0.9279718555536338,0.011024751300814291,0.9261628418183416,0.011336761217608854 +flat_mae,reg,logistic,aabc_sex,23,0.046415888336127774,test,0.8727272727272727,0.04421212578146069,0.8711943793911007,0.044292396225834856,0.8783967391304348,0.04240395180879072 +flat_mae,reg,logistic,aabc_sex,24,0.046415888336127774,train,0.9395085066162571,0.010340116738124369,0.9378268790033496,0.010659390817998913,0.9367654386119171,0.010917154008432057 +flat_mae,reg,logistic,aabc_sex,24,0.046415888336127774,test,0.8,0.056854356484263076,0.7931623931623932,0.05930896897701842,0.7914402173913043,0.05911911643893872 +flat_mae,reg,logistic,aabc_sex,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,25,2.782559402207126,test,0.9090909090909091,0.03926592533688699,0.9071259709557582,0.03999848010068465,0.9096467391304348,0.03948805602494126 +flat_mae,reg,logistic,aabc_sex,26,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,26,2.782559402207126,test,0.8363636363636363,0.04695190435236942,0.8281846581048247,0.05102422213138079,0.8226902173913043,0.05123264011911881 +flat_mae,reg,logistic,aabc_sex,27,0.3593813663804626,train,0.9829867674858223,0.00552686065760658,0.9825679104559584,0.005659520751172331,0.9828614554940063,0.005656468583705112 +flat_mae,reg,logistic,aabc_sex,27,0.3593813663804626,test,0.9272727272727272,0.03524752614260403,0.9260752688172043,0.035559903196655765,0.9313858695652174,0.033841162711995984 +flat_mae,reg,logistic,aabc_sex,28,0.3593813663804626,train,0.9867674858223062,0.004832964873200447,0.9864252066645893,0.004960971686408213,0.9861294293502154,0.005127997432679226 +flat_mae,reg,logistic,aabc_sex,28,0.3593813663804626,test,0.8363636363636363,0.04811021781130529,0.8250265111346766,0.0540248404198094,0.8165760869565217,0.05339341791515997 +flat_mae,reg,logistic,aabc_sex,29,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,29,2.782559402207126,test,0.7818181818181819,0.054852216179792676,0.7727272727272727,0.0580988508718159,0.7697010869565217,0.05786356783416841 +flat_mae,reg,logistic,aabc_sex,30,0.046415888336127774,train,0.9357277882797732,0.010367772012474854,0.9338555457487496,0.010712912382394184,0.9322811336791816,0.011018754440800223 +flat_mae,reg,logistic,aabc_sex,30,0.046415888336127774,test,0.8727272727272727,0.04695381940827383,0.8683760683760684,0.04924152563453307,0.8661684782608696,0.04981734038213885 +flat_mae,reg,logistic,aabc_sex,31,0.005994842503189409,train,0.8941398865784499,0.013519499874971893,0.8907637393433434,0.014032395270222452,0.8884272692634603,0.014309363146109262 +flat_mae,reg,logistic,aabc_sex,31,0.005994842503189409,test,0.7636363636363637,0.05456271242136757,0.7585275244849713,0.055510202381927415,0.7601902173913043,0.05518687793278597 +flat_mae,reg,logistic,aabc_sex,32,0.046415888336127774,train,0.9338374291115312,0.011072148488610071,0.9320413294426397,0.011415418447881628,0.9312553122893402,0.011724822972523186 +flat_mae,reg,logistic,aabc_sex,32,0.046415888336127774,test,0.8363636363636363,0.04896068924054366,0.8307692307692308,0.05121166106337207,0.8288043478260869,0.05137583124752967 +flat_mae,reg,logistic,aabc_sex,33,0.3593813663804626,train,0.9829867674858223,0.005685087923596742,0.9825466942830434,0.005833464597177776,0.9822532899557432,0.005938094586991113 +flat_mae,reg,logistic,aabc_sex,33,0.3593813663804626,test,0.8909090909090909,0.04274303771057074,0.8879076086956521,0.04413885798553689,0.8879076086956521,0.04463059924205706 +flat_mae,reg,logistic,aabc_sex,34,0.046415888336127774,train,0.9376181474480151,0.010430131699606143,0.9357586819802679,0.010803174405199784,0.9339151206072862,0.011196644628403613 +flat_mae,reg,logistic,aabc_sex,34,0.046415888336127774,test,0.8545454545454545,0.049630315981895656,0.8505434782608696,0.05112727479563819,0.8505434782608696,0.05124837074600901 +flat_mae,reg,logistic,aabc_sex,35,0.3593813663804626,train,0.9905482041587902,0.004140230108922264,0.9903037190461352,0.0042525539202850435,0.9900055687446877,0.004482635268053346 +flat_mae,reg,logistic,aabc_sex,35,0.3593813663804626,test,0.8909090909090909,0.0431836516357179,0.8879076086956521,0.04441240803978878,0.8879076086956521,0.04435461205274731 +flat_mae,reg,logistic,aabc_sex,36,0.3593813663804626,train,0.9867674858223062,0.0048062715498857775,0.9864577733405013,0.004911481286254246,0.9873457604267417,0.004696304704040427 +flat_mae,reg,logistic,aabc_sex,36,0.3593813663804626,test,0.9454545454545454,0.02845326166142564,0.9442755825734549,0.028959359502138102,0.9470108695652174,0.028088534436259534 +flat_mae,reg,logistic,aabc_sex,37,0.3593813663804626,train,0.9867674858223062,0.005112526608594206,0.9864252066645893,0.005248838343071143,0.9861294293502154,0.005429426191716867 +flat_mae,reg,logistic,aabc_sex,37,0.3593813663804626,test,0.8,0.05669318323037953,0.795677136102668,0.05799268217757258,0.7975543478260869,0.057904730736509355 +flat_mae,reg,logistic,aabc_sex,38,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,38,1291.5496650148827,test,0.8181818181818182,0.052022766789770095,0.8106060606060606,0.05537970332391331,0.8070652173913043,0.05520860214413044 +flat_mae,reg,logistic,aabc_sex,39,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,39,2.782559402207126,test,0.8545454545454545,0.04674282019379468,0.8484848484848485,0.04946578335276241,0.8444293478260869,0.04985596656010442 +flat_mae,reg,logistic,aabc_sex,40,0.3593813663804626,train,0.9886578449905482,0.004319644013350081,0.9883855386416862,0.00441835660351287,0.9889797473548463,0.004274985761948315 +flat_mae,reg,logistic,aabc_sex,40,0.3593813663804626,test,0.9090909090909091,0.035965437954690996,0.9045470322804582,0.038963106376659694,0.8974184782608696,0.04072490750545638 +flat_mae,reg,logistic,aabc_sex,41,0.005994842503189409,train,0.8865784499054821,0.0138268369802455,0.8827986529599433,0.01437335037342015,0.8800668249362524,0.014620604638302113 +flat_mae,reg,logistic,aabc_sex,41,0.005994842503189409,test,0.8727272727272727,0.0446201081306038,0.8683760683760684,0.04684766657686533,0.8661684782608696,0.04738095570658806 +flat_mae,reg,logistic,aabc_sex,42,0.046415888336127774,train,0.9395085066162571,0.010643679677028601,0.9379053320421398,0.010950964228225096,0.9373736041501802,0.011173876110503992 +flat_mae,reg,logistic,aabc_sex,42,0.046415888336127774,test,0.7818181818181819,0.05489838547054663,0.7782258064516129,0.05559487457958633,0.7819293478260869,0.05510047015608764 +flat_mae,reg,logistic,aabc_sex,43,0.3593813663804626,train,0.9792060491493384,0.006293072392622945,0.9786941127795048,0.006441589681143561,0.978985316099534,0.006386576684649413 +flat_mae,reg,logistic,aabc_sex,43,0.3593813663804626,test,0.9272727272727272,0.033817223837848874,0.9242424242424243,0.03582180159484371,0.9191576086956521,0.03741466570181812 +flat_mae,reg,logistic,aabc_sex,44,0.3593813663804626,train,0.9924385633270322,0.0037988224384364277,0.9922570257611241,0.0038853820137578748,0.9928558867493186,0.0036450575174691285 +flat_mae,reg,logistic,aabc_sex,44,0.3593813663804626,test,0.8,0.05259222831691809,0.790003471017008,0.05716854145135937,0.7853260869565217,0.0565634232397054 +flat_mae,reg,logistic,aabc_sex,45,0.046415888336127774,train,0.9357277882797732,0.011000419548428985,0.9338555457487496,0.011349981467087813,0.9322811336791816,0.011578681037220767 +flat_mae,reg,logistic,aabc_sex,45,0.046415888336127774,test,0.9454545454545454,0.02804520553889753,0.9447975911676145,0.028078716100433287,0.953125,0.02410134850999006 +flat_mae,reg,logistic,aabc_sex,46,0.3593813663804626,train,0.9848771266540642,0.005559763241297944,0.9845140515222482,0.0056851769772685605,0.9851036079603739,0.005544434541144345 +flat_mae,reg,logistic,aabc_sex,46,0.3593813663804626,test,0.8909090909090909,0.04283198001956825,0.8863636363636364,0.04553781642480681,0.8817934782608696,0.04657279733433218 +flat_mae,reg,logistic,aabc_sex,47,0.046415888336127774,train,0.9376181474480151,0.010174257250213184,0.9357586819802679,0.01052171004856194,0.9339151206072862,0.010840639959839455 +flat_mae,reg,logistic,aabc_sex,47,0.046415888336127774,test,0.8909090909090909,0.04035308625431187,0.8863636363636364,0.04277138875903686,0.8817934782608696,0.04377913413131523 +flat_mae,reg,logistic,aabc_sex,48,0.005994842503189409,train,0.888468809073724,0.013137329816774524,0.8849902534113061,0.013604232203501933,0.8829171429408833,0.013825620797239275 +flat_mae,reg,logistic,aabc_sex,48,0.005994842503189409,test,0.8545454545454545,0.04803717568648143,0.8484848484848485,0.051172154423212594,0.8444293478260869,0.05169053943945587 +flat_mae,reg,logistic,aabc_sex,49,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,49,2.782559402207126,test,0.7818181818181819,0.05590338773572293,0.7782258064516129,0.05672342297684629,0.7819293478260869,0.056312456710942 +flat_mae,reg,logistic,aabc_sex,50,0.046415888336127774,train,0.9338374291115312,0.010201148759948488,0.9318652687669509,0.01057577154963335,0.930038981212814,0.011051584647658144 +flat_mae,reg,logistic,aabc_sex,50,0.046415888336127774,test,0.8727272727272727,0.046376112403401074,0.8683760683760684,0.04819229938553598,0.8661684782608696,0.04849357150018031 +flat_mae,reg,logistic,aabc_sex,51,0.3593813663804626,train,0.9829867674858223,0.005217961120633082,0.9825885657235016,0.00532770432249382,0.9834696210322693,0.005062590254714511 +flat_mae,reg,logistic,aabc_sex,51,0.3593813663804626,test,0.8727272727272727,0.042457951975459346,0.8639095086603039,0.0484148754291216,0.8539402173913043,0.048711395486196706 +flat_mae,reg,logistic,aabc_sex,52,0.3593813663804626,train,0.9810964083175804,0.006278109056156394,0.9806425644028103,0.00642259562987256,0.9812274685659017,0.006349777741563214 +flat_mae,reg,logistic,aabc_sex,52,0.3593813663804626,test,0.8545454545454545,0.04817240388300927,0.8505434782608696,0.04956431764283657,0.8505434782608696,0.049519671426699656 +flat_mae,reg,logistic,aabc_sex,53,0.046415888336127774,train,0.9338374291115312,0.011268364247690805,0.9319544133158395,0.011624028451369877,0.9306471467510771,0.01188000440403572 +flat_mae,reg,logistic,aabc_sex,53,0.046415888336127774,test,0.8727272727272727,0.04407506744462149,0.8699763593380614,0.04491718615243175,0.8722826086956521,0.04466382290694478 +flat_mae,reg,logistic,aabc_sex,54,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,54,2.782559402207126,test,0.8545454545454545,0.05007387600187584,0.8505434782608696,0.05134827709148917,0.8505434782608696,0.0511930705870845 +flat_mae,reg,logistic,aabc_sex,55,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,55,2.782559402207126,test,0.8727272727272727,0.04144208744223976,0.8720505151213027,0.04131796539084334,0.8845108695652174,0.03817719087207436 +flat_mae,reg,logistic,aabc_sex,56,0.046415888336127774,train,0.9357277882797732,0.011082246383518082,0.9337678597731625,0.011490699898658498,0.9316729681409186,0.011960756421670323 +flat_mae,reg,logistic,aabc_sex,56,0.046415888336127774,test,0.8727272727272727,0.043464875151101326,0.8699763593380614,0.044375923414330755,0.8722826086956521,0.04433445807018652 +flat_mae,reg,logistic,aabc_sex,57,0.046415888336127774,train,0.9319470699432892,0.010467210099618554,0.929871851524525,0.01084511386163324,0.9277968287464463,0.011159915665563552 +flat_mae,reg,logistic,aabc_sex,57,0.046415888336127774,test,0.8909090909090909,0.04187341806559225,0.8879076086956521,0.04324370316732738,0.8879076086956521,0.04343313034334395 +flat_mae,reg,logistic,aabc_sex,58,0.046415888336127774,train,0.9338374291115312,0.01063097324484806,0.9318652687669509,0.01098817628105085,0.930038981212814,0.011278344904006416 +flat_mae,reg,logistic,aabc_sex,58,0.046415888336127774,test,0.7454545454545455,0.05783728672350728,0.7348484848484849,0.061258514035939994,0.7323369565217391,0.06054040349355993 +flat_mae,reg,logistic,aabc_sex,59,0.046415888336127774,train,0.9395085066162571,0.010850186720208068,0.9377463959988231,0.011212142205070188,0.936157273073654,0.011522715346966524 +flat_mae,reg,logistic,aabc_sex,59,0.046415888336127774,test,0.8727272727272727,0.04331548689508957,0.8663658451926415,0.04679044902192612,0.8600543478260869,0.047537525188265 +flat_mae,reg,logistic,aabc_sex,60,0.3593813663804626,train,0.9867674858223062,0.004717892652771928,0.9864417081324122,0.00483122759263692,0.9867375948884786,0.004794110834710163 +flat_mae,reg,logistic,aabc_sex,60,0.3593813663804626,test,0.8181818181818182,0.05036712820189158,0.8074229691876751,0.054931844858681814,0.8009510869565217,0.05442129699285104 +flat_mae,reg,logistic,aabc_sex,61,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,61,21.54434690031882,test,0.8181818181818182,0.052487530199527184,0.8166666666666667,0.05267950022118556,0.8254076086956521,0.05134494185158184 +flat_mae,reg,logistic,aabc_sex,62,0.3593813663804626,train,0.9867674858223062,0.004847529661173065,0.9864417081324122,0.004964639123729806,0.9867375948884786,0.004943161290628398 +flat_mae,reg,logistic,aabc_sex,62,0.3593813663804626,test,0.8909090909090909,0.04106951977495542,0.8879076086956521,0.04224201871112184,0.8879076086956521,0.04239144030426917 +flat_mae,reg,logistic,aabc_sex,63,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,63,166.81005372000556,test,0.9454545454545454,0.029209213988366452,0.9435897435897436,0.030424008093417467,0.9408967391304348,0.0316368431148425 +flat_mae,reg,logistic,aabc_sex,64,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,64,166.81005372000556,test,0.8727272727272727,0.04299853543537007,0.8711943793911007,0.04319544453010382,0.8783967391304348,0.04187453135318125 +flat_mae,reg,logistic,aabc_sex,65,0.005994842503189409,train,0.8846880907372401,0.013743457188248591,0.8812508969938286,0.014234126998200298,0.8796491690846742,0.01448134455314129 +flat_mae,reg,logistic,aabc_sex,65,0.005994842503189409,test,0.8727272727272727,0.04575861929373984,0.8663658451926415,0.04917566421994209,0.8600543478260869,0.04973728802598292 +flat_mae,reg,logistic,aabc_sex,66,0.046415888336127774,train,0.9300567107750473,0.010867578679321787,0.9280660940767447,0.011187522777609963,0.9267710073566048,0.011315060245015654 +flat_mae,reg,logistic,aabc_sex,66,0.046415888336127774,test,0.8181818181818182,0.0494411746630894,0.8106060606060606,0.05231249414218975,0.8070652173913043,0.052431999711953635 +flat_mae,reg,logistic,aabc_sex,67,0.046415888336127774,train,0.9357277882797732,0.010346866013465796,0.9337678597731625,0.010724016108971397,0.9316729681409186,0.011085285759768564 +flat_mae,reg,logistic,aabc_sex,67,0.046415888336127774,test,0.9090909090909091,0.03885112079177201,0.9079959852793577,0.0389576980222639,0.9157608695652174,0.036567444666493 +flat_mae,reg,logistic,aabc_sex,68,0.3593813663804626,train,0.9848771266540642,0.005284382660023345,0.9845140515222482,0.005403643948835778,0.9851036079603739,0.0052477490495036 +flat_mae,reg,logistic,aabc_sex,68,0.3593813663804626,test,0.8727272727272727,0.04522303223610838,0.8663658451926415,0.0487326678771809,0.8600543478260869,0.04947834285910888 +flat_mae,reg,logistic,aabc_sex,69,0.046415888336127774,train,0.9281663516068053,0.011132887356156067,0.9261694188164776,0.011462261559403752,0.9251370204285002,0.011632643950237841 +flat_mae,reg,logistic,aabc_sex,69,0.046415888336127774,test,0.9272727272727272,0.035812846856959034,0.9252717391304348,0.0367843647926844,0.9252717391304348,0.03677683890579939 +flat_mae,reg,logistic,aabc_sex,70,0.3593813663804626,train,0.9829867674858223,0.005459865190098938,0.9825885657235016,0.0055803942348352925,0.9834696210322693,0.005451420874813083 +flat_mae,reg,logistic,aabc_sex,70,0.3593813663804626,test,0.8727272727272727,0.04431608479887213,0.8711943793911007,0.04448986193144981,0.8783967391304348,0.042974754284908934 +flat_mae,reg,logistic,aabc_sex,71,0.005994842503189409,train,0.888468809073724,0.013257829416786989,0.8848323831663623,0.013790130181052303,0.8823089774026203,0.014088415558752529 +flat_mae,reg,logistic,aabc_sex,71,0.005994842503189409,test,0.8727272727272727,0.04110274970190986,0.8663658451926415,0.04429131709125571,0.8600543478260869,0.04458897454238408 +flat_mae,reg,logistic,aabc_sex,72,0.046415888336127774,train,0.9300567107750473,0.01038141127522623,0.9280660940767447,0.010713928379812705,0.9267710073566048,0.010972601763350395 +flat_mae,reg,logistic,aabc_sex,72,0.046415888336127774,test,0.9454545454545454,0.03018617712225579,0.9435897435897436,0.031505214878279515,0.9408967391304348,0.03282378955010323 +flat_mae,reg,logistic,aabc_sex,73,0.3593813663804626,train,0.9848771266540642,0.005115500522553907,0.98453216374269,0.005220861782204868,0.9857117734986371,0.004908482577850991 +flat_mae,reg,logistic,aabc_sex,73,0.3593813663804626,test,0.8727272727272727,0.04369782035905487,0.8663658451926415,0.04729583650063397,0.8600543478260869,0.04826969482918865 +flat_mae,reg,logistic,aabc_sex,74,0.046415888336127774,train,0.9357277882797732,0.01022631895759805,0.9338555457487496,0.010581835024119308,0.9322811336791816,0.010989602382215548 +flat_mae,reg,logistic,aabc_sex,74,0.046415888336127774,test,0.8545454545454545,0.04745146628811969,0.8505434782608696,0.04873958380731786,0.8505434782608696,0.04874323822147129 +flat_mae,reg,logistic,aabc_sex,75,0.3593813663804626,train,0.9867674858223062,0.004697447823991161,0.9864577733405013,0.004796753167046303,0.9873457604267417,0.004524511359328294 +flat_mae,reg,logistic,aabc_sex,75,0.3593813663804626,test,0.8727272727272727,0.04307964563188274,0.8699763593380614,0.04402546779141044,0.8722826086956521,0.044181392654163966 +flat_mae,reg,logistic,aabc_sex,76,0.046415888336127774,train,0.9338374291115312,0.010975265791935026,0.9318652687669509,0.011389740915911623,0.930038981212814,0.011882989784608571 +flat_mae,reg,logistic,aabc_sex,76,0.046415888336127774,test,0.8363636363636363,0.050972739432850314,0.8307692307692308,0.05320453755873417,0.8288043478260869,0.053200012439348056 +flat_mae,reg,logistic,aabc_sex,77,0.046415888336127774,train,0.9319470699432892,0.010623667833898207,0.9299646954986761,0.010977785230486403,0.9284049942847094,0.0112621579755032 +flat_mae,reg,logistic,aabc_sex,77,0.046415888336127774,test,0.8727272727272727,0.04737693409558621,0.8663658451926415,0.051059848847233906,0.8600543478260869,0.05176638023502369 +flat_mae,reg,logistic,aabc_sex,78,0.3593813663804626,train,0.9829867674858223,0.005630153538248126,0.9825885657235016,0.005750631164153215,0.9834696210322693,0.0055331588846844245 +flat_mae,reg,logistic,aabc_sex,78,0.3593813663804626,test,0.9090909090909091,0.03765663046771204,0.905982905982906,0.039131984533180224,0.9035326086956521,0.039800483407144 +flat_mae,reg,logistic,aabc_sex,79,0.3593813663804626,train,0.9829867674858223,0.005388099329171976,0.9825679104559584,0.005520051293354894,0.9828614554940063,0.005549736123373777 +flat_mae,reg,logistic,aabc_sex,79,0.3593813663804626,test,0.8,0.04940981934731073,0.7861435136090491,0.056013082984203,0.7792119565217391,0.05441442244459399 +flat_mae,reg,logistic,aabc_sex,80,0.046415888336127774,train,0.9319470699432892,0.011385085106322475,0.929871851524525,0.011805707858337924,0.9277968287464463,0.012155920502910403 +flat_mae,reg,logistic,aabc_sex,80,0.046415888336127774,test,0.7818181818181819,0.05484209036892245,0.7727272727272727,0.05826663328896273,0.7697010869565217,0.05804699376350601 +flat_mae,reg,logistic,aabc_sex,81,0.046415888336127774,train,0.9300567107750473,0.010615548180489855,0.9281579768393621,0.01091195972632998,0.9273791728948679,0.011048285348135766 +flat_mae,reg,logistic,aabc_sex,81,0.046415888336127774,test,0.8727272727272727,0.043073398820506516,0.8663658451926415,0.04634042299830829,0.8600543478260869,0.0471814380205916 +flat_mae,reg,logistic,aabc_sex,82,0.046415888336127774,train,0.9319470699432892,0.010928332300403522,0.929871851524525,0.011334566548346461,0.9277968287464463,0.011782925761646306 +flat_mae,reg,logistic,aabc_sex,82,0.046415888336127774,test,0.8909090909090909,0.0420238263782711,0.8863636363636364,0.04437841547844663,0.8817934782608696,0.045260560949532305 +flat_mae,reg,logistic,aabc_sex,83,0.046415888336127774,train,0.9357277882797732,0.011129126736445841,0.9340244152947736,0.011426763214011546,0.9334974647557079,0.011519349277326276 +flat_mae,reg,logistic,aabc_sex,83,0.046415888336127774,test,0.8727272727272727,0.04320200485093828,0.8639095086603039,0.04884123150048822,0.8539402173913043,0.049007871544259875 +flat_mae,reg,logistic,aabc_sex,84,0.046415888336127774,train,0.9395085066162571,0.010782781027158541,0.9376638680217999,0.011168286507930612,0.9355491075353908,0.011520410678626738 +flat_mae,reg,logistic,aabc_sex,84,0.046415888336127774,test,0.7636363636363637,0.059075085993369206,0.7518222839291913,0.06276073242600563,0.7479619565217391,0.06192120399980101 +flat_mae,reg,logistic,aabc_sex,85,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,85,166.81005372000556,test,0.9090909090909091,0.040433665704633436,0.905982905982906,0.04217502880012336,0.9035326086956521,0.04299182592687202 +flat_mae,reg,logistic,aabc_sex,86,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,86,2.782559402207126,test,0.9090909090909091,0.03933885005903125,0.9071259709557582,0.04021449345204065,0.9096467391304348,0.04005607784429026 +flat_mae,reg,logistic,aabc_sex,87,0.046415888336127774,train,0.9376181474480151,0.01042057812409486,0.9357586819802679,0.010802672366022888,0.9339151206072862,0.0113029939861927 +flat_mae,reg,logistic,aabc_sex,87,0.046415888336127774,test,0.8727272727272727,0.04431703961232066,0.8663658451926415,0.04769768851496206,0.8600543478260869,0.04815981932370044 +flat_mae,reg,logistic,aabc_sex,88,0.046415888336127774,train,0.9376181474480151,0.010300952700499449,0.9357586819802679,0.010656786686108753,0.9339151206072862,0.010994440283892267 +flat_mae,reg,logistic,aabc_sex,88,0.046415888336127774,test,0.8909090909090909,0.04284326229370194,0.8863636363636364,0.04541370578276888,0.8817934782608696,0.046577740726911794 +flat_mae,reg,logistic,aabc_sex,89,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,89,21.54434690031882,test,0.8363636363636363,0.05082948321236761,0.8307692307692308,0.05296438894571743,0.8288043478260869,0.05312025184149232 +flat_mae,reg,logistic,aabc_sex,90,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,90,166.81005372000556,test,0.8363636363636363,0.05244534029833596,0.8307692307692308,0.05454965250020428,0.8288043478260869,0.05457472337298821 +flat_mae,reg,logistic,aabc_sex,91,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,91,166.81005372000556,test,0.8363636363636363,0.05162975629941698,0.8328267477203647,0.05252505382733081,0.8349184782608696,0.05200563583907484 +flat_mae,reg,logistic,aabc_sex,92,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,92,2.782559402207126,test,0.9272727272727272,0.03144771339359908,0.9229691876750701,0.03494981423729797,0.9130434782608696,0.03760052688365107 +flat_mae,reg,logistic,aabc_sex,93,0.046415888336127774,train,0.9376181474480151,0.010946742691796837,0.9359246820459175,0.011274242147955266,0.9351314516838125,0.011500791920170762 +flat_mae,reg,logistic,aabc_sex,93,0.046415888336127774,test,0.8727272727272727,0.0399220894135126,0.8609606356085229,0.047900383924878075,0.8478260869565217,0.04773293299441726 +flat_mae,reg,logistic,aabc_sex,94,0.3593813663804626,train,0.9829867674858223,0.00549518793952231,0.9825679104559584,0.005627931031314142,0.9828614554940063,0.005621531858249162 +flat_mae,reg,logistic,aabc_sex,94,0.3593813663804626,test,0.9636363636363636,0.02444372183588422,0.9621212121212122,0.026212622911368975,0.9565217391304348,0.0292261891516007 +flat_mae,reg,logistic,aabc_sex,95,0.3593813663804626,train,0.9867674858223062,0.004900620426031007,0.9864417081324122,0.005018533600143062,0.9867375948884786,0.004962171926581205 +flat_mae,reg,logistic,aabc_sex,95,0.3593813663804626,test,0.8909090909090909,0.04221785294680458,0.8879076086956521,0.04346054227662537,0.8879076086956521,0.043627257776545324 +flat_mae,reg,logistic,aabc_sex,96,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,96,21.54434690031882,test,0.9272727272727272,0.034463270663031814,0.9242424242424243,0.03654961204154012,0.9191576086956521,0.0382486010034183 +flat_mae,reg,logistic,aabc_sex,97,0.3593813663804626,train,0.9829867674858223,0.005798004915763054,0.9825679104559584,0.005939341824714773,0.9828614554940063,0.005947766657011616 +flat_mae,reg,logistic,aabc_sex,97,0.3593813663804626,test,0.8363636363636363,0.04933868781901762,0.8281846581048247,0.052718096352016144,0.8226902173913043,0.05264268266381832 +flat_mae,reg,logistic,aabc_sex,98,0.3593813663804626,train,0.9886578449905482,0.00442691444214696,0.9883991228070176,0.004518190915616173,0.9895879128931093,0.0041070663356773274 +flat_mae,reg,logistic,aabc_sex,98,0.3593813663804626,test,0.8,0.05273698970025333,0.7931623931623932,0.054816159628546704,0.7914402173913043,0.05501272448506233 +flat_mae,reg,logistic,aabc_sex,99,0.005994842503189409,train,0.8865784499054821,0.01447364258703536,0.8831197525408749,0.014976132039852048,0.8812831560127787,0.01518688807541718 +flat_mae,reg,logistic,aabc_sex,99,0.005994842503189409,test,0.8727272727272727,0.04671688600513232,0.8663658451926415,0.05068616286610326,0.8600543478260869,0.051469582387591986 +flat_mae,reg,logistic,aabc_sex,100,0.046415888336127774,train,0.9300567107750473,0.011402593226673516,0.9280660940767447,0.011781180982007665,0.9267710073566048,0.012132377040501895 +flat_mae,reg,logistic,aabc_sex,100,0.046415888336127774,test,0.8545454545454545,0.04795452391210199,0.8533333333333333,0.04794050810556676,0.8627717391304348,0.046037338702627204 diff --git a/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..408e1be11abf8ee04a8126876ac78901e5bb6162 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:24:53 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (aabc_sex reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/aabc_sex__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:21:33 time: 5.4827 data: 4.2913 max mem: 3219 +extract (train) [ 20/236] eta: 0:01:44 time: 0.2330 data: 0.0797 max mem: 3409 +extract (train) [ 40/236] eta: 0:01:06 time: 0.1838 data: 0.0507 max mem: 3409 +extract (train) [ 60/236] eta: 0:00:50 time: 0.1787 data: 0.0507 max mem: 3409 +extract (train) [ 80/236] eta: 0:00:41 time: 0.2001 data: 0.0618 max mem: 3409 +extract (train) [100/236] eta: 0:00:34 time: 0.2113 data: 0.0689 max mem: 3409 +extract (train) [120/236] eta: 0:00:28 time: 0.1926 data: 0.0600 max mem: 3409 +extract (train) [140/236] eta: 0:00:22 time: 0.2026 data: 0.0647 max mem: 3409 +extract (train) [160/236] eta: 0:00:17 time: 0.2024 data: 0.0617 max mem: 3409 +extract (train) [180/236] eta: 0:00:12 time: 0.2176 data: 0.0731 max mem: 3409 +extract (train) [200/236] eta: 0:00:08 time: 0.1938 data: 0.0566 max mem: 3409 +extract (train) [220/236] eta: 0:00:03 time: 0.1862 data: 0.0588 max mem: 3409 +extract (train) [235/236] eta: 0:00:00 time: 0.1734 data: 0.0530 max mem: 3409 +extract (train) Total time: 0:00:52 (0.2232 s / it) +extract (validation) [ 0/29] eta: 0:02:05 time: 4.3370 data: 4.1839 max mem: 3409 +extract (validation) [20/29] eta: 0:00:03 time: 0.1947 data: 0.0618 max mem: 3409 +extract (validation) [28/29] eta: 0:00:00 time: 0.1739 data: 0.0517 max mem: 3409 +extract (validation) Total time: 0:00:10 (0.3452 s / it) +extract (test) [ 0/28] eta: 0:01:57 time: 4.2135 data: 4.0597 max mem: 3409 +extract (test) [20/28] eta: 0:00:02 time: 0.1726 data: 0.0499 max mem: 3409 +extract (test) [27/28] eta: 0:00:00 time: 0.1693 data: 0.0500 max mem: 3409 +extract (test) Total time: 0:00:09 (0.3276 s / it) +feature extraction time: 0:01:11 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_sex | | 0.0059948 | train | 0.88658 | 0.013817 | 0.88296 | 0.014355 | 0.8803 | 0.014579 | +| flat_mae | reg | logistic | aabc_sex | | 0.0059948 | test | 0.92727 | 0.036699 | 0.92424 | 0.038537 | 0.92424 | 0.039328 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.053222986396779096, "f1": 0.8106060606060606, "f1_std": 0.05643769746699359, "bacc": 0.8070652173913043, "bacc_std": 0.05650308573365163} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03144022795534883, "f1": 0.9442755825734549, "f1_std": 0.03190057281850923, "bacc": 0.9470108695652174, "bacc_std": 0.03055835897153896} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.05500177607951241, "f1": 0.790003471017008, "f1_std": 0.05900656717252356, "bacc": 0.7853260869565217, "bacc_std": 0.058734313455016535} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05520180857020434, "f1": 0.795677136102668, "f1_std": 0.056197365685708, "bacc": 0.7975543478260869, "bacc_std": 0.05595791715270819} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04931397133262579, "f1": 0.8281846581048247, "f1_std": 0.0531419292519252, "bacc": 0.8226902173913043, "bacc_std": 0.0531212444984994} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03943017261434058, "f1": 0.884453781512605, "f1_std": 0.043732451540602145, "bacc": 0.8756793478260869, "bacc_std": 0.04502440385574885} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05043586550189872, "f1": 0.8328267477203647, "f1_std": 0.051538525642100715, "bacc": 0.8349184782608696, "bacc_std": 0.05153539772917681} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 21.54434690031882, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.0538571235034523, "f1": 0.7782258064516129, "f1_std": 0.05467933750891791, "bacc": 0.7819293478260869, "bacc_std": 0.054714885865105936} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04950386578109558, "f1": 0.8505434782608696, "f1_std": 0.051100039024539815, "bacc": 0.8505434782608696, "bacc_std": 0.051474012385593064} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04298820134112911, "f1": 0.8891129032258065, "f1_std": 0.04346138414649903, "bacc": 0.8940217391304348, "bacc_std": 0.04245773421246041} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041392233870538905, "f1": 0.884453781512605, "f1_std": 0.04545452727209712, "bacc": 0.8756793478260869, "bacc_std": 0.04667310987071823} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.0502682260026604, "f1": 0.8307692307692308, "f1_std": 0.05239193819414586, "bacc": 0.8288043478260869, "bacc_std": 0.05259271751595481} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 166.81005372000556, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04654545454545453, "f1": 0.8711943793911007, "f1_std": 0.04663055464948849, "bacc": 0.8783967391304348, "bacc_std": 0.044548254410187636} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.049121485427239577, "f1": 0.8505434782608696, "f1_std": 0.05068689470239224, "bacc": 0.8505434782608696, "bacc_std": 0.05081451353485448} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04334258684839592, "f1": 0.8711943793911007, "f1_std": 0.04357594918443374, "bacc": 0.8783967391304348, "bacc_std": 0.04228430100628678} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.044378224129177406, "f1": 0.8863636363636364, "f1_std": 0.04726546026250132, "bacc": 0.8817934782608696, "bacc_std": 0.04831437519134406} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04270057192796375, "f1": 0.8639095086603039, "f1_std": 0.048128933941479705, "bacc": 0.8539402173913043, "bacc_std": 0.04856021467883373} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04189676411102898, "f1": 0.8879076086956521, "f1_std": 0.04320853274271461, "bacc": 0.8879076086956521, "bacc_std": 0.04381651866181505} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04884788329579222, "f1": 0.8343927735028438, "f1_std": 0.04900749017351836, "bacc": 0.8410326086956521, "bacc_std": 0.04775226784749395} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04631939422090636, "f1": 0.8505434782608696, "f1_std": 0.04802139861366552, "bacc": 0.8505434782608696, "bacc_std": 0.048322132088063664} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05635594082362304, "f1": 0.7782258064516129, "f1_std": 0.05725088283733767, "bacc": 0.7819293478260869, "bacc_std": 0.0572068841138336} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04288745217099062, "f1": 0.8879076086956521, "f1_std": 0.0443488709000987, "bacc": 0.8879076086956521, "bacc_std": 0.04497260300992225} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04421212578146069, "f1": 0.8711943793911007, "f1_std": 0.044292396225834856, "bacc": 0.8783967391304348, "bacc_std": 0.04240395180879072} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.056854356484263076, "f1": 0.7931623931623932, "f1_std": 0.05930896897701842, "bacc": 0.7914402173913043, "bacc_std": 0.05911911643893872} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03926592533688699, "f1": 0.9071259709557582, "f1_std": 0.03999848010068465, "bacc": 0.9096467391304348, "bacc_std": 0.03948805602494126} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04695190435236942, "f1": 0.8281846581048247, "f1_std": 0.05102422213138079, "bacc": 0.8226902173913043, "bacc_std": 0.05123264011911881} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03524752614260403, "f1": 0.9260752688172043, "f1_std": 0.035559903196655765, "bacc": 0.9313858695652174, "bacc_std": 0.033841162711995984} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04811021781130529, "f1": 0.8250265111346766, "f1_std": 0.0540248404198094, "bacc": 0.8165760869565217, "bacc_std": 0.05339341791515997} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 2.782559402207126, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.054852216179792676, "f1": 0.7727272727272727, "f1_std": 0.0580988508718159, "bacc": 0.7697010869565217, "bacc_std": 0.05786356783416841} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04695381940827383, "f1": 0.8683760683760684, "f1_std": 0.04924152563453307, "bacc": 0.8661684782608696, "bacc_std": 0.04981734038213885} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05456271242136757, "f1": 0.7585275244849713, "f1_std": 0.055510202381927415, "bacc": 0.7601902173913043, "bacc_std": 0.05518687793278597} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04896068924054366, "f1": 0.8307692307692308, "f1_std": 0.05121166106337207, "bacc": 0.8288043478260869, "bacc_std": 0.05137583124752967} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04274303771057074, "f1": 0.8879076086956521, "f1_std": 0.04413885798553689, "bacc": 0.8879076086956521, "bacc_std": 0.04463059924205706} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.049630315981895656, "f1": 0.8505434782608696, "f1_std": 0.05112727479563819, "bacc": 0.8505434782608696, "bacc_std": 0.05124837074600901} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0431836516357179, "f1": 0.8879076086956521, "f1_std": 0.04441240803978878, "bacc": 0.8879076086956521, "bacc_std": 0.04435461205274731} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02845326166142564, "f1": 0.9442755825734549, "f1_std": 0.028959359502138102, "bacc": 0.9470108695652174, "bacc_std": 0.028088534436259534} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.05669318323037953, "f1": 0.795677136102668, "f1_std": 0.05799268217757258, "bacc": 0.7975543478260869, "bacc_std": 0.057904730736509355} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 1291.5496650148827, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052022766789770095, "f1": 0.8106060606060606, "f1_std": 0.05537970332391331, "bacc": 0.8070652173913043, "bacc_std": 0.05520860214413044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04674282019379468, "f1": 0.8484848484848485, "f1_std": 0.04946578335276241, "bacc": 0.8444293478260869, "bacc_std": 0.04985596656010442} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.035965437954690996, "f1": 0.9045470322804582, "f1_std": 0.038963106376659694, "bacc": 0.8974184782608696, "bacc_std": 0.04072490750545638} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0446201081306038, "f1": 0.8683760683760684, "f1_std": 0.04684766657686533, "bacc": 0.8661684782608696, "bacc_std": 0.04738095570658806} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05489838547054663, "f1": 0.7782258064516129, "f1_std": 0.05559487457958633, "bacc": 0.7819293478260869, "bacc_std": 0.05510047015608764} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033817223837848874, "f1": 0.9242424242424243, "f1_std": 0.03582180159484371, "bacc": 0.9191576086956521, "bacc_std": 0.03741466570181812} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.05259222831691809, "f1": 0.790003471017008, "f1_std": 0.05716854145135937, "bacc": 0.7853260869565217, "bacc_std": 0.0565634232397054} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.02804520553889753, "f1": 0.9447975911676145, "f1_std": 0.028078716100433287, "bacc": 0.953125, "bacc_std": 0.02410134850999006} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04283198001956825, "f1": 0.8863636363636364, "f1_std": 0.04553781642480681, "bacc": 0.8817934782608696, "bacc_std": 0.04657279733433218} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04035308625431187, "f1": 0.8863636363636364, "f1_std": 0.04277138875903686, "bacc": 0.8817934782608696, "bacc_std": 0.04377913413131523} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04803717568648143, "f1": 0.8484848484848485, "f1_std": 0.051172154423212594, "bacc": 0.8444293478260869, "bacc_std": 0.05169053943945587} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 2.782559402207126, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05590338773572293, "f1": 0.7782258064516129, "f1_std": 0.05672342297684629, "bacc": 0.7819293478260869, "bacc_std": 0.056312456710942} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046376112403401074, "f1": 0.8683760683760684, "f1_std": 0.04819229938553598, "bacc": 0.8661684782608696, "bacc_std": 0.04849357150018031} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042457951975459346, "f1": 0.8639095086603039, "f1_std": 0.0484148754291216, "bacc": 0.8539402173913043, "bacc_std": 0.048711395486196706} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04817240388300927, "f1": 0.8505434782608696, "f1_std": 0.04956431764283657, "bacc": 0.8505434782608696, "bacc_std": 0.049519671426699656} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04407506744462149, "f1": 0.8699763593380614, "f1_std": 0.04491718615243175, "bacc": 0.8722826086956521, "bacc_std": 0.04466382290694478} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.05007387600187584, "f1": 0.8505434782608696, "f1_std": 0.05134827709148917, "bacc": 0.8505434782608696, "bacc_std": 0.0511930705870845} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04144208744223976, "f1": 0.8720505151213027, "f1_std": 0.04131796539084334, "bacc": 0.8845108695652174, "bacc_std": 0.03817719087207436} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.043464875151101326, "f1": 0.8699763593380614, "f1_std": 0.044375923414330755, "bacc": 0.8722826086956521, "bacc_std": 0.04433445807018652} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04187341806559225, "f1": 0.8879076086956521, "f1_std": 0.04324370316732738, "bacc": 0.8879076086956521, "bacc_std": 0.04343313034334395} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.7454545454545455, "acc_std": 0.05783728672350728, "f1": 0.7348484848484849, "f1_std": 0.061258514035939994, "bacc": 0.7323369565217391, "bacc_std": 0.06054040349355993} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04331548689508957, "f1": 0.8663658451926415, "f1_std": 0.04679044902192612, "bacc": 0.8600543478260869, "bacc_std": 0.047537525188265} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05036712820189158, "f1": 0.8074229691876751, "f1_std": 0.054931844858681814, "bacc": 0.8009510869565217, "bacc_std": 0.05442129699285104} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 21.54434690031882, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052487530199527184, "f1": 0.8166666666666667, "f1_std": 0.05267950022118556, "bacc": 0.8254076086956521, "bacc_std": 0.05134494185158184} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04106951977495542, "f1": 0.8879076086956521, "f1_std": 0.04224201871112184, "bacc": 0.8879076086956521, "bacc_std": 0.04239144030426917} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 166.81005372000556, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029209213988366452, "f1": 0.9435897435897436, "f1_std": 0.030424008093417467, "bacc": 0.9408967391304348, "bacc_std": 0.0316368431148425} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 166.81005372000556, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04299853543537007, "f1": 0.8711943793911007, "f1_std": 0.04319544453010382, "bacc": 0.8783967391304348, "bacc_std": 0.04187453135318125} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04575861929373984, "f1": 0.8663658451926415, "f1_std": 0.04917566421994209, "bacc": 0.8600543478260869, "bacc_std": 0.04973728802598292} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.0494411746630894, "f1": 0.8106060606060606, "f1_std": 0.05231249414218975, "bacc": 0.8070652173913043, "bacc_std": 0.052431999711953635} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03885112079177201, "f1": 0.9079959852793577, "f1_std": 0.0389576980222639, "bacc": 0.9157608695652174, "bacc_std": 0.036567444666493} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04522303223610838, "f1": 0.8663658451926415, "f1_std": 0.0487326678771809, "bacc": 0.8600543478260869, "bacc_std": 0.04947834285910888} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.035812846856959034, "f1": 0.9252717391304348, "f1_std": 0.0367843647926844, "bacc": 0.9252717391304348, "bacc_std": 0.03677683890579939} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04431608479887213, "f1": 0.8711943793911007, "f1_std": 0.04448986193144981, "bacc": 0.8783967391304348, "bacc_std": 0.042974754284908934} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04110274970190986, "f1": 0.8663658451926415, "f1_std": 0.04429131709125571, "bacc": 0.8600543478260869, "bacc_std": 0.04458897454238408} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.03018617712225579, "f1": 0.9435897435897436, "f1_std": 0.031505214878279515, "bacc": 0.9408967391304348, "bacc_std": 0.03282378955010323} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04369782035905487, "f1": 0.8663658451926415, "f1_std": 0.04729583650063397, "bacc": 0.8600543478260869, "bacc_std": 0.04826969482918865} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04745146628811969, "f1": 0.8505434782608696, "f1_std": 0.04873958380731786, "bacc": 0.8505434782608696, "bacc_std": 0.04874323822147129} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04307964563188274, "f1": 0.8699763593380614, "f1_std": 0.04402546779141044, "bacc": 0.8722826086956521, "bacc_std": 0.044181392654163966} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.050972739432850314, "f1": 0.8307692307692308, "f1_std": 0.05320453755873417, "bacc": 0.8288043478260869, "bacc_std": 0.053200012439348056} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04737693409558621, "f1": 0.8663658451926415, "f1_std": 0.051059848847233906, "bacc": 0.8600543478260869, "bacc_std": 0.05176638023502369} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03765663046771204, "f1": 0.905982905982906, "f1_std": 0.039131984533180224, "bacc": 0.9035326086956521, "bacc_std": 0.039800483407144} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.04940981934731073, "f1": 0.7861435136090491, "f1_std": 0.056013082984203, "bacc": 0.7792119565217391, "bacc_std": 0.05441442244459399} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05484209036892245, "f1": 0.7727272727272727, "f1_std": 0.05826663328896273, "bacc": 0.7697010869565217, "bacc_std": 0.05804699376350601} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.043073398820506516, "f1": 0.8663658451926415, "f1_std": 0.04634042299830829, "bacc": 0.8600543478260869, "bacc_std": 0.0471814380205916} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0420238263782711, "f1": 0.8863636363636364, "f1_std": 0.04437841547844663, "bacc": 0.8817934782608696, "bacc_std": 0.045260560949532305} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04320200485093828, "f1": 0.8639095086603039, "f1_std": 0.04884123150048822, "bacc": 0.8539402173913043, "bacc_std": 0.049007871544259875} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.059075085993369206, "f1": 0.7518222839291913, "f1_std": 0.06276073242600563, "bacc": 0.7479619565217391, "bacc_std": 0.06192120399980101} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 166.81005372000556, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.040433665704633436, "f1": 0.905982905982906, "f1_std": 0.04217502880012336, "bacc": 0.9035326086956521, "bacc_std": 0.04299182592687202} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03933885005903125, "f1": 0.9071259709557582, "f1_std": 0.04021449345204065, "bacc": 0.9096467391304348, "bacc_std": 0.04005607784429026} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04431703961232066, "f1": 0.8663658451926415, "f1_std": 0.04769768851496206, "bacc": 0.8600543478260869, "bacc_std": 0.04815981932370044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04284326229370194, "f1": 0.8863636363636364, "f1_std": 0.04541370578276888, "bacc": 0.8817934782608696, "bacc_std": 0.046577740726911794} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05082948321236761, "f1": 0.8307692307692308, "f1_std": 0.05296438894571743, "bacc": 0.8288043478260869, "bacc_std": 0.05312025184149232} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05244534029833596, "f1": 0.8307692307692308, "f1_std": 0.05454965250020428, "bacc": 0.8288043478260869, "bacc_std": 0.05457472337298821} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 166.81005372000556, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05162975629941698, "f1": 0.8328267477203647, "f1_std": 0.05252505382733081, "bacc": 0.8349184782608696, "bacc_std": 0.05200563583907484} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 2.782559402207126, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03144771339359908, "f1": 0.9229691876750701, "f1_std": 0.03494981423729797, "bacc": 0.9130434782608696, "bacc_std": 0.03760052688365107} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0399220894135126, "f1": 0.8609606356085229, "f1_std": 0.047900383924878075, "bacc": 0.8478260869565217, "bacc_std": 0.04773293299441726} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02444372183588422, "f1": 0.9621212121212122, "f1_std": 0.026212622911368975, "bacc": 0.9565217391304348, "bacc_std": 0.0292261891516007} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04221785294680458, "f1": 0.8879076086956521, "f1_std": 0.04346054227662537, "bacc": 0.8879076086956521, "bacc_std": 0.043627257776545324} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 21.54434690031882, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034463270663031814, "f1": 0.9242424242424243, "f1_std": 0.03654961204154012, "bacc": 0.9191576086956521, "bacc_std": 0.0382486010034183} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04933868781901762, "f1": 0.8281846581048247, "f1_std": 0.052718096352016144, "bacc": 0.8226902173913043, "bacc_std": 0.05264268266381832} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.05273698970025333, "f1": 0.7931623931623932, "f1_std": 0.054816159628546704, "bacc": 0.7914402173913043, "bacc_std": 0.05501272448506233} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04671688600513232, "f1": 0.8663658451926415, "f1_std": 0.05068616286610326, "bacc": 0.8600543478260869, "bacc_std": 0.051469582387591986} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04795452391210199, "f1": 0.8533333333333333, "f1_std": 0.04794050810556676, "bacc": 0.8627717391304348, "bacc_std": 0.046037338702627204} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_sex | train | 100 | 26.074 | 134.74 | 0.96106 | 0.035263 | 0.95992 | 0.036353 | 0.95928 | 0.037295 | +| flat_mae | reg | logistic | aabc_sex | test | 100 | 26.074 | 134.74 | 0.862 | 0.046235 | 0.85713 | 0.047896 | 0.85573 | 0.048254 | + + +done! total time: 0:05:01 diff --git a/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..665321ef8e9224bbebea8ec8bfdba78f2f08b750 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..75c3a057ec34f7a531861b04b8f45f6ee4823988 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.005994842503189409,train,0.7037037037037037,0.016748807497152855,0.6883116883116883,0.018385484905993243,0.6879227132444679,0.017438561264896266 +flat_mae,patch,logistic,abide_dx,,0.005994842503189409,test,0.5645161290322581,0.039652926481711245,0.5291139240506328,0.045104753785393914,0.5459544383346426,0.040233603212515914 +flat_mae,patch,logistic,abide_dx,1,2.782559402207126,train,0.9814814814814815,0.005138681132558448,0.9812439499098781,0.005216462636075942,0.9802510151347361,0.005481374202758555 +flat_mae,patch,logistic,abide_dx,1,2.782559402207126,test,0.5887096774193549,0.045205424863004495,0.5873947935016637,0.04538446641891654,0.5887605042016807,0.04554811535748944 +flat_mae,patch,logistic,abide_dx,2,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,2,166.81005372000556,test,0.532258064516129,0.04418517697966419,0.5311603650586701,0.04426510762119983,0.532563025210084,0.04415545368875416 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,train,0.9786324786324786,0.005312829648932905,0.978372272143774,0.005387567435187193,0.9776670358065707,0.005595512029063445 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,test,0.5564516129032258,0.041136365570143656,0.5307877536979704,0.04441015335367699,0.5388655462184874,0.04161395015532878 +flat_mae,patch,logistic,abide_dx,4,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,4,1291.5496650148827,test,0.6290322580645161,0.044181405795946996,0.6242424242424243,0.045119444225273767,0.6239495798319328,0.04498061624741221 +flat_mae,patch,logistic,abide_dx,5,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,5,1291.5496650148827,test,0.6048387096774194,0.045381502280329625,0.6041951664386684,0.04543635308774009,0.6066176470588236,0.045480930754272286 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,train,0.8888888888888888,0.011875063220225945,0.8870320855614973,0.012147749222084862,0.8850498338870432,0.012300205538585551 +flat_mae,patch,logistic,abide_dx,6,0.3593813663804626,test,0.6209677419354839,0.04513193458351614,0.6203504657677024,0.045311861216949946,0.6228991596638656,0.04535849874978362 +flat_mae,patch,logistic,abide_dx,7,2.782559402207126,train,0.98005698005698,0.0052647660946287395,0.9798449612403101,0.00532288554666018,0.9798449612403101,0.005384753566298991 +flat_mae,patch,logistic,abide_dx,7,2.782559402207126,test,0.5887096774193549,0.04149739846164199,0.5712833028269271,0.04383445338003771,0.5745798319327731,0.04202704161058298 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,train,0.8888888888888888,0.01112271145485095,0.8871149960829589,0.01136076025586629,0.8853451458102621,0.01150670924242024 +flat_mae,patch,logistic,abide_dx,8,0.3593813663804626,test,0.6451612903225806,0.041613528377399685,0.6356837606837606,0.04299208682179839,0.6355042016806722,0.04216772019483604 +flat_mae,patch,logistic,abide_dx,9,0.046415888336127774,train,0.7621082621082621,0.015500791696752465,0.7557803076858979,0.01618342748943261,0.7535252860834256,0.016032153642014817 +flat_mae,patch,logistic,abide_dx,9,0.046415888336127774,test,0.6693548387096774,0.038835477708200554,0.6502235982112143,0.042965204737977436,0.6528361344537815,0.040125283441127806 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,train,0.8760683760683761,0.012720239393317002,0.8743113507506457,0.012943682773040652,0.8731266149870801,0.013043811736922142 +flat_mae,patch,logistic,abide_dx,10,0.3593813663804626,test,0.6209677419354839,0.04271674242316023,0.6137071651090342,0.0437152360926037,0.6134453781512605,0.04319238454673617 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,train,0.8888888888888888,0.01151993024927275,0.8871149960829589,0.011776552912458955,0.8853451458102621,0.011952382728821717 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,test,0.5967741935483871,0.04311616752663928,0.5929621848739496,0.04361130706011947,0.5929621848739496,0.043548789579384774 +flat_mae,patch,logistic,abide_dx,12,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,12,10000.0,test,0.5806451612903226,0.04335563975354448,0.5802083333333333,0.0433388514347746,0.5829831932773109,0.04348263069901864 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,train,0.8760683760683761,0.012012513665923083,0.8743961352657005,0.012178019927810204,0.873421926910299,0.012202414341385075 +flat_mae,patch,logistic,abide_dx,13,0.3593813663804626,test,0.6129032258064516,0.045079418876506114,0.6119947848761408,0.04511489194145898,0.6139705882352942,0.045155517652732825 +flat_mae,patch,logistic,abide_dx,14,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,14,21.54434690031882,test,0.5967741935483871,0.04488441624952199,0.5880946053680574,0.04617495625242622,0.5882352941176471,0.04537392578511937 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,train,0.8817663817663818,0.012290994529391754,0.8800071667020197,0.01250716140411915,0.8785898855666298,0.012585195545636394 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,test,0.6048387096774194,0.044154736312356516,0.6035753898349319,0.04434532644000162,0.6050420168067226,0.04466288478096597 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,train,0.7777777777777778,0.015714302996772126,0.7723905723905724,0.016337419242266952,0.7700996677740863,0.016240751453602507 +flat_mae,patch,logistic,abide_dx,16,0.046415888336127774,test,0.6048387096774194,0.04174397960792386,0.585171024783232,0.04490681468176621,0.5892857142857143,0.04252605520669293 +flat_mae,patch,logistic,abide_dx,17,2.782559402207126,train,0.9772079772079773,0.005369047726067739,0.9769230769230769,0.005446060621965156,0.9760797342192691,0.0056497901700819425 +flat_mae,patch,logistic,abide_dx,17,2.782559402207126,test,0.6129032258064516,0.04313639042595275,0.6112852664576802,0.043296847006835074,0.6123949579831933,0.04351816913141192 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,train,0.8803418803418803,0.01268327272184242,0.8781572335361015,0.013028214061157662,0.8758213362864526,0.013177569966419564 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,test,0.6209677419354839,0.04089432079721021,0.6137071651090342,0.04203757857965072,0.6134453781512605,0.04139514206220138 +flat_mae,patch,logistic,abide_dx,19,2.782559402207126,train,0.9829059829059829,0.004882416238709766,0.982703253201048,0.004946889267352334,0.9821336286452566,0.005117929013568181 +flat_mae,patch,logistic,abide_dx,19,2.782559402207126,test,0.6048387096774194,0.04149363691298207,0.5953379953379954,0.04329118564825425,0.5955882352941176,0.042356395334002116 +flat_mae,patch,logistic,abide_dx,20,0.046415888336127774,train,0.7635327635327636,0.01588587638431763,0.7578002244668911,0.016500239663772256,0.755703211517165,0.016360641835686775 +flat_mae,patch,logistic,abide_dx,20,0.046415888336127774,test,0.6048387096774194,0.04235989945934757,0.5953379953379954,0.04363970731281757,0.5955882352941176,0.04282306092252856 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,train,0.7849002849002849,0.015640525111478128,0.7787545787545788,0.01642373312542992,0.775968992248062,0.01626578928836598 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,test,0.6129032258064516,0.04244631793627751,0.6045708211533352,0.04355947933246242,0.6045168067226891,0.042843832172544394 +flat_mae,patch,logistic,abide_dx,22,0.046415888336127774,train,0.7834757834757835,0.0151154234800187,0.7767325075326414,0.015861383311211407,0.7737910668143226,0.015634684738144118 +flat_mae,patch,logistic,abide_dx,22,0.046415888336127774,test,0.6048387096774194,0.04130488654439531,0.585171024783232,0.04476062122588312,0.5892857142857143,0.042206131689744575 +flat_mae,patch,logistic,abide_dx,23,2.782559402207126,train,0.9814814814814815,0.0049909911454235545,0.9812559691912708,0.005062028139452666,0.980546327057955,0.005275560974161686 +flat_mae,patch,logistic,abide_dx,23,2.782559402207126,test,0.6129032258064516,0.043949763204641,0.6063492063492064,0.04525073266245381,0.60609243697479,0.04461586672977618 +flat_mae,patch,logistic,abide_dx,24,2.782559402207126,train,0.9715099715099715,0.006086058930931296,0.9711898351828747,0.006162025120680047,0.9709117755629384,0.006282998096479091 +flat_mae,patch,logistic,abide_dx,24,2.782559402207126,test,0.5806451612903226,0.044051983647361785,0.5802083333333333,0.04426585868618001,0.5829831932773109,0.044424205225150705 +flat_mae,patch,logistic,abide_dx,25,2.782559402207126,train,0.9772079772079773,0.005682297436051023,0.9769518681462999,0.005748642337147411,0.9766703580657069,0.005818960686768123 +flat_mae,patch,logistic,abide_dx,25,2.782559402207126,test,0.49193548387096775,0.04465882925219714,0.4903112155020552,0.04469656543045754,0.4910714285714286,0.0448124276322054 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,train,0.8803418803418803,0.01181919777014934,0.8786037204476396,0.012037329526253741,0.877297895902547,0.012140313497451429 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,test,0.532258064516129,0.044387761974572934,0.5170561375235025,0.0464308994061024,0.5199579831932774,0.044891359904164915 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,train,0.886039886039886,0.01185558510126597,0.8843844956644186,0.012085447793744477,0.8830564784053156,0.012229898033429863 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,test,0.5967741935483871,0.04341959449677423,0.5915678524374176,0.04372348959550257,0.5913865546218487,0.043540233131301655 +flat_mae,patch,logistic,abide_dx,28,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,28,1291.5496650148827,test,0.5645161290322581,0.04486634968466964,0.5571428571428572,0.045271990402458474,0.5572478991596639,0.04495942892122963 +flat_mae,patch,logistic,abide_dx,29,0.046415888336127774,train,0.7678062678062678,0.015898196379200452,0.7624927612037884,0.01645906824920682,0.7604651162790698,0.016355121224372444 +flat_mae,patch,logistic,abide_dx,29,0.046415888336127774,test,0.6370967741935484,0.04244295921210655,0.6190346145968457,0.045978863778200804,0.6218487394957983,0.04347821544817601 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,train,0.7720797720797721,0.015654783024895685,0.7661266813809187,0.016307163960229454,0.76375046142488,0.016148496302802007 +flat_mae,patch,logistic,abide_dx,30,0.046415888336127774,test,0.6451612903225806,0.04388506652012215,0.6405797101449275,0.04483922753441156,0.6402310924369747,0.04457468322771345 +flat_mae,patch,logistic,abide_dx,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,31,166.81005372000556,test,0.5645161290322581,0.04451646797439924,0.5634941329856584,0.04465883355290821,0.5651260504201681,0.04470931800313382 +flat_mae,patch,logistic,abide_dx,32,0.3593813663804626,train,0.8945868945868946,0.01132330474639023,0.8930556584895872,0.011540497575762663,0.8916943521594685,0.011699546140048128 +flat_mae,patch,logistic,abide_dx,32,0.3593813663804626,test,0.6048387096774194,0.043316755547180986,0.5972691721349506,0.04441690249866183,0.5971638655462186,0.04388127022261936 +flat_mae,patch,logistic,abide_dx,33,0.3593813663804626,train,0.8760683760683761,0.013003546565357025,0.8743113507506457,0.013225662673100016,0.8731266149870801,0.01328786058760674 +flat_mae,patch,logistic,abide_dx,33,0.3593813663804626,test,0.5725806451612904,0.0420441396322883,0.5703170970905524,0.042392598040571154,0.5709033613445378,0.04255946675005134 +flat_mae,patch,logistic,abide_dx,34,0.3593813663804626,train,0.886039886039886,0.011928198582056538,0.8841354723707665,0.01220985573770312,0.882170542635659,0.01237300825965788 +flat_mae,patch,logistic,abide_dx,34,0.3593813663804626,test,0.5403225806451613,0.044926981457151086,0.537888198757764,0.044996124863734596,0.5383403361344539,0.04494857087279262 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,train,0.8760683760683761,0.012761942819163789,0.874224379555129,0.013034172297279613,0.8728313030638613,0.013194805546125109 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,test,0.6612903225806451,0.04318397108883157,0.6580882352941176,0.04382490818776768,0.6580882352941176,0.043708435065995754 +flat_mae,patch,logistic,abide_dx,36,2.782559402207126,train,0.9857549857549858,0.004473942398278293,0.9855860443342066,0.004531827335594894,0.9850129198966409,0.004698817237798278 +flat_mae,patch,logistic,abide_dx,36,2.782559402207126,test,0.6129032258064516,0.04437277936288301,0.6112852664576802,0.04462765241814954,0.6123949579831933,0.04478399730511641 +flat_mae,patch,logistic,abide_dx,37,0.046415888336127774,train,0.7735042735042735,0.01517143506007683,0.768321159701855,0.01575584720432106,0.7662236987818383,0.01571833965533286 +flat_mae,patch,logistic,abide_dx,37,0.046415888336127774,test,0.6129032258064516,0.04262533090249677,0.6003223207091055,0.044953607487561456,0.6013655462184874,0.04344674462837698 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,train,0.8846153846153846,0.012381408448485213,0.8827304731244445,0.01265035087230542,0.8808785529715762,0.012783362609673506 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,test,0.5887096774193549,0.046540291138663835,0.5808311791608669,0.04746397892753263,0.5808823529411764,0.046935627811945546 +flat_mae,patch,logistic,abide_dx,39,0.3593813663804626,train,0.8931623931623932,0.011815884774067932,0.8915727409958009,0.01205610766227227,0.8901070505721669,0.012213948015466469 +flat_mae,patch,logistic,abide_dx,39,0.3593813663804626,test,0.5403225806451613,0.04276254828585528,0.5366764995083579,0.04327889777810432,0.5367647058823529,0.043173424341507435 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,train,0.7735042735042735,0.015392855237745586,0.7681170861422443,0.015885714067669983,0.7659283868586194,0.01574093707569875 +flat_mae,patch,logistic,abide_dx,40,0.046415888336127774,test,0.6209677419354839,0.041362874137562955,0.5990368077055384,0.045625670287334635,0.6039915966386554,0.04242096799584375 +flat_mae,patch,logistic,abide_dx,41,2.782559402207126,train,0.99002849002849,0.0038469462094012272,0.9899194830504128,0.0038913155427731773,0.9897748246585456,0.003987763017606204 +flat_mae,patch,logistic,abide_dx,41,2.782559402207126,test,0.5241935483870968,0.04820193335097787,0.5204195345788266,0.04868793603532564,0.520483193277311,0.048556967057830504 +flat_mae,patch,logistic,abide_dx,42,2.782559402207126,train,0.9829059829059829,0.004659505618150868,0.9826923076923078,0.004728956397507564,0.9818383167220377,0.004997571415848504 +flat_mae,patch,logistic,abide_dx,42,2.782559402207126,test,0.5967741935483871,0.04365540911567811,0.5941345902068604,0.043810760159971464,0.5945378151260504,0.04378318017830617 +flat_mae,patch,logistic,abide_dx,43,0.3593813663804626,train,0.8846153846153846,0.012274962746686657,0.8828985602754649,0.012519451317771352,0.8814691768180141,0.012655349055163667 +flat_mae,patch,logistic,abide_dx,43,0.3593813663804626,test,0.6048387096774194,0.04078213925745131,0.6017043592264831,0.041013689506574774,0.601890756302521,0.04086653063803409 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.6923076923076923,0.017007283283284377,0.6787920384351407,0.018285892106464474,0.6784053156146179,0.01757151995140546 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.6209677419354839,0.039126183312502345,0.5839223245520098,0.04620566752538352,0.5976890756302521,0.040385860059417585 +flat_mae,patch,logistic,abide_dx,45,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,45,166.81005372000556,test,0.6048387096774194,0.0447969055531562,0.6004471624909581,0.04537714954531374,0.6003151260504203,0.045139735239256386 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,train,0.886039886039886,0.012122771932923087,0.884303513745138,0.012376863713742569,0.8827611664820967,0.012541684788530344 +flat_mae,patch,logistic,abide_dx,46,0.3593813663804626,test,0.5564516129032258,0.042725471570431064,0.5498646953996436,0.043504414228589944,0.5498949579831933,0.04319234330307799 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,train,0.8817663817663818,0.01267643351996073,0.8803265725288831,0.0128651440445408,0.8797711332595054,0.012946724011253567 +flat_mae,patch,logistic,abide_dx,47,0.3593813663804626,test,0.6209677419354839,0.04255557668719835,0.6118548118548119,0.04389059698344236,0.6118697478991597,0.04313413294223839 +flat_mae,patch,logistic,abide_dx,48,0.046415888336127774,train,0.7635327635327636,0.0164346388188454,0.7582263458841298,0.016859692736500537,0.7562938353636028,0.016702464718591003 +flat_mae,patch,logistic,abide_dx,48,0.046415888336127774,test,0.6370967741935484,0.04105913098511537,0.6217205613178767,0.04362190407594121,0.6234243697478992,0.04177247161202411 +flat_mae,patch,logistic,abide_dx,49,2.782559402207126,train,0.9857549857549858,0.004127357615240502,0.9855860443342066,0.004182640599734146,0.9850129198966409,0.00437072650273517 +flat_mae,patch,logistic,abide_dx,49,2.782559402207126,test,0.5806451612903226,0.04450442810224166,0.5716183895827798,0.04564074482421478,0.571953781512605,0.04496328322004908 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,train,0.9045584045584045,0.010912097096196772,0.9027006899119767,0.011229859708442926,0.8998523440383905,0.011449950690064868 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,test,0.532258064516129,0.045441526846297646,0.5221897422269466,0.046787014878575964,0.523109243697479,0.04581500807789133 +flat_mae,patch,logistic,abide_dx,51,0.005994842503189409,train,0.6994301994301995,0.01609661397074564,0.6836047890121861,0.017609493748119355,0.6836840162421558,0.01667836526294983 +flat_mae,patch,logistic,abide_dx,51,0.005994842503189409,test,0.532258064516129,0.03887947972656699,0.5031776733904394,0.0431323054787482,0.513655462184874,0.03956987670915465 +flat_mae,patch,logistic,abide_dx,52,0.3593813663804626,train,0.8774928774928775,0.012404500495201337,0.8756262772760235,0.01265228380848947,0.8741232927279439,0.01272269040199147 +flat_mae,patch,logistic,abide_dx,52,0.3593813663804626,test,0.6048387096774194,0.04257525625723709,0.5989703649924097,0.04305543076677795,0.5987394957983193,0.04275477501805091 +flat_mae,patch,logistic,abide_dx,53,0.3593813663804626,train,0.8803418803418803,0.012347951394346588,0.8786866359447005,0.012541196725452456,0.877593207825766,0.012596803795640741 +flat_mae,patch,logistic,abide_dx,53,0.3593813663804626,test,0.6532258064516129,0.043826471742432316,0.6493719997369632,0.044453115790424436,0.6491596638655461,0.0444025449330437 +flat_mae,patch,logistic,abide_dx,54,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,54,21.54434690031882,test,0.5564516129032258,0.04475014460588546,0.5498646953996436,0.04559492122269857,0.5498949579831933,0.04503868850780014 +flat_mae,patch,logistic,abide_dx,55,0.3593813663804626,train,0.8817663817663818,0.012334701818608578,0.8797456467494835,0.012639210349809393,0.8777039497969731,0.012804897167498499 +flat_mae,patch,logistic,abide_dx,55,0.3593813663804626,test,0.6048387096774194,0.043616490952832286,0.5953379953379954,0.044972726910527866,0.5955882352941176,0.04411760077778685 +flat_mae,patch,logistic,abide_dx,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,56,21.54434690031882,test,0.6290322580645161,0.04167093665252124,0.6266038229903116,0.0417853100370245,0.6271008403361344,0.04173732388391498 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,train,0.8974358974358975,0.011775868639520475,0.8962195192062878,0.01192635903921613,0.8957548911037283,0.011998117991995242 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,test,0.6209677419354839,0.042743761373051116,0.6118548118548119,0.04413007740326406,0.6118697478991597,0.043371881290043164 +flat_mae,patch,logistic,abide_dx,58,0.3593813663804626,train,0.8774928774928775,0.012497038553098293,0.8752562152869612,0.012819960297072755,0.8729420450350683,0.012928301200550281 +flat_mae,patch,logistic,abide_dx,58,0.3593813663804626,test,0.6290322580645161,0.041313614902047886,0.6191239316239316,0.042803176679883245,0.6192226890756303,0.04186755877262569 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,train,0.7962962962962963,0.01564882835386701,0.791072733062356,0.01626696425811629,0.7883720930232558,0.016151555859315048 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,test,0.5564516129032258,0.04542112750847914,0.5479551932126997,0.046488573824590484,0.5483193277310925,0.04585411921434212 +flat_mae,patch,logistic,abide_dx,60,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,60,10000.0,test,0.5080645161290323,0.043665967312688236,0.5041625696492953,0.04391532849354406,0.5042016806722689,0.04398050637287572 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,train,0.9002849002849003,0.011319966721574055,0.8989728702888957,0.011483191144756783,0.8980435585086748,0.011512374478373989 +flat_mae,patch,logistic,abide_dx,61,0.3593813663804626,test,0.6209677419354839,0.041652328785269754,0.6153389215233318,0.042298282848011834,0.6150210084033614,0.04196717724127924 +flat_mae,patch,logistic,abide_dx,62,0.046415888336127774,train,0.7777777777777778,0.014775932703934708,0.7721841299427507,0.015341930868813611,0.7698043558508675,0.015229287541823573 +flat_mae,patch,logistic,abide_dx,62,0.046415888336127774,test,0.5161290322580645,0.04261756402925584,0.5057135264416689,0.042900767984325815,0.506827731092437,0.04244550483941754 +flat_mae,patch,logistic,abide_dx,63,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,63,21.54434690031882,test,0.6048387096774194,0.046736300000889595,0.6017043592264831,0.046817071354882354,0.601890756302521,0.04661941663292296 +flat_mae,patch,logistic,abide_dx,64,0.005994842503189409,train,0.688034188034188,0.016427749411371075,0.6728999602130199,0.017803180477464868,0.6730527870062755,0.01695699289789884 +flat_mae,patch,logistic,abide_dx,64,0.005994842503189409,test,0.6370967741935484,0.039939353087876155,0.6094351508364246,0.04537703036227468,0.6171218487394958,0.041083487827485894 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,train,0.8917378917378918,0.012322538726821696,0.8903846153846153,0.012491603083992336,0.8897009966777409,0.0125451593909032 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,test,0.5967741935483871,0.04217801763592203,0.5810810810810811,0.04440536047547774,0.5835084033613446,0.04284006924025757 +flat_mae,patch,logistic,abide_dx,66,0.005994842503189409,train,0.7165242165242165,0.015577631403433342,0.7059701335466151,0.016518622106789026,0.7045035068290882,0.016044987845048424 +flat_mae,patch,logistic,abide_dx,66,0.005994842503189409,test,0.5887096774193549,0.03969663840851672,0.5712833028269271,0.041943218284378254,0.5745798319327731,0.040106975246796454 +flat_mae,patch,logistic,abide_dx,67,0.3593813663804626,train,0.8903133903133903,0.011311752251336887,0.8887583219287324,0.011521509664591196,0.8875230712440014,0.011653192406455909 +flat_mae,patch,logistic,abide_dx,67,0.3593813663804626,test,0.5967741935483871,0.04229977011177301,0.58994708994709,0.04341832001487429,0.5898109243697479,0.04290499105420917 +flat_mae,patch,logistic,abide_dx,68,0.046415888336127774,train,0.7720797720797721,0.01478864223285571,0.766761911090438,0.015192183985620198,0.7646363971945367,0.015043975322024259 +flat_mae,patch,logistic,abide_dx,68,0.046415888336127774,test,0.6370967741935484,0.041313551933488867,0.6342182890855457,0.04175230567166643,0.634453781512605,0.04171584618540634 +flat_mae,patch,logistic,abide_dx,69,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,69,10000.0,test,0.6612903225806451,0.04070201796458227,0.6539994685091681,0.04198758494477469,0.6533613445378151,0.04138720646374869 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,train,0.98005698005698,0.005092865730925544,0.9798076923076923,0.00516831312192758,0.9789590254706534,0.0053964072430805555 +flat_mae,patch,logistic,abide_dx,70,2.782559402207126,test,0.5967741935483871,0.04100778776827985,0.5929621848739496,0.04126379937708953,0.5929621848739496,0.0412217196257725 +flat_mae,patch,logistic,abide_dx,71,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,71,21.54434690031882,test,0.5645161290322581,0.04514383015013624,0.555142173797502,0.04606182024566255,0.555672268907563,0.04538928963586455 +flat_mae,patch,logistic,abide_dx,72,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,72,21.54434690031882,test,0.5725806451612904,0.045725951527334295,0.5691904293674206,0.04622064335293859,0.569327731092437,0.04611220203718042 +flat_mae,patch,logistic,abide_dx,73,0.005994842503189409,train,0.707977207977208,0.016315744327443316,0.6967628150423849,0.017395122291942153,0.6955703211517165,0.01687806094541224 +flat_mae,patch,logistic,abide_dx,73,0.005994842503189409,test,0.5483870967741935,0.042575302084126555,0.5241228070175439,0.045732008489694144,0.5315126050420168,0.04309188339079259 +flat_mae,patch,logistic,abide_dx,74,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,74,21.54434690031882,test,0.6209677419354839,0.04404318663859368,0.6179613241560145,0.044413691323022586,0.618172268907563,0.0443152623324423 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,train,0.9757834757834758,0.0056550489023385305,0.9754885750962773,0.005731439725253049,0.9747877445551865,0.005875514170537212 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,test,0.5725806451612904,0.04147617886343127,0.5599598259122867,0.04333781546084559,0.5614495798319328,0.042028259612937074 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.8945868945868946,0.011396750688270698,0.8932692307692307,0.011570413924945736,0.8925802879291251,0.011678093293669523 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.5645161290322581,0.0425405817145448,0.5528846153846154,0.04397958104698822,0.5540966386554622,0.04291338338743696 +flat_mae,patch,logistic,abide_dx,77,2.782559402207126,train,0.98005698005698,0.005465837025396468,0.9798449612403101,0.005525661206811336,0.9798449612403101,0.005579702175401067 +flat_mae,patch,logistic,abide_dx,77,2.782559402207126,test,0.6048387096774194,0.04519221003751555,0.6035753898349319,0.0452602409357992,0.6050420168067226,0.04529046324572801 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,train,0.9829059829059829,0.0048584804983637575,0.9826923076923078,0.004929737464758341,0.9818383167220377,0.005176157042415649 +flat_mae,patch,logistic,abide_dx,78,2.782559402207126,test,0.5483870967741935,0.04386953270897764,0.5482695810564664,0.04390919066824766,0.5551470588235294,0.04412705155615162 +flat_mae,patch,logistic,abide_dx,79,0.046415888336127774,train,0.7905982905982906,0.015563466831830514,0.7859911446613922,0.016091355683827774,0.7837947582133629,0.01605039030900184 +flat_mae,patch,logistic,abide_dx,79,0.046415888336127774,test,0.532258064516129,0.046053770658692594,0.5262187088274045,0.04667104725767462,0.5262605042016807,0.046417510410533935 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,train,0.8846153846153846,0.0122722450395884,0.8827304731244445,0.012530610204865204,0.8808785529715762,0.01263931191971068 +flat_mae,patch,logistic,abide_dx,80,0.3593813663804626,test,0.6209677419354839,0.042917036341348885,0.6189604445897352,0.0431202822098294,0.6197478991596639,0.04316032420786954 +flat_mae,patch,logistic,abide_dx,81,0.005994842503189409,train,0.688034188034188,0.01696783317824974,0.6753040763871142,0.01821370437087185,0.6748246585455888,0.017525126267884546 +flat_mae,patch,logistic,abide_dx,81,0.005994842503189409,test,0.5806451612903226,0.042795799899918704,0.5581140350877193,0.04655007788266785,0.5640756302521008,0.043523019486096465 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,train,0.7507122507122507,0.016269790968687567,0.7440811607486955,0.01689092707152148,0.7420081210778885,0.016695432177857565 +flat_mae,patch,logistic,abide_dx,82,0.046415888336127774,test,0.6209677419354839,0.04143584173428756,0.6049081418208935,0.04459010415095075,0.6071428571428572,0.0424427967343476 +flat_mae,patch,logistic,abide_dx,83,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,83,21.54434690031882,test,0.6451612903225806,0.044860298817435376,0.6447916666666667,0.04505004401656693,0.648109243697479,0.045263791277254994 +flat_mae,patch,logistic,abide_dx,84,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,84,21.54434690031882,test,0.5887096774193549,0.04436649406980211,0.5873947935016637,0.04450378559112864,0.5887605042016807,0.044728367080461996 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,train,0.7849002849002849,0.015407965818704558,0.7791786015603028,0.016099435002298518,0.7765596160944999,0.015969633111226317 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,test,0.6290322580645161,0.04131230198773113,0.6145945945945945,0.04386965846110171,0.6160714285714286,0.04199744175596435 +flat_mae,patch,logistic,abide_dx,86,0.005994842503189409,train,0.7022792022792023,0.016345546233795777,0.6904912084550718,0.017480673399451283,0.689516426725729,0.016898522380614858 +flat_mae,patch,logistic,abide_dx,86,0.005994842503189409,test,0.5483870967741935,0.042755007130808244,0.5276190476190477,0.04572136189021808,0.5330882352941176,0.04341473855783209 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,train,0.8803418803418803,0.011679944369648363,0.8785186894323951,0.011911212196834265,0.8770025839793282,0.012015379598452081 +flat_mae,patch,logistic,abide_dx,87,0.3593813663804626,test,0.5967741935483871,0.0456092386856649,0.5929621848739496,0.046194358451374824,0.5929621848739496,0.04600200747675543 +flat_mae,patch,logistic,abide_dx,88,0.3593813663804626,train,0.8988603988603988,0.011611935531048119,0.8972827598998423,0.011851955899712264,0.8955703211517165,0.011998977288313032 +flat_mae,patch,logistic,abide_dx,88,0.3593813663804626,test,0.6290322580645161,0.043770805963960165,0.6210470369386127,0.04522031289270762,0.6207983193277311,0.0444194004525438 +flat_mae,patch,logistic,abide_dx,89,2.782559402207126,train,0.9786324786324786,0.005417050594124901,0.978358403742167,0.005502260958439708,0.9773717238833518,0.005797364828056613 +flat_mae,patch,logistic,abide_dx,89,2.782559402207126,test,0.6048387096774194,0.04495590104203852,0.602745995423341,0.045166068134886446,0.6034663865546219,0.04533532278032923 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,train,0.8917378917378918,0.011650203189509786,0.8903134020279438,0.011808477775122658,0.889405684754522,0.011848472397928744 +flat_mae,patch,logistic,abide_dx,90,0.3593813663804626,test,0.6048387096774194,0.04336113865517677,0.5931704050887178,0.045126893331152856,0.5940126050420168,0.04384510384047145 +flat_mae,patch,logistic,abide_dx,91,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,91,21.54434690031882,test,0.6209677419354839,0.04354650832267466,0.6167554415729598,0.044188383316062965,0.6165966386554622,0.04405968755563899 +flat_mae,patch,logistic,abide_dx,92,0.046415888336127774,train,0.7849002849002849,0.015879640347729356,0.7780876118699953,0.016751784470225867,0.7750830564784053,0.016539727502585252 +flat_mae,patch,logistic,abide_dx,92,0.046415888336127774,test,0.5483870967741935,0.04317188198794273,0.5386659580122243,0.04408239941221167,0.539390756302521,0.04335254311854147 +flat_mae,patch,logistic,abide_dx,93,0.005994842503189409,train,0.6951566951566952,0.01673771376519312,0.6813747115515134,0.01790507787159051,0.6809892949427834,0.017194190550844764 +flat_mae,patch,logistic,abide_dx,93,0.005994842503189409,test,0.5564516129032258,0.043716911078620184,0.5376584638329605,0.04582041696307409,0.542016806722689,0.04401969162378585 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,train,0.7792022792022792,0.014916041142820817,0.7737475645789451,0.015534398074731766,0.7713916574381691,0.015471536500487295 +flat_mae,patch,logistic,abide_dx,94,0.046415888336127774,test,0.5564516129032258,0.041670312362185664,0.543354536324071,0.04328337918686221,0.5451680672268907,0.04206679603739902 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,train,0.886039886039886,0.01154545143700945,0.8841354723707665,0.011830105645293437,0.882170542635659,0.011989559872721196 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,test,0.6451612903225806,0.04183007533956437,0.6356837606837606,0.04365135316704817,0.6355042016806722,0.04273198786688958 +flat_mae,patch,logistic,abide_dx,96,0.046415888336127774,train,0.8005698005698005,0.014985970555142517,0.7966059602649007,0.015382674326260847,0.7946105574012551,0.015356795749067322 +flat_mae,patch,logistic,abide_dx,96,0.046415888336127774,test,0.6290322580645161,0.04368871060037131,0.6210470369386127,0.04452443692138907,0.6207983193277311,0.0439222225337013 +flat_mae,patch,logistic,abide_dx,97,2.782559402207126,train,0.9886039886039886,0.0038055426915634336,0.9884688354673653,0.003856911127762873,0.9878922111480251,0.00406777669389997 +flat_mae,patch,logistic,abide_dx,97,2.782559402207126,test,0.6129032258064516,0.041717722448440527,0.610369206598586,0.04191255674901792,0.6108193277310925,0.04204412977152911 +flat_mae,patch,logistic,abide_dx,98,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,98,1291.5496650148827,test,0.5725806451612904,0.04709737902837431,0.5723303182143554,0.04742076048104122,0.5803571428571428,0.04668011661129554 +flat_mae,patch,logistic,abide_dx,99,2.782559402207126,train,0.9829059829059829,0.004644356152828679,0.9827242524916944,0.004694841684178626,0.9827242524916944,0.004740489376258721 +flat_mae,patch,logistic,abide_dx,99,2.782559402207126,test,0.6532258064516129,0.04014134755534239,0.6408702094699266,0.04268472826956552,0.641281512605042,0.041098458405557314 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,train,0.7877492877492878,0.015383532725437864,0.7825057233694375,0.015985639022905857,0.780029531192322,0.015890805898587268 +flat_mae,patch,logistic,abide_dx,100,0.046415888336127774,test,0.6209677419354839,0.03990263905480414,0.6021028196900389,0.04364304214506595,0.6055672268907563,0.04096331429710203 diff --git a/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c4a61f914ac846435577de183de99062cdb7ea41 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:49:47 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:27:38 time: 5.7389 data: 4.6642 max mem: 2708 +extract (train) [ 20/289] eta: 0:02:08 time: 0.2166 data: 0.0805 max mem: 2863 +extract (train) [ 40/289] eta: 0:01:21 time: 0.1692 data: 0.0548 max mem: 2863 +extract (train) [ 60/289] eta: 0:01:04 time: 0.1906 data: 0.0737 max mem: 2863 +extract (train) [ 80/289] eta: 0:00:54 time: 0.1902 data: 0.0703 max mem: 2863 +extract (train) [100/289] eta: 0:00:46 time: 0.1871 data: 0.0645 max mem: 2863 +extract (train) [120/289] eta: 0:00:39 time: 0.1749 data: 0.0610 max mem: 2863 +extract (train) [140/289] eta: 0:00:33 time: 0.1756 data: 0.0591 max mem: 2863 +extract (train) [160/289] eta: 0:00:28 time: 0.1701 data: 0.0577 max mem: 2863 +extract (train) [180/289] eta: 0:00:23 time: 0.1785 data: 0.0600 max mem: 2863 +extract (train) [200/289] eta: 0:00:18 time: 0.1701 data: 0.0555 max mem: 2863 +extract (train) [220/289] eta: 0:00:14 time: 0.1724 data: 0.0589 max mem: 2863 +extract (train) [240/289] eta: 0:00:10 time: 0.1826 data: 0.0616 max mem: 2863 +extract (train) [260/289] eta: 0:00:05 time: 0.1800 data: 0.0596 max mem: 2863 +extract (train) [280/289] eta: 0:00:01 time: 0.1597 data: 0.0510 max mem: 2863 +extract (train) [288/289] eta: 0:00:00 time: 0.1639 data: 0.0539 max mem: 2863 +extract (train) Total time: 0:00:57 (0.2004 s / it) +extract (validation) [ 0/62] eta: 0:04:09 time: 4.0250 data: 3.8752 max mem: 2863 +extract (validation) [20/62] eta: 0:00:17 time: 0.2337 data: 0.0858 max mem: 2863 +extract (validation) [40/62] eta: 0:00:06 time: 0.1945 data: 0.0690 max mem: 2863 +extract (validation) [60/62] eta: 0:00:00 time: 0.1550 data: 0.0462 max mem: 2863 +extract (validation) [61/62] eta: 0:00:00 time: 0.1553 data: 0.0463 max mem: 2863 +extract (validation) Total time: 0:00:16 (0.2604 s / it) +extract (test) [ 0/62] eta: 0:04:08 time: 4.0063 data: 3.8436 max mem: 2863 +extract (test) [20/62] eta: 0:00:16 time: 0.2046 data: 0.0714 max mem: 2863 +extract (test) [40/62] eta: 0:00:05 time: 0.1502 data: 0.0429 max mem: 2863 +extract (test) [60/62] eta: 0:00:00 time: 0.1530 data: 0.0456 max mem: 2863 +extract (test) [61/62] eta: 0:00:00 time: 0.1537 data: 0.0462 max mem: 2863 +extract (test) Total time: 0:00:14 (0.2360 s / it) +feature extraction time: 0:01:28 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.0059948 | train | 0.7037 | 0.016749 | 0.68831 | 0.018385 | 0.68792 | 0.017439 | +| flat_mae | patch | logistic | abide_dx | | 0.0059948 | test | 0.56452 | 0.039653 | 0.52911 | 0.045105 | 0.54595 | 0.040234 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.045205424863004495, "f1": 0.5873947935016637, "f1_std": 0.04538446641891654, "bacc": 0.5887605042016807, "bacc_std": 0.04554811535748944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 166.81005372000556, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04418517697966419, "f1": 0.5311603650586701, "f1_std": 0.04426510762119983, "bacc": 0.532563025210084, "bacc_std": 0.04415545368875416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.041136365570143656, "f1": 0.5307877536979704, "f1_std": 0.04441015335367699, "bacc": 0.5388655462184874, "bacc_std": 0.04161395015532878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 1291.5496650148827, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.044181405795946996, "f1": 0.6242424242424243, "f1_std": 0.045119444225273767, "bacc": 0.6239495798319328, "bacc_std": 0.04498061624741221} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 1291.5496650148827, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.045381502280329625, "f1": 0.6041951664386684, "f1_std": 0.04543635308774009, "bacc": 0.6066176470588236, "bacc_std": 0.045480930754272286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04513193458351614, "f1": 0.6203504657677024, "f1_std": 0.045311861216949946, "bacc": 0.6228991596638656, "bacc_std": 0.04535849874978362} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04149739846164199, "f1": 0.5712833028269271, "f1_std": 0.04383445338003771, "bacc": 0.5745798319327731, "bacc_std": 0.04202704161058298} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.041613528377399685, "f1": 0.6356837606837606, "f1_std": 0.04299208682179839, "bacc": 0.6355042016806722, "bacc_std": 0.04216772019483604} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.038835477708200554, "f1": 0.6502235982112143, "f1_std": 0.042965204737977436, "bacc": 0.6528361344537815, "bacc_std": 0.040125283441127806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04271674242316023, "f1": 0.6137071651090342, "f1_std": 0.0437152360926037, "bacc": 0.6134453781512605, "bacc_std": 0.04319238454673617} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04311616752663928, "f1": 0.5929621848739496, "f1_std": 0.04361130706011947, "bacc": 0.5929621848739496, "bacc_std": 0.043548789579384774} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 10000.0, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04335563975354448, "f1": 0.5802083333333333, "f1_std": 0.0433388514347746, "bacc": 0.5829831932773109, "bacc_std": 0.04348263069901864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.045079418876506114, "f1": 0.6119947848761408, "f1_std": 0.04511489194145898, "bacc": 0.6139705882352942, "bacc_std": 0.045155517652732825} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 21.54434690031882, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04488441624952199, "f1": 0.5880946053680574, "f1_std": 0.04617495625242622, "bacc": 0.5882352941176471, "bacc_std": 0.04537392578511937} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044154736312356516, "f1": 0.6035753898349319, "f1_std": 0.04434532644000162, "bacc": 0.6050420168067226, "bacc_std": 0.04466288478096597} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04174397960792386, "f1": 0.585171024783232, "f1_std": 0.04490681468176621, "bacc": 0.5892857142857143, "bacc_std": 0.04252605520669293} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04313639042595275, "f1": 0.6112852664576802, "f1_std": 0.043296847006835074, "bacc": 0.6123949579831933, "bacc_std": 0.04351816913141192} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04089432079721021, "f1": 0.6137071651090342, "f1_std": 0.04203757857965072, "bacc": 0.6134453781512605, "bacc_std": 0.04139514206220138} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04149363691298207, "f1": 0.5953379953379954, "f1_std": 0.04329118564825425, "bacc": 0.5955882352941176, "bacc_std": 0.042356395334002116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04235989945934757, "f1": 0.5953379953379954, "f1_std": 0.04363970731281757, "bacc": 0.5955882352941176, "bacc_std": 0.04282306092252856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04244631793627751, "f1": 0.6045708211533352, "f1_std": 0.04355947933246242, "bacc": 0.6045168067226891, "bacc_std": 0.042843832172544394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04130488654439531, "f1": 0.585171024783232, "f1_std": 0.04476062122588312, "bacc": 0.5892857142857143, "bacc_std": 0.042206131689744575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043949763204641, "f1": 0.6063492063492064, "f1_std": 0.04525073266245381, "bacc": 0.60609243697479, "bacc_std": 0.04461586672977618} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.044051983647361785, "f1": 0.5802083333333333, "f1_std": 0.04426585868618001, "bacc": 0.5829831932773109, "bacc_std": 0.044424205225150705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.49193548387096775, "acc_std": 0.04465882925219714, "f1": 0.4903112155020552, "f1_std": 0.04469656543045754, "bacc": 0.4910714285714286, "bacc_std": 0.0448124276322054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.532258064516129, "acc_std": 0.044387761974572934, "f1": 0.5170561375235025, "f1_std": 0.0464308994061024, "bacc": 0.5199579831932774, "bacc_std": 0.044891359904164915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04341959449677423, "f1": 0.5915678524374176, "f1_std": 0.04372348959550257, "bacc": 0.5913865546218487, "bacc_std": 0.043540233131301655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 1291.5496650148827, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04486634968466964, "f1": 0.5571428571428572, "f1_std": 0.045271990402458474, "bacc": 0.5572478991596639, "bacc_std": 0.04495942892122963} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04244295921210655, "f1": 0.6190346145968457, "f1_std": 0.045978863778200804, "bacc": 0.6218487394957983, "bacc_std": 0.04347821544817601} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04388506652012215, "f1": 0.6405797101449275, "f1_std": 0.04483922753441156, "bacc": 0.6402310924369747, "bacc_std": 0.04457468322771345} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04451646797439924, "f1": 0.5634941329856584, "f1_std": 0.04465883355290821, "bacc": 0.5651260504201681, "bacc_std": 0.04470931800313382} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043316755547180986, "f1": 0.5972691721349506, "f1_std": 0.04441690249866183, "bacc": 0.5971638655462186, "bacc_std": 0.04388127022261936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.0420441396322883, "f1": 0.5703170970905524, "f1_std": 0.042392598040571154, "bacc": 0.5709033613445378, "bacc_std": 0.04255946675005134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.044926981457151086, "f1": 0.537888198757764, "f1_std": 0.044996124863734596, "bacc": 0.5383403361344539, "bacc_std": 0.04494857087279262} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04318397108883157, "f1": 0.6580882352941176, "f1_std": 0.04382490818776768, "bacc": 0.6580882352941176, "bacc_std": 0.043708435065995754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04437277936288301, "f1": 0.6112852664576802, "f1_std": 0.04462765241814954, "bacc": 0.6123949579831933, "bacc_std": 0.04478399730511641} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04262533090249677, "f1": 0.6003223207091055, "f1_std": 0.044953607487561456, "bacc": 0.6013655462184874, "bacc_std": 0.04344674462837698} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.046540291138663835, "f1": 0.5808311791608669, "f1_std": 0.04746397892753263, "bacc": 0.5808823529411764, "bacc_std": 0.046935627811945546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04276254828585528, "f1": 0.5366764995083579, "f1_std": 0.04327889777810432, "bacc": 0.5367647058823529, "bacc_std": 0.043173424341507435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041362874137562955, "f1": 0.5990368077055384, "f1_std": 0.045625670287334635, "bacc": 0.6039915966386554, "bacc_std": 0.04242096799584375} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 2.782559402207126, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.04820193335097787, "f1": 0.5204195345788266, "f1_std": 0.04868793603532564, "bacc": 0.520483193277311, "bacc_std": 0.048556967057830504} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04365540911567811, "f1": 0.5941345902068604, "f1_std": 0.043810760159971464, "bacc": 0.5945378151260504, "bacc_std": 0.04378318017830617} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04078213925745131, "f1": 0.6017043592264831, "f1_std": 0.041013689506574774, "bacc": 0.601890756302521, "bacc_std": 0.04086653063803409} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.039126183312502345, "f1": 0.5839223245520098, "f1_std": 0.04620566752538352, "bacc": 0.5976890756302521, "bacc_std": 0.040385860059417585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 166.81005372000556, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.0447969055531562, "f1": 0.6004471624909581, "f1_std": 0.04537714954531374, "bacc": 0.6003151260504203, "bacc_std": 0.045139735239256386} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042725471570431064, "f1": 0.5498646953996436, "f1_std": 0.043504414228589944, "bacc": 0.5498949579831933, "bacc_std": 0.04319234330307799} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04255557668719835, "f1": 0.6118548118548119, "f1_std": 0.04389059698344236, "bacc": 0.6118697478991597, "bacc_std": 0.04313413294223839} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04105913098511537, "f1": 0.6217205613178767, "f1_std": 0.04362190407594121, "bacc": 0.6234243697478992, "bacc_std": 0.04177247161202411} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04450442810224166, "f1": 0.5716183895827798, "f1_std": 0.04564074482421478, "bacc": 0.571953781512605, "bacc_std": 0.04496328322004908} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.532258064516129, "acc_std": 0.045441526846297646, "f1": 0.5221897422269466, "f1_std": 0.046787014878575964, "bacc": 0.523109243697479, "bacc_std": 0.04581500807789133} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.532258064516129, "acc_std": 0.03887947972656699, "f1": 0.5031776733904394, "f1_std": 0.0431323054787482, "bacc": 0.513655462184874, "bacc_std": 0.03956987670915465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04257525625723709, "f1": 0.5989703649924097, "f1_std": 0.04305543076677795, "bacc": 0.5987394957983193, "bacc_std": 0.04275477501805091} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.043826471742432316, "f1": 0.6493719997369632, "f1_std": 0.044453115790424436, "bacc": 0.6491596638655461, "bacc_std": 0.0444025449330437} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 21.54434690031882, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04475014460588546, "f1": 0.5498646953996436, "f1_std": 0.04559492122269857, "bacc": 0.5498949579831933, "bacc_std": 0.04503868850780014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.043616490952832286, "f1": 0.5953379953379954, "f1_std": 0.044972726910527866, "bacc": 0.5955882352941176, "bacc_std": 0.04411760077778685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04167093665252124, "f1": 0.6266038229903116, "f1_std": 0.0417853100370245, "bacc": 0.6271008403361344, "bacc_std": 0.04173732388391498} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042743761373051116, "f1": 0.6118548118548119, "f1_std": 0.04413007740326406, "bacc": 0.6118697478991597, "bacc_std": 0.043371881290043164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.041313614902047886, "f1": 0.6191239316239316, "f1_std": 0.042803176679883245, "bacc": 0.6192226890756303, "bacc_std": 0.04186755877262569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04542112750847914, "f1": 0.5479551932126997, "f1_std": 0.046488573824590484, "bacc": 0.5483193277310925, "bacc_std": 0.04585411921434212} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 10000.0, "split": "test", "acc": 0.5080645161290323, "acc_std": 0.043665967312688236, "f1": 0.5041625696492953, "f1_std": 0.04391532849354406, "bacc": 0.5042016806722689, "bacc_std": 0.04398050637287572} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041652328785269754, "f1": 0.6153389215233318, "f1_std": 0.042298282848011834, "bacc": 0.6150210084033614, "bacc_std": 0.04196717724127924} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.5161290322580645, "acc_std": 0.04261756402925584, "f1": 0.5057135264416689, "f1_std": 0.042900767984325815, "bacc": 0.506827731092437, "bacc_std": 0.04244550483941754} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 21.54434690031882, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.046736300000889595, "f1": 0.6017043592264831, "f1_std": 0.046817071354882354, "bacc": 0.601890756302521, "bacc_std": 0.04661941663292296} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.039939353087876155, "f1": 0.6094351508364246, "f1_std": 0.04537703036227468, "bacc": 0.6171218487394958, "bacc_std": 0.041083487827485894} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04217801763592203, "f1": 0.5810810810810811, "f1_std": 0.04440536047547774, "bacc": 0.5835084033613446, "bacc_std": 0.04284006924025757} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.03969663840851672, "f1": 0.5712833028269271, "f1_std": 0.041943218284378254, "bacc": 0.5745798319327731, "bacc_std": 0.040106975246796454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04229977011177301, "f1": 0.58994708994709, "f1_std": 0.04341832001487429, "bacc": 0.5898109243697479, "bacc_std": 0.04290499105420917} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.041313551933488867, "f1": 0.6342182890855457, "f1_std": 0.04175230567166643, "bacc": 0.634453781512605, "bacc_std": 0.04171584618540634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 10000.0, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04070201796458227, "f1": 0.6539994685091681, "f1_std": 0.04198758494477469, "bacc": 0.6533613445378151, "bacc_std": 0.04138720646374869} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04100778776827985, "f1": 0.5929621848739496, "f1_std": 0.04126379937708953, "bacc": 0.5929621848739496, "bacc_std": 0.0412217196257725} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 21.54434690031882, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04514383015013624, "f1": 0.555142173797502, "f1_std": 0.04606182024566255, "bacc": 0.555672268907563, "bacc_std": 0.04538928963586455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 21.54434690031882, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.045725951527334295, "f1": 0.5691904293674206, "f1_std": 0.04622064335293859, "bacc": 0.569327731092437, "bacc_std": 0.04611220203718042} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.042575302084126555, "f1": 0.5241228070175439, "f1_std": 0.045732008489694144, "bacc": 0.5315126050420168, "bacc_std": 0.04309188339079259} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 21.54434690031882, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04404318663859368, "f1": 0.6179613241560145, "f1_std": 0.044413691323022586, "bacc": 0.618172268907563, "bacc_std": 0.0443152623324423} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04147617886343127, "f1": 0.5599598259122867, "f1_std": 0.04333781546084559, "bacc": 0.5614495798319328, "bacc_std": 0.042028259612937074} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.0425405817145448, "f1": 0.5528846153846154, "f1_std": 0.04397958104698822, "bacc": 0.5540966386554622, "bacc_std": 0.04291338338743696} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04519221003751555, "f1": 0.6035753898349319, "f1_std": 0.0452602409357992, "bacc": 0.6050420168067226, "bacc_std": 0.04529046324572801} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 2.782559402207126, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04386953270897764, "f1": 0.5482695810564664, "f1_std": 0.04390919066824766, "bacc": 0.5551470588235294, "bacc_std": 0.04412705155615162} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.532258064516129, "acc_std": 0.046053770658692594, "f1": 0.5262187088274045, "f1_std": 0.04667104725767462, "bacc": 0.5262605042016807, "bacc_std": 0.046417510410533935} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.042917036341348885, "f1": 0.6189604445897352, "f1_std": 0.0431202822098294, "bacc": 0.6197478991596639, "bacc_std": 0.04316032420786954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042795799899918704, "f1": 0.5581140350877193, "f1_std": 0.04655007788266785, "bacc": 0.5640756302521008, "bacc_std": 0.043523019486096465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04143584173428756, "f1": 0.6049081418208935, "f1_std": 0.04459010415095075, "bacc": 0.6071428571428572, "bacc_std": 0.0424427967343476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 21.54434690031882, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.044860298817435376, "f1": 0.6447916666666667, "f1_std": 0.04505004401656693, "bacc": 0.648109243697479, "bacc_std": 0.045263791277254994} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 21.54434690031882, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04436649406980211, "f1": 0.5873947935016637, "f1_std": 0.04450378559112864, "bacc": 0.5887605042016807, "bacc_std": 0.044728367080461996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04131230198773113, "f1": 0.6145945945945945, "f1_std": 0.04386965846110171, "bacc": 0.6160714285714286, "bacc_std": 0.04199744175596435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.042755007130808244, "f1": 0.5276190476190477, "f1_std": 0.04572136189021808, "bacc": 0.5330882352941176, "bacc_std": 0.04341473855783209} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0456092386856649, "f1": 0.5929621848739496, "f1_std": 0.046194358451374824, "bacc": 0.5929621848739496, "bacc_std": 0.04600200747675543} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.043770805963960165, "f1": 0.6210470369386127, "f1_std": 0.04522031289270762, "bacc": 0.6207983193277311, "bacc_std": 0.0444194004525438} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04495590104203852, "f1": 0.602745995423341, "f1_std": 0.045166068134886446, "bacc": 0.6034663865546219, "bacc_std": 0.04533532278032923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04336113865517677, "f1": 0.5931704050887178, "f1_std": 0.045126893331152856, "bacc": 0.5940126050420168, "bacc_std": 0.04384510384047145} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 21.54434690031882, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04354650832267466, "f1": 0.6167554415729598, "f1_std": 0.044188383316062965, "bacc": 0.6165966386554622, "bacc_std": 0.04405968755563899} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04317188198794273, "f1": 0.5386659580122243, "f1_std": 0.04408239941221167, "bacc": 0.539390756302521, "bacc_std": 0.04335254311854147} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.043716911078620184, "f1": 0.5376584638329605, "f1_std": 0.04582041696307409, "bacc": 0.542016806722689, "bacc_std": 0.04401969162378585} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.041670312362185664, "f1": 0.543354536324071, "f1_std": 0.04328337918686221, "bacc": 0.5451680672268907, "bacc_std": 0.04206679603739902} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04183007533956437, "f1": 0.6356837606837606, "f1_std": 0.04365135316704817, "bacc": 0.6355042016806722, "bacc_std": 0.04273198786688958} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04368871060037131, "f1": 0.6210470369386127, "f1_std": 0.04452443692138907, "bacc": 0.6207983193277311, "bacc_std": 0.0439222225337013} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041717722448440527, "f1": 0.610369206598586, "f1_std": 0.04191255674901792, "bacc": 0.6108193277310925, "bacc_std": 0.04204412977152911} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 1291.5496650148827, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04709737902837431, "f1": 0.5723303182143554, "f1_std": 0.04742076048104122, "bacc": 0.5803571428571428, "bacc_std": 0.04668011661129554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 2.782559402207126, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04014134755534239, "f1": 0.6408702094699266, "f1_std": 0.04268472826956552, "bacc": 0.641281512605042, "bacc_std": 0.041098458405557314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.03990263905480414, "f1": 0.6021028196900389, "f1_std": 0.04364304214506595, "bacc": 0.6055672268907563, "bacc_std": 0.04096331429710203} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 359.48 | 1722.8 | 0.89028 | 0.098114 | 0.88751 | 0.10149 | 0.8864 | 0.10204 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 359.48 | 1722.8 | 0.5954 | 0.037214 | 0.58676 | 0.037897 | 0.58834 | 0.037239 | + + +done! total time: 0:06:23 diff --git a/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..15b960be8fd477fc64cb8b40043782be2b33aa58 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (abide_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic +model: flat_mae +representation: reg +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..562b92256d6249b2d3c68cb2d433f78c5a50e48d --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,abide_dx,,0.046415888336127774,train,0.7849002849002849,0.014938238882725191,0.7787545787545788,0.015603742010722193,0.775953772407906,0.015421232253349635 +flat_mae,reg,logistic,abide_dx,,0.046415888336127774,test,0.5887096774193549,0.04311913897194124,0.5740553647201454,0.04506741490944212,0.5775072008379156,0.04344813383995713 +flat_mae,reg,logistic,abide_dx,1,0.046415888336127774,train,0.7849002849002849,0.015221755646197889,0.7791786015603028,0.015829643565954725,0.7765596160944999,0.01569480114493717 +flat_mae,reg,logistic,abide_dx,1,0.046415888336127774,test,0.5645161290322581,0.044518755766355285,0.5503626107977437,0.04708714295209538,0.5525210084033614,0.04542270435785846 +flat_mae,reg,logistic,abide_dx,2,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,2,1291.5496650148827,test,0.5241935483870968,0.04514537449960602,0.5216737495913697,0.045076440846920834,0.5220588235294117,0.045062379478635325 +flat_mae,reg,logistic,abide_dx,3,0.046415888336127774,train,0.7977207977207977,0.014507685358903209,0.7926291439222474,0.01507070242551384,0.7899593946105574,0.0149802860829525 +flat_mae,reg,logistic,abide_dx,3,0.046415888336127774,test,0.6129032258064516,0.0438743950274172,0.6003223207091055,0.046001979101804036,0.6013655462184874,0.04457834353630537 +flat_mae,reg,logistic,abide_dx,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,4,166.81005372000556,test,0.6451612903225806,0.04283077802592349,0.6418067226890756,0.04344974433865964,0.6418067226890756,0.04343013995469458 +flat_mae,reg,logistic,abide_dx,5,0.046415888336127774,train,0.7962962962962963,0.01534088540713863,0.7914512158386222,0.015807170011036004,0.7889627168696935,0.015688685028729627 +flat_mae,reg,logistic,abide_dx,5,0.046415888336127774,test,0.6048387096774194,0.04327162953942083,0.6017043592264831,0.043639821211172145,0.601890756302521,0.04371192163706521 +flat_mae,reg,logistic,abide_dx,6,0.046415888336127774,train,0.8005698005698005,0.014197956175521064,0.7964391347213362,0.014663310262134946,0.7943152454780362,0.014684611035419414 +flat_mae,reg,logistic,abide_dx,6,0.046415888336127774,test,0.5483870967741935,0.0437432914434423,0.5386659580122243,0.04530050023718753,0.539390756302521,0.04433611170728133 +flat_mae,reg,logistic,abide_dx,7,2.782559402207126,train,0.9914529914529915,0.0033484256671489163,0.9913671541942677,0.0033791642305187873,0.9916574381690662,0.0032575122538878567 +flat_mae,reg,logistic,abide_dx,7,2.782559402207126,test,0.5403225806451613,0.044477472697124036,0.5292707292707293,0.04554589344606468,0.5304621848739496,0.044701731754214956 +flat_mae,reg,logistic,abide_dx,8,0.046415888336127774,train,0.7948717948717948,0.014651327822729904,0.7895140132428268,0.015157363001813246,0.7867847914359543,0.015011609325430197 +flat_mae,reg,logistic,abide_dx,8,0.046415888336127774,test,0.6129032258064516,0.040720475537396106,0.607905138339921,0.04121455061520624,0.6076680672268908,0.040993309874647235 +flat_mae,reg,logistic,abide_dx,9,0.3593813663804626,train,0.8903133903133903,0.0115698633585381,0.8886024297505333,0.01182454273574787,0.8869324473975637,0.011981916113931342 +flat_mae,reg,logistic,abide_dx,9,0.3593813663804626,test,0.5887096774193549,0.04419890184198541,0.5765651155005022,0.046033362188947685,0.5777310924369747,0.0448657301252564 +flat_mae,reg,logistic,abide_dx,10,0.046415888336127774,train,0.7834757834757835,0.015666399845615256,0.7780255625083211,0.01636628199604882,0.775562938353636,0.01632388531546551 +flat_mae,reg,logistic,abide_dx,10,0.046415888336127774,test,0.5725806451612904,0.04285292649345049,0.5599598259122867,0.04418133750075569,0.5614495798319328,0.043098317571978746 +flat_mae,reg,logistic,abide_dx,11,0.3593813663804626,train,0.886039886039886,0.01280603772899876,0.8842205088030347,0.013061508003623368,0.8824658545588778,0.01314917095250811 +flat_mae,reg,logistic,abide_dx,11,0.3593813663804626,test,0.532258064516129,0.04276863134662212,0.5170561375235025,0.04475376331746757,0.5199579831932774,0.04335527695714466 +flat_mae,reg,logistic,abide_dx,12,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,12,21.54434690031882,test,0.5725806451612904,0.042707825707836586,0.5718845677806006,0.042706224277830274,0.5740546218487395,0.04279366358415975 +flat_mae,reg,logistic,abide_dx,13,0.046415888336127774,train,0.7763532763532763,0.015389224539063108,0.7708281783154476,0.01598517334629581,0.7685123661867848,0.015886758160338542 +flat_mae,reg,logistic,abide_dx,13,0.046415888336127774,test,0.5806451612903226,0.04489199375186728,0.5716183895827798,0.04634357729300094,0.571953781512605,0.045549847464558646 +flat_mae,reg,logistic,abide_dx,14,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,14,10000.0,test,0.532258064516129,0.04527088085608621,0.5262187088274045,0.04546630832389479,0.5262605042016807,0.04532386433116002 +flat_mae,reg,logistic,abide_dx,15,0.3593813663804626,train,0.8903133903133903,0.011856780423839327,0.8888333610972292,0.012054549680984376,0.8878183831672204,0.01215297021548755 +flat_mae,reg,logistic,abide_dx,15,0.3593813663804626,test,0.5806451612903226,0.043988090810975065,0.5766806722689075,0.044708396261203105,0.5766806722689075,0.044696781618941056 +flat_mae,reg,logistic,abide_dx,16,0.3593813663804626,train,0.8974358974358975,0.011751134896431434,0.8961538461538461,0.011942897029123087,0.8954595791805093,0.012087389509513173 +flat_mae,reg,logistic,abide_dx,16,0.3593813663804626,test,0.5967741935483871,0.0417583105937254,0.5836690840719849,0.043738177750147364,0.5850840336134454,0.04225366666178234 +flat_mae,reg,logistic,abide_dx,17,0.005994842503189409,train,0.7051282051282052,0.016308530462393285,0.6904227782571182,0.017570655983366996,0.6900332225913621,0.01677868244300121 +flat_mae,reg,logistic,abide_dx,17,0.005994842503189409,test,0.5887096774193549,0.03965531445620104,0.5682392298764252,0.04224649600996889,0.5730042016806722,0.04020529565183837 +flat_mae,reg,logistic,abide_dx,18,2.782559402207126,train,0.9843304843304843,0.004815236246496849,0.9841776236929942,0.004857286211572106,0.9846068660022149,0.004745653064069849 +flat_mae,reg,logistic,abide_dx,18,2.782559402207126,test,0.5806451612903226,0.04264003678155743,0.5716183895827798,0.04363945050098277,0.571953781512605,0.04289420536324737 +flat_mae,reg,logistic,abide_dx,19,0.3593813663804626,train,0.9017094017094017,0.011240750037635057,0.9001762032829455,0.011463481821777703,0.8984496124031007,0.011583038207268522 +flat_mae,reg,logistic,abide_dx,19,0.3593813663804626,test,0.6048387096774194,0.04273403457103017,0.5907590759075907,0.04503938104348942,0.592436974789916,0.043499001960029 +flat_mae,reg,logistic,abide_dx,20,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,20,166.81005372000556,test,0.5725806451612904,0.04034346233497787,0.5643931861867832,0.041679951322854236,0.5646008403361344,0.040945064088438565 +flat_mae,reg,logistic,abide_dx,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,21,21.54434690031882,test,0.532258064516129,0.043685194309663423,0.5278361344537815,0.04414818638942065,0.5278361344537815,0.04399220956759607 +flat_mae,reg,logistic,abide_dx,22,0.046415888336127774,train,0.7891737891737892,0.015009378755883802,0.7836671802773498,0.015616015943188281,0.7810262089331856,0.015485770756340075 +flat_mae,reg,logistic,abide_dx,22,0.046415888336127774,test,0.5887096774193549,0.04051695088543892,0.5612903225806452,0.04483370054439903,0.5698529411764706,0.041262274795568314 +flat_mae,reg,logistic,abide_dx,23,0.046415888336127774,train,0.7948717948717948,0.014537159246322184,0.7898989898989899,0.015037993567512052,0.787375415282392,0.014960012240781844 +flat_mae,reg,logistic,abide_dx,23,0.046415888336127774,test,0.6129032258064516,0.042188674252359434,0.6025641025641025,0.044422719240832166,0.6029411764705883,0.04321543370563923 +flat_mae,reg,logistic,abide_dx,24,0.3593813663804626,train,0.8846153846153846,0.011346820829445057,0.8831353802077018,0.011510200338893058,0.8823551125876707,0.011586272614052099 +flat_mae,reg,logistic,abide_dx,24,0.3593813663804626,test,0.5806451612903226,0.04300677535373634,0.5788923719958203,0.04326615559748417,0.5798319327731092,0.04331211299281947 +flat_mae,reg,logistic,abide_dx,25,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,25,10000.0,test,0.5725806451612904,0.044588472656736766,0.5662332519305657,0.04522788038731881,0.5661764705882353,0.044830021536190624 +flat_mae,reg,logistic,abide_dx,26,0.3593813663804626,train,0.9002849002849003,0.01163754021561039,0.8988364337063663,0.011839897591049357,0.8974529346622371,0.01194262133514691 +flat_mae,reg,logistic,abide_dx,26,0.3593813663804626,test,0.5403225806451613,0.044658130225226855,0.5292707292707293,0.04579305492748321,0.5304621848739496,0.04491279854318109 +flat_mae,reg,logistic,abide_dx,27,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,27,10000.0,test,0.532258064516129,0.04192300062339899,0.5278361344537815,0.04224967218774897,0.5278361344537815,0.04207465314230655 +flat_mae,reg,logistic,abide_dx,28,0.3593813663804626,train,0.8988603988603988,0.011437568104273805,0.8971318183037751,0.01169383184153327,0.8949796973052786,0.01182212771693912 +flat_mae,reg,logistic,abide_dx,28,0.3593813663804626,test,0.6612903225806451,0.04141288513435021,0.6539994685091681,0.0429579204073099,0.6533613445378151,0.042301422307118836 +flat_mae,reg,logistic,abide_dx,29,0.3593813663804626,train,0.905982905982906,0.011259762076849417,0.9047458491295302,0.01143826675610992,0.9038021410114434,0.01154540656697699 +flat_mae,reg,logistic,abide_dx,29,0.3593813663804626,test,0.6290322580645161,0.043776211116649276,0.6191239316239316,0.045433101240720954,0.6192226890756303,0.044471085889409644 +flat_mae,reg,logistic,abide_dx,30,0.3593813663804626,train,0.8888888888888888,0.011969369637987075,0.8874269126076266,0.012145514506854038,0.8865263935031378,0.012210052869349886 +flat_mae,reg,logistic,abide_dx,30,0.3593813663804626,test,0.6209677419354839,0.04134767627069835,0.6153389215233318,0.042573243729992515,0.6150210084033614,0.042135094995925375 +flat_mae,reg,logistic,abide_dx,31,0.046415888336127774,train,0.7905982905982906,0.016138155199598284,0.7861720710397573,0.0166697433308368,0.7840900701365818,0.016619997021959713 +flat_mae,reg,logistic,abide_dx,31,0.046415888336127774,test,0.5645161290322581,0.043764157810301275,0.5528846153846154,0.04518708714845193,0.5540966386554622,0.04421089349214402 +flat_mae,reg,logistic,abide_dx,32,2.782559402207126,train,0.9928774928774928,0.0031622276078941396,0.9928120168333965,0.0031861279605566073,0.9935400516795866,0.002868066900183052 +flat_mae,reg,logistic,abide_dx,32,2.782559402207126,test,0.5967741935483871,0.041954573818691235,0.58994708994709,0.04286502636347971,0.5898109243697479,0.042448827529272405 +flat_mae,reg,logistic,abide_dx,33,0.005994842503189409,train,0.7008547008547008,0.016375997745626224,0.6888297872340425,0.017304260690726648,0.6879291251384274,0.01676204474491446 +flat_mae,reg,logistic,abide_dx,33,0.005994842503189409,test,0.5403225806451613,0.042653176251351135,0.5239442311578096,0.04485181959114433,0.5273109243697479,0.04315024530770486 +flat_mae,reg,logistic,abide_dx,34,0.005994842503189409,train,0.6965811965811965,0.01646735870773545,0.6838259082345329,0.017625321169014465,0.6831672203765227,0.01695672418721221 +flat_mae,reg,logistic,abide_dx,34,0.005994842503189409,test,0.5725806451612904,0.04461796148405613,0.5662332519305657,0.04535615350219074,0.5661764705882353,0.044988889822220726 +flat_mae,reg,logistic,abide_dx,35,0.3593813663804626,train,0.8903133903133903,0.01115900263948151,0.8886024297505333,0.011407016213488053,0.8869324473975637,0.011567098130296239 +flat_mae,reg,logistic,abide_dx,35,0.3593813663804626,test,0.6370967741935484,0.041856240264929484,0.6342182890855457,0.04222265384112563,0.634453781512605,0.04213027131104822 +flat_mae,reg,logistic,abide_dx,36,0.005994842503189409,train,0.6965811965811965,0.0160090385668058,0.6852846153036634,0.016997512887316043,0.6843484680693983,0.016506804430614714 +flat_mae,reg,logistic,abide_dx,36,0.005994842503189409,test,0.5806451612903226,0.04007950929785334,0.5694444444444444,0.0414657397437233,0.5703781512605042,0.040422090811791385 +flat_mae,reg,logistic,abide_dx,37,0.3593813663804626,train,0.9031339031339032,0.011519705835460008,0.9015151515151515,0.011782922431548146,0.8994462901439646,0.011937845242819012 +flat_mae,reg,logistic,abide_dx,37,0.3593813663804626,test,0.5887096774193549,0.045081666558917814,0.5865315462569467,0.045198836332457464,0.5871848739495797,0.04526020507667945 +flat_mae,reg,logistic,abide_dx,38,2.782559402207126,train,0.9886039886039886,0.004022520631992245,0.9884960465402106,0.004054660230821571,0.9890734588409007,0.003835949661954845 +flat_mae,reg,logistic,abide_dx,38,2.782559402207126,test,0.6693548387096774,0.04143011555023379,0.6644445911160979,0.04243356551908633,0.6638655462184874,0.04218380944411694 +flat_mae,reg,logistic,abide_dx,39,0.005994842503189409,train,0.707977207977208,0.016419323972758592,0.6945850444083659,0.01769249303566483,0.6937984496124031,0.016982780748546644 +flat_mae,reg,logistic,abide_dx,39,0.005994842503189409,test,0.45161290322580644,0.04400762633747111,0.4337899543378996,0.0444249127569215,0.4385504201680672,0.04364747172679911 +flat_mae,reg,logistic,abide_dx,40,0.046415888336127774,train,0.7834757834757835,0.015069606869217468,0.7789910605545936,0.015465919464126445,0.7770394979697306,0.015395107224014591 +flat_mae,reg,logistic,abide_dx,40,0.046415888336127774,test,0.5564516129032258,0.04295244569347582,0.5343756400628115,0.04642472204025583,0.5404411764705883,0.043752113399376964 +flat_mae,reg,logistic,abide_dx,41,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,41,166.81005372000556,test,0.5564516129032258,0.04495775274341205,0.5550336008351275,0.04498923944668507,0.5561974789915967,0.044973758558657075 +flat_mae,reg,logistic,abide_dx,42,0.046415888336127774,train,0.801994301994302,0.01429126707496001,0.7967273219661066,0.014920607074891904,0.7938353636028055,0.014821424261577919 +flat_mae,reg,logistic,abide_dx,42,0.046415888336127774,test,0.5887096774193549,0.0466905007641008,0.5841388834089565,0.04698921331601806,0.5840336134453781,0.04686050285437231 +flat_mae,reg,logistic,abide_dx,43,0.3593813663804626,train,0.9002849002849003,0.011600471759416963,0.8989728702888957,0.011756933447736173,0.8980435585086748,0.011780691577310105 +flat_mae,reg,logistic,abide_dx,43,0.3593813663804626,test,0.6209677419354839,0.041209910989805844,0.607462787095036,0.04266220276560639,0.608718487394958,0.04136891094714091 +flat_mae,reg,logistic,abide_dx,44,0.005994842503189409,train,0.7022792022792023,0.016758555469341088,0.6886257282016999,0.018011506405628545,0.6880398671096346,0.017283757958973838 +flat_mae,reg,logistic,abide_dx,44,0.005994842503189409,test,0.532258064516129,0.042196023775666204,0.49888517279821626,0.04632433963225677,0.5120798319327731,0.04267222396784233 +flat_mae,reg,logistic,abide_dx,45,0.005994842503189409,train,0.7094017094017094,0.0164842290504569,0.6962637437220035,0.017743235263006127,0.6953857511997047,0.017045576156685626 +flat_mae,reg,logistic,abide_dx,45,0.005994842503189409,test,0.5564516129032258,0.042907215434194027,0.543354536324071,0.04459366184585476,0.5451680672268907,0.04339823985002167 +flat_mae,reg,logistic,abide_dx,46,0.046415888336127774,train,0.8034188034188035,0.013932029136668092,0.7990074441687345,0.014375222376269549,0.7966039128829827,0.01433718754382624 +flat_mae,reg,logistic,abide_dx,46,0.046415888336127774,test,0.5564516129032258,0.04198784262378567,0.5457875457875458,0.043087366836105145,0.5467436974789917,0.04238832253541902 +flat_mae,reg,logistic,abide_dx,47,0.3593813663804626,train,0.8888888888888888,0.011789529048555224,0.8875,0.011958315671976338,0.8868217054263565,0.012031112367399137 +flat_mae,reg,logistic,abide_dx,47,0.3593813663804626,test,0.6209677419354839,0.04262547737609588,0.6189604445897352,0.04283919059345905,0.6197478991596639,0.04291078755612905 +flat_mae,reg,logistic,abide_dx,48,0.005994842503189409,train,0.6994301994301995,0.016685707340155512,0.6864180542176964,0.017901601259212082,0.6857511997046881,0.017216083040727036 +flat_mae,reg,logistic,abide_dx,48,0.005994842503189409,test,0.5887096774193549,0.0424280746587773,0.5682392298764252,0.0458045440702839,0.5730042016806722,0.043188120684140435 +flat_mae,reg,logistic,abide_dx,49,0.3593813663804626,train,0.9102564102564102,0.010472275290893802,0.9089211024364727,0.010686905946091629,0.9073827980804725,0.010875061597661433 +flat_mae,reg,logistic,abide_dx,49,0.3593813663804626,test,0.5080645161290323,0.042585688239971047,0.5054593004249754,0.04291830011439899,0.5057773109243697,0.04280140616626618 +flat_mae,reg,logistic,abide_dx,50,0.3593813663804626,train,0.8903133903133903,0.011281721771354274,0.8883539362394275,0.01156411443085173,0.886046511627907,0.011712199671961696 +flat_mae,reg,logistic,abide_dx,50,0.3593813663804626,test,0.5564516129032258,0.045709108289761706,0.551522325244953,0.04613352997655308,0.5514705882352942,0.045951821849425464 +flat_mae,reg,logistic,abide_dx,51,0.005994842503189409,train,0.6965811965811965,0.016812683961639718,0.6845675952197623,0.01786468480298537,0.6837578442229605,0.01727317413639195 +flat_mae,reg,logistic,abide_dx,51,0.005994842503189409,test,0.5564516129032258,0.03882082162277381,0.5180552611122888,0.04389207505992633,0.5341386554621849,0.03941093102404342 +flat_mae,reg,logistic,abide_dx,52,0.046415888336127774,train,0.8048433048433048,0.014912120448535187,0.800201514474764,0.015438032971209955,0.7976005906238464,0.015343924656283125 +flat_mae,reg,logistic,abide_dx,52,0.046415888336127774,test,0.5806451612903226,0.0426361167266877,0.5694444444444444,0.04404825379217877,0.5703781512605042,0.043197177688233265 +flat_mae,reg,logistic,abide_dx,53,0.046415888336127774,train,0.7948717948717948,0.015217134971588211,0.7897084276394621,0.015806135856970722,0.7870801033591732,0.015705996596677114 +flat_mae,reg,logistic,abide_dx,53,0.046415888336127774,test,0.5806451612903226,0.04119973366552632,0.5670158474348643,0.04243270954635795,0.5688025210084033,0.041382986825271674 +flat_mae,reg,logistic,abide_dx,54,0.046415888336127774,train,0.782051282051282,0.014975896955800878,0.7772560893414491,0.015451778806128576,0.77515688445921,0.015377959839842402 +flat_mae,reg,logistic,abide_dx,54,0.046415888336127774,test,0.6209677419354839,0.04449574100677429,0.6118548118548119,0.04616122429292724,0.6118697478991597,0.04514175024805693 +flat_mae,reg,logistic,abide_dx,55,0.046415888336127774,train,0.8005698005698005,0.016149307210392094,0.7966059602649007,0.01655386083901294,0.7946105574012551,0.016489425120248494 +flat_mae,reg,logistic,abide_dx,55,0.046415888336127774,test,0.5645161290322581,0.04533348508472694,0.5528846153846154,0.046868187240718596,0.5540966386554622,0.045783591851823055 +flat_mae,reg,logistic,abide_dx,56,0.046415888336127774,train,0.7877492877492878,0.015583326545806216,0.7832628475164887,0.016076993323208055,0.7812107788851974,0.016026744278881053 +flat_mae,reg,logistic,abide_dx,56,0.046415888336127774,test,0.6209677419354839,0.04063303390504853,0.6118548118548119,0.0420421229375917,0.6118697478991597,0.04107294351264788 +flat_mae,reg,logistic,abide_dx,57,0.3593813663804626,train,0.8831908831908832,0.011943466790427073,0.8812388591800357,0.012223235749660956,0.8792912513842747,0.012355081432752938 +flat_mae,reg,logistic,abide_dx,57,0.3593813663804626,test,0.5725806451612904,0.04551934958085747,0.5691904293674206,0.045987095522188194,0.569327731092437,0.045958785010372254 +flat_mae,reg,logistic,abide_dx,58,0.3593813663804626,train,0.8974358974358975,0.011635700148346232,0.8960863808685784,0.011814713447723642,0.8951642672572906,0.011905200710963048 +flat_mae,reg,logistic,abide_dx,58,0.3593813663804626,test,0.5725806451612904,0.045907997394417775,0.5662332519305657,0.046670200534039,0.5661764705882353,0.046268935225734775 +flat_mae,reg,logistic,abide_dx,59,2.782559402207126,train,0.99002849002849,0.0037466835576963663,0.9899254350986032,0.0037839153104738447,0.9900701365817646,0.0037494802934452767 +flat_mae,reg,logistic,abide_dx,59,2.782559402207126,test,0.5645161290322581,0.04443544288974166,0.5603991596638656,0.04486266550592663,0.5603991596638656,0.044782259069298454 +flat_mae,reg,logistic,abide_dx,60,0.046415888336127774,train,0.7891737891737892,0.015175881650455683,0.7838669950738917,0.01572493378024085,0.7813215208564046,0.015602121041847515 +flat_mae,reg,logistic,abide_dx,60,0.046415888336127774,test,0.5483870967741935,0.044271475914007874,0.5363247863247864,0.04574031620227208,0.5378151260504201,0.044732407206554116 +flat_mae,reg,logistic,abide_dx,61,0.3593813663804626,train,0.8931623931623932,0.011136379697560627,0.891792018710835,0.011299848319397943,0.8909929863418236,0.01137150399314306 +flat_mae,reg,logistic,abide_dx,61,0.3593813663804626,test,0.5564516129032258,0.04388309545368575,0.5479551932126997,0.044362236049448715,0.5483193277310925,0.043892656829541465 +flat_mae,reg,logistic,abide_dx,62,0.046415888336127774,train,0.7934472934472935,0.014722103065331551,0.7892559673542401,0.015163613626300324,0.787264673311185,0.015148741930570132 +flat_mae,reg,logistic,abide_dx,62,0.046415888336127774,test,0.5161290322580645,0.04234372934913159,0.5057135264416689,0.04363081226565192,0.506827731092437,0.04289633973058741 +flat_mae,reg,logistic,abide_dx,63,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,63,21.54434690031882,test,0.6129032258064516,0.043864002649187266,0.607905138339921,0.04450986195891473,0.6076680672268908,0.044365847197314796 +flat_mae,reg,logistic,abide_dx,64,0.005994842503189409,train,0.6894586894586895,0.016764366526433056,0.6754190986833175,0.017986751776412912,0.6752307124400148,0.017249099867276487 +flat_mae,reg,logistic,abide_dx,64,0.005994842503189409,test,0.5967741935483871,0.04057975728553286,0.575109649122807,0.04392679998141624,0.5803571428571428,0.04133114218742307 +flat_mae,reg,logistic,abide_dx,65,0.046415888336127774,train,0.801994301994302,0.014860723302350307,0.7983004636414561,0.015288607981312735,0.7964931709117755,0.015320788161366335 +flat_mae,reg,logistic,abide_dx,65,0.046415888336127774,test,0.6693548387096774,0.04115298480266741,0.6575739206573719,0.043606460730697155,0.657563025210084,0.04209694830757878 +flat_mae,reg,logistic,abide_dx,66,0.3593813663804626,train,0.8888888888888888,0.011604495719611696,0.887571145806812,0.011760054512254951,0.8871170173495755,0.011835691983551897 +flat_mae,reg,logistic,abide_dx,66,0.3593813663804626,test,0.5887096774193549,0.043662607080016805,0.5880398671096345,0.04375447363108648,0.5903361344537814,0.04365435325212573 +flat_mae,reg,logistic,abide_dx,67,0.3593813663804626,train,0.8903133903133903,0.011486041808176781,0.8887583219287324,0.011705237055440569,0.8875230712440014,0.011851329139345106 +flat_mae,reg,logistic,abide_dx,67,0.3593813663804626,test,0.5564516129032258,0.042811568355009016,0.5406479423452549,0.04467698219419057,0.54359243697479,0.04324857773566792 +flat_mae,reg,logistic,abide_dx,68,0.046415888336127774,train,0.7863247863247863,0.015512284451507239,0.7809462787911063,0.016054799992006565,0.7784422296050203,0.015936753794852623 +flat_mae,reg,logistic,abide_dx,68,0.046415888336127774,test,0.5887096774193549,0.04083767452696139,0.5854473942969518,0.04133768191150257,0.585609243697479,0.04118539770962134 +flat_mae,reg,logistic,abide_dx,69,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,69,1291.5496650148827,test,0.5725806451612904,0.0454128936020044,0.5703170970905524,0.04525307519212954,0.5709033613445378,0.04521748244734315 +flat_mae,reg,logistic,abide_dx,70,2.782559402207126,train,0.99002849002849,0.0037769698293356672,0.98993121507736,0.00381002040222911,0.9903654485049834,0.0036613758019720215 +flat_mae,reg,logistic,abide_dx,70,2.782559402207126,test,0.6129032258064516,0.043251629263219626,0.6092436974789917,0.043844535090928005,0.6092436974789917,0.04361354232433648 +flat_mae,reg,logistic,abide_dx,71,0.046415888336127774,train,0.7792022792022792,0.015656127665791206,0.7749045811396477,0.016028530156192496,0.7731635289774825,0.015954378932060923 +flat_mae,reg,logistic,abide_dx,71,0.046415888336127774,test,0.5967741935483871,0.040707274608297955,0.5782312925170068,0.04387462008725824,0.5819327731092437,0.04157012040933598 +flat_mae,reg,logistic,abide_dx,72,0.046415888336127774,train,0.7891737891737892,0.014655889569239883,0.7842547677586551,0.015219179035917739,0.7819121447028423,0.015180663505844502 +flat_mae,reg,logistic,abide_dx,72,0.046415888336127774,test,0.5161290322580645,0.044508329728181306,0.5115546218487395,0.04498508532319034,0.5115546218487395,0.04478060680806414 +flat_mae,reg,logistic,abide_dx,73,0.3593813663804626,train,0.9116809116809117,0.010997218900636204,0.9102708943223519,0.011213706470283904,0.9083794758213363,0.011337305380997639 +flat_mae,reg,logistic,abide_dx,73,0.3593813663804626,test,0.5887096774193549,0.040912138415377934,0.5740553647201454,0.043535913286514655,0.576155462184874,0.04170573497796926 +flat_mae,reg,logistic,abide_dx,74,2.782559402207126,train,0.9914529914529915,0.0033385779473011066,0.9913621262458472,0.003374273713329635,0.9913621262458472,0.0033868765746559626 +flat_mae,reg,logistic,abide_dx,74,2.782559402207126,test,0.5564516129032258,0.046580399427463705,0.5541026479241582,0.04656095832210816,0.5546218487394958,0.04657079323537288 +flat_mae,reg,logistic,abide_dx,75,0.3593813663804626,train,0.9031339031339032,0.011500050377092274,0.9016579866833674,0.011732117476383806,0.9000369139904023,0.01187737605088627 +flat_mae,reg,logistic,abide_dx,75,0.3593813663804626,test,0.6854838709677419,0.04359119461151173,0.6794591370053689,0.044638323383712146,0.6785714285714286,0.044099542040829984 +flat_mae,reg,logistic,abide_dx,76,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,76,10000.0,test,0.4435483870967742,0.044801957553485865,0.4391347099311701,0.04480831908372212,0.43907563025210083,0.044844619145602886 +flat_mae,reg,logistic,abide_dx,77,0.046415888336127774,train,0.7977207977207977,0.01517196711476815,0.7937003311258278,0.01556280565838572,0.7917312661498708,0.015493484049821924 +flat_mae,reg,logistic,abide_dx,77,0.046415888336127774,test,0.5241935483870968,0.04610070188012056,0.5171275823377994,0.046914123523772625,0.5173319327731093,0.046491536582398074 +flat_mae,reg,logistic,abide_dx,78,0.3593813663804626,train,0.8974358974358975,0.01148237184871722,0.8958731623706242,0.011697225086733468,0.8942783314876339,0.011811821643646062 +flat_mae,reg,logistic,abide_dx,78,0.3593813663804626,test,0.5564516129032258,0.044500511519467705,0.5529334644378892,0.04505443883277149,0.553046218487395,0.04499699923890052 +flat_mae,reg,logistic,abide_dx,79,0.3593813663804626,train,0.896011396011396,0.01146093189044435,0.8943893165167394,0.011717635783521104,0.8926910299003323,0.011911457047304905 +flat_mae,reg,logistic,abide_dx,79,0.3593813663804626,test,0.5,0.047569268732907365,0.4952731092436975,0.047799017751428016,0.4952731092436975,0.047659838553257866 +flat_mae,reg,logistic,abide_dx,80,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,80,21.54434690031882,test,0.5967741935483871,0.04208403898331056,0.5967741935483871,0.04224452423363413,0.6024159663865546,0.042066429153493255 +flat_mae,reg,logistic,abide_dx,81,0.3593813663804626,train,0.8888888888888888,0.012343212698350585,0.8875,0.012541473109769372,0.8868217054263565,0.012697537247801972 +flat_mae,reg,logistic,abide_dx,81,0.3593813663804626,test,0.6129032258064516,0.041286349985307016,0.5921052631578947,0.044496458316269714,0.5966386554621849,0.04202837260719537 +flat_mae,reg,logistic,abide_dx,82,0.3593813663804626,train,0.8846153846153846,0.011595427245418366,0.8828985602754649,0.011818228971302839,0.8814691768180141,0.01192547610253226 +flat_mae,reg,logistic,abide_dx,82,0.3593813663804626,test,0.5887096774193549,0.043035604043636065,0.5712833028269271,0.04539076803723819,0.5745798319327731,0.04360906441015335 +flat_mae,reg,logistic,abide_dx,83,0.3593813663804626,train,0.8974358974358975,0.011750073547632361,0.8957219251336899,0.0120126505515919,0.893687707641196,0.012159273859908774 +flat_mae,reg,logistic,abide_dx,83,0.3593813663804626,test,0.5403225806451613,0.04515417858750829,0.531517200238616,0.0461671000845186,0.5320378151260504,0.04557034075470851 +flat_mae,reg,logistic,abide_dx,84,2.782559402207126,train,0.9857549857549858,0.004701818083101523,0.9855860443342066,0.004764667333415059,0.9850129198966409,0.004958831403792987 +flat_mae,reg,logistic,abide_dx,84,2.782559402207126,test,0.5564516129032258,0.04350655099164201,0.5479551932126997,0.044192846736977584,0.5483193277310925,0.04374310300029739 +flat_mae,reg,logistic,abide_dx,85,0.046415888336127774,train,0.7991452991452992,0.01519510908706132,0.7947261999813353,0.01569006964628756,0.7924326319675157,0.015654033022059526 +flat_mae,reg,logistic,abide_dx,85,0.046415888336127774,test,0.6370967741935484,0.04091262166939002,0.6241664982824813,0.04360885956351044,0.625,0.0419249294313575 +flat_mae,reg,logistic,abide_dx,86,2.782559402207126,train,0.9914529914529915,0.00353080889773285,0.9913671541942677,0.00356348484009617,0.9916574381690662,0.0034591429432327043 +flat_mae,reg,logistic,abide_dx,86,2.782559402207126,test,0.5,0.04446088203373255,0.49882659713168187,0.044403078088396074,0.5,0.04452064699777732 +flat_mae,reg,logistic,abide_dx,87,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,87,21.54434690031882,test,0.6370967741935484,0.0435910752543617,0.6365057650967364,0.04366323319010745,0.6391806722689075,0.043519804568995214 +flat_mae,reg,logistic,abide_dx,88,0.3593813663804626,train,0.8874643874643875,0.011996095175591727,0.8857899538489102,0.012235327604260906,0.8843484680693983,0.012379247401585181 +flat_mae,reg,logistic,abide_dx,88,0.3593813663804626,test,0.5806451612903226,0.04457736263065705,0.5802083333333333,0.044711478131177484,0.5829831932773109,0.044844815501936516 +flat_mae,reg,logistic,abide_dx,89,2.782559402207126,train,0.98005698005698,0.0053215918615037135,0.9798328846280123,0.005383949129123794,0.9795496493170912,0.005466350470743861 +flat_mae,reg,logistic,abide_dx,89,2.782559402207126,test,0.5806451612903226,0.042015738961721,0.5778999738151349,0.04220278004814212,0.5782563025210083,0.04220097635987818 +flat_mae,reg,logistic,abide_dx,90,0.046415888336127774,train,0.8005698005698005,0.015007825546673513,0.7967691505992704,0.015449741752270698,0.7949058693244739,0.015480787581882075 +flat_mae,reg,logistic,abide_dx,90,0.046415888336127774,test,0.5564516129032258,0.04252361772610757,0.5307877536979704,0.045775090699760296,0.5388655462184874,0.04294900430377092 +flat_mae,reg,logistic,abide_dx,91,0.046415888336127774,train,0.782051282051282,0.015414861847037907,0.7764624346751081,0.015984972807575607,0.7739756367663344,0.015863077448563967 +flat_mae,reg,logistic,abide_dx,91,0.046415888336127774,test,0.5967741935483871,0.04205695496559573,0.58994708994709,0.04310766387751679,0.5898109243697479,0.042654774250860256 +flat_mae,reg,logistic,abide_dx,92,0.3593813663804626,train,0.9031339031339032,0.011005211975582805,0.9018593597092128,0.01117778620928044,0.900922849760059,0.011281130536981075 +flat_mae,reg,logistic,abide_dx,92,0.3593813663804626,test,0.5483870967741935,0.04416553150067067,0.5464994775339603,0.04422737471677947,0.5472689075630253,0.04415442064835837 +flat_mae,reg,logistic,abide_dx,93,0.046415888336127774,train,0.7905982905982906,0.014347748913355397,0.7852286137074569,0.014885228272182026,0.7826135105204872,0.014772637158269507 +flat_mae,reg,logistic,abide_dx,93,0.046415888336127774,test,0.5483870967741935,0.04256249307615146,0.5241228070175439,0.04514514127370682,0.5315126050420168,0.04286848043725064 +flat_mae,reg,logistic,abide_dx,94,0.3593813663804626,train,0.8945868945868946,0.011741440008046422,0.8933367280731292,0.011914526713527461,0.8928755998523441,0.012060390685410559 +flat_mae,reg,logistic,abide_dx,94,0.3593813663804626,test,0.6048387096774194,0.04296302829419867,0.5972691721349506,0.043861314543003356,0.5971638655462186,0.043343410859295925 +flat_mae,reg,logistic,abide_dx,95,0.046415888336127774,train,0.7863247863247863,0.015102192722602934,0.7815298306181897,0.01556790636826281,0.7793281653746771,0.015463765932692783 +flat_mae,reg,logistic,abide_dx,95,0.046415888336127774,test,0.6129032258064516,0.041550415698823714,0.5951020408163266,0.04494491025171577,0.5982142857142857,0.04245837721595636 +flat_mae,reg,logistic,abide_dx,96,0.3593813663804626,train,0.8931623931623932,0.01216362706707,0.8917208062635349,0.01238852848279558,0.8906976744186046,0.012567298823305414 +flat_mae,reg,logistic,abide_dx,96,0.3593813663804626,test,0.5967741935483871,0.044753397024866706,0.5860042735042735,0.04662732823096634,0.5866596638655462,0.04549651909509667 +flat_mae,reg,logistic,abide_dx,97,0.000774263682681127,train,0.6495726495726496,0.014967851632591492,0.6023120854826824,0.01880007319528184,0.6207456626061277,0.01561519057843935 +flat_mae,reg,logistic,abide_dx,97,0.000774263682681127,test,0.5645161290322581,0.03512233340554351,0.5080811049074346,0.04247915923678754,0.5367647058823529,0.035767692072483606 +flat_mae,reg,logistic,abide_dx,98,0.3593813663804626,train,0.8874643874643875,0.011680555897576612,0.8856260169979149,0.011921298944725798,0.8837578442229606,0.012009436678084595 +flat_mae,reg,logistic,abide_dx,98,0.3593813663804626,test,0.5564516129032258,0.04385145142276884,0.5406479423452549,0.04608622536726042,0.54359243697479,0.04444596486285978 +flat_mae,reg,logistic,abide_dx,99,0.046415888336127774,train,0.7962962962962963,0.014371828687603158,0.7918145148746876,0.014773117374431401,0.7895533407161315,0.014700729359439533 +flat_mae,reg,logistic,abide_dx,99,0.046415888336127774,test,0.6048387096774194,0.04447780900940147,0.5931704050887178,0.046255852776700246,0.5940126050420168,0.04503883824268437 +flat_mae,reg,logistic,abide_dx,100,0.005994842503189409,train,0.7122507122507122,0.015875499523922053,0.6996110729810112,0.01710518537658545,0.6985603543743079,0.0164635046400145 +flat_mae,reg,logistic,abide_dx,100,0.005994842503189409,test,0.5241935483870968,0.04058911586549991,0.4924731182795699,0.04420579986030442,0.5047268907563025,0.04110783697571518 diff --git a/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b13e3679c1bed0ba4cd43760345f8162ac8f3727 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:23:22 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (abide_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic +model: flat_mae +representation: reg +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/abide_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:21:08 time: 4.3884 data: 3.4196 max mem: 2708 +extract (train) [ 20/289] eta: 0:01:42 time: 0.1788 data: 0.0580 max mem: 2863 +extract (train) [ 40/289] eta: 0:01:08 time: 0.1647 data: 0.0494 max mem: 2863 +extract (train) [ 60/289] eta: 0:00:54 time: 0.1684 data: 0.0534 max mem: 2863 +extract (train) [ 80/289] eta: 0:00:46 time: 0.1697 data: 0.0544 max mem: 2863 +extract (train) [100/289] eta: 0:00:40 time: 0.1746 data: 0.0575 max mem: 2863 +extract (train) [120/289] eta: 0:00:34 time: 0.1735 data: 0.0573 max mem: 2863 +extract (train) [140/289] eta: 0:00:30 time: 0.1820 data: 0.0610 max mem: 2863 +extract (train) [160/289] eta: 0:00:25 time: 0.1628 data: 0.0510 max mem: 2863 +extract (train) [180/289] eta: 0:00:21 time: 0.1677 data: 0.0541 max mem: 2863 +extract (train) [200/289] eta: 0:00:17 time: 0.1711 data: 0.0552 max mem: 2863 +extract (train) [220/289] eta: 0:00:13 time: 0.1762 data: 0.0567 max mem: 2863 +extract (train) [240/289] eta: 0:00:09 time: 0.1594 data: 0.0508 max mem: 2863 +extract (train) [260/289] eta: 0:00:05 time: 0.1552 data: 0.0461 max mem: 2863 +extract (train) [280/289] eta: 0:00:01 time: 0.1422 data: 0.0400 max mem: 2863 +extract (train) [288/289] eta: 0:00:00 time: 0.1423 data: 0.0402 max mem: 2863 +extract (train) Total time: 0:00:52 (0.1829 s / it) +extract (validation) [ 0/62] eta: 0:03:39 time: 3.5446 data: 3.4098 max mem: 2863 +extract (validation) [20/62] eta: 0:00:15 time: 0.2141 data: 0.0790 max mem: 2863 +extract (validation) [40/62] eta: 0:00:05 time: 0.1673 data: 0.0547 max mem: 2863 +extract (validation) [60/62] eta: 0:00:00 time: 0.1594 data: 0.0524 max mem: 2863 +extract (validation) [61/62] eta: 0:00:00 time: 0.1589 data: 0.0520 max mem: 2863 +extract (validation) Total time: 0:00:14 (0.2392 s / it) +extract (test) [ 0/62] eta: 0:03:34 time: 3.4568 data: 3.3171 max mem: 2863 +extract (test) [20/62] eta: 0:00:15 time: 0.2261 data: 0.0815 max mem: 2863 +extract (test) [40/62] eta: 0:00:05 time: 0.1556 data: 0.0460 max mem: 2863 +extract (test) [60/62] eta: 0:00:00 time: 0.1458 data: 0.0419 max mem: 2863 +extract (test) [61/62] eta: 0:00:00 time: 0.1461 data: 0.0420 max mem: 2863 +extract (test) Total time: 0:00:14 (0.2335 s / it) +feature extraction time: 0:01:22 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | abide_dx | | 0.046416 | train | 0.7849 | 0.014938 | 0.77875 | 0.015604 | 0.77595 | 0.015421 | +| flat_mae | reg | logistic | abide_dx | | 0.046416 | test | 0.58871 | 0.043119 | 0.57406 | 0.045067 | 0.57751 | 0.043448 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.044518755766355285, "f1": 0.5503626107977437, "f1_std": 0.04708714295209538, "bacc": 0.5525210084033614, "bacc_std": 0.04542270435785846} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 1291.5496650148827, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.04514537449960602, "f1": 0.5216737495913697, "f1_std": 0.045076440846920834, "bacc": 0.5220588235294117, "bacc_std": 0.045062379478635325} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.0438743950274172, "f1": 0.6003223207091055, "f1_std": 0.046001979101804036, "bacc": 0.6013655462184874, "bacc_std": 0.04457834353630537} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04283077802592349, "f1": 0.6418067226890756, "f1_std": 0.04344974433865964, "bacc": 0.6418067226890756, "bacc_std": 0.04343013995469458} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04327162953942083, "f1": 0.6017043592264831, "f1_std": 0.043639821211172145, "bacc": 0.601890756302521, "bacc_std": 0.04371192163706521} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.0437432914434423, "f1": 0.5386659580122243, "f1_std": 0.04530050023718753, "bacc": 0.539390756302521, "bacc_std": 0.04433611170728133} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.044477472697124036, "f1": 0.5292707292707293, "f1_std": 0.04554589344606468, "bacc": 0.5304621848739496, "bacc_std": 0.044701731754214956} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.040720475537396106, "f1": 0.607905138339921, "f1_std": 0.04121455061520624, "bacc": 0.6076680672268908, "bacc_std": 0.040993309874647235} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04419890184198541, "f1": 0.5765651155005022, "f1_std": 0.046033362188947685, "bacc": 0.5777310924369747, "bacc_std": 0.0448657301252564} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04285292649345049, "f1": 0.5599598259122867, "f1_std": 0.04418133750075569, "bacc": 0.5614495798319328, "bacc_std": 0.043098317571978746} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04276863134662212, "f1": 0.5170561375235025, "f1_std": 0.04475376331746757, "bacc": 0.5199579831932774, "bacc_std": 0.04335527695714466} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 21.54434690031882, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.042707825707836586, "f1": 0.5718845677806006, "f1_std": 0.042706224277830274, "bacc": 0.5740546218487395, "bacc_std": 0.04279366358415975} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04489199375186728, "f1": 0.5716183895827798, "f1_std": 0.04634357729300094, "bacc": 0.571953781512605, "bacc_std": 0.045549847464558646} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 10000.0, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04527088085608621, "f1": 0.5262187088274045, "f1_std": 0.04546630832389479, "bacc": 0.5262605042016807, "bacc_std": 0.04532386433116002} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043988090810975065, "f1": 0.5766806722689075, "f1_std": 0.044708396261203105, "bacc": 0.5766806722689075, "bacc_std": 0.044696781618941056} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0417583105937254, "f1": 0.5836690840719849, "f1_std": 0.043738177750147364, "bacc": 0.5850840336134454, "bacc_std": 0.04225366666178234} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.03965531445620104, "f1": 0.5682392298764252, "f1_std": 0.04224649600996889, "bacc": 0.5730042016806722, "bacc_std": 0.04020529565183837} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04264003678155743, "f1": 0.5716183895827798, "f1_std": 0.04363945050098277, "bacc": 0.571953781512605, "bacc_std": 0.04289420536324737} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04273403457103017, "f1": 0.5907590759075907, "f1_std": 0.04503938104348942, "bacc": 0.592436974789916, "bacc_std": 0.043499001960029} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 166.81005372000556, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04034346233497787, "f1": 0.5643931861867832, "f1_std": 0.041679951322854236, "bacc": 0.5646008403361344, "bacc_std": 0.040945064088438565} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.532258064516129, "acc_std": 0.043685194309663423, "f1": 0.5278361344537815, "f1_std": 0.04414818638942065, "bacc": 0.5278361344537815, "bacc_std": 0.04399220956759607} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04051695088543892, "f1": 0.5612903225806452, "f1_std": 0.04483370054439903, "bacc": 0.5698529411764706, "bacc_std": 0.041262274795568314} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.042188674252359434, "f1": 0.6025641025641025, "f1_std": 0.044422719240832166, "bacc": 0.6029411764705883, "bacc_std": 0.04321543370563923} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04300677535373634, "f1": 0.5788923719958203, "f1_std": 0.04326615559748417, "bacc": 0.5798319327731092, "bacc_std": 0.04331211299281947} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 10000.0, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.044588472656736766, "f1": 0.5662332519305657, "f1_std": 0.04522788038731881, "bacc": 0.5661764705882353, "bacc_std": 0.044830021536190624} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.044658130225226855, "f1": 0.5292707292707293, "f1_std": 0.04579305492748321, "bacc": 0.5304621848739496, "bacc_std": 0.04491279854318109} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 10000.0, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04192300062339899, "f1": 0.5278361344537815, "f1_std": 0.04224967218774897, "bacc": 0.5278361344537815, "bacc_std": 0.04207465314230655} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04141288513435021, "f1": 0.6539994685091681, "f1_std": 0.0429579204073099, "bacc": 0.6533613445378151, "bacc_std": 0.042301422307118836} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.043776211116649276, "f1": 0.6191239316239316, "f1_std": 0.045433101240720954, "bacc": 0.6192226890756303, "bacc_std": 0.044471085889409644} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04134767627069835, "f1": 0.6153389215233318, "f1_std": 0.042573243729992515, "bacc": 0.6150210084033614, "bacc_std": 0.042135094995925375} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.043764157810301275, "f1": 0.5528846153846154, "f1_std": 0.04518708714845193, "bacc": 0.5540966386554622, "bacc_std": 0.04421089349214402} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.041954573818691235, "f1": 0.58994708994709, "f1_std": 0.04286502636347971, "bacc": 0.5898109243697479, "bacc_std": 0.042448827529272405} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.042653176251351135, "f1": 0.5239442311578096, "f1_std": 0.04485181959114433, "bacc": 0.5273109243697479, "bacc_std": 0.04315024530770486} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04461796148405613, "f1": 0.5662332519305657, "f1_std": 0.04535615350219074, "bacc": 0.5661764705882353, "bacc_std": 0.044988889822220726} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.041856240264929484, "f1": 0.6342182890855457, "f1_std": 0.04222265384112563, "bacc": 0.634453781512605, "bacc_std": 0.04213027131104822} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04007950929785334, "f1": 0.5694444444444444, "f1_std": 0.0414657397437233, "bacc": 0.5703781512605042, "bacc_std": 0.040422090811791385} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.045081666558917814, "f1": 0.5865315462569467, "f1_std": 0.045198836332457464, "bacc": 0.5871848739495797, "bacc_std": 0.04526020507667945} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04143011555023379, "f1": 0.6644445911160979, "f1_std": 0.04243356551908633, "bacc": 0.6638655462184874, "bacc_std": 0.04218380944411694} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.45161290322580644, "acc_std": 0.04400762633747111, "f1": 0.4337899543378996, "f1_std": 0.0444249127569215, "bacc": 0.4385504201680672, "bacc_std": 0.04364747172679911} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04295244569347582, "f1": 0.5343756400628115, "f1_std": 0.04642472204025583, "bacc": 0.5404411764705883, "bacc_std": 0.043752113399376964} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 166.81005372000556, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04495775274341205, "f1": 0.5550336008351275, "f1_std": 0.04498923944668507, "bacc": 0.5561974789915967, "bacc_std": 0.044973758558657075} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.0466905007641008, "f1": 0.5841388834089565, "f1_std": 0.04698921331601806, "bacc": 0.5840336134453781, "bacc_std": 0.04686050285437231} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041209910989805844, "f1": 0.607462787095036, "f1_std": 0.04266220276560639, "bacc": 0.608718487394958, "bacc_std": 0.04136891094714091} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.532258064516129, "acc_std": 0.042196023775666204, "f1": 0.49888517279821626, "f1_std": 0.04632433963225677, "bacc": 0.5120798319327731, "bacc_std": 0.04267222396784233} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042907215434194027, "f1": 0.543354536324071, "f1_std": 0.04459366184585476, "bacc": 0.5451680672268907, "bacc_std": 0.04339823985002167} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04198784262378567, "f1": 0.5457875457875458, "f1_std": 0.043087366836105145, "bacc": 0.5467436974789917, "bacc_std": 0.04238832253541902} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04262547737609588, "f1": 0.6189604445897352, "f1_std": 0.04283919059345905, "bacc": 0.6197478991596639, "bacc_std": 0.04291078755612905} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.0424280746587773, "f1": 0.5682392298764252, "f1_std": 0.0458045440702839, "bacc": 0.5730042016806722, "bacc_std": 0.043188120684140435} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.5080645161290323, "acc_std": 0.042585688239971047, "f1": 0.5054593004249754, "f1_std": 0.04291830011439899, "bacc": 0.5057773109243697, "bacc_std": 0.04280140616626618} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.045709108289761706, "f1": 0.551522325244953, "f1_std": 0.04613352997655308, "bacc": 0.5514705882352942, "bacc_std": 0.045951821849425464} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.03882082162277381, "f1": 0.5180552611122888, "f1_std": 0.04389207505992633, "bacc": 0.5341386554621849, "bacc_std": 0.03941093102404342} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.0426361167266877, "f1": 0.5694444444444444, "f1_std": 0.04404825379217877, "bacc": 0.5703781512605042, "bacc_std": 0.043197177688233265} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04119973366552632, "f1": 0.5670158474348643, "f1_std": 0.04243270954635795, "bacc": 0.5688025210084033, "bacc_std": 0.041382986825271674} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04449574100677429, "f1": 0.6118548118548119, "f1_std": 0.04616122429292724, "bacc": 0.6118697478991597, "bacc_std": 0.04514175024805693} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04533348508472694, "f1": 0.5528846153846154, "f1_std": 0.046868187240718596, "bacc": 0.5540966386554622, "bacc_std": 0.045783591851823055} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04063303390504853, "f1": 0.6118548118548119, "f1_std": 0.0420421229375917, "bacc": 0.6118697478991597, "bacc_std": 0.04107294351264788} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04551934958085747, "f1": 0.5691904293674206, "f1_std": 0.045987095522188194, "bacc": 0.569327731092437, "bacc_std": 0.045958785010372254} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.045907997394417775, "f1": 0.5662332519305657, "f1_std": 0.046670200534039, "bacc": 0.5661764705882353, "bacc_std": 0.046268935225734775} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 2.782559402207126, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04443544288974166, "f1": 0.5603991596638656, "f1_std": 0.04486266550592663, "bacc": 0.5603991596638656, "bacc_std": 0.044782259069298454} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.044271475914007874, "f1": 0.5363247863247864, "f1_std": 0.04574031620227208, "bacc": 0.5378151260504201, "bacc_std": 0.044732407206554116} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04388309545368575, "f1": 0.5479551932126997, "f1_std": 0.044362236049448715, "bacc": 0.5483193277310925, "bacc_std": 0.043892656829541465} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.5161290322580645, "acc_std": 0.04234372934913159, "f1": 0.5057135264416689, "f1_std": 0.04363081226565192, "bacc": 0.506827731092437, "bacc_std": 0.04289633973058741} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 21.54434690031882, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043864002649187266, "f1": 0.607905138339921, "f1_std": 0.04450986195891473, "bacc": 0.6076680672268908, "bacc_std": 0.044365847197314796} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04057975728553286, "f1": 0.575109649122807, "f1_std": 0.04392679998141624, "bacc": 0.5803571428571428, "bacc_std": 0.04133114218742307} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04115298480266741, "f1": 0.6575739206573719, "f1_std": 0.043606460730697155, "bacc": 0.657563025210084, "bacc_std": 0.04209694830757878} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043662607080016805, "f1": 0.5880398671096345, "f1_std": 0.04375447363108648, "bacc": 0.5903361344537814, "bacc_std": 0.04365435325212573} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042811568355009016, "f1": 0.5406479423452549, "f1_std": 0.04467698219419057, "bacc": 0.54359243697479, "bacc_std": 0.04324857773566792} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04083767452696139, "f1": 0.5854473942969518, "f1_std": 0.04133768191150257, "bacc": 0.585609243697479, "bacc_std": 0.04118539770962134} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 1291.5496650148827, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.0454128936020044, "f1": 0.5703170970905524, "f1_std": 0.04525307519212954, "bacc": 0.5709033613445378, "bacc_std": 0.04521748244734315} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043251629263219626, "f1": 0.6092436974789917, "f1_std": 0.043844535090928005, "bacc": 0.6092436974789917, "bacc_std": 0.04361354232433648} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.040707274608297955, "f1": 0.5782312925170068, "f1_std": 0.04387462008725824, "bacc": 0.5819327731092437, "bacc_std": 0.04157012040933598} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.5161290322580645, "acc_std": 0.044508329728181306, "f1": 0.5115546218487395, "f1_std": 0.04498508532319034, "bacc": 0.5115546218487395, "bacc_std": 0.04478060680806414} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.040912138415377934, "f1": 0.5740553647201454, "f1_std": 0.043535913286514655, "bacc": 0.576155462184874, "bacc_std": 0.04170573497796926} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 2.782559402207126, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.046580399427463705, "f1": 0.5541026479241582, "f1_std": 0.04656095832210816, "bacc": 0.5546218487394958, "bacc_std": 0.04657079323537288} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.6854838709677419, "acc_std": 0.04359119461151173, "f1": 0.6794591370053689, "f1_std": 0.044638323383712146, "bacc": 0.6785714285714286, "bacc_std": 0.044099542040829984} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 10000.0, "split": "test", "acc": 0.4435483870967742, "acc_std": 0.044801957553485865, "f1": 0.4391347099311701, "f1_std": 0.04480831908372212, "bacc": 0.43907563025210083, "bacc_std": 0.044844619145602886} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.04610070188012056, "f1": 0.5171275823377994, "f1_std": 0.046914123523772625, "bacc": 0.5173319327731093, "bacc_std": 0.046491536582398074} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.044500511519467705, "f1": 0.5529334644378892, "f1_std": 0.04505443883277149, "bacc": 0.553046218487395, "bacc_std": 0.04499699923890052} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.047569268732907365, "f1": 0.4952731092436975, "f1_std": 0.047799017751428016, "bacc": 0.4952731092436975, "bacc_std": 0.047659838553257866} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 21.54434690031882, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04208403898331056, "f1": 0.5967741935483871, "f1_std": 0.04224452423363413, "bacc": 0.6024159663865546, "bacc_std": 0.042066429153493255} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041286349985307016, "f1": 0.5921052631578947, "f1_std": 0.044496458316269714, "bacc": 0.5966386554621849, "bacc_std": 0.04202837260719537} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043035604043636065, "f1": 0.5712833028269271, "f1_std": 0.04539076803723819, "bacc": 0.5745798319327731, "bacc_std": 0.04360906441015335} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04515417858750829, "f1": 0.531517200238616, "f1_std": 0.0461671000845186, "bacc": 0.5320378151260504, "bacc_std": 0.04557034075470851} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 2.782559402207126, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04350655099164201, "f1": 0.5479551932126997, "f1_std": 0.044192846736977584, "bacc": 0.5483193277310925, "bacc_std": 0.04374310300029739} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04091262166939002, "f1": 0.6241664982824813, "f1_std": 0.04360885956351044, "bacc": 0.625, "bacc_std": 0.0419249294313575} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.04446088203373255, "f1": 0.49882659713168187, "f1_std": 0.044403078088396074, "bacc": 0.5, "bacc_std": 0.04452064699777732} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 21.54434690031882, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.0435910752543617, "f1": 0.6365057650967364, "f1_std": 0.04366323319010745, "bacc": 0.6391806722689075, "bacc_std": 0.043519804568995214} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04457736263065705, "f1": 0.5802083333333333, "f1_std": 0.044711478131177484, "bacc": 0.5829831932773109, "bacc_std": 0.044844815501936516} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042015738961721, "f1": 0.5778999738151349, "f1_std": 0.04220278004814212, "bacc": 0.5782563025210083, "bacc_std": 0.04220097635987818} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04252361772610757, "f1": 0.5307877536979704, "f1_std": 0.045775090699760296, "bacc": 0.5388655462184874, "bacc_std": 0.04294900430377092} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04205695496559573, "f1": 0.58994708994709, "f1_std": 0.04310766387751679, "bacc": 0.5898109243697479, "bacc_std": 0.042654774250860256} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04416553150067067, "f1": 0.5464994775339603, "f1_std": 0.04422737471677947, "bacc": 0.5472689075630253, "bacc_std": 0.04415442064835837} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04256249307615146, "f1": 0.5241228070175439, "f1_std": 0.04514514127370682, "bacc": 0.5315126050420168, "bacc_std": 0.04286848043725064} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04296302829419867, "f1": 0.5972691721349506, "f1_std": 0.043861314543003356, "bacc": 0.5971638655462186, "bacc_std": 0.043343410859295925} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041550415698823714, "f1": 0.5951020408163266, "f1_std": 0.04494491025171577, "bacc": 0.5982142857142857, "bacc_std": 0.04245837721595636} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044753397024866706, "f1": 0.5860042735042735, "f1_std": 0.04662732823096634, "bacc": 0.5866596638655462, "bacc_std": 0.04549651909509667} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.000774263682681127, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.03512233340554351, "f1": 0.5080811049074346, "f1_std": 0.04247915923678754, "bacc": 0.5367647058823529, "bacc_std": 0.035767692072483606} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04385145142276884, "f1": 0.5406479423452549, "f1_std": 0.04608622536726042, "bacc": 0.54359243697479, "bacc_std": 0.04444596486285978} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04447780900940147, "f1": 0.5931704050887178, "f1_std": 0.046255852776700246, "bacc": 0.5940126050420168, "bacc_std": 0.04503883824268437} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.04058911586549991, "f1": 0.4924731182795699, "f1_std": 0.04420579986030442, "bacc": 0.5047268907563025, "bacc_std": 0.04110783697571518} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | abide_dx | train | 100 | 432.32 | 1971.3 | 0.86338 | 0.097727 | 0.85948 | 0.10215 | 0.85844 | 0.10223 | +| flat_mae | reg | logistic | abide_dx | test | 100 | 432.32 | 1971.3 | 0.57637 | 0.041573 | 0.56602 | 0.043357 | 0.56801 | 0.042191 | + + +done! total time: 0:05:50 diff --git a/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3350be7c936f3bca42e8c6b674da2de3c0a4619b --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..8001c09d5236a9d10c1d9ed80c2fd4540d27ec94 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,train,0.726027397260274,0.022386600286696548,0.7132667169431876,0.024160123093145313,0.7106460279660499,0.0234795288427223 +flat_mae,patch,logistic,adhd200_dx,,0.005994842503189409,test,0.5384615384615384,0.05439696301999603,0.4846723044397463,0.06087938449713914,0.5033783783783784,0.05496478138146534 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,train,0.7315068493150685,0.0228856686593786,0.7183109683109683,0.02453232580695459,0.7155003968980888,0.02378797116974989 +flat_mae,patch,logistic,adhd200_dx,1,0.005994842503189409,test,0.6,0.05966276033183682,0.5833333333333333,0.06227910300215068,0.5834942084942085,0.060596175261615065 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,train,0.7068493150684931,0.02320100941890073,0.6956555620494838,0.02444761304766887,0.693655736703914,0.02400492427477366 +flat_mae,patch,logistic,adhd200_dx,2,0.005994842503189409,test,0.6461538461538462,0.05681656563166692,0.6233308138070043,0.06176332542582999,0.6240347490347491,0.05864676332085262 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,train,0.7424657534246575,0.023105182810282326,0.7304707139265962,0.024893801003908412,0.7273615436282591,0.02427709215974455 +flat_mae,patch,logistic,adhd200_dx,3,0.005994842503189409,test,0.5538461538461539,0.05963121377940192,0.5321419707123356,0.0630691929586715,0.5342664092664092,0.06083832755968385 +flat_mae,patch,logistic,adhd200_dx,4,0.046415888336127774,train,0.8054794520547945,0.020840392668994047,0.8007902282283668,0.021420508825704416,0.7989711180313854,0.02144961474522082 +flat_mae,patch,logistic,adhd200_dx,4,0.046415888336127774,test,0.676923076923077,0.058432535315797764,0.6690909090909091,0.06036603406707303,0.6684362934362934,0.05997536414767835 +flat_mae,patch,logistic,adhd200_dx,5,0.046415888336127774,train,0.8410958904109589,0.019900430700186315,0.8368325317548403,0.02074898501926985,0.8341118641997924,0.020972736514584013 +flat_mae,patch,logistic,adhd200_dx,5,0.046415888336127774,test,0.49230769230769234,0.0603332441944703,0.4879446168536643,0.06069833937518913,0.4888996138996139,0.06127899701475652 +flat_mae,patch,logistic,adhd200_dx,6,0.046415888336127774,train,0.821917808219178,0.01886155941907434,0.8166268617494068,0.019622448171509294,0.8135342248275019,0.01964923649490192 +flat_mae,patch,logistic,adhd200_dx,6,0.046415888336127774,test,0.6153846153846154,0.061920384079049776,0.606060606060606,0.06363418828170457,0.6056949806949807,0.0630879043696591 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,train,0.726027397260274,0.02351892336081293,0.7146118721461188,0.02505351783579914,0.7120809672101117,0.02454175046808116 +flat_mae,patch,logistic,adhd200_dx,7,0.005994842503189409,test,0.676923076923077,0.05437486366710788,0.6612062546537603,0.05842661669751474,0.6597490347490347,0.056381689654824214 +flat_mae,patch,logistic,adhd200_dx,8,0.046415888336127774,train,0.8191780821917808,0.020619663698918166,0.8143266740658528,0.021405326246946833,0.8118245099835135,0.021482222453288187 +flat_mae,patch,logistic,adhd200_dx,8,0.046415888336127774,test,0.6153846153846154,0.06168103484193175,0.606060606060606,0.06339601300051742,0.6056949806949807,0.06277419019784093 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,train,0.7232876712328767,0.02373545068964977,0.715602700096432,0.024699266104137398,0.7139586004762777,0.024562189119617685 +flat_mae,patch,logistic,adhd200_dx,9,0.005994842503189409,test,0.6461538461538462,0.05690281552086139,0.6167649320687003,0.06408292307195822,0.6196911196911197,0.05922099497387309 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,train,0.7205479452054795,0.023529333692319118,0.7082288401253918,0.02504879251384155,0.7057916590340111,0.02441800517698965 +flat_mae,patch,logistic,adhd200_dx,10,0.005994842503189409,test,0.5538461538461539,0.06004131910609559,0.5250692869740489,0.06456839396869556,0.5299227799227799,0.06114573529641867 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,train,0.7150684931506849,0.021583043461456276,0.6995314083080041,0.0235906781794723,0.6973499419918178,0.02269396804085223 +flat_mae,patch,logistic,adhd200_dx,11,0.005994842503189409,test,0.5538461538461539,0.05570335632011273,0.5250692869740489,0.061145063414686236,0.5299227799227799,0.05730203505106971 +flat_mae,patch,logistic,adhd200_dx,12,0.046415888336127774,train,0.8027397260273973,0.020714804519717557,0.7966825524540446,0.021606563756984977,0.7936740550772424,0.021538402565855555 +flat_mae,patch,logistic,adhd200_dx,12,0.046415888336127774,test,0.5692307692307692,0.05584806947339654,0.5512820512820513,0.05903187238348149,0.5521235521235521,0.05703249183708538 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,train,0.7287671232876712,0.023968515659425375,0.7177857092650011,0.025349028734213352,0.715225621298162,0.024890108409822823 +flat_mae,patch,logistic,adhd200_dx,13,0.005994842503189409,test,0.6307692307692307,0.059052046044246714,0.6235521235521235,0.059983020688376305,0.6235521235521235,0.05979902316293084 +flat_mae,patch,logistic,adhd200_dx,14,0.005994842503189409,train,0.736986301369863,0.021879086343255118,0.726642950758285,0.023079550071786758,0.7239421139402821,0.022683076903921653 +flat_mae,patch,logistic,adhd200_dx,14,0.005994842503189409,test,0.6,0.05496162405117952,0.5775,0.05941689039774497,0.5791505791505791,0.05682717516998861 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,train,0.7315068493150685,0.021761127651727937,0.7183109683109683,0.023446312370865224,0.7155003968980888,0.022723025592348723 +flat_mae,patch,logistic,adhd200_dx,15,0.005994842503189409,test,0.5692307692307692,0.06083521247536723,0.5565302144249512,0.06271443349568895,0.5564671814671815,0.06182479384442199 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,train,0.7424657534246575,0.021737849570724953,0.7329212853406402,0.022975456757077593,0.7302314221163827,0.0226375274224939 +flat_mae,patch,logistic,adhd200_dx,16,0.005994842503189409,test,0.5692307692307692,0.06267365272235319,0.5608108108108107,0.06379927375746387,0.5608108108108107,0.06380539726634211 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,train,0.8,0.019680723470874333,0.7944455159112825,0.020428084663006565,0.7919643402332539,0.02047143103376846 +flat_mae,patch,logistic,adhd200_dx,17,0.046415888336127774,test,0.5692307692307692,0.058811672149881006,0.5376016260162602,0.06502272198205132,0.5434362934362934,0.06052230805642295 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,train,0.7287671232876712,0.023010371579467878,0.7164748252242072,0.024710841683751067,0.7137906820541002,0.024019868664454377 +flat_mae,patch,logistic,adhd200_dx,18,0.005994842503189409,test,0.5846153846153846,0.054128455586151834,0.5578231292517006,0.05821589786851953,0.5612934362934363,0.05508076696427302 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,train,0.7315068493150685,0.023412012929453434,0.7175993178803765,0.025689498443328396,0.7147829272760579,0.024778011800644817 +flat_mae,patch,logistic,adhd200_dx,19,0.005994842503189409,test,0.676923076923077,0.058055138043539595,0.6612062546537603,0.06227047626890958,0.6597490347490347,0.060416444196321514 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,train,0.7123287671232876,0.022233973757317782,0.701985210068351,0.023355310266689935,0.6999450448800146,0.022966393924305273 +flat_mae,patch,logistic,adhd200_dx,20,0.005994842503189409,test,0.6,0.056797458064631295,0.5775,0.06170274408446519,0.5791505791505791,0.058614270578808324 +flat_mae,patch,logistic,adhd200_dx,21,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,21,21.54434690031882,test,0.49230769230769234,0.06120416120749002,0.49037776193870275,0.06255880457504902,0.5106177606177607,0.06183605330165441 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,train,0.6986301369863014,0.022871426507703425,0.6830196425187898,0.024627942358372554,0.6813518959516395,0.023747762651161644 +flat_mae,patch,logistic,adhd200_dx,22,0.005994842503189409,test,0.6153846153846154,0.05997455081584297,0.6018132810585641,0.06279940288273309,0.6013513513513513,0.06157381163049622 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,train,0.7534246575342466,0.02063413812643211,0.7413059913059913,0.022437926109384627,0.7377877511143677,0.021833793046329562 +flat_mae,patch,logistic,adhd200_dx,23,0.005994842503189409,test,0.5692307692307692,0.054612489630748745,0.5190274841437632,0.06199072249172965,0.5347490347490347,0.055387273680126796 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,train,0.7780821917808219,0.0202116153209616,0.7723334950447016,0.020974805193935082,0.7703944556390059,0.020979384653258267 +flat_mae,patch,logistic,adhd200_dx,24,0.046415888336127774,test,0.6153846153846154,0.05783796996118354,0.5905769715293525,0.06272039053112337,0.5926640926640927,0.05936791280094268 +flat_mae,patch,logistic,adhd200_dx,25,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,25,166.81005372000556,test,0.5538461538461539,0.05990505308081601,0.5500119360229172,0.06055104181643479,0.5516409266409266,0.0612559660723685 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,train,0.7479452054794521,0.02023721213787931,0.7362053795877326,0.02186379271887657,0.7329333821823288,0.021315233981433108 +flat_mae,patch,logistic,adhd200_dx,26,0.005994842503189409,test,0.6,0.05824738102652947,0.5833333333333333,0.06134778598467154,0.5834942084942085,0.059600869575884854 +flat_mae,patch,logistic,adhd200_dx,27,0.000774263682681127,train,0.6547945205479452,0.02370597653177784,0.6378283878283879,0.02523587906731478,0.6374946571411125,0.02434930648315961 +flat_mae,patch,logistic,adhd200_dx,27,0.000774263682681127,test,0.6461538461538462,0.05882583661329806,0.6375757575757576,0.06056792533760488,0.6370656370656371,0.05997429312540856 +flat_mae,patch,logistic,adhd200_dx,28,0.005994842503189409,train,0.736986301369863,0.021098676919686362,0.726027397260274,0.022306382711375312,0.7232246443182512,0.02184765923596438 +flat_mae,patch,logistic,adhd200_dx,28,0.005994842503189409,test,0.5846153846153846,0.05918108605581316,0.5578231292517006,0.06390614488491919,0.5612934362934363,0.0606023374727288 +flat_mae,patch,logistic,adhd200_dx,29,0.3593813663804626,train,0.9534246575342465,0.011329784453501631,0.9525339453050297,0.0115754294408791,0.951563167857361,0.011826490550251782 +flat_mae,patch,logistic,adhd200_dx,29,0.3593813663804626,test,0.5230769230769231,0.06585744691080476,0.5189782764382908,0.06589057858559953,0.5202702702702703,0.06624991107618636 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,train,0.7232876712328767,0.023271445757676243,0.7139343053798819,0.02442099971210815,0.711806191610185,0.024082453387019653 +flat_mae,patch,logistic,adhd200_dx,30,0.005994842503189409,test,0.5538461538461539,0.056186805922416636,0.5250692869740489,0.06069505840618855,0.5299227799227799,0.05716336915320982 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,train,0.7287671232876712,0.02237274432198481,0.7150798344175044,0.023923869792708535,0.7123557428100384,0.0231741425208761 +flat_mae,patch,logistic,adhd200_dx,31,0.005994842503189409,test,0.6,0.06104183452461253,0.588206627680312,0.06298819262268386,0.5878378378378378,0.06235392273072612 +flat_mae,patch,logistic,adhd200_dx,32,0.005994842503189409,train,0.7452054794520548,0.023347144685089846,0.734283634314163,0.024729139283984458,0.7312236673383403,0.024163312828294346 +flat_mae,patch,logistic,adhd200_dx,32,0.005994842503189409,test,0.6,0.06107594651418471,0.5953065134099617,0.06154312884361415,0.5965250965250966,0.0617195033910934 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,train,0.7123287671232876,0.02348915258124056,0.7013442431326709,0.024835643838758355,0.6992275752579837,0.02436879570542469 +flat_mae,patch,logistic,adhd200_dx,33,0.005994842503189409,test,0.6153846153846154,0.05969271213185748,0.6139225469232596,0.0597297369949006,0.6187258687258688,0.05993129270567676 +flat_mae,patch,logistic,adhd200_dx,34,0.3593813663804626,train,0.9452054794520548,0.011763885883138083,0.9441998410077661,0.011986792510695614,0.9435641448372718,0.012112265921945541 +flat_mae,patch,logistic,adhd200_dx,34,0.3593813663804626,test,0.5076923076923077,0.06247075339377458,0.5047619047619047,0.06301043820856556,0.5067567567567568,0.06363655726337746 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,train,0.7123287671232876,0.023242957234118292,0.6978119455943228,0.025051383224213783,0.6956402271478292,0.02419524123783205 +flat_mae,patch,logistic,adhd200_dx,35,0.005994842503189409,test,0.5846153846153846,0.05724872340376636,0.5644080416976918,0.061053989476235394,0.5656370656370656,0.058599988328509836 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,train,0.6712328767123288,0.024286486152700987,0.6523809523809523,0.02635474792626445,0.652057763937229,0.02520503433983414 +flat_mae,patch,logistic,adhd200_dx,36,0.000774263682681127,test,0.5538461538461539,0.05547803232817398,0.5250692869740489,0.059655434101498435,0.5299227799227799,0.05639575341616171 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,train,0.7013698630136986,0.022870067117864018,0.687835918681198,0.024344344781351356,0.6859314892837516,0.023695206704746296 +flat_mae,patch,logistic,adhd200_dx,37,0.005994842503189409,test,0.6461538461538462,0.05746209658878362,0.6233308138070043,0.06414993123468181,0.6240347490347491,0.059885046219525104 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,train,0.7178082191780822,0.023503134744987917,0.7082696381596816,0.02474412391019247,0.7062343530561153,0.024398909621410482 +flat_mae,patch,logistic,adhd200_dx,38,0.005994842503189409,test,0.5384615384615384,0.059476365949079936,0.5294401544401545,0.06054230473419438,0.5294401544401545,0.05992099942966141 +flat_mae,patch,logistic,adhd200_dx,39,0.046415888336127774,train,0.810958904109589,0.01923457433088587,0.8045689809030876,0.020175437666204554,0.8009556084753007,0.020101570996476255 +flat_mae,patch,logistic,adhd200_dx,39,0.046415888336127774,test,0.6461538461538462,0.05650159132701669,0.6167649320687003,0.0633843477503081,0.6196911196911197,0.05839305718936094 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,train,0.7287671232876712,0.023244878652332084,0.7184102863822326,0.024588115576345982,0.7159430909201929,0.024201058227729853 +flat_mae,patch,logistic,adhd200_dx,40,0.005994842503189409,test,0.6615384615384615,0.04981266681425448,0.622093023255814,0.059939099101357064,0.6288610038610039,0.05263209109907507 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,train,0.663013698630137,0.021183278173131162,0.6306792474560098,0.025124257637588642,0.6354491054527691,0.02244919387936628 +flat_mae,patch,logistic,adhd200_dx,41,0.000774263682681127,test,0.6,0.06014341046602867,0.5833333333333333,0.0628568050445923,0.5834942084942085,0.0609801788619855 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,train,0.7232876712328767,0.022585503764505473,0.7120844104622738,0.02385759909115425,0.7096537827440923,0.023394066533556045 +flat_mae,patch,logistic,adhd200_dx,42,0.005994842503189409,test,0.5692307692307692,0.061793195849174504,0.564176245210728,0.06219704813314564,0.5651544401544402,0.062308234115824535 +flat_mae,patch,logistic,adhd200_dx,43,0.046415888336127774,train,0.8136986301369863,0.01899632066774026,0.8067941213102503,0.020221358232590962,0.8026653233192893,0.020197090077348732 +flat_mae,patch,logistic,adhd200_dx,43,0.046415888336127774,test,0.6153846153846154,0.058459748960466046,0.5966741126830479,0.061267749343580626,0.597007722007722,0.05920227895012655 +flat_mae,patch,logistic,adhd200_dx,44,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adhd200_dx,44,10000.0,test,0.5076923076923077,0.05975396498443385,0.4980694980694981,0.060589848290144445,0.4980694980694981,0.06041639786254466 +flat_mae,patch,logistic,adhd200_dx,45,0.000774263682681127,train,0.673972602739726,0.02298270842329635,0.646355264979116,0.02639189585337149,0.6487451914270013,0.024191943140480097 +flat_mae,patch,logistic,adhd200_dx,45,0.000774263682681127,test,0.5076923076923077,0.057695351714565836,0.48,0.06114988047802967,0.48503861003861004,0.05824168080027079 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,train,0.7205479452054795,0.022417361178153437,0.7075320512820513,0.023992091193363013,0.7050741894119802,0.023308430104023167 +flat_mae,patch,logistic,adhd200_dx,46,0.005994842503189409,test,0.6615384615384615,0.0582335635951818,0.6366869918699187,0.06513227208978496,0.6375482625482626,0.060590565572679445 +flat_mae,patch,logistic,adhd200_dx,47,0.046415888336127774,train,0.8164383561643835,0.0197847611149985,0.8113404050144648,0.020609889832311774,0.8086798558954631,0.020697516513267466 +flat_mae,patch,logistic,adhd200_dx,47,0.046415888336127774,test,0.5230769230769231,0.056511912133794855,0.4834657780056396,0.06128402688794509,0.4942084942084942,0.05708780847701859 +flat_mae,patch,logistic,adhd200_dx,48,0.046415888336127774,train,0.8054794520547945,0.01993607724278681,0.7984852372843134,0.021177524287810185,0.7946663002992,0.02113615524296622 +flat_mae,patch,logistic,adhd200_dx,48,0.046415888336127774,test,0.6461538461538462,0.05731619761355197,0.6375757575757576,0.05861724956477301,0.6370656370656371,0.05811930503084732 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,train,0.7150684931506849,0.021610733139502618,0.701797385620915,0.023051812632860075,0.6995023508579105,0.022363411511278693 +flat_mae,patch,logistic,adhd200_dx,49,0.005994842503189409,test,0.5846153846153846,0.0620793079324567,0.5644080416976918,0.0659624804294108,0.5656370656370656,0.06339227654927523 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,train,0.7342465753424657,0.021275613023224036,0.721529640320589,0.022898925316614076,0.7186450509861391,0.022271778450294048 +flat_mae,patch,logistic,adhd200_dx,50,0.005994842503189409,test,0.6,0.0565501631009634,0.570630081300813,0.06266719069329077,0.5748069498069498,0.05821804429397302 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,train,0.7424657534246575,0.022823030116458105,0.734031007751938,0.023843767482378278,0.7316663613604445,0.023603605230976973 +flat_mae,patch,logistic,adhd200_dx,51,0.005994842503189409,test,0.6153846153846154,0.06053235234544725,0.6018132810585641,0.06384403565351428,0.6013513513513513,0.062348825084963796 +flat_mae,patch,logistic,adhd200_dx,52,0.046415888336127774,train,0.7835616438356164,0.02082855770121708,0.7762456448020858,0.021850499692384093,0.773096415704952,0.021687363634560607 +flat_mae,patch,logistic,adhd200_dx,52,0.046415888336127774,test,0.676923076923077,0.054313889382750495,0.6500897205844656,0.061939995603703155,0.6510617760617761,0.05717900683841391 +flat_mae,patch,logistic,adhd200_dx,53,0.000774263682681127,train,0.6328767123287671,0.021784263706699156,0.6024352971777864,0.02458678068766804,0.6073151370824937,0.02254355373341028 +flat_mae,patch,logistic,adhd200_dx,53,0.000774263682681127,test,0.6307692307692307,0.05200545260443097,0.587737843551797,0.061668857110856505,0.5974903474903475,0.05443315612621023 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,train,0.7424657534246575,0.021279683274139708,0.7345577768150028,0.022267495706857546,0.7323838309824754,0.022131005906646316 +flat_mae,patch,logistic,adhd200_dx,54,0.005994842503189409,test,0.5230769230769231,0.06102273123853644,0.5062484685126194,0.06268275275637886,0.5072393822393823,0.0612732741213254 +flat_mae,patch,logistic,adhd200_dx,55,0.046415888336127774,train,0.810958904109589,0.020626843230669132,0.8053423609339857,0.021566778531189056,0.8023905477193625,0.021642331296383016 +flat_mae,patch,logistic,adhd200_dx,55,0.046415888336127774,test,0.5846153846153846,0.060000441812969006,0.5830363506771205,0.06022342894983551,0.5873552123552124,0.060255689715603744 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,train,0.7013698630136986,0.023081030660605018,0.6870796989169505,0.024611998731857484,0.6852140196617207,0.023815817370639567 +flat_mae,patch,logistic,adhd200_dx,56,0.005994842503189409,test,0.5384615384615384,0.06299605322473377,0.5192307692307693,0.06580462782417368,0.5207528957528957,0.06413751177681697 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,train,0.8191780821917808,0.020081110812074133,0.8143266740658528,0.020792879450875337,0.8118245099835135,0.020817381891315608 +flat_mae,patch,logistic,adhd200_dx,57,0.046415888336127774,test,0.5384615384615384,0.056209885630585925,0.5045731707317074,0.06140760600336114,0.5120656370656371,0.05746641141432253 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,train,0.7095890410958904,0.023042994399982402,0.6994624658215263,0.02427363383934421,0.6975178604139952,0.02388159664860667 +flat_mae,patch,logistic,adhd200_dx,58,0.005994842503189409,test,0.6153846153846154,0.058624961866479315,0.6094688776736361,0.05968040897926644,0.61003861003861,0.05941821416926358 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,train,0.7506849315068493,0.0221704643097244,0.74059090447591,0.023557753099984962,0.737512975514441,0.023166406513465097 +flat_mae,patch,logistic,adhd200_dx,59,0.005994842503189409,test,0.5384615384615384,0.056258776567113526,0.4953416149068323,0.06171977354825464,0.5077220077220077,0.05695082077332002 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,train,0.7397260273972602,0.02272804056909305,0.7314700803072895,0.02363499402536364,0.7292391768944251,0.023362572232572088 +flat_mae,patch,logistic,adhd200_dx,60,0.005994842503189409,test,0.6615384615384615,0.05653736262668312,0.6515594541910331,0.05878873611178601,0.6505791505791505,0.058035022760551475 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,train,0.7068493150684931,0.023498241550735897,0.694283321200166,0.024966901461308925,0.6922207974598522,0.024336861219363567 +flat_mae,patch,logistic,adhd200_dx,61,0.005994842503189409,test,0.6,0.06055349437046035,0.5833333333333333,0.06448878533999411,0.5834942084942085,0.06231867425256164 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,train,0.7287671232876712,0.022831371687234665,0.7184102863822326,0.024115810575760562,0.7159430909201929,0.023687068637004222 +flat_mae,patch,logistic,adhd200_dx,62,0.005994842503189409,test,0.5538461538461539,0.056884344410859246,0.5381034060279344,0.059224134248217,0.5386100386100386,0.05802949941438239 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,train,0.7315068493150685,0.022040840306034936,0.7203196347031964,0.02336959012377697,0.7176528057641814,0.022905692619865758 +flat_mae,patch,logistic,adhd200_dx,63,0.005994842503189409,test,0.5538461538461539,0.05737988019234245,0.543030303030303,0.05852571859395937,0.542953667953668,0.05817786493802208 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,train,0.7123287671232876,0.02289760345425276,0.6978119455943228,0.024706693677689535,0.6956402271478292,0.023889372439042003 +flat_mae,patch,logistic,adhd200_dx,64,0.005994842503189409,test,0.6153846153846154,0.056803066839448586,0.5966741126830479,0.06027175112431256,0.597007722007722,0.05821836379278418 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,train,0.7232876712328767,0.023823283850960237,0.7100463265193762,0.025720224905552026,0.7075013738779996,0.024996925223532983 +flat_mae,patch,logistic,adhd200_dx,65,0.005994842503189409,test,0.676923076923077,0.053382407402798385,0.6500897205844656,0.06119146903301269,0.6510617760617761,0.05603366381525318 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,train,0.7205479452054795,0.02365060999158989,0.7095581351806777,0.02505692588022763,0.7072265982780729,0.0245627974694703 +flat_mae,patch,logistic,adhd200_dx,66,0.005994842503189409,test,0.6,0.058557160664505906,0.5833333333333333,0.06110511986712878,0.5834942084942085,0.059499485686344555 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,train,0.7397260273972602,0.02099044917700143,0.7291883068704555,0.022327328786624415,0.7263692984063015,0.021949524566015448 +flat_mae,patch,logistic,adhd200_dx,67,0.005994842503189409,test,0.6307692307692307,0.050001079278292414,0.587737843551797,0.06059195203608342,0.5974903474903475,0.052492258396873916 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,train,0.6438356164383562,0.021896565047815737,0.6075398663402369,0.026240173928027955,0.6148714660804787,0.023147040376873842 +flat_mae,patch,logistic,adhd200_dx,68,0.000774263682681127,test,0.6,0.055500826796975995,0.5626293995859213,0.06287290598490769,0.5704633204633205,0.057278546928616766 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,train,0.726027397260274,0.022507102609068373,0.7146118721461188,0.02409019553709622,0.7120809672101117,0.023562809564342504 +flat_mae,patch,logistic,adhd200_dx,69,0.005994842503189409,test,0.5384615384615384,0.06201968765484661,0.5248538011695907,0.06389125406869214,0.525096525096525,0.06277544613539557 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,train,0.7178082191780822,0.021668358571488192,0.7043046696187697,0.023252368032174016,0.7019295353239299,0.022541967836899022 +flat_mae,patch,logistic,adhd200_dx,70,0.005994842503189409,test,0.5230769230769231,0.059702901518302626,0.49987589972697943,0.06307232048957923,0.502895752895753,0.06064467005329896 +flat_mae,patch,logistic,adhd200_dx,71,0.046415888336127774,train,0.8136986301369863,0.019613410648719066,0.8079779662065978,0.02044401638750004,0.8048177321853819,0.02041101371361693 +flat_mae,patch,logistic,adhd200_dx,71,0.046415888336127774,test,0.6307692307692307,0.06015033631310703,0.6198830409356726,0.06264771480013216,0.6192084942084942,0.061560993532757735 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,train,0.7123287671232876,0.02337057860761838,0.6999976516450226,0.024924549795723536,0.6977926360139219,0.024302786634013224 +flat_mae,patch,logistic,adhd200_dx,72,0.005994842503189409,test,0.676923076923077,0.05640491816233233,0.6655231560891939,0.059087302628923664,0.6640926640926641,0.0579890685002377 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,train,0.6438356164383562,0.02353566200473498,0.6191080143847932,0.02614284435609267,0.6213286926787568,0.02439370771951679 +flat_mae,patch,logistic,adhd200_dx,73,0.000774263682681127,test,0.5384615384615384,0.06154845303503506,0.5192307692307693,0.06423567664901118,0.5207528957528957,0.06259289302043254 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,train,0.7068493150684931,0.0216268662452901,0.6949805140540921,0.023065622704840544,0.6929382670818831,0.02252613809108944 +flat_mae,patch,logistic,adhd200_dx,74,0.005994842503189409,test,0.6,0.062124677085346525,0.5833333333333333,0.06516808929144341,0.5834942084942085,0.06292807098969126 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,train,0.7123287671232876,0.02283470904016013,0.6985630127181632,0.024408233475482877,0.6963576967698601,0.023665200545642185 +flat_mae,patch,logistic,adhd200_dx,75,0.005994842503189409,test,0.5846153846153846,0.06164129101013743,0.578226387887527,0.06228521048616152,0.5786679536679536,0.062212484607248576 +flat_mae,patch,logistic,adhd200_dx,76,0.046415888336127774,train,0.810958904109589,0.01935692656692871,0.8049624793810841,0.020219682565443455,0.8016730780973316,0.02020442925398418 +flat_mae,patch,logistic,adhd200_dx,76,0.046415888336127774,test,0.5692307692307692,0.05534572138602627,0.5289855072463768,0.06259214344891895,0.5390926640926641,0.056778197128026064 +flat_mae,patch,logistic,adhd200_dx,77,0.046415888336127774,train,0.8027397260273973,0.021078502708021866,0.7970719051149,0.021978910764909626,0.7943915246992733,0.021988303692770727 +flat_mae,patch,logistic,adhd200_dx,77,0.046415888336127774,test,0.6461538461538462,0.057723888792059974,0.6233308138070043,0.06365814124446458,0.6240347490347491,0.059759434999989876 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,train,0.8164383561643835,0.02083902037346591,0.8129279020845286,0.021264546223009856,0.8122672040056176,0.02133739544359467 +flat_mae,patch,logistic,adhd200_dx,78,0.046415888336127774,test,0.5384615384615384,0.05732230892585988,0.4953416149068323,0.06347023529195289,0.5077220077220077,0.058262611421206666 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,train,0.7452054794520548,0.02160909367037451,0.7348896056731828,0.02294152478078437,0.7319411369603712,0.022488874740297725 +flat_mae,patch,logistic,adhd200_dx,79,0.005994842503189409,test,0.5846153846153846,0.06028158775683672,0.578226387887527,0.061502393233488134,0.5786679536679536,0.06146533275186672 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,train,0.7205479452054795,0.02337177656814326,0.7095581351806777,0.024778998894355225,0.7072265982780729,0.024319316193558923 +flat_mae,patch,logistic,adhd200_dx,80,0.005994842503189409,test,0.6307692307692307,0.05737004558284327,0.5962732919254659,0.0660326957626276,0.6018339768339769,0.05995115329411317 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,train,0.726027397260274,0.021433425666125456,0.7158737078091917,0.022632552348080585,0.7135159064541735,0.022257239554012036 +flat_mae,patch,logistic,adhd200_dx,81,0.005994842503189409,test,0.6153846153846154,0.05375883909707398,0.5905769715293525,0.05932553151303257,0.5926640926640927,0.055475962667836304 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,train,0.726027397260274,0.023639664388640996,0.7125622125622125,0.025625268223786506,0.709928558344019,0.02479837960965627 +flat_mae,patch,logistic,adhd200_dx,82,0.005994842503189409,test,0.6461538461538462,0.05753911147308782,0.6407113674597452,0.05861394961698809,0.6414092664092663,0.05846701350575067 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,train,0.7095890410958904,0.02184259079763345,0.6974885844748858,0.022918231063713514,0.6953654515479025,0.022378782570640826 +flat_mae,patch,logistic,adhd200_dx,83,0.005994842503189409,test,0.6923076923076923,0.055316915888649766,0.6794871794871795,0.05912012559829709,0.6776061776061776,0.057697736597334986 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,train,0.736986301369863,0.021628154541441014,0.72473604826546,0.02322227655198136,0.7217897050741894,0.02260815631435253 +flat_mae,patch,logistic,adhd200_dx,84,0.005994842503189409,test,0.5384615384615384,0.06005598965541342,0.5248538011695907,0.062046321188969834,0.525096525096525,0.06107128363867923 +flat_mae,patch,logistic,adhd200_dx,85,0.000774263682681127,train,0.6520547945205479,0.022442018200174843,0.6213105245529331,0.025737684275734,0.6257403675886914,0.02339501708823261 +flat_mae,patch,logistic,adhd200_dx,85,0.000774263682681127,test,0.5692307692307692,0.05133372883374372,0.5075757575757576,0.0606713193611255,0.5304054054054055,0.0523757019905395 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,train,0.7205479452054795,0.023242760885295585,0.7075320512820513,0.02480343816101231,0.7050741894119802,0.02411714280974858 +flat_mae,patch,logistic,adhd200_dx,86,0.005994842503189409,test,0.5846153846153846,0.059197593106356944,0.5644080416976918,0.06206142806920466,0.5656370656370656,0.06013867509273076 +flat_mae,patch,logistic,adhd200_dx,87,0.046415888336127774,train,0.8054794520547945,0.020471375875831546,0.7993092179138691,0.021415316851288703,0.7961012395432618,0.02138962355764093 +flat_mae,patch,logistic,adhd200_dx,87,0.046415888336127774,test,0.5384615384615384,0.058826802247971065,0.5125,0.06288210226691654,0.5164092664092664,0.05993418363233873 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,train,0.673972602739726,0.023367151394821335,0.6566430304898776,0.025117198921404536,0.6559198876473102,0.024119937966148263 +flat_mae,patch,logistic,adhd200_dx,88,0.000774263682681127,test,0.5846153846153846,0.05884341672870205,0.5578231292517006,0.06332214302603559,0.5612934362934363,0.060180051915991066 +flat_mae,patch,logistic,adhd200_dx,89,0.000774263682681127,train,0.6684931506849315,0.022120172646383177,0.643856494286705,0.025060173029469723,0.6453257617390242,0.023235925443608224 +flat_mae,patch,logistic,adhd200_dx,89,0.000774263682681127,test,0.6,0.05467624777731111,0.5775,0.059315884444795006,0.5791505791505791,0.056414386895998335 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,train,0.7315068493150685,0.02234349022957149,0.7190013826043238,0.02396655427998583,0.7162178665201197,0.023371224977797665 +flat_mae,patch,logistic,adhd200_dx,90,0.005994842503189409,test,0.6153846153846154,0.05683455903402186,0.5966741126830479,0.0608367718682449,0.597007722007722,0.05840018402221312 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,train,0.7397260273972602,0.020991754361482696,0.7265917602996255,0.02262862417661963,0.7234994199181779,0.021967802947413427 +flat_mae,patch,logistic,adhd200_dx,91,0.005994842503189409,test,0.6,0.04796782945602077,0.5305555555555556,0.06224673759384742,0.5574324324324325,0.05012911746377066 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,train,0.7205479452054795,0.021503656337449956,0.7068134568134568,0.023449827718032164,0.7043567197899493,0.022662744834452474 +flat_mae,patch,logistic,adhd200_dx,92,0.005994842503189409,test,0.676923076923077,0.05246001351268868,0.6431372549019607,0.06099238258988072,0.6467181467181468,0.05510156094661427 +flat_mae,patch,logistic,adhd200_dx,93,0.046415888336127774,train,0.7945205479452054,0.02051586463740266,0.787132292905965,0.021593858101392593,0.7835226231910606,0.02142599579995832 +flat_mae,patch,logistic,adhd200_dx,93,0.046415888336127774,test,0.6307692307692307,0.05739763927273352,0.61,0.062188281106768356,0.6105212355212355,0.059267845366374465 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,train,0.726027397260274,0.022611621335129093,0.7164740243599304,0.02376840514509688,0.7142333760762044,0.023451741268318407 +flat_mae,patch,logistic,adhd200_dx,94,0.005994842503189409,test,0.6307692307692307,0.0542405861272899,0.5962732919254659,0.06266454691255315,0.6018339768339769,0.05653135811205398 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,train,0.736986301369863,0.024189418895232316,0.7299297077321495,0.025047663741949916,0.7282469316724675,0.024951165367686816 +flat_mae,patch,logistic,adhd200_dx,95,0.005994842503189409,test,0.5076923076923077,0.057187833356612386,0.4871794871794872,0.06040503368322291,0.48938223938223935,0.0584414662764882 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,train,0.7123287671232876,0.02365532443613954,0.7013442431326709,0.02480819554580474,0.6992275752579837,0.024352093638282887 +flat_mae,patch,logistic,adhd200_dx,96,0.005994842503189409,test,0.6307692307692307,0.062405363143823035,0.6235521235521235,0.06383676576034304,0.6235521235521235,0.0636443540518627 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,train,0.7506849315068493,0.021887976273472505,0.7387546110224081,0.023659163318276992,0.7353605666483483,0.023073316136309394 +flat_mae,patch,logistic,adhd200_dx,97,0.005994842503189409,test,0.5538461538461539,0.05436570446968573,0.49612403100775193,0.06318092117048242,0.5168918918918919,0.055503590868231666 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,train,0.7205479452054795,0.022868380732035017,0.7068134568134568,0.024343254934494813,0.7043567197899493,0.023574522157863778 +flat_mae,patch,logistic,adhd200_dx,98,0.005994842503189409,test,0.6615384615384615,0.05937166060369406,0.6474358974358974,0.06279103927584444,0.6462355212355213,0.06088127785772765 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,train,0.6876712328767123,0.02416532225679635,0.6739028213166145,0.025897957267439816,0.6723606277095927,0.025146015454312547 +flat_mae,patch,logistic,adhd200_dx,99,0.000774263682681127,test,0.6,0.058676939211808526,0.5833333333333333,0.06208702898191553,0.5834942084942085,0.06036178569316929 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,train,0.7095890410958904,0.022364013529433395,0.6967868338557994,0.023910558349833487,0.6946479819258716,0.023300548552307173 +flat_mae,patch,logistic,adhd200_dx,100,0.005994842503189409,test,0.7076923076923077,0.050062739335982064,0.6834145091002307,0.05787824077199924,0.6824324324324325,0.05342210441200439 diff --git a/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e34499aae0799aed6cd844d406376d55351fae69 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:49:47 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adhd200_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:14:45 time: 5.8647 data: 4.7082 max mem: 2708 +extract (train) [ 20/151] eta: 0:01:04 time: 0.2249 data: 0.0862 max mem: 2863 +extract (train) [ 40/151] eta: 0:00:37 time: 0.1782 data: 0.0588 max mem: 2863 +extract (train) [ 60/151] eta: 0:00:26 time: 0.1933 data: 0.0718 max mem: 2863 +extract (train) [ 80/151] eta: 0:00:19 time: 0.2023 data: 0.0725 max mem: 2863 +extract (train) [100/151] eta: 0:00:12 time: 0.1948 data: 0.0687 max mem: 2863 +extract (train) [120/151] eta: 0:00:07 time: 0.1939 data: 0.0702 max mem: 2863 +extract (train) [140/151] eta: 0:00:02 time: 0.1758 data: 0.0582 max mem: 2863 +extract (train) [150/151] eta: 0:00:00 time: 0.1700 data: 0.0563 max mem: 2863 +extract (train) Total time: 0:00:35 (0.2331 s / it) +extract (validation) [ 0/32] eta: 0:02:19 time: 4.3445 data: 4.1739 max mem: 2863 +extract (validation) [20/32] eta: 0:00:04 time: 0.1936 data: 0.0667 max mem: 2863 +extract (validation) [31/32] eta: 0:00:00 time: 0.1602 data: 0.0500 max mem: 2863 +extract (validation) Total time: 0:00:10 (0.3258 s / it) +extract (test) [ 0/33] eta: 0:02:15 time: 4.1159 data: 3.9701 max mem: 2863 +extract (test) [20/33] eta: 0:00:04 time: 0.1818 data: 0.0608 max mem: 2863 +extract (test) [32/33] eta: 0:00:00 time: 0.1535 data: 0.0479 max mem: 2863 +extract (test) Total time: 0:00:09 (0.2975 s / it) +feature extraction time: 0:00:55 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | train | 0.72603 | 0.022387 | 0.71327 | 0.02416 | 0.71065 | 0.02348 | +| flat_mae | patch | logistic | adhd200_dx | | 0.0059948 | test | 0.53846 | 0.054397 | 0.48467 | 0.060879 | 0.50338 | 0.054965 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05966276033183682, "f1": 0.5833333333333333, "f1_std": 0.06227910300215068, "bacc": 0.5834942084942085, "bacc_std": 0.060596175261615065} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05681656563166692, "f1": 0.6233308138070043, "f1_std": 0.06176332542582999, "bacc": 0.6240347490347491, "bacc_std": 0.05864676332085262} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05963121377940192, "f1": 0.5321419707123356, "f1_std": 0.0630691929586715, "bacc": 0.5342664092664092, "bacc_std": 0.06083832755968385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.676923076923077, "acc_std": 0.058432535315797764, "f1": 0.6690909090909091, "f1_std": 0.06036603406707303, "bacc": 0.6684362934362934, "bacc_std": 0.05997536414767835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.0603332441944703, "f1": 0.4879446168536643, "f1_std": 0.06069833937518913, "bacc": 0.4888996138996139, "bacc_std": 0.06127899701475652} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.061920384079049776, "f1": 0.606060606060606, "f1_std": 0.06363418828170457, "bacc": 0.6056949806949807, "bacc_std": 0.0630879043696591} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05437486366710788, "f1": 0.6612062546537603, "f1_std": 0.05842661669751474, "bacc": 0.6597490347490347, "bacc_std": 0.056381689654824214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06168103484193175, "f1": 0.606060606060606, "f1_std": 0.06339601300051742, "bacc": 0.6056949806949807, "bacc_std": 0.06277419019784093} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05690281552086139, "f1": 0.6167649320687003, "f1_std": 0.06408292307195822, "bacc": 0.6196911196911197, "bacc_std": 0.05922099497387309} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06004131910609559, "f1": 0.5250692869740489, "f1_std": 0.06456839396869556, "bacc": 0.5299227799227799, "bacc_std": 0.06114573529641867} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05570335632011273, "f1": 0.5250692869740489, "f1_std": 0.061145063414686236, "bacc": 0.5299227799227799, "bacc_std": 0.05730203505106971} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05584806947339654, "f1": 0.5512820512820513, "f1_std": 0.05903187238348149, "bacc": 0.5521235521235521, "bacc_std": 0.05703249183708538} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.059052046044246714, "f1": 0.6235521235521235, "f1_std": 0.059983020688376305, "bacc": 0.6235521235521235, "bacc_std": 0.05979902316293084} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05496162405117952, "f1": 0.5775, "f1_std": 0.05941689039774497, "bacc": 0.5791505791505791, "bacc_std": 0.05682717516998861} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06083521247536723, "f1": 0.5565302144249512, "f1_std": 0.06271443349568895, "bacc": 0.5564671814671815, "bacc_std": 0.06182479384442199} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06267365272235319, "f1": 0.5608108108108107, "f1_std": 0.06379927375746387, "bacc": 0.5608108108108107, "bacc_std": 0.06380539726634211} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.058811672149881006, "f1": 0.5376016260162602, "f1_std": 0.06502272198205132, "bacc": 0.5434362934362934, "bacc_std": 0.06052230805642295} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.054128455586151834, "f1": 0.5578231292517006, "f1_std": 0.05821589786851953, "bacc": 0.5612934362934363, "bacc_std": 0.05508076696427302} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.058055138043539595, "f1": 0.6612062546537603, "f1_std": 0.06227047626890958, "bacc": 0.6597490347490347, "bacc_std": 0.060416444196321514} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.056797458064631295, "f1": 0.5775, "f1_std": 0.06170274408446519, "bacc": 0.5791505791505791, "bacc_std": 0.058614270578808324} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 21.54434690031882, "split": "test", "acc": 0.49230769230769234, "acc_std": 0.06120416120749002, "f1": 0.49037776193870275, "f1_std": 0.06255880457504902, "bacc": 0.5106177606177607, "bacc_std": 0.06183605330165441} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05997455081584297, "f1": 0.6018132810585641, "f1_std": 0.06279940288273309, "bacc": 0.6013513513513513, "bacc_std": 0.06157381163049622} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.054612489630748745, "f1": 0.5190274841437632, "f1_std": 0.06199072249172965, "bacc": 0.5347490347490347, "bacc_std": 0.055387273680126796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05783796996118354, "f1": 0.5905769715293525, "f1_std": 0.06272039053112337, "bacc": 0.5926640926640927, "bacc_std": 0.05936791280094268} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 166.81005372000556, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05990505308081601, "f1": 0.5500119360229172, "f1_std": 0.06055104181643479, "bacc": 0.5516409266409266, "bacc_std": 0.0612559660723685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.05824738102652947, "f1": 0.5833333333333333, "f1_std": 0.06134778598467154, "bacc": 0.5834942084942085, "bacc_std": 0.059600869575884854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.000774263682681127, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05882583661329806, "f1": 0.6375757575757576, "f1_std": 0.06056792533760488, "bacc": 0.6370656370656371, "bacc_std": 0.05997429312540856} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05918108605581316, "f1": 0.5578231292517006, "f1_std": 0.06390614488491919, "bacc": 0.5612934362934363, "bacc_std": 0.0606023374727288} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06585744691080476, "f1": 0.5189782764382908, "f1_std": 0.06589057858559953, "bacc": 0.5202702702702703, "bacc_std": 0.06624991107618636} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.056186805922416636, "f1": 0.5250692869740489, "f1_std": 0.06069505840618855, "bacc": 0.5299227799227799, "bacc_std": 0.05716336915320982} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06104183452461253, "f1": 0.588206627680312, "f1_std": 0.06298819262268386, "bacc": 0.5878378378378378, "bacc_std": 0.06235392273072612} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06107594651418471, "f1": 0.5953065134099617, "f1_std": 0.06154312884361415, "bacc": 0.5965250965250966, "bacc_std": 0.0617195033910934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05969271213185748, "f1": 0.6139225469232596, "f1_std": 0.0597297369949006, "bacc": 0.6187258687258688, "bacc_std": 0.05993129270567676} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.06247075339377458, "f1": 0.5047619047619047, "f1_std": 0.06301043820856556, "bacc": 0.5067567567567568, "bacc_std": 0.06363655726337746} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05724872340376636, "f1": 0.5644080416976918, "f1_std": 0.061053989476235394, "bacc": 0.5656370656370656, "bacc_std": 0.058599988328509836} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.000774263682681127, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05547803232817398, "f1": 0.5250692869740489, "f1_std": 0.059655434101498435, "bacc": 0.5299227799227799, "bacc_std": 0.05639575341616171} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05746209658878362, "f1": 0.6233308138070043, "f1_std": 0.06414993123468181, "bacc": 0.6240347490347491, "bacc_std": 0.059885046219525104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.059476365949079936, "f1": 0.5294401544401545, "f1_std": 0.06054230473419438, "bacc": 0.5294401544401545, "bacc_std": 0.05992099942966141} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05650159132701669, "f1": 0.6167649320687003, "f1_std": 0.0633843477503081, "bacc": 0.6196911196911197, "bacc_std": 0.05839305718936094} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.04981266681425448, "f1": 0.622093023255814, "f1_std": 0.059939099101357064, "bacc": 0.6288610038610039, "bacc_std": 0.05263209109907507} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.06014341046602867, "f1": 0.5833333333333333, "f1_std": 0.0628568050445923, "bacc": 0.5834942084942085, "bacc_std": 0.0609801788619855} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.061793195849174504, "f1": 0.564176245210728, "f1_std": 0.06219704813314564, "bacc": 0.5651544401544402, "bacc_std": 0.062308234115824535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058459748960466046, "f1": 0.5966741126830479, "f1_std": 0.061267749343580626, "bacc": 0.597007722007722, "bacc_std": 0.05920227895012655} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 10000.0, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.05975396498443385, "f1": 0.4980694980694981, "f1_std": 0.060589848290144445, "bacc": 0.4980694980694981, "bacc_std": 0.06041639786254466} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.057695351714565836, "f1": 0.48, "f1_std": 0.06114988047802967, "bacc": 0.48503861003861004, "bacc_std": 0.05824168080027079} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.0582335635951818, "f1": 0.6366869918699187, "f1_std": 0.06513227208978496, "bacc": 0.6375482625482626, "bacc_std": 0.060590565572679445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.056511912133794855, "f1": 0.4834657780056396, "f1_std": 0.06128402688794509, "bacc": 0.4942084942084942, "bacc_std": 0.05708780847701859} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05731619761355197, "f1": 0.6375757575757576, "f1_std": 0.05861724956477301, "bacc": 0.6370656370656371, "bacc_std": 0.05811930503084732} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.0620793079324567, "f1": 0.5644080416976918, "f1_std": 0.0659624804294108, "bacc": 0.5656370656370656, "bacc_std": 0.06339227654927523} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.0565501631009634, "f1": 0.570630081300813, "f1_std": 0.06266719069329077, "bacc": 0.5748069498069498, "bacc_std": 0.05821804429397302} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06053235234544725, "f1": 0.6018132810585641, "f1_std": 0.06384403565351428, "bacc": 0.6013513513513513, "bacc_std": 0.062348825084963796} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.676923076923077, "acc_std": 0.054313889382750495, "f1": 0.6500897205844656, "f1_std": 0.061939995603703155, "bacc": 0.6510617760617761, "bacc_std": 0.05717900683841391} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05200545260443097, "f1": 0.587737843551797, "f1_std": 0.061668857110856505, "bacc": 0.5974903474903475, "bacc_std": 0.05443315612621023} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06102273123853644, "f1": 0.5062484685126194, "f1_std": 0.06268275275637886, "bacc": 0.5072393822393823, "bacc_std": 0.0612732741213254} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.060000441812969006, "f1": 0.5830363506771205, "f1_std": 0.06022342894983551, "bacc": 0.5873552123552124, "bacc_std": 0.060255689715603744} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06299605322473377, "f1": 0.5192307692307693, "f1_std": 0.06580462782417368, "bacc": 0.5207528957528957, "bacc_std": 0.06413751177681697} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.056209885630585925, "f1": 0.5045731707317074, "f1_std": 0.06140760600336114, "bacc": 0.5120656370656371, "bacc_std": 0.05746641141432253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.058624961866479315, "f1": 0.6094688776736361, "f1_std": 0.05968040897926644, "bacc": 0.61003861003861, "bacc_std": 0.05941821416926358} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.056258776567113526, "f1": 0.4953416149068323, "f1_std": 0.06171977354825464, "bacc": 0.5077220077220077, "bacc_std": 0.05695082077332002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05653736262668312, "f1": 0.6515594541910331, "f1_std": 0.05878873611178601, "bacc": 0.6505791505791505, "bacc_std": 0.058035022760551475} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06055349437046035, "f1": 0.5833333333333333, "f1_std": 0.06448878533999411, "bacc": 0.5834942084942085, "bacc_std": 0.06231867425256164} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.056884344410859246, "f1": 0.5381034060279344, "f1_std": 0.059224134248217, "bacc": 0.5386100386100386, "bacc_std": 0.05802949941438239} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05737988019234245, "f1": 0.543030303030303, "f1_std": 0.05852571859395937, "bacc": 0.542953667953668, "bacc_std": 0.05817786493802208} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.056803066839448586, "f1": 0.5966741126830479, "f1_std": 0.06027175112431256, "bacc": 0.597007722007722, "bacc_std": 0.05821836379278418} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.053382407402798385, "f1": 0.6500897205844656, "f1_std": 0.06119146903301269, "bacc": 0.6510617760617761, "bacc_std": 0.05603366381525318} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.058557160664505906, "f1": 0.5833333333333333, "f1_std": 0.06110511986712878, "bacc": 0.5834942084942085, "bacc_std": 0.059499485686344555} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.050001079278292414, "f1": 0.587737843551797, "f1_std": 0.06059195203608342, "bacc": 0.5974903474903475, "bacc_std": 0.052492258396873916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.055500826796975995, "f1": 0.5626293995859213, "f1_std": 0.06287290598490769, "bacc": 0.5704633204633205, "bacc_std": 0.057278546928616766} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06201968765484661, "f1": 0.5248538011695907, "f1_std": 0.06389125406869214, "bacc": 0.525096525096525, "bacc_std": 0.06277544613539557} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.059702901518302626, "f1": 0.49987589972697943, "f1_std": 0.06307232048957923, "bacc": 0.502895752895753, "bacc_std": 0.06064467005329896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06015033631310703, "f1": 0.6198830409356726, "f1_std": 0.06264771480013216, "bacc": 0.6192084942084942, "bacc_std": 0.061560993532757735} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05640491816233233, "f1": 0.6655231560891939, "f1_std": 0.059087302628923664, "bacc": 0.6640926640926641, "bacc_std": 0.0579890685002377} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06154845303503506, "f1": 0.5192307692307693, "f1_std": 0.06423567664901118, "bacc": 0.5207528957528957, "bacc_std": 0.06259289302043254} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.062124677085346525, "f1": 0.5833333333333333, "f1_std": 0.06516808929144341, "bacc": 0.5834942084942085, "bacc_std": 0.06292807098969126} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06164129101013743, "f1": 0.578226387887527, "f1_std": 0.06228521048616152, "bacc": 0.5786679536679536, "bacc_std": 0.062212484607248576} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05534572138602627, "f1": 0.5289855072463768, "f1_std": 0.06259214344891895, "bacc": 0.5390926640926641, "bacc_std": 0.056778197128026064} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.057723888792059974, "f1": 0.6233308138070043, "f1_std": 0.06365814124446458, "bacc": 0.6240347490347491, "bacc_std": 0.059759434999989876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05732230892585988, "f1": 0.4953416149068323, "f1_std": 0.06347023529195289, "bacc": 0.5077220077220077, "bacc_std": 0.058262611421206666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06028158775683672, "f1": 0.578226387887527, "f1_std": 0.061502393233488134, "bacc": 0.5786679536679536, "bacc_std": 0.06146533275186672} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05737004558284327, "f1": 0.5962732919254659, "f1_std": 0.0660326957626276, "bacc": 0.6018339768339769, "bacc_std": 0.05995115329411317} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05375883909707398, "f1": 0.5905769715293525, "f1_std": 0.05932553151303257, "bacc": 0.5926640926640927, "bacc_std": 0.055475962667836304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05753911147308782, "f1": 0.6407113674597452, "f1_std": 0.05861394961698809, "bacc": 0.6414092664092663, "bacc_std": 0.05846701350575067} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.055316915888649766, "f1": 0.6794871794871795, "f1_std": 0.05912012559829709, "bacc": 0.6776061776061776, "bacc_std": 0.057697736597334986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06005598965541342, "f1": 0.5248538011695907, "f1_std": 0.062046321188969834, "bacc": 0.525096525096525, "bacc_std": 0.06107128363867923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05133372883374372, "f1": 0.5075757575757576, "f1_std": 0.0606713193611255, "bacc": 0.5304054054054055, "bacc_std": 0.0523757019905395} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059197593106356944, "f1": 0.5644080416976918, "f1_std": 0.06206142806920466, "bacc": 0.5656370656370656, "bacc_std": 0.06013867509273076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.058826802247971065, "f1": 0.5125, "f1_std": 0.06288210226691654, "bacc": 0.5164092664092664, "bacc_std": 0.05993418363233873} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05884341672870205, "f1": 0.5578231292517006, "f1_std": 0.06332214302603559, "bacc": 0.5612934362934363, "bacc_std": 0.060180051915991066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05467624777731111, "f1": 0.5775, "f1_std": 0.059315884444795006, "bacc": 0.5791505791505791, "bacc_std": 0.056414386895998335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05683455903402186, "f1": 0.5966741126830479, "f1_std": 0.0608367718682449, "bacc": 0.597007722007722, "bacc_std": 0.05840018402221312} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04796782945602077, "f1": 0.5305555555555556, "f1_std": 0.06224673759384742, "bacc": 0.5574324324324325, "bacc_std": 0.05012911746377066} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05246001351268868, "f1": 0.6431372549019607, "f1_std": 0.06099238258988072, "bacc": 0.6467181467181468, "bacc_std": 0.05510156094661427} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05739763927273352, "f1": 0.61, "f1_std": 0.062188281106768356, "bacc": 0.6105212355212355, "bacc_std": 0.059267845366374465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.0542405861272899, "f1": 0.5962732919254659, "f1_std": 0.06266454691255315, "bacc": 0.6018339768339769, "bacc_std": 0.05653135811205398} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.057187833356612386, "f1": 0.4871794871794872, "f1_std": 0.06040503368322291, "bacc": 0.48938223938223935, "bacc_std": 0.0584414662764882} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.062405363143823035, "f1": 0.6235521235521235, "f1_std": 0.06383676576034304, "bacc": 0.6235521235521235, "bacc_std": 0.0636443540518627} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.05436570446968573, "f1": 0.49612403100775193, "f1_std": 0.06318092117048242, "bacc": 0.5168918918918919, "bacc_std": 0.055503590868231666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05937166060369406, "f1": 0.6474358974358974, "f1_std": 0.06279103927584444, "bacc": 0.6462355212355213, "bacc_std": 0.06088127785772765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.058676939211808526, "f1": 0.5833333333333333, "f1_std": 0.06208702898191553, "bacc": 0.5834942084942085, "bacc_std": 0.06036178569316929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.050062739335982064, "f1": 0.6834145091002307, "f1_std": 0.05787824077199924, "bacc": 0.6824324324324325, "bacc_std": 0.05342210441200439} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adhd200_dx | train | 100 | 101.9 | 999.95 | 0.74773 | 0.069571 | 0.73632 | 0.074719 | 0.73441 | 0.074218 | +| flat_mae | patch | logistic | adhd200_dx | test | 100 | 101.9 | 999.95 | 0.59523 | 0.049801 | 0.57433 | 0.051687 | 0.57735 | 0.049335 | + + +done! total time: 0:05:02 diff --git a/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0bee9531f4fce221166fa3bd7a6a984ad58bb8c4 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adhd200_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic +model: flat_mae +representation: reg +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..1329cd379787ad49d553d0293595eb861bb95922 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,adhd200_dx,,0.005994842503189409,train,0.7589041095890411,0.020938060366881905,0.7488584474885844,0.022350586356384324,0.7455119985345301,0.02196556397649647 +flat_mae,reg,logistic,adhd200_dx,,0.005994842503189409,test,0.6153846153846154,0.057625397096528065,0.5905769715293525,0.06236951780092626,0.5926640926640927,0.05913561500931882 +flat_mae,reg,logistic,adhd200_dx,1,0.046415888336127774,train,0.8575342465753425,0.018098204615952535,0.8534408203607611,0.018823107081985424,0.8501099102399707,0.01898932868095773 +flat_mae,reg,logistic,adhd200_dx,1,0.046415888336127774,test,0.6,0.060707279034813044,0.5921814671814671,0.06123178981076584,0.5921814671814671,0.06085749253149747 +flat_mae,reg,logistic,adhd200_dx,2,0.005994842503189409,train,0.7726027397260274,0.022133595291613444,0.7653896491105794,0.02307745799396973,0.7626702082188435,0.022918846070330706 +flat_mae,reg,logistic,adhd200_dx,2,0.005994842503189409,test,0.676923076923077,0.055213273423427606,0.656084656084656,0.060952774269968264,0.6554054054054055,0.05784034389207626 +flat_mae,reg,logistic,adhd200_dx,3,0.005994842503189409,train,0.7863013698630137,0.021600903492985362,0.7778973974911065,0.022968181759305196,0.7740886609269096,0.022723117958914813 +flat_mae,reg,logistic,adhd200_dx,3,0.005994842503189409,test,0.5846153846153846,0.05886734460084835,0.5644080416976918,0.0626293427190368,0.5656370656370656,0.06028953488532466 +flat_mae,reg,logistic,adhd200_dx,4,0.005994842503189409,train,0.7534246575342466,0.022492559350176747,0.7458531905675558,0.023639803887694984,0.7435275080906149,0.02355458891427222 +flat_mae,reg,logistic,adhd200_dx,4,0.005994842503189409,test,0.676923076923077,0.0560866531602831,0.6655231560891939,0.0593130143297974,0.6640926640926641,0.05816887972455575 +flat_mae,reg,logistic,adhd200_dx,5,0.005994842503189409,train,0.7808219178082192,0.02129027398979004,0.7736434108527132,0.022548882696024376,0.7706692312389326,0.02250651938015083 +flat_mae,reg,logistic,adhd200_dx,5,0.005994842503189409,test,0.5230769230769231,0.06450448358344452,0.5189782764382908,0.06489703697005733,0.5202702702702703,0.06525232855375976 +flat_mae,reg,logistic,adhd200_dx,6,0.046415888336127774,train,0.8328767123287671,0.01856392423943746,0.8275755252499439,0.01940078107522706,0.8239604323136106,0.01942513274907353 +flat_mae,reg,logistic,adhd200_dx,6,0.046415888336127774,test,0.6307692307692307,0.06089829332729707,0.6299810246679317,0.06106890728140279,0.6365830115830116,0.061548893037202845 +flat_mae,reg,logistic,adhd200_dx,7,0.046415888336127774,train,0.8273972602739726,0.018889300532593082,0.8222691121571173,0.019667390578155215,0.8191060633815718,0.01972306994326931 +flat_mae,reg,logistic,adhd200_dx,7,0.046415888336127774,test,0.6153846153846154,0.0589396722964609,0.6018132810585641,0.06133216354183448,0.6013513513513513,0.06013710169723944 +flat_mae,reg,logistic,adhd200_dx,8,0.000774263682681127,train,0.7123287671232876,0.022876039691530403,0.6962407564457196,0.025405895467853025,0.6942052879037675,0.024295338387742987 +flat_mae,reg,logistic,adhd200_dx,8,0.000774263682681127,test,0.6307692307692307,0.06134445572764266,0.6153846153846154,0.06530247790735864,0.6148648648648649,0.06338919463900186 +flat_mae,reg,logistic,adhd200_dx,9,0.005994842503189409,train,0.7726027397260274,0.022433207966449615,0.7662873674059788,0.023264136343170896,0.7641051474629053,0.023206189265881454 +flat_mae,reg,logistic,adhd200_dx,9,0.005994842503189409,test,0.6307692307692307,0.05790552599561119,0.6036585365853658,0.06413793908689208,0.6061776061776062,0.05988444137205735 +flat_mae,reg,logistic,adhd200_dx,10,0.046415888336127774,train,0.8328767123287671,0.019678251886227204,0.8282352941176471,0.020386828252681306,0.8253953715576724,0.020423994002186745 +flat_mae,reg,logistic,adhd200_dx,10,0.046415888336127774,test,0.6,0.0590654155458968,0.5775,0.06345542029917184,0.5791505791505791,0.060373004779775925 +flat_mae,reg,logistic,adhd200_dx,11,0.005994842503189409,train,0.7479452054794521,0.021295338969190485,0.7391561024111359,0.022218679896679198,0.7365207302924833,0.02194481821704597 +flat_mae,reg,logistic,adhd200_dx,11,0.005994842503189409,test,0.6307692307692307,0.0561730125351855,0.61,0.061335954884655264,0.6105212355212355,0.05829987274529371 +flat_mae,reg,logistic,adhd200_dx,12,0.005994842503189409,train,0.7698630136986301,0.022204272486275562,0.7618381804623415,0.023256762066444694,0.7588080845087622,0.023014700682353756 +flat_mae,reg,logistic,adhd200_dx,12,0.005994842503189409,test,0.5846153846153846,0.05734479955063893,0.5644080416976918,0.06176937411803161,0.5656370656370656,0.059138752155352 +flat_mae,reg,logistic,adhd200_dx,13,0.000774263682681127,train,0.6904109589041096,0.023547415901675126,0.6713048190562714,0.025840355622716638,0.6704829944434267,0.024519727095481496 +flat_mae,reg,logistic,adhd200_dx,13,0.000774263682681127,test,0.5846153846153846,0.059545664442057854,0.5745454545454545,0.060956741688393275,0.5743243243243243,0.06060527251906438 +flat_mae,reg,logistic,adhd200_dx,14,0.005994842503189409,train,0.7479452054794521,0.0218168661868702,0.7391561024111359,0.022842663060280877,0.7365207302924833,0.022598885531726533 +flat_mae,reg,logistic,adhd200_dx,14,0.005994842503189409,test,0.6307692307692307,0.054559529401569364,0.6036585365853658,0.06054526560325099,0.6061776061776062,0.05647509907201201 +flat_mae,reg,logistic,adhd200_dx,15,0.000774263682681127,train,0.6767123287671233,0.022877858063344192,0.6532206119162641,0.025364565580817403,0.6540422543811443,0.02369878237374669 +flat_mae,reg,logistic,adhd200_dx,15,0.000774263682681127,test,0.6461538461538462,0.05716630778318756,0.6336682185738789,0.06000045729795002,0.6327220077220077,0.05861835555189784 +flat_mae,reg,logistic,adhd200_dx,16,0.005994842503189409,train,0.7534246575342466,0.021230010235144727,0.7458531905675558,0.022262155775159897,0.7435275080906149,0.022120859231629368 +flat_mae,reg,logistic,adhd200_dx,16,0.005994842503189409,test,0.6461538461538462,0.05891717986156701,0.6336682185738789,0.06163303731621899,0.6327220077220077,0.06040816705824471 +flat_mae,reg,logistic,adhd200_dx,17,0.005994842503189409,train,0.7616438356164383,0.021122670068969965,0.7530734597709193,0.022341276566993442,0.7500915918666422,0.022119201452930712 +flat_mae,reg,logistic,adhd200_dx,17,0.005994842503189409,test,0.6307692307692307,0.05334936544045682,0.587737843551797,0.06408668858733474,0.5974903474903475,0.05599402392979974 +flat_mae,reg,logistic,adhd200_dx,18,0.005994842503189409,train,0.7534246575342466,0.022440246796759905,0.7442863370282725,0.023802511384914807,0.7413750992245222,0.02343998098907877 +flat_mae,reg,logistic,adhd200_dx,18,0.005994842503189409,test,0.6153846153846154,0.05623197094369908,0.6018132810585641,0.058608789151448376,0.6013513513513513,0.05732587756612467 +flat_mae,reg,logistic,adhd200_dx,19,0.000774263682681127,train,0.684931506849315,0.02341414424012287,0.6604541299617379,0.026631958114472533,0.6613238077792025,0.02465683081592631 +flat_mae,reg,logistic,adhd200_dx,19,0.000774263682681127,test,0.6461538461538462,0.05043198947226034,0.6003742314889067,0.06178411872825358,0.6110038610038611,0.05322954317652886 +flat_mae,reg,logistic,adhd200_dx,20,0.3593813663804626,train,0.958904109589041,0.010344559708193948,0.9580527271473556,0.010603097450155086,0.9564175367893998,0.011021099442961028 +flat_mae,reg,logistic,adhd200_dx,20,0.3593813663804626,test,0.5538461538461539,0.058381516082732406,0.5469838981014179,0.059205055762357,0.5472972972972974,0.059271356364151095 +flat_mae,reg,logistic,adhd200_dx,21,0.005994842503189409,train,0.7287671232876712,0.022285612554474,0.7190146266358737,0.023382979628968938,0.7166605605422238,0.0230238448170537 +flat_mae,reg,logistic,adhd200_dx,21,0.005994842503189409,test,0.7076923076923077,0.052997612986327235,0.6973780936045086,0.05553344105515485,0.6954633204633205,0.05447271250305293 +flat_mae,reg,logistic,adhd200_dx,22,0.005994842503189409,train,0.7315068493150685,0.02314006467919013,0.7221445438727319,0.024306351757921753,0.7198052146302741,0.02397583676938377 +flat_mae,reg,logistic,adhd200_dx,22,0.005994842503189409,test,0.6153846153846154,0.06438501791988863,0.6094688776736361,0.06535029972812952,0.61003861003861,0.06544929321066625 +flat_mae,reg,logistic,adhd200_dx,23,0.005994842503189409,train,0.7808219178082192,0.020383929883255023,0.7736434108527132,0.021399789617614923,0.7706692312389326,0.021267633178049597 +flat_mae,reg,logistic,adhd200_dx,23,0.005994842503189409,test,0.6461538461538462,0.05164488667357716,0.6091503267973856,0.06099975572352973,0.6153474903474904,0.054222100983927976 +flat_mae,reg,logistic,adhd200_dx,24,0.005994842503189409,train,0.7698630136986301,0.02058758623720853,0.7608125819134994,0.021803463421068474,0.7573731452647005,0.021511598624807674 +flat_mae,reg,logistic,adhd200_dx,24,0.005994842503189409,test,0.6153846153846154,0.054949358073254344,0.5834401435529352,0.06182825048128351,0.5883204633204633,0.05667430478441108 +flat_mae,reg,logistic,adhd200_dx,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adhd200_dx,25,2.782559402207126,test,0.5384615384615384,0.05902314058282865,0.5330459770114943,0.0595026500791029,0.5337837837837838,0.059702133922600466 +flat_mae,reg,logistic,adhd200_dx,26,0.005994842503189409,train,0.7808219178082192,0.020058221879450937,0.771689497716895,0.021331804983922092,0.767799352750809,0.020977022810334558 +flat_mae,reg,logistic,adhd200_dx,26,0.005994842503189409,test,0.6615384615384615,0.057911738598108255,0.6575670498084292,0.058370914593579855,0.6592664092664093,0.05848710989299784 +flat_mae,reg,logistic,adhd200_dx,27,0.005994842503189409,train,0.7671232876712328,0.021270933636112998,0.7587499319600937,0.02247637113128748,0.7556634304207119,0.022286447592768644 +flat_mae,reg,logistic,adhd200_dx,27,0.005994842503189409,test,0.6923076923076923,0.053752921483835064,0.6832358674463938,0.055758138121379565,0.6819498069498069,0.05509214172226039 +flat_mae,reg,logistic,adhd200_dx,28,0.005994842503189409,train,0.7780821917808219,0.02063960269662604,0.7705809775818855,0.021629648635481804,0.7675245771508823,0.021504253625784914 +flat_mae,reg,logistic,adhd200_dx,28,0.005994842503189409,test,0.6461538461538462,0.05654925904222664,0.6336682185738789,0.05880081453388411,0.6327220077220077,0.0578733908913043 +flat_mae,reg,logistic,adhd200_dx,29,0.000774263682681127,train,0.7068493150684931,0.022696062387315332,0.6896184504367038,0.024819852967544076,0.6879159797276668,0.02367609744806281 +flat_mae,reg,logistic,adhd200_dx,29,0.000774263682681127,test,0.6,0.05916559851245721,0.5775,0.0634187424678971,0.5791505791505791,0.060535804985222805 +flat_mae,reg,logistic,adhd200_dx,30,0.005994842503189409,train,0.7561643835616438,0.021279056101263173,0.74891985685688,0.022227805330604207,0.7466721621786652,0.02214248429589805 +flat_mae,reg,logistic,adhd200_dx,30,0.005994842503189409,test,0.5846153846153846,0.06244392324554774,0.5699583435432491,0.06475744472659399,0.5699806949806949,0.06359021401165693 +flat_mae,reg,logistic,adhd200_dx,31,0.005994842503189409,train,0.7506849315068493,0.022714030704446966,0.7417205153925708,0.023824681872129338,0.7389479147585027,0.023489675348941762 +flat_mae,reg,logistic,adhd200_dx,31,0.005994842503189409,test,0.6153846153846154,0.055448988231147994,0.5966741126830479,0.05964586888506354,0.597007722007722,0.05753488524920535 +flat_mae,reg,logistic,adhd200_dx,32,0.005994842503189409,train,0.7616438356164383,0.022489540363988078,0.7540831261761494,0.023454976907237753,0.751526531110704,0.023210313635392263 +flat_mae,reg,logistic,adhd200_dx,32,0.005994842503189409,test,0.6153846153846154,0.06201281791532149,0.61207925519217,0.06230888006666315,0.6143822393822393,0.062450854390049756 +flat_mae,reg,logistic,adhd200_dx,33,0.046415888336127774,train,0.8438356164383561,0.018405454982916524,0.8385569842242898,0.019354107650236468,0.8343866397997192,0.019460571759645672 +flat_mae,reg,logistic,adhd200_dx,33,0.046415888336127774,test,0.5846153846153846,0.05916179800509165,0.5842217484008528,0.05937099424917247,0.5916988416988418,0.059552763776855346 +flat_mae,reg,logistic,adhd200_dx,34,0.046415888336127774,train,0.821917808219178,0.01921678990034327,0.8169720347155256,0.020005689647354535,0.8142516944495328,0.0201217447476333 +flat_mae,reg,logistic,adhd200_dx,34,0.046415888336127774,test,0.6153846153846154,0.05986508697941777,0.6150201374081972,0.06013819799960458,0.6230694980694981,0.060110676341275454 +flat_mae,reg,logistic,adhd200_dx,35,0.005994842503189409,train,0.7452054794520548,0.02293939407085057,0.7348896056731828,0.02424306980216799,0.7319411369603712,0.02380591066866244 +flat_mae,reg,logistic,adhd200_dx,35,0.005994842503189409,test,0.6153846153846154,0.059067907965995294,0.6018132810585641,0.061461008598663415,0.6013513513513513,0.06019945718518891 +flat_mae,reg,logistic,adhd200_dx,36,0.005994842503189409,train,0.7671232876712328,0.021825748444837614,0.7597363876433645,0.02285867267396159,0.7570983696647737,0.02273036110641878 +flat_mae,reg,logistic,adhd200_dx,36,0.005994842503189409,test,0.6307692307692307,0.05791629135859554,0.6198830409356726,0.05981900021843811,0.6192084942084942,0.05880401091791518 +flat_mae,reg,logistic,adhd200_dx,37,0.005994842503189409,train,0.7589041095890411,0.021358847881171726,0.7499688628720886,0.022427785080224732,0.7469469377785919,0.022131256262775095 +flat_mae,reg,logistic,adhd200_dx,37,0.005994842503189409,test,0.6615384615384615,0.05566727869367932,0.6425000000000001,0.06067186358598766,0.6418918918918919,0.057819022886779044 +flat_mae,reg,logistic,adhd200_dx,38,0.005994842503189409,train,0.7643835616438356,0.022781764080715663,0.757148604320109,0.02374071134580356,0.7546711851987543,0.023530059885559427 +flat_mae,reg,logistic,adhd200_dx,38,0.005994842503189409,test,0.5692307692307692,0.05705428537182761,0.5512820512820513,0.058982250557456636,0.5521235521235521,0.05723716377946786 +flat_mae,reg,logistic,adhd200_dx,39,0.046415888336127774,train,0.8383561643835616,0.018492054762047797,0.8325440704193592,0.01950140411879276,0.8280973316236184,0.019545684585146595 +flat_mae,reg,logistic,adhd200_dx,39,0.046415888336127774,test,0.6,0.057383246013770636,0.5626293995859213,0.06443601160742361,0.5704633204633205,0.058971370269005306 +flat_mae,reg,logistic,adhd200_dx,40,0.000774263682681127,train,0.7013698630136986,0.02307420291814541,0.68111028286083,0.025578986799237338,0.6801917323075044,0.024149401493674543 +flat_mae,reg,logistic,adhd200_dx,40,0.000774263682681127,test,0.7076923076923077,0.048221618565135495,0.6698743651430099,0.059661161465517636,0.6737451737451737,0.051808384166357586 +flat_mae,reg,logistic,adhd200_dx,41,0.046415888336127774,train,0.8301369863013699,0.02017523457294077,0.8255796029103466,0.02097729153702695,0.822968187091653,0.02113951045451517 +flat_mae,reg,logistic,adhd200_dx,41,0.046415888336127774,test,0.5692307692307692,0.06150109634852867,0.5683111954459203,0.06169739167860845,0.5738416988416988,0.06217317957804463 +flat_mae,reg,logistic,adhd200_dx,42,0.3593813663804626,train,0.9643835616438357,0.009814957507808685,0.9635865519649449,0.010095732211391905,0.9612719057214386,0.010736545793590896 +flat_mae,reg,logistic,adhd200_dx,42,0.3593813663804626,test,0.5230769230769231,0.06333826535348253,0.521263958184842,0.06328270628948138,0.5246138996138996,0.06345772722113589 +flat_mae,reg,logistic,adhd200_dx,43,0.005994842503189409,train,0.7561643835616438,0.022326245760661022,0.7484298647089345,0.023190846957887614,0.7459546925566343,0.022916573505290208 +flat_mae,reg,logistic,adhd200_dx,43,0.005994842503189409,test,0.6461538461538462,0.060033095408938385,0.6336682185738789,0.06184846955927299,0.6327220077220077,0.06091261481354763 +flat_mae,reg,logistic,adhd200_dx,44,0.005994842503189409,train,0.7397260273972602,0.022378755037984203,0.7303675710142223,0.023674365099391883,0.7278042376503633,0.023415963303032073 +flat_mae,reg,logistic,adhd200_dx,44,0.005994842503189409,test,0.6923076923076923,0.05504686760512441,0.6832358674463938,0.057288182264934664,0.6819498069498069,0.056702740232194654 +flat_mae,reg,logistic,adhd200_dx,45,0.000774263682681127,train,0.7123287671232876,0.023128565910598052,0.6962407564457196,0.02545433786242634,0.6942052879037675,0.02437681253937212 +flat_mae,reg,logistic,adhd200_dx,45,0.000774263682681127,test,0.5692307692307692,0.058680488778755154,0.5512820512820513,0.06188776265300774,0.5521235521235521,0.05988767893692963 +flat_mae,reg,logistic,adhd200_dx,46,0.046415888336127774,train,0.8246575342465754,0.01920884890224741,0.8185433755903555,0.0202088282440732,0.8145264700494597,0.020249486691586802 +flat_mae,reg,logistic,adhd200_dx,46,0.046415888336127774,test,0.6461538461538462,0.05971447645441474,0.6407113674597452,0.06053011038637422,0.6414092664092663,0.060373322913243474 +flat_mae,reg,logistic,adhd200_dx,47,0.005994842503189409,train,0.7616438356164383,0.021015208818588316,0.752542372881356,0.02242381161148606,0.7493741222446113,0.022095458755044668 +flat_mae,reg,logistic,adhd200_dx,47,0.005994842503189409,test,0.6153846153846154,0.05613016149616709,0.6094688776736361,0.057070340728196334,0.61003861003861,0.057056476005575424 +flat_mae,reg,logistic,adhd200_dx,48,0.005994842503189409,train,0.7452054794520548,0.022620204792456956,0.7354763296317943,0.024126123781086715,0.7326586065824021,0.02383370999089964 +flat_mae,reg,logistic,adhd200_dx,48,0.005994842503189409,test,0.6923076923076923,0.059352721606765246,0.6886973180076628,0.060153628078354754,0.6906370656370657,0.060299907689311476 +flat_mae,reg,logistic,adhd200_dx,49,0.000774263682681127,train,0.7013698630136986,0.022156858027834257,0.68111028286083,0.024696131667223505,0.6801917323075044,0.023262591911269 +flat_mae,reg,logistic,adhd200_dx,49,0.000774263682681127,test,0.5846153846153846,0.06153731537394163,0.5644080416976918,0.06513990290019475,0.5656370656370656,0.06259774613080822 +flat_mae,reg,logistic,adhd200_dx,50,0.005994842503189409,train,0.7671232876712328,0.021782521515492714,0.7587499319600937,0.02302307634870855,0.7556634304207119,0.02285865320148472 +flat_mae,reg,logistic,adhd200_dx,50,0.005994842503189409,test,0.676923076923077,0.0576976407791453,0.6690909090909091,0.05950036286099448,0.6684362934362934,0.0591665810849385 +flat_mae,reg,logistic,adhd200_dx,51,0.005994842503189409,train,0.7534246575342466,0.021260903111719284,0.7463398813936248,0.022230412071893364,0.7442449777126457,0.022176143387695246 +flat_mae,reg,logistic,adhd200_dx,51,0.005994842503189409,test,0.6153846153846154,0.06119553682917286,0.6094688776736361,0.06252710220554109,0.61003861003861,0.06250788512594918 +flat_mae,reg,logistic,adhd200_dx,52,0.046415888336127774,train,0.8328767123287671,0.018860572458695258,0.8275755252499439,0.01971103859461919,0.8239604323136106,0.01978670342825182 +flat_mae,reg,logistic,adhd200_dx,52,0.046415888336127774,test,0.6615384615384615,0.05756786578984524,0.6549227799227799,0.05864633361323745,0.6549227799227799,0.05857995437950616 +flat_mae,reg,logistic,adhd200_dx,53,0.005994842503189409,train,0.7589041095890411,0.021011591042886295,0.7515008974438324,0.021902975437527467,0.7490993466446846,0.021738438950464768 +flat_mae,reg,logistic,adhd200_dx,53,0.005994842503189409,test,0.6923076923076923,0.05573458658689265,0.675,0.060829631626270864,0.6732625482625483,0.05836335724138786 +flat_mae,reg,logistic,adhd200_dx,54,0.005994842503189409,train,0.7589041095890411,0.02127894886625495,0.7515008974438324,0.022275213452592108,0.7490993466446846,0.022144060002303942 +flat_mae,reg,logistic,adhd200_dx,54,0.005994842503189409,test,0.5692307692307692,0.06153288436265738,0.564176245210728,0.062409997856373065,0.5651544401544402,0.06265035137794399 +flat_mae,reg,logistic,adhd200_dx,55,0.005994842503189409,train,0.7616438356164383,0.02233507667808195,0.7530734597709193,0.02355162116877502,0.7500915918666422,0.023322833381471043 +flat_mae,reg,logistic,adhd200_dx,55,0.005994842503189409,test,0.6153846153846154,0.059564104992439,0.6139225469232596,0.06003910947470155,0.6187258687258688,0.06031101169458571 +flat_mae,reg,logistic,adhd200_dx,56,0.005994842503189409,train,0.7452054794520548,0.022602765628876812,0.7348896056731828,0.023902853093557736,0.7319411369603712,0.023426719182362055 +flat_mae,reg,logistic,adhd200_dx,56,0.005994842503189409,test,0.6461538461538462,0.05954077514884606,0.6407113674597452,0.06052922961892826,0.6414092664092663,0.060209605963818365 +flat_mae,reg,logistic,adhd200_dx,57,0.005994842503189409,train,0.7643835616438356,0.021939988776771602,0.7566666666666667,0.022882172651672552,0.7539537155767234,0.022631332810388535 +flat_mae,reg,logistic,adhd200_dx,57,0.005994842503189409,test,0.5846153846153846,0.05798980526603705,0.5644080416976918,0.06143674472291177,0.5656370656370656,0.05903005531533699 +flat_mae,reg,logistic,adhd200_dx,58,0.005994842503189409,train,0.7534246575342466,0.021131991881462888,0.7463398813936248,0.02197740808637753,0.7442449777126457,0.02183491542494974 +flat_mae,reg,logistic,adhd200_dx,58,0.005994842503189409,test,0.6615384615384615,0.054149746348305265,0.6474358974358974,0.05740864825911451,0.6462355212355213,0.055723520479210385 +flat_mae,reg,logistic,adhd200_dx,59,0.005994842503189409,train,0.7589041095890411,0.022108330157163604,0.7494227048617612,0.023418199153457747,0.746229468156561,0.023049008262049673 +flat_mae,reg,logistic,adhd200_dx,59,0.005994842503189409,test,0.6153846153846154,0.06081578742399049,0.6018132810585641,0.06347857557871399,0.6013513513513513,0.06220150389384834 +flat_mae,reg,logistic,adhd200_dx,60,0.005994842503189409,train,0.7561643835616438,0.022480145072920035,0.7498479143083758,0.023176539995699727,0.748107101422727,0.0230717245224725 +flat_mae,reg,logistic,adhd200_dx,60,0.005994842503189409,test,0.6307692307692307,0.05638551998434816,0.61,0.06086674864379356,0.6105212355212355,0.058166257758696646 +flat_mae,reg,logistic,adhd200_dx,61,0.005994842503189409,train,0.7479452054794521,0.022411478039336786,0.7391561024111359,0.02345227738139609,0.7365207302924833,0.0231457242515689 +flat_mae,reg,logistic,adhd200_dx,61,0.005994842503189409,test,0.6,0.06204330612015713,0.5833333333333333,0.06552598885183532,0.5834942084942085,0.06366332113623539 +flat_mae,reg,logistic,adhd200_dx,62,0.046415888336127774,train,0.8383561643835616,0.019076423323451847,0.8338669238187078,0.019804527643885843,0.8309672101117421,0.01991530958363105 +flat_mae,reg,logistic,adhd200_dx,62,0.046415888336127774,test,0.6307692307692307,0.054151005170234336,0.6198830409356726,0.05647165538250065,0.6192084942084942,0.05554102651057014 +flat_mae,reg,logistic,adhd200_dx,63,0.005994842503189409,train,0.7671232876712328,0.022756930939791975,0.7606557377049181,0.023705368949944506,0.7585333089088355,0.02375118770199565 +flat_mae,reg,logistic,adhd200_dx,63,0.005994842503189409,test,0.5846153846153846,0.05960128667051631,0.5745454545454545,0.061253536130914214,0.5743243243243243,0.060737236824382826 +flat_mae,reg,logistic,adhd200_dx,64,0.005994842503189409,train,0.7315068493150685,0.021577344721182414,0.7203196347031964,0.02292529793372906,0.7176528057641814,0.022440250326608104 +flat_mae,reg,logistic,adhd200_dx,64,0.005994842503189409,test,0.6461538461538462,0.0577908983231277,0.6375757575757576,0.05952234904246693,0.6370656370656371,0.05894792768976722 +flat_mae,reg,logistic,adhd200_dx,65,0.005994842503189409,train,0.7342465753424657,0.022381583051667,0.7234870080677283,0.023783040657468803,0.7207974598522318,0.02334181735772442 +flat_mae,reg,logistic,adhd200_dx,65,0.005994842503189409,test,0.6923076923076923,0.05439403900511471,0.6794871794871795,0.05820363494130626,0.6776061776061776,0.05665373976181334 +flat_mae,reg,logistic,adhd200_dx,66,0.000774263682681127,train,0.6958904109589041,0.023821019621183968,0.6780154018548983,0.02586585427930074,0.6767723026195274,0.02471702753504786 +flat_mae,reg,logistic,adhd200_dx,66,0.000774263682681127,test,0.6307692307692307,0.058490227778340294,0.6198830409356726,0.060286664107740855,0.6192084942084942,0.059526330819849524 +flat_mae,reg,logistic,adhd200_dx,67,0.005994842503189409,train,0.7835616438356164,0.020704188441664655,0.7762456448020858,0.021840056911254815,0.773096415704952,0.021762497792561272 +flat_mae,reg,logistic,adhd200_dx,67,0.005994842503189409,test,0.676923076923077,0.050677315397108284,0.6431372549019607,0.060617754003031626,0.6467181467181468,0.053781688834838026 +flat_mae,reg,logistic,adhd200_dx,68,0.005994842503189409,train,0.7561643835616438,0.021889419285919812,0.7457122952038764,0.02360640432323869,0.7423673444464798,0.023228197417142157 +flat_mae,reg,logistic,adhd200_dx,68,0.005994842503189409,test,0.7076923076923077,0.05450997411581213,0.6973780936045086,0.05685946352208832,0.6954633204633205,0.05596330131745825 +flat_mae,reg,logistic,adhd200_dx,69,0.005994842503189409,train,0.7616438356164383,0.021010573609858318,0.7545621072645906,0.022105366367216283,0.7522440007327349,0.022061140012150364 +flat_mae,reg,logistic,adhd200_dx,69,0.005994842503189409,test,0.6,0.06416118017477639,0.5833333333333333,0.06762508136915615,0.5834942084942085,0.06551726924782401 +flat_mae,reg,logistic,adhd200_dx,70,0.005994842503189409,train,0.7452054794520548,0.022564977005908128,0.7371233417745046,0.023573722259959157,0.7348110154484948,0.023337189879568915 +flat_mae,reg,logistic,adhd200_dx,70,0.005994842503189409,test,0.5538461538461539,0.06265161680880546,0.543030303030303,0.06447106499904373,0.542953667953668,0.06413719387269122 +flat_mae,reg,logistic,adhd200_dx,71,0.046415888336127774,train,0.8273972602739726,0.01862763802740474,0.8215629825636888,0.019596919015449014,0.8176711241375099,0.01965769270389804 +flat_mae,reg,logistic,adhd200_dx,71,0.046415888336127774,test,0.6461538461538462,0.05815689857678972,0.6431129147767964,0.05872459811934013,0.6457528957528957,0.05903636636034522 +flat_mae,reg,logistic,adhd200_dx,72,0.005994842503189409,train,0.7452054794520548,0.022942404245282363,0.7360440432033966,0.024078704278836873,0.733376076204433,0.023734578454468476 +flat_mae,reg,logistic,adhd200_dx,72,0.005994842503189409,test,0.7230769230769231,0.05649293614532287,0.7176640926640927,0.057672554535555996,0.7176640926640927,0.0572718936948747 +flat_mae,reg,logistic,adhd200_dx,73,0.005994842503189409,train,0.7616438356164383,0.022761632623446496,0.7535869759212843,0.02378182256278148,0.7508090614886731,0.023539090924204715 +flat_mae,reg,logistic,adhd200_dx,73,0.005994842503189409,test,0.6307692307692307,0.0604472482623089,0.61,0.06486028871642777,0.6105212355212355,0.06223777514613452 +flat_mae,reg,logistic,adhd200_dx,74,0.005994842503189409,train,0.7534246575342466,0.02126406617782008,0.7442863370282725,0.02246779909372091,0.7413750992245222,0.022191918848255932 +flat_mae,reg,logistic,adhd200_dx,74,0.005994842503189409,test,0.6615384615384615,0.05787148381589378,0.6474358974358974,0.06167886970136229,0.6462355212355213,0.05952082698969735 +flat_mae,reg,logistic,adhd200_dx,75,0.005994842503189409,train,0.7643835616438356,0.022434203706962096,0.7576136644427971,0.02322609878827812,0.7553886548207852,0.023084479851312484 +flat_mae,reg,logistic,adhd200_dx,75,0.005994842503189409,test,0.6153846153846154,0.05796696876200808,0.61207925519217,0.05861412462230665,0.6143822393822393,0.05886860503813531 +flat_mae,reg,logistic,adhd200_dx,76,0.005994842503189409,train,0.7561643835616438,0.02231563610872736,0.747922308701084,0.02335530424359973,0.7452372229346034,0.02310256797541392 +flat_mae,reg,logistic,adhd200_dx,76,0.005994842503189409,test,0.5692307692307692,0.048201264438717,0.49444444444444446,0.06079790015836899,0.5260617760617761,0.04963130430826381 +flat_mae,reg,logistic,adhd200_dx,77,0.005994842503189409,train,0.7506849315068493,0.022577137180955234,0.74059090447591,0.024034868440771153,0.737512975514441,0.023658449310213606 +flat_mae,reg,logistic,adhd200_dx,77,0.005994842503189409,test,0.7538461538461538,0.04975570140682581,0.7357723577235773,0.056395966300536664,0.7316602316602316,0.05299306456048523 +flat_mae,reg,logistic,adhd200_dx,78,0.005994842503189409,train,0.7671232876712328,0.021904637138437957,0.7606557377049181,0.02265109339184277,0.7585333089088355,0.022533158197346078 +flat_mae,reg,logistic,adhd200_dx,78,0.005994842503189409,test,0.6153846153846154,0.057625397096528065,0.5905769715293525,0.06294423249331563,0.5926640926640927,0.05931432234409837 +flat_mae,reg,logistic,adhd200_dx,79,0.000774263682681127,train,0.6986301369863014,0.023429867881638228,0.6853448275862069,0.02505845997725178,0.6835043048177322,0.02434903557111274 +flat_mae,reg,logistic,adhd200_dx,79,0.000774263682681127,test,0.6153846153846154,0.055289525207159594,0.5905769715293525,0.060216423283950854,0.5926640926640927,0.05657134466693279 +flat_mae,reg,logistic,adhd200_dx,80,0.000774263682681127,train,0.7150684931506849,0.021183660857686012,0.6987301587301586,0.023134431461911124,0.6966324723697869,0.022165606516216803 +flat_mae,reg,logistic,adhd200_dx,80,0.000774263682681127,test,0.6461538461538462,0.05827416125370219,0.6167649320687003,0.0650872233923777,0.6196911196911197,0.060551231690099794 +flat_mae,reg,logistic,adhd200_dx,81,0.000774263682681127,train,0.7123287671232876,0.023653988518385703,0.7013442431326709,0.024929881417688208,0.6992275752579837,0.024459386154415726 +flat_mae,reg,logistic,adhd200_dx,81,0.000774263682681127,test,0.6,0.05560410354785829,0.570630081300813,0.06173985173548995,0.5748069498069498,0.05727707428183242 +flat_mae,reg,logistic,adhd200_dx,82,0.005994842503189409,train,0.7479452054794521,0.02185428877988679,0.7396899224806202,0.022955082067081026,0.7372381999145142,0.02273082780979243 +flat_mae,reg,logistic,adhd200_dx,82,0.005994842503189409,test,0.7230769230769231,0.05137060149759639,0.7176640926640927,0.0529088631170858,0.7176640926640927,0.0531076797258266 +flat_mae,reg,logistic,adhd200_dx,83,0.005994842503189409,train,0.7424657534246575,0.02137567535988949,0.7345577768150028,0.02216283554810893,0.7323838309824754,0.021934635790358516 +flat_mae,reg,logistic,adhd200_dx,83,0.005994842503189409,test,0.7538461538461538,0.054071362007527726,0.74,0.05825456507107676,0.7360038610038611,0.05649080402166382 +flat_mae,reg,logistic,adhd200_dx,84,0.000774263682681127,train,0.6876712328767123,0.022797091530457923,0.6706401975683891,0.02445934539842356,0.6694907492214691,0.023475745465008697 +flat_mae,reg,logistic,adhd200_dx,84,0.000774263682681127,test,0.6153846153846154,0.06006910418931274,0.6018132810585641,0.06259946244122429,0.6013513513513513,0.06121096944447728 +flat_mae,reg,logistic,adhd200_dx,85,0.005994842503189409,train,0.7397260273972602,0.021841029218602058,0.7285693038693062,0.023153358392282577,0.7256518287842706,0.02264201518064777 +flat_mae,reg,logistic,adhd200_dx,85,0.005994842503189409,test,0.7230769230769231,0.05394589443717862,0.7115384615384616,0.05756580632540266,0.708976833976834,0.05644801624238615 +flat_mae,reg,logistic,adhd200_dx,86,0.005994842503189409,train,0.7534246575342466,0.023155684634801048,0.7453488372093022,0.024235396671430764,0.742810038468584,0.024018869603799002 +flat_mae,reg,logistic,adhd200_dx,86,0.005994842503189409,test,0.5846153846153846,0.06100211656042822,0.5644080416976918,0.06436443020177783,0.5656370656370656,0.062154623297319606 +flat_mae,reg,logistic,adhd200_dx,87,0.005994842503189409,train,0.7506849315068493,0.02271092349867145,0.7422576414808837,0.023692867897726493,0.7396653843805336,0.023438447206799443 +flat_mae,reg,logistic,adhd200_dx,87,0.005994842503189409,test,0.676923076923077,0.05494129411304914,0.656084656084656,0.06067278756768207,0.6554054054054055,0.05749263036241408 +flat_mae,reg,logistic,adhd200_dx,88,0.005994842503189409,train,0.7643835616438356,0.020140947518317878,0.7566666666666667,0.021148303153148158,0.7539537155767234,0.021042840718284102 +flat_mae,reg,logistic,adhd200_dx,88,0.005994842503189409,test,0.6615384615384615,0.05903745476465561,0.6515594541910331,0.0616468118075516,0.6505791505791505,0.060884076719537175 +flat_mae,reg,logistic,adhd200_dx,89,0.005994842503189409,train,0.7698630136986301,0.021725941024893523,0.7623255813953489,0.022810898466159746,0.7595255541307931,0.022642298302020827 +flat_mae,reg,logistic,adhd200_dx,89,0.005994842503189409,test,0.6461538461538462,0.05769689417666376,0.6289401836684041,0.06172407572518089,0.6283783783783784,0.05962804438732754 +flat_mae,reg,logistic,adhd200_dx,90,0.000774263682681127,train,0.7013698630136986,0.02256023633440183,0.6863000197122019,0.024378182605981086,0.6844965500396898,0.023547744318301044 +flat_mae,reg,logistic,adhd200_dx,90,0.000774263682681127,test,0.6307692307692307,0.05119980584282713,0.587737843551797,0.06066689623293587,0.5974903474903475,0.053141557712909585 +flat_mae,reg,logistic,adhd200_dx,91,0.046415888336127774,train,0.8356164383561644,0.01868438837438227,0.8315073552040377,0.019392085975580866,0.8292574952677536,0.019625546469770622 +flat_mae,reg,logistic,adhd200_dx,91,0.046415888336127774,test,0.5384615384615384,0.05617298725403002,0.5045731707317074,0.06016242644776883,0.5120656370656371,0.05676692361597073 +flat_mae,reg,logistic,adhd200_dx,92,0.005994842503189409,train,0.7397260273972602,0.02147327560065255,0.730928307040483,0.02250485363540215,0.7285217072723942,0.022237866494013513 +flat_mae,reg,logistic,adhd200_dx,92,0.005994842503189409,test,0.6923076923076923,0.05433184034927996,0.6697154471544715,0.06075344927114371,0.6689189189189189,0.05690465073014783 +flat_mae,reg,logistic,adhd200_dx,93,0.005994842503189409,train,0.7561643835616438,0.021602779857677647,0.7462922032786373,0.02300023513177545,0.7430848140685107,0.022666761468717014 +flat_mae,reg,logistic,adhd200_dx,93,0.005994842503189409,test,0.6307692307692307,0.04917776954835873,0.577922077922078,0.06137636142055501,0.5931467181467182,0.051654285961888834 +flat_mae,reg,logistic,adhd200_dx,94,0.005994842503189409,train,0.7726027397260274,0.02250135234984282,0.7639197350477304,0.023695935818350687,0.7605177993527508,0.023386315977885878 +flat_mae,reg,logistic,adhd200_dx,94,0.005994842503189409,test,0.6615384615384615,0.0500851251701901,0.622093023255814,0.06140455406081385,0.6288610038610039,0.053411143078725375 +flat_mae,reg,logistic,adhd200_dx,95,0.005994842503189409,train,0.7808219178082192,0.02281481183259358,0.7753431402720503,0.023547566235839718,0.7735391097270562,0.02355586738539892 +flat_mae,reg,logistic,adhd200_dx,95,0.005994842503189409,test,0.5076923076923077,0.057161869195651985,0.48,0.061480311251213414,0.48503861003861004,0.05833733101419725 +flat_mae,reg,logistic,adhd200_dx,96,0.005994842503189409,train,0.7452054794520548,0.023177796559009468,0.7376353560414589,0.024048609420869928,0.7355284850705257,0.023865558468504095 +flat_mae,reg,logistic,adhd200_dx,96,0.005994842503189409,test,0.6461538461538462,0.06010246871437254,0.6375757575757576,0.06164661193854062,0.6370656370656371,0.06119138751973631 +flat_mae,reg,logistic,adhd200_dx,97,0.005994842503189409,train,0.7506849315068493,0.021726299640713403,0.7417205153925708,0.02298555363202584,0.7389479147585027,0.02272048970362985 +flat_mae,reg,logistic,adhd200_dx,97,0.005994842503189409,test,0.676923076923077,0.05251491982983243,0.6500897205844656,0.060082899533591264,0.6510617760617761,0.05528684086380925 +flat_mae,reg,logistic,adhd200_dx,98,0.005994842503189409,train,0.7424657534246575,0.02230656531316637,0.7311128526645768,0.02351419644227174,0.72807901325029,0.022954375590937208 +flat_mae,reg,logistic,adhd200_dx,98,0.005994842503189409,test,0.676923076923077,0.05929961233995244,0.6655231560891939,0.061819705518045,0.6640926640926641,0.060347036583652355 +flat_mae,reg,logistic,adhd200_dx,99,0.000774263682681127,train,0.7041095890410959,0.02356815392700743,0.6937919463087248,0.024963808160330083,0.6919460218599255,0.02458852593417635 +flat_mae,reg,logistic,adhd200_dx,99,0.000774263682681127,test,0.6615384615384615,0.05864827665865031,0.6474358974358974,0.06201584268352816,0.6462355212355213,0.060633714178344664 +flat_mae,reg,logistic,adhd200_dx,100,0.005994842503189409,train,0.7506849315068493,0.02198509944224626,0.7422576414808837,0.023241987519685252,0.7396653843805336,0.02308334286088704 +flat_mae,reg,logistic,adhd200_dx,100,0.005994842503189409,test,0.7076923076923077,0.050409832796822,0.6888384983623079,0.05616619189934944,0.6867760617760618,0.05331620349115245 diff --git a/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..8fc79eafd49f68d9b3261bb7eb0a5af54d07969b --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic/log.txt @@ -0,0 +1,241 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:23:53 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adhd200_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic +model: flat_mae +representation: reg +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adhd200_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adhd200_dx (flat) +train (n=301): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 301 +}), + labels=['ADHD' 'Control'], + counts=[131 170] +) + +validation (n=64): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 64 +}), + labels=['ADHD' 'Control'], + counts=[28 36] +) + +test (n=65): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'gender', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 65 +}), + labels=['ADHD' 'Control'], + counts=[28 37] +) + +extracting features for all splits +extract (train) [ 0/151] eta: 0:10:49 time: 4.2987 data: 3.3012 max mem: 2708 +extract (train) [ 20/151] eta: 0:00:51 time: 0.1943 data: 0.0675 max mem: 2863 +extract (train) [ 40/151] eta: 0:00:31 time: 0.1722 data: 0.0564 max mem: 2863 +extract (train) [ 60/151] eta: 0:00:22 time: 0.1744 data: 0.0578 max mem: 2863 +extract (train) [ 80/151] eta: 0:00:16 time: 0.1701 data: 0.0551 max mem: 2863 +extract (train) [100/151] eta: 0:00:11 time: 0.1918 data: 0.0686 max mem: 2863 +extract (train) [120/151] eta: 0:00:06 time: 0.1746 data: 0.0576 max mem: 2863 +extract (train) [140/151] eta: 0:00:02 time: 0.1566 data: 0.0499 max mem: 2863 +extract (train) [150/151] eta: 0:00:00 time: 0.1565 data: 0.0501 max mem: 2863 +extract (train) Total time: 0:00:30 (0.2049 s / it) +extract (validation) [ 0/32] eta: 0:01:57 time: 3.6756 data: 3.5441 max mem: 2863 +extract (validation) [20/32] eta: 0:00:04 time: 0.1791 data: 0.0613 max mem: 2863 +extract (validation) [31/32] eta: 0:00:00 time: 0.1474 data: 0.0436 max mem: 2863 +extract (validation) Total time: 0:00:09 (0.2840 s / it) +extract (test) [ 0/33] eta: 0:02:03 time: 3.7487 data: 3.6178 max mem: 2863 +extract (test) [20/33] eta: 0:00:04 time: 0.1770 data: 0.0579 max mem: 2863 +extract (test) [32/33] eta: 0:00:00 time: 0.1468 data: 0.0453 max mem: 2863 +extract (test) Total time: 0:00:09 (0.2811 s / it) +feature extraction time: 0:00:49 +train features: (301, 768) +validation features: (64, 768) +test features: (65, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adhd200_dx | | 0.0059948 | train | 0.7589 | 0.020938 | 0.74886 | 0.022351 | 0.74551 | 0.021966 | +| flat_mae | reg | logistic | adhd200_dx | | 0.0059948 | test | 0.61538 | 0.057625 | 0.59058 | 0.06237 | 0.59266 | 0.059136 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.060707279034813044, "f1": 0.5921814671814671, "f1_std": 0.06123178981076584, "bacc": 0.5921814671814671, "bacc_std": 0.06085749253149747} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 2, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.055213273423427606, "f1": 0.656084656084656, "f1_std": 0.060952774269968264, "bacc": 0.6554054054054055, "bacc_std": 0.05784034389207626} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05886734460084835, "f1": 0.5644080416976918, "f1_std": 0.0626293427190368, "bacc": 0.5656370656370656, "bacc_std": 0.06028953488532466} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.0560866531602831, "f1": 0.6655231560891939, "f1_std": 0.0593130143297974, "bacc": 0.6640926640926641, "bacc_std": 0.05816887972455575} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06450448358344452, "f1": 0.5189782764382908, "f1_std": 0.06489703697005733, "bacc": 0.5202702702702703, "bacc_std": 0.06525232855375976} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06089829332729707, "f1": 0.6299810246679317, "f1_std": 0.06106890728140279, "bacc": 0.6365830115830116, "bacc_std": 0.061548893037202845} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.0589396722964609, "f1": 0.6018132810585641, "f1_std": 0.06133216354183448, "bacc": 0.6013513513513513, "bacc_std": 0.06013710169723944} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 8, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.06134445572764266, "f1": 0.6153846153846154, "f1_std": 0.06530247790735864, "bacc": 0.6148648648648649, "bacc_std": 0.06338919463900186} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05790552599561119, "f1": 0.6036585365853658, "f1_std": 0.06413793908689208, "bacc": 0.6061776061776062, "bacc_std": 0.05988444137205735} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.0590654155458968, "f1": 0.5775, "f1_std": 0.06345542029917184, "bacc": 0.5791505791505791, "bacc_std": 0.060373004779775925} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.0561730125351855, "f1": 0.61, "f1_std": 0.061335954884655264, "bacc": 0.6105212355212355, "bacc_std": 0.05829987274529371} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05734479955063893, "f1": 0.5644080416976918, "f1_std": 0.06176937411803161, "bacc": 0.5656370656370656, "bacc_std": 0.059138752155352} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 13, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.059545664442057854, "f1": 0.5745454545454545, "f1_std": 0.060956741688393275, "bacc": 0.5743243243243243, "bacc_std": 0.06060527251906438} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.054559529401569364, "f1": 0.6036585365853658, "f1_std": 0.06054526560325099, "bacc": 0.6061776061776062, "bacc_std": 0.05647509907201201} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 15, "C": 0.000774263682681127, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05716630778318756, "f1": 0.6336682185738789, "f1_std": 0.06000045729795002, "bacc": 0.6327220077220077, "bacc_std": 0.05861835555189784} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05891717986156701, "f1": 0.6336682185738789, "f1_std": 0.06163303731621899, "bacc": 0.6327220077220077, "bacc_std": 0.06040816705824471} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 17, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05334936544045682, "f1": 0.587737843551797, "f1_std": 0.06408668858733474, "bacc": 0.5974903474903475, "bacc_std": 0.05599402392979974} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05623197094369908, "f1": 0.6018132810585641, "f1_std": 0.058608789151448376, "bacc": 0.6013513513513513, "bacc_std": 0.05732587756612467} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 19, "C": 0.000774263682681127, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05043198947226034, "f1": 0.6003742314889067, "f1_std": 0.06178411872825358, "bacc": 0.6110038610038611, "bacc_std": 0.05322954317652886} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.058381516082732406, "f1": 0.5469838981014179, "f1_std": 0.059205055762357, "bacc": 0.5472972972972974, "bacc_std": 0.059271356364151095} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.052997612986327235, "f1": 0.6973780936045086, "f1_std": 0.05553344105515485, "bacc": 0.6954633204633205, "bacc_std": 0.05447271250305293} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06438501791988863, "f1": 0.6094688776736361, "f1_std": 0.06535029972812952, "bacc": 0.61003861003861, "bacc_std": 0.06544929321066625} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05164488667357716, "f1": 0.6091503267973856, "f1_std": 0.06099975572352973, "bacc": 0.6153474903474904, "bacc_std": 0.054222100983927976} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.054949358073254344, "f1": 0.5834401435529352, "f1_std": 0.06182825048128351, "bacc": 0.5883204633204633, "bacc_std": 0.05667430478441108} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05902314058282865, "f1": 0.5330459770114943, "f1_std": 0.0595026500791029, "bacc": 0.5337837837837838, "bacc_std": 0.059702133922600466} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.057911738598108255, "f1": 0.6575670498084292, "f1_std": 0.058370914593579855, "bacc": 0.6592664092664093, "bacc_std": 0.05848710989299784} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.053752921483835064, "f1": 0.6832358674463938, "f1_std": 0.055758138121379565, "bacc": 0.6819498069498069, "bacc_std": 0.05509214172226039} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05654925904222664, "f1": 0.6336682185738789, "f1_std": 0.05880081453388411, "bacc": 0.6327220077220077, "bacc_std": 0.0578733908913043} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 29, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05916559851245721, "f1": 0.5775, "f1_std": 0.0634187424678971, "bacc": 0.5791505791505791, "bacc_std": 0.060535804985222805} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06244392324554774, "f1": 0.5699583435432491, "f1_std": 0.06475744472659399, "bacc": 0.5699806949806949, "bacc_std": 0.06359021401165693} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.055448988231147994, "f1": 0.5966741126830479, "f1_std": 0.05964586888506354, "bacc": 0.597007722007722, "bacc_std": 0.05753488524920535} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06201281791532149, "f1": 0.61207925519217, "f1_std": 0.06230888006666315, "bacc": 0.6143822393822393, "bacc_std": 0.062450854390049756} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05916179800509165, "f1": 0.5842217484008528, "f1_std": 0.05937099424917247, "bacc": 0.5916988416988418, "bacc_std": 0.059552763776855346} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05986508697941777, "f1": 0.6150201374081972, "f1_std": 0.06013819799960458, "bacc": 0.6230694980694981, "bacc_std": 0.060110676341275454} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.059067907965995294, "f1": 0.6018132810585641, "f1_std": 0.061461008598663415, "bacc": 0.6013513513513513, "bacc_std": 0.06019945718518891} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05791629135859554, "f1": 0.6198830409356726, "f1_std": 0.05981900021843811, "bacc": 0.6192084942084942, "bacc_std": 0.05880401091791518} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05566727869367932, "f1": 0.6425000000000001, "f1_std": 0.06067186358598766, "bacc": 0.6418918918918919, "bacc_std": 0.057819022886779044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.05705428537182761, "f1": 0.5512820512820513, "f1_std": 0.058982250557456636, "bacc": 0.5521235521235521, "bacc_std": 0.05723716377946786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.6, "acc_std": 0.057383246013770636, "f1": 0.5626293995859213, "f1_std": 0.06443601160742361, "bacc": 0.5704633204633205, "bacc_std": 0.058971370269005306} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 40, "C": 0.000774263682681127, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.048221618565135495, "f1": 0.6698743651430099, "f1_std": 0.059661161465517636, "bacc": 0.6737451737451737, "bacc_std": 0.051808384166357586} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06150109634852867, "f1": 0.5683111954459203, "f1_std": 0.06169739167860845, "bacc": 0.5738416988416988, "bacc_std": 0.06217317957804463} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.5230769230769231, "acc_std": 0.06333826535348253, "f1": 0.521263958184842, "f1_std": 0.06328270628948138, "bacc": 0.5246138996138996, "bacc_std": 0.06345772722113589} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.060033095408938385, "f1": 0.6336682185738789, "f1_std": 0.06184846955927299, "bacc": 0.6327220077220077, "bacc_std": 0.06091261481354763} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05504686760512441, "f1": 0.6832358674463938, "f1_std": 0.057288182264934664, "bacc": 0.6819498069498069, "bacc_std": 0.056702740232194654} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 45, "C": 0.000774263682681127, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.058680488778755154, "f1": 0.5512820512820513, "f1_std": 0.06188776265300774, "bacc": 0.5521235521235521, "bacc_std": 0.05988767893692963} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05971447645441474, "f1": 0.6407113674597452, "f1_std": 0.06053011038637422, "bacc": 0.6414092664092663, "bacc_std": 0.060373322913243474} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05613016149616709, "f1": 0.6094688776736361, "f1_std": 0.057070340728196334, "bacc": 0.61003861003861, "bacc_std": 0.057056476005575424} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.059352721606765246, "f1": 0.6886973180076628, "f1_std": 0.060153628078354754, "bacc": 0.6906370656370657, "bacc_std": 0.060299907689311476} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 49, "C": 0.000774263682681127, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06153731537394163, "f1": 0.5644080416976918, "f1_std": 0.06513990290019475, "bacc": 0.5656370656370656, "bacc_std": 0.06259774613080822} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.0576976407791453, "f1": 0.6690909090909091, "f1_std": 0.05950036286099448, "bacc": 0.6684362934362934, "bacc_std": 0.0591665810849385} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06119553682917286, "f1": 0.6094688776736361, "f1_std": 0.06252710220554109, "bacc": 0.61003861003861, "bacc_std": 0.06250788512594918} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05756786578984524, "f1": 0.6549227799227799, "f1_std": 0.05864633361323745, "bacc": 0.6549227799227799, "bacc_std": 0.05857995437950616} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05573458658689265, "f1": 0.675, "f1_std": 0.060829631626270864, "bacc": 0.6732625482625483, "bacc_std": 0.05836335724138786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.06153288436265738, "f1": 0.564176245210728, "f1_std": 0.062409997856373065, "bacc": 0.5651544401544402, "bacc_std": 0.06265035137794399} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.059564104992439, "f1": 0.6139225469232596, "f1_std": 0.06003910947470155, "bacc": 0.6187258687258688, "bacc_std": 0.06031101169458571} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05954077514884606, "f1": 0.6407113674597452, "f1_std": 0.06052922961892826, "bacc": 0.6414092664092663, "bacc_std": 0.060209605963818365} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 57, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05798980526603705, "f1": 0.5644080416976918, "f1_std": 0.06143674472291177, "bacc": 0.5656370656370656, "bacc_std": 0.05903005531533699} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.054149746348305265, "f1": 0.6474358974358974, "f1_std": 0.05740864825911451, "bacc": 0.6462355212355213, "bacc_std": 0.055723520479210385} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06081578742399049, "f1": 0.6018132810585641, "f1_std": 0.06347857557871399, "bacc": 0.6013513513513513, "bacc_std": 0.06220150389384834} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05638551998434816, "f1": 0.61, "f1_std": 0.06086674864379356, "bacc": 0.6105212355212355, "bacc_std": 0.058166257758696646} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06204330612015713, "f1": 0.5833333333333333, "f1_std": 0.06552598885183532, "bacc": 0.5834942084942085, "bacc_std": 0.06366332113623539} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.054151005170234336, "f1": 0.6198830409356726, "f1_std": 0.05647165538250065, "bacc": 0.6192084942084942, "bacc_std": 0.05554102651057014} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.05960128667051631, "f1": 0.5745454545454545, "f1_std": 0.061253536130914214, "bacc": 0.5743243243243243, "bacc_std": 0.060737236824382826} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.0577908983231277, "f1": 0.6375757575757576, "f1_std": 0.05952234904246693, "bacc": 0.6370656370656371, "bacc_std": 0.05894792768976722} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05439403900511471, "f1": 0.6794871794871795, "f1_std": 0.05820363494130626, "bacc": 0.6776061776061776, "bacc_std": 0.05665373976181334} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 66, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.058490227778340294, "f1": 0.6198830409356726, "f1_std": 0.060286664107740855, "bacc": 0.6192084942084942, "bacc_std": 0.059526330819849524} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.050677315397108284, "f1": 0.6431372549019607, "f1_std": 0.060617754003031626, "bacc": 0.6467181467181468, "bacc_std": 0.053781688834838026} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.05450997411581213, "f1": 0.6973780936045086, "f1_std": 0.05685946352208832, "bacc": 0.6954633204633205, "bacc_std": 0.05596330131745825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.06416118017477639, "f1": 0.5833333333333333, "f1_std": 0.06762508136915615, "bacc": 0.5834942084942085, "bacc_std": 0.06551726924782401} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.5538461538461539, "acc_std": 0.06265161680880546, "f1": 0.543030303030303, "f1_std": 0.06447106499904373, "bacc": 0.542953667953668, "bacc_std": 0.06413719387269122} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05815689857678972, "f1": 0.6431129147767964, "f1_std": 0.05872459811934013, "bacc": 0.6457528957528957, "bacc_std": 0.05903636636034522} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05649293614532287, "f1": 0.7176640926640927, "f1_std": 0.057672554535555996, "bacc": 0.7176640926640927, "bacc_std": 0.0572718936948747} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.0604472482623089, "f1": 0.61, "f1_std": 0.06486028871642777, "bacc": 0.6105212355212355, "bacc_std": 0.06223777514613452} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05787148381589378, "f1": 0.6474358974358974, "f1_std": 0.06167886970136229, "bacc": 0.6462355212355213, "bacc_std": 0.05952082698969735} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.05796696876200808, "f1": 0.61207925519217, "f1_std": 0.05861412462230665, "bacc": 0.6143822393822393, "bacc_std": 0.05886860503813531} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5692307692307692, "acc_std": 0.048201264438717, "f1": 0.49444444444444446, "f1_std": 0.06079790015836899, "bacc": 0.5260617760617761, "bacc_std": 0.04963130430826381} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 77, "C": 0.005994842503189409, "split": "test", "acc": 0.7538461538461538, "acc_std": 0.04975570140682581, "f1": 0.7357723577235773, "f1_std": 0.056395966300536664, "bacc": 0.7316602316602316, "bacc_std": 0.05299306456048523} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.057625397096528065, "f1": 0.5905769715293525, "f1_std": 0.06294423249331563, "bacc": 0.5926640926640927, "bacc_std": 0.05931432234409837} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 79, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.055289525207159594, "f1": 0.5905769715293525, "f1_std": 0.060216423283950854, "bacc": 0.5926640926640927, "bacc_std": 0.05657134466693279} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 80, "C": 0.000774263682681127, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05827416125370219, "f1": 0.6167649320687003, "f1_std": 0.0650872233923777, "bacc": 0.6196911196911197, "bacc_std": 0.060551231690099794} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 81, "C": 0.000774263682681127, "split": "test", "acc": 0.6, "acc_std": 0.05560410354785829, "f1": 0.570630081300813, "f1_std": 0.06173985173548995, "bacc": 0.5748069498069498, "bacc_std": 0.05727707428183242} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05137060149759639, "f1": 0.7176640926640927, "f1_std": 0.0529088631170858, "bacc": 0.7176640926640927, "bacc_std": 0.0531076797258266} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 83, "C": 0.005994842503189409, "split": "test", "acc": 0.7538461538461538, "acc_std": 0.054071362007527726, "f1": 0.74, "f1_std": 0.05825456507107676, "bacc": 0.7360038610038611, "bacc_std": 0.05649080402166382} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 84, "C": 0.000774263682681127, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06006910418931274, "f1": 0.6018132810585641, "f1_std": 0.06259946244122429, "bacc": 0.6013513513513513, "bacc_std": 0.06121096944447728} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.7230769230769231, "acc_std": 0.05394589443717862, "f1": 0.7115384615384616, "f1_std": 0.05756580632540266, "bacc": 0.708976833976834, "bacc_std": 0.05644801624238615} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.5846153846153846, "acc_std": 0.06100211656042822, "f1": 0.5644080416976918, "f1_std": 0.06436443020177783, "bacc": 0.5656370656370656, "bacc_std": 0.062154623297319606} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05494129411304914, "f1": 0.656084656084656, "f1_std": 0.06067278756768207, "bacc": 0.6554054054054055, "bacc_std": 0.05749263036241408} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 88, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05903745476465561, "f1": 0.6515594541910331, "f1_std": 0.0616468118075516, "bacc": 0.6505791505791505, "bacc_std": 0.060884076719537175} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.05769689417666376, "f1": 0.6289401836684041, "f1_std": 0.06172407572518089, "bacc": 0.6283783783783784, "bacc_std": 0.05962804438732754} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.05119980584282713, "f1": 0.587737843551797, "f1_std": 0.06066689623293587, "bacc": 0.5974903474903475, "bacc_std": 0.053141557712909585} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05617298725403002, "f1": 0.5045731707317074, "f1_std": 0.06016242644776883, "bacc": 0.5120656370656371, "bacc_std": 0.05676692361597073} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.6923076923076923, "acc_std": 0.05433184034927996, "f1": 0.6697154471544715, "f1_std": 0.06075344927114371, "bacc": 0.6689189189189189, "bacc_std": 0.05690465073014783} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6307692307692307, "acc_std": 0.04917776954835873, "f1": 0.577922077922078, "f1_std": 0.06137636142055501, "bacc": 0.5931467181467182, "bacc_std": 0.051654285961888834} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.0500851251701901, "f1": 0.622093023255814, "f1_std": 0.06140455406081385, "bacc": 0.6288610038610039, "bacc_std": 0.053411143078725375} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.5076923076923077, "acc_std": 0.057161869195651985, "f1": 0.48, "f1_std": 0.061480311251213414, "bacc": 0.48503861003861004, "bacc_std": 0.05833733101419725} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.6461538461538462, "acc_std": 0.06010246871437254, "f1": 0.6375757575757576, "f1_std": 0.06164661193854062, "bacc": 0.6370656370656371, "bacc_std": 0.06119138751973631} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05251491982983243, "f1": 0.6500897205844656, "f1_std": 0.060082899533591264, "bacc": 0.6510617760617761, "bacc_std": 0.05528684086380925} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.676923076923077, "acc_std": 0.05929961233995244, "f1": 0.6655231560891939, "f1_std": 0.061819705518045, "bacc": 0.6640926640926641, "bacc_std": 0.060347036583652355} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 99, "C": 0.000774263682681127, "split": "test", "acc": 0.6615384615384615, "acc_std": 0.05864827665865031, "f1": 0.6474358974358974, "f1_std": 0.06201584268352816, "bacc": 0.6462355212355213, "bacc_std": 0.060633714178344664} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adhd200_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.7076923076923077, "acc_std": 0.050409832796822, "f1": 0.6888384983623079, "f1_std": 0.05616619189934944, "bacc": 0.6867760617760618, "bacc_std": 0.05331620349115245} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:-----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adhd200_dx | train | 100 | 0.0453 | 0.28116 | 0.76523 | 0.052854 | 0.75621 | 0.056285 | 0.75368 | 0.056014 | +| flat_mae | reg | logistic | adhd200_dx | test | 100 | 0.0453 | 0.28116 | 0.63185 | 0.049588 | 0.61519 | 0.05161 | 0.61681 | 0.049611 | + + +done! total time: 0:04:54 diff --git a/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..76c03bc0bf23e212d01fd449f2a9bc4f8d514df4 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..f74cd739ae703cb5e8f940746324d11f21b4b72d --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,adni_ad_vs_cn,,0.3593813663804626,train,0.9728997289972899,0.007664347609458442,0.9608013937282229,0.011619276192426102,0.9425287356321839,0.01625370268902394 +flat_mae,patch,logistic,adni_ad_vs_cn,,0.3593813663804626,test,0.7560975609756098,0.061909799866036605,0.6440972222222222,0.09098181448846566,0.6440972222222222,0.09048257326587708 +flat_mae,patch,logistic,adni_ad_vs_cn,1,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,1,2.782559402207126,test,0.8048780487804879,0.04479780737389527,0.6554621848739496,0.09749513950630406,0.6338709677419355,0.07780202008189852 +flat_mae,patch,logistic,adni_ad_vs_cn,2,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,2,2.782559402207126,test,0.6829268292682927,0.0625889206830291,0.5547201336675021,0.08584538056123783,0.5532258064516129,0.08272138278350397 +flat_mae,patch,logistic,adni_ad_vs_cn,3,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,3,166.81005372000556,test,0.7073170731707317,0.05627101497849751,0.5340909090909092,0.08464319586922124,0.535483870967742,0.07183146674671478 +flat_mae,patch,logistic,adni_ad_vs_cn,4,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,4,21.54434690031882,test,0.8536585365853658,0.057596433890533566,0.8136363636363637,0.06991638165114575,0.8354838709677419,0.07135650664503362 +flat_mae,patch,logistic,adni_ad_vs_cn,5,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,5,2.782559402207126,test,0.6585365853658537,0.051994119467978744,0.4564393939393939,0.06424562752493705,0.4693548387096774,0.05598849889329649 +flat_mae,patch,logistic,adni_ad_vs_cn,6,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,6,1291.5496650148827,test,0.7317073170731707,0.06691066789153917,0.6479313036690086,0.08710240835072448,0.6532258064516129,0.09057293621272056 +flat_mae,patch,logistic,adni_ad_vs_cn,7,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,7,21.54434690031882,test,0.7560975609756098,0.05956453116572199,0.6693548387096775,0.0807272789617199,0.6693548387096775,0.0831174060241484 +flat_mae,patch,logistic,adni_ad_vs_cn,8,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,8,21.54434690031882,test,0.7317073170731707,0.06406828228355291,0.6232247284878863,0.08746532721276744,0.6193548387096774,0.08599468342591542 +flat_mae,patch,logistic,adni_ad_vs_cn,9,0.046415888336127774,train,0.8726287262872628,0.013975412953248036,0.7869541182974019,0.027441313819898994,0.7469800312268879,0.02705969002857491 +flat_mae,patch,logistic,adni_ad_vs_cn,9,0.046415888336127774,test,0.7560975609756098,0.05547461113578238,0.6117424242424243,0.09269487101370444,0.6016129032258064,0.0793008976779495 +flat_mae,patch,logistic,adni_ad_vs_cn,10,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,10,21.54434690031882,test,0.7804878048780488,0.06077234412812203,0.7119437939110069,0.07792224384442309,0.7193548387096774,0.0824930228185129 +flat_mae,patch,logistic,adni_ad_vs_cn,11,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,11,1291.5496650148827,test,0.7560975609756098,0.0517877653054861,0.6117424242424243,0.08742628314618349,0.6016129032258064,0.07522596525186581 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,12,166.81005372000556,test,0.7317073170731707,0.06215445825157913,0.6479313036690086,0.08166537194184627,0.6532258064516129,0.08587457276550892 +flat_mae,patch,logistic,adni_ad_vs_cn,13,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,13,21.54434690031882,test,0.7073170731707317,0.06145598096742618,0.5729166666666666,0.08760161998110641,0.5693548387096774,0.08163693232896031 +flat_mae,patch,logistic,adni_ad_vs_cn,14,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,14,1291.5496650148827,test,0.7317073170731707,0.06379316667338068,0.6232247284878863,0.08931414235862883,0.6193548387096774,0.08796256748092103 +flat_mae,patch,logistic,adni_ad_vs_cn,15,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,15,166.81005372000556,test,0.6341463414634146,0.07532204899524678,0.5684210526315789,0.0802867494848112,0.5887096774193548,0.08927068186699909 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,train,0.9701897018970189,0.008255694471854477,0.956306446925089,0.012761541257298522,0.936046511627907,0.01771134453554824 +flat_mae,patch,logistic,adni_ad_vs_cn,16,0.3593813663804626,test,0.7073170731707317,0.05713775790964418,0.5340909090909092,0.08200700212117182,0.535483870967742,0.07027068009311721 +flat_mae,patch,logistic,adni_ad_vs_cn,17,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,17,166.81005372000556,test,0.7073170731707317,0.06206080187275884,0.5729166666666666,0.08817582660208699,0.5693548387096774,0.08130318101068233 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,18,2.782559402207126,test,0.8292682926829268,0.05524163566124239,0.7602339181286549,0.08065917580272323,0.7516129032258064,0.08278831272737461 +flat_mae,patch,logistic,adni_ad_vs_cn,19,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,19,166.81005372000556,test,0.7560975609756098,0.06528708395502426,0.6693548387096775,0.08269650213230685,0.6693548387096775,0.08408280511820038 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,train,0.964769647696477,0.009200761918098523,0.9478932446964512,0.014448562637677928,0.9244186046511628,0.01973884388243228 +flat_mae,patch,logistic,adni_ad_vs_cn,20,0.3593813663804626,test,0.8048780487804879,0.06605913742337816,0.764367816091954,0.07292869583975863,0.8032258064516129,0.07520541214998643 +flat_mae,patch,logistic,adni_ad_vs_cn,21,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,21,166.81005372000556,test,0.8292682926829268,0.051010397745633755,0.7402714932126697,0.0835801166795464,0.717741935483871,0.08038232005691008 +flat_mae,patch,logistic,adni_ad_vs_cn,22,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,22,10000.0,test,0.7317073170731707,0.057623446876962796,0.5918552036199095,0.08852257322343907,0.5854838709677419,0.07800929691919588 +flat_mae,patch,logistic,adni_ad_vs_cn,23,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,23,166.81005372000556,test,0.7804878048780488,0.04989545286434201,0.6328358208955224,0.097097170512455,0.6177419354838709,0.08124056970807896 +flat_mae,patch,logistic,adni_ad_vs_cn,24,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,24,1291.5496650148827,test,0.6341463414634146,0.0777150793054827,0.5467943994104643,0.08688748755295128,0.5548387096774194,0.09381592866002762 +flat_mae,patch,logistic,adni_ad_vs_cn,25,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,25,2.782559402207126,test,0.7073170731707317,0.06467188957813268,0.603225806451613,0.08332475234594601,0.603225806451613,0.08313221068691766 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,train,0.8726287262872628,0.013010129701773565,0.781895695260133,0.027215937077340224,0.7388856931547374,0.026336018927725628 +flat_mae,patch,logistic,adni_ad_vs_cn,26,0.046415888336127774,test,0.7560975609756098,0.053810074268689716,0.6117424242424243,0.08920894065327675,0.6016129032258064,0.07682716328024813 +flat_mae,patch,logistic,adni_ad_vs_cn,27,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,27,1291.5496650148827,test,0.7073170731707317,0.06882155840036153,0.6272727272727273,0.08303191854411014,0.6370967741935484,0.08822599510506456 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,28,2.782559402207126,test,0.7804878048780488,0.035602939541359825,0.5886287625418061,0.08648499815970767,0.5838709677419355,0.06076914539680531 +flat_mae,patch,logistic,adni_ad_vs_cn,29,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,29,1291.5496650148827,test,0.6585365853658537,0.0725894963419575,0.5651515151515152,0.08194743151667143,0.5709677419354839,0.08654432552719638 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,30,166.81005372000556,test,0.6829268292682927,0.058880372577255376,0.5176470588235295,0.08193546236108663,0.5193548387096775,0.07287956931341633 +flat_mae,patch,logistic,adni_ad_vs_cn,31,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,31,21.54434690031882,test,0.7560975609756098,0.0558175620925314,0.6440972222222222,0.08738708613805182,0.635483870967742,0.08229713809486706 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.005994842503189409,train,0.7967479674796748,0.011091940630522504,0.5836154366960054,0.031190962979931836,0.5801421645163941,0.020600737325751926 +flat_mae,patch,logistic,adni_ad_vs_cn,32,0.005994842503189409,test,0.7804878048780488,0.04014071027098167,0.5886287625418061,0.0947394502946888,0.5838709677419355,0.067460427063301 +flat_mae,patch,logistic,adni_ad_vs_cn,33,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,33,166.81005372000556,test,0.6585365853658537,0.07081534163965285,0.5876436781609196,0.07878375764004292,0.6048387096774194,0.08759418602623312 +flat_mae,patch,logistic,adni_ad_vs_cn,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,34,21.54434690031882,test,0.7804878048780488,0.06142226652045022,0.7119437939110069,0.07883869630061623,0.7193548387096774,0.08334889690946709 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.3593813663804626,train,0.967479674796748,0.008794835879800603,0.9521193771626297,0.013683532717268129,0.9302325581395349,0.018867990928176856 +flat_mae,patch,logistic,adni_ad_vs_cn,35,0.3593813663804626,test,0.8536585365853658,0.052812938043127026,0.7864583333333333,0.08241136358519328,0.7677419354838709,0.084641375984893 +flat_mae,patch,logistic,adni_ad_vs_cn,36,0.046415888336127774,train,0.8888888888888888,0.013541846787360654,0.8202715706190526,0.025233194885393967,0.7818637521571206,0.026600875525255186 +flat_mae,patch,logistic,adni_ad_vs_cn,36,0.046415888336127774,test,0.7073170731707317,0.0635355507616715,0.5729166666666666,0.08759034746417757,0.5693548387096774,0.08199378164792864 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,37,166.81005372000556,test,0.7804878048780488,0.05649184871156797,0.6660633484162897,0.09355230700225356,0.6516129032258065,0.08611024677339886 +flat_mae,patch,logistic,adni_ad_vs_cn,38,0.046415888336127774,train,0.8644986449864499,0.013934514522798515,0.7720421073440744,0.027602692711290684,0.7335853397978469,0.026382903798211597 +flat_mae,patch,logistic,adni_ad_vs_cn,38,0.046415888336127774,test,0.7804878048780488,0.06311710691253934,0.6917293233082706,0.0881924435385117,0.685483870967742,0.08713256247998691 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.3593813663804626,train,0.9728997289972899,0.007428440845099974,0.9608013937282229,0.011106581152838873,0.9459076341523543,0.01504391324437844 +flat_mae,patch,logistic,adni_ad_vs_cn,39,0.3593813663804626,test,0.7073170731707317,0.06745075097623143,0.603225806451613,0.08885623427540171,0.603225806451613,0.08997614870680018 +flat_mae,patch,logistic,adni_ad_vs_cn,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,40,21.54434690031882,test,0.6097560975609756,0.0729259482775728,0.5030303030303029,0.080740142991839,0.5048387096774194,0.08553520375965697 +flat_mae,patch,logistic,adni_ad_vs_cn,41,0.3593813663804626,train,0.9701897018970189,0.008537882638986645,0.9566924513203521,0.012957562048425233,0.9400936806639822,0.01750339423257828 +flat_mae,patch,logistic,adni_ad_vs_cn,41,0.3593813663804626,test,0.7073170731707317,0.06727837346421568,0.6272727272727273,0.08165574952372759,0.6370967741935484,0.08890842129816236 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,42,166.81005372000556,test,0.7560975609756098,0.052572965640529865,0.6117424242424243,0.08653656535146192,0.6016129032258064,0.07477572787816002 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,43,166.81005372000556,test,0.8048780487804879,0.06015983074260747,0.7354838709677419,0.08346376402364207,0.7354838709677419,0.08703567002327024 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,train,0.8726287262872628,0.013688185654417222,0.7844652954700801,0.02817880485755508,0.7429328621908127,0.027252586748244764 +flat_mae,patch,logistic,adni_ad_vs_cn,44,0.046415888336127774,test,0.8536585365853658,0.03882200569413445,0.7415966386554622,0.09351776100265889,0.7,0.07958511167297562 +flat_mae,patch,logistic,adni_ad_vs_cn,45,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,45,21.54434690031882,test,0.7073170731707317,0.06144349270634595,0.5729166666666666,0.0879744817628684,0.5693548387096774,0.08143738847369304 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,46,21.54434690031882,test,0.7317073170731707,0.05736585365853659,0.5918552036199095,0.08714489579578186,0.5854838709677419,0.07834808607139672 +flat_mae,patch,logistic,adni_ad_vs_cn,47,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,47,2.782559402207126,test,0.7804878048780488,0.055772462016067836,0.6660633484162897,0.09271041346395878,0.6516129032258065,0.08480523784699338 +flat_mae,patch,logistic,adni_ad_vs_cn,48,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,48,21.54434690031882,test,0.7317073170731707,0.04213674235763818,0.4972129319955407,0.07908184835198535,0.5177419354838709,0.056496400574156835 +flat_mae,patch,logistic,adni_ad_vs_cn,49,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,49,166.81005372000556,test,0.6341463414634146,0.06998684332889551,0.5199063231850116,0.08215761805703045,0.5209677419354839,0.08430517874586049 +flat_mae,patch,logistic,adni_ad_vs_cn,50,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,50,1291.5496650148827,test,0.8292682926829268,0.04852368991581128,0.7402714932126697,0.0835323417321934,0.717741935483871,0.07818419318836851 +flat_mae,patch,logistic,adni_ad_vs_cn,51,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,51,21.54434690031882,test,0.7317073170731707,0.05913875234188181,0.6232247284878863,0.08494219804297647,0.6193548387096774,0.08270941793276189 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,train,0.8861788617886179,0.01378288558387189,0.8128260869565218,0.026754297984959402,0.7720026296326732,0.02760969394100752 +flat_mae,patch,logistic,adni_ad_vs_cn,52,0.046415888336127774,test,0.7073170731707317,0.046951669304148944,0.4831932773109243,0.07205570227798344,0.5016129032258064,0.05533262158479761 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,train,0.8780487804878049,0.013727571054767723,0.7936369850245448,0.028275912100208783,0.7505136001314816,0.027530051484730835 +flat_mae,patch,logistic,adni_ad_vs_cn,53,0.046415888336127774,test,0.7804878048780488,0.05589920392460984,0.6660633484162897,0.09012444799878958,0.6516129032258065,0.08205532631391353 +flat_mae,patch,logistic,adni_ad_vs_cn,54,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,54,2.782559402207126,test,0.6829268292682927,0.07254186671934153,0.6072218128224024,0.08341969521958849,0.6209677419354839,0.09012479375583468 +flat_mae,patch,logistic,adni_ad_vs_cn,55,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,55,2.782559402207126,test,0.7560975609756098,0.0615659230357066,0.6693548387096775,0.08644065391883698,0.6693548387096775,0.08756575647224016 +flat_mae,patch,logistic,adni_ad_vs_cn,56,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,56,10000.0,test,0.8048780487804879,0.045277411823290245,0.6893939393939394,0.0865894473016625,0.667741935483871,0.0763971208413039 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.3593813663804626,train,0.967479674796748,0.009309707940476523,0.9525462962962963,0.01433066559403618,0.9342797271756101,0.019251524167838787 +flat_mae,patch,logistic,adni_ad_vs_cn,57,0.3593813663804626,test,0.8292682926829268,0.055032173813777695,0.7602339181286549,0.08265525209716552,0.7516129032258064,0.0841637902545412 +flat_mae,patch,logistic,adni_ad_vs_cn,58,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,58,2.782559402207126,test,0.7073170731707317,0.06998425929930825,0.6272727272727273,0.08434872996849807,0.6370967741935484,0.08996986308930346 +flat_mae,patch,logistic,adni_ad_vs_cn,59,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,59,10000.0,test,0.7317073170731707,0.06968271767215509,0.6479313036690086,0.08695983042923502,0.6532258064516129,0.09094965932150151 +flat_mae,patch,logistic,adni_ad_vs_cn,60,0.3593813663804626,train,0.9728997289972899,0.008136256011103491,0.9604552469135802,0.012428676556289686,0.9418604651162791,0.017455107372658037 +flat_mae,patch,logistic,adni_ad_vs_cn,60,0.3593813663804626,test,0.7804878048780488,0.06253506333523189,0.6917293233082706,0.09105565271622072,0.685483870967742,0.09002305959644505 +flat_mae,patch,logistic,adni_ad_vs_cn,61,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,61,21.54434690031882,test,0.6341463414634146,0.07066706886696704,0.5467943994104643,0.08051806267017055,0.5548387096774194,0.08650847786764061 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.3593813663804626,train,0.9701897018970189,0.008090198471933872,0.9566924513203521,0.012247131990473658,0.9400936806639822,0.016727398529441804 +flat_mae,patch,logistic,adni_ad_vs_cn,62,0.3593813663804626,test,0.7073170731707317,0.06940789779287494,0.603225806451613,0.08845744805163287,0.603225806451613,0.0889861434454048 +flat_mae,patch,logistic,adni_ad_vs_cn,63,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,63,21.54434690031882,test,0.6097560975609756,0.05959408600069456,0.4305555555555556,0.06444964015873486,0.43709677419354837,0.06189246582341338 +flat_mae,patch,logistic,adni_ad_vs_cn,64,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,64,2.782559402207126,test,0.6097560975609756,0.05401002396662743,0.3787878787878788,0.021213683492701228,0.4032258064516129,0.03571630617147943 +flat_mae,patch,logistic,adni_ad_vs_cn,65,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,65,166.81005372000556,test,0.6585365853658537,0.06756610000817931,0.5651515151515152,0.07956409600310343,0.5709677419354839,0.08444222107021813 +flat_mae,patch,logistic,adni_ad_vs_cn,66,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,66,1291.5496650148827,test,0.6585365853658537,0.07106690967952649,0.5651515151515152,0.0831066997281248,0.5709677419354839,0.0878795922061928 +flat_mae,patch,logistic,adni_ad_vs_cn,67,0.3593813663804626,train,0.967479674796748,0.008539946858274569,0.9521193771626297,0.013283688541852596,0.9302325581395349,0.018321165062228563 +flat_mae,patch,logistic,adni_ad_vs_cn,67,0.3593813663804626,test,0.7560975609756098,0.05381960305329092,0.6117424242424243,0.08983198807454842,0.6016129032258064,0.0770420445504399 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,train,0.8699186991869918,0.014840425128409766,0.7836623021301544,0.02901635199783562,0.7452132467745911,0.028378270231649457 +flat_mae,patch,logistic,adni_ad_vs_cn,68,0.046415888336127774,test,0.7317073170731707,0.05187602482090847,0.5512437810945273,0.08660743341514252,0.5516129032258065,0.0690661659262654 +flat_mae,patch,logistic,adni_ad_vs_cn,69,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,69,166.81005372000556,test,0.8048780487804879,0.05704979717339302,0.7354838709677419,0.07811875597339732,0.7354838709677419,0.08262272743288937 +flat_mae,patch,logistic,adni_ad_vs_cn,70,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,70,21.54434690031882,test,0.7073170731707317,0.06146178859637746,0.5729166666666666,0.08919328421862575,0.5693548387096774,0.0821683974280873 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,train,0.8807588075880759,0.013684548509140932,0.8039130434782609,0.02614441635270589,0.7644218916920043,0.026514584788043413 +flat_mae,patch,logistic,adni_ad_vs_cn,71,0.046415888336127774,test,0.7317073170731707,0.05056624047512551,0.5512437810945273,0.08461850535039529,0.5516129032258065,0.06920723039404002 +flat_mae,patch,logistic,adni_ad_vs_cn,72,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,72,2.782559402207126,test,0.7560975609756098,0.06024362594979507,0.6440972222222222,0.09174898206726606,0.635483870967742,0.08675050642044663 +flat_mae,patch,logistic,adni_ad_vs_cn,73,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,73,2.782559402207126,test,0.7317073170731707,0.06603002579857245,0.6479313036690086,0.0830846923161951,0.6532258064516129,0.08699149018866463 +flat_mae,patch,logistic,adni_ad_vs_cn,74,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,74,1291.5496650148827,test,0.7073170731707317,0.06226490585307525,0.5729166666666666,0.08829091327929685,0.5693548387096774,0.08259900400767138 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.046415888336127774,train,0.8780487804878049,0.01417007737796018,0.7983288193643198,0.02768301543428987,0.7586079382036321,0.027649340287393284 +flat_mae,patch,logistic,adni_ad_vs_cn,75,0.046415888336127774,test,0.7560975609756098,0.052597039294376695,0.6117424242424243,0.09415111024533142,0.6016129032258064,0.08132260310168465 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,76,166.81005372000556,test,0.6097560975609756,0.06838688624721069,0.5030303030303029,0.07575332878522376,0.5048387096774194,0.08050616951429701 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.3593813663804626,train,0.962059620596206,0.009290818756494571,0.9436272370144041,0.014707998314169081,0.9186046511627908,0.01993204721596799 +flat_mae,patch,logistic,adni_ad_vs_cn,77,0.3593813663804626,test,0.7560975609756098,0.058230827473879185,0.6440972222222222,0.08833004054527922,0.635483870967742,0.08464305139728784 +flat_mae,patch,logistic,adni_ad_vs_cn,78,0.3593813663804626,train,0.9728997289972899,0.007998824834185111,0.9604552469135802,0.012249368241374035,0.9418604651162791,0.017160269557059883 +flat_mae,patch,logistic,adni_ad_vs_cn,78,0.3593813663804626,test,0.7317073170731707,0.07263603004977645,0.6676492262343405,0.08447603573226005,0.6870967741935483,0.09089378576868258 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.967479674796748,0.00863469411362052,0.9525462962962963,0.013169467729225665,0.9342797271756101,0.01766647865095302 +flat_mae,patch,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.8292682926829268,0.055934418129353625,0.7759562841530054,0.0723326720025382,0.7854838709677419,0.07710372616786962 +flat_mae,patch,logistic,adni_ad_vs_cn,80,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,80,1291.5496650148827,test,0.6097560975609756,0.07022696272709432,0.5030303030303029,0.08036808914965325,0.5048387096774194,0.08454108096332487 +flat_mae,patch,logistic,adni_ad_vs_cn,81,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,81,2.782559402207126,test,0.6829268292682927,0.052635276553791466,0.4696517412935323,0.07339336803892038,0.4854838709677419,0.06048175815664623 +flat_mae,patch,logistic,adni_ad_vs_cn,82,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,82,166.81005372000556,test,0.7560975609756098,0.061004168921623435,0.6440972222222222,0.08858880402870296,0.635483870967742,0.0846235526976731 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,83,166.81005372000556,test,0.7073170731707317,0.06932728508221643,0.6272727272727273,0.08282288330229787,0.6370967741935484,0.08673392008216842 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,train,0.8834688346883469,0.013224633476566473,0.8050856826976229,0.02679138204840767,0.7621415071082258,0.026927510390827372 +flat_mae,patch,logistic,adni_ad_vs_cn,84,0.046415888336127774,test,0.7317073170731707,0.049589654655981065,0.5512437810945273,0.08624050607606071,0.5516129032258065,0.06798108470163769 +flat_mae,patch,logistic,adni_ad_vs_cn,85,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,85,166.81005372000556,test,0.7804878048780488,0.06468520762634448,0.7280766396462786,0.07635429507489525,0.7532258064516129,0.08262074247044968 +flat_mae,patch,logistic,adni_ad_vs_cn,86,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,86,1291.5496650148827,test,0.6585365853658537,0.06212382331249842,0.5017361111111112,0.07628195218440215,0.5032258064516129,0.07140020862633005 +flat_mae,patch,logistic,adni_ad_vs_cn,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,87,166.81005372000556,test,0.8048780487804879,0.05122610875059263,0.6893939393939394,0.09494653645960115,0.667741935483871,0.08363635044348051 +flat_mae,patch,logistic,adni_ad_vs_cn,88,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,88,166.81005372000556,test,0.6829268292682927,0.06251519743844212,0.5547201336675021,0.08217664575583432,0.5532258064516129,0.0787094708484862 +flat_mae,patch,logistic,adni_ad_vs_cn,89,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,89,2.782559402207126,test,0.8048780487804879,0.05514232302162557,0.7354838709677419,0.07655479390226375,0.7354838709677419,0.0811895012255968 +flat_mae,patch,logistic,adni_ad_vs_cn,90,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,90,1291.5496650148827,test,0.7804878048780488,0.06069398377817163,0.6917293233082706,0.08365876403283498,0.685483870967742,0.08425068701338194 +flat_mae,patch,logistic,adni_ad_vs_cn,91,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,91,166.81005372000556,test,0.8048780487804879,0.05595817253244365,0.7354838709677419,0.07683172958184835,0.7354838709677419,0.08148292493001759 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,train,0.9701897018970189,0.00832337342978057,0.956306446925089,0.012830686376386638,0.936046511627907,0.017856539509238517 +flat_mae,patch,logistic,adni_ad_vs_cn,92,0.3593813663804626,test,0.7317073170731707,0.058630899630089856,0.5918552036199095,0.09041278423061992,0.5854838709677419,0.0804967734179277 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,93,166.81005372000556,test,0.6585365853658537,0.07173344471735099,0.6057692307692308,0.07740536197078791,0.6387096774193548,0.0894236545887049 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,train,0.8780487804878049,0.013299778210177806,0.8005668920623101,0.02510343597245223,0.7626551072397074,0.025176007429043974 +flat_mae,patch,logistic,adni_ad_vs_cn,94,0.046415888336127774,test,0.7073170731707317,0.0470152809717676,0.4831932773109243,0.07081371882112411,0.5016129032258064,0.05513411366000076 +flat_mae,patch,logistic,adni_ad_vs_cn,95,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,95,2.782559402207126,test,0.7073170731707317,0.0717171222763617,0.6272727272727273,0.08621365772943085,0.6370967741935484,0.09097149752027942 +flat_mae,patch,logistic,adni_ad_vs_cn,96,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,adni_ad_vs_cn,96,10000.0,test,0.6829268292682927,0.06229195713617327,0.5547201336675021,0.08129933042806847,0.5532258064516129,0.07832586510624061 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.3593813663804626,train,0.9728997289972899,0.007511819697560681,0.9604552469135802,0.011504428292664287,0.9418604651162791,0.016115473653487707 +flat_mae,patch,logistic,adni_ad_vs_cn,97,0.3593813663804626,test,0.7317073170731707,0.06870071485288087,0.6479313036690086,0.08698672436741924,0.6532258064516129,0.09051264587600753 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.046415888336127774,train,0.8780487804878049,0.01348738968265609,0.7983288193643198,0.026440326973362783,0.7586079382036321,0.026674859950663474 +flat_mae,patch,logistic,adni_ad_vs_cn,98,0.046415888336127774,test,0.7560975609756098,0.045137742787099325,0.569327731092437,0.09382216416068442,0.567741935483871,0.07101005893775467 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,train,0.8807588075880759,0.014356055928792799,0.80606784519828,0.02679344098052817,0.7684690607280795,0.02708794748911344 +flat_mae,patch,logistic,adni_ad_vs_cn,99,0.046415888336127774,test,0.7804878048780488,0.04674614065006001,0.6328358208955224,0.09198262718771437,0.6177419354838709,0.07417204983055678 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.046415888336127774,train,0.8915989159891599,0.013788979005344325,0.8236980410893455,0.02614123849311931,0.7836305366094174,0.02721418860261835 +flat_mae,patch,logistic,adni_ad_vs_cn,100,0.046415888336127774,test,0.6829268292682927,0.0501409316622612,0.4696517412935323,0.06735354689961845,0.4854838709677419,0.05543220353139025 diff --git a/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7c644645659c15cae5c7ca4231a4d50bd1f062a9 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:49:46 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adni_ad_vs_cn patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic +model: flat_mae +representation: patch +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:12:10 time: 4.4517 data: 3.5014 max mem: 2708 +extract (train) [ 20/164] eta: 0:00:59 time: 0.2136 data: 0.0839 max mem: 2863 +extract (train) [ 40/164] eta: 0:00:37 time: 0.1757 data: 0.0571 max mem: 2863 +extract (train) [ 60/164] eta: 0:00:26 time: 0.1704 data: 0.0543 max mem: 2863 +extract (train) [ 80/164] eta: 0:00:19 time: 0.1712 data: 0.0549 max mem: 2863 +extract (train) [100/164] eta: 0:00:14 time: 0.1754 data: 0.0594 max mem: 2863 +extract (train) [120/164] eta: 0:00:09 time: 0.1801 data: 0.0609 max mem: 2863 +extract (train) [140/164] eta: 0:00:05 time: 0.1636 data: 0.0524 max mem: 2863 +extract (train) [160/164] eta: 0:00:00 time: 0.1625 data: 0.0516 max mem: 2863 +extract (train) [163/164] eta: 0:00:00 time: 0.1647 data: 0.0530 max mem: 2863 +extract (train) Total time: 0:00:33 (0.2041 s / it) +extract (validation) [ 0/21] eta: 0:01:12 time: 3.4385 data: 3.3198 max mem: 2863 +extract (validation) [20/21] eta: 0:00:00 time: 0.1660 data: 0.0539 max mem: 2863 +extract (validation) Total time: 0:00:06 (0.3324 s / it) +extract (test) [ 0/21] eta: 0:01:11 time: 3.4240 data: 3.3038 max mem: 2863 +extract (test) [20/21] eta: 0:00:00 time: 0.1630 data: 0.0523 max mem: 2863 +extract (test) Total time: 0:00:06 (0.3284 s / it) +feature extraction time: 0:00:47 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|--------:|:--------|-------:|----------:|-------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.35938 | train | 0.9729 | 0.0076643 | 0.9608 | 0.011619 | 0.94253 | 0.016254 | +| flat_mae | patch | logistic | adni_ad_vs_cn | | 0.35938 | test | 0.7561 | 0.06191 | 0.6441 | 0.090982 | 0.6441 | 0.090483 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04479780737389527, "f1": 0.6554621848739496, "f1_std": 0.09749513950630406, "bacc": 0.6338709677419355, "bacc_std": 0.07780202008189852} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0625889206830291, "f1": 0.5547201336675021, "f1_std": 0.08584538056123783, "bacc": 0.5532258064516129, "bacc_std": 0.08272138278350397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05627101497849751, "f1": 0.5340909090909092, "f1_std": 0.08464319586922124, "bacc": 0.535483870967742, "bacc_std": 0.07183146674671478} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 21.54434690031882, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.057596433890533566, "f1": 0.8136363636363637, "f1_std": 0.06991638165114575, "bacc": 0.8354838709677419, "bacc_std": 0.07135650664503362} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 2.782559402207126, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.051994119467978744, "f1": 0.4564393939393939, "f1_std": 0.06424562752493705, "bacc": 0.4693548387096774, "bacc_std": 0.05598849889329649} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06691066789153917, "f1": 0.6479313036690086, "f1_std": 0.08710240835072448, "bacc": 0.6532258064516129, "bacc_std": 0.09057293621272056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05956453116572199, "f1": 0.6693548387096775, "f1_std": 0.0807272789617199, "bacc": 0.6693548387096775, "bacc_std": 0.0831174060241484} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06406828228355291, "f1": 0.6232247284878863, "f1_std": 0.08746532721276744, "bacc": 0.6193548387096774, "bacc_std": 0.08599468342591542} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05547461113578238, "f1": 0.6117424242424243, "f1_std": 0.09269487101370444, "bacc": 0.6016129032258064, "bacc_std": 0.0793008976779495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06077234412812203, "f1": 0.7119437939110069, "f1_std": 0.07792224384442309, "bacc": 0.7193548387096774, "bacc_std": 0.0824930228185129} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0517877653054861, "f1": 0.6117424242424243, "f1_std": 0.08742628314618349, "bacc": 0.6016129032258064, "bacc_std": 0.07522596525186581} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06215445825157913, "f1": 0.6479313036690086, "f1_std": 0.08166537194184627, "bacc": 0.6532258064516129, "bacc_std": 0.08587457276550892} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06145598096742618, "f1": 0.5729166666666666, "f1_std": 0.08760161998110641, "bacc": 0.5693548387096774, "bacc_std": 0.08163693232896031} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06379316667338068, "f1": 0.6232247284878863, "f1_std": 0.08931414235862883, "bacc": 0.6193548387096774, "bacc_std": 0.08796256748092103} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07532204899524678, "f1": 0.5684210526315789, "f1_std": 0.0802867494848112, "bacc": 0.5887096774193548, "bacc_std": 0.08927068186699909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05713775790964418, "f1": 0.5340909090909092, "f1_std": 0.08200700212117182, "bacc": 0.535483870967742, "bacc_std": 0.07027068009311721} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06206080187275884, "f1": 0.5729166666666666, "f1_std": 0.08817582660208699, "bacc": 0.5693548387096774, "bacc_std": 0.08130318101068233} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 2.782559402207126, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.05524163566124239, "f1": 0.7602339181286549, "f1_std": 0.08065917580272323, "bacc": 0.7516129032258064, "bacc_std": 0.08278831272737461} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06528708395502426, "f1": 0.6693548387096775, "f1_std": 0.08269650213230685, "bacc": 0.6693548387096775, "bacc_std": 0.08408280511820038} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06605913742337816, "f1": 0.764367816091954, "f1_std": 0.07292869583975863, "bacc": 0.8032258064516129, "bacc_std": 0.07520541214998643} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 166.81005372000556, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.051010397745633755, "f1": 0.7402714932126697, "f1_std": 0.0835801166795464, "bacc": 0.717741935483871, "bacc_std": 0.08038232005691008} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 10000.0, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.057623446876962796, "f1": 0.5918552036199095, "f1_std": 0.08852257322343907, "bacc": 0.5854838709677419, "bacc_std": 0.07800929691919588} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04989545286434201, "f1": 0.6328358208955224, "f1_std": 0.097097170512455, "bacc": 0.6177419354838709, "bacc_std": 0.08124056970807896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 1291.5496650148827, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.0777150793054827, "f1": 0.5467943994104643, "f1_std": 0.08688748755295128, "bacc": 0.5548387096774194, "bacc_std": 0.09381592866002762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06467188957813268, "f1": 0.603225806451613, "f1_std": 0.08332475234594601, "bacc": 0.603225806451613, "bacc_std": 0.08313221068691766} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.053810074268689716, "f1": 0.6117424242424243, "f1_std": 0.08920894065327675, "bacc": 0.6016129032258064, "bacc_std": 0.07682716328024813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06882155840036153, "f1": 0.6272727272727273, "f1_std": 0.08303191854411014, "bacc": 0.6370967741935484, "bacc_std": 0.08822599510506456} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.035602939541359825, "f1": 0.5886287625418061, "f1_std": 0.08648499815970767, "bacc": 0.5838709677419355, "bacc_std": 0.06076914539680531} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 1291.5496650148827, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0725894963419575, "f1": 0.5651515151515152, "f1_std": 0.08194743151667143, "bacc": 0.5709677419354839, "bacc_std": 0.08654432552719638} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.058880372577255376, "f1": 0.5176470588235295, "f1_std": 0.08193546236108663, "bacc": 0.5193548387096775, "bacc_std": 0.07287956931341633} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0558175620925314, "f1": 0.6440972222222222, "f1_std": 0.08738708613805182, "bacc": 0.635483870967742, "bacc_std": 0.08229713809486706} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04014071027098167, "f1": 0.5886287625418061, "f1_std": 0.0947394502946888, "bacc": 0.5838709677419355, "bacc_std": 0.067460427063301} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07081534163965285, "f1": 0.5876436781609196, "f1_std": 0.07878375764004292, "bacc": 0.6048387096774194, "bacc_std": 0.08759418602623312} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06142226652045022, "f1": 0.7119437939110069, "f1_std": 0.07883869630061623, "bacc": 0.7193548387096774, "bacc_std": 0.08334889690946709} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.052812938043127026, "f1": 0.7864583333333333, "f1_std": 0.08241136358519328, "bacc": 0.7677419354838709, "bacc_std": 0.084641375984893} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0635355507616715, "f1": 0.5729166666666666, "f1_std": 0.08759034746417757, "bacc": 0.5693548387096774, "bacc_std": 0.08199378164792864} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05649184871156797, "f1": 0.6660633484162897, "f1_std": 0.09355230700225356, "bacc": 0.6516129032258065, "bacc_std": 0.08611024677339886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06311710691253934, "f1": 0.6917293233082706, "f1_std": 0.0881924435385117, "bacc": 0.685483870967742, "bacc_std": 0.08713256247998691} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06745075097623143, "f1": 0.603225806451613, "f1_std": 0.08885623427540171, "bacc": 0.603225806451613, "bacc_std": 0.08997614870680018} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.0729259482775728, "f1": 0.5030303030303029, "f1_std": 0.080740142991839, "bacc": 0.5048387096774194, "bacc_std": 0.08553520375965697} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06727837346421568, "f1": 0.6272727272727273, "f1_std": 0.08165574952372759, "bacc": 0.6370967741935484, "bacc_std": 0.08890842129816236} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.052572965640529865, "f1": 0.6117424242424243, "f1_std": 0.08653656535146192, "bacc": 0.6016129032258064, "bacc_std": 0.07477572787816002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06015983074260747, "f1": 0.7354838709677419, "f1_std": 0.08346376402364207, "bacc": 0.7354838709677419, "bacc_std": 0.08703567002327024} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.03882200569413445, "f1": 0.7415966386554622, "f1_std": 0.09351776100265889, "bacc": 0.7, "bacc_std": 0.07958511167297562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06144349270634595, "f1": 0.5729166666666666, "f1_std": 0.0879744817628684, "bacc": 0.5693548387096774, "bacc_std": 0.08143738847369304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05736585365853659, "f1": 0.5918552036199095, "f1_std": 0.08714489579578186, "bacc": 0.5854838709677419, "bacc_std": 0.07834808607139672} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.055772462016067836, "f1": 0.6660633484162897, "f1_std": 0.09271041346395878, "bacc": 0.6516129032258065, "bacc_std": 0.08480523784699338} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.04213674235763818, "f1": 0.4972129319955407, "f1_std": 0.07908184835198535, "bacc": 0.5177419354838709, "bacc_std": 0.056496400574156835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06998684332889551, "f1": 0.5199063231850116, "f1_std": 0.08215761805703045, "bacc": 0.5209677419354839, "bacc_std": 0.08430517874586049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 1291.5496650148827, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.04852368991581128, "f1": 0.7402714932126697, "f1_std": 0.0835323417321934, "bacc": 0.717741935483871, "bacc_std": 0.07818419318836851} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05913875234188181, "f1": 0.6232247284878863, "f1_std": 0.08494219804297647, "bacc": 0.6193548387096774, "bacc_std": 0.08270941793276189} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.046951669304148944, "f1": 0.4831932773109243, "f1_std": 0.07205570227798344, "bacc": 0.5016129032258064, "bacc_std": 0.05533262158479761} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.05589920392460984, "f1": 0.6660633484162897, "f1_std": 0.09012444799878958, "bacc": 0.6516129032258065, "bacc_std": 0.08205532631391353} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07254186671934153, "f1": 0.6072218128224024, "f1_std": 0.08341969521958849, "bacc": 0.6209677419354839, "bacc_std": 0.09012479375583468} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.0615659230357066, "f1": 0.6693548387096775, "f1_std": 0.08644065391883698, "bacc": 0.6693548387096775, "bacc_std": 0.08756575647224016} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 10000.0, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.045277411823290245, "f1": 0.6893939393939394, "f1_std": 0.0865894473016625, "bacc": 0.667741935483871, "bacc_std": 0.0763971208413039} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.055032173813777695, "f1": 0.7602339181286549, "f1_std": 0.08265525209716552, "bacc": 0.7516129032258064, "bacc_std": 0.0841637902545412} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06998425929930825, "f1": 0.6272727272727273, "f1_std": 0.08434872996849807, "bacc": 0.6370967741935484, "bacc_std": 0.08996986308930346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 10000.0, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06968271767215509, "f1": 0.6479313036690086, "f1_std": 0.08695983042923502, "bacc": 0.6532258064516129, "bacc_std": 0.09094965932150151} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06253506333523189, "f1": 0.6917293233082706, "f1_std": 0.09105565271622072, "bacc": 0.685483870967742, "bacc_std": 0.09002305959644505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07066706886696704, "f1": 0.5467943994104643, "f1_std": 0.08051806267017055, "bacc": 0.5548387096774194, "bacc_std": 0.08650847786764061} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06940789779287494, "f1": 0.603225806451613, "f1_std": 0.08845744805163287, "bacc": 0.603225806451613, "bacc_std": 0.0889861434454048} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 21.54434690031882, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.05959408600069456, "f1": 0.4305555555555556, "f1_std": 0.06444964015873486, "bacc": 0.43709677419354837, "bacc_std": 0.06189246582341338} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 2.782559402207126, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.05401002396662743, "f1": 0.3787878787878788, "f1_std": 0.021213683492701228, "bacc": 0.4032258064516129, "bacc_std": 0.03571630617147943} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06756610000817931, "f1": 0.5651515151515152, "f1_std": 0.07956409600310343, "bacc": 0.5709677419354839, "bacc_std": 0.08444222107021813} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 1291.5496650148827, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07106690967952649, "f1": 0.5651515151515152, "f1_std": 0.0831066997281248, "bacc": 0.5709677419354839, "bacc_std": 0.0878795922061928} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05381960305329092, "f1": 0.6117424242424243, "f1_std": 0.08983198807454842, "bacc": 0.6016129032258064, "bacc_std": 0.0770420445504399} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05187602482090847, "f1": 0.5512437810945273, "f1_std": 0.08660743341514252, "bacc": 0.5516129032258065, "bacc_std": 0.0690661659262654} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05704979717339302, "f1": 0.7354838709677419, "f1_std": 0.07811875597339732, "bacc": 0.7354838709677419, "bacc_std": 0.08262272743288937} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 21.54434690031882, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06146178859637746, "f1": 0.5729166666666666, "f1_std": 0.08919328421862575, "bacc": 0.5693548387096774, "bacc_std": 0.0821683974280873} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05056624047512551, "f1": 0.5512437810945273, "f1_std": 0.08461850535039529, "bacc": 0.5516129032258065, "bacc_std": 0.06920723039404002} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06024362594979507, "f1": 0.6440972222222222, "f1_std": 0.09174898206726606, "bacc": 0.635483870967742, "bacc_std": 0.08675050642044663} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06603002579857245, "f1": 0.6479313036690086, "f1_std": 0.0830846923161951, "bacc": 0.6532258064516129, "bacc_std": 0.08699149018866463} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 1291.5496650148827, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06226490585307525, "f1": 0.5729166666666666, "f1_std": 0.08829091327929685, "bacc": 0.5693548387096774, "bacc_std": 0.08259900400767138} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.052597039294376695, "f1": 0.6117424242424243, "f1_std": 0.09415111024533142, "bacc": 0.6016129032258064, "bacc_std": 0.08132260310168465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 166.81005372000556, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06838688624721069, "f1": 0.5030303030303029, "f1_std": 0.07575332878522376, "bacc": 0.5048387096774194, "bacc_std": 0.08050616951429701} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.058230827473879185, "f1": 0.6440972222222222, "f1_std": 0.08833004054527922, "bacc": 0.635483870967742, "bacc_std": 0.08464305139728784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.07263603004977645, "f1": 0.6676492262343405, "f1_std": 0.08447603573226005, "bacc": 0.6870967741935483, "bacc_std": 0.09089378576868258} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.8292682926829268, "acc_std": 0.055934418129353625, "f1": 0.7759562841530054, "f1_std": 0.0723326720025382, "bacc": 0.7854838709677419, "bacc_std": 0.07710372616786962} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 1291.5496650148827, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07022696272709432, "f1": 0.5030303030303029, "f1_std": 0.08036808914965325, "bacc": 0.5048387096774194, "bacc_std": 0.08454108096332487} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.052635276553791466, "f1": 0.4696517412935323, "f1_std": 0.07339336803892038, "bacc": 0.4854838709677419, "bacc_std": 0.06048175815664623} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.061004168921623435, "f1": 0.6440972222222222, "f1_std": 0.08858880402870296, "bacc": 0.635483870967742, "bacc_std": 0.0846235526976731} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06932728508221643, "f1": 0.6272727272727273, "f1_std": 0.08282288330229787, "bacc": 0.6370967741935484, "bacc_std": 0.08673392008216842} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.049589654655981065, "f1": 0.5512437810945273, "f1_std": 0.08624050607606071, "bacc": 0.5516129032258065, "bacc_std": 0.06798108470163769} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06468520762634448, "f1": 0.7280766396462786, "f1_std": 0.07635429507489525, "bacc": 0.7532258064516129, "bacc_std": 0.08262074247044968} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 1291.5496650148827, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06212382331249842, "f1": 0.5017361111111112, "f1_std": 0.07628195218440215, "bacc": 0.5032258064516129, "bacc_std": 0.07140020862633005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05122610875059263, "f1": 0.6893939393939394, "f1_std": 0.09494653645960115, "bacc": 0.667741935483871, "bacc_std": 0.08363635044348051} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06251519743844212, "f1": 0.5547201336675021, "f1_std": 0.08217664575583432, "bacc": 0.5532258064516129, "bacc_std": 0.0787094708484862} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05514232302162557, "f1": 0.7354838709677419, "f1_std": 0.07655479390226375, "bacc": 0.7354838709677419, "bacc_std": 0.0811895012255968} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 1291.5496650148827, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06069398377817163, "f1": 0.6917293233082706, "f1_std": 0.08365876403283498, "bacc": 0.685483870967742, "bacc_std": 0.08425068701338194} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 166.81005372000556, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05595817253244365, "f1": 0.7354838709677419, "f1_std": 0.07683172958184835, "bacc": 0.7354838709677419, "bacc_std": 0.08148292493001759} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.058630899630089856, "f1": 0.5918552036199095, "f1_std": 0.09041278423061992, "bacc": 0.5854838709677419, "bacc_std": 0.0804967734179277} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07173344471735099, "f1": 0.6057692307692308, "f1_std": 0.07740536197078791, "bacc": 0.6387096774193548, "bacc_std": 0.0894236545887049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0470152809717676, "f1": 0.4831932773109243, "f1_std": 0.07081371882112411, "bacc": 0.5016129032258064, "bacc_std": 0.05513411366000076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0717171222763617, "f1": 0.6272727272727273, "f1_std": 0.08621365772943085, "bacc": 0.6370967741935484, "bacc_std": 0.09097149752027942} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 10000.0, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06229195713617327, "f1": 0.5547201336675021, "f1_std": 0.08129933042806847, "bacc": 0.5532258064516129, "bacc_std": 0.07832586510624061} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06870071485288087, "f1": 0.6479313036690086, "f1_std": 0.08698672436741924, "bacc": 0.6532258064516129, "bacc_std": 0.09051264587600753} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.045137742787099325, "f1": 0.569327731092437, "f1_std": 0.09382216416068442, "bacc": 0.567741935483871, "bacc_std": 0.07101005893775467} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.04674614065006001, "f1": 0.6328358208955224, "f1_std": 0.09198262718771437, "bacc": 0.6177419354838709, "bacc_std": 0.07417204983055678} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0501409316622612, "f1": 0.4696517412935323, "f1_std": 0.06735354689961845, "bacc": 0.4854838709677419, "bacc_std": 0.05543220353139025} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | adni_ad_vs_cn | train | 100 | 597.09 | 1972.1 | 0.97542 | 0.046797 | 0.95924 | 0.081054 | 0.95046 | 0.093819 | +| flat_mae | patch | logistic | adni_ad_vs_cn | test | 100 | 597.09 | 1972.1 | 0.73293 | 0.05958 | 0.61549 | 0.084298 | 0.61576 | 0.081408 | + + +done! total time: 0:04:47 diff --git a/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..02ca6ec4965992c03922487449f93a01634e559d --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adni_ad_vs_cn reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic +model: flat_mae +representation: reg +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b70ae41c928659eb26901aa04359132e1acd0350 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,adni_ad_vs_cn,,0.3593813663804626,train,0.978319783197832,0.007302040163000957,0.969172932330827,0.010667279029165564,0.9579970652971387,0.014406590278314532 +flat_mae,reg,logistic,adni_ad_vs_cn,,0.3593813663804626,test,0.6829268292682927,0.06748328719883186,0.5547201336675021,0.08341849617364556,0.5572916666666666,0.08586975837373469 +flat_mae,reg,logistic,adni_ad_vs_cn,1,0.3593813663804626,train,0.981029810298103,0.007023392732545779,0.9729123189697663,0.010277905441000644,0.9633494946174705,0.014076096633500394 +flat_mae,reg,logistic,adni_ad_vs_cn,1,0.3593813663804626,test,0.8048780487804879,0.05069079025363261,0.6893939393939394,0.09175212886034423,0.667741935483871,0.08194663475049041 +flat_mae,reg,logistic,adni_ad_vs_cn,2,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,2,1291.5496650148827,test,0.6829268292682927,0.06806330817911764,0.5839188134270101,0.08566432089559475,0.5870967741935484,0.0886064945954602 +flat_mae,reg,logistic,adni_ad_vs_cn,3,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,3,2.782559402207126,test,0.7073170731707317,0.048060318040321195,0.4831932773109243,0.07206495643337076,0.5016129032258064,0.05616159780168187 +flat_mae,reg,logistic,adni_ad_vs_cn,4,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,4,10000.0,test,0.7804878048780488,0.06039668589306007,0.6917293233082706,0.08248949859895109,0.685483870967742,0.08240649953403342 +flat_mae,reg,logistic,adni_ad_vs_cn,5,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,5,2.782559402207126,test,0.6829268292682927,0.060077661418756124,0.5176470588235295,0.08400428465214163,0.5193548387096775,0.07464398359680996 +flat_mae,reg,logistic,adni_ad_vs_cn,6,0.3593813663804626,train,0.981029810298103,0.006636579163187577,0.9729123189697663,0.009680398899527185,0.9633494946174705,0.013227935768838139 +flat_mae,reg,logistic,adni_ad_vs_cn,6,0.3593813663804626,test,0.7317073170731707,0.0493782641297884,0.5512437810945273,0.0834444659198743,0.5516129032258065,0.06654691029274706 +flat_mae,reg,logistic,adni_ad_vs_cn,7,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,7,2.782559402207126,test,0.7073170731707317,0.06794223672526103,0.603225806451613,0.09055394245282206,0.603225806451613,0.0907567466095545 +flat_mae,reg,logistic,adni_ad_vs_cn,8,0.046415888336127774,train,0.8780487804878049,0.013630610889468053,0.7936369850245448,0.027661266899486288,0.7505136001314816,0.02694526826079701 +flat_mae,reg,logistic,adni_ad_vs_cn,8,0.046415888336127774,test,0.7804878048780488,0.054581224368271175,0.6660633484162897,0.0882978481295122,0.6516129032258065,0.08032687350880968 +flat_mae,reg,logistic,adni_ad_vs_cn,9,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,9,1291.5496650148827,test,0.7560975609756098,0.07041435957603584,0.7054597701149425,0.07918886379394144,0.7370967741935484,0.08503930755447409 +flat_mae,reg,logistic,adni_ad_vs_cn,10,0.3593813663804626,train,0.981029810298103,0.006990390801720948,0.9731387984733936,0.010033246818725717,0.9673966636535458,0.012719629050898294 +flat_mae,reg,logistic,adni_ad_vs_cn,10,0.3593813663804626,test,0.7073170731707317,0.04798611736581039,0.4831932773109243,0.07482428053719127,0.5016129032258064,0.057296099952082624 +flat_mae,reg,logistic,adni_ad_vs_cn,11,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,11,2.782559402207126,test,0.7560975609756098,0.05258572785974313,0.6117424242424243,0.09014167895400273,0.6016129032258064,0.07659122484465825 +flat_mae,reg,logistic,adni_ad_vs_cn,12,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,12,166.81005372000556,test,0.6829268292682927,0.07044746925933264,0.6072218128224024,0.08251854145842454,0.6209677419354839,0.08902851903088395 +flat_mae,reg,logistic,adni_ad_vs_cn,13,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,13,166.81005372000556,test,0.7317073170731707,0.06484266410811415,0.6232247284878863,0.09005871309897895,0.6193548387096774,0.08801878169641715 +flat_mae,reg,logistic,adni_ad_vs_cn,14,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,14,166.81005372000556,test,0.7804878048780488,0.06402401393617634,0.7119437939110069,0.08121746809353826,0.7193548387096774,0.08515582607103138 +flat_mae,reg,logistic,adni_ad_vs_cn,15,0.005994842503189409,train,0.8130081300813008,0.011474852545895822,0.6228949745989899,0.03316244183302864,0.6069315473744761,0.0229136298689283 +flat_mae,reg,logistic,adni_ad_vs_cn,15,0.005994842503189409,test,0.7560975609756098,1.1102230246251565e-16,0.4305555555555556,1.6653345369377348e-16,0.5,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,16,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,16,166.81005372000556,test,0.7560975609756098,0.04499941172197934,0.569327731092437,0.08796278252921381,0.567741935483871,0.06606474695965217 +flat_mae,reg,logistic,adni_ad_vs_cn,17,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,17,10000.0,test,0.6829268292682927,0.06590117526906589,0.5547201336675021,0.08734488087187109,0.5532258064516129,0.08329626649788689 +flat_mae,reg,logistic,adni_ad_vs_cn,18,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,18,166.81005372000556,test,0.7804878048780488,0.06083181092735907,0.6917293233082706,0.08951183531081841,0.685483870967742,0.08969162216376936 +flat_mae,reg,logistic,adni_ad_vs_cn,19,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,19,21.54434690031882,test,0.6829268292682927,0.06804098215653342,0.5547201336675021,0.0859890043768733,0.5532258064516129,0.08244494110772342 +flat_mae,reg,logistic,adni_ad_vs_cn,20,0.3593813663804626,train,0.989159891598916,0.005222975265754609,0.9845864661654136,0.007590149962472053,0.9767441860465116,0.011205103913159643 +flat_mae,reg,logistic,adni_ad_vs_cn,20,0.3593813663804626,test,0.8048780487804879,0.06233365728447241,0.7354838709677419,0.0841245370470007,0.7354838709677419,0.0874810125972283 +flat_mae,reg,logistic,adni_ad_vs_cn,21,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,21,1291.5496650148827,test,0.7317073170731707,0.051433675374430596,0.5512437810945273,0.08879504686697719,0.5516129032258065,0.070951844187085 +flat_mae,reg,logistic,adni_ad_vs_cn,22,0.3593813663804626,train,0.978319783197832,0.007082457639768019,0.9689106074648244,0.010436565435122511,0.9575355411290984,0.014372691880913339 +flat_mae,reg,logistic,adni_ad_vs_cn,22,0.3593813663804626,test,0.8048780487804879,0.04140380219746612,0.6554621848739496,0.09106376774598174,0.6338709677419355,0.07195598319229343 +flat_mae,reg,logistic,adni_ad_vs_cn,23,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,23,1291.5496650148827,test,0.6341463414634146,0.07103100679445831,0.5199063231850116,0.08341993147364012,0.5209677419354839,0.08542658311683601 +flat_mae,reg,logistic,adni_ad_vs_cn,24,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,24,2.782559402207126,test,0.7560975609756098,0.06440892190296282,0.6693548387096775,0.08576872746913847,0.6693548387096775,0.08848575204096974 +flat_mae,reg,logistic,adni_ad_vs_cn,25,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,25,21.54434690031882,test,0.7560975609756098,0.06484926924487498,0.6693548387096775,0.085461612373221,0.6693548387096775,0.0874424204780693 +flat_mae,reg,logistic,adni_ad_vs_cn,26,0.3593813663804626,train,0.983739837398374,0.006280250271042171,0.9768796992481203,0.009053343909053468,0.9691634481058427,0.011957896427811032 +flat_mae,reg,logistic,adni_ad_vs_cn,26,0.3593813663804626,test,0.6585365853658537,0.06932108946329642,0.5370967741935484,0.08295448463493081,0.5370967741935484,0.08253174610720825 +flat_mae,reg,logistic,adni_ad_vs_cn,27,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,27,2.782559402207126,test,0.6097560975609756,0.06729508301132771,0.47096774193548385,0.07539093490100014,0.47096774193548385,0.07558540531318172 +flat_mae,reg,logistic,adni_ad_vs_cn,28,0.3593813663804626,train,0.981029810298103,0.007135097361185498,0.9729123189697663,0.010417741224358904,0.9633494946174705,0.014090133403400838 +flat_mae,reg,logistic,adni_ad_vs_cn,28,0.3593813663804626,test,0.7073170731707317,0.05172284626447957,0.5340909090909092,0.07921144007951922,0.535483870967742,0.06632737022996849 +flat_mae,reg,logistic,adni_ad_vs_cn,29,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,29,166.81005372000556,test,0.7317073170731707,0.064474649039976,0.6479313036690086,0.08291221312599424,0.6532258064516129,0.08665078711349444 +flat_mae,reg,logistic,adni_ad_vs_cn,30,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,30,166.81005372000556,test,0.6585365853658537,0.061050178793804546,0.5017361111111112,0.07860171803158197,0.5032258064516129,0.07196356778571733 +flat_mae,reg,logistic,adni_ad_vs_cn,31,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,31,166.81005372000556,test,0.7073170731707317,0.07073177460047263,0.6272727272727273,0.08775672569268889,0.6370967741935484,0.09474783988762744 +flat_mae,reg,logistic,adni_ad_vs_cn,32,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,32,2.782559402207126,test,0.8780487804878049,0.04449836738110267,0.8144796380090498,0.07656583876176262,0.7838709677419355,0.07828806302147555 +flat_mae,reg,logistic,adni_ad_vs_cn,33,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,33,166.81005372000556,test,0.6585365853658537,0.06627227381956909,0.5651515151515152,0.08122888204972668,0.5709677419354839,0.08551501629823263 +flat_mae,reg,logistic,adni_ad_vs_cn,34,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,34,21.54434690031882,test,0.7317073170731707,0.06886319193048956,0.6676492262343405,0.07945910968342276,0.6870967741935483,0.08576924975744053 +flat_mae,reg,logistic,adni_ad_vs_cn,35,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,35,21.54434690031882,test,0.7317073170731707,0.05112593077044717,0.5512437810945273,0.08736524779367069,0.5516129032258065,0.06985467380679324 +flat_mae,reg,logistic,adni_ad_vs_cn,36,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,36,166.81005372000556,test,0.6585365853658537,0.0675424118195974,0.5370967741935484,0.08164989060412585,0.5370967741935484,0.08175586681446664 +flat_mae,reg,logistic,adni_ad_vs_cn,37,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,37,166.81005372000556,test,0.5853658536585366,0.07103712027433903,0.4558938329430133,0.07471302965070004,0.45483870967741935,0.07820563517783868 +flat_mae,reg,logistic,adni_ad_vs_cn,38,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,38,2.782559402207126,test,0.7560975609756098,0.06538798314884507,0.6893939393939394,0.08023137466425113,0.7032258064516128,0.08543440437301777 +flat_mae,reg,logistic,adni_ad_vs_cn,39,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,39,2.782559402207126,test,0.6829268292682927,0.07198823355503854,0.6072218128224024,0.08401816127858142,0.6209677419354839,0.09263450158820587 +flat_mae,reg,logistic,adni_ad_vs_cn,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,40,21.54434690031882,test,0.6097560975609756,0.07388714322913534,0.5494505494505495,0.07697280766727974,0.5725806451612903,0.08915162515888504 +flat_mae,reg,logistic,adni_ad_vs_cn,41,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,41,21.54434690031882,test,0.6341463414634146,0.06915559365122981,0.5199063231850116,0.08003943103008346,0.5209677419354839,0.08263939259915412 +flat_mae,reg,logistic,adni_ad_vs_cn,42,0.046415888336127774,train,0.8753387533875339,0.015012203866733295,0.7949999999999999,0.028968716659157064,0.7568411537513353,0.028853845379654717 +flat_mae,reg,logistic,adni_ad_vs_cn,42,0.046415888336127774,test,0.8048780487804879,0.052456854597746454,0.6893939393939394,0.09117433151804834,0.667741935483871,0.08221835062819499 +flat_mae,reg,logistic,adni_ad_vs_cn,43,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,43,166.81005372000556,test,0.7317073170731707,0.06711307017253303,0.6479313036690086,0.08516645890461463,0.6532258064516129,0.08837096738868051 +flat_mae,reg,logistic,adni_ad_vs_cn,44,0.046415888336127774,train,0.8780487804878049,0.013785762687804147,0.7960199004975124,0.02785629012009669,0.7545607691675569,0.027358385246350814 +flat_mae,reg,logistic,adni_ad_vs_cn,44,0.046415888336127774,test,0.7804878048780488,0.03860293762882888,0.5886287625418061,0.09377197674805447,0.5838709677419355,0.06739633068809103 +flat_mae,reg,logistic,adni_ad_vs_cn,45,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,45,2.782559402207126,test,0.7804878048780488,0.06645347430700475,0.7119437939110069,0.08506471770693612,0.7193548387096774,0.0886581045980914 +flat_mae,reg,logistic,adni_ad_vs_cn,46,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,46,166.81005372000556,test,0.7317073170731707,0.05720468483163329,0.5918552036199095,0.08711308329207405,0.5854838709677419,0.07809478079027139 +flat_mae,reg,logistic,adni_ad_vs_cn,47,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,47,166.81005372000556,test,0.7560975609756098,0.05848688947390804,0.6440972222222222,0.08521735319913254,0.635483870967742,0.08111397641353174 +flat_mae,reg,logistic,adni_ad_vs_cn,48,0.046415888336127774,train,0.8834688346883469,0.013468732175865245,0.8072919829481278,0.026163653973985755,0.7661886761443011,0.026498040276387927 +flat_mae,reg,logistic,adni_ad_vs_cn,48,0.046415888336127774,test,0.6585365853658537,0.06368966625089588,0.5017361111111112,0.08289057801851836,0.5032258064516129,0.07744918907682409 +flat_mae,reg,logistic,adni_ad_vs_cn,49,0.3593813663804626,train,0.981029810298103,0.006801446749135937,0.9729123189697663,0.009938154335242933,0.9633494946174705,0.013596962275597608 +flat_mae,reg,logistic,adni_ad_vs_cn,49,0.3593813663804626,test,0.7804878048780488,0.048761240105081066,0.6328358208955224,0.09530498158106261,0.6177419354838709,0.07750289652537574 +flat_mae,reg,logistic,adni_ad_vs_cn,50,0.046415888336127774,train,0.8726287262872628,0.014434840739312192,0.7893656557805118,0.028658975533457774,0.7510272002629632,0.028154815836031973 +flat_mae,reg,logistic,adni_ad_vs_cn,50,0.046415888336127774,test,0.7560975609756098,0.046991487325080496,0.569327731092437,0.09278427326021584,0.567741935483871,0.06960953413474173 +flat_mae,reg,logistic,adni_ad_vs_cn,51,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,51,21.54434690031882,test,0.6097560975609756,0.07092922799312126,0.5287356321839081,0.07797354651625979,0.5387096774193548,0.08736959064461083 +flat_mae,reg,logistic,adni_ad_vs_cn,52,0.046415888336127774,train,0.8834688346883469,0.014263309017256066,0.8094305857484296,0.027262938108323666,0.7702358451803764,0.028058079614486024 +flat_mae,reg,logistic,adni_ad_vs_cn,52,0.046415888336127774,test,0.6829268292682927,0.057896068854596514,0.5176470588235295,0.08222877310634379,0.5193548387096775,0.07227715322459664 +flat_mae,reg,logistic,adni_ad_vs_cn,53,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,53,21.54434690031882,test,0.7560975609756098,0.06694508390740446,0.6893939393939394,0.08237644293878948,0.7032258064516128,0.08804493555213026 +flat_mae,reg,logistic,adni_ad_vs_cn,54,0.3593813663804626,train,0.978319783197832,0.007475469144795568,0.9689106074648244,0.011029619200316362,0.9575355411290984,0.014976889747065134 +flat_mae,reg,logistic,adni_ad_vs_cn,54,0.3593813663804626,test,0.7560975609756098,0.05701391545598016,0.6440972222222222,0.08554351958075973,0.635483870967742,0.08083277531445039 +flat_mae,reg,logistic,adni_ad_vs_cn,55,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,55,2.782559402207126,test,0.7317073170731707,0.05815687823993917,0.5918552036199095,0.08913324520533054,0.5854838709677419,0.07898940740903419 +flat_mae,reg,logistic,adni_ad_vs_cn,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,56,21.54434690031882,test,0.6829268292682927,0.054025441822062,0.4696517412935323,0.06903693382394868,0.4854838709677419,0.05828171955722778 +flat_mae,reg,logistic,adni_ad_vs_cn,57,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,57,166.81005372000556,test,0.6341463414634146,0.07490400757624094,0.5467943994104643,0.08439397528204892,0.5548387096774194,0.09096309665558762 +flat_mae,reg,logistic,adni_ad_vs_cn,58,0.3593813663804626,train,0.981029810298103,0.0070353785879715075,0.9726796763445977,0.010475534447762697,0.9593023255813953,0.01509334127303187 +flat_mae,reg,logistic,adni_ad_vs_cn,58,0.3593813663804626,test,0.7317073170731707,0.05825950683642387,0.5918552036199095,0.08865272200355369,0.5854838709677419,0.0790552477425095 +flat_mae,reg,logistic,adni_ad_vs_cn,59,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,59,166.81005372000556,test,0.7073170731707317,0.06965831454497645,0.603225806451613,0.09016671625101351,0.603225806451613,0.09173354165130539 +flat_mae,reg,logistic,adni_ad_vs_cn,60,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,60,166.81005372000556,test,0.7804878048780488,0.06328111647686062,0.7119437939110069,0.08237452413667236,0.7193548387096774,0.08560401119439577 +flat_mae,reg,logistic,adni_ad_vs_cn,61,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,61,166.81005372000556,test,0.7073170731707317,0.06272668113233358,0.5729166666666666,0.08909079650920727,0.5693548387096774,0.08305425999946224 +flat_mae,reg,logistic,adni_ad_vs_cn,62,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,62,2.782559402207126,test,0.7317073170731707,0.056695666256587944,0.5918552036199095,0.08872864547192694,0.5854838709677419,0.08020838436196241 +flat_mae,reg,logistic,adni_ad_vs_cn,63,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,63,166.81005372000556,test,0.7073170731707317,0.070737829844353,0.646551724137931,0.07995422304543322,0.6709677419354838,0.08761877029146287 +flat_mae,reg,logistic,adni_ad_vs_cn,64,0.046415888336127774,train,0.8807588075880759,0.013021158786996187,0.8039130434782609,0.025196246336372408,0.7644218916920043,0.025506834670084102 +flat_mae,reg,logistic,adni_ad_vs_cn,64,0.046415888336127774,test,0.7560975609756098,0.053801914873184725,0.6117424242424243,0.09350532752808359,0.6016129032258064,0.07989098555757766 +flat_mae,reg,logistic,adni_ad_vs_cn,65,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,65,2.782559402207126,test,0.7317073170731707,0.06583999858326531,0.6479313036690086,0.08370836811388362,0.6532258064516129,0.08745115859997891 +flat_mae,reg,logistic,adni_ad_vs_cn,66,0.046415888336127774,train,0.8563685636856369,0.013997660137244117,0.747967060582239,0.030811934117828267,0.7080491412605802,0.027935678869625617 +flat_mae,reg,logistic,adni_ad_vs_cn,66,0.046415888336127774,test,0.8780487804878049,0.03756097560975611,0.7960199004975124,0.08288655444914525,0.75,0.07700000000000001 +flat_mae,reg,logistic,adni_ad_vs_cn,67,0.046415888336127774,train,0.8726287262872628,0.012807691292747543,0.7844652954700801,0.02648499219802697,0.7429328621908127,0.025877451213166168 +flat_mae,reg,logistic,adni_ad_vs_cn,67,0.046415888336127774,test,0.8536585365853658,0.03795849199866364,0.7415966386554622,0.09056680974905587,0.7,0.07781490859726047 +flat_mae,reg,logistic,adni_ad_vs_cn,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,68,2.782559402207126,test,0.5365853658536586,0.06352446399051762,0.3918813427010148,0.05786250718726969,0.3887096774193548,0.06230082728282884 +flat_mae,reg,logistic,adni_ad_vs_cn,69,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,69,166.81005372000556,test,0.7560975609756098,0.060587074324915426,0.6440972222222222,0.08914285212523629,0.635483870967742,0.08409751902116427 +flat_mae,reg,logistic,adni_ad_vs_cn,70,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,70,166.81005372000556,test,0.7073170731707317,0.07355579977909409,0.646551724137931,0.08225562353243862,0.6709677419354838,0.09044376110598717 +flat_mae,reg,logistic,adni_ad_vs_cn,71,0.3593813663804626,train,0.986449864498645,0.00567141791459655,0.9809709458832265,0.00800563435416763,0.97902457063029,0.009819105861984409 +flat_mae,reg,logistic,adni_ad_vs_cn,71,0.3593813663804626,test,0.6341463414634146,0.04766669925354119,0.3880597014925373,0.01804481349664766,0.41935483870967744,0.03152152692572884 +flat_mae,reg,logistic,adni_ad_vs_cn,72,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,72,2.782559402207126,test,0.7073170731707317,0.04631452362008984,0.4831932773109243,0.06981620022846667,0.5016129032258064,0.05370851253217049 +flat_mae,reg,logistic,adni_ad_vs_cn,73,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,73,10000.0,test,0.7073170731707317,0.06960705551361464,0.646551724137931,0.07921824533154806,0.6709677419354838,0.08952597307105026 +flat_mae,reg,logistic,adni_ad_vs_cn,74,0.046415888336127774,train,0.8888888888888888,0.013652099829709613,0.8202715706190526,0.025235763631033248,0.7818637521571206,0.026253267355312197 +flat_mae,reg,logistic,adni_ad_vs_cn,74,0.046415888336127774,test,0.7560975609756098,1.1102230246251565e-16,0.4305555555555556,1.6653345369377348e-16,0.5,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,75,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,75,166.81005372000556,test,0.7073170731707317,0.06280654035214289,0.5729166666666666,0.08939505641047726,0.5693548387096774,0.08327319549800845 +flat_mae,reg,logistic,adni_ad_vs_cn,76,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,76,2.782559402207126,test,0.6341463414634146,0.06315660450376487,0.48621553884711777,0.07461042969787691,0.48709677419354835,0.0725359187639208 +flat_mae,reg,logistic,adni_ad_vs_cn,77,0.046415888336127774,train,0.8780487804878049,0.01391801533157814,0.7960199004975124,0.02824868742117542,0.7545607691675569,0.02816733971249686 +flat_mae,reg,logistic,adni_ad_vs_cn,77,0.046415888336127774,test,0.8048780487804879,0.04097151547489229,0.6554621848739496,0.09413618069274811,0.6338709677419355,0.07507016842464714 +flat_mae,reg,logistic,adni_ad_vs_cn,78,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,78,21.54434690031882,test,0.7804878048780488,0.06173297451745023,0.7119437939110069,0.07753094783855281,0.7193548387096774,0.08104444150241968 +flat_mae,reg,logistic,adni_ad_vs_cn,79,0.3593813663804626,train,0.986449864498645,0.005856227480057139,0.9808134274809954,0.0084219540083481,0.9749774015942148,0.011474341315585591 +flat_mae,reg,logistic,adni_ad_vs_cn,79,0.3593813663804626,test,0.8048780487804879,0.0605723248994454,0.7354838709677419,0.08158592916248399,0.7354838709677419,0.08364228849426437 +flat_mae,reg,logistic,adni_ad_vs_cn,80,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,80,1291.5496650148827,test,0.5853658536585366,0.07555466128020145,0.4863669859985261,0.07924411222875788,0.4887096774193548,0.08624349673110378 +flat_mae,reg,logistic,adni_ad_vs_cn,81,0.3593813663804626,train,0.9728997289972899,0.008259100928293685,0.9608013937282229,0.012439070613503512,0.9459076341523543,0.016951964199178222 +flat_mae,reg,logistic,adni_ad_vs_cn,81,0.3593813663804626,test,0.7560975609756098,0.05696464562063137,0.6117424242424243,0.09380473843864907,0.6016129032258064,0.08027681193756714 +flat_mae,reg,logistic,adni_ad_vs_cn,82,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,82,1291.5496650148827,test,0.6341463414634146,0.060456246684988384,0.44343891402714936,0.06794765267540193,0.45322580645161287,0.06302983280241933 +flat_mae,reg,logistic,adni_ad_vs_cn,83,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,83,21.54434690031882,test,0.6341463414634146,0.06462381877913939,0.48621553884711777,0.07723999868874148,0.48709677419354835,0.0740263768132677 +flat_mae,reg,logistic,adni_ad_vs_cn,84,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,84,1291.5496650148827,test,0.6829268292682927,0.06523720503578022,0.5547201336675021,0.08339920873847209,0.5532258064516129,0.08043320087059375 +flat_mae,reg,logistic,adni_ad_vs_cn,85,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,85,10000.0,test,0.7560975609756098,0.07153621531175856,0.7054597701149425,0.08122654894620172,0.7370967741935484,0.08943507117621993 +flat_mae,reg,logistic,adni_ad_vs_cn,86,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,86,10000.0,test,0.6585365853658537,0.06641000763155236,0.5370967741935484,0.08027297661532769,0.5370967741935484,0.08062281393595173 +flat_mae,reg,logistic,adni_ad_vs_cn,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,87,166.81005372000556,test,0.7560975609756098,0.058792610833655924,0.6440972222222222,0.08782824114979185,0.635483870967742,0.08219833751936184 +flat_mae,reg,logistic,adni_ad_vs_cn,88,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,88,166.81005372000556,test,0.6585365853658537,0.06719060230030455,0.5370967741935484,0.08301575858360248,0.5370967741935484,0.08275299624241272 +flat_mae,reg,logistic,adni_ad_vs_cn,89,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,89,21.54434690031882,test,0.6829268292682927,0.07095681588406093,0.6259649122807017,0.07750429266522546,0.6548387096774193,0.08746970006076438 +flat_mae,reg,logistic,adni_ad_vs_cn,90,0.3593813663804626,train,0.978319783197832,0.007544222875862343,0.9689106074648244,0.011145966747149634,0.9575355411290984,0.015067712275355784 +flat_mae,reg,logistic,adni_ad_vs_cn,90,0.3593813663804626,test,0.7560975609756098,0.06093217965532727,0.6440972222222222,0.09103053125442215,0.635483870967742,0.08579752706438691 +flat_mae,reg,logistic,adni_ad_vs_cn,91,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,91,21.54434690031882,test,0.5365853658536586,0.07117089887808649,0.42593957258658804,0.07053260655224582,0.42258064516129035,0.07699005868497788 +flat_mae,reg,logistic,adni_ad_vs_cn,92,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,92,21.54434690031882,test,0.7804878048780488,0.06453293502203353,0.6917293233082706,0.0892138212339983,0.685483870967742,0.08883383095044332 +flat_mae,reg,logistic,adni_ad_vs_cn,93,0.3593813663804626,train,0.991869918699187,0.004518011014598034,0.9884880564885973,0.006498682127184174,0.9825581395348837,0.009692709676666768 +flat_mae,reg,logistic,adni_ad_vs_cn,93,0.3593813663804626,test,0.6097560975609756,0.06660993024956915,0.5030303030303029,0.0752151207968464,0.5048387096774194,0.08051387739821049 +flat_mae,reg,logistic,adni_ad_vs_cn,94,0.3593813663804626,train,0.981029810298103,0.006841755263674737,0.9729123189697663,0.009991370736257063,0.9633494946174705,0.013408427498368871 +flat_mae,reg,logistic,adni_ad_vs_cn,94,0.3593813663804626,test,0.6829268292682927,0.06245038006494276,0.5176470588235295,0.08244751589367243,0.5193548387096775,0.07435924519865737 +flat_mae,reg,logistic,adni_ad_vs_cn,95,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,95,166.81005372000556,test,0.6585365853658537,0.0743818467871655,0.5876436781609196,0.08258436971723092,0.6048387096774194,0.09228655977716735 +flat_mae,reg,logistic,adni_ad_vs_cn,96,0.046415888336127774,train,0.8915989159891599,0.013460298396935366,0.825597882597599,0.02496159974128616,0.7876777056454927,0.026520268548611267 +flat_mae,reg,logistic,adni_ad_vs_cn,96,0.046415888336127774,test,0.7804878048780488,0.03759466338525411,0.5886287625418061,0.09151954698084103,0.5838709677419355,0.06472790170479109 +flat_mae,reg,logistic,adni_ad_vs_cn,97,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,97,166.81005372000556,test,0.6585365853658537,0.07535060229296875,0.6057692307692308,0.08046861274230321,0.6387096774193548,0.09261560517850459 +flat_mae,reg,logistic,adni_ad_vs_cn,98,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,98,2.782559402207126,test,0.7073170731707317,0.0587997944206809,0.5729166666666666,0.08418432011672541,0.5693548387096774,0.07871995246259235 +flat_mae,reg,logistic,adni_ad_vs_cn,99,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,adni_ad_vs_cn,99,166.81005372000556,test,0.6829268292682927,0.0603854365870977,0.5176470588235295,0.08285733635255953,0.5193548387096775,0.07339655550529346 +flat_mae,reg,logistic,adni_ad_vs_cn,100,0.3593813663804626,train,0.983739837398374,0.006508805860281758,0.9768796992481203,0.009411946590487597,0.9691634481058427,0.012713807063594842 +flat_mae,reg,logistic,adni_ad_vs_cn,100,0.3593813663804626,test,0.6585365853658537,0.06322092365181371,0.5370967741935484,0.0824302671175155,0.5370967741935484,0.0827817532941888 diff --git a/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f8226580ea4fa8267f2384bfddc9ded9e5f2c81e --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic/log.txt @@ -0,0 +1,240 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:23:58 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (adni_ad_vs_cn reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic +model: flat_mae +representation: reg +dataset: adni_ad_vs_cn +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/adni_ad_vs_cn__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: adni_ad_vs_cn (flat) +train (n=328): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 525 +}), + labels=[0 1], + counts=[251 77] +) + +validation (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[31 10] +) + +test (n=41): +ADNIDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'bold', 'mean', 'std'], + num_rows: 66 +}), + labels=[0 1], + counts=[32 9] +) + +extracting features for all splits +extract (train) [ 0/164] eta: 0:12:22 time: 4.5283 data: 3.5070 max mem: 2708 +extract (train) [ 20/164] eta: 0:00:58 time: 0.2022 data: 0.0731 max mem: 2863 +extract (train) [ 40/164] eta: 0:00:35 time: 0.1640 data: 0.0527 max mem: 2863 +extract (train) [ 60/164] eta: 0:00:26 time: 0.1884 data: 0.0633 max mem: 2863 +extract (train) [ 80/164] eta: 0:00:19 time: 0.1666 data: 0.0538 max mem: 2863 +extract (train) [100/164] eta: 0:00:14 time: 0.1696 data: 0.0546 max mem: 2863 +extract (train) [120/164] eta: 0:00:09 time: 0.1713 data: 0.0565 max mem: 2863 +extract (train) [140/164] eta: 0:00:04 time: 0.1567 data: 0.0493 max mem: 2863 +extract (train) [160/164] eta: 0:00:00 time: 0.1580 data: 0.0494 max mem: 2863 +extract (train) [163/164] eta: 0:00:00 time: 0.1596 data: 0.0496 max mem: 2863 +extract (train) Total time: 0:00:33 (0.2014 s / it) +extract (validation) [ 0/21] eta: 0:01:15 time: 3.6010 data: 3.4949 max mem: 2863 +extract (validation) [20/21] eta: 0:00:00 time: 0.1442 data: 0.0426 max mem: 2863 +extract (validation) Total time: 0:00:06 (0.3240 s / it) +extract (test) [ 0/21] eta: 0:01:12 time: 3.4493 data: 3.3452 max mem: 2863 +extract (test) [20/21] eta: 0:00:00 time: 0.1446 data: 0.0429 max mem: 2863 +extract (test) Total time: 0:00:06 (0.3176 s / it) +feature extraction time: 0:00:46 +train features: (328, 768) +validation features: (41, 768) +test features: (41, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adni_ad_vs_cn | | 0.35938 | train | 0.97832 | 0.007302 | 0.96917 | 0.010667 | 0.958 | 0.014407 | +| flat_mae | reg | logistic | adni_ad_vs_cn | | 0.35938 | test | 0.68293 | 0.067483 | 0.55472 | 0.083418 | 0.55729 | 0.08587 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.05069079025363261, "f1": 0.6893939393939394, "f1_std": 0.09175212886034423, "bacc": 0.667741935483871, "bacc_std": 0.08194663475049041} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 2, "C": 1291.5496650148827, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06806330817911764, "f1": 0.5839188134270101, "f1_std": 0.08566432089559475, "bacc": 0.5870967741935484, "bacc_std": 0.0886064945954602} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.048060318040321195, "f1": 0.4831932773109243, "f1_std": 0.07206495643337076, "bacc": 0.5016129032258064, "bacc_std": 0.05616159780168187} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 4, "C": 10000.0, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06039668589306007, "f1": 0.6917293233082706, "f1_std": 0.08248949859895109, "bacc": 0.685483870967742, "bacc_std": 0.08240649953403342} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 5, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.060077661418756124, "f1": 0.5176470588235295, "f1_std": 0.08400428465214163, "bacc": 0.5193548387096775, "bacc_std": 0.07464398359680996} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.0493782641297884, "f1": 0.5512437810945273, "f1_std": 0.0834444659198743, "bacc": 0.5516129032258065, "bacc_std": 0.06654691029274706} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06794223672526103, "f1": 0.603225806451613, "f1_std": 0.09055394245282206, "bacc": 0.603225806451613, "bacc_std": 0.0907567466095545} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 8, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.054581224368271175, "f1": 0.6660633484162897, "f1_std": 0.0882978481295122, "bacc": 0.6516129032258065, "bacc_std": 0.08032687350880968} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 9, "C": 1291.5496650148827, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.07041435957603584, "f1": 0.7054597701149425, "f1_std": 0.07918886379394144, "bacc": 0.7370967741935484, "bacc_std": 0.08503930755447409} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 10, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.04798611736581039, "f1": 0.4831932773109243, "f1_std": 0.07482428053719127, "bacc": 0.5016129032258064, "bacc_std": 0.057296099952082624} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 11, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05258572785974313, "f1": 0.6117424242424243, "f1_std": 0.09014167895400273, "bacc": 0.6016129032258064, "bacc_std": 0.07659122484465825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 12, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07044746925933264, "f1": 0.6072218128224024, "f1_std": 0.08251854145842454, "bacc": 0.6209677419354839, "bacc_std": 0.08902851903088395} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 13, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06484266410811415, "f1": 0.6232247284878863, "f1_std": 0.09005871309897895, "bacc": 0.6193548387096774, "bacc_std": 0.08801878169641715} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 14, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06402401393617634, "f1": 0.7119437939110069, "f1_std": 0.08121746809353826, "bacc": 0.7193548387096774, "bacc_std": 0.08515582607103138} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.7560975609756098, "acc_std": 1.1102230246251565e-16, "f1": 0.4305555555555556, "f1_std": 1.6653345369377348e-16, "bacc": 0.5, "bacc_std": 0.0} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 16, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.04499941172197934, "f1": 0.569327731092437, "f1_std": 0.08796278252921381, "bacc": 0.567741935483871, "bacc_std": 0.06606474695965217} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 17, "C": 10000.0, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06590117526906589, "f1": 0.5547201336675021, "f1_std": 0.08734488087187109, "bacc": 0.5532258064516129, "bacc_std": 0.08329626649788689} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 18, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06083181092735907, "f1": 0.6917293233082706, "f1_std": 0.08951183531081841, "bacc": 0.685483870967742, "bacc_std": 0.08969162216376936} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 19, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06804098215653342, "f1": 0.5547201336675021, "f1_std": 0.0859890043768733, "bacc": 0.5532258064516129, "bacc_std": 0.08244494110772342} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.06233365728447241, "f1": 0.7354838709677419, "f1_std": 0.0841245370470007, "bacc": 0.7354838709677419, "bacc_std": 0.0874810125972283} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 21, "C": 1291.5496650148827, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.051433675374430596, "f1": 0.5512437810945273, "f1_std": 0.08879504686697719, "bacc": 0.5516129032258065, "bacc_std": 0.070951844187085} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04140380219746612, "f1": 0.6554621848739496, "f1_std": 0.09106376774598174, "bacc": 0.6338709677419355, "bacc_std": 0.07195598319229343} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 23, "C": 1291.5496650148827, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07103100679445831, "f1": 0.5199063231850116, "f1_std": 0.08341993147364012, "bacc": 0.5209677419354839, "bacc_std": 0.08542658311683601} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 24, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06440892190296282, "f1": 0.6693548387096775, "f1_std": 0.08576872746913847, "bacc": 0.6693548387096775, "bacc_std": 0.08848575204096974} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 25, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06484926924487498, "f1": 0.6693548387096775, "f1_std": 0.085461612373221, "bacc": 0.6693548387096775, "bacc_std": 0.0874424204780693} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06932108946329642, "f1": 0.5370967741935484, "f1_std": 0.08295448463493081, "bacc": 0.5370967741935484, "bacc_std": 0.08253174610720825} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 27, "C": 2.782559402207126, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06729508301132771, "f1": 0.47096774193548385, "f1_std": 0.07539093490100014, "bacc": 0.47096774193548385, "bacc_std": 0.07558540531318172} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.05172284626447957, "f1": 0.5340909090909092, "f1_std": 0.07921144007951922, "bacc": 0.535483870967742, "bacc_std": 0.06632737022996849} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 29, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.064474649039976, "f1": 0.6479313036690086, "f1_std": 0.08291221312599424, "bacc": 0.6532258064516129, "bacc_std": 0.08665078711349444} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 30, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.061050178793804546, "f1": 0.5017361111111112, "f1_std": 0.07860171803158197, "bacc": 0.5032258064516129, "bacc_std": 0.07196356778571733} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 31, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07073177460047263, "f1": 0.6272727272727273, "f1_std": 0.08775672569268889, "bacc": 0.6370967741935484, "bacc_std": 0.09474783988762744} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 32, "C": 2.782559402207126, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.04449836738110267, "f1": 0.8144796380090498, "f1_std": 0.07656583876176262, "bacc": 0.7838709677419355, "bacc_std": 0.07828806302147555} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 33, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06627227381956909, "f1": 0.5651515151515152, "f1_std": 0.08122888204972668, "bacc": 0.5709677419354839, "bacc_std": 0.08551501629823263} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 34, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06886319193048956, "f1": 0.6676492262343405, "f1_std": 0.07945910968342276, "bacc": 0.6870967741935483, "bacc_std": 0.08576924975744053} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 35, "C": 21.54434690031882, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05112593077044717, "f1": 0.5512437810945273, "f1_std": 0.08736524779367069, "bacc": 0.5516129032258065, "bacc_std": 0.06985467380679324} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 36, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0675424118195974, "f1": 0.5370967741935484, "f1_std": 0.08164989060412585, "bacc": 0.5370967741935484, "bacc_std": 0.08175586681446664} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 37, "C": 166.81005372000556, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07103712027433903, "f1": 0.4558938329430133, "f1_std": 0.07471302965070004, "bacc": 0.45483870967741935, "bacc_std": 0.07820563517783868} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 38, "C": 2.782559402207126, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06538798314884507, "f1": 0.6893939393939394, "f1_std": 0.08023137466425113, "bacc": 0.7032258064516128, "bacc_std": 0.08543440437301777} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 39, "C": 2.782559402207126, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07198823355503854, "f1": 0.6072218128224024, "f1_std": 0.08401816127858142, "bacc": 0.6209677419354839, "bacc_std": 0.09263450158820587} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07388714322913534, "f1": 0.5494505494505495, "f1_std": 0.07697280766727974, "bacc": 0.5725806451612903, "bacc_std": 0.08915162515888504} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 41, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06915559365122981, "f1": 0.5199063231850116, "f1_std": 0.08003943103008346, "bacc": 0.5209677419354839, "bacc_std": 0.08263939259915412} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.052456854597746454, "f1": 0.6893939393939394, "f1_std": 0.09117433151804834, "bacc": 0.667741935483871, "bacc_std": 0.08221835062819499} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 43, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06711307017253303, "f1": 0.6479313036690086, "f1_std": 0.08516645890461463, "bacc": 0.6532258064516129, "bacc_std": 0.08837096738868051} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.03860293762882888, "f1": 0.5886287625418061, "f1_std": 0.09377197674805447, "bacc": 0.5838709677419355, "bacc_std": 0.06739633068809103} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 45, "C": 2.782559402207126, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06645347430700475, "f1": 0.7119437939110069, "f1_std": 0.08506471770693612, "bacc": 0.7193548387096774, "bacc_std": 0.0886581045980914} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 46, "C": 166.81005372000556, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05720468483163329, "f1": 0.5918552036199095, "f1_std": 0.08711308329207405, "bacc": 0.5854838709677419, "bacc_std": 0.07809478079027139} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 47, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05848688947390804, "f1": 0.6440972222222222, "f1_std": 0.08521735319913254, "bacc": 0.635483870967742, "bacc_std": 0.08111397641353174} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06368966625089588, "f1": 0.5017361111111112, "f1_std": 0.08289057801851836, "bacc": 0.5032258064516129, "bacc_std": 0.07744918907682409} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 49, "C": 0.3593813663804626, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.048761240105081066, "f1": 0.6328358208955224, "f1_std": 0.09530498158106261, "bacc": 0.6177419354838709, "bacc_std": 0.07750289652537574} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.046991487325080496, "f1": 0.569327731092437, "f1_std": 0.09278427326021584, "bacc": 0.567741935483871, "bacc_std": 0.06960953413474173} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 51, "C": 21.54434690031882, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.07092922799312126, "f1": 0.5287356321839081, "f1_std": 0.07797354651625979, "bacc": 0.5387096774193548, "bacc_std": 0.08736959064461083} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.057896068854596514, "f1": 0.5176470588235295, "f1_std": 0.08222877310634379, "bacc": 0.5193548387096775, "bacc_std": 0.07227715322459664} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 53, "C": 21.54434690031882, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06694508390740446, "f1": 0.6893939393939394, "f1_std": 0.08237644293878948, "bacc": 0.7032258064516128, "bacc_std": 0.08804493555213026} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05701391545598016, "f1": 0.6440972222222222, "f1_std": 0.08554351958075973, "bacc": 0.635483870967742, "bacc_std": 0.08083277531445039} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05815687823993917, "f1": 0.5918552036199095, "f1_std": 0.08913324520533054, "bacc": 0.5854838709677419, "bacc_std": 0.07898940740903419} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.054025441822062, "f1": 0.4696517412935323, "f1_std": 0.06903693382394868, "bacc": 0.4854838709677419, "bacc_std": 0.05828171955722778} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 57, "C": 166.81005372000556, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.07490400757624094, "f1": 0.5467943994104643, "f1_std": 0.08439397528204892, "bacc": 0.5548387096774194, "bacc_std": 0.09096309665558762} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.05825950683642387, "f1": 0.5918552036199095, "f1_std": 0.08865272200355369, "bacc": 0.5854838709677419, "bacc_std": 0.0790552477425095} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 59, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06965831454497645, "f1": 0.603225806451613, "f1_std": 0.09016671625101351, "bacc": 0.603225806451613, "bacc_std": 0.09173354165130539} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 60, "C": 166.81005372000556, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06328111647686062, "f1": 0.7119437939110069, "f1_std": 0.08237452413667236, "bacc": 0.7193548387096774, "bacc_std": 0.08560401119439577} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 61, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06272668113233358, "f1": 0.5729166666666666, "f1_std": 0.08909079650920727, "bacc": 0.5693548387096774, "bacc_std": 0.08305425999946224} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 62, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.056695666256587944, "f1": 0.5918552036199095, "f1_std": 0.08872864547192694, "bacc": 0.5854838709677419, "bacc_std": 0.08020838436196241} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 63, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.070737829844353, "f1": 0.646551724137931, "f1_std": 0.07995422304543322, "bacc": 0.6709677419354838, "bacc_std": 0.08761877029146287} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.053801914873184725, "f1": 0.6117424242424243, "f1_std": 0.09350532752808359, "bacc": 0.6016129032258064, "bacc_std": 0.07989098555757766} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 65, "C": 2.782559402207126, "split": "test", "acc": 0.7317073170731707, "acc_std": 0.06583999858326531, "f1": 0.6479313036690086, "f1_std": 0.08370836811388362, "bacc": 0.6532258064516129, "bacc_std": 0.08745115859997891} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.8780487804878049, "acc_std": 0.03756097560975611, "f1": 0.7960199004975124, "f1_std": 0.08288655444914525, "bacc": 0.75, "bacc_std": 0.07700000000000001} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.8536585365853658, "acc_std": 0.03795849199866364, "f1": 0.7415966386554622, "f1_std": 0.09056680974905587, "bacc": 0.7, "bacc_std": 0.07781490859726047} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.5365853658536586, "acc_std": 0.06352446399051762, "f1": 0.3918813427010148, "f1_std": 0.05786250718726969, "bacc": 0.3887096774193548, "bacc_std": 0.06230082728282884} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 69, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.060587074324915426, "f1": 0.6440972222222222, "f1_std": 0.08914285212523629, "bacc": 0.635483870967742, "bacc_std": 0.08409751902116427} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 70, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.07355579977909409, "f1": 0.646551724137931, "f1_std": 0.08225562353243862, "bacc": 0.6709677419354838, "bacc_std": 0.09044376110598717} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.04766669925354119, "f1": 0.3880597014925373, "f1_std": 0.01804481349664766, "bacc": 0.41935483870967744, "bacc_std": 0.03152152692572884} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 72, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.04631452362008984, "f1": 0.4831932773109243, "f1_std": 0.06981620022846667, "bacc": 0.5016129032258064, "bacc_std": 0.05370851253217049} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 73, "C": 10000.0, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06960705551361464, "f1": 0.646551724137931, "f1_std": 0.07921824533154806, "bacc": 0.6709677419354838, "bacc_std": 0.08952597307105026} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.7560975609756098, "acc_std": 1.1102230246251565e-16, "f1": 0.4305555555555556, "f1_std": 1.6653345369377348e-16, "bacc": 0.5, "bacc_std": 0.0} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 75, "C": 166.81005372000556, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.06280654035214289, "f1": 0.5729166666666666, "f1_std": 0.08939505641047726, "bacc": 0.5693548387096774, "bacc_std": 0.08327319549800845} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 76, "C": 2.782559402207126, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06315660450376487, "f1": 0.48621553884711777, "f1_std": 0.07461042969787691, "bacc": 0.48709677419354835, "bacc_std": 0.0725359187639208} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.04097151547489229, "f1": 0.6554621848739496, "f1_std": 0.09413618069274811, "bacc": 0.6338709677419355, "bacc_std": 0.07507016842464714} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 78, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06173297451745023, "f1": 0.7119437939110069, "f1_std": 0.07753094783855281, "bacc": 0.7193548387096774, "bacc_std": 0.08104444150241968} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.8048780487804879, "acc_std": 0.0605723248994454, "f1": 0.7354838709677419, "f1_std": 0.08158592916248399, "bacc": 0.7354838709677419, "bacc_std": 0.08364228849426437} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 80, "C": 1291.5496650148827, "split": "test", "acc": 0.5853658536585366, "acc_std": 0.07555466128020145, "f1": 0.4863669859985261, "f1_std": 0.07924411222875788, "bacc": 0.4887096774193548, "bacc_std": 0.08624349673110378} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.05696464562063137, "f1": 0.6117424242424243, "f1_std": 0.09380473843864907, "bacc": 0.6016129032258064, "bacc_std": 0.08027681193756714} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 82, "C": 1291.5496650148827, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.060456246684988384, "f1": 0.44343891402714936, "f1_std": 0.06794765267540193, "bacc": 0.45322580645161287, "bacc_std": 0.06302983280241933} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 83, "C": 21.54434690031882, "split": "test", "acc": 0.6341463414634146, "acc_std": 0.06462381877913939, "f1": 0.48621553884711777, "f1_std": 0.07723999868874148, "bacc": 0.48709677419354835, "bacc_std": 0.0740263768132677} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 84, "C": 1291.5496650148827, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06523720503578022, "f1": 0.5547201336675021, "f1_std": 0.08339920873847209, "bacc": 0.5532258064516129, "bacc_std": 0.08043320087059375} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 85, "C": 10000.0, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.07153621531175856, "f1": 0.7054597701149425, "f1_std": 0.08122654894620172, "bacc": 0.7370967741935484, "bacc_std": 0.08943507117621993} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 86, "C": 10000.0, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06641000763155236, "f1": 0.5370967741935484, "f1_std": 0.08027297661532769, "bacc": 0.5370967741935484, "bacc_std": 0.08062281393595173} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.058792610833655924, "f1": 0.6440972222222222, "f1_std": 0.08782824114979185, "bacc": 0.635483870967742, "bacc_std": 0.08219833751936184} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 88, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06719060230030455, "f1": 0.5370967741935484, "f1_std": 0.08301575858360248, "bacc": 0.5370967741935484, "bacc_std": 0.08275299624241272} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 89, "C": 21.54434690031882, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.07095681588406093, "f1": 0.6259649122807017, "f1_std": 0.07750429266522546, "bacc": 0.6548387096774193, "bacc_std": 0.08746970006076438} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.7560975609756098, "acc_std": 0.06093217965532727, "f1": 0.6440972222222222, "f1_std": 0.09103053125442215, "bacc": 0.635483870967742, "bacc_std": 0.08579752706438691} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 91, "C": 21.54434690031882, "split": "test", "acc": 0.5365853658536586, "acc_std": 0.07117089887808649, "f1": 0.42593957258658804, "f1_std": 0.07053260655224582, "bacc": 0.42258064516129035, "bacc_std": 0.07699005868497788} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 92, "C": 21.54434690031882, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.06453293502203353, "f1": 0.6917293233082706, "f1_std": 0.0892138212339983, "bacc": 0.685483870967742, "bacc_std": 0.08883383095044332} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 93, "C": 0.3593813663804626, "split": "test", "acc": 0.6097560975609756, "acc_std": 0.06660993024956915, "f1": 0.5030303030303029, "f1_std": 0.0752151207968464, "bacc": 0.5048387096774194, "bacc_std": 0.08051387739821049} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.06245038006494276, "f1": 0.5176470588235295, "f1_std": 0.08244751589367243, "bacc": 0.5193548387096775, "bacc_std": 0.07435924519865737} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 95, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.0743818467871655, "f1": 0.5876436781609196, "f1_std": 0.08258436971723092, "bacc": 0.6048387096774194, "bacc_std": 0.09228655977716735} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.7804878048780488, "acc_std": 0.03759466338525411, "f1": 0.5886287625418061, "f1_std": 0.09151954698084103, "bacc": 0.5838709677419355, "bacc_std": 0.06472790170479109} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 97, "C": 166.81005372000556, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.07535060229296875, "f1": 0.6057692307692308, "f1_std": 0.08046861274230321, "bacc": 0.6387096774193548, "bacc_std": 0.09261560517850459} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 98, "C": 2.782559402207126, "split": "test", "acc": 0.7073170731707317, "acc_std": 0.0587997944206809, "f1": 0.5729166666666666, "f1_std": 0.08418432011672541, "bacc": 0.5693548387096774, "bacc_std": 0.07871995246259235} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 99, "C": 166.81005372000556, "split": "test", "acc": 0.6829268292682927, "acc_std": 0.0603854365870977, "f1": 0.5176470588235295, "f1_std": 0.08285733635255953, "bacc": 0.5193548387096775, "bacc_std": 0.07339655550529346} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "adni_ad_vs_cn", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.6585365853658537, "acc_std": 0.06322092365181371, "f1": 0.5370967741935484, "f1_std": 0.0824302671175155, "bacc": 0.5370967741935484, "bacc_std": 0.0827817532941888} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:--------------|:--------|-----------:|----:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | adni_ad_vs_cn | train | 100 | 639 | 2182.6 | 0.98049 | 0.042799 | 0.96758 | 0.074241 | 0.96109 | 0.086193 | +| flat_mae | reg | logistic | adni_ad_vs_cn | test | 100 | 639 | 2182.6 | 0.71512 | 0.06622 | 0.59106 | 0.088284 | 0.59382 | 0.083573 | + + +done! total time: 0:04:35 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/config.yaml b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..170cc2e9a244c5aae46251c2326a0c3bda4df866 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..ebf9f0bb3b27016ddf606409a180ee2a33ff5dc3 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 16, "eval/id_best": 44, "eval/lr_best": 0.0078, "eval/wd_best": 0.05, "eval/train/loss": 0.0009354565991088748, "eval/train/acc": 1.0, "eval/train/acc_std": 0.0, "eval/train/f1": 1.0, "eval/train/f1_std": 0.0, "eval/validation/loss": 0.05683054402470589, "eval/validation/acc": 0.9836309523809523, "eval/validation/acc_std": 0.0019465981426831347, "eval/validation/f1": 0.9818194336467304, "eval/validation/f1_std": 0.002327038560977579, "eval/test/loss": 0.06464730203151703, "eval/test/acc": 0.9841269841269841, "eval/test/acc_std": 0.0016518094402224132, "eval/test/f1": 0.9797357943655101, "eval/test/f1_std": 0.0023427510616397217} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..6b1848a4078029b6e4a8fb311416396514714856 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 16, "eval/best/id_best": 44, "eval/best/lr_best": 0.0078, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.0009354565991088748, "eval/best/train/acc": 1.0, "eval/best/train/acc_std": 0.0, "eval/best/train/f1": 1.0, "eval/best/train/f1_std": 0.0, "eval/best/validation/loss": 0.05683054402470589, "eval/best/validation/acc": 0.9836309523809523, "eval/best/validation/acc_std": 0.0019465981426831347, "eval/best/validation/f1": 0.9818194336467304, "eval/best/validation/f1_std": 0.002327038560977579, "eval/best/test/loss": 0.06464730203151703, "eval/best/test/acc": 0.9841269841269841, "eval/best/test/acc_std": 0.0016518094402224132, "eval/best/test/f1": 0.9797357943655101, "eval/best/test/f1_std": 0.0023427510616397217} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..5985da26c14aee924fecdf8936f2554a26f46806 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 44, "eval/last/lr_best": 0.0078, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.0009078171569854021, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.0559634231030941, "eval/last/validation/acc": 0.9833829365079365, "eval/last/validation/acc_std": 0.001944227987931744, "eval/last/validation/f1": 0.9816426098928077, "eval/last/validation/f1_std": 0.0023198863630492592, "eval/last/test/loss": 0.06415454298257828, "eval/last/test/acc": 0.9837301587301587, "eval/last/test/acc_std": 0.0017192304494664174, "eval/last/test/f1": 0.9792333705879851, "eval/last/test/f1_std": 0.002400178954922575} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..3421d37e79f2c8ccb511253133a67f6a68d8d6ee --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,16,0.0078,0.05,44,"[26, 1.0]",train,0.0009354565991088748,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,16,0.0078,0.05,44,"[26, 1.0]",validation,0.05683054402470589,0.9836309523809523,0.0019465981426831347,0.9818194336467304,0.002327038560977579 +flat_mae,patch,attn,hcpya_task21,best,16,0.0078,0.05,44,"[26, 1.0]",test,0.06464730203151703,0.9841269841269841,0.0016518094402224132,0.9797357943655101,0.0023427510616397217 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..3421d37e79f2c8ccb511253133a67f6a68d8d6ee --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,best,16,0.0078,0.05,44,"[26, 1.0]",train,0.0009354565991088748,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,best,16,0.0078,0.05,44,"[26, 1.0]",validation,0.05683054402470589,0.9836309523809523,0.0019465981426831347,0.9818194336467304,0.002327038560977579 +flat_mae,patch,attn,hcpya_task21,best,16,0.0078,0.05,44,"[26, 1.0]",test,0.06464730203151703,0.9841269841269841,0.0016518094402224132,0.9797357943655101,0.0023427510616397217 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..31ece24b592a681c4c9761f3199ef1a3c7bb272d --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,hcpya_task21,last,19,0.0078,0.05,44,"[26, 1.0]",train,0.0009078171569854021,1.0,0.0,1.0,0.0 +flat_mae,patch,attn,hcpya_task21,last,19,0.0078,0.05,44,"[26, 1.0]",validation,0.0559634231030941,0.9833829365079365,0.001944227987931744,0.9816426098928077,0.0023198863630492592 +flat_mae,patch,attn,hcpya_task21,last,19,0.0078,0.05,44,"[26, 1.0]",test,0.06415454298257828,0.9837301587301587,0.0017192304494664174,0.9792333705879851,0.002400178954922575 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/log.txt b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..651856ee10bf29a082235b266704e76b09a23688 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/log.txt @@ -0,0 +1,1335 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 22:39:50 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:26:05 lr: nan time: 3.9150 data: 3.3297 max mem: 21742 +train: [0] [ 20/400] eta: 0:03:55 lr: 0.000003 loss: 3.0419 (3.0461) grad: 0.1197 (0.1196) time: 0.4552 data: 0.0027 max mem: 22447 +train: [0] [ 40/400] eta: 0:03:12 lr: 0.000006 loss: 3.0403 (3.0328) grad: 0.1103 (0.1125) time: 0.4470 data: 0.0031 max mem: 22447 +train: [0] [ 60/400] eta: 0:02:57 lr: 0.000009 loss: 2.9960 (3.0194) grad: 0.1024 (0.1098) time: 0.4929 data: 0.0033 max mem: 22447 +train: [0] [ 80/400] eta: 0:02:41 lr: 0.000012 loss: 2.9795 (3.0079) grad: 0.1008 (0.1083) time: 0.4576 data: 0.0036 max mem: 22447 +train: [0] [100/400] eta: 0:02:28 lr: 0.000015 loss: 2.9648 (2.9975) grad: 0.0981 (0.1057) time: 0.4485 data: 0.0035 max mem: 22447 +train: [0] [120/400] eta: 0:02:17 lr: 0.000018 loss: 2.9427 (2.9841) grad: 0.0955 (0.1043) time: 0.4756 data: 0.0035 max mem: 22447 +train: [0] [140/400] eta: 0:02:06 lr: 0.000021 loss: 2.9049 (2.9705) grad: 0.0896 (0.1030) time: 0.4616 data: 0.0034 max mem: 22447 +train: [0] [160/400] eta: 0:01:56 lr: 0.000024 loss: 2.8957 (2.9600) grad: 0.0891 (0.1014) time: 0.4605 data: 0.0034 max mem: 22447 +train: [0] [180/400] eta: 0:01:45 lr: 0.000027 loss: 2.8276 (2.9415) grad: 0.0891 (0.1003) time: 0.4649 data: 0.0032 max mem: 22447 +train: [0] [200/400] eta: 0:01:35 lr: 0.000030 loss: 2.7575 (2.9224) grad: 0.0893 (0.0998) time: 0.4530 data: 0.0033 max mem: 22447 +train: [0] [220/400] eta: 0:01:25 lr: 0.000033 loss: 2.7298 (2.9038) grad: 0.0968 (0.0992) time: 0.4538 data: 0.0034 max mem: 22447 +train: [0] [240/400] eta: 0:01:16 lr: 0.000036 loss: 2.6726 (2.8818) grad: 0.0907 (0.0986) time: 0.4605 data: 0.0035 max mem: 22447 +train: [0] [260/400] eta: 0:01:06 lr: 0.000039 loss: 2.6196 (2.8582) grad: 0.1007 (0.0994) time: 0.4543 data: 0.0035 max mem: 22447 +train: [0] [280/400] eta: 0:00:56 lr: 0.000042 loss: 2.5789 (2.8378) grad: 0.1048 (0.0993) time: 0.4560 data: 0.0035 max mem: 22447 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 2.5388 (2.8160) grad: 0.0983 (0.0990) time: 0.6409 data: 0.1781 max mem: 22447 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 2.4882 (2.7935) grad: 0.0933 (0.0986) time: 0.4435 data: 0.0028 max mem: 22447 +train: [0] [340/400] eta: 0:00:28 lr: 0.000051 loss: 2.4290 (2.7699) grad: 0.0942 (0.0985) time: 0.4650 data: 0.0034 max mem: 22447 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 2.3716 (2.7478) grad: 0.0940 (0.0980) time: 0.4600 data: 0.0034 max mem: 22447 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 2.3346 (2.7236) grad: 0.0909 (0.0980) time: 0.4514 data: 0.0034 max mem: 22447 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.2695 (2.6997) grad: 0.0964 (0.0979) time: 0.4439 data: 0.0030 max mem: 22447 +train: [0] Total time: 0:03:10 (0.4761 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.2695 (2.6997) grad: 0.0964 (0.0979) +eval (validation): [0] [ 0/63] eta: 0:03:33 time: 3.3902 data: 3.1457 max mem: 22447 +eval (validation): [0] [20/63] eta: 0:00:21 time: 0.3607 data: 0.0237 max mem: 22447 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3478 data: 0.0036 max mem: 22447 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3439 data: 0.0028 max mem: 22447 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3426 data: 0.0029 max mem: 22447 +eval (validation): [0] Total time: 0:00:25 (0.4031 s / it) +cv: [0] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.264 acc: 0.922 f1: 0.907 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:23:16 lr: nan time: 3.4911 data: 3.0886 max mem: 22447 +train: [1] [ 20/400] eta: 0:03:48 lr: 0.000063 loss: 2.1948 (2.2011) grad: 0.0957 (0.0968) time: 0.4578 data: 0.0030 max mem: 22447 +train: [1] [ 40/400] eta: 0:03:12 lr: 0.000066 loss: 2.1935 (2.1886) grad: 0.0922 (0.0935) time: 0.4634 data: 0.0033 max mem: 22447 +train: [1] [ 60/400] eta: 0:02:54 lr: 0.000069 loss: 2.1351 (2.1673) grad: 0.0899 (0.0927) time: 0.4676 data: 0.0037 max mem: 22447 +train: [1] [ 80/400] eta: 0:02:39 lr: 0.000072 loss: 2.0961 (2.1479) grad: 0.0898 (0.0932) time: 0.4611 data: 0.0034 max mem: 22447 +train: [1] [100/400] eta: 0:02:27 lr: 0.000075 loss: 2.0832 (2.1305) grad: 0.0949 (0.0941) time: 0.4591 data: 0.0033 max mem: 22447 +train: [1] [120/400] eta: 0:02:16 lr: 0.000078 loss: 2.0550 (2.1155) grad: 0.1010 (0.0959) time: 0.4696 data: 0.0033 max mem: 22447 +train: [1] [140/400] eta: 0:02:05 lr: 0.000081 loss: 2.0550 (2.1066) grad: 0.0963 (0.0960) time: 0.4537 data: 0.0034 max mem: 22447 +train: [1] [160/400] eta: 0:01:55 lr: 0.000084 loss: 2.0382 (2.0958) grad: 0.0969 (0.0965) time: 0.4558 data: 0.0035 max mem: 22447 +train: [1] [180/400] eta: 0:01:45 lr: 0.000087 loss: 2.0065 (2.0827) grad: 0.0979 (0.0959) time: 0.4592 data: 0.0034 max mem: 22447 +train: [1] [200/400] eta: 0:01:35 lr: 0.000090 loss: 1.9863 (2.0733) grad: 0.0940 (0.0960) time: 0.4597 data: 0.0035 max mem: 22447 +train: [1] [220/400] eta: 0:01:25 lr: 0.000093 loss: 1.9718 (2.0599) grad: 0.0961 (0.0958) time: 0.4564 data: 0.0036 max mem: 22447 +train: [1] [240/400] eta: 0:01:15 lr: 0.000096 loss: 1.9083 (2.0459) grad: 0.0977 (0.0965) time: 0.4626 data: 0.0034 max mem: 22447 +train: [1] [260/400] eta: 0:01:06 lr: 0.000099 loss: 1.8886 (2.0326) grad: 0.0974 (0.0967) time: 0.4683 data: 0.0036 max mem: 22447 +train: [1] [280/400] eta: 0:00:56 lr: 0.000102 loss: 1.8700 (2.0201) grad: 0.0917 (0.0963) time: 0.4651 data: 0.0035 max mem: 22447 +train: [1] [300/400] eta: 0:00:48 lr: 0.000105 loss: 1.8245 (2.0068) grad: 0.0922 (0.0962) time: 0.6095 data: 0.1758 max mem: 22447 +train: [1] [320/400] eta: 0:00:38 lr: 0.000108 loss: 1.8076 (1.9950) grad: 0.0856 (0.0954) time: 0.4529 data: 0.0032 max mem: 22447 +train: [1] [340/400] eta: 0:00:28 lr: 0.000111 loss: 1.7885 (1.9821) grad: 0.0879 (0.0957) time: 0.4622 data: 0.0037 max mem: 22447 +train: [1] [360/400] eta: 0:00:19 lr: 0.000114 loss: 1.7707 (1.9702) grad: 0.0945 (0.0955) time: 0.4642 data: 0.0035 max mem: 22447 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 1.7485 (1.9573) grad: 0.0907 (0.0952) time: 0.4556 data: 0.0035 max mem: 22447 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 1.7170 (1.9463) grad: 0.0917 (0.0955) time: 0.4591 data: 0.0034 max mem: 22447 +train: [1] Total time: 0:03:10 (0.4761 s / it) +train: [1] Summary: lr: 0.000120 loss: 1.7170 (1.9463) grad: 0.0917 (0.0955) +eval (validation): [1] [ 0/63] eta: 0:04:04 time: 3.8775 data: 3.5903 max mem: 22447 +eval (validation): [1] [20/63] eta: 0:00:22 time: 0.3566 data: 0.0028 max mem: 22447 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3527 data: 0.0033 max mem: 22447 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3344 data: 0.0032 max mem: 22447 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3373 data: 0.0031 max mem: 22447 +eval (validation): [1] Total time: 0:00:25 (0.4090 s / it) +cv: [1] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 0.208 acc: 0.937 f1: 0.923 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:21:34 lr: nan time: 3.2371 data: 2.8868 max mem: 22447 +train: [2] [ 20/400] eta: 0:03:44 lr: 0.000123 loss: 1.7021 (1.7109) grad: 0.0976 (0.1013) time: 0.4580 data: 0.0031 max mem: 22447 +train: [2] [ 40/400] eta: 0:03:10 lr: 0.000126 loss: 1.6806 (1.6863) grad: 0.0975 (0.1000) time: 0.4635 data: 0.0033 max mem: 22447 +train: [2] [ 60/400] eta: 0:02:55 lr: 0.000129 loss: 1.6732 (1.6864) grad: 0.0951 (0.0981) time: 0.4881 data: 0.0033 max mem: 22447 +train: [2] [ 80/400] eta: 0:02:38 lr: 0.000132 loss: 1.6725 (1.6781) grad: 0.0939 (0.0966) time: 0.4406 data: 0.0032 max mem: 22447 +train: [2] [100/400] eta: 0:02:27 lr: 0.000135 loss: 1.6406 (1.6691) grad: 0.0873 (0.0957) time: 0.4674 data: 0.0034 max mem: 22447 +train: [2] [120/400] eta: 0:02:16 lr: 0.000138 loss: 1.6304 (1.6585) grad: 0.0887 (0.0956) time: 0.4652 data: 0.0034 max mem: 22447 +train: [2] [140/400] eta: 0:02:05 lr: 0.000141 loss: 1.6075 (1.6459) grad: 0.0907 (0.0946) time: 0.4600 data: 0.0032 max mem: 22447 +train: [2] [160/400] eta: 0:01:55 lr: 0.000144 loss: 1.5574 (1.6355) grad: 0.0907 (0.0940) time: 0.4578 data: 0.0034 max mem: 22447 +train: [2] [180/400] eta: 0:01:45 lr: 0.000147 loss: 1.5513 (1.6282) grad: 0.0926 (0.0946) time: 0.4597 data: 0.0035 max mem: 22447 +train: [2] [200/400] eta: 0:01:35 lr: 0.000150 loss: 1.5459 (1.6205) grad: 0.0988 (0.0951) time: 0.4591 data: 0.0034 max mem: 22447 +train: [2] [220/400] eta: 0:01:25 lr: 0.000153 loss: 1.5084 (1.6076) grad: 0.0976 (0.0957) time: 0.4392 data: 0.0033 max mem: 22447 +train: [2] [240/400] eta: 0:01:15 lr: 0.000156 loss: 1.4800 (1.6018) grad: 0.0976 (0.0959) time: 0.4496 data: 0.0031 max mem: 22447 +train: [2] [260/400] eta: 0:01:05 lr: 0.000159 loss: 1.5270 (1.5954) grad: 0.0947 (0.0956) time: 0.4528 data: 0.0030 max mem: 22447 +train: [2] [280/400] eta: 0:00:56 lr: 0.000162 loss: 1.5059 (1.5887) grad: 0.0950 (0.0958) time: 0.4515 data: 0.0031 max mem: 22447 +train: [2] [300/400] eta: 0:00:47 lr: 0.000165 loss: 1.4956 (1.5821) grad: 0.0921 (0.0957) time: 0.6168 data: 0.1683 max mem: 22447 +train: [2] [320/400] eta: 0:00:38 lr: 0.000168 loss: 1.4611 (1.5734) grad: 0.0904 (0.0955) time: 0.4468 data: 0.0026 max mem: 22447 +train: [2] [340/400] eta: 0:00:28 lr: 0.000171 loss: 1.4402 (1.5661) grad: 0.0906 (0.0954) time: 0.4462 data: 0.0031 max mem: 22447 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 1.4409 (1.5596) grad: 0.1011 (0.0962) time: 0.4619 data: 0.0032 max mem: 22447 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 1.4439 (1.5524) grad: 0.1011 (0.0966) time: 0.4573 data: 0.0034 max mem: 22447 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 1.4078 (1.5458) grad: 0.0999 (0.0972) time: 0.4470 data: 0.0034 max mem: 22447 +train: [2] Total time: 0:03:08 (0.4717 s / it) +train: [2] Summary: lr: 0.000180 loss: 1.4078 (1.5458) grad: 0.0999 (0.0972) +eval (validation): [2] [ 0/63] eta: 0:03:31 time: 3.3520 data: 3.0610 max mem: 22447 +eval (validation): [2] [20/63] eta: 0:00:22 time: 0.3713 data: 0.0038 max mem: 22447 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3272 data: 0.0033 max mem: 22447 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3281 data: 0.0033 max mem: 22447 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3300 data: 0.0033 max mem: 22447 +eval (validation): [2] Total time: 0:00:24 (0.3948 s / it) +cv: [2] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.123 acc: 0.959 f1: 0.953 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:58 lr: nan time: 3.4471 data: 3.1028 max mem: 22447 +train: [3] [ 20/400] eta: 0:03:49 lr: 0.000183 loss: 1.4362 (1.4348) grad: 0.1123 (0.1159) time: 0.4607 data: 0.0028 max mem: 22447 +train: [3] [ 40/400] eta: 0:03:10 lr: 0.000186 loss: 1.4299 (1.4206) grad: 0.1123 (0.1135) time: 0.4534 data: 0.0032 max mem: 22447 +train: [3] [ 60/400] eta: 0:02:55 lr: 0.000189 loss: 1.3991 (1.4167) grad: 0.1132 (0.1182) time: 0.4853 data: 0.0034 max mem: 22447 +train: [3] [ 80/400] eta: 0:02:39 lr: 0.000192 loss: 1.3991 (1.4070) grad: 0.1278 (0.1244) time: 0.4522 data: 0.0034 max mem: 22447 +train: [3] [100/400] eta: 0:02:27 lr: 0.000195 loss: 1.3884 (1.4024) grad: 0.1311 (0.1258) time: 0.4590 data: 0.0034 max mem: 22447 +train: [3] [120/400] eta: 0:02:16 lr: 0.000198 loss: 1.3762 (1.3950) grad: 0.1311 (0.1296) time: 0.4592 data: 0.0034 max mem: 22447 +train: [3] [140/400] eta: 0:02:05 lr: 0.000201 loss: 1.3368 (1.3885) grad: 0.1496 (0.1344) time: 0.4622 data: 0.0034 max mem: 22447 +train: [3] [160/400] eta: 0:01:55 lr: 0.000204 loss: 1.3349 (1.3829) grad: 0.1549 (0.1362) time: 0.4599 data: 0.0033 max mem: 22447 +train: [3] [180/400] eta: 0:01:44 lr: 0.000207 loss: 1.3735 (1.3885) grad: 0.1767 (0.1446) time: 0.4520 data: 0.0034 max mem: 22447 +train: [3] [200/400] eta: 0:01:34 lr: 0.000210 loss: 1.4106 (1.3881) grad: 0.1888 (0.1498) time: 0.4477 data: 0.0035 max mem: 22447 +train: [3] [220/400] eta: 0:01:24 lr: 0.000213 loss: 1.3898 (1.3897) grad: 0.1921 (0.1568) time: 0.4523 data: 0.0034 max mem: 22447 +train: [3] [240/400] eta: 0:01:15 lr: 0.000216 loss: 1.3903 (1.3935) grad: 0.2285 (0.1639) time: 0.4598 data: 0.0034 max mem: 22447 +train: [3] [260/400] eta: 0:01:05 lr: 0.000219 loss: 1.3616 (1.3935) grad: 0.2321 (0.1688) time: 0.4575 data: 0.0035 max mem: 22447 +train: [3] [280/400] eta: 0:00:56 lr: 0.000222 loss: 1.3308 (1.3889) grad: 0.2258 (0.1720) time: 0.4441 data: 0.0034 max mem: 22447 +train: [3] [300/400] eta: 0:00:47 lr: 0.000225 loss: 1.3397 (1.3873) grad: 0.2226 (0.1763) time: 0.6217 data: 0.1788 max mem: 22447 +train: [3] [320/400] eta: 0:00:38 lr: 0.000228 loss: 1.2956 (1.3804) grad: 0.1896 (0.1771) time: 0.4603 data: 0.0031 max mem: 22447 +train: [3] [340/400] eta: 0:00:28 lr: 0.000231 loss: 1.2804 (1.3756) grad: 0.1672 (0.1759) time: 0.4571 data: 0.0033 max mem: 22447 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 1.2791 (1.3707) grad: 0.1606 (0.1758) time: 0.4490 data: 0.0032 max mem: 22447 +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 1.2717 (1.3660) grad: 0.1505 (0.1736) time: 0.4563 data: 0.0034 max mem: 22447 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 1.2486 (1.3596) grad: 0.1383 (0.1719) time: 0.4531 data: 0.0033 max mem: 22447 +train: [3] Total time: 0:03:09 (0.4730 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.2486 (1.3596) grad: 0.1383 (0.1719) +eval (validation): [3] [ 0/63] eta: 0:03:25 time: 3.2627 data: 2.9905 max mem: 22447 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3520 data: 0.0038 max mem: 22447 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3287 data: 0.0033 max mem: 22447 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3216 data: 0.0031 max mem: 22447 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3238 data: 0.0031 max mem: 22447 +eval (validation): [3] Total time: 0:00:24 (0.3852 s / it) +cv: [3] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.143 acc: 0.957 f1: 0.952 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:23:26 lr: nan time: 3.5166 data: 3.1265 max mem: 22447 +train: [4] [ 20/400] eta: 0:03:52 lr: 0.000243 loss: 1.2514 (1.2428) grad: 0.1341 (0.1416) time: 0.4676 data: 0.0029 max mem: 22447 +train: [4] [ 40/400] eta: 0:03:11 lr: 0.000246 loss: 1.2389 (1.2377) grad: 0.1359 (0.1464) time: 0.4454 data: 0.0032 max mem: 22447 +train: [4] [ 60/400] eta: 0:02:55 lr: 0.000249 loss: 1.2086 (1.2308) grad: 0.1383 (0.1418) time: 0.4855 data: 0.0036 max mem: 22447 +train: [4] [ 80/400] eta: 0:02:40 lr: 0.000252 loss: 1.1973 (1.2198) grad: 0.1313 (0.1382) time: 0.4520 data: 0.0034 max mem: 22447 +train: [4] [100/400] eta: 0:02:26 lr: 0.000255 loss: 1.1675 (1.2131) grad: 0.1404 (0.1385) time: 0.4435 data: 0.0034 max mem: 22447 +train: [4] [120/400] eta: 0:02:15 lr: 0.000258 loss: 1.1799 (1.2115) grad: 0.1450 (0.1411) time: 0.4684 data: 0.0034 max mem: 22447 +train: [4] [140/400] eta: 0:02:05 lr: 0.000261 loss: 1.2004 (1.2129) grad: 0.1460 (0.1423) time: 0.4528 data: 0.0034 max mem: 22447 +train: [4] [160/400] eta: 0:01:54 lr: 0.000264 loss: 1.2014 (1.2096) grad: 0.1542 (0.1441) time: 0.4526 data: 0.0035 max mem: 22447 +train: [4] [180/400] eta: 0:01:44 lr: 0.000267 loss: 1.1731 (1.2081) grad: 0.1454 (0.1440) time: 0.4506 data: 0.0034 max mem: 22447 +train: [4] [200/400] eta: 0:01:34 lr: 0.000270 loss: 1.1963 (1.2021) grad: 0.1394 (0.1440) time: 0.4483 data: 0.0033 max mem: 22447 +train: [4] [220/400] eta: 0:01:24 lr: 0.000273 loss: 1.1463 (1.1966) grad: 0.1268 (0.1431) time: 0.4568 data: 0.0035 max mem: 22447 +train: [4] [240/400] eta: 0:01:15 lr: 0.000276 loss: 1.1362 (1.1909) grad: 0.1266 (0.1428) time: 0.4497 data: 0.0034 max mem: 22447 +train: [4] [260/400] eta: 0:01:05 lr: 0.000279 loss: 1.1302 (1.1857) grad: 0.1334 (0.1418) time: 0.4518 data: 0.0034 max mem: 22447 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 1.1428 (1.1870) grad: 0.1386 (0.1421) time: 0.4548 data: 0.0034 max mem: 22447 +train: [4] [300/400] eta: 0:00:47 lr: 0.000285 loss: 1.1462 (1.1856) grad: 0.1472 (0.1426) time: 0.6128 data: 0.1741 max mem: 22447 +train: [4] [320/400] eta: 0:00:38 lr: 0.000288 loss: 1.1314 (1.1799) grad: 0.1392 (0.1422) time: 0.4651 data: 0.0037 max mem: 22447 +train: [4] [340/400] eta: 0:00:28 lr: 0.000291 loss: 1.0999 (1.1747) grad: 0.1359 (0.1420) time: 0.4498 data: 0.0032 max mem: 22447 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 1.1170 (1.1720) grad: 0.1435 (0.1422) time: 0.4642 data: 0.0034 max mem: 22447 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 1.1021 (1.1677) grad: 0.1410 (0.1421) time: 0.4434 data: 0.0032 max mem: 22447 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 1.0421 (1.1618) grad: 0.1274 (0.1413) time: 0.4530 data: 0.0031 max mem: 22447 +train: [4] Total time: 0:03:08 (0.4713 s / it) +train: [4] Summary: lr: 0.000300 loss: 1.0421 (1.1618) grad: 0.1274 (0.1413) +eval (validation): [4] [ 0/63] eta: 0:03:26 time: 3.2807 data: 3.0527 max mem: 22447 +eval (validation): [4] [20/63] eta: 0:00:21 time: 0.3504 data: 0.0035 max mem: 22447 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3354 data: 0.0029 max mem: 22447 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3225 data: 0.0031 max mem: 22447 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3231 data: 0.0031 max mem: 22447 +eval (validation): [4] Total time: 0:00:24 (0.3870 s / it) +cv: [4] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.095 acc: 0.971 f1: 0.965 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:41 lr: nan time: 3.4037 data: 3.0631 max mem: 22447 +train: [5] [ 20/400] eta: 0:03:43 lr: 0.000300 loss: 1.0727 (1.1017) grad: 0.1438 (0.1511) time: 0.4477 data: 0.0029 max mem: 22447 +train: [5] [ 40/400] eta: 0:03:08 lr: 0.000300 loss: 1.0752 (1.0940) grad: 0.1516 (0.1537) time: 0.4537 data: 0.0027 max mem: 22447 +train: [5] [ 60/400] eta: 0:02:53 lr: 0.000300 loss: 1.0774 (1.0893) grad: 0.1548 (0.1538) time: 0.4816 data: 0.0035 max mem: 22447 +train: [5] [ 80/400] eta: 0:02:39 lr: 0.000300 loss: 1.0774 (1.0894) grad: 0.1407 (0.1515) time: 0.4618 data: 0.0033 max mem: 22447 +train: [5] [100/400] eta: 0:02:26 lr: 0.000300 loss: 1.0768 (1.0908) grad: 0.1479 (0.1541) time: 0.4589 data: 0.0034 max mem: 22447 +train: [5] [120/400] eta: 0:02:15 lr: 0.000300 loss: 1.0787 (1.0864) grad: 0.1533 (0.1530) time: 0.4607 data: 0.0034 max mem: 22447 +train: [5] [140/400] eta: 0:02:04 lr: 0.000300 loss: 1.0410 (1.0781) grad: 0.1511 (0.1521) time: 0.4511 data: 0.0034 max mem: 22447 +train: [5] [160/400] eta: 0:01:54 lr: 0.000299 loss: 1.0228 (1.0705) grad: 0.1472 (0.1508) time: 0.4563 data: 0.0032 max mem: 22447 +train: [5] [180/400] eta: 0:01:44 lr: 0.000299 loss: 1.0307 (1.0686) grad: 0.1471 (0.1504) time: 0.4589 data: 0.0034 max mem: 22447 +train: [5] [200/400] eta: 0:01:34 lr: 0.000299 loss: 1.0393 (1.0638) grad: 0.1453 (0.1486) time: 0.4610 data: 0.0034 max mem: 22447 +train: [5] [220/400] eta: 0:01:25 lr: 0.000299 loss: 1.0123 (1.0605) grad: 0.1315 (0.1472) time: 0.4584 data: 0.0034 max mem: 22447 +train: [5] [240/400] eta: 0:01:15 lr: 0.000299 loss: 1.0164 (1.0552) grad: 0.1425 (0.1533) time: 0.4515 data: 0.0033 max mem: 22447 +train: [5] [260/400] eta: 0:01:05 lr: 0.000299 loss: 1.0164 (1.0488) grad: 0.1471 (0.1532) time: 0.4551 data: 0.0034 max mem: 22447 +train: [5] [280/400] eta: 0:00:56 lr: 0.000298 loss: 1.0274 (1.0467) grad: 0.1431 (0.1526) time: 0.4512 data: 0.0036 max mem: 22447 +train: [5] [300/400] eta: 0:00:47 lr: 0.000298 loss: 0.9801 (1.0408) grad: 0.1357 (0.1512) time: 0.6069 data: 0.1749 max mem: 22447 +train: [5] [320/400] eta: 0:00:38 lr: 0.000298 loss: 0.9617 (1.0359) grad: 0.1278 (0.1495) time: 0.4665 data: 0.0031 max mem: 22447 +train: [5] [340/400] eta: 0:00:28 lr: 0.000298 loss: 0.9600 (1.0316) grad: 0.1220 (0.1476) time: 0.4629 data: 0.0036 max mem: 22447 +train: [5] [360/400] eta: 0:00:19 lr: 0.000297 loss: 0.9322 (1.0256) grad: 0.1055 (0.1457) time: 0.4707 data: 0.0035 max mem: 22447 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 0.9083 (1.0200) grad: 0.1037 (0.1434) time: 0.4526 data: 0.0033 max mem: 22447 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.9045 (1.0148) grad: 0.1053 (0.1419) time: 0.4695 data: 0.0032 max mem: 22447 +train: [5] Total time: 0:03:09 (0.4745 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.9045 (1.0148) grad: 0.1053 (0.1419) +eval (validation): [5] [ 0/63] eta: 0:03:49 time: 3.6375 data: 3.3500 max mem: 22447 +eval (validation): [5] [20/63] eta: 0:00:22 time: 0.3609 data: 0.0028 max mem: 22447 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3419 data: 0.0033 max mem: 22447 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3387 data: 0.0033 max mem: 22447 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3366 data: 0.0032 max mem: 22447 +eval (validation): [5] Total time: 0:00:25 (0.4025 s / it) +cv: [5] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.112 acc: 0.966 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:23:00 lr: nan time: 3.4517 data: 3.0412 max mem: 22447 +train: [6] [ 20/400] eta: 0:03:48 lr: 0.000296 loss: 0.8909 (0.8896) grad: 0.1089 (0.1138) time: 0.4576 data: 0.0038 max mem: 22447 +train: [6] [ 40/400] eta: 0:03:09 lr: 0.000296 loss: 0.8968 (0.9041) grad: 0.1089 (0.1104) time: 0.4489 data: 0.0033 max mem: 22447 +train: [6] [ 60/400] eta: 0:02:55 lr: 0.000296 loss: 0.9210 (0.9232) grad: 0.1051 (0.1137) time: 0.4941 data: 0.0036 max mem: 22447 +train: [6] [ 80/400] eta: 0:02:40 lr: 0.000295 loss: 0.9423 (0.9334) grad: 0.1276 (0.1167) time: 0.4554 data: 0.0035 max mem: 22447 +train: [6] [100/400] eta: 0:02:27 lr: 0.000295 loss: 0.9205 (0.9297) grad: 0.1152 (0.1158) time: 0.4521 data: 0.0033 max mem: 22447 +train: [6] [120/400] eta: 0:02:15 lr: 0.000295 loss: 0.9110 (0.9289) grad: 0.1113 (0.1143) time: 0.4528 data: 0.0034 max mem: 22447 +train: [6] [140/400] eta: 0:02:04 lr: 0.000294 loss: 0.9110 (0.9260) grad: 0.1040 (0.1144) time: 0.4519 data: 0.0034 max mem: 22447 +train: [6] [160/400] eta: 0:01:54 lr: 0.000294 loss: 0.8842 (0.9205) grad: 0.1086 (0.1141) time: 0.4654 data: 0.0034 max mem: 22447 +train: [6] [180/400] eta: 0:01:44 lr: 0.000293 loss: 0.8842 (0.9156) grad: 0.1058 (0.1135) time: 0.4511 data: 0.0035 max mem: 22447 +train: [6] [200/400] eta: 0:01:34 lr: 0.000293 loss: 0.8933 (0.9169) grad: 0.1114 (0.1139) time: 0.4515 data: 0.0035 max mem: 22447 +train: [6] [220/400] eta: 0:01:24 lr: 0.000292 loss: 0.9026 (0.9138) grad: 0.1069 (0.1133) time: 0.4527 data: 0.0035 max mem: 22447 +train: [6] [240/400] eta: 0:01:15 lr: 0.000292 loss: 0.8849 (0.9115) grad: 0.1003 (0.1125) time: 0.4503 data: 0.0035 max mem: 22447 +train: [6] [260/400] eta: 0:01:05 lr: 0.000291 loss: 0.8546 (0.9083) grad: 0.1016 (0.1121) time: 0.4451 data: 0.0033 max mem: 22447 +train: [6] [280/400] eta: 0:00:56 lr: 0.000291 loss: 0.8597 (0.9060) grad: 0.1056 (0.1119) time: 0.4596 data: 0.0035 max mem: 22447 +train: [6] [300/400] eta: 0:00:47 lr: 0.000290 loss: 0.8670 (0.9028) grad: 0.1037 (0.1111) time: 0.6201 data: 0.1798 max mem: 22447 +train: [6] [320/400] eta: 0:00:38 lr: 0.000290 loss: 0.8610 (0.9006) grad: 0.0995 (0.1107) time: 0.4442 data: 0.0031 max mem: 22447 +train: [6] [340/400] eta: 0:00:28 lr: 0.000289 loss: 0.8610 (0.8980) grad: 0.0993 (0.1100) time: 0.4762 data: 0.0031 max mem: 22447 +train: [6] [360/400] eta: 0:00:19 lr: 0.000288 loss: 0.8477 (0.8944) grad: 0.0870 (0.1086) time: 0.4799 data: 0.0037 max mem: 22447 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 0.8426 (0.8915) grad: 0.0856 (0.1077) time: 0.4481 data: 0.0035 max mem: 22447 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.8146 (0.8870) grad: 0.0866 (0.1068) time: 0.4580 data: 0.0033 max mem: 22447 +train: [6] Total time: 0:03:09 (0.4735 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.8146 (0.8870) grad: 0.0866 (0.1068) +eval (validation): [6] [ 0/63] eta: 0:03:32 time: 3.3694 data: 3.0853 max mem: 22447 +eval (validation): [6] [20/63] eta: 0:00:22 time: 0.3861 data: 0.0035 max mem: 22447 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3309 data: 0.0031 max mem: 22447 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3312 data: 0.0032 max mem: 22447 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3334 data: 0.0032 max mem: 22447 +eval (validation): [6] Total time: 0:00:25 (0.4015 s / it) +cv: [6] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.102 acc: 0.971 f1: 0.965 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:22:45 lr: nan time: 3.4143 data: 3.0231 max mem: 22447 +train: [7] [ 20/400] eta: 0:03:49 lr: 0.000286 loss: 0.8100 (0.8019) grad: 0.0841 (0.0864) time: 0.4621 data: 0.0039 max mem: 22447 +train: [7] [ 40/400] eta: 0:03:09 lr: 0.000286 loss: 0.8116 (0.8224) grad: 0.0855 (0.0890) time: 0.4483 data: 0.0034 max mem: 22447 +train: [7] [ 60/400] eta: 0:02:53 lr: 0.000285 loss: 0.8158 (0.8144) grad: 0.0866 (0.0884) time: 0.4715 data: 0.0036 max mem: 22447 +train: [7] [ 80/400] eta: 0:02:38 lr: 0.000284 loss: 0.8158 (0.8151) grad: 0.0854 (0.0876) time: 0.4488 data: 0.0036 max mem: 22447 +train: [7] [100/400] eta: 0:02:25 lr: 0.000284 loss: 0.8193 (0.8118) grad: 0.0844 (0.0879) time: 0.4514 data: 0.0034 max mem: 22447 +train: [7] [120/400] eta: 0:02:15 lr: 0.000283 loss: 0.8216 (0.8166) grad: 0.0868 (0.0894) time: 0.4782 data: 0.0034 max mem: 22447 +train: [7] [140/400] eta: 0:02:05 lr: 0.000282 loss: 0.8246 (0.8152) grad: 0.0933 (0.0905) time: 0.4625 data: 0.0034 max mem: 22447 +train: [7] [160/400] eta: 0:01:54 lr: 0.000282 loss: 0.7984 (0.8137) grad: 0.0923 (0.0904) time: 0.4519 data: 0.0034 max mem: 22447 +train: [7] [180/400] eta: 0:01:44 lr: 0.000281 loss: 0.7960 (0.8131) grad: 0.0887 (0.0911) time: 0.4497 data: 0.0034 max mem: 22447 +train: [7] [200/400] eta: 0:01:34 lr: 0.000280 loss: 0.7924 (0.8115) grad: 0.0893 (0.0906) time: 0.4607 data: 0.0036 max mem: 22447 +train: [7] [220/400] eta: 0:01:24 lr: 0.000279 loss: 0.7851 (0.8096) grad: 0.0840 (0.0903) time: 0.4579 data: 0.0034 max mem: 22447 +train: [7] [240/400] eta: 0:01:15 lr: 0.000278 loss: 0.7649 (0.8062) grad: 0.0848 (0.0901) time: 0.4464 data: 0.0036 max mem: 22447 +train: [7] [260/400] eta: 0:01:05 lr: 0.000278 loss: 0.7532 (0.8047) grad: 0.0877 (0.0908) time: 0.4582 data: 0.0029 max mem: 22447 +train: [7] [280/400] eta: 0:00:56 lr: 0.000277 loss: 0.7725 (0.8036) grad: 0.0890 (0.0907) time: 0.4566 data: 0.0034 max mem: 22447 +train: [7] [300/400] eta: 0:00:47 lr: 0.000276 loss: 0.7798 (0.8025) grad: 0.0897 (0.0910) time: 0.6139 data: 0.1736 max mem: 22447 +train: [7] [320/400] eta: 0:00:38 lr: 0.000275 loss: 0.7798 (0.8007) grad: 0.0878 (0.0906) time: 0.4548 data: 0.0030 max mem: 22447 +train: [7] [340/400] eta: 0:00:28 lr: 0.000274 loss: 0.7562 (0.7979) grad: 0.0834 (0.0902) time: 0.4601 data: 0.0036 max mem: 22447 +train: [7] [360/400] eta: 0:00:19 lr: 0.000273 loss: 0.7367 (0.7934) grad: 0.0821 (0.0897) time: 0.4719 data: 0.0034 max mem: 22447 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 0.7268 (0.7910) grad: 0.0783 (0.0891) time: 0.4525 data: 0.0032 max mem: 22447 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.7596 (0.7904) grad: 0.0797 (0.0892) time: 0.4512 data: 0.0033 max mem: 22447 +train: [7] Total time: 0:03:09 (0.4731 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.7596 (0.7904) grad: 0.0797 (0.0892) +eval (validation): [7] [ 0/63] eta: 0:03:40 time: 3.5048 data: 3.2120 max mem: 22447 +eval (validation): [7] [20/63] eta: 0:00:21 time: 0.3383 data: 0.0073 max mem: 22447 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3384 data: 0.0030 max mem: 22447 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3231 data: 0.0029 max mem: 22447 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3267 data: 0.0030 max mem: 22447 +eval (validation): [7] Total time: 0:00:24 (0.3900 s / it) +cv: [7] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.093 acc: 0.971 f1: 0.966 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:22:52 lr: nan time: 3.4312 data: 3.0388 max mem: 22447 +train: [8] [ 20/400] eta: 0:03:59 lr: 0.000270 loss: 0.7316 (0.7369) grad: 0.0839 (0.0864) time: 0.4893 data: 0.0034 max mem: 22447 +train: [8] [ 40/400] eta: 0:03:15 lr: 0.000270 loss: 0.7502 (0.7596) grad: 0.0855 (0.0863) time: 0.4531 data: 0.0032 max mem: 22447 +train: [8] [ 60/400] eta: 0:02:58 lr: 0.000269 loss: 0.7549 (0.7539) grad: 0.0818 (0.0849) time: 0.4839 data: 0.0035 max mem: 22447 +train: [8] [ 80/400] eta: 0:02:42 lr: 0.000268 loss: 0.7437 (0.7542) grad: 0.0787 (0.0846) time: 0.4542 data: 0.0034 max mem: 22447 +train: [8] [100/400] eta: 0:02:29 lr: 0.000267 loss: 0.7325 (0.7487) grad: 0.0779 (0.0828) time: 0.4625 data: 0.0033 max mem: 22447 +train: [8] [120/400] eta: 0:02:17 lr: 0.000266 loss: 0.7155 (0.7440) grad: 0.0740 (0.0821) time: 0.4531 data: 0.0034 max mem: 22447 +train: [8] [140/400] eta: 0:02:06 lr: 0.000265 loss: 0.7155 (0.7424) grad: 0.0770 (0.0818) time: 0.4580 data: 0.0036 max mem: 22447 +train: [8] [160/400] eta: 0:01:55 lr: 0.000264 loss: 0.7224 (0.7388) grad: 0.0803 (0.0813) time: 0.4535 data: 0.0034 max mem: 22447 +train: [8] [180/400] eta: 0:01:45 lr: 0.000263 loss: 0.7278 (0.7386) grad: 0.0800 (0.0811) time: 0.4547 data: 0.0033 max mem: 22447 +train: [8] [200/400] eta: 0:01:35 lr: 0.000262 loss: 0.7330 (0.7370) grad: 0.0770 (0.0806) time: 0.4489 data: 0.0033 max mem: 22447 +train: [8] [220/400] eta: 0:01:25 lr: 0.000260 loss: 0.7066 (0.7346) grad: 0.0757 (0.0804) time: 0.4519 data: 0.0036 max mem: 22447 +train: [8] [240/400] eta: 0:01:15 lr: 0.000259 loss: 0.7116 (0.7334) grad: 0.0776 (0.0799) time: 0.4538 data: 0.0033 max mem: 22447 +train: [8] [260/400] eta: 0:01:05 lr: 0.000258 loss: 0.7168 (0.7311) grad: 0.0776 (0.0798) time: 0.4505 data: 0.0033 max mem: 22447 +train: [8] [280/400] eta: 0:00:56 lr: 0.000257 loss: 0.7198 (0.7315) grad: 0.0799 (0.0800) time: 0.4514 data: 0.0036 max mem: 22447 +train: [8] [300/400] eta: 0:00:48 lr: 0.000256 loss: 0.7117 (0.7297) grad: 0.0786 (0.0797) time: 0.6373 data: 0.1778 max mem: 22447 +train: [8] [320/400] eta: 0:00:38 lr: 0.000255 loss: 0.7071 (0.7290) grad: 0.0738 (0.0792) time: 0.4460 data: 0.0031 max mem: 22447 +train: [8] [340/400] eta: 0:00:28 lr: 0.000254 loss: 0.7243 (0.7282) grad: 0.0733 (0.0789) time: 0.4553 data: 0.0034 max mem: 22447 +train: [8] [360/400] eta: 0:00:19 lr: 0.000253 loss: 0.6979 (0.7268) grad: 0.0707 (0.0783) time: 0.4645 data: 0.0034 max mem: 22447 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 0.6858 (0.7236) grad: 0.0685 (0.0777) time: 0.4532 data: 0.0033 max mem: 22447 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.6657 (0.7211) grad: 0.0680 (0.0772) time: 0.4563 data: 0.0032 max mem: 22447 +train: [8] Total time: 0:03:09 (0.4743 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.6657 (0.7211) grad: 0.0680 (0.0772) +eval (validation): [8] [ 0/63] eta: 0:03:22 time: 3.2084 data: 2.9747 max mem: 22447 +eval (validation): [8] [20/63] eta: 0:00:21 time: 0.3702 data: 0.0083 max mem: 22447 +eval (validation): [8] [40/63] eta: 0:00:09 time: 0.3465 data: 0.0027 max mem: 22447 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3258 data: 0.0031 max mem: 22447 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3267 data: 0.0031 max mem: 22447 +eval (validation): [8] Total time: 0:00:25 (0.3976 s / it) +cv: [8] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.085 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:22:20 lr: nan time: 3.3520 data: 3.0163 max mem: 22447 +train: [9] [ 20/400] eta: 0:03:55 lr: 0.000249 loss: 0.6724 (0.6777) grad: 0.0725 (0.0720) time: 0.4844 data: 0.0241 max mem: 22447 +train: [9] [ 40/400] eta: 0:03:16 lr: 0.000248 loss: 0.6740 (0.6795) grad: 0.0703 (0.0708) time: 0.4674 data: 0.0033 max mem: 22447 +train: [9] [ 60/400] eta: 0:02:57 lr: 0.000247 loss: 0.6733 (0.6778) grad: 0.0671 (0.0704) time: 0.4741 data: 0.0033 max mem: 22447 +train: [9] [ 80/400] eta: 0:02:40 lr: 0.000246 loss: 0.6745 (0.6800) grad: 0.0663 (0.0693) time: 0.4395 data: 0.0034 max mem: 22447 +train: [9] [100/400] eta: 0:02:28 lr: 0.000244 loss: 0.6847 (0.6817) grad: 0.0663 (0.0695) time: 0.4650 data: 0.0034 max mem: 22447 +train: [9] [120/400] eta: 0:02:16 lr: 0.000243 loss: 0.6731 (0.6817) grad: 0.0707 (0.0700) time: 0.4591 data: 0.0035 max mem: 22447 +train: [9] [140/400] eta: 0:02:06 lr: 0.000242 loss: 0.6579 (0.6808) grad: 0.0707 (0.0706) time: 0.4674 data: 0.0036 max mem: 22447 +train: [9] [160/400] eta: 0:01:55 lr: 0.000241 loss: 0.6577 (0.6789) grad: 0.0663 (0.0699) time: 0.4558 data: 0.0034 max mem: 22447 +train: [9] [180/400] eta: 0:01:45 lr: 0.000240 loss: 0.6477 (0.6758) grad: 0.0669 (0.0700) time: 0.4488 data: 0.0035 max mem: 22447 +train: [9] [200/400] eta: 0:01:35 lr: 0.000238 loss: 0.6435 (0.6735) grad: 0.0747 (0.0704) time: 0.4541 data: 0.0035 max mem: 22447 +train: [9] [220/400] eta: 0:01:25 lr: 0.000237 loss: 0.6526 (0.6718) grad: 0.0747 (0.0702) time: 0.4464 data: 0.0032 max mem: 22447 +train: [9] [240/400] eta: 0:01:15 lr: 0.000236 loss: 0.6282 (0.6687) grad: 0.0654 (0.0699) time: 0.4484 data: 0.0034 max mem: 22447 +train: [9] [260/400] eta: 0:01:05 lr: 0.000234 loss: 0.6378 (0.6678) grad: 0.0668 (0.0699) time: 0.4448 data: 0.0035 max mem: 22447 +train: [9] [280/400] eta: 0:00:56 lr: 0.000233 loss: 0.6473 (0.6674) grad: 0.0701 (0.0700) time: 0.4500 data: 0.0034 max mem: 22447 +train: [9] [300/400] eta: 0:00:47 lr: 0.000232 loss: 0.6618 (0.6674) grad: 0.0704 (0.0702) time: 0.6032 data: 0.1724 max mem: 22447 +train: [9] [320/400] eta: 0:00:37 lr: 0.000230 loss: 0.6585 (0.6673) grad: 0.0701 (0.0701) time: 0.4373 data: 0.0027 max mem: 22447 +train: [9] [340/400] eta: 0:00:28 lr: 0.000229 loss: 0.6455 (0.6671) grad: 0.0701 (0.0701) time: 0.4600 data: 0.0031 max mem: 22447 +train: [9] [360/400] eta: 0:00:18 lr: 0.000228 loss: 0.6354 (0.6655) grad: 0.0649 (0.0697) time: 0.4664 data: 0.0034 max mem: 22447 +train: [9] [380/400] eta: 0:00:09 lr: 0.000226 loss: 0.6319 (0.6633) grad: 0.0636 (0.0696) time: 0.4450 data: 0.0032 max mem: 22447 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.6401 (0.6631) grad: 0.0662 (0.0695) time: 0.4564 data: 0.0036 max mem: 22447 +train: [9] Total time: 0:03:08 (0.4712 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.6401 (0.6631) grad: 0.0662 (0.0695) +eval (validation): [9] [ 0/63] eta: 0:03:30 time: 3.3432 data: 3.1017 max mem: 22447 +eval (validation): [9] [20/63] eta: 0:00:22 time: 0.3807 data: 0.0038 max mem: 22447 +eval (validation): [9] [40/63] eta: 0:00:10 time: 0.3495 data: 0.0027 max mem: 22447 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3291 data: 0.0032 max mem: 22447 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3323 data: 0.0032 max mem: 22447 +eval (validation): [9] Total time: 0:00:25 (0.4051 s / it) +cv: [9] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.101 acc: 0.975 f1: 0.970 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:43 lr: nan time: 3.4098 data: 3.0560 max mem: 22447 +train: [10] [ 20/400] eta: 0:03:52 lr: 0.000224 loss: 0.6485 (0.6302) grad: 0.0600 (0.0654) time: 0.4730 data: 0.0032 max mem: 22447 +train: [10] [ 40/400] eta: 0:03:14 lr: 0.000222 loss: 0.6416 (0.6342) grad: 0.0627 (0.0645) time: 0.4622 data: 0.0030 max mem: 22447 +train: [10] [ 60/400] eta: 0:02:58 lr: 0.000221 loss: 0.6368 (0.6336) grad: 0.0622 (0.0640) time: 0.4960 data: 0.0036 max mem: 22447 +train: [10] [ 80/400] eta: 0:02:42 lr: 0.000220 loss: 0.6371 (0.6345) grad: 0.0622 (0.0639) time: 0.4552 data: 0.0033 max mem: 22447 +train: [10] [100/400] eta: 0:02:30 lr: 0.000218 loss: 0.6434 (0.6338) grad: 0.0644 (0.0640) time: 0.4683 data: 0.0034 max mem: 22447 +train: [10] [120/400] eta: 0:02:18 lr: 0.000217 loss: 0.6455 (0.6346) grad: 0.0647 (0.0643) time: 0.4601 data: 0.0035 max mem: 22447 +train: [10] [140/400] eta: 0:02:07 lr: 0.000215 loss: 0.6421 (0.6360) grad: 0.0647 (0.0644) time: 0.4623 data: 0.0033 max mem: 22447 +train: [10] [160/400] eta: 0:01:56 lr: 0.000214 loss: 0.6289 (0.6350) grad: 0.0655 (0.0643) time: 0.4463 data: 0.0033 max mem: 22447 +train: [10] [180/400] eta: 0:01:45 lr: 0.000213 loss: 0.6304 (0.6353) grad: 0.0656 (0.0644) time: 0.4574 data: 0.0034 max mem: 22447 +train: [10] [200/400] eta: 0:01:35 lr: 0.000211 loss: 0.6432 (0.6357) grad: 0.0639 (0.0642) time: 0.4452 data: 0.0033 max mem: 22447 +train: [10] [220/400] eta: 0:01:25 lr: 0.000210 loss: 0.6340 (0.6346) grad: 0.0632 (0.0644) time: 0.4488 data: 0.0032 max mem: 22447 +train: [10] [240/400] eta: 0:01:15 lr: 0.000208 loss: 0.6165 (0.6339) grad: 0.0659 (0.0648) time: 0.4484 data: 0.0036 max mem: 22447 +train: [10] [260/400] eta: 0:01:06 lr: 0.000207 loss: 0.6160 (0.6334) grad: 0.0659 (0.0648) time: 0.4601 data: 0.0034 max mem: 22447 +train: [10] [280/400] eta: 0:00:56 lr: 0.000205 loss: 0.6304 (0.6336) grad: 0.0606 (0.0648) time: 0.4560 data: 0.0035 max mem: 22447 +train: [10] [300/400] eta: 0:00:47 lr: 0.000204 loss: 0.6224 (0.6328) grad: 0.0597 (0.0647) time: 0.6107 data: 0.1743 max mem: 22447 +train: [10] [320/400] eta: 0:00:38 lr: 0.000202 loss: 0.6138 (0.6321) grad: 0.0584 (0.0644) time: 0.4389 data: 0.0029 max mem: 22447 +train: [10] [340/400] eta: 0:00:28 lr: 0.000201 loss: 0.6233 (0.6305) grad: 0.0575 (0.0641) time: 0.4495 data: 0.0033 max mem: 22447 +train: [10] [360/400] eta: 0:00:19 lr: 0.000199 loss: 0.6233 (0.6298) grad: 0.0584 (0.0639) time: 0.4753 data: 0.0035 max mem: 22447 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 0.6100 (0.6281) grad: 0.0598 (0.0637) time: 0.4680 data: 0.0036 max mem: 22447 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.6094 (0.6271) grad: 0.0578 (0.0634) time: 0.4525 data: 0.0031 max mem: 22447 +train: [10] Total time: 0:03:09 (0.4745 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.6094 (0.6271) grad: 0.0578 (0.0634) +eval (validation): [10] [ 0/63] eta: 0:03:32 time: 3.3686 data: 3.0666 max mem: 22447 +eval (validation): [10] [20/63] eta: 0:00:22 time: 0.3824 data: 0.0042 max mem: 22447 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3399 data: 0.0029 max mem: 22447 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3393 data: 0.0031 max mem: 22447 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3399 data: 0.0031 max mem: 22447 +eval (validation): [10] Total time: 0:00:25 (0.4069 s / it) +cv: [10] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.077 acc: 0.980 f1: 0.976 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:54:01 lr: nan time: 8.1025 data: 7.7109 max mem: 22447 +train: [11] [ 20/400] eta: 0:05:10 lr: 0.000195 loss: 0.6016 (0.6005) grad: 0.0574 (0.0593) time: 0.4516 data: 0.0026 max mem: 22447 +train: [11] [ 40/400] eta: 0:03:52 lr: 0.000193 loss: 0.5975 (0.5987) grad: 0.0578 (0.0602) time: 0.4698 data: 0.0036 max mem: 22447 +train: [11] [ 60/400] eta: 0:03:18 lr: 0.000192 loss: 0.5975 (0.6018) grad: 0.0599 (0.0603) time: 0.4500 data: 0.0034 max mem: 22447 +train: [11] [ 80/400] eta: 0:02:57 lr: 0.000190 loss: 0.6081 (0.6043) grad: 0.0599 (0.0600) time: 0.4656 data: 0.0035 max mem: 22447 +train: [11] [100/400] eta: 0:02:40 lr: 0.000189 loss: 0.6074 (0.6035) grad: 0.0550 (0.0593) time: 0.4614 data: 0.0036 max mem: 22447 +train: [11] [120/400] eta: 0:02:26 lr: 0.000187 loss: 0.6084 (0.6030) grad: 0.0582 (0.0601) time: 0.4620 data: 0.0034 max mem: 22447 +train: [11] [140/400] eta: 0:02:13 lr: 0.000186 loss: 0.6095 (0.6032) grad: 0.0604 (0.0602) time: 0.4572 data: 0.0035 max mem: 22447 +train: [11] [160/400] eta: 0:02:01 lr: 0.000184 loss: 0.6079 (0.6032) grad: 0.0591 (0.0606) time: 0.4540 data: 0.0033 max mem: 22447 +train: [11] [180/400] eta: 0:01:49 lr: 0.000183 loss: 0.5979 (0.6019) grad: 0.0600 (0.0607) time: 0.4428 data: 0.0034 max mem: 22447 +train: [11] [200/400] eta: 0:01:38 lr: 0.000181 loss: 0.5935 (0.6010) grad: 0.0640 (0.0608) time: 0.4464 data: 0.0035 max mem: 22447 +train: [11] [220/400] eta: 0:01:28 lr: 0.000180 loss: 0.5935 (0.6013) grad: 0.0580 (0.0605) time: 0.4525 data: 0.0035 max mem: 22447 +train: [11] [240/400] eta: 0:01:18 lr: 0.000178 loss: 0.5917 (0.6004) grad: 0.0556 (0.0601) time: 0.4577 data: 0.0034 max mem: 22447 +train: [11] [260/400] eta: 0:01:08 lr: 0.000177 loss: 0.5901 (0.5997) grad: 0.0563 (0.0600) time: 0.4643 data: 0.0036 max mem: 22447 +train: [11] [280/400] eta: 0:00:58 lr: 0.000175 loss: 0.5831 (0.5994) grad: 0.0611 (0.0601) time: 0.4584 data: 0.0035 max mem: 22447 +train: [11] [300/400] eta: 0:00:49 lr: 0.000174 loss: 0.5831 (0.6000) grad: 0.0611 (0.0603) time: 0.6150 data: 0.1760 max mem: 22447 +train: [11] [320/400] eta: 0:00:39 lr: 0.000172 loss: 0.5942 (0.5995) grad: 0.0591 (0.0601) time: 0.4600 data: 0.0029 max mem: 22447 +train: [11] [340/400] eta: 0:00:29 lr: 0.000170 loss: 0.5876 (0.5989) grad: 0.0592 (0.0603) time: 0.4734 data: 0.0035 max mem: 22447 +train: [11] [360/400] eta: 0:00:19 lr: 0.000169 loss: 0.5765 (0.5974) grad: 0.0584 (0.0601) time: 0.4587 data: 0.0034 max mem: 22447 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 0.5760 (0.5967) grad: 0.0546 (0.0600) time: 0.4597 data: 0.0034 max mem: 22447 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.5760 (0.5959) grad: 0.0595 (0.0600) time: 0.4698 data: 0.0034 max mem: 22447 +train: [11] Total time: 0:03:14 (0.4859 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.5760 (0.5959) grad: 0.0595 (0.0600) +eval (validation): [11] [ 0/63] eta: 0:03:28 time: 3.3045 data: 3.0725 max mem: 22447 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3545 data: 0.0034 max mem: 22447 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3387 data: 0.0029 max mem: 22447 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3385 data: 0.0032 max mem: 22447 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3384 data: 0.0032 max mem: 22447 +eval (validation): [11] Total time: 0:00:24 (0.3956 s / it) +cv: [11] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.077 acc: 0.980 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:22:02 lr: nan time: 3.3068 data: 2.9721 max mem: 22447 +train: [12] [ 20/400] eta: 0:03:44 lr: 0.000164 loss: 0.5803 (0.5726) grad: 0.0595 (0.0611) time: 0.4544 data: 0.0029 max mem: 22447 +train: [12] [ 40/400] eta: 0:03:11 lr: 0.000163 loss: 0.5803 (0.5691) grad: 0.0573 (0.0582) time: 0.4692 data: 0.0034 max mem: 22447 +train: [12] [ 60/400] eta: 0:02:51 lr: 0.000161 loss: 0.5716 (0.5709) grad: 0.0569 (0.0586) time: 0.4452 data: 0.0034 max mem: 22447 +train: [12] [ 80/400] eta: 0:02:37 lr: 0.000160 loss: 0.5894 (0.5753) grad: 0.0605 (0.0592) time: 0.4650 data: 0.0033 max mem: 22447 +train: [12] [100/400] eta: 0:02:26 lr: 0.000158 loss: 0.5985 (0.5789) grad: 0.0616 (0.0598) time: 0.4625 data: 0.0035 max mem: 22447 +train: [12] [120/400] eta: 0:02:15 lr: 0.000156 loss: 0.5694 (0.5745) grad: 0.0600 (0.0593) time: 0.4661 data: 0.0035 max mem: 22447 +train: [12] [140/400] eta: 0:02:04 lr: 0.000155 loss: 0.5674 (0.5764) grad: 0.0561 (0.0590) time: 0.4549 data: 0.0036 max mem: 22447 +train: [12] [160/400] eta: 0:01:54 lr: 0.000153 loss: 0.5789 (0.5774) grad: 0.0570 (0.0589) time: 0.4570 data: 0.0035 max mem: 22447 +train: [12] [180/400] eta: 0:01:44 lr: 0.000152 loss: 0.5715 (0.5763) grad: 0.0553 (0.0586) time: 0.4601 data: 0.0034 max mem: 22447 +train: [12] [200/400] eta: 0:01:34 lr: 0.000150 loss: 0.5715 (0.5768) grad: 0.0551 (0.0581) time: 0.4602 data: 0.0036 max mem: 22447 +train: [12] [220/400] eta: 0:01:24 lr: 0.000149 loss: 0.5776 (0.5764) grad: 0.0548 (0.0582) time: 0.4559 data: 0.0037 max mem: 22447 +train: [12] [240/400] eta: 0:01:15 lr: 0.000147 loss: 0.5634 (0.5759) grad: 0.0558 (0.0582) time: 0.4657 data: 0.0036 max mem: 22447 +train: [12] [260/400] eta: 0:01:05 lr: 0.000145 loss: 0.5681 (0.5758) grad: 0.0558 (0.0580) time: 0.4645 data: 0.0034 max mem: 22447 +train: [12] [280/400] eta: 0:00:56 lr: 0.000144 loss: 0.5744 (0.5760) grad: 0.0529 (0.0579) time: 0.4596 data: 0.0036 max mem: 22447 +train: [12] [300/400] eta: 0:00:48 lr: 0.000142 loss: 0.5792 (0.5761) grad: 0.0562 (0.0578) time: 0.6203 data: 0.1637 max mem: 22447 +train: [12] [320/400] eta: 0:00:38 lr: 0.000141 loss: 0.5654 (0.5745) grad: 0.0562 (0.0577) time: 0.4842 data: 0.0032 max mem: 22447 +train: [12] [340/400] eta: 0:00:28 lr: 0.000139 loss: 0.5654 (0.5753) grad: 0.0544 (0.0575) time: 0.4699 data: 0.0036 max mem: 22447 +train: [12] [360/400] eta: 0:00:19 lr: 0.000138 loss: 0.5646 (0.5746) grad: 0.0539 (0.0576) time: 0.4630 data: 0.0034 max mem: 22447 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 0.5536 (0.5733) grad: 0.0547 (0.0574) time: 0.4599 data: 0.0034 max mem: 22447 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.5575 (0.5727) grad: 0.0563 (0.0574) time: 0.4664 data: 0.0033 max mem: 22447 +train: [12] Total time: 0:03:11 (0.4775 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.5575 (0.5727) grad: 0.0563 (0.0574) +eval (validation): [12] [ 0/63] eta: 0:03:16 time: 3.1228 data: 2.8935 max mem: 22447 +eval (validation): [12] [20/63] eta: 0:00:20 time: 0.3477 data: 0.0035 max mem: 22447 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.4177 data: 0.0032 max mem: 22447 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3478 data: 0.0034 max mem: 22447 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3465 data: 0.0033 max mem: 22447 +eval (validation): [12] Total time: 0:00:26 (0.4186 s / it) +cv: [12] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.064 acc: 0.983 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:22:02 lr: nan time: 3.3059 data: 2.9587 max mem: 22447 +train: [13] [ 20/400] eta: 0:03:53 lr: 0.000133 loss: 0.5452 (0.5468) grad: 0.0538 (0.0565) time: 0.4796 data: 0.0036 max mem: 22447 +train: [13] [ 40/400] eta: 0:03:15 lr: 0.000131 loss: 0.5633 (0.5635) grad: 0.0544 (0.0569) time: 0.4682 data: 0.0036 max mem: 22447 +train: [13] [ 60/400] eta: 0:02:56 lr: 0.000130 loss: 0.5615 (0.5566) grad: 0.0567 (0.0566) time: 0.4699 data: 0.0034 max mem: 22447 +train: [13] [ 80/400] eta: 0:02:42 lr: 0.000128 loss: 0.5413 (0.5547) grad: 0.0549 (0.0566) time: 0.4676 data: 0.0035 max mem: 22447 +train: [13] [100/400] eta: 0:02:29 lr: 0.000127 loss: 0.5500 (0.5595) grad: 0.0549 (0.0567) time: 0.4666 data: 0.0030 max mem: 22447 +train: [13] [120/400] eta: 0:02:17 lr: 0.000125 loss: 0.5762 (0.5597) grad: 0.0546 (0.0563) time: 0.4547 data: 0.0034 max mem: 22447 +train: [13] [140/400] eta: 0:02:06 lr: 0.000124 loss: 0.5578 (0.5615) grad: 0.0582 (0.0569) time: 0.4599 data: 0.0033 max mem: 22447 +train: [13] [160/400] eta: 0:01:55 lr: 0.000122 loss: 0.5509 (0.5580) grad: 0.0582 (0.0569) time: 0.4579 data: 0.0031 max mem: 22447 +train: [13] [180/400] eta: 0:01:45 lr: 0.000120 loss: 0.5478 (0.5579) grad: 0.0561 (0.0573) time: 0.4551 data: 0.0033 max mem: 22447 +train: [13] [200/400] eta: 0:01:35 lr: 0.000119 loss: 0.5512 (0.5582) grad: 0.0590 (0.0574) time: 0.4648 data: 0.0035 max mem: 22447 +train: [13] [220/400] eta: 0:01:25 lr: 0.000117 loss: 0.5518 (0.5576) grad: 0.0605 (0.0577) time: 0.4579 data: 0.0034 max mem: 22447 +train: [13] [240/400] eta: 0:01:15 lr: 0.000116 loss: 0.5531 (0.5572) grad: 0.0582 (0.0576) time: 0.4444 data: 0.0033 max mem: 22447 +train: [13] [260/400] eta: 0:01:06 lr: 0.000114 loss: 0.5566 (0.5583) grad: 0.0550 (0.0577) time: 0.4686 data: 0.0034 max mem: 22447 +train: [13] [280/400] eta: 0:00:56 lr: 0.000113 loss: 0.5619 (0.5578) grad: 0.0554 (0.0576) time: 0.4676 data: 0.0034 max mem: 22447 +train: [13] [300/400] eta: 0:00:48 lr: 0.000111 loss: 0.5434 (0.5560) grad: 0.0546 (0.0574) time: 0.6190 data: 0.1732 max mem: 22447 +train: [13] [320/400] eta: 0:00:38 lr: 0.000110 loss: 0.5434 (0.5566) grad: 0.0546 (0.0574) time: 0.4564 data: 0.0028 max mem: 22447 +train: [13] [340/400] eta: 0:00:28 lr: 0.000108 loss: 0.5499 (0.5564) grad: 0.0559 (0.0573) time: 0.4609 data: 0.0033 max mem: 22447 +train: [13] [360/400] eta: 0:00:19 lr: 0.000107 loss: 0.5352 (0.5558) grad: 0.0544 (0.0573) time: 0.4433 data: 0.0032 max mem: 22447 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 0.5338 (0.5556) grad: 0.0569 (0.0573) time: 0.4544 data: 0.0033 max mem: 22447 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.5451 (0.5556) grad: 0.0569 (0.0573) time: 0.4513 data: 0.0032 max mem: 22447 +train: [13] Total time: 0:03:10 (0.4758 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.5451 (0.5556) grad: 0.0569 (0.0573) +eval (validation): [13] [ 0/63] eta: 0:03:18 time: 3.1502 data: 2.8817 max mem: 22447 +eval (validation): [13] [20/63] eta: 0:00:20 time: 0.3505 data: 0.0038 max mem: 22447 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3457 data: 0.0027 max mem: 22447 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3356 data: 0.0030 max mem: 22447 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3365 data: 0.0030 max mem: 22447 +eval (validation): [13] Total time: 0:00:24 (0.3944 s / it) +cv: [13] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.057 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:24:28 lr: nan time: 3.6706 data: 3.2801 max mem: 22447 +train: [14] [ 20/400] eta: 0:03:57 lr: 0.000102 loss: 0.5371 (0.5532) grad: 0.0585 (0.0598) time: 0.4730 data: 0.0022 max mem: 22447 +train: [14] [ 40/400] eta: 0:03:16 lr: 0.000101 loss: 0.5495 (0.5550) grad: 0.0534 (0.0553) time: 0.4644 data: 0.0035 max mem: 22447 +train: [14] [ 60/400] eta: 0:02:55 lr: 0.000099 loss: 0.5496 (0.5534) grad: 0.0530 (0.0553) time: 0.4555 data: 0.0035 max mem: 22447 +train: [14] [ 80/400] eta: 0:02:41 lr: 0.000098 loss: 0.5458 (0.5519) grad: 0.0567 (0.0566) time: 0.4677 data: 0.0034 max mem: 22447 +train: [14] [100/400] eta: 0:02:28 lr: 0.000096 loss: 0.5458 (0.5515) grad: 0.0585 (0.0569) time: 0.4630 data: 0.0035 max mem: 22447 +train: [14] [120/400] eta: 0:02:17 lr: 0.000095 loss: 0.5411 (0.5494) grad: 0.0540 (0.0562) time: 0.4537 data: 0.0035 max mem: 22447 +train: [14] [140/400] eta: 0:02:05 lr: 0.000093 loss: 0.5394 (0.5478) grad: 0.0533 (0.0561) time: 0.4515 data: 0.0033 max mem: 22447 +train: [14] [160/400] eta: 0:01:55 lr: 0.000092 loss: 0.5381 (0.5483) grad: 0.0558 (0.0563) time: 0.4619 data: 0.0033 max mem: 22447 +train: [14] [180/400] eta: 0:01:45 lr: 0.000090 loss: 0.5536 (0.5488) grad: 0.0556 (0.0561) time: 0.4598 data: 0.0033 max mem: 22447 +train: [14] [200/400] eta: 0:01:35 lr: 0.000089 loss: 0.5388 (0.5487) grad: 0.0553 (0.0560) time: 0.4675 data: 0.0036 max mem: 22447 +train: [14] [220/400] eta: 0:01:25 lr: 0.000088 loss: 0.5417 (0.5484) grad: 0.0545 (0.0558) time: 0.4638 data: 0.0030 max mem: 22447 +train: [14] [240/400] eta: 0:01:15 lr: 0.000086 loss: 0.5442 (0.5481) grad: 0.0546 (0.0557) time: 0.4439 data: 0.0034 max mem: 22447 +train: [14] [260/400] eta: 0:01:06 lr: 0.000085 loss: 0.5442 (0.5485) grad: 0.0543 (0.0558) time: 0.4640 data: 0.0032 max mem: 22447 +train: [14] [280/400] eta: 0:00:56 lr: 0.000083 loss: 0.5496 (0.5475) grad: 0.0535 (0.0556) time: 0.4574 data: 0.0034 max mem: 22447 +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:34:32 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +train: [14] [300/400] eta: 0:00:48 lr: 0.000082 loss: 0.5282 (0.5471) grad: 0.0535 (0.0555) time: 0.6216 data: 0.1715 max mem: 22447 +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train: [14] [320/400] eta: 0:00:38 lr: 0.000081 loss: 0.5273 (0.5460) grad: 0.0537 (0.0554) time: 0.4861 data: 0.0037 max mem: 22447 +train: [14] [340/400] eta: 0:00:28 lr: 0.000079 loss: 0.5101 (0.5444) grad: 0.0547 (0.0553) time: 0.4596 data: 0.0033 max mem: 22447 +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +train: [14] [360/400] eta: 0:00:19 lr: 0.000078 loss: 0.5101 (0.5423) grad: 0.0547 (0.0552) time: 0.4461 data: 0.0031 max mem: 22447 +loaded model and optimizer state, resuming training from 14 +start training for 20 epochs +train: [14] [ 0/400] eta: 0:22:20 lr: nan time: 3.3519 data: 2.8409 max mem: 22190 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.5166 (0.5417) grad: 0.0540 (0.0552) time: 0.4725 data: 0.0033 max mem: 22447 +train: [14] [ 20/400] eta: 0:03:38 lr: 0.000102 loss: 0.5352 (0.5426) grad: 0.0568 (0.0572) time: 0.4351 data: 0.0030 max mem: 22446 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.5339 (0.5413) grad: 0.0512 (0.0550) time: 0.4769 data: 0.0034 max mem: 22447 +train: [14] Total time: 0:03:11 (0.4789 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.5339 (0.5413) grad: 0.0512 (0.0550) +train: [14] [ 40/400] eta: 0:03:04 lr: 0.000101 loss: 0.5515 (0.5462) grad: 0.0577 (0.0583) time: 0.4472 data: 0.0033 max mem: 22446 +eval (validation): [14] [ 0/63] eta: 0:03:32 time: 3.3713 data: 3.1182 max mem: 22447 +train: [14] [ 60/400] eta: 0:02:48 lr: 0.000099 loss: 0.5443 (0.5482) grad: 0.0571 (0.0578) time: 0.4583 data: 0.0035 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:21 time: 0.3686 data: 0.0036 max mem: 22447 +eval (validation): [14] [40/63] eta: 0:00:10 time: 0.3572 data: 0.0029 max mem: 22447 +train: [14] [ 80/400] eta: 0:02:33 lr: 0.000098 loss: 0.5482 (0.5502) grad: 0.0529 (0.0563) time: 0.4320 data: 0.0035 max mem: 22446 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3317 data: 0.0031 max mem: 22447 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3239 data: 0.0031 max mem: 22447 +eval (validation): [14] Total time: 0:00:25 (0.4044 s / it) +cv: [14] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.055 acc: 0.983 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [14] [100/400] eta: 0:02:21 lr: 0.000096 loss: 0.5479 (0.5499) grad: 0.0523 (0.0555) time: 0.4491 data: 0.0034 max mem: 22446 +train: [15] [ 0/400] eta: 0:23:23 lr: nan time: 3.5086 data: 3.1080 max mem: 22447 +train: [14] [120/400] eta: 0:02:11 lr: 0.000095 loss: 0.5460 (0.5493) grad: 0.0540 (0.0553) time: 0.4527 data: 0.0036 max mem: 22446 +train: [15] [ 20/400] eta: 0:03:56 lr: 0.000074 loss: 0.5457 (0.5625) grad: 0.0593 (0.0581) time: 0.4778 data: 0.0038 max mem: 22447 +train: [14] [140/400] eta: 0:02:01 lr: 0.000093 loss: 0.5454 (0.5500) grad: 0.0540 (0.0556) time: 0.4440 data: 0.0035 max mem: 22446 +train: [15] [ 40/400] eta: 0:03:13 lr: 0.000072 loss: 0.5375 (0.5417) grad: 0.0517 (0.0547) time: 0.4466 data: 0.0036 max mem: 22447 +train: [14] [160/400] eta: 0:01:52 lr: 0.000092 loss: 0.5561 (0.5516) grad: 0.0556 (0.0555) time: 0.4742 data: 0.0035 max mem: 22446 +train: [15] [ 60/400] eta: 0:02:53 lr: 0.000071 loss: 0.5319 (0.5466) grad: 0.0506 (0.0541) time: 0.4574 data: 0.0036 max mem: 22447 +train: [14] [180/400] eta: 0:01:42 lr: 0.000090 loss: 0.5407 (0.5491) grad: 0.0519 (0.0551) time: 0.4670 data: 0.0035 max mem: 22446 +train: [15] [ 80/400] eta: 0:02:39 lr: 0.000070 loss: 0.5390 (0.5426) grad: 0.0531 (0.0542) time: 0.4553 data: 0.0033 max mem: 22447 +train: [14] [200/400] eta: 0:01:33 lr: 0.000089 loss: 0.5277 (0.5481) grad: 0.0519 (0.0551) time: 0.4606 data: 0.0036 max mem: 22446 +train: [15] [100/400] eta: 0:02:27 lr: 0.000068 loss: 0.5305 (0.5422) grad: 0.0569 (0.0550) time: 0.4674 data: 0.0034 max mem: 22447 +train: [14] [220/400] eta: 0:01:23 lr: 0.000088 loss: 0.5433 (0.5486) grad: 0.0558 (0.0550) time: 0.4591 data: 0.0033 max mem: 22446 +train: [15] [120/400] eta: 0:02:15 lr: 0.000067 loss: 0.5476 (0.5434) grad: 0.0569 (0.0551) time: 0.4506 data: 0.0034 max mem: 22447 +train: [14] [240/400] eta: 0:01:14 lr: 0.000086 loss: 0.5382 (0.5474) grad: 0.0551 (0.0551) time: 0.4721 data: 0.0035 max mem: 22446 +train: [15] [140/400] eta: 0:02:04 lr: 0.000066 loss: 0.5434 (0.5420) grad: 0.0539 (0.0551) time: 0.4449 data: 0.0033 max mem: 22447 +train: [14] [260/400] eta: 0:01:05 lr: 0.000085 loss: 0.5382 (0.5469) grad: 0.0576 (0.0557) time: 0.4442 data: 0.0035 max mem: 22446 +train: [15] [160/400] eta: 0:01:54 lr: 0.000064 loss: 0.5301 (0.5403) grad: 0.0517 (0.0546) time: 0.4694 data: 0.0035 max mem: 22447 +train: [14] [280/400] eta: 0:00:55 lr: 0.000083 loss: 0.5488 (0.5479) grad: 0.0608 (0.0557) time: 0.4468 data: 0.0035 max mem: 22446 +train: [15] [180/400] eta: 0:01:44 lr: 0.000063 loss: 0.5281 (0.5383) grad: 0.0517 (0.0550) time: 0.4517 data: 0.0034 max mem: 22447 +train: [14] [300/400] eta: 0:00:47 lr: 0.000082 loss: 0.5592 (0.5479) grad: 0.0538 (0.0555) time: 0.6211 data: 0.1694 max mem: 22446 +train: [15] [200/400] eta: 0:01:34 lr: 0.000062 loss: 0.5305 (0.5379) grad: 0.0553 (0.0550) time: 0.4599 data: 0.0033 max mem: 22447 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 0.5553 (0.5481) grad: 0.0527 (0.0552) time: 0.4356 data: 0.0026 max mem: 22446 +train: [15] [220/400] eta: 0:01:24 lr: 0.000061 loss: 0.5365 (0.5373) grad: 0.0558 (0.0550) time: 0.4599 data: 0.0039 max mem: 22447 +train: [14] [340/400] eta: 0:00:28 lr: 0.000079 loss: 0.5404 (0.5475) grad: 0.0545 (0.0553) time: 0.4520 data: 0.0034 max mem: 22446 +train: [15] [240/400] eta: 0:01:15 lr: 0.000059 loss: 0.5390 (0.5376) grad: 0.0525 (0.0548) time: 0.4481 data: 0.0035 max mem: 22447 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 0.5491 (0.5478) grad: 0.0530 (0.0552) time: 0.4501 data: 0.0034 max mem: 22446 +train: [15] [260/400] eta: 0:01:05 lr: 0.000058 loss: 0.5382 (0.5369) grad: 0.0499 (0.0547) time: 0.4457 data: 0.0034 max mem: 22447 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 0.5422 (0.5472) grad: 0.0515 (0.0552) time: 0.4410 data: 0.0035 max mem: 22446 +train: [15] [280/400] eta: 0:00:56 lr: 0.000057 loss: 0.5153 (0.5347) grad: 0.0517 (0.0544) time: 0.4472 data: 0.0033 max mem: 22447 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.5251 (0.5464) grad: 0.0514 (0.0550) time: 0.4550 data: 0.0036 max mem: 22446 +train: [14] Total time: 0:03:06 (0.4674 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.5251 (0.5464) grad: 0.0514 (0.0550) +train: [15] [300/400] eta: 0:00:47 lr: 0.000056 loss: 0.5180 (0.5349) grad: 0.0517 (0.0544) time: 0.6129 data: 0.1748 max mem: 22447 +eval (validation): [14] [ 0/63] eta: 0:03:16 time: 3.1234 data: 2.8909 max mem: 22446 +eval (validation): [14] [20/63] eta: 0:00:20 time: 0.3494 data: 0.0047 max mem: 22446 +train: [15] [320/400] eta: 0:00:38 lr: 0.000054 loss: 0.5401 (0.5351) grad: 0.0507 (0.0541) time: 0.4546 data: 0.0031 max mem: 22447 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3538 data: 0.0030 max mem: 22446 +train: [15] [340/400] eta: 0:00:28 lr: 0.000053 loss: 0.5467 (0.5359) grad: 0.0496 (0.0540) time: 0.4601 data: 0.0033 max mem: 22447 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3186 data: 0.0033 max mem: 22446 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3175 data: 0.0033 max mem: 22446 +eval (validation): [14] Total time: 0:00:24 (0.3883 s / it) +cv: [14] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 0.5386 (0.5348) grad: 0.0524 (0.0540) time: 0.4438 data: 0.0033 max mem: 22447 +train: [15] [ 0/400] eta: 0:26:24 lr: nan time: 3.9618 data: 3.5689 max mem: 22446 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.5425 (0.5352) grad: 0.0519 (0.0538) time: 0.4571 data: 0.0036 max mem: 22447 +train: [15] [ 20/400] eta: 0:03:53 lr: 0.000074 loss: 0.5173 (0.5336) grad: 0.0582 (0.0587) time: 0.4475 data: 0.0023 max mem: 22446 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.5425 (0.5351) grad: 0.0518 (0.0538) time: 0.4518 data: 0.0033 max mem: 22447 +train: [15] Total time: 0:03:08 (0.4711 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.5425 (0.5351) grad: 0.0518 (0.0538) +train: [15] [ 40/400] eta: 0:03:11 lr: 0.000072 loss: 0.5334 (0.5362) grad: 0.0546 (0.0558) time: 0.4476 data: 0.0029 max mem: 22446 +eval (validation): [15] [ 0/63] eta: 0:03:39 time: 3.4870 data: 3.1824 max mem: 22447 +train: [15] [ 60/400] eta: 0:02:53 lr: 0.000071 loss: 0.5221 (0.5328) grad: 0.0535 (0.0546) time: 0.4629 data: 0.0037 max mem: 22446 +eval (validation): [15] [20/63] eta: 0:00:23 time: 0.3999 data: 0.0035 max mem: 22447 +train: [15] [ 80/400] eta: 0:02:38 lr: 0.000070 loss: 0.5221 (0.5304) grad: 0.0514 (0.0538) time: 0.4486 data: 0.0035 max mem: 22446 +eval (validation): [15] [40/63] eta: 0:00:10 time: 0.3469 data: 0.0029 max mem: 22447 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3266 data: 0.0033 max mem: 22447 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3199 data: 0.0033 max mem: 22447 +eval (validation): [15] Total time: 0:00:25 (0.4107 s / it) +train: [15] [100/400] eta: 0:02:25 lr: 0.000068 loss: 0.5272 (0.5304) grad: 0.0531 (0.0543) time: 0.4528 data: 0.0034 max mem: 22446 +cv: [15] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.984 f1: 0.983 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:22:42 lr: nan time: 3.4069 data: 3.0167 max mem: 22447 +train: [15] [120/400] eta: 0:02:14 lr: 0.000067 loss: 0.5272 (0.5303) grad: 0.0572 (0.0553) time: 0.4550 data: 0.0035 max mem: 22446 +train: [16] [ 20/400] eta: 0:03:46 lr: 0.000048 loss: 0.5541 (0.5466) grad: 0.0523 (0.0535) time: 0.4558 data: 0.0040 max mem: 22447 +train: [15] [140/400] eta: 0:02:04 lr: 0.000066 loss: 0.5498 (0.5337) grad: 0.0587 (0.0555) time: 0.4554 data: 0.0035 max mem: 22446 +train: [16] [ 40/400] eta: 0:03:09 lr: 0.000047 loss: 0.5226 (0.5330) grad: 0.0523 (0.0528) time: 0.4537 data: 0.0035 max mem: 22447 +train: [15] [160/400] eta: 0:01:54 lr: 0.000064 loss: 0.5500 (0.5351) grad: 0.0566 (0.0555) time: 0.4713 data: 0.0034 max mem: 22446 +train: [16] [ 60/400] eta: 0:02:50 lr: 0.000046 loss: 0.5103 (0.5301) grad: 0.0514 (0.0533) time: 0.4494 data: 0.0034 max mem: 22447 +train: [15] [180/400] eta: 0:01:45 lr: 0.000063 loss: 0.5367 (0.5353) grad: 0.0519 (0.0550) time: 0.4888 data: 0.0037 max mem: 22446 +train: [16] [ 80/400] eta: 0:02:36 lr: 0.000045 loss: 0.5232 (0.5316) grad: 0.0519 (0.0535) time: 0.4578 data: 0.0034 max mem: 22447 +train: [15] [200/400] eta: 0:01:35 lr: 0.000062 loss: 0.5546 (0.5377) grad: 0.0526 (0.0553) time: 0.4865 data: 0.0036 max mem: 22446 +train: [16] [100/400] eta: 0:02:24 lr: 0.000044 loss: 0.5181 (0.5310) grad: 0.0548 (0.0539) time: 0.4486 data: 0.0033 max mem: 22447 +train: [15] [220/400] eta: 0:01:25 lr: 0.000061 loss: 0.5527 (0.5376) grad: 0.0553 (0.0553) time: 0.4565 data: 0.0033 max mem: 22446 +train: [16] [120/400] eta: 0:02:13 lr: 0.000043 loss: 0.5181 (0.5307) grad: 0.0548 (0.0536) time: 0.4524 data: 0.0034 max mem: 22447 +train: [15] [240/400] eta: 0:01:16 lr: 0.000059 loss: 0.5382 (0.5371) grad: 0.0587 (0.0556) time: 0.4677 data: 0.0034 max mem: 22446 +train: [16] [140/400] eta: 0:02:03 lr: 0.000042 loss: 0.5274 (0.5302) grad: 0.0528 (0.0537) time: 0.4522 data: 0.0034 max mem: 22447 +train: [15] [260/400] eta: 0:01:06 lr: 0.000058 loss: 0.5334 (0.5368) grad: 0.0558 (0.0555) time: 0.4625 data: 0.0035 max mem: 22446 +train: [16] [160/400] eta: 0:01:53 lr: 0.000041 loss: 0.5274 (0.5304) grad: 0.0529 (0.0540) time: 0.4545 data: 0.0034 max mem: 22447 +train: [15] [280/400] eta: 0:00:56 lr: 0.000057 loss: 0.5334 (0.5372) grad: 0.0512 (0.0552) time: 0.4550 data: 0.0036 max mem: 22446 +train: [16] [180/400] eta: 0:01:43 lr: 0.000040 loss: 0.5160 (0.5285) grad: 0.0538 (0.0539) time: 0.4477 data: 0.0034 max mem: 22447 +train: [15] [300/400] eta: 0:00:48 lr: 0.000056 loss: 0.5276 (0.5370) grad: 0.0527 (0.0552) time: 0.6270 data: 0.1867 max mem: 22446 +train: [16] [200/400] eta: 0:01:33 lr: 0.000039 loss: 0.5121 (0.5269) grad: 0.0551 (0.0542) time: 0.4471 data: 0.0034 max mem: 22447 +train: [15] [320/400] eta: 0:00:38 lr: 0.000054 loss: 0.5399 (0.5377) grad: 0.0526 (0.0550) time: 0.4491 data: 0.0033 max mem: 22446 +train: [16] [220/400] eta: 0:01:23 lr: 0.000038 loss: 0.5188 (0.5286) grad: 0.0557 (0.0546) time: 0.4529 data: 0.0033 max mem: 22447 +train: [15] [340/400] eta: 0:00:28 lr: 0.000053 loss: 0.5445 (0.5376) grad: 0.0500 (0.0549) time: 0.4522 data: 0.0029 max mem: 22446 +train: [16] [240/400] eta: 0:01:14 lr: 0.000036 loss: 0.5281 (0.5286) grad: 0.0568 (0.0549) time: 0.4489 data: 0.0034 max mem: 22447 +train: [15] [360/400] eta: 0:00:19 lr: 0.000052 loss: 0.5400 (0.5381) grad: 0.0514 (0.0549) time: 0.4380 data: 0.0035 max mem: 22446 +train: [16] [260/400] eta: 0:01:04 lr: 0.000035 loss: 0.5302 (0.5294) grad: 0.0568 (0.0549) time: 0.4527 data: 0.0034 max mem: 22447 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 0.5387 (0.5378) grad: 0.0502 (0.0547) time: 0.4486 data: 0.0035 max mem: 22446 +train: [16] [280/400] eta: 0:00:55 lr: 0.000034 loss: 0.5292 (0.5300) grad: 0.0545 (0.0550) time: 0.4591 data: 0.0036 max mem: 22447 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.5321 (0.5381) grad: 0.0497 (0.0546) time: 0.4554 data: 0.0035 max mem: 22446 +train: [15] Total time: 0:03:10 (0.4755 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.5321 (0.5381) grad: 0.0497 (0.0546) +eval (validation): [15] [ 0/63] eta: 0:03:23 time: 3.2304 data: 2.9523 max mem: 22446 +train: [16] [300/400] eta: 0:00:47 lr: 0.000033 loss: 0.5261 (0.5299) grad: 0.0526 (0.0549) time: 0.6279 data: 0.1854 max mem: 22447 +eval (validation): [15] [20/63] eta: 0:00:21 time: 0.3563 data: 0.0053 max mem: 22446 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 0.5107 (0.5285) grad: 0.0559 (0.0550) time: 0.4507 data: 0.0030 max mem: 22447 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3371 data: 0.0028 max mem: 22446 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 0.5263 (0.5292) grad: 0.0552 (0.0548) time: 0.4749 data: 0.0031 max mem: 22447 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3250 data: 0.0032 max mem: 22446 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3260 data: 0.0031 max mem: 22446 +eval (validation): [15] Total time: 0:00:24 (0.3903 s / it) +cv: [15] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:42 lr: nan time: 3.2550 data: 2.9239 max mem: 22446 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 0.5400 (0.5299) grad: 0.0506 (0.0546) time: 0.4505 data: 0.0033 max mem: 22447 +train: [16] [ 20/400] eta: 0:03:37 lr: 0.000048 loss: 0.5379 (0.5363) grad: 0.0557 (0.0568) time: 0.4375 data: 0.0025 max mem: 22446 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.5296 (0.5300) grad: 0.0504 (0.0545) time: 0.4765 data: 0.0037 max mem: 22447 +train: [16] [ 40/400] eta: 0:03:06 lr: 0.000047 loss: 0.5295 (0.5281) grad: 0.0550 (0.0548) time: 0.4622 data: 0.0037 max mem: 22446 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.5289 (0.5305) grad: 0.0514 (0.0545) time: 0.4622 data: 0.0034 max mem: 22447 +train: [16] Total time: 0:03:08 (0.4714 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.5289 (0.5305) grad: 0.0514 (0.0545) +eval (validation): [16] [ 0/63] eta: 0:03:57 time: 3.7717 data: 3.5198 max mem: 22447 +train: [16] [ 60/400] eta: 0:02:53 lr: 0.000046 loss: 0.5330 (0.5333) grad: 0.0527 (0.0548) time: 0.4902 data: 0.0038 max mem: 22446 +eval (validation): [16] [20/63] eta: 0:00:22 time: 0.3521 data: 0.0063 max mem: 22447 +train: [16] [ 80/400] eta: 0:02:40 lr: 0.000045 loss: 0.5397 (0.5345) grad: 0.0530 (0.0545) time: 0.4830 data: 0.0036 max mem: 22446 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3429 data: 0.0030 max mem: 22447 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3316 data: 0.0030 max mem: 22447 +train: [16] [100/400] eta: 0:02:29 lr: 0.000044 loss: 0.5339 (0.5352) grad: 0.0532 (0.0549) time: 0.4741 data: 0.0036 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3294 data: 0.0030 max mem: 22447 +eval (validation): [16] Total time: 0:00:25 (0.4007 s / it) +cv: [16] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.056 acc: 0.984 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:32 lr: nan time: 3.3809 data: 2.9814 max mem: 22447 +train: [16] [120/400] eta: 0:02:17 lr: 0.000043 loss: 0.5355 (0.5338) grad: 0.0542 (0.0544) time: 0.4518 data: 0.0037 max mem: 22446 +train: [17] [ 20/400] eta: 0:03:51 lr: 0.000028 loss: 0.5349 (0.5360) grad: 0.0514 (0.0544) time: 0.4693 data: 0.0034 max mem: 22447 +train: [16] [140/400] eta: 0:02:05 lr: 0.000042 loss: 0.5355 (0.5325) grad: 0.0539 (0.0543) time: 0.4447 data: 0.0036 max mem: 22446 +train: [17] [ 40/400] eta: 0:03:13 lr: 0.000027 loss: 0.5225 (0.5317) grad: 0.0518 (0.0526) time: 0.4615 data: 0.0032 max mem: 22447 +train: [16] [160/400] eta: 0:01:55 lr: 0.000041 loss: 0.5170 (0.5316) grad: 0.0523 (0.0542) time: 0.4527 data: 0.0034 max mem: 22446 +train: [17] [ 60/400] eta: 0:02:54 lr: 0.000026 loss: 0.5188 (0.5321) grad: 0.0521 (0.0530) time: 0.4673 data: 0.0034 max mem: 22447 +train: [16] [180/400] eta: 0:01:45 lr: 0.000040 loss: 0.5170 (0.5318) grad: 0.0519 (0.0541) time: 0.4761 data: 0.0036 max mem: 22446 +train: [17] [ 80/400] eta: 0:02:40 lr: 0.000025 loss: 0.5224 (0.5299) grad: 0.0555 (0.0539) time: 0.4690 data: 0.0035 max mem: 22447 +train: [16] [200/400] eta: 0:01:35 lr: 0.000039 loss: 0.5316 (0.5320) grad: 0.0531 (0.0541) time: 0.4614 data: 0.0034 max mem: 22446 +train: [17] [100/400] eta: 0:02:28 lr: 0.000024 loss: 0.5275 (0.5277) grad: 0.0552 (0.0543) time: 0.4639 data: 0.0034 max mem: 22447 +train: [16] [220/400] eta: 0:01:25 lr: 0.000038 loss: 0.5086 (0.5289) grad: 0.0511 (0.0536) time: 0.4564 data: 0.0035 max mem: 22446 +train: [17] [120/400] eta: 0:02:17 lr: 0.000023 loss: 0.5211 (0.5265) grad: 0.0532 (0.0538) time: 0.4641 data: 0.0033 max mem: 22447 +train: [16] [240/400] eta: 0:01:15 lr: 0.000036 loss: 0.5046 (0.5299) grad: 0.0493 (0.0539) time: 0.4617 data: 0.0035 max mem: 22446 +train: [17] [140/400] eta: 0:02:06 lr: 0.000023 loss: 0.5162 (0.5254) grad: 0.0519 (0.0538) time: 0.4621 data: 0.0033 max mem: 22447 +train: [16] [260/400] eta: 0:01:06 lr: 0.000035 loss: 0.5428 (0.5305) grad: 0.0518 (0.0537) time: 0.4635 data: 0.0036 max mem: 22446 +train: [17] [160/400] eta: 0:01:56 lr: 0.000022 loss: 0.5162 (0.5254) grad: 0.0539 (0.0538) time: 0.4666 data: 0.0035 max mem: 22447 +train: [16] [280/400] eta: 0:00:56 lr: 0.000034 loss: 0.5395 (0.5309) grad: 0.0512 (0.0537) time: 0.4608 data: 0.0038 max mem: 22446 +train: [17] [180/400] eta: 0:01:45 lr: 0.000021 loss: 0.5151 (0.5256) grad: 0.0564 (0.0543) time: 0.4620 data: 0.0036 max mem: 22447 +train: [16] [300/400] eta: 0:00:48 lr: 0.000033 loss: 0.5373 (0.5314) grad: 0.0544 (0.0538) time: 0.6147 data: 0.1770 max mem: 22446 +train: [17] [200/400] eta: 0:01:35 lr: 0.000020 loss: 0.5153 (0.5265) grad: 0.0565 (0.0542) time: 0.4661 data: 0.0037 max mem: 22447 +train: [16] [320/400] eta: 0:00:38 lr: 0.000032 loss: 0.5265 (0.5309) grad: 0.0544 (0.0538) time: 0.4534 data: 0.0033 max mem: 22446 +train: [17] [220/400] eta: 0:01:26 lr: 0.000019 loss: 0.5157 (0.5253) grad: 0.0524 (0.0538) time: 0.4650 data: 0.0035 max mem: 22447 +train: [16] [340/400] eta: 0:00:28 lr: 0.000031 loss: 0.5216 (0.5308) grad: 0.0528 (0.0536) time: 0.4595 data: 0.0037 max mem: 22446 +train: [17] [240/400] eta: 0:01:16 lr: 0.000019 loss: 0.5233 (0.5261) grad: 0.0505 (0.0538) time: 0.4594 data: 0.0035 max mem: 22447 +train: [16] [360/400] eta: 0:00:19 lr: 0.000031 loss: 0.5239 (0.5305) grad: 0.0500 (0.0537) time: 0.4776 data: 0.0037 max mem: 22446 +train: [17] [260/400] eta: 0:01:06 lr: 0.000018 loss: 0.5329 (0.5272) grad: 0.0505 (0.0537) time: 0.4658 data: 0.0033 max mem: 22447 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 0.5239 (0.5301) grad: 0.0523 (0.0537) time: 0.4522 data: 0.0034 max mem: 22446 +train: [17] [280/400] eta: 0:00:56 lr: 0.000017 loss: 0.5310 (0.5268) grad: 0.0502 (0.0535) time: 0.4601 data: 0.0035 max mem: 22447 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.5257 (0.5301) grad: 0.0519 (0.0538) time: 0.4566 data: 0.0035 max mem: 22446 +train: [16] Total time: 0:03:10 (0.4768 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.5257 (0.5301) grad: 0.0519 (0.0538) +eval (validation): [16] [ 0/63] eta: 0:03:31 time: 3.3640 data: 3.0849 max mem: 22446 +train: [17] [300/400] eta: 0:00:48 lr: 0.000016 loss: 0.5178 (0.5277) grad: 0.0523 (0.0538) time: 0.6387 data: 0.1849 max mem: 22447 +eval (validation): [16] [20/63] eta: 0:00:20 time: 0.3394 data: 0.0041 max mem: 22446 +train: [17] [320/400] eta: 0:00:38 lr: 0.000016 loss: 0.5304 (0.5278) grad: 0.0542 (0.0537) time: 0.4627 data: 0.0040 max mem: 22447 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3397 data: 0.0034 max mem: 22446 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3285 data: 0.0030 max mem: 22446 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3285 data: 0.0033 max mem: 22446 +eval (validation): [16] Total time: 0:00:24 (0.3884 s / it) +cv: [16] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.057 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [17] [340/400] eta: 0:00:29 lr: 0.000015 loss: 0.5153 (0.5276) grad: 0.0514 (0.0537) time: 0.4818 data: 0.0032 max mem: 22447 +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +train: [17] [ 0/400] eta: 0:22:31 lr: nan time: 3.3796 data: 3.0402 max mem: 22446 +train: [17] [360/400] eta: 0:00:19 lr: 0.000014 loss: 0.5153 (0.5276) grad: 0.0514 (0.0537) time: 0.4915 data: 0.0036 max mem: 22447 +train: [17] [ 20/400] eta: 0:03:42 lr: 0.000028 loss: 0.5446 (0.5434) grad: 0.0550 (0.0573) time: 0.4445 data: 0.0031 max mem: 22446 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.5317 (0.5279) grad: 0.0503 (0.0536) time: 0.4583 data: 0.0032 max mem: 22447 +train: [17] [ 40/400] eta: 0:03:07 lr: 0.000027 loss: 0.5347 (0.5356) grad: 0.0525 (0.0540) time: 0.4530 data: 0.0033 max mem: 22446 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.5189 (0.5272) grad: 0.0561 (0.0537) time: 0.4678 data: 0.0033 max mem: 22447 +train: [17] Total time: 0:03:13 (0.4828 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.5189 (0.5272) grad: 0.0561 (0.0537) +eval (validation): [17] [ 0/63] eta: 0:03:33 time: 3.3904 data: 3.1023 max mem: 22447 +train: [17] [ 60/400] eta: 0:02:50 lr: 0.000026 loss: 0.5283 (0.5349) grad: 0.0512 (0.0544) time: 0.4672 data: 0.0035 max mem: 22446 +eval (validation): [17] [20/63] eta: 0:00:21 time: 0.3435 data: 0.0038 max mem: 22447 +train: [17] [ 80/400] eta: 0:02:37 lr: 0.000025 loss: 0.5237 (0.5297) grad: 0.0551 (0.0547) time: 0.4544 data: 0.0037 max mem: 22446 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3407 data: 0.0029 max mem: 22447 +train: [17] [100/400] eta: 0:02:24 lr: 0.000024 loss: 0.5334 (0.5304) grad: 0.0542 (0.0545) time: 0.4516 data: 0.0037 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3327 data: 0.0031 max mem: 22447 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3233 data: 0.0030 max mem: 22447 +eval (validation): [17] Total time: 0:00:24 (0.3919 s / it) +cv: [17] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.056 acc: 0.984 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:23:17 lr: nan time: 3.4948 data: 3.0793 max mem: 22447 +train: [17] [120/400] eta: 0:02:13 lr: 0.000023 loss: 0.5311 (0.5277) grad: 0.0530 (0.0541) time: 0.4556 data: 0.0034 max mem: 22446 +train: [18] [ 20/400] eta: 0:03:48 lr: 0.000012 loss: 0.5190 (0.5329) grad: 0.0505 (0.0519) time: 0.4564 data: 0.0030 max mem: 22447 +train: [17] [140/400] eta: 0:02:03 lr: 0.000023 loss: 0.5101 (0.5259) grad: 0.0529 (0.0538) time: 0.4564 data: 0.0037 max mem: 22446 +train: [18] [ 40/400] eta: 0:03:13 lr: 0.000012 loss: 0.5209 (0.5291) grad: 0.0505 (0.0513) time: 0.4683 data: 0.0032 max mem: 22447 +train: [17] [160/400] eta: 0:01:53 lr: 0.000022 loss: 0.5101 (0.5254) grad: 0.0519 (0.0537) time: 0.4628 data: 0.0035 max mem: 22446 +train: [18] [ 60/400] eta: 0:02:52 lr: 0.000011 loss: 0.5209 (0.5273) grad: 0.0496 (0.0507) time: 0.4512 data: 0.0034 max mem: 22447 +train: [17] [180/400] eta: 0:01:44 lr: 0.000021 loss: 0.5288 (0.5278) grad: 0.0546 (0.0544) time: 0.4708 data: 0.0036 max mem: 22446 +train: [18] [ 80/400] eta: 0:02:39 lr: 0.000011 loss: 0.5202 (0.5267) grad: 0.0506 (0.0513) time: 0.4709 data: 0.0033 max mem: 22447 +train: [17] [200/400] eta: 0:01:34 lr: 0.000020 loss: 0.5457 (0.5288) grad: 0.0546 (0.0541) time: 0.4801 data: 0.0037 max mem: 22446 +train: [18] [100/400] eta: 0:02:27 lr: 0.000010 loss: 0.5364 (0.5300) grad: 0.0528 (0.0517) time: 0.4610 data: 0.0029 max mem: 22447 +train: [17] [220/400] eta: 0:01:25 lr: 0.000019 loss: 0.5293 (0.5287) grad: 0.0527 (0.0544) time: 0.4630 data: 0.0036 max mem: 22446 +train: [18] [120/400] eta: 0:02:15 lr: 0.000009 loss: 0.5277 (0.5273) grad: 0.0510 (0.0516) time: 0.4531 data: 0.0033 max mem: 22447 +train: [17] [240/400] eta: 0:01:15 lr: 0.000019 loss: 0.5324 (0.5295) grad: 0.0527 (0.0542) time: 0.4614 data: 0.0035 max mem: 22446 +train: [18] [140/400] eta: 0:02:04 lr: 0.000009 loss: 0.5295 (0.5296) grad: 0.0501 (0.0521) time: 0.4449 data: 0.0032 max mem: 22447 +train: [17] [260/400] eta: 0:01:06 lr: 0.000018 loss: 0.5324 (0.5294) grad: 0.0532 (0.0542) time: 0.4706 data: 0.0035 max mem: 22446 +train: [18] [160/400] eta: 0:01:54 lr: 0.000008 loss: 0.5284 (0.5294) grad: 0.0515 (0.0522) time: 0.4762 data: 0.0034 max mem: 22447 +train: [17] [280/400] eta: 0:00:56 lr: 0.000017 loss: 0.5091 (0.5284) grad: 0.0543 (0.0540) time: 0.4557 data: 0.0035 max mem: 22446 +train: [18] [180/400] eta: 0:01:44 lr: 0.000008 loss: 0.5257 (0.5293) grad: 0.0527 (0.0527) time: 0.4584 data: 0.0034 max mem: 22447 +train: [17] [300/400] eta: 0:00:48 lr: 0.000016 loss: 0.5145 (0.5285) grad: 0.0522 (0.0540) time: 0.6207 data: 0.1727 max mem: 22446 +train: [18] [200/400] eta: 0:01:35 lr: 0.000007 loss: 0.5374 (0.5297) grad: 0.0531 (0.0531) time: 0.4588 data: 0.0034 max mem: 22447 +train: [17] [320/400] eta: 0:00:38 lr: 0.000016 loss: 0.5233 (0.5279) grad: 0.0495 (0.0537) time: 0.4676 data: 0.0029 max mem: 22446 +train: [18] [220/400] eta: 0:01:25 lr: 0.000007 loss: 0.5252 (0.5279) grad: 0.0534 (0.0529) time: 0.4612 data: 0.0031 max mem: 22447 +train: [17] [340/400] eta: 0:00:28 lr: 0.000015 loss: 0.5233 (0.5281) grad: 0.0495 (0.0537) time: 0.4601 data: 0.0034 max mem: 22446 +train: [18] [240/400] eta: 0:01:15 lr: 0.000006 loss: 0.5252 (0.5289) grad: 0.0534 (0.0533) time: 0.4534 data: 0.0034 max mem: 22447 +train: [17] [360/400] eta: 0:00:19 lr: 0.000014 loss: 0.5352 (0.5288) grad: 0.0541 (0.0539) time: 0.4641 data: 0.0037 max mem: 22446 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 0.5202 (0.5281) grad: 0.0551 (0.0532) time: 0.4592 data: 0.0035 max mem: 22447 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 0.5393 (0.5293) grad: 0.0540 (0.0539) time: 0.4437 data: 0.0035 max mem: 22446 +train: [18] [280/400] eta: 0:00:56 lr: 0.000006 loss: 0.5168 (0.5281) grad: 0.0515 (0.0531) time: 0.4665 data: 0.0035 max mem: 22447 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.5230 (0.5290) grad: 0.0539 (0.0539) time: 0.4551 data: 0.0035 max mem: 22446 +train: [17] Total time: 0:03:10 (0.4755 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.5230 (0.5290) grad: 0.0539 (0.0539) +eval (validation): [17] [ 0/63] eta: 0:03:24 time: 3.2521 data: 3.0150 max mem: 22446 +train: [18] [300/400] eta: 0:00:48 lr: 0.000005 loss: 0.5148 (0.5275) grad: 0.0512 (0.0530) time: 0.6634 data: 0.1850 max mem: 22447 +eval (validation): [17] [20/63] eta: 0:00:21 time: 0.3648 data: 0.0037 max mem: 22446 +train: [18] [320/400] eta: 0:00:38 lr: 0.000005 loss: 0.5224 (0.5279) grad: 0.0488 (0.0529) time: 0.4610 data: 0.0031 max mem: 22447 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3446 data: 0.0030 max mem: 22446 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3177 data: 0.0030 max mem: 22446 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3223 data: 0.0031 max mem: 22446 +eval (validation): [17] Total time: 0:00:24 (0.3939 s / it) +cv: [17] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.5308 (0.5279) grad: 0.0520 (0.0531) time: 0.4754 data: 0.0033 max mem: 22447 +train: [18] [ 0/400] eta: 0:22:58 lr: nan time: 3.4457 data: 3.0469 max mem: 22446 +train: [18] [360/400] eta: 0:00:19 lr: 0.000004 loss: 0.5286 (0.5283) grad: 0.0554 (0.0532) time: 0.4756 data: 0.0034 max mem: 22447 +train: [18] [ 20/400] eta: 0:03:59 lr: 0.000012 loss: 0.5340 (0.5360) grad: 0.0560 (0.0554) time: 0.4882 data: 0.0039 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.5273 (0.5283) grad: 0.0524 (0.0532) time: 0.4679 data: 0.0035 max mem: 22447 +train: [18] [ 40/400] eta: 0:03:14 lr: 0.000012 loss: 0.5226 (0.5271) grad: 0.0536 (0.0546) time: 0.4456 data: 0.0033 max mem: 22446 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.5254 (0.5284) grad: 0.0525 (0.0530) time: 0.4514 data: 0.0034 max mem: 22447 +train: [18] Total time: 0:03:11 (0.4796 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.5254 (0.5284) grad: 0.0525 (0.0530) +eval (validation): [18] [ 0/63] eta: 0:03:33 time: 3.3823 data: 3.0793 max mem: 22447 +train: [18] [ 60/400] eta: 0:02:54 lr: 0.000011 loss: 0.5226 (0.5283) grad: 0.0532 (0.0538) time: 0.4564 data: 0.0035 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:22 time: 0.3748 data: 0.0047 max mem: 22447 +train: [18] [ 80/400] eta: 0:02:38 lr: 0.000011 loss: 0.5223 (0.5280) grad: 0.0513 (0.0533) time: 0.4472 data: 0.0033 max mem: 22446 +eval (validation): [18] [40/63] eta: 0:00:10 time: 0.3512 data: 0.0031 max mem: 22447 +train: [18] [100/400] eta: 0:02:25 lr: 0.000010 loss: 0.5153 (0.5252) grad: 0.0526 (0.0535) time: 0.4471 data: 0.0033 max mem: 22446 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3546 data: 0.0034 max mem: 22447 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3438 data: 0.0033 max mem: 22447 +eval (validation): [18] Total time: 0:00:25 (0.4124 s / it) +cv: [18] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [18] [120/400] eta: 0:02:14 lr: 0.000009 loss: 0.5044 (0.5234) grad: 0.0515 (0.0531) time: 0.4543 data: 0.0036 max mem: 22446 +train: [19] [ 0/400] eta: 0:22:53 lr: nan time: 3.4326 data: 3.0376 max mem: 22447 +train: [18] [140/400] eta: 0:02:03 lr: 0.000009 loss: 0.5207 (0.5255) grad: 0.0515 (0.0538) time: 0.4485 data: 0.0034 max mem: 22446 +train: [19] [ 20/400] eta: 0:03:44 lr: 0.000003 loss: 0.5258 (0.5345) grad: 0.0521 (0.0525) time: 0.4487 data: 0.0037 max mem: 22447 +train: [18] [160/400] eta: 0:01:54 lr: 0.000008 loss: 0.5352 (0.5261) grad: 0.0540 (0.0538) time: 0.4649 data: 0.0035 max mem: 22446 +train: [19] [ 40/400] eta: 0:03:09 lr: 0.000003 loss: 0.5258 (0.5301) grad: 0.0521 (0.0529) time: 0.4588 data: 0.0032 max mem: 22447 +train: [18] [180/400] eta: 0:01:44 lr: 0.000008 loss: 0.5338 (0.5266) grad: 0.0497 (0.0536) time: 0.4711 data: 0.0035 max mem: 22446 +train: [19] [ 60/400] eta: 0:02:50 lr: 0.000002 loss: 0.5231 (0.5258) grad: 0.0520 (0.0522) time: 0.4468 data: 0.0033 max mem: 22447 +train: [18] [200/400] eta: 0:01:34 lr: 0.000007 loss: 0.5288 (0.5248) grad: 0.0497 (0.0534) time: 0.4505 data: 0.0034 max mem: 22446 +train: [19] [ 80/400] eta: 0:02:37 lr: 0.000002 loss: 0.5245 (0.5268) grad: 0.0523 (0.0531) time: 0.4614 data: 0.0035 max mem: 22447 +train: [18] [220/400] eta: 0:01:24 lr: 0.000007 loss: 0.5171 (0.5242) grad: 0.0503 (0.0534) time: 0.4445 data: 0.0032 max mem: 22446 +train: [19] [100/400] eta: 0:02:25 lr: 0.000002 loss: 0.5270 (0.5266) grad: 0.0523 (0.0527) time: 0.4603 data: 0.0035 max mem: 22447 +train: [18] [240/400] eta: 0:01:15 lr: 0.000006 loss: 0.5243 (0.5243) grad: 0.0520 (0.0534) time: 0.4669 data: 0.0034 max mem: 22446 +train: [19] [120/400] eta: 0:02:14 lr: 0.000002 loss: 0.5244 (0.5281) grad: 0.0493 (0.0523) time: 0.4618 data: 0.0036 max mem: 22447 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 0.5328 (0.5245) grad: 0.0531 (0.0534) time: 0.4434 data: 0.0035 max mem: 22446 +train: [19] [140/400] eta: 0:02:03 lr: 0.000001 loss: 0.5255 (0.5294) grad: 0.0496 (0.0521) time: 0.4518 data: 0.0033 max mem: 22447 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 0.5410 (0.5269) grad: 0.0533 (0.0534) time: 0.4478 data: 0.0035 max mem: 22446 +train: [19] [160/400] eta: 0:01:54 lr: 0.000001 loss: 0.5303 (0.5304) grad: 0.0516 (0.0525) time: 0.4708 data: 0.0031 max mem: 22447 +train: [19] [180/400] eta: 0:01:44 lr: 0.000001 loss: 0.5312 (0.5307) grad: 0.0541 (0.0526) time: 0.4592 data: 0.0035 max mem: 22447 +train: [18] [300/400] eta: 0:00:47 lr: 0.000005 loss: 0.5367 (0.5274) grad: 0.0523 (0.0533) time: 0.6315 data: 0.1815 max mem: 22446 +train: [19] [200/400] eta: 0:01:34 lr: 0.000001 loss: 0.5185 (0.5298) grad: 0.0521 (0.0525) time: 0.4639 data: 0.0035 max mem: 22447 +train: [18] [320/400] eta: 0:00:38 lr: 0.000005 loss: 0.5186 (0.5264) grad: 0.0515 (0.0533) time: 0.4461 data: 0.0031 max mem: 22446 +train: [19] [220/400] eta: 0:01:24 lr: 0.000001 loss: 0.5127 (0.5291) grad: 0.0501 (0.0526) time: 0.4539 data: 0.0034 max mem: 22447 +train: [18] [340/400] eta: 0:00:28 lr: 0.000004 loss: 0.5111 (0.5257) grad: 0.0499 (0.0532) time: 0.4399 data: 0.0035 max mem: 22446 +train: [19] [240/400] eta: 0:01:15 lr: 0.000001 loss: 0.5192 (0.5286) grad: 0.0501 (0.0526) time: 0.4655 data: 0.0034 max mem: 22447 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 0.5111 (0.5261) grad: 0.0491 (0.0533) time: 0.4423 data: 0.0034 max mem: 22446 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 0.5062 (0.5259) grad: 0.0485 (0.0531) time: 0.4484 data: 0.0034 max mem: 22446 +train: [19] [260/400] eta: 0:01:05 lr: 0.000000 loss: 0.5193 (0.5279) grad: 0.0521 (0.0527) time: 0.4648 data: 0.0035 max mem: 22447 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.5078 (0.5257) grad: 0.0485 (0.0531) time: 0.4389 data: 0.0035 max mem: 22446 +train: [18] Total time: 0:03:07 (0.4690 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.5078 (0.5257) grad: 0.0485 (0.0531) +train: [19] [280/400] eta: 0:00:56 lr: 0.000000 loss: 0.5271 (0.5283) grad: 0.0521 (0.0527) time: 0.4521 data: 0.0035 max mem: 22447 +eval (validation): [18] [ 0/63] eta: 0:03:23 time: 3.2248 data: 2.9489 max mem: 22446 +eval (validation): [18] [20/63] eta: 0:00:20 time: 0.3435 data: 0.0045 max mem: 22446 +train: [19] [300/400] eta: 0:00:47 lr: 0.000000 loss: 0.5171 (0.5272) grad: 0.0520 (0.0528) time: 0.6214 data: 0.1710 max mem: 22447 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3446 data: 0.0029 max mem: 22446 +train: [19] [320/400] eta: 0:00:38 lr: 0.000000 loss: 0.5171 (0.5269) grad: 0.0540 (0.0529) time: 0.4527 data: 0.0036 max mem: 22447 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3162 data: 0.0032 max mem: 22446 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3140 data: 0.0032 max mem: 22446 +eval (validation): [18] Total time: 0:00:24 (0.3841 s / it) +cv: [18] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 0.5332 (0.5275) grad: 0.0520 (0.0528) time: 0.4632 data: 0.0034 max mem: 22447 +train: [19] [ 0/400] eta: 0:22:22 lr: nan time: 3.3555 data: 3.0192 max mem: 22446 +train: [19] [360/400] eta: 0:00:19 lr: 0.000000 loss: 0.5434 (0.5274) grad: 0.0516 (0.0529) time: 0.4570 data: 0.0034 max mem: 22447 +train: [19] [ 20/400] eta: 0:03:41 lr: 0.000003 loss: 0.5263 (0.5274) grad: 0.0510 (0.0523) time: 0.4439 data: 0.0038 max mem: 22446 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.5219 (0.5274) grad: 0.0516 (0.0528) time: 0.4629 data: 0.0033 max mem: 22447 +train: [19] [ 40/400] eta: 0:03:04 lr: 0.000003 loss: 0.5272 (0.5280) grad: 0.0519 (0.0531) time: 0.4393 data: 0.0030 max mem: 22446 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.5185 (0.5264) grad: 0.0520 (0.0529) time: 0.4518 data: 0.0031 max mem: 22447 +train: [19] Total time: 0:03:09 (0.4742 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.5185 (0.5264) grad: 0.0520 (0.0529) +train: [19] [ 60/400] eta: 0:02:47 lr: 0.000002 loss: 0.5284 (0.5275) grad: 0.0533 (0.0535) time: 0.4560 data: 0.0037 max mem: 22446 +eval (validation): [19] [ 0/63] eta: 0:03:22 time: 3.2177 data: 2.9703 max mem: 22447 +train: [19] [ 80/400] eta: 0:02:35 lr: 0.000002 loss: 0.5332 (0.5296) grad: 0.0512 (0.0528) time: 0.4635 data: 0.0037 max mem: 22446 +eval (validation): [19] [20/63] eta: 0:00:21 time: 0.3639 data: 0.0039 max mem: 22447 +train: [19] [100/400] eta: 0:02:23 lr: 0.000002 loss: 0.5391 (0.5319) grad: 0.0526 (0.0539) time: 0.4440 data: 0.0035 max mem: 22446 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3450 data: 0.0029 max mem: 22447 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3261 data: 0.0033 max mem: 22447 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3266 data: 0.0032 max mem: 22447 +eval (validation): [19] Total time: 0:00:24 (0.3949 s / it) +cv: [19] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +train: [19] [120/400] eta: 0:02:12 lr: 0.000002 loss: 0.5312 (0.5306) grad: 0.0518 (0.0533) time: 0.4495 data: 0.0033 max mem: 22446 +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9836309523809523, "hparam": [26, 1.0], "hparam_id": 44, "epoch": 19, "is_best": false, "best_score": 0.9841269841269841} +eval (train): [20] [ 0/297] eta: 0:14:37 time: 2.9559 data: 2.6820 max mem: 22447 +train: [19] [140/400] eta: 0:02:03 lr: 0.000001 loss: 0.5192 (0.5299) grad: 0.0495 (0.0528) time: 0.4731 data: 0.0034 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:05 time: 0.3276 data: 0.0046 max mem: 22447 +train: [19] [160/400] eta: 0:01:53 lr: 0.000001 loss: 0.5161 (0.5283) grad: 0.0500 (0.0529) time: 0.4563 data: 0.0035 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:44 time: 0.3542 data: 0.0032 max mem: 22447 +eval (train): [20] [ 60/297] eta: 0:01:30 time: 0.3353 data: 0.0033 max mem: 22447 +train: [19] [180/400] eta: 0:01:43 lr: 0.000001 loss: 0.5354 (0.5297) grad: 0.0551 (0.0530) time: 0.4682 data: 0.0036 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:20 time: 0.3403 data: 0.0034 max mem: 22447 +train: [19] [200/400] eta: 0:01:34 lr: 0.000001 loss: 0.5396 (0.5294) grad: 0.0514 (0.0528) time: 0.4649 data: 0.0036 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:11 time: 0.3384 data: 0.0033 max mem: 22447 +train: [19] [220/400] eta: 0:01:24 lr: 0.000001 loss: 0.5360 (0.5295) grad: 0.0514 (0.0527) time: 0.4403 data: 0.0035 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:04 time: 0.3500 data: 0.0037 max mem: 22447 +eval (train): [20] [140/297] eta: 0:00:56 time: 0.3303 data: 0.0033 max mem: 22447 +train: [19] [240/400] eta: 0:01:14 lr: 0.000001 loss: 0.5207 (0.5277) grad: 0.0525 (0.0527) time: 0.4592 data: 0.0035 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:48 time: 0.3527 data: 0.0032 max mem: 22447 +train: [19] [260/400] eta: 0:01:05 lr: 0.000000 loss: 0.5096 (0.5269) grad: 0.0512 (0.0525) time: 0.4440 data: 0.0034 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:41 time: 0.3604 data: 0.0032 max mem: 22447 +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 0.5225 (0.5269) grad: 0.0515 (0.0527) time: 0.4459 data: 0.0035 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:34 time: 0.3447 data: 0.0032 max mem: 22447 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3368 data: 0.0033 max mem: 22447 +train: [19] [300/400] eta: 0:00:47 lr: 0.000000 loss: 0.5225 (0.5262) grad: 0.0514 (0.0526) time: 0.6038 data: 0.1761 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3292 data: 0.0031 max mem: 22447 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 0.5256 (0.5261) grad: 0.0490 (0.0525) time: 0.4405 data: 0.0029 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3379 data: 0.0033 max mem: 22447 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3427 data: 0.0035 max mem: 22447 +train: [19] [340/400] eta: 0:00:28 lr: 0.000000 loss: 0.5331 (0.5265) grad: 0.0511 (0.0524) time: 0.4408 data: 0.0035 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3230 data: 0.0031 max mem: 22447 +eval (train): [20] Total time: 0:01:44 (0.3507 s / it) +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 0.5178 (0.5259) grad: 0.0514 (0.0524) time: 0.4451 data: 0.0035 max mem: 22446 +eval (validation): [20] [ 0/63] eta: 0:03:11 time: 3.0369 data: 2.7601 max mem: 22447 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 0.5120 (0.5261) grad: 0.0525 (0.0524) time: 0.4427 data: 0.0036 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3612 data: 0.0032 max mem: 22447 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3497 data: 0.0032 max mem: 22447 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.5164 (0.5258) grad: 0.0538 (0.0526) time: 0.4499 data: 0.0034 max mem: 22446 +train: [19] Total time: 0:03:06 (0.4661 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.5164 (0.5258) grad: 0.0538 (0.0526) +eval (validation): [19] [ 0/63] eta: 0:03:23 time: 3.2225 data: 2.9947 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3409 data: 0.0032 max mem: 22447 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3386 data: 0.0032 max mem: 22447 +eval (validation): [20] Total time: 0:00:24 (0.3959 s / it) +eval (test): [20] [ 0/79] eta: 0:04:18 time: 3.2660 data: 2.9741 max mem: 22447 +eval (validation): [19] [20/63] eta: 0:00:20 time: 0.3282 data: 0.0043 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3596 data: 0.0028 max mem: 22447 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3522 data: 0.0026 max mem: 22446 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3292 data: 0.0035 max mem: 22446 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3285 data: 0.0034 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3713 data: 0.0031 max mem: 22447 +eval (validation): [19] Total time: 0:00:24 (0.3868 s / it) +cv: [19] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.056 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.9833829365079365, "hparam": [26, 1.0], "hparam_id": 44, "epoch": 19, "is_best": false, "best_score": 0.9836309523809523} +eval (train): [20] [ 0/297] eta: 0:14:47 time: 2.9876 data: 2.7118 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3720 data: 0.0034 max mem: 22447 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3399 data: 0.0032 max mem: 22447 +eval (train): [20] [ 20/297] eta: 0:02:08 time: 0.3379 data: 0.0024 max mem: 22446 +eval (test): [20] Total time: 0:00:31 (0.4002 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9836309523809523, "hparam": [26, 1.0], "hparam_id": 44, "epoch": 16, "is_best": true, "best_score": 0.9836309523809523} +eval (train): [20] [ 0/297] eta: 0:16:21 time: 3.3052 data: 3.0071 max mem: 22447 +eval (train): [20] [ 40/297] eta: 0:01:42 time: 0.3292 data: 0.0035 max mem: 22446 +eval (train): [20] [ 20/297] eta: 0:02:22 time: 0.3733 data: 0.0062 max mem: 22447 +eval (train): [20] [ 60/297] eta: 0:01:30 time: 0.3484 data: 0.0032 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:51 time: 0.3510 data: 0.0033 max mem: 22447 +eval (train): [20] [ 80/297] eta: 0:01:23 time: 0.3858 data: 0.0035 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:36 time: 0.3475 data: 0.0035 max mem: 22447 +eval (train): [20] [100/297] eta: 0:01:15 time: 0.3781 data: 0.0038 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:24 time: 0.3425 data: 0.0033 max mem: 22447 +eval (train): [20] [120/297] eta: 0:01:06 time: 0.3515 data: 0.0037 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:14 time: 0.3318 data: 0.0030 max mem: 22447 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3733 data: 0.0039 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:05 time: 0.3421 data: 0.0035 max mem: 22447 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3506 data: 0.0035 max mem: 22446 +eval (train): [20] [140/297] eta: 0:00:57 time: 0.3398 data: 0.0034 max mem: 22447 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3644 data: 0.0039 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:49 time: 0.3343 data: 0.0034 max mem: 22447 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3462 data: 0.0035 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:42 time: 0.3352 data: 0.0034 max mem: 22447 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3587 data: 0.0032 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:34 time: 0.3363 data: 0.0035 max mem: 22447 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3510 data: 0.0032 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3363 data: 0.0033 max mem: 22447 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3754 data: 0.0038 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3464 data: 0.0037 max mem: 22447 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3626 data: 0.0034 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3367 data: 0.0034 max mem: 22447 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3377 data: 0.0034 max mem: 22446 +eval (train): [20] Total time: 0:01:49 (0.3676 s / it) +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3466 data: 0.0035 max mem: 22447 +eval (validation): [20] [ 0/63] eta: 0:03:05 time: 2.9501 data: 2.6853 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3310 data: 0.0031 max mem: 22447 +eval (train): [20] Total time: 0:01:44 (0.3535 s / it) +eval (validation): [20] [20/63] eta: 0:00:19 time: 0.3216 data: 0.0040 max mem: 22446 +eval (validation): [20] [ 0/63] eta: 0:03:10 time: 3.0248 data: 2.7510 max mem: 22447 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3556 data: 0.0040 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3695 data: 0.0038 max mem: 22447 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3218 data: 0.0027 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3207 data: 0.0030 max mem: 22446 +eval (validation): [20] Total time: 0:00:23 (0.3786 s / it) +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3326 data: 0.0032 max mem: 22447 +eval (test): [20] [ 0/79] eta: 0:04:00 time: 3.0441 data: 2.7711 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3202 data: 0.0031 max mem: 22447 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3204 data: 0.0031 max mem: 22447 +eval (validation): [20] Total time: 0:00:24 (0.3866 s / it) +eval (test): [20] [20/79] eta: 0:00:29 time: 0.3658 data: 0.0037 max mem: 22446 +eval (test): [20] [ 0/79] eta: 0:03:52 time: 2.9368 data: 2.7077 max mem: 22447 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3534 data: 0.0031 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:27 time: 0.3442 data: 0.0137 max mem: 22447 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3508 data: 0.0035 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:15 time: 0.3388 data: 0.0034 max mem: 22447 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3260 data: 0.0032 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3871 s / it) +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3339 data: 0.0026 max mem: 22447 +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.9836309523809523, "hparam": [26, 1.0], "hparam_id": 44, "epoch": 16, "is_best": true, "best_score": 0.9836309523809523} +eval (train): [20] [ 0/297] eta: 0:15:06 time: 3.0538 data: 2.7714 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3151 data: 0.0029 max mem: 22447 +eval (test): [20] Total time: 0:00:29 (0.3694 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 16 | 0.0078 | 0.05 | 44 | [26, 1.0] | train | 0.00093546 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 16 | 0.0078 | 0.05 | 44 | [26, 1.0] | validation | 0.056831 | 0.98363 | 0.0019466 | 0.98182 | 0.002327 | +| flat_mae | patch | attn | hcpya_task21 | best | 16 | 0.0078 | 0.05 | 44 | [26, 1.0] | test | 0.064647 | 0.98413 | 0.0016518 | 0.97974 | 0.0023428 | + + +done! total time: 1:19:32 +eval (train): [20] [ 20/297] eta: 0:02:22 time: 0.3890 data: 0.0040 max mem: 22446 +eval (train): [20] [ 40/297] eta: 0:01:52 time: 0.3524 data: 0.0032 max mem: 22446 +eval (train): [20] [ 60/297] eta: 0:01:35 time: 0.3351 data: 0.0033 max mem: 22446 +eval (train): [20] [ 80/297] eta: 0:01:23 time: 0.3375 data: 0.0032 max mem: 22446 +eval (train): [20] [100/297] eta: 0:01:14 time: 0.3481 data: 0.0033 max mem: 22446 +eval (train): [20] [120/297] eta: 0:01:06 time: 0.3429 data: 0.0035 max mem: 22446 +eval (train): [20] [140/297] eta: 0:00:57 time: 0.3388 data: 0.0034 max mem: 22446 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3447 data: 0.0032 max mem: 22446 +eval (train): [20] [180/297] eta: 0:00:42 time: 0.3462 data: 0.0034 max mem: 22446 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3751 data: 0.0035 max mem: 22446 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3513 data: 0.0035 max mem: 22446 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3417 data: 0.0034 max mem: 22446 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3677 data: 0.0036 max mem: 22446 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3418 data: 0.0034 max mem: 22446 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3369 data: 0.0032 max mem: 22446 +eval (train): [20] Total time: 0:01:47 (0.3609 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:12 time: 3.0495 data: 2.8090 max mem: 22446 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3769 data: 0.0034 max mem: 22446 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3884 data: 0.0036 max mem: 22446 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3262 data: 0.0032 max mem: 22446 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3275 data: 0.0032 max mem: 22446 +eval (validation): [20] Total time: 0:00:25 (0.4095 s / it) +eval (test): [20] [ 0/79] eta: 0:04:01 time: 3.0514 data: 2.8242 max mem: 22446 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3518 data: 0.0039 max mem: 22446 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3624 data: 0.0031 max mem: 22446 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3391 data: 0.0036 max mem: 22446 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3232 data: 0.0033 max mem: 22446 +eval (test): [20] Total time: 0:00:30 (0.3824 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-----------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | hcpya_task21 | best | 16 | 0.0078 | 0.05 | 44 | [26, 1.0] | train | 0.00093546 | 1 | 0 | 1 | 0 | +| flat_mae | patch | attn | hcpya_task21 | best | 16 | 0.0078 | 0.05 | 44 | [26, 1.0] | validation | 0.056831 | 0.98363 | 0.0019466 | 0.98182 | 0.002327 | +| flat_mae | patch | attn | hcpya_task21 | best | 16 | 0.0078 | 0.05 | 44 | [26, 1.0] | test | 0.064647 | 0.98413 | 0.0016518 | 0.97974 | 0.0023428 | + + +done! total time: 0:27:36 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/train_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..11a57f7206852440f6621d15e6133724f2fd0ccd --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__attn/train_log.json @@ -0,0 +1,26 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.6996571159362794, "train/grad": 0.0979245050996542, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.041300048828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.04036376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.03871826171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.03707763671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.035506591796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.03332275390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.030782470703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.028060302734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.024490966796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0206591796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.01698486328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.0115087890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.006156005859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.998514404296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.99145263671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.984857177734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.97677001953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9676800537109376, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9582196044921876, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9499871826171873, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.9407073974609377, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9316717529296876, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.92221435546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.91272216796875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9030712890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8916326904296876, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.881351318359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8718243408203126, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.8582763671875, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8407232666015627, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.823323059082031, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.8055679321289064, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.7781349182128907, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7495289611816407, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.7094561767578127, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.662279510498047, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.602156734466553, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5349765014648438, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.450342016220093, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3345343601703643, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.237157964706421, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.151180188059807, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.045100096166134, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9488795682787896, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.8349508182704448, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.7358211377263069, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.6618295473605393, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.5734008369594812, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.497973748743534, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0160581575287506, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01603284590411931, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01599292135797441, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01595440606586635, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015914267841726542, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.015856829979456963, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.015794262145645915, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01572424022015184, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01563362210523337, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.015536357751116156, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015441665421240031, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.015298161418177187, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.015158889396116138, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014951873803511262, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014751735152676701, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014557302575558423, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0143087277142331, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.014023646006826311, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013724331082776188, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013473807200789452, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.013209564231801777, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012980887147132308, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.012772102123126388, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.012586028552614153, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.012424969656858593, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01226213722024113, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012143351049162447, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.012052100945729761, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011952774170786142, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01186082456028089, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011803740379400551, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.011764016593806445, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.011717173515353351, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.011684968452900648, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.011661624172702431, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.011630899228621275, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.011610455550253392, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011597394403070211, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011669896012172103, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.012027103228028864, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.012230799861717968, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012533877324312926, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.013019248188938945, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.013415391913149506, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.013771971976384521, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.014547430905513465, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014956146699842066, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.015591599463950842, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.016051326259039343, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.027489185333252, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.024527072906494, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0196533203125, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.014908790588379, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.010221004486084, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0037574768066406, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.996533155441284, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9886586666107178, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.97855544090271, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.968055486679077, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9579594135284424, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.943392038345337, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.929940938949585, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.911726474761963, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.895942449569702, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.882289171218872, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.867205858230591, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.852552652359009, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.8394863605499268, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8295841217041016, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8190813064575195, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.8091607093811035, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.798236131668091, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.785876512527466, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.771519422531128, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.751924514770508, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.73138427734375, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.70990252494812, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.675504684448242, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6251320838928223, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5688047409057617, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5062899589538574, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4041550159454346, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.296651601791382, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.1431312561035156, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.9661482572555542, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.7464921474456787, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.4961938858032227, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.2245064973831177, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9769405722618103, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.7912203669548035, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6505599021911621, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5297223925590515, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.44539549946784973, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.37355300784111023, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.31958773732185364, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2791631519794464, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.26353004574775696, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.30379971861839294, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1701388888888889, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17261904761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1857638888888889, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.27232142857142855, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.36904761904761907, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.40401785714285715, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.43601190476190477, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5104166666666666, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.589781746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5773809523809523, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6517857142857143, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7584325396825397, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8023313492063492, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8407738095238095, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8665674603174603, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8881448412698413, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8970734126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9191468253968254, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9216269841269841, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9017857142857143, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01436300840451241, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.013885104794195705, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.01656247431453036, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.029986327130408538, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.10346547214448863, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.13693271898767156, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17039329201856496, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.22047378892997646, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.3085182642767832, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.4239474061654661, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.40978388306256736, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5329334786481008, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7067269941758061, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7520058396109514, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.797846721896487, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8341815672154321, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8555284947242056, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8809078271693854, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9094856464135646, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9065314680934721, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8760774539413385, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 1.5734008369594812, "validation/loss_best": 0.26353004574775696, "validation/acc_best": 0.9216269841269841, "validation/f1_best": 0.9065314680934721} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.946309089064598, "train/grad": 0.09546202041208744, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.003304443359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9972021484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.987569580078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.978372802734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.96943115234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.9578955078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.94571044921875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.9331396484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.9182525634765626, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9044964599609373, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8925885009765624, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.87737548828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.864981689453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8500067138671876, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.837713623046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8272662353515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8151458740234374, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8013702392578126, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7859161376953123, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.770771484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.750225830078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.7259646606445314, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.694228515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.65340576171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.6020187377929687, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5270870971679686, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.446198272705078, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3599438858032227, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2203482246398925, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0206417870521545, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8286564934253693, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.6543623858690262, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4298630997538566, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2430300423502922, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.0451637932658195, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8729828970134258, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7102670001238585, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.5810432304441929, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.48113609045743944, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.398377298861742, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3319209469854832, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.29361511370167137, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.25893961823545397, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.23579754510894418, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.21941841092891992, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.20977087841369213, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.20901282696984708, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.22654972990974784, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.2206662075407803, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015174190453253687, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015018549957312643, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014764243494719267, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014517763932235538, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014275080892257392, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01394473772495985, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013575322623364628, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013176819528453051, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01268332988023758, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012210108547005803, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011808613094035535, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01132448758231476, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01097330701071769, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010624657168518752, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01041525048436597, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010289967998396606, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010202426868490875, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010165560645982624, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01017591281561181, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010212091167923064, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010273245631251484, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010343166512902825, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010424121206160635, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01051237576873973, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01060424217255786, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010696873373817653, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010759526854380965, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010797227639704943, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010814102326985448, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01108630422502756, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011609826628118753, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012168484744615854, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.012935794540680945, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01365801299456507, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014258331903256476, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014817139781080187, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01541518779937178, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.015895203752443195, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.016348241369705648, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01677460300270468, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016315171932801603, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01614887745818123, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.015750209554098546, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015726300640963017, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015744618927128612, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.016147653269581497, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.016644936371594667, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.018141667200252412, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.017558792228810488, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.973371744155884, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.963906764984131, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.948887825012207, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.935053586959839, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9222817420959473, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9062302112579346, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.890343189239502, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8754055500030518, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.859534740447998, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8464486598968506, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.836305856704712, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.82428240776062, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.814455986022949, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8017237186431885, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.78977370262146, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.777951717376709, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7619431018829346, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.741128444671631, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7145845890045166, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6860859394073486, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.644807815551758, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5935842990875244, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5241057872772217, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4330928325653076, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.3188788890838623, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.1564831733703613, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.9841469526290894, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.7953852415084839, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.4816148281097412, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1037873029708862, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.8819066882133484, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.7187336087226868, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.5487160086631775, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.4548097550868988, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.37793266773223877, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.30995801091194153, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.257343590259552, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.22517113387584686, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.20803017914295197, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.21458274126052856, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.23324446380138397, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.24595791101455688, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.23838920891284943, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.24949006736278534, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2297557294368744, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.249505877494812, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.27524763345718384, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.624918520450592, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3848715126514435, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17683531746031747, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.20064484126984128, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2564484126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.34399801587301587, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.40302579365079366, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.45634920634920634, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5049603174603174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6063988095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7232142857142857, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7708333333333334, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8023313492063492, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8536706349206349, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8762400793650794, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9002976190476191, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9124503968253969, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9255952380952381, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9367559523809523, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9300595238095238, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9250992063492064, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9186507936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9174107142857143, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9193948412698413, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9255952380952381, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9164186507936508, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9169146825396826, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8544146825396826, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8916170634920635, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013893937558059696, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.021157146281496494, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.040777719251202424, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.08636678727531094, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.12834998756260743, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.17167518758474928, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2087885571094685, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.27585497460288655, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.42303787069663407, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6039390310689262, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7013427809202585, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7394795723898002, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8101389478202725, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8414249411061451, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8741607376715412, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8912116404270636, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9097988155561874, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9225962962006866, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9234003433330116, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9171801481410611, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9117464953078125, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.903236452254114, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9023250121282045, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9109397888399862, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9216780985899756, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9015284651237471, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9146755200706194, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8714614039892745, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8625885621284956, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 0.48113609045743944, "validation/loss_best": 0.20803017914295197, "validation/acc_best": 0.9367559523809523, "validation/f1_best": 0.9234003433330116} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.545750383734703, "train/grad": 0.09723402388393879, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.940966796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.92901123046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.911287841796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8961322021484377, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.883193359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.8683984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.854951171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8429931640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.8303558349609377, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.819249267578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8094677734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.795723876953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7824139404296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.762386474609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7414697265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7194830322265626, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.688059997558594, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.64502685546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5881700134277343, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5256292724609377, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4347264099121095, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.323597831726074, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1761358070373533, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9845652866363526, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7498492038249969, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.4628771901130677, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.219414133131504, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.0124162162840367, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.7756141586601735, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.579059513360262, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4570381334424019, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.3757692722603679, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.30376971006393433, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.25999537885189056, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.22149654775857924, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1877181404083967, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.16641708062961696, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.15319560838863253, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.14716556429862976, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1421166831254959, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.14607124846428632, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.14352119203656913, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.14811268175020814, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.15885680502280594, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.15725337765179576, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.19318500235676767, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2307730075251311, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.224942409992218, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3717463324498385, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01349083652254194, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013131039061117917, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012556006682571024, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01203413343988359, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011581675091292709, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011080932253971696, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010676010362803936, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010394206594210118, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010206955522298812, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010143203185871244, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010145559418015182, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010192764899693429, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010251023960299789, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01032744399504736, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010390389191452415, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010446850180160254, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01051600428065285, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010602841784711927, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010701054490637034, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010775431280490012, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010821711753960699, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01080286008771509, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010734571951907128, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010780559554696083, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011188449158798902, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011955030295066536, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012729482729919256, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01345934443641454, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.014362556370906531, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.014914674954488873, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.014834806681610644, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.014595073566306382, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.014277462926693262, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014029848219361157, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01368000705493614, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012838442798238248, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.012637376133352519, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.012531093675643206, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012881169286556542, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.012843519556336105, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.013657019477104768, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01362472641747445, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01469782542437315, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.015357847406994552, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.015260787277948112, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.018302372407633813, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.020777379827341066, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.020173877936322242, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.029562034076079727, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.905987501144409, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.892425537109375, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.873676061630249, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8590028285980225, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.847499370574951, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.835125207901001, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8242006301879883, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.814098834991455, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.802248954772949, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.790351629257202, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.778653621673584, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7603402137756348, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.741302967071533, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7108912467956543, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.677919864654541, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6420648097991943, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5896432399749756, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5167088508605957, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.419312000274658, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.313286066055298, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.1614794731140137, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9778013229370117, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.728223443031311, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.389925241470337, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.0657168626785278, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.8134488463401794, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6188657283782959, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.49072790145874023, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3845955431461334, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.31089118123054504, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.27183184027671814, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.24451614916324615, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.21913158893585205, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.20295356214046478, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.184270977973938, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1706196665763855, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.14989477396011353, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.13493235409259796, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1305980384349823, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12304092943668365, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13425710797309875, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.15930107235908508, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1792626976966858, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17274202406406403, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.15637478232383728, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.15249532461166382, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.3650306463241577, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.29714271426200867, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7430374026298523, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17509920634920634, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19940476190476192, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.27976190476190477, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3509424603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.38764880952380953, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4211309523809524, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5049603174603174, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5999503968253969, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.7093253968253969, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8050595238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8556547619047619, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8809523809523809, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9072420634920635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.921875, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9278273809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.933531746031746, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9340277777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9389880952380952, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9441964285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9427083333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.951140873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9568452380952381, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9558531746031746, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9513888888888888, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9474206349206349, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9476686507936508, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9484126984126984, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.949156746031746, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9052579365079365, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9223710317460317, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8707837301587301, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013885104794195705, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.019448390565723978, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.04330062421513575, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1055263479047171, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13239948978219518, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14075501792141204, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16446399764661862, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2811810366621045, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4328715881632579, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.6031514416922722, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.7386185730770065, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8223781191958618, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8522926085038595, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8849287759918913, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9038523845556564, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9131588828096426, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9214186958474935, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9235614835788445, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.929791284335836, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9385082284086811, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9356358963247641, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9450629963319315, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9507374877673901, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9496758702948349, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.953006223462958, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9491964226172452, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9393977905162842, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9361309606757315, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9389382355922048, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9442616716977092, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.934124614405721, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8905204296118789, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9050742749427145, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.85183018422588, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.1421166831254959, "validation/loss_best": 0.12304092943668365, "validation/acc_best": 0.9585813492063492, "validation/f1_best": 0.953006223462958} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 1.3595926529169082, "train/grad": 0.17191165771335362, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.88167236328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8695147705078123, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8535467529296876, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.84145751953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.831826171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.820570068359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.80943603515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.79771728515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.782427978515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7657464599609374, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.74848876953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7203399658203127, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6901617431640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.64010009765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.584429931640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.523305206298828, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4340535736083986, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3120762634277345, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.1523804473876953, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9766743278503418, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.7172538924217224, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.4314073261618614, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.1396226140856742, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.8776142621040344, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6756158941984176, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5051380079984665, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.40072937205433845, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.33519160374999046, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.27111642483621834, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.22170295029878617, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.19289007712155581, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.17397896237671376, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.1558847837895155, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.14398692981339992, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.12881883662194013, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.11671030637808144, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.11238026440143585, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.11292095360346138, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.11163944531232119, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12416019930504263, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1408663562592119, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1495623779296875, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.15887665403075515, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.18195397523231804, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.2388476588204503, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.3905792830698192, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5700275806803257, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.0740430250950157, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.73059546623379, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011425120050553232, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011004125480540097, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01052889139391482, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010275694124866277, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010164357342291623, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010134202798362822, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010169324637390674, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01022811045171693, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01029991805087775, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010362115055322647, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010411926079541445, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010479057675693184, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01054163436871022, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010633370650466531, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0107192967296578, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010792352582793683, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010854693369474262, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010869377134367824, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010808667680248619, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01079072681022808, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011191045297309757, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012030974617227913, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01324056128039956, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.014238283312879503, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.014860661672428251, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.015013305307365953, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01475646679289639, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.014345561512745917, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.013679726540576666, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.013210098769050091, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.012968441166449338, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012683381899259985, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.012460608249530197, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01244210012955591, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.012381552108563483, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012163381110876798, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.012226059128297493, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.012821636642329395, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012885489738546313, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.014219547823304311, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01567150984075852, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016393471396295354, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.016941454987972976, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.019434307925403117, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.024329564662184566, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.033968668668530884, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04206528064329177, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.06671374415047467, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.10525981990620494, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8534321784973145, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8425917625427246, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.828800678253174, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.818059206008911, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8088247776031494, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7970378398895264, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7841267585754395, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.769583225250244, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.749551296234131, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7267706394195557, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.702542304992676, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6621477603912354, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6174733638763428, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.542620897293091, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4586284160614014, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.367016077041626, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.2354068756103516, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.0581939220428467, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.8222287893295288, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.5456953048706055, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.1785391569137573, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.9260539412498474, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7247423529624939, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5294312834739685, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.4128860831260681, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.325175017118454, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2704866826534271, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.23499949276447296, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.2006300836801529, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1748412847518921, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.15861184895038605, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.14749708771705627, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1433364897966385, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.15659429132938385, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1539801061153412, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1540224403142929, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1578761488199234, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15707828104496002, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15419965982437134, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2133144736289978, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1539389044046402, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.19168172776699066, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.16482634842395782, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.21022117137908936, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5418394804000854, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.47952139377593994, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4132276177406311, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.1296236515045166, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6600795984268188, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17385912698412698, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1902281746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.23065476190476192, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.3020833333333333, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.36532738095238093, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.4027777777777778, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.46850198412698413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.5778769841269841, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.6696428571428571, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7385912698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8100198412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.8673115079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8918650793650794, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9159226190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9325396825396826, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.939484126984127, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9449404761904762, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9489087301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9528769841269841, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9538690476190477, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9494047619047619, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9499007936507936, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.949156746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9508928571428571, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9317956349206349, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9362599206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9496527777777778, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9459325396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9025297619047619, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9184027777777778, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9350198412698413, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9104662698412699, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9379960317460317, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01787194159539838, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.034267941216589756, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07129435777578448, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11763317287305051, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1387150560283193, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.15911619581329992, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.24214968347674942, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.3752475860966039, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.5387894925387493, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.6526204686922993, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.7668384579395903, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8389460509157777, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8657951751343114, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8944523639880371, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9155770141266262, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9240986904022054, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9324264041131084, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9399759758169434, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9464534906981047, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9496905009850574, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9524273590408795, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.948512119791391, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.947747619399425, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9452576862515991, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9455652597028891, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9442740993690484, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9449637647325475, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9274210503270555, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9500129996155868, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9307343242566103, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9405831244501651, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9404676663801671, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.855613275015796, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8888739510629667, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9218490764266158, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8673399218220194, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9210406842690206, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.1558847837895155, "validation/loss_best": 0.1433364897966385, "validation/acc_best": 0.9573412698412699, "validation/f1_best": 0.9524273590408795} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.161843977868557, "train/grad": 0.14128521103411912, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8393316650390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.82982666015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8167919921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.80557861328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.794920654296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7803802490234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7634136962890623, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.743558349609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7153253173828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6823629760742187, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.646540222167969, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.585815124511719, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.518355407714844, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.405856170654297, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.282638931274414, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.150231819152832, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9578826904296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.6850921869277955, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.3541513872146607, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.082821124792099, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.8285226276516915, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6349540251493454, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.47832563512027265, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.36781645476818087, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.297415967322886, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.23864912547171116, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.20227441772818566, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.17836901353672147, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.15450614793226122, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.1358907498139888, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.12396272385492921, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.11621358211152255, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.10833702005445957, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.10040029268711806, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.10074530256912112, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.10314374877139926, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1056561712641269, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.10388845802284777, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.12327007931657136, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.11708257863298059, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1478386540338397, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.15456346962600948, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.21306801956146956, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.39173063430003824, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5468707198556513, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.605618695486337, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4459803810808808, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.7177816614322364, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.6466045463923364, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010261945154052227, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010134201599285006, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010086504330392926, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010114092242438345, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01016060533002019, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010222185389138758, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010279550487175583, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010332077955827117, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010393764981999993, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010458662249147892, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010526928904000669, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010633376308251173, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010725461700931192, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01080515150912106, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010798494596965611, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010731554734520614, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01067079634172842, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.011057834548410028, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012098330454900861, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013117809314280748, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0139702252112329, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.014392920008394866, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.014360498599708081, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.014073943868279457, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.013534485353156924, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01284732842585072, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012345421777572483, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.011993186683394014, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011676060988102109, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.011564203870948404, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011541118986206128, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.011728456834098323, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.011981221956666559, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.011793111162260174, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.012262101467931642, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012818014527438209, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01329911184613593, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.013740777637576685, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.015587755498709157, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.014939437286229804, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01728522683493793, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0178910001704935, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02221730068558827, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.034858033671043814, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04429369835648686, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04334187868982554, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03435531418304891, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04849524396471679, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.050143006159923974, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.820931911468506, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8118507862091064, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7984182834625244, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.785722017288208, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7730491161346436, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7549726963043213, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7332513332366943, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7072556018829346, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.669613838195801, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6247990131378174, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.575430154800415, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.4911434650421143, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.397878885269165, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.2447900772094727, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.079606533050537, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.9011049270629883, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.6285350322723389, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2487839460372925, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9483178853988647, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.75644451379776, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.5596215724945068, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.426304429769516, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.34443399310112, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.28727516531944275, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.24540984630584717, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.20928308367729187, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.18925277888774872, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.1760510951280594, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.16202472150325775, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.14899882674217224, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.14209696650505066, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.13100150227546692, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.11986496299505234, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.11271799355745316, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.11175741255283356, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.13348549604415894, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09518231451511383, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1692807972431183, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13800111413002014, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2267792671918869, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2705966830253601, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.8771700859069824, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.219380721449852, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.36567506194114685, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4563707709312439, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2588435113430023, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.44180285930633545, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6317937970161438, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6052698493003845, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17559523809523808, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.21081349206349206, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2775297619047619, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.3559027777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.4166666666666667, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.466765873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.5905257936507936, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6877480158730159, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7740575396825397, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.832093253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8653273809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8918650793650794, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9134424603174603, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9246031746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9317956349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9397321428571429, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9429563492063492, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9454365079365079, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9471726190476191, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9533730158730159, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.957093253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.964781746031746, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.964781746031746, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9503968253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9580853174603174, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9417162698412699, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9226190476190477, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8377976190476191, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9476686507936508, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9300595238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9362599206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9595734126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9375, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9332837301587301, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9382440476190477, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.020202385798042264, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.054882786855489855, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.09749620587552166, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.14322140412824302, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18996181896465317, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.24743998120161925, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.4171529960638805, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5673160154975817, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.6967657852689142, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7729480374907115, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8294743001836815, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8624077140890285, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8905817979362668, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.905500995329396, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9169235047052761, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9269447785776831, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9324932271314, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9353186391194148, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9370654350165104, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9425594808977833, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9459799570473447, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9497889675029038, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9545328457453637, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9593509398213821, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9583132047569446, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9537721868120466, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9648417178400164, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9419016088106696, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9473191350953135, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9183074919561663, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8957313544902907, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7947582041162417, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9409462384886977, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9115232739000586, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9231194207093223, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9557444524414128, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9256460777942737, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9209027992000852, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9326904916984937, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.1056561712641269, "validation/loss_best": 0.09518231451511383, "validation/acc_best": 0.9714781746031746, "validation/f1_best": 0.9648417178400164} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 1.0147806441783904, "train/grad": 0.14191283218562603, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.80766357421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7976324462890627, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7818511962890624, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.7661810302734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.75001708984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.726563720703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.6977838134765624, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.662964172363281, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.611735534667969, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5502001953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.482591247558594, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.3686872863769532, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.245205993652344, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.0450871276855467, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.8226055908203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.5708392810821534, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.2469942536950112, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9546985653042793, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7306646594405174, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.5628283210098743, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.42130418710410594, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.33558383166790007, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.2744781669974327, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.2279799333959818, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.1935144068300724, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.16319497844204306, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.14305591782554983, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.12832489671185612, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.11129867318086326, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0971485495287925, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.08769082017242909, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.08108005557209254, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0742946295067668, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.07114065905101598, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0692425976973027, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.06862764455378055, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.06586484635248781, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.08093742745928466, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1004895590711385, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.10785561522468924, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.15063536752946674, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.23073184482753276, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.26983115685172376, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3058119790349156, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.29429866902530194, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5319819603767246, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.08186558842659, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.41498014161363245, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.3582135585788637, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00986711860401556, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009906760405283422, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009978788814041763, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.0100412412523292, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01009060509968549, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010148878770414739, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01021015241742134, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010279518708121032, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010378156995866448, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010480023147538304, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010563667330425233, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010632799242157489, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01062251177150756, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010526699211914093, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010552612976171076, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01103319025132805, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012126332670450211, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.013360418342053891, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.014073412576690316, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0142027883278206, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01386832786956802, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.013244912545196712, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.012603991029318423, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.012069806493818759, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011709739346988499, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011378929514903576, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01103240913245827, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010747676249593496, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010268564047291874, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009799075287301093, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009473744456190616, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009449350003851578, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009559471814427525, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009751554602989926, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009534266970586031, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009800823128316552, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009714100504643284, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011220763502642513, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012689989754580893, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.013752094671363011, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.016597146766725926, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02336719451472163, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026135549533646555, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027476784840691836, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.028200328278471715, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.043746677916496994, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.07302098208107054, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.03595100077916868, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.030372872301377356, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7983765602111816, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.787663698196411, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7698476314544678, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7515339851379395, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.732346296310425, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.703829526901245, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.668430805206299, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.6247925758361816, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.560241222381592, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.482389450073242, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.3973188400268555, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.255669116973877, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.1040918827056885, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.8550490140914917, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.561132788658142, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2435263395309448, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.9598652720451355, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.7396464943885803, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.544824481010437, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.42142701148986816, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.33931127190589905, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.2845240831375122, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.24107523262500763, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.20718447864055634, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.18255285918712616, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1597347855567932, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.14691723883152008, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.13996577262878418, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.1353778839111328, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1332101821899414, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1288362443447113, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.12401733547449112, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.11580059677362442, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.11321326345205307, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.11456956714391708, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.10992861539125443, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.11157087236642838, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11775675415992737, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12604780495166779, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1306672841310501, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.20038555562496185, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14676062762737274, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15944422781467438, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.33610811829566956, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.25568175315856934, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5448741316795349, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.7486625909805298, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4342016279697418, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5901519060134888, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.1765873015873016, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.20734126984126985, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.283234126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.38268849206349204, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.43253968253968256, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5094246031746031, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6029265873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.6748511904761905, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7549603174603174, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8345734126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8737599206349206, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.894593253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9122023809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9268353174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9337797619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9461805555555556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9506448412698413, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9541170634920635, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9630456349206349, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9501488095238095, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9429563492063492, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9377480158730159, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8936011904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9375, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9288194444444444, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.02129981118466903, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05072512602403387, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.10883969244629409, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.16787798986421917, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.20786711330935834, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.29881677771311926, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.42619938721342543, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5317410118621965, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.6707118679162861, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7879383546778388, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8443068357597427, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8683178704102493, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8897824716208456, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9099579200309456, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9194032514636751, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9279949522889146, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9368101775092568, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9417067522457219, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9453110784282268, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9473138845397072, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9475723723509343, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9457898178858273, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9463593720619533, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9480464763315174, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9554242999358326, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9560738138578928, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9573783163377717, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9589838982589237, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9590170210738918, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9601258437830891, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9563025982548846, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.954367064502588, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9420752394870655, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9551588991448182, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9541982234744039, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9338452944428866, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9485130127557623, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9278839144863722, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8946044353299598, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9282546749612256, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9254327546108159, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.06586484635248781, "validation/loss_best": 0.11157087236642838, "validation/acc_best": 0.9660218253968254, "validation/f1_best": 0.9590170210738918} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.886966553926468, "train/grad": 0.10678331421688199, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7945751953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.782374267578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7615338134765626, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.7397723388671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7166571044921874, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.6819287109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.6382281494140627, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.5841162109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.5039935302734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.408017120361328, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.3047975158691405, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.1347853088378907, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.9512665939331055, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.6346236276626587, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2921777117252349, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.0298955678939818, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.8008480796217918, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5957342012226582, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.4383369641005993, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.34963236309587953, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.2821192902699113, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.23545757960528135, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.19798166766762734, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.16873604618012905, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.14610245870426297, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.1253020893037319, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.11079446868039668, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.10011899593286216, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0880478423461318, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.07828729419969022, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.07257543600164354, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.06753119164146483, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.05972643624059856, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.05409591830335558, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04974134743213653, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.05745212241075933, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.05512630514800548, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0628193727787584, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.09142552535049617, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06897218460217118, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11286425107158721, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10640732331201434, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.16425055960193277, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.16940696441568434, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1415358498506248, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.36764424790628253, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6290240113157779, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.2562359951715916, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.19828503599390387, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010084726398345083, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010138956620357931, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010211218821350485, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010268334588035942, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010318450673948973, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010389979768078775, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010473863885272295, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010567017237190158, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010669049853459001, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010723645295947791, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010709233884699642, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01058743694331497, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010440316312015056, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010739886844530701, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011903986227698624, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013000522702932359, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.013873381493613123, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.014032794712111354, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013715071850456298, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013236747849732637, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.012632677275687456, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012041666663717478, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01153831758769229, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011188997230492532, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01088365624193102, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01061431881505996, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010430836146697401, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010297014112584293, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010059480865020305, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009943998281378298, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010103268943494186, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01007614440866746, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009427702588727698, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008682450075866655, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00848139426263515, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010041420654160901, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00939552933734376, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009849456737865693, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012617046250379644, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010420766305178403, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.014820166238350793, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.013169740514713339, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.017158477186749222, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.017806787091540172, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01650662840314908, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.030673861795658012, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.04677706804126501, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.024304569483447266, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.020379497667890975, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7783849239349365, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7645604610443115, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.740692615509033, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7151215076446533, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.68788480758667, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6464338302612305, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.594074010848999, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.528874158859253, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.4326298236846924, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.3187735080718994, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.197737216949463, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.9996447563171387, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7815494537353516, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.392450213432312, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.0581367015838623, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.8505374193191528, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.6523472666740417, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.47340458631515503, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.3682153522968292, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.30737340450286865, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.2570464313030243, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.22158321738243103, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.1929212063550949, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.17070558667182922, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.154944509267807, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.14283710718154907, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.13629259169101715, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.13078811764717102, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.1248951256275177, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1189001128077507, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.11277391761541367, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.1075630709528923, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.10568626970052719, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.10101023316383362, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09949339181184769, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1334783285856247, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.10175381600856781, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10271693766117096, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10596588999032974, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1353076696395874, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13011600077152252, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1693011075258255, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1875089704990387, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1737346351146698, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1339149922132492, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.49460849165916443, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4313437342643738, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.27794358134269714, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.16986724734306335, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.1736111111111111, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.19122023809523808, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2544642857142857, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3430059523809524, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.38244047619047616, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.44221230158730157, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5409226190476191, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.671875, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.763640873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8236607142857143, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8680555555555556, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8921130952380952, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9087301587301587, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9203869047619048, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9325396825396826, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9402281746031746, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9461805555555556, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9503968253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9536210317460317, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9580853174603174, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9618055555555556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9620535714285714, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.964781746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.966765873015873, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9618055555555556, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9650297619047619, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9556051587301587, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9360119047619048, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9494047619047619, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9521329365079365, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9605654761904762, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.017739485021690954, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.035474447659285605, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.09083925881216061, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.13276880242369365, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.1525833120006071, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.2205359342694136, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.3482285962372001, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.5322794516608698, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6718714518658964, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.761591235929327, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.827188337109474, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8634974947084528, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8852121252092372, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8986064836247165, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9137346041384872, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9237461778027404, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9325846911740813, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9383829420847772, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9434751605691796, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9480913565548195, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9508831014143088, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9530535445817014, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9533080936755715, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.955875040553809, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9563305046099292, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9589739318026069, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9576050247464309, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9589994493694507, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9615593565986383, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9540344374874964, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9649451583643908, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9662859678221177, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9644423107149003, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9561239921993163, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9565996778110935, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9568507560020763, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9461507706290624, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9546099455985338, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9659158976066439, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9242538540845363, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9387185513016114, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9451613660074639, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9500392061956778, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.05512630514800548, "validation/loss_best": 0.10175381600856781, "validation/acc_best": 0.9712301587301587, "validation/f1_best": 0.9649451583643908} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.7903685021400452, "train/grad": 0.08917538592591882, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.771531982421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7557733154296873, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7281201171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6983673095703127, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.666204833984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.617138671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.5550466918945314, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.477985534667969, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.365494842529297, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.234175109863281, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.0956151580810545, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8664129066467285, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.6048486518859864, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.1957835620641708, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.9203923532366752, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.7345522132515907, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.5417913238704205, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.4008231332153082, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.314616858959198, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.2622099735960364, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.21684162992984057, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.18383788086473943, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.15642357021570205, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.13420273705385624, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.1167368740029633, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.10042002765461802, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.08887750223278999, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.07998904795385897, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.06981216900981962, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.06176606181077659, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0559423603862524, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.051267087729647755, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.04300843053497374, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.04501564047299325, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04052211369387806, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.04126703574322164, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.045474771736189724, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.050194788398221134, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0349724502209574, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.06541864961385727, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.09240261635743081, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06505852371454239, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09438948376104235, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.08820057002827525, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09212943689897657, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.17775171377696097, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3316367605794221, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1959295131918043, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.10168332464993, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010265234061516821, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010314492324832827, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010381169077008963, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01044190480839461, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010501843318343163, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010589255248196422, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01067934749647975, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01075266681611538, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010772300229873508, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010696018789894879, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01055362165439874, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010372816750314087, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010664302555378527, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01210121588781476, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013203983455896377, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013794639082625508, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.013845976325683296, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.013451091796159744, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012839892916381358, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.012333428235724569, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011705443479586393, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011251917898189277, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01083721101982519, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010466369383502752, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010189409067388624, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009928984243888408, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009705524349119515, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00951410552021116, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009242357931798324, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009156330379191786, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009115975170279853, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009004937858553603, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008202482524793595, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00901571758207865, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008279287346522324, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00802939588931622, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00903133109852206, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008869640235207043, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006705547510646284, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010381672197254374, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.012819976946047973, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011010745343519375, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012758675618097187, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012612749387553777, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01329929136642022, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01943494665523758, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.029832519243936987, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.022335799959255383, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012777486656850669, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7587218284606934, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.74116849899292, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.710085391998291, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6763689517974854, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6398568153381348, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.58354115486145, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.512385368347168, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.424391269683838, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.297081232070923, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.150238275527954, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.9957226514816284, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.735276699066162, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.4288115501403809, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.031907320022583, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.7989981770515442, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.6284915804862976, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.45685258507728577, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.35695093870162964, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.2907558083534241, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.24865108728408813, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.2120443880558014, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1860312521457672, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.1655602604150772, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.15131406486034393, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.14281341433525085, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.13525035977363586, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.1272428035736084, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.12053770571947098, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.11739324033260345, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1164563000202179, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.11917773634195328, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10974099487066269, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.11012645065784454, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.11569112539291382, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1106770858168602, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1326320469379425, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12346760928630829, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09303838014602661, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10143490880727768, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1933901011943817, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14885151386260986, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1328243911266327, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.19327577948570251, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17619909346103668, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.16893905401229858, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.19974245131015778, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.33337730169296265, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4975365698337555, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.16938740015029907, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.1736111111111111, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.19345238095238096, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.25148809523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.34499007936507936, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3950892857142857, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.42956349206349204, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5347222222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6346726190476191, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7341269841269841, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.830109126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8695436507936508, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8953373015873016, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9131944444444444, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9285714285714286, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9357638888888888, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9434523809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9494047619047619, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9521329365079365, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9548611111111112, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.957093253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9613095238095238, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9630456349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9623015873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9600694444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9709821428571429, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9471726190476191, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.957093253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9255952380952381, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9618055555555556, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.017739485021690954, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.03834475296364549, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.08606855958622564, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.1389694125693889, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.15764446434104137, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.19217203231582586, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.32744008079966097, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.45990355283794787, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6415156937613743, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7852746831068035, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8389459307349822, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8681128588094453, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8913899558563846, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9106372899715934, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9190339832726958, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9287851187100613, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9398559840905845, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9433874359360322, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9489350610930707, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9520170499019116, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9515398098855086, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9553419363831623, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9565362620697956, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9577617983964886, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9571677565790915, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9577264448242049, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9599150322196043, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9605961935595255, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9557801369325946, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9584227697324543, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9570532153030545, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.956618220861833, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9657525247509016, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.962395233714889, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9348526620894079, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9553478837013356, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9630466558997194, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9543456657213772, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9575205252343864, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9621554523956614, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9605311880225067, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9521620123426787, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9192147305600942, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9578581094590642, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.050194788398221134, "validation/loss_best": 0.09303838014602661, "validation/acc_best": 0.9709821428571429, "validation/f1_best": 0.9657525247509016} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.721119130551815, "train/grad": 0.07719222538173198, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7520782470703127, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7325091552734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.697352294921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6590740966796873, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.6172726440429686, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.553025817871094, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4718692016601564, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.372613830566406, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2308599090576173, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0686096954345703, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8967153167724609, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.5993875122070313, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.2712924325466155, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.9257374554872513, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.7082228748500348, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.5398075214028358, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.40013675279915334, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.3128449309617281, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.2527384924516082, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.21347388528287412, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.17808977797627448, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.15250313103199006, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.1308014685474336, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.11223938305862248, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.09699415551498532, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.08250623925589025, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.07141487766057253, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.062145534856244924, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.05078299516811967, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.041694266470149156, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.036261419570073485, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03242941261269152, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.027145805563777686, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.022453625062480567, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.022398603884503245, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0218933261372149, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.022003373559564353, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.02310544847510755, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.026652303701266648, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.045604923581704496, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05757064555771649, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.05803086029365659, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.07245464527979494, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.07839474325999618, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.06598016616888344, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08636476044543087, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10675795332528651, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.2031009160168469, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0714411960914731, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010354649997316301, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01040017326362431, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010468271013814956, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010536490408703685, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010606562693137676, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010697393117006869, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010774755496531724, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010804284098558128, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010743939576204866, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010595734158996492, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010455025366973132, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010681819971650838, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011711807087995112, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013035563318990171, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013769796979613603, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013806560565717519, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.013404045449569822, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01275871079415083, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012083501534070819, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.011517569073475897, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010907401028089226, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010503404028713702, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01018866039812565, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00987406208179891, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009621093809837476, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009385649535106495, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009066957311006263, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008652038519503549, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007994052747962997, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007422204239992425, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007073778768535703, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006858317235601135, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006575221009552479, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0058600298181409015, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005926379271550104, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005677094176644459, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0055754485234501775, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005366300148161827, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005941671464242972, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00861084726813715, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009481228636868764, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00973151059319207, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011012604054703843, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01200090820537298, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010644064196676482, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011545544259715825, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014638379462776357, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0211502851737896, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00953256578402943, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.73974347114563, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7182655334472656, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6797122955322266, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6373698711395264, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5909583568573, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.519649028778076, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.429896354675293, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.320797920227051, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.166250228881836, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9898158311843872, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8010993003845215, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.4658913612365723, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.1338838338851929, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.8301255106925964, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.6278770565986633, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.4754634201526642, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.37169501185417175, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.30250102281570435, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.25229212641716003, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.21823392808437347, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.18734489381313324, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.16499179601669312, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.14771424233913422, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.1349990963935852, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.12714670598506927, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.12156391143798828, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.12134738266468048, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.12277775257825851, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.11908484995365143, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.11310499906539917, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1082291528582573, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10666393488645554, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.10998397320508957, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.10364334285259247, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.11256346851587296, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.10791990160942078, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.12189289927482605, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10632387548685074, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09602387994527817, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.125701904296875, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.19714951515197754, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.17488443851470947, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.18022730946540833, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1530410498380661, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.15444625914096832, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.15312299132347107, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2219337522983551, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.18728844821453094, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.08482208847999573, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.18948412698412698, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.24454365079365079, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.33209325396825395, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3854166666666667, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.43253968253968256, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5161210317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6557539682539683, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7472718253968254, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8201884920634921, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8678075396825397, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.890625, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9094742063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9223710317460317, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9337797619047619, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.939484126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9479166666666666, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9523809523809523, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9556051587301587, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.957093253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9615575396825397, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.964781746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9697420634920635, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9558531746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9632936507936508, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.966765873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9766865079365079, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.018055658849796694, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0342890039188111, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0841273887128134, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.13053770846329849, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.1540892809515567, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.20400471154533473, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.31938531174779033, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5041472956082443, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6462378282996278, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.771978733808673, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8384088108209456, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8638923306675996, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8850726695460861, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9009582472592993, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9150482152885852, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9222041752128466, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9339621259011579, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.941018732424534, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9463773506743852, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9489055652580409, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9522078832095117, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9536142961911548, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9567925766649514, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.952630039743176, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.953875141309698, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9561011523154486, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9583896393351006, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9603621168557072, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9581107710182211, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9624298641818395, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9601224244381111, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.963211222091356, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9611029824091981, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9643426244730994, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9678907944307812, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.960444904711379, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9521493468645701, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9551530868111, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.956431893802862, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9626349689009127, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9571547412557048, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9617137667738627, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9640370052781299, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.956291608648708, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9751905629944323, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.0714411960914731, "validation/loss_best": 0.08482208847999573, "validation/acc_best": 0.9766865079365079, "validation/f1_best": 0.9751905629944323} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.6630741408467293, "train/grad": 0.06951072920113802, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7291180419921877, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.705313720703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6621441650390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6145965576171877, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5626187133789062, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.4828485107421874, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3832382202148437, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.2636868286132814, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.09611515045166, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.9049591064453124, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.697300853729248, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.3328850531578065, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.027342437505722, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.7458551524579525, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.5445728600025177, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.414849888831377, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.3220948236435652, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2572010450437665, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.20988020237535238, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1781759525462985, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.1491542164981365, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.12772032836452127, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.10944556241855025, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.09302627433091402, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.07942607720382512, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.06629491586238145, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.05629646081477404, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0484021676145494, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.039430618761107324, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.03192184185609222, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02659912271425128, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.022678640326485037, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.017705718763172628, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.014164356105029583, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.013779312605038285, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.009927203357219696, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.01268386867828667, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.010780208893120289, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.01412262043915689, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.03480925035662949, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.02554278335534036, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.02615960923023522, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0367963382974267, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.04186599123291671, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.046180424932390454, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.04465509626083076, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.04420824822038412, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.07436343661509454, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.03769553639926016, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010642514599021524, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010689317020587624, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010766481149476021, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010844236749690025, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010917124124243855, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010992368480656297, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011016860587988049, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010958651644177735, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010778598794713616, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010556975731160491, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010507528039161116, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011370749522466212, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012540178473573178, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013762467566411942, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014069559932686389, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013847290601115675, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0133100519888103, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012708866554312408, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012028306487482042, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.011438429306726903, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010763475118437782, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010246366765350103, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009817699601408094, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009413166143931449, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009024894995382055, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00854323873994872, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008075135151157155, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007623148300335742, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007171084422734566, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006669892976642586, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006049676371621899, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005621089562191628, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004907442073745188, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00414184184250189, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004473583592189243, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003310833148425445, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004010473498055944, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003562506777016097, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004369766080417321, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007952045455895132, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006473021918936866, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006859028529579519, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007571841849712655, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008564920710168735, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008919924523852388, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009067458304270986, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008829913508561731, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011839294677920408, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.007311604180431459, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.721386671066284, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6958913803100586, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.649664878845215, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5985472202301025, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5425426959991455, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.4566733837127686, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.3500430583953857, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.222810983657837, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0451555252075195, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.8412951231002808, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.615991234779358, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.2315858602523804, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.9512560367584229, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.6881374716758728, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.4976130723953247, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3945165276527405, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.3185887634754181, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.2628916800022125, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.22049252688884735, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.19225947558879852, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.16786085069179535, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.15081706643104553, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.13749688863754272, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.12806884944438934, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.12139236927032471, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.11492541432380676, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.11108370870351791, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10973931103944778, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.11131055653095245, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.11060868948698044, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10918741673231125, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.11113996058702469, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.11058573424816132, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.10995417088270187, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.10676734149456024, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.10441474616527557, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1063109040260315, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.11190219223499298, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11397749930620193, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11790687590837479, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10091910511255264, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12071023881435394, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.16094113886356354, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.11238120496273041, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.16508068144321442, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1469445526599884, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1969558745622635, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.11274391412734985, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.14174385368824005, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.18452380952380953, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2261904761904762, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.30654761904761907, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.36532738095238093, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4114583333333333, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4888392857142857, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5887896825396826, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6974206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7800099206349206, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8563988095238095, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.886656746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9072420634920635, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9231150793650794, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9397321428571429, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9528769841269841, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9573412698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9603174603174603, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9625496031746031, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9632936507936508, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.964781746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.964781746031746, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.964781746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9642857142857143, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.96875, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9747023809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9677579365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9645337301587301, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9613095238095238, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016893042209509622, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.029160847953036084, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.066190289417751, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.11671109213149282, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.1447144892600559, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.17842874370144954, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.28298529138106676, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.41286063218516356, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5696424221964909, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7106420158264549, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8182445225082982, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8587733337378619, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8817048035659012, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9011155116570263, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9140359670394398, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9227108272470033, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9320123248140048, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.940476575251749, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9472851842371771, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9519623981880915, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9543239439307226, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9554825956299617, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9584042049012411, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9593302921059743, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9596895093717832, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9610575278465522, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9599609678479967, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9605442357503877, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9593070529859586, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9636764476007385, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9612166180361867, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9638410468321587, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9644103533364928, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9614641880133048, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9606783830743415, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.961957558281337, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9642816764037333, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9696574909053874, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.968841806078827, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9588223724074865, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9643785058367033, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9450568656175782, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9638048372519064, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9627783773572373, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9648678356149011, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9610077794820064, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 0.02554278335534036, "validation/loss_best": 0.10091910511255264, "validation/acc_best": 0.9747023809523809, "validation/f1_best": 0.9696574909053874} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.6271157956123352, "train/grad": 0.06344343876466155, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.7157476806640624, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6879705810546874, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6377163696289063, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5819464111328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.5209579467773438, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.4280731201171877, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.313520660400391, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.177862777709961, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.9889774703979493, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.7707358551025392, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.526492052078247, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.1431181275844573, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.8869115045666695, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6299108403921128, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.45327374115586283, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.35899410024285316, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.28605325996875763, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.23141048349440096, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.18967281958088278, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1610718862339854, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.13481412816792726, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.11538879686966538, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09838992707431317, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.08306024992838502, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06999370230361819, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.057288375524803994, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.047788697658106685, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.040349946543574336, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0316205788590014, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.024141716370359063, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.019369704993441702, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.01608241711743176, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.012617371259257198, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.01087011988274753, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.01118456332013011, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0069178103562444445, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0070722300000488755, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00518407273106277, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.019048304837197064, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.023695660522207618, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.01723520865663886, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.016382580008357763, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.02440677033737302, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.015103329010307788, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.02398051298223436, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.02127767285332084, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.02500460552982986, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.02339028055779636, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.03659743633121252, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010314311913680286, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010368023335468024, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010463016843423247, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01055614520329982, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010634367442689837, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010700889290310442, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010695101041346789, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010597108076326548, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010399863764178008, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010262197465635836, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01055021076463163, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011845422210171819, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013014925271272659, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01386065644910559, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013870133289601653, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013372921906411648, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012718363991007208, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012062824179884047, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011390885161235929, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010875370292924345, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010329966926947235, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009887516086455434, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009449960764031857, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008967774065677076, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008490850934758782, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007895834614755586, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0073288593871984635, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006826721542747691, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0060911522433161735, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005269528162025381, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004714215547428466, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004251037489739247, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003702431475248886, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003374542878300417, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0033151147916214542, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0024290532151644583, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0025694280953757697, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0019691352455629384, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0056584065509377975, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006280523965178872, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004497779791799985, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0047738800539809745, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005571760019374778, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004354983259763685, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.006154438623307215, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005356394058799197, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.006071801723774115, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005616835861728759, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006832012463564752, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.704355239868164, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6750216484069824, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.621612310409546, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5622267723083496, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4973833560943604, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3987948894500732, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.278184413909912, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.1361334323883057, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.938657522201538, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.7085177898406982, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.4481592178344727, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.069634199142456, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.8293349742889404, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.5788673758506775, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.42743924260139465, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3491896688938141, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2865087687969208, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.2392270863056183, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.20326261222362518, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.17961402237415314, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.15971943736076355, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.14471156895160675, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.13279356062412262, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.12341715395450592, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.11560092866420746, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1081933081150055, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10465952008962631, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.1042923629283905, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10393999516963959, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10125485062599182, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10034285485744476, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.09974242001771927, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0969238132238388, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09124244749546051, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0897296890616417, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.10151047259569168, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09401494264602661, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08688763529062271, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11398174613714218, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11365009099245071, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.10019077360630035, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09101659804582596, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.096988745033741, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.07963856309652328, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09630335122346878, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.07742663472890854, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09550339728593826, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.08429457247257233, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.11190534383058548, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.1775793650793651, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2003968253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.27331349206349204, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.35267857142857145, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39806547619047616, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.46081349206349204, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5669642857142857, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6557539682539683, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7591765873015873, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8298611111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8844246031746031, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9052579365079365, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9141865079365079, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9270833333333334, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9375, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9449404761904762, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9501488095238095, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9521329365079365, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9553571428571429, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.957093253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9613095238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9635416666666666, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.96875, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.96875, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.972718253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9670138888888888, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9704861111111112, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9774305555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.970734126984127, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.022530802208930195, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.044792952995169534, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.100703927940158, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1400035943697091, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.16637372663420721, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2427359740466271, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3819869498322915, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.50469767046596, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6758262661655243, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7831656644085118, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8591002934136092, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8804935826119162, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8907459967787494, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9087836672544427, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9202542689998209, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9305220534161999, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9385813160692623, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9420274522450598, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9460495956852961, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9470261002851055, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.952589624976099, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9567356313191449, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9598600073485815, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9622000972011633, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9619374185021602, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.962605017850102, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.963310170155587, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9638730732541347, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9637979223723157, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9670318466305662, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9695863179700167, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9693724982234668, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.967099476549831, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9665855699039625, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9699279464587909, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9578744912533386, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9664736448454747, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9719059332791021, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9729333184444342, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9715137008649586, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9727239778744877, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9731238479297065, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.976446736699332, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9768883059986716, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9674567919427953, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9668264300097814, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.02127767285332084, "validation/loss_best": 0.07742663472890854, "validation/acc_best": 0.9801587301587301, "validation/f1_best": 0.976446736699332} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.5959062911570072, "train/grad": 0.060018715113401414, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6958477783203123, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6644610595703124, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6071817016601564, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5435302734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.474198913574219, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3693544006347658, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2417566680908205, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.0920267868041993, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.883611297607422, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.6385785579681396, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.364226884841919, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.0042738401889801, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.7764782238006592, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.5303379932045936, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3925330360978842, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.31725874967873097, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.25632324315607546, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.20948372915387153, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.17344500090926884, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.14837326109409332, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.1248684991709888, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.10678828814998269, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09038458632305264, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.07532118234783411, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06279434812255204, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.05086690865457058, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04211580728180706, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.0350532416254282, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.026946379179134963, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.020334851946681737, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0160361010953784, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.012851305725052952, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.008286310462281107, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.005644879322499036, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.004195241192355752, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.003082677274942398, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0029680788423866035, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0025630880706012248, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.005800119843333959, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.006965417880564928, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00646964424289763, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.007957054292783141, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.008326840735971928, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0042566217854619025, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.008737640967592598, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.014987166756764054, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.014859679210931063, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.014278546506538987, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.032386946072801945, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01039264225633815, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010450027342885733, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01055009697098285, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010638666634913535, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01070463149342686, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010732299953233451, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010668785346206277, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010514328929129988, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010278674638830126, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010240819302853197, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010832067863084376, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012154077137820423, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013143898150883616, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013549638520926237, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013228686326183379, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012736080256290734, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01216465986566618, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01157469330355525, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01093671582872048, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010450859556440264, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009939920040778816, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009506503965239973, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009060921764466911, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00859874333254993, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008183447933988645, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007727737489622086, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007378227369626984, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006977973307366483, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006323143757763319, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005492372243897989, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004789656187058427, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004163146087084897, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002939530557196122, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0020481366441526916, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001615593561436981, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0012337781689711847, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0012368493008398217, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0010713506814136054, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00247884717224224, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0024280813018776825, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.002587985609516181, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00287118542861208, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0026969567384730908, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0017114769688123489, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.003039986977037188, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004409914583329737, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004234798798825068, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.003536802786766202, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005785403189511271, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6891024112701416, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6562962532043457, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5962750911712646, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.529529571533203, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.457066774368286, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3479344844818115, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.215867519378662, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.0615627765655518, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.8469977378845215, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.592409372329712, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.3083840608596802, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.9605603218078613, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.7413656711578369, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.503879725933075, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3845312297344208, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.3186957836151123, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.26420220732688904, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.22212904691696167, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.18999986350536346, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.16842970252037048, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.14999771118164062, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.13713441789150238, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.12764732539653778, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.12033584713935852, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.11455558240413666, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10923127830028534, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10710921883583069, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.1077795922756195, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10784875601530075, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10682537406682968, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10559903830289841, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10521301627159119, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0964585468173027, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09260830283164978, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0921911969780922, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09313684701919556, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09181077033281326, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08611147105693817, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08099424093961716, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08257399499416351, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07873892039060593, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09788383543491364, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.07718653976917267, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.07788791507482529, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.07689934968948364, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0960383489727974, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.0943404883146286, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.08311689645051956, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.08502817153930664, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.171875, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.18526785714285715, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21676587301587302, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.30654761904761907, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.36755952380952384, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.40922619047619047, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4930555555555556, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6078869047619048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.689484126984127, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7906746031746031, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8494543650793651, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8891369047619048, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9104662698412699, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9228670634920635, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9337797619047619, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9409722222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9489087301587301, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9556051587301587, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9561011904761905, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9583333333333334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9610615079365079, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9625496031746031, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.966765873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9657738095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9652777777777778, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9670138888888888, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.980406746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9749503968253969, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9759424603174603, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015615046696687809, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.029672982512466226, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.058584873945048285, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.11828527596485133, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1461192240464349, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.17495000915248757, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2914754140321019, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.44374621584636004, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.5587452675223904, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.728420761782667, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8088972361416974, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8629808504270975, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8877639163910898, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9026843116904475, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9158118779061478, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9246629447775183, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.936220943813917, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9451360663003912, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9456675256445315, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9490946544958877, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.953036806501089, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9527880015427757, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.954872015881385, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.957717857568138, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9603467041473344, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9603584924065144, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9581364710930681, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9583500718079628, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9609148057951857, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9607459341659502, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9646392553154638, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9656001025831993, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9668463910186207, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9692199494211232, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9657738778949717, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9708591449829269, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9742363441640155, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9755605022529081, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9742521204887076, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9717439135103542, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9785186214867041, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9737931221030178, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9773402756671863, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9683395229603734, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9737383949744887, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9727052386061326, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9730499946567636, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 0.008326840735971928, "validation/loss_best": 0.07718653976917267, "validation/acc_best": 0.980406746031746, "validation/f1_best": 0.9785186214867041} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.5727336883544922, "train/grad": 0.057446765229105946, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6842608642578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.649412841796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.58559814453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5148712158203126, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4382456970214843, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.323605194091797, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.185859603881836, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.025510063171387, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.8022886085510255, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.5359373092651367, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.2474132180213928, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.9151553201675415, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6996159574389458, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.4689500626921654, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.355162128508091, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.29007319748401644, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.23530748359858988, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.19224892921745776, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.15794926097616555, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1341080722399056, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.11191614632494748, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0945683017000556, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07919144610874355, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06507642904296518, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.053262519165873524, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.041946422588080165, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03373169656842947, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.02740157412365079, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.02039598803035915, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.014767611231654883, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.010963071770966053, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.008097370192408561, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.004868193734437227, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.003382758563384414, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0024880964774638414, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0019209518563002349, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0016379789356142282, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.001468294393271208, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0022396001126617194, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.002083838079124689, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0017371851392090321, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00533158571459353, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.002834226917475462, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0018678565323352813, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0020816556550562384, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0050905266497284175, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0037554436270147563, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.005586038874462247, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.01268541419878602, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010604435850400478, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010660559181123972, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01075185481691733, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01082705050939694, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010869055618532002, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010854144513141364, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010743995141237974, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010558828804641962, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010347562476526946, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010512606874108314, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011361296405084431, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012703663501888514, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013506722040474414, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013566346135921776, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013033621399663388, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012491296264342963, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01187789875548333, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01125313737662509, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010579273079056293, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010101638413034379, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009586442748550326, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00910072555183433, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0086199932906311, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008108213564846665, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007578893904574216, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006913558573578484, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006312534436583519, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005799245142843574, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00504630967770936, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004233824006805662, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0035125337267527357, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0027284821793728043, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001642247774361749, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0011457704018175718, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.000845606419898104, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0006619520610183827, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0005957533882610732, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0005017279914682149, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0008182279494212707, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0009104316072989604, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00078602017765661, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0019700013124020186, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0011058627589682147, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0008654893719176471, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0008844378214189419, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0016280841525258439, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0016268941785165226, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0016312298159573402, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0029800845534919064, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.676116466522217, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6403329372406006, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.57466983795166, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5019583702087402, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.423227310180664, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3056540489196777, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.164829969406128, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.001049041748047, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.7721232175827026, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.4970101118087769, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.205210566520691, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.8854913711547852, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6756879687309265, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.4577411413192749, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3566482365131378, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.29864203929901123, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.24952314794063568, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.21115390956401825, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.18164338171482086, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.16194288432598114, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1443300098180771, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.13188543915748596, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.122162364423275, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.11532057076692581, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.11076819896697998, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1062375009059906, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10395659506320953, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10248500108718872, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10232874006032944, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10128215700387955, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10025765746831894, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10021436959505081, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0953497663140297, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09152105450630188, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09049701690673828, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09286268055438995, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09212615340948105, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08659936487674713, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07707389444112778, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07969488203525543, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07715045660734177, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.07897268235683441, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.07997305691242218, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06696226447820663, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.06417237967252731, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.06479855626821518, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.08287845551967621, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.06079252064228058, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.06995587050914764, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17584325396825398, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.19990079365079366, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.25297619047619047, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3392857142857143, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.39112103174603174, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.43154761904761907, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5374503968253969, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6440972222222222, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.71875, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8167162698412699, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8673115079365079, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8963293650793651, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9139384920634921, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9246031746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9357638888888888, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9427083333333334, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9499007936507936, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9538690476190477, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9583333333333334, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.966765873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.96875, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.972718253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.980406746031746, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.980406746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9799107142857143, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.020263948266814123, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.044245395136166446, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.08716483151245592, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.13593934811764902, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.15724718754207787, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.20084219823696, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3504793624354052, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.49004206073634055, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6023880066371282, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7666788305104438, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8356871374094383, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8701619586198992, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8903807678805931, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9042138241920196, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9175163843548511, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.925271824150719, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9358600616613276, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9425181337726339, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9488153212684656, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9521355991545646, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9567646012991673, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9583892036185615, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9597619868308561, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9623405233505767, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.962317500372784, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9633734234864276, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9617905251106733, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9632497458943658, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9633469267059289, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9631646489162006, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9670070441791639, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9671493654735495, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9676810607326558, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9700660048603286, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9671951410869404, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9702672025608402, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9734871050634416, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9756281230435367, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9765585352452022, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9766268756712961, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9797369993400816, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.976370498137067, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9809075972673941, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9806971844742534, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9769159057473163, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9788080886649256, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9770884803342705, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0020816556550562384, "validation/loss_best": 0.06417237967252731, "validation/acc_best": 0.9833829365079365, "validation/f1_best": 0.9809075972673941} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.5556242468953133, "train/grad": 0.05729130513966083, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6669940185546874, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6293841552734376, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.560274658203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4841375732421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4020016479492186, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2799184417724607, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.1345098876953124, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.966065444946289, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.7304463005065918, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.4476096248626709, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.1596007239818573, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.8534021210670472, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.644586988389492, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.4344560323655605, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3330835524201393, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2734912087023258, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.22263258680701256, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.18217055363580584, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1497642032057047, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.12682566145434976, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.10524041029624641, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08857085647061468, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07358559703454376, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.059602232594043014, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04810185547918081, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.037400124054402115, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.029408119339495897, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.023251811573281884, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.016390015166252853, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.01119440200738609, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.008065927382558584, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.005904827266931534, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.003706383239477873, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0027020827401429415, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.001987334620207548, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.001629173392429948, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0013888000044971704, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0011823017057031393, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0011809584219008684, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0009386031329631805, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0010141895525157452, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0010094315838068723, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0015837591234594583, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0009364694822579622, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.001262834556400776, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.001774528007954359, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.002856960613280535, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.00430032909847796, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.008062924155965448, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010650268718600274, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01071183297317475, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010806299545802176, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010877811079844833, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010907528423704207, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010865194173529744, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010729009467177093, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010526813790202141, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01034897604957223, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010689312117174268, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011645389823243021, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01302668495103717, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013671443578787149, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01356871030293405, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01293681335169822, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012417036835104226, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011859578122384846, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01127890455769375, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010653011901304126, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01016665781615302, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009631100567057729, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00918120692949742, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008729252410121261, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008241877425462008, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00767472088104114, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006957314412575215, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0062636642181314525, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005575955853564665, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004563970260205679, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0035739728168118746, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0028040539580979386, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0021322896938363554, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0014063283515861258, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0009979701260454021, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0007256067530033761, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0005834227778905188, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0005110963955667103, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0004056580768155982, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0004737679308891529, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0003717891118503758, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0004433185751622659, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0004762886418211565, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0005620165965228807, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00037441350155859255, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0005515352212569269, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0008047000628357637, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0011682265268609627, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015380671328603058, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0020662937143060846, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.665532350540161, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6272969245910645, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5570430755615234, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4794564247131348, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.395815134048462, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2718935012817383, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.1243624687194824, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.9531726837158203, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.7131470441818237, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.4228044748306274, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.1332088708877563, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.8321315050125122, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6237901449203491, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.42854705452919006, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.33813461661338806, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.28434595465660095, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.238138347864151, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.2017165571451187, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1738598495721817, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.1550941914319992, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13868629932403564, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12721668183803558, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11821085214614868, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.11216665059328079, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10753040760755539, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10341891646385193, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10151128470897675, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10093732178211212, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10137784481048584, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10022006183862686, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10011220723390579, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10063330829143524, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09651630371809006, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09274602681398392, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09029753506183624, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09420909732580185, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09146033227443695, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08719657361507416, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07607938349246979, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0717896893620491, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07441773265600204, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06857357174158096, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06500571221113205, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06637928634881973, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.057282108813524246, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.057937316596508026, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.07004772871732712, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.06435645371675491, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.06576842069625854, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17881944444444445, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.21031746031746032, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.27653769841269843, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3541666666666667, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4000496031746032, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.45287698412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5610119047619048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6669146825396826, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7435515873015873, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8303571428571429, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.875, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9020337301587301, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9181547619047619, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9270833333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9367559523809523, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9446924603174603, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9526289682539683, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9543650793650794, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.96875, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.970734126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9786706349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013885104794195705, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.023718395756823447, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05316162128048575, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.10102083555342072, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14068461258422657, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.16440806601002872, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.23125157965275786, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3793014623021348, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.523491627962911, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6464778275955105, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7826267916697198, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8426082222429297, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.874868598332463, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.896083996749689, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9074381223682425, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9197097818583904, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9296097259806921, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9402560354389001, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9437326407497464, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9505594820128807, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9542971250404623, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9568197779768145, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9585672573973182, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9604829666430926, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9636217750297581, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9620475669667622, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9621456195471242, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9613081679932753, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9620798070495147, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9629750117453882, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9645023142976805, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9666295859554529, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9662532168278104, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.96757911947538, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9686604804241276, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9675081440197502, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9705285994783998, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9748104536942984, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9774482834915403, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9752874393507647, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.977231330471148, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9803982762561935, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9765845156226567, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9816963041278103, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9793080168791897, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9788085246612122, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9778290476227782, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9760535287790272, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.001262834556400776, "validation/loss_best": 0.057282108813524246, "validation/acc_best": 0.9833829365079365, "validation/f1_best": 0.9816963041278103} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.5413352301716805, "train/grad": 0.055022747181355955, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6541644287109376, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6144149780273436, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5415380859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4610626220703127, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.37458740234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2464022827148438, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.094051513671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.9176753616333009, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.6703386116027832, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3735754346847535, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.08872230052948, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7963357824087143, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.588265315592289, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3989703370630741, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3088125829398632, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2548051068931818, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2084120848402381, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.17133992064744233, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.14153712229803206, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.12055307492613793, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.10038880763575435, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08448282646946609, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07006494138389825, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05646204491145909, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04513400539755821, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03436185183003545, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0265036385320127, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.020700169689953328, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.014189373953267932, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00922582706436515, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.006379955485463142, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.00470001732930541, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0030750628001987934, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002310315100476146, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0017310098931193351, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0014188777841627597, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0011654211953282356, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0010385840013623238, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0009111323207616806, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006900292262434959, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0007671959325671196, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0007116594072431326, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007463086396455765, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008850221708416938, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009303891658782959, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0012238283455371856, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0016302433982491493, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.002947457078844309, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.005086353858932853, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010530185734387488, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010595868804957718, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010698159837629647, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010768810627050698, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010788010037504136, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010726878351997584, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010568255491089076, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010352556419093162, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010199208983685822, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010643422494176775, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0115977126872167, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012872688067145645, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013350984356366098, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01311152100097388, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012530087712220847, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012021539898123592, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011447874091099947, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010820051201153546, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010128663701470942, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00958736116765067, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008981568997260183, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008478528964333236, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007960504796355962, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007387803265592083, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006816309745190665, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006137840250739828, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005452486952999607, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004798162580118515, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003819831163273193, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002833510110795032, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002098809143062681, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0015783388901036233, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0010467187233734875, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0007803780744143296, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0005860297103208723, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0004567551270883996, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00038174641278601487, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00032978235871269137, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0003069213454000419, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00025249294756577, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0002817536412658228, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0002572460015380784, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0002880052828368207, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00030563190624889104, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0003142944308456208, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00038853875990753296, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0005316567126465088, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0008092265560117085, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0012509177681204165, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6575560569763184, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6173627376556396, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5436594486236572, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4625794887542725, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.375462770462036, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.246936321258545, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0946383476257324, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.91825532913208, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6700326204299927, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3698723316192627, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.084932565689087, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.794791579246521, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5875551104545593, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.40906834602355957, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3250481188297272, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.27438515424728394, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2303575575351715, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.19588740170001984, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1691150963306427, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.15128803253173828, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13564442098140717, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12519879639148712, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11770263314247131, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.11308576166629791, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.11033827811479568, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10722816735506058, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10568208247423172, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10537911206483841, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10523741692304611, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10413149744272232, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10302752256393433, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10263747721910477, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09541453421115875, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09264912456274033, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09081070125102997, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09323772042989731, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.090834841132164, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08549001067876816, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07615003734827042, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07125198841094971, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07284774631261826, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06670250743627548, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06351690739393234, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06370805203914642, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05531955882906914, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05570724233984947, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06792991608381271, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05749061331152916, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.05982488393783569, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1817956349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2204861111111111, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.28943452380952384, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3576388888888889, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4017857142857143, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4556051587301587, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5791170634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6773313492063492, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7497519841269841, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8368055555555556, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8829365079365079, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9055059523809523, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9203869047619048, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9300595238095238, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.939484126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9466765873015873, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9536210317460317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9565972222222222, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9603174603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9627976190476191, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.966765873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.96875, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9719742063492064, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.982390873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9801587301587301, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013888047800722664, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02681143430730654, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0625674377978372, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.10750357153634227, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14128319274079895, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.16513934771597216, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2352831455283388, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4030586468958221, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5399617419529965, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6607182060032293, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7956869028324628, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8589297764236302, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8803111801010188, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8989341392413872, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9114764186004588, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9228146674917429, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9327578276935875, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9421300694963092, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.947489211939706, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9522196516023439, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9552157869574639, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9581826848541611, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.96035489038688, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9606473351815142, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9620270434485004, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9620992347574018, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9621059036108073, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9603861050691261, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9609067958928057, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9620016780052235, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9631349583824571, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9658656424515799, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9659022227286336, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9666175770638632, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9698371359717047, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9680120883301202, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9709281599185473, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9747648834335157, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9770290623819518, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9746832587656555, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.977702567904979, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.98014465625866, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9778799007519513, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9812850446625532, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9803160508626719, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9789361107558979, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9788373460267772, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9775009461024557, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0009303891658782959, "validation/loss_best": 0.05531955882906914, "validation/acc_best": 0.9831349206349206, "validation/f1_best": 0.9812850446625532} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.5463548131287098, "train/grad": 0.05502687584608793, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.66521240234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6251959228515624, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.552084655761719, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4714410400390623, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.384798736572266, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2567308807373045, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.1049393081665038, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.9294317626953126, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.683546905517578, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.388231315612793, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.1041313207149506, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.8110451397299766, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.6021634191274643, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.4117797122895718, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.31968843974173067, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.264142073020339, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.21630339320749045, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.17814177822321653, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.14702922973781823, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1253310932777822, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.10483469653874636, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08874729208648205, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.07403028526343405, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06008125397376716, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04825611968524754, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03704265019856393, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02880708044394851, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.022388559859246017, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.015462124506011605, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.010110323755070568, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0069621622562408446, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0050411241594702, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0033169961534440517, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0024618276115506888, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0018346395436674356, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0014635507855564355, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0012258136738091706, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0010745777003467083, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0009542268607765437, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0007044294290244579, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.000783972404897213, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.000754504082724452, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0008436953742057085, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0009028023481369019, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009867668617516757, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0013194362074136735, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.001600045459344983, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.003106672614812851, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.004920303067192436, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010494776335544884, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010559633190277964, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010659173163585365, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010729580132756383, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01075092083774507, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010693844235502183, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010544051385950296, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010337317890953273, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010196609012782574, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010669974791817367, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01164315028116107, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012907210760749877, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013393271653912962, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013169517475180328, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012548848639708012, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012007366160396486, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011394891638774425, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010757854303810745, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010067884200252593, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009550831033848226, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008984685327159242, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008512638452230022, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007997007641242816, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007406720322323963, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006761233806610107, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005979241625173017, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005298791656969115, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004645857085706666, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037838138415827414, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0029059607119415885, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002210806584917009, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0016749761201208457, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0011152491984830703, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0008085725661658216, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0006084172298869816, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00046648041723528876, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0003931241335521918, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00033418627383071, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0003110612667296664, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00026218460907330156, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0002848171684308909, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00026815300325324645, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00031337621982856944, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00030583264751840036, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00035629075862743777, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0004218742334887793, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0005893479556834791, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0009254363262152765, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0011633236575289629, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6575701236724854, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6174156665802, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.543794870376587, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.462697744369507, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3756015300750732, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.246896982192993, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0944809913635254, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.9180651903152466, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6696984767913818, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3693561553955078, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0845606327056885, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7944881319999695, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.587253749370575, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.40860360860824585, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.32445457577705383, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.27389171719551086, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.22975094616413116, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1949392557144165, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1680685430765152, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.15008941292762756, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13447241485118866, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12356621026992798, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11554714292287827, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.11012781411409378, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10659194737672806, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10335153341293335, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10256969928741455, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.1027783527970314, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10349579155445099, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10167588293552399, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1010255515575409, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.1017739474773407, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09667609632015228, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09371490776538849, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09160562604665756, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09365975111722946, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09207622706890106, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08697674423456192, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07653055340051651, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07297677546739578, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0734798014163971, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06879901140928268, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06453102082014084, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06519778817892075, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.056035421788692474, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.057727374136447906, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06935741007328033, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05985298007726669, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.05979480966925621, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1708829365079365, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1847718253968254, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.22643849206349206, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.30257936507936506, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3680555555555556, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.40600198412698413, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4635416666666667, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5793650793650794, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6721230158730159, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7433035714285714, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8340773809523809, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8799603174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9052579365079365, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9208829365079365, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9310515873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9399801587301587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9484126984126984, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9546130952380952, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9598214285714286, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9635416666666666, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9645337301587301, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9670138888888888, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9675099206349206, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.96875, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.970734126984127, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.982390873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.980406746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9799107142857143, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0142525659991365, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.029262833350254067, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.06707250437339807, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.11620249500805595, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14575814447133373, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1685215498300162, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.24575173737413292, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4081833796115016, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5335961627054591, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6468058007329451, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.7910645121576272, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8546937875363699, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8800190053004755, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.899617458235168, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9138151383429474, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9235766761635075, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.935434701318823, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.944077394622314, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9509243709049396, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.954579735901663, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9565354961652158, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9574973339720438, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.959786967912966, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.959724820097689, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9611408072935349, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9615809544740643, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9605878589795034, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.961396146343158, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9623398183452481, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9624036938319639, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9651766829425212, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9649832192046747, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9672513686056958, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9674085156794254, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9693614366656058, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9672202326306373, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9704088994959128, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9738505375612737, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9768411456813242, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9752014230497013, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9759134610914502, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9797795599551475, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9778351161878205, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9815044110638685, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9800531112292542, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9777395620833254, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9792520593491383, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9774407404819289, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0009867668617516757, "validation/loss_best": 0.056035421788692474, "validation/acc_best": 0.9833829365079365, "validation/f1_best": 0.9815044110638685} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.5350722815096378, "train/grad": 0.05384581604972482, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6503411865234376, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.608883972167969, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5329049682617186, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4493341064453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.359732818603516, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.227921447753906, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0722671127319336, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8921009445190429, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.6389040565490722, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3363688707351684, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0587879186868667, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7756481617689133, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5688628029823303, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.39105353251099584, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.3042146772891283, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2513182444125414, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20528900239616632, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.16832692593336104, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1384824987128377, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11727254427969455, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09732645271345973, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08152331661432982, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06713092380203306, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.053359938701614734, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04212277784943581, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03168457405641675, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.024112613294273614, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.018314971243962645, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.012339779334142804, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.00808783777989447, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005711107486858964, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.004261444415897131, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002777531873434782, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002125103259459138, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.001588063407689333, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0013262598775327205, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.001075186599045992, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009859967231750488, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0008534510340541601, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006580776441842317, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0007186969649046659, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0007087958138436079, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0008000759687274695, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008409608248621226, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009315500501543283, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0012875473592430353, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.001589617058634758, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.002598044266924262, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.003685950553044677, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010303266616538166, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010369461642112584, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010470426427200436, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010535457250662149, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01054611787898466, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010471218414604664, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010304451435804367, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01009431820595637, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009995965131092816, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010584594884421676, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011580380746163427, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012786733000539244, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013178148376755416, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012850105012767017, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012251262178178877, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011736744788940996, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011159482861403376, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010547144038137049, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00989701210288331, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009406936077866704, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008861222674604506, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008355637110071257, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00781853381660767, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007195446867262945, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0065371646347921345, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005746695420239121, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005025217563961633, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00433256889344193, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0033929232324589973, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0025063466989377046, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0018784729814797173, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0014413525322743226, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0009633580586523749, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0007058829617017182, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0005275842317860224, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0004148206272657262, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0003412193096664851, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00029688611590245273, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00026669670687624604, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00021844540075107943, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0002400926018526661, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0002280459980465821, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0002603044843635871, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002808254728006432, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0002973395563276426, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00039169118161225925, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0005082715175376507, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006492347256426001, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0008420448706601746, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6518735885620117, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.610410690307617, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5344018936157227, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4507062435150146, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.361210823059082, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2294156551361084, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0737969875335693, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8938138484954834, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.639941930770874, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3335950374603271, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0530871152877808, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7695168852806091, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5642862319946289, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3962463438510895, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3162125051021576, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2675139605998993, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.22501669824123383, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.19115404784679413, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1652539223432541, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14767716825008392, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13245131075382233, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12186537683010101, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11362035572528839, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10844113677740097, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10524031519889832, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1018051952123642, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10076899081468582, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10131537169218063, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10211437195539474, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10097291320562363, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1003601923584938, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10131894052028656, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09546229243278503, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09282613545656204, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09096929430961609, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09434658288955688, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09185236692428589, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08613976836204529, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07678955048322678, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07163023203611374, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07273726165294647, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06710747629404068, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06454519182443619, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06415975093841553, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05621683970093727, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05557522550225258, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06514788419008255, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05688059702515602, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.058520156890153885, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17113095238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1865079365079365, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.23239087301587302, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.30654761904761907, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.36929563492063494, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.40947420634920634, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.47271825396825395, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5932539682539683, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6867559523809523, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7596726190476191, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.84375, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8851686507936508, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9074900793650794, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9226190476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9317956349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9399801587301587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9499007936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9563492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9605654761904762, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9610615079365079, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9660218253968254, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.966765873015873, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.966765873015873, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.972718253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9816468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014606805419953402, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.031105941092725613, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07291346491928741, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.11767409961875, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14537545037386712, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17221670330496933, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2622071384869102, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.423961947999373, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5509338612901726, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6766153184811284, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8034561359037643, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8601425463668593, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8834238902587719, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.901203601595851, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.914118348829666, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9238467700172942, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9375160130437824, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9455397072319278, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9518242052311181, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9531111194134733, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.956923792759481, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9594759027975266, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9591685873257637, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9600651259186059, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9610992848431604, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9618369940995452, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9618928842473095, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9615016630800248, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9624210797561601, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9623640894872698, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9631517693540723, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9667384201129313, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9674378610444685, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9676057135305136, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9696286323541192, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9676967166984379, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9698135369718704, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9748717774734958, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9770444895041724, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.975968382530957, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9770101051443596, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9791349280774773, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9770302733541375, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.982624690022995, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.98108493895599, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9790467028439706, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9799315870061752, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9796405966055876, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0009315500501543283, "validation/loss_best": 0.05621683970093727, "validation/acc_best": 0.9841269841269841, "validation/f1_best": 0.982624690022995} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.5381086042523384, "train/grad": 0.05459214057773352, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.656871337890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.615880432128906, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.540439453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4576400756835937, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3687525939941407, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2379190063476564, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.083157081604004, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.9039002227783204, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.651313533782959, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3476456022262573, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.067204179763794, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.781703200340271, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5744775353372097, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3953873787820339, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.30757556967437266, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2544381543248892, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20841575935482978, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.17140421148389579, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.141469063218683, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.12012819515541195, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0997684471681714, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08360097701661288, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06882462851703167, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.054843812566250566, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.043399372659623625, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03256646442227065, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02465192049741745, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01869233027100563, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.012532230224460364, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.008079690402373671, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005672335950657725, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.004240763997659087, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002826889678835869, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002158328853547573, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0016286414209753274, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0013401373196393251, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.001098455749452114, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009665477462112904, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.000851752320304513, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006642405223101377, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0007228514738380909, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0007050867285579443, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.000758343692868948, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0009017072804272174, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.000963553637266159, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0013198341522365807, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.001532326927408576, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0025418082997202872, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0037460104376077653, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010406636374536902, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010476888560224324, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010581832467578352, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01065095245372504, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010670182052999735, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010610609683208167, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010464192028157413, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010275298736523837, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010188297592103482, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010772788906469941, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01181727295741439, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013129447987303138, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013551740953698755, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013173975627869367, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01257526352070272, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012051024036481976, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011449949478264897, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010782863786444068, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010042250289116055, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009492214000783861, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008904254888184368, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008391601053299383, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007854516819352285, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00723471482982859, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006562532588141039, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005732990772812628, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00495593610976357, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004218652576673776, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0032286035869037734, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0023462909352383577, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017403688191552646, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0013293609098764137, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0008608846839342732, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0006472912040771917, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.000492211353048333, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0003992413748346735, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00032787383661343484, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00029280799804837443, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00025875482122501126, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0002129467400663998, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00023379900583677226, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00022174205294504646, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.000252358974503295, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002911961828795029, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0002852548237206065, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00040265485100462686, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00046979275852208956, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006380199587874814, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0008289042972319294, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6519412994384766, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6104352474212646, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.534473419189453, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4507997035980225, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.361325263977051, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2295656204223633, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0739214420318604, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8938673734664917, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6398191452026367, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3334605693817139, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0532969236373901, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7698025107383728, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5645164251327515, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3965250849723816, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.31641870737075806, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2675423324108124, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.22506831586360931, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.19127586483955383, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16544373333454132, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14802004396915436, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13266363739967346, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12195731699466705, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11413464695215225, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10918169468641281, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1057487353682518, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.1026538535952568, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10148131102323532, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.102048859000206, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10257108509540558, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10089384019374847, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10021389275789261, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10101053863763809, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09580151736736298, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09335927665233612, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09127707779407501, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09395493566989899, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09145773202180862, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08648739755153656, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07626321911811829, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07100369036197662, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07229488343000412, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06682227551937103, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06396140158176422, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06386616080999374, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05591655522584915, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.0553336963057518, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06573209166526794, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.056252434849739075, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.057652562856674194, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17113095238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1865079365079365, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.23189484126984128, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3082837301587302, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37003968253968256, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4097222222222222, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4729662698412698, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.5947420634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6850198412698413, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7628968253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8444940476190477, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8839285714285714, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9092261904761905, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9340277777777778, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9399801587301587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9499007936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9585813492063492, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9618055555555556, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9635416666666666, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9672619047619048, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9747023809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.980406746031746, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9813988095238095, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014607677752740736, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0307452005294039, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07278301556299835, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.11905168625578808, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1449925958089852, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17189827668013843, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2631728115643047, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4251112440286749, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5480298850494226, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6815511618603761, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8044489454737762, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8571156445508017, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8857236689679346, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9018263901552753, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9165784801233479, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9228446210725252, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9375138683191929, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9442270827483277, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9488573181821128, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9539511162112991, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9561424682193633, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9599401562414801, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9597754257651937, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9620272848325494, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9622829458777235, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9621377805468401, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9628172448906485, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9631779074078821, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.96189311497005, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9634467350983625, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9636096101327926, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.968375091774019, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.968194848216663, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9676637744546527, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9693617844745837, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9671778856799885, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.969663185709752, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9736264704065759, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9765010166872873, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9752662087393014, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9772357592686512, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.979912188670977, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9763204547409513, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9816845578016307, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9807462746735596, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9787495608722567, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9803529841388096, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9790565844169722, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.000963553637266159, "validation/loss_best": 0.05591655522584915, "validation/acc_best": 0.9831349206349206, "validation/f1_best": 0.9816845578016307} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.5305194860696792, "train/grad": 0.05447894221171737, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6468597412109376, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6045455932617188, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.526891174316406, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.441656188964844, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3506434631347655, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2169457244873048, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0593576049804687, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8775252151489257, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.6213300132751465, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3151471996307373, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0401213359832764, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7593384450674057, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.553161447942257, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3809210042655468, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.29615480251610277, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2445315369591117, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.19974871814250947, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1636492832005024, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13451623532921075, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11373648520559072, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09418876053765417, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07866376485675573, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06454728573560714, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05122486608102918, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04014421296305955, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.029622911037877203, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.022215771153569222, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.016788701079785823, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.011335463048890233, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007336972625926137, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005162898665294052, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003884229641407728, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002596232742071152, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.001983226463198662, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0015380731411278247, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0012527100089937447, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0010466566495597363, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009344033244997263, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0008316497132182121, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006430893763899803, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0007002333737909794, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0007043495681136846, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007857532147318124, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008592750318348408, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009604589361697436, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0013609313778579235, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0015081615559756755, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.002453662734478712, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.003399349320679903, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01052321330178529, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01059298791224137, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010696317504625767, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010760516121517866, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01077052888693288, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01069279974559322, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01052458080695942, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010315634773578495, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010228334895800799, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010848303274251521, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011880762139335276, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013100686226971447, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013497501839883625, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013083197087980806, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012448235175106674, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011899538468569518, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011269172870088369, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010621174771804362, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00994092769920826, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00943675456335768, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008882095222361386, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008356832325225695, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007787598827853799, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007079219981096685, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006357264929683879, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0054784710018429906, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0046683653409127146, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00393562534765806, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003000538004853297, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0021595123210863677, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0015957892185542732, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0012251434428617357, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0008152795548812719, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0006213696246413747, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00047824838489759716, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0003801847025169991, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00031934062208165414, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00028179075630760056, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00024838824858306905, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00021117299802426716, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00023409196552165668, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00022386312825801725, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00025199015166435854, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002694916014024784, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0002969133837177651, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00039241747948835835, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004664194423094159, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006162848256644793, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0007220533942745533, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.648305654525757, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6060373783111572, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5285212993621826, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.443375587463379, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.35231876373291, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2186856269836426, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0610263347625732, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.878869891166687, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6213783025741577, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.312010645866394, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0344432592391968, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7544537782669067, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5511213541030884, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.38920366764068604, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.311387300491333, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2637633681297302, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.22210870683193207, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18886932730674744, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16317205131053925, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14647305011749268, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13166989386081696, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12129514664411545, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11357197910547256, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10849469900131226, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10490110516548157, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10161243379116058, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10035742074251175, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10077688097953796, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10188157856464386, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1007683128118515, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10116824507713318, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10191024094820023, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09615431725978851, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09402290731668472, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09190675616264343, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09455583989620209, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09205708652734756, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08697621524333954, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.0768153965473175, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07241780310869217, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07286522537469864, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06739917397499084, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06468401104211807, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06505490839481354, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05600973963737488, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05556688457727432, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06537696719169617, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.056343965232372284, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.05860854685306549, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17113095238095238, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18824404761904762, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.23561507936507936, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31200396825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37202380952380953, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4097222222222222, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.48115079365079366, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6011904761904762, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6904761904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.769593253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8472222222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8834325396825397, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9097222222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9226190476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9327876984126984, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.939484126984127, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9489087301587301, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9553571428571429, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.96875, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9680059523809523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9811507936507936, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014608627590065645, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0329199506062145, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07534001532982258, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12116812854765403, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14593584482001187, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17315056114575192, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2764840249248954, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.43365194429685905, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5590726123703702, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.693364510996173, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8066819136586719, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8567911631273668, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8863543598672082, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.902673426843965, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.915219933748894, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9231460533919007, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.936426151494938, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9449898879053745, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9506187449761809, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9543971874146977, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9553020738078231, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9575410297225482, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9594177539488422, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9621710705393492, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9632542547608264, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9625768640060851, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9621838662095252, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.962391523562283, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9627532957578754, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9626326531357814, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9639360632510483, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9665362892065456, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9671028364098438, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9668845857551218, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.971205198298579, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9673085113232309, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.969995503155751, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9742558739856496, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9776149880933203, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9750638632085584, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9769557951123905, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9795237197852477, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9774325719503678, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9814644112916608, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.980572241203034, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9790001345366499, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9787129102391108, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9784448793934188, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.0013609313778579235, "validation/loss_best": 0.05556688457727432, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.980572241203034} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.530061780065298, "train/grad": 0.05377227945253253, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.649227294921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6065899658203127, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.528597106933594, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4428663635253907, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.351370849609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2169058990478514, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.058363189697266, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8751898384094239, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.6168695926666259, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.3082313871383666, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0318188047409058, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7510656487941741, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.545387890636921, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3755110820382834, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2926002309471369, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.24224625039845704, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.1987929552793503, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.16411886567249895, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13599556941539048, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1159553905390203, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09646845689043403, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08108204681426287, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06688992914743722, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05339225202798843, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04203280810266733, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03116153166629374, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0233464723918587, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.017669407203793525, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.011903976006433368, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007694309130311012, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005345040168613195, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003996520135551691, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0026878705248236656, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0020526758302003146, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00157603214494884, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0012961357180029153, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0010667992010712623, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009553563222289086, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0008544329274445772, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006569830793887376, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.000715326489880681, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0006963468715548515, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007795459404587745, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008556816074997187, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009966627974063158, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0013695343770086766, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0015872928779572248, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.002583675002679229, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.003610378140583634, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010502601312473415, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01057277481770143, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010674415316898375, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010731666423380375, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010730144288390874, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010630905616562814, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010433608591556549, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010188627352472395, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010051151365041732, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010618985937908292, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011619712139945478, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012830075388774276, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013196517382748425, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012817172915674746, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012257515252567828, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01175640720874071, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011166094816289843, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010523927439935505, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009818773192819208, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009313498199917376, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008747669699368998, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00823066106881015, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007653297840151936, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006975751673453487, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006257289782515727, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005391426190908532, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004602549648261629, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003895846163795795, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0029644646582892165, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002121100215881597, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0015643288686987944, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011914663801144343, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0008068309152440634, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0006103354839433451, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0004640986831509508, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00037536961393925595, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0003167408154331497, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0002805812817678088, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00025626056904002323, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00020885723792162024, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.000231678717664181, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00021724187885411084, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0002470344627727172, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00025967113931983475, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0002874947994496324, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.000386458181492344, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00048375687656516676, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0006169235095148906, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.000745938127147383, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.648320198059082, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6060903072357178, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5285940170288086, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4434194564819336, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3524117469787598, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2188758850097656, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.061143398284912, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.879008173942566, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6214804649353027, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3120394945144653, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.034734845161438, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7549501061439514, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5514529943466187, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3894411623477936, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3119064271450043, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2642849385738373, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.22255423665046692, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18946252763271332, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16407287120819092, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14696133136749268, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13172338902950287, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1214018240571022, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11335384100675583, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10832437872886658, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10456308722496033, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10128828883171082, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10006409883499146, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10064434260129929, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.1016187071800232, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10026136785745621, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10026487708091736, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10135281831026077, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09616734832525253, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09344614297151566, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09159310162067413, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09445793926715851, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09209710359573364, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0869777575135231, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07716962695121765, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07139444351196289, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07341542094945908, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06716763228178024, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06489105522632599, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06458470225334167, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05683054402470589, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05578150972723961, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.0663176104426384, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05636574700474739, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.05856790766119957, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18824404761904762, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2371031746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31374007936507936, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37475198412698413, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.41021825396825395, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.484375, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6024305555555556, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6904761904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7643849206349206, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8462301587301587, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8849206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9094742063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9228670634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9332837301587301, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9402281746031746, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9484126984126984, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9588293650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9608134920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9632936507936508, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9677579365079365, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.980406746031746, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.980406746031746, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9821428571428571, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014949789439585356, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03266504575101663, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07659479104474919, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12211269539734261, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14688118365210298, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1730976184594817, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.28049206909075447, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4337621887520172, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5553551709300806, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6879755722909247, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8065704015281997, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8597651342331926, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8850254499831889, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9023900432906412, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9145691000921597, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9234898313787718, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.934914227409109, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9448816713309918, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9486119801069345, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9536217529144495, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9562481539781592, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9586300361259891, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9592708056440505, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9608499127161425, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9627600710914073, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9632992782206229, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9626484931936157, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9631704123351725, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.962537147984123, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9631925425430716, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9640070542264267, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9666531051036336, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9660595021485958, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9674718740406676, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9708619224362417, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9666853625381878, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.970577965183012, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9738401159041155, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9768128474276164, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9757912037563198, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9779701896445507, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9792426632200326, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9769069619369597, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9818194336467304, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9803614391446716, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9781069448176938, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9788444670277189, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9800366771854145, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0009966627974063158, "validation/loss_best": 0.05683054402470589, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.9818194336467304} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.5272478666901589, "train/grad": 0.05367919839918613, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6458709716796873, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.602555847167969, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5232244873046876, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4361474609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3431944274902343, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2072116851806642, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0469975662231445, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8622021484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.6021416282653809, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.2928914213180542, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0195446711778642, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7427246582508087, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.53998494759202, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.375243454426527, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.29412582360208034, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.24429747499525548, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20038178823888303, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.16428954442963004, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13477225163951517, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.1137678280286491, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09377411711029708, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07794153202325106, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.0636311934888363, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05033302132040262, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.039475464774295685, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.02940683870576322, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.022207502499222754, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.016798628233373164, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.011143324114382267, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007100944956764579, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004948356365785003, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0037191407661885025, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002507712570950389, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0019333937857300043, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.001488771429285407, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0012284359522163868, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0010330107901245355, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0009477683249861002, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0008143384847790003, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006355071812868118, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006679028365761041, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0006709237955510616, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007705850899219512, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008493066020309925, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009559419471770525, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.001336064850911498, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0015466291178017856, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0024676143005490305, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0032418666873127223, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01059865449788049, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010664050313644112, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010756877469830214, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010809531041886658, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01080685029970482, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010714679423253983, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010535736954770981, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010319886000361293, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010240680517163127, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010865566127467901, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011820124110672623, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01289877445437014, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01319962453097105, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012740249070338905, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012118742177262902, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011599566452205182, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011006339476443827, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010367791934404522, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009700876222923397, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009188406290486456, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008614256584551186, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008083865344524384, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00749999002320692, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0068047197302803395, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006088700760155916, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005227904688799754, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004431706095929257, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003716614949516952, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00280829923809506, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001985092671820894, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0014533267595106735, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0011057951286784374, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0007421821652678773, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0005684507144178497, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00043835571530507876, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0003545257046789629, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0002978250950036454, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0002619708580823499, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00024301596295117633, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00019838885667923024, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00021271379797326516, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0002112728044994583, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00023947640122059965, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002609273759480857, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00028017958758937313, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0003656006414348667, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004565148660185514, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005611713331018108, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006488419629022246, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6464555263519287, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6037182807922363, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.525484561920166, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.439481258392334, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3477425575256348, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2131237983703613, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0544137954711914, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8710353374481201, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6119129657745361, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.300984501838684, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0250041484832764, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7465891242027283, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5444855690002441, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.38521209359169006, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3086586594581604, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.26141074299812317, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.22023092210292816, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18735317885875702, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16214028000831604, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14509978890419006, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13038218021392822, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.1201053187251091, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11225471645593643, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.107487753033638, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10430188477039337, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10117671638727188, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10013597458600998, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10097965598106384, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.1020829901099205, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1012539491057396, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10096841305494308, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10169509053230286, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0962742418050766, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09399627894163132, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09191786497831345, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0949934720993042, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0920393317937851, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08682535588741302, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07686755806207657, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0721963495016098, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07298852503299713, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06710868328809738, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06449682265520096, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06446247547864914, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.056295257061719894, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.055510807782411575, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06458450108766556, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05614105239510536, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.058862317353487015, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18898809523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2378472222222222, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3169642857142857, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37723214285714285, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.41195436507936506, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4851190476190476, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6036706349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6917162698412699, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7693452380952381, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8482142857142857, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8849206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9107142857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.923859126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9347718253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9412202380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9489087301587301, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9563492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9588293650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9632936507936508, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9657738095238095, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.96875, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.972718253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.972718253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9811507936507936, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014949119901437002, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.033921040586351384, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07688085825127138, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12414476615258285, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14862043410669146, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17563692764537017, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.28267629205907907, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.4350790829338434, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5600505309630975, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6956974437766622, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8100278616886231, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8582675370850745, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8873566156950055, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9042906554398561, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9176486712984397, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9252208179014804, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9367042641697048, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9463890999916542, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9500467394144849, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9544630680444289, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9555974740595349, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9587457220710773, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9593872245505635, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9623403253758214, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9626658602977697, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9629274845032368, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.963032861969071, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9627688385428624, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9617747563029164, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.96269534012965, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.96320062862191, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9670084103849044, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9661439949433995, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.967061511031338, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9712235551967112, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9676967166984379, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9707126490710064, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9744247399190175, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9779824754276127, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9752436893444564, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9780427289243199, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9797110362668465, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9773515340873813, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9816874561597475, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9809131270996515, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9782388805330536, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9786402805643485, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9782503172095938, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.001336064850911498, "validation/loss_best": 0.055510807782411575, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.9809131270996515} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.5290201759338379, "train/grad": 0.05388637503609061, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.651170654296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.608388671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5300753784179686, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4440098571777344, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3520352172851564, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.216949005126953, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0571879959106445, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8721549606323242, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.6105862617492677, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.298963990211487, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0242258358001708, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7462557548284531, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5441517467796803, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3791788658499718, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2967281039059162, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.24560936510562897, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20059103097766637, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.16400692587718368, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1341884191520512, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11281509241089224, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09256430506706238, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.076771419076249, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06244486416690052, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04922489173710346, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03846493953838945, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.02835825612768531, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.021148328743875025, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.015831626132130624, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.010516448272392153, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.006788633996620774, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004801282892003655, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0036269330885261297, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0024602402746677398, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0018929994478821754, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0014473486132919788, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.001190683376044035, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0009812031500041486, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0008886832650750876, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0007692714501172305, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0005875922925770283, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006607736926525831, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0006658384669572115, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007131258025765419, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008085690904408693, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009207679890096187, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0012082845345139503, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0015262377448379994, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0023099519591778515, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0031425762362778187, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010561243710108102, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010622431400697678, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010713621287140995, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010768061545677483, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010771257835440338, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01069278371753171, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010530850135255605, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010331842959858476, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010263813729397952, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010903106057085096, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011907589142210781, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013048137347213924, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01334963201545179, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012909725569188594, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012322697713971138, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01181346882833168, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01121558750513941, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010561943589709698, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009859546541702003, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00931810837937519, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008672295241849497, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008083785700146109, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007454111729748547, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006760464588878677, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0060022062569623814, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005095771178603172, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004276739874621853, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0035689351899782194, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0026933076317072844, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001887144142674515, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0013747473024704959, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0010500494259758852, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.000709897926353733, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.000546298144836328, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0004172086651669815, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00034119692776585, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0002908379671134753, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00025588681590306807, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00022562525196917705, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00018680368950299453, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00020950677511791583, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0002057821572634566, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00022686749527565554, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002501510368892923, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0002724045538525388, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00035429253404799965, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004416160556320392, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005543649596074829, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006387413039192324, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6464622020721436, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6037886142730713, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5254905223846436, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.439580202102661, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3478238582611084, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2132411003112793, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0545315742492676, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8711737394332886, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.611926555633545, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3009899854660034, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0251966714859009, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7469821572303772, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.544421911239624, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.38528138399124146, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.30876126885414124, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2617468237876892, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2204025834798813, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18764865398406982, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16238944232463837, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.1452646404504776, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13044698536396027, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.12010165303945541, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11232561618089676, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10745792835950851, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10428386926651001, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10106297582387924, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10023120790719986, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10068798065185547, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10173467546701431, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10097135603427887, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10071577876806259, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10177353024482727, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09662384539842606, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09380451589822769, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09173770248889923, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09453152865171432, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09216959774494171, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08740647882223129, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07695033401250839, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07210648059844971, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.0729767307639122, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06696078926324844, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06458964198827744, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06413698196411133, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05610690265893936, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.055564410984516144, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06461629271507263, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.0562249980866909, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.05908855423331261, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17162698412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18948412698412698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.23958333333333334, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31919642857142855, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3767361111111111, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4114583333333333, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.486359126984127, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.605406746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6927083333333334, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7698412698412699, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8482142857142857, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8856646825396826, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9099702380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9226190476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.933531746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9503968253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9556051587301587, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9600694444444444, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9613095238095238, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.972718253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.982390873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.015284391966896177, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03421991391966327, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07833305248471101, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1254657818781112, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14758413220782998, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17599781098741474, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2835196665366985, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.43607395375268676, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5601755416832884, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6967925884947634, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8105831072645125, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8597166424760115, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8867319884718596, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.902828949565409, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.915994281614311, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9241734138719567, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9378723809318736, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9445134192461211, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9507365801400496, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9539034291362601, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9564240948608541, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9595444061007287, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9617318411883071, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.963907461848782, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9638098798900905, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9631979942142993, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9637385947859006, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9629271401419909, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9625663354058582, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9635159654758066, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9636450524213707, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9672048896236134, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9670471233140112, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9667607617194294, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.970070283991301, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9673331911133151, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9709288513109046, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9744247399190175, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9774414565122097, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9757494517741341, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.978031780390775, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9791349280774773, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9772599949567797, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9815061415723201, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9811663367278921, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9782765722980313, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9792552741074895, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9798935141567048, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0009207679890096187, "validation/loss_best": 0.05610690265893936, "validation/acc_best": 0.9833829365079365, "validation/f1_best": 0.9815061415723201} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.528373508900404, "train/grad": 0.053043722212314605, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.649764099121094, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6064776611328124, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5276788330078124, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4411051940917967, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.348588409423828, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2131288146972654, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.053379592895508, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8685404968261718, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.607305097579956, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.2952087545394897, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0213614982366561, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7444028136134148, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5405900476872921, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3757008706778288, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2946515142917633, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2447323863208294, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2007534446939826, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1650208418443799, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13566842332482337, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11475967368111015, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0946591342613101, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07875996483489871, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06418313449248672, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.050569070978090165, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03947690522298217, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.028994035767391325, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.02151762494817376, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.016032083332538603, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.010489556733518838, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.006674761259928346, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004703461872413755, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0035294772684574126, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0023750153463333846, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.001842265771701932, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0014222753699868918, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0011763014737516642, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0009859442338347436, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0008861804194748401, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0007782951556146145, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006078725401312113, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006348766759037972, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0006328175868839025, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.000720883384346962, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008259095158427953, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009163697808980942, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0012227571941912175, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0014921104907989501, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0022890165727585555, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0030857659690082073, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010301903588697314, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010370837312657387, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010471027495805174, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010532002369873226, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010533543275669218, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010450553505215794, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010282170393038541, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0100811746600084, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010025726207531989, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01067623615032062, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011668229452334344, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012805950026959181, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013132330039516091, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012621803265064955, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012039983042050152, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011559983433689922, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011008778223767876, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010418510038871318, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009787614934612065, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009294171478832141, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008716930496739224, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00817161805811338, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00756504871067591, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00685487822862342, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00609837181516923, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005182226083124988, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004346712096594274, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003609242385136895, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0026853240258060394, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0018927554166293702, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0013884284296364058, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.001064404750650283, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0007096721715060994, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.000544246644130908, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00041612243334384404, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0003410874892506399, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00027948088474659015, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0002501544707411085, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0002263410915111308, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0001875070024652814, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00021148026722585202, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00019625857812570756, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00022769235856685556, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00024082765468847356, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00026651681817384086, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00034853582430514505, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004284822321642423, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005293665091448929, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006089189062186051, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.645750045776367, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6029000282287598, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5243494510650635, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4380581378936768, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.345994472503662, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.211036205291748, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0519988536834717, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8681957721710205, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6084848642349243, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2970280647277832, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0215675830841064, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7438448667526245, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5420552492141724, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.38391104340553284, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3075738847255707, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2604221999645233, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.21949133276939392, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18678255379199982, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1615128219127655, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14470316469669342, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.12989173829555511, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11966078728437424, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11191501468420029, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10717243701219559, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10379079729318619, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10065911710262299, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09992270916700363, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10056573897600174, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.1017017737030983, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1011025607585907, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.100881427526474, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10163403302431107, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09648147970438004, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09377036988735199, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09162063151597977, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09497962146997452, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09236115962266922, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08704011887311935, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07695361971855164, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07222071290016174, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07315042614936829, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06709601730108261, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06436939537525177, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06429927796125412, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05591415986418724, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05543982610106468, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06419137865304947, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05590328574180603, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.058469001203775406, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1892361111111111, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.24032738095238096, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3179563492063492, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37797619047619047, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4134424603174603, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.48561507936507936, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.607390873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6934523809523809, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.769593253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8509424603174603, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8851686507936508, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9107142857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9246031746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9347718253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9419642857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9501488095238095, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9565972222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9623015873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9635416666666666, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.96875, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.96875, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.980406746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9816468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014948477377321598, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03407205634968008, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07851803139258742, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12414637034238764, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1489075771040452, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17640128564925003, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.28303125108730837, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.43975752363320014, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5626255965922728, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6955208190326094, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8135338265406711, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.859145524320158, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8868543639429728, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9047800017667149, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9179424998414879, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9262150390992919, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9378607533937648, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9463760842324462, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9503676428595866, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9554867282225775, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9564124051509226, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.958082668150433, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9617655181717168, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9625761461874858, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9632067722091939, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9633147888247174, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9627467271009748, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9626853573828524, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9622894308105988, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.963500794479179, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9640099494347686, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9678330616886777, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9660335776947743, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9667577227891468, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9695978812234964, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9678311606276624, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9699836264483953, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9742558739856496, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9779824754276127, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9754297891520665, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9779502815477624, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9791337040686604, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9767155403491368, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9816881992241113, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9805030420810549, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9785930038267603, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.979575480575914, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9789182961829769, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0009163697808980942, "validation/loss_best": 0.05591415986418724, "validation/acc_best": 0.9833829365079365, "validation/f1_best": 0.9816881992241113} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.525689759850502, "train/grad": 0.05311739236116409, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6471484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6037667846679686, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5244683837890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.43743896484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3444837951660156, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2084640502929687, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0481371307373046, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.8629132080078126, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.601706428527832, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.290322470664978, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0156688153743745, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7351332813501358, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.531400750130415, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.36753933772444725, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.28673509873449804, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.23701866019517184, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.19354888439178466, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.15858083598315717, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13003352833911777, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10992592209950089, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09085157954134047, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07564558767713607, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06185022107325494, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04891803587786853, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03801213844679296, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.027624297691509127, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.020323987985029816, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.015134770404547453, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.009926645793020725, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.006384404581040144, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004546592868864536, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003428422324359417, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.00228433090262115, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.001797652430832386, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0014045103266835213, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.001173532474786043, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0010000394843518734, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0008905529696494341, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0007875354774296284, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006088307127356529, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006695225741714239, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0006660053972154856, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007197647355496883, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008084100577980279, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0009100634418427945, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0012370996456593274, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0015107588097453117, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0022365927882492544, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.003012172747403383, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010467957369983197, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010533414056990296, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010628640444483608, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010681623972486705, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010678015884477645, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010586018920876086, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010412045766133814, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010206418950110674, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01015394345857203, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010832890027668327, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011822813868056982, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012872671689838171, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013129362580366432, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012627240661531687, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01203021096996963, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011521580307744443, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010960403478238732, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010340398584958166, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009668826055712999, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009142770386533812, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008547321372898296, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00798233161913231, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007375230961479247, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0066722126398235555, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005929865199141205, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005020841300138273, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004211289655941073, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0034885468473657964, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0025864136597374453, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0018227359227603302, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0013359753345139325, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0010174181192996912, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0006848896837982466, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0005245554141947651, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00041381103392268415, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00033415425148632496, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00028103783592086984, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0002446377794149157, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0002207229936720978, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.000185269673820585, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0001983158103439564, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001962611059389019, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00021621711610350758, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002395597937356797, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00026324878934246953, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0003473922609555302, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004221533281088341, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005138367055042181, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0006062067129823845, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6458022594451904, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.602918863296509, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5244243144989014, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4381353855133057, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3461174964904785, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2111480236053467, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0520875453948975, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8682708740234375, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6084822416305542, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2969688177108765, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0216256380081177, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.743897020816803, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5421182513237, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.38375693559646606, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3076257109642029, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2608017325401306, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2195717841386795, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18690437078475952, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.1617140918970108, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14476485550403595, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.13006292283535004, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11986647546291351, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11204524338245392, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10745223611593246, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10413891822099686, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10112961381673813, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.10032696276903152, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10113950818777084, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10222053527832031, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10145466029644012, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10095992684364319, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10184561461210251, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09651678800582886, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09393800050020218, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09181607514619827, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09466855227947235, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09245239943265915, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08737297356128693, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07717486470937729, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0721607357263565, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07295092940330505, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06702683866024017, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06455802917480469, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06431032717227936, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.056000661104917526, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05533619225025177, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.0641799196600914, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05582226812839508, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.057991351932287216, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17162698412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18948412698412698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.24156746031746032, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.32018849206349204, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3777281746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.41195436507936506, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4871031746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.607390873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6941964285714286, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.769593253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8494543650793651, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8849206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9107142857142857, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.923859126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9337797619047619, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9412202380952381, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9503968253968254, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9558531746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9677579365079365, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.972718253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9816468253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.015282617691967407, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03421991391966327, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07991820933869566, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1257906429949839, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14815139387436618, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17670130596434272, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2843713978663153, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.43953286209140774, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5633165900375352, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6959390351669774, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8119938589550321, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8583097373467559, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8870797183589898, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9038308334656658, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9169741503715899, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9244220681237222, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9384673802443899, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9453417098234534, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9504448423793145, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9548310603869616, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9571818645110513, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9599345560508359, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9618176697908687, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9629147006185749, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9628741007246162, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9634547775626023, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.963916736146457, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9631138963448593, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9626288574081783, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9635159654758066, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9648027054736892, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9672320714687709, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9671147855020573, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9665274903542388, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9706335560675309, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9674007698681454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9702060489132052, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9746028439285617, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9774414565122097, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9756137984290907, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9778528977166697, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9791337040686604, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9772599949567797, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9816426098928077, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.980456326846529, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9791639878150726, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9790922798748092, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9788047673037693, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0009100634418427945, "validation/loss_best": 0.056000661104917526, "validation/acc_best": 0.9833829365079365, "validation/f1_best": 0.9816426098928077} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.5264373028278351, "train/grad": 0.05287676265463233, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.642652893066406, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.599295654296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.520202941894531, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4334071350097655, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.340975646972656, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2056571197509767, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.046475257873535, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.862499656677246, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.602751932144165, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.2932543754577637, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.0212413203716277, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7446124306321145, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5418218134343624, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.3769852378964424, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2946096193045378, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.24341206900775433, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.19841976873576642, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.1618471121415496, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.1321444621309638, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11113447582349181, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09108188732527196, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07543370444327593, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06132436074316502, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.047965181786566974, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.037225536983460185, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.027356204576790333, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.020297513278201222, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.015100306496024132, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.009955188622698188, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.006439517457038164, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004583243615925312, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.003456724854186177, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0023375843651592732, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0018383795861154795, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0014150325581431388, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0011687687039375306, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0009768054354935885, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.000896284207701683, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0007723207864910364, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0006006499286741018, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006537787802517414, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0006532696727663278, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007037651725113392, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0008156935218721628, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0008929964900016785, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0012742796819657086, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0014799809269607066, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.002267119288444519, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.003061453187838197, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010333400738891213, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010404297686181962, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010509348856285215, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010573526378720999, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010579508042428642, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010499257396440953, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010331207064446062, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010125755975022912, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01006107060238719, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010723532033152879, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01172450558282435, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012841369193047285, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013152138460427523, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012663339679129422, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0120603799354285, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01153479256434366, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010952941810246556, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010321872350759804, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009638985230121761, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009095192451495678, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008481874172575772, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007921899445354938, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007324370748829096, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0066214849473908545, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005879825546289794, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0049880864424631, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004174898432684131, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0034590721246786416, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0025682557400432417, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0017873385426355527, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0013170940353302285, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0010019663973071147, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0006828262022463605, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0005283810322725913, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00041140027024084703, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0003376640174246859, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.000283717069796694, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00025005653689731845, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00022693533290294, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00019054393315855124, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0002077657141308009, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001970543414608983, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00022016482511389769, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002422901405407174, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00026250680355587974, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0003386078786206781, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0004132965498502017, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0005018995637510671, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0005815127689857036, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.645648241043091, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.602769136428833, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5241713523864746, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4378750324249268, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.34578275680542, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2107367515563965, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.0516223907470703, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8677847385406494, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.607972502708435, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.2964586019515991, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0210869312286377, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7434388399124146, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5417070388793945, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.38368135690689087, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.3074146509170532, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.2604031264781952, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2193584144115448, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.186674103140831, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16149847209453583, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.14461281895637512, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.12974461913108826, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11946640908718109, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11184760183095932, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10694891959428787, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10380623489618301, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10074494779109955, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.09989723563194275, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10047588497400284, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10191681981086731, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10104382783174515, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1009863018989563, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10177572816610336, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09639688581228256, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09374837577342987, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.09184133261442184, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09488502144813538, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09235936403274536, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08710411936044693, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07704805582761765, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07221619784832001, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07311451435089111, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06701522320508957, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06423459947109222, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06439018249511719, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.05605209991335869, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.05538424104452133, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06392888724803925, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.056078508496284485, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.058635637164115906, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17137896825396826, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18948412698412698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.24131944444444445, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31820436507936506, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3784722222222222, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.4131944444444444, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4853670634920635, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6078869047619048, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6929563492063492, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7700892857142857, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8501984126984127, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8849206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9112103174603174, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.923859126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9347718253968254, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9409722222222222, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9499007936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9565972222222222, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9590773809523809, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9623015873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9660218253968254, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9689980158730159, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9704861111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.980406746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9813988095238095, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014948477377321598, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03421991391966327, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.07940890686199843, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12425761496390492, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14929539724164412, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1762915331340037, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.28219861144129954, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.44108276969449145, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.561621181150875, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6970779898431644, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8123452148802974, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8585373008941924, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.88767955795831, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9034755466937632, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9178183267028605, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.924709255084475, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9373746199473365, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9462096211459018, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9503676428595866, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9551370384842031, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9571818645110513, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9588800192619497, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9603878414646939, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9627768797086751, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9636094830637308, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.962893549620968, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9632498843276712, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9623736845885928, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9624689861050623, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.963500794479179, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9636625003945907, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9680596651805905, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9662634444864774, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9667512846359179, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9704976720917354, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9678311606276624, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9702060489132052, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9746028439285617, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9779824754276127, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9754297891520665, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9776009857379039, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9791337040686604, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9767155403491368, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9818667276517797, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9804272986238735, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9791197862926398, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9788163213561396, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9787881789574401, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0008929964900016785, "validation/loss_best": 0.05605209991335869, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.9818667276517797} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.5258327063918113, "train/grad": 0.052614414896816016, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.640594177246094, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.597044677734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5174105834960936, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4301329040527344, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3371617126464845, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.201046371459961, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.0408944702148437, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.856101303100586, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.5958673477172851, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.2868694496154784, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.016641408801079, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.7422915640473365, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.5400027640163898, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.37697258286178115, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.29622942604124547, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.2460692520439625, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.20187761161476372, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.16554887589067221, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.13581345485523344, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.11427092984318733, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09379710999317467, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07733419697731733, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06241290018893778, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04861860762350261, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03751495160162449, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.02724149196408689, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.01999704816378653, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.014849038682878018, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.009668476218357681, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0062580752652138475, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.004470227202400565, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0034073666855692865, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0023177317250519993, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0017837974801659584, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0013793625123798847, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0011529943067580461, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0009734130185097456, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0008773067593574524, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0007682118192315102, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0005943255033344031, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006434827949851751, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0006540636811405421, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007133075688034296, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0007725349348038435, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0008772241976112128, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0012256922200322151, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.001495041400194168, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0022428724355995655, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.002921352367848158, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010303194501902908, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010377850760705768, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01048948316834867, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010562194813974201, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010577353173866868, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010512816035188735, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010362160063814373, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010172674271743745, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010115450939629227, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010764757103752345, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011771562253125012, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012853930976707489, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013075950886122883, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012554025850258768, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0119312505540438, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011401193272322417, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010817972961813211, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01019721050048247, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009553908649832011, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009044312153710052, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00844205753877759, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007888882816769183, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007280217092484236, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006580671758856624, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005849356143735349, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004964961573132314, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004167223885888234, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0034526039409684016, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0025615320578799582, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0017934216452704277, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0013110348937334492, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0010059772980457638, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0006871818135550711, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0005254651080031181, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00041160422326356636, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0003337887494490133, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0002852129130769754, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0002489430418427219, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00022773650289309444, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00017865156734842458, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00020159753303232718, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00019566680530260782, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00021655953945810325, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00023106807046133326, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00024761714581472916, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0003231134999259666, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.000410114252990752, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0004930886261718115, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0005778805474983529, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6456971168518066, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6027963161468506, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5242533683776855, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4379496574401855, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.3458406925201416, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.2108309268951416, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.051697254180908, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.8678597211837769, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.6079870462417603, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.296372413635254, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.0211313962936401, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.7434329390525818, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.5417677164077759, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.3837074041366577, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.30745476484298706, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.26058730483055115, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.2194434255361557, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.18678170442581177, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.16176201403141022, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.144673153758049, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.1301293522119522, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.11983619630336761, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.11202042549848557, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.10735023766756058, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.10417045652866364, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.10101441293954849, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.1001746878027916, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10093026608228683, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.10206150263547897, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.10130887478590012, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.10110540688037872, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.10195513069629669, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.09667285531759262, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.09399576485157013, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0918566882610321, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09486236423254013, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09249316155910492, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08728422224521637, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.07705971598625183, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07202549278736115, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.07300934940576553, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.06701289117336273, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.06466101109981537, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.06438745558261871, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.0559634231030941, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.055274706333875656, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.06415574252605438, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.05593286454677582, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.058232203125953674, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17162698412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.18973214285714285, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.24206349206349206, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31994047619047616, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.37797619047619047, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.41220238095238093, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.48759920634920634, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.607390873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.6949404761904762, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.7703373015873016, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.8504464285714286, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8861607142857143, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9109623015873016, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9236111111111112, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9342757936507936, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9407242063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9506448412698413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9561011904761905, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9588293650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9620535714285714, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9682539682539683, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9692460317460317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9694940476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9699900793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.972718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9818948412698413, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01528087794146642, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.034423988951448325, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.08012723567199599, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12549033939334922, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1482225852027997, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17678552854617097, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.28598435050351295, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.44002201620210474, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.5641967107636714, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.6969269443271369, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.8131879492958505, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.8598788026391991, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8873509186672655, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9036455786800672, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9175127317955094, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9239418808359263, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9392054600131274, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9456092909576803, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9502978893470494, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9548535707844232, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9564363467067969, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9593873733879893, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9612823005094729, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9627605177082129, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9635553414606606, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9638452718628395, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.963916736146457, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9637155042372042, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9628284960099914, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9627923979903622, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9634654971269073, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9653971872920482, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9667059457785202, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9662613462235987, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9710392814783558, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9674007698681454, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9705085211492901, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9746028439285617, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9774414565122097, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9756134645723165, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9775036019068111, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9793138926979827, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9772599949567797, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9816426098928077, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9804566867914217, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9784607984860637, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.979092176476625, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9793466291449262, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.0008772241976112128, "validation/loss_best": 0.0559634231030941, "validation/acc_best": 0.9833829365079365, "validation/f1_best": 0.9816426098928077} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/config.yaml b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d9f55cdafdf750c9c2fde9bf96ba94f592106c6c --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..943ca3977b17a1176183b0ebcba8686b24fd8d17 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 18, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 0.39686325192451477, "eval/train/acc": 0.9246276119795779, "eval/train/acc_std": 0.001835526541877298, "eval/train/f1": 0.9177205473806689, "eval/train/f1_std": 0.002297745164473063, "eval/validation/loss": 0.4169345498085022, "eval/validation/acc": 0.9188988095238095, "eval/validation/acc_std": 0.003986972345472204, "eval/validation/f1": 0.9114588509884194, "eval/validation/f1_std": 0.004768962481631679, "eval/test/loss": 0.4336282014846802, "eval/test/acc": 0.9045634920634921, "eval/test/acc_std": 0.003883363806776569, "eval/test/f1": 0.8925949553167059, "eval/test/f1_std": 0.0048750129048626524} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..2fca0f056c4ec388b0faa6d1f78ceae6a099142e --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 18, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.39686325192451477, "eval/best/train/acc": 0.9246276119795779, "eval/best/train/acc_std": 0.001835526541877298, "eval/best/train/f1": 0.9177205473806689, "eval/best/train/f1_std": 0.002297745164473063, "eval/best/validation/loss": 0.4169345498085022, "eval/best/validation/acc": 0.9188988095238095, "eval/best/validation/acc_std": 0.003986972345472204, "eval/best/validation/f1": 0.9114588509884194, "eval/best/validation/f1_std": 0.004768962481631679, "eval/best/test/loss": 0.4336282014846802, "eval/best/test/acc": 0.9045634920634921, "eval/best/test/acc_std": 0.003883363806776569, "eval/best/test/f1": 0.8925949553167059, "eval/best/test/f1_std": 0.0048750129048626524} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..556bb741d019fcdcdcb8a5255cfdcc18416b70ff --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 48, "eval/last/lr_best": 0.015, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.3962176442146301, "eval/last/train/acc": 0.9252592241696932, "eval/last/train/acc_std": 0.001795963995706179, "eval/last/train/f1": 0.9183098468770398, "eval/last/train/f1_std": 0.0022583861586730957, "eval/last/validation/loss": 0.4163023829460144, "eval/last/validation/acc": 0.9169146825396826, "eval/last/validation/acc_std": 0.004061298171696756, "eval/last/validation/f1": 0.9093250816133511, "eval/last/validation/f1_std": 0.004803360823443858, "eval/last/test/loss": 0.4326916038990021, "eval/last/test/acc": 0.9049603174603175, "eval/last/test/acc_std": 0.0039797423186561185, "eval/last/test/f1": 0.8927827354945345, "eval/last/test/f1_std": 0.004942381923492108} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..3acb1e05412155621c9bb6884037eb23323d245f --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",train,0.39686325192451477,0.9246276119795779,0.001835526541877298,0.9177205473806689,0.002297745164473063 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",validation,0.4169345498085022,0.9188988095238095,0.003986972345472204,0.9114588509884194,0.004768962481631679 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",test,0.4336282014846802,0.9045634920634921,0.003883363806776569,0.8925949553167059,0.0048750129048626524 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..3acb1e05412155621c9bb6884037eb23323d245f --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",train,0.39686325192451477,0.9246276119795779,0.001835526541877298,0.9177205473806689,0.002297745164473063 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",validation,0.4169345498085022,0.9188988095238095,0.003986972345472204,0.9114588509884194,0.004768962481631679 +flat_mae,patch,linear,hcpya_task21,best,18,0.015,0.05,48,"[50, 1.0]",test,0.4336282014846802,0.9045634920634921,0.003883363806776569,0.8925949553167059,0.0048750129048626524 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..ea3b6be64d5d1bf0c5cc2102c8fec7b90a013f0f --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",train,0.3962176442146301,0.9252592241696932,0.001795963995706179,0.9183098468770398,0.0022583861586730957 +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",validation,0.4163023829460144,0.9169146825396826,0.004061298171696756,0.9093250816133511,0.004803360823443858 +flat_mae,patch,linear,hcpya_task21,last,19,0.015,0.05,48,"[50, 1.0]",test,0.4326916038990021,0.9049603174603175,0.0039797423186561185,0.8927827354945345,0.004942381923492108 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/log.txt b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..4c89468ceb2fa334f8380c6628f9ff30dfe9ddfc --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/log.txt @@ -0,0 +1,893 @@ +fMRI foundation model probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 23:05:22 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 0.8M (0.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:07 lr: nan time: 3.6180 data: 3.1810 max mem: 3929 +train: [0] [ 20/400] eta: 0:03:21 lr: 0.000003 loss: 3.0405 (3.0406) grad: 0.1336 (0.1423) time: 0.3748 data: 0.0033 max mem: 3970 +train: [0] [ 40/400] eta: 0:02:41 lr: 0.000006 loss: 3.0418 (3.0401) grad: 0.1389 (0.1414) time: 0.3627 data: 0.0029 max mem: 3970 +train: [0] [ 60/400] eta: 0:02:21 lr: 0.000009 loss: 3.0350 (3.0358) grad: 0.1410 (0.1411) time: 0.3468 data: 0.0034 max mem: 3970 +train: [0] [ 80/400] eta: 0:02:06 lr: 0.000012 loss: 3.0045 (3.0265) grad: 0.1332 (0.1396) time: 0.3316 data: 0.0033 max mem: 3970 +train: [0] [100/400] eta: 0:01:55 lr: 0.000015 loss: 3.0011 (3.0223) grad: 0.1347 (0.1387) time: 0.3471 data: 0.0033 max mem: 3970 +train: [0] [120/400] eta: 0:01:46 lr: 0.000018 loss: 2.9866 (3.0144) grad: 0.1284 (0.1354) time: 0.3561 data: 0.0031 max mem: 3970 +train: [0] [140/400] eta: 0:01:38 lr: 0.000021 loss: 2.9668 (3.0088) grad: 0.1195 (0.1334) time: 0.3645 data: 0.0034 max mem: 3970 +train: [0] [160/400] eta: 0:01:30 lr: 0.000024 loss: 2.9689 (3.0028) grad: 0.1220 (0.1318) time: 0.3583 data: 0.0034 max mem: 3970 +train: [0] [180/400] eta: 0:01:22 lr: 0.000027 loss: 2.9541 (2.9973) grad: 0.1220 (0.1311) time: 0.3640 data: 0.0032 max mem: 3970 +train: [0] [200/400] eta: 0:01:13 lr: 0.000030 loss: 2.9501 (2.9920) grad: 0.1204 (0.1300) time: 0.3313 data: 0.0033 max mem: 3970 +train: [0] [220/400] eta: 0:01:06 lr: 0.000033 loss: 2.9447 (2.9877) grad: 0.1103 (0.1281) time: 0.3461 data: 0.0033 max mem: 3970 +train: [0] [240/400] eta: 0:00:58 lr: 0.000036 loss: 2.9313 (2.9827) grad: 0.1047 (0.1266) time: 0.3482 data: 0.0033 max mem: 3970 +train: [0] [260/400] eta: 0:00:51 lr: 0.000039 loss: 2.9057 (2.9765) grad: 0.1185 (0.1265) time: 0.3604 data: 0.0033 max mem: 3970 +train: [0] [280/400] eta: 0:00:43 lr: 0.000042 loss: 2.8990 (2.9713) grad: 0.1185 (0.1257) time: 0.3761 data: 0.0035 max mem: 3970 +train: [0] [300/400] eta: 0:00:37 lr: 0.000045 loss: 2.9081 (2.9673) grad: 0.1021 (0.1238) time: 0.5306 data: 0.1806 max mem: 3970 +train: [0] [320/400] eta: 0:00:30 lr: 0.000048 loss: 2.8769 (2.9605) grad: 0.1014 (0.1231) time: 0.3419 data: 0.0033 max mem: 3970 +train: [0] [340/400] eta: 0:00:22 lr: 0.000051 loss: 2.8569 (2.9552) grad: 0.1118 (0.1224) time: 0.3631 data: 0.0034 max mem: 3970 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 2.8626 (2.9505) grad: 0.1066 (0.1214) time: 0.3825 data: 0.0024 max mem: 3970 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 2.8626 (2.9458) grad: 0.1007 (0.1203) time: 0.3668 data: 0.0032 max mem: 3970 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.8465 (2.9406) grad: 0.1007 (0.1194) time: 0.3866 data: 0.0032 max mem: 3970 +train: [0] Total time: 0:02:30 (0.3753 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.8465 (2.9406) grad: 0.1007 (0.1194) +eval (validation): [0] [ 0/63] eta: 0:03:38 time: 3.4712 data: 3.1731 max mem: 3970 +eval (validation): [0] [20/63] eta: 0:00:22 time: 0.3859 data: 0.0035 max mem: 3970 +eval (validation): [0] [40/63] eta: 0:00:10 time: 0.3584 data: 0.0034 max mem: 3970 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3703 data: 0.0034 max mem: 3970 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3663 data: 0.0034 max mem: 3970 +eval (validation): [0] Total time: 0:00:26 (0.4246 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.147 acc: 0.432 f1: 0.235 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:24:02 lr: nan time: 3.6067 data: 3.3160 max mem: 3970 +train: [1] [ 20/400] eta: 0:03:22 lr: 0.000063 loss: 2.8273 (2.8354) grad: 0.1064 (0.1052) time: 0.3802 data: 0.0044 max mem: 3970 +train: [1] [ 40/400] eta: 0:02:41 lr: 0.000066 loss: 2.8111 (2.8155) grad: 0.1071 (0.1068) time: 0.3612 data: 0.0028 max mem: 3970 +train: [1] [ 60/400] eta: 0:02:25 lr: 0.000069 loss: 2.8210 (2.8212) grad: 0.1046 (0.1053) time: 0.3792 data: 0.0032 max mem: 3970 +train: [1] [ 80/400] eta: 0:02:13 lr: 0.000072 loss: 2.8144 (2.8126) grad: 0.0997 (0.1040) time: 0.3866 data: 0.0034 max mem: 3970 +train: [1] [100/400] eta: 0:02:04 lr: 0.000075 loss: 2.7655 (2.8011) grad: 0.1003 (0.1048) time: 0.3999 data: 0.0035 max mem: 3970 +train: [1] [120/400] eta: 0:01:54 lr: 0.000078 loss: 2.7463 (2.7951) grad: 0.0989 (0.1039) time: 0.3879 data: 0.0031 max mem: 3970 +train: [1] [140/400] eta: 0:01:44 lr: 0.000081 loss: 2.7429 (2.7888) grad: 0.0961 (0.1024) time: 0.3597 data: 0.0034 max mem: 3970 +train: [1] [160/400] eta: 0:01:36 lr: 0.000084 loss: 2.7052 (2.7768) grad: 0.0996 (0.1039) time: 0.4120 data: 0.0038 max mem: 3970 +train: [1] [180/400] eta: 0:01:28 lr: 0.000087 loss: 2.6919 (2.7676) grad: 0.1043 (0.1038) time: 0.4015 data: 0.0034 max mem: 3970 +train: [1] [200/400] eta: 0:01:20 lr: 0.000090 loss: 2.7107 (2.7638) grad: 0.0985 (0.1033) time: 0.3738 data: 0.0034 max mem: 3970 +train: [1] [220/400] eta: 0:01:11 lr: 0.000093 loss: 2.7088 (2.7577) grad: 0.0985 (0.1027) time: 0.3647 data: 0.0034 max mem: 3970 +train: [1] [240/400] eta: 0:01:03 lr: 0.000096 loss: 2.6916 (2.7509) grad: 0.0952 (0.1023) time: 0.3768 data: 0.0035 max mem: 3970 +train: [1] [260/400] eta: 0:00:55 lr: 0.000099 loss: 2.6749 (2.7452) grad: 0.0938 (0.1019) time: 0.3753 data: 0.0034 max mem: 3970 +train: [1] [280/400] eta: 0:00:47 lr: 0.000102 loss: 2.6626 (2.7393) grad: 0.0940 (0.1017) time: 0.3692 data: 0.0033 max mem: 3970 +train: [1] [300/400] eta: 0:00:40 lr: 0.000105 loss: 2.6554 (2.7335) grad: 0.0955 (0.1014) time: 0.5570 data: 0.1958 max mem: 3970 +train: [1] [320/400] eta: 0:00:32 lr: 0.000108 loss: 2.6554 (2.7282) grad: 0.0938 (0.1007) time: 0.3770 data: 0.0033 max mem: 3970 +train: [1] [340/400] eta: 0:00:23 lr: 0.000111 loss: 2.6382 (2.7230) grad: 0.0894 (0.1004) time: 0.3504 data: 0.0031 max mem: 3970 +train: [1] [360/400] eta: 0:00:15 lr: 0.000114 loss: 2.6152 (2.7170) grad: 0.0894 (0.0999) time: 0.3486 data: 0.0035 max mem: 3970 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 2.6194 (2.7125) grad: 0.0988 (0.1000) time: 0.3354 data: 0.0035 max mem: 3970 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.5998 (2.7054) grad: 0.0948 (0.0997) time: 0.3563 data: 0.0034 max mem: 3970 +train: [1] Total time: 0:02:36 (0.3911 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.5998 (2.7054) grad: 0.0948 (0.0997) +eval (validation): [1] [ 0/63] eta: 0:03:34 time: 3.4120 data: 3.1962 max mem: 3970 +eval (validation): [1] [20/63] eta: 0:00:22 time: 0.3712 data: 0.0042 max mem: 3970 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3518 data: 0.0032 max mem: 3970 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3323 data: 0.0032 max mem: 3970 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3341 data: 0.0032 max mem: 3970 +eval (validation): [1] Total time: 0:00:25 (0.4048 s / it) +cv: [1] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 1.407 acc: 0.692 f1: 0.628 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:41 lr: nan time: 3.4036 data: 3.1342 max mem: 3970 +train: [2] [ 20/400] eta: 0:03:14 lr: 0.000123 loss: 2.5825 (2.5788) grad: 0.0892 (0.0921) time: 0.3677 data: 0.0029 max mem: 3970 +train: [2] [ 40/400] eta: 0:02:36 lr: 0.000126 loss: 2.5938 (2.5860) grad: 0.0892 (0.0908) time: 0.3537 data: 0.0034 max mem: 3970 +train: [2] [ 60/400] eta: 0:02:18 lr: 0.000129 loss: 2.5819 (2.5743) grad: 0.0885 (0.0915) time: 0.3542 data: 0.0035 max mem: 3970 +train: [2] [ 80/400] eta: 0:02:05 lr: 0.000132 loss: 2.5639 (2.5702) grad: 0.0902 (0.0918) time: 0.3463 data: 0.0037 max mem: 3970 +train: [2] [100/400] eta: 0:01:55 lr: 0.000135 loss: 2.5411 (2.5581) grad: 0.0905 (0.0919) time: 0.3582 data: 0.0034 max mem: 3970 +train: [2] [120/400] eta: 0:01:47 lr: 0.000138 loss: 2.4992 (2.5506) grad: 0.0877 (0.0911) time: 0.3635 data: 0.0034 max mem: 3970 +train: [2] [140/400] eta: 0:01:38 lr: 0.000141 loss: 2.5093 (2.5414) grad: 0.0866 (0.0912) time: 0.3512 data: 0.0033 max mem: 3970 +train: [2] [160/400] eta: 0:01:29 lr: 0.000144 loss: 2.4946 (2.5355) grad: 0.0924 (0.0916) time: 0.3522 data: 0.0034 max mem: 3970 +train: [2] [180/400] eta: 0:01:22 lr: 0.000147 loss: 2.5020 (2.5348) grad: 0.0905 (0.0914) time: 0.3574 data: 0.0035 max mem: 3970 +train: [2] [200/400] eta: 0:01:13 lr: 0.000150 loss: 2.5168 (2.5309) grad: 0.0915 (0.0912) time: 0.3346 data: 0.0033 max mem: 3970 +train: [2] [220/400] eta: 0:01:06 lr: 0.000153 loss: 2.4972 (2.5263) grad: 0.0920 (0.0910) time: 0.3628 data: 0.0034 max mem: 3970 +train: [2] [240/400] eta: 0:00:58 lr: 0.000156 loss: 2.4972 (2.5231) grad: 0.0845 (0.0903) time: 0.3484 data: 0.0032 max mem: 3970 +train: [2] [260/400] eta: 0:00:51 lr: 0.000159 loss: 2.4919 (2.5187) grad: 0.0810 (0.0900) time: 0.3509 data: 0.0034 max mem: 3970 +train: [2] [280/400] eta: 0:00:43 lr: 0.000162 loss: 2.4470 (2.5136) grad: 0.0847 (0.0901) time: 0.3572 data: 0.0036 max mem: 3970 +train: [2] [300/400] eta: 0:00:37 lr: 0.000165 loss: 2.4228 (2.5067) grad: 0.0873 (0.0897) time: 0.5519 data: 0.1911 max mem: 3970 +train: [2] [320/400] eta: 0:00:30 lr: 0.000168 loss: 2.4155 (2.5017) grad: 0.0824 (0.0892) time: 0.3598 data: 0.0036 max mem: 3970 +train: [2] [340/400] eta: 0:00:22 lr: 0.000171 loss: 2.4075 (2.4960) grad: 0.0838 (0.0891) time: 0.3668 data: 0.0034 max mem: 3970 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 2.3886 (2.4909) grad: 0.0847 (0.0888) time: 0.3568 data: 0.0035 max mem: 3970 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 2.4154 (2.4871) grad: 0.0794 (0.0883) time: 0.3428 data: 0.0033 max mem: 3970 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.4108 (2.4833) grad: 0.0791 (0.0882) time: 0.3657 data: 0.0032 max mem: 3970 +train: [2] Total time: 0:02:29 (0.3731 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.4108 (2.4833) grad: 0.0791 (0.0882) +eval (validation): [2] [ 0/63] eta: 0:03:38 time: 3.4706 data: 3.2356 max mem: 3970 +eval (validation): [2] [20/63] eta: 0:00:20 time: 0.3379 data: 0.0035 max mem: 3970 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3688 data: 0.0033 max mem: 3970 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3407 data: 0.0034 max mem: 3970 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3290 data: 0.0032 max mem: 3970 +eval (validation): [2] Total time: 0:00:25 (0.4023 s / it) +cv: [2] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 1.021 acc: 0.763 f1: 0.692 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:22 lr: nan time: 3.3562 data: 3.0821 max mem: 3970 +train: [3] [ 20/400] eta: 0:03:16 lr: 0.000183 loss: 2.3470 (2.3499) grad: 0.0836 (0.0869) time: 0.3758 data: 0.0243 max mem: 3970 +train: [3] [ 40/400] eta: 0:02:40 lr: 0.000186 loss: 2.3470 (2.3601) grad: 0.0833 (0.0828) time: 0.3697 data: 0.0028 max mem: 3970 +train: [3] [ 60/400] eta: 0:02:21 lr: 0.000189 loss: 2.3490 (2.3539) grad: 0.0820 (0.0848) time: 0.3589 data: 0.0032 max mem: 3970 +train: [3] [ 80/400] eta: 0:02:08 lr: 0.000192 loss: 2.3541 (2.3504) grad: 0.0812 (0.0836) time: 0.3527 data: 0.0033 max mem: 3970 +train: [3] [100/400] eta: 0:01:57 lr: 0.000195 loss: 2.3290 (2.3449) grad: 0.0764 (0.0830) time: 0.3586 data: 0.0034 max mem: 3970 +train: [3] [120/400] eta: 0:01:48 lr: 0.000198 loss: 2.3339 (2.3528) grad: 0.0770 (0.0822) time: 0.3547 data: 0.0035 max mem: 3970 +train: [3] [140/400] eta: 0:01:39 lr: 0.000201 loss: 2.3642 (2.3546) grad: 0.0838 (0.0828) time: 0.3553 data: 0.0034 max mem: 3970 +train: [3] [160/400] eta: 0:01:31 lr: 0.000204 loss: 2.3512 (2.3511) grad: 0.0861 (0.0831) time: 0.3595 data: 0.0033 max mem: 3970 +train: [3] [180/400] eta: 0:01:23 lr: 0.000207 loss: 2.3248 (2.3483) grad: 0.0830 (0.0828) time: 0.3621 data: 0.0032 max mem: 3970 +train: [3] [200/400] eta: 0:01:14 lr: 0.000210 loss: 2.3248 (2.3444) grad: 0.0830 (0.0829) time: 0.3537 data: 0.0033 max mem: 3970 +train: [3] [220/400] eta: 0:01:07 lr: 0.000213 loss: 2.2942 (2.3398) grad: 0.0809 (0.0832) time: 0.3796 data: 0.0034 max mem: 3970 +train: [3] [240/400] eta: 0:00:59 lr: 0.000216 loss: 2.3049 (2.3389) grad: 0.0809 (0.0833) time: 0.3607 data: 0.0033 max mem: 3970 +train: [3] [260/400] eta: 0:00:52 lr: 0.000219 loss: 2.3276 (2.3355) grad: 0.0766 (0.0829) time: 0.3706 data: 0.0034 max mem: 3970 +train: [3] [280/400] eta: 0:00:44 lr: 0.000222 loss: 2.2777 (2.3303) grad: 0.0774 (0.0829) time: 0.3705 data: 0.0035 max mem: 3970 +train: [3] [300/400] eta: 0:00:38 lr: 0.000225 loss: 2.2680 (2.3260) grad: 0.0774 (0.0825) time: 0.5711 data: 0.2005 max mem: 3970 +train: [3] [320/400] eta: 0:00:30 lr: 0.000228 loss: 2.2582 (2.3197) grad: 0.0772 (0.0825) time: 0.3944 data: 0.0032 max mem: 3970 +train: [3] [340/400] eta: 0:00:23 lr: 0.000231 loss: 2.2250 (2.3140) grad: 0.0799 (0.0825) time: 0.3790 data: 0.0036 max mem: 3970 +train: [3] [360/400] eta: 0:00:15 lr: 0.000234 loss: 2.2207 (2.3092) grad: 0.0807 (0.0825) time: 0.3453 data: 0.0033 max mem: 3970 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 2.2503 (2.3055) grad: 0.0807 (0.0826) time: 0.3485 data: 0.0030 max mem: 3970 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.2281 (2.3019) grad: 0.0782 (0.0824) time: 0.3601 data: 0.0031 max mem: 3970 +train: [3] Total time: 0:02:32 (0.3818 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.2281 (2.3019) grad: 0.0782 (0.0824) +eval (validation): [3] [ 0/63] eta: 0:03:34 time: 3.4047 data: 3.1801 max mem: 3970 +eval (validation): [3] [20/63] eta: 0:00:23 time: 0.3928 data: 0.0262 max mem: 3970 +eval (validation): [3] [40/63] eta: 0:00:10 time: 0.3322 data: 0.0029 max mem: 3970 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3337 data: 0.0033 max mem: 3970 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3254 data: 0.0033 max mem: 3970 +eval (validation): [3] Total time: 0:00:25 (0.4052 s / it) +cv: [3] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.787 acc: 0.806 f1: 0.747 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:23:01 lr: nan time: 3.4545 data: 3.2270 max mem: 3970 +train: [4] [ 20/400] eta: 0:03:09 lr: 0.000243 loss: 2.1788 (2.2085) grad: 0.0752 (0.0759) time: 0.3511 data: 0.0098 max mem: 3970 +train: [4] [ 40/400] eta: 0:02:34 lr: 0.000246 loss: 2.2159 (2.2224) grad: 0.0718 (0.0735) time: 0.3567 data: 0.0032 max mem: 3970 +train: [4] [ 60/400] eta: 0:02:18 lr: 0.000249 loss: 2.2150 (2.2139) grad: 0.0717 (0.0748) time: 0.3622 data: 0.0031 max mem: 3970 +train: [4] [ 80/400] eta: 0:02:06 lr: 0.000252 loss: 2.2037 (2.2066) grad: 0.0752 (0.0752) time: 0.3545 data: 0.0032 max mem: 3970 +train: [4] [100/400] eta: 0:01:55 lr: 0.000255 loss: 2.1891 (2.2030) grad: 0.0734 (0.0755) time: 0.3549 data: 0.0036 max mem: 3970 +train: [4] [120/400] eta: 0:01:46 lr: 0.000258 loss: 2.2024 (2.2032) grad: 0.0734 (0.0759) time: 0.3515 data: 0.0033 max mem: 3970 +train: [4] [140/400] eta: 0:01:37 lr: 0.000261 loss: 2.2053 (2.2006) grad: 0.0726 (0.0758) time: 0.3435 data: 0.0032 max mem: 3970 +train: [4] [160/400] eta: 0:01:29 lr: 0.000264 loss: 2.1431 (2.1898) grad: 0.0825 (0.0768) time: 0.3535 data: 0.0034 max mem: 3970 +train: [4] [180/400] eta: 0:01:21 lr: 0.000267 loss: 2.1336 (2.1874) grad: 0.0817 (0.0765) time: 0.3493 data: 0.0033 max mem: 3970 +train: [4] [200/400] eta: 0:01:13 lr: 0.000270 loss: 2.1392 (2.1810) grad: 0.0755 (0.0767) time: 0.3426 data: 0.0039 max mem: 3970 +train: [4] [220/400] eta: 0:01:06 lr: 0.000273 loss: 2.1648 (2.1806) grad: 0.0755 (0.0765) time: 0.3650 data: 0.0036 max mem: 3970 +train: [4] [240/400] eta: 0:00:58 lr: 0.000276 loss: 2.1506 (2.1769) grad: 0.0703 (0.0759) time: 0.3657 data: 0.0033 max mem: 3970 +train: [4] [260/400] eta: 0:00:51 lr: 0.000279 loss: 2.1387 (2.1733) grad: 0.0717 (0.0759) time: 0.3500 data: 0.0031 max mem: 3970 +train: [4] [280/400] eta: 0:00:43 lr: 0.000282 loss: 2.1311 (2.1699) grad: 0.0749 (0.0759) time: 0.3625 data: 0.0034 max mem: 3970 +train: [4] [300/400] eta: 0:00:37 lr: 0.000285 loss: 2.1326 (2.1700) grad: 0.0708 (0.0755) time: 0.5401 data: 0.1942 max mem: 3970 +train: [4] [320/400] eta: 0:00:30 lr: 0.000288 loss: 2.1355 (2.1672) grad: 0.0696 (0.0751) time: 0.3666 data: 0.0037 max mem: 3970 +train: [4] [340/400] eta: 0:00:22 lr: 0.000291 loss: 2.1102 (2.1632) grad: 0.0721 (0.0751) time: 0.3792 data: 0.0027 max mem: 3970 +train: [4] [360/400] eta: 0:00:15 lr: 0.000294 loss: 2.1133 (2.1610) grad: 0.0736 (0.0752) time: 0.3863 data: 0.0034 max mem: 3970 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 2.0956 (2.1558) grad: 0.0734 (0.0752) time: 0.3780 data: 0.0033 max mem: 3970 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.0740 (2.1544) grad: 0.0680 (0.0747) time: 0.3672 data: 0.0034 max mem: 3970 +train: [4] Total time: 0:02:30 (0.3768 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.0740 (2.1544) grad: 0.0680 (0.0747) +eval (validation): [4] [ 0/63] eta: 0:03:39 time: 3.4880 data: 3.2315 max mem: 3970 +eval (validation): [4] [20/63] eta: 0:00:23 time: 0.3969 data: 0.0384 max mem: 3970 +eval (validation): [4] [40/63] eta: 0:00:10 time: 0.3520 data: 0.0028 max mem: 3970 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3344 data: 0.0033 max mem: 3970 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3367 data: 0.0032 max mem: 3970 +eval (validation): [4] Total time: 0:00:26 (0.4159 s / it) +cv: [4] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.670 acc: 0.852 f1: 0.827 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:14 lr: nan time: 3.3365 data: 3.0656 max mem: 3970 +train: [5] [ 20/400] eta: 0:03:10 lr: 0.000300 loss: 2.1040 (2.0952) grad: 0.0713 (0.0723) time: 0.3600 data: 0.0041 max mem: 3970 +train: [5] [ 40/400] eta: 0:02:38 lr: 0.000300 loss: 2.1097 (2.1175) grad: 0.0717 (0.0736) time: 0.3741 data: 0.0031 max mem: 3970 +train: [5] [ 60/400] eta: 0:02:20 lr: 0.000300 loss: 2.0975 (2.1014) grad: 0.0758 (0.0753) time: 0.3600 data: 0.0034 max mem: 3970 +train: [5] [ 80/400] eta: 0:02:07 lr: 0.000300 loss: 2.0627 (2.0894) grad: 0.0758 (0.0754) time: 0.3587 data: 0.0034 max mem: 3970 +train: [5] [100/400] eta: 0:01:57 lr: 0.000300 loss: 2.0468 (2.0887) grad: 0.0721 (0.0754) time: 0.3590 data: 0.0033 max mem: 3970 +train: [5] [120/400] eta: 0:01:48 lr: 0.000300 loss: 2.1227 (2.0930) grad: 0.0743 (0.0750) time: 0.3703 data: 0.0031 max mem: 3970 +train: [5] [140/400] eta: 0:01:39 lr: 0.000300 loss: 2.0968 (2.0915) grad: 0.0684 (0.0743) time: 0.3427 data: 0.0033 max mem: 3970 +train: [5] [160/400] eta: 0:01:31 lr: 0.000299 loss: 2.0699 (2.0891) grad: 0.0715 (0.0739) time: 0.3668 data: 0.0034 max mem: 3970 +train: [5] [180/400] eta: 0:01:22 lr: 0.000299 loss: 2.0229 (2.0867) grad: 0.0727 (0.0739) time: 0.3497 data: 0.0033 max mem: 3970 +train: [5] [200/400] eta: 0:01:14 lr: 0.000299 loss: 2.0494 (2.0820) grad: 0.0705 (0.0734) time: 0.3529 data: 0.0033 max mem: 3970 +train: [5] [220/400] eta: 0:01:07 lr: 0.000299 loss: 2.0158 (2.0751) grad: 0.0688 (0.0732) time: 0.3776 data: 0.0035 max mem: 3970 +train: [5] [240/400] eta: 0:00:59 lr: 0.000299 loss: 2.0319 (2.0723) grad: 0.0670 (0.0728) time: 0.3595 data: 0.0035 max mem: 3970 +train: [5] [260/400] eta: 0:00:51 lr: 0.000299 loss: 2.0393 (2.0678) grad: 0.0753 (0.0734) time: 0.3392 data: 0.0034 max mem: 3970 +train: [5] [280/400] eta: 0:00:44 lr: 0.000298 loss: 1.9863 (2.0632) grad: 0.0756 (0.0731) time: 0.3506 data: 0.0034 max mem: 3970 +train: [5] [300/400] eta: 0:00:37 lr: 0.000298 loss: 1.9862 (2.0585) grad: 0.0667 (0.0727) time: 0.5263 data: 0.1945 max mem: 3970 +train: [5] [320/400] eta: 0:00:30 lr: 0.000298 loss: 1.9922 (2.0570) grad: 0.0666 (0.0723) time: 0.3960 data: 0.0044 max mem: 3970 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 2.0222 (2.0539) grad: 0.0666 (0.0718) time: 0.3652 data: 0.0031 max mem: 3970 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 2.0276 (2.0541) grad: 0.0679 (0.0718) time: 0.3625 data: 0.0034 max mem: 3970 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.9999 (2.0481) grad: 0.0688 (0.0718) time: 0.3422 data: 0.0035 max mem: 3970 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 1.9599 (2.0449) grad: 0.0673 (0.0717) time: 0.3479 data: 0.0033 max mem: 3970 +train: [5] Total time: 0:02:30 (0.3758 s / it) +train: [5] Summary: lr: 0.000297 loss: 1.9599 (2.0449) grad: 0.0673 (0.0717) +eval (validation): [5] [ 0/63] eta: 0:03:46 time: 3.5936 data: 3.3024 max mem: 3970 +eval (validation): [5] [20/63] eta: 0:00:23 time: 0.3923 data: 0.0032 max mem: 3970 +eval (validation): [5] [40/63] eta: 0:00:10 time: 0.3533 data: 0.0035 max mem: 3970 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3359 data: 0.0035 max mem: 3970 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3409 data: 0.0033 max mem: 3970 +eval (validation): [5] Total time: 0:00:26 (0.4168 s / it) +cv: [5] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.578 acc: 0.864 f1: 0.846 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:21:53 lr: nan time: 3.2848 data: 3.0128 max mem: 3970 +train: [6] [ 20/400] eta: 0:03:16 lr: 0.000296 loss: 1.9415 (1.9756) grad: 0.0621 (0.0626) time: 0.3797 data: 0.0042 max mem: 3970 +train: [6] [ 40/400] eta: 0:02:39 lr: 0.000296 loss: 1.9847 (1.9910) grad: 0.0660 (0.0636) time: 0.3645 data: 0.0032 max mem: 3970 +train: [6] [ 60/400] eta: 0:02:22 lr: 0.000296 loss: 1.9773 (1.9729) grad: 0.0685 (0.0664) time: 0.3731 data: 0.0035 max mem: 3970 +train: [6] [ 80/400] eta: 0:02:11 lr: 0.000295 loss: 1.9409 (1.9724) grad: 0.0737 (0.0690) time: 0.3802 data: 0.0033 max mem: 3970 +train: [6] [100/400] eta: 0:02:01 lr: 0.000295 loss: 1.9981 (1.9728) grad: 0.0713 (0.0685) time: 0.3855 data: 0.0033 max mem: 3970 +train: [6] [120/400] eta: 0:01:53 lr: 0.000295 loss: 1.9817 (1.9747) grad: 0.0668 (0.0685) time: 0.3961 data: 0.0034 max mem: 3970 +train: [6] [140/400] eta: 0:01:44 lr: 0.000294 loss: 1.9627 (1.9700) grad: 0.0699 (0.0692) time: 0.3810 data: 0.0034 max mem: 3970 +train: [6] [160/400] eta: 0:01:35 lr: 0.000294 loss: 1.9570 (1.9728) grad: 0.0681 (0.0688) time: 0.3869 data: 0.0034 max mem: 3970 +train: [6] [180/400] eta: 0:01:26 lr: 0.000293 loss: 1.9397 (1.9655) grad: 0.0666 (0.0689) time: 0.3669 data: 0.0033 max mem: 3970 +train: [6] [200/400] eta: 0:01:17 lr: 0.000293 loss: 1.9532 (1.9685) grad: 0.0686 (0.0687) time: 0.3409 data: 0.0032 max mem: 3970 +train: [6] [220/400] eta: 0:01:09 lr: 0.000292 loss: 1.9577 (1.9655) grad: 0.0667 (0.0686) time: 0.3596 data: 0.0035 max mem: 3970 +train: [6] [240/400] eta: 0:01:01 lr: 0.000292 loss: 1.9205 (1.9628) grad: 0.0667 (0.0684) time: 0.3857 data: 0.0035 max mem: 3970 +train: [6] [260/400] eta: 0:00:54 lr: 0.000291 loss: 1.9509 (1.9618) grad: 0.0659 (0.0684) time: 0.3867 data: 0.0034 max mem: 3970 +train: [6] [280/400] eta: 0:00:46 lr: 0.000291 loss: 1.9509 (1.9570) grad: 0.0662 (0.0683) time: 0.3885 data: 0.0032 max mem: 3970 +train: [6] [300/400] eta: 0:00:39 lr: 0.000290 loss: 1.8805 (1.9556) grad: 0.0721 (0.0687) time: 0.5764 data: 0.2022 max mem: 3970 +train: [6] [320/400] eta: 0:00:31 lr: 0.000290 loss: 1.9134 (1.9534) grad: 0.0668 (0.0683) time: 0.3835 data: 0.0043 max mem: 3970 +train: [6] [340/400] eta: 0:00:23 lr: 0.000289 loss: 1.9168 (1.9510) grad: 0.0640 (0.0683) time: 0.3937 data: 0.0022 max mem: 3970 +train: [6] [360/400] eta: 0:00:15 lr: 0.000288 loss: 1.9228 (1.9502) grad: 0.0664 (0.0683) time: 0.3875 data: 0.0032 max mem: 3970 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 1.9340 (1.9499) grad: 0.0607 (0.0679) time: 0.3702 data: 0.0033 max mem: 3970 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 1.9469 (1.9484) grad: 0.0607 (0.0679) time: 0.3846 data: 0.0036 max mem: 3970 +train: [6] Total time: 0:02:38 (0.3962 s / it) +train: [6] Summary: lr: 0.000287 loss: 1.9469 (1.9484) grad: 0.0607 (0.0679) +eval (validation): [6] [ 0/63] eta: 0:03:44 time: 3.5612 data: 3.3024 max mem: 3970 +eval (validation): [6] [20/63] eta: 0:00:23 time: 0.3928 data: 0.0038 max mem: 3970 +eval (validation): [6] [40/63] eta: 0:00:10 time: 0.3712 data: 0.0033 max mem: 3970 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3497 data: 0.0034 max mem: 3970 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3525 data: 0.0033 max mem: 3970 +eval (validation): [6] Total time: 0:00:26 (0.4267 s / it) +cv: [6] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.570 acc: 0.881 f1: 0.868 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:23:15 lr: nan time: 3.4900 data: 3.2330 max mem: 3970 +train: [7] [ 20/400] eta: 0:03:22 lr: 0.000286 loss: 1.9052 (1.9355) grad: 0.0666 (0.0687) time: 0.3839 data: 0.0035 max mem: 3970 +train: [7] [ 40/400] eta: 0:02:48 lr: 0.000286 loss: 1.9052 (1.9217) grad: 0.0672 (0.0682) time: 0.4002 data: 0.0030 max mem: 3970 +train: [7] [ 60/400] eta: 0:02:30 lr: 0.000285 loss: 1.8725 (1.9059) grad: 0.0672 (0.0687) time: 0.3933 data: 0.0029 max mem: 3970 +train: [7] [ 80/400] eta: 0:02:20 lr: 0.000284 loss: 1.8668 (1.9010) grad: 0.0717 (0.0694) time: 0.4207 data: 0.0033 max mem: 3970 +train: [7] [100/400] eta: 0:02:06 lr: 0.000284 loss: 1.9081 (1.9035) grad: 0.0699 (0.0687) time: 0.3645 data: 0.0035 max mem: 3970 +train: [7] [120/400] eta: 0:01:56 lr: 0.000283 loss: 1.9114 (1.9034) grad: 0.0627 (0.0674) time: 0.3743 data: 0.0034 max mem: 3970 +train: [7] [140/400] eta: 0:01:45 lr: 0.000282 loss: 1.8820 (1.9001) grad: 0.0627 (0.0667) time: 0.3602 data: 0.0035 max mem: 3970 +train: [7] [160/400] eta: 0:01:36 lr: 0.000282 loss: 1.8940 (1.9000) grad: 0.0641 (0.0670) time: 0.3603 data: 0.0038 max mem: 3970 +train: [7] [180/400] eta: 0:01:27 lr: 0.000281 loss: 1.8940 (1.9007) grad: 0.0657 (0.0668) time: 0.3755 data: 0.0034 max mem: 3970 +train: [7] [200/400] eta: 0:01:18 lr: 0.000280 loss: 1.8835 (1.8964) grad: 0.0642 (0.0667) time: 0.3493 data: 0.0033 max mem: 3970 +train: [7] [220/400] eta: 0:01:10 lr: 0.000279 loss: 1.8793 (1.8932) grad: 0.0642 (0.0665) time: 0.3633 data: 0.0035 max mem: 3970 +train: [7] [240/400] eta: 0:01:02 lr: 0.000278 loss: 1.8869 (1.8954) grad: 0.0646 (0.0665) time: 0.3666 data: 0.0035 max mem: 3970 +train: [7] [260/400] eta: 0:00:54 lr: 0.000278 loss: 1.8850 (1.8911) grad: 0.0641 (0.0661) time: 0.3718 data: 0.0034 max mem: 3970 +train: [7] [280/400] eta: 0:00:46 lr: 0.000277 loss: 1.8595 (1.8916) grad: 0.0634 (0.0659) time: 0.3648 data: 0.0035 max mem: 3970 +train: [7] [300/400] eta: 0:00:39 lr: 0.000276 loss: 1.8861 (1.8915) grad: 0.0656 (0.0660) time: 0.5548 data: 0.2048 max mem: 3970 +train: [7] [320/400] eta: 0:00:31 lr: 0.000275 loss: 1.8434 (1.8892) grad: 0.0659 (0.0658) time: 0.3888 data: 0.0032 max mem: 3970 +train: [7] [340/400] eta: 0:00:23 lr: 0.000274 loss: 1.8689 (1.8902) grad: 0.0599 (0.0654) time: 0.3751 data: 0.0029 max mem: 3970 +train: [7] [360/400] eta: 0:00:15 lr: 0.000273 loss: 1.8689 (1.8890) grad: 0.0590 (0.0651) time: 0.3907 data: 0.0034 max mem: 3970 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 1.8423 (1.8869) grad: 0.0599 (0.0649) time: 0.3803 data: 0.0033 max mem: 3970 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 1.8395 (1.8845) grad: 0.0637 (0.0650) time: 0.3763 data: 0.0032 max mem: 3970 +train: [7] Total time: 0:02:37 (0.3938 s / it) +train: [7] Summary: lr: 0.000271 loss: 1.8395 (1.8845) grad: 0.0637 (0.0650) +eval (validation): [7] [ 0/63] eta: 0:03:56 time: 3.7584 data: 3.4450 max mem: 3970 +eval (validation): [7] [20/63] eta: 0:00:22 time: 0.3538 data: 0.0038 max mem: 3970 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3460 data: 0.0033 max mem: 3970 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3270 data: 0.0034 max mem: 3970 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3226 data: 0.0032 max mem: 3970 +eval (validation): [7] Total time: 0:00:25 (0.4015 s / it) +cv: [7] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.508 acc: 0.889 f1: 0.875 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:21:42 lr: nan time: 3.2574 data: 3.0386 max mem: 3970 +train: [8] [ 20/400] eta: 0:03:13 lr: 0.000270 loss: 1.8755 (1.8809) grad: 0.0583 (0.0604) time: 0.3714 data: 0.0036 max mem: 3970 +train: [8] [ 40/400] eta: 0:02:36 lr: 0.000270 loss: 1.8755 (1.8845) grad: 0.0638 (0.0652) time: 0.3557 data: 0.0029 max mem: 3970 +train: [8] [ 60/400] eta: 0:02:19 lr: 0.000269 loss: 1.8385 (1.8669) grad: 0.0658 (0.0661) time: 0.3586 data: 0.0034 max mem: 3970 +train: [8] [ 80/400] eta: 0:02:06 lr: 0.000268 loss: 1.8368 (1.8642) grad: 0.0642 (0.0651) time: 0.3578 data: 0.0034 max mem: 3970 +train: [8] [100/400] eta: 0:01:56 lr: 0.000267 loss: 1.8420 (1.8608) grad: 0.0614 (0.0645) time: 0.3575 data: 0.0035 max mem: 3970 +train: [8] [120/400] eta: 0:01:47 lr: 0.000266 loss: 1.8077 (1.8539) grad: 0.0598 (0.0635) time: 0.3594 data: 0.0034 max mem: 3970 +train: [8] [140/400] eta: 0:01:39 lr: 0.000265 loss: 1.8013 (1.8480) grad: 0.0597 (0.0638) time: 0.3615 data: 0.0034 max mem: 3970 +train: [8] [160/400] eta: 0:01:30 lr: 0.000264 loss: 1.8013 (1.8450) grad: 0.0606 (0.0635) time: 0.3563 data: 0.0036 max mem: 3970 +train: [8] [180/400] eta: 0:01:22 lr: 0.000263 loss: 1.7841 (1.8368) grad: 0.0622 (0.0634) time: 0.3672 data: 0.0035 max mem: 3970 +train: [8] [200/400] eta: 0:01:14 lr: 0.000262 loss: 1.8099 (1.8375) grad: 0.0634 (0.0635) time: 0.3537 data: 0.0032 max mem: 3970 +train: [8] [220/400] eta: 0:01:07 lr: 0.000260 loss: 1.8302 (1.8383) grad: 0.0602 (0.0633) time: 0.3681 data: 0.0032 max mem: 3970 +train: [8] [240/400] eta: 0:00:59 lr: 0.000259 loss: 1.8210 (1.8351) grad: 0.0606 (0.0632) time: 0.3651 data: 0.0035 max mem: 3970 +train: [8] [260/400] eta: 0:00:52 lr: 0.000258 loss: 1.8352 (1.8354) grad: 0.0612 (0.0634) time: 0.3574 data: 0.0032 max mem: 3970 +train: [8] [280/400] eta: 0:00:44 lr: 0.000257 loss: 1.8352 (1.8346) grad: 0.0600 (0.0635) time: 0.3537 data: 0.0032 max mem: 3970 +train: [8] [300/400] eta: 0:00:38 lr: 0.000256 loss: 1.8283 (1.8323) grad: 0.0597 (0.0634) time: 0.5144 data: 0.1870 max mem: 3970 +train: [8] [320/400] eta: 0:00:30 lr: 0.000255 loss: 1.8169 (1.8306) grad: 0.0607 (0.0634) time: 0.3570 data: 0.0033 max mem: 3970 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 1.7879 (1.8274) grad: 0.0653 (0.0636) time: 0.3434 data: 0.0032 max mem: 3970 +train: [8] [360/400] eta: 0:00:15 lr: 0.000253 loss: 1.7653 (1.8262) grad: 0.0670 (0.0639) time: 0.3571 data: 0.0030 max mem: 3970 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 1.7653 (1.8234) grad: 0.0670 (0.0640) time: 0.3756 data: 0.0034 max mem: 3970 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 1.8105 (1.8242) grad: 0.0600 (0.0638) time: 0.3488 data: 0.0033 max mem: 3970 +train: [8] Total time: 0:02:29 (0.3745 s / it) +train: [8] Summary: lr: 0.000250 loss: 1.8105 (1.8242) grad: 0.0600 (0.0638) +eval (validation): [8] [ 0/63] eta: 0:03:48 time: 3.6313 data: 3.3229 max mem: 3970 +eval (validation): [8] [20/63] eta: 0:00:22 time: 0.3758 data: 0.0040 max mem: 3970 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3547 data: 0.0031 max mem: 3970 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3498 data: 0.0031 max mem: 3970 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3489 data: 0.0032 max mem: 3970 +eval (validation): [8] Total time: 0:00:26 (0.4167 s / it) +cv: [8] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.508 acc: 0.898 f1: 0.885 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:23:05 lr: nan time: 3.4644 data: 3.1618 max mem: 3970 +train: [9] [ 20/400] eta: 0:03:12 lr: 0.000249 loss: 1.8076 (1.8143) grad: 0.0540 (0.0601) time: 0.3587 data: 0.0044 max mem: 3970 +train: [9] [ 40/400] eta: 0:02:39 lr: 0.000248 loss: 1.8150 (1.8135) grad: 0.0602 (0.0600) time: 0.3756 data: 0.0030 max mem: 3970 +train: [9] [ 60/400] eta: 0:02:24 lr: 0.000247 loss: 1.8071 (1.8144) grad: 0.0602 (0.0597) time: 0.3926 data: 0.0033 max mem: 3970 +train: [9] [ 80/400] eta: 0:02:13 lr: 0.000246 loss: 1.7921 (1.8017) grad: 0.0613 (0.0612) time: 0.3956 data: 0.0034 max mem: 3970 +train: [9] [100/400] eta: 0:02:03 lr: 0.000244 loss: 1.7552 (1.7959) grad: 0.0615 (0.0614) time: 0.3911 data: 0.0033 max mem: 3970 +train: [9] [120/400] eta: 0:01:55 lr: 0.000243 loss: 1.7512 (1.7941) grad: 0.0614 (0.0612) time: 0.4035 data: 0.0034 max mem: 3970 +train: [9] [140/400] eta: 0:01:46 lr: 0.000242 loss: 1.7541 (1.7942) grad: 0.0588 (0.0610) time: 0.3888 data: 0.0033 max mem: 3970 +train: [9] [160/400] eta: 0:01:36 lr: 0.000241 loss: 1.7493 (1.7888) grad: 0.0555 (0.0606) time: 0.3713 data: 0.0034 max mem: 3970 +train: [9] [180/400] eta: 0:01:28 lr: 0.000240 loss: 1.7493 (1.7871) grad: 0.0601 (0.0611) time: 0.4043 data: 0.0033 max mem: 3970 +train: [9] [200/400] eta: 0:01:20 lr: 0.000238 loss: 1.7823 (1.7867) grad: 0.0610 (0.0611) time: 0.3940 data: 0.0033 max mem: 3970 +train: [9] [220/400] eta: 0:01:11 lr: 0.000237 loss: 1.7722 (1.7848) grad: 0.0571 (0.0608) time: 0.3662 data: 0.0031 max mem: 3970 +train: [9] [240/400] eta: 0:01:03 lr: 0.000236 loss: 1.7668 (1.7856) grad: 0.0588 (0.0609) time: 0.3908 data: 0.0033 max mem: 3970 +train: [9] [260/400] eta: 0:00:56 lr: 0.000234 loss: 1.7863 (1.7878) grad: 0.0615 (0.0610) time: 0.4176 data: 0.0033 max mem: 3970 +train: [9] [280/400] eta: 0:00:48 lr: 0.000233 loss: 1.7863 (1.7866) grad: 0.0615 (0.0611) time: 0.4018 data: 0.0033 max mem: 3970 +train: [9] [300/400] eta: 0:00:41 lr: 0.000232 loss: 1.7541 (1.7848) grad: 0.0619 (0.0611) time: 0.5641 data: 0.1847 max mem: 3970 +train: [9] [320/400] eta: 0:00:32 lr: 0.000230 loss: 1.7830 (1.7863) grad: 0.0608 (0.0611) time: 0.3858 data: 0.0074 max mem: 3970 +train: [9] [340/400] eta: 0:00:24 lr: 0.000229 loss: 1.7830 (1.7855) grad: 0.0625 (0.0611) time: 0.3651 data: 0.0030 max mem: 3970 +train: [9] [360/400] eta: 0:00:16 lr: 0.000228 loss: 1.7472 (1.7840) grad: 0.0547 (0.0607) time: 0.4160 data: 0.0036 max mem: 3970 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 1.7472 (1.7826) grad: 0.0541 (0.0606) time: 0.3836 data: 0.0033 max mem: 3970 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 1.7480 (1.7812) grad: 0.0606 (0.0605) time: 0.3751 data: 0.0032 max mem: 3970 +train: [9] Total time: 0:02:41 (0.4050 s / it) +train: [9] Summary: lr: 0.000225 loss: 1.7480 (1.7812) grad: 0.0606 (0.0605) +eval (validation): [9] [ 0/63] eta: 0:03:47 time: 3.6175 data: 3.3018 max mem: 3970 +eval (validation): [9] [20/63] eta: 0:00:24 time: 0.4245 data: 0.0030 max mem: 3970 +eval (validation): [9] [40/63] eta: 0:00:11 time: 0.3790 data: 0.0033 max mem: 3970 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3606 data: 0.0033 max mem: 3970 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3590 data: 0.0033 max mem: 3970 +eval (validation): [9] Total time: 0:00:27 (0.4436 s / it) +cv: [9] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.475 acc: 0.904 f1: 0.893 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:24:28 lr: nan time: 3.6718 data: 3.3936 max mem: 3970 +train: [10] [ 20/400] eta: 0:03:22 lr: 0.000224 loss: 1.7415 (1.7447) grad: 0.0566 (0.0573) time: 0.3746 data: 0.0034 max mem: 3970 +train: [10] [ 40/400] eta: 0:02:45 lr: 0.000222 loss: 1.7415 (1.7578) grad: 0.0599 (0.0588) time: 0.3844 data: 0.0031 max mem: 3970 +train: [10] [ 60/400] eta: 0:02:26 lr: 0.000221 loss: 1.7339 (1.7553) grad: 0.0611 (0.0602) time: 0.3708 data: 0.0036 max mem: 3970 +train: [10] [ 80/400] eta: 0:02:12 lr: 0.000220 loss: 1.7337 (1.7592) grad: 0.0611 (0.0603) time: 0.3617 data: 0.0034 max mem: 3970 +train: [10] [100/400] eta: 0:02:01 lr: 0.000218 loss: 1.7980 (1.7707) grad: 0.0589 (0.0604) time: 0.3704 data: 0.0037 max mem: 3970 +train: [10] [120/400] eta: 0:01:51 lr: 0.000217 loss: 1.8059 (1.7670) grad: 0.0589 (0.0608) time: 0.3649 data: 0.0036 max mem: 3970 +train: [10] [140/400] eta: 0:01:43 lr: 0.000215 loss: 1.7317 (1.7612) grad: 0.0616 (0.0612) time: 0.3881 data: 0.0032 max mem: 3970 +train: [10] [160/400] eta: 0:01:34 lr: 0.000214 loss: 1.7479 (1.7631) grad: 0.0602 (0.0610) time: 0.3632 data: 0.0035 max mem: 3970 +train: [10] [180/400] eta: 0:01:25 lr: 0.000213 loss: 1.7479 (1.7597) grad: 0.0568 (0.0606) time: 0.3690 data: 0.0033 max mem: 3970 +train: [10] [200/400] eta: 0:01:17 lr: 0.000211 loss: 1.7041 (1.7571) grad: 0.0568 (0.0604) time: 0.3590 data: 0.0031 max mem: 3970 +train: [10] [220/400] eta: 0:01:09 lr: 0.000210 loss: 1.7524 (1.7556) grad: 0.0597 (0.0604) time: 0.3534 data: 0.0032 max mem: 3970 +train: [10] [240/400] eta: 0:01:01 lr: 0.000208 loss: 1.7331 (1.7531) grad: 0.0621 (0.0605) time: 0.3605 data: 0.0034 max mem: 3970 +train: [10] [260/400] eta: 0:00:53 lr: 0.000207 loss: 1.7238 (1.7523) grad: 0.0633 (0.0606) time: 0.3721 data: 0.0034 max mem: 3970 +train: [10] [280/400] eta: 0:00:45 lr: 0.000205 loss: 1.7565 (1.7516) grad: 0.0642 (0.0607) time: 0.3817 data: 0.0034 max mem: 3970 +train: [10] [300/400] eta: 0:00:39 lr: 0.000204 loss: 1.7466 (1.7503) grad: 0.0640 (0.0608) time: 0.5583 data: 0.1985 max mem: 3970 +train: [10] [320/400] eta: 0:00:31 lr: 0.000202 loss: 1.7191 (1.7488) grad: 0.0595 (0.0605) time: 0.3589 data: 0.0037 max mem: 3970 +train: [10] [340/400] eta: 0:00:23 lr: 0.000201 loss: 1.7526 (1.7512) grad: 0.0604 (0.0607) time: 0.3556 data: 0.0032 max mem: 3970 +train: [10] [360/400] eta: 0:00:15 lr: 0.000199 loss: 1.7526 (1.7502) grad: 0.0627 (0.0605) time: 0.3721 data: 0.0032 max mem: 3970 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 1.7186 (1.7499) grad: 0.0597 (0.0606) time: 0.3565 data: 0.0034 max mem: 3970 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 1.7082 (1.7482) grad: 0.0593 (0.0603) time: 0.3583 data: 0.0033 max mem: 3970 +train: [10] Total time: 0:02:34 (0.3853 s / it) +train: [10] Summary: lr: 0.000196 loss: 1.7082 (1.7482) grad: 0.0593 (0.0603) +eval (validation): [10] [ 0/63] eta: 0:03:34 time: 3.4035 data: 3.1705 max mem: 3970 +eval (validation): [10] [20/63] eta: 0:00:22 time: 0.3905 data: 0.0238 max mem: 3970 +eval (validation): [10] [40/63] eta: 0:00:10 time: 0.3322 data: 0.0028 max mem: 3970 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3306 data: 0.0032 max mem: 3970 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3258 data: 0.0032 max mem: 3970 +eval (validation): [10] Total time: 0:00:25 (0.4043 s / it) +cv: [10] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 0.561 acc: 0.883 f1: 0.872 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:10 lr: nan time: 3.3274 data: 3.1054 max mem: 3970 +train: [11] [ 20/400] eta: 0:03:14 lr: 0.000195 loss: 1.7294 (1.6978) grad: 0.0512 (0.0541) time: 0.3719 data: 0.0047 max mem: 3970 +train: [11] [ 40/400] eta: 0:02:38 lr: 0.000193 loss: 1.7294 (1.7228) grad: 0.0528 (0.0577) time: 0.3633 data: 0.0028 max mem: 3970 +train: [11] [ 60/400] eta: 0:02:19 lr: 0.000192 loss: 1.7088 (1.7215) grad: 0.0579 (0.0579) time: 0.3506 data: 0.0035 max mem: 3970 +train: [11] [ 80/400] eta: 0:02:06 lr: 0.000190 loss: 1.7194 (1.7297) grad: 0.0570 (0.0584) time: 0.3549 data: 0.0035 max mem: 3970 +train: [11] [100/400] eta: 0:01:56 lr: 0.000189 loss: 1.7356 (1.7297) grad: 0.0579 (0.0582) time: 0.3485 data: 0.0035 max mem: 3970 +train: [11] [120/400] eta: 0:01:46 lr: 0.000187 loss: 1.7001 (1.7261) grad: 0.0579 (0.0584) time: 0.3519 data: 0.0035 max mem: 3970 +train: [11] [140/400] eta: 0:01:37 lr: 0.000186 loss: 1.7002 (1.7271) grad: 0.0576 (0.0587) time: 0.3439 data: 0.0033 max mem: 3970 +train: [11] [160/400] eta: 0:01:30 lr: 0.000184 loss: 1.7002 (1.7219) grad: 0.0576 (0.0587) time: 0.3822 data: 0.0033 max mem: 3970 +train: [11] [180/400] eta: 0:01:22 lr: 0.000183 loss: 1.6670 (1.7161) grad: 0.0614 (0.0589) time: 0.3573 data: 0.0031 max mem: 3970 +train: [11] [200/400] eta: 0:01:14 lr: 0.000181 loss: 1.7068 (1.7186) grad: 0.0576 (0.0587) time: 0.3478 data: 0.0033 max mem: 3970 +train: [11] [220/400] eta: 0:01:06 lr: 0.000180 loss: 1.7104 (1.7181) grad: 0.0563 (0.0587) time: 0.3428 data: 0.0031 max mem: 3970 +train: [11] [240/400] eta: 0:00:58 lr: 0.000178 loss: 1.7350 (1.7238) grad: 0.0568 (0.0586) time: 0.3550 data: 0.0033 max mem: 3970 +train: [11] [260/400] eta: 0:00:51 lr: 0.000177 loss: 1.7617 (1.7262) grad: 0.0558 (0.0585) time: 0.3614 data: 0.0033 max mem: 3970 +train: [11] [280/400] eta: 0:00:44 lr: 0.000175 loss: 1.7267 (1.7253) grad: 0.0585 (0.0586) time: 0.3594 data: 0.0031 max mem: 3970 +train: [11] [300/400] eta: 0:00:37 lr: 0.000174 loss: 1.6973 (1.7236) grad: 0.0585 (0.0587) time: 0.5317 data: 0.1961 max mem: 3970 +train: [11] [320/400] eta: 0:00:30 lr: 0.000172 loss: 1.6973 (1.7249) grad: 0.0567 (0.0587) time: 0.3385 data: 0.0034 max mem: 3970 +train: [11] [340/400] eta: 0:00:22 lr: 0.000170 loss: 1.7175 (1.7239) grad: 0.0584 (0.0591) time: 0.3623 data: 0.0034 max mem: 3970 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 1.7175 (1.7235) grad: 0.0576 (0.0589) time: 0.3753 data: 0.0036 max mem: 3970 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 1.6870 (1.7211) grad: 0.0582 (0.0589) time: 0.3605 data: 0.0033 max mem: 3970 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 1.7118 (1.7223) grad: 0.0595 (0.0590) time: 0.3633 data: 0.0032 max mem: 3970 +train: [11] Total time: 0:02:29 (0.3738 s / it) +train: [11] Summary: lr: 0.000166 loss: 1.7118 (1.7223) grad: 0.0595 (0.0590) +eval (validation): [11] [ 0/63] eta: 0:03:31 time: 3.3575 data: 3.1196 max mem: 3970 +eval (validation): [11] [20/63] eta: 0:00:22 time: 0.3801 data: 0.0044 max mem: 3970 +eval (validation): [11] [40/63] eta: 0:00:10 time: 0.3460 data: 0.0030 max mem: 3970 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3352 data: 0.0034 max mem: 3970 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3336 data: 0.0034 max mem: 3970 +eval (validation): [11] Total time: 0:00:25 (0.4067 s / it) +cv: [11] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.466 acc: 0.899 f1: 0.878 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:23:55 lr: nan time: 3.5894 data: 3.3033 max mem: 3970 +train: [12] [ 20/400] eta: 0:03:23 lr: 0.000164 loss: 1.7168 (1.7127) grad: 0.0538 (0.0592) time: 0.3825 data: 0.0034 max mem: 3970 +train: [12] [ 40/400] eta: 0:02:49 lr: 0.000163 loss: 1.6756 (1.6921) grad: 0.0538 (0.0569) time: 0.4018 data: 0.0033 max mem: 3970 +train: [12] [ 60/400] eta: 0:02:29 lr: 0.000161 loss: 1.6929 (1.7049) grad: 0.0540 (0.0575) time: 0.3744 data: 0.0035 max mem: 3970 +train: [12] [ 80/400] eta: 0:02:15 lr: 0.000160 loss: 1.7139 (1.7058) grad: 0.0580 (0.0573) time: 0.3731 data: 0.0035 max mem: 3970 +train: [12] [100/400] eta: 0:02:03 lr: 0.000158 loss: 1.7040 (1.7006) grad: 0.0574 (0.0568) time: 0.3721 data: 0.0035 max mem: 3970 +train: [12] [120/400] eta: 0:01:53 lr: 0.000156 loss: 1.6676 (1.6930) grad: 0.0572 (0.0571) time: 0.3734 data: 0.0036 max mem: 3970 +train: [12] [140/400] eta: 0:01:44 lr: 0.000155 loss: 1.6525 (1.6921) grad: 0.0572 (0.0573) time: 0.3751 data: 0.0033 max mem: 3970 +train: [12] [160/400] eta: 0:01:35 lr: 0.000153 loss: 1.6783 (1.6931) grad: 0.0584 (0.0576) time: 0.3746 data: 0.0034 max mem: 3970 +train: [12] [180/400] eta: 0:01:27 lr: 0.000152 loss: 1.7031 (1.6973) grad: 0.0566 (0.0574) time: 0.3754 data: 0.0036 max mem: 3970 +train: [12] [200/400] eta: 0:01:18 lr: 0.000150 loss: 1.7261 (1.6996) grad: 0.0566 (0.0578) time: 0.3500 data: 0.0033 max mem: 3970 +train: [12] [220/400] eta: 0:01:10 lr: 0.000149 loss: 1.7289 (1.6986) grad: 0.0535 (0.0578) time: 0.3671 data: 0.0033 max mem: 3970 +train: [12] [240/400] eta: 0:01:02 lr: 0.000147 loss: 1.7027 (1.7000) grad: 0.0585 (0.0580) time: 0.3759 data: 0.0033 max mem: 3970 +train: [12] [260/400] eta: 0:00:54 lr: 0.000145 loss: 1.6686 (1.6967) grad: 0.0593 (0.0580) time: 0.3652 data: 0.0032 max mem: 3970 +train: [12] [280/400] eta: 0:00:46 lr: 0.000144 loss: 1.6602 (1.6950) grad: 0.0593 (0.0579) time: 0.3729 data: 0.0032 max mem: 3970 +train: [12] [300/400] eta: 0:00:39 lr: 0.000142 loss: 1.6764 (1.6951) grad: 0.0588 (0.0581) time: 0.5373 data: 0.1939 max mem: 3970 +train: [12] [320/400] eta: 0:00:31 lr: 0.000141 loss: 1.6902 (1.6965) grad: 0.0576 (0.0581) time: 0.4166 data: 0.0042 max mem: 3970 +train: [12] [340/400] eta: 0:00:23 lr: 0.000139 loss: 1.6902 (1.6966) grad: 0.0569 (0.0578) time: 0.3685 data: 0.0032 max mem: 3970 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 1.6559 (1.6945) grad: 0.0576 (0.0578) time: 0.3664 data: 0.0035 max mem: 3970 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 1.6700 (1.6951) grad: 0.0602 (0.0578) time: 0.3662 data: 0.0034 max mem: 3970 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 1.6871 (1.6951) grad: 0.0597 (0.0579) time: 0.3655 data: 0.0034 max mem: 3970 +train: [12] Total time: 0:02:36 (0.3910 s / it) +train: [12] Summary: lr: 0.000134 loss: 1.6871 (1.6951) grad: 0.0597 (0.0579) +eval (validation): [12] [ 0/63] eta: 0:03:37 time: 3.4511 data: 3.2235 max mem: 3970 +eval (validation): [12] [20/63] eta: 0:00:24 time: 0.4220 data: 0.0045 max mem: 3970 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3660 data: 0.0031 max mem: 3970 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3350 data: 0.0034 max mem: 3970 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3332 data: 0.0033 max mem: 3970 +eval (validation): [12] Total time: 0:00:26 (0.4280 s / it) +cv: [12] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.455 acc: 0.898 f1: 0.873 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:21:52 lr: nan time: 3.2825 data: 3.0158 max mem: 3970 +train: [13] [ 20/400] eta: 0:03:18 lr: 0.000133 loss: 1.6884 (1.6983) grad: 0.0565 (0.0606) time: 0.3849 data: 0.0044 max mem: 3970 +train: [13] [ 40/400] eta: 0:02:38 lr: 0.000131 loss: 1.7047 (1.6944) grad: 0.0565 (0.0601) time: 0.3538 data: 0.0030 max mem: 3970 +train: [13] [ 60/400] eta: 0:02:19 lr: 0.000130 loss: 1.6975 (1.6915) grad: 0.0598 (0.0604) time: 0.3493 data: 0.0036 max mem: 3970 +train: [13] [ 80/400] eta: 0:02:06 lr: 0.000128 loss: 1.6929 (1.6949) grad: 0.0604 (0.0603) time: 0.3534 data: 0.0034 max mem: 3970 +train: [13] [100/400] eta: 0:01:56 lr: 0.000127 loss: 1.6910 (1.6918) grad: 0.0604 (0.0603) time: 0.3574 data: 0.0033 max mem: 3970 +train: [13] [120/400] eta: 0:01:46 lr: 0.000125 loss: 1.6855 (1.6880) grad: 0.0558 (0.0594) time: 0.3464 data: 0.0035 max mem: 3970 +train: [13] [140/400] eta: 0:01:38 lr: 0.000124 loss: 1.6685 (1.6836) grad: 0.0561 (0.0591) time: 0.3495 data: 0.0033 max mem: 3970 +train: [13] [160/400] eta: 0:01:30 lr: 0.000122 loss: 1.6638 (1.6817) grad: 0.0588 (0.0588) time: 0.3646 data: 0.0033 max mem: 3970 +train: [13] [180/400] eta: 0:01:22 lr: 0.000120 loss: 1.7003 (1.6848) grad: 0.0605 (0.0591) time: 0.3701 data: 0.0035 max mem: 3970 +train: [13] [200/400] eta: 0:01:14 lr: 0.000119 loss: 1.7055 (1.6843) grad: 0.0557 (0.0587) time: 0.3542 data: 0.0031 max mem: 3970 +train: [13] [220/400] eta: 0:01:06 lr: 0.000117 loss: 1.6801 (1.6859) grad: 0.0557 (0.0586) time: 0.3492 data: 0.0033 max mem: 3970 +train: [13] [240/400] eta: 0:00:59 lr: 0.000116 loss: 1.6954 (1.6859) grad: 0.0605 (0.0590) time: 0.3863 data: 0.0032 max mem: 3970 +train: [13] [260/400] eta: 0:00:52 lr: 0.000114 loss: 1.7117 (1.6883) grad: 0.0605 (0.0591) time: 0.3685 data: 0.0031 max mem: 3970 +train: [13] [280/400] eta: 0:00:44 lr: 0.000113 loss: 1.6959 (1.6868) grad: 0.0604 (0.0591) time: 0.3732 data: 0.0035 max mem: 3970 +train: [13] [300/400] eta: 0:00:38 lr: 0.000111 loss: 1.6621 (1.6855) grad: 0.0574 (0.0590) time: 0.5443 data: 0.2023 max mem: 3970 +train: [13] [320/400] eta: 0:00:30 lr: 0.000110 loss: 1.6888 (1.6874) grad: 0.0563 (0.0590) time: 0.3637 data: 0.0113 max mem: 3970 +train: [13] [340/400] eta: 0:00:22 lr: 0.000108 loss: 1.6787 (1.6855) grad: 0.0566 (0.0588) time: 0.3530 data: 0.0024 max mem: 3970 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 1.6587 (1.6847) grad: 0.0568 (0.0589) time: 0.3814 data: 0.0034 max mem: 3970 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 1.6717 (1.6850) grad: 0.0569 (0.0590) time: 0.3581 data: 0.0037 max mem: 3970 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 1.6984 (1.6860) grad: 0.0559 (0.0588) time: 0.3526 data: 0.0035 max mem: 3970 +train: [13] Total time: 0:02:31 (0.3783 s / it) +train: [13] Summary: lr: 0.000104 loss: 1.6984 (1.6860) grad: 0.0559 (0.0588) +eval (validation): [13] [ 0/63] eta: 0:03:37 time: 3.4484 data: 3.2086 max mem: 3970 +eval (validation): [13] [20/63] eta: 0:00:22 time: 0.3770 data: 0.0224 max mem: 3970 +eval (validation): [13] [40/63] eta: 0:00:10 time: 0.3452 data: 0.0033 max mem: 3970 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3375 data: 0.0033 max mem: 3970 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3316 data: 0.0028 max mem: 3970 +eval (validation): [13] Total time: 0:00:25 (0.4087 s / it) +cv: [13] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.442 acc: 0.908 f1: 0.897 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:22:54 lr: nan time: 3.4374 data: 3.2110 max mem: 3970 +train: [14] [ 20/400] eta: 0:03:21 lr: 0.000102 loss: 1.6426 (1.6614) grad: 0.0542 (0.0532) time: 0.3849 data: 0.0044 max mem: 3970 +train: [14] [ 40/400] eta: 0:02:48 lr: 0.000101 loss: 1.6534 (1.6649) grad: 0.0542 (0.0535) time: 0.4040 data: 0.0033 max mem: 3970 +train: [14] [ 60/400] eta: 0:02:29 lr: 0.000099 loss: 1.6628 (1.6594) grad: 0.0539 (0.0533) time: 0.3837 data: 0.0036 max mem: 3970 +train: [14] [ 80/400] eta: 0:02:16 lr: 0.000098 loss: 1.6721 (1.6705) grad: 0.0536 (0.0533) time: 0.3808 data: 0.0035 max mem: 3970 +train: [14] [100/400] eta: 0:02:04 lr: 0.000096 loss: 1.6700 (1.6650) grad: 0.0556 (0.0543) time: 0.3775 data: 0.0033 max mem: 3970 +train: [14] [120/400] eta: 0:01:54 lr: 0.000095 loss: 1.6062 (1.6664) grad: 0.0579 (0.0552) time: 0.3754 data: 0.0035 max mem: 3970 +train: [14] [140/400] eta: 0:01:45 lr: 0.000093 loss: 1.6153 (1.6651) grad: 0.0547 (0.0547) time: 0.3697 data: 0.0034 max mem: 3970 +train: [14] [160/400] eta: 0:01:36 lr: 0.000092 loss: 1.6682 (1.6694) grad: 0.0546 (0.0551) time: 0.3859 data: 0.0034 max mem: 3970 +train: [14] [180/400] eta: 0:01:27 lr: 0.000090 loss: 1.6682 (1.6685) grad: 0.0573 (0.0552) time: 0.3751 data: 0.0036 max mem: 3970 +train: [14] [200/400] eta: 0:01:18 lr: 0.000089 loss: 1.6662 (1.6689) grad: 0.0553 (0.0554) time: 0.3527 data: 0.0035 max mem: 3970 +train: [14] [220/400] eta: 0:01:10 lr: 0.000088 loss: 1.6731 (1.6691) grad: 0.0569 (0.0558) time: 0.3539 data: 0.0033 max mem: 3970 +train: [14] [240/400] eta: 0:01:02 lr: 0.000086 loss: 1.6514 (1.6689) grad: 0.0569 (0.0558) time: 0.3885 data: 0.0038 max mem: 3970 +train: [14] [260/400] eta: 0:00:54 lr: 0.000085 loss: 1.6518 (1.6685) grad: 0.0545 (0.0556) time: 0.4080 data: 0.0037 max mem: 3970 +train: [14] [280/400] eta: 0:00:46 lr: 0.000083 loss: 1.6389 (1.6678) grad: 0.0541 (0.0555) time: 0.3637 data: 0.0035 max mem: 3970 +train: [14] [300/400] eta: 0:00:40 lr: 0.000082 loss: 1.6280 (1.6687) grad: 0.0571 (0.0557) time: 0.5718 data: 0.2297 max mem: 3970 +train: [14] [320/400] eta: 0:00:32 lr: 0.000081 loss: 1.7005 (1.6716) grad: 0.0545 (0.0557) time: 0.3736 data: 0.0096 max mem: 3970 +train: [14] [340/400] eta: 0:00:23 lr: 0.000079 loss: 1.6685 (1.6699) grad: 0.0534 (0.0556) time: 0.3569 data: 0.0032 max mem: 3970 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 1.6685 (1.6709) grad: 0.0534 (0.0556) time: 0.3637 data: 0.0033 max mem: 3970 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 1.6704 (1.6712) grad: 0.0559 (0.0558) time: 0.3746 data: 0.0034 max mem: 3970 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 1.6580 (1.6708) grad: 0.0559 (0.0559) time: 0.3574 data: 0.0034 max mem: 3970 +train: [14] Total time: 0:02:37 (0.3930 s / it) +train: [14] Summary: lr: 0.000075 loss: 1.6580 (1.6708) grad: 0.0559 (0.0559) +eval (validation): [14] [ 0/63] eta: 0:03:40 time: 3.5033 data: 3.2006 max mem: 3970 +eval (validation): [14] [20/63] eta: 0:00:23 time: 0.3980 data: 0.0040 max mem: 3970 +eval (validation): [14] [40/63] eta: 0:00:10 time: 0.3454 data: 0.0033 max mem: 3970 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3375 data: 0.0034 max mem: 3970 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3380 data: 0.0034 max mem: 3970 +eval (validation): [14] Total time: 0:00:26 (0.4159 s / it) +cv: [14] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.430 acc: 0.912 f1: 0.906 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [15] [ 0/400] eta: 0:22:58 lr: nan time: 3.4463 data: 3.1645 max mem: 3970 +train: [15] [ 20/400] eta: 0:03:29 lr: 0.000074 loss: 1.6191 (1.6665) grad: 0.0573 (0.0542) time: 0.4067 data: 0.0043 max mem: 3970 +train: [15] [ 40/400] eta: 0:02:49 lr: 0.000072 loss: 1.6896 (1.6985) grad: 0.0583 (0.0571) time: 0.3866 data: 0.0031 max mem: 3970 +train: [15] [ 60/400] eta: 0:02:28 lr: 0.000071 loss: 1.6896 (1.6844) grad: 0.0592 (0.0578) time: 0.3703 data: 0.0034 max mem: 3970 +train: [15] [ 80/400] eta: 0:02:16 lr: 0.000070 loss: 1.6348 (1.6700) grad: 0.0584 (0.0580) time: 0.3868 data: 0.0034 max mem: 3970 +train: [15] [100/400] eta: 0:02:05 lr: 0.000068 loss: 1.6305 (1.6612) grad: 0.0582 (0.0576) time: 0.3854 data: 0.0034 max mem: 3970 +train: [15] [120/400] eta: 0:01:55 lr: 0.000067 loss: 1.6285 (1.6533) grad: 0.0595 (0.0583) time: 0.3806 data: 0.0034 max mem: 3970 +train: [15] [140/400] eta: 0:01:45 lr: 0.000066 loss: 1.6337 (1.6559) grad: 0.0590 (0.0574) time: 0.3721 data: 0.0034 max mem: 3970 +train: [15] [160/400] eta: 0:01:36 lr: 0.000064 loss: 1.6559 (1.6563) grad: 0.0556 (0.0573) time: 0.3852 data: 0.0036 max mem: 3970 +train: [15] [180/400] eta: 0:01:27 lr: 0.000063 loss: 1.6291 (1.6570) grad: 0.0542 (0.0572) time: 0.3665 data: 0.0031 max mem: 3970 +train: [15] [200/400] eta: 0:01:19 lr: 0.000062 loss: 1.6871 (1.6610) grad: 0.0568 (0.0577) time: 0.3826 data: 0.0034 max mem: 3970 +train: [15] [220/400] eta: 0:01:10 lr: 0.000061 loss: 1.6638 (1.6602) grad: 0.0580 (0.0576) time: 0.3601 data: 0.0032 max mem: 3970 +train: [15] [240/400] eta: 0:01:02 lr: 0.000059 loss: 1.6323 (1.6587) grad: 0.0591 (0.0581) time: 0.3871 data: 0.0035 max mem: 3970 +train: [15] [260/400] eta: 0:00:55 lr: 0.000058 loss: 1.6394 (1.6593) grad: 0.0618 (0.0580) time: 0.3854 data: 0.0035 max mem: 3970 +train: [15] [280/400] eta: 0:00:46 lr: 0.000057 loss: 1.6422 (1.6582) grad: 0.0554 (0.0580) time: 0.3607 data: 0.0036 max mem: 3970 +train: [15] [300/400] eta: 0:00:40 lr: 0.000056 loss: 1.6581 (1.6592) grad: 0.0557 (0.0579) time: 0.5475 data: 0.1980 max mem: 3970 +train: [15] [320/400] eta: 0:00:32 lr: 0.000054 loss: 1.6755 (1.6600) grad: 0.0526 (0.0576) time: 0.4099 data: 0.0043 max mem: 3970 +train: [15] [340/400] eta: 0:00:23 lr: 0.000053 loss: 1.6530 (1.6602) grad: 0.0513 (0.0577) time: 0.3722 data: 0.0028 max mem: 3970 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 1.6769 (1.6604) grad: 0.0556 (0.0577) time: 0.3569 data: 0.0035 max mem: 3970 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 1.6769 (1.6610) grad: 0.0543 (0.0576) time: 0.3914 data: 0.0033 max mem: 3970 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 1.6555 (1.6601) grad: 0.0543 (0.0574) time: 0.3567 data: 0.0035 max mem: 3970 +train: [15] Total time: 0:02:38 (0.3955 s / it) +train: [15] Summary: lr: 0.000050 loss: 1.6555 (1.6601) grad: 0.0543 (0.0574) +eval (validation): [15] [ 0/63] eta: 0:03:47 time: 3.6111 data: 3.3301 max mem: 3970 +eval (validation): [15] [20/63] eta: 0:00:22 time: 0.3598 data: 0.0167 max mem: 3970 +eval (validation): [15] [40/63] eta: 0:00:10 time: 0.3594 data: 0.0031 max mem: 3970 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3298 data: 0.0029 max mem: 3970 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3303 data: 0.0032 max mem: 3970 +eval (validation): [15] Total time: 0:00:25 (0.4059 s / it) +cv: [15] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.429 acc: 0.911 f1: 0.903 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:14 lr: nan time: 3.3362 data: 3.1090 max mem: 3970 +train: [16] [ 20/400] eta: 0:03:11 lr: 0.000048 loss: 1.6554 (1.6717) grad: 0.0565 (0.0567) time: 0.3612 data: 0.0034 max mem: 3970 +train: [16] [ 40/400] eta: 0:02:40 lr: 0.000047 loss: 1.6554 (1.6634) grad: 0.0565 (0.0559) time: 0.3863 data: 0.0031 max mem: 3970 +train: [16] [ 60/400] eta: 0:02:22 lr: 0.000046 loss: 1.6350 (1.6537) grad: 0.0570 (0.0573) time: 0.3681 data: 0.0035 max mem: 3970 +train: [16] [ 80/400] eta: 0:02:11 lr: 0.000045 loss: 1.6387 (1.6531) grad: 0.0585 (0.0580) time: 0.3876 data: 0.0035 max mem: 3970 +train: [16] [100/400] eta: 0:02:00 lr: 0.000044 loss: 1.6388 (1.6543) grad: 0.0575 (0.0571) time: 0.3525 data: 0.0036 max mem: 3970 +train: [16] [120/400] eta: 0:01:50 lr: 0.000043 loss: 1.6424 (1.6542) grad: 0.0535 (0.0566) time: 0.3722 data: 0.0034 max mem: 3970 +train: [16] [140/400] eta: 0:01:41 lr: 0.000042 loss: 1.6603 (1.6550) grad: 0.0574 (0.0569) time: 0.3618 data: 0.0034 max mem: 3970 +train: [16] [160/400] eta: 0:01:34 lr: 0.000041 loss: 1.6300 (1.6508) grad: 0.0586 (0.0570) time: 0.4096 data: 0.0032 max mem: 3970 +train: [16] [180/400] eta: 0:01:25 lr: 0.000040 loss: 1.6195 (1.6477) grad: 0.0571 (0.0569) time: 0.3713 data: 0.0033 max mem: 3970 +train: [16] [200/400] eta: 0:01:17 lr: 0.000039 loss: 1.6445 (1.6498) grad: 0.0575 (0.0571) time: 0.3634 data: 0.0032 max mem: 3970 +train: [16] [220/400] eta: 0:01:09 lr: 0.000038 loss: 1.6428 (1.6450) grad: 0.0560 (0.0569) time: 0.3550 data: 0.0032 max mem: 3970 +train: [16] [240/400] eta: 0:01:01 lr: 0.000036 loss: 1.6475 (1.6503) grad: 0.0531 (0.0570) time: 0.3826 data: 0.0034 max mem: 3970 +train: [16] [260/400] eta: 0:00:53 lr: 0.000035 loss: 1.6920 (1.6477) grad: 0.0558 (0.0572) time: 0.3713 data: 0.0035 max mem: 3970 +train: [16] [280/400] eta: 0:00:45 lr: 0.000034 loss: 1.6223 (1.6488) grad: 0.0558 (0.0570) time: 0.3704 data: 0.0033 max mem: 3970 +train: [16] [300/400] eta: 0:00:39 lr: 0.000033 loss: 1.6323 (1.6494) grad: 0.0512 (0.0567) time: 0.5589 data: 0.1968 max mem: 3970 +train: [16] [320/400] eta: 0:00:31 lr: 0.000032 loss: 1.6617 (1.6517) grad: 0.0540 (0.0570) time: 0.3623 data: 0.0034 max mem: 3970 +train: [16] [340/400] eta: 0:00:23 lr: 0.000031 loss: 1.6638 (1.6525) grad: 0.0540 (0.0567) time: 0.3633 data: 0.0031 max mem: 3970 +train: [16] [360/400] eta: 0:00:15 lr: 0.000031 loss: 1.6601 (1.6518) grad: 0.0528 (0.0566) time: 0.3641 data: 0.0037 max mem: 3970 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 1.6248 (1.6501) grad: 0.0505 (0.0563) time: 0.3660 data: 0.0033 max mem: 3970 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 1.6176 (1.6490) grad: 0.0508 (0.0562) time: 0.3525 data: 0.0033 max mem: 3970 +train: [16] Total time: 0:02:34 (0.3867 s / it) +train: [16] Summary: lr: 0.000029 loss: 1.6176 (1.6490) grad: 0.0508 (0.0562) +eval (validation): [16] [ 0/63] eta: 0:03:33 time: 3.3932 data: 3.1549 max mem: 3970 +eval (validation): [16] [20/63] eta: 0:00:21 time: 0.3610 data: 0.0042 max mem: 3970 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3571 data: 0.0031 max mem: 3970 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3282 data: 0.0034 max mem: 3970 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3267 data: 0.0034 max mem: 3970 +eval (validation): [16] Total time: 0:00:25 (0.4017 s / it) +cv: [16] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.421 acc: 0.913 f1: 0.905 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [17] [ 0/400] eta: 0:21:45 lr: nan time: 3.2644 data: 3.0406 max mem: 3970 +train: [17] [ 20/400] eta: 0:03:29 lr: 0.000028 loss: 1.6045 (1.6219) grad: 0.0537 (0.0585) time: 0.4152 data: 0.0030 max mem: 3970 +train: [17] [ 40/400] eta: 0:02:45 lr: 0.000027 loss: 1.6045 (1.6246) grad: 0.0537 (0.0578) time: 0.3638 data: 0.0035 max mem: 3970 +train: [17] [ 60/400] eta: 0:02:25 lr: 0.000026 loss: 1.6294 (1.6327) grad: 0.0530 (0.0561) time: 0.3591 data: 0.0035 max mem: 3970 +train: [17] [ 80/400] eta: 0:02:11 lr: 0.000025 loss: 1.6450 (1.6357) grad: 0.0530 (0.0556) time: 0.3579 data: 0.0036 max mem: 3970 +train: [17] [100/400] eta: 0:02:00 lr: 0.000024 loss: 1.6410 (1.6401) grad: 0.0530 (0.0555) time: 0.3750 data: 0.0032 max mem: 3970 +train: [17] [120/400] eta: 0:01:51 lr: 0.000023 loss: 1.6410 (1.6418) grad: 0.0582 (0.0562) time: 0.3657 data: 0.0034 max mem: 3970 +train: [17] [140/400] eta: 0:01:41 lr: 0.000023 loss: 1.6345 (1.6431) grad: 0.0572 (0.0562) time: 0.3599 data: 0.0035 max mem: 3970 +train: [17] [160/400] eta: 0:01:33 lr: 0.000022 loss: 1.6376 (1.6438) grad: 0.0541 (0.0558) time: 0.3809 data: 0.0032 max mem: 3970 +train: [17] [180/400] eta: 0:01:25 lr: 0.000021 loss: 1.6423 (1.6455) grad: 0.0542 (0.0561) time: 0.3669 data: 0.0035 max mem: 3970 +train: [17] [200/400] eta: 0:01:16 lr: 0.000020 loss: 1.6677 (1.6517) grad: 0.0577 (0.0564) time: 0.3530 data: 0.0034 max mem: 3970 +train: [17] [220/400] eta: 0:01:08 lr: 0.000019 loss: 1.6593 (1.6497) grad: 0.0569 (0.0564) time: 0.3589 data: 0.0033 max mem: 3970 +train: [17] [240/400] eta: 0:01:00 lr: 0.000019 loss: 1.6159 (1.6492) grad: 0.0569 (0.0566) time: 0.3677 data: 0.0033 max mem: 3970 +train: [17] [260/400] eta: 0:00:53 lr: 0.000018 loss: 1.6291 (1.6505) grad: 0.0589 (0.0568) time: 0.3592 data: 0.0034 max mem: 3970 +train: [17] [280/400] eta: 0:00:45 lr: 0.000017 loss: 1.6324 (1.6497) grad: 0.0589 (0.0569) time: 0.3653 data: 0.0034 max mem: 3970 +train: [17] [300/400] eta: 0:00:38 lr: 0.000016 loss: 1.6324 (1.6499) grad: 0.0570 (0.0568) time: 0.5222 data: 0.1897 max mem: 3970 +train: [17] [320/400] eta: 0:00:31 lr: 0.000016 loss: 1.6778 (1.6516) grad: 0.0548 (0.0568) time: 0.3948 data: 0.0165 max mem: 3970 +train: [17] [340/400] eta: 0:00:23 lr: 0.000015 loss: 1.6552 (1.6516) grad: 0.0552 (0.0568) time: 0.3665 data: 0.0023 max mem: 3970 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 1.6469 (1.6515) grad: 0.0554 (0.0568) time: 0.3826 data: 0.0034 max mem: 3970 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 1.6540 (1.6521) grad: 0.0524 (0.0567) time: 0.3565 data: 0.0035 max mem: 3970 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 1.6540 (1.6511) grad: 0.0562 (0.0569) time: 0.3616 data: 0.0031 max mem: 3970 +train: [17] Total time: 0:02:33 (0.3841 s / it) +train: [17] Summary: lr: 0.000013 loss: 1.6540 (1.6511) grad: 0.0562 (0.0569) +eval (validation): [17] [ 0/63] eta: 0:04:11 time: 3.9880 data: 3.6889 max mem: 3970 +eval (validation): [17] [20/63] eta: 0:00:24 time: 0.3873 data: 0.0028 max mem: 3970 +eval (validation): [17] [40/63] eta: 0:00:10 time: 0.3615 data: 0.0034 max mem: 3970 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3361 data: 0.0033 max mem: 3970 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3294 data: 0.0033 max mem: 3970 +eval (validation): [17] Total time: 0:00:26 (0.4238 s / it) +cv: [17] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.417 acc: 0.917 f1: 0.910 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:22:48 lr: nan time: 3.4213 data: 3.1445 max mem: 3970 +train: [18] [ 20/400] eta: 0:03:12 lr: 0.000012 loss: 1.6729 (1.6830) grad: 0.0553 (0.0554) time: 0.3617 data: 0.0043 max mem: 3970 +train: [18] [ 40/400] eta: 0:02:42 lr: 0.000012 loss: 1.6616 (1.6649) grad: 0.0561 (0.0571) time: 0.3954 data: 0.0029 max mem: 3970 +train: [18] [ 60/400] eta: 0:02:24 lr: 0.000011 loss: 1.6557 (1.6608) grad: 0.0559 (0.0567) time: 0.3726 data: 0.0037 max mem: 3970 +train: [18] [ 80/400] eta: 0:02:12 lr: 0.000011 loss: 1.6557 (1.6570) grad: 0.0541 (0.0566) time: 0.3744 data: 0.0036 max mem: 3970 +train: [18] [100/400] eta: 0:02:01 lr: 0.000010 loss: 1.6136 (1.6492) grad: 0.0553 (0.0564) time: 0.3761 data: 0.0034 max mem: 3970 +train: [18] [120/400] eta: 0:01:52 lr: 0.000009 loss: 1.6151 (1.6476) grad: 0.0526 (0.0561) time: 0.3692 data: 0.0034 max mem: 3970 +train: [18] [140/400] eta: 0:01:43 lr: 0.000009 loss: 1.6277 (1.6464) grad: 0.0518 (0.0558) time: 0.3729 data: 0.0033 max mem: 3970 +train: [18] [160/400] eta: 0:01:35 lr: 0.000008 loss: 1.6265 (1.6438) grad: 0.0571 (0.0563) time: 0.3964 data: 0.0034 max mem: 3970 +train: [18] [180/400] eta: 0:01:27 lr: 0.000008 loss: 1.6265 (1.6434) grad: 0.0571 (0.0562) time: 0.3948 data: 0.0034 max mem: 3970 +train: [18] [200/400] eta: 0:01:18 lr: 0.000007 loss: 1.6689 (1.6467) grad: 0.0558 (0.0564) time: 0.3523 data: 0.0034 max mem: 3970 +train: [18] [220/400] eta: 0:01:10 lr: 0.000007 loss: 1.6615 (1.6440) grad: 0.0552 (0.0562) time: 0.3801 data: 0.0031 max mem: 3970 +train: [18] [240/400] eta: 0:01:02 lr: 0.000006 loss: 1.6403 (1.6464) grad: 0.0509 (0.0556) time: 0.3734 data: 0.0033 max mem: 3970 +train: [18] [260/400] eta: 0:00:54 lr: 0.000006 loss: 1.6431 (1.6465) grad: 0.0509 (0.0557) time: 0.3728 data: 0.0034 max mem: 3970 +train: [18] [280/400] eta: 0:00:46 lr: 0.000006 loss: 1.6278 (1.6428) grad: 0.0572 (0.0560) time: 0.3783 data: 0.0036 max mem: 3970 +train: [18] [300/400] eta: 0:00:39 lr: 0.000005 loss: 1.6230 (1.6449) grad: 0.0577 (0.0559) time: 0.5602 data: 0.1882 max mem: 3970 +train: [18] [320/400] eta: 0:00:31 lr: 0.000005 loss: 1.6520 (1.6440) grad: 0.0595 (0.0561) time: 0.3687 data: 0.0031 max mem: 3970 +train: [18] [340/400] eta: 0:00:23 lr: 0.000004 loss: 1.6225 (1.6440) grad: 0.0636 (0.0566) time: 0.3573 data: 0.0030 max mem: 3970 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 1.6056 (1.6428) grad: 0.0639 (0.0568) time: 0.3674 data: 0.0033 max mem: 3970 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 1.5955 (1.6415) grad: 0.0542 (0.0567) time: 0.3633 data: 0.0034 max mem: 3970 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 1.6295 (1.6413) grad: 0.0542 (0.0566) time: 0.3393 data: 0.0032 max mem: 3970 +train: [18] Total time: 0:02:35 (0.3893 s / it) +train: [18] Summary: lr: 0.000003 loss: 1.6295 (1.6413) grad: 0.0542 (0.0566) +eval (validation): [18] [ 0/63] eta: 0:03:40 time: 3.4935 data: 3.2538 max mem: 3970 +eval (validation): [18] [20/63] eta: 0:00:21 time: 0.3604 data: 0.0042 max mem: 3970 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3375 data: 0.0028 max mem: 3970 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3379 data: 0.0034 max mem: 3970 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3374 data: 0.0034 max mem: 3970 +eval (validation): [18] Total time: 0:00:25 (0.3989 s / it) +cv: [18] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.417 acc: 0.919 f1: 0.911 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +train: [19] [ 0/400] eta: 0:22:22 lr: nan time: 3.3560 data: 3.0895 max mem: 3970 +train: [19] [ 20/400] eta: 0:03:11 lr: 0.000003 loss: 1.6263 (1.6618) grad: 0.0489 (0.0509) time: 0.3603 data: 0.0108 max mem: 3970 +train: [19] [ 40/400] eta: 0:02:36 lr: 0.000003 loss: 1.6263 (1.6332) grad: 0.0519 (0.0553) time: 0.3639 data: 0.0037 max mem: 3970 +train: [19] [ 60/400] eta: 0:02:18 lr: 0.000002 loss: 1.6381 (1.6431) grad: 0.0565 (0.0551) time: 0.3504 data: 0.0031 max mem: 3970 +train: [19] [ 80/400] eta: 0:02:05 lr: 0.000002 loss: 1.6464 (1.6381) grad: 0.0555 (0.0545) time: 0.3513 data: 0.0036 max mem: 3970 +train: [19] [100/400] eta: 0:01:55 lr: 0.000002 loss: 1.6173 (1.6361) grad: 0.0512 (0.0544) time: 0.3576 data: 0.0032 max mem: 3970 +train: [19] [120/400] eta: 0:01:47 lr: 0.000002 loss: 1.6173 (1.6385) grad: 0.0547 (0.0550) time: 0.3637 data: 0.0036 max mem: 3970 +train: [19] [140/400] eta: 0:01:38 lr: 0.000001 loss: 1.6217 (1.6347) grad: 0.0597 (0.0556) time: 0.3562 data: 0.0031 max mem: 3970 +train: [19] [160/400] eta: 0:01:30 lr: 0.000001 loss: 1.6217 (1.6334) grad: 0.0597 (0.0558) time: 0.3694 data: 0.0034 max mem: 3970 +train: [19] [180/400] eta: 0:01:22 lr: 0.000001 loss: 1.6377 (1.6370) grad: 0.0557 (0.0562) time: 0.3554 data: 0.0034 max mem: 3970 +train: [19] [200/400] eta: 0:01:14 lr: 0.000001 loss: 1.6640 (1.6375) grad: 0.0557 (0.0558) time: 0.3541 data: 0.0034 max mem: 3970 +train: [19] [220/400] eta: 0:01:06 lr: 0.000001 loss: 1.6260 (1.6358) grad: 0.0553 (0.0561) time: 0.3552 data: 0.0033 max mem: 3970 +train: [19] [240/400] eta: 0:00:59 lr: 0.000001 loss: 1.6068 (1.6336) grad: 0.0535 (0.0557) time: 0.3841 data: 0.0034 max mem: 3970 +train: [19] [260/400] eta: 0:00:52 lr: 0.000000 loss: 1.5838 (1.6321) grad: 0.0536 (0.0560) time: 0.3669 data: 0.0034 max mem: 3970 +train: [19] [280/400] eta: 0:00:44 lr: 0.000000 loss: 1.5841 (1.6324) grad: 0.0567 (0.0561) time: 0.3568 data: 0.0036 max mem: 3970 +train: [19] [300/400] eta: 0:00:38 lr: 0.000000 loss: 1.6061 (1.6313) grad: 0.0572 (0.0560) time: 0.5280 data: 0.1841 max mem: 3970 +train: [19] [320/400] eta: 0:00:30 lr: 0.000000 loss: 1.6213 (1.6316) grad: 0.0518 (0.0558) time: 0.3839 data: 0.0172 max mem: 3970 +train: [19] [340/400] eta: 0:00:22 lr: 0.000000 loss: 1.6458 (1.6335) grad: 0.0556 (0.0561) time: 0.3539 data: 0.0025 max mem: 3970 +train: [19] [360/400] eta: 0:00:15 lr: 0.000000 loss: 1.6365 (1.6333) grad: 0.0565 (0.0561) time: 0.3638 data: 0.0033 max mem: 3970 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 1.6298 (1.6334) grad: 0.0521 (0.0561) time: 0.3545 data: 0.0033 max mem: 3970 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 1.6910 (1.6373) grad: 0.0522 (0.0562) time: 0.3536 data: 0.0034 max mem: 3970 +train: [19] Total time: 0:02:30 (0.3769 s / it) +train: [19] Summary: lr: 0.000000 loss: 1.6910 (1.6373) grad: 0.0522 (0.0562) +eval (validation): [19] [ 0/63] eta: 0:03:35 time: 3.4194 data: 3.1315 max mem: 3970 +eval (validation): [19] [20/63] eta: 0:00:24 time: 0.4208 data: 0.0043 max mem: 3970 +eval (validation): [19] [40/63] eta: 0:00:10 time: 0.3485 data: 0.0037 max mem: 3970 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3394 data: 0.0034 max mem: 3970 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3366 data: 0.0033 max mem: 3970 +eval (validation): [19] Total time: 0:00:26 (0.4208 s / it) +cv: [19] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.416 acc: 0.917 f1: 0.909 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-last.pth +eval model info: +{"score": 0.9169146825396826, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 19, "is_best": false, "best_score": 0.9188988095238095} +eval (train): [20] [ 0/297] eta: 0:16:36 time: 3.3559 data: 3.0861 max mem: 3970 +eval (train): [20] [ 20/297] eta: 0:02:24 time: 0.3806 data: 0.0079 max mem: 3970 +eval (train): [20] [ 40/297] eta: 0:01:53 time: 0.3536 data: 0.0031 max mem: 3970 +eval (train): [20] [ 60/297] eta: 0:01:38 time: 0.3595 data: 0.0036 max mem: 3970 +eval (train): [20] [ 80/297] eta: 0:01:26 time: 0.3486 data: 0.0036 max mem: 3970 +eval (train): [20] [100/297] eta: 0:01:16 time: 0.3571 data: 0.0036 max mem: 3970 +eval (train): [20] [120/297] eta: 0:01:07 time: 0.3494 data: 0.0033 max mem: 3970 +eval (train): [20] [140/297] eta: 0:00:59 time: 0.3497 data: 0.0034 max mem: 3970 +eval (train): [20] [160/297] eta: 0:00:51 time: 0.3548 data: 0.0038 max mem: 3970 +eval (train): [20] [180/297] eta: 0:00:43 time: 0.3483 data: 0.0032 max mem: 3970 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3523 data: 0.0038 max mem: 3970 +eval (train): [20] [220/297] eta: 0:00:28 time: 0.3331 data: 0.0033 max mem: 3970 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3411 data: 0.0035 max mem: 3970 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3731 data: 0.0039 max mem: 3970 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3764 data: 0.0041 max mem: 3970 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3464 data: 0.0033 max mem: 3970 +eval (train): [20] Total time: 0:01:48 (0.3667 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:29 time: 3.3224 data: 3.0319 max mem: 3970 +eval (validation): [20] [20/63] eta: 0:00:23 time: 0.4018 data: 0.0047 max mem: 3970 +eval (validation): [20] [40/63] eta: 0:00:10 time: 0.3551 data: 0.0033 max mem: 3970 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3500 data: 0.0034 max mem: 3970 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3440 data: 0.0034 max mem: 3970 +eval (validation): [20] Total time: 0:00:26 (0.4208 s / it) +eval (test): [20] [ 0/79] eta: 0:04:23 time: 3.3301 data: 3.0536 max mem: 3970 +eval (test): [20] [20/79] eta: 0:00:32 time: 0.4153 data: 0.0040 max mem: 3970 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3292 data: 0.0032 max mem: 3970 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3310 data: 0.0032 max mem: 3970 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3303 data: 0.0035 max mem: 3970 +eval (test): [20] Total time: 0:00:31 (0.3959 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/checkpoint-best.pth +eval model info: +{"score": 0.9188988095238095, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 18, "is_best": true, "best_score": 0.9188988095238095} +eval (train): [20] [ 0/297] eta: 0:17:03 time: 3.4451 data: 3.1666 max mem: 3970 +eval (train): [20] [ 20/297] eta: 0:02:19 time: 0.3557 data: 0.0052 max mem: 3970 +eval (train): [20] [ 40/297] eta: 0:01:48 time: 0.3370 data: 0.0036 max mem: 3970 +eval (train): [20] [ 60/297] eta: 0:01:34 time: 0.3460 data: 0.0035 max mem: 3970 +eval (train): [20] [ 80/297] eta: 0:01:23 time: 0.3465 data: 0.0036 max mem: 3970 +eval (train): [20] [100/297] eta: 0:01:14 time: 0.3625 data: 0.0035 max mem: 3970 +eval (train): [20] [120/297] eta: 0:01:06 time: 0.3423 data: 0.0034 max mem: 3970 +eval (train): [20] [140/297] eta: 0:00:58 time: 0.3509 data: 0.0035 max mem: 3970 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3481 data: 0.0037 max mem: 3970 +eval (train): [20] [180/297] eta: 0:00:42 time: 0.3473 data: 0.0035 max mem: 3970 +eval (train): [20] [200/297] eta: 0:00:35 time: 0.3494 data: 0.0035 max mem: 3970 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3386 data: 0.0036 max mem: 3970 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3449 data: 0.0034 max mem: 3970 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3448 data: 0.0036 max mem: 3970 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3267 data: 0.0036 max mem: 3970 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3191 data: 0.0033 max mem: 3970 +eval (train): [20] Total time: 0:01:45 (0.3565 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:32 time: 3.3692 data: 3.0931 max mem: 3970 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3336 data: 0.0048 max mem: 3970 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3380 data: 0.0036 max mem: 3970 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3311 data: 0.0027 max mem: 3970 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3291 data: 0.0030 max mem: 3970 +eval (validation): [20] Total time: 0:00:24 (0.3865 s / it) +eval (test): [20] [ 0/79] eta: 0:04:26 time: 3.3706 data: 3.0980 max mem: 3970 +eval (test): [20] [20/79] eta: 0:00:28 time: 0.3390 data: 0.0032 max mem: 3970 +eval (test): [20] [40/79] eta: 0:00:15 time: 0.3223 data: 0.0033 max mem: 3970 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3221 data: 0.0035 max mem: 3970 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.2998 data: 0.0032 max mem: 3970 +eval (test): [20] Total time: 0:00:28 (0.3634 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|--------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | linear | hcpya_task21 | best | 18 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 0.39686 | 0.92463 | 0.0018355 | 0.91772 | 0.0022977 | +| flat_mae | patch | linear | hcpya_task21 | best | 18 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 0.41693 | 0.9189 | 0.003987 | 0.91146 | 0.004769 | +| flat_mae | patch | linear | hcpya_task21 | best | 18 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 0.43363 | 0.90456 | 0.0038834 | 0.89259 | 0.004875 | + + +done! total time: 1:06:47 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/train_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..f87e803401bc07c52237a3fb3c5bc4dc02f10a38 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__patch__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.9405845308303835, "train/grad": 0.1193541955947876, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.0408154296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.040626220703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.040291748046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0399658203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.039600830078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.039171142578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.0386376953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.03802001953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.03726806640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.03642822265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.035548095703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.034324951171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0329736328125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.031239013671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.029385986328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0275439453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.025223388671875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.02228759765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.01893798828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.015697021484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.011435546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.006939697265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.00169677734375, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.995860595703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.989486083984375, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.9816064453125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.97457763671875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.968013916015625, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9590966796875, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.9488323974609374, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.9398388671875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.9319183349609377, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9216766357421875, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.912645263671875, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.9022186279296873, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.891781005859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.8804010009765624, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.8692523193359376, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.8563421630859374, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.8389129638671875, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.8243011474609374, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.8103369140625, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.790487060546875, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.7717401123046876, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7479168701171877, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.7198858642578125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.693445129394531, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.658524475097656, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.6254873657226563, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019688580427318813, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01968220961280167, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019672493920661508, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019661707687191665, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.019651309703476727, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019636698942631484, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.019620281890966, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.019601092576049268, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.019574339506216346, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.019545806827954947, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01951822134666145, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.019475998454727233, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.019434323292225598, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.019372885352931916, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019313301327638328, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.019254263760522007, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01917418268043548, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01907562255859375, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.018960330137051642, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01884673242457211, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.018698911792598666, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0185385660873726, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.018344699619337917, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.018126863758079707, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.017885597865097226, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01758097046520561, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.017292385110631584, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01702068854589015, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.016642824872396888, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01619546287227422, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.015805588176008314, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0154671551566571, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.015048485707957297, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014709337286185474, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014345976659096777, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.014023641431704164, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01371807896066457, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.013455928207840771, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01320073209470138, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.012924526163842529, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.012734613344073296, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012582750674337149, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012404156376142055, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01226939940592274, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012135112339165062, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012024890738539398, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011958500661421567, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011901899226941168, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011856357522774488, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0373332500457764, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.036774158477783, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0357868671417236, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.034691333770752, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.033738613128662, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.032271146774292, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.030691623687744, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.028825044631958, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.026420831680298, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.023925542831421, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.021419048309326, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.0176033973693848, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.013843297958374, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0083401203155518, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.003049850463867, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.997799873352051, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.9910876750946045, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9830336570739746, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.973788261413574, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.964996337890625, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.954043388366699, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.942579507827759, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.929750442504883, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.915959119796753, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.90183424949646, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8855154514312744, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.871507167816162, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.859529972076416, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.8444602489471436, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.8285324573516846, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.815952777862549, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.805539846420288, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.79219651222229, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.780259370803833, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7653391361236572, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7491488456726074, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.7298505306243896, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.709024667739868, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6834499835968018, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6465091705322266, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.613612651824951, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5812175273895264, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5337722301483154, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4878697395324707, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.4293127059936523, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.360607862472534, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.297482490539551, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.2179465293884277, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.1467742919921875, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.015625, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.015376984126984126, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.013640873015873016, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.011656746031746032, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.011408730158730158, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.01066468253968254, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.011160714285714286, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.014384920634920634, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.01984126984126984, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.031994047619047616, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.03943452380952381, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05828373015873016, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0716765873015873, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0798611111111111, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08531746031746032, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08680555555555555, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08705357142857142, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.08705357142857142, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.08680555555555555, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.08705357142857142, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08630952380952381, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08953373015873016, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.09895833333333333, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.13864087301587302, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.16989087301587302, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.17162698412698413, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.1765873015873016, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18452380952380953, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19593253968253968, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20858134920634921, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.2390873015873016, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.27976190476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.3318452380952381, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.39112103174603174, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.43154761904761907, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0018072271942697583, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00200539401294077, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.001926995592298095, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0017775977601535947, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0017648349973769383, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.001787567747101775, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0019314089158410394, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0024386531729655896, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0029543054407756434, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00419820242480341, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004605781853727455, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006124043508861411, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0070672046400201746, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0071584189231248055, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007526281819872448, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007627765064836004, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007630351844001696, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00762861054965117, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0076103500761035, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007751057394085213, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007701128236842522, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010676527596751795, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.018017386486580075, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.020598137584732754, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014739741355195488, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.015295782757869717, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02129235738619805, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.028116402229941485, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03854523844967733, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0523001123949488, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.08311394371290766, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.11521967187751836, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.15179416537059043, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.18735931927709396, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.2345003920877604, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.6254873657226563, "validation/loss_best": 2.1467742919921875, "validation/acc_best": 0.43154761904761907, "validation/f1_best": 0.2345003920877604} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.7053820085525513, "train/grad": 0.09974536869674921, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.031419677734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.029920654296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.02778564453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.025501708984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.023270263671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.020216064453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.016776123046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.012923583984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.0079345703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.002752685546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.997734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.99024658203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.983175048828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.97302734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.96361083984375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.95475341796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.943992919921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.931629638671875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.918419189453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.90672119140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.893076171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.8798699951171876, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8661785888671876, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.852640380859375, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.8396783447265626, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8249365234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.8123828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.8011993408203124, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.78580078125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.767027587890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.74925537109375, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7321588134765626, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.70717529296875, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.6827838134765627, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.651015625, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.61633056640625, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.5751885986328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.531999206542969, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.4801739501953124, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4087820434570313, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.348134002685547, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.291273345947266, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2123655700683593, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.140582733154297, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.054152603149414, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.9590351104736328, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.875431365966797, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.774392375946045, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.6888884544372558, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.019582378957420588, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.019536226419731975, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.019461489715613425, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.019387594261206686, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01931579813826829, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.019217025162652134, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01910576405003667, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01898207145743072, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01881804207805544, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.018641928429715335, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01847276990301907, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01821205986198038, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.017961360421031712, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.017596058901399373, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.017245272640138865, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.016908015571534634, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.016477420744486153, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015969665804877877, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015400342871434986, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.014873337161261588, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.014232729461509734, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.013597565430682152, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.012941017933189868, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.012316885327454657, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011762288657482713, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011234333992470057, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010874939316418022, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010626507299020886, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010389320175163448, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010221941203344614, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010140763493254781, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0101008211215958, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010073710542637854, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010061656408943236, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010052075888961554, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010042529124766587, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01002940661739558, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010014893591869623, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009994716842193156, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009964896966703236, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009939617174677551, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009915844642091543, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009889347886200994, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009873194009996951, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009858144600875675, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009828579924069346, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009773359978571533, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009709377146791667, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009684358327649533, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0250356197357178, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0226893424987793, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.018826961517334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.014977216720581, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.0112383365631104, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.006011962890625, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.000300645828247, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.994105100631714, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.986081838607788, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.9778220653533936, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9699220657348633, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9584357738494873, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.947798490524292, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9331183433532715, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.919877529144287, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.907867431640625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8936028480529785, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.878247022628784, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.862623929977417, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8496525287628174, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.8353984355926514, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.822474956512451, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.8097519874572754, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.7973341941833496, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.784700632095337, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.769177198410034, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.754166841506958, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7393858432769775, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.717557430267334, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6889638900756836, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.660987615585327, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.633491039276123, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5933666229248047, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5543932914733887, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5042591094970703, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4499974250793457, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.3869130611419678, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.321850299835205, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.245900869369507, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.1448802947998047, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.0622966289520264, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.9869529008865356, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.8857426643371582, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.7968683242797852, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.6946803331375122, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.5896059274673462, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.503962516784668, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.4072422981262207, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.3294094800949097, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.022569444444444444, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.033234126984126984, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04836309523809524, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0642361111111111, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07490079365079365, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08060515873015874, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08531746031746032, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08680555555555555, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.08705357142857142, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.08680555555555555, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.08655753968253968, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.08705357142857142, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0882936507936508, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.10987103174603174, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15550595238095238, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17038690476190477, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.17137896825396826, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.17807539682539683, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.19469246031746032, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2390873015873016, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2837301587301587, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.32936507936507936, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.36929563492063494, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.39632936507936506, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.42782738095238093, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.46651785714285715, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.5101686507936508, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.5622519841269841, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.6304563492063492, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.6741071428571429, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.6922123015873016, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.6902281746031746, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.003237790793668626, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004263419474396685, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005335487361724862, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006619169952141374, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007339674854200107, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007209965281244107, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007524553229651989, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0076207895137936285, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00762861054965117, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0076103500761035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007715223941599408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008233154372860254, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011699474673810785, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.019984463848693616, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.018866706406209792, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014298201798201798, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.015148867478402259, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.02409499651687236, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.04214048953963315, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.08517400180237747, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.11913794694107224, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1594071562421771, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19568935161703588, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21917971794478802, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2567082935931256, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.3092638912126903, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.3697973710510207, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.444037027370215, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.5453003319310901, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.6021639269450889, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.6277765619698644, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.624477313341175, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 1.774392375946045, "validation/loss_best": 1.4072422981262207, "validation/acc_best": 0.6922123015873016, "validation/f1_best": 0.6277765619698644} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 2.483253399133682, "train/grad": 0.08816154537722469, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.018514404296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.014888916015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.0090576171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.00340087890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.99781494140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.99042724609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.982347412109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.97365234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.96278564453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9518310546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.941722412109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.9275048828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.914693603515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.89799560546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8836767578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.871280517578125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.85727783203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8428558349609374, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.828836669921875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.8172406005859374, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8040087890625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.7910894775390624, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.7766876220703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.7605706787109376, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.742720947265625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.7194903564453123, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.696678466796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.67429443359375, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.6413818359375, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.598673095703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5574920654296873, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.517500915527344, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.460077209472656, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4055328369140625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3366629028320314, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2645809936523436, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.183310699462891, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.102492218017578, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0114893341064453, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8953975677490233, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8047292709350586, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7254681777954102, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.6237516403198242, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.538423900604248, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.4436613655090331, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3478273391723632, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.269951992034912, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.1829686546325684, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.1146993589401246, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.018990253009833397, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.018878613454289733, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01868997804354876, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.018501183958724143, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.018315173992887138, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0180626260349527, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01777640308253467, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.017467077565379442, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.017071129051037134, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01665984948631376, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01626653236337006, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01569275419227779, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.015152325942181051, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.014405704727396369, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013730957196094096, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013126371945254504, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012430336941033602, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.011730569908395409, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011103853697422892, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010665927107911557, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010295597293879837, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010061671652365475, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009919322188943624, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009846926676109433, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0098147008754313, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009796605920419097, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009783310466445982, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009772217336576431, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009754908601753414, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009732098374515772, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009708947597537189, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009686858903151005, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009652141553815455, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009616834654007107, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00957034390885383, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00951961608370766, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00945836554048583, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009395445343106984, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009320835932157934, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009224926398601382, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009153089814353733, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009091879951301961, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009018945980351419, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008962847129441797, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008900271840393542, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008836522626224905, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00880836038151756, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.008808045545592905, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008818288201000541, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.005748987197876, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.00089430809021, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.993054151535034, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.985522508621216, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9783313274383545, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9687135219573975, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.95832896232605, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.947551727294922, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9341609477996826, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.921119213104248, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.909315824508667, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.893162488937378, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.8793063163757324, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8617727756500244, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8475050926208496, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8356852531433105, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8227624893188477, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.8097116947174072, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7967042922973633, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.785263776779175, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7710869312286377, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.7557642459869385, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.7374022006988525, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.716094970703125, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.6918303966522217, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6601595878601074, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.629155397415161, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5988223552703857, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5546655654907227, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4979770183563232, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4438719749450684, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.392235279083252, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.319119691848755, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.2510855197906494, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.167238712310791, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.0813405513763428, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.9866325855255127, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.894691824913025, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.7945252656936646, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.6721235513687134, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.5800697803497314, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.5015804767608643, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.4036378860473633, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.3247077465057373, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.241363525390625, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.157979130744934, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.0915074348449707, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0205072164535522, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.9643768072128296, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.08258928571428571, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.08556547619047619, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.08705357142857142, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.08705357142857142, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08680555555555555, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.08705357142857142, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08655753968253968, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08754960317460317, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09623015873015874, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.12276785714285714, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.16344246031746032, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.17063492063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.17410714285714285, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.18601190476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21478174603174602, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25322420634920634, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.31274801587301587, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.3551587301587302, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.40228174603174605, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.45287698412698413, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.5012400793650794, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5409226190476191, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.5751488095238095, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.621031746031746, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.6557539682539683, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.6850198412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7150297619047619, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.734375, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7430555555555556, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7566964285714286, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7604166666666666, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7628968253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.7604166666666666, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0073480736131338546, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.007542962088416634, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007632093933463797, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00762861054965117, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007608612949859241, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007751057394085213, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007719844638227552, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008827791048912752, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0166439337611441, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02087273615251035, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.017739214830171886, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013902781566689906, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013882163034705408, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01831726499723379, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.03304564928522301, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0645935190297181, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0957047553153338, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.137982431448741, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17494596433278856, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.21829436130578994, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.27914507439755115, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.33434600779232854, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.3887703901300272, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.4422860000739631, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.5114984011724572, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.5560851358435671, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.5967839344404166, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.6414427369161874, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.6691643078413769, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.6773566854321322, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.6909650840215493, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.6902494778737133, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.692184054165787, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.6891507820126899, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 1.1829686546325684, "validation/loss_best": 1.0205072164535522, "validation/acc_best": 0.7628968253968254, "validation/f1_best": 0.692184054165787} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 2.3018914914131163, "train/grad": 0.08237766105681658, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.994691162109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.988472900390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.97857177734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.969212646484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.96038818359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.948873291015625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.936829833984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.924388427734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.9094873046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.895413818359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.88314453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.866944580078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.8534088134765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.8370269775390624, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8239520263671873, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8131329345703127, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.8007470703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7871820068359376, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7723193359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.758089599609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.739609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.719217529296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.6946649169921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.666259765625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.634007568359375, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5923345947265624, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.5518228149414064, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.5125961303710938, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.456040954589844, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3846160888671877, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.317596435546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2546322631835936, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1673619079589845, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0875811767578125, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9918739318847656, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.896300277709961, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.7946092987060547, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.6990613174438476, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.597926368713379, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.4776368141174316, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.3897614860534668, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.3168582344055175, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.2277331352233887, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.1563292026519776, "train/loss_044_lr2.6e+01_wd1.0e+00": 1.0801648569107056, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0067152976989746, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.9500370979309082, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.8878033375740051, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.8392564368247986, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.018562144082970918, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.018349533709697427, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.018005195786245168, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.017674952559173108, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.017357349693775177, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.016924107274971904, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01645855173934251, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01595918645616621, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015333311692811548, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.014703486380167306, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.014125203769654036, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013330541632603854, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012649585127364844, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011836636727675796, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011246636707801372, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010838727781083435, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010500000561587513, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010278038231190294, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010160215434152632, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010110093583352863, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010081006686668843, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010060250347014516, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010042783692479134, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010022710170596838, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00999913090839982, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009966637738980353, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009934031327720732, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009899690689053386, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00984807375119999, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009781277847941965, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009716653963550925, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009653648191597313, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009564400597009809, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009476754567585885, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0093625134578906, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009235762432217598, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00909063897561282, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00894825648283586, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00879837614716962, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00863102251663804, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008525154895614832, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008454671245999634, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008386022537015378, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00834708723705262, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008322712799999863, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.008339467588812113, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008373365902807564, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00831895336508751, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008262990333605558, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9816315174102783, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9740610122680664, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.962158441543579, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9510960578918457, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9407613277435303, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.927546977996826, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.913886785507202, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.900249719619751, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8843464851379395, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8696372509002686, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.8571391105651855, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.8412723541259766, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.828493356704712, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.813325881958008, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.801165819168091, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7905514240264893, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7775933742523193, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7622854709625244, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.744332790374756, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7267067432403564, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7034366130828857, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.677727460861206, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.6469054222106934, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.611194372177124, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.571072816848755, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.519487142562866, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.469970464706421, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.422476053237915, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.354736089706421, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.270850658416748, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.1934616565704346, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.122100591659546, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.0248022079467773, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.938088297843933, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.8362114429473877, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.7377368211746216, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.6362038850784302, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.5432219505310059, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.446631908416748, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.3335944414138794, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.2519813776016235, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.1845921277999878, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.1031450033187866, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.0420054197311401, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.9864562749862671, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9390292763710022, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8952994346618652, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8351473212242126, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.7872397303581238, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.08705357142857142, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.08680555555555555, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.08655753968253968, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0873015873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.08953373015873016, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.10962301587301587, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.15674603174603174, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1708829365079365, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.17435515873015872, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.18774801587301587, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.21453373015873015, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27232142857142855, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.34399801587301587, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.390625, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.4312996031746032, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.4878472222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.5364583333333334, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.5907738095238095, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6277281746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.6646825396825397, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.6951884920634921, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7189980158730159, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7395833333333334, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7497519841269841, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7631448412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.7777777777777778, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.7814980158730159, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.7678571428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.7487599206349206, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.7562003968253969, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.7931547619047619, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8055555555555556, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.00762861054965117, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0076103500761035, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007718303058717821, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008479068740590862, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012615209778536685, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.020145523240058725, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.01911093405804108, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.014127600156060698, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.014426009634826912, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0204107111486249, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.03777783699520856, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06376847221530792, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11237509184847368, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1746159534386074, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20830772747394932, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2562656536944159, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.337255168325582, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.39095671638240376, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.4488818309458247, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.49038691219667657, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.5526421732448746, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6068495358608896, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.6441931524505091, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6684008142089197, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.6777457199504192, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.6957503026676667, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.7147084736250254, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.7247704661229717, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.7164957190505412, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.6983062141494111, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.7070712627813558, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.7400330668302395, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.7467093848643198, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.8392564368247986, "validation/loss_best": 0.7872397303581238, "validation/acc_best": 0.8055555555555556, "validation/f1_best": 0.7467093848643198} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.154368245601654, "train/grad": 0.07468371445313096, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.968656005859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.959920654296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.946156005859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.933623046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.922340087890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.907933349609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.893521728515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.879447021484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.86351318359375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.849324951171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8375579833984377, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8227410888671876, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.81082763671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7959185791015626, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.782974853515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.770831298828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7552728271484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.736224365234375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7138037109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.691815185546875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.662900390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.631043701171875, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.592979736328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.54938720703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.50080078125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.43894287109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.38002197265625, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3241140747070315, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2455426025390626, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1496267700195313, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.063015899658203, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9844671630859374, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.8799665832519532, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.7887572860717773, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.684006233215332, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.5845012474060058, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.4831269073486328, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.391732120513916, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.2981580924987792, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.190792498588562, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.1150955724716187, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.0538595008850098, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.9806673336029053, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.9235541081428528, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.8637140297889709, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.8057617509365081, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.7611190176010132, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.7140533030033112, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.6799339532852173, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01732890240382403, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01700899048708379, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016493692267686128, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.016008658907376228, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015548501047305763, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01494049500208348, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014293049946427345, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01362790649291128, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01284659261116758, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01212745206663385, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011537190780509264, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010869751835707575, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010438354082871228, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010081814981531352, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00992416933644563, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009856503799092024, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009819505896884947, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00979920343030244, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009782493554521352, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009766234909184277, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009744848366826772, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009719021921046078, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009685842078179121, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009644924523308873, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009597134531941266, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009534233105368913, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009472329476848245, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009411986488848924, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00932395747397095, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0092151997750625, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009114430565387011, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00902521138312295, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008904009510297328, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008798103851731867, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008671140612568707, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00854497833410278, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008405966504942625, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008263270042371006, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00810554092284292, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007948839596938342, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007881649639457464, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007849610194098204, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007810743763111532, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007793005981948226, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0077618671767413615, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0076179427723400295, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007453532698564231, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007387018161825836, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.007463966603390873, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.955044984817505, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.94515323638916, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.93011474609375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.916515350341797, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.90438175201416, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.889284133911133, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.874516010284424, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8604207038879395, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.8449044227600098, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8313868045806885, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.820269823074341, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.806305408477783, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.794578790664673, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7789862155914307, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7643702030181885, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.750199556350708, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7315735816955566, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.708737373352051, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6817729473114014, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6552679538726807, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.620637893676758, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5827572345733643, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5377368927001953, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4864859580993652, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4299027919769287, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.358466148376465, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.291276454925537, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.228229522705078, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.140770196914673, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.036268711090088, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.9436219930648804, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.8611539602279663, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.7533878087997437, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.6613481044769287, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.5583364963531494, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.4628609418869019, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.367203712463379, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.2827013731002808, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.1974834203720093, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.1007875204086304, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.0320801734924316, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.9760782718658447, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.9100176095962524, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.858909010887146, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.8030151128768921, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7503281831741333, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.7109043598175049, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.6703627705574036, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6459383368492126, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.08680555555555555, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.08903769841269842, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.10119047619047619, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.14310515873015872, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.1701388888888889, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.17261904761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.17906746031746032, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1974206349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24479166666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.28918650793650796, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.32490079365079366, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.3695436507936508, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.41716269841269843, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.4642857142857143, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.5094246031746031, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.5691964285714286, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.6096230158730159, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.6520337301587301, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.6760912698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7003968253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7189980158730159, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7371031746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7604166666666666, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7777777777777778, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.7919146825396826, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8082837301587301, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8115079365079365, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8283730158730159, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8390376984126984, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8454861111111112, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8521825396825397, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8462301587301587, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.008089998158425217, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010162427216136093, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.018716001198926066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.020314714920161618, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01527629944648046, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.013885104794195705, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01685418159498096, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.025556917512724413, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04623338205552208, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.09251970278223261, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1287971155230215, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1541885497279341, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.183674422455314, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.24112325343708577, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.3073188340180859, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.36566605186778584, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.4431140230294921, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.4925791294456011, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.5532477526060952, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.5770866712571925, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.6135199195917687, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.6418631449799074, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.671770486007135, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7040514144046962, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7316628576526838, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7522560857711694, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.7740032621412778, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.7726450643767452, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.7907146251366216, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.804070483488064, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8165353712454362, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8274692281412493, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8217098085225787, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.7140533030033112, "validation/loss_best": 0.6703627705574036, "validation/acc_best": 0.8521825396825397, "validation/f1_best": 0.8274692281412493} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.0449387204647063, "train/grad": 0.07172567935660482, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.944969482421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9343212890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.918388671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.904329833984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.892100830078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.8770556640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.862703857421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.8493408203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.83488037109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.8222979736328124, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.811756591796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7978814697265624, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7854962158203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.767969970703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7509185791015627, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.734146728515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.712210693359375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6849957275390626, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.65318603515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6218939208984375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5811956787109374, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5370068359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4848486328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.42594482421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3614736938476564, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.28110595703125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.206604766845703, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.1375347900390627, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0431834411621095, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.932356719970703, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.8358937072753907, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.75137393951416, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.6428205871582031, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.5514497756958008, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.4502151107788086, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.3571823501586915, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.2650859546661377, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.1842460823059082, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.1035388326644897, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.0134139108657836, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.9512242031097412, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9021700859069824, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8451260507106781, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.8009188187122345, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7541384363174438, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.7086680534482003, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6744073411822319, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6407590478658676, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.6172665458917618, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016557779088616373, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016138821416534485, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015485140117816628, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014873867318965495, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014302782975137233, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01358430105028674, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012868011742830277, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012184260562062264, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011479609091766178, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010953074286226184, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010614524274133145, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010328932902775706, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010200544151011855, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010123040580656379, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010091574024409055, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010071384848561137, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010051583803724498, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010028154356405139, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009997359702829271, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00996787336654961, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009926833463832736, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009877010653726757, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009815956712700427, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009743765534367413, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009659281293861567, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009547776763793082, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00943874565185979, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009335045062471181, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009187705593649297, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00900984887033701, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008850591643713414, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008708467418327927, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008526428344193846, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008376644279342144, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00821059615816921, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00805851461365819, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007903266763314605, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007768505485728383, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0076416704105213284, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007529097874648869, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00748796021216549, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00749427784467116, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00752783355419524, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.007520012611057609, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007446634098887444, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.007359863861929625, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007339505013078451, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007455674558877945, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.007601640948560089, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.930187940597534, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9186534881591797, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9016873836517334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.887056589126587, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.874262809753418, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8590431213378906, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.844740867614746, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.831613779067993, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.817521810531616, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.805187940597534, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7945642471313477, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.779916763305664, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7662134170532227, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.746319532394409, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7268178462982178, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.707576036453247, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6822729110717773, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6512906551361084, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6148808002471924, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5794034004211426, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.533480405807495, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4836559295654297, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4253416061401367, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.3599853515625, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.289144277572632, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.2016773223876953, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.121575355529785, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.047974109649658, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.9485504627227783, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.8332589864730835, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.7347239255905151, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.6498101949691772, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.5427902936935425, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.4546664953231812, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.3585238456726074, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.2708193063735962, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.183917760848999, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.1071840524673462, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.0300501585006714, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.9432247281074524, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.8837302327156067, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.836748480796814, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.7810325622558594, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.7378197312355042, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6951810717582703, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6618215441703796, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6356263160705566, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.60420823097229, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5784748792648315, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.10119047619047619, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.13467261904761904, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1701388888888889, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17212301587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.17906746031746032, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.20535714285714285, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24801587301587302, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2943948412698413, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.33878968253968256, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.37797619047619047, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.4146825396825397, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.4583333333333333, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5233134920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.5900297619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6450892857142857, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.6927083333333334, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7209821428571429, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7415674603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7609126984126984, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7678571428571429, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7765376984126984, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7862103174603174, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7936507936507936, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8067956349206349, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8196924603174603, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8348214285714286, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8489583333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.857390873015873, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8506944444444444, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8544146825396826, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8581349206349206, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8643353174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.018674856002996832, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.020602736635345332, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014343212586900841, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.014423093279588366, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.016707760439376655, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.026719448680846324, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.058166786822728384, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.09517618310879203, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1281476490567278, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.15875842886688518, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1920861760065116, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.23627584852713876, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.29572995489641773, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.3865108223542057, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.4810596444092771, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.5443450343850604, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6023120536238337, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.64429786519827, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6845609738025844, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.7150766322976473, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7251429515706204, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.7359815058497033, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.7452314568555679, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7512891542132778, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7731039937723853, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7913719631950403, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8125420058044203, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8284422995892144, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8391459625816289, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8346261676982498, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8426818276581458, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8417835556899068, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8458548313299229, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.6172665458917618, "validation/loss_best": 0.5784748792648315, "validation/acc_best": 0.8643353174603174, "validation/f1_best": 0.8458548313299229} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 1.9483711642026902, "train/grad": 0.06792021322995424, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.91928955078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9074365234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.88998779296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.875323486328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.86266845703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.84787109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.8340533447265623, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.82154052734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.807896728515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.795682373046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7845648193359374, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.7686859130859376, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.753392333984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.730885009765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.7087591552734374, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.686968994140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.65838134765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.62330078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.582393798828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5427471923828127, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.491475830078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4362322998046877, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3720718383789063, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.300520324707031, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.22369384765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.129790802001953, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.044647979736328, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9673452758789063, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.8641658020019531, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.7464712524414063, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.64709716796875, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.5620849609375, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.4555872344970704, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.3681079864501953, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.2729826068878174, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.1869649696350097, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.103126516342163, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.030444951057434, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.9588690996170044, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8796672105789185, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.8257303237915039, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7832264637947083, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.7337357306480408, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6959543025493622, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6571342945098877, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.6212473326921463, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5942521971464158, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5667600640654564, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5489714285731315, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015574360908940434, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015070793414488436, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014284486460965126, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013580644351895899, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012961779905017465, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01220918119419366, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011526464824564755, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01097332003992051, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010511457331012934, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010246974998153746, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010118277862202376, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010037384368479252, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010005037833470851, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009980701745953412, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009962091641500592, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009943106551654637, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009920107887592167, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009890027772635222, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009854045363608748, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009819590055849403, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009772354774177074, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009717753548175096, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009653053234796972, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00957690108101815, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009489316849503666, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009374594888649881, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009259903286583722, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009146109435241669, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008981133718043566, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008777661246713251, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00859755813376978, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008440892922226339, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008244973118416965, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00808338489383459, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00790059389313683, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.007727669889573008, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007546972434502095, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007390909411478788, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007231221785768866, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007059907651273534, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006965327621437609, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006913949851877987, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006871665267972275, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.006862011215416714, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.006847322258399799, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006834250299725682, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.006807376982178539, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.006756685415748507, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0067988576681818815, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.909480094909668, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8971009254455566, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8794445991516113, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.86452579498291, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8519930839538574, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.837496757507324, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8241629600524902, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.812028169631958, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7985899448394775, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.785933017730713, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.774224281311035, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.7569541931152344, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.74011492729187, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.7152767181396484, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6908273696899414, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.6667706966400146, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6353325843811035, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5969035625457764, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5521152019500732, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5087528228759766, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4532227516174316, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.393570899963379, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.324620485305786, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.248500108718872, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.167203187942505, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.0688722133636475, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.980542778968811, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.901177167892456, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.7962538003921509, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.6782130002975464, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.579787015914917, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.4967445135116577, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.3936606645584106, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.3098807334899902, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.2193665504455566, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.1372424364089966, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.0578114986419678, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9906213283538818, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.9269044995307922, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.8580361604690552, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.8085691928863525, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.7651628851890564, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.7105687856674194, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6705434918403625, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6334654688835144, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5975872278213501, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5700791478157043, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5537785887718201, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5453397035598755, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1644345238095238, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1753472222222222, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.18799603174603174, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22495039682539683, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27653769841269843, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3368055555555556, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3812003968253968, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4260912698412698, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.4603174603174603, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5034722222222222, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.564484126984127, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6272321428571429, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6676587301587301, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6951884920634921, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7175099206349206, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7336309523809523, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7462797619047619, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.7643849206349206, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.7844742063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.7924107142857143, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.7971230158730159, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.7993551587301587, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8075396825396826, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8167162698412699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8370535714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8501984126984127, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8549107142857143, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8678075396825397, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8812003968253969, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8705357142857143, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8668154761904762, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01704823195821514, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01394717103529364, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.014435017857135949, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.021598407463574918, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.03784580535890604, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.07789593282913747, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.12381021477822778, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.17020791581054237, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20452816905420415, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.25513488755014224, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.3003102640757759, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.3657761586922918, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.452167101130998, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5253312913519232, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.5813613840377561, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6246845175262289, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.656053994730865, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.677894629496965, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.6951433125238122, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.7212150250926597, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7446485821070876, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.7492026506412329, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.7523498265470051, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.7566721651644654, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7667490750824262, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7785457737493199, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8113920168535975, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8308169580981234, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8374082686916418, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.85068092902636, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8675577116235116, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.856964479314049, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8506075259254795, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.5942521971464158, "validation/loss_best": 0.5700791478157043, "validation/acc_best": 0.8812003968253969, "validation/f1_best": 0.8675577116235116} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 1.8845387232303619, "train/grad": 0.06497869554907083, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.9009765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8884423828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.870731201171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.85602294921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8437158203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.829515380859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.8167138671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.80470458984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7910711669921877, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7777899169921874, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7651580810546874, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.74643798828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7278790283203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.7006109619140624, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.673802490234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6474542236328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6130340576171873, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5711651611328126, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.52243896484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.475589599609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4156588745117187, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.351656188964844, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2782046508789064, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.197596130371094, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.112281494140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0100161743164064, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9191378021240235, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.8381669616699219, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7321380615234374, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.6139543151855469, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.5162115097045898, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.4339897918701172, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.3325363159179688, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.2503927993774413, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.1619535827636718, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.0831126689910888, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.007180471420288, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.9419540691375733, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.8780798721313476, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.8078960871696472, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.7602615940570832, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.7228959786891938, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6794781368970871, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.6465920048952103, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6139808410406112, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5850489413738251, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.562959586083889, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5403550279140472, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5254550734162331, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01466961245285347, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014089827372226865, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013231800582725555, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012489169908221812, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011853533021640033, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01116442988626659, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010628232005983592, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010264797280542552, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010019957292824984, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00991136543219909, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009867090547922999, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009835697489324956, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009818111308850347, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009794454115908593, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00977206465555355, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009748702112119645, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009718019652646036, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009679775706026704, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009632726279087366, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009584057852625847, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009521117573603988, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009449229957535863, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009361185042653233, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009260510923340917, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009145067597273737, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008998767547309399, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00886197434971109, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008735411090310664, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008563396628014744, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008364985450170934, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008196404087357223, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008052556880284101, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007868841886520386, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007716956730000675, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007549904531333596, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0073986160196363926, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007258543770294636, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007144292332231999, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0070347901852801445, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006922207967145369, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006851825109915808, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0067975585209205745, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006720195608213544, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0066872889897786085, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.006726528002182022, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006814877041615546, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.006775044557871297, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.006686907060211525, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006662430507130921, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8925516605377197, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8799116611480713, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8620967864990234, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8475708961486816, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8356220722198486, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8219218254089355, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8093454837799072, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.797499895095825, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.783594846725464, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7696051597595215, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.756103754043579, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.735771417617798, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.71575927734375, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6861917972564697, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.6572265625, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.628793239593506, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.591717004776001, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.546678304672241, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.494621992111206, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.444554567337036, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.380969762802124, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.3133351802825928, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.236116409301758, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.1520185470581055, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.063671350479126, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.9585680961608887, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.8660904169082642, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.7843427658081055, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.6782222986221313, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.561224102973938, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.4652704000473022, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.3850396871566772, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.2865116596221924, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.2070465087890625, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.1214526891708374, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.0443699359893799, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.9696334004402161, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9056246876716614, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.8444684743881226, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.7775357365608215, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.7315776944160461, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6950560808181763, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6519826650619507, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6213783621788025, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5913349986076355, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5621309876441956, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5410719513893127, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.5196990966796875, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5084778070449829, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17237103174603174, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1783234126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.19122023809523808, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2261904761904762, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.27306547619047616, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3323412698412698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.376984126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.4236111111111111, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.47197420634920634, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5210813492063492, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5649801587301587, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6259920634920635, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.6741071428571429, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7026289682539683, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7254464285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7428075396825397, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7594246031746031, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7757936507936508, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.792906746031746, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8070436507936508, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8206845238095238, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8311011904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8390376984126984, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8447420634920635, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8509424603174603, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8568948412698413, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8618551587301587, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8660714285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8762400793650794, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8824404761904762, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.886656746031746, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8891369047619048, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013888047800722664, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01650686959327476, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.023929074966945296, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.037854129154538174, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07536208077273043, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.11844171396274475, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.16477823221868917, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1996430312287737, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2502893512754692, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.3172397744988181, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.3797791049135666, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.4415869570101742, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5182756608422018, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.5773412171023518, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6146202614780034, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6515122776201223, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.6826971517116798, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7071114275038792, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7320826963189406, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.7573175072016464, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7754956127309567, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.7925682878503005, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8083003608914103, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8200802263062702, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8249951013561492, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8315883740797977, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8360432886127912, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8395476610907486, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8427181625865917, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8509334176115207, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.862592857230941, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8720859766258042, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.875026827943435, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.5254550734162331, "validation/loss_best": 0.5084778070449829, "validation/acc_best": 0.8891369047619048, "validation/f1_best": 0.875026827943435} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 1.8242246758937837, "train/grad": 0.06381763216108084, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.886456298828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.873837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.856314697265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.842066650390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8305377197265624, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.817347412109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.804984130859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7929559326171876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7784197998046873, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.763526611328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7488525390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.726634521484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.70488037109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.672691650390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6411334228515626, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.6102691650390626, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.5701617431640624, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5214407348632815, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.465374755859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4115875244140623, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3436602783203124, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2718328857421874, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.190138397216797, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1017584228515624, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.009504852294922, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.900677719116211, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.8056265258789062, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.722176284790039, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.6144580459594726, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4965734481811523, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4004354286193847, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3205175590515137, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.222973051071167, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.1445840835571288, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.061151418685913, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9872128534317016, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.9165431690216065, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8562635183334351, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7976581525802612, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.7338381314277649, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6909129452705384, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6575726461410523, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.6195230174064636, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5909359985589981, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5625460362434387, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5369748938083648, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5189428445696831, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.5018956220149994, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.49064938694238663, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014163744961842894, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013556343093514443, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012674386005382985, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011942257010377943, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011373334594536573, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010821866190526634, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01044970698421821, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010235661775805056, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010116430304478854, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010067289038561284, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01004332697018981, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010019125076942146, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009997159868944436, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009966579705942422, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00993439493700862, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009902712649200111, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009859134138096123, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009805229476187378, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009739282492082566, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009673590608872473, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009585228848736733, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00948828160064295, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00937129809288308, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009238245193846523, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009092793045565485, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00891201150137931, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008746564707253128, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008596954138483852, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008399655777029693, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008174890796653926, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00798968544928357, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007830946245230735, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007634682366624474, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00746595005155541, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.007279046342009678, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0071020174655132, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006935748073738068, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006799606356071308, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006672098106937483, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006530659247655422, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006434633784228936, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006360633919248357, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006285756371216849, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.006254915575264022, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.006263156955828891, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.006283585074124858, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.006323129908414557, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.006434516576118768, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.006500682508340105, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.878727436065674, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8659863471984863, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8484346866607666, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.83451771736145, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8231303691864014, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.810089349746704, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7977287769317627, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7855224609375, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.770446300506592, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7547316551208496, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7393133640289307, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.715891122817993, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6928975582122803, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6590402126312256, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.625828266143799, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5933563709259033, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.5512874126434326, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5004100799560547, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4419713020324707, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.3861615657806396, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.3157835006713867, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.2417545318603516, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.158100128173828, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.06811785697937, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.9748609066009521, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.8657581806182861, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.7710840702056885, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.6884486675262451, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.5826159715652466, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.4673677682876587, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.3739546537399292, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.2961636781692505, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.2013202905654907, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.1251678466796875, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.0440068244934082, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9718083143234253, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.9021748304367065, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.8421435356140137, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7843676209449768, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.7230933904647827, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6819314956665039, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6491773128509521, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.6103969812393188, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5804129838943481, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5510343313217163, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5259497761726379, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5077858567237854, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.49276110529899597, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.49067264795303345, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17113095238095238, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1765873015873016, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19345238095238096, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23313492063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.28893849206349204, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.34250992063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.3834325396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.42237103174603174, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.46478174603174605, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5210813492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5773809523809523, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6135912698412699, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6607142857142857, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7041170634920635, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.730406746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7529761904761905, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7748015873015873, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7886904761904762, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8053075396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8189484126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8306051587301587, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8405257936507936, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8479662698412699, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8529265873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.863343253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8725198412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8819444444444444, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8871527777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8918650793650794, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8958333333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8983134920634921, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8975694444444444, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8861607142857143, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014793193072563427, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.022457264984061302, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04339710230961186, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.08315693101494707, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.12843939081167352, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17574526454952336, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20467032213585307, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.24907821840307912, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.30612131513542107, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.38236923709391696, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.45541924084060637, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5023881243162973, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.5654212455872145, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6322228650376525, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6723925963049936, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7053614821862522, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7352512769613911, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.752308359645791, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7733883390765615, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.790967939909607, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8047285335008858, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8163549668394183, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8240555947890694, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8309946110780407, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8436292472477696, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8551829124269452, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8667073322594547, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8726191361266125, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8781235452471912, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8827334793691425, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8849248158768187, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8848890200469693, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8734975714186842, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.5189428445696831, "validation/loss_best": 0.5077858567237854, "validation/acc_best": 0.8983134920634921, "validation/f1_best": 0.8849248158768187} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 1.7811992621421815, "train/grad": 0.060539629831910136, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.87259765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.859822998046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.842318115234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8282647705078126, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8169134521484374, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.8037664794921877, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.791087646484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.77826171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.76231689453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7454351806640624, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7288189697265626, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.70392578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.679146728515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.642833251953125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.6073675537109375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5728173828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.5279937744140626, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4739678955078124, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.4121087646484374, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.3532229614257814, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.2793511962890625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.201893005371094, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.1148719787597656, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.021839141845703, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.9258419799804687, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.8143922424316405, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.718234100341797, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.6348714065551757, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.5286313056945802, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.4137938117980957, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.3211638832092285, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.244821081161499, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1521622943878174, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0783620548248292, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.0000864458084107, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.9310644221305847, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8654643702507019, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.8099045586585999, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7562244868278504, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.697966912984848, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.658803037405014, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.6283411777019501, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.593213364481926, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.566917575597763, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5406974357366562, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5172485196590424, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5003141823410988, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4844478711485863, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4748538006842136, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013326109102927149, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012690601036883891, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011779026340227573, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011089136071968824, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010600302233360708, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010176872943993658, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009927379579748959, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009804576018359512, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009741154129151254, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009712609932757915, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00969311582390219, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009668888100422919, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009645156513433903, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009610718721523881, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009576327747199685, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009541112792212515, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009492932241410018, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009433502431493252, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00936251760693267, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009290609068702906, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009195723461452872, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009090111462865025, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008966481850948185, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008825521382968873, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008673301402013748, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008484807834029197, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008318122678902, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008166749575175346, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00797076895367354, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007753889076411724, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007572953505441547, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0074188679805956784, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007224437377881259, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007065919402521104, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006892312321579084, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006734837430994958, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006583294486626983, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006459032809361815, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006340480460785329, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006198669912992045, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0061031512496992945, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006026645589154214, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0059311147348489615, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0058710324508138, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0058339970966335385, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005830495310947299, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005826827540295199, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005867265074048191, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005990728961769491, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.867631673812866, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.855034589767456, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8379971981048584, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8246140480041504, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8136792182922363, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8009185791015625, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7882964611053467, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7753841876983643, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.75883150100708, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.741396427154541, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7241482734680176, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6980419158935547, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.67236328125, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.6345572471618652, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.597759246826172, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.561802864074707, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.515324592590332, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.459567070007324, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.3956668376922607, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.33516263961792, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.2592952251434326, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.180217981338501, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.0915379524230957, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9973121881484985, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.9004753828048706, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.7885589599609375, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.6926499605178833, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.6095857620239258, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.5041255950927734, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.3906219005584717, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2993574142456055, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.224342942237854, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.1336725950241089, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.0614513158798218, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.9851477742195129, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.9176502823829651, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8529759049415588, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.7978081107139587, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7445252537727356, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6875170469284058, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6495599746704102, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.6203101277351379, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5864842534065247, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5603255033493042, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5335351228713989, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5078000426292419, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4887770414352417, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4748918414115906, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.46866390109062195, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17509920634920634, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1865079365079365, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22197420634920634, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2631448412698413, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3216765873015873, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.3663194444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.41369047619047616, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.45436507936507936, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.4990079365079365, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5615079365079365, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6088789682539683, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6502976190476191, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6959325396825397, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7328869047619048, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7532242063492064, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7683531746031746, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.783234126984127, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.7924107142857143, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8023313492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8134920634920635, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8283730158730159, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8368055555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8464781746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8561507936507936, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.859375, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8673115079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.878968253968254, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8881448412698413, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8936011904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8988095238095238, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9027777777777778, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9040178571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9027777777777778, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.014431929789323717, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.020343381995778606, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03429602004950631, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.07257566099534854, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.10786903308622647, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14924878696313804, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18269403936589595, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2333679169707019, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.28476226466228205, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.34754099326725985, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.43425189067451797, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.49604801786759106, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5524926074282563, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6202866053125096, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6706609954857246, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.698974118986684, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7221964218444646, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7454027493881422, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7595766740089995, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7739689359781897, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.787839455097841, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8057714848712714, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8152141379929748, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8273230147839908, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8386794087179835, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8417330339343736, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8512112455490106, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8650666482585275, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8750172912302541, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8813930186656013, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8865735440447777, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8919896101400837, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8928267274280853, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8921238261792969, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.4844478711485863, "validation/loss_best": 0.4748918414115906, "validation/acc_best": 0.9040178571428571, "validation/f1_best": 0.8928267274280853} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 1.748247880935669, "train/grad": 0.060345300137996674, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.86466064453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.85238525390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8358154296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.822864990234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8122003173828123, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.799630126953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.786845703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.773349609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.75602294921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7374884033203126, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.7192926025390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6916162109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.66447509765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.6246282958984377, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5857879638671877, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.54798583984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.499244384765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4407403564453123, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3740493774414064, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.310921936035156, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.232117919921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1501158142089842, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0587059020996095, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9619214630126953, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.8630826568603516, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.7492914581298828, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6523727798461914, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5688176345825195, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.4633389854431151, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.3501848602294921, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.259687328338623, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1853867626190187, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0956858205795288, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.02458411693573, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9494492197036744, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8835277962684631, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.8209451878070831, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7682407236099243, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.7174210244417191, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6626691877841949, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6259698605537415, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5973713383078575, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5645042428374291, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5399247801303864, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5157663643360137, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.495053251683712, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4809319666028023, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4674809451401234, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4595929242670536, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012958876974880695, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012318592160008848, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011469202970620245, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010883346078917383, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010504895502235741, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010208556910511106, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010054766181856394, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009984491462819278, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009944124380126595, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009918753707315773, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009898327721748501, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009868529066443444, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009839408777188509, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009795987075194716, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009751906890887767, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009706844729371368, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00964606537250802, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009570911210030317, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00948081201640889, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009389884623233228, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00927013497101143, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009139493312686682, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008985205623321234, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008814780910033732, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008631197265349328, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008412248557433485, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008218776679132133, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008048338301014155, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007824909219052642, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007580066812224686, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0073780078208073975, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007207680575083942, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006995602210517973, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006824714659014717, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006642698260257021, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006483307108283043, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0063431149593088775, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0062387471529655155, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006156805098289624, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006061216653324664, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005980491824448109, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005907663429388777, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005805898933904246, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00574113215203397, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0056916741060558705, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005723032355308533, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005806276634102687, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005883738507982343, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005988913218025118, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8587138652801514, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8463692665100098, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.829861640930176, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8168892860412598, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.8062736988067627, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7934529781341553, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7804274559020996, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.766582489013672, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7486412525177, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.729579210281372, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.71079421043396, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.682192802429199, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6542131900787354, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.613036870956421, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5730953216552734, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.5341832637786865, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.484034776687622, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.424022674560547, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.35581636428833, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.2913832664489746, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.2112061977386475, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.128175973892212, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.035977840423584, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.9387444257736206, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.8398890495300293, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.7266110181808472, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.6305973529815674, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.5481537580490112, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.4444217681884766, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.3337066173553467, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2453463077545166, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.1732187271118164, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.086182951927185, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.016848087310791, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.943472146987915, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.8785662055015564, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.8164818286895752, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.7632295489311218, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.7111001014709473, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6548700928688049, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6181948184967041, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5907261967658997, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5606063604354858, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5400803685188293, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5227525234222412, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5101976990699768, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5042493343353271, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.49740904569625854, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.47986042499542236, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17113095238095238, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1746031746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18452380952380953, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21750992063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.26066468253968256, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.31101190476190477, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3539186507936508, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.39112103174603174, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.43526785714285715, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.47842261904761907, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5260416666666666, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.5875496031746031, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6297123015873016, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6592261904761905, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6929563492063492, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7214781746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7393353174603174, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7566964285714286, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7690972222222222, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.783234126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.7976190476190477, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8100198412698413, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8246527777777778, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8392857142857143, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8534226190476191, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8712797619047619, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8767361111111112, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8772321428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8831845238095238, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8826884920634921, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8757440476190477, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8732638888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8715277777777778, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8715277777777778, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8742559523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.014790243818943, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.019573318248601663, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.031426592616222285, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.06762165469662054, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.10187863742911875, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13589974930609625, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.16831137500499538, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.20036219945959863, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.25896272008875404, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3202361523687987, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.3831564553472707, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.4579917888514722, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5076433425033267, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.5457910251526767, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6068401360983516, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.65605370906123, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.6814822875088262, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7055805348215821, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7213390142284174, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7399819469141216, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7572191471644684, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.7739798508566655, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.7917386599933803, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8090965191499726, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8294042772511477, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8547625088594089, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8624513951405343, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8641119987427537, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8722235134885455, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8711956662547651, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8604377121458597, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8555928388264034, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8537654828184209, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8521487615979536, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8510892228154887, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 0.5645042428374291, "validation/loss_best": 0.5606063604354858, "validation/acc_best": 0.8831845238095238, "validation/f1_best": 0.8722235134885455} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 1.7223172342777253, "train/grad": 0.05904883209615946, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.857264404296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.845242919921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.829034423828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8163568115234376, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.805872802734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7931939697265626, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.779876708984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.765494384765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7469451904296873, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.72710693359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.707530517578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6777520751953126, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.648553466796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.605750732421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5642633056640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5238043212890626, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.471737976074219, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.4097930908203127, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.33925048828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.272879333496094, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.190551452636719, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.1054788208007813, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.0113868713378906, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.9122824096679687, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.812108612060547, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6976598358154298, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.6008845520019532, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.5180101776123047, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.413918514251709, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.30288818359375, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.2143997955322265, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.1420383548736572, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0549822568893432, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.986139235496521, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9136399984359741, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8502539730072022, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7903108668327331, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7397779178619385, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6911177974939346, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6389537328481674, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.6042891901731491, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5775253063440323, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5471006047725677, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5245205825567245, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.5025609463453293, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4835532107949257, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.47046204179525375, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4585668644309044, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.45048028469085694, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012566067115403711, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011928915733005852, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011128142988309265, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010613543780054897, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010304340438451617, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01008240633411333, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009976336262188851, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009927655293140561, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00989588678115979, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00987211347091943, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009851096731144935, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00982005439698696, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009787503411062062, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009738972429186105, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009689660591538996, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00964065910084173, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00957441498991102, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009491174062713981, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009392286294605583, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00929492654511705, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009165999197866767, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00902886013034731, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008869201540946961, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008694154152181, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008509240797720849, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00829038328723982, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008098857647273689, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007928559377323835, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007706361461896449, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00746104430872947, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007256631979253143, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007082202401943505, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006864281324669719, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006682402172591537, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0064836342190392315, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0063010384561494, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006124277499038726, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0059685539838392285, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005815845661563799, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005656393143581227, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005552434324054048, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005478506064973771, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005397611270891503, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005348764250520617, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005329115736531094, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005360362196806818, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005437740009510889, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005562145868316293, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005628872178494931, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8517019748687744, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8396122455596924, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8235113620758057, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8108668327331543, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.800377130508423, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7873735427856445, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7737669944763184, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7590770721435547, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.739891767501831, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.719463586807251, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.699228525161743, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6685805320739746, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6386289596557617, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5946295261383057, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5519955158233643, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.510659694671631, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4575002193450928, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.394090414047241, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.322221517562866, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.254835367202759, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.171262502670288, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.0853216648101807, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.990447998046875, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.890979290008545, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7907226085662842, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.6768219470977783, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.5808039903640747, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.4988367557525635, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.3961418867111206, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.2870099544525146, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.2003366947174072, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.1295311450958252, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.044784665107727, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9778612852096558, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.9078565239906311, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.8466514945030212, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.788830578327179, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.740148663520813, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6932094693183899, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6422191262245178, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.6083160042762756, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5820533037185669, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5522385835647583, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5305150151252747, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.5093798637390137, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4906640648841858, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4771321713924408, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4655716121196747, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4581850469112396, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17162698412698413, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17609126984126985, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18675595238095238, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.22495039682539683, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2740575396825397, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3263888888888889, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.36904761904761907, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.41418650793650796, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.451140873015873, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5029761904761905, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5607638888888888, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6220238095238095, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6686507936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.6989087301587301, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7356150793650794, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7663690476190477, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7889384920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7993551587301587, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8139880952380952, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8239087301587301, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8306051587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8375496031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.847718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8546626984126984, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8606150793650794, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8702876984126984, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8737599206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8762400793650794, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8819444444444444, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8901289682539683, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8938492063492064, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8960813492063492, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8980654761904762, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8993055555555556, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8963293650793651, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.015500978577687138, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.021748437602209455, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.03441652797228912, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07562899536408463, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11467021198933065, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15510804887549978, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1859843693526806, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.23581729763822706, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2820990080959203, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3567029716193088, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4344714667268989, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5116123145174895, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.574132945503621, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6208243329205727, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6807882273148973, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7238866606545175, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7528804888792243, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7680120824466854, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7864457472741558, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7967456307943722, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.803668741300114, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8106295434980776, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8224297489034478, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8306610503619289, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8370008444790106, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8477437112319558, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8536474464793861, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.857961290276806, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8651025794336145, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8730796990101952, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8758571836009301, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8781212254442239, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8795131400797083, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8782375634749299, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.872343119780386, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.4585668644309044, "validation/loss_best": 0.4655716121196747, "validation/acc_best": 0.8993055555555556, "validation/f1_best": 0.8782375634749299} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 1.6951490640640259, "train/grad": 0.05789343064650893, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.85081787109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.838782958984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.822921142578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8104718017578123, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7998065185546874, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7867047119140627, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7726165771484377, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7573779296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7373541259765624, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7160052490234374, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.694927978515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6630047607421874, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.631785888671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5859332275390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5415966796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.498885498046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.44359130859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.37799560546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3037493896484373, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2341375732421875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1481918334960937, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0600411987304685, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9629485321044922, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8615273284912108, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7598137664794922, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6445292663574218, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.547812957763672, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4655647087097168, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3628778457641602, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2541243648529052, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.168033103942871, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0979083919525146, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.0139442014694213, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9476557278633118, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8781389904022217, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8173906373977661, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7599202013015747, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.7113798427581787, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6647521650791168, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6145713752508164, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5812546366453171, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5555300131440163, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5265569490194321, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.5052466231584549, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4846350491046906, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4668942154943943, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.45440240800380705, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4426526670157909, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4355396123230457, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01217786492779851, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011550410313066094, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01080396831035614, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010356576647609472, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010106696537695825, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00994404443539679, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00987222709460184, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00983816222520545, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009811176641378552, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009788288644049317, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009765962543897331, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009731535511091351, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009697523715440184, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009646056334022433, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009594398539047689, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009541690635960548, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009471657872200012, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009384263777174056, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00928174245171249, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009179475400596857, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009047333493363112, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008904729504138231, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008739280784502625, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00855815023649484, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008368438109755516, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008142969880718737, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007946975061204285, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007774795354343951, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007551707401871681, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007306140272412449, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007104145707562566, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006933034628164023, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006721314139431342, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006545605330029502, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0063506958133075385, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006165673002833501, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005976913606282323, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005806845818879083, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005637595722218975, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005458247584756464, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005348124216543511, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005269564602058381, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005201805927790701, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005163044718792662, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005146480553084984, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00515442538773641, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005155185592593625, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005130250788060948, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005137436294462532, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8463950157165527, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8344953060150146, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8187661170959473, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8063316345214844, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.795799732208252, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7825334072113037, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.768383264541626, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7529125213623047, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.732635974884033, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7110252380371094, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6897051334381104, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.657388210296631, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.625765562057495, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.579542398452759, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.534790515899658, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4914472103118896, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.435772657394409, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.369718074798584, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.295083999633789, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.225273370742798, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.139253854751587, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.0510544776916504, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.9543379545211792, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.8535901308059692, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7524571418762207, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.6382089853286743, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.5424330234527588, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.4609254598617554, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.3593419790267944, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.25162935256958, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.1664111614227295, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.096993327140808, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.0138708353042603, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9481995701789856, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8794440031051636, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.8193326592445374, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7626060843467712, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.7144585251808167, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6677621006965637, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.617446780204773, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5847507119178772, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5601948499679565, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.53363436460495, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5143150687217712, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.49548962712287903, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.47950035333633423, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4688952565193176, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.45994555950164795, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.45495176315307617, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1728670634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.17906746031746032, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1966765873015873, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.24231150793650794, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.29737103174603174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3410218253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.3814484126984127, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.42509920634920634, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.4729662698412698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5238095238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5858134920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6403769841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.685515873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7140376984126984, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7423115079365079, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7686011904761905, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7847222222222222, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.7956349206349206, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8100198412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8214285714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8315972222222222, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8390376984126984, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.847718253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8546626984126984, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8660714285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8777281746031746, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8839285714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8874007936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8918650793650794, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8940972222222222, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8953373015873016, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.8960813492063492, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.8953373015873016, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.8975694444444444, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.8983134920634921, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013885104794195705, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01713057177193038, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.025790166304880353, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.04520755848215545, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08950804820310856, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1295774563622405, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16304504276670043, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.19390787033796789, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.25012937629373105, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3190676918298364, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.3831581057106942, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.46496377814584744, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5359111295488646, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.5976948537877369, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6445916955192265, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.6856444982802161, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7213821520736732, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7412250759564635, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7547043283919472, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7730636725099226, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.7874855983835302, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.7996260877512542, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8108339512493036, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8235569152291905, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8326233485598179, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8467804293526784, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.861335938265092, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8683771829976396, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8721388629978379, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8748696919940997, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8745829327274871, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8742124271152728, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.871247154119162, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.8687954643243962, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8728989652055814, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8730502969603051, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.4355396123230457, "validation/loss_best": 0.45495176315307617, "validation/acc_best": 0.8983134920634921, "validation/f1_best": 0.8730502969603051} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 1.686007552742958, "train/grad": 0.058793462570756676, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8526953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8415570068359375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8268133544921876, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.815157470703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.804964599609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.79201904296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7776861572265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.762042236328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7413470458984377, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.71909423828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6972039794921874, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.664154052734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6316802978515623, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5842950439453123, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5384368896484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.49416748046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.4371826171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3696588134765624, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2933755493164063, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2221722412109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1344317626953124, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0446038818359376, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9461007690429688, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8436798858642578, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7410826873779297, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.6253812026977539, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.5283832931518555, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.4461839294433594, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3436757850646972, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.2352355098724366, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1494285583496093, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0796233749389648, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.995982756614685, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9299772024154663, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8608243989944458, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8003688037395478, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7433659267425538, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6954841542243958, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6496030825376511, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.6006155776977539, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5682188105583191, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5433533975481987, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.5153186357021332, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4945424035191536, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4741495686769486, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.45626454025506974, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.44384537905454635, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4327529023587704, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.42619015589356424, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011953019015491008, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011378830415196717, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010739249675534666, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010387049452401698, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010210907240398227, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010108848672825844, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010067892412189394, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010046748036984354, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01002584887901321, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010004368224181236, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009982859049923718, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009948986172676087, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009914164913352579, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00986191479722038, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00980883008101955, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009755711818579585, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00968417761148885, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009595486691687256, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00949046557303518, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009388293856754899, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009253644484560937, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009110002736561, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008944959687069058, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008765362382400782, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008575986044015736, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00835291768424213, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008155774583574384, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007983249335084111, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00775754306698218, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007501235188683495, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007285588179947808, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0071013978845439855, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006864419534103945, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0066676817124243825, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006448254332644865, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006246108525665477, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006046357826562598, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005877473307773471, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005717351053608582, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005554364620475098, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0054524915176443756, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005383925705682486, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005307623649714515, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00524447278585285, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.005179042303934693, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00513963263714686, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.005136739069130271, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0051747173035983, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.005223395877983421, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8424506187438965, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8307127952575684, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.815303325653076, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.802933692932129, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.792351484298706, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7788047790527344, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.764148235321045, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.748063564300537, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7269625663757324, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.704423666000366, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6821839809417725, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6485402584075928, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6156322956085205, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5676560401916504, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5211429595947266, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.476304769515991, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4188458919525146, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3505940437316895, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2738304138183594, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.2022604942321777, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.114201307296753, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.0244486331939697, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.9262570142745972, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.824526309967041, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.722848653793335, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.6086159944534302, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.5131841897964478, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.43248450756073, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.3318785429000854, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.22585928440094, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.1422377824783325, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0741653442382812, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9929612874984741, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9290497303009033, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8621474504470825, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.8038133978843689, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7486188411712646, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.701940655708313, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6570996046066284, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.608433187007904, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.575955331325531, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5509831309318542, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5226024985313416, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5016331672668457, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.48112547397613525, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4632599353790283, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.45171624422073364, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.44160887598991394, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.43528541922569275, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1708829365079365, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1753472222222222, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18353174603174602, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.21378968253968253, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2586805555555556, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3187003968253968, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.35615079365079366, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4000496031746032, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.4412202380952381, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.4908234126984127, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5496031746031746, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6108630952380952, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6656746031746031, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7075892857142857, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7341269841269841, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7599206349206349, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7834821428571429, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.7973710317460317, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8095238095238095, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8204365079365079, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8263888888888888, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8335813492063492, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8395337301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8469742063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8539186507936508, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8625992063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8722718253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8807043650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8839285714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8896329365079365, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.894593253968254, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9002976190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9020337301587301, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9074900793650794, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9084821428571429, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9074900793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014431929789323717, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.020701746470306585, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03075852884798711, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.06435359998105894, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10045656232799868, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14635052672605858, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17232928617267398, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.21474201891004505, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.27098221332819844, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3429333369384449, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.42323960231384994, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5045027684572876, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5704907903773508, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6353853819570933, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.677117503213902, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7160634927045516, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7442495119534984, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7645935265452954, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7799030234618297, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.794285684332096, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.800547950409673, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8082489586059785, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8146214290134473, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8236001047261206, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8322971768607308, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8425021601825013, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8544696853711157, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8633438238954021, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.867974857997204, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.873695853941953, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8807379570041379, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8872823383141036, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8891401430314342, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.89577741425696, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.8970706897454455, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.8972200544266654, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.4327529023587704, "validation/loss_best": 0.44160887598991394, "validation/acc_best": 0.9084821428571429, "validation/f1_best": 0.8970706897454455} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 1.6708368426561355, "train/grad": 0.0558686637878418, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.84583251953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8345843505859376, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.819677734375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8076422119140627, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7971148681640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7835479736328126, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7687078857421876, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7523907470703124, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7309918212890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7078558349609376, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.68519287109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.650977783203125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.617430419921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.568470458984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5212579345703126, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.475552978515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.417113952636719, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.347920227050781, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.270013427734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.197559051513672, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.1084544372558596, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.0175846862792968, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9185155487060548, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8158158111572265, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.7132884216308595, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5980898666381835, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.502047996520996, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.420494556427002, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.3192144203186036, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.212365608215332, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1278510570526123, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0592564678192138, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9770961093902588, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.9125331592559814, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8448463606834412, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.78585298538208, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7302901768684387, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6835971468687058, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6386871886253357, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5906629294157029, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5588775429129601, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5344570052623748, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.507138977944851, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.487099769115448, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.46761415094137193, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.45075553089380266, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.438980895280838, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.42808980971574784, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.421613509953022, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011488534389063715, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010893978318199516, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010242240715306251, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00989484044490382, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009726525531150401, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009629351701587439, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009588588105980306, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00956470048520714, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009542018396314234, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009521792789455504, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009500262758228928, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00946773445699364, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009434238213580103, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009384010753128677, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009333131867460907, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009281907060649247, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009212743886746467, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00912818766431883, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009027563945855945, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008928648435976357, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00879996047122404, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008661938491277396, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008502230632584542, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008328251850325614, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008144063393119723, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007928165274206549, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007735755706671625, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007566628688946367, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007343803981784731, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007093668703455478, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006882438396569341, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006702892847824842, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006475816194433719, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006288397599710152, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0060793574387207625, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005891764404950663, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005705539138289168, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005540205342695117, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005378044102108106, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005209167671855539, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005106660659657791, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005037590201245621, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004978503943420947, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004942374272504821, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004908525801729411, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004886507751652971, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004884694811189547, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004916358314221725, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004979703915305436, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8395726680755615, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.828026056289673, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.812742233276367, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8004918098449707, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7897982597351074, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7759883403778076, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7609341144561768, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.744380474090576, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7226295471191406, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.699388265609741, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6765191555023193, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6418850421905518, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6080548763275146, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.558683395385742, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.510977268218994, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4649970531463623, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.4060959815979004, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3363680839538574, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.258017063140869, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.185086965560913, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0957016944885254, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.0047495365142822, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.905609369277954, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.8031402826309204, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.7011204957962036, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.58681058883667, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.491599202156067, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.4110451936721802, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.3111493587493896, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.205886960029602, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.1228395700454712, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0553004741668701, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9745740294456482, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.9110262989997864, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8444930911064148, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7867342829704285, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7323886752128601, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6868420243263245, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.643351137638092, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5968996286392212, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5660560131072998, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5424309968948364, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.515744686126709, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.49610647559165955, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4771074056625366, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4605449438095093, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.44879400730133057, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.43741559982299805, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.43049827218055725, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17113095238095238, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17633928571428573, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1865079365079365, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.22123015873015872, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.26711309523809523, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3263888888888889, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3630952380952381, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4087301587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.44816468253968256, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.49702380952380953, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5558035714285714, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6140873015873016, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6644345238095238, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.6989087301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7261904761904762, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7529761904761905, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7755456349206349, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.792906746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8028273809523809, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8179563492063492, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8286210317460317, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8395337301587301, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8501984126984127, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8583829365079365, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8692956349206349, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8762400793650794, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8856646825396826, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8896329365079365, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8940972222222222, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8993055555555556, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9017857142857143, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9045138888888888, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9077380952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9122023809523809, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9109623015873016, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9124503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.014790243818943, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.022104161811762387, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03438980686520906, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0718984158385718, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10759273496946531, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1541212537288603, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.17999739733725237, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.22798846284900512, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2802768615876428, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.34990269730025425, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4296908699423859, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5003800156710531, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5616142547883056, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6169532841731036, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6646498640276673, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7044567404985143, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7332119241426986, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.758243311042302, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7719803804182694, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7905549819627604, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8034387760572275, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8161982896552357, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8297887799444033, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8392841737391414, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8529675881809105, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8624198026224816, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8730023386852297, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8781815065207892, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8823960559819541, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8891165196462586, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8912106782474396, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8941204975747491, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.897723553296309, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9034315378384428, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9029225653341759, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9056232534703346, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.421613509953022, "validation/loss_best": 0.43049827218055725, "validation/acc_best": 0.9124503968253969, "validation/f1_best": 0.9056232534703346} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 1.660132172703743, "train/grad": 0.057427060604095456, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.844468994140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.83359619140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8190771484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8074200439453123, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.797008056640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7833367919921876, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.768265380859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7515496826171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7294573974609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.7056634521484373, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6823101806640626, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6470416259765623, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6125048828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5621832275390624, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.513564147949219, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4666934204101563, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.40670654296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3358224487304686, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2561611938476562, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.182071533203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0913075256347655, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9989335632324219, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8985009765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7946717834472656, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6915600967407227, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5759968948364258, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4798942184448243, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3988530540466309, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2982685661315918, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1924954319000245, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.1090230464935302, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0413293266296386, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9604470109939576, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8968960928916931, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8302705836296081, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7721975803375244, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7175782132148742, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6715788173675538, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6275943148136139, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5804914355278015, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5493497562408447, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5253574138879776, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.49831138968467714, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4783840122818947, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.45891654878854754, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.44189091920852663, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4299743750691414, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.41906171023845673, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4124409452080727, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011735539564397187, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011180909315589816, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010587583966553212, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010281289294362068, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01013755659107119, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010053668771870434, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010015834642108529, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009991341209970415, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009967956107575447, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009942346084862948, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009916749517433345, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009876855271868408, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00983724378515035, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009777227840386331, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00971735660918057, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00965661257505417, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009575132566969841, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009475514413788915, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009357520600315184, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009241891019046307, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00909265710040927, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00893321342766285, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008751883949153126, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008554970626719297, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008347949059680105, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008106123646721244, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007894760034978389, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00771023680921644, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0074687481857836245, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007200097430031746, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006976032748352737, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006783618109766394, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006544505839701742, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0063461386878043416, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006127031238283962, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00592752545257099, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0057313192437868565, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005559681142913177, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005391923064598814, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.005207803767407313, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005089012499665841, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005001425065565854, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004908734880154952, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004848275042604655, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004800243413774297, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004763404722325504, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004747732172254473, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0047545536747202275, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004780114955501631, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.837549924850464, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8261098861694336, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.811016798019409, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7987821102142334, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7880446910858154, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7740466594696045, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7587227821350098, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7417948246002197, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.719636917114258, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6959195137023926, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.672551393508911, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.637218952178955, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.6027071475982666, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.552438259124756, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.5038626194000244, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.4570493698120117, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3972115516662598, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.326434373855591, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2469937801361084, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.17324161529541, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.0829312801361084, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9911153316497803, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.891405701637268, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.78842031955719, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.686165690422058, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.5719150304794312, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.4768444299697876, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3965739011764526, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2970110177993774, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1923203468322754, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.1097688674926758, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.042784333229065, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9627823233604431, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8998094797134399, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8339720368385315, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7766051888465881, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.722684919834137, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.677410364151001, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6342265605926514, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5880809426307678, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5577632784843445, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.534616231918335, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5087694525718689, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4897881746292114, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4715803861618042, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.4557245969772339, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4449683427810669, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.43527546525001526, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.42947664856910706, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17162698412698413, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17733134920634921, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18799603174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2261904761904762, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.27157738095238093, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.330109126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3655753968253968, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4134424603174603, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.45188492063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.501984126984127, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5620039682539683, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6170634920634921, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6711309523809523, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7125496031746031, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7378472222222222, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7626488095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7859623015873016, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8025793650793651, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8134920634920635, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8251488095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8360615079365079, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8444940476190477, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8511904761904762, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8576388888888888, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8658234126984127, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8752480158730159, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8824404761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8871527777777778, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8928571428571429, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8960813492063492, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8995535714285714, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9030257936507936, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9072420634920635, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9094742063492064, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9089781746031746, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9109623015873016, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015500978577687138, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02345607814452309, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.035768810382315795, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07625005586156007, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1107918437719069, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.15679764539374472, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1809652257643584, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.23481430485443008, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.2865220680923979, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3554621993896531, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4374378697668638, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5089928949653263, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5747561923018961, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6394874954238651, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6816950327908791, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7149144243728776, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7457172957017594, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7682924505709411, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7840910497080648, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7983608885960062, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8123377396310154, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8232343049387145, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8305408911666683, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8371557314395478, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8476422583378654, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8589386921295566, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8671812060036802, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8727019318632211, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.880014452295103, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8842998375016777, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8881606424967949, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8927689641181686, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8974483055663305, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9007572820304761, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9006019411820952, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9034703276875785, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.4124409452080727, "validation/loss_best": 0.42947664856910706, "validation/acc_best": 0.9109623015873016, "validation/f1_best": 0.9034703276875785} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 1.6490412199497222, "train/grad": 0.05621261525899172, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.84119140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.83010009765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.81546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.803480224609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.792845458984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7788018798828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7633514404296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7461376953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7234783935546876, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.69914794921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6753558349609374, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6393182373046873, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.604044189453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.552657470703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5031060791015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.455286865234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.394283447265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.322057189941406, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2411053466796873, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.166029357910156, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0740786743164064, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9807034301757813, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8794205474853516, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7749810791015626, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.671246337890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5555359268188476, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4595050239562988, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3786171913146972, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2784685802459717, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1734002876281737, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.090756378173828, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0238314008712768, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9440449357032776, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8815772056579589, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8162224805355072, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7594061744213104, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7059328955411911, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6610548508167267, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6181323629617691, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5721380978822708, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5416525769233703, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.518226098716259, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4917245802283287, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4721690681576729, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.45304965153336524, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.43620932251214983, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4243512538075447, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.41318870708346367, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.40614917129278183, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011451159419957549, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01090266291750595, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010327078215777875, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010039164605550467, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009907578954007477, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009833143472205848, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009798460151068866, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009776637589093298, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009751702982466668, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009727807585150003, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009702718041371555, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009664818434976042, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009625103136058896, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009566947063431143, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009507653664331882, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009449682908598333, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00937096782727167, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009274273950140924, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009159043347463012, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009047962795011699, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008904934714082628, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00875331443734467, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008580526965670288, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008393748574890196, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008200176774989814, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007973424142692238, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0077753166551701725, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007600984293967486, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007373364754021168, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007120934645645321, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006907991480547934, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0067264576815068726, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006495696108322591, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0063043950812425465, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0060895371530205016, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005891599500318989, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005692850349005312, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005516989859752357, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005339303559157998, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00514135152567178, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005001198123209178, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004895526602631435, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00477502322755754, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004685606568818912, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004600909689906984, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004526466272072867, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0044748114026151595, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0044360723462887105, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004425758299184963, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.836388111114502, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8250255584716797, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.809957981109619, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.797741174697876, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.786921262741089, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7728123664855957, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.757338523864746, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.74019455909729, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.717731475830078, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6937458515167236, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.670063018798828, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6343014240264893, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.599375009536743, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.548495292663574, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.499450445175171, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.452134609222412, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3917529582977295, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3202521800994873, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2401888370513916, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1658682823181152, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.074892044067383, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9826277494430542, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8824819326400757, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.779270887374878, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6769007444381714, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.5625745058059692, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.467506766319275, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3873528242111206, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.288170576095581, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.183719277381897, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.1015219688415527, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.034859299659729, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9551888108253479, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.892584502696991, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.827061116695404, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7701324820518494, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7165007591247559, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6715739369392395, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6286832094192505, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5829340815544128, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5528424978256226, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.529829204082489, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5038831830024719, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.484866738319397, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4663771390914917, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.45020341873168945, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.4386545717716217, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.42786747217178345, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.42112603783607483, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.171875, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1793154761904762, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.19047619047619047, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.23363095238095238, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28447420634920634, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.34052579365079366, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3767361111111111, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.421875, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.46205357142857145, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5101686507936508, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5711805555555556, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6242559523809523, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6773313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7098214285714286, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7358630952380952, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7643849206349206, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7886904761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8015873015873016, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8137400793650794, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8246527777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8328373015873016, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8439980158730159, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8509424603174603, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.859375, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8678075396825397, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8754960317460317, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8841765873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8878968253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8911210317460317, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8968253968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9010416666666666, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.904265873015873, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9079861111111112, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9092261904761905, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9112103174603174, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9131944444444444, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015841728456389138, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02587055581842375, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03879952358516679, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.08268079802784059, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.11986022268046703, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1635072155390034, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19158750918675693, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.24457203303567904, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.29619771710712, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.3637858927555925, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.44714687099398504, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5157552684472919, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.582548135524608, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6372514333206417, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6771492111496565, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7176864371476936, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7493955941880566, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7680036022156906, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7842157974400117, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7983265324500843, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8071817242439692, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8216238014014056, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8310953188726571, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8413183144663509, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8504465589116915, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8613284894186426, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8715728433942416, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8764544597068478, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8807930038453333, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8869222622032934, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8910342131077579, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8949363820926718, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8989750261644348, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9008511542926231, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9031027907966188, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.905129273709746, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.40614917129278183, "validation/loss_best": 0.42112603783607483, "validation/acc_best": 0.9131944444444444, "validation/f1_best": 0.905129273709746} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 1.651081371307373, "train/grad": 0.05685514558106661, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.84169189453125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8310186767578127, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.816619873046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.804859619140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.7943408203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7803509521484373, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.764945068359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7476605224609374, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.7249462890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.700745849609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6769183349609373, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6407318115234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.6055230712890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.554151611328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.5046759033203125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4568280029296874, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.395980224609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3239230346679687, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2432696533203127, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1682818603515623, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.076722412109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9838189697265625, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8829288482666016, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.778925323486328, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.67578182220459, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5605224227905274, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4647816467285155, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3841654205322265, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2841388130187987, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1789624977111817, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.096238613128662, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.0291012144088745, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9489888072013855, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8860822629928589, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8202610349655152, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.762920458316803, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7089064937829971, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6635243582725525, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.619909308552742, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5732456544041633, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5422768297791482, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.518334476351738, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4912682515382767, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.47126736044883727, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4515883533656597, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4343837533891201, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4221896433830261, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.41080171808600424, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4034887716174126, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011598077469971031, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011069614903535694, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010527033908292651, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010263209368567915, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01014665344497189, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01008080692961812, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010048682009801269, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010025508997496218, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010000412596855312, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009972192940767854, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009945635499898344, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009902324604336172, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009860880074556917, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00979705959558487, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009731663977727295, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009666251335293054, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00958064168225974, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009473685938864947, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009346598752308637, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009223477342166006, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00906559998402372, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00889766046544537, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008705746766645461, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008496864088810981, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0082792959199287, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008025300139561296, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007803404582664371, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007608338366262615, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007356400133576244, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007076603921595961, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006844091974198818, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006646122543606907, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0063988711428828535, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006193353683920577, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005966522588860244, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005759541199076921, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005553307818481699, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005372124388813972, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005188860468333587, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0049860839173197745, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004846664136275649, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004738282174803317, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0046122122963424775, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004517375975847244, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004428005496738479, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004351058775791898, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004300420500803739, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0042588458536192775, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00423755977419205, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8357136249542236, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.824368476867676, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8093159198760986, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7971584796905518, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7863759994506836, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7721686363220215, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7565929889678955, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7393641471862793, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.716719150543213, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.692563056945801, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6687233448028564, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.632744789123535, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.597654342651367, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5464460849761963, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.497112989425659, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.449523448944092, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.388807773590088, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.317021369934082, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.2365992069244385, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.1619873046875, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.070795774459839, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9782122373580933, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.877821922302246, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.77446711063385, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6720365285873413, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.5576214790344238, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.4627649784088135, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3827769756317139, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2836085557937622, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1794661283493042, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.0973819494247437, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.030941367149353, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9515219926834106, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8891229629516602, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8239317536354065, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.767139196395874, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7137197852134705, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6688340306282043, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6260576844215393, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5802175402641296, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5500915050506592, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5268915295600891, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5007045269012451, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.48147016763687134, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4627712070941925, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.44640496373176575, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.43489569425582886, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4239233732223511, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.416947603225708, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17212301587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1800595238095238, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.19246031746031747, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.23635912698412698, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2857142857142857, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3412698412698413, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3784722222222222, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.42336309523809523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.46577380952380953, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5119047619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5739087301587301, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6252480158730159, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6790674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7140376984126984, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7388392857142857, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7661210317460317, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7881944444444444, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8028273809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8142361111111112, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8266369047619048, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8380456349206349, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8459821428571429, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8546626984126984, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8648313492063492, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8720238095238095, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8792162698412699, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8891369047619048, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8921130952380952, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8965773809523809, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9012896825396826, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9030257936507936, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9067460317460317, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9119543650793651, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9149305555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9166666666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9174107142857143, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01617711249832046, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02671422824014518, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0407818641858033, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0848385401002591, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12081714664925006, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16341526299612652, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1926190480462215, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.24441531289730326, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3013026340701648, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.36693620626643064, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4492572643016624, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5147669058187511, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5844128696912401, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6414088086870615, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6821216693540337, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7208832973022185, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7504072182004142, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7698254735233713, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7848940097665812, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8001611135542956, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8148017726735634, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8245626402173747, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8349298009200339, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8485661656624482, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8583518041877576, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8671266482597788, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8764295883036406, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8790621789514669, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8854891005448771, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8906086224759575, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8929812588822353, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8976244244845839, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9034120961457226, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9069290967030755, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9088599630303789, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9095397403164045, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.4034887716174126, "validation/loss_best": 0.416947603225708, "validation/acc_best": 0.9174107142857143, "validation/f1_best": 0.9095397403164045} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 1.6412950521707534, "train/grad": 0.05660989170894027, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.841148681640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.830201416015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.8155279541015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.8034405517578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.792733154296875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7785577392578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.76290283203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7455291748046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.722469482421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.697991943359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.67388427734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.63739990234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.60175537109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5497882080078127, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.4996768188476564, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.4514639282226565, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.3898489379882815, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.3169741821289063, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.2353118896484374, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.159529724121094, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.066802673339844, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9728392028808595, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8707260131835937, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.765579376220703, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6613462448120118, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5450746536254882, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4487044715881348, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.367433376312256, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.267132511138916, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.161891164779663, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.0791522836685181, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.01231867313385, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9324060583114624, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8697370886802673, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.8043930816650391, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7474464631080627, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6938939666748047, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6488791275024414, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6058056074380874, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5596781635284424, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5290846282243729, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5055045694112777, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.478838184773922, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.45905784457921983, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4396868622303009, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.42268189758062363, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.4105208595097065, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.39904672965407373, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.39166141286492345, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011589952297508716, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01105945123359561, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010512839597649872, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010246025547385216, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01012519771233201, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010055162038188428, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010020043414551765, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00999484010739252, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009966020253486932, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00993820944800973, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009909976860508323, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009865034916438163, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009820554521866143, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009752968745306134, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009685805370099842, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009617309088353067, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009526793956756591, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009416822127532214, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00928636823548004, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009159140500705688, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008998428373597562, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008828019858337938, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008634422370232642, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00842790418304503, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00821313681313768, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00796522291842848, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007748423486482352, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0075600683549419045, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007315750229172409, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007044356313999742, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006820154674351216, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006627510577673092, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006385858440771699, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0061831414606422185, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005961998634738848, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00575746271875687, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005553543318528682, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005375051696319133, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0051950433466117826, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004995057614287361, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004857098171487451, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.004746983234072104, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004618784774793312, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004521641660248861, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004422479944769293, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004337247502990067, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004273424551356584, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004213761657010764, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004177344500785694, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8354876041412354, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8241536617279053, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.809114933013916, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7969698905944824, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7861502170562744, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.771929979324341, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7562992572784424, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.739048719406128, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7163336277008057, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6921205520629883, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6682276725769043, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.632175922393799, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.597001552581787, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5456326007843018, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.4962403774261475, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.448582887649536, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.387726068496704, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3157808780670166, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.235245943069458, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.160498857498169, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.069162368774414, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9765914678573608, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8761054277420044, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.772707462310791, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6702038049697876, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.5558488368988037, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.4609272480010986, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.3809934854507446, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2818787097930908, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1777962446212769, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.0957876443862915, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0295027494430542, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.9500132203102112, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.887740433216095, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8225083351135254, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7658434510231018, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7125080823898315, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6677954196929932, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6250887513160706, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5794727802276611, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.549385666847229, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5263035297393799, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.5002849102020264, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4811387360095978, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4625093936920166, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.44620636105537415, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.43469348549842834, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4238441586494446, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4169345498085022, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17212301587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1800595238095238, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1932043650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.23660714285714285, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.28695436507936506, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.34226190476190477, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.37996031746031744, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.4236111111111111, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.466765873015873, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5133928571428571, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5756448412698413, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6262400793650794, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6803075396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7140376984126984, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7413194444444444, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7681051587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7889384920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8048115079365079, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8174603174603174, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8271329365079365, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8375496031746031, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8459821428571429, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8551587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8623511904761905, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.8712797619047619, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8797123015873016, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8861607142857143, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8903769841269841, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8953373015873016, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8998015873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9037698412698413, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9092261904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9099702380952381, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9129464285714286, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9154265873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9188988095238095, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01617711249832046, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.02671422824014518, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.04172678423366264, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.08499686308555315, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12194962627037957, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.16450453352320282, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19490730091459324, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.24531877881816486, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.30347285024926435, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.36881429521704656, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4534530628540687, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5163730739361897, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.586742169179878, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6413428959772609, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6854015950879268, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7229911536930534, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7508438712711267, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7727888295071584, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7888194937039266, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8002826425250636, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8144272650457925, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8234771937735443, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8369663726572777, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8447016081179338, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8550329146750056, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8660772062769757, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8737352508507424, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8785301242059445, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8839913216792, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8892918756207305, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.894227152581662, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9008791743162392, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9015204474588918, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9051249575918197, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9082643389254333, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9114588509884194, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.39166141286492345, "validation/loss_best": 0.4169345498085022, "validation/acc_best": 0.9188988095238095, "validation/f1_best": 0.9114588509884194} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 1.6373373943567275, "train/grad": 0.056155886240303515, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.83663330078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.8253729248046877, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.81035888671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.7980462646484376, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.787255859375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7728533935546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7571112060546876, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.73962158203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.71662109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.6921441650390623, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.6679296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6315252685546877, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5959539794921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.5439398193359377, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.493893737792969, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.445694580078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.38422119140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.311446533203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.22989990234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.1542507934570314, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.061770477294922, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9681105041503906, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.8661729431152343, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.7612723541259765, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6572677612304687, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.541268424987793, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.445063648223877, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3640459823608397, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.2637673759460448, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.1586951160430907, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.075958046913147, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.009123110771179, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.9292994832992554, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.8667371392250061, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.801421525478363, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.7446073305606842, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.6911258423328399, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6463433730602265, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6033178305625916, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5574411690235138, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.5269613254070282, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.5035758137702941, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4770547032356262, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4574346581101418, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.43824373990297316, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.42124271631240845, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.40923758879303934, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.3977974560856819, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.390402272939682, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011431185721885413, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010903086762409657, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010363031651359052, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010102848107926547, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009987581013701856, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0099235426238738, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00989225527504459, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009869824037887156, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009845002375077455, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009818435162305832, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009792537800967694, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009750937866047025, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00970880095846951, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009646191271021962, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009582423744723201, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00951944944448769, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009435789685230702, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00933186903828755, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009211224855389446, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009092389803845436, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008942314677406103, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008782070213928819, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008601064793765545, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008404805294703692, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008202536494936795, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007964453001040966, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007756391516886651, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007573704752139747, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00733555955812335, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007069319481961429, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006845623399131, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006653399467468262, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00641138099366799, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006207847635960206, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005983500962611288, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005777121266582981, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00557081641512923, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005387973075266927, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005204813320888207, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004998420696938411, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0048571210540831085, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0047434460744261745, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004612034944584593, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0045114888192620125, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004411948581691832, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00432098277960904, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004255954929394647, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.004193757865577936, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.004152607317082584, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.835456371307373, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.824127197265625, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.809074878692627, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.796950101852417, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7861123085021973, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.771894693374634, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7562687397003174, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.738983154296875, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.71628475189209, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.6920740604400635, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6681504249572754, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6321089267730713, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.596904754638672, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.545535087585449, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.496121406555176, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.448474168777466, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3875348567962646, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.3156347274780273, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.235020637512207, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.160305976867676, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.068936824798584, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.9763420820236206, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.8758734464645386, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.7724031209945679, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.6699107885360718, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.5555846691131592, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.4606261253356934, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.380698561668396, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.2816550731658936, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.1775658130645752, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.0955995321273804, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0292487144470215, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.949877142906189, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8875564932823181, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.8223146796226501, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.7656586766242981, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.7123962640762329, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.6676043272018433, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.6248395442962646, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.5792346596717834, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.5491448044776917, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5260191559791565, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.499988317489624, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.48082080483436584, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.4620811641216278, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.44574910402297974, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.43419745564460754, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4232357442378998, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4163023829460144, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.17063492063492064, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.17063492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.17212301587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17981150793650794, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1932043650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.23660714285714285, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2867063492063492, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.3427579365079365, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.37996031746031744, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.42336309523809523, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.46651785714285715, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.5131448412698413, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5766369047619048, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.6272321428571429, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6803075396825397, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7155257936507936, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7405753968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.7681051587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7881944444444444, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8043154761904762, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8177083333333334, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.8278769841269841, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8365575396825397, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.845734126984127, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8531746031746031, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8625992063492064, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.871031746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.8807043650793651, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.8871527777777778, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.8911210317460317, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8963293650793651, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9015376984126984, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9047619047619048, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9074900793650794, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9104662698412699, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9139384920634921, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9164186507936508, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9169146825396826, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.013882163034705408, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013882163034705408, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.01617711249832046, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.026451782211603533, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.04171654822488972, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.08496023933817701, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12139138783957204, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1651741246392901, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.19498204719712092, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.24531514744921515, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.3030878910123481, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.36904419108128683, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.4542518844373136, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.5172687184413396, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.5866722319225907, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6427509641064961, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.6842488417050155, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.7233776530159364, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.7498997296015041, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7719998564556674, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.7895902140133731, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.8012848798298187, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8127971641849101, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8233319072667669, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8334722521206777, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8448618148908781, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8547778852993912, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.8673312355129345, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.8746649932533442, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.8784869830568498, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.8851274944976986, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8922062599384316, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.895376350496993, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8984868644903108, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9027434323997303, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9062075249250517, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9089870572218376, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9093250816133511, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.390402272939682, "validation/loss_best": 0.4163023829460144, "validation/acc_best": 0.9169146825396826, "validation/f1_best": 0.9093250816133511} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/config.yaml b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0dca6d5205725f7b5495e922cb0ce63344f08e36 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..dffc9c03a8a1fb4fb6da8aee14370480c3b64d4b --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 14, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 0.001065184362232685, "eval/train/acc": 0.9997894626032949, "eval/train/acc_std": 0.00010542522180874744, "eval/train/f1": 0.9998037842668062, "eval/train/f1_std": 0.00012400846868490864, "eval/validation/loss": 0.27482545375823975, "eval/validation/acc": 0.984375, "eval/validation/acc_std": 0.002024554893085694, "eval/validation/f1": 0.9823737145403995, "eval/validation/f1_std": 0.002525071194013464, "eval/test/loss": 0.43538838624954224, "eval/test/acc": 0.975, "eval/test/acc_std": 0.0021804683894359185, "eval/test/f1": 0.9690875203539719, "eval/test/f1_std": 0.0029553282500794156} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..6fa2c9f1a87936f90f14ad1a7fcd19e343b7f29b --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 14, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.001065184362232685, "eval/best/train/acc": 0.9997894626032949, "eval/best/train/acc_std": 0.00010542522180874744, "eval/best/train/f1": 0.9998037842668062, "eval/best/train/f1_std": 0.00012400846868490864, "eval/best/validation/loss": 0.27482545375823975, "eval/best/validation/acc": 0.984375, "eval/best/validation/acc_std": 0.002024554893085694, "eval/best/validation/f1": 0.9823737145403995, "eval/best/validation/f1_std": 0.002525071194013464, "eval/best/test/loss": 0.43538838624954224, "eval/best/test/acc": 0.975, "eval/best/test/acc_std": 0.0021804683894359185, "eval/best/test/f1": 0.9690875203539719, "eval/best/test/f1_std": 0.0029553282500794156} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..fa2faa5e6a82ac9661cdd9ee8020954e87b684ff --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 39, "eval/last/lr_best": 0.0036, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.00016167439753189683, "eval/last/train/acc": 1.0, "eval/last/train/acc_std": 0.0, "eval/last/train/f1": 1.0, "eval/last/train/f1_std": 0.0, "eval/last/validation/loss": 0.07654120028018951, "eval/last/validation/acc": 0.9841269841269841, "eval/last/validation/acc_std": 0.0019163664438165467, "eval/last/validation/f1": 0.9819471875116325, "eval/last/validation/f1_std": 0.0024004891648264698, "eval/last/test/loss": 0.13080595433712006, "eval/last/test/acc": 0.9751984126984127, "eval/last/test/acc_std": 0.0020929904295098013, "eval/last/test/f1": 0.9694896154083872, "eval/last/test/f1_std": 0.0028537524361802306} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b0fe29c60b01205f63c028a7820bd6d1f2d98190 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,hcpya_task21,best,14,0.015,0.05,48,"[50, 1.0]",train,0.001065184362232685,0.9997894626032949,0.00010542522180874744,0.9998037842668062,0.00012400846868490864 +flat_mae,reg,attn,hcpya_task21,best,14,0.015,0.05,48,"[50, 1.0]",validation,0.27482545375823975,0.984375,0.002024554893085694,0.9823737145403995,0.002525071194013464 +flat_mae,reg,attn,hcpya_task21,best,14,0.015,0.05,48,"[50, 1.0]",test,0.43538838624954224,0.975,0.0021804683894359185,0.9690875203539719,0.0029553282500794156 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..b0fe29c60b01205f63c028a7820bd6d1f2d98190 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,hcpya_task21,best,14,0.015,0.05,48,"[50, 1.0]",train,0.001065184362232685,0.9997894626032949,0.00010542522180874744,0.9998037842668062,0.00012400846868490864 +flat_mae,reg,attn,hcpya_task21,best,14,0.015,0.05,48,"[50, 1.0]",validation,0.27482545375823975,0.984375,0.002024554893085694,0.9823737145403995,0.002525071194013464 +flat_mae,reg,attn,hcpya_task21,best,14,0.015,0.05,48,"[50, 1.0]",test,0.43538838624954224,0.975,0.0021804683894359185,0.9690875203539719,0.0029553282500794156 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..97ca26c8ef83235f705ea2de57d3422c14be55b8 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,hcpya_task21,last,19,0.0036,0.05,39,"[12, 1.0]",train,0.00016167439753189683,1.0,0.0,1.0,0.0 +flat_mae,reg,attn,hcpya_task21,last,19,0.0036,0.05,39,"[12, 1.0]",validation,0.07654120028018951,0.9841269841269841,0.0019163664438165467,0.9819471875116325,0.0024004891648264698 +flat_mae,reg,attn,hcpya_task21,last,19,0.0036,0.05,39,"[12, 1.0]",test,0.13080595433712006,0.9751984126984127,0.0020929904295098013,0.9694896154083872,0.0028537524361802306 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/log.txt b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..063e46ce47d1659a6c02e91082a0cd4361e2bc4f --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/log.txt @@ -0,0 +1,890 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:45:14 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 58.7M (58.7M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:09 lr: nan time: 3.3227 data: 2.9469 max mem: 4150 +train: [0] [ 20/400] eta: 0:03:24 lr: 0.000003 loss: 3.0524 (3.0538) grad: 0.1028 (0.1024) time: 0.4002 data: 0.0028 max mem: 4873 +train: [0] [ 40/400] eta: 0:02:42 lr: 0.000006 loss: 3.0431 (3.0347) grad: 0.0956 (0.0978) time: 0.3605 data: 0.0038 max mem: 4873 +train: [0] [ 60/400] eta: 0:02:22 lr: 0.000009 loss: 2.9852 (3.0107) grad: 0.0922 (0.0964) time: 0.3522 data: 0.0041 max mem: 4873 +train: [0] [ 80/400] eta: 0:02:07 lr: 0.000012 loss: 2.9177 (2.9811) grad: 0.0921 (0.0959) time: 0.3355 data: 0.0040 max mem: 4873 +train: [0] [100/400] eta: 0:01:56 lr: 0.000015 loss: 2.8443 (2.9459) grad: 0.0912 (0.0946) time: 0.3497 data: 0.0039 max mem: 4873 +train: [0] [120/400] eta: 0:01:47 lr: 0.000018 loss: 2.7413 (2.9041) grad: 0.0894 (0.0940) time: 0.3632 data: 0.0040 max mem: 4873 +train: [0] [140/400] eta: 0:01:39 lr: 0.000021 loss: 2.6452 (2.8589) grad: 0.0866 (0.0932) time: 0.3589 data: 0.0041 max mem: 4873 +train: [0] [160/400] eta: 0:01:30 lr: 0.000024 loss: 2.5310 (2.8153) grad: 0.0855 (0.0921) time: 0.3522 data: 0.0039 max mem: 4873 +train: [0] [180/400] eta: 0:01:22 lr: 0.000027 loss: 2.4544 (2.7660) grad: 0.0844 (0.0915) time: 0.3425 data: 0.0035 max mem: 4873 +train: [0] [200/400] eta: 0:01:14 lr: 0.000030 loss: 2.3177 (2.7187) grad: 0.0867 (0.0913) time: 0.3646 data: 0.0042 max mem: 4873 +train: [0] [220/400] eta: 0:01:06 lr: 0.000033 loss: 2.2706 (2.6747) grad: 0.0878 (0.0907) time: 0.3385 data: 0.0042 max mem: 4873 +train: [0] [240/400] eta: 0:00:58 lr: 0.000036 loss: 2.1803 (2.6308) grad: 0.0844 (0.0905) time: 0.3545 data: 0.0040 max mem: 4873 +train: [0] [260/400] eta: 0:00:51 lr: 0.000039 loss: 2.1171 (2.5882) grad: 0.0909 (0.0907) time: 0.3507 data: 0.0037 max mem: 4873 +train: [0] [280/400] eta: 0:00:43 lr: 0.000042 loss: 2.0709 (2.5501) grad: 0.0881 (0.0902) time: 0.3508 data: 0.0037 max mem: 4873 +train: [0] [300/400] eta: 0:00:37 lr: 0.000045 loss: 2.0123 (2.5126) grad: 0.0843 (0.0897) time: 0.5476 data: 0.1971 max mem: 4873 +train: [0] [320/400] eta: 0:00:30 lr: 0.000048 loss: 1.9611 (2.4765) grad: 0.0776 (0.0890) time: 0.3557 data: 0.0031 max mem: 4873 +train: [0] [340/400] eta: 0:00:22 lr: 0.000051 loss: 1.8992 (2.4404) grad: 0.0784 (0.0886) time: 0.3487 data: 0.0037 max mem: 4873 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 1.8555 (2.4072) grad: 0.0784 (0.0878) time: 0.3452 data: 0.0038 max mem: 4873 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 1.8069 (2.3741) grad: 0.0786 (0.0875) time: 0.3336 data: 0.0040 max mem: 4873 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 1.7686 (2.3424) grad: 0.0791 (0.0872) time: 0.3239 data: 0.0042 max mem: 4873 +train: [0] Total time: 0:02:27 (0.3694 s / it) +train: [0] Summary: lr: 0.000060 loss: 1.7686 (2.3424) grad: 0.0791 (0.0872) +eval (validation): [0] [ 0/63] eta: 0:03:05 time: 2.9494 data: 2.6980 max mem: 4873 +eval (validation): [0] [20/63] eta: 0:00:19 time: 0.3298 data: 0.0026 max mem: 4873 +eval (validation): [0] [40/63] eta: 0:00:08 time: 0.3035 data: 0.0034 max mem: 4873 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.2902 data: 0.0032 max mem: 4873 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.2908 data: 0.0034 max mem: 4873 +eval (validation): [0] Total time: 0:00:22 (0.3536 s / it) +cv: [0] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.096 acc: 0.970 f1: 0.964 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:19:39 lr: nan time: 2.9481 data: 2.7405 max mem: 4873 +train: [1] [ 20/400] eta: 0:02:58 lr: 0.000063 loss: 1.6953 (1.7017) grad: 0.0750 (0.0795) time: 0.3468 data: 0.0034 max mem: 4873 +train: [1] [ 40/400] eta: 0:02:28 lr: 0.000066 loss: 1.6873 (1.6844) grad: 0.0777 (0.0781) time: 0.3503 data: 0.0039 max mem: 4873 +train: [1] [ 60/400] eta: 0:02:10 lr: 0.000069 loss: 1.6413 (1.6643) grad: 0.0792 (0.0786) time: 0.3282 data: 0.0041 max mem: 4873 +train: [1] [ 80/400] eta: 0:01:58 lr: 0.000072 loss: 1.6028 (1.6447) grad: 0.0764 (0.0786) time: 0.3310 data: 0.0043 max mem: 4873 +train: [1] [100/400] eta: 0:01:48 lr: 0.000075 loss: 1.5796 (1.6284) grad: 0.0780 (0.0789) time: 0.3236 data: 0.0041 max mem: 4873 +train: [1] [120/400] eta: 0:01:39 lr: 0.000078 loss: 1.5443 (1.6128) grad: 0.0805 (0.0794) time: 0.3279 data: 0.0041 max mem: 4873 +train: [1] [140/400] eta: 0:01:31 lr: 0.000081 loss: 1.5223 (1.6027) grad: 0.0809 (0.0792) time: 0.3377 data: 0.0041 max mem: 4873 +train: [1] [160/400] eta: 0:01:24 lr: 0.000084 loss: 1.5115 (1.5898) grad: 0.0736 (0.0784) time: 0.3246 data: 0.0041 max mem: 4873 +train: [1] [180/400] eta: 0:01:16 lr: 0.000087 loss: 1.4804 (1.5758) grad: 0.0709 (0.0775) time: 0.3206 data: 0.0041 max mem: 4873 +train: [1] [200/400] eta: 0:01:08 lr: 0.000090 loss: 1.4728 (1.5654) grad: 0.0707 (0.0774) time: 0.3244 data: 0.0041 max mem: 4873 +train: [1] [220/400] eta: 0:01:01 lr: 0.000093 loss: 1.4394 (1.5524) grad: 0.0734 (0.0772) time: 0.3208 data: 0.0041 max mem: 4873 +train: [1] [240/400] eta: 0:00:54 lr: 0.000096 loss: 1.4057 (1.5384) grad: 0.0741 (0.0771) time: 0.3558 data: 0.0041 max mem: 4873 +train: [1] [260/400] eta: 0:00:48 lr: 0.000099 loss: 1.3651 (1.5252) grad: 0.0749 (0.0770) time: 0.3604 data: 0.0040 max mem: 4873 +train: [1] [280/400] eta: 0:00:41 lr: 0.000102 loss: 1.3467 (1.5129) grad: 0.0735 (0.0769) time: 0.3552 data: 0.0042 max mem: 4873 +train: [1] [300/400] eta: 0:00:35 lr: 0.000105 loss: 1.3380 (1.4996) grad: 0.0712 (0.0767) time: 0.5258 data: 0.1867 max mem: 4873 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 1.3014 (1.4880) grad: 0.0696 (0.0761) time: 0.4010 data: 0.0039 max mem: 4873 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 1.2790 (1.4749) grad: 0.0670 (0.0758) time: 0.3580 data: 0.0043 max mem: 4873 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 1.2613 (1.4632) grad: 0.0690 (0.0754) time: 0.3676 data: 0.0044 max mem: 4873 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 1.2488 (1.4514) grad: 0.0693 (0.0751) time: 0.3620 data: 0.0042 max mem: 4873 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 1.2304 (1.4409) grad: 0.0704 (0.0749) time: 0.3659 data: 0.0042 max mem: 4873 +train: [1] Total time: 0:02:24 (0.3612 s / it) +train: [1] Summary: lr: 0.000120 loss: 1.2304 (1.4409) grad: 0.0704 (0.0749) +eval (validation): [1] [ 0/63] eta: 0:03:09 time: 3.0112 data: 2.7725 max mem: 4873 +eval (validation): [1] [20/63] eta: 0:00:19 time: 0.3261 data: 0.0034 max mem: 4873 +eval (validation): [1] [40/63] eta: 0:00:08 time: 0.3123 data: 0.0030 max mem: 4873 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3074 data: 0.0035 max mem: 4873 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3072 data: 0.0035 max mem: 4873 +eval (validation): [1] Total time: 0:00:22 (0.3622 s / it) +cv: [1] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.084 acc: 0.972 f1: 0.967 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:02 lr: nan time: 3.3051 data: 3.0746 max mem: 4873 +train: [2] [ 20/400] eta: 0:03:19 lr: 0.000123 loss: 1.1930 (1.2039) grad: 0.0693 (0.0732) time: 0.3859 data: 0.0033 max mem: 4873 +train: [2] [ 40/400] eta: 0:02:41 lr: 0.000126 loss: 1.1888 (1.1861) grad: 0.0711 (0.0727) time: 0.3666 data: 0.0036 max mem: 4873 +train: [2] [ 60/400] eta: 0:02:21 lr: 0.000129 loss: 1.1882 (1.1887) grad: 0.0705 (0.0723) time: 0.3535 data: 0.0041 max mem: 4873 +train: [2] [ 80/400] eta: 0:02:09 lr: 0.000132 loss: 1.1805 (1.1778) grad: 0.0697 (0.0721) time: 0.3671 data: 0.0044 max mem: 4873 +train: [2] [100/400] eta: 0:01:58 lr: 0.000135 loss: 1.1404 (1.1707) grad: 0.0708 (0.0723) time: 0.3489 data: 0.0044 max mem: 4873 +train: [2] [120/400] eta: 0:01:48 lr: 0.000138 loss: 1.1169 (1.1593) grad: 0.0720 (0.0719) time: 0.3572 data: 0.0042 max mem: 4873 +train: [2] [140/400] eta: 0:01:39 lr: 0.000141 loss: 1.0984 (1.1481) grad: 0.0705 (0.0719) time: 0.3667 data: 0.0043 max mem: 4873 +train: [2] [160/400] eta: 0:01:31 lr: 0.000144 loss: 1.0731 (1.1393) grad: 0.0704 (0.0720) time: 0.3617 data: 0.0041 max mem: 4873 +train: [2] [180/400] eta: 0:01:23 lr: 0.000147 loss: 1.0614 (1.1326) grad: 0.0728 (0.0723) time: 0.3566 data: 0.0045 max mem: 4873 +train: [2] [200/400] eta: 0:01:15 lr: 0.000150 loss: 1.0614 (1.1264) grad: 0.0744 (0.0732) time: 0.3438 data: 0.0041 max mem: 4873 +train: [2] [220/400] eta: 0:01:06 lr: 0.000153 loss: 1.0197 (1.1152) grad: 0.0748 (0.0732) time: 0.3296 data: 0.0041 max mem: 4873 +train: [2] [240/400] eta: 0:00:59 lr: 0.000156 loss: 1.0139 (1.1098) grad: 0.0736 (0.0735) time: 0.3420 data: 0.0039 max mem: 4873 +train: [2] [260/400] eta: 0:00:51 lr: 0.000159 loss: 1.0319 (1.1044) grad: 0.0754 (0.0737) time: 0.3678 data: 0.0044 max mem: 4873 +train: [2] [280/400] eta: 0:00:44 lr: 0.000162 loss: 1.0319 (1.0989) grad: 0.0780 (0.0746) time: 0.3583 data: 0.0044 max mem: 4873 +train: [2] [300/400] eta: 0:00:37 lr: 0.000165 loss: 1.0006 (1.0928) grad: 0.0819 (0.0750) time: 0.5148 data: 0.1801 max mem: 4873 +train: [2] [320/400] eta: 0:00:30 lr: 0.000168 loss: 0.9839 (1.0853) grad: 0.0825 (0.0757) time: 0.3630 data: 0.0030 max mem: 4873 +train: [2] [340/400] eta: 0:00:22 lr: 0.000171 loss: 0.9669 (1.0789) grad: 0.0834 (0.0763) time: 0.3618 data: 0.0033 max mem: 4873 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 0.9772 (1.0732) grad: 0.0902 (0.0777) time: 0.3511 data: 0.0041 max mem: 4873 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 0.9552 (1.0663) grad: 0.0919 (0.0783) time: 0.3635 data: 0.0039 max mem: 4873 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 0.9336 (1.0602) grad: 0.0920 (0.0798) time: 0.3599 data: 0.0041 max mem: 4873 +train: [2] Total time: 0:02:29 (0.3739 s / it) +train: [2] Summary: lr: 0.000180 loss: 0.9336 (1.0602) grad: 0.0920 (0.0798) +eval (validation): [2] [ 0/63] eta: 0:03:04 time: 2.9311 data: 2.7309 max mem: 4873 +eval (validation): [2] [20/63] eta: 0:00:19 time: 0.3205 data: 0.0039 max mem: 4873 +eval (validation): [2] [40/63] eta: 0:00:08 time: 0.3042 data: 0.0034 max mem: 4873 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3037 data: 0.0038 max mem: 4873 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3017 data: 0.0037 max mem: 4873 +eval (validation): [2] Total time: 0:00:22 (0.3565 s / it) +cv: [2] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 0.090 acc: 0.976 f1: 0.974 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:54 lr: nan time: 3.4360 data: 3.1922 max mem: 4873 +train: [3] [ 20/400] eta: 0:03:27 lr: 0.000183 loss: 0.9356 (0.9574) grad: 0.0981 (0.1060) time: 0.4021 data: 0.0038 max mem: 4873 +train: [3] [ 40/400] eta: 0:02:43 lr: 0.000186 loss: 0.9330 (0.9408) grad: 0.0981 (0.1040) time: 0.3561 data: 0.0033 max mem: 4873 +train: [3] [ 60/400] eta: 0:02:24 lr: 0.000189 loss: 0.9167 (0.9371) grad: 0.1045 (0.1057) time: 0.3675 data: 0.0041 max mem: 4873 +train: [3] [ 80/400] eta: 0:02:10 lr: 0.000192 loss: 0.9167 (0.9293) grad: 0.1082 (0.1099) time: 0.3483 data: 0.0044 max mem: 4873 +train: [3] [100/400] eta: 0:01:58 lr: 0.000195 loss: 0.9092 (0.9296) grad: 0.1232 (0.1146) time: 0.3529 data: 0.0042 max mem: 4873 +train: [3] [120/400] eta: 0:01:48 lr: 0.000198 loss: 0.8941 (0.9227) grad: 0.1264 (0.1165) time: 0.3513 data: 0.0042 max mem: 4873 +train: [3] [140/400] eta: 0:01:39 lr: 0.000201 loss: 0.8335 (0.9126) grad: 0.1140 (0.1155) time: 0.3609 data: 0.0042 max mem: 4873 +train: [3] [160/400] eta: 0:01:31 lr: 0.000204 loss: 0.8335 (0.9104) grad: 0.0993 (0.1149) time: 0.3629 data: 0.0040 max mem: 4873 +train: [3] [180/400] eta: 0:01:23 lr: 0.000207 loss: 0.8928 (0.9166) grad: 0.1209 (0.1178) time: 0.3639 data: 0.0042 max mem: 4873 +train: [3] [200/400] eta: 0:01:15 lr: 0.000210 loss: 0.9052 (0.9171) grad: 0.1247 (0.1194) time: 0.3574 data: 0.0045 max mem: 4873 +train: [3] [220/400] eta: 0:01:07 lr: 0.000213 loss: 0.8886 (0.9126) grad: 0.1209 (0.1191) time: 0.3423 data: 0.0042 max mem: 4873 +train: [3] [240/400] eta: 0:00:59 lr: 0.000216 loss: 0.8911 (0.9113) grad: 0.1152 (0.1196) time: 0.3349 data: 0.0043 max mem: 4873 +train: [3] [260/400] eta: 0:00:52 lr: 0.000219 loss: 0.8911 (0.9089) grad: 0.1211 (0.1199) time: 0.3760 data: 0.0047 max mem: 4873 +train: [3] [280/400] eta: 0:00:44 lr: 0.000222 loss: 0.7967 (0.9034) grad: 0.1211 (0.1204) time: 0.3624 data: 0.0042 max mem: 4873 +train: [3] [300/400] eta: 0:00:38 lr: 0.000225 loss: 0.8437 (0.9041) grad: 0.1248 (0.1214) time: 0.5200 data: 0.1820 max mem: 4873 +train: [3] [320/400] eta: 0:00:30 lr: 0.000228 loss: 0.8066 (0.8965) grad: 0.1223 (0.1219) time: 0.3940 data: 0.0037 max mem: 4873 +train: [3] [340/400] eta: 0:00:22 lr: 0.000231 loss: 0.8029 (0.8931) grad: 0.1190 (0.1226) time: 0.3498 data: 0.0039 max mem: 4873 +train: [3] [360/400] eta: 0:00:15 lr: 0.000234 loss: 0.8023 (0.8892) grad: 0.1253 (0.1233) time: 0.3561 data: 0.0043 max mem: 4873 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 0.8081 (0.8861) grad: 0.1253 (0.1235) time: 0.3678 data: 0.0041 max mem: 4873 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 0.8081 (0.8814) grad: 0.1198 (0.1239) time: 0.3546 data: 0.0043 max mem: 4873 +train: [3] Total time: 0:02:30 (0.3773 s / it) +train: [3] Summary: lr: 0.000240 loss: 0.8081 (0.8814) grad: 0.1198 (0.1239) +eval (validation): [3] [ 0/63] eta: 0:03:08 time: 2.9899 data: 2.7934 max mem: 4873 +eval (validation): [3] [20/63] eta: 0:00:20 time: 0.3436 data: 0.0039 max mem: 4873 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3450 data: 0.0031 max mem: 4873 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3163 data: 0.0037 max mem: 4873 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3129 data: 0.0037 max mem: 4873 +eval (validation): [3] Total time: 0:00:24 (0.3810 s / it) +cv: [3] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 0.074 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:23:01 lr: nan time: 3.4544 data: 3.2079 max mem: 4873 +train: [4] [ 20/400] eta: 0:03:14 lr: 0.000243 loss: 0.7341 (0.7624) grad: 0.1740 (0.1628) time: 0.3636 data: 0.0026 max mem: 4873 +train: [4] [ 40/400] eta: 0:02:37 lr: 0.000246 loss: 0.7590 (0.7952) grad: 0.1702 (0.1623) time: 0.3627 data: 0.0038 max mem: 4873 +train: [4] [ 60/400] eta: 0:02:19 lr: 0.000249 loss: 0.7729 (0.7861) grad: 0.1436 (0.1548) time: 0.3561 data: 0.0041 max mem: 4873 +train: [4] [ 80/400] eta: 0:02:07 lr: 0.000252 loss: 0.7615 (0.7801) grad: 0.1304 (0.1530) time: 0.3598 data: 0.0044 max mem: 4873 +train: [4] [100/400] eta: 0:01:57 lr: 0.000255 loss: 0.7615 (0.7788) grad: 0.1255 (0.1482) time: 0.3625 data: 0.0040 max mem: 4873 +train: [4] [120/400] eta: 0:01:48 lr: 0.000258 loss: 0.7738 (0.7882) grad: 0.1382 (0.1493) time: 0.3695 data: 0.0044 max mem: 4873 +train: [4] [140/400] eta: 0:01:39 lr: 0.000261 loss: 0.8044 (0.7933) grad: 0.1436 (0.1492) time: 0.3584 data: 0.0041 max mem: 4873 +train: [4] [160/400] eta: 0:01:31 lr: 0.000264 loss: 0.7261 (0.7883) grad: 0.1447 (0.1515) time: 0.3541 data: 0.0046 max mem: 4873 +train: [4] [180/400] eta: 0:01:23 lr: 0.000267 loss: 0.7654 (0.7922) grad: 0.1598 (0.1533) time: 0.3603 data: 0.0041 max mem: 4873 +train: [4] [200/400] eta: 0:01:15 lr: 0.000270 loss: 0.7654 (0.7915) grad: 0.1598 (0.1542) time: 0.3643 data: 0.0041 max mem: 4873 +train: [4] [220/400] eta: 0:01:07 lr: 0.000273 loss: 0.7544 (0.7913) grad: 0.1576 (0.1548) time: 0.3540 data: 0.0038 max mem: 4873 +train: [4] [240/400] eta: 0:00:59 lr: 0.000276 loss: 0.7600 (0.7881) grad: 0.1610 (0.1569) time: 0.3376 data: 0.0043 max mem: 4873 +train: [4] [260/400] eta: 0:00:51 lr: 0.000279 loss: 0.7390 (0.7856) grad: 0.1557 (0.1573) time: 0.3344 data: 0.0039 max mem: 4873 +train: [4] [280/400] eta: 0:00:44 lr: 0.000282 loss: 0.7595 (0.7920) grad: 0.1535 (0.1573) time: 0.3521 data: 0.0041 max mem: 4873 +train: [4] [300/400] eta: 0:00:37 lr: 0.000285 loss: 0.7849 (0.7934) grad: 0.1579 (0.1585) time: 0.5099 data: 0.1787 max mem: 4873 +train: [4] [320/400] eta: 0:00:30 lr: 0.000288 loss: 0.7192 (0.7867) grad: 0.1587 (0.1587) time: 0.3986 data: 0.0040 max mem: 4873 +train: [4] [340/400] eta: 0:00:22 lr: 0.000291 loss: 0.6895 (0.7807) grad: 0.1515 (0.1582) time: 0.3560 data: 0.0042 max mem: 4873 +train: [4] [360/400] eta: 0:00:15 lr: 0.000294 loss: 0.6425 (0.7766) grad: 0.1492 (0.1573) time: 0.3552 data: 0.0040 max mem: 4873 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 0.6651 (0.7727) grad: 0.1492 (0.1572) time: 0.3573 data: 0.0040 max mem: 4873 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 0.6463 (0.7662) grad: 0.1454 (0.1569) time: 0.3388 data: 0.0041 max mem: 4873 +train: [4] Total time: 0:02:29 (0.3736 s / it) +train: [4] Summary: lr: 0.000300 loss: 0.6463 (0.7662) grad: 0.1454 (0.1569) +eval (validation): [4] [ 0/63] eta: 0:03:16 time: 3.1184 data: 2.8723 max mem: 4873 +eval (validation): [4] [20/63] eta: 0:00:21 time: 0.3794 data: 0.0038 max mem: 4873 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3446 data: 0.0033 max mem: 4873 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3028 data: 0.0034 max mem: 4873 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3013 data: 0.0032 max mem: 4873 +eval (validation): [4] Total time: 0:00:24 (0.3895 s / it) +cv: [4] best hparam: (4.3, 1.0) (033) ('033_lr4.3e+00_wd1.0e+00') loss: 0.071 acc: 0.977 f1: 0.975 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:27 lr: nan time: 3.3692 data: 3.0663 max mem: 4873 +train: [5] [ 20/400] eta: 0:03:19 lr: 0.000300 loss: 0.7125 (0.7330) grad: 0.1626 (0.1801) time: 0.3834 data: 0.0043 max mem: 4873 +train: [5] [ 40/400] eta: 0:02:41 lr: 0.000300 loss: 0.6912 (0.7036) grad: 0.1557 (0.1666) time: 0.3687 data: 0.0034 max mem: 4873 +train: [5] [ 60/400] eta: 0:02:24 lr: 0.000300 loss: 0.6640 (0.6940) grad: 0.1519 (0.1626) time: 0.3718 data: 0.0046 max mem: 4873 +train: [5] [ 80/400] eta: 0:02:10 lr: 0.000300 loss: 0.7068 (0.7191) grad: 0.1661 (0.1646) time: 0.3614 data: 0.0046 max mem: 4873 +train: [5] [100/400] eta: 0:02:00 lr: 0.000300 loss: 0.7381 (0.7244) grad: 0.1700 (0.1671) time: 0.3668 data: 0.0045 max mem: 4873 +train: [5] [120/400] eta: 0:01:50 lr: 0.000300 loss: 0.7244 (0.7205) grad: 0.1589 (0.1643) time: 0.3669 data: 0.0045 max mem: 4873 +train: [5] [140/400] eta: 0:01:41 lr: 0.000300 loss: 0.6381 (0.7064) grad: 0.1415 (0.1614) time: 0.3625 data: 0.0043 max mem: 4873 +train: [5] [160/400] eta: 0:01:32 lr: 0.000299 loss: 0.6267 (0.6960) grad: 0.1367 (0.1585) time: 0.3609 data: 0.0043 max mem: 4873 +train: [5] [180/400] eta: 0:01:24 lr: 0.000299 loss: 0.6601 (0.6963) grad: 0.1586 (0.1590) time: 0.3630 data: 0.0041 max mem: 4873 +train: [5] [200/400] eta: 0:01:16 lr: 0.000299 loss: 0.6710 (0.6921) grad: 0.1597 (0.1586) time: 0.3650 data: 0.0040 max mem: 4873 +train: [5] [220/400] eta: 0:01:08 lr: 0.000299 loss: 0.7240 (0.6960) grad: 0.1485 (0.1570) time: 0.3504 data: 0.0045 max mem: 4873 +train: [5] [240/400] eta: 0:01:00 lr: 0.000299 loss: 0.6428 (0.6895) grad: 0.1446 (0.1567) time: 0.3351 data: 0.0039 max mem: 4873 +train: [5] [260/400] eta: 0:00:52 lr: 0.000299 loss: 0.5880 (0.6817) grad: 0.1431 (0.1560) time: 0.3300 data: 0.0041 max mem: 4873 +train: [5] [280/400] eta: 0:00:44 lr: 0.000298 loss: 0.6176 (0.6778) grad: 0.1431 (0.1553) time: 0.3583 data: 0.0044 max mem: 4873 +train: [5] [300/400] eta: 0:00:38 lr: 0.000298 loss: 0.5791 (0.6702) grad: 0.1352 (0.1533) time: 0.5256 data: 0.1862 max mem: 4873 +train: [5] [320/400] eta: 0:00:30 lr: 0.000298 loss: 0.5598 (0.6645) grad: 0.1269 (0.1517) time: 0.3694 data: 0.0033 max mem: 4873 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 0.5598 (0.6585) grad: 0.1127 (0.1494) time: 0.3599 data: 0.0039 max mem: 4873 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 0.4986 (0.6506) grad: 0.1049 (0.1470) time: 0.3855 data: 0.0045 max mem: 4873 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 0.4632 (0.6433) grad: 0.1100 (0.1454) time: 0.3527 data: 0.0037 max mem: 4873 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 0.4744 (0.6360) grad: 0.1129 (0.1446) time: 0.3455 data: 0.0042 max mem: 4873 +train: [5] Total time: 0:02:30 (0.3772 s / it) +train: [5] Summary: lr: 0.000297 loss: 0.4744 (0.6360) grad: 0.1129 (0.1446) +eval (validation): [5] [ 0/63] eta: 0:03:17 time: 3.1391 data: 2.8907 max mem: 4873 +eval (validation): [5] [20/63] eta: 0:00:22 time: 0.3856 data: 0.0036 max mem: 4873 +eval (validation): [5] [40/63] eta: 0:00:10 time: 0.3589 data: 0.0035 max mem: 4873 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3155 data: 0.0033 max mem: 4873 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3133 data: 0.0034 max mem: 4873 +eval (validation): [5] Total time: 0:00:25 (0.4010 s / it) +cv: [5] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 0.077 acc: 0.980 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:28:14 lr: nan time: 4.2361 data: 3.9789 max mem: 4873 +train: [6] [ 20/400] eta: 0:03:29 lr: 0.000296 loss: 0.4611 (0.5097) grad: 0.1223 (0.1277) time: 0.3671 data: 0.0029 max mem: 4873 +train: [6] [ 40/400] eta: 0:02:45 lr: 0.000296 loss: 0.4874 (0.5011) grad: 0.1108 (0.1169) time: 0.3656 data: 0.0033 max mem: 4873 +train: [6] [ 60/400] eta: 0:02:25 lr: 0.000296 loss: 0.4897 (0.5242) grad: 0.1020 (0.1145) time: 0.3593 data: 0.0044 max mem: 4873 +train: [6] [ 80/400] eta: 0:02:10 lr: 0.000295 loss: 0.4864 (0.5280) grad: 0.1236 (0.1172) time: 0.3440 data: 0.0040 max mem: 4873 +train: [6] [100/400] eta: 0:01:59 lr: 0.000295 loss: 0.4864 (0.5280) grad: 0.1236 (0.1178) time: 0.3717 data: 0.0042 max mem: 4873 +train: [6] [120/400] eta: 0:01:50 lr: 0.000295 loss: 0.4796 (0.5194) grad: 0.1112 (0.1152) time: 0.3626 data: 0.0043 max mem: 4873 +train: [6] [140/400] eta: 0:01:40 lr: 0.000294 loss: 0.4796 (0.5195) grad: 0.0962 (0.1139) time: 0.3544 data: 0.0041 max mem: 4873 +train: [6] [160/400] eta: 0:01:32 lr: 0.000294 loss: 0.4805 (0.5163) grad: 0.1129 (0.1154) time: 0.3602 data: 0.0044 max mem: 4873 +train: [6] [180/400] eta: 0:01:24 lr: 0.000293 loss: 0.4506 (0.5125) grad: 0.1154 (0.1153) time: 0.3621 data: 0.0045 max mem: 4873 +train: [6] [200/400] eta: 0:01:15 lr: 0.000293 loss: 0.4821 (0.5145) grad: 0.1266 (0.1171) time: 0.3433 data: 0.0041 max mem: 4873 +train: [6] [220/400] eta: 0:01:07 lr: 0.000292 loss: 0.5066 (0.5131) grad: 0.1266 (0.1181) time: 0.3646 data: 0.0046 max mem: 4873 +train: [6] [240/400] eta: 0:00:59 lr: 0.000292 loss: 0.5059 (0.5109) grad: 0.1228 (0.1187) time: 0.3477 data: 0.0041 max mem: 4873 +train: [6] [260/400] eta: 0:00:52 lr: 0.000291 loss: 0.4461 (0.5098) grad: 0.1133 (0.1184) time: 0.3332 data: 0.0043 max mem: 4873 +train: [6] [280/400] eta: 0:00:44 lr: 0.000291 loss: 0.4184 (0.5047) grad: 0.1088 (0.1183) time: 0.3496 data: 0.0043 max mem: 4873 +train: [6] [300/400] eta: 0:00:38 lr: 0.000290 loss: 0.4313 (0.5016) grad: 0.1075 (0.1177) time: 0.5558 data: 0.1788 max mem: 4873 +train: [6] [320/400] eta: 0:00:30 lr: 0.000290 loss: 0.4505 (0.4988) grad: 0.1036 (0.1171) time: 0.3823 data: 0.0036 max mem: 4873 +train: [6] [340/400] eta: 0:00:22 lr: 0.000289 loss: 0.4214 (0.4971) grad: 0.1074 (0.1170) time: 0.3664 data: 0.0044 max mem: 4873 +train: [6] [360/400] eta: 0:00:15 lr: 0.000288 loss: 0.4069 (0.4931) grad: 0.1016 (0.1162) time: 0.3644 data: 0.0043 max mem: 4873 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 0.4063 (0.4897) grad: 0.1016 (0.1165) time: 0.3499 data: 0.0044 max mem: 4873 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 0.3894 (0.4852) grad: 0.1115 (0.1161) time: 0.3336 data: 0.0044 max mem: 4873 +train: [6] Total time: 0:02:30 (0.3771 s / it) +train: [6] Summary: lr: 0.000287 loss: 0.3894 (0.4852) grad: 0.1115 (0.1161) +eval (validation): [6] [ 0/63] eta: 0:03:33 time: 3.3940 data: 3.1021 max mem: 4873 +eval (validation): [6] [20/63] eta: 0:00:22 time: 0.3807 data: 0.0052 max mem: 4873 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3360 data: 0.0033 max mem: 4873 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3199 data: 0.0033 max mem: 4873 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3209 data: 0.0035 max mem: 4873 +eval (validation): [6] Total time: 0:00:25 (0.3978 s / it) +cv: [6] best hparam: (1.9, 1.0) (028) ('028_lr1.9e+00_wd1.0e+00') loss: 0.066 acc: 0.980 f1: 0.978 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:22:39 lr: nan time: 3.3979 data: 3.1438 max mem: 4873 +train: [7] [ 20/400] eta: 0:03:21 lr: 0.000286 loss: 0.3802 (0.4099) grad: 0.0856 (0.0945) time: 0.3870 data: 0.0030 max mem: 4873 +train: [7] [ 40/400] eta: 0:02:41 lr: 0.000286 loss: 0.3873 (0.4145) grad: 0.0856 (0.0916) time: 0.3627 data: 0.0041 max mem: 4873 +train: [7] [ 60/400] eta: 0:02:25 lr: 0.000285 loss: 0.3906 (0.4145) grad: 0.0884 (0.0953) time: 0.3822 data: 0.0042 max mem: 4873 +train: [7] [ 80/400] eta: 0:02:12 lr: 0.000284 loss: 0.3900 (0.4157) grad: 0.0930 (0.0936) time: 0.3706 data: 0.0043 max mem: 4873 +train: [7] [100/400] eta: 0:02:01 lr: 0.000284 loss: 0.3751 (0.4103) grad: 0.0840 (0.0952) time: 0.3649 data: 0.0040 max mem: 4873 +train: [7] [120/400] eta: 0:01:51 lr: 0.000283 loss: 0.3778 (0.4076) grad: 0.0846 (0.0933) time: 0.3638 data: 0.0044 max mem: 4873 +train: [7] [140/400] eta: 0:01:42 lr: 0.000282 loss: 0.3778 (0.4046) grad: 0.0879 (0.0934) time: 0.3668 data: 0.0041 max mem: 4873 +train: [7] [160/400] eta: 0:01:33 lr: 0.000282 loss: 0.3889 (0.4050) grad: 0.0879 (0.0928) time: 0.3682 data: 0.0040 max mem: 4873 +train: [7] [180/400] eta: 0:01:24 lr: 0.000281 loss: 0.3961 (0.4020) grad: 0.0829 (0.0921) time: 0.3557 data: 0.0040 max mem: 4873 +train: [7] [200/400] eta: 0:01:16 lr: 0.000280 loss: 0.3669 (0.3990) grad: 0.0810 (0.0917) time: 0.3391 data: 0.0038 max mem: 4873 +train: [7] [220/400] eta: 0:01:08 lr: 0.000279 loss: 0.3837 (0.4012) grad: 0.0850 (0.0933) time: 0.3479 data: 0.0045 max mem: 4873 +train: [7] [240/400] eta: 0:01:00 lr: 0.000278 loss: 0.3606 (0.3985) grad: 0.0998 (0.0934) time: 0.3585 data: 0.0039 max mem: 4873 +train: [7] [260/400] eta: 0:00:52 lr: 0.000278 loss: 0.3606 (0.3993) grad: 0.0998 (0.0951) time: 0.3353 data: 0.0037 max mem: 4873 +train: [7] [280/400] eta: 0:00:44 lr: 0.000277 loss: 0.3827 (0.3987) grad: 0.1079 (0.0958) time: 0.3350 data: 0.0043 max mem: 4873 +train: [7] [300/400] eta: 0:00:38 lr: 0.000276 loss: 0.3732 (0.3977) grad: 0.0999 (0.0964) time: 0.5623 data: 0.1895 max mem: 4873 +train: [7] [320/400] eta: 0:00:30 lr: 0.000275 loss: 0.3382 (0.3939) grad: 0.0892 (0.0956) time: 0.3564 data: 0.0035 max mem: 4873 +train: [7] [340/400] eta: 0:00:22 lr: 0.000274 loss: 0.3406 (0.3918) grad: 0.0850 (0.0950) time: 0.3606 data: 0.0043 max mem: 4873 +train: [7] [360/400] eta: 0:00:15 lr: 0.000273 loss: 0.3253 (0.3871) grad: 0.0791 (0.0939) time: 0.3700 data: 0.0042 max mem: 4873 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 0.3104 (0.3837) grad: 0.0732 (0.0930) time: 0.3538 data: 0.0040 max mem: 4873 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 0.3475 (0.3827) grad: 0.0874 (0.0929) time: 0.3323 data: 0.0044 max mem: 4873 +train: [7] Total time: 0:02:30 (0.3768 s / it) +train: [7] Summary: lr: 0.000271 loss: 0.3475 (0.3827) grad: 0.0874 (0.0929) +eval (validation): [7] [ 0/63] eta: 0:03:38 time: 3.4729 data: 3.1789 max mem: 4873 +eval (validation): [7] [20/63] eta: 0:00:21 time: 0.3419 data: 0.0036 max mem: 4873 +eval (validation): [7] [40/63] eta: 0:00:09 time: 0.3212 data: 0.0029 max mem: 4873 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3332 data: 0.0031 max mem: 4873 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3305 data: 0.0032 max mem: 4873 +eval (validation): [7] Total time: 0:00:24 (0.3860 s / it) +cv: [7] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 0.061 acc: 0.981 f1: 0.980 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:22:40 lr: nan time: 3.4008 data: 3.0965 max mem: 4873 +train: [8] [ 20/400] eta: 0:03:14 lr: 0.000270 loss: 0.3054 (0.3102) grad: 0.0729 (0.0733) time: 0.3663 data: 0.0038 max mem: 4873 +train: [8] [ 40/400] eta: 0:02:40 lr: 0.000270 loss: 0.3217 (0.3337) grad: 0.0757 (0.0821) time: 0.3770 data: 0.0035 max mem: 4873 +train: [8] [ 60/400] eta: 0:02:22 lr: 0.000269 loss: 0.3265 (0.3446) grad: 0.0889 (0.0828) time: 0.3646 data: 0.0041 max mem: 4873 +train: [8] [ 80/400] eta: 0:02:09 lr: 0.000268 loss: 0.3265 (0.3459) grad: 0.0842 (0.0852) time: 0.3625 data: 0.0045 max mem: 4873 +train: [8] [100/400] eta: 0:01:59 lr: 0.000267 loss: 0.3224 (0.3408) grad: 0.0837 (0.0841) time: 0.3628 data: 0.0043 max mem: 4873 +train: [8] [120/400] eta: 0:01:49 lr: 0.000266 loss: 0.3150 (0.3367) grad: 0.0740 (0.0831) time: 0.3561 data: 0.0043 max mem: 4873 +train: [8] [140/400] eta: 0:01:40 lr: 0.000265 loss: 0.3091 (0.3328) grad: 0.0725 (0.0822) time: 0.3602 data: 0.0042 max mem: 4873 +train: [8] [160/400] eta: 0:01:32 lr: 0.000264 loss: 0.2884 (0.3276) grad: 0.0687 (0.0801) time: 0.3693 data: 0.0042 max mem: 4873 +train: [8] [180/400] eta: 0:01:23 lr: 0.000263 loss: 0.3105 (0.3275) grad: 0.0687 (0.0801) time: 0.3582 data: 0.0040 max mem: 4873 +train: [8] [200/400] eta: 0:01:15 lr: 0.000262 loss: 0.3321 (0.3296) grad: 0.0780 (0.0807) time: 0.3447 data: 0.0042 max mem: 4873 +train: [8] [220/400] eta: 0:01:07 lr: 0.000260 loss: 0.3321 (0.3295) grad: 0.0737 (0.0803) time: 0.3562 data: 0.0042 max mem: 4873 +train: [8] [240/400] eta: 0:00:59 lr: 0.000259 loss: 0.3138 (0.3278) grad: 0.0739 (0.0800) time: 0.3611 data: 0.0039 max mem: 4873 +train: [8] [260/400] eta: 0:00:52 lr: 0.000258 loss: 0.3053 (0.3270) grad: 0.0809 (0.0799) time: 0.3725 data: 0.0040 max mem: 4873 +train: [8] [280/400] eta: 0:00:44 lr: 0.000257 loss: 0.2872 (0.3264) grad: 0.0691 (0.0793) time: 0.3575 data: 0.0040 max mem: 4873 +train: [8] [300/400] eta: 0:00:38 lr: 0.000256 loss: 0.2903 (0.3250) grad: 0.0727 (0.0792) time: 0.5450 data: 0.1822 max mem: 4873 +train: [8] [320/400] eta: 0:00:30 lr: 0.000255 loss: 0.2916 (0.3251) grad: 0.0727 (0.0787) time: 0.3546 data: 0.0039 max mem: 4873 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 0.2960 (0.3236) grad: 0.0617 (0.0780) time: 0.3659 data: 0.0042 max mem: 4873 +train: [8] [360/400] eta: 0:00:15 lr: 0.000253 loss: 0.2960 (0.3221) grad: 0.0673 (0.0775) time: 0.3653 data: 0.0042 max mem: 4873 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 0.2916 (0.3201) grad: 0.0719 (0.0770) time: 0.3573 data: 0.0040 max mem: 4873 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 0.2683 (0.3177) grad: 0.0708 (0.0767) time: 0.3446 data: 0.0044 max mem: 4873 +train: [8] Total time: 0:02:31 (0.3782 s / it) +train: [8] Summary: lr: 0.000250 loss: 0.2683 (0.3177) grad: 0.0708 (0.0767) +eval (validation): [8] [ 0/63] eta: 0:03:36 time: 3.4442 data: 3.1622 max mem: 4873 +eval (validation): [8] [20/63] eta: 0:00:23 time: 0.3916 data: 0.0041 max mem: 4873 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3335 data: 0.0034 max mem: 4873 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3096 data: 0.0034 max mem: 4873 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3079 data: 0.0031 max mem: 4873 +eval (validation): [8] Total time: 0:00:25 (0.3982 s / it) +cv: [8] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 0.123 acc: 0.980 f1: 0.978 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:21 lr: nan time: 3.3537 data: 3.0729 max mem: 4873 +train: [9] [ 20/400] eta: 0:03:19 lr: 0.000249 loss: 0.2593 (0.2751) grad: 0.0680 (0.0700) time: 0.3826 data: 0.0328 max mem: 4873 +train: [9] [ 40/400] eta: 0:02:40 lr: 0.000248 loss: 0.2593 (0.2813) grad: 0.0669 (0.0700) time: 0.3662 data: 0.0034 max mem: 4873 +train: [9] [ 60/400] eta: 0:02:22 lr: 0.000247 loss: 0.2732 (0.2842) grad: 0.0669 (0.0725) time: 0.3588 data: 0.0030 max mem: 4873 +train: [9] [ 80/400] eta: 0:02:08 lr: 0.000246 loss: 0.2748 (0.2847) grad: 0.0736 (0.0721) time: 0.3513 data: 0.0037 max mem: 4873 +train: [9] [100/400] eta: 0:01:58 lr: 0.000244 loss: 0.2750 (0.2834) grad: 0.0667 (0.0715) time: 0.3645 data: 0.0044 max mem: 4873 +train: [9] [120/400] eta: 0:01:49 lr: 0.000243 loss: 0.2773 (0.2828) grad: 0.0665 (0.0715) time: 0.3645 data: 0.0042 max mem: 4873 +train: [9] [140/400] eta: 0:01:40 lr: 0.000242 loss: 0.2643 (0.2825) grad: 0.0668 (0.0706) time: 0.3595 data: 0.0042 max mem: 4873 +train: [9] [160/400] eta: 0:01:31 lr: 0.000241 loss: 0.2567 (0.2802) grad: 0.0668 (0.0698) time: 0.3565 data: 0.0041 max mem: 4873 +train: [9] [180/400] eta: 0:01:23 lr: 0.000240 loss: 0.2556 (0.2770) grad: 0.0642 (0.0693) time: 0.3665 data: 0.0042 max mem: 4873 +train: [9] [200/400] eta: 0:01:15 lr: 0.000238 loss: 0.2535 (0.2763) grad: 0.0616 (0.0696) time: 0.3420 data: 0.0040 max mem: 4873 +train: [9] [220/400] eta: 0:01:07 lr: 0.000237 loss: 0.2617 (0.2752) grad: 0.0715 (0.0699) time: 0.3582 data: 0.0044 max mem: 4873 +train: [9] [240/400] eta: 0:00:59 lr: 0.000236 loss: 0.2454 (0.2725) grad: 0.0694 (0.0693) time: 0.3620 data: 0.0041 max mem: 4873 +train: [9] [260/400] eta: 0:00:52 lr: 0.000234 loss: 0.2426 (0.2720) grad: 0.0676 (0.0701) time: 0.3619 data: 0.0041 max mem: 4873 +train: [9] [280/400] eta: 0:00:44 lr: 0.000233 loss: 0.2565 (0.2719) grad: 0.0730 (0.0703) time: 0.3425 data: 0.0042 max mem: 4873 +train: [9] [300/400] eta: 0:00:38 lr: 0.000232 loss: 0.2565 (0.2727) grad: 0.0678 (0.0704) time: 0.5225 data: 0.1758 max mem: 4873 +train: [9] [320/400] eta: 0:00:30 lr: 0.000230 loss: 0.2550 (0.2728) grad: 0.0668 (0.0705) time: 0.3816 data: 0.0043 max mem: 4873 +train: [9] [340/400] eta: 0:00:22 lr: 0.000229 loss: 0.2550 (0.2713) grad: 0.0605 (0.0696) time: 0.3382 data: 0.0040 max mem: 4873 +train: [9] [360/400] eta: 0:00:15 lr: 0.000228 loss: 0.2396 (0.2695) grad: 0.0565 (0.0691) time: 0.3393 data: 0.0038 max mem: 4873 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 0.2390 (0.2680) grad: 0.0542 (0.0686) time: 0.3468 data: 0.0040 max mem: 4873 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.2490 (0.2675) grad: 0.0542 (0.0681) time: 0.3394 data: 0.0043 max mem: 4873 +train: [9] Total time: 0:02:29 (0.3733 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.2490 (0.2675) grad: 0.0542 (0.0681) +eval (validation): [9] [ 0/63] eta: 0:03:38 time: 3.4749 data: 3.1796 max mem: 4873 +eval (validation): [9] [20/63] eta: 0:00:22 time: 0.3691 data: 0.0039 max mem: 4873 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3194 data: 0.0026 max mem: 4873 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3172 data: 0.0035 max mem: 4873 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3176 data: 0.0034 max mem: 4873 +eval (validation): [9] Total time: 0:00:24 (0.3891 s / it) +cv: [9] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 0.118 acc: 0.982 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:22:40 lr: nan time: 3.4016 data: 3.1556 max mem: 4873 +train: [10] [ 20/400] eta: 0:03:11 lr: 0.000224 loss: 0.2367 (0.2482) grad: 0.0601 (0.0631) time: 0.3591 data: 0.0029 max mem: 4873 +train: [10] [ 40/400] eta: 0:02:33 lr: 0.000222 loss: 0.2297 (0.2386) grad: 0.0563 (0.0581) time: 0.3461 data: 0.0034 max mem: 4873 +train: [10] [ 60/400] eta: 0:02:15 lr: 0.000221 loss: 0.2266 (0.2396) grad: 0.0547 (0.0579) time: 0.3439 data: 0.0041 max mem: 4873 +train: [10] [ 80/400] eta: 0:02:05 lr: 0.000220 loss: 0.2333 (0.2403) grad: 0.0554 (0.0579) time: 0.3681 data: 0.0043 max mem: 4873 +train: [10] [100/400] eta: 0:01:56 lr: 0.000218 loss: 0.2433 (0.2399) grad: 0.0552 (0.0584) time: 0.3674 data: 0.0042 max mem: 4873 +train: [10] [120/400] eta: 0:01:47 lr: 0.000217 loss: 0.2409 (0.2418) grad: 0.0565 (0.0587) time: 0.3706 data: 0.0044 max mem: 4873 +train: [10] [140/400] eta: 0:01:39 lr: 0.000215 loss: 0.2408 (0.2425) grad: 0.0565 (0.0593) time: 0.3645 data: 0.0040 max mem: 4873 +train: [10] [160/400] eta: 0:01:30 lr: 0.000214 loss: 0.2301 (0.2418) grad: 0.0550 (0.0592) time: 0.3616 data: 0.0042 max mem: 4873 +train: [10] [180/400] eta: 0:01:22 lr: 0.000213 loss: 0.2355 (0.2411) grad: 0.0548 (0.0588) time: 0.3616 data: 0.0044 max mem: 4873 +train: [10] [200/400] eta: 0:01:14 lr: 0.000211 loss: 0.2370 (0.2411) grad: 0.0548 (0.0584) time: 0.3415 data: 0.0039 max mem: 4873 +train: [10] [220/400] eta: 0:01:07 lr: 0.000210 loss: 0.2304 (0.2406) grad: 0.0543 (0.0578) time: 0.3787 data: 0.0044 max mem: 4873 +train: [10] [240/400] eta: 0:00:59 lr: 0.000208 loss: 0.2213 (0.2387) grad: 0.0532 (0.0574) time: 0.3543 data: 0.0040 max mem: 4873 +train: [10] [260/400] eta: 0:00:52 lr: 0.000207 loss: 0.2213 (0.2390) grad: 0.0532 (0.0572) time: 0.3690 data: 0.0042 max mem: 4873 +train: [10] [280/400] eta: 0:00:44 lr: 0.000205 loss: 0.2366 (0.2392) grad: 0.0549 (0.0573) time: 0.3635 data: 0.0042 max mem: 4873 +train: [10] [300/400] eta: 0:00:37 lr: 0.000204 loss: 0.2287 (0.2381) grad: 0.0554 (0.0571) time: 0.4920 data: 0.1684 max mem: 4873 +train: [10] [320/400] eta: 0:00:30 lr: 0.000202 loss: 0.2210 (0.2372) grad: 0.0540 (0.0568) time: 0.3700 data: 0.0041 max mem: 4873 +train: [10] [340/400] eta: 0:00:22 lr: 0.000201 loss: 0.2140 (0.2357) grad: 0.0500 (0.0562) time: 0.3744 data: 0.0037 max mem: 4873 +train: [10] [360/400] eta: 0:00:15 lr: 0.000199 loss: 0.2233 (0.2353) grad: 0.0500 (0.0561) time: 0.3649 data: 0.0039 max mem: 4873 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 0.2130 (0.2336) grad: 0.0501 (0.0556) time: 0.3360 data: 0.0041 max mem: 4873 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.2068 (0.2329) grad: 0.0484 (0.0553) time: 0.3476 data: 0.0042 max mem: 4873 +train: [10] Total time: 0:02:29 (0.3749 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.2068 (0.2329) grad: 0.0484 (0.0553) +eval (validation): [10] [ 0/63] eta: 0:03:31 time: 3.3587 data: 3.0724 max mem: 4873 +eval (validation): [10] [20/63] eta: 0:00:20 time: 0.3376 data: 0.0072 max mem: 4873 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3396 data: 0.0032 max mem: 4873 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3132 data: 0.0033 max mem: 4873 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3110 data: 0.0033 max mem: 4873 +eval (validation): [10] Total time: 0:00:24 (0.3825 s / it) +cv: [10] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.090 acc: 0.982 f1: 0.979 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:22 lr: nan time: 3.3561 data: 3.0524 max mem: 4873 +train: [11] [ 20/400] eta: 0:03:15 lr: 0.000195 loss: 0.2093 (0.2171) grad: 0.0540 (0.0547) time: 0.3725 data: 0.0045 max mem: 4873 +train: [11] [ 40/400] eta: 0:02:38 lr: 0.000193 loss: 0.2093 (0.2162) grad: 0.0513 (0.0535) time: 0.3615 data: 0.0034 max mem: 4873 +train: [11] [ 60/400] eta: 0:02:21 lr: 0.000192 loss: 0.2093 (0.2145) grad: 0.0495 (0.0516) time: 0.3671 data: 0.0044 max mem: 4873 +train: [11] [ 80/400] eta: 0:02:11 lr: 0.000190 loss: 0.2145 (0.2160) grad: 0.0460 (0.0509) time: 0.3907 data: 0.0043 max mem: 4873 +train: [11] [100/400] eta: 0:02:00 lr: 0.000189 loss: 0.2145 (0.2150) grad: 0.0457 (0.0500) time: 0.3611 data: 0.0042 max mem: 4873 +train: [11] [120/400] eta: 0:01:50 lr: 0.000187 loss: 0.2085 (0.2135) grad: 0.0461 (0.0497) time: 0.3777 data: 0.0041 max mem: 4873 +train: [11] [140/400] eta: 0:01:41 lr: 0.000186 loss: 0.2063 (0.2128) grad: 0.0457 (0.0489) time: 0.3638 data: 0.0043 max mem: 4873 +train: [11] [160/400] eta: 0:01:33 lr: 0.000184 loss: 0.1987 (0.2124) grad: 0.0452 (0.0486) time: 0.3579 data: 0.0041 max mem: 4873 +train: [11] [180/400] eta: 0:01:24 lr: 0.000183 loss: 0.2029 (0.2114) grad: 0.0451 (0.0481) time: 0.3363 data: 0.0040 max mem: 4873 +train: [11] [200/400] eta: 0:01:15 lr: 0.000181 loss: 0.2011 (0.2102) grad: 0.0451 (0.0478) time: 0.3423 data: 0.0041 max mem: 4873 +train: [11] [220/400] eta: 0:01:07 lr: 0.000180 loss: 0.2016 (0.2107) grad: 0.0456 (0.0476) time: 0.3573 data: 0.0040 max mem: 4873 +train: [11] [240/400] eta: 0:00:59 lr: 0.000178 loss: 0.2121 (0.2105) grad: 0.0426 (0.0471) time: 0.3561 data: 0.0039 max mem: 4873 +train: [11] [260/400] eta: 0:00:52 lr: 0.000177 loss: 0.1994 (0.2104) grad: 0.0448 (0.0474) time: 0.3722 data: 0.0040 max mem: 4873 +train: [11] [280/400] eta: 0:00:44 lr: 0.000175 loss: 0.1974 (0.2101) grad: 0.0507 (0.0476) time: 0.3714 data: 0.0042 max mem: 4873 +train: [11] [300/400] eta: 0:00:38 lr: 0.000174 loss: 0.2051 (0.2103) grad: 0.0427 (0.0472) time: 0.5044 data: 0.1776 max mem: 4873 +train: [11] [320/400] eta: 0:00:30 lr: 0.000172 loss: 0.2033 (0.2097) grad: 0.0427 (0.0470) time: 0.3677 data: 0.0031 max mem: 4873 +train: [11] [340/400] eta: 0:00:22 lr: 0.000170 loss: 0.1937 (0.2089) grad: 0.0433 (0.0468) time: 0.3684 data: 0.0038 max mem: 4873 +train: [11] [360/400] eta: 0:00:15 lr: 0.000169 loss: 0.1853 (0.2078) grad: 0.0414 (0.0467) time: 0.3616 data: 0.0043 max mem: 4873 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 0.1863 (0.2072) grad: 0.0414 (0.0465) time: 0.3372 data: 0.0039 max mem: 4873 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.1957 (0.2067) grad: 0.0391 (0.0461) time: 0.3571 data: 0.0042 max mem: 4873 +train: [11] Total time: 0:02:30 (0.3774 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.1957 (0.2067) grad: 0.0391 (0.0461) +eval (validation): [11] [ 0/63] eta: 0:03:29 time: 3.3331 data: 3.0973 max mem: 4873 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3508 data: 0.0038 max mem: 4873 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3547 data: 0.0035 max mem: 4873 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3098 data: 0.0033 max mem: 4873 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.2982 data: 0.0032 max mem: 4873 +eval (validation): [11] Total time: 0:00:24 (0.3890 s / it) +cv: [11] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.084 acc: 0.983 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:20:07 lr: nan time: 3.0191 data: 2.7642 max mem: 4873 +train: [12] [ 20/400] eta: 0:02:59 lr: 0.000164 loss: 0.1943 (0.1977) grad: 0.0413 (0.0455) time: 0.3460 data: 0.0032 max mem: 4873 +train: [12] [ 40/400] eta: 0:02:24 lr: 0.000163 loss: 0.1943 (0.1926) grad: 0.0409 (0.0430) time: 0.3252 data: 0.0039 max mem: 4873 +train: [12] [ 60/400] eta: 0:02:08 lr: 0.000161 loss: 0.1854 (0.1910) grad: 0.0378 (0.0417) time: 0.3267 data: 0.0038 max mem: 4873 +train: [12] [ 80/400] eta: 0:01:56 lr: 0.000160 loss: 0.1941 (0.1936) grad: 0.0390 (0.0420) time: 0.3300 data: 0.0038 max mem: 4873 +train: [12] [100/400] eta: 0:01:46 lr: 0.000158 loss: 0.1989 (0.1961) grad: 0.0417 (0.0425) time: 0.3180 data: 0.0037 max mem: 4873 +train: [12] [120/400] eta: 0:01:38 lr: 0.000156 loss: 0.1951 (0.1934) grad: 0.0394 (0.0420) time: 0.3378 data: 0.0041 max mem: 4873 +train: [12] [140/400] eta: 0:01:30 lr: 0.000155 loss: 0.1840 (0.1924) grad: 0.0379 (0.0414) time: 0.3313 data: 0.0039 max mem: 4873 +train: [12] [160/400] eta: 0:01:23 lr: 0.000153 loss: 0.1932 (0.1937) grad: 0.0379 (0.0418) time: 0.3235 data: 0.0040 max mem: 4873 +train: [12] [180/400] eta: 0:01:15 lr: 0.000152 loss: 0.1916 (0.1925) grad: 0.0425 (0.0420) time: 0.3283 data: 0.0042 max mem: 4873 +train: [12] [200/400] eta: 0:01:08 lr: 0.000150 loss: 0.1862 (0.1928) grad: 0.0425 (0.0421) time: 0.3331 data: 0.0041 max mem: 4873 +train: [12] [220/400] eta: 0:01:01 lr: 0.000149 loss: 0.1901 (0.1923) grad: 0.0449 (0.0426) time: 0.3349 data: 0.0040 max mem: 4873 +train: [12] [240/400] eta: 0:00:54 lr: 0.000147 loss: 0.1792 (0.1920) grad: 0.0435 (0.0425) time: 0.3373 data: 0.0037 max mem: 4873 +train: [12] [260/400] eta: 0:00:47 lr: 0.000145 loss: 0.1831 (0.1917) grad: 0.0418 (0.0425) time: 0.3366 data: 0.0042 max mem: 4873 +train: [12] [280/400] eta: 0:00:40 lr: 0.000144 loss: 0.1911 (0.1918) grad: 0.0414 (0.0426) time: 0.3269 data: 0.0039 max mem: 4873 +train: [12] [300/400] eta: 0:00:35 lr: 0.000142 loss: 0.1759 (0.1908) grad: 0.0374 (0.0422) time: 0.4889 data: 0.1605 max mem: 4873 +train: [12] [320/400] eta: 0:00:27 lr: 0.000141 loss: 0.1754 (0.1897) grad: 0.0365 (0.0421) time: 0.3377 data: 0.0034 max mem: 4873 +train: [12] [340/400] eta: 0:00:21 lr: 0.000139 loss: 0.1780 (0.1901) grad: 0.0367 (0.0418) time: 0.3860 data: 0.0047 max mem: 4873 +train: [12] [360/400] eta: 0:00:14 lr: 0.000138 loss: 0.1828 (0.1897) grad: 0.0368 (0.0417) time: 0.3578 data: 0.0039 max mem: 4873 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 0.1800 (0.1892) grad: 0.0395 (0.0416) time: 0.3429 data: 0.0041 max mem: 4873 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.1756 (0.1887) grad: 0.0374 (0.0414) time: 0.3573 data: 0.0045 max mem: 4873 +train: [12] Total time: 0:02:20 (0.3525 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.1756 (0.1887) grad: 0.0374 (0.0414) +eval (validation): [12] [ 0/63] eta: 0:03:35 time: 3.4263 data: 3.1320 max mem: 4873 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.3761 data: 0.0029 max mem: 4873 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.4066 data: 0.0037 max mem: 4873 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3439 data: 0.0039 max mem: 4873 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3373 data: 0.0037 max mem: 4873 +eval (validation): [12] Total time: 0:00:26 (0.4272 s / it) +cv: [12] best hparam: (8.3, 1.0) (037) ('037_lr8.3e+00_wd1.0e+00') loss: 0.078 acc: 0.984 f1: 0.983 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:22:39 lr: nan time: 3.3980 data: 3.1207 max mem: 4873 +train: [13] [ 20/400] eta: 0:03:19 lr: 0.000133 loss: 0.1725 (0.1720) grad: 0.0370 (0.0378) time: 0.3803 data: 0.0038 max mem: 4873 +train: [13] [ 40/400] eta: 0:02:41 lr: 0.000131 loss: 0.1761 (0.1779) grad: 0.0387 (0.0390) time: 0.3694 data: 0.0041 max mem: 4873 +train: [13] [ 60/400] eta: 0:02:22 lr: 0.000130 loss: 0.1742 (0.1739) grad: 0.0387 (0.0385) time: 0.3619 data: 0.0043 max mem: 4873 +train: [13] [ 80/400] eta: 0:02:09 lr: 0.000128 loss: 0.1717 (0.1754) grad: 0.0355 (0.0380) time: 0.3633 data: 0.0043 max mem: 4873 +train: [13] [100/400] eta: 0:01:59 lr: 0.000127 loss: 0.1810 (0.1778) grad: 0.0363 (0.0378) time: 0.3749 data: 0.0045 max mem: 4873 +train: [13] [120/400] eta: 0:01:50 lr: 0.000125 loss: 0.1855 (0.1787) grad: 0.0374 (0.0380) time: 0.3667 data: 0.0040 max mem: 4873 +train: [13] [140/400] eta: 0:01:41 lr: 0.000124 loss: 0.1844 (0.1804) grad: 0.0384 (0.0385) time: 0.3677 data: 0.0044 max mem: 4873 +train: [13] [160/400] eta: 0:01:32 lr: 0.000122 loss: 0.1737 (0.1784) grad: 0.0385 (0.0386) time: 0.3490 data: 0.0042 max mem: 4873 +train: [13] [180/400] eta: 0:01:24 lr: 0.000120 loss: 0.1720 (0.1784) grad: 0.0385 (0.0390) time: 0.3555 data: 0.0042 max mem: 4873 +train: [13] [200/400] eta: 0:01:15 lr: 0.000119 loss: 0.1754 (0.1796) grad: 0.0400 (0.0393) time: 0.3478 data: 0.0043 max mem: 4873 +train: [13] [220/400] eta: 0:01:07 lr: 0.000117 loss: 0.1783 (0.1797) grad: 0.0408 (0.0395) time: 0.3543 data: 0.0044 max mem: 4873 +train: [13] [240/400] eta: 0:00:59 lr: 0.000116 loss: 0.1856 (0.1793) grad: 0.0406 (0.0396) time: 0.3503 data: 0.0043 max mem: 4873 +train: [13] [260/400] eta: 0:00:52 lr: 0.000114 loss: 0.1823 (0.1794) grad: 0.0392 (0.0395) time: 0.3545 data: 0.0041 max mem: 4873 +train: [13] [280/400] eta: 0:00:44 lr: 0.000113 loss: 0.1809 (0.1793) grad: 0.0356 (0.0393) time: 0.3638 data: 0.0044 max mem: 4873 +train: [13] [300/400] eta: 0:00:38 lr: 0.000111 loss: 0.1714 (0.1781) grad: 0.0340 (0.0391) time: 0.5543 data: 0.1911 max mem: 4873 +train: [13] [320/400] eta: 0:00:30 lr: 0.000110 loss: 0.1707 (0.1780) grad: 0.0335 (0.0388) time: 0.4160 data: 0.0040 max mem: 4873 +train: [13] [340/400] eta: 0:00:23 lr: 0.000108 loss: 0.1811 (0.1781) grad: 0.0350 (0.0387) time: 0.3430 data: 0.0038 max mem: 4873 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 0.1697 (0.1779) grad: 0.0350 (0.0385) time: 0.3462 data: 0.0038 max mem: 4873 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 0.1685 (0.1778) grad: 0.0359 (0.0385) time: 0.3559 data: 0.0040 max mem: 4873 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.1739 (0.1775) grad: 0.0362 (0.0383) time: 0.3640 data: 0.0040 max mem: 4873 +train: [13] Total time: 0:02:32 (0.3801 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.1739 (0.1775) grad: 0.0362 (0.0383) +eval (validation): [13] [ 0/63] eta: 0:03:26 time: 3.2841 data: 3.0639 max mem: 4873 +eval (validation): [13] [20/63] eta: 0:00:19 time: 0.3098 data: 0.0025 max mem: 4873 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3354 data: 0.0033 max mem: 4873 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3117 data: 0.0026 max mem: 4873 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3089 data: 0.0029 max mem: 4873 +eval (validation): [13] Total time: 0:00:23 (0.3699 s / it) +cv: [13] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.080 acc: 0.984 f1: 0.981 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:22:40 lr: nan time: 3.4009 data: 3.0940 max mem: 4873 +train: [14] [ 20/400] eta: 0:03:11 lr: 0.000102 loss: 0.1700 (0.1740) grad: 0.0369 (0.0375) time: 0.3592 data: 0.0038 max mem: 4873 +train: [14] [ 40/400] eta: 0:02:36 lr: 0.000101 loss: 0.1688 (0.1716) grad: 0.0360 (0.0359) time: 0.3599 data: 0.0029 max mem: 4873 +train: [14] [ 60/400] eta: 0:02:22 lr: 0.000099 loss: 0.1661 (0.1730) grad: 0.0339 (0.0355) time: 0.3875 data: 0.0036 max mem: 4873 +train: [14] [ 80/400] eta: 0:02:09 lr: 0.000098 loss: 0.1683 (0.1723) grad: 0.0364 (0.0363) time: 0.3585 data: 0.0043 max mem: 4873 +train: [14] [100/400] eta: 0:01:57 lr: 0.000096 loss: 0.1664 (0.1708) grad: 0.0377 (0.0364) time: 0.3505 data: 0.0040 max mem: 4873 +train: [14] [120/400] eta: 0:01:49 lr: 0.000095 loss: 0.1655 (0.1690) grad: 0.0363 (0.0364) time: 0.3702 data: 0.0036 max mem: 4873 +train: [14] [140/400] eta: 0:01:40 lr: 0.000093 loss: 0.1669 (0.1691) grad: 0.0356 (0.0365) time: 0.3736 data: 0.0039 max mem: 4873 +train: [14] [160/400] eta: 0:01:32 lr: 0.000092 loss: 0.1710 (0.1698) grad: 0.0365 (0.0366) time: 0.3627 data: 0.0039 max mem: 4873 +train: [14] [180/400] eta: 0:01:23 lr: 0.000090 loss: 0.1647 (0.1694) grad: 0.0350 (0.0365) time: 0.3563 data: 0.0043 max mem: 4873 +train: [14] [200/400] eta: 0:01:15 lr: 0.000089 loss: 0.1662 (0.1698) grad: 0.0341 (0.0364) time: 0.3569 data: 0.0042 max mem: 4873 +train: [14] [220/400] eta: 0:01:08 lr: 0.000088 loss: 0.1674 (0.1699) grad: 0.0348 (0.0364) time: 0.3735 data: 0.0043 max mem: 4873 +train: [14] [240/400] eta: 0:01:00 lr: 0.000086 loss: 0.1674 (0.1696) grad: 0.0353 (0.0364) time: 0.3706 data: 0.0041 max mem: 4873 +train: [14] [260/400] eta: 0:00:52 lr: 0.000085 loss: 0.1656 (0.1699) grad: 0.0357 (0.0363) time: 0.3542 data: 0.0044 max mem: 4873 +train: [14] [280/400] eta: 0:00:44 lr: 0.000083 loss: 0.1671 (0.1693) grad: 0.0346 (0.0361) time: 0.3590 data: 0.0040 max mem: 4873 +train: [14] [300/400] eta: 0:00:38 lr: 0.000082 loss: 0.1600 (0.1693) grad: 0.0346 (0.0361) time: 0.5332 data: 0.1889 max mem: 4873 +train: [14] [320/400] eta: 0:00:30 lr: 0.000081 loss: 0.1536 (0.1687) grad: 0.0350 (0.0359) time: 0.3584 data: 0.0035 max mem: 4873 +train: [14] [340/400] eta: 0:00:22 lr: 0.000079 loss: 0.1520 (0.1680) grad: 0.0327 (0.0358) time: 0.3192 data: 0.0031 max mem: 4873 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 0.1415 (0.1665) grad: 0.0334 (0.0357) time: 0.3486 data: 0.0042 max mem: 4873 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 0.1473 (0.1663) grad: 0.0352 (0.0357) time: 0.3658 data: 0.0044 max mem: 4873 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.1654 (0.1660) grad: 0.0351 (0.0357) time: 0.3652 data: 0.0041 max mem: 4873 +train: [14] Total time: 0:02:30 (0.3773 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.1654 (0.1660) grad: 0.0351 (0.0357) +eval (validation): [14] [ 0/63] eta: 0:03:30 time: 3.3342 data: 3.0475 max mem: 4873 +eval (validation): [14] [20/63] eta: 0:00:22 time: 0.3852 data: 0.0039 max mem: 4873 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3345 data: 0.0032 max mem: 4873 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3157 data: 0.0035 max mem: 4873 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3157 data: 0.0034 max mem: 4873 +eval (validation): [14] Total time: 0:00:24 (0.3968 s / it) +cv: [14] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.275 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +train: [15] [ 0/400] eta: 0:22:32 lr: nan time: 3.3819 data: 3.0766 max mem: 4873 +train: [15] [ 20/400] eta: 0:03:29 lr: 0.000074 loss: 0.1714 (0.1793) grad: 0.0356 (0.0373) time: 0.4088 data: 0.0049 max mem: 4873 +train: [15] [ 40/400] eta: 0:02:50 lr: 0.000072 loss: 0.1658 (0.1684) grad: 0.0345 (0.0363) time: 0.3937 data: 0.0040 max mem: 4873 +train: [15] [ 60/400] eta: 0:02:29 lr: 0.000071 loss: 0.1578 (0.1682) grad: 0.0330 (0.0354) time: 0.3697 data: 0.0041 max mem: 4873 +train: [15] [ 80/400] eta: 0:02:12 lr: 0.000070 loss: 0.1558 (0.1662) grad: 0.0339 (0.0361) time: 0.3352 data: 0.0044 max mem: 4873 +train: [15] [100/400] eta: 0:02:00 lr: 0.000068 loss: 0.1600 (0.1653) grad: 0.0388 (0.0367) time: 0.3504 data: 0.0043 max mem: 4873 +train: [15] [120/400] eta: 0:01:50 lr: 0.000067 loss: 0.1690 (0.1671) grad: 0.0359 (0.0367) time: 0.3673 data: 0.0044 max mem: 4873 +train: [15] [140/400] eta: 0:01:41 lr: 0.000066 loss: 0.1719 (0.1672) grad: 0.0340 (0.0364) time: 0.3650 data: 0.0040 max mem: 4873 +train: [15] [160/400] eta: 0:01:33 lr: 0.000064 loss: 0.1545 (0.1651) grad: 0.0340 (0.0360) time: 0.3758 data: 0.0045 max mem: 4873 +train: [15] [180/400] eta: 0:01:24 lr: 0.000063 loss: 0.1515 (0.1644) grad: 0.0331 (0.0362) time: 0.3598 data: 0.0045 max mem: 4873 +train: [15] [200/400] eta: 0:01:16 lr: 0.000062 loss: 0.1592 (0.1641) grad: 0.0338 (0.0361) time: 0.3685 data: 0.0042 max mem: 4873 +train: [15] [220/400] eta: 0:01:08 lr: 0.000061 loss: 0.1662 (0.1646) grad: 0.0347 (0.0362) time: 0.3721 data: 0.0041 max mem: 4873 +train: [15] [240/400] eta: 0:01:01 lr: 0.000059 loss: 0.1661 (0.1642) grad: 0.0345 (0.0359) time: 0.3724 data: 0.0043 max mem: 4873 +train: [15] [260/400] eta: 0:00:53 lr: 0.000058 loss: 0.1519 (0.1634) grad: 0.0319 (0.0358) time: 0.3769 data: 0.0043 max mem: 4873 +train: [15] [280/400] eta: 0:00:45 lr: 0.000057 loss: 0.1505 (0.1622) grad: 0.0334 (0.0355) time: 0.3623 data: 0.0040 max mem: 4873 +train: [15] [300/400] eta: 0:00:39 lr: 0.000056 loss: 0.1523 (0.1621) grad: 0.0349 (0.0356) time: 0.5267 data: 0.1833 max mem: 4873 +train: [15] [320/400] eta: 0:00:31 lr: 0.000054 loss: 0.1571 (0.1617) grad: 0.0351 (0.0354) time: 0.3493 data: 0.0037 max mem: 4873 +train: [15] [340/400] eta: 0:00:23 lr: 0.000053 loss: 0.1658 (0.1620) grad: 0.0330 (0.0353) time: 0.3296 data: 0.0037 max mem: 4873 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 0.1680 (0.1619) grad: 0.0330 (0.0353) time: 0.3682 data: 0.0044 max mem: 4873 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 0.1658 (0.1620) grad: 0.0334 (0.0352) time: 0.3696 data: 0.0041 max mem: 4873 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.1632 (0.1619) grad: 0.0341 (0.0352) time: 0.3636 data: 0.0044 max mem: 4873 +train: [15] Total time: 0:02:32 (0.3824 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.1632 (0.1619) grad: 0.0341 (0.0352) +eval (validation): [15] [ 0/63] eta: 0:03:37 time: 3.4507 data: 3.1482 max mem: 4873 +eval (validation): [15] [20/63] eta: 0:00:23 time: 0.3943 data: 0.0030 max mem: 4873 +eval (validation): [15] [40/63] eta: 0:00:10 time: 0.3588 data: 0.0037 max mem: 4873 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.3080 data: 0.0032 max mem: 4873 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.3115 data: 0.0031 max mem: 4873 +eval (validation): [15] Total time: 0:00:25 (0.4060 s / it) +cv: [15] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.078 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:59 lr: nan time: 3.4483 data: 3.2095 max mem: 4873 +train: [16] [ 20/400] eta: 0:03:22 lr: 0.000048 loss: 0.1713 (0.1715) grad: 0.0315 (0.0368) time: 0.3871 data: 0.0027 max mem: 4873 +train: [16] [ 40/400] eta: 0:02:41 lr: 0.000047 loss: 0.1546 (0.1612) grad: 0.0317 (0.0347) time: 0.3584 data: 0.0044 max mem: 4873 +train: [16] [ 60/400] eta: 0:02:23 lr: 0.000046 loss: 0.1485 (0.1597) grad: 0.0329 (0.0349) time: 0.3685 data: 0.0043 max mem: 4873 +train: [16] [ 80/400] eta: 0:02:10 lr: 0.000045 loss: 0.1602 (0.1611) grad: 0.0347 (0.0348) time: 0.3617 data: 0.0040 max mem: 4873 +train: [16] [100/400] eta: 0:01:59 lr: 0.000044 loss: 0.1617 (0.1603) grad: 0.0332 (0.0347) time: 0.3605 data: 0.0043 max mem: 4873 +train: [16] [120/400] eta: 0:01:49 lr: 0.000043 loss: 0.1617 (0.1608) grad: 0.0331 (0.0345) time: 0.3575 data: 0.0040 max mem: 4873 +train: [16] [140/400] eta: 0:01:40 lr: 0.000042 loss: 0.1609 (0.1604) grad: 0.0342 (0.0347) time: 0.3572 data: 0.0042 max mem: 4873 +train: [16] [160/400] eta: 0:01:31 lr: 0.000041 loss: 0.1526 (0.1599) grad: 0.0342 (0.0348) time: 0.3521 data: 0.0043 max mem: 4873 +train: [16] [180/400] eta: 0:01:23 lr: 0.000040 loss: 0.1501 (0.1585) grad: 0.0326 (0.0346) time: 0.3646 data: 0.0044 max mem: 4873 +train: [16] [200/400] eta: 0:01:15 lr: 0.000039 loss: 0.1499 (0.1580) grad: 0.0343 (0.0348) time: 0.3634 data: 0.0040 max mem: 4873 +train: [16] [220/400] eta: 0:01:07 lr: 0.000038 loss: 0.1522 (0.1588) grad: 0.0347 (0.0349) time: 0.3406 data: 0.0043 max mem: 4873 +train: [16] [240/400] eta: 0:00:59 lr: 0.000036 loss: 0.1522 (0.1588) grad: 0.0345 (0.0349) time: 0.3530 data: 0.0045 max mem: 4873 +train: [16] [260/400] eta: 0:00:52 lr: 0.000035 loss: 0.1577 (0.1593) grad: 0.0345 (0.0348) time: 0.3779 data: 0.0041 max mem: 4873 +train: [16] [280/400] eta: 0:00:44 lr: 0.000034 loss: 0.1597 (0.1591) grad: 0.0325 (0.0348) time: 0.3544 data: 0.0043 max mem: 4873 +train: [16] [300/400] eta: 0:00:38 lr: 0.000033 loss: 0.1602 (0.1593) grad: 0.0340 (0.0348) time: 0.5187 data: 0.1801 max mem: 4873 +train: [16] [320/400] eta: 0:00:30 lr: 0.000032 loss: 0.1550 (0.1587) grad: 0.0344 (0.0348) time: 0.3788 data: 0.0034 max mem: 4873 +train: [16] [340/400] eta: 0:00:22 lr: 0.000031 loss: 0.1550 (0.1590) grad: 0.0327 (0.0347) time: 0.3402 data: 0.0038 max mem: 4873 +train: [16] [360/400] eta: 0:00:15 lr: 0.000031 loss: 0.1628 (0.1593) grad: 0.0319 (0.0346) time: 0.3602 data: 0.0045 max mem: 4873 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 0.1572 (0.1596) grad: 0.0330 (0.0346) time: 0.3583 data: 0.0038 max mem: 4873 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.1684 (0.1602) grad: 0.0349 (0.0347) time: 0.3612 data: 0.0046 max mem: 4873 +train: [16] Total time: 0:02:30 (0.3769 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.1684 (0.1602) grad: 0.0349 (0.0347) +eval (validation): [16] [ 0/63] eta: 0:03:33 time: 3.3841 data: 3.0962 max mem: 4873 +eval (validation): [16] [20/63] eta: 0:00:23 time: 0.3940 data: 0.0036 max mem: 4873 +eval (validation): [16] [40/63] eta: 0:00:10 time: 0.3422 data: 0.0035 max mem: 4873 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3196 data: 0.0037 max mem: 4873 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3185 data: 0.0037 max mem: 4873 +eval (validation): [16] Total time: 0:00:25 (0.4031 s / it) +cv: [16] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.077 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:32 lr: nan time: 3.3821 data: 3.0911 max mem: 4873 +train: [17] [ 20/400] eta: 0:03:15 lr: 0.000028 loss: 0.1550 (0.1601) grad: 0.0333 (0.0343) time: 0.3710 data: 0.0038 max mem: 4873 +train: [17] [ 40/400] eta: 0:02:38 lr: 0.000027 loss: 0.1526 (0.1582) grad: 0.0333 (0.0334) time: 0.3636 data: 0.0034 max mem: 4873 +train: [17] [ 60/400] eta: 0:02:20 lr: 0.000026 loss: 0.1493 (0.1593) grad: 0.0330 (0.0329) time: 0.3581 data: 0.0041 max mem: 4873 +train: [17] [ 80/400] eta: 0:02:09 lr: 0.000025 loss: 0.1507 (0.1576) grad: 0.0340 (0.0336) time: 0.3723 data: 0.0044 max mem: 4873 +train: [17] [100/400] eta: 0:01:59 lr: 0.000024 loss: 0.1516 (0.1570) grad: 0.0353 (0.0340) time: 0.3763 data: 0.0041 max mem: 4873 +train: [17] [120/400] eta: 0:01:49 lr: 0.000023 loss: 0.1513 (0.1552) grad: 0.0324 (0.0335) time: 0.3521 data: 0.0041 max mem: 4873 +train: [17] [140/400] eta: 0:01:40 lr: 0.000023 loss: 0.1499 (0.1550) grad: 0.0324 (0.0336) time: 0.3569 data: 0.0045 max mem: 4873 +train: [17] [160/400] eta: 0:01:31 lr: 0.000022 loss: 0.1513 (0.1550) grad: 0.0348 (0.0339) time: 0.3565 data: 0.0045 max mem: 4873 +train: [17] [180/400] eta: 0:01:23 lr: 0.000021 loss: 0.1540 (0.1556) grad: 0.0344 (0.0340) time: 0.3617 data: 0.0044 max mem: 4873 +train: [17] [200/400] eta: 0:01:15 lr: 0.000020 loss: 0.1593 (0.1562) grad: 0.0334 (0.0340) time: 0.3746 data: 0.0040 max mem: 4873 +train: [17] [220/400] eta: 0:01:08 lr: 0.000019 loss: 0.1442 (0.1552) grad: 0.0318 (0.0339) time: 0.3667 data: 0.0043 max mem: 4873 +train: [17] [240/400] eta: 0:01:00 lr: 0.000019 loss: 0.1516 (0.1562) grad: 0.0325 (0.0339) time: 0.3664 data: 0.0041 max mem: 4873 +train: [17] [260/400] eta: 0:00:52 lr: 0.000018 loss: 0.1572 (0.1573) grad: 0.0341 (0.0339) time: 0.3558 data: 0.0042 max mem: 4873 +train: [17] [280/400] eta: 0:00:44 lr: 0.000017 loss: 0.1530 (0.1569) grad: 0.0327 (0.0339) time: 0.3601 data: 0.0044 max mem: 4873 +train: [17] [300/400] eta: 0:00:38 lr: 0.000016 loss: 0.1480 (0.1575) grad: 0.0348 (0.0340) time: 0.5799 data: 0.1977 max mem: 4873 +train: [17] [320/400] eta: 0:00:30 lr: 0.000016 loss: 0.1522 (0.1574) grad: 0.0346 (0.0340) time: 0.3622 data: 0.0035 max mem: 4873 +train: [17] [340/400] eta: 0:00:23 lr: 0.000015 loss: 0.1515 (0.1574) grad: 0.0336 (0.0341) time: 0.3361 data: 0.0034 max mem: 4873 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 0.1516 (0.1572) grad: 0.0336 (0.0340) time: 0.3655 data: 0.0043 max mem: 4873 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 0.1586 (0.1573) grad: 0.0316 (0.0340) time: 0.3627 data: 0.0045 max mem: 4873 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.1530 (0.1569) grad: 0.0327 (0.0340) time: 0.3703 data: 0.0043 max mem: 4873 +train: [17] Total time: 0:02:32 (0.3813 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.1530 (0.1569) grad: 0.0327 (0.0340) +eval (validation): [17] [ 0/63] eta: 0:03:26 time: 3.2724 data: 3.0463 max mem: 4873 +eval (validation): [17] [20/63] eta: 0:00:21 time: 0.3587 data: 0.0040 max mem: 4873 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3360 data: 0.0032 max mem: 4873 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3263 data: 0.0037 max mem: 4873 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3193 data: 0.0035 max mem: 4873 +eval (validation): [17] Total time: 0:00:24 (0.3903 s / it) +cv: [17] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.077 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:22:42 lr: nan time: 3.4071 data: 3.1014 max mem: 4873 +train: [18] [ 20/400] eta: 0:03:15 lr: 0.000012 loss: 0.1508 (0.1645) grad: 0.0343 (0.0335) time: 0.3705 data: 0.0039 max mem: 4873 +train: [18] [ 40/400] eta: 0:02:37 lr: 0.000012 loss: 0.1512 (0.1596) grad: 0.0325 (0.0330) time: 0.3573 data: 0.0038 max mem: 4873 +train: [18] [ 60/400] eta: 0:02:20 lr: 0.000011 loss: 0.1558 (0.1604) grad: 0.0325 (0.0328) time: 0.3631 data: 0.0045 max mem: 4873 +train: [18] [ 80/400] eta: 0:02:08 lr: 0.000011 loss: 0.1558 (0.1594) grad: 0.0325 (0.0329) time: 0.3611 data: 0.0043 max mem: 4873 +train: [18] [100/400] eta: 0:01:57 lr: 0.000010 loss: 0.1570 (0.1608) grad: 0.0329 (0.0332) time: 0.3605 data: 0.0043 max mem: 4873 +train: [18] [120/400] eta: 0:01:47 lr: 0.000009 loss: 0.1570 (0.1602) grad: 0.0338 (0.0332) time: 0.3494 data: 0.0042 max mem: 4873 +train: [18] [140/400] eta: 0:01:38 lr: 0.000009 loss: 0.1557 (0.1609) grad: 0.0335 (0.0335) time: 0.3511 data: 0.0041 max mem: 4873 +train: [18] [160/400] eta: 0:01:30 lr: 0.000008 loss: 0.1519 (0.1598) grad: 0.0334 (0.0334) time: 0.3499 data: 0.0043 max mem: 4873 +train: [18] [180/400] eta: 0:01:22 lr: 0.000008 loss: 0.1519 (0.1595) grad: 0.0346 (0.0336) time: 0.3627 data: 0.0044 max mem: 4873 +train: [18] [200/400] eta: 0:01:15 lr: 0.000007 loss: 0.1554 (0.1592) grad: 0.0356 (0.0341) time: 0.3823 data: 0.0041 max mem: 4873 +train: [18] [220/400] eta: 0:01:07 lr: 0.000007 loss: 0.1455 (0.1577) grad: 0.0334 (0.0340) time: 0.3594 data: 0.0042 max mem: 4873 +train: [18] [240/400] eta: 0:00:59 lr: 0.000006 loss: 0.1487 (0.1582) grad: 0.0334 (0.0342) time: 0.3400 data: 0.0039 max mem: 4873 +train: [18] [260/400] eta: 0:00:51 lr: 0.000006 loss: 0.1519 (0.1578) grad: 0.0327 (0.0341) time: 0.3646 data: 0.0045 max mem: 4873 +train: [18] [280/400] eta: 0:00:44 lr: 0.000006 loss: 0.1503 (0.1576) grad: 0.0317 (0.0339) time: 0.3613 data: 0.0047 max mem: 4873 +train: [18] [300/400] eta: 0:00:38 lr: 0.000005 loss: 0.1529 (0.1575) grad: 0.0307 (0.0339) time: 0.5588 data: 0.1919 max mem: 4873 +train: [18] [320/400] eta: 0:00:30 lr: 0.000005 loss: 0.1578 (0.1575) grad: 0.0324 (0.0340) time: 0.3650 data: 0.0041 max mem: 4873 +train: [18] [340/400] eta: 0:00:22 lr: 0.000004 loss: 0.1571 (0.1574) grad: 0.0345 (0.0340) time: 0.3220 data: 0.0030 max mem: 4873 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 0.1560 (0.1572) grad: 0.0335 (0.0341) time: 0.3478 data: 0.0042 max mem: 4873 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 0.1577 (0.1574) grad: 0.0335 (0.0340) time: 0.3445 data: 0.0044 max mem: 4873 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.1562 (0.1575) grad: 0.0331 (0.0340) time: 0.3588 data: 0.0044 max mem: 4873 +train: [18] Total time: 0:02:29 (0.3747 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.1562 (0.1575) grad: 0.0331 (0.0340) +eval (validation): [18] [ 0/63] eta: 0:03:35 time: 3.4182 data: 3.1249 max mem: 4873 +eval (validation): [18] [20/63] eta: 0:00:21 time: 0.3590 data: 0.0046 max mem: 4873 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3287 data: 0.0033 max mem: 4873 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3095 data: 0.0036 max mem: 4873 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3099 data: 0.0027 max mem: 4873 +eval (validation): [18] Total time: 0:00:24 (0.3870 s / it) +cv: [18] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.077 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:28 lr: nan time: 3.3709 data: 3.1273 max mem: 4873 +train: [19] [ 20/400] eta: 0:03:18 lr: 0.000003 loss: 0.1573 (0.1625) grad: 0.0329 (0.0327) time: 0.3788 data: 0.0043 max mem: 4873 +train: [19] [ 40/400] eta: 0:02:40 lr: 0.000003 loss: 0.1573 (0.1591) grad: 0.0335 (0.0329) time: 0.3671 data: 0.0030 max mem: 4873 +train: [19] [ 60/400] eta: 0:02:21 lr: 0.000002 loss: 0.1535 (0.1572) grad: 0.0322 (0.0328) time: 0.3583 data: 0.0040 max mem: 4873 +train: [19] [ 80/400] eta: 0:02:09 lr: 0.000002 loss: 0.1566 (0.1583) grad: 0.0344 (0.0335) time: 0.3725 data: 0.0042 max mem: 4873 +train: [19] [100/400] eta: 0:01:59 lr: 0.000002 loss: 0.1525 (0.1574) grad: 0.0344 (0.0335) time: 0.3699 data: 0.0041 max mem: 4873 +train: [19] [120/400] eta: 0:01:49 lr: 0.000002 loss: 0.1525 (0.1576) grad: 0.0326 (0.0334) time: 0.3596 data: 0.0042 max mem: 4873 +train: [19] [140/400] eta: 0:01:40 lr: 0.000001 loss: 0.1559 (0.1580) grad: 0.0311 (0.0331) time: 0.3390 data: 0.0039 max mem: 4873 +train: [19] [160/400] eta: 0:01:31 lr: 0.000001 loss: 0.1540 (0.1579) grad: 0.0318 (0.0333) time: 0.3414 data: 0.0043 max mem: 4873 +train: [19] [180/400] eta: 0:01:23 lr: 0.000001 loss: 0.1567 (0.1584) grad: 0.0353 (0.0335) time: 0.3748 data: 0.0043 max mem: 4873 +train: [19] [200/400] eta: 0:01:15 lr: 0.000001 loss: 0.1582 (0.1582) grad: 0.0348 (0.0336) time: 0.3787 data: 0.0042 max mem: 4873 +train: [19] [220/400] eta: 0:01:07 lr: 0.000001 loss: 0.1519 (0.1576) grad: 0.0330 (0.0334) time: 0.3416 data: 0.0041 max mem: 4873 +train: [19] [240/400] eta: 0:00:59 lr: 0.000001 loss: 0.1546 (0.1575) grad: 0.0341 (0.0335) time: 0.3671 data: 0.0047 max mem: 4873 +train: [19] [260/400] eta: 0:00:52 lr: 0.000000 loss: 0.1547 (0.1567) grad: 0.0346 (0.0336) time: 0.3678 data: 0.0043 max mem: 4873 +train: [19] [280/400] eta: 0:00:44 lr: 0.000000 loss: 0.1522 (0.1568) grad: 0.0328 (0.0336) time: 0.3686 data: 0.0046 max mem: 4873 +train: [19] [300/400] eta: 0:00:38 lr: 0.000000 loss: 0.1506 (0.1566) grad: 0.0320 (0.0335) time: 0.5273 data: 0.1763 max mem: 4873 +train: [19] [320/400] eta: 0:00:30 lr: 0.000000 loss: 0.1479 (0.1567) grad: 0.0326 (0.0336) time: 0.3755 data: 0.0036 max mem: 4873 +train: [19] [340/400] eta: 0:00:22 lr: 0.000000 loss: 0.1596 (0.1571) grad: 0.0333 (0.0337) time: 0.3544 data: 0.0041 max mem: 4873 +train: [19] [360/400] eta: 0:00:15 lr: 0.000000 loss: 0.1575 (0.1570) grad: 0.0328 (0.0338) time: 0.3422 data: 0.0038 max mem: 4873 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 0.1513 (0.1569) grad: 0.0328 (0.0337) time: 0.3449 data: 0.0040 max mem: 4873 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.1520 (0.1566) grad: 0.0328 (0.0338) time: 0.3453 data: 0.0043 max mem: 4873 +train: [19] Total time: 0:02:30 (0.3769 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.1520 (0.1566) grad: 0.0328 (0.0338) +eval (validation): [19] [ 0/63] eta: 0:03:34 time: 3.4017 data: 3.1716 max mem: 4873 +eval (validation): [19] [20/63] eta: 0:00:20 time: 0.3394 data: 0.0131 max mem: 4873 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3404 data: 0.0035 max mem: 4873 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.3113 data: 0.0029 max mem: 4873 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.3104 data: 0.0029 max mem: 4873 +eval (validation): [19] Total time: 0:00:24 (0.3837 s / it) +cv: [19] best hparam: (12, 1.0) (039) ('039_lr1.2e+01_wd1.0e+00') loss: 0.077 acc: 0.984 f1: 0.982 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-last.pth +eval model info: +{"score": 0.9841269841269841, "hparam": [12, 1.0], "hparam_id": 39, "epoch": 19, "is_best": false, "best_score": 0.984375} +eval (train): [20] [ 0/297] eta: 0:15:06 time: 3.0527 data: 2.8220 max mem: 4873 +eval (train): [20] [ 20/297] eta: 0:02:23 time: 0.3910 data: 0.0194 max mem: 4873 +eval (train): [20] [ 40/297] eta: 0:01:52 time: 0.3535 data: 0.0036 max mem: 4873 +eval (train): [20] [ 60/297] eta: 0:01:36 time: 0.3466 data: 0.0039 max mem: 4873 +eval (train): [20] [ 80/297] eta: 0:01:25 time: 0.3473 data: 0.0038 max mem: 4873 +eval (train): [20] [100/297] eta: 0:01:15 time: 0.3337 data: 0.0038 max mem: 4873 +eval (train): [20] [120/297] eta: 0:01:06 time: 0.3464 data: 0.0036 max mem: 4873 +eval (train): [20] [140/297] eta: 0:00:58 time: 0.3418 data: 0.0038 max mem: 4873 +eval (train): [20] [160/297] eta: 0:00:50 time: 0.3270 data: 0.0031 max mem: 4873 +eval (train): [20] [180/297] eta: 0:00:42 time: 0.3502 data: 0.0036 max mem: 4873 +eval (train): [20] [200/297] eta: 0:00:34 time: 0.3322 data: 0.0036 max mem: 4873 +eval (train): [20] [220/297] eta: 0:00:27 time: 0.3851 data: 0.0040 max mem: 4873 +eval (train): [20] [240/297] eta: 0:00:20 time: 0.3610 data: 0.0034 max mem: 4873 +eval (train): [20] [260/297] eta: 0:00:13 time: 0.3706 data: 0.0038 max mem: 4873 +eval (train): [20] [280/297] eta: 0:00:06 time: 0.3270 data: 0.0035 max mem: 4873 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.2998 data: 0.0034 max mem: 4873 +eval (train): [20] Total time: 0:01:46 (0.3590 s / it) +eval (validation): [20] [ 0/63] eta: 0:02:52 time: 2.7391 data: 2.5079 max mem: 4873 +eval (validation): [20] [20/63] eta: 0:00:19 time: 0.3379 data: 0.0046 max mem: 4873 +eval (validation): [20] [40/63] eta: 0:00:08 time: 0.3131 data: 0.0027 max mem: 4873 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3110 data: 0.0037 max mem: 4873 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3106 data: 0.0037 max mem: 4873 +eval (validation): [20] Total time: 0:00:22 (0.3625 s / it) +eval (test): [20] [ 0/79] eta: 0:03:39 time: 2.7748 data: 2.5301 max mem: 4873 +eval (test): [20] [20/79] eta: 0:00:27 time: 0.3442 data: 0.0039 max mem: 4873 +eval (test): [20] [40/79] eta: 0:00:14 time: 0.2961 data: 0.0028 max mem: 4873 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3581 data: 0.0036 max mem: 4873 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.2974 data: 0.0032 max mem: 4873 +eval (test): [20] Total time: 0:00:28 (0.3565 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/checkpoint-best.pth +eval model info: +{"score": 0.984375, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 14, "is_best": true, "best_score": 0.984375} +eval (train): [20] [ 0/297] eta: 0:13:46 time: 2.7845 data: 2.5704 max mem: 4873 +eval (train): [20] [ 20/297] eta: 0:01:53 time: 0.2918 data: 0.0033 max mem: 4873 +eval (train): [20] [ 40/297] eta: 0:01:34 time: 0.3211 data: 0.0030 max mem: 4873 +eval (train): [20] [ 60/297] eta: 0:01:22 time: 0.3123 data: 0.0029 max mem: 4873 +eval (train): [20] [ 80/297] eta: 0:01:13 time: 0.3159 data: 0.0033 max mem: 4873 +eval (train): [20] [100/297] eta: 0:01:06 time: 0.3177 data: 0.0032 max mem: 4873 +eval (train): [20] [120/297] eta: 0:00:58 time: 0.3087 data: 0.0032 max mem: 4873 +eval (train): [20] [140/297] eta: 0:00:51 time: 0.3029 data: 0.0033 max mem: 4873 +eval (train): [20] [160/297] eta: 0:00:44 time: 0.3234 data: 0.0034 max mem: 4873 +eval (train): [20] [180/297] eta: 0:00:38 time: 0.3371 data: 0.0032 max mem: 4873 +eval (train): [20] [200/297] eta: 0:00:31 time: 0.3377 data: 0.0032 max mem: 4873 +eval (train): [20] [220/297] eta: 0:00:25 time: 0.3372 data: 0.0036 max mem: 4873 +eval (train): [20] [240/297] eta: 0:00:18 time: 0.3371 data: 0.0036 max mem: 4873 +eval (train): [20] [260/297] eta: 0:00:12 time: 0.3328 data: 0.0034 max mem: 4873 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3215 data: 0.0031 max mem: 4873 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.2959 data: 0.0037 max mem: 4873 +eval (train): [20] Total time: 0:01:38 (0.3303 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:18 time: 3.1497 data: 2.9182 max mem: 4873 +eval (validation): [20] [20/63] eta: 0:00:21 time: 0.3665 data: 0.0200 max mem: 4873 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3325 data: 0.0030 max mem: 4873 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3327 data: 0.0031 max mem: 4873 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3291 data: 0.0034 max mem: 4873 +eval (validation): [20] Total time: 0:00:24 (0.3920 s / it) +eval (test): [20] [ 0/79] eta: 0:05:03 time: 3.8366 data: 3.6210 max mem: 4873 +eval (test): [20] [20/79] eta: 0:00:30 time: 0.3519 data: 0.0178 max mem: 4873 +eval (test): [20] [40/79] eta: 0:00:17 time: 0.3538 data: 0.0028 max mem: 4873 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3472 data: 0.0035 max mem: 4873 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3132 data: 0.0036 max mem: 4873 +eval (test): [20] Total time: 0:00:30 (0.3885 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|----------:|--------:|-----------:|--------:|-----------:| +| flat_mae | reg | attn | hcpya_task21 | best | 14 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 0.0010652 | 0.99979 | 0.00010543 | 0.9998 | 0.00012401 | +| flat_mae | reg | attn | hcpya_task21 | best | 14 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 0.27483 | 0.98438 | 0.0020246 | 0.98237 | 0.0025251 | +| flat_mae | reg | attn | hcpya_task21 | best | 14 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 0.43539 | 0.975 | 0.0021805 | 0.96909 | 0.0029553 | + + +done! total time: 1:06:30 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/train_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..5b6c82b0f842d9db44350c81a53dcd569ccf7d7e --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.342431766986847, "train/grad": 0.08717490687966346, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.045379638671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.04437744140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.042796630859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.0411328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.03947265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.037186279296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.03461181640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.03171630859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.027860107421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.0236669921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.019599609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.013248291015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.0069287109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.9975830078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.988331298828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.979188232421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.967032470703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.952047119140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.934320068359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.916944580078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.894091796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.8690093994140624, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8390643310546877, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.804568176269531, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.7656991577148435, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.7146923828125, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.664408874511719, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.614485626220703, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.5409095764160154, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.446056060791016, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3559359741210937, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2706296920776365, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.15159836769104, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0428424143791197, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9153769099712372, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.795173152834177, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.6751819436252118, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.5687901628762484, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.4622260209172964, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.3424703122675419, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.2581233305111528, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.1892465881910175, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.1072045977879315, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.0427226328197867, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.974678360465914, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.9094348497502506, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.8586823925282806, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.8030220045056194, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7594094773102552, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013872946253977716, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01386459314264357, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013849442512728273, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013834801479242742, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013820308395661413, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.013801233218982816, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013780552661046386, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013757372703403235, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.013727618851698936, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013697634134441614, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.013667853539809585, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.013625735132955015, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013586068558506668, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013531664605252444, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013482621675357222, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.013435404635965825, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01337846711743623, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01331382289994508, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013240774446167052, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013171931402757764, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.013082672283053398, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.012988028046675027, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.012883306611329318, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.012782517191953956, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01269792034290731, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.012625542781315745, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012576184892095625, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.012531640916131436, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.012456387192942201, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.012335972175933421, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.012206839295104147, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012085208133794368, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.011922878939658403, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01176173059269786, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01154363171895966, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01134726453339681, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.011168793097604067, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01091098862234503, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01060407888609916, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010335415217559785, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01014504603925161, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009951190333813429, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009796217477414756, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00984448701608926, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009854909891728311, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00970920812804252, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009685243428684771, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009736010909546167, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009740366823971272, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.03183913230896, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0288350582122803, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0238940715789795, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0189528465270996, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.014068841934204, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0072038173675537, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9993951320648193, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9906558990478516, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.979085922241211, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.966709613800049, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.95436429977417, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.935580015182495, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.91694974899292, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.8893649578094482, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.862051010131836, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8350987434387207, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7996926307678223, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.756092071533203, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.705073356628418, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6553328037261963, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5910792350769043, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.521291494369507, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4384055137634277, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.342050075531006, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.2309958934783936, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.082221031188965, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.9340900182724, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.788977026939392, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.5823227167129517, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.3343924283981323, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.117560625076294, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.9239192008972168, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6703309416770935, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.4775752127170563, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.3211565911769867, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.23574313521385193, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.18579120934009552, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15720948576927185, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.13644886016845703, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12029644846916199, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11146242916584015, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10556630790233612, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.10068065673112869, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.09874702244997025, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.09768377989530563, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.09564685821533203, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.09634856879711151, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.09920109808444977, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1083013042807579, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04439484126984127, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.060515873015873016, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.11334325396825397, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17385912698412698, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.20709325396825398, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2214781746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2197420634920635, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.21825396825396826, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2113095238095238, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.20535714285714285, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.19890873015873015, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.1909722222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18551587301587302, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1800595238095238, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.17733134920634921, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1753472222222222, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1736111111111111, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17311507936507936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.17336309523809523, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17385912698412698, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17857142857142858, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.1892361111111111, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.21676587301587302, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.28893849206349204, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3521825396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.4565972222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.5213293650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.5540674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.6321924603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.7425595238095238, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8390376984126984, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8901289682539683, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9174107142857143, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9285714285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9441964285714286, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9503968253968254, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9645337301587301, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9680059523809523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9682539682539683, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9689980158730159, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9692460317460317, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9702380952380952, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.96875, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9675099206349206, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.024697610845246243, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03122015481648074, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.043857279378661115, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.054376895228747515, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.05777156748135316, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05840979939681839, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05467281193653925, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.05422826776488655, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05092252469170747, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.046162347000710015, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.04173767608611062, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03621209320668856, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03152307092905601, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.026108310340040203, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.023015923762452584, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.02050794899509827, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.018138040194126837, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.017453232726474043, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.017803679334990156, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.01848849057724876, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.02480296324132438, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.037136211719389856, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.06031712534148634, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.10465452552402502, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.148812740213287, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2572928180091797, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.30863749375552535, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.366498658179868, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.523125370246168, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.6848504432004725, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.7913165807570137, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8639147089493927, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9038731099790338, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9153070810113151, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9318962282128512, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9405950720858931, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9442701006127944, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9521201225422654, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9587022035528685, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9618977006056016, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9619652036630562, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9631748863573629, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9618914263818497, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9630541228312838, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9650394698836811, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9644951268539531, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9636419008254512, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9640531117108166, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9620083616728327, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.9094348497502506, "validation/loss_best": 0.09564685821533203, "validation/acc_best": 0.9702380952380952, "validation/f1_best": 0.9644951268539531} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 1.4409423053264618, "train/grad": 0.0749436465650797, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.00588134765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.999130859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.987921142578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.97701416015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.966033935546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.950831298828125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.933502197265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.914287109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.8890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.861912841796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.8352777099609376, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.794873046875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.75535400390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.697623291015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.641478271484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.586285400390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.513646545410156, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.423822326660156, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.316836700439453, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.2111470031738283, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.0730015563964845, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.9232736206054688, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.7494737243652343, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.55696870803833, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.3545393419265748, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.124080138206482, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.9390545797348022, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.7917982093989849, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6239921223372221, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.46784315079450606, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.36230665020644665, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.28990458462387325, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.22114941468462349, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.18127960238605736, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.15183436076156795, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.13441542863845826, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.12234977995045483, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.11402522346936167, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.10776982693001629, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.10248090562410653, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0999632424954325, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0989335207734257, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09848806506954133, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09850901543162763, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09959980436600745, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10063468937762082, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.11014540107920766, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.12134224960580468, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.125095276767388, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01359384048730135, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013546664123423398, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013474574917927385, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013407799839042127, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013346307948231696, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.013268129262141883, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013184875673614442, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013101105606183409, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.013000584226101636, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012901129452511668, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012807811992242932, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012670333222486079, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012537609091959894, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01235585453454405, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012210461338981985, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012106569153256714, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012020151447504759, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01196337299887091, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011920098490081727, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01186610985081643, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011760191754437982, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01161156274843961, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011428803531453013, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011217841212637723, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010933193797245621, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010519883041270077, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01015332120936364, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009790727174840868, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009317140619968996, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00878769974107854, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008305641234619543, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007919737607007846, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007554680979810655, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.007281780813354999, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.006988414006773382, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006816669524414465, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006677549594314769, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006631744838086888, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006682620849460363, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006754121930571273, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006872940998291597, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007040766318677925, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00728824106103275, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0074303794151637705, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00757828229572624, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.007566017671488226, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.008309198043425567, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009062617889139802, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009177790820831432, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.973134756088257, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9616713523864746, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9427130222320557, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.923980951309204, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9053921699523926, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.879589319229126, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8505399227142334, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.818202018737793, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.7757568359375, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.7306325435638428, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.6864569187164307, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6203880310058594, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.5564775466918945, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.463517665863037, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.3722269535064697, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.2812232971191406, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.159236431121826, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.0061209201812744, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.824671745300293, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.6501491069793701, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.4333974123001099, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2120959758758545, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.9667750597000122, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7116717100143433, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.492986798286438, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.32796669006347656, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.2461884617805481, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2028987854719162, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.16771218180656433, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.1429644525051117, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.1285155862569809, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.11978067457675934, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.11206965893507004, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.10732526332139969, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1033477857708931, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.09939774870872498, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09495518356561661, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.09147808700799942, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08767405152320862, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0844990462064743, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08418432623147964, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08520825952291489, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.08753400295972824, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.0968855544924736, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.11932422965765, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1225355714559555, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19273273646831512, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.15696142613887787, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.19659720361232758, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.20535714285714285, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.19990079365079366, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.19072420634920634, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.18501984126984128, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.18129960317460317, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.1775793650793651, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.17485119047619047, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17336309523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.17311507936507936, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.17336309523809523, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.17559523809523808, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.18129960317460317, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.20709325396825398, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.267609126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.32341269841269843, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.4000496031746032, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5243055555555556, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.5629960317460317, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6264880952380952, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7175099206349206, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8132440476190477, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8846726190476191, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9188988095238095, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9379960317460317, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9471726190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9546130952380952, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.957093253968254, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9640376984126984, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.964781746031746, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9655257936507936, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9665178571428571, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.966765873015873, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9685019841269841, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9702380952380952, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.970734126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9714781746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.966765873015873, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9499007936507936, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9503968253968254, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.04691095394520142, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.04222385571235129, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.03575568599385839, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.031014419754407288, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.027478847410436897, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.023340907307461238, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.019840983352384794, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01779513457145966, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.017456783951637984, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.017108669843080307, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.017810828915348378, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.020878784053251914, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.02815352386591643, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.053501897349531716, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.09467065540173183, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.11775978118852704, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.20722778674313957, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.32238326760108366, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.37442267846849475, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.485826555074008, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6111117128886696, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.745031326609064, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8621656046054169, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9091062782314809, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9270345872281887, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9368227935370893, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9475907134156293, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9505359005402136, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9522604095336151, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9545745936395521, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.957798239563061, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9581631960827989, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9594406028912943, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9582639332375814, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9588174338328638, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.959719962856782, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9620147658637352, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9652381387149335, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.965661739551315, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9661232415503772, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9668888110441255, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9657364568718402, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9677448629651311, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9632667726269969, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9569673318444598, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9524958807857757, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9372308559759637, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9523691631567324, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9312987636209092, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 0.0999632424954325, "validation/loss_best": 0.08418432623147964, "validation/acc_best": 0.9724702380952381, "validation/f1_best": 0.9668888110441255} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.0602447137236595, "train/grad": 0.07982166519388556, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.92947509765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.91181884765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.882674560546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.854007568359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.825528564453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.7864813232421874, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.7426531982421873, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.6944427490234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.631878662109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.565923156738281, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.501284484863281, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4032131958007814, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.305816345214844, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.160226593017578, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.0158346557617186, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.8746953582763672, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.6935960388183593, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.48056640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.2459465980529785, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.037895004749298, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.8087537348270416, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6140686452388764, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.44807861372828484, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.32463463172316553, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.24369266197085382, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.18821056358516217, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.15918679170310499, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.1415714303031564, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.12502179709263145, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.11153048155829311, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.10295101032592356, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.09688995058648288, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.09048032911494375, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.08579135349020361, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.08138180633075535, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0781670378241688, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.07547368425875903, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.07375921919941902, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.07286727340891958, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07367746138013899, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07517676992341876, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0767693386413157, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08461533531546593, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09091161394491792, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.11132356852293014, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.12242288077250123, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.15435253475792707, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.23378411206416785, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.46248904038220645, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01317442453932017, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0130995028372854, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012989210705272853, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012893602973781526, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01280373496003449, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01268503289669752, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012552914042025805, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01240494953468442, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01222325911745429, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012067202222533524, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011964260721579195, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011896783928386867, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01189814340788871, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011930886916816234, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011917489683255553, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011829554559662938, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011623538169078528, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.011311566806398332, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010924251549877226, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0104989102948457, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009880815006326885, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009213213615585119, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00850957095157355, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007848489134339616, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007304816163377836, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006838188929250464, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006563556204782799, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.006404190557077527, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.006276608124026097, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006221276731230319, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.006253260031808167, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.006284869395312853, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006297826679656282, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006266971927834675, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00626983238500543, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.006336979515617713, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.006437483764020726, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006542215800145641, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0066466001234948635, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006811643958208151, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.006992603333201259, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007192643689340912, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.007659308952861465, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008320239669410512, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009761197083280422, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009960493005928583, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013223813024815172, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.017694908055709675, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03025892193429172, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.879020929336548, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8544178009033203, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8138084411621094, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7738840579986572, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7346553802490234, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6809375286102295, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.621241331100464, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.5561416149139404, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.4718337059020996, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.382150411605835, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.2927324771881104, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.1543850898742676, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.0155210494995117, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.8100693225860596, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.613818645477295, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.430720567703247, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.2061853408813477, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9502612948417664, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.6842818856239319, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.49050194025039673, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.3393464982509613, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.25352638959884644, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.19917559623718262, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.16453927755355835, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.14165331423282623, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.12361937761306763, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.11254091560840607, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.10508504509925842, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.09762153029441833, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.09170068800449371, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.08836065977811813, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.0869666188955307, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.08520276844501495, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.08354820311069489, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0850653275847435, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08678065985441208, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08474091440439224, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.084098681807518, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08590133488178253, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08507035672664642, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.08697397261857986, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09027891606092453, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09314092248678207, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.10678212344646454, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.21077005565166473, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1933722347021103, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19832322001457214, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.532423734664917, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.1228506565093994, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.17683531746031747, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17509920634920634, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17261904761904762, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.17311507936507936, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.17311507936507936, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.1753472222222222, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.18154761904761904, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2048611111111111, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.263640873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.32068452380952384, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.40476190476190477, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5243055555555556, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.574156746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.6436011904761905, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7271825396825397, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8385416666666666, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8965773809523809, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9166666666666666, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9315476190476191, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9451884920634921, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9528769841269841, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9588293650793651, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9635416666666666, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9660218253968254, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9697420634920635, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9712301587301587, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9724702380952381, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9744543650793651, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9699900793650794, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.953125, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9660218253968254, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9476686507936508, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9479166666666666, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02244976918120559, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.02019476793183413, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.017104050265570964, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.016754343681351536, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01745911268420169, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01745911268420169, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.02053323847091853, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.028491645458729467, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05193429297123536, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.09184552284365961, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.11753020104257304, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.21226750400298405, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.32630610900225593, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.386022339704378, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5231362735642227, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6539322947994543, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8033360272761767, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8821472648134212, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.905540595003393, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9240796975132328, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9385838453883069, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9456288135373725, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9523213733896718, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9572094203633172, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9598158165328999, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9640170144609433, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9659311109153534, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9681704787546117, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9685388809736699, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9666148390796542, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9668025478595192, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9679795164752578, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9674287693231126, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9701008424903822, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.970173081352702, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9696442292707695, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9706072519691683, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9695119514702291, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9686947539229036, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9700372133086274, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9704871922316846, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9743283718962479, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9701180293316073, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9658920132806004, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9491051506431968, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9467411429372847, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9593439679614642, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9389914955441941, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.940141791622348, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 0.0767693386413157, "validation/loss_best": 0.09027891606092453, "validation/acc_best": 0.9764384920634921, "validation/f1_best": 0.9743283718962479} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 0.8813521155714988, "train/grad": 0.12386201661080122, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.8211328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7885882568359377, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.7354693603515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6836181640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.6330133056640626, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.56405517578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.486882629394531, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.4013958740234376, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.287818603515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.164495544433594, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.0413249206542967, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8549327087402343, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.6757833862304687, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4249524307250976, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.1955841064453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.9888833379745483, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.7566756451129913, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.5421827512979508, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.3788020753860474, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.2847087971121073, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.21698739014565946, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.17669322561472656, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.14894169475883245, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.12926604581996798, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.11479928344488144, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.102132015703246, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.09360863695852459, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.08729723041877151, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.08032177831046283, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.07356608936563135, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.06841669409535825, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.06436871819198131, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.05988523256964982, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.05663632013835013, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.05367147621698678, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.05177457924000919, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.05099145555868745, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.051336400760337714, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.05350066497921944, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.058223137240856884, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06750248493626713, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.07336400563828648, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.08512892102822661, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10447952234186232, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1542036122083664, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.2835660712700337, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6852491366770118, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.4120671364106239, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.8179757748171688, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012698184717446565, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012602595132775604, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0124487189296633, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012293713157996536, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012147482819855213, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011978034139610827, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011860336223617197, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01182273296173662, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011871021245606244, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011950279530137777, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011989386505447328, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011910667372867466, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011700333035551012, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011305263126268983, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01094074064400047, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010577274025417865, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010014573894441128, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009222325088921934, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008359178663231432, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007736100163310766, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00721451566554606, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006862490394851193, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006610740786418319, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00644123203586787, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006324757549446076, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00623221475048922, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.006162993629113771, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0061106201936490835, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00604034900024999, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005957017675391398, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005868800135795027, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0057786224037408825, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005648345988884102, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005552747129113414, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005499907277699095, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005492971953935921, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0055634791465126905, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005691494823840912, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006056200939638074, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.006579510013980325, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007206822367734276, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.007539362231618725, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00826282677706331, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00952672424784396, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012659995213034562, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.020812555968586822, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03818109471569187, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.059614976369775835, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.06864323438251585, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.754354238510132, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.712986469268799, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.6457815170288086, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5807363986968994, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.517500400543213, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.4309048652648926, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.332785129547119, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.2223801612854004, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.074134588241577, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9142121076583862, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.7579455375671387, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.5305931568145752, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.321535348892212, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.0361943244934082, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.7810580134391785, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.5759872198104858, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.39868539571762085, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.28281527757644653, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.21566708385944366, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.18020521104335785, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.15324094891548157, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.13519293069839478, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.12127956748008728, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.11080048978328705, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.1027270033955574, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.09523990750312805, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08966434001922607, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.08535785973072052, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.08111700415611267, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07752436399459839, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07533349096775055, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07410280406475067, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07350047677755356, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0742778480052948, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07598142325878143, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07773040980100632, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08094180375337601, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08652757853269577, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10113890469074249, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.10125371068716049, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11125331372022629, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12103643268346786, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13046838343143463, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.23370414972305298, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.20457471907138824, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.7040902972221375, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.3179270029067993, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.531486988067627, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.337818145751953, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1728670634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.17311507936507936, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17509920634920634, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.17981150793650794, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.19072420634920634, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.23313492063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3097718253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3621031746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.48660714285714285, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5535714285714286, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5972222222222222, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.7065972222222222, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.8139880952380952, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8864087301587301, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9161706349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9278273809523809, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9432043650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9518849206349206, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9575892857142857, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9598214285714286, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9637896825396826, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9665178571428571, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9670138888888888, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9714781746031746, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9722222222222222, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9749503968253969, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9744543650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9717261904761905, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9719742063492064, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9528769841269841, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9382440476190477, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9523809523809523, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.017104785268273973, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01745911268420169, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.020190131598721173, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.02641977669936087, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0390451311974176, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.07488279958495876, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.11299482880372044, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.15683740926920697, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2958632502692667, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3453527398953028, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4257212212055541, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6278000177945428, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.762633288165589, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8685767302024501, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9051466680178196, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9182374896623448, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9356058525391304, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9437622551135453, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9501991844445634, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9525105339895693, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9559994111714797, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9587943249853943, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9593879113432904, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9634198437789407, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9652535621244758, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9655412857847038, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9668042888808298, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9697411939755552, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9714636242498281, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9727844429355764, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9723716023255439, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9747516542172218, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9743371918520294, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9736827593871253, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9743232120622357, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.975339928679678, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9730212040229924, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9716543078937273, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9656094701294958, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9689783142050787, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9658773401892982, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9639426623940014, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9650938253108534, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9553576299304183, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9603020224705777, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.940802576493598, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9542837339752269, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9325568892710316, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9472678235892028, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 0.06436871819198131, "validation/loss_best": 0.07410280406475067, "validation/acc_best": 0.9771825396825397, "validation/f1_best": 0.9747516542172218} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 0.7661905178427696, "train/grad": 0.15694349583238362, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6822698974609374, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6319036865234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5504681396484377, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.471171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.3928866577148438, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.2835787963867187, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.1582273864746093, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.017494964599609, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.833175811767578, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.6421339416503906, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.4626354217529296, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.2080118942260742, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.9777280521392823, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.6908167445659638, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.4890937173366547, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.361552392244339, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.2650956080853939, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.2032875697314739, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.16494856268167496, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.14280676264315845, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.1241681190021336, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.11058369275182485, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.09926055936142802, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.09002842780202627, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.08226205448620022, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0745278595201671, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.06870443806052208, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.06410957830958068, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.058626216128468515, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.052935347855091096, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.04867615284398198, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.04573440957814455, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.043206398310139775, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.04193088763393462, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.04122674733400345, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.04084471944719553, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04295582647435367, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05165676886215806, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.06612926289439201, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.09215881739743054, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.10278926745988429, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1235631406493485, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.2092709476966411, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4141458381991833, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.7599086144566536, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.3554107548017056, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.268832774683833, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.4256641828920693, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.9147368159517646, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012375029786489904, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012220429885201157, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012004413083195687, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011877109631896018, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011838489337824285, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011877016709186138, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01195392380002886, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011984494621865452, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011874610367231071, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01160473693627864, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011283624498173595, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010851882072165609, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01047499594744295, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009745256006717683, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008866411168128252, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008087684558704495, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007360474090091884, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006870970379095525, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006563482949277386, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006380443397210911, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006222703249659389, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006109791685594246, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006033264329889789, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0059668993123341355, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00589933916926384, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0058046936721075325, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005706532901385799, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005619154087617062, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005508733985479921, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005376513127121143, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0052872736757854, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005229641695332248, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.005222283993498422, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.005270129744458245, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005361085331387585, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005433343112963484, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005568944317637943, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006453340519801714, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.007749001532210968, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009878237575176172, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009683989465847843, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011807108401553705, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01696101034700405, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027461651332996554, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04478418070546695, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0600685810491268, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.058440430099144576, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.05962752017219351, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0738667352032777, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6024181842803955, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.542569160461426, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.445418119430542, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.3496241569519043, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.2538700103759766, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.119223117828369, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.9655945301055908, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.7959516048431396, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.5810080766677856, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.3662388324737549, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.168168067932129, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.8882004022598267, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.6507668495178223, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.41725876927375793, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.2976956367492676, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.23460425436496735, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.18859606981277466, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.15712222456932068, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.13531017303466797, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.12159188836812973, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.10950640588998795, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.10073918849229813, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.09389346837997437, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0884396955370903, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.08453772217035294, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.08166882395744324, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.08046849817037582, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.0800291895866394, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.07866887748241425, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07596824318170547, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07396268099546432, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07329658418893814, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.0716000348329544, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07062020152807236, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07129186391830444, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07456491887569427, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08048786222934723, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10570916533470154, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.12972111999988556, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17209668457508087, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16978996992111206, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.18931400775909424, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.3775881230831146, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5849828124046326, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.3378591537475586, "validation/loss_045_lr3.1e+01_wd1.0e+00": 1.5528287887573242, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.603735327720642, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.172154664993286, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.6221506595611572, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.1793154761904762, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.1884920634920635, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.22569444444444445, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2934027777777778, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.33903769841269843, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.4412202380952381, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.544890873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.5798611111111112, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.6659226190476191, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.7824900793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.8628472222222222, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9159226190476191, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9325396825396826, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9456845238095238, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9526289682539683, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9580853174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9613095238095238, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9650297619047619, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.96875, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9719742063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9729662698412699, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9739583333333334, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9742063492063492, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9737103174603174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9734623015873016, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9729662698412699, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9662698412698413, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9630456349206349, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9662698412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9635416666666666, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9598214285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9533730158730159, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9479166666666666, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9479166666666666, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.025656081956850874, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03644379887171332, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.06732354032145016, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.1048762658027183, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.13366125561326717, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.2543531276702822, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.34130306170420865, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.39251416524763044, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.5639250901833921, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.7267849746884182, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.834609198045459, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9021778259974237, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9213814431879401, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9362512100760083, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9437807139466785, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.94980439310177, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9532423173734463, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9579364291204749, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9629651674170855, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9626712204067277, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9652743927558989, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9665477053014881, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9675759476692889, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.968995821380384, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9686677414921955, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9677825548585955, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9697329141970159, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9704223814273463, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9696866081065265, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9718946160799119, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9734849981204153, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9736231440786847, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9740896543598655, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9750659507342915, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9744192661729796, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9749209602598338, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9752817217100329, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9696822533611398, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9614983335260598, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9600848347058708, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9566420833988568, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9633384990620103, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.959365334795743, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.956476869293605, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.956168220363216, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9436820610484149, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.95869225691694, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9472953889727177, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9441842653686356, "id_best": 33, "lr_best": 0.00129, "wd_best": 0.05, "train/loss_best": 0.04193088763393462, "validation/loss_best": 0.07062020152807236, "validation/acc_best": 0.9774305555555556, "validation/f1_best": 0.9750659507342915} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 0.635998474508524, "train/grad": 0.1446331513673067, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.520909423828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.450775451660156, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.335512390136719, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.220321044921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.1049835205078127, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.944496612548828, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.76592529296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.5753941345214844, "train/loss_008_lr7.4e-02_wd1.0e+00": 1.3410606384277344, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.1088923072814942, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.897946434020996, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.6310386025905609, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.44970072746276857, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.30085489004850385, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.2287876334786415, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.18948633335530757, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.1590820564702153, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.13660943541675807, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.11977781204506754, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.10841173287481069, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.09783496269024909, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.08925981157459319, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.08163299314677715, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0748387737479061, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.06867769309319556, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.062067740950733426, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.056737269656732675, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.052419556761160495, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.04726230722852051, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.04229295411147177, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.03884890536777675, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.03658956414088607, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.03416642295196652, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.03274596506729722, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.03255909622646868, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.035115461368113755, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.04490673927590251, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.05125919230282307, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.06492810245603323, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.07116476022638381, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.07949113780632615, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.21377279481850564, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.4212789255939424, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.4736367122363299, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.8088658874295652, "train/loss_045_lr3.1e+01_wd1.0e+00": 1.0245795506983995, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.340224767345935, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.3492121267970651, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.747589157661423, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011831726394593716, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01173325756099075, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011721278340555728, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011802180847153067, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011877995487302541, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011887058257125318, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011734964866191149, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011426518792286516, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010987407830543815, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010620090239681303, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010277224024757742, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009504712799098343, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008572779267560691, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0075013101845979695, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0069147127866745, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006605180818587542, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006384128007339313, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00622661693370901, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006100614828756079, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006012883414514363, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005932339312275872, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005865132372127846, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005797364092431962, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005728696590522304, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0056441921892110255, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005531525306869298, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005425708031980321, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005332364625064656, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.005221332173678092, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.005123745260061696, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005084828932303935, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0050383391726063565, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0049016889784252275, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.004775453929032665, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004762926140101626, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005031424215412699, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005882975457207067, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.006578289243698236, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00715932439736207, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008057566526258598, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008742923471254471, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.017721311312634498, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02558576502258802, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.031142464977227745, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0437113184426064, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.04643868529459872, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.05706837461283385, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.054856130891280934, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.062334360629506896, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.446173906326294, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.365889549255371, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.232454776763916, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.0983922481536865, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.964756965637207, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.7815192937850952, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.5827845335006714, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.375932216644287, "validation/loss_008_lr7.4e-02_wd1.0e+00": 1.1243500709533691, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.8757868409156799, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.6623062491416931, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.436403751373291, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.31345656514167786, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.2242612987756729, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.1813383549451828, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.15669071674346924, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.1366935521364212, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1212235540151596, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.10937699675559998, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.10142572969198227, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.09404692053794861, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.08831457048654556, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.08352020382881165, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07937218993902206, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.07574833184480667, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.07210215926170349, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06975741684436798, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06890487670898438, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06867682933807373, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.07031374424695969, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.07192014157772064, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.07159870117902756, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06774640828371048, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06616128981113434, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06949206441640854, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07362222671508789, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07701101154088974, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10786276310682297, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11296837031841278, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.13089214265346527, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1410776972770691, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.3305577039718628, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.4304471015930176, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.6563076376914978, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.0709532499313354, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.870962381362915, "validation/loss_046_lr3.6e+01_wd1.0e+00": 1.1058801412582397, "validation/loss_047_lr4.3e+01_wd1.0e+00": 2.1793580055236816, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.687326669692993, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.21329365079365079, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2725694444444444, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.345734126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.45262896825396826, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.544890873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.5892857142857143, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.6812996031746031, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.7936507936507936, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.8814484126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9188988095238095, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9303075396825397, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9466765873015873, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9541170634920635, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9595734126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9613095238095238, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9640376984126984, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9675099206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9694940476190477, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9719742063492064, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9764384920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9754464285714286, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9739583333333334, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9759424603174603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.970734126984127, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9737103174603174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9652777777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9600694444444444, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9642857142857143, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9568452380952381, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05891911701786865, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.09677850935201975, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.14140168242386594, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.2677322703216142, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.3441198739057058, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.4123577315263392, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.5969529249754743, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.7438801819991132, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.8553084763687295, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9035371895487885, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9192620134966673, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.937266725838983, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9463043679150428, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9521626576421528, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9538745238224214, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9560674586223692, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9600150561778313, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9619066311144812, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9644198100727804, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9662706349843544, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9690217760169925, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9704857441568961, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9720437952376673, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9720482901034796, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9723135464861601, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9733621061348107, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9755202191493169, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9749899246694662, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9746835375709576, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9743385003142351, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9734766360277234, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9755721673327268, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.97701083681609, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9762612017386213, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9780162902117011, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9793410352083547, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9790052823665434, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9719017590422412, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9748905995703784, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9674579297307505, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9702590835062853, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9591033294295487, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9639929393345131, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.955328766304785, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.960535469240162, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9676169076451218, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.969039649604124, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9500272973054832, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9552831410171512, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 0.04490673927590251, "validation/loss_best": 0.07701101154088974, "validation/acc_best": 0.9801587301587301, "validation/f1_best": 0.9790052823665434} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 0.48516977950930595, "train/grad": 0.11613997273147106, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.3792169189453123, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.2882537841796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.135970458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.9838059997558595, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.8345193481445312, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.6342727661132812, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.4223610687255859, "train/loss_007_lr6.2e-02_wd1.0e+00": 1.203712501525879, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.938299789428711, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.6927279663085938, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.5103055465221406, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.34335228353738784, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.25836150601506236, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.19561313174664974, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.16348336532711982, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.14388824094086886, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.12671499030664563, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.11240799050778151, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.10064228881150485, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.09214468670077622, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.08354356398805976, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.07612296271137893, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.06902365925721825, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.06235138604417443, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.05603452167473733, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.0492654478829354, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.04395784193649888, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.03983443223871291, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.034922741437330845, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.03027348714880645, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02691837233491242, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.024492041878402232, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.022407031003385782, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.02192940833978355, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.022660234859213233, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.027512407237663863, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.026877217357978225, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.03540117098018527, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0475442813616246, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.058432140052318574, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.06770846179686486, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.13661198064684868, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1936212877742946, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.3838033933192492, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.4986815802846104, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.4527732166554779, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.6815680726617575, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.9120560966990888, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.0269365932326764, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011725328783504664, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011785037624649703, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011908505805768072, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011941391811706125, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011845605722628534, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011546263908967376, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01112536943051964, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010742874871939421, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010381161118857563, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009852037078235298, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009103382548782974, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0080149258649908, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007271867858944461, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006647426220588386, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006331060234224424, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006143686784198508, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005988573293434456, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005875902615953237, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0057965844590216874, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005744795426726341, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005684683977160603, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005618985819164663, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005530316867516376, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005421446426189505, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.005289817831362597, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005138535310397856, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004992428730474785, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004861883523408324, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004686149849148933, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004496761566551868, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0043020521895959975, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0041653714852873235, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.004085591070761439, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0041121455577376766, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004362305445974926, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004864774707239121, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004787074296327774, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.005720128037501127, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006485187135185697, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007721967981633497, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008179912584164412, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.013929829545668326, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.016828515458232687, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027253516974578246, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.03164688724711134, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03220133137002164, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.038576588198423266, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04659018676350974, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.050766445582514266, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.2985169887542725, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.1963353157043457, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.0258867740631104, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.8576278686523438, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.695424199104309, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.4828587770462036, "validation/loss_006_lr5.3e-02_wd1.0e+00": 1.2612119913101196, "validation/loss_007_lr6.2e-02_wd1.0e+00": 1.0326166152954102, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.7595323920249939, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.5324119925498962, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.3867875337600708, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.2677714228630066, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.20925071835517883, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.16506819427013397, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.14155423641204834, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.12691177427768707, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.11400207132101059, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.1034863293170929, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0952281802892685, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08955437690019608, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.08429274708032608, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0802847370505333, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07668349891901016, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.07354147732257843, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.07089037448167801, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0683872327208519, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0672418624162674, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06644158810377121, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06567081809043884, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0656660720705986, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06713968515396118, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06885833293199539, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.07014195621013641, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06985239684581757, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06736955046653748, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07313502579927444, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08858060091733932, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.120073601603508, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10286445170640945, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11246906965970993, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1261209398508072, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.21523557603359222, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.26321226358413696, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.5008081793785095, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.6718488335609436, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.8649319410324097, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.9782006144523621, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.3002159595489502, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.7928351163864136, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.3209325396825397, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.373015873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.515625, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.5634920634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.6158234126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.7281746031746031, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.8382936507936508, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.8933531746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9243551587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9387400793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.949156746031746, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9543650793650794, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9585813492063492, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9652777777777778, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9682539682539683, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9694940476190477, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.970734126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9729662698412699, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9739583333333334, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9771825396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9756944444444444, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9732142857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9751984126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9734623015873016, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9685019841269841, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9714781746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9717261904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9694940476190477, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9672619047619048, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9665178571428571, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9704861111111112, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.117194264272167, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.17262931434182513, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3189242649912698, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.36174575977787493, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.4660199809505338, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.6661794259931061, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8038448057484096, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.8777015129903525, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9152086201969271, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9290488371176563, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9404001067975206, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9456313124690225, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9514563474523738, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9589870946066299, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9620814803515894, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9635105449246282, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9636099169713541, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9653843412321331, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9679147955164977, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9684702977238725, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9688408594726654, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9700744381698551, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9711000812286683, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.973586243211317, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9755436907811457, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9769515993696797, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.976856705004047, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9767232306728649, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9784858780360476, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9773771286786528, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9762425727407658, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.974982789114255, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9752973193257857, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9751789010482061, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9778990407888845, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9786811411218134, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9703068644352713, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9689280150179099, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9714629899507647, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9695307150019484, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9699244276832483, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9651357922134477, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9656046123141516, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9633115740208932, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9684747113430108, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9616481783342556, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9607355259874143, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9645616563245709, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9668261413277195, "id_best": 28, "lr_best": 0.00057, "wd_best": 0.05, "train/loss_best": 0.034922741437330845, "validation/loss_best": 0.06567081809043884, "validation/acc_best": 0.9801587301587301, "validation/f1_best": 0.9784858780360476} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 0.3826651695370674, "train/grad": 0.09291572289541364, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.230038757324219, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.117057189941406, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.9299951171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.7487493896484374, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.5773891448974608, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.356429901123047, "train/loss_006_lr5.3e-02_wd1.0e+00": 1.1266584014892578, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.8908282470703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.627752673625946, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.43521236300468447, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.3223432067036629, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.2320317579805851, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.1866841673105955, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.15075096640735863, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.13049021176993847, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.11706715391948819, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.10460122147575021, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.09373035927303136, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.08436177394352853, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07730512769892811, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.06993251814506948, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.06336435914039612, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05696920611895621, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.05089119060896337, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.04523236606270075, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03922294460237026, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.03476698969490826, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.031270348345860836, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.02739920303225517, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.02341311770491302, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.02031089808791876, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.018271407466381787, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.01679364500567317, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.01592130783945322, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.014006944494321943, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.016140897013247012, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.024564556172117592, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.023005093978717923, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.03072941454127431, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.04667305270209909, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.05419578960165381, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.06542604118585586, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09904829450882971, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.18874636161141098, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.24291722615249456, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.21645536304451526, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.3537982286605984, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.6086961336992681, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.7129535400401801, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011887271413579583, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011959588550962508, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011946754953823984, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011745865009725093, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011423776927404105, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010953115858137607, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010565510806627572, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01024788391776383, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009576890259049833, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008577378657646477, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0077263852441683415, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0069064818834885956, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006476782492827624, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006140860327286645, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0059463016176596285, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00581464291899465, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005690545544493944, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005591875105164945, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005502211459679529, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005429257887881249, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005337463419418782, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005230832134839147, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005106190283549949, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004981161387404427, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004862367835594341, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004722130588488653, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004606324682245031, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004484120988636277, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0042919318989152085, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0039949083644023635, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00371070889668772, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0035192212833499072, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003352832252567168, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0032666617022186983, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0030081407997204226, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003444484561914578, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.004605127573013306, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004433155934966635, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.005566351815723465, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.007150498953997157, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00770569713502482, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008057828696055367, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00988046798508094, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.016016988349912074, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.021575451936893406, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02078309803962418, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.028320223581720812, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.037606539412822604, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.04146740154305838, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.158308982849121, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.0353806018829346, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.834063172340393, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.6421825885772705, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.4635367393493652, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.2350391149520874, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.9971386194229126, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.7569335699081421, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.5121408104896545, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.3537918031215668, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.2674809694290161, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.19979731738567352, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.16544745862483978, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.1375742405653, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.12142466008663177, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.11082837730646133, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.101192407310009, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.09327209740877151, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.08698445558547974, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.08260811120271683, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07821355015039444, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07472724467515945, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07146705687046051, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06854870170354843, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06607476621866226, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06396795064210892, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06280317157506943, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.0617842897772789, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.061235275119543076, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.061407070606946945, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06192581728100777, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.061594538390636444, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.060994651168584824, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06296373158693314, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07059768587350845, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07731478661298752, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09000200033187866, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.0876031368970871, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09046813100576401, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1149010956287384, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13599547743797302, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1394936740398407, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.17360542714595795, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2915913462638855, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.528289794921875, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.6154789924621582, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.6462632417678833, "validation/loss_047_lr4.3e+01_wd1.0e+00": 1.0327118635177612, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.1631830930709839, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.3990575396825397, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5042162698412699, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.5615079365079365, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.6341765873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.7368551587301587, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8469742063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9007936507936508, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9248511904761905, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9404761904761905, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.951140873015873, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9563492063492064, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9615575396825397, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9645337301587301, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9675099206349206, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9729662698412699, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9744543650793651, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.980406746031746, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9776785714285714, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.980406746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9761904761904762, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9739583333333334, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9724702380952381, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9779265873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9712301587301587, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9749503968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.2034200304094821, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.30917330382524505, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.3659615543668386, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.5081699170198657, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.6783443333257119, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8137027905467061, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.8866796165345511, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9140707799797367, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9304855358893456, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9431519233003447, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9493617428964986, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9548274172876722, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9583580345454246, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9607162785035166, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9638672154320861, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9655371613228516, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9674037204102387, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9678933835985996, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9694923478917219, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.970439832801531, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9710473724175068, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9716385512399057, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.972185621662915, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9747299811453765, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9765470149755868, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9765490451354308, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.978316283645821, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.977779238475308, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9787162926582708, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.977858576293869, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9787381170659806, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9788694661391182, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9797078815524989, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9779738021553797, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9788242343349426, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9763664183814565, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9773600578862081, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9764933694288654, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9799303837381271, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9758738600956173, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9711451246275293, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.973060850292317, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9726217068219495, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9713052813685303, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9668020864450918, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9685351580760663, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9723473676521976, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9691645698465582, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.970740194494244, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 0.01679364500567317, "validation/loss_best": 0.060994651168584824, "validation/acc_best": 0.9809027777777778, "validation/f1_best": 0.9797078815524989} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 0.3177031743526459, "train/grad": 0.07665733756497502, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.09572021484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.96388427734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.7505267333984376, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.5506207275390624, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.3665627288818358, "train/loss_005_lr4.5e-02_wd1.0e+00": 1.1315095520019531, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.8876098442077637, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.6535870170593262, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.4376196002960205, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.30806604623794553, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.23846944972872733, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.18295345738530158, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.1537980929762125, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.12888427678495645, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.1138548251800239, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.1035258512571454, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.0936486700642854, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.08469827054999769, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.07671070194803178, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.07039567419327795, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.0635801743157208, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.05736266548745334, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.05112506072036922, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.04506842241622508, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.0393690062686801, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.03325371718965471, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.028711587311699985, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.025081903049722312, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.020622982038185002, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.016113328589126466, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.013301390958949923, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.011656241668388247, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.010508847897872329, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.01014120263978839, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0094203379470855, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.011015212778002024, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.01299243649467826, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.02233547658659518, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.014784611789509653, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.029462901754304768, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.052923484072089196, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.03708972572349012, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.04489254702813923, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.06275164051912725, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13402696952223778, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.13354875723831355, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2021108632069081, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.45235716621391475, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.5292010475881398, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012000914933159947, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012008847738616168, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011805858057923614, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011426290064118803, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01102293231524527, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010596061628311872, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010243772962130606, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009660322871059179, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008558904367964715, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007567121353931725, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006967188494745642, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006498571154661476, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.006263581237290055, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006049666855251417, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005908117602812127, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005808847474399954, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005720559505280107, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005644404618069529, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0055608099204255265, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005481832161312923, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005380886582424864, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005272502768784762, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005132095851004124, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004943735161505174, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004718388410401531, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0044287822706974116, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004215127767238301, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004022617289156188, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0037102170492289586, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0032875347694789527, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002976020503847394, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0027813492559653243, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00260567612516752, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002511180691763002, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002234891693587997, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0025705157347692877, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0028062388211037613, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004168092351865198, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003300150631221186, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004949615400473704, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.007458323115961321, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.006260919034891685, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.006728700040934541, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009511229055758576, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.014461708671813208, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.015199751824551183, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01943450451347585, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.031537873426580265, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.03231343588728321, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.029355049133301, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.8894579410552979, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.666007399559021, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.4598968029022217, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.2716648578643799, "validation/loss_005_lr4.5e-02_wd1.0e+00": 1.031386375427246, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.7840339541435242, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.5603203773498535, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.37256455421447754, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.26735588908195496, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.21197021007537842, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.16759006679058075, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.14393003284931183, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.12337985634803772, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.1111091747879982, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.10278476774692535, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.09525640308856964, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.08880005031824112, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.083518847823143, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07977043092250824, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07614371180534363, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07319359481334686, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.07060598582029343, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.0681096613407135, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06588570028543472, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06368650496006012, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06270808726549149, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.062318142503499985, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06191924214363098, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0621991865336895, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06427933275699615, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06595256179571152, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06923976540565491, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07443112879991531, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07949160039424896, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.08439210057258606, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.09361220896244049, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10919798165559769, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.10190778225660324, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.12836989760398865, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.17686393857002258, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.12285172194242477, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1762705296278, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.2855948805809021, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3955433666706085, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.5213959217071533, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5716496109962463, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8274884819984436, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.8385751247406006, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5126488095238095, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.5580357142857143, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.6302083333333334, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.7447916666666666, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8385416666666666, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.8963293650793651, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9206349206349206, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9365079365079365, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.949156746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9561011904761905, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9588293650793651, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9627976190476191, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9662698412698413, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9685019841269841, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9717261904761905, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9744543650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9769345238095238, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9774305555555556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9761904761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9704861111111112, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9709821428571429, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.980406746031746, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9754464285714286, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9732142857142857, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9784226190476191, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.31769106753058424, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.35163553333498204, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.4933770548323109, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.6878061547803206, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.801415621090568, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.8811238916866566, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9102798924131786, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9256791818924242, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9396559607220832, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9483869561247008, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9516775777822699, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9555404429981456, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9597948626402132, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9612185208883413, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9634462019578319, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9661909857495014, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9677870473114237, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9702503099485605, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.970185915813082, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9687577086835297, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9703055181429072, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9717500551201861, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9741421479066117, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9738431751239399, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9749717500982988, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9761832119534223, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9773542104251001, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9763829932574405, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.977053336881005, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9782902433847654, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.977998183879362, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9777438151912596, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9775130281372865, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9788575212127435, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9756328951182193, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9751336944348706, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9788809381926207, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9752224507275542, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9743497413012935, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9632780408466894, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9670596990304364, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9780895197399802, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.974575359252996, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.972674708345228, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9750121352810568, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9710894630530726, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9728863191578608, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9747999942638014, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9750875911726455, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 0.03708972572349012, "validation/loss_best": 0.12285172194242477, "validation/acc_best": 0.980406746031746, "validation/f1_best": 0.9780895197399802} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 0.2675159391015768, "train/grad": 0.06805758476257324, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.9685342407226563, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.8219091796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.5905744934082031, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.3799955749511719, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.1884548568725586, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.9437106704711914, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.6984099626541138, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.49113800287246706, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.328547822535038, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.24012948900461198, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.19333837136626245, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.15492037851363422, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.13343417335301638, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.11391308922320605, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.10145238524302841, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.09256836107932032, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.08374466201290488, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.0755372339207679, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.06796271370723844, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.06192444022744894, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.05535513174720109, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04929261756129563, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.04326214921660721, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.03740275165066123, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.03191066958010197, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.026240215562283994, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.021830457299947738, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.01828634469769895, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.01423267443664372, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.010735274590551853, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.008833058029413223, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0076873330213129525, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.006967529291287065, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.006750366007909178, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.006430538771674037, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0068042722530663015, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00874021753668785, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.013885945212095976, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.01433491357602179, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.016902193361893296, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.03316533706150949, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.020738386837765573, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.01759608226828277, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.034262159131467344, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.08770774936303496, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10155808123759925, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10015468892641366, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.24609442381188273, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.33091962438076733, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01211710911244154, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012005081423558295, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01160215463489294, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011121111884713174, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010733582954853773, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010383013812825083, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009922875503543765, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009089363403618336, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00798756854608655, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.007213670113123953, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006788895867066458, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006449688586872071, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0062571981910150495, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.006066738193621859, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005941201919922605, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005852618383942172, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005756167622748763, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005659120834898204, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005542454128153622, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005427451303112321, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005270443211193196, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005089287856244482, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0048637166182743385, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0046076131978770715, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004337532290956006, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0040317201302968895, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003728849979233928, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0034111282028607094, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0029784341622143985, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0025503804057370873, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0022678664691920857, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0020468810684542405, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0019086585738841678, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0018641745606510086, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.001621359492673946, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0019413564776914428, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0023957133705698654, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003083397725731629, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.003122605141170425, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0037404223674275274, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.005399522593620301, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0043312934120760364, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.004313443343644003, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.006547290123675112, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011763569689130367, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012730545688186774, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.015163355705817212, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0240042597032141, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.029223722250036034, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.9148890972137451, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.7622625827789307, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.5242869853973389, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.3098278045654297, "validation/loss_004_lr3.8e-02_wd1.0e+00": 1.1150039434432983, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.8661389946937561, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.6245964765548706, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.43447190523147583, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.29448819160461426, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.22034935653209686, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.1810220181941986, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1483270227909088, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.12996916472911835, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.11355484277009964, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.1035597175359726, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0967206358909607, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.09056621044874191, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.0852547213435173, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.08086571842432022, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07765581458806992, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07445965707302094, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.07196065038442612, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06984561681747437, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06794175505638123, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06660265475511551, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06649032980203629, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06616311520338058, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.065861776471138, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06557703018188477, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06566085666418076, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06607028096914291, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06637886166572571, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06727411597967148, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06931278854608536, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07345563173294067, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07532976567745209, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08047404885292053, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.10354888439178467, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.11224832385778427, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.11272625625133514, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11750505864620209, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14225713908672333, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.18578383326530457, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.20971757173538208, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.3791661560535431, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.38994184136390686, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.5940820574760437, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.8279749751091003, "validation/loss_048_lr5.0e+01_wd1.0e+00": 1.1616891622543335, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5518353174603174, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.589781746031746, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7018849206349206, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8214285714285714, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.8814484126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.917906746031746, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.933531746031746, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9432043650793651, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9533730158730159, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9588293650793651, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9623015873015873, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9655257936507936, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9675099206349206, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9722222222222222, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9732142857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9774305555555556, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9784226190476191, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9786706349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9796626984126984, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9779265873015873, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9766865079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9766865079365079, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.982390873015873, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9756944444444444, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9764384920634921, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9751984126984127, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9732142857142857, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9722222222222222, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9689980158730159, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3460597539692412, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.4140155337526874, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.6301437162319676, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.7791063300651351, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8631963175041472, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9075427452034222, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9243561712758561, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9337825178455419, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9457625931221416, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9520457702432393, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.956327140673807, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9593647597765758, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9603341208680753, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9640202827637041, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9654856792316967, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.967517450925937, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9682404387699579, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9711791034236241, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9717276771597948, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9709813678844939, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9744366357160307, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9767028769293701, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9763238408429429, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9762622649065309, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9774181655884883, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9768130473270502, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9773271089384988, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9769986420275, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9768902057204834, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.976933218677138, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9758814943697691, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9760862318280692, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9765606530627996, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9759895612247783, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9777703463002868, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9778617160370876, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9768008071043042, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.975480121983682, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9746439167450311, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9719376051011194, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9786028030523872, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9772856344397256, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9710716212218177, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9737578059383184, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9723484730432953, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.971517647959339, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9713675008038074, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9702134225495824, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.963911515767309, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 0.03316533706150949, "validation/loss_best": 0.11750505864620209, "validation/acc_best": 0.982390873015873, "validation/f1_best": 0.9786028030523872} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.23290990225970745, "train/grad": 0.055320426933467386, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.86645263671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.708562469482422, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.4651043701171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.2472156524658202, "train/loss_004_lr3.8e-02_wd1.0e+00": 1.049031982421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.7970656776428222, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.5630158805847167, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.3897511267662048, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.26730581134557724, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.2027352698147297, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.1678366696089506, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.13776706721633672, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.12000828061252833, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.1030668504908681, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.09183492886833847, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.08361966894939542, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.0753433332964778, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06741280199028551, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05993095514364541, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.053972913073375824, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04740415354259312, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04133496874943376, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03532858313992619, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.029669236587360502, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.02462297085672617, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.01945792424492538, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.015728795751929283, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.012941983053460717, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.010052339099347591, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.007417353661730885, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.005450593838468194, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.004185118936002255, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0033137959707528353, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.003239291151985526, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0023754906933754682, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.003245492521673441, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.004058557273820043, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.009992184536531567, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.004684768235310912, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00994145100004971, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.021970753548666833, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00987690013833344, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.011165857426822185, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.015098438374698162, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.043232411351054906, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.058960239039734005, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.06149665816687047, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.14563364739529788, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.23367107558995484, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011929142875596882, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011719939573667943, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01120686465408653, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010726232784800232, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010399317401461303, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01002460040152073, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009299191196914762, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008279403659980745, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0072584474203176794, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006659482615068555, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0063566758343949915, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006113200051477179, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005971279195509851, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005818613301962614, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005721430436242372, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005647157803177833, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00555987152387388, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005453903180314228, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005324544162722305, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005195504673174582, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005024582324549556, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004833250705851242, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004599336935789324, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004324156076763757, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004038552784477361, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003672451876627747, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0033264206122839823, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0029941889600013385, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0025808925593446474, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0021257953697931954, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0017326501016214023, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0014302579545619665, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.001159220082772663, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0011742689577658894, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0009739750301832828, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.000997707087526578, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0014036246453451894, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002487397528557267, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0013696684071919662, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0021671300069101562, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.004226124507893019, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0027811905885710077, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0023760100880470957, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.004318406065893783, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.007389257186263055, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009270993302844165, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009851826562945885, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014887414618621168, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.021443029284461776, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.8168675899505615, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.655227780342102, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.4085149765014648, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.1886545419692993, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.9883474707603455, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.7366880178451538, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.5135568976402283, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3566090762615204, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.2491769790649414, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.1928386241197586, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.16239412128925323, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1361652910709381, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.12092726677656174, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.1068807914853096, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09810435026884079, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.09219806641340256, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08662064373493195, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.08192633837461472, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0779721662402153, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0750865787267685, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.07201283425092697, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0692768320441246, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06673353910446167, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06477843225002289, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06345837563276291, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0626300796866417, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06261269003152847, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06273547559976578, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06334187090396881, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06457563489675522, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06588058173656464, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06674427539110184, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06816971302032471, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.07178295403718948, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07445181906223297, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07442403584718704, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.08044901490211487, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.086307592689991, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08698758482933044, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.09043411165475845, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13723565638065338, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.10865412652492523, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15449737012386322, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.19727879762649536, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2714115083217621, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.37008658051490784, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.38793256878852844, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.4669056832790375, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5942250490188599, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5724206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6336805555555556, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.7671130952380952, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8611111111111112, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9005456349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9250992063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9389880952380952, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.949156746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9563492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9608134920634921, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9645337301587301, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9672619047619048, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.96875, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.970734126984127, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9719742063492064, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9737103174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9786706349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9794146825396826, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9789186507936508, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9781746031746031, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.980406746031746, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.980406746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9771825396825397, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9784226190476191, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9791666666666666, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9776785714285714, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9786706349206349, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9796626984126984, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.3838497364440186, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5044593869924826, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7159635524646125, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8358808052218587, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.8875189159831651, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9154800259026628, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9291529770204188, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9413877102466215, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9488738347916904, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9541742680335303, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9581505278719731, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9603244515253293, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9616524771599935, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9642486298007975, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9666550756298742, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9685108020654989, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9687291574243775, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9709283383605357, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9716926614167407, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9724960658093453, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9740208078484265, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9760294120485717, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9766988053661882, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9767903433265314, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9753490129951038, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9777622443078423, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9780098119578766, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9770265112869266, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9776864931902571, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9776414179847083, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9779748341480722, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9782674440027256, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9788719297815528, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9785450802264913, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9772410420642996, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9777117052922085, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9778826894748388, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9788104811897814, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9777380754047222, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9786383626843732, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9766676006514924, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9791036746000814, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9749161510029511, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9760424617537663, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.974246132175906, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9759960777190289, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9739915232403817, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9768929026229086, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9748689459567433, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.00994145100004971, "validation/loss_best": 0.09043411165475845, "validation/acc_best": 0.9816468253968254, "validation/f1_best": 0.9786383626843732} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.2066839525103569, "train/grad": 0.04612772163003683, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.771763153076172, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.6065359497070313, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.3561989593505859, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.133950538635254, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.931317367553711, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6814969062805176, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.4701548945903778, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.32836897373199464, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.23289285376667976, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.18245601102709771, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.1544925256073475, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.12947849683463575, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.11404380584135651, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.09907044444233179, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08897731753997505, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.08149016702547669, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.07384539351798594, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06635593115352094, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05923173176124692, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.05340740470215678, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04687470841221511, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.04078999247401953, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.03461803437210619, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.028764606649056078, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.023301103478297593, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.017583796530961992, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.013515253188088536, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.010569262774661184, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.007521977061405778, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0049828759022057054, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0034329471364617347, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.002702660970389843, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.002642313186079264, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.002529133390635252, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.002245956873521209, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0015736532956361772, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0036400829441845415, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.004320877278223634, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0027533274050801993, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.003272979920729995, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.010273409383371472, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.003948081228882075, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.004496926991268992, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.010410784864798189, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.019776814971119164, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.02510410524904728, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.03980698828585446, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.050016662757843736, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.09051570575684309, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011830583442933857, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011520446930080652, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010925731109455227, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010467402157373726, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010162029205821455, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009663657865021378, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008750208271667361, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007744265832006931, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006914544464088976, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006481063137762248, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006269575520418584, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.006087605610955507, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005970068543683737, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005840756503166631, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005749031096929685, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005670430528116412, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005574626367888413, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005457117309560999, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005306632890133187, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005156826568418182, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004950725217349827, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004716682529542595, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004442664843518287, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004132722495123744, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0037888769930577836, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003335785208764719, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0029116618949046823, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00251488385227276, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0020104470718069934, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.001481650342757348, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0010784885435350588, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0008545553224757896, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0007365138632303569, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.000711904851395957, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.000584850444292897, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0004315876920099981, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0009570498326115739, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0010958258549862876, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0009368253962577455, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0012150769287973162, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0024968915020610895, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0013477357255081302, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0016935410259362983, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0025290237753142985, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00455049356855609, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.005625368856219504, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.007833357797104257, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.007808080896322899, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011907792312797611, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.7355711460113525, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.5681116580963135, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.3158127069473267, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.092089056968689, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.8879207372665405, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.6400465965270996, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.438266396522522, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.3072521984577179, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.22037260234355927, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.17448492348194122, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.14940257370471954, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.12694098055362701, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.11366685479879379, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.101291224360466, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.093646340072155, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08835872262716293, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08345808833837509, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07928192615509033, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07563772052526474, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07284176349639893, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0699014738202095, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06723611801862717, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06527817994356155, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06374618411064148, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0631335973739624, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06293492764234543, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06367642432451248, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06443142145872116, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06559611111879349, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06687109917402267, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06718854606151581, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06651550531387329, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06605402380228043, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06663215160369873, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06719856709241867, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07039357721805573, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.0738164484500885, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.08368087559938431, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.09391946345567703, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.08259058743715286, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.11040607839822769, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09594164788722992, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11864995211362839, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.17760217189788818, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2652660608291626, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.2830287516117096, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2781725227832794, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3914489150047302, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.5429630875587463, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.5947420634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.6775793650793651, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8115079365079365, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8809523809523809, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9149305555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9315476190476191, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9441964285714286, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9528769841269841, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9600694444444444, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9632936507936508, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.966765873015873, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9712301587301587, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9724702380952381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9771825396825397, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.980406746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9818948412698413, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.980406746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9789186507936508, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9796626984126984, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9759424603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9789186507936508, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.982390873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9764384920634921, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.42772626807528047, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.5930397962765499, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.7704554545918192, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8604099425616532, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9037577258655032, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9212232354425021, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9358715743540729, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9452835091223525, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.953405745115264, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9571091591059332, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.960588916265013, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9634632352861036, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9643474970423187, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.965880386548258, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9680717278586967, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9685913542869911, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9700441996015743, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9713989918933758, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.973325923729643, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9752852705163642, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9783840766867107, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9796333598734076, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9785476728523028, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9786092939210287, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9789764981049913, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9785671222031553, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9783451145637512, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9779772585218203, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9776332453063054, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9773869660231751, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9776974939713506, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9785944989755888, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.979535846977668, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9796373325536807, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9790980676430707, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.977951164911165, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9811812935770499, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9820081166250958, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9778881581249882, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9778320030179702, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9797428557147393, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9791276280268771, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9751655920468448, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9763764433901544, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9740380128218641, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9758497813484018, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9789813380684358, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9756171052902868, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9714884983003677, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.004320877278223634, "validation/loss_best": 0.08368087559938431, "validation/acc_best": 0.9826388888888888, "validation/f1_best": 0.9820081166250958} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.1887164318561554, "train/grad": 0.04138046168722212, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.7028346252441406, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.5326290130615234, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.2774730682373048, "train/loss_003_lr3.3e-02_wd1.0e+00": 1.0512615203857423, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.8456348037719726, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.6017218065261841, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.41080739617347717, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.29031125202775, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.21077268838882446, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.1682749553769827, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.14413340348750353, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.12168785158544779, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.10751924268901349, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.09347141877748072, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.0838659317791462, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07657489040866494, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06897249070927501, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.06149324141442776, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05432572096586227, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.048337083039805294, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04168970540165901, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.035535308578982946, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02948736622929573, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.023829451026394964, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.018767882566899062, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.013731252504512667, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.010308915423229337, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.007898707240819931, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.005483280923217535, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0036635331343859434, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.002565709725022316, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0019161287788301707, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.001400057775899768, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.001057899547740817, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0008266327064484358, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0006190112885087729, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.001399283930659294, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0013449733704328536, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0011976960208266974, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0014424822758883238, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0014657411631196738, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.001581963449716568, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.002395601747557521, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0022726619429886343, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0052024458907544615, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.006524227149784565, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.009772394355386495, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.019235961847007276, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.042386722825467585, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011777467108331621, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011418501492589711, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010814027101732791, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010392822851426899, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010074587697163224, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00940836037741974, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008358096526935697, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007390287208836526, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006662170022027567, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0062841817073058335, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006085423505865038, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005907892010873184, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005794182621175423, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0056880779808852824, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005615388399455697, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005553428904386237, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0054638423339929435, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00535183398576919, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005205619061598554, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0050462964968755845, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00482704761554487, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004566309264337178, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00424623278377112, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003876991168508539, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0034941501788853203, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003002932867675554, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0025696958860498853, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0021720550207828637, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001677729058865225, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0012469750062882668, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0009347863617767871, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0007258002431262867, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0005385794278663525, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0004214390394918155, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0003384120409782554, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.000302450300887358, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0005033374335255303, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0004932393068582996, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00044129838560820646, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0006345041181427291, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0007201619238179546, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0008338786827994227, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0011189975556136745, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0013426087117311613, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002571961799089699, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.002848492057424673, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0033378959273534193, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.005331279285529296, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.008379144619067119, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.6707762479782104, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4994642734527588, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.2436435222625732, "validation/loss_003_lr3.3e-02_wd1.0e+00": 1.0166981220245361, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.8107115626335144, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5704644322395325, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3880915343761444, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2756039500236511, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.20217430591583252, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.16332563757896423, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.141382098197937, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1217268779873848, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10982108861207962, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0986829400062561, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.09161316603422165, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08681445568799973, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.08217030763626099, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07824939489364624, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07474030554294586, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07198414951562881, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06922324746847153, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06688177585601807, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06510738283395767, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06375688314437866, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06309430301189423, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06268661469221115, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06250900030136108, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06295309215784073, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06321538239717484, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0640716478228569, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06490861624479294, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06559441983699799, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06653151661157608, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.0681162178516388, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.0694490298628807, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07107511162757874, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07348800450563431, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07751306146383286, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08276341110467911, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07829387485980988, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09977138042449951, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.09688597172498703, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1113230511546135, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.16000930964946747, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.2199542075395584, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.25043368339538574, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.23213960230350494, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.30796948075294495, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.4429510831832886, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6240079365079365, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7125496031746031, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8430059523809523, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.8960813492063492, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9223710317460317, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9360119047619048, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9466765873015873, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9546130952380952, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9610615079365079, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9650297619047619, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9680059523809523, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9702380952380952, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9784226190476191, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.980406746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.980406746031746, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.980406746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9836309523809523, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.980406746031746, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9786706349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.4821060920445072, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6508305860413388, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8101850034058542, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8793504330172626, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9120908227746446, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9259729471714783, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.937223889409646, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9471929248848422, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9542858785346644, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9585200933951059, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9613570472641338, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9640153175230767, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.964871074976333, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.966152727445554, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9684518850014343, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9679910773179753, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9704439920692257, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9713843336574661, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9731224987323763, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9760181576520691, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9775672147299853, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9784258449606279, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9783066624132776, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9768388752974934, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9775248245943962, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9781128700311316, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9799544216400895, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9794742546298051, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9786340291974877, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9788484100242963, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.978473992306559, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.978329092831952, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9781384121142286, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9785555746233312, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9793903767508351, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9781924261794795, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9808060807358698, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9826378766674808, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9790406573138875, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9805310577881998, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.981050823441725, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9780472376959573, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.976784548378965, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9768179544425689, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9788812144603302, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9773608982935121, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9805336385635061, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9785981003652321, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9753781246747321, "id_best": 37, "lr_best": 0.00249, "wd_best": 0.05, "train/loss_best": 0.0013449733704328536, "validation/loss_best": 0.07751306146383286, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.9826378766674808} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.1774726824834943, "train/grad": 0.03833199387416244, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.641516876220703, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.4690109252929688, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.2126541137695312, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.9851316833496093, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.7793814182281494, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.5440046525001526, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3701447492837906, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2645014925301075, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.19533349327743055, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.1580886282771826, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.13657985247671603, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.11645824717357754, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.10359679644927383, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.09065930916927754, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.08162929699756205, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07472144341096282, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06735880562104285, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05997921193018556, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.05276617198251188, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04675538898445666, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.04007228434085846, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.03389861480332911, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02786071175709367, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.02217579336836934, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.01713417592458427, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.012166484976187348, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.008970896545797587, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.006868889508768916, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.004868492754176259, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.003420552695170045, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.00261034419760108, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0020726531837135555, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0014643253944814204, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0009981470555067062, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0006409631669521331, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0007611316349357367, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0005668256245553494, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00039017960429191587, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0004381321370601654, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0010305648762732745, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0006726787146180868, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0013579988572746515, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0007206548657268286, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.000788126140832901, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0038620884623378517, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.005473575619980693, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.008199263764545321, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.020316904671490194, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.016087570898234843, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011619437923654915, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01122067338321358, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010629484956152737, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010267719943076372, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009961726847104729, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009217510384041816, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00815544045995921, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.007276674949098378, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0066479961317963895, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006319205098552629, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006126616420224309, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0059332028543576595, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005805445916485042, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005688516476657242, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0056139489635825155, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005547429801663384, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005449761096970178, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005315633671416436, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005145579153904691, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004974692631803918, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004735448119463399, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004466953732189722, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0041345268810982815, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00374423862202093, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003304470894508995, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.002745394730445696, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002270560590113746, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0018851122820342425, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0014450569490145426, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0010642787545839382, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0008139570294952137, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0006299502291403769, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00044305167702987094, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00030932688293432874, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00020219311329128687, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00022521688652432203, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00019635825120985827, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00016187858822831912, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0001595111144342809, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00033247902686227347, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0002615372732539001, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0004808045916621495, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0002914655497158947, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0005008103802929754, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0011291975751727943, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0013244182077596586, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002115624906408899, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00403394714225619, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0031854464737418016, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.6211483478546143, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4473837614059448, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.1893373727798462, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.9602744579315186, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7536793947219849, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.5215844511985779, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.35447588562965393, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2544216215610504, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.18983034789562225, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.15530306100845337, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.13553579151630402, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.11752171069383621, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10639224201440811, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.096067413687706, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08947758376598358, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08483508974313736, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0805574357509613, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07668526470661163, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0732179582118988, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.07081805169582367, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06821839511394501, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06604089587926865, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06457409262657166, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06356184184551239, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06315650790929794, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06322968006134033, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06357825547456741, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06423527002334595, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06484781950712204, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0662137120962143, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06703822314739227, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06741659343242645, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06834711879491806, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06908099353313446, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.07002917677164078, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07137387245893478, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07384578883647919, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07765209674835205, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08361633867025375, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07963421195745468, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09547706693410873, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08990401029586792, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.11019398272037506, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.14553070068359375, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.20111128687858582, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.20818056166172028, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.23792190849781036, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.28087127208709717, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.3272619843482971, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6493055555555556, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7388392857142857, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8588789682539683, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9057539682539683, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9265873015873016, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9407242063492064, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9496527777777778, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9546130952380952, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9623015873015873, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9657738095238095, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9704861111111112, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9734623015873016, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9747023809523809, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9789186507936508, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9796626984126984, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9791666666666666, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9794146825396826, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.980406746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.980406746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9836309523809523, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9813988095238095, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9799107142857143, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9794146825396826, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9828869047619048, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.539205042490469, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.6835930956658993, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.833106926236341, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8941242933407161, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9174199243667697, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9324970925725774, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9411608706685725, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9471128984620857, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9556308976334081, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9590753322277528, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9626194871672679, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.963646524300609, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9645732257061975, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.967792011014253, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.967607426765139, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9691977475089063, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.970508338947005, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9724318906933427, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9730286706811762, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9751659004859425, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9764180656488696, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9785011457734553, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9786225398433853, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9773802864305106, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9763262482269196, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9778455861149127, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9777168297352473, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9782716046479416, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9779742395143417, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9780635929788841, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9782682710059298, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9786974814328472, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9794968529106343, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9791001870503018, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9794046072709413, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9789582982213274, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9814512612393412, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9828396335031955, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9785189614688522, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9808305664259664, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9809720539078226, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9788330386425171, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9764124894312215, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9772991723570944, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9795358984486985, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.977195195447681, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9781917390733326, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9762205361802129, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9816493048984475, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.0010305648762732745, "validation/loss_best": 0.07963421195745468, "validation/acc_best": 0.9836309523809523, "validation/f1_best": 0.9808305664259664} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.16598969157785176, "train/grad": 0.03572291687130928, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5893344116210937, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.41435791015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.15568359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.9263749313354492, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.7212427043914795, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.49477295398712157, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.33548000574111936, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.2412289696931839, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.17995959155261518, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.14651734299957753, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.12678785357624292, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.10798389624804258, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.0957666933350265, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.08343827439472079, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.07480213834904134, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06811001422815025, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06107256269082427, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05402827557176351, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.047164834793657066, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04151307661086321, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.035167972082272174, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02943937777541578, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02385817456059158, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.0187926075886935, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.014415805889293552, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.010276675866916775, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.0075028036348521706, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.00559795405715704, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.003786060595884919, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0024741757567971947, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0017546658869832753, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0013547612354159356, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0009416175540536642, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.000691954679787159, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0005319750308990478, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0004686391539871693, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0003092586155980825, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0002772384323179722, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00023928762413561345, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00021470478735864163, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00021828798577189446, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00030089606530964375, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00037237804383039475, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0003482815809547901, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0006259924359619618, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.0007901373971253633, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0007659914065152407, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.004162449268624187, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0021948339510709045, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01152947307098657, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01109306470490992, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010478251413442195, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010080484678037465, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009677261661272496, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00878163592889905, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007680043084546923, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0068542290246114135, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006315259095281363, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006065913422498852, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005917779803276062, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005767399508040398, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00566479132277891, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005559646904002875, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005477733545703813, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005393641234841198, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005279512034030631, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005121022354578599, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0049236632761312646, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004721366343437694, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004441090287582483, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004128177696256899, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003750940872851061, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0033370220217329915, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.002892090084569645, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0023586134050128747, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001899691031940165, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0015155872564355376, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.001093184413111885, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0007532372209789174, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0005609667021781206, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00044406102337234187, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00030918854038645803, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00021052908589808795, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00016042262644987203, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00014982220177444104, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00011448028899394558, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0001142199481046191, "train/grad_038_lr9.8e+00_wd1.0e+00": 9.942842064219803e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00014002170487287913, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00014805426307468395, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00021894153993883946, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00020568509805201529, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00027125471268554693, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0005181631990333335, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0003674166742873669, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.000660968489384215, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.002095403199081658, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0011999000203596082, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5848784446716309, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.4094865322113037, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.150058627128601, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.9193468689918518, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.7131963968276978, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4883788526058197, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.33209627866744995, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.24053235352039337, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.18150271475315094, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.1497814655303955, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.13138994574546814, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.11446905136108398, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10404784232378006, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.09416424483060837, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08783851563930511, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08348643034696579, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.07923587411642075, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07544054836034775, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07197999209165573, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06934689730405807, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06671763956546783, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06442423909902573, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06274982541799545, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06158655881881714, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.061009954661130905, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.060973700135946274, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06148279085755348, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06198524683713913, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06305747479200363, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.0643732026219368, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06540635973215103, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06609250605106354, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06722741574048996, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06819453835487366, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06909230351448059, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07072092592716217, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07316101342439651, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07688532024621964, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08183126896619797, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0788482055068016, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09370410442352295, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08639010787010193, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.10476575791835785, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1375570148229599, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.19361776113510132, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1871238499879837, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2046622633934021, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2261783331632614, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.27482545375823975, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6674107142857143, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7596726190476191, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8675595238095238, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9104662698412699, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9283234126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9424603174603174, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9523809523809523, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9568452380952381, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9625496031746031, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9670138888888888, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9692460317460317, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9709821428571429, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9724702380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9754464285714286, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9791666666666666, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.980406746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9821428571428571, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9833829365079365, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.982390873015873, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.980406746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9811507936507936, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.984375, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5740811208947557, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7090824376845998, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8448865926453386, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.8999465794940595, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9189416217947779, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9336623419287848, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.944419571046462, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9496821585016147, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9561502856097179, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9600204709232296, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9626465009021217, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.962769075587497, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9660119980461294, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9680517410944673, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9690805005325969, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9701474069104092, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9704434788851162, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9717572390097609, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9747081760970365, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9765139334278007, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9776680472876671, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9785737438813517, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9777139617823684, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9775328421198373, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9788652248554144, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9797483328354886, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9797255203509773, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9800209746959053, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9798122501375305, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9802842107540118, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9797347453201165, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9790288097673612, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9796698791297624, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.980528964705959, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9792072127292322, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9774473363798435, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9821228651159493, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9827541600558402, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9787225637873325, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9817378935712694, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9806181577333594, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9787655735019353, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9765244229012395, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9785004293818877, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9801037649194709, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9786964776184803, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9796075484396684, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9787339304354581, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9823737145403995, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.0021948339510709045, "validation/loss_best": 0.27482545375823975, "validation/acc_best": 0.984375, "validation/f1_best": 0.9823737145403995} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.16191758137196302, "train/grad": 0.0351646114513278, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5656800842285157, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.389682846069336, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1299932861328126, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.8998890113830567, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6954473495483399, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4747328579425812, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3228895762562752, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.23398923337459565, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.17585290797054767, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.14397086396813394, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.1250380450487137, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.10672118885442615, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.09473041315563023, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.08258854012936354, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.07401293660514056, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06739382672123612, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06028825778514147, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05327997509390116, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04640731596387923, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.040670777074992656, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.034286614190787074, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.02841002627275884, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02273211544379592, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.017490508705377578, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012959113968536258, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008862658310681582, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006325633125379681, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004683922193944454, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0031839107256382703, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.002096250206232071, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0014710206910967826, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0011163034010678529, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0007989210542291402, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0006049126479774714, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00046784824691712855, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00039345086552202704, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0002764793764799833, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.0002008247934281826, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00021371975541114807, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0003040757868438959, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00028295491822063925, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0003273950703442097, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002291823085397482, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0006161361187696457, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00017826078459620476, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00035530699416995047, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.000323867779225111, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0006753804348409176, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0008355849608778954, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01125141658820212, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01082161686848849, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010264826756902039, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009934765570797026, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00955194046255201, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008649830094072967, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007586101996712387, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006845993001479656, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0063907795632258055, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00618148005916737, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006065343603258952, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005929148566210642, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005831204106798395, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00572291596326977, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005627564664464444, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005535359631758183, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00540506731485948, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0052343318291241305, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0050297421059804035, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004817722049192525, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004532980744843371, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004206555751443375, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003816792751022149, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0033638528815936298, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0028528952022315933, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0022436825727345424, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0017689048017200549, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0013990746929630404, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0010031731731578474, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.000681907907310233, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00048494047954591226, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00036569153395248576, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002604439566493966, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00019707782434124965, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00015198358377347177, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0001396460772593855, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00010444304056363763, "train/grad_037_lr8.3e+00_wd1.0e+00": 9.812608217089291e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.971037585524755e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00011183806666053897, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.00011506209095223597, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00016593130844114512, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001535595708043047, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0002257125284637951, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0002821234042911758, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00020476519490600253, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0003686021939578787, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.000604094526779267, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0003931927810861401, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5601239204406738, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3838872909545898, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.1232494115829468, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8917927145957947, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.686424970626831, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4668600261211395, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.31772229075431824, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2316606640815735, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.17620953917503357, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.14622551202774048, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.12886986136436462, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.112639881670475, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10252538323402405, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0930732786655426, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08696132153272629, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08257976919412613, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.07837938517332077, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07468337565660477, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.0712098553776741, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06858478486537933, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06608252227306366, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06397845596075058, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06250011920928955, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06169196218252182, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06129322201013565, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.0616278350353241, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.062195271253585815, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06305613368749619, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06421095877885818, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06579681485891342, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06712021678686142, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06801292300224304, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06886671483516693, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06960681080818176, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06988858431577682, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07106493413448334, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07295026630163193, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07713326066732407, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08161412924528122, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07820103317499161, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09256311506032944, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08516239374876022, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.10232912003993988, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1354372501373291, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.17821666598320007, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.17648519575595856, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19727912545204163, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.22154761850833893, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.26955050230026245, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6803075396825397, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7735615079365079, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8737599206349206, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9136904761904762, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9285714285714286, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9434523809523809, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9526289682539683, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9583333333333334, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9625496031746031, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9677579365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9694940476190477, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.9724702380952381, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9739583333333334, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9744543650793651, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9756944444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9799107142857143, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9799107142857143, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.980406746031746, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.980406746031746, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9818948412698413, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9828869047619048, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.980406746031746, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.982390873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.5973439584513771, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7244367068545804, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8527199125186351, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.902256189706732, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9194364089195823, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9338316123197773, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9448192741367795, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9519635624548644, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9557810947506233, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.961088878607781, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9630029494546386, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9633730172970552, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9662819237805018, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9678043021340682, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9690268103862257, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9689678582990479, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9705789946917427, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9715368691698533, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9745941412339727, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9770723055764825, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9784558274851131, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9792677264037902, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9791423362437965, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9792111579314723, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9790200897917254, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9794645714905783, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9784174145991757, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9786389141845968, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9797104296473468, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9796158096750107, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9787223727365534, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9793217523824173, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9789012807991048, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.980388653285341, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9794853879504667, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9777665890032882, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9820805671089798, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.982364998900746, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9789158127311085, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.981883230988281, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9812927141744439, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9791197964511336, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9766314623528409, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9779752734421463, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9800477609769817, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9789283052905289, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9794986326200342, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9785823362710145, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9803152994924551, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.0003040757868438959, "validation/loss_best": 0.07820103317499161, "validation/acc_best": 0.9838789682539683, "validation/f1_best": 0.981883230988281} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.16023050874471664, "train/grad": 0.03468553219921887, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5500522613525392, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3739358520507812, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.1140970611572265, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.883077278137207, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.678825626373291, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.46157182693481447, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.31519297093153, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.23053060188889504, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.17555185835808515, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.14512044370174407, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.12696624659001826, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.1092838067561388, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.0976034121774137, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0855876749381423, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.07690789092332125, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.07010311839170753, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.06273837815970182, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05529277716763317, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04789966271258891, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04178416122682393, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.034948761966079475, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.028763716071844102, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.022855657236650586, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.017481248937547208, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012936334516853094, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008849984174594283, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.006274972930550575, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004621194787323475, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0031333405338227747, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0020412789564579724, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0014344929158687592, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0010915913060307503, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0008006437961012125, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0006213287357240916, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.000481918565928936, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0004105751495808363, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.0002865300420671701, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00021691421046853064, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00021273711696267127, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.0001789947785437107, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.0001645277254283428, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00021552808582782744, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.000260829646140337, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0002642263378947973, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.00017240933142602442, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00012054032646119595, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0001930235978215933, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.000106927203014493, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.2015014439821244e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011314831278286874, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010874716714024544, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010302249491214752, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009938895527739078, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009497843319550156, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008531734175048768, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007484109725337476, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00679214283823967, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006371347991516813, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0061545349343214185, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.006014066734351218, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005861973526189104, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005749512092443183, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0056261809496209025, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005520708613330498, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0054122950509190556, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00527097518730443, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00509546582296025, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004878772163065151, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004662443432025611, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004365952919761185, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004027688331261743, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0036348737243679353, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003173899381654337, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0026664068280661014, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00207382106105797, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.001613331005210057, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0012569182180595818, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.000895986734321923, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0006057039866573178, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00043101124039822023, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0003304665988252964, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00024131971264068852, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001853996395584545, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00014504640394079614, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.000128960320898841, "train/grad_036_lr7.1e+00_wd1.0e+00": 9.630188551909669e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.79811020786292e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 8.164403516616403e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.114349183756531e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 8.123818883575496e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00010941382984015036, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001230536363993906, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0001583381435108322, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00011892139404900859, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00010222137917877849, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00015202939070701804, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0001480773379961373, "train/grad_048_lr5.0e+01_wd1.0e+00": 9.803810950490422e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5448648929595947, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3679560422897339, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.107071042060852, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8748469948768616, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6701276302337646, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4538988471031189, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3092428743839264, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.22630997002124786, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.17310546338558197, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.14415250718593597, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.1272944211959839, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.11155149340629578, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10172003507614136, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.09244418889284134, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08645117282867432, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08213284611701965, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.07807023078203201, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.0743556097149849, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07102490216493607, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06849761307239532, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06582510471343994, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06377637386322021, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.062354668974876404, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06138944625854492, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06107454001903534, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06121575087308884, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.061946604400873184, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06268861144781113, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06380380690097809, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06544085592031479, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06677041947841644, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06773761659860611, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06889613717794418, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06975547224283218, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06992651522159576, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.0708962082862854, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07245010882616043, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07631319016218185, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08123959600925446, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.0769907608628273, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09123780578374863, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08349517732858658, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1006300076842308, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13220223784446716, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1751895695924759, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.17164547741413116, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.19011817872524261, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.21088451147079468, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2646755278110504, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6884920634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7824900793650794, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8772321428571429, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9161706349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9295634920634921, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9434523809523809, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9523809523809523, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9590773809523809, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9632936507936508, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9672619047619048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9689980158730159, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9714781746031746, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9739583333333334, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9769345238095238, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9779265873015873, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9816468253968254, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.982390873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9838789682539683, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.982390873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6110791721185449, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7372146880846447, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8583684797822806, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9058554831552259, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9208201480310565, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9337748688233157, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.94426521099511, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9522241848537606, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9562909068731, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9607281629595616, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9626417372311176, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9629999110022479, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9658588775259928, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9681588013727561, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9689091355394727, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.969918006603721, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9705773128918967, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9727757318769541, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9747774448509358, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9776258112438299, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9793090546569568, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9793010468458674, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9793126080392137, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9786904732870434, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9793335941944716, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9796708034757374, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9782512712729436, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9786909857589473, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9788807598581241, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9790719620725605, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.978888747060331, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9791917001491905, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9789940452463914, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9795790540191843, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9791417214470731, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9777665890032882, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9817542530583141, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9825398865460652, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9790966394434739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9817639567846049, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9812897423028323, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9792223957802487, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9767603245858306, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9781564759878362, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9800247384503391, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.979820464310311, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9798611929721449, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9785123918449832, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9801417035240388, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.0001789947785437107, "validation/loss_best": 0.0769907608628273, "validation/acc_best": 0.9838789682539683, "validation/f1_best": 0.9817639567846049} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.1568785835802555, "train/grad": 0.03395290583372116, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5359056854248048, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3583502960205078, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.09677978515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.8649139595031738, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6611322975158691, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.44733365535736086, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.30490657180547714, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.22291836954653263, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.1696122432872653, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.14010977517813444, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.12237163178622723, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.1050835170969367, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.09366104865446687, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.08191701505333185, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.07354995662346482, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06700127750635147, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.059917742768302557, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05283205163665116, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.045834089824929834, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.04001082442700863, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03359823509119451, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.027777794199064374, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.022160840677097438, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.01702854781411588, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.012571993125602603, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.008461611568927765, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.005875800615176559, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.004240480503067374, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.0028324163146317004, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0018401775602251292, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0013042355142533779, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.000992580996826291, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0007312414981424808, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005647181626409292, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004386953543871641, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.00038045713678002357, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00025247693993151187, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00021161108277738096, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.0002063257247209549, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00017509181052446365, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00015626522712409497, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.0002120752725750208, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002284728642553091, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0002298656664788723, "train/loss_044_lr2.6e+01_wd1.0e+00": 9.61765181273222e-05, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.00010525955818593502, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.0001441800221800804, "train/loss_047_lr4.3e+01_wd1.0e+00": 6.604205816984176e-05, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.5266511365771293e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01133574335835874, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010875673023983836, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010280038183555006, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009891290576197207, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00941256619989872, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008390246722847224, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0072852058010175825, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006551163420081139, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006121799373067916, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005915649839444086, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005786864396650344, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005643989681266249, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005542798292590305, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005427911854931153, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005335745755000971, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005239675674820319, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005108109931461513, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0049371828691801055, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004718374268850312, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004499597352114506, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00420132983563235, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003871996934176423, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0034754677678574806, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003022463395027444, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0025191588341840544, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0019383939169347287, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00148453665067791, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00114143824808707, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0008067525143633247, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005408671363329631, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00038756424057282855, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0002959925696632126, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00021985240922731464, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00017096861166464804, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0001338527033885839, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011938818050111877, "train/grad_036_lr7.1e+00_wd1.0e+00": 8.953474279451257e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 8.067851788382541e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.740348093648208e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 8.117768630881983e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.672515370330756e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0001036698109498957, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00011296786247498858, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00014778840233283574, "train/grad_044_lr2.6e+01_wd1.0e+00": 9.180697770028723e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00010003946668071139, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00013471598897105697, "train/grad_047_lr4.3e+01_wd1.0e+00": 7.347363805619095e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 3.5241756241729866e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.536899209022522, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3597140312194824, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0984779596328735, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8663130402565002, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6618272066116333, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.44728606939315796, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.30484822392463684, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.22357653081417084, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.1713695377111435, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.14308194816112518, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.12648634612560272, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.1108950525522232, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10118986666202545, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.0920485183596611, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08608812093734741, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08190211653709412, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.07783423364162445, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07413645088672638, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07078423351049423, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.0682031661272049, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.0656217634677887, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06358097493648529, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06217024102807045, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06136816367506981, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.06115697696805, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.061529651284217834, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06218940392136574, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06310581415891647, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06417956203222275, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06559613347053528, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06673626601696014, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06758363544940948, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06834430247545242, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06912838667631149, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06936272233724594, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07051754742860794, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07191532105207443, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07609443366527557, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08077164739370346, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07664122432470322, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09060966968536377, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08341372758150101, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09991729259490967, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13105891644954681, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.17333897948265076, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.16871869564056396, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.18640300631523132, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.20637567341327667, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.25775977969169617, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.691468253968254, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7864583333333334, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8782242063492064, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9174107142857143, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9300595238095238, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9437003968253969, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9528769841269841, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9593253968253969, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9635416666666666, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9675099206349206, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9692460317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9717261904761905, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9761904761904762, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9766865079365079, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.980406746031746, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9806547619047619, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.980406746031746, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9806547619047619, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.982390873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9826388888888888, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6167681065706874, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7410498184388556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8589821752250246, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9074217522244026, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.9208406926568726, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9344195290134947, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.94491724236703, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9527200855015701, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9568527875371755, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9613703421408224, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9628223668521427, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9629999110022479, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9667414295065041, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9682056149509359, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9690103246146606, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9696418163762788, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9709346143927436, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9725936219319274, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9753209707346371, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9777947799491811, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9792072396458951, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9793113457891833, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9785095315097834, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9787424925371068, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9796938748662372, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9801121217801717, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9786909104969406, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9790034021380497, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.979127108430722, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9790666599798143, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9790913730075432, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9784630123072086, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9792765302763234, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9795338124121838, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9791417214470731, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9778102157793084, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9819354451670893, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9825398865460652, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9790966394434739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9819471875116325, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9814738899136204, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9792223957802487, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9771627232645809, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9781564759878362, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9798660602649586, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9796386040843744, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9798611929721449, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9777903875569155, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9804129748306045, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.00017509181052446365, "validation/loss_best": 0.07664122432470322, "validation/acc_best": 0.9841269841269841, "validation/f1_best": 0.9819471875116325} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.15746954709291458, "train/grad": 0.033991218460723754, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5388715362548828, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3614285278320313, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.0996072387695313, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.8669440269470214, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6623434782028198, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.44801387906074525, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.30616083383560183, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.22491897627711296, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.1722195113450289, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.14285612460225822, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.12514410652220248, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.10760350126773119, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.09592381745576858, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.08373728837817908, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.07502560367807747, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06814144171774388, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.060699431775137785, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05322980254888535, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.045934101715683934, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03980890695005655, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03313681007362902, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.0270957815553993, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.021337673095986248, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.016176391569897534, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.011836171802133321, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.007924094796180725, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.005508793191984296, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.003991891397163272, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.002676006555557251, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0017322866339236499, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0012274639960378408, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0009403475653380156, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0006913256831467152, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005363162979483604, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.0004146318044513464, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0003563193418085575, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00024251623079180718, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00018326355144381522, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00019967141561210154, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00015061245299875738, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00014053809456527234, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00018236045725643634, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.0002081097662448883, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.00017463780008256436, "train/loss_044_lr2.6e+01_wd1.0e+00": 7.358877919614316e-05, "train/loss_045_lr3.1e+01_wd1.0e+00": 9.072113782167435e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.00011452159844338894, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.8100499659776686e-05, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.4830501750111579e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01119769921991974, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010748736965470016, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010182491806335747, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009826442976482212, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00937093898653984, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008376060950104148, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007315704063512385, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006611044583842159, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.006203809413127601, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.006021295568207279, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0059110874391626565, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005785672683268786, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.005682564654853195, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005560034138616174, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005454067091923207, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005348856772179715, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005201798118650913, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005013374247355386, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004782895582029596, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004540821177652105, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004217679710418452, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.003854159746551886, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0034189971297746524, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0029433004866586997, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0024381385224114638, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0018652607990952675, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0014191794059297536, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0010852230271848383, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007643241005280288, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.000512234545458341, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0003674456621592981, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00028291648719459773, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002097054222576844, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0001639002441697812, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00012858709082138375, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00011617908739026461, "train/grad_036_lr7.1e+00_wd1.0e+00": 8.520803830833757e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.609564228914678e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.387251690829544e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.32679169777839e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.001179451265215e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.629364442162114e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0001091412124191038, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00013891085998551489, "train/grad_044_lr2.6e+01_wd1.0e+00": 7.809379581514176e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.00010087505769602267, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.00012748650303249677, "train/grad_047_lr4.3e+01_wd1.0e+00": 7.263776739019234e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 2.6325884904765518e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5339010953903198, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3566334247589111, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.0952403545379639, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.8628913760185242, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6586899757385254, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4447135329246521, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3032096326351166, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.2225925475358963, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.17076238989830017, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.14274384081363678, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.12616479396820068, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.11070102453231812, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10101384669542313, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.09185439348220825, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08598172664642334, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.08182760328054428, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.0777214840054512, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07407767325639725, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07080280780792236, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06820353865623474, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06560803204774857, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.06365944445133209, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.06220982223749161, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06140344589948654, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.061094217002391815, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06136113777756691, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.0620645172894001, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06287876516580582, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.06394842267036438, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06538818776607513, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.06660579890012741, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06738173216581345, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06839369237422943, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06916983425617218, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06934665143489838, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07049023360013962, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07210506498813629, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07602829486131668, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08067862689495087, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07652239501476288, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09055249392986298, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08312927186489105, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09953086078166962, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1306769698858261, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1724962443113327, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.16854971647262573, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1856922209262848, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.20575116574764252, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.2555832862854004, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6919642857142857, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7891865079365079, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8797123015873016, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.9176587301587301, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9305555555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9441964285714286, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9528769841269841, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9598214285714286, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9630456349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9675099206349206, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9692460317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9699900793650794, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9719742063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9742063492063492, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9749503968253969, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.980406746031746, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.980406746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9813988095238095, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9831349206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9816468253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9828869047619048, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9826388888888888, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6178073484822076, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.744327639819515, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8614486919372843, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9083290140264902, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.920626677994384, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9347734711089686, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9451586630118478, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9528965253932176, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9561216898626668, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9613703421408224, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9628223668521427, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9635510775020067, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9669637310243102, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9681588013727561, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.9686915412614224, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9696418163762788, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9703903967056688, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9720492470170926, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9753209707346371, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9777947799491811, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.978715079329944, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9793568300456402, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9786452008105058, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9786467315603841, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9794751947028063, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9792573016279795, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9782746569222186, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9783758953652422, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.979106630345944, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9790669119076648, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9790926378171859, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9793516698012877, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.979457841076814, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9793128726478797, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9791417214470731, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9777665890032882, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9818903835148463, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9825398865460652, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9790966394434739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9819471875116325, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9816525790718367, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9792223957802487, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9773373219470827, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9781564759878362, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9798272456788835, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9794567084307324, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9800424034570224, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9777939960039534, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9804129748306045, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.00015061245299875738, "validation/loss_best": 0.07652239501476288, "validation/acc_best": 0.9841269841269841, "validation/f1_best": 0.9819471875116325} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.15661715991795064, "train/grad": 0.03378329849801957, "train/loss_000_lr2.0e-02_wd1.0e+00": 1.5320738220214845, "train/loss_001_lr2.3e-02_wd1.0e+00": 1.3555841827392578, "train/loss_002_lr2.8e-02_wd1.0e+00": 1.0953434371948243, "train/loss_003_lr3.3e-02_wd1.0e+00": 0.86398286819458, "train/loss_004_lr3.8e-02_wd1.0e+00": 0.6605586528778076, "train/loss_005_lr4.5e-02_wd1.0e+00": 0.4475890624523163, "train/loss_006_lr5.3e-02_wd1.0e+00": 0.3066280081868172, "train/loss_007_lr6.2e-02_wd1.0e+00": 0.22561013281345368, "train/loss_008_lr7.4e-02_wd1.0e+00": 0.1726906716823578, "train/loss_009_lr8.7e-02_wd1.0e+00": 0.14297265335917472, "train/loss_010_lr1.0e-01_wd1.0e+00": 0.12492245879024268, "train/loss_011_lr1.2e-01_wd1.0e+00": 0.10701604906469583, "train/loss_012_lr1.4e-01_wd1.0e+00": 0.09500778295099735, "train/loss_013_lr1.7e-01_wd1.0e+00": 0.0824781590141356, "train/loss_014_lr2.0e-01_wd1.0e+00": 0.07352106055244803, "train/loss_015_lr2.3e-01_wd1.0e+00": 0.06646713955327868, "train/loss_016_lr2.7e-01_wd1.0e+00": 0.05892689598724246, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.05142325556837022, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.04413431379944086, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.03815428993664682, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.03156444814987481, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.025636580092832446, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.02004613360390067, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.015083516361191868, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.010936906281858682, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.007245156662538648, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.005040989033877849, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.003675228226929903, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.002494186498224735, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.0016439823992550372, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.0011786579806357623, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.0009073988627642393, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.0006763246655464172, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.0005292080901563167, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.00041117284446954725, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.0003435804881155491, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.00023807655088603497, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.00019117289222776889, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.00019320370629429817, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.00015005145221948623, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.00014262543991208076, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.00017145318910479545, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.00019548999145627022, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.0001717211026698351, "train/loss_044_lr2.6e+01_wd1.0e+00": 6.685846485197544e-05, "train/loss_045_lr3.1e+01_wd1.0e+00": 7.692989893257618e-05, "train/loss_046_lr3.6e+01_wd1.0e+00": 9.175776503980159e-05, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.026889801025391e-05, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.303732395172119e-05, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011189344450831413, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010737500563263893, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010166532015427948, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00979418192524463, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009312728382647038, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00829347580904141, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.007240366924088448, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.006556575074791908, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0061534758366178725, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.005957469653803855, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.005840279436670244, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.005711093714926392, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00562046421924606, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.005514060866553336, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.005415059255901724, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.005312210262054577, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.005170508753508329, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00498641450307332, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.004754310711286962, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004518902588170021, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004197457293630577, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0038276311950176025, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0033953639303217643, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0029161318713158834, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0024031886440934614, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.001827301784651354, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0013932741472672205, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.001065631280071102, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0007527315900370013, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0005064300827507395, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0003615411063401552, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.000276334400568885, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0002042755755064718, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00015930255625789868, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00012414360284310533, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.000112056362313524, "train/grad_036_lr7.1e+00_wd1.0e+00": 8.496158511661633e-05, "train/grad_037_lr8.3e+00_wd1.0e+00": 7.759792397564524e-05, "train/grad_038_lr9.8e+00_wd1.0e+00": 7.381710867775836e-05, "train/grad_039_lr1.2e+01_wd1.0e+00": 7.294263990047512e-05, "train/grad_040_lr1.4e+01_wd1.0e+00": 7.170120938525315e-05, "train/grad_041_lr1.6e+01_wd1.0e+00": 9.587429453318919e-05, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00010590078085044752, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0001402770194881464, "train/grad_044_lr2.6e+01_wd1.0e+00": 7.85603095824161e-05, "train/grad_045_lr3.1e+01_wd1.0e+00": 8.957485133792658e-05, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0001115409163040626, "train/grad_047_lr4.3e+01_wd1.0e+00": 6.630983016038858e-05, "train/grad_048_lr5.0e+01_wd1.0e+00": 2.5840818271661428e-05, "validation/loss_000_lr2.0e-02_wd1.0e+00": 1.5334819555282593, "validation/loss_001_lr2.3e-02_wd1.0e+00": 1.3562122583389282, "validation/loss_002_lr2.8e-02_wd1.0e+00": 1.094751238822937, "validation/loss_003_lr3.3e-02_wd1.0e+00": 0.862424910068512, "validation/loss_004_lr3.8e-02_wd1.0e+00": 0.6582298278808594, "validation/loss_005_lr4.5e-02_wd1.0e+00": 0.4444061815738678, "validation/loss_006_lr5.3e-02_wd1.0e+00": 0.3029497265815735, "validation/loss_007_lr6.2e-02_wd1.0e+00": 0.22241713106632233, "validation/loss_008_lr7.4e-02_wd1.0e+00": 0.17071351408958435, "validation/loss_009_lr8.7e-02_wd1.0e+00": 0.14269106090068817, "validation/loss_010_lr1.0e-01_wd1.0e+00": 0.12609294056892395, "validation/loss_011_lr1.2e-01_wd1.0e+00": 0.11065328121185303, "validation/loss_012_lr1.4e-01_wd1.0e+00": 0.10097386687994003, "validation/loss_013_lr1.7e-01_wd1.0e+00": 0.09181463718414307, "validation/loss_014_lr2.0e-01_wd1.0e+00": 0.08596240729093552, "validation/loss_015_lr2.3e-01_wd1.0e+00": 0.0817771703004837, "validation/loss_016_lr2.7e-01_wd1.0e+00": 0.07767200469970703, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.07407131046056747, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.07073748856782913, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.06816710531711578, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.06563632190227509, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.0635850802063942, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.062147341668605804, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.06151481717824936, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.0611206516623497, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.06144857406616211, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.06215602532029152, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.06299389898777008, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.0640891045331955, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.06546096503734589, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.066585972905159, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.06745132803916931, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.06839057803153992, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.06914150714874268, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.06933657079935074, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.07044438272714615, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.07199899852275848, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.07599928230047226, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.08063305914402008, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.07654120028018951, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.09054707735776901, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.08313291519880295, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.09953200817108154, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13080205023288727, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1720016449689865, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.16838338971138, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1856788992881775, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.20555894076824188, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.25545650720596313, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.6922123015873016, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.7886904761904762, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.8799603174603174, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.917906746031746, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.9305555555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.9441964285714286, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.9528769841269841, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.9598214285714286, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.9630456349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.9672619047619048, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.9692460317460317, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.9697420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.9717261904761905, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.972718253968254, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.9739583333333334, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.9751984126984127, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9759424603174603, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9764384920634921, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9781746031746031, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9801587301587301, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9811507936507936, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9813988095238095, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9809027777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.980406746031746, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9806547619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9811507936507936, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9816468253968254, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9801587301587301, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9826388888888888, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9831349206349206, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9809027777777778, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9841269841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9833829365079365, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9809027777777778, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9818948412698413, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9821428571428571, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9826388888888888, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9801587301587301, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9826388888888888, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.6172999386846045, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.7437770177927632, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.8616319511933025, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.9082292276066791, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.920591129613825, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.9348234924826941, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.9452804664240381, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.9528965253932176, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.9561216898626668, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.9609961767979908, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.9628223668521427, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.9629999110022479, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.9664093867470223, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.9681588013727561, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.968463180002056, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.9700666032296371, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9703903967056688, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9720492470170926, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9753209707346371, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9776133437688524, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9790812247608952, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9793113457891833, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9786452008105058, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9786434577319432, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9791128447255165, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9798060009809786, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.978268261658416, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.978548660801881, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9789246938176968, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.978884942968231, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9789063432608339, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9794042848350616, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.979457841076814, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9795366792179724, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9791417214470731, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9777665890032882, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9819354451670893, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9825398865460652, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9790966394434739, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9819471875116325, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9818340806179767, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9792223957802487, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9773373219470827, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9781564759878362, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9799862760161788, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9794567084307324, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9798611929721449, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9777939960039534, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9804129748306045, "id_best": 39, "lr_best": 0.0036, "wd_best": 0.05, "train/loss_best": 0.00015005145221948623, "validation/loss_best": 0.07654120028018951, "validation/acc_best": 0.9841269841269841, "validation/f1_best": 0.9819471875116325} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/config.yaml b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9c0c175812bab00282d527a52b84131a53c134ca --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..fcb367de149a20c490ef229f4cd043dd11679cfc --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 13, "eval/id_best": 47, "eval/lr_best": 0.012899999999999998, "eval/wd_best": 0.05, "eval/train/loss": 0.08525362610816956, "eval/train/acc": 0.9823674930259487, "eval/train/acc_std": 0.0008657816080374579, "eval/train/f1": 0.9829294314269125, "eval/train/f1_std": 0.0009095226097774374, "eval/validation/loss": 0.12551695108413696, "eval/validation/acc": 0.9640376984126984, "eval/validation/acc_std": 0.002795946815321116, "eval/validation/f1": 0.9596783023261295, "eval/validation/f1_std": 0.0035716459971804806, "eval/test/loss": 0.1440315544605255, "eval/test/acc": 0.9577380952380953, "eval/test/acc_std": 0.00272619047619048, "eval/test/f1": 0.9508678631502228, "eval/test/f1_std": 0.0035852767155503014} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..dca5e6107a37f29e92ff4ad3b89ce391b5f65899 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 13, "eval/best/id_best": 47, "eval/best/lr_best": 0.012899999999999998, "eval/best/wd_best": 0.05, "eval/best/train/loss": 0.08525362610816956, "eval/best/train/acc": 0.9823674930259487, "eval/best/train/acc_std": 0.0008657816080374579, "eval/best/train/f1": 0.9829294314269125, "eval/best/train/f1_std": 0.0009095226097774374, "eval/best/validation/loss": 0.12551695108413696, "eval/best/validation/acc": 0.9640376984126984, "eval/best/validation/acc_std": 0.002795946815321116, "eval/best/validation/f1": 0.9596783023261295, "eval/best/validation/f1_std": 0.0035716459971804806, "eval/best/test/loss": 0.1440315544605255, "eval/best/test/acc": 0.9577380952380953, "eval/best/test/acc_std": 0.00272619047619048, "eval/best/test/f1": 0.9508678631502228, "eval/best/test/f1_std": 0.0035852767155503014} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..41804a1f025aee4be3f0f232c061d3fa3a8964b6 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 47, "eval/last/lr_best": 0.012899999999999998, "eval/last/wd_best": 0.05, "eval/last/train/loss": 0.08010412007570267, "eval/last/train/acc": 0.9843149639454708, "eval/last/train/acc_std": 0.0008725408080563321, "eval/last/train/f1": 0.9850712778430978, "eval/last/train/f1_std": 0.0009065052033785558, "eval/last/validation/loss": 0.12352041900157928, "eval/last/validation/acc": 0.9630456349206349, "eval/last/validation/acc_std": 0.0027922780461021608, "eval/last/validation/f1": 0.9588233560039492, "eval/last/validation/f1_std": 0.0036408226456957024, "eval/last/test/loss": 0.14171263575553894, "eval/last/test/acc": 0.9589285714285715, "eval/last/test/acc_std": 0.002669531335227332, "eval/last/test/f1": 0.9522065502718778, "eval/last/test/f1_std": 0.003530889548811274} diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..8e6a3a88baa8463734d27cd713dbd09d389652f0 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,best,13,0.012899999999999998,0.05,47,"[43, 1.0]",train,0.08525362610816956,0.9823674930259487,0.0008657816080374579,0.9829294314269125,0.0009095226097774374 +flat_mae,reg,linear,hcpya_task21,best,13,0.012899999999999998,0.05,47,"[43, 1.0]",validation,0.12551695108413696,0.9640376984126984,0.002795946815321116,0.9596783023261295,0.0035716459971804806 +flat_mae,reg,linear,hcpya_task21,best,13,0.012899999999999998,0.05,47,"[43, 1.0]",test,0.1440315544605255,0.9577380952380953,0.00272619047619048,0.9508678631502228,0.0035852767155503014 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..8e6a3a88baa8463734d27cd713dbd09d389652f0 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table_best.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,best,13,0.012899999999999998,0.05,47,"[43, 1.0]",train,0.08525362610816956,0.9823674930259487,0.0008657816080374579,0.9829294314269125,0.0009095226097774374 +flat_mae,reg,linear,hcpya_task21,best,13,0.012899999999999998,0.05,47,"[43, 1.0]",validation,0.12551695108413696,0.9640376984126984,0.002795946815321116,0.9596783023261295,0.0035716459971804806 +flat_mae,reg,linear,hcpya_task21,best,13,0.012899999999999998,0.05,47,"[43, 1.0]",test,0.1440315544605255,0.9577380952380953,0.00272619047619048,0.9508678631502228,0.0035852767155503014 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..5a569f50310fee5d0d2690c2fd0ddb95f0810e23 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/eval_table_last.csv @@ -0,0 +1,4 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,hcpya_task21,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",train,0.08010412007570267,0.9843149639454708,0.0008725408080563321,0.9850712778430978,0.0009065052033785558 +flat_mae,reg,linear,hcpya_task21,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",validation,0.12352041900157928,0.9630456349206349,0.0027922780461021608,0.9588233560039492,0.0036408226456957024 +flat_mae,reg,linear,hcpya_task21,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",test,0.14171263575553894,0.9589285714285715,0.002669531335227332,0.9522065502718778,0.003530889548811274 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/log.txt b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d18a3191c8752b1d23c0686e9e148ed44e68546b --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/log.txt @@ -0,0 +1,890 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: clean, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 21:36:07 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (hcpya_task21 reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: hcpya_task21 +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: hcpya_task21 (flat) +train (n=18999): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 18999 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[ 832 1248 3201 1660 832 832 832 832 832 1248 1247 1243 832 416 + 416 416 416 416 416 416 416] +) + +validation (n=4032): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 4032 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[176 264 688 352 176 176 176 176 176 264 264 264 176 88 88 88 88 88 + 88 88 88] +) + +test (n=5040): +HFDataset( + dataset=Dataset({ + features: ['sub', 'task', 'cond', 'cond_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5040 +}), + labels=[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20], + counts=[220 330 860 440 220 220 220 220 220 330 330 330 220 110 110 110 110 110 + 110 110 110] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=21, bias=True) + ) +) +classifier params (train): 0.8M (0.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:22:44 lr: nan time: 3.4114 data: 2.9837 max mem: 3929 +train: [0] [ 20/400] eta: 0:03:07 lr: 0.000003 loss: 3.0308 (3.0329) grad: 0.1123 (0.1197) time: 0.3486 data: 0.0034 max mem: 3970 +train: [0] [ 40/400] eta: 0:02:32 lr: 0.000006 loss: 3.0301 (3.0301) grad: 0.1170 (0.1195) time: 0.3472 data: 0.0033 max mem: 3970 +train: [0] [ 60/400] eta: 0:02:14 lr: 0.000009 loss: 3.0192 (3.0231) grad: 0.1181 (0.1192) time: 0.3438 data: 0.0030 max mem: 3970 +train: [0] [ 80/400] eta: 0:02:03 lr: 0.000012 loss: 2.9967 (3.0148) grad: 0.1145 (0.1186) time: 0.3485 data: 0.0031 max mem: 3970 +train: [0] [100/400] eta: 0:01:52 lr: 0.000015 loss: 2.9826 (3.0060) grad: 0.1164 (0.1182) time: 0.3355 data: 0.0032 max mem: 3970 +train: [0] [120/400] eta: 0:01:43 lr: 0.000018 loss: 2.9544 (2.9956) grad: 0.1117 (0.1163) time: 0.3438 data: 0.0030 max mem: 3970 +train: [0] [140/400] eta: 0:01:35 lr: 0.000021 loss: 2.9238 (2.9836) grad: 0.1062 (0.1151) time: 0.3448 data: 0.0034 max mem: 3970 +train: [0] [160/400] eta: 0:01:26 lr: 0.000024 loss: 2.8971 (2.9705) grad: 0.1078 (0.1143) time: 0.3281 data: 0.0033 max mem: 3970 +train: [0] [180/400] eta: 0:01:19 lr: 0.000027 loss: 2.8641 (2.9565) grad: 0.1104 (0.1139) time: 0.3675 data: 0.0032 max mem: 3970 +train: [0] [200/400] eta: 0:01:11 lr: 0.000030 loss: 2.8273 (2.9420) grad: 0.1075 (0.1132) time: 0.3339 data: 0.0028 max mem: 3970 +train: [0] [220/400] eta: 0:01:04 lr: 0.000033 loss: 2.7904 (2.9275) grad: 0.0986 (0.1120) time: 0.3595 data: 0.0035 max mem: 3970 +train: [0] [240/400] eta: 0:00:57 lr: 0.000036 loss: 2.7561 (2.9116) grad: 0.0954 (0.1110) time: 0.3478 data: 0.0031 max mem: 3970 +train: [0] [260/400] eta: 0:00:50 lr: 0.000039 loss: 2.7047 (2.8946) grad: 0.1063 (0.1110) time: 0.3583 data: 0.0035 max mem: 3970 +train: [0] [280/400] eta: 0:00:42 lr: 0.000042 loss: 2.6714 (2.8781) grad: 0.1045 (0.1104) time: 0.3392 data: 0.0033 max mem: 3970 +train: [0] [300/400] eta: 0:00:36 lr: 0.000045 loss: 2.6470 (2.8623) grad: 0.0926 (0.1090) time: 0.5025 data: 0.1821 max mem: 3970 +train: [0] [320/400] eta: 0:00:29 lr: 0.000048 loss: 2.6240 (2.8447) grad: 0.0922 (0.1085) time: 0.3599 data: 0.0222 max mem: 3970 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 2.5686 (2.8284) grad: 0.0999 (0.1080) time: 0.3374 data: 0.0028 max mem: 3970 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 2.5444 (2.8121) grad: 0.0967 (0.1071) time: 0.3530 data: 0.0033 max mem: 3970 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 2.5167 (2.7965) grad: 0.0917 (0.1063) time: 0.3647 data: 0.0039 max mem: 3970 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 2.4779 (2.7801) grad: 0.0891 (0.1055) time: 0.3483 data: 0.0034 max mem: 3970 +train: [0] Total time: 0:02:25 (0.3636 s / it) +train: [0] Summary: lr: 0.000060 loss: 2.4779 (2.7801) grad: 0.0891 (0.1055) +eval (validation): [0] [ 0/63] eta: 0:03:38 time: 3.4746 data: 3.2551 max mem: 3970 +eval (validation): [0] [20/63] eta: 0:00:20 time: 0.3322 data: 0.0034 max mem: 3970 +eval (validation): [0] [40/63] eta: 0:00:09 time: 0.3295 data: 0.0032 max mem: 3970 +eval (validation): [0] [60/63] eta: 0:00:01 time: 0.3275 data: 0.0031 max mem: 3970 +eval (validation): [0] [62/63] eta: 0:00:00 time: 0.3234 data: 0.0030 max mem: 3970 +eval (validation): [0] Total time: 0:00:24 (0.3832 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.668 acc: 0.918 f1: 0.911 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:00 lr: nan time: 3.3017 data: 3.0856 max mem: 3970 +train: [1] [ 20/400] eta: 0:03:00 lr: 0.000063 loss: 2.4516 (2.4490) grad: 0.0912 (0.0929) time: 0.3349 data: 0.0040 max mem: 3970 +train: [1] [ 40/400] eta: 0:02:27 lr: 0.000066 loss: 2.4169 (2.4198) grad: 0.0951 (0.0949) time: 0.3420 data: 0.0027 max mem: 3970 +train: [1] [ 60/400] eta: 0:02:13 lr: 0.000069 loss: 2.3937 (2.4140) grad: 0.0937 (0.0933) time: 0.3519 data: 0.0031 max mem: 3970 +train: [1] [ 80/400] eta: 0:02:00 lr: 0.000072 loss: 2.3859 (2.3975) grad: 0.0900 (0.0922) time: 0.3364 data: 0.0031 max mem: 3970 +train: [1] [100/400] eta: 0:01:52 lr: 0.000075 loss: 2.3273 (2.3806) grad: 0.0900 (0.0928) time: 0.3654 data: 0.0030 max mem: 3970 +train: [1] [120/400] eta: 0:01:43 lr: 0.000078 loss: 2.3164 (2.3683) grad: 0.0900 (0.0920) time: 0.3381 data: 0.0032 max mem: 3970 +train: [1] [140/400] eta: 0:01:35 lr: 0.000081 loss: 2.2833 (2.3563) grad: 0.0844 (0.0910) time: 0.3624 data: 0.0036 max mem: 3970 +train: [1] [160/400] eta: 0:01:27 lr: 0.000084 loss: 2.2434 (2.3395) grad: 0.0916 (0.0922) time: 0.3456 data: 0.0031 max mem: 3970 +train: [1] [180/400] eta: 0:01:19 lr: 0.000087 loss: 2.2155 (2.3249) grad: 0.0947 (0.0922) time: 0.3361 data: 0.0034 max mem: 3970 +train: [1] [200/400] eta: 0:01:12 lr: 0.000090 loss: 2.2155 (2.3150) grad: 0.0894 (0.0917) time: 0.3542 data: 0.0032 max mem: 3970 +train: [1] [220/400] eta: 0:01:04 lr: 0.000093 loss: 2.2053 (2.3036) grad: 0.0870 (0.0912) time: 0.3326 data: 0.0032 max mem: 3970 +train: [1] [240/400] eta: 0:00:57 lr: 0.000096 loss: 2.1620 (2.2909) grad: 0.0856 (0.0909) time: 0.3630 data: 0.0034 max mem: 3970 +train: [1] [260/400] eta: 0:00:50 lr: 0.000099 loss: 2.1473 (2.2797) grad: 0.0844 (0.0906) time: 0.3404 data: 0.0031 max mem: 3970 +train: [1] [280/400] eta: 0:00:42 lr: 0.000102 loss: 2.1331 (2.2687) grad: 0.0844 (0.0904) time: 0.3485 data: 0.0032 max mem: 3970 +train: [1] [300/400] eta: 0:00:36 lr: 0.000105 loss: 2.1087 (2.2574) grad: 0.0866 (0.0902) time: 0.5181 data: 0.1780 max mem: 3970 +train: [1] [320/400] eta: 0:00:29 lr: 0.000108 loss: 2.0879 (2.2464) grad: 0.0860 (0.0896) time: 0.3510 data: 0.0037 max mem: 3970 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 2.0838 (2.2362) grad: 0.0797 (0.0894) time: 0.3281 data: 0.0027 max mem: 3970 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 2.0450 (2.2247) grad: 0.0797 (0.0889) time: 0.3273 data: 0.0030 max mem: 3970 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 2.0285 (2.2149) grad: 0.0861 (0.0889) time: 0.3789 data: 0.0034 max mem: 3970 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 2.0285 (2.2044) grad: 0.0825 (0.0886) time: 0.3664 data: 0.0035 max mem: 3970 +train: [1] Total time: 0:02:25 (0.3635 s / it) +train: [1] Summary: lr: 0.000120 loss: 2.0285 (2.2044) grad: 0.0825 (0.0886) +eval (validation): [1] [ 0/63] eta: 0:03:21 time: 3.1917 data: 2.9340 max mem: 3970 +eval (validation): [1] [20/63] eta: 0:00:21 time: 0.3549 data: 0.0095 max mem: 3970 +eval (validation): [1] [40/63] eta: 0:00:10 time: 0.3915 data: 0.0036 max mem: 3970 +eval (validation): [1] [60/63] eta: 0:00:01 time: 0.3577 data: 0.0036 max mem: 3970 +eval (validation): [1] [62/63] eta: 0:00:00 time: 0.3469 data: 0.0035 max mem: 3970 +eval (validation): [1] Total time: 0:00:26 (0.4156 s / it) +cv: [1] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.301 acc: 0.937 f1: 0.933 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:12 lr: nan time: 3.3321 data: 3.1109 max mem: 3970 +train: [2] [ 20/400] eta: 0:03:07 lr: 0.000123 loss: 1.9859 (1.9871) grad: 0.0755 (0.0812) time: 0.3513 data: 0.0038 max mem: 3970 +train: [2] [ 40/400] eta: 0:02:44 lr: 0.000126 loss: 1.9859 (1.9801) grad: 0.0788 (0.0804) time: 0.4179 data: 0.0041 max mem: 3970 +train: [2] [ 60/400] eta: 0:02:26 lr: 0.000129 loss: 1.9569 (1.9700) grad: 0.0788 (0.0808) time: 0.3771 data: 0.0035 max mem: 3970 +train: [2] [ 80/400] eta: 0:02:09 lr: 0.000132 loss: 1.9542 (1.9657) grad: 0.0814 (0.0812) time: 0.3289 data: 0.0031 max mem: 3970 +train: [2] [100/400] eta: 0:02:00 lr: 0.000135 loss: 1.9363 (1.9540) grad: 0.0814 (0.0811) time: 0.3873 data: 0.0033 max mem: 3970 +train: [2] [120/400] eta: 0:01:49 lr: 0.000138 loss: 1.8966 (1.9440) grad: 0.0774 (0.0807) time: 0.3467 data: 0.0036 max mem: 3970 +train: [2] [140/400] eta: 0:01:40 lr: 0.000141 loss: 1.8891 (1.9349) grad: 0.0777 (0.0806) time: 0.3421 data: 0.0031 max mem: 3970 +train: [2] [160/400] eta: 0:01:31 lr: 0.000144 loss: 1.8760 (1.9258) grad: 0.0798 (0.0809) time: 0.3429 data: 0.0032 max mem: 3970 +train: [2] [180/400] eta: 0:01:22 lr: 0.000147 loss: 1.8710 (1.9212) grad: 0.0795 (0.0804) time: 0.3423 data: 0.0033 max mem: 3970 +train: [2] [200/400] eta: 0:01:14 lr: 0.000150 loss: 1.8710 (1.9159) grad: 0.0785 (0.0802) time: 0.3617 data: 0.0034 max mem: 3970 +train: [2] [220/400] eta: 0:01:07 lr: 0.000153 loss: 1.8526 (1.9103) grad: 0.0781 (0.0800) time: 0.3492 data: 0.0033 max mem: 3970 +train: [2] [240/400] eta: 0:00:59 lr: 0.000156 loss: 1.8471 (1.9036) grad: 0.0745 (0.0795) time: 0.3662 data: 0.0035 max mem: 3970 +train: [2] [260/400] eta: 0:00:51 lr: 0.000159 loss: 1.8267 (1.8967) grad: 0.0745 (0.0794) time: 0.3568 data: 0.0035 max mem: 3970 +train: [2] [280/400] eta: 0:00:44 lr: 0.000162 loss: 1.8019 (1.8893) grad: 0.0761 (0.0794) time: 0.3512 data: 0.0034 max mem: 3970 +train: [2] [300/400] eta: 0:00:37 lr: 0.000165 loss: 1.7759 (1.8817) grad: 0.0773 (0.0791) time: 0.5203 data: 0.1864 max mem: 3970 +train: [2] [320/400] eta: 0:00:30 lr: 0.000168 loss: 1.7665 (1.8751) grad: 0.0737 (0.0788) time: 0.3705 data: 0.0041 max mem: 3970 +train: [2] [340/400] eta: 0:00:22 lr: 0.000171 loss: 1.7663 (1.8683) grad: 0.0737 (0.0787) time: 0.3336 data: 0.0032 max mem: 3970 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 1.7584 (1.8614) grad: 0.0748 (0.0786) time: 0.3429 data: 0.0035 max mem: 3970 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 1.7491 (1.8550) grad: 0.0695 (0.0781) time: 0.3525 data: 0.0032 max mem: 3970 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 1.7375 (1.8493) grad: 0.0695 (0.0779) time: 0.3504 data: 0.0032 max mem: 3970 +train: [2] Total time: 0:02:28 (0.3723 s / it) +train: [2] Summary: lr: 0.000180 loss: 1.7375 (1.8493) grad: 0.0695 (0.0779) +eval (validation): [2] [ 0/63] eta: 0:03:29 time: 3.3308 data: 3.1181 max mem: 3970 +eval (validation): [2] [20/63] eta: 0:00:20 time: 0.3357 data: 0.0034 max mem: 3970 +eval (validation): [2] [40/63] eta: 0:00:09 time: 0.3360 data: 0.0026 max mem: 3970 +eval (validation): [2] [60/63] eta: 0:00:01 time: 0.3263 data: 0.0032 max mem: 3970 +eval (validation): [2] [62/63] eta: 0:00:00 time: 0.3227 data: 0.0032 max mem: 3970 +eval (validation): [2] Total time: 0:00:24 (0.3854 s / it) +cv: [2] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.202 acc: 0.949 f1: 0.946 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:45 lr: nan time: 3.4146 data: 3.1460 max mem: 3970 +train: [3] [ 20/400] eta: 0:03:15 lr: 0.000183 loss: 1.6866 (1.6920) grad: 0.0735 (0.0760) time: 0.3696 data: 0.0037 max mem: 3970 +train: [3] [ 40/400] eta: 0:02:42 lr: 0.000186 loss: 1.6816 (1.6876) grad: 0.0717 (0.0729) time: 0.3823 data: 0.0035 max mem: 3970 +train: [3] [ 60/400] eta: 0:02:24 lr: 0.000189 loss: 1.6688 (1.6808) grad: 0.0709 (0.0745) time: 0.3723 data: 0.0034 max mem: 3970 +train: [3] [ 80/400] eta: 0:02:10 lr: 0.000192 loss: 1.6688 (1.6790) grad: 0.0715 (0.0736) time: 0.3549 data: 0.0032 max mem: 3970 +train: [3] [100/400] eta: 0:01:58 lr: 0.000195 loss: 1.6548 (1.6729) grad: 0.0693 (0.0733) time: 0.3396 data: 0.0032 max mem: 3970 +train: [3] [120/400] eta: 0:01:48 lr: 0.000198 loss: 1.6548 (1.6746) grad: 0.0686 (0.0726) time: 0.3601 data: 0.0036 max mem: 3970 +train: [3] [140/400] eta: 0:01:40 lr: 0.000201 loss: 1.6797 (1.6750) grad: 0.0730 (0.0727) time: 0.3665 data: 0.0033 max mem: 3970 +train: [3] [160/400] eta: 0:01:31 lr: 0.000204 loss: 1.6425 (1.6693) grad: 0.0739 (0.0727) time: 0.3530 data: 0.0032 max mem: 3970 +train: [3] [180/400] eta: 0:01:22 lr: 0.000207 loss: 1.6151 (1.6647) grad: 0.0698 (0.0725) time: 0.3413 data: 0.0030 max mem: 3970 +train: [3] [200/400] eta: 0:01:14 lr: 0.000210 loss: 1.6141 (1.6601) grad: 0.0705 (0.0725) time: 0.3433 data: 0.0031 max mem: 3970 +train: [3] [220/400] eta: 0:01:07 lr: 0.000213 loss: 1.5901 (1.6540) grad: 0.0689 (0.0726) time: 0.3660 data: 0.0033 max mem: 3970 +train: [3] [240/400] eta: 0:00:59 lr: 0.000216 loss: 1.5906 (1.6510) grad: 0.0692 (0.0725) time: 0.3677 data: 0.0035 max mem: 3970 +train: [3] [260/400] eta: 0:00:51 lr: 0.000219 loss: 1.5933 (1.6460) grad: 0.0649 (0.0722) time: 0.3492 data: 0.0034 max mem: 3970 +train: [3] [280/400] eta: 0:00:44 lr: 0.000222 loss: 1.5933 (1.6419) grad: 0.0657 (0.0722) time: 0.3518 data: 0.0033 max mem: 3970 +train: [3] [300/400] eta: 0:00:37 lr: 0.000225 loss: 1.5933 (1.6369) grad: 0.0672 (0.0719) time: 0.4975 data: 0.1816 max mem: 3970 +train: [3] [320/400] eta: 0:00:30 lr: 0.000228 loss: 1.5380 (1.6303) grad: 0.0675 (0.0720) time: 0.3591 data: 0.0196 max mem: 3970 +train: [3] [340/400] eta: 0:00:22 lr: 0.000231 loss: 1.5220 (1.6238) grad: 0.0708 (0.0720) time: 0.3508 data: 0.0027 max mem: 3970 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 1.5177 (1.6181) grad: 0.0715 (0.0719) time: 0.3447 data: 0.0032 max mem: 3970 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 1.5282 (1.6130) grad: 0.0710 (0.0719) time: 0.3556 data: 0.0032 max mem: 3970 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 1.5196 (1.6082) grad: 0.0670 (0.0716) time: 0.3754 data: 0.0036 max mem: 3970 +train: [3] Total time: 0:02:29 (0.3729 s / it) +train: [3] Summary: lr: 0.000240 loss: 1.5196 (1.6082) grad: 0.0670 (0.0716) +eval (validation): [3] [ 0/63] eta: 0:03:33 time: 3.3847 data: 3.1722 max mem: 3970 +eval (validation): [3] [20/63] eta: 0:00:21 time: 0.3478 data: 0.0381 max mem: 3970 +eval (validation): [3] [40/63] eta: 0:00:09 time: 0.3440 data: 0.0032 max mem: 3970 +eval (validation): [3] [60/63] eta: 0:00:01 time: 0.3417 data: 0.0024 max mem: 3970 +eval (validation): [3] [62/63] eta: 0:00:00 time: 0.3403 data: 0.0027 max mem: 3970 +eval (validation): [3] Total time: 0:00:25 (0.3977 s / it) +cv: [3] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.177 acc: 0.955 f1: 0.947 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:23:06 lr: nan time: 3.4658 data: 3.2398 max mem: 3970 +train: [4] [ 20/400] eta: 0:03:10 lr: 0.000243 loss: 1.4967 (1.4984) grad: 0.0642 (0.0663) time: 0.3538 data: 0.0039 max mem: 3970 +train: [4] [ 40/400] eta: 0:02:32 lr: 0.000246 loss: 1.5039 (1.5054) grad: 0.0645 (0.0649) time: 0.3413 data: 0.0030 max mem: 3970 +train: [4] [ 60/400] eta: 0:02:14 lr: 0.000249 loss: 1.4947 (1.4985) grad: 0.0650 (0.0659) time: 0.3374 data: 0.0033 max mem: 3970 +train: [4] [ 80/400] eta: 0:02:01 lr: 0.000252 loss: 1.4828 (1.4940) grad: 0.0655 (0.0665) time: 0.3321 data: 0.0032 max mem: 3970 +train: [4] [100/400] eta: 0:01:51 lr: 0.000255 loss: 1.4774 (1.4889) grad: 0.0655 (0.0664) time: 0.3431 data: 0.0033 max mem: 3970 +train: [4] [120/400] eta: 0:01:43 lr: 0.000258 loss: 1.4642 (1.4852) grad: 0.0640 (0.0660) time: 0.3535 data: 0.0035 max mem: 3970 +train: [4] [140/400] eta: 0:01:35 lr: 0.000261 loss: 1.4642 (1.4820) grad: 0.0609 (0.0657) time: 0.3608 data: 0.0037 max mem: 3970 +train: [4] [160/400] eta: 0:01:27 lr: 0.000264 loss: 1.4324 (1.4733) grad: 0.0677 (0.0664) time: 0.3485 data: 0.0034 max mem: 3970 +train: [4] [180/400] eta: 0:01:20 lr: 0.000267 loss: 1.4181 (1.4703) grad: 0.0699 (0.0662) time: 0.3526 data: 0.0031 max mem: 3970 +train: [4] [200/400] eta: 0:01:12 lr: 0.000270 loss: 1.4344 (1.4647) grad: 0.0690 (0.0664) time: 0.3329 data: 0.0031 max mem: 3970 +train: [4] [220/400] eta: 0:01:05 lr: 0.000273 loss: 1.4309 (1.4618) grad: 0.0641 (0.0664) time: 0.3682 data: 0.0032 max mem: 3970 +train: [4] [240/400] eta: 0:00:57 lr: 0.000276 loss: 1.4191 (1.4572) grad: 0.0623 (0.0660) time: 0.3440 data: 0.0032 max mem: 3970 +train: [4] [260/400] eta: 0:00:50 lr: 0.000279 loss: 1.3993 (1.4526) grad: 0.0630 (0.0659) time: 0.3519 data: 0.0034 max mem: 3970 +train: [4] [280/400] eta: 0:00:43 lr: 0.000282 loss: 1.3846 (1.4481) grad: 0.0632 (0.0657) time: 0.3552 data: 0.0034 max mem: 3970 +train: [4] [300/400] eta: 0:00:37 lr: 0.000285 loss: 1.3846 (1.4464) grad: 0.0588 (0.0653) time: 0.5289 data: 0.1867 max mem: 3970 +train: [4] [320/400] eta: 0:00:29 lr: 0.000288 loss: 1.3920 (1.4427) grad: 0.0586 (0.0650) time: 0.3545 data: 0.0036 max mem: 3970 +train: [4] [340/400] eta: 0:00:22 lr: 0.000291 loss: 1.3747 (1.4381) grad: 0.0628 (0.0650) time: 0.3437 data: 0.0031 max mem: 3970 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 1.3680 (1.4346) grad: 0.0635 (0.0649) time: 0.3399 data: 0.0032 max mem: 3970 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.3539 (1.4298) grad: 0.0614 (0.0649) time: 0.3656 data: 0.0033 max mem: 3970 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 1.3529 (1.4274) grad: 0.0604 (0.0646) time: 0.3629 data: 0.0032 max mem: 3970 +train: [4] Total time: 0:02:26 (0.3666 s / it) +train: [4] Summary: lr: 0.000300 loss: 1.3529 (1.4274) grad: 0.0604 (0.0646) +eval (validation): [4] [ 0/63] eta: 0:03:39 time: 3.4818 data: 3.2057 max mem: 3970 +eval (validation): [4] [20/63] eta: 0:00:20 time: 0.3366 data: 0.0042 max mem: 3970 +eval (validation): [4] [40/63] eta: 0:00:09 time: 0.3188 data: 0.0034 max mem: 3970 +eval (validation): [4] [60/63] eta: 0:00:01 time: 0.3183 data: 0.0032 max mem: 3970 +eval (validation): [4] [62/63] eta: 0:00:00 time: 0.3145 data: 0.0031 max mem: 3970 +eval (validation): [4] Total time: 0:00:23 (0.3784 s / it) +cv: [4] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.170 acc: 0.955 f1: 0.951 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:36 lr: nan time: 3.3903 data: 3.1234 max mem: 3970 +train: [5] [ 20/400] eta: 0:03:21 lr: 0.000300 loss: 1.3704 (1.3621) grad: 0.0563 (0.0621) time: 0.3886 data: 0.0044 max mem: 3970 +train: [5] [ 40/400] eta: 0:02:39 lr: 0.000300 loss: 1.3704 (1.3721) grad: 0.0624 (0.0626) time: 0.3510 data: 0.0033 max mem: 3970 +train: [5] [ 60/400] eta: 0:02:19 lr: 0.000300 loss: 1.3514 (1.3600) grad: 0.0649 (0.0638) time: 0.3390 data: 0.0028 max mem: 3970 +train: [5] [ 80/400] eta: 0:02:05 lr: 0.000300 loss: 1.3116 (1.3490) grad: 0.0649 (0.0639) time: 0.3444 data: 0.0036 max mem: 3970 +train: [5] [100/400] eta: 0:01:55 lr: 0.000300 loss: 1.3116 (1.3451) grad: 0.0608 (0.0636) time: 0.3503 data: 0.0035 max mem: 3970 +train: [5] [120/400] eta: 0:01:46 lr: 0.000300 loss: 1.3553 (1.3489) grad: 0.0595 (0.0631) time: 0.3481 data: 0.0033 max mem: 3970 +train: [5] [140/400] eta: 0:01:37 lr: 0.000300 loss: 1.3462 (1.3448) grad: 0.0573 (0.0625) time: 0.3526 data: 0.0034 max mem: 3970 +train: [5] [160/400] eta: 0:01:30 lr: 0.000299 loss: 1.3237 (1.3416) grad: 0.0593 (0.0623) time: 0.3919 data: 0.0035 max mem: 3970 +train: [5] [180/400] eta: 0:01:22 lr: 0.000299 loss: 1.2922 (1.3378) grad: 0.0607 (0.0622) time: 0.3545 data: 0.0035 max mem: 3970 +train: [5] [200/400] eta: 0:01:14 lr: 0.000299 loss: 1.2852 (1.3331) grad: 0.0602 (0.0619) time: 0.3476 data: 0.0031 max mem: 3970 +train: [5] [220/400] eta: 0:01:06 lr: 0.000299 loss: 1.2737 (1.3271) grad: 0.0570 (0.0617) time: 0.3510 data: 0.0032 max mem: 3970 +train: [5] [240/400] eta: 0:00:59 lr: 0.000299 loss: 1.2737 (1.3244) grad: 0.0554 (0.0615) time: 0.3643 data: 0.0036 max mem: 3970 +train: [5] [260/400] eta: 0:00:51 lr: 0.000299 loss: 1.2985 (1.3206) grad: 0.0630 (0.0619) time: 0.3691 data: 0.0035 max mem: 3970 +train: [5] [280/400] eta: 0:00:44 lr: 0.000298 loss: 1.2557 (1.3158) grad: 0.0612 (0.0617) time: 0.3355 data: 0.0033 max mem: 3970 +train: [5] [300/400] eta: 0:00:37 lr: 0.000298 loss: 1.2428 (1.3119) grad: 0.0572 (0.0614) time: 0.5242 data: 0.1864 max mem: 3970 +train: [5] [320/400] eta: 0:00:30 lr: 0.000298 loss: 1.2516 (1.3099) grad: 0.0575 (0.0611) time: 0.4035 data: 0.0065 max mem: 3970 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 1.2601 (1.3068) grad: 0.0545 (0.0607) time: 0.3422 data: 0.0037 max mem: 3970 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 1.2617 (1.3046) grad: 0.0551 (0.0606) time: 0.3433 data: 0.0031 max mem: 3970 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 1.2240 (1.2993) grad: 0.0579 (0.0607) time: 0.3478 data: 0.0033 max mem: 3970 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 1.2102 (1.2958) grad: 0.0607 (0.0606) time: 0.3510 data: 0.0032 max mem: 3970 +train: [5] Total time: 0:02:29 (0.3728 s / it) +train: [5] Summary: lr: 0.000297 loss: 1.2102 (1.2958) grad: 0.0607 (0.0606) +eval (validation): [5] [ 0/63] eta: 0:03:38 time: 3.4675 data: 3.2043 max mem: 3970 +eval (validation): [5] [20/63] eta: 0:00:20 time: 0.3239 data: 0.0034 max mem: 3970 +eval (validation): [5] [40/63] eta: 0:00:09 time: 0.3315 data: 0.0037 max mem: 3970 +eval (validation): [5] [60/63] eta: 0:00:01 time: 0.3176 data: 0.0029 max mem: 3970 +eval (validation): [5] [62/63] eta: 0:00:00 time: 0.3182 data: 0.0032 max mem: 3970 +eval (validation): [5] Total time: 0:00:23 (0.3783 s / it) +cv: [5] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 0.159 acc: 0.957 f1: 0.952 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:21:46 lr: nan time: 3.2654 data: 2.9998 max mem: 3970 +train: [6] [ 20/400] eta: 0:03:10 lr: 0.000296 loss: 1.2075 (1.2196) grad: 0.0531 (0.0541) time: 0.3641 data: 0.0042 max mem: 3970 +train: [6] [ 40/400] eta: 0:02:35 lr: 0.000296 loss: 1.2235 (1.2295) grad: 0.0555 (0.0546) time: 0.3601 data: 0.0027 max mem: 3970 +train: [6] [ 60/400] eta: 0:02:18 lr: 0.000296 loss: 1.2288 (1.2197) grad: 0.0574 (0.0565) time: 0.3573 data: 0.0031 max mem: 3970 +train: [6] [ 80/400] eta: 0:02:05 lr: 0.000295 loss: 1.1863 (1.2179) grad: 0.0610 (0.0581) time: 0.3488 data: 0.0031 max mem: 3970 +train: [6] [100/400] eta: 0:01:55 lr: 0.000295 loss: 1.2056 (1.2182) grad: 0.0607 (0.0579) time: 0.3434 data: 0.0032 max mem: 3970 +train: [6] [120/400] eta: 0:01:45 lr: 0.000295 loss: 1.2056 (1.2176) grad: 0.0560 (0.0574) time: 0.3393 data: 0.0030 max mem: 3970 +train: [6] [140/400] eta: 0:01:36 lr: 0.000294 loss: 1.1996 (1.2142) grad: 0.0562 (0.0577) time: 0.3458 data: 0.0032 max mem: 3970 +train: [6] [160/400] eta: 0:01:28 lr: 0.000294 loss: 1.1970 (1.2144) grad: 0.0537 (0.0573) time: 0.3552 data: 0.0034 max mem: 3970 +train: [6] [180/400] eta: 0:01:20 lr: 0.000293 loss: 1.1799 (1.2089) grad: 0.0542 (0.0575) time: 0.3435 data: 0.0032 max mem: 3970 +train: [6] [200/400] eta: 0:01:12 lr: 0.000293 loss: 1.1910 (1.2101) grad: 0.0562 (0.0572) time: 0.3469 data: 0.0033 max mem: 3970 +train: [6] [220/400] eta: 0:01:05 lr: 0.000292 loss: 1.2001 (1.2072) grad: 0.0556 (0.0573) time: 0.3430 data: 0.0033 max mem: 3970 +train: [6] [240/400] eta: 0:00:57 lr: 0.000292 loss: 1.1743 (1.2045) grad: 0.0556 (0.0571) time: 0.3489 data: 0.0032 max mem: 3970 +train: [6] [260/400] eta: 0:00:50 lr: 0.000291 loss: 1.1828 (1.2028) grad: 0.0557 (0.0572) time: 0.3513 data: 0.0034 max mem: 3970 +train: [6] [280/400] eta: 0:00:43 lr: 0.000291 loss: 1.1595 (1.1985) grad: 0.0574 (0.0572) time: 0.3540 data: 0.0033 max mem: 3970 +train: [6] [300/400] eta: 0:00:36 lr: 0.000290 loss: 1.1505 (1.1964) grad: 0.0575 (0.0573) time: 0.5022 data: 0.1828 max mem: 3970 +train: [6] [320/400] eta: 0:00:29 lr: 0.000290 loss: 1.1590 (1.1941) grad: 0.0557 (0.0570) time: 0.3848 data: 0.0037 max mem: 3970 +train: [6] [340/400] eta: 0:00:22 lr: 0.000289 loss: 1.1590 (1.1925) grad: 0.0565 (0.0570) time: 0.3416 data: 0.0032 max mem: 3970 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 1.1555 (1.1912) grad: 0.0573 (0.0570) time: 0.3577 data: 0.0036 max mem: 3970 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 1.1571 (1.1897) grad: 0.0538 (0.0567) time: 0.3467 data: 0.0033 max mem: 3970 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 1.1571 (1.1879) grad: 0.0530 (0.0567) time: 0.3572 data: 0.0033 max mem: 3970 +train: [6] Total time: 0:02:26 (0.3670 s / it) +train: [6] Summary: lr: 0.000287 loss: 1.1571 (1.1879) grad: 0.0530 (0.0567) +eval (validation): [6] [ 0/63] eta: 0:03:39 time: 3.4870 data: 3.2674 max mem: 3970 +eval (validation): [6] [20/63] eta: 0:00:21 time: 0.3457 data: 0.0032 max mem: 3970 +eval (validation): [6] [40/63] eta: 0:00:09 time: 0.3493 data: 0.0033 max mem: 3970 +eval (validation): [6] [60/63] eta: 0:00:01 time: 0.3113 data: 0.0034 max mem: 3970 +eval (validation): [6] [62/63] eta: 0:00:00 time: 0.3106 data: 0.0031 max mem: 3970 +eval (validation): [6] Total time: 0:00:24 (0.3892 s / it) +cv: [6] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.146 acc: 0.959 f1: 0.954 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:21:34 lr: nan time: 3.2363 data: 3.0180 max mem: 3970 +train: [7] [ 20/400] eta: 0:03:04 lr: 0.000286 loss: 1.1432 (1.1727) grad: 0.0532 (0.0571) time: 0.3468 data: 0.0061 max mem: 3970 +train: [7] [ 40/400] eta: 0:02:30 lr: 0.000286 loss: 1.1402 (1.1582) grad: 0.0564 (0.0562) time: 0.3494 data: 0.0029 max mem: 3970 +train: [7] [ 60/400] eta: 0:02:13 lr: 0.000285 loss: 1.1172 (1.1448) grad: 0.0564 (0.0564) time: 0.3430 data: 0.0033 max mem: 3970 +train: [7] [ 80/400] eta: 0:02:01 lr: 0.000284 loss: 1.1019 (1.1426) grad: 0.0572 (0.0568) time: 0.3375 data: 0.0033 max mem: 3970 +train: [7] [100/400] eta: 0:01:51 lr: 0.000284 loss: 1.1053 (1.1424) grad: 0.0561 (0.0561) time: 0.3347 data: 0.0035 max mem: 3970 +train: [7] [120/400] eta: 0:01:43 lr: 0.000283 loss: 1.1176 (1.1374) grad: 0.0511 (0.0553) time: 0.3531 data: 0.0033 max mem: 3970 +train: [7] [140/400] eta: 0:01:35 lr: 0.000282 loss: 1.0991 (1.1335) grad: 0.0510 (0.0550) time: 0.3669 data: 0.0032 max mem: 3970 +train: [7] [160/400] eta: 0:01:28 lr: 0.000282 loss: 1.1150 (1.1329) grad: 0.0524 (0.0551) time: 0.3776 data: 0.0036 max mem: 3970 +train: [7] [180/400] eta: 0:01:20 lr: 0.000281 loss: 1.1158 (1.1330) grad: 0.0520 (0.0548) time: 0.3556 data: 0.0035 max mem: 3970 +train: [7] [200/400] eta: 0:01:13 lr: 0.000280 loss: 1.1076 (1.1303) grad: 0.0519 (0.0547) time: 0.3496 data: 0.0033 max mem: 3970 +train: [7] [220/400] eta: 0:01:05 lr: 0.000279 loss: 1.0974 (1.1286) grad: 0.0526 (0.0546) time: 0.3427 data: 0.0029 max mem: 3970 +train: [7] [240/400] eta: 0:00:57 lr: 0.000278 loss: 1.1074 (1.1289) grad: 0.0525 (0.0545) time: 0.3340 data: 0.0031 max mem: 3970 +train: [7] [260/400] eta: 0:00:50 lr: 0.000278 loss: 1.0970 (1.1255) grad: 0.0521 (0.0543) time: 0.3550 data: 0.0031 max mem: 3970 +train: [7] [280/400] eta: 0:00:43 lr: 0.000277 loss: 1.0940 (1.1249) grad: 0.0521 (0.0542) time: 0.3541 data: 0.0033 max mem: 3970 +train: [7] [300/400] eta: 0:00:37 lr: 0.000276 loss: 1.0986 (1.1244) grad: 0.0534 (0.0542) time: 0.5185 data: 0.1841 max mem: 3970 +train: [7] [320/400] eta: 0:00:29 lr: 0.000275 loss: 1.0906 (1.1224) grad: 0.0531 (0.0541) time: 0.3855 data: 0.0037 max mem: 3970 +train: [7] [340/400] eta: 0:00:22 lr: 0.000274 loss: 1.1181 (1.1229) grad: 0.0507 (0.0538) time: 0.3659 data: 0.0032 max mem: 3970 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 1.0961 (1.1209) grad: 0.0507 (0.0536) time: 0.3738 data: 0.0034 max mem: 3970 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 1.0708 (1.1183) grad: 0.0513 (0.0535) time: 0.3400 data: 0.0032 max mem: 3970 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 1.0671 (1.1161) grad: 0.0527 (0.0536) time: 0.3358 data: 0.0031 max mem: 3970 +train: [7] Total time: 0:02:27 (0.3684 s / it) +train: [7] Summary: lr: 0.000271 loss: 1.0671 (1.1161) grad: 0.0527 (0.0536) +eval (validation): [7] [ 0/63] eta: 0:03:31 time: 3.3599 data: 3.0918 max mem: 3970 +eval (validation): [7] [20/63] eta: 0:00:22 time: 0.3843 data: 0.0046 max mem: 3970 +eval (validation): [7] [40/63] eta: 0:00:10 time: 0.3950 data: 0.0036 max mem: 3970 +eval (validation): [7] [60/63] eta: 0:00:01 time: 0.3264 data: 0.0033 max mem: 3970 +eval (validation): [7] [62/63] eta: 0:00:00 time: 0.3181 data: 0.0033 max mem: 3970 +eval (validation): [7] Total time: 0:00:26 (0.4185 s / it) +cv: [7] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.138 acc: 0.961 f1: 0.957 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:22:05 lr: nan time: 3.3132 data: 3.0500 max mem: 3970 +train: [8] [ 20/400] eta: 0:03:20 lr: 0.000270 loss: 1.0807 (1.0866) grad: 0.0502 (0.0502) time: 0.3894 data: 0.0040 max mem: 3970 +train: [8] [ 40/400] eta: 0:02:40 lr: 0.000270 loss: 1.0880 (1.0903) grad: 0.0513 (0.0524) time: 0.3575 data: 0.0032 max mem: 3970 +train: [8] [ 60/400] eta: 0:02:22 lr: 0.000269 loss: 1.0615 (1.0811) grad: 0.0519 (0.0525) time: 0.3678 data: 0.0036 max mem: 3970 +train: [8] [ 80/400] eta: 0:02:08 lr: 0.000268 loss: 1.0589 (1.0808) grad: 0.0515 (0.0524) time: 0.3422 data: 0.0033 max mem: 3970 +train: [8] [100/400] eta: 0:01:56 lr: 0.000267 loss: 1.0749 (1.0790) grad: 0.0507 (0.0520) time: 0.3412 data: 0.0033 max mem: 3970 +train: [8] [120/400] eta: 0:01:46 lr: 0.000266 loss: 1.0466 (1.0760) grad: 0.0489 (0.0516) time: 0.3457 data: 0.0036 max mem: 3970 +train: [8] [140/400] eta: 0:01:38 lr: 0.000265 loss: 1.0466 (1.0727) grad: 0.0509 (0.0519) time: 0.3647 data: 0.0037 max mem: 3970 +train: [8] [160/400] eta: 0:01:29 lr: 0.000264 loss: 1.0465 (1.0700) grad: 0.0509 (0.0517) time: 0.3424 data: 0.0033 max mem: 3970 +train: [8] [180/400] eta: 0:01:22 lr: 0.000263 loss: 1.0350 (1.0639) grad: 0.0517 (0.0520) time: 0.3653 data: 0.0034 max mem: 3970 +train: [8] [200/400] eta: 0:01:14 lr: 0.000262 loss: 1.0274 (1.0636) grad: 0.0521 (0.0520) time: 0.3461 data: 0.0034 max mem: 3970 +train: [8] [220/400] eta: 0:01:06 lr: 0.000260 loss: 1.0586 (1.0634) grad: 0.0506 (0.0518) time: 0.3442 data: 0.0034 max mem: 3970 +train: [8] [240/400] eta: 0:00:58 lr: 0.000259 loss: 1.0586 (1.0609) grad: 0.0511 (0.0518) time: 0.3446 data: 0.0032 max mem: 3970 +train: [8] [260/400] eta: 0:00:50 lr: 0.000258 loss: 1.0621 (1.0603) grad: 0.0511 (0.0519) time: 0.3366 data: 0.0032 max mem: 3970 +train: [8] [280/400] eta: 0:00:43 lr: 0.000257 loss: 1.0432 (1.0590) grad: 0.0508 (0.0518) time: 0.3572 data: 0.0033 max mem: 3970 +train: [8] [300/400] eta: 0:00:37 lr: 0.000256 loss: 1.0431 (1.0577) grad: 0.0490 (0.0518) time: 0.5181 data: 0.1906 max mem: 3970 +train: [8] [320/400] eta: 0:00:29 lr: 0.000255 loss: 1.0431 (1.0561) grad: 0.0490 (0.0517) time: 0.3573 data: 0.0215 max mem: 3970 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 1.0338 (1.0542) grad: 0.0508 (0.0519) time: 0.3459 data: 0.0088 max mem: 3970 +train: [8] [360/400] eta: 0:00:14 lr: 0.000253 loss: 1.0034 (1.0526) grad: 0.0534 (0.0520) time: 0.3505 data: 0.0037 max mem: 3970 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 1.0034 (1.0505) grad: 0.0506 (0.0520) time: 0.3444 data: 0.0029 max mem: 3970 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 1.0342 (1.0507) grad: 0.0491 (0.0518) time: 0.3500 data: 0.0031 max mem: 3970 +train: [8] Total time: 0:02:27 (0.3683 s / it) +train: [8] Summary: lr: 0.000250 loss: 1.0342 (1.0507) grad: 0.0491 (0.0518) +eval (validation): [8] [ 0/63] eta: 0:03:40 time: 3.4941 data: 3.2015 max mem: 3970 +eval (validation): [8] [20/63] eta: 0:00:22 time: 0.3834 data: 0.0039 max mem: 3970 +eval (validation): [8] [40/63] eta: 0:00:10 time: 0.3543 data: 0.0030 max mem: 3970 +eval (validation): [8] [60/63] eta: 0:00:01 time: 0.3285 data: 0.0032 max mem: 3970 +eval (validation): [8] [62/63] eta: 0:00:00 time: 0.3200 data: 0.0029 max mem: 3970 +eval (validation): [8] Total time: 0:00:25 (0.4086 s / it) +cv: [8] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.143 acc: 0.960 f1: 0.954 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:22:06 lr: nan time: 3.3164 data: 3.0521 max mem: 3970 +train: [9] [ 20/400] eta: 0:03:25 lr: 0.000249 loss: 1.0336 (1.0391) grad: 0.0458 (0.0496) time: 0.4010 data: 0.0030 max mem: 3970 +train: [9] [ 40/400] eta: 0:02:37 lr: 0.000248 loss: 1.0338 (1.0372) grad: 0.0486 (0.0491) time: 0.3279 data: 0.0031 max mem: 3970 +train: [9] [ 60/400] eta: 0:02:19 lr: 0.000247 loss: 1.0338 (1.0346) grad: 0.0479 (0.0488) time: 0.3543 data: 0.0032 max mem: 3970 +train: [9] [ 80/400] eta: 0:02:07 lr: 0.000246 loss: 1.0014 (1.0234) grad: 0.0477 (0.0497) time: 0.3593 data: 0.0031 max mem: 3970 +train: [9] [100/400] eta: 0:01:56 lr: 0.000244 loss: 0.9965 (1.0211) grad: 0.0521 (0.0502) time: 0.3559 data: 0.0034 max mem: 3970 +train: [9] [120/400] eta: 0:01:47 lr: 0.000243 loss: 0.9909 (1.0155) grad: 0.0497 (0.0501) time: 0.3528 data: 0.0034 max mem: 3970 +train: [9] [140/400] eta: 0:01:38 lr: 0.000242 loss: 0.9909 (1.0155) grad: 0.0491 (0.0500) time: 0.3429 data: 0.0032 max mem: 3970 +train: [9] [160/400] eta: 0:01:29 lr: 0.000241 loss: 0.9805 (1.0109) grad: 0.0482 (0.0498) time: 0.3370 data: 0.0033 max mem: 3970 +train: [9] [180/400] eta: 0:01:21 lr: 0.000240 loss: 0.9782 (1.0104) grad: 0.0481 (0.0500) time: 0.3572 data: 0.0032 max mem: 3970 +train: [9] [200/400] eta: 0:01:14 lr: 0.000238 loss: 1.0137 (1.0109) grad: 0.0481 (0.0500) time: 0.3837 data: 0.0035 max mem: 3970 +train: [9] [220/400] eta: 0:01:06 lr: 0.000237 loss: 1.0200 (1.0096) grad: 0.0477 (0.0498) time: 0.3478 data: 0.0036 max mem: 3970 +train: [9] [240/400] eta: 0:00:58 lr: 0.000236 loss: 0.9860 (1.0088) grad: 0.0489 (0.0498) time: 0.3541 data: 0.0033 max mem: 3970 +train: [9] [260/400] eta: 0:00:51 lr: 0.000234 loss: 1.0015 (1.0093) grad: 0.0492 (0.0497) time: 0.3296 data: 0.0033 max mem: 3970 +train: [9] [280/400] eta: 0:00:43 lr: 0.000233 loss: 1.0157 (1.0089) grad: 0.0479 (0.0497) time: 0.3698 data: 0.0034 max mem: 3970 +train: [9] [300/400] eta: 0:00:37 lr: 0.000232 loss: 0.9929 (1.0079) grad: 0.0494 (0.0497) time: 0.5496 data: 0.1899 max mem: 3970 +train: [9] [320/400] eta: 0:00:30 lr: 0.000230 loss: 1.0016 (1.0079) grad: 0.0474 (0.0496) time: 0.3406 data: 0.0034 max mem: 3970 +train: [9] [340/400] eta: 0:00:22 lr: 0.000229 loss: 1.0019 (1.0072) grad: 0.0474 (0.0495) time: 0.3223 data: 0.0033 max mem: 3970 +train: [9] [360/400] eta: 0:00:14 lr: 0.000228 loss: 0.9904 (1.0060) grad: 0.0464 (0.0493) time: 0.3523 data: 0.0035 max mem: 3970 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 0.9837 (1.0049) grad: 0.0470 (0.0493) time: 0.3504 data: 0.0035 max mem: 3970 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 0.9837 (1.0039) grad: 0.0499 (0.0493) time: 0.3479 data: 0.0040 max mem: 3970 +train: [9] Total time: 0:02:27 (0.3695 s / it) +train: [9] Summary: lr: 0.000225 loss: 0.9837 (1.0039) grad: 0.0499 (0.0493) +eval (validation): [9] [ 0/63] eta: 0:03:39 time: 3.4768 data: 3.2078 max mem: 3970 +eval (validation): [9] [20/63] eta: 0:00:21 time: 0.3539 data: 0.0043 max mem: 3970 +eval (validation): [9] [40/63] eta: 0:00:09 time: 0.3367 data: 0.0037 max mem: 3970 +eval (validation): [9] [60/63] eta: 0:00:01 time: 0.3525 data: 0.0035 max mem: 3970 +eval (validation): [9] [62/63] eta: 0:00:00 time: 0.3477 data: 0.0035 max mem: 3970 +eval (validation): [9] Total time: 0:00:25 (0.4016 s / it) +cv: [9] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.144 acc: 0.961 f1: 0.958 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:21:18 lr: nan time: 3.1950 data: 2.9858 max mem: 3970 +train: [10] [ 20/400] eta: 0:03:02 lr: 0.000224 loss: 0.9716 (0.9791) grad: 0.0481 (0.0485) time: 0.3457 data: 0.0038 max mem: 3970 +train: [10] [ 40/400] eta: 0:02:30 lr: 0.000222 loss: 0.9820 (0.9878) grad: 0.0481 (0.0482) time: 0.3518 data: 0.0022 max mem: 3970 +train: [10] [ 60/400] eta: 0:02:14 lr: 0.000221 loss: 1.0016 (0.9855) grad: 0.0496 (0.0484) time: 0.3483 data: 0.0031 max mem: 3970 +train: [10] [ 80/400] eta: 0:02:02 lr: 0.000220 loss: 0.9701 (0.9840) grad: 0.0486 (0.0487) time: 0.3402 data: 0.0033 max mem: 3970 +train: [10] [100/400] eta: 0:01:53 lr: 0.000218 loss: 0.9827 (0.9889) grad: 0.0481 (0.0486) time: 0.3602 data: 0.0037 max mem: 3970 +train: [10] [120/400] eta: 0:01:44 lr: 0.000217 loss: 1.0062 (0.9890) grad: 0.0482 (0.0489) time: 0.3449 data: 0.0033 max mem: 3970 +train: [10] [140/400] eta: 0:01:35 lr: 0.000215 loss: 0.9634 (0.9842) grad: 0.0501 (0.0492) time: 0.3466 data: 0.0034 max mem: 3970 +train: [10] [160/400] eta: 0:01:28 lr: 0.000214 loss: 0.9634 (0.9828) grad: 0.0483 (0.0489) time: 0.3596 data: 0.0033 max mem: 3970 +train: [10] [180/400] eta: 0:01:20 lr: 0.000213 loss: 0.9497 (0.9791) grad: 0.0465 (0.0487) time: 0.3443 data: 0.0031 max mem: 3970 +train: [10] [200/400] eta: 0:01:12 lr: 0.000211 loss: 0.9381 (0.9766) grad: 0.0484 (0.0487) time: 0.3570 data: 0.0032 max mem: 3970 +train: [10] [220/400] eta: 0:01:05 lr: 0.000210 loss: 0.9441 (0.9745) grad: 0.0484 (0.0486) time: 0.3544 data: 0.0033 max mem: 3970 +train: [10] [240/400] eta: 0:00:57 lr: 0.000208 loss: 0.9418 (0.9731) grad: 0.0489 (0.0486) time: 0.3471 data: 0.0036 max mem: 3970 +train: [10] [260/400] eta: 0:00:50 lr: 0.000207 loss: 0.9334 (0.9722) grad: 0.0494 (0.0486) time: 0.3573 data: 0.0032 max mem: 3970 +train: [10] [280/400] eta: 0:00:43 lr: 0.000205 loss: 0.9514 (0.9702) grad: 0.0493 (0.0486) time: 0.3404 data: 0.0032 max mem: 3970 +train: [10] [300/400] eta: 0:00:37 lr: 0.000204 loss: 0.9480 (0.9689) grad: 0.0482 (0.0485) time: 0.5504 data: 0.2172 max mem: 3970 +train: [10] [320/400] eta: 0:00:29 lr: 0.000202 loss: 0.9494 (0.9677) grad: 0.0460 (0.0484) time: 0.3411 data: 0.0033 max mem: 3970 +train: [10] [340/400] eta: 0:00:22 lr: 0.000201 loss: 0.9550 (0.9683) grad: 0.0456 (0.0483) time: 0.3267 data: 0.0034 max mem: 3970 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 0.9617 (0.9682) grad: 0.0471 (0.0482) time: 0.3245 data: 0.0027 max mem: 3970 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 0.9498 (0.9681) grad: 0.0479 (0.0483) time: 0.3326 data: 0.0030 max mem: 3970 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 0.9498 (0.9673) grad: 0.0476 (0.0483) time: 0.3510 data: 0.0035 max mem: 3970 +train: [10] Total time: 0:02:25 (0.3635 s / it) +train: [10] Summary: lr: 0.000196 loss: 0.9498 (0.9673) grad: 0.0476 (0.0483) +eval (validation): [10] [ 0/63] eta: 0:03:30 time: 3.3465 data: 3.1323 max mem: 3970 +eval (validation): [10] [20/63] eta: 0:00:20 time: 0.3438 data: 0.0035 max mem: 3970 +eval (validation): [10] [40/63] eta: 0:00:09 time: 0.3479 data: 0.0031 max mem: 3970 +eval (validation): [10] [60/63] eta: 0:00:01 time: 0.3151 data: 0.0033 max mem: 3970 +eval (validation): [10] [62/63] eta: 0:00:00 time: 0.3156 data: 0.0031 max mem: 3970 +eval (validation): [10] Total time: 0:00:24 (0.3877 s / it) +cv: [10] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 0.141 acc: 0.961 f1: 0.957 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:23:20 lr: nan time: 3.5001 data: 3.2240 max mem: 3970 +train: [11] [ 20/400] eta: 0:03:12 lr: 0.000195 loss: 0.9278 (0.9246) grad: 0.0433 (0.0456) time: 0.3582 data: 0.0288 max mem: 3970 +train: [11] [ 40/400] eta: 0:02:34 lr: 0.000193 loss: 0.9388 (0.9402) grad: 0.0461 (0.0473) time: 0.3445 data: 0.0036 max mem: 3970 +train: [11] [ 60/400] eta: 0:02:15 lr: 0.000192 loss: 0.9429 (0.9412) grad: 0.0469 (0.0474) time: 0.3385 data: 0.0027 max mem: 3970 +train: [11] [ 80/400] eta: 0:02:02 lr: 0.000190 loss: 0.9407 (0.9483) grad: 0.0463 (0.0474) time: 0.3384 data: 0.0029 max mem: 3970 +train: [11] [100/400] eta: 0:01:54 lr: 0.000189 loss: 0.9407 (0.9465) grad: 0.0466 (0.0473) time: 0.3659 data: 0.0034 max mem: 3970 +train: [11] [120/400] eta: 0:01:45 lr: 0.000187 loss: 0.9347 (0.9456) grad: 0.0470 (0.0475) time: 0.3518 data: 0.0033 max mem: 3970 +train: [11] [140/400] eta: 0:01:37 lr: 0.000186 loss: 0.9349 (0.9454) grad: 0.0470 (0.0474) time: 0.3674 data: 0.0037 max mem: 3970 +train: [11] [160/400] eta: 0:01:28 lr: 0.000184 loss: 0.9382 (0.9420) grad: 0.0470 (0.0474) time: 0.3370 data: 0.0034 max mem: 3970 +train: [11] [180/400] eta: 0:01:20 lr: 0.000183 loss: 0.9134 (0.9373) grad: 0.0477 (0.0475) time: 0.3368 data: 0.0029 max mem: 3970 +train: [11] [200/400] eta: 0:01:12 lr: 0.000181 loss: 0.9254 (0.9378) grad: 0.0479 (0.0474) time: 0.3345 data: 0.0031 max mem: 3970 +train: [11] [220/400] eta: 0:01:04 lr: 0.000180 loss: 0.9263 (0.9365) grad: 0.0452 (0.0472) time: 0.3418 data: 0.0031 max mem: 3970 +train: [11] [240/400] eta: 0:00:57 lr: 0.000178 loss: 0.9454 (0.9392) grad: 0.0449 (0.0470) time: 0.3391 data: 0.0032 max mem: 3970 +train: [11] [260/400] eta: 0:00:50 lr: 0.000177 loss: 0.9520 (0.9399) grad: 0.0449 (0.0469) time: 0.3461 data: 0.0032 max mem: 3970 +train: [11] [280/400] eta: 0:00:42 lr: 0.000175 loss: 0.9365 (0.9396) grad: 0.0456 (0.0469) time: 0.3377 data: 0.0033 max mem: 3970 +train: [11] [300/400] eta: 0:00:36 lr: 0.000174 loss: 0.9237 (0.9391) grad: 0.0468 (0.0470) time: 0.4812 data: 0.1629 max mem: 3970 +train: [11] [320/400] eta: 0:00:29 lr: 0.000172 loss: 0.9470 (0.9405) grad: 0.0471 (0.0470) time: 0.3446 data: 0.0031 max mem: 3970 +train: [11] [340/400] eta: 0:00:21 lr: 0.000170 loss: 0.9410 (0.9397) grad: 0.0465 (0.0471) time: 0.3397 data: 0.0032 max mem: 3970 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 0.9236 (0.9392) grad: 0.0455 (0.0470) time: 0.3487 data: 0.0029 max mem: 3970 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 0.9234 (0.9374) grad: 0.0453 (0.0470) time: 0.3435 data: 0.0031 max mem: 3970 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 0.9234 (0.9375) grad: 0.0465 (0.0470) time: 0.3295 data: 0.0031 max mem: 3970 +train: [11] Total time: 0:02:23 (0.3592 s / it) +train: [11] Summary: lr: 0.000166 loss: 0.9234 (0.9375) grad: 0.0465 (0.0470) +eval (validation): [11] [ 0/63] eta: 0:04:00 time: 3.8212 data: 3.5629 max mem: 3970 +eval (validation): [11] [20/63] eta: 0:00:21 time: 0.3288 data: 0.0022 max mem: 3970 +eval (validation): [11] [40/63] eta: 0:00:09 time: 0.3294 data: 0.0033 max mem: 3970 +eval (validation): [11] [60/63] eta: 0:00:01 time: 0.3148 data: 0.0035 max mem: 3970 +eval (validation): [11] [62/63] eta: 0:00:00 time: 0.3113 data: 0.0035 max mem: 3970 +eval (validation): [11] Total time: 0:00:24 (0.3842 s / it) +cv: [11] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 0.136 acc: 0.962 f1: 0.958 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:20:54 lr: nan time: 3.1362 data: 2.9335 max mem: 3970 +train: [12] [ 20/400] eta: 0:02:54 lr: 0.000164 loss: 0.9164 (0.9353) grad: 0.0444 (0.0461) time: 0.3259 data: 0.0135 max mem: 3970 +train: [12] [ 40/400] eta: 0:02:21 lr: 0.000163 loss: 0.9008 (0.9106) grad: 0.0444 (0.0455) time: 0.3216 data: 0.0029 max mem: 3970 +train: [12] [ 60/400] eta: 0:02:08 lr: 0.000161 loss: 0.9008 (0.9198) grad: 0.0438 (0.0456) time: 0.3485 data: 0.0031 max mem: 3970 +train: [12] [ 80/400] eta: 0:01:58 lr: 0.000160 loss: 0.9196 (0.9214) grad: 0.0437 (0.0451) time: 0.3485 data: 0.0032 max mem: 3970 +train: [12] [100/400] eta: 0:01:49 lr: 0.000158 loss: 0.9093 (0.9170) grad: 0.0437 (0.0450) time: 0.3407 data: 0.0032 max mem: 3970 +train: [12] [120/400] eta: 0:01:41 lr: 0.000156 loss: 0.8826 (0.9112) grad: 0.0446 (0.0453) time: 0.3491 data: 0.0033 max mem: 3970 +train: [12] [140/400] eta: 0:01:33 lr: 0.000155 loss: 0.8850 (0.9128) grad: 0.0450 (0.0455) time: 0.3563 data: 0.0033 max mem: 3970 +train: [12] [160/400] eta: 0:01:26 lr: 0.000153 loss: 0.9026 (0.9111) grad: 0.0457 (0.0457) time: 0.3477 data: 0.0033 max mem: 3970 +train: [12] [180/400] eta: 0:01:18 lr: 0.000152 loss: 0.9073 (0.9136) grad: 0.0455 (0.0456) time: 0.3527 data: 0.0034 max mem: 3970 +train: [12] [200/400] eta: 0:01:11 lr: 0.000150 loss: 0.9315 (0.9160) grad: 0.0454 (0.0458) time: 0.3479 data: 0.0036 max mem: 3970 +train: [12] [220/400] eta: 0:01:04 lr: 0.000149 loss: 0.9294 (0.9149) grad: 0.0448 (0.0458) time: 0.3501 data: 0.0037 max mem: 3970 +train: [12] [240/400] eta: 0:00:57 lr: 0.000147 loss: 0.9189 (0.9147) grad: 0.0448 (0.0458) time: 0.3631 data: 0.0037 max mem: 3970 +train: [12] [260/400] eta: 0:00:49 lr: 0.000145 loss: 0.8864 (0.9128) grad: 0.0458 (0.0458) time: 0.3282 data: 0.0031 max mem: 3970 +train: [12] [280/400] eta: 0:00:42 lr: 0.000144 loss: 0.8835 (0.9109) grad: 0.0448 (0.0458) time: 0.3516 data: 0.0033 max mem: 3970 +train: [12] [300/400] eta: 0:00:36 lr: 0.000142 loss: 0.8923 (0.9111) grad: 0.0449 (0.0459) time: 0.5086 data: 0.1832 max mem: 3970 +train: [12] [320/400] eta: 0:00:29 lr: 0.000141 loss: 0.9119 (0.9119) grad: 0.0455 (0.0459) time: 0.3653 data: 0.0205 max mem: 3970 +train: [12] [340/400] eta: 0:00:21 lr: 0.000139 loss: 0.9145 (0.9121) grad: 0.0447 (0.0457) time: 0.3505 data: 0.0029 max mem: 3970 +train: [12] [360/400] eta: 0:00:14 lr: 0.000138 loss: 0.9077 (0.9116) grad: 0.0462 (0.0458) time: 0.3524 data: 0.0034 max mem: 3970 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 0.9061 (0.9121) grad: 0.0460 (0.0458) time: 0.3786 data: 0.0034 max mem: 3970 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 0.9147 (0.9115) grad: 0.0451 (0.0457) time: 0.3408 data: 0.0032 max mem: 3970 +train: [12] Total time: 0:02:25 (0.3637 s / it) +train: [12] Summary: lr: 0.000134 loss: 0.9147 (0.9115) grad: 0.0451 (0.0457) +eval (validation): [12] [ 0/63] eta: 0:03:33 time: 3.3851 data: 3.1713 max mem: 3970 +eval (validation): [12] [20/63] eta: 0:00:22 time: 0.3788 data: 0.0043 max mem: 3970 +eval (validation): [12] [40/63] eta: 0:00:10 time: 0.3463 data: 0.0029 max mem: 3970 +eval (validation): [12] [60/63] eta: 0:00:01 time: 0.3223 data: 0.0035 max mem: 3970 +eval (validation): [12] [62/63] eta: 0:00:00 time: 0.3223 data: 0.0035 max mem: 3970 +eval (validation): [12] Total time: 0:00:25 (0.4013 s / it) +cv: [12] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.126 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [13] [ 0/400] eta: 0:22:13 lr: nan time: 3.3329 data: 3.0716 max mem: 3970 +train: [13] [ 20/400] eta: 0:03:06 lr: 0.000133 loss: 0.8971 (0.8986) grad: 0.0432 (0.0462) time: 0.3500 data: 0.0069 max mem: 3970 +train: [13] [ 40/400] eta: 0:02:30 lr: 0.000131 loss: 0.9031 (0.9016) grad: 0.0444 (0.0463) time: 0.3401 data: 0.0033 max mem: 3970 +train: [13] [ 60/400] eta: 0:02:13 lr: 0.000130 loss: 0.9032 (0.9013) grad: 0.0463 (0.0468) time: 0.3403 data: 0.0027 max mem: 3970 +train: [13] [ 80/400] eta: 0:02:02 lr: 0.000128 loss: 0.9141 (0.9029) grad: 0.0464 (0.0464) time: 0.3585 data: 0.0036 max mem: 3970 +train: [13] [100/400] eta: 0:01:53 lr: 0.000127 loss: 0.9104 (0.9024) grad: 0.0460 (0.0464) time: 0.3579 data: 0.0035 max mem: 3970 +train: [13] [120/400] eta: 0:01:43 lr: 0.000125 loss: 0.8813 (0.8988) grad: 0.0439 (0.0459) time: 0.3206 data: 0.0033 max mem: 3970 +train: [13] [140/400] eta: 0:01:34 lr: 0.000124 loss: 0.8813 (0.8950) grad: 0.0438 (0.0458) time: 0.3357 data: 0.0033 max mem: 3970 +train: [13] [160/400] eta: 0:01:27 lr: 0.000122 loss: 0.8726 (0.8941) grad: 0.0438 (0.0456) time: 0.3539 data: 0.0033 max mem: 3970 +train: [13] [180/400] eta: 0:01:19 lr: 0.000120 loss: 0.9030 (0.8976) grad: 0.0443 (0.0458) time: 0.3436 data: 0.0033 max mem: 3970 +train: [13] [200/400] eta: 0:01:12 lr: 0.000119 loss: 0.9108 (0.8977) grad: 0.0458 (0.0456) time: 0.3621 data: 0.0037 max mem: 3970 +train: [13] [220/400] eta: 0:01:04 lr: 0.000117 loss: 0.8819 (0.8985) grad: 0.0443 (0.0456) time: 0.3213 data: 0.0033 max mem: 3970 +train: [13] [240/400] eta: 0:00:56 lr: 0.000116 loss: 0.8858 (0.8981) grad: 0.0458 (0.0457) time: 0.3412 data: 0.0029 max mem: 3970 +train: [13] [260/400] eta: 0:00:49 lr: 0.000114 loss: 0.8858 (0.8996) grad: 0.0469 (0.0458) time: 0.3397 data: 0.0032 max mem: 3970 +train: [13] [280/400] eta: 0:00:42 lr: 0.000113 loss: 0.8905 (0.8984) grad: 0.0471 (0.0458) time: 0.3370 data: 0.0034 max mem: 3970 +train: [13] [300/400] eta: 0:00:36 lr: 0.000111 loss: 0.8905 (0.8973) grad: 0.0449 (0.0458) time: 0.4966 data: 0.1809 max mem: 3970 +train: [13] [320/400] eta: 0:00:28 lr: 0.000110 loss: 0.8939 (0.8979) grad: 0.0439 (0.0457) time: 0.3276 data: 0.0035 max mem: 3970 +train: [13] [340/400] eta: 0:00:21 lr: 0.000108 loss: 0.8815 (0.8968) grad: 0.0445 (0.0456) time: 0.3455 data: 0.0026 max mem: 3970 +train: [13] [360/400] eta: 0:00:14 lr: 0.000107 loss: 0.8815 (0.8962) grad: 0.0430 (0.0456) time: 0.4180 data: 0.0039 max mem: 3970 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 0.8907 (0.8960) grad: 0.0430 (0.0456) time: 0.3725 data: 0.0033 max mem: 3970 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 0.8985 (0.8966) grad: 0.0413 (0.0455) time: 0.3258 data: 0.0031 max mem: 3970 +train: [13] Total time: 0:02:24 (0.3621 s / it) +train: [13] Summary: lr: 0.000104 loss: 0.8985 (0.8966) grad: 0.0413 (0.0455) +eval (validation): [13] [ 0/63] eta: 0:03:12 time: 3.0511 data: 2.8044 max mem: 3970 +eval (validation): [13] [20/63] eta: 0:00:20 time: 0.3464 data: 0.0037 max mem: 3970 +eval (validation): [13] [40/63] eta: 0:00:09 time: 0.3238 data: 0.0029 max mem: 3970 +eval (validation): [13] [60/63] eta: 0:00:01 time: 0.3083 data: 0.0029 max mem: 3970 +eval (validation): [13] [62/63] eta: 0:00:00 time: 0.3052 data: 0.0030 max mem: 3970 +eval (validation): [13] Total time: 0:00:23 (0.3735 s / it) +cv: [13] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.126 acc: 0.964 f1: 0.960 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:20:41 lr: nan time: 3.1025 data: 2.8990 max mem: 3970 +train: [14] [ 20/400] eta: 0:02:59 lr: 0.000102 loss: 0.8591 (0.8769) grad: 0.0425 (0.0427) time: 0.3413 data: 0.0186 max mem: 3970 +train: [14] [ 40/400] eta: 0:02:25 lr: 0.000101 loss: 0.8750 (0.8816) grad: 0.0432 (0.0431) time: 0.3336 data: 0.0028 max mem: 3970 +train: [14] [ 60/400] eta: 0:02:08 lr: 0.000099 loss: 0.8877 (0.8821) grad: 0.0419 (0.0431) time: 0.3215 data: 0.0030 max mem: 3970 +train: [14] [ 80/400] eta: 0:01:57 lr: 0.000098 loss: 0.8947 (0.8865) grad: 0.0411 (0.0428) time: 0.3316 data: 0.0034 max mem: 3970 +train: [14] [100/400] eta: 0:01:48 lr: 0.000096 loss: 0.8712 (0.8820) grad: 0.0438 (0.0434) time: 0.3376 data: 0.0034 max mem: 3970 +train: [14] [120/400] eta: 0:01:40 lr: 0.000095 loss: 0.8365 (0.8806) grad: 0.0448 (0.0440) time: 0.3493 data: 0.0035 max mem: 3970 +train: [14] [140/400] eta: 0:01:32 lr: 0.000093 loss: 0.8608 (0.8791) grad: 0.0441 (0.0438) time: 0.3423 data: 0.0031 max mem: 3970 +train: [14] [160/400] eta: 0:01:25 lr: 0.000092 loss: 0.8871 (0.8809) grad: 0.0441 (0.0439) time: 0.3430 data: 0.0033 max mem: 3970 +train: [14] [180/400] eta: 0:01:17 lr: 0.000090 loss: 0.8836 (0.8799) grad: 0.0445 (0.0439) time: 0.3262 data: 0.0033 max mem: 3970 +train: [14] [200/400] eta: 0:01:09 lr: 0.000089 loss: 0.8698 (0.8809) grad: 0.0437 (0.0440) time: 0.3300 data: 0.0033 max mem: 3970 +train: [14] [220/400] eta: 0:01:02 lr: 0.000088 loss: 0.8698 (0.8807) grad: 0.0435 (0.0442) time: 0.3360 data: 0.0035 max mem: 3970 +train: [14] [240/400] eta: 0:00:55 lr: 0.000086 loss: 0.8808 (0.8815) grad: 0.0440 (0.0442) time: 0.3297 data: 0.0034 max mem: 3970 +train: [14] [260/400] eta: 0:00:48 lr: 0.000085 loss: 0.8890 (0.8821) grad: 0.0423 (0.0440) time: 0.3292 data: 0.0032 max mem: 3970 +train: [14] [280/400] eta: 0:00:41 lr: 0.000083 loss: 0.8639 (0.8813) grad: 0.0423 (0.0440) time: 0.3358 data: 0.0036 max mem: 3970 +train: [14] [300/400] eta: 0:00:35 lr: 0.000082 loss: 0.8639 (0.8821) grad: 0.0436 (0.0440) time: 0.5077 data: 0.1853 max mem: 3970 +train: [14] [320/400] eta: 0:00:28 lr: 0.000081 loss: 0.8777 (0.8830) grad: 0.0428 (0.0440) time: 0.3253 data: 0.0032 max mem: 3970 +train: [14] [340/400] eta: 0:00:21 lr: 0.000079 loss: 0.8725 (0.8817) grad: 0.0427 (0.0439) time: 0.3256 data: 0.0034 max mem: 3970 +train: [14] [360/400] eta: 0:00:14 lr: 0.000078 loss: 0.8894 (0.8826) grad: 0.0440 (0.0440) time: 0.3326 data: 0.0034 max mem: 3970 +train: [14] [380/400] eta: 0:00:06 lr: 0.000076 loss: 0.8912 (0.8826) grad: 0.0450 (0.0441) time: 0.3293 data: 0.0035 max mem: 3970 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 0.8787 (0.8820) grad: 0.0437 (0.0441) time: 0.3454 data: 0.0035 max mem: 3970 +train: [14] Total time: 0:02:19 (0.3499 s / it) +train: [14] Summary: lr: 0.000075 loss: 0.8787 (0.8820) grad: 0.0437 (0.0441) +eval (validation): [14] [ 0/63] eta: 0:03:29 time: 3.3176 data: 3.1077 max mem: 3970 +eval (validation): [14] [20/63] eta: 0:00:20 time: 0.3301 data: 0.0038 max mem: 3970 +eval (validation): [14] [40/63] eta: 0:00:09 time: 0.3280 data: 0.0032 max mem: 3970 +eval (validation): [14] [60/63] eta: 0:00:01 time: 0.3032 data: 0.0032 max mem: 3970 +eval (validation): [14] [62/63] eta: 0:00:00 time: 0.3034 data: 0.0032 max mem: 3970 +eval (validation): [14] Total time: 0:00:23 (0.3723 s / it) +cv: [14] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.127 acc: 0.962 f1: 0.958 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:20:41 lr: nan time: 3.1028 data: 2.8966 max mem: 3970 +train: [15] [ 20/400] eta: 0:03:05 lr: 0.000074 loss: 0.8664 (0.8810) grad: 0.0425 (0.0432) time: 0.3582 data: 0.0042 max mem: 3970 +train: [15] [ 40/400] eta: 0:02:28 lr: 0.000072 loss: 0.8807 (0.8991) grad: 0.0441 (0.0440) time: 0.3344 data: 0.0031 max mem: 3970 +train: [15] [ 60/400] eta: 0:02:09 lr: 0.000071 loss: 0.8807 (0.8882) grad: 0.0441 (0.0445) time: 0.3152 data: 0.0033 max mem: 3970 +train: [15] [ 80/400] eta: 0:01:57 lr: 0.000070 loss: 0.8763 (0.8824) grad: 0.0453 (0.0449) time: 0.3249 data: 0.0031 max mem: 3970 +train: [15] [100/400] eta: 0:01:47 lr: 0.000068 loss: 0.8527 (0.8779) grad: 0.0447 (0.0447) time: 0.3292 data: 0.0032 max mem: 3970 +train: [15] [120/400] eta: 0:01:38 lr: 0.000067 loss: 0.8497 (0.8754) grad: 0.0453 (0.0450) time: 0.3213 data: 0.0031 max mem: 3970 +train: [15] [140/400] eta: 0:01:31 lr: 0.000066 loss: 0.8607 (0.8762) grad: 0.0459 (0.0446) time: 0.3391 data: 0.0032 max mem: 3970 +train: [15] [160/400] eta: 0:01:23 lr: 0.000064 loss: 0.8607 (0.8759) grad: 0.0459 (0.0447) time: 0.3310 data: 0.0035 max mem: 3970 +train: [15] [180/400] eta: 0:01:16 lr: 0.000063 loss: 0.8586 (0.8747) grad: 0.0459 (0.0447) time: 0.3196 data: 0.0035 max mem: 3970 +train: [15] [200/400] eta: 0:01:09 lr: 0.000062 loss: 0.8696 (0.8764) grad: 0.0431 (0.0449) time: 0.3450 data: 0.0036 max mem: 3970 +train: [15] [220/400] eta: 0:01:02 lr: 0.000061 loss: 0.8613 (0.8737) grad: 0.0428 (0.0447) time: 0.3387 data: 0.0033 max mem: 3970 +train: [15] [240/400] eta: 0:00:55 lr: 0.000059 loss: 0.8441 (0.8725) grad: 0.0429 (0.0449) time: 0.3345 data: 0.0029 max mem: 3970 +train: [15] [260/400] eta: 0:00:47 lr: 0.000058 loss: 0.8502 (0.8737) grad: 0.0452 (0.0449) time: 0.3254 data: 0.0032 max mem: 3970 +train: [15] [280/400] eta: 0:00:41 lr: 0.000057 loss: 0.8593 (0.8723) grad: 0.0451 (0.0449) time: 0.3523 data: 0.0034 max mem: 3970 +train: [15] [300/400] eta: 0:00:35 lr: 0.000056 loss: 0.8660 (0.8730) grad: 0.0440 (0.0449) time: 0.5040 data: 0.1809 max mem: 3970 +train: [15] [320/400] eta: 0:00:28 lr: 0.000054 loss: 0.8718 (0.8730) grad: 0.0440 (0.0447) time: 0.3612 data: 0.0200 max mem: 3970 +train: [15] [340/400] eta: 0:00:21 lr: 0.000053 loss: 0.8655 (0.8724) grad: 0.0431 (0.0449) time: 0.3194 data: 0.0024 max mem: 3970 +train: [15] [360/400] eta: 0:00:14 lr: 0.000052 loss: 0.8655 (0.8720) grad: 0.0431 (0.0448) time: 0.3263 data: 0.0030 max mem: 3970 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 0.8678 (0.8721) grad: 0.0437 (0.0448) time: 0.3449 data: 0.0032 max mem: 3970 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 0.8482 (0.8713) grad: 0.0425 (0.0446) time: 0.3239 data: 0.0032 max mem: 3970 +train: [15] Total time: 0:02:19 (0.3496 s / it) +train: [15] Summary: lr: 0.000050 loss: 0.8482 (0.8713) grad: 0.0425 (0.0446) +eval (validation): [15] [ 0/63] eta: 0:03:27 time: 3.2911 data: 3.0472 max mem: 3970 +eval (validation): [15] [20/63] eta: 0:00:21 time: 0.3512 data: 0.0037 max mem: 3970 +eval (validation): [15] [40/63] eta: 0:00:09 time: 0.3155 data: 0.0032 max mem: 3970 +eval (validation): [15] [60/63] eta: 0:00:01 time: 0.2938 data: 0.0032 max mem: 3970 +eval (validation): [15] [62/63] eta: 0:00:00 time: 0.2929 data: 0.0032 max mem: 3970 +eval (validation): [15] Total time: 0:00:23 (0.3703 s / it) +cv: [15] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.124 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:18 lr: nan time: 3.3467 data: 3.0838 max mem: 3970 +train: [16] [ 20/400] eta: 0:03:05 lr: 0.000048 loss: 0.8648 (0.8790) grad: 0.0441 (0.0445) time: 0.3442 data: 0.0040 max mem: 3970 +train: [16] [ 40/400] eta: 0:02:27 lr: 0.000047 loss: 0.8648 (0.8720) grad: 0.0442 (0.0445) time: 0.3282 data: 0.0028 max mem: 3970 +train: [16] [ 60/400] eta: 0:02:09 lr: 0.000046 loss: 0.8474 (0.8641) grad: 0.0448 (0.0446) time: 0.3264 data: 0.0034 max mem: 3970 +train: [16] [ 80/400] eta: 0:01:57 lr: 0.000045 loss: 0.8528 (0.8636) grad: 0.0459 (0.0452) time: 0.3182 data: 0.0032 max mem: 3970 +train: [16] [100/400] eta: 0:01:48 lr: 0.000044 loss: 0.8540 (0.8614) grad: 0.0438 (0.0446) time: 0.3358 data: 0.0033 max mem: 3970 +train: [16] [120/400] eta: 0:01:39 lr: 0.000043 loss: 0.8557 (0.8630) grad: 0.0430 (0.0444) time: 0.3309 data: 0.0033 max mem: 3970 +train: [16] [140/400] eta: 0:01:31 lr: 0.000042 loss: 0.8626 (0.8646) grad: 0.0432 (0.0444) time: 0.3300 data: 0.0034 max mem: 3970 +train: [16] [160/400] eta: 0:01:23 lr: 0.000041 loss: 0.8502 (0.8635) grad: 0.0437 (0.0444) time: 0.3237 data: 0.0036 max mem: 3970 +train: [16] [180/400] eta: 0:01:16 lr: 0.000040 loss: 0.8381 (0.8624) grad: 0.0437 (0.0444) time: 0.3323 data: 0.0034 max mem: 3970 +train: [16] [200/400] eta: 0:01:08 lr: 0.000039 loss: 0.8404 (0.8627) grad: 0.0445 (0.0444) time: 0.3273 data: 0.0034 max mem: 3970 +train: [16] [220/400] eta: 0:01:01 lr: 0.000038 loss: 0.8430 (0.8608) grad: 0.0444 (0.0444) time: 0.3397 data: 0.0036 max mem: 3970 +train: [16] [240/400] eta: 0:00:55 lr: 0.000036 loss: 0.8635 (0.8642) grad: 0.0424 (0.0444) time: 0.3622 data: 0.0032 max mem: 3970 +train: [16] [260/400] eta: 0:00:48 lr: 0.000035 loss: 0.8757 (0.8629) grad: 0.0443 (0.0445) time: 0.3474 data: 0.0034 max mem: 3970 +train: [16] [280/400] eta: 0:00:41 lr: 0.000034 loss: 0.8662 (0.8629) grad: 0.0431 (0.0443) time: 0.3231 data: 0.0032 max mem: 3970 +train: [16] [300/400] eta: 0:00:35 lr: 0.000033 loss: 0.8541 (0.8629) grad: 0.0415 (0.0442) time: 0.5080 data: 0.1819 max mem: 3970 +train: [16] [320/400] eta: 0:00:28 lr: 0.000032 loss: 0.8652 (0.8643) grad: 0.0427 (0.0442) time: 0.3616 data: 0.0042 max mem: 3970 +train: [16] [340/400] eta: 0:00:21 lr: 0.000031 loss: 0.8722 (0.8644) grad: 0.0419 (0.0441) time: 0.3289 data: 0.0035 max mem: 3970 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 0.8538 (0.8640) grad: 0.0419 (0.0440) time: 0.3434 data: 0.0031 max mem: 3970 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 0.8621 (0.8639) grad: 0.0422 (0.0439) time: 0.3505 data: 0.0035 max mem: 3970 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 0.8430 (0.8632) grad: 0.0417 (0.0439) time: 0.3644 data: 0.0036 max mem: 3970 +train: [16] Total time: 0:02:21 (0.3539 s / it) +train: [16] Summary: lr: 0.000029 loss: 0.8430 (0.8632) grad: 0.0417 (0.0439) +eval (validation): [16] [ 0/63] eta: 0:03:23 time: 3.2253 data: 2.9841 max mem: 3970 +eval (validation): [16] [20/63] eta: 0:00:20 time: 0.3323 data: 0.0035 max mem: 3970 +eval (validation): [16] [40/63] eta: 0:00:09 time: 0.3379 data: 0.0028 max mem: 3970 +eval (validation): [16] [60/63] eta: 0:00:01 time: 0.3226 data: 0.0035 max mem: 3970 +eval (validation): [16] [62/63] eta: 0:00:00 time: 0.3205 data: 0.0035 max mem: 3970 +eval (validation): [16] Total time: 0:00:23 (0.3800 s / it) +cv: [16] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.124 acc: 0.963 f1: 0.958 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:02 lr: nan time: 3.3064 data: 3.0921 max mem: 3970 +train: [17] [ 20/400] eta: 0:03:03 lr: 0.000028 loss: 0.8502 (0.8472) grad: 0.0432 (0.0460) time: 0.3426 data: 0.0037 max mem: 3970 +train: [17] [ 40/400] eta: 0:02:26 lr: 0.000027 loss: 0.8409 (0.8421) grad: 0.0432 (0.0451) time: 0.3275 data: 0.0030 max mem: 3970 +train: [17] [ 60/400] eta: 0:02:10 lr: 0.000026 loss: 0.8518 (0.8499) grad: 0.0432 (0.0446) time: 0.3380 data: 0.0032 max mem: 3970 +train: [17] [ 80/400] eta: 0:02:02 lr: 0.000025 loss: 0.8618 (0.8557) grad: 0.0432 (0.0444) time: 0.3826 data: 0.0037 max mem: 3970 +train: [17] [100/400] eta: 0:01:51 lr: 0.000024 loss: 0.8654 (0.8605) grad: 0.0419 (0.0441) time: 0.3151 data: 0.0034 max mem: 3970 +train: [17] [120/400] eta: 0:01:41 lr: 0.000023 loss: 0.8670 (0.8585) grad: 0.0433 (0.0446) time: 0.3308 data: 0.0034 max mem: 3970 +train: [17] [140/400] eta: 0:01:33 lr: 0.000023 loss: 0.8485 (0.8578) grad: 0.0446 (0.0444) time: 0.3351 data: 0.0034 max mem: 3970 +train: [17] [160/400] eta: 0:01:25 lr: 0.000022 loss: 0.8515 (0.8566) grad: 0.0417 (0.0442) time: 0.3332 data: 0.0034 max mem: 3970 +train: [17] [180/400] eta: 0:01:17 lr: 0.000021 loss: 0.8521 (0.8566) grad: 0.0427 (0.0441) time: 0.3327 data: 0.0031 max mem: 3970 +train: [17] [200/400] eta: 0:01:10 lr: 0.000020 loss: 0.8645 (0.8596) grad: 0.0427 (0.0441) time: 0.3379 data: 0.0035 max mem: 3970 +train: [17] [220/400] eta: 0:01:03 lr: 0.000019 loss: 0.8645 (0.8588) grad: 0.0417 (0.0439) time: 0.3313 data: 0.0034 max mem: 3970 +train: [17] [240/400] eta: 0:00:55 lr: 0.000019 loss: 0.8413 (0.8585) grad: 0.0423 (0.0441) time: 0.3323 data: 0.0033 max mem: 3970 +train: [17] [260/400] eta: 0:00:48 lr: 0.000018 loss: 0.8413 (0.8592) grad: 0.0464 (0.0442) time: 0.3326 data: 0.0032 max mem: 3970 +train: [17] [280/400] eta: 0:00:41 lr: 0.000017 loss: 0.8629 (0.8593) grad: 0.0445 (0.0442) time: 0.3302 data: 0.0032 max mem: 3970 +train: [17] [300/400] eta: 0:00:35 lr: 0.000016 loss: 0.8629 (0.8594) grad: 0.0431 (0.0441) time: 0.4801 data: 0.1764 max mem: 3970 +train: [17] [320/400] eta: 0:00:28 lr: 0.000016 loss: 0.8649 (0.8604) grad: 0.0432 (0.0441) time: 0.3271 data: 0.0036 max mem: 3970 +train: [17] [340/400] eta: 0:00:21 lr: 0.000015 loss: 0.8520 (0.8598) grad: 0.0439 (0.0441) time: 0.3452 data: 0.0035 max mem: 3970 +train: [17] [360/400] eta: 0:00:14 lr: 0.000014 loss: 0.8518 (0.8599) grad: 0.0426 (0.0441) time: 0.3200 data: 0.0032 max mem: 3970 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 0.8355 (0.8594) grad: 0.0422 (0.0440) time: 0.3385 data: 0.0031 max mem: 3970 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 0.8428 (0.8587) grad: 0.0438 (0.0441) time: 0.3319 data: 0.0031 max mem: 3970 +train: [17] Total time: 0:02:19 (0.3499 s / it) +train: [17] Summary: lr: 0.000013 loss: 0.8428 (0.8587) grad: 0.0438 (0.0441) +eval (validation): [17] [ 0/63] eta: 0:03:28 time: 3.3097 data: 3.0526 max mem: 3970 +eval (validation): [17] [20/63] eta: 0:00:21 time: 0.3595 data: 0.0087 max mem: 3970 +eval (validation): [17] [40/63] eta: 0:00:09 time: 0.3111 data: 0.0040 max mem: 3970 +eval (validation): [17] [60/63] eta: 0:00:01 time: 0.3111 data: 0.0020 max mem: 3970 +eval (validation): [17] [62/63] eta: 0:00:00 time: 0.3082 data: 0.0022 max mem: 3970 +eval (validation): [17] Total time: 0:00:23 (0.3786 s / it) +cv: [17] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 0.123 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [18] [ 0/400] eta: 0:21:29 lr: nan time: 3.2229 data: 3.0136 max mem: 3970 +train: [18] [ 20/400] eta: 0:02:54 lr: 0.000012 loss: 0.8762 (0.8800) grad: 0.0400 (0.0412) time: 0.3203 data: 0.0043 max mem: 3970 +train: [18] [ 40/400] eta: 0:02:23 lr: 0.000012 loss: 0.8557 (0.8675) grad: 0.0411 (0.0430) time: 0.3376 data: 0.0028 max mem: 3970 +train: [18] [ 60/400] eta: 0:02:10 lr: 0.000011 loss: 0.8476 (0.8650) grad: 0.0438 (0.0430) time: 0.3520 data: 0.0033 max mem: 3970 +train: [18] [ 80/400] eta: 0:01:58 lr: 0.000011 loss: 0.8476 (0.8640) grad: 0.0437 (0.0435) time: 0.3301 data: 0.0033 max mem: 3970 +train: [18] [100/400] eta: 0:01:48 lr: 0.000010 loss: 0.8393 (0.8576) grad: 0.0451 (0.0438) time: 0.3300 data: 0.0032 max mem: 3970 +train: [18] [120/400] eta: 0:01:38 lr: 0.000009 loss: 0.8251 (0.8558) grad: 0.0440 (0.0439) time: 0.3054 data: 0.0031 max mem: 3970 +train: [18] [140/400] eta: 0:01:31 lr: 0.000009 loss: 0.8438 (0.8562) grad: 0.0423 (0.0438) time: 0.3349 data: 0.0033 max mem: 3970 +train: [18] [160/400] eta: 0:01:24 lr: 0.000008 loss: 0.8358 (0.8550) grad: 0.0423 (0.0440) time: 0.3486 data: 0.0032 max mem: 3970 +train: [18] [180/400] eta: 0:01:16 lr: 0.000008 loss: 0.8534 (0.8555) grad: 0.0429 (0.0440) time: 0.3432 data: 0.0034 max mem: 3970 +train: [18] [200/400] eta: 0:01:09 lr: 0.000007 loss: 0.8552 (0.8565) grad: 0.0425 (0.0439) time: 0.3526 data: 0.0034 max mem: 3970 +train: [18] [220/400] eta: 0:01:02 lr: 0.000007 loss: 0.8500 (0.8554) grad: 0.0425 (0.0439) time: 0.3097 data: 0.0032 max mem: 3970 +train: [18] [240/400] eta: 0:00:55 lr: 0.000006 loss: 0.8552 (0.8560) grad: 0.0413 (0.0436) time: 0.3381 data: 0.0032 max mem: 3970 +train: [18] [260/400] eta: 0:00:48 lr: 0.000006 loss: 0.8619 (0.8555) grad: 0.0410 (0.0436) time: 0.3432 data: 0.0033 max mem: 3970 +train: [18] [280/400] eta: 0:00:41 lr: 0.000006 loss: 0.8416 (0.8541) grad: 0.0434 (0.0439) time: 0.3311 data: 0.0034 max mem: 3970 +train: [18] [300/400] eta: 0:00:35 lr: 0.000005 loss: 0.8626 (0.8556) grad: 0.0446 (0.0438) time: 0.4823 data: 0.1753 max mem: 3970 +train: [18] [320/400] eta: 0:00:28 lr: 0.000005 loss: 0.8693 (0.8553) grad: 0.0439 (0.0439) time: 0.3390 data: 0.0039 max mem: 3970 +train: [18] [340/400] eta: 0:00:21 lr: 0.000004 loss: 0.8693 (0.8559) grad: 0.0457 (0.0441) time: 0.3172 data: 0.0032 max mem: 3970 +train: [18] [360/400] eta: 0:00:13 lr: 0.000004 loss: 0.8466 (0.8547) grad: 0.0457 (0.0442) time: 0.3293 data: 0.0033 max mem: 3970 +train: [18] [380/400] eta: 0:00:06 lr: 0.000004 loss: 0.8207 (0.8536) grad: 0.0437 (0.0442) time: 0.3346 data: 0.0035 max mem: 3970 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 0.8359 (0.8531) grad: 0.0419 (0.0441) time: 0.3341 data: 0.0032 max mem: 3970 +train: [18] Total time: 0:02:19 (0.3481 s / it) +train: [18] Summary: lr: 0.000003 loss: 0.8359 (0.8531) grad: 0.0419 (0.0441) +eval (validation): [18] [ 0/63] eta: 0:03:29 time: 3.3224 data: 3.1157 max mem: 3970 +eval (validation): [18] [20/63] eta: 0:00:21 time: 0.3544 data: 0.0202 max mem: 3970 +eval (validation): [18] [40/63] eta: 0:00:09 time: 0.3191 data: 0.0029 max mem: 3970 +eval (validation): [18] [60/63] eta: 0:00:01 time: 0.3032 data: 0.0034 max mem: 3970 +eval (validation): [18] [62/63] eta: 0:00:00 time: 0.3013 data: 0.0034 max mem: 3970 +eval (validation): [18] Total time: 0:00:23 (0.3767 s / it) +cv: [18] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 0.125 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:21:33 lr: nan time: 3.2344 data: 3.0124 max mem: 3970 +train: [19] [ 20/400] eta: 0:02:56 lr: 0.000003 loss: 0.8463 (0.8697) grad: 0.0404 (0.0404) time: 0.3263 data: 0.0038 max mem: 3970 +train: [19] [ 40/400] eta: 0:02:25 lr: 0.000003 loss: 0.8338 (0.8502) grad: 0.0409 (0.0427) time: 0.3398 data: 0.0039 max mem: 3970 +train: [19] [ 60/400] eta: 0:02:07 lr: 0.000002 loss: 0.8645 (0.8565) grad: 0.0442 (0.0429) time: 0.3188 data: 0.0029 max mem: 3970 +train: [19] [ 80/400] eta: 0:01:58 lr: 0.000002 loss: 0.8684 (0.8566) grad: 0.0431 (0.0432) time: 0.3498 data: 0.0034 max mem: 3970 +train: [19] [100/400] eta: 0:01:48 lr: 0.000002 loss: 0.8299 (0.8519) grad: 0.0429 (0.0432) time: 0.3334 data: 0.0032 max mem: 3970 +train: [19] [120/400] eta: 0:01:40 lr: 0.000002 loss: 0.8175 (0.8534) grad: 0.0426 (0.0433) time: 0.3312 data: 0.0029 max mem: 3970 +train: [19] [140/400] eta: 0:01:31 lr: 0.000001 loss: 0.8319 (0.8504) grad: 0.0442 (0.0436) time: 0.3140 data: 0.0031 max mem: 3970 +train: [19] [160/400] eta: 0:01:23 lr: 0.000001 loss: 0.8263 (0.8477) grad: 0.0452 (0.0438) time: 0.3326 data: 0.0033 max mem: 3970 +train: [19] [180/400] eta: 0:01:16 lr: 0.000001 loss: 0.8455 (0.8502) grad: 0.0430 (0.0439) time: 0.3551 data: 0.0033 max mem: 3970 +train: [19] [200/400] eta: 0:01:10 lr: 0.000001 loss: 0.8737 (0.8519) grad: 0.0429 (0.0438) time: 0.3594 data: 0.0034 max mem: 3970 +train: [19] [220/400] eta: 0:01:02 lr: 0.000001 loss: 0.8572 (0.8511) grad: 0.0422 (0.0438) time: 0.3274 data: 0.0034 max mem: 3970 +train: [19] [240/400] eta: 0:00:55 lr: 0.000001 loss: 0.8348 (0.8495) grad: 0.0422 (0.0438) time: 0.3399 data: 0.0035 max mem: 3970 +train: [19] [260/400] eta: 0:00:48 lr: 0.000000 loss: 0.8297 (0.8488) grad: 0.0429 (0.0438) time: 0.3442 data: 0.0031 max mem: 3970 +train: [19] [280/400] eta: 0:00:41 lr: 0.000000 loss: 0.8297 (0.8496) grad: 0.0442 (0.0439) time: 0.3426 data: 0.0031 max mem: 3970 +train: [19] [300/400] eta: 0:00:35 lr: 0.000000 loss: 0.8359 (0.8492) grad: 0.0442 (0.0438) time: 0.5219 data: 0.1839 max mem: 3970 +train: [19] [320/400] eta: 0:00:28 lr: 0.000000 loss: 0.8468 (0.8494) grad: 0.0413 (0.0437) time: 0.3550 data: 0.0033 max mem: 3970 +train: [19] [340/400] eta: 0:00:21 lr: 0.000000 loss: 0.8468 (0.8502) grad: 0.0432 (0.0438) time: 0.3440 data: 0.0030 max mem: 3970 +train: [19] [360/400] eta: 0:00:14 lr: 0.000000 loss: 0.8503 (0.8498) grad: 0.0444 (0.0439) time: 0.3316 data: 0.0034 max mem: 3970 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 0.8503 (0.8495) grad: 0.0441 (0.0439) time: 0.3262 data: 0.0033 max mem: 3970 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 0.8718 (0.8523) grad: 0.0441 (0.0439) time: 0.3350 data: 0.0032 max mem: 3970 +train: [19] Total time: 0:02:21 (0.3540 s / it) +train: [19] Summary: lr: 0.000000 loss: 0.8718 (0.8523) grad: 0.0441 (0.0439) +eval (validation): [19] [ 0/63] eta: 0:03:30 time: 3.3342 data: 3.0747 max mem: 3970 +eval (validation): [19] [20/63] eta: 0:00:20 time: 0.3314 data: 0.0047 max mem: 3970 +eval (validation): [19] [40/63] eta: 0:00:09 time: 0.3181 data: 0.0029 max mem: 3970 +eval (validation): [19] [60/63] eta: 0:00:01 time: 0.2973 data: 0.0031 max mem: 3970 +eval (validation): [19] [62/63] eta: 0:00:00 time: 0.2974 data: 0.0031 max mem: 3970 +eval (validation): [19] Total time: 0:00:23 (0.3683 s / it) +cv: [19] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 0.124 acc: 0.963 f1: 0.959 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-last.pth +eval model info: +{"score": 0.9630456349206349, "hparam": [43, 1.0], "hparam_id": 47, "epoch": 19, "is_best": false, "best_score": 0.9640376984126984} +eval (train): [20] [ 0/297] eta: 0:15:52 time: 3.2085 data: 2.9486 max mem: 3970 +eval (train): [20] [ 20/297] eta: 0:02:16 time: 0.3571 data: 0.0034 max mem: 3970 +eval (train): [20] [ 40/297] eta: 0:01:45 time: 0.3223 data: 0.0032 max mem: 3970 +eval (train): [20] [ 60/297] eta: 0:01:28 time: 0.3044 data: 0.0034 max mem: 3970 +eval (train): [20] [ 80/297] eta: 0:01:18 time: 0.3181 data: 0.0036 max mem: 3970 +eval (train): [20] [100/297] eta: 0:01:10 time: 0.3333 data: 0.0038 max mem: 3970 +eval (train): [20] [120/297] eta: 0:01:02 time: 0.3326 data: 0.0030 max mem: 3970 +eval (train): [20] [140/297] eta: 0:00:54 time: 0.3103 data: 0.0035 max mem: 3970 +eval (train): [20] [160/297] eta: 0:00:46 time: 0.2997 data: 0.0031 max mem: 3970 +eval (train): [20] [180/297] eta: 0:00:39 time: 0.3358 data: 0.0038 max mem: 3970 +eval (train): [20] [200/297] eta: 0:00:32 time: 0.3214 data: 0.0030 max mem: 3970 +eval (train): [20] [220/297] eta: 0:00:25 time: 0.3097 data: 0.0035 max mem: 3970 +eval (train): [20] [240/297] eta: 0:00:18 time: 0.3100 data: 0.0036 max mem: 3970 +eval (train): [20] [260/297] eta: 0:00:12 time: 0.3104 data: 0.0032 max mem: 3970 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3352 data: 0.0036 max mem: 3970 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3054 data: 0.0028 max mem: 3970 +eval (train): [20] Total time: 0:01:38 (0.3312 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:26 time: 3.2724 data: 3.0234 max mem: 3970 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3454 data: 0.0147 max mem: 3970 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3229 data: 0.0029 max mem: 3970 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3049 data: 0.0033 max mem: 3970 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3021 data: 0.0033 max mem: 3970 +eval (validation): [20] Total time: 0:00:23 (0.3751 s / it) +eval (test): [20] [ 0/79] eta: 0:04:19 time: 3.2808 data: 3.0185 max mem: 3970 +eval (test): [20] [20/79] eta: 0:00:27 time: 0.3281 data: 0.0042 max mem: 3970 +eval (test): [20] [40/79] eta: 0:00:16 time: 0.3721 data: 0.0038 max mem: 3970 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3306 data: 0.0037 max mem: 3970 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3035 data: 0.0032 max mem: 3970 +eval (test): [20] Total time: 0:00:29 (0.3760 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/checkpoint-best.pth +eval model info: +{"score": 0.9640376984126984, "hparam": [43, 1.0], "hparam_id": 47, "epoch": 13, "is_best": true, "best_score": 0.9640376984126984} +eval (train): [20] [ 0/297] eta: 0:15:18 time: 3.0910 data: 2.8810 max mem: 3970 +eval (train): [20] [ 20/297] eta: 0:02:12 time: 0.3494 data: 0.0035 max mem: 3970 +eval (train): [20] [ 40/297] eta: 0:01:47 time: 0.3514 data: 0.0035 max mem: 3970 +eval (train): [20] [ 60/297] eta: 0:01:35 time: 0.3680 data: 0.0035 max mem: 3970 +eval (train): [20] [ 80/297] eta: 0:01:22 time: 0.3209 data: 0.0036 max mem: 3970 +eval (train): [20] [100/297] eta: 0:01:12 time: 0.3019 data: 0.0034 max mem: 3970 +eval (train): [20] [120/297] eta: 0:01:03 time: 0.3225 data: 0.0034 max mem: 3970 +eval (train): [20] [140/297] eta: 0:00:56 time: 0.3547 data: 0.0037 max mem: 3970 +eval (train): [20] [160/297] eta: 0:00:48 time: 0.3147 data: 0.0034 max mem: 3970 +eval (train): [20] [180/297] eta: 0:00:41 time: 0.3446 data: 0.0031 max mem: 3970 +eval (train): [20] [200/297] eta: 0:00:33 time: 0.3040 data: 0.0032 max mem: 3970 +eval (train): [20] [220/297] eta: 0:00:26 time: 0.3323 data: 0.0034 max mem: 3970 +eval (train): [20] [240/297] eta: 0:00:19 time: 0.3493 data: 0.0035 max mem: 3970 +eval (train): [20] [260/297] eta: 0:00:12 time: 0.3374 data: 0.0035 max mem: 3970 +eval (train): [20] [280/297] eta: 0:00:05 time: 0.3206 data: 0.0034 max mem: 3970 +eval (train): [20] [296/297] eta: 0:00:00 time: 0.3053 data: 0.0033 max mem: 3970 +eval (train): [20] Total time: 0:01:41 (0.3428 s / it) +eval (validation): [20] [ 0/63] eta: 0:03:25 time: 3.2685 data: 3.0447 max mem: 3970 +eval (validation): [20] [20/63] eta: 0:00:20 time: 0.3357 data: 0.0106 max mem: 3970 +eval (validation): [20] [40/63] eta: 0:00:09 time: 0.3311 data: 0.0032 max mem: 3970 +eval (validation): [20] [60/63] eta: 0:00:01 time: 0.3061 data: 0.0032 max mem: 3970 +eval (validation): [20] [62/63] eta: 0:00:00 time: 0.3037 data: 0.0031 max mem: 3970 +eval (validation): [20] Total time: 0:00:23 (0.3745 s / it) +eval (test): [20] [ 0/79] eta: 0:04:16 time: 3.2474 data: 2.9952 max mem: 3970 +eval (test): [20] [20/79] eta: 0:00:27 time: 0.3303 data: 0.0048 max mem: 3970 +eval (test): [20] [40/79] eta: 0:00:15 time: 0.3337 data: 0.0031 max mem: 3970 +eval (test): [20] [60/79] eta: 0:00:07 time: 0.3088 data: 0.0034 max mem: 3970 +eval (test): [20] [78/79] eta: 0:00:00 time: 0.3130 data: 0.0030 max mem: 3970 +eval (test): [20] Total time: 0:00:28 (0.3632 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|---------:|--------:|-----------:|--------:|-----------:| +| flat_mae | reg | linear | hcpya_task21 | best | 13 | 0.0129 | 0.05 | 47 | [43, 1.0] | train | 0.085254 | 0.98237 | 0.00086578 | 0.98293 | 0.00090952 | +| flat_mae | reg | linear | hcpya_task21 | best | 13 | 0.0129 | 0.05 | 47 | [43, 1.0] | validation | 0.12552 | 0.96404 | 0.0027959 | 0.95968 | 0.0035716 | +| flat_mae | reg | linear | hcpya_task21 | best | 13 | 0.0129 | 0.05 | 47 | [43, 1.0] | test | 0.14403 | 0.95774 | 0.0027262 | 0.95087 | 0.0035853 | + + +done! total time: 1:02:48 diff --git a/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/train_log.json b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..8dcc690937e689d69f3f9981c65f099ef03d6a8d --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/hcpya_task21__reg__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 2.7801408410072326, "train/grad": 0.10552559576928616, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.0320458984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.031827392578125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.03149169921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.03114501953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.030787353515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.0303076171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.029765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.029150390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.028360595703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.02742919921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.0265380859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.025177001953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.023778076171875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.021795654296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.01978515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0177880859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.015020751953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.01170654296875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.007747802734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.003798828125, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.998604736328125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.992783203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.985665283203125, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.977408447265625, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.968189697265625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.95587890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.94389404296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.93216796875, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.914923095703125, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.89262939453125, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.871060791015625, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.850101318359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.8199322509765623, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7909088134765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.75389892578125, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.714278564453125, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.66838134765625, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.62096923828125, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.5652066040039063, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4895370483398436, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.42632080078125, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3676856994628905, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2874356079101563, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2150946044921875, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.129209671020508, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.035568313598633, "train/loss_046_lr3.6e+01_wd1.0e+00": 1.9542386627197266, "train/loss_047_lr4.3e+01_wd1.0e+00": 1.8563356399536133, "train/loss_048_lr5.0e+01_wd1.0e+00": 1.7731484222412108, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016629730029962958, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016627639243379237, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01662434222176671, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.016620644871145486, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.016616918738000096, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.016611888976767658, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.016606794856488704, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.016601119292899966, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.016593633671291172, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.016584264417178928, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016575780799612402, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.016562428791075945, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.016549456263892353, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0165301617840305, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.016510594682767988, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.016491452301852404, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.016465391432866454, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.016434325664304198, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.016395441396161912, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.016357417195104064, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01630755721591413, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.016251041726209222, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.016184216383844614, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.016106565273366867, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.016017461530864238, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.015902153383940458, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.015789229786023498, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01567934034857899, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.015519758113659918, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.015316676967777311, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01512395076919347, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.014940937850624322, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01468404002021998, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.014445854877121746, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.014157130173407495, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01386692099738866, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.013554835617542267, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01325631800107658, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012931435471400618, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.012527772814501077, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01221296124625951, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011936564804054797, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011573139566462488, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011257484401576222, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010893698702566325, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010507514062337577, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010176929484587163, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009786732634529472, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009460650022374466, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.0282599925994873, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0276331901550293, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0266096591949463, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.025508403778076, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.024423122406006, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.0229363441467285, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.02126145362854, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.0193898677825928, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.016903877258301, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.0141730308532715, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.011451244354248, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.007326602935791, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.0031113624572754, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.9969608783721924, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9908432960510254, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.984694242477417, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.976628065109253, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.9665403366088867, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.9547171592712402, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.9428935050964355, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.9273681640625, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.9102025032043457, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.889669418334961, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.865800619125366, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.838958740234375, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.8041820526123047, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.7705116271972656, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7378106117248535, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6905295848846436, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.6304616928100586, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.573385715484619, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5189733505249023, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4415321350097656, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.3686344623565674, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.2773234844207764, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.181593179702759, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.0731780529022217, "validation/loss_037_lr8.3e+00_wd1.0e+00": 1.964538812637329, "validation/loss_038_lr9.8e+00_wd1.0e+00": 1.840994119644165, "validation/loss_039_lr1.2e+01_wd1.0e+00": 1.682004690170288, "validation/loss_040_lr1.4e+01_wd1.0e+00": 1.5571788549423218, "validation/loss_041_lr1.6e+01_wd1.0e+00": 1.4483178853988647, "validation/loss_042_lr1.9e+01_wd1.0e+00": 1.3097935914993286, "validation/loss_043_lr2.2e+01_wd1.0e+00": 1.1952608823776245, "validation/loss_044_lr2.6e+01_wd1.0e+00": 1.0703749656677246, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.9477534294128418, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.8513525128364563, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.7471132278442383, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.6676458120346069, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07068452380952381, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07118055555555555, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07316468253968254, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0763888888888889, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07961309523809523, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0835813492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.08705357142857142, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.08953373015873016, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.09275793650793651, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.09846230158730158, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.10267857142857142, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.11011904761904762, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.11607142857142858, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.12872023809523808, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1463293650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.16344246031746032, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.1827876984126984, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.20337301587301587, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2214781746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2309027777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23387896825396826, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.23387896825396826, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.23511904761904762, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24057539682539683, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24776785714285715, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2517361111111111, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2591765873015873, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2638888888888889, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27529761904761907, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.29117063492063494, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.3162202380952381, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.3323412698412698, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.34945436507936506, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.36334325396825395, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.3819444444444444, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.42237103174603174, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.49181547619047616, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.5595238095238095, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.6138392857142857, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.6989087301587301, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.7628968253968254, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.8127480158730159, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.8596230158730159, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.8831845238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.8948412698412699, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9030257936507936, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9087301587301587, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9131944444444444, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9181547619047619, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.02219714621012825, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.022248930417464594, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.02263985437318191, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.023662693128061078, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.024422394657453012, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.026254917364647044, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.026988365878339374, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.027277351291829146, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.027916295834048734, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.02959891825199535, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.03063221259898435, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.03180999582211809, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.03307279398344017, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.036228785189273895, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04064093478788457, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.04248825561805589, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.04604439049802027, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.04880920787110622, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.050744522117726676, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.05173976776771215, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.05116433527843939, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.05013135424333051, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.05326053452330198, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06193265306879446, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.07168556401280708, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.07984210559720113, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.09110405042818186, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.09770394816211704, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.11069194519583213, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.12432008279019718, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.14179515207499416, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.15138718966204026, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1607070658592809, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17075595331578025, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18815216391641196, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2413385678497439, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.3203600185771088, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.38818562371381643, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.4683182234871165, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.6359661808818233, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.7306209375227579, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.7945333260016225, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.8531023987143316, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.8780220664506634, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.8875273049415178, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.8956098050507402, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9002329222765046, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9055688343008884, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9107826186693077, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 1.7731484222412108, "validation/loss_best": 0.6676458120346069, "validation/acc_best": 0.9181547619047619, "validation/f1_best": 0.9107826186693077} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 2.204389504790306, "train/grad": 0.08862096609547734, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.024224853515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.022740478515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.020291748046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.017938232421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.015506591796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.01216796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.008270263671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.0039892578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.99830078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.9921435546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.98598876953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.97658935546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.967401123046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.95377685546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.940289306640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.926998291015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.909617919921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.888321533203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.86344970703125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.838994140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.807578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.77333984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.7330029296875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.6872705078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.6368560791015625, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5730389404296874, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.512615966796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.45520263671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.373887634277344, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.273265686035156, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.180597839355469, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.094606628417969, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9768716430664062, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.8712020874023438, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.7460162353515625, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.623260726928711, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.4945327758789062, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.3755587005615235, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.251378860473633, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.1061360549926758, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.0017750549316407, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.9166991996765137, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.8148913192749023, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.7356605434417725, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.6539989757537842, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.5779401350021363, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.5209046268463134, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.4617321491241455, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.4182649374008179, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016673397719860077, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016658384455367922, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01663521891925484, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.016613387055695056, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.016590431164950133, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01655922507867217, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01652332971803844, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.016481469380669297, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.016426662425510587, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0163677541911602, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.016309987935237587, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.016220552097074688, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01613228534348309, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01600215715356171, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01587421210948378, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.015747877205722034, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.015585194965824485, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01538668834604323, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.015154273742809891, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.014929285752587021, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.014640999287366866, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01433198337443173, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.013974174587056042, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01357868649996817, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.013160420190542936, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.012655292171984911, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.012210195264779032, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01181783678010106, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011311904760077596, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01075830617453903, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01030758155276999, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00992885509505868, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009455657901708037, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009063427117653192, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008624098431318998, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008208123606164009, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.007777326107025147, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.007376746169757098, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.006951026825699955, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0064369540533516555, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0060560221166815606, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.005736337518319487, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.005343663686653599, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.005029762415215373, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.004699503503507003, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.004386938877869398, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.004147078790701926, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0038967359019443392, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0037108304601861162, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.015463352203369, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.0129220485687256, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.0087318420410156, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.0044989585876465, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.000354051589966, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.994539260864258, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9878993034362793, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.9805614948272705, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.9707486629486084, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.960344076156616, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.9499356746673584, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.9342286586761475, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.918761730194092, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.895970106124878, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8736655712127686, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8517792224884033, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.8233580589294434, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7888875007629395, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.748903274536133, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7104363441467285, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.661097288131714, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6080448627471924, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5464558601379395, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.477562427520752, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4026923179626465, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.3092963695526123, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.222241163253784, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.1406912803649902, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.0271918773651123, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.8906604051589966, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.7687923908233643, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.6600093841552734, "validation/loss_032_lr3.7e+00_wd1.0e+00": 1.5178840160369873, "validation/loss_033_lr4.3e+00_wd1.0e+00": 1.396990418434143, "validation/loss_034_lr5.1e+00_wd1.0e+00": 1.2623093128204346, "validation/loss_035_lr6.0e+00_wd1.0e+00": 1.1390610933303833, "validation/loss_036_lr7.1e+00_wd1.0e+00": 1.0182397365570068, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.9136542081832886, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.8113508224487305, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.6998937726020813, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.624625027179718, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.5663633346557617, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.50050950050354, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.4517189860343933, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.40390560030937195, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.36132723093032837, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.33084243535995483, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.3009772002696991, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.280698299407959, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.09573412698412699, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.10069444444444445, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.10838293650793651, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.11532738095238096, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.12351190476190477, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.13814484126984128, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.15823412698412698, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.17708333333333334, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.19915674603174602, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.21825396825396826, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2269345238095238, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.23239087301587302, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.23313492063492064, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2326388888888889, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2371031746031746, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.23958333333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.24479166666666666, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2482638888888889, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2517361111111111, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2571924603174603, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2698412698412698, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.28422619047619047, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.30654761904761907, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.3246527777777778, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.3420138888888889, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.3638392857142857, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.3943452380952381, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.4402281746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.5188492063492064, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.5910218253968254, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.6416170634920635, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.6979166666666666, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.7663690476190477, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.8142361111111112, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.8606150793650794, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.8809523809523809, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.8998015873015873, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9045138888888888, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9084821428571429, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9144345238095238, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9193948412698413, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9203869047619048, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9243551587301587, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9288194444444444, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9293154761904762, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9310515873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9332837301587301, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9370039682539683, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9370039682539683, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.028790615559704497, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.03019472306520834, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.031357938712716756, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.032985451681858124, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.035061789049123104, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.03888081568866944, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.04236533926808966, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.04570684044079633, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0485059535751959, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.05052807177408549, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.050823979374562456, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.05065622524031891, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.05066474775643272, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.05294848933831188, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06072241519434211, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06612677439703293, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07629187490287376, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08352824511921184, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.09127023329545743, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.09821710128774098, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.11194299056366612, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.12323474300966698, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.13718842374397405, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.14683792949286856, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15735545552990812, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.17577079291675737, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21411150527019554, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.27252104670831095, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.3575387335524073, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.4332538679446579, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.52142737737322, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.6355702579280806, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.7452043978670139, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.8118551802346274, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.8572199448354961, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.8739253736497244, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.8916204785858458, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.8964048738428768, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9022850607927118, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9080551264492759, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9129644344983987, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9138283769694856, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9190379987051726, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9229257008329764, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9248675035129643, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9266220086951136, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.928827701053593, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9325677598521303, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9332756210536324, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.4617321491241455, "validation/loss_best": 0.3009772002696991, "validation/acc_best": 0.9370039682539683, "validation/f1_best": 0.9325677598521303} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 1.8492593258619308, "train/grad": 0.07789801387116313, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.007213134765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.00331787109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.996622314453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.990218505859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.983709716796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.974691162109375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.964415283203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.953101806640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.938187255859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.92232177734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.906689453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.8830615234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.86005859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.82653564453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.793948974609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.762442626953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7219482421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6733978271484373, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.61780517578125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.565008544921875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4981207275390624, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.426947021484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.34544921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.2554766845703127, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.159114990234375, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0414999389648436, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9344912719726564, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.837102813720703, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.7066525268554686, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.5575559997558595, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.4315304565429687, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.3242525482177734, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.1907468414306641, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.0825697326660155, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.9667332458496094, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.8647173309326172, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.7682427978515625, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.6873476028442382, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.6106692981719971, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.5295516967773437, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.4764512777328491, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.4360064506530762, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.3908497428894043, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.35771790742874143, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.3251910543441772, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.29619776606559756, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.2751600342988968, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.25398138344287874, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.23868510037660598, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016444895598106087, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016407879278995098, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016344527304172515, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.016281855320557953, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.016219188598915933, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.016130291004665197, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.016032428229227663, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01592336299829185, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015781092327088117, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.015629569934681058, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.015480709681287407, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.015259812856093048, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.015043965191580355, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01473012251779437, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.014429291328415274, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.014141960646957158, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01377602422144264, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.013348827729932964, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012879504538141191, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.012453372660093009, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011945237824693321, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011452337014488875, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010947957006283104, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010460598475765437, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010008621795568615, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00953049419214949, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009144472868647426, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008817117237485945, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008397075009997933, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007922710236161947, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007517824647948146, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007165347256232053, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.006714607730973512, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.006335496089886874, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.005914399217581376, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.005528211690252647, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.005146742375800386, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.004814558898797259, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.004487037671497092, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.004129138912539929, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0038885863206814973, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.003701484843622893, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.003489200146868825, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.003327898128191009, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0031723283923929557, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0030421981017570944, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002961402838700451, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0029035972646670417, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002871219342923723, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.994401454925537, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9887750148773193, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9795475006103516, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.9703493118286133, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.96128249168396, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.9486589431762695, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.9344990253448486, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.918762683868408, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.898175001144409, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.8763532638549805, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.85493803024292, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.822843074798584, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.7917072772979736, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.746760845184326, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.7035701274871826, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.662043809890747, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.608994245529175, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.5460638999938965, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.4746224880218506, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.4072389602661133, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.322700023651123, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.233891725540161, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.132840156555176, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.022940158843994, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.9073179960250854, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.7695859670639038, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.6482599973678589, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.5413011312484741, "validation/loss_028_lr1.9e+00_wd1.0e+00": 1.4034433364868164, "validation/loss_029_lr2.3e+00_wd1.0e+00": 1.253235101699829, "validation/loss_030_lr2.7e+00_wd1.0e+00": 1.132189393043518, "validation/loss_031_lr3.1e+00_wd1.0e+00": 1.0331453084945679, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.914380669593811, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.8215340971946716, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.7259210348129272, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.6443254947662354, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.5696489214897156, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.5090564489364624, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.4532000720500946, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.39578863978385925, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.3594374358654022, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.33236491680145264, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.30284377932548523, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.28156813979148865, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.26024869084358215, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.24109609425067902, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.2273848056793213, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.2135831117630005, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.20243750512599945, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.13938492063492064, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.15426587301587302, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.17981150793650794, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.20014880952380953, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.21825396825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.22991071428571427, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2333829365079365, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.23412698412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.23462301587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.24032738095238096, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.24404761904761904, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.24925595238095238, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.25297619047619047, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.2591765873015873, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.2646329365079365, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.27356150793650796, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2867063492063492, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3087797619047619, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.32663690476190477, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.3420138888888889, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.35912698412698413, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.38318452380952384, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.43874007936507936, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.5161210317460317, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.5855654761904762, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.6498015873015873, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.7204861111111112, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.7782738095238095, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.8405257936507936, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.876984126984127, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.8918650793650794, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.8993055555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9069940476190477, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9122023809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9193948412698413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9208829365079365, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9248511904761905, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9265873015873016, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9288194444444444, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9310515873015873, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.933531746031746, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9340277777777778, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9365079365079365, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9377480158730159, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9397321428571429, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9427083333333334, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9451884920634921, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9456845238095238, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9489087301587301, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.040182368834044246, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.042789104525183606, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.04653017932897719, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.04921035404420119, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.051579228624471916, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05287620149334128, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.05292944172160922, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0533769420946977, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.05593088461753585, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.06511261217870441, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.07079061021651044, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.07999963004444591, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.08854498035000552, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.09657726898720694, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.10219567114774916, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10964222744862706, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11888206490397939, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13220074839452026, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14012208929786882, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.14927873894834007, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.16036740392868665, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1887496430660729, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.26500013440519626, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.34780115754225643, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.4279427849228414, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.534808678406173, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.6637796740132952, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.7571353377533562, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8350775885918783, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.8736766788488131, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.8857851950606597, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.8933115436769822, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9011912305905354, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9049355928072584, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9114443915794302, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9128160182141668, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9175482993028455, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9201802057386207, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9236103748374846, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9261028989973082, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9288764544316909, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9298032830433571, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9319995484764414, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9330116684533414, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9349609682204785, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9395546809494003, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9416718854907251, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9429050803098608, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9458076760469115, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.23868510037660598, "validation/loss_best": 0.20243750512599945, "validation/acc_best": 0.9489087301587301, "validation/f1_best": 0.9458076760469115} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 1.6082194292545318, "train/grad": 0.07157001741230488, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.9814892578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9739306640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.96137939453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.949163818359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.937061767578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.920296630859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.901539306640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.880823974609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.853876953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.82543701171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.79774169921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.756673583984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.7170343017578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.660352783203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.606390380859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.5548602294921876, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.489564208984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.41257568359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.3260113525390627, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.245176086425781, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.144673156738281, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.040450439453125, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.9242257690429687, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.8008848571777343, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.6750465393066407, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.5304934692382812, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.4080097961425782, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.3034455108642578, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.1729429626464845, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.0358693313598633, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.9288396835327148, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.8432097244262695, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.743243751525879, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.6668920516967773, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.5897888088226318, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.5254257774353027, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.46753668308258056, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.42113778114318845, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.37867960691452024, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.335202066898346, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.3073316812515259, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.2863714861869812, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.26287566125392914, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.24552079021930695, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.22830422818660737, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.21280069261789322, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.20143678426742553, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.18969785571098327, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.18103769555687904, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.016419630544260145, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.016345880869776012, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.016226374944671988, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.016109242718666792, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.015993353803642096, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.015835283352062107, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.015657509798184036, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.015464437459595502, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.015214019417762757, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.014949357700534165, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.014692055811174214, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.014315314134582877, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.013958477084524929, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.013460696013644337, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013005558704026043, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.012587853665463626, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012091447482816875, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.011554265385493636, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011017513577826321, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010578146716579796, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010105954713653774, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009680956578813493, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009259139548521488, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008842309340834617, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008432605240959673, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007962970577646047, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007559582679532468, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.007206345121376217, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0067539612436667085, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.006258508472237736, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.005854450147598982, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.005519652306102216, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00511014872812666, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0047836469183675945, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.004438806324033067, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.004138487639138475, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.003857233353191987, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.003625446141231805, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0034107416984625162, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.003191249272786081, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0030524180282372982, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0029513694561319427, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0028388627874664962, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0027603505877777934, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002689679848845117, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.002647814096999355, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002633987033041194, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0026186744606820868, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0025863770203432067, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9655911922454834, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.9559731483459473, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.9400689601898193, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.924391031265259, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.9089908599853516, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8878173828125, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.8641068935394287, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.8381385803222656, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.80436110496521, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.769073009490967, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.7349157333374023, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.6843719482421875, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.636087417602539, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.5673601627349854, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.502509832382202, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.44096040725708, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.3635036945343018, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.2728755474090576, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.1719679832458496, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.0783209800720215, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.9634734392166138, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.846293330192566, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.7186850309371948, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.5868661403656006, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.4564143419265747, "validation/loss_025_lr1.2e+00_wd1.0e+00": 1.311504602432251, "validation/loss_026_lr1.4e+00_wd1.0e+00": 1.1926767826080322, "validation/loss_027_lr1.6e+00_wd1.0e+00": 1.0939021110534668, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.9739598631858826, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.8512989282608032, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.7582147717475891, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.6852825880050659, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.6019306778907776, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.539758563041687, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.47825294733047485, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.4279475808143616, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.38319092988967896, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.34796956181526184, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.3160206079483032, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2839560806751251, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.2637266218662262, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.24846608936786652, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.2314475178718567, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.21893152594566345, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.20688141882419586, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.19646941125392914, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.18930545449256897, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.18215784430503845, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1772584468126297, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.21006944444444445, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.22470238095238096, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2326388888888889, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.234375, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.23387896825396826, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2353670634920635, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.23859126984126985, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.24231150793650794, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2465277777777778, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2482638888888889, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.25297619047619047, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.26264880952380953, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.2740575396825397, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.29811507936507936, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.31919642857142855, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.33283730158730157, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.34970238095238093, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.3695436507936508, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.40773809523809523, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.4677579365079365, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.5434027777777778, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.6034226190476191, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.6622023809523809, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.7361111111111112, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8005952380952381, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.8544146825396826, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.8829365079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.8933531746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9047619047619048, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9124503968253969, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9159226190476191, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9191468253968254, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9228670634920635, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9248511904761905, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9300595238095238, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9315476190476191, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.933531746031746, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9387400793650794, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9407242063492064, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9432043650793651, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9449404761904762, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9466765873015873, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9486607142857143, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9503968253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9523809523809523, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9528769841269841, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9538690476190477, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9546130952380952, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.04976391719536897, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.051924653599603916, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05236707832686087, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.05310445874311448, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.053683225379936535, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.05842805862642085, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.06522857753621115, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.07331146619158718, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.08210014585819658, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.08787631011976435, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.09452260367617028, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.10483615115192074, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.11475218240415633, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.13115861185146635, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.14193028844962163, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.14948949341388634, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.15849516794460808, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.17533994004791628, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.22422561704295077, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.29660747737826804, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.37761658887959687, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.4561967494659926, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.5598395789511373, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.6977457023712242, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.7854585008059237, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8504901739689921, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.8785891302214603, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.8873136314974185, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.8980957124166405, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9063825066862998, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.909805537240335, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9125600530719521, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.915287732097781, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9174662896860923, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9235232237199726, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9255434195665816, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9278649682519405, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9293804229026564, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9327029409224364, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.934694913550532, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9368693021098183, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9386591012500961, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9401473351453598, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9413918022625719, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9416528500839246, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9448122534174672, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9447160614413315, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9462757000458081, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9474776832214941, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.18103769555687904, "validation/loss_best": 0.1772584468126297, "validation/acc_best": 0.9546130952380952, "validation/f1_best": 0.9474776832214941} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 1.4273562067747116, "train/grad": 0.0645629140175879, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.94944091796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.9373583984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.917593994140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.89822998046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.879241943359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.853214111328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.8242578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.7926416015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.751934814453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.709481201171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.668748779296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.6088409423828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.5519122314453124, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.4715362548828126, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.3961279296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.32509033203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.2360247802734374, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.132760314941406, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.019026794433594, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.9151956176757812, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.7900845336914062, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.6655476379394532, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.5333981323242187, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.4008377075195313, "train/loss_024_lr1.0e+00_wd1.0e+00": 1.273150634765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 1.1352742004394532, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.0249490356445312, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.9349887847900391, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.827780990600586, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.7205313110351562, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.6406171607971192, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.5789564704895019, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.5095558547973633, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.4583825826644897, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.40803047180175783, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.3670735669136047, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.33092143297195437, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.30223153710365297, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.27599738001823426, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.24907176434993744, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.23170590937137603, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.21846848219633103, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.20343001559376717, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1924467997252941, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.18160583943128586, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.17181153185665607, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.16481050238013267, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.15772118784487246, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.1524152807146311, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015885387798771262, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015767955319024623, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015579401911236346, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.015396376615390181, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01521739900112152, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014975121840834618, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014703843705356122, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.014409136455506087, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.014033241881988942, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.013653506357222796, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.013295221580192447, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012785353744402529, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012324856114573776, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011720409756526351, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01120868418365717, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010776032763533294, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010303486362099648, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009836194082163274, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009396322795655578, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009034038602840156, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008626888021826744, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008231833388563245, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007812488847412169, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00738376269582659, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006959240208379925, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.006485641796607524, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0060919459816068415, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.005759224937064573, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0053455362934619185, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004912607677979395, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.004574564006179571, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.004304163185879588, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00399027575389482, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0037531642301473767, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0035160865797661243, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003321636797627434, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0031505153910256923, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0030162289121653885, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002892748818267137, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0027714934147661553, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0026912108535179866, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0026295061450218784, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002564092308166437, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0025289788394002245, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0025116614962462334, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0025140420615207405, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0025352731463499367, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.002574234568164684, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0025790969759691505, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.9299724102020264, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.915404796600342, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8917157649993896, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8684465885162354, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.845789909362793, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.8148162364959717, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.7805495262145996, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.7433083057403564, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.6955366134643555, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.646056652069092, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.5986545085906982, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.529418468475342, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.464053153991699, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.3719921112060547, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.2862327098846436, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.2058169841766357, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.1057896614074707, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.9908685684204102, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.8660759925842285, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.7539414167404175, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.6218273639678955, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.4934988021850586, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.360672116279602, "validation/loss_023_lr8.5e-01_wd1.0e+00": 1.2311387062072754, "validation/loss_024_lr1.0e+00_wd1.0e+00": 1.1093156337738037, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.9809021353721619, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.8803892135620117, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.799720287322998, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.7052106857299805, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.6126251816749573, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.5447419285774231, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.49335619807243347, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.43592438101768494, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.39413437247276306, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.35365378856658936, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.320913165807724, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.29206135869026184, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.2695327699184418, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.2488943636417389, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.2277895212173462, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.21430939435958862, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.20417922735214233, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1927231103181839, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1843225359916687, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1763802468776703, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.16959230601787567, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.16586606204509735, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.16339793801307678, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.16005751490592957, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.23412698412698413, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.23313492063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.23660714285714285, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.23834325396825398, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2435515873015873, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.24677579365079366, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2517361111111111, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.25669642857142855, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.2666170634920635, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.2777777777777778, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.2914186507936508, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.3162202380952381, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3325892857142857, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.35466269841269843, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.37351190476190477, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.40500992063492064, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.47197420634920634, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.5443948412698413, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.6051587301587301, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.6557539682539683, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.7301587301587301, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.7976190476190477, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8484623015873016, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.876984126984127, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.8928571428571429, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9030257936507936, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9072420634920635, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9117063492063492, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9181547619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9228670634920635, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9255952380952381, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9270833333333334, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9295634920634921, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9308035714285714, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9379960317460317, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9402281746031746, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9409722222222222, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9429563492063492, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9476686507936508, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9518849206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.953125, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9541170634920635, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9541170634920635, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9548611111111112, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9533730158730159, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9499007936507936, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9513888888888888, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.052063672510335, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.05177074144876983, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.05796268152265359, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0631159095718214, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.07079915382964169, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0786575236220594, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.08650143626630033, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.09415016139680037, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.10548044359319564, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.11594583198822539, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.1262423428780904, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.14065619866439671, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.1499056099486856, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.1615400874819953, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.18151846436868077, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.21974468204213315, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.3021761453570588, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.3752841201981548, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.45251545462568155, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.5456460446977963, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.6800267335857497, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.7743095497634551, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8371002245597878, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.8688713555260937, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.8832853319989311, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.8937042334620102, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.898797132297708, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9050054260540761, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9120628948484738, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9174085558916518, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9200195660349457, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9215001628307776, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9245408688201899, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9273737501800539, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.931174258642403, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9341582645404978, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9356501818352291, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9370911706139005, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9387346316164114, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9446387284525589, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9479647128744306, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9488330175626903, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9496555521446469, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9502471344128536, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9500230762212183, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9508887894754801, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9494773853306535, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9465583053729318, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9472702159295088, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.17181153185665607, "validation/loss_best": 0.16959230601787567, "validation/acc_best": 0.9548611111111112, "validation/f1_best": 0.9508887894754801} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 1.2957709044218064, "train/grad": 0.06058940721675753, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.913487548828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.896513671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.868966064453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.842059326171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.8158642578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.78033447265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.741094970703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.69853271484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.6444256591796873, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.5884979248046873, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.5352838134765623, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.4577679443359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.38485107421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.2827166748046874, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.188143615722656, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.0999676513671877, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.9911721801757813, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.8678582763671876, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.7364773559570312, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.6205851745605468, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.4868450927734376, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.3596437072753906, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.2309503173828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 1.1075142669677733, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.993628044128418, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.8756318664550782, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.7846152114868165, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.7125471305847167, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.6291021347045899, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.5483652305603027, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.4899601936340332, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.4457441854476929, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.396774525642395, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.36120019912719725, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.3263933801651001, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2980855989456177, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.27297001361846923, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2528756421804428, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.2342309209704399, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.214886617064476, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.20220358341932296, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.19247173324227332, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.18144223272800444, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.17328354135155677, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.1651484501361847, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1579292221367359, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.15283420983701945, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.1476410322263837, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.14325743675231933, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.015660920329391956, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015502230837009847, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.015243669603951276, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014995198915712535, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014749011164531112, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.014416729523800314, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.014059202834032477, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.013683068542741239, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01321234053466469, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01274563102517277, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.01232474600430578, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011754750763066113, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011268357848748564, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01067463323008269, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01020924086915329, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00983184464275837, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009418802866712213, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008993144826963544, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008557758938986809, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00818010039627552, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007739595919847488, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0073117361636832355, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006866255144122988, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.006426171131897718, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.006005669680889696, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.005551700621144846, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.005186530731152743, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0048872445791494105, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.004528750033350661, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.004170266321161762, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003903465517796576, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0036983217007946225, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0034693989425431935, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.003300080761546269, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.003135412986157462, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.003001110074110329, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002882692392449826, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002788036621059291, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0027006192377302795, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00261332182737533, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.002555341031984426, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0025135613180464135, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0024707385041983798, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0024533270573010666, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0024537534260889514, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0024800954316742717, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0025096885091625155, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0025024412415223197, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002429385143623222, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.891897439956665, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8723981380462646, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.8406641483306885, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.8098745346069336, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.779996871948242, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.7395782470703125, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6951003074645996, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.6471385955810547, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.586214780807495, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.5237488746643066, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.464385747909546, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.378261089324951, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.297672986984253, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.1853976249694824, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.0820627212524414, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.9864661693572998, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.8698983192443848, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.7396005392074585, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.603058934211731, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.4847960472106934, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.350846767425537, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.2258678674697876, "validation/loss_022_lr7.2e-01_wd1.0e+00": 1.1015013456344604, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.9843398332595825, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.8778020739555359, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.7689883708953857, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.6864498853683472, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.6216930747032166, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.547844409942627, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.4775192439556122, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.4272206127643585, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.3895905017852783, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.34831494092941284, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.3184530436992645, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.2898962199687958, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.26678383350372314, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.2465672641992569, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.23048101365566254, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.21610383689403534, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.20175161957740784, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.19269412755966187, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.185775026679039, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.17714478075504303, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1704014092683792, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.16423402726650238, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.15910062193870544, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.15559248626232147, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.15273235738277435, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.15090623497962952, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.23685515873015872, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.23759920634920634, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.24479166666666666, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.24975198412698413, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.25223214285714285, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2586805555555556, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.267609126984127, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.28174603174603174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.30009920634920634, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3209325396825397, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.33482142857142855, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.35441468253968256, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.3705357142857143, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.41393849206349204, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.48487103174603174, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.5471230158730159, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.605406746031746, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.6644345238095238, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.7408234126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.7951388888888888, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8497023809523809, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.8784722222222222, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.8943452380952381, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9069940476190477, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9129464285714286, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9169146825396826, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9208829365079365, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9246031746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9268353174603174, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9303075396825397, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9305555555555556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9337797619047619, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9375, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9419642857142857, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9444444444444444, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9486607142857143, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9489087301587301, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9528769841269841, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9518849206349206, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9518849206349206, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9538690476190477, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9546130952380952, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9543650793650794, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.05777360816326092, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.06179461228482818, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.07268735249268576, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.08211273603640679, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0869023130138366, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.09626115808208628, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.10665711626276037, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.12001092152041284, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.13240531173651748, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.14318820032839524, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.15070228282021006, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.16103619385079837, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.17600393977075737, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.23258592269677397, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.3150942265553565, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.38060640670361195, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.45037775030996224, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.5581743343403048, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.7026682396733432, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.7766795363017187, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8465918102641231, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.8757928212097925, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.8899783683259637, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9016323171691363, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9078734794995669, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9118131112023826, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9152940427629377, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9176430095510627, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9204907185618227, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.92481529097145, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9260076614821122, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9304534266137621, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9336077536533578, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9361238625984796, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9384006484311781, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9410543889992227, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9434724418525694, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9450688008011285, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.945505836280215, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.949454134713874, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9487578075080163, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9487464316978207, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9505374681440552, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9514187015612214, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.952875953916608, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9517804790519271, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9518494156489701, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.949121672570533, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9487195832926723, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 0.1579292221367359, "validation/loss_best": 0.15910062193870544, "validation/acc_best": 0.9565972222222222, "validation/f1_best": 0.9517804790519271} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 1.1878602808713914, "train/grad": 0.056667435839772226, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.874212646484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.85245849609375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.817081298828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.782938232421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.749881591796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.70512451171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.656326904296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.603731689453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.5372509765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.4691436767578123, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.4046868896484375, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.311607666015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.224676513671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 2.1043655395507814, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.9944009399414062, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.8935781860351562, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.7718002319335937, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.637742919921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.4994264221191407, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.3816038513183593, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.2499122619628906, "train/loss_021_lr6.1e-01_wd1.0e+00": 1.12900634765625, "train/loss_022_lr7.2e-01_wd1.0e+00": 1.0102313232421876, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.8995758056640625, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.800290756225586, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.6999392509460449, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.6245494079589844, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.5660779762268067, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.4996295642852783, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.4367631435394287, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.3919298434257507, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.3583696985244751, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.32144139766693114, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.29461172699928284, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.26839113116264346, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.24699192732572556, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.22775179475545884, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.2123749829828739, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1981102278828621, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.18304027207195758, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.17308528542518617, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.16540063425898552, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1566443357616663, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.15005474142730235, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.14352411668747664, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.13761618122458458, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.133243213519454, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.12882128819823266, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.12573729993775487, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01525837245862931, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.015057944636791944, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014728491771966218, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.014409976215101778, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.014106061207130552, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.0137100834492594, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.013284174045547843, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012837677095085383, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012308468334376812, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011804807079024614, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011364636910147965, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01080234054941684, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010353347309865058, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009831355325877667, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00942221567966044, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009081016508862377, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008688290736172348, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008262361397501082, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007818315660115331, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.007430045532528311, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006982863419689238, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.006557558493223041, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.006121084096375853, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.005697336337761954, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0052981781598646195, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004875609402079135, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00454427304212004, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.004278268128400669, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003964433936635032, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0036599095608107744, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.003436504801502451, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0032688388321548702, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.003080244845477864, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0029448687052354215, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0028123671264620497, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0027053282916313036, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002606918893288821, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002530219038017094, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002456653471454047, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.002381679814425297, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0023350856988690796, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0023000630509341135, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0022621629829518495, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0022317549749277534, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.002208449928148184, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0021932212586398235, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0021844446018803865, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.002184842086280696, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002196941235451959, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8558685779571533, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.8317928314208984, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7929491996765137, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7554399967193604, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.7191274166107178, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6703598499298096, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.6170971393585205, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.5600645542144775, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.4881160259246826, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.41473650932312, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.3453528881073, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.245492458343506, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.1526849269866943, "validation/loss_013_lr1.7e-01_wd1.0e+00": 2.024874210357666, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.9089943170547485, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.8036348819732666, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.677983283996582, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.5414773225784302, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.4026515483856201, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.2860714197158813, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.1575738191604614, "validation/loss_021_lr6.1e-01_wd1.0e+00": 1.0410292148590088, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.9277992248535156, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.823411762714386, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.7307784557342529, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.6382260322570801, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.5693930983543396, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.5164925456047058, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.4569370746612549, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.4010316729545593, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3614901006221771, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.33214694261550903, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.30013105273246765, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2769181728363037, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.25444164872169495, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.23621539771556854, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.22022204101085663, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.20735515654087067, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.19571727514266968, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.18376199901103973, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.17612093687057495, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.17022204399108887, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.16351467370986938, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1586599200963974, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1534845381975174, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.14852891862392426, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.14578263461589813, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.14374102652072906, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.14190362393856049, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.24057539682539683, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2465277777777778, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.25024801587301587, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2591765873015873, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2619047619047619, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.27356150793650796, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.2881944444444444, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3072916666666667, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.32762896825396826, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.3454861111111111, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.3586309523809524, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.3871527777777778, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.435515873015873, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5238095238095238, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.5840773809523809, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.636656746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.6986607142857143, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.7752976190476191, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8358134920634921, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8715277777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.8936011904761905, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9047619047619048, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9104662698412699, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9159226190476191, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9206349206349206, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.925843253968254, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9275793650793651, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9290674603174603, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9308035714285714, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9325396825396826, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9360119047619048, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9384920634920635, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9422123015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9439484126984127, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9533730158730159, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.955109126984127, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9563492063492064, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.957093253968254, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9580853174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.06659510621703325, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.07585649942037725, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.08390306787413263, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.09454553688829723, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0997746683898475, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.11312398852221696, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.12447876277097687, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.1368067539720238, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.1476249968174152, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.15837681912251078, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.16477404338563625, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.195846908098332, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.2601716878975952, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.3542629102282917, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.42211411799234644, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.5094445292622849, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.625567479408171, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.7532975363503039, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8331574303407627, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8710244588691206, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.8900294838976203, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9010480055685173, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9041912620885248, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9103289302387704, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9155674380493327, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9189523337021692, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9203617982536284, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.922197950535977, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9260670510023955, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.928258221701096, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9320236829554841, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9339219274372367, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.937973132658604, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9399844897544982, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9429887698898589, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9458696256990577, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9492347097463382, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9514844012740475, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.951091184251265, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9524334939194564, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9527027211300941, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9532981973320117, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9523237895770458, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9523613899234269, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9532373556664084, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9542895136154405, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9537252251373793, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9535907356287439, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9533241629610568, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.133243213519454, "validation/loss_best": 0.14578263461589813, "validation/acc_best": 0.9588293650793651, "validation/f1_best": 0.9537252251373793} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 1.1160941755771636, "train/grad": 0.05355077490210533, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.839920654296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.81392333984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.771788330078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.731361083984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.692261962890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.639947509765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.583031005859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.5220281982421877, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.44529296875, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.3672796630859376, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.293731689453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.1882122802734374, "train/loss_012_lr1.4e-01_wd1.0e+00": 2.0905828857421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.9569137573242188, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.83686279296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.72879638671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.6011332702636718, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.4641204833984376, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.3268032836914063, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.2128031158447266, "train/loss_020_lr5.2e-01_wd1.0e+00": 1.0884868621826171, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.9769224548339843, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.8695265579223633, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.7716511917114258, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.6854167747497558, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5999777793884278, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.5368377685546875, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.4884358596801758, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.43407577991485596, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.3829947090148926, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.34672568321228026, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.3196292996406555, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.2897026193141937, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.2678196811676025, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.24631572723388673, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.2285878700017929, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.21258843451738357, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.199559063911438, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.18732208952307702, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.17437505424022676, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.16570527464151383, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.15891702264547347, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.15111199609935283, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.14513555742800235, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.13920183062553407, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.1338431342691183, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.1300076062977314, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.12640040945261716, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.12454704262316227, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014858990306966007, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014614698602817952, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.014219410764053465, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013850563848391175, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01350600176025182, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.013048744383268059, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0125690300995484, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012089888560585677, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01153057602699846, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01101731945760548, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010592476911842823, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010073349974118174, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009668364650569855, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009190350982826202, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0088003333308734, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008460796282161027, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008062176269013434, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00762833354761824, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007180507387965917, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006796549111604691, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.006361941345967352, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005954617450479418, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005543500783387572, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00515064007602632, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004787008769344538, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004408079880522564, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.004117315539624542, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0038870145322289318, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0036223549058195205, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0033705247566103934, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0031898639170685784, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.003054617139860056, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002903405640390702, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002794006674084812, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002686258213943802, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0025952773314202203, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00251519457786344, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002444254988222383, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002380217919126153, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0023139002663083376, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0022715460910694672, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0022364210966043176, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0021954436250962318, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0021662710374221205, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0021454638396971857, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0021400166986859405, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.002152370782860089, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.002202958112175111, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.002286010321113281, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.8225674629211426, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.794419050216675, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7491321563720703, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.7056915760040283, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.664001941680908, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.6079905033111572, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.547236919403076, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.48246693611145, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.401094675064087, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.318458080291748, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.2408297061920166, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.129655361175537, "validation/loss_012_lr1.4e-01_wd1.0e+00": 2.0272457599639893, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.8879793882369995, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.7637484073638916, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.6530365943908691, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.5234858989715576, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.3858824968338013, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.2496140003204346, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.1375012397766113, "validation/loss_020_lr5.2e-01_wd1.0e+00": 1.0163899660110474, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.9085832238197327, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.8056687116622925, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.7125602960586548, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.6312941908836365, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.5514183044433594, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.49299192428588867, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.44848188757896423, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.39907363057136536, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.3531346917152405, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.3209003806114197, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.29716941714286804, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2713060677051544, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2525496780872345, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.23454955220222473, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.22003096342086792, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.2071390151977539, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.19682684540748596, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1871207356452942, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.17637702822685242, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.16900473833084106, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1633547991514206, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15747123956680298, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1534423530101776, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.14944204688072205, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.14505286514759064, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1417800933122635, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.13895298540592194, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1375056356191635, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.24776785714285715, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.25049603174603174, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2591765873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.26339285714285715, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.27331349206349204, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.2874503968253968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.30927579365079366, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.32787698412698413, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3479662698412698, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.36532738095238093, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.38665674603174605, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.44642857142857145, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5190972222222222, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.5942460317460317, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.654265873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.716765873015873, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.7906746031746031, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8469742063492064, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8816964285714286, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.8953373015873016, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9067460317460317, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9119543650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9156746031746031, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.925843253968254, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9273313492063492, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9295634920634921, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.933531746031746, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9352678571428571, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9370039682539683, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9392361111111112, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9422123015873016, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9466765873015873, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9499007936507936, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9506448412698413, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9516369047619048, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9536210317460317, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9543650793650794, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9553571428571429, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9561011904761905, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9573412698412699, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9610615079365079, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.07793378950904287, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.08395997407844809, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.09485870879066087, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.10154334232852809, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.11152485829778398, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.12351411697943579, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.13771847613090413, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.14746073666402384, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.15958673221500974, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.17126094272823325, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.19655633811582973, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.27422932416266604, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.3502850932829549, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.4374220438986939, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.5427164252536769, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.6579926760389047, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.7732264259033095, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.844951582590957, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8788635204390732, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.8904385329183216, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9015588937416974, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9063478773577118, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9098573806039235, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9157850975126282, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9192121524634468, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9205623373207058, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9232613239969542, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9278597428531496, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9301589452702921, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9328882333314197, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9350141913106511, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9359826621739542, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9375678371271414, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9391135126575059, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9408086324202248, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9423648166984843, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9460861484364038, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9469387676605237, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9472875104171731, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9480962743315773, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.950090875738952, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9504726237811002, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9510050683736375, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9507511245321729, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9521448151995179, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9524796530741098, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9531131673870192, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9544336126325758, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9565120068918932, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.12454704262316227, "validation/loss_best": 0.1375056356191635, "validation/acc_best": 0.9610615079365079, "validation/f1_best": 0.9565120068918932} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 1.0507224121689795, "train/grad": 0.05184268161654473, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.80712158203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.777078857421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.728865966796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.68273193359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.6385113525390627, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.5793182373046877, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.5151617431640627, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.446893310546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.361260986328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.2745135498046873, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.1931719970703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 2.0769778442382814, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.9704287719726563, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.8264321899414062, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.699215087890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.5867579650878907, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.4564479064941407, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.3194992065429687, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.185290298461914, "train/loss_019_lr4.4e-01_wd1.0e+00": 1.0759664154052735, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.9587554550170898, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.8553524780273437, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.7573387908935547, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6693303871154785, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5929474449157714, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.5183097076416016, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.4637858724594116, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.42234333992004397, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3762233304977417, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.3331532168388367, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.3027675461769104, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.2800467014312744, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.2548816335201263, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.23645917892456056, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.21824265956878663, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.20313316196203232, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.18935003787279128, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.17811419755220415, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.16746655926108361, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.15611091166734695, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.14838817924261094, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.14242921829223631, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.13562754169106483, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.13061199322342873, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.12567895159125328, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.12124161202460527, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.11795886293053627, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.11487827314063907, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.11282698018476367, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014689544122666121, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.014409836353734136, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0139718596637249, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.013568594963289797, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.013182460204698146, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01268550822045654, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01218170031439513, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011681916336528956, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011116560795344413, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01061913336161524, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010217299624346197, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009727611229754985, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009338461756706239, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008857244795653968, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008448578440584243, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008088856295216829, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007664933467749506, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.007207961941603571, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006745081720873713, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.006353745448868722, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005918831047601998, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005518057062290609, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.005120308274636045, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004747140187537298, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.004407921099336818, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.004063799133291468, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003803674434311688, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0036028112180065365, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0033764980151318015, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0031645944598130884, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0030146095488453283, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002903498787782155, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0027788154972949995, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0026871493383077904, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0025932584470137955, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002512974065029994, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002434058552607894, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0023685076541732995, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0023012389993527903, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.002233737632050179, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0021911413839552554, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0021624524478102104, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0021367130998987704, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0021313230114174075, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00213840785989305, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0021483479876769707, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0021671094186604023, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0022052376708597875, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0022480648523196577, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.792168140411377, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.760448932647705, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.7095794677734375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.6609764099121094, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.6144323348999023, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.552233934402466, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.485018253326416, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.413539171218872, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.3242075443267822, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.233839273452759, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.1493756771087646, "validation/loss_011_lr1.2e-01_wd1.0e+00": 2.0290563106536865, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.9193298816680908, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.7719135284423828, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.6428356170654297, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.5294713973999023, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.3991692066192627, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.2634679079055786, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.1313520669937134, "validation/loss_019_lr4.4e-01_wd1.0e+00": 1.024490475654602, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.9107486605644226, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.8108430504798889, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.7169312238693237, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.6330108046531677, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5606158971786499, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.49046432971954346, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.43955734372138977, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.4011259973049164, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3584936559200287, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.31886711716651917, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2912551760673523, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.27082154154777527, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2482852041721344, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.23203662037849426, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.2163151353597641, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.2033357173204422, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.19170548021793365, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1824204921722412, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.17381873726844788, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.16510345041751862, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1594751477241516, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.15520597994327545, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.15029625594615936, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1465672105550766, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.14298270642757416, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13971024751663208, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.13762207329273224, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.13633126020431519, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1360887587070465, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2509920634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.25768849206349204, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2638888888888889, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.27331349206349204, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.28596230158730157, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.30679563492063494, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.32589285714285715, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.34226190476190477, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.3611111111111111, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.38591269841269843, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.42683531746031744, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5099206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.5749007936507936, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6453373015873016, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7118055555555556, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.7725694444444444, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8278769841269841, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8683035714285714, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.8923611111111112, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9045138888888888, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9114583333333334, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9156746031746031, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9196428571428571, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9223710317460317, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9260912698412699, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9290674603174603, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9298115079365079, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9325396825396826, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9357638888888888, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9384920634920635, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9422123015873016, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9456845238095238, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9469246031746031, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9499007936507936, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9521329365079365, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9541170634920635, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9565972222222222, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9575892857142857, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9595734126984127, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9573412698412699, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.08439819508040862, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.09271749684961124, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.10125397422118787, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.11157164627292879, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.12235651162002414, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.13642033170996337, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1459293301648225, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.1550399220575088, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.16601460724908962, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.19394977849056333, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.24975097633666876, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.34095778723019604, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4127435465117399, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.529317194145225, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.6569239983870959, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.7535084761939205, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.824154265571588, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8667833401034156, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.8898827306824288, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9009250782788099, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9069952099055456, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9104351002565322, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9144923768045762, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9164046871546335, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9193674069511557, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9232447406776949, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9237623786393505, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9285264640024606, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9318945089430325, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9346553010454665, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9360879483623205, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9387417094826025, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9421983282128352, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9433496627476807, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9458919245727615, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9477719416516405, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9487606730508734, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9500773766921768, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9513747025505085, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9517204797866926, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9516986255921653, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9524945418385865, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9535112821661647, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9538611736350908, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.95360181559158, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9527281881164927, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9520243550139555, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9527306339912055, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9510714008258276, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.12567895159125328, "validation/loss_best": 0.14298270642757416, "validation/acc_best": 0.9595734126984127, "validation/f1_best": 0.95360181559158} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 1.003943801522255, "train/grad": 0.04929643938317895, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.77859130859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.7451416015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6917236328125, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6406781005859377, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.591810302734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.526678466796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.456533203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.381885986328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2887847900390623, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1949273681640626, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.1073260498046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.9832516479492188, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.8705810546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.7204278564453126, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.5899029541015626, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.4762812805175782, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.3467118835449219, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.212876739501953, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.0837433624267578, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.9799779891967774, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.8702031707763672, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.774372444152832, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6847352600097656, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.6050602912902832, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.5365893650054931, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.4703879547119141, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.42227701187133787, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3858291006088257, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.3453139042854309, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.30743420362472534, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.28052146792411803, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.26030903816223144, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.2378397625684738, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.22118141651153564, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.2046528071165085, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.19088103324174882, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.17828851625323294, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.16785119891166686, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.15799914360046385, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.14729463309049606, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1401130848377943, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.13441143825650215, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.12776203729212285, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.1227277484536171, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.11759752973914146, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.11296127684414387, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10967344101518392, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.10653422167524695, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.10460961857810616, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014290271741338074, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013981675445102155, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013504649391397833, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01305496966931969, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012636431399732828, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012113437373191118, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01158675253391266, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01107712286990136, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010522816558368503, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01004974354756996, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009673050602432341, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009212511938530952, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008836624496616423, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008360072383657097, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007951101111248136, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007590793082490563, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.007171017716173083, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006722418919671327, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.006274950678925961, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005900561870075763, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005487840243149549, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.005109065579017624, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0047388050321023915, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00439581441343762, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0040870174451265485, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0037785452511161564, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003547723952215165, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0033700179879087955, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0031700755597557874, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0029788392351474615, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002841256185201928, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0027365262858802452, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002617904494400136, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0025279964867513625, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0024375073838746176, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002359281601384282, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00228737672616262, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0022298479644814505, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002175354743958451, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0021171158499782906, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.002078144117258489, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0020468421297846363, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.002008768249070272, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0019827096723020075, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001955399254220538, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001940775999100879, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0019396678626071662, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0019525150692788883, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00197636478493223, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7652037143707275, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.7303550243377686, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.67467999458313, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.621616840362549, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5709879398345947, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.5035512447357178, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.4308295249938965, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.3537845611572266, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.257744550704956, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.1610100269317627, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.070812702178955, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.9434025287628174, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.8282407522201538, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.6755435466766357, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.543612003326416, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.4295451641082764, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.300067663192749, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.1674236059188843, "validation/loss_018_lr3.8e-01_wd1.0e+00": 1.0398821830749512, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.9381322860717773, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.8308562636375427, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.7378116250038147, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6511232852935791, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5746355652809143, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.5093543529510498, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.4464873969554901, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.4013005197048187, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3673025071620941, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3297969400882721, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.29509708285331726, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2708216905593872, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2526964545249939, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.23282364010810852, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.21855269372463226, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.20455050468444824, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1932598203420639, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.18323998153209686, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.17509841918945312, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.16762419044971466, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1600240021944046, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15506592392921448, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1510990709066391, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1467217355966568, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1437297910451889, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.14109623432159424, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13933315873146057, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.13831976056098938, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.13825184106826782, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1381339728832245, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2562003968253968, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2594246031746032, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2708333333333333, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2819940476190476, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.2993551587301587, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3209325396825397, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.33705357142857145, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.35441468253968256, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.376984126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4166666666666667, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.47842261904761907, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5607638888888888, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6207837301587301, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.6934523809523809, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.7681051587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8201884920634921, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8638392857142857, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8901289682539683, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9050099206349206, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.910218253968254, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9146825396825397, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9203869047619048, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9236111111111112, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9270833333333334, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9300595238095238, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9327876984126984, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9332837301587301, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9345238095238095, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9397321428571429, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9417162698412699, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9459325396825397, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9486607142857143, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9508928571428571, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.957093253968254, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9568452380952381, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9580853174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.09103212724746917, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.09672497493195613, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.10957826901629315, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.11873846871024323, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.13109042982971686, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14273986206049527, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.15230752453018676, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.1602841973457783, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.18361435762392592, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.23657608394002805, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.3096096601565354, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.3967825673749338, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.4804091976145898, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6174153679009177, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7473013440145643, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8145186838975034, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8630528038593172, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8880939842301538, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.900868233229453, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9052273254441736, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9092983036157527, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9144501466538615, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9169983147114654, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9209050748433014, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9238953400049796, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9277105996603661, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9286735890339896, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9304715860369532, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9361798184228745, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9381234072995832, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9401662212593717, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9423648348848684, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.944815528563942, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9473666609497859, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9483919507907901, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9507470455304514, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9513682565397972, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9529290719419007, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9527446457078087, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9525398442532926, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9549385216153189, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9550413208616352, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9560584951151702, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9578669697121525, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.956994395081729, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.954872329553425, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9551873917600124, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9548507707725481, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9537453248645694, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.1227277484536171, "validation/loss_best": 0.1437297910451889, "validation/acc_best": 0.9613095238095238, "validation/f1_best": 0.9578669697121525} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 0.9673196545243263, "train/grad": 0.04825516508892178, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.754962158203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.718824462890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.661175537109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.6063568115234377, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.55409912109375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.4845562744140626, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.4096612548828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.330301513671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.2314935302734376, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.1321231079101564, "train/loss_010_lr1.0e-01_wd1.0e+00": 2.039587097167969, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.9092257690429688, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.79181640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.6370454406738282, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.5044282531738282, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.3903033447265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.2616780090332032, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.1305245971679687, "train/loss_018_lr3.8e-01_wd1.0e+00": 1.0055074310302734, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.9060045623779297, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.8018268203735351, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.7117618179321289, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.6282999610900879, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.554908971786499, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.49227267265319824, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.4321567964553833, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3887679362297058, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3560540986061096, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.31968052506446837, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.28570998072624204, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.26157559335231784, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.2433469060063362, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.22303113996982574, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.20802318572998046, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.19301950693130493, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1804360856115818, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.16882267840206622, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.15925911754369737, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.15014251001179219, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.14036553151905537, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.13373021461069584, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1285990422591567, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.12267446774989367, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.11826191540807486, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.11379121627658606, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10984830988571048, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10691651152446865, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.10389230689033865, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.10181338965892792, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.014110750523395837, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01378421793691814, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013276074198074639, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012801279644481838, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012373052379116416, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011840435513295233, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011313300710171462, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010816993126645684, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010290215606801212, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009843989666551351, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00948391604470089, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009030931508168577, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008647317350842058, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008150575230829418, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007720712404698134, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.007341937636956572, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006904328521341085, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006442650444805622, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005986497446428984, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005608957610093057, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.005196948500815779, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004826571521116421, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00446840395918116, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.004142599162878469, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0038555751007515937, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0035746895719785243, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0033686644316185265, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0032138444884913043, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.003038039103266783, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0028754960326477885, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0027565365348709747, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002668036664836109, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0025661782844690604, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0024914763757260517, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0024165074317716063, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002351551062311046, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00229379819589667, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0022473187843570484, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002204764648922719, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0021663127234205605, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0021436498378170654, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.002132038275594823, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0021272276726085693, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0021234157291473823, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0021155756516964175, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.002114661864179652, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0021037398694898003, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0020925152066047304, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0020924275659490376, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.741791248321533, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.704233169555664, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.644437313079834, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5877280235290527, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.5335853099823, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.4617786407470703, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.3844943046569824, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.302772045135498, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.2012040615081787, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.099189281463623, "validation/loss_010_lr1.0e-01_wd1.0e+00": 2.004572868347168, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.871639370918274, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.7525546550750732, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5964100360870361, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.463326334953308, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.3494428396224976, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.221731424331665, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.0921547412872314, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9692674875259399, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.8718283772468567, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7702049612998962, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6827108860015869, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.6020826697349548, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.5315903425216675, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.47176241874694824, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.4146221876144409, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.37362000346183777, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3430243134498596, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.3092828691005707, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.2780439257621765, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2562626004219055, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.24014531075954437, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.2225392460823059, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2097536325454712, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.19752569496631622, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.18738485872745514, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1783047467470169, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.17092175781726837, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.16395895183086395, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.15679393708705902, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.15206097066402435, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14841267466545105, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.14413484930992126, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1410529613494873, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13843123614788055, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13643401861190796, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.13547353446483612, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.1352822184562683, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.13564375042915344, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2584325396825397, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.263640873015873, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2760416666666667, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.2916666666666667, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31101190476190477, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3315972222222222, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3492063492063492, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3655753968253968, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.39558531746031744, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.4548611111111111, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5248015873015873, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.5964781746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6527777777777778, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7361111111111112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8028273809523809, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8489583333333334, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8807043650793651, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.8988095238095238, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9089781746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9119543650793651, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9174107142857143, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9223710317460317, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9250992063492064, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9285714285714286, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9303075396825397, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9320436507936508, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9340277777777778, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9372519841269841, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9399801587301587, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9422123015873016, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9461805555555556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9481646825396826, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.951140873015873, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9521329365079365, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9526289682539683, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9563492063492064, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9580853174603174, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9598214285714286, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9593253968253969, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9593253968253969, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0952044805372269, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.10174878384047657, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.11399038140949608, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.12588604448993002, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.1379969376312623, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.14867371719293132, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.15809093802548613, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.16954232117834298, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2062204356400184, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.28325122115033124, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.35667967420954677, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.44001149150552266, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.5404788651832545, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.6961208340531793, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.7903022897884762, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8471637294711859, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8792392164903637, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.8953988175700784, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9037424159574604, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9063033325224096, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9125334251452137, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9167089068358201, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9184662250210958, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9224050597984599, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9244008360794599, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9274506936547108, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9296152914293094, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9331315378916043, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9357024988024601, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9389633698667043, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9415130916275443, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9422603724985411, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9440473581328016, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9446187027743647, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.947856212030295, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9484124236146341, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9488406929376093, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9514124086810269, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.952223409513132, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9544412378765411, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9552738544485389, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9551690477400091, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9564448662159247, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.956773010498057, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9559291857669778, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.95706109201904, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9571834922414824, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9559591261864566, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9563670965926916, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 0.11826191540807486, "validation/loss_best": 0.1410529613494873, "validation/acc_best": 0.9608134920634921, "validation/f1_best": 0.956773010498057} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 0.9375308290123939, "train/grad": 0.04702358588576317, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.73376953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.695340576171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.633963623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5756463623046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.520166015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.446522216796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.3672900390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.283662109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.1796295166015627, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0754666137695312, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.9789593505859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.8436941528320312, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.722952880859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.5654550170898438, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.4319952392578126, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.3183522033691406, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.191484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.0633774566650391, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.9423988723754883, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8470981979370117, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.7480794143676758, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6632909774780273, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5852872371673584, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.5173220443725586, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.459642596244812, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.4046213269233704, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3651250767707825, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3353557634353638, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.30229990601539614, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.27140661180019376, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.24940629780292511, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.23279016256332397, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.21419452592730523, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.2003784540295601, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.18652418918907643, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.17481600515544415, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1640268975496292, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.15503269888460636, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.14642310928553343, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.13705997858196498, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1306901368126273, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.12565430272370576, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.11973426405340433, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.11516620226204395, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.11058645443990826, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.10627702109515667, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.10313218889757991, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.09985677935183049, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.0976068764552474, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013954687644727529, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013612357969395816, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.013068417576141656, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012575795501470565, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012134428420104086, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011588382576592266, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011056719147600234, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01056930682156235, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0100577050447464, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009627673637587576, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009276630028616638, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008825875683687628, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008438824093900621, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007934022261761129, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007496975976973772, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0071145717962645, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00667345249094069, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.006212348311673849, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005756678828038275, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005382272938732058, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004975871928036213, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004611251460155472, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004260268108919263, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0039429412491153925, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0036649251554626973, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0033926061633974313, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.003195033841766417, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.003044908248120919, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002878180968691595, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0027227695554029197, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0026099016226362438, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002526260603335686, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0024317233747569843, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00236046290199738, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0022874714294448496, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0022237301140557975, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002164528398425318, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0021167704806430267, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.002069510305300355, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.002020742899912875, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0019883206181111747, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001962867010443006, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0019361555451177992, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0019122898663044908, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0018933354402543045, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001874946823809296, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0018628660062677228, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0018426286772591993, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0018305558187421411, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.7219064235687256, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6822354793548584, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.618990182876587, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5591962337493896, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.502216339111328, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.426771879196167, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.345730781555176, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.2601845264434814, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.154167413711548, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.04789137840271, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.9497990608215332, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.8127366304397583, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.6908601522445679, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.5326086282730103, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3991773128509521, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2859081029891968, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.160150170326233, "validation/loss_017_lr3.2e-01_wd1.0e+00": 1.033513069152832, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.9143883585929871, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.820778489112854, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.7237650752067566, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6408680081367493, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5650537610054016, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.49917230010032654, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.44350290298461914, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3907614052295685, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.35303086042404175, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3249000906944275, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.29385077953338623, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.2652212083339691, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2450418770313263, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.23005862534046173, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.21355807781219482, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.2014952450990677, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1898644119501114, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1802026778459549, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.17165935039520264, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.16484999656677246, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15853695571422577, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.15201915800571442, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14783170819282532, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14449352025985718, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.14091789722442627, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13827960193157196, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13582322001457214, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.13426071405410767, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1336435228586197, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.13394898176193237, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1355450600385666, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.25992063492063494, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2683531746031746, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2822420634920635, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3023313492063492, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.31994047619047616, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3373015873015873, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3549107142857143, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.37524801587301587, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4176587301587302, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.49181547619047616, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5518353174603174, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6217757936507936, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.6755952380952381, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7708333333333334, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8315972222222222, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8668154761904762, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8911210317460317, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9047619047619048, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9114583333333334, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9146825396825397, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9196428571428571, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9250992063492064, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9273313492063492, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9295634920634921, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9322916666666666, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9325396825396826, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9347718253968254, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9379960317460317, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9419642857142857, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9479166666666666, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9499007936507936, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9536210317460317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9541170634920635, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9546130952380952, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9546130952380952, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9553571428571429, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9578373015873016, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9588293650793651, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9585813492063492, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9590773809523809, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9598214285714286, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9598214285714286, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9580853174603174, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.09714209669076622, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.10695050281125881, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.1198711872595273, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.13301324731003897, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.14269391537449547, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.15246421347193778, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.16106487713144638, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.1819028546449732, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.23683469321826256, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3229425072635011, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.3855261263290351, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.48308312602398035, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.585262617356379, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7501425644023734, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8281544431108668, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.866375437091914, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8886625490695682, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9001413497263753, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9053017556651299, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9086016904096862, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9142922478737825, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9184874499347695, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9208029030302808, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9240334057523899, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9272683583238988, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9274000454966295, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9306422730774735, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9339051643189267, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9384032563701945, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9396145401769896, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9434998627972104, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9455492205551342, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9487319946982135, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9493285424144977, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9499777790982611, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9498974479078368, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9511496657024449, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9520963464719446, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9541249596985097, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.955181406339143, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9555634582816607, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9563147175306287, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9560558129633295, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9561542813387476, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9581310172900479, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9558069392161428, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9557148922602474, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9561954117062557, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9533854955393191, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 0.11058645443990826, "validation/loss_best": 0.13582322001457214, "validation/acc_best": 0.9615575396825397, "validation/f1_best": 0.9581310172900479} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 0.9115307122468949, "train/grad": 0.045728900600224734, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.714024658203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.673477783203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.6089495849609374, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5477728271484374, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.489666748046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.4125775146484374, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.329969482421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.2427069091796876, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.134688720703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0266488647460936, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.9270330810546874, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.7881350708007813, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.66511962890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.5060658264160156, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.372697296142578, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.2600260162353516, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.1352558135986328, "train/loss_017_lr3.2e-01_wd1.0e+00": 1.0102450561523437, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8931010818481445, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.8014023208618164, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.7066376495361328, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6260228538513184, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5523095989227295, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4882990455627441, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.4343576431274414, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.38294655799865723, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.34615267157554624, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.31837587475776674, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2876161575317383, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2587335166335106, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.2381182688474655, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.22253383547067643, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.2049192200601101, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.19173255883157253, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.17845544271171093, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1671935087442398, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1567251755297184, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.1479039278253913, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.13942769914865494, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1301209169253707, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.12367241680622101, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11856620708480477, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.11254702104255557, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10796686390414834, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.10336510881781578, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09922265205532313, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09629962051287294, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0935299120657146, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.09168953962624073, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013714292044751346, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013354869349859655, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01278891142923385, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012284539793618023, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011834739521145821, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011282439180649816, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010756536056287586, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010281937732361256, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009788894588127732, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009371608975343407, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009027548921294511, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00857649190351367, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008184614123310894, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007672124621458352, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007229495709761977, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0068455947120673955, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0064070535474456845, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0059512745728716255, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005505963414907456, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005143768007401377, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0047541627730242906, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004408709264826029, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.004082134545315057, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003790142728248611, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0035351912665646523, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0032897169305942955, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0031120797561015935, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002976565437857062, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0028243307204684244, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0026787105819676073, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002574654644122347, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002492642205907032, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0023979550215881317, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0023274785588728265, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002252455619745888, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002189611155190505, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0021273319859756155, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00207391801988706, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0020220487064216285, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0019644329126458616, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.001921350866323337, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001886847140849568, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0018400156541611068, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0018001000600634143, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0017553678699187003, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001719488240487408, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0017022734726197086, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001698823323531542, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0017033801999059505, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.705717086791992, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.664275884628296, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5983171463012695, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5360403060913086, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4767816066741943, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3984553813934326, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.3142805099487305, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.225835084915161, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.1161065101623535, "validation/loss_009_lr8.7e-02_wd1.0e+00": 2.0065701007843018, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.905754804611206, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.7657054662704468, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.641804575920105, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.482374668121338, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.348945140838623, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.2366230487823486, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.1124699115753174, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.988493800163269, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8726509809494019, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7820263504981995, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6887158751487732, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.6095573306083679, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.537411630153656, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.47494152188301086, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.4226315915584564, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3730442225933075, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3378017246723175, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3114035427570343, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.28249967098236084, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.25575917959213257, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2370169311761856, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2229258120059967, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.20755791664123535, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1962171494960785, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1851905733346939, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.17602640390396118, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.16787640750408173, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1614188849925995, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1554379016160965, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1492101103067398, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.145173117518425, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.14181563258171082, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13770784437656403, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1347203403711319, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13184209167957306, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1295439898967743, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12797895073890686, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12652094662189484, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12554021179676056, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2631448412698413, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2725694444444444, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2876984126984127, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3082837301587302, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3253968253968254, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3430059523809524, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3601190476190476, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.3844246031746032, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.44072420634920634, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5168650793650794, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5763888888888888, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6443452380952381, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7105654761904762, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.7924107142857143, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8494543650793651, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8799603174603174, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.8975694444444444, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9084821428571429, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9126984126984127, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9171626984126984, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9236111111111112, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9263392857142857, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9283234126984127, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9310515873015873, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9327876984126984, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9345238095238095, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9372519841269841, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9432043650793651, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9441964285714286, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9494047619047619, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9516369047619048, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9546130952380952, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9568452380952381, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9590773809523809, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9600694444444444, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9630456349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10114874486844441, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11104347398937801, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.12342444436048056, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.13652128668166874, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.14525695552887607, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1548888985541221, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.16420560811012092, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.19230190142417766, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2663286977958655, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.34862938764675283, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4161732760191677, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5273493555753304, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.6529621265281692, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.7758664261240582, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8477082852201121, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8783674270715922, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8935172887806356, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9028535015829606, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9072355311893451, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9118026614170117, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9181635877506548, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9201592419378845, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9218692248885904, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9256665522210815, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9280655206568356, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9304386595167395, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9331157824899663, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9364233252917205, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.939499462273067, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9408907462859133, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9435458310561773, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9461385224177006, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9475859759818197, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9500165808713659, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9502394913161121, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9511697434063241, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9522862813921694, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9527889032902424, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9549176334083137, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.955898133293435, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9565002199599716, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9571275063471312, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9578013214877394, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9586507223799003, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9585505130430784, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9581959477876373, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9574292674673492, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.958104130725801, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.959336388548711, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.09168953962624073, "validation/loss_best": 0.12554021179676056, "validation/acc_best": 0.9630456349206349, "validation/f1_best": 0.959336388548711} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 0.8965722498297691, "train/grad": 0.04546076258644462, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.705367431640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6637591552734374, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.597486572265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5349542236328126, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4753411865234374, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3965289306640627, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.31179931640625, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.2225, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.111708984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 2.0011041259765623, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8991650390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.7576553344726562, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.6327468872070312, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4721559143066407, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.3382530212402344, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.2257547760009766, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.1016932678222657, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9780668640136718, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8627391052246094, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7728247833251953, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6803472709655761, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.6019425964355469, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5306404304504394, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.46890466690063476, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.41695016384124756, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3676830577850342, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.33243370056152344, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.3059082889556885, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.27662146627902984, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.24904756665229796, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.2293883430957794, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.21453774124383926, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.19771284118294716, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.18521053656935693, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.17253657549619675, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.16171592608094215, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.15172490857541562, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.14331716425716878, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1351781513914466, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12626098871231078, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.12019215937703848, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.1152708811685443, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.1095928194001317, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10528050428256393, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.10086472697556019, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09691193154081702, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09400860503315926, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.09113945934921502, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.08911271188408136, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013548758174292743, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013180633718147873, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012613473339006304, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012116121458820999, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011673638354986906, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011139132245443762, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010640502218157053, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010197735107503832, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009739206121303141, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009346917551010848, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00901788592338562, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008578643235377967, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008191716212313621, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007684074395801872, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007245886998716742, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006865534191019833, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006432153037749231, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005980976030696183, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005539757634978742, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.005178671304602176, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004788155095884577, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004442072546808049, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00411279471241869, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0038164919638074934, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003559663409832865, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003310161456465721, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0031297394656576217, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0029925350821577014, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0028379461250733584, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0026912794780218972, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002586846156627871, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0025060537696117535, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00241163159313146, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0023410484998021273, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002267685975821223, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.002203001625020988, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0021406398559338413, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0020871018921025095, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0020327191590331496, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0019719906235695817, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0019299427946680226, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0018947013418073766, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0018589260496082716, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001834453684859909, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0018114092882024124, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0017969731151242741, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0017851657293795143, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0017727056797593832, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0017605287361948285, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6930599212646484, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6502349376678467, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.582213878631592, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.517939329147339, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4569709300994873, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3763773441314697, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.2899889945983887, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.198988199234009, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0864975452423096, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9745144844055176, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8716299533843994, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.729309320449829, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.6042044162750244, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.4439215660095215, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.3107388019561768, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1991870403289795, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0766377449035645, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9546183943748474, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8412039875984192, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7529066205024719, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6624346971511841, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5860409736633301, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5166745781898499, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4569186866283417, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.40695539116859436, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.359914094209671, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.32633790373802185, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.3014002740383148, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.2739622890949249, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.24860946834087372, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.23076458275318146, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.21754521131515503, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.20287162065505981, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.19221535325050354, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1815890520811081, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.17293302714824677, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.16514256596565247, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15883031487464905, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1528761237859726, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1466083824634552, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14242766797542572, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13926748931407928, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13571465015411377, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13313795626163483, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13053929805755615, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12830953299999237, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12686316668987274, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12551695108413696, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12481268495321274, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2648809523809524, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.27331349206349204, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2904265873015873, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3134920634920635, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.330109126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3492063492063492, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.36731150793650796, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39112103174603174, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4556051587301587, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5369543650793651, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.5910218253968254, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6572420634920635, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7266865079365079, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8110119047619048, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.861359126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8859126984126984, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9002976190476191, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9097222222222222, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9151785714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9184027777777778, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9243551587301587, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9260912698412699, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9285714285714286, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9320436507936508, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9320436507936508, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9387400793650794, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9422123015873016, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9451884920634921, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9474206349206349, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9496527777777778, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9526289682539683, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9538690476190477, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.955109126984127, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9573412698412699, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9637896825396826, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9640376984126984, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9635416666666666, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10335763278543915, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11189636204789165, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.1248094722437583, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.13909209229765518, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.14743154171528652, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.15805801363029653, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17171004176057778, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.19977005179463672, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.2839390310657523, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3699643141594561, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4349661578249525, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5501271452434019, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.684419761766581, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8022607753205551, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8600370971885065, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8841271030199627, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.895846325191944, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9045195948249314, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9090055620196724, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9129105720843681, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9184195399571978, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9190078501927237, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.922718041057405, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9268577086385152, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9271365952594944, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9302666988968437, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9348074056404249, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9367294402047703, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9386348203063909, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.941522411223645, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9443096531787882, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9457537687571913, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9485262432140902, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9492786241745406, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.950557474890125, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9515029839331623, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9535849544782268, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9554411615735484, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.955806088957918, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9582981105967722, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.958106670153527, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.957684788233029, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9579757937482275, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9588314309572968, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9590964517123419, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9596516761645433, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9595074295381614, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9596783023261295, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9590439457087692, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.09113945934921502, "validation/loss_best": 0.12551695108413696, "validation/acc_best": 0.9640376984126984, "validation/f1_best": 0.9596783023261295} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 0.8819532254338265, "train/grad": 0.044114271700382235, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.691588134765625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.648570556640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5802484130859376, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5157684326171874, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.454368896484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3733660888671877, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.286427001953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.19487060546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0817071533203126, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.968870849609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8652304077148438, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.7220309448242188, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5962913513183594, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4354920959472657, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.3022352600097655, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.1907047271728515, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.068447036743164, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9470584869384766, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8343543624877929, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.74685546875, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6572586250305176, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.581677074432373, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.5130692481994629, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4538733673095703, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.4043007588386536, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.357294065952301, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.32376453042030334, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.29848765015602113, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.27046227633953096, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2441827291250229, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.22531018197536468, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.21104428619146348, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.19492379650473596, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.18284157499670983, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.17050174094736575, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.16004488207399845, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.15031008664518594, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.141993520334363, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.13392733085900546, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1250755376368761, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11898987002670765, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11414983831346034, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10840720742940903, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10406495288014411, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09962130265310407, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09560089949518442, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.09268421763554216, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.0897466370370239, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.08761463209986686, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013381259548477829, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012991852089762689, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012397389449179173, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011875493670813739, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011413642819970846, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01086072789505124, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0103508809232153, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009901582915335893, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009437870681285859, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009043967800680548, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008711084465030581, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008266888356301934, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007876752356532962, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007364730653353036, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006925723443273455, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006546149582136423, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006115349840838462, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005669951596064493, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005237039463827387, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004886936763068661, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004511445118114352, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004183576272334903, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00387479787459597, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003600488103693351, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033655056590214372, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00313780689612031, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0029730497085256502, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.002847600801032968, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0027067697088932617, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002571696835802868, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0024727065325714647, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0023965260793920606, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0023089071409776807, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0022416628315113487, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002172129781683907, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.00211304125667084, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002054781992628705, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0020059489147388376, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0019567360074142924, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001900095413730014, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0018621141382027418, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001831429602461867, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0017961970070609823, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0017693991152918898, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.001747957741317805, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0017327929858583957, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.001727502062858548, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0017136515930178575, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0016977170188329184, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6836464405059814, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6397242546081543, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.570197582244873, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.5044262409210205, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.442192316055298, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3598828315734863, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.271665096282959, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.179030656814575, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0646049976348877, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.95075261592865, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8464221954345703, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.7025853395462036, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.5765161514282227, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.4158765077590942, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2829205989837646, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.172058343887329, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.050539493560791, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9300351738929749, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8185275197029114, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7320084571838379, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6435953974723816, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5691512227058411, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.5018370151519775, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.44409236311912537, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3957520127296448, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3503459393978119, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3181561529636383, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2941915690898895, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.26779353618621826, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.2434571087360382, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.22630296647548676, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.21352286636829376, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.19936080276966095, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18908078968524933, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.17891190946102142, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.1706438660621643, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.16312700510025024, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15708863735198975, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1514936238527298, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1457919180393219, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.14189410209655762, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13908398151397705, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13593129813671112, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13381868600845337, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.13162833452224731, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12971460819244385, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1284223049879074, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12702053785324097, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12602533400058746, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2666170634920635, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.27554563492063494, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2951388888888889, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.31646825396825395, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3333333333333333, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.35044642857142855, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.36904761904761907, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.39856150793650796, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4714781746031746, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5478670634920635, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6029265873015873, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6676587301587301, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7442956349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8236607142857143, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8670634920634921, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8901289682539683, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9020337301587301, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9122023809523809, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9151785714285714, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9206349206349206, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9255952380952381, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9273313492063492, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9298115079365079, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9317956349206349, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9325396825396826, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9350198412698413, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9387400793650794, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9446924603174603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9476686507936508, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9508928571428571, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9518849206349206, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9543650793650794, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9565972222222222, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.957093253968254, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9598214285714286, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9605654761904762, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9623015873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10550856566411707, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11392861863198955, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.12832598609523402, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.14074926205617888, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.14981153259858243, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.15795188940226235, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.1744636262957889, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.2100822736727506, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3017599823475966, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3801443627768072, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.45093202020817535, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5696434795033969, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.711431131657353, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8178330701514007, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8653918717437499, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8878015289742981, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8966370295487651, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9061414104273996, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9089570603105728, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9148397008240154, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9193555424043103, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9202462226115811, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9237606380101759, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9268984209222089, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.928040381026831, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9311963634900894, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9349802634352861, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9372636010844995, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.94069475953852, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9442202729886722, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9467075829961619, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9475840655892744, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.950298819293025, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9516192233677456, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9524236162714694, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.952622511882143, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9536724098555147, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9558404664826208, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9557688660707171, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9573356422027689, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9587689673227333, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9584130996753645, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9581229160527018, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9578619914436837, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9584650171618522, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9583373981189431, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9582533385797338, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9584781559974354, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9584673834926443, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.0897466370370239, "validation/loss_best": 0.12702053785324097, "validation/acc_best": 0.9623015873015873, "validation/f1_best": 0.9584781559974354} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 0.8713114756345749, "train/grad": 0.044630259443074465, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.684681396484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6408013916015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5710516357421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.5053271484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.442882080078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3604180908203123, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2719329833984374, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.178763427734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0636642456054686, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.949052734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8441311645507812, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6993173217773438, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.572573699951172, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.4112332153320313, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2780313110351562, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.166964569091797, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.045525131225586, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9254170608520508, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.8142920303344726, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7283149719238281, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6405077934265136, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5665793704986573, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4997478771209717, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4422495079040527, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.39416717529296874, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.34860165357589723, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.31609989643096925, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2916952919960022, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2645103061199188, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.23904703855514525, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.22071931898593902, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.20673997610807418, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.19099267095327377, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.17908598184585572, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1670422859489918, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.15667107969522476, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.14699976734817027, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.1387852269411087, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.13072183568030596, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12189342081546783, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11572177231311798, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.11076095744967461, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10494833720847964, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.10049611886963249, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09588970536366105, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09169904805719853, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08859682470560074, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.08553717301227153, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.08338011949323118, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013499553399160504, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013107204320840537, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012512755454517901, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01199271887075156, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011531934957019985, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010984339537099003, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01048212123569101, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010038496190682054, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0095783068286255, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009180630678310991, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008841702700592577, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008385559380985796, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007983704991638661, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007457861928269267, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.007007997564505786, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006620262612123042, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006180776981636882, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00572746621677652, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005287982802838087, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004933118572225794, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00455581542570144, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0042258466908242556, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003917789567494765, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003645042417338118, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0034123839403036984, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.003188906570430845, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0030262735160067676, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0029035116668092087, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.002765120284166187, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0026328808546531943, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0025355405890149997, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00245804691046942, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002370421258965507, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0023024829401401803, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.002230782601982355, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0021648621838539837, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.002102623383398168, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.002047547962865792, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001991450836067088, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.001927703371620737, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0018810722974012606, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001842380417510867, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0017962603067280725, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0017610658766352573, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0017232902272371576, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.001690366362745408, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0016660312376916408, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.001649429160170257, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0016417535513755866, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.677013397216797, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.632495403289795, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.561800003051758, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.49518084526062, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4319396018981934, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.348435640335083, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.259093761444092, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.165286064147949, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0493569374084473, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9343433380126953, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8290226459503174, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6840739250183105, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.5575300455093384, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.3965809345245361, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2637991905212402, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1532928943634033, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0325322151184082, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9133661985397339, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.8030169606208801, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7177813053131104, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6307761669158936, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5576881170272827, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4917353093624115, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.43529972434043884, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3882771134376526, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3440646529197693, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.31267979741096497, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2893543541431427, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.26366516947746277, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.23995184898376465, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.22327204048633575, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.21081428229808807, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.19696669280529022, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.1868891566991806, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.17696374654769897, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.16892355680465698, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.16151808202266693, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1556302011013031, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.15010720491409302, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.1444293111562729, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1406618356704712, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13779272139072418, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13467749953269958, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13220828771591187, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1299905925989151, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12800462543964386, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1265510469675064, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12526027858257294, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12439631670713425, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2683531746031746, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.27728174603174605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.2993551587301587, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.31820436507936506, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3345734126984127, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3521825396825397, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3722718253968254, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.40500992063492064, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.48313492063492064, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5570436507936508, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6088789682539683, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6773313492063492, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7549603174603174, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8315972222222222, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.873015873015873, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8933531746031746, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9045138888888888, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9126984126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9159226190476191, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9213789682539683, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9248511904761905, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9278273809523809, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9300595238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9315476190476191, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9340277777777778, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.935515873015873, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9419642857142857, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9432043650793651, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9454365079365079, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9494047619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9521329365079365, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.953125, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9583333333333334, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9588293650793651, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9627976190476191, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10742143439698096, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11528778831079903, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.13110514916760244, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.14109611624783241, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.15000282173372906, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1590968128076821, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.17764127665011517, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.21953103732861626, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3134267350147396, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3929795671627622, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.4591943486816068, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.5889772179869769, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7279285278347609, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8271998835723774, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8714905672262505, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8904029825039756, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.8998700487804632, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9068098413355971, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9096152742021324, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9160899952772018, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9185908028814063, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.92096512664947, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9246931970701036, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9266383748069639, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.929638491100906, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9312062809818089, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9365416372867178, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9381434787475371, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.939410018030094, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9424194254140356, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9457968959428226, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9479805178749126, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9488812567347031, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9503971063233546, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9513251117146818, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9532970038895088, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9540171464395528, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9546793115012107, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9563113135446196, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9557126992403805, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9560892407265916, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9567234546736634, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9570906081155948, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9573321686888031, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9566986921812214, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9579340719854731, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9578893065844502, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9582170117435531, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9585587714506723, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.08338011949323118, "validation/loss_best": 0.12439631670713425, "validation/acc_best": 0.9627976190476191, "validation/f1_best": 0.9585587714506723} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 0.8631641191244125, "train/grad": 0.04387704085558653, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.678505859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6339178466796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5630853271484373, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4963970947265626, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.43296142578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.349171142578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2595794677734373, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.1652288818359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0487271118164063, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.9328890991210939, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8270074462890624, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.681199951171875, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5539608764648438, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.392279815673828, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.259219207763672, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.1486253356933593, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0279496002197266, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9088479995727539, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7989706039428711, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7140546035766602, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6275318527221679, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5547982692718506, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4892076873779297, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4329752254486084, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.38591857433319093, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.34143923163414003, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3097130024433136, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.2859659057855606, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.25949945211410524, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.23470683842897416, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.216884243786335, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.20330306753516197, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.18796401746571065, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.17639579817652704, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.16461962550878526, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.15459589950740338, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1450906676799059, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.13706784322857857, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.12930197544395924, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.12051734559237957, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11449021834880113, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10963575348258019, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10380996217951179, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09932740876451135, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09472037781029939, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.09042100796476006, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08719472469761967, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.08387560980394483, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.08149239351972938, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013315948280505837, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01291833755094558, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012321286695078015, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011798092941753567, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011337355608120561, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01079294343944639, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010297365430742502, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009860379353631288, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009409084320068359, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009017018543090671, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008683341587893665, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0082318688579835, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007833735523745418, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007315531931817531, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0068744171480648215, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006495283730328083, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0060683936183340845, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005629456056049094, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0052046992664691065, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004861728233518079, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004496795727172867, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004177519914228469, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038755860237870365, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00360955954878591, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003380071464343928, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0031582923769019546, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002997115312027745, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0028742326440988107, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0027355134702520445, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0026014081545872613, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002502761585637927, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.002425274716806598, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0023346398636931555, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0022641389578348025, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0021885957306949423, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0021227079327218235, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0020575392586761154, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0019991270612808878, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001942563282791525, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0018732578778872266, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0018245630816090851, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0017839123960584403, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001731608510017395, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0016919003319344483, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0016480078661697917, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0016082953131990507, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0015780838913633489, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015473573084454984, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0015260145330103115, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6729495525360107, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6278655529022217, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5565836429595947, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4892630577087402, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.4254794120788574, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3413100242614746, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.251250743865967, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.156592845916748, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0399527549743652, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9239826202392578, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8182003498077393, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6725726127624512, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.545619249343872, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.3844801187515259, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2519475221633911, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1416996717453003, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.021491527557373, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.9027786254882812, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7933279275894165, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7088049054145813, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6228324770927429, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.550559937953949, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.48557108640670776, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4298109710216522, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.38359376788139343, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.34010612964630127, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3093205392360687, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2863185405731201, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.26109376549720764, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.23789159953594208, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.22135323286056519, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.20918534696102142, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.19560720026493073, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18572159111499786, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.17605376243591309, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.16786538064479828, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1607220619916916, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1547561138868332, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.14930245280265808, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14364133775234222, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13979999721050262, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13695849478244781, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13363562524318695, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1311817318201065, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12884733080863953, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12675711512565613, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.1252167969942093, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12377110868692398, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12257618457078934, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.2698412698412698, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.27827380952380953, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.3013392857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.32043650793650796, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3353174603174603, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3531746031746032, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3742559523809524, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.40773809523809523, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4908234126984127, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5615079365079365, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6153273809523809, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6850198412698413, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7604166666666666, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8375496031746031, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8745039682539683, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8943452380952381, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9050099206349206, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9126984126984127, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.917906746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.921875, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9255952380952381, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9275793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9303075396825397, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9317956349206349, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9332837301587301, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9375, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9404761904761905, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.941468253968254, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9427083333333334, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9461805555555556, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9486607142857143, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9513888888888888, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9526289682539683, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9541170634920635, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9563492063492064, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9578373015873016, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9605654761904762, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9603174603174603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9608134920634921, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9610615079365079, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9613095238095238, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9627976190476191, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10890768481062241, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11607006588038649, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.13216356083831818, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.1421443078637352, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.15074026951359465, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.15933950694785165, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.18005916912811895, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.22382158577309696, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.32209824934976117, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.3982539425144009, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.47031946261065344, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.603244961953826, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7361062231706151, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8350405703673631, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8726315888966185, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8907618907283451, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9001231108407485, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9071494177453394, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9121586177820975, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9155465697938032, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9181806438603444, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9206503676590719, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9248894421747625, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9269667511535337, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9289986098787918, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9326534863743473, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9365649271978282, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9377537451886669, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9390338698094147, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9430529323476196, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9449116790356465, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9475356956153446, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9483772440080168, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9497463318538406, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9517155946228344, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.952764471630406, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9550079002343219, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9562718930156772, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9565266366680498, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9562372979711343, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9568831045784074, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9568068022144209, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9574616813312861, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9569618186824923, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9584672154651114, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9579329294645953, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9576620419464693, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9581071950955491, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9582493222939111, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.08387560980394483, "validation/loss_best": 0.12377110868692398, "validation/acc_best": 0.9627976190476191, "validation/f1_best": 0.9581071950955491} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 0.8587240082025528, "train/grad": 0.044088680986315014, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.67640380859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.631500244140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5604730224609376, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.4934381103515624, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4297503662109374, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.345625, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.25557861328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.1608282470703126, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0436761474609373, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.927447509765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8210903930664062, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6748249816894532, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.547233123779297, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.3854472351074218, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2522953033447266, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.14176513671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0211165618896485, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.9022095489501953, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7924655151367187, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.7078753089904786, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.621594352722168, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5492316150665283, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.48400007247924803, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4279107713699341, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.38112711668014526, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3369129967689514, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.30534711241722107, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.28167186081409457, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.2553697210550308, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.23064735054969787, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.212889154702425, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.19937503799796105, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.18405621275305747, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.17255329869687558, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.1608544585853815, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.1508834759145975, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.14145515378564597, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.13349920839071275, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.1257297122851014, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1170755111053586, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11109259681776167, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10626194121316075, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.10046599062159657, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09597365879453719, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.09136113750748337, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08705551798455417, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08378885575570166, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.08037358376197518, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.07787552686408163, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013403690848499537, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.013004772756248712, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012406251304782926, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011883363192901016, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011423974256031215, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010881138173863292, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010389951325487345, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00995627093827352, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009505972974002361, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009113317725714297, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008773699414450675, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008314068506006151, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00790683799656108, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007374223256483674, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006919579932000488, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006527285797055811, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0060837442870251834, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005627229704987258, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005185697756242007, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004829738438129425, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004452494491124526, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00412218074197881, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038159195589832964, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003544071927899495, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.003312185942195356, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0030908564757555724, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0029286855540703984, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0028081540006678553, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0026707431324757636, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0025399757659761235, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0024432778515620156, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0023669650155352428, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0022791084041818978, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0022118288674391807, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0021405880263773726, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0020791422910406256, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0020184818061534317, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00196496210526675, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.001909770661732182, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0018451412272406742, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0017980336569598876, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.001759225798305124, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0017108092477428726, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.001671640914864838, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0016300321742892265, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0015917377738514915, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0015623786178184673, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015312846755841747, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0015076773634064011, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.670769453048706, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6255171298980713, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.553816556930542, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.486243486404419, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.422126293182373, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3375813961029053, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.247093439102173, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.1521003246307373, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.034852981567383, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9186369180679321, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.8124029636383057, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6665042638778687, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.5393626689910889, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.3781003952026367, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2455979585647583, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1355863809585571, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0156323909759521, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.8972843289375305, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7882814407348633, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.7041085958480835, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6185216903686523, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5467451214790344, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4821796715259552, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4269585907459259, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3810390532016754, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.33803144097328186, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.3074200451374054, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.28470462560653687, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.25970175862312317, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.23660822212696075, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.2202320247888565, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.20819257199764252, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1947213113307953, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18481133878231049, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.17514297366142273, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.16714335978031158, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.16001227498054504, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15416285395622253, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.14868125319480896, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14308993518352509, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13933680951595306, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1364995688199997, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1333494484424591, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.1308719515800476, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12865298986434937, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.1267005354166031, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12525564432144165, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12387415021657944, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.1229226142168045, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.27033730158730157, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.2787698412698413, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.3010912698412698, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.32018849206349204, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.3368055555555556, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.35342261904761907, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.3757440476190476, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4089781746031746, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.49231150793650796, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5639880952380952, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6173115079365079, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6902281746031746, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7633928571428571, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8370535714285714, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8754960317460317, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8953373015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.90625, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9119543650793651, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.9176587301587301, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9246031746031746, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9275793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9300595238095238, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9312996031746031, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9332837301587301, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9372519841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9419642857142857, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9432043650793651, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.951140873015873, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9518849206349206, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9541170634920635, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9558531746031746, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9556051587301587, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9575892857142857, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9595734126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9615575396825397, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9627976190476191, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10935025430043892, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11656412216586338, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.13208047872488274, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.14163214805667543, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.15179641231139104, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.15956623003777948, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.18251127076172363, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.22522494073687768, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.323718915719478, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4010432812506167, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.47631089963274226, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6133834381625053, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7409619909788406, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8348535536586096, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8742766452371358, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8916204283711948, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9009878283835308, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.9067131418306082, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9114306710046923, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9161341062938119, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.917597722164782, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9209556357499373, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9241642910008662, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.92622444913116, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9290417199683092, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9329120548669306, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9363916980216986, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9384476384606278, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.939410018030094, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9430724898017657, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9471232539847192, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9477928483757966, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9496361066600989, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9510189535535754, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9510457173806867, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9529965354664056, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9547167171286931, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9562481659915747, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9567432819116216, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9576703728990817, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.958185637295401, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.958475262811961, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9583676912901806, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.958547180555126, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9578259010961329, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9586222463776182, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9583234337501167, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9583122255496408, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9588663501949642, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 0.07787552686408163, "validation/loss_best": 0.1229226142168045, "validation/acc_best": 0.9627976190476191, "validation/f1_best": 0.9588663501949642} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 0.8530785399675369, "train/grad": 0.04411057885736227, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.67264404296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6275738525390624, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5561431884765624, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.488824462890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4246954345703124, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.34012939453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2496002197265623, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.1543157958984374, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0367388916015625, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.920013427734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8132586669921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6663731384277343, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5384747314453124, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.3761932373046875, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.2429346466064453, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.132239761352539, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.0115340423583985, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8926930618286133, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7832413864135742, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6987426567077637, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6128204917907715, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5408688068389893, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4759458923339844, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.42033790588378905, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.37404913902282716, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.33029704093933104, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.2991084420681, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.27566960871219637, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.24972566068172455, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.22535942018032074, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.20784908935427665, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.1945568384230137, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.17948392316699027, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.1681926503032446, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.15665783166885375, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.14688816837966442, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.1376623910665512, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.12991330493241549, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.12235545452684164, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.11391512509435416, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.1081140965782106, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10345433359965682, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09786343647167087, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09354161044582725, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0890859940648079, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08483913743868471, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08166303297504783, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.07836942211724818, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.07589700601994992, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013395634810440243, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012993982578627765, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012392300190404057, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011867331084795296, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011404862250201405, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010859706499613821, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010364936874248087, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009929644661024212, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009477278916165233, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009084046988282352, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008743503482546657, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00828289256663993, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.007877434624824674, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007347352663055062, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0068970879283733666, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006509778497274965, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006073529846034944, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005626350349048153, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005194047265686095, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004845081539824605, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004475309458794072, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004152450737310573, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.003850282665807754, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0035835687059443443, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033553822175599636, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0031365855102194473, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.002977925763698295, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0028573139681247993, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0027233546192292125, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.002595556078013033, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002500146936508827, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00242550753406249, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002340002340497449, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0022731740650488064, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0022030138212721794, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0021399788084090687, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0020749034875188954, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0020190070269745773, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0019626663214876317, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0018923793657450005, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0018442841232172214, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0018022430938435718, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0017504117387579755, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0017079264711355791, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0016643552007735707, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0016212448495207354, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0015882486547343434, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00155271990748588, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0015266082718153485, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.6699488162994385, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.624645233154297, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.5528128147125244, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.485109567642212, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.420879364013672, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.336134672164917, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.2455878257751465, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.1504228115081787, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0330379009246826, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9165619611740112, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.81029212474823, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6641913652420044, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.5369477272033691, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.3756941556930542, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.2432538270950317, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1332732439041138, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0134077072143555, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.8952195644378662, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.786272406578064, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.702253520488739, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6168882846832275, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.545316219329834, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.4808596968650818, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.4258301258087158, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.37996265292167664, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.33714529871940613, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.30665814876556396, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.28401580452919006, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.2590682804584503, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.236154705286026, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.21990807354450226, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.20793896913528442, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.1944355070590973, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18470126390457153, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.17504677176475525, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.16703790426254272, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1599423587322235, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.15409605205059052, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.1487244963645935, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14313924312591553, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.13943487405776978, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.1366022378206253, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.13338884711265564, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13095441460609436, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.1288384050130844, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12686574459075928, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12524697184562683, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12383969128131866, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12280967086553574, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.27058531746031744, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.28000992063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.30158730158730157, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3211805555555556, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.33556547619047616, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.35342261904761907, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37524801587301587, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4104662698412698, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4928075396825397, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5647321428571429, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6192956349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6927083333333334, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7658730158730159, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8385416666666666, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.876984126984127, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8953373015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9060019841269841, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9122023809523809, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.917906746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.925843253968254, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9275793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9305555555555556, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9320436507936508, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9330357142857143, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9372519841269841, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9424603174603174, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9464285714285714, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9523809523809523, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9533730158730159, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9585813492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9595734126984127, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9608134920634921, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9623015873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9630456349206349, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9623015873015873, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10934539409500602, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11787272214020324, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.13232496996155865, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.14262955788996343, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.150720813954304, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.1594442349399262, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.18165475353303254, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.22716297649291717, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.32399154233966715, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4019877248029229, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.48094889238643423, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6174163657514551, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7441566242490294, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8370223462302782, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8751542270993186, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8911844398007561, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9009221249562678, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.90649507406416, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.9117021134278017, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9156401123409568, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9188147584705058, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9207816779037917, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9251311685076651, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9268244417676973, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9287754669855155, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9332730849606922, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9363916980216986, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9389222802806504, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9395977249159041, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9432420403063534, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9463889817730601, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9481999248833853, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9489953317352795, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9502926976028899, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9514845665863161, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9537045888683705, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9549126074533038, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9562490290106127, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.9567948102932304, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9583200887454808, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.9587271096490088, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9585672957703556, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9583755501352806, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9587277489333261, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9587524224151321, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9580650366628393, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.958819427278757, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9584198906496508, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9582149466821942, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 0.08166303297504783, "validation/loss_best": 0.12524697184562683, "validation/acc_best": 0.9630456349206349, "validation/f1_best": 0.958819427278757} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 0.8522933033108712, "train/grad": 0.043850171249359846, "train/loss_000_lr2.0e-02_wd1.0e+00": 2.6702978515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 2.6249053955078123, "train/loss_002_lr2.8e-02_wd1.0e+00": 2.5529998779296874, "train/loss_003_lr3.3e-02_wd1.0e+00": 2.485123291015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 2.4207037353515624, "train/loss_005_lr4.5e-02_wd1.0e+00": 2.3356195068359376, "train/loss_006_lr5.3e-02_wd1.0e+00": 2.2447369384765623, "train/loss_007_lr6.2e-02_wd1.0e+00": 2.1492156982421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 2.0311788940429687, "train/loss_009_lr8.7e-02_wd1.0e+00": 1.914266357421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 1.8073275756835938, "train/loss_011_lr1.2e-01_wd1.0e+00": 1.6603569030761718, "train/loss_012_lr1.4e-01_wd1.0e+00": 1.5325177001953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 1.3704525756835937, "train/loss_014_lr2.0e-01_wd1.0e+00": 1.237529067993164, "train/loss_015_lr2.3e-01_wd1.0e+00": 1.1271141052246094, "train/loss_016_lr2.7e-01_wd1.0e+00": 1.006997299194336, "train/loss_017_lr3.2e-01_wd1.0e+00": 0.8888145065307618, "train/loss_018_lr3.8e-01_wd1.0e+00": 0.7800447463989257, "train/loss_019_lr4.4e-01_wd1.0e+00": 0.6961798477172851, "train/loss_020_lr5.2e-01_wd1.0e+00": 0.6110652160644531, "train/loss_021_lr6.1e-01_wd1.0e+00": 0.5396378803253173, "train/loss_022_lr7.2e-01_wd1.0e+00": 0.4754397678375244, "train/loss_023_lr8.5e-01_wd1.0e+00": 0.4203823184967041, "train/loss_024_lr1.0e+00_wd1.0e+00": 0.37456101179122925, "train/loss_025_lr1.2e+00_wd1.0e+00": 0.3313681745529175, "train/loss_026_lr1.4e+00_wd1.0e+00": 0.3005986416339874, "train/loss_027_lr1.6e+00_wd1.0e+00": 0.27747861206531527, "train/loss_028_lr1.9e+00_wd1.0e+00": 0.25185735285282135, "train/loss_029_lr2.3e+00_wd1.0e+00": 0.2278358495235443, "train/loss_030_lr2.7e+00_wd1.0e+00": 0.2106277184188366, "train/loss_031_lr3.1e+00_wd1.0e+00": 0.197466029971838, "train/loss_032_lr3.7e+00_wd1.0e+00": 0.18254270076751708, "train/loss_033_lr4.3e+00_wd1.0e+00": 0.17124307535588743, "train/loss_034_lr5.1e+00_wd1.0e+00": 0.15973843418061734, "train/loss_035_lr6.0e+00_wd1.0e+00": 0.149896393828094, "train/loss_036_lr7.1e+00_wd1.0e+00": 0.14061137940734625, "train/loss_037_lr8.3e+00_wd1.0e+00": 0.13269133999943733, "train/loss_038_lr9.8e+00_wd1.0e+00": 0.12498717505484819, "train/loss_039_lr1.2e+01_wd1.0e+00": 0.1163940236158669, "train/loss_040_lr1.4e+01_wd1.0e+00": 0.11040605012327433, "train/loss_041_lr1.6e+01_wd1.0e+00": 0.10559206699952484, "train/loss_042_lr1.9e+01_wd1.0e+00": 0.09987846786156297, "train/loss_043_lr2.2e+01_wd1.0e+00": 0.09543794503435493, "train/loss_044_lr2.6e+01_wd1.0e+00": 0.0908794773183763, "train/loss_045_lr3.1e+01_wd1.0e+00": 0.08657271847128868, "train/loss_046_lr3.6e+01_wd1.0e+00": 0.08333758970722556, "train/loss_047_lr4.3e+01_wd1.0e+00": 0.07998842821456492, "train/loss_048_lr5.0e+01_wd1.0e+00": 0.07747494242154061, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.013297204645350575, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012895969692617654, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012298383614979685, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011776118082925677, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011316932099871337, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010777365970425308, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01028967345599085, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009862452177330852, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009419082230888307, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00903473436133936, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008701486105564982, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008250858676619828, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00785276916110888, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.007330948729068041, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.006887674217578024, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.006505517514888197, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.006073256500530988, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.005628481176681816, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.005198025862919167, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.004848272482631728, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.004476781325647608, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.004151559612946585, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0038457087439019233, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.003576053836150095, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0033452233939897267, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0031249544548336418, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.0029656357801286504, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0028454149881144987, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0027110832376638426, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0025838066812139005, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.002490315207396634, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0024162150640040635, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.002330427264678292, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.002264417850528844, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0021930059103760866, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0021306803336483427, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0020674900608719324, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0020101128821261227, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0019537968808435837, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0018873392028035596, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.001837520979170222, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0017956661272910423, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.001743546708021313, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0017027468417654746, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0016586529577034526, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0016140796718536875, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0015806580267963, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0015442400588653981, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.001517283036664594, "validation/loss_000_lr2.0e-02_wd1.0e+00": 2.669851303100586, "validation/loss_001_lr2.3e-02_wd1.0e+00": 2.6244964599609375, "validation/loss_002_lr2.8e-02_wd1.0e+00": 2.552669048309326, "validation/loss_003_lr3.3e-02_wd1.0e+00": 2.4849555492401123, "validation/loss_004_lr3.8e-02_wd1.0e+00": 2.420712471008301, "validation/loss_005_lr4.5e-02_wd1.0e+00": 2.3359463214874268, "validation/loss_006_lr5.3e-02_wd1.0e+00": 2.24538516998291, "validation/loss_007_lr6.2e-02_wd1.0e+00": 2.150196075439453, "validation/loss_008_lr7.4e-02_wd1.0e+00": 2.0327413082122803, "validation/loss_009_lr8.7e-02_wd1.0e+00": 1.9162834882736206, "validation/loss_010_lr1.0e-01_wd1.0e+00": 1.809970498085022, "validation/loss_011_lr1.2e-01_wd1.0e+00": 1.6638710498809814, "validation/loss_012_lr1.4e-01_wd1.0e+00": 1.5366238355636597, "validation/loss_013_lr1.7e-01_wd1.0e+00": 1.3753591775894165, "validation/loss_014_lr2.0e-01_wd1.0e+00": 1.242974042892456, "validation/loss_015_lr2.3e-01_wd1.0e+00": 1.1328667402267456, "validation/loss_016_lr2.7e-01_wd1.0e+00": 1.0130820274353027, "validation/loss_017_lr3.2e-01_wd1.0e+00": 0.8948892951011658, "validation/loss_018_lr3.8e-01_wd1.0e+00": 0.7860445380210876, "validation/loss_019_lr4.4e-01_wd1.0e+00": 0.701975405216217, "validation/loss_020_lr5.2e-01_wd1.0e+00": 0.6166993379592896, "validation/loss_021_lr6.1e-01_wd1.0e+00": 0.5451077222824097, "validation/loss_022_lr7.2e-01_wd1.0e+00": 0.48064249753952026, "validation/loss_023_lr8.5e-01_wd1.0e+00": 0.42563802003860474, "validation/loss_024_lr1.0e+00_wd1.0e+00": 0.3798462152481079, "validation/loss_025_lr1.2e+00_wd1.0e+00": 0.3370305597782135, "validation/loss_026_lr1.4e+00_wd1.0e+00": 0.30657050013542175, "validation/loss_027_lr1.6e+00_wd1.0e+00": 0.2839013934135437, "validation/loss_028_lr1.9e+00_wd1.0e+00": 0.2590232789516449, "validation/loss_029_lr2.3e+00_wd1.0e+00": 0.23609645664691925, "validation/loss_030_lr2.7e+00_wd1.0e+00": 0.21988436579704285, "validation/loss_031_lr3.1e+00_wd1.0e+00": 0.2078714817762375, "validation/loss_032_lr3.7e+00_wd1.0e+00": 0.19436681270599365, "validation/loss_033_lr4.3e+00_wd1.0e+00": 0.18467819690704346, "validation/loss_034_lr5.1e+00_wd1.0e+00": 0.1750245839357376, "validation/loss_035_lr6.0e+00_wd1.0e+00": 0.16704942286014557, "validation/loss_036_lr7.1e+00_wd1.0e+00": 0.1599137932062149, "validation/loss_037_lr8.3e+00_wd1.0e+00": 0.1540517359972, "validation/loss_038_lr9.8e+00_wd1.0e+00": 0.14865858852863312, "validation/loss_039_lr1.2e+01_wd1.0e+00": 0.14302325248718262, "validation/loss_040_lr1.4e+01_wd1.0e+00": 0.1393805593252182, "validation/loss_041_lr1.6e+01_wd1.0e+00": 0.13644427061080933, "validation/loss_042_lr1.9e+01_wd1.0e+00": 0.1332729607820511, "validation/loss_043_lr2.2e+01_wd1.0e+00": 0.13089218735694885, "validation/loss_044_lr2.6e+01_wd1.0e+00": 0.12860070168972015, "validation/loss_045_lr3.1e+01_wd1.0e+00": 0.12653502821922302, "validation/loss_046_lr3.6e+01_wd1.0e+00": 0.12504182755947113, "validation/loss_047_lr4.3e+01_wd1.0e+00": 0.12352041900157928, "validation/loss_048_lr5.0e+01_wd1.0e+00": 0.12249380350112915, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.27058531746031744, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.28000992063492064, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.3013392857142857, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.3209325396825397, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.33581349206349204, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.3531746031746032, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.37524801587301587, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.4104662698412698, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.4930555555555556, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.5652281746031746, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.6195436507936508, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.6929563492063492, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.7648809523809523, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.8387896825396826, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.8774801587301587, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.8953373015873016, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.9060019841269841, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.9122023809523809, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.917906746031746, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.9216269841269841, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.9255952380952381, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.9275793650793651, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.9305555555555556, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.9322916666666666, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.9330357142857143, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.9375, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.9407242063492064, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.9422123015873016, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.9434523809523809, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.9471726190476191, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.9501488095238095, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.9521329365079365, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.9536210317460317, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.9548611111111112, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.9561011904761905, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.9585813492063492, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.9593253968253969, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.9603174603174603, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.9610615079365079, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.9620535714285714, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.9627976190476191, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.9625496031746031, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.9618055555555556, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.9630456349206349, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.9630456349206349, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.10934316551628186, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.11787272214020324, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.13212048377309657, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.1424963731455644, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.15089292634981405, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.15915150938453712, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.18165475353303254, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.22716297649291717, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.3242609784203972, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.4034292004688185, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.48164875015857705, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.6175128338772646, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.7430299799413428, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.8374568450304147, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.8759007070745722, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.8911844398007561, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.9010606326514348, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.90649507406416, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.911669486883192, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.9156401123409568, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.9185442510056335, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.9207816779037917, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.9248073562777909, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.9270940118216965, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.9287754669855155, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.9334615254143023, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.9363916980216986, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.9386388693047084, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.9395977249159041, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.9438047918945225, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.9463889817730601, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.9480999427118357, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.9490981866288789, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.9502926976028899, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.9514888936181161, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.9537045888683705, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.9547352738044944, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.9562490290106127, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.956975886836067, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.9583324063509158, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.95835477155597, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.9584785764155561, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.9587448415288574, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.9587308584779021, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.9585906997245599, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.9577080785230377, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.9577089988711249, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.9588233560039492, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.9587593093495832, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 0.07998842821456492, "validation/loss_best": 0.12352041900157928, "validation/acc_best": 0.9630456349206349, "validation/f1_best": 0.9588233560039492} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/config.yaml b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..783c2794e746216af51d56148ee12d1f398b6490 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..ecee347857a47da342e9645df23d46d88288a4c6 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 13, "eval/id_best": 26, "eval/lr_best": 0.00041999999999999996, "eval/wd_best": 0.05, "eval/train/loss": 2.0554676055908203, "eval/train/acc": 0.37637911429361687, "eval/train/acc_std": 0.0024195795059926135, "eval/train/f1": 0.3161793295740971, "eval/train/f1_std": 0.002509909122359917, "eval/validation/loss": 2.4422013759613037, "eval/validation/acc": 0.28183831672203763, "eval/validation/acc_std": 0.005374191153467242, "eval/validation/f1": 0.21507144587847712, "eval/validation/f1_std": 0.004902225130186002, "eval/test/loss": 2.4777956008911133, "eval/test/acc": 0.25769944341372913, "eval/test/acc_std": 0.004786675569052382, "eval/test/f1": 0.19012978393637714, "eval/test/f1_std": 0.004730094851710683, "eval/testid/loss": 2.2359120845794678, "eval/testid/acc": 0.3209947946790052, "eval/testid/acc_std": 0.00572681858401502, "eval/testid/f1": 0.26373491718349285, "eval/testid/f1_std": 0.00570836447384588} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..9b4f8ea344998234c06247306274c7a173a060e4 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 13, "eval/best/id_best": 26, "eval/best/lr_best": 0.00041999999999999996, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.0554676055908203, "eval/best/train/acc": 0.37637911429361687, "eval/best/train/acc_std": 0.0024195795059926135, "eval/best/train/f1": 0.3161793295740971, "eval/best/train/f1_std": 0.002509909122359917, "eval/best/validation/loss": 2.4422013759613037, "eval/best/validation/acc": 0.28183831672203763, "eval/best/validation/acc_std": 0.005374191153467242, "eval/best/validation/f1": 0.21507144587847712, "eval/best/validation/f1_std": 0.004902225130186002, "eval/best/test/loss": 2.4777956008911133, "eval/best/test/acc": 0.25769944341372913, "eval/best/test/acc_std": 0.004786675569052382, "eval/best/test/f1": 0.19012978393637714, "eval/best/test/f1_std": 0.004730094851710683, "eval/best/testid/loss": 2.2359120845794678, "eval/best/testid/acc": 0.3209947946790052, "eval/best/testid/acc_std": 0.00572681858401502, "eval/best/testid/f1": 0.26373491718349285, "eval/best/testid/f1_std": 0.00570836447384588} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..7b884c5ed25be413f9ec28b4644693cd6dda9e6c --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 24, "eval/last/lr_best": 0.0003, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.1095664501190186, "eval/last/train/acc": 0.3623344294538861, "eval/last/train/acc_std": 0.002306558749967573, "eval/last/train/f1": 0.30073556622010106, "eval/last/train/f1_std": 0.002356145280090068, "eval/last/validation/loss": 2.421489953994751, "eval/last/validation/acc": 0.27593207825765964, "eval/last/validation/acc_std": 0.005302239746164288, "eval/last/validation/f1": 0.20931114368656611, "eval/last/validation/f1_std": 0.0045875710397123995, "eval/last/test/loss": 2.431932210922241, "eval/last/test/acc": 0.2660482374768089, "eval/last/test/acc_std": 0.005018244305480431, "eval/last/test/f1": 0.20665364925075722, "eval/last/test/f1_std": 0.004845294007299649, "eval/last/testid/loss": 2.2549822330474854, "eval/last/testid/acc": 0.31617505301715826, "eval/last/testid/acc_std": 0.006165223405809169, "eval/last/testid/f1": 0.25907689838488673, "eval/last/testid/f1_std": 0.006007614026091455} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..de1f57d76555d2b43be3dada592cdf09bc598b2c --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",train,2.0554676055908203,0.37637911429361687,0.0024195795059926135,0.3161793295740971,0.002509909122359917 +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",validation,2.4422013759613037,0.28183831672203763,0.005374191153467242,0.21507144587847712,0.004902225130186002 +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",test,2.4777956008911133,0.25769944341372913,0.004786675569052382,0.19012978393637714,0.004730094851710683 +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",testid,2.2359120845794678,0.3209947946790052,0.00572681858401502,0.26373491718349285,0.00570836447384588 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..de1f57d76555d2b43be3dada592cdf09bc598b2c --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",train,2.0554676055908203,0.37637911429361687,0.0024195795059926135,0.3161793295740971,0.002509909122359917 +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",validation,2.4422013759613037,0.28183831672203763,0.005374191153467242,0.21507144587847712,0.004902225130186002 +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",test,2.4777956008911133,0.25769944341372913,0.004786675569052382,0.19012978393637714,0.004730094851710683 +flat_mae,patch,attn,nsd_cococlip,best,13,0.00041999999999999996,0.05,26,"[1.4, 1.0]",testid,2.2359120845794678,0.3209947946790052,0.00572681858401502,0.26373491718349285,0.00570836447384588 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..937902b5ce35a7fa99ab0818ca5b7fd79c5bcc2f --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,attn,nsd_cococlip,last,19,0.0003,0.05,24,"[1, 1.0]",train,2.1095664501190186,0.3623344294538861,0.002306558749967573,0.30073556622010106,0.002356145280090068 +flat_mae,patch,attn,nsd_cococlip,last,19,0.0003,0.05,24,"[1, 1.0]",validation,2.421489953994751,0.27593207825765964,0.005302239746164288,0.20931114368656611,0.0045875710397123995 +flat_mae,patch,attn,nsd_cococlip,last,19,0.0003,0.05,24,"[1, 1.0]",test,2.431932210922241,0.2660482374768089,0.005018244305480431,0.20665364925075722,0.004845294007299649 +flat_mae,patch,attn,nsd_cococlip,last,19,0.0003,0.05,24,"[1, 1.0]",testid,2.2549822330474854,0.31617505301715826,0.006165223405809169,0.25907689838488673,0.006007614026091455 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/log.txt b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2f89aaf151f5ce8ee614590e2bf473178889245d --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/log.txt @@ -0,0 +1,1507 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 22:46:31 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:26:07 lr: nan time: 3.9187 data: 3.4077 max mem: 21742 +train: [0] [ 20/400] eta: 0:04:01 lr: 0.000003 loss: 3.1828 (3.1813) grad: 0.0683 (0.0645) time: 0.4705 data: 0.0031 max mem: 22449 +train: [0] [ 40/400] eta: 0:03:18 lr: 0.000006 loss: 3.1785 (3.1788) grad: 0.0707 (0.0697) time: 0.4618 data: 0.0048 max mem: 22449 +train: [0] [ 60/400] eta: 0:02:59 lr: 0.000009 loss: 3.1716 (3.1733) grad: 0.0707 (0.0689) time: 0.4817 data: 0.0051 max mem: 22449 +train: [0] [ 80/400] eta: 0:02:44 lr: 0.000012 loss: 3.1641 (3.1724) grad: 0.0628 (0.0670) time: 0.4720 data: 0.0050 max mem: 22449 +train: [0] [100/400] eta: 0:02:30 lr: 0.000015 loss: 3.1666 (3.1709) grad: 0.0628 (0.0663) time: 0.4524 data: 0.0048 max mem: 22449 +train: [0] [120/400] eta: 0:02:20 lr: 0.000018 loss: 3.1616 (3.1710) grad: 0.0680 (0.0668) time: 0.5020 data: 0.0053 max mem: 22449 +train: [0] [140/400] eta: 0:02:09 lr: 0.000021 loss: 3.1595 (3.1690) grad: 0.0698 (0.0673) time: 0.4699 data: 0.0049 max mem: 22449 +train: [0] [160/400] eta: 0:01:58 lr: 0.000024 loss: 3.1545 (3.1684) grad: 0.0674 (0.0666) time: 0.4714 data: 0.0050 max mem: 22449 +train: [0] [180/400] eta: 0:01:48 lr: 0.000027 loss: 3.1480 (3.1654) grad: 0.0667 (0.0668) time: 0.4863 data: 0.0053 max mem: 22449 +train: [0] [200/400] eta: 0:01:38 lr: 0.000030 loss: 3.1379 (3.1627) grad: 0.0667 (0.0666) time: 0.4862 data: 0.0049 max mem: 22449 +train: [0] [220/400] eta: 0:01:28 lr: 0.000033 loss: 3.1485 (3.1617) grad: 0.0660 (0.0665) time: 0.4543 data: 0.0049 max mem: 22449 +train: [0] [240/400] eta: 0:01:17 lr: 0.000036 loss: 3.1508 (3.1606) grad: 0.0659 (0.0662) time: 0.4670 data: 0.0050 max mem: 22449 +train: [0] [260/400] eta: 0:01:07 lr: 0.000039 loss: 3.1514 (3.1603) grad: 0.0666 (0.0665) time: 0.4613 data: 0.0050 max mem: 22449 +train: [0] [280/400] eta: 0:00:57 lr: 0.000042 loss: 3.1490 (3.1592) grad: 0.0667 (0.0665) time: 0.4542 data: 0.0050 max mem: 22449 +train: [0] [300/400] eta: 0:00:48 lr: 0.000045 loss: 3.1539 (3.1592) grad: 0.0599 (0.0659) time: 0.4560 data: 0.0048 max mem: 22449 +train: [0] [320/400] eta: 0:00:38 lr: 0.000048 loss: 3.1513 (3.1587) grad: 0.0577 (0.0657) time: 0.4565 data: 0.0050 max mem: 22449 +train: [0] [340/400] eta: 0:00:28 lr: 0.000051 loss: 3.1486 (3.1585) grad: 0.0594 (0.0653) time: 0.4517 data: 0.0049 max mem: 22449 +train: [0] [360/400] eta: 0:00:19 lr: 0.000054 loss: 3.1440 (3.1578) grad: 0.0608 (0.0652) time: 0.4482 data: 0.0049 max mem: 22449 +train: [0] [380/400] eta: 0:00:09 lr: 0.000057 loss: 3.1471 (3.1576) grad: 0.0629 (0.0652) time: 0.4476 data: 0.0048 max mem: 22449 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1561 (3.1574) grad: 0.0629 (0.0651) time: 0.4459 data: 0.0047 max mem: 22449 +train: [0] Total time: 0:03:09 (0.4741 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1561 (3.1574) grad: 0.0629 (0.0651) +eval (validation): [0] [ 0/85] eta: 0:04:37 time: 3.2672 data: 2.9802 max mem: 22449 +eval (validation): [0] [20/85] eta: 0:00:31 time: 0.3478 data: 0.0045 max mem: 22449 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3510 data: 0.0036 max mem: 22449 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3221 data: 0.0040 max mem: 22449 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3430 data: 0.0040 max mem: 22449 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3466 data: 0.0043 max mem: 22449 +eval (validation): [0] Total time: 0:00:32 (0.3815 s / it) +cv: [0] best hparam: (0.17, 1.0) (013) ('013_lr1.7e-01_wd1.0e+00') loss: 3.140 acc: 0.073 f1: 0.010 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:37 lr: nan time: 3.3948 data: 3.0004 max mem: 22449 +train: [1] [ 20/400] eta: 0:03:47 lr: 0.000063 loss: 3.1331 (3.1383) grad: 0.0585 (0.0569) time: 0.4588 data: 0.0036 max mem: 22449 +train: [1] [ 40/400] eta: 0:03:10 lr: 0.000066 loss: 3.1351 (3.1371) grad: 0.0585 (0.0587) time: 0.4537 data: 0.0046 max mem: 22449 +train: [1] [ 60/400] eta: 0:02:53 lr: 0.000069 loss: 3.1434 (3.1358) grad: 0.0591 (0.0603) time: 0.4706 data: 0.0053 max mem: 22449 +train: [1] [ 80/400] eta: 0:02:39 lr: 0.000072 loss: 3.1494 (3.1412) grad: 0.0660 (0.0622) time: 0.4647 data: 0.0050 max mem: 22449 +train: [1] [100/400] eta: 0:02:26 lr: 0.000075 loss: 3.1366 (3.1389) grad: 0.0660 (0.0628) time: 0.4517 data: 0.0048 max mem: 22449 +train: [1] [120/400] eta: 0:02:15 lr: 0.000078 loss: 3.1366 (3.1419) grad: 0.0650 (0.0633) time: 0.4480 data: 0.0047 max mem: 22449 +train: [1] [140/400] eta: 0:02:03 lr: 0.000081 loss: 3.1568 (3.1412) grad: 0.0667 (0.0645) time: 0.4435 data: 0.0050 max mem: 22449 +train: [1] [160/400] eta: 0:01:53 lr: 0.000084 loss: 3.1260 (3.1406) grad: 0.0711 (0.0653) time: 0.4528 data: 0.0048 max mem: 22449 +train: [1] [180/400] eta: 0:01:43 lr: 0.000087 loss: 3.1354 (3.1408) grad: 0.0719 (0.0661) time: 0.4505 data: 0.0049 max mem: 22449 +train: [1] [200/400] eta: 0:01:33 lr: 0.000090 loss: 3.1305 (3.1387) grad: 0.0725 (0.0671) time: 0.4500 data: 0.0050 max mem: 22449 +train: [1] [220/400] eta: 0:01:24 lr: 0.000093 loss: 3.1264 (3.1382) grad: 0.0805 (0.0693) time: 0.4432 data: 0.0047 max mem: 22449 +train: [1] [240/400] eta: 0:01:14 lr: 0.000096 loss: 3.1348 (3.1376) grad: 0.0812 (0.0704) time: 0.4500 data: 0.0048 max mem: 22449 +train: [1] [260/400] eta: 0:01:04 lr: 0.000099 loss: 3.1226 (3.1355) grad: 0.0787 (0.0714) time: 0.4434 data: 0.0046 max mem: 22449 +train: [1] [280/400] eta: 0:00:55 lr: 0.000102 loss: 3.1214 (3.1345) grad: 0.0793 (0.0722) time: 0.4632 data: 0.0049 max mem: 22449 +train: [1] [300/400] eta: 0:00:46 lr: 0.000105 loss: 3.1186 (3.1334) grad: 0.0793 (0.0732) time: 0.4421 data: 0.0045 max mem: 22449 +train: [1] [320/400] eta: 0:00:36 lr: 0.000108 loss: 3.1166 (3.1326) grad: 0.0884 (0.0749) time: 0.4345 data: 0.0047 max mem: 22449 +train: [1] [340/400] eta: 0:00:27 lr: 0.000111 loss: 3.1121 (3.1310) grad: 0.0892 (0.0757) time: 0.4782 data: 0.0051 max mem: 22449 +train: [1] [360/400] eta: 0:00:18 lr: 0.000114 loss: 3.1034 (3.1292) grad: 0.0952 (0.0782) time: 0.4524 data: 0.0051 max mem: 22449 +train: [1] [380/400] eta: 0:00:09 lr: 0.000117 loss: 3.0889 (3.1270) grad: 0.1045 (0.0802) time: 0.4478 data: 0.0050 max mem: 22449 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.0910 (3.1258) grad: 0.1304 (0.0833) time: 0.4672 data: 0.0050 max mem: 22449 +train: [1] Total time: 0:03:04 (0.4611 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.0910 (3.1258) grad: 0.1304 (0.0833) +eval (validation): [1] [ 0/85] eta: 0:04:44 time: 3.3483 data: 3.0589 max mem: 22449 +eval (validation): [1] [20/85] eta: 0:00:31 time: 0.3445 data: 0.0038 max mem: 22449 +eval (validation): [1] [40/85] eta: 0:00:18 time: 0.3427 data: 0.0042 max mem: 22449 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3426 data: 0.0045 max mem: 22449 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3320 data: 0.0047 max mem: 22449 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3226 data: 0.0046 max mem: 22449 +eval (validation): [1] Total time: 0:00:32 (0.3785 s / it) +cv: [1] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 2.857 acc: 0.167 f1: 0.109 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:00 lr: nan time: 3.3004 data: 2.9576 max mem: 22449 +train: [2] [ 20/400] eta: 0:03:42 lr: 0.000123 loss: 3.0623 (3.0778) grad: 0.0995 (0.1035) time: 0.4495 data: 0.0048 max mem: 22449 +train: [2] [ 40/400] eta: 0:03:05 lr: 0.000126 loss: 3.0709 (3.0893) grad: 0.1085 (0.1105) time: 0.4427 data: 0.0045 max mem: 22449 +train: [2] [ 60/400] eta: 0:02:47 lr: 0.000129 loss: 3.0682 (3.0826) grad: 0.1176 (0.1132) time: 0.4424 data: 0.0050 max mem: 22449 +train: [2] [ 80/400] eta: 0:02:33 lr: 0.000132 loss: 3.0484 (3.0724) grad: 0.1223 (0.1174) time: 0.4457 data: 0.0051 max mem: 22449 +train: [2] [100/400] eta: 0:02:22 lr: 0.000135 loss: 3.0484 (3.0701) grad: 0.1223 (0.1174) time: 0.4480 data: 0.0051 max mem: 22449 +train: [2] [120/400] eta: 0:02:11 lr: 0.000138 loss: 3.0470 (3.0653) grad: 0.1264 (0.1206) time: 0.4390 data: 0.0050 max mem: 22449 +train: [2] [140/400] eta: 0:02:01 lr: 0.000141 loss: 3.0470 (3.0616) grad: 0.1291 (0.1214) time: 0.4667 data: 0.0052 max mem: 22449 +train: [2] [160/400] eta: 0:01:51 lr: 0.000144 loss: 3.0475 (3.0595) grad: 0.1200 (0.1223) time: 0.4496 data: 0.0050 max mem: 22449 +train: [2] [180/400] eta: 0:01:41 lr: 0.000147 loss: 3.0585 (3.0604) grad: 0.1289 (0.1241) time: 0.4327 data: 0.0048 max mem: 22449 +train: [2] [200/400] eta: 0:01:32 lr: 0.000150 loss: 3.0553 (3.0595) grad: 0.1427 (0.1274) time: 0.4496 data: 0.0051 max mem: 22449 +train: [2] [220/400] eta: 0:01:22 lr: 0.000153 loss: 3.0743 (3.0632) grad: 0.1666 (0.1347) time: 0.4510 data: 0.0050 max mem: 22449 +train: [2] [240/400] eta: 0:01:13 lr: 0.000156 loss: 3.1138 (3.0761) grad: 0.2388 (0.1648) time: 0.4506 data: 0.0050 max mem: 22449 +train: [2] [260/400] eta: 0:01:04 lr: 0.000159 loss: 3.4215 (3.1364) grad: 0.7961 (0.2480) time: 0.4571 data: 0.0048 max mem: 22449 +WARNING: classifier 48 (50, 1.0) diverged (loss=71.20 > 63.56) at step 531. Freezing. +train: [2] [280/400] eta: 0:00:55 lr: 0.000162 loss: 3.4215 (3.1359) grad: 0.8101 (0.2497) time: 0.4791 data: 0.0053 max mem: 22449 +train: [2] [300/400] eta: 0:00:45 lr: 0.000165 loss: 3.0029 (3.1278) grad: 0.1298 (0.2426) time: 0.4475 data: 0.0050 max mem: 22449 +train: [2] [320/400] eta: 0:00:36 lr: 0.000168 loss: 3.0108 (3.1206) grad: 0.1387 (0.2358) time: 0.4750 data: 0.0050 max mem: 22449 +train: [2] [340/400] eta: 0:00:27 lr: 0.000171 loss: 3.0246 (3.1156) grad: 0.1211 (0.2296) time: 0.4564 data: 0.0049 max mem: 22449 +train: [2] [360/400] eta: 0:00:18 lr: 0.000174 loss: 3.0246 (3.1091) grad: 0.1232 (0.2240) time: 0.4613 data: 0.0052 max mem: 22449 +train: [2] [380/400] eta: 0:00:09 lr: 0.000177 loss: 2.9990 (3.1033) grad: 0.1213 (0.2184) time: 0.4466 data: 0.0050 max mem: 22449 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.0005 (3.0980) grad: 0.1245 (0.2143) time: 0.4811 data: 0.0051 max mem: 22449 +train: [2] Total time: 0:03:04 (0.4612 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.0005 (3.0980) grad: 0.1245 (0.2143) +eval (validation): [2] [ 0/85] eta: 0:04:33 time: 3.2222 data: 2.9311 max mem: 22449 +eval (validation): [2] [20/85] eta: 0:00:32 time: 0.3613 data: 0.0060 max mem: 22449 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3400 data: 0.0031 max mem: 22449 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3514 data: 0.0038 max mem: 22449 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3417 data: 0.0041 max mem: 22449 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3294 data: 0.0039 max mem: 22449 +eval (validation): [2] Total time: 0:00:32 (0.3844 s / it) +cv: [2] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 2.598 acc: 0.217 f1: 0.160 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:13 lr: nan time: 3.3335 data: 2.9385 max mem: 22449 +train: [3] [ 20/400] eta: 0:03:48 lr: 0.000183 loss: 2.9777 (2.9767) grad: 0.1440 (0.1528) time: 0.4641 data: 0.0052 max mem: 22449 +train: [3] [ 40/400] eta: 0:03:09 lr: 0.000186 loss: 2.9711 (2.9771) grad: 0.1449 (0.1500) time: 0.4473 data: 0.0047 max mem: 22449 +train: [3] [ 60/400] eta: 0:02:52 lr: 0.000189 loss: 2.9838 (2.9884) grad: 0.1549 (0.1593) time: 0.4678 data: 0.0051 max mem: 22449 +train: [3] [ 80/400] eta: 0:02:38 lr: 0.000192 loss: 3.0473 (3.0465) grad: 0.2190 (0.2504) time: 0.4570 data: 0.0051 max mem: 22449 +WARNING: classifier 47 (43, 1.0) diverged (loss=67.60 > 63.56) at step 647. Freezing. +train: [3] [100/400] eta: 0:02:25 lr: 0.000195 loss: 3.3335 (3.1584) grad: 0.5859 (0.3882) time: 0.4461 data: 0.0048 max mem: 22449 +train: [3] [120/400] eta: 0:02:15 lr: 0.000198 loss: 3.0403 (3.1287) grad: 0.1545 (0.3475) time: 0.4683 data: 0.0052 max mem: 22449 +train: [3] [140/400] eta: 0:02:04 lr: 0.000201 loss: 2.9837 (3.1109) grad: 0.1477 (0.3192) time: 0.4518 data: 0.0052 max mem: 22449 +train: [3] [160/400] eta: 0:01:53 lr: 0.000204 loss: 3.0002 (3.0974) grad: 0.1558 (0.2996) time: 0.4484 data: 0.0052 max mem: 22449 +train: [3] [180/400] eta: 0:01:43 lr: 0.000207 loss: 2.9881 (3.0847) grad: 0.1508 (0.2822) time: 0.4487 data: 0.0052 max mem: 22449 +train: [3] [200/400] eta: 0:01:34 lr: 0.000210 loss: 2.9700 (3.0739) grad: 0.1457 (0.2690) time: 0.4597 data: 0.0052 max mem: 22449 +train: [3] [220/400] eta: 0:01:24 lr: 0.000213 loss: 2.9700 (3.0656) grad: 0.1498 (0.2599) time: 0.4440 data: 0.0049 max mem: 22449 +train: [3] [240/400] eta: 0:01:14 lr: 0.000216 loss: 2.9715 (3.0586) grad: 0.1455 (0.2501) time: 0.4681 data: 0.0051 max mem: 22449 +train: [3] [260/400] eta: 0:01:05 lr: 0.000219 loss: 2.9780 (3.0528) grad: 0.1442 (0.2423) time: 0.4419 data: 0.0050 max mem: 22449 +train: [3] [280/400] eta: 0:00:55 lr: 0.000222 loss: 2.9765 (3.0467) grad: 0.1460 (0.2358) time: 0.4595 data: 0.0050 max mem: 22449 +train: [3] [300/400] eta: 0:00:46 lr: 0.000225 loss: 2.9371 (3.0409) grad: 0.1508 (0.2305) time: 0.4564 data: 0.0050 max mem: 22449 +train: [3] [320/400] eta: 0:00:37 lr: 0.000228 loss: 2.9269 (3.0336) grad: 0.1583 (0.2265) time: 0.4767 data: 0.0052 max mem: 22449 +train: [3] [340/400] eta: 0:00:27 lr: 0.000231 loss: 2.9654 (3.0337) grad: 0.1784 (0.2277) time: 0.4485 data: 0.0052 max mem: 22449 +train: [3] [360/400] eta: 0:00:18 lr: 0.000234 loss: 3.0629 (3.0447) grad: 0.2959 (0.2488) time: 0.4463 data: 0.0050 max mem: 22449 +WARNING: classifier 46 (36, 1.0) diverged (loss=66.67 > 63.56) at step 785. Freezing. +train: [3] [380/400] eta: 0:00:09 lr: 0.000237 loss: 3.1703 (3.0624) grad: 0.4725 (0.2675) time: 0.4436 data: 0.0049 max mem: 22449 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.9507 (3.0560) grad: 0.1441 (0.2615) time: 0.4489 data: 0.0050 max mem: 22449 +train: [3] Total time: 0:03:05 (0.4625 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.9507 (3.0560) grad: 0.1441 (0.2615) +eval (validation): [3] [ 0/85] eta: 0:04:54 time: 3.4690 data: 3.1996 max mem: 22449 +eval (validation): [3] [20/85] eta: 0:00:32 time: 0.3543 data: 0.0043 max mem: 22449 +eval (validation): [3] [40/85] eta: 0:00:19 time: 0.3407 data: 0.0035 max mem: 22449 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3513 data: 0.0046 max mem: 22449 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3263 data: 0.0042 max mem: 22449 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3207 data: 0.0042 max mem: 22449 +eval (validation): [3] Total time: 0:00:32 (0.3827 s / it) +cv: [3] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 2.503 acc: 0.247 f1: 0.180 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:45 lr: nan time: 3.4134 data: 3.0239 max mem: 22449 +train: [4] [ 20/400] eta: 0:03:42 lr: 0.000243 loss: 2.8932 (2.9293) grad: 0.1413 (0.1472) time: 0.4430 data: 0.0036 max mem: 22449 +train: [4] [ 40/400] eta: 0:03:04 lr: 0.000246 loss: 2.9102 (2.9275) grad: 0.1453 (0.1536) time: 0.4393 data: 0.0047 max mem: 22449 +train: [4] [ 60/400] eta: 0:02:48 lr: 0.000249 loss: 2.9252 (2.9204) grad: 0.1534 (0.1537) time: 0.4621 data: 0.0054 max mem: 22449 +train: [4] [ 80/400] eta: 0:02:35 lr: 0.000252 loss: 2.9579 (2.9357) grad: 0.1565 (0.1571) time: 0.4535 data: 0.0051 max mem: 22449 +train: [4] [100/400] eta: 0:02:22 lr: 0.000255 loss: 2.9480 (2.9347) grad: 0.1746 (0.1611) time: 0.4383 data: 0.0048 max mem: 22449 +train: [4] [120/400] eta: 0:02:13 lr: 0.000258 loss: 2.9304 (2.9365) grad: 0.1896 (0.1680) time: 0.4703 data: 0.0051 max mem: 22449 +train: [4] [140/400] eta: 0:02:03 lr: 0.000261 loss: 2.9573 (2.9402) grad: 0.2114 (0.1809) time: 0.4607 data: 0.0051 max mem: 22449 +train: [4] [160/400] eta: 0:01:53 lr: 0.000264 loss: 3.0282 (2.9695) grad: 0.3707 (0.2256) time: 0.4618 data: 0.0052 max mem: 22449 +train: [4] [180/400] eta: 0:01:43 lr: 0.000267 loss: 3.3288 (3.0435) grad: 0.8230 (0.3127) time: 0.4594 data: 0.0052 max mem: 22449 +WARNING: classifier 44 (26, 1.0) diverged (loss=80.00 > 63.56) at step 900. Freezing. +train: [4] [200/400] eta: 0:01:33 lr: 0.000270 loss: 3.7188 (3.1328) grad: 1.1898 (0.4239) time: 0.4501 data: 0.0048 max mem: 22449 +train: [4] [220/400] eta: 0:01:24 lr: 0.000273 loss: 3.0021 (3.1129) grad: 0.1663 (0.3983) time: 0.4492 data: 0.0050 max mem: 22449 +train: [4] [240/400] eta: 0:01:14 lr: 0.000276 loss: 2.9183 (3.0978) grad: 0.1481 (0.3781) time: 0.4613 data: 0.0051 max mem: 22449 +train: [4] [260/400] eta: 0:01:05 lr: 0.000279 loss: 2.9105 (3.0843) grad: 0.1481 (0.3600) time: 0.4415 data: 0.0050 max mem: 22449 +train: [4] [280/400] eta: 0:00:55 lr: 0.000282 loss: 2.8930 (3.0714) grad: 0.1461 (0.3451) time: 0.4478 data: 0.0050 max mem: 22449 +train: [4] [300/400] eta: 0:00:46 lr: 0.000285 loss: 2.8982 (3.0619) grad: 0.1520 (0.3330) time: 0.4655 data: 0.0054 max mem: 22449 +train: [4] [320/400] eta: 0:00:37 lr: 0.000288 loss: 2.9157 (3.0534) grad: 0.1522 (0.3223) time: 0.4516 data: 0.0050 max mem: 22449 +train: [4] [340/400] eta: 0:00:27 lr: 0.000291 loss: 2.9194 (3.0439) grad: 0.1483 (0.3121) time: 0.4506 data: 0.0049 max mem: 22449 +train: [4] [360/400] eta: 0:00:18 lr: 0.000294 loss: 2.9161 (3.0378) grad: 0.1468 (0.3031) time: 0.4651 data: 0.0052 max mem: 22449 +train: [4] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.9306 (3.0303) grad: 0.1468 (0.2952) time: 0.4632 data: 0.0053 max mem: 22449 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.8872 (3.0228) grad: 0.1576 (0.2889) time: 0.4660 data: 0.0052 max mem: 22449 +train: [4] Total time: 0:03:05 (0.4629 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.8872 (3.0228) grad: 0.1576 (0.2889) +eval (validation): [4] [ 0/85] eta: 0:04:40 time: 3.2988 data: 3.0490 max mem: 22449 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3557 data: 0.0054 max mem: 22449 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3425 data: 0.0034 max mem: 22449 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3433 data: 0.0043 max mem: 22449 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3235 data: 0.0042 max mem: 22449 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3196 data: 0.0041 max mem: 22449 +eval (validation): [4] Total time: 0:00:32 (0.3778 s / it) +cv: [4] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.495 acc: 0.241 f1: 0.173 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:54 lr: nan time: 3.4374 data: 3.0806 max mem: 22449 +train: [5] [ 20/400] eta: 0:03:44 lr: 0.000300 loss: 2.8514 (2.8596) grad: 0.1388 (0.1458) time: 0.4486 data: 0.0047 max mem: 22449 +train: [5] [ 40/400] eta: 0:03:08 lr: 0.000300 loss: 2.8514 (2.8634) grad: 0.1424 (0.1468) time: 0.4556 data: 0.0046 max mem: 22449 +train: [5] [ 60/400] eta: 0:02:49 lr: 0.000300 loss: 2.8643 (2.8785) grad: 0.1548 (0.1538) time: 0.4428 data: 0.0049 max mem: 22449 +train: [5] [ 80/400] eta: 0:02:35 lr: 0.000300 loss: 2.8809 (2.8808) grad: 0.1616 (0.1548) time: 0.4466 data: 0.0052 max mem: 22449 +train: [5] [100/400] eta: 0:02:23 lr: 0.000300 loss: 2.9080 (2.8986) grad: 0.1782 (0.1815) time: 0.4543 data: 0.0050 max mem: 22449 +train: [5] [120/400] eta: 0:02:12 lr: 0.000300 loss: 3.0272 (2.9772) grad: 0.4295 (0.2968) time: 0.4472 data: 0.0048 max mem: 22449 +WARNING: classifier 45 (31, 1.0) diverged (loss=67.57 > 63.56) at step 1061. Freezing. +train: [5] [140/400] eta: 0:02:02 lr: 0.000300 loss: 3.0076 (2.9835) grad: 0.4886 (0.3038) time: 0.4540 data: 0.0051 max mem: 22449 +train: [5] [160/400] eta: 0:01:52 lr: 0.000299 loss: 2.9007 (2.9762) grad: 0.1582 (0.2851) time: 0.4482 data: 0.0051 max mem: 22449 +train: [5] [180/400] eta: 0:01:42 lr: 0.000299 loss: 2.8592 (2.9604) grad: 0.1540 (0.2711) time: 0.4421 data: 0.0051 max mem: 22449 +train: [5] [200/400] eta: 0:01:32 lr: 0.000299 loss: 2.8427 (2.9501) grad: 0.1484 (0.2577) time: 0.4298 data: 0.0046 max mem: 22449 +train: [5] [220/400] eta: 0:01:22 lr: 0.000299 loss: 2.8471 (2.9433) grad: 0.1412 (0.2487) time: 0.4483 data: 0.0048 max mem: 22449 +train: [5] [240/400] eta: 0:01:13 lr: 0.000299 loss: 2.8729 (2.9385) grad: 0.1529 (0.2411) time: 0.4484 data: 0.0050 max mem: 22449 +train: [5] [260/400] eta: 0:01:04 lr: 0.000299 loss: 2.8803 (2.9344) grad: 0.1493 (0.2338) time: 0.4288 data: 0.0045 max mem: 22449 +train: [5] [280/400] eta: 0:00:54 lr: 0.000298 loss: 2.8746 (2.9313) grad: 0.1513 (0.2294) time: 0.4387 data: 0.0049 max mem: 22449 +train: [5] [300/400] eta: 0:00:45 lr: 0.000298 loss: 2.8721 (2.9270) grad: 0.1698 (0.2253) time: 0.4437 data: 0.0048 max mem: 22449 +train: [5] [320/400] eta: 0:00:36 lr: 0.000298 loss: 2.8355 (2.9220) grad: 0.1561 (0.2202) time: 0.4347 data: 0.0050 max mem: 22449 +train: [5] [340/400] eta: 0:00:27 lr: 0.000298 loss: 2.8801 (2.9193) grad: 0.1373 (0.2155) time: 0.4328 data: 0.0047 max mem: 22449 +train: [5] [360/400] eta: 0:00:18 lr: 0.000297 loss: 2.8751 (2.9165) grad: 0.1523 (0.2125) time: 0.4264 data: 0.0047 max mem: 22449 +train: [5] [380/400] eta: 0:00:09 lr: 0.000297 loss: 2.8726 (2.9149) grad: 0.1514 (0.2090) time: 0.4447 data: 0.0051 max mem: 22449 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.8411 (2.9100) grad: 0.1446 (0.2055) time: 0.4449 data: 0.0049 max mem: 22449 +train: [5] Total time: 0:03:00 (0.4510 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.8411 (2.9100) grad: 0.1446 (0.2055) +eval (validation): [5] [ 0/85] eta: 0:04:18 time: 3.0374 data: 2.7729 max mem: 22449 +eval (validation): [5] [20/85] eta: 0:00:29 time: 0.3222 data: 0.0039 max mem: 22449 +eval (validation): [5] [40/85] eta: 0:00:17 time: 0.3383 data: 0.0039 max mem: 22449 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3421 data: 0.0040 max mem: 22449 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3404 data: 0.0044 max mem: 22449 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3261 data: 0.0043 max mem: 22449 +eval (validation): [5] Total time: 0:00:31 (0.3698 s / it) +cv: [5] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.479 acc: 0.248 f1: 0.174 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:21:18 lr: nan time: 3.1974 data: 2.8663 max mem: 22449 +train: [6] [ 20/400] eta: 0:03:38 lr: 0.000296 loss: 2.8136 (2.8032) grad: 0.1426 (0.1502) time: 0.4434 data: 0.0044 max mem: 22449 +train: [6] [ 40/400] eta: 0:03:03 lr: 0.000296 loss: 2.8136 (2.8236) grad: 0.1457 (0.1490) time: 0.4416 data: 0.0044 max mem: 22449 +train: [6] [ 60/400] eta: 0:02:46 lr: 0.000296 loss: 2.8255 (2.8280) grad: 0.1403 (0.1453) time: 0.4483 data: 0.0051 max mem: 22449 +train: [6] [ 80/400] eta: 0:02:33 lr: 0.000295 loss: 2.8170 (2.8254) grad: 0.1438 (0.1473) time: 0.4489 data: 0.0048 max mem: 22449 +train: [6] [100/400] eta: 0:02:22 lr: 0.000295 loss: 2.8170 (2.8277) grad: 0.1524 (0.1471) time: 0.4556 data: 0.0050 max mem: 22449 +train: [6] [120/400] eta: 0:02:11 lr: 0.000295 loss: 2.8286 (2.8253) grad: 0.1403 (0.1457) time: 0.4420 data: 0.0050 max mem: 22449 +train: [6] [140/400] eta: 0:02:01 lr: 0.000294 loss: 2.8332 (2.8268) grad: 0.1421 (0.1476) time: 0.4500 data: 0.0047 max mem: 22449 +train: [6] [160/400] eta: 0:01:51 lr: 0.000294 loss: 2.8158 (2.8258) grad: 0.1498 (0.1477) time: 0.4435 data: 0.0050 max mem: 22449 +train: [6] [180/400] eta: 0:01:41 lr: 0.000293 loss: 2.8158 (2.8255) grad: 0.1442 (0.1476) time: 0.4460 data: 0.0048 max mem: 22449 +train: [6] [200/400] eta: 0:01:31 lr: 0.000293 loss: 2.8265 (2.8262) grad: 0.1454 (0.1476) time: 0.4395 data: 0.0049 max mem: 22449 +train: [6] [220/400] eta: 0:01:22 lr: 0.000292 loss: 2.8152 (2.8263) grad: 0.1486 (0.1477) time: 0.4571 data: 0.0049 max mem: 22449 +train: [6] [240/400] eta: 0:01:13 lr: 0.000292 loss: 2.8194 (2.8268) grad: 0.1559 (0.1494) time: 0.4393 data: 0.0049 max mem: 22449 +train: [6] [260/400] eta: 0:01:03 lr: 0.000291 loss: 2.8194 (2.8247) grad: 0.1538 (0.1494) time: 0.4397 data: 0.0049 max mem: 22449 +train: [6] [280/400] eta: 0:00:54 lr: 0.000291 loss: 2.8020 (2.8223) grad: 0.1489 (0.1496) time: 0.4472 data: 0.0047 max mem: 22449 +train: [6] [300/400] eta: 0:00:45 lr: 0.000290 loss: 2.7817 (2.8201) grad: 0.1478 (0.1498) time: 0.4458 data: 0.0051 max mem: 22449 +train: [6] [320/400] eta: 0:00:36 lr: 0.000290 loss: 2.7817 (2.8194) grad: 0.1526 (0.1502) time: 0.4332 data: 0.0050 max mem: 22449 +train: [6] [340/400] eta: 0:00:27 lr: 0.000289 loss: 2.8007 (2.8186) grad: 0.1543 (0.1504) time: 0.4369 data: 0.0052 max mem: 22449 +train: [6] [360/400] eta: 0:00:18 lr: 0.000288 loss: 2.8047 (2.8190) grad: 0.1605 (0.1515) time: 0.4456 data: 0.0050 max mem: 22449 +train: [6] [380/400] eta: 0:00:09 lr: 0.000288 loss: 2.8066 (2.8182) grad: 0.1656 (0.1524) time: 0.4698 data: 0.0050 max mem: 22449 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.8124 (2.8186) grad: 0.1656 (0.1527) time: 0.4542 data: 0.0051 max mem: 22449 +train: [6] Total time: 0:03:01 (0.4537 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.8124 (2.8186) grad: 0.1656 (0.1527) +eval (validation): [6] [ 0/85] eta: 0:04:20 time: 3.0647 data: 2.8263 max mem: 22449 +eval (validation): [6] [20/85] eta: 0:00:30 time: 0.3367 data: 0.0037 max mem: 22449 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3528 data: 0.0034 max mem: 22449 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3401 data: 0.0042 max mem: 22449 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3436 data: 0.0044 max mem: 22449 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3394 data: 0.0044 max mem: 22449 +eval (validation): [6] Total time: 0:00:32 (0.3786 s / it) +cv: [6] best hparam: (3.1, 1.0) (031) ('031_lr3.1e+00_wd1.0e+00') loss: 2.459 acc: 0.262 f1: 0.196 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [7] [ 0/400] eta: 0:21:50 lr: nan time: 3.2761 data: 2.9477 max mem: 22449 +train: [7] [ 20/400] eta: 0:03:39 lr: 0.000286 loss: 2.7954 (2.7932) grad: 0.1428 (0.1444) time: 0.4436 data: 0.0037 max mem: 22449 +train: [7] [ 40/400] eta: 0:03:04 lr: 0.000286 loss: 2.7938 (2.8020) grad: 0.1413 (0.1430) time: 0.4407 data: 0.0047 max mem: 22449 +train: [7] [ 60/400] eta: 0:02:45 lr: 0.000285 loss: 2.7657 (2.7836) grad: 0.1413 (0.1445) time: 0.4373 data: 0.0051 max mem: 22449 +train: [7] [ 80/400] eta: 0:02:32 lr: 0.000284 loss: 2.7515 (2.7837) grad: 0.1420 (0.1449) time: 0.4467 data: 0.0048 max mem: 22449 +train: [7] [100/400] eta: 0:02:21 lr: 0.000284 loss: 2.7564 (2.7837) grad: 0.1373 (0.1446) time: 0.4457 data: 0.0049 max mem: 22449 +train: [7] [120/400] eta: 0:02:10 lr: 0.000283 loss: 2.7499 (2.7805) grad: 0.1440 (0.1464) time: 0.4399 data: 0.0050 max mem: 22449 +train: [7] [140/400] eta: 0:02:00 lr: 0.000282 loss: 2.7636 (2.7798) grad: 0.1536 (0.1478) time: 0.4376 data: 0.0051 max mem: 22449 +train: [7] [160/400] eta: 0:01:50 lr: 0.000282 loss: 2.7797 (2.7791) grad: 0.1536 (0.1490) time: 0.4393 data: 0.0049 max mem: 22449 +train: [7] [180/400] eta: 0:01:40 lr: 0.000281 loss: 2.7797 (2.7788) grad: 0.1526 (0.1494) time: 0.4363 data: 0.0051 max mem: 22449 +train: [7] [200/400] eta: 0:01:31 lr: 0.000280 loss: 2.7850 (2.7808) grad: 0.1507 (0.1496) time: 0.4492 data: 0.0050 max mem: 22449 +train: [7] [220/400] eta: 0:01:22 lr: 0.000279 loss: 2.7931 (2.7819) grad: 0.1581 (0.1509) time: 0.4577 data: 0.0049 max mem: 22449 +train: [7] [240/400] eta: 0:01:12 lr: 0.000278 loss: 2.7723 (2.7813) grad: 0.1606 (0.1521) time: 0.4304 data: 0.0048 max mem: 22449 +train: [7] [260/400] eta: 0:01:03 lr: 0.000278 loss: 2.7874 (2.7808) grad: 0.1612 (0.1532) time: 0.4506 data: 0.0046 max mem: 22449 +train: [7] [280/400] eta: 0:00:54 lr: 0.000277 loss: 2.7906 (2.7842) grad: 0.1716 (0.1550) time: 0.4438 data: 0.0051 max mem: 22449 +train: [7] [300/400] eta: 0:00:45 lr: 0.000276 loss: 2.8130 (2.7848) grad: 0.1742 (0.1559) time: 0.4487 data: 0.0049 max mem: 22449 +train: [7] [320/400] eta: 0:00:36 lr: 0.000275 loss: 2.7941 (2.7844) grad: 0.1572 (0.1557) time: 0.4390 data: 0.0048 max mem: 22449 +train: [7] [340/400] eta: 0:00:27 lr: 0.000274 loss: 2.7614 (2.7823) grad: 0.1457 (0.1551) time: 0.4389 data: 0.0050 max mem: 22449 +train: [7] [360/400] eta: 0:00:18 lr: 0.000273 loss: 2.7807 (2.7838) grad: 0.1525 (0.1560) time: 0.4556 data: 0.0049 max mem: 22449 +train: [7] [380/400] eta: 0:00:09 lr: 0.000272 loss: 2.7813 (2.7829) grad: 0.1649 (0.1565) time: 0.4511 data: 0.0050 max mem: 22449 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.7619 (2.7826) grad: 0.1660 (0.1572) time: 0.4609 data: 0.0052 max mem: 22449 +train: [7] Total time: 0:03:00 (0.4523 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.7619 (2.7826) grad: 0.1660 (0.1572) +eval (validation): [7] [ 0/85] eta: 0:04:24 time: 3.1113 data: 2.8253 max mem: 22449 +eval (validation): [7] [20/85] eta: 0:00:32 time: 0.3647 data: 0.0032 max mem: 22449 +eval (validation): [7] [40/85] eta: 0:00:19 time: 0.3686 data: 0.0049 max mem: 22449 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3333 data: 0.0039 max mem: 22449 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3324 data: 0.0041 max mem: 22449 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3299 data: 0.0041 max mem: 22449 +eval (validation): [7] Total time: 0:00:32 (0.3846 s / it) +cv: [7] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.442 acc: 0.263 f1: 0.195 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:21:37 lr: nan time: 3.2445 data: 2.8712 max mem: 22449 +train: [8] [ 20/400] eta: 0:03:41 lr: 0.000270 loss: 2.7074 (2.7201) grad: 0.1452 (0.1521) time: 0.4492 data: 0.0054 max mem: 22449 +train: [8] [ 40/400] eta: 0:03:02 lr: 0.000270 loss: 2.6895 (2.7162) grad: 0.1508 (0.1550) time: 0.4305 data: 0.0048 max mem: 22449 +train: [8] [ 60/400] eta: 0:02:44 lr: 0.000269 loss: 2.7057 (2.7266) grad: 0.1620 (0.1592) time: 0.4328 data: 0.0048 max mem: 22449 +train: [8] [ 80/400] eta: 0:02:32 lr: 0.000268 loss: 2.7057 (2.7240) grad: 0.1654 (0.1599) time: 0.4617 data: 0.0051 max mem: 22449 +train: [8] [100/400] eta: 0:02:21 lr: 0.000267 loss: 2.7012 (2.7250) grad: 0.1620 (0.1605) time: 0.4435 data: 0.0050 max mem: 22449 +train: [8] [120/400] eta: 0:02:10 lr: 0.000266 loss: 2.7012 (2.7249) grad: 0.1649 (0.1615) time: 0.4377 data: 0.0051 max mem: 22449 +train: [8] [140/400] eta: 0:02:00 lr: 0.000265 loss: 2.7443 (2.7278) grad: 0.1655 (0.1620) time: 0.4416 data: 0.0053 max mem: 22449 +train: [8] [160/400] eta: 0:01:50 lr: 0.000264 loss: 2.7443 (2.7303) grad: 0.1624 (0.1618) time: 0.4393 data: 0.0050 max mem: 22449 +train: [8] [180/400] eta: 0:01:40 lr: 0.000263 loss: 2.7380 (2.7310) grad: 0.1659 (0.1626) time: 0.4509 data: 0.0051 max mem: 22449 +train: [8] [200/400] eta: 0:01:31 lr: 0.000262 loss: 2.7306 (2.7335) grad: 0.1705 (0.1637) time: 0.4618 data: 0.0054 max mem: 22449 +train: [8] [220/400] eta: 0:01:22 lr: 0.000260 loss: 2.7818 (2.7407) grad: 0.1682 (0.1644) time: 0.4402 data: 0.0051 max mem: 22449 +train: [8] [240/400] eta: 0:01:13 lr: 0.000259 loss: 2.7798 (2.7410) grad: 0.1689 (0.1650) time: 0.4605 data: 0.0052 max mem: 22449 +train: [8] [260/400] eta: 0:01:03 lr: 0.000258 loss: 2.7494 (2.7406) grad: 0.1751 (0.1670) time: 0.4526 data: 0.0052 max mem: 22449 +train: [8] [280/400] eta: 0:00:54 lr: 0.000257 loss: 2.7139 (2.7388) grad: 0.1631 (0.1664) time: 0.4334 data: 0.0049 max mem: 22449 +train: [8] [300/400] eta: 0:00:45 lr: 0.000256 loss: 2.7090 (2.7362) grad: 0.1524 (0.1655) time: 0.4372 data: 0.0051 max mem: 22449 +train: [8] [320/400] eta: 0:00:36 lr: 0.000255 loss: 2.7225 (2.7373) grad: 0.1524 (0.1655) time: 0.4341 data: 0.0050 max mem: 22449 +train: [8] [340/400] eta: 0:00:27 lr: 0.000254 loss: 2.7390 (2.7385) grad: 0.1616 (0.1652) time: 0.4431 data: 0.0050 max mem: 22449 +train: [8] [360/400] eta: 0:00:18 lr: 0.000253 loss: 2.7460 (2.7378) grad: 0.1616 (0.1651) time: 0.4566 data: 0.0052 max mem: 22449 +train: [8] [380/400] eta: 0:00:09 lr: 0.000252 loss: 2.7460 (2.7389) grad: 0.1691 (0.1657) time: 0.4545 data: 0.0050 max mem: 22449 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.7162 (2.7366) grad: 0.1774 (0.1663) time: 0.4403 data: 0.0051 max mem: 22449 +train: [8] Total time: 0:03:01 (0.4525 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.7162 (2.7366) grad: 0.1774 (0.1663) +eval (validation): [8] [ 0/85] eta: 0:04:30 time: 3.1867 data: 2.8925 max mem: 22449 +eval (validation): [8] [20/85] eta: 0:00:33 time: 0.3866 data: 0.0039 max mem: 22449 +eval (validation): [8] [40/85] eta: 0:00:19 time: 0.3478 data: 0.0043 max mem: 22449 +eval (validation): [8] [60/85] eta: 0:00:10 time: 0.3372 data: 0.0040 max mem: 22449 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3282 data: 0.0042 max mem: 22449 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3221 data: 0.0041 max mem: 22449 +eval (validation): [8] Total time: 0:00:32 (0.3850 s / it) +cv: [8] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.457 acc: 0.267 f1: 0.193 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:21:51 lr: nan time: 3.2789 data: 2.8933 max mem: 22449 +train: [9] [ 20/400] eta: 0:03:38 lr: 0.000249 loss: 2.6815 (2.7056) grad: 0.1624 (0.1601) time: 0.4407 data: 0.0045 max mem: 22449 +train: [9] [ 40/400] eta: 0:03:01 lr: 0.000248 loss: 2.6904 (2.7041) grad: 0.1632 (0.1630) time: 0.4273 data: 0.0042 max mem: 22449 +train: [9] [ 60/400] eta: 0:02:44 lr: 0.000247 loss: 2.6941 (2.7068) grad: 0.1736 (0.1673) time: 0.4467 data: 0.0048 max mem: 22449 +train: [9] [ 80/400] eta: 0:02:31 lr: 0.000246 loss: 2.7379 (2.7115) grad: 0.1746 (0.1691) time: 0.4338 data: 0.0047 max mem: 22449 +train: [9] [100/400] eta: 0:02:19 lr: 0.000244 loss: 2.7379 (2.7103) grad: 0.1664 (0.1682) time: 0.4349 data: 0.0049 max mem: 22449 +train: [9] [120/400] eta: 0:02:09 lr: 0.000243 loss: 2.7254 (2.7142) grad: 0.1620 (0.1680) time: 0.4422 data: 0.0050 max mem: 22449 +train: [9] [140/400] eta: 0:01:59 lr: 0.000242 loss: 2.7158 (2.7137) grad: 0.1620 (0.1683) time: 0.4384 data: 0.0051 max mem: 22449 +train: [9] [160/400] eta: 0:01:49 lr: 0.000241 loss: 2.6877 (2.7097) grad: 0.1724 (0.1699) time: 0.4378 data: 0.0050 max mem: 22449 +train: [9] [180/400] eta: 0:01:40 lr: 0.000240 loss: 2.6877 (2.7121) grad: 0.1717 (0.1698) time: 0.4590 data: 0.0051 max mem: 22449 +train: [9] [200/400] eta: 0:01:30 lr: 0.000238 loss: 2.7243 (2.7109) grad: 0.1630 (0.1692) time: 0.4456 data: 0.0048 max mem: 22449 +train: [9] [220/400] eta: 0:01:21 lr: 0.000237 loss: 2.7093 (2.7094) grad: 0.1689 (0.1700) time: 0.4292 data: 0.0049 max mem: 22449 +train: [9] [240/400] eta: 0:01:12 lr: 0.000236 loss: 2.6812 (2.7078) grad: 0.1780 (0.1711) time: 0.4503 data: 0.0051 max mem: 22449 +train: [9] [260/400] eta: 0:01:03 lr: 0.000234 loss: 2.6867 (2.7066) grad: 0.1849 (0.1725) time: 0.4469 data: 0.0052 max mem: 22449 +train: [9] [280/400] eta: 0:00:54 lr: 0.000233 loss: 2.6878 (2.7087) grad: 0.1853 (0.1725) time: 0.4335 data: 0.0052 max mem: 22449 +train: [9] [300/400] eta: 0:00:44 lr: 0.000232 loss: 2.6878 (2.7092) grad: 0.1683 (0.1726) time: 0.4407 data: 0.0051 max mem: 22449 +train: [9] [320/400] eta: 0:00:35 lr: 0.000230 loss: 2.6771 (2.7059) grad: 0.1680 (0.1721) time: 0.4394 data: 0.0052 max mem: 22449 +train: [9] [340/400] eta: 0:00:26 lr: 0.000229 loss: 2.6770 (2.7041) grad: 0.1610 (0.1714) time: 0.4473 data: 0.0048 max mem: 22449 +train: [9] [360/400] eta: 0:00:17 lr: 0.000228 loss: 2.6890 (2.7048) grad: 0.1668 (0.1713) time: 0.4531 data: 0.0051 max mem: 22449 +train: [9] [380/400] eta: 0:00:08 lr: 0.000226 loss: 2.6914 (2.7035) grad: 0.1732 (0.1712) time: 0.4487 data: 0.0051 max mem: 22449 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.6621 (2.7018) grad: 0.1691 (0.1710) time: 0.4485 data: 0.0049 max mem: 22449 +train: [9] Total time: 0:02:59 (0.4499 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.6621 (2.7018) grad: 0.1691 (0.1710) +eval (validation): [9] [ 0/85] eta: 0:04:45 time: 3.3627 data: 3.0611 max mem: 22449 +eval (validation): [9] [20/85] eta: 0:00:32 time: 0.3640 data: 0.0045 max mem: 22449 +eval (validation): [9] [40/85] eta: 0:00:19 time: 0.3616 data: 0.0042 max mem: 22449 +eval (validation): [9] [60/85] eta: 0:00:10 time: 0.3345 data: 0.0041 max mem: 22449 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3270 data: 0.0037 max mem: 22449 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3210 data: 0.0038 max mem: 22449 +eval (validation): [9] Total time: 0:00:32 (0.3836 s / it) +cv: [9] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.432 acc: 0.276 f1: 0.211 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:21:35 lr: nan time: 3.2399 data: 2.9117 max mem: 22449 +train: [10] [ 20/400] eta: 0:03:38 lr: 0.000224 loss: 2.6389 (2.6454) grad: 0.1612 (0.1602) time: 0.4414 data: 0.0048 max mem: 22449 +train: [10] [ 40/400] eta: 0:03:02 lr: 0.000222 loss: 2.6389 (2.6538) grad: 0.1625 (0.1643) time: 0.4382 data: 0.0045 max mem: 22449 +train: [10] [ 60/400] eta: 0:02:47 lr: 0.000221 loss: 2.6583 (2.6525) grad: 0.1521 (0.1580) time: 0.4611 data: 0.0051 max mem: 22449 +train: [10] [ 80/400] eta: 0:02:33 lr: 0.000220 loss: 2.6628 (2.6595) grad: 0.1521 (0.1608) time: 0.4392 data: 0.0051 max mem: 22449 +train: [10] [100/400] eta: 0:02:21 lr: 0.000218 loss: 2.6475 (2.6538) grad: 0.1628 (0.1615) time: 0.4412 data: 0.0050 max mem: 22449 +train: [10] [120/400] eta: 0:02:11 lr: 0.000217 loss: 2.6847 (2.6639) grad: 0.1731 (0.1662) time: 0.4562 data: 0.0050 max mem: 22449 +train: [10] [140/400] eta: 0:02:01 lr: 0.000215 loss: 2.6884 (2.6667) grad: 0.1838 (0.1681) time: 0.4461 data: 0.0050 max mem: 22449 +train: [10] [160/400] eta: 0:01:51 lr: 0.000214 loss: 2.6707 (2.6692) grad: 0.1822 (0.1703) time: 0.4510 data: 0.0050 max mem: 22449 +train: [10] [180/400] eta: 0:01:41 lr: 0.000213 loss: 2.6749 (2.6730) grad: 0.1760 (0.1704) time: 0.4584 data: 0.0050 max mem: 22449 +train: [10] [200/400] eta: 0:01:32 lr: 0.000211 loss: 2.6749 (2.6728) grad: 0.1718 (0.1714) time: 0.4286 data: 0.0048 max mem: 22449 +train: [10] [220/400] eta: 0:01:22 lr: 0.000210 loss: 2.6606 (2.6725) grad: 0.1692 (0.1713) time: 0.4510 data: 0.0049 max mem: 22449 +train: [10] [240/400] eta: 0:01:13 lr: 0.000208 loss: 2.6704 (2.6741) grad: 0.1632 (0.1711) time: 0.4481 data: 0.0050 max mem: 22449 +train: [10] [260/400] eta: 0:01:04 lr: 0.000207 loss: 2.6822 (2.6745) grad: 0.1780 (0.1725) time: 0.4448 data: 0.0049 max mem: 22449 +train: [10] [280/400] eta: 0:00:54 lr: 0.000205 loss: 2.6793 (2.6752) grad: 0.1878 (0.1730) time: 0.4397 data: 0.0049 max mem: 22449 +train: [10] [300/400] eta: 0:00:45 lr: 0.000204 loss: 2.6881 (2.6759) grad: 0.1634 (0.1720) time: 0.4462 data: 0.0049 max mem: 22449 +train: [10] [320/400] eta: 0:00:36 lr: 0.000202 loss: 2.6751 (2.6749) grad: 0.1562 (0.1715) time: 0.4382 data: 0.0047 max mem: 22449 +train: [10] [340/400] eta: 0:00:27 lr: 0.000201 loss: 2.6509 (2.6739) grad: 0.1671 (0.1716) time: 0.4514 data: 0.0052 max mem: 22449 +train: [10] [360/400] eta: 0:00:18 lr: 0.000199 loss: 2.6450 (2.6738) grad: 0.1669 (0.1712) time: 0.4503 data: 0.0052 max mem: 22449 +train: [10] [380/400] eta: 0:00:09 lr: 0.000198 loss: 2.6883 (2.6757) grad: 0.1646 (0.1710) time: 0.4436 data: 0.0047 max mem: 22449 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.6753 (2.6739) grad: 0.1645 (0.1709) time: 0.4466 data: 0.0051 max mem: 22449 +train: [10] Total time: 0:03:01 (0.4536 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.6753 (2.6739) grad: 0.1645 (0.1709) +eval (validation): [10] [ 0/85] eta: 0:04:38 time: 3.2707 data: 2.9848 max mem: 22449 +eval (validation): [10] [20/85] eta: 0:00:32 time: 0.3624 data: 0.0051 max mem: 22449 +eval (validation): [10] [40/85] eta: 0:00:18 time: 0.3373 data: 0.0036 max mem: 22449 +eval (validation): [10] [60/85] eta: 0:00:09 time: 0.3431 data: 0.0043 max mem: 22449 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3192 data: 0.0041 max mem: 22449 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3141 data: 0.0041 max mem: 22449 +eval (validation): [10] Total time: 0:00:32 (0.3770 s / it) +cv: [10] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.453 acc: 0.267 f1: 0.193 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:07 lr: nan time: 3.3179 data: 2.9316 max mem: 22449 +train: [11] [ 20/400] eta: 0:03:41 lr: 0.000195 loss: 2.6368 (2.6204) grad: 0.1540 (0.1577) time: 0.4475 data: 0.0038 max mem: 22449 +train: [11] [ 40/400] eta: 0:03:02 lr: 0.000193 loss: 2.6651 (2.6416) grad: 0.1605 (0.1623) time: 0.4286 data: 0.0049 max mem: 22449 +train: [11] [ 60/400] eta: 0:02:46 lr: 0.000192 loss: 2.6676 (2.6480) grad: 0.1664 (0.1649) time: 0.4534 data: 0.0049 max mem: 22449 +train: [11] [ 80/400] eta: 0:02:32 lr: 0.000190 loss: 2.6344 (2.6390) grad: 0.1788 (0.1706) time: 0.4357 data: 0.0049 max mem: 22449 +train: [11] [100/400] eta: 0:02:20 lr: 0.000189 loss: 2.6215 (2.6396) grad: 0.1779 (0.1710) time: 0.4408 data: 0.0052 max mem: 22449 +train: [11] [120/400] eta: 0:02:10 lr: 0.000187 loss: 2.6367 (2.6407) grad: 0.1676 (0.1702) time: 0.4400 data: 0.0052 max mem: 22449 +train: [11] [140/400] eta: 0:01:59 lr: 0.000186 loss: 2.6297 (2.6401) grad: 0.1663 (0.1692) time: 0.4389 data: 0.0050 max mem: 22449 +train: [11] [160/400] eta: 0:01:49 lr: 0.000184 loss: 2.6404 (2.6415) grad: 0.1621 (0.1689) time: 0.4365 data: 0.0050 max mem: 22449 +train: [11] [180/400] eta: 0:01:40 lr: 0.000183 loss: 2.6151 (2.6375) grad: 0.1654 (0.1688) time: 0.4544 data: 0.0050 max mem: 22449 +train: [11] [200/400] eta: 0:01:30 lr: 0.000181 loss: 2.6216 (2.6432) grad: 0.1698 (0.1698) time: 0.4307 data: 0.0047 max mem: 22449 +train: [11] [220/400] eta: 0:01:21 lr: 0.000180 loss: 2.6303 (2.6391) grad: 0.1807 (0.1711) time: 0.4451 data: 0.0049 max mem: 22449 +train: [11] [240/400] eta: 0:01:12 lr: 0.000178 loss: 2.6195 (2.6414) grad: 0.1819 (0.1725) time: 0.4461 data: 0.0050 max mem: 22449 +train: [11] [260/400] eta: 0:01:03 lr: 0.000177 loss: 2.6431 (2.6411) grad: 0.1768 (0.1730) time: 0.4367 data: 0.0051 max mem: 22449 +train: [11] [280/400] eta: 0:00:54 lr: 0.000175 loss: 2.6532 (2.6424) grad: 0.1739 (0.1727) time: 0.4421 data: 0.0049 max mem: 22449 +train: [11] [300/400] eta: 0:00:45 lr: 0.000174 loss: 2.6532 (2.6419) grad: 0.1663 (0.1722) time: 0.4453 data: 0.0051 max mem: 22449 +train: [11] [320/400] eta: 0:00:36 lr: 0.000172 loss: 2.6295 (2.6398) grad: 0.1590 (0.1712) time: 0.4506 data: 0.0050 max mem: 22449 +train: [11] [340/400] eta: 0:00:27 lr: 0.000170 loss: 2.6295 (2.6392) grad: 0.1590 (0.1708) time: 0.4636 data: 0.0051 max mem: 22449 +train: [11] [360/400] eta: 0:00:18 lr: 0.000169 loss: 2.6136 (2.6379) grad: 0.1651 (0.1710) time: 0.4491 data: 0.0051 max mem: 22449 +train: [11] [380/400] eta: 0:00:09 lr: 0.000167 loss: 2.6094 (2.6404) grad: 0.1703 (0.1713) time: 0.4401 data: 0.0047 max mem: 22449 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.6791 (2.6415) grad: 0.1610 (0.1705) time: 0.4495 data: 0.0050 max mem: 22449 +train: [11] Total time: 0:03:00 (0.4515 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.6791 (2.6415) grad: 0.1610 (0.1705) +eval (validation): [11] [ 0/85] eta: 0:04:40 time: 3.3006 data: 3.0145 max mem: 22449 +eval (validation): [11] [20/85] eta: 0:00:32 time: 0.3527 data: 0.0049 max mem: 22449 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3606 data: 0.0036 max mem: 22449 +eval (validation): [11] [60/85] eta: 0:00:10 time: 0.3455 data: 0.0042 max mem: 22449 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3218 data: 0.0041 max mem: 22449 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3186 data: 0.0041 max mem: 22449 +eval (validation): [11] Total time: 0:00:32 (0.3821 s / it) +cv: [11] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.440 acc: 0.279 f1: 0.217 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:22:34 lr: nan time: 3.3867 data: 3.0130 max mem: 22449 +train: [12] [ 20/400] eta: 0:03:38 lr: 0.000164 loss: 2.5464 (2.5756) grad: 0.1748 (0.1846) time: 0.4338 data: 0.0049 max mem: 22449 +train: [12] [ 40/400] eta: 0:03:05 lr: 0.000163 loss: 2.5765 (2.5959) grad: 0.1800 (0.1770) time: 0.4550 data: 0.0046 max mem: 22449 +train: [12] [ 60/400] eta: 0:02:46 lr: 0.000161 loss: 2.6187 (2.5970) grad: 0.1795 (0.1739) time: 0.4361 data: 0.0049 max mem: 22449 +train: [12] [ 80/400] eta: 0:02:33 lr: 0.000160 loss: 2.6021 (2.6022) grad: 0.1646 (0.1701) time: 0.4476 data: 0.0050 max mem: 22449 +train: [12] [100/400] eta: 0:02:21 lr: 0.000158 loss: 2.6021 (2.6006) grad: 0.1674 (0.1720) time: 0.4446 data: 0.0050 max mem: 22449 +train: [12] [120/400] eta: 0:02:10 lr: 0.000156 loss: 2.6129 (2.6065) grad: 0.1832 (0.1742) time: 0.4379 data: 0.0050 max mem: 22449 +train: [12] [140/400] eta: 0:02:00 lr: 0.000155 loss: 2.6068 (2.6106) grad: 0.1835 (0.1763) time: 0.4441 data: 0.0049 max mem: 22449 +train: [12] [160/400] eta: 0:01:50 lr: 0.000153 loss: 2.6068 (2.6113) grad: 0.1731 (0.1756) time: 0.4496 data: 0.0050 max mem: 22449 +train: [12] [180/400] eta: 0:01:41 lr: 0.000152 loss: 2.5944 (2.6086) grad: 0.1668 (0.1744) time: 0.4557 data: 0.0051 max mem: 22449 +train: [12] [200/400] eta: 0:01:31 lr: 0.000150 loss: 2.5982 (2.6119) grad: 0.1668 (0.1742) time: 0.4323 data: 0.0047 max mem: 22449 +train: [12] [220/400] eta: 0:01:22 lr: 0.000149 loss: 2.6374 (2.6167) grad: 0.1768 (0.1753) time: 0.4400 data: 0.0051 max mem: 22449 +train: [12] [240/400] eta: 0:01:12 lr: 0.000147 loss: 2.6374 (2.6168) grad: 0.1791 (0.1757) time: 0.4456 data: 0.0050 max mem: 22449 +train: [12] [260/400] eta: 0:01:03 lr: 0.000145 loss: 2.6233 (2.6170) grad: 0.1682 (0.1748) time: 0.4383 data: 0.0051 max mem: 22449 +train: [12] [280/400] eta: 0:00:54 lr: 0.000144 loss: 2.6404 (2.6192) grad: 0.1753 (0.1754) time: 0.4394 data: 0.0051 max mem: 22449 +train: [12] [300/400] eta: 0:00:45 lr: 0.000142 loss: 2.6320 (2.6188) grad: 0.1797 (0.1758) time: 0.4397 data: 0.0049 max mem: 22449 +train: [12] [320/400] eta: 0:00:36 lr: 0.000141 loss: 2.5868 (2.6157) grad: 0.1815 (0.1764) time: 0.4529 data: 0.0050 max mem: 22449 +train: [12] [340/400] eta: 0:00:27 lr: 0.000139 loss: 2.5868 (2.6155) grad: 0.1751 (0.1761) time: 0.4618 data: 0.0051 max mem: 22449 +train: [12] [360/400] eta: 0:00:18 lr: 0.000138 loss: 2.6186 (2.6160) grad: 0.1599 (0.1755) time: 0.4396 data: 0.0052 max mem: 22449 +train: [12] [380/400] eta: 0:00:09 lr: 0.000136 loss: 2.6186 (2.6163) grad: 0.1574 (0.1750) time: 0.4384 data: 0.0050 max mem: 22449 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.6266 (2.6169) grad: 0.1633 (0.1747) time: 0.4566 data: 0.0052 max mem: 22449 +train: [12] Total time: 0:03:00 (0.4524 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.6266 (2.6169) grad: 0.1633 (0.1747) +eval (validation): [12] [ 0/85] eta: 0:04:42 time: 3.3229 data: 3.0764 max mem: 22449 +eval (validation): [12] [20/85] eta: 0:00:32 time: 0.3603 data: 0.0047 max mem: 22449 +eval (validation): [12] [40/85] eta: 0:00:19 time: 0.3396 data: 0.0035 max mem: 22449 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3426 data: 0.0043 max mem: 22449 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3274 data: 0.0040 max mem: 22449 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3188 data: 0.0038 max mem: 22449 +eval (validation): [12] Total time: 0:00:32 (0.3794 s / it) +cv: [12] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.428 acc: 0.277 f1: 0.209 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:21:45 lr: nan time: 3.2627 data: 2.8626 max mem: 22449 +train: [13] [ 20/400] eta: 0:03:48 lr: 0.000133 loss: 2.5533 (2.5745) grad: 0.1640 (0.1705) time: 0.4683 data: 0.0039 max mem: 22449 +train: [13] [ 40/400] eta: 0:03:09 lr: 0.000131 loss: 2.5915 (2.5965) grad: 0.1620 (0.1645) time: 0.4461 data: 0.0050 max mem: 22449 +train: [13] [ 60/400] eta: 0:02:51 lr: 0.000130 loss: 2.5927 (2.5904) grad: 0.1658 (0.1663) time: 0.4616 data: 0.0049 max mem: 22449 +train: [13] [ 80/400] eta: 0:02:36 lr: 0.000128 loss: 2.5924 (2.5940) grad: 0.1701 (0.1660) time: 0.4416 data: 0.0051 max mem: 22449 +train: [13] [100/400] eta: 0:02:24 lr: 0.000127 loss: 2.5984 (2.6040) grad: 0.1678 (0.1666) time: 0.4455 data: 0.0051 max mem: 22449 +train: [13] [120/400] eta: 0:02:12 lr: 0.000125 loss: 2.5936 (2.5960) grad: 0.1624 (0.1652) time: 0.4435 data: 0.0049 max mem: 22449 +train: [13] [140/400] eta: 0:02:02 lr: 0.000124 loss: 2.5396 (2.5850) grad: 0.1565 (0.1641) time: 0.4401 data: 0.0050 max mem: 22449 +train: [13] [160/400] eta: 0:01:52 lr: 0.000122 loss: 2.5396 (2.5852) grad: 0.1577 (0.1647) time: 0.4592 data: 0.0050 max mem: 22449 +train: [13] [180/400] eta: 0:01:42 lr: 0.000120 loss: 2.6047 (2.5858) grad: 0.1649 (0.1661) time: 0.4576 data: 0.0052 max mem: 22449 +train: [13] [200/400] eta: 0:01:32 lr: 0.000119 loss: 2.6163 (2.5866) grad: 0.1669 (0.1667) time: 0.4345 data: 0.0048 max mem: 22449 +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:38:16 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip patch attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn +model: flat_mae +representation: patch +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn +remote_dir: null + +creating frozen backbone model: flat_mae +train: [13] [220/400] eta: 0:01:23 lr: 0.000117 loss: 2.6274 (2.5913) grad: 0.1721 (0.1677) time: 0.4562 data: 0.0050 max mem: 22449 +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train: [13] [240/400] eta: 0:01:13 lr: 0.000116 loss: 2.5856 (2.5884) grad: 0.1694 (0.1678) time: 0.4380 data: 0.0050 max mem: 22449 +train: [13] [260/400] eta: 0:01:04 lr: 0.000114 loss: 2.5614 (2.5901) grad: 0.1673 (0.1685) time: 0.4440 data: 0.0050 max mem: 22449 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 2.5952 (2.5903) grad: 0.1655 (0.1684) time: 0.4378 data: 0.0050 max mem: 22449 +train: [13] [300/400] eta: 0:00:45 lr: 0.000111 loss: 2.5805 (2.5918) grad: 0.1655 (0.1684) time: 0.4397 data: 0.0050 max mem: 22449 +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +loaded model and optimizer state, resuming training from 13 +freezing diverged classifier 44 (26, 1.0) +freezing diverged classifier 45 (31, 1.0) +freezing diverged classifier 46 (36, 1.0) +freezing diverged classifier 47 (43, 1.0) +freezing diverged classifier 48 (50, 1.0) +start training for 20 epochs +train: [13] [ 0/400] eta: 0:22:20 lr: nan time: 3.3503 data: 2.8813 max mem: 20539 +train: [13] [320/400] eta: 0:00:36 lr: 0.000110 loss: 2.6170 (2.5946) grad: 0.1658 (0.1680) time: 0.4428 data: 0.0051 max mem: 22449 +train: [13] [ 20/400] eta: 0:03:56 lr: 0.000133 loss: 2.5758 (2.5817) grad: 0.1594 (0.1648) time: 0.4846 data: 0.0065 max mem: 20773 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 2.6163 (2.5929) grad: 0.1655 (0.1683) time: 0.4597 data: 0.0052 max mem: 22449 +train: [13] [ 40/400] eta: 0:03:12 lr: 0.000131 loss: 2.5870 (2.5888) grad: 0.1750 (0.1737) time: 0.4463 data: 0.0037 max mem: 20773 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 2.5868 (2.5943) grad: 0.1683 (0.1681) time: 0.4414 data: 0.0049 max mem: 22449 +train: [13] [ 60/400] eta: 0:02:50 lr: 0.000130 loss: 2.5971 (2.5935) grad: 0.1795 (0.1750) time: 0.4310 data: 0.0040 max mem: 20773 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 2.6153 (2.5955) grad: 0.1601 (0.1681) time: 0.4278 data: 0.0048 max mem: 22449 +train: [13] [ 80/400] eta: 0:02:36 lr: 0.000128 loss: 2.6050 (2.5951) grad: 0.1696 (0.1718) time: 0.4466 data: 0.0042 max mem: 20773 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.5856 (2.5937) grad: 0.1601 (0.1679) time: 0.4488 data: 0.0049 max mem: 22449 +train: [13] Total time: 0:03:01 (0.4543 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.5856 (2.5937) grad: 0.1601 (0.1679) +eval (validation): [13] [ 0/85] eta: 0:04:16 time: 3.0145 data: 2.7337 max mem: 22449 +train: [13] [100/400] eta: 0:02:23 lr: 0.000127 loss: 2.6034 (2.5976) grad: 0.1659 (0.1702) time: 0.4421 data: 0.0041 max mem: 20773 +eval (validation): [13] [20/85] eta: 0:00:32 time: 0.3743 data: 0.0054 max mem: 22449 +train: [13] [120/400] eta: 0:02:12 lr: 0.000125 loss: 2.5707 (2.5984) grad: 0.1678 (0.1709) time: 0.4369 data: 0.0041 max mem: 20773 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3503 data: 0.0037 max mem: 22449 +train: [13] [140/400] eta: 0:02:01 lr: 0.000124 loss: 2.5646 (2.5986) grad: 0.1735 (0.1715) time: 0.4384 data: 0.0042 max mem: 20773 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3485 data: 0.0042 max mem: 22449 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3389 data: 0.0043 max mem: 22449 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3297 data: 0.0042 max mem: 22449 +train: [13] [160/400] eta: 0:01:51 lr: 0.000122 loss: 2.5654 (2.5971) grad: 0.1753 (0.1723) time: 0.4458 data: 0.0041 max mem: 20773 +eval (validation): [13] Total time: 0:00:32 (0.3859 s / it) +cv: [13] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.456 acc: 0.267 f1: 0.200 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:21:08 lr: nan time: 3.1702 data: 2.7995 max mem: 22449 +train: [13] [180/400] eta: 0:01:41 lr: 0.000120 loss: 2.5669 (2.5946) grad: 0.1729 (0.1727) time: 0.4450 data: 0.0041 max mem: 20773 +train: [14] [ 20/400] eta: 0:03:37 lr: 0.000102 loss: 2.5532 (2.5536) grad: 0.1508 (0.1594) time: 0.4418 data: 0.0040 max mem: 22449 +train: [13] [200/400] eta: 0:01:32 lr: 0.000119 loss: 2.5643 (2.5939) grad: 0.1692 (0.1724) time: 0.4466 data: 0.0041 max mem: 20773 +train: [14] [ 40/400] eta: 0:03:03 lr: 0.000101 loss: 2.5544 (2.5618) grad: 0.1611 (0.1616) time: 0.4467 data: 0.0050 max mem: 22449 +train: [13] [220/400] eta: 0:01:22 lr: 0.000117 loss: 2.5795 (2.5944) grad: 0.1699 (0.1727) time: 0.4532 data: 0.0041 max mem: 20773 +train: [14] [ 60/400] eta: 0:02:45 lr: 0.000099 loss: 2.5942 (2.5657) grad: 0.1616 (0.1647) time: 0.4388 data: 0.0050 max mem: 22449 +train: [13] [240/400] eta: 0:01:13 lr: 0.000116 loss: 2.5935 (2.5958) grad: 0.1842 (0.1737) time: 0.4412 data: 0.0043 max mem: 20773 +train: [14] [ 80/400] eta: 0:02:32 lr: 0.000098 loss: 2.5535 (2.5649) grad: 0.1657 (0.1665) time: 0.4386 data: 0.0050 max mem: 22449 +train: [13] [260/400] eta: 0:01:04 lr: 0.000114 loss: 2.5935 (2.5960) grad: 0.1851 (0.1751) time: 0.4474 data: 0.0045 max mem: 20773 +train: [14] [100/400] eta: 0:02:20 lr: 0.000096 loss: 2.5574 (2.5669) grad: 0.1661 (0.1684) time: 0.4390 data: 0.0048 max mem: 22449 +train: [13] [280/400] eta: 0:00:54 lr: 0.000113 loss: 2.5784 (2.5942) grad: 0.1851 (0.1760) time: 0.4437 data: 0.0042 max mem: 20773 +train: [14] [120/400] eta: 0:02:09 lr: 0.000095 loss: 2.5575 (2.5676) grad: 0.1704 (0.1688) time: 0.4385 data: 0.0050 max mem: 22449 +train: [13] [300/400] eta: 0:00:45 lr: 0.000111 loss: 2.6107 (2.5973) grad: 0.1765 (0.1756) time: 0.4511 data: 0.0042 max mem: 20773 +train: [14] [140/400] eta: 0:01:59 lr: 0.000093 loss: 2.5795 (2.5786) grad: 0.1708 (0.1695) time: 0.4316 data: 0.0047 max mem: 22449 +train: [13] [320/400] eta: 0:00:36 lr: 0.000110 loss: 2.6271 (2.5984) grad: 0.1698 (0.1751) time: 0.4524 data: 0.0043 max mem: 20773 +train: [14] [160/400] eta: 0:01:49 lr: 0.000092 loss: 2.6080 (2.5822) grad: 0.1660 (0.1697) time: 0.4432 data: 0.0048 max mem: 22449 +train: [13] [340/400] eta: 0:00:27 lr: 0.000108 loss: 2.5793 (2.5994) grad: 0.1615 (0.1743) time: 0.4495 data: 0.0044 max mem: 20773 +train: [14] [180/400] eta: 0:01:40 lr: 0.000090 loss: 2.6080 (2.5850) grad: 0.1588 (0.1687) time: 0.4528 data: 0.0050 max mem: 22449 +train: [13] [360/400] eta: 0:00:18 lr: 0.000107 loss: 2.5663 (2.5957) grad: 0.1604 (0.1738) time: 0.4381 data: 0.0042 max mem: 20773 +train: [14] [200/400] eta: 0:01:30 lr: 0.000089 loss: 2.5599 (2.5822) grad: 0.1626 (0.1693) time: 0.4273 data: 0.0046 max mem: 22449 +train: [13] [380/400] eta: 0:00:09 lr: 0.000105 loss: 2.5579 (2.5962) grad: 0.1603 (0.1732) time: 0.4510 data: 0.0041 max mem: 20773 +train: [14] [220/400] eta: 0:01:21 lr: 0.000088 loss: 2.5717 (2.5828) grad: 0.1719 (0.1701) time: 0.4450 data: 0.0050 max mem: 22449 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.6341 (2.5982) grad: 0.1610 (0.1730) time: 0.4695 data: 0.0043 max mem: 20773 +train: [13] Total time: 0:03:02 (0.4555 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.6341 (2.5982) grad: 0.1610 (0.1730) +eval (validation): [13] [ 0/85] eta: 0:04:37 time: 3.2686 data: 2.9891 max mem: 20773 +train: [14] [240/400] eta: 0:01:12 lr: 0.000086 loss: 2.5583 (2.5801) grad: 0.1681 (0.1704) time: 0.4422 data: 0.0051 max mem: 22449 +eval (validation): [13] [20/85] eta: 0:00:30 time: 0.3331 data: 0.0036 max mem: 20773 +train: [14] [260/400] eta: 0:01:03 lr: 0.000085 loss: 2.5603 (2.5831) grad: 0.1722 (0.1715) time: 0.4365 data: 0.0050 max mem: 22449 +eval (validation): [13] [40/85] eta: 0:00:17 time: 0.3182 data: 0.0047 max mem: 20773 +train: [14] [280/400] eta: 0:00:53 lr: 0.000083 loss: 2.5876 (2.5821) grad: 0.1756 (0.1713) time: 0.4371 data: 0.0050 max mem: 22449 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3361 data: 0.0042 max mem: 20773 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3397 data: 0.0040 max mem: 20773 +train: [14] [300/400] eta: 0:00:44 lr: 0.000082 loss: 2.5743 (2.5807) grad: 0.1704 (0.1713) time: 0.4390 data: 0.0049 max mem: 22449 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3310 data: 0.0038 max mem: 20773 +eval (validation): [13] Total time: 0:00:31 (0.3689 s / it) +cv: [13] best hparam: (1.4, 1.0) (026) ('026_lr1.4e+00_wd1.0e+00') loss: 2.442 acc: 0.282 f1: 0.215 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +train: [14] [320/400] eta: 0:00:35 lr: 0.000081 loss: 2.5982 (2.5835) grad: 0.1630 (0.1713) time: 0.4383 data: 0.0051 max mem: 22449 +train: [14] [ 0/400] eta: 0:23:59 lr: nan time: 3.5988 data: 3.2394 max mem: 20773 +train: [14] [340/400] eta: 0:00:26 lr: 0.000079 loss: 2.5891 (2.5834) grad: 0.1645 (0.1715) time: 0.4533 data: 0.0051 max mem: 22449 +train: [14] [ 20/400] eta: 0:03:58 lr: 0.000102 loss: 2.5978 (2.5817) grad: 0.1491 (0.1580) time: 0.4780 data: 0.0034 max mem: 20773 +train: [14] [360/400] eta: 0:00:17 lr: 0.000078 loss: 2.5819 (2.5847) grad: 0.1646 (0.1712) time: 0.4543 data: 0.0052 max mem: 22449 +train: [14] [ 40/400] eta: 0:03:14 lr: 0.000101 loss: 2.5110 (2.5442) grad: 0.1567 (0.1609) time: 0.4520 data: 0.0040 max mem: 20773 +train: [14] [380/400] eta: 0:00:08 lr: 0.000076 loss: 2.5657 (2.5829) grad: 0.1530 (0.1704) time: 0.4222 data: 0.0047 max mem: 22449 +train: [14] [ 60/400] eta: 0:02:52 lr: 0.000099 loss: 2.5027 (2.5473) grad: 0.1810 (0.1696) time: 0.4346 data: 0.0040 max mem: 20773 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.5592 (2.5826) grad: 0.1555 (0.1699) time: 0.4558 data: 0.0050 max mem: 22449 +train: [14] Total time: 0:02:59 (0.4485 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.5592 (2.5826) grad: 0.1555 (0.1699) +train: [14] [ 80/400] eta: 0:02:39 lr: 0.000098 loss: 2.5681 (2.5603) grad: 0.1852 (0.1732) time: 0.4741 data: 0.0040 max mem: 20773 +eval (validation): [14] [ 0/85] eta: 0:04:22 time: 3.0914 data: 2.8567 max mem: 22449 +train: [14] [100/400] eta: 0:02:26 lr: 0.000096 loss: 2.5656 (2.5628) grad: 0.1852 (0.1740) time: 0.4499 data: 0.0041 max mem: 20773 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3687 data: 0.0034 max mem: 22449 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3628 data: 0.0044 max mem: 22449 +train: [14] [120/400] eta: 0:02:15 lr: 0.000095 loss: 2.5764 (2.5706) grad: 0.1721 (0.1738) time: 0.4524 data: 0.0041 max mem: 20773 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3469 data: 0.0042 max mem: 22449 +train: [14] [140/400] eta: 0:02:04 lr: 0.000093 loss: 2.5764 (2.5665) grad: 0.1721 (0.1736) time: 0.4602 data: 0.0041 max mem: 20773 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3280 data: 0.0043 max mem: 22449 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3195 data: 0.0041 max mem: 22449 +eval (validation): [14] Total time: 0:00:32 (0.3861 s / it) +cv: [14] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.420 acc: 0.274 f1: 0.207 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [14] [160/400] eta: 0:01:54 lr: 0.000092 loss: 2.5574 (2.5688) grad: 0.1734 (0.1734) time: 0.4474 data: 0.0042 max mem: 20773 +train: [15] [ 0/400] eta: 0:21:37 lr: nan time: 3.2444 data: 2.8659 max mem: 22449 +train: [14] [180/400] eta: 0:01:43 lr: 0.000090 loss: 2.5809 (2.5719) grad: 0.1713 (0.1737) time: 0.4484 data: 0.0042 max mem: 20773 +train: [15] [ 20/400] eta: 0:03:39 lr: 0.000074 loss: 2.5061 (2.5541) grad: 0.1716 (0.1692) time: 0.4433 data: 0.0029 max mem: 22449 +train: [14] [200/400] eta: 0:01:34 lr: 0.000089 loss: 2.5809 (2.5728) grad: 0.1752 (0.1739) time: 0.4492 data: 0.0041 max mem: 20773 +train: [15] [ 40/400] eta: 0:03:06 lr: 0.000072 loss: 2.5638 (2.5692) grad: 0.1638 (0.1664) time: 0.4583 data: 0.0044 max mem: 22449 +train: [14] [220/400] eta: 0:01:24 lr: 0.000088 loss: 2.5933 (2.5735) grad: 0.1778 (0.1744) time: 0.4508 data: 0.0042 max mem: 20773 +train: [15] [ 60/400] eta: 0:02:47 lr: 0.000071 loss: 2.5749 (2.5625) grad: 0.1661 (0.1691) time: 0.4379 data: 0.0051 max mem: 22449 +train: [14] [240/400] eta: 0:01:14 lr: 0.000086 loss: 2.5933 (2.5766) grad: 0.1700 (0.1736) time: 0.4479 data: 0.0041 max mem: 20773 +train: [15] [ 80/400] eta: 0:02:32 lr: 0.000070 loss: 2.5507 (2.5593) grad: 0.1661 (0.1676) time: 0.4327 data: 0.0049 max mem: 22449 +train: [14] [260/400] eta: 0:01:05 lr: 0.000085 loss: 2.5607 (2.5753) grad: 0.1629 (0.1733) time: 0.4572 data: 0.0040 max mem: 20773 +train: [15] [100/400] eta: 0:02:21 lr: 0.000068 loss: 2.5605 (2.5621) grad: 0.1579 (0.1672) time: 0.4423 data: 0.0050 max mem: 22449 +train: [14] [280/400] eta: 0:00:55 lr: 0.000083 loss: 2.5517 (2.5765) grad: 0.1629 (0.1727) time: 0.4502 data: 0.0040 max mem: 20773 +train: [15] [120/400] eta: 0:02:10 lr: 0.000067 loss: 2.5366 (2.5556) grad: 0.1649 (0.1676) time: 0.4343 data: 0.0049 max mem: 22449 +train: [14] [300/400] eta: 0:00:46 lr: 0.000082 loss: 2.5721 (2.5762) grad: 0.1734 (0.1732) time: 0.4445 data: 0.0042 max mem: 20773 +train: [15] [140/400] eta: 0:01:59 lr: 0.000066 loss: 2.5093 (2.5496) grad: 0.1613 (0.1664) time: 0.4323 data: 0.0050 max mem: 22449 +train: [14] [320/400] eta: 0:00:37 lr: 0.000081 loss: 2.5678 (2.5774) grad: 0.1862 (0.1741) time: 0.4532 data: 0.0042 max mem: 20773 +train: [15] [160/400] eta: 0:01:49 lr: 0.000064 loss: 2.5239 (2.5491) grad: 0.1525 (0.1651) time: 0.4431 data: 0.0050 max mem: 22449 +train: [14] [340/400] eta: 0:00:27 lr: 0.000079 loss: 2.5678 (2.5781) grad: 0.1714 (0.1738) time: 0.4578 data: 0.0042 max mem: 20773 +train: [15] [180/400] eta: 0:01:40 lr: 0.000063 loss: 2.5601 (2.5498) grad: 0.1594 (0.1655) time: 0.4457 data: 0.0051 max mem: 22449 +train: [14] [360/400] eta: 0:00:18 lr: 0.000078 loss: 2.5606 (2.5754) grad: 0.1708 (0.1735) time: 0.4543 data: 0.0043 max mem: 20773 +train: [15] [200/400] eta: 0:01:30 lr: 0.000062 loss: 2.5689 (2.5520) grad: 0.1662 (0.1665) time: 0.4302 data: 0.0048 max mem: 22449 +train: [14] [380/400] eta: 0:00:09 lr: 0.000076 loss: 2.5408 (2.5746) grad: 0.1760 (0.1736) time: 0.4529 data: 0.0042 max mem: 20773 +train: [15] [220/400] eta: 0:01:21 lr: 0.000061 loss: 2.5507 (2.5513) grad: 0.1662 (0.1667) time: 0.4545 data: 0.0053 max mem: 22449 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.5973 (2.5751) grad: 0.1733 (0.1733) time: 0.4670 data: 0.0044 max mem: 20773 +train: [14] Total time: 0:03:04 (0.4622 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.5973 (2.5751) grad: 0.1733 (0.1733) +train: [15] [240/400] eta: 0:01:12 lr: 0.000059 loss: 2.5711 (2.5563) grad: 0.1679 (0.1674) time: 0.4443 data: 0.0051 max mem: 22449 +eval (validation): [14] [ 0/85] eta: 0:04:47 time: 3.3772 data: 3.0941 max mem: 20773 +train: [15] [260/400] eta: 0:01:03 lr: 0.000058 loss: 2.6115 (2.5585) grad: 0.1623 (0.1670) time: 0.4335 data: 0.0050 max mem: 22449 +eval (validation): [14] [20/85] eta: 0:00:33 time: 0.3784 data: 0.0042 max mem: 20773 +train: [15] [280/400] eta: 0:00:54 lr: 0.000057 loss: 2.5725 (2.5567) grad: 0.1645 (0.1674) time: 0.4351 data: 0.0051 max mem: 22449 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3516 data: 0.0040 max mem: 20773 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3461 data: 0.0042 max mem: 20773 +train: [15] [300/400] eta: 0:00:44 lr: 0.000056 loss: 2.5795 (2.5599) grad: 0.1705 (0.1675) time: 0.4405 data: 0.0049 max mem: 22449 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3308 data: 0.0039 max mem: 20773 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3214 data: 0.0035 max mem: 20773 +eval (validation): [14] Total time: 0:00:33 (0.3888 s / it) +cv: [14] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.434 acc: 0.271 f1: 0.207 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [320/400] eta: 0:00:35 lr: 0.000054 loss: 2.5799 (2.5616) grad: 0.1638 (0.1667) time: 0.4510 data: 0.0049 max mem: 22449 +train: [15] [ 0/400] eta: 0:22:48 lr: nan time: 3.4210 data: 3.0464 max mem: 20773 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 2.5519 (2.5610) grad: 0.1516 (0.1669) time: 0.4661 data: 0.0053 max mem: 22449 +train: [15] [ 20/400] eta: 0:03:45 lr: 0.000074 loss: 2.5648 (2.5696) grad: 0.1618 (0.1663) time: 0.4508 data: 0.0038 max mem: 20773 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 2.5529 (2.5616) grad: 0.1529 (0.1664) time: 0.4503 data: 0.0050 max mem: 22449 +train: [15] [ 40/400] eta: 0:03:10 lr: 0.000072 loss: 2.5680 (2.5853) grad: 0.1618 (0.1663) time: 0.4648 data: 0.0037 max mem: 20773 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.5794 (2.5636) grad: 0.1649 (0.1663) time: 0.4464 data: 0.0049 max mem: 22449 +train: [15] [ 60/400] eta: 0:02:49 lr: 0.000071 loss: 2.5590 (2.5731) grad: 0.1646 (0.1696) time: 0.4368 data: 0.0040 max mem: 20773 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.5410 (2.5632) grad: 0.1654 (0.1659) time: 0.4645 data: 0.0052 max mem: 22449 +train: [15] Total time: 0:03:00 (0.4518 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.5410 (2.5632) grad: 0.1654 (0.1659) +train: [15] [ 80/400] eta: 0:02:37 lr: 0.000070 loss: 2.5076 (2.5589) grad: 0.1630 (0.1688) time: 0.4687 data: 0.0042 max mem: 20773 +eval (validation): [15] [ 0/85] eta: 0:04:29 time: 3.1760 data: 2.9371 max mem: 22449 +eval (validation): [15] [20/85] eta: 0:00:31 time: 0.3422 data: 0.0042 max mem: 22449 +train: [15] [100/400] eta: 0:02:25 lr: 0.000068 loss: 2.5300 (2.5613) grad: 0.1611 (0.1685) time: 0.4543 data: 0.0042 max mem: 20773 +eval (validation): [15] [40/85] eta: 0:00:18 time: 0.3583 data: 0.0039 max mem: 22449 +train: [15] [120/400] eta: 0:02:14 lr: 0.000067 loss: 2.5415 (2.5591) grad: 0.1581 (0.1675) time: 0.4531 data: 0.0039 max mem: 20773 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3449 data: 0.0042 max mem: 22449 +train: [15] [140/400] eta: 0:02:03 lr: 0.000066 loss: 2.5480 (2.5552) grad: 0.1581 (0.1667) time: 0.4398 data: 0.0041 max mem: 20773 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3409 data: 0.0043 max mem: 22449 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3354 data: 0.0043 max mem: 22449 +eval (validation): [15] Total time: 0:00:32 (0.3816 s / it) +cv: [15] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.443 acc: 0.275 f1: 0.209 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [15] [160/400] eta: 0:01:53 lr: 0.000064 loss: 2.5150 (2.5532) grad: 0.1638 (0.1668) time: 0.4580 data: 0.0040 max mem: 20773 +train: [16] [ 0/400] eta: 0:20:52 lr: nan time: 3.1322 data: 2.8139 max mem: 22449 +train: [15] [180/400] eta: 0:01:43 lr: 0.000063 loss: 2.5321 (2.5545) grad: 0.1604 (0.1664) time: 0.4517 data: 0.0041 max mem: 20773 +train: [16] [ 20/400] eta: 0:03:37 lr: 0.000048 loss: 2.6086 (2.5991) grad: 0.1488 (0.1529) time: 0.4451 data: 0.0034 max mem: 22449 +train: [15] [200/400] eta: 0:01:33 lr: 0.000062 loss: 2.5430 (2.5535) grad: 0.1602 (0.1670) time: 0.4519 data: 0.0041 max mem: 20773 +train: [16] [ 40/400] eta: 0:03:08 lr: 0.000047 loss: 2.5728 (2.5740) grad: 0.1512 (0.1590) time: 0.4716 data: 0.0048 max mem: 22449 +train: [15] [220/400] eta: 0:01:23 lr: 0.000061 loss: 2.5867 (2.5575) grad: 0.1740 (0.1678) time: 0.4473 data: 0.0041 max mem: 20773 +train: [16] [ 60/400] eta: 0:02:49 lr: 0.000046 loss: 2.5561 (2.5755) grad: 0.1631 (0.1616) time: 0.4513 data: 0.0050 max mem: 22449 +train: [15] [240/400] eta: 0:01:14 lr: 0.000059 loss: 2.5465 (2.5552) grad: 0.1729 (0.1677) time: 0.4570 data: 0.0042 max mem: 20773 +train: [16] [ 80/400] eta: 0:02:35 lr: 0.000045 loss: 2.5588 (2.5714) grad: 0.1612 (0.1626) time: 0.4415 data: 0.0050 max mem: 22449 +train: [15] [260/400] eta: 0:01:05 lr: 0.000058 loss: 2.5373 (2.5555) grad: 0.1655 (0.1676) time: 0.4540 data: 0.0041 max mem: 20773 +train: [16] [100/400] eta: 0:02:23 lr: 0.000044 loss: 2.5476 (2.5667) grad: 0.1691 (0.1653) time: 0.4443 data: 0.0048 max mem: 22449 +train: [15] [280/400] eta: 0:00:55 lr: 0.000057 loss: 2.5360 (2.5538) grad: 0.1577 (0.1674) time: 0.4579 data: 0.0041 max mem: 20773 +train: [16] [120/400] eta: 0:02:11 lr: 0.000043 loss: 2.5566 (2.5681) grad: 0.1759 (0.1673) time: 0.4375 data: 0.0049 max mem: 22449 +train: [15] [300/400] eta: 0:00:46 lr: 0.000056 loss: 2.5391 (2.5539) grad: 0.1603 (0.1670) time: 0.4450 data: 0.0042 max mem: 20773 +train: [16] [140/400] eta: 0:02:01 lr: 0.000042 loss: 2.5775 (2.5684) grad: 0.1632 (0.1668) time: 0.4368 data: 0.0050 max mem: 22449 +train: [15] [320/400] eta: 0:00:36 lr: 0.000054 loss: 2.5657 (2.5540) grad: 0.1581 (0.1668) time: 0.4489 data: 0.0042 max mem: 20773 +train: [16] [160/400] eta: 0:01:51 lr: 0.000041 loss: 2.5664 (2.5701) grad: 0.1632 (0.1675) time: 0.4548 data: 0.0052 max mem: 22449 +train: [15] [340/400] eta: 0:00:27 lr: 0.000053 loss: 2.5699 (2.5554) grad: 0.1668 (0.1665) time: 0.4518 data: 0.0041 max mem: 20773 +train: [16] [180/400] eta: 0:01:41 lr: 0.000040 loss: 2.5588 (2.5675) grad: 0.1652 (0.1671) time: 0.4458 data: 0.0051 max mem: 22449 +train: [15] [360/400] eta: 0:00:18 lr: 0.000052 loss: 2.5658 (2.5560) grad: 0.1544 (0.1656) time: 0.4489 data: 0.0041 max mem: 20773 +train: [16] [200/400] eta: 0:01:31 lr: 0.000039 loss: 2.5416 (2.5660) grad: 0.1586 (0.1662) time: 0.4279 data: 0.0050 max mem: 22449 +train: [15] [380/400] eta: 0:00:09 lr: 0.000051 loss: 2.5658 (2.5567) grad: 0.1493 (0.1653) time: 0.4677 data: 0.0041 max mem: 20773 +train: [16] [220/400] eta: 0:01:22 lr: 0.000038 loss: 2.5370 (2.5636) grad: 0.1607 (0.1660) time: 0.4700 data: 0.0050 max mem: 22449 +train: [16] [240/400] eta: 0:01:13 lr: 0.000036 loss: 2.5243 (2.5613) grad: 0.1574 (0.1653) time: 0.4309 data: 0.0049 max mem: 22449 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.5743 (2.5565) grad: 0.1635 (0.1651) time: 0.4837 data: 0.0043 max mem: 20773 +train: [15] Total time: 0:03:04 (0.4623 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.5743 (2.5565) grad: 0.1635 (0.1651) +eval (validation): [15] [ 0/85] eta: 0:04:38 time: 3.2767 data: 3.0344 max mem: 20773 +train: [16] [260/400] eta: 0:01:03 lr: 0.000035 loss: 2.5251 (2.5586) grad: 0.1603 (0.1659) time: 0.4322 data: 0.0049 max mem: 22449 +eval (validation): [15] [20/85] eta: 0:00:32 time: 0.3584 data: 0.0053 max mem: 20773 +train: [16] [280/400] eta: 0:00:54 lr: 0.000034 loss: 2.5483 (2.5567) grad: 0.1685 (0.1661) time: 0.4372 data: 0.0049 max mem: 22449 +eval (validation): [15] [40/85] eta: 0:00:18 time: 0.3419 data: 0.0039 max mem: 20773 +train: [16] [300/400] eta: 0:00:45 lr: 0.000033 loss: 2.5379 (2.5549) grad: 0.1671 (0.1656) time: 0.4346 data: 0.0049 max mem: 22449 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3658 data: 0.0047 max mem: 20773 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3262 data: 0.0041 max mem: 20773 +train: [16] [320/400] eta: 0:00:36 lr: 0.000032 loss: 2.5162 (2.5543) grad: 0.1540 (0.1654) time: 0.4348 data: 0.0049 max mem: 22449 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3224 data: 0.0041 max mem: 20773 +eval (validation): [15] Total time: 0:00:32 (0.3847 s / it) +cv: [15] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.429 acc: 0.272 f1: 0.207 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:22:53 lr: nan time: 3.4342 data: 3.0477 max mem: 20773 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 2.5331 (2.5536) grad: 0.1537 (0.1652) time: 0.4476 data: 0.0049 max mem: 22449 +train: [16] [ 20/400] eta: 0:03:59 lr: 0.000048 loss: 2.4893 (2.5126) grad: 0.1484 (0.1566) time: 0.4904 data: 0.0034 max mem: 20773 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 2.5674 (2.5547) grad: 0.1556 (0.1649) time: 0.4416 data: 0.0050 max mem: 22449 +train: [16] [ 40/400] eta: 0:03:17 lr: 0.000047 loss: 2.5387 (2.5314) grad: 0.1532 (0.1561) time: 0.4617 data: 0.0037 max mem: 20773 +train: [16] [380/400] eta: 0:00:08 lr: 0.000030 loss: 2.5462 (2.5527) grad: 0.1536 (0.1645) time: 0.4287 data: 0.0049 max mem: 22449 +train: [16] [ 60/400] eta: 0:02:55 lr: 0.000046 loss: 2.5487 (2.5382) grad: 0.1532 (0.1566) time: 0.4537 data: 0.0041 max mem: 20773 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.5386 (2.5526) grad: 0.1543 (0.1644) time: 0.4768 data: 0.0051 max mem: 22449 +train: [16] Total time: 0:03:00 (0.4518 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.5386 (2.5526) grad: 0.1543 (0.1644) +eval (validation): [16] [ 0/85] eta: 0:04:30 time: 3.1789 data: 2.9371 max mem: 22449 +train: [16] [ 80/400] eta: 0:02:41 lr: 0.000045 loss: 2.5738 (2.5458) grad: 0.1513 (0.1564) time: 0.4635 data: 0.0042 max mem: 20773 +eval (validation): [16] [20/85] eta: 0:00:30 time: 0.3316 data: 0.0043 max mem: 22449 +train: [16] [100/400] eta: 0:02:27 lr: 0.000044 loss: 2.5621 (2.5459) grad: 0.1577 (0.1583) time: 0.4460 data: 0.0043 max mem: 20773 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3485 data: 0.0034 max mem: 22449 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3595 data: 0.0046 max mem: 22449 +train: [16] [120/400] eta: 0:02:15 lr: 0.000043 loss: 2.5378 (2.5470) grad: 0.1703 (0.1611) time: 0.4400 data: 0.0041 max mem: 20773 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3343 data: 0.0041 max mem: 22449 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3265 data: 0.0043 max mem: 22449 +eval (validation): [16] Total time: 0:00:32 (0.3801 s / it) +cv: [16] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.421 acc: 0.278 f1: 0.209 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [16] [140/400] eta: 0:02:04 lr: 0.000042 loss: 2.5747 (2.5529) grad: 0.1676 (0.1617) time: 0.4425 data: 0.0040 max mem: 20773 +train: [17] [ 0/400] eta: 0:21:36 lr: nan time: 3.2419 data: 2.8836 max mem: 22449 +train: [16] [160/400] eta: 0:01:54 lr: 0.000041 loss: 2.5747 (2.5547) grad: 0.1574 (0.1627) time: 0.4565 data: 0.0042 max mem: 20773 +train: [17] [ 20/400] eta: 0:03:41 lr: 0.000028 loss: 2.5574 (2.5586) grad: 0.1655 (0.1617) time: 0.4492 data: 0.0048 max mem: 22449 +train: [16] [180/400] eta: 0:01:44 lr: 0.000040 loss: 2.5697 (2.5546) grad: 0.1658 (0.1626) time: 0.4533 data: 0.0041 max mem: 20773 +train: [17] [ 40/400] eta: 0:03:08 lr: 0.000027 loss: 2.5414 (2.5510) grad: 0.1655 (0.1628) time: 0.4641 data: 0.0050 max mem: 22449 +train: [16] [200/400] eta: 0:01:34 lr: 0.000039 loss: 2.5561 (2.5538) grad: 0.1600 (0.1624) time: 0.4449 data: 0.0043 max mem: 20773 +train: [17] [ 60/400] eta: 0:02:49 lr: 0.000026 loss: 2.5414 (2.5613) grad: 0.1676 (0.1655) time: 0.4416 data: 0.0051 max mem: 22449 +train: [16] [220/400] eta: 0:01:24 lr: 0.000038 loss: 2.5472 (2.5556) grad: 0.1510 (0.1615) time: 0.4474 data: 0.0042 max mem: 20773 +train: [17] [ 80/400] eta: 0:02:36 lr: 0.000025 loss: 2.5441 (2.5563) grad: 0.1561 (0.1630) time: 0.4626 data: 0.0050 max mem: 22449 +train: [16] [240/400] eta: 0:01:14 lr: 0.000036 loss: 2.5545 (2.5581) grad: 0.1472 (0.1611) time: 0.4530 data: 0.0043 max mem: 20773 +train: [17] [100/400] eta: 0:02:23 lr: 0.000024 loss: 2.5160 (2.5552) grad: 0.1466 (0.1610) time: 0.4386 data: 0.0047 max mem: 22449 +train: [16] [260/400] eta: 0:01:05 lr: 0.000035 loss: 2.5837 (2.5591) grad: 0.1536 (0.1615) time: 0.4557 data: 0.0044 max mem: 20773 +train: [17] [120/400] eta: 0:02:12 lr: 0.000023 loss: 2.5034 (2.5459) grad: 0.1438 (0.1595) time: 0.4437 data: 0.0048 max mem: 22449 +train: [16] [280/400] eta: 0:00:55 lr: 0.000034 loss: 2.5894 (2.5615) grad: 0.1536 (0.1612) time: 0.4396 data: 0.0042 max mem: 20773 +train: [17] [140/400] eta: 0:02:02 lr: 0.000023 loss: 2.5315 (2.5493) grad: 0.1528 (0.1608) time: 0.4522 data: 0.0050 max mem: 22449 +train: [16] [300/400] eta: 0:00:46 lr: 0.000033 loss: 2.5525 (2.5611) grad: 0.1618 (0.1617) time: 0.4525 data: 0.0042 max mem: 20773 +train: [17] [160/400] eta: 0:01:52 lr: 0.000022 loss: 2.5674 (2.5503) grad: 0.1561 (0.1604) time: 0.4675 data: 0.0051 max mem: 22449 +train: [16] [320/400] eta: 0:00:37 lr: 0.000032 loss: 2.5415 (2.5591) grad: 0.1618 (0.1617) time: 0.4529 data: 0.0046 max mem: 20773 +train: [17] [180/400] eta: 0:01:42 lr: 0.000021 loss: 2.5674 (2.5500) grad: 0.1625 (0.1608) time: 0.4502 data: 0.0049 max mem: 22449 +train: [16] [340/400] eta: 0:00:27 lr: 0.000031 loss: 2.5622 (2.5605) grad: 0.1567 (0.1616) time: 0.4555 data: 0.0041 max mem: 20773 +train: [17] [200/400] eta: 0:01:32 lr: 0.000020 loss: 2.5507 (2.5491) grad: 0.1637 (0.1607) time: 0.4390 data: 0.0048 max mem: 22449 +train: [16] [360/400] eta: 0:00:18 lr: 0.000031 loss: 2.5800 (2.5598) grad: 0.1531 (0.1619) time: 0.4336 data: 0.0040 max mem: 20773 +train: [17] [220/400] eta: 0:01:23 lr: 0.000019 loss: 2.5567 (2.5506) grad: 0.1558 (0.1607) time: 0.4763 data: 0.0050 max mem: 22449 +train: [16] [380/400] eta: 0:00:09 lr: 0.000030 loss: 2.5401 (2.5597) grad: 0.1641 (0.1623) time: 0.4525 data: 0.0041 max mem: 20773 +train: [17] [240/400] eta: 0:01:14 lr: 0.000019 loss: 2.5735 (2.5500) grad: 0.1583 (0.1606) time: 0.4497 data: 0.0049 max mem: 22449 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.5495 (2.5599) grad: 0.1641 (0.1622) time: 0.4578 data: 0.0040 max mem: 20773 +train: [16] Total time: 0:03:04 (0.4604 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.5495 (2.5599) grad: 0.1641 (0.1622) +eval (validation): [16] [ 0/85] eta: 0:04:24 time: 3.1065 data: 2.8757 max mem: 20773 +train: [17] [260/400] eta: 0:01:04 lr: 0.000018 loss: 2.5709 (2.5523) grad: 0.1598 (0.1612) time: 0.4498 data: 0.0051 max mem: 22449 +eval (validation): [16] [20/85] eta: 0:00:29 time: 0.3231 data: 0.0035 max mem: 20773 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 2.5377 (2.5498) grad: 0.1599 (0.1612) time: 0.4369 data: 0.0051 max mem: 22449 +eval (validation): [16] [40/85] eta: 0:00:17 time: 0.3389 data: 0.0040 max mem: 20773 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3566 data: 0.0040 max mem: 20773 +train: [17] [300/400] eta: 0:00:46 lr: 0.000016 loss: 2.5508 (2.5545) grad: 0.1560 (0.1609) time: 0.4400 data: 0.0051 max mem: 22449 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3342 data: 0.0038 max mem: 20773 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3256 data: 0.0037 max mem: 20773 +eval (validation): [16] Total time: 0:00:31 (0.3728 s / it) +cv: [16] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.423 acc: 0.274 f1: 0.207 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [320/400] eta: 0:00:36 lr: 0.000016 loss: 2.5806 (2.5554) grad: 0.1560 (0.1612) time: 0.4514 data: 0.0051 max mem: 22449 +train: [17] [ 0/400] eta: 0:21:46 lr: nan time: 3.2665 data: 2.8917 max mem: 20773 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 2.5563 (2.5541) grad: 0.1605 (0.1606) time: 0.4632 data: 0.0053 max mem: 22449 +train: [17] [ 20/400] eta: 0:03:53 lr: 0.000028 loss: 2.5306 (2.5539) grad: 0.1442 (0.1523) time: 0.4807 data: 0.0045 max mem: 20773 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 2.5141 (2.5520) grad: 0.1541 (0.1599) time: 0.4586 data: 0.0054 max mem: 22449 +train: [17] [ 40/400] eta: 0:03:11 lr: 0.000027 loss: 2.5010 (2.5351) grad: 0.1557 (0.1545) time: 0.4473 data: 0.0044 max mem: 20773 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 2.5161 (2.5518) grad: 0.1547 (0.1597) time: 0.4356 data: 0.0049 max mem: 22449 +train: [17] [ 60/400] eta: 0:02:49 lr: 0.000026 loss: 2.4894 (2.5234) grad: 0.1523 (0.1539) time: 0.4335 data: 0.0042 max mem: 20773 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.5542 (2.5526) grad: 0.1547 (0.1590) time: 0.4660 data: 0.0051 max mem: 22449 +train: [17] Total time: 0:03:03 (0.4594 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.5542 (2.5526) grad: 0.1547 (0.1590) +train: [17] [ 80/400] eta: 0:02:35 lr: 0.000025 loss: 2.5690 (2.5401) grad: 0.1475 (0.1549) time: 0.4449 data: 0.0043 max mem: 20773 +eval (validation): [17] [ 0/85] eta: 0:04:38 time: 3.2725 data: 2.9721 max mem: 22449 +eval (validation): [17] [20/85] eta: 0:00:32 time: 0.3657 data: 0.0051 max mem: 22449 +train: [17] [100/400] eta: 0:02:23 lr: 0.000024 loss: 2.5441 (2.5378) grad: 0.1476 (0.1532) time: 0.4498 data: 0.0043 max mem: 20773 +eval (validation): [17] [40/85] eta: 0:00:19 time: 0.3392 data: 0.0040 max mem: 22449 +train: [17] [120/400] eta: 0:02:12 lr: 0.000023 loss: 2.5165 (2.5386) grad: 0.1486 (0.1546) time: 0.4493 data: 0.0042 max mem: 20773 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.3572 data: 0.0043 max mem: 22449 +train: [17] [140/400] eta: 0:02:02 lr: 0.000023 loss: 2.5408 (2.5370) grad: 0.1541 (0.1555) time: 0.4512 data: 0.0041 max mem: 20773 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3373 data: 0.0043 max mem: 22449 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3282 data: 0.0042 max mem: 22449 +eval (validation): [17] Total time: 0:00:32 (0.3861 s / it) +cv: [17] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.420 acc: 0.275 f1: 0.208 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [17] [160/400] eta: 0:01:52 lr: 0.000022 loss: 2.5367 (2.5371) grad: 0.1608 (0.1563) time: 0.4545 data: 0.0041 max mem: 20773 +train: [18] [ 0/400] eta: 0:21:28 lr: nan time: 3.2204 data: 2.8601 max mem: 22449 +train: [17] [180/400] eta: 0:01:42 lr: 0.000021 loss: 2.5367 (2.5396) grad: 0.1525 (0.1550) time: 0.4509 data: 0.0041 max mem: 20773 +train: [18] [ 20/400] eta: 0:03:43 lr: 0.000012 loss: 2.5552 (2.5703) grad: 0.1530 (0.1514) time: 0.4574 data: 0.0032 max mem: 22449 +train: [17] [200/400] eta: 0:01:32 lr: 0.000020 loss: 2.5587 (2.5420) grad: 0.1551 (0.1560) time: 0.4447 data: 0.0043 max mem: 20773 +train: [18] [ 40/400] eta: 0:03:14 lr: 0.000012 loss: 2.5510 (2.5464) grad: 0.1525 (0.1546) time: 0.4865 data: 0.0050 max mem: 22449 +train: [17] [220/400] eta: 0:01:23 lr: 0.000019 loss: 2.5443 (2.5415) grad: 0.1584 (0.1559) time: 0.4510 data: 0.0047 max mem: 20773 +train: [18] [ 60/400] eta: 0:02:53 lr: 0.000011 loss: 2.5258 (2.5521) grad: 0.1493 (0.1539) time: 0.4484 data: 0.0053 max mem: 22449 +train: [17] [240/400] eta: 0:01:14 lr: 0.000019 loss: 2.5321 (2.5422) grad: 0.1565 (0.1565) time: 0.4559 data: 0.0042 max mem: 20773 +train: [18] [ 80/400] eta: 0:02:38 lr: 0.000011 loss: 2.5578 (2.5598) grad: 0.1435 (0.1533) time: 0.4485 data: 0.0051 max mem: 22449 +train: [17] [260/400] eta: 0:01:04 lr: 0.000018 loss: 2.5198 (2.5418) grad: 0.1531 (0.1561) time: 0.4552 data: 0.0042 max mem: 20773 +train: [18] [100/400] eta: 0:02:25 lr: 0.000010 loss: 2.5657 (2.5580) grad: 0.1489 (0.1536) time: 0.4506 data: 0.0051 max mem: 22449 +train: [17] [280/400] eta: 0:00:55 lr: 0.000017 loss: 2.4981 (2.5404) grad: 0.1516 (0.1562) time: 0.4553 data: 0.0044 max mem: 20773 +train: [18] [120/400] eta: 0:02:14 lr: 0.000009 loss: 2.5261 (2.5532) grad: 0.1561 (0.1556) time: 0.4505 data: 0.0051 max mem: 22449 +train: [17] [300/400] eta: 0:00:45 lr: 0.000016 loss: 2.5140 (2.5410) grad: 0.1573 (0.1565) time: 0.4302 data: 0.0040 max mem: 20773 +train: [18] [140/400] eta: 0:02:04 lr: 0.000009 loss: 2.5536 (2.5566) grad: 0.1526 (0.1548) time: 0.4657 data: 0.0051 max mem: 22449 +train: [17] [320/400] eta: 0:00:36 lr: 0.000016 loss: 2.5337 (2.5426) grad: 0.1601 (0.1572) time: 0.4488 data: 0.0042 max mem: 20773 +train: [18] [160/400] eta: 0:01:54 lr: 0.000008 loss: 2.5653 (2.5558) grad: 0.1600 (0.1567) time: 0.4669 data: 0.0051 max mem: 22449 +train: [17] [340/400] eta: 0:00:27 lr: 0.000015 loss: 2.5291 (2.5419) grad: 0.1568 (0.1570) time: 0.4350 data: 0.0040 max mem: 20773 +train: [18] [180/400] eta: 0:01:44 lr: 0.000008 loss: 2.5497 (2.5540) grad: 0.1639 (0.1566) time: 0.4466 data: 0.0047 max mem: 22449 +train: [17] [360/400] eta: 0:00:18 lr: 0.000014 loss: 2.5309 (2.5434) grad: 0.1564 (0.1573) time: 0.4285 data: 0.0040 max mem: 20773 +train: [18] [200/400] eta: 0:01:34 lr: 0.000007 loss: 2.5271 (2.5491) grad: 0.1490 (0.1562) time: 0.4486 data: 0.0049 max mem: 22449 +train: [17] [380/400] eta: 0:00:09 lr: 0.000014 loss: 2.5473 (2.5428) grad: 0.1595 (0.1576) time: 0.4600 data: 0.0043 max mem: 20773 +train: [18] [220/400] eta: 0:01:24 lr: 0.000007 loss: 2.5271 (2.5477) grad: 0.1465 (0.1553) time: 0.4594 data: 0.0049 max mem: 22449 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.5220 (2.5412) grad: 0.1595 (0.1577) time: 0.4624 data: 0.0044 max mem: 20773 +train: [17] Total time: 0:03:02 (0.4568 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.5220 (2.5412) grad: 0.1595 (0.1577) +train: [18] [240/400] eta: 0:01:14 lr: 0.000006 loss: 2.5417 (2.5457) grad: 0.1458 (0.1545) time: 0.4516 data: 0.0050 max mem: 22449 +eval (validation): [17] [ 0/85] eta: 0:04:46 time: 3.3662 data: 3.1180 max mem: 20773 +eval (validation): [17] [20/85] eta: 0:00:32 time: 0.3612 data: 0.0047 max mem: 20773 +train: [18] [260/400] eta: 0:01:05 lr: 0.000006 loss: 2.5415 (2.5472) grad: 0.1469 (0.1544) time: 0.4471 data: 0.0047 max mem: 22449 +eval (validation): [17] [40/85] eta: 0:00:19 time: 0.3475 data: 0.0035 max mem: 20773 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 2.5415 (2.5465) grad: 0.1448 (0.1539) time: 0.4491 data: 0.0051 max mem: 22449 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.4224 data: 0.0047 max mem: 20773 +train: [18] [300/400] eta: 0:00:46 lr: 0.000005 loss: 2.5349 (2.5456) grad: 0.1430 (0.1533) time: 0.4467 data: 0.0051 max mem: 22449 +eval (validation): [17] [80/85] eta: 0:00:02 time: 0.3552 data: 0.0043 max mem: 20773 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3425 data: 0.0041 max mem: 20773 +eval (validation): [17] Total time: 0:00:34 (0.4075 s / it) +cv: [17] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.429 acc: 0.275 f1: 0.207 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [320/400] eta: 0:00:37 lr: 0.000005 loss: 2.5458 (2.5451) grad: 0.1452 (0.1532) time: 0.4516 data: 0.0050 max mem: 22449 +train: [18] [ 0/400] eta: 0:22:38 lr: nan time: 3.3957 data: 3.0143 max mem: 20773 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 2.5446 (2.5465) grad: 0.1561 (0.1532) time: 0.4704 data: 0.0052 max mem: 22449 +train: [18] [ 20/400] eta: 0:03:39 lr: 0.000012 loss: 2.5139 (2.5130) grad: 0.1525 (0.1598) time: 0.4376 data: 0.0043 max mem: 20773 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 2.5362 (2.5462) grad: 0.1488 (0.1530) time: 0.4498 data: 0.0050 max mem: 22449 +train: [18] [ 40/400] eta: 0:03:06 lr: 0.000012 loss: 2.5240 (2.5203) grad: 0.1513 (0.1538) time: 0.4571 data: 0.0039 max mem: 20773 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 2.5341 (2.5464) grad: 0.1576 (0.1535) time: 0.4625 data: 0.0050 max mem: 22449 +train: [18] [ 60/400] eta: 0:02:48 lr: 0.000011 loss: 2.5240 (2.5304) grad: 0.1568 (0.1546) time: 0.4434 data: 0.0042 max mem: 20773 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.5588 (2.5475) grad: 0.1630 (0.1538) time: 0.4652 data: 0.0049 max mem: 22449 +train: [18] Total time: 0:03:05 (0.4636 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.5588 (2.5475) grad: 0.1630 (0.1538) +train: [18] [ 80/400] eta: 0:02:34 lr: 0.000011 loss: 2.5319 (2.5362) grad: 0.1568 (0.1537) time: 0.4488 data: 0.0041 max mem: 20773 +eval (validation): [18] [ 0/85] eta: 0:04:25 time: 3.1253 data: 2.8828 max mem: 22449 +train: [18] [100/400] eta: 0:02:22 lr: 0.000010 loss: 2.5538 (2.5430) grad: 0.1578 (0.1558) time: 0.4466 data: 0.0041 max mem: 20773 +eval (validation): [18] [20/85] eta: 0:00:30 time: 0.3380 data: 0.0048 max mem: 22449 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3478 data: 0.0038 max mem: 22449 +train: [18] [120/400] eta: 0:02:11 lr: 0.000009 loss: 2.5495 (2.5436) grad: 0.1505 (0.1552) time: 0.4413 data: 0.0042 max mem: 20773 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3639 data: 0.0042 max mem: 22449 +train: [18] [140/400] eta: 0:02:01 lr: 0.000009 loss: 2.5268 (2.5390) grad: 0.1487 (0.1557) time: 0.4389 data: 0.0042 max mem: 20773 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3402 data: 0.0042 max mem: 22449 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3328 data: 0.0041 max mem: 22449 +eval (validation): [18] Total time: 0:00:32 (0.3827 s / it) +cv: [18] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.441 acc: 0.275 f1: 0.206 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [18] [160/400] eta: 0:01:51 lr: 0.000008 loss: 2.5123 (2.5464) grad: 0.1434 (0.1545) time: 0.4506 data: 0.0043 max mem: 20773 +train: [19] [ 0/400] eta: 0:21:52 lr: nan time: 3.2812 data: 2.8936 max mem: 22449 +train: [18] [180/400] eta: 0:01:41 lr: 0.000008 loss: 2.5124 (2.5385) grad: 0.1418 (0.1546) time: 0.4401 data: 0.0041 max mem: 20773 +train: [19] [ 20/400] eta: 0:03:45 lr: 0.000003 loss: 2.5201 (2.5324) grad: 0.1580 (0.1575) time: 0.4598 data: 0.0028 max mem: 22449 +train: [18] [200/400] eta: 0:01:32 lr: 0.000007 loss: 2.4834 (2.5350) grad: 0.1486 (0.1538) time: 0.4517 data: 0.0043 max mem: 20773 +train: [19] [ 40/400] eta: 0:03:09 lr: 0.000003 loss: 2.5061 (2.5071) grad: 0.1587 (0.1570) time: 0.4554 data: 0.0050 max mem: 22449 +train: [18] [220/400] eta: 0:01:22 lr: 0.000007 loss: 2.5135 (2.5359) grad: 0.1551 (0.1547) time: 0.4585 data: 0.0042 max mem: 20773 +train: [19] [ 60/400] eta: 0:02:50 lr: 0.000002 loss: 2.4939 (2.5070) grad: 0.1505 (0.1539) time: 0.4485 data: 0.0051 max mem: 22449 +train: [18] [240/400] eta: 0:01:13 lr: 0.000006 loss: 2.5219 (2.5367) grad: 0.1582 (0.1550) time: 0.4420 data: 0.0043 max mem: 20773 +train: [19] [ 80/400] eta: 0:02:35 lr: 0.000002 loss: 2.5442 (2.5214) grad: 0.1448 (0.1514) time: 0.4460 data: 0.0051 max mem: 22449 +train: [18] [260/400] eta: 0:01:04 lr: 0.000006 loss: 2.5514 (2.5390) grad: 0.1509 (0.1549) time: 0.4556 data: 0.0043 max mem: 20773 +train: [19] [100/400] eta: 0:02:23 lr: 0.000002 loss: 2.5417 (2.5178) grad: 0.1466 (0.1513) time: 0.4469 data: 0.0051 max mem: 22449 +train: [18] [280/400] eta: 0:00:55 lr: 0.000006 loss: 2.5608 (2.5398) grad: 0.1536 (0.1556) time: 0.4605 data: 0.0044 max mem: 20773 +train: [19] [120/400] eta: 0:02:12 lr: 0.000002 loss: 2.5380 (2.5254) grad: 0.1475 (0.1515) time: 0.4382 data: 0.0049 max mem: 22449 +train: [18] [300/400] eta: 0:00:45 lr: 0.000005 loss: 2.5492 (2.5393) grad: 0.1539 (0.1554) time: 0.4483 data: 0.0043 max mem: 20773 +train: [19] [140/400] eta: 0:02:02 lr: 0.000001 loss: 2.5015 (2.5201) grad: 0.1518 (0.1516) time: 0.4625 data: 0.0051 max mem: 22449 +train: [18] [320/400] eta: 0:00:36 lr: 0.000005 loss: 2.5363 (2.5390) grad: 0.1539 (0.1555) time: 0.4268 data: 0.0041 max mem: 20773 +train: [19] [160/400] eta: 0:01:52 lr: 0.000001 loss: 2.4804 (2.5186) grad: 0.1557 (0.1533) time: 0.4625 data: 0.0051 max mem: 22449 +train: [18] [340/400] eta: 0:00:27 lr: 0.000004 loss: 2.5363 (2.5411) grad: 0.1539 (0.1553) time: 0.4363 data: 0.0039 max mem: 20773 +train: [19] [180/400] eta: 0:01:42 lr: 0.000001 loss: 2.5472 (2.5231) grad: 0.1617 (0.1552) time: 0.4416 data: 0.0048 max mem: 22449 +train: [18] [360/400] eta: 0:00:18 lr: 0.000004 loss: 2.5481 (2.5409) grad: 0.1581 (0.1563) time: 0.4480 data: 0.0041 max mem: 20773 +train: [19] [200/400] eta: 0:01:33 lr: 0.000001 loss: 2.5553 (2.5279) grad: 0.1629 (0.1552) time: 0.4647 data: 0.0051 max mem: 22449 +train: [18] [380/400] eta: 0:00:09 lr: 0.000004 loss: 2.5306 (2.5427) grad: 0.1555 (0.1561) time: 0.4581 data: 0.0042 max mem: 20773 +train: [19] [220/400] eta: 0:01:23 lr: 0.000001 loss: 2.5535 (2.5269) grad: 0.1548 (0.1549) time: 0.4608 data: 0.0049 max mem: 22449 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.4903 (2.5398) grad: 0.1502 (0.1559) time: 0.4512 data: 0.0042 max mem: 20773 +train: [18] Total time: 0:03:01 (0.4547 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.4903 (2.5398) grad: 0.1502 (0.1559) +eval (validation): [18] [ 0/85] eta: 0:04:39 time: 3.2923 data: 3.0148 max mem: 20773 +train: [19] [240/400] eta: 0:01:14 lr: 0.000001 loss: 2.4963 (2.5268) grad: 0.1534 (0.1546) time: 0.4453 data: 0.0050 max mem: 22449 +eval (validation): [18] [20/85] eta: 0:00:30 time: 0.3302 data: 0.0033 max mem: 20773 +train: [19] [260/400] eta: 0:01:04 lr: 0.000000 loss: 2.5299 (2.5284) grad: 0.1493 (0.1548) time: 0.4510 data: 0.0049 max mem: 22449 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3513 data: 0.0037 max mem: 20773 +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 2.5361 (2.5275) grad: 0.1385 (0.1541) time: 0.4437 data: 0.0049 max mem: 22449 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3503 data: 0.0045 max mem: 20773 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3625 data: 0.0042 max mem: 20773 +train: [19] [300/400] eta: 0:00:46 lr: 0.000000 loss: 2.5491 (2.5301) grad: 0.1482 (0.1542) time: 0.4538 data: 0.0051 max mem: 22449 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3522 data: 0.0040 max mem: 20773 +eval (validation): [18] Total time: 0:00:32 (0.3857 s / it) +cv: [18] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.419 acc: 0.276 f1: 0.210 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:37 lr: nan time: 3.3925 data: 3.0457 max mem: 20773 +train: [19] [320/400] eta: 0:00:36 lr: 0.000000 loss: 2.5669 (2.5339) grad: 0.1542 (0.1547) time: 0.4473 data: 0.0051 max mem: 22449 +train: [19] [ 20/400] eta: 0:03:48 lr: 0.000003 loss: 2.5026 (2.5090) grad: 0.1396 (0.1472) time: 0.4618 data: 0.0049 max mem: 20773 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 2.5669 (2.5344) grad: 0.1511 (0.1545) time: 0.4606 data: 0.0051 max mem: 22449 +train: [19] [ 40/400] eta: 0:03:08 lr: 0.000003 loss: 2.5128 (2.5221) grad: 0.1454 (0.1519) time: 0.4421 data: 0.0040 max mem: 20773 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.5336 (2.5346) grad: 0.1496 (0.1545) time: 0.4589 data: 0.0050 max mem: 22449 +train: [19] [ 60/400] eta: 0:02:50 lr: 0.000002 loss: 2.5128 (2.5241) grad: 0.1572 (0.1524) time: 0.4563 data: 0.0041 max mem: 20773 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 2.5336 (2.5356) grad: 0.1491 (0.1541) time: 0.4603 data: 0.0050 max mem: 22449 +train: [19] [ 80/400] eta: 0:02:37 lr: 0.000002 loss: 2.5095 (2.5180) grad: 0.1522 (0.1529) time: 0.4582 data: 0.0044 max mem: 20773 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.5128 (2.5339) grad: 0.1491 (0.1540) time: 0.4658 data: 0.0053 max mem: 22449 +train: [19] Total time: 0:03:04 (0.4613 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.5128 (2.5339) grad: 0.1491 (0.1540) +eval (validation): [19] [ 0/85] eta: 0:04:38 time: 3.2715 data: 2.9646 max mem: 22449 +train: [19] [100/400] eta: 0:02:25 lr: 0.000002 loss: 2.5074 (2.5230) grad: 0.1512 (0.1522) time: 0.4537 data: 0.0043 max mem: 20773 +eval (validation): [19] [20/85] eta: 0:00:33 time: 0.3736 data: 0.0043 max mem: 22449 +train: [19] [120/400] eta: 0:02:13 lr: 0.000002 loss: 2.5074 (2.5232) grad: 0.1428 (0.1498) time: 0.4513 data: 0.0043 max mem: 20773 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3473 data: 0.0040 max mem: 22449 +train: [19] [140/400] eta: 0:02:03 lr: 0.000001 loss: 2.5326 (2.5268) grad: 0.1437 (0.1507) time: 0.4464 data: 0.0043 max mem: 20773 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3680 data: 0.0045 max mem: 22449 +train: [19] [160/400] eta: 0:01:53 lr: 0.000001 loss: 2.5473 (2.5275) grad: 0.1523 (0.1508) time: 0.4572 data: 0.0044 max mem: 20773 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3497 data: 0.0044 max mem: 22449 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3391 data: 0.0044 max mem: 22449 +eval (validation): [19] Total time: 0:00:33 (0.3968 s / it) +cv: [19] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 2.443 acc: 0.275 f1: 0.206 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.2753783684016242, "hparam": [1.2, 1.0], "hparam_id": 25, "epoch": 19, "is_best": false, "best_score": 0.27888519748984864} +train: [19] [180/400] eta: 0:01:43 lr: 0.000001 loss: 2.5284 (2.5285) grad: 0.1501 (0.1510) time: 0.4444 data: 0.0041 max mem: 20773 +eval (train): [20] [ 0/509] eta: 0:25:05 time: 2.9585 data: 2.6711 max mem: 22449 +eval (train): [20] [ 20/509] eta: 0:04:05 time: 0.3800 data: 0.0046 max mem: 22449 +train: [19] [200/400] eta: 0:01:33 lr: 0.000001 loss: 2.5284 (2.5303) grad: 0.1501 (0.1517) time: 0.4679 data: 0.0042 max mem: 20773 +eval (train): [20] [ 40/509] eta: 0:03:19 time: 0.3431 data: 0.0035 max mem: 22449 +train: [19] [220/400] eta: 0:01:24 lr: 0.000001 loss: 2.5251 (2.5311) grad: 0.1536 (0.1521) time: 0.4577 data: 0.0045 max mem: 20773 +eval (train): [20] [ 60/509] eta: 0:02:59 time: 0.3468 data: 0.0044 max mem: 22449 +train: [19] [240/400] eta: 0:01:14 lr: 0.000001 loss: 2.5258 (2.5328) grad: 0.1569 (0.1527) time: 0.4503 data: 0.0043 max mem: 20773 +eval (train): [20] [ 80/509] eta: 0:02:45 time: 0.3451 data: 0.0041 max mem: 22449 +train: [19] [260/400] eta: 0:01:04 lr: 0.000000 loss: 2.5380 (2.5310) grad: 0.1466 (0.1519) time: 0.4410 data: 0.0042 max mem: 20773 +eval (train): [20] [100/509] eta: 0:02:35 time: 0.3564 data: 0.0043 max mem: 22449 +eval (train): [20] [120/509] eta: 0:02:26 time: 0.3564 data: 0.0042 max mem: 22449 +train: [19] [280/400] eta: 0:00:55 lr: 0.000000 loss: 2.5094 (2.5295) grad: 0.1432 (0.1519) time: 0.4498 data: 0.0040 max mem: 20773 +eval (train): [20] [140/509] eta: 0:02:17 time: 0.3491 data: 0.0044 max mem: 22449 +train: [19] [300/400] eta: 0:00:46 lr: 0.000000 loss: 2.5037 (2.5278) grad: 0.1460 (0.1516) time: 0.4547 data: 0.0044 max mem: 20773 +eval (train): [20] [160/509] eta: 0:02:09 time: 0.3713 data: 0.0043 max mem: 22449 +train: [19] [320/400] eta: 0:00:37 lr: 0.000000 loss: 2.5037 (2.5274) grad: 0.1460 (0.1516) time: 0.4666 data: 0.0040 max mem: 20773 +eval (train): [20] [180/509] eta: 0:02:02 time: 0.3771 data: 0.0045 max mem: 22449 +train: [19] [340/400] eta: 0:00:27 lr: 0.000000 loss: 2.5247 (2.5279) grad: 0.1456 (0.1512) time: 0.4554 data: 0.0045 max mem: 20773 +eval (train): [20] [220/509] eta: 0:01:46 time: 0.3432 data: 0.0040 max mem: 22449 +train: [19] [360/400] eta: 0:00:18 lr: 0.000000 loss: 2.5380 (2.5290) grad: 0.1492 (0.1519) time: 0.4622 data: 0.0043 max mem: 20773 +eval (train): [20] [240/509] eta: 0:01:38 time: 0.3446 data: 0.0039 max mem: 22449 +train: [19] [380/400] eta: 0:00:09 lr: 0.000000 loss: 2.5220 (2.5289) grad: 0.1551 (0.1522) time: 0.4608 data: 0.0042 max mem: 20773 +eval (train): [20] [260/509] eta: 0:01:31 time: 0.3887 data: 0.0044 max mem: 22449 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.5367 (2.5298) grad: 0.1520 (0.1520) time: 0.4574 data: 0.0043 max mem: 20773 +train: [19] Total time: 0:03:04 (0.4624 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.5367 (2.5298) grad: 0.1520 (0.1520) +eval (train): [20] [280/509] eta: 0:01:24 time: 0.3590 data: 0.0041 max mem: 22449 +eval (validation): [19] [ 0/85] eta: 0:04:31 time: 3.1975 data: 2.9291 max mem: 20773 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3409 data: 0.0041 max mem: 22449 +eval (validation): [19] [20/85] eta: 0:00:30 time: 0.3382 data: 0.0043 max mem: 20773 +eval (train): [20] [320/509] eta: 0:01:08 time: 0.3396 data: 0.0041 max mem: 22449 +eval (validation): [19] [40/85] eta: 0:00:18 time: 0.3534 data: 0.0035 max mem: 20773 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3566 data: 0.0043 max mem: 22449 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3529 data: 0.0045 max mem: 20773 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3545 data: 0.0042 max mem: 22449 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3348 data: 0.0039 max mem: 20773 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3279 data: 0.0039 max mem: 20773 +eval (validation): [19] Total time: 0:00:32 (0.3809 s / it) +cv: [19] best hparam: (1, 1.0) (024) ('024_lr1.0e+00_wd1.0e+00') loss: 2.421 acc: 0.276 f1: 0.209 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval (train): [20] [380/509] eta: 0:00:46 time: 0.3401 data: 0.0042 max mem: 22449 +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-last.pth +eval model info: +{"score": 0.27593207825765964, "hparam": [1, 1.0], "hparam_id": 24, "epoch": 19, "is_best": false, "best_score": 0.28183831672203763} +eval (train): [20] [ 0/509] eta: 0:26:36 time: 3.1371 data: 2.8425 max mem: 20773 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3535 data: 0.0042 max mem: 22449 +eval (train): [20] [ 20/509] eta: 0:04:01 time: 0.3615 data: 0.0052 max mem: 20773 +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3965 data: 0.0047 max mem: 22449 +eval (train): [20] [ 40/509] eta: 0:03:23 time: 0.3713 data: 0.0041 max mem: 20773 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3641 data: 0.0044 max mem: 22449 +eval (train): [20] [ 60/509] eta: 0:03:03 time: 0.3561 data: 0.0041 max mem: 20773 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3466 data: 0.0038 max mem: 22449 +eval (train): [20] [ 80/509] eta: 0:02:49 time: 0.3583 data: 0.0044 max mem: 20773 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3314 data: 0.0038 max mem: 22449 +eval (train): [20] [100/509] eta: 0:02:39 time: 0.3659 data: 0.0042 max mem: 20773 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3834 data: 0.0045 max mem: 22449 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3563 data: 0.0046 max mem: 22449 +eval (train): [20] Total time: 0:03:04 (0.3634 s / it) +eval (train): [20] [120/509] eta: 0:02:30 time: 0.3710 data: 0.0044 max mem: 20773 +eval (train): [20] [140/509] eta: 0:02:20 time: 0.3513 data: 0.0041 max mem: 20773 +eval (validation): [20] [ 0/85] eta: 0:04:21 time: 3.0769 data: 2.7986 max mem: 22449 +eval (validation): [20] [20/85] eta: 0:00:30 time: 0.3364 data: 0.0056 max mem: 22449 +eval (train): [20] [160/509] eta: 0:02:13 time: 0.3817 data: 0.0045 max mem: 20773 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3423 data: 0.0034 max mem: 22449 +eval (train): [20] [180/509] eta: 0:02:04 time: 0.3619 data: 0.0041 max mem: 20773 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3832 data: 0.0043 max mem: 22449 +eval (train): [20] [200/509] eta: 0:01:56 time: 0.3576 data: 0.0040 max mem: 20773 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3582 data: 0.0044 max mem: 22449 +eval (train): [20] [220/509] eta: 0:01:49 time: 0.3765 data: 0.0045 max mem: 20773 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3378 data: 0.0041 max mem: 22449 +eval (validation): [20] Total time: 0:00:32 (0.3876 s / it) +eval (test): [20] [ 0/85] eta: 0:04:13 time: 2.9771 data: 2.7220 max mem: 22449 +eval (train): [20] [240/509] eta: 0:01:41 time: 0.3608 data: 0.0040 max mem: 20773 +eval (test): [20] [20/85] eta: 0:00:33 time: 0.3905 data: 0.0051 max mem: 22449 +eval (train): [20] [260/509] eta: 0:01:33 time: 0.3601 data: 0.0042 max mem: 20773 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3512 data: 0.0036 max mem: 22449 +eval (train): [20] [280/509] eta: 0:01:25 time: 0.3638 data: 0.0044 max mem: 20773 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3706 data: 0.0043 max mem: 22449 +eval (train): [20] [300/509] eta: 0:01:18 time: 0.3798 data: 0.0043 max mem: 20773 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3426 data: 0.0044 max mem: 22449 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3265 data: 0.0039 max mem: 22449 +eval (test): [20] Total time: 0:00:33 (0.3951 s / it) +eval (train): [20] [320/509] eta: 0:01:10 time: 0.3623 data: 0.0045 max mem: 20773 +eval (testid): [20] [ 0/82] eta: 0:04:07 time: 3.0190 data: 2.7654 max mem: 22449 +eval (train): [20] [340/509] eta: 0:01:03 time: 0.3663 data: 0.0042 max mem: 20773 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3533 data: 0.0044 max mem: 22449 +eval (train): [20] [360/509] eta: 0:00:55 time: 0.3806 data: 0.0048 max mem: 20773 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3604 data: 0.0035 max mem: 22449 +eval (train): [20] [380/509] eta: 0:00:48 time: 0.3502 data: 0.0041 max mem: 20773 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3356 data: 0.0039 max mem: 22449 +eval (train): [20] [400/509] eta: 0:00:40 time: 0.3620 data: 0.0042 max mem: 20773 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3536 data: 0.0043 max mem: 22449 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3430 data: 0.0042 max mem: 22449 +eval (testid): [20] Total time: 0:00:31 (0.3850 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.28183831672203763, "hparam": [1.4, 1.0], "hparam_id": 26, "epoch": 13, "is_best": true, "best_score": 0.28183831672203763} +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3491 data: 0.0044 max mem: 20773 +eval (train): [20] [ 0/509] eta: 0:26:14 time: 3.0936 data: 2.8572 max mem: 22449 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3431 data: 0.0042 max mem: 20773 +eval (train): [20] [ 20/509] eta: 0:04:24 time: 0.4141 data: 0.0267 max mem: 22449 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3437 data: 0.0040 max mem: 20773 +eval (train): [20] [ 40/509] eta: 0:03:28 time: 0.3413 data: 0.0032 max mem: 22449 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3700 data: 0.0043 max mem: 20773 +eval (train): [20] [ 60/509] eta: 0:03:11 time: 0.3935 data: 0.0042 max mem: 22449 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3571 data: 0.0043 max mem: 20773 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3401 data: 0.0041 max mem: 20773 +eval (train): [20] Total time: 0:03:07 (0.3685 s / it) +eval (train): [20] [ 80/509] eta: 0:03:00 time: 0.3998 data: 0.0044 max mem: 22449 +eval (train): [20] [100/509] eta: 0:02:47 time: 0.3664 data: 0.0044 max mem: 22449 +eval (validation): [20] [ 0/85] eta: 0:04:22 time: 3.0839 data: 2.7987 max mem: 20773 +eval (train): [20] [120/509] eta: 0:02:35 time: 0.3502 data: 0.0039 max mem: 22449 +eval (validation): [20] [20/85] eta: 0:00:33 time: 0.3867 data: 0.0049 max mem: 20773 +eval (train): [20] [140/509] eta: 0:02:25 time: 0.3625 data: 0.0042 max mem: 22449 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3689 data: 0.0038 max mem: 20773 +eval (train): [20] [160/509] eta: 0:02:16 time: 0.3709 data: 0.0045 max mem: 22449 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3766 data: 0.0046 max mem: 20773 +eval (train): [20] [180/509] eta: 0:02:08 time: 0.3725 data: 0.0044 max mem: 22449 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3363 data: 0.0042 max mem: 20773 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3279 data: 0.0040 max mem: 20773 +eval (validation): [20] Total time: 0:00:34 (0.4005 s / it) +eval (test): [20] [ 0/85] eta: 0:04:22 time: 3.0876 data: 2.7971 max mem: 20773 +eval (train): [20] [200/509] eta: 0:01:59 time: 0.3703 data: 0.0043 max mem: 22449 +eval (train): [20] [220/509] eta: 0:01:51 time: 0.3735 data: 0.0044 max mem: 22449 +eval (test): [20] [20/85] eta: 0:00:33 time: 0.3922 data: 0.0050 max mem: 20773 +eval (train): [20] [240/509] eta: 0:01:43 time: 0.3760 data: 0.0045 max mem: 22449 +eval (test): [20] [40/85] eta: 0:00:20 time: 0.3708 data: 0.0040 max mem: 20773 +eval (train): [20] [260/509] eta: 0:01:35 time: 0.3674 data: 0.0043 max mem: 22449 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3927 data: 0.0044 max mem: 20773 +eval (train): [20] [280/509] eta: 0:01:27 time: 0.3679 data: 0.0041 max mem: 22449 +eval (test): [20] [80/85] eta: 0:00:02 time: 0.3588 data: 0.0042 max mem: 20773 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3488 data: 0.0040 max mem: 20773 +eval (test): [20] Total time: 0:00:34 (0.4106 s / it) +eval (testid): [20] [ 0/82] eta: 0:03:50 time: 2.8133 data: 2.5556 max mem: 20773 +eval (train): [20] [300/509] eta: 0:01:19 time: 0.3679 data: 0.0043 max mem: 22449 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3631 data: 0.0045 max mem: 20773 +eval (train): [20] [320/509] eta: 0:01:12 time: 0.3789 data: 0.0045 max mem: 22449 +eval (testid): [20] [40/82] eta: 0:00:18 time: 0.4007 data: 0.0038 max mem: 20773 +eval (train): [20] [340/509] eta: 0:01:04 time: 0.3668 data: 0.0042 max mem: 22449 +eval (train): [20] [360/509] eta: 0:00:56 time: 0.3417 data: 0.0041 max mem: 22449 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3628 data: 0.0045 max mem: 20773 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3408 data: 0.0043 max mem: 20773 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3274 data: 0.0040 max mem: 20773 +eval (testid): [20] Total time: 0:00:32 (0.3980 s / it) +eval (train): [20] [380/509] eta: 0:00:48 time: 0.3655 data: 0.0042 max mem: 22449 +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/checkpoint-best.pth +eval model info: +{"score": 0.28183831672203763, "hparam": [1.4, 1.0], "hparam_id": 26, "epoch": 13, "is_best": true, "best_score": 0.28183831672203763} +eval (train): [20] [ 0/509] eta: 0:26:08 time: 3.0823 data: 2.8052 max mem: 20773 +eval (train): [20] [400/509] eta: 0:00:41 time: 0.3752 data: 0.0047 max mem: 22449 +eval (train): [20] [ 20/509] eta: 0:04:02 time: 0.3675 data: 0.0051 max mem: 20773 +eval (train): [20] [420/509] eta: 0:00:33 time: 0.3719 data: 0.0046 max mem: 22449 +eval (train): [20] [ 40/509] eta: 0:03:27 time: 0.3841 data: 0.0041 max mem: 20773 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3389 data: 0.0039 max mem: 22449 +eval (train): [20] [ 60/509] eta: 0:03:03 time: 0.3429 data: 0.0042 max mem: 20773 +eval (train): [20] [460/509] eta: 0:00:18 time: 0.3743 data: 0.0041 max mem: 22449 +eval (train): [20] [ 80/509] eta: 0:02:51 time: 0.3688 data: 0.0045 max mem: 20773 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3723 data: 0.0042 max mem: 22449 +eval (train): [20] [100/509] eta: 0:02:40 time: 0.3629 data: 0.0045 max mem: 20773 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3450 data: 0.0044 max mem: 22449 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3417 data: 0.0044 max mem: 22449 +eval (train): [20] Total time: 0:03:11 (0.3761 s / it) +eval (train): [20] [120/509] eta: 0:02:30 time: 0.3616 data: 0.0046 max mem: 20773 +eval (validation): [20] [ 0/85] eta: 0:04:22 time: 3.0913 data: 2.7649 max mem: 22449 +eval (train): [20] [140/509] eta: 0:02:20 time: 0.3485 data: 0.0042 max mem: 20773 +eval (train): [20] [160/509] eta: 0:02:11 time: 0.3400 data: 0.0042 max mem: 20773 +eval (validation): [20] [20/85] eta: 0:00:35 time: 0.4222 data: 0.0151 max mem: 22449 +eval (train): [20] [180/509] eta: 0:02:03 time: 0.3604 data: 0.0042 max mem: 20773 +eval (validation): [20] [40/85] eta: 0:00:20 time: 0.3715 data: 0.0040 max mem: 22449 +eval (train): [20] [200/509] eta: 0:01:55 time: 0.3711 data: 0.0046 max mem: 20773 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3856 data: 0.0047 max mem: 22449 +eval (train): [20] [220/509] eta: 0:01:47 time: 0.3489 data: 0.0042 max mem: 20773 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3700 data: 0.0043 max mem: 22449 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3463 data: 0.0040 max mem: 22449 +eval (validation): [20] Total time: 0:00:35 (0.4193 s / it) +eval (train): [20] [240/509] eta: 0:01:39 time: 0.3480 data: 0.0039 max mem: 20773 +eval (test): [20] [ 0/85] eta: 0:04:06 time: 2.9006 data: 2.6237 max mem: 22449 +eval (train): [20] [260/509] eta: 0:01:31 time: 0.3547 data: 0.0041 max mem: 20773 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3776 data: 0.0049 max mem: 22449 +eval (train): [20] [280/509] eta: 0:01:23 time: 0.3335 data: 0.0041 max mem: 20773 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3434 data: 0.0040 max mem: 22449 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3595 data: 0.0041 max mem: 20773 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3501 data: 0.0039 max mem: 22449 +eval (train): [20] [320/509] eta: 0:01:09 time: 0.3559 data: 0.0041 max mem: 20773 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3417 data: 0.0043 max mem: 22449 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3285 data: 0.0040 max mem: 22449 +eval (test): [20] Total time: 0:00:32 (0.3841 s / it) +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3496 data: 0.0042 max mem: 20773 +eval (testid): [20] [ 0/82] eta: 0:03:59 time: 2.9202 data: 2.6809 max mem: 22449 +eval (train): [20] [360/509] eta: 0:00:54 time: 0.3497 data: 0.0040 max mem: 20773 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3624 data: 0.0043 max mem: 22449 +eval (train): [20] [380/509] eta: 0:00:47 time: 0.3912 data: 0.0044 max mem: 20773 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3415 data: 0.0036 max mem: 22449 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3410 data: 0.0041 max mem: 22449 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3854 data: 0.0045 max mem: 20773 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3289 data: 0.0041 max mem: 22449 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3180 data: 0.0039 max mem: 22449 +eval (testid): [20] Total time: 0:00:30 (0.3760 s / it) +eval (train): [20] [420/509] eta: 0:00:32 time: 0.3812 data: 0.0043 max mem: 20773 +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | train | 2.0555 | 0.37638 | 0.0024196 | 0.31618 | 0.0025099 | +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | validation | 2.4422 | 0.28184 | 0.0053742 | 0.21507 | 0.0049022 | +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | test | 2.4778 | 0.2577 | 0.0047867 | 0.19013 | 0.0047301 | +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | testid | 2.2359 | 0.32099 | 0.0057268 | 0.26373 | 0.0057084 | + + +done! total time: 1:24:50 +eval (train): [20] [440/509] eta: 0:00:25 time: 0.3773 data: 0.0044 max mem: 20773 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3658 data: 0.0044 max mem: 20773 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.4132 data: 0.0047 max mem: 20773 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3483 data: 0.0043 max mem: 20773 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3338 data: 0.0042 max mem: 20773 +eval (train): [20] Total time: 0:03:07 (0.3691 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:23 time: 3.1023 data: 2.8694 max mem: 20773 +eval (validation): [20] [20/85] eta: 0:00:30 time: 0.3355 data: 0.0040 max mem: 20773 +eval (validation): [20] [40/85] eta: 0:00:19 time: 0.3929 data: 0.0038 max mem: 20773 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3748 data: 0.0049 max mem: 20773 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3414 data: 0.0037 max mem: 20773 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3335 data: 0.0040 max mem: 20773 +eval (validation): [20] Total time: 0:00:33 (0.3943 s / it) +eval (test): [20] [ 0/85] eta: 0:04:01 time: 2.8415 data: 2.5833 max mem: 20773 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3834 data: 0.0036 max mem: 20773 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3661 data: 0.0042 max mem: 20773 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3714 data: 0.0042 max mem: 20773 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3534 data: 0.0042 max mem: 20773 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3247 data: 0.0037 max mem: 20773 +eval (test): [20] Total time: 0:00:33 (0.3976 s / it) +eval (testid): [20] [ 0/82] eta: 0:03:55 time: 2.8755 data: 2.6420 max mem: 20773 +eval (testid): [20] [20/82] eta: 0:00:28 time: 0.3358 data: 0.0062 max mem: 20773 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3553 data: 0.0035 max mem: 20773 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3293 data: 0.0041 max mem: 20773 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3283 data: 0.0040 max mem: 20773 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3171 data: 0.0038 max mem: 20773 +eval (testid): [20] Total time: 0:00:30 (0.3686 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|--------:|-----:|------------:|:-----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | train | 2.0555 | 0.37638 | 0.0024196 | 0.31618 | 0.0025099 | +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | validation | 2.4422 | 0.28184 | 0.0053742 | 0.21507 | 0.0049022 | +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | test | 2.4778 | 0.2577 | 0.0047867 | 0.19013 | 0.0047301 | +| flat_mae | patch | attn | nsd_cococlip | best | 13 | 0.00042 | 0.05 | 26 | [1.4, 1.0] | testid | 2.2359 | 0.32099 | 0.0057268 | 0.26373 | 0.0057084 | + + +done! total time: 0:35:55 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/train_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..2a1ab1f38618d7118dd42355e3f7b83dd1811802 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__attn/train_log.json @@ -0,0 +1,27 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.1573505079746247, "train/grad": 0.06514614075422287, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.18021484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.179903564453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.179429931640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.178951416015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1783935546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.177725830078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.176923828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.176165771484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.175107421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.17398193359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.172840576171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1713330078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1698828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1678955078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.166038818359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.164378662109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.162470703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.160323486328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.158153076171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.15639892578125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.154456787109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.15273681640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.15110107421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.14961669921875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.148223876953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.146846923828125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.145787353515625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.145006103515625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.144246826171875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.143499755859375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.143096923828125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.142955322265625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.142965087890625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.143121337890625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.143436279296875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.143858642578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.14433837890625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.14483154296875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.14539794921875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.146153564453125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.146739501953125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1474560546875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.148590087890625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.14955322265625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1503955078125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.151363525390625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.15272216796875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.155633544921875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.15953369140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009853414052631706, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009841788774356246, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009822626567911356, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009803978633135558, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009786158786155283, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009762120915111154, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009735511238686741, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009706700576934964, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009671074340585619, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009633550366852433, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009598210910335183, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009547257786616683, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009500286646652967, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009437007943633944, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009381041962187737, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009333315915428101, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009278578220400959, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009223344000056387, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009173364811576903, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009137272958178073, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009104694726411254, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009081061938777566, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009065605711657553, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009054597767535597, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009048217546660454, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009043195152189583, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009040335605386645, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0090371067635715, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009033523895777763, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009030268855858593, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009026308890897781, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009022504212334753, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009018843537196517, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009010803359560669, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008998091481626034, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008978202054277063, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008952249828726054, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008925122737418861, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008892529800068587, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008859724667854608, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008844445545691996, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008851696425117551, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.00890472883824259, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008981575898360461, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009072258211672306, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009235153328627349, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009428493848536163, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.00973946017678827, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009970644102431835, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.171736478805542, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.170808792114258, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1693129539489746, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1678428649902344, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1664280891418457, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.164487838745117, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.162360191345215, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.160090923309326, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.15722918510437, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.154332160949707, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.151624917984009, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1478841304779053, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.144562244415283, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.140294075012207, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1368019580841064, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1339714527130127, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.131056308746338, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1285035610198975, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1265411376953125, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1253933906555176, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1245334148406982, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1240592002868652, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.123746156692505, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.123518705368042, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1233208179473877, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1230783462524414, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1229164600372314, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.122903347015381, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1231229305267334, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.123755931854248, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.124560832977295, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1253268718719482, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.126316547393799, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.127018690109253, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1277973651885986, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1287484169006348, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1300065517425537, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1312994956970215, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1327035427093506, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.134044647216797, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.135082244873047, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1371474266052246, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1404361724853516, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1398062705993652, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1382436752319336, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1495931148529053, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1564266681671143, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1539485454559326, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.145097494125366, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05278700627537837, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.05666297526762643, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0725359911406423, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06386120339608711, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06386120339608711, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06423034330011074, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0636766334440753, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06589147286821706, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06902916205241787, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0651531930601698, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0636766334440753, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06607604282022887, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06256921373200443, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.007430364231747251, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00884994381015416, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00988409238081739, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009364260424926144, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008907214343463879, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008140834345336334, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00707782076753054, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005842121076074378, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005557470273996209, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005555555555555556, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0055565127498277056, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010396803512024398, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009355343070752899, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.004972744142890281, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.004965832754227473, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.010819005093532683, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.008872491390282745, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.00499045304634612, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.004988721152177685, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.00498958694897605, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.005241169531521001, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.006163517100394817, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.0063362568603064886, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.006003003087211041, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.009111691005073358, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.010001649114552341, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.008060603320824193, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.00498958694897605, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.014559896963563792, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.009237092311855906, "id_best": 13, "lr_best": 5.1e-05, "wd_best": 0.05, "train/loss_best": 3.1678955078125, "validation/loss_best": 3.140294075012207, "validation/acc_best": 0.0725359911406423, "validation/f1_best": 0.010396803512024398} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.1257795000076296, "train/grad": 0.08332472493872047, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.167294921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.165523681640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.162640380859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1600537109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.157572021484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.154398193359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.151134033203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.147955322265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.14443603515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1412548828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.138623046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.135457763671875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.13311767578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.130792236328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129266357421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.128355712890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.127479248046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.126971435546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.126705322265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.126605224609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.126826171875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.126854248046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.127236328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1274853515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12778076171875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.128216552734375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.128656005859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12915771484375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.129794921875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.13088623046875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.131805419921875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.132725830078125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.134117431640625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.13530517578125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.136693115234375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.137919921875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.138839111328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.139432373046875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.13960205078125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.137593994140625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.119508972167969, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1027699279785157, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0965621948242186, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1034121704101563, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.07405517578125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.053720245361328, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9872768402099608, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0538970947265627, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.069429817199707, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009693815184291452, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009639318524859846, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009555218569003045, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009479253282770515, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00941007396671921, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009324112029280513, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009242312584538013, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009168169687036425, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009091330049559474, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009032809936907143, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008993822557386011, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008963538052048534, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008957457675132901, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00896910359384492, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008990283822640777, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009014958483166993, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009047696983907371, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009083659767638893, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00911840045126155, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009142142594791949, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009162841509096324, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00917375649092719, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009178080805577337, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009172760588116944, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009160154997371137, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009133607724215835, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009101541636046023, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009063397301360965, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009001836467068642, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008910512775182724, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00881739946315065, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008730287970975041, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008619033014401794, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008530491555575281, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008447492783889175, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008390593915246427, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008369256851729005, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.008408014210872353, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008502571389544755, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008919255088549106, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011252017703372984, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012544215598609298, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.013831572392955422, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.014145703453104943, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.016325533986091614, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.017856221173424273, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.020680171034764498, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.02482051861938089, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.027773076891899107, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1554718017578125, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.15283465385437, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.148869037628174, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1453676223754883, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1422677040100098, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1385724544525146, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.135133743286133, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1321048736572266, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1291871070861816, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.127089500427246, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.125765562057495, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124619960784912, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124054431915283, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1237587928771973, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1237497329711914, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1238327026367188, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123958110809326, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1241753101348877, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.124436855316162, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.124725580215454, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1251633167266846, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1257123947143555, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1264238357543945, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1274001598358154, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1286113262176514, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1302924156188965, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.132092237472534, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1339755058288574, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1368751525878906, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1406025886535645, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1441526412963867, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.147092819213867, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.150355339050293, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1522226333618164, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1524085998535156, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.150322914123535, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.148904800415039, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.149322748184204, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1573362350463867, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.059485673904419, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.851677656173706, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.829896926879883, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.841454029083252, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.860610008239746, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.860747814178467, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.8582653999328613, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.877984046936035, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.119544744491577, "validation/loss_048_lr5.0e+01_wd1.0e+00": 2.8574283123016357, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.07198228128460686, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.07124400147655961, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.059431524547803614, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.09486895533407161, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.12403100775193798, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.13713547434477666, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.13215208564045774, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1301218161683278, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.14101144333702473, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.12993724621631597, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.1642672572905131, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.11351052048726468, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.16685123661867848, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005555555555555556, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005555555555555556, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005555555555555556, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005555555555555556, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008687709475955494, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010511123053872714, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006732273201251303, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.00496410790783837, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005896023554320497, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.007896188081693841, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.009513507132732362, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009862812910005209, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.009804216882387938, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.009668284669619819, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.00888039466405492, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.005401646188636138, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.00859085478220368, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.011709588838299435, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.009223705348386416, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.030083055028157408, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.06338301225316018, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.06255541451678227, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.07867401895831054, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05087179405181047, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.07474871272838755, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06226207548748936, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.08028990375423538, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0419823799640357, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.1089545248804528, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.069429817199707, "validation/loss_best": 2.8574283123016357, "validation/acc_best": 0.16685123661867848, "validation/f1_best": 0.1089545248804528} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.0980148696899414, "train/grad": 0.21430460561066866, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.14943603515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1464453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.142115478515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.138775634765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.135953369140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.133011474609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130599365234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1288671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127315673828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12654541015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12614013671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12580810546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1258154296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1256494140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125780029296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.125753173828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125792236328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12576904296875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.125826416015625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12583251953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.125897216796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.125982666015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126092529296875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126201171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12640869140625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.126607666015625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1267626953125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.127001953125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.127305908203125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12762451171875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1280517578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.12824951171875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.12860107421875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1228082275390623, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.083663330078125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0400051879882812, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.981528472900391, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.914866371154785, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.8678961563110352, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.7240026664733885, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6536210060119627, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6352672004699706, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.644640817642212, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6921278190612794, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.702163257598877, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.745058898925781, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.7460016059875487, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.856898059844971, "train/loss_048_lr5.0e+01_wd1.0e+00": 6.124163389205933, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009109184045810252, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009035044501069933, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008939860393293203, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008872412382625044, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008828682645689695, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00879720454569906, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008792593197431415, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008808607736136764, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008840674359817058, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008879674097988755, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008916144787799568, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008958735920023173, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00898712319554761, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009010674792807549, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009019431199412793, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009021637255791574, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009018616762477904, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009011693669017405, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008999178253579885, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008981858741026371, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008953647410962731, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008911702290643007, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008852663135621696, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008775396889541298, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00867906775791198, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0085454714554362, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008410884866025299, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008286734283901752, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008122537995222955, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.007948207594454288, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.007819903835188597, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.007728680553846061, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.007659115807618946, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008200148255564272, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010206464952789247, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.012287967505399138, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.014347012385260314, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.016399376795161517, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.018518052925355733, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02425036620348692, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.026171295805834233, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02754495636560023, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.028981291679665445, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.030057545728050174, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.033499351837672296, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03571891789324581, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.038366959458217026, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.04021171980537474, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.13640500124543906, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1388065814971924, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1358888149261475, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.132119655609131, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.129469394683838, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.127657413482666, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.126023530960083, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1250529289245605, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124600648880005, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124492883682251, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1246273517608643, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1248409748077393, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125232219696045, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.125683546066284, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1263201236724854, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.126941204071045, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1275129318237305, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1281864643096924, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1288914680480957, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1295406818389893, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.129934310913086, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.130220651626587, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1303954124450684, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1305370330810547, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.130638837814331, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1308226585388184, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.130943775177002, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.131011486053467, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1310486793518066, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.13128662109375, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1315205097198486, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.131338119506836, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.130751848220825, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1278936862945557, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.9697482585906982, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.82222056388855, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.7410037517547607, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6994709968566895, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6006438732147217, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.584817886352539, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.645847797393799, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6172285079956055, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.597869873046875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6669814586639404, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6477110385894775, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8662726879119873, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6762964725494385, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.6207122802734375, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0074801445007324, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0710594315245478, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.07216685123661867, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.09043927648578812, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.13658176448874124, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.16482096714654854, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.17792543373938724, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.21354743447766703, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2146548541897379, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20155038759689922, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21557770394979697, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18973791066814322, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20081210778885197, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.15337763012181616, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19324473975636766, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.21225544481358435, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.1554078995939461, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006340360906829853, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010305131937794058, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009578962631440155, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005909973970961685, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.004963245933900562, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.004966695626991023, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005183923162761039, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00621422223363971, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008884844692190396, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010482849925943788, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012101646979012984, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.011513942758034988, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008742636332654742, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.00882425638548999, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.009998609571568366, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010246085124815297, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.00782961486472059, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005744292053608174, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.004936019917781252, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.004964970181228649, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.015058662458734324, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.06135984595866093, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.08733728056096751, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.10564038526935016, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1421917413182131, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.14492693463232784, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14847458734925137, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16039240799538684, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16021050500366243, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.12816638276216774, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.123761488004693, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.08683411224345201, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.12047449816150023, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.13844571209821716, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.07831449072508899, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 2.6352672004699706, "validation/loss_best": 2.597869873046875, "validation/acc_best": 0.21668512366186785, "validation/f1_best": 0.16021050500366243} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.0560354268550873, "train/grad": 0.26146731719374655, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13687744140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13451904296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131978759765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13034912109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129400634765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12864501953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.128380126953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12816650390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12798828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127879638671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12802001953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1278515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.127835693359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1279443359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128031005859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.128121337890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.128121337890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.128265380859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12845458984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12869384765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12892822265625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12923583984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1296240234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1299462890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.130430908203125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.13112548828125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.131702880859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.132135009765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.132650146484375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1100494384765627, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.032232360839844, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.956296234130859, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.859521484375, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.7294898223876953, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.6450141525268553, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6374227523803713, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.590520305633545, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5590358352661133, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.553788909912109, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.516315641403198, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5019227647781372, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.513740396499634, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.564327178001404, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6005241966247556, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.646824836730957, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.7630853390693666, "train/loss_046_lr3.6e+01_wd1.0e+00": 4.789146733283997, "train/loss_047_lr4.3e+01_wd1.0e+00": 5.243303289413452, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008748879004269839, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008722531320527195, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008718545993324368, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008743329495191575, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00877989147324115, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008830480424221606, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008875978894066066, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008912433984223754, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008941884406376631, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008961490609217436, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008972205882892013, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008979283033404499, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008980647528078407, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00897688587429002, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008968303725123406, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008955841702409088, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008934051683172583, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008900379962287843, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00885283352341503, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00879810226149857, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008715388646814972, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008615860806312412, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008494131693150848, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00835603340761736, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008211680804379284, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008051971071399749, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.007931027843151242, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00784920913167298, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.007791825535241515, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009074749029241502, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011701307808980346, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01419029114767909, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.017508140166755767, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.020402329401113094, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.022573676886968316, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.023245218810625374, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02568557516671717, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02595028686337173, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02702927283011377, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03042063641361892, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0328147248737514, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03504408484324813, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.039328993577510116, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04078856904059649, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.04693075265735388, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.053670414658263325, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.11147088010795414, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.08156135007739067, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1284072399139404, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1268279552459717, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1253280639648438, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1246438026428223, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124358654022217, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124277114868164, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124366283416748, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124511480331421, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124671697616577, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124814748764038, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1249241828918457, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1250767707824707, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1252071857452393, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.125378131866455, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1255950927734375, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.125833511352539, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1262307167053223, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.126753330230713, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.127366304397583, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1279425621032715, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.128652572631836, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1292943954467773, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1296849250793457, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1296722888946533, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1292102336883545, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.128354072570801, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1276087760925293, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1269447803497314, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.123591661453247, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.848383903503418, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.7334988117218018, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6241064071655273, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.617400884628296, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.544787883758545, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.527580976486206, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5562689304351807, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.545339584350586, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5956037044525146, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6286849975585938, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6019999980926514, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.502502918243408, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.737025022506714, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.763319969177246, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.778371572494507, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.955549716949463, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.064138412475586, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.073827980804725, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07216685123661867, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0753045404208195, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.13528977482465854, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.1821705426356589, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.20468807678110004, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.20653377630121816, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23403469915097821, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23015873015873015, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23163528977482467, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22129937246216316, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21963824289405684, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.20911775562938353, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24713916574381692, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.1925064599483204, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.19232188999630861, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19564414913252123, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17718715393134, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.17626430417128092, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.004937735302635389, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009197400130019283, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010182729571510485, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.006703832758115623, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005558428128231645, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005808561471254318, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006039763173004795, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00798368788762203, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.011123383605299844, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.011935268849753764, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01345404621634595, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.05714240337419735, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.10220895695846345, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.13240384178514927, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.13544744742946632, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1510561736137962, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1523925181604552, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.15766207815489422, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.14909205628666317, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.14581495366264474, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.13228788984303705, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14643923283946478, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.18035878545485615, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12464480744810662, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.11627453953525563, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.10831776580000053, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.10644654710981279, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.10334999041607844, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 2.5019227647781372, "validation/loss_best": 2.502502918243408, "validation/acc_best": 0.24713916574381692, "validation/f1_best": 0.18035878545485615} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.0227914905548094, "train/grad": 0.28887267265468836, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.131265869140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1304736328125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12975341796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12945556640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129346923828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12936767578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12935546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.129398193359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12939208984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129320068359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1293408203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.129346923828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129283447265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.129481201171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12947265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.129595947265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12971435546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129879150390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.129957275390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.130115966796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.130286865234375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.130313720703125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.130377197265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.130390625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1301220703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.129150390625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.0984146118164064, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.009259033203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.8555287170410155, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.674779510498047, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5970028686523436, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5424177932739256, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.5346425437927245, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.48469539642334, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.4592934226989747, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.4668109893798826, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.4201933670043947, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4414964866638185, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.4581427478790285, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4552606534957886, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4582433032989504, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.496861536502838, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5311079692840575, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6270550870895386, "train/loss_044_lr2.6e+01_wd1.0e+00": 7.927075185775757, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6889219522476195, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008685337647330016, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008724332111887634, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008787863589823246, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008833743738941848, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00886740388115868, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008896660355385394, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008914396960753947, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008924313471652567, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008927813649643212, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008926920893136412, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00892230996163562, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008913046200759708, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00889976989943534, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008876141612417995, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008845864329487085, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008811590287368744, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008759692565072329, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008685729682911187, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008587978025898337, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008483062086161225, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00834111671661958, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008191131115891039, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008031782580073922, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007881653003860265, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.007757131736725569, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.007700485580135137, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00920439549954608, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.012067734617739917, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01597482424462214, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01982888379134238, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.021832405738532543, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.023570039477199316, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.023389753000810743, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.023852486554533245, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02554628162179142, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.026267161932773887, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.029016319066286086, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.029995298329740763, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.031983605260029434, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03640120672993362, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03979868620634079, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.043507784381508825, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04706093276850879, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.05085462117567659, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.18182018568739294, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.055589846493676306, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124706268310547, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1242733001708984, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12400221824646, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1239852905273438, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124022960662842, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124110221862793, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1242072582244873, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124316930770874, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124492883682251, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1246705055236816, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.124854326248169, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.125135898590088, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.125433921813965, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.125795841217041, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1260879039764404, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.126314640045166, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1264355182647705, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.12640380859375, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1261210441589355, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1256704330444336, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.125089645385742, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124636650085449, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124359130859375, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1240851879119873, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1229801177978516, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.116577625274658, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.835303783416748, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7456109523773193, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.564434766769409, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5323925018310547, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4979023933410645, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.505079746246338, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5138421058654785, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5252609252929688, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.500298023223877, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5405263900756836, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4949522018432617, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.562415599822998, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5547728538513184, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.615992784500122, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6489386558532715, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6853227615356445, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.709214448928833, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6997923851013184, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.062582492828369, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.1391657438169066, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.15780730897009967, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.22978959025470652, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2395717977113326, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2397563676633444, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23661867847914358, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22739018087855298, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22591362126245848, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23145071982281284, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23274270948689554, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23126614987080105, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20579549649317092, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21760797342192692, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.17811000369139904, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00496410790783837, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005457949259536479, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0064343363359526395, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007212918524108387, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007115101812342944, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.00714803065151335, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007377063936408909, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009532029119142775, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.014748467224017256, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01712776678125516, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.017058619871826695, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.021174658824932736, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.04634900600973671, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.06886222433767669, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.14438991309607238, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.15032965722011088, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.16258494643509006, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1662883341237045, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.15474093448072043, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.15280228903359733, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16066719245486216, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1575296726016642, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17292466223848554, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1579384051587678, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.15383126283359302, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14874961639998222, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.14630198337699798, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15204938353031558, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1525396444635984, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14634952267504, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.11128546749627145, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 2.4201933670043947, "validation/loss_best": 2.4949522018432617, "validation/acc_best": 0.2412329272794389, "validation/f1_best": 0.17292466223848554} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.9099819505214692, "train/grad": 0.2055380904302001, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1295703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129429931640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129166259765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12910400390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1290771484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1290185546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12905029296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12900634765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12899658203125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1289599609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129041748046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128944091796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.128951416015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128955078125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128948974609375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.128992919921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.128868408203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1288818359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.128721923828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.128560791015625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1283203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12806640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.127412109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.124652099609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.036130065917969, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8602408599853515, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.6945370483398436, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.600022277832031, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.5306024169921875, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.4766458892822265, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.4526740646362306, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.4152975559234617, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.427207336425781, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.412291555404663, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3899833869934084, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.396830005645752, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.367200741767883, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.390741024017334, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.4042843055725096, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3900041079521177, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4022811460494995, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3992351269721985, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4356015801429747, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.5084307909011843, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 4.822680088281632, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008826473066583275, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008861308293417096, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008896770917344839, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008914616941474378, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008923332644626499, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008928203221876175, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008929350792896003, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008928274759091437, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008924525913316756, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008919135080650448, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008910975807812065, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00889516090042889, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00887372336583212, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008833564715459943, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008785023640375584, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008727345059160143, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008643837484996766, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008529019362758844, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008389792686793953, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00825392197119072, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008093945700675249, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.007952906715217978, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.007851718866731972, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.007979381082113832, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011550458536949009, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.016436441109981388, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01963360043242574, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02146444526501, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.022779441545717417, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.024254108923487366, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02440440244972706, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02669869488105178, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.027037085769698023, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.028491993732750416, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.030515447743237018, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.031225044978782535, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03291557257995009, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.033153608376160264, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03508920225314796, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03871956462040543, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0414321119338274, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0426605308521539, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04452919568866491, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.045805006902664896, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0790644627250731, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.124221086502075, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1241796016693115, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124229669570923, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242761611938477, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124363422393799, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1244235038757324, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1244847774505615, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124530553817749, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124555826187134, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124544382095337, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1244924068450928, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.12435245513916, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1241557598114014, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123755693435669, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1233057975769043, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122877836227417, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1223788261413574, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.121966600418091, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1217212677001953, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1216986179351807, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.121887445449829, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1220555305480957, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.121570348739624, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.099980592727661, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.817126989364624, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6468844413757324, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5700039863586426, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5519561767578125, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.524789810180664, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.524451494216919, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4974913597106934, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5015101432800293, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4785408973693848, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5082147121429443, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5322208404541016, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5478341579437256, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5521862506866455, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.546557664871216, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5713248252868652, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7074837684631348, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6648056507110596, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.822707176208496, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6961588859558105, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8279614448547363, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.09708379475821337, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.1256921373200443, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.19748984865263935, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2222222222222222, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.22517534145441123, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23754152823920266, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2482465854558878, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2336655592469546, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21557770394979697, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19767441860465115, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21650055370985605, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1998892580287929, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004963245933900562, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00497187916739143, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005890220667919035, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00836314730643799, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009265458490815566, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009924221948607065, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010207412232692793, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010208948014688338, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009803883391718506, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009358942780031052, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008964029637364783, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.008799230131348602, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008995173461558011, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.00904417512592169, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009130345395216342, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.009096429547951758, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009921483139562585, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.012194280131849337, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.021348382623552417, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.04539292760797629, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.125864346867169, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1452831200054435, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1542472510231132, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1662539691887619, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.16062581642378768, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.17422640680339951, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.17005594559224999, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17354094446264964, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17267909590882233, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.16704668329765474, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1728162873550236, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17495238595346874, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1885664975372711, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17968599575607277, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1617132308332274, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1731275471603941, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1369788421582474, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15851930884819615, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1369538935518966, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.427207336425781, "validation/loss_best": 2.4785408973693848, "validation/acc_best": 0.2482465854558878, "validation/f1_best": 0.17354094446264964} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.8185555267333986, "train/grad": 0.15268334805965422, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129603271484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129605712890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129588623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129561767578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12954345703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129664306640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129642333984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.129564208984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1295556640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129619140625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129556884765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12957275390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12955078125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.129437255859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12937255859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1293408203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.129234619140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12908203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.128699951171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.128388671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12758056640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12555908203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.0472088623046876, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.8544158935546875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.6704057312011718, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.549305114746094, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4805830764770507, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.434573059082031, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4053327465057373, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.35496639251709, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3500007820129394, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.33211464881897, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.345291805267334, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.331815800666809, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.303041262626648, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.305521173477173, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.29426239490509, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3362707138061523, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.3351195859909057, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2885796535015106, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.301569468975067, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3185310482978823, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.351186521053314, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.418428809642792, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00890341074904427, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00892405780730769, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008941347496584057, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008949089860543609, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008952919465955347, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008954279546160251, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008953913082368672, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008952147176023573, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008945908136665822, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008935337534639985, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00892103505320847, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008892844172660262, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008857839021366089, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00879579624859616, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008722723165992647, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008642050386406482, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008531127374153584, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008390378348995, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008237576326355339, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008108385601080953, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.007994762621819973, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008020144526381046, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010965214667376131, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.016201511342078447, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.019193614684045315, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02136890823021531, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02309827474411577, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02420926149468869, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02492642676923424, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.026012127511203288, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.026809766152873636, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.028402966726571322, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.028512066481634974, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02907912099733949, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03189917279407382, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03202850127592683, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.033519039433449506, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.035003898395225407, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.037045787777751686, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03836748849600553, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03971566236577928, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04200687856413424, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04327556505799293, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04213097535073757, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1238982677459717, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123891592025757, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123894453048706, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123880624771118, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1238486766815186, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123831272125244, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123786211013794, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1237263679504395, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1236777305603027, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123610019683838, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123522996902466, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1233692169189453, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123203992843628, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122925043106079, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1226935386657715, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1225075721740723, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122246503829956, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.121926784515381, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.121443510055542, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1208882331848145, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1201446056365967, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1170785427093506, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.8108701705932617, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.67476224899292, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.571350336074829, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5297486782073975, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5063157081604004, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4898500442504883, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.459141254425049, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.474933385848999, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.468247175216675, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4587600231170654, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.496178150177002, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.524710178375244, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.572023391723633, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5418589115142822, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.542833089828491, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.517847776412964, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.537930488586426, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.512367010116577, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.564093828201294, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.541935920715332, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.569615364074707, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5520083904266357, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0754891103728313, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.08084163898117387, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.08231819859726837, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.15134736064968624, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.19601328903654486, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24234034699150978, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22812846068660023, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24769287559985234, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22831303063861202, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24031007751937986, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2292358803986711, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00554951160246405, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0061484799564170784, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.00750834558984577, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.009306273910388173, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.011275451783313885, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.015240668098856103, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.022631349017917485, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.020914680876817106, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0636288043478029, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.12022282246485909, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.15715241091513124, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1764482622571543, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18066230016980697, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.18287876278572793, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19258166401356544, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18426712354949423, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19028233292147168, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19642382773164505, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18291022552200184, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1777517790388025, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.17861485449743716, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.17967673973303408, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17452128522664992, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1874774459174842, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18684742176573002, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19792258995728365, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.17207695860733088, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18715205757942288, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16493534820675926, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16174708510372895, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 31, "lr_best": 0.0009299999999999999, "wd_best": 0.05, "train/loss_best": 2.33211464881897, "validation/loss_best": 2.4587600231170654, "validation/acc_best": 0.26153562200073827, "validation/f1_best": 0.19642382773164505} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.7826112341880798, "train/grad": 0.1571636150404811, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13270263671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13270263671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.132705078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.132635498046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.132615966796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13257080078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.132529296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.132442626953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132432861328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13230224609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.13218994140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.132039794921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.131859130859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.131627197265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.131363525390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.130987548828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.13062744140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129945068359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.129100341796875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12787353515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121658935546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.9652471923828125, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.7543365478515627, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.597746353149414, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.517987594604492, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4443073654174805, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3882838821411134, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3521952629089355, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3396349716186524, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.29993106842041, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.294698967933655, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.282599468231201, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3067974281311034, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.294972524642944, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2546649503707887, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2706612801551818, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2555276489257814, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2961217021942137, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2910996413230897, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.254007214307785, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2769666075706483, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2765337371826173, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3254842877388002, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.3938607954978943, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008770930566824972, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008781209427397699, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00878959773108363, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00879203831544146, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008792783205863089, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008791145754512399, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00878643976058811, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00877915378427133, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008765134327113629, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00874667929718271, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008722836482338608, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008679152156691999, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008628560467623175, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008541859178803861, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008446149844676256, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008346545109525323, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008214864204637707, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008063000570982694, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.007925113565288484, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00786755844950676, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008292571080382914, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01374479111051187, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.017720849686302245, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.020388183989562093, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02124861054122448, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.023067346629686653, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.024605652084574103, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.025456086536869406, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.025381233394145965, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.026789145413786172, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.027062757229432462, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.027827795147895813, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.028137106373906137, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029114058134146036, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0318398179858923, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.032167134992778304, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03339082553051412, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.035945654548704624, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.037182773919776084, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04022390681318939, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04090254497714341, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.042468815231695774, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.045066398978233335, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04366453909315169, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.123246669769287, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123194932937622, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1231002807617188, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123020887374878, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122939348220825, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1228678226470947, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1228103637695312, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1227900981903076, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122795581817627, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122817277908325, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122853994369507, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1229372024536133, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123013734817505, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1230649948120117, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1230812072753906, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1230292320251465, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1228384971618652, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122446298599243, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.121598482131958, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1198678016662598, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.0806491374969482, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.7690389156341553, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.630549430847168, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.532991409301758, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.487220525741577, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4634687900543213, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4420976638793945, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4576215744018555, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.46533465385437, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4922921657562256, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.482741117477417, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4830944538116455, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4964869022369385, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.549736261367798, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.546351671218872, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.52237868309021, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.600731134414673, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.537466287612915, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5032055377960205, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.585178852081299, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.651237726211548, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6367545127868652, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6683053970336914, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.705130100250244, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0932078257659653, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.15023994093761536, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.19859726836471023, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24363233665559247, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23624953857511996, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2249907715023994, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24160206718346253, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23015873015873015, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22978959025470652, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21391657438169065, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.18696936138796605, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004935162672224152, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005135937148183923, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0055501650329236535, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0057453606506962795, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006173415696587649, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006141375460230449, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006092104908703167, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.006024556788569245, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.006713458391036133, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.008050804822548356, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.024204251633520458, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.050931336789253795, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.10731186197750418, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.15438482037953688, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.17083139136395253, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18645877716410517, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19490909401756676, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2003186472240217, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19773694534438802, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18601296994397495, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18863712152506942, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18646804283044602, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18592289214569757, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1770817434409195, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18417264664143215, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18851889826782633, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17125107383883229, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1746704429749627, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.182789854333564, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17838860173449766, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16142302702732267, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17546218535456434, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16993476795916115, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.14589562030755823, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.3882838821411134, "validation/loss_best": 2.4420976638793945, "validation/acc_best": 0.26264304171280917, "validation/f1_best": 0.19490909401756676} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.736622508764267, "train/grad": 0.1662778516858816, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1278955078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127818603515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127816162109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127750244140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127625732421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127626953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12756103515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12740234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12734130859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1270703125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1270263671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.126805419921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1266259765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12631103515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126024169921875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12578857421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125343017578125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12461669921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123226318359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.115916748046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.8954925537109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.727117004394531, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.5714266967773436, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.47821346282959, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4156781578063966, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3597632598876954, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.301940860748291, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2788011741638186, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2739557456970214, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2394631004333494, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.235774121284485, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.233784203529358, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.260785446166992, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.2439944458007814, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1933031702041625, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.194021954536438, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.196521385908127, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.225638144016266, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2127594602108003, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.176300435066223, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.199644650220871, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.204132310152054, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2571686196327208, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.3358577835559844, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008945322355721146, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008949549715034665, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00895152986748144, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008950152227189392, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008948038066737354, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008942786075640469, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008934475660789759, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00892358978977427, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008904534289613367, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008879880257882177, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008850249347742646, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008797963925171643, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00873723765136674, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008637835625559092, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00853172390256077, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008424514515791088, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008294191977474838, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008163317977450789, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00812274835538119, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008681792826391756, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.015309632937423885, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.018902815701439975, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02115125586744398, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02307473147287965, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02422993889078498, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.025463799107819797, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.027484979061409832, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028024976924061775, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.028210654249414803, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029392992407083512, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03040158135816455, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031421877732500436, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031612402526661754, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.032658960232511164, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.034252188112586734, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03465770093724132, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03488243113271892, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03592639449983835, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03809478449635208, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0410765496455133, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04117641245946288, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.042879200596362355, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04518807790242135, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.042777195554226634, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1232097148895264, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1231348514556885, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123008966445923, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1228857040405273, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122799873352051, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1226603984832764, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1225693225860596, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122471570968628, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122405529022217, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1223647594451904, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122392177581787, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1224348545074463, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1225345134735107, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122675895690918, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.122796058654785, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1228322982788086, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1226696968078613, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1219937801361084, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1197121143341064, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.0781805515289307, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7611584663391113, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6856186389923096, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.537827491760254, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4922211170196533, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4719653129577637, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4569482803344727, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4640183448791504, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4718196392059326, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4400219917297363, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5053226947784424, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.496791362762451, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5328025817871094, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.514301300048828, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5492680072784424, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.521261692047119, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.508937120437622, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.552410125732422, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.537006139755249, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.526923418045044, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6654374599456787, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5334553718566895, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5132710933685303, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.575993537902832, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.625511407852173, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.07419712070874862, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.07069029162052418, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0725359911406423, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07161314138058324, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.09800664451827243, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.16519010705057216, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.18087855297157623, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.23385012919896642, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.25064599483204136, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2571059431524548, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2617201919527501, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23846437799926173, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2563676633444075, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2499077150239941, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2397563676633444, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21520856404577335, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049814104798419885, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007527039592815543, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.009996041504530838, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010873317187151772, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0089598537409939, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007606928395989535, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006025328370129302, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005557470273996209, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005565142364106989, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.006704405959288319, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.02143297002425915, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.07671107539176279, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.09762763147513148, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.15302965411430036, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.16958813922941798, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.17962374843027296, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19251593996448899, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19223682502592, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1936838939184636, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20093064101405425, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18568885356669, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19733955518250088, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1895023089180964, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1874710501114468, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1872846393684592, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18382617846708849, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18448398651161899, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18090528503745815, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18782890832551924, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18244551251173058, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1636783566051526, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.196796310221531, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18612526345692285, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17514496054946735, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15815319524294694, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.3597632598876954, "validation/loss_best": 2.4569482803344727, "validation/acc_best": 0.2672572905131045, "validation/f1_best": 0.19251593996448899} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.7017673516273497, "train/grad": 0.17101039551198483, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1254052734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.125352783203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125303955078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.125225830078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.125189208984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12502685546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.124915771484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.124783935546875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12455322265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124366455078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1238330078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.123426513671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12289794921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.122252197265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.121729736328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12077392578125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1192041015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.113626708984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.9124765014648437, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.7239190673828126, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5720604705810546, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4728268241882323, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.391781015396118, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3367635726928713, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2886053133010864, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.238780393600464, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.215445339679718, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.223641493320465, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.187955083847046, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.185400881767273, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1911586904525757, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.2172463083267213, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.20342369556427, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1475904202461242, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1600036644935607, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.164171025753021, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.183523817062378, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1743568909168243, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1452953362464906, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.165992661714554, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1753946888446807, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.216662551164627, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2907438349723814, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009015132782515138, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009017460278701038, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009017088147811592, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009014940166380256, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00901219754712656, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009005843300838024, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008996063398662955, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008982890145853161, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00895943860989064, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008929033083841204, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008893466242589056, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008830650902818888, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008759650203865021, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00864518418442458, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008526291772723198, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008411187324672937, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008284866388421505, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008214684715494514, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008610271990764886, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.015185147803276778, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.018585128537379206, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02303637221455574, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02306458787061274, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02473897031508386, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.025924422051757573, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02717167470604181, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028609261624515058, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029351703338325024, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02958378616720438, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030334366019815207, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031138664418831466, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031721519446000455, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031742659229785204, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.032825414771214124, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.034432960022240874, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.035065315067768096, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03565465819090605, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03695460163988173, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.038862804248929024, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04201223462820053, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.041956338221207264, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04397687572054565, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04499299512244761, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04309906979091466, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235764026641846, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1235616207122803, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1235480308532715, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123549461364746, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123532772064209, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123483896255493, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1234610080718994, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1234130859375, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1233315467834473, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123232841491699, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1231019496917725, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1228928565979004, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1226603984832764, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122251033782959, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1218035221099854, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1212515830993652, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1203222274780273, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1183128356933594, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1037867069244385, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7886152267456055, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.699544906616211, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.567937135696411, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5013344287872314, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4760360717773438, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.440609931945801, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4318299293518066, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4504570960998535, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4774820804595947, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4713501930236816, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4903724193573, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.484226942062378, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.495244264602661, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.497614622116089, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5258710384368896, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.522707462310791, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5044920444488525, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5682320594787598, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.516775369644165, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.525254011154175, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.549644708633423, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.523725986480713, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6449215412139893, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.577359437942505, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.684166669845581, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15466961978589885, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.17663344407530454, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.23458840900701367, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2517534145441122, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2587670727205611, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2722406792174234, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2757475083056478, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23477297895902546, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24621631598375784, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23901808785529716, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21133259505352528, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004921544786057553, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0058012789849620945, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006444722679197688, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008279180753236056, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008176597459516358, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008604205361117952, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009338275909273877, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.009566822460820525, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01312047134070065, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.08053638273549434, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1033830396276642, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1577477889425769, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17745387960548972, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18622477737106613, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19991461354634152, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21147384540062172, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2004174844724703, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1887696883524658, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19253516515121702, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.186109866515372, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18265673981408867, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18456615278230049, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18287600465648127, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18094860084886863, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18699654724136616, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19579985901452038, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1817739779458266, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2049608972183872, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19266951355310913, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20425187985946688, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20104988687958417, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.17964518669426868, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18459250137445668, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1503657502636784, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.2886053133010864, "validation/loss_best": 2.4318299293518066, "validation/acc_best": 0.2757475083056478, "validation/f1_best": 0.21147384540062172} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.673899893760681, "train/grad": 0.17090002447366714, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12629638671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.126229248046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.126146240234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126016845703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.125972900390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125848388671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.125548095703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.125399169921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12522705078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12498291015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124635009765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124356689453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1238818359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.123363037109375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.122669677734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1219775390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1206787109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11769775390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.9883062744140627, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7617843627929686, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.628109130859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.474012222290039, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4162757110595705, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3265952968597414, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2860382270812987, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.236482915878296, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.195185441970825, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.172192597389221, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.177911014556885, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1532293152809143, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.1342916011810305, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1520352602005004, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.176433458328247, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.165989065170288, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1076198196411133, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1199725127220153, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1311960363388063, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1540841627120972, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1324723958969116, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.100155770778656, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1368750858306886, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1379626977443693, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1916626143455504, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2679216384887697, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008732202660758049, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00873417584458366, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008735330367926508, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008734433413483202, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.0087331862305291, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008728164359927177, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008720399087760598, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008708936881739647, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008688746416009963, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008660785662941635, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008627837700769305, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008568044393323362, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008500591143965721, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008391817689407617, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008281350750476122, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008181824500206858, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008098934253212065, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008215257138945163, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.013310901594813913, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01806566829793155, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.021185261895880103, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02488412382081151, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.024117058338597418, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02618329896591604, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.026945191724225877, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.027894719326868652, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029447178663685916, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029864180283620954, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029610661482438447, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029832668052986264, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030126213813200593, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.0308579205814749, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031083594765514134, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03194952572695911, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0343555900733918, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03495646913535893, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03493364540860057, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.036412728307768705, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03808939967304468, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04092520550824702, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.041612017238512634, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04287506352178752, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04532005337998271, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.043285170178860424, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1234805583953857, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1234545707702637, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1233975887298584, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123340368270874, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232681274414062, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1231868267059326, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123074531555176, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1229770183563232, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1228878498077393, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1227800846099854, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1226933002471924, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.122558832168579, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1224541664123535, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1222548484802246, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.121957540512085, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.121518135070801, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1204373836517334, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.116426944732666, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.853135347366333, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.718282461166382, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.590752124786377, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5011487007141113, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.473919630050659, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.455490827560425, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4445903301239014, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4528110027313232, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.478630542755127, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4888570308685303, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.478163003921509, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.492180585861206, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.49996280670166, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.537482500076294, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5743465423583984, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5875821113586426, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.551805019378662, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5297932624816895, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5445988178253174, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5401058197021484, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5304160118103027, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5874977111816406, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5761871337890625, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5732812881469727, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6788973808288574, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.653611183166504, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07475083056478406, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.15300849021779253, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.17515688445921004, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.22591362126245848, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2440014765596161, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2528608342561831, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26153562200073827, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2469545957918051, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24603174603174602, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25839793281653745, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25452196382428943, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.22111480251015134, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22314507198228128, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.004936019917781252, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005345064917104308, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0057205359865420925, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005844064437814438, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007871643343192342, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010479672893104641, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011851890987114394, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012843402017216359, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013689364047468393, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014233082646012645, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01643236994700695, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06624301768521842, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.091288342432849, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1436868785910118, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16458665563776256, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1756783505536871, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18604005583374442, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19253538823842486, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.19334553254972606, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19161641984172784, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19529803727898085, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19259636799931826, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18901396928885095, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1900883804278255, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18832056359788218, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17313402418045307, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17746421175657737, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18643922015260758, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19196242420511542, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18443959103187665, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19184356497845026, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19524828827024396, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18286534410861557, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1860126071259125, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.18033627687167134, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15915224661867972, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.159328453679869, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.236482915878296, "validation/loss_best": 2.4528110027313232, "validation/acc_best": 0.2672572905131045, "validation/f1_best": 0.19334553254972606} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.641450135707855, "train/grad": 0.1705415178835392, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12783203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127783203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1275830078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127451171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127340087890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127176513671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12703369140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126785888671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1264208984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126064453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12568115234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1252734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.124632568359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12386474609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1228173828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1217529296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11980224609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.110853271484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.8134719848632814, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6952711486816407, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5214206695556642, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4037776374816895, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.3625278663635254, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.2738570308685304, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.2352864933013916, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.1825918340682984, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1430791664123534, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.124460551738739, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.125565905570984, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.101129333972931, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0898219990730285, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0958078575134276, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.133058032989502, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.120107665061951, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.064348564147949, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.069690957069397, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0919635987281797, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1149430322647094, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.079923837184906, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.034145432114601, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0636891758441926, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.059480290412903, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.111287559270859, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2148277068138125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008947487757541239, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008949502224568277, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008949223291128874, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008946756767109036, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00894373827148229, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008936023998539894, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008923735900316388, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008907369687221944, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0088792987447232, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008843008209951222, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0088015853241086, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008729881369508802, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008652366718742997, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008533347568009048, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008421845484990627, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008334716584067791, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008324125085491687, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.0090603743144311, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.017961008814163505, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.019468121198005974, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02348030049353838, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.025752551509067415, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02495724060572684, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.026870072800666094, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027077040569856763, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.027976218927651644, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02915714407339692, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029251775238662958, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029317860640585423, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.02964235285297036, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030476600341498853, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03149135590530932, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031489493371918795, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03266570458188653, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03499713880009949, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03531020204536617, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03565837301313877, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03738506973721087, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.039171891286969185, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0400859922170639, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03982306881807744, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04069170059636235, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.042082567177712915, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.04056798019446432, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1238086223602295, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1237847805023193, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123729705810547, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123660087585449, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1235828399658203, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1234629154205322, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123326301574707, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.12312912940979, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1228554248809814, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1225357055664062, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122225761413574, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1217217445373535, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121176242828369, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.120349407196045, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1194300651550293, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.118259906768799, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.115760326385498, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.092719793319702, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7467424869537354, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.687619686126709, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.539170503616333, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4866421222686768, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4519259929656982, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4515795707702637, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.445549964904785, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.428530216217041, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4397940635681152, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4525632858276367, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.453752040863037, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.460488796234131, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4780876636505127, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.46935772895813, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5247504711151123, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.535283327102661, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5463626384735107, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5055322647094727, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5806477069854736, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5409650802612305, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5570826530456543, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.563007354736328, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5162880420684814, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5495996475219727, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.593471050262451, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5628838539123535, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0769656699889258, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.16906607604282023, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.18752307124400147, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2397563676633444, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2502768549280177, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.257844222960502, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26541159099298633, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27556293835363604, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27888519748984864, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26448874123292726, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.266703580657069, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25230712440014763, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25987449243263194, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2517534145441122, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24307862679955702, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2456626061277224, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.004948775829137003, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.004924110763526821, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00513968846432312, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005555125242588935, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005758606547489807, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005714058432506483, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01842507232074793, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.09129844090339889, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.11246758374987176, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1628984781339846, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17920668323865677, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.18516186763900197, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19519245569161306, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20209484947049572, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.21162194433763268, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21738396852742722, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20965765197762964, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2189770242922103, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21227367825647592, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21195695122015915, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.21108330902637507, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1970343140277692, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19831867476846501, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19360126925696397, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20613662088923213, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1847879695894471, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1964307397156795, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19750694581991338, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19313255968916085, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2088477481803732, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19971729424452142, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17778624807480378, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17957109004930596, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.1430791664123534, "validation/loss_best": 2.4397940635681152, "validation/acc_best": 0.27888519748984864, "validation/f1_best": 0.21738396852742722} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.6168754327297212, "train/grad": 0.17472247269004584, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127529296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1274169921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127291259765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127130126953125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12695556640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1267724609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126705322265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1263671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1259423828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125670166015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.125274658203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124759521484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1240478515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.123228759765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.122100830078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.120643310546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.117611083984375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0238604736328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7481088256835937, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.62305419921875, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.462099494934082, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.3588428497314453, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.311757164001465, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.225311737060547, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1913136768341066, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.141043152809143, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.1017713928222657, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.079932165145874, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0919616127014162, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.066603639125824, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0493407821655274, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.063000440597534, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.090374994277954, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0809793281555176, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.0232540225982665, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0354762744903563, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.055356435775757, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.077361295223236, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.039555079936981, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9923970520496368, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.025420855283737, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.032414439916611, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.080709035396576, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.170776786804199, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00908706545131281, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009087691463064403, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009085448912810535, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009081705706194043, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009076155202928931, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009066750274505465, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009053074622061104, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009035333960782736, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009006736944429576, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008969957211520522, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008926989580504596, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008853692933917046, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008773331767879427, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008653032528236508, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008545371196232736, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008479729320388287, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008592863641679287, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.013047487323638052, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.018987179291434585, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02137036746367812, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02488689573481679, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026658698190003632, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026162931537255643, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02785948338918388, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028063418455421926, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029332687454298137, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030144126052036882, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03062169697135687, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030814090268686412, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0311635981220752, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031839834284037354, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03303783372975886, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03224637414328754, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0330963237117976, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.034668951947242024, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03580230029299855, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03589309102855623, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03677112776786089, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03888093400746584, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04023913488723338, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.04055530942045152, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04229284381493926, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.04373354729264975, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.040208720713853834, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1234912872314453, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1234078407287598, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123290538787842, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1231610774993896, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1230199337005615, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1228280067443848, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1226673126220703, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1224679946899414, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1222426891326904, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1220405101776123, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1218039989471436, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1214871406555176, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1211626529693604, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1205601692199707, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1197636127471924, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1185054779052734, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1149380207061768, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.933370351791382, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7159979343414307, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6044013500213623, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5007917881011963, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4656472206115723, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4322431087493896, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.430800437927246, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.420339584350586, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4278757572174072, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4340920448303223, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.447604179382324, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4595251083374023, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4622132778167725, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.464221477508545, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.484058380126953, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.50117564201355, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5397801399230957, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5601232051849365, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5525708198547363, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5986082553863525, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.562222719192505, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.592529296875, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6162846088409424, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5194544792175293, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5406413078308105, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5142338275909424, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.549647092819214, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.073827980804725, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1389811738648948, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1760797342192691, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21760797342192692, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24381690660760427, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25359911406423036, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2691029900332226, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26707272056109266, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2722406792174234, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2766703580657069, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2692875599852344, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2541528239202658, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25396825396825395, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25396825396825395, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24363233665559247, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25212255444813586, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23163528977482467, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004936877461199907, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005547597389532627, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005848709519884647, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007105172312653958, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008411630421199799, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009078017848047591, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009454005114382472, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010301235669210693, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010408785618426624, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010416460320536286, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011954066654331014, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.05622789156679364, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.08981748157809215, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13999486418528165, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17254596430671232, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18569739081170242, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20241662280221648, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19942138570338033, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20757802776515719, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2089117290221384, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20793050413024727, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20688436319052958, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.211477872364109, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21030908646941296, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2137826805663328, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20393159574220143, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1978995939804594, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1978461443363946, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2006499779730644, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2043741468017779, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18636772616697864, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1904999757728654, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1873629151004681, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18740122062228012, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20920888155044493, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19759029423054356, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2015829709160102, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17666977261349595, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.141043152809143, "validation/loss_best": 2.4278757572174072, "validation/acc_best": 0.2766703580657069, "validation/f1_best": 0.2089117290221384} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.5936772179603578, "train/grad": 0.16788300491869448, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12506103515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124991455078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124774169921875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124583740234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12445556640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1243310546875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.124091796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123787841796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123414306640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.123038330078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1226318359375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.122030029296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1213037109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1203369140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11896240234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.117275390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.112501220703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8929733276367187, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7050662231445313, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.548970413208008, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.41933012008667, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.3323688888549805, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.28776611328125, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.2003823947906493, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1663754272460936, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.1102894496917726, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0725099182128908, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.050651388168335, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.051638026237488, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.040803451538086, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.014886643886566, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0361349034309386, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.069579520225525, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0618419551849367, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.0001692891120912, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9990110421180725, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0244032454490664, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.0363722157478334, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0006125664710996, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9494699072837829, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9746101808547973, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9715137314796447, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0140979623794557, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.121411609649658, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009007208438124508, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009006032785400749, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009001009287312628, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008994183393660933, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008987196036614478, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008975462459493428, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008959445552900434, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008940013174433261, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008909465109463782, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008870011528488249, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008825633120723068, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008750341711565851, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00866951174568385, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008551836325787009, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0084545593499206, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008421199668664486, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008728154697455465, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.016069934437982738, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01965027289930731, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.022768954858183862, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.025410496769472955, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026651527360081674, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026176968477666377, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027822546502575277, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027919434579089283, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028921990133821966, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02965965057723224, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030040094694122672, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030143919084221125, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03045773033052683, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03141778588294983, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03219693088904023, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03201536050997675, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0328296316601336, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03420158079825342, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.034213664652779696, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03409256969578564, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.034917626976966855, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.035465107103809713, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.037328209932893514, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.037195868557319045, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.038961802748963235, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.039055603938177225, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03682399016804993, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235644817352295, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123492479324341, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123401641845703, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233065128326416, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232011318206787, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1230828762054443, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1229312419891357, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1228010654449463, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122586488723755, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1223433017730713, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1220929622650146, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121708393096924, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121264934539795, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1204874515533447, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1194300651550293, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1177570819854736, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.112067222595215, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.836270570755005, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6962509155273438, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5719611644744873, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.508054494857788, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4925897121429443, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.456787109375, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.471112012863159, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4563398361206055, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.482778310775757, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.483994722366333, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5062830448150635, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5215563774108887, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5039191246032715, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.505354404449463, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5513272285461426, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5757806301116943, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5962157249450684, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6105217933654785, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.606765031814575, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6058480739593506, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.582824468612671, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6140196323394775, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.58872652053833, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.567965269088745, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5737082958221436, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.616870880126953, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.623222827911377, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.15208564045773348, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1777408637873754, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2264673311184939, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2469545957918051, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24916943521594684, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26116648209671467, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26153562200073827, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24289405684754523, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23901808785529716, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24621631598375784, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2513842746400886, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25359911406423036, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2528608342561831, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24141749723145073, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23181985972683647, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004923255140457573, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005553549858894901, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005547597389532627, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005919992295035484, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005812688704979872, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006524054040949505, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.007643269698364527, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008446112863783547, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.012462616584311132, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.05969190545661749, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.09122172606264485, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1474574661215792, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1720171745583674, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17833632618077702, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19166183038688075, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.19309759897807158, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.19995290827864065, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2010879902918382, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20232683602557397, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2000586574498029, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19107488663093752, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20067575368004334, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20033428877247672, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19196952014123891, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1802935391720788, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.181500681114633, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1853535089005457, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18837646458088111, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18451342422476938, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19482494104849488, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18857384238577446, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19938091747025213, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20372055412939738, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19951561864598086, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18404703170642187, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17347827073960978, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.1663754272460936, "validation/loss_best": 2.4563398361206055, "validation/acc_best": 0.2672572905131045, "validation/f1_best": 0.19995290827864065} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.5981997311115266, "train/grad": 0.17301966063678265, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.129605712890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12947509765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129361572265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129207763671875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1290576171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128792724609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12848388671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12817138671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127777099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127431640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1269775390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12631103515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12561279296875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.124464111328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.123111572265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1213232421875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.11651123046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.899224853515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.713029479980469, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5555474853515623, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.42244140625, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.334723596572876, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.287254238128662, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.203196496963501, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1711176872253417, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.1154741430282593, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0784479784965515, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0580747389793395, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0618701040744782, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0477922105789186, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0246018999814988, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0424825966358187, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.073339681625366, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0611361980438234, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9957109117507934, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.004668699502945, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0273839795589446, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.0422929227352142, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.001001273393631, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.9562343788146972, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.977283393740654, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9752619445323945, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.034650628566742, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.1364950847625734, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00885302938055247, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008850910449400545, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008845273852348328, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008838487663306296, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00883081106003374, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00881811639526859, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008801702631171793, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008780878910329193, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008749017901718616, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008709290511906147, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008663907980080694, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008588085568044334, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008507085524033755, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008388933441601694, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00829246325418353, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008259212647099048, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008561130659654737, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.015905424705706536, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01949521612841636, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.022621356677263976, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02539038151502609, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026661130078136922, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02624985862523317, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02799823073670268, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02818671370856464, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028989451583474875, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030067919827997683, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030429630624130368, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030519855925813317, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03066106829792261, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03187999404035509, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03271416173316538, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03279071716591716, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03356950224377215, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.034919165316969154, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03525537901557982, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.035589908845722676, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03573554870672524, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03782095511443913, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.04067897001281381, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03957320354878902, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.040641417894512415, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0424379753600806, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03882934455759823, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1236650943756104, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123648166656494, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123570203781128, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123523473739624, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1234805583953857, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1233980655670166, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123358964920044, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1232848167419434, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1232004165649414, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123084306716919, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122957468032837, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.122706890106201, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1223676204681396, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1216514110565186, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1206185817718506, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.118920087814331, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.112990617752075, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.834104299545288, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6966254711151123, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5687379837036133, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.495570421218872, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4690961837768555, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.429866075515747, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.432333469390869, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.420740842819214, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.430682420730591, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4422013759613037, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4497969150543213, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.457582950592041, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4497945308685303, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.450629234313965, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4637176990509033, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.482201337814331, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4986610412597656, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.496692180633545, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5152525901794434, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.555925130844116, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5187299251556396, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5458054542541504, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.578744649887085, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4959840774536133, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5390896797180176, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.518831491470337, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5347211360931396, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1568844592100406, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.18180140273163528, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.22978959025470652, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24750830564784054, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.257844222960502, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26836471022517533, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2748246585455888, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27464008859357697, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2812846068660022, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.28183831672203763, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.27113325950535255, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2698412698412698, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2733480989294943, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26799557032115173, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25083056478405313, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2602436323366556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25212255444813586, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25046142488002954, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23809523809523808, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004948775829137003, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.004923255140457573, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005346494699348458, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005550371404029941, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005739501745723698, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0055175161377693715, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00617079517435339, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007335933753412908, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009995144377563471, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0668418325221355, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.09671713558645788, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15021902488198918, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17234719487109018, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18353547719910543, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19428203406879763, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2027913583612685, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20169646750060574, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20687744891399373, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21507144587847712, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20409477774230358, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2091989225396492, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20734624638032773, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21109260724171333, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2035422930923433, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19721931293355646, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19528979058762438, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1978971053403882, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19557717402068917, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1856500103025267, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19955029912562192, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1988677719199914, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19520369701569415, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21123333324345725, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20743777205415517, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2059608443078567, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18466259536523935, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 26, "lr_best": 0.00041999999999999996, "wd_best": 0.05, "train/loss_best": 2.0784479784965515, "validation/loss_best": 2.4422013759613037, "validation/acc_best": 0.28183831672203763, "validation/f1_best": 0.21507144587847712} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.5826465344429015, "train/grad": 0.16988358937203885, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12447265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124322509765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124083251953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.123931884765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123726806640625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123492431640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123292236328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122974853515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.122574462890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12218505859375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.121678466796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121014404296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.120286865234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.119112548828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11763671875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.115584716796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10858642578125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.834433288574219, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.685206298828125, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.523488693237305, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4043976402282716, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.32219482421875, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.276782150268555, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1942112922668455, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1653594398498535, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.10428617477417, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.066922917366028, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.041203420162201, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.043353500366211, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.029130527973175, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.0065307569503785, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.0161261999607087, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0539119052886963, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0434920167922974, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9770884323120117, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9793243277072907, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0022957253456117, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.0205988729000093, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9653666067123412, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.928350732922554, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.9375840854644775, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9366758227348329, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9807614123821258, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0922746121883393, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008890872560441495, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008888793478254229, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008882764410227537, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008875271056313068, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008868064342532306, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008855678986292333, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008839301269035786, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008819448677822948, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008787556930910797, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008748522128444165, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008704049920197576, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008629011707380414, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008548543723300099, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008435376496054232, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008351311997976153, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008357323815580457, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008929706290364265, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.017543764049187303, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.020491748405620454, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02332070960663259, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02566809787414968, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026753954067826272, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026307768737897277, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028031287956982853, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028155854102224112, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02910937851294875, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029897679435089232, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030519078271463513, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03072402094490826, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030523123210296033, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03152015395462513, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03228440474718809, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0318432729318738, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03279072156175971, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03385867912322283, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03432420100085437, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03448300284333527, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.035194045221433046, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.036892360094934705, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.039051976399496195, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.038033941788598896, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03934309711679816, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.039879317320883276, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03717200663872063, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235616207122803, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123520612716675, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234095096588135, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123338460922241, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123248338699341, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1231300830841064, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1230123043060303, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1228911876678467, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122694253921509, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1225197315216064, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1223013401031494, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1219606399536133, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1216063499450684, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.120884656906128, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.119858980178833, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.117990016937256, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.109492063522339, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.786227226257324, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.678096294403076, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5476925373077393, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.486605405807495, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.465251922607422, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.42783784866333, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4314632415771484, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.419924020767212, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4394948482513428, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.447568416595459, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.474472999572754, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4829800128936768, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4915685653686523, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.493656873703003, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.537714958190918, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5423974990844727, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.587756633758545, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5863840579986572, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6298553943634033, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.649506092071533, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.594928026199341, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6430106163024902, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.627000093460083, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5529792308807373, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6046345233917236, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.591078996658325, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.552438974380493, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07087486157253599, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.16555924695459578, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1834625322997416, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23717238833517904, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2528608342561831, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27205610926541157, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2727943890734588, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2702104097452935, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2571059431524548, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2454780361757106, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2382798080472499, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2336655592469546, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24381690660760427, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25064599483204136, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23717238833517904, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2425249169435216, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2382798080472499, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004921544786057553, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005550826233976736, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005715732448327192, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005820929577171033, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006897872521997015, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007961680369210819, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00831268654173945, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008959821822134785, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009281497151706211, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011505148052218452, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01513599967962602, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07660251704942365, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.09859817372490975, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.158834984185401, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.18232238449135196, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19238142840210257, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2058692661804081, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20664575843962507, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20739767074000484, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20451973632370568, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2070536498590716, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20371620473410287, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1972163285652012, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19875910425397114, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20500639461854933, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19311259553028878, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18604447415320458, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18435004157205181, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18786376777477662, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18025149542761235, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17212693351014893, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1836707017992212, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.17728756658573316, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.18929131522741358, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2039865020600151, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19372069735746664, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19769589897002401, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18270091979266376, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.1653594398498535, "validation/loss_best": 2.419924020767212, "validation/acc_best": 0.27408637873754155, "validation/f1_best": 0.20739767074000484} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.5750801050662995, "train/grad": 0.17332089252769947, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12462646484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124423828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124298095703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12416748046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124027099609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123758544921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123455810546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123118896484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.122720947265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.122177734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.121824951171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121080322265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12037109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.119166259765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11767578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1155078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.108458251953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.8277618408203127, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6747171020507814, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5112540435791018, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3906975746154786, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.307118911743164, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.260214958190918, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1743474817276, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1428439235687256, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0865948963165284, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.047841682434082, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0220377326011656, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0275454235076906, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.0109805965423586, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9904409337043762, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.004861695766449, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.039196004867554, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0287922692298888, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9601537203788757, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9644822406768798, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9910927104949951, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.0048368406295776, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9556512367725372, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.90302949488163, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.932938756942749, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.9297015190124511, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9797846853733063, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.089774990081787, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009113667437341065, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009111158419400453, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009104983422439546, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009098242612089961, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009091227492317557, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009079174273647368, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009062790165189653, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009042787754442543, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009011370164807886, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008971217572689056, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008924799512606114, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008846911995206028, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008763836417347192, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008643633166793735, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008552643551956863, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008550640589091926, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0091164182825014, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.018062145989388226, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02121072936337441, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024122214345261454, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026555122723802924, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027600187296047806, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026984074395149948, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02857941762544215, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02849468508735299, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029504601238295437, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03013414077460766, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030493996795266865, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03095718692056835, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030766032580286266, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03178108443506062, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03269577455706894, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03222743238322437, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.032952826637774706, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.034309313977137205, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03456688961014152, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.035144234467297794, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.035386390872299674, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.0377461900562048, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.038860007142648104, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03925673616118729, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.04030644943006337, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.041373558957129714, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.039161509545519946, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235947608947754, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1235342025756836, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234488487243652, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123354434967041, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232552528381348, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123128652572632, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1229805946350098, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1228039264678955, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1225602626800537, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1223042011260986, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122039318084717, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.12157940864563, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1211354732513428, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.120274066925049, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.11909818649292, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1171014308929443, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1083807945251465, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7847673892974854, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6798489093780518, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5556888580322266, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.499234199523926, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4825308322906494, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4392333030700684, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4483072757720947, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4343199729919434, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4519660472869873, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.461030960083008, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4832561016082764, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5048975944519043, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5008556842803955, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.507737874984741, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.53568959236145, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.543555498123169, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.56961989402771, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.561398983001709, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.554262161254883, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6171133518218994, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.546496868133545, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6028940677642822, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.569646120071411, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5163493156433105, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5742523670196533, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6040022373199463, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.588925838470459, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.16149870801033592, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.18881506090808417, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23145071982281284, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24455518641565152, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2528608342561831, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.26504245108896274, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2678110003691399, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2713178294573643, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2672572905131045, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2593207825765965, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2563676633444075, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2528608342561831, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2606127722406792, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2602436323366556, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25193798449612403, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24234034699150978, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23329641934293097, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004937735302635389, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005551495260946708, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005746438876054745, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005910763203159839, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005965790571547769, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006658464461520822, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01381939973132488, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07492665026635371, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1060108409899128, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15685643040986777, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1730311659230063, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.17927653353697873, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.19503555063503775, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20109818512626712, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20700052739701813, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20557961118909973, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21016806930907758, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20548525869687964, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20681404058565542, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20398606890673465, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20786998890977268, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20129103935876227, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18791192140893054, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18835169628743953, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18901189681347622, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19287405704518149, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17438640321884566, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19714398306293582, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18256077709863347, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20145876325311962, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20055308723221668, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1939078297067521, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18377419053958852, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17456129937530085, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.1428439235687256, "validation/loss_best": 2.4343199729919434, "validation/acc_best": 0.2713178294573643, "validation/f1_best": 0.20700052739701813} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.5632184982299804, "train/grad": 0.1658878129348159, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12774658203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1276513671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127459716796875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1272509765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127064208984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126834716796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126610107421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126248779296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125794677734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125369873046875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124930419921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124329833984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12351806640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12233154296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12068603515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11830322265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.107928466796875, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7976800537109376, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.650992736816406, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4881683731079103, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.374659290313721, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2951714515686037, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.252751560211182, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.165300850868225, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.134799237251282, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0735031604766845, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0349508261680604, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0094778060913088, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.0036400425434113, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.997940607070923, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9658744311332703, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9858920359611512, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0189187002182005, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0049928522109983, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9395678305625916, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9360459464788438, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9569922292232513, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9836776161193848, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9243472105264663, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.869833256006241, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8886961525678634, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8806973081827163, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.937560828924179, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.05614280462265, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009082530282903463, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009079868902917952, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009074570320080966, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009068026293534785, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009061438057105988, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009050195289310068, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00903545797104016, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009015925887506455, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008985726279206574, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008947309548966586, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008903282342944295, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008828930279705674, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008749564178287983, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008638837742619216, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008565300651825964, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008610667260363698, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009510363838635384, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.018673118446022274, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.021793090179562567, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02412633285857737, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026281783683225514, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02722083605825901, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026756805973127483, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028185870051383972, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028097592517733572, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028958355840295553, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029430845389142632, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02972258470021188, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030103017715737222, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029685149434953928, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03058175913989544, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031179285403341056, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03108739893883467, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03142200967296958, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03233691728673875, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03299114123918116, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03315051302313805, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.033673330610617995, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03524720044806599, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.037174897640943526, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.036970855966210366, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03775479940697551, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03833068815991283, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03525604830123484, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235413551330566, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123501777648926, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234240531921387, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233341693878174, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232426166534424, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1231110095977783, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122969627380371, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122844696044922, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1226301193237305, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1223948001861572, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122145652770996, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1217103004455566, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121232271194458, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1203134059906006, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118992805480957, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1166834831237793, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1036319732666016, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.763007164001465, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6631829738616943, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5379798412323, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.483954668045044, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.461721181869507, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.426231622695923, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.435969352722168, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.421272039413452, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4432461261749268, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.456381320953369, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4770944118499756, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4918012619018555, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.482269763946533, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.51755690574646, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5315756797790527, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.555676221847534, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.590362787246704, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5896081924438477, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5720300674438477, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.595348358154297, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.560781478881836, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5806117057800293, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.567377805709839, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5633280277252197, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.567976474761963, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5943603515625, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5609793663024902, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08028792912513842, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17054263565891473, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19047619047619047, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23772609819121446, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2500922849760059, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2582133628645257, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27260981912144705, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2733480989294943, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27500922849760057, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2681801402731635, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2587670727205611, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2576596530084902, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2410483573274271, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.26005906238464377, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24861572535991142, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24437061646363972, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23938722775932078, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24012550756736803, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005345224633884001, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005730306308651315, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006142257768599029, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.007288979289790459, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008296760710553814, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00888805561812196, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009296130772381275, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009212621241411631, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.009756167750943172, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010081268684170988, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011017492605268612, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.016690136621187932, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08356324464148672, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11098655180357168, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1611804944908594, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1792241583340619, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18945778315748898, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2046028025060689, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20629746570202165, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.21035318232553432, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2087991502146689, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21099341023170212, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20505986949448748, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20495803935971937, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2082726706784169, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20706617151433063, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2033617055772006, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19492113269877998, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19079503661039046, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19232791905848165, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19508792553105617, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19390204597809255, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20337959112025575, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20109220898171945, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2102861459888741, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.2025751264031509, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20362471095589205, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19617075593246622, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1891908224108311, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.0735031604766845, "validation/loss_best": 2.4432461261749268, "validation/acc_best": 0.27500922849760057, "validation/f1_best": 0.2087991502146689} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.5564787197113037, "train/grad": 0.16507647316902876, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12454345703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12445556640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124283447265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124088134765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123931884765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123720703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123387451171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123023681640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.122669677734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.122216796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.121739501953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12100830078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.120172119140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11881591796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.117218017578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.114691162109375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.103809814453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.796147766113281, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.645802307128906, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4844461822509767, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.366484146118164, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2861654281616213, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.239113416671753, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1554178905487063, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.122802219390869, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0619829726219177, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0259671926498415, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9984911036491395, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9938894987106324, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9875029277801515, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9585509836673736, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9773204505443573, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.016892418861389, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0011971509456634, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9326695346832274, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.929739819765091, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9521104633808135, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9701750999689103, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.904505628347397, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.85635979115963, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8754803067445756, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8668166095018386, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.91540186047554, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0328761661052703, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008990948537830263, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008988173173274844, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008981832363642752, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008974535721354187, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008967045911122113, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008953979974612593, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00893762688850984, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008917120634578168, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008884420334361494, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008842360572889446, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008795201941393316, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008716803181450815, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008633835297077895, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008518609816674143, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008441336175892503, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008481416443828493, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009366911014076322, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01848391626961529, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02152442345395684, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024002218749374152, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026117841564118862, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.0270935795083642, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026665071975439786, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028119490165263415, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028025364307686686, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0288739597145468, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02958841299638152, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030032506678253412, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030512478910386564, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03026055104099214, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031130650229752064, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03163320867344737, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.031734508275985715, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03225199048407376, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03314182629808784, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03357979620806873, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03325374623760581, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.033661898421123625, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03501518903300166, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03558025736361742, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03544026075862348, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.036289329770952464, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03665355356410146, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.034197222935035826, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235783100128174, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1235177516937256, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234283447265625, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233489513397217, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232547760009766, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123135566711426, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1229841709136963, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1228060722351074, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122606039047241, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1223673820495605, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122123956680298, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1217522621154785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121349811553955, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1205904483795166, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.119429349899292, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1172919273376465, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.104518175125122, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.765287399291992, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6662163734436035, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5410783290863037, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.487396001815796, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4676575660705566, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4337193965911865, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4418137073516846, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4292256832122803, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4491143226623535, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.465069055557251, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4813594818115234, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.486140727996826, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.487597703933716, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.497119188308716, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5207486152648926, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.523386240005493, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.572047233581543, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5806448459625244, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6102142333984375, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6123735904693604, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.586742401123047, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.660285472869873, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6282031536102295, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5894405841827393, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.625425100326538, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.62484073638916, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6149497032165527, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07604282022886674, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.16611295681063123, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1906607604282023, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2369878183831672, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24750830564784054, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.25599852344038393, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2692875599852344, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27205610926541157, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2709486895533407, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26208933185677374, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.266703580657069, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25599852344038393, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23846437799926173, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.23311184939091917, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.24473975636766335, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2556293835363603, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2410483573274271, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23292727943890734, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.004935162672224152, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0053455601676037955, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005737075921968609, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005858176561773835, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006486639398903991, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007571918116870704, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008741937556196896, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00941307059781987, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.011162983696186414, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.016631632310281957, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08042390108283454, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.10815936905234179, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16172774263058518, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17877114858642962, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1881970386588868, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20090181238438962, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20366156814960348, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20674386727449132, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20562825339888716, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20819791653742717, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20565269314799073, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2071266975659226, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2091942416168253, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20734739207978403, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20015966060256082, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.193193321706999, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18582733381530736, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19051774750416528, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18698765201471193, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18243597578834947, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19576902834624796, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1788695301681856, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19326655731190648, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20651886739024064, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19221026027819166, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.18294543129610727, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1784191297661456, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.122802219390869, "validation/loss_best": 2.4292256832122803, "validation/acc_best": 0.27205610926541157, "validation/f1_best": 0.20674386727449132} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.5526183819770814, "train/grad": 0.1643853186070919, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12520263671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12505126953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124853515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12466796875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124510498046875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1242822265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123951416015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123641357421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123175048828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.122685546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122193603515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121466064453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.120650634765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11931884765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1176318359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11491455078125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10007080078125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7833132934570313, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.63484733581543, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.477959098815918, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.366155033111572, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2878536701202394, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2416968154907226, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.156902322769165, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.122926173210144, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0634288597106933, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0279783272743224, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9999310874938965, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9937933087348938, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9862443065643312, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9549548101425172, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9662287330627441, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.003777756690979, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9925516653060913, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9286099505424499, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9196198976039887, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9373110723495484, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9636919164657594, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8971140134334563, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8338904809951782, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8551424551010132, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8410277163982391, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8985483741760254, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.025161921977997, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009023326155729592, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009020464990753681, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00901447776472196, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009007448109332471, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009000363869126886, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008987828507088125, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008972009615972639, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008951762928627432, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008920268809888512, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008879818024579435, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0088337623141706, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008757320987060667, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00867696758825332, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008567156789358705, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008501291528809816, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008574534652289002, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009763040244579316, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01887045906390995, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022211813451722264, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02446433057077229, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026557948580011724, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02750116846524179, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027019130066037178, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028434648886322977, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02843429146334529, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02925592112354934, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029793120278045534, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03022347008809447, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030704703936353325, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.0302505339961499, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03132908184081316, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03141708239912987, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03147789885289967, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03164881506934762, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03283406348899007, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0326606254838407, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0325965204462409, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03299062641337514, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03429590472020209, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03528235004283488, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03470244711264968, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03545831865631044, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03678325399756432, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0343192645907402, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.123532772064209, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1234750747680664, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1233878135681152, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1232848167419434, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123196840286255, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1230554580688477, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1229069232940674, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122737169265747, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122509002685547, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122227191925049, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121952772140503, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1215076446533203, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1209893226623535, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.120039701461792, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118663787841797, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116093158721924, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.098039150238037, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.752890110015869, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6542558670043945, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.532977342605591, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4850451946258545, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4654011726379395, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.423567771911621, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.437068223953247, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.420740842819214, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4433693885803223, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.447770595550537, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.458707094192505, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.466890573501587, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.461652994155884, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4692394733428955, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.490636110305786, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.509622812271118, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5489187240600586, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.558730363845825, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5422098636627197, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.566709518432617, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5368731021881104, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5849523544311523, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.598053216934204, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5777194499969482, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6036839485168457, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6460769176483154, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.625439167022705, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07493540051679587, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1701734957548911, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19656699889258028, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2395717977113326, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24861572535991142, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2587670727205611, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2731635289774825, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26965669988925806, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2779623477297896, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27556293835363604, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27353266888150607, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26744186046511625, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.27297895902547065, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24787744555186417, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24916943521594684, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2502768549280177, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25858250276854927, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24455518641565152, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24197120708748615, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23255813953488372, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004923255140457573, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005345389704860774, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005542257128625691, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005898754354959523, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005792644392174872, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006311881033327911, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007531782126524629, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007815517510919912, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00834286065523388, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008069181414000252, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014729859124052995, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08351576582378063, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11532343517047383, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1632463596308764, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17660101624520821, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1884746275932481, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20218390901014002, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2019958831167006, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2088218722012968, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20517191753008476, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21222990409828477, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20739822528461818, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2086336523999135, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2108179984488822, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21355150603848314, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20707647506869675, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20194488600921778, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19667455040557533, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19495639136612378, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1964105977679189, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1922242884221653, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20166405229217568, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20021729985326928, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1997059773024601, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20474039383112572, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19615432533823607, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1874723930579484, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17707184746241897, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.122926173210144, "validation/loss_best": 2.420740842819214, "validation/acc_best": 0.2779623477297896, "validation/f1_best": 0.2088218722012968} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.559856958389282, "train/grad": 0.16222460709512235, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12686279296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.126685791015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126468505859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126068115234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12574462890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1254443359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125010986328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124482421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124019775390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1232958984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122513427734375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121099853515625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.119471435546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.11677734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.101790771484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7987713623046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.655211639404297, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4974549865722655, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.38417781829834, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.304379644393921, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2586141204833985, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1742085552215578, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1408546113967897, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.077663989067078, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0391720223426817, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.0141117787361145, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.005787093639374, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9953476333618163, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9601550662517548, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9751797723770141, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0147515153884887, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.0018617963790892, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.937690395116806, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.932666654586792, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9424585437774657, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.977660898566246, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.9068798446655273, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8452187478542328, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8615916192531585, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.8476300841569901, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.9064312064647675, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0285910868644716, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00892863831249997, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008926389843691141, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008920002251397819, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00891266689170152, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008905085884034634, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008891944359056651, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008876393677201121, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008855760390870273, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008824336221441626, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.0087840406014584, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008739043162204325, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008665028442628682, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008586343009956181, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008480476529803127, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008417112894821912, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008491395490709692, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009677219891455025, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.018648969731293617, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.021953852875158192, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024207090735435487, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026207499941810965, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027134138979017734, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026760683208703995, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027999976677820088, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02779171023517847, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028603498442098498, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02907459771260619, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029444541949778795, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029938689190894364, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029536823770031334, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.030491636851802468, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03091519041918218, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030801442982628942, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03124790819361806, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03234941621311009, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03266704835928977, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.032916688602417706, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03290348112583161, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03420207878574729, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.034926645010709766, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03463570625521242, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03525241009891033, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03644191686064005, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.033330910205841065, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235814094543457, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1235318183898926, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123438835144043, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123363494873047, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123246192932129, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1231226921081543, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12298583984375, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122844696044922, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1226186752319336, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1224019527435303, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122157096862793, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121777296066284, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1213395595550537, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1205050945281982, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1192054748535156, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.11678147315979, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0986413955688477, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.757120132446289, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.657036781311035, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.534045696258545, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.483372211456299, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.462815284729004, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.425846815109253, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4342455863952637, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.423023223876953, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.44553279876709, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.45957612991333, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4711883068084717, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.484346866607666, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4894115924835205, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4890689849853516, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5201213359832764, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.526430368423462, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5641746520996094, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.548541307449341, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.542330026626587, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5770418643951416, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5348684787750244, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5814924240112305, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.594835042953491, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5747265815734863, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.581111431121826, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.59375262260437, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5778698921203613, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1699889258028793, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19564414913252123, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24141749723145073, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2499077150239941, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27408637873754155, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27260981912144705, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2589516426725729, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24455518641565152, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2441860465116279, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2556293835363603, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.25950535252860835, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24935400516795866, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2499077150239941, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23588039867109634, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.004948775829137003, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005346494699348458, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0055482278347451265, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005737075921968609, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005876493604403843, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005793705303562092, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006231840518546628, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006474040056129608, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.007029553571146758, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.014165613405876196, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0812532920915831, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11436475209510293, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1642631074609908, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17772765688755773, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.18875946038244043, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20388841644415992, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2044823482383934, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20663804072165562, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20223382113893731, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2088903206370573, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2039000939571739, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20058711773772617, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2058408230503014, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20280821691925266, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19755210937076498, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19599400032314776, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18977488297689574, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1931235300700802, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19970191775951365, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18698137176843957, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1978236979459873, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19827125669744064, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2030732387387788, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20924959921740982, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20277472804090338, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19993060158667242, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18096305342997784, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.1408546113967897, "validation/loss_best": 2.423023223876953, "validation/acc_best": 0.27408637873754155, "validation/f1_best": 0.20663804072165562} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.5526140451431276, "train/grad": 0.1589877038449049, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1294677734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129378662109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12914306640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12900146484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128839111328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12861328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12829833984375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127991943359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12754150390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1270849609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126610107421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125855712890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125064697265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12373291015625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.122083740234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.119173583984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.100146484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7882611083984377, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6434617614746094, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4863047790527344, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.375450305938721, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.295957546234131, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2470139026641847, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.163779783248901, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.131287679672241, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.073128547668457, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0298712778091432, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9995885038375854, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9992229890823365, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9855311608314514, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9553534245491029, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9713068735599517, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.0034876108169555, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9872096395492553, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.919472997188568, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.9102703267335892, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.929229485988617, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.955356116294861, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.882553390264511, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.8253320842981338, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.836038537621498, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.821336390376091, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.871839432120323, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.003043148517609, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008852113031316548, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008849608979653567, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00884378323564306, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008837615128140897, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008831001655198633, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008819495900534094, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008804767932742834, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008784929679241032, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008754474490415306, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008715197388082742, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008670683118980378, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00859671070240438, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00851894283434376, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008413933389820159, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008354839631356298, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008444880531169475, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009850101906340569, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01874147533904761, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022182814301922916, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024239121489226818, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026115946946665646, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026981123462319373, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026543924333527685, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02779940596781671, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027743844278156758, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02855678826570511, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02907060441561043, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029292529495432974, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029810457201674582, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029180899281054735, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.0301611159555614, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030527406306937337, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030146795036271216, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030487800827249886, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03150181167759001, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03166957682929933, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03215960089117289, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03182858902029693, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03321948006749153, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03381032787263393, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.033393883211538196, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.033892983449622986, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03477825377136469, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03207013387233019, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235222816467285, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1234700679779053, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1233670711517334, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123284101486206, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123180866241455, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1230413913726807, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1229236125946045, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1227474212646484, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1225147247314453, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12225341796875, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121983528137207, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121541738510132, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1210389137268066, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1200883388519287, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1186881065368652, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116034984588623, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0943210124969482, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7495992183685303, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6492910385131836, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.528503179550171, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4803569316864014, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4595110416412354, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4221243858337402, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4330663681030273, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.420116424560547, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4419970512390137, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4503958225250244, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4644060134887695, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.477226972579956, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4759936332702637, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.479107141494751, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5150816440582275, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5188519954681396, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.555816650390625, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5717060565948486, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5874898433685303, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5977389812469482, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5664620399475098, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6220359802246094, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6094911098480225, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5665860176086426, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5902512073516846, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5817103385925293, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5747036933898926, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08213362864525656, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17054263565891473, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19804355850867478, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2425249169435216, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25046142488002954, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26208933185677374, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2739018087855297, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27464008859357697, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2742709486895533, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2698412698412698, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2622739018087855, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2532299741602067, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24363233665559247, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24012550756736803, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25046142488002954, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2604282022886674, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24861572535991142, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2511997046880768, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23901808785529716, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004923255140457573, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005345389704860774, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005737075921968609, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005863139339575795, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005950976835042479, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0070129267636437785, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00753319029933269, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0084205249343007, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00888045929556825, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00964676175129237, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.019188158301618238, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08381805552719047, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11747510215136191, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16640679254432197, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1804638548886166, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19438052622403612, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2046669590387983, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2067696851518591, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20783040630972113, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20451602861946774, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20951181709684064, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20618835443307568, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20546745984560186, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20980426805715238, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21274030598122806, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20598028496456225, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19375746716202777, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19056647220050094, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18793758299525432, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19399710280909754, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18636160233945362, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19556726865031973, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.18743350933167857, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1956806408789359, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20891125305988892, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1991836083293195, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19773624598343487, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1812983605410782, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.131287679672241, "validation/loss_best": 2.420116424560547, "validation/acc_best": 0.27464008859357697, "validation/f1_best": 0.20783040630972113} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.5412391662597655, "train/grad": 0.157739769667387, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1284033203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128228759765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128004150390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127786865234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127568359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12724609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126898193359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12641357421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125992431640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12543701171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1248828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124080810546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12308349609375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121639404296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11975341796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.116705322265625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.096761474609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.772271728515625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6213307189941406, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4655616760253904, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3548804092407227, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.277148838043213, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.229046049118042, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1474289417266847, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.114982590675354, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0530451130867005, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0138153624534607, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9834689116477966, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9786264073848725, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.969198067188263, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9345292901992799, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9500086045265197, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9863535904884337, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.967386920452118, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.89436048746109, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8878169357776642, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.9072290456295014, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9386375641822815, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8688612568378449, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7997901809215546, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8174080979824065, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.803490309715271, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8482662320137024, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9775172805786132, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008871535337530077, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008869118497241289, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008862676876597107, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00885557155823335, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008848161641508341, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008835186052601784, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008819513279013336, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008799104678910225, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008767532669007778, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008727750997059048, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00868303137132898, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008609375527594238, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008530785567127169, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008425560041796416, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008365482545923442, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00845315759535879, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009856867312919348, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01872159664519131, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022088794820010662, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.0241934974770993, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026093277735635637, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026981014022603632, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0265177365206182, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02779552430845797, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027713074656203388, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028428940381854773, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.029004667876288293, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02923042588867247, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02954830599017441, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028927635047584773, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029671046938747166, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03021066979505122, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030163812432438136, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030445041228085758, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.031301636388525365, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.0314413255173713, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03150080911815167, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.031481649558991194, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03265566497109831, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0334961502533406, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03291971673257649, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03349180260673165, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.033936275159940126, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.031484981318935755, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235644817352295, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1234757900238037, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123399019241333, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233038902282715, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232097148895264, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1230568885803223, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122913122177124, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122741937637329, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1225271224975586, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122288465499878, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1220366954803467, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.121638059616089, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121170997619629, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1202645301818848, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.11889910697937, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116328716278076, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0941219329833984, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7512869834899902, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.651735782623291, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5332353115081787, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4871177673339844, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4675796031951904, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.428652286529541, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4413323402404785, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4285120964050293, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4478907585144043, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.453062057495117, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.465549945831299, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.479099988937378, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.478085517883301, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.482569932937622, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5056214332580566, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.507991075515747, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.545128345489502, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5448169708251953, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.562384605407715, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5817484855651855, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.547724723815918, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6086435317993164, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5960981845855713, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.544735908508301, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5650510787963867, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5721278190612793, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5417213439941406, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06256921373200443, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08102620893318568, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.16943521594684385, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20081210778885197, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2412329272794389, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2484311554078996, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2591362126245847, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26799557032115173, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27500922849760057, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27205610926541157, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2727943890734588, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26559616094499816, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.266703580657069, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25950535252860835, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2561830933923957, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2648578811369509, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2511997046880768, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24898486526393504, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24215577703949798, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004936877461199907, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0055501650329236535, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005728451217721103, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005801375277242692, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006502350238753317, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007590132827324478, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007776860583335665, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008461734798896711, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008178046271418167, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008249801306027302, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.018933592150488402, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08272747451309877, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11967919569907011, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1650401477342703, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1787136147929178, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19003102189793064, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20236950479324986, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20100998350429525, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20689242490650475, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2051878535547058, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.21176777086031415, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2054339200108406, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20561764871850638, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20859723869730676, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20831725271781754, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20216637332646506, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1982548923966396, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19694723369525455, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19652405415775032, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1980406690153503, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19559289829107707, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20696639819321436, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19388221943511905, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20505220419604067, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21654778883785042, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20687833043555856, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20233397963575558, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19204936699725703, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.114982590675354, "validation/loss_best": 2.4285120964050293, "validation/acc_best": 0.27500922849760057, "validation/f1_best": 0.20689242490650475} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.547499945163727, "train/grad": 0.15380604702979325, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.134520263671875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13438720703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1341357421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.133975830078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.133778076171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1334521484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.133155517578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13283203125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1322607421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.131787109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.131292724609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1304736328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129583740234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128310546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126329345703125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.123509521484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.10222900390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7886138916015626, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.636454086303711, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4793989181518556, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3656814765930174, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2880226802825927, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2441108131408694, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.164121289253235, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.132201118469238, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0705392837524412, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.027306804656982, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.99758770942688, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9892434787750244, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9792791104316712, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9403777647018432, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9575326871871948, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9884114480018615, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9721787357330323, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.9088108611106873, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8981200885772704, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.912115443944931, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9471258127689361, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8668699306249619, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7978883308172227, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.8029311990737915, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7884775722026824, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8409122323989868, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9777988767623902, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00882617749972269, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008823721690569074, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008817086960189045, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008810485692229121, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008803514186292887, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008791024016682058, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008775700950063765, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00875534710707143, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008724222262389957, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008683748219627887, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00863896227441728, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00856343369698152, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008484719411935657, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008378695060964675, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008321215631440282, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008419178545009344, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009940960933454335, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.018555475836619734, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.021993702352046965, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024112568963319064, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026038856664672493, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026867391336709262, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026429914021864533, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027606301419436933, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02752405875362456, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.028209452349692583, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028672986859455706, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02882401746697724, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029125027675181627, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028600314585492014, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029384244075044988, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02974910518154502, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.029303623270243405, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02986498937010765, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.030368941333144904, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03053103937767446, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03062280923128128, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030101109435781835, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03132370609790087, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03197243176400662, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03132203827612102, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03136172289028764, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.031864289389923216, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03015189972706139, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235299110412598, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123483180999756, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.123382568359375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123281240463257, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232030391693115, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123067855834961, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1229193210601807, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1227657794952393, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1225404739379883, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122272253036499, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121995687484741, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1215691566467285, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1210784912109375, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1201326847076416, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.11871600151062, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1160295009613037, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0928430557250977, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7486348152160645, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6490230560302734, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.530186176300049, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.484140157699585, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4628658294677734, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4240915775299072, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.4359233379364014, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4233062267303467, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.441448211669922, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.449660062789917, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4633350372314453, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.473971366882324, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4727518558502197, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.475362777709961, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.505375862121582, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.509153127670288, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.548513412475586, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5596444606781006, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5674004554748535, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.578737497329712, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.551426887512207, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.599968910217285, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.592679262161255, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5520901679992676, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5714151859283447, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5799851417541504, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5604560375213623, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08047249907715023, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17201919527500922, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20062753783684018, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23938722775932078, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24953857511997046, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2593207825765965, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27297895902547065, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2705795496493171, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2748246585455888, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2753783684016242, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27002583979328165, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26448874123292726, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26578073089701, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2724252491694352, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2484311554078996, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24086378737541528, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25452196382428943, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2593207825765965, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25212255444813586, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25083056478405313, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2410483573274271, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004936019917781252, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005345736060058657, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005545150631288239, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0058867966146703326, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005792644392174872, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006334356613208109, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007214826640788653, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007900886551374997, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008714069125693863, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008926146069265306, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01871853862618497, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08446598191755926, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11948658664790585, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16351876066192347, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1791765736765921, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19028511777978827, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20367651181237267, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20399662499375112, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20768680991311475, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2062305441779375, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.210181821919777, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20918574609379584, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20809081736855908, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.21238060407851148, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21459708667411073, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2065051239246073, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20232136046448015, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19670863093076796, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19867015295258608, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1989943156643097, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1929203094458899, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20477808843018797, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19297917210769144, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20553750343986618, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21178349941370736, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21156031644494946, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20390878487582606, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19122088825519526, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.0705392837524412, "validation/loss_best": 2.441448211669922, "validation/acc_best": 0.2753783684016242, "validation/f1_best": 0.2062305441779375} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.5398218953609466, "train/grad": 0.1559490652754903, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128328857421875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128216552734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1280126953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127806396484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1275830078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127259521484375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126947021484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12656494140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1260546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125589599609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12506103515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124219970703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.123223876953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121883544921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.119990234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.117135009765625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.09470703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.778736877441406, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6300222778320315, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.473661880493164, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3620612144470217, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2867955207824706, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2370459461212158, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.156135416030884, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.124621911048889, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0593477058410645, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0245506668090822, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9951892042160033, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9837324953079223, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.967344923019409, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.939298508167267, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9424521470069884, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9738202595710754, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9577764964103699, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8930678462982178, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8815062588453293, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8946364569664, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9323362523317338, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.854892972111702, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7858726012706756, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.7905277550220489, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7777837473154068, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8311011952161789, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.95899738073349, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00892967259278521, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008926883549429476, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008919538233894854, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008912204070948065, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008904239600524307, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008890717681497335, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008874945321585982, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00885382722131908, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008821001045871526, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008780145985074341, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008733631472568958, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008657474720384925, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00857680746819824, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008468486729543655, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008407764963340014, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008502945550717414, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01005455363774672, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.018942416054196654, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022316664746031164, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024479320095852016, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026309014596045018, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02717582047916949, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026753383874893188, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027939960155636073, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027842005025595428, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02841581027954817, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.02903414636850357, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029382245605811475, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029642806258052587, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029175499556586146, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029843490179628132, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030179065251722932, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02956209149211645, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030003278013318778, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.030800675936043263, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.031087288362905384, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03089195791631937, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030952031165361403, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03188669775612652, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03242692893370986, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03149368365295231, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03219770420342684, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0324683182220906, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.030415911097079515, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235601902008057, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123494863510132, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234216690063477, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123305082321167, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123206615447998, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123070240020752, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122920036315918, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122767925262451, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.122549057006836, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.122330904006958, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122067451477051, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1216814517974854, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1212141513824463, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1203360557556152, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118940591812134, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116299867630005, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0924713611602783, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.75011944770813, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6490871906280518, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5300071239471436, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4824657440185547, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4611949920654297, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.423969268798828, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.431523561477661, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4191904067993164, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.439594030380249, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.445085048675537, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4603397846221924, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.478945255279541, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.479435682296753, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4822776317596436, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.509941816329956, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.516843557357788, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5628232955932617, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.565061569213867, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5840201377868652, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6002118587493896, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.571382522583008, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.629423141479492, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6109254360198975, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5760767459869385, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5881242752075195, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.598806142807007, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5767910480499268, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08342561830933924, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.16777408637873753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20044296788482835, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24141749723145073, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25064599483204136, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26005906238464377, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2733480989294943, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2709486895533407, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2763012181616833, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.27297895902547065, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2722406792174234, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2631967515688446, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25802879291251385, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24584717607973422, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2456626061277224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24307862679955702, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2526762643041713, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26005906238464377, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25359911406423036, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2502768549280177, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23901808785529716, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004935162672224152, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005551495260946708, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005735097114155815, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00583993083993084, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006233738133134984, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006872718978102189, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007926013415507758, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008269238541714729, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008363488332992794, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00880308537851922, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.020148907491557042, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08203721835977654, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11932725025880159, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16549587604032562, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.18130501913144204, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19230445407472221, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.20337610054335234, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20513502082274684, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20976408469257202, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20463300747646407, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2113382984404013, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20832969486938233, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.20633673916770726, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20938201563069123, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20902666351197197, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20303410112738232, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19614961871374306, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19364232422177205, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19696762834559592, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19388472906414145, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.18828218532670604, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2001259207769679, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19222830477412386, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1986566677758698, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20993262202284502, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2071571055394615, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19982865254413493, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18600241345113744, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.124621911048889, "validation/loss_best": 2.4191904067993164, "validation/acc_best": 0.2763012181616833, "validation/f1_best": 0.20976408469257202} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.5339425802230835, "train/grad": 0.1539688976109028, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123990478515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12381103515625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123603515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12341064453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12316650390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.122840576171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.122520751953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122183837890625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1216650390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12110107421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.120576171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.119764404296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1188671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11740966796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.11542236328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.112384033203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.089473876953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7682736206054686, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6214183807373046, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.468675537109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3599083328247072, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2833425045013427, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2375221824645997, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.15106662273407, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.11732964515686, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.053035328388214, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.0118687844276426, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9836739158630372, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.97564239859581, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9605651807785034, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9237550830841064, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9388959908485413, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9676864910125733, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9503271007537841, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.889491069316864, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.876493501663208, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8878790378570556, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.924180463552475, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8409873944520951, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7727274137735367, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.775237850546837, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.7677461755275727, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8185069024562837, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.955385663509369, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008998006889596582, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008995480828452855, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008988782092928886, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008982209879904985, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008975138645619154, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008962397826835514, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00894654429750517, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008925833576358854, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008893683324567974, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008851805292069912, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008806458828039467, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008729822020977735, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00865071966778487, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008544858992099762, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008490175227634608, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008597708712331951, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01020979608874768, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.018926568645983934, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0224446723703295, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024394059348851443, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026283338200300932, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027161829760298132, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026625849017873408, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.0278709863871336, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02788199409842491, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02845153900794685, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028896122872829437, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.029058831464499234, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02947084203362465, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028929467182606458, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.029499061992391943, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.030014272192493082, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.029517592648044228, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.02974662103690207, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03028105603531003, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03032562798820436, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.030529485996812582, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0298626375105232, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030974988546222448, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.031457326812669634, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030951293371617793, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.031074133003130555, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03134114882908762, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.029559284290298818, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.12353777885437, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1234939098358154, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1233763694763184, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123293161392212, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.123201847076416, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1230738162994385, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122926950454712, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1227664947509766, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1225523948669434, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1222851276397705, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.122020959854126, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1215760707855225, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121084451675415, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1201651096343994, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118744373321533, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1160590648651123, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.092686176300049, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7486274242401123, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.649013042449951, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5301032066345215, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.484076499938965, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4626553058624268, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4236860275268555, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.435128688812256, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.422996997833252, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.442652940750122, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.450990676879883, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.464005708694458, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4772698879241943, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.474914789199829, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.479722499847412, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.508981466293335, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5130412578582764, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5524661540985107, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.563978672027588, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.574387550354004, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.58614444732666, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5551657676696777, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6053459644317627, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5988285541534424, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5603132247924805, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.578458786010742, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5861332416534424, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.567704439163208, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08065706902916205, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.17091177556293835, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.19952011812476927, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.24031007751937986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.24880029531192321, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2596899224806202, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.27353266888150607, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.27113325950535255, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27500922849760057, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2753783684016242, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2703949796973053, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2633813215208564, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26965669988925806, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24234034699150978, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2567368032484312, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2631967515688446, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25046142488002954, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.24658545588778147, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24086378737541528, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004935162672224152, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005345917420552075, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005545150631288239, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005904058643792405, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005818287079845315, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00637321042045725, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0071143101420376095, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007980711514600605, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008587805524683694, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008965245490764736, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.019349808394062116, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08418969275593796, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1192558934866874, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16444299421211314, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.17815423688264398, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1906747845809196, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2038705412064669, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.2042764883189875, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.2079178696825746, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.20605826032000488, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.20991028540414494, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.2075955450774104, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2088874097700427, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2094800170302216, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21150218508160754, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2048682953624019, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1989711912787341, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1939471660811288, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19504357023393795, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19413002409376245, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19025891805937026, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20332974647565408, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19139697040253645, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20255136451779635, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21279937193861242, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20701208364183943, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1971383466896245, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1879225438630563, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 2.053035328388214, "validation/loss_best": 2.442652940750122, "validation/acc_best": 0.2753783684016242, "validation/f1_best": 0.20605826032000488} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.529835020303726, "train/grad": 0.15195697713643314, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128616943359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128524169921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1283203125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1281201171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12791015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127532958984375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1272119140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126851806640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12641845703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125948486328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1254150390625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.124554443359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1237060546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.122236328125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1202734375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.117227783203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.093800048828125, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.773038330078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6181993103027343, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.458607749938965, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.3469431304931643, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.2694180107116697, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.2204458141326904, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.1356070709228514, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.1012767648696897, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.0377815651893614, "train/loss_026_lr1.4e+00_wd1.0e+00": 1.9991411995887756, "train/loss_027_lr1.6e+00_wd1.0e+00": 1.9693003678321839, "train/loss_028_lr1.9e+00_wd1.0e+00": 1.9616346549987793, "train/loss_029_lr2.3e+00_wd1.0e+00": 1.9486444067955018, "train/loss_030_lr2.7e+00_wd1.0e+00": 1.9158911538124084, "train/loss_031_lr3.1e+00_wd1.0e+00": 1.9283861231803894, "train/loss_032_lr3.7e+00_wd1.0e+00": 1.9627056336402893, "train/loss_033_lr4.3e+00_wd1.0e+00": 1.9420169520378112, "train/loss_034_lr5.1e+00_wd1.0e+00": 1.8795013737678528, "train/loss_035_lr6.0e+00_wd1.0e+00": 1.8674814760684968, "train/loss_036_lr7.1e+00_wd1.0e+00": 1.8721972227096557, "train/loss_037_lr8.3e+00_wd1.0e+00": 1.9162963783740998, "train/loss_038_lr9.8e+00_wd1.0e+00": 1.8338489836454392, "train/loss_039_lr1.2e+01_wd1.0e+00": 1.7620383459329605, "train/loss_040_lr1.4e+01_wd1.0e+00": 1.7715281522274018, "train/loss_041_lr1.6e+01_wd1.0e+00": 1.756230082511902, "train/loss_042_lr1.9e+01_wd1.0e+00": 1.8136548435688018, "train/loss_043_lr2.2e+01_wd1.0e+00": 1.9380599808692933, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008939589124638587, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008936620692256838, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008929098192602396, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008921350627206266, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008913251627236605, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008899476809892804, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008882948961108923, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00886153500759974, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008827625275589526, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008785851625725627, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008738570150453597, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008660885388962924, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00857863072771579, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008467940837144852, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008403512351214885, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008495637124869972, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01006069490686059, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01877082158345729, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022226781779900194, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024201574344187973, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02601498073898256, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026889088023453953, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02648035831749439, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02766534423455596, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.027511501759290694, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02816152253188193, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.028630473595112563, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028889880562201143, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.029062839737161995, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.028574162740260364, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02900082865729928, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.029331339886412025, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02903010429814458, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.029268908835947512, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.029817665498703717, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.030046881837770344, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.029820817755535245, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02973332946188748, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.030559415435418485, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.0307333068177104, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030646579088643194, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.030816260417923333, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03074835205450654, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028843571338802575, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1235580444335938, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1234982013702393, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234278678894043, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.123305082321167, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232032775878906, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.123070240020752, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.122925043106079, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1227660179138184, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1225626468658447, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1223201751708984, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1220836639404297, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1216790676116943, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.121224880218506, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1203184127807617, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.118946075439453, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.116284132003784, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.092231512069702, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.7499563694000244, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6490914821624756, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5302131175994873, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.4832746982574463, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.4626288414001465, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.4248321056365967, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.433669090270996, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.421489953994751, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4419186115264893, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.448690891265869, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4629950523376465, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4792895317077637, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4780802726745605, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4802651405334473, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.507025957107544, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5125958919525146, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.554271697998047, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5567657947540283, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5741569995880127, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.593590259552002, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5602807998657227, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.611790180206299, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.599656343460083, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.566110610961914, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.578388214111328, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.587623119354248, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.5607762336730957, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.08361018826135105, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.16795865633074936, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.20062753783684018, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2425249169435216, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.25101513473606496, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.26098191214470284, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2724252491694352, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.26947212993724623, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.27593207825765964, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.271686969361388, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.27113325950535255, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2663344407530454, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.260797342192691, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.24953857511997046, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24861572535991142, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24344776670358065, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2547065337763012, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26116648209671467, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25230712440014763, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25212255444813586, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.23938722775932078, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004935162672224152, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005551495260946708, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005735097114155815, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005843559243174759, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006233738133134984, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006875458928777954, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007958855344148747, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007926724458790967, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008402729528122538, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008561067317050905, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.020209267984869224, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.08202444580758847, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.11937049747940477, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.16637772210427804, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1814996809684487, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.19286585089409414, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.2023858239616186, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.20302394173979854, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.20931114368656611, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.2035060902830328, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.2103760243026538, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.20658749403311516, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.2069814298851068, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.2097666271858041, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.21095374190684635, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20376608651466113, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19935832649222848, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19584159783385605, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1973342185417081, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19922935111997717, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19148996627192058, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20274131736535575, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1932010677247584, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20285789218040332, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21276353863215314, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2072874460802839, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20232002865723672, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18695338164196607, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 24, "lr_best": 0.0003, "wd_best": 0.05, "train/loss_best": 2.1012767648696897, "validation/loss_best": 2.421489953994751, "validation/acc_best": 0.27593207825765964, "validation/f1_best": 0.20931114368656611} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/config.yaml b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7998926139da70ed6a9bc71c17958d3a56c3edaa --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..99c64d46502fb7ca90eccb7e24180842f3f0cf3d --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 17, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 3.0587871074676514, "eval/train/acc": 0.10418267309997234, "eval/train/acc_std": 0.0013816007361252905, "eval/train/f1": 0.041624863461506734, "eval/train/f1_std": 0.0008255211864355043, "eval/validation/loss": 3.084916591644287, "eval/validation/acc": 0.09449981543004798, "eval/validation/acc_std": 0.003243145196719641, "eval/validation/f1": 0.038688258007162094, "eval/validation/f1_std": 0.0017939023910818863, "eval/test/loss": 3.091268539428711, "eval/test/acc": 0.09128014842300557, "eval/test/acc_std": 0.003189866873452152, "eval/test/f1": 0.03319201579501841, "eval/test/f1_std": 0.0017517972253926232, "eval/testid/loss": 3.094123601913452, "eval/testid/acc": 0.09196067090803933, "eval/testid/acc_std": 0.0035887716615775832, "eval/testid/f1": 0.034371303432593626, "eval/testid/f1_std": 0.0019058672218581478} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..c86476de846b6c49e61d6c3ca58f3569d74d2489 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 17, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 3.0587871074676514, "eval/best/train/acc": 0.10418267309997234, "eval/best/train/acc_std": 0.0013816007361252905, "eval/best/train/f1": 0.041624863461506734, "eval/best/train/f1_std": 0.0008255211864355043, "eval/best/validation/loss": 3.084916591644287, "eval/best/validation/acc": 0.09449981543004798, "eval/best/validation/acc_std": 0.003243145196719641, "eval/best/validation/f1": 0.038688258007162094, "eval/best/validation/f1_std": 0.0017939023910818863, "eval/best/test/loss": 3.091268539428711, "eval/best/test/acc": 0.09128014842300557, "eval/best/test/acc_std": 0.003189866873452152, "eval/best/test/f1": 0.03319201579501841, "eval/best/test/f1_std": 0.0017517972253926232, "eval/best/testid/loss": 3.094123601913452, "eval/best/testid/acc": 0.09196067090803933, "eval/best/testid/acc_std": 0.0035887716615775832, "eval/best/testid/f1": 0.034371303432593626, "eval/best/testid/f1_std": 0.0019058672218581478} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..cc35fe215420dbf788d83763929bb1485e869dc0 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 47, "eval/last/lr_best": 0.012899999999999998, "eval/last/wd_best": 0.05, "eval/last/train/loss": 3.055461883544922, "eval/last/train/acc": 0.10814714650112173, "eval/last/train/acc_std": 0.0013147080968552464, "eval/last/train/f1": 0.0471382439654069, "eval/last/train/f1_std": 0.0009303680560626303, "eval/last/validation/loss": 3.0805742740631104, "eval/last/validation/acc": 0.08767072720561092, "eval/last/validation/acc_std": 0.002844772209684542, "eval/last/validation/f1": 0.03599413693633031, "eval/last/validation/f1_std": 0.001889970317073207, "eval/last/test/loss": 3.0902934074401855, "eval/last/test/acc": 0.08515769944341373, "eval/last/test/acc_std": 0.00289476623504984, "eval/last/test/f1": 0.030858388747383336, "eval/last/test/f1_std": 0.0018732931262585718, "eval/last/testid/loss": 3.09000563621521, "eval/last/testid/acc": 0.09022556390977443, "eval/last/testid/acc_std": 0.0035097684473339805, "eval/last/testid/f1": 0.036234535320989684, "eval/last/testid/f1_std": 0.002079404247308496} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..03c41fd63798021e2e07c6991c2670a6f2fdc9aa --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",train,3.0587871074676514,0.10418267309997234,0.0013816007361252905,0.041624863461506734,0.0008255211864355043 +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",validation,3.084916591644287,0.09449981543004798,0.003243145196719641,0.038688258007162094,0.0017939023910818863 +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",test,3.091268539428711,0.09128014842300557,0.003189866873452152,0.03319201579501841,0.0017517972253926232 +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",testid,3.094123601913452,0.09196067090803933,0.0035887716615775832,0.034371303432593626,0.0019058672218581478 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..03c41fd63798021e2e07c6991c2670a6f2fdc9aa --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",train,3.0587871074676514,0.10418267309997234,0.0013816007361252905,0.041624863461506734,0.0008255211864355043 +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",validation,3.084916591644287,0.09449981543004798,0.003243145196719641,0.038688258007162094,0.0017939023910818863 +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",test,3.091268539428711,0.09128014842300557,0.003189866873452152,0.03319201579501841,0.0017517972253926232 +flat_mae,patch,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",testid,3.094123601913452,0.09196067090803933,0.0035887716615775832,0.034371303432593626,0.0019058672218581478 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..9a90494de060262250f23c98df54a89a7d465bd3 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",train,3.055461883544922,0.10814714650112173,0.0013147080968552464,0.0471382439654069,0.0009303680560626303 +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",validation,3.0805742740631104,0.08767072720561092,0.002844772209684542,0.03599413693633031,0.001889970317073207 +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",test,3.0902934074401855,0.08515769944341373,0.00289476623504984,0.030858388747383336,0.0018732931262585718 +flat_mae,patch,linear,nsd_cococlip,last,19,0.012899999999999998,0.05,47,"[43, 1.0]",testid,3.09000563621521,0.09022556390977443,0.0035097684473339805,0.036234535320989684,0.002079404247308496 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/log.txt b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c21cc0cb8cdd4277b9a2073bc41acc6776e45fe8 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/log.txt @@ -0,0 +1,958 @@ +fMRI foundation model probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 23:06:15 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip patch linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear +model: flat_mae +representation: patch +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (patch): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:24 lr: nan time: 3.6603 data: 3.2954 max mem: 3929 +train: [0] [ 20/400] eta: 0:03:16 lr: 0.000003 loss: 3.1803 (3.1808) grad: 0.0831 (0.0853) time: 0.3587 data: 0.0040 max mem: 3972 +train: [0] [ 40/400] eta: 0:02:32 lr: 0.000006 loss: 3.1803 (3.1818) grad: 0.0867 (0.0880) time: 0.3253 data: 0.0038 max mem: 3972 +train: [0] [ 60/400] eta: 0:02:15 lr: 0.000009 loss: 3.1785 (3.1800) grad: 0.0867 (0.0878) time: 0.3458 data: 0.0041 max mem: 3972 +train: [0] [ 80/400] eta: 0:02:03 lr: 0.000012 loss: 3.1778 (3.1798) grad: 0.0859 (0.0868) time: 0.3440 data: 0.0041 max mem: 3972 +train: [0] [100/400] eta: 0:01:53 lr: 0.000015 loss: 3.1773 (3.1783) grad: 0.0841 (0.0864) time: 0.3490 data: 0.0041 max mem: 3972 +train: [0] [120/400] eta: 0:01:44 lr: 0.000018 loss: 3.1655 (3.1751) grad: 0.0863 (0.0865) time: 0.3449 data: 0.0042 max mem: 3972 +train: [0] [140/400] eta: 0:01:35 lr: 0.000021 loss: 3.1620 (3.1735) grad: 0.0835 (0.0858) time: 0.3415 data: 0.0041 max mem: 3972 +train: [0] [160/400] eta: 0:01:27 lr: 0.000024 loss: 3.1614 (3.1715) grad: 0.0791 (0.0846) time: 0.3529 data: 0.0042 max mem: 3972 +train: [0] [180/400] eta: 0:01:20 lr: 0.000027 loss: 3.1497 (3.1690) grad: 0.0804 (0.0843) time: 0.3506 data: 0.0041 max mem: 3972 +train: [0] [200/400] eta: 0:01:13 lr: 0.000030 loss: 3.1475 (3.1671) grad: 0.0835 (0.0844) time: 0.3772 data: 0.0040 max mem: 3972 +train: [0] [220/400] eta: 0:01:05 lr: 0.000033 loss: 3.1555 (3.1665) grad: 0.0843 (0.0840) time: 0.3678 data: 0.0043 max mem: 3972 +train: [0] [240/400] eta: 0:00:59 lr: 0.000036 loss: 3.1576 (3.1655) grad: 0.0802 (0.0840) time: 0.4082 data: 0.0044 max mem: 3972 +train: [0] [260/400] eta: 0:00:51 lr: 0.000039 loss: 3.1550 (3.1648) grad: 0.0804 (0.0835) time: 0.3801 data: 0.0044 max mem: 3972 +train: [0] [280/400] eta: 0:00:44 lr: 0.000042 loss: 3.1511 (3.1641) grad: 0.0777 (0.0832) time: 0.3799 data: 0.0043 max mem: 3972 +train: [0] [300/400] eta: 0:00:37 lr: 0.000045 loss: 3.1573 (3.1632) grad: 0.0765 (0.0829) time: 0.3688 data: 0.0042 max mem: 3972 +train: [0] [320/400] eta: 0:00:29 lr: 0.000048 loss: 3.1541 (3.1625) grad: 0.0755 (0.0826) time: 0.3714 data: 0.0043 max mem: 3972 +train: [0] [340/400] eta: 0:00:22 lr: 0.000051 loss: 3.1560 (3.1624) grad: 0.0775 (0.0824) time: 0.3742 data: 0.0043 max mem: 3972 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 3.1602 (3.1620) grad: 0.0779 (0.0824) time: 0.3623 data: 0.0042 max mem: 3972 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 3.1527 (3.1621) grad: 0.0744 (0.0818) time: 0.3636 data: 0.0042 max mem: 3972 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1516 (3.1614) grad: 0.0756 (0.0817) time: 0.3921 data: 0.0042 max mem: 3972 +train: [0] Total time: 0:02:28 (0.3714 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1516 (3.1614) grad: 0.0756 (0.0817) +eval (validation): [0] [ 0/85] eta: 0:05:04 time: 3.5853 data: 3.3444 max mem: 3972 +eval (validation): [0] [20/85] eta: 0:00:33 time: 0.3682 data: 0.0045 max mem: 3972 +eval (validation): [0] [40/85] eta: 0:00:20 time: 0.3668 data: 0.0039 max mem: 3972 +eval (validation): [0] [60/85] eta: 0:00:10 time: 0.3564 data: 0.0045 max mem: 3972 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3342 data: 0.0039 max mem: 3972 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3274 data: 0.0039 max mem: 3972 +eval (validation): [0] Total time: 0:00:33 (0.3959 s / it) +cv: [0] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.138 acc: 0.067 f1: 0.013 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:24:45 lr: nan time: 3.7131 data: 3.4199 max mem: 3972 +train: [1] [ 20/400] eta: 0:03:16 lr: 0.000063 loss: 3.1555 (3.1555) grad: 0.0791 (0.0783) time: 0.3577 data: 0.0041 max mem: 3972 +train: [1] [ 40/400] eta: 0:02:37 lr: 0.000066 loss: 3.1495 (3.1533) grad: 0.0805 (0.0798) time: 0.3522 data: 0.0040 max mem: 3972 +train: [1] [ 60/400] eta: 0:02:23 lr: 0.000069 loss: 3.1444 (3.1477) grad: 0.0801 (0.0781) time: 0.3944 data: 0.0039 max mem: 3972 +train: [1] [ 80/400] eta: 0:02:13 lr: 0.000072 loss: 3.1499 (3.1481) grad: 0.0739 (0.0781) time: 0.3946 data: 0.0043 max mem: 3972 +train: [1] [100/400] eta: 0:02:02 lr: 0.000075 loss: 3.1499 (3.1473) grad: 0.0785 (0.0784) time: 0.3758 data: 0.0043 max mem: 3972 +train: [1] [120/400] eta: 0:01:52 lr: 0.000078 loss: 3.1454 (3.1471) grad: 0.0805 (0.0790) time: 0.3788 data: 0.0043 max mem: 3972 +train: [1] [140/400] eta: 0:01:44 lr: 0.000081 loss: 3.1460 (3.1463) grad: 0.0779 (0.0792) time: 0.3817 data: 0.0041 max mem: 3972 +train: [1] [160/400] eta: 0:01:35 lr: 0.000084 loss: 3.1484 (3.1482) grad: 0.0765 (0.0787) time: 0.3674 data: 0.0042 max mem: 3972 +train: [1] [180/400] eta: 0:01:25 lr: 0.000087 loss: 3.1437 (3.1471) grad: 0.0792 (0.0790) time: 0.3471 data: 0.0041 max mem: 3972 +train: [1] [200/400] eta: 0:01:17 lr: 0.000090 loss: 3.1404 (3.1481) grad: 0.0831 (0.0793) time: 0.3669 data: 0.0043 max mem: 3972 +train: [1] [220/400] eta: 0:01:09 lr: 0.000093 loss: 3.1435 (3.1481) grad: 0.0814 (0.0793) time: 0.3572 data: 0.0040 max mem: 3972 +train: [1] [240/400] eta: 0:01:01 lr: 0.000096 loss: 3.1481 (3.1476) grad: 0.0753 (0.0793) time: 0.3525 data: 0.0041 max mem: 3972 +train: [1] [260/400] eta: 0:00:53 lr: 0.000099 loss: 3.1460 (3.1479) grad: 0.0736 (0.0790) time: 0.3764 data: 0.0044 max mem: 3972 +train: [1] [280/400] eta: 0:00:45 lr: 0.000102 loss: 3.1375 (3.1473) grad: 0.0718 (0.0787) time: 0.3530 data: 0.0041 max mem: 3972 +train: [1] [300/400] eta: 0:00:37 lr: 0.000105 loss: 3.1474 (3.1478) grad: 0.0756 (0.0786) time: 0.3741 data: 0.0042 max mem: 3972 +train: [1] [320/400] eta: 0:00:30 lr: 0.000108 loss: 3.1346 (3.1475) grad: 0.0778 (0.0787) time: 0.3640 data: 0.0041 max mem: 3972 +train: [1] [340/400] eta: 0:00:22 lr: 0.000111 loss: 3.1447 (3.1486) grad: 0.0734 (0.0783) time: 0.3493 data: 0.0043 max mem: 3972 +train: [1] [360/400] eta: 0:00:15 lr: 0.000114 loss: 3.1498 (3.1479) grad: 0.0736 (0.0783) time: 0.3679 data: 0.0041 max mem: 3972 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 3.1431 (3.1475) grad: 0.0763 (0.0784) time: 0.3770 data: 0.0042 max mem: 3972 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.1499 (3.1485) grad: 0.0763 (0.0783) time: 0.3644 data: 0.0042 max mem: 3972 +train: [1] Total time: 0:02:30 (0.3762 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.1499 (3.1485) grad: 0.0763 (0.0783) +eval (validation): [1] [ 0/85] eta: 0:05:12 time: 3.6764 data: 3.3913 max mem: 3972 +eval (validation): [1] [20/85] eta: 0:00:36 time: 0.4097 data: 0.0052 max mem: 3972 +eval (validation): [1] [40/85] eta: 0:00:20 time: 0.3562 data: 0.0042 max mem: 3972 +eval (validation): [1] [60/85] eta: 0:00:10 time: 0.3314 data: 0.0042 max mem: 3972 +eval (validation): [1] [80/85] eta: 0:00:02 time: 0.3560 data: 0.0043 max mem: 3972 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3486 data: 0.0042 max mem: 3972 +eval (validation): [1] Total time: 0:00:34 (0.4041 s / it) +cv: [1] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 3.133 acc: 0.066 f1: 0.016 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [2] [ 0/400] eta: 0:23:31 lr: nan time: 3.5281 data: 3.2835 max mem: 3972 +train: [2] [ 20/400] eta: 0:03:10 lr: 0.000123 loss: 3.1550 (3.1572) grad: 0.0753 (0.0787) time: 0.3510 data: 0.0051 max mem: 3972 +train: [2] [ 40/400] eta: 0:02:35 lr: 0.000126 loss: 3.1480 (3.1483) grad: 0.0787 (0.0798) time: 0.3582 data: 0.0041 max mem: 3972 +train: [2] [ 60/400] eta: 0:02:19 lr: 0.000129 loss: 3.1399 (3.1491) grad: 0.0839 (0.0817) time: 0.3615 data: 0.0036 max mem: 3972 +train: [2] [ 80/400] eta: 0:02:07 lr: 0.000132 loss: 3.1535 (3.1504) grad: 0.0816 (0.0809) time: 0.3704 data: 0.0043 max mem: 3972 +train: [2] [100/400] eta: 0:01:56 lr: 0.000135 loss: 3.1412 (3.1495) grad: 0.0776 (0.0807) time: 0.3491 data: 0.0039 max mem: 3972 +train: [2] [120/400] eta: 0:01:47 lr: 0.000138 loss: 3.1307 (3.1462) grad: 0.0749 (0.0793) time: 0.3650 data: 0.0040 max mem: 3972 +train: [2] [140/400] eta: 0:01:39 lr: 0.000141 loss: 3.1404 (3.1470) grad: 0.0733 (0.0787) time: 0.3738 data: 0.0042 max mem: 3972 +train: [2] [160/400] eta: 0:01:31 lr: 0.000144 loss: 3.1456 (3.1456) grad: 0.0734 (0.0783) time: 0.3485 data: 0.0043 max mem: 3972 +train: [2] [180/400] eta: 0:01:23 lr: 0.000147 loss: 3.1332 (3.1442) grad: 0.0726 (0.0778) time: 0.3784 data: 0.0040 max mem: 3972 +train: [2] [200/400] eta: 0:01:15 lr: 0.000150 loss: 3.1332 (3.1431) grad: 0.0744 (0.0777) time: 0.3611 data: 0.0042 max mem: 3972 +train: [2] [220/400] eta: 0:01:07 lr: 0.000153 loss: 3.1279 (3.1423) grad: 0.0727 (0.0772) time: 0.3587 data: 0.0045 max mem: 3972 +train: [2] [240/400] eta: 0:00:59 lr: 0.000156 loss: 3.1327 (3.1414) grad: 0.0750 (0.0773) time: 0.3597 data: 0.0042 max mem: 3972 +train: [2] [260/400] eta: 0:00:52 lr: 0.000159 loss: 3.1255 (3.1406) grad: 0.0751 (0.0771) time: 0.3561 data: 0.0041 max mem: 3972 +train: [2] [280/400] eta: 0:00:44 lr: 0.000162 loss: 3.1255 (3.1408) grad: 0.0746 (0.0773) time: 0.3742 data: 0.0041 max mem: 3972 +train: [2] [300/400] eta: 0:00:37 lr: 0.000165 loss: 3.1364 (3.1402) grad: 0.0730 (0.0772) time: 0.3671 data: 0.0042 max mem: 3972 +train: [2] [320/400] eta: 0:00:29 lr: 0.000168 loss: 3.1364 (3.1403) grad: 0.0748 (0.0771) time: 0.3549 data: 0.0042 max mem: 3972 +train: [2] [340/400] eta: 0:00:22 lr: 0.000171 loss: 3.1432 (3.1404) grad: 0.0748 (0.0771) time: 0.3465 data: 0.0042 max mem: 3972 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 3.1424 (3.1407) grad: 0.0751 (0.0772) time: 0.3631 data: 0.0043 max mem: 3972 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 3.1381 (3.1404) grad: 0.0728 (0.0771) time: 0.3683 data: 0.0043 max mem: 3972 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.1348 (3.1403) grad: 0.0728 (0.0771) time: 0.3651 data: 0.0041 max mem: 3972 +train: [2] Total time: 0:02:27 (0.3698 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.1348 (3.1403) grad: 0.0728 (0.0771) +eval (validation): [2] [ 0/85] eta: 0:05:08 time: 3.6328 data: 3.3982 max mem: 3972 +eval (validation): [2] [20/85] eta: 0:00:34 time: 0.3694 data: 0.0051 max mem: 3972 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3475 data: 0.0040 max mem: 3972 +eval (validation): [2] [60/85] eta: 0:00:10 time: 0.3505 data: 0.0044 max mem: 3972 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3486 data: 0.0043 max mem: 3972 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3344 data: 0.0042 max mem: 3972 +eval (validation): [2] Total time: 0:00:33 (0.3948 s / it) +cv: [2] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 3.141 acc: 0.070 f1: 0.016 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:25:57 lr: nan time: 3.8944 data: 3.6325 max mem: 3972 +train: [3] [ 20/400] eta: 0:03:29 lr: 0.000183 loss: 3.1271 (3.1399) grad: 0.0735 (0.0745) time: 0.3851 data: 0.0040 max mem: 3972 +train: [3] [ 40/400] eta: 0:02:46 lr: 0.000186 loss: 3.1322 (3.1405) grad: 0.0763 (0.0771) time: 0.3663 data: 0.0040 max mem: 3972 +train: [3] [ 60/400] eta: 0:02:27 lr: 0.000189 loss: 3.1335 (3.1348) grad: 0.0764 (0.0770) time: 0.3743 data: 0.0041 max mem: 3972 +train: [3] [ 80/400] eta: 0:02:13 lr: 0.000192 loss: 3.1375 (3.1362) grad: 0.0764 (0.0773) time: 0.3699 data: 0.0040 max mem: 3972 +train: [3] [100/400] eta: 0:02:02 lr: 0.000195 loss: 3.1471 (3.1403) grad: 0.0789 (0.0780) time: 0.3695 data: 0.0041 max mem: 3972 +train: [3] [120/400] eta: 0:01:53 lr: 0.000198 loss: 3.1409 (3.1394) grad: 0.0830 (0.0787) time: 0.4012 data: 0.0041 max mem: 3972 +train: [3] [140/400] eta: 0:01:45 lr: 0.000201 loss: 3.1320 (3.1381) grad: 0.0819 (0.0795) time: 0.3927 data: 0.0047 max mem: 3972 +train: [3] [160/400] eta: 0:01:35 lr: 0.000204 loss: 3.1283 (3.1382) grad: 0.0790 (0.0792) time: 0.3610 data: 0.0041 max mem: 3972 +train: [3] [180/400] eta: 0:01:27 lr: 0.000207 loss: 3.1295 (3.1397) grad: 0.0722 (0.0789) time: 0.3751 data: 0.0041 max mem: 3972 +train: [3] [200/400] eta: 0:01:18 lr: 0.000210 loss: 3.1512 (3.1430) grad: 0.0736 (0.0785) time: 0.3638 data: 0.0044 max mem: 3972 +train: [3] [220/400] eta: 0:01:10 lr: 0.000213 loss: 3.1387 (3.1426) grad: 0.0736 (0.0783) time: 0.3563 data: 0.0042 max mem: 3972 +train: [3] [240/400] eta: 0:01:01 lr: 0.000216 loss: 3.1190 (3.1402) grad: 0.0734 (0.0780) time: 0.3490 data: 0.0042 max mem: 3972 +train: [3] [260/400] eta: 0:00:53 lr: 0.000219 loss: 3.1210 (3.1406) grad: 0.0747 (0.0780) time: 0.3529 data: 0.0041 max mem: 3972 +train: [3] [280/400] eta: 0:00:45 lr: 0.000222 loss: 3.1342 (3.1405) grad: 0.0736 (0.0774) time: 0.3643 data: 0.0042 max mem: 3972 +train: [3] [300/400] eta: 0:00:38 lr: 0.000225 loss: 3.1360 (3.1402) grad: 0.0682 (0.0771) time: 0.3614 data: 0.0041 max mem: 3972 +train: [3] [320/400] eta: 0:00:30 lr: 0.000228 loss: 3.1466 (3.1406) grad: 0.0696 (0.0769) time: 0.3453 data: 0.0040 max mem: 3972 +train: [3] [340/400] eta: 0:00:22 lr: 0.000231 loss: 3.1466 (3.1398) grad: 0.0727 (0.0768) time: 0.3645 data: 0.0042 max mem: 3972 +train: [3] [360/400] eta: 0:00:15 lr: 0.000234 loss: 3.1326 (3.1393) grad: 0.0729 (0.0766) time: 0.3580 data: 0.0042 max mem: 3972 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 3.1270 (3.1388) grad: 0.0729 (0.0765) time: 0.3506 data: 0.0042 max mem: 3972 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.1438 (3.1389) grad: 0.0727 (0.0764) time: 0.3658 data: 0.0043 max mem: 3972 +train: [3] Total time: 0:02:30 (0.3755 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.1438 (3.1389) grad: 0.0727 (0.0764) +eval (validation): [3] [ 0/85] eta: 0:05:00 time: 3.5402 data: 3.3075 max mem: 3972 +eval (validation): [3] [20/85] eta: 0:00:33 time: 0.3598 data: 0.0050 max mem: 3972 +eval (validation): [3] [40/85] eta: 0:00:19 time: 0.3403 data: 0.0034 max mem: 3972 +eval (validation): [3] [60/85] eta: 0:00:10 time: 0.3600 data: 0.0046 max mem: 3972 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3457 data: 0.0042 max mem: 3972 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3270 data: 0.0040 max mem: 3972 +eval (validation): [3] Total time: 0:00:33 (0.3902 s / it) +cv: [3] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.143 acc: 0.070 f1: 0.020 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:36 lr: nan time: 3.3901 data: 3.1647 max mem: 3972 +train: [4] [ 20/400] eta: 0:03:15 lr: 0.000243 loss: 3.1509 (3.1431) grad: 0.0728 (0.0736) time: 0.3720 data: 0.0049 max mem: 3972 +train: [4] [ 40/400] eta: 0:02:37 lr: 0.000246 loss: 3.1509 (3.1455) grad: 0.0690 (0.0708) time: 0.3540 data: 0.0035 max mem: 3972 +train: [4] [ 60/400] eta: 0:02:20 lr: 0.000249 loss: 3.1443 (3.1441) grad: 0.0690 (0.0717) time: 0.3644 data: 0.0043 max mem: 3972 +train: [4] [ 80/400] eta: 0:02:08 lr: 0.000252 loss: 3.1230 (3.1394) grad: 0.0727 (0.0729) time: 0.3722 data: 0.0042 max mem: 3972 +train: [4] [100/400] eta: 0:01:58 lr: 0.000255 loss: 3.1378 (3.1414) grad: 0.0752 (0.0736) time: 0.3687 data: 0.0042 max mem: 3972 +train: [4] [120/400] eta: 0:01:49 lr: 0.000258 loss: 3.1517 (3.1432) grad: 0.0761 (0.0741) time: 0.3686 data: 0.0043 max mem: 3972 +train: [4] [140/400] eta: 0:01:40 lr: 0.000261 loss: 3.1517 (3.1430) grad: 0.0787 (0.0756) time: 0.3604 data: 0.0043 max mem: 3972 +train: [4] [160/400] eta: 0:01:33 lr: 0.000264 loss: 3.1355 (3.1433) grad: 0.0761 (0.0752) time: 0.3925 data: 0.0045 max mem: 3972 +train: [4] [180/400] eta: 0:01:25 lr: 0.000267 loss: 3.1355 (3.1418) grad: 0.0720 (0.0749) time: 0.3846 data: 0.0044 max mem: 3972 +train: [4] [200/400] eta: 0:01:17 lr: 0.000270 loss: 3.1396 (3.1425) grad: 0.0759 (0.0755) time: 0.3781 data: 0.0044 max mem: 3972 +train: [4] [220/400] eta: 0:01:09 lr: 0.000273 loss: 3.1588 (3.1434) grad: 0.0768 (0.0757) time: 0.3576 data: 0.0043 max mem: 3972 +train: [4] [240/400] eta: 0:01:01 lr: 0.000276 loss: 3.1542 (3.1433) grad: 0.0787 (0.0760) time: 0.3613 data: 0.0041 max mem: 3972 +train: [4] [260/400] eta: 0:00:53 lr: 0.000279 loss: 3.1205 (3.1414) grad: 0.0780 (0.0763) time: 0.3685 data: 0.0041 max mem: 3972 +train: [4] [280/400] eta: 0:00:45 lr: 0.000282 loss: 3.1210 (3.1413) grad: 0.0775 (0.0768) time: 0.3724 data: 0.0040 max mem: 3972 +train: [4] [300/400] eta: 0:00:37 lr: 0.000285 loss: 3.1391 (3.1407) grad: 0.0764 (0.0768) time: 0.3736 data: 0.0041 max mem: 3972 +train: [4] [320/400] eta: 0:00:30 lr: 0.000288 loss: 3.1419 (3.1415) grad: 0.0741 (0.0769) time: 0.3539 data: 0.0041 max mem: 3972 +train: [4] [340/400] eta: 0:00:22 lr: 0.000291 loss: 3.1614 (3.1416) grad: 0.0768 (0.0771) time: 0.3754 data: 0.0045 max mem: 3972 +train: [4] [360/400] eta: 0:00:15 lr: 0.000294 loss: 3.1438 (3.1414) grad: 0.0762 (0.0771) time: 0.3578 data: 0.0041 max mem: 3972 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1410 (3.1412) grad: 0.0762 (0.0771) time: 0.3651 data: 0.0042 max mem: 3972 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.1280 (3.1410) grad: 0.0753 (0.0769) time: 0.3717 data: 0.0041 max mem: 3972 +train: [4] Total time: 0:02:30 (0.3763 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.1280 (3.1410) grad: 0.0753 (0.0769) +eval (validation): [4] [ 0/85] eta: 0:04:59 time: 3.5182 data: 3.2835 max mem: 3972 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3253 data: 0.0050 max mem: 3972 +eval (validation): [4] [40/85] eta: 0:00:19 time: 0.3764 data: 0.0037 max mem: 3972 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3504 data: 0.0046 max mem: 3972 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3406 data: 0.0041 max mem: 3972 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3235 data: 0.0038 max mem: 3972 +eval (validation): [4] Total time: 0:00:32 (0.3857 s / it) +cv: [4] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 3.136 acc: 0.075 f1: 0.011 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:58 lr: nan time: 3.4472 data: 3.1751 max mem: 3972 +train: [5] [ 20/400] eta: 0:03:30 lr: 0.000300 loss: 3.1385 (3.1361) grad: 0.0729 (0.0753) time: 0.4079 data: 0.0040 max mem: 3972 +train: [5] [ 40/400] eta: 0:02:45 lr: 0.000300 loss: 3.1300 (3.1265) grad: 0.0729 (0.0750) time: 0.3642 data: 0.0040 max mem: 3972 +train: [5] [ 60/400] eta: 0:02:26 lr: 0.000300 loss: 3.1325 (3.1317) grad: 0.0742 (0.0760) time: 0.3694 data: 0.0043 max mem: 3972 +train: [5] [ 80/400] eta: 0:02:13 lr: 0.000300 loss: 3.1386 (3.1349) grad: 0.0733 (0.0757) time: 0.3701 data: 0.0045 max mem: 3972 +train: [5] [100/400] eta: 0:02:01 lr: 0.000300 loss: 3.1438 (3.1379) grad: 0.0778 (0.0776) time: 0.3668 data: 0.0040 max mem: 3972 +train: [5] [120/400] eta: 0:01:50 lr: 0.000300 loss: 3.1442 (3.1385) grad: 0.0809 (0.0784) time: 0.3443 data: 0.0041 max mem: 3972 +train: [5] [140/400] eta: 0:01:41 lr: 0.000300 loss: 3.1348 (3.1385) grad: 0.0799 (0.0781) time: 0.3683 data: 0.0043 max mem: 3972 +train: [5] [160/400] eta: 0:01:33 lr: 0.000299 loss: 3.1348 (3.1381) grad: 0.0757 (0.0776) time: 0.3722 data: 0.0043 max mem: 3972 +train: [5] [180/400] eta: 0:01:25 lr: 0.000299 loss: 3.1195 (3.1354) grad: 0.0745 (0.0775) time: 0.3618 data: 0.0043 max mem: 3972 +train: [5] [200/400] eta: 0:01:17 lr: 0.000299 loss: 3.1195 (3.1349) grad: 0.0738 (0.0770) time: 0.3723 data: 0.0042 max mem: 3972 +train: [5] [220/400] eta: 0:01:09 lr: 0.000299 loss: 3.1413 (3.1370) grad: 0.0731 (0.0773) time: 0.3758 data: 0.0040 max mem: 3972 +train: [5] [240/400] eta: 0:01:01 lr: 0.000299 loss: 3.1561 (3.1375) grad: 0.0765 (0.0773) time: 0.3597 data: 0.0040 max mem: 3972 +train: [5] [260/400] eta: 0:00:53 lr: 0.000299 loss: 3.1534 (3.1390) grad: 0.0746 (0.0772) time: 0.3654 data: 0.0040 max mem: 3972 +train: [5] [280/400] eta: 0:00:45 lr: 0.000298 loss: 3.1489 (3.1391) grad: 0.0805 (0.0775) time: 0.3724 data: 0.0043 max mem: 3972 +train: [5] [300/400] eta: 0:00:37 lr: 0.000298 loss: 3.1390 (3.1390) grad: 0.0796 (0.0777) time: 0.3642 data: 0.0041 max mem: 3972 +train: [5] [320/400] eta: 0:00:30 lr: 0.000298 loss: 3.1321 (3.1390) grad: 0.0779 (0.0776) time: 0.3805 data: 0.0043 max mem: 3972 +train: [5] [340/400] eta: 0:00:22 lr: 0.000298 loss: 3.1321 (3.1388) grad: 0.0737 (0.0776) time: 0.3859 data: 0.0046 max mem: 3972 +train: [5] [360/400] eta: 0:00:15 lr: 0.000297 loss: 3.1369 (3.1388) grad: 0.0723 (0.0774) time: 0.3849 data: 0.0045 max mem: 3972 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1298 (3.1382) grad: 0.0735 (0.0773) time: 0.3911 data: 0.0044 max mem: 3972 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 3.1298 (3.1388) grad: 0.0734 (0.0772) time: 0.3847 data: 0.0042 max mem: 3972 +train: [5] Total time: 0:02:32 (0.3810 s / it) +train: [5] Summary: lr: 0.000297 loss: 3.1298 (3.1388) grad: 0.0734 (0.0772) +eval (validation): [5] [ 0/85] eta: 0:05:08 time: 3.6274 data: 3.4043 max mem: 3972 +eval (validation): [5] [20/85] eta: 0:00:33 time: 0.3570 data: 0.0045 max mem: 3972 +eval (validation): [5] [40/85] eta: 0:00:20 time: 0.3757 data: 0.0036 max mem: 3972 +eval (validation): [5] [60/85] eta: 0:00:10 time: 0.4177 data: 0.0047 max mem: 3972 +eval (validation): [5] [80/85] eta: 0:00:02 time: 0.3427 data: 0.0041 max mem: 3972 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3321 data: 0.0041 max mem: 3972 +eval (validation): [5] Total time: 0:00:35 (0.4129 s / it) +cv: [5] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 3.138 acc: 0.083 f1: 0.015 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:24:37 lr: nan time: 3.6946 data: 3.4379 max mem: 3972 +train: [6] [ 20/400] eta: 0:03:27 lr: 0.000296 loss: 3.1304 (3.1306) grad: 0.0711 (0.0692) time: 0.3893 data: 0.0044 max mem: 3972 +train: [6] [ 40/400] eta: 0:02:46 lr: 0.000296 loss: 3.1357 (3.1372) grad: 0.0718 (0.0730) time: 0.3714 data: 0.0042 max mem: 3972 +train: [6] [ 60/400] eta: 0:02:28 lr: 0.000296 loss: 3.1434 (3.1381) grad: 0.0766 (0.0741) time: 0.3855 data: 0.0043 max mem: 3972 +train: [6] [ 80/400] eta: 0:02:16 lr: 0.000295 loss: 3.1318 (3.1371) grad: 0.0741 (0.0747) time: 0.3912 data: 0.0042 max mem: 3972 +train: [6] [100/400] eta: 0:02:05 lr: 0.000295 loss: 3.1460 (3.1435) grad: 0.0738 (0.0740) time: 0.3900 data: 0.0043 max mem: 3972 +train: [6] [120/400] eta: 0:01:54 lr: 0.000295 loss: 3.1436 (3.1410) grad: 0.0736 (0.0742) time: 0.3624 data: 0.0039 max mem: 3972 +train: [6] [140/400] eta: 0:01:45 lr: 0.000294 loss: 3.1141 (3.1386) grad: 0.0759 (0.0746) time: 0.3850 data: 0.0043 max mem: 3972 +train: [6] [160/400] eta: 0:01:37 lr: 0.000294 loss: 3.1206 (3.1380) grad: 0.0783 (0.0755) time: 0.4051 data: 0.0043 max mem: 3972 +train: [6] [180/400] eta: 0:01:28 lr: 0.000293 loss: 3.1335 (3.1389) grad: 0.0797 (0.0760) time: 0.3940 data: 0.0044 max mem: 3972 +train: [6] [200/400] eta: 0:01:20 lr: 0.000293 loss: 3.1513 (3.1383) grad: 0.0721 (0.0755) time: 0.3937 data: 0.0042 max mem: 3972 +train: [6] [220/400] eta: 0:01:12 lr: 0.000292 loss: 3.1200 (3.1371) grad: 0.0713 (0.0757) time: 0.3775 data: 0.0042 max mem: 3972 +train: [6] [240/400] eta: 0:01:03 lr: 0.000292 loss: 3.1114 (3.1353) grad: 0.0732 (0.0755) time: 0.3892 data: 0.0041 max mem: 3972 +train: [6] [260/400] eta: 0:00:56 lr: 0.000291 loss: 3.1124 (3.1342) grad: 0.0732 (0.0754) time: 0.4096 data: 0.0044 max mem: 3972 +train: [6] [280/400] eta: 0:00:48 lr: 0.000291 loss: 3.1251 (3.1342) grad: 0.0772 (0.0758) time: 0.3991 data: 0.0046 max mem: 3972 +train: [6] [300/400] eta: 0:00:39 lr: 0.000290 loss: 3.1446 (3.1342) grad: 0.0780 (0.0756) time: 0.3919 data: 0.0043 max mem: 3972 +train: [6] [320/400] eta: 0:00:32 lr: 0.000290 loss: 3.1455 (3.1347) grad: 0.0727 (0.0756) time: 0.4106 data: 0.0042 max mem: 3972 +train: [6] [340/400] eta: 0:00:23 lr: 0.000289 loss: 3.1359 (3.1346) grad: 0.0792 (0.0757) time: 0.3826 data: 0.0044 max mem: 3972 +train: [6] [360/400] eta: 0:00:15 lr: 0.000288 loss: 3.1274 (3.1334) grad: 0.0757 (0.0756) time: 0.3898 data: 0.0040 max mem: 3972 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 3.1337 (3.1338) grad: 0.0757 (0.0758) time: 0.4035 data: 0.0042 max mem: 3972 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 3.1351 (3.1339) grad: 0.0769 (0.0758) time: 0.3922 data: 0.0043 max mem: 3972 +train: [6] Total time: 0:02:39 (0.3992 s / it) +train: [6] Summary: lr: 0.000287 loss: 3.1351 (3.1339) grad: 0.0769 (0.0758) +eval (validation): [6] [ 0/85] eta: 0:04:36 time: 3.2586 data: 2.9928 max mem: 3972 +eval (validation): [6] [20/85] eta: 0:00:33 time: 0.3717 data: 0.0046 max mem: 3972 +eval (validation): [6] [40/85] eta: 0:00:20 time: 0.3998 data: 0.0039 max mem: 3972 +eval (validation): [6] [60/85] eta: 0:00:10 time: 0.3605 data: 0.0045 max mem: 3972 +eval (validation): [6] [80/85] eta: 0:00:02 time: 0.3450 data: 0.0041 max mem: 3972 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3422 data: 0.0041 max mem: 3972 +eval (validation): [6] Total time: 0:00:34 (0.4058 s / it) +cv: [6] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.220 acc: 0.078 f1: 0.026 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:23:54 lr: nan time: 3.5872 data: 3.2844 max mem: 3972 +train: [7] [ 20/400] eta: 0:03:34 lr: 0.000286 loss: 3.1233 (3.1198) grad: 0.0775 (0.0770) time: 0.4138 data: 0.0055 max mem: 3972 +train: [7] [ 40/400] eta: 0:02:48 lr: 0.000286 loss: 3.1236 (3.1288) grad: 0.0769 (0.0764) time: 0.3682 data: 0.0036 max mem: 3972 +train: [7] [ 60/400] eta: 0:02:31 lr: 0.000285 loss: 3.1341 (3.1310) grad: 0.0750 (0.0754) time: 0.4004 data: 0.0042 max mem: 3972 +train: [7] [ 80/400] eta: 0:02:19 lr: 0.000284 loss: 3.1333 (3.1303) grad: 0.0751 (0.0766) time: 0.4083 data: 0.0041 max mem: 3972 +train: [7] [100/400] eta: 0:02:08 lr: 0.000284 loss: 3.1333 (3.1323) grad: 0.0737 (0.0759) time: 0.3914 data: 0.0042 max mem: 3972 +train: [7] [120/400] eta: 0:01:57 lr: 0.000283 loss: 3.1109 (3.1269) grad: 0.0708 (0.0752) time: 0.3819 data: 0.0040 max mem: 3972 +train: [7] [140/400] eta: 0:01:48 lr: 0.000282 loss: 3.0971 (3.1252) grad: 0.0708 (0.0757) time: 0.3926 data: 0.0042 max mem: 3972 +train: [7] [160/400] eta: 0:01:38 lr: 0.000282 loss: 3.1170 (3.1270) grad: 0.0812 (0.0764) time: 0.3771 data: 0.0043 max mem: 3972 +train: [7] [180/400] eta: 0:01:29 lr: 0.000281 loss: 3.1196 (3.1277) grad: 0.0740 (0.0759) time: 0.3700 data: 0.0043 max mem: 3972 +train: [7] [200/400] eta: 0:01:20 lr: 0.000280 loss: 3.1290 (3.1262) grad: 0.0699 (0.0757) time: 0.3723 data: 0.0039 max mem: 3972 +train: [7] [220/400] eta: 0:01:11 lr: 0.000279 loss: 3.1290 (3.1279) grad: 0.0716 (0.0759) time: 0.3498 data: 0.0041 max mem: 3972 +train: [7] [240/400] eta: 0:01:03 lr: 0.000278 loss: 3.1279 (3.1278) grad: 0.0799 (0.0763) time: 0.3658 data: 0.0041 max mem: 3972 +train: [7] [260/400] eta: 0:00:55 lr: 0.000278 loss: 3.1351 (3.1294) grad: 0.0824 (0.0766) time: 0.3735 data: 0.0039 max mem: 3972 +train: [7] [280/400] eta: 0:00:46 lr: 0.000277 loss: 3.1395 (3.1282) grad: 0.0812 (0.0767) time: 0.3502 data: 0.0043 max mem: 3972 +train: [7] [300/400] eta: 0:00:38 lr: 0.000276 loss: 3.1135 (3.1276) grad: 0.0735 (0.0764) time: 0.3695 data: 0.0042 max mem: 3972 +train: [7] [320/400] eta: 0:00:31 lr: 0.000275 loss: 3.1259 (3.1286) grad: 0.0754 (0.0764) time: 0.3773 data: 0.0043 max mem: 3972 +train: [7] [340/400] eta: 0:00:23 lr: 0.000274 loss: 3.1508 (3.1296) grad: 0.0774 (0.0765) time: 0.3619 data: 0.0043 max mem: 3972 +train: [7] [360/400] eta: 0:00:15 lr: 0.000273 loss: 3.1502 (3.1302) grad: 0.0753 (0.0765) time: 0.3811 data: 0.0041 max mem: 3972 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 3.1485 (3.1317) grad: 0.0747 (0.0765) time: 0.3821 data: 0.0042 max mem: 3972 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 3.1378 (3.1313) grad: 0.0760 (0.0767) time: 0.3640 data: 0.0039 max mem: 3972 +train: [7] Total time: 0:02:34 (0.3858 s / it) +train: [7] Summary: lr: 0.000271 loss: 3.1378 (3.1313) grad: 0.0760 (0.0767) +eval (validation): [7] [ 0/85] eta: 0:04:53 time: 3.4522 data: 3.2161 max mem: 3972 +eval (validation): [7] [20/85] eta: 0:00:36 time: 0.4232 data: 0.0196 max mem: 3972 +eval (validation): [7] [40/85] eta: 0:00:20 time: 0.3517 data: 0.0037 max mem: 3972 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3493 data: 0.0044 max mem: 3972 +eval (validation): [7] [80/85] eta: 0:00:02 time: 0.3422 data: 0.0041 max mem: 3972 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3334 data: 0.0040 max mem: 3972 +eval (validation): [7] Total time: 0:00:34 (0.4041 s / it) +cv: [7] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 3.142 acc: 0.078 f1: 0.017 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [8] [ 0/400] eta: 0:23:45 lr: nan time: 3.5646 data: 3.2728 max mem: 3972 +train: [8] [ 20/400] eta: 0:03:18 lr: 0.000270 loss: 3.1236 (3.1325) grad: 0.0693 (0.0695) time: 0.3709 data: 0.0045 max mem: 3972 +train: [8] [ 40/400] eta: 0:02:40 lr: 0.000270 loss: 3.1259 (3.1330) grad: 0.0727 (0.0763) time: 0.3675 data: 0.0040 max mem: 3972 +train: [8] [ 60/400] eta: 0:02:24 lr: 0.000269 loss: 3.1188 (3.1256) grad: 0.0781 (0.0772) time: 0.3798 data: 0.0041 max mem: 3972 +train: [8] [ 80/400] eta: 0:02:12 lr: 0.000268 loss: 3.1167 (3.1244) grad: 0.0797 (0.0783) time: 0.3783 data: 0.0040 max mem: 3972 +train: [8] [100/400] eta: 0:02:01 lr: 0.000267 loss: 3.1264 (3.1268) grad: 0.0761 (0.0774) time: 0.3629 data: 0.0044 max mem: 3972 +train: [8] [120/400] eta: 0:01:52 lr: 0.000266 loss: 3.1258 (3.1253) grad: 0.0707 (0.0769) time: 0.4032 data: 0.0044 max mem: 3972 +train: [8] [140/400] eta: 0:01:43 lr: 0.000265 loss: 3.1275 (3.1264) grad: 0.0728 (0.0767) time: 0.3777 data: 0.0044 max mem: 3972 +train: [8] [160/400] eta: 0:01:35 lr: 0.000264 loss: 3.1358 (3.1267) grad: 0.0792 (0.0772) time: 0.3772 data: 0.0044 max mem: 3972 +train: [8] [180/400] eta: 0:01:26 lr: 0.000263 loss: 3.1320 (3.1272) grad: 0.0804 (0.0772) time: 0.3648 data: 0.0043 max mem: 3972 +train: [8] [200/400] eta: 0:01:18 lr: 0.000262 loss: 3.1327 (3.1269) grad: 0.0788 (0.0772) time: 0.3739 data: 0.0042 max mem: 3972 +train: [8] [220/400] eta: 0:01:10 lr: 0.000260 loss: 3.1267 (3.1266) grad: 0.0784 (0.0773) time: 0.4015 data: 0.0042 max mem: 3972 +train: [8] [240/400] eta: 0:01:02 lr: 0.000259 loss: 3.1182 (3.1267) grad: 0.0725 (0.0768) time: 0.3869 data: 0.0042 max mem: 3972 +train: [8] [260/400] eta: 0:00:54 lr: 0.000258 loss: 3.1281 (3.1278) grad: 0.0768 (0.0776) time: 0.3903 data: 0.0041 max mem: 3972 +train: [8] [280/400] eta: 0:00:46 lr: 0.000257 loss: 3.1375 (3.1292) grad: 0.0774 (0.0773) time: 0.3699 data: 0.0042 max mem: 3972 +train: [8] [300/400] eta: 0:00:39 lr: 0.000256 loss: 3.1299 (3.1280) grad: 0.0778 (0.0775) time: 0.4056 data: 0.0041 max mem: 3972 +train: [8] [320/400] eta: 0:00:31 lr: 0.000255 loss: 3.1025 (3.1284) grad: 0.0784 (0.0773) time: 0.3931 data: 0.0042 max mem: 3972 +train: [8] [340/400] eta: 0:00:23 lr: 0.000254 loss: 3.1338 (3.1290) grad: 0.0769 (0.0773) time: 0.4287 data: 0.0041 max mem: 3972 +train: [8] [360/400] eta: 0:00:15 lr: 0.000253 loss: 3.1395 (3.1297) grad: 0.0766 (0.0774) time: 0.4103 data: 0.0043 max mem: 3972 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 3.1385 (3.1300) grad: 0.0757 (0.0773) time: 0.3707 data: 0.0038 max mem: 3972 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 3.1250 (3.1299) grad: 0.0744 (0.0772) time: 0.3704 data: 0.0041 max mem: 3972 +train: [8] Total time: 0:02:37 (0.3925 s / it) +train: [8] Summary: lr: 0.000250 loss: 3.1250 (3.1299) grad: 0.0744 (0.0772) +eval (validation): [8] [ 0/85] eta: 0:06:44 time: 4.7547 data: 4.4282 max mem: 3972 +eval (validation): [8] [20/85] eta: 0:00:40 time: 0.4124 data: 0.0033 max mem: 3972 +eval (validation): [8] [40/85] eta: 0:00:22 time: 0.3790 data: 0.0043 max mem: 3972 +eval (validation): [8] [60/85] eta: 0:00:11 time: 0.3581 data: 0.0042 max mem: 3972 +eval (validation): [8] [80/85] eta: 0:00:02 time: 0.3809 data: 0.0045 max mem: 3972 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3672 data: 0.0045 max mem: 3972 +eval (validation): [8] Total time: 0:00:37 (0.4366 s / it) +cv: [8] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 3.134 acc: 0.080 f1: 0.024 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [9] [ 0/400] eta: 0:24:26 lr: nan time: 3.6670 data: 3.4321 max mem: 3972 +train: [9] [ 20/400] eta: 0:03:33 lr: 0.000249 loss: 3.0878 (3.1148) grad: 0.0763 (0.0791) time: 0.4054 data: 0.0178 max mem: 3972 +train: [9] [ 40/400] eta: 0:02:54 lr: 0.000248 loss: 3.1148 (3.1147) grad: 0.0767 (0.0772) time: 0.4038 data: 0.0040 max mem: 3972 +train: [9] [ 60/400] eta: 0:02:33 lr: 0.000247 loss: 3.1168 (3.1200) grad: 0.0762 (0.0764) time: 0.3852 data: 0.0041 max mem: 3972 +train: [9] [ 80/400] eta: 0:02:18 lr: 0.000246 loss: 3.1263 (3.1223) grad: 0.0731 (0.0756) time: 0.3740 data: 0.0043 max mem: 3972 +train: [9] [100/400] eta: 0:02:07 lr: 0.000244 loss: 3.1233 (3.1215) grad: 0.0731 (0.0756) time: 0.3940 data: 0.0043 max mem: 3972 +train: [9] [120/400] eta: 0:01:57 lr: 0.000243 loss: 3.1199 (3.1224) grad: 0.0687 (0.0747) time: 0.3856 data: 0.0044 max mem: 3972 +train: [9] [140/400] eta: 0:01:47 lr: 0.000242 loss: 3.1319 (3.1229) grad: 0.0695 (0.0743) time: 0.3769 data: 0.0042 max mem: 3972 +train: [9] [160/400] eta: 0:01:38 lr: 0.000241 loss: 3.1127 (3.1214) grad: 0.0718 (0.0743) time: 0.3831 data: 0.0042 max mem: 3972 +train: [9] [180/400] eta: 0:01:30 lr: 0.000240 loss: 3.1023 (3.1213) grad: 0.0768 (0.0750) time: 0.4212 data: 0.0040 max mem: 3972 +train: [9] [200/400] eta: 0:01:21 lr: 0.000238 loss: 3.1168 (3.1238) grad: 0.0797 (0.0756) time: 0.3687 data: 0.0042 max mem: 3972 +train: [9] [220/400] eta: 0:01:12 lr: 0.000237 loss: 3.1465 (3.1245) grad: 0.0797 (0.0761) time: 0.3872 data: 0.0046 max mem: 3972 +train: [9] [240/400] eta: 0:01:04 lr: 0.000236 loss: 3.1420 (3.1265) grad: 0.0744 (0.0758) time: 0.3763 data: 0.0042 max mem: 3972 +train: [9] [260/400] eta: 0:00:55 lr: 0.000234 loss: 3.1335 (3.1253) grad: 0.0724 (0.0756) time: 0.3701 data: 0.0042 max mem: 3972 +train: [9] [280/400] eta: 0:00:47 lr: 0.000233 loss: 3.1173 (3.1252) grad: 0.0684 (0.0750) time: 0.3713 data: 0.0041 max mem: 3972 +train: [9] [300/400] eta: 0:00:39 lr: 0.000232 loss: 3.1249 (3.1263) grad: 0.0660 (0.0745) time: 0.3721 data: 0.0041 max mem: 3972 +train: [9] [320/400] eta: 0:00:31 lr: 0.000230 loss: 3.1217 (3.1258) grad: 0.0664 (0.0745) time: 0.3667 data: 0.0041 max mem: 3972 +train: [9] [340/400] eta: 0:00:23 lr: 0.000229 loss: 3.1315 (3.1270) grad: 0.0739 (0.0745) time: 0.3858 data: 0.0044 max mem: 3972 +train: [9] [360/400] eta: 0:00:15 lr: 0.000228 loss: 3.1372 (3.1267) grad: 0.0739 (0.0743) time: 0.3741 data: 0.0041 max mem: 3972 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 3.1079 (3.1271) grad: 0.0708 (0.0743) time: 0.3622 data: 0.0041 max mem: 3972 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 3.1319 (3.1273) grad: 0.0686 (0.0740) time: 0.3573 data: 0.0040 max mem: 3972 +train: [9] Total time: 0:02:35 (0.3893 s / it) +train: [9] Summary: lr: 0.000225 loss: 3.1319 (3.1273) grad: 0.0686 (0.0740) +eval (validation): [9] [ 0/85] eta: 0:05:19 time: 3.7628 data: 3.4964 max mem: 3972 +eval (validation): [9] [20/85] eta: 0:00:37 time: 0.4097 data: 0.0050 max mem: 3972 +eval (validation): [9] [40/85] eta: 0:00:21 time: 0.3600 data: 0.0043 max mem: 3972 +eval (validation): [9] [60/85] eta: 0:00:10 time: 0.3515 data: 0.0045 max mem: 3972 +eval (validation): [9] [80/85] eta: 0:00:02 time: 0.3736 data: 0.0044 max mem: 3972 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3670 data: 0.0042 max mem: 3972 +eval (validation): [9] Total time: 0:00:35 (0.4169 s / it) +cv: [9] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 3.121 acc: 0.083 f1: 0.030 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:26:32 lr: nan time: 3.9809 data: 3.7487 max mem: 3972 +train: [10] [ 20/400] eta: 0:03:37 lr: 0.000224 loss: 3.1227 (3.1321) grad: 0.0675 (0.0727) time: 0.4028 data: 0.0046 max mem: 3972 +train: [10] [ 40/400] eta: 0:02:49 lr: 0.000222 loss: 3.1204 (3.1255) grad: 0.0719 (0.0737) time: 0.3657 data: 0.0035 max mem: 3972 +train: [10] [ 60/400] eta: 0:02:28 lr: 0.000221 loss: 3.1276 (3.1321) grad: 0.0694 (0.0725) time: 0.3663 data: 0.0043 max mem: 3972 +train: [10] [ 80/400] eta: 0:02:13 lr: 0.000220 loss: 3.1204 (3.1265) grad: 0.0681 (0.0725) time: 0.3602 data: 0.0043 max mem: 3972 +train: [10] [100/400] eta: 0:02:02 lr: 0.000218 loss: 3.1254 (3.1287) grad: 0.0719 (0.0728) time: 0.3672 data: 0.0042 max mem: 3972 +train: [10] [120/400] eta: 0:01:52 lr: 0.000217 loss: 3.1273 (3.1258) grad: 0.0764 (0.0738) time: 0.3666 data: 0.0044 max mem: 3972 +train: [10] [140/400] eta: 0:01:42 lr: 0.000215 loss: 3.1004 (3.1228) grad: 0.0773 (0.0741) time: 0.3598 data: 0.0041 max mem: 3972 +train: [10] [160/400] eta: 0:01:34 lr: 0.000214 loss: 3.0923 (3.1219) grad: 0.0759 (0.0741) time: 0.3721 data: 0.0043 max mem: 3972 +train: [10] [180/400] eta: 0:01:25 lr: 0.000213 loss: 3.1255 (3.1237) grad: 0.0753 (0.0746) time: 0.3570 data: 0.0044 max mem: 3972 +train: [10] [200/400] eta: 0:01:17 lr: 0.000211 loss: 3.1255 (3.1230) grad: 0.0701 (0.0739) time: 0.3699 data: 0.0043 max mem: 3972 +train: [10] [220/400] eta: 0:01:09 lr: 0.000210 loss: 3.1192 (3.1233) grad: 0.0701 (0.0736) time: 0.3791 data: 0.0042 max mem: 3972 +train: [10] [240/400] eta: 0:01:01 lr: 0.000208 loss: 3.1113 (3.1223) grad: 0.0705 (0.0733) time: 0.3686 data: 0.0041 max mem: 3972 +train: [10] [260/400] eta: 0:00:53 lr: 0.000207 loss: 3.1064 (3.1221) grad: 0.0716 (0.0735) time: 0.3559 data: 0.0042 max mem: 3972 +train: [10] [280/400] eta: 0:00:45 lr: 0.000205 loss: 3.1175 (3.1220) grad: 0.0781 (0.0739) time: 0.3630 data: 0.0041 max mem: 3972 +train: [10] [300/400] eta: 0:00:38 lr: 0.000204 loss: 3.1323 (3.1236) grad: 0.0802 (0.0744) time: 0.3806 data: 0.0044 max mem: 3972 +train: [10] [320/400] eta: 0:00:30 lr: 0.000202 loss: 3.1412 (3.1245) grad: 0.0829 (0.0749) time: 0.3688 data: 0.0040 max mem: 3972 +train: [10] [340/400] eta: 0:00:22 lr: 0.000201 loss: 3.1132 (3.1243) grad: 0.0762 (0.0748) time: 0.3629 data: 0.0044 max mem: 3972 +train: [10] [360/400] eta: 0:00:15 lr: 0.000199 loss: 3.1177 (3.1240) grad: 0.0762 (0.0750) time: 0.3697 data: 0.0040 max mem: 3972 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 3.1268 (3.1239) grad: 0.0792 (0.0752) time: 0.3405 data: 0.0042 max mem: 3972 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 3.1259 (3.1240) grad: 0.0747 (0.0752) time: 0.3737 data: 0.0044 max mem: 3972 +train: [10] Total time: 0:02:30 (0.3769 s / it) +train: [10] Summary: lr: 0.000196 loss: 3.1259 (3.1240) grad: 0.0747 (0.0752) +eval (validation): [10] [ 0/85] eta: 0:05:07 time: 3.6138 data: 3.3268 max mem: 3972 +eval (validation): [10] [20/85] eta: 0:00:34 time: 0.3807 data: 0.0060 max mem: 3972 +eval (validation): [10] [40/85] eta: 0:00:19 time: 0.3343 data: 0.0044 max mem: 3972 +eval (validation): [10] [60/85] eta: 0:00:10 time: 0.3583 data: 0.0039 max mem: 3972 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3384 data: 0.0043 max mem: 3972 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3326 data: 0.0042 max mem: 3972 +eval (validation): [10] Total time: 0:00:33 (0.3940 s / it) +cv: [10] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.126 acc: 0.080 f1: 0.030 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:23:11 lr: nan time: 3.4775 data: 3.2415 max mem: 3972 +train: [11] [ 20/400] eta: 0:03:20 lr: 0.000195 loss: 3.1197 (3.1216) grad: 0.0686 (0.0700) time: 0.3791 data: 0.0039 max mem: 3972 +train: [11] [ 40/400] eta: 0:02:41 lr: 0.000193 loss: 3.1081 (3.1238) grad: 0.0714 (0.0726) time: 0.3654 data: 0.0036 max mem: 3972 +train: [11] [ 60/400] eta: 0:02:22 lr: 0.000192 loss: 3.1081 (3.1187) grad: 0.0727 (0.0732) time: 0.3566 data: 0.0042 max mem: 3972 +train: [11] [ 80/400] eta: 0:02:09 lr: 0.000190 loss: 3.1324 (3.1196) grad: 0.0727 (0.0732) time: 0.3664 data: 0.0044 max mem: 3972 +train: [11] [100/400] eta: 0:01:59 lr: 0.000189 loss: 3.1177 (3.1193) grad: 0.0720 (0.0730) time: 0.3740 data: 0.0044 max mem: 3972 +train: [11] [120/400] eta: 0:01:50 lr: 0.000187 loss: 3.1231 (3.1219) grad: 0.0700 (0.0728) time: 0.3727 data: 0.0043 max mem: 3972 +train: [11] [140/400] eta: 0:01:41 lr: 0.000186 loss: 3.1243 (3.1218) grad: 0.0725 (0.0732) time: 0.3726 data: 0.0042 max mem: 3972 +train: [11] [160/400] eta: 0:01:33 lr: 0.000184 loss: 3.1254 (3.1227) grad: 0.0736 (0.0731) time: 0.3786 data: 0.0041 max mem: 3972 +train: [11] [180/400] eta: 0:01:25 lr: 0.000183 loss: 3.1254 (3.1233) grad: 0.0715 (0.0731) time: 0.3623 data: 0.0042 max mem: 3972 +train: [11] [200/400] eta: 0:01:17 lr: 0.000181 loss: 3.1341 (3.1258) grad: 0.0688 (0.0729) time: 0.3762 data: 0.0041 max mem: 3972 +train: [11] [220/400] eta: 0:01:09 lr: 0.000180 loss: 3.1401 (3.1251) grad: 0.0687 (0.0725) time: 0.3773 data: 0.0040 max mem: 3972 +train: [11] [240/400] eta: 0:01:01 lr: 0.000178 loss: 3.1300 (3.1250) grad: 0.0714 (0.0728) time: 0.3813 data: 0.0040 max mem: 3972 +train: [11] [260/400] eta: 0:00:53 lr: 0.000177 loss: 3.1200 (3.1247) grad: 0.0767 (0.0730) time: 0.3593 data: 0.0039 max mem: 3972 +train: [11] [280/400] eta: 0:00:45 lr: 0.000175 loss: 3.1123 (3.1240) grad: 0.0744 (0.0729) time: 0.3748 data: 0.0045 max mem: 3972 +train: [11] [300/400] eta: 0:00:38 lr: 0.000174 loss: 3.1142 (3.1237) grad: 0.0786 (0.0736) time: 0.3660 data: 0.0042 max mem: 3972 +train: [11] [320/400] eta: 0:00:30 lr: 0.000172 loss: 3.1215 (3.1229) grad: 0.0786 (0.0736) time: 0.3674 data: 0.0043 max mem: 3972 +train: [11] [340/400] eta: 0:00:22 lr: 0.000170 loss: 3.1215 (3.1231) grad: 0.0721 (0.0736) time: 0.3690 data: 0.0041 max mem: 3972 +train: [11] [360/400] eta: 0:00:15 lr: 0.000169 loss: 3.1032 (3.1222) grad: 0.0684 (0.0732) time: 0.3557 data: 0.0040 max mem: 3972 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 3.1004 (3.1217) grad: 0.0676 (0.0733) time: 0.3601 data: 0.0041 max mem: 3972 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 3.1210 (3.1226) grad: 0.0690 (0.0730) time: 0.3883 data: 0.0043 max mem: 3972 +train: [11] Total time: 0:02:31 (0.3782 s / it) +train: [11] Summary: lr: 0.000166 loss: 3.1210 (3.1226) grad: 0.0690 (0.0730) +eval (validation): [11] [ 0/85] eta: 0:04:57 time: 3.5051 data: 3.2788 max mem: 3972 +eval (validation): [11] [20/85] eta: 0:00:37 time: 0.4358 data: 0.0066 max mem: 3972 +eval (validation): [11] [40/85] eta: 0:00:20 time: 0.3335 data: 0.0040 max mem: 3972 +eval (validation): [11] [60/85] eta: 0:00:10 time: 0.3692 data: 0.0044 max mem: 3972 +eval (validation): [11] [80/85] eta: 0:00:02 time: 0.3372 data: 0.0041 max mem: 3972 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3297 data: 0.0041 max mem: 3972 +eval (validation): [11] Total time: 0:00:34 (0.4081 s / it) +cv: [11] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.130 acc: 0.092 f1: 0.036 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:24:13 lr: nan time: 3.6342 data: 3.3614 max mem: 3972 +train: [12] [ 20/400] eta: 0:03:25 lr: 0.000164 loss: 3.1093 (3.1195) grad: 0.0695 (0.0735) time: 0.3850 data: 0.0053 max mem: 3972 +train: [12] [ 40/400] eta: 0:02:45 lr: 0.000163 loss: 3.1126 (3.1153) grad: 0.0707 (0.0733) time: 0.3770 data: 0.0036 max mem: 3972 +train: [12] [ 60/400] eta: 0:02:27 lr: 0.000161 loss: 3.1097 (3.1149) grad: 0.0722 (0.0737) time: 0.3827 data: 0.0044 max mem: 3972 +train: [12] [ 80/400] eta: 0:02:14 lr: 0.000160 loss: 3.1065 (3.1135) grad: 0.0737 (0.0729) time: 0.3798 data: 0.0041 max mem: 3972 +train: [12] [100/400] eta: 0:02:02 lr: 0.000158 loss: 3.1101 (3.1120) grad: 0.0710 (0.0732) time: 0.3605 data: 0.0041 max mem: 3972 +train: [12] [120/400] eta: 0:01:52 lr: 0.000156 loss: 3.1101 (3.1133) grad: 0.0685 (0.0727) time: 0.3672 data: 0.0042 max mem: 3972 +train: [12] [140/400] eta: 0:01:42 lr: 0.000155 loss: 3.1069 (3.1137) grad: 0.0672 (0.0726) time: 0.3577 data: 0.0046 max mem: 3972 +train: [12] [160/400] eta: 0:01:33 lr: 0.000153 loss: 3.0928 (3.1131) grad: 0.0682 (0.0724) time: 0.3516 data: 0.0041 max mem: 3972 +train: [12] [180/400] eta: 0:01:25 lr: 0.000152 loss: 3.1123 (3.1152) grad: 0.0694 (0.0725) time: 0.3628 data: 0.0042 max mem: 3972 +train: [12] [200/400] eta: 0:01:17 lr: 0.000150 loss: 3.1182 (3.1140) grad: 0.0694 (0.0725) time: 0.3672 data: 0.0043 max mem: 3972 +train: [12] [220/400] eta: 0:01:09 lr: 0.000149 loss: 3.1029 (3.1138) grad: 0.0727 (0.0726) time: 0.3747 data: 0.0044 max mem: 3972 +train: [12] [240/400] eta: 0:01:01 lr: 0.000147 loss: 3.1046 (3.1144) grad: 0.0688 (0.0721) time: 0.3545 data: 0.0042 max mem: 3972 +train: [12] [260/400] eta: 0:00:53 lr: 0.000145 loss: 3.1344 (3.1157) grad: 0.0676 (0.0718) time: 0.3623 data: 0.0041 max mem: 3972 +train: [12] [280/400] eta: 0:00:45 lr: 0.000144 loss: 3.1286 (3.1160) grad: 0.0753 (0.0722) time: 0.3732 data: 0.0042 max mem: 3972 +train: [12] [300/400] eta: 0:00:37 lr: 0.000142 loss: 3.1167 (3.1163) grad: 0.0764 (0.0721) time: 0.3654 data: 0.0042 max mem: 3972 +train: [12] [320/400] eta: 0:00:30 lr: 0.000141 loss: 3.1285 (3.1166) grad: 0.0691 (0.0720) time: 0.3665 data: 0.0042 max mem: 3972 +train: [12] [340/400] eta: 0:00:22 lr: 0.000139 loss: 3.1313 (3.1181) grad: 0.0724 (0.0721) time: 0.3715 data: 0.0043 max mem: 3972 +train: [12] [360/400] eta: 0:00:15 lr: 0.000138 loss: 3.1291 (3.1184) grad: 0.0729 (0.0723) time: 0.3467 data: 0.0041 max mem: 3972 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 3.1098 (3.1163) grad: 0.0702 (0.0722) time: 0.3787 data: 0.0046 max mem: 3972 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 3.1038 (3.1163) grad: 0.0682 (0.0719) time: 0.3703 data: 0.0041 max mem: 3972 +train: [12] Total time: 0:02:30 (0.3761 s / it) +train: [12] Summary: lr: 0.000134 loss: 3.1038 (3.1163) grad: 0.0682 (0.0719) +eval (validation): [12] [ 0/85] eta: 0:05:02 time: 3.5584 data: 3.2799 max mem: 3972 +eval (validation): [12] [20/85] eta: 0:00:35 time: 0.3984 data: 0.0047 max mem: 3972 +eval (validation): [12] [40/85] eta: 0:00:20 time: 0.3695 data: 0.0045 max mem: 3972 +eval (validation): [12] [60/85] eta: 0:00:10 time: 0.3651 data: 0.0045 max mem: 3972 +eval (validation): [12] [80/85] eta: 0:00:02 time: 0.3429 data: 0.0043 max mem: 3972 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3340 data: 0.0041 max mem: 3972 +eval (validation): [12] Total time: 0:00:34 (0.4085 s / it) +cv: [12] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.105 acc: 0.081 f1: 0.028 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:23:59 lr: nan time: 3.5996 data: 3.3337 max mem: 3972 +train: [13] [ 20/400] eta: 0:03:24 lr: 0.000133 loss: 3.0966 (3.1102) grad: 0.0768 (0.0755) time: 0.3841 data: 0.0141 max mem: 3972 +train: [13] [ 40/400] eta: 0:02:42 lr: 0.000131 loss: 3.1050 (3.1126) grad: 0.0752 (0.0749) time: 0.3592 data: 0.0035 max mem: 3972 +train: [13] [ 60/400] eta: 0:02:24 lr: 0.000130 loss: 3.1263 (3.1178) grad: 0.0726 (0.0760) time: 0.3770 data: 0.0043 max mem: 3972 +train: [13] [ 80/400] eta: 0:02:12 lr: 0.000128 loss: 3.1244 (3.1183) grad: 0.0726 (0.0748) time: 0.3747 data: 0.0041 max mem: 3972 +train: [13] [100/400] eta: 0:02:02 lr: 0.000127 loss: 3.1058 (3.1175) grad: 0.0680 (0.0736) time: 0.3851 data: 0.0042 max mem: 3972 +train: [13] [120/400] eta: 0:01:53 lr: 0.000125 loss: 3.1100 (3.1191) grad: 0.0680 (0.0741) time: 0.3990 data: 0.0043 max mem: 3972 +train: [13] [140/400] eta: 0:01:45 lr: 0.000124 loss: 3.1163 (3.1199) grad: 0.0742 (0.0740) time: 0.3919 data: 0.0042 max mem: 3972 +train: [13] [160/400] eta: 0:01:36 lr: 0.000122 loss: 3.1005 (3.1169) grad: 0.0711 (0.0735) time: 0.3711 data: 0.0044 max mem: 3972 +train: [13] [180/400] eta: 0:01:27 lr: 0.000120 loss: 3.0907 (3.1179) grad: 0.0722 (0.0737) time: 0.3932 data: 0.0042 max mem: 3972 +train: [13] [200/400] eta: 0:01:19 lr: 0.000119 loss: 3.1189 (3.1158) grad: 0.0725 (0.0733) time: 0.3815 data: 0.0041 max mem: 3972 +train: [13] [220/400] eta: 0:01:11 lr: 0.000117 loss: 3.1109 (3.1159) grad: 0.0704 (0.0730) time: 0.3888 data: 0.0039 max mem: 3972 +train: [13] [240/400] eta: 0:01:03 lr: 0.000116 loss: 3.1081 (3.1161) grad: 0.0699 (0.0730) time: 0.3733 data: 0.0041 max mem: 3972 +train: [13] [260/400] eta: 0:00:55 lr: 0.000114 loss: 3.1081 (3.1173) grad: 0.0731 (0.0735) time: 0.3761 data: 0.0041 max mem: 3972 +train: [13] [280/400] eta: 0:00:47 lr: 0.000113 loss: 3.1103 (3.1162) grad: 0.0731 (0.0734) time: 0.3801 data: 0.0042 max mem: 3972 +train: [13] [300/400] eta: 0:00:39 lr: 0.000111 loss: 3.1103 (3.1172) grad: 0.0720 (0.0732) time: 0.3903 data: 0.0040 max mem: 3972 +train: [13] [320/400] eta: 0:00:31 lr: 0.000110 loss: 3.1214 (3.1168) grad: 0.0702 (0.0730) time: 0.3943 data: 0.0042 max mem: 3972 +train: [13] [340/400] eta: 0:00:23 lr: 0.000108 loss: 3.1236 (3.1182) grad: 0.0691 (0.0730) time: 0.3750 data: 0.0043 max mem: 3972 +train: [13] [360/400] eta: 0:00:15 lr: 0.000107 loss: 3.1214 (3.1180) grad: 0.0714 (0.0729) time: 0.3628 data: 0.0041 max mem: 3972 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 3.1014 (3.1172) grad: 0.0689 (0.0728) time: 0.3842 data: 0.0045 max mem: 3972 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 3.1148 (3.1174) grad: 0.0709 (0.0728) time: 0.3685 data: 0.0043 max mem: 3972 +train: [13] Total time: 0:02:35 (0.3889 s / it) +train: [13] Summary: lr: 0.000104 loss: 3.1148 (3.1174) grad: 0.0709 (0.0728) +eval (validation): [13] [ 0/85] eta: 0:05:02 time: 3.5610 data: 3.3070 max mem: 3972 +eval (validation): [13] [20/85] eta: 0:00:32 time: 0.3519 data: 0.0050 max mem: 3972 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3530 data: 0.0038 max mem: 3972 +eval (validation): [13] [60/85] eta: 0:00:10 time: 0.3651 data: 0.0037 max mem: 3972 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3536 data: 0.0041 max mem: 3972 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3499 data: 0.0039 max mem: 3972 +eval (validation): [13] Total time: 0:00:33 (0.3968 s / it) +cv: [13] best hparam: (14, 1.0) (040) ('040_lr1.4e+01_wd1.0e+00') loss: 3.109 acc: 0.074 f1: 0.025 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:24:20 lr: nan time: 3.6501 data: 3.3500 max mem: 3972 +train: [14] [ 20/400] eta: 0:03:20 lr: 0.000102 loss: 3.1155 (3.1218) grad: 0.0752 (0.0736) time: 0.3722 data: 0.0047 max mem: 3972 +train: [14] [ 40/400] eta: 0:02:43 lr: 0.000101 loss: 3.1094 (3.1146) grad: 0.0734 (0.0738) time: 0.3755 data: 0.0040 max mem: 3972 +train: [14] [ 60/400] eta: 0:02:25 lr: 0.000099 loss: 3.1069 (3.1165) grad: 0.0729 (0.0741) time: 0.3753 data: 0.0041 max mem: 3972 +train: [14] [ 80/400] eta: 0:02:14 lr: 0.000098 loss: 3.1157 (3.1164) grad: 0.0713 (0.0741) time: 0.3915 data: 0.0043 max mem: 3972 +train: [14] [100/400] eta: 0:02:03 lr: 0.000096 loss: 3.1064 (3.1157) grad: 0.0757 (0.0737) time: 0.3820 data: 0.0043 max mem: 3972 +train: [14] [120/400] eta: 0:01:54 lr: 0.000095 loss: 3.1117 (3.1172) grad: 0.0706 (0.0732) time: 0.4016 data: 0.0041 max mem: 3972 +train: [14] [140/400] eta: 0:01:44 lr: 0.000093 loss: 3.1205 (3.1180) grad: 0.0681 (0.0724) time: 0.3655 data: 0.0041 max mem: 3972 +train: [14] [160/400] eta: 0:01:36 lr: 0.000092 loss: 3.1205 (3.1164) grad: 0.0681 (0.0717) time: 0.3803 data: 0.0042 max mem: 3972 +train: [14] [180/400] eta: 0:01:27 lr: 0.000090 loss: 3.1226 (3.1153) grad: 0.0703 (0.0722) time: 0.3794 data: 0.0041 max mem: 3972 +train: [14] [200/400] eta: 0:01:19 lr: 0.000089 loss: 3.1010 (3.1143) grad: 0.0724 (0.0723) time: 0.3964 data: 0.0039 max mem: 3972 +train: [14] [220/400] eta: 0:01:11 lr: 0.000088 loss: 3.1037 (3.1166) grad: 0.0706 (0.0721) time: 0.3825 data: 0.0040 max mem: 3972 +train: [14] [240/400] eta: 0:01:03 lr: 0.000086 loss: 3.1220 (3.1165) grad: 0.0731 (0.0724) time: 0.3741 data: 0.0042 max mem: 3972 +train: [14] [260/400] eta: 0:00:55 lr: 0.000085 loss: 3.1273 (3.1185) grad: 0.0736 (0.0721) time: 0.3690 data: 0.0045 max mem: 3972 +train: [14] [280/400] eta: 0:00:46 lr: 0.000083 loss: 3.1340 (3.1186) grad: 0.0742 (0.0724) time: 0.3737 data: 0.0039 max mem: 3972 +train: [14] [300/400] eta: 0:00:39 lr: 0.000082 loss: 3.1021 (3.1177) grad: 0.0780 (0.0726) time: 0.3862 data: 0.0042 max mem: 3972 +train: [14] [320/400] eta: 0:00:31 lr: 0.000081 loss: 3.0990 (3.1170) grad: 0.0745 (0.0728) time: 0.3764 data: 0.0043 max mem: 3972 +train: [14] [340/400] eta: 0:00:23 lr: 0.000079 loss: 3.1060 (3.1162) grad: 0.0745 (0.0729) time: 0.3485 data: 0.0041 max mem: 3972 +train: [14] [360/400] eta: 0:00:15 lr: 0.000078 loss: 3.0986 (3.1155) grad: 0.0709 (0.0727) time: 0.3692 data: 0.0043 max mem: 3972 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 3.1116 (3.1160) grad: 0.0697 (0.0726) time: 0.3718 data: 0.0042 max mem: 3972 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 3.1058 (3.1154) grad: 0.0711 (0.0726) time: 0.3721 data: 0.0041 max mem: 3972 +train: [14] Total time: 0:02:34 (0.3856 s / it) +train: [14] Summary: lr: 0.000075 loss: 3.1058 (3.1154) grad: 0.0711 (0.0726) +eval (validation): [14] [ 0/85] eta: 0:04:50 time: 3.4201 data: 3.1994 max mem: 3972 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3491 data: 0.0038 max mem: 3972 +eval (validation): [14] [40/85] eta: 0:00:19 time: 0.3517 data: 0.0048 max mem: 3972 +eval (validation): [14] [60/85] eta: 0:00:10 time: 0.3605 data: 0.0041 max mem: 3972 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3734 data: 0.0045 max mem: 3972 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3577 data: 0.0043 max mem: 3972 +eval (validation): [14] Total time: 0:00:33 (0.3970 s / it) +cv: [14] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.109 acc: 0.092 f1: 0.027 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:23:51 lr: nan time: 3.5779 data: 3.2843 max mem: 3972 +train: [15] [ 20/400] eta: 0:03:11 lr: 0.000074 loss: 3.1002 (3.1142) grad: 0.0700 (0.0723) time: 0.3494 data: 0.0069 max mem: 3972 +train: [15] [ 40/400] eta: 0:02:38 lr: 0.000072 loss: 3.0897 (3.0954) grad: 0.0700 (0.0712) time: 0.3769 data: 0.0045 max mem: 3972 +train: [15] [ 60/400] eta: 0:02:23 lr: 0.000071 loss: 3.0983 (3.1028) grad: 0.0717 (0.0716) time: 0.3796 data: 0.0042 max mem: 3972 +train: [15] [ 80/400] eta: 0:02:12 lr: 0.000070 loss: 3.1089 (3.1026) grad: 0.0715 (0.0710) time: 0.3871 data: 0.0042 max mem: 3972 +train: [15] [100/400] eta: 0:02:01 lr: 0.000068 loss: 3.0917 (3.1021) grad: 0.0703 (0.0711) time: 0.3683 data: 0.0042 max mem: 3972 +train: [15] [120/400] eta: 0:01:51 lr: 0.000067 loss: 3.0986 (3.1037) grad: 0.0674 (0.0704) time: 0.3776 data: 0.0040 max mem: 3972 +train: [15] [140/400] eta: 0:01:42 lr: 0.000066 loss: 3.1245 (3.1075) grad: 0.0652 (0.0698) time: 0.3661 data: 0.0041 max mem: 3972 +train: [15] [160/400] eta: 0:01:33 lr: 0.000064 loss: 3.1085 (3.1076) grad: 0.0662 (0.0697) time: 0.3662 data: 0.0042 max mem: 3972 +train: [15] [180/400] eta: 0:01:25 lr: 0.000063 loss: 3.0863 (3.1052) grad: 0.0668 (0.0698) time: 0.3776 data: 0.0042 max mem: 3972 +train: [15] [200/400] eta: 0:01:18 lr: 0.000062 loss: 3.0904 (3.1067) grad: 0.0666 (0.0695) time: 0.4048 data: 0.0042 max mem: 3972 +train: [15] [220/400] eta: 0:01:10 lr: 0.000061 loss: 3.1105 (3.1085) grad: 0.0712 (0.0698) time: 0.3669 data: 0.0043 max mem: 3972 +train: [15] [240/400] eta: 0:01:02 lr: 0.000059 loss: 3.1084 (3.1091) grad: 0.0712 (0.0699) time: 0.3721 data: 0.0043 max mem: 3972 +train: [15] [260/400] eta: 0:00:54 lr: 0.000058 loss: 3.1102 (3.1086) grad: 0.0721 (0.0701) time: 0.3690 data: 0.0043 max mem: 3972 +train: [15] [280/400] eta: 0:00:46 lr: 0.000057 loss: 3.1128 (3.1097) grad: 0.0731 (0.0704) time: 0.3675 data: 0.0041 max mem: 3972 +train: [15] [300/400] eta: 0:00:38 lr: 0.000056 loss: 3.1207 (3.1097) grad: 0.0664 (0.0702) time: 0.3691 data: 0.0040 max mem: 3972 +train: [15] [320/400] eta: 0:00:30 lr: 0.000054 loss: 3.0958 (3.1091) grad: 0.0664 (0.0701) time: 0.3596 data: 0.0041 max mem: 3972 +train: [15] [340/400] eta: 0:00:22 lr: 0.000053 loss: 3.0951 (3.1096) grad: 0.0717 (0.0703) time: 0.3540 data: 0.0039 max mem: 3972 +train: [15] [360/400] eta: 0:00:15 lr: 0.000052 loss: 3.1031 (3.1093) grad: 0.0740 (0.0705) time: 0.3692 data: 0.0042 max mem: 3972 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 3.0860 (3.1088) grad: 0.0740 (0.0706) time: 0.3644 data: 0.0042 max mem: 3972 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 3.0949 (3.1091) grad: 0.0729 (0.0706) time: 0.3724 data: 0.0042 max mem: 3972 +train: [15] Total time: 0:02:31 (0.3792 s / it) +train: [15] Summary: lr: 0.000050 loss: 3.0949 (3.1091) grad: 0.0729 (0.0706) +eval (validation): [15] [ 0/85] eta: 0:04:51 time: 3.4274 data: 3.1509 max mem: 3972 +eval (validation): [15] [20/85] eta: 0:00:32 time: 0.3539 data: 0.0044 max mem: 3972 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3500 data: 0.0044 max mem: 3972 +eval (validation): [15] [60/85] eta: 0:00:10 time: 0.3563 data: 0.0038 max mem: 3972 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3378 data: 0.0043 max mem: 3972 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3322 data: 0.0041 max mem: 3972 +eval (validation): [15] Total time: 0:00:33 (0.3884 s / it) +cv: [15] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.090 acc: 0.092 f1: 0.047 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:22:42 lr: nan time: 3.4050 data: 3.1831 max mem: 3972 +train: [16] [ 20/400] eta: 0:03:08 lr: 0.000048 loss: 3.0840 (3.0792) grad: 0.0675 (0.0676) time: 0.3509 data: 0.0033 max mem: 3972 +train: [16] [ 40/400] eta: 0:02:36 lr: 0.000047 loss: 3.1102 (3.1006) grad: 0.0675 (0.0668) time: 0.3674 data: 0.0039 max mem: 3972 +train: [16] [ 60/400] eta: 0:02:19 lr: 0.000046 loss: 3.1212 (3.1009) grad: 0.0672 (0.0666) time: 0.3600 data: 0.0041 max mem: 3972 +train: [16] [ 80/400] eta: 0:02:07 lr: 0.000045 loss: 3.1158 (3.1051) grad: 0.0684 (0.0684) time: 0.3629 data: 0.0042 max mem: 3972 +train: [16] [100/400] eta: 0:01:57 lr: 0.000044 loss: 3.1153 (3.1058) grad: 0.0708 (0.0693) time: 0.3681 data: 0.0042 max mem: 3972 +train: [16] [120/400] eta: 0:01:48 lr: 0.000043 loss: 3.1195 (3.1086) grad: 0.0687 (0.0689) time: 0.3631 data: 0.0042 max mem: 3972 +train: [16] [140/400] eta: 0:01:39 lr: 0.000042 loss: 3.1274 (3.1099) grad: 0.0671 (0.0696) time: 0.3562 data: 0.0042 max mem: 3972 +train: [16] [160/400] eta: 0:01:31 lr: 0.000041 loss: 3.1174 (3.1110) grad: 0.0724 (0.0699) time: 0.3682 data: 0.0043 max mem: 3972 +train: [16] [180/400] eta: 0:01:23 lr: 0.000040 loss: 3.1137 (3.1110) grad: 0.0676 (0.0700) time: 0.3673 data: 0.0043 max mem: 3972 +train: [16] [200/400] eta: 0:01:15 lr: 0.000039 loss: 3.1163 (3.1120) grad: 0.0691 (0.0702) time: 0.3760 data: 0.0043 max mem: 3972 +train: [16] [220/400] eta: 0:01:08 lr: 0.000038 loss: 3.1254 (3.1119) grad: 0.0687 (0.0702) time: 0.3679 data: 0.0038 max mem: 3972 +train: [16] [240/400] eta: 0:01:00 lr: 0.000036 loss: 3.1172 (3.1111) grad: 0.0701 (0.0711) time: 0.3630 data: 0.0042 max mem: 3972 +train: [16] [260/400] eta: 0:00:52 lr: 0.000035 loss: 3.1172 (3.1117) grad: 0.0693 (0.0708) time: 0.3607 data: 0.0040 max mem: 3972 +train: [16] [280/400] eta: 0:00:45 lr: 0.000034 loss: 3.1006 (3.1108) grad: 0.0676 (0.0708) time: 0.3698 data: 0.0042 max mem: 3972 +train: [16] [300/400] eta: 0:00:37 lr: 0.000033 loss: 3.0950 (3.1102) grad: 0.0693 (0.0709) time: 0.3686 data: 0.0042 max mem: 3972 +train: [16] [320/400] eta: 0:00:29 lr: 0.000032 loss: 3.0893 (3.1101) grad: 0.0658 (0.0707) time: 0.3562 data: 0.0042 max mem: 3972 +train: [16] [340/400] eta: 0:00:22 lr: 0.000031 loss: 3.0917 (3.1098) grad: 0.0649 (0.0706) time: 0.3683 data: 0.0040 max mem: 3972 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 3.1082 (3.1100) grad: 0.0661 (0.0704) time: 0.3792 data: 0.0040 max mem: 3972 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 3.1189 (3.1103) grad: 0.0672 (0.0705) time: 0.3732 data: 0.0042 max mem: 3972 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 3.1041 (3.1088) grad: 0.0687 (0.0704) time: 0.3735 data: 0.0039 max mem: 3972 +train: [16] Total time: 0:02:29 (0.3738 s / it) +train: [16] Summary: lr: 0.000029 loss: 3.1041 (3.1088) grad: 0.0687 (0.0704) +eval (validation): [16] [ 0/85] eta: 0:04:50 time: 3.4230 data: 3.1924 max mem: 3972 +eval (validation): [16] [20/85] eta: 0:00:32 time: 0.3538 data: 0.0051 max mem: 3972 +eval (validation): [16] [40/85] eta: 0:00:19 time: 0.3633 data: 0.0035 max mem: 3972 +eval (validation): [16] [60/85] eta: 0:00:10 time: 0.3717 data: 0.0045 max mem: 3972 +eval (validation): [16] [80/85] eta: 0:00:02 time: 0.3685 data: 0.0045 max mem: 3972 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.3624 data: 0.0044 max mem: 3972 +eval (validation): [16] Total time: 0:00:34 (0.4028 s / it) +cv: [16] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.091 acc: 0.091 f1: 0.036 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:22:54 lr: nan time: 3.4374 data: 3.2064 max mem: 3972 +train: [17] [ 20/400] eta: 0:03:18 lr: 0.000028 loss: 3.1022 (3.1048) grad: 0.0729 (0.0741) time: 0.3762 data: 0.0039 max mem: 3972 +train: [17] [ 40/400] eta: 0:02:43 lr: 0.000027 loss: 3.1061 (3.1082) grad: 0.0728 (0.0724) time: 0.3828 data: 0.0034 max mem: 3972 +train: [17] [ 60/400] eta: 0:02:26 lr: 0.000026 loss: 3.1102 (3.1126) grad: 0.0728 (0.0729) time: 0.3855 data: 0.0041 max mem: 3972 +train: [17] [ 80/400] eta: 0:02:14 lr: 0.000025 loss: 3.1102 (3.1115) grad: 0.0744 (0.0732) time: 0.3830 data: 0.0040 max mem: 3972 +train: [17] [100/400] eta: 0:02:03 lr: 0.000024 loss: 3.1044 (3.1100) grad: 0.0715 (0.0731) time: 0.3874 data: 0.0041 max mem: 3972 +train: [17] [120/400] eta: 0:01:54 lr: 0.000023 loss: 3.1191 (3.1127) grad: 0.0687 (0.0723) time: 0.3792 data: 0.0040 max mem: 3972 +train: [17] [140/400] eta: 0:01:44 lr: 0.000023 loss: 3.1278 (3.1115) grad: 0.0698 (0.0722) time: 0.3713 data: 0.0043 max mem: 3972 +train: [17] [160/400] eta: 0:01:36 lr: 0.000022 loss: 3.1154 (3.1101) grad: 0.0698 (0.0715) time: 0.3882 data: 0.0040 max mem: 3972 +train: [17] [180/400] eta: 0:01:28 lr: 0.000021 loss: 3.1159 (3.1103) grad: 0.0682 (0.0712) time: 0.3953 data: 0.0042 max mem: 3972 +train: [17] [200/400] eta: 0:01:19 lr: 0.000020 loss: 3.1159 (3.1100) grad: 0.0667 (0.0707) time: 0.3931 data: 0.0041 max mem: 3972 +train: [17] [220/400] eta: 0:01:11 lr: 0.000019 loss: 3.1069 (3.1098) grad: 0.0683 (0.0708) time: 0.3772 data: 0.0041 max mem: 3972 +train: [17] [240/400] eta: 0:01:03 lr: 0.000019 loss: 3.1003 (3.1089) grad: 0.0713 (0.0710) time: 0.3748 data: 0.0042 max mem: 3972 +train: [17] [260/400] eta: 0:00:55 lr: 0.000018 loss: 3.1003 (3.1081) grad: 0.0700 (0.0707) time: 0.3703 data: 0.0043 max mem: 3972 +train: [17] [280/400] eta: 0:00:47 lr: 0.000017 loss: 3.1078 (3.1084) grad: 0.0665 (0.0705) time: 0.3771 data: 0.0042 max mem: 3972 +train: [17] [300/400] eta: 0:00:39 lr: 0.000016 loss: 3.1223 (3.1093) grad: 0.0672 (0.0707) time: 0.3863 data: 0.0042 max mem: 3972 +train: [17] [320/400] eta: 0:00:31 lr: 0.000016 loss: 3.1196 (3.1098) grad: 0.0699 (0.0705) time: 0.3482 data: 0.0040 max mem: 3972 +train: [17] [340/400] eta: 0:00:23 lr: 0.000015 loss: 3.1118 (3.1103) grad: 0.0668 (0.0701) time: 0.3729 data: 0.0045 max mem: 3972 +train: [17] [360/400] eta: 0:00:15 lr: 0.000014 loss: 3.0956 (3.1103) grad: 0.0637 (0.0702) time: 0.3732 data: 0.0044 max mem: 3972 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 3.0949 (3.1099) grad: 0.0712 (0.0702) time: 0.3690 data: 0.0042 max mem: 3972 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 3.0951 (3.1100) grad: 0.0708 (0.0702) time: 0.3619 data: 0.0042 max mem: 3972 +train: [17] Total time: 0:02:34 (0.3856 s / it) +train: [17] Summary: lr: 0.000013 loss: 3.0951 (3.1100) grad: 0.0708 (0.0702) +eval (validation): [17] [ 0/85] eta: 0:05:01 time: 3.5442 data: 3.2711 max mem: 3972 +eval (validation): [17] [20/85] eta: 0:00:33 time: 0.3591 data: 0.0045 max mem: 3972 +eval (validation): [17] [40/85] eta: 0:00:19 time: 0.3597 data: 0.0037 max mem: 3972 +eval (validation): [17] [60/85] eta: 0:00:10 time: 0.3591 data: 0.0045 max mem: 3972 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3316 data: 0.0039 max mem: 3972 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3243 data: 0.0038 max mem: 3972 +eval (validation): [17] Total time: 0:00:33 (0.3917 s / it) +cv: [17] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.085 acc: 0.094 f1: 0.039 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:23:17 lr: nan time: 3.4950 data: 3.2513 max mem: 3972 +train: [18] [ 20/400] eta: 0:03:31 lr: 0.000012 loss: 3.1376 (3.1378) grad: 0.0621 (0.0697) time: 0.4085 data: 0.0074 max mem: 3972 +train: [18] [ 40/400] eta: 0:02:45 lr: 0.000012 loss: 3.1163 (3.1136) grad: 0.0694 (0.0714) time: 0.3609 data: 0.0039 max mem: 3972 +train: [18] [ 60/400] eta: 0:02:25 lr: 0.000011 loss: 3.1055 (3.1155) grad: 0.0710 (0.0711) time: 0.3587 data: 0.0039 max mem: 3972 +train: [18] [ 80/400] eta: 0:02:11 lr: 0.000011 loss: 3.0987 (3.1123) grad: 0.0710 (0.0714) time: 0.3623 data: 0.0043 max mem: 3972 +train: [18] [100/400] eta: 0:02:00 lr: 0.000010 loss: 3.0934 (3.1104) grad: 0.0742 (0.0719) time: 0.3653 data: 0.0043 max mem: 3972 +train: [18] [120/400] eta: 0:01:50 lr: 0.000009 loss: 3.0986 (3.1091) grad: 0.0722 (0.0714) time: 0.3589 data: 0.0041 max mem: 3972 +train: [18] [140/400] eta: 0:01:42 lr: 0.000009 loss: 3.0989 (3.1076) grad: 0.0649 (0.0703) time: 0.3769 data: 0.0044 max mem: 3972 +train: [18] [160/400] eta: 0:01:33 lr: 0.000008 loss: 3.1035 (3.1073) grad: 0.0641 (0.0702) time: 0.3627 data: 0.0041 max mem: 3972 +train: [18] [180/400] eta: 0:01:24 lr: 0.000008 loss: 3.1070 (3.1077) grad: 0.0685 (0.0702) time: 0.3639 data: 0.0042 max mem: 3972 +train: [18] [200/400] eta: 0:01:16 lr: 0.000007 loss: 3.0980 (3.1064) grad: 0.0707 (0.0703) time: 0.3588 data: 0.0042 max mem: 3972 +train: [18] [220/400] eta: 0:01:08 lr: 0.000007 loss: 3.0874 (3.1050) grad: 0.0724 (0.0704) time: 0.3547 data: 0.0039 max mem: 3972 +train: [18] [240/400] eta: 0:01:00 lr: 0.000006 loss: 3.1039 (3.1051) grad: 0.0695 (0.0700) time: 0.3767 data: 0.0040 max mem: 3972 +train: [18] [260/400] eta: 0:00:53 lr: 0.000006 loss: 3.0909 (3.1037) grad: 0.0641 (0.0696) time: 0.3746 data: 0.0043 max mem: 3972 +train: [18] [280/400] eta: 0:00:45 lr: 0.000006 loss: 3.0892 (3.1025) grad: 0.0670 (0.0695) time: 0.3727 data: 0.0041 max mem: 3972 +train: [18] [300/400] eta: 0:00:37 lr: 0.000005 loss: 3.0953 (3.1037) grad: 0.0706 (0.0699) time: 0.3542 data: 0.0040 max mem: 3972 +train: [18] [320/400] eta: 0:00:30 lr: 0.000005 loss: 3.1004 (3.1038) grad: 0.0725 (0.0701) time: 0.3834 data: 0.0041 max mem: 3972 +train: [18] [340/400] eta: 0:00:22 lr: 0.000004 loss: 3.1031 (3.1042) grad: 0.0718 (0.0700) time: 0.3634 data: 0.0042 max mem: 3972 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 3.1178 (3.1052) grad: 0.0635 (0.0696) time: 0.3734 data: 0.0042 max mem: 3972 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 3.1191 (3.1061) grad: 0.0637 (0.0694) time: 0.3598 data: 0.0041 max mem: 3972 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 3.1218 (3.1067) grad: 0.0705 (0.0696) time: 0.3689 data: 0.0042 max mem: 3972 +train: [18] Total time: 0:02:30 (0.3761 s / it) +train: [18] Summary: lr: 0.000003 loss: 3.1218 (3.1067) grad: 0.0705 (0.0696) +eval (validation): [18] [ 0/85] eta: 0:05:06 time: 3.6103 data: 3.3102 max mem: 3972 +eval (validation): [18] [20/85] eta: 0:00:36 time: 0.4047 data: 0.0042 max mem: 3972 +eval (validation): [18] [40/85] eta: 0:00:20 time: 0.3589 data: 0.0042 max mem: 3972 +eval (validation): [18] [60/85] eta: 0:00:10 time: 0.3413 data: 0.0045 max mem: 3972 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3320 data: 0.0043 max mem: 3972 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3285 data: 0.0042 max mem: 3972 +eval (validation): [18] Total time: 0:00:33 (0.3993 s / it) +cv: [18] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.080 acc: 0.089 f1: 0.038 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:23:34 lr: nan time: 3.5354 data: 3.2973 max mem: 3972 +train: [19] [ 20/400] eta: 0:03:21 lr: 0.000003 loss: 3.0778 (3.0783) grad: 0.0721 (0.0718) time: 0.3791 data: 0.0051 max mem: 3972 +train: [19] [ 40/400] eta: 0:02:42 lr: 0.000003 loss: 3.0867 (3.0863) grad: 0.0759 (0.0731) time: 0.3706 data: 0.0041 max mem: 3972 +train: [19] [ 60/400] eta: 0:02:24 lr: 0.000002 loss: 3.1076 (3.0976) grad: 0.0716 (0.0727) time: 0.3725 data: 0.0041 max mem: 3972 +train: [19] [ 80/400] eta: 0:02:12 lr: 0.000002 loss: 3.1007 (3.0962) grad: 0.0695 (0.0721) time: 0.3821 data: 0.0043 max mem: 3972 +train: [19] [100/400] eta: 0:02:01 lr: 0.000002 loss: 3.0829 (3.0948) grad: 0.0677 (0.0709) time: 0.3637 data: 0.0044 max mem: 3972 +train: [19] [120/400] eta: 0:01:51 lr: 0.000002 loss: 3.0946 (3.0986) grad: 0.0668 (0.0703) time: 0.3745 data: 0.0043 max mem: 3972 +train: [19] [140/400] eta: 0:01:43 lr: 0.000001 loss: 3.0962 (3.0962) grad: 0.0668 (0.0704) time: 0.3899 data: 0.0045 max mem: 3972 +train: [19] [160/400] eta: 0:01:34 lr: 0.000001 loss: 3.0901 (3.0961) grad: 0.0689 (0.0706) time: 0.3635 data: 0.0040 max mem: 3972 +train: [19] [180/400] eta: 0:01:25 lr: 0.000001 loss: 3.0991 (3.0969) grad: 0.0686 (0.0700) time: 0.3555 data: 0.0042 max mem: 3972 +train: [19] [200/400] eta: 0:01:17 lr: 0.000001 loss: 3.1157 (3.1000) grad: 0.0663 (0.0695) time: 0.3593 data: 0.0041 max mem: 3972 +train: [19] [220/400] eta: 0:01:09 lr: 0.000001 loss: 3.1157 (3.0991) grad: 0.0640 (0.0692) time: 0.3812 data: 0.0042 max mem: 3972 +train: [19] [240/400] eta: 0:01:01 lr: 0.000001 loss: 3.1100 (3.1011) grad: 0.0640 (0.0692) time: 0.3677 data: 0.0041 max mem: 3972 +train: [19] [260/400] eta: 0:00:53 lr: 0.000000 loss: 3.1100 (3.1014) grad: 0.0652 (0.0689) time: 0.3701 data: 0.0039 max mem: 3972 +train: [19] [280/400] eta: 0:00:45 lr: 0.000000 loss: 3.1153 (3.1022) grad: 0.0686 (0.0691) time: 0.3453 data: 0.0039 max mem: 3972 +train: [19] [300/400] eta: 0:00:38 lr: 0.000000 loss: 3.1132 (3.1022) grad: 0.0651 (0.0689) time: 0.3690 data: 0.0043 max mem: 3972 +train: [19] [320/400] eta: 0:00:30 lr: 0.000000 loss: 3.1111 (3.1030) grad: 0.0685 (0.0692) time: 0.3835 data: 0.0047 max mem: 3972 +train: [19] [340/400] eta: 0:00:22 lr: 0.000000 loss: 3.1111 (3.1035) grad: 0.0702 (0.0693) time: 0.3776 data: 0.0037 max mem: 3972 +train: [19] [360/400] eta: 0:00:15 lr: 0.000000 loss: 3.1043 (3.1038) grad: 0.0731 (0.0698) time: 0.3628 data: 0.0042 max mem: 3972 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 3.1049 (3.1036) grad: 0.0731 (0.0697) time: 0.3760 data: 0.0040 max mem: 3972 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 3.1032 (3.1039) grad: 0.0688 (0.0696) time: 0.3526 data: 0.0038 max mem: 3972 +train: [19] Total time: 0:02:31 (0.3781 s / it) +train: [19] Summary: lr: 0.000000 loss: 3.1032 (3.1039) grad: 0.0688 (0.0696) +eval (validation): [19] [ 0/85] eta: 0:05:10 time: 3.6587 data: 3.3677 max mem: 3972 +eval (validation): [19] [20/85] eta: 0:00:34 time: 0.3730 data: 0.0198 max mem: 3972 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3419 data: 0.0041 max mem: 3972 +eval (validation): [19] [60/85] eta: 0:00:10 time: 0.3496 data: 0.0040 max mem: 3972 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3397 data: 0.0042 max mem: 3972 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3387 data: 0.0042 max mem: 3972 +eval (validation): [19] Total time: 0:00:33 (0.3928 s / it) +cv: [19] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.081 acc: 0.088 f1: 0.036 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-last.pth +eval model info: +{"score": 0.08767072720561092, "hparam": [43, 1.0], "hparam_id": 47, "epoch": 19, "is_best": false, "best_score": 0.09449981543004798} +eval (train): [20] [ 0/509] eta: 0:31:15 time: 3.6847 data: 3.4385 max mem: 3972 +eval (train): [20] [ 20/509] eta: 0:04:17 time: 0.3682 data: 0.0040 max mem: 3972 +eval (train): [20] [ 40/509] eta: 0:03:31 time: 0.3706 data: 0.0038 max mem: 3972 +eval (train): [20] [ 60/509] eta: 0:03:07 time: 0.3529 data: 0.0043 max mem: 3972 +eval (train): [20] [ 80/509] eta: 0:02:53 time: 0.3645 data: 0.0045 max mem: 3972 +eval (train): [20] [100/509] eta: 0:02:42 time: 0.3648 data: 0.0046 max mem: 3972 +eval (train): [20] [120/509] eta: 0:02:31 time: 0.3518 data: 0.0045 max mem: 3972 +eval (train): [20] [140/509] eta: 0:02:21 time: 0.3491 data: 0.0042 max mem: 3972 +eval (train): [20] [160/509] eta: 0:02:12 time: 0.3506 data: 0.0042 max mem: 3972 +eval (train): [20] [180/509] eta: 0:02:04 time: 0.3571 data: 0.0044 max mem: 3972 +eval (train): [20] [200/509] eta: 0:01:55 time: 0.3410 data: 0.0041 max mem: 3972 +eval (train): [20] [220/509] eta: 0:01:47 time: 0.3691 data: 0.0046 max mem: 3972 +eval (train): [20] [240/509] eta: 0:01:39 time: 0.3437 data: 0.0045 max mem: 3972 +eval (train): [20] [260/509] eta: 0:01:31 time: 0.3362 data: 0.0046 max mem: 3972 +eval (train): [20] [280/509] eta: 0:01:23 time: 0.3369 data: 0.0043 max mem: 3972 +eval (train): [20] [300/509] eta: 0:01:16 time: 0.3496 data: 0.0042 max mem: 3972 +eval (train): [20] [320/509] eta: 0:01:08 time: 0.3430 data: 0.0045 max mem: 3972 +eval (train): [20] [340/509] eta: 0:01:01 time: 0.3545 data: 0.0043 max mem: 3972 +eval (train): [20] [360/509] eta: 0:00:53 time: 0.3299 data: 0.0043 max mem: 3972 +eval (train): [20] [380/509] eta: 0:00:46 time: 0.3410 data: 0.0044 max mem: 3972 +eval (train): [20] [400/509] eta: 0:00:39 time: 0.3198 data: 0.0042 max mem: 3972 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3485 data: 0.0044 max mem: 3972 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3185 data: 0.0043 max mem: 3972 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3282 data: 0.0042 max mem: 3972 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3504 data: 0.0045 max mem: 3972 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3328 data: 0.0041 max mem: 3972 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3233 data: 0.0038 max mem: 3972 +eval (train): [20] Total time: 0:03:00 (0.3544 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:58 time: 3.5081 data: 3.2093 max mem: 3972 +eval (validation): [20] [20/85] eta: 0:00:36 time: 0.4116 data: 0.0057 max mem: 3972 +eval (validation): [20] [40/85] eta: 0:00:20 time: 0.3602 data: 0.0039 max mem: 3972 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3507 data: 0.0046 max mem: 3972 +eval (validation): [20] [80/85] eta: 0:00:02 time: 0.3436 data: 0.0044 max mem: 3972 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3247 data: 0.0039 max mem: 3972 +eval (validation): [20] Total time: 0:00:34 (0.4050 s / it) +eval (test): [20] [ 0/85] eta: 0:04:52 time: 3.4432 data: 3.2150 max mem: 3972 +eval (test): [20] [20/85] eta: 0:00:32 time: 0.3453 data: 0.0048 max mem: 3972 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3798 data: 0.0043 max mem: 3972 +eval (test): [20] [60/85] eta: 0:00:10 time: 0.3437 data: 0.0044 max mem: 3972 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3354 data: 0.0041 max mem: 3972 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3222 data: 0.0041 max mem: 3972 +eval (test): [20] Total time: 0:00:33 (0.3884 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:56 time: 3.6173 data: 3.3043 max mem: 3972 +eval (testid): [20] [20/82] eta: 0:00:33 time: 0.3886 data: 0.0040 max mem: 3972 +eval (testid): [20] [40/82] eta: 0:00:19 time: 0.3763 data: 0.0042 max mem: 3972 +eval (testid): [20] [60/82] eta: 0:00:09 time: 0.3420 data: 0.0043 max mem: 3972 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3357 data: 0.0042 max mem: 3972 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3253 data: 0.0040 max mem: 3972 +eval (testid): [20] Total time: 0:00:33 (0.4025 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/checkpoint-best.pth +eval model info: +{"score": 0.09449981543004798, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 17, "is_best": true, "best_score": 0.09449981543004798} +eval (train): [20] [ 0/509] eta: 0:27:47 time: 3.2754 data: 3.0560 max mem: 3972 +eval (train): [20] [ 20/509] eta: 0:04:07 time: 0.3684 data: 0.0243 max mem: 3972 +eval (train): [20] [ 40/509] eta: 0:03:25 time: 0.3639 data: 0.0040 max mem: 3972 +eval (train): [20] [ 60/509] eta: 0:03:05 time: 0.3632 data: 0.0043 max mem: 3972 +eval (train): [20] [ 80/509] eta: 0:02:51 time: 0.3604 data: 0.0044 max mem: 3972 +eval (train): [20] [100/509] eta: 0:02:36 time: 0.3167 data: 0.0042 max mem: 3972 +eval (train): [20] [120/509] eta: 0:02:25 time: 0.3246 data: 0.0039 max mem: 3972 +eval (train): [20] [140/509] eta: 0:02:15 time: 0.3297 data: 0.0041 max mem: 3972 +eval (train): [20] [160/509] eta: 0:02:06 time: 0.3375 data: 0.0041 max mem: 3972 +eval (train): [20] [180/509] eta: 0:01:58 time: 0.3301 data: 0.0042 max mem: 3972 +eval (train): [20] [200/509] eta: 0:01:51 time: 0.3661 data: 0.0046 max mem: 3972 +eval (train): [20] [220/509] eta: 0:01:43 time: 0.3374 data: 0.0039 max mem: 3972 +eval (train): [20] [240/509] eta: 0:01:35 time: 0.3202 data: 0.0037 max mem: 3972 +eval (train): [20] [260/509] eta: 0:01:28 time: 0.3551 data: 0.0044 max mem: 3972 +eval (train): [20] [280/509] eta: 0:01:20 time: 0.3277 data: 0.0041 max mem: 3972 +eval (train): [20] [300/509] eta: 0:01:13 time: 0.3296 data: 0.0042 max mem: 3972 +eval (train): [20] [320/509] eta: 0:01:06 time: 0.3646 data: 0.0045 max mem: 3972 +eval (train): [20] [340/509] eta: 0:00:59 time: 0.3635 data: 0.0042 max mem: 3972 +eval (train): [20] [360/509] eta: 0:00:52 time: 0.3209 data: 0.0042 max mem: 3972 +eval (train): [20] [380/509] eta: 0:00:45 time: 0.3182 data: 0.0038 max mem: 3972 +eval (train): [20] [400/509] eta: 0:00:38 time: 0.3515 data: 0.0042 max mem: 3972 +eval (train): [20] [420/509] eta: 0:00:31 time: 0.3758 data: 0.0045 max mem: 3972 +eval (train): [20] [440/509] eta: 0:00:24 time: 0.3445 data: 0.0045 max mem: 3972 +eval (train): [20] [460/509] eta: 0:00:17 time: 0.3271 data: 0.0039 max mem: 3972 +eval (train): [20] [480/509] eta: 0:00:10 time: 0.3339 data: 0.0042 max mem: 3972 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3466 data: 0.0045 max mem: 3972 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3300 data: 0.0042 max mem: 3972 +eval (train): [20] Total time: 0:02:57 (0.3497 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:31 time: 3.1910 data: 2.9274 max mem: 3972 +eval (validation): [20] [20/85] eta: 0:00:30 time: 0.3353 data: 0.0046 max mem: 3972 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3470 data: 0.0032 max mem: 3972 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3237 data: 0.0038 max mem: 3972 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3047 data: 0.0035 max mem: 3972 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2971 data: 0.0034 max mem: 3972 +eval (validation): [20] Total time: 0:00:30 (0.3633 s / it) +eval (test): [20] [ 0/85] eta: 0:04:34 time: 3.2322 data: 3.0071 max mem: 3972 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3328 data: 0.0038 max mem: 3972 +eval (test): [20] [40/85] eta: 0:00:17 time: 0.3156 data: 0.0035 max mem: 3972 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3147 data: 0.0040 max mem: 3972 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3026 data: 0.0038 max mem: 3972 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2943 data: 0.0036 max mem: 3972 +eval (test): [20] Total time: 0:00:29 (0.3521 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:15 time: 3.1131 data: 2.9095 max mem: 3972 +eval (testid): [20] [20/82] eta: 0:00:27 time: 0.3069 data: 0.0035 max mem: 3972 +eval (testid): [20] [40/82] eta: 0:00:15 time: 0.3116 data: 0.0038 max mem: 3972 +eval (testid): [20] [60/82] eta: 0:00:07 time: 0.3081 data: 0.0036 max mem: 3972 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3044 data: 0.0037 max mem: 3972 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2951 data: 0.0035 max mem: 3972 +eval (testid): [20] Total time: 0:00:28 (0.3431 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|-------:|---------:|----------:|---------:|-----------:| +| flat_mae | patch | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 3.0588 | 0.10418 | 0.0013816 | 0.041625 | 0.00082552 | +| flat_mae | patch | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 3.0849 | 0.0945 | 0.0032431 | 0.038688 | 0.0017939 | +| flat_mae | patch | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 3.0913 | 0.09128 | 0.0031899 | 0.033192 | 0.0017518 | +| flat_mae | patch | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | testid | 3.0941 | 0.091961 | 0.0035888 | 0.034371 | 0.0019059 | + + +done! total time: 1:12:55 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/train_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..c6dc54f433d3612eea51afbc93c36294b259710f --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__patch__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.161413596868515, "train/grad": 0.08174931768327952, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.183280029296875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.183182373046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.183016357421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.182840576171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1826611328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.182432861328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1821875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.18192138671875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.181536865234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.18114501953125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.180736083984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.18017333984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.179564208984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.178626708984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.17784423828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.177027587890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.176009521484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.17478271484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.173287353515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.171866455078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.17019287109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.168416748046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.16657958984375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.16454345703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1623779296875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.16009033203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.158026123046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.15634765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.154281005859375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.152021484375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1502001953125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.148753662109375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1470556640625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.145684814453125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.144345703125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.143074951171875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1419140625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.141015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.140054931640625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1393798828125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.138936767578125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.138763427734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1387158203125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.138878173828125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.139232177734375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.140045166015625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.14093505859375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1420166015625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1432666015625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.0126683729281649, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012664015446789563, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012656339048407971, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012648939527571202, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012641741810366511, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012631456004455685, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.01261974432040006, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012606443893164397, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012589476788416504, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012571120699867606, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012553111659362912, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0125256303884089, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012498515103943645, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012459226413629948, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.012419990175403654, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01238192681223154, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.012331921425648033, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.012272445070557296, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.012203523381613195, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.012137427437119186, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.012055189651437103, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011969391312450171, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0118728280486539, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01177009979262948, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011663957606069744, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011543384036049247, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011441111229360104, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01135452167596668, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.011247088697273285, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.011135073523037135, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.011048010964877904, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010977132574189453, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010894300907384604, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010829468693118542, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010762570614460856, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010706508117727935, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01065732417628169, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01061982202809304, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010588132604025304, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01056313524255529, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010556136721279473, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010557166959624737, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010569140962325037, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010588907829951495, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010623953361064196, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010672657194081694, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010718400727491827, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010780049725435675, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010846134868916123, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.180422782897949, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1801133155822754, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.179619073867798, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.179112195968628, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.178619623184204, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.177914619445801, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1771042346954346, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.17625093460083, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1751279830932617, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1739110946655273, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1727538108825684, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.170944929122925, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.169238328933716, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.166778802871704, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1644327640533447, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.162203073501587, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1594009399414062, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1561620235443115, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1526310443878174, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1494669914245605, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1457605361938477, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.142199993133545, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.138589382171631, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.135202646255493, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1322476863861084, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1295278072357178, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.127772569656372, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1266632080078125, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1257286071777344, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.125286340713501, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.12528920173645, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1255288124084473, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1260197162628174, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.126512289047241, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1271088123321533, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.127553701400757, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.127864122390747, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.127955913543701, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.127906560897827, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1277573108673096, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.127821207046509, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.128206253051758, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.129422903060913, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1310014724731445, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.132948160171509, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.134441614151001, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1349494457244873, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1359174251556396, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.138319969177246, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.03433001107419712, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.03433001107419712, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.03451458102620893, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.03451458102620893, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.03506829088224437, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.03525286083425618, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.035437430786267994, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.036544850498338874, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.038390550018456995, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.04318936877076412, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.050387596899224806, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.058508674787744554, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06404577334809892, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06478405315614617, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06736803248431156, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0029934233490614462, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0029934233490614462, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0032277244328055414, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0034309693088117204, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0040795968715919674, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004500916852125979, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004965983588302168, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005398793632951284, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006483860314901572, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006925691412485711, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007130235907975625, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006797096822946838, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006667056248636082, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005375094836877664, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005375094836877664, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005375282208142159, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005165567525875469, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005375475166513589, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005375094836877664, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005165567525875469, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0051652360414530096, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005375094836877664, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005374736698072694, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005374913013221991, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.005374913013221991, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00557362889548776, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005564707902444081, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005751419151553455, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005905897841363581, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.006967816726787368, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.007840976331572479, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.008197673146884308, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.008377557401637597, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.008023730791674772, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.006956591771870059, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.006043994563557842, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.005165901973636297, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.0049615228837586066, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0049615228837586066, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.0049615228837586066, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0049615228837586066, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0049615228837586066, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0049615228837586066, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.005360789454518971, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.007807372337053358, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.010067904957510159, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.01293995259716547, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.1432666015625, "validation/loss_best": 3.138319969177246, "validation/acc_best": 0.06736803248431156, "validation/f1_best": 0.01293995259716547} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.1484543013572694, "train/grad": 0.0783452151156962, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.179095458984375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1784423828125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17751220703125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.176461181640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.175460205078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.17411865234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.172681884765625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.171046142578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.168917236328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.167037353515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.16495361328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.162078857421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.159510498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.156136474609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.153106689453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.15055419921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.147503662109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.144495849609375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.141668701171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.13928955078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.137132568359375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.135389404296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.133912353515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.132763671875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.132056884765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.131561279296875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.13132568359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.13125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.131407470703125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.131710205078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.132015380859375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.132454833984375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.133040771484375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.133619384765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.13430908203125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.135064697265625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.135950927734375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.136884765625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.137879638671875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.13915283203125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1400732421875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.141181640625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1429931640625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.144893798828125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.147132568359375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.149788818359375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.15234130859375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1562548828125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.16065185546875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012582261702045799, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012553318021818995, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01250639397650957, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012460407493636012, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.012415182893164456, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.012353620417416096, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012284659990109503, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012209468921646476, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012112850060220807, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012012603404000401, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011916013660375029, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011777973603457212, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011651246384717524, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011479069695342332, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011326796796638519, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011193010597489774, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011037904233671725, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010878741745837034, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010729293555486947, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010614358827006072, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010499838278628887, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.01040845222538337, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010333856653887778, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010279338280670345, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010243949636351318, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010223101859446615, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010215125824324787, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0102160201407969, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010224363051820546, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010240456806495785, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010258068549446761, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010277308651711791, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01030541031388566, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010333845925051719, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010374065518844873, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010420381787698716, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010478261944372206, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010541194821707905, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010618134529795497, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010727701294235885, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010824616577010601, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010922465424519032, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011067898094188422, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011202319064177573, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011347917318344116, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011490155782084913, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011634238567203282, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011859334977343679, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012117774703074246, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1745595932006836, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.173454999923706, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1716461181640625, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1699204444885254, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1682565212249756, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.165982484817505, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.163540840148926, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1609365940093994, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.157708168029785, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1545300483703613, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.151627779006958, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.147651195526123, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1442368030548096, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1399552822113037, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1365411281585693, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1338603496551514, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.131138324737549, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.12876558303833, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1269729137420654, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1258771419525146, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.12510085105896, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1247072219848633, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1245312690734863, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.124537229537964, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1246304512023926, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.124837875366211, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.125086545944214, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1253485679626465, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.125765323638916, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1263248920440674, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1268532276153564, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.127359390258789, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1280486583709717, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1286401748657227, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1293511390686035, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1301186084747314, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1310813426971436, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1318628787994385, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1323626041412354, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.132500410079956, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1328330039978027, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.13368558883667, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.136025905609131, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.139320135116577, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.145294427871704, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1576104164123535, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1691150665283203, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.178553342819214, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.183887243270874, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.03820598006644518, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.04355850867478774, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.052417866371354746, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06035437430786268, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.05703211517165006, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.05629383536360281, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06552233296419344, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06183093392395718, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.060538944259874494, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.05758582502768549, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.05795496493170912, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0636766334440753, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06183093392395718, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06201550387596899, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06183093392395718, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006487387511821496, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006974610448888929, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007016360241927939, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006866457019126961, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006862938809651754, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005374240418470817, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005374085754065246, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005374240418470817, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00537351991755462, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005373936408419167, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0053732681851602565, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0053733914822591934, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005374085754065246, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005373936408419167, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005577901892464303, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005374085754065246, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005165567525875469, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005165567525875469, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005164582043125153, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005178739732164899, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.005434186749051923, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.007463617162049736, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.010332166876114634, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.013767422200198371, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.015583757949167866, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.015941617053234505, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.009117901168098188, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.010050460526348632, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.01199645861842994, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.01747532022469456, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.0113326108758796, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.007883838670094285, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0053231172649277035, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.005082125603864735, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 3.1400732421875, "validation/loss_best": 3.1328330039978027, "validation/acc_best": 0.06552233296419344, "validation/f1_best": 0.015941617053234505} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.140289999246597, "train/grad": 0.07713767042383551, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.17041748046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1688671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.166470947265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.164200439453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.16207763671875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1591796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.156251220703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.153275146484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.149683837890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.14638916015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1435546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.13998779296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1371044921875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.13392578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1317236328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1302490234375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12884521484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.127900390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12724365234375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1269482421875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.126749267578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1267333984375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126759033203125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126837158203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12694580078125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.127071533203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12713623046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12728759765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1275537109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.127813720703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.128292236328125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.12860107421875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.129228515625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.129813232421875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.130518798828125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.13141845703125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.132479248046875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.133560791015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.134876708984375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.13664306640625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.138026123046875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.139107666015625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.141090087890625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.14357666015625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.147430419921875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.152880859375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.158699951171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.167313232421875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1754730224609373, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012255428708158433, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012186379753984511, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012074174787849189, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011966975182294845, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01186424077488482, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011727945166639983, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011584214740432799, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011437065901700407, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011263041007332504, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011099081239663064, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010956454407423735, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01077324091689661, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010628013075329363, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010466498613823205, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010355555161368102, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010279483902268112, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010214333687908948, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010168634089641273, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010142388208769261, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01013087719446048, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01012757909949869, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010130198672413826, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010137340887449681, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010146394458133727, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010156703633256256, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010170074137859047, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010183484880253673, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010197200269903988, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010218548865523189, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010248797938693315, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010279986816458404, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010312515641562641, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010359096846077592, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010407023369334639, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010469830804504454, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010542471958324313, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01063112978124991, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010727496778126806, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01084457867546007, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011006444632075727, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01113464218331501, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011249747325200588, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011425118409097195, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011612881519831718, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011875206655822694, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012215642512310297, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01255079961149022, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01297605139669031, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013332938007079066, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.166102886199951, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1640617847442627, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1608238220214844, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.157850980758667, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1550979614257812, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1516053676605225, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1480727195739746, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1446261405944824, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1407487392425537, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.137359619140625, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1346397399902344, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1315367221832275, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.129345655441284, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1272544860839844, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1260640621185303, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1253662109375, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1248817443847656, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1246354579925537, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1245267391204834, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1245148181915283, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1245298385620117, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1245453357696533, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124600648880005, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1246795654296875, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.124786138534546, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.124904155731201, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.125025987625122, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1250908374786377, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1251275539398193, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1250336170196533, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.124866008758545, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.124723196029663, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.124617099761963, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.124554395675659, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1244804859161377, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1244726181030273, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1250040531158447, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1264538764953613, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1295299530029297, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.135164976119995, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.139287233352661, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.141313076019287, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1422536373138428, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.142997980117798, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1427266597747803, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.142712116241455, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1485042572021484, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1653573513031006, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1863651275634766, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06201550387596899, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.060538944259874494, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06164636397194537, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.062384643779992616, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06478405315614617, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06995201181247693, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0651531930601698, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06312292358803986, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06681432262827612, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06533776301218161, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06441491325212255, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06773717238833518, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06626061277224068, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005164582043125153, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005178739732164899, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005178417788241079, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005177783121513583, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0053647418968355036, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.008622517216649443, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.009262894239067981, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.008284312396649408, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.007490365283058136, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.00783432691112728, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.009311460639640957, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.009497456053745008, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.009573730733444624, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.010300529239262356, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.009561751698225608, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.008540623430029903, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.007751877709629234, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.010747701543345353, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.016175438267784104, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.012906015272172243, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.010693113451557006, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.013421156923303307, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.01656353424449655, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0165463399788154, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.01071257656741434, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.012544019737454648, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 3.139107666015625, "validation/loss_best": 3.141313076019287, "validation/acc_best": 0.06995201181247693, "validation/f1_best": 0.016175438267784104} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.1389110136032103, "train/grad": 0.07635831715539097, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.162799072265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.160400390625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1567822265625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.15352294921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.150673828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.147059326171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.143677978515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.140479736328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13724609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.134549560546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.132655029296875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.130621337890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129322509765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128280029296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12775634765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.127623291015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.127437744140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.127445068359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.127430419921875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12745361328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.127523193359375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.127635498046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.127801513671875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.127825927734375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.127994384765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.128280029296875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.128470458984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.128719482421875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.129117431640625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12960205078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.129879150390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.130301513671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.130887451171875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.131461181640625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.132237548828125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.133182373046875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.13438720703125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.135428466796875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.13662841796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.138179931640625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.13977294921875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.14173583984375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1454150390625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.149732666015625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.155264892578125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.16086181640625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.165989990234375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.174617919921875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1844921875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011757517808582633, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011642158962786198, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011464852464850992, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01130621504969895, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011163896308280527, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010989882776048034, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010820991578511893, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.01066085511352867, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010490879947319627, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010354015065822751, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010256325672380627, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010159649439156055, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010101770907640457, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010054399787914009, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010032797032035887, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010024784964043647, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01002225883072242, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01002578602405265, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01003191178664565, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01003972427919507, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01004952216753736, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010060005690902471, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01007299451623112, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010087687950581313, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010105333253741265, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010128180873580276, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010151578665245324, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010174919883720577, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010210263705812395, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010255991064477712, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010301952925510704, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010347385599743575, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01041471486678347, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01047965465579182, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010563713151495903, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010655826444271953, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01077078162226826, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010893392930738629, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011040471056476235, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011235338787082582, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011405317622702568, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01156736506614834, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011803256045095623, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012040494713000954, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01232986057177186, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012607439202256501, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01287188371643424, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01330802173819393, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013782024905085564, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1563844680786133, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.153568744659424, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1493873596191406, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1457767486572266, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.142657518386841, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1390113830566406, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1356797218322754, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1328060626983643, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.130082130432129, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1280734539031982, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1267426013946533, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1255226135253906, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124892234802246, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.124464273452759, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.124324083328247, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1242642402648926, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1242451667785645, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.124246597290039, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1242570877075195, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.124281644821167, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1243302822113037, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124380588531494, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1244094371795654, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.124500036239624, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1245903968811035, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1247811317443848, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.125088691711426, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.125464916229248, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.126248836517334, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1274726390838623, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1287331581115723, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.129761219024658, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1308138370513916, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1313562393188477, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.131584644317627, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1314711570739746, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1313316822052, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.131079912185669, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.130239963531494, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1290900707244873, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1304714679718018, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.134819269180298, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1432504653930664, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1527395248413086, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1620993614196777, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1715991497039795, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.175396203994751, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.180042266845703, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.18418025970459, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.058693244739756366, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.059616094499815434, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06736803248431156, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0664451827242525, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06662975267626431, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07013658176448874, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06718346253229975, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06866002214839424, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06939830195644149, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0695828719084533, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.060538944259874494, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06090808416389812, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0049504950495049506, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0052137941492611875, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.006355672734291338, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.006792503376196348, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.008153841539661227, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.00971460121511617, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.009695097388413247, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.00773583081206685, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.008158631659055874, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.014432233757511867, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.013147947380465505, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.01280811475175802, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.020461805001083053, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.02269490845227165, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.022912679494676333, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.016484921945901135, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.021155561650838425, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.018673286723531125, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.017056585712436872, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 3.1454150390625, "validation/loss_best": 3.1432504653930664, "validation/acc_best": 0.07013658176448874, "validation/f1_best": 0.020461805001083053} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.1409513890743255, "train/grad": 0.07689195416867733, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.15455810546875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.151766357421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1476904296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1444775390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.141708984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.138702392578125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.136165771484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.134154052734375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.132376708984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.13120361328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1305712890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.130020751953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129783935546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.129716796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129681396484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.129732666015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.129801025390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12988525390625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.129827880859375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.129906005859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.129884033203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12998046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.129949951171875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12987060546875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12987548828125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1299169921875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.129825439453125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.129892578125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.130028076171875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.130322265625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.130628662109375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.131058349609375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.131766357421875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1326171875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.133680419921875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.134820556640625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.13617431640625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.137523193359375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.139405517578125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.142109375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.144697265625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.147747802734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1531378173828126, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1598388671875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.168514404296875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.17861572265625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.188006591796875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.19756103515625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.2074407958984374, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011329390753526241, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011188689696136862, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010984832691028713, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010812402761075646, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010667618287261576, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010502302146051079, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010360966445878148, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010251709928270429, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.01016056295717135, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010102895619347692, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010068796554114669, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010043795078527182, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010033873543143272, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010031382769811898, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010035299891605974, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010040126228705048, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01004722249461338, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010056525578256696, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010067923541646451, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010078452553134411, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010091126007027924, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010105549963191152, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01012261115713045, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010141291038598866, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010161162964068353, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01018753772135824, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010213526401203125, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010239306080620736, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010278143303003162, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01033066845498979, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010383722581900656, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010439714277163148, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010521760014817118, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01060056226560846, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01070026058005169, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010809392186347395, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010941087282262743, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011085437536239624, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01127011129166931, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011537067047320305, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01174759533489123, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011931004342623055, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01221502507571131, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012512863213196397, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012859062710776924, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01328329652082175, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013655198365449905, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013985148197971285, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014464672580361366, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1469244956970215, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.143829822540283, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1395373344421387, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1361372470855713, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.133481502532959, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1306958198547363, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1285150051116943, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.126887798309326, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.125577449798584, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1247987747192383, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.124370574951172, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124051809310913, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1239078044891357, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123782157897949, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1236610412597656, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123575448989868, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123455286026001, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123310089111328, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1231441497802734, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1230051517486572, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1228580474853516, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.122720956802368, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.122614622116089, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.122546911239624, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1225483417510986, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.122600555419922, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1227643489837646, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.122967481613159, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.123445510864258, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.124420404434204, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.125659704208374, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1271679401397705, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1297659873962402, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1323068141937256, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.134798765182495, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1364214420318604, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1386451721191406, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.141728401184082, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1437788009643555, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1427416801452637, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.143167495727539, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.145951986312866, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1528759002685547, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.158529758453369, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1568901538848877, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.155021905899048, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1776676177978516, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.220411777496338, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2439701557159424, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06109265411590993, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.05887781469176818, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06183093392395718, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06626061277224068, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07161314138058324, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07438169066076043, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06902916205241787, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06256921373200443, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.05813953488372093, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.058508674787744554, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.004963245933900562, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005167617973985362, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.007619139923137247, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.009352792029928511, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.00871702116780857, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0055565127498277056, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0055565127498277056, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.009460043518435721, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.011073420410922524, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.011642090128542393, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.013953588205212678, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.014834174642626005, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.011916634497164796, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.008935346652823703, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.011400837394376742, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.017746246466143544, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.02149960595573862, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.022745596899707038, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.020680402637841145, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.013597109836812645, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.004584352078239608, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.005364605417528851, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 3.134820556640625, "validation/loss_best": 3.1364214420318604, "validation/acc_best": 0.07456626061277224, "validation/f1_best": 0.011073420410922524} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 3.1387809646129607, "train/grad": 0.07719500118866562, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.146429443359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.143653564453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1397998046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13699462890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13487548828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.13288818359375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.131334228515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1303369140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129578857421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129293212890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129078369140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.128885498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128905029296875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12885986328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12879150390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1287939453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12868896484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12873291015625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.128587646484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.128480224609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.128463134765625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.128336181640625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12829833984375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.128277587890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.128135986328125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12800537109375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.128052978515625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.128023681640625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.128228759765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.128507080078125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.128983154296875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1294921875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.13024169921875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.131339111328125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.132498779296875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.13413330078125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.136134033203125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1390869140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.143585205078125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.147396240234375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.150792236328125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.155792236328125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.16072509765625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.16752685546875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1746307373046876, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1822235107421877, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1947576904296877, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.206629638671875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010917615075595678, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010770045174285769, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010570448276121169, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010416155802085996, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010303818904794752, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010199652267619968, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010126634712796657, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010078114483039826, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010043246774002909, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.01002692564856261, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010022320800926536, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010023105684667825, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010026157558895648, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010031708015594632, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01003685526549816, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010042457391973585, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010048730259295553, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010056789538357407, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010065651978366078, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010074274078942836, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010084470955189318, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010096952489111572, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010113309083972127, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010131338099017739, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010152238146401942, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010177977827843278, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010205075396224856, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010231234431266785, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010269223209470511, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010320659277494997, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010375630878843366, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010431476735975593, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010519394625443965, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010606270949356258, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01071728509152308, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01084146643988788, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01100233049597591, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011181656315457075, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01139917253749445, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011693724798969924, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011944401864893735, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01218240532791242, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012523695826530457, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012846554461866617, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01328920149244368, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.013765027364715934, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.014168756387662143, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014681097792927176, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01508815146284178, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1395511627197266, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.136678695678711, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1329843997955322, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1304101943969727, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.128587484359741, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.126891851425171, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.125753402709961, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.125056266784668, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1246023178100586, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1244027614593506, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1243081092834473, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1242454051971436, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1241989135742188, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.124143362045288, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1240592002868652, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123969078063965, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1238651275634766, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1237099170684814, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.123508930206299, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1233439445495605, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1231067180633545, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.122882604598999, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1226611137390137, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.122506856918335, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1223673820495605, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1222851276397705, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1222527027130127, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1222739219665527, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1224281787872314, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1227481365203857, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.123110294342041, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.123396635055542, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.123878240585327, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.124314308166504, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.124718189239502, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1246445178985596, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1241443157196045, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.123695135116577, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1228981018066406, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.122208833694458, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.125277519226074, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1308979988098145, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1368167400360107, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1378471851348877, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1383450031280518, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.153795003890991, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1868605613708496, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.215346574783325, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.226466178894043, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.061461794019933555, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06183093392395718, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.067921742340347, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07659653008490218, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07641196013289037, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07216685123661867, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07087486157253599, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0754891103728313, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08231819859726837, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0828719084533038, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.082687338501292, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07290513104466592, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0651531930601698, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06829088224437062, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07290513104466592, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.004949635290031261, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.00495565988523735, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.004949053857350801, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0053635508687819725, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0054607935786223525, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.007872227836366518, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.014043926912227904, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01841751566525721, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.019507195018847717, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.018941609163905818, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.017023110033366356, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.014700859754507562, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.012722028971832527, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.012170035430974292, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.01697973276525895, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.019699713459383834, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.01503089820327242, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.016755909315177547, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.014694019270255232, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.008378563309902056, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.010444979090174271, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.01476722718530002, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 3.16072509765625, "validation/loss_best": 3.1378471851348877, "validation/acc_best": 0.0828719084533038, "validation/f1_best": 0.01503089820327242} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 3.133878690004349, "train/grad": 0.0758370716124773, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.139873046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.137069091796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.133834228515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131485595703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129967041015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128499755859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127587890625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127164306640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126734619140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1266259765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12653076171875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.126507568359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.126436767578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1264013671875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126424560546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12635498046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126431884765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1263916015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12644775390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1263623046875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1265283203125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.126373291015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126392822265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126429443359375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.126376953125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.126361083984375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12629150390625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12635009765625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.12630615234375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.126319580078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.126248779296875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.126226806640625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.126220703125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.126287841796875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1264599609375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.126712646484375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.12743408203125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.128421630859375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.129830322265625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.13236083984375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.134991455078125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.137684326171875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.142332763671875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1476959228515624, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.15582763671875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.166717529296875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.178447265625, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.189014892578125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.194283447265625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010489285478834064, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010350032893475145, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01018137066392228, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010075050462037325, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010008128469344228, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009949897082988173, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009913216547574847, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009892620195169002, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009882270782254636, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009880286266561598, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009881674309726805, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009884999026544392, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00988844782114029, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009894058599602431, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009900007476098836, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009905756779480725, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0099122618813999, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00992152393097058, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00993203276535496, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009941965867765247, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009955445167142897, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009970651406329125, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009988390989601612, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010009414902888238, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010032619410194456, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010064158984459937, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010096260923892259, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01012690548086539, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010172323584556579, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010232901657000184, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010292101695667952, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010349000829737633, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010429035215638578, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010504399556666613, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010599158108234405, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010704732618760317, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01083655826980248, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010982320436742157, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011161066668573767, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011414463925175368, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0116373410820961, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01185583504382521, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012183025171980262, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012523110185284167, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012993489338550717, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01356840290594846, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01410245310049504, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01450100241228938, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01481020960956812, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1345598697662354, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1321303844451904, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.129281520843506, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.127436637878418, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.126269578933716, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1252987384796143, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124769687652588, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124485969543457, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1243679523468018, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124352216720581, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.124387502670288, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124438762664795, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124533176422119, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1246840953826904, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1248204708099365, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1249797344207764, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.125178098678589, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1253793239593506, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.125619411468506, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.125821590423584, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1260197162628174, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1261911392211914, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1263647079467773, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1266207695007324, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.126957893371582, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.12753963470459, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1282527446746826, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1290876865386963, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.130295991897583, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.131716728210449, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1327850818634033, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1333093643188477, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.133145570755005, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.131924867630005, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1295948028564453, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1270623207092285, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1245508193969727, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1228878498077393, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.123196840286255, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.129387855529785, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.139350414276123, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.146559000015259, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1476664543151855, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.148397922515869, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1558988094329834, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.177385091781616, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.199775457382202, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.2204997539520264, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.220496892929077, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07327427094868956, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.073827980804725, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06736803248431156, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06201550387596899, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.060723514211886306, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06404577334809892, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0769656699889258, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06459948320413436, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07198228128460686, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07788851974898486, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.005225773840701306, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.006236610062467582, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.007622010688202424, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.01088634240539523, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.01524182616597556, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.01654605583435954, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.015545429935648433, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.013779709929423007, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.013975762597270546, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0162712474570402, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.017759877937372093, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.014525629242787117, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.01870298680165523, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.026413943775006037, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.194283447265625, "validation/loss_best": 3.220496892929077, "validation/acc_best": 0.07788851974898486, "validation/f1_best": 0.026413943775006037} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 3.1312905168533325, "train/grad": 0.07666751882061362, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1355859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.133436279296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131031494140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12952392578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12865234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127938232421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12748046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12731689453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127222900390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127183837890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12712158203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12706787109375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12703857421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.126912841796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12678466796875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.126656494140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126558837890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.126328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.126119384765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12603759765625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.125648193359375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.125450439453125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.125284423828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12507080078125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.124854736328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.124691162109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.124569091796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12451904296875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.124359130859375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1244189453125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12436279296875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.124395751953125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1244677734375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1243408203125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.124251708984375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.124239501953125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.124180908203125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.12424072265625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1251202392578126, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1275396728515625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1302532958984375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.132872314453125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1374090576171874, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1432818603515624, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.15050537109375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1574371337890623, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.16361328125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1742120361328126, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1856500244140626, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010436305571347474, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010322858083527535, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010201941006816923, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010131557153072209, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010087814207654446, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010051224420312792, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010031669167801738, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0100238802540116, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010021427199244499, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010022175770718605, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.0100243316963315, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.01002767653670162, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010031060634646564, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010036092367954552, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01004100895486772, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010044820113107563, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01005042731994763, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010056341055314989, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01006407937966287, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010071162465028465, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010080446826759727, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010090982920955867, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010104583725333214, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010120785986073315, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010140752021688968, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010168480852153152, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010197264940943569, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010227705002762377, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010273382822051645, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010336614332627505, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010402296392712743, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010470820101909339, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01057516278233379, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010676638695877046, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010803687982261181, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010936054955236614, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.011084678459446877, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011232501287013292, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011411879770457744, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011676893685944378, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011890247894916684, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012081924283411354, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012379410634748638, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012701553483493626, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.013102795784361661, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.013532953928224742, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013889498161152005, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014369191830046474, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014864172893576324, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1312732696533203, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.129316806793213, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1271655559539795, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.125927209854126, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12520694732666, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124695062637329, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1244401931762695, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124356508255005, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1242868900299072, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124260902404785, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.124239683151245, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124188184738159, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124109983444214, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1240031719207764, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1238784790039062, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1237239837646484, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123563051223755, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123382806777954, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.123239278793335, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1231179237365723, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1230053901672363, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1229474544525146, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1229279041290283, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1229090690612793, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1229488849639893, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1230664253234863, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1232588291168213, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.123535633087158, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1240713596343994, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1247196197509766, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1251893043518066, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1253764629364014, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1253814697265625, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.125514030456543, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.126295328140259, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.127871036529541, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.130040407180786, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1319429874420166, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.133898973464966, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.136389970779419, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1384880542755127, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1387956142425537, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1377813816070557, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.141550064086914, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.151291847229004, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1583094596862793, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1636557579040527, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.158257246017456, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.163330078125, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07179771133259505, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0754891103728313, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07069029162052418, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07069029162052418, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07272056109265411, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07493540051679587, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07770394979697305, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07770394979697305, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07567368032484312, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0664451827242525, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07235142118863049, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06459948320413436, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005164582043125153, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00797178518031304, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009304972674196983, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008642873145936257, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005558428128231645, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005555555555555556, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005555555555555556, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.0055565127498277056, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.006317633316924011, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.007204085511905325, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.009506216279615294, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01156334914192021, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.014130574895402148, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.015408566048405098, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.016469358783125564, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.01680803037814655, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.015487548305374485, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.01211103549424423, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.011695533003025128, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.013813174089678915, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.014701977842044099, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.016842354784741723, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.01684858729405322, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.019523118270425327, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.019287394685749536, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.029163534739366847, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.020709810959979962, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 3.1432818603515624, "validation/loss_best": 3.141550064086914, "validation/acc_best": 0.07770394979697305, "validation/f1_best": 0.016842354784741723} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 3.1299112367630006, "train/grad": 0.07716805759817362, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.133765869140625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.132286376953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13054931640625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1297412109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12930908203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12881103515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12880615234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128658447265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.128597412109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128558349609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.128597412109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12851806640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.128424072265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128314208984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128253173828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12813720703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.128067626953125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.127904052734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12771728515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.127593994140625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.127464599609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.127276611328125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126978759765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126688232421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.126488037109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.126181640625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.125770263671875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.125782470703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.1254296875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1252587890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12499267578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.12490234375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.12459716796875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.124337158203125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1242120361328123, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1241961669921876, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1247698974609377, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.125499267578125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.12612060546875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1264898681640627, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.126607666015625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.12721435546875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1292547607421874, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.13204833984375, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.13699951171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.14408203125, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1508343505859373, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.15851318359375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1660528564453125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010461598203983158, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010377032412216068, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010290446165017784, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010240924297831952, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010211479689460248, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010192565345205367, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010185107325669377, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.0101835933374241, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010184587927069515, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010187196715269237, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010191027179826052, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010195565910544246, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010200417079031467, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010207138829864562, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010214228234253823, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010221169649157672, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010229239931795746, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01023940988117829, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010250824100803585, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01026256533106789, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010276434826664627, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010291990714613349, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010309561854228377, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010330115377437324, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010353714148513972, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010385083127766847, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010418251345399768, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01045140920439735, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010502522869501263, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010570070550311356, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010635976830963045, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010698446778114885, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010786522491835059, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010868210878688842, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010970881623215974, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.011081816575024278, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.011218721957411616, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011356993375811726, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011505619373638183, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011692818654701113, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01185755118727684, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.012034337178338319, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.012302937742788345, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012540326789021491, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012836397308856249, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01317591780098155, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013519464943092316, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.014004758056253196, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01444898612331599, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.129040241241455, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1274614334106445, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1258623600006104, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1250152587890625, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124554395675659, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124262809753418, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124100685119629, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124028205871582, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123957395553589, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1238932609558105, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123812437057495, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123697280883789, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123605251312256, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1234664916992188, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1233863830566406, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123305082321167, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1232292652130127, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1231420040130615, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1230995655059814, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1230735778808594, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1230974197387695, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1231677532196045, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.12331223487854, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.12353777885437, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.123840570449829, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1243183612823486, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1247520446777344, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.125121831893921, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1255245208740234, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1257598400115967, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.125661611557007, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.12534761428833, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.124464273452759, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.123318672180176, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1218583583831787, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.121323347091675, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.122575044631958, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1251089572906494, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1280360221862793, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1310648918151855, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.132897138595581, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.134291172027588, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.134873867034912, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1309328079223633, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1262869834899902, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.13110089302063, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.138770341873169, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.134108781814575, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1250202655792236, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06847545219638243, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07419712070874862, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07954964931709117, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07456626061277224, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07751937984496124, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07585825027685493, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07198228128460686, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07419712070874862, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07475083056478406, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07308970099667775, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005225856490714887, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.00683273903566196, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.008727085468871252, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.00959468012803063, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00967934718520449, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009399047560005326, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009590999411986219, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.00958102873760805, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.009545767787627618, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.009850462601006381, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009886740979343805, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.01010418399472611, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.009459227915431261, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0106716176039521, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.013417538842231286, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.017207850710299327, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.01787838731466152, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.016464993615201304, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.01662305230149532, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.019960845889189605, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.023575171751625143, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.020424995624850294, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.022780390998079086, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.023116359037670658, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.021953389387634734, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.023378481468715864, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.025692779389009157, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.027166204084637977, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 3.12721435546875, "validation/loss_best": 3.134291172027588, "validation/acc_best": 0.07954964931709117, "validation/f1_best": 0.023575171751625143} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 3.127321674823761, "train/grad": 0.07400911960750818, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.133560791015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131192626953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130635986328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130341796875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1301513671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13015380859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.130052490234375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.130054931640625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129991455078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129906005859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12984619140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1298095703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129718017578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.129619140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.129478759765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12935302734375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1291943359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12900146484375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12868896484375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.128441162109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.128095703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.127601318359375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.127186279296875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.126630859375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.126083984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.125543212890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.124713134765625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.123673095703125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12286376953125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.122130126953125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.121197509765625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1202294921875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.11936279296875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1185205078125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.117767333984375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.117266845703125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.117208251953125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1175518798828126, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.11827880859375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1191748046875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1210113525390626, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.123409423828125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.126942138671875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.13119384765625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1364642333984376, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1449505615234377, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1523345947265624, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010033669606782496, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00996976230526343, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009906540396623314, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009874534881673754, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009859398603439332, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009851577768567949, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00984848740277812, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009848516113124787, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009850180516950786, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00985219303984195, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009854752037208528, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009858508128672838, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009862871230579913, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0098679853300564, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0098732483596541, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009878002619370819, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009883982848841698, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009889944819733501, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00989665879867971, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009902833371888846, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009910521900746972, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009918931068386882, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009930039232131094, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009943990691099316, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009960665721446276, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009982846938073634, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010004361760802567, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010024990441743285, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010053776826243848, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010092575757298619, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010132470116950572, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010173681098967791, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010237655567470938, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01030303126666695, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010390171569306404, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010491826559882612, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010619294743519277, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010753207763191313, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010908671910874546, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011117180625442416, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011301508143078535, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011478613172657788, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011741249957121908, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012014717478305102, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01234299293719232, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012646867253351957, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012950472270604222, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01341079132631421, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013757663229480386, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1276168823242188, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1263763904571533, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1251542568206787, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124579668045044, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1242988109588623, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241161823272705, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124027729034424, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123962163925171, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123908758163452, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1238598823547363, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1237974166870117, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1236965656280518, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1236190795898438, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.12349271774292, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.12337064743042, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123262405395508, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1231632232666016, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123016595840454, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1228601932525635, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1227333545684814, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122544765472412, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1223549842834473, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.122122287750244, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.121868371963501, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1215999126434326, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1212704181671143, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1209914684295654, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.120781898498535, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.120589017868042, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1204257011413574, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1202046871185303, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.119873046875, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.119036912918091, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.118009328842163, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.116912841796875, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1165311336517334, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.117252826690674, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.118746280670166, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.120945930480957, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1232171058654785, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1242897510528564, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.125678539276123, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.129134178161621, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.134660005569458, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.143000364303589, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.14925479888916, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.146247148513794, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.13210129737854, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1262481212615967, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0769656699889258, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07788851974898486, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07973421926910298, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07604282022886674, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06976744186046512, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07438169066076043, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0769656699889258, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.073827980804725, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06921373200442968, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.067921742340347, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.004963245933900562, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.004963245933900562, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005215130628296858, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.006592568190501028, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008736714623982086, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00932855486455149, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.009481739386836158, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.00985462255532907, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.009919859651013845, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.009852416989580335, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009902471480851943, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.010554567719871547, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.014645412204167174, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.018496060511681872, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.021404598415188835, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.02111237456635352, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0224975600339902, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.023109319768476466, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.024784898019264954, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.0236407653295886, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.023310435909753017, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02528941435932718, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.030077422441981777, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03093258244038342, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02748026319381426, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.01885250129990507, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.015239792805711474, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.016106224453298026, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.01885520026565442, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02101772873461008, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0200133429253591, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.025100683646871774, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.030436928137814828, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 3.117208251953125, "validation/loss_best": 3.120945930480957, "validation/acc_best": 0.0828719084533038, "validation/f1_best": 0.030077422441981777} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 3.1240129494667053, "train/grad": 0.07524566005915403, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.132427978515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.131463623046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13047607421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.130137939453125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129993896484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12990966796875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12983642578125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.129837646484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129686279296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129605712890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12945068359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.129395751953125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.129251708984375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129088134765625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.128907470703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.128687744140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.128375244140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.128179931640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1279345703125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12740966796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.127108154296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12658203125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126107177734375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12548828125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.124656982421875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12405517578125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.123387451171875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.122510986328125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12134033203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.120196533203125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.119268798828125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.117958984375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.11667724609375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.115296630859375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.11389892578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.112611083984375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.111402587890625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.110428466796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1098681640625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.109986572265625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1104248046875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1119744873046873, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.114044189453125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.117620849609375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.122071533203125, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.126693115234375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.134273681640625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.140882568359375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01022511680610478, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010173392344731837, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010123960019554942, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010100457912776618, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010091704479418696, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010087423215154559, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010086789783090353, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010087250147480518, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010088954959064722, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010091706784442067, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010094243690837175, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010097497708629817, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010100972766522318, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010105661724228412, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010110747055150568, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01011485353577882, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010120808365754783, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010128275253809988, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010137175300624222, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010145427118986845, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010155647918581963, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010166282998397946, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010178921041078865, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.01019369857851416, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010210500161629171, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010232813239563257, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010254656774923205, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010275975645054131, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010308514325879514, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010348060661926865, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010386072429828346, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010422018906101584, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01047682924894616, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010529582093004137, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01060182936489582, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010682635621633381, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010778649288695305, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010879352528136224, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011003420688211918, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011184871818404645, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01134654345922172, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01151399734430015, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011769711226224899, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012029440263286234, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012363982317037881, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012706467867828905, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01300937716383487, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013417953331954778, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013710799273103475, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.126709461212158, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1257035732269287, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1248064041137695, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124385356903076, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1242072582244873, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240992546081543, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124058485031128, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1240320205688477, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1240007877349854, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1239798069000244, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1239631175994873, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1239352226257324, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1239171028137207, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1239211559295654, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1239376068115234, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1239686012268066, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.124016523361206, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1241023540496826, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1241824626922607, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.124281883239746, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1244282722473145, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1246113777160645, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124802350997925, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1250388622283936, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1252949237823486, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1256401538848877, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1260344982147217, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.126477003097534, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1272222995758057, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1283254623413086, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1295669078826904, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1309409141540527, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1330907344818115, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.135133981704712, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.137502908706665, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.139554977416992, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1409454345703125, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1403567790985107, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.137155294418335, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.131936550140381, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.128971576690674, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1279098987579346, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.129605531692505, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1329472064971924, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.134953498840332, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.131134510040283, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.124718189239502, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1262505054473877, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1557424068450928, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07401255075673681, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07179771133259505, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07475083056478406, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07807308970099668, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07715023994093761, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06884459210040605, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06902916205241787, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06939830195644149, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07198228128460686, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08047249907715023, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07456626061277224, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.00496410790783837, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.004967558799675587, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.005443713508229637, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005651061901061901, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.006988009683049024, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.008554361821780472, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.009819216483637339, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.010227272727272729, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.010751941152506744, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.014152974887749583, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.017030460799911634, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01842259001925437, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.019443646607759647, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.020186748808645124, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.021397285483649876, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.021813304431572575, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.0263738693867277, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02955014449233635, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.028448642998001126, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.019305072559661022, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.014251560446109292, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.01345557565134773, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.015610476875190843, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02275318264511773, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.030283552379647555, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.020218908320143402, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.134273681640625, "validation/loss_best": 3.1262505054473877, "validation/acc_best": 0.08047249907715023, "validation/f1_best": 0.030283552379647555} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 3.122642993927002, "train/grad": 0.07302932612597943, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1334033203125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.132672119140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13208984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131798095703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.131666259765625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.131561279296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.131536865234375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.131488037109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13134765625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.131217041015625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.13109619140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.130980224609375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.13082275390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.130638427734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1303271484375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.13013916015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.129769287109375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129464111328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.129056396484375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.128709716796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12814453125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.127685546875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12703857421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126466064453125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.125650634765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.124840087890625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.123978271484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1232177734375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.122191162109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1208544921875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.119853515625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.11888427734375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1173779296875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.116146240234375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.11455810546875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1131396484375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.111602783203125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.110335693359375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.108973388671875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.10775146484375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.107178955078125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1070220947265623, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.107177734375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.10773193359375, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1085540771484377, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1100616455078125, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.112379150390625, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.11723876953125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.12369140625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010027237976901233, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009985729514155536, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.0099483402678743, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009933376526460052, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009928734654095024, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00992684402037412, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00992630586028099, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00992721139220521, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009929055047687143, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009930426208302378, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009932405902072788, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009935142137110234, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00993755237199366, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009941726450342685, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009945050671231002, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009948909503873438, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009953206735663116, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009958891165442765, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00996524006128311, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00997066345065832, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009977824026718736, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00998550538206473, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009996629795059562, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010008304410148413, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010023003986570984, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010042144281324, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01006011297693476, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010078006028197705, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01010307743679732, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010133272239472716, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010161231628153473, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010187818056438118, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010228551023174078, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010270995595492423, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010329249890055507, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010395819772966206, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010477843142580242, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010562652344815434, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010662214544136078, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010803271171171218, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010932359090074896, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011067865316290408, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011280810500029475, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01148662150837481, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011715858490206302, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011930247901473194, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012115858462639153, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012404732285067438, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012768628466874361, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1261496543884277, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1253209114074707, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1246185302734375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1243247985839844, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124207019805908, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241419315338135, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1240837574005127, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1240622997283936, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1240079402923584, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1239616870880127, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1239092350006104, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1238327026367188, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1237454414367676, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1236250400543213, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1234889030456543, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.12337064743042, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123194932937622, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1230223178863525, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.122849941253662, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1226823329925537, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122553825378418, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1224238872528076, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.122330904006958, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1222891807556152, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1222729682922363, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1222591400146484, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.122328519821167, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1224141120910645, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1226320266723633, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1229989528656006, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1232638359069824, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.123382091522217, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.12325382232666, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.122727870941162, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1216518878936768, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1202144622802734, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.118804931640625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1180026531219482, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.118659019470215, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1223676204681396, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1269025802612305, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1304545402526855, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.131362199783325, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1273176670074463, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1211345195770264, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.12152099609375, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1301209926605225, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1484642028808594, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.169008731842041, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06976744186046512, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07327427094868956, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07715023994093761, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07881136950904392, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0784422296050203, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08010335917312661, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08231819859726837, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08951642672572906, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08896271686969362, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08213362864525656, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0710594315245478, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.004953937076308013, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005547425409239578, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.006441441824233411, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0071964630495005176, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.007718759486562625, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.008406266280378754, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0085484299716676, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.008690853258171712, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00872707050367041, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.00876622088492991, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.00887712469283085, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.008668068229259855, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.008401209652982316, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.008618747754844181, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009291402713790696, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.008903018727107305, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.010182441289246552, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.010940242742548718, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.012190317434204354, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.01415252262039037, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.016821948794728498, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.021275868990179025, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.024339984247100214, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.025008912738981034, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.02565805407044051, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.02838606374277854, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03169137166370504, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.035841026575408226, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03354926450777674, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03578948211156043, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.029673853496281002, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.023394744426430567, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 3.112379150390625, "validation/loss_best": 3.1301209926605225, "validation/acc_best": 0.09154669619785899, "validation/f1_best": 0.03578948211156043} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 3.11629500746727, "train/grad": 0.0718662533722818, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128389892578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12765869140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12697509765625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12673828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126632080078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1264794921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.126351318359375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126295166015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126220703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12607421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12594970703125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125782470703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125648193359375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12533203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125078125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1249169921875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.124559326171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124219970703125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123775634765625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12341552734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12296875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.122349853515625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.121749267578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.120982666015625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.120233154296875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.11928955078125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.1184716796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.11763671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.116597900390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.11519287109375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.114097900390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.112945556640625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.11146484375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.110120849609375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.10855712890625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.107015380859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.105426025390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.104078369140625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.102523193359375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.100538330078125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.099254150390625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.098125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0972955322265623, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.09705810546875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.097589111328125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0992041015625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1017816162109373, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.106619873046875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1127978515625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009903070582076907, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009864328503608704, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009830280765891075, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009818230986129493, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009812942210119217, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009810598988551647, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009810013552196324, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009810513770207762, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009811587315052748, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009813029989600182, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009814357440918684, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009816446546465159, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009818400784861297, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009821904057171196, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009825029757339508, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009828197518363595, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009832494279835373, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009837453500367702, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009842977679800241, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009848726580385119, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00985538819571957, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009862353061325848, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009870922982227057, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009881694098003208, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009894848333206028, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009911769884638488, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009930127474945039, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009948062144685537, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009974634451791644, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010010795681737364, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010045539271086455, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010078940121456981, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010123914473224431, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010168117142748088, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010224246552679688, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010286723896861076, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010360089973546564, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010436642384156584, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010520693045109511, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010620761066675186, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010702719211112708, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010788156816270203, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010919100465252995, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011052351363468915, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01124437578720972, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011506078159436583, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011780410034116357, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012175007280893624, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012537060498725622, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1257822513580322, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125089645385742, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1245338916778564, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124295949935913, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124206304550171, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241648197174072, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1241376399993896, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124096155166626, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.12404727935791, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12402081489563, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1239473819732666, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1238834857940674, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1237778663635254, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123650312423706, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.123511552810669, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123375177383423, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1232128143310547, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1230227947235107, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.12278151512146, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1225345134735107, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122239828109741, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.121889591217041, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1215314865112305, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.121138334274292, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120692253112793, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.120136260986328, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.119584798812866, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1190717220306396, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1183388233184814, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.117459297180176, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1166272163391113, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.115825653076172, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1147477626800537, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.113710880279541, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1124706268310547, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1111128330230713, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1097192764282227, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1086971759796143, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.108147144317627, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.107858896255493, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1077873706817627, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1079554557800293, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.108590602874756, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.108555316925049, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.106468677520752, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1054115295410156, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.110071897506714, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.119751214981079, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1247339248657227, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.067921742340347, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07179771133259505, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07419712070874862, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07327427094868956, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0754891103728313, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07401255075673681, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07308970099667775, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07216685123661867, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07678110003691399, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08065706902916205, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0799187892211148, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0769656699889258, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07770394979697305, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049479166666666664, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.004949635290031261, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005153656190858486, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006070888769362896, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.006445334026344282, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.007061935610721842, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.00821664057876801, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.009265106657304881, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.010900602236418198, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.01260868923657956, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0156417870704724, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.017906164621272477, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.018728197212254428, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.020672139466323597, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.02254826615480233, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.02375451996584736, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02462703853703933, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.025352899689332815, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.02495773725318846, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02651085541539255, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.02503415941503802, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.02133781553948956, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.020008641853974638, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.023127555504968287, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02754892385589817, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.026476407446251984, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.02340059759511394, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.023081274946562983, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.0992041015625, "validation/loss_best": 3.1054115295410156, "validation/acc_best": 0.08065706902916205, "validation/f1_best": 0.02754892385589817} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 3.117402163743973, "train/grad": 0.07277192179113627, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13021240234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1297216796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129442138671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12934326171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129317626953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12928466796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12923095703125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129144287109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1290576171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.128922119140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128746337890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1285498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128353271484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.128013916015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.127852783203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12745361328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.127076416015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12663330078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.126190185546875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.125679931640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1251025390625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.124296875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.123590087890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.122806396484375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.121668701171875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.120760498046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.119971923828125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.118619384765625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.117080078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.11572021484375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.11439453125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.11267578125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.11103759765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.10923828125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1072821044921874, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1050537109375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.1029302978515627, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1007366943359376, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.098216552734375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.096695556640625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0955450439453127, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0945343017578124, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.09419677734375, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.094818115234375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0967071533203123, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.099345703125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.103714599609375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1084466552734376, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01005577927455306, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0100231446698308, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009997397277038545, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009988894669804722, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009986274254042655, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009985485987272114, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009985436899587512, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009986673733219504, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009988314234651624, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009989630852360279, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009991518249735236, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009993357241619379, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009995766882784664, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009998805311042816, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010002653796691447, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010005738874897361, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010010011084377766, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01001467158086598, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010020488251466304, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010025895333383232, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.01003203168977052, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010040006786584853, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010048624379560351, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010059121425729244, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.01007119981572032, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.01008646970614791, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.01010239533847198, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.01011679976945743, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010139164295978845, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010167686846107244, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010197089100256563, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01022539054043591, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01026644090656191, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010306376211810858, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01035826509585604, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010412849895656108, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010474086441099643, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010534904992673545, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010608588820323348, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010717400223948062, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010818287474103272, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010916636113543064, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011052091922610998, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01117802475579083, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01134370846208185, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011555792586877943, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011760109367314727, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012030121271964163, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012275418271310628, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1255218982696533, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1249301433563232, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1244513988494873, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124263048171997, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124194383621216, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241486072540283, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124117136001587, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124086856842041, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.12402081489563, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123955011367798, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1238901615142822, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1237945556640625, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1236798763275146, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1235432624816895, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1233649253845215, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1232213973999023, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123035430908203, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122818946838379, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.12256121635437, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1223320960998535, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1220455169677734, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1217739582061768, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.121446371078491, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1211140155792236, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120753049850464, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1202776432037354, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1198313236236572, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.119420289993286, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.118849992752075, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.118090867996216, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.117366313934326, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1166720390319824, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1156744956970215, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1147375106811523, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1136553287506104, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.112586259841919, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.11137056350708, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.110179901123047, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.109055280685425, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1085851192474365, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1089048385620117, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.109356164932251, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1100099086761475, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1110527515411377, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.112685441970825, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1155412197113037, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1184639930725098, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.121690273284912, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1255950927734375, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07235142118863049, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06976744186046512, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07124400147655961, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07198228128460686, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07364341085271318, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07272056109265411, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07069029162052418, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06921373200442968, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06829088224437062, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07032115171650055, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07290513104466592, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07308970099667775, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07364341085271318, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.004949635290031261, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005359423462871739, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005910763203159839, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.006423150788310221, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.007320182836749977, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.007906457822684154, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.008797853742169447, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01005393394297964, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.011546430796280123, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.014050240287941081, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01658474876945479, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.018438779952760647, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.021244013235991326, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.02147363711527452, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.020344093198354684, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01827813775502022, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01602359119808161, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.015127381057057196, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.016349900183930018, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.018684624153849208, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.023771592099350026, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.025663894459231975, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.024978067904809706, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.022792157933962373, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.02128028810433689, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.020850035155438137, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.020378954595300255, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.022812651418932173, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0259685321278559, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.024315261832161875, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.023761308664843054, "id_best": 40, "lr_best": 0.0042, "wd_best": 0.05, "train/loss_best": 3.096695556640625, "validation/loss_best": 3.1089048385620117, "validation/acc_best": 0.07364341085271318, "validation/f1_best": 0.024978067904809706} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 3.115415987968445, "train/grad": 0.07262190951034427, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12961181640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129193115234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128800048828125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128624267578125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12861572265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128524169921875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12850830078125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128443603515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.128338623046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128173828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.128031005859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127862548828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12765869140625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.127457275390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.127215576171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12699462890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126666259765625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.126370849609375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.125933837890625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.125440673828125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.124925537109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1244189453125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.123631591796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.122886962890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.122086181640625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.120955810546875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12004638671875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.118895263671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.117666015625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.115963134765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1143896484375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.11301025390625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.110849609375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.109013671875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.10663330078125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1043603515625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.10183837890625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0995751953125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0973114013671874, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.09495849609375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.093385009765625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0922332763671876, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.09135009765625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.09094970703125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0911126708984376, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0916033935546876, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0927020263671876, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.094700927734375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0974688720703125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010117278906982392, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.0100873628933914, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010063132653012872, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010054572049994022, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010051611659582705, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01005061216186732, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010050035705789924, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010050761771854013, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010051770841237158, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010053107135463505, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010054419508669525, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010055933666881173, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.01005792761221528, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010060279679019004, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010062374647241086, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010064928927458822, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.01006832865299657, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01007294240174815, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.010077269941102713, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010081576507072896, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010086313735228032, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010092553508002311, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010098909537773579, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010105482873041183, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010114265384618192, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010124513888731599, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010133622544817627, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010142871253192425, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010156002051662654, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010173341219779104, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010190144048538059, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01020818670745939, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010233084347564727, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01025844995630905, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010292695970274508, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010331452616956085, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010380174114834518, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010435211912263185, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010505799474194645, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01060983415460214, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01070103155914694, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010788247312884778, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010917268509510905, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011044172048568725, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011206279888283462, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011389453916344792, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011542309338692576, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01172915247734636, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011921933628618717, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1253514289855957, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124829053878784, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124405860900879, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242361068725586, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124181032180786, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241347789764404, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124077558517456, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124041795730591, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1239733695983887, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123904228210449, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1238327026367188, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123717784881592, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1236019134521484, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1234519481658936, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1232895851135254, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123142719268799, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1229326725006104, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1227073669433594, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1224491596221924, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1222026348114014, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1218719482421875, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1215004920959473, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.12107253074646, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120584011077881, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120069980621338, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1194279193878174, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.118809223175049, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.118230104446411, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1174051761627197, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1163108348846436, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.115251064300537, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.114246368408203, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1128170490264893, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.111490249633789, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1099207401275635, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1084413528442383, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1069865226745605, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1057498455047607, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1044864654541016, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.103302478790283, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1028614044189453, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.102933406829834, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1034514904022217, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1041195392608643, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.104801893234253, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.105455160140991, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.106623649597168, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.108708143234253, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1113359928131104, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06921373200442968, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07604282022886674, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08047249907715023, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.082687338501292, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.0843484680693983, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08600959763750461, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08471760797342193, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08213362864525656, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08139534883720931, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0812107788851975, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08361018826135105, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08785529715762273, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08656330749354005, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.004948775829137003, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.004937735302635389, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005359575335584777, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006008113488544267, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.006252118517628929, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006172285781652256, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00668455536064359, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.007404365631641739, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.007623312450091159, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.009438762641396155, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.009910969609727146, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.01098235761017497, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.012874961844668159, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.015517374587650916, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.017158024115198647, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.019677813242470314, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.02156617085618612, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.0221490145072545, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.022642454624637706, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.024136719135984853, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.023322862980893134, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02256503285578887, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.022353341552558414, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.022429420405475086, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.022903889281795705, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.023382931399625734, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02598473237612765, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.026061873371546192, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.02725652633994351, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.026895782265778156, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.094700927734375, "validation/loss_best": 3.108708143234253, "validation/acc_best": 0.09154669619785899, "validation/f1_best": 0.02725652633994351} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 3.109079496860504, "train/grad": 0.07059513637796044, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1276318359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127119140625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.126715087890625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12647705078125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126282958984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126219482421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12614501953125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.125972900390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12567138671875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12557861328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125399169921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125220947265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12495849609375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12462890625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.124296875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.123948974609375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12356201171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12301513671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1225, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121861572265625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.121131591796875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12027587890625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.119344482421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.118248291015625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.116976318359375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.115845947265625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.114659423828125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.113060302734375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.111126708984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1092578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.107603759765625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.105184326171875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.10304931640625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.100404052734375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.09764892578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.094793701171875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.092015380859375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.088944091796875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.08515625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.082437744140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.08003173828125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0773779296875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.075430908203125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0737384033203123, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0726324462890626, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0723773193359376, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0729766845703126, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0741033935546875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00994467368349433, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009920434313826262, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009903033103328199, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009897966827265918, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009896203381940723, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009895657827146352, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009896017550490797, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009896422121673822, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009897168669849634, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009897583113051951, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009898046222515404, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009899311047047377, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009900191787164659, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009901555536780507, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00990307847969234, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009903799800667912, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009905216458719224, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009907402363605797, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0099096320848912, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009912400122266263, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009914906835183502, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009917793655768036, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.0099215503083542, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009925643308088183, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009930449745152146, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009937042065430432, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009943809031974525, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009949896731413901, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009959271114785223, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009971029099542648, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009982463228516281, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009994828887283803, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010012157789897174, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010027687191031873, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010050238075200469, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010074667283333838, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010103704100474715, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01013648055261001, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010176964420825243, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010237146941944957, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.0102900161431171, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010340558115858585, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010410932989325375, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010475255805067718, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010560169864911586, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01066371709574014, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010765114664100111, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010898115311283619, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011023172475397587, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125243663787842, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1247520446777344, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124354124069214, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242003440856934, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1241579055786133, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240973472595215, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124056339263916, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1239981651306152, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1239235401153564, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123838424682617, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1237685680389404, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123659372329712, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123527765274048, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1233720779418945, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1232104301452637, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123044967651367, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1228559017181396, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1226372718811035, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1223971843719482, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1221420764923096, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1218655109405518, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1215288639068604, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.121187925338745, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1207656860351562, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120354413986206, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.119839668273926, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.119356155395508, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.118899345397949, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1182427406311035, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1173858642578125, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.116576910018921, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.115767240524292, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1145358085632324, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.113341808319092, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1117377281188965, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1100246906280518, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1080546379089355, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1060736179351807, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1038472652435303, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.101011037826538, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0988123416900635, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0969629287719727, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0948026180267334, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0932867527008057, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0919575691223145, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0909223556518555, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0903148651123047, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.090453624725342, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0914735794067383, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0769656699889258, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07954964931709117, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08250276854928018, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0843484680693983, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08453303802141011, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08748615725359911, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08785529715762273, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08859357696567, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08988556662975268, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0917312661498708, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08822443706164636, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.004948775829137003, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.004942028985507246, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005748624482629438, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005926900202601137, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005862208372888182, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0065711494790795634, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.00701568984965335, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.007192582329334942, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.008342892784171536, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009740505811212871, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.010200758531598101, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.011415690415518672, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.013666234111368919, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.016246982136827785, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.01907102106434593, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.021538520009528713, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.025785564493571885, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.028468201489825182, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.030059417692464216, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03297444680619292, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03437776418414562, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.035215166167321336, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03623924229607595, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.038182987785879884, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03642785410441259, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0362437833998382, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03614149435567336, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03855285466779476, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04047699269641531, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.046982520234702035, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.047722861848174224, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.0729766845703126, "validation/loss_best": 3.090453624725342, "validation/acc_best": 0.0917312661498708, "validation/f1_best": 0.046982520234702035} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 3.1088414442539216, "train/grad": 0.07043232871219515, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12849609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127947998046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127481689453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1272412109375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127078857421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127001953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12690185546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.126788330078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126668701171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126544189453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12638427734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.126102294921875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125843505859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12552490234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125264892578125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12494140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12458740234375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124039306640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123504638671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12296875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1222509765625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.121539306640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.120667724609375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.119703369140625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.118638916015625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.11741943359375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.11608154296875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.114805908203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.11312744140625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.110977783203125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.109095458984375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.10729248046875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.104755859375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.10249267578125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.099774169921875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.09697265625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.094000244140625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.091123046875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.08797119140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.084208984375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0814111328125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.079022216796875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0761529541015626, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.07387451171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0717242431640623, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.069951171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0690643310546877, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0686474609375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0691741943359374, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.00996455539483577, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009944296767935156, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009932089843787253, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009929680104833097, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009929174224380404, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00992937601171434, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009929359357338399, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009929738864302635, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009930362235754728, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009930743314325809, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009931186018511652, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009931670965161175, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009932127597276122, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009933057292364537, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009934012915473432, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009934790167026222, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009936317091342062, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009937755754217506, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00993942137574777, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009941059262491763, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009942814831156284, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009945288633462042, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00994768423261121, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009950710467528552, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009954693107865752, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00995956698199734, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009964029968250543, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009968630308285355, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009974181468132884, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009983036480844022, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009991375098470598, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009999837439972908, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010012575145810842, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01002539810258895, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010041908149141819, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010059909091796725, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010082222507335245, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01010553156491369, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010133734238334, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010174391770269721, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010210614069364965, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010244060000404715, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010290245835203677, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0103354485752061, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010392023248132319, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010460151452571153, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01052753810537979, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010621843351982534, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010713560252916067, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1251730918884277, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1246917247772217, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124316453933716, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1241774559020996, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124117136001587, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240439414978027, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1240057945251465, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123945474624634, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123861312866211, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1237740516662598, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123699426651001, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123565673828125, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123455047607422, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123279333114624, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1231117248535156, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1229658126831055, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1227638721466064, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122533082962036, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.122297763824463, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.122063159942627, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.121732234954834, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1214287281036377, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1210474967956543, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120607852935791, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120124101638794, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1194798946380615, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.118861675262451, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.118252754211426, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1173651218414307, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1161835193634033, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.115028142929077, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1139044761657715, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.112258195877075, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1107077598571777, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.108755588531494, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.106745481491089, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.104546308517456, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.102421998977661, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1001458168029785, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0974135398864746, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.095442056655884, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.093920946121216, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.09228777885437, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0913589000701904, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0908501148223877, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0908050537109375, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0909576416015625, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0910820960998535, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.091355562210083, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07862679955703211, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08084163898117387, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08416389811738649, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08490217792543374, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08324104835732743, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08545588778146918, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08527131782945736, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0873015873015873, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08859357696567, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09062384643779993, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09007013658176449, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.004949635290031261, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005153112606999578, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005759896379517722, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005912050841409473, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.006186357257044962, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006402625152625153, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.006840566113778978, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.007821911290958636, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.008310357079316485, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.008341226476475816, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.008497871337786924, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.009167677062627555, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.010020705168638922, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.010203990132878945, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.01057954566790946, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.011569622838810445, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.013470909712770226, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01657736635582163, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.020089751437543015, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.023150019828978158, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.025647414173748814, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.029703395957975633, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03224446082909944, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0356953964008965, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03597063917912282, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0350430651945984, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.035919485597416735, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03526706226435898, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.035892078221295726, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03520684348328774, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03553268566715281, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.035528408577293405, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.0686474609375, "validation/loss_best": 3.0910820960998535, "validation/acc_best": 0.09062384643779993, "validation/f1_best": 0.03553268566715281} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 3.110043703317642, "train/grad": 0.07018429078161717, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1304052734375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129901123046875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1296630859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129515380859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12936767578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129364013671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129298095703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12910400390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12896484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128819580078125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128394775390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.128173828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.127840576171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1275439453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.127244873046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12689453125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.126319580078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1257177734375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1251513671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.124422607421875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12369140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12283203125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12182861328125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.120787353515625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.119456787109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.117960205078125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1167626953125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.115078125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.11293212890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.110947265625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.109083251953125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.106480712890625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1041162109375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.1012255859375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.098387451171875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0950927734375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.092010498046875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.08869140625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.08451416015625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.081231689453125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.07846923828125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.075223388671875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0725640869140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.06998046875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.067625732421875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0659307861328124, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0645501708984373, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0639898681640627, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010003646672703325, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009980094579514116, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009965110174380242, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009960973230190575, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009959816366899759, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009959114992525428, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009959227326326071, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009959392563905567, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009959692612756043, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009960039947181941, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009959777656476945, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009960359134711326, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009960786604788155, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00996086371364072, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009961716507095843, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009962291363626719, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009963124552741646, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009963728862348944, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00996461314847693, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009965691366232932, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00996619540732354, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00996711514191702, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009968602946028114, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009970446662046016, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009972785939462483, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009975314200855791, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00997737044468522, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009979835716076196, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009984201127663255, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009988580651115625, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009993034794460983, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009996387418359518, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010001287613995373, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010006461774464697, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010013707831967622, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010020497424993663, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010029074687045067, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010038326482754201, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01004991274094209, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01006527985446155, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010080850315280259, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010096830320544542, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010122715993784368, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010149541655555367, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01018749370239675, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010234442732762545, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010280562124680728, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010344885243102907, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010403784443624317, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1251444816589355, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124667167663574, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1242945194244385, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124159812927246, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1241016387939453, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240432262420654, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124004364013672, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123931407928467, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123847246170044, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1237549781799316, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1236798763275146, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1235666275024414, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1234397888183594, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123260736465454, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.123110055923462, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122941493988037, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122770071029663, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1225321292877197, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1222739219665527, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.122032880783081, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.121727466583252, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.121400833129883, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1209945678710938, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1205341815948486, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120016574859619, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.119332790374756, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1186954975128174, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.118053436279297, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1171457767486572, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1160082817077637, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.114961862564087, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.113985538482666, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1126153469085693, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1113736629486084, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.109842300415039, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1082534790039062, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1064565181732178, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1046626567840576, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.102663516998291, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.100104570388794, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0980610847473145, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0963213443756104, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.094045639038086, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0921785831451416, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.090207576751709, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.088273763656616, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0868444442749023, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0855185985565186, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.084916591644287, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07678110003691399, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.0784422296050203, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08416389811738649, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08600959763750461, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08767072720561092, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08988556662975268, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09228497600590624, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09228497600590624, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09449981543004798, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049479166666666664, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049504950495049506, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005359423462871739, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0057453606506962795, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005921352452289005, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0058588456899266545, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0066619920684259995, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.007009327549804594, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.007189664821923753, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.00836025293602564, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009149159826368868, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.00936040535945389, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.009341378409912652, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.010436267187445064, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.01147213535342823, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.013569254511704957, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.015519228830828596, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.017884386672931064, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.020404549140998672, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.023842066131002943, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.026445176036001813, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.028701932590009988, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.0310312917335497, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03277137333330362, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.034079567848761115, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.036047162759042024, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.036268343308030616, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03621801897037789, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03785696544385744, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.037761532019092874, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.037558153786259534, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.038688258007162094, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.0639898681640627, "validation/loss_best": 3.084916591644287, "validation/acc_best": 0.09449981543004798, "validation/f1_best": 0.038688258007162094} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 3.1067295932769774, "train/grad": 0.06964751791208983, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1282861328125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127783203125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127493896484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12737548828125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127259521484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12723876953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12718994140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127039794921875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126856689453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126690673828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12647216796875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.126285400390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12603759765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.125640869140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125335693359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.124952392578125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.124547119140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124005126953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12340087890625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.122781982421875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121947021484375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.121185302734375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.120255126953125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11921142578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.117998046875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1166162109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.115257568359375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.11394775390625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.112218017578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.10990234375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.107850341796875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.105931396484375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.10324951171875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.100809326171875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.097886962890625, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.094864501953125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.091492919921875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.08824462890625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.08468505859375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.08027099609375, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.076717529296875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0737481689453126, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.070020751953125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.066904296875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0638336181640624, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0608636474609376, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0587396240234375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0567901611328123, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0556378173828125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009966653955634683, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009943571982439607, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00993011808488518, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009926103700418026, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00992446582764387, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009923731114249677, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00992344788275659, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009923550691455603, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009923710729926824, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009923939830623568, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009923679430503398, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009923646817915141, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009923892924562097, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009923997591249645, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009924067880492658, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009924025731161237, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0099243237497285, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009924774456303567, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009924103172961623, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009924330431967974, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0099245519307442, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009924625437706709, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009925418284256011, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009925334276631474, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009925684549380094, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009926209130790085, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009926282120868563, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009926480937283487, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009927754644304515, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009929511304944754, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009931411070283502, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009933211945462973, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009935713796876371, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009938346701674164, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.00994163499912247, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009944379392545671, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009948648596182465, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009952352244872599, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009957372369244695, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009965889565646648, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009971856917254628, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009978714424651116, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009989000442437827, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009999831938184798, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010015013187658042, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010033864334691316, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010052794613875449, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01007924011675641, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010104793710634113, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1251332759857178, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1246635913848877, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1242804527282715, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124159336090088, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124084711074829, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124035596847534, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123992443084717, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123906373977661, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.12382435798645, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1237361431121826, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123657464981079, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123528480529785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1234192848205566, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1232151985168457, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.123065710067749, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1229171752929688, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1227285861968994, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1225013732910156, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1222293376922607, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.121969699859619, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.12165904045105, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1213061809539795, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.120906352996826, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120410919189453, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1198501586914062, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.119145393371582, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1184701919555664, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.117753505706787, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.116783380508423, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.115530014038086, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1143438816070557, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1131906509399414, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1115570068359375, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1099884510040283, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.10805082321167, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.106045961380005, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.103764057159424, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.101546287536621, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0990993976593018, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0960607528686523, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.093750476837158, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0917885303497314, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0893313884735107, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.087393045425415, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0853819847106934, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.083469867706299, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0820600986480713, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0807764530181885, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.080014228820801, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.073827980804725, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07936507936507936, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08453303802141011, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08527131782945736, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08564045773348099, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0843484680693983, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08527131782945736, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08619416758951642, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08674787744555186, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08656330749354005, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08748615725359911, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08896271686969362, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.004949635290031261, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.004941169651654784, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005563383890141423, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005925497051568043, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005856648613543263, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006276874965097448, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.007361609906903994, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.007889030531509104, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00855529671586198, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009090140034554413, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009571720582765364, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.010437522241529879, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.010686358102182455, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.010862698514309583, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.012317084781510739, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0146694953330437, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.016859520143299236, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01818548301104173, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.021300359675869452, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.023833670112337585, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.027038589484251457, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02905738053575906, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03302088853664686, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.033689380089476605, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.033981176555654496, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03416695936793975, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.034956597247166266, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.035365833552314464, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03676354247255857, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03664995597070719, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03727579894250645, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03812413410560584, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.0556378173828125, "validation/loss_best": 3.080014228820801, "validation/acc_best": 0.08896271686969362, "validation/f1_best": 0.03812413410560584} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 3.103922312259674, "train/grad": 0.06961120944470167, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1254345703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124820556640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124407958984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124154052734375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12400146484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12394775390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12387939453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12373291015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.123626708984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12350341796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12333984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12308837890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122894287109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12263427734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.122313232421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.121968994140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.121597900390625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12104736328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1205322265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12001953125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1193505859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1186181640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11773193359375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1166357421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.115625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.11419921875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.112926025390625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.111619873046875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.109952392578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.107740478515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.105853271484375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.103929443359375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.101248779296875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.098807373046875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.095849609375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0926904296875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.08932861328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0860791015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0823876953125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0777978515625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0741943359375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0710986328125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.067176513671875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0640203857421877, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.060611572265625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0574212646484376, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0549578857421875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0525286865234373, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0508709716796876, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009988599719945342, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00996624396648258, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009951655154582113, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009946932750754058, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009945126795209945, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009944827614817768, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009944298618938774, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00994451112812385, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00994458890054375, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009944668374955654, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009944652104750276, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00994472311809659, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00994462929200381, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009945204856339842, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00994531948817894, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009945333909709007, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009945347460452468, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00994453431572765, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009944413951598109, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009943714293185621, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00994325171923265, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009942507648374885, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009942451482638717, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00994170297170058, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009941658831667154, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009941030864138157, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009939971086569131, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009939211618620903, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009938785021658987, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00993849705439061, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009937966661527752, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009937261783052235, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009936727022286505, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009935967219062149, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009935324070975185, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009934829068370163, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009935041184071451, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009934556663502007, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009935512857045978, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009936560783535242, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009938873301725834, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009939522668719291, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009941713861189782, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009943576699588447, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009945511356927455, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009948413020465523, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009951188846025616, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009955739979632198, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009959984845481813, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125131845474243, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1246607303619385, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124281167984009, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124157190322876, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1240861415863037, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240317821502686, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123997211456299, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123903751373291, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1238269805908203, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.12373685836792, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1236655712127686, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1235392093658447, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123422861099243, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123225688934326, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1230671405792236, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122922420501709, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1227335929870605, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1225104331970215, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1222236156463623, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.121976852416992, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1216647624969482, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1213042736053467, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1209142208099365, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120424270629883, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1199002265930176, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1191697120666504, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.118490695953369, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.117809772491455, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1168460845947266, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.115588426589966, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1144182682037354, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1132888793945312, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1116750240325928, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.110140562057495, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.108253240585327, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.106294870376587, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.10412335395813, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.101956844329834, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0995826721191406, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.096662759780884, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0944011211395264, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.092435598373413, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0899853706359863, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0880088806152344, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0858235359191895, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0837409496307373, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0821382999420166, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0805742740631104, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0795340538024902, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.067921742340347, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06939830195644149, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07567368032484312, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07807308970099668, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08028792912513842, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08213362864525656, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08342561830933924, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08305647840531562, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.082687338501292, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08305647840531562, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0843484680693983, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0858250276854928, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08674787744555186, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08767072720561092, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08748615725359911, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.004948775829137003, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.004940310616597126, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005563383890141423, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005926900202601137, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005857742717951854, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006292634835966853, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.006836487661706397, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.007654657801919832, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.008339394751754197, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.008614344241939123, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009523957021521316, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.01034394716943772, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.01038049913026215, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.010755405423833903, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.01119347688423906, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.013055280257643706, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.015086531016047325, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.017093298904675123, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.018932696613871623, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.022209191856303392, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02510342333359855, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02786218218487403, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.029956806450617005, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03141443640660516, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.031457775699872216, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03191993450794219, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03273929332794582, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03354328561056511, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03475820107989186, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.035431570050803184, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03599413693633031, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.036243036078090554, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.0525286865234373, "validation/loss_best": 3.0805742740631104, "validation/acc_best": 0.08767072720561092, "validation/f1_best": 0.03599413693633031} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/config.yaml b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f998d18a8af5705e050930391f4fd80ba3f71b2e --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..752fc3de051cc959cf3cfd20cbedaafa0127ca3c --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 17, "eval/id_best": 41, "eval/lr_best": 0.0048, "eval/wd_best": 0.05, "eval/train/loss": 2.062237501144409, "eval/train/acc": 0.372568302652202, "eval/train/acc_std": 0.002469017416856133, "eval/train/f1": 0.3255660013374387, "eval/train/f1_std": 0.0025967055970697165, "eval/validation/loss": 2.452381134033203, "eval/validation/acc": 0.27260981912144705, "eval/validation/acc_std": 0.0053846242310042385, "eval/validation/f1": 0.21158476658860004, "eval/validation/f1_std": 0.00477650952012854, "eval/test/loss": 2.3251588344573975, "eval/test/acc": 0.3055658627087198, "eval/test/acc_std": 0.005318868133213203, "eval/test/f1": 0.24520047876166337, "eval/test/f1_std": 0.005280489915656855, "eval/testid/loss": 2.4315075874328613, "eval/testid/acc": 0.26855600539811064, "eval/testid/acc_std": 0.0054350775188430735, "eval/testid/f1": 0.21962484790439263, "eval/testid/f1_std": 0.005264704051085441} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..a5f43c7798b8615866a2e786075dd66fa6dfcd04 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 17, "eval/best/id_best": 41, "eval/best/lr_best": 0.0048, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.062237501144409, "eval/best/train/acc": 0.372568302652202, "eval/best/train/acc_std": 0.002469017416856133, "eval/best/train/f1": 0.3255660013374387, "eval/best/train/f1_std": 0.0025967055970697165, "eval/best/validation/loss": 2.452381134033203, "eval/best/validation/acc": 0.27260981912144705, "eval/best/validation/acc_std": 0.0053846242310042385, "eval/best/validation/f1": 0.21158476658860004, "eval/best/validation/f1_std": 0.00477650952012854, "eval/best/test/loss": 2.3251588344573975, "eval/best/test/acc": 0.3055658627087198, "eval/best/test/acc_std": 0.005318868133213203, "eval/best/test/f1": 0.24520047876166337, "eval/best/test/f1_std": 0.005280489915656855, "eval/best/testid/loss": 2.4315075874328613, "eval/best/testid/acc": 0.26855600539811064, "eval/best/testid/acc_std": 0.0054350775188430735, "eval/best/testid/f1": 0.21962484790439263, "eval/best/testid/f1_std": 0.005264704051085441} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..9974110d4cf14c2d66785022ee919b6e0f705563 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 41, "eval/last/lr_best": 0.0048, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.0434505939483643, "eval/last/train/acc": 0.3797904053597222, "eval/last/train/acc_std": 0.002404379096335571, "eval/last/train/f1": 0.3347871560709368, "eval/last/train/f1_std": 0.002603657465134304, "eval/last/validation/loss": 2.4515979290008545, "eval/last/validation/acc": 0.2681801402731635, "eval/last/validation/acc_std": 0.005218332828103721, "eval/last/validation/f1": 0.20918490608613471, "eval/last/validation/f1_std": 0.004854069853745508, "eval/last/test/loss": 2.3110108375549316, "eval/last/test/acc": 0.3131725417439703, "eval/last/test/acc_std": 0.005397624778375215, "eval/last/test/f1": 0.2538940034485557, "eval/last/test/f1_std": 0.00548960409451735, "eval/last/testid/loss": 2.422670364379883, "eval/last/testid/acc": 0.2739541160593792, "eval/last/testid/acc_std": 0.005591472232305107, "eval/last/testid/f1": 0.22618279872340796, "eval/last/testid/f1_std": 0.0054460928998384} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..d1f790b80aef45bc2ebb5edb58161c853509e0b4 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",train,2.062237501144409,0.372568302652202,0.002469017416856133,0.3255660013374387,0.0025967055970697165 +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",validation,2.452381134033203,0.27260981912144705,0.0053846242310042385,0.21158476658860004,0.00477650952012854 +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",test,2.3251588344573975,0.3055658627087198,0.005318868133213203,0.24520047876166337,0.005280489915656855 +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",testid,2.4315075874328613,0.26855600539811064,0.0054350775188430735,0.21962484790439263,0.005264704051085441 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..d1f790b80aef45bc2ebb5edb58161c853509e0b4 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",train,2.062237501144409,0.372568302652202,0.002469017416856133,0.3255660013374387,0.0025967055970697165 +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",validation,2.452381134033203,0.27260981912144705,0.0053846242310042385,0.21158476658860004,0.00477650952012854 +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",test,2.3251588344573975,0.3055658627087198,0.005318868133213203,0.24520047876166337,0.005280489915656855 +flat_mae,reg,attn,nsd_cococlip,best,17,0.0048,0.05,41,"[16, 1.0]",testid,2.4315075874328613,0.26855600539811064,0.0054350775188430735,0.21962484790439263,0.005264704051085441 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..506bd4174f703c5f4960869382e06ac42caaeae9 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,attn,nsd_cococlip,last,19,0.0048,0.05,41,"[16, 1.0]",train,2.0434505939483643,0.3797904053597222,0.002404379096335571,0.3347871560709368,0.002603657465134304 +flat_mae,reg,attn,nsd_cococlip,last,19,0.0048,0.05,41,"[16, 1.0]",validation,2.4515979290008545,0.2681801402731635,0.005218332828103721,0.20918490608613471,0.004854069853745508 +flat_mae,reg,attn,nsd_cococlip,last,19,0.0048,0.05,41,"[16, 1.0]",test,2.3110108375549316,0.3131725417439703,0.005397624778375215,0.2538940034485557,0.00548960409451735 +flat_mae,reg,attn,nsd_cococlip,last,19,0.0048,0.05,41,"[16, 1.0]",testid,2.422670364379883,0.2739541160593792,0.005591472232305107,0.22618279872340796,0.0054460928998384 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/log.txt b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..15199a480549c1fac1e487af38c30dd010c56eaf --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/log.txt @@ -0,0 +1,967 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 23:49:10 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip reg attn) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn +model: flat_mae +representation: reg +classifier: attn +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x AttnPoolClassifier( + (kv): Linear(in_features=768, out_features=1536, bias=True) + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 58.8M (58.8M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:21:35 lr: nan time: 3.2395 data: 2.7896 max mem: 4150 +train: [0] [ 20/400] eta: 0:03:12 lr: 0.000003 loss: 3.1813 (3.1826) grad: 0.0668 (0.0637) time: 0.3696 data: 0.0037 max mem: 4874 +train: [0] [ 40/400] eta: 0:02:35 lr: 0.000006 loss: 3.1813 (3.1819) grad: 0.0679 (0.0682) time: 0.3514 data: 0.0046 max mem: 4874 +train: [0] [ 60/400] eta: 0:02:17 lr: 0.000009 loss: 3.1709 (3.1768) grad: 0.0675 (0.0674) time: 0.3550 data: 0.0045 max mem: 4874 +train: [0] [ 80/400] eta: 0:02:05 lr: 0.000012 loss: 3.1696 (3.1771) grad: 0.0630 (0.0660) time: 0.3480 data: 0.0048 max mem: 4874 +train: [0] [100/400] eta: 0:01:55 lr: 0.000015 loss: 3.1740 (3.1753) grad: 0.0630 (0.0654) time: 0.3532 data: 0.0050 max mem: 4874 +train: [0] [120/400] eta: 0:01:46 lr: 0.000018 loss: 3.1684 (3.1746) grad: 0.0666 (0.0658) time: 0.3662 data: 0.0048 max mem: 4874 +train: [0] [140/400] eta: 0:01:38 lr: 0.000021 loss: 3.1621 (3.1727) grad: 0.0690 (0.0662) time: 0.3579 data: 0.0048 max mem: 4874 +train: [0] [160/400] eta: 0:01:30 lr: 0.000024 loss: 3.1607 (3.1720) grad: 0.0646 (0.0656) time: 0.3710 data: 0.0047 max mem: 4874 +train: [0] [180/400] eta: 0:01:22 lr: 0.000027 loss: 3.1508 (3.1689) grad: 0.0644 (0.0658) time: 0.3581 data: 0.0045 max mem: 4874 +train: [0] [200/400] eta: 0:01:14 lr: 0.000030 loss: 3.1407 (3.1665) grad: 0.0644 (0.0656) time: 0.3510 data: 0.0048 max mem: 4874 +train: [0] [220/400] eta: 0:01:06 lr: 0.000033 loss: 3.1534 (3.1655) grad: 0.0644 (0.0654) time: 0.3373 data: 0.0046 max mem: 4874 +train: [0] [240/400] eta: 0:00:59 lr: 0.000036 loss: 3.1534 (3.1641) grad: 0.0644 (0.0652) time: 0.3875 data: 0.0053 max mem: 4874 +train: [0] [260/400] eta: 0:00:51 lr: 0.000039 loss: 3.1521 (3.1636) grad: 0.0656 (0.0654) time: 0.3360 data: 0.0045 max mem: 4874 +train: [0] [280/400] eta: 0:00:43 lr: 0.000042 loss: 3.1514 (3.1625) grad: 0.0662 (0.0654) time: 0.3176 data: 0.0050 max mem: 4874 +train: [0] [300/400] eta: 0:00:36 lr: 0.000045 loss: 3.1514 (3.1623) grad: 0.0607 (0.0649) time: 0.3451 data: 0.0050 max mem: 4874 +train: [0] [320/400] eta: 0:00:29 lr: 0.000048 loss: 3.1527 (3.1618) grad: 0.0579 (0.0648) time: 0.3547 data: 0.0044 max mem: 4874 +train: [0] [340/400] eta: 0:00:21 lr: 0.000051 loss: 3.1512 (3.1614) grad: 0.0580 (0.0644) time: 0.3543 data: 0.0047 max mem: 4874 +train: [0] [360/400] eta: 0:00:14 lr: 0.000054 loss: 3.1454 (3.1605) grad: 0.0583 (0.0643) time: 0.3639 data: 0.0051 max mem: 4874 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 3.1531 (3.1602) grad: 0.0605 (0.0642) time: 0.3520 data: 0.0045 max mem: 4874 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1587 (3.1598) grad: 0.0605 (0.0642) time: 0.3574 data: 0.0044 max mem: 4874 +train: [0] Total time: 0:02:24 (0.3621 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1587 (3.1598) grad: 0.0605 (0.0642) +eval (validation): [0] [ 0/85] eta: 0:04:34 time: 3.2268 data: 2.9754 max mem: 4874 +eval (validation): [0] [20/85] eta: 0:00:30 time: 0.3311 data: 0.0049 max mem: 4874 +eval (validation): [0] [40/85] eta: 0:00:18 time: 0.3287 data: 0.0050 max mem: 4874 +eval (validation): [0] [60/85] eta: 0:00:09 time: 0.3481 data: 0.0043 max mem: 4874 +eval (validation): [0] [80/85] eta: 0:00:01 time: 0.3188 data: 0.0043 max mem: 4874 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3097 data: 0.0041 max mem: 4874 +eval (validation): [0] Total time: 0:00:31 (0.3667 s / it) +cv: [0] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 3.126 acc: 0.074 f1: 0.013 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:19:32 lr: nan time: 2.9323 data: 2.7187 max mem: 4874 +train: [1] [ 20/400] eta: 0:03:02 lr: 0.000063 loss: 3.1311 (3.1373) grad: 0.0580 (0.0575) time: 0.3573 data: 0.0059 max mem: 4874 +train: [1] [ 40/400] eta: 0:02:30 lr: 0.000066 loss: 3.1311 (3.1321) grad: 0.0599 (0.0606) time: 0.3558 data: 0.0042 max mem: 4874 +train: [1] [ 60/400] eta: 0:02:13 lr: 0.000069 loss: 3.1346 (3.1288) grad: 0.0645 (0.0644) time: 0.3381 data: 0.0046 max mem: 4874 +train: [1] [ 80/400] eta: 0:02:04 lr: 0.000072 loss: 3.1365 (3.1312) grad: 0.0726 (0.0678) time: 0.3806 data: 0.0049 max mem: 4874 +train: [1] [100/400] eta: 0:01:56 lr: 0.000075 loss: 3.1124 (3.1257) grad: 0.0726 (0.0689) time: 0.3797 data: 0.0049 max mem: 4874 +train: [1] [120/400] eta: 0:01:48 lr: 0.000078 loss: 3.1147 (3.1269) grad: 0.0725 (0.0701) time: 0.3756 data: 0.0047 max mem: 4874 +train: [1] [140/400] eta: 0:01:39 lr: 0.000081 loss: 3.1251 (3.1241) grad: 0.0824 (0.0728) time: 0.3576 data: 0.0050 max mem: 4874 +train: [1] [160/400] eta: 0:01:31 lr: 0.000084 loss: 3.0944 (3.1208) grad: 0.0837 (0.0737) time: 0.3611 data: 0.0048 max mem: 4874 +train: [1] [180/400] eta: 0:01:22 lr: 0.000087 loss: 3.0931 (3.1189) grad: 0.0782 (0.0741) time: 0.3523 data: 0.0047 max mem: 4874 +train: [1] [200/400] eta: 0:01:14 lr: 0.000090 loss: 3.0931 (3.1156) grad: 0.0805 (0.0751) time: 0.3482 data: 0.0049 max mem: 4874 +train: [1] [220/400] eta: 0:01:06 lr: 0.000093 loss: 3.0878 (3.1131) grad: 0.0894 (0.0766) time: 0.3339 data: 0.0050 max mem: 4874 +train: [1] [240/400] eta: 0:00:59 lr: 0.000096 loss: 3.0871 (3.1101) grad: 0.0853 (0.0772) time: 0.3617 data: 0.0049 max mem: 4874 +train: [1] [260/400] eta: 0:00:51 lr: 0.000099 loss: 3.0656 (3.1058) grad: 0.0853 (0.0782) time: 0.3418 data: 0.0047 max mem: 4874 +train: [1] [280/400] eta: 0:00:43 lr: 0.000102 loss: 3.0680 (3.1041) grad: 0.0962 (0.0798) time: 0.3335 data: 0.0048 max mem: 4874 +train: [1] [300/400] eta: 0:00:36 lr: 0.000105 loss: 3.0726 (3.1017) grad: 0.0962 (0.0805) time: 0.3636 data: 0.0049 max mem: 4874 +train: [1] [320/400] eta: 0:00:29 lr: 0.000108 loss: 3.0645 (3.0998) grad: 0.0923 (0.0817) time: 0.3627 data: 0.0049 max mem: 4874 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 3.0634 (3.0973) grad: 0.0923 (0.0822) time: 0.3569 data: 0.0049 max mem: 4874 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 3.0613 (3.0943) grad: 0.0943 (0.0834) time: 0.3494 data: 0.0049 max mem: 4874 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 3.0274 (3.0908) grad: 0.1002 (0.0845) time: 0.3544 data: 0.0048 max mem: 4874 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.0319 (3.0890) grad: 0.1121 (0.0866) time: 0.3641 data: 0.0050 max mem: 4874 +train: [1] Total time: 0:02:25 (0.3635 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.0319 (3.0890) grad: 0.1121 (0.0866) +eval (validation): [1] [ 0/85] eta: 0:04:44 time: 3.3526 data: 3.0585 max mem: 4874 +eval (validation): [1] [20/85] eta: 0:00:33 time: 0.3796 data: 0.0037 max mem: 4874 +eval (validation): [1] [40/85] eta: 0:00:19 time: 0.3281 data: 0.0038 max mem: 4874 +eval (validation): [1] [60/85] eta: 0:00:09 time: 0.3387 data: 0.0041 max mem: 4874 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3192 data: 0.0045 max mem: 4874 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3133 data: 0.0044 max mem: 4874 +eval (validation): [1] Total time: 0:00:32 (0.3782 s / it) +cv: [1] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 2.735 acc: 0.185 f1: 0.096 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [2] [ 0/400] eta: 0:22:11 lr: nan time: 3.3280 data: 3.0801 max mem: 4874 +train: [2] [ 20/400] eta: 0:03:09 lr: 0.000123 loss: 3.0395 (3.0349) grad: 0.1126 (0.1117) time: 0.3585 data: 0.0039 max mem: 4874 +train: [2] [ 40/400] eta: 0:02:33 lr: 0.000126 loss: 3.0395 (3.0455) grad: 0.1096 (0.1127) time: 0.3474 data: 0.0042 max mem: 4874 +train: [2] [ 60/400] eta: 0:02:16 lr: 0.000129 loss: 3.0251 (3.0368) grad: 0.1090 (0.1120) time: 0.3559 data: 0.0049 max mem: 4874 +train: [2] [ 80/400] eta: 0:02:05 lr: 0.000132 loss: 2.9828 (3.0249) grad: 0.1093 (0.1134) time: 0.3549 data: 0.0053 max mem: 4874 +train: [2] [100/400] eta: 0:01:55 lr: 0.000135 loss: 2.9900 (3.0217) grad: 0.1050 (0.1113) time: 0.3551 data: 0.0047 max mem: 4874 +train: [2] [120/400] eta: 0:01:45 lr: 0.000138 loss: 3.0046 (3.0184) grad: 0.1096 (0.1130) time: 0.3379 data: 0.0049 max mem: 4874 +train: [2] [140/400] eta: 0:01:36 lr: 0.000141 loss: 2.9966 (3.0136) grad: 0.1120 (0.1131) time: 0.3499 data: 0.0048 max mem: 4874 +train: [2] [160/400] eta: 0:01:29 lr: 0.000144 loss: 2.9906 (3.0105) grad: 0.1127 (0.1132) time: 0.3644 data: 0.0047 max mem: 4874 +train: [2] [180/400] eta: 0:01:20 lr: 0.000147 loss: 2.9973 (3.0111) grad: 0.1168 (0.1140) time: 0.3359 data: 0.0046 max mem: 4874 +train: [2] [200/400] eta: 0:01:13 lr: 0.000150 loss: 2.9973 (3.0093) grad: 0.1220 (0.1153) time: 0.3469 data: 0.0049 max mem: 4874 +train: [2] [220/400] eta: 0:01:05 lr: 0.000153 loss: 3.0100 (3.0102) grad: 0.1277 (0.1171) time: 0.3575 data: 0.0046 max mem: 4874 +train: [2] [240/400] eta: 0:00:58 lr: 0.000156 loss: 3.0066 (3.0076) grad: 0.1288 (0.1186) time: 0.3431 data: 0.0047 max mem: 4874 +train: [2] [260/400] eta: 0:00:50 lr: 0.000159 loss: 2.9657 (3.0065) grad: 0.1368 (0.1207) time: 0.3297 data: 0.0048 max mem: 4874 +train: [2] [280/400] eta: 0:00:43 lr: 0.000162 loss: 2.9758 (3.0042) grad: 0.1501 (0.1235) time: 0.3412 data: 0.0050 max mem: 4874 +train: [2] [300/400] eta: 0:00:36 lr: 0.000165 loss: 2.9925 (3.0053) grad: 0.1833 (0.1306) time: 0.3885 data: 0.0051 max mem: 4874 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 3.0881 (3.0261) grad: 0.3179 (0.1677) time: 0.3595 data: 0.0050 max mem: 4874 +WARNING: classifier 48 (50, 1.0) diverged (loss=65.75 > 63.56) at step 567. Freezing. +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 3.4029 (3.0590) grad: 0.7413 (0.2101) time: 0.3534 data: 0.0049 max mem: 4874 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 3.0347 (3.0548) grad: 0.1627 (0.2067) time: 0.3605 data: 0.0050 max mem: 4874 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 2.9869 (3.0514) grad: 0.1412 (0.2029) time: 0.3630 data: 0.0051 max mem: 4874 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 2.9869 (3.0480) grad: 0.1350 (0.1996) time: 0.3867 data: 0.0052 max mem: 4874 +train: [2] Total time: 0:02:24 (0.3623 s / it) +train: [2] Summary: lr: 0.000180 loss: 2.9869 (3.0480) grad: 0.1350 (0.1996) +eval (validation): [2] [ 0/85] eta: 0:04:36 time: 3.2558 data: 2.9737 max mem: 4874 +eval (validation): [2] [20/85] eta: 0:00:32 time: 0.3674 data: 0.0046 max mem: 4874 +eval (validation): [2] [40/85] eta: 0:00:18 time: 0.3203 data: 0.0039 max mem: 4874 +eval (validation): [2] [60/85] eta: 0:00:09 time: 0.3434 data: 0.0044 max mem: 4874 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3008 data: 0.0040 max mem: 4874 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.2943 data: 0.0038 max mem: 4874 +eval (validation): [2] Total time: 0:00:31 (0.3680 s / it) +cv: [2] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 2.620 acc: 0.208 f1: 0.128 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:31 lr: nan time: 3.3783 data: 3.0666 max mem: 4874 +train: [3] [ 20/400] eta: 0:03:13 lr: 0.000183 loss: 2.9327 (2.9470) grad: 0.1223 (0.1281) time: 0.3671 data: 0.0050 max mem: 4874 +train: [3] [ 40/400] eta: 0:02:34 lr: 0.000186 loss: 2.9366 (2.9461) grad: 0.1302 (0.1332) time: 0.3447 data: 0.0036 max mem: 4874 +train: [3] [ 60/400] eta: 0:02:16 lr: 0.000189 loss: 2.9527 (2.9522) grad: 0.1456 (0.1394) time: 0.3476 data: 0.0050 max mem: 4874 +train: [3] [ 80/400] eta: 0:02:04 lr: 0.000192 loss: 2.9553 (2.9616) grad: 0.1456 (0.1382) time: 0.3534 data: 0.0043 max mem: 4874 +train: [3] [100/400] eta: 0:01:55 lr: 0.000195 loss: 2.9631 (2.9589) grad: 0.1338 (0.1392) time: 0.3557 data: 0.0046 max mem: 4874 +train: [3] [120/400] eta: 0:01:46 lr: 0.000198 loss: 2.9376 (2.9576) grad: 0.1343 (0.1388) time: 0.3632 data: 0.0048 max mem: 4874 +train: [3] [140/400] eta: 0:01:37 lr: 0.000201 loss: 2.9376 (2.9613) grad: 0.1387 (0.1400) time: 0.3558 data: 0.0043 max mem: 4874 +train: [3] [160/400] eta: 0:01:29 lr: 0.000204 loss: 2.9729 (2.9651) grad: 0.1533 (0.1428) time: 0.3426 data: 0.0047 max mem: 4874 +train: [3] [180/400] eta: 0:01:21 lr: 0.000207 loss: 2.9648 (2.9653) grad: 0.1653 (0.1465) time: 0.3693 data: 0.0050 max mem: 4874 +train: [3] [200/400] eta: 0:01:14 lr: 0.000210 loss: 2.9940 (2.9684) grad: 0.1781 (0.1535) time: 0.3601 data: 0.0049 max mem: 4874 +train: [3] [220/400] eta: 0:01:06 lr: 0.000213 loss: 3.0487 (2.9994) grad: 0.2508 (0.1986) time: 0.3612 data: 0.0045 max mem: 4874 +WARNING: classifier 46 (36, 1.0) diverged (loss=73.32 > 63.56) at step 719. Freezing. +train: [3] [240/400] eta: 0:00:58 lr: 0.000216 loss: 3.3900 (3.0715) grad: 0.8560 (0.2930) time: 0.3392 data: 0.0046 max mem: 4874 +train: [3] [260/400] eta: 0:00:51 lr: 0.000219 loss: 3.0270 (3.0636) grad: 0.1656 (0.2817) time: 0.3647 data: 0.0049 max mem: 4874 +train: [3] [280/400] eta: 0:00:43 lr: 0.000222 loss: 2.9715 (3.0563) grad: 0.1443 (0.2724) time: 0.3545 data: 0.0049 max mem: 4874 +train: [3] [300/400] eta: 0:00:36 lr: 0.000225 loss: 2.9693 (3.0515) grad: 0.1776 (0.2691) time: 0.3578 data: 0.0050 max mem: 4874 +train: [3] [320/400] eta: 0:00:29 lr: 0.000228 loss: 3.0079 (3.0525) grad: 0.2428 (0.2769) time: 0.3633 data: 0.0049 max mem: 4874 +WARNING: classifier 47 (43, 1.0) diverged (loss=73.93 > 63.56) at step 768. Freezing. +train: [3] [340/400] eta: 0:00:21 lr: 0.000231 loss: 3.1151 (3.0848) grad: 0.5528 (0.3184) time: 0.3643 data: 0.0049 max mem: 4874 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 2.9752 (3.0760) grad: 0.1451 (0.3084) time: 0.3630 data: 0.0047 max mem: 4874 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 2.9225 (3.0687) grad: 0.1303 (0.2990) time: 0.3660 data: 0.0052 max mem: 4874 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 2.9288 (3.0612) grad: 0.1335 (0.2911) time: 0.3716 data: 0.0051 max mem: 4874 +train: [3] Total time: 0:02:26 (0.3663 s / it) +train: [3] Summary: lr: 0.000240 loss: 2.9288 (3.0612) grad: 0.1335 (0.2911) +eval (validation): [3] [ 0/85] eta: 0:04:46 time: 3.3655 data: 3.0740 max mem: 4874 +eval (validation): [3] [20/85] eta: 0:00:35 time: 0.3992 data: 0.0058 max mem: 4874 +eval (validation): [3] [40/85] eta: 0:00:19 time: 0.3257 data: 0.0038 max mem: 4874 +eval (validation): [3] [60/85] eta: 0:00:09 time: 0.3159 data: 0.0042 max mem: 4874 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3078 data: 0.0043 max mem: 4874 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3090 data: 0.0042 max mem: 4874 +eval (validation): [3] Total time: 0:00:31 (0.3754 s / it) +cv: [3] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 2.580 acc: 0.226 f1: 0.143 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [4] [ 0/400] eta: 0:22:45 lr: nan time: 3.4131 data: 3.1530 max mem: 4874 +train: [4] [ 20/400] eta: 0:03:11 lr: 0.000243 loss: 2.8713 (2.9021) grad: 0.1404 (0.1407) time: 0.3594 data: 0.0039 max mem: 4874 +train: [4] [ 40/400] eta: 0:02:33 lr: 0.000246 loss: 2.9008 (2.9030) grad: 0.1388 (0.1408) time: 0.3439 data: 0.0038 max mem: 4874 +train: [4] [ 60/400] eta: 0:02:16 lr: 0.000249 loss: 2.9008 (2.8973) grad: 0.1375 (0.1404) time: 0.3540 data: 0.0050 max mem: 4874 +train: [4] [ 80/400] eta: 0:02:05 lr: 0.000252 loss: 2.9164 (2.9055) grad: 0.1366 (0.1402) time: 0.3586 data: 0.0047 max mem: 4874 +train: [4] [100/400] eta: 0:01:56 lr: 0.000255 loss: 2.9063 (2.9037) grad: 0.1418 (0.1426) time: 0.3696 data: 0.0048 max mem: 4874 +train: [4] [120/400] eta: 0:01:47 lr: 0.000258 loss: 2.8940 (2.9057) grad: 0.1530 (0.1475) time: 0.3608 data: 0.0048 max mem: 4874 +train: [4] [140/400] eta: 0:01:37 lr: 0.000261 loss: 2.9338 (2.9130) grad: 0.1915 (0.1632) time: 0.3356 data: 0.0047 max mem: 4874 +train: [4] [160/400] eta: 0:01:29 lr: 0.000264 loss: 2.9971 (2.9952) grad: 0.4158 (0.2511) time: 0.3397 data: 0.0049 max mem: 4874 +WARNING: classifier 44 (26, 1.0) diverged (loss=67.97 > 63.56) at step 886. Freezing. +train: [4] [180/400] eta: 0:01:21 lr: 0.000267 loss: 3.5960 (3.0547) grad: 0.8574 (0.3332) time: 0.3633 data: 0.0048 max mem: 4874 +train: [4] [200/400] eta: 0:01:14 lr: 0.000270 loss: 2.9417 (3.0409) grad: 0.1457 (0.3141) time: 0.3654 data: 0.0046 max mem: 4874 +train: [4] [220/400] eta: 0:01:06 lr: 0.000273 loss: 2.8961 (3.0279) grad: 0.1411 (0.2980) time: 0.3473 data: 0.0045 max mem: 4874 +train: [4] [240/400] eta: 0:00:58 lr: 0.000276 loss: 2.8977 (3.0189) grad: 0.1434 (0.2854) time: 0.3351 data: 0.0049 max mem: 4874 +train: [4] [260/400] eta: 0:00:51 lr: 0.000279 loss: 2.9141 (3.0107) grad: 0.1426 (0.2739) time: 0.3582 data: 0.0050 max mem: 4874 +train: [4] [280/400] eta: 0:00:43 lr: 0.000282 loss: 2.8913 (3.0022) grad: 0.1407 (0.2650) time: 0.3776 data: 0.0049 max mem: 4874 +train: [4] [300/400] eta: 0:00:36 lr: 0.000285 loss: 2.8921 (2.9969) grad: 0.1480 (0.2578) time: 0.3683 data: 0.0047 max mem: 4874 +train: [4] [320/400] eta: 0:00:29 lr: 0.000288 loss: 2.9017 (2.9916) grad: 0.1400 (0.2512) time: 0.3581 data: 0.0049 max mem: 4874 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 2.8880 (2.9854) grad: 0.1360 (0.2442) time: 0.3443 data: 0.0044 max mem: 4874 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 2.9077 (2.9823) grad: 0.1360 (0.2387) time: 0.3637 data: 0.0052 max mem: 4874 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 2.9196 (2.9769) grad: 0.1442 (0.2340) time: 0.3666 data: 0.0049 max mem: 4874 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 2.8733 (2.9716) grad: 0.1506 (0.2300) time: 0.3654 data: 0.0049 max mem: 4874 +train: [4] Total time: 0:02:25 (0.3649 s / it) +train: [4] Summary: lr: 0.000300 loss: 2.8733 (2.9716) grad: 0.1506 (0.2300) +eval (validation): [4] [ 0/85] eta: 0:04:44 time: 3.3500 data: 3.0605 max mem: 4874 +eval (validation): [4] [20/85] eta: 0:00:32 time: 0.3589 data: 0.0034 max mem: 4874 +eval (validation): [4] [40/85] eta: 0:00:18 time: 0.3193 data: 0.0037 max mem: 4874 +eval (validation): [4] [60/85] eta: 0:00:09 time: 0.3476 data: 0.0044 max mem: 4874 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3121 data: 0.0042 max mem: 4874 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3107 data: 0.0041 max mem: 4874 +eval (validation): [4] Total time: 0:00:31 (0.3715 s / it) +cv: [4] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 2.559 acc: 0.237 f1: 0.151 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [5] [ 0/400] eta: 0:22:57 lr: nan time: 3.4440 data: 3.1825 max mem: 4874 +train: [5] [ 20/400] eta: 0:03:10 lr: 0.000300 loss: 2.8642 (2.8514) grad: 0.1329 (0.1369) time: 0.3555 data: 0.0033 max mem: 4874 +train: [5] [ 40/400] eta: 0:02:32 lr: 0.000300 loss: 2.8554 (2.8586) grad: 0.1409 (0.1416) time: 0.3408 data: 0.0034 max mem: 4874 +train: [5] [ 60/400] eta: 0:02:17 lr: 0.000300 loss: 2.8554 (2.8640) grad: 0.1502 (0.1471) time: 0.3625 data: 0.0050 max mem: 4874 +train: [5] [ 80/400] eta: 0:02:06 lr: 0.000300 loss: 2.8559 (2.8614) grad: 0.1502 (0.1469) time: 0.3675 data: 0.0051 max mem: 4874 +train: [5] [100/400] eta: 0:01:57 lr: 0.000300 loss: 2.8700 (2.8679) grad: 0.1557 (0.1500) time: 0.3751 data: 0.0051 max mem: 4874 +train: [5] [120/400] eta: 0:01:47 lr: 0.000300 loss: 2.8707 (2.8683) grad: 0.1479 (0.1487) time: 0.3452 data: 0.0048 max mem: 4874 +train: [5] [140/400] eta: 0:01:37 lr: 0.000300 loss: 2.8610 (2.8698) grad: 0.1556 (0.1509) time: 0.3356 data: 0.0049 max mem: 4874 +train: [5] [160/400] eta: 0:01:29 lr: 0.000299 loss: 2.8842 (2.8754) grad: 0.1615 (0.1517) time: 0.3565 data: 0.0047 max mem: 4874 +train: [5] [180/400] eta: 0:01:21 lr: 0.000299 loss: 2.8679 (2.8721) grad: 0.1636 (0.1529) time: 0.3531 data: 0.0048 max mem: 4874 +train: [5] [200/400] eta: 0:01:13 lr: 0.000299 loss: 2.8583 (2.8709) grad: 0.1527 (0.1526) time: 0.3528 data: 0.0047 max mem: 4874 +train: [5] [220/400] eta: 0:01:06 lr: 0.000299 loss: 2.8586 (2.8698) grad: 0.1537 (0.1543) time: 0.3435 data: 0.0047 max mem: 4874 +train: [5] [240/400] eta: 0:00:58 lr: 0.000299 loss: 2.8586 (2.8707) grad: 0.1575 (0.1546) time: 0.3426 data: 0.0048 max mem: 4874 +train: [5] [260/400] eta: 0:00:51 lr: 0.000299 loss: 2.8873 (2.8711) grad: 0.1531 (0.1543) time: 0.3628 data: 0.0048 max mem: 4874 +train: [5] [280/400] eta: 0:00:43 lr: 0.000298 loss: 2.8860 (2.8728) grad: 0.1605 (0.1559) time: 0.3526 data: 0.0050 max mem: 4874 +train: [5] [300/400] eta: 0:00:36 lr: 0.000298 loss: 2.8742 (2.8725) grad: 0.1708 (0.1561) time: 0.3730 data: 0.0050 max mem: 4874 +train: [5] [320/400] eta: 0:00:29 lr: 0.000298 loss: 2.8378 (2.8698) grad: 0.1465 (0.1550) time: 0.3617 data: 0.0049 max mem: 4874 +train: [5] [340/400] eta: 0:00:21 lr: 0.000298 loss: 2.8712 (2.8703) grad: 0.1428 (0.1547) time: 0.3716 data: 0.0047 max mem: 4874 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 2.8772 (2.8694) grad: 0.1493 (0.1555) time: 0.3595 data: 0.0051 max mem: 4874 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 2.8641 (2.8702) grad: 0.1565 (0.1556) time: 0.3771 data: 0.0049 max mem: 4874 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 2.8340 (2.8681) grad: 0.1546 (0.1556) time: 0.3749 data: 0.0051 max mem: 4874 +train: [5] Total time: 0:02:26 (0.3664 s / it) +train: [5] Summary: lr: 0.000297 loss: 2.8340 (2.8681) grad: 0.1546 (0.1556) +eval (validation): [5] [ 0/85] eta: 0:04:40 time: 3.3041 data: 3.0606 max mem: 4874 +eval (validation): [5] [20/85] eta: 0:00:30 time: 0.3219 data: 0.0043 max mem: 4874 +eval (validation): [5] [40/85] eta: 0:00:17 time: 0.3218 data: 0.0041 max mem: 4874 +eval (validation): [5] [60/85] eta: 0:00:09 time: 0.3438 data: 0.0044 max mem: 4874 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3208 data: 0.0040 max mem: 4874 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3203 data: 0.0038 max mem: 4874 +eval (validation): [5] Total time: 0:00:30 (0.3647 s / it) +cv: [5] best hparam: (3.7, 1.0) (032) ('032_lr3.7e+00_wd1.0e+00') loss: 2.543 acc: 0.235 f1: 0.162 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [6] [ 0/400] eta: 0:22:29 lr: nan time: 3.3745 data: 3.1069 max mem: 4874 +train: [6] [ 20/400] eta: 0:03:06 lr: 0.000296 loss: 2.8013 (2.7907) grad: 0.1500 (0.1573) time: 0.3458 data: 0.0045 max mem: 4874 +train: [6] [ 40/400] eta: 0:02:32 lr: 0.000296 loss: 2.8143 (2.8156) grad: 0.1500 (0.1557) time: 0.3523 data: 0.0044 max mem: 4874 +train: [6] [ 60/400] eta: 0:02:15 lr: 0.000296 loss: 2.8293 (2.8181) grad: 0.1465 (0.1491) time: 0.3498 data: 0.0039 max mem: 4874 +train: [6] [ 80/400] eta: 0:02:04 lr: 0.000295 loss: 2.7918 (2.8130) grad: 0.1465 (0.1514) time: 0.3636 data: 0.0047 max mem: 4874 +train: [6] [100/400] eta: 0:01:55 lr: 0.000295 loss: 2.7918 (2.8192) grad: 0.1547 (0.1532) time: 0.3587 data: 0.0048 max mem: 4874 +train: [6] [120/400] eta: 0:01:45 lr: 0.000295 loss: 2.8362 (2.8179) grad: 0.1517 (0.1520) time: 0.3437 data: 0.0048 max mem: 4874 +train: [6] [140/400] eta: 0:01:36 lr: 0.000294 loss: 2.8362 (2.8235) grad: 0.1518 (0.1541) time: 0.3326 data: 0.0050 max mem: 4874 +train: [6] [160/400] eta: 0:01:28 lr: 0.000294 loss: 2.8144 (2.8223) grad: 0.1625 (0.1555) time: 0.3585 data: 0.0052 max mem: 4874 +train: [6] [180/400] eta: 0:01:21 lr: 0.000293 loss: 2.7966 (2.8207) grad: 0.1555 (0.1552) time: 0.3683 data: 0.0049 max mem: 4874 +train: [6] [200/400] eta: 0:01:13 lr: 0.000293 loss: 2.7892 (2.8206) grad: 0.1555 (0.1550) time: 0.3662 data: 0.0047 max mem: 4874 +train: [6] [220/400] eta: 0:01:06 lr: 0.000292 loss: 2.7977 (2.8205) grad: 0.1561 (0.1554) time: 0.3576 data: 0.0048 max mem: 4874 +train: [6] [240/400] eta: 0:00:58 lr: 0.000292 loss: 2.8066 (2.8204) grad: 0.1591 (0.1561) time: 0.3300 data: 0.0048 max mem: 4874 +train: [6] [260/400] eta: 0:00:50 lr: 0.000291 loss: 2.7966 (2.8174) grad: 0.1516 (0.1553) time: 0.3558 data: 0.0049 max mem: 4874 +train: [6] [280/400] eta: 0:00:43 lr: 0.000291 loss: 2.7712 (2.8149) grad: 0.1485 (0.1552) time: 0.3638 data: 0.0046 max mem: 4874 +train: [6] [300/400] eta: 0:00:36 lr: 0.000290 loss: 2.7712 (2.8148) grad: 0.1555 (0.1554) time: 0.3801 data: 0.0048 max mem: 4874 +train: [6] [320/400] eta: 0:00:29 lr: 0.000290 loss: 2.7924 (2.8144) grad: 0.1564 (0.1560) time: 0.3729 data: 0.0051 max mem: 4874 +train: [6] [340/400] eta: 0:00:21 lr: 0.000289 loss: 2.7959 (2.8149) grad: 0.1551 (0.1558) time: 0.3616 data: 0.0050 max mem: 4874 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 2.8138 (2.8147) grad: 0.1566 (0.1562) time: 0.3574 data: 0.0051 max mem: 4874 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 2.8130 (2.8140) grad: 0.1606 (0.1567) time: 0.3658 data: 0.0050 max mem: 4874 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 2.8216 (2.8149) grad: 0.1643 (0.1573) time: 0.3730 data: 0.0050 max mem: 4874 +train: [6] Total time: 0:02:26 (0.3659 s / it) +train: [6] Summary: lr: 0.000287 loss: 2.8216 (2.8149) grad: 0.1643 (0.1573) +eval (validation): [6] [ 0/85] eta: 0:04:36 time: 3.2567 data: 2.9697 max mem: 4874 +eval (validation): [6] [20/85] eta: 0:00:32 time: 0.3549 data: 0.0048 max mem: 4874 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3290 data: 0.0034 max mem: 4874 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3523 data: 0.0047 max mem: 4874 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3300 data: 0.0041 max mem: 4874 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3169 data: 0.0040 max mem: 4874 +eval (validation): [6] Total time: 0:00:32 (0.3771 s / it) +cv: [6] best hparam: (2.3, 1.0) (029) ('029_lr2.3e+00_wd1.0e+00') loss: 2.538 acc: 0.237 f1: 0.165 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:23:21 lr: nan time: 3.5031 data: 3.1708 max mem: 4874 +train: [7] [ 20/400] eta: 0:03:23 lr: 0.000286 loss: 2.8016 (2.7910) grad: 0.1450 (0.1550) time: 0.3869 data: 0.0030 max mem: 4874 +train: [7] [ 40/400] eta: 0:02:39 lr: 0.000286 loss: 2.8067 (2.8115) grad: 0.1531 (0.1557) time: 0.3473 data: 0.0044 max mem: 4874 +train: [7] [ 60/400] eta: 0:02:24 lr: 0.000285 loss: 2.7758 (2.7865) grad: 0.1535 (0.1543) time: 0.3877 data: 0.0048 max mem: 4874 +train: [7] [ 80/400] eta: 0:02:14 lr: 0.000284 loss: 2.7681 (2.7858) grad: 0.1389 (0.1522) time: 0.4094 data: 0.0058 max mem: 4874 +train: [7] [100/400] eta: 0:02:05 lr: 0.000284 loss: 2.7714 (2.7843) grad: 0.1340 (0.1475) time: 0.3988 data: 0.0053 max mem: 4874 +train: [7] [120/400] eta: 0:01:53 lr: 0.000283 loss: 2.7701 (2.7843) grad: 0.1340 (0.1482) time: 0.3450 data: 0.0049 max mem: 4874 +train: [7] [140/400] eta: 0:01:42 lr: 0.000282 loss: 2.7861 (2.7839) grad: 0.1500 (0.1490) time: 0.3408 data: 0.0052 max mem: 4874 +train: [7] [160/400] eta: 0:01:34 lr: 0.000282 loss: 2.7963 (2.7845) grad: 0.1517 (0.1487) time: 0.3628 data: 0.0052 max mem: 4874 +train: [7] [180/400] eta: 0:01:25 lr: 0.000281 loss: 2.7809 (2.7852) grad: 0.1516 (0.1493) time: 0.3559 data: 0.0047 max mem: 4874 +train: [7] [200/400] eta: 0:01:16 lr: 0.000280 loss: 2.7844 (2.7860) grad: 0.1546 (0.1497) time: 0.3538 data: 0.0047 max mem: 4874 +train: [7] [220/400] eta: 0:01:08 lr: 0.000279 loss: 2.7943 (2.7866) grad: 0.1635 (0.1517) time: 0.3377 data: 0.0048 max mem: 4874 +train: [7] [240/400] eta: 0:01:00 lr: 0.000278 loss: 2.7722 (2.7846) grad: 0.1686 (0.1525) time: 0.3537 data: 0.0052 max mem: 4874 +train: [7] [260/400] eta: 0:00:52 lr: 0.000278 loss: 2.7937 (2.7843) grad: 0.1554 (0.1533) time: 0.3596 data: 0.0051 max mem: 4874 +train: [7] [280/400] eta: 0:00:45 lr: 0.000277 loss: 2.7992 (2.7877) grad: 0.1696 (0.1562) time: 0.3550 data: 0.0047 max mem: 4874 +train: [7] [300/400] eta: 0:00:37 lr: 0.000276 loss: 2.8105 (2.7880) grad: 0.1784 (0.1578) time: 0.3555 data: 0.0048 max mem: 4874 +train: [7] [320/400] eta: 0:00:29 lr: 0.000275 loss: 2.7843 (2.7874) grad: 0.1650 (0.1582) time: 0.3837 data: 0.0050 max mem: 4874 +train: [7] [340/400] eta: 0:00:22 lr: 0.000274 loss: 2.7810 (2.7858) grad: 0.1610 (0.1581) time: 0.3935 data: 0.0056 max mem: 4874 +train: [7] [360/400] eta: 0:00:15 lr: 0.000273 loss: 2.7670 (2.7881) grad: 0.1653 (0.1593) time: 0.3745 data: 0.0051 max mem: 4874 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 2.7882 (2.7880) grad: 0.1668 (0.1590) time: 0.3824 data: 0.0047 max mem: 4874 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 2.7748 (2.7887) grad: 0.1556 (0.1588) time: 0.3668 data: 0.0053 max mem: 4874 +train: [7] Total time: 0:02:30 (0.3756 s / it) +train: [7] Summary: lr: 0.000271 loss: 2.7748 (2.7887) grad: 0.1556 (0.1588) +eval (validation): [7] [ 0/85] eta: 0:04:33 time: 3.2130 data: 2.9820 max mem: 4874 +eval (validation): [7] [20/85] eta: 0:00:30 time: 0.3350 data: 0.0035 max mem: 4874 +eval (validation): [7] [40/85] eta: 0:00:18 time: 0.3445 data: 0.0044 max mem: 4874 +eval (validation): [7] [60/85] eta: 0:00:09 time: 0.3386 data: 0.0044 max mem: 4874 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3353 data: 0.0043 max mem: 4874 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3332 data: 0.0043 max mem: 4874 +eval (validation): [7] Total time: 0:00:31 (0.3745 s / it) +cv: [7] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 2.499 acc: 0.252 f1: 0.189 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:23:11 lr: nan time: 3.4778 data: 3.1756 max mem: 4874 +train: [8] [ 20/400] eta: 0:03:29 lr: 0.000270 loss: 2.7264 (2.7254) grad: 0.1548 (0.1535) time: 0.4048 data: 0.0045 max mem: 4874 +train: [8] [ 40/400] eta: 0:02:41 lr: 0.000270 loss: 2.7252 (2.7221) grad: 0.1608 (0.1598) time: 0.3385 data: 0.0041 max mem: 4874 +train: [8] [ 60/400] eta: 0:02:21 lr: 0.000269 loss: 2.7252 (2.7356) grad: 0.1712 (0.1673) time: 0.3491 data: 0.0045 max mem: 4874 +train: [8] [ 80/400] eta: 0:02:07 lr: 0.000268 loss: 2.7237 (2.7335) grad: 0.1722 (0.1682) time: 0.3518 data: 0.0049 max mem: 4874 +train: [8] [100/400] eta: 0:01:56 lr: 0.000267 loss: 2.7089 (2.7409) grad: 0.1722 (0.1685) time: 0.3409 data: 0.0050 max mem: 4874 +train: [8] [120/400] eta: 0:01:47 lr: 0.000266 loss: 2.7217 (2.7402) grad: 0.1725 (0.1677) time: 0.3604 data: 0.0051 max mem: 4874 +train: [8] [140/400] eta: 0:01:38 lr: 0.000265 loss: 2.7523 (2.7465) grad: 0.1674 (0.1672) time: 0.3612 data: 0.0051 max mem: 4874 +train: [8] [160/400] eta: 0:01:30 lr: 0.000264 loss: 2.7618 (2.7474) grad: 0.1610 (0.1658) time: 0.3451 data: 0.0045 max mem: 4874 +train: [8] [180/400] eta: 0:01:22 lr: 0.000263 loss: 2.7475 (2.7479) grad: 0.1657 (0.1673) time: 0.3638 data: 0.0046 max mem: 4874 +train: [8] [200/400] eta: 0:01:14 lr: 0.000262 loss: 2.7357 (2.7471) grad: 0.1772 (0.1685) time: 0.3593 data: 0.0049 max mem: 4874 +train: [8] [220/400] eta: 0:01:07 lr: 0.000260 loss: 2.7818 (2.7532) grad: 0.1645 (0.1681) time: 0.3664 data: 0.0051 max mem: 4874 +train: [8] [240/400] eta: 0:00:59 lr: 0.000259 loss: 2.7818 (2.7531) grad: 0.1611 (0.1671) time: 0.3505 data: 0.0049 max mem: 4874 +train: [8] [260/400] eta: 0:00:51 lr: 0.000258 loss: 2.7617 (2.7531) grad: 0.1589 (0.1670) time: 0.3519 data: 0.0050 max mem: 4874 +train: [8] [280/400] eta: 0:00:44 lr: 0.000257 loss: 2.7359 (2.7524) grad: 0.1555 (0.1661) time: 0.3671 data: 0.0050 max mem: 4874 +train: [8] [300/400] eta: 0:00:36 lr: 0.000256 loss: 2.7359 (2.7513) grad: 0.1591 (0.1664) time: 0.3571 data: 0.0052 max mem: 4874 +train: [8] [320/400] eta: 0:00:29 lr: 0.000255 loss: 2.7605 (2.7530) grad: 0.1740 (0.1669) time: 0.3568 data: 0.0049 max mem: 4874 +train: [8] [340/400] eta: 0:00:22 lr: 0.000254 loss: 2.7605 (2.7543) grad: 0.1626 (0.1662) time: 0.3622 data: 0.0048 max mem: 4874 +train: [8] [360/400] eta: 0:00:14 lr: 0.000253 loss: 2.7321 (2.7538) grad: 0.1614 (0.1665) time: 0.3419 data: 0.0049 max mem: 4874 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 2.7481 (2.7536) grad: 0.1846 (0.1679) time: 0.3638 data: 0.0050 max mem: 4874 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 2.7083 (2.7511) grad: 0.1818 (0.1682) time: 0.3380 data: 0.0046 max mem: 4874 +train: [8] Total time: 0:02:25 (0.3649 s / it) +train: [8] Summary: lr: 0.000250 loss: 2.7083 (2.7511) grad: 0.1818 (0.1682) +eval (validation): [8] [ 0/85] eta: 0:04:53 time: 3.4505 data: 3.2000 max mem: 4874 +eval (validation): [8] [20/85] eta: 0:00:33 time: 0.3714 data: 0.0352 max mem: 4874 +eval (validation): [8] [40/85] eta: 0:00:19 time: 0.3340 data: 0.0047 max mem: 4874 +eval (validation): [8] [60/85] eta: 0:00:10 time: 0.3427 data: 0.0035 max mem: 4874 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3170 data: 0.0038 max mem: 4874 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3070 data: 0.0024 max mem: 4874 +eval (validation): [8] Total time: 0:00:32 (0.3785 s / it) +cv: [8] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.459 acc: 0.258 f1: 0.196 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:22:20 lr: nan time: 3.3509 data: 3.1006 max mem: 4874 +train: [9] [ 20/400] eta: 0:03:13 lr: 0.000249 loss: 2.6692 (2.6951) grad: 0.1485 (0.1586) time: 0.3685 data: 0.0046 max mem: 4874 +train: [9] [ 40/400] eta: 0:02:37 lr: 0.000248 loss: 2.6759 (2.6908) grad: 0.1582 (0.1645) time: 0.3620 data: 0.0044 max mem: 4874 +train: [9] [ 60/400] eta: 0:02:18 lr: 0.000247 loss: 2.6774 (2.7012) grad: 0.1748 (0.1689) time: 0.3458 data: 0.0034 max mem: 4874 +train: [9] [ 80/400] eta: 0:02:07 lr: 0.000246 loss: 2.7123 (2.7097) grad: 0.1673 (0.1660) time: 0.3715 data: 0.0052 max mem: 4874 +train: [9] [100/400] eta: 0:01:58 lr: 0.000244 loss: 2.7196 (2.7081) grad: 0.1520 (0.1643) time: 0.3825 data: 0.0051 max mem: 4874 +train: [9] [120/400] eta: 0:01:48 lr: 0.000243 loss: 2.7254 (2.7144) grad: 0.1630 (0.1655) time: 0.3529 data: 0.0051 max mem: 4874 +train: [9] [140/400] eta: 0:01:39 lr: 0.000242 loss: 2.7254 (2.7132) grad: 0.1722 (0.1677) time: 0.3588 data: 0.0052 max mem: 4874 +train: [9] [160/400] eta: 0:01:31 lr: 0.000241 loss: 2.7006 (2.7120) grad: 0.1819 (0.1704) time: 0.3491 data: 0.0049 max mem: 4874 +train: [9] [180/400] eta: 0:01:22 lr: 0.000240 loss: 2.7024 (2.7176) grad: 0.1819 (0.1717) time: 0.3469 data: 0.0048 max mem: 4874 +train: [9] [200/400] eta: 0:01:14 lr: 0.000238 loss: 2.7621 (2.7196) grad: 0.1662 (0.1713) time: 0.3547 data: 0.0047 max mem: 4874 +train: [9] [220/400] eta: 0:01:07 lr: 0.000237 loss: 2.6966 (2.7158) grad: 0.1662 (0.1718) time: 0.3577 data: 0.0046 max mem: 4874 +train: [9] [240/400] eta: 0:00:59 lr: 0.000236 loss: 2.6968 (2.7165) grad: 0.1768 (0.1728) time: 0.3605 data: 0.0046 max mem: 4874 +train: [9] [260/400] eta: 0:00:51 lr: 0.000234 loss: 2.7391 (2.7162) grad: 0.1796 (0.1742) time: 0.3615 data: 0.0048 max mem: 4874 +train: [9] [280/400] eta: 0:00:44 lr: 0.000233 loss: 2.7391 (2.7202) grad: 0.1795 (0.1746) time: 0.3626 data: 0.0047 max mem: 4874 +train: [9] [300/400] eta: 0:00:36 lr: 0.000232 loss: 2.7272 (2.7218) grad: 0.1755 (0.1746) time: 0.3559 data: 0.0047 max mem: 4874 +train: [9] [320/400] eta: 0:00:29 lr: 0.000230 loss: 2.7239 (2.7201) grad: 0.1673 (0.1742) time: 0.3578 data: 0.0049 max mem: 4874 +train: [9] [340/400] eta: 0:00:22 lr: 0.000229 loss: 2.6932 (2.7180) grad: 0.1582 (0.1735) time: 0.3559 data: 0.0049 max mem: 4874 +train: [9] [360/400] eta: 0:00:14 lr: 0.000228 loss: 2.6991 (2.7200) grad: 0.1603 (0.1731) time: 0.3444 data: 0.0046 max mem: 4874 +train: [9] [380/400] eta: 0:00:07 lr: 0.000226 loss: 2.7455 (2.7194) grad: 0.1619 (0.1726) time: 0.3374 data: 0.0045 max mem: 4874 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 2.6990 (2.7178) grad: 0.1635 (0.1724) time: 0.3987 data: 0.0049 max mem: 4874 +train: [9] Total time: 0:02:26 (0.3672 s / it) +train: [9] Summary: lr: 0.000225 loss: 2.6990 (2.7178) grad: 0.1635 (0.1724) +eval (validation): [9] [ 0/85] eta: 0:04:39 time: 3.2935 data: 3.0606 max mem: 4874 +eval (validation): [9] [20/85] eta: 0:00:32 time: 0.3644 data: 0.0052 max mem: 4874 +eval (validation): [9] [40/85] eta: 0:00:18 time: 0.3253 data: 0.0033 max mem: 4874 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3235 data: 0.0045 max mem: 4874 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3229 data: 0.0044 max mem: 4874 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3226 data: 0.0045 max mem: 4874 +eval (validation): [9] Total time: 0:00:31 (0.3700 s / it) +cv: [9] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 2.556 acc: 0.245 f1: 0.194 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [10] [ 0/400] eta: 0:22:50 lr: nan time: 3.4269 data: 3.1714 max mem: 4874 +train: [10] [ 20/400] eta: 0:03:42 lr: 0.000224 loss: 2.6549 (2.6542) grad: 0.1583 (0.1604) time: 0.4448 data: 0.0047 max mem: 4874 +train: [10] [ 40/400] eta: 0:02:53 lr: 0.000222 loss: 2.6637 (2.6730) grad: 0.1601 (0.1624) time: 0.3728 data: 0.0044 max mem: 4874 +train: [10] [ 60/400] eta: 0:02:27 lr: 0.000221 loss: 2.6726 (2.6731) grad: 0.1550 (0.1569) time: 0.3368 data: 0.0047 max mem: 4874 +train: [10] [ 80/400] eta: 0:02:13 lr: 0.000220 loss: 2.6673 (2.6770) grad: 0.1556 (0.1614) time: 0.3612 data: 0.0053 max mem: 4874 +train: [10] [100/400] eta: 0:02:01 lr: 0.000218 loss: 2.6866 (2.6766) grad: 0.1669 (0.1622) time: 0.3652 data: 0.0052 max mem: 4874 +train: [10] [120/400] eta: 0:01:51 lr: 0.000217 loss: 2.6953 (2.6871) grad: 0.1723 (0.1662) time: 0.3571 data: 0.0050 max mem: 4874 +train: [10] [140/400] eta: 0:01:42 lr: 0.000215 loss: 2.7288 (2.6897) grad: 0.1780 (0.1660) time: 0.3657 data: 0.0047 max mem: 4874 +train: [10] [160/400] eta: 0:01:32 lr: 0.000214 loss: 2.7226 (2.6922) grad: 0.1667 (0.1669) time: 0.3324 data: 0.0046 max mem: 4874 +train: [10] [180/400] eta: 0:01:23 lr: 0.000213 loss: 2.7089 (2.6968) grad: 0.1681 (0.1669) time: 0.3347 data: 0.0048 max mem: 4874 +train: [10] [200/400] eta: 0:01:15 lr: 0.000211 loss: 2.7220 (2.6992) grad: 0.1643 (0.1668) time: 0.3319 data: 0.0047 max mem: 4874 +train: [10] [220/400] eta: 0:01:07 lr: 0.000210 loss: 2.7328 (2.7008) grad: 0.1695 (0.1678) time: 0.3464 data: 0.0046 max mem: 4874 +train: [10] [240/400] eta: 0:00:59 lr: 0.000208 loss: 2.7392 (2.7028) grad: 0.1752 (0.1687) time: 0.3269 data: 0.0047 max mem: 4874 +train: [10] [260/400] eta: 0:00:51 lr: 0.000207 loss: 2.7275 (2.7026) grad: 0.1860 (0.1708) time: 0.3265 data: 0.0050 max mem: 4874 +train: [10] [280/400] eta: 0:00:43 lr: 0.000205 loss: 2.6834 (2.7017) grad: 0.1877 (0.1714) time: 0.3247 data: 0.0049 max mem: 4874 +train: [10] [300/400] eta: 0:00:36 lr: 0.000204 loss: 2.7213 (2.7026) grad: 0.1634 (0.1706) time: 0.3220 data: 0.0050 max mem: 4874 +train: [10] [320/400] eta: 0:00:28 lr: 0.000202 loss: 2.7124 (2.7033) grad: 0.1540 (0.1702) time: 0.3282 data: 0.0045 max mem: 4874 +train: [10] [340/400] eta: 0:00:21 lr: 0.000201 loss: 2.6769 (2.7025) grad: 0.1612 (0.1699) time: 0.3239 data: 0.0047 max mem: 4874 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 2.6769 (2.7046) grad: 0.1616 (0.1697) time: 0.3352 data: 0.0046 max mem: 4874 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 2.7525 (2.7076) grad: 0.1616 (0.1695) time: 0.3297 data: 0.0048 max mem: 4874 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 2.7356 (2.7071) grad: 0.1731 (0.1701) time: 0.3359 data: 0.0050 max mem: 4874 +train: [10] Total time: 0:02:21 (0.3533 s / it) +train: [10] Summary: lr: 0.000196 loss: 2.7356 (2.7071) grad: 0.1731 (0.1701) +eval (validation): [10] [ 0/85] eta: 0:04:16 time: 3.0221 data: 2.7701 max mem: 4874 +eval (validation): [10] [20/85] eta: 0:00:29 time: 0.3222 data: 0.0051 max mem: 4874 +eval (validation): [10] [40/85] eta: 0:00:17 time: 0.3147 data: 0.0038 max mem: 4874 +eval (validation): [10] [60/85] eta: 0:00:08 time: 0.3023 data: 0.0035 max mem: 4874 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3014 data: 0.0040 max mem: 4874 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3036 data: 0.0040 max mem: 4874 +eval (validation): [10] Total time: 0:00:29 (0.3452 s / it) +cv: [10] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.463 acc: 0.262 f1: 0.198 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [11] [ 0/400] eta: 0:23:05 lr: nan time: 3.4650 data: 3.2109 max mem: 4874 +train: [11] [ 20/400] eta: 0:03:27 lr: 0.000195 loss: 2.6273 (2.6451) grad: 0.1644 (0.1594) time: 0.4000 data: 0.0392 max mem: 4874 +train: [11] [ 40/400] eta: 0:02:39 lr: 0.000193 loss: 2.6695 (2.6705) grad: 0.1644 (0.1607) time: 0.3374 data: 0.0037 max mem: 4874 +train: [11] [ 60/400] eta: 0:02:22 lr: 0.000192 loss: 2.6841 (2.6777) grad: 0.1621 (0.1618) time: 0.3651 data: 0.0048 max mem: 4874 +train: [11] [ 80/400] eta: 0:02:09 lr: 0.000190 loss: 2.6841 (2.6791) grad: 0.1743 (0.1683) time: 0.3642 data: 0.0045 max mem: 4874 +train: [11] [100/400] eta: 0:01:59 lr: 0.000189 loss: 2.6651 (2.6798) grad: 0.1743 (0.1680) time: 0.3699 data: 0.0052 max mem: 4874 +train: [11] [120/400] eta: 0:01:49 lr: 0.000187 loss: 2.6640 (2.6790) grad: 0.1639 (0.1676) time: 0.3560 data: 0.0045 max mem: 4874 +train: [11] [140/400] eta: 0:01:39 lr: 0.000186 loss: 2.6640 (2.6745) grad: 0.1679 (0.1680) time: 0.3437 data: 0.0044 max mem: 4874 +train: [11] [160/400] eta: 0:01:30 lr: 0.000184 loss: 2.6617 (2.6743) grad: 0.1683 (0.1678) time: 0.3414 data: 0.0047 max mem: 4874 +train: [11] [180/400] eta: 0:01:22 lr: 0.000183 loss: 2.6303 (2.6689) grad: 0.1664 (0.1683) time: 0.3515 data: 0.0055 max mem: 4874 +train: [11] [200/400] eta: 0:01:14 lr: 0.000181 loss: 2.6650 (2.6742) grad: 0.1815 (0.1697) time: 0.3642 data: 0.0049 max mem: 4874 +train: [11] [220/400] eta: 0:01:07 lr: 0.000180 loss: 2.6779 (2.6712) grad: 0.1840 (0.1704) time: 0.3554 data: 0.0045 max mem: 4874 +train: [11] [240/400] eta: 0:00:59 lr: 0.000178 loss: 2.6776 (2.6725) grad: 0.1872 (0.1722) time: 0.3590 data: 0.0050 max mem: 4874 +train: [11] [260/400] eta: 0:00:51 lr: 0.000177 loss: 2.6872 (2.6750) grad: 0.1885 (0.1730) time: 0.3617 data: 0.0051 max mem: 4874 +train: [11] [280/400] eta: 0:00:44 lr: 0.000175 loss: 2.6993 (2.6757) grad: 0.1751 (0.1728) time: 0.3644 data: 0.0046 max mem: 4874 +train: [11] [300/400] eta: 0:00:36 lr: 0.000174 loss: 2.6885 (2.6742) grad: 0.1691 (0.1727) time: 0.3572 data: 0.0047 max mem: 4874 +train: [11] [320/400] eta: 0:00:29 lr: 0.000172 loss: 2.6341 (2.6717) grad: 0.1634 (0.1722) time: 0.3631 data: 0.0048 max mem: 4874 +train: [11] [340/400] eta: 0:00:22 lr: 0.000170 loss: 2.6426 (2.6723) grad: 0.1712 (0.1726) time: 0.3490 data: 0.0048 max mem: 4874 +train: [11] [360/400] eta: 0:00:14 lr: 0.000169 loss: 2.6618 (2.6721) grad: 0.1738 (0.1728) time: 0.3532 data: 0.0048 max mem: 4874 +train: [11] [380/400] eta: 0:00:07 lr: 0.000167 loss: 2.6618 (2.6741) grad: 0.1680 (0.1728) time: 0.3437 data: 0.0049 max mem: 4874 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 2.6776 (2.6753) grad: 0.1584 (0.1719) time: 0.3624 data: 0.0049 max mem: 4874 +train: [11] Total time: 0:02:26 (0.3665 s / it) +train: [11] Summary: lr: 0.000166 loss: 2.6776 (2.6753) grad: 0.1584 (0.1719) +eval (validation): [11] [ 0/85] eta: 0:04:46 time: 3.3706 data: 3.0715 max mem: 4874 +eval (validation): [11] [20/85] eta: 0:00:35 time: 0.3987 data: 0.0046 max mem: 4874 +eval (validation): [11] [40/85] eta: 0:00:19 time: 0.3251 data: 0.0037 max mem: 4874 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3234 data: 0.0041 max mem: 4874 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3649 data: 0.0054 max mem: 4874 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3295 data: 0.0049 max mem: 4874 +eval (validation): [11] Total time: 0:00:33 (0.3888 s / it) +cv: [11] best hparam: (1.6, 1.0) (027) ('027_lr1.6e+00_wd1.0e+00') loss: 2.469 acc: 0.260 f1: 0.198 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [12] [ 0/400] eta: 0:22:51 lr: nan time: 3.4295 data: 3.1316 max mem: 4874 +train: [12] [ 20/400] eta: 0:03:04 lr: 0.000164 loss: 2.5762 (2.6163) grad: 0.1651 (0.1837) time: 0.3382 data: 0.0032 max mem: 4874 +train: [12] [ 40/400] eta: 0:02:40 lr: 0.000163 loss: 2.6263 (2.6205) grad: 0.1695 (0.1735) time: 0.4027 data: 0.0044 max mem: 4874 +train: [12] [ 60/400] eta: 0:02:22 lr: 0.000161 loss: 2.6267 (2.6229) grad: 0.1695 (0.1718) time: 0.3671 data: 0.0047 max mem: 4874 +train: [12] [ 80/400] eta: 0:02:09 lr: 0.000160 loss: 2.6289 (2.6241) grad: 0.1653 (0.1700) time: 0.3646 data: 0.0049 max mem: 4874 +train: [12] [100/400] eta: 0:01:58 lr: 0.000158 loss: 2.6289 (2.6261) grad: 0.1619 (0.1705) time: 0.3451 data: 0.0048 max mem: 4874 +train: [12] [120/400] eta: 0:01:48 lr: 0.000156 loss: 2.6421 (2.6357) grad: 0.1705 (0.1719) time: 0.3472 data: 0.0046 max mem: 4874 +train: [12] [140/400] eta: 0:01:38 lr: 0.000155 loss: 2.6618 (2.6431) grad: 0.1760 (0.1735) time: 0.3459 data: 0.0045 max mem: 4874 +train: [12] [160/400] eta: 0:01:30 lr: 0.000153 loss: 2.6456 (2.6423) grad: 0.1715 (0.1726) time: 0.3367 data: 0.0047 max mem: 4874 +train: [12] [180/400] eta: 0:01:22 lr: 0.000152 loss: 2.6073 (2.6395) grad: 0.1601 (0.1712) time: 0.3618 data: 0.0053 max mem: 4874 +train: [12] [200/400] eta: 0:01:14 lr: 0.000150 loss: 2.6325 (2.6432) grad: 0.1632 (0.1708) time: 0.3571 data: 0.0043 max mem: 4874 +train: [12] [220/400] eta: 0:01:06 lr: 0.000149 loss: 2.6911 (2.6476) grad: 0.1673 (0.1718) time: 0.3589 data: 0.0042 max mem: 4874 +train: [12] [240/400] eta: 0:00:59 lr: 0.000147 loss: 2.6911 (2.6489) grad: 0.1693 (0.1725) time: 0.3619 data: 0.0050 max mem: 4874 +train: [12] [260/400] eta: 0:00:51 lr: 0.000145 loss: 2.6735 (2.6497) grad: 0.1693 (0.1723) time: 0.3627 data: 0.0051 max mem: 4874 +train: [12] [280/400] eta: 0:00:44 lr: 0.000144 loss: 2.6735 (2.6522) grad: 0.1753 (0.1734) time: 0.3690 data: 0.0044 max mem: 4874 +train: [12] [300/400] eta: 0:00:36 lr: 0.000142 loss: 2.6755 (2.6538) grad: 0.1868 (0.1743) time: 0.3524 data: 0.0047 max mem: 4874 +train: [12] [320/400] eta: 0:00:29 lr: 0.000141 loss: 2.6686 (2.6521) grad: 0.1892 (0.1756) time: 0.3713 data: 0.0051 max mem: 4874 +train: [12] [340/400] eta: 0:00:22 lr: 0.000139 loss: 2.6240 (2.6522) grad: 0.1856 (0.1754) time: 0.3523 data: 0.0049 max mem: 4874 +train: [12] [360/400] eta: 0:00:14 lr: 0.000138 loss: 2.6532 (2.6538) grad: 0.1653 (0.1750) time: 0.3742 data: 0.0051 max mem: 4874 +train: [12] [380/400] eta: 0:00:07 lr: 0.000136 loss: 2.6532 (2.6537) grad: 0.1631 (0.1746) time: 0.3657 data: 0.0049 max mem: 4874 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 2.6528 (2.6561) grad: 0.1718 (0.1748) time: 0.3691 data: 0.0049 max mem: 4874 +train: [12] Total time: 0:02:27 (0.3683 s / it) +train: [12] Summary: lr: 0.000134 loss: 2.6528 (2.6561) grad: 0.1718 (0.1748) +eval (validation): [12] [ 0/85] eta: 0:04:40 time: 3.3012 data: 3.0609 max mem: 4874 +eval (validation): [12] [20/85] eta: 0:00:30 time: 0.3245 data: 0.0041 max mem: 4874 +eval (validation): [12] [40/85] eta: 0:00:18 time: 0.3381 data: 0.0039 max mem: 4874 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3558 data: 0.0042 max mem: 4874 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3665 data: 0.0047 max mem: 4874 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3438 data: 0.0044 max mem: 4874 +eval (validation): [12] Total time: 0:00:32 (0.3823 s / it) +cv: [12] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 2.455 acc: 0.258 f1: 0.200 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:19:12 lr: nan time: 2.8801 data: 2.6595 max mem: 4874 +train: [13] [ 20/400] eta: 0:02:56 lr: 0.000133 loss: 2.5807 (2.6345) grad: 0.1731 (0.1786) time: 0.3425 data: 0.0036 max mem: 4874 +train: [13] [ 40/400] eta: 0:02:28 lr: 0.000131 loss: 2.6048 (2.6335) grad: 0.1731 (0.1733) time: 0.3593 data: 0.0045 max mem: 4874 +train: [13] [ 60/400] eta: 0:02:14 lr: 0.000130 loss: 2.6048 (2.6225) grad: 0.1760 (0.1724) time: 0.3605 data: 0.0050 max mem: 4874 +train: [13] [ 80/400] eta: 0:02:02 lr: 0.000128 loss: 2.6132 (2.6228) grad: 0.1671 (0.1708) time: 0.3415 data: 0.0052 max mem: 4874 +train: [13] [100/400] eta: 0:01:54 lr: 0.000127 loss: 2.6393 (2.6350) grad: 0.1690 (0.1719) time: 0.3749 data: 0.0049 max mem: 4874 +train: [13] [120/400] eta: 0:01:46 lr: 0.000125 loss: 2.6213 (2.6291) grad: 0.1551 (0.1700) time: 0.3760 data: 0.0049 max mem: 4874 +train: [13] [140/400] eta: 0:01:37 lr: 0.000124 loss: 2.5705 (2.6196) grad: 0.1551 (0.1693) time: 0.3406 data: 0.0048 max mem: 4874 +train: [13] [160/400] eta: 0:01:28 lr: 0.000122 loss: 2.5730 (2.6185) grad: 0.1624 (0.1699) time: 0.3255 data: 0.0048 max mem: 4874 +train: [13] [180/400] eta: 0:01:21 lr: 0.000120 loss: 2.6188 (2.6199) grad: 0.1726 (0.1706) time: 0.3856 data: 0.0050 max mem: 4874 +train: [13] [200/400] eta: 0:01:13 lr: 0.000119 loss: 2.6247 (2.6218) grad: 0.1701 (0.1709) time: 0.3637 data: 0.0049 max mem: 4874 +train: [13] [220/400] eta: 0:01:06 lr: 0.000117 loss: 2.6646 (2.6310) grad: 0.1649 (0.1715) time: 0.3568 data: 0.0049 max mem: 4874 +train: [13] [240/400] eta: 0:00:58 lr: 0.000116 loss: 2.6321 (2.6261) grad: 0.1747 (0.1715) time: 0.3430 data: 0.0045 max mem: 4874 +train: [13] [260/400] eta: 0:00:50 lr: 0.000114 loss: 2.6133 (2.6283) grad: 0.1751 (0.1731) time: 0.3361 data: 0.0049 max mem: 4874 +train: [13] [280/400] eta: 0:00:43 lr: 0.000113 loss: 2.6330 (2.6296) grad: 0.1768 (0.1731) time: 0.3614 data: 0.0051 max mem: 4874 +train: [13] [300/400] eta: 0:00:36 lr: 0.000111 loss: 2.6578 (2.6308) grad: 0.1625 (0.1729) time: 0.3663 data: 0.0047 max mem: 4874 +train: [13] [320/400] eta: 0:00:29 lr: 0.000110 loss: 2.6578 (2.6339) grad: 0.1625 (0.1725) time: 0.3539 data: 0.0047 max mem: 4874 +train: [13] [340/400] eta: 0:00:21 lr: 0.000108 loss: 2.6207 (2.6326) grad: 0.1690 (0.1725) time: 0.3502 data: 0.0049 max mem: 4874 +train: [13] [360/400] eta: 0:00:14 lr: 0.000107 loss: 2.6207 (2.6331) grad: 0.1657 (0.1720) time: 0.3634 data: 0.0051 max mem: 4874 +train: [13] [380/400] eta: 0:00:07 lr: 0.000105 loss: 2.6602 (2.6353) grad: 0.1597 (0.1715) time: 0.3606 data: 0.0053 max mem: 4874 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 2.6387 (2.6339) grad: 0.1570 (0.1711) time: 0.3755 data: 0.0047 max mem: 4874 +train: [13] Total time: 0:02:25 (0.3638 s / it) +train: [13] Summary: lr: 0.000104 loss: 2.6387 (2.6339) grad: 0.1570 (0.1711) +eval (validation): [13] [ 0/85] eta: 0:04:44 time: 3.3423 data: 3.0946 max mem: 4874 +eval (validation): [13] [20/85] eta: 0:00:32 time: 0.3642 data: 0.0059 max mem: 4874 +eval (validation): [13] [40/85] eta: 0:00:18 time: 0.3242 data: 0.0034 max mem: 4874 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3432 data: 0.0053 max mem: 4874 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3199 data: 0.0040 max mem: 4874 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3167 data: 0.0041 max mem: 4874 +eval (validation): [13] Total time: 0:00:31 (0.3747 s / it) +cv: [13] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.481 acc: 0.263 f1: 0.204 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [14] [ 0/400] eta: 0:20:17 lr: nan time: 3.0428 data: 2.7561 max mem: 4874 +train: [14] [ 20/400] eta: 0:03:15 lr: 0.000102 loss: 2.5819 (2.5938) grad: 0.1559 (0.1561) time: 0.3877 data: 0.0043 max mem: 4874 +train: [14] [ 40/400] eta: 0:02:38 lr: 0.000101 loss: 2.5909 (2.6068) grad: 0.1663 (0.1630) time: 0.3617 data: 0.0045 max mem: 4874 +train: [14] [ 60/400] eta: 0:02:20 lr: 0.000099 loss: 2.6079 (2.6050) grad: 0.1717 (0.1671) time: 0.3559 data: 0.0050 max mem: 4874 +train: [14] [ 80/400] eta: 0:02:06 lr: 0.000098 loss: 2.6025 (2.6087) grad: 0.1631 (0.1689) time: 0.3460 data: 0.0048 max mem: 4874 +train: [14] [100/400] eta: 0:01:56 lr: 0.000096 loss: 2.6159 (2.6143) grad: 0.1727 (0.1724) time: 0.3640 data: 0.0044 max mem: 4874 +train: [14] [120/400] eta: 0:01:47 lr: 0.000095 loss: 2.6328 (2.6188) grad: 0.1686 (0.1708) time: 0.3627 data: 0.0049 max mem: 4874 +train: [14] [140/400] eta: 0:01:38 lr: 0.000093 loss: 2.6602 (2.6292) grad: 0.1676 (0.1706) time: 0.3463 data: 0.0045 max mem: 4874 +train: [14] [160/400] eta: 0:01:30 lr: 0.000092 loss: 2.6602 (2.6309) grad: 0.1718 (0.1710) time: 0.3547 data: 0.0050 max mem: 4874 +train: [14] [180/400] eta: 0:01:22 lr: 0.000090 loss: 2.6597 (2.6341) grad: 0.1597 (0.1698) time: 0.3564 data: 0.0048 max mem: 4874 +train: [14] [200/400] eta: 0:01:14 lr: 0.000089 loss: 2.6153 (2.6317) grad: 0.1593 (0.1696) time: 0.3548 data: 0.0049 max mem: 4874 +train: [14] [220/400] eta: 0:01:06 lr: 0.000088 loss: 2.6161 (2.6318) grad: 0.1710 (0.1699) time: 0.3626 data: 0.0047 max mem: 4874 +train: [14] [240/400] eta: 0:00:59 lr: 0.000086 loss: 2.6161 (2.6277) grad: 0.1730 (0.1704) time: 0.3537 data: 0.0049 max mem: 4874 +train: [14] [260/400] eta: 0:00:51 lr: 0.000085 loss: 2.5899 (2.6307) grad: 0.1687 (0.1711) time: 0.3610 data: 0.0050 max mem: 4874 +train: [14] [280/400] eta: 0:00:44 lr: 0.000083 loss: 2.6446 (2.6298) grad: 0.1702 (0.1711) time: 0.3593 data: 0.0049 max mem: 4874 +train: [14] [300/400] eta: 0:00:36 lr: 0.000082 loss: 2.6060 (2.6290) grad: 0.1691 (0.1710) time: 0.3622 data: 0.0048 max mem: 4874 +train: [14] [320/400] eta: 0:00:29 lr: 0.000081 loss: 2.6358 (2.6323) grad: 0.1614 (0.1704) time: 0.3498 data: 0.0048 max mem: 4874 +train: [14] [340/400] eta: 0:00:22 lr: 0.000079 loss: 2.6414 (2.6311) grad: 0.1645 (0.1706) time: 0.3654 data: 0.0052 max mem: 4874 +train: [14] [360/400] eta: 0:00:14 lr: 0.000078 loss: 2.6390 (2.6330) grad: 0.1663 (0.1703) time: 0.3839 data: 0.0050 max mem: 4874 +train: [14] [380/400] eta: 0:00:07 lr: 0.000076 loss: 2.6437 (2.6308) grad: 0.1545 (0.1696) time: 0.3455 data: 0.0046 max mem: 4874 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 2.6249 (2.6307) grad: 0.1568 (0.1692) time: 0.3547 data: 0.0054 max mem: 4874 +train: [14] Total time: 0:02:26 (0.3666 s / it) +train: [14] Summary: lr: 0.000075 loss: 2.6249 (2.6307) grad: 0.1568 (0.1692) +eval (validation): [14] [ 0/85] eta: 0:04:41 time: 3.3128 data: 3.0280 max mem: 4874 +eval (validation): [14] [20/85] eta: 0:00:30 time: 0.3304 data: 0.0037 max mem: 4874 +eval (validation): [14] [40/85] eta: 0:00:17 time: 0.3157 data: 0.0037 max mem: 4874 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3453 data: 0.0047 max mem: 4874 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.3262 data: 0.0044 max mem: 4874 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.3183 data: 0.0044 max mem: 4874 +eval (validation): [14] Total time: 0:00:31 (0.3664 s / it) +cv: [14] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.496 acc: 0.261 f1: 0.210 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [15] [ 0/400] eta: 0:20:44 lr: nan time: 3.1118 data: 2.8421 max mem: 4874 +train: [15] [ 20/400] eta: 0:03:08 lr: 0.000074 loss: 2.5835 (2.5957) grad: 0.1666 (0.1720) time: 0.3656 data: 0.0051 max mem: 4874 +train: [15] [ 40/400] eta: 0:02:34 lr: 0.000072 loss: 2.6158 (2.6072) grad: 0.1639 (0.1697) time: 0.3586 data: 0.0038 max mem: 4874 +train: [15] [ 60/400] eta: 0:02:18 lr: 0.000071 loss: 2.6276 (2.6022) grad: 0.1639 (0.1722) time: 0.3652 data: 0.0049 max mem: 4874 +train: [15] [ 80/400] eta: 0:02:06 lr: 0.000070 loss: 2.5954 (2.6021) grad: 0.1698 (0.1734) time: 0.3579 data: 0.0050 max mem: 4874 +train: [15] [100/400] eta: 0:01:56 lr: 0.000068 loss: 2.6299 (2.6093) grad: 0.1689 (0.1714) time: 0.3609 data: 0.0054 max mem: 4874 +train: [15] [120/400] eta: 0:01:47 lr: 0.000067 loss: 2.5844 (2.5987) grad: 0.1703 (0.1710) time: 0.3599 data: 0.0050 max mem: 4874 +train: [15] [140/400] eta: 0:01:38 lr: 0.000066 loss: 2.5620 (2.5927) grad: 0.1688 (0.1700) time: 0.3383 data: 0.0048 max mem: 4874 +train: [15] [160/400] eta: 0:01:29 lr: 0.000064 loss: 2.5620 (2.5933) grad: 0.1618 (0.1696) time: 0.3421 data: 0.0048 max mem: 4874 +train: [15] [180/400] eta: 0:01:21 lr: 0.000063 loss: 2.5749 (2.5936) grad: 0.1647 (0.1699) time: 0.3623 data: 0.0046 max mem: 4874 +train: [15] [200/400] eta: 0:01:14 lr: 0.000062 loss: 2.6155 (2.5978) grad: 0.1661 (0.1702) time: 0.3563 data: 0.0048 max mem: 4874 +train: [15] [220/400] eta: 0:01:06 lr: 0.000061 loss: 2.6149 (2.5985) grad: 0.1645 (0.1700) time: 0.3631 data: 0.0047 max mem: 4874 +train: [15] [240/400] eta: 0:00:59 lr: 0.000059 loss: 2.6149 (2.6020) grad: 0.1677 (0.1701) time: 0.3732 data: 0.0049 max mem: 4874 +train: [15] [260/400] eta: 0:00:51 lr: 0.000058 loss: 2.6250 (2.6048) grad: 0.1617 (0.1695) time: 0.3630 data: 0.0049 max mem: 4874 +train: [15] [280/400] eta: 0:00:44 lr: 0.000057 loss: 2.6037 (2.6021) grad: 0.1616 (0.1694) time: 0.3627 data: 0.0052 max mem: 4874 +train: [15] [300/400] eta: 0:00:36 lr: 0.000056 loss: 2.6414 (2.6072) grad: 0.1663 (0.1692) time: 0.3522 data: 0.0050 max mem: 4874 +train: [15] [320/400] eta: 0:00:29 lr: 0.000054 loss: 2.6448 (2.6079) grad: 0.1599 (0.1687) time: 0.3480 data: 0.0049 max mem: 4874 +train: [15] [340/400] eta: 0:00:21 lr: 0.000053 loss: 2.6137 (2.6063) grad: 0.1530 (0.1692) time: 0.3668 data: 0.0052 max mem: 4874 +train: [15] [360/400] eta: 0:00:14 lr: 0.000052 loss: 2.6137 (2.6075) grad: 0.1594 (0.1690) time: 0.3649 data: 0.0051 max mem: 4874 +train: [15] [380/400] eta: 0:00:07 lr: 0.000051 loss: 2.6421 (2.6110) grad: 0.1763 (0.1696) time: 0.3689 data: 0.0048 max mem: 4874 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 2.6241 (2.6096) grad: 0.1659 (0.1694) time: 0.3640 data: 0.0050 max mem: 4874 +train: [15] Total time: 0:02:26 (0.3672 s / it) +train: [15] Summary: lr: 0.000050 loss: 2.6241 (2.6096) grad: 0.1659 (0.1694) +eval (validation): [15] [ 0/85] eta: 0:04:35 time: 3.2354 data: 3.0001 max mem: 4874 +eval (validation): [15] [20/85] eta: 0:00:30 time: 0.3368 data: 0.0052 max mem: 4874 +eval (validation): [15] [40/85] eta: 0:00:18 time: 0.3259 data: 0.0037 max mem: 4874 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3574 data: 0.0045 max mem: 4874 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3105 data: 0.0038 max mem: 4874 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.2995 data: 0.0037 max mem: 4874 +eval (validation): [15] Total time: 0:00:31 (0.3677 s / it) +cv: [15] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 2.445 acc: 0.268 f1: 0.215 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [16] [ 0/400] eta: 0:23:19 lr: nan time: 3.4988 data: 3.2013 max mem: 4874 +train: [16] [ 20/400] eta: 0:03:26 lr: 0.000048 loss: 2.6322 (2.6264) grad: 0.1613 (0.1585) time: 0.3959 data: 0.0050 max mem: 4874 +train: [16] [ 40/400] eta: 0:02:43 lr: 0.000047 loss: 2.6067 (2.6183) grad: 0.1620 (0.1664) time: 0.3621 data: 0.0039 max mem: 4874 +train: [16] [ 60/400] eta: 0:02:22 lr: 0.000046 loss: 2.5920 (2.6163) grad: 0.1642 (0.1679) time: 0.3496 data: 0.0048 max mem: 4874 +train: [16] [ 80/400] eta: 0:02:09 lr: 0.000045 loss: 2.6019 (2.6212) grad: 0.1683 (0.1699) time: 0.3613 data: 0.0049 max mem: 4874 +train: [16] [100/400] eta: 0:02:00 lr: 0.000044 loss: 2.6158 (2.6166) grad: 0.1705 (0.1708) time: 0.3926 data: 0.0050 max mem: 4874 +train: [16] [120/400] eta: 0:01:50 lr: 0.000043 loss: 2.5872 (2.6148) grad: 0.1717 (0.1719) time: 0.3466 data: 0.0047 max mem: 4874 +train: [16] [140/400] eta: 0:01:40 lr: 0.000042 loss: 2.5836 (2.6143) grad: 0.1768 (0.1722) time: 0.3315 data: 0.0049 max mem: 4874 +train: [16] [160/400] eta: 0:01:31 lr: 0.000041 loss: 2.6152 (2.6144) grad: 0.1727 (0.1725) time: 0.3566 data: 0.0051 max mem: 4874 +train: [16] [180/400] eta: 0:01:23 lr: 0.000040 loss: 2.6187 (2.6127) grad: 0.1669 (0.1723) time: 0.3624 data: 0.0051 max mem: 4874 +train: [16] [200/400] eta: 0:01:15 lr: 0.000039 loss: 2.6226 (2.6145) grad: 0.1653 (0.1715) time: 0.3587 data: 0.0049 max mem: 4874 +train: [16] [220/400] eta: 0:01:07 lr: 0.000038 loss: 2.6128 (2.6137) grad: 0.1667 (0.1719) time: 0.3563 data: 0.0049 max mem: 4874 +train: [16] [240/400] eta: 0:00:59 lr: 0.000036 loss: 2.5671 (2.6098) grad: 0.1629 (0.1711) time: 0.3629 data: 0.0049 max mem: 4874 +train: [16] [260/400] eta: 0:00:52 lr: 0.000035 loss: 2.5419 (2.6038) grad: 0.1574 (0.1718) time: 0.3603 data: 0.0050 max mem: 4874 +train: [16] [280/400] eta: 0:00:44 lr: 0.000034 loss: 2.5526 (2.6020) grad: 0.1696 (0.1711) time: 0.3519 data: 0.0048 max mem: 4874 +train: [16] [300/400] eta: 0:00:37 lr: 0.000033 loss: 2.5875 (2.5996) grad: 0.1621 (0.1702) time: 0.3449 data: 0.0049 max mem: 4874 +train: [16] [320/400] eta: 0:00:29 lr: 0.000032 loss: 2.5693 (2.6002) grad: 0.1626 (0.1702) time: 0.3498 data: 0.0048 max mem: 4874 +train: [16] [340/400] eta: 0:00:22 lr: 0.000031 loss: 2.5740 (2.5985) grad: 0.1687 (0.1698) time: 0.3682 data: 0.0047 max mem: 4874 +train: [16] [360/400] eta: 0:00:14 lr: 0.000031 loss: 2.5759 (2.5996) grad: 0.1586 (0.1693) time: 0.3597 data: 0.0049 max mem: 4874 +train: [16] [380/400] eta: 0:00:07 lr: 0.000030 loss: 2.5733 (2.5970) grad: 0.1487 (0.1685) time: 0.3444 data: 0.0046 max mem: 4874 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 2.5531 (2.5973) grad: 0.1502 (0.1682) time: 0.3547 data: 0.0051 max mem: 4874 +train: [16] Total time: 0:02:26 (0.3670 s / it) +train: [16] Summary: lr: 0.000029 loss: 2.5531 (2.5973) grad: 0.1502 (0.1682) +eval (validation): [16] [ 0/85] eta: 0:04:24 time: 3.1088 data: 2.9008 max mem: 4874 +eval (validation): [16] [20/85] eta: 0:00:30 time: 0.3430 data: 0.0058 max mem: 4874 +eval (validation): [16] [40/85] eta: 0:00:17 time: 0.3187 data: 0.0035 max mem: 4874 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3178 data: 0.0042 max mem: 4874 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.2963 data: 0.0034 max mem: 4874 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.2906 data: 0.0038 max mem: 4874 +eval (validation): [16] Total time: 0:00:30 (0.3531 s / it) +cv: [16] best hparam: (7.1, 1.0) (036) ('036_lr7.1e+00_wd1.0e+00') loss: 2.463 acc: 0.269 f1: 0.207 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [17] [ 0/400] eta: 0:22:34 lr: nan time: 3.3859 data: 3.1438 max mem: 4874 +train: [17] [ 20/400] eta: 0:03:10 lr: 0.000028 loss: 2.5642 (2.5681) grad: 0.1697 (0.1677) time: 0.3582 data: 0.0034 max mem: 4874 +train: [17] [ 40/400] eta: 0:02:36 lr: 0.000027 loss: 2.5536 (2.5672) grad: 0.1706 (0.1713) time: 0.3658 data: 0.0046 max mem: 4874 +train: [17] [ 60/400] eta: 0:02:19 lr: 0.000026 loss: 2.5873 (2.5827) grad: 0.1731 (0.1734) time: 0.3619 data: 0.0051 max mem: 4874 +train: [17] [ 80/400] eta: 0:02:06 lr: 0.000025 loss: 2.5951 (2.5770) grad: 0.1678 (0.1716) time: 0.3518 data: 0.0044 max mem: 4874 +train: [17] [100/400] eta: 0:01:55 lr: 0.000024 loss: 2.5913 (2.5838) grad: 0.1580 (0.1689) time: 0.3423 data: 0.0046 max mem: 4874 +train: [17] [120/400] eta: 0:01:46 lr: 0.000023 loss: 2.5834 (2.5821) grad: 0.1559 (0.1682) time: 0.3475 data: 0.0051 max mem: 4874 +train: [17] [140/400] eta: 0:01:38 lr: 0.000023 loss: 2.5834 (2.5856) grad: 0.1624 (0.1698) time: 0.3618 data: 0.0051 max mem: 4874 +train: [17] [160/400] eta: 0:01:30 lr: 0.000022 loss: 2.6051 (2.5886) grad: 0.1662 (0.1686) time: 0.3728 data: 0.0047 max mem: 4874 +train: [17] [180/400] eta: 0:01:22 lr: 0.000021 loss: 2.5916 (2.5908) grad: 0.1676 (0.1694) time: 0.3657 data: 0.0048 max mem: 4874 +train: [17] [200/400] eta: 0:01:15 lr: 0.000020 loss: 2.6045 (2.5912) grad: 0.1647 (0.1687) time: 0.3739 data: 0.0049 max mem: 4874 +train: [17] [220/400] eta: 0:01:07 lr: 0.000019 loss: 2.6045 (2.5918) grad: 0.1607 (0.1685) time: 0.3708 data: 0.0048 max mem: 4874 +train: [17] [240/400] eta: 0:00:59 lr: 0.000019 loss: 2.6052 (2.5902) grad: 0.1638 (0.1681) time: 0.3660 data: 0.0048 max mem: 4874 +train: [17] [260/400] eta: 0:00:52 lr: 0.000018 loss: 2.6076 (2.5917) grad: 0.1619 (0.1680) time: 0.3451 data: 0.0047 max mem: 4874 +train: [17] [280/400] eta: 0:00:44 lr: 0.000017 loss: 2.5918 (2.5915) grad: 0.1654 (0.1683) time: 0.3491 data: 0.0053 max mem: 4874 +train: [17] [300/400] eta: 0:00:37 lr: 0.000016 loss: 2.6001 (2.5951) grad: 0.1632 (0.1678) time: 0.3711 data: 0.0050 max mem: 4874 +train: [17] [320/400] eta: 0:00:29 lr: 0.000016 loss: 2.6359 (2.5957) grad: 0.1633 (0.1680) time: 0.3512 data: 0.0047 max mem: 4874 +train: [17] [340/400] eta: 0:00:22 lr: 0.000015 loss: 2.5784 (2.5934) grad: 0.1652 (0.1674) time: 0.3474 data: 0.0046 max mem: 4874 +train: [17] [360/400] eta: 0:00:14 lr: 0.000014 loss: 2.5588 (2.5916) grad: 0.1564 (0.1666) time: 0.3555 data: 0.0051 max mem: 4874 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 2.5637 (2.5911) grad: 0.1550 (0.1662) time: 0.3677 data: 0.0050 max mem: 4874 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 2.5858 (2.5926) grad: 0.1512 (0.1652) time: 0.3724 data: 0.0052 max mem: 4874 +train: [17] Total time: 0:02:27 (0.3680 s / it) +train: [17] Summary: lr: 0.000013 loss: 2.5858 (2.5926) grad: 0.1512 (0.1652) +eval (validation): [17] [ 0/85] eta: 0:04:17 time: 3.0285 data: 2.7853 max mem: 4874 +eval (validation): [17] [20/85] eta: 0:00:29 time: 0.3291 data: 0.0043 max mem: 4874 +eval (validation): [17] [40/85] eta: 0:00:18 time: 0.3500 data: 0.0043 max mem: 4874 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3314 data: 0.0039 max mem: 4874 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.3049 data: 0.0038 max mem: 4874 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.3031 data: 0.0037 max mem: 4874 +eval (validation): [17] Total time: 0:00:30 (0.3627 s / it) +cv: [17] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 2.452 acc: 0.273 f1: 0.212 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:22:18 lr: nan time: 3.3454 data: 3.1074 max mem: 4874 +train: [18] [ 20/400] eta: 0:03:15 lr: 0.000012 loss: 2.6011 (2.6008) grad: 0.1597 (0.1632) time: 0.3718 data: 0.0040 max mem: 4874 +train: [18] [ 40/400] eta: 0:02:38 lr: 0.000012 loss: 2.5871 (2.5796) grad: 0.1597 (0.1625) time: 0.3633 data: 0.0038 max mem: 4874 +train: [18] [ 60/400] eta: 0:02:24 lr: 0.000011 loss: 2.5568 (2.5815) grad: 0.1568 (0.1606) time: 0.3967 data: 0.0048 max mem: 4874 +train: [18] [ 80/400] eta: 0:02:11 lr: 0.000011 loss: 2.5822 (2.5899) grad: 0.1558 (0.1602) time: 0.3602 data: 0.0050 max mem: 4874 +train: [18] [100/400] eta: 0:01:59 lr: 0.000010 loss: 2.6079 (2.5875) grad: 0.1542 (0.1597) time: 0.3488 data: 0.0048 max mem: 4874 +train: [18] [120/400] eta: 0:01:50 lr: 0.000009 loss: 2.5608 (2.5851) grad: 0.1586 (0.1610) time: 0.3731 data: 0.0053 max mem: 4874 +train: [18] [140/400] eta: 0:01:42 lr: 0.000009 loss: 2.5848 (2.5927) grad: 0.1619 (0.1604) time: 0.3979 data: 0.0052 max mem: 4874 +train: [18] [160/400] eta: 0:01:34 lr: 0.000008 loss: 2.6128 (2.5927) grad: 0.1642 (0.1622) time: 0.3758 data: 0.0053 max mem: 4874 +train: [18] [180/400] eta: 0:01:25 lr: 0.000008 loss: 2.5979 (2.5925) grad: 0.1642 (0.1619) time: 0.3461 data: 0.0048 max mem: 4874 +train: [18] [200/400] eta: 0:01:16 lr: 0.000007 loss: 2.5535 (2.5868) grad: 0.1571 (0.1617) time: 0.3380 data: 0.0046 max mem: 4874 +train: [18] [220/400] eta: 0:01:08 lr: 0.000007 loss: 2.5658 (2.5867) grad: 0.1559 (0.1610) time: 0.3498 data: 0.0047 max mem: 4874 +train: [18] [240/400] eta: 0:01:00 lr: 0.000006 loss: 2.6006 (2.5854) grad: 0.1527 (0.1610) time: 0.3930 data: 0.0051 max mem: 4874 +train: [18] [260/400] eta: 0:00:53 lr: 0.000006 loss: 2.6162 (2.5881) grad: 0.1578 (0.1611) time: 0.3884 data: 0.0049 max mem: 4874 +train: [18] [280/400] eta: 0:00:45 lr: 0.000006 loss: 2.6036 (2.5877) grad: 0.1531 (0.1604) time: 0.3537 data: 0.0051 max mem: 4874 +train: [18] [300/400] eta: 0:00:37 lr: 0.000005 loss: 2.5935 (2.5869) grad: 0.1458 (0.1597) time: 0.3697 data: 0.0053 max mem: 4874 +train: [18] [320/400] eta: 0:00:30 lr: 0.000005 loss: 2.5935 (2.5873) grad: 0.1516 (0.1599) time: 0.3822 data: 0.0052 max mem: 4874 +train: [18] [340/400] eta: 0:00:22 lr: 0.000004 loss: 2.5912 (2.5872) grad: 0.1616 (0.1598) time: 0.3687 data: 0.0051 max mem: 4874 +train: [18] [360/400] eta: 0:00:15 lr: 0.000004 loss: 2.5578 (2.5867) grad: 0.1576 (0.1599) time: 0.3766 data: 0.0050 max mem: 4874 +train: [18] [380/400] eta: 0:00:07 lr: 0.000004 loss: 2.5708 (2.5873) grad: 0.1627 (0.1603) time: 0.3357 data: 0.0047 max mem: 4874 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 2.6177 (2.5887) grad: 0.1669 (0.1608) time: 0.3278 data: 0.0042 max mem: 4874 +train: [18] Total time: 0:02:29 (0.3740 s / it) +train: [18] Summary: lr: 0.000003 loss: 2.6177 (2.5887) grad: 0.1669 (0.1608) +eval (validation): [18] [ 0/85] eta: 0:04:13 time: 2.9774 data: 2.7740 max mem: 4874 +eval (validation): [18] [20/85] eta: 0:00:28 time: 0.3146 data: 0.0168 max mem: 4874 +eval (validation): [18] [40/85] eta: 0:00:16 time: 0.3086 data: 0.0040 max mem: 4874 +eval (validation): [18] [60/85] eta: 0:00:08 time: 0.2894 data: 0.0033 max mem: 4874 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3085 data: 0.0039 max mem: 4874 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.2976 data: 0.0039 max mem: 4874 +eval (validation): [18] Total time: 0:00:28 (0.3387 s / it) +cv: [18] best hparam: (22, 1.0) (043) ('043_lr2.2e+01_wd1.0e+00') loss: 2.456 acc: 0.268 f1: 0.215 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:20:35 lr: nan time: 3.0900 data: 2.8287 max mem: 4874 +train: [19] [ 20/400] eta: 0:02:52 lr: 0.000003 loss: 2.5257 (2.5626) grad: 0.1611 (0.1629) time: 0.3235 data: 0.0036 max mem: 4874 +train: [19] [ 40/400] eta: 0:02:20 lr: 0.000003 loss: 2.5438 (2.5410) grad: 0.1614 (0.1628) time: 0.3219 data: 0.0035 max mem: 4874 +train: [19] [ 60/400] eta: 0:02:06 lr: 0.000002 loss: 2.5438 (2.5389) grad: 0.1568 (0.1607) time: 0.3372 data: 0.0046 max mem: 4874 +train: [19] [ 80/400] eta: 0:01:55 lr: 0.000002 loss: 2.5803 (2.5597) grad: 0.1543 (0.1581) time: 0.3304 data: 0.0046 max mem: 4874 +train: [19] [100/400] eta: 0:01:49 lr: 0.000002 loss: 2.5939 (2.5609) grad: 0.1559 (0.1572) time: 0.3691 data: 0.0049 max mem: 4874 +train: [19] [120/400] eta: 0:01:40 lr: 0.000002 loss: 2.5957 (2.5677) grad: 0.1547 (0.1571) time: 0.3288 data: 0.0048 max mem: 4874 +train: [19] [140/400] eta: 0:01:31 lr: 0.000001 loss: 2.5566 (2.5638) grad: 0.1538 (0.1573) time: 0.3283 data: 0.0046 max mem: 4874 +train: [19] [160/400] eta: 0:01:24 lr: 0.000001 loss: 2.5444 (2.5639) grad: 0.1595 (0.1585) time: 0.3268 data: 0.0045 max mem: 4874 +train: [19] [180/400] eta: 0:01:16 lr: 0.000001 loss: 2.5734 (2.5666) grad: 0.1660 (0.1607) time: 0.3252 data: 0.0045 max mem: 4874 +train: [19] [200/400] eta: 0:01:09 lr: 0.000001 loss: 2.5994 (2.5713) grad: 0.1644 (0.1609) time: 0.3420 data: 0.0049 max mem: 4874 +train: [19] [220/400] eta: 0:01:02 lr: 0.000001 loss: 2.5877 (2.5697) grad: 0.1611 (0.1612) time: 0.3694 data: 0.0050 max mem: 4874 +train: [19] [240/400] eta: 0:00:55 lr: 0.000001 loss: 2.5391 (2.5683) grad: 0.1543 (0.1605) time: 0.3588 data: 0.0050 max mem: 4874 +train: [19] [260/400] eta: 0:00:49 lr: 0.000000 loss: 2.5506 (2.5702) grad: 0.1502 (0.1607) time: 0.3673 data: 0.0049 max mem: 4874 +train: [19] [280/400] eta: 0:00:42 lr: 0.000000 loss: 2.5613 (2.5709) grad: 0.1464 (0.1600) time: 0.3632 data: 0.0048 max mem: 4874 +train: [19] [300/400] eta: 0:00:35 lr: 0.000000 loss: 2.5948 (2.5744) grad: 0.1607 (0.1605) time: 0.3628 data: 0.0044 max mem: 4874 +train: [19] [320/400] eta: 0:00:28 lr: 0.000000 loss: 2.6062 (2.5777) grad: 0.1663 (0.1611) time: 0.3333 data: 0.0047 max mem: 4874 +train: [19] [340/400] eta: 0:00:21 lr: 0.000000 loss: 2.5802 (2.5772) grad: 0.1615 (0.1606) time: 0.3329 data: 0.0049 max mem: 4874 +train: [19] [360/400] eta: 0:00:14 lr: 0.000000 loss: 2.5842 (2.5788) grad: 0.1509 (0.1606) time: 0.3502 data: 0.0049 max mem: 4874 +train: [19] [380/400] eta: 0:00:07 lr: 0.000000 loss: 2.5904 (2.5787) grad: 0.1550 (0.1605) time: 0.3566 data: 0.0047 max mem: 4874 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 2.5528 (2.5770) grad: 0.1542 (0.1602) time: 0.3698 data: 0.0045 max mem: 4874 +train: [19] Total time: 0:02:20 (0.3522 s / it) +train: [19] Summary: lr: 0.000000 loss: 2.5528 (2.5770) grad: 0.1542 (0.1602) +eval (validation): [19] [ 0/85] eta: 0:04:06 time: 2.9022 data: 2.7101 max mem: 4874 +eval (validation): [19] [20/85] eta: 0:00:33 time: 0.3997 data: 0.0221 max mem: 4874 +eval (validation): [19] [40/85] eta: 0:00:19 time: 0.3521 data: 0.0040 max mem: 4874 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3191 data: 0.0043 max mem: 4874 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3210 data: 0.0042 max mem: 4874 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.3064 data: 0.0040 max mem: 4874 +eval (validation): [19] Total time: 0:00:32 (0.3790 s / it) +cv: [19] best hparam: (16, 1.0) (041) ('041_lr1.6e+01_wd1.0e+00') loss: 2.452 acc: 0.268 f1: 0.209 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-last.pth +eval model info: +{"score": 0.2681801402731635, "hparam": [16, 1.0], "hparam_id": 41, "epoch": 19, "is_best": false, "best_score": 0.27260981912144705} +eval (train): [20] [ 0/509] eta: 0:22:51 time: 2.6938 data: 2.4516 max mem: 4874 +eval (train): [20] [ 20/509] eta: 0:03:34 time: 0.3252 data: 0.0044 max mem: 4874 +eval (train): [20] [ 40/509] eta: 0:02:56 time: 0.3094 data: 0.0040 max mem: 4874 +eval (train): [20] [ 60/509] eta: 0:02:35 time: 0.2886 data: 0.0038 max mem: 4874 +eval (train): [20] [ 80/509] eta: 0:02:23 time: 0.2937 data: 0.0038 max mem: 4874 +eval (train): [20] [100/509] eta: 0:02:14 time: 0.3147 data: 0.0038 max mem: 4874 +eval (train): [20] [120/509] eta: 0:02:07 time: 0.3168 data: 0.0040 max mem: 4874 +eval (train): [20] [140/509] eta: 0:01:59 time: 0.2959 data: 0.0040 max mem: 4874 +eval (train): [20] [160/509] eta: 0:01:52 time: 0.3049 data: 0.0041 max mem: 4874 +eval (train): [20] [180/509] eta: 0:01:45 time: 0.3117 data: 0.0041 max mem: 4874 +eval (train): [20] [200/509] eta: 0:01:38 time: 0.2996 data: 0.0040 max mem: 4874 +eval (train): [20] [220/509] eta: 0:01:31 time: 0.3037 data: 0.0037 max mem: 4874 +eval (train): [20] [240/509] eta: 0:01:25 time: 0.3176 data: 0.0041 max mem: 4874 +eval (train): [20] [260/509] eta: 0:01:18 time: 0.3052 data: 0.0038 max mem: 4874 +eval (train): [20] [280/509] eta: 0:01:12 time: 0.3224 data: 0.0040 max mem: 4874 +eval (train): [20] [300/509] eta: 0:01:05 time: 0.2949 data: 0.0038 max mem: 4874 +eval (train): [20] [320/509] eta: 0:00:59 time: 0.2999 data: 0.0038 max mem: 4874 +eval (train): [20] [340/509] eta: 0:00:53 time: 0.3118 data: 0.0039 max mem: 4874 +eval (train): [20] [360/509] eta: 0:00:46 time: 0.3064 data: 0.0039 max mem: 4874 +eval (train): [20] [380/509] eta: 0:00:40 time: 0.3239 data: 0.0041 max mem: 4874 +eval (train): [20] [400/509] eta: 0:00:34 time: 0.3327 data: 0.0044 max mem: 4874 +eval (train): [20] [420/509] eta: 0:00:28 time: 0.3513 data: 0.0044 max mem: 4874 +eval (train): [20] [440/509] eta: 0:00:21 time: 0.3494 data: 0.0044 max mem: 4874 +eval (train): [20] [460/509] eta: 0:00:15 time: 0.3259 data: 0.0040 max mem: 4874 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3106 data: 0.0041 max mem: 4874 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.3072 data: 0.0040 max mem: 4874 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2945 data: 0.0040 max mem: 4874 +eval (train): [20] Total time: 0:02:42 (0.3188 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:21 time: 3.0726 data: 2.8502 max mem: 4874 +eval (validation): [20] [20/85] eta: 0:00:29 time: 0.3230 data: 0.0043 max mem: 4874 +eval (validation): [20] [40/85] eta: 0:00:17 time: 0.3357 data: 0.0040 max mem: 4874 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3830 data: 0.0041 max mem: 4874 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3302 data: 0.0039 max mem: 4874 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3224 data: 0.0038 max mem: 4874 +eval (validation): [20] Total time: 0:00:31 (0.3749 s / it) +eval (test): [20] [ 0/85] eta: 0:04:27 time: 3.1417 data: 2.8545 max mem: 4874 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3285 data: 0.0031 max mem: 4874 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3668 data: 0.0044 max mem: 4874 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3348 data: 0.0042 max mem: 4874 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3255 data: 0.0043 max mem: 4874 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3141 data: 0.0041 max mem: 4874 +eval (test): [20] Total time: 0:00:31 (0.3726 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:08 time: 3.0338 data: 2.8151 max mem: 4874 +eval (testid): [20] [20/82] eta: 0:00:28 time: 0.3337 data: 0.0041 max mem: 4874 +eval (testid): [20] [40/82] eta: 0:00:16 time: 0.3301 data: 0.0036 max mem: 4874 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3313 data: 0.0043 max mem: 4874 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3188 data: 0.0047 max mem: 4874 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3090 data: 0.0045 max mem: 4874 +eval (testid): [20] Total time: 0:00:29 (0.3622 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/checkpoint-best.pth +eval model info: +{"score": 0.27260981912144705, "hparam": [16, 1.0], "hparam_id": 41, "epoch": 17, "is_best": true, "best_score": 0.27260981912144705} +eval (train): [20] [ 0/509] eta: 0:26:31 time: 3.1273 data: 2.9026 max mem: 4874 +eval (train): [20] [ 20/509] eta: 0:04:07 time: 0.3746 data: 0.0271 max mem: 4874 +eval (train): [20] [ 40/509] eta: 0:03:22 time: 0.3532 data: 0.0046 max mem: 4874 +eval (train): [20] [ 60/509] eta: 0:03:00 time: 0.3412 data: 0.0039 max mem: 4874 +eval (train): [20] [ 80/509] eta: 0:02:43 time: 0.3200 data: 0.0041 max mem: 4874 +eval (train): [20] [100/509] eta: 0:02:33 time: 0.3480 data: 0.0045 max mem: 4874 +eval (train): [20] [120/509] eta: 0:02:23 time: 0.3326 data: 0.0043 max mem: 4874 +eval (train): [20] [140/509] eta: 0:02:14 time: 0.3456 data: 0.0049 max mem: 4874 +eval (train): [20] [160/509] eta: 0:02:06 time: 0.3520 data: 0.0037 max mem: 4874 +eval (train): [20] [180/509] eta: 0:01:57 time: 0.3069 data: 0.0043 max mem: 4874 +eval (train): [20] [200/509] eta: 0:01:49 time: 0.3254 data: 0.0042 max mem: 4874 +eval (train): [20] [220/509] eta: 0:01:41 time: 0.3246 data: 0.0043 max mem: 4874 +eval (train): [20] [240/509] eta: 0:01:33 time: 0.3245 data: 0.0040 max mem: 4874 +eval (train): [20] [260/509] eta: 0:01:26 time: 0.3194 data: 0.0041 max mem: 4874 +eval (train): [20] [280/509] eta: 0:01:19 time: 0.3399 data: 0.0047 max mem: 4874 +eval (train): [20] [300/509] eta: 0:01:12 time: 0.3325 data: 0.0038 max mem: 4874 +eval (train): [20] [320/509] eta: 0:01:04 time: 0.3227 data: 0.0039 max mem: 4874 +eval (train): [20] [340/509] eta: 0:00:57 time: 0.3226 data: 0.0041 max mem: 4874 +eval (train): [20] [360/509] eta: 0:00:51 time: 0.3524 data: 0.0049 max mem: 4874 +eval (train): [20] [380/509] eta: 0:00:44 time: 0.3534 data: 0.0043 max mem: 4874 +eval (train): [20] [400/509] eta: 0:00:37 time: 0.3326 data: 0.0040 max mem: 4874 +eval (train): [20] [420/509] eta: 0:00:30 time: 0.3327 data: 0.0041 max mem: 4874 +eval (train): [20] [440/509] eta: 0:00:23 time: 0.3711 data: 0.0042 max mem: 4874 +eval (train): [20] [460/509] eta: 0:00:16 time: 0.3678 data: 0.0045 max mem: 4874 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3392 data: 0.0039 max mem: 4874 +eval (train): [20] [500/509] eta: 0:00:03 time: 0.3354 data: 0.0038 max mem: 4874 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.3162 data: 0.0036 max mem: 4874 +eval (train): [20] Total time: 0:02:55 (0.3454 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:40 time: 3.2998 data: 3.0118 max mem: 4874 +eval (validation): [20] [20/85] eta: 0:00:34 time: 0.3994 data: 0.0054 max mem: 4874 +eval (validation): [20] [40/85] eta: 0:00:20 time: 0.3469 data: 0.0043 max mem: 4874 +eval (validation): [20] [60/85] eta: 0:00:10 time: 0.3351 data: 0.0045 max mem: 4874 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3098 data: 0.0039 max mem: 4874 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3001 data: 0.0039 max mem: 4874 +eval (validation): [20] Total time: 0:00:32 (0.3827 s / it) +eval (test): [20] [ 0/85] eta: 0:04:35 time: 3.2417 data: 2.9528 max mem: 4874 +eval (test): [20] [20/85] eta: 0:00:34 time: 0.3891 data: 0.0051 max mem: 4874 +eval (test): [20] [40/85] eta: 0:00:19 time: 0.3215 data: 0.0038 max mem: 4874 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3464 data: 0.0045 max mem: 4874 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3413 data: 0.0045 max mem: 4874 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3308 data: 0.0044 max mem: 4874 +eval (test): [20] Total time: 0:00:32 (0.3832 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:20 time: 3.1730 data: 2.8967 max mem: 4874 +eval (testid): [20] [20/82] eta: 0:00:29 time: 0.3494 data: 0.0065 max mem: 4874 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3664 data: 0.0045 max mem: 4874 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3561 data: 0.0047 max mem: 4874 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.3329 data: 0.0044 max mem: 4874 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.3233 data: 0.0041 max mem: 4874 +eval (testid): [20] Total time: 0:00:31 (0.3865 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:------|:-------------|:-------|--------:|-------:|-----:|------------:|:----------|:-----------|-------:|--------:|----------:|--------:|----------:| +| flat_mae | reg | attn | nsd_cococlip | best | 17 | 0.0048 | 0.05 | 41 | [16, 1.0] | train | 2.0622 | 0.37257 | 0.002469 | 0.32557 | 0.0025967 | +| flat_mae | reg | attn | nsd_cococlip | best | 17 | 0.0048 | 0.05 | 41 | [16, 1.0] | validation | 2.4524 | 0.27261 | 0.0053846 | 0.21158 | 0.0047765 | +| flat_mae | reg | attn | nsd_cococlip | best | 17 | 0.0048 | 0.05 | 41 | [16, 1.0] | test | 2.3252 | 0.30557 | 0.0053189 | 0.2452 | 0.0052805 | +| flat_mae | reg | attn | nsd_cococlip | best | 17 | 0.0048 | 0.05 | 41 | [16, 1.0] | testid | 2.4315 | 0.26856 | 0.0054351 | 0.21962 | 0.0052647 | + + +done! total time: 1:11:31 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/train_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..f62db2209bcccaab0bcc7a2a6f4dc6296fadc242 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__attn/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.159836786985397, "train/grad": 0.06415268294513225, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.185142822265625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.184765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1842333984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.183712158203125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1832080078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1824951171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.18169189453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.180797119140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.17977294921875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.17855712890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.177427978515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.175830078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.174322509765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.17219482421875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.170289306640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.16845703125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.166383056640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.164119873046875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.161795654296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.159852294921875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.15764892578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.15573486328125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.153900146484375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.152215576171875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1506689453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.14911865234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.147860107421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.146925048828125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.145992431640625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.14504638671875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.144488525390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.144151611328125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.144058837890625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.14413330078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.14430908203125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.14469482421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.145247802734375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.14570068359375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.146256103515625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.14691650390625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.14736083984375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.14790771484375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.148699951171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.149600830078125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1503955078125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1513031005859373, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1527410888671876, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.15561767578125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.15826171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009639218032825738, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009628830151632429, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00961187229724601, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00959505484206602, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009578311296645553, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009555683396756649, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009530632726382464, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009503063147421926, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009468260877765715, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009432701589539648, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009399631624110043, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009352160536218434, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00930897449143231, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009250287564937025, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009199761776253581, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00915613594930619, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009106840549502521, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00905757256783545, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00901359940180555, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008982768668793141, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008954640373121946, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008936928412877023, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00892658171011135, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00892243861220777, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008921570603270083, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008923860101494938, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008926226599141955, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008928030251991004, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008930246878881007, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008932035095058381, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008932777461595834, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008933500749990345, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00893360778922215, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0089319052034989, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008926027773413807, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008915683354716748, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.008898874141741543, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.00887950926553458, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.008855909283738583, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.008822751597035676, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.008799005805049092, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.008785684464965016, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.008792197909206151, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.008833759718108923, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.008927397294901312, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009088249560445547, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009291788837872446, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009620856447145342, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009923506702762097, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1790192127227783, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.178013801574707, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1763644218444824, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1747608184814453, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1732125282287598, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1710991859436035, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.168757438659668, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1662790775299072, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1631298065185547, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1599338054656982, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.156963348388672, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1528096199035645, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1490697860717773, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1442341804504395, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1402101516723633, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1368629932403564, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.133298397064209, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.130033493041992, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.127384901046753, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.125657558441162, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1243128776550293, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.123502492904663, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1229474544525146, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1225876808166504, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.122260570526123, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1219117641448975, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.121659755706787, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.12149977684021, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1214852333068848, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.121823310852051, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1223793029785156, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1229970455169678, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.123767375946045, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.124403476715088, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1251189708709717, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1259751319885254, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.127269744873047, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1287176609039307, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1301684379577637, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.131136178970337, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1309170722961426, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1307291984558105, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1312453746795654, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1317296028137207, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.134269952774048, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.140194892883301, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.142404794692993, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.13900089263916, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1579160690307617, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04780361757105943, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.052417866371354746, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.056847545219638244, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05795496493170912, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.057770394979697305, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.059431524547803614, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06109265411590993, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06201550387596899, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06090808416389812, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07032115171650055, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.0725359911406423, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07345884090070137, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07179771133259505, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07087486157253599, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06866002214839424, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06736803248431156, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.06939830195644149, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.06755260243632337, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0664451827242525, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06256921373200443, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.015298631115864209, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.016357322034544916, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016763438481745736, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014910579548053833, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014118050081621723, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013601133572406323, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012538717727385707, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01138666166890223, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0096426884076877, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00956820238701284, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009563009007160107, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0086449180679695, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007764769492816961, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.004967753181105108, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.004963245933900562, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0049615228837586066, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.004963245933900562, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.004965832754227473, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.005438754055883038, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.006079774273844356, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.006486736327011167, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0077698966735743336, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.009594053082508514, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.012859979943182403, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.013206760648489824, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.011626945606950295, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.014084502873455937, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.014747173969637107, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.014097900528577767, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.012306074794107058, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.010731316284640349, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.010982901962294516, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.011035286226906053, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.01343466822872072, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.015750767921219707, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.01862901709478815, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.014184045792783791, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.010679408187328205, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 3.14469482421875, "validation/loss_best": 3.1259751319885254, "validation/acc_best": 0.07364341085271318, "validation/f1_best": 0.013206760648489824} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.0890160501003265, "train/grad": 0.08655033377930522, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1724951171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.17062255859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.167659912109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.164822998046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.16219970703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.15879150390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.155322265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.15193603515625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.148006591796875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.144544677734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.14162109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.137991943359375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.135384521484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.13263427734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.13063720703125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.129393310546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.128189697265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12742431640625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1268408203125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.126707763671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12662841796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.126591796875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12672607421875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12675048828125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.126954345703125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.12714599609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.127310791015625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.127542724609375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.127847900390625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.128463134765625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12900390625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.129559326171875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.130384521484375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.130980224609375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.131016845703125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1277447509765626, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1028646850585937, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.072168273925781, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.040411376953125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0065496826171874, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.983343276977539, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.9524740600585937, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.910846710205078, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.8938554382324218, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.8843491744995116, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.890537796020508, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.868574523925781, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.883336944580078, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.9086000442504885, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009456522895488888, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009404222399462014, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009324674375820905, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009253473109565676, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009188682704698295, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009111187469679862, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009037268969696016, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008969972331542522, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.00890327150700614, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008853539482224733, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008821507298853249, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00879936087410897, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008799687598366291, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008819432067684829, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00884852848481387, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008881090548820794, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008922066900413483, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00896614498924464, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009006445158738642, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00903545605717227, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009060665383003652, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009076271839439869, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00908387013943866, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009083163330797107, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009074467362370341, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009055121771525591, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009030884054955095, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009001422454603017, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.008952179292682558, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008879410224035383, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.008805303270928561, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.008734677345491946, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.008642254951409996, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.008568328083492815, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.008513001352548599, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.008708736919797956, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009902290573809296, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.011103939616587013, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.012210614811629057, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01332175774499774, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.014794814339838923, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.016176407106686382, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.017076404846739023, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01842898408183828, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.019683346867095677, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.020769965138752015, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.022656052899546923, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.024037623836193234, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.02601841519586742, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1612977981567383, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.158416986465454, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1540215015411377, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.150113821029663, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1466407775878906, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.142435073852539, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1384408473968506, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.134812593460083, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1311874389648438, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.128450870513916, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.126585006713867, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124835968017578, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.12388277053833, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1232311725616455, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1230123043060303, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1229355335235596, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1229631900787354, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123041868209839, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1232008934020996, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.123392105102539, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.123697280883789, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124159812927246, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124774217605591, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1256089210510254, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1267080307006836, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1283626556396484, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1301653385162354, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.132054090499878, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1350338459014893, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.138993501663208, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1426656246185303, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1456592082977295, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.148235559463501, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.147773027420044, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.140160322189331, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0734732151031494, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.922813653945923, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.8746273517608643, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.834322214126587, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.7679929733276367, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.725080966949463, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.707965612411499, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7352774143218994, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.8396871089935303, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.8391220569610596, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0072758197784424, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0990142822265625, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0316877365112305, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1558029651641846, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06570690291620525, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.09191583610188261, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.13233665559246954, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.15485418973791068, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.1539313399778516, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.1758951642672573, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.18161683277962348, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.18290882244370615, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18549280177187155, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.1613141380583241, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.17515688445921004, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.13990402362495385, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.14174972314507198, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.14285714285714285, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.13215208564045774, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.009962237182079668, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009612025942096127, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009226003325611966, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007939998213112379, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0062209503568187614, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00495997215454229, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.005444250545806686, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.007914348954136122, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.009772210728211156, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01156695096696469, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.010231022495331003, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009335035785550614, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.0099514832457087, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.00986422782888116, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.00984970851435149, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009585191342025444, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.009676292238678117, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01009056482289321, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.019222564191914166, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.033257108252489745, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.05363332134122276, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.07142710605794642, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.07476636244624511, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.0894972765891378, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.09643744779563701, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.102554419101473, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.09556367654523319, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.08731987717257188, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.07634660521294608, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.06663654940668655, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.07068135122579829, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.07034937695823575, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.056025556504151273, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 2.910846710205078, "validation/loss_best": 2.7352774143218994, "validation/acc_best": 0.18549280177187155, "validation/f1_best": 0.09556367654523319} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.0480228793621063, "train/grad": 0.1995675752684474, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.153441162109375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.15011962890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1454248046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.141480712890625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1383349609375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.134937744140625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13201416015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.129725341796875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127777099609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12666259765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12588134765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125357666015625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125064697265625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.124879150390625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.124644775390625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12466552734375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.124521484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124329833984375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12428955078125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.124144287109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12373779296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.123489990234375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.123280029296875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1230224609375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1226513671875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.122337646484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12181640625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.120753173828125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1144757080078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.0845126342773437, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.041781005859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.9656248474121094, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.915769271850586, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.8579912567138672, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.7810979080200195, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.733511505126953, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.7012345886230467, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.6857102966308593, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.6662952423095705, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.653678092956543, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6542030715942384, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.654794158935547, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.671536617279053, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7020417428016663, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.706820845603943, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.770733575820923, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9208832216262817, "train/loss_048_lr5.0e+01_wd1.0e+00": 5.337737073898316, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008944617388769983, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008877064264379442, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008790132515132427, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008730095282662659, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008692803378216922, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008666913257911801, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00866516601992771, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00868462582817301, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008724035159684718, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00877101460006088, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00881412509130314, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008867075992748141, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008903782474808395, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008934192857705057, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008948736560996621, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008955171627458186, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008957386831752956, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008954868391156197, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008946993902791292, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00893475286429748, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008912691690493375, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008880661588627846, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008835184671916067, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008772570276632904, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008694735122844577, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00858657926786691, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.008484762229491025, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.008390383855439722, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00829470083117485, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.008600010927766561, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010227722995914519, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.012170021866913884, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01458612403832376, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.016493756528943776, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01843963195104152, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.020095986276865006, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.021528650331310926, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02276993464678526, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.024036814351566137, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.023533022808842362, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02392604487016797, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02486351992469281, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02680328531190753, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.029373578717932104, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.028112350581213832, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.031161707499995826, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.03460657803341746, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0488452812936157, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.12095645193941891, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1424736976623535, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.139050006866455, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1345250606536865, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1312313079833984, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1288442611694336, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1266424655914307, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1251635551452637, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.124300241470337, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1238574981689453, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123786687850952, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123893976211548, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124213457107544, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1245782375335693, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.125148057937622, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.125753879547119, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.126312255859375, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.127018451690674, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.127779722213745, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.128498077392578, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.129002094268799, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.129462480545044, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.129808187484741, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.130070686340332, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1303470134735107, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1305172443389893, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.130349636077881, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.129459857940674, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.127810478210449, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.122563362121582, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.0501582622528076, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.9107556343078613, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.827399253845215, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.7597131729125977, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.7451329231262207, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.7274088859558105, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.6930229663848877, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.6609578132629395, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.638225793838501, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.619586229324341, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6848950386047363, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.692593574523926, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.7054879665374756, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.7334554195404053, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.747189521789551, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.744267463684082, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7932944297790527, "validation/loss_046_lr3.6e+01_wd1.0e+00": 2.8661649227142334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.052922487258911, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06829088224437062, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.067921742340347, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.067921742340347, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06201550387596899, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06275378368401624, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.10483573274270949, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.13252122554448137, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.1491325212255445, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.17368032484311555, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.1773717238833518, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.1834625322997416, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.19029162052417867, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.19878183831672203, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.20431893687707642, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.20764119601328904, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.19195275009228496, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.19509043927648578, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19121447028423771, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.18660022148394242, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.18383167220376523, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.18290882244370615, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.1644518272425249, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.18715393133997785, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.17958656330749354, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005865511674553923, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.005181771846187326, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005179761676255856, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006164074825332432, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007506647315793878, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00798493196368265, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008228058291289296, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009781629298169274, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011115179700088533, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012262143563300028, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.013061964419239838, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01377902964059424, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.013525091053716064, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.012488655183912586, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.011659871619879929, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010357567661527905, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00996228770216191, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010834222290603551, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.00973852145322082, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.008373377748530395, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.006408776240232572, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.006003253334777504, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005437826867406809, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.006051478011674094, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.030620446641311482, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.05038512606036797, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.0670546886474246, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.0867715910443218, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.09301296342946001, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.09753603704931006, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.10426969547484256, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.11436885355784436, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.12396716070963433, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.12790673520849086, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.13006943739608343, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12910227679319697, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.12699556760715489, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.13184844665100948, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.12506982218061138, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11944742220965171, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.11105381845187594, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.10153692764693582, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.10738322383045047, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 2.6857102966308593, "validation/loss_best": 2.619586229324341, "validation/acc_best": 0.20764119601328904, "validation/f1_best": 0.12790673520849086} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.0611548709869383, "train/grad": 0.29113490201532843, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13884521484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.136241455078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.133094482421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131182861328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12993408203125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128802490234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1282421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127799072265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127572021484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127333984375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.127115478515625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12692626953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12680908203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126343994140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1261083984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12593017578125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.125694580078125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12550537109375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12542724609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1251806640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12482666015625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12447509765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.123782958984375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.122760009765625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1168414306640626, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.077413787841797, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.0146333312988283, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.9137832641601564, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.8058275604248046, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.7394189643859863, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.7042828750610353, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.665050325393677, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.649902582168579, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.634509496688843, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.6143295192718505, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.6082727813720705, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.589451274871826, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.581548223495483, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5979697036743166, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.6110355949401853, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.6386185264587403, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.650151629447937, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6812238550186156, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.7327667570114134, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.929391760826111, "train/loss_046_lr3.6e+01_wd1.0e+00": 6.147349400520325, "train/loss_047_lr4.3e+01_wd1.0e+00": 4.928448009490967, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008606413369998336, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00858583150897175, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008586587342433631, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00861454074503854, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00865415574517101, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008712543337605894, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008769843294285238, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008818518563639372, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0088605374423787, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008887057851534336, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008902622289024293, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008913754634559155, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008917358457110822, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008916901738848538, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0089119554287754, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008903430406935513, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008888386068865656, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008864064554218202, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008828535091597587, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008786214932333678, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008723761897999793, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008648423741105945, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00855886998353526, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.008465793975628912, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.008411237942054868, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.008774572091642768, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010873140955809504, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.013458154979161918, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.01684494046261534, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.020729755158536135, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.022352787810377778, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02313884957227856, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.02421364700887352, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.024762767823413013, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02544086747802794, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.02627111837733537, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.027232643188908695, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.027373434798792003, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.02780624818056822, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.026038926905021072, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02699418170377612, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.029328165110200644, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03214713611640036, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.036445850767195226, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.034170933207497, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.05416520365513861, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.12514644861221313, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.1102890097629279, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1299779415130615, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1278514862060547, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1256871223449707, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.12455153465271, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1239683628082275, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1236395835876465, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1235363483428955, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1235313415527344, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123591184616089, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1236701011657715, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1237404346466064, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1238443851470947, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1239120960235596, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1240081787109375, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.12414813041687, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.124290943145752, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.124558687210083, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.124912738800049, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1253654956817627, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1258010864257812, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.126300573348999, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.126546859741211, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1262588500976562, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1246509552001953, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1194546222686768, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.063002109527588, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.882943630218506, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.7929046154022217, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.708726167678833, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.657728910446167, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6574907302856445, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6504833698272705, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.6204841136932373, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.6119282245635986, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.6011698246002197, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5799121856689453, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5934343338012695, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.639596939086914, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.620027542114258, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6299197673797607, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.664534330368042, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.716343641281128, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.8176193237304688, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7801101207733154, "validation/loss_044_lr2.6e+01_wd1.0e+00": 2.7909111976623535, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.768562078475952, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06773717238833518, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0753045404208195, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.10169804355850867, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.14987080103359174, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.1716500553709856, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.19564414913252123, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.21188630490956073, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.21373200442967885, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.21410114433370248, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22000738279808046, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.21834625322997417, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22609819121447028, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2203765227021041, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2117017349575489, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22572905131044665, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21613141380583242, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2059800664451827, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.19896640826873385, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.1877076411960133, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19306016980435586, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.0049615228837586066, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.004964970181228649, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00497187916739143, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007231408905561187, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009307939670250795, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0100751904238732, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009966059968039667, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010139537868314055, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.009901979078625292, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009825669145405747, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010518027710221372, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.011255799328606516, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.012343130081673577, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012592894665484952, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.017665912792532722, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.03533791302802602, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.07995783684316449, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.10385348969615364, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.12411833321607517, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.13755599595723336, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.13884547882473933, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1413470478331407, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.14704085091585226, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1455468970585632, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.13724127184741394, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.14265846695805517, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1340706394143936, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.13996873291045506, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.139085293987155, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.12438099206508736, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.12023517856893778, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.11785968997848995, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.11376902546919106, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1098386859417439, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.11386038409181709, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1187274353006942, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 2.6143295192718505, "validation/loss_best": 2.5799121856689453, "validation/acc_best": 0.22609819121447028, "validation/f1_best": 0.14265846695805517} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 2.971577979326248, "train/grad": 0.23004617676138878, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.132215576171875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1310107421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129891357421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129384765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129097900390625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1288720703125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.128790283203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.128551025390625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12831298828125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1280712890625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.127843017578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1274365234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12718017578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.126746826171875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12646728515625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12609130859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125714111328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12525634765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12453857421875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12390380859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12289306640625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12118408203125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.115128173828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.065594482421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.9633331298828125, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.8206693267822267, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.7233816528320314, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.666156883239746, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.6179092788696288, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.585471954345703, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5645486068725587, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5531764602661133, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.535140724182129, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.529165153503418, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.52175479888916, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.509169826507568, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.509961633682251, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.5132329177856447, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.521293487548828, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.56274284362793, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.588863935470581, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.608174180984497, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.6270909786224363, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.6618288803100585, "train/loss_044_lr2.6e+01_wd1.0e+00": 6.241693823337555, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6867627906799316, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008552285654004663, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008592150409240275, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008661490769591183, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008718688068911433, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008761408682912588, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00880020834505558, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008824861322063953, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008839100170880555, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008846803524065763, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00884800319094211, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008847141419537366, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008841811416205018, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008834021207876503, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008818523022346198, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008798921953421086, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008774414577055722, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008737984618637711, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008684143824502825, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008614647674839944, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008541250638663768, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.008454061064403504, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.008407117982860654, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.008714885476510972, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011273877478670329, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.015535557121038436, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.020082485233433544, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.022149072950705884, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.023807682814076542, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.025611793110147118, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.026447612773627043, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.026799271022900938, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.02672918557189405, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.026856202417984604, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.027086026091128586, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.02755484313238412, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.028426869991235434, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.028869871222414075, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030110576897859575, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03176510212011635, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030752829341217876, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03211095241829753, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03307791861705482, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03724062025547028, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03963532689958811, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.1151211806666106, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03986558564007282, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1247470378875732, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1240291595458984, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1234772205352783, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233038902282715, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1232314109802246, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1232285499572754, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1232588291168213, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1233065128326416, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123420000076294, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1235244274139404, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1236634254455566, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123899459838867, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124133825302124, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1244444847106934, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1246840953826904, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.124868392944336, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1249611377716064, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.124807596206665, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1241769790649414, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.123154401779175, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.120973825454712, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.115941047668457, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.0781068801879883, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.8778982162475586, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.749027729034424, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.6855475902557373, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6492910385131836, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.629014253616333, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.6083033084869385, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.598560094833374, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.6054229736328125, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.6222641468048096, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5840704441070557, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5731863975524902, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5592353343963623, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5547075271606445, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.555511951446533, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5577645301818848, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.6089911460876465, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.638936758041382, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.631941556930542, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.617795705795288, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6480650901794434, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7914717197418213, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7893481254577637, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07345884090070137, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.08896271686969362, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.15430047988187523, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.18309339239571798, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.19619785898855666, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.20468807678110004, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.21077888519748986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.21336286452565523, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.22314507198228128, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2262827611664821, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2249907715023994, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22554448135843486, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23126614987080105, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23735695828719083, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.23329641934293097, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.23311184939091917, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2157622739018088, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21096345514950166, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2069029162052418, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22277593207825766, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21262458471760798, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.19195275009228496, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2039497969730528, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005183194838367252, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005185412745483022, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.00518733503861716, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005186945309284807, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005183557613447877, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.004971014492753623, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.004967558799675587, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004963245933900562, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004962384259259259, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.004963245933900562, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005226638214635013, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006550153143884296, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008137829390581582, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008236072206660443, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.00825842324613137, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.008969027926448825, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.010239592917631641, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.012378731802303207, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.01868443822206385, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.024556558824048474, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.031690674837584774, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.06914570744187741, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.09726205959133229, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.10839906387193733, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.11916174890571646, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.12575671557548548, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.12941106457028093, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.14026130545313512, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.14142129987457616, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.14138339959808832, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1414375596987959, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.14338272984271935, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.15066802852465375, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.15253397452237108, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.15644190740893069, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.16664441953384143, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1463505330276842, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.14560818312201343, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.13410297145325287, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.14440641553908304, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1466244792751616, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.10703382119606068, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.12702331334528252, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 2.52175479888916, "validation/loss_best": 2.5592353343963623, "validation/acc_best": 0.23735695828719083, "validation/f1_best": 0.15066802852465375} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 2.8681088244915007, "train/grad": 0.15562157429754733, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12920166015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12872802734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128262939453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.128153076171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.127904052734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.127724609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12734130859375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127108154296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126817626953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126571044921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126357421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12584716796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125423583984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.124940185546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.124451904296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12387939453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.123094482421875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12201416015625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1203515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.117705078125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.101944580078125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.0179798889160154, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.8774632263183593, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.7487892150878905, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.6700455474853517, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.6151527786254882, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.585335121154785, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.563649158477783, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.543434476852417, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.5244560718536375, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.5111039066314698, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.5100346183776856, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4928280544281005, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.493708930015564, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.494361492395401, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.495456680059433, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.498871042728424, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4982442665100097, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.502446985244751, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.5472311425209044, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.5613398432731627, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.588812619447708, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5949199080467222, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.630182435512543, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.6701656985282898, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008713334072381259, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008758197610732169, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00880658824928105, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008833076448645442, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008846311264205724, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008854860560968519, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008858058035839349, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008858591027092189, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008858020829502494, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008856157602276654, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008852826233487576, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008844289232511073, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008833564466331155, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008809178983792663, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008777970792725681, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0087402882007882, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.0086844880040735, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00861400272231549, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.008552501609083265, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.008594060393515974, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009681126063223928, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.014226900395005942, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.01957041644025594, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.022891258113086222, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.023996920986101032, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02604848125949502, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.027459288509562613, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.028026000401005148, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.0290349552500993, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.029171455809846522, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.02961674902588129, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.029958448661491274, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030722569227218628, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.031074894620105625, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.031071877181529997, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.032487249430269004, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03257784597575664, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.032737748483195904, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.034132750276476144, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.031551708681508896, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.031754082795232536, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03291184666566551, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03549069684930146, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03802433412522078, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.039358203830197454, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1236517429351807, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.123485565185547, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1233582496643066, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1233339309692383, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1233222484588623, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1233208179473877, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123300313949585, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1232821941375732, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1232171058654785, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123138427734375, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1230220794677734, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.122755289077759, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.122417449951172, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.121752977371216, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1209957599639893, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1201953887939453, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.119051218032837, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1175127029418945, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1149322986602783, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1086971759796143, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.038731098175049, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.884688138961792, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.768242597579956, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.6982345581054688, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.658754825592041, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.621216058731079, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.6071364879608154, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.599630355834961, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.577063798904419, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5820748805999756, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.564854621887207, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5490970611572266, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.54299259185791, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.545280694961548, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.544875144958496, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.555717706680298, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.550544261932373, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.560825824737549, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5548312664031982, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.622293710708618, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6229145526885986, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.673954725265503, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.6479063034057617, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.716892719268799, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7747421264648438, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.067921742340347, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07050572166851236, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07881136950904392, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.11867847914359542, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.13805832410483573, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.16814322628276115, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.18512366186784793, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2026578073089701, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.21686969361387967, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.22056109265411591, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.22314507198228128, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2277593207825766, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2321889996308601, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.22978959025470652, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2264673311184939, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2279438907345884, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.22720561092654115, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2320044296788483, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.22554448135843486, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.22240679217423404, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.21816168327796234, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21244001476559615, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20579549649317092, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.20616463639719454, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005186945309284807, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00516183043345318, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005154515101336135, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006044802274481723, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0061686781464087926, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006960174012339368, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007865411454453606, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008802006507024868, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00929885183050049, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009944552408671875, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010633468823982401, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010638060185550349, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.010472821134821396, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010368387366907568, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010354784362380626, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010261537122714846, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.010259928701185172, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010147638704796227, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01192094867681309, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.018659739717474384, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.04640660420896981, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0595523298037608, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.08658267668765107, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.10625456900123396, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1216615989421443, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.13822155484923074, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.14562143814832978, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.14747300124950682, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1511777113827484, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.14870989726928666, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.15041571204394752, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.15559148491256947, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1622490169927174, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16108830188305628, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1666502345347031, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1614335386227571, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16834280244643773, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.1698333017967121, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16615050969539125, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.16298479317479572, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16074280959527007, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1512452691870477, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.15681713604860628, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15293631813067163, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.12772399875000323, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 32, "lr_best": 0.0011099999999999999, "wd_best": 0.05, "train/loss_best": 2.4928280544281005, "validation/loss_best": 2.54299259185791, "validation/acc_best": 0.2351421188630491, "validation/f1_best": 0.1622490169927174} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 2.8148716747760774, "train/grad": 0.15729474391788245, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12907470703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12899169921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.128765869140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12869873046875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.128487548828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1283251953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127996826171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127757568359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127330322265625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126951904296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126595458984375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12601806640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125430908203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12462890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.123695068359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.122784423828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.121307373046875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.118546142578125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1070037841796876, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.0341346740722654, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.863384552001953, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.7377320098876954, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.6522270965576173, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5972147369384766, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.556446113586426, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.5213216972351074, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.499195499420166, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.483286905288696, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.468334698677063, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.4541024017333983, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.4383643007278444, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.439555525779724, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.430973744392395, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.4284775161743166, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.4295425701141355, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.423023614883423, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.429326868057251, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4304275560379027, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.43532675743103, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.4831675624847414, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4921820425987242, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.512809998989105, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.509870419502258, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.532277581691742, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.580118305683136, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008805723635014147, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008834360137116163, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008860739273950457, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00887307922821492, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008878884194418788, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008882508433889597, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00888437225483358, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008884245939552783, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008882044597994536, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00887703723507002, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008869563201442362, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00885290224570781, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008831209174823017, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008790914905257524, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008744772095233201, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008695467887446285, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008641741743776948, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.008653968635480852, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00940444048959762, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.013353062171954661, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.019382076696492733, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02224816507194191, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.023591734156943857, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02455808465834707, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.025483271908015012, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.026265202504582703, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.026799435578286648, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02746552586555481, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.02841212195344269, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030134283248335125, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03147831943817437, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031614177264273166, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03202659321017563, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03191359093412757, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03155580551363528, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.032355433879420165, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03161546114832163, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03174407140351832, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03270354119129479, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030595998438075186, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03104280020110309, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03211284689605236, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03427676251158118, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0355339399073273, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.037092512445524334, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.123131275177002, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1230309009552, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1229326725006104, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122860908508301, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.122777223587036, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122663974761963, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12253999710083, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.122445583343506, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1222808361053467, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1220879554748535, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.121870279312134, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1214888095855713, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1210720539093018, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1203453540802, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1194777488708496, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1184732913970947, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.116504669189453, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1111881732940674, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.07173752784729, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.8953378200531006, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.7593517303466797, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.685129165649414, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.633568525314331, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5957348346710205, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.565498113632202, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5437681674957275, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5374014377593994, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5340137481689453, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.52864933013916, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5376245975494385, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5524916648864746, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.5623667240142822, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5743823051452637, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5622305870056152, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.570192813873291, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.547631025314331, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.544142246246338, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.6068761348724365, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.616103410720825, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.6230556964874268, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.6368932723999023, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.6275782585144043, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.683119297027588, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.7162067890167236, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.7631750106811523, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.11369509043927649, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.15780730897009967, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.18715393133997785, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.20801033591731266, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.21686969361387967, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.22406792174234036, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23255813953488372, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2336655592469546, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2353266888150609, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2368032484311554, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2369878183831672, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.23421926910299004, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.22849760059062385, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.23385012919896642, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.22425249169435216, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.22831303063861202, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2294204503506829, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2201919527500923, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.21926910299003322, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.21797711332595054, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21520856404577335, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.22111480251015134, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21539313399778517, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.20191952750092285, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.19619785898855666, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.004969286045433472, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.004969286045433472, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.004967558799675587, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.004967558799675587, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.004965832754227473, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00496410790783837, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0049615228837586066, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.004962384259259259, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.004963245933900562, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.004963245933900562, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00517939273657259, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00613431855781917, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007201245994639995, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.008294482394051299, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.009266460649935379, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01070772682303695, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01706139435751122, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.04314102636679191, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.07572312447256181, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.10917875085240454, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.13043437711098774, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.14465893314077513, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1523982511331331, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16417090296985276, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16836580514050734, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16924130138585522, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.17144173626968576, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.16948553836710656, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1654090599531991, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1610795824387621, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.15983066836184043, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.15303533796577296, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.16675661521553606, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1611131630340961, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.16391583168827703, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.16272995385112976, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.15746119250673363, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1578827170722443, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.15556506655007019, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1563424859084058, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.15156285936582825, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.14242076220607516, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.13580070964102928, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.14437117932788532, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 29, "lr_best": 0.0006899999999999999, "wd_best": 0.05, "train/loss_best": 2.4541024017333983, "validation/loss_best": 2.5376245975494385, "validation/acc_best": 0.2369878183831672, "validation/f1_best": 0.1654090599531991} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 2.7887384974956513, "train/grad": 0.15878871068358422, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.132171630859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.132039794921875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131746826171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13150146484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.131265869140625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130885009765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130557861328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1301123046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12972900390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129090576171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12855224609375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127728271484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12684814453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.125482177734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.124049072265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12209716796875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1180810546875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.0959954833984376, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.950389404296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.7995532989501952, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6947827911376954, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.6269731521606445, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.578449249267578, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.5427742767333985, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.5124135398864746, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4849855709075928, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4681518363952635, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.456758432388306, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.444277229309082, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.4221631193161013, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.4083327627182007, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.4084116506576536, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.4045968675613403, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.403759219646454, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.40185387134552, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.398210997581482, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.407088451385498, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.4167682194709776, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.424335827827454, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.468354706764221, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4779154539108275, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.4947338569164277, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.5075361466407777, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.512497764825821, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5666869962215424, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008709250749088824, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008724749754182994, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008737382721155882, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008742393534630537, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008745053275488317, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008745301375165581, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008743572318926453, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008739755214191973, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008732087020762265, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00872032520826906, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008706932431086898, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008679885289166123, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008649079944007099, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008598220623098314, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008548271942418069, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008519507460296154, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.008615615484304727, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010107661250513046, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01684394615702331, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02102638172917068, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.022565644569694995, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02308198918122798, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.023594738813117147, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02435621525160968, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.025136618064716457, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02609253813512623, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.027007040921598672, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.02793199185281992, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.028779464848339556, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.030772673496976495, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.031594550935551524, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03136022360064089, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030951423104852438, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.031066122399643063, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.0305084397085011, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03128266791813075, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.031229343861341477, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.031576728271320464, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03385787580162287, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.031096828933805228, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.031292258854955436, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03139562730677426, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.035293493857607244, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0361420460883528, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.036760966517031195, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122346878051758, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1222174167633057, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122007131576538, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1218295097351074, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121666669845581, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1214864253997803, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121290683746338, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.121103048324585, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120908498764038, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1207056045532227, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120502471923828, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1201930046081543, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1198432445526123, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1191890239715576, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1181480884552, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1163575649261475, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1101107597351074, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.046135187149048, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.846940755844116, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.7430951595306396, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6649839878082275, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.6220462322235107, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5930233001708984, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.566129684448242, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.545008420944214, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.536212921142578, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5362021923065186, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.532644033432007, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5273213386535645, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.500460386276245, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4862303733825684, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4869918823242188, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4836506843566895, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.496063470840454, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4992003440856934, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.503084421157837, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5325636863708496, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5356009006500244, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5675575733184814, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5552620887756348, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.62723445892334, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5912132263183594, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.63588285446167, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6938204765319824, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6414408683776855, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.11406423034330011, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.15171650055370986, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.1836471022517534, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.20062753783684018, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.21520856404577335, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2235142118863049, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23292727943890734, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24197120708748615, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24344776670358065, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2427094868955334, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24732373569582872, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24658545588778147, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.24067921742340348, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.22535991140642303, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.23421926910299004, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.21945367294204504, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2235142118863049, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.21410114433370248, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21668512366186785, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22111480251015134, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005166471865487415, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.00535716665733699, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005735968656431165, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005728645395921841, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005906129665931049, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006043379882677409, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006186357257044962, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0062751770954294, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00650243391481364, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006912793705246535, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00733347935599699, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008604952576153143, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009521868302371126, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010891694352568938, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.012609092048908324, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.012849875100845523, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.013551936235454747, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.03745224259561578, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.06533319423086556, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.09337956469887265, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.11106241534989565, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.12532381995002342, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.13511587483760967, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1495662260946802, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1595797603816862, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16530512919567653, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16640851273712184, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1699382375443922, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17476072356726183, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17798816193268854, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18360183131427635, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.17939582046282834, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18894378806069131, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.18150001922859704, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18903590525426842, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18906453057759953, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.17986974594457325, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.17886024249957944, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.16401853392383492, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.17122268351162662, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.16157723501168775, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16872832150284092, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16745170176545177, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16957027886795284, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.16391627028113256, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 2.40185387134552, "validation/loss_best": 2.4992003440856934, "validation/acc_best": 0.25193798449612403, "validation/f1_best": 0.18903590525426842} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 2.7511253798007966, "train/grad": 0.16824721671640874, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127271728515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.127052001953125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12671630859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126396484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1261328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1256640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1253076171875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.124747314453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12409912109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12339111328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122664794921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.121627197265625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.120732421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11881591796875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.116536865234375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.112618408203125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.090855712890625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.9375587463378907, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.7632733154296876, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6752395629882812, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.6057357788085938, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.560440330505371, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.525206413269043, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4977653312683104, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.474027519226074, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4496193885803224, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.4327299308776857, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.420327653884888, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.4064654159545897, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3783820629119874, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3666022539138796, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.368109860420227, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3643670904636385, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.360159225463867, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3551885783672333, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.3501254177093505, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.35951167345047, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.362745513916016, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.360672914981842, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.3983712124824526, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.4174815821647644, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.441067337989807, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.440342357158661, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.457512778043747, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.5279874181747437, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008853027487639338, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008860446482431143, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008865160893183201, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008865644347388298, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008864935368765146, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008862514356151223, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008858487682882697, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008852672055363655, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008842799363192171, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008828482865355909, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008811619272455573, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0087814050889574, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.0087494613439776, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008703863851260395, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.008692474372219294, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.008830361606087536, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010387582744006068, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.017490229015238584, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.022404705313965677, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02374630664475262, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02459745262749493, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.025449064443819225, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02651826278772205, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02786536218132824, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02909364744089544, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030026389518752694, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030569747928529976, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.031128334952518343, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03178197185508907, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03310719771310687, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.033772489000111816, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.033689305279403926, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03281777929514647, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03255317362956703, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03211831062100828, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.032640676638111474, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03192306437529623, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.031826302148401736, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.033304945435374975, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030084983175620438, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.031247863294556737, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.031778958290815354, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.034199242684990167, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.035393460113555195, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03786645982414484, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122278928756714, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1221442222595215, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121917724609375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121711254119873, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121526002883911, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121317148208618, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.121060848236084, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120826244354248, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1205649375915527, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120283365249634, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.120079278945923, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1196975708007812, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119312286376953, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1184237003326416, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1165573596954346, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1111042499542236, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.0576024055480957, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.868497133255005, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.7499818801879883, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6820850372314453, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.6358323097229004, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.611694812774658, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.587693691253662, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5615713596343994, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.53956937789917, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5228536128997803, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5132834911346436, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.507526159286499, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.5069692134857178, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.481769323348999, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.476444721221924, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4713432788848877, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4654335975646973, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4609172344207764, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4504504203796387, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4589273929595947, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.45904541015625, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4781365394592285, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.470818519592285, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4952173233032227, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5322422981262207, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5121378898620605, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.570749044418335, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.536114454269409, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.725039005279541, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.07142857142857142, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0710594315245478, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07198228128460686, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07438169066076043, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.07733480989294943, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.10834256183093392, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1583610188261351, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.18660022148394242, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.20431893687707642, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.21410114433370248, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2201919527500923, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.22591362126245848, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2336655592469546, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2469545957918051, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2467700258397933, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24640088593576967, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24603174603174602, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2500922849760059, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.257844222960502, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.257844222960502, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2467700258397933, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2469545957918051, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24787744555186417, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23994093761535623, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24713916574381692, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2117017349575489, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006027083530507456, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006921508811691199, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007133203475168864, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008456463153981972, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.009381490714675625, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.010504994879900394, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.010130082669359967, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.01024606574316706, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010029199224841856, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010531908991496156, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010347894550395718, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010790520465981309, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011615215848691901, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.012612038717656706, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01271941875107826, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.016089747986109265, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.04288553658758008, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.07827212330670748, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.10214911249038887, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.12174150076160146, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.13284876153926076, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1390701870292909, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.14608605528160254, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1542262062406882, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1606659495073934, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16711897870406703, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16906161369868858, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1768252343932759, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17804696727490996, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.18154140353624368, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1850121225393515, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18436377601736229, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18554749147272218, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1855545265386562, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19121839129630902, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19143007879461807, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19597741037303182, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18859445152692375, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19275156275466002, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.16196626506809408, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.162621946956049, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.16442834174854534, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.16391496255828308, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.17621993924252208, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.1336371564422776, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 2.35951167345047, "validation/loss_best": 2.45904541015625, "validation/acc_best": 0.25839793281653745, "validation/f1_best": 0.19597741037303182} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 2.7178486812114717, "train/grad": 0.1724067662283778, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.124583740234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.124342041015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.123958740234375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12359619140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1232080078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.122705078125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.122109375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121590576171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12072021484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11982421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1190185546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.117550048828125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1159912109375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.11325927734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.10841064453125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.092767333984375, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.968336181640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.781119384765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6732367706298827, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.6075518798828123, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.5535411834716797, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.5149201774597167, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4814260673522948, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.453202362060547, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4284635639190673, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.405060682296753, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.389089584350586, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3751792740821838, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.359163174629211, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.3302228772640228, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.3183146154880525, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3167783200740812, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.318398697376251, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.317942178249359, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.3167421627044678, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.3147225725650786, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3217445516586306, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3247195410728456, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.324466760158539, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.359096963405609, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3731476080417635, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3826626420021055, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.4078366005420686, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4151233661174776, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4612430119514466, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008930682558566333, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00893519525649026, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008938409648835658, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008938851023558528, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008938012416474522, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008935527440626175, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00893095479812473, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00892431011190638, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008911718607414514, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00889486854430288, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00887543176067993, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008841265195515006, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008807607693597674, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008784805196337403, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00891888610785827, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00995786348124966, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.015969862272031607, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02161565869115293, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.023753314139321448, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024473166456446052, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.025184524366632103, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02604883996769786, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.026965511264279485, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.027914347238838674, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.028779865326359868, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.02983421113342047, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030748338140547275, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.031559154223650694, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03229182856157422, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03351442938670516, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03396519442088902, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03365568279288709, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.0330658389814198, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03326179754920304, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03349419321864843, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03432391389273107, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.033795431395992635, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.0338021073769778, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.035616185804829004, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03147703865543008, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.03191678778268397, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03176228164695203, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03581650203093886, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03690331938676536, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03698192049749196, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1225154399871826, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122439384460449, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122361898422241, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122251033782959, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1221747398376465, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1220433712005615, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1219096183776855, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1217217445373535, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1214563846588135, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1211466789245605, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1207733154296875, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1200952529907227, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.119178533554077, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.116888999938965, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1110589504241943, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.0815258026123047, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.9091796875, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.767245292663574, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6801211833953857, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.6289350986480713, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.592852830886841, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5702531337738037, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.553779363632202, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5399928092956543, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.531076669692993, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.528940200805664, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.531691312789917, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5263118743896484, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.528107166290283, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.5220022201538086, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.5168700218200684, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.513599395751953, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.5133469104766846, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.5145468711853027, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.5291671752929688, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.5298409461975098, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.5278475284576416, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.5402369499206543, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.556471586227417, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5687003135681152, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.543926239013672, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5383782386779785, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.567112922668457, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6327757835388184, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6098411083221436, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.08490217792543374, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.14248800295311922, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1805094130675526, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.1998892580287929, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21077888519748986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.22056109265411591, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22978959025470652, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2364341085271318, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23772609819121446, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24160206718346253, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24031007751937986, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.23938722775932078, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.23809523809523808, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2425249169435216, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2364341085271318, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.23791066814322628, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2355112587670727, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.24141749723145073, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2412329272794389, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24529346622369877, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2369878183831672, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.23791066814322628, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.23311184939091917, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2277593207825766, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.22000738279808046, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.22997416020671835, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005731015629792394, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005728645395921841, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005732634808721766, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005738554245350115, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005536025646905114, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0055385030678068185, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0055377600228432395, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005743343310666304, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006686802969303445, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007823050761509335, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008795225552548983, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.010925883404549017, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012955462106642288, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.013692102956911277, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01729743779889549, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.03288854536775703, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.07067735002811594, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.10288071321702023, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1215835023791909, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.13343555164483845, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14342082658204172, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15356566233020327, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1605889496176002, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.163451091234089, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16936021714062907, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16839300347576588, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16787847880009635, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1689056515971363, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1698792438024661, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1678540733391999, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.17130297947781523, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.17074776720454923, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.17858805356847032, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.17731413589529252, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.1812350465510413, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.18411552499556763, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.1877679458239656, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.18865761644943266, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19350740336305441, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1844282685708302, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1945135031076706, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1832664890601069, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.17458997057352663, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.16084654748406202, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.16826958797299688, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 2.324466760158539, "validation/loss_best": 2.556471586227417, "validation/acc_best": 0.24529346622369877, "validation/f1_best": 0.19350740336305441} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 2.7070687675476073, "train/grad": 0.17010666113346815, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125001220703125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1246875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.124189453125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.123782958984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123294677734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12277099609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12220703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121474609375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120638427734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.119705810546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.118642578125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.117037353515625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1152783203125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.111187744140625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.100211181640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.0334600830078124, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.840188293457031, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.7152224731445314, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.6326216888427734, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.581128005981445, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.537177619934082, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.50410943031311, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.474533758163452, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4488934803009035, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.4264593887329102, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.4048258686065673, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.3896126079559328, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3714244556427, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.352666621208191, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.322525353431702, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.309313998222351, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.3082687139511107, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.3086173689365386, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.3079748129844666, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.305694785118103, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.3025977659225463, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.3133917260169983, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.3162898516654966, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.3132924485206603, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.348518943786621, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.3615150594711305, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3797163772583008, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.394101802110672, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.4076224684715273, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.4569976341724398, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008680268109310418, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00868429854279384, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008688319628126918, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008690112885087729, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008691429924219847, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008691506399773062, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008689543574582785, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008685986096970737, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008677666583098471, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00866587927332148, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008652003163006157, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00862735024653375, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008613247284665703, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.008680158152710647, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009354873653501272, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01314438667614013, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.020055027925409377, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.023047477141954004, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.024394026715308426, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.024940918842330576, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02560492552816868, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.026371634900569915, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027302604457363485, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028336678808555008, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029277170840650797, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030378473242744803, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031170810060575604, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03172422907315195, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.032264649048447606, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.032882857993245126, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03316498339176178, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03276089117862284, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03186901300214231, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0319543035980314, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03226349809207022, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03271008907817304, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03232049213722348, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03207773292437196, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03348562933504581, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.030409481823444367, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030696841040626168, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.031192531790584326, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03457792395725846, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03567930447869003, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03695386923849583, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122408866882324, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1223323345184326, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122180700302124, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1220405101776123, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1219022274017334, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1217098236083984, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1214685440063477, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1211748123168945, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120811939239502, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120382785797119, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.119932174682617, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.119081497192383, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1178832054138184, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1141974925994873, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.097672939300537, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.9898252487182617, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.814260959625244, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.71280837059021, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6386311054229736, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.598109722137451, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.570267915725708, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5516855716705322, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5376203060150146, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5280821323394775, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5289249420166016, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.539342164993286, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.538357973098755, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.523240566253662, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.507685899734497, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.480938196182251, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.468003273010254, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4698989391326904, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4738264083862305, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.47922945022583, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4761722087860107, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.46396803855896, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.462902545928955, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4715566635131836, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4783003330230713, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5193586349487305, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.506183385848999, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.541255235671997, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5872602462768555, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.6501781940460205, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.6136515140533447, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06718346253229975, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.07124400147655961, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.08305647840531562, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.13510520487264674, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.17404946474713917, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.19878183831672203, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.21650055370985605, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.22462163159837578, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2294204503506829, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2334809892949428, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.23661867847914358, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23791066814322628, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23458840900701367, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.23274270948689554, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2351421188630491, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24178663713547435, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24750830564784054, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2502768549280177, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25489110372831303, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2528608342561831, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2591362126245847, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.257844222960502, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2454780361757106, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2469545957918051, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24916943521594684, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.23846437799926173, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.21982281284606867, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2320044296788483, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006648809179388245, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006953833917368279, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0065393587641478365, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0066480862268244794, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006614679623516649, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0071231894964842125, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00798025301676549, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008935828713939506, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009657098983370417, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011033641205005917, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011816297192667845, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.012407097276453753, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013195418409065, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.017031956356507755, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.028095087878973305, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.06455432920133373, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.09513523500418226, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12041173712517099, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1378960298030972, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.14496714638913957, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.15145979656688344, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15552353419587014, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.16083150533355325, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.16330789541950744, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16091782513556757, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.1605031212558759, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.16416140419322542, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.16845376765838796, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.17277488993283777, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.17659030558847452, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.18471817208210886, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.18425959673112333, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.18268851228829228, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1834364554445916, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.18819792080398853, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19553530324999516, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19795429181825816, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19960510935583034, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19757423865670168, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19248391268197287, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.194348065686577, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1846141919334099, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.1732057763197189, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.15567024755523237, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.16531192253982518, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 2.3133917260169983, "validation/loss_best": 2.462902545928955, "validation/acc_best": 0.2619047619047619, "validation/f1_best": 0.19795429181825816} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 2.675339628458023, "train/grad": 0.171943535245955, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1265966796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.126309814453125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125751953125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.125328369140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.124783935546875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12417724609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.123427734375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122598876953125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121558837890625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.120321044921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11910888671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.117183837890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11462890625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1079345703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0753076171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.9256912231445313, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.7600836181640624, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6595216369628907, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5848948669433596, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.538987464904785, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4986752128601073, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4669365310668945, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.438024024963379, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.4124108123779298, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3890651512145995, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.3656001567840574, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.347937831878662, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3258965492248533, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.3066967916488648, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.276333725452423, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.260801260471344, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.259997606277466, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.26337198138237, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.26377946972847, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.260494360923767, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2556360948085783, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2629837119579315, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.265377039909363, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.2575963771343233, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2916831719875335, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.295947868824005, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.3136842751502993, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.3277339339256287, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.350826187133789, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.402457695007324, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008882198296487332, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008884700485505164, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008887266656383872, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008887751318980008, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008886314104311168, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008882862103637307, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008876941108610481, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008868600551504641, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008853981010615826, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008835397779475897, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008816671352833509, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008791158767417073, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008793287049047648, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0090459117712453, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011223061534110457, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.017677442976273595, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.022659648754633964, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.024732594001106917, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02566295615863055, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026010503489524127, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026500242883339523, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027214115597307683, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028171156151220202, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02912293227389455, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02984283690340817, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.03053179755806923, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030983350640162825, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03174866915680468, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.032256891718134284, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03306479273363948, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03348457126878202, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.033280446138232944, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03283291230909526, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.033214170252904296, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.033365234220400455, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.033593774996697905, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.032875738954171535, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.032470281226560475, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.033308826722204685, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.029708540318533778, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.029586188262328506, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.029655877873301505, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03273786552250385, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03489258149638772, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.035338153587654235, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1227405071258545, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1226673126220703, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.122532844543457, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.122384548187256, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1222331523895264, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.122014045715332, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1217007637023926, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1213464736938477, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1207916736602783, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.120143175125122, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.119394063949585, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1179604530334473, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.115823745727539, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1080739498138428, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.0568079948425293, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.893812894821167, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.764296770095825, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.687796115875244, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6306707859039307, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.599461793899536, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5772173404693604, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5614795684814453, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.550171375274658, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5386710166931152, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.524278163909912, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.5028066635131836, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.486534595489502, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.469395160675049, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4692444801330566, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4498023986816406, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4460933208465576, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4504950046539307, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4616692066192627, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4622204303741455, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4720656871795654, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.480884313583374, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4591195583343506, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4499568939208984, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4672584533691406, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.484038829803467, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5044169425964355, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.503275156021118, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.488530158996582, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.508458375930786, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.544222831726074, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.10151347360649686, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.15485418973791068, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.18715393133997785, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.1984126984126984, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.21114802510151348, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.21853082318198597, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2233296419342931, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.22997416020671835, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2336655592469546, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24012550756736803, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24326319675156885, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2526762643041713, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2497231450719823, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25101513473606496, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24215577703949798, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.24141749723145073, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25046142488002954, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24492432631967515, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.24344776670358065, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0059130559130559125, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005911878258042479, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005705919226908489, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.005707628645335204, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0057156021381315975, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.005514641124571909, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00601987028005779, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0061792924589519765, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006829671314897747, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006822897142387465, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.00759602644814919, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.007883507927298894, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.008340706082135024, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008888448152955591, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.04740870953734868, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.08237133909554387, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11144026199592766, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.12258230878370241, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.13372688025691057, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1406877800910009, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.14500744407537627, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.15382031471507795, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.15928371385003218, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1670467584391655, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.1706412384007426, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18289559625574503, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.19051138476285437, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19776913656574724, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19889169997792078, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.1966603198862328, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19962727127120752, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19508907615526372, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.1978705109247565, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19745914929361216, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19966832328819858, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19416882587771112, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.19616353411616458, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2037587363410018, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20252809394074692, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20270574402171607, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19850621362810275, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1925352691473102, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19615002731387657, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.18748025786953168, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.18254671946930415, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 27, "lr_best": 0.00047999999999999996, "wd_best": 0.05, "train/loss_best": 2.3258965492248533, "validation/loss_best": 2.469395160675049, "validation/acc_best": 0.2602436323366556, "validation/f1_best": 0.19776913656574724} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 2.656129916906357, "train/grad": 0.1748285288736224, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12605224609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12574951171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125185546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124696044921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1242236328125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123436279296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1226416015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121920166015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.120660400390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11939697265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11810546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11569580078125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.112635498046875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.10135009765625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.0229302978515626, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.8454461669921876, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.715810775756836, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6294251251220704, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.562126426696777, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.519782123565674, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4814734268188476, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4501877784729005, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.421061677932739, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.39427152633667, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3701812267303466, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.346612138748169, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.327152509689331, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.3011587285995483, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2817281007766725, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2516436553001404, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.235046989917755, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.232034749984741, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.233299558162689, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.231355140209198, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.2285840797424314, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.2259396934509277, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.2341031360626222, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.2382304453849793, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.232571549415588, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.263271210193634, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2711867475509644, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.2856782031059266, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2946512055397035, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.306242264509201, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.347932496070862, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008991737517062575, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00899367565754801, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008994592728558928, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008993937717750668, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008991934636142104, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00898783969692886, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00898175237234682, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008973646503873169, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008960582513827831, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008944879416376353, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008929128465242684, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008915837437380105, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008957794501911849, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009586877578403801, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.013987760613672436, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.020292823668569326, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.023730250145308673, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.025203008786775172, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.025796891101635994, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026062699211761357, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026545079639181495, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02726466242223978, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028135483097285034, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028994545945897697, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02977598374709487, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030779274655506016, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03155470843426883, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03239682322368026, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.033101955531165, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03438958589918911, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03483116178773343, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03446374890394509, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03375823301263153, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03359930705279112, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03377816393971443, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03417582081630826, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03346070033498108, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03296536201611161, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03486937060952187, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.03060898281633854, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.030535753788426517, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.03074506014585495, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.03325141685083508, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.0345354188978672, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.033817031290382146, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122364044189453, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1222329139709473, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12199068069458, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1217479705810547, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1215097904205322, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121188163757324, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.120833396911621, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120398998260498, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1198346614837646, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119196891784668, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1184606552124023, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.116994619369507, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.114504814147949, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.101608991622925, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.000901460647583, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8394808769226074, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.732090950012207, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.660360813140869, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.605360984802246, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.576706647872925, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.553919792175293, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5367467403411865, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5232322216033936, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.509568691253662, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.500659942626953, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4953649044036865, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.487530469894409, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4669547080993652, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4648897647857666, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4565653800964355, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4547009468078613, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.456244468688965, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.458320140838623, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4487571716308594, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4545395374298096, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4651403427124023, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4568376541137695, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.46972918510437, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4968340396881104, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4779891967773438, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.5003204345703125, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5042693614959717, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.482412576675415, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.518871545791626, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5149548053741455, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06976744186046512, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08010335917312661, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1301218161683278, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.16943521594684385, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19601328903654486, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21244001476559615, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23311184939091917, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23791066814322628, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2427094868955334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2469545957918051, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24880029531192321, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2511997046880768, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2556293835363603, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25359911406423036, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25802879291251385, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2547065337763012, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2558139534883721, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25101513473606496, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.24787744555186417, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2497231450719823, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25655223329641935, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.24510889627168697, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.24510889627168697, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005724847805893006, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006044802274481723, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006007055179305869, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006447048213593289, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006347494025770245, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006636835690314394, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007631927039821777, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008439925170606485, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009514882981140648, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009705440729471047, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010202109039580753, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011441031571907496, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01338723578451644, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.02244637117684434, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06390670528938712, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0922276659682058, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1189112697941636, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13586625705794264, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14661033249574468, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15636338397039792, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.16414362791941642, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1705783724788076, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17737606896205194, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.18014736548679744, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18384242435233897, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18469617879845032, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18703434765531876, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.18882415186027482, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.1952477725096817, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20115522262198252, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20227063194422598, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20066904890635215, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.2009079784740764, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19995238519714145, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20037515164193773, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19695672534504718, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20002931285417228, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20226652524510322, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1977523693198231, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2006271396711279, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19337808395146452, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.1993815917934473, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.21219276768229434, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.1974020931082896, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19239981678476145, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 2.2285840797424314, "validation/loss_best": 2.4545395374298096, "validation/acc_best": 0.2582133628645257, "validation/f1_best": 0.20037515164193773} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 2.633916288614273, "train/grad": 0.1711094155535102, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.123359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1229541015625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.122347412109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121832275390625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.121329345703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12063232421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1198388671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11885986328125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.117635498046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.116236572265625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11482666015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11214111328125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.108250732421875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.089345703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.9582464599609377, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7918092346191408, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.681201629638672, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.6017259979248046, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.540803985595703, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5011214447021484, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.463955535888672, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4329944610595704, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4043605804443358, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3775377655029297, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3532826042175294, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.328164234161377, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.30676552772522, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.277599906921387, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2574383068084716, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.226311538219452, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.206913788318634, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.201702690124512, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.204264142513275, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.203273000717163, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.199116017818451, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.1895706832408903, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.1950392854213714, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.197432897090912, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.185487478375435, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.2170987725257874, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.217093455791473, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.231869218349457, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.2426300537586212, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.2476756381988525, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.3023249888420105, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008932150227483362, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008931905128993094, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008931001408491283, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008927836769726128, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008924416447989643, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008919421832542867, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008911762225907296, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008902230665553361, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008888355735689402, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008871942430268974, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00885803567012772, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008854925353080034, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008945064533036203, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010126818229909986, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01617455044295639, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.021373767629265784, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.02411012664437294, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02538032790645957, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.025968195311725138, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026246454203501343, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026672234302386643, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02729894656687975, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028063574507832527, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028897145008668305, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029646570030599832, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030495386635884643, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031194828636944293, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03209820467047393, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03270849412307143, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.033944546161219474, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03437893954105675, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.033930386705324056, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.033336296798661354, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03350092931650579, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03341004740446806, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03329412045888603, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03221962880343199, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.03150328199379146, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03268391673453152, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.028887606877833604, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02885376101359725, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.028530506240203975, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0308500050753355, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03201955756172538, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03216438023373484, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1223843097686768, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1222639083862305, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1220338344573975, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1217970848083496, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1215977668762207, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1212728023529053, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.120948553085327, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120537519454956, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.119971513748169, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.11928129196167, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1184444427490234, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1166412830352783, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.113269805908203, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0912792682647705, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.9484126567840576, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.8058409690856934, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7140958309173584, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.651116132736206, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.6054816246032715, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.583716630935669, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5688600540161133, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.558903455734253, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.553678274154663, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5473861694335938, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.543358325958252, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.540745735168457, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.5311203002929688, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.5040247440338135, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.498610258102417, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4882102012634277, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.472391366958618, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4768755435943604, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4816768169403076, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4750661849975586, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4820454120635986, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4786884784698486, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4813108444213867, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4958784580230713, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.5051467418670654, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.5187087059020996, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.534085988998413, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.5389513969421387, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.5139944553375244, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.527315139770508, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.5231618881225586, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.08157991878922112, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.14377999261720192, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1777408637873754, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2011812476928756, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21207087486157253, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2201919527500923, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.22757475083056478, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23108157991878922, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2334809892949428, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2336655592469546, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.23569582871908454, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.23864894795127353, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24049464747139165, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24381690660760427, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.25396825396825395, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25802879291251385, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25212255444813586, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25378368401624213, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2572905131044666, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25230712440014763, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2515688445921004, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25249169435215946, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25378368401624213, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.25249169435215946, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2547065337763012, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005745818169318781, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.005564243845962672, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.005724843454201252, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0060950719109674366, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.005865652906742745, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00633354630202104, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006782660173328421, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00732220042323409, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00805165622121601, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.008152497193077696, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.008871718480155966, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.009269636539234065, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.012173604710526177, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.023504988282614783, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.06539693379469898, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09447940212017399, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.11845390136055144, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13066913511876332, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1392051990381304, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.14755794853504992, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.153108823677258, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.1570700590199885, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.15964745431705232, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.16207748152032186, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.16671868592233163, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.16925592008896204, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.17456021987615591, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.18413397315220306, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19187614517539223, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19042404926462284, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.1929945113743894, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19371296488470016, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19551243310661912, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19448196644407809, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19587074660881096, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.1960158897896445, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20357777200524643, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2043704551919325, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19671213553614988, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.1973826318331818, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1949715735937804, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.19426302506783222, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19359545288659671, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19837449561954792, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19296942602025766, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 2.1950392854213714, "validation/loss_best": 2.4813108444213867, "validation/acc_best": 0.26301218161683276, "validation/f1_best": 0.20357777200524643} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 2.630663297176361, "train/grad": 0.16919049091637134, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12280517578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1224951171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.121988525390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.121439208984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1207568359375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.120089111328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.119248046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.118314208984375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.11703125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.115667724609375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.114154052734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.111357421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.106947021484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.07924072265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.91830810546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.773848876953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6777360534667967, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.604875946044922, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.547718353271484, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.5097601318359377, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4735828399658204, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4430360984802246, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.4144569778442384, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.3867314720153807, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.361518659591675, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.334792537689209, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.310904903411865, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2823824310302734, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.261273908615112, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.2280673742294312, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.2073528385162353, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.2007836151123046, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1990103769302367, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1979050636291504, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.188834295272827, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.179153847694397, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.184450967311859, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1857577848434446, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.1714210891723633, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.201706233024597, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.2027024745941164, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.215806257724762, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.22689475774765, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.230174732208252, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.282520604133606, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008836314072832465, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008835975474212318, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008833824645262212, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008830432968679816, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008826784586999566, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008820847154129296, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00881365961395204, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008804604618344456, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008791305157355964, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008775966435205191, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008764857097994537, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008776756424922497, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.008923342823982239, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010734684697818011, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01753787200432271, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.022035726457834245, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.024488147553056477, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02557525597512722, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026037478847429157, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026245113890618087, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026650740392506124, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027287036115303635, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028066671881824733, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02884569739922881, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02966401935555041, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030569473495706916, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031224653320387007, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.031941775269806384, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.032470239214599135, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03335658847354352, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.033800553316250447, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.033475470300763845, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.032870281459763645, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0327218106854707, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03238323677331209, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03226294541731477, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.031488333716988566, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030750131625682117, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03202179454267025, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.028320883698761463, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.028466441109776495, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02810265908949077, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.030276676500216128, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.03149123708717525, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03132536614313722, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1223418712615967, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122230052947998, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1220078468322754, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121795892715454, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121593475341797, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121321201324463, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1209921836853027, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120626449584961, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1200966835021973, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1194393634796143, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1186201572418213, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.116744041442871, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1128158569335938, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0813286304473877, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.915803909301758, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.786827564239502, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.7003328800201416, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.636462688446045, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.589325428009033, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.564406156539917, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.543715238571167, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5272634029388428, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5147812366485596, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5040030479431152, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4982664585113525, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.497297525405884, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.491060256958008, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4783077239990234, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4895007610321045, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.490068197250366, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.490349292755127, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4921936988830566, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4988133907318115, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.499565601348877, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.500690221786499, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4998037815093994, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.492715358734131, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4960479736328125, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4893484115600586, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.507530689239502, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.502413034439087, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.490966796875, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.471787214279175, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4790914058685303, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.4964325428009033, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06607604282022887, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.09265411590992986, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.14987080103359174, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.1788482834994463, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.19785898855666298, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2129937246216316, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2233296419342931, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.22868217054263565, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23385012919896642, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24067921742340348, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.2456626061277224, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24640088593576967, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24492432631967515, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.24510889627168697, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.24769287559985234, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.24806201550387597, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2499077150239941, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.24621631598375784, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.25692137320044295, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2530454042081949, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.25249169435215946, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.25046142488002954, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2532299741602067, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.25987449243263194, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2541528239202658, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2587670727205611, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26098191214470284, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.005907260957322437, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006040399793049385, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006007055179305869, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006451195396267216, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006659038126599342, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0070181938390298645, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007815796359018358, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008753478805325246, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010091609001667029, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.011019276888071215, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011560805355707774, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011709564927391966, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013903737360372653, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.038248607756457005, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07263312141150463, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.09635168792905145, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1172735628321655, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1327329056180098, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1456601088339278, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15277870154535206, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1594697234341589, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16740682025606823, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17329211108989792, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.17596622469944811, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.17557351914921904, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.17728266438408577, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1848567731889973, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1863199801727162, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.18952655851316402, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19195639280758783, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19627548303183903, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19549553589124982, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19978661338267237, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19828577662323055, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.197190129615596, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19309128331234204, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20179019707805668, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.19786953966517573, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.1964950497116027, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.19569274259201674, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.19614881670813222, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.2041447053251546, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19762878428018782, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.20084793437837853, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2101797841242807, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.282520604133606, "validation/loss_best": 2.4964325428009033, "validation/acc_best": 0.26098191214470284, "validation/f1_best": 0.2101797841242807} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 2.609562696218491, "train/grad": 0.1693541357666254, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1261376953125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.125772705078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.125067138671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.124468994140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123927001953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123094482421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.122225341796875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.121151123046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1197412109375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.11828125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.116566162109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.113397216796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.107921142578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0697625732421874, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8867498779296876, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.750017547607422, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.656384353637695, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.58431583404541, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5282991409301756, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4912845993041994, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4553572082519532, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4244246292114258, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.395116491317749, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.366851396560669, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3410112380981447, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.313536834716797, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2874186706542967, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2575109815597534, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2339647436141967, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1962105989456178, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.1713436961174013, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1628504157066346, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1606017708778382, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.155581226348877, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1473936939239504, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.13605208158493, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.146276710033417, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.147825666666031, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.126763570904732, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1501910454034805, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1417300981283187, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1527083778381346, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.1702660059928895, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.1769136995077134, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.2286082887649536, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008996940781362355, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00899646086152643, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008995008482597768, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008992500365711748, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008989664900582284, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008984916624613107, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008978966891299933, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008971709231846035, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008960853940807282, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008948888930026442, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008942387369461357, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008969146695453673, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00917570234509185, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011611851216293871, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.018899372937157752, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.023009184156544505, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025255451491102577, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02620070959441364, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026562153613194823, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026736529441550375, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02709977710619569, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027712059896439312, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028480665609240532, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02926667945459485, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.030018723141402005, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030806614141911267, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.03141524289734662, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03214493065141141, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03248076884075999, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.033157412381842735, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03353669314645231, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03302186963148415, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03237423405051231, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.0323123870883137, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.032134766755625606, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03209114952012897, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.03160596875473857, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030957378959283233, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03210351567715406, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.028511104974895715, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.028261337196454406, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02760763846337795, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.02940594549290836, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.030799428038299083, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.03004440659657121, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1223506927490234, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1222188472747803, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12200927734375, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1218011379241943, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12158465385437, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1213107109069824, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.120975971221924, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1205861568450928, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.120025873184204, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119277000427246, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1183512210845947, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1161904335021973, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1115033626556396, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.070539712905884, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8939101696014404, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.774557113647461, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.693347215652466, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6322219371795654, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5876259803771973, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5646042823791504, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.545607805252075, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5300965309143066, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.518904447555542, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5081098079681396, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.5022177696228027, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.500361680984497, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4907591342926025, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.475386619567871, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.481400966644287, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4768965244293213, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.479792356491089, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.481499671936035, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.495650053024292, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4871749877929688, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.484443187713623, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4850473403930664, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4786112308502197, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4767041206359863, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.467010259628296, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4636826515197754, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.460331916809082, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.462646722793579, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.4637575149536133, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.46773099899292, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.445470094680786, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0651531930601698, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.07069029162052418, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0976375046142488, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15282392026578073, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18456995201181248, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20450350682908822, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21410114433370248, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22406792174234036, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23255813953488372, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23606496862310816, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24215577703949798, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24529346622369877, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2484311554078996, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24898486526393504, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2500922849760059, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2561830933923957, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2567368032484312, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.25083056478405313, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.24880029531192321, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25101513473606496, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2515688445921004, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2602436323366556, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2604282022886674, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26264304171280917, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.257844222960502, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2589516426725729, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.260797342192691, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2678110003691399, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006489139250945391, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.0065477723648813555, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0065759599149039965, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006617767894742248, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00785768888285287, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.008830818601768277, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.009739866414209342, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010729118127361837, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.010942201661291194, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010946463313994235, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011934021614552067, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013267796410731614, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015205365728368295, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0407843256016637, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07743333519112236, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.106383613142716, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12671449295685816, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13549621287749694, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1457759745915481, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15490305428316367, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.15993469099104088, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16731355339039566, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17226884284375735, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.17776903400490918, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18042237320626378, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18364364917929274, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18631905600573942, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19286283087440395, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19316548047546642, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19742030339275893, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.19679878455353403, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.19570870632598225, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.19446380412513786, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.1953156547588859, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19771246706743864, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19673945870686152, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.2081558244031355, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.207369570908883, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20966446966538835, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20895692624653162, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21292104658015254, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20675288256036814, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20871696888308003, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2048245508185406, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2153142526557914, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 2.2286082887649536, "validation/loss_best": 2.445470094680786, "validation/acc_best": 0.2678110003691399, "validation/f1_best": 0.2153142526557914} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 2.597270692586899, "train/grad": 0.1681889284774661, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12366455078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12330322265625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12263671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.122099609375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.121458740234375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.120728759765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1198046875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11883056640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.117506103515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.115975341796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11419921875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.110858154296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.10482666015625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.0581890869140627, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8680191040039062, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7405072021484376, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6509213256835937, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5808813858032225, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.526706199645996, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.489936809539795, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4535890579223634, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4218482398986816, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.391535530090332, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.362370195388794, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.33483624458313, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.304317874908447, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2745175552368164, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2438653230667116, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.2184629225730896, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.175910761356354, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.149420585632324, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1395829153060912, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.134775609970093, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.130621132850647, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1202618002891542, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.108505915403366, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.114042730331421, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.1178113269805907, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.096515935063362, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.125577843785286, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.1170746755599974, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.1283036518096923, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.139339872002602, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.1369013601541518, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.18772431075573, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008945160114672035, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008944914720486849, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008942997194826602, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008940120998304338, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008936946650501341, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008931942814961076, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008924436396919191, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008916259440593422, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008904325012117624, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008891409218776972, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008884543746244162, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008917632999364287, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009161028957460076, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011973938727751375, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.01928612750954926, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.0231453347671777, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025266211312264204, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.026156825264915824, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.02649398684501648, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026645227689296006, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02698511234484613, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.02755328806117177, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.028271592408418655, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028999146074056625, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029699170142412187, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030480887265875934, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.031098577920347453, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03176766169257462, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03219389637932182, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03302231385372579, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03338611552491784, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03298622896894812, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03240618774667382, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03238771670497954, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.032241439186036586, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03215464475564658, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.031486026234924795, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.030712035028263928, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03188701754435897, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02828017935156822, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.027958389474079012, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.027383595462888478, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.0291842635627836, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.02968272887170315, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02904969940893352, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122309684753418, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1221609115600586, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121943712234497, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121731758117676, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121514081954956, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1212310791015625, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1208746433258057, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120471477508545, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.119852304458618, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119080066680908, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1181111335754395, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.115807294845581, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.110713243484497, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.063546895980835, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.881945848464966, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.766530752182007, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6870429515838623, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.627243757247925, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5847530364990234, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5628299713134766, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5439743995666504, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.52839994430542, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5165398120880127, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5046651363372803, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.496939182281494, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4921512603759766, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.478933811187744, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.460820198059082, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4631435871124268, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4518775939941406, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4455676078796387, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4482550621032715, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4585072994232178, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4546830654144287, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.460547924041748, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4646637439727783, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.46303653717041, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.466926097869873, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4614503383636475, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4680213928222656, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4797277450561523, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.4686923027038574, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.474724292755127, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.480354070663452, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.475261688232422, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.0651531930601698, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06902916205241787, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.09560723514211886, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.1539313399778516, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18401624215577703, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20505721668512367, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21779254337393872, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.2249907715023994, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2321889996308601, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2369878183831672, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24141749723145073, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24344776670358065, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24806201550387597, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.24935400516795866, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25193798449612403, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2513842746400886, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25655223329641935, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.260797342192691, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26301218161683276, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.2646733111849391, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26688815060908083, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.25987449243263194, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25839793281653745, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26854928017718716, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26393503137689184, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.2622739018087855, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2622739018087855, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.26578073089701, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25452196382428943, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.2606127722406792, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.25987449243263194, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.0060405654168220095, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006021736880034081, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006466095358765381, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0063951431342954045, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006596806784821882, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007264409348886521, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008210641076555331, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008544338679106816, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009135151498282066, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009609991047537505, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010487658589439295, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011159816594494942, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013502896212755468, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.03857779194274432, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07714885953080673, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10468457441487443, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.1263539885223041, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13854392621001668, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1467244953781083, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.1530647404398596, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1598534459088254, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16419048212778045, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.1689445339287133, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.17542412976070945, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.17764936287896735, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18278432294703872, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18355360393348966, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19089273897844816, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19615140181272617, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19954529732349688, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2018230370892549, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2022982225651291, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20247772478161308, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.19783639505465786, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.19806399513890305, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.19999209448006558, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20665602211272205, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20100590551240494, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.19964127532960782, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2004778210777359, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.1995968434324927, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20291723741880233, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.19479873333592349, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.19929034488175482, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.19828811488573647, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 36, "lr_best": 0.0021299999999999995, "wd_best": 0.05, "train/loss_best": 2.114042730331421, "validation/loss_best": 2.46303653717041, "validation/acc_best": 0.26854928017718716, "validation/f1_best": 0.20665602211272205} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 2.592618565559387, "train/grad": 0.16524013444781305, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.127940673828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1275634765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12685791015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126353759765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12580322265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.125029296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.124072265625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.123101806640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121885986328125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.120238037109375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.118687744140625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.11529296875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.109150390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.05883544921875, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8667117309570314, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.742983856201172, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.6549617767333986, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.584587173461914, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5291941070556643, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4913215827941895, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.453747262954712, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4210572719573973, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.389965124130249, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.360574893951416, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3332087421417236, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.303639307022095, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2731775665283203, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2411498737335207, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.214525055885315, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1731624722480776, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.14617406129837, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.133645484447479, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.12674075961113, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.1183852410316466, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1064255332946775, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.097127685546875, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0973628079891204, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.103093857169151, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.078899231553078, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.1025102031230927, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0860580736398697, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0959827417135237, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.110014451146126, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.104556527733803, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.159054898619652, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008804214810952544, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008803426919039339, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00880171877797693, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008799500628374517, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008796727727167308, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008792181743774562, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00878638748312369, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008778977042529732, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008768427604809403, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008756848769262433, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008753313547931612, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008793495579157025, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009064104205463082, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012085621994920075, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019307427979074417, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.02303911205846816, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025166541426442562, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.026059409105218947, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026436344976536928, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026633615083992482, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.02701156562194228, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027617480400949718, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.02834438916295767, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.02905187680386007, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.02969211695715785, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.030369699019938707, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030876425616443156, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03141376392915845, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.03169241725467145, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03244637834839523, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03274189063347876, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.032342464672401545, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.03158744735643268, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.031464577605947855, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03127461045049131, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.031241896552965043, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.030452216397970914, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.029822614258155227, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.03065991846844554, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.02740303519181907, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02728811669163406, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.0266153319273144, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.028167533287778497, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.028939282232895495, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02835518610663712, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.12229061126709, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122159004211426, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1219570636749268, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1217477321624756, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121533155441284, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121232271194458, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.120891571044922, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120469331741333, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1198630332946777, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1190826892852783, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.118074417114258, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.115722417831421, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.11038875579834, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0597732067108154, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8768749237060547, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.764261245727539, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.685608148574829, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.6253740787506104, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.582426071166992, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5600345134735107, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5408475399017334, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5248658657073975, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.512458086013794, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5006048679351807, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4921152591705322, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.485887289047241, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4698569774627686, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.4513678550720215, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.4528896808624268, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.442996025085449, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.439246654510498, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.440882444381714, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.450040102005005, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4439492225646973, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.448129415512085, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.4468917846679688, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4460413455963135, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.453033924102783, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.450998067855835, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.4545137882232666, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4582507610321045, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.452381134033203, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.4648020267486572, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4620118141174316, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.4609482288360596, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.10151347360649686, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15780730897009967, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18420081210778885, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20487264673311184, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.2188999630860096, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22665190107050573, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23440383905500184, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23735695828719083, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.24363233665559247, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24621631598375784, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.2499077150239941, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.2517534145441122, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25341454411221853, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2543373938722776, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2643041712809155, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26688815060908083, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26541159099298633, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.26356589147286824, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.262827611664821, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2652270210409745, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26688815060908083, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2648578811369509, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.26965669988925806, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.26559616094499816, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.27260981912144705, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2587670727205611, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.26707272056109266, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2631967515688446, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006025891471878652, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006017670652923513, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006440633873036643, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006527522581381991, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006596806784821882, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007121202262454447, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008056664406052086, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008738992484854682, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009334249046188738, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010538182554312756, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011133071337376232, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01143248356603835, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.014271193756301781, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04286781632332712, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07941375254239248, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10541621106865325, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12662132700058468, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1392761306650793, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.14786189192747987, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15573184687343852, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.1615013043940083, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16785294468372067, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17182919121635223, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.17794730166614267, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18037114807450097, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18538238061082923, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18752946308532306, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.192277596887187, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19984368057957325, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20363924690680577, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20510304078637667, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.20437331074367618, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20462550750459726, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20545702524009615, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20680379064416363, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2067930725547041, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20667731536196107, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.2057422888125362, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2046657573911026, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.21205347781570572, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20754329746831282, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21158476658860004, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20339766017730362, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2092335904292643, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.20527594138655278, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 2.0959827417135237, "validation/loss_best": 2.452381134033203, "validation/acc_best": 0.27260981912144705, "validation/f1_best": 0.21158476658860004} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 2.588732880353928, "train/grad": 0.1607858270406723, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.132978515625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.132498779296875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131820068359375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.131187744140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130560302734375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129693603515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12870361328125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1276904296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126241455078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124476318359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.122725830078125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.119171142578125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.112767333984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.060108642578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.866413116455078, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.7417958068847654, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.651762161254883, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5805890274047854, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.5254079818725588, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4876104545593263, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4504583644866944, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4182027053833006, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.387264986038208, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.357198190689087, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.3290367698669434, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.2986216831207273, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.2674878644943237, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2356177806854247, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.209539222717285, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.1666098403930665, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.1379397654533387, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1279155588150025, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.120480556488037, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.113786795139313, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.1004645156860353, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0870141196250915, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0934001135826112, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.093543348312378, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0658528196811674, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.084379994869232, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.069230933189392, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0746411836147307, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.0893191039562224, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.078669285774231, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.13953608751297, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008788994285278023, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008788667188491672, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008787092121783644, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008784743212163448, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008781796204857528, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008776993388310075, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008770590049680322, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008762663768138737, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008751257145777345, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.008739107733126729, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008734655915759504, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008776708818040789, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009055598773993551, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012160398880951107, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019294911664910614, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.022889324589632453, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.024915445991791785, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.02575111056677997, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026080394024029376, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.026236392157152295, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026587072676047683, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027155336067080496, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027838703421875836, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028526034727692603, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029152675122022628, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.029824205059558153, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030274924635887147, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.03076539024710655, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.031023869374766946, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03155894072726369, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03183015990070999, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.03133957440033555, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030761761022731662, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.03063251117244363, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.03029820904135704, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.03007109803147614, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02930775359272957, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.02864077052101493, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.029388401824980974, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.026222277712076903, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.026020028404891492, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.02548740966245532, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.027012604251503945, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.027590928254649042, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.02681882950477302, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.122300624847412, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1221771240234375, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1219470500946045, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.121744155883789, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.121530294418335, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.121250867843628, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1208908557891846, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1204729080200195, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1198551654815674, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1190743446350098, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1180949211120605, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1157031059265137, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1102874279022217, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.058493137359619, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.874929666519165, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7631118297576904, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6853389739990234, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.625966787338257, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.5833919048309326, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5612306594848633, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5423359870910645, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.526737689971924, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5148115158081055, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5033371448516846, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4954378604888916, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.4893600940704346, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4731762409210205, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.455256938934326, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.456843852996826, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.447014093399048, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4424166679382324, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.442995548248291, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.452662706375122, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4458181858062744, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4494011402130127, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.449786901473999, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.4454774856567383, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4529802799224854, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.4494755268096924, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.452707052230835, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.454577922821045, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.4536538124084473, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.4584591388702393, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4555349349975586, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.4507203102111816, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.1020671834625323, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15633074935400518, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18660022148394242, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.2059800664451827, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21816168327796234, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22554448135843486, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.23292727943890734, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.2368032484311554, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2412329272794389, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24529346622369877, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24769287559985234, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.25046142488002954, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.2552602436323367, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.2596899224806202, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26135105204872644, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26375046142488, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26264304171280917, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.2604282022886674, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2606127722406792, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.25858250276854927, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.2661498708010336, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.26504245108896274, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.26504245108896274, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2652270210409745, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2652270210409745, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.25839793281653745, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.26799557032115173, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.2652270210409745, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006027296256169496, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006025891471878652, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006296256866391531, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.0063951431342954045, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006465702580729298, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0070079372599092145, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.007650319722401271, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.008491420365347413, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.009182847244597038, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009799118559565605, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010701455311136095, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011040779096328314, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013917316267007237, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04339007111895459, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07868393027288408, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.1061782829036985, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12699918964828286, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.1383625923997369, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1468705154731854, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15310150143215798, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.16005150278434793, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16574321668071143, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.17036704527902713, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.1758111746559491, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.18012809262370466, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18292147988794905, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.18909434841583941, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.1919522601534347, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19720368042247272, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.20134991286202797, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.2048681060170092, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.2026161395401623, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20390323292947468, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20657569057942157, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.20413409049594913, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.2083635312412234, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.21031640063928372, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.20893840340124634, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.2099880246737542, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.2089855172275078, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.21027326372755364, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.21099945042948773, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.20620726095146438, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.2154692848222687, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.2124753542556994, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 43, "lr_best": 0.006599999999999999, "wd_best": 0.05, "train/loss_best": 2.078669285774231, "validation/loss_best": 2.4555349349975586, "validation/acc_best": 0.26799557032115173, "validation/f1_best": 0.2154692848222687} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 2.5769711005687714, "train/grad": 0.16018606625497342, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.121925048828125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.121539306640625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12080810546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.120179443359375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.119630126953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1186572265625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.117650146484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.11659912109375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.115098876953125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.113515625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.11164306640625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.10802001953125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1013525390625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.046898193359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 2.8503558349609377, "train/loss_015_lr2.3e-01_wd1.0e+00": 2.727609100341797, "train/loss_016_lr2.7e-01_wd1.0e+00": 2.640202941894531, "train/loss_017_lr3.2e-01_wd1.0e+00": 2.5707970809936525, "train/loss_018_lr3.8e-01_wd1.0e+00": 2.516995697021484, "train/loss_019_lr4.4e-01_wd1.0e+00": 2.4805680465698243, "train/loss_020_lr5.2e-01_wd1.0e+00": 2.4443653297424315, "train/loss_021_lr6.1e-01_wd1.0e+00": 2.4127787208557128, "train/loss_022_lr7.2e-01_wd1.0e+00": 2.381978759765625, "train/loss_023_lr8.5e-01_wd1.0e+00": 2.352246403694153, "train/loss_024_lr1.0e+00_wd1.0e+00": 2.324166717529297, "train/loss_025_lr1.2e+00_wd1.0e+00": 2.293431625366211, "train/loss_026_lr1.4e+00_wd1.0e+00": 2.261707327365875, "train/loss_027_lr1.6e+00_wd1.0e+00": 2.2294458508491517, "train/loss_028_lr1.9e+00_wd1.0e+00": 2.202161407470703, "train/loss_029_lr2.3e+00_wd1.0e+00": 2.158544132709503, "train/loss_030_lr2.7e+00_wd1.0e+00": 2.1282802164554595, "train/loss_031_lr3.1e+00_wd1.0e+00": 2.1164140689373014, "train/loss_032_lr3.7e+00_wd1.0e+00": 2.1072528386116027, "train/loss_033_lr4.3e+00_wd1.0e+00": 2.097967302799225, "train/loss_034_lr5.1e+00_wd1.0e+00": 2.083587909936905, "train/loss_035_lr6.0e+00_wd1.0e+00": 2.0696448004245758, "train/loss_036_lr7.1e+00_wd1.0e+00": 2.0680124914646147, "train/loss_037_lr8.3e+00_wd1.0e+00": 2.071757036447525, "train/loss_038_lr9.8e+00_wd1.0e+00": 2.0432922941446305, "train/loss_039_lr1.2e+01_wd1.0e+00": 2.0606255680322647, "train/loss_040_lr1.4e+01_wd1.0e+00": 2.0467382740974425, "train/loss_041_lr1.6e+01_wd1.0e+00": 2.0510490572452547, "train/loss_042_lr1.9e+01_wd1.0e+00": 2.066575826406479, "train/loss_043_lr2.2e+01_wd1.0e+00": 2.0565902668237688, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.11542728304863, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.171875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.171875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.008920621150173247, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.008919980525970459, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.008918786647263914, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.008916513249278068, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.008913500783964991, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.008908547391183675, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.008901646642480046, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.008893757334444672, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.008882402775343507, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00887073228834197, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.008866898543201386, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.008912034425884485, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009201763786841184, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.012412131247110665, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.019737184816040098, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.023375198915600776, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.025400646328926087, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.026222405452281237, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.026503178589046, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.02659918403252959, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.026859267698600888, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.027336335787549616, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.027948368629440664, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.028541939659044148, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.029120766427367925, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.0297314852848649, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.030137943029403688, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.030547497821971775, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.030779674630612135, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.03133712589740753, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.03155661093071103, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.031093504754826428, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.030396300293505193, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.030238614324480294, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.030005838833749295, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.029787038546055557, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.02899664668366313, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.028313599498942493, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.029080612175166606, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.025999374818056822, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.02577600536867976, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.025052214171737433, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.026411730591207744, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.026881863186135887, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.026228965097106993, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.0, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.0, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1222984790802, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.122191905975342, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.121948480606079, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1217563152313232, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1215436458587646, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1212317943573, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1208958625793457, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.120483160018921, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1198649406433105, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.119096040725708, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1180992126464844, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.11572003364563, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.110304594039917, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.0583672523498535, "validation/loss_014_lr2.0e-01_wd1.0e+00": 2.8747076988220215, "validation/loss_015_lr2.3e-01_wd1.0e+00": 2.7630038261413574, "validation/loss_016_lr2.7e-01_wd1.0e+00": 2.6853673458099365, "validation/loss_017_lr3.2e-01_wd1.0e+00": 2.625981569290161, "validation/loss_018_lr3.8e-01_wd1.0e+00": 2.583461046218872, "validation/loss_019_lr4.4e-01_wd1.0e+00": 2.5612564086914062, "validation/loss_020_lr5.2e-01_wd1.0e+00": 2.5423741340637207, "validation/loss_021_lr6.1e-01_wd1.0e+00": 2.5268733501434326, "validation/loss_022_lr7.2e-01_wd1.0e+00": 2.5151002407073975, "validation/loss_023_lr8.5e-01_wd1.0e+00": 2.5037341117858887, "validation/loss_024_lr1.0e+00_wd1.0e+00": 2.4959754943847656, "validation/loss_025_lr1.2e+00_wd1.0e+00": 2.49039363861084, "validation/loss_026_lr1.4e+00_wd1.0e+00": 2.4746952056884766, "validation/loss_027_lr1.6e+00_wd1.0e+00": 2.457075834274292, "validation/loss_028_lr1.9e+00_wd1.0e+00": 2.458885908126831, "validation/loss_029_lr2.3e+00_wd1.0e+00": 2.4493770599365234, "validation/loss_030_lr2.7e+00_wd1.0e+00": 2.4441075325012207, "validation/loss_031_lr3.1e+00_wd1.0e+00": 2.4453675746917725, "validation/loss_032_lr3.7e+00_wd1.0e+00": 2.4557387828826904, "validation/loss_033_lr4.3e+00_wd1.0e+00": 2.4487082958221436, "validation/loss_034_lr5.1e+00_wd1.0e+00": 2.4517321586608887, "validation/loss_035_lr6.0e+00_wd1.0e+00": 2.451824903488159, "validation/loss_036_lr7.1e+00_wd1.0e+00": 2.447922945022583, "validation/loss_037_lr8.3e+00_wd1.0e+00": 2.4537150859832764, "validation/loss_038_lr9.8e+00_wd1.0e+00": 2.451695680618286, "validation/loss_039_lr1.2e+01_wd1.0e+00": 2.454941749572754, "validation/loss_040_lr1.4e+01_wd1.0e+00": 2.4567294120788574, "validation/loss_041_lr1.6e+01_wd1.0e+00": 2.4515979290008545, "validation/loss_042_lr1.9e+01_wd1.0e+00": 2.4589126110076904, "validation/loss_043_lr2.2e+01_wd1.0e+00": 2.4560794830322266, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_045_lr3.1e+01_wd1.0e+00": 2.4463796615600586, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1780545711517334, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1780545711517334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.10243632336655592, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.15725359911406422, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.18604651162790697, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.20524178663713546, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.21816168327796234, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.22591362126245848, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.2336655592469546, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.23606496862310816, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.2427094868955334, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.24437061646363972, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.24806201550387597, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.25064599483204136, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.2500922849760059, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.25544481358434845, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.25507567368032485, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.26005906238464377, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.26116648209671467, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.26411960132890366, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.26153562200073827, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.26098191214470284, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.2582133628645257, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.2574750830564784, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.2619047619047619, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.26707272056109266, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.2678110003691399, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.26245847176079734, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.26411960132890366, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.2648578811369509, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.2681801402731635, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.2591362126245847, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.26596530084902176, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.26651901070505724, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.036360280546327055, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.036360280546327055, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.006027296256169496, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.006028711103706571, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.006301773862699523, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006400738328511845, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006477307160671697, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007039049691638369, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00771398244315169, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0084115049643377, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.00911882954549026, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.009854715916343093, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.010859516588297452, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011132285791312542, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.013955927889924669, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.04406111100436119, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.07887193587803097, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.10616065355880673, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.12642748225458997, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.13829483160693753, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.1470807918171156, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.15327793058789752, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.15952478954176819, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.16666353286435234, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.16985178504325313, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.17606953365779757, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.17968307479759416, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.18291923673968025, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.1881168579379904, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.19096980947104433, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.19637715866189867, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.19906530174054315, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.20331236605556602, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.1996143987327413, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.20282547832450407, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.20180013947819042, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.2001488004325793, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.20410120816831365, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.20768420965305914, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.21013674903114624, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.20522490397332982, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.20578243762733064, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.20718663563239095, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.20918490608613471, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.2043625563705018, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.21026323235633446, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.20842926920490143, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0029237162362718908, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0029237162362718908, "id_best": 41, "lr_best": 0.0048, "wd_best": 0.05, "train/loss_best": 2.0510490572452547, "validation/loss_best": 2.4515979290008545, "validation/acc_best": 0.2681801402731635, "validation/f1_best": 0.20918490608613471} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/config.yaml b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c9f15e95e90b3456e12b1df9ba7c1f0a849140a3 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/config.yaml @@ -0,0 +1,96 @@ +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log.json new file mode 100644 index 0000000000000000000000000000000000000000..9082421820a35cc17971370a5bb582d3b395e3d4 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log.json @@ -0,0 +1 @@ +{"eval/epoch": 17, "eval/id_best": 48, "eval/lr_best": 0.015, "eval/wd_best": 0.05, "eval/train/loss": 2.9882452487945557, "eval/train/acc": 0.1260948400381081, "eval/train/acc_std": 0.0016799803398922983, "eval/train/f1": 0.06748049706394292, "eval/train/f1_std": 0.001232039036904175, "eval/validation/loss": 3.0699357986450195, "eval/validation/acc": 0.09856035437430787, "eval/validation/acc_std": 0.003519068052350125, "eval/validation/f1": 0.05337065353277928, "eval/validation/f1_std": 0.0025437532292329223, "eval/test/loss": 3.0537221431732178, "eval/test/acc": 0.10853432282003711, "eval/test/acc_std": 0.003694582884327914, "eval/test/f1": 0.05344040844793413, "eval/test/f1_std": 0.0023398666262379013, "eval/testid/loss": 3.0763120651245117, "eval/testid/acc": 0.09851551956815115, "eval/testid/acc_std": 0.003319479753087605, "eval/testid/f1": 0.04813280744449903, "eval/testid/f1_std": 0.002157374080036415} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json new file mode 100644 index 0000000000000000000000000000000000000000..93fde83acded65bc57daceea12c1baa14f395b93 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log_best.json @@ -0,0 +1 @@ +{"eval/best/epoch": 17, "eval/best/id_best": 48, "eval/best/lr_best": 0.015, "eval/best/wd_best": 0.05, "eval/best/train/loss": 2.9882452487945557, "eval/best/train/acc": 0.1260948400381081, "eval/best/train/acc_std": 0.0016799803398922983, "eval/best/train/f1": 0.06748049706394292, "eval/best/train/f1_std": 0.001232039036904175, "eval/best/validation/loss": 3.0699357986450195, "eval/best/validation/acc": 0.09856035437430787, "eval/best/validation/acc_std": 0.003519068052350125, "eval/best/validation/f1": 0.05337065353277928, "eval/best/validation/f1_std": 0.0025437532292329223, "eval/best/test/loss": 3.0537221431732178, "eval/best/test/acc": 0.10853432282003711, "eval/best/test/acc_std": 0.003694582884327914, "eval/best/test/f1": 0.05344040844793413, "eval/best/test/f1_std": 0.0023398666262379013, "eval/best/testid/loss": 3.0763120651245117, "eval/best/testid/acc": 0.09851551956815115, "eval/best/testid/acc_std": 0.003319479753087605, "eval/best/testid/f1": 0.04813280744449903, "eval/best/testid/f1_std": 0.002157374080036415} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json new file mode 100644 index 0000000000000000000000000000000000000000..92a8266bc3a7d2e3285e68484d7790c8423ad710 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_log_last.json @@ -0,0 +1 @@ +{"eval/last/epoch": 19, "eval/last/id_best": 48, "eval/last/lr_best": 0.015, "eval/last/wd_best": 0.05, "eval/last/train/loss": 2.982571601867676, "eval/last/train/acc": 0.13153446633270843, "eval/last/train/acc_std": 0.001709823373025919, "eval/last/train/f1": 0.07768764015066677, "eval/last/train/f1_std": 0.0013312216759696093, "eval/last/validation/loss": 3.0664048194885254, "eval/last/validation/acc": 0.09246954595791805, "eval/last/validation/acc_std": 0.003412208573411792, "eval/last/validation/f1": 0.05131313342992503, "eval/last/validation/f1_std": 0.002574510593444556, "eval/last/test/loss": 3.0546157360076904, "eval/last/test/acc": 0.10500927643784787, "eval/last/test/acc_std": 0.0038386365023441076, "eval/last/test/f1": 0.053889122218424686, "eval/last/test/f1_std": 0.002406258779541723, "eval/last/testid/loss": 3.07027268409729, "eval/last/testid/acc": 0.09928667823404666, "eval/last/testid/acc_std": 0.0035890550098870364, "eval/last/testid/f1": 0.053817882650971864, "eval/last/testid/f1_std": 0.002504878568639584} diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..609b81615d60e3b7ed45a34b09e7b0d4d01c7757 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",train,2.9882452487945557,0.1260948400381081,0.0016799803398922983,0.06748049706394292,0.001232039036904175 +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",validation,3.0699357986450195,0.09856035437430787,0.003519068052350125,0.05337065353277928,0.0025437532292329223 +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",test,3.0537221431732178,0.10853432282003711,0.003694582884327914,0.05344040844793413,0.0023398666262379013 +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",testid,3.0763120651245117,0.09851551956815115,0.003319479753087605,0.04813280744449903,0.002157374080036415 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv new file mode 100644 index 0000000000000000000000000000000000000000..609b81615d60e3b7ed45a34b09e7b0d4d01c7757 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table_best.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",train,2.9882452487945557,0.1260948400381081,0.0016799803398922983,0.06748049706394292,0.001232039036904175 +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",validation,3.0699357986450195,0.09856035437430787,0.003519068052350125,0.05337065353277928,0.0025437532292329223 +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",test,3.0537221431732178,0.10853432282003711,0.003694582884327914,0.05344040844793413,0.0023398666262379013 +flat_mae,reg,linear,nsd_cococlip,best,17,0.015,0.05,48,"[50, 1.0]",testid,3.0763120651245117,0.09851551956815115,0.003319479753087605,0.04813280744449903,0.002157374080036415 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv new file mode 100644 index 0000000000000000000000000000000000000000..b754c292977962da5be73eea457682be599a8b47 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/eval_table_last.csv @@ -0,0 +1,5 @@ +model,repr,clf,dataset,ckpt,epoch,lr,wd,hparam_id,hparam,split,loss,acc,acc_std,f1,f1_std +flat_mae,reg,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",train,2.982571601867676,0.13153446633270843,0.001709823373025919,0.07768764015066677,0.0013312216759696093 +flat_mae,reg,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",validation,3.0664048194885254,0.09246954595791805,0.003412208573411792,0.05131313342992503,0.002574510593444556 +flat_mae,reg,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",test,3.0546157360076904,0.10500927643784787,0.0038386365023441076,0.053889122218424686,0.002406258779541723 +flat_mae,reg,linear,nsd_cococlip,last,19,0.015,0.05,48,"[50, 1.0]",testid,3.07027268409729,0.09928667823404666,0.0035890550098870364,0.053817882650971864,0.002504878568639584 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/log.txt b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5bc8391f83c6508183e8b748afa97667aebb64ec --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/log.txt @@ -0,0 +1,959 @@ +fMRI foundation model probe eval +version: 0.1.dev65+g4003a1397 +sha: 6c01b606db98add5848cecd23e5d599250c0bf86, status: clean, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-02-24 21:41:14 +config: +output_root: experiments/decoders/output +name_prefix: eval_probe +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (nsd_cococlip reg linear) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +classifier_kwargs: + embed_dim: null + dropout: 0.0 + xavier_init: false + norm: false +lr_scale_grid: +- 0.02 +- 0.023 +- 0.028 +- 0.033 +- 0.038 +- 0.045 +- 0.053 +- 0.062 +- 0.074 +- 0.087 +- 0.1 +- 0.12 +- 0.14 +- 0.17 +- 0.2 +- 0.23 +- 0.27 +- 0.32 +- 0.38 +- 0.44 +- 0.52 +- 0.61 +- 0.72 +- 0.85 +- 1 +- 1.2 +- 1.4 +- 1.6 +- 1.9 +- 2.3 +- 2.7 +- 3.1 +- 3.7 +- 4.3 +- 5.1 +- 6 +- 7.1 +- 8.3 +- 9.8 +- 12 +- 14 +- 16 +- 19 +- 22 +- 26 +- 31 +- 36 +- 43 +- 50 +wd_scale_grid: +- 1.0 +num_workers: 8 +prefetch_factor: null +balanced_sampling: false +epochs: 20 +steps_per_epoch: 200 +batch_size: 64 +accum_iter: 2 +lr: 0.0003 +warmup_epochs: 5 +no_decay: false +weight_decay: 0.05 +clip_grad: 1.0 +metrics: +- acc +- f1 +cv_metric: acc +early_stopping: true +amp: true +device: cuda +seed: 4466 +debug: false +wandb: false +wandb_entity: null +wandb_project: fMRI-fm-eval +name: decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear +model: flat_mae +representation: reg +classifier: linear +dataset: nsd_cococlip +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: nsd_cococlip (flat) +train (n=32539): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 32539 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[1286 1180 1639 1868 834 824 1026 1042 913 1853 1503 2092 1001 1410 + 794 1241 1904 1872 2267 1428 889 904 1447 1322] +) + +validation (n=5418): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5418 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 161 276 345 126 142 143 185 112 295 285 387 169 250 159 193 316 334 + 343 215 172 141 226 246] +) + +test (n=5390): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5390 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[202 172 274 298 144 180 134 182 186 293 218 343 165 185 140 177 346 333 + 345 271 165 140 251 246] +) + +testid (n=5187): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'run', 'trial_id', 'nsd_id', 'category_id', 'path', 'start', 'end', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 5187 +}), + labels=[ 3 4 5 6 10 11 17 18 19 20 22 23 25 30 31 33 36 37 38 53 55 59 61 74], + counts=[197 159 267 273 123 153 175 184 139 310 215 386 153 230 118 192 330 306 + 349 223 143 127 249 186] +) + +running backbone on example batch to get embedding dim +embedding feature dim (reg): 768 +initializing sweep of classifier heads +classifiers: +ModuleList( + (0-48): 49 x LinearClassifier( + (linear): Linear(in_features=768, out_features=24, bias=True) + ) +) +classifier params (train): 0.9M (0.9M) +setting up optimizer +total batch size: 128 = 64 bs per gpu x 2 accum +lr: 3.00e-04 +full schedule: epochs = 20 (steps = 4000) (decay = True) +warmup: epochs = 5 (steps = 1000) +start training for 20 epochs +train: [0] [ 0/400] eta: 0:24:35 lr: nan time: 3.6895 data: 3.1968 max mem: 3929 +train: [0] [ 20/400] eta: 0:05:23 lr: 0.000003 loss: 3.1782 (3.1802) grad: 0.0775 (0.0813) time: 0.7102 data: 0.3367 max mem: 3972 +train: [0] [ 40/400] eta: 0:03:36 lr: 0.000006 loss: 3.1838 (3.1852) grad: 0.0831 (0.0841) time: 0.3388 data: 0.0033 max mem: 3972 +train: [0] [ 60/400] eta: 0:02:56 lr: 0.000009 loss: 3.1846 (3.1817) grad: 0.0838 (0.0840) time: 0.3519 data: 0.0038 max mem: 3972 +train: [0] [ 80/400] eta: 0:02:33 lr: 0.000012 loss: 3.1740 (3.1816) grad: 0.0815 (0.0829) time: 0.3572 data: 0.0041 max mem: 3972 +train: [0] [100/400] eta: 0:02:16 lr: 0.000015 loss: 3.1740 (3.1795) grad: 0.0791 (0.0822) time: 0.3511 data: 0.0039 max mem: 3972 +train: [0] [120/400] eta: 0:02:01 lr: 0.000018 loss: 3.1717 (3.1776) grad: 0.0830 (0.0826) time: 0.3371 data: 0.0039 max mem: 3972 +train: [0] [140/400] eta: 0:01:49 lr: 0.000021 loss: 3.1724 (3.1768) grad: 0.0826 (0.0821) time: 0.3457 data: 0.0037 max mem: 3972 +train: [0] [160/400] eta: 0:01:38 lr: 0.000024 loss: 3.1662 (3.1747) grad: 0.0766 (0.0810) time: 0.3337 data: 0.0039 max mem: 3972 +train: [0] [180/400] eta: 0:01:29 lr: 0.000027 loss: 3.1549 (3.1724) grad: 0.0771 (0.0808) time: 0.3514 data: 0.0037 max mem: 3972 +train: [0] [200/400] eta: 0:01:19 lr: 0.000030 loss: 3.1542 (3.1703) grad: 0.0800 (0.0808) time: 0.3420 data: 0.0041 max mem: 3972 +train: [0] [220/400] eta: 0:01:11 lr: 0.000033 loss: 3.1583 (3.1694) grad: 0.0772 (0.0806) time: 0.3733 data: 0.0039 max mem: 3972 +train: [0] [240/400] eta: 0:01:03 lr: 0.000036 loss: 3.1583 (3.1685) grad: 0.0786 (0.0808) time: 0.3892 data: 0.0044 max mem: 3972 +train: [0] [260/400] eta: 0:00:54 lr: 0.000039 loss: 3.1583 (3.1679) grad: 0.0806 (0.0804) time: 0.3384 data: 0.0039 max mem: 3972 +train: [0] [280/400] eta: 0:00:46 lr: 0.000042 loss: 3.1554 (3.1670) grad: 0.0755 (0.0801) time: 0.3566 data: 0.0041 max mem: 3972 +train: [0] [300/400] eta: 0:00:38 lr: 0.000045 loss: 3.1518 (3.1659) grad: 0.0735 (0.0798) time: 0.3498 data: 0.0042 max mem: 3972 +train: [0] [320/400] eta: 0:00:30 lr: 0.000048 loss: 3.1536 (3.1651) grad: 0.0735 (0.0797) time: 0.3541 data: 0.0043 max mem: 3972 +train: [0] [340/400] eta: 0:00:22 lr: 0.000051 loss: 3.1587 (3.1650) grad: 0.0750 (0.0795) time: 0.3471 data: 0.0039 max mem: 3972 +train: [0] [360/400] eta: 0:00:15 lr: 0.000054 loss: 3.1537 (3.1642) grad: 0.0748 (0.0794) time: 0.3393 data: 0.0041 max mem: 3972 +train: [0] [380/400] eta: 0:00:07 lr: 0.000057 loss: 3.1523 (3.1644) grad: 0.0723 (0.0789) time: 0.3410 data: 0.0040 max mem: 3972 +train: [0] [399/400] eta: 0:00:00 lr: 0.000060 loss: 3.1527 (3.1638) grad: 0.0759 (0.0789) time: 0.3488 data: 0.0040 max mem: 3972 +train: [0] Total time: 0:02:30 (0.3765 s / it) +train: [0] Summary: lr: 0.000060 loss: 3.1527 (3.1638) grad: 0.0759 (0.0789) +eval (validation): [0] [ 0/85] eta: 0:17:16 time: 12.1931 data: 11.9281 max mem: 3972 +eval (validation): [0] [20/85] eta: 0:00:59 time: 0.3480 data: 0.0154 max mem: 3972 +eval (validation): [0] [40/85] eta: 0:00:28 time: 0.3554 data: 0.0043 max mem: 3972 +eval (validation): [0] [60/85] eta: 0:00:13 time: 0.3547 data: 0.0037 max mem: 3972 +eval (validation): [0] [80/85] eta: 0:00:02 time: 0.3239 data: 0.0039 max mem: 3972 +eval (validation): [0] [84/85] eta: 0:00:00 time: 0.3155 data: 0.0038 max mem: 3972 +eval (validation): [0] Total time: 0:00:41 (0.4874 s / it) +cv: [0] best hparam: (1.2, 1.0) (025) ('025_lr1.2e+00_wd1.0e+00') loss: 3.130 acc: 0.072 f1: 0.009 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [1] [ 0/400] eta: 0:22:26 lr: nan time: 3.3672 data: 3.1085 max mem: 3972 +train: [1] [ 20/400] eta: 0:03:22 lr: 0.000063 loss: 3.1468 (3.1537) grad: 0.0735 (0.0756) time: 0.3916 data: 0.0043 max mem: 3972 +train: [1] [ 40/400] eta: 0:02:40 lr: 0.000066 loss: 3.1474 (3.1545) grad: 0.0767 (0.0765) time: 0.3518 data: 0.0036 max mem: 3972 +train: [1] [ 60/400] eta: 0:02:22 lr: 0.000069 loss: 3.1539 (3.1492) grad: 0.0759 (0.0752) time: 0.3625 data: 0.0042 max mem: 3972 +train: [1] [ 80/400] eta: 0:02:07 lr: 0.000072 loss: 3.1491 (3.1486) grad: 0.0752 (0.0751) time: 0.3389 data: 0.0039 max mem: 3972 +train: [1] [100/400] eta: 0:01:56 lr: 0.000075 loss: 3.1498 (3.1483) grad: 0.0756 (0.0754) time: 0.3428 data: 0.0038 max mem: 3972 +train: [1] [120/400] eta: 0:01:46 lr: 0.000078 loss: 3.1496 (3.1477) grad: 0.0773 (0.0761) time: 0.3452 data: 0.0035 max mem: 3972 +train: [1] [140/400] eta: 0:01:37 lr: 0.000081 loss: 3.1381 (3.1467) grad: 0.0775 (0.0764) time: 0.3327 data: 0.0041 max mem: 3972 +train: [1] [160/400] eta: 0:01:29 lr: 0.000084 loss: 3.1496 (3.1483) grad: 0.0728 (0.0760) time: 0.3520 data: 0.0040 max mem: 3972 +train: [1] [180/400] eta: 0:01:21 lr: 0.000087 loss: 3.1448 (3.1475) grad: 0.0747 (0.0763) time: 0.3464 data: 0.0043 max mem: 3972 +train: [1] [200/400] eta: 0:01:13 lr: 0.000090 loss: 3.1391 (3.1486) grad: 0.0805 (0.0767) time: 0.3442 data: 0.0040 max mem: 3972 +train: [1] [220/400] eta: 0:01:05 lr: 0.000093 loss: 3.1447 (3.1485) grad: 0.0776 (0.0766) time: 0.3606 data: 0.0037 max mem: 3972 +train: [1] [240/400] eta: 0:00:58 lr: 0.000096 loss: 3.1434 (3.1480) grad: 0.0735 (0.0766) time: 0.3413 data: 0.0038 max mem: 3972 +train: [1] [260/400] eta: 0:00:50 lr: 0.000099 loss: 3.1430 (3.1482) grad: 0.0706 (0.0763) time: 0.3578 data: 0.0041 max mem: 3972 +train: [1] [280/400] eta: 0:00:43 lr: 0.000102 loss: 3.1387 (3.1477) grad: 0.0707 (0.0760) time: 0.3437 data: 0.0040 max mem: 3972 +train: [1] [300/400] eta: 0:00:36 lr: 0.000105 loss: 3.1446 (3.1480) grad: 0.0733 (0.0759) time: 0.3430 data: 0.0040 max mem: 3972 +train: [1] [320/400] eta: 0:00:28 lr: 0.000108 loss: 3.1377 (3.1474) grad: 0.0742 (0.0760) time: 0.3448 data: 0.0042 max mem: 3972 +train: [1] [340/400] eta: 0:00:21 lr: 0.000111 loss: 3.1487 (3.1489) grad: 0.0718 (0.0756) time: 0.3352 data: 0.0040 max mem: 3972 +train: [1] [360/400] eta: 0:00:14 lr: 0.000114 loss: 3.1487 (3.1482) grad: 0.0694 (0.0757) time: 0.3513 data: 0.0041 max mem: 3972 +train: [1] [380/400] eta: 0:00:07 lr: 0.000117 loss: 3.1385 (3.1476) grad: 0.0740 (0.0758) time: 0.3508 data: 0.0042 max mem: 3972 +train: [1] [399/400] eta: 0:00:00 lr: 0.000120 loss: 3.1450 (3.1488) grad: 0.0740 (0.0758) time: 0.3497 data: 0.0042 max mem: 3972 +train: [1] Total time: 0:02:22 (0.3571 s / it) +train: [1] Summary: lr: 0.000120 loss: 3.1450 (3.1488) grad: 0.0740 (0.0758) +eval (validation): [1] [ 0/85] eta: 0:04:50 time: 3.4197 data: 3.2034 max mem: 3972 +eval (validation): [1] [20/85] eta: 0:00:33 time: 0.3752 data: 0.0349 max mem: 3972 +eval (validation): [1] [40/85] eta: 0:00:19 time: 0.3401 data: 0.0039 max mem: 3972 +eval (validation): [1] [60/85] eta: 0:00:10 time: 0.3507 data: 0.0045 max mem: 3972 +eval (validation): [1] [80/85] eta: 0:00:01 time: 0.3198 data: 0.0042 max mem: 3972 +eval (validation): [1] [84/85] eta: 0:00:00 time: 0.3098 data: 0.0042 max mem: 3972 +eval (validation): [1] Total time: 0:00:32 (0.3840 s / it) +cv: [1] best hparam: (0.32, 1.0) (017) ('017_lr3.2e-01_wd1.0e+00') loss: 3.130 acc: 0.071 f1: 0.010 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [2] [ 0/400] eta: 0:28:35 lr: nan time: 4.2892 data: 4.0316 max mem: 3972 +train: [2] [ 20/400] eta: 0:03:16 lr: 0.000123 loss: 3.1440 (3.1516) grad: 0.0729 (0.0755) time: 0.3287 data: 0.0033 max mem: 3972 +train: [2] [ 40/400] eta: 0:02:38 lr: 0.000126 loss: 3.1393 (3.1453) grad: 0.0747 (0.0770) time: 0.3617 data: 0.0040 max mem: 3972 +train: [2] [ 60/400] eta: 0:02:20 lr: 0.000129 loss: 3.1392 (3.1473) grad: 0.0818 (0.0786) time: 0.3577 data: 0.0033 max mem: 3972 +train: [2] [ 80/400] eta: 0:02:07 lr: 0.000132 loss: 3.1468 (3.1482) grad: 0.0777 (0.0780) time: 0.3505 data: 0.0038 max mem: 3972 +train: [2] [100/400] eta: 0:01:56 lr: 0.000135 loss: 3.1456 (3.1475) grad: 0.0744 (0.0778) time: 0.3451 data: 0.0042 max mem: 3972 +train: [2] [120/400] eta: 0:01:46 lr: 0.000138 loss: 3.1318 (3.1449) grad: 0.0722 (0.0767) time: 0.3401 data: 0.0040 max mem: 3972 +train: [2] [140/400] eta: 0:01:37 lr: 0.000141 loss: 3.1423 (3.1456) grad: 0.0719 (0.0762) time: 0.3393 data: 0.0040 max mem: 3972 +train: [2] [160/400] eta: 0:01:29 lr: 0.000144 loss: 3.1470 (3.1447) grad: 0.0732 (0.0758) time: 0.3620 data: 0.0043 max mem: 3972 +train: [2] [180/400] eta: 0:01:21 lr: 0.000147 loss: 3.1301 (3.1433) grad: 0.0718 (0.0753) time: 0.3528 data: 0.0041 max mem: 3972 +train: [2] [200/400] eta: 0:01:13 lr: 0.000150 loss: 3.1285 (3.1425) grad: 0.0723 (0.0753) time: 0.3388 data: 0.0043 max mem: 3972 +train: [2] [220/400] eta: 0:01:05 lr: 0.000153 loss: 3.1311 (3.1419) grad: 0.0723 (0.0749) time: 0.3411 data: 0.0040 max mem: 3972 +train: [2] [240/400] eta: 0:00:57 lr: 0.000156 loss: 3.1358 (3.1411) grad: 0.0712 (0.0749) time: 0.3325 data: 0.0041 max mem: 3972 +train: [2] [260/400] eta: 0:00:50 lr: 0.000159 loss: 3.1270 (3.1404) grad: 0.0721 (0.0748) time: 0.3600 data: 0.0040 max mem: 3972 +train: [2] [280/400] eta: 0:00:43 lr: 0.000162 loss: 3.1270 (3.1405) grad: 0.0721 (0.0750) time: 0.3430 data: 0.0042 max mem: 3972 +train: [2] [300/400] eta: 0:00:36 lr: 0.000165 loss: 3.1358 (3.1398) grad: 0.0707 (0.0748) time: 0.3504 data: 0.0043 max mem: 3972 +train: [2] [320/400] eta: 0:00:28 lr: 0.000168 loss: 3.1359 (3.1398) grad: 0.0739 (0.0748) time: 0.3676 data: 0.0044 max mem: 3972 +train: [2] [340/400] eta: 0:00:21 lr: 0.000171 loss: 3.1485 (3.1398) grad: 0.0739 (0.0748) time: 0.3314 data: 0.0043 max mem: 3972 +train: [2] [360/400] eta: 0:00:14 lr: 0.000174 loss: 3.1399 (3.1398) grad: 0.0723 (0.0748) time: 0.3493 data: 0.0043 max mem: 3972 +train: [2] [380/400] eta: 0:00:07 lr: 0.000177 loss: 3.1370 (3.1395) grad: 0.0714 (0.0748) time: 0.3473 data: 0.0041 max mem: 3972 +train: [2] [399/400] eta: 0:00:00 lr: 0.000180 loss: 3.1335 (3.1392) grad: 0.0714 (0.0748) time: 0.3441 data: 0.0039 max mem: 3972 +train: [2] Total time: 0:02:22 (0.3573 s / it) +train: [2] Summary: lr: 0.000180 loss: 3.1335 (3.1392) grad: 0.0714 (0.0748) +eval (validation): [2] [ 0/85] eta: 0:04:54 time: 3.4631 data: 3.2035 max mem: 3972 +eval (validation): [2] [20/85] eta: 0:00:33 time: 0.3681 data: 0.0046 max mem: 3972 +eval (validation): [2] [40/85] eta: 0:00:19 time: 0.3636 data: 0.0044 max mem: 3972 +eval (validation): [2] [60/85] eta: 0:00:10 time: 0.3674 data: 0.0043 max mem: 3972 +eval (validation): [2] [80/85] eta: 0:00:01 time: 0.3363 data: 0.0040 max mem: 3972 +eval (validation): [2] [84/85] eta: 0:00:00 time: 0.3203 data: 0.0040 max mem: 3972 +eval (validation): [2] Total time: 0:00:33 (0.3961 s / it) +cv: [2] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.174 acc: 0.076 f1: 0.029 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [3] [ 0/400] eta: 0:22:19 lr: nan time: 3.3477 data: 3.1392 max mem: 3972 +train: [3] [ 20/400] eta: 0:03:02 lr: 0.000183 loss: 3.1232 (3.1411) grad: 0.0700 (0.0727) time: 0.3360 data: 0.0043 max mem: 3972 +train: [3] [ 40/400] eta: 0:02:32 lr: 0.000186 loss: 3.1232 (3.1368) grad: 0.0753 (0.0748) time: 0.3645 data: 0.0036 max mem: 3972 +train: [3] [ 60/400] eta: 0:02:16 lr: 0.000189 loss: 3.1208 (3.1316) grad: 0.0751 (0.0749) time: 0.3581 data: 0.0041 max mem: 3972 +train: [3] [ 80/400] eta: 0:02:04 lr: 0.000192 loss: 3.1373 (3.1328) grad: 0.0750 (0.0751) time: 0.3480 data: 0.0040 max mem: 3972 +train: [3] [100/400] eta: 0:01:55 lr: 0.000195 loss: 3.1450 (3.1368) grad: 0.0781 (0.0755) time: 0.3663 data: 0.0041 max mem: 3972 +train: [3] [120/400] eta: 0:01:45 lr: 0.000198 loss: 3.1305 (3.1352) grad: 0.0790 (0.0760) time: 0.3499 data: 0.0042 max mem: 3972 +train: [3] [140/400] eta: 0:01:37 lr: 0.000201 loss: 3.1271 (3.1339) grad: 0.0772 (0.0767) time: 0.3629 data: 0.0042 max mem: 3972 +train: [3] [160/400] eta: 0:01:30 lr: 0.000204 loss: 3.1271 (3.1339) grad: 0.0772 (0.0765) time: 0.3669 data: 0.0040 max mem: 3972 +train: [3] [180/400] eta: 0:01:22 lr: 0.000207 loss: 3.1252 (3.1350) grad: 0.0706 (0.0761) time: 0.3567 data: 0.0040 max mem: 3972 +train: [3] [200/400] eta: 0:01:14 lr: 0.000210 loss: 3.1422 (3.1385) grad: 0.0706 (0.0757) time: 0.3426 data: 0.0039 max mem: 3972 +train: [3] [220/400] eta: 0:01:06 lr: 0.000213 loss: 3.1410 (3.1381) grad: 0.0719 (0.0755) time: 0.3434 data: 0.0037 max mem: 3972 +train: [3] [240/400] eta: 0:00:58 lr: 0.000216 loss: 3.1076 (3.1358) grad: 0.0719 (0.0753) time: 0.3408 data: 0.0038 max mem: 3972 +train: [3] [260/400] eta: 0:00:51 lr: 0.000219 loss: 3.1258 (3.1367) grad: 0.0736 (0.0753) time: 0.3538 data: 0.0042 max mem: 3972 +train: [3] [280/400] eta: 0:00:43 lr: 0.000222 loss: 3.1313 (3.1363) grad: 0.0716 (0.0748) time: 0.3664 data: 0.0040 max mem: 3972 +train: [3] [300/400] eta: 0:00:36 lr: 0.000225 loss: 3.1313 (3.1361) grad: 0.0670 (0.0745) time: 0.3455 data: 0.0041 max mem: 3972 +train: [3] [320/400] eta: 0:00:28 lr: 0.000228 loss: 3.1470 (3.1366) grad: 0.0672 (0.0744) time: 0.3363 data: 0.0041 max mem: 3972 +train: [3] [340/400] eta: 0:00:21 lr: 0.000231 loss: 3.1389 (3.1358) grad: 0.0718 (0.0743) time: 0.3516 data: 0.0043 max mem: 3972 +train: [3] [360/400] eta: 0:00:14 lr: 0.000234 loss: 3.1308 (3.1355) grad: 0.0728 (0.0742) time: 0.3470 data: 0.0039 max mem: 3972 +train: [3] [380/400] eta: 0:00:07 lr: 0.000237 loss: 3.1308 (3.1349) grad: 0.0720 (0.0741) time: 0.3413 data: 0.0043 max mem: 3972 +train: [3] [399/400] eta: 0:00:00 lr: 0.000240 loss: 3.1386 (3.1354) grad: 0.0707 (0.0740) time: 0.3488 data: 0.0041 max mem: 3972 +train: [3] Total time: 0:02:23 (0.3591 s / it) +train: [3] Summary: lr: 0.000240 loss: 3.1386 (3.1354) grad: 0.0707 (0.0740) +eval (validation): [3] [ 0/85] eta: 0:04:51 time: 3.4255 data: 3.2003 max mem: 3972 +eval (validation): [3] [20/85] eta: 0:00:33 time: 0.3648 data: 0.0349 max mem: 3972 +eval (validation): [3] [40/85] eta: 0:00:20 time: 0.3789 data: 0.0044 max mem: 3972 +eval (validation): [3] [60/85] eta: 0:00:10 time: 0.3493 data: 0.0042 max mem: 3972 +eval (validation): [3] [80/85] eta: 0:00:01 time: 0.3199 data: 0.0038 max mem: 3972 +eval (validation): [3] [84/85] eta: 0:00:00 time: 0.3055 data: 0.0036 max mem: 3972 +eval (validation): [3] Total time: 0:00:33 (0.3895 s / it) +cv: [3] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.174 acc: 0.073 f1: 0.027 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [4] [ 0/400] eta: 0:21:09 lr: nan time: 3.1745 data: 2.9707 max mem: 3972 +train: [4] [ 20/400] eta: 0:03:06 lr: 0.000243 loss: 3.1375 (3.1339) grad: 0.0712 (0.0712) time: 0.3554 data: 0.0044 max mem: 3972 +train: [4] [ 40/400] eta: 0:02:33 lr: 0.000246 loss: 3.1396 (3.1383) grad: 0.0671 (0.0688) time: 0.3614 data: 0.0043 max mem: 3972 +train: [4] [ 60/400] eta: 0:02:17 lr: 0.000249 loss: 3.1350 (3.1375) grad: 0.0671 (0.0699) time: 0.3555 data: 0.0041 max mem: 3972 +train: [4] [ 80/400] eta: 0:02:04 lr: 0.000252 loss: 3.1217 (3.1329) grad: 0.0710 (0.0709) time: 0.3502 data: 0.0038 max mem: 3972 +train: [4] [100/400] eta: 0:01:54 lr: 0.000255 loss: 3.1402 (3.1354) grad: 0.0730 (0.0715) time: 0.3436 data: 0.0042 max mem: 3972 +train: [4] [120/400] eta: 0:01:45 lr: 0.000258 loss: 3.1464 (3.1364) grad: 0.0720 (0.0720) time: 0.3478 data: 0.0041 max mem: 3972 +train: [4] [140/400] eta: 0:01:36 lr: 0.000261 loss: 3.1334 (3.1360) grad: 0.0746 (0.0733) time: 0.3424 data: 0.0040 max mem: 3972 +train: [4] [160/400] eta: 0:01:28 lr: 0.000264 loss: 3.1334 (3.1363) grad: 0.0742 (0.0729) time: 0.3589 data: 0.0039 max mem: 3972 +train: [4] [180/400] eta: 0:01:20 lr: 0.000267 loss: 3.1316 (3.1353) grad: 0.0708 (0.0727) time: 0.3582 data: 0.0042 max mem: 3972 +train: [4] [200/400] eta: 0:01:13 lr: 0.000270 loss: 3.1382 (3.1360) grad: 0.0734 (0.0732) time: 0.3553 data: 0.0043 max mem: 3972 +train: [4] [220/400] eta: 0:01:05 lr: 0.000273 loss: 3.1501 (3.1373) grad: 0.0755 (0.0734) time: 0.3532 data: 0.0040 max mem: 3972 +train: [4] [240/400] eta: 0:00:58 lr: 0.000276 loss: 3.1503 (3.1371) grad: 0.0756 (0.0737) time: 0.3280 data: 0.0040 max mem: 3972 +train: [4] [260/400] eta: 0:00:50 lr: 0.000279 loss: 3.1096 (3.1352) grad: 0.0760 (0.0739) time: 0.3635 data: 0.0041 max mem: 3972 +train: [4] [280/400] eta: 0:00:43 lr: 0.000282 loss: 3.1104 (3.1349) grad: 0.0749 (0.0742) time: 0.3533 data: 0.0040 max mem: 3972 +train: [4] [300/400] eta: 0:00:36 lr: 0.000285 loss: 3.1339 (3.1340) grad: 0.0743 (0.0743) time: 0.3422 data: 0.0039 max mem: 3972 +train: [4] [320/400] eta: 0:00:28 lr: 0.000288 loss: 3.1377 (3.1349) grad: 0.0709 (0.0744) time: 0.3511 data: 0.0036 max mem: 3972 +train: [4] [340/400] eta: 0:00:21 lr: 0.000291 loss: 3.1479 (3.1352) grad: 0.0757 (0.0746) time: 0.3541 data: 0.0040 max mem: 3972 +train: [4] [360/400] eta: 0:00:14 lr: 0.000294 loss: 3.1345 (3.1351) grad: 0.0750 (0.0745) time: 0.3495 data: 0.0038 max mem: 3972 +train: [4] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1345 (3.1349) grad: 0.0750 (0.0746) time: 0.3394 data: 0.0042 max mem: 3972 +train: [4] [399/400] eta: 0:00:00 lr: 0.000300 loss: 3.1249 (3.1348) grad: 0.0730 (0.0744) time: 0.3483 data: 0.0041 max mem: 3972 +train: [4] Total time: 0:02:23 (0.3579 s / it) +train: [4] Summary: lr: 0.000300 loss: 3.1249 (3.1348) grad: 0.0730 (0.0744) +eval (validation): [4] [ 0/85] eta: 0:04:53 time: 3.4548 data: 3.2293 max mem: 3972 +eval (validation): [4] [20/85] eta: 0:00:31 time: 0.3322 data: 0.0039 max mem: 3972 +eval (validation): [4] [40/85] eta: 0:00:19 time: 0.3768 data: 0.0050 max mem: 3972 +eval (validation): [4] [60/85] eta: 0:00:10 time: 0.3895 data: 0.0048 max mem: 3972 +eval (validation): [4] [80/85] eta: 0:00:01 time: 0.3193 data: 0.0036 max mem: 3972 +eval (validation): [4] [84/85] eta: 0:00:00 time: 0.3014 data: 0.0035 max mem: 3972 +eval (validation): [4] Total time: 0:00:33 (0.3920 s / it) +cv: [4] best hparam: (5.1, 1.0) (034) ('034_lr5.1e+00_wd1.0e+00') loss: 3.132 acc: 0.074 f1: 0.019 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [5] [ 0/400] eta: 0:22:14 lr: nan time: 3.3361 data: 3.0659 max mem: 3972 +train: [5] [ 20/400] eta: 0:03:28 lr: 0.000300 loss: 3.1243 (3.1282) grad: 0.0713 (0.0727) time: 0.4090 data: 0.0056 max mem: 3972 +train: [5] [ 40/400] eta: 0:02:44 lr: 0.000300 loss: 3.1196 (3.1182) grad: 0.0713 (0.0728) time: 0.3594 data: 0.0036 max mem: 3972 +train: [5] [ 60/400] eta: 0:02:22 lr: 0.000300 loss: 3.1215 (3.1235) grad: 0.0716 (0.0737) time: 0.3426 data: 0.0044 max mem: 3972 +train: [5] [ 80/400] eta: 0:02:07 lr: 0.000300 loss: 3.1319 (3.1265) grad: 0.0716 (0.0733) time: 0.3310 data: 0.0044 max mem: 3972 +train: [5] [100/400] eta: 0:01:55 lr: 0.000300 loss: 3.1497 (3.1297) grad: 0.0749 (0.0750) time: 0.3380 data: 0.0040 max mem: 3972 +train: [5] [120/400] eta: 0:01:46 lr: 0.000300 loss: 3.1317 (3.1303) grad: 0.0788 (0.0757) time: 0.3625 data: 0.0042 max mem: 3972 +train: [5] [140/400] eta: 0:01:37 lr: 0.000300 loss: 3.1301 (3.1308) grad: 0.0774 (0.0754) time: 0.3421 data: 0.0044 max mem: 3972 +train: [5] [160/400] eta: 0:01:29 lr: 0.000299 loss: 3.1358 (3.1299) grad: 0.0732 (0.0750) time: 0.3358 data: 0.0039 max mem: 3972 +train: [5] [180/400] eta: 0:01:21 lr: 0.000299 loss: 3.1101 (3.1274) grad: 0.0721 (0.0748) time: 0.3459 data: 0.0041 max mem: 3972 +train: [5] [200/400] eta: 0:01:13 lr: 0.000299 loss: 3.1241 (3.1272) grad: 0.0715 (0.0744) time: 0.3630 data: 0.0040 max mem: 3972 +train: [5] [220/400] eta: 0:01:05 lr: 0.000299 loss: 3.1414 (3.1296) grad: 0.0709 (0.0747) time: 0.3470 data: 0.0040 max mem: 3972 +train: [5] [240/400] eta: 0:00:58 lr: 0.000299 loss: 3.1400 (3.1299) grad: 0.0731 (0.0748) time: 0.3384 data: 0.0038 max mem: 3972 +train: [5] [260/400] eta: 0:00:51 lr: 0.000299 loss: 3.1405 (3.1315) grad: 0.0713 (0.0747) time: 0.3820 data: 0.0042 max mem: 3972 +train: [5] [280/400] eta: 0:00:43 lr: 0.000298 loss: 3.1395 (3.1312) grad: 0.0762 (0.0749) time: 0.3598 data: 0.0042 max mem: 3972 +train: [5] [300/400] eta: 0:00:36 lr: 0.000298 loss: 3.1219 (3.1310) grad: 0.0765 (0.0750) time: 0.3783 data: 0.0044 max mem: 3972 +train: [5] [320/400] eta: 0:00:29 lr: 0.000298 loss: 3.1243 (3.1310) grad: 0.0746 (0.0750) time: 0.3380 data: 0.0041 max mem: 3972 +train: [5] [340/400] eta: 0:00:21 lr: 0.000298 loss: 3.1310 (3.1310) grad: 0.0712 (0.0749) time: 0.3382 data: 0.0037 max mem: 3972 +train: [5] [360/400] eta: 0:00:14 lr: 0.000297 loss: 3.1310 (3.1310) grad: 0.0697 (0.0747) time: 0.3429 data: 0.0036 max mem: 3972 +train: [5] [380/400] eta: 0:00:07 lr: 0.000297 loss: 3.1320 (3.1306) grad: 0.0710 (0.0747) time: 0.3449 data: 0.0039 max mem: 3972 +train: [5] [399/400] eta: 0:00:00 lr: 0.000297 loss: 3.1320 (3.1309) grad: 0.0709 (0.0746) time: 0.3399 data: 0.0038 max mem: 3972 +train: [5] Total time: 0:02:23 (0.3597 s / it) +train: [5] Summary: lr: 0.000297 loss: 3.1320 (3.1309) grad: 0.0709 (0.0746) +eval (validation): [5] [ 0/85] eta: 0:04:44 time: 3.3433 data: 3.1202 max mem: 3972 +eval (validation): [5] [20/85] eta: 0:00:32 time: 0.3632 data: 0.0107 max mem: 3972 +eval (validation): [5] [40/85] eta: 0:00:19 time: 0.3740 data: 0.0044 max mem: 3972 +eval (validation): [5] [60/85] eta: 0:00:10 time: 0.3366 data: 0.0040 max mem: 3972 +eval (validation): [5] [80/85] eta: 0:00:01 time: 0.3057 data: 0.0039 max mem: 3972 +eval (validation): [5] [84/85] eta: 0:00:00 time: 0.3021 data: 0.0037 max mem: 3972 +eval (validation): [5] Total time: 0:00:32 (0.3817 s / it) +cv: [5] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.236 acc: 0.081 f1: 0.028 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [6] [ 0/400] eta: 0:22:08 lr: nan time: 3.3221 data: 3.1074 max mem: 3972 +train: [6] [ 20/400] eta: 0:03:04 lr: 0.000296 loss: 3.1213 (3.1220) grad: 0.0675 (0.0675) time: 0.3428 data: 0.0051 max mem: 3972 +train: [6] [ 40/400] eta: 0:02:32 lr: 0.000296 loss: 3.1216 (3.1267) grad: 0.0703 (0.0709) time: 0.3595 data: 0.0033 max mem: 3972 +train: [6] [ 60/400] eta: 0:02:16 lr: 0.000296 loss: 3.1282 (3.1282) grad: 0.0749 (0.0721) time: 0.3565 data: 0.0041 max mem: 3972 +train: [6] [ 80/400] eta: 0:02:04 lr: 0.000295 loss: 3.1258 (3.1263) grad: 0.0716 (0.0725) time: 0.3541 data: 0.0040 max mem: 3972 +train: [6] [100/400] eta: 0:01:54 lr: 0.000295 loss: 3.1348 (3.1315) grad: 0.0704 (0.0720) time: 0.3454 data: 0.0044 max mem: 3972 +train: [6] [120/400] eta: 0:01:44 lr: 0.000295 loss: 3.1289 (3.1275) grad: 0.0704 (0.0721) time: 0.3390 data: 0.0043 max mem: 3972 +train: [6] [140/400] eta: 0:01:36 lr: 0.000294 loss: 3.1026 (3.1249) grad: 0.0749 (0.0725) time: 0.3425 data: 0.0043 max mem: 3972 +train: [6] [160/400] eta: 0:01:28 lr: 0.000294 loss: 3.1071 (3.1250) grad: 0.0760 (0.0733) time: 0.3568 data: 0.0041 max mem: 3972 +train: [6] [180/400] eta: 0:01:20 lr: 0.000293 loss: 3.1303 (3.1256) grad: 0.0767 (0.0738) time: 0.3675 data: 0.0041 max mem: 3972 +train: [6] [200/400] eta: 0:01:13 lr: 0.000293 loss: 3.1374 (3.1252) grad: 0.0694 (0.0733) time: 0.3509 data: 0.0042 max mem: 3972 +train: [6] [220/400] eta: 0:01:05 lr: 0.000292 loss: 3.1103 (3.1244) grad: 0.0712 (0.0735) time: 0.3435 data: 0.0042 max mem: 3972 +train: [6] [240/400] eta: 0:00:57 lr: 0.000292 loss: 3.1021 (3.1229) grad: 0.0712 (0.0733) time: 0.3298 data: 0.0040 max mem: 3972 +train: [6] [260/400] eta: 0:00:50 lr: 0.000291 loss: 3.1057 (3.1222) grad: 0.0707 (0.0733) time: 0.3508 data: 0.0039 max mem: 3972 +train: [6] [280/400] eta: 0:00:43 lr: 0.000291 loss: 3.1200 (3.1227) grad: 0.0736 (0.0736) time: 0.3425 data: 0.0039 max mem: 3972 +train: [6] [300/400] eta: 0:00:35 lr: 0.000290 loss: 3.1327 (3.1225) grad: 0.0736 (0.0734) time: 0.3433 data: 0.0039 max mem: 3972 +train: [6] [320/400] eta: 0:00:28 lr: 0.000290 loss: 3.1301 (3.1232) grad: 0.0697 (0.0734) time: 0.3503 data: 0.0040 max mem: 3972 +train: [6] [340/400] eta: 0:00:21 lr: 0.000289 loss: 3.1319 (3.1233) grad: 0.0752 (0.0734) time: 0.3450 data: 0.0041 max mem: 3972 +train: [6] [360/400] eta: 0:00:14 lr: 0.000288 loss: 3.1221 (3.1223) grad: 0.0728 (0.0733) time: 0.3456 data: 0.0041 max mem: 3972 +train: [6] [380/400] eta: 0:00:07 lr: 0.000288 loss: 3.1221 (3.1227) grad: 0.0732 (0.0735) time: 0.3426 data: 0.0044 max mem: 3972 +train: [6] [399/400] eta: 0:00:00 lr: 0.000287 loss: 3.1271 (3.1229) grad: 0.0742 (0.0735) time: 0.3565 data: 0.0041 max mem: 3972 +train: [6] Total time: 0:02:22 (0.3559 s / it) +train: [6] Summary: lr: 0.000287 loss: 3.1271 (3.1229) grad: 0.0742 (0.0735) +eval (validation): [6] [ 0/85] eta: 0:04:44 time: 3.3458 data: 3.1251 max mem: 3972 +eval (validation): [6] [20/85] eta: 0:00:31 time: 0.3342 data: 0.0044 max mem: 3972 +eval (validation): [6] [40/85] eta: 0:00:18 time: 0.3359 data: 0.0038 max mem: 3972 +eval (validation): [6] [60/85] eta: 0:00:09 time: 0.3405 data: 0.0053 max mem: 3972 +eval (validation): [6] [80/85] eta: 0:00:01 time: 0.3041 data: 0.0031 max mem: 3972 +eval (validation): [6] [84/85] eta: 0:00:00 time: 0.3059 data: 0.0036 max mem: 3972 +eval (validation): [6] Total time: 0:00:31 (0.3670 s / it) +cv: [6] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.151 acc: 0.078 f1: 0.030 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [7] [ 0/400] eta: 0:22:42 lr: nan time: 3.4055 data: 3.1848 max mem: 3972 +train: [7] [ 20/400] eta: 0:03:05 lr: 0.000286 loss: 3.0984 (3.1053) grad: 0.0747 (0.0745) time: 0.3429 data: 0.0127 max mem: 3972 +train: [7] [ 40/400] eta: 0:02:28 lr: 0.000286 loss: 3.1165 (3.1142) grad: 0.0738 (0.0740) time: 0.3325 data: 0.0039 max mem: 3972 +train: [7] [ 60/400] eta: 0:02:13 lr: 0.000285 loss: 3.1213 (3.1177) grad: 0.0722 (0.0729) time: 0.3478 data: 0.0035 max mem: 3972 +train: [7] [ 80/400] eta: 0:02:02 lr: 0.000284 loss: 3.1275 (3.1166) grad: 0.0728 (0.0740) time: 0.3539 data: 0.0040 max mem: 3972 +train: [7] [100/400] eta: 0:01:52 lr: 0.000284 loss: 3.1275 (3.1196) grad: 0.0705 (0.0734) time: 0.3472 data: 0.0042 max mem: 3972 +train: [7] [120/400] eta: 0:01:43 lr: 0.000283 loss: 3.1021 (3.1143) grad: 0.0697 (0.0729) time: 0.3485 data: 0.0043 max mem: 3972 +train: [7] [140/400] eta: 0:01:35 lr: 0.000282 loss: 3.0852 (3.1125) grad: 0.0697 (0.0733) time: 0.3511 data: 0.0042 max mem: 3972 +train: [7] [160/400] eta: 0:01:27 lr: 0.000282 loss: 3.1079 (3.1147) grad: 0.0774 (0.0738) time: 0.3408 data: 0.0039 max mem: 3972 +train: [7] [180/400] eta: 0:01:20 lr: 0.000281 loss: 3.1138 (3.1149) grad: 0.0730 (0.0735) time: 0.3606 data: 0.0043 max mem: 3972 +train: [7] [200/400] eta: 0:01:12 lr: 0.000280 loss: 3.1017 (3.1135) grad: 0.0692 (0.0734) time: 0.3489 data: 0.0044 max mem: 3972 +train: [7] [220/400] eta: 0:01:05 lr: 0.000279 loss: 3.1180 (3.1153) grad: 0.0716 (0.0736) time: 0.3464 data: 0.0037 max mem: 3972 +train: [7] [240/400] eta: 0:00:57 lr: 0.000278 loss: 3.1222 (3.1157) grad: 0.0759 (0.0739) time: 0.3351 data: 0.0040 max mem: 3972 +train: [7] [260/400] eta: 0:00:50 lr: 0.000278 loss: 3.1270 (3.1172) grad: 0.0796 (0.0742) time: 0.3382 data: 0.0039 max mem: 3972 +train: [7] [280/400] eta: 0:00:42 lr: 0.000277 loss: 3.1270 (3.1162) grad: 0.0769 (0.0742) time: 0.3538 data: 0.0042 max mem: 3972 +train: [7] [300/400] eta: 0:00:35 lr: 0.000276 loss: 3.1103 (3.1159) grad: 0.0719 (0.0740) time: 0.3443 data: 0.0041 max mem: 3972 +train: [7] [320/400] eta: 0:00:28 lr: 0.000275 loss: 3.1194 (3.1172) grad: 0.0723 (0.0739) time: 0.3596 data: 0.0043 max mem: 3972 +train: [7] [340/400] eta: 0:00:21 lr: 0.000274 loss: 3.1367 (3.1180) grad: 0.0746 (0.0741) time: 0.3327 data: 0.0041 max mem: 3972 +train: [7] [360/400] eta: 0:00:14 lr: 0.000273 loss: 3.1293 (3.1187) grad: 0.0736 (0.0740) time: 0.3464 data: 0.0040 max mem: 3972 +train: [7] [380/400] eta: 0:00:07 lr: 0.000272 loss: 3.1404 (3.1201) grad: 0.0721 (0.0741) time: 0.3629 data: 0.0043 max mem: 3972 +train: [7] [399/400] eta: 0:00:00 lr: 0.000271 loss: 3.1282 (3.1197) grad: 0.0750 (0.0742) time: 0.3495 data: 0.0042 max mem: 3972 +train: [7] Total time: 0:02:22 (0.3551 s / it) +train: [7] Summary: lr: 0.000271 loss: 3.1282 (3.1197) grad: 0.0750 (0.0742) +eval (validation): [7] [ 0/85] eta: 0:04:50 time: 3.4176 data: 3.1369 max mem: 3972 +eval (validation): [7] [20/85] eta: 0:00:34 time: 0.3843 data: 0.0051 max mem: 3972 +eval (validation): [7] [40/85] eta: 0:00:20 time: 0.3693 data: 0.0043 max mem: 3972 +eval (validation): [7] [60/85] eta: 0:00:10 time: 0.3121 data: 0.0045 max mem: 3972 +eval (validation): [7] [80/85] eta: 0:00:01 time: 0.3235 data: 0.0037 max mem: 3972 +eval (validation): [7] [84/85] eta: 0:00:00 time: 0.3240 data: 0.0040 max mem: 3972 +eval (validation): [7] Total time: 0:00:32 (0.3857 s / it) +cv: [7] best hparam: (6, 1.0) (035) ('035_lr6.0e+00_wd1.0e+00') loss: 3.119 acc: 0.085 f1: 0.028 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [8] [ 0/400] eta: 0:23:07 lr: nan time: 3.4690 data: 3.2352 max mem: 3972 +train: [8] [ 20/400] eta: 0:03:09 lr: 0.000270 loss: 3.1035 (3.1174) grad: 0.0680 (0.0678) time: 0.3500 data: 0.0053 max mem: 3972 +train: [8] [ 40/400] eta: 0:02:32 lr: 0.000270 loss: 3.1210 (3.1186) grad: 0.0720 (0.0739) time: 0.3423 data: 0.0037 max mem: 3972 +train: [8] [ 60/400] eta: 0:02:15 lr: 0.000269 loss: 3.1078 (3.1101) grad: 0.0761 (0.0746) time: 0.3457 data: 0.0044 max mem: 3972 +train: [8] [ 80/400] eta: 0:02:02 lr: 0.000268 loss: 3.1019 (3.1087) grad: 0.0768 (0.0755) time: 0.3452 data: 0.0043 max mem: 3972 +train: [8] [100/400] eta: 0:01:53 lr: 0.000267 loss: 3.1108 (3.1129) grad: 0.0734 (0.0748) time: 0.3475 data: 0.0042 max mem: 3972 +train: [8] [120/400] eta: 0:01:43 lr: 0.000266 loss: 3.1172 (3.1118) grad: 0.0700 (0.0744) time: 0.3389 data: 0.0043 max mem: 3972 +train: [8] [140/400] eta: 0:01:35 lr: 0.000265 loss: 3.1179 (3.1130) grad: 0.0716 (0.0743) time: 0.3506 data: 0.0037 max mem: 3972 +train: [8] [160/400] eta: 0:01:27 lr: 0.000264 loss: 3.1252 (3.1137) grad: 0.0769 (0.0747) time: 0.3357 data: 0.0043 max mem: 3972 +train: [8] [180/400] eta: 0:01:19 lr: 0.000263 loss: 3.1090 (3.1140) grad: 0.0769 (0.0747) time: 0.3487 data: 0.0038 max mem: 3972 +train: [8] [200/400] eta: 0:01:12 lr: 0.000262 loss: 3.1090 (3.1131) grad: 0.0760 (0.0746) time: 0.3442 data: 0.0042 max mem: 3972 +train: [8] [220/400] eta: 0:01:05 lr: 0.000260 loss: 3.1075 (3.1128) grad: 0.0760 (0.0747) time: 0.3731 data: 0.0040 max mem: 3972 +train: [8] [240/400] eta: 0:00:57 lr: 0.000259 loss: 3.0977 (3.1127) grad: 0.0708 (0.0744) time: 0.3379 data: 0.0042 max mem: 3972 +train: [8] [260/400] eta: 0:00:50 lr: 0.000258 loss: 3.1112 (3.1135) grad: 0.0737 (0.0750) time: 0.3369 data: 0.0042 max mem: 3972 +train: [8] [280/400] eta: 0:00:42 lr: 0.000257 loss: 3.1269 (3.1149) grad: 0.0754 (0.0747) time: 0.3470 data: 0.0041 max mem: 3972 +train: [8] [300/400] eta: 0:00:36 lr: 0.000256 loss: 3.1090 (3.1137) grad: 0.0758 (0.0749) time: 0.4050 data: 0.0050 max mem: 3972 +train: [8] [320/400] eta: 0:00:28 lr: 0.000255 loss: 3.0848 (3.1141) grad: 0.0758 (0.0747) time: 0.3530 data: 0.0044 max mem: 3972 +train: [8] [340/400] eta: 0:00:21 lr: 0.000254 loss: 3.1238 (3.1146) grad: 0.0739 (0.0747) time: 0.3279 data: 0.0037 max mem: 3972 +train: [8] [360/400] eta: 0:00:14 lr: 0.000253 loss: 3.1258 (3.1155) grad: 0.0742 (0.0748) time: 0.3374 data: 0.0041 max mem: 3972 +train: [8] [380/400] eta: 0:00:07 lr: 0.000252 loss: 3.1274 (3.1157) grad: 0.0727 (0.0747) time: 0.3533 data: 0.0041 max mem: 3972 +train: [8] [399/400] eta: 0:00:00 lr: 0.000250 loss: 3.1158 (3.1158) grad: 0.0726 (0.0746) time: 0.3499 data: 0.0044 max mem: 3972 +train: [8] Total time: 0:02:22 (0.3566 s / it) +train: [8] Summary: lr: 0.000250 loss: 3.1158 (3.1158) grad: 0.0726 (0.0746) +eval (validation): [8] [ 0/85] eta: 0:05:04 time: 3.5788 data: 3.3077 max mem: 3972 +eval (validation): [8] [20/85] eta: 0:00:35 time: 0.3904 data: 0.0151 max mem: 3972 +eval (validation): [8] [40/85] eta: 0:00:19 time: 0.3157 data: 0.0040 max mem: 3972 +eval (validation): [8] [60/85] eta: 0:00:10 time: 0.3420 data: 0.0045 max mem: 3972 +eval (validation): [8] [80/85] eta: 0:00:01 time: 0.3386 data: 0.0042 max mem: 3972 +eval (validation): [8] [84/85] eta: 0:00:00 time: 0.3202 data: 0.0041 max mem: 3972 +eval (validation): [8] Total time: 0:00:32 (0.3861 s / it) +cv: [8] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.121 acc: 0.086 f1: 0.044 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [9] [ 0/400] eta: 0:23:19 lr: nan time: 3.4976 data: 3.2291 max mem: 3972 +train: [9] [ 20/400] eta: 0:03:16 lr: 0.000249 loss: 3.0671 (3.0946) grad: 0.0732 (0.0761) time: 0.3684 data: 0.0132 max mem: 3972 +train: [9] [ 40/400] eta: 0:02:33 lr: 0.000248 loss: 3.0959 (3.0967) grad: 0.0732 (0.0744) time: 0.3313 data: 0.0031 max mem: 3972 +train: [9] [ 60/400] eta: 0:02:17 lr: 0.000247 loss: 3.1027 (3.1024) grad: 0.0724 (0.0738) time: 0.3581 data: 0.0043 max mem: 3972 +train: [9] [ 80/400] eta: 0:02:05 lr: 0.000246 loss: 3.1141 (3.1052) grad: 0.0706 (0.0730) time: 0.3511 data: 0.0042 max mem: 3972 +train: [9] [100/400] eta: 0:01:55 lr: 0.000244 loss: 3.1011 (3.1037) grad: 0.0705 (0.0730) time: 0.3553 data: 0.0041 max mem: 3972 +train: [9] [120/400] eta: 0:01:45 lr: 0.000243 loss: 3.1011 (3.1047) grad: 0.0693 (0.0722) time: 0.3387 data: 0.0040 max mem: 3972 +train: [9] [140/400] eta: 0:01:36 lr: 0.000242 loss: 3.1128 (3.1049) grad: 0.0693 (0.0719) time: 0.3316 data: 0.0039 max mem: 3972 +train: [9] [160/400] eta: 0:01:27 lr: 0.000241 loss: 3.0974 (3.1044) grad: 0.0700 (0.0719) time: 0.3319 data: 0.0039 max mem: 3972 +train: [9] [180/400] eta: 0:01:19 lr: 0.000240 loss: 3.0916 (3.1049) grad: 0.0744 (0.0726) time: 0.3353 data: 0.0040 max mem: 3972 +train: [9] [200/400] eta: 0:01:11 lr: 0.000238 loss: 3.1022 (3.1071) grad: 0.0763 (0.0731) time: 0.3319 data: 0.0042 max mem: 3972 +train: [9] [220/400] eta: 0:01:04 lr: 0.000237 loss: 3.1190 (3.1072) grad: 0.0763 (0.0735) time: 0.3346 data: 0.0037 max mem: 3972 +train: [9] [240/400] eta: 0:00:56 lr: 0.000236 loss: 3.1210 (3.1092) grad: 0.0719 (0.0733) time: 0.3266 data: 0.0040 max mem: 3972 +train: [9] [260/400] eta: 0:00:49 lr: 0.000234 loss: 3.1100 (3.1078) grad: 0.0701 (0.0731) time: 0.3186 data: 0.0036 max mem: 3972 +train: [9] [280/400] eta: 0:00:42 lr: 0.000233 loss: 3.0903 (3.1077) grad: 0.0676 (0.0726) time: 0.3377 data: 0.0039 max mem: 3972 +train: [9] [300/400] eta: 0:00:35 lr: 0.000232 loss: 3.1174 (3.1091) grad: 0.0656 (0.0722) time: 0.3465 data: 0.0040 max mem: 3972 +train: [9] [320/400] eta: 0:00:28 lr: 0.000230 loss: 3.1082 (3.1085) grad: 0.0656 (0.0723) time: 0.3499 data: 0.0041 max mem: 3972 +train: [9] [340/400] eta: 0:00:20 lr: 0.000229 loss: 3.1077 (3.1099) grad: 0.0716 (0.0722) time: 0.3442 data: 0.0044 max mem: 3972 +train: [9] [360/400] eta: 0:00:13 lr: 0.000228 loss: 3.1146 (3.1099) grad: 0.0716 (0.0721) time: 0.3423 data: 0.0044 max mem: 3972 +train: [9] [380/400] eta: 0:00:06 lr: 0.000226 loss: 3.0966 (3.1102) grad: 0.0690 (0.0720) time: 0.3312 data: 0.0041 max mem: 3972 +train: [9] [399/400] eta: 0:00:00 lr: 0.000225 loss: 3.1209 (3.1106) grad: 0.0679 (0.0718) time: 0.3511 data: 0.0043 max mem: 3972 +train: [9] Total time: 0:02:19 (0.3490 s / it) +train: [9] Summary: lr: 0.000225 loss: 3.1209 (3.1106) grad: 0.0679 (0.0718) +eval (validation): [9] [ 0/85] eta: 0:04:47 time: 3.3841 data: 3.1686 max mem: 3972 +eval (validation): [9] [20/85] eta: 0:00:33 time: 0.3731 data: 0.0074 max mem: 3972 +eval (validation): [9] [40/85] eta: 0:00:19 time: 0.3309 data: 0.0036 max mem: 3972 +eval (validation): [9] [60/85] eta: 0:00:09 time: 0.3018 data: 0.0041 max mem: 3972 +eval (validation): [9] [80/85] eta: 0:00:01 time: 0.3213 data: 0.0040 max mem: 3972 +eval (validation): [9] [84/85] eta: 0:00:00 time: 0.3109 data: 0.0038 max mem: 3972 +eval (validation): [9] Total time: 0:00:31 (0.3702 s / it) +cv: [9] best hparam: (9.8, 1.0) (038) ('038_lr9.8e+00_wd1.0e+00') loss: 3.105 acc: 0.087 f1: 0.046 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [10] [ 0/400] eta: 0:22:17 lr: nan time: 3.3434 data: 3.1276 max mem: 3972 +train: [10] [ 20/400] eta: 0:03:10 lr: 0.000224 loss: 3.1091 (3.1175) grad: 0.0657 (0.0709) time: 0.3593 data: 0.0292 max mem: 3972 +train: [10] [ 40/400] eta: 0:02:31 lr: 0.000222 loss: 3.1035 (3.1095) grad: 0.0707 (0.0717) time: 0.3366 data: 0.0039 max mem: 3972 +train: [10] [ 60/400] eta: 0:02:13 lr: 0.000221 loss: 3.1070 (3.1158) grad: 0.0676 (0.0707) time: 0.3302 data: 0.0040 max mem: 3972 +train: [10] [ 80/400] eta: 0:02:01 lr: 0.000220 loss: 3.0956 (3.1104) grad: 0.0676 (0.0708) time: 0.3445 data: 0.0043 max mem: 3972 +train: [10] [100/400] eta: 0:01:51 lr: 0.000218 loss: 3.1037 (3.1116) grad: 0.0697 (0.0710) time: 0.3427 data: 0.0038 max mem: 3972 +train: [10] [120/400] eta: 0:01:43 lr: 0.000217 loss: 3.1074 (3.1080) grad: 0.0726 (0.0718) time: 0.3507 data: 0.0042 max mem: 3972 +train: [10] [140/400] eta: 0:01:35 lr: 0.000215 loss: 3.0803 (3.1053) grad: 0.0741 (0.0720) time: 0.3547 data: 0.0041 max mem: 3972 +train: [10] [160/400] eta: 0:01:27 lr: 0.000214 loss: 3.0741 (3.1049) grad: 0.0736 (0.0721) time: 0.3336 data: 0.0042 max mem: 3972 +train: [10] [180/400] eta: 0:01:19 lr: 0.000213 loss: 3.1121 (3.1071) grad: 0.0727 (0.0725) time: 0.3395 data: 0.0041 max mem: 3972 +train: [10] [200/400] eta: 0:01:11 lr: 0.000211 loss: 3.1121 (3.1064) grad: 0.0687 (0.0718) time: 0.3325 data: 0.0039 max mem: 3972 +train: [10] [220/400] eta: 0:01:03 lr: 0.000210 loss: 3.1078 (3.1073) grad: 0.0684 (0.0716) time: 0.3249 data: 0.0039 max mem: 3972 +train: [10] [240/400] eta: 0:00:57 lr: 0.000208 loss: 3.0997 (3.1062) grad: 0.0685 (0.0713) time: 0.3858 data: 0.0041 max mem: 3972 +train: [10] [260/400] eta: 0:00:49 lr: 0.000207 loss: 3.0918 (3.1054) grad: 0.0694 (0.0715) time: 0.3479 data: 0.0040 max mem: 3972 +train: [10] [280/400] eta: 0:00:42 lr: 0.000205 loss: 3.0997 (3.1051) grad: 0.0754 (0.0718) time: 0.3593 data: 0.0043 max mem: 3972 +train: [10] [300/400] eta: 0:00:35 lr: 0.000204 loss: 3.1231 (3.1066) grad: 0.0779 (0.0723) time: 0.3296 data: 0.0042 max mem: 3972 +train: [10] [320/400] eta: 0:00:28 lr: 0.000202 loss: 3.1360 (3.1078) grad: 0.0786 (0.0726) time: 0.3511 data: 0.0043 max mem: 3972 +train: [10] [340/400] eta: 0:00:21 lr: 0.000201 loss: 3.1005 (3.1075) grad: 0.0735 (0.0726) time: 0.3268 data: 0.0041 max mem: 3972 +train: [10] [360/400] eta: 0:00:14 lr: 0.000199 loss: 3.0975 (3.1070) grad: 0.0747 (0.0727) time: 0.3316 data: 0.0037 max mem: 3972 +train: [10] [380/400] eta: 0:00:07 lr: 0.000198 loss: 3.1090 (3.1070) grad: 0.0759 (0.0729) time: 0.3363 data: 0.0038 max mem: 3972 +train: [10] [399/400] eta: 0:00:00 lr: 0.000196 loss: 3.1090 (3.1070) grad: 0.0730 (0.0729) time: 0.3667 data: 0.0042 max mem: 3972 +train: [10] Total time: 0:02:20 (0.3519 s / it) +train: [10] Summary: lr: 0.000196 loss: 3.1090 (3.1070) grad: 0.0730 (0.0729) +eval (validation): [10] [ 0/85] eta: 0:05:55 time: 4.1807 data: 3.9535 max mem: 3972 +eval (validation): [10] [20/85] eta: 0:00:34 time: 0.3527 data: 0.0186 max mem: 3972 +eval (validation): [10] [40/85] eta: 0:00:19 time: 0.3143 data: 0.0035 max mem: 3972 +eval (validation): [10] [60/85] eta: 0:00:10 time: 0.3481 data: 0.0045 max mem: 3972 +eval (validation): [10] [80/85] eta: 0:00:01 time: 0.3450 data: 0.0046 max mem: 3972 +eval (validation): [10] [84/85] eta: 0:00:00 time: 0.3225 data: 0.0046 max mem: 3972 +eval (validation): [10] Total time: 0:00:32 (0.3870 s / it) +cv: [10] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.115 acc: 0.083 f1: 0.044 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [11] [ 0/400] eta: 0:22:09 lr: nan time: 3.3241 data: 3.1098 max mem: 3972 +train: [11] [ 20/400] eta: 0:03:00 lr: 0.000195 loss: 3.0982 (3.0968) grad: 0.0668 (0.0684) time: 0.3315 data: 0.0053 max mem: 3972 +train: [11] [ 40/400] eta: 0:02:30 lr: 0.000193 loss: 3.0885 (3.1012) grad: 0.0687 (0.0706) time: 0.3590 data: 0.0038 max mem: 3972 +train: [11] [ 60/400] eta: 0:02:11 lr: 0.000192 loss: 3.0885 (3.0961) grad: 0.0706 (0.0712) time: 0.3202 data: 0.0034 max mem: 3972 +train: [11] [ 80/400] eta: 0:01:58 lr: 0.000190 loss: 3.1073 (3.0977) grad: 0.0706 (0.0712) time: 0.3220 data: 0.0039 max mem: 3972 +train: [11] [100/400] eta: 0:01:49 lr: 0.000189 loss: 3.1044 (3.0980) grad: 0.0690 (0.0709) time: 0.3518 data: 0.0041 max mem: 3972 +train: [11] [120/400] eta: 0:01:41 lr: 0.000187 loss: 3.1095 (3.1014) grad: 0.0686 (0.0708) time: 0.3453 data: 0.0042 max mem: 3972 +train: [11] [140/400] eta: 0:01:33 lr: 0.000186 loss: 3.1048 (3.1010) grad: 0.0704 (0.0711) time: 0.3390 data: 0.0042 max mem: 3972 +train: [11] [160/400] eta: 0:01:25 lr: 0.000184 loss: 3.1035 (3.1018) grad: 0.0712 (0.0710) time: 0.3261 data: 0.0041 max mem: 3972 +train: [11] [180/400] eta: 0:01:17 lr: 0.000183 loss: 3.1042 (3.1026) grad: 0.0699 (0.0710) time: 0.3455 data: 0.0041 max mem: 3972 +train: [11] [200/400] eta: 0:01:10 lr: 0.000181 loss: 3.1164 (3.1057) grad: 0.0674 (0.0708) time: 0.3601 data: 0.0043 max mem: 3972 +train: [11] [220/400] eta: 0:01:03 lr: 0.000180 loss: 3.1277 (3.1051) grad: 0.0677 (0.0704) time: 0.3536 data: 0.0041 max mem: 3972 +train: [11] [240/400] eta: 0:00:56 lr: 0.000178 loss: 3.1079 (3.1054) grad: 0.0685 (0.0707) time: 0.3185 data: 0.0039 max mem: 3972 +train: [11] [260/400] eta: 0:00:48 lr: 0.000177 loss: 3.1028 (3.1049) grad: 0.0754 (0.0709) time: 0.3271 data: 0.0040 max mem: 3972 +train: [11] [280/400] eta: 0:00:41 lr: 0.000175 loss: 3.0913 (3.1046) grad: 0.0729 (0.0709) time: 0.3380 data: 0.0040 max mem: 3972 +train: [11] [300/400] eta: 0:00:34 lr: 0.000174 loss: 3.1067 (3.1046) grad: 0.0756 (0.0714) time: 0.3488 data: 0.0041 max mem: 3972 +train: [11] [320/400] eta: 0:00:27 lr: 0.000172 loss: 3.1078 (3.1038) grad: 0.0769 (0.0713) time: 0.3372 data: 0.0040 max mem: 3972 +train: [11] [340/400] eta: 0:00:20 lr: 0.000170 loss: 3.0927 (3.1041) grad: 0.0697 (0.0714) time: 0.3428 data: 0.0040 max mem: 3972 +train: [11] [360/400] eta: 0:00:13 lr: 0.000169 loss: 3.0846 (3.1032) grad: 0.0666 (0.0711) time: 0.3261 data: 0.0038 max mem: 3972 +train: [11] [380/400] eta: 0:00:06 lr: 0.000167 loss: 3.0804 (3.1029) grad: 0.0661 (0.0710) time: 0.3251 data: 0.0036 max mem: 3972 +train: [11] [399/400] eta: 0:00:00 lr: 0.000166 loss: 3.1110 (3.1039) grad: 0.0681 (0.0709) time: 0.3319 data: 0.0039 max mem: 3972 +train: [11] Total time: 0:02:18 (0.3452 s / it) +train: [11] Summary: lr: 0.000166 loss: 3.1110 (3.1039) grad: 0.0681 (0.0709) +eval (validation): [11] [ 0/85] eta: 0:04:36 time: 3.2521 data: 3.0090 max mem: 3972 +eval (validation): [11] [20/85] eta: 0:00:28 time: 0.3018 data: 0.0049 max mem: 3972 +eval (validation): [11] [40/85] eta: 0:00:17 time: 0.3133 data: 0.0034 max mem: 3972 +eval (validation): [11] [60/85] eta: 0:00:09 time: 0.3325 data: 0.0043 max mem: 3972 +eval (validation): [11] [80/85] eta: 0:00:01 time: 0.3225 data: 0.0040 max mem: 3972 +eval (validation): [11] [84/85] eta: 0:00:00 time: 0.3056 data: 0.0037 max mem: 3972 +eval (validation): [11] Total time: 0:00:30 (0.3537 s / it) +cv: [11] best hparam: (31, 1.0) (045) ('045_lr3.1e+01_wd1.0e+00') loss: 3.122 acc: 0.090 f1: 0.044 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [12] [ 0/400] eta: 0:21:09 lr: nan time: 3.1736 data: 2.9170 max mem: 3972 +train: [12] [ 20/400] eta: 0:03:07 lr: 0.000164 loss: 3.0971 (3.0973) grad: 0.0682 (0.0711) time: 0.3584 data: 0.0054 max mem: 3972 +train: [12] [ 40/400] eta: 0:02:29 lr: 0.000163 loss: 3.0901 (3.0929) grad: 0.0693 (0.0710) time: 0.3318 data: 0.0040 max mem: 3972 +train: [12] [ 60/400] eta: 0:02:13 lr: 0.000161 loss: 3.0865 (3.0943) grad: 0.0710 (0.0714) time: 0.3505 data: 0.0041 max mem: 3972 +train: [12] [ 80/400] eta: 0:02:01 lr: 0.000160 loss: 3.0873 (3.0935) grad: 0.0718 (0.0707) time: 0.3376 data: 0.0041 max mem: 3972 +train: [12] [100/400] eta: 0:01:50 lr: 0.000158 loss: 3.0873 (3.0927) grad: 0.0708 (0.0710) time: 0.3294 data: 0.0040 max mem: 3972 +train: [12] [120/400] eta: 0:01:41 lr: 0.000156 loss: 3.0865 (3.0936) grad: 0.0681 (0.0706) time: 0.3190 data: 0.0039 max mem: 3972 +train: [12] [140/400] eta: 0:01:32 lr: 0.000155 loss: 3.0779 (3.0939) grad: 0.0645 (0.0705) time: 0.3307 data: 0.0042 max mem: 3972 +train: [12] [160/400] eta: 0:01:24 lr: 0.000153 loss: 3.0821 (3.0938) grad: 0.0659 (0.0703) time: 0.3267 data: 0.0041 max mem: 3972 +train: [12] [180/400] eta: 0:01:16 lr: 0.000152 loss: 3.0934 (3.0957) grad: 0.0671 (0.0704) time: 0.3214 data: 0.0039 max mem: 3972 +train: [12] [200/400] eta: 0:01:09 lr: 0.000150 loss: 3.0939 (3.0943) grad: 0.0671 (0.0704) time: 0.3396 data: 0.0043 max mem: 3972 +train: [12] [220/400] eta: 0:01:02 lr: 0.000149 loss: 3.0858 (3.0942) grad: 0.0702 (0.0705) time: 0.3283 data: 0.0038 max mem: 3972 +train: [12] [240/400] eta: 0:00:55 lr: 0.000147 loss: 3.0846 (3.0945) grad: 0.0678 (0.0701) time: 0.3168 data: 0.0038 max mem: 3972 +train: [12] [260/400] eta: 0:00:48 lr: 0.000145 loss: 3.1075 (3.0956) grad: 0.0664 (0.0698) time: 0.3490 data: 0.0042 max mem: 3972 +train: [12] [280/400] eta: 0:00:41 lr: 0.000144 loss: 3.0965 (3.0960) grad: 0.0717 (0.0702) time: 0.3587 data: 0.0046 max mem: 3972 +train: [12] [300/400] eta: 0:00:34 lr: 0.000142 loss: 3.0941 (3.0962) grad: 0.0733 (0.0701) time: 0.3372 data: 0.0038 max mem: 3972 +train: [12] [320/400] eta: 0:00:27 lr: 0.000141 loss: 3.0957 (3.0966) grad: 0.0681 (0.0700) time: 0.3356 data: 0.0040 max mem: 3972 +train: [12] [340/400] eta: 0:00:20 lr: 0.000139 loss: 3.1083 (3.0980) grad: 0.0694 (0.0702) time: 0.3235 data: 0.0040 max mem: 3972 +train: [12] [360/400] eta: 0:00:13 lr: 0.000138 loss: 3.1083 (3.0982) grad: 0.0709 (0.0702) time: 0.3245 data: 0.0042 max mem: 3972 +train: [12] [380/400] eta: 0:00:06 lr: 0.000136 loss: 3.0902 (3.0959) grad: 0.0689 (0.0702) time: 0.3502 data: 0.0040 max mem: 3972 +train: [12] [399/400] eta: 0:00:00 lr: 0.000134 loss: 3.0862 (3.0959) grad: 0.0667 (0.0699) time: 0.3410 data: 0.0041 max mem: 3972 +train: [12] Total time: 0:02:17 (0.3427 s / it) +train: [12] Summary: lr: 0.000134 loss: 3.0862 (3.0959) grad: 0.0667 (0.0699) +eval (validation): [12] [ 0/85] eta: 0:04:40 time: 3.2967 data: 3.0491 max mem: 3972 +eval (validation): [12] [20/85] eta: 0:00:29 time: 0.3063 data: 0.0035 max mem: 3972 +eval (validation): [12] [40/85] eta: 0:00:17 time: 0.3486 data: 0.0036 max mem: 3972 +eval (validation): [12] [60/85] eta: 0:00:09 time: 0.3398 data: 0.0041 max mem: 3972 +eval (validation): [12] [80/85] eta: 0:00:01 time: 0.3114 data: 0.0042 max mem: 3972 +eval (validation): [12] [84/85] eta: 0:00:00 time: 0.3062 data: 0.0037 max mem: 3972 +eval (validation): [12] Total time: 0:00:30 (0.3632 s / it) +cv: [12] best hparam: (26, 1.0) (044) ('044_lr2.6e+01_wd1.0e+00') loss: 3.101 acc: 0.088 f1: 0.042 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [13] [ 0/400] eta: 0:21:46 lr: nan time: 3.2658 data: 3.0569 max mem: 3972 +train: [13] [ 20/400] eta: 0:02:57 lr: 0.000133 loss: 3.0689 (3.0890) grad: 0.0738 (0.0739) time: 0.3272 data: 0.0041 max mem: 3972 +train: [13] [ 40/400] eta: 0:02:22 lr: 0.000131 loss: 3.0831 (3.0913) grad: 0.0726 (0.0728) time: 0.3205 data: 0.0041 max mem: 3972 +train: [13] [ 60/400] eta: 0:02:08 lr: 0.000130 loss: 3.1062 (3.0958) grad: 0.0722 (0.0737) time: 0.3426 data: 0.0036 max mem: 3972 +train: [13] [ 80/400] eta: 0:01:57 lr: 0.000128 loss: 3.1018 (3.0966) grad: 0.0701 (0.0726) time: 0.3375 data: 0.0042 max mem: 3972 +train: [13] [100/400] eta: 0:01:48 lr: 0.000127 loss: 3.0940 (3.0952) grad: 0.0666 (0.0716) time: 0.3363 data: 0.0042 max mem: 3972 +train: [13] [120/400] eta: 0:01:40 lr: 0.000125 loss: 3.0855 (3.0967) grad: 0.0660 (0.0719) time: 0.3369 data: 0.0041 max mem: 3972 +train: [13] [140/400] eta: 0:01:32 lr: 0.000124 loss: 3.0890 (3.0981) grad: 0.0718 (0.0719) time: 0.3420 data: 0.0040 max mem: 3972 +train: [13] [160/400] eta: 0:01:24 lr: 0.000122 loss: 3.0831 (3.0945) grad: 0.0693 (0.0713) time: 0.3376 data: 0.0040 max mem: 3972 +train: [13] [180/400] eta: 0:01:17 lr: 0.000120 loss: 3.0759 (3.0951) grad: 0.0709 (0.0715) time: 0.3336 data: 0.0041 max mem: 3972 +train: [13] [200/400] eta: 0:01:09 lr: 0.000119 loss: 3.0913 (3.0930) grad: 0.0709 (0.0712) time: 0.3364 data: 0.0038 max mem: 3972 +train: [13] [220/400] eta: 0:01:03 lr: 0.000117 loss: 3.0917 (3.0937) grad: 0.0687 (0.0709) time: 0.3604 data: 0.0047 max mem: 3972 +train: [13] [240/400] eta: 0:00:56 lr: 0.000116 loss: 3.0995 (3.0945) grad: 0.0687 (0.0710) time: 0.3794 data: 0.0045 max mem: 3972 +train: [13] [260/400] eta: 0:00:49 lr: 0.000114 loss: 3.0995 (3.0960) grad: 0.0700 (0.0714) time: 0.3256 data: 0.0041 max mem: 3972 +train: [13] [280/400] eta: 0:00:41 lr: 0.000113 loss: 3.0914 (3.0946) grad: 0.0707 (0.0713) time: 0.3297 data: 0.0041 max mem: 3972 +train: [13] [300/400] eta: 0:00:34 lr: 0.000111 loss: 3.0914 (3.0959) grad: 0.0704 (0.0711) time: 0.3304 data: 0.0039 max mem: 3972 +train: [13] [320/400] eta: 0:00:27 lr: 0.000110 loss: 3.0987 (3.0955) grad: 0.0679 (0.0709) time: 0.3358 data: 0.0039 max mem: 3972 +train: [13] [340/400] eta: 0:00:20 lr: 0.000108 loss: 3.1082 (3.0969) grad: 0.0673 (0.0709) time: 0.3232 data: 0.0039 max mem: 3972 +train: [13] [360/400] eta: 0:00:13 lr: 0.000107 loss: 3.1066 (3.0968) grad: 0.0679 (0.0708) time: 0.3442 data: 0.0041 max mem: 3972 +train: [13] [380/400] eta: 0:00:06 lr: 0.000105 loss: 3.0881 (3.0962) grad: 0.0675 (0.0707) time: 0.3265 data: 0.0039 max mem: 3972 +train: [13] [399/400] eta: 0:00:00 lr: 0.000104 loss: 3.0932 (3.0963) grad: 0.0689 (0.0707) time: 0.3315 data: 0.0042 max mem: 3972 +train: [13] Total time: 0:02:17 (0.3445 s / it) +train: [13] Summary: lr: 0.000104 loss: 3.0932 (3.0963) grad: 0.0689 (0.0707) +eval (validation): [13] [ 0/85] eta: 0:04:33 time: 3.2134 data: 3.0044 max mem: 3972 +eval (validation): [13] [20/85] eta: 0:00:33 time: 0.3869 data: 0.0123 max mem: 3972 +eval (validation): [13] [40/85] eta: 0:00:19 time: 0.3219 data: 0.0043 max mem: 3972 +eval (validation): [13] [60/85] eta: 0:00:09 time: 0.3151 data: 0.0043 max mem: 3972 +eval (validation): [13] [80/85] eta: 0:00:01 time: 0.3242 data: 0.0041 max mem: 3972 +eval (validation): [13] [84/85] eta: 0:00:00 time: 0.3017 data: 0.0038 max mem: 3972 +eval (validation): [13] Total time: 0:00:31 (0.3715 s / it) +cv: [13] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.106 acc: 0.087 f1: 0.043 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [14] [ 0/400] eta: 0:21:56 lr: nan time: 3.2912 data: 3.0789 max mem: 3972 +train: [14] [ 20/400] eta: 0:03:12 lr: 0.000102 loss: 3.0896 (3.0977) grad: 0.0721 (0.0717) time: 0.3676 data: 0.0043 max mem: 3972 +train: [14] [ 40/400] eta: 0:02:31 lr: 0.000101 loss: 3.0896 (3.0929) grad: 0.0712 (0.0716) time: 0.3319 data: 0.0040 max mem: 3972 +train: [14] [ 60/400] eta: 0:02:14 lr: 0.000099 loss: 3.0870 (3.0944) grad: 0.0709 (0.0718) time: 0.3403 data: 0.0044 max mem: 3972 +train: [14] [ 80/400] eta: 0:02:01 lr: 0.000098 loss: 3.0872 (3.0945) grad: 0.0698 (0.0719) time: 0.3274 data: 0.0044 max mem: 3972 +train: [14] [100/400] eta: 0:01:50 lr: 0.000096 loss: 3.0865 (3.0942) grad: 0.0726 (0.0716) time: 0.3257 data: 0.0040 max mem: 3972 +train: [14] [120/400] eta: 0:01:41 lr: 0.000095 loss: 3.0954 (3.0956) grad: 0.0679 (0.0712) time: 0.3397 data: 0.0040 max mem: 3972 +train: [14] [140/400] eta: 0:01:33 lr: 0.000093 loss: 3.0973 (3.0966) grad: 0.0667 (0.0705) time: 0.3405 data: 0.0040 max mem: 3972 +train: [14] [160/400] eta: 0:01:25 lr: 0.000092 loss: 3.0895 (3.0947) grad: 0.0663 (0.0699) time: 0.3255 data: 0.0043 max mem: 3972 +train: [14] [180/400] eta: 0:01:18 lr: 0.000090 loss: 3.0957 (3.0936) grad: 0.0682 (0.0704) time: 0.3565 data: 0.0041 max mem: 3972 +train: [14] [200/400] eta: 0:01:10 lr: 0.000089 loss: 3.0763 (3.0924) grad: 0.0712 (0.0705) time: 0.2998 data: 0.0041 max mem: 3972 +train: [14] [220/400] eta: 0:01:03 lr: 0.000088 loss: 3.0793 (3.0945) grad: 0.0681 (0.0703) time: 0.3567 data: 0.0040 max mem: 3972 +train: [14] [240/400] eta: 0:00:56 lr: 0.000086 loss: 3.1033 (3.0947) grad: 0.0711 (0.0705) time: 0.3745 data: 0.0041 max mem: 3972 +train: [14] [260/400] eta: 0:00:49 lr: 0.000085 loss: 3.1117 (3.0970) grad: 0.0711 (0.0702) time: 0.3311 data: 0.0041 max mem: 3972 +train: [14] [280/400] eta: 0:00:42 lr: 0.000083 loss: 3.1137 (3.0971) grad: 0.0712 (0.0705) time: 0.3714 data: 0.0044 max mem: 3972 +train: [14] [300/400] eta: 0:00:35 lr: 0.000082 loss: 3.0868 (3.0963) grad: 0.0749 (0.0706) time: 0.3305 data: 0.0039 max mem: 3972 +train: [14] [320/400] eta: 0:00:27 lr: 0.000081 loss: 3.0851 (3.0959) grad: 0.0709 (0.0707) time: 0.3300 data: 0.0041 max mem: 3972 +train: [14] [340/400] eta: 0:00:20 lr: 0.000079 loss: 3.0807 (3.0950) grad: 0.0720 (0.0709) time: 0.3364 data: 0.0039 max mem: 3972 +train: [14] [360/400] eta: 0:00:13 lr: 0.000078 loss: 3.0807 (3.0944) grad: 0.0691 (0.0707) time: 0.3363 data: 0.0039 max mem: 3972 +train: [14] [380/400] eta: 0:00:06 lr: 0.000076 loss: 3.0908 (3.0947) grad: 0.0678 (0.0706) time: 0.3586 data: 0.0040 max mem: 3972 +train: [14] [399/400] eta: 0:00:00 lr: 0.000075 loss: 3.0908 (3.0940) grad: 0.0689 (0.0706) time: 0.3287 data: 0.0041 max mem: 3972 +train: [14] Total time: 0:02:19 (0.3481 s / it) +train: [14] Summary: lr: 0.000075 loss: 3.0908 (3.0940) grad: 0.0689 (0.0706) +eval (validation): [14] [ 0/85] eta: 0:05:15 time: 3.7091 data: 3.4431 max mem: 3972 +eval (validation): [14] [20/85] eta: 0:00:32 time: 0.3471 data: 0.0036 max mem: 3972 +eval (validation): [14] [40/85] eta: 0:00:18 time: 0.3300 data: 0.0061 max mem: 3972 +eval (validation): [14] [60/85] eta: 0:00:09 time: 0.3328 data: 0.0045 max mem: 3972 +eval (validation): [14] [80/85] eta: 0:00:01 time: 0.2950 data: 0.0038 max mem: 3972 +eval (validation): [14] [84/85] eta: 0:00:00 time: 0.2900 data: 0.0039 max mem: 3972 +eval (validation): [14] Total time: 0:00:31 (0.3675 s / it) +cv: [14] best hparam: (19, 1.0) (042) ('042_lr1.9e+01_wd1.0e+00') loss: 3.081 acc: 0.095 f1: 0.042 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [15] [ 0/400] eta: 0:21:26 lr: nan time: 3.2172 data: 3.0122 max mem: 3972 +train: [15] [ 20/400] eta: 0:03:13 lr: 0.000074 loss: 3.0685 (3.0849) grad: 0.0670 (0.0694) time: 0.3733 data: 0.0305 max mem: 3972 +train: [15] [ 40/400] eta: 0:02:30 lr: 0.000072 loss: 3.0642 (3.0702) grad: 0.0670 (0.0693) time: 0.3254 data: 0.0041 max mem: 3972 +train: [15] [ 60/400] eta: 0:02:12 lr: 0.000071 loss: 3.0711 (3.0792) grad: 0.0699 (0.0695) time: 0.3251 data: 0.0042 max mem: 3972 +train: [15] [ 80/400] eta: 0:01:59 lr: 0.000070 loss: 3.0888 (3.0793) grad: 0.0697 (0.0692) time: 0.3330 data: 0.0041 max mem: 3972 +train: [15] [100/400] eta: 0:01:49 lr: 0.000068 loss: 3.0750 (3.0791) grad: 0.0687 (0.0694) time: 0.3197 data: 0.0041 max mem: 3972 +train: [15] [120/400] eta: 0:01:40 lr: 0.000067 loss: 3.0685 (3.0804) grad: 0.0670 (0.0688) time: 0.3280 data: 0.0042 max mem: 3972 +train: [15] [140/400] eta: 0:01:31 lr: 0.000066 loss: 3.0939 (3.0847) grad: 0.0641 (0.0682) time: 0.3226 data: 0.0041 max mem: 3972 +train: [15] [160/400] eta: 0:01:24 lr: 0.000064 loss: 3.0873 (3.0842) grad: 0.0651 (0.0681) time: 0.3304 data: 0.0039 max mem: 3972 +train: [15] [180/400] eta: 0:01:16 lr: 0.000063 loss: 3.0736 (3.0823) grad: 0.0671 (0.0682) time: 0.3174 data: 0.0040 max mem: 3972 +train: [15] [200/400] eta: 0:01:08 lr: 0.000062 loss: 3.0733 (3.0840) grad: 0.0648 (0.0680) time: 0.3313 data: 0.0040 max mem: 3972 +train: [15] [220/400] eta: 0:01:02 lr: 0.000061 loss: 3.0833 (3.0856) grad: 0.0689 (0.0683) time: 0.3462 data: 0.0040 max mem: 3972 +train: [15] [240/400] eta: 0:00:55 lr: 0.000059 loss: 3.0833 (3.0860) grad: 0.0689 (0.0683) time: 0.3344 data: 0.0038 max mem: 3972 +train: [15] [260/400] eta: 0:00:47 lr: 0.000058 loss: 3.0859 (3.0853) grad: 0.0700 (0.0685) time: 0.3199 data: 0.0037 max mem: 3972 +train: [15] [280/400] eta: 0:00:41 lr: 0.000057 loss: 3.0875 (3.0866) grad: 0.0709 (0.0687) time: 0.3454 data: 0.0040 max mem: 3972 +train: [15] [300/400] eta: 0:00:34 lr: 0.000056 loss: 3.0969 (3.0866) grad: 0.0648 (0.0685) time: 0.3379 data: 0.0039 max mem: 3972 +train: [15] [320/400] eta: 0:00:27 lr: 0.000054 loss: 3.0812 (3.0863) grad: 0.0648 (0.0685) time: 0.3372 data: 0.0041 max mem: 3972 +train: [15] [340/400] eta: 0:00:20 lr: 0.000053 loss: 3.0770 (3.0864) grad: 0.0708 (0.0687) time: 0.3317 data: 0.0036 max mem: 3972 +train: [15] [360/400] eta: 0:00:13 lr: 0.000052 loss: 3.0770 (3.0861) grad: 0.0718 (0.0688) time: 0.3235 data: 0.0037 max mem: 3972 +train: [15] [380/400] eta: 0:00:06 lr: 0.000051 loss: 3.0642 (3.0856) grad: 0.0717 (0.0689) time: 0.3290 data: 0.0038 max mem: 3972 +train: [15] [399/400] eta: 0:00:00 lr: 0.000050 loss: 3.0779 (3.0861) grad: 0.0710 (0.0688) time: 0.3444 data: 0.0040 max mem: 3972 +train: [15] Total time: 0:02:16 (0.3402 s / it) +train: [15] Summary: lr: 0.000050 loss: 3.0779 (3.0861) grad: 0.0710 (0.0688) +eval (validation): [15] [ 0/85] eta: 0:04:41 time: 3.3161 data: 3.0642 max mem: 3972 +eval (validation): [15] [20/85] eta: 0:00:33 time: 0.3690 data: 0.0052 max mem: 3972 +eval (validation): [15] [40/85] eta: 0:00:19 time: 0.3371 data: 0.0044 max mem: 3972 +eval (validation): [15] [60/85] eta: 0:00:09 time: 0.3301 data: 0.0044 max mem: 3972 +eval (validation): [15] [80/85] eta: 0:00:01 time: 0.3156 data: 0.0045 max mem: 3972 +eval (validation): [15] [84/85] eta: 0:00:00 time: 0.3074 data: 0.0043 max mem: 3972 +eval (validation): [15] Total time: 0:00:31 (0.3733 s / it) +cv: [15] best hparam: (43, 1.0) (047) ('047_lr4.3e+01_wd1.0e+00') loss: 3.081 acc: 0.092 f1: 0.056 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [16] [ 0/400] eta: 0:21:13 lr: nan time: 3.1836 data: 2.9373 max mem: 3972 +train: [16] [ 20/400] eta: 0:03:04 lr: 0.000048 loss: 3.0572 (3.0537) grad: 0.0661 (0.0663) time: 0.3496 data: 0.0054 max mem: 3972 +train: [16] [ 40/400] eta: 0:02:31 lr: 0.000047 loss: 3.0809 (3.0761) grad: 0.0661 (0.0657) time: 0.3540 data: 0.0037 max mem: 3972 +train: [16] [ 60/400] eta: 0:02:15 lr: 0.000046 loss: 3.0935 (3.0760) grad: 0.0654 (0.0655) time: 0.3525 data: 0.0043 max mem: 3972 +train: [16] [ 80/400] eta: 0:02:04 lr: 0.000045 loss: 3.0798 (3.0800) grad: 0.0666 (0.0669) time: 0.3592 data: 0.0046 max mem: 3972 +train: [16] [100/400] eta: 0:01:53 lr: 0.000044 loss: 3.0798 (3.0814) grad: 0.0688 (0.0677) time: 0.3328 data: 0.0040 max mem: 3972 +train: [16] [120/400] eta: 0:01:43 lr: 0.000043 loss: 3.0980 (3.0846) grad: 0.0667 (0.0673) time: 0.3378 data: 0.0039 max mem: 3972 +train: [16] [140/400] eta: 0:01:34 lr: 0.000042 loss: 3.1055 (3.0860) grad: 0.0670 (0.0680) time: 0.3277 data: 0.0040 max mem: 3972 +train: [16] [160/400] eta: 0:01:26 lr: 0.000041 loss: 3.1003 (3.0872) grad: 0.0711 (0.0683) time: 0.3253 data: 0.0038 max mem: 3972 +train: [16] [180/400] eta: 0:01:18 lr: 0.000040 loss: 3.0930 (3.0876) grad: 0.0666 (0.0683) time: 0.3472 data: 0.0040 max mem: 3972 +train: [16] [200/400] eta: 0:01:11 lr: 0.000039 loss: 3.0910 (3.0884) grad: 0.0675 (0.0686) time: 0.3408 data: 0.0044 max mem: 3972 +train: [16] [220/400] eta: 0:01:04 lr: 0.000038 loss: 3.1019 (3.0881) grad: 0.0675 (0.0685) time: 0.3669 data: 0.0039 max mem: 3972 +train: [16] [240/400] eta: 0:00:56 lr: 0.000036 loss: 3.0904 (3.0877) grad: 0.0685 (0.0692) time: 0.3228 data: 0.0042 max mem: 3972 +train: [16] [260/400] eta: 0:00:49 lr: 0.000035 loss: 3.0904 (3.0881) grad: 0.0661 (0.0690) time: 0.3305 data: 0.0043 max mem: 3972 +train: [16] [280/400] eta: 0:00:42 lr: 0.000034 loss: 3.0775 (3.0876) grad: 0.0657 (0.0690) time: 0.3335 data: 0.0042 max mem: 3972 +train: [16] [300/400] eta: 0:00:35 lr: 0.000033 loss: 3.0775 (3.0871) grad: 0.0685 (0.0690) time: 0.3315 data: 0.0041 max mem: 3972 +train: [16] [320/400] eta: 0:00:27 lr: 0.000032 loss: 3.0740 (3.0870) grad: 0.0652 (0.0689) time: 0.3378 data: 0.0040 max mem: 3972 +train: [16] [340/400] eta: 0:00:20 lr: 0.000031 loss: 3.0732 (3.0867) grad: 0.0633 (0.0688) time: 0.3252 data: 0.0045 max mem: 3972 +train: [16] [360/400] eta: 0:00:13 lr: 0.000031 loss: 3.0820 (3.0868) grad: 0.0632 (0.0687) time: 0.3151 data: 0.0038 max mem: 3972 +train: [16] [380/400] eta: 0:00:06 lr: 0.000030 loss: 3.0934 (3.0870) grad: 0.0664 (0.0687) time: 0.3380 data: 0.0041 max mem: 3972 +train: [16] [399/400] eta: 0:00:00 lr: 0.000029 loss: 3.0777 (3.0855) grad: 0.0668 (0.0686) time: 0.3454 data: 0.0044 max mem: 3972 +train: [16] Total time: 0:02:18 (0.3461 s / it) +train: [16] Summary: lr: 0.000029 loss: 3.0777 (3.0855) grad: 0.0668 (0.0686) +eval (validation): [16] [ 0/85] eta: 0:04:30 time: 3.1877 data: 2.9918 max mem: 3972 +eval (validation): [16] [20/85] eta: 0:00:28 time: 0.3069 data: 0.0038 max mem: 3972 +eval (validation): [16] [40/85] eta: 0:00:18 time: 0.3615 data: 0.0039 max mem: 3972 +eval (validation): [16] [60/85] eta: 0:00:09 time: 0.3589 data: 0.0048 max mem: 3972 +eval (validation): [16] [80/85] eta: 0:00:01 time: 0.3210 data: 0.0044 max mem: 3972 +eval (validation): [16] [84/85] eta: 0:00:00 time: 0.2984 data: 0.0040 max mem: 3972 +eval (validation): [16] Total time: 0:00:31 (0.3715 s / it) +cv: [16] best hparam: (36, 1.0) (046) ('046_lr3.6e+01_wd1.0e+00') loss: 3.076 acc: 0.093 f1: 0.048 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [17] [ 0/400] eta: 0:21:19 lr: nan time: 3.1978 data: 2.9984 max mem: 3972 +train: [17] [ 20/400] eta: 0:03:08 lr: 0.000028 loss: 3.0866 (3.0811) grad: 0.0719 (0.0713) time: 0.3603 data: 0.0160 max mem: 3972 +train: [17] [ 40/400] eta: 0:02:34 lr: 0.000027 loss: 3.0832 (3.0832) grad: 0.0700 (0.0699) time: 0.3579 data: 0.0037 max mem: 3972 +train: [17] [ 60/400] eta: 0:02:13 lr: 0.000026 loss: 3.0755 (3.0893) grad: 0.0700 (0.0708) time: 0.3184 data: 0.0042 max mem: 3972 +train: [17] [ 80/400] eta: 0:02:00 lr: 0.000025 loss: 3.0732 (3.0875) grad: 0.0726 (0.0709) time: 0.3308 data: 0.0042 max mem: 3972 +train: [17] [100/400] eta: 0:01:51 lr: 0.000024 loss: 3.0680 (3.0863) grad: 0.0699 (0.0709) time: 0.3464 data: 0.0041 max mem: 3972 +train: [17] [120/400] eta: 0:01:45 lr: 0.000023 loss: 3.0979 (3.0888) grad: 0.0659 (0.0702) time: 0.4126 data: 0.0048 max mem: 3972 +train: [17] [140/400] eta: 0:01:36 lr: 0.000023 loss: 3.0953 (3.0872) grad: 0.0682 (0.0702) time: 0.3356 data: 0.0040 max mem: 3972 +train: [17] [160/400] eta: 0:01:28 lr: 0.000022 loss: 3.0899 (3.0853) grad: 0.0679 (0.0696) time: 0.3437 data: 0.0039 max mem: 3972 +train: [17] [180/400] eta: 0:01:20 lr: 0.000021 loss: 3.0799 (3.0853) grad: 0.0665 (0.0692) time: 0.3522 data: 0.0040 max mem: 3972 +train: [17] [200/400] eta: 0:01:13 lr: 0.000020 loss: 3.0864 (3.0852) grad: 0.0653 (0.0688) time: 0.3555 data: 0.0041 max mem: 3972 +train: [17] [220/400] eta: 0:01:05 lr: 0.000019 loss: 3.0803 (3.0851) grad: 0.0666 (0.0689) time: 0.3610 data: 0.0048 max mem: 3972 +train: [17] [240/400] eta: 0:00:57 lr: 0.000019 loss: 3.0699 (3.0845) grad: 0.0682 (0.0690) time: 0.3186 data: 0.0038 max mem: 3972 +train: [17] [260/400] eta: 0:00:50 lr: 0.000018 loss: 3.0775 (3.0837) grad: 0.0678 (0.0688) time: 0.3315 data: 0.0038 max mem: 3972 +train: [17] [280/400] eta: 0:00:42 lr: 0.000017 loss: 3.0892 (3.0840) grad: 0.0663 (0.0686) time: 0.3461 data: 0.0041 max mem: 3972 +train: [17] [300/400] eta: 0:00:35 lr: 0.000016 loss: 3.0874 (3.0847) grad: 0.0668 (0.0688) time: 0.3429 data: 0.0040 max mem: 3972 +train: [17] [320/400] eta: 0:00:28 lr: 0.000016 loss: 3.0874 (3.0855) grad: 0.0682 (0.0687) time: 0.3299 data: 0.0039 max mem: 3972 +train: [17] [340/400] eta: 0:00:21 lr: 0.000015 loss: 3.0848 (3.0859) grad: 0.0650 (0.0683) time: 0.3179 data: 0.0038 max mem: 3972 +train: [17] [360/400] eta: 0:00:14 lr: 0.000014 loss: 3.0848 (3.0862) grad: 0.0633 (0.0684) time: 0.3433 data: 0.0041 max mem: 3972 +train: [17] [380/400] eta: 0:00:07 lr: 0.000014 loss: 3.0712 (3.0857) grad: 0.0697 (0.0684) time: 0.3426 data: 0.0040 max mem: 3972 +train: [17] [399/400] eta: 0:00:00 lr: 0.000013 loss: 3.0712 (3.0860) grad: 0.0698 (0.0684) time: 0.3534 data: 0.0045 max mem: 3972 +train: [17] Total time: 0:02:20 (0.3524 s / it) +train: [17] Summary: lr: 0.000013 loss: 3.0712 (3.0860) grad: 0.0698 (0.0684) +eval (validation): [17] [ 0/85] eta: 0:04:41 time: 3.3062 data: 3.1029 max mem: 3972 +eval (validation): [17] [20/85] eta: 0:00:30 time: 0.3238 data: 0.0201 max mem: 3972 +eval (validation): [17] [40/85] eta: 0:00:17 time: 0.3160 data: 0.0036 max mem: 3972 +eval (validation): [17] [60/85] eta: 0:00:09 time: 0.3183 data: 0.0041 max mem: 3972 +eval (validation): [17] [80/85] eta: 0:00:01 time: 0.2941 data: 0.0039 max mem: 3972 +eval (validation): [17] [84/85] eta: 0:00:00 time: 0.2860 data: 0.0040 max mem: 3972 +eval (validation): [17] Total time: 0:00:29 (0.3497 s / it) +cv: [17] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.070 acc: 0.099 f1: 0.053 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +saving best checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +train: [18] [ 0/400] eta: 0:21:31 lr: nan time: 3.2298 data: 3.0045 max mem: 3972 +train: [18] [ 20/400] eta: 0:02:59 lr: 0.000012 loss: 3.1133 (3.1148) grad: 0.0615 (0.0682) time: 0.3332 data: 0.0053 max mem: 3972 +train: [18] [ 40/400] eta: 0:02:27 lr: 0.000012 loss: 3.1033 (3.0939) grad: 0.0677 (0.0698) time: 0.3437 data: 0.0039 max mem: 3972 +train: [18] [ 60/400] eta: 0:02:10 lr: 0.000011 loss: 3.0809 (3.0934) grad: 0.0690 (0.0694) time: 0.3325 data: 0.0042 max mem: 3972 +train: [18] [ 80/400] eta: 0:01:58 lr: 0.000011 loss: 3.0735 (3.0889) grad: 0.0690 (0.0697) time: 0.3283 data: 0.0040 max mem: 3972 +train: [18] [100/400] eta: 0:01:49 lr: 0.000010 loss: 3.0735 (3.0868) grad: 0.0716 (0.0699) time: 0.3502 data: 0.0041 max mem: 3972 +train: [18] [120/400] eta: 0:01:40 lr: 0.000009 loss: 3.0794 (3.0858) grad: 0.0697 (0.0695) time: 0.3287 data: 0.0042 max mem: 3972 +train: [18] [140/400] eta: 0:01:32 lr: 0.000009 loss: 3.0877 (3.0848) grad: 0.0641 (0.0685) time: 0.3309 data: 0.0042 max mem: 3972 +train: [18] [160/400] eta: 0:01:24 lr: 0.000008 loss: 3.0783 (3.0848) grad: 0.0632 (0.0685) time: 0.3358 data: 0.0040 max mem: 3972 +train: [18] [180/400] eta: 0:01:17 lr: 0.000008 loss: 3.0740 (3.0851) grad: 0.0670 (0.0685) time: 0.3540 data: 0.0040 max mem: 3972 +train: [18] [200/400] eta: 0:01:10 lr: 0.000007 loss: 3.0726 (3.0840) grad: 0.0679 (0.0686) time: 0.3265 data: 0.0039 max mem: 3972 +train: [18] [220/400] eta: 0:01:02 lr: 0.000007 loss: 3.0657 (3.0820) grad: 0.0709 (0.0687) time: 0.3362 data: 0.0041 max mem: 3972 +train: [18] [240/400] eta: 0:00:55 lr: 0.000006 loss: 3.0732 (3.0818) grad: 0.0690 (0.0684) time: 0.3533 data: 0.0045 max mem: 3972 +train: [18] [260/400] eta: 0:00:48 lr: 0.000006 loss: 3.0685 (3.0803) grad: 0.0638 (0.0680) time: 0.3365 data: 0.0037 max mem: 3972 +train: [18] [280/400] eta: 0:00:41 lr: 0.000006 loss: 3.0627 (3.0789) grad: 0.0657 (0.0679) time: 0.3439 data: 0.0042 max mem: 3972 +train: [18] [300/400] eta: 0:00:34 lr: 0.000005 loss: 3.0700 (3.0798) grad: 0.0680 (0.0682) time: 0.3341 data: 0.0035 max mem: 3972 +train: [18] [320/400] eta: 0:00:27 lr: 0.000005 loss: 3.0748 (3.0797) grad: 0.0704 (0.0684) time: 0.3367 data: 0.0038 max mem: 3972 +train: [18] [340/400] eta: 0:00:20 lr: 0.000004 loss: 3.0826 (3.0802) grad: 0.0698 (0.0683) time: 0.3486 data: 0.0039 max mem: 3972 +train: [18] [360/400] eta: 0:00:13 lr: 0.000004 loss: 3.0916 (3.0812) grad: 0.0618 (0.0679) time: 0.3560 data: 0.0040 max mem: 3972 +train: [18] [380/400] eta: 0:00:06 lr: 0.000004 loss: 3.1067 (3.0822) grad: 0.0618 (0.0678) time: 0.3381 data: 0.0039 max mem: 3972 +train: [18] [399/400] eta: 0:00:00 lr: 0.000003 loss: 3.1002 (3.0828) grad: 0.0686 (0.0680) time: 0.3321 data: 0.0039 max mem: 3972 +train: [18] Total time: 0:02:18 (0.3464 s / it) +train: [18] Summary: lr: 0.000003 loss: 3.1002 (3.0828) grad: 0.0686 (0.0680) +eval (validation): [18] [ 0/85] eta: 0:04:28 time: 3.1628 data: 2.9622 max mem: 3972 +eval (validation): [18] [20/85] eta: 0:00:30 time: 0.3419 data: 0.0052 max mem: 3972 +eval (validation): [18] [40/85] eta: 0:00:18 time: 0.3291 data: 0.0040 max mem: 3972 +eval (validation): [18] [60/85] eta: 0:00:09 time: 0.3289 data: 0.0046 max mem: 3972 +eval (validation): [18] [80/85] eta: 0:00:01 time: 0.3175 data: 0.0039 max mem: 3972 +eval (validation): [18] [84/85] eta: 0:00:00 time: 0.3113 data: 0.0042 max mem: 3972 +eval (validation): [18] Total time: 0:00:30 (0.3642 s / it) +cv: [18] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.067 acc: 0.093 f1: 0.051 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +train: [19] [ 0/400] eta: 0:22:09 lr: nan time: 3.3241 data: 3.1085 max mem: 3972 +train: [19] [ 20/400] eta: 0:02:58 lr: 0.000003 loss: 3.0604 (3.0614) grad: 0.0691 (0.0692) time: 0.3265 data: 0.0077 max mem: 3972 +train: [19] [ 40/400] eta: 0:02:27 lr: 0.000003 loss: 3.0623 (3.0639) grad: 0.0730 (0.0706) time: 0.3455 data: 0.0054 max mem: 3972 +train: [19] [ 60/400] eta: 0:02:13 lr: 0.000002 loss: 3.0796 (3.0729) grad: 0.0697 (0.0705) time: 0.3570 data: 0.0031 max mem: 3972 +train: [19] [ 80/400] eta: 0:01:59 lr: 0.000002 loss: 3.0737 (3.0712) grad: 0.0695 (0.0700) time: 0.3196 data: 0.0041 max mem: 3972 +train: [19] [100/400] eta: 0:01:49 lr: 0.000002 loss: 3.0550 (3.0702) grad: 0.0662 (0.0691) time: 0.3248 data: 0.0039 max mem: 3972 +train: [19] [120/400] eta: 0:01:40 lr: 0.000002 loss: 3.0681 (3.0733) grad: 0.0647 (0.0687) time: 0.3402 data: 0.0041 max mem: 3972 +train: [19] [140/400] eta: 0:01:33 lr: 0.000001 loss: 3.0703 (3.0709) grad: 0.0647 (0.0687) time: 0.3468 data: 0.0040 max mem: 3972 +train: [19] [160/400] eta: 0:01:25 lr: 0.000001 loss: 3.0607 (3.0705) grad: 0.0670 (0.0688) time: 0.3325 data: 0.0042 max mem: 3972 +train: [19] [180/400] eta: 0:01:17 lr: 0.000001 loss: 3.0699 (3.0709) grad: 0.0670 (0.0683) time: 0.3242 data: 0.0040 max mem: 3972 +train: [19] [200/400] eta: 0:01:10 lr: 0.000001 loss: 3.0872 (3.0744) grad: 0.0640 (0.0679) time: 0.3480 data: 0.0040 max mem: 3972 +train: [19] [220/400] eta: 0:01:02 lr: 0.000001 loss: 3.0932 (3.0739) grad: 0.0624 (0.0677) time: 0.3290 data: 0.0039 max mem: 3972 +train: [19] [240/400] eta: 0:00:55 lr: 0.000001 loss: 3.0802 (3.0762) grad: 0.0640 (0.0676) time: 0.3236 data: 0.0037 max mem: 3972 +train: [19] [260/400] eta: 0:00:48 lr: 0.000000 loss: 3.0882 (3.0768) grad: 0.0648 (0.0674) time: 0.3407 data: 0.0039 max mem: 3972 +train: [19] [280/400] eta: 0:00:41 lr: 0.000000 loss: 3.0843 (3.0773) grad: 0.0673 (0.0676) time: 0.3334 data: 0.0038 max mem: 3972 +train: [19] [300/400] eta: 0:00:34 lr: 0.000000 loss: 3.0843 (3.0771) grad: 0.0656 (0.0675) time: 0.3311 data: 0.0038 max mem: 3972 +train: [19] [320/400] eta: 0:00:27 lr: 0.000000 loss: 3.0859 (3.0778) grad: 0.0668 (0.0677) time: 0.3211 data: 0.0037 max mem: 3972 +train: [19] [340/400] eta: 0:00:20 lr: 0.000000 loss: 3.0877 (3.0785) grad: 0.0684 (0.0678) time: 0.3282 data: 0.0038 max mem: 3972 +train: [19] [360/400] eta: 0:00:13 lr: 0.000000 loss: 3.0837 (3.0790) grad: 0.0710 (0.0683) time: 0.3339 data: 0.0039 max mem: 3972 +train: [19] [380/400] eta: 0:00:06 lr: 0.000000 loss: 3.0786 (3.0786) grad: 0.0710 (0.0682) time: 0.3225 data: 0.0038 max mem: 3972 +train: [19] [399/400] eta: 0:00:00 lr: 0.000000 loss: 3.0781 (3.0790) grad: 0.0670 (0.0681) time: 0.3239 data: 0.0039 max mem: 3972 +train: [19] Total time: 0:02:16 (0.3404 s / it) +train: [19] Summary: lr: 0.000000 loss: 3.0781 (3.0790) grad: 0.0670 (0.0681) +eval (validation): [19] [ 0/85] eta: 0:04:40 time: 3.3057 data: 3.0488 max mem: 3972 +eval (validation): [19] [20/85] eta: 0:00:29 time: 0.3183 data: 0.0224 max mem: 3972 +eval (validation): [19] [40/85] eta: 0:00:18 time: 0.3687 data: 0.0046 max mem: 3972 +eval (validation): [19] [60/85] eta: 0:00:09 time: 0.3156 data: 0.0029 max mem: 3972 +eval (validation): [19] [80/85] eta: 0:00:01 time: 0.3002 data: 0.0042 max mem: 3972 +eval (validation): [19] [84/85] eta: 0:00:00 time: 0.2950 data: 0.0040 max mem: 3972 +eval (validation): [19] Total time: 0:00:30 (0.3608 s / it) +cv: [19] best hparam: (50, 1.0) (048) ('048_lr5.0e+01_wd1.0e+00') loss: 3.066 acc: 0.092 f1: 0.051 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +evaluating last checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-last.pth +eval model info: +{"score": 0.09246954595791805, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 19, "is_best": false, "best_score": 0.09856035437430787} +eval (train): [20] [ 0/509] eta: 0:28:38 time: 3.3772 data: 3.1673 max mem: 3972 +eval (train): [20] [ 20/509] eta: 0:04:12 time: 0.3723 data: 0.0051 max mem: 3972 +eval (train): [20] [ 40/509] eta: 0:03:18 time: 0.3281 data: 0.0041 max mem: 3972 +eval (train): [20] [ 60/509] eta: 0:02:50 time: 0.2883 data: 0.0040 max mem: 3972 +eval (train): [20] [ 80/509] eta: 0:02:36 time: 0.3201 data: 0.0043 max mem: 3972 +eval (train): [20] [100/509] eta: 0:02:24 time: 0.3114 data: 0.0046 max mem: 3972 +eval (train): [20] [120/509] eta: 0:02:16 time: 0.3313 data: 0.0044 max mem: 3972 +eval (train): [20] [140/509] eta: 0:02:06 time: 0.3024 data: 0.0045 max mem: 3972 +eval (train): [20] [160/509] eta: 0:01:58 time: 0.3189 data: 0.0044 max mem: 3972 +eval (train): [20] [180/509] eta: 0:01:50 time: 0.3093 data: 0.0044 max mem: 3972 +eval (train): [20] [200/509] eta: 0:01:43 time: 0.3133 data: 0.0045 max mem: 3972 +eval (train): [20] [220/509] eta: 0:01:36 time: 0.3234 data: 0.0045 max mem: 3972 +eval (train): [20] [240/509] eta: 0:01:29 time: 0.3011 data: 0.0042 max mem: 3972 +eval (train): [20] [260/509] eta: 0:01:22 time: 0.3101 data: 0.0044 max mem: 3972 +eval (train): [20] [280/509] eta: 0:01:14 time: 0.3020 data: 0.0041 max mem: 3972 +eval (train): [20] [300/509] eta: 0:01:08 time: 0.3198 data: 0.0043 max mem: 3972 +eval (train): [20] [320/509] eta: 0:01:01 time: 0.3021 data: 0.0042 max mem: 3972 +eval (train): [20] [340/509] eta: 0:00:54 time: 0.3144 data: 0.0042 max mem: 3972 +eval (train): [20] [360/509] eta: 0:00:48 time: 0.2940 data: 0.0043 max mem: 3972 +eval (train): [20] [380/509] eta: 0:00:41 time: 0.3231 data: 0.0046 max mem: 3972 +eval (train): [20] [400/509] eta: 0:00:35 time: 0.3082 data: 0.0045 max mem: 3972 +eval (train): [20] [420/509] eta: 0:00:28 time: 0.3102 data: 0.0040 max mem: 3972 +eval (train): [20] [440/509] eta: 0:00:22 time: 0.3141 data: 0.0042 max mem: 3972 +eval (train): [20] [460/509] eta: 0:00:15 time: 0.3136 data: 0.0042 max mem: 3972 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3067 data: 0.0042 max mem: 3972 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.2904 data: 0.0041 max mem: 3972 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2797 data: 0.0038 max mem: 3972 +eval (train): [20] Total time: 0:02:42 (0.3199 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:38 time: 3.2804 data: 3.0718 max mem: 3972 +eval (validation): [20] [20/85] eta: 0:00:31 time: 0.3523 data: 0.0043 max mem: 3972 +eval (validation): [20] [40/85] eta: 0:00:18 time: 0.3400 data: 0.0035 max mem: 3972 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3253 data: 0.0043 max mem: 3972 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.3144 data: 0.0042 max mem: 3972 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.3039 data: 0.0042 max mem: 3972 +eval (validation): [20] Total time: 0:00:31 (0.3692 s / it) +eval (test): [20] [ 0/85] eta: 0:04:38 time: 3.2813 data: 3.0534 max mem: 3972 +eval (test): [20] [20/85] eta: 0:00:30 time: 0.3317 data: 0.0050 max mem: 3972 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3270 data: 0.0035 max mem: 3972 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3199 data: 0.0038 max mem: 3972 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.3169 data: 0.0044 max mem: 3972 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.3007 data: 0.0040 max mem: 3972 +eval (test): [20] Total time: 0:00:30 (0.3603 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:29 time: 3.2805 data: 3.0433 max mem: 3972 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3532 data: 0.0043 max mem: 3972 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3215 data: 0.0041 max mem: 3972 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.3102 data: 0.0041 max mem: 3972 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.2864 data: 0.0037 max mem: 3972 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2765 data: 0.0035 max mem: 3972 +eval (testid): [20] Total time: 0:00:29 (0.3550 s / it) +evaluating best checkpoint: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/checkpoint-best.pth +eval model info: +{"score": 0.09856035437430787, "hparam": [50, 1.0], "hparam_id": 48, "epoch": 17, "is_best": true, "best_score": 0.09856035437430787} +eval (train): [20] [ 0/509] eta: 0:27:35 time: 3.2528 data: 3.0110 max mem: 3972 +eval (train): [20] [ 20/509] eta: 0:03:58 time: 0.3502 data: 0.0055 max mem: 3972 +eval (train): [20] [ 40/509] eta: 0:03:05 time: 0.2978 data: 0.0038 max mem: 3972 +eval (train): [20] [ 60/509] eta: 0:02:43 time: 0.2995 data: 0.0040 max mem: 3972 +eval (train): [20] [ 80/509] eta: 0:02:31 time: 0.3160 data: 0.0044 max mem: 3972 +eval (train): [20] [100/509] eta: 0:02:20 time: 0.3135 data: 0.0042 max mem: 3972 +eval (train): [20] [120/509] eta: 0:02:11 time: 0.3065 data: 0.0043 max mem: 3972 +eval (train): [20] [140/509] eta: 0:02:03 time: 0.3110 data: 0.0045 max mem: 3972 +eval (train): [20] [160/509] eta: 0:01:55 time: 0.2958 data: 0.0044 max mem: 3972 +eval (train): [20] [180/509] eta: 0:01:47 time: 0.2948 data: 0.0040 max mem: 3972 +eval (train): [20] [200/509] eta: 0:01:39 time: 0.3017 data: 0.0041 max mem: 3972 +eval (train): [20] [220/509] eta: 0:01:33 time: 0.3124 data: 0.0047 max mem: 3972 +eval (train): [20] [240/509] eta: 0:01:26 time: 0.3068 data: 0.0041 max mem: 3972 +eval (train): [20] [260/509] eta: 0:01:19 time: 0.3177 data: 0.0043 max mem: 3972 +eval (train): [20] [280/509] eta: 0:01:13 time: 0.3029 data: 0.0041 max mem: 3972 +eval (train): [20] [300/509] eta: 0:01:06 time: 0.3041 data: 0.0040 max mem: 3972 +eval (train): [20] [320/509] eta: 0:01:00 time: 0.3320 data: 0.0042 max mem: 3972 +eval (train): [20] [340/509] eta: 0:00:53 time: 0.3036 data: 0.0044 max mem: 3972 +eval (train): [20] [360/509] eta: 0:00:47 time: 0.3132 data: 0.0044 max mem: 3972 +eval (train): [20] [380/509] eta: 0:00:40 time: 0.2989 data: 0.0039 max mem: 3972 +eval (train): [20] [400/509] eta: 0:00:34 time: 0.3240 data: 0.0042 max mem: 3972 +eval (train): [20] [420/509] eta: 0:00:28 time: 0.3267 data: 0.0043 max mem: 3972 +eval (train): [20] [440/509] eta: 0:00:21 time: 0.3132 data: 0.0044 max mem: 3972 +eval (train): [20] [460/509] eta: 0:00:15 time: 0.3107 data: 0.0044 max mem: 3972 +eval (train): [20] [480/509] eta: 0:00:09 time: 0.3008 data: 0.0041 max mem: 3972 +eval (train): [20] [500/509] eta: 0:00:02 time: 0.3077 data: 0.0041 max mem: 3972 +eval (train): [20] [508/509] eta: 0:00:00 time: 0.2957 data: 0.0037 max mem: 3972 +eval (train): [20] Total time: 0:02:41 (0.3171 s / it) +eval (validation): [20] [ 0/85] eta: 0:04:37 time: 3.2624 data: 3.0112 max mem: 3972 +eval (validation): [20] [20/85] eta: 0:00:29 time: 0.3170 data: 0.0042 max mem: 3972 +eval (validation): [20] [40/85] eta: 0:00:17 time: 0.3377 data: 0.0039 max mem: 3972 +eval (validation): [20] [60/85] eta: 0:00:09 time: 0.3297 data: 0.0043 max mem: 3972 +eval (validation): [20] [80/85] eta: 0:00:01 time: 0.2920 data: 0.0042 max mem: 3972 +eval (validation): [20] [84/85] eta: 0:00:00 time: 0.2813 data: 0.0042 max mem: 3972 +eval (validation): [20] Total time: 0:00:30 (0.3548 s / it) +eval (test): [20] [ 0/85] eta: 0:04:27 time: 3.1431 data: 2.8948 max mem: 3972 +eval (test): [20] [20/85] eta: 0:00:28 time: 0.2996 data: 0.0039 max mem: 3972 +eval (test): [20] [40/85] eta: 0:00:18 time: 0.3645 data: 0.0047 max mem: 3972 +eval (test): [20] [60/85] eta: 0:00:09 time: 0.3112 data: 0.0036 max mem: 3972 +eval (test): [20] [80/85] eta: 0:00:01 time: 0.2936 data: 0.0041 max mem: 3972 +eval (test): [20] [84/85] eta: 0:00:00 time: 0.2821 data: 0.0039 max mem: 3972 +eval (test): [20] Total time: 0:00:29 (0.3509 s / it) +eval (testid): [20] [ 0/82] eta: 0:04:26 time: 3.2524 data: 3.0065 max mem: 3972 +eval (testid): [20] [20/82] eta: 0:00:30 time: 0.3538 data: 0.0050 max mem: 3972 +eval (testid): [20] [40/82] eta: 0:00:17 time: 0.3231 data: 0.0040 max mem: 3972 +eval (testid): [20] [60/82] eta: 0:00:08 time: 0.2995 data: 0.0041 max mem: 3972 +eval (testid): [20] [80/82] eta: 0:00:00 time: 0.2989 data: 0.0042 max mem: 3972 +eval (testid): [20] [81/82] eta: 0:00:00 time: 0.2888 data: 0.0041 max mem: 3972 +eval (testid): [20] Total time: 0:00:29 (0.3555 s / it) +eval results: + +| model | repr | clf | dataset | ckpt | epoch | lr | wd | hparam_id | hparam | split | loss | acc | acc_std | f1 | f1_std | +|:---------|:-------|:-------|:-------------|:-------|--------:|------:|-----:|------------:|:----------|:-----------|-------:|---------:|----------:|---------:|----------:| +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | train | 2.9882 | 0.12609 | 0.00168 | 0.06748 | 0.001232 | +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | validation | 3.0699 | 0.09856 | 0.0035191 | 0.053371 | 0.0025438 | +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | test | 3.0537 | 0.10853 | 0.0036946 | 0.05344 | 0.0023399 | +| flat_mae | reg | linear | nsd_cococlip | best | 17 | 0.015 | 0.05 | 48 | [50, 1.0] | testid | 3.0763 | 0.098516 | 0.0033195 | 0.048133 | 0.0021574 | + + +done! total time: 1:07:42 diff --git a/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/train_log.json b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/train_log.json new file mode 100644 index 0000000000000000000000000000000000000000..3833bcad5a043328457d15226f69b2c198df736c --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/nsd_cococlip__reg__linear/train_log.json @@ -0,0 +1,20 @@ +{"epoch": 0, "train/lr": 2.987987987987988e-05, "train/loss": 3.16375985622406, "train/grad": 0.07890527375042439, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1861962890625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.186094970703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.18593994140625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1857666015625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.185621337890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.18541259765625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.185191650390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1848828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.184495849609375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.18408935546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.183668212890625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.183082275390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.18254638671875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.181680908203125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.180760498046875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.179942626953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.179000244140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.177696533203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.17629638671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.17484130859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.173240966796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.171497802734375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.169481201171875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1672607421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.165137939453125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1627099609375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.160604248046875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1587548828125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.15645751953125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.154202880859375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.152371826171875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.150843505859375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1490380859375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.147562255859375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.14606201171875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.144771728515625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.143594970703125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.142633056640625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.14166748046875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.14078125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.14030029296875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.14013427734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.13998046875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.14007080078125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.140518798828125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.14121826171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.142061767578125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.143349609375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.144720458984375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01214025668334216, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012136608930304646, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.012130696992389858, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.012124824784696103, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01211870317813009, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.01211051563732326, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.012101294989697635, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.012090790094807744, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.012077076747082173, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.012062007845379412, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.012046829089522362, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.012024267446249723, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.012001787777990103, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.01196859904564917, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011936000431887805, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.011904477612115444, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.011863758899271487, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.01181471260264516, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.011758481808938086, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.01170460763387382, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.011635438995435834, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.011562397363595664, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.011480533508583904, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.011391231648158282, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.011298724126536399, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.011190419404301792, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.011097437171265483, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0110178649937734, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010917683204170317, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.01081298385746777, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010730799403972924, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010664482100401074, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010586581353563815, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010526681365445257, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01046506462385878, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010412553707137704, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010366926330607384, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010330597187858075, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010300427703186869, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010275417258962988, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010265169094782322, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010263504858594388, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01027015532599762, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010285196891054511, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010312248654663562, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01035116579849273, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010391372069716454, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010446627209894359, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010505135369021446, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.182356834411621, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.182055950164795, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.181563138961792, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1810529232025146, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.180546998977661, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.179889440536499, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1790969371795654, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1782596111297607, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1771273612976074, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.175922155380249, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.174758195877075, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.173001527786255, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1712939739227295, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1688382625579834, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.166492223739624, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.164263963699341, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1614255905151367, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1581594944000244, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1545586585998535, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.151287794113159, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1474533081054688, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.143735647201538, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.139922857284546, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.136305570602417, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.133146286010742, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1301512718200684, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1281988620758057, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1269631385803223, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1259849071502686, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1255695819854736, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1255862712860107, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.125788688659668, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.126218795776367, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.126685619354248, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.127239465713501, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.127718687057495, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1281044483184814, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.128286123275757, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1282880306243896, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.128175973892212, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1282055377960205, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.128480911254883, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1295151710510254, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1309151649475098, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1328485012054443, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1344501972198486, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1352438926696777, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1367695331573486, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.140007734298706, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.04964931709117756, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.049464747139165745, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.04983388704318937, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.04983388704318937, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05001845699520118, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.04928017718715393, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.050387596899224806, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.04928017718715393, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.04983388704318937, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.05057216685123662, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.05094130675526024, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.05370985603543743, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.05334071613141381, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.05260243632336656, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.05334071613141381, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.05629383536360281, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.05647840531561462, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.057770394979697305, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06127722406792174, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.061461794019933555, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06183093392395718, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06164636397194537, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.0636766334440753, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.06312292358803986, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06349206349206349, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.06349206349206349, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06330749354005168, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.062200073827980804, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.061461794019933555, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06404577334809892, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06312292358803986, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013552960305006348, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013528187085221832, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013370864014511317, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013379893952249857, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013621607264396806, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013474334897555883, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013935907193074845, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013782778225535981, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.014087057736882956, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.014474949349082883, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014782633221383417, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.015406849012142988, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.015610163884880242, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.015738159544793146, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.016034550177982516, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.017518967253733284, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01678206960122215, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.01573568328823401, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.01519269969402129, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.011928557300241907, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.011154579179233093, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010057858482389338, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.00871896848500733, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.008519832335619105, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.008019192795529576, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.009063094839011255, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.009461826290251453, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.009716075289845782, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.010272359310638997, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.01009042061607454, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.009454436041823014, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.009379359469445596, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.00945739806970246, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.009456679356161714, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.00948238630578792, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.00915521441588872, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.008617546453060865, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.008264569015516102, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0077246334980335075, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.00714611556127081, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.005931929236215205, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.005357884051895963, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.005372117400419287, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.005372928774151079, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.0055315567030503575, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.007302485629840765, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.01040305467479475, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.014350677684757243, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.018672744975558615, "id_best": 25, "lr_best": 0.00035999999999999997, "wd_best": 0.05, "train/loss_best": 3.1627099609375, "validation/loss_best": 3.1301512718200684, "validation/acc_best": 0.07198228128460686, "validation/f1_best": 0.009063094839011255} +{"epoch": 1, "train/lr": 8.993993993993998e-05, "train/loss": 3.1487721824645996, "train/grad": 0.07577714156359434, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.181024169921875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.18041259765625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.17942138671875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.17844482421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.17749267578125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1761376953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.174688720703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1731201171875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.171151123046875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.169039306640625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.167093505859375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.164310302734375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1616259765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.158275146484375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.155123291015625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1524853515625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.14939697265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.146195068359375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.14309814453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1407763671875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1382666015625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.136380615234375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.1347412109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1336376953125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.132679443359375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.13212158203125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.13181396484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.131751708984375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.131787109375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1320458984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1321826171875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.13247314453125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.13289794921875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.133214111328125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.133797607421875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.13435302734375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.13495849609375, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.13554443359375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.136351318359375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.137374267578125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.13811767578125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.13900146484375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.140440673828125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.14207275390625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1443359375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.14698974609375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.14965576171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.153472900390625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.158067626953125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.012055250331759453, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.012031398443505169, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011992789744399488, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.01195454471744597, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011916507766582072, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011865231348201633, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011808202979154884, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011745934337377549, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011666666585952043, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.011584663547109813, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.011506013805046678, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.011391859957948327, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.011284785836469382, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.011138053499162198, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.011007392352912575, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.010890485015697777, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010754150981083512, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.010610344300512225, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.01047144853277132, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010361912015359848, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010250249765813351, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010160713254008443, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010085192834958434, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010028602385427804, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009990556119009852, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009965414742473512, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009956277660094201, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00995559063507244, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009961719936691225, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00997575358254835, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009991755054797977, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010007491724099964, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010031418686266988, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01005573439411819, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010088227386586369, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010127263099420816, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010174536309204996, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010227000061422586, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010291794778313488, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010383176221512257, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01046362024033442, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010544780895579607, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010667755424510688, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01078493043780327, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010918568933848292, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011047051534987987, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011170026047620922, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011359011202584953, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.0115734111238271, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1766347885131836, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.175565004348755, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1737635135650635, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1720635890960693, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.170438766479492, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.168184280395508, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1657726764678955, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1631741523742676, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1599392890930176, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.156726837158203, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.153783082962036, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1497159004211426, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1461892127990723, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1417078971862793, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1380932331085205, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1352100372314453, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1322314739227295, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.12958025932312, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1275362968444824, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.126267910003662, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.125347852706909, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.124864339828491, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124664068222046, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1246449947357178, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1247167587280273, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.124868154525757, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1250429153442383, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1252493858337402, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1255879402160645, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1260814666748047, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.126600503921509, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.127126932144165, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.12782621383667, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1284430027008057, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1292061805725098, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1299657821655273, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1308600902557373, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1316442489624023, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1320881843566895, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.132005453109741, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.131972551345825, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1325182914733887, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1345953941345215, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.137983798980713, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1442272663116455, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.156038999557495, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1672463417053223, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1761929988861084, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1821579933166504, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.050387596899224806, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.04983388704318937, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.0518641565153193, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05370985603543743, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05389442598744924, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.051310446659283866, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.05094130675526024, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.056109265411590996, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.05666297526762643, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.057770394979697305, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.058693244739756366, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06109265411590993, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06035437430786268, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06736803248431156, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07142857142857142, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06939830195644149, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06755260243632337, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06552233296419344, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.060538944259874494, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.060538944259874494, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.059800664451827246, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.060723514211886306, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.06423034330011074, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.06109265411590993, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.060538944259874494, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.059431524547803614, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.067921742340347, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.067921742340347, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06386120339608711, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06662975267626431, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.014204114781438784, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014227107702357543, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.015025006878418545, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.01549309171223912, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015998630558119103, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.015278753923995046, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.015179610244537662, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.017487534432092725, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01648826926559927, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.015444990990139877, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.014671823039352256, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.013037260514762812, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.011342824958526766, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.010869407065527302, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.009933295253128279, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.008929241477037294, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.01008287647524087, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.010447709174720626, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.00990847124659941, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010318870290178672, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.010117774571403233, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00976317297293784, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.008864343703117986, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.00785329899600922, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.006696032696811901, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.0059199352213927395, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.00570658788961051, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005357687751168555, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005167969791408111, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.004967558799675587, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.004965832754227473, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.005334359780157588, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.005548365218196529, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.00808390816194172, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.011251557630031939, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.012352807407012972, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.01490820161572843, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.016213373790714528, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.01925592639082276, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.0219877123931773, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.022548873015672228, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.02016714980272763, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.01423517519862254, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.017332349347643106, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.02345710325556952, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.023041113279550607, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02106900468435845, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.015230853542603078, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.017917787135819443, "id_best": 17, "lr_best": 9.599999999999999e-05, "wd_best": 0.05, "train/loss_best": 3.146195068359375, "validation/loss_best": 3.12958025932312, "validation/acc_best": 0.07142857142857142, "validation/f1_best": 0.010447709174720626} +{"epoch": 2, "train/lr": 0.00014999999999999988, "train/loss": 3.1392265248298643, "train/grad": 0.07480087161064147, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.176866455078125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.175301513671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.172764892578125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.170521240234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.168172607421875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.165234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.162099609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.15880859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.154991455078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.151375732421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.148248291015625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.144117431640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.140806884765625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.13703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.13429931640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.132337646484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.130548095703125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.129093017578125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.128070068359375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1274951171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.1270263671875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.126851806640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126634521484375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1264599609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1263427734375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.12609130859375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12602294921875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.125880126953125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.125831298828125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.125865478515625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12585693359375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.125926513671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.126103515625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.12622314453125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.126544189453125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1268017578125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1272900390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.12786865234375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.128643798828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.129765625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.130452880859375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.131136474609375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.132406005859375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.134326171875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1377032470703123, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.14266357421875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1484527587890625, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.15716064453125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1655865478515626, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011833876841701568, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011776214526034891, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.011684006270952523, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011596539998427033, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.011513053779490292, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.011402142634615302, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.011281857797876, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.011156084714457393, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.011003879171330482, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010857609484810382, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010728536180686206, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.010561156934127212, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.010425525843165815, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.010269166100770236, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.010155680323950946, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.01007473231991753, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.010003198005724698, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009949391467962414, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00991658935090527, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009900720799341798, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00989392896881327, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009894833648577333, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009899125886149704, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009906310571823269, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.0099140611756593, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00992517793783918, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00993629704695195, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009948169575072824, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009965358218178153, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009989503195974976, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01001428063493222, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01004052026430145, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01007913674460724, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010118240416049957, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01017081605968997, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010230100320186467, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01030252849450335, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010382890675682575, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010483200689777731, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01062174532096833, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010730568952858448, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010828766440972686, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010974765727296472, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011135347650852055, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011360326849389821, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011652714796364308, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011943825618363917, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012316183773800731, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012626397632993757, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.168245553970337, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.166191577911377, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.16298246383667, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.159977912902832, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.157219648361206, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.153640031814575, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.150007486343384, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.146430253982544, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.142361879348755, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1387577056884766, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1358437538146973, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1324288845062256, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1300086975097656, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1276397705078125, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.126282215118408, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1255147457122803, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.124992847442627, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1247470378875732, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.124608039855957, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1245858669281006, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1245696544647217, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1245667934417725, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.124542236328125, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1245226860046387, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1245458126068115, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1245481967926025, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1245415210723877, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.124495267868042, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.124370574951172, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1240007877349854, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.123587131500244, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.123149871826172, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1225974559783936, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1222054958343506, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.121807098388672, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1216723918914795, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1221067905426025, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.123621940612793, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.126958131790161, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1332294940948486, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1382105350494385, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1406102180480957, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1414971351623535, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1415109634399414, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.139770984649658, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1374144554138184, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1404953002929688, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.155707836151123, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.174471855163574, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05260243632336656, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.051125876707272054, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.05463270579549649, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.05537098560354374, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.05721668512366187, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.05887781469176818, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0592469545957918, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06699889258028793, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06921373200442968, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.07013658176448874, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06995201181247693, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0695828719084533, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06293835363602805, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.062200073827980804, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06570690291620525, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07198228128460686, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07087486157253599, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07013658176448874, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07032115171650055, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07345884090070137, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07290513104466592, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07216685123661867, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07198228128460686, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07438169066076043, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07641196013289037, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.015570298339319956, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.015407461547531557, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.016867353344209423, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.015906234961716184, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.015747288979103654, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014998178007994358, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.013359759800536407, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012733579089912517, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.011306768631040362, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0113901645381869, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.01125506739035375, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.011991650149289287, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.01158380706824614, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.011089798085763962, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.01050506843850286, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010060183181757562, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.009359785552569, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00802032980671922, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.006746161489013494, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.006308475103908998, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005923806323451083, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.006007247290489164, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.00551102416307064, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005330646380462202, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.005566818365568341, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.006699886282786015, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.008635876097550824, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01082276377782955, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.011400713254496903, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.012817843648572788, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.012626414649650334, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.012898792402167717, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.012864769113165433, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.01384641575678351, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.014079416019995758, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.016949523364021096, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.019447607744284858, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.01985834574402651, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.020296109553393057, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.021746360275714915, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0206698032552273, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.02262220047909101, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.022576598462016113, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.02524745447478686, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.02783143276735027, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.027285298086900726, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02644784043131695, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.026735965832386955, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.028855902171725633, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.1655865478515626, "validation/loss_best": 3.174471855163574, "validation/acc_best": 0.07641196013289037, "validation/f1_best": 0.028855902171725633} +{"epoch": 3, "train/lr": 0.0002100600600600602, "train/loss": 3.135363667011261, "train/grad": 0.07399845886975527, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.166839599609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.164349365234375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.160654296875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1572119140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.154212646484375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.150516357421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.14688232421875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.143338623046875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13974365234375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.136668701171875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.13441162109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.131947021484375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.130458984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1290380859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12835693359375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.127957763671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.127667236328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12743896484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.127349853515625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.127266845703125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12697998046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.126943359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.126796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126671142578125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.126634521484375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.126409912109375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.12640380859375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.12623779296875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.126180419921875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.126064453125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12607177734375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.125941162109375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.125816650390625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1257080078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.12573974609375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.126026611328125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.126309814453125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.12660888671875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.12691650390625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.127381591796875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1279754638671875, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1291015625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1317474365234377, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1351385498046875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1401220703125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.145618896484375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1510675048828123, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1604962158203125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1714013671875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01139508532360196, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.011302347190212458, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01115617022383958, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.011020010518841446, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.01089526166440919, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010740012901369483, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010587512131314725, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010442942960653455, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.010287565630860626, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.010157525660470129, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.010059680580161512, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009955553794279695, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009891172104980797, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009837151148822158, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009812609925866127, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009802817781455815, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009799429373815656, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009801093738060445, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.0098066662135534, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009812409044243395, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00982019558083266, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009828845884185285, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009839751007966697, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009852620654273779, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009866837430745363, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009886947493068874, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009905991579871624, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009925123390275984, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009954006776679307, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009992528185248374, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010030748136341573, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010069839181378484, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010126207580324263, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010181285052094608, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010252249527256936, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010330555136315525, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010427532868925482, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010532745388336479, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010657884846441448, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010827638756018132, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010974136288277805, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011113999316003174, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01131265633739531, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011510145659558475, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.011756047396920622, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011996705532073975, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012226324235089124, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012605605777353049, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013013361049816012, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.158522605895996, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.155627489089966, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1513750553131104, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.147665023803711, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1444220542907715, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1405842304229736, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1370153427124023, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.133896589279175, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1308376789093018, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.128586530685425, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1270503997802734, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1256754398345947, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124953508377075, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1244471073150635, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1242551803588867, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1241564750671387, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1240673065185547, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.123974084854126, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.123866558074951, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1237430572509766, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.123629093170166, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.12353777885437, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.123417377471924, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1233158111572266, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.123274326324463, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1232659816741943, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1234068870544434, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.123692750930786, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1243896484375, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1255900859832764, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1268510818481445, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1279423236846924, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1290316581726074, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1295948028564453, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1297378540039062, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1293246746063232, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.128448486328125, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1272192001342773, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1254491806030273, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1233468055725098, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.124562978744507, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.129575729370117, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1397159099578857, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.150317907333374, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1620144844055176, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.173567533493042, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1770544052124023, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.18135142326355, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.190589666366577, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05463270579549649, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.057770394979697305, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.059616094499815434, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06127722406792174, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.062200073827980804, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.067921742340347, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06866002214839424, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06847545219638243, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06423034330011074, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0710594315245478, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.06976744186046512, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07124400147655961, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07069029162052418, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07013658176448874, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.0695828719084533, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.06866002214839424, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07308970099667775, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07272056109265411, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07087486157253599, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07161314138058324, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.015499771837901957, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.015617487577579983, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014835552953529911, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013844543323579811, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.012982671732601194, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.01219177352060106, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011848001805022051, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.013812509197686005, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.013430508191535661, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.012322474690678945, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.011480211582660617, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.01028819776531715, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.009625356874510958, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.007934913049904992, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00695234335097466, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0063278100199251645, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005942588702002434, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.0059850913415515974, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.006005687445089146, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005826572518993493, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005821841713848066, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.0056510810367752864, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006367013235189344, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.006822378434671153, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0070615042553818065, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.007128759940347382, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.006762946419563502, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.006239664524168993, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005684835904049113, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.006805674149040013, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.008129281506054796, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.010919640063666566, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.011757786777561882, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.011907757399755867, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.010652051585032551, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.011928830798618152, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.015024766269557774, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.016695879564829985, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.018335107384161893, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.021045109914405464, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.022653169702849293, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.022984741298908432, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.024458962104569177, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.025410714836127547, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.026544618138994017, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02727582163802954, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.030445924747809657, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.032424458237486034, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.032683834793471, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.145618896484375, "validation/loss_best": 3.173567533493042, "validation/acc_best": 0.07308970099667775, "validation/f1_best": 0.02727582163802954} +{"epoch": 4, "train/lr": 0.0002701201201201201, "train/loss": 3.134768842458725, "train/grad": 0.074395532310009, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.156781005859375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.15391845703125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.149771728515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1462646484375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.14335205078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.140133056640625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13724609375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13499267578125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.1329150390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.131484375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.130606689453125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.129969482421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12952880859375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1291845703125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.129090576171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.128765869140625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.128602294921875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12836181640625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12818603515625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12787353515625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.127633056640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12727294921875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.126881103515625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.126441650390625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.125875244140625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.125428466796875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.124991455078125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.124542236328125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.12401123046875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.12366455078125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.123487548828125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.12337890625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1234765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.12366455078125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.123890380859375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.12406494140625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.12448486328125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.125050048828125, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.1264764404296876, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1278680419921874, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.129754638671875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1341436767578124, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1404833984375, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1493231201171876, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1594451904296874, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.169326171875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.180501708984375, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1921795654296874, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.011007842088583858, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010884567217435687, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01070397867821157, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010553381976205856, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010425596062559635, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010277912095189095, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.010148422413039952, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.010042103086598218, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009945924011990428, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009882978682871907, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009847819828428328, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00982181403087452, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009812434099148958, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009810763092245907, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009813955861609429, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009818016251083464, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009824012671597302, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009831090338993818, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009839337556622923, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009848172659985721, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00985899314051494, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009871036761905998, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009884503928478807, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009900638638064264, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009918092638254166, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009940251805819571, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009961773143149912, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009983415931928903, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010015284409746528, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010058973715640605, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010104735093191266, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010151690852362663, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010222069979645311, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010290870305616408, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.01037737793289125, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010469702670816332, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.0105803098436445, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010702917308080942, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010861382470466197, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011093492363579571, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01127384540392086, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011427105711773038, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011663696034811438, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011920910398475825, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01222918827086687, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012589648785069584, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012917145290412008, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01322733549401164, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01365020964294672, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.148970603942871, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1457858085632324, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.141268014907837, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1376726627349854, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1347832679748535, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.131734609603882, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1292672157287598, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1273937225341797, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.125883102416992, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1249871253967285, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1244802474975586, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1241064071655273, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1239049434661865, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1236932277679443, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1235501766204834, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1233580112457275, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1231513023376465, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122934341430664, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1226534843444824, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1223857402801514, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122091293334961, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.12178373336792, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.121454954147339, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1211392879486084, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120832681655884, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1205263137817383, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.120387554168701, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1203176975250244, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.120492458343506, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1211917400360107, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.122282028198242, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.123706579208374, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1263375282287598, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.128971815109253, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1318626403808594, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.133790969848633, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.136085033416748, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1393651962280273, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.142469882965088, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1420865058898926, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.141515016555786, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1424760818481445, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1491470336914062, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.158348798751831, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1642355918884277, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1696057319641113, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.193938970565796, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.233289957046509, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2492129802703857, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.05887781469176818, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.062384643779992616, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06164636397194537, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07032115171650055, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07124400147655961, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.073827980804725, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07419712070874862, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06829088224437062, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.0695828719084533, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.067921742340347, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07087486157253599, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07272056109265411, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07161314138058324, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07216685123661867, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0695828719084533, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.06164636397194537, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.06312292358803986, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013951263377251092, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013736016522182757, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.01228908823988794, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.012389678810933174, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.014013865702007336, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.014257426055271803, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.012747713387649157, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.012233193675421743, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.01119343204024177, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.010257986946024436, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.009142383231649082, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.008316826017090849, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00724316820125842, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006980130434491742, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0068120420839149045, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006620494021010489, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006337312190546563, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.006399358051190493, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005648903326460431, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005506254746691801, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005970967103098202, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.006699839593002838, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.008161548071902737, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.010875145750701023, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.011211273503456133, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.011343126568026426, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.010172812636778356, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.00892922098132865, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.007946643061645931, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.00770406120096965, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.007900770646588557, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.01028561809983052, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.012088942242666373, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.017172017853012134, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.01924359140319737, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.020750765155678086, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.024871884311240783, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.026492084000652446, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02546250079440703, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.027227854729787462, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.027285354531899966, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.029583814891830772, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.029019836344846024, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0293587657290014, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.027935283271140633, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02674052256744519, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.026945360461637802, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.020674539868015113, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.028513911132605995, "id_best": 34, "lr_best": 0.0015299999999999997, "wd_best": 0.05, "train/loss_best": 3.12366455078125, "validation/loss_best": 3.1318626403808594, "validation/acc_best": 0.07419712070874862, "validation/f1_best": 0.01924359140319737} +{"epoch": 5, "train/lr": 0.00029891323817685334, "train/loss": 3.1309367990493775, "train/grad": 0.0745941874012351, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.148638916015625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.145609130859375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.14153076171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.138465576171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.136083984375, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.133779296875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.13201904296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.13075439453125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.129835205078125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129388427734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129033203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1287890625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12849365234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128255615234375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1279736328125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1278271484375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.127431640625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1271484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1267822265625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.126390380859375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.125994873046875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.125562744140625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.124962158203125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12444091796875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.12370361328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.122843017578125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.122095947265625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.121533203125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.12061279296875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.119735107421875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.119141845703125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.11856689453125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.11805908203125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.117735595703125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.117401123046875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.117183837890625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.117379150390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.117979736328125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.119488525390625, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.122276611328125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1251025390625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1279559326171875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1323663330078126, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.137547607421875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.1451788330078125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1538690185546874, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.163346862792969, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1779275512695313, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1916851806640625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010681015700101852, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.01055141209391877, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.01036980117438361, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010228960977401584, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.010120432486291974, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.010009230989962816, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009925667124334722, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009868008613120765, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009828171452973038, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009809098604600877, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009801671195309608, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009799755366984755, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009801048410590738, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00980418149381876, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009808267806656659, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009811803416814655, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009817283903248607, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009823769044596703, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009831265578977764, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009839077412616462, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009849045490846038, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009859634770546109, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009873974481597542, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009888882650993764, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009906532876193523, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009928845996037126, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009950357847847044, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009971195633988827, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010003132817801089, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010046268161386252, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010091385499108582, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010138550659175962, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010210734049323947, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010283013181760907, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010377455588895827, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010481534912250935, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010614226474426686, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010764129683375359, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010948704045731575, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011198164969682694, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011411552052013576, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01161358220037073, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011904460161458701, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012185089718550444, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012568751752842217, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012997763413004577, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013370649523567408, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013835279955528676, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014214583104476333, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1413776874542236, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1383049488067627, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.134348154067993, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1314809322357178, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.129427433013916, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1274938583374023, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1261751651763916, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.125352621078491, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1248395442962646, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1245994567871094, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1244866847991943, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124401569366455, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124333381652832, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.124236822128296, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.124084711074829, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123974084854126, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.123785972595215, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1235311031341553, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1231870651245117, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.122847557067871, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1224348545074463, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.122013807296753, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1215505599975586, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.121088743209839, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1207172870635986, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.120382070541382, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1201348304748535, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.119994878768921, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.119960308074951, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1200122833251953, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.120161771774292, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1201882362365723, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.12022066116333, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.120248794555664, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.120363473892212, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.12045955657959, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1206297874450684, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1214499473571777, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1224844455718994, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.123218536376953, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.125939130783081, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.130330801010132, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.134934425354004, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1349477767944336, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1369659900665283, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1587042808532715, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.2004282474517822, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.227022409439087, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2359676361083984, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06312292358803986, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06699889258028793, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.073827980804725, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07604282022886674, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07567368032484312, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0725359911406423, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07364341085271318, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07327427094868956, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07641196013289037, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07493540051679587, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07585825027685493, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0769656699889258, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07585825027685493, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08084163898117387, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012733972883489514, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012873972736108547, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.014364590650744543, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.014088851700690942, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.013191044608064348, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.013217236052350805, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.011240445033668897, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.010831343141763804, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.008611456378251519, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.007837804174081813, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.007564612396987175, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006599614211242934, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.0065095789230009546, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006600799418486527, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0062482512146941685, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005535486075764897, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005161885396782485, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005172794237128182, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005176977048755833, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005182381751227386, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005334972943266247, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.005894731197710033, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.006007744774802746, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.006003851991124398, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.005843611625046707, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.005721568642916958, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.005726575869975219, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.005921616053643399, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.005982094505836893, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.006673710707248804, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.007205116104647958, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.00950763078104329, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.013071106614449907, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.018542079079751146, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.02186732688594188, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.02371146465652484, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.024884007024048808, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.02580145699334434, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.029311673815420197, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.02838544369923381, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.026941828150143527, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.029498196434806195, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.029539921415698975, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03264681273500506, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.02929157602760495, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.02493438606879851, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02365611139783731, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.02223284778624879, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.028043127413199212, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 3.1916851806640625, "validation/loss_best": 3.2359676361083984, "validation/acc_best": 0.08084163898117387, "validation/f1_best": 0.028043127413199212} +{"epoch": 6, "train/lr": 0.0002924170901991409, "train/loss": 3.1229151463508606, "train/grad": 0.07354222083464265, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.14146484375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.138582763671875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1349755859375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.132293701171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130548095703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1288525390625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12775390625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127047119140625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.126514892578125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.126219482421875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126004638671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12578857421875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12554931640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12533447265625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12508056640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12481689453125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.124544677734375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.124124755859375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1237158203125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.123441162109375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12277099609375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1223046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.121781005859375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.12103759765625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.120380859375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.119393310546875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.118624267578125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.11772216796875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.116671142578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.115230712890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.11387939453125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.1127001953125, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.11097412109375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.109593505859375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.107923583984375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.1064056396484374, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.1052618408203125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.104432373046875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.1042279052734374, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.10469482421875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1060369873046874, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.107904052734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.1113946533203123, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1164752197265626, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.124515380859375, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1363189697265623, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.149364013671875, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1617431640625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.170428466796875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01031664591981098, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010189409407321364, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010031606422271579, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009920553690753876, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009843336096964776, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009775595329701901, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009733481663279236, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00971118912100792, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009699136859271675, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00969676065724343, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009696953329257667, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009699277265463024, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009701858886983246, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.00970629334449768, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009710590031463653, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009714639896992594, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.00972067926544696, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009727484728209675, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009735681694000959, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00974417728604749, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009754537944681943, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00976639037951827, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009781143346335739, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009798478407319636, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009817934355232864, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009843952530063689, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009869917631149291, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00989518512506038, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00993299291934818, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009983202086295932, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010032473022583872, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010079975759144872, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010149416963104159, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010214598765596748, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010297614100854844, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010391485444270075, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010506486666854472, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010633643630426378, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010787561838515102, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011005370873026549, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011198249901644886, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011385173951275647, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011665176548995078, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011957106557674705, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.012360586447175591, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012864594829734415, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013325239294208585, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013663538731634617, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013919597114436329, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1360576152801514, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1333706378936768, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.130164384841919, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1280691623687744, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1267030239105225, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.125608444213867, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1249492168426514, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1246213912963867, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.124455213546753, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1244001388549805, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1243879795074463, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.124405860900879, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.124431610107422, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.124488115310669, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.124528169631958, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1246204376220703, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1246938705444336, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.124788761138916, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1248421669006348, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1248748302459717, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1248528957366943, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1248176097869873, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1247057914733887, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.124647378921509, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.124626636505127, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1247594356536865, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1251275539398193, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1255900859832764, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.12640380859375, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1274430751800537, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1282155513763428, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1285085678100586, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.127959966659546, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1263809204101562, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1234397888183594, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.120241165161133, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1173317432403564, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.115917921066284, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1170973777770996, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.124589681625366, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1354928016662598, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.143308401107788, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1431000232696533, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1430892944335938, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1512842178344727, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1766810417175293, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.203024387359619, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.225804090499878, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.2270376682281494, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06570690291620525, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06921373200442968, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.06330749354005168, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.06349206349206349, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.06459948320413436, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.06681432262827612, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.06976744186046512, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07069029162052418, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07142857142857142, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07050572166851236, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07401255075673681, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07807308970099668, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.0754891103728313, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0710594315245478, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07308970099667775, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07733480989294943, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012860469284653397, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.014194422721435488, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.013907131405171686, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.013143148408451774, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.01224676195358889, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.011127788711010613, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008996521420946119, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00795822509060322, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006783524896915309, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006350998400325464, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005991273482124792, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006044956910899878, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005504084948006049, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005157486740963505, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005154526666458385, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005167269003630184, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0049573838928509304, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.004956521739130435, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.004970150118819915, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.004968422272437568, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.004968422272437568, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.004969286045433472, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.00521047809428619, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.005208245356915153, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.005205473086398855, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.00520529635576004, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.004963245933900562, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.004963245933900562, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.004962384259259259, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.004963245933900562, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.004963245933900562, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.004963245933900562, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.004963245933900562, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.005333919348460961, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.008223238447522126, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.012937804858933916, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.01696186648276197, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.0196277274251295, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.02101689315027108, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.021640839733918, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.02084300899374755, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.02169423927824458, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.0228360026049552, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.02729853721618501, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.029701427397972453, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.026321771859223728, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.02422459723865385, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.027574975451682332, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.036628790448876465, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.124515380859375, "validation/loss_best": 3.1512842178344727, "validation/acc_best": 0.07807308970099668, "validation/f1_best": 0.029701427397972453} +{"epoch": 7, "train/lr": 0.00027969249556793234, "train/loss": 3.119657497406006, "train/grad": 0.07420098558068275, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.137318115234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.134912109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13213623046875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13039794921875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129317626953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128323974609375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.127779541015625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127486572265625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127215576171875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12695068359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126739501953125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12640869140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.126153564453125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.125687255859375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.125220947265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12487060546875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12436279296875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12364501953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1229833984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12230224609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.121436767578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12057373046875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.119725341796875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11875732421875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.117711181640625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1164990234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.115401611328125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1144970703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.113065185546875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.1115625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.110198974609375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.109058837890625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.107281494140625, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.105743408203125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.103846435546875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.102078857421875, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.10016845703125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.09875, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0978790283203126, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0984857177734373, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.1000286865234377, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.1018695068359374, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.10559326171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.1111895751953127, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.11887939453125, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1269744873046874, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.135023193359375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.1485394287109374, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.1621893310546874, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010248459076974541, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010138432716485114, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010007352721877395, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009925013689789921, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009874520213343204, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009836147252935917, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009815374386962504, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009806473187636585, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009803019084502011, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00980360820889473, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009804892051033676, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00980681082000956, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009809560582507402, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009813193178270013, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00981634199153632, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009819082978647203, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009823329329956323, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00982789532514289, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009833232320379465, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009839510107412934, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009847202221862972, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009856759426184, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00986803657375276, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009881489267572761, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009898107193876057, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009921408307272941, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009945548728574068, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009969192000571638, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010006427282933146, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010058569186367095, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010112888941075654, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010169988255947829, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010256723775528371, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010342990593053401, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010451921082567423, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010567456639837474, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010698051122017205, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01083102069562301, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010992226137313993, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.011229865830391645, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01141953476704657, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011586268781684339, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.011842391572427004, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.012118183982092887, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01246482875198126, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012848115358501673, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.013180390787310899, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013621031926013528, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.014028153903782368, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1323916912078857, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1301727294921875, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1277353763580322, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.126302719116211, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.125485897064209, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124876022338867, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1245810985565186, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1244401931762695, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1243531703948975, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.124288320541382, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1242048740386963, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1240806579589844, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1239473819732666, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1237409114837646, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1235179901123047, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123305320739746, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1230194568634033, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1226918697357178, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.122340202331543, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1220388412475586, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1216909885406494, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1214001178741455, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.121077537536621, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1207468509674072, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1204473972320557, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1201276779174805, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.119929313659668, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.119832754135132, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1197636127471924, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1197516918182373, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1195642948150635, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1191534996032715, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.118333101272583, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.117623805999756, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.117598056793213, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1186602115631104, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1210029125213623, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.123826265335083, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1272852420806885, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.131554126739502, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.135133981704712, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.137706756591797, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.139686346054077, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1462295055389404, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1604957580566406, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1726155281066895, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1785519123077393, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1723592281341553, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.180856227874756, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06829088224437062, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06773717238833518, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06662975267626431, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0681063122923588, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06884459210040605, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.07161314138058324, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.07235142118863049, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.07272056109265411, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.07364341085271318, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.07327427094868956, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.07179771133259505, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.07124400147655961, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07124400147655961, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07124400147655961, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07345884090070137, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07567368032484312, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08157991878922112, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.08342561830933924, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08527131782945736, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07715023994093761, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07751937984496124, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07899593946105574, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07788851974898486, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07881136950904392, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08231819859726837, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08047249907715023, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07659653008490218, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07622739018087855, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0799187892211148, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0769656699889258, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.014249027540601597, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.013550229273458947, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.012648805357400818, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.010880538887182658, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.010078789748428813, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00899382770950261, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.008164906650747213, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006829925594855856, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0067483287617456054, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00653288740245262, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006244841373347007, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006754708075979715, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.007560531521167289, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.008477660474961445, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.010153193737070533, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.010696094016999273, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.011306918329879135, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.012389259070511716, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.011408944739142493, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010711738045478066, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0102441031519614, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.010234083433767863, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.009928749420178856, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.00851670513997999, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.008061205150256575, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.007188543618648528, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.00704251388306339, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.007052014993343736, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.007146862431569866, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.008368000289290066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.01149390132968045, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.01466174832128529, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.018857471755396617, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.022033949419740986, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.0250167850269955, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.028299021675232777, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03108422259291056, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03170317712370723, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.031005577678112392, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03141272474406225, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.029741101858553068, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.027565766800387678, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.028025975090071403, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0332595262547764, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03412515236322495, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03255432039780412, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.0337598487709879, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04084711473963363, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.0390316359208211, "id_best": 35, "lr_best": 0.0018, "wd_best": 0.05, "train/loss_best": 3.102078857421875, "validation/loss_best": 3.1186602115631104, "validation/acc_best": 0.08527131782945736, "validation/f1_best": 0.028299021675232777} +{"epoch": 8, "train/lr": 0.0002612959497061927, "train/loss": 3.1158024168014524, "train/grad": 0.07455356819555163, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1360400390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.134132080078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.13207275390625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13093505859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.13016845703125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12965576171875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129285888671875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.129029541015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.128690185546875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.128370361328125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12815185546875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.127796630859375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12751708984375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12700439453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1265185546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12609619140625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.125625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1249951171875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.124229736328125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12351806640625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12274169921875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1217529296875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.12072998046875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.119542236328125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.11823974609375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.116705322265625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.11532470703125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.11405517578125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.112349853515625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.110225830078125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.1083642578125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.106707763671875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.1043597412109376, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.1022283935546877, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0998602294921875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0977630615234375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.09597900390625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0946917724609375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.09351318359375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0916668701171877, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0901470947265626, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0894805908203127, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.090067138671875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.092225341796875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.096899108886719, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.1049838256835938, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.1135552978515624, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.124479064941406, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.135849609375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.010263529943767936, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.010170655841939151, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.010068328003399074, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.010011110547930002, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009978836295194924, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009956318503245711, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009945955532602966, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009941920191049575, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009941493882797659, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009943275738041848, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00994506545132026, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.00994834718061611, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.00995164448628202, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009957175888121127, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009962330076377838, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009967889187391847, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009974770285189151, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009983460437506437, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009993380319792777, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.010003311156760902, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.010014809654094278, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.010027715098112821, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.010042446397710592, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.010059990724548697, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.010079198074527085, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.010105519851204009, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.010132410023361444, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010160255460068584, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010202700120862574, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010259964202996344, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.01031532488996163, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.01036790682002902, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.010441989083774387, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01051141970558092, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010597919796127826, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01069396487204358, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.01080810722662136, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010927159984130413, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.011054803426377475, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01121243288507685, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.011348846815526486, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011496773816179483, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01172963690944016, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011936305649578571, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01219607365783304, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012511435251217335, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01281645879149437, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.013231388367712498, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013616735562682152, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.129875898361206, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1280720233917236, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.126220941543579, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1252448558807373, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124727487564087, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1243584156036377, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124178409576416, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1240339279174805, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1239137649536133, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123784065246582, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.12365460395813, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1234524250030518, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.123253107070923, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1230037212371826, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1227567195892334, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.12253999710083, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1222848892211914, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.121987819671631, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.121674060821533, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.121398687362671, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.121103048324585, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1208248138427734, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.120604991912842, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.120441198348999, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.120389699935913, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1204376220703125, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.120534658432007, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1206719875335693, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.120824098587036, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1207876205444336, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1204311847686768, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.119724988937378, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1182310581207275, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1163899898529053, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.113980293273926, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.112520933151245, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.112757444381714, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1145310401916504, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1164867877960205, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.118130922317505, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1186273097991943, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1188507080078125, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.1185109615325928, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.114250898361206, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1100704669952393, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.116051197052002, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1235194206237793, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.120915412902832, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.12207293510437, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06736803248431156, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06755260243632337, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06256921373200443, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06496862310815799, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06902916205241787, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.073827980804725, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07881136950904392, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08047249907715023, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07899593946105574, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07862679955703211, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07862679955703211, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.082687338501292, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08231819859726837, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08379475821336287, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08324104835732743, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07881136950904392, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.082687338501292, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08600959763750461, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08379475821336287, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.013529259013400302, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.012574594514356434, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010863845652903588, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00974102072652595, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008474284927098763, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.007254293281997893, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006721189773119761, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005909993735745558, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005975303607610261, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.00603157123963377, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005866819545258692, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.0055332683951548264, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005147674160457092, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005171261240151344, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005170636398473636, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005171135783231614, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.004966021955044433, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.00497642744892614, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.005193559288396296, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005203523594328192, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007779019012557783, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009293886887113058, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.01008765447660602, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.011920039409737933, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013105859120541996, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01311988696448021, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.012854603715505711, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.013876437364827956, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.014598707507077863, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.016345228783896066, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.019263289711069814, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.020161017482081305, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.021547958965219893, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.023996758505214977, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.026140391307000698, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.02989688602036389, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.029808295320924053, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.029138192977070387, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.027771335100717203, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.030506780242002245, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.033705387851517624, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.037682383062792, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03676753761972624, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.036504193533343395, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03880086614538075, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03605051951223955, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.039708830814418554, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04418910079053943, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05045069723853678, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.124479064941406, "validation/loss_best": 3.120915412902832, "validation/acc_best": 0.08600959763750461, "validation/f1_best": 0.04418910079053943} +{"epoch": 9, "train/lr": 0.00023803200426111704, "train/loss": 3.1105807328224184, "train/grad": 0.07179782703518868, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13461181640625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13314208984375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131710205078125, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1309130859375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1305419921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.130245361328125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.130040283203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.129906005859375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12970458984375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.129427490234375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.129193115234375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128863525390625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.128468017578125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.128060302734375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12744140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.126998291015625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12640380859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.125625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.124720458984375, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.123878173828125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.122750244140625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.121712646484375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.120322265625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.11878662109375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.117164306640625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.115096435546875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.113209228515625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.11138671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.10885009765625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.10575927734375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.102886962890625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.100357666015625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.096982421875, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0941015625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0905938720703126, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0871722412109377, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0838702392578123, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0812078857421876, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.078753662109375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.07669921875, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.075972900390625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.07584716796875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0767431640625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.078885498046875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0824493408203124, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.087655334472656, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0938262939453125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.104405822753906, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.11511474609375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009845217955298722, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009774252297356725, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009705804563127458, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009673567591235041, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009659582700114697, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009652442035730928, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009650605975184589, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009650768814608454, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.0096520676324144, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009653996671549975, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00965530369663611, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009658154312055557, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009661062532104551, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009664891583379359, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009668950848281383, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009672193822916597, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009676519776694476, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009682121332734822, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009687253807205707, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009692605223972351, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00969896885799244, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009706326185259968, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009715687730349601, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009727146555669607, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009740627438295632, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009759361478500069, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009777075855527072, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009794183778576554, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00981816227780655, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009850069794338197, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009882420934736728, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009916176972910761, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009969344302080572, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.01002385826781392, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010096423756331206, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.01018086747964844, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010289201815612613, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01040567407850176, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01054118286119774, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010721128529403358, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010881344289518893, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011032728331629186, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01125707701779902, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011491114229429514, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01177224682411179, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012030053464695812, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012286253336351366, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.01269111800007522, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.013039708784781397, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1283037662506104, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1268694400787354, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1254804134368896, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124807834625244, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1244614124298096, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1242311000823975, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1241092681884766, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.12399959564209, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123875379562378, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1237504482269287, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123605728149414, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.123436212539673, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1232616901397705, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.123002529144287, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.122739791870117, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1225244998931885, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.122227191925049, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1218926906585693, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1215267181396484, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.121181011199951, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1207942962646484, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.120346784591675, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1198346614837646, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.119272232055664, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.11865496635437, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.117889642715454, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1172027587890625, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1165754795074463, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.11575984954834, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1148204803466797, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.113868236541748, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.112799882888794, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.110891103744507, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.108797073364258, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1063191890716553, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1043851375579834, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.1033875942230225, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.1037449836730957, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1052160263061523, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.107365608215332, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1091530323028564, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1122357845306396, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.119335651397705, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1284584999084473, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1408615112304688, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.150768518447876, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.150834083557129, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1389987468719482, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.134855031967163, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06939830195644149, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06847545219638243, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06626061277224068, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.062200073827980804, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06386120339608711, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06441491325212255, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.0636766334440753, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06404577334809892, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06736803248431156, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07142857142857142, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07327427094868956, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0812107788851975, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08508674787744555, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08748615725359911, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08637873754152824, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08711701734957548, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08508674787744555, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0812107788851975, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08084163898117387, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08028792912513842, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08231819859726837, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07807308970099668, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07659653008490218, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07511997046880768, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012917744118474439, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011973315918662958, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.010291480147041494, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.009467640255661037, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.008148889442469581, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0070650631257571555, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006967464623580962, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006429336996805951, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006038460631577511, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.006053864711480595, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.006057145582369367, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.006070971957709872, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.006084608994897354, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.006094500436314706, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006226322990727104, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006326358885989327, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.0071734559766474665, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007759507519921525, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.00879689749162769, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.010935535962268825, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.011905567332114085, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.012449151076333672, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.013803263614138653, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.015323314153039934, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.01626415577573596, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.017030688144794744, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01732625151739241, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.018810173352371576, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.022853572234012617, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.02730811651230838, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.029142283332183886, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.031089261119596156, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.032402800307851636, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.032819721497259764, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03412443372045335, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03788441362129578, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03988750521505151, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.043226126933048566, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.0459636873572395, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04391963750524206, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04335142433750803, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.040798910475543175, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.036148448693739, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.03508786913904038, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.03524949576893355, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03700570314194243, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03565666456702399, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04363955748874607, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.048980996040190454, "id_best": 38, "lr_best": 0.00294, "wd_best": 0.05, "train/loss_best": 3.078753662109375, "validation/loss_best": 3.1052160263061523, "validation/acc_best": 0.08748615725359911, "validation/f1_best": 0.0459636873572395} +{"epoch": 10, "train/lr": 0.00021091808096876188, "train/loss": 3.1070060765743257, "train/grad": 0.07290893020108342, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.1333349609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13206787109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.131033935546875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.13043701171875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.130069580078125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.129864501953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.129571533203125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12940673828125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12915771484375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1287841796875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12857177734375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.128162841796875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12771484375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12715087890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.126546630859375, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.125926513671875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12525146484375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12432861328125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.123380126953125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.12238525390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12114990234375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.120047607421875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.118519287109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1168310546875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1150537109375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1128955078125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.11081298828125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.108734130859375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.106131591796875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.102847900390625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.09980224609375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.096888427734375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0929754638671874, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.089686279296875, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0857342529296874, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.081976318359375, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.078135986328125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0748248291015625, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0716571044921874, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0688336181640623, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.06753173828125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.06703125, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0675811767578125, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0692193603515623, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.07299560546875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.078502197265625, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.084586181640625, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0948782348632813, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.104289855957031, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.01000992748187855, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009949872193392367, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00989539796486497, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009871243250090629, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00986035973066464, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009854982402175664, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009852907338645309, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009853447847999632, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009854852738790214, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009856399674899876, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009858260087203235, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009860685574822128, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009863543098326773, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.0098673266870901, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.0098707988508977, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009874530651140958, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009879441978409887, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009885203305166214, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009891810619737953, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009898452202323825, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009907066347077489, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00991539414273575, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009926193507853896, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009937678310088814, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009951767718885094, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.00997043524403125, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009989008733537048, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.010007888975087554, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.010033354689367115, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.010067666447721422, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.010099583691917359, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.010130317925941199, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.01017664847197011, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010222999963443726, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010283499746583403, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010351923385169357, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010435417687986046, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.01052274598972872, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010630039777606726, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010786506303120405, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01092604177305475, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.011069154122378678, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01128711640369147, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011514803455211222, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.0118124008923769, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.012118531437590719, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.012386900437995792, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.012755948607809842, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01301265981514007, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1272897720336914, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.126140832901001, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1250534057617188, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1245782375335693, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124356269836426, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124192476272583, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1241066455841064, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1240298748016357, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1239254474639893, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123849391937256, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.12375807762146, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1236207485198975, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1235265731811523, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1234018802642822, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.123262405395508, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.123155355453491, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1230342388153076, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.122894048690796, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1227617263793945, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.122645378112793, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.122488021850586, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1223020553588867, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1220991611480713, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.121804714202881, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.121474027633667, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.121053457260132, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1207401752471924, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.120514154434204, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1203601360321045, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.120480537414551, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1209566593170166, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.121737241744995, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.123178482055664, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.12467098236084, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.1264545917510986, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1279830932617188, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.12872052192688, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.127375602722168, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1232919692993164, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.117170810699463, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.1140894889831543, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.113196611404419, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.115623712539673, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1195101737976074, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1217336654663086, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1179633140563965, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1118528842926025, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1146035194396973, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1429710388183594, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06976744186046512, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06866002214839424, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06496862310815799, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06533776301218161, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.067921742340347, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07161314138058324, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.073827980804725, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07641196013289037, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08028792912513842, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07475083056478406, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07475083056478406, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07438169066076043, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07659653008490218, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07936507936507936, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.07973421926910298, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.07825765965300849, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.07751937984496124, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.07678110003691399, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.07899593946105574, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08176448874123293, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08305647840531562, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08047249907715023, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01332579381540582, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.011445685532036412, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.009893002593221898, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.008462831391670521, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.007257076285118577, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.0069170179429475466, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006328057262549325, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005932959637792421, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.006000313485765786, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005876848803902472, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005357169626260291, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005372241249829633, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00517088461903021, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005183194838367252, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005184061924297015, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.004978807408697672, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005172867612874997, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005380546669534089, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0059573559966578675, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005884934580672838, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0060187069832738525, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.007083910454300822, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.00923783303349246, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.010213309780326035, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.011807871099581453, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.012824771342204208, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.014756323453293753, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.017538616105276295, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.018908701251651092, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.021600150080562052, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.022799059190411187, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.022346125342477995, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.025072402451360956, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.0255162088874204, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.028164036873545368, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03136544704170018, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.030569380387071392, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03130926510656384, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03309530878025118, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03481867505595083, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03734767073447922, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.039315773906894835, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.035309933766650405, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.030828785319436624, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.029607366146570797, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.035712193748738456, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04192244958746446, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04412774782794197, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03878435677448686, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.0948782348632813, "validation/loss_best": 3.1146035194396973, "validation/acc_best": 0.08305647840531562, "validation/f1_best": 0.04412774782794197} +{"epoch": 11, "train/lr": 0.00018113997589164516, "train/loss": 3.103894673585892, "train/grad": 0.0708762470446527, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13443115234375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.133641357421875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.132896728515625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.132607421875, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.132408447265625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.132193603515625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.131968994140625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.131710205078125, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.13140869140625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1310302734375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.130614013671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1300439453125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1295556640625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12878173828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12804931640625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12745361328125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.126495361328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.125430908203125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12422119140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.123074951171875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.12160400390625, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.12022705078125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.118399658203125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.116558837890625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.11459716796875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.112030029296875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.109757080078125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.1074853515625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.10461181640625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.100975341796875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.097637939453125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0947479248046874, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0906689453125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.087015380859375, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.082889404296875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0787469482421876, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0745843505859374, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0708978271484373, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.067099609375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.06319580078125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.06078125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.05919677734375, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0579693603515623, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.057510986328125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0577142333984373, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0589389038085937, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0618057250976562, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0682186889648437, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0769580078125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009817939039785416, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009771297133993358, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009734370929654687, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009719054270535708, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009713652385398746, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009711407620925457, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.0097114192484878, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009712062149774284, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009712981567718089, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00971409656573087, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009715042093303055, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009717008851002901, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009718417732510715, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009721088253427298, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00972341300919652, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009725912041030824, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009729566210880876, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009733320688828826, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009737608637660742, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00974228628212586, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009748112650122494, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009754667298402638, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009762839111499489, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009772872435860336, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.00978394747711718, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009799980816897005, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009814711993094534, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009829272548668087, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009849768148269504, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009873709257226438, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009896483719348908, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009917884338647128, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009950565183535218, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009984593547414988, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010030977372080087, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010085482611320912, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010153064401820303, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010223442825954408, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01030659483280033, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010427183993160725, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010536918847355992, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010653030877001583, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01083187394309789, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.011004332611337304, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01119855560362339, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.011380799766629934, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011539679889101534, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011797691527754069, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.012121290410868823, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1266369819641113, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1256754398345947, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1248607635498047, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124492883682251, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124316930770874, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241953372955322, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1241140365600586, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1240122318267822, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1238925457000732, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1237728595733643, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1236560344696045, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1234402656555176, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1232621669769287, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1229841709136963, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1227025985717773, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122424602508545, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1220703125, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1216511726379395, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.121185064315796, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1207809448242188, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1202657222747803, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1197667121887207, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1192357540130615, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1186771392822266, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.118082284927368, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.117414712905884, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1168150901794434, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1163017749786377, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.11572003364563, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1151251792907715, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1146793365478516, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.114185333251953, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1134729385375977, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.112542152404785, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.111177444458008, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.1096508502960205, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.108419418334961, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.108125925064087, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.1095945835113525, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.1147990226745605, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.120471477508545, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.1253366470336914, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.128127336502075, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.1250462532043457, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.1194889545440674, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.122408151626587, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1343705654144287, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1594276428222656, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1881542205810547, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.07013658176448874, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06441491325212255, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06459948320413436, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06607604282022887, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.067921742340347, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06866002214839424, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06976744186046512, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07087486157253599, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07290513104466592, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07807308970099668, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08010335917312661, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08139534883720931, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08324104835732743, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08361018826135105, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08490217792543374, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08231819859726837, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08545588778146918, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08656330749354005, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08564045773348099, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08859357696567, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08785529715762273, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07807308970099668, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07087486157253599, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.012989994009769528, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.01137880950108503, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008884515346730747, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.00795434747407667, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.00711789463531205, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006457549020229075, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0062102087286028005, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005972816638355955, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005838757916959887, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005696326832271573, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005342592228371597, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005357180777643286, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005181063589061803, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005372307402088376, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005691059283123998, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006900028857558869, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.007291497890272721, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007607686430528012, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.008455460372113997, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.009016797830551643, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.009597593280353553, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009698836761943557, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.009716160714468064, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.010116272828120207, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.01084418977349195, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.011392934388571469, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.012456024172843728, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01396003606834098, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.015739004463910116, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.01777982754690562, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02131185818084186, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.02351401126088608, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.026898391804698062, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.030856883350113395, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03256845165077627, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03300720799223155, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03507413246012763, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03659173034193697, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03716546491979991, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.038682073602216545, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.036608503398250745, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03857632439863797, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.03960060217170696, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.0406960778760744, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04479777090727327, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.044187503470317864, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.043424142565195334, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.03808027487382021, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03328789223352036, "id_best": 45, "lr_best": 0.0093, "wd_best": 0.05, "train/loss_best": 3.0589389038085937, "validation/loss_best": 3.122408151626587, "validation/acc_best": 0.08970099667774087, "validation/f1_best": 0.044187503470317864} +{"epoch": 12, "train/lr": 0.0001499999999999999, "train/loss": 3.0958834433555604, "train/grad": 0.06994258908554912, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.12944091796875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.128433837890625, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127388916015625, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1269970703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1266015625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126270751953125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.1259521484375, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.125601806640625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.125169677734375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124825439453125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.1244482421875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.123853759765625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.123411865234375, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.122578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.121873779296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.121072998046875, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12021728515625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.119166259765625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1179150390625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11676025390625, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.115194091796875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.113662109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.111905517578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.109879150390625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.107783203125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.105113525390625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.102689208984375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.100379638671875, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.0972265625, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.0934423828125, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.089940185546875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0867919921875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.082406005859375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0787353515625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.07427734375, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0701275634765626, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.065772705078125, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0618646240234373, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.05802734375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0534454345703126, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0500726318359375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.047633056640625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0452569580078124, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.044127197265625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0440545654296876, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.04574951171875, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.04842041015625, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.054296569824219, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.062037353515625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009705995556432754, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009665867045987398, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009633036425802856, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009620050541125238, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.00961499850731343, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009612822798080742, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009612195743247866, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009612534360494465, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009612963132094593, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009613991777878255, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009615269834175705, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009616766730323434, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009617901684250682, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009619819691870361, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009622224881313741, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009624617288354785, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009627443626523019, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009630639073438942, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00963465987239033, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009638866151217371, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009644750815350562, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009650302852969616, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00965683656744659, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009665411007590592, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009675852877553553, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009689658498391509, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00970330223441124, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00971737839281559, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009740144365932792, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009768970883451402, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009797023772262037, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009823652713093907, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009861426874995232, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009897040012292564, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009943891649600118, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009996137828566135, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010057114730589092, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010123235690407455, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010198412919417024, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010288837379775942, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.01036289454670623, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010436748419888318, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010550122982822359, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010664587167557329, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010828808683436364, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01105728421593085, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.011294697551056743, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011644932487979532, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011969035444781184, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1262214183807373, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1254138946533203, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1247360706329346, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1244571208953857, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1243185997009277, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1242008209228516, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124133348464966, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1240222454071045, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123915195465088, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1237940788269043, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123654365539551, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1234326362609863, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1232244968414307, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122929334640503, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1226258277893066, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.122328042984009, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1219217777252197, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1214499473571777, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1208677291870117, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1203317642211914, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.119636297225952, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.118880271911621, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.118032455444336, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.117051124572754, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.116013765335083, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1146767139434814, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1134235858917236, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1122453212738037, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.110590934753418, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.108623743057251, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.106872797012329, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1053006649017334, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.103224277496338, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1014323234558105, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.099280595779419, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0972230434417725, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0950305461883545, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.093310594558716, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0923023223876953, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.092501163482666, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0934414863586426, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.094714641571045, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.09723162651062, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.099292755126953, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.100522518157959, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1035776138305664, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.1117448806762695, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.125481605529785, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.1326444149017334, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06995201181247693, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06662975267626431, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07327427094868956, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07401255075673681, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07604282022886674, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07770394979697305, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07715023994093761, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.0784422296050203, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08102620893318568, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0843484680693983, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08656330749354005, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.0858250276854928, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08619416758951642, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08803986710963455, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08305647840531562, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.07954964931709117, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.07825765965300849, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.07770394979697305, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01195861770798883, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.010343283124620328, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.008220861546765398, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.007174810318754621, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006436327675344796, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.00622072716370962, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0063082965140461205, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005869180869180869, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0055346181287559, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005159422940498359, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005169405160438159, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005169042139953131, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005168324437192818, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.004975340876124165, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0049762070566388115, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.004978807408697672, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005185530807722231, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.005558629341699922, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.00573100895601576, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.005887851086303071, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.005986680047440927, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.006984131244443915, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.007605616835079712, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.009102320207852661, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.0104566885826265, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.01287823153459614, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.014398680658185545, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01606797361512212, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.018012046319705086, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.02228716625148598, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.024346970705740423, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.025166984942376434, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.027230051177531137, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.028418124468257117, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.030705162170135136, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03380968333775153, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.035572585848818394, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.036330335898958246, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03707376742393179, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.037897626180802065, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.03976491806239136, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.041346214354587, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04099395531958857, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04104019017615491, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04233683124830207, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.03914652032088595, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.03693517158371207, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.0347642311365007, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.03325381489539865, "id_best": 44, "lr_best": 0.0078, "wd_best": 0.05, "train/loss_best": 3.0440545654296876, "validation/loss_best": 3.100522518157959, "validation/acc_best": 0.08803986710963455, "validation/f1_best": 0.04233683124830207} +{"epoch": 13, "train/lr": 0.00011886002410835478, "train/loss": 3.0963079810142515, "train/grad": 0.07069244913756847, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13116943359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.13040771484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129720458984375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12932861328125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.129122314453125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.12886962890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.128643798828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12838134765625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12801025390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127576904296875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.127198486328125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12657958984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.1259716796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1252392578125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.124390869140625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.123668212890625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.122696533203125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.121563720703125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.12031494140625, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.119229736328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11752685546875, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11591064453125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.114112548828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.112056884765625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.10980224609375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.107095947265625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.10461181640625, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.102154541015625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.09880615234375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.094837646484375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.091209716796875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0877655029296873, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.083302001953125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0792926025390623, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0746807861328125, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0699554443359376, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.06500732421875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.060443115234375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0555633544921874, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.050250244140625, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.046624755859375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0439251708984374, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.04115234375, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.039686279296875, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0392828369140625, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0406005859375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0432659912109377, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.048172607421875, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.053914794921875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009847234033513815, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009812022752594202, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009783623553812505, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009772246174979954, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009767726233694702, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.00976614270126447, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009765990423038601, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009766218361910432, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009766692656558006, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00976726833032444, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.00976822234224528, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009769409862346947, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009770350230392069, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009772232507821173, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009774227559100837, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00977625114377588, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009778465062845498, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.00978189863730222, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009785459905397148, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009789508651010692, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00979474316816777, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00980081533547491, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.00980733819771558, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00981572674587369, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009825004991143941, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009837718640919774, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009849823487456888, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009861704481299966, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009879711556714028, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009903744307812302, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009927217641379684, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009949789037927986, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00998443369520828, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.010017596671823413, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010060606573242694, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010106822655070574, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010158127045724542, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010208961418829859, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.01026981186354533, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.010359450017567724, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010444703495595604, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010527289912570268, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010642868834547698, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010749905563425272, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010892760066781193, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.01107500220881775, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01125226157484576, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011482248888351023, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.01169372146949172, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1259076595306396, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.125168800354004, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.124603748321533, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124366521835327, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124255657196045, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241559982299805, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.12404727935791, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1239631175994873, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123774290084839, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1236424446105957, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1234631538391113, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1232333183288574, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1229889392852783, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1226327419281006, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1222894191741943, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.121943473815918, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.121516227722168, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1209805011749268, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.120415210723877, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.119860887527466, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1191773414611816, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1184744834899902, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1176676750183105, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.116765260696411, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1158080101013184, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1145832538604736, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1134283542633057, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1123263835906982, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1107730865478516, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.108887195587158, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.107191562652588, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1056742668151855, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.103651285171509, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1018764972686768, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.099977493286133, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.098134994506836, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0961356163024902, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0942084789276123, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.092308759689331, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0909993648529053, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.090886354446411, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0912344455718994, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.091785430908203, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.09272837638855, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.095273494720459, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.1003050804138184, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.105565071105957, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.1130945682525635, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.122844696044922, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06884459210040605, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06552233296419344, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06459948320413436, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06626061277224068, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06681432262827612, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06921373200442968, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.07032115171650055, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07235142118863049, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07364341085271318, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0753045404208195, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07419712070874862, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07456626061277224, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0725359911406423, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.07401255075673681, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.07475083056478406, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.07807308970099668, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.07733480989294943, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.07936507936507936, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08028792912513842, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08379475821336287, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08545588778146918, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08619416758951642, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08619416758951642, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0873015873015873, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.08397932816537468, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08490217792543374, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.011359750283058759, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009497140395375699, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007845818610650738, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006825329071131602, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006343431211360773, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006273680559414911, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006040399793049385, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005501523685545067, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005357317780818393, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0051586406918454316, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005169770936299526, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005169770936299526, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005169042139953131, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.004979674796747967, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005188519774762791, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.005371788110781765, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005867563273754796, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.006654405954769124, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007332547487465569, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007794082215899545, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008633018295276188, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00996441325177414, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.012113041376301368, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013717613897196015, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.015618343618071193, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.018418333586131565, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.02177988803466367, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.024847042608964726, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.027215914029402166, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.029725598766981942, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.03001061251431177, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.031104503431830768, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.030592916059614315, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.031545584950189, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03074523871418722, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03063380313355728, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03252077402067342, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.03431133828814555, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03679934549050156, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.036812828810377, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0388225479984336, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.03939051144285577, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04212580825603631, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04413600770431617, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04419015861285245, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04378509011385984, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04316471404560832, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.04046525988969358, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.039942526519401, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 3.0432659912109377, "validation/loss_best": 3.105565071105957, "validation/acc_best": 0.0873015873015873, "validation/f1_best": 0.04316471404560832} +{"epoch": 14, "train/lr": 8.9081919031238e-05, "train/loss": 3.094000712633133, "train/grad": 0.07063332507386803, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.130526123046875, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.129881591796875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1293701171875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.1289990234375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12878173828125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128511962890625, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.128287353515625, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1278857421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127547607421875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.127135009765625, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12682373046875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.126187744140625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125662841796875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.124783935546875, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.124080810546875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12331298828125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.12236572265625, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.1211962890625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11993408203125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11865966796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.11706787109375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.115445556640625, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.113565673828125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1113720703125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.109046630859375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.1061865234375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.103509521484375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.10091064453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.097374267578125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.09308837890625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.089212646484375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.085625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.08073486328125, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0762896728515625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.071053466796875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0659722900390625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0605645751953126, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0557440185546874, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.05082763671875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.045450439453125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0419842529296877, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.039293212890625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0365789794921874, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0351812744140627, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.034344482421875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0344677734375, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.0355850219726563, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.0380435180664063, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0415835571289063, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009892950328066944, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009863764506299048, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.00984179318882525, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00983399756019935, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009831727768760174, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009830317187588661, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009830435772892087, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.00983043508604169, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009830872705206275, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00983176170149818, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009832796952687205, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.0098341015400365, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009835965484380722, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009837122622411699, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009838976231403649, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009841125740204007, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009843039014376699, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009845634982921183, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009848682163283228, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009851908069103956, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.0098556869616732, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.00985945964930579, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009864148062188178, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009869127720594405, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009875231739133596, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009882602815050632, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009889106650371104, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009896246881689877, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009906330762896686, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009919408611021936, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009932575728744269, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009946208237670362, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009967068911064416, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00998721333919093, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.010014947075396775, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.010046891786623746, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.010085900784470142, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.010130588116589933, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.010189163140021265, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.01027510175248608, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.010351618856657297, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.01042491773609072, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.010532904576975852, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.01063926886767149, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01077981612412259, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010938959824852646, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.01107457428239286, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.011240315879695118, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.011408901549875736, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125699996948242, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1250603199005127, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1245667934417725, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1243374347686768, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124237298965454, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241278648376465, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.124028205871582, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1239206790924072, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.123757839202881, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123599052429199, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1234216690063477, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1231820583343506, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.122915029525757, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1225664615631104, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1221983432769775, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1218810081481934, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1214282512664795, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1209206581115723, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.120312213897705, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.119731903076172, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1189894676208496, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.11816143989563, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.117204189300537, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.116114616394043, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1149063110351562, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1134109497070312, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1119637489318848, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1106128692626953, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.1086626052856445, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.106205701828003, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.103912115097046, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.101809024810791, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0989058017730713, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0963847637176514, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.093446731567383, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.090726852416992, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0880579948425293, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.085766553878784, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.083601474761963, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0813512802124023, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.080249309539795, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0799520015716553, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.08052396774292, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0815539360046387, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0831408500671387, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.084442138671875, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.086027145385742, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.088538885116577, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0924010276794434, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.0681063122923588, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06533776301218161, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06275378368401624, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06293835363602805, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.0651531930601698, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06478405315614617, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06552233296419344, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0664451827242525, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07216685123661867, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0754891103728313, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.0769656699889258, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07807308970099668, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08047249907715023, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08305647840531562, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08416389811738649, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08674787744555186, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08859357696567, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09099298634182355, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09376153562200074, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09486895533407161, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09339239571797711, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0932078257659653, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09265411590992986, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.08600959763750461, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01113388818363376, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.009586058098402751, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007364199308197, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006855789279774837, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006176472906124883, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006277498037558044, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.0066078634939825695, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0055007187885211875, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.0053572832697506316, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005159030532179161, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005170510683132682, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005170139449738868, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005170636398473636, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.004984016274338855, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005178717361807008, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0053615606238936325, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.005696307897360732, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.006115793051475926, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.006444774912273837, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007084241229001338, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.0076559197725527455, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009310066509502474, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010270988217038382, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.011800162026454966, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.012498574008347946, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.013443979229844388, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.014138545917470659, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.015395784811566166, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.016680277447401484, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.020129461948584115, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.022030032077631944, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.025201046414720592, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.027547775863095203, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03022318376434477, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.032187541782390895, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03399280637077932, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.035891099795789694, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.036345212426009195, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.03772567109437651, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.03865765733409663, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04053775559066089, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04184958833412864, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04229469230656696, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04155685283942225, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04147394130493745, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04158967697729503, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.040820029298218465, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.041987310043413606, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04123185514753519, "id_best": 42, "lr_best": 0.005699999999999999, "wd_best": 0.05, "train/loss_best": 3.0365789794921874, "validation/loss_best": 3.08052396774292, "validation/acc_best": 0.09486895533407161, "validation/f1_best": 0.04229469230656696} +{"epoch": 15, "train/lr": 6.196799573888289e-05, "train/loss": 3.0860863530635836, "train/grad": 0.06884809641167522, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128238525390625, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.1275830078125, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.12688232421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.126510009765625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126180419921875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.1258740234375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12548828125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12513916015625, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.124644775390625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.124171142578125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.123712158203125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.123056640625, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.122440185546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.121507568359375, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.1206982421875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.119886474609375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.118836669921875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.11752685546875, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.116171875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11466796875, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.113031005859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.111162109375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10907470703125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.10680419921875, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1042138671875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.101121826171875, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.098133544921875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.095439453125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.091495361328125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.08686279296875, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.082523193359375, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.078621826171875, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0732427978515626, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0684576416015625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.06274169921875, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.057125244140625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0510833740234373, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0455859375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0398065185546876, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0328118896484373, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0279754638671874, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0239642333984373, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0194879150390626, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.016187744140625, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0134698486328126, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0115863037109376, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.011240234375, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.011993408203125, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.0137738037109374, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009734669723547995, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009712570703122765, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009697830581571906, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009693359432276338, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009692788044922053, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009692938937805593, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.00969336619367823, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009693668254185469, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009693792110774667, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.00969421916641295, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009694354389794171, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009694869890809059, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009695007076952606, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009695459306240082, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009696271882858128, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009697051357943565, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009697498064488172, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009698463731911033, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009699524424504488, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009700642626266926, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009701700061559676, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009703668607398868, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009706553197465837, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009708909371402114, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009712124017532915, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009717022411059588, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.00972103262320161, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00972546051023528, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009731967172119766, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.00974024259718135, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009748477817047387, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00975653632543981, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009768747698981315, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009780573213938624, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009796841440256686, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009815269706305117, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009837736119516194, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009862467541825026, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009894181892741471, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.00994295307667926, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009985689630266279, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.010027789762243628, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.01008588250959292, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010141583106014878, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.010210500489920378, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.0102975048054941, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010385315504390747, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010504161284770816, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010616565912496299, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125577449798584, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124979019165039, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1245226860046387, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242973804473877, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1241939067840576, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1241066455841064, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123997211456299, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1238608360290527, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1237051486968994, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1235480308532715, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1233627796173096, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1231179237365723, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.12286376953125, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122499704360962, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1221561431884766, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1218230724334717, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1214041709899902, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1209142208099365, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.120351791381836, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.119807481765747, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1191630363464355, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.118441343307495, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1176421642303467, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1167285442352295, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.115760326385498, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.11458158493042, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.113417625427246, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1123440265655518, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.110797882080078, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.108865976333618, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1070804595947266, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.105386972427368, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.103013753890991, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.1008212566375732, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0982017517089844, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.095539093017578, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0927650928497314, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.0902092456817627, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0876083374023438, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.084716796875, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.082806348800659, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0814919471740723, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0802786350250244, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0797677040100098, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.079620361328125, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.07981276512146, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.080096960067749, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.081324338912964, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.083256244659424, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06496862310815799, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06884459210040605, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06976744186046512, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.07013658176448874, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07272056109265411, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.0753045404208195, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07751937984496124, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08157991878922112, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08379475821336287, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08637873754152824, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08896271686969362, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09191583610188261, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09191583610188261, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.08896271686969362, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0902547065337763, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01062976103789459, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008932865974944965, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.0072724298827952045, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006709302266601741, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006345851831370823, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006276216324105378, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006321304418079289, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.00568477805077357, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005533711955730304, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005160215397298097, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005172022469784948, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.00517088461903021, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005173184030996101, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.00538653284576415, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.005167384625964663, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00570869545468599, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006585644605552177, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.006683376433320759, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.0075432560361721746, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007325774191863805, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007688893592422044, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.008553320709108378, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010286745432690656, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.01217699708218141, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013402454010213881, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.014722738497850366, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.018257732012319883, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.02011147830744822, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02236485588622733, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.025759385664255795, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.029263362003354613, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.030795276399480733, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.03250015601190055, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03541102235469245, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.037638269124421336, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.0391216966453965, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.04138257929513601, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.044049030236672525, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04460702798844074, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04668999751831138, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0489889350919463, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.05071323275157846, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.052377629734391105, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.051641890250596435, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04865421449254644, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04984810872943196, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05147916467365848, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05578248504079481, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.055894271701986666, "id_best": 47, "lr_best": 0.012899999999999998, "wd_best": 0.05, "train/loss_best": 3.011993408203125, "validation/loss_best": 3.081324338912964, "validation/acc_best": 0.09210040605389443, "validation/f1_best": 0.05578248504079481} +{"epoch": 16, "train/lr": 3.870405029380728e-05, "train/loss": 3.0855003929138185, "train/grad": 0.068647173140198, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128642578125, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12800537109375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127493896484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.127125244140625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.1268603515625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126551513671875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12623779296875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.12587646484375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12544189453125, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.125018310546875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124503173828125, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.123935546875, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.123331298828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.1223828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.121561279296875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.120751953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1196826171875, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.118353271484375, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.116964111328125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.1155908203125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.113968505859375, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.11200927734375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10990478515625, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.107552490234375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1049755859375, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.10175048828125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.098699951171875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.095860595703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.09188232421875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.08697021484375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.082528076171875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.078603515625, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.072952880859375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0680078125, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0621429443359376, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.056368408203125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.050322265625, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.044581298828125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.038607177734375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0314044189453124, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0262933349609376, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.02195556640625, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0169305419921875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.013009033203125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.0092938232421873, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0062738037109376, "train/loss_046_lr3.6e+01_wd1.0e+00": 3.004483642578125, "train/loss_047_lr4.3e+01_wd1.0e+00": 3.00369140625, "train/loss_048_lr5.0e+01_wd1.0e+00": 3.004188232421875, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009742726588156074, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009723881597165019, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009712458071298898, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009709959423635155, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009709693430922926, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009710517963394522, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009711117292754352, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009711139674764127, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009711284399963915, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009711012369953096, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009711266660597176, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009711322551593184, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009711204993072898, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009711605696938932, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.00971174709731713, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00971156424144283, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009712078622542322, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009712491277605295, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009713133161421866, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009714147695340215, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.00971487101400271, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009716178781818598, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009717717685271054, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00971987342927605, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009721642553340643, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009724576640874148, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009727977658621966, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009730750813614577, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009735455450136215, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009740741157438606, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009747353633865714, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009752730973996222, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009761509015224873, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009770507789216936, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009782246351242065, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009795302525162697, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009812289450783282, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009829699778929352, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009852036458905786, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009884584825485945, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009912965598050504, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009939642925746738, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009978937113191932, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.010015052508097142, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.01006110270973295, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.010118450282607227, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.010175579134374857, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010256634324323386, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010337169452104717, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125499725341797, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1249423027038574, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.12446928024292, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242735385894775, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.12416934967041, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240551471710205, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1239380836486816, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123812198638916, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1236374378204346, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.123469352722168, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123284101486206, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1230173110961914, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1227729320526123, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1223936080932617, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1220555305480957, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1217310428619385, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1212985515594482, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.120795965194702, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.120253801345825, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1197268962860107, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.119046211242676, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1183266639709473, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1174967288970947, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1165432929992676, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1154608726501465, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1140904426574707, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.112765312194824, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.1114892959594727, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.109619140625, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.107286214828491, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.105112314224243, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1030972003936768, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.1002824306488037, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.097754955291748, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0947554111480713, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.091831922531128, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.088822841644287, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.08614444732666, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.083522319793701, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0805935859680176, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.078596830368042, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.077134132385254, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0757007598876953, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0750536918640137, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.074779987335205, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0751473903656006, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.075672149658203, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.076399803161621, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.077190637588501, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06478405315614617, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.0664451827242525, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06626061277224068, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.0681063122923588, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.06921373200442968, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07585825027685493, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.0784422296050203, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08028792912513842, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08397932816537468, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08914728682170543, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.08859357696567, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09117755629383537, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.08988556662975268, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09210040605389443, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09339239571797711, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09339239571797711, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09191583610188261, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010580897316830649, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008982800543727581, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007247789302645055, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006832264148511146, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006337290417479096, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006228570698687863, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006284047156014441, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005856648613543263, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005516130755366861, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005533711955730304, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005147266761077554, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005175984075265612, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005179332375600856, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005359037477490972, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006373641871843691, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00640526822185224, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006942991825500055, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007439725298455115, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007553630152338449, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007842306255169502, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008961253961226068, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009897554535804008, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.010988919849399016, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.013227685964100412, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013483169213283653, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.014915543042068838, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.015847008683744668, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01786790226832338, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.02087287283490456, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.022885413583804737, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.02649408354974527, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.028675899809881732, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.029795761410904342, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03262305969529144, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03406120348724214, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.036796466559632895, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.03891434833476331, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04275971259589076, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.044934009213208996, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.047933493026862985, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.0472778968638887, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04818438859060988, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.04661679757212108, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.047986944726128467, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.047365289360308566, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04787075133722616, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04843831949662338, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.046479507272257414, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.04587437130118263, "id_best": 46, "lr_best": 0.010799999999999999, "wd_best": 0.05, "train/loss_best": 3.004483642578125, "validation/loss_best": 3.075672149658203, "validation/acc_best": 0.09339239571797711, "validation/f1_best": 0.04843831949662338} +{"epoch": 17, "train/lr": 2.030750443206766e-05, "train/loss": 3.085955013036728, "train/grad": 0.06840448219329119, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.13070068359375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.130150146484375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.129656982421875, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.129351806640625, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.12903076171875, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.128797607421875, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12841064453125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.127991943359375, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.127562255859375, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12710693359375, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.126629638671875, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.125892333984375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.125174560546875, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12433837890625, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.123424072265625, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1224755859375, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.1214111328125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.12005126953125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.1185888671875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.11714111328125, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.115469970703125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.1135595703125, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.11142578125, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.109019775390625, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.1064111328125, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.103109130859375, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.10016357421875, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.09730712890625, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.093377685546875, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.088421630859375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.084033203125, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.07993896484375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.074349365234375, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0692291259765625, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0631915283203126, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.057193603515625, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0507879638671875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.044669189453125, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.03826904296875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.0305072021484376, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.024779052734375, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.019930419921875, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.01418701171875, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0098095703125, "train/loss_044_lr2.6e+01_wd1.0e+00": 3.005340576171875, "train/loss_045_lr3.1e+01_wd1.0e+00": 3.0015740966796876, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9989544677734377, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.9968939208984375, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.99600830078125, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009782940559089183, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009759322823956609, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009742027760948986, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00973636410664767, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009734396210405975, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009733642938081176, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009733475854154676, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009733654661104083, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009733511314261705, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009733151397667825, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009733172690030188, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009732753613498062, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009732478202786297, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009732193688396364, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009732254752889276, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009732137836981564, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009732075915671885, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009732312171254308, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009732213490642606, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009731975472532213, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009732087021693587, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009732041042298079, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009731995037291198, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00973276237025857, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009733288574498147, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009734898484311997, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009735819166526199, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.0097364746266976, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009738311576656998, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009740072700660676, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.00974207655293867, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.00974345050053671, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009745714014861732, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009747950232122094, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009750748206861316, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009754169262014329, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00975903281243518, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009764505496714265, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.00977166138123721, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009782102140598, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009792949515394866, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009804893534164876, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009823848616797477, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.009845490113366395, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009875377011485397, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009914830066263676, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009954213798046112, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.010007504834793507, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.010059122228994966, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1254661083221436, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124905586242676, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1244542598724365, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242713928222656, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1241438388824463, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.124046564102173, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123915672302246, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1237826347351074, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1236085891723633, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1234347820281982, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1232707500457764, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1229968070983887, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1227505207061768, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1223764419555664, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1220345497131348, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1217041015625, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.121271848678589, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1207692623138428, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1202123165130615, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.119677782058716, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.118976593017578, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1182618141174316, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.117393732070923, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1164064407348633, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1153056621551514, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1138503551483154, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1124868392944336, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.111168146133423, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.109278440475464, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1069495677948, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.1048309803009033, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.102905750274658, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.100266218185425, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0979771614074707, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0952882766723633, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.0927131175994873, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0899994373321533, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.087506055831909, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.0849339962005615, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0819103717803955, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.0797622203826904, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.078075885772705, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0760445594787598, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.0745625495910645, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.073127508163452, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.071747303009033, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.070845365524292, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0702450275421143, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0699357986450195, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06681432262827612, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06386120339608711, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06293835363602805, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.062384643779992616, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06386120339608711, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06478405315614617, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06589147286821706, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06607604282022887, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07032115171650055, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07235142118863049, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07493540051679587, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08065706902916205, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0828719084533038, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08637873754152824, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08785529715762273, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08785529715762273, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08822443706164636, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09431524547803617, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09523809523809523, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09689922480620156, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09745293466223699, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0976375046142488, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09819121447028424, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09856035437430787, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.01048226563385543, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008620235333365218, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007266618923480542, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006841143536972436, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0063396951097941965, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006232058081274148, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.00628538548941637, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.005862208372888182, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005531144216429056, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.005534161853083611, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005161422947651889, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005175171455019081, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005177221532361719, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005372631685816232, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.00606068377164301, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.006483373186380946, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006486979228237198, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007289090604160873, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007471463036422834, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007412693414401999, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.007839512892555802, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00955766763379315, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.0111083442201183, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012074822107830036, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013015713289556663, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.014258563017779231, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.015239983286928403, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.017752593048629212, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.020085004968263452, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.023680469828725608, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.026716590287106292, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.029889155528556494, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.031677477155783194, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03509085651314179, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.036619747209851415, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03959235386476006, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.041174411221511276, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04217284427913457, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04308011413836543, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04487436609874651, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04588345208133787, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04623693129856333, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.050310540823801986, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.05143802498099146, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.05257461202084751, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.05272775336815149, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.05259977790458911, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05264543518072923, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05337065353277928, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.99600830078125, "validation/loss_best": 3.0699357986450195, "validation/acc_best": 0.09856035437430787, "validation/f1_best": 0.05337065353277928} +{"epoch": 18, "train/lr": 7.5829098008590064e-06, "train/loss": 3.08276896238327, "train/grad": 0.06799159944057465, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.128714599609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.12809326171875, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.127659912109375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12719970703125, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.126949462890625, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.126630859375, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12626220703125, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.1258154296875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.12537353515625, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.12493408203125, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.124456787109375, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.12380615234375, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.12315673828125, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.12216064453125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.12128173828125, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.12036376953125, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.119281005859375, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.117984619140625, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11655029296875, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.115120849609375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.113389892578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.111507568359375, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.109287109375, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.1068408203125, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.104207763671875, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.100865478515625, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.09772705078125, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.094844970703125, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.09077880859375, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.08579833984375, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.08119384765625, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0770281982421874, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0712091064453126, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0661224365234374, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0599200439453127, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0537548828125, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0472711181640624, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.041048583984375, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.034530029296875, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.026436767578125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.0204815673828125, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0153094482421876, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.0092181396484374, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.004300537109375, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9993438720703125, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.994727783203125, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9914349365234374, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.988546142578125, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.986761474609375, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009749844809994102, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.009728077955078334, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009712988371029496, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.00970823114970699, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009706119406037033, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009705532756634057, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009705357695929706, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009705044960137457, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009704912290908396, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009704363076016307, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009703907500952482, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009703392195515335, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009702622308395803, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009702317302580922, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009701424774248154, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.009700911291874946, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009700086878146975, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009699035792145878, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.009698518598452211, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.009697797216940671, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009696450093761086, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009695558624807745, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009695397219620644, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.00969546771608293, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009694462101906538, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009694203971885145, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009693669567350299, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.009694141077343375, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.00969422705238685, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009694397368002683, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009694262724369764, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009694832530803978, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.00969594644382596, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.00969660461647436, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009697877876460552, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009699087354820222, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.009700232185423374, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009702079689595848, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009705344361718745, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009709784309379757, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009713839327450841, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.009718996926676483, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009727604154031724, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00973617167910561, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.009748912828508765, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009765002003405243, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009780728791374713, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009804322009440512, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.009825643475633115, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.1254379749298096, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.1248931884765625, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1244375705718994, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.124253749847412, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.124143123626709, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240410804748535, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.1239044666290283, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.1237869262695312, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.12359619140625, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1234185695648193, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.123248815536499, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1229703426361084, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.122727155685425, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.122349739074707, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1220145225524902, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.121673107147217, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.121250867843628, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1207520961761475, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.120185613632202, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.1196305751800537, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.1189239025115967, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.118180990219116, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.117305040359497, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.116281270980835, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.115159749984741, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.113673210144043, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.1122498512268066, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.110898494720459, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.108945608139038, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.1064839363098145, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.104212522506714, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1021158695220947, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0992608070373535, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.0966689586639404, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.093646287918091, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.090684413909912, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.0876758098602295, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.08492374420166, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.082103967666626, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.0789389610290527, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.076822280883789, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.0750539302825928, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.073094129562378, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.071723461151123, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0703377723693848, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.0691065788269043, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0683164596557617, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.0675649642944336, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0671582221984863, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06699889258028793, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06423034330011074, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06589147286821706, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06718346253229975, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.067921742340347, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.067921742340347, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06995201181247693, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.06921373200442968, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07198228128460686, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07659653008490218, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07825765965300849, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.08047249907715023, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.0799187892211148, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08250276854928018, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.0858250276854928, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08564045773348099, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08693244739756367, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08785529715762273, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09080841638981174, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.08951642672572906, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.09043927648578812, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.0902547065337763, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09043927648578812, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.0917312661498708, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.0917312661498708, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.0932078257659653, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010549927090426596, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008641789722644863, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007266618923480542, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006835787555220997, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.006338488666081593, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006228570698687863, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006284047156014441, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.006034472387327748, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005514940080815008, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0055332683951548264, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005162240378484243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005176806596511394, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.005179332375600856, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.005358132988327623, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.0065499837470739284, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.00658865236311094, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006713531713531714, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007405927858592784, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007313797064735381, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.0074502469798208674, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.008504396371529097, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.00962973707152663, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.011353352931490741, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012443159094781294, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013795397852445615, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.015250953710825623, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.016622570420805848, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.01990606149211307, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.021979403935122474, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.025172908923247098, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.028027591763111894, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03165697050638371, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.034036207342601085, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.03640454868032221, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.03600881234101453, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.03887736853811193, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.041900236355132146, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.042048286533436646, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.04385852220268912, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.045426827343864246, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.04754409125684489, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04700146124418639, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.047115089317485974, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.04841790964953285, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04825621798136906, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.048947141626869466, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.04968222297353473, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05008956587778585, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05143214849119359, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.986761474609375, "validation/loss_best": 3.0671582221984863, "validation/acc_best": 0.0932078257659653, "validation/f1_best": 0.05143214849119359} +{"epoch": 19, "train/lr": 1.0867618231465446e-06, "train/loss": 3.079022949934006, "train/grad": 0.0680977701768279, "train/loss_000_lr2.0e-02_wd1.0e+00": 3.125902099609375, "train/loss_001_lr2.3e-02_wd1.0e+00": 3.125091552734375, "train/loss_002_lr2.8e-02_wd1.0e+00": 3.1243896484375, "train/loss_003_lr3.3e-02_wd1.0e+00": 3.12392333984375, "train/loss_004_lr3.8e-02_wd1.0e+00": 3.123536376953125, "train/loss_005_lr4.5e-02_wd1.0e+00": 3.123262939453125, "train/loss_006_lr5.3e-02_wd1.0e+00": 3.12283935546875, "train/loss_007_lr6.2e-02_wd1.0e+00": 3.122391357421875, "train/loss_008_lr7.4e-02_wd1.0e+00": 3.121942138671875, "train/loss_009_lr8.7e-02_wd1.0e+00": 3.1214794921875, "train/loss_010_lr1.0e-01_wd1.0e+00": 3.12103759765625, "train/loss_011_lr1.2e-01_wd1.0e+00": 3.1204345703125, "train/loss_012_lr1.4e-01_wd1.0e+00": 3.11974853515625, "train/loss_013_lr1.7e-01_wd1.0e+00": 3.118721923828125, "train/loss_014_lr2.0e-01_wd1.0e+00": 3.117840576171875, "train/loss_015_lr2.3e-01_wd1.0e+00": 3.1169775390625, "train/loss_016_lr2.7e-01_wd1.0e+00": 3.115928955078125, "train/loss_017_lr3.2e-01_wd1.0e+00": 3.114581298828125, "train/loss_018_lr3.8e-01_wd1.0e+00": 3.11309814453125, "train/loss_019_lr4.4e-01_wd1.0e+00": 3.111732177734375, "train/loss_020_lr5.2e-01_wd1.0e+00": 3.109892578125, "train/loss_021_lr6.1e-01_wd1.0e+00": 3.107938232421875, "train/loss_022_lr7.2e-01_wd1.0e+00": 3.10580810546875, "train/loss_023_lr8.5e-01_wd1.0e+00": 3.10323974609375, "train/loss_024_lr1.0e+00_wd1.0e+00": 3.100621337890625, "train/loss_025_lr1.2e+00_wd1.0e+00": 3.09723876953125, "train/loss_026_lr1.4e+00_wd1.0e+00": 3.094154052734375, "train/loss_027_lr1.6e+00_wd1.0e+00": 3.091224365234375, "train/loss_028_lr1.9e+00_wd1.0e+00": 3.08714111328125, "train/loss_029_lr2.3e+00_wd1.0e+00": 3.082086181640625, "train/loss_030_lr2.7e+00_wd1.0e+00": 3.077607421875, "train/loss_031_lr3.1e+00_wd1.0e+00": 3.0733349609375, "train/loss_032_lr3.7e+00_wd1.0e+00": 3.0676019287109373, "train/loss_033_lr4.3e+00_wd1.0e+00": 3.0624420166015627, "train/loss_034_lr5.1e+00_wd1.0e+00": 3.0562420654296876, "train/loss_035_lr6.0e+00_wd1.0e+00": 3.0500885009765626, "train/loss_036_lr7.1e+00_wd1.0e+00": 3.0436248779296875, "train/loss_037_lr8.3e+00_wd1.0e+00": 3.0372369384765623, "train/loss_038_lr9.8e+00_wd1.0e+00": 3.0306005859375, "train/loss_039_lr1.2e+01_wd1.0e+00": 3.022491455078125, "train/loss_040_lr1.4e+01_wd1.0e+00": 3.01640869140625, "train/loss_041_lr1.6e+01_wd1.0e+00": 3.0113250732421877, "train/loss_042_lr1.9e+01_wd1.0e+00": 3.00504150390625, "train/loss_043_lr2.2e+01_wd1.0e+00": 3.0000323486328124, "train/loss_044_lr2.6e+01_wd1.0e+00": 2.9947369384765623, "train/loss_045_lr3.1e+01_wd1.0e+00": 2.98973388671875, "train/loss_046_lr3.6e+01_wd1.0e+00": 2.9862799072265624, "train/loss_047_lr4.3e+01_wd1.0e+00": 2.98263916015625, "train/loss_048_lr5.0e+01_wd1.0e+00": 2.980455322265625, "train/grad_000_lr2.0e-02_wd1.0e+00": 0.009794068001210689, "train/grad_001_lr2.3e-02_wd1.0e+00": 0.00977044423110783, "train/grad_002_lr2.8e-02_wd1.0e+00": 0.009753781934268773, "train/grad_003_lr3.3e-02_wd1.0e+00": 0.009747551511973143, "train/grad_004_lr3.8e-02_wd1.0e+00": 0.009745974633842707, "train/grad_005_lr4.5e-02_wd1.0e+00": 0.009744686090853065, "train/grad_006_lr5.3e-02_wd1.0e+00": 0.009744504990521818, "train/grad_007_lr6.2e-02_wd1.0e+00": 0.009744009852875024, "train/grad_008_lr7.4e-02_wd1.0e+00": 0.009743750060442835, "train/grad_009_lr8.7e-02_wd1.0e+00": 0.009743567074183375, "train/grad_010_lr1.0e-01_wd1.0e+00": 0.009742895620875061, "train/grad_011_lr1.2e-01_wd1.0e+00": 0.009742195196449756, "train/grad_012_lr1.4e-01_wd1.0e+00": 0.009741707537323237, "train/grad_013_lr1.7e-01_wd1.0e+00": 0.009740990037098527, "train/grad_014_lr2.0e-01_wd1.0e+00": 0.009740125501994044, "train/grad_015_lr2.3e-01_wd1.0e+00": 0.00973966289544478, "train/grad_016_lr2.7e-01_wd1.0e+00": 0.009739108313806356, "train/grad_017_lr3.2e-01_wd1.0e+00": 0.009738016268238425, "train/grad_018_lr3.8e-01_wd1.0e+00": 0.00973690377548337, "train/grad_019_lr4.4e-01_wd1.0e+00": 0.00973567348672077, "train/grad_020_lr5.2e-01_wd1.0e+00": 0.009735163287259638, "train/grad_021_lr6.1e-01_wd1.0e+00": 0.009733486918266863, "train/grad_022_lr7.2e-01_wd1.0e+00": 0.009731857443694026, "train/grad_023_lr8.5e-01_wd1.0e+00": 0.009730563948396593, "train/grad_024_lr1.0e+00_wd1.0e+00": 0.009728940799832345, "train/grad_025_lr1.2e+00_wd1.0e+00": 0.009727250649593771, "train/grad_026_lr1.4e+00_wd1.0e+00": 0.009725593423936515, "train/grad_027_lr1.6e+00_wd1.0e+00": 0.00972468702821061, "train/grad_028_lr1.9e+00_wd1.0e+00": 0.009722592984326183, "train/grad_029_lr2.3e+00_wd1.0e+00": 0.009720327549148351, "train/grad_030_lr2.7e+00_wd1.0e+00": 0.009719116727355868, "train/grad_031_lr3.1e+00_wd1.0e+00": 0.009717218347359448, "train/grad_032_lr3.7e+00_wd1.0e+00": 0.009714613424148411, "train/grad_033_lr4.3e+00_wd1.0e+00": 0.009712853769306093, "train/grad_034_lr5.1e+00_wd1.0e+00": 0.009710684157907963, "train/grad_035_lr6.0e+00_wd1.0e+00": 0.009708353036548942, "train/grad_036_lr7.1e+00_wd1.0e+00": 0.00970642847707495, "train/grad_037_lr8.3e+00_wd1.0e+00": 0.009705180320888757, "train/grad_038_lr9.8e+00_wd1.0e+00": 0.009703852247912436, "train/grad_039_lr1.2e+01_wd1.0e+00": 0.009703380134887994, "train/grad_040_lr1.4e+01_wd1.0e+00": 0.009702137755230069, "train/grad_041_lr1.6e+01_wd1.0e+00": 0.00970223335782066, "train/grad_042_lr1.9e+01_wd1.0e+00": 0.009702944699674844, "train/grad_043_lr2.2e+01_wd1.0e+00": 0.00970360975479707, "train/grad_044_lr2.6e+01_wd1.0e+00": 0.00970455830451101, "train/grad_045_lr3.1e+01_wd1.0e+00": 0.009705480975098909, "train/grad_046_lr3.6e+01_wd1.0e+00": 0.009707210271153599, "train/grad_047_lr4.3e+01_wd1.0e+00": 0.009711057089734822, "train/grad_048_lr5.0e+01_wd1.0e+00": 0.00971479998435825, "validation/loss_000_lr2.0e-02_wd1.0e+00": 3.125431537628174, "validation/loss_001_lr2.3e-02_wd1.0e+00": 3.124889612197876, "validation/loss_002_lr2.8e-02_wd1.0e+00": 3.1244382858276367, "validation/loss_003_lr3.3e-02_wd1.0e+00": 3.1242599487304688, "validation/loss_004_lr3.8e-02_wd1.0e+00": 3.1241438388824463, "validation/loss_005_lr4.5e-02_wd1.0e+00": 3.1240460872650146, "validation/loss_006_lr5.3e-02_wd1.0e+00": 3.123901605606079, "validation/loss_007_lr6.2e-02_wd1.0e+00": 3.123781204223633, "validation/loss_008_lr7.4e-02_wd1.0e+00": 3.1236026287078857, "validation/loss_009_lr8.7e-02_wd1.0e+00": 3.1234242916107178, "validation/loss_010_lr1.0e-01_wd1.0e+00": 3.1232354640960693, "validation/loss_011_lr1.2e-01_wd1.0e+00": 3.1229729652404785, "validation/loss_012_lr1.4e-01_wd1.0e+00": 3.1227238178253174, "validation/loss_013_lr1.7e-01_wd1.0e+00": 3.1223645210266113, "validation/loss_014_lr2.0e-01_wd1.0e+00": 3.1220180988311768, "validation/loss_015_lr2.3e-01_wd1.0e+00": 3.1216702461242676, "validation/loss_016_lr2.7e-01_wd1.0e+00": 3.1212403774261475, "validation/loss_017_lr3.2e-01_wd1.0e+00": 3.1207492351531982, "validation/loss_018_lr3.8e-01_wd1.0e+00": 3.1201820373535156, "validation/loss_019_lr4.4e-01_wd1.0e+00": 3.11963152885437, "validation/loss_020_lr5.2e-01_wd1.0e+00": 3.118967294692993, "validation/loss_021_lr6.1e-01_wd1.0e+00": 3.1182034015655518, "validation/loss_022_lr7.2e-01_wd1.0e+00": 3.1173133850097656, "validation/loss_023_lr8.5e-01_wd1.0e+00": 3.1163125038146973, "validation/loss_024_lr1.0e+00_wd1.0e+00": 3.1151905059814453, "validation/loss_025_lr1.2e+00_wd1.0e+00": 3.1137073040008545, "validation/loss_026_lr1.4e+00_wd1.0e+00": 3.112295389175415, "validation/loss_027_lr1.6e+00_wd1.0e+00": 3.110943555831909, "validation/loss_028_lr1.9e+00_wd1.0e+00": 3.108994245529175, "validation/loss_029_lr2.3e+00_wd1.0e+00": 3.106538772583008, "validation/loss_030_lr2.7e+00_wd1.0e+00": 3.104311943054199, "validation/loss_031_lr3.1e+00_wd1.0e+00": 3.1022350788116455, "validation/loss_032_lr3.7e+00_wd1.0e+00": 3.0994009971618652, "validation/loss_033_lr4.3e+00_wd1.0e+00": 3.096888780593872, "validation/loss_034_lr5.1e+00_wd1.0e+00": 3.0938880443573, "validation/loss_035_lr6.0e+00_wd1.0e+00": 3.091045618057251, "validation/loss_036_lr7.1e+00_wd1.0e+00": 3.088071346282959, "validation/loss_037_lr8.3e+00_wd1.0e+00": 3.085407257080078, "validation/loss_038_lr9.8e+00_wd1.0e+00": 3.082695245742798, "validation/loss_039_lr1.2e+01_wd1.0e+00": 3.079655647277832, "validation/loss_040_lr1.4e+01_wd1.0e+00": 3.077493667602539, "validation/loss_041_lr1.6e+01_wd1.0e+00": 3.075772762298584, "validation/loss_042_lr1.9e+01_wd1.0e+00": 3.0737717151641846, "validation/loss_043_lr2.2e+01_wd1.0e+00": 3.072256326675415, "validation/loss_044_lr2.6e+01_wd1.0e+00": 3.0706686973571777, "validation/loss_045_lr3.1e+01_wd1.0e+00": 3.069204330444336, "validation/loss_046_lr3.6e+01_wd1.0e+00": 3.0681278705596924, "validation/loss_047_lr4.3e+01_wd1.0e+00": 3.067073106765747, "validation/loss_048_lr5.0e+01_wd1.0e+00": 3.0664048194885254, "validation/acc_000_lr2.0e-02_wd1.0e+00": 0.06718346253229975, "validation/acc_001_lr2.3e-02_wd1.0e+00": 0.06404577334809892, "validation/acc_002_lr2.8e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_003_lr3.3e-02_wd1.0e+00": 0.0636766334440753, "validation/acc_004_lr3.8e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_005_lr4.5e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_006_lr5.3e-02_wd1.0e+00": 0.06349206349206349, "validation/acc_007_lr6.2e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_008_lr7.4e-02_wd1.0e+00": 0.06312292358803986, "validation/acc_009_lr8.7e-02_wd1.0e+00": 0.06330749354005168, "validation/acc_010_lr1.0e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_011_lr1.2e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_012_lr1.4e-01_wd1.0e+00": 0.06349206349206349, "validation/acc_013_lr1.7e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_014_lr2.0e-01_wd1.0e+00": 0.06441491325212255, "validation/acc_015_lr2.3e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_016_lr2.7e-01_wd1.0e+00": 0.06404577334809892, "validation/acc_017_lr3.2e-01_wd1.0e+00": 0.0636766334440753, "validation/acc_018_lr3.8e-01_wd1.0e+00": 0.06256921373200443, "validation/acc_019_lr4.4e-01_wd1.0e+00": 0.06275378368401624, "validation/acc_020_lr5.2e-01_wd1.0e+00": 0.06312292358803986, "validation/acc_021_lr6.1e-01_wd1.0e+00": 0.06330749354005168, "validation/acc_022_lr7.2e-01_wd1.0e+00": 0.06423034330011074, "validation/acc_023_lr8.5e-01_wd1.0e+00": 0.06533776301218161, "validation/acc_024_lr1.0e+00_wd1.0e+00": 0.06662975267626431, "validation/acc_025_lr1.2e+00_wd1.0e+00": 0.06755260243632337, "validation/acc_026_lr1.4e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_027_lr1.6e+00_wd1.0e+00": 0.06773717238833518, "validation/acc_028_lr1.9e+00_wd1.0e+00": 0.0695828719084533, "validation/acc_029_lr2.3e+00_wd1.0e+00": 0.07050572166851236, "validation/acc_030_lr2.7e+00_wd1.0e+00": 0.07308970099667775, "validation/acc_031_lr3.1e+00_wd1.0e+00": 0.07511997046880768, "validation/acc_032_lr3.7e+00_wd1.0e+00": 0.07622739018087855, "validation/acc_033_lr4.3e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_034_lr5.1e+00_wd1.0e+00": 0.07918050941306755, "validation/acc_035_lr6.0e+00_wd1.0e+00": 0.08176448874123293, "validation/acc_036_lr7.1e+00_wd1.0e+00": 0.08600959763750461, "validation/acc_037_lr8.3e+00_wd1.0e+00": 0.08711701734957548, "validation/acc_038_lr9.8e+00_wd1.0e+00": 0.08840900701365817, "validation/acc_039_lr1.2e+01_wd1.0e+00": 0.08877814691768181, "validation/acc_040_lr1.4e+01_wd1.0e+00": 0.09007013658176449, "validation/acc_041_lr1.6e+01_wd1.0e+00": 0.09099298634182355, "validation/acc_042_lr1.9e+01_wd1.0e+00": 0.09117755629383537, "validation/acc_043_lr2.2e+01_wd1.0e+00": 0.08970099667774087, "validation/acc_044_lr2.6e+01_wd1.0e+00": 0.09043927648578812, "validation/acc_045_lr3.1e+01_wd1.0e+00": 0.09136212624584718, "validation/acc_046_lr3.6e+01_wd1.0e+00": 0.09136212624584718, "validation/acc_047_lr4.3e+01_wd1.0e+00": 0.09154669619785899, "validation/acc_048_lr5.0e+01_wd1.0e+00": 0.09246954595791805, "validation/f1_000_lr2.0e-02_wd1.0e+00": 0.010604487949516966, "validation/f1_001_lr2.3e-02_wd1.0e+00": 0.008573970766796552, "validation/f1_002_lr2.8e-02_wd1.0e+00": 0.007268547474762465, "validation/f1_003_lr3.3e-02_wd1.0e+00": 0.006842947950814596, "validation/f1_004_lr3.8e-02_wd1.0e+00": 0.0063396951097941965, "validation/f1_005_lr4.5e-02_wd1.0e+00": 0.006228570698687863, "validation/f1_006_lr5.3e-02_wd1.0e+00": 0.006284047156014441, "validation/f1_007_lr6.2e-02_wd1.0e+00": 0.0058555633212685615, "validation/f1_008_lr7.4e-02_wd1.0e+00": 0.005514940080815008, "validation/f1_009_lr8.7e-02_wd1.0e+00": 0.0055332683951548264, "validation/f1_010_lr1.0e-01_wd1.0e+00": 0.005162240378484243, "validation/f1_011_lr1.2e-01_wd1.0e+00": 0.005175984075265612, "validation/f1_012_lr1.4e-01_wd1.0e+00": 0.00537180666787618, "validation/f1_013_lr1.7e-01_wd1.0e+00": 0.0053580847157173395, "validation/f1_014_lr2.0e-01_wd1.0e+00": 0.006554591781864509, "validation/f1_015_lr2.3e-01_wd1.0e+00": 0.0066013015531994935, "validation/f1_016_lr2.7e-01_wd1.0e+00": 0.006715464522392342, "validation/f1_017_lr3.2e-01_wd1.0e+00": 0.007416711582338618, "validation/f1_018_lr3.8e-01_wd1.0e+00": 0.007324338134888231, "validation/f1_019_lr4.4e-01_wd1.0e+00": 0.007472674056560172, "validation/f1_020_lr5.2e-01_wd1.0e+00": 0.00826859877936321, "validation/f1_021_lr6.1e-01_wd1.0e+00": 0.009184938022062375, "validation/f1_022_lr7.2e-01_wd1.0e+00": 0.011048570138379043, "validation/f1_023_lr8.5e-01_wd1.0e+00": 0.012313910489676921, "validation/f1_024_lr1.0e+00_wd1.0e+00": 0.013367334300791359, "validation/f1_025_lr1.2e+00_wd1.0e+00": 0.014609766456491778, "validation/f1_026_lr1.4e+00_wd1.0e+00": 0.01626519418858583, "validation/f1_027_lr1.6e+00_wd1.0e+00": 0.017697087494083597, "validation/f1_028_lr1.9e+00_wd1.0e+00": 0.020929627621152292, "validation/f1_029_lr2.3e+00_wd1.0e+00": 0.024134464545453743, "validation/f1_030_lr2.7e+00_wd1.0e+00": 0.027521950504365775, "validation/f1_031_lr3.1e+00_wd1.0e+00": 0.03018287776752353, "validation/f1_032_lr3.7e+00_wd1.0e+00": 0.032064524628834586, "validation/f1_033_lr4.3e+00_wd1.0e+00": 0.035198402364008126, "validation/f1_034_lr5.1e+00_wd1.0e+00": 0.035250818571305846, "validation/f1_035_lr6.0e+00_wd1.0e+00": 0.037758958214461756, "validation/f1_036_lr7.1e+00_wd1.0e+00": 0.041914619217594797, "validation/f1_037_lr8.3e+00_wd1.0e+00": 0.04256318789538804, "validation/f1_038_lr9.8e+00_wd1.0e+00": 0.044374548165929985, "validation/f1_039_lr1.2e+01_wd1.0e+00": 0.04535971274582063, "validation/f1_040_lr1.4e+01_wd1.0e+00": 0.046610340804650284, "validation/f1_041_lr1.6e+01_wd1.0e+00": 0.04688130389138245, "validation/f1_042_lr1.9e+01_wd1.0e+00": 0.047365769644048546, "validation/f1_043_lr2.2e+01_wd1.0e+00": 0.047092194175789186, "validation/f1_044_lr2.6e+01_wd1.0e+00": 0.04873187427973299, "validation/f1_045_lr3.1e+01_wd1.0e+00": 0.04988585194711618, "validation/f1_046_lr3.6e+01_wd1.0e+00": 0.050100208030867725, "validation/f1_047_lr4.3e+01_wd1.0e+00": 0.05028503122586513, "validation/f1_048_lr5.0e+01_wd1.0e+00": 0.05131313342992503, "id_best": 48, "lr_best": 0.015, "wd_best": 0.05, "train/loss_best": 2.980455322265625, "validation/loss_best": 3.0664048194885254, "validation/acc_best": 0.09246954595791805, "validation/f1_best": 0.05131313342992503} diff --git a/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b9c125efc4367fa7d1f03bce7bc5d1fe116fa9c1 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..ae2d72816d83121130f5f9ac563372dce8e5fdff --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,train,0.7900355871886121,0.0165028518519904,0.7660349134220517,0.019314469864228127,0.7563213784812663,0.018823956539402907 +flat_mae,patch,logistic,ppmi_dx,,0.046415888336127774,test,0.62,0.0433889340731021,0.5634191176470589,0.0501809939908774,0.5645645645645646,0.04633295091630095 +flat_mae,patch,logistic,ppmi_dx,1,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,1,10000.0,test,0.61,0.04411629630873381,0.5793334052421529,0.04844214340319935,0.5785229202037352,0.04771997048104614 +flat_mae,patch,logistic,ppmi_dx,2,0.3593813663804626,train,0.9110320284697508,0.011694738029658928,0.903396589658966,0.013077109582943744,0.8938262684649968,0.01404182896483642 +flat_mae,patch,logistic,ppmi_dx,2,0.3593813663804626,test,0.65,0.04597865156787441,0.6178622120318812,0.050207107642801195,0.615874363327674,0.04854764609908454 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,train,0.7188612099644128,0.01601721245548957,0.6634730538922156,0.021640415464421615,0.6603511025476343,0.018682854665950068 +flat_mae,patch,logistic,ppmi_dx,3,0.005994842503189409,test,0.64,0.04278027115388588,0.592944369063772,0.05017025849674424,0.5925297113752122,0.04631889135034441 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,train,0.702846975088968,0.016747124892673923,0.6461264087414551,0.021584997212478835,0.644736137871976,0.018797804842066966 +flat_mae,patch,logistic,ppmi_dx,4,0.005994842503189409,test,0.68,0.04137583836008643,0.6323529411764706,0.04933795920562124,0.6298811544991512,0.04526785718093922 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,train,0.896797153024911,0.012452719055561695,0.8876944915312633,0.014003446756216557,0.8779169342753157,0.014825284751404917 +flat_mae,patch,logistic,ppmi_dx,5,0.3593813663804626,test,0.58,0.04950433920375061,0.5586380832282472,0.050589534575090654,0.5594227504244482,0.05086860058378877 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,train,0.7348754448398577,0.016569484826284352,0.6904039190313338,0.021280993827844208,0.6837936202098052,0.019160226760538357 +flat_mae,patch,logistic,ppmi_dx,6,0.005994842503189409,test,0.58,0.04570880002800336,0.525101763907734,0.05291638721304515,0.5288624787775891,0.048691354527697635 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,train,0.8042704626334519,0.015999776391213655,0.782987208110423,0.018609817059329518,0.7732016698779705,0.01845445459213815 +flat_mae,patch,logistic,ppmi_dx,7,0.046415888336127774,test,0.56,0.05031748801361212,0.5416666666666666,0.051142075882720434,0.5432937181663837,0.051751960437530546 +flat_mae,patch,logistic,ppmi_dx,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,8,166.81005372000556,test,0.61,0.048400099173452116,0.5953937130407718,0.048890222554707076,0.5988964346349746,0.04956883138160025 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,train,0.7064056939501779,0.015745746145396138,0.6503644158223958,0.020650459434427462,0.6484960393919932,0.01794550624698899 +flat_mae,patch,logistic,ppmi_dx,9,0.005994842503189409,test,0.7,0.038065937529502665,0.6357455075279261,0.05060243084449114,0.6358234295415959,0.043129309945520285 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,train,0.6903914590747331,0.016045935803966918,0.6319165273950946,0.020758091478001027,0.6320113466067223,0.01801866139529787 +flat_mae,patch,logistic,ppmi_dx,10,0.005994842503189409,test,0.68,0.03765835365493292,0.6031746031746031,0.05213300400264528,0.6095076400679117,0.04252579348687397 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,train,0.7686832740213523,0.015745963307921853,0.739536541889483,0.018893360336488578,0.7303842860201242,0.018117134127883166 +flat_mae,patch,logistic,ppmi_dx,11,0.046415888336127774,test,0.64,0.044573283477886166,0.5863970588235294,0.05363595683075175,0.5874363327674024,0.04839815153854416 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,train,0.7651245551601423,0.016487857491577093,0.7376061120543294,0.019449181785510503,0.7292335688289445,0.018865156999722164 +flat_mae,patch,logistic,ppmi_dx,12,0.046415888336127774,test,0.62,0.04015619005832103,0.5476190476190476,0.0495827694319964,0.5560271646859083,0.0430017627722091 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,train,0.7651245551601423,0.01589933434020415,0.7362327909887358,0.01885186017493161,0.7274941126097195,0.01814197972143164 +flat_mae,patch,logistic,ppmi_dx,13,0.046415888336127774,test,0.63,0.04433934595818933,0.5906626839252129,0.04846200736332563,0.5895585738539898,0.04641242749953584 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,train,0.7135231316725978,0.017583578755936965,0.667544816892818,0.021660145969195153,0.6629736673089275,0.019636531298313224 +flat_mae,patch,logistic,ppmi_dx,14,0.005994842503189409,test,0.62,0.03628002205070996,0.5062370062370062,0.05045819592381781,0.5356536502546689,0.03906823358652263 +flat_mae,patch,logistic,ppmi_dx,15,0.046415888336127774,train,0.7704626334519573,0.015533407926759855,0.7411922619706344,0.01867998007614274,0.7318293727253264,0.017964645108512325 +flat_mae,patch,logistic,ppmi_dx,15,0.046415888336127774,test,0.59,0.045978360127346865,0.5523528769516323,0.04988622252676851,0.5522071307300509,0.048264777809328085 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,train,0.791814946619217,0.016529816618807362,0.7665143331948484,0.019573420469397612,0.7561282380646542,0.01909613726345179 +flat_mae,patch,logistic,ppmi_dx,16,0.046415888336127774,test,0.54,0.050638368852086856,0.5166036149642708,0.05152939824655192,0.5169779286926994,0.0519014923235425 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,train,0.7758007117437722,0.016689746476243085,0.7468685655456417,0.020142684783617876,0.7370343609505459,0.019276431206757403 +flat_mae,patch,logistic,ppmi_dx,17,0.046415888336127774,test,0.61,0.046780589992004164,0.5623386825272135,0.052778097933620524,0.5632427843803056,0.04935398030789127 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,train,0.7099644128113879,0.015169099570954882,0.6613143543765598,0.01906352054303907,0.6574743095696853,0.017071613318616542 +flat_mae,patch,logistic,ppmi_dx,18,0.005994842503189409,test,0.61,0.042163922967390036,0.5311936530833032,0.05163735961001522,0.5428692699490663,0.044463118974973195 +flat_mae,patch,logistic,ppmi_dx,19,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,19,166.81005372000556,test,0.6,0.04658127950153366,0.5920032639738881,0.04688993456412704,0.601018675721562,0.048509631721798056 +flat_mae,patch,logistic,ppmi_dx,20,0.3593813663804626,train,0.8861209964412812,0.012828819201107521,0.8760766803103595,0.014446978756319782,0.8666372297152645,0.015218384943545273 +flat_mae,patch,logistic,ppmi_dx,20,0.3593813663804626,test,0.59,0.04825490234162742,0.5626666666666666,0.051025219864154335,0.5623938879456706,0.05056924790847196 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,train,0.7758007117437722,0.016006087290755706,0.7454710144927537,0.01916336043521043,0.7352949047313209,0.018186976236705933 +flat_mae,patch,logistic,ppmi_dx,21,0.046415888336127774,test,0.71,0.040391340656135685,0.6695156695156695,0.04901448733159222,0.6642614601018676,0.04545880018501558 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,train,0.7793594306049823,0.01626851347207394,0.7522186824439641,0.019167277503141008,0.742533718689788,0.01851018819769939 +flat_mae,patch,logistic,ppmi_dx,22,0.046415888336127774,test,0.62,0.04403218822634188,0.5766488413547237,0.049980353459064514,0.5764006791171477,0.047264171723210915 +flat_mae,patch,logistic,ppmi_dx,23,0.3593813663804626,train,0.9039145907473309,0.011327063923315851,0.8954396990118658,0.012685976951865819,0.88543673731535,0.013468846656306393 +flat_mae,patch,logistic,ppmi_dx,23,0.3593813663804626,test,0.58,0.04691462884857983,0.5320855614973261,0.052004798974323765,0.533955857385399,0.04909105456817088 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,train,0.7829181494661922,0.01627001584152865,0.7581038935380534,0.0189679589229963,0.7489028045386428,0.01847554483603233 +flat_mae,patch,logistic,ppmi_dx,24,0.046415888336127774,test,0.64,0.049313673560180044,0.609375,0.05338291130435854,0.6078098471986417,0.05200398798070887 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,train,0.7793594306049823,0.01578204589821531,0.7502043157215571,0.019068311730167976,0.7399245343609505,0.018281413630678027 +flat_mae,patch,logistic,ppmi_dx,25,0.046415888336127774,test,0.67,0.037103417632342164,0.6033177064551027,0.05021328488504345,0.6065365025466893,0.04236044872962906 +flat_mae,patch,logistic,ppmi_dx,26,0.3593813663804626,train,0.8896797153024911,0.012305213628508506,0.8809728769556603,0.013517905457687366,0.8738760436737316,0.01407150733841277 +flat_mae,patch,logistic,ppmi_dx,26,0.3593813663804626,test,0.63,0.04680722593788272,0.6009060511271707,0.049328317123060725,0.5997453310696095,0.048467735051534726 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,train,0.7046263345195729,0.016357049953082608,0.6426798627282755,0.022120999034074103,0.6427023121387283,0.018811991863508452 +flat_mae,patch,logistic,ppmi_dx,27,0.005994842503189409,test,0.62,0.03818336810706987,0.5287698412698413,0.05092833683367362,0.5458404074702886,0.041644515848551895 +flat_mae,patch,logistic,ppmi_dx,28,0.005994842503189409,train,0.7135231316725978,0.015392847529581982,0.6611199125103463,0.020135078768087743,0.6577552986512524,0.017652848461356074 +flat_mae,patch,logistic,ppmi_dx,28,0.005994842503189409,test,0.68,0.038393806792241886,0.6114618746964546,0.0517994074597162,0.6146010186757216,0.04364890997612452 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,train,0.7775800711743772,0.015776812983459194,0.74784184927942,0.019073015985775866,0.7376097195461357,0.018177343444568297 +flat_mae,patch,logistic,ppmi_dx,29,0.046415888336127774,test,0.61,0.04612150908198907,0.5623386825272135,0.05210034230792149,0.5632427843803056,0.04893104439155929 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,train,0.9911032028469751,0.00418001942629754,0.9905920323553734,0.004423161401472823,0.9901653821451509,0.004669097250230807 +flat_mae,patch,logistic,ppmi_dx,30,2.782559402207126,test,0.6,0.050354328513048406,0.5755517826825127,0.05269817401990444,0.5755517826825127,0.05258850814472098 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,train,0.7135231316725978,0.01644124878676855,0.663329054343175,0.021295055014275747,0.6594947548704775,0.01887478778693268 +flat_mae,patch,logistic,ppmi_dx,31,0.005994842503189409,test,0.64,0.04422035730294364,0.5863970588235294,0.05165248078667233,0.5874363327674024,0.047226941656892465 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,train,0.905693950177936,0.011562331798652464,0.8979298811934795,0.012852309257470856,0.8894910083493899,0.013785013382021517 +flat_mae,patch,logistic,ppmi_dx,32,0.3593813663804626,test,0.62,0.05135811133599054,0.6041666666666667,0.05245515742538223,0.6069609507640068,0.053019044027108934 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,train,0.7597864768683275,0.016328461261865844,0.7298798397863818,0.019639694424979797,0.7214193962748876,0.018837940600155142 +flat_mae,patch,logistic,ppmi_dx,33,0.046415888336127774,test,0.68,0.04409660304377197,0.6483516483516483,0.0490376554209703,0.6451612903225806,0.047251920406046116 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,train,0.7722419928825622,0.015665946077114287,0.7421463904222525,0.018718748826073286,0.7324047313209163,0.017889472871024784 +flat_mae,patch,logistic,ppmi_dx,34,0.046415888336127774,test,0.67,0.044672582195346616,0.6396986570586308,0.0496662898493526,0.6370967741935484,0.04850449062407517 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,train,0.7099644128113879,0.01624530174859415,0.65222112124767,0.02173902740670588,0.6505164846927853,0.018669709679769757 +flat_mae,patch,logistic,ppmi_dx,35,0.005994842503189409,test,0.65,0.04572073490223009,0.6178622120318812,0.05014937299901063,0.615874363327674,0.04857385609647685 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,train,0.708185053380783,0.01606199915235661,0.6553745830902918,0.02115883028533876,0.652550310426033,0.018592810045688635 +flat_mae,patch,logistic,ppmi_dx,36,0.005994842503189409,test,0.67,0.03619195490713371,0.5862068965517242,0.0521236009494688,0.5963497453310695,0.041445255306177674 +flat_mae,patch,logistic,ppmi_dx,37,0.005994842503189409,train,0.7206405693950177,0.015769185229310905,0.6748008830803138,0.01992716631093297,0.6696237422393492,0.017951166007014404 +flat_mae,patch,logistic,ppmi_dx,37,0.005994842503189409,test,0.63,0.04262211163234408,0.5713127099988413,0.0521476311910776,0.5742784380305602,0.046733558861084254 +flat_mae,patch,logistic,ppmi_dx,38,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,38,1291.5496650148827,test,0.63,0.04346078692338647,0.5906626839252129,0.04880285528025395,0.5895585738539898,0.046740429640491535 +flat_mae,patch,logistic,ppmi_dx,39,0.3593813663804626,train,0.8861209964412812,0.012820556229080862,0.8768758900208128,0.014170416371641653,0.8692464140441019,0.014783609625895906 +flat_mae,patch,logistic,ppmi_dx,39,0.3593813663804626,test,0.69,0.04629031864223879,0.6615351020853806,0.05017032091054785,0.6583191850594228,0.04906479674374038 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,train,0.702846975088968,0.016659926745172658,0.6424377959715486,0.022412676969476637,0.6421269535431385,0.019108312217863584 +flat_mae,patch,logistic,ppmi_dx,40,0.005994842503189409,test,0.68,0.04393138286009216,0.6381727725011307,0.051886471502477986,0.634974533106961,0.04863755929272304 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,train,0.7793594306049823,0.016208343180994445,0.750886524822695,0.019333661100734624,0.740794262470563,0.018543407015004815 +flat_mae,patch,logistic,ppmi_dx,41,0.046415888336127774,test,0.68,0.046506618883767496,0.6527777777777778,0.05106711420121512,0.6502546689303905,0.05002543825556078 +flat_mae,patch,logistic,ppmi_dx,42,0.005994842503189409,train,0.701067615658363,0.016625415488542374,0.6446090609331948,0.02156323520843812,0.6432910511667738,0.01870324832579563 +flat_mae,patch,logistic,ppmi_dx,42,0.005994842503189409,test,0.71,0.03434536941131948,0.6363636363636364,0.0500494178766777,0.6387945670628183,0.04055355605893765 +flat_mae,patch,logistic,ppmi_dx,43,0.046415888336127774,train,0.7829181494661922,0.0160108988221523,0.7581038935380534,0.01856610343503073,0.7489028045386428,0.01808313169658999 +flat_mae,patch,logistic,ppmi_dx,43,0.046415888336127774,test,0.61,0.043723362176301135,0.5555555555555556,0.04960911748096179,0.5581494057724957,0.045699166636240574 +flat_mae,patch,logistic,ppmi_dx,44,0.046415888336127774,train,0.7811387900355872,0.01461983906475904,0.7525584991570108,0.017588204992734623,0.7422393491757653,0.016904025904565325 +flat_mae,patch,logistic,ppmi_dx,44,0.046415888336127774,test,0.7,0.04397999545247816,0.6703296703296704,0.04966390886569701,0.666383701188455,0.04827250613813292 +flat_mae,patch,logistic,ppmi_dx,45,0.046415888336127774,train,0.7704626334519573,0.016474510026998613,0.7411922619706344,0.019615731094647586,0.7318293727253264,0.018718731769065883 +flat_mae,patch,logistic,ppmi_dx,45,0.046415888336127774,test,0.67,0.04171757902851027,0.6176572818908586,0.05063960648105099,0.616723259762309,0.04602890167340929 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,train,0.7651245551601423,0.016294892970988045,0.7348146877144819,0.01930746390867716,0.7257546563904946,0.018406396205185756 +flat_mae,patch,logistic,ppmi_dx,46,0.046415888336127774,test,0.63,0.04548087510151932,0.5906626839252129,0.05160029102270635,0.5895585738539898,0.04886606279278499 +flat_mae,patch,logistic,ppmi_dx,47,0.3593813663804626,train,0.891459074733096,0.01242864615709659,0.8825230708075896,0.013750223850675055,0.8744514022693213,0.014337763597925771 +flat_mae,patch,logistic,ppmi_dx,47,0.3593813663804626,test,0.72,0.038189862529210555,0.6880570409982174,0.0446011278104304,0.6825127334465195,0.04302844757462542 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,train,0.702846975088968,0.01654788619678792,0.6449161038911904,0.021818410475135646,0.6438664097623635,0.01884502743338326 +flat_mae,patch,logistic,ppmi_dx,48,0.005994842503189409,test,0.71,0.041097206717732045,0.6695156695156695,0.05007141536362938,0.6642614601018676,0.04639733884725464 +flat_mae,patch,logistic,ppmi_dx,49,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,49,1291.5496650148827,test,0.58,0.04324791786895642,0.525101763907734,0.0485480798671048,0.5288624787775891,0.044920516912603445 +flat_mae,patch,logistic,ppmi_dx,50,0.005994842503189409,train,0.6957295373665481,0.016345999578880083,0.6364111003915782,0.02149921000585686,0.6363466067223293,0.01858675748947042 +flat_mae,patch,logistic,ppmi_dx,50,0.005994842503189409,test,0.7,0.04016438223102652,0.6428571428571428,0.05182328358410523,0.6409168081494058,0.04521793618647286 +flat_mae,patch,logistic,ppmi_dx,51,0.3593813663804626,train,0.8985765124555161,0.011572916529817238,0.8899912429815072,0.01291736812206718,0.8811014771997432,0.01369400867877631 +flat_mae,patch,logistic,ppmi_dx,51,0.3593813663804626,test,0.59,0.04689919402292538,0.5523528769516323,0.05042145591008586,0.5522071307300509,0.04893703007916049 +flat_mae,patch,logistic,ppmi_dx,52,0.3593813663804626,train,0.891459074733096,0.012960326429895124,0.8820152600296666,0.014491560606261463,0.8727119460500963,0.015207596857398155 +flat_mae,patch,logistic,ppmi_dx,52,0.3593813663804626,test,0.55,0.04590295851031826,0.508679986898133,0.04876068556485285,0.5097623089983022,0.047220479796067104 +flat_mae,patch,logistic,ppmi_dx,53,2.782559402207126,train,0.99644128113879,0.0024826776679898847,0.9962334964144495,0.002634256679478211,0.9953703703703703,0.003229779744005356 +flat_mae,patch,logistic,ppmi_dx,53,2.782559402207126,test,0.59,0.048553059635825215,0.5626666666666666,0.05152891702326979,0.5623938879456706,0.05121746847872511 +flat_mae,patch,logistic,ppmi_dx,54,0.3593813663804626,train,0.902135231316726,0.01274225912522548,0.8945205993659634,0.013943819783024681,0.8874705630485977,0.014529732353257009 +flat_mae,patch,logistic,ppmi_dx,54,0.3593813663804626,test,0.52,0.04693500186428035,0.4652406417112299,0.049616327662134835,0.4702886247877759,0.04739064052806034 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,train,0.7046263345195729,0.015929391700257225,0.6464337148487834,0.021040405608823358,0.6453114964675658,0.018113069439740007 +flat_mae,patch,logistic,ppmi_dx,55,0.005994842503189409,test,0.67,0.042973754781261544,0.6176572818908586,0.052387581386575066,0.616723259762309,0.047177026134290104 +flat_mae,patch,logistic,ppmi_dx,56,0.046415888336127774,train,0.7740213523131673,0.015880478978719716,0.7472189265286607,0.01861286526085336,0.7381984585741812,0.018038819166743738 +flat_mae,patch,logistic,ppmi_dx,56,0.046415888336127774,test,0.63,0.048734726838261855,0.5960257670051315,0.053169608547608424,0.5946519524617997,0.05130582081825587 +flat_mae,patch,logistic,ppmi_dx,57,0.046415888336127774,train,0.7811387900355872,0.016125864787757904,0.7518763796909492,0.01936983500211835,0.7413696210661529,0.018492151438039627 +flat_mae,patch,logistic,ppmi_dx,57,0.046415888336127774,test,0.72,0.04369209997242065,0.6923076923076923,0.049658181146406466,0.6876061120543294,0.0483031471065455 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,train,0.708185053380783,0.015740021224012666,0.6542316926770708,0.020667341882235814,0.6516805823164205,0.018023888495944572 +flat_mae,patch,logistic,ppmi_dx,58,0.005994842503189409,test,0.62,0.04243112065453846,0.5558672276764843,0.05135017306682566,0.5611205432937181,0.045719173333764594 +flat_mae,patch,logistic,ppmi_dx,59,0.046415888336127774,train,0.7775800711743772,0.016106289395708177,0.751199730835296,0.019036471855756736,0.7419583600941982,0.018502104828664507 +flat_mae,patch,logistic,ppmi_dx,59,0.046415888336127774,test,0.64,0.04571084772786434,0.5989304812834224,0.05177266647412086,0.597623089983022,0.04877448508233287 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,train,0.7686832740213523,0.01564871062898609,0.740229263852543,0.01854700614143763,0.7312540141297367,0.017868440145076075 +flat_mae,patch,logistic,ppmi_dx,60,0.046415888336127774,test,0.63,0.044169722661569884,0.5906626839252129,0.04955038728656665,0.5895585738539898,0.047215681316423876 +flat_mae,patch,logistic,ppmi_dx,61,0.046415888336127774,train,0.7864768683274022,0.016921408441724826,0.7608408868462488,0.020127987415673763,0.7509232498394348,0.0196036583114383 +flat_mae,patch,logistic,ppmi_dx,61,0.046415888336127774,test,0.64,0.04042664467897379,0.592944369063772,0.04723171475601195,0.5925297113752122,0.04383927215276605 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,train,0.7170818505338078,0.01684944360958273,0.6685767694413227,0.021507643002911497,0.664124384500107,0.01924240087737301 +flat_mae,patch,logistic,ppmi_dx,62,0.005994842503189409,test,0.62,0.03829094409909477,0.5386109762020399,0.04987393738630591,0.5509337860780985,0.04159734042670936 +flat_mae,patch,logistic,ppmi_dx,63,0.005994842503189409,train,0.7117437722419929,0.015283185703615592,0.6584483793517407,0.0199352844238675,0.6554404838364376,0.01745553165074327 +flat_mae,patch,logistic,ppmi_dx,63,0.005994842503189409,test,0.64,0.03631512632499026,0.5628946090335114,0.0472736977958344,0.5721561969439728,0.03953865594258082 +flat_mae,patch,logistic,ppmi_dx,64,0.005994842503189409,train,0.7170818505338078,0.017055315615142792,0.669625658563638,0.022150123519719414,0.6649941126097195,0.019832379279912493 +flat_mae,patch,logistic,ppmi_dx,64,0.005994842503189409,test,0.62,0.04116928466709132,0.5386109762020399,0.05151845058595703,0.5509337860780985,0.04381911580767996 +flat_mae,patch,logistic,ppmi_dx,65,0.046415888336127774,train,0.7544483985765125,0.016264092353785092,0.7242433723973148,0.0191946705445919,0.7162144080496682,0.018383861821880575 +flat_mae,patch,logistic,ppmi_dx,65,0.046415888336127774,test,0.62,0.04333635886873746,0.5703301673450927,0.048776949398738965,0.5713073005093379,0.045409977899762026 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,train,0.7829181494661922,0.016544041149367226,0.7574844368986984,0.019272746096262,0.7480330764290302,0.018667835426685545 +flat_mae,patch,logistic,ppmi_dx,66,0.046415888336127774,test,0.62,0.04511643159648157,0.5766488413547237,0.05052690433867025,0.5764006791171477,0.04764834453048925 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,train,0.7722419928825622,0.01662139027299495,0.7407038943437576,0.020219909312659184,0.7306652751016913,0.019199481127207124 +flat_mae,patch,logistic,ppmi_dx,67,0.046415888336127774,test,0.63,0.044403148537012556,0.5847828526540231,0.050742196464797495,0.5844651952461799,0.04758155077598606 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,train,0.697508896797153,0.016588622039684822,0.639155789219241,0.022021740521458843,0.6386614215371441,0.01896942461265035 +flat_mae,patch,logistic,ppmi_dx,68,0.005994842503189409,test,0.71,0.03967110283317064,0.6640018537828757,0.049662853121617404,0.6591680814940577,0.04506136438326521 +flat_mae,patch,logistic,ppmi_dx,69,0.3593813663804626,train,0.8807829181494662,0.012948125568989013,0.8701241364086326,0.014566167424395347,0.8605625133804324,0.015225052661959393 +flat_mae,patch,logistic,ppmi_dx,69,0.3593813663804626,test,0.64,0.04572187222763302,0.609375,0.04961354771009108,0.6078098471986417,0.0483530301547729 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,train,0.7064056939501779,0.016000317796137246,0.6491686056409965,0.021615939328913186,0.6476263112823807,0.018618729986910405 +flat_mae,patch,logistic,ppmi_dx,70,0.005994842503189409,test,0.64,0.04498525980807491,0.592944369063772,0.05186369520803708,0.5925297113752122,0.04826829474828846 +flat_mae,patch,logistic,ppmi_dx,71,0.046415888336127774,train,0.7829181494661922,0.01645526511648548,0.7568549016270196,0.019374113345402653,0.7471633483194177,0.01877006805683962 +flat_mae,patch,logistic,ppmi_dx,71,0.046415888336127774,test,0.61,0.04660933812016643,0.5555555555555556,0.05369097602564633,0.5581494057724957,0.049437382433988306 +flat_mae,patch,logistic,ppmi_dx,72,0.3593813663804626,train,0.8807829181494662,0.01311725428202071,0.8698332036989024,0.014736941506930648,0.8596927852708199,0.015247675985768896 +flat_mae,patch,logistic,ppmi_dx,72,0.3593813663804626,test,0.62,0.04903329073190989,0.5967741935483871,0.05096471227592998,0.5967741935483871,0.05093053200555909 +flat_mae,patch,logistic,ppmi_dx,73,0.3593813663804626,train,0.8754448398576512,0.013820507717005407,0.8641574585635359,0.01560729453669095,0.8544877970456005,0.016266931545182807 +flat_mae,patch,logistic,ppmi_dx,73,0.3593813663804626,test,0.6,0.05248885214976605,0.570999570999571,0.055451753685265816,0.5704584040747029,0.05465424126308131 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,train,0.7295373665480427,0.017098166881209406,0.6805910770105144,0.022070817340492876,0.6751097195461357,0.01961963799528188 +flat_mae,patch,logistic,ppmi_dx,74,0.005994842503189409,test,0.59,0.04260833721233439,0.5249681381068243,0.049628287024344006,0.5318336162988115,0.04446781157887144 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,train,0.7188612099644128,0.015944301235401772,0.6634730538922156,0.021005389270884644,0.6603511025476343,0.0182259173601787 +flat_mae,patch,logistic,ppmi_dx,75,0.005994842503189409,test,0.65,0.04061144666224044,0.5944849959448499,0.04934550068721782,0.5955008488964346,0.0443856173500838 +flat_mae,patch,logistic,ppmi_dx,76,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,76,1291.5496650148827,test,0.6,0.04510600403493974,0.5604395604395604,0.04970621242594627,0.5602716468590832,0.04762052278896896 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,train,0.7900355871886121,0.01620882175424257,0.7666244369369369,0.01894997040567687,0.7572923356882895,0.018663621756946348 +flat_mae,patch,logistic,ppmi_dx,77,0.046415888336127774,test,0.66,0.045309932685891285,0.6353496353496353,0.04911131387376803,0.634125636672326,0.04862959823018387 +flat_mae,patch,logistic,ppmi_dx,78,0.3593813663804626,train,0.891459074733096,0.012838687304135404,0.8827705302032931,0.014151966556397767,0.8753211303789339,0.014736009591788292 +flat_mae,patch,logistic,ppmi_dx,78,0.3593813663804626,test,0.62,0.04664855410406629,0.5766488413547237,0.05241131927162618,0.5764006791171477,0.0496943289178841 +flat_mae,patch,logistic,ppmi_dx,79,0.046415888336127774,train,0.7633451957295374,0.016418349153575446,0.7324413039665238,0.01948453003196592,0.7234398415756798,0.018499113985129642 +flat_mae,patch,logistic,ppmi_dx,79,0.046415888336127774,test,0.63,0.043843042777617525,0.5847828526540231,0.04990939701534502,0.5844651952461799,0.04682505711885812 +flat_mae,patch,logistic,ppmi_dx,80,0.005994842503189409,train,0.7117437722419929,0.016465334964116392,0.6606887298747763,0.020889196850660013,0.6571799400556626,0.018531363202307603 +flat_mae,patch,logistic,ppmi_dx,80,0.005994842503189409,test,0.66,0.043232483157921886,0.6026180458158018,0.05288298382038853,0.6035653650254669,0.04723338501984354 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,train,0.7651245551601423,0.016362910378606467,0.7369249755308737,0.019205540845694567,0.728363840719332,0.01847049155278311 +flat_mae,patch,logistic,ppmi_dx,81,0.046415888336127774,test,0.65,0.04520594651149338,0.612789025334661,0.05068403077491324,0.6107809847198642,0.04834495826969563 +flat_mae,patch,logistic,ppmi_dx,82,0.3593813663804626,train,0.895017793594306,0.011392847568636738,0.8861312865948934,0.012673793492279721,0.877341575679726,0.013331473420071112 +flat_mae,patch,logistic,ppmi_dx,82,0.3593813663804626,test,0.69,0.04456341100050578,0.6615351020853806,0.049314595316680206,0.6583191850594228,0.04818599229948516 +flat_mae,patch,logistic,ppmi_dx,83,0.046415888336127774,train,0.7882562277580071,0.0175154325532699,0.7631421437552017,0.020333073377102415,0.7532380646542496,0.019661459301970087 +flat_mae,patch,logistic,ppmi_dx,83,0.046415888336127774,test,0.53,0.05092194418912145,0.5123975516132379,0.05199829048109705,0.5140067911714771,0.05294282183504052 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,train,0.7882562277580071,0.01576554187569726,0.7631421437552017,0.018608329420273493,0.7532380646542496,0.018139046159228983 +flat_mae,patch,logistic,ppmi_dx,84,0.046415888336127774,test,0.56,0.048851689837711855,0.5280995280995281,0.05165788048640389,0.5280135823429541,0.051199808766838335 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,train,0.7900355871886121,0.01619999967166163,0.765435766836446,0.019086599412358064,0.7555528794690645,0.018616746390453073 +flat_mae,patch,logistic,ppmi_dx,85,0.046415888336127774,test,0.62,0.03910388216021525,0.5634191176470589,0.04579952463966702,0.566213921901528,0.04167700230488661 +flat_mae,patch,logistic,ppmi_dx,86,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,86,1291.5496650148827,test,0.52,0.045950978226801664,0.4851994851994852,0.04869289651126707,0.48556876061120546,0.04797674756339242 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,train,0.7295373665480427,0.016033829056682564,0.6773628233019096,0.021566638059306604,0.6725005352172982,0.018818465525386324 +flat_mae,patch,logistic,ppmi_dx,87,0.005994842503189409,test,0.66,0.04313908204864818,0.6026180458158018,0.05254630674302509,0.6035653650254669,0.046691789862819355 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,train,0.7704626334519573,0.01658496626815012,0.7425670853173969,0.019595055322473118,0.7335688289445514,0.018865097770087342 +flat_mae,patch,logistic,ppmi_dx,88,0.046415888336127774,test,0.61,0.04222274268685065,0.5400400990682863,0.05113173483102542,0.547962648556876,0.04495435852714419 +flat_mae,patch,logistic,ppmi_dx,89,0.046415888336127774,train,0.7651245551601423,0.0158284114069314,0.7326008910420001,0.019218767087154594,0.723145472061657,0.018202576981860185 +flat_mae,patch,logistic,ppmi_dx,89,0.046415888336127774,test,0.67,0.041345466498758955,0.6239316239316239,0.05029896346168723,0.6218166383701189,0.04610751128287766 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,train,0.7046263345195729,0.016273539637994792,0.6523106738223017,0.02025627287613009,0.6496601370156283,0.018020866676519937 +flat_mae,patch,logistic,ppmi_dx,90,0.005994842503189409,test,0.62,0.04151001806793151,0.5634191176470589,0.048697514170143806,0.566213921901528,0.044288248532992916 +flat_mae,patch,logistic,ppmi_dx,91,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,ppmi_dx,91,21.54434690031882,test,0.62,0.047268661923096575,0.6041666666666667,0.04874345523701827,0.6069609507640068,0.049434249111011436 +flat_mae,patch,logistic,ppmi_dx,92,0.005994842503189409,train,0.708185053380783,0.015889849480827282,0.6518914672467973,0.02122290613563919,0.6499411260971955,0.018359599436280172 +flat_mae,patch,logistic,ppmi_dx,92,0.005994842503189409,test,0.68,0.03839029043912014,0.6190476190476191,0.048248894415075565,0.6196943972835314,0.04244589900160933 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,train,0.7188612099644128,0.01618742685971266,0.6634730538922156,0.021124200053307993,0.6603511025476343,0.018356819706231382 +flat_mae,patch,logistic,ppmi_dx,93,0.005994842503189409,test,0.6,0.04514798334366664,0.5659722222222222,0.04860213540956173,0.565365025466893,0.04742144322840052 +flat_mae,patch,logistic,ppmi_dx,94,0.046415888336127774,train,0.7615658362989324,0.01657822640421277,0.7315222816399287,0.0196107905713675,0.7228644829800899,0.01869296130365253 +flat_mae,patch,logistic,ppmi_dx,94,0.046415888336127774,test,0.67,0.04461914835583485,0.6396986570586308,0.04935268985788384,0.6370967741935484,0.04801692902602599 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,train,0.7224199288256228,0.01660015519255817,0.6721855790371069,0.02162708423918478,0.6675899165061014,0.019140131455613545 +flat_mae,patch,logistic,ppmi_dx,95,0.005994842503189409,test,0.59,0.03699065287339492,0.48589341692789967,0.04561065253033838,0.5114601018675722,0.037807361140664464 +flat_mae,patch,logistic,ppmi_dx,96,0.046415888336127774,train,0.7704626334519573,0.016686944685035728,0.7432381222220255,0.01981895195079996,0.734438557054164,0.01920234851955102 +flat_mae,patch,logistic,ppmi_dx,96,0.046415888336127774,test,0.59,0.04392265930018354,0.539894512400404,0.05012201955883044,0.5420203735144312,0.0469281918844686 +flat_mae,patch,logistic,ppmi_dx,97,0.3593813663804626,train,0.8825622775800712,0.013227229023666801,0.8722040765700583,0.01485559939478881,0.8628773281952473,0.015529507487170892 +flat_mae,patch,logistic,ppmi_dx,97,0.3593813663804626,test,0.64,0.04781411925362633,0.6279454319966928,0.04880458794067069,0.633276740237691,0.04994877399734933 +flat_mae,patch,logistic,ppmi_dx,98,0.046415888336127774,train,0.7793594306049823,0.015366023456502807,0.750886524822695,0.018772988570680525,0.740794262470563,0.018166840922068765 +flat_mae,patch,logistic,ppmi_dx,98,0.046415888336127774,test,0.67,0.04043548441653691,0.6108031607500884,0.05213378090545162,0.6116298811544991,0.045515019546338485 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,train,0.7811387900355872,0.015454661750604903,0.753890520694259,0.01836120338812398,0.7439788053949904,0.017742470030467333 +flat_mae,patch,logistic,ppmi_dx,99,0.046415888336127774,test,0.61,0.04303068672470845,0.5623386825272135,0.049213709472489195,0.5632427843803056,0.04594806734454578 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,train,0.7704626334519573,0.015692413236448696,0.7432381222220255,0.01848321027583966,0.734438557054164,0.017899727651610284 +flat_mae,patch,logistic,ppmi_dx,100,0.046415888336127774,test,0.64,0.04376563035076726,0.6043956043956044,0.0490330044494389,0.6027164685908319,0.04719577753887003 diff --git a/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d2ef8ca8f74d4f40a4a2c34a3a0397368110e02b --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:50:51 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (ppmi_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic +model: flat_mae +representation: patch +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/ppmi_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:17:26 time: 4.5090 data: 3.7592 max mem: 2708 +extract (train) [ 20/232] eta: 0:01:24 time: 0.1950 data: 0.0680 max mem: 2863 +extract (train) [ 40/232] eta: 0:00:54 time: 0.1580 data: 0.0479 max mem: 2863 +extract (train) [ 60/232] eta: 0:00:42 time: 0.1794 data: 0.0604 max mem: 2863 +extract (train) [ 80/232] eta: 0:00:35 time: 0.1778 data: 0.0612 max mem: 2863 +extract (train) [100/232] eta: 0:00:28 time: 0.1673 data: 0.0533 max mem: 2863 +extract (train) [120/232] eta: 0:00:23 time: 0.1693 data: 0.0535 max mem: 2863 +extract (train) [140/232] eta: 0:00:18 time: 0.1729 data: 0.0568 max mem: 2863 +extract (train) [160/232] eta: 0:00:14 time: 0.1704 data: 0.0555 max mem: 2863 +extract (train) [180/232] eta: 0:00:10 time: 0.1736 data: 0.0577 max mem: 2863 +extract (train) [200/232] eta: 0:00:06 time: 0.1820 data: 0.0602 max mem: 2863 +extract (train) [220/232] eta: 0:00:02 time: 0.1637 data: 0.0533 max mem: 2863 +extract (train) [231/232] eta: 0:00:00 time: 0.1560 data: 0.0497 max mem: 2863 +extract (train) Total time: 0:00:44 (0.1931 s / it) +extract (validation) [ 0/50] eta: 0:02:52 time: 3.4556 data: 3.2879 max mem: 2863 +extract (validation) [20/50] eta: 0:00:11 time: 0.2238 data: 0.0813 max mem: 2863 +extract (validation) [40/50] eta: 0:00:02 time: 0.1581 data: 0.0482 max mem: 2863 +extract (validation) [49/50] eta: 0:00:00 time: 0.1559 data: 0.0497 max mem: 2863 +extract (validation) Total time: 0:00:12 (0.2539 s / it) +extract (test) [ 0/50] eta: 0:02:54 time: 3.4904 data: 3.3225 max mem: 2863 +extract (test) [20/50] eta: 0:00:10 time: 0.2016 data: 0.0705 max mem: 2863 +extract (test) [40/50] eta: 0:00:02 time: 0.1578 data: 0.0491 max mem: 2863 +extract (test) [49/50] eta: 0:00:00 time: 0.1599 data: 0.0502 max mem: 2863 +extract (test) Total time: 0:00:12 (0.2470 s / it) +feature extraction time: 0:01:09 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | train | 0.79004 | 0.016503 | 0.76603 | 0.019314 | 0.75632 | 0.018824 | +| flat_mae | patch | logistic | ppmi_dx | | 0.046416 | test | 0.62 | 0.043389 | 0.56342 | 0.050181 | 0.56456 | 0.046333 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 10000.0, "split": "test", "acc": 0.61, "acc_std": 0.04411629630873381, "f1": 0.5793334052421529, "f1_std": 0.04844214340319935, "bacc": 0.5785229202037352, "bacc_std": 0.04771997048104614} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.65, "acc_std": 0.04597865156787441, "f1": 0.6178622120318812, "f1_std": 0.050207107642801195, "bacc": 0.615874363327674, "bacc_std": 0.04854764609908454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04278027115388588, "f1": 0.592944369063772, "f1_std": 0.05017025849674424, "bacc": 0.5925297113752122, "bacc_std": 0.04631889135034441} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04137583836008643, "f1": 0.6323529411764706, "f1_std": 0.04933795920562124, "bacc": 0.6298811544991512, "bacc_std": 0.04526785718093922} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04950433920375061, "f1": 0.5586380832282472, "f1_std": 0.050589534575090654, "bacc": 0.5594227504244482, "bacc_std": 0.05086860058378877} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.58, "acc_std": 0.04570880002800336, "f1": 0.525101763907734, "f1_std": 0.05291638721304515, "bacc": 0.5288624787775891, "bacc_std": 0.048691354527697635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.05031748801361212, "f1": 0.5416666666666666, "f1_std": 0.051142075882720434, "bacc": 0.5432937181663837, "bacc_std": 0.051751960437530546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.61, "acc_std": 0.048400099173452116, "f1": 0.5953937130407718, "f1_std": 0.048890222554707076, "bacc": 0.5988964346349746, "bacc_std": 0.04956883138160025} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.038065937529502665, "f1": 0.6357455075279261, "f1_std": 0.05060243084449114, "bacc": 0.6358234295415959, "bacc_std": 0.043129309945520285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03765835365493292, "f1": 0.6031746031746031, "f1_std": 0.05213300400264528, "bacc": 0.6095076400679117, "bacc_std": 0.04252579348687397} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.044573283477886166, "f1": 0.5863970588235294, "f1_std": 0.05363595683075175, "bacc": 0.5874363327674024, "bacc_std": 0.04839815153854416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04015619005832103, "f1": 0.5476190476190476, "f1_std": 0.0495827694319964, "bacc": 0.5560271646859083, "bacc_std": 0.0430017627722091} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04433934595818933, "f1": 0.5906626839252129, "f1_std": 0.04846200736332563, "bacc": 0.5895585738539898, "bacc_std": 0.04641242749953584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03628002205070996, "f1": 0.5062370062370062, "f1_std": 0.05045819592381781, "bacc": 0.5356536502546689, "bacc_std": 0.03906823358652263} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.045978360127346865, "f1": 0.5523528769516323, "f1_std": 0.04988622252676851, "bacc": 0.5522071307300509, "bacc_std": 0.048264777809328085} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.54, "acc_std": 0.050638368852086856, "f1": 0.5166036149642708, "f1_std": 0.05152939824655192, "bacc": 0.5169779286926994, "bacc_std": 0.0519014923235425} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.046780589992004164, "f1": 0.5623386825272135, "f1_std": 0.052778097933620524, "bacc": 0.5632427843803056, "bacc_std": 0.04935398030789127} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.042163922967390036, "f1": 0.5311936530833032, "f1_std": 0.05163735961001522, "bacc": 0.5428692699490663, "bacc_std": 0.044463118974973195} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.04658127950153366, "f1": 0.5920032639738881, "f1_std": 0.04688993456412704, "bacc": 0.601018675721562, "bacc_std": 0.048509631721798056} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04825490234162742, "f1": 0.5626666666666666, "f1_std": 0.051025219864154335, "bacc": 0.5623938879456706, "bacc_std": 0.05056924790847196} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.71, "acc_std": 0.040391340656135685, "f1": 0.6695156695156695, "f1_std": 0.04901448733159222, "bacc": 0.6642614601018676, "bacc_std": 0.04545880018501558} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04403218822634188, "f1": 0.5766488413547237, "f1_std": 0.049980353459064514, "bacc": 0.5764006791171477, "bacc_std": 0.047264171723210915} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04691462884857983, "f1": 0.5320855614973261, "f1_std": 0.052004798974323765, "bacc": 0.533955857385399, "bacc_std": 0.04909105456817088} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.049313673560180044, "f1": 0.609375, "f1_std": 0.05338291130435854, "bacc": 0.6078098471986417, "bacc_std": 0.05200398798070887} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.037103417632342164, "f1": 0.6033177064551027, "f1_std": 0.05021328488504345, "bacc": 0.6065365025466893, "bacc_std": 0.04236044872962906} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04680722593788272, "f1": 0.6009060511271707, "f1_std": 0.049328317123060725, "bacc": 0.5997453310696095, "bacc_std": 0.048467735051534726} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03818336810706987, "f1": 0.5287698412698413, "f1_std": 0.05092833683367362, "bacc": 0.5458404074702886, "bacc_std": 0.041644515848551895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.038393806792241886, "f1": 0.6114618746964546, "f1_std": 0.0517994074597162, "bacc": 0.6146010186757216, "bacc_std": 0.04364890997612452} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04612150908198907, "f1": 0.5623386825272135, "f1_std": 0.05210034230792149, "bacc": 0.5632427843803056, "bacc_std": 0.04893104439155929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 2.782559402207126, "split": "test", "acc": 0.6, "acc_std": 0.050354328513048406, "f1": 0.5755517826825127, "f1_std": 0.05269817401990444, "bacc": 0.5755517826825127, "bacc_std": 0.05258850814472098} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04422035730294364, "f1": 0.5863970588235294, "f1_std": 0.05165248078667233, "bacc": 0.5874363327674024, "bacc_std": 0.047226941656892465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.05135811133599054, "f1": 0.6041666666666667, "f1_std": 0.05245515742538223, "bacc": 0.6069609507640068, "bacc_std": 0.053019044027108934} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.04409660304377197, "f1": 0.6483516483516483, "f1_std": 0.0490376554209703, "bacc": 0.6451612903225806, "bacc_std": 0.047251920406046116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.044672582195346616, "f1": 0.6396986570586308, "f1_std": 0.0496662898493526, "bacc": 0.6370967741935484, "bacc_std": 0.04850449062407517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04572073490223009, "f1": 0.6178622120318812, "f1_std": 0.05014937299901063, "bacc": 0.615874363327674, "bacc_std": 0.04857385609647685} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.03619195490713371, "f1": 0.5862068965517242, "f1_std": 0.0521236009494688, "bacc": 0.5963497453310695, "bacc_std": 0.041445255306177674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04262211163234408, "f1": 0.5713127099988413, "f1_std": 0.0521476311910776, "bacc": 0.5742784380305602, "bacc_std": 0.046733558861084254} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 1291.5496650148827, "split": "test", "acc": 0.63, "acc_std": 0.04346078692338647, "f1": 0.5906626839252129, "f1_std": 0.04880285528025395, "bacc": 0.5895585738539898, "bacc_std": 0.046740429640491535} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.69, "acc_std": 0.04629031864223879, "f1": 0.6615351020853806, "f1_std": 0.05017032091054785, "bacc": 0.6583191850594228, "bacc_std": 0.04906479674374038} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.04393138286009216, "f1": 0.6381727725011307, "f1_std": 0.051886471502477986, "bacc": 0.634974533106961, "bacc_std": 0.04863755929272304} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.68, "acc_std": 0.046506618883767496, "f1": 0.6527777777777778, "f1_std": 0.05106711420121512, "bacc": 0.6502546689303905, "bacc_std": 0.05002543825556078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03434536941131948, "f1": 0.6363636363636364, "f1_std": 0.0500494178766777, "bacc": 0.6387945670628183, "bacc_std": 0.04055355605893765} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.043723362176301135, "f1": 0.5555555555555556, "f1_std": 0.04960911748096179, "bacc": 0.5581494057724957, "bacc_std": 0.045699166636240574} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.7, "acc_std": 0.04397999545247816, "f1": 0.6703296703296704, "f1_std": 0.04966390886569701, "bacc": 0.666383701188455, "bacc_std": 0.04827250613813292} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04171757902851027, "f1": 0.6176572818908586, "f1_std": 0.05063960648105099, "bacc": 0.616723259762309, "bacc_std": 0.04602890167340929} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04548087510151932, "f1": 0.5906626839252129, "f1_std": 0.05160029102270635, "bacc": 0.5895585738539898, "bacc_std": 0.04886606279278499} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 0.3593813663804626, "split": "test", "acc": 0.72, "acc_std": 0.038189862529210555, "f1": 0.6880570409982174, "f1_std": 0.0446011278104304, "bacc": 0.6825127334465195, "bacc_std": 0.04302844757462542} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.041097206717732045, "f1": 0.6695156695156695, "f1_std": 0.05007141536362938, "bacc": 0.6642614601018676, "bacc_std": 0.04639733884725464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 1291.5496650148827, "split": "test", "acc": 0.58, "acc_std": 0.04324791786895642, "f1": 0.525101763907734, "f1_std": 0.0485480798671048, "bacc": 0.5288624787775891, "bacc_std": 0.044920516912603445} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.04016438223102652, "f1": 0.6428571428571428, "f1_std": 0.05182328358410523, "bacc": 0.6409168081494058, "bacc_std": 0.04521793618647286} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.59, "acc_std": 0.04689919402292538, "f1": 0.5523528769516323, "f1_std": 0.05042145591008586, "bacc": 0.5522071307300509, "bacc_std": 0.04893703007916049} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.3593813663804626, "split": "test", "acc": 0.55, "acc_std": 0.04590295851031826, "f1": 0.508679986898133, "f1_std": 0.04876068556485285, "bacc": 0.5097623089983022, "bacc_std": 0.047220479796067104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 2.782559402207126, "split": "test", "acc": 0.59, "acc_std": 0.048553059635825215, "f1": 0.5626666666666666, "f1_std": 0.05152891702326979, "bacc": 0.5623938879456706, "bacc_std": 0.05121746847872511} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.52, "acc_std": 0.04693500186428035, "f1": 0.4652406417112299, "f1_std": 0.049616327662134835, "bacc": 0.4702886247877759, "bacc_std": 0.04739064052806034} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.042973754781261544, "f1": 0.6176572818908586, "f1_std": 0.052387581386575066, "bacc": 0.616723259762309, "bacc_std": 0.047177026134290104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.048734726838261855, "f1": 0.5960257670051315, "f1_std": 0.053169608547608424, "bacc": 0.5946519524617997, "bacc_std": 0.05130582081825587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.72, "acc_std": 0.04369209997242065, "f1": 0.6923076923076923, "f1_std": 0.049658181146406466, "bacc": 0.6876061120543294, "bacc_std": 0.0483031471065455} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04243112065453846, "f1": 0.5558672276764843, "f1_std": 0.05135017306682566, "bacc": 0.5611205432937181, "bacc_std": 0.045719173333764594} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04571084772786434, "f1": 0.5989304812834224, "f1_std": 0.05177266647412086, "bacc": 0.597623089983022, "bacc_std": 0.04877448508233287} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.044169722661569884, "f1": 0.5906626839252129, "f1_std": 0.04955038728656665, "bacc": 0.5895585738539898, "bacc_std": 0.047215681316423876} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04042664467897379, "f1": 0.592944369063772, "f1_std": 0.04723171475601195, "bacc": 0.5925297113752122, "bacc_std": 0.04383927215276605} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03829094409909477, "f1": 0.5386109762020399, "f1_std": 0.04987393738630591, "bacc": 0.5509337860780985, "bacc_std": 0.04159734042670936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.03631512632499026, "f1": 0.5628946090335114, "f1_std": 0.0472736977958344, "bacc": 0.5721561969439728, "bacc_std": 0.03953865594258082} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04116928466709132, "f1": 0.5386109762020399, "f1_std": 0.05151845058595703, "bacc": 0.5509337860780985, "bacc_std": 0.04381911580767996} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04333635886873746, "f1": 0.5703301673450927, "f1_std": 0.048776949398738965, "bacc": 0.5713073005093379, "bacc_std": 0.045409977899762026} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04511643159648157, "f1": 0.5766488413547237, "f1_std": 0.05052690433867025, "bacc": 0.5764006791171477, "bacc_std": 0.04764834453048925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.044403148537012556, "f1": 0.5847828526540231, "f1_std": 0.050742196464797495, "bacc": 0.5844651952461799, "bacc_std": 0.04758155077598606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.03967110283317064, "f1": 0.6640018537828757, "f1_std": 0.049662853121617404, "bacc": 0.6591680814940577, "bacc_std": 0.04506136438326521} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04572187222763302, "f1": 0.609375, "f1_std": 0.04961354771009108, "bacc": 0.6078098471986417, "bacc_std": 0.0483530301547729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04498525980807491, "f1": 0.592944369063772, "f1_std": 0.05186369520803708, "bacc": 0.5925297113752122, "bacc_std": 0.04826829474828846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04660933812016643, "f1": 0.5555555555555556, "f1_std": 0.05369097602564633, "bacc": 0.5581494057724957, "bacc_std": 0.049437382433988306} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04903329073190989, "f1": 0.5967741935483871, "f1_std": 0.05096471227592998, "bacc": 0.5967741935483871, "bacc_std": 0.05093053200555909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.6, "acc_std": 0.05248885214976605, "f1": 0.570999570999571, "f1_std": 0.055451753685265816, "bacc": 0.5704584040747029, "bacc_std": 0.05465424126308131} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.04260833721233439, "f1": 0.5249681381068243, "f1_std": 0.049628287024344006, "bacc": 0.5318336162988115, "bacc_std": 0.04446781157887144} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04061144666224044, "f1": 0.5944849959448499, "f1_std": 0.04934550068721782, "bacc": 0.5955008488964346, "bacc_std": 0.0443856173500838} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.04510600403493974, "f1": 0.5604395604395604, "f1_std": 0.04970621242594627, "bacc": 0.5602716468590832, "bacc_std": 0.04762052278896896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.045309932685891285, "f1": 0.6353496353496353, "f1_std": 0.04911131387376803, "bacc": 0.634125636672326, "bacc_std": 0.04862959823018387} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04664855410406629, "f1": 0.5766488413547237, "f1_std": 0.05241131927162618, "bacc": 0.5764006791171477, "bacc_std": 0.0496943289178841} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.043843042777617525, "f1": 0.5847828526540231, "f1_std": 0.04990939701534502, "bacc": 0.5844651952461799, "bacc_std": 0.04682505711885812} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.043232483157921886, "f1": 0.6026180458158018, "f1_std": 0.05288298382038853, "bacc": 0.6035653650254669, "bacc_std": 0.04723338501984354} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04520594651149338, "f1": 0.612789025334661, "f1_std": 0.05068403077491324, "bacc": 0.6107809847198642, "bacc_std": 0.04834495826969563} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.69, "acc_std": 0.04456341100050578, "f1": 0.6615351020853806, "f1_std": 0.049314595316680206, "bacc": 0.6583191850594228, "bacc_std": 0.04818599229948516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.53, "acc_std": 0.05092194418912145, "f1": 0.5123975516132379, "f1_std": 0.05199829048109705, "bacc": 0.5140067911714771, "bacc_std": 0.05294282183504052} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.048851689837711855, "f1": 0.5280995280995281, "f1_std": 0.05165788048640389, "bacc": 0.5280135823429541, "bacc_std": 0.051199808766838335} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.03910388216021525, "f1": 0.5634191176470589, "f1_std": 0.04579952463966702, "bacc": 0.566213921901528, "bacc_std": 0.04167700230488661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 1291.5496650148827, "split": "test", "acc": 0.52, "acc_std": 0.045950978226801664, "f1": 0.4851994851994852, "f1_std": 0.04869289651126707, "bacc": 0.48556876061120546, "bacc_std": 0.04797674756339242} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.04313908204864818, "f1": 0.6026180458158018, "f1_std": 0.05254630674302509, "bacc": 0.6035653650254669, "bacc_std": 0.046691789862819355} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04222274268685065, "f1": 0.5400400990682863, "f1_std": 0.05113173483102542, "bacc": 0.547962648556876, "bacc_std": 0.04495435852714419} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.041345466498758955, "f1": 0.6239316239316239, "f1_std": 0.05029896346168723, "bacc": 0.6218166383701189, "bacc_std": 0.04610751128287766} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04151001806793151, "f1": 0.5634191176470589, "f1_std": 0.048697514170143806, "bacc": 0.566213921901528, "bacc_std": 0.044288248532992916} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 21.54434690031882, "split": "test", "acc": 0.62, "acc_std": 0.047268661923096575, "f1": 0.6041666666666667, "f1_std": 0.04874345523701827, "bacc": 0.6069609507640068, "bacc_std": 0.049434249111011436} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03839029043912014, "f1": 0.6190476190476191, "f1_std": 0.048248894415075565, "bacc": 0.6196943972835314, "bacc_std": 0.04244589900160933} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04514798334366664, "f1": 0.5659722222222222, "f1_std": 0.04860213540956173, "bacc": 0.565365025466893, "bacc_std": 0.04742144322840052} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04461914835583485, "f1": 0.6396986570586308, "f1_std": 0.04935268985788384, "bacc": 0.6370967741935484, "bacc_std": 0.04801692902602599} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.03699065287339492, "f1": 0.48589341692789967, "f1_std": 0.04561065253033838, "bacc": 0.5114601018675722, "bacc_std": 0.037807361140664464} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04392265930018354, "f1": 0.539894512400404, "f1_std": 0.05012201955883044, "bacc": 0.5420203735144312, "bacc_std": 0.0469281918844686} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.04781411925362633, "f1": 0.6279454319966928, "f1_std": 0.04880458794067069, "bacc": 0.633276740237691, "bacc_std": 0.04994877399734933} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.04043548441653691, "f1": 0.6108031607500884, "f1_std": 0.05213378090545162, "bacc": 0.6116298811544991, "bacc_std": 0.045515019546338485} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04303068672470845, "f1": 0.5623386825272135, "f1_std": 0.049213709472489195, "bacc": 0.5632427843803056, "bacc_std": 0.04594806734454578} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04376563035076726, "f1": 0.6043956043956044, "f1_std": 0.0490330044494389, "bacc": 0.6027164685908319, "bacc_std": 0.04719577753887003} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | ppmi_dx | train | 100 | 155.35 | 1026.5 | 0.79724 | 0.091261 | 0.76707 | 0.10911 | 0.7608 | 0.10903 | +| flat_mae | patch | logistic | ppmi_dx | test | 100 | 155.35 | 1026.5 | 0.6319 | 0.043617 | 0.58621 | 0.046052 | 0.58778 | 0.042977 | + + +done! total time: 0:05:43 diff --git a/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/config.yaml b/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a15d7cc085858c4fc88363abd531bc8c19f90ac9 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..c36860aac8d5c85990fad77ee32c52403b601a15 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,ppmi_dx,,0.3593813663804626,train,0.9199288256227758,0.011544806503869522,0.9143858223734322,0.012500644801883636,0.9091364456020838,0.01318208905398755 +flat_mae,reg,logistic,ppmi_dx,,0.3593813663804626,test,0.58,0.04354199811676078,0.5320855614973261,0.048358851679126943,0.5328185328185329,0.046202045194424474 +flat_mae,reg,logistic,ppmi_dx,1,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,1,21.54434690031882,test,0.63,0.0499095341593167,0.6009060511271707,0.054024798870955744,0.5997453310696095,0.05324684926424627 +flat_mae,reg,logistic,ppmi_dx,2,0.046415888336127774,train,0.7846975088967971,0.016199863645192207,0.7609897544944906,0.018630956130374063,0.75208734746307,0.018188815174353987 +flat_mae,reg,logistic,ppmi_dx,2,0.046415888336127774,test,0.66,0.04210168167662664,0.6212121212121212,0.04814600750829279,0.6188455008488964,0.04568957278232296 +flat_mae,reg,logistic,ppmi_dx,3,0.046415888336127774,train,0.7846975088967971,0.01674409369597753,0.7591613394485666,0.01979025857261812,0.7494781631342324,0.01927506399712674 +flat_mae,reg,logistic,ppmi_dx,3,0.046415888336127774,test,0.63,0.04763845505471394,0.6129302228266555,0.04884520040868717,0.615025466893039,0.049130755425708356 +flat_mae,reg,logistic,ppmi_dx,4,0.046415888336127774,train,0.8096085409252669,0.016087969436921985,0.7875746689133576,0.019020397602393914,0.7766672018839649,0.01875032862793181 +flat_mae,reg,logistic,ppmi_dx,4,0.046415888336127774,test,0.63,0.04426314042180017,0.5906626839252129,0.04923334630554499,0.5895585738539898,0.047033716077161856 +flat_mae,reg,logistic,ppmi_dx,5,0.005994842503189409,train,0.7259786476868327,0.01738071697534277,0.6763883280238105,0.022554453573626853,0.6713498180261186,0.01995629060699903 +flat_mae,reg,logistic,ppmi_dx,5,0.005994842503189409,test,0.64,0.04348128792940706,0.5792426367461431,0.05171450501923204,0.5823429541595926,0.04621802508265062 +flat_mae,reg,logistic,ppmi_dx,6,0.005994842503189409,train,0.7330960854092526,0.01586960550456695,0.6858228980322003,0.020899631822170462,0.6797393491757653,0.01859380209580954 +flat_mae,reg,logistic,ppmi_dx,6,0.005994842503189409,test,0.62,0.0453374194236946,0.5634191176470589,0.0540525709838087,0.566213921901528,0.049034241408607626 +flat_mae,reg,logistic,ppmi_dx,7,0.046415888336127774,train,0.8238434163701067,0.014582608180352204,0.8063303432503838,0.016763004675342582,0.7969251766217085,0.016935175572594056 +flat_mae,reg,logistic,ppmi_dx,7,0.046415888336127774,test,0.55,0.05081856353735315,0.52,0.053405901882583866,0.5199490662139219,0.05326431035415618 +flat_mae,reg,logistic,ppmi_dx,8,0.3593813663804626,train,0.9181494661921709,0.012074692191201627,0.9122256627553238,0.013122520849959166,0.9065644401627061,0.01377128686796211 +flat_mae,reg,logistic,ppmi_dx,8,0.3593813663804626,test,0.5,0.04391499060685315,0.4429590017825312,0.04570295050277101,0.4490662139219015,0.0438706597530806 +flat_mae,reg,logistic,ppmi_dx,9,0.005994842503189409,train,0.708185053380783,0.016209720261764343,0.6518914672467973,0.021808655671185406,0.6499411260971955,0.018864084534540915 +flat_mae,reg,logistic,ppmi_dx,9,0.005994842503189409,test,0.78,0.03523359760228865,0.7428705002337541,0.045358602981809236,0.730899830220713,0.042108335195176455 +flat_mae,reg,logistic,ppmi_dx,10,0.005994842503189409,train,0.7206405693950177,0.015953816830959037,0.6716935498874439,0.02047261332584741,0.6670145579105117,0.018258036569030148 +flat_mae,reg,logistic,ppmi_dx,10,0.005994842503189409,test,0.67,0.03914246287601228,0.6033177064551027,0.050755661227283505,0.6065365025466893,0.04327769545210837 +flat_mae,reg,logistic,ppmi_dx,11,0.3593813663804626,train,0.9199288256227758,0.011423855605427458,0.9140482947304025,0.01242956836260366,0.9080095268679084,0.013067795073895579 +flat_mae,reg,logistic,ppmi_dx,11,0.3593813663804626,test,0.57,0.047996249853504175,0.5413333333333333,0.05048827666393301,0.5411714770797962,0.05002647680022573 +flat_mae,reg,logistic,ppmi_dx,12,0.005994842503189409,train,0.7295373665480427,0.015787373341594434,0.6875585205992509,0.01986700192626371,0.6811978163134232,0.01818331710024032 +flat_mae,reg,logistic,ppmi_dx,12,0.005994842503189409,test,0.56,0.03847876817155143,0.45436507936507936,0.04527729999237772,0.48217317487266553,0.03868030804179343 +flat_mae,reg,logistic,ppmi_dx,13,0.046415888336127774,train,0.8131672597864769,0.015243220478963149,0.793106349857478,0.017535940836663513,0.7830362877328195,0.01742610063570322 +flat_mae,reg,logistic,ppmi_dx,13,0.046415888336127774,test,0.65,0.039885155133207145,0.6011396011396011,0.04804363549864813,0.6005942275042444,0.04397945666662895 +flat_mae,reg,logistic,ppmi_dx,14,0.046415888336127774,train,0.7953736654804271,0.015472080213857669,0.7711037523684723,0.018343737830241943,0.7607578676942839,0.01797253675144076 +flat_mae,reg,logistic,ppmi_dx,14,0.046415888336127774,test,0.63,0.04439467986144286,0.5783475783475784,0.05141474779768542,0.5793718166383701,0.0474373160900983 +flat_mae,reg,logistic,ppmi_dx,15,0.046415888336127774,train,0.8131672597864769,0.015135299093726292,0.7941054350442948,0.01743142951536868,0.7847757439520446,0.017497462400743718 +flat_mae,reg,logistic,ppmi_dx,15,0.046415888336127774,test,0.61,0.04706803586299305,0.568536342515765,0.051516055534118636,0.5683361629881154,0.04934460898772196 +flat_mae,reg,logistic,ppmi_dx,16,0.046415888336127774,train,0.8167259786476868,0.01533675713278589,0.7955158027857554,0.01808398640156701,0.7841870049239992,0.017994534698467058 +flat_mae,reg,logistic,ppmi_dx,16,0.046415888336127774,test,0.55,0.048707929539244424,0.5146154675870995,0.050689247473681615,0.514855687606112,0.049825374363380595 +flat_mae,reg,logistic,ppmi_dx,17,0.046415888336127774,train,0.8078291814946619,0.01648828263470277,0.785314091680815,0.019378045154063186,0.7743523870691501,0.01904665337147378 +flat_mae,reg,logistic,ppmi_dx,17,0.046415888336127774,test,0.57,0.04434322496165564,0.5174503422735944,0.04843969882898947,0.5207979626485568,0.045613584303229204 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,train,0.7330960854092526,0.015199687784035526,0.6847938259972182,0.019803881503972304,0.6788696210661529,0.01754781471438217 +flat_mae,reg,logistic,ppmi_dx,18,0.005994842503189409,test,0.62,0.04240715034047914,0.5558672276764843,0.05131996911709308,0.5611205432937181,0.045468044677054474 +flat_mae,reg,logistic,ppmi_dx,19,0.046415888336127774,train,0.802491103202847,0.016033274170443545,0.7801925983869092,0.018653629827181564,0.7700171269535432,0.018302477389091094 +flat_mae,reg,logistic,ppmi_dx,19,0.046415888336127774,test,0.59,0.04521965944144206,0.5710848415106182,0.04675125417406717,0.5725806451612903,0.04736585454706807 +flat_mae,reg,logistic,ppmi_dx,20,0.046415888336127774,train,0.7935943060498221,0.015503130567988119,0.770579954954955,0.01804358274688581,0.7610522372083066,0.017727708787101445 +flat_mae,reg,logistic,ppmi_dx,20,0.046415888336127774,test,0.63,0.04106646320295918,0.5713127099988413,0.04917540729999301,0.5742784380305602,0.04414824549432513 +flat_mae,reg,logistic,ppmi_dx,21,0.005994842503189409,train,0.7153024911032029,0.016798504077398028,0.6626650660264106,0.02151595673790513,0.6592003853564548,0.018921298794963695 +flat_mae,reg,logistic,ppmi_dx,21,0.005994842503189409,test,0.71,0.037623497976663464,0.6514004087029691,0.0508607518159989,0.648981324278438,0.04345985814659336 +flat_mae,reg,logistic,ppmi_dx,22,0.005994842503189409,train,0.7224199288256228,0.01718433778998563,0.6783623156504512,0.021431626266554416,0.6728082851637764,0.019511241642920958 +flat_mae,reg,logistic,ppmi_dx,22,0.005994842503189409,test,0.64,0.03614636911226355,0.54337899543379,0.05056223376470784,0.5619694397283531,0.03976464843296028 +flat_mae,reg,logistic,ppmi_dx,23,0.005994842503189409,train,0.7224199288256228,0.016107824192856113,0.6732558139534883,0.020690823169070796,0.6684596446157139,0.018390346602527127 +flat_mae,reg,logistic,ppmi_dx,23,0.005994842503189409,test,0.66,0.046655760630387316,0.6263736263736264,0.052702826489222455,0.6239388794567062,0.050929229309464745 +flat_mae,reg,logistic,ppmi_dx,24,0.005994842503189409,train,0.7366548042704626,0.01641969898044655,0.6900119260584376,0.02139169111352111,0.6834992506957824,0.019083524904252518 +flat_mae,reg,logistic,ppmi_dx,24,0.005994842503189409,test,0.57,0.04264961899009181,0.5017958521608157,0.049587174663170634,0.5106112054329371,0.044631107826413045 +flat_mae,reg,logistic,ppmi_dx,25,0.046415888336127774,train,0.7935943060498221,0.01641484332762879,0.7717111160914387,0.018716030273865758,0.7627916934275316,0.018342052005656303 +flat_mae,reg,logistic,ppmi_dx,25,0.046415888336127774,test,0.62,0.0396278487934937,0.5476190476190476,0.04981329270370754,0.5560271646859083,0.04282157648878089 +flat_mae,reg,logistic,ppmi_dx,26,0.046415888336127774,train,0.8149466192170819,0.014999757684326716,0.7948242694862182,0.017403403062683735,0.7844813744380219,0.017321775257132157 +flat_mae,reg,logistic,ppmi_dx,26,0.046415888336127774,test,0.64,0.04607841577137825,0.6043956043956044,0.050138194376756616,0.6027164685908319,0.048257252429533326 +flat_mae,reg,logistic,ppmi_dx,27,0.005994842503189409,train,0.7153024911032029,0.016574807116508355,0.6568200900694603,0.02257537680825537,0.6548517448083923,0.01929538888017567 +flat_mae,reg,logistic,ppmi_dx,27,0.005994842503189409,test,0.62,0.03941084114809021,0.5476190476190476,0.04990915551316597,0.5560271646859083,0.04299317738417799 +flat_mae,reg,logistic,ppmi_dx,28,0.005994842503189409,train,0.7153024911032029,0.015535287908519026,0.661532438983995,0.020325292603171872,0.6583306572468423,0.017737296850102124 +flat_mae,reg,logistic,ppmi_dx,28,0.005994842503189409,test,0.68,0.03852489584671189,0.6114618746964546,0.05201087211814649,0.6146010186757216,0.043857000934164676 +flat_mae,reg,logistic,ppmi_dx,29,0.3593813663804626,train,0.9110320284697508,0.012479640592308952,0.9044022589644145,0.01360556329759358,0.8981749090130593,0.014215318587897754 +flat_mae,reg,logistic,ppmi_dx,29,0.3593813663804626,test,0.56,0.046043440357992356,0.5024875621890548,0.050775333996672244,0.5076400679117148,0.047358969640841644 +flat_mae,reg,logistic,ppmi_dx,30,0.005994842503189409,train,0.7099644128113879,0.016243895328992904,0.6546024229033365,0.020823008683471665,0.6522559409120103,0.018223087430562803 +flat_mae,reg,logistic,ppmi_dx,30,0.005994842503189409,test,0.66,0.03643064094961822,0.5687468290208015,0.053569408143431065,0.5831918505942275,0.04165502730115667 +flat_mae,reg,logistic,ppmi_dx,31,0.3593813663804626,train,0.9234875444839857,0.011002865253246858,0.9173628327662557,0.012163118870109678,0.909160244059088,0.013158085247429717 +flat_mae,reg,logistic,ppmi_dx,31,0.3593813663804626,test,0.61,0.05127496075083822,0.5920075321686369,0.05209542374417806,0.5938030560271647,0.0523710449837072 +flat_mae,reg,logistic,ppmi_dx,32,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,32,166.81005372000556,test,0.6,0.05312399081394394,0.5833333333333333,0.053977144259582284,0.5857385398981324,0.0545336239343147 +flat_mae,reg,logistic,ppmi_dx,33,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,33,2.782559402207126,test,0.63,0.049589982859444506,0.6214833759590792,0.05029220533003846,0.6303056027164686,0.05171418696238178 +flat_mae,reg,logistic,ppmi_dx,34,0.046415888336127774,train,0.7900355871886121,0.016097898892540242,0.765435766836446,0.018741563699481826,0.7555528794690645,0.01828985451586833 +flat_mae,reg,logistic,ppmi_dx,34,0.046415888336127774,test,0.65,0.04650056343744664,0.6072270227808326,0.05370823895507381,0.6056876061120543,0.050432288295400765 +flat_mae,reg,logistic,ppmi_dx,35,0.005994842503189409,train,0.7259786476868327,0.016700721446470917,0.6774448419797257,0.0215454804460664,0.6722195461357311,0.019189982397830287 +flat_mae,reg,logistic,ppmi_dx,35,0.005994842503189409,test,0.63,0.046046081266487814,0.5906626839252129,0.05138675883852866,0.5895585738539898,0.0491727806558091 +flat_mae,reg,logistic,ppmi_dx,36,0.005994842503189409,train,0.7259786476868327,0.016114936445944507,0.6774448419797257,0.021020993103054962,0.6722195461357311,0.018690755031006857 +flat_mae,reg,logistic,ppmi_dx,36,0.005994842503189409,test,0.68,0.03688221251497799,0.6114618746964546,0.04946295362840079,0.6146010186757216,0.04162095411365629 +flat_mae,reg,logistic,ppmi_dx,37,0.3593813663804626,train,0.9234875444839857,0.011009833602832385,0.9178683705201625,0.012031135846886493,0.9117694283879255,0.012912977079161803 +flat_mae,reg,logistic,ppmi_dx,37,0.3593813663804626,test,0.63,0.04796446601391492,0.6093337556752191,0.050244278041146354,0.6099320882852293,0.050617103929864606 +flat_mae,reg,logistic,ppmi_dx,38,0.046415888336127774,train,0.802491103202847,0.015300531199492358,0.7801925983869092,0.017998590517576876,0.7700171269535432,0.017794581256506736 +flat_mae,reg,logistic,ppmi_dx,38,0.046415888336127774,test,0.61,0.045690979416072926,0.5793334052421529,0.04965550730732412,0.5785229202037352,0.04858393154968167 +flat_mae,reg,logistic,ppmi_dx,39,0.005994842503189409,train,0.7170818505338078,0.016152325147784162,0.6630784370652179,0.021702199457926986,0.6597757439520445,0.018854125799563425 +flat_mae,reg,logistic,ppmi_dx,39,0.005994842503189409,test,0.7,0.03865773402567718,0.6428571428571428,0.05041086680147096,0.6409168081494058,0.04378706538615221 +flat_mae,reg,logistic,ppmi_dx,40,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,40,1291.5496650148827,test,0.6,0.04756002943649215,0.5796553173602353,0.04925722117584302,0.5806451612903225,0.04968476100493029 +flat_mae,reg,logistic,ppmi_dx,41,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,41,2.782559402207126,test,0.57,0.04791868111707583,0.5538956323270048,0.04917490693650139,0.5564516129032258,0.050170819928362545 +flat_mae,reg,logistic,ppmi_dx,42,0.3593813663804626,train,0.9128113879003559,0.011410407029735522,0.9056332863864245,0.01267259852277757,0.8970108113894242,0.013530330924586163 +flat_mae,reg,logistic,ppmi_dx,42,0.3593813663804626,test,0.64,0.045742758989811706,0.5989304812834224,0.05187369591013659,0.597623089983022,0.049264856770046335 +flat_mae,reg,logistic,ppmi_dx,43,0.005994842503189409,train,0.7135231316725978,0.01595622986528413,0.6611199125103463,0.020778274905478306,0.6577552986512524,0.018297930863894852 +flat_mae,reg,logistic,ppmi_dx,43,0.005994842503189409,test,0.68,0.041211571190625566,0.6259934548854604,0.05177287287423394,0.6247877758913413,0.046035247875031375 +flat_mae,reg,logistic,ppmi_dx,44,0.005994842503189409,train,0.7313167259786477,0.01614805730778995,0.6832124472250946,0.021045447751132835,0.6774245343609505,0.018719871226887792 +flat_mae,reg,logistic,ppmi_dx,44,0.005994842503189409,test,0.67,0.04073816883464449,0.6176572818908586,0.0496837635072147,0.616723259762309,0.044971009872502334 +flat_mae,reg,logistic,ppmi_dx,45,0.005994842503189409,train,0.7224199288256228,0.015552444662269701,0.6699941280093952,0.02053410701878903,0.6658504602868764,0.01794643777568048 +flat_mae,reg,logistic,ppmi_dx,45,0.005994842503189409,test,0.74,0.03669705165268732,0.6843127731908694,0.050989509718079286,0.6782682512733447,0.04387098742029657 +flat_mae,reg,logistic,ppmi_dx,46,0.046415888336127774,train,0.802491103202847,0.01596881498858522,0.7807426673461857,0.018354163144955044,0.7708868550631557,0.0180212293000464 +flat_mae,reg,logistic,ppmi_dx,46,0.046415888336127774,test,0.61,0.0442713225463166,0.5623386825272135,0.050510839882907756,0.5632427843803056,0.047212381589857626 +flat_mae,reg,logistic,ppmi_dx,47,2.782559402207126,train,0.998220640569395,0.0018318796998606298,0.9981216765874674,0.00193059180307546,0.9985549132947977,0.0014877404498868164 +flat_mae,reg,logistic,ppmi_dx,47,2.782559402207126,test,0.59,0.04866250712817825,0.5710848415106182,0.05014159919338645,0.5725806451612903,0.051157973303087766 +flat_mae,reg,logistic,ppmi_dx,48,0.046415888336127774,train,0.806049822064057,0.015293342875009379,0.7830461652883781,0.018054724643660678,0.7720375722543353,0.017726761183882483 +flat_mae,reg,logistic,ppmi_dx,48,0.046415888336127774,test,0.63,0.04638868827634599,0.6053333333333333,0.04935873887456703,0.6048387096774194,0.048959503632948306 +flat_mae,reg,logistic,ppmi_dx,49,0.046415888336127774,train,0.7953736654804271,0.01651004860357136,0.7705055411744236,0.019281628012291444,0.7598881395846714,0.01864899125653171 +flat_mae,reg,logistic,ppmi_dx,49,0.046415888336127774,test,0.64,0.044743285529786486,0.5863970588235294,0.05353469354780367,0.5874363327674024,0.04854915897929678 +flat_mae,reg,logistic,ppmi_dx,50,0.005994842503189409,train,0.7206405693950177,0.01491114074311263,0.6650227977661606,0.019759758672316382,0.6617961892528367,0.017129068925858054 +flat_mae,reg,logistic,ppmi_dx,50,0.005994842503189409,test,0.67,0.039075700889427425,0.5951417004048583,0.052739327808502864,0.6014431239388794,0.04393279030214322 +flat_mae,reg,logistic,ppmi_dx,51,0.046415888336127774,train,0.802491103202847,0.015844162548415176,0.7823400313325402,0.01823087962020882,0.7734960393919932,0.018113634137942865 +flat_mae,reg,logistic,ppmi_dx,51,0.046415888336127774,test,0.58,0.04669497189205706,0.5384615384615385,0.05086803867027863,0.5390492359932089,0.04897482452983264 +flat_mae,reg,logistic,ppmi_dx,52,0.046415888336127774,train,0.7900355871886121,0.017000018624224997,0.7683364773283029,0.0194227829653287,0.759901520017127,0.01907938665515337 +flat_mae,reg,logistic,ppmi_dx,52,0.046415888336127774,test,0.58,0.04668728306509171,0.5320855614973261,0.051199483258458,0.533955857385399,0.04847390378553142 +flat_mae,reg,logistic,ppmi_dx,53,0.046415888336127774,train,0.7900355871886121,0.017083064532780176,0.764826872065478,0.02003620670402816,0.754683151359452,0.019468364983570737 +flat_mae,reg,logistic,ppmi_dx,53,0.046415888336127774,test,0.65,0.04703708749486941,0.6178622120318812,0.051049288554219543,0.615874363327674,0.049527339883342306 +flat_mae,reg,logistic,ppmi_dx,54,0.005994842503189409,train,0.7348754448398577,0.017072750764224015,0.686378055677277,0.022408136216410544,0.6803147077713552,0.01981045649533842 +flat_mae,reg,logistic,ppmi_dx,54,0.005994842503189409,test,0.57,0.047982742731111146,0.5305164319248826,0.05052836018375847,0.5309847198641766,0.04913540068809277 +flat_mae,reg,logistic,ppmi_dx,55,0.005994842503189409,train,0.7206405693950177,0.01568584574595831,0.6661786126402209,0.020889157360326146,0.6626659173624492,0.01811440611979903 +flat_mae,reg,logistic,ppmi_dx,55,0.005994842503189409,test,0.66,0.042499294111784956,0.6155585707824514,0.04943120535513247,0.6137521222410866,0.04571566592788445 +flat_mae,reg,logistic,ppmi_dx,56,0.046415888336127774,train,0.7811387900355872,0.01565386986651702,0.7582288442369236,0.01808574275254291,0.7500669021622779,0.017844142392298527 +flat_mae,reg,logistic,ppmi_dx,56,0.046415888336127774,test,0.61,0.047181670169675005,0.5793334052421529,0.050412926793411944,0.5785229202037352,0.04946618494288171 +flat_mae,reg,logistic,ppmi_dx,57,0.046415888336127774,train,0.800711743772242,0.016156255973600757,0.778490990990991,0.018760648878794528,0.7685720402483409,0.01845227668246743 +flat_mae,reg,logistic,ppmi_dx,57,0.046415888336127774,test,0.72,0.043011328740228436,0.6783088235294117,0.052227059790612367,0.6723259762308998,0.048476900966668235 +flat_mae,reg,logistic,ppmi_dx,58,0.005994842503189409,train,0.7313167259786477,0.015664421344969776,0.6842402932038474,0.02071962946588703,0.678294262470563,0.018445006556207486 +flat_mae,reg,logistic,ppmi_dx,58,0.005994842503189409,test,0.67,0.041969031439860506,0.6108031607500884,0.05240800584549883,0.6116298811544991,0.046379951187567006 +flat_mae,reg,logistic,ppmi_dx,59,0.005994842503189409,train,0.708185053380783,0.01587917543226529,0.6597711332595053,0.01981720856183081,0.6560292228644831,0.01779677041817575 +flat_mae,reg,logistic,ppmi_dx,59,0.005994842503189409,test,0.69,0.03789443758653767,0.6196785670469881,0.05245995483730231,0.6226655348047538,0.04347693740996444 +flat_mae,reg,logistic,ppmi_dx,60,0.3593813663804626,train,0.9128113879003559,0.011293206720320281,0.9062194569596415,0.01230409905794127,0.8996199957182616,0.012854721036961215 +flat_mae,reg,logistic,ppmi_dx,60,0.3593813663804626,test,0.62,0.04644109817823003,0.6072757337742869,0.047936782162365396,0.6120543293718166,0.04935185637806466 +flat_mae,reg,logistic,ppmi_dx,61,0.046415888336127774,train,0.791814946619217,0.01557576849720642,0.7688909196351686,0.017950148153836325,0.7596071505031042,0.01762499828552097 +flat_mae,reg,logistic,ppmi_dx,61,0.046415888336127774,test,0.63,0.04257922028407754,0.5783475783475784,0.04873715782009806,0.5793718166383701,0.0449064610724365 +flat_mae,reg,logistic,ppmi_dx,62,0.005994842503189409,train,0.7224199288256228,0.017012347853354703,0.6783623156504512,0.02127756324233299,0.6728082851637764,0.01935683424565014 +flat_mae,reg,logistic,ppmi_dx,62,0.005994842503189409,test,0.62,0.036802059724966495,0.5287698412698413,0.048861619657422584,0.5458404074702886,0.03955898805316649 +flat_mae,reg,logistic,ppmi_dx,63,0.005994842503189409,train,0.7348754448398577,0.015634438208957165,0.6904039190313338,0.020059712787642958,0.6837936202098052,0.018076180592566563 +flat_mae,reg,logistic,ppmi_dx,63,0.005994842503189409,test,0.59,0.04104555517958065,0.5071523019593701,0.05178173417539456,0.5216468590831919,0.04400866843053116 +flat_mae,reg,logistic,ppmi_dx,64,0.046415888336127774,train,0.8274021352313167,0.01524562636424146,0.8088696755826226,0.017584360916257927,0.798075893812888,0.017628300547944783 +flat_mae,reg,logistic,ppmi_dx,64,0.046415888336127774,test,0.54,0.04430806247174435,0.47987336047037543,0.04779675411931733,0.4864176570458404,0.044802691676399664 +flat_mae,reg,logistic,ppmi_dx,65,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,65,1291.5496650148827,test,0.52,0.0480700280840359,0.5104039167686658,0.04800241410382182,0.5161290322580645,0.049512145440414955 +flat_mae,reg,logistic,ppmi_dx,66,0.005994842503189409,train,0.7330960854092526,0.016064470042006524,0.6878332740846071,0.020615991800334632,0.6814788053949904,0.01853356141003599 +flat_mae,reg,logistic,ppmi_dx,66,0.005994842503189409,test,0.6,0.04469172630364596,0.5404411764705883,0.05143716496628181,0.5449915110356536,0.046821136427767245 +flat_mae,reg,logistic,ppmi_dx,67,0.046415888336127774,train,0.798932384341637,0.016135205807582972,0.7750845566751076,0.019084063785797033,0.764517769214301,0.01869632608596061 +flat_mae,reg,logistic,ppmi_dx,67,0.046415888336127774,test,0.63,0.04625408090104051,0.6009060511271707,0.049856758039558004,0.5997453310696095,0.04911023474556803 +flat_mae,reg,logistic,ppmi_dx,68,0.3593813663804626,train,0.9145907473309609,0.011898995201375006,0.9084093872229465,0.01292856667746339,0.902804538642689,0.013514912262884687 +flat_mae,reg,logistic,ppmi_dx,68,0.3593813663804626,test,0.69,0.046626155749750584,0.6656239887822242,0.05020280687507287,0.6634125636672326,0.04952580908554402 +flat_mae,reg,logistic,ppmi_dx,69,0.046415888336127774,train,0.7953736654804271,0.015961961343344353,0.7716924011685619,0.018466407509462227,0.7616275958038964,0.018004556902192433 +flat_mae,reg,logistic,ppmi_dx,69,0.046415888336127774,test,0.66,0.04509248717912996,0.6310763888888888,0.04896250993443045,0.6290322580645161,0.04817594200140022 +flat_mae,reg,logistic,ppmi_dx,70,0.046415888336127774,train,0.7900355871886121,0.01616246581119386,0.7660349134220517,0.018995892309102213,0.756422607578677,0.018631367337901893 +flat_mae,reg,logistic,ppmi_dx,70,0.046415888336127774,test,0.61,0.046041455233300346,0.5623386825272135,0.05173753041858209,0.5632427843803056,0.0484844846279608 +flat_mae,reg,logistic,ppmi_dx,71,0.046415888336127774,train,0.8078291814946619,0.01586121395669284,0.7847567981616239,0.018736707858522748,0.7734826589595376,0.01837098604231185 +flat_mae,reg,logistic,ppmi_dx,71,0.046415888336127774,test,0.65,0.041400212559840804,0.5872154735228211,0.050707433483875276,0.5904074702886248,0.04471203379112382 +flat_mae,reg,logistic,ppmi_dx,72,0.005994842503189409,train,0.7224199288256228,0.016713542738144762,0.6721855790371069,0.021434952100248587,0.6675899165061014,0.01898171342562595 +flat_mae,reg,logistic,ppmi_dx,72,0.005994842503189409,test,0.67,0.044998151073127435,0.6296711929076422,0.05150344821002075,0.6269100169779287,0.04851048304931694 +flat_mae,reg,logistic,ppmi_dx,73,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,73,10000.0,test,0.57,0.05190367617038315,0.5538956323270048,0.05245027154668126,0.5564516129032258,0.05338190724600396 +flat_mae,reg,logistic,ppmi_dx,74,0.005994842503189409,train,0.7402135231316725,0.016948797876877815,0.6980540508714084,0.02114676330420251,0.6907380646542496,0.019312503249666026 +flat_mae,reg,logistic,ppmi_dx,74,0.005994842503189409,test,0.61,0.04368294403997972,0.5481404240528328,0.05109579914536465,0.5530560271646858,0.046102485084373555 +flat_mae,reg,logistic,ppmi_dx,75,0.3593813663804626,train,0.9110320284697508,0.01164845335099452,0.9036047038160189,0.012937789145574988,0.8946959965746093,0.013783733784779045 +flat_mae,reg,logistic,ppmi_dx,75,0.3593813663804626,test,0.58,0.04867052907047549,0.5543293718166383,0.05083008140614569,0.5543293718166383,0.050887470304247374 +flat_mae,reg,logistic,ppmi_dx,76,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,76,1291.5496650148827,test,0.56,0.05004587895121834,0.537620849096259,0.05211677438708133,0.5382003395585738,0.052493046193019255 +flat_mae,reg,logistic,ppmi_dx,77,0.046415888336127774,train,0.798932384341637,0.016636268847525833,0.7756629681047609,0.019597058014705248,0.7653874973239134,0.019288228013552594 +flat_mae,reg,logistic,ppmi_dx,77,0.046415888336127774,test,0.65,0.044421634368852304,0.6178622120318812,0.048562329345000044,0.615874363327674,0.047126602233577904 +flat_mae,reg,logistic,ppmi_dx,78,0.3593813663804626,train,0.9199288256227758,0.010478330878110316,0.9143858223734322,0.011356195457972014,0.9097489830871334,0.012053707929262539 +flat_mae,reg,logistic,ppmi_dx,78,0.3593813663804626,test,0.57,0.049833322185060064,0.5413333333333333,0.05331476039137783,0.5411714770797962,0.05298410108665623 +flat_mae,reg,logistic,ppmi_dx,79,0.046415888336127774,train,0.802491103202847,0.015687973862299934,0.7796335350409598,0.018505159147998714,0.7691473988439306,0.01821656700752534 +flat_mae,reg,logistic,ppmi_dx,79,0.046415888336127774,test,0.64,0.044695820833720014,0.5863970588235294,0.05248300962755759,0.5874363327674024,0.047851373985115304 +flat_mae,reg,logistic,ppmi_dx,80,0.046415888336127774,train,0.802491103202847,0.015212238608859108,0.7801925983869092,0.017700988553408632,0.7700171269535432,0.017395899434192837 +flat_mae,reg,logistic,ppmi_dx,80,0.046415888336127774,test,0.67,0.044784300820711706,0.6396986570586308,0.049418959626811094,0.6370967741935484,0.04801940686605571 +flat_mae,reg,logistic,ppmi_dx,81,0.005994842503189409,train,0.7224199288256228,0.01562638274171951,0.6710984393757502,0.02034070832722521,0.666720188396489,0.017913211025747153 +flat_mae,reg,logistic,ppmi_dx,81,0.005994842503189409,test,0.67,0.04323015614128637,0.6296711929076422,0.048899567721008,0.6269100169779287,0.04609683109718206 +flat_mae,reg,logistic,ppmi_dx,82,0.046415888336127774,train,0.798932384341637,0.0156786810106611,0.7756629681047609,0.018388690128002,0.7653874973239134,0.01799808937040264 +flat_mae,reg,logistic,ppmi_dx,82,0.046415888336127774,test,0.62,0.04261408217948616,0.5634191176470589,0.051618822406668985,0.566213921901528,0.04632459372801382 +flat_mae,reg,logistic,ppmi_dx,83,0.046415888336127774,train,0.8131672597864769,0.01543531857987923,0.793106349857478,0.017705547340530252,0.7830362877328195,0.01749223233831085 +flat_mae,reg,logistic,ppmi_dx,83,0.046415888336127774,test,0.51,0.053465035303457906,0.5015766453056658,0.05347990074340936,0.5080645161290323,0.05537253561493708 +flat_mae,reg,logistic,ppmi_dx,84,0.046415888336127774,train,0.802491103202847,0.01573481014987964,0.7807426673461857,0.018215335509493776,0.7708868550631557,0.017916330628816396 +flat_mae,reg,logistic,ppmi_dx,84,0.046415888336127774,test,0.56,0.04739398696037293,0.5280995280995281,0.05021899730274558,0.5280135823429541,0.049713155101350125 +flat_mae,reg,logistic,ppmi_dx,85,0.005994842503189409,train,0.7330960854092526,0.015446684295463274,0.6878332740846071,0.019733179565817674,0.6814788053949904,0.01771222229862081 +flat_mae,reg,logistic,ppmi_dx,85,0.005994842503189409,test,0.68,0.039767705490762216,0.6190476190476191,0.050350217739151056,0.6196943972835314,0.0441969631147414 +flat_mae,reg,logistic,ppmi_dx,86,0.046415888336127774,train,0.8078291814946619,0.015788432197463755,0.7894605394605394,0.018018317550480435,0.7813102119460501,0.018099279596490714 +flat_mae,reg,logistic,ppmi_dx,86,0.046415888336127774,test,0.62,0.04393181535060895,0.5703301673450927,0.0512721019607354,0.5713073005093379,0.04743998521334064 +flat_mae,reg,logistic,ppmi_dx,87,0.005994842503189409,train,0.7313167259786477,0.015617100275026751,0.6862482669377946,0.020148020117068597,0.680033718689788,0.018178661669388283 +flat_mae,reg,logistic,ppmi_dx,87,0.005994842503189409,test,0.63,0.04647623048397966,0.5847828526540231,0.053271752065400725,0.5844651952461799,0.04977821013133427 +flat_mae,reg,logistic,ppmi_dx,88,0.046415888336127774,train,0.8113879003558719,0.015031911783085336,0.7903575450450451,0.017433892260513964,0.7798517448083921,0.017230145365947785 +flat_mae,reg,logistic,ppmi_dx,88,0.046415888336127774,test,0.62,0.04598279678314489,0.5703301673450927,0.05296304875111113,0.5713073005093379,0.049200478702518195 +flat_mae,reg,logistic,ppmi_dx,89,0.005994842503189409,train,0.7224199288256228,0.015075816382934632,0.6677328886530736,0.020187880044150504,0.6641110040676514,0.017431633345038635 +flat_mae,reg,logistic,ppmi_dx,89,0.005994842503189409,test,0.68,0.03918813595975189,0.6114618746964546,0.05320006289469476,0.6146010186757216,0.044669689413933435 +flat_mae,reg,logistic,ppmi_dx,90,0.005994842503189409,train,0.708185053380783,0.016371088861148297,0.656499701848539,0.02079561307912531,0.6534200385356455,0.018438659807439542 +flat_mae,reg,logistic,ppmi_dx,90,0.005994842503189409,test,0.65,0.04296984524058703,0.6011396011396011,0.049795370628921413,0.6005942275042444,0.04590470931039738 +flat_mae,reg,logistic,ppmi_dx,91,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,ppmi_dx,91,21.54434690031882,test,0.62,0.04569958861959263,0.5824175824175825,0.050259417339058275,0.5814940577249575,0.048338197814444046 +flat_mae,reg,logistic,ppmi_dx,92,0.046415888336127774,train,0.7900355871886121,0.015698523393365936,0.764826872065478,0.018599824427351468,0.754683151359452,0.018150009508560733 +flat_mae,reg,logistic,ppmi_dx,92,0.046415888336127774,test,0.72,0.041034989947604475,0.6880570409982174,0.047099911838848624,0.6825127334465195,0.045162158965055925 +flat_mae,reg,logistic,ppmi_dx,93,0.046415888336127774,train,0.791814946619217,0.015603535116338118,0.767721834232363,0.01809615756101316,0.7578676942838793,0.01760505058634972 +flat_mae,reg,logistic,ppmi_dx,93,0.046415888336127774,test,0.59,0.04724649828294156,0.5626666666666666,0.05019118407739106,0.5623938879456706,0.04988749177446763 +flat_mae,reg,logistic,ppmi_dx,94,0.3593813663804626,train,0.905693950177936,0.011577393076397201,0.8987679915713631,0.012665564831845805,0.8929699207878399,0.013492651862644171 +flat_mae,reg,logistic,ppmi_dx,94,0.3593813663804626,test,0.7,0.04555385384355532,0.6782496782496783,0.04884758127665062,0.6765704584040747,0.048386926249960154 +flat_mae,reg,logistic,ppmi_dx,95,0.3593813663804626,train,0.9234875444839857,0.011250672287901293,0.9183479015958076,0.012129745268378473,0.914378612716763,0.01277244483618104 +flat_mae,reg,logistic,ppmi_dx,95,0.3593813663804626,test,0.61,0.048005149723753596,0.584,0.05103636950164025,0.583616298811545,0.0506298625944047 +flat_mae,reg,logistic,ppmi_dx,96,0.005994842503189409,train,0.7241992882562278,0.016567867434567143,0.6769144607761323,0.021515453780202594,0.6716441875401413,0.01925729851847994 +flat_mae,reg,logistic,ppmi_dx,96,0.005994842503189409,test,0.67,0.038220413393892004,0.6108031607500884,0.04823625687146553,0.6116298811544991,0.04235671670721057 +flat_mae,reg,logistic,ppmi_dx,97,0.046415888336127774,train,0.7846975088967971,0.01648963940932138,0.7603901297731173,0.018957475540845845,0.7512176193534575,0.018413876720509346 +flat_mae,reg,logistic,ppmi_dx,97,0.046415888336127774,test,0.71,0.04410577739933852,0.6938021328265231,0.04621516032476202,0.6948217317487266,0.04647323191892248 +flat_mae,reg,logistic,ppmi_dx,98,0.3593813663804626,train,0.9217081850533808,0.0114148141705569,0.9158739878886848,0.012495105047308039,0.9094546135731107,0.013364361581352997 +flat_mae,reg,logistic,ppmi_dx,98,0.3593813663804626,test,0.63,0.04727493627705911,0.5906626839252129,0.05350631964763428,0.5895585738539898,0.05116631507706112 +flat_mae,reg,logistic,ppmi_dx,99,0.005994842503189409,train,0.7295373665480427,0.015880372115065086,0.6784558170347954,0.020960750219691668,0.6733702633269107,0.018430364980747762 +flat_mae,reg,logistic,ppmi_dx,99,0.005994842503189409,test,0.62,0.03999251930048919,0.5386109762020399,0.051965521783725585,0.5509337860780985,0.043435993592401044 +flat_mae,reg,logistic,ppmi_dx,100,0.005994842503189409,train,0.7117437722419929,0.01636080928917486,0.6628599360113757,0.0208529759246454,0.6589193962748876,0.018669013980465565 +flat_mae,reg,logistic,ppmi_dx,100,0.005994842503189409,test,0.66,0.038185861257800637,0.587178241864983,0.05080952875750765,0.5933786078098472,0.0427005994448756 diff --git a/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/log.txt b/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5a69cb6ce99494b919fcfee1eb7eb6b3c605f565 --- /dev/null +++ b/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic/log.txt @@ -0,0 +1,247 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:24:35 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg16; eval v2 (ppmi_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic +model: flat_mae +representation: reg +dataset: ppmi_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg16/eval_v2/ppmi_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: ppmi_dx (flat) +train (n=463): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 463 +}), + labels=['PD' 'Prodromal'], + counts=[178 285] +) + +validation (n=99): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 99 +}), + labels=['PD' 'Prodromal'], + counts=[39 60] +) + +test (n=100): +HFDataset( + dataset=Dataset({ + features: ['sub', 'ses', 'dir', 'sex', 'age', 'age_bin', 'dx', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 100 +}), + labels=['PD' 'Prodromal'], + counts=[37 63] +) + +extracting features for all splits +extract (train) [ 0/232] eta: 0:17:39 time: 4.5675 data: 3.6046 max mem: 2708 +extract (train) [ 20/232] eta: 0:01:24 time: 0.1889 data: 0.0604 max mem: 2863 +extract (train) [ 40/232] eta: 0:00:55 time: 0.1754 data: 0.0548 max mem: 2863 +extract (train) [ 60/232] eta: 0:00:43 time: 0.1718 data: 0.0540 max mem: 2863 +extract (train) [ 80/232] eta: 0:00:34 time: 0.1591 data: 0.0486 max mem: 2863 +extract (train) [100/232] eta: 0:00:28 time: 0.1852 data: 0.0624 max mem: 2863 +extract (train) [120/232] eta: 0:00:23 time: 0.1725 data: 0.0562 max mem: 2863 +extract (train) [140/232] eta: 0:00:18 time: 0.1703 data: 0.0559 max mem: 2863 +extract (train) [160/232] eta: 0:00:14 time: 0.1860 data: 0.0640 max mem: 2863 +extract (train) [180/232] eta: 0:00:10 time: 0.1593 data: 0.0496 max mem: 2863 +extract (train) [200/232] eta: 0:00:06 time: 0.1613 data: 0.0505 max mem: 2863 +extract (train) [220/232] eta: 0:00:02 time: 0.1560 data: 0.0480 max mem: 2863 +extract (train) [231/232] eta: 0:00:00 time: 0.1552 data: 0.0505 max mem: 2863 +extract (train) Total time: 0:00:44 (0.1921 s / it) +extract (validation) [ 0/50] eta: 0:03:11 time: 3.8244 data: 3.6696 max mem: 2863 +extract (validation) [20/50] eta: 0:00:11 time: 0.2267 data: 0.0840 max mem: 2863 +extract (validation) [40/50] eta: 0:00:02 time: 0.1610 data: 0.0516 max mem: 2863 +extract (validation) [49/50] eta: 0:00:00 time: 0.1618 data: 0.0540 max mem: 2863 +extract (validation) Total time: 0:00:13 (0.2675 s / it) +extract (test) [ 0/50] eta: 0:03:21 time: 4.0361 data: 3.8167 max mem: 2863 +extract (test) [20/50] eta: 0:00:12 time: 0.2261 data: 0.0831 max mem: 2863 +extract (test) [40/50] eta: 0:00:02 time: 0.1498 data: 0.0453 max mem: 2863 +extract (test) [49/50] eta: 0:00:00 time: 0.1472 data: 0.0442 max mem: 2863 +extract (test) Total time: 0:00:13 (0.2648 s / it) +feature extraction time: 0:01:11 +train features: (463, 768) +validation features: (99, 768) +test features: (100, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | | 0.35938 | train | 0.91993 | 0.011545 | 0.91439 | 0.012501 | 0.90914 | 0.013182 | +| flat_mae | reg | logistic | ppmi_dx | | 0.35938 | test | 0.58 | 0.043542 | 0.53209 | 0.048359 | 0.53282 | 0.046202 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 1, "C": 21.54434690031882, "split": "test", "acc": 0.63, "acc_std": 0.0499095341593167, "f1": 0.6009060511271707, "f1_std": 0.054024798870955744, "bacc": 0.5997453310696095, "bacc_std": 0.05324684926424627} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04210168167662664, "f1": 0.6212121212121212, "f1_std": 0.04814600750829279, "bacc": 0.6188455008488964, "bacc_std": 0.04568957278232296} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04763845505471394, "f1": 0.6129302228266555, "f1_std": 0.04884520040868717, "bacc": 0.615025466893039, "bacc_std": 0.049130755425708356} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04426314042180017, "f1": 0.5906626839252129, "f1_std": 0.04923334630554499, "bacc": 0.5895585738539898, "bacc_std": 0.047033716077161856} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 5, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.04348128792940706, "f1": 0.5792426367461431, "f1_std": 0.05171450501923204, "bacc": 0.5823429541595926, "bacc_std": 0.04621802508265062} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.0453374194236946, "f1": 0.5634191176470589, "f1_std": 0.0540525709838087, "bacc": 0.566213921901528, "bacc_std": 0.049034241408607626} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.05081856353735315, "f1": 0.52, "f1_std": 0.053405901882583866, "bacc": 0.5199490662139219, "bacc_std": 0.05326431035415618} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 8, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.04391499060685315, "f1": 0.4429590017825312, "f1_std": 0.04570295050277101, "bacc": 0.4490662139219015, "bacc_std": 0.0438706597530806} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.78, "acc_std": 0.03523359760228865, "f1": 0.7428705002337541, "f1_std": 0.045358602981809236, "bacc": 0.730899830220713, "bacc_std": 0.042108335195176455} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.03914246287601228, "f1": 0.6033177064551027, "f1_std": 0.050755661227283505, "bacc": 0.6065365025466893, "bacc_std": 0.04327769545210837} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.047996249853504175, "f1": 0.5413333333333333, "f1_std": 0.05048827666393301, "bacc": 0.5411714770797962, "bacc_std": 0.05002647680022573} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.56, "acc_std": 0.03847876817155143, "f1": 0.45436507936507936, "f1_std": 0.04527729999237772, "bacc": 0.48217317487266553, "bacc_std": 0.03868030804179343} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.039885155133207145, "f1": 0.6011396011396011, "f1_std": 0.04804363549864813, "bacc": 0.6005942275042444, "bacc_std": 0.04397945666662895} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04439467986144286, "f1": 0.5783475783475784, "f1_std": 0.05141474779768542, "bacc": 0.5793718166383701, "bacc_std": 0.0474373160900983} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 15, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.04706803586299305, "f1": 0.568536342515765, "f1_std": 0.051516055534118636, "bacc": 0.5683361629881154, "bacc_std": 0.04934460898772196} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.55, "acc_std": 0.048707929539244424, "f1": 0.5146154675870995, "f1_std": 0.050689247473681615, "bacc": 0.514855687606112, "bacc_std": 0.049825374363380595} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.57, "acc_std": 0.04434322496165564, "f1": 0.5174503422735944, "f1_std": 0.04843969882898947, "bacc": 0.5207979626485568, "bacc_std": 0.045613584303229204} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.04240715034047914, "f1": 0.5558672276764843, "f1_std": 0.05131996911709308, "bacc": 0.5611205432937181, "bacc_std": 0.045468044677054474} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04521965944144206, "f1": 0.5710848415106182, "f1_std": 0.04675125417406717, "bacc": 0.5725806451612903, "bacc_std": 0.04736585454706807} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04106646320295918, "f1": 0.5713127099988413, "f1_std": 0.04917540729999301, "bacc": 0.5742784380305602, "bacc_std": 0.04414824549432513} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 21, "C": 0.005994842503189409, "split": "test", "acc": 0.71, "acc_std": 0.037623497976663464, "f1": 0.6514004087029691, "f1_std": 0.0508607518159989, "bacc": 0.648981324278438, "bacc_std": 0.04345985814659336} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.64, "acc_std": 0.03614636911226355, "f1": 0.54337899543379, "f1_std": 0.05056223376470784, "bacc": 0.5619694397283531, "bacc_std": 0.03976464843296028} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 23, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.046655760630387316, "f1": 0.6263736263736264, "f1_std": 0.052702826489222455, "bacc": 0.6239388794567062, "bacc_std": 0.050929229309464745} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.04264961899009181, "f1": 0.5017958521608157, "f1_std": 0.049587174663170634, "bacc": 0.5106112054329371, "bacc_std": 0.044631107826413045} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.0396278487934937, "f1": 0.5476190476190476, "f1_std": 0.04981329270370754, "bacc": 0.5560271646859083, "bacc_std": 0.04282157648878089} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.04607841577137825, "f1": 0.6043956043956044, "f1_std": 0.050138194376756616, "bacc": 0.6027164685908319, "bacc_std": 0.048257252429533326} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03941084114809021, "f1": 0.5476190476190476, "f1_std": 0.04990915551316597, "bacc": 0.5560271646859083, "bacc_std": 0.04299317738417799} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03852489584671189, "f1": 0.6114618746964546, "f1_std": 0.05201087211814649, "bacc": 0.6146010186757216, "bacc_std": 0.043857000934164676} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.56, "acc_std": 0.046043440357992356, "f1": 0.5024875621890548, "f1_std": 0.050775333996672244, "bacc": 0.5076400679117148, "bacc_std": 0.047358969640841644} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.03643064094961822, "f1": 0.5687468290208015, "f1_std": 0.053569408143431065, "bacc": 0.5831918505942275, "bacc_std": 0.04165502730115667} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.05127496075083822, "f1": 0.5920075321686369, "f1_std": 0.05209542374417806, "bacc": 0.5938030560271647, "bacc_std": 0.0523710449837072} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 32, "C": 166.81005372000556, "split": "test", "acc": 0.6, "acc_std": 0.05312399081394394, "f1": 0.5833333333333333, "f1_std": 0.053977144259582284, "bacc": 0.5857385398981324, "bacc_std": 0.0545336239343147} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 33, "C": 2.782559402207126, "split": "test", "acc": 0.63, "acc_std": 0.049589982859444506, "f1": 0.6214833759590792, "f1_std": 0.05029220533003846, "bacc": 0.6303056027164686, "bacc_std": 0.05171418696238178} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04650056343744664, "f1": 0.6072270227808326, "f1_std": 0.05370823895507381, "bacc": 0.6056876061120543, "bacc_std": 0.050432288295400765} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 35, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.046046081266487814, "f1": 0.5906626839252129, "f1_std": 0.05138675883852866, "bacc": 0.5895585738539898, "bacc_std": 0.0491727806558091} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 36, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03688221251497799, "f1": 0.6114618746964546, "f1_std": 0.04946295362840079, "bacc": 0.6146010186757216, "bacc_std": 0.04162095411365629} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 37, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04796446601391492, "f1": 0.6093337556752191, "f1_std": 0.050244278041146354, "bacc": 0.6099320882852293, "bacc_std": 0.050617103929864606} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.045690979416072926, "f1": 0.5793334052421529, "f1_std": 0.04965550730732412, "bacc": 0.5785229202037352, "bacc_std": 0.04858393154968167} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.7, "acc_std": 0.03865773402567718, "f1": 0.6428571428571428, "f1_std": 0.05041086680147096, "bacc": 0.6409168081494058, "bacc_std": 0.04378706538615221} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 40, "C": 1291.5496650148827, "split": "test", "acc": 0.6, "acc_std": 0.04756002943649215, "f1": 0.5796553173602353, "f1_std": 0.04925722117584302, "bacc": 0.5806451612903225, "bacc_std": 0.04968476100493029} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 41, "C": 2.782559402207126, "split": "test", "acc": 0.57, "acc_std": 0.04791868111707583, "f1": 0.5538956323270048, "f1_std": 0.04917490693650139, "bacc": 0.5564516129032258, "bacc_std": 0.050170819928362545} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 42, "C": 0.3593813663804626, "split": "test", "acc": 0.64, "acc_std": 0.045742758989811706, "f1": 0.5989304812834224, "f1_std": 0.05187369591013659, "bacc": 0.597623089983022, "bacc_std": 0.049264856770046335} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.041211571190625566, "f1": 0.6259934548854604, "f1_std": 0.05177287287423394, "bacc": 0.6247877758913413, "bacc_std": 0.046035247875031375} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04073816883464449, "f1": 0.6176572818908586, "f1_std": 0.0496837635072147, "bacc": 0.616723259762309, "bacc_std": 0.044971009872502334} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.74, "acc_std": 0.03669705165268732, "f1": 0.6843127731908694, "f1_std": 0.050989509718079286, "bacc": 0.6782682512733447, "bacc_std": 0.04387098742029657} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.0442713225463166, "f1": 0.5623386825272135, "f1_std": 0.050510839882907756, "bacc": 0.5632427843803056, "bacc_std": 0.047212381589857626} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 47, "C": 2.782559402207126, "split": "test", "acc": 0.59, "acc_std": 0.04866250712817825, "f1": 0.5710848415106182, "f1_std": 0.05014159919338645, "bacc": 0.5725806451612903, "bacc_std": 0.051157973303087766} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04638868827634599, "f1": 0.6053333333333333, "f1_std": 0.04935873887456703, "bacc": 0.6048387096774194, "bacc_std": 0.048959503632948306} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.044743285529786486, "f1": 0.5863970588235294, "f1_std": 0.05353469354780367, "bacc": 0.5874363327674024, "bacc_std": 0.04854915897929678} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.039075700889427425, "f1": 0.5951417004048583, "f1_std": 0.052739327808502864, "bacc": 0.6014431239388794, "bacc_std": 0.04393279030214322} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04669497189205706, "f1": 0.5384615384615385, "f1_std": 0.05086803867027863, "bacc": 0.5390492359932089, "bacc_std": 0.04897482452983264} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.58, "acc_std": 0.04668728306509171, "f1": 0.5320855614973261, "f1_std": 0.051199483258458, "bacc": 0.533955857385399, "bacc_std": 0.04847390378553142} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.04703708749486941, "f1": 0.6178622120318812, "f1_std": 0.051049288554219543, "bacc": 0.615874363327674, "bacc_std": 0.049527339883342306} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.57, "acc_std": 0.047982742731111146, "f1": 0.5305164319248826, "f1_std": 0.05052836018375847, "bacc": 0.5309847198641766, "bacc_std": 0.04913540068809277} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.042499294111784956, "f1": 0.6155585707824514, "f1_std": 0.04943120535513247, "bacc": 0.6137521222410866, "bacc_std": 0.04571566592788445} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.047181670169675005, "f1": 0.5793334052421529, "f1_std": 0.050412926793411944, "bacc": 0.5785229202037352, "bacc_std": 0.04946618494288171} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.72, "acc_std": 0.043011328740228436, "f1": 0.6783088235294117, "f1_std": 0.052227059790612367, "bacc": 0.6723259762308998, "bacc_std": 0.048476900966668235} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 58, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.041969031439860506, "f1": 0.6108031607500884, "f1_std": 0.05240800584549883, "bacc": 0.6116298811544991, "bacc_std": 0.046379951187567006} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.69, "acc_std": 0.03789443758653767, "f1": 0.6196785670469881, "f1_std": 0.05245995483730231, "bacc": 0.6226655348047538, "bacc_std": 0.04347693740996444} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.62, "acc_std": 0.04644109817823003, "f1": 0.6072757337742869, "f1_std": 0.047936782162365396, "bacc": 0.6120543293718166, "bacc_std": 0.04935185637806466} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04257922028407754, "f1": 0.5783475783475784, "f1_std": 0.04873715782009806, "bacc": 0.5793718166383701, "bacc_std": 0.0449064610724365} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.036802059724966495, "f1": 0.5287698412698413, "f1_std": 0.048861619657422584, "bacc": 0.5458404074702886, "bacc_std": 0.03955898805316649} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.59, "acc_std": 0.04104555517958065, "f1": 0.5071523019593701, "f1_std": 0.05178173417539456, "bacc": 0.5216468590831919, "bacc_std": 0.04400866843053116} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.54, "acc_std": 0.04430806247174435, "f1": 0.47987336047037543, "f1_std": 0.04779675411931733, "bacc": 0.4864176570458404, "bacc_std": 0.044802691676399664} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 65, "C": 1291.5496650148827, "split": "test", "acc": 0.52, "acc_std": 0.0480700280840359, "f1": 0.5104039167686658, "f1_std": 0.04800241410382182, "bacc": 0.5161290322580645, "bacc_std": 0.049512145440414955} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 66, "C": 0.005994842503189409, "split": "test", "acc": 0.6, "acc_std": 0.04469172630364596, "f1": 0.5404411764705883, "f1_std": 0.05143716496628181, "bacc": 0.5449915110356536, "bacc_std": 0.046821136427767245} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.63, "acc_std": 0.04625408090104051, "f1": 0.6009060511271707, "f1_std": 0.049856758039558004, "bacc": 0.5997453310696095, "bacc_std": 0.04911023474556803} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.69, "acc_std": 0.046626155749750584, "f1": 0.6656239887822242, "f1_std": 0.05020280687507287, "bacc": 0.6634125636672326, "bacc_std": 0.04952580908554402} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.66, "acc_std": 0.04509248717912996, "f1": 0.6310763888888888, "f1_std": 0.04896250993443045, "bacc": 0.6290322580645161, "bacc_std": 0.04817594200140022} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.61, "acc_std": 0.046041455233300346, "f1": 0.5623386825272135, "f1_std": 0.05173753041858209, "bacc": 0.5632427843803056, "bacc_std": 0.0484844846279608} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 71, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.041400212559840804, "f1": 0.5872154735228211, "f1_std": 0.050707433483875276, "bacc": 0.5904074702886248, "bacc_std": 0.04471203379112382} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.044998151073127435, "f1": 0.6296711929076422, "f1_std": 0.05150344821002075, "bacc": 0.6269100169779287, "bacc_std": 0.04851048304931694} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 73, "C": 10000.0, "split": "test", "acc": 0.57, "acc_std": 0.05190367617038315, "f1": 0.5538956323270048, "f1_std": 0.05245027154668126, "bacc": 0.5564516129032258, "bacc_std": 0.05338190724600396} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.61, "acc_std": 0.04368294403997972, "f1": 0.5481404240528328, "f1_std": 0.05109579914536465, "bacc": 0.5530560271646858, "bacc_std": 0.046102485084373555} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.58, "acc_std": 0.04867052907047549, "f1": 0.5543293718166383, "f1_std": 0.05083008140614569, "bacc": 0.5543293718166383, "bacc_std": 0.050887470304247374} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 76, "C": 1291.5496650148827, "split": "test", "acc": 0.56, "acc_std": 0.05004587895121834, "f1": 0.537620849096259, "f1_std": 0.05211677438708133, "bacc": 0.5382003395585738, "bacc_std": 0.052493046193019255} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.65, "acc_std": 0.044421634368852304, "f1": 0.6178622120318812, "f1_std": 0.048562329345000044, "bacc": 0.615874363327674, "bacc_std": 0.047126602233577904} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.57, "acc_std": 0.049833322185060064, "f1": 0.5413333333333333, "f1_std": 0.05331476039137783, "bacc": 0.5411714770797962, "bacc_std": 0.05298410108665623} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.64, "acc_std": 0.044695820833720014, "f1": 0.5863970588235294, "f1_std": 0.05248300962755759, "bacc": 0.5874363327674024, "bacc_std": 0.047851373985115304} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.67, "acc_std": 0.044784300820711706, "f1": 0.6396986570586308, "f1_std": 0.049418959626811094, "bacc": 0.6370967741935484, "bacc_std": 0.04801940686605571} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 81, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.04323015614128637, "f1": 0.6296711929076422, "f1_std": 0.048899567721008, "bacc": 0.6269100169779287, "bacc_std": 0.04609683109718206} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04261408217948616, "f1": 0.5634191176470589, "f1_std": 0.051618822406668985, "bacc": 0.566213921901528, "bacc_std": 0.04632459372801382} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.51, "acc_std": 0.053465035303457906, "f1": 0.5015766453056658, "f1_std": 0.05347990074340936, "bacc": 0.5080645161290323, "bacc_std": 0.05537253561493708} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.56, "acc_std": 0.04739398696037293, "f1": 0.5280995280995281, "f1_std": 0.05021899730274558, "bacc": 0.5280135823429541, "bacc_std": 0.049713155101350125} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 85, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.039767705490762216, "f1": 0.6190476190476191, "f1_std": 0.050350217739151056, "bacc": 0.6196943972835314, "bacc_std": 0.0441969631147414} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04393181535060895, "f1": 0.5703301673450927, "f1_std": 0.0512721019607354, "bacc": 0.5713073005093379, "bacc_std": 0.04743998521334064} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.63, "acc_std": 0.04647623048397966, "f1": 0.5847828526540231, "f1_std": 0.053271752065400725, "bacc": 0.5844651952461799, "bacc_std": 0.04977821013133427} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.62, "acc_std": 0.04598279678314489, "f1": 0.5703301673450927, "f1_std": 0.05296304875111113, "bacc": 0.5713073005093379, "bacc_std": 0.049200478702518195} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 89, "C": 0.005994842503189409, "split": "test", "acc": 0.68, "acc_std": 0.03918813595975189, "f1": 0.6114618746964546, "f1_std": 0.05320006289469476, "bacc": 0.6146010186757216, "bacc_std": 0.044669689413933435} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.65, "acc_std": 0.04296984524058703, "f1": 0.6011396011396011, "f1_std": 0.049795370628921413, "bacc": 0.6005942275042444, "bacc_std": 0.04590470931039738} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 91, "C": 21.54434690031882, "split": "test", "acc": 0.62, "acc_std": 0.04569958861959263, "f1": 0.5824175824175825, "f1_std": 0.050259417339058275, "bacc": 0.5814940577249575, "bacc_std": 0.048338197814444046} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.72, "acc_std": 0.041034989947604475, "f1": 0.6880570409982174, "f1_std": 0.047099911838848624, "bacc": 0.6825127334465195, "bacc_std": 0.045162158965055925} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.59, "acc_std": 0.04724649828294156, "f1": 0.5626666666666666, "f1_std": 0.05019118407739106, "bacc": 0.5623938879456706, "bacc_std": 0.04988749177446763} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 94, "C": 0.3593813663804626, "split": "test", "acc": 0.7, "acc_std": 0.04555385384355532, "f1": 0.6782496782496783, "f1_std": 0.04884758127665062, "bacc": 0.6765704584040747, "bacc_std": 0.048386926249960154} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.61, "acc_std": 0.048005149723753596, "f1": 0.584, "f1_std": 0.05103636950164025, "bacc": 0.583616298811545, "bacc_std": 0.0506298625944047} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.67, "acc_std": 0.038220413393892004, "f1": 0.6108031607500884, "f1_std": 0.04823625687146553, "bacc": 0.6116298811544991, "bacc_std": 0.04235671670721057} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.71, "acc_std": 0.04410577739933852, "f1": 0.6938021328265231, "f1_std": 0.04621516032476202, "bacc": 0.6948217317487266, "bacc_std": 0.04647323191892248} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 98, "C": 0.3593813663804626, "split": "test", "acc": 0.63, "acc_std": 0.04727493627705911, "f1": 0.5906626839252129, "f1_std": 0.05350631964763428, "bacc": 0.5895585738539898, "bacc_std": 0.05116631507706112} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 99, "C": 0.005994842503189409, "split": "test", "acc": 0.62, "acc_std": 0.03999251930048919, "f1": 0.5386109762020399, "f1_std": 0.051965521783725585, "bacc": 0.5509337860780985, "bacc_std": 0.043435993592401044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "ppmi_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.66, "acc_std": 0.038185861257800637, "f1": 0.587178241864983, "f1_std": 0.05080952875750765, "bacc": 0.5933786078098472, "bacc_std": 0.0427005994448756} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|----:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | ppmi_dx | train | 100 | 141 | 1020.2 | 0.80722 | 0.089598 | 0.77915 | 0.10688 | 0.77259 | 0.10762 | +| flat_mae | reg | logistic | ppmi_dx | test | 100 | 141 | 1020.2 | 0.6281 | 0.049639 | 0.58303 | 0.050381 | 0.58492 | 0.047195 | + + +done! total time: 0:05:42 diff --git a/decoders/crossreg_reg16/pretrain/config.yaml b/decoders/crossreg_reg16/pretrain/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0212da7357fe4951e2b57dc7d99a1babb77920ea --- /dev/null +++ b/decoders/crossreg_reg16/pretrain/config.yaml @@ -0,0 +1,99 @@ +name: decoders/crossreg_reg16/pretrain +notes: decoder ablations crossreg_reg16 (model_kwargs.decoding=crossreg model_kwargs.reg_tokens=16) +output_dir: experiments/decoders/output/decoders/crossreg_reg16/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: crossreg + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + class_token: false + reg_tokens: 16 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 diff --git a/decoders/crossreg_reg16/pretrain/log.json b/decoders/crossreg_reg16/pretrain/log.json new file mode 100644 index 0000000000000000000000000000000000000000..fbeed71cd301e68105b5667ae46c1f4c105d3828 --- /dev/null +++ b/decoders/crossreg_reg16/pretrain/log.json @@ -0,0 +1,100 @@ +{"epoch": 0, "train/lr": 1.2502400076802458e-05, "train/grad": 0.04736446576416493, "train/loss": 0.9936215397548676, "eval/hcp-train-subset/loss": 0.9916379788229542, "eval/hcp-val/loss": 0.9901699798722421} +{"epoch": 1, "train/lr": 3.750320010240327e-05, "train/grad": 0.09057954107284547, "train/loss": 0.988085025320053, "eval/hcp-train-subset/loss": 0.988719759448882, "eval/hcp-val/loss": 0.9872314324302058} +{"epoch": 2, "train/lr": 6.250400012800409e-05, "train/grad": 0.2309953954940856, "train/loss": 0.9793872850036621, "eval/hcp-train-subset/loss": 0.9792282485192821, "eval/hcp-val/loss": 0.9768391588041859} +{"epoch": 3, "train/lr": 8.75048001536049e-05, "train/grad": 0.26918891608257073, "train/loss": 0.9617084410381317, "eval/hcp-train-subset/loss": 0.9513785887149072, "eval/hcp-val/loss": 0.9485994221702698} +{"epoch": 4, "train/lr": 0.00011250559953918529, "train/grad": 0.21567218102366878, "train/loss": 0.9320091476821899, "eval/hcp-train-subset/loss": 0.9241067046119321, "eval/hcp-val/loss": 0.9186396560361308} +{"epoch": 5, "train/lr": 0.00012498860637884563, "train/grad": 0.12212712674374274, "train/loss": 0.9109017757892609, "eval/hcp-train-subset/loss": 0.9110347119069868, "eval/hcp-val/loss": 0.9048220380660026} +{"epoch": 6, "train/lr": 0.0001249202705377922, "train/grad": 0.10031445108309962, "train/loss": 0.900637757101059, "eval/hcp-train-subset/loss": 0.9020071923732758, "eval/hcp-val/loss": 0.8970477955956613} +{"epoch": 7, "train/lr": 0.0001247836790473516, "train/grad": 0.09320321503435686, "train/loss": 0.8945792699050903, "eval/hcp-train-subset/loss": 0.8991558820970597, "eval/hcp-val/loss": 0.8941048883622692} +{"epoch": 8, "train/lr": 0.000124578981268311, "train/grad": 0.08707837700636287, "train/loss": 0.8896657013225555, "eval/hcp-train-subset/loss": 0.8955229597706948, "eval/hcp-val/loss": 0.8918121120622081} +{"epoch": 9, "train/lr": 0.00012430640103468907, "train/grad": 0.08613166844093083, "train/loss": 0.8850337583637238, "eval/hcp-train-subset/loss": 0.8945684413756093, "eval/hcp-val/loss": 0.8898004658760563} +{"epoch": 10, "train/lr": 0.00012396623640896796, "train/grad": 0.08314616355994923, "train/loss": 0.8822357574558258, "eval/hcp-train-subset/loss": 0.8922734962355706, "eval/hcp-val/loss": 0.8880951125775615} +{"epoch": 11, "train/lr": 0.0001235588593561712, "train/grad": 0.0816068814551069, "train/loss": 0.8796595867061615, "eval/hcp-train-subset/loss": 0.8901112262279757, "eval/hcp-val/loss": 0.8868422988922365} +{"epoch": 12, "train/lr": 0.00012308471533712604, "train/grad": 0.08321449312163635, "train/loss": 0.875657040977478, "eval/hcp-train-subset/loss": 0.8928705732668599, "eval/hcp-val/loss": 0.8879774501246791} +{"epoch": 13, "train/lr": 0.00012254432282135565, "train/grad": 0.08153530295041513, "train/loss": 0.8734730882167816, "eval/hcp-train-subset/loss": 0.8890964398461003, "eval/hcp-val/loss": 0.8853185128781104} +{"epoch": 14, "train/lr": 0.00012193827272014171, "train/grad": 0.0803091107853197, "train/loss": 0.8734144730377197, "eval/hcp-train-subset/loss": 0.8890817146147451, "eval/hcp-val/loss": 0.8847570371243262} +{"epoch": 15, "train/lr": 0.00012126722774037197, "train/grad": 0.08238919606402204, "train/loss": 0.8713975847148895, "eval/hcp-train-subset/loss": 0.8870261349985676, "eval/hcp-val/loss": 0.884686000885502} +{"epoch": 16, "train/lr": 0.00012053192165988122, "train/grad": 0.08089718536298517, "train/loss": 0.8721666114711761, "eval/hcp-train-subset/loss": 0.886949441125316, "eval/hcp-val/loss": 0.8839396420986422} +{"epoch": 17, "train/lr": 0.00011973315852507104, "train/grad": 0.08424036569174183, "train/loss": 0.8659425991630554, "eval/hcp-train-subset/loss": 0.8871988086931167, "eval/hcp-val/loss": 0.8841812533717002} +{"epoch": 18, "train/lr": 0.00011887181177170142, "train/grad": 0.08181449510449311, "train/loss": 0.8682864148426056, "eval/hcp-train-subset/loss": 0.8854114749739247, "eval/hcp-val/loss": 0.8833682719738253} +{"epoch": 19, "train/lr": 0.00011794882326980209, "train/grad": 0.08110096325224955, "train/loss": 0.8672996426582337, "eval/hcp-train-subset/loss": 0.886165040154611, "eval/hcp-val/loss": 0.8842989215927739} +{"epoch": 20, "train/lr": 0.00011696520229374954, "train/grad": 0.08402570782505958, "train/loss": 0.8643286367797851, "eval/hcp-train-subset/loss": 0.8839212281088675, "eval/hcp-val/loss": 0.8815840694212145} +{"epoch": 21, "train/lr": 0.00011592202441863837, "train/grad": 0.08527849321880493, "train/loss": 0.8621381789398194, "eval/hcp-train-subset/loss": 0.8843407909716329, "eval/hcp-val/loss": 0.8837256287374804} +{"epoch": 22, "train/lr": 0.00011482043034415979, "train/grad": 0.08422368928272475, "train/loss": 0.8640264272212982, "eval/hcp-train-subset/loss": 0.8834040145720204, "eval/hcp-val/loss": 0.8820864827402176} +{"epoch": 23, "train/lr": 0.00011366162464726024, "train/grad": 0.08564269863716467, "train/loss": 0.8606427566814423, "eval/hcp-train-subset/loss": 0.8841432727152302, "eval/hcp-val/loss": 0.8819441256984588} +{"epoch": 24, "train/lr": 0.0001124468744649569, "train/grad": 0.08504888760191372, "train/loss": 0.8596072100353241, "eval/hcp-train-subset/loss": 0.8835405024789995, "eval/hcp-val/loss": 0.88094364635406} +{"epoch": 25, "train/lr": 0.0001111775081087387, "train/grad": 0.08813177857419212, "train/loss": 0.8573632600212098, "eval/hcp-train-subset/loss": 0.882519135552068, "eval/hcp-val/loss": 0.8803254115966058} +{"epoch": 26, "train/lr": 0.0001098549136120796, "train/grad": 0.08718607715651794, "train/loss": 0.8562628261661529, "eval/hcp-train-subset/loss": 0.8799601081878908, "eval/hcp-val/loss": 0.8808196984952495} +{"epoch": 27, "train/lr": 0.00010848053721264312, "train/grad": 0.08643717818619329, "train/loss": 0.8578086182785034, "eval/hcp-train-subset/loss": 0.8826324593636298, "eval/hcp-val/loss": 0.8805495192927699} +{"epoch": 28, "train/lr": 0.00010705588177084458, "train/grad": 0.08510091699833926, "train/loss": 0.8576847392559052, "eval/hcp-train-subset/loss": 0.8833607041066692, "eval/hcp-val/loss": 0.8800982006134526} +{"epoch": 29, "train/lr": 0.00010558250512649171, "train/grad": 0.08529845295151615, "train/loss": 0.8581333083915711, "eval/hcp-train-subset/loss": 0.884329951578571, "eval/hcp-val/loss": 0.8808265289952678} +{"epoch": 30, "train/lr": 0.00010406201839531515, "train/grad": 0.0846227374202653, "train/loss": 0.8565675529956818, "eval/hcp-train-subset/loss": 0.8820169395016085, "eval/hcp-val/loss": 0.8793923460668133} +{"epoch": 31, "train/lr": 0.00010249608420723018, "train/grad": 0.08473549606985306, "train/loss": 0.857230650472641, "eval/hcp-train-subset/loss": 0.8825452635365147, "eval/hcp-val/loss": 0.8796864642250922} +{"epoch": 32, "train/lr": 0.00010088641488828097, "train/grad": 0.08950570935416828, "train/loss": 0.8520912811756134, "eval/hcp-train-subset/loss": 0.8781871266903416, "eval/hcp-val/loss": 0.8778176913338323} +{"epoch": 33, "train/lr": 9.923477058823526e-05, "train/grad": 0.08772887508641265, "train/loss": 0.8535924441528321, "eval/hcp-train-subset/loss": 0.8785596268792306, "eval/hcp-val/loss": 0.8783595350480848} +{"epoch": 34, "train/lr": 9.754295735588547e-05, "train/grad": 0.08800788677671881, "train/loss": 0.8531582337760926, "eval/hcp-train-subset/loss": 0.8800527818741337, "eval/hcp-val/loss": 0.8777211866071147} +{"epoch": 35, "train/lr": 9.581282516416285e-05, "train/grad": 0.0900317771944386, "train/loss": 0.8503104526424408, "eval/hcp-train-subset/loss": 0.8798580669587658, "eval/hcp-val/loss": 0.8780833530810571} +{"epoch": 36, "train/lr": 9.404626588721676e-05, "train/grad": 0.09099075537313267, "train/loss": 0.849441345691681, "eval/hcp-train-subset/loss": 0.8804164028936817, "eval/hcp-val/loss": 0.8789996841261464} +{"epoch": 37, "train/lr": 9.224521123168153e-05, "train/grad": 0.09057375769248215, "train/loss": 0.8490013228702545, "eval/hcp-train-subset/loss": 0.8789547316489681, "eval/hcp-val/loss": 0.8775714299371166} +{"epoch": 38, "train/lr": 9.041163062437843e-05, "train/grad": 0.09020280182867212, "train/loss": 0.8507658285808564, "eval/hcp-train-subset/loss": 0.8777541883530156, "eval/hcp-val/loss": 0.8769541113607345} +{"epoch": 39, "train/lr": 8.85475290587822e-05, "train/grad": 0.09160917352605327, "train/loss": 0.851321068572998, "eval/hcp-train-subset/loss": 0.8756641947454021, "eval/hcp-val/loss": 0.8768252874574354} +{"epoch": 40, "train/lr": 8.665494490258622e-05, "train/grad": 0.09275840139110432, "train/loss": 0.8475015573120117, "eval/hcp-train-subset/loss": 0.8779891056399192, "eval/hcp-val/loss": 0.8767981500394882} +{"epoch": 41, "train/lr": 8.473594766877838e-05, "train/grad": 0.0923427064198328, "train/loss": 0.8477112183380127, "eval/hcp-train-subset/loss": 0.8773381210142567, "eval/hcp-val/loss": 0.8771977290030448} +{"epoch": 42, "train/lr": 8.279263575265999e-05, "train/grad": 0.0932717057805497, "train/loss": 0.8471168390655518, "eval/hcp-train-subset/loss": 0.8766935429265422, "eval/hcp-val/loss": 0.8761664927005768} +{"epoch": 43, "train/lr": 8.082713413727944e-05, "train/grad": 0.09481171124984651, "train/loss": 0.845700146408081, "eval/hcp-train-subset/loss": 0.8769633779602666, "eval/hcp-val/loss": 0.8765889319681353} +{"epoch": 44, "train/lr": 7.884159206979602e-05, "train/grad": 0.0950301459003073, "train/loss": 0.8460325436019898, "eval/hcp-train-subset/loss": 0.8750111701027039, "eval/hcp-val/loss": 0.8759181278367196} +{"epoch": 45, "train/lr": 7.683818071130916e-05, "train/grad": 0.09504133193168154, "train/loss": 0.845634200181961, "eval/hcp-train-subset/loss": 0.8753365345539585, "eval/hcp-val/loss": 0.8760314631846643} +{"epoch": 46, "train/lr": 7.481909076272522e-05, "train/grad": 0.09764468188591245, "train/loss": 0.8441264307403564, "eval/hcp-train-subset/loss": 0.8741533967756456, "eval/hcp-val/loss": 0.8753765408069857} +{"epoch": 47, "train/lr": 7.278653006925963e-05, "train/grad": 0.09645632137706209, "train/loss": 0.8452223344993591, "eval/hcp-train-subset/loss": 0.8742292359952004, "eval/hcp-val/loss": 0.8759265138256934} +{"epoch": 48, "train/lr": 7.074272120618864e-05, "train/grad": 0.09761701633786442, "train/loss": 0.8430116205692292, "eval/hcp-train-subset/loss": 0.8734727761437816, "eval/hcp-val/loss": 0.8754483307561567} +{"epoch": 49, "train/lr": 6.868989904849677e-05, "train/grad": 0.10100780523271227, "train/loss": 0.8408755163669586, "eval/hcp-train-subset/loss": 0.8702639572082027, "eval/hcp-val/loss": 0.8748659683812049} +{"epoch": 50, "train/lr": 6.6630308327075e-05, "train/grad": 0.09938236343207732, "train/loss": 0.8424100349521637, "eval/hcp-train-subset/loss": 0.8725094045362165, "eval/hcp-val/loss": 0.8743369262064656} +{"epoch": 51, "train/lr": 6.456620117413798e-05, "train/grad": 0.09813919322809136, "train/loss": 0.8436547775363922, "eval/hcp-train-subset/loss": 0.8721129528937801, "eval/hcp-val/loss": 0.8749471277959885} +{"epoch": 52, "train/lr": 6.249983466055255e-05, "train/grad": 0.10182146442991763, "train/loss": 0.8399578283405303, "eval/hcp-train-subset/loss": 0.8695157276045892, "eval/hcp-val/loss": 0.8747757855922945} +{"epoch": 53, "train/lr": 6.0433468327763305e-05, "train/grad": 0.10227690382876103, "train/loss": 0.8416636351013184, "eval/hcp-train-subset/loss": 0.8685790319596568, "eval/hcp-val/loss": 0.8745847930831294} +{"epoch": 54, "train/lr": 5.83693617170174e-05, "train/grad": 0.10327455636159195, "train/loss": 0.8425834802436829, "eval/hcp-train-subset/loss": 0.870477573525521, "eval/hcp-val/loss": 0.8739131256457298} +{"epoch": 55, "train/lr": 5.6309771898588165e-05, "train/grad": 0.10464570939388226, "train/loss": 0.8416355387020111, "eval/hcp-train-subset/loss": 0.8689847482788947, "eval/hcp-val/loss": 0.8734286869725874} +{"epoch": 56, "train/lr": 5.4256951003704155e-05, "train/grad": 0.10619453265976722, "train/loss": 0.8400013266277313, "eval/hcp-train-subset/loss": 0.8682983536874095, "eval/hcp-val/loss": 0.8741802563590388} +{"epoch": 57, "train/lr": 5.221314376187425e-05, "train/grad": 0.10874584723364147, "train/loss": 0.8371524644756317, "eval/hcp-train-subset/loss": 0.8705120317397579, "eval/hcp-val/loss": 0.8736811789774126} +{"epoch": 58, "train/lr": 5.018058504631059e-05, "train/grad": 0.1099502067414831, "train/loss": 0.8368151514148712, "eval/hcp-train-subset/loss": 0.867378948196288, "eval/hcp-val/loss": 0.8732048301927505} +{"epoch": 59, "train/lr": 4.816149743012713e-05, "train/grad": 0.11184621024748621, "train/loss": 0.8359989368152618, "eval/hcp-train-subset/loss": 0.8661077301348409, "eval/hcp-val/loss": 0.872367698338724} +{"epoch": 60, "train/lr": 4.615808875598772e-05, "train/grad": 0.11442054984506778, "train/loss": 0.8344877775669098, "eval/hcp-train-subset/loss": 0.8648674613045108, "eval/hcp-val/loss": 0.8727621022732027} +{"epoch": 61, "train/lr": 4.417254972186445e-05, "train/grad": 0.11299693717641539, "train/loss": 0.8371485692214966, "eval/hcp-train-subset/loss": 0.8643926035973334, "eval/hcp-val/loss": 0.8727863084885382} +{"epoch": 62, "train/lr": 4.220705148553925e-05, "train/grad": 0.11174341159897752, "train/loss": 0.8404773879432679, "eval/hcp-train-subset/loss": 0.8629904024062618, "eval/hcp-val/loss": 0.872586541598843} +{"epoch": 63, "train/lr": 4.026374329047657e-05, "train/grad": 0.11444256472181537, "train/loss": 0.8378817178630829, "eval/hcp-train-subset/loss": 0.8633227973215042, "eval/hcp-val/loss": 0.8719311116203186} +{"epoch": 64, "train/lr": 3.834475011565652e-05, "train/grad": 0.11807613187128589, "train/loss": 0.8340781542301178, "eval/hcp-train-subset/loss": 0.8626246490786152, "eval/hcp-val/loss": 0.8726356433283898} +{"epoch": 65, "train/lr": 3.6452170351940815e-05, "train/grad": 0.11597643802646028, "train/loss": 0.8382829402732849, "eval/hcp-train-subset/loss": 0.8621692234469999, "eval/hcp-val/loss": 0.8720188448506017} +{"epoch": 66, "train/lr": 3.458807350751516e-05, "train/grad": 0.1215903597336894, "train/loss": 0.8338609189510345, "eval/hcp-train-subset/loss": 0.8615750132068511, "eval/hcp-val/loss": 0.8707416922815384} +{"epoch": 67, "train/lr": 3.2754497944910164e-05, "train/grad": 0.12002089603776625, "train/loss": 0.8343381651115418, "eval/hcp-train-subset/loss": 0.8611697025837437, "eval/hcp-val/loss": 0.871633046096371} +{"epoch": 68, "train/lr": 3.0953448652083367e-05, "train/grad": 0.12328751533460251, "train/loss": 0.8341627596282959, "eval/hcp-train-subset/loss": 0.8580277100686104, "eval/hcp-val/loss": 0.8715467606821368} +{"epoch": 69, "train/lr": 2.9186895049993948e-05, "train/grad": 0.1267831209932529, "train/loss": 0.8308715549659729, "eval/hcp-train-subset/loss": 0.8595802351351707, "eval/hcp-val/loss": 0.8707171322837952} +{"epoch": 70, "train/lr": 2.7456768839068717e-05, "train/grad": 0.12561684400940468, "train/loss": 0.8346162019634247, "eval/hcp-train-subset/loss": 0.8568506221617421, "eval/hcp-val/loss": 0.8700909172334979} +{"epoch": 71, "train/lr": 2.5764961886919063e-05, "train/grad": 0.12910909316336758, "train/loss": 0.8330819794082641, "eval/hcp-train-subset/loss": 0.8564589744614016, "eval/hcp-val/loss": 0.8703627894001622} +{"epoch": 72, "train/lr": 2.411332415960724e-05, "train/grad": 0.12895582340107892, "train/loss": 0.8334026066589355, "eval/hcp-train-subset/loss": 0.8566390420159986, "eval/hcp-val/loss": 0.8701825439929962} +{"epoch": 73, "train/lr": 2.2503661698739544e-05, "train/grad": 0.1322013007085794, "train/loss": 0.8323655721664429, "eval/hcp-train-subset/loss": 0.856461921045857, "eval/hcp-val/loss": 0.8692863968110853} +{"epoch": 74, "train/lr": 2.0937734646583902e-05, "train/grad": 0.1299159682395173, "train/loss": 0.8337948703670501, "eval/hcp-train-subset/loss": 0.8564263812957271, "eval/hcp-val/loss": 0.8703142885238894} +{"epoch": 75, "train/lr": 1.9417255321381202e-05, "train/grad": 0.13536899243213854, "train/loss": 0.831548527879715, "eval/hcp-train-subset/loss": 0.8557913755216906, "eval/hcp-val/loss": 0.8693539913623564} +{"epoch": 76, "train/lr": 1.7943886344950134e-05, "train/grad": 0.13544278533192125, "train/loss": 0.8318717273139954, "eval/hcp-train-subset/loss": 0.8543289198029426, "eval/hcp-val/loss": 0.8689188111212945} +{"epoch": 77, "train/lr": 1.651923882463461e-05, "train/grad": 0.1363703325107052, "train/loss": 0.8351548118495942, "eval/hcp-train-subset/loss": 0.8532256157167496, "eval/hcp-val/loss": 0.8695693189097989} +{"epoch": 78, "train/lr": 1.5144870591581508e-05, "train/grad": 0.13911622191989673, "train/loss": 0.8339882147979736, "eval/hcp-train-subset/loss": 0.8511532074020755, "eval/hcp-val/loss": 0.869096883843022} +{"epoch": 79, "train/lr": 1.3822284497275662e-05, "train/grad": 0.13940446005642415, "train/loss": 0.8331114482784271, "eval/hcp-train-subset/loss": 0.8517234229272411, "eval/hcp-val/loss": 0.8685152895988957} +{"epoch": 80, "train/lr": 1.2552926770192975e-05, "train/grad": 0.1430589948117905, "train/loss": 0.8321611892604828, "eval/hcp-train-subset/loss": 0.8493987158421548, "eval/hcp-val/loss": 0.8680259710358035} +{"epoch": 81, "train/lr": 1.1338185434371453e-05, "train/grad": 0.1448515784508154, "train/loss": 0.8313203579998016, "eval/hcp-train-subset/loss": 0.8486213972491603, "eval/hcp-val/loss": 0.8682239738202864} +{"epoch": 82, "train/lr": 1.0179388791627326e-05, "train/grad": 0.1460884036193643, "train/loss": 0.8316526358890534, "eval/hcp-train-subset/loss": 0.8473311989538131, "eval/hcp-val/loss": 0.8679943805740725} +{"epoch": 83, "train/lr": 9.07780396907607e-06, "train/grad": 0.14611725271864295, "train/loss": 0.8345687065219879, "eval/hcp-train-subset/loss": 0.8480655666320555, "eval/hcp-val/loss": 0.8680218910017321} +{"epoch": 84, "train/lr": 8.034635533547902e-06, "train/grad": 0.1487755847477119, "train/loss": 0.8325265183258057, "eval/hcp-train-subset/loss": 0.8466931360383187, "eval/hcp-val/loss": 0.8684300664932497} +{"epoch": 85, "train/lr": 7.051024174411275e-06, "train/grad": 0.14882530510062997, "train/loss": 0.8343977784919738, "eval/hcp-train-subset/loss": 0.8467695530383818, "eval/hcp-val/loss": 0.8675346403352676} +{"epoch": 86, "train/lr": 6.1280454562463606e-06, "train/grad": 0.15191440156657396, "train/loss": 0.8324859927082062, "eval/hcp-train-subset/loss": 0.8457069983405452, "eval/hcp-val/loss": 0.8670323327664406} +{"epoch": 87, "train/lr": 5.266708642730326e-06, "train/grad": 0.15157942061888463, "train/loss": 0.8362964143180848, "eval/hcp-train-subset/loss": 0.8455773207449144, "eval/hcp-val/loss": 0.8676192250943953} +{"epoch": 88, "train/lr": 4.467955593022733e-06, "train/grad": 0.1534531902457455, "train/loss": 0.8347679039287567, "eval/hcp-train-subset/loss": 0.8444502526713956, "eval/hcp-val/loss": 0.8673250040700359} +{"epoch": 89, "train/lr": 3.732659731856291e-06, "train/grad": 0.15966627294514876, "train/loss": 0.8316212647628785, "eval/hcp-train-subset/loss": 0.8434534938104691, "eval/hcp-val/loss": 0.8668633478303109} +{"epoch": 90, "train/lr": 3.0616250944596583e-06, "train/grad": 0.1544706854377796, "train/loss": 0.8368482497787476, "eval/hcp-train-subset/loss": 0.8430805090935, "eval/hcp-val/loss": 0.8668070099046153} +{"epoch": 91, "train/lr": 2.4555854473568305e-06, "train/grad": 0.15902408102441973, "train/loss": 0.8353111394023895, "eval/hcp-train-subset/loss": 0.8409850837722901, "eval/hcp-val/loss": 0.8665950903969426} +{"epoch": 92, "train/lr": 1.915203486004091e-06, "train/grad": 0.1570650304956724, "train/loss": 0.8371546503162384, "eval/hcp-train-subset/loss": 0.8405998253053234, "eval/hcp-val/loss": 0.8660612240914376} +{"epoch": 93, "train/lr": 1.4410701101423926e-06, "train/grad": 0.16095881032761486, "train/loss": 0.8369262317752838, "eval/hcp-train-subset/loss": 0.8396559857553051, "eval/hcp-val/loss": 0.8661747478669689} +{"epoch": 94, "train/lr": 1.0337037776570775e-06, "train/grad": 0.16330006045841453, "train/loss": 0.8363215612602234, "eval/hcp-train-subset/loss": 0.8395945602847684, "eval/hcp-val/loss": 0.8659185920992205} +{"epoch": 95, "train/lr": 6.935499376518293e-07, "train/grad": 0.16642421219979678, "train/loss": 0.8364436416721344, "eval/hcp-train-subset/loss": 0.8392915398843827, "eval/hcp-val/loss": 0.8655971173317202} +{"epoch": 96, "train/lr": 4.209805433566085e-07, "train/grad": 0.1632838679353237, "train/loss": 0.8377499903488159, "eval/hcp-train-subset/loss": 0.8389032511941849, "eval/hcp-val/loss": 0.8653298241476859} +{"epoch": 97, "train/lr": 2.1629364540224422e-07, "train/grad": 0.16493930601207318, "train/loss": 0.838709210767746, "eval/hcp-train-subset/loss": 0.8384819376853204, "eval/hcp-val/loss": 0.8656014059820483} +{"epoch": 98, "train/lr": 7.971306590647406e-08, "train/grad": 0.16758060497423352, "train/loss": 0.8379621538352966, "eval/hcp-train-subset/loss": 0.8384971512902167, "eval/hcp-val/loss": 0.8657781462515554} +{"epoch": 99, "train/lr": 1.1388153727718725e-08, "train/grad": 0.17039703311119586, "train/loss": 0.8398120947360992, "eval/hcp-train-subset/loss": 0.8383024700226323, "eval/hcp-val/loss": 0.8654518281259844} diff --git a/decoders/crossreg_reg16/pretrain/log.txt b/decoders/crossreg_reg16/pretrain/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..52d0fe99d4d75c9b2ebc28f6bff1c86739746d4a --- /dev/null +++ b/decoders/crossreg_reg16/pretrain/log.txt @@ -0,0 +1,7774 @@ +pretraining fmri mae +start: 2026-01-16 00:34:31 +cwd: /admin/home/connor/fmri-fm +sha: f9ef1eebbc1a5292e462bf6c7741545659511885, status: has uncommitted changes, branch: dev/clane9 +config: +name: decoders/crossreg_reg16/pretrain +notes: decoder ablations crossreg_reg16 (model_kwargs.decoding=crossreg model_kwargs.reg_tokens=16) +output_dir: experiments/decoders/output/decoders/crossreg_reg16/pretrain +input_space: flat +patch_size: 16 +num_frames: 16 +t_patch_size: 4 +mask_ratio: 0.9 +pred_mask_ratio: null +masking: tube +masking_kwargs: {} +mask_patch_size: null +model: mae_vit_base +model_kwargs: + decoding: crossreg + pos_embed: sep + target_norm: null + t_pred_stride: 2 + no_decode_pos: true + mask_drop_scale: false + pred_edge_pad: 0 + class_token: false + reg_tokens: 16 + no_embed_class: true + head_init_scale: 0.0 + decoder_depth: 4 + drop_path_rate: 0.0 +datasets: + hcp-train: + type: wds + url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar + clipping: random + clipping_kwargs: + oversample: 4.0 + shuffle: true + buffer_size: 2000 + samples_per_epoch: 200000 + hcp-train-subset: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation + split_range: + - 0 + - 2000 + shuffle: false + hcp-val: + type: arrow + root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test + split_range: + - 0 + - 2000 + shuffle: false +train_dataset: hcp-train +eval_datasets: +- hcp-train-subset +- hcp-val +clip_vmax: 3.0 +normalize: frame +tr_scale: null +crop_scale: null +crop_aspect: null +gray_jitter: null +gauss_sigma: null +num_workers: 16 +epochs: 100 +batch_size: 32 +accum_iter: 1 +base_lr: 0.001 +min_lr: 0.0 +warmup_epochs: 5 +weight_decay: 0.05 +betas: +- 0.9 +- 0.95 +clip_grad: 1.0 +amp: true +amp_dtype: float16 +ckpt: null +resume: true +auto_resume: true +start_epoch: 0 +max_checkpoints: 5 +checkpoint_period: 20 +plot_period: 5 +device: cuda +presend_cuda: false +seed: 7338 +debug: false +wandb: true +wandb_entity: null +wandb_project: fMRI-foundation-model +rank: 0 +world_size: 1 +gpu: 0 +distributed: true +dist_backend: nccl +in_chans: 1 +img_size: +- 224 +- 560 + +train transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +val transform: +Transform( +transform=Compose( + ToTensor() + TemporalCenterCrop(num_frames=16) + Normalize(mode='frame') + Clip(vmax=3.0) + FlatUnmask((224, 560)) +), +noise_transform=None +) +mask generator: +TubeMasking( + mask_ratio=0.9 + (patchify): Patchify2D((224, 560), (16, 16), in_chans=1) +) +loading dataset: hcp-train + +type: wds +url: /data/fmri-datasets/pretrain/hcpya-all.${input_space}.wds/hcpya-all-${input_space}-{00000..01799}.tar +clipping: random +clipping_kwargs: + oversample: 4.0 +shuffle: true +buffer_size: 2000 +samples_per_epoch: 200000 + +loading dataset: hcp-train-subset + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/validation +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [899, 472, 767, 116, 1265, 1852, 300, 1335, 361, 1560] +loading dataset: hcp-val + +type: arrow +root: s3://medarc/fmri-datasets/eval/hcpya-clips.${input_space}.arrow/test +split_range: +- 0 +- 2000 +shuffle: false + +split indices: [1075, 1189, 738, 1350, 965, 1964, 1367, 1183, 1619, 1407] +model: +MaskedAutoencoderViT( + decoding=crossreg, t_pred_stride=2, pred_edge_pad=0, no_decode_pos=True + (encoder): MaskedEncoder( + class_token=False, reg_tokens=16, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) + (pred_patchify): StridedPatchify3D((16, 224, 560), (2, 16, 16), in_chans=1, t_stride=2) + (decoder): MaskedDecoder( + cross_decode=True, class_token=False, no_embed_class=True + (pos_embed): SeparablePosEmbed(512, (4, 14, 35)) + (proj): Identity() + (blocks): ModuleList( + (0-3): 4 x Block( + (norm1): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=16 + (q): Linear(in_features=512, out_features=512, bias=True) + (k): Linear(in_features=768, out_features=512, bias=True) + (v): Linear(in_features=768, out_features=512, bias=True) + (proj): Linear(in_features=512, out_features=512, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=512, out_features=2048, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=2048, out_features=512, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((512,), eps=1e-06, elementwise_affine=True) + (head): Linear(in_features=512, out_features=512, bias=True) + ) +) +num params: 100.4M +total batch size: 32 = 32 bs per gpu x 1 accum x 1 gpus +lr: 1.25e-04 = 1.00e-03 x 32 / 256 +full schedule: epochs = 100 (steps = 625000) +warmup: epochs = 5 (steps = 31250) +start training for 100 epochs +Train: [0] [ 0/6250] eta: 14:49:02 lr: 0.000000 grad: 0.0262 (0.0262) loss: 0.9995 (0.9995) time: 8.5347 data: 7.2135 max mem: 7649 +Train: [0] [ 100/6250] eta: 0:29:05 lr: 0.000000 grad: 0.0133 (0.0153) loss: 0.9952 (0.9957) time: 0.2005 data: 0.0999 max mem: 8452 +Train: [0] [ 200/6250] eta: 0:23:58 lr: 0.000001 grad: 0.0130 (0.0146) loss: 0.9964 (0.9959) time: 0.2152 data: 0.1047 max mem: 8452 +Train: [0] [ 300/6250] eta: 0:23:05 lr: 0.000001 grad: 0.0127 (0.0141) loss: 0.9959 (0.9959) time: 0.1836 data: 0.0840 max mem: 8452 +Train: [0] [ 400/6250] eta: 0:21:31 lr: 0.000002 grad: 0.0126 (0.0138) loss: 0.9956 (0.9959) time: 0.1838 data: 0.1026 max mem: 8452 +Train: [0] [ 500/6250] eta: 0:20:36 lr: 0.000002 grad: 0.0124 (0.0136) loss: 0.9955 (0.9959) time: 0.1949 data: 0.1110 max mem: 8452 +Train: [0] [ 600/6250] eta: 0:19:48 lr: 0.000002 grad: 0.0125 (0.0134) loss: 0.9958 (0.9959) time: 0.1920 data: 0.1129 max mem: 8452 +Train: [0] [ 700/6250] eta: 0:19:06 lr: 0.000003 grad: 0.0126 (0.0133) loss: 0.9961 (0.9959) time: 0.1864 data: 0.1084 max mem: 8452 +Train: [0] [ 800/6250] eta: 0:18:26 lr: 0.000003 grad: 0.0127 (0.0133) loss: 0.9959 (0.9959) time: 0.1487 data: 0.0552 max mem: 8452 +Train: [0] [ 900/6250] eta: 0:17:40 lr: 0.000004 grad: 0.0124 (0.0132) loss: 0.9962 (0.9959) time: 0.1423 data: 0.0552 max mem: 8452 +Train: [0] [1000/6250] eta: 0:17:01 lr: 0.000004 grad: 0.0126 (0.0132) loss: 0.9959 (0.9959) time: 0.1578 data: 0.0805 max mem: 8452 +Train: [0] [1100/6250] eta: 0:16:27 lr: 0.000004 grad: 0.0128 (0.0131) loss: 0.9962 (0.9959) time: 0.1795 data: 0.0926 max mem: 8452 +Train: [0] [1200/6250] eta: 0:15:57 lr: 0.000005 grad: 0.0127 (0.0131) loss: 0.9956 (0.9959) time: 0.1753 data: 0.0970 max mem: 8452 +Train: [0] [1300/6250] eta: 0:15:25 lr: 0.000005 grad: 0.0131 (0.0131) loss: 0.9953 (0.9959) time: 0.1444 data: 0.0550 max mem: 8452 +Train: [0] [1400/6250] eta: 0:15:01 lr: 0.000006 grad: 0.0127 (0.0131) loss: 0.9955 (0.9959) time: 0.1783 data: 0.1051 max mem: 8452 +Train: [0] [1500/6250] eta: 0:14:30 lr: 0.000006 grad: 0.0128 (0.0131) loss: 0.9957 (0.9959) time: 0.1450 data: 0.0670 max mem: 8452 +Train: [0] [1600/6250] eta: 0:14:07 lr: 0.000006 grad: 0.0127 (0.0131) loss: 0.9958 (0.9959) time: 0.1893 data: 0.1084 max mem: 8452 +Train: [0] [1700/6250] eta: 0:13:42 lr: 0.000007 grad: 0.0131 (0.0131) loss: 0.9959 (0.9959) time: 0.1517 data: 0.0705 max mem: 8452 +Train: [0] [1800/6250] eta: 0:13:21 lr: 0.000007 grad: 0.0134 (0.0131) loss: 0.9957 (0.9959) time: 0.1777 data: 0.1015 max mem: 8452 +Train: [0] [1900/6250] eta: 0:13:00 lr: 0.000008 grad: 0.0136 (0.0131) loss: 0.9958 (0.9959) time: 0.1679 data: 0.0874 max mem: 8452 +Train: [0] [2000/6250] eta: 0:12:38 lr: 0.000008 grad: 0.0151 (0.0132) loss: 0.9956 (0.9959) time: 0.1697 data: 0.0913 max mem: 8452 +Train: [0] [2100/6250] eta: 0:12:19 lr: 0.000008 grad: 0.0159 (0.0134) loss: 0.9957 (0.9959) time: 0.1716 data: 0.0808 max mem: 8452 +Train: [0] [2200/6250] eta: 0:11:59 lr: 0.000009 grad: 0.0156 (0.0135) loss: 0.9955 (0.9959) time: 0.1551 data: 0.0671 max mem: 8452 +Train: [0] [2300/6250] eta: 0:11:38 lr: 0.000009 grad: 0.0163 (0.0138) loss: 0.9955 (0.9959) time: 0.1529 data: 0.0759 max mem: 8452 +Train: [0] [2400/6250] eta: 0:11:16 lr: 0.000010 grad: 0.0208 (0.0142) loss: 0.9954 (0.9958) time: 0.1499 data: 0.0698 max mem: 8452 +Train: [0] [2500/6250] eta: 0:10:58 lr: 0.000010 grad: 0.0209 (0.0147) loss: 0.9956 (0.9958) time: 0.1683 data: 0.0883 max mem: 8452 +Train: [0] [2600/6250] eta: 0:10:38 lr: 0.000010 grad: 0.0325 (0.0153) loss: 0.9947 (0.9958) time: 0.1590 data: 0.0769 max mem: 8452 +Train: [0] [2700/6250] eta: 0:10:20 lr: 0.000011 grad: 0.0247 (0.0159) loss: 0.9955 (0.9958) time: 0.1768 data: 0.0995 max mem: 8452 +Train: [0] [2800/6250] eta: 0:10:01 lr: 0.000011 grad: 0.0386 (0.0167) loss: 0.9948 (0.9958) time: 0.1554 data: 0.0757 max mem: 8452 +Train: [0] [2900/6250] eta: 0:09:42 lr: 0.000012 grad: 0.0384 (0.0176) loss: 0.9957 (0.9957) time: 0.1668 data: 0.0881 max mem: 8452 +Train: [0] [3000/6250] eta: 0:09:23 lr: 0.000012 grad: 0.0520 (0.0185) loss: 0.9944 (0.9957) time: 0.1805 data: 0.1099 max mem: 8452 +Train: [0] [3100/6250] eta: 0:09:04 lr: 0.000012 grad: 0.0413 (0.0194) loss: 0.9945 (0.9956) time: 0.1686 data: 0.0893 max mem: 8452 +Train: [0] [3200/6250] eta: 0:08:46 lr: 0.000013 grad: 0.0400 (0.0202) loss: 0.9945 (0.9956) time: 0.1578 data: 0.0836 max mem: 8452 +Train: [0] [3300/6250] eta: 0:08:27 lr: 0.000013 grad: 0.0426 (0.0210) loss: 0.9942 (0.9956) time: 0.1545 data: 0.0710 max mem: 8452 +Train: [0] [3400/6250] eta: 0:08:09 lr: 0.000014 grad: 0.0444 (0.0219) loss: 0.9942 (0.9955) time: 0.1747 data: 0.1011 max mem: 8452 +Train: [0] [3500/6250] eta: 0:07:51 lr: 0.000014 grad: 0.0489 (0.0228) loss: 0.9937 (0.9954) time: 0.1656 data: 0.0953 max mem: 8452 +Train: [0] [3600/6250] eta: 0:07:32 lr: 0.000014 grad: 0.0429 (0.0236) loss: 0.9935 (0.9954) time: 0.1588 data: 0.0812 max mem: 8452 +Train: [0] [3700/6250] eta: 0:07:14 lr: 0.000015 grad: 0.0591 (0.0244) loss: 0.9922 (0.9953) time: 0.1604 data: 0.0750 max mem: 8452 +Train: [0] [3800/6250] eta: 0:06:57 lr: 0.000015 grad: 0.0554 (0.0252) loss: 0.9939 (0.9953) time: 0.1906 data: 0.1209 max mem: 8452 +Train: [0] [3900/6250] eta: 0:06:39 lr: 0.000016 grad: 0.0707 (0.0263) loss: 0.9929 (0.9952) time: 0.1604 data: 0.0750 max mem: 8452 +Train: [0] [4000/6250] eta: 0:06:22 lr: 0.000016 grad: 0.0486 (0.0273) loss: 0.9935 (0.9952) time: 0.1677 data: 0.0918 max mem: 8452 +Train: [0] [4100/6250] eta: 0:06:04 lr: 0.000016 grad: 0.0570 (0.0283) loss: 0.9930 (0.9951) time: 0.1663 data: 0.0895 max mem: 8452 +Train: [0] [4200/6250] eta: 0:05:46 lr: 0.000017 grad: 0.0738 (0.0294) loss: 0.9912 (0.9951) time: 0.1608 data: 0.0856 max mem: 8452 +Train: [0] [4300/6250] eta: 0:05:29 lr: 0.000017 grad: 0.0775 (0.0307) loss: 0.9925 (0.9950) time: 0.1576 data: 0.0815 max mem: 8452 +Train: [0] [4400/6250] eta: 0:05:11 lr: 0.000018 grad: 0.0776 (0.0318) loss: 0.9918 (0.9949) time: 0.1445 data: 0.0715 max mem: 8452 +Train: [0] [4500/6250] eta: 0:04:54 lr: 0.000018 grad: 0.0770 (0.0328) loss: 0.9910 (0.9948) time: 0.1596 data: 0.0818 max mem: 8452 +Train: [0] [4600/6250] eta: 0:04:37 lr: 0.000018 grad: 0.0830 (0.0340) loss: 0.9919 (0.9948) time: 0.1615 data: 0.0766 max mem: 8452 +Train: [0] [4700/6250] eta: 0:04:20 lr: 0.000019 grad: 0.0844 (0.0352) loss: 0.9913 (0.9947) time: 0.1765 data: 0.1008 max mem: 8452 +Train: [0] [4800/6250] eta: 0:04:03 lr: 0.000019 grad: 0.0814 (0.0362) loss: 0.9905 (0.9946) time: 0.1533 data: 0.0658 max mem: 8452 +Train: [0] [4900/6250] eta: 0:03:46 lr: 0.000020 grad: 0.0879 (0.0373) loss: 0.9910 (0.9945) time: 0.1627 data: 0.0784 max mem: 8452 +Train: [0] [5000/6250] eta: 0:03:29 lr: 0.000020 grad: 0.0730 (0.0385) loss: 0.9918 (0.9944) time: 0.1309 data: 0.0527 max mem: 8452 +Train: [0] [5100/6250] eta: 0:03:12 lr: 0.000020 grad: 0.0611 (0.0395) loss: 0.9925 (0.9943) time: 0.1675 data: 0.0756 max mem: 8452 +Train: [0] [5200/6250] eta: 0:02:55 lr: 0.000021 grad: 0.0934 (0.0405) loss: 0.9895 (0.9943) time: 0.1577 data: 0.0716 max mem: 8452 +Train: [0] [5300/6250] eta: 0:02:38 lr: 0.000021 grad: 0.0744 (0.0413) loss: 0.9914 (0.9942) time: 0.1472 data: 0.0702 max mem: 8452 +Train: [0] [5400/6250] eta: 0:02:22 lr: 0.000022 grad: 0.0800 (0.0421) loss: 0.9904 (0.9941) time: 0.1567 data: 0.0795 max mem: 8452 +Train: [0] [5500/6250] eta: 0:02:05 lr: 0.000022 grad: 0.0694 (0.0428) loss: 0.9914 (0.9941) time: 0.1496 data: 0.0692 max mem: 8452 +Train: [0] [5600/6250] eta: 0:01:48 lr: 0.000022 grad: 0.0840 (0.0436) loss: 0.9907 (0.9940) time: 0.1822 data: 0.1094 max mem: 8452 +Train: [0] [5700/6250] eta: 0:01:31 lr: 0.000023 grad: 0.0752 (0.0442) loss: 0.9907 (0.9939) time: 0.1533 data: 0.0723 max mem: 8452 +Train: [0] [5800/6250] eta: 0:01:14 lr: 0.000023 grad: 0.0721 (0.0449) loss: 0.9899 (0.9939) time: 0.1432 data: 0.0549 max mem: 8452 +Train: [0] [5900/6250] eta: 0:00:58 lr: 0.000024 grad: 0.0743 (0.0456) loss: 0.9915 (0.9938) time: 0.1779 data: 0.1061 max mem: 8452 +Train: [0] [6000/6250] eta: 0:00:41 lr: 0.000024 grad: 0.0708 (0.0461) loss: 0.9906 (0.9938) time: 0.1480 data: 0.0706 max mem: 8452 +Train: [0] [6100/6250] eta: 0:00:25 lr: 0.000024 grad: 0.0631 (0.0466) loss: 0.9909 (0.9937) time: 0.1620 data: 0.1016 max mem: 8452 +Train: [0] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.0667 (0.0471) loss: 0.9906 (0.9937) time: 0.1876 data: 0.1043 max mem: 8452 +Train: [0] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.0719 (0.0474) loss: 0.9888 (0.9936) time: 0.1476 data: 0.0704 max mem: 8452 +Train: [0] Total time: 0:17:26 (0.1675 s / it) +Averaged stats: lr: 0.000025 grad: 0.0719 (0.0474) loss: 0.9888 (0.9936) +Eval (hcp-train-subset): [0] [ 0/62] eta: 0:02:56 loss: 0.9905 (0.9905) time: 2.8388 data: 2.6410 max mem: 8452 +Eval (hcp-train-subset): [0] [61/62] eta: 0:00:00 loss: 0.9911 (0.9916) time: 0.1356 data: 0.1144 max mem: 8452 +Eval (hcp-train-subset): [0] Total time: 0:00:13 (0.2189 s / it) +Averaged stats (hcp-train-subset): loss: 0.9911 (0.9916) +Eval (hcp-val): [0] [ 0/62] eta: 0:04:48 loss: 0.9887 (0.9887) time: 4.6546 data: 4.6277 max mem: 8452 +Eval (hcp-val): [0] [61/62] eta: 0:00:00 loss: 0.9891 (0.9902) time: 0.1212 data: 0.0984 max mem: 8452 +Eval (hcp-val): [0] Total time: 0:00:13 (0.2190 s / it) +Averaged stats (hcp-val): loss: 0.9891 (0.9902) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [1] [ 0/6250] eta: 7:32:34 lr: 0.000025 grad: 0.0629 (0.0629) loss: 0.9897 (0.9897) time: 4.3448 data: 4.1764 max mem: 8452 +Train: [1] [ 100/6250] eta: 0:21:32 lr: 0.000025 grad: 0.0858 (0.0927) loss: 0.9904 (0.9898) time: 0.1595 data: 0.0734 max mem: 8452 +Train: [1] [ 200/6250] eta: 0:18:36 lr: 0.000026 grad: 0.0798 (0.0897) loss: 0.9906 (0.9899) time: 0.1488 data: 0.0386 max mem: 8452 +Train: [1] [ 300/6250] eta: 0:17:22 lr: 0.000026 grad: 0.0866 (0.0938) loss: 0.9891 (0.9896) time: 0.1605 data: 0.0552 max mem: 8452 +Train: [1] [ 400/6250] eta: 0:16:33 lr: 0.000027 grad: 0.0802 (0.0937) loss: 0.9895 (0.9893) time: 0.1369 data: 0.0369 max mem: 8452 +Train: [1] [ 500/6250] eta: 0:16:28 lr: 0.000027 grad: 0.0766 (0.0939) loss: 0.9901 (0.9891) time: 0.1876 data: 0.1087 max mem: 8452 +Train: [1] [ 600/6250] eta: 0:16:05 lr: 0.000027 grad: 0.0839 (0.0929) loss: 0.9900 (0.9891) time: 0.1538 data: 0.0764 max mem: 8452 +Train: [1] [ 700/6250] eta: 0:15:51 lr: 0.000028 grad: 0.0778 (0.0917) loss: 0.9906 (0.9893) time: 0.1701 data: 0.0990 max mem: 8452 +Train: [1] [ 800/6250] eta: 0:15:43 lr: 0.000028 grad: 0.0805 (0.0906) loss: 0.9892 (0.9892) time: 0.1455 data: 0.0594 max mem: 8452 +Train: [1] [ 900/6250] eta: 0:15:24 lr: 0.000029 grad: 0.0693 (0.0892) loss: 0.9910 (0.9893) time: 0.1751 data: 0.0799 max mem: 8452 +Train: [1] [1000/6250] eta: 0:15:05 lr: 0.000029 grad: 0.0669 (0.0878) loss: 0.9900 (0.9894) time: 0.1825 data: 0.1083 max mem: 8452 +Train: [1] [1100/6250] eta: 0:14:46 lr: 0.000029 grad: 0.0701 (0.0869) loss: 0.9897 (0.9895) time: 0.1494 data: 0.0751 max mem: 8452 +Train: [1] [1200/6250] eta: 0:14:25 lr: 0.000030 grad: 0.0609 (0.0856) loss: 0.9916 (0.9895) time: 0.1647 data: 0.0818 max mem: 8452 +Train: [1] [1300/6250] eta: 0:14:04 lr: 0.000030 grad: 0.0649 (0.0846) loss: 0.9907 (0.9896) time: 0.1740 data: 0.0890 max mem: 8452 +Train: [1] [1400/6250] eta: 0:13:45 lr: 0.000031 grad: 0.0733 (0.0842) loss: 0.9899 (0.9897) time: 0.1777 data: 0.1023 max mem: 8452 +Train: [1] [1500/6250] eta: 0:13:29 lr: 0.000031 grad: 0.0722 (0.0838) loss: 0.9890 (0.9896) time: 0.1711 data: 0.0938 max mem: 8452 +Train: [1] [1600/6250] eta: 0:13:08 lr: 0.000031 grad: 0.0737 (0.0833) loss: 0.9907 (0.9897) time: 0.1737 data: 0.0957 max mem: 8452 +Train: [1] [1700/6250] eta: 0:12:48 lr: 0.000032 grad: 0.0661 (0.0827) loss: 0.9915 (0.9897) time: 0.1776 data: 0.0950 max mem: 8452 +Train: [1] [1800/6250] eta: 0:12:28 lr: 0.000032 grad: 0.0683 (0.0823) loss: 0.9890 (0.9897) time: 0.1587 data: 0.0803 max mem: 8452 +Train: [1] [1900/6250] eta: 0:12:10 lr: 0.000033 grad: 0.0673 (0.0819) loss: 0.9876 (0.9896) time: 0.1504 data: 0.0775 max mem: 8452 +Train: [1] [2000/6250] eta: 0:11:52 lr: 0.000033 grad: 0.0745 (0.0815) loss: 0.9897 (0.9897) time: 0.1617 data: 0.0816 max mem: 8452 +Train: [1] [2100/6250] eta: 0:11:33 lr: 0.000033 grad: 0.0748 (0.0812) loss: 0.9886 (0.9896) time: 0.1570 data: 0.0785 max mem: 8452 +Train: [1] [2200/6250] eta: 0:11:14 lr: 0.000034 grad: 0.0713 (0.0810) loss: 0.9895 (0.9896) time: 0.1616 data: 0.0933 max mem: 8452 +Train: [1] [2300/6250] eta: 0:10:57 lr: 0.000034 grad: 0.0685 (0.0807) loss: 0.9890 (0.9896) time: 0.1581 data: 0.0781 max mem: 8452 +Train: [1] [2400/6250] eta: 0:10:40 lr: 0.000035 grad: 0.0757 (0.0806) loss: 0.9890 (0.9895) time: 0.1612 data: 0.0934 max mem: 8452 +Train: [1] [2500/6250] eta: 0:10:22 lr: 0.000035 grad: 0.0735 (0.0806) loss: 0.9891 (0.9895) time: 0.1709 data: 0.0991 max mem: 8452 +Train: [1] [2600/6250] eta: 0:10:05 lr: 0.000035 grad: 0.0839 (0.0808) loss: 0.9876 (0.9894) time: 0.1484 data: 0.0725 max mem: 8452 +Train: [1] [2700/6250] eta: 0:09:49 lr: 0.000036 grad: 0.0782 (0.0809) loss: 0.9891 (0.9894) time: 0.1950 data: 0.1096 max mem: 8452 +Train: [1] [2800/6250] eta: 0:09:32 lr: 0.000036 grad: 0.0743 (0.0811) loss: 0.9886 (0.9893) time: 0.1577 data: 0.0801 max mem: 8452 +Train: [1] [2900/6250] eta: 0:09:14 lr: 0.000037 grad: 0.0774 (0.0810) loss: 0.9863 (0.9893) time: 0.1504 data: 0.0668 max mem: 8452 +Train: [1] [3000/6250] eta: 0:08:58 lr: 0.000037 grad: 0.0799 (0.0812) loss: 0.9875 (0.9892) time: 0.1451 data: 0.0731 max mem: 8452 +Train: [1] [3100/6250] eta: 0:08:41 lr: 0.000037 grad: 0.0929 (0.0813) loss: 0.9878 (0.9892) time: 0.1497 data: 0.0779 max mem: 8452 +Train: [1] [3200/6250] eta: 0:08:23 lr: 0.000038 grad: 0.0771 (0.0814) loss: 0.9878 (0.9891) time: 0.1487 data: 0.0758 max mem: 8452 +Train: [1] [3300/6250] eta: 0:08:06 lr: 0.000038 grad: 0.0733 (0.0816) loss: 0.9877 (0.9891) time: 0.1624 data: 0.0876 max mem: 8452 +Train: [1] [3400/6250] eta: 0:07:49 lr: 0.000039 grad: 0.0828 (0.0816) loss: 0.9887 (0.9891) time: 0.1519 data: 0.0743 max mem: 8452 +Train: [1] [3500/6250] eta: 0:07:32 lr: 0.000039 grad: 0.0761 (0.0817) loss: 0.9895 (0.9890) time: 0.1587 data: 0.0816 max mem: 8452 +Train: [1] [3600/6250] eta: 0:07:15 lr: 0.000039 grad: 0.0900 (0.0820) loss: 0.9871 (0.9890) time: 0.1642 data: 0.0821 max mem: 8452 +Train: [1] [3700/6250] eta: 0:06:59 lr: 0.000040 grad: 0.0718 (0.0821) loss: 0.9884 (0.9890) time: 0.1555 data: 0.0827 max mem: 8452 +Train: [1] [3800/6250] eta: 0:06:42 lr: 0.000040 grad: 0.0751 (0.0822) loss: 0.9887 (0.9890) time: 0.1923 data: 0.1142 max mem: 8452 +Train: [1] [3900/6250] eta: 0:06:26 lr: 0.000041 grad: 0.0734 (0.0823) loss: 0.9884 (0.9889) time: 0.1915 data: 0.1174 max mem: 8452 +Train: [1] [4000/6250] eta: 0:06:10 lr: 0.000041 grad: 0.0756 (0.0824) loss: 0.9880 (0.9889) time: 0.1886 data: 0.1121 max mem: 8452 +Train: [1] [4100/6250] eta: 0:05:53 lr: 0.000041 grad: 0.0743 (0.0825) loss: 0.9888 (0.9889) time: 0.1552 data: 0.0778 max mem: 8452 +Train: [1] [4200/6250] eta: 0:05:37 lr: 0.000042 grad: 0.0994 (0.0827) loss: 0.9872 (0.9888) time: 0.1713 data: 0.0915 max mem: 8452 +Train: [1] [4300/6250] eta: 0:05:20 lr: 0.000042 grad: 0.0960 (0.0828) loss: 0.9867 (0.9888) time: 0.1502 data: 0.0762 max mem: 8452 +Train: [1] [4400/6250] eta: 0:05:03 lr: 0.000043 grad: 0.0943 (0.0832) loss: 0.9863 (0.9887) time: 0.1492 data: 0.0708 max mem: 8452 +Train: [1] [4500/6250] eta: 0:04:47 lr: 0.000043 grad: 0.0816 (0.0835) loss: 0.9862 (0.9887) time: 0.1599 data: 0.0809 max mem: 8452 +Train: [1] [4600/6250] eta: 0:04:30 lr: 0.000043 grad: 0.0736 (0.0836) loss: 0.9875 (0.9886) time: 0.1785 data: 0.0991 max mem: 8452 +Train: [1] [4700/6250] eta: 0:04:14 lr: 0.000044 grad: 0.0943 (0.0840) loss: 0.9866 (0.9886) time: 0.1837 data: 0.1048 max mem: 8452 +Train: [1] [4800/6250] eta: 0:03:57 lr: 0.000044 grad: 0.0887 (0.0842) loss: 0.9863 (0.9886) time: 0.1760 data: 0.1010 max mem: 8452 +Train: [1] [4900/6250] eta: 0:03:41 lr: 0.000045 grad: 0.0766 (0.0846) loss: 0.9867 (0.9885) time: 0.1325 data: 0.0541 max mem: 8452 +Train: [1] [5000/6250] eta: 0:03:25 lr: 0.000045 grad: 0.1007 (0.0849) loss: 0.9871 (0.9885) time: 0.1823 data: 0.1091 max mem: 8452 +Train: [1] [5100/6250] eta: 0:03:08 lr: 0.000045 grad: 0.0788 (0.0850) loss: 0.9873 (0.9885) time: 0.1633 data: 0.0846 max mem: 8452 +Train: [1] [5200/6250] eta: 0:02:52 lr: 0.000046 grad: 0.0873 (0.0852) loss: 0.9869 (0.9884) time: 0.1413 data: 0.0603 max mem: 8452 +Train: [1] [5300/6250] eta: 0:02:35 lr: 0.000046 grad: 0.0845 (0.0856) loss: 0.9865 (0.9884) time: 0.1812 data: 0.1121 max mem: 8452 +Train: [1] [5400/6250] eta: 0:02:19 lr: 0.000047 grad: 0.0862 (0.0858) loss: 0.9866 (0.9884) time: 0.1796 data: 0.1038 max mem: 8452 +Train: [1] [5500/6250] eta: 0:02:02 lr: 0.000047 grad: 0.0970 (0.0861) loss: 0.9866 (0.9883) time: 0.1557 data: 0.0699 max mem: 8452 +Train: [1] [5600/6250] eta: 0:01:46 lr: 0.000047 grad: 0.0898 (0.0863) loss: 0.9868 (0.9883) time: 0.1490 data: 0.0671 max mem: 8452 +Train: [1] [5700/6250] eta: 0:01:30 lr: 0.000048 grad: 0.0996 (0.0867) loss: 0.9863 (0.9883) time: 0.1735 data: 0.0965 max mem: 8452 +Train: [1] [5800/6250] eta: 0:01:13 lr: 0.000048 grad: 0.1331 (0.0873) loss: 0.9873 (0.9883) time: 0.1559 data: 0.0651 max mem: 8452 +Train: [1] [5900/6250] eta: 0:00:57 lr: 0.000049 grad: 0.1154 (0.0877) loss: 0.9866 (0.9882) time: 0.2013 data: 0.1357 max mem: 8452 +Train: [1] [6000/6250] eta: 0:00:40 lr: 0.000049 grad: 0.1079 (0.0884) loss: 0.9868 (0.9882) time: 0.1844 data: 0.1234 max mem: 8452 +Train: [1] [6100/6250] eta: 0:00:24 lr: 0.000049 grad: 0.1067 (0.0891) loss: 0.9867 (0.9881) time: 0.2931 data: 0.2250 max mem: 8452 +Train: [1] [6200/6250] eta: 0:00:08 lr: 0.000050 grad: 0.1230 (0.0900) loss: 0.9849 (0.9881) time: 0.1503 data: 0.0790 max mem: 8452 +Train: [1] [6249/6250] eta: 0:00:00 lr: 0.000050 grad: 0.1270 (0.0906) loss: 0.9867 (0.9881) time: 0.1544 data: 0.0772 max mem: 8452 +Train: [1] Total time: 0:17:11 (0.1651 s / it) +Averaged stats: lr: 0.000050 grad: 0.1270 (0.0906) loss: 0.9867 (0.9881) +Eval (hcp-train-subset): [1] [ 0/62] eta: 0:03:17 loss: 0.9881 (0.9881) time: 3.1846 data: 3.1016 max mem: 8452 +Eval (hcp-train-subset): [1] [61/62] eta: 0:00:00 loss: 0.9894 (0.9887) time: 0.1269 data: 0.1045 max mem: 8452 +Eval (hcp-train-subset): [1] Total time: 0:00:14 (0.2318 s / it) +Averaged stats (hcp-train-subset): loss: 0.9894 (0.9887) +Eval (hcp-val): [1] [ 0/62] eta: 0:03:56 loss: 0.9828 (0.9828) time: 3.8149 data: 3.7253 max mem: 8452 +Eval (hcp-val): [1] [61/62] eta: 0:00:00 loss: 0.9869 (0.9872) time: 0.1229 data: 0.1004 max mem: 8452 +Eval (hcp-val): [1] Total time: 0:00:13 (0.2168 s / it) +Averaged stats (hcp-val): loss: 0.9869 (0.9872) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [2] [ 0/6250] eta: 10:00:19 lr: 0.000050 grad: 0.3107 (0.3107) loss: 0.9917 (0.9917) time: 5.7631 data: 5.5783 max mem: 8452 +Train: [2] [ 100/6250] eta: 0:22:04 lr: 0.000050 grad: 0.1636 (0.1684) loss: 0.9851 (0.9853) time: 0.1765 data: 0.0890 max mem: 8452 +Train: [2] [ 200/6250] eta: 0:18:57 lr: 0.000051 grad: 0.1045 (0.1908) loss: 0.9867 (0.9848) time: 0.1607 data: 0.0683 max mem: 8452 +Train: [2] [ 300/6250] eta: 0:17:57 lr: 0.000051 grad: 0.1427 (0.1770) loss: 0.9846 (0.9850) time: 0.1781 data: 0.0796 max mem: 8452 +Train: [2] [ 400/6250] eta: 0:16:56 lr: 0.000052 grad: 0.1087 (0.1728) loss: 0.9857 (0.9853) time: 0.1479 data: 0.0412 max mem: 8452 +Train: [2] [ 500/6250] eta: 0:16:18 lr: 0.000052 grad: 0.1403 (0.1729) loss: 0.9853 (0.9852) time: 0.1308 data: 0.0282 max mem: 8452 +Train: [2] [ 600/6250] eta: 0:15:59 lr: 0.000052 grad: 0.1219 (0.1737) loss: 0.9872 (0.9851) time: 0.1754 data: 0.0886 max mem: 8452 +Train: [2] [ 700/6250] eta: 0:15:33 lr: 0.000053 grad: 0.1926 (0.1777) loss: 0.9827 (0.9850) time: 0.1666 data: 0.0819 max mem: 8452 +Train: [2] [ 800/6250] eta: 0:15:11 lr: 0.000053 grad: 0.1795 (0.1848) loss: 0.9857 (0.9848) time: 0.1508 data: 0.0725 max mem: 8452 +Train: [2] [ 900/6250] eta: 0:15:04 lr: 0.000054 grad: 0.1852 (0.1882) loss: 0.9823 (0.9846) time: 0.2124 data: 0.1278 max mem: 8452 +Train: [2] [1000/6250] eta: 0:14:45 lr: 0.000054 grad: 0.2561 (0.1915) loss: 0.9851 (0.9844) time: 0.1637 data: 0.0923 max mem: 8452 +Train: [2] [1100/6250] eta: 0:14:25 lr: 0.000054 grad: 0.1955 (0.1960) loss: 0.9828 (0.9844) time: 0.1373 data: 0.0519 max mem: 8452 +Train: [2] [1200/6250] eta: 0:14:12 lr: 0.000055 grad: 0.1898 (0.2019) loss: 0.9862 (0.9843) time: 0.2094 data: 0.1350 max mem: 8452 +Train: [2] [1300/6250] eta: 0:13:49 lr: 0.000055 grad: 0.2027 (0.2049) loss: 0.9836 (0.9842) time: 0.1597 data: 0.0829 max mem: 8452 +Train: [2] [1400/6250] eta: 0:13:26 lr: 0.000056 grad: 0.2121 (0.2099) loss: 0.9818 (0.9841) time: 0.1616 data: 0.0820 max mem: 8452 +Train: [2] [1500/6250] eta: 0:13:06 lr: 0.000056 grad: 0.1797 (0.2128) loss: 0.9826 (0.9841) time: 0.1646 data: 0.0706 max mem: 8452 +Train: [2] [1600/6250] eta: 0:12:46 lr: 0.000056 grad: 0.1657 (0.2124) loss: 0.9830 (0.9840) time: 0.1471 data: 0.0728 max mem: 8452 +Train: [2] [1700/6250] eta: 0:12:30 lr: 0.000057 grad: 0.1845 (0.2138) loss: 0.9829 (0.9839) time: 0.1619 data: 0.0840 max mem: 8452 +Train: [2] [1800/6250] eta: 0:12:12 lr: 0.000057 grad: 0.2599 (0.2154) loss: 0.9819 (0.9838) time: 0.1706 data: 0.0958 max mem: 8452 +Train: [2] [1900/6250] eta: 0:11:56 lr: 0.000058 grad: 0.2079 (0.2177) loss: 0.9821 (0.9836) time: 0.1633 data: 0.0899 max mem: 8452 +Train: [2] [2000/6250] eta: 0:11:40 lr: 0.000058 grad: 0.2505 (0.2189) loss: 0.9818 (0.9835) time: 0.1396 data: 0.0561 max mem: 8452 +Train: [2] [2100/6250] eta: 0:11:23 lr: 0.000058 grad: 0.1809 (0.2194) loss: 0.9807 (0.9834) time: 0.1925 data: 0.1067 max mem: 8452 +Train: [2] [2200/6250] eta: 0:11:06 lr: 0.000059 grad: 0.1963 (0.2198) loss: 0.9789 (0.9832) time: 0.1920 data: 0.0642 max mem: 8452 +Train: [2] [2300/6250] eta: 0:10:48 lr: 0.000059 grad: 0.1746 (0.2200) loss: 0.9806 (0.9832) time: 0.1552 data: 0.0684 max mem: 8452 +Train: [2] [2400/6250] eta: 0:10:30 lr: 0.000060 grad: 0.2463 (0.2207) loss: 0.9829 (0.9831) time: 0.1422 data: 0.0632 max mem: 8452 +Train: [2] [2500/6250] eta: 0:10:12 lr: 0.000060 grad: 0.1700 (0.2218) loss: 0.9786 (0.9830) time: 0.1368 data: 0.0452 max mem: 8452 +Train: [2] [2600/6250] eta: 0:09:55 lr: 0.000060 grad: 0.1848 (0.2225) loss: 0.9808 (0.9829) time: 0.1673 data: 0.0870 max mem: 8452 +Train: [2] [2700/6250] eta: 0:09:38 lr: 0.000061 grad: 0.3544 (0.2246) loss: 0.9817 (0.9828) time: 0.1527 data: 0.0730 max mem: 8452 +Train: [2] [2800/6250] eta: 0:09:21 lr: 0.000061 grad: 0.1591 (0.2261) loss: 0.9809 (0.9827) time: 0.1351 data: 0.0485 max mem: 8452 +Train: [2] [2900/6250] eta: 0:09:04 lr: 0.000062 grad: 0.2871 (0.2278) loss: 0.9791 (0.9826) time: 0.1577 data: 0.0867 max mem: 8452 +Train: [2] [3000/6250] eta: 0:08:47 lr: 0.000062 grad: 0.2077 (0.2283) loss: 0.9786 (0.9824) time: 0.1283 data: 0.0581 max mem: 8452 +Train: [2] [3100/6250] eta: 0:08:30 lr: 0.000062 grad: 0.1717 (0.2288) loss: 0.9758 (0.9823) time: 0.1476 data: 0.0665 max mem: 8452 +Train: [2] [3200/6250] eta: 0:08:13 lr: 0.000063 grad: 0.1963 (0.2296) loss: 0.9774 (0.9822) time: 0.1589 data: 0.0907 max mem: 8452 +Train: [2] [3300/6250] eta: 0:07:57 lr: 0.000063 grad: 0.1882 (0.2311) loss: 0.9781 (0.9821) time: 0.1519 data: 0.0673 max mem: 8452 +Train: [2] [3400/6250] eta: 0:07:40 lr: 0.000064 grad: 0.2065 (0.2309) loss: 0.9785 (0.9820) time: 0.1197 data: 0.0347 max mem: 8452 +Train: [2] [3500/6250] eta: 0:07:25 lr: 0.000064 grad: 0.2887 (0.2317) loss: 0.9823 (0.9819) time: 0.1943 data: 0.1034 max mem: 8452 +Train: [2] [3600/6250] eta: 0:07:08 lr: 0.000064 grad: 0.2133 (0.2314) loss: 0.9776 (0.9818) time: 0.1601 data: 0.0828 max mem: 8452 +Train: [2] [3700/6250] eta: 0:06:51 lr: 0.000065 grad: 0.1777 (0.2319) loss: 0.9780 (0.9816) time: 0.1702 data: 0.0977 max mem: 8452 +Train: [2] [3800/6250] eta: 0:06:35 lr: 0.000065 grad: 0.2112 (0.2320) loss: 0.9793 (0.9815) time: 0.1601 data: 0.0753 max mem: 8452 +Train: [2] [3900/6250] eta: 0:06:19 lr: 0.000066 grad: 0.2569 (0.2325) loss: 0.9786 (0.9815) time: 0.1533 data: 0.0740 max mem: 8452 +Train: [2] [4000/6250] eta: 0:06:03 lr: 0.000066 grad: 0.1879 (0.2334) loss: 0.9771 (0.9813) time: 0.1717 data: 0.0836 max mem: 8452 +Train: [2] [4100/6250] eta: 0:05:47 lr: 0.000066 grad: 0.1986 (0.2339) loss: 0.9801 (0.9813) time: 0.1694 data: 0.0859 max mem: 8452 +Train: [2] [4200/6250] eta: 0:05:31 lr: 0.000067 grad: 0.2299 (0.2339) loss: 0.9754 (0.9812) time: 0.1952 data: 0.1093 max mem: 8452 +Train: [2] [4300/6250] eta: 0:05:15 lr: 0.000067 grad: 0.1785 (0.2335) loss: 0.9770 (0.9811) time: 0.1910 data: 0.1138 max mem: 8452 +Train: [2] [4400/6250] eta: 0:04:59 lr: 0.000068 grad: 0.1926 (0.2331) loss: 0.9755 (0.9810) time: 0.1495 data: 0.0697 max mem: 8452 +Train: [2] [4500/6250] eta: 0:04:42 lr: 0.000068 grad: 0.2490 (0.2338) loss: 0.9775 (0.9809) time: 0.1542 data: 0.0789 max mem: 8452 +Train: [2] [4600/6250] eta: 0:04:26 lr: 0.000068 grad: 0.2186 (0.2335) loss: 0.9786 (0.9808) time: 0.1184 data: 0.0335 max mem: 8452 +Train: [2] [4700/6250] eta: 0:04:10 lr: 0.000069 grad: 0.1830 (0.2331) loss: 0.9763 (0.9807) time: 0.1666 data: 0.0858 max mem: 8452 +Train: [2] [4800/6250] eta: 0:03:54 lr: 0.000069 grad: 0.2121 (0.2332) loss: 0.9769 (0.9806) time: 0.1441 data: 0.0609 max mem: 8452 +Train: [2] [4900/6250] eta: 0:03:38 lr: 0.000070 grad: 0.1685 (0.2331) loss: 0.9752 (0.9806) time: 0.1864 data: 0.1184 max mem: 8452 +Train: [2] [5000/6250] eta: 0:03:21 lr: 0.000070 grad: 0.1948 (0.2325) loss: 0.9781 (0.9805) time: 0.1678 data: 0.0908 max mem: 8452 +Train: [2] [5100/6250] eta: 0:03:05 lr: 0.000070 grad: 0.1963 (0.2323) loss: 0.9762 (0.9804) time: 0.1577 data: 0.0865 max mem: 8452 +Train: [2] [5200/6250] eta: 0:02:49 lr: 0.000071 grad: 0.2117 (0.2316) loss: 0.9760 (0.9803) time: 0.1399 data: 0.0623 max mem: 8452 +Train: [2] [5300/6250] eta: 0:02:32 lr: 0.000071 grad: 0.2557 (0.2320) loss: 0.9773 (0.9802) time: 0.1748 data: 0.0959 max mem: 8452 +Train: [2] [5400/6250] eta: 0:02:16 lr: 0.000072 grad: 0.2316 (0.2322) loss: 0.9744 (0.9801) time: 0.1203 data: 0.0492 max mem: 8452 +Train: [2] [5500/6250] eta: 0:02:01 lr: 0.000072 grad: 0.2306 (0.2327) loss: 0.9766 (0.9801) time: 0.2197 data: 0.1310 max mem: 8452 +Train: [2] [5600/6250] eta: 0:01:45 lr: 0.000072 grad: 0.2205 (0.2327) loss: 0.9767 (0.9800) time: 0.1461 data: 0.0655 max mem: 8452 +Train: [2] [5700/6250] eta: 0:01:29 lr: 0.000073 grad: 0.1347 (0.2322) loss: 0.9754 (0.9799) time: 0.2086 data: 0.1438 max mem: 8452 +Train: [2] [5800/6250] eta: 0:01:13 lr: 0.000073 grad: 0.1751 (0.2321) loss: 0.9747 (0.9798) time: 0.1290 data: 0.0466 max mem: 8452 +Train: [2] [5900/6250] eta: 0:00:56 lr: 0.000074 grad: 0.1812 (0.2317) loss: 0.9741 (0.9797) time: 0.1771 data: 0.1018 max mem: 8452 +Train: [2] [6000/6250] eta: 0:00:40 lr: 0.000074 grad: 0.2148 (0.2313) loss: 0.9716 (0.9796) time: 0.1763 data: 0.0954 max mem: 8452 +Train: [2] [6100/6250] eta: 0:00:24 lr: 0.000074 grad: 0.2044 (0.2312) loss: 0.9753 (0.9795) time: 0.2094 data: 0.1374 max mem: 8452 +Train: [2] [6200/6250] eta: 0:00:08 lr: 0.000075 grad: 0.1915 (0.2312) loss: 0.9726 (0.9794) time: 0.1476 data: 0.0729 max mem: 8452 +Train: [2] [6249/6250] eta: 0:00:00 lr: 0.000075 grad: 0.1955 (0.2310) loss: 0.9745 (0.9794) time: 0.1876 data: 0.1088 max mem: 8452 +Train: [2] Total time: 0:17:09 (0.1647 s / it) +Averaged stats: lr: 0.000075 grad: 0.1955 (0.2310) loss: 0.9745 (0.9794) +Eval (hcp-train-subset): [2] [ 0/62] eta: 0:04:09 loss: 0.9783 (0.9783) time: 4.0300 data: 3.9876 max mem: 8452 +Eval (hcp-train-subset): [2] [61/62] eta: 0:00:00 loss: 0.9796 (0.9792) time: 0.1052 data: 0.0783 max mem: 8452 +Eval (hcp-train-subset): [2] Total time: 0:00:12 (0.2067 s / it) +Averaged stats (hcp-train-subset): loss: 0.9796 (0.9792) +Eval (hcp-val): [2] [ 0/62] eta: 0:03:04 loss: 0.9700 (0.9700) time: 2.9803 data: 2.8921 max mem: 8452 +Eval (hcp-val): [2] [61/62] eta: 0:00:00 loss: 0.9774 (0.9768) time: 0.0766 data: 0.0554 max mem: 8452 +Eval (hcp-val): [2] Total time: 0:00:14 (0.2388 s / it) +Averaged stats (hcp-val): loss: 0.9774 (0.9768) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [3] [ 0/6250] eta: 7:07:25 lr: 0.000075 grad: 0.3166 (0.3166) loss: 0.9792 (0.9792) time: 4.1034 data: 3.7382 max mem: 8452 +Train: [3] [ 100/6250] eta: 0:22:47 lr: 0.000075 grad: 0.1726 (0.2192) loss: 0.9773 (0.9772) time: 0.1667 data: 0.0709 max mem: 8452 +Train: [3] [ 200/6250] eta: 0:19:31 lr: 0.000076 grad: 0.1565 (0.2083) loss: 0.9729 (0.9762) time: 0.1512 data: 0.0716 max mem: 8452 +Train: [3] [ 300/6250] eta: 0:18:11 lr: 0.000076 grad: 0.1700 (0.2114) loss: 0.9743 (0.9755) time: 0.1622 data: 0.0738 max mem: 8452 +Train: [3] [ 400/6250] eta: 0:17:32 lr: 0.000077 grad: 0.1769 (0.2070) loss: 0.9746 (0.9750) time: 0.1838 data: 0.0808 max mem: 8452 +Train: [3] [ 500/6250] eta: 0:16:47 lr: 0.000077 grad: 0.1495 (0.2065) loss: 0.9756 (0.9749) time: 0.1631 data: 0.0624 max mem: 8452 +Train: [3] [ 600/6250] eta: 0:16:09 lr: 0.000077 grad: 0.1649 (0.2092) loss: 0.9753 (0.9746) time: 0.1421 data: 0.0576 max mem: 8452 +Train: [3] [ 700/6250] eta: 0:15:49 lr: 0.000078 grad: 0.1572 (0.2093) loss: 0.9740 (0.9742) time: 0.1595 data: 0.0818 max mem: 8452 +Train: [3] [ 800/6250] eta: 0:15:50 lr: 0.000078 grad: 0.1536 (0.2086) loss: 0.9703 (0.9738) time: 0.1901 data: 0.1189 max mem: 8452 +Train: [3] [ 900/6250] eta: 0:15:35 lr: 0.000079 grad: 0.1720 (0.2094) loss: 0.9709 (0.9736) time: 0.1605 data: 0.0720 max mem: 8452 +Train: [3] [1000/6250] eta: 0:15:14 lr: 0.000079 grad: 0.1642 (0.2097) loss: 0.9720 (0.9733) time: 0.1820 data: 0.0977 max mem: 8452 +Train: [3] [1100/6250] eta: 0:14:51 lr: 0.000079 grad: 0.1528 (0.2123) loss: 0.9712 (0.9732) time: 0.1483 data: 0.0695 max mem: 8452 +Train: [3] [1200/6250] eta: 0:14:33 lr: 0.000080 grad: 0.1852 (0.2114) loss: 0.9695 (0.9730) time: 0.1919 data: 0.1196 max mem: 8452 +Train: [3] [1300/6250] eta: 0:14:12 lr: 0.000080 grad: 0.1830 (0.2129) loss: 0.9722 (0.9728) time: 0.1526 data: 0.0743 max mem: 8452 +Train: [3] [1400/6250] eta: 0:13:57 lr: 0.000081 grad: 0.1977 (0.2147) loss: 0.9691 (0.9727) time: 0.1930 data: 0.1101 max mem: 8452 +Train: [3] [1500/6250] eta: 0:13:42 lr: 0.000081 grad: 0.1553 (0.2138) loss: 0.9681 (0.9724) time: 0.1865 data: 0.1025 max mem: 8452 +Train: [3] [1600/6250] eta: 0:13:24 lr: 0.000081 grad: 0.2036 (0.2139) loss: 0.9688 (0.9722) time: 0.1355 data: 0.0343 max mem: 8452 +Train: [3] [1700/6250] eta: 0:13:10 lr: 0.000082 grad: 0.1884 (0.2137) loss: 0.9708 (0.9720) time: 0.1212 data: 0.0166 max mem: 8452 +Train: [3] [1800/6250] eta: 0:12:51 lr: 0.000082 grad: 0.2003 (0.2146) loss: 0.9670 (0.9718) time: 0.1353 data: 0.0652 max mem: 8452 +Train: [3] [1900/6250] eta: 0:12:33 lr: 0.000083 grad: 0.2330 (0.2151) loss: 0.9668 (0.9716) time: 0.1921 data: 0.1029 max mem: 8452 +Train: [3] [2000/6250] eta: 0:12:13 lr: 0.000083 grad: 0.1770 (0.2154) loss: 0.9664 (0.9715) time: 0.1451 data: 0.0729 max mem: 8452 +Train: [3] [2100/6250] eta: 0:11:54 lr: 0.000083 grad: 0.2012 (0.2163) loss: 0.9670 (0.9713) time: 0.1712 data: 0.0880 max mem: 8452 +Train: [3] [2200/6250] eta: 0:11:34 lr: 0.000084 grad: 0.2246 (0.2175) loss: 0.9636 (0.9710) time: 0.1650 data: 0.0810 max mem: 8452 +Train: [3] [2300/6250] eta: 0:11:14 lr: 0.000084 grad: 0.1706 (0.2181) loss: 0.9669 (0.9708) time: 0.1436 data: 0.0569 max mem: 8452 +Train: [3] [2400/6250] eta: 0:10:56 lr: 0.000085 grad: 0.1734 (0.2183) loss: 0.9641 (0.9706) time: 0.1841 data: 0.1035 max mem: 8452 +Train: [3] [2500/6250] eta: 0:10:38 lr: 0.000085 grad: 0.1976 (0.2190) loss: 0.9674 (0.9704) time: 0.1809 data: 0.0963 max mem: 8452 +Train: [3] [2600/6250] eta: 0:10:19 lr: 0.000085 grad: 0.2598 (0.2208) loss: 0.9646 (0.9702) time: 0.1598 data: 0.0759 max mem: 8452 +Train: [3] [2700/6250] eta: 0:10:03 lr: 0.000086 grad: 0.2282 (0.2218) loss: 0.9655 (0.9700) time: 0.1921 data: 0.1031 max mem: 8452 +Train: [3] [2800/6250] eta: 0:09:44 lr: 0.000086 grad: 0.2585 (0.2229) loss: 0.9671 (0.9698) time: 0.1642 data: 0.0771 max mem: 8452 +Train: [3] [2900/6250] eta: 0:09:26 lr: 0.000087 grad: 0.2397 (0.2244) loss: 0.9628 (0.9696) time: 0.1603 data: 0.0763 max mem: 8452 +Train: [3] [3000/6250] eta: 0:09:11 lr: 0.000087 grad: 0.2932 (0.2258) loss: 0.9647 (0.9694) time: 0.1849 data: 0.0981 max mem: 8452 +Train: [3] [3100/6250] eta: 0:08:53 lr: 0.000087 grad: 0.2430 (0.2273) loss: 0.9639 (0.9692) time: 0.1396 data: 0.0596 max mem: 8452 +Train: [3] [3200/6250] eta: 0:08:35 lr: 0.000088 grad: 0.2250 (0.2291) loss: 0.9639 (0.9690) time: 0.1710 data: 0.0945 max mem: 8452 +Train: [3] [3300/6250] eta: 0:08:18 lr: 0.000088 grad: 0.2960 (0.2312) loss: 0.9626 (0.9688) time: 0.1404 data: 0.0554 max mem: 8452 +Train: [3] [3400/6250] eta: 0:08:01 lr: 0.000089 grad: 0.2566 (0.2334) loss: 0.9629 (0.9686) time: 0.1769 data: 0.1049 max mem: 8452 +Train: [3] [3500/6250] eta: 0:07:44 lr: 0.000089 grad: 0.2341 (0.2354) loss: 0.9631 (0.9683) time: 0.1234 data: 0.0298 max mem: 8452 +Train: [3] [3600/6250] eta: 0:07:27 lr: 0.000089 grad: 0.2667 (0.2374) loss: 0.9619 (0.9681) time: 0.1680 data: 0.0929 max mem: 8452 +Train: [3] [3700/6250] eta: 0:07:09 lr: 0.000090 grad: 0.2900 (0.2394) loss: 0.9586 (0.9679) time: 0.1556 data: 0.0773 max mem: 8452 +Train: [3] [3800/6250] eta: 0:06:51 lr: 0.000090 grad: 0.2996 (0.2415) loss: 0.9614 (0.9677) time: 0.1511 data: 0.0641 max mem: 8452 +Train: [3] [3900/6250] eta: 0:06:35 lr: 0.000091 grad: 0.3162 (0.2433) loss: 0.9587 (0.9674) time: 0.1773 data: 0.0948 max mem: 8452 +Train: [3] [4000/6250] eta: 0:06:18 lr: 0.000091 grad: 0.2957 (0.2449) loss: 0.9581 (0.9672) time: 0.1521 data: 0.0800 max mem: 8452 +Train: [3] [4100/6250] eta: 0:06:01 lr: 0.000091 grad: 0.3304 (0.2464) loss: 0.9564 (0.9670) time: 0.1316 data: 0.0582 max mem: 8452 +Train: [3] [4200/6250] eta: 0:05:44 lr: 0.000092 grad: 0.3450 (0.2479) loss: 0.9551 (0.9668) time: 0.1875 data: 0.1123 max mem: 8452 +Train: [3] [4300/6250] eta: 0:05:27 lr: 0.000092 grad: 0.2704 (0.2496) loss: 0.9567 (0.9665) time: 0.1526 data: 0.0811 max mem: 8452 +Train: [3] [4400/6250] eta: 0:05:10 lr: 0.000093 grad: 0.3051 (0.2512) loss: 0.9537 (0.9663) time: 0.1250 data: 0.0504 max mem: 8452 +Train: [3] [4500/6250] eta: 0:04:53 lr: 0.000093 grad: 0.2717 (0.2526) loss: 0.9570 (0.9661) time: 0.1538 data: 0.0716 max mem: 8452 +Train: [3] [4600/6250] eta: 0:04:36 lr: 0.000093 grad: 0.3134 (0.2537) loss: 0.9561 (0.9659) time: 0.1758 data: 0.0947 max mem: 8452 +Train: [3] [4700/6250] eta: 0:04:19 lr: 0.000094 grad: 0.2557 (0.2544) loss: 0.9520 (0.9656) time: 0.1843 data: 0.0908 max mem: 8452 +Train: [3] [4800/6250] eta: 0:04:03 lr: 0.000094 grad: 0.3091 (0.2560) loss: 0.9509 (0.9654) time: 0.1560 data: 0.0406 max mem: 8452 +Train: [3] [4900/6250] eta: 0:03:46 lr: 0.000095 grad: 0.2659 (0.2575) loss: 0.9537 (0.9651) time: 0.1883 data: 0.1043 max mem: 8452 +Train: [3] [5000/6250] eta: 0:03:29 lr: 0.000095 grad: 0.2683 (0.2589) loss: 0.9505 (0.9648) time: 0.1621 data: 0.0805 max mem: 8452 +Train: [3] [5100/6250] eta: 0:03:12 lr: 0.000095 grad: 0.3447 (0.2602) loss: 0.9494 (0.9645) time: 0.1595 data: 0.0680 max mem: 8452 +Train: [3] [5200/6250] eta: 0:02:55 lr: 0.000096 grad: 0.3338 (0.2620) loss: 0.9500 (0.9643) time: 0.1570 data: 0.0819 max mem: 8452 +Train: [3] [5300/6250] eta: 0:02:38 lr: 0.000096 grad: 0.2850 (0.2628) loss: 0.9513 (0.9640) time: 0.1522 data: 0.0725 max mem: 8452 +Train: [3] [5400/6250] eta: 0:02:22 lr: 0.000097 grad: 0.2795 (0.2638) loss: 0.9504 (0.9638) time: 0.1379 data: 0.0554 max mem: 8452 +Train: [3] [5500/6250] eta: 0:02:05 lr: 0.000097 grad: 0.2865 (0.2646) loss: 0.9509 (0.9635) time: 0.1376 data: 0.0575 max mem: 8452 +Train: [3] [5600/6250] eta: 0:01:48 lr: 0.000097 grad: 0.2732 (0.2658) loss: 0.9495 (0.9633) time: 0.1685 data: 0.0854 max mem: 8452 +Train: [3] [5700/6250] eta: 0:01:31 lr: 0.000098 grad: 0.3158 (0.2665) loss: 0.9516 (0.9630) time: 0.1469 data: 0.0675 max mem: 8452 +Train: [3] [5800/6250] eta: 0:01:15 lr: 0.000098 grad: 0.2222 (0.2668) loss: 0.9501 (0.9628) time: 0.1098 data: 0.0189 max mem: 8452 +Train: [3] [5900/6250] eta: 0:00:58 lr: 0.000099 grad: 0.3372 (0.2677) loss: 0.9470 (0.9626) time: 0.2090 data: 0.1442 max mem: 8452 +Train: [3] [6000/6250] eta: 0:00:41 lr: 0.000099 grad: 0.3133 (0.2683) loss: 0.9463 (0.9623) time: 0.1930 data: 0.1174 max mem: 8452 +Train: [3] [6100/6250] eta: 0:00:25 lr: 0.000099 grad: 0.2931 (0.2688) loss: 0.9477 (0.9621) time: 0.2102 data: 0.1418 max mem: 8452 +Train: [3] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.2289 (0.2690) loss: 0.9434 (0.9618) time: 0.1699 data: 0.0938 max mem: 8452 +Train: [3] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.2968 (0.2692) loss: 0.9453 (0.9617) time: 0.1692 data: 0.0939 max mem: 8452 +Train: [3] Total time: 0:17:32 (0.1684 s / it) +Averaged stats: lr: 0.000100 grad: 0.2968 (0.2692) loss: 0.9453 (0.9617) +Eval (hcp-train-subset): [3] [ 0/62] eta: 0:05:06 loss: 0.9512 (0.9512) time: 4.9437 data: 4.9159 max mem: 8452 +Eval (hcp-train-subset): [3] [61/62] eta: 0:00:00 loss: 0.9539 (0.9514) time: 0.1316 data: 0.1104 max mem: 8452 +Eval (hcp-train-subset): [3] Total time: 0:00:13 (0.2232 s / it) +Averaged stats (hcp-train-subset): loss: 0.9539 (0.9514) +Eval (hcp-val): [3] [ 0/62] eta: 0:05:23 loss: 0.9466 (0.9466) time: 5.2149 data: 5.1853 max mem: 8452 +Eval (hcp-val): [3] [61/62] eta: 0:00:00 loss: 0.9483 (0.9486) time: 0.1288 data: 0.1063 max mem: 8452 +Eval (hcp-val): [3] Total time: 0:00:13 (0.2258 s / it) +Averaged stats (hcp-val): loss: 0.9483 (0.9486) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [4] [ 0/6250] eta: 9:51:23 lr: 0.000100 grad: 0.2342 (0.2342) loss: 0.9592 (0.9592) time: 5.6774 data: 5.4977 max mem: 8452 +Train: [4] [ 100/6250] eta: 0:23:18 lr: 0.000100 grad: 0.2968 (0.3251) loss: 0.9521 (0.9492) time: 0.1593 data: 0.0526 max mem: 8452 +Train: [4] [ 200/6250] eta: 0:19:38 lr: 0.000101 grad: 0.3204 (0.3157) loss: 0.9475 (0.9482) time: 0.1572 data: 0.0648 max mem: 8452 +Train: [4] [ 300/6250] eta: 0:18:26 lr: 0.000101 grad: 0.2759 (0.3109) loss: 0.9478 (0.9476) time: 0.1567 data: 0.0517 max mem: 8452 +Train: [4] [ 400/6250] eta: 0:17:19 lr: 0.000102 grad: 0.2566 (0.3055) loss: 0.9402 (0.9465) time: 0.1527 data: 0.0511 max mem: 8452 +Train: [4] [ 500/6250] eta: 0:16:37 lr: 0.000102 grad: 0.2921 (0.3062) loss: 0.9432 (0.9459) time: 0.1630 data: 0.0496 max mem: 8452 +Train: [4] [ 600/6250] eta: 0:16:18 lr: 0.000102 grad: 0.2380 (0.3040) loss: 0.9437 (0.9458) time: 0.1834 data: 0.1022 max mem: 8452 +Train: [4] [ 700/6250] eta: 0:16:59 lr: 0.000103 grad: 0.2169 (0.2988) loss: 0.9436 (0.9457) time: 0.3300 data: 0.2307 max mem: 8452 +Train: [4] [ 800/6250] eta: 0:16:39 lr: 0.000103 grad: 0.2904 (0.2972) loss: 0.9436 (0.9455) time: 0.1876 data: 0.0970 max mem: 8452 +Train: [4] [ 900/6250] eta: 0:16:24 lr: 0.000104 grad: 0.2804 (0.2959) loss: 0.9420 (0.9453) time: 0.1619 data: 0.0637 max mem: 8452 +Train: [4] [1000/6250] eta: 0:15:56 lr: 0.000104 grad: 0.3178 (0.2939) loss: 0.9455 (0.9452) time: 0.1320 data: 0.0471 max mem: 8452 +Train: [4] [1100/6250] eta: 0:15:28 lr: 0.000104 grad: 0.2745 (0.2930) loss: 0.9429 (0.9449) time: 0.1428 data: 0.0461 max mem: 8452 +Train: [4] [1200/6250] eta: 0:15:03 lr: 0.000105 grad: 0.2904 (0.2918) loss: 0.9391 (0.9445) time: 0.1625 data: 0.0805 max mem: 8452 +Train: [4] [1300/6250] eta: 0:14:34 lr: 0.000105 grad: 0.2583 (0.2904) loss: 0.9432 (0.9442) time: 0.1621 data: 0.0862 max mem: 8452 +Train: [4] [1400/6250] eta: 0:14:10 lr: 0.000106 grad: 0.2404 (0.2885) loss: 0.9399 (0.9439) time: 0.1778 data: 0.1015 max mem: 8452 +Train: [4] [1500/6250] eta: 0:13:49 lr: 0.000106 grad: 0.2879 (0.2878) loss: 0.9411 (0.9437) time: 0.1679 data: 0.0679 max mem: 8452 +Train: [4] [1600/6250] eta: 0:13:30 lr: 0.000106 grad: 0.2607 (0.2869) loss: 0.9416 (0.9436) time: 0.1418 data: 0.0430 max mem: 8452 +Train: [4] [1700/6250] eta: 0:13:12 lr: 0.000107 grad: 0.2917 (0.2861) loss: 0.9403 (0.9434) time: 0.1683 data: 0.0788 max mem: 8452 +Train: [4] [1800/6250] eta: 0:12:57 lr: 0.000107 grad: 0.2302 (0.2846) loss: 0.9379 (0.9431) time: 0.1920 data: 0.1088 max mem: 8452 +Train: [4] [1900/6250] eta: 0:12:40 lr: 0.000108 grad: 0.2848 (0.2832) loss: 0.9400 (0.9429) time: 0.1883 data: 0.0888 max mem: 8452 +Train: [4] [2000/6250] eta: 0:12:23 lr: 0.000108 grad: 0.2710 (0.2821) loss: 0.9385 (0.9426) time: 0.1486 data: 0.0529 max mem: 8452 +Train: [4] [2100/6250] eta: 0:12:06 lr: 0.000108 grad: 0.2092 (0.2802) loss: 0.9388 (0.9424) time: 0.1510 data: 0.0758 max mem: 8452 +Train: [4] [2200/6250] eta: 0:11:50 lr: 0.000109 grad: 0.2797 (0.2791) loss: 0.9375 (0.9422) time: 0.2279 data: 0.1495 max mem: 8452 +Train: [4] [2300/6250] eta: 0:11:32 lr: 0.000109 grad: 0.2212 (0.2772) loss: 0.9374 (0.9419) time: 0.2051 data: 0.1385 max mem: 8452 +Train: [4] [2400/6250] eta: 0:11:13 lr: 0.000110 grad: 0.2365 (0.2752) loss: 0.9425 (0.9417) time: 0.1883 data: 0.0789 max mem: 8452 +Train: [4] [2500/6250] eta: 0:10:57 lr: 0.000110 grad: 0.1944 (0.2731) loss: 0.9337 (0.9414) time: 0.1701 data: 0.0889 max mem: 8452 +Train: [4] [2600/6250] eta: 0:10:38 lr: 0.000110 grad: 0.1968 (0.2711) loss: 0.9352 (0.9412) time: 0.1541 data: 0.0793 max mem: 8452 +Train: [4] [2700/6250] eta: 0:10:19 lr: 0.000111 grad: 0.1798 (0.2703) loss: 0.9330 (0.9410) time: 0.1233 data: 0.0446 max mem: 8452 +Train: [4] [2800/6250] eta: 0:09:59 lr: 0.000111 grad: 0.1867 (0.2680) loss: 0.9332 (0.9407) time: 0.1652 data: 0.0871 max mem: 8452 +Train: [4] [2900/6250] eta: 0:09:41 lr: 0.000112 grad: 0.1986 (0.2659) loss: 0.9314 (0.9404) time: 0.1967 data: 0.1266 max mem: 8452 +Train: [4] [3000/6250] eta: 0:09:23 lr: 0.000112 grad: 0.1991 (0.2634) loss: 0.9284 (0.9401) time: 0.1442 data: 0.0491 max mem: 8452 +Train: [4] [3100/6250] eta: 0:09:05 lr: 0.000112 grad: 0.1817 (0.2619) loss: 0.9331 (0.9399) time: 0.1723 data: 0.1003 max mem: 8452 +Train: [4] [3200/6250] eta: 0:08:46 lr: 0.000113 grad: 0.1963 (0.2601) loss: 0.9335 (0.9396) time: 0.1334 data: 0.0486 max mem: 8452 +Train: [4] [3300/6250] eta: 0:08:29 lr: 0.000113 grad: 0.1830 (0.2579) loss: 0.9282 (0.9393) time: 0.1794 data: 0.0882 max mem: 8452 +Train: [4] [3400/6250] eta: 0:08:11 lr: 0.000114 grad: 0.1893 (0.2561) loss: 0.9336 (0.9391) time: 0.1769 data: 0.0807 max mem: 8452 +Train: [4] [3500/6250] eta: 0:07:52 lr: 0.000114 grad: 0.1548 (0.2539) loss: 0.9279 (0.9388) time: 0.2015 data: 0.1256 max mem: 8452 +Train: [4] [3600/6250] eta: 0:07:34 lr: 0.000114 grad: 0.1639 (0.2519) loss: 0.9281 (0.9385) time: 0.1478 data: 0.0657 max mem: 8452 +Train: [4] [3700/6250] eta: 0:07:16 lr: 0.000115 grad: 0.1640 (0.2503) loss: 0.9319 (0.9383) time: 0.1476 data: 0.0669 max mem: 8452 +Train: [4] [3800/6250] eta: 0:06:59 lr: 0.000115 grad: 0.1465 (0.2482) loss: 0.9265 (0.9380) time: 0.1844 data: 0.1029 max mem: 8452 +Train: [4] [3900/6250] eta: 0:06:41 lr: 0.000116 grad: 0.1517 (0.2464) loss: 0.9273 (0.9377) time: 0.1494 data: 0.0720 max mem: 8452 +Train: [4] [4000/6250] eta: 0:06:23 lr: 0.000116 grad: 0.1634 (0.2448) loss: 0.9250 (0.9375) time: 0.1551 data: 0.0617 max mem: 8452 +Train: [4] [4100/6250] eta: 0:06:06 lr: 0.000116 grad: 0.1813 (0.2430) loss: 0.9259 (0.9372) time: 0.1795 data: 0.0964 max mem: 8452 +Train: [4] [4200/6250] eta: 0:05:48 lr: 0.000117 grad: 0.1602 (0.2411) loss: 0.9253 (0.9370) time: 0.1467 data: 0.0672 max mem: 8452 +Train: [4] [4300/6250] eta: 0:05:31 lr: 0.000117 grad: 0.1670 (0.2396) loss: 0.9281 (0.9367) time: 0.1643 data: 0.0736 max mem: 8452 +Train: [4] [4400/6250] eta: 0:05:14 lr: 0.000118 grad: 0.1626 (0.2385) loss: 0.9256 (0.9365) time: 0.1489 data: 0.0591 max mem: 8452 +Train: [4] [4500/6250] eta: 0:04:57 lr: 0.000118 grad: 0.1511 (0.2367) loss: 0.9277 (0.9363) time: 0.1327 data: 0.0513 max mem: 8452 +Train: [4] [4600/6250] eta: 0:04:40 lr: 0.000118 grad: 0.1935 (0.2354) loss: 0.9220 (0.9360) time: 0.1904 data: 0.1023 max mem: 8452 +Train: [4] [4700/6250] eta: 0:04:23 lr: 0.000119 grad: 0.1740 (0.2339) loss: 0.9261 (0.9358) time: 0.1568 data: 0.0825 max mem: 8452 +Train: [4] [4800/6250] eta: 0:04:05 lr: 0.000119 grad: 0.1591 (0.2326) loss: 0.9223 (0.9355) time: 0.1602 data: 0.0860 max mem: 8452 +Train: [4] [4900/6250] eta: 0:03:48 lr: 0.000120 grad: 0.1522 (0.2312) loss: 0.9231 (0.9353) time: 0.1542 data: 0.0676 max mem: 8452 +Train: [4] [5000/6250] eta: 0:03:32 lr: 0.000120 grad: 0.1357 (0.2298) loss: 0.9246 (0.9351) time: 0.1791 data: 0.0905 max mem: 8452 +Train: [4] [5100/6250] eta: 0:03:15 lr: 0.000120 grad: 0.1413 (0.2283) loss: 0.9232 (0.9349) time: 0.1908 data: 0.1113 max mem: 8452 +Train: [4] [5200/6250] eta: 0:02:58 lr: 0.000121 grad: 0.1598 (0.2268) loss: 0.9267 (0.9346) time: 0.2223 data: 0.1351 max mem: 8452 +Train: [4] [5300/6250] eta: 0:02:41 lr: 0.000121 grad: 0.1487 (0.2256) loss: 0.9204 (0.9344) time: 0.1470 data: 0.0655 max mem: 8452 +Train: [4] [5400/6250] eta: 0:02:24 lr: 0.000122 grad: 0.1405 (0.2242) loss: 0.9209 (0.9342) time: 0.1621 data: 0.0794 max mem: 8452 +Train: [4] [5500/6250] eta: 0:02:07 lr: 0.000122 grad: 0.1529 (0.2230) loss: 0.9236 (0.9339) time: 0.1545 data: 0.0776 max mem: 8452 +Train: [4] [5600/6250] eta: 0:01:50 lr: 0.000122 grad: 0.1485 (0.2219) loss: 0.9145 (0.9336) time: 0.1606 data: 0.0780 max mem: 8452 +Train: [4] [5700/6250] eta: 0:01:33 lr: 0.000123 grad: 0.1719 (0.2210) loss: 0.9172 (0.9334) time: 0.1574 data: 0.0780 max mem: 8452 +Train: [4] [5800/6250] eta: 0:01:16 lr: 0.000123 grad: 0.1639 (0.2202) loss: 0.9216 (0.9331) time: 0.1947 data: 0.1267 max mem: 8452 +Train: [4] [5900/6250] eta: 0:00:59 lr: 0.000124 grad: 0.1615 (0.2194) loss: 0.9226 (0.9329) time: 0.1620 data: 0.0856 max mem: 8452 +Train: [4] [6000/6250] eta: 0:00:42 lr: 0.000124 grad: 0.1481 (0.2183) loss: 0.9202 (0.9326) time: 0.1585 data: 0.0919 max mem: 8452 +Train: [4] [6100/6250] eta: 0:00:25 lr: 0.000124 grad: 0.1519 (0.2172) loss: 0.9204 (0.9324) time: 0.1714 data: 0.0999 max mem: 8452 +Train: [4] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1400 (0.2161) loss: 0.9182 (0.9321) time: 0.1834 data: 0.1106 max mem: 8452 +Train: [4] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.1527 (0.2157) loss: 0.9207 (0.9320) time: 0.1391 data: 0.0706 max mem: 8452 +Train: [4] Total time: 0:17:42 (0.1699 s / it) +Averaged stats: lr: 0.000125 grad: 0.1527 (0.2157) loss: 0.9207 (0.9320) +Eval (hcp-train-subset): [4] [ 0/62] eta: 0:04:54 loss: 0.9306 (0.9306) time: 4.7483 data: 4.7195 max mem: 8452 +Eval (hcp-train-subset): [4] [61/62] eta: 0:00:00 loss: 0.9259 (0.9241) time: 0.1322 data: 0.1109 max mem: 8452 +Eval (hcp-train-subset): [4] Total time: 0:00:14 (0.2341 s / it) +Averaged stats (hcp-train-subset): loss: 0.9259 (0.9241) +Making plots (hcp-train-subset): example=39 +Eval (hcp-val): [4] [ 0/62] eta: 0:04:19 loss: 0.9120 (0.9120) time: 4.1819 data: 4.0960 max mem: 8452 +Eval (hcp-val): [4] [61/62] eta: 0:00:00 loss: 0.9185 (0.9186) time: 0.1117 data: 0.0904 max mem: 8452 +Eval (hcp-val): [4] Total time: 0:00:14 (0.2292 s / it) +Averaged stats (hcp-val): loss: 0.9185 (0.9186) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [5] [ 0/6250] eta: 9:08:52 lr: 0.000125 grad: 0.0979 (0.0979) loss: 0.9481 (0.9481) time: 5.2693 data: 4.9113 max mem: 8452 +Train: [5] [ 100/6250] eta: 0:23:09 lr: 0.000125 grad: 0.1698 (0.1939) loss: 0.9149 (0.9210) time: 0.1910 data: 0.0934 max mem: 8452 +Train: [5] [ 200/6250] eta: 0:19:44 lr: 0.000125 grad: 0.1817 (0.1723) loss: 0.9191 (0.9193) time: 0.1577 data: 0.0625 max mem: 8452 +Train: [5] [ 300/6250] eta: 0:18:19 lr: 0.000125 grad: 0.1258 (0.1630) loss: 0.9226 (0.9189) time: 0.1548 data: 0.0585 max mem: 8452 +Train: [5] [ 400/6250] eta: 0:17:26 lr: 0.000125 grad: 0.1250 (0.1579) loss: 0.9195 (0.9186) time: 0.1697 data: 0.0764 max mem: 8452 +Train: [5] [ 500/6250] eta: 0:16:42 lr: 0.000125 grad: 0.1367 (0.1560) loss: 0.9156 (0.9184) time: 0.1706 data: 0.0744 max mem: 8452 +Train: [5] [ 600/6250] eta: 0:16:14 lr: 0.000125 grad: 0.1406 (0.1536) loss: 0.9159 (0.9178) time: 0.1861 data: 0.0965 max mem: 8452 +Train: [5] [ 700/6250] eta: 0:15:46 lr: 0.000125 grad: 0.1346 (0.1518) loss: 0.9141 (0.9173) time: 0.1668 data: 0.0795 max mem: 8452 +Train: [5] [ 800/6250] eta: 0:15:31 lr: 0.000125 grad: 0.1195 (0.1501) loss: 0.9161 (0.9169) time: 0.1832 data: 0.1013 max mem: 8452 +Train: [5] [ 900/6250] eta: 0:15:14 lr: 0.000125 grad: 0.1204 (0.1482) loss: 0.9152 (0.9168) time: 0.1792 data: 0.1041 max mem: 8452 +Train: [5] [1000/6250] eta: 0:14:57 lr: 0.000125 grad: 0.1235 (0.1469) loss: 0.9143 (0.9166) time: 0.1790 data: 0.1055 max mem: 8452 +Train: [5] [1100/6250] eta: 0:14:41 lr: 0.000125 grad: 0.1178 (0.1453) loss: 0.9132 (0.9164) time: 0.1839 data: 0.1157 max mem: 8452 +Train: [5] [1200/6250] eta: 0:14:32 lr: 0.000125 grad: 0.1100 (0.1438) loss: 0.9122 (0.9161) time: 0.1849 data: 0.1145 max mem: 8452 +Train: [5] [1300/6250] eta: 0:14:21 lr: 0.000125 grad: 0.1253 (0.1433) loss: 0.9147 (0.9160) time: 0.1703 data: 0.0949 max mem: 8452 +Train: [5] [1400/6250] eta: 0:14:08 lr: 0.000125 grad: 0.1278 (0.1422) loss: 0.9126 (0.9160) time: 0.1843 data: 0.1019 max mem: 8452 +Train: [5] [1500/6250] eta: 0:13:53 lr: 0.000125 grad: 0.1246 (0.1413) loss: 0.9116 (0.9158) time: 0.1681 data: 0.0836 max mem: 8452 +Train: [5] [1600/6250] eta: 0:13:31 lr: 0.000125 grad: 0.1247 (0.1410) loss: 0.9102 (0.9156) time: 0.1446 data: 0.0694 max mem: 8452 +Train: [5] [1700/6250] eta: 0:13:10 lr: 0.000125 grad: 0.1219 (0.1400) loss: 0.9117 (0.9154) time: 0.1594 data: 0.0717 max mem: 8452 +Train: [5] [1800/6250] eta: 0:12:48 lr: 0.000125 grad: 0.1319 (0.1395) loss: 0.9084 (0.9152) time: 0.1492 data: 0.0715 max mem: 8452 +Train: [5] [1900/6250] eta: 0:12:28 lr: 0.000125 grad: 0.1277 (0.1387) loss: 0.9155 (0.9150) time: 0.1564 data: 0.0807 max mem: 8452 +Train: [5] [2000/6250] eta: 0:12:09 lr: 0.000125 grad: 0.1220 (0.1379) loss: 0.9145 (0.9150) time: 0.1427 data: 0.0685 max mem: 8452 +Train: [5] [2100/6250] eta: 0:11:50 lr: 0.000125 grad: 0.1155 (0.1371) loss: 0.9128 (0.9149) time: 0.1592 data: 0.0812 max mem: 8452 +Train: [5] [2200/6250] eta: 0:11:33 lr: 0.000125 grad: 0.1145 (0.1362) loss: 0.9150 (0.9149) time: 0.1481 data: 0.0698 max mem: 8452 +Train: [5] [2300/6250] eta: 0:11:16 lr: 0.000125 grad: 0.1170 (0.1354) loss: 0.9113 (0.9149) time: 0.1606 data: 0.0843 max mem: 8452 +Train: [5] [2400/6250] eta: 0:10:58 lr: 0.000125 grad: 0.1217 (0.1346) loss: 0.9115 (0.9148) time: 0.1515 data: 0.0676 max mem: 8452 +Train: [5] [2500/6250] eta: 0:10:41 lr: 0.000125 grad: 0.1217 (0.1341) loss: 0.9133 (0.9148) time: 0.2084 data: 0.1403 max mem: 8452 +Train: [5] [2600/6250] eta: 0:10:24 lr: 0.000125 grad: 0.1079 (0.1338) loss: 0.9133 (0.9148) time: 0.1489 data: 0.0498 max mem: 8452 +Train: [5] [2700/6250] eta: 0:10:09 lr: 0.000125 grad: 0.1296 (0.1333) loss: 0.9138 (0.9148) time: 0.1649 data: 0.0955 max mem: 8452 +Train: [5] [2800/6250] eta: 0:09:53 lr: 0.000125 grad: 0.1152 (0.1328) loss: 0.9138 (0.9147) time: 0.1753 data: 0.0858 max mem: 8452 +Train: [5] [2900/6250] eta: 0:09:36 lr: 0.000125 grad: 0.1090 (0.1324) loss: 0.9131 (0.9146) time: 0.1663 data: 0.0846 max mem: 8452 +Train: [5] [3000/6250] eta: 0:09:18 lr: 0.000125 grad: 0.1297 (0.1319) loss: 0.9126 (0.9146) time: 0.1601 data: 0.0877 max mem: 8452 +Train: [5] [3100/6250] eta: 0:08:59 lr: 0.000125 grad: 0.1027 (0.1313) loss: 0.9122 (0.9146) time: 0.1390 data: 0.0509 max mem: 8452 +Train: [5] [3200/6250] eta: 0:08:42 lr: 0.000125 grad: 0.1135 (0.1309) loss: 0.9140 (0.9146) time: 0.1719 data: 0.0855 max mem: 8452 +Train: [5] [3300/6250] eta: 0:08:24 lr: 0.000125 grad: 0.1046 (0.1304) loss: 0.9137 (0.9146) time: 0.1322 data: 0.0329 max mem: 8452 +Train: [5] [3400/6250] eta: 0:08:07 lr: 0.000125 grad: 0.1103 (0.1300) loss: 0.9124 (0.9145) time: 0.1516 data: 0.0789 max mem: 8452 +Train: [5] [3500/6250] eta: 0:07:49 lr: 0.000125 grad: 0.1182 (0.1296) loss: 0.9108 (0.9144) time: 0.1930 data: 0.1034 max mem: 8452 +Train: [5] [3600/6250] eta: 0:07:31 lr: 0.000125 grad: 0.1107 (0.1291) loss: 0.9101 (0.9144) time: 0.1550 data: 0.0745 max mem: 8452 +Train: [5] [3700/6250] eta: 0:07:14 lr: 0.000125 grad: 0.1204 (0.1288) loss: 0.9086 (0.9143) time: 0.1607 data: 0.0698 max mem: 8452 +Train: [5] [3800/6250] eta: 0:06:55 lr: 0.000125 grad: 0.1212 (0.1284) loss: 0.9101 (0.9142) time: 0.1687 data: 0.0851 max mem: 8452 +Train: [5] [3900/6250] eta: 0:06:38 lr: 0.000125 grad: 0.1107 (0.1279) loss: 0.9097 (0.9141) time: 0.1509 data: 0.0710 max mem: 8452 +Train: [5] [4000/6250] eta: 0:06:20 lr: 0.000125 grad: 0.1036 (0.1275) loss: 0.9099 (0.9140) time: 0.1770 data: 0.0976 max mem: 8452 +Train: [5] [4100/6250] eta: 0:06:02 lr: 0.000125 grad: 0.1307 (0.1273) loss: 0.9062 (0.9138) time: 0.1595 data: 0.0816 max mem: 8452 +Train: [5] [4200/6250] eta: 0:05:45 lr: 0.000125 grad: 0.1097 (0.1269) loss: 0.9076 (0.9136) time: 0.1620 data: 0.0719 max mem: 8452 +Train: [5] [4300/6250] eta: 0:05:28 lr: 0.000125 grad: 0.1097 (0.1265) loss: 0.9065 (0.9135) time: 0.1480 data: 0.0689 max mem: 8452 +Train: [5] [4400/6250] eta: 0:05:11 lr: 0.000125 grad: 0.1003 (0.1262) loss: 0.9083 (0.9133) time: 0.1733 data: 0.0948 max mem: 8452 +Train: [5] [4500/6250] eta: 0:04:54 lr: 0.000125 grad: 0.1102 (0.1260) loss: 0.9056 (0.9132) time: 0.1851 data: 0.1033 max mem: 8452 +Train: [5] [4600/6250] eta: 0:04:37 lr: 0.000125 grad: 0.1095 (0.1257) loss: 0.9055 (0.9130) time: 0.1968 data: 0.1156 max mem: 8452 +Train: [5] [4700/6250] eta: 0:04:20 lr: 0.000125 grad: 0.1098 (0.1256) loss: 0.9016 (0.9129) time: 0.1723 data: 0.0974 max mem: 8452 +Train: [5] [4800/6250] eta: 0:04:03 lr: 0.000125 grad: 0.1186 (0.1254) loss: 0.9048 (0.9127) time: 0.1658 data: 0.0936 max mem: 8452 +Train: [5] [4900/6250] eta: 0:03:46 lr: 0.000125 grad: 0.1119 (0.1251) loss: 0.9088 (0.9126) time: 0.1476 data: 0.0630 max mem: 8452 +Train: [5] [5000/6250] eta: 0:03:30 lr: 0.000125 grad: 0.1116 (0.1249) loss: 0.9022 (0.9125) time: 0.1525 data: 0.0681 max mem: 8452 +Train: [5] [5100/6250] eta: 0:03:13 lr: 0.000125 grad: 0.1032 (0.1247) loss: 0.9060 (0.9123) time: 0.1542 data: 0.0823 max mem: 8452 +Train: [5] [5200/6250] eta: 0:02:56 lr: 0.000125 grad: 0.1041 (0.1245) loss: 0.9035 (0.9122) time: 0.1592 data: 0.0805 max mem: 8452 +Train: [5] [5300/6250] eta: 0:02:39 lr: 0.000125 grad: 0.1044 (0.1242) loss: 0.9069 (0.9120) time: 0.1632 data: 0.0936 max mem: 8452 +Train: [5] [5400/6250] eta: 0:02:22 lr: 0.000125 grad: 0.1034 (0.1240) loss: 0.9022 (0.9119) time: 0.1578 data: 0.0695 max mem: 8452 +Train: [5] [5500/6250] eta: 0:02:05 lr: 0.000125 grad: 0.1075 (0.1238) loss: 0.9061 (0.9118) time: 0.2146 data: 0.1373 max mem: 8452 +Train: [5] [5600/6250] eta: 0:01:48 lr: 0.000125 grad: 0.1045 (0.1236) loss: 0.9047 (0.9116) time: 0.1537 data: 0.0697 max mem: 8452 +Train: [5] [5700/6250] eta: 0:01:31 lr: 0.000125 grad: 0.1008 (0.1234) loss: 0.9070 (0.9115) time: 0.1591 data: 0.0872 max mem: 8452 +Train: [5] [5800/6250] eta: 0:01:15 lr: 0.000125 grad: 0.1011 (0.1231) loss: 0.9072 (0.9114) time: 0.1941 data: 0.1069 max mem: 8452 +Train: [5] [5900/6250] eta: 0:00:58 lr: 0.000125 grad: 0.1062 (0.1228) loss: 0.9028 (0.9113) time: 0.1726 data: 0.0975 max mem: 8452 +Train: [5] [6000/6250] eta: 0:00:41 lr: 0.000125 grad: 0.1149 (0.1227) loss: 0.9086 (0.9112) time: 0.1599 data: 0.0907 max mem: 8452 +Train: [5] [6100/6250] eta: 0:00:25 lr: 0.000125 grad: 0.1094 (0.1225) loss: 0.9033 (0.9110) time: 0.1808 data: 0.1184 max mem: 8452 +Train: [5] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.1043 (0.1223) loss: 0.9070 (0.9109) time: 0.1511 data: 0.0645 max mem: 8452 +Train: [5] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0950 (0.1221) loss: 0.9049 (0.9109) time: 0.1489 data: 0.0645 max mem: 8452 +Train: [5] Total time: 0:17:31 (0.1683 s / it) +Averaged stats: lr: 0.000125 grad: 0.0950 (0.1221) loss: 0.9049 (0.9109) +Eval (hcp-train-subset): [5] [ 0/62] eta: 0:02:56 loss: 0.9189 (0.9189) time: 2.8419 data: 2.7762 max mem: 8452 +Eval (hcp-train-subset): [5] [61/62] eta: 0:00:00 loss: 0.9101 (0.9110) time: 0.1192 data: 0.0974 max mem: 8452 +Eval (hcp-train-subset): [5] Total time: 0:00:13 (0.2192 s / it) +Averaged stats (hcp-train-subset): loss: 0.9101 (0.9110) +Eval (hcp-val): [5] [ 0/62] eta: 0:03:43 loss: 0.9022 (0.9022) time: 3.5973 data: 3.5009 max mem: 8452 +Eval (hcp-val): [5] [61/62] eta: 0:00:00 loss: 0.9046 (0.9048) time: 0.1339 data: 0.1121 max mem: 8452 +Eval (hcp-val): [5] Total time: 0:00:13 (0.2229 s / it) +Averaged stats (hcp-val): loss: 0.9046 (0.9048) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [6] [ 0/6250] eta: 8:16:32 lr: 0.000125 grad: 0.1536 (0.1536) loss: 0.9084 (0.9084) time: 4.7669 data: 4.3323 max mem: 8452 +Train: [6] [ 100/6250] eta: 0:22:53 lr: 0.000125 grad: 0.1045 (0.1182) loss: 0.9038 (0.9067) time: 0.1779 data: 0.0759 max mem: 8452 +Train: [6] [ 200/6250] eta: 0:19:21 lr: 0.000125 grad: 0.1096 (0.1158) loss: 0.9085 (0.9053) time: 0.1572 data: 0.0545 max mem: 8452 +Train: [6] [ 300/6250] eta: 0:17:50 lr: 0.000125 grad: 0.1034 (0.1140) loss: 0.9006 (0.9046) time: 0.1125 data: 0.0045 max mem: 8452 +Train: [6] [ 400/6250] eta: 0:16:55 lr: 0.000125 grad: 0.0959 (0.1127) loss: 0.9066 (0.9041) time: 0.1707 data: 0.0850 max mem: 8452 +Train: [6] [ 500/6250] eta: 0:16:59 lr: 0.000125 grad: 0.1067 (0.1117) loss: 0.9013 (0.9037) time: 0.1744 data: 0.0722 max mem: 8452 +Train: [6] [ 600/6250] eta: 0:16:44 lr: 0.000125 grad: 0.0964 (0.1109) loss: 0.9062 (0.9038) time: 0.1958 data: 0.1251 max mem: 8452 +Train: [6] [ 700/6250] eta: 0:16:23 lr: 0.000125 grad: 0.1046 (0.1096) loss: 0.9012 (0.9038) time: 0.1615 data: 0.0783 max mem: 8452 +Train: [6] [ 800/6250] eta: 0:16:08 lr: 0.000125 grad: 0.0926 (0.1085) loss: 0.9078 (0.9039) time: 0.2055 data: 0.0992 max mem: 8452 +Train: [6] [ 900/6250] eta: 0:15:48 lr: 0.000125 grad: 0.1047 (0.1080) loss: 0.9017 (0.9038) time: 0.1992 data: 0.1057 max mem: 8452 +Train: [6] [1000/6250] eta: 0:15:14 lr: 0.000125 grad: 0.0983 (0.1076) loss: 0.9016 (0.9035) time: 0.1410 data: 0.0556 max mem: 8452 +Train: [6] [1100/6250] eta: 0:14:53 lr: 0.000125 grad: 0.0931 (0.1072) loss: 0.9026 (0.9033) time: 0.1680 data: 0.0952 max mem: 8452 +Train: [6] [1200/6250] eta: 0:14:29 lr: 0.000125 grad: 0.0996 (0.1068) loss: 0.8971 (0.9030) time: 0.1720 data: 0.0987 max mem: 8452 +Train: [6] [1300/6250] eta: 0:14:04 lr: 0.000125 grad: 0.1070 (0.1062) loss: 0.9003 (0.9029) time: 0.1588 data: 0.0819 max mem: 8452 +Train: [6] [1400/6250] eta: 0:13:52 lr: 0.000125 grad: 0.1061 (0.1062) loss: 0.8977 (0.9027) time: 0.1512 data: 0.0727 max mem: 8452 +Train: [6] [1500/6250] eta: 0:13:34 lr: 0.000125 grad: 0.0985 (0.1056) loss: 0.9014 (0.9027) time: 0.2183 data: 0.1459 max mem: 8452 +Train: [6] [1600/6250] eta: 0:13:19 lr: 0.000125 grad: 0.0954 (0.1054) loss: 0.9016 (0.9027) time: 0.1336 data: 0.0556 max mem: 8452 +Train: [6] [1700/6250] eta: 0:13:03 lr: 0.000125 grad: 0.0938 (0.1049) loss: 0.9014 (0.9028) time: 0.2068 data: 0.1276 max mem: 8452 +Train: [6] [1800/6250] eta: 0:12:48 lr: 0.000125 grad: 0.1013 (0.1047) loss: 0.9013 (0.9028) time: 0.1931 data: 0.1126 max mem: 8452 +Train: [6] [1900/6250] eta: 0:12:32 lr: 0.000125 grad: 0.0912 (0.1044) loss: 0.9042 (0.9028) time: 0.1586 data: 0.0970 max mem: 8452 +Train: [6] [2000/6250] eta: 0:12:12 lr: 0.000125 grad: 0.0943 (0.1041) loss: 0.9027 (0.9029) time: 0.1861 data: 0.1129 max mem: 8452 +Train: [6] [2100/6250] eta: 0:11:53 lr: 0.000125 grad: 0.1020 (0.1039) loss: 0.9056 (0.9029) time: 0.1476 data: 0.0686 max mem: 8452 +Train: [6] [2200/6250] eta: 0:11:34 lr: 0.000125 grad: 0.0975 (0.1037) loss: 0.9040 (0.9029) time: 0.1620 data: 0.0807 max mem: 8452 +Train: [6] [2300/6250] eta: 0:11:17 lr: 0.000125 grad: 0.0951 (0.1036) loss: 0.9018 (0.9030) time: 0.1297 data: 0.0363 max mem: 8452 +Train: [6] [2400/6250] eta: 0:11:01 lr: 0.000125 grad: 0.1024 (0.1035) loss: 0.9028 (0.9029) time: 0.1720 data: 0.0954 max mem: 8452 +Train: [6] [2500/6250] eta: 0:10:40 lr: 0.000125 grad: 0.1042 (0.1036) loss: 0.9048 (0.9029) time: 0.1607 data: 0.0838 max mem: 8452 +Train: [6] [2600/6250] eta: 0:10:22 lr: 0.000125 grad: 0.1006 (0.1036) loss: 0.8985 (0.9028) time: 0.1567 data: 0.0838 max mem: 8452 +Train: [6] [2700/6250] eta: 0:10:07 lr: 0.000125 grad: 0.1004 (0.1036) loss: 0.9046 (0.9028) time: 0.2258 data: 0.1427 max mem: 8452 +Train: [6] [2800/6250] eta: 0:09:48 lr: 0.000125 grad: 0.1003 (0.1034) loss: 0.9044 (0.9028) time: 0.1627 data: 0.0653 max mem: 8452 +Train: [6] [2900/6250] eta: 0:09:33 lr: 0.000125 grad: 0.1040 (0.1035) loss: 0.9042 (0.9028) time: 0.1387 data: 0.0495 max mem: 8452 +Train: [6] [3000/6250] eta: 0:09:16 lr: 0.000125 grad: 0.0947 (0.1033) loss: 0.8992 (0.9027) time: 0.2075 data: 0.1267 max mem: 8452 +Train: [6] [3100/6250] eta: 0:09:03 lr: 0.000125 grad: 0.1015 (0.1033) loss: 0.9053 (0.9025) time: 0.3696 data: 0.2768 max mem: 8452 +Train: [6] [3200/6250] eta: 0:08:44 lr: 0.000125 grad: 0.0900 (0.1033) loss: 0.8988 (0.9025) time: 0.1824 data: 0.0883 max mem: 8452 +Train: [6] [3300/6250] eta: 0:08:27 lr: 0.000125 grad: 0.1053 (0.1032) loss: 0.8986 (0.9024) time: 0.1487 data: 0.0584 max mem: 8452 +Train: [6] [3400/6250] eta: 0:08:10 lr: 0.000125 grad: 0.1017 (0.1032) loss: 0.9010 (0.9023) time: 0.1476 data: 0.0664 max mem: 8452 +Train: [6] [3500/6250] eta: 0:07:51 lr: 0.000125 grad: 0.0967 (0.1031) loss: 0.9001 (0.9023) time: 0.1382 data: 0.0618 max mem: 8452 +Train: [6] [3600/6250] eta: 0:07:33 lr: 0.000125 grad: 0.0982 (0.1030) loss: 0.8999 (0.9022) time: 0.1656 data: 0.0875 max mem: 8452 +Train: [6] [3700/6250] eta: 0:07:15 lr: 0.000125 grad: 0.0994 (0.1030) loss: 0.8942 (0.9021) time: 0.1550 data: 0.0824 max mem: 8452 +Train: [6] [3800/6250] eta: 0:06:58 lr: 0.000125 grad: 0.0964 (0.1028) loss: 0.9030 (0.9021) time: 0.1846 data: 0.0667 max mem: 8452 +Train: [6] [3900/6250] eta: 0:06:44 lr: 0.000125 grad: 0.0963 (0.1026) loss: 0.8953 (0.9020) time: 0.2124 data: 0.0514 max mem: 8452 +Train: [6] [4000/6250] eta: 0:06:26 lr: 0.000125 grad: 0.0989 (0.1025) loss: 0.8960 (0.9019) time: 0.1669 data: 0.0817 max mem: 8452 +Train: [6] [4100/6250] eta: 0:06:09 lr: 0.000125 grad: 0.0859 (0.1024) loss: 0.8993 (0.9018) time: 0.2138 data: 0.1392 max mem: 8452 +Train: [6] [4200/6250] eta: 0:05:52 lr: 0.000125 grad: 0.1010 (0.1023) loss: 0.8999 (0.9017) time: 0.1395 data: 0.0536 max mem: 8452 +Train: [6] [4300/6250] eta: 0:05:35 lr: 0.000125 grad: 0.0948 (0.1022) loss: 0.8988 (0.9017) time: 0.1070 data: 0.0186 max mem: 8452 +Train: [6] [4400/6250] eta: 0:05:18 lr: 0.000125 grad: 0.0915 (0.1022) loss: 0.8996 (0.9016) time: 0.1689 data: 0.0896 max mem: 8452 +Train: [6] [4500/6250] eta: 0:05:01 lr: 0.000125 grad: 0.0899 (0.1020) loss: 0.9004 (0.9016) time: 0.1768 data: 0.0764 max mem: 8452 +Train: [6] [4600/6250] eta: 0:04:43 lr: 0.000125 grad: 0.1038 (0.1019) loss: 0.8929 (0.9015) time: 0.1347 data: 0.0476 max mem: 8452 +Train: [6] [4700/6250] eta: 0:04:26 lr: 0.000125 grad: 0.0976 (0.1018) loss: 0.8992 (0.9014) time: 0.1810 data: 0.0978 max mem: 8452 +Train: [6] [4800/6250] eta: 0:04:09 lr: 0.000125 grad: 0.0932 (0.1017) loss: 0.8945 (0.9013) time: 0.2067 data: 0.1374 max mem: 8452 +Train: [6] [4900/6250] eta: 0:03:51 lr: 0.000125 grad: 0.0864 (0.1016) loss: 0.8965 (0.9013) time: 0.1666 data: 0.0891 max mem: 8452 +Train: [6] [5000/6250] eta: 0:03:35 lr: 0.000125 grad: 0.0960 (0.1015) loss: 0.8941 (0.9012) time: 0.2658 data: 0.1813 max mem: 8452 +Train: [6] [5100/6250] eta: 0:03:17 lr: 0.000125 grad: 0.0906 (0.1015) loss: 0.8970 (0.9011) time: 0.1496 data: 0.0654 max mem: 8452 +Train: [6] [5200/6250] eta: 0:03:00 lr: 0.000125 grad: 0.0865 (0.1013) loss: 0.8970 (0.9010) time: 0.2167 data: 0.0675 max mem: 8452 +Train: [6] [5300/6250] eta: 0:02:43 lr: 0.000125 grad: 0.0966 (0.1012) loss: 0.8954 (0.9010) time: 0.1640 data: 0.0780 max mem: 8452 +Train: [6] [5400/6250] eta: 0:02:26 lr: 0.000125 grad: 0.0986 (0.1012) loss: 0.8985 (0.9009) time: 0.2224 data: 0.1187 max mem: 8452 +Train: [6] [5500/6250] eta: 0:02:08 lr: 0.000125 grad: 0.0919 (0.1011) loss: 0.9012 (0.9009) time: 0.1829 data: 0.1018 max mem: 8452 +Train: [6] [5600/6250] eta: 0:01:51 lr: 0.000125 grad: 0.0908 (0.1010) loss: 0.8958 (0.9009) time: 0.1674 data: 0.0874 max mem: 8452 +Train: [6] [5700/6250] eta: 0:01:34 lr: 0.000125 grad: 0.1060 (0.1009) loss: 0.8974 (0.9008) time: 0.1288 data: 0.0429 max mem: 8452 +Train: [6] [5800/6250] eta: 0:01:17 lr: 0.000125 grad: 0.0915 (0.1008) loss: 0.8966 (0.9008) time: 0.1720 data: 0.0934 max mem: 8452 +Train: [6] [5900/6250] eta: 0:01:00 lr: 0.000125 grad: 0.0932 (0.1008) loss: 0.8953 (0.9007) time: 0.1846 data: 0.1200 max mem: 8452 +Train: [6] [6000/6250] eta: 0:00:42 lr: 0.000125 grad: 0.0856 (0.1006) loss: 0.8997 (0.9007) time: 0.1387 data: 0.0603 max mem: 8452 +Train: [6] [6100/6250] eta: 0:00:25 lr: 0.000125 grad: 0.0856 (0.1005) loss: 0.8979 (0.9007) time: 0.1343 data: 0.0626 max mem: 8452 +Train: [6] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.0889 (0.1003) loss: 0.8982 (0.9006) time: 0.1353 data: 0.0641 max mem: 8452 +Train: [6] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0928 (0.1003) loss: 0.9005 (0.9006) time: 0.1438 data: 0.0531 max mem: 8452 +Train: [6] Total time: 0:18:00 (0.1728 s / it) +Averaged stats: lr: 0.000125 grad: 0.0928 (0.1003) loss: 0.9005 (0.9006) +Eval (hcp-train-subset): [6] [ 0/62] eta: 0:05:26 loss: 0.9128 (0.9128) time: 5.2635 data: 5.2349 max mem: 8452 +Eval (hcp-train-subset): [6] [61/62] eta: 0:00:00 loss: 0.9025 (0.9020) time: 0.1549 data: 0.1336 max mem: 8452 +Eval (hcp-train-subset): [6] Total time: 0:00:14 (0.2307 s / it) +Averaged stats (hcp-train-subset): loss: 0.9025 (0.9020) +Eval (hcp-val): [6] [ 0/62] eta: 0:03:40 loss: 0.8945 (0.8945) time: 3.5621 data: 3.4954 max mem: 8452 +Eval (hcp-val): [6] [61/62] eta: 0:00:00 loss: 0.8961 (0.8970) time: 0.1305 data: 0.1076 max mem: 8452 +Eval (hcp-val): [6] Total time: 0:00:14 (0.2297 s / it) +Averaged stats (hcp-val): loss: 0.8961 (0.8970) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [7] [ 0/6250] eta: 11:07:28 lr: 0.000125 grad: 0.0969 (0.0969) loss: 0.9133 (0.9133) time: 6.4077 data: 6.2896 max mem: 8452 +Train: [7] [ 100/6250] eta: 0:22:15 lr: 0.000125 grad: 0.1000 (0.1042) loss: 0.8972 (0.9058) time: 0.1507 data: 0.0440 max mem: 8452 +Train: [7] [ 200/6250] eta: 0:19:23 lr: 0.000125 grad: 0.0945 (0.1001) loss: 0.8917 (0.9018) time: 0.1621 data: 0.0662 max mem: 8452 +Train: [7] [ 300/6250] eta: 0:17:54 lr: 0.000125 grad: 0.0977 (0.1018) loss: 0.8962 (0.8998) time: 0.1669 data: 0.0665 max mem: 8452 +Train: [7] [ 400/6250] eta: 0:17:13 lr: 0.000125 grad: 0.0984 (0.1011) loss: 0.9020 (0.8991) time: 0.1807 data: 0.0719 max mem: 8452 +Train: [7] [ 500/6250] eta: 0:16:39 lr: 0.000125 grad: 0.0915 (0.1013) loss: 0.8950 (0.8984) time: 0.1749 data: 0.0807 max mem: 8452 +Train: [7] [ 600/6250] eta: 0:16:21 lr: 0.000125 grad: 0.0845 (0.1003) loss: 0.9039 (0.8985) time: 0.2027 data: 0.1236 max mem: 8452 +Train: [7] [ 700/6250] eta: 0:16:05 lr: 0.000125 grad: 0.0957 (0.1000) loss: 0.8932 (0.8982) time: 0.1853 data: 0.1064 max mem: 8452 +Train: [7] [ 800/6250] eta: 0:15:47 lr: 0.000125 grad: 0.0960 (0.1001) loss: 0.8993 (0.8979) time: 0.1719 data: 0.0807 max mem: 8452 +Train: [7] [ 900/6250] eta: 0:15:44 lr: 0.000125 grad: 0.1033 (0.1003) loss: 0.8989 (0.8975) time: 0.2435 data: 0.1591 max mem: 8452 +Train: [7] [1000/6250] eta: 0:15:21 lr: 0.000125 grad: 0.0930 (0.1003) loss: 0.8932 (0.8970) time: 0.0935 data: 0.0079 max mem: 8452 +Train: [7] [1100/6250] eta: 0:14:51 lr: 0.000125 grad: 0.0927 (0.1008) loss: 0.8869 (0.8966) time: 0.1426 data: 0.0434 max mem: 8452 +Train: [7] [1200/6250] eta: 0:14:44 lr: 0.000125 grad: 0.0931 (0.1003) loss: 0.8927 (0.8964) time: 0.1608 data: 0.0742 max mem: 8452 +Train: [7] [1300/6250] eta: 0:14:17 lr: 0.000125 grad: 0.0912 (0.0999) loss: 0.8956 (0.8961) time: 0.1544 data: 0.0791 max mem: 8452 +Train: [7] [1400/6250] eta: 0:13:54 lr: 0.000125 grad: 0.0890 (0.0994) loss: 0.8960 (0.8960) time: 0.1614 data: 0.0799 max mem: 8452 +Train: [7] [1500/6250] eta: 0:13:36 lr: 0.000125 grad: 0.0878 (0.0994) loss: 0.8968 (0.8959) time: 0.1675 data: 0.0890 max mem: 8452 +Train: [7] [1600/6250] eta: 0:13:17 lr: 0.000125 grad: 0.0973 (0.0997) loss: 0.8941 (0.8957) time: 0.1485 data: 0.0695 max mem: 8452 +Train: [7] [1700/6250] eta: 0:13:00 lr: 0.000125 grad: 0.0933 (0.0995) loss: 0.8943 (0.8955) time: 0.1977 data: 0.1218 max mem: 8452 +Train: [7] [1800/6250] eta: 0:12:42 lr: 0.000125 grad: 0.1001 (0.0992) loss: 0.8961 (0.8955) time: 0.1580 data: 0.0740 max mem: 8452 +Train: [7] [1900/6250] eta: 0:12:24 lr: 0.000125 grad: 0.0892 (0.0989) loss: 0.8962 (0.8954) time: 0.1861 data: 0.1125 max mem: 8452 +Train: [7] [2000/6250] eta: 0:12:06 lr: 0.000125 grad: 0.0984 (0.0989) loss: 0.8948 (0.8954) time: 0.1661 data: 0.1014 max mem: 8452 +Train: [7] [2100/6250] eta: 0:11:48 lr: 0.000125 grad: 0.0929 (0.0987) loss: 0.8936 (0.8953) time: 0.1581 data: 0.0845 max mem: 8452 +Train: [7] [2200/6250] eta: 0:11:31 lr: 0.000125 grad: 0.0983 (0.0985) loss: 0.8996 (0.8954) time: 0.1595 data: 0.0839 max mem: 8452 +Train: [7] [2300/6250] eta: 0:11:13 lr: 0.000125 grad: 0.0885 (0.0982) loss: 0.8957 (0.8954) time: 0.1739 data: 0.0932 max mem: 8452 +Train: [7] [2400/6250] eta: 0:10:54 lr: 0.000125 grad: 0.0975 (0.0981) loss: 0.8947 (0.8954) time: 0.1725 data: 0.0950 max mem: 8452 +Train: [7] [2500/6250] eta: 0:10:38 lr: 0.000125 grad: 0.0862 (0.0979) loss: 0.8932 (0.8953) time: 0.1385 data: 0.0547 max mem: 8452 +Train: [7] [2600/6250] eta: 0:10:21 lr: 0.000125 grad: 0.0902 (0.0978) loss: 0.8970 (0.8953) time: 0.1868 data: 0.1119 max mem: 8452 +Train: [7] [2700/6250] eta: 0:10:03 lr: 0.000125 grad: 0.0965 (0.0976) loss: 0.8913 (0.8952) time: 0.1517 data: 0.0749 max mem: 8452 +Train: [7] [2800/6250] eta: 0:09:44 lr: 0.000125 grad: 0.0903 (0.0974) loss: 0.8888 (0.8952) time: 0.1295 data: 0.0500 max mem: 8452 +Train: [7] [2900/6250] eta: 0:09:27 lr: 0.000125 grad: 0.0901 (0.0972) loss: 0.8899 (0.8951) time: 0.1722 data: 0.1001 max mem: 8452 +Train: [7] [3000/6250] eta: 0:09:09 lr: 0.000125 grad: 0.0813 (0.0970) loss: 0.8976 (0.8952) time: 0.1621 data: 0.0885 max mem: 8452 +Train: [7] [3100/6250] eta: 0:08:53 lr: 0.000125 grad: 0.0824 (0.0967) loss: 0.8943 (0.8952) time: 0.1468 data: 0.0635 max mem: 8452 +Train: [7] [3200/6250] eta: 0:08:35 lr: 0.000125 grad: 0.0929 (0.0965) loss: 0.8948 (0.8952) time: 0.1827 data: 0.1068 max mem: 8452 +Train: [7] [3300/6250] eta: 0:08:19 lr: 0.000125 grad: 0.0809 (0.0963) loss: 0.8944 (0.8952) time: 0.1577 data: 0.0798 max mem: 8452 +Train: [7] [3400/6250] eta: 0:08:05 lr: 0.000125 grad: 0.0785 (0.0961) loss: 0.8959 (0.8952) time: 0.3101 data: 0.2269 max mem: 8452 +Train: [7] [3500/6250] eta: 0:07:46 lr: 0.000125 grad: 0.0930 (0.0960) loss: 0.8958 (0.8952) time: 0.1774 data: 0.1013 max mem: 8452 +Train: [7] [3600/6250] eta: 0:07:30 lr: 0.000125 grad: 0.0859 (0.0958) loss: 0.8926 (0.8951) time: 0.2039 data: 0.1249 max mem: 8452 +Train: [7] [3700/6250] eta: 0:07:13 lr: 0.000125 grad: 0.0878 (0.0956) loss: 0.8936 (0.8951) time: 0.1547 data: 0.0748 max mem: 8452 +Train: [7] [3800/6250] eta: 0:06:56 lr: 0.000125 grad: 0.0855 (0.0955) loss: 0.8944 (0.8950) time: 0.1735 data: 0.0698 max mem: 8452 +Train: [7] [3900/6250] eta: 0:06:40 lr: 0.000125 grad: 0.0890 (0.0954) loss: 0.8985 (0.8951) time: 0.2090 data: 0.1351 max mem: 8452 +Train: [7] [4000/6250] eta: 0:06:23 lr: 0.000125 grad: 0.0849 (0.0953) loss: 0.8954 (0.8951) time: 0.1846 data: 0.1052 max mem: 8452 +Train: [7] [4100/6250] eta: 0:06:06 lr: 0.000125 grad: 0.0882 (0.0953) loss: 0.8932 (0.8950) time: 0.1844 data: 0.0923 max mem: 8452 +Train: [7] [4200/6250] eta: 0:05:50 lr: 0.000125 grad: 0.0865 (0.0951) loss: 0.8922 (0.8950) time: 0.1786 data: 0.0902 max mem: 8452 +Train: [7] [4300/6250] eta: 0:05:32 lr: 0.000125 grad: 0.0796 (0.0949) loss: 0.8968 (0.8951) time: 0.1581 data: 0.0800 max mem: 8452 +Train: [7] [4400/6250] eta: 0:05:16 lr: 0.000125 grad: 0.0849 (0.0948) loss: 0.8902 (0.8951) time: 0.3370 data: 0.2440 max mem: 8452 +Train: [7] [4500/6250] eta: 0:04:58 lr: 0.000125 grad: 0.0850 (0.0946) loss: 0.8965 (0.8951) time: 0.1624 data: 0.0817 max mem: 8452 +Train: [7] [4600/6250] eta: 0:04:41 lr: 0.000125 grad: 0.0832 (0.0945) loss: 0.8953 (0.8951) time: 0.1574 data: 0.0658 max mem: 8452 +Train: [7] [4700/6250] eta: 0:04:23 lr: 0.000125 grad: 0.0881 (0.0944) loss: 0.8947 (0.8950) time: 0.1428 data: 0.0536 max mem: 8452 +Train: [7] [4800/6250] eta: 0:04:07 lr: 0.000125 grad: 0.0807 (0.0943) loss: 0.8939 (0.8950) time: 0.2047 data: 0.1266 max mem: 8452 +Train: [7] [4900/6250] eta: 0:03:49 lr: 0.000125 grad: 0.0966 (0.0942) loss: 0.8911 (0.8950) time: 0.1330 data: 0.0486 max mem: 8452 +Train: [7] [5000/6250] eta: 0:03:32 lr: 0.000125 grad: 0.0828 (0.0941) loss: 0.8937 (0.8949) time: 0.1811 data: 0.1024 max mem: 8452 +Train: [7] [5100/6250] eta: 0:03:14 lr: 0.000125 grad: 0.0804 (0.0940) loss: 0.8920 (0.8949) time: 0.1582 data: 0.0833 max mem: 8452 +Train: [7] [5200/6250] eta: 0:02:57 lr: 0.000125 grad: 0.0880 (0.0939) loss: 0.8929 (0.8948) time: 0.1568 data: 0.0837 max mem: 8452 +Train: [7] [5300/6250] eta: 0:02:40 lr: 0.000125 grad: 0.0874 (0.0938) loss: 0.8928 (0.8948) time: 0.1489 data: 0.0722 max mem: 8452 +Train: [7] [5400/6250] eta: 0:02:23 lr: 0.000125 grad: 0.0880 (0.0937) loss: 0.8956 (0.8948) time: 0.1530 data: 0.0877 max mem: 8452 +Train: [7] [5500/6250] eta: 0:02:06 lr: 0.000125 grad: 0.0922 (0.0936) loss: 0.8934 (0.8948) time: 0.1797 data: 0.1113 max mem: 8452 +Train: [7] [5600/6250] eta: 0:01:49 lr: 0.000125 grad: 0.0847 (0.0936) loss: 0.8953 (0.8948) time: 0.1930 data: 0.1036 max mem: 8452 +Train: [7] [5700/6250] eta: 0:01:33 lr: 0.000125 grad: 0.0810 (0.0935) loss: 0.8947 (0.8948) time: 0.2301 data: 0.1676 max mem: 8452 +Train: [7] [5800/6250] eta: 0:01:16 lr: 0.000125 grad: 0.0981 (0.0935) loss: 0.8923 (0.8947) time: 0.1520 data: 0.0822 max mem: 8452 +Train: [7] [5900/6250] eta: 0:00:59 lr: 0.000125 grad: 0.0845 (0.0934) loss: 0.8958 (0.8947) time: 0.1511 data: 0.0679 max mem: 8452 +Train: [7] [6000/6250] eta: 0:00:42 lr: 0.000125 grad: 0.0808 (0.0933) loss: 0.8926 (0.8946) time: 0.1649 data: 0.0915 max mem: 8452 +Train: [7] [6100/6250] eta: 0:00:25 lr: 0.000125 grad: 0.0873 (0.0932) loss: 0.8908 (0.8946) time: 0.2092 data: 0.1233 max mem: 8452 +Train: [7] [6200/6250] eta: 0:00:08 lr: 0.000125 grad: 0.0944 (0.0932) loss: 0.8950 (0.8946) time: 0.2099 data: 0.1292 max mem: 8452 +Train: [7] [6249/6250] eta: 0:00:00 lr: 0.000125 grad: 0.0858 (0.0932) loss: 0.8935 (0.8946) time: 0.2016 data: 0.1267 max mem: 8452 +Train: [7] Total time: 0:17:49 (0.1711 s / it) +Averaged stats: lr: 0.000125 grad: 0.0858 (0.0932) loss: 0.8935 (0.8946) +Eval (hcp-train-subset): [7] [ 0/62] eta: 0:04:42 loss: 0.9088 (0.9088) time: 4.5611 data: 4.4840 max mem: 8452 +Eval (hcp-train-subset): [7] [61/62] eta: 0:00:00 loss: 0.9006 (0.8992) time: 0.1229 data: 0.1018 max mem: 8452 +Eval (hcp-train-subset): [7] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-train-subset): loss: 0.9006 (0.8992) +Eval (hcp-val): [7] [ 0/62] eta: 0:05:57 loss: 0.8924 (0.8924) time: 5.7611 data: 5.7321 max mem: 8452 +Eval (hcp-val): [7] [61/62] eta: 0:00:00 loss: 0.8934 (0.8941) time: 0.1203 data: 0.0981 max mem: 8452 +Eval (hcp-val): [7] Total time: 0:00:15 (0.2538 s / it) +Averaged stats (hcp-val): loss: 0.8934 (0.8941) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [8] [ 0/6250] eta: 9:46:58 lr: 0.000125 grad: 0.0668 (0.0668) loss: 0.9110 (0.9110) time: 5.6350 data: 5.3171 max mem: 8452 +Train: [8] [ 100/6250] eta: 0:23:46 lr: 0.000125 grad: 0.0981 (0.0913) loss: 0.8988 (0.8994) time: 0.1657 data: 0.0730 max mem: 8452 +Train: [8] [ 200/6250] eta: 0:20:46 lr: 0.000125 grad: 0.0874 (0.0940) loss: 0.8930 (0.8959) time: 0.1936 data: 0.0931 max mem: 8452 +Train: [8] [ 300/6250] eta: 0:18:59 lr: 0.000125 grad: 0.0866 (0.0931) loss: 0.8897 (0.8949) time: 0.1488 data: 0.0377 max mem: 8452 +Train: [8] [ 400/6250] eta: 0:18:12 lr: 0.000125 grad: 0.0822 (0.0919) loss: 0.8960 (0.8945) time: 0.1986 data: 0.1089 max mem: 8452 +Train: [8] [ 500/6250] eta: 0:17:36 lr: 0.000125 grad: 0.0851 (0.0905) loss: 0.8939 (0.8944) time: 0.1969 data: 0.1014 max mem: 8452 +Train: [8] [ 600/6250] eta: 0:17:03 lr: 0.000125 grad: 0.0888 (0.0900) loss: 0.8917 (0.8940) time: 0.1837 data: 0.1051 max mem: 8452 +Train: [8] [ 700/6250] eta: 0:16:47 lr: 0.000125 grad: 0.0891 (0.0904) loss: 0.8879 (0.8932) time: 0.1132 data: 0.0185 max mem: 8452 +Train: [8] [ 800/6250] eta: 0:16:24 lr: 0.000125 grad: 0.0874 (0.0906) loss: 0.8841 (0.8926) time: 0.1980 data: 0.1121 max mem: 8452 +Train: [8] [ 900/6250] eta: 0:16:15 lr: 0.000125 grad: 0.0802 (0.0907) loss: 0.8921 (0.8923) time: 0.2507 data: 0.1586 max mem: 8452 +Train: [8] [1000/6250] eta: 0:15:53 lr: 0.000125 grad: 0.0862 (0.0902) loss: 0.8892 (0.8921) time: 0.1706 data: 0.0743 max mem: 8452 +Train: [8] [1100/6250] eta: 0:15:35 lr: 0.000125 grad: 0.0780 (0.0901) loss: 0.8931 (0.8919) time: 0.2285 data: 0.1486 max mem: 8452 +Train: [8] [1200/6250] eta: 0:15:05 lr: 0.000125 grad: 0.0830 (0.0904) loss: 0.8872 (0.8918) time: 0.1527 data: 0.0673 max mem: 8452 +Train: [8] [1300/6250] eta: 0:14:41 lr: 0.000125 grad: 0.0824 (0.0901) loss: 0.8884 (0.8917) time: 0.1687 data: 0.0821 max mem: 8452 +Train: [8] [1400/6250] eta: 0:14:20 lr: 0.000125 grad: 0.0828 (0.0899) loss: 0.8916 (0.8916) time: 0.1813 data: 0.0903 max mem: 8452 +Train: [8] [1500/6250] eta: 0:14:03 lr: 0.000125 grad: 0.0795 (0.0900) loss: 0.8939 (0.8915) time: 0.2103 data: 0.1308 max mem: 8452 +Train: [8] [1600/6250] eta: 0:13:40 lr: 0.000125 grad: 0.0875 (0.0899) loss: 0.8900 (0.8914) time: 0.1741 data: 0.1086 max mem: 8452 +Train: [8] [1700/6250] eta: 0:13:18 lr: 0.000125 grad: 0.0878 (0.0900) loss: 0.8908 (0.8913) time: 0.1527 data: 0.0679 max mem: 8452 +Train: [8] [1800/6250] eta: 0:12:56 lr: 0.000125 grad: 0.0869 (0.0900) loss: 0.8849 (0.8910) time: 0.1335 data: 0.0581 max mem: 8452 +Train: [8] [1900/6250] eta: 0:12:42 lr: 0.000125 grad: 0.0783 (0.0899) loss: 0.8878 (0.8910) time: 0.1426 data: 0.0464 max mem: 8452 +Train: [8] [2000/6250] eta: 0:12:24 lr: 0.000125 grad: 0.0801 (0.0896) loss: 0.8898 (0.8908) time: 0.1660 data: 0.0978 max mem: 8452 +Train: [8] [2100/6250] eta: 0:12:07 lr: 0.000125 grad: 0.0873 (0.0895) loss: 0.8846 (0.8908) time: 0.1991 data: 0.1310 max mem: 8452 +Train: [8] [2200/6250] eta: 0:11:48 lr: 0.000125 grad: 0.0871 (0.0893) loss: 0.8886 (0.8907) time: 0.1713 data: 0.0956 max mem: 8452 +Train: [8] [2300/6250] eta: 0:11:31 lr: 0.000125 grad: 0.0884 (0.0895) loss: 0.8878 (0.8906) time: 0.1638 data: 0.0954 max mem: 8452 +Train: [8] [2400/6250] eta: 0:11:15 lr: 0.000125 grad: 0.0845 (0.0894) loss: 0.8850 (0.8905) time: 0.1600 data: 0.0859 max mem: 8452 +Train: [8] [2500/6250] eta: 0:10:59 lr: 0.000125 grad: 0.0777 (0.0892) loss: 0.8932 (0.8905) time: 0.2322 data: 0.1522 max mem: 8452 +Train: [8] [2600/6250] eta: 0:10:41 lr: 0.000125 grad: 0.0841 (0.0890) loss: 0.8936 (0.8905) time: 0.1701 data: 0.0964 max mem: 8452 +Train: [8] [2700/6250] eta: 0:10:25 lr: 0.000125 grad: 0.0791 (0.0888) loss: 0.8951 (0.8905) time: 0.1685 data: 0.0714 max mem: 8452 +Train: [8] [2800/6250] eta: 0:10:09 lr: 0.000125 grad: 0.0822 (0.0888) loss: 0.8917 (0.8905) time: 0.2275 data: 0.1550 max mem: 8452 +Train: [8] [2900/6250] eta: 0:09:51 lr: 0.000125 grad: 0.0863 (0.0887) loss: 0.8871 (0.8905) time: 0.1972 data: 0.1170 max mem: 8452 +Train: [8] [3000/6250] eta: 0:09:33 lr: 0.000125 grad: 0.0832 (0.0887) loss: 0.8898 (0.8904) time: 0.1798 data: 0.1020 max mem: 8452 +Train: [8] [3100/6250] eta: 0:09:18 lr: 0.000125 grad: 0.0832 (0.0886) loss: 0.8911 (0.8904) time: 0.1036 data: 0.0194 max mem: 8452 +Train: [8] [3200/6250] eta: 0:08:59 lr: 0.000125 grad: 0.0868 (0.0886) loss: 0.8851 (0.8904) time: 0.1521 data: 0.0782 max mem: 8452 +Train: [8] [3300/6250] eta: 0:08:43 lr: 0.000125 grad: 0.0782 (0.0884) loss: 0.8902 (0.8904) time: 0.1133 data: 0.0370 max mem: 8452 +Train: [8] [3400/6250] eta: 0:08:24 lr: 0.000125 grad: 0.0793 (0.0883) loss: 0.8868 (0.8904) time: 0.1700 data: 0.0976 max mem: 8452 +Train: [8] [3500/6250] eta: 0:08:06 lr: 0.000125 grad: 0.0848 (0.0882) loss: 0.8873 (0.8903) time: 0.1587 data: 0.0787 max mem: 8452 +Train: [8] [3600/6250] eta: 0:07:48 lr: 0.000125 grad: 0.0870 (0.0882) loss: 0.8890 (0.8904) time: 0.1346 data: 0.0611 max mem: 8452 +Train: [8] [3700/6250] eta: 0:07:31 lr: 0.000125 grad: 0.0784 (0.0881) loss: 0.8906 (0.8904) time: 0.1871 data: 0.0943 max mem: 8452 +Train: [8] [3800/6250] eta: 0:07:13 lr: 0.000125 grad: 0.0774 (0.0880) loss: 0.8909 (0.8904) time: 0.1539 data: 0.0397 max mem: 8452 +Train: [8] [3900/6250] eta: 0:06:56 lr: 0.000125 grad: 0.0806 (0.0880) loss: 0.8854 (0.8904) time: 0.1894 data: 0.0889 max mem: 8452 +Train: [8] [4000/6250] eta: 0:06:38 lr: 0.000125 grad: 0.0929 (0.0881) loss: 0.8862 (0.8903) time: 0.1860 data: 0.1066 max mem: 8452 +Train: [8] [4100/6250] eta: 0:06:21 lr: 0.000125 grad: 0.0910 (0.0881) loss: 0.8899 (0.8903) time: 0.2261 data: 0.1505 max mem: 8452 +Train: [8] [4200/6250] eta: 0:06:03 lr: 0.000125 grad: 0.0804 (0.0881) loss: 0.8874 (0.8902) time: 0.1859 data: 0.1120 max mem: 8452 +Train: [8] [4300/6250] eta: 0:05:44 lr: 0.000125 grad: 0.0837 (0.0881) loss: 0.8919 (0.8902) time: 0.1891 data: 0.1077 max mem: 8452 +Train: [8] [4400/6250] eta: 0:05:26 lr: 0.000125 grad: 0.0805 (0.0881) loss: 0.8882 (0.8901) time: 0.1554 data: 0.0735 max mem: 8452 +Train: [8] [4500/6250] eta: 0:05:08 lr: 0.000125 grad: 0.0801 (0.0880) loss: 0.8899 (0.8901) time: 0.1209 data: 0.0229 max mem: 8452 +Train: [8] [4600/6250] eta: 0:04:50 lr: 0.000125 grad: 0.0868 (0.0880) loss: 0.8895 (0.8901) time: 0.1602 data: 0.0891 max mem: 8452 +Train: [8] [4700/6250] eta: 0:04:33 lr: 0.000125 grad: 0.0818 (0.0879) loss: 0.8857 (0.8900) time: 0.2020 data: 0.1198 max mem: 8452 +Train: [8] [4800/6250] eta: 0:04:16 lr: 0.000125 grad: 0.0860 (0.0879) loss: 0.8878 (0.8900) time: 0.2785 data: 0.2000 max mem: 8452 +Train: [8] [4900/6250] eta: 0:03:57 lr: 0.000125 grad: 0.0790 (0.0878) loss: 0.8896 (0.8900) time: 0.1758 data: 0.0881 max mem: 8452 +Train: [8] [5000/6250] eta: 0:03:39 lr: 0.000125 grad: 0.0919 (0.0879) loss: 0.8852 (0.8899) time: 0.1611 data: 0.0717 max mem: 8452 +Train: [8] [5100/6250] eta: 0:03:21 lr: 0.000125 grad: 0.0788 (0.0879) loss: 0.8895 (0.8899) time: 0.1807 data: 0.0960 max mem: 8452 +Train: [8] [5200/6250] eta: 0:03:04 lr: 0.000124 grad: 0.0854 (0.0878) loss: 0.8868 (0.8898) time: 0.1218 data: 0.0259 max mem: 8452 +Train: [8] [5300/6250] eta: 0:02:46 lr: 0.000124 grad: 0.0824 (0.0878) loss: 0.8863 (0.8897) time: 0.1716 data: 0.0914 max mem: 8452 +Train: [8] [5400/6250] eta: 0:02:28 lr: 0.000124 grad: 0.0826 (0.0877) loss: 0.8911 (0.8897) time: 0.1574 data: 0.0682 max mem: 8452 +Train: [8] [5500/6250] eta: 0:02:11 lr: 0.000124 grad: 0.0827 (0.0877) loss: 0.8916 (0.8897) time: 0.2027 data: 0.1089 max mem: 8452 +Train: [8] [5600/6250] eta: 0:01:53 lr: 0.000124 grad: 0.0813 (0.0876) loss: 0.8910 (0.8897) time: 0.1602 data: 0.0882 max mem: 8452 +Train: [8] [5700/6250] eta: 0:01:36 lr: 0.000124 grad: 0.0817 (0.0876) loss: 0.8889 (0.8897) time: 0.1628 data: 0.0883 max mem: 8452 +Train: [8] [5800/6250] eta: 0:01:18 lr: 0.000124 grad: 0.0797 (0.0875) loss: 0.8867 (0.8897) time: 0.1586 data: 0.0823 max mem: 8452 +Train: [8] [5900/6250] eta: 0:01:01 lr: 0.000124 grad: 0.0785 (0.0874) loss: 0.8912 (0.8896) time: 0.1752 data: 0.0862 max mem: 8452 +Train: [8] [6000/6250] eta: 0:00:43 lr: 0.000124 grad: 0.0775 (0.0873) loss: 0.8912 (0.8897) time: 0.1722 data: 0.0982 max mem: 8452 +Train: [8] [6100/6250] eta: 0:00:26 lr: 0.000124 grad: 0.0793 (0.0873) loss: 0.8912 (0.8897) time: 0.1446 data: 0.0553 max mem: 8452 +Train: [8] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0738 (0.0871) loss: 0.8930 (0.8897) time: 0.1525 data: 0.0738 max mem: 8452 +Train: [8] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0815 (0.0871) loss: 0.8904 (0.8897) time: 0.1952 data: 0.1332 max mem: 8452 +Train: [8] Total time: 0:18:22 (0.1764 s / it) +Averaged stats: lr: 0.000124 grad: 0.0815 (0.0871) loss: 0.8904 (0.8897) +Eval (hcp-train-subset): [8] [ 0/62] eta: 0:06:06 loss: 0.9079 (0.9079) time: 5.9192 data: 5.8917 max mem: 8452 +Eval (hcp-train-subset): [8] [61/62] eta: 0:00:00 loss: 0.8970 (0.8955) time: 0.1391 data: 0.1181 max mem: 8452 +Eval (hcp-train-subset): [8] Total time: 0:00:14 (0.2293 s / it) +Averaged stats (hcp-train-subset): loss: 0.8970 (0.8955) +Eval (hcp-val): [8] [ 0/62] eta: 0:05:00 loss: 0.8889 (0.8889) time: 4.8506 data: 4.8182 max mem: 8452 +Eval (hcp-val): [8] [61/62] eta: 0:00:00 loss: 0.8915 (0.8918) time: 0.1211 data: 0.0997 max mem: 8452 +Eval (hcp-val): [8] Total time: 0:00:13 (0.2175 s / it) +Averaged stats (hcp-val): loss: 0.8915 (0.8918) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [9] [ 0/6250] eta: 10:26:44 lr: 0.000124 grad: 0.0776 (0.0776) loss: 0.9205 (0.9205) time: 6.0167 data: 5.8528 max mem: 8452 +Train: [9] [ 100/6250] eta: 0:23:30 lr: 0.000124 grad: 0.1111 (0.1084) loss: 0.8897 (0.8969) time: 0.1801 data: 0.0791 max mem: 8452 +Train: [9] [ 200/6250] eta: 0:19:57 lr: 0.000124 grad: 0.0770 (0.0992) loss: 0.8972 (0.8937) time: 0.1558 data: 0.0674 max mem: 8452 +Train: [9] [ 300/6250] eta: 0:18:19 lr: 0.000124 grad: 0.0787 (0.0930) loss: 0.8914 (0.8928) time: 0.1425 data: 0.0513 max mem: 8452 +Train: [9] [ 400/6250] eta: 0:17:26 lr: 0.000124 grad: 0.0755 (0.0902) loss: 0.8891 (0.8923) time: 0.1669 data: 0.0792 max mem: 8452 +Train: [9] [ 500/6250] eta: 0:16:36 lr: 0.000124 grad: 0.0787 (0.0889) loss: 0.8912 (0.8922) time: 0.1599 data: 0.0723 max mem: 8452 +Train: [9] [ 600/6250] eta: 0:16:23 lr: 0.000124 grad: 0.0876 (0.0878) loss: 0.8916 (0.8917) time: 0.1982 data: 0.1212 max mem: 8452 +Train: [9] [ 700/6250] eta: 0:16:08 lr: 0.000124 grad: 0.0873 (0.0876) loss: 0.8871 (0.8913) time: 0.1850 data: 0.1061 max mem: 8452 +Train: [9] [ 800/6250] eta: 0:16:11 lr: 0.000124 grad: 0.0790 (0.0869) loss: 0.8871 (0.8909) time: 0.2066 data: 0.1348 max mem: 8452 +Train: [9] [ 900/6250] eta: 0:16:02 lr: 0.000124 grad: 0.0780 (0.0862) loss: 0.8929 (0.8907) time: 0.1876 data: 0.1009 max mem: 8452 +Train: [9] [1000/6250] eta: 0:15:39 lr: 0.000124 grad: 0.0793 (0.0855) loss: 0.8903 (0.8907) time: 0.1617 data: 0.0715 max mem: 8452 +Train: [9] [1100/6250] eta: 0:15:41 lr: 0.000124 grad: 0.0751 (0.0850) loss: 0.8906 (0.8907) time: 0.3125 data: 0.2214 max mem: 8452 +Train: [9] [1200/6250] eta: 0:15:11 lr: 0.000124 grad: 0.0770 (0.0846) loss: 0.8892 (0.8907) time: 0.1557 data: 0.0725 max mem: 8452 +Train: [9] [1300/6250] eta: 0:14:49 lr: 0.000124 grad: 0.0827 (0.0854) loss: 0.8916 (0.8904) time: 0.1980 data: 0.1095 max mem: 8452 +Train: [9] [1400/6250] eta: 0:14:25 lr: 0.000124 grad: 0.0835 (0.0857) loss: 0.8889 (0.8901) time: 0.1528 data: 0.0652 max mem: 8452 +Train: [9] [1500/6250] eta: 0:14:02 lr: 0.000124 grad: 0.0766 (0.0858) loss: 0.8882 (0.8899) time: 0.1682 data: 0.0596 max mem: 8452 +Train: [9] [1600/6250] eta: 0:13:44 lr: 0.000124 grad: 0.0810 (0.0858) loss: 0.8888 (0.8896) time: 0.2413 data: 0.1581 max mem: 8452 +Train: [9] [1700/6250] eta: 0:13:21 lr: 0.000124 grad: 0.0769 (0.0855) loss: 0.8866 (0.8894) time: 0.1757 data: 0.0943 max mem: 8452 +Train: [9] [1800/6250] eta: 0:13:02 lr: 0.000124 grad: 0.0825 (0.0855) loss: 0.8862 (0.8892) time: 0.1669 data: 0.0834 max mem: 8452 +Train: [9] [1900/6250] eta: 0:12:43 lr: 0.000124 grad: 0.0758 (0.0853) loss: 0.8843 (0.8890) time: 0.1737 data: 0.0860 max mem: 8452 +Train: [9] [2000/6250] eta: 0:12:26 lr: 0.000124 grad: 0.0787 (0.0852) loss: 0.8818 (0.8887) time: 0.1912 data: 0.1120 max mem: 8452 +Train: [9] [2100/6250] eta: 0:12:06 lr: 0.000124 grad: 0.0869 (0.0850) loss: 0.8823 (0.8885) time: 0.1467 data: 0.0596 max mem: 8452 +Train: [9] [2200/6250] eta: 0:11:46 lr: 0.000124 grad: 0.0752 (0.0848) loss: 0.8840 (0.8883) time: 0.1836 data: 0.1047 max mem: 8452 +Train: [9] [2300/6250] eta: 0:11:25 lr: 0.000124 grad: 0.0758 (0.0849) loss: 0.8908 (0.8882) time: 0.1360 data: 0.0528 max mem: 8452 +Train: [9] [2400/6250] eta: 0:11:06 lr: 0.000124 grad: 0.0781 (0.0845) loss: 0.8848 (0.8881) time: 0.1691 data: 0.0983 max mem: 8452 +Train: [9] [2500/6250] eta: 0:10:49 lr: 0.000124 grad: 0.0763 (0.0843) loss: 0.8816 (0.8879) time: 0.1980 data: 0.1045 max mem: 8452 +Train: [9] [2600/6250] eta: 0:10:31 lr: 0.000124 grad: 0.0759 (0.0841) loss: 0.8798 (0.8878) time: 0.1528 data: 0.0830 max mem: 8452 +Train: [9] [2700/6250] eta: 0:10:15 lr: 0.000124 grad: 0.0792 (0.0840) loss: 0.8793 (0.8877) time: 0.1216 data: 0.0291 max mem: 8452 +Train: [9] [2800/6250] eta: 0:09:56 lr: 0.000124 grad: 0.0802 (0.0839) loss: 0.8863 (0.8876) time: 0.1448 data: 0.0642 max mem: 8452 +Train: [9] [2900/6250] eta: 0:09:38 lr: 0.000124 grad: 0.0788 (0.0837) loss: 0.8872 (0.8876) time: 0.1969 data: 0.1286 max mem: 8452 +Train: [9] [3000/6250] eta: 0:09:19 lr: 0.000124 grad: 0.0780 (0.0837) loss: 0.8874 (0.8876) time: 0.1723 data: 0.0977 max mem: 8452 +Train: [9] [3100/6250] eta: 0:09:01 lr: 0.000124 grad: 0.0789 (0.0836) loss: 0.8869 (0.8876) time: 0.1482 data: 0.0690 max mem: 8452 +Train: [9] [3200/6250] eta: 0:08:45 lr: 0.000124 grad: 0.0769 (0.0835) loss: 0.8883 (0.8876) time: 0.1695 data: 0.0703 max mem: 8452 +Train: [9] [3300/6250] eta: 0:08:28 lr: 0.000124 grad: 0.0805 (0.0837) loss: 0.8805 (0.8875) time: 0.2108 data: 0.1339 max mem: 8452 +Train: [9] [3400/6250] eta: 0:08:13 lr: 0.000124 grad: 0.0808 (0.0837) loss: 0.8849 (0.8874) time: 0.2123 data: 0.1110 max mem: 8452 +Train: [9] [3500/6250] eta: 0:07:53 lr: 0.000124 grad: 0.0824 (0.0837) loss: 0.8846 (0.8874) time: 0.1494 data: 0.0641 max mem: 8452 +Train: [9] [3600/6250] eta: 0:07:35 lr: 0.000124 grad: 0.0845 (0.0838) loss: 0.8891 (0.8873) time: 0.1886 data: 0.1076 max mem: 8452 +Train: [9] [3700/6250] eta: 0:07:17 lr: 0.000124 grad: 0.0859 (0.0839) loss: 0.8833 (0.8872) time: 0.1612 data: 0.0837 max mem: 8452 +Train: [9] [3800/6250] eta: 0:06:59 lr: 0.000124 grad: 0.0777 (0.0839) loss: 0.8841 (0.8871) time: 0.1671 data: 0.0864 max mem: 8452 +Train: [9] [3900/6250] eta: 0:06:42 lr: 0.000124 grad: 0.0763 (0.0839) loss: 0.8858 (0.8870) time: 0.1915 data: 0.1018 max mem: 8452 +Train: [9] [4000/6250] eta: 0:06:24 lr: 0.000124 grad: 0.0838 (0.0841) loss: 0.8836 (0.8869) time: 0.1420 data: 0.0525 max mem: 8452 +Train: [9] [4100/6250] eta: 0:06:06 lr: 0.000124 grad: 0.0820 (0.0842) loss: 0.8837 (0.8868) time: 0.1514 data: 0.0786 max mem: 8452 +Train: [9] [4200/6250] eta: 0:05:49 lr: 0.000124 grad: 0.0833 (0.0844) loss: 0.8840 (0.8867) time: 0.1818 data: 0.1063 max mem: 8452 +Train: [9] [4300/6250] eta: 0:05:32 lr: 0.000124 grad: 0.0799 (0.0845) loss: 0.8810 (0.8866) time: 0.1451 data: 0.0703 max mem: 8452 +Train: [9] [4400/6250] eta: 0:05:15 lr: 0.000124 grad: 0.0857 (0.0846) loss: 0.8832 (0.8864) time: 0.1767 data: 0.0955 max mem: 8452 +Train: [9] [4500/6250] eta: 0:04:57 lr: 0.000124 grad: 0.1003 (0.0847) loss: 0.8772 (0.8863) time: 0.1589 data: 0.0815 max mem: 8452 +Train: [9] [4600/6250] eta: 0:04:40 lr: 0.000124 grad: 0.0813 (0.0849) loss: 0.8824 (0.8862) time: 0.1353 data: 0.0494 max mem: 8452 +Train: [9] [4700/6250] eta: 0:04:24 lr: 0.000124 grad: 0.0862 (0.0850) loss: 0.8776 (0.8861) time: 0.1874 data: 0.0909 max mem: 8452 +Train: [9] [4800/6250] eta: 0:04:07 lr: 0.000124 grad: 0.0850 (0.0851) loss: 0.8765 (0.8860) time: 0.1899 data: 0.1004 max mem: 8452 +Train: [9] [4900/6250] eta: 0:03:50 lr: 0.000124 grad: 0.0894 (0.0854) loss: 0.8806 (0.8859) time: 0.1959 data: 0.1145 max mem: 8452 +Train: [9] [5000/6250] eta: 0:03:33 lr: 0.000124 grad: 0.0803 (0.0855) loss: 0.8842 (0.8858) time: 0.1743 data: 0.0778 max mem: 8452 +Train: [9] [5100/6250] eta: 0:03:16 lr: 0.000124 grad: 0.0846 (0.0856) loss: 0.8819 (0.8857) time: 0.1541 data: 0.0671 max mem: 8452 +Train: [9] [5200/6250] eta: 0:02:59 lr: 0.000124 grad: 0.0904 (0.0858) loss: 0.8775 (0.8856) time: 0.1418 data: 0.0639 max mem: 8452 +Train: [9] [5300/6250] eta: 0:02:42 lr: 0.000124 grad: 0.0885 (0.0859) loss: 0.8792 (0.8855) time: 0.1270 data: 0.0201 max mem: 8452 +Train: [9] [5400/6250] eta: 0:02:25 lr: 0.000124 grad: 0.0820 (0.0859) loss: 0.8793 (0.8855) time: 0.1582 data: 0.0698 max mem: 8452 +Train: [9] [5500/6250] eta: 0:02:08 lr: 0.000124 grad: 0.0874 (0.0859) loss: 0.8775 (0.8854) time: 0.1723 data: 0.0944 max mem: 8452 +Train: [9] [5600/6250] eta: 0:01:51 lr: 0.000124 grad: 0.0786 (0.0860) loss: 0.8844 (0.8853) time: 0.1937 data: 0.1163 max mem: 8452 +Train: [9] [5700/6250] eta: 0:01:34 lr: 0.000124 grad: 0.0786 (0.0860) loss: 0.8836 (0.8853) time: 0.1871 data: 0.1159 max mem: 8452 +Train: [9] [5800/6250] eta: 0:01:16 lr: 0.000124 grad: 0.0855 (0.0861) loss: 0.8857 (0.8852) time: 0.1901 data: 0.1070 max mem: 8452 +Train: [9] [5900/6250] eta: 0:00:59 lr: 0.000124 grad: 0.0888 (0.0861) loss: 0.8829 (0.8852) time: 0.1285 data: 0.0455 max mem: 8452 +Train: [9] [6000/6250] eta: 0:00:42 lr: 0.000124 grad: 0.0800 (0.0861) loss: 0.8810 (0.8851) time: 0.1469 data: 0.0697 max mem: 8452 +Train: [9] [6100/6250] eta: 0:00:25 lr: 0.000124 grad: 0.0825 (0.0861) loss: 0.8838 (0.8851) time: 0.1426 data: 0.0590 max mem: 8452 +Train: [9] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0843 (0.0862) loss: 0.8855 (0.8850) time: 0.1631 data: 0.0720 max mem: 8452 +Train: [9] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0789 (0.0861) loss: 0.8799 (0.8850) time: 0.1699 data: 0.0832 max mem: 8452 +Train: [9] Total time: 0:17:57 (0.1725 s / it) +Averaged stats: lr: 0.000124 grad: 0.0789 (0.0861) loss: 0.8799 (0.8850) +Eval (hcp-train-subset): [9] [ 0/62] eta: 0:06:23 loss: 0.9037 (0.9037) time: 6.1815 data: 6.1529 max mem: 8452 +Eval (hcp-train-subset): [9] [61/62] eta: 0:00:00 loss: 0.8957 (0.8946) time: 0.1125 data: 0.0903 max mem: 8452 +Eval (hcp-train-subset): [9] Total time: 0:00:14 (0.2361 s / it) +Averaged stats (hcp-train-subset): loss: 0.8957 (0.8946) +Making plots (hcp-train-subset): example=54 +Eval (hcp-val): [9] [ 0/62] eta: 0:07:48 loss: 0.8866 (0.8866) time: 7.5611 data: 7.5327 max mem: 8452 +Eval (hcp-val): [9] [61/62] eta: 0:00:00 loss: 0.8883 (0.8898) time: 0.1331 data: 0.1121 max mem: 8452 +Eval (hcp-val): [9] Total time: 0:00:14 (0.2370 s / it) +Averaged stats (hcp-val): loss: 0.8883 (0.8898) +Making plots (hcp-val): example=9 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [10] [ 0/6250] eta: 12:05:34 lr: 0.000124 grad: 0.1002 (0.1002) loss: 0.9062 (0.9062) time: 6.9655 data: 6.8088 max mem: 8452 +Train: [10] [ 100/6250] eta: 0:23:53 lr: 0.000124 grad: 0.1045 (0.1066) loss: 0.8849 (0.8852) time: 0.2097 data: 0.1145 max mem: 8452 +Train: [10] [ 200/6250] eta: 0:20:09 lr: 0.000124 grad: 0.0867 (0.1038) loss: 0.8746 (0.8818) time: 0.1741 data: 0.0773 max mem: 8452 +Train: [10] [ 300/6250] eta: 0:18:47 lr: 0.000124 grad: 0.0773 (0.0977) loss: 0.8852 (0.8819) time: 0.1839 data: 0.0968 max mem: 8452 +Train: [10] [ 400/6250] eta: 0:17:53 lr: 0.000124 grad: 0.0862 (0.0950) loss: 0.8820 (0.8822) time: 0.1409 data: 0.0483 max mem: 8452 +Train: [10] [ 500/6250] eta: 0:17:07 lr: 0.000124 grad: 0.0812 (0.0924) loss: 0.8823 (0.8824) time: 0.1829 data: 0.0941 max mem: 8452 +Train: [10] [ 600/6250] eta: 0:16:21 lr: 0.000124 grad: 0.0795 (0.0904) loss: 0.8833 (0.8824) time: 0.1361 data: 0.0553 max mem: 8452 +Train: [10] [ 700/6250] eta: 0:15:50 lr: 0.000124 grad: 0.0791 (0.0895) loss: 0.8821 (0.8821) time: 0.1520 data: 0.0602 max mem: 8452 +Train: [10] [ 800/6250] eta: 0:15:27 lr: 0.000124 grad: 0.0771 (0.0888) loss: 0.8852 (0.8821) time: 0.1603 data: 0.0737 max mem: 8452 +Train: [10] [ 900/6250] eta: 0:15:07 lr: 0.000124 grad: 0.0811 (0.0878) loss: 0.8831 (0.8822) time: 0.1923 data: 0.1141 max mem: 8452 +Train: [10] [1000/6250] eta: 0:14:42 lr: 0.000124 grad: 0.0814 (0.0875) loss: 0.8830 (0.8821) time: 0.1436 data: 0.0636 max mem: 8452 +Train: [10] [1100/6250] eta: 0:14:22 lr: 0.000124 grad: 0.0829 (0.0874) loss: 0.8813 (0.8822) time: 0.1380 data: 0.0508 max mem: 8452 +Train: [10] [1200/6250] eta: 0:14:05 lr: 0.000124 grad: 0.0747 (0.0869) loss: 0.8867 (0.8823) time: 0.1604 data: 0.0840 max mem: 8452 +Train: [10] [1300/6250] eta: 0:13:46 lr: 0.000124 grad: 0.0812 (0.0865) loss: 0.8837 (0.8823) time: 0.1453 data: 0.0576 max mem: 8452 +Train: [10] [1400/6250] eta: 0:13:26 lr: 0.000124 grad: 0.0750 (0.0860) loss: 0.8848 (0.8824) time: 0.1612 data: 0.0752 max mem: 8452 +Train: [10] [1500/6250] eta: 0:13:07 lr: 0.000124 grad: 0.0713 (0.0856) loss: 0.8897 (0.8825) time: 0.1694 data: 0.0928 max mem: 8452 +Train: [10] [1600/6250] eta: 0:12:50 lr: 0.000124 grad: 0.0696 (0.0852) loss: 0.8846 (0.8825) time: 0.1664 data: 0.0851 max mem: 8452 +Train: [10] [1700/6250] eta: 0:12:38 lr: 0.000124 grad: 0.0769 (0.0849) loss: 0.8844 (0.8827) time: 0.2122 data: 0.1298 max mem: 8452 +Train: [10] [1800/6250] eta: 0:12:22 lr: 0.000124 grad: 0.0791 (0.0846) loss: 0.8806 (0.8827) time: 0.1831 data: 0.0988 max mem: 8452 +Train: [10] [1900/6250] eta: 0:12:03 lr: 0.000124 grad: 0.0793 (0.0844) loss: 0.8826 (0.8827) time: 0.1861 data: 0.1097 max mem: 8452 +Train: [10] [2000/6250] eta: 0:11:44 lr: 0.000124 grad: 0.0851 (0.0843) loss: 0.8853 (0.8827) time: 0.1646 data: 0.0902 max mem: 8452 +Train: [10] [2100/6250] eta: 0:11:25 lr: 0.000124 grad: 0.0743 (0.0842) loss: 0.8817 (0.8827) time: 0.1379 data: 0.0598 max mem: 8452 +Train: [10] [2200/6250] eta: 0:11:10 lr: 0.000124 grad: 0.0753 (0.0840) loss: 0.8811 (0.8827) time: 0.1338 data: 0.0406 max mem: 8452 +Train: [10] [2300/6250] eta: 0:10:53 lr: 0.000124 grad: 0.0806 (0.0841) loss: 0.8779 (0.8826) time: 0.1609 data: 0.0864 max mem: 8452 +Train: [10] [2400/6250] eta: 0:10:39 lr: 0.000124 grad: 0.0772 (0.0841) loss: 0.8847 (0.8824) time: 0.2078 data: 0.1459 max mem: 8452 +Train: [10] [2500/6250] eta: 0:10:24 lr: 0.000124 grad: 0.0776 (0.0840) loss: 0.8825 (0.8825) time: 0.1801 data: 0.1115 max mem: 8452 +Train: [10] [2600/6250] eta: 0:10:08 lr: 0.000124 grad: 0.0876 (0.0839) loss: 0.8817 (0.8824) time: 0.1821 data: 0.1031 max mem: 8452 +Train: [10] [2700/6250] eta: 0:09:52 lr: 0.000124 grad: 0.0754 (0.0839) loss: 0.8831 (0.8824) time: 0.1602 data: 0.0790 max mem: 8452 +Train: [10] [2800/6250] eta: 0:09:37 lr: 0.000124 grad: 0.0849 (0.0839) loss: 0.8847 (0.8824) time: 0.1915 data: 0.1188 max mem: 8452 +Train: [10] [2900/6250] eta: 0:09:20 lr: 0.000124 grad: 0.0771 (0.0838) loss: 0.8795 (0.8824) time: 0.1882 data: 0.1006 max mem: 8452 +Train: [10] [3000/6250] eta: 0:09:06 lr: 0.000124 grad: 0.0785 (0.0836) loss: 0.8821 (0.8824) time: 0.2271 data: 0.1461 max mem: 8452 +Train: [10] [3100/6250] eta: 0:08:49 lr: 0.000124 grad: 0.0833 (0.0835) loss: 0.8798 (0.8825) time: 0.1577 data: 0.0799 max mem: 8452 +Train: [10] [3200/6250] eta: 0:08:32 lr: 0.000124 grad: 0.0769 (0.0834) loss: 0.8840 (0.8825) time: 0.2229 data: 0.1473 max mem: 8452 +Train: [10] [3300/6250] eta: 0:08:15 lr: 0.000124 grad: 0.0825 (0.0833) loss: 0.8885 (0.8826) time: 0.1918 data: 0.0969 max mem: 8452 +Train: [10] [3400/6250] eta: 0:08:02 lr: 0.000124 grad: 0.0833 (0.0834) loss: 0.8828 (0.8826) time: 0.1800 data: 0.0759 max mem: 8452 +Train: [10] [3500/6250] eta: 0:07:46 lr: 0.000124 grad: 0.0780 (0.0833) loss: 0.8836 (0.8826) time: 0.2162 data: 0.0962 max mem: 8452 +Train: [10] [3600/6250] eta: 0:07:30 lr: 0.000124 grad: 0.0759 (0.0833) loss: 0.8844 (0.8827) time: 0.1557 data: 0.0694 max mem: 8452 +Train: [10] [3700/6250] eta: 0:07:13 lr: 0.000124 grad: 0.0772 (0.0833) loss: 0.8776 (0.8827) time: 0.1657 data: 0.0835 max mem: 8452 +Train: [10] [3800/6250] eta: 0:06:56 lr: 0.000124 grad: 0.0848 (0.0833) loss: 0.8852 (0.8827) time: 0.1471 data: 0.0547 max mem: 8452 +Train: [10] [3900/6250] eta: 0:06:39 lr: 0.000124 grad: 0.0797 (0.0833) loss: 0.8785 (0.8826) time: 0.1975 data: 0.1071 max mem: 8452 +Train: [10] [4000/6250] eta: 0:06:22 lr: 0.000124 grad: 0.0766 (0.0832) loss: 0.8842 (0.8827) time: 0.1661 data: 0.0774 max mem: 8452 +Train: [10] [4100/6250] eta: 0:06:04 lr: 0.000124 grad: 0.0784 (0.0832) loss: 0.8844 (0.8827) time: 0.1588 data: 0.0814 max mem: 8452 +Train: [10] [4200/6250] eta: 0:05:46 lr: 0.000124 grad: 0.0805 (0.0832) loss: 0.8820 (0.8827) time: 0.1679 data: 0.0930 max mem: 8452 +Train: [10] [4300/6250] eta: 0:05:29 lr: 0.000124 grad: 0.0739 (0.0832) loss: 0.8810 (0.8826) time: 0.1480 data: 0.0675 max mem: 8452 +Train: [10] [4400/6250] eta: 0:05:13 lr: 0.000124 grad: 0.0758 (0.0833) loss: 0.8794 (0.8825) time: 0.2036 data: 0.1253 max mem: 8452 +Train: [10] [4500/6250] eta: 0:04:55 lr: 0.000124 grad: 0.0806 (0.0832) loss: 0.8817 (0.8826) time: 0.1567 data: 0.0786 max mem: 8452 +Train: [10] [4600/6250] eta: 0:04:38 lr: 0.000124 grad: 0.0806 (0.0832) loss: 0.8806 (0.8825) time: 0.1541 data: 0.0772 max mem: 8452 +Train: [10] [4700/6250] eta: 0:04:21 lr: 0.000124 grad: 0.0776 (0.0831) loss: 0.8772 (0.8824) time: 0.1493 data: 0.0745 max mem: 8452 +Train: [10] [4800/6250] eta: 0:04:05 lr: 0.000124 grad: 0.0801 (0.0831) loss: 0.8877 (0.8824) time: 0.1638 data: 0.0762 max mem: 8452 +Train: [10] [4900/6250] eta: 0:03:48 lr: 0.000124 grad: 0.0782 (0.0831) loss: 0.8840 (0.8824) time: 0.2329 data: 0.1545 max mem: 8452 +Train: [10] [5000/6250] eta: 0:03:31 lr: 0.000124 grad: 0.0772 (0.0831) loss: 0.8828 (0.8823) time: 0.1603 data: 0.0758 max mem: 8452 +Train: [10] [5100/6250] eta: 0:03:14 lr: 0.000124 grad: 0.0803 (0.0832) loss: 0.8837 (0.8823) time: 0.1605 data: 0.0809 max mem: 8452 +Train: [10] [5200/6250] eta: 0:02:57 lr: 0.000124 grad: 0.0827 (0.0831) loss: 0.8768 (0.8823) time: 0.1875 data: 0.1145 max mem: 8452 +Train: [10] [5300/6250] eta: 0:02:40 lr: 0.000124 grad: 0.0768 (0.0831) loss: 0.8818 (0.8823) time: 0.1871 data: 0.1021 max mem: 8452 +Train: [10] [5400/6250] eta: 0:02:23 lr: 0.000124 grad: 0.0743 (0.0830) loss: 0.8801 (0.8823) time: 0.1513 data: 0.0731 max mem: 8452 +Train: [10] [5500/6250] eta: 0:02:06 lr: 0.000124 grad: 0.0815 (0.0831) loss: 0.8803 (0.8823) time: 0.1974 data: 0.1231 max mem: 8452 +Train: [10] [5600/6250] eta: 0:01:49 lr: 0.000124 grad: 0.0718 (0.0831) loss: 0.8852 (0.8822) time: 0.1454 data: 0.0704 max mem: 8452 +Train: [10] [5700/6250] eta: 0:01:32 lr: 0.000124 grad: 0.0756 (0.0831) loss: 0.8846 (0.8822) time: 0.1714 data: 0.0924 max mem: 8452 +Train: [10] [5800/6250] eta: 0:01:15 lr: 0.000124 grad: 0.0777 (0.0832) loss: 0.8862 (0.8822) time: 0.1735 data: 0.0983 max mem: 8452 +Train: [10] [5900/6250] eta: 0:00:59 lr: 0.000124 grad: 0.0739 (0.0832) loss: 0.8830 (0.8822) time: 0.1613 data: 0.0817 max mem: 8452 +Train: [10] [6000/6250] eta: 0:00:42 lr: 0.000124 grad: 0.0776 (0.0831) loss: 0.8861 (0.8823) time: 0.2375 data: 0.1156 max mem: 8452 +Train: [10] [6100/6250] eta: 0:00:25 lr: 0.000124 grad: 0.0810 (0.0831) loss: 0.8839 (0.8822) time: 0.1721 data: 0.0827 max mem: 8452 +Train: [10] [6200/6250] eta: 0:00:08 lr: 0.000124 grad: 0.0851 (0.0832) loss: 0.8801 (0.8822) time: 0.1621 data: 0.0766 max mem: 8452 +Train: [10] [6249/6250] eta: 0:00:00 lr: 0.000124 grad: 0.0842 (0.0831) loss: 0.8808 (0.8822) time: 0.1821 data: 0.0839 max mem: 8452 +Train: [10] Total time: 0:17:39 (0.1695 s / it) +Averaged stats: lr: 0.000124 grad: 0.0842 (0.0831) loss: 0.8808 (0.8822) +Eval (hcp-train-subset): [10] [ 0/62] eta: 0:08:29 loss: 0.9002 (0.9002) time: 8.2199 data: 8.1898 max mem: 8452 +Eval (hcp-train-subset): [10] [61/62] eta: 0:00:00 loss: 0.8933 (0.8923) time: 0.1264 data: 0.0999 max mem: 8452 +Eval (hcp-train-subset): [10] Total time: 0:00:15 (0.2462 s / it) +Averaged stats (hcp-train-subset): loss: 0.8933 (0.8923) +Eval (hcp-val): [10] [ 0/62] eta: 0:05:30 loss: 0.8848 (0.8848) time: 5.3372 data: 5.3113 max mem: 8452 +Eval (hcp-val): [10] [61/62] eta: 0:00:00 loss: 0.8876 (0.8881) time: 0.1272 data: 0.1053 max mem: 8452 +Eval (hcp-val): [10] Total time: 0:00:14 (0.2270 s / it) +Averaged stats (hcp-val): loss: 0.8876 (0.8881) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [11] [ 0/6250] eta: 9:01:44 lr: 0.000124 grad: 0.0545 (0.0545) loss: 0.9099 (0.9099) time: 5.2007 data: 4.8836 max mem: 8452 +Train: [11] [ 100/6250] eta: 0:22:28 lr: 0.000124 grad: 0.0861 (0.0947) loss: 0.8733 (0.8849) time: 0.1781 data: 0.0803 max mem: 8452 +Train: [11] [ 200/6250] eta: 0:19:17 lr: 0.000124 grad: 0.0928 (0.0952) loss: 0.8819 (0.8840) time: 0.1683 data: 0.0818 max mem: 8452 +Train: [11] [ 300/6250] eta: 0:17:37 lr: 0.000124 grad: 0.0782 (0.0919) loss: 0.8876 (0.8840) time: 0.1315 data: 0.0323 max mem: 8452 +Train: [11] [ 400/6250] eta: 0:17:01 lr: 0.000124 grad: 0.0757 (0.0888) loss: 0.8862 (0.8843) time: 0.1496 data: 0.0717 max mem: 8452 +Train: [11] [ 500/6250] eta: 0:16:43 lr: 0.000124 grad: 0.0788 (0.0866) loss: 0.8823 (0.8844) time: 0.1761 data: 0.0693 max mem: 8452 +Train: [11] [ 600/6250] eta: 0:16:56 lr: 0.000124 grad: 0.0722 (0.0844) loss: 0.8894 (0.8848) time: 0.1782 data: 0.1022 max mem: 8452 +Train: [11] [ 700/6250] eta: 0:16:52 lr: 0.000124 grad: 0.0716 (0.0838) loss: 0.8897 (0.8852) time: 0.2112 data: 0.0808 max mem: 8452 +Train: [11] [ 800/6250] eta: 0:17:12 lr: 0.000124 grad: 0.0692 (0.0826) loss: 0.8898 (0.8856) time: 0.3662 data: 0.2693 max mem: 8452 +Train: [11] [ 900/6250] eta: 0:16:41 lr: 0.000124 grad: 0.0701 (0.0821) loss: 0.8843 (0.8856) time: 0.1944 data: 0.0963 max mem: 8452 +Train: [11] [1000/6250] eta: 0:16:20 lr: 0.000124 grad: 0.0725 (0.0816) loss: 0.8870 (0.8854) time: 0.1572 data: 0.0636 max mem: 8452 +Train: [11] [1100/6250] eta: 0:15:53 lr: 0.000124 grad: 0.0801 (0.0813) loss: 0.8859 (0.8853) time: 0.1876 data: 0.1122 max mem: 8452 +Train: [11] [1200/6250] eta: 0:15:26 lr: 0.000124 grad: 0.0736 (0.0810) loss: 0.8895 (0.8854) time: 0.1859 data: 0.1148 max mem: 8452 +Train: [11] [1300/6250] eta: 0:15:02 lr: 0.000124 grad: 0.0809 (0.0808) loss: 0.8831 (0.8851) time: 0.1514 data: 0.0716 max mem: 8452 +Train: [11] [1400/6250] eta: 0:14:44 lr: 0.000124 grad: 0.0774 (0.0811) loss: 0.8808 (0.8849) time: 0.2312 data: 0.1308 max mem: 8452 +Train: [11] [1500/6250] eta: 0:14:17 lr: 0.000124 grad: 0.0744 (0.0809) loss: 0.8818 (0.8848) time: 0.1461 data: 0.0662 max mem: 8452 +Train: [11] [1600/6250] eta: 0:13:51 lr: 0.000124 grad: 0.0740 (0.0808) loss: 0.8806 (0.8846) time: 0.1233 data: 0.0370 max mem: 8452 +Train: [11] [1700/6250] eta: 0:13:32 lr: 0.000124 grad: 0.0776 (0.0809) loss: 0.8780 (0.8844) time: 0.1549 data: 0.0727 max mem: 8452 +Train: [11] [1800/6250] eta: 0:13:09 lr: 0.000124 grad: 0.0801 (0.0809) loss: 0.8810 (0.8843) time: 0.1506 data: 0.0583 max mem: 8452 +Train: [11] [1900/6250] eta: 0:12:50 lr: 0.000124 grad: 0.0801 (0.0811) loss: 0.8807 (0.8842) time: 0.1508 data: 0.0785 max mem: 8452 +Train: [11] [2000/6250] eta: 0:12:35 lr: 0.000124 grad: 0.0806 (0.0811) loss: 0.8839 (0.8840) time: 0.2710 data: 0.1580 max mem: 8452 +Train: [11] [2100/6250] eta: 0:12:13 lr: 0.000124 grad: 0.0742 (0.0812) loss: 0.8822 (0.8839) time: 0.1812 data: 0.0736 max mem: 8452 +Train: [11] [2200/6250] eta: 0:11:52 lr: 0.000124 grad: 0.0784 (0.0815) loss: 0.8826 (0.8838) time: 0.1724 data: 0.0935 max mem: 8452 +Train: [11] [2300/6250] eta: 0:11:31 lr: 0.000124 grad: 0.0764 (0.0814) loss: 0.8865 (0.8836) time: 0.1332 data: 0.0519 max mem: 8452 +Train: [11] [2400/6250] eta: 0:11:13 lr: 0.000124 grad: 0.0793 (0.0815) loss: 0.8783 (0.8834) time: 0.1883 data: 0.1181 max mem: 8452 +Train: [11] [2500/6250] eta: 0:10:52 lr: 0.000124 grad: 0.0726 (0.0815) loss: 0.8793 (0.8833) time: 0.1369 data: 0.0588 max mem: 8452 +Train: [11] [2600/6250] eta: 0:10:32 lr: 0.000124 grad: 0.0754 (0.0815) loss: 0.8795 (0.8831) time: 0.1600 data: 0.0793 max mem: 8452 +Train: [11] [2700/6250] eta: 0:10:15 lr: 0.000124 grad: 0.0725 (0.0813) loss: 0.8839 (0.8831) time: 0.1363 data: 0.0220 max mem: 8452 +Train: [11] [2800/6250] eta: 0:09:58 lr: 0.000124 grad: 0.0727 (0.0812) loss: 0.8794 (0.8829) time: 0.1239 data: 0.0157 max mem: 8452 +Train: [11] [2900/6250] eta: 0:09:39 lr: 0.000124 grad: 0.0807 (0.0813) loss: 0.8805 (0.8827) time: 0.1715 data: 0.0954 max mem: 8452 +Train: [11] [3000/6250] eta: 0:09:21 lr: 0.000124 grad: 0.0768 (0.0812) loss: 0.8837 (0.8827) time: 0.1706 data: 0.0953 max mem: 8452 +Train: [11] [3100/6250] eta: 0:09:05 lr: 0.000124 grad: 0.0781 (0.0811) loss: 0.8814 (0.8826) time: 0.1597 data: 0.0712 max mem: 8452 +Train: [11] [3200/6250] eta: 0:08:50 lr: 0.000124 grad: 0.0822 (0.0810) loss: 0.8817 (0.8825) time: 0.2740 data: 0.1919 max mem: 8452 +Train: [11] [3300/6250] eta: 0:08:30 lr: 0.000124 grad: 0.0803 (0.0810) loss: 0.8731 (0.8824) time: 0.1701 data: 0.0869 max mem: 8452 +Train: [11] [3400/6250] eta: 0:08:16 lr: 0.000124 grad: 0.0751 (0.0811) loss: 0.8815 (0.8822) time: 0.2119 data: 0.1317 max mem: 8452 +Train: [11] [3500/6250] eta: 0:07:59 lr: 0.000124 grad: 0.0760 (0.0810) loss: 0.8811 (0.8821) time: 0.2036 data: 0.1328 max mem: 8452 +Train: [11] [3600/6250] eta: 0:07:41 lr: 0.000124 grad: 0.0835 (0.0811) loss: 0.8732 (0.8820) time: 0.1642 data: 0.0899 max mem: 8452 +Train: [11] [3700/6250] eta: 0:07:25 lr: 0.000124 grad: 0.0777 (0.0810) loss: 0.8781 (0.8819) time: 0.1499 data: 0.0717 max mem: 8452 +Train: [11] [3800/6250] eta: 0:07:10 lr: 0.000124 grad: 0.0823 (0.0810) loss: 0.8784 (0.8817) time: 0.3535 data: 0.2607 max mem: 8452 +Train: [11] [3900/6250] eta: 0:06:51 lr: 0.000124 grad: 0.0782 (0.0811) loss: 0.8790 (0.8815) time: 0.1729 data: 0.0880 max mem: 8452 +Train: [11] [4000/6250] eta: 0:06:34 lr: 0.000123 grad: 0.0828 (0.0816) loss: 0.8712 (0.8813) time: 0.1654 data: 0.0604 max mem: 8452 +Train: [11] [4100/6250] eta: 0:06:17 lr: 0.000123 grad: 0.0785 (0.0816) loss: 0.8745 (0.8811) time: 0.2503 data: 0.1701 max mem: 8452 +Train: [11] [4200/6250] eta: 0:05:59 lr: 0.000123 grad: 0.0766 (0.0816) loss: 0.8755 (0.8810) time: 0.1926 data: 0.1161 max mem: 8452 +Train: [11] [4300/6250] eta: 0:05:42 lr: 0.000123 grad: 0.0816 (0.0817) loss: 0.8754 (0.8808) time: 0.1383 data: 0.0490 max mem: 8452 +Train: [11] [4400/6250] eta: 0:05:24 lr: 0.000123 grad: 0.0847 (0.0818) loss: 0.8753 (0.8807) time: 0.1677 data: 0.0863 max mem: 8452 +Train: [11] [4500/6250] eta: 0:05:05 lr: 0.000123 grad: 0.0739 (0.0818) loss: 0.8806 (0.8806) time: 0.1254 data: 0.0474 max mem: 8452 +Train: [11] [4600/6250] eta: 0:04:47 lr: 0.000123 grad: 0.0699 (0.0818) loss: 0.8817 (0.8805) time: 0.1530 data: 0.0693 max mem: 8452 +Train: [11] [4700/6250] eta: 0:04:29 lr: 0.000123 grad: 0.0711 (0.0817) loss: 0.8746 (0.8804) time: 0.1499 data: 0.0721 max mem: 8452 +Train: [11] [4800/6250] eta: 0:04:11 lr: 0.000123 grad: 0.0747 (0.0817) loss: 0.8793 (0.8803) time: 0.1473 data: 0.0613 max mem: 8452 +Train: [11] [4900/6250] eta: 0:03:53 lr: 0.000123 grad: 0.0719 (0.0817) loss: 0.8800 (0.8803) time: 0.1974 data: 0.1101 max mem: 8452 +Train: [11] [5000/6250] eta: 0:03:36 lr: 0.000123 grad: 0.0878 (0.0817) loss: 0.8758 (0.8802) time: 0.1518 data: 0.0773 max mem: 8452 +Train: [11] [5100/6250] eta: 0:03:18 lr: 0.000123 grad: 0.0824 (0.0817) loss: 0.8796 (0.8802) time: 0.1620 data: 0.0833 max mem: 8452 +Train: [11] [5200/6250] eta: 0:03:01 lr: 0.000123 grad: 0.0780 (0.0817) loss: 0.8739 (0.8801) time: 0.1635 data: 0.0650 max mem: 8452 +Train: [11] [5300/6250] eta: 0:02:44 lr: 0.000123 grad: 0.0836 (0.0817) loss: 0.8796 (0.8800) time: 0.1731 data: 0.0849 max mem: 8452 +Train: [11] [5400/6250] eta: 0:02:27 lr: 0.000123 grad: 0.0794 (0.0817) loss: 0.8727 (0.8800) time: 0.1224 data: 0.0244 max mem: 8452 +Train: [11] [5500/6250] eta: 0:02:10 lr: 0.000123 grad: 0.0775 (0.0817) loss: 0.8797 (0.8799) time: 0.1623 data: 0.0947 max mem: 8452 +Train: [11] [5600/6250] eta: 0:01:53 lr: 0.000123 grad: 0.0782 (0.0817) loss: 0.8758 (0.8799) time: 0.1913 data: 0.1167 max mem: 8452 +Train: [11] [5700/6250] eta: 0:01:36 lr: 0.000123 grad: 0.0780 (0.0816) loss: 0.8803 (0.8799) time: 0.1692 data: 0.0961 max mem: 8452 +Train: [11] [5800/6250] eta: 0:01:18 lr: 0.000123 grad: 0.0811 (0.0816) loss: 0.8795 (0.8798) time: 0.2037 data: 0.1117 max mem: 8452 +Train: [11] [5900/6250] eta: 0:01:01 lr: 0.000123 grad: 0.0732 (0.0816) loss: 0.8766 (0.8798) time: 0.1778 data: 0.1069 max mem: 8452 +Train: [11] [6000/6250] eta: 0:00:43 lr: 0.000123 grad: 0.0793 (0.0816) loss: 0.8760 (0.8797) time: 0.1835 data: 0.0938 max mem: 8452 +Train: [11] [6100/6250] eta: 0:00:26 lr: 0.000123 grad: 0.0758 (0.0816) loss: 0.8807 (0.8797) time: 0.1921 data: 0.1080 max mem: 8452 +Train: [11] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.0859 (0.0816) loss: 0.8793 (0.8797) time: 0.1909 data: 0.1125 max mem: 8452 +Train: [11] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0755 (0.0816) loss: 0.8805 (0.8797) time: 0.1779 data: 0.0945 max mem: 8452 +Train: [11] Total time: 0:18:28 (0.1773 s / it) +Averaged stats: lr: 0.000123 grad: 0.0755 (0.0816) loss: 0.8805 (0.8797) +Eval (hcp-train-subset): [11] [ 0/62] eta: 0:06:05 loss: 0.8999 (0.8999) time: 5.8985 data: 5.8711 max mem: 8452 +Eval (hcp-train-subset): [11] [61/62] eta: 0:00:00 loss: 0.8903 (0.8901) time: 0.1204 data: 0.0979 max mem: 8452 +Eval (hcp-train-subset): [11] Total time: 0:00:14 (0.2344 s / it) +Averaged stats (hcp-train-subset): loss: 0.8903 (0.8901) +Eval (hcp-val): [11] [ 0/62] eta: 0:06:37 loss: 0.8851 (0.8851) time: 6.4059 data: 6.3630 max mem: 8452 +Eval (hcp-val): [11] [61/62] eta: 0:00:00 loss: 0.8860 (0.8868) time: 0.1398 data: 0.1184 max mem: 8452 +Eval (hcp-val): [11] Total time: 0:00:17 (0.2754 s / it) +Averaged stats (hcp-val): loss: 0.8860 (0.8868) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [12] [ 0/6250] eta: 10:13:59 lr: 0.000123 grad: 0.0581 (0.0581) loss: 0.9018 (0.9018) time: 5.8944 data: 5.7476 max mem: 8452 +Train: [12] [ 100/6250] eta: 0:21:33 lr: 0.000123 grad: 0.0899 (0.0923) loss: 0.8877 (0.8905) time: 0.1549 data: 0.0606 max mem: 8452 +Train: [12] [ 200/6250] eta: 0:19:36 lr: 0.000123 grad: 0.0793 (0.0893) loss: 0.8927 (0.8875) time: 0.1696 data: 0.0803 max mem: 8452 +Train: [12] [ 300/6250] eta: 0:18:28 lr: 0.000123 grad: 0.0726 (0.0863) loss: 0.8823 (0.8861) time: 0.1727 data: 0.0762 max mem: 8452 +Train: [12] [ 400/6250] eta: 0:17:27 lr: 0.000123 grad: 0.0706 (0.0842) loss: 0.8830 (0.8847) time: 0.1505 data: 0.0533 max mem: 8452 +Train: [12] [ 500/6250] eta: 0:16:40 lr: 0.000123 grad: 0.0760 (0.0827) loss: 0.8818 (0.8834) time: 0.1374 data: 0.0372 max mem: 8452 +Train: [12] [ 600/6250] eta: 0:16:35 lr: 0.000123 grad: 0.0834 (0.0823) loss: 0.8761 (0.8828) time: 0.2481 data: 0.1302 max mem: 8452 +Train: [12] [ 700/6250] eta: 0:16:19 lr: 0.000123 grad: 0.0734 (0.0816) loss: 0.8768 (0.8820) time: 0.2036 data: 0.0971 max mem: 8452 +Train: [12] [ 800/6250] eta: 0:16:03 lr: 0.000123 grad: 0.0737 (0.0811) loss: 0.8804 (0.8818) time: 0.1546 data: 0.0599 max mem: 8452 +Train: [12] [ 900/6250] eta: 0:16:34 lr: 0.000123 grad: 0.0761 (0.0808) loss: 0.8772 (0.8814) time: 0.4930 data: 0.3896 max mem: 8452 +Train: [12] [1000/6250] eta: 0:16:09 lr: 0.000123 grad: 0.0733 (0.0808) loss: 0.8839 (0.8813) time: 0.1995 data: 0.1231 max mem: 8452 +Train: [12] [1100/6250] eta: 0:15:47 lr: 0.000123 grad: 0.0713 (0.0806) loss: 0.8777 (0.8810) time: 0.1572 data: 0.0512 max mem: 8452 +Train: [12] [1200/6250] eta: 0:15:22 lr: 0.000123 grad: 0.0732 (0.0804) loss: 0.8789 (0.8808) time: 0.1687 data: 0.0912 max mem: 8452 +Train: [12] [1300/6250] eta: 0:14:57 lr: 0.000123 grad: 0.0740 (0.0801) loss: 0.8808 (0.8808) time: 0.1493 data: 0.0589 max mem: 8452 +Train: [12] [1400/6250] eta: 0:14:33 lr: 0.000123 grad: 0.0722 (0.0799) loss: 0.8771 (0.8806) time: 0.1756 data: 0.0927 max mem: 8452 +Train: [12] [1500/6250] eta: 0:14:18 lr: 0.000123 grad: 0.0748 (0.0798) loss: 0.8781 (0.8804) time: 0.1058 data: 0.0308 max mem: 8452 +Train: [12] [1600/6250] eta: 0:13:56 lr: 0.000123 grad: 0.0746 (0.0798) loss: 0.8779 (0.8803) time: 0.1883 data: 0.0985 max mem: 8452 +Train: [12] [1700/6250] eta: 0:13:36 lr: 0.000123 grad: 0.0787 (0.0800) loss: 0.8791 (0.8803) time: 0.2367 data: 0.1558 max mem: 8452 +Train: [12] [1800/6250] eta: 0:13:14 lr: 0.000123 grad: 0.0698 (0.0802) loss: 0.8810 (0.8802) time: 0.1519 data: 0.0791 max mem: 8452 +Train: [12] [1900/6250] eta: 0:12:54 lr: 0.000123 grad: 0.0812 (0.0803) loss: 0.8704 (0.8801) time: 0.1754 data: 0.0925 max mem: 8452 +Train: [12] [2000/6250] eta: 0:12:32 lr: 0.000123 grad: 0.0827 (0.0807) loss: 0.8800 (0.8799) time: 0.1741 data: 0.1025 max mem: 8452 +Train: [12] [2100/6250] eta: 0:12:10 lr: 0.000123 grad: 0.0762 (0.0814) loss: 0.8791 (0.8795) time: 0.1640 data: 0.1007 max mem: 8452 +Train: [12] [2200/6250] eta: 0:11:50 lr: 0.000123 grad: 0.0782 (0.0816) loss: 0.8739 (0.8792) time: 0.1590 data: 0.0683 max mem: 8452 +Train: [12] [2300/6250] eta: 0:11:31 lr: 0.000123 grad: 0.0877 (0.0818) loss: 0.8645 (0.8789) time: 0.1784 data: 0.1079 max mem: 8452 +Train: [12] [2400/6250] eta: 0:11:14 lr: 0.000123 grad: 0.0729 (0.0819) loss: 0.8764 (0.8787) time: 0.1149 data: 0.0244 max mem: 8452 +Train: [12] [2500/6250] eta: 0:10:54 lr: 0.000123 grad: 0.0826 (0.0821) loss: 0.8733 (0.8785) time: 0.1960 data: 0.1251 max mem: 8452 +Train: [12] [2600/6250] eta: 0:10:36 lr: 0.000123 grad: 0.0735 (0.0822) loss: 0.8811 (0.8784) time: 0.1677 data: 0.1004 max mem: 8452 +Train: [12] [2700/6250] eta: 0:10:22 lr: 0.000123 grad: 0.0801 (0.0824) loss: 0.8676 (0.8780) time: 0.0983 data: 0.0002 max mem: 8452 +Train: [12] [2800/6250] eta: 0:10:02 lr: 0.000123 grad: 0.0744 (0.0826) loss: 0.8759 (0.8779) time: 0.1563 data: 0.0687 max mem: 8452 +Train: [12] [2900/6250] eta: 0:09:42 lr: 0.000123 grad: 0.0800 (0.0828) loss: 0.8746 (0.8777) time: 0.1384 data: 0.0572 max mem: 8452 +Train: [12] [3000/6250] eta: 0:09:24 lr: 0.000123 grad: 0.0837 (0.0828) loss: 0.8760 (0.8776) time: 0.1044 data: 0.0081 max mem: 8452 +Train: [12] [3100/6250] eta: 0:09:06 lr: 0.000123 grad: 0.0891 (0.0829) loss: 0.8668 (0.8775) time: 0.1444 data: 0.0785 max mem: 8452 +Train: [12] [3200/6250] eta: 0:08:47 lr: 0.000123 grad: 0.0840 (0.0829) loss: 0.8696 (0.8773) time: 0.1659 data: 0.0767 max mem: 8452 +Train: [12] [3300/6250] eta: 0:08:29 lr: 0.000123 grad: 0.0810 (0.0831) loss: 0.8721 (0.8771) time: 0.1707 data: 0.0882 max mem: 8452 +Train: [12] [3400/6250] eta: 0:08:12 lr: 0.000123 grad: 0.0795 (0.0833) loss: 0.8707 (0.8769) time: 0.2072 data: 0.1225 max mem: 8452 +Train: [12] [3500/6250] eta: 0:07:57 lr: 0.000123 grad: 0.0792 (0.0835) loss: 0.8669 (0.8767) time: 0.2068 data: 0.1218 max mem: 8452 +Train: [12] [3600/6250] eta: 0:07:38 lr: 0.000123 grad: 0.0761 (0.0836) loss: 0.8734 (0.8765) time: 0.1689 data: 0.0938 max mem: 8452 +Train: [12] [3700/6250] eta: 0:07:21 lr: 0.000123 grad: 0.0827 (0.0837) loss: 0.8749 (0.8764) time: 0.1616 data: 0.0810 max mem: 8452 +Train: [12] [3800/6250] eta: 0:07:03 lr: 0.000123 grad: 0.0841 (0.0838) loss: 0.8746 (0.8762) time: 0.1751 data: 0.0827 max mem: 8452 +Train: [12] [3900/6250] eta: 0:06:48 lr: 0.000123 grad: 0.0805 (0.0838) loss: 0.8711 (0.8760) time: 0.1168 data: 0.0003 max mem: 8452 +Train: [12] [4000/6250] eta: 0:06:30 lr: 0.000123 grad: 0.0860 (0.0839) loss: 0.8757 (0.8759) time: 0.1745 data: 0.0886 max mem: 8452 +Train: [12] [4100/6250] eta: 0:06:15 lr: 0.000123 grad: 0.0739 (0.0840) loss: 0.8751 (0.8758) time: 0.3020 data: 0.1956 max mem: 8452 +Train: [12] [4200/6250] eta: 0:05:57 lr: 0.000123 grad: 0.0780 (0.0839) loss: 0.8785 (0.8757) time: 0.1403 data: 0.0617 max mem: 8452 +Train: [12] [4300/6250] eta: 0:05:40 lr: 0.000123 grad: 0.0740 (0.0839) loss: 0.8703 (0.8757) time: 0.1732 data: 0.0788 max mem: 8452 +Train: [12] [4400/6250] eta: 0:05:23 lr: 0.000123 grad: 0.0774 (0.0837) loss: 0.8800 (0.8758) time: 0.2107 data: 0.1258 max mem: 8452 +Train: [12] [4500/6250] eta: 0:05:06 lr: 0.000123 grad: 0.0777 (0.0837) loss: 0.8755 (0.8757) time: 0.1207 data: 0.0193 max mem: 8452 +Train: [12] [4600/6250] eta: 0:04:48 lr: 0.000123 grad: 0.0760 (0.0836) loss: 0.8778 (0.8758) time: 0.1612 data: 0.0719 max mem: 8452 +Train: [12] [4700/6250] eta: 0:04:31 lr: 0.000123 grad: 0.0783 (0.0836) loss: 0.8776 (0.8758) time: 0.1528 data: 0.0731 max mem: 8452 +Train: [12] [4800/6250] eta: 0:04:13 lr: 0.000123 grad: 0.0761 (0.0836) loss: 0.8732 (0.8758) time: 0.1450 data: 0.0656 max mem: 8452 +Train: [12] [4900/6250] eta: 0:03:55 lr: 0.000123 grad: 0.0748 (0.0834) loss: 0.8758 (0.8758) time: 0.1864 data: 0.1139 max mem: 8452 +Train: [12] [5000/6250] eta: 0:03:37 lr: 0.000123 grad: 0.0768 (0.0835) loss: 0.8745 (0.8757) time: 0.1624 data: 0.0830 max mem: 8452 +Train: [12] [5100/6250] eta: 0:03:19 lr: 0.000123 grad: 0.0792 (0.0835) loss: 0.8729 (0.8757) time: 0.1485 data: 0.0758 max mem: 8452 +Train: [12] [5200/6250] eta: 0:03:02 lr: 0.000123 grad: 0.0796 (0.0835) loss: 0.8734 (0.8757) time: 0.1394 data: 0.0520 max mem: 8452 +Train: [12] [5300/6250] eta: 0:02:45 lr: 0.000123 grad: 0.0732 (0.0834) loss: 0.8775 (0.8756) time: 0.1911 data: 0.1186 max mem: 8452 +Train: [12] [5400/6250] eta: 0:02:27 lr: 0.000123 grad: 0.0804 (0.0834) loss: 0.8738 (0.8756) time: 0.1593 data: 0.0915 max mem: 8452 +Train: [12] [5500/6250] eta: 0:02:10 lr: 0.000123 grad: 0.0785 (0.0834) loss: 0.8783 (0.8756) time: 0.1706 data: 0.1046 max mem: 8452 +Train: [12] [5600/6250] eta: 0:01:52 lr: 0.000123 grad: 0.0785 (0.0834) loss: 0.8753 (0.8756) time: 0.1650 data: 0.0900 max mem: 8452 +Train: [12] [5700/6250] eta: 0:01:35 lr: 0.000123 grad: 0.0687 (0.0833) loss: 0.8760 (0.8757) time: 0.1787 data: 0.0903 max mem: 8452 +Train: [12] [5800/6250] eta: 0:01:18 lr: 0.000123 grad: 0.0819 (0.0833) loss: 0.8718 (0.8757) time: 0.1540 data: 0.0766 max mem: 8452 +Train: [12] [5900/6250] eta: 0:01:00 lr: 0.000123 grad: 0.0734 (0.0833) loss: 0.8766 (0.8757) time: 0.1785 data: 0.0870 max mem: 8452 +Train: [12] [6000/6250] eta: 0:00:43 lr: 0.000123 grad: 0.0781 (0.0832) loss: 0.8743 (0.8756) time: 0.1986 data: 0.1160 max mem: 8452 +Train: [12] [6100/6250] eta: 0:00:26 lr: 0.000123 grad: 0.0771 (0.0832) loss: 0.8828 (0.8756) time: 0.1380 data: 0.0565 max mem: 8452 +Train: [12] [6200/6250] eta: 0:00:08 lr: 0.000123 grad: 0.0851 (0.0832) loss: 0.8744 (0.8756) time: 0.1801 data: 0.0930 max mem: 8452 +Train: [12] [6249/6250] eta: 0:00:00 lr: 0.000123 grad: 0.0820 (0.0832) loss: 0.8742 (0.8757) time: 0.1350 data: 0.0354 max mem: 8452 +Train: [12] Total time: 0:18:16 (0.1755 s / it) +Averaged stats: lr: 0.000123 grad: 0.0820 (0.0832) loss: 0.8742 (0.8757) +Eval (hcp-train-subset): [12] [ 0/62] eta: 0:06:35 loss: 0.9009 (0.9009) time: 6.3864 data: 6.3594 max mem: 8452 +Eval (hcp-train-subset): [12] [61/62] eta: 0:00:00 loss: 0.8929 (0.8929) time: 0.1258 data: 0.1046 max mem: 8452 +Eval (hcp-train-subset): [12] Total time: 0:00:14 (0.2378 s / it) +Averaged stats (hcp-train-subset): loss: 0.8929 (0.8929) +Eval (hcp-val): [12] [ 0/62] eta: 0:06:07 loss: 0.8874 (0.8874) time: 5.9244 data: 5.8966 max mem: 8452 +Eval (hcp-val): [12] [61/62] eta: 0:00:00 loss: 0.8870 (0.8880) time: 0.1745 data: 0.1535 max mem: 8452 +Eval (hcp-val): [12] Total time: 0:00:15 (0.2470 s / it) +Averaged stats (hcp-val): loss: 0.8870 (0.8880) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [13] [ 0/6250] eta: 12:04:16 lr: 0.000123 grad: 0.1408 (0.1408) loss: 0.9117 (0.9117) time: 6.9530 data: 6.8511 max mem: 8452 +Train: [13] [ 100/6250] eta: 0:22:28 lr: 0.000123 grad: 0.1135 (0.1058) loss: 0.8723 (0.8842) time: 0.1680 data: 0.0721 max mem: 8452 +Train: [13] [ 200/6250] eta: 0:19:30 lr: 0.000123 grad: 0.0788 (0.1002) loss: 0.8754 (0.8816) time: 0.1706 data: 0.0741 max mem: 8452 +Train: [13] [ 300/6250] eta: 0:18:34 lr: 0.000123 grad: 0.0831 (0.0938) loss: 0.8757 (0.8794) time: 0.1848 data: 0.0895 max mem: 8452 +Train: [13] [ 400/6250] eta: 0:17:51 lr: 0.000123 grad: 0.0815 (0.0915) loss: 0.8733 (0.8779) time: 0.1485 data: 0.0694 max mem: 8452 +Train: [13] [ 500/6250] eta: 0:17:18 lr: 0.000123 grad: 0.0875 (0.0910) loss: 0.8726 (0.8768) time: 0.2004 data: 0.1061 max mem: 8452 +Train: [13] [ 600/6250] eta: 0:16:43 lr: 0.000123 grad: 0.0786 (0.0904) loss: 0.8743 (0.8754) time: 0.1546 data: 0.0694 max mem: 8452 +Train: [13] [ 700/6250] eta: 0:16:25 lr: 0.000123 grad: 0.0785 (0.0903) loss: 0.8810 (0.8746) time: 0.1130 data: 0.0003 max mem: 8452 +Train: [13] [ 800/6250] eta: 0:16:09 lr: 0.000123 grad: 0.0844 (0.0898) loss: 0.8731 (0.8739) time: 0.1703 data: 0.0915 max mem: 8452 +Train: [13] [ 900/6250] eta: 0:16:14 lr: 0.000123 grad: 0.0787 (0.0890) loss: 0.8715 (0.8734) time: 0.1236 data: 0.0003 max mem: 8452 +Train: [13] [1000/6250] eta: 0:15:57 lr: 0.000123 grad: 0.0832 (0.0884) loss: 0.8737 (0.8730) time: 0.1948 data: 0.1110 max mem: 8452 +Train: [13] [1100/6250] eta: 0:15:42 lr: 0.000123 grad: 0.0748 (0.0875) loss: 0.8723 (0.8728) time: 0.1633 data: 0.0948 max mem: 8452 +Train: [13] [1200/6250] eta: 0:15:25 lr: 0.000123 grad: 0.0794 (0.0870) loss: 0.8714 (0.8727) time: 0.1234 data: 0.0469 max mem: 8452 +Train: [13] [1300/6250] eta: 0:14:58 lr: 0.000123 grad: 0.0803 (0.0866) loss: 0.8607 (0.8724) time: 0.1545 data: 0.0719 max mem: 8452 +Train: [13] [1400/6250] eta: 0:14:33 lr: 0.000123 grad: 0.0782 (0.0864) loss: 0.8719 (0.8722) time: 0.1626 data: 0.0908 max mem: 8452 +Train: [13] [1500/6250] eta: 0:14:11 lr: 0.000123 grad: 0.0790 (0.0861) loss: 0.8668 (0.8720) time: 0.1672 data: 0.0835 max mem: 8452 +Train: [13] [1600/6250] eta: 0:13:48 lr: 0.000123 grad: 0.0818 (0.0858) loss: 0.8692 (0.8718) time: 0.1708 data: 0.0951 max mem: 8452 +Train: [13] [1700/6250] eta: 0:13:29 lr: 0.000123 grad: 0.0769 (0.0854) loss: 0.8658 (0.8718) time: 0.2035 data: 0.1294 max mem: 8452 +Train: [13] [1800/6250] eta: 0:13:11 lr: 0.000123 grad: 0.0747 (0.0852) loss: 0.8763 (0.8718) time: 0.1698 data: 0.0985 max mem: 8452 +Train: [13] [1900/6250] eta: 0:12:50 lr: 0.000123 grad: 0.0797 (0.0850) loss: 0.8699 (0.8719) time: 0.1598 data: 0.0806 max mem: 8452 +Train: [13] [2000/6250] eta: 0:12:31 lr: 0.000123 grad: 0.0777 (0.0847) loss: 0.8779 (0.8720) time: 0.1857 data: 0.1033 max mem: 8452 +Train: [13] [2100/6250] eta: 0:12:13 lr: 0.000123 grad: 0.0731 (0.0846) loss: 0.8734 (0.8720) time: 0.1761 data: 0.1005 max mem: 8452 +Train: [13] [2200/6250] eta: 0:11:54 lr: 0.000123 grad: 0.0819 (0.0845) loss: 0.8734 (0.8719) time: 0.1780 data: 0.0905 max mem: 8452 +Train: [13] [2300/6250] eta: 0:11:37 lr: 0.000123 grad: 0.0744 (0.0843) loss: 0.8711 (0.8720) time: 0.1696 data: 0.0592 max mem: 8452 +Train: [13] [2400/6250] eta: 0:11:19 lr: 0.000123 grad: 0.0848 (0.0842) loss: 0.8680 (0.8719) time: 0.1921 data: 0.1125 max mem: 8452 +Train: [13] [2500/6250] eta: 0:11:02 lr: 0.000123 grad: 0.0774 (0.0842) loss: 0.8735 (0.8718) time: 0.1566 data: 0.0512 max mem: 8452 +Train: [13] [2600/6250] eta: 0:10:42 lr: 0.000123 grad: 0.0748 (0.0840) loss: 0.8700 (0.8717) time: 0.1465 data: 0.0682 max mem: 8452 +Train: [13] [2700/6250] eta: 0:10:23 lr: 0.000123 grad: 0.0744 (0.0838) loss: 0.8669 (0.8716) time: 0.1643 data: 0.0820 max mem: 8452 +Train: [13] [2800/6250] eta: 0:10:04 lr: 0.000123 grad: 0.0761 (0.0838) loss: 0.8733 (0.8715) time: 0.1499 data: 0.0651 max mem: 8452 +Train: [13] [2900/6250] eta: 0:09:49 lr: 0.000123 grad: 0.0712 (0.0839) loss: 0.8748 (0.8715) time: 0.1511 data: 0.0552 max mem: 8452 +Train: [13] [3000/6250] eta: 0:09:29 lr: 0.000123 grad: 0.0863 (0.0839) loss: 0.8738 (0.8715) time: 0.1742 data: 0.0921 max mem: 8452 +Train: [13] [3100/6250] eta: 0:09:11 lr: 0.000123 grad: 0.0772 (0.0838) loss: 0.8718 (0.8715) time: 0.1796 data: 0.0968 max mem: 8452 +Train: [13] [3200/6250] eta: 0:08:53 lr: 0.000123 grad: 0.0707 (0.0837) loss: 0.8768 (0.8715) time: 0.1807 data: 0.1067 max mem: 8452 +Train: [13] [3300/6250] eta: 0:08:36 lr: 0.000123 grad: 0.0724 (0.0836) loss: 0.8799 (0.8715) time: 0.1508 data: 0.0608 max mem: 8452 +Train: [13] [3400/6250] eta: 0:08:17 lr: 0.000123 grad: 0.0744 (0.0835) loss: 0.8704 (0.8716) time: 0.1307 data: 0.0392 max mem: 8452 +Train: [13] [3500/6250] eta: 0:07:58 lr: 0.000123 grad: 0.0779 (0.0834) loss: 0.8799 (0.8717) time: 0.1607 data: 0.0857 max mem: 8452 +Train: [13] [3600/6250] eta: 0:07:39 lr: 0.000123 grad: 0.0718 (0.0833) loss: 0.8789 (0.8718) time: 0.1441 data: 0.0567 max mem: 8452 +Train: [13] [3700/6250] eta: 0:07:21 lr: 0.000122 grad: 0.0775 (0.0832) loss: 0.8742 (0.8719) time: 0.1680 data: 0.0939 max mem: 8452 +Train: [13] [3800/6250] eta: 0:07:04 lr: 0.000122 grad: 0.0742 (0.0831) loss: 0.8760 (0.8720) time: 0.1709 data: 0.0957 max mem: 8452 +Train: [13] [3900/6250] eta: 0:06:46 lr: 0.000122 grad: 0.0773 (0.0829) loss: 0.8831 (0.8722) time: 0.1615 data: 0.0755 max mem: 8452 +Train: [13] [4000/6250] eta: 0:06:29 lr: 0.000122 grad: 0.0741 (0.0828) loss: 0.8730 (0.8723) time: 0.1465 data: 0.0705 max mem: 8452 +Train: [13] [4100/6250] eta: 0:06:11 lr: 0.000122 grad: 0.0766 (0.0826) loss: 0.8796 (0.8724) time: 0.1513 data: 0.0775 max mem: 8452 +Train: [13] [4200/6250] eta: 0:05:55 lr: 0.000122 grad: 0.0765 (0.0825) loss: 0.8766 (0.8726) time: 0.2983 data: 0.1945 max mem: 8452 +Train: [13] [4300/6250] eta: 0:05:37 lr: 0.000122 grad: 0.0729 (0.0823) loss: 0.8784 (0.8727) time: 0.1621 data: 0.0778 max mem: 8452 +Train: [13] [4400/6250] eta: 0:05:20 lr: 0.000122 grad: 0.0755 (0.0822) loss: 0.8785 (0.8728) time: 0.1757 data: 0.1051 max mem: 8452 +Train: [13] [4500/6250] eta: 0:05:03 lr: 0.000122 grad: 0.0771 (0.0820) loss: 0.8766 (0.8730) time: 0.1727 data: 0.0859 max mem: 8452 +Train: [13] [4600/6250] eta: 0:04:46 lr: 0.000122 grad: 0.0793 (0.0820) loss: 0.8791 (0.8730) time: 0.1726 data: 0.0923 max mem: 8452 +Train: [13] [4700/6250] eta: 0:04:30 lr: 0.000122 grad: 0.0737 (0.0820) loss: 0.8776 (0.8731) time: 0.3200 data: 0.2275 max mem: 8452 +Train: [13] [4800/6250] eta: 0:04:12 lr: 0.000122 grad: 0.0860 (0.0820) loss: 0.8669 (0.8731) time: 0.1489 data: 0.0720 max mem: 8452 +Train: [13] [4900/6250] eta: 0:03:54 lr: 0.000122 grad: 0.0718 (0.0819) loss: 0.8770 (0.8731) time: 0.2455 data: 0.1423 max mem: 8452 +Train: [13] [5000/6250] eta: 0:03:37 lr: 0.000122 grad: 0.0815 (0.0819) loss: 0.8705 (0.8731) time: 0.1440 data: 0.0578 max mem: 8452 +Train: [13] [5100/6250] eta: 0:03:19 lr: 0.000122 grad: 0.0750 (0.0818) loss: 0.8706 (0.8731) time: 0.2575 data: 0.1669 max mem: 8452 +Train: [13] [5200/6250] eta: 0:03:02 lr: 0.000122 grad: 0.0764 (0.0818) loss: 0.8736 (0.8731) time: 0.1261 data: 0.0421 max mem: 8452 +Train: [13] [5300/6250] eta: 0:02:45 lr: 0.000122 grad: 0.0764 (0.0818) loss: 0.8746 (0.8732) time: 0.2553 data: 0.1910 max mem: 8452 +Train: [13] [5400/6250] eta: 0:02:27 lr: 0.000122 grad: 0.0812 (0.0817) loss: 0.8767 (0.8732) time: 0.1567 data: 0.0802 max mem: 8452 +Train: [13] [5500/6250] eta: 0:02:10 lr: 0.000122 grad: 0.0774 (0.0817) loss: 0.8729 (0.8732) time: 0.1669 data: 0.0959 max mem: 8452 +Train: [13] [5600/6250] eta: 0:01:52 lr: 0.000122 grad: 0.0749 (0.0817) loss: 0.8735 (0.8732) time: 0.1721 data: 0.0970 max mem: 8452 +Train: [13] [5700/6250] eta: 0:01:35 lr: 0.000122 grad: 0.0772 (0.0817) loss: 0.8772 (0.8732) time: 0.1726 data: 0.0919 max mem: 8452 +Train: [13] [5800/6250] eta: 0:01:18 lr: 0.000122 grad: 0.0754 (0.0816) loss: 0.8810 (0.8733) time: 0.1576 data: 0.0689 max mem: 8452 +Train: [13] [5900/6250] eta: 0:01:00 lr: 0.000122 grad: 0.0742 (0.0816) loss: 0.8760 (0.8733) time: 0.1329 data: 0.0407 max mem: 8452 +Train: [13] [6000/6250] eta: 0:00:43 lr: 0.000122 grad: 0.0778 (0.0816) loss: 0.8817 (0.8734) time: 0.1580 data: 0.0620 max mem: 8452 +Train: [13] [6100/6250] eta: 0:00:25 lr: 0.000122 grad: 0.0739 (0.0816) loss: 0.8811 (0.8734) time: 0.1492 data: 0.0630 max mem: 8452 +Train: [13] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0793 (0.0815) loss: 0.8721 (0.8735) time: 0.1326 data: 0.0401 max mem: 8452 +Train: [13] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0808 (0.0815) loss: 0.8729 (0.8735) time: 0.1657 data: 0.0775 max mem: 8452 +Train: [13] Total time: 0:18:01 (0.1731 s / it) +Averaged stats: lr: 0.000122 grad: 0.0808 (0.0815) loss: 0.8729 (0.8735) +Eval (hcp-train-subset): [13] [ 0/62] eta: 0:05:00 loss: 0.8997 (0.8997) time: 4.8523 data: 4.8253 max mem: 8452 +Eval (hcp-train-subset): [13] [61/62] eta: 0:00:00 loss: 0.8897 (0.8891) time: 0.1373 data: 0.1146 max mem: 8452 +Eval (hcp-train-subset): [13] Total time: 0:00:14 (0.2299 s / it) +Averaged stats (hcp-train-subset): loss: 0.8897 (0.8891) +Eval (hcp-val): [13] [ 0/62] eta: 0:05:37 loss: 0.8814 (0.8814) time: 5.4516 data: 5.4240 max mem: 8452 +Eval (hcp-val): [13] [61/62] eta: 0:00:00 loss: 0.8838 (0.8853) time: 0.1419 data: 0.1198 max mem: 8452 +Eval (hcp-val): [13] Total time: 0:00:14 (0.2266 s / it) +Averaged stats (hcp-val): loss: 0.8838 (0.8853) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [14] [ 0/6250] eta: 11:32:58 lr: 0.000122 grad: 0.0818 (0.0818) loss: 0.8732 (0.8732) time: 6.6526 data: 6.5490 max mem: 8452 +Train: [14] [ 100/6250] eta: 0:23:00 lr: 0.000122 grad: 0.1155 (0.1149) loss: 0.8747 (0.8725) time: 0.1545 data: 0.0707 max mem: 8452 +Train: [14] [ 200/6250] eta: 0:19:47 lr: 0.000122 grad: 0.0808 (0.1029) loss: 0.8686 (0.8708) time: 0.1946 data: 0.1024 max mem: 8452 +Train: [14] [ 300/6250] eta: 0:18:49 lr: 0.000122 grad: 0.0768 (0.0960) loss: 0.8778 (0.8719) time: 0.1769 data: 0.0867 max mem: 8452 +Train: [14] [ 400/6250] eta: 0:18:41 lr: 0.000122 grad: 0.0785 (0.0923) loss: 0.8707 (0.8725) time: 0.2323 data: 0.1251 max mem: 8452 +Train: [14] [ 500/6250] eta: 0:18:07 lr: 0.000122 grad: 0.0692 (0.0898) loss: 0.8744 (0.8726) time: 0.1668 data: 0.0591 max mem: 8452 +Train: [14] [ 600/6250] eta: 0:17:28 lr: 0.000122 grad: 0.0702 (0.0878) loss: 0.8693 (0.8724) time: 0.1514 data: 0.0649 max mem: 8452 +Train: [14] [ 700/6250] eta: 0:17:09 lr: 0.000122 grad: 0.0806 (0.0866) loss: 0.8742 (0.8723) time: 0.1938 data: 0.1070 max mem: 8452 +Train: [14] [ 800/6250] eta: 0:16:46 lr: 0.000122 grad: 0.0773 (0.0861) loss: 0.8666 (0.8723) time: 0.1728 data: 0.0839 max mem: 8452 +Train: [14] [ 900/6250] eta: 0:16:51 lr: 0.000122 grad: 0.0772 (0.0865) loss: 0.8721 (0.8721) time: 0.2379 data: 0.1392 max mem: 8452 +Train: [14] [1000/6250] eta: 0:16:24 lr: 0.000122 grad: 0.0801 (0.0856) loss: 0.8708 (0.8720) time: 0.1772 data: 0.1058 max mem: 8452 +Train: [14] [1100/6250] eta: 0:16:14 lr: 0.000122 grad: 0.0823 (0.0852) loss: 0.8658 (0.8719) time: 0.3247 data: 0.2314 max mem: 8452 +Train: [14] [1200/6250] eta: 0:15:42 lr: 0.000122 grad: 0.0745 (0.0848) loss: 0.8750 (0.8719) time: 0.1597 data: 0.0868 max mem: 8452 +Train: [14] [1300/6250] eta: 0:15:26 lr: 0.000122 grad: 0.0685 (0.0843) loss: 0.8732 (0.8719) time: 0.1186 data: 0.0003 max mem: 8452 +Train: [14] [1400/6250] eta: 0:14:59 lr: 0.000122 grad: 0.0756 (0.0840) loss: 0.8731 (0.8720) time: 0.1768 data: 0.1017 max mem: 8452 +Train: [14] [1500/6250] eta: 0:14:39 lr: 0.000122 grad: 0.0799 (0.0837) loss: 0.8728 (0.8722) time: 0.1741 data: 0.0717 max mem: 8452 +Train: [14] [1600/6250] eta: 0:14:17 lr: 0.000122 grad: 0.0784 (0.0833) loss: 0.8697 (0.8723) time: 0.1671 data: 0.0848 max mem: 8452 +Train: [14] [1700/6250] eta: 0:13:54 lr: 0.000122 grad: 0.0779 (0.0831) loss: 0.8728 (0.8724) time: 0.1686 data: 0.0719 max mem: 8452 +Train: [14] [1800/6250] eta: 0:13:34 lr: 0.000122 grad: 0.0737 (0.0828) loss: 0.8721 (0.8724) time: 0.1983 data: 0.1261 max mem: 8452 +Train: [14] [1900/6250] eta: 0:13:13 lr: 0.000122 grad: 0.0726 (0.0826) loss: 0.8769 (0.8725) time: 0.2119 data: 0.1145 max mem: 8452 +Train: [14] [2000/6250] eta: 0:12:49 lr: 0.000122 grad: 0.0781 (0.0824) loss: 0.8696 (0.8725) time: 0.1426 data: 0.0625 max mem: 8452 +Train: [14] [2100/6250] eta: 0:12:28 lr: 0.000122 grad: 0.0750 (0.0823) loss: 0.8715 (0.8724) time: 0.1631 data: 0.0849 max mem: 8452 +Train: [14] [2200/6250] eta: 0:12:07 lr: 0.000122 grad: 0.0736 (0.0822) loss: 0.8742 (0.8725) time: 0.1702 data: 0.0696 max mem: 8452 +Train: [14] [2300/6250] eta: 0:11:50 lr: 0.000122 grad: 0.0768 (0.0820) loss: 0.8700 (0.8725) time: 0.2528 data: 0.1594 max mem: 8452 +Train: [14] [2400/6250] eta: 0:11:30 lr: 0.000122 grad: 0.0760 (0.0819) loss: 0.8780 (0.8726) time: 0.1268 data: 0.0249 max mem: 8452 +Train: [14] [2500/6250] eta: 0:11:10 lr: 0.000122 grad: 0.0799 (0.0817) loss: 0.8686 (0.8726) time: 0.1682 data: 0.0860 max mem: 8452 +Train: [14] [2600/6250] eta: 0:10:51 lr: 0.000122 grad: 0.0764 (0.0815) loss: 0.8796 (0.8727) time: 0.1796 data: 0.0976 max mem: 8452 +Train: [14] [2700/6250] eta: 0:10:33 lr: 0.000122 grad: 0.0863 (0.0814) loss: 0.8758 (0.8728) time: 0.2052 data: 0.1165 max mem: 8452 +Train: [14] [2800/6250] eta: 0:10:12 lr: 0.000122 grad: 0.0737 (0.0813) loss: 0.8808 (0.8729) time: 0.1729 data: 0.0971 max mem: 8452 +Train: [14] [2900/6250] eta: 0:09:54 lr: 0.000122 grad: 0.0736 (0.0811) loss: 0.8681 (0.8729) time: 0.1656 data: 0.0840 max mem: 8452 +Train: [14] [3000/6250] eta: 0:09:35 lr: 0.000122 grad: 0.0726 (0.0811) loss: 0.8762 (0.8729) time: 0.1715 data: 0.0931 max mem: 8452 +Train: [14] [3100/6250] eta: 0:09:16 lr: 0.000122 grad: 0.0721 (0.0811) loss: 0.8713 (0.8730) time: 0.1576 data: 0.0782 max mem: 8452 +Train: [14] [3200/6250] eta: 0:08:59 lr: 0.000122 grad: 0.0702 (0.0810) loss: 0.8774 (0.8729) time: 0.1598 data: 0.0636 max mem: 8452 +Train: [14] [3300/6250] eta: 0:08:41 lr: 0.000122 grad: 0.0788 (0.0809) loss: 0.8715 (0.8729) time: 0.2028 data: 0.1209 max mem: 8452 +Train: [14] [3400/6250] eta: 0:08:24 lr: 0.000122 grad: 0.0748 (0.0808) loss: 0.8720 (0.8730) time: 0.1146 data: 0.0203 max mem: 8452 +Train: [14] [3500/6250] eta: 0:08:06 lr: 0.000122 grad: 0.0737 (0.0808) loss: 0.8747 (0.8731) time: 0.2351 data: 0.1189 max mem: 8452 +Train: [14] [3600/6250] eta: 0:07:48 lr: 0.000122 grad: 0.0761 (0.0807) loss: 0.8757 (0.8731) time: 0.1303 data: 0.0377 max mem: 8452 +Train: [14] [3700/6250] eta: 0:07:31 lr: 0.000122 grad: 0.0727 (0.0805) loss: 0.8785 (0.8733) time: 0.1668 data: 0.0421 max mem: 8452 +Train: [14] [3800/6250] eta: 0:07:12 lr: 0.000122 grad: 0.0749 (0.0805) loss: 0.8673 (0.8733) time: 0.1701 data: 0.1005 max mem: 8452 +Train: [14] [3900/6250] eta: 0:06:53 lr: 0.000122 grad: 0.0809 (0.0805) loss: 0.8723 (0.8734) time: 0.1460 data: 0.0589 max mem: 8452 +Train: [14] [4000/6250] eta: 0:06:35 lr: 0.000122 grad: 0.0811 (0.0805) loss: 0.8716 (0.8734) time: 0.1764 data: 0.1008 max mem: 8452 +Train: [14] [4100/6250] eta: 0:06:17 lr: 0.000122 grad: 0.0738 (0.0807) loss: 0.8802 (0.8734) time: 0.1728 data: 0.0814 max mem: 8452 +Train: [14] [4200/6250] eta: 0:06:00 lr: 0.000122 grad: 0.0770 (0.0807) loss: 0.8686 (0.8733) time: 0.1803 data: 0.0942 max mem: 8452 +Train: [14] [4300/6250] eta: 0:05:42 lr: 0.000122 grad: 0.0815 (0.0807) loss: 0.8688 (0.8733) time: 0.1152 data: 0.0098 max mem: 8452 +Train: [14] [4400/6250] eta: 0:05:24 lr: 0.000122 grad: 0.0816 (0.0807) loss: 0.8735 (0.8733) time: 0.1562 data: 0.0760 max mem: 8452 +Train: [14] [4500/6250] eta: 0:05:06 lr: 0.000122 grad: 0.0776 (0.0807) loss: 0.8727 (0.8733) time: 0.1685 data: 0.0854 max mem: 8452 +Train: [14] [4600/6250] eta: 0:04:48 lr: 0.000122 grad: 0.0752 (0.0807) loss: 0.8816 (0.8733) time: 0.2009 data: 0.1191 max mem: 8452 +Train: [14] [4700/6250] eta: 0:04:31 lr: 0.000122 grad: 0.0811 (0.0808) loss: 0.8679 (0.8732) time: 0.1045 data: 0.0049 max mem: 8452 +Train: [14] [4800/6250] eta: 0:04:14 lr: 0.000122 grad: 0.0852 (0.0808) loss: 0.8713 (0.8732) time: 0.1692 data: 0.0857 max mem: 8452 +Train: [14] [4900/6250] eta: 0:03:56 lr: 0.000122 grad: 0.0745 (0.0807) loss: 0.8756 (0.8732) time: 0.1774 data: 0.1058 max mem: 8452 +Train: [14] [5000/6250] eta: 0:03:38 lr: 0.000122 grad: 0.0747 (0.0807) loss: 0.8734 (0.8732) time: 0.1581 data: 0.0777 max mem: 8452 +Train: [14] [5100/6250] eta: 0:03:21 lr: 0.000122 grad: 0.0766 (0.0807) loss: 0.8782 (0.8732) time: 0.1122 data: 0.0278 max mem: 8452 +Train: [14] [5200/6250] eta: 0:03:03 lr: 0.000122 grad: 0.0788 (0.0807) loss: 0.8715 (0.8732) time: 0.1970 data: 0.1314 max mem: 8452 +Train: [14] [5300/6250] eta: 0:02:46 lr: 0.000122 grad: 0.0786 (0.0807) loss: 0.8786 (0.8733) time: 0.1383 data: 0.0673 max mem: 8452 +Train: [14] [5400/6250] eta: 0:02:29 lr: 0.000122 grad: 0.0715 (0.0807) loss: 0.8712 (0.8733) time: 0.1571 data: 0.0816 max mem: 8452 +Train: [14] [5500/6250] eta: 0:02:11 lr: 0.000122 grad: 0.0687 (0.0805) loss: 0.8804 (0.8734) time: 0.2210 data: 0.1488 max mem: 8452 +Train: [14] [5600/6250] eta: 0:01:53 lr: 0.000122 grad: 0.0745 (0.0805) loss: 0.8795 (0.8734) time: 0.1686 data: 0.0823 max mem: 8452 +Train: [14] [5700/6250] eta: 0:01:36 lr: 0.000122 grad: 0.0747 (0.0804) loss: 0.8804 (0.8734) time: 0.1800 data: 0.0909 max mem: 8452 +Train: [14] [5800/6250] eta: 0:01:18 lr: 0.000122 grad: 0.0805 (0.0804) loss: 0.8681 (0.8734) time: 0.1428 data: 0.0571 max mem: 8452 +Train: [14] [5900/6250] eta: 0:01:01 lr: 0.000122 grad: 0.0776 (0.0804) loss: 0.8704 (0.8734) time: 0.1679 data: 0.0962 max mem: 8452 +Train: [14] [6000/6250] eta: 0:00:43 lr: 0.000122 grad: 0.0711 (0.0803) loss: 0.8757 (0.8734) time: 0.1539 data: 0.0703 max mem: 8452 +Train: [14] [6100/6250] eta: 0:00:26 lr: 0.000122 grad: 0.0813 (0.0803) loss: 0.8778 (0.8734) time: 0.1689 data: 0.0826 max mem: 8452 +Train: [14] [6200/6250] eta: 0:00:08 lr: 0.000122 grad: 0.0786 (0.0803) loss: 0.8708 (0.8734) time: 0.1651 data: 0.0832 max mem: 8452 +Train: [14] [6249/6250] eta: 0:00:00 lr: 0.000122 grad: 0.0758 (0.0803) loss: 0.8694 (0.8734) time: 0.1498 data: 0.0589 max mem: 8452 +Train: [14] Total time: 0:18:10 (0.1745 s / it) +Averaged stats: lr: 0.000122 grad: 0.0758 (0.0803) loss: 0.8694 (0.8734) +Eval (hcp-train-subset): [14] [ 0/62] eta: 0:04:46 loss: 0.8986 (0.8986) time: 4.6228 data: 4.5898 max mem: 8452 +Eval (hcp-train-subset): [14] [61/62] eta: 0:00:00 loss: 0.8889 (0.8891) time: 0.1156 data: 0.0934 max mem: 8452 +Eval (hcp-train-subset): [14] Total time: 0:00:14 (0.2329 s / it) +Averaged stats (hcp-train-subset): loss: 0.8889 (0.8891) +Making plots (hcp-train-subset): example=46 +Eval (hcp-val): [14] [ 0/62] eta: 0:04:25 loss: 0.8832 (0.8832) time: 4.2836 data: 4.1575 max mem: 8452 +Eval (hcp-val): [14] [61/62] eta: 0:00:00 loss: 0.8835 (0.8848) time: 0.1412 data: 0.1132 max mem: 8452 +Eval (hcp-val): [14] Total time: 0:00:13 (0.2234 s / it) +Averaged stats (hcp-val): loss: 0.8835 (0.8848) +Making plots (hcp-val): example=55 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [15] [ 0/6250] eta: 10:24:28 lr: 0.000122 grad: 0.1200 (0.1200) loss: 0.9036 (0.9036) time: 5.9950 data: 5.8480 max mem: 8452 +Train: [15] [ 100/6250] eta: 0:24:31 lr: 0.000122 grad: 0.0880 (0.0945) loss: 0.8768 (0.8837) time: 0.1915 data: 0.1115 max mem: 8452 +Train: [15] [ 200/6250] eta: 0:21:33 lr: 0.000122 grad: 0.0917 (0.1016) loss: 0.8736 (0.8751) time: 0.1759 data: 0.0894 max mem: 8452 +Train: [15] [ 300/6250] eta: 0:20:16 lr: 0.000122 grad: 0.0781 (0.0960) loss: 0.8734 (0.8734) time: 0.2081 data: 0.1223 max mem: 8452 +Train: [15] [ 400/6250] eta: 0:19:45 lr: 0.000122 grad: 0.0822 (0.0933) loss: 0.8800 (0.8731) time: 0.1873 data: 0.0934 max mem: 8452 +Train: [15] [ 500/6250] eta: 0:19:04 lr: 0.000122 grad: 0.0783 (0.0914) loss: 0.8740 (0.8729) time: 0.1871 data: 0.0810 max mem: 8452 +Train: [15] [ 600/6250] eta: 0:18:32 lr: 0.000122 grad: 0.0759 (0.0892) loss: 0.8739 (0.8731) time: 0.2278 data: 0.1418 max mem: 8452 +Train: [15] [ 700/6250] eta: 0:17:46 lr: 0.000122 grad: 0.0738 (0.0876) loss: 0.8695 (0.8732) time: 0.1703 data: 0.0783 max mem: 8452 +Train: [15] [ 800/6250] eta: 0:17:23 lr: 0.000122 grad: 0.0832 (0.0868) loss: 0.8715 (0.8731) time: 0.1309 data: 0.0339 max mem: 8452 +Train: [15] [ 900/6250] eta: 0:17:15 lr: 0.000122 grad: 0.0751 (0.0859) loss: 0.8717 (0.8731) time: 0.1309 data: 0.0002 max mem: 8452 +Train: [15] [1000/6250] eta: 0:16:45 lr: 0.000122 grad: 0.0788 (0.0851) loss: 0.8776 (0.8731) time: 0.1609 data: 0.0819 max mem: 8452 +Train: [15] [1100/6250] eta: 0:16:18 lr: 0.000121 grad: 0.0726 (0.0844) loss: 0.8807 (0.8731) time: 0.1688 data: 0.0933 max mem: 8452 +Train: [15] [1200/6250] eta: 0:15:50 lr: 0.000121 grad: 0.0774 (0.0837) loss: 0.8720 (0.8732) time: 0.1755 data: 0.1033 max mem: 8452 +Train: [15] [1300/6250] eta: 0:15:30 lr: 0.000121 grad: 0.0708 (0.0833) loss: 0.8754 (0.8732) time: 0.2009 data: 0.1287 max mem: 8452 +Train: [15] [1400/6250] eta: 0:15:16 lr: 0.000121 grad: 0.0795 (0.0830) loss: 0.8759 (0.8732) time: 0.2751 data: 0.1693 max mem: 8452 +Train: [15] [1500/6250] eta: 0:14:46 lr: 0.000121 grad: 0.0712 (0.0826) loss: 0.8722 (0.8731) time: 0.1528 data: 0.0786 max mem: 8452 +Train: [15] [1600/6250] eta: 0:14:19 lr: 0.000121 grad: 0.0735 (0.0823) loss: 0.8725 (0.8731) time: 0.1474 data: 0.0636 max mem: 8452 +Train: [15] [1700/6250] eta: 0:13:58 lr: 0.000121 grad: 0.0767 (0.0821) loss: 0.8739 (0.8731) time: 0.1902 data: 0.0902 max mem: 8452 +Train: [15] [1800/6250] eta: 0:13:36 lr: 0.000121 grad: 0.0804 (0.0820) loss: 0.8665 (0.8731) time: 0.1632 data: 0.0823 max mem: 8452 +Train: [15] [1900/6250] eta: 0:13:17 lr: 0.000121 grad: 0.0765 (0.0820) loss: 0.8660 (0.8729) time: 0.1934 data: 0.1216 max mem: 8452 +Train: [15] [2000/6250] eta: 0:13:02 lr: 0.000121 grad: 0.0757 (0.0818) loss: 0.8758 (0.8729) time: 0.1099 data: 0.0165 max mem: 8452 +Train: [15] [2100/6250] eta: 0:12:38 lr: 0.000121 grad: 0.0782 (0.0817) loss: 0.8657 (0.8728) time: 0.1726 data: 0.0990 max mem: 8452 +Train: [15] [2200/6250] eta: 0:12:16 lr: 0.000121 grad: 0.0758 (0.0818) loss: 0.8742 (0.8728) time: 0.1610 data: 0.0784 max mem: 8452 +Train: [15] [2300/6250] eta: 0:11:56 lr: 0.000121 grad: 0.0839 (0.0819) loss: 0.8699 (0.8726) time: 0.1397 data: 0.0552 max mem: 8452 +Train: [15] [2400/6250] eta: 0:11:37 lr: 0.000121 grad: 0.0793 (0.0819) loss: 0.8712 (0.8725) time: 0.2292 data: 0.1349 max mem: 8452 +Train: [15] [2500/6250] eta: 0:11:15 lr: 0.000121 grad: 0.0743 (0.0820) loss: 0.8746 (0.8724) time: 0.1643 data: 0.0795 max mem: 8452 +Train: [15] [2600/6250] eta: 0:10:54 lr: 0.000121 grad: 0.0816 (0.0819) loss: 0.8716 (0.8723) time: 0.1430 data: 0.0667 max mem: 8452 +Train: [15] [2700/6250] eta: 0:10:36 lr: 0.000121 grad: 0.0811 (0.0820) loss: 0.8722 (0.8722) time: 0.1083 data: 0.0130 max mem: 8452 +Train: [15] [2800/6250] eta: 0:10:17 lr: 0.000121 grad: 0.0815 (0.0820) loss: 0.8706 (0.8722) time: 0.1595 data: 0.0698 max mem: 8452 +Train: [15] [2900/6250] eta: 0:10:02 lr: 0.000121 grad: 0.0764 (0.0821) loss: 0.8746 (0.8721) time: 0.3372 data: 0.2629 max mem: 8452 +Train: [15] [3000/6250] eta: 0:09:43 lr: 0.000121 grad: 0.0813 (0.0822) loss: 0.8704 (0.8721) time: 0.1611 data: 0.0704 max mem: 8452 +Train: [15] [3100/6250] eta: 0:09:23 lr: 0.000121 grad: 0.0793 (0.0824) loss: 0.8765 (0.8722) time: 0.1615 data: 0.0867 max mem: 8452 +Train: [15] [3200/6250] eta: 0:09:06 lr: 0.000121 grad: 0.0795 (0.0823) loss: 0.8738 (0.8722) time: 0.2924 data: 0.2096 max mem: 8452 +Train: [15] [3300/6250] eta: 0:08:45 lr: 0.000121 grad: 0.0827 (0.0824) loss: 0.8704 (0.8722) time: 0.1495 data: 0.0718 max mem: 8452 +Train: [15] [3400/6250] eta: 0:08:26 lr: 0.000121 grad: 0.0750 (0.0826) loss: 0.8720 (0.8721) time: 0.1658 data: 0.0844 max mem: 8452 +Train: [15] [3500/6250] eta: 0:08:07 lr: 0.000121 grad: 0.0817 (0.0826) loss: 0.8677 (0.8721) time: 0.1332 data: 0.0456 max mem: 8452 +Train: [15] [3600/6250] eta: 0:07:49 lr: 0.000121 grad: 0.0849 (0.0827) loss: 0.8669 (0.8721) time: 0.1621 data: 0.0870 max mem: 8452 +Train: [15] [3700/6250] eta: 0:07:30 lr: 0.000121 grad: 0.0828 (0.0828) loss: 0.8711 (0.8720) time: 0.1484 data: 0.0642 max mem: 8452 +Train: [15] [3800/6250] eta: 0:07:12 lr: 0.000121 grad: 0.0735 (0.0827) loss: 0.8732 (0.8720) time: 0.1797 data: 0.0975 max mem: 8452 +Train: [15] [3900/6250] eta: 0:06:53 lr: 0.000121 grad: 0.0748 (0.0827) loss: 0.8723 (0.8720) time: 0.1553 data: 0.0866 max mem: 8452 +Train: [15] [4000/6250] eta: 0:06:35 lr: 0.000121 grad: 0.0733 (0.0827) loss: 0.8702 (0.8720) time: 0.2005 data: 0.1336 max mem: 8452 +Train: [15] [4100/6250] eta: 0:06:17 lr: 0.000121 grad: 0.0741 (0.0826) loss: 0.8758 (0.8719) time: 0.1873 data: 0.1104 max mem: 8452 +Train: [15] [4200/6250] eta: 0:06:00 lr: 0.000121 grad: 0.0779 (0.0826) loss: 0.8706 (0.8720) time: 0.2304 data: 0.1456 max mem: 8452 +Train: [15] [4300/6250] eta: 0:05:42 lr: 0.000121 grad: 0.0816 (0.0826) loss: 0.8735 (0.8719) time: 0.1596 data: 0.0768 max mem: 8452 +Train: [15] [4400/6250] eta: 0:05:25 lr: 0.000121 grad: 0.0813 (0.0826) loss: 0.8646 (0.8718) time: 0.1690 data: 0.0917 max mem: 8452 +Train: [15] [4500/6250] eta: 0:05:07 lr: 0.000121 grad: 0.0739 (0.0827) loss: 0.8735 (0.8718) time: 0.1786 data: 0.0987 max mem: 8452 +Train: [15] [4600/6250] eta: 0:04:50 lr: 0.000121 grad: 0.0807 (0.0827) loss: 0.8720 (0.8717) time: 0.1883 data: 0.1037 max mem: 8452 +Train: [15] [4700/6250] eta: 0:04:32 lr: 0.000121 grad: 0.0889 (0.0826) loss: 0.8633 (0.8717) time: 0.1779 data: 0.1033 max mem: 8452 +Train: [15] [4800/6250] eta: 0:04:15 lr: 0.000121 grad: 0.0773 (0.0826) loss: 0.8681 (0.8717) time: 0.1576 data: 0.0502 max mem: 8452 +Train: [15] [4900/6250] eta: 0:03:58 lr: 0.000121 grad: 0.0727 (0.0826) loss: 0.8734 (0.8716) time: 0.2786 data: 0.1999 max mem: 8452 +Train: [15] [5000/6250] eta: 0:03:40 lr: 0.000121 grad: 0.0760 (0.0825) loss: 0.8672 (0.8716) time: 0.1846 data: 0.0997 max mem: 8452 +Train: [15] [5100/6250] eta: 0:03:22 lr: 0.000121 grad: 0.0869 (0.0826) loss: 0.8673 (0.8716) time: 0.2095 data: 0.1355 max mem: 8452 +Train: [15] [5200/6250] eta: 0:03:05 lr: 0.000121 grad: 0.0800 (0.0827) loss: 0.8663 (0.8715) time: 0.1925 data: 0.0957 max mem: 8452 +Train: [15] [5300/6250] eta: 0:02:48 lr: 0.000121 grad: 0.0881 (0.0827) loss: 0.8679 (0.8715) time: 0.2054 data: 0.1312 max mem: 8452 +Train: [15] [5400/6250] eta: 0:02:30 lr: 0.000121 grad: 0.0775 (0.0826) loss: 0.8730 (0.8714) time: 0.1566 data: 0.0912 max mem: 8452 +Train: [15] [5500/6250] eta: 0:02:12 lr: 0.000121 grad: 0.0743 (0.0826) loss: 0.8710 (0.8714) time: 0.1756 data: 0.0919 max mem: 8452 +Train: [15] [5600/6250] eta: 0:01:54 lr: 0.000121 grad: 0.0783 (0.0825) loss: 0.8734 (0.8714) time: 0.1577 data: 0.0819 max mem: 8452 +Train: [15] [5700/6250] eta: 0:01:37 lr: 0.000121 grad: 0.0819 (0.0825) loss: 0.8650 (0.8714) time: 0.1583 data: 0.0749 max mem: 8452 +Train: [15] [5800/6250] eta: 0:01:19 lr: 0.000121 grad: 0.0776 (0.0825) loss: 0.8720 (0.8714) time: 0.1513 data: 0.0639 max mem: 8452 +Train: [15] [5900/6250] eta: 0:01:01 lr: 0.000121 grad: 0.0767 (0.0825) loss: 0.8744 (0.8714) time: 0.1600 data: 0.0715 max mem: 8452 +Train: [15] [6000/6250] eta: 0:00:43 lr: 0.000121 grad: 0.0756 (0.0825) loss: 0.8726 (0.8714) time: 0.1349 data: 0.0391 max mem: 8452 +Train: [15] [6100/6250] eta: 0:00:26 lr: 0.000121 grad: 0.0777 (0.0824) loss: 0.8719 (0.8714) time: 0.1543 data: 0.0681 max mem: 8452 +Train: [15] [6200/6250] eta: 0:00:08 lr: 0.000121 grad: 0.0752 (0.0824) loss: 0.8743 (0.8714) time: 0.2341 data: 0.1619 max mem: 8452 +Train: [15] [6249/6250] eta: 0:00:00 lr: 0.000121 grad: 0.0812 (0.0824) loss: 0.8686 (0.8714) time: 0.1755 data: 0.1018 max mem: 8452 +Train: [15] Total time: 0:18:24 (0.1767 s / it) +Averaged stats: lr: 0.000121 grad: 0.0812 (0.0824) loss: 0.8686 (0.8714) +Eval (hcp-train-subset): [15] [ 0/62] eta: 0:05:14 loss: 0.9000 (0.9000) time: 5.0675 data: 5.0399 max mem: 8452 +Eval (hcp-train-subset): [15] [61/62] eta: 0:00:00 loss: 0.8875 (0.8870) time: 0.1373 data: 0.1140 max mem: 8452 +Eval (hcp-train-subset): [15] Total time: 0:00:14 (0.2328 s / it) +Averaged stats (hcp-train-subset): loss: 0.8875 (0.8870) +Eval (hcp-val): [15] [ 0/62] eta: 0:03:15 loss: 0.8832 (0.8832) time: 3.1610 data: 3.1172 max mem: 8452 +Eval (hcp-val): [15] [61/62] eta: 0:00:00 loss: 0.8842 (0.8847) time: 0.1389 data: 0.1155 max mem: 8452 +Eval (hcp-val): [15] Total time: 0:00:14 (0.2304 s / it) +Averaged stats (hcp-val): loss: 0.8842 (0.8847) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [16] [ 0/6250] eta: 15:31:19 lr: 0.000121 grad: 0.0534 (0.0534) loss: 0.9106 (0.9106) time: 8.9408 data: 8.7218 max mem: 8452 +Train: [16] [ 100/6250] eta: 0:25:03 lr: 0.000121 grad: 0.0884 (0.0847) loss: 0.8731 (0.8898) time: 0.1735 data: 0.0912 max mem: 8452 +Train: [16] [ 200/6250] eta: 0:20:46 lr: 0.000121 grad: 0.0813 (0.0881) loss: 0.8766 (0.8833) time: 0.1835 data: 0.0843 max mem: 8452 +Train: [16] [ 300/6250] eta: 0:19:03 lr: 0.000121 grad: 0.0871 (0.0900) loss: 0.8779 (0.8799) time: 0.1758 data: 0.0824 max mem: 8452 +Train: [16] [ 400/6250] eta: 0:18:38 lr: 0.000121 grad: 0.0727 (0.0880) loss: 0.8837 (0.8787) time: 0.1840 data: 0.0943 max mem: 8452 +Train: [16] [ 500/6250] eta: 0:18:32 lr: 0.000121 grad: 0.0712 (0.0862) loss: 0.8780 (0.8782) time: 0.2422 data: 0.1633 max mem: 8452 +Train: [16] [ 600/6250] eta: 0:17:39 lr: 0.000121 grad: 0.0754 (0.0844) loss: 0.8778 (0.8777) time: 0.1776 data: 0.0918 max mem: 8452 +Train: [16] [ 700/6250] eta: 0:17:08 lr: 0.000121 grad: 0.0701 (0.0833) loss: 0.8781 (0.8773) time: 0.1508 data: 0.0650 max mem: 8452 +Train: [16] [ 800/6250] eta: 0:17:17 lr: 0.000121 grad: 0.0734 (0.0825) loss: 0.8751 (0.8770) time: 0.3113 data: 0.2362 max mem: 8452 +Train: [16] [ 900/6250] eta: 0:17:01 lr: 0.000121 grad: 0.0752 (0.0816) loss: 0.8785 (0.8769) time: 0.2457 data: 0.1525 max mem: 8452 +Train: [16] [1000/6250] eta: 0:16:38 lr: 0.000121 grad: 0.0716 (0.0812) loss: 0.8750 (0.8769) time: 0.0921 data: 0.0002 max mem: 8452 +Train: [16] [1100/6250] eta: 0:16:08 lr: 0.000121 grad: 0.0708 (0.0808) loss: 0.8763 (0.8767) time: 0.1729 data: 0.0796 max mem: 8452 +Train: [16] [1200/6250] eta: 0:15:46 lr: 0.000121 grad: 0.0693 (0.0805) loss: 0.8780 (0.8766) time: 0.1679 data: 0.0787 max mem: 8452 +Train: [16] [1300/6250] eta: 0:15:20 lr: 0.000121 grad: 0.0772 (0.0803) loss: 0.8698 (0.8764) time: 0.1795 data: 0.0961 max mem: 8452 +Train: [16] [1400/6250] eta: 0:14:58 lr: 0.000121 grad: 0.0718 (0.0801) loss: 0.8778 (0.8763) time: 0.1883 data: 0.0886 max mem: 8452 +Train: [16] [1500/6250] eta: 0:14:33 lr: 0.000121 grad: 0.0757 (0.0800) loss: 0.8732 (0.8762) time: 0.1611 data: 0.0811 max mem: 8452 +Train: [16] [1600/6250] eta: 0:14:08 lr: 0.000121 grad: 0.0761 (0.0800) loss: 0.8752 (0.8760) time: 0.1430 data: 0.0623 max mem: 8452 +Train: [16] [1700/6250] eta: 0:13:46 lr: 0.000121 grad: 0.0768 (0.0799) loss: 0.8742 (0.8759) time: 0.1348 data: 0.0516 max mem: 8452 +Train: [16] [1800/6250] eta: 0:13:26 lr: 0.000121 grad: 0.0705 (0.0797) loss: 0.8723 (0.8757) time: 0.1784 data: 0.0965 max mem: 8452 +Train: [16] [1900/6250] eta: 0:13:08 lr: 0.000121 grad: 0.0786 (0.0798) loss: 0.8712 (0.8756) time: 0.1102 data: 0.0003 max mem: 8452 +Train: [16] [2000/6250] eta: 0:12:48 lr: 0.000121 grad: 0.0713 (0.0797) loss: 0.8755 (0.8756) time: 0.1786 data: 0.1032 max mem: 8452 +Train: [16] [2100/6250] eta: 0:12:30 lr: 0.000121 grad: 0.0760 (0.0798) loss: 0.8706 (0.8755) time: 0.2080 data: 0.1240 max mem: 8452 +Train: [16] [2200/6250] eta: 0:12:07 lr: 0.000121 grad: 0.0814 (0.0800) loss: 0.8739 (0.8753) time: 0.1654 data: 0.0868 max mem: 8452 +Train: [16] [2300/6250] eta: 0:11:49 lr: 0.000121 grad: 0.0751 (0.0799) loss: 0.8706 (0.8752) time: 0.1611 data: 0.0797 max mem: 8452 +Train: [16] [2400/6250] eta: 0:11:27 lr: 0.000121 grad: 0.0777 (0.0799) loss: 0.8683 (0.8750) time: 0.1589 data: 0.0788 max mem: 8452 +Train: [16] [2500/6250] eta: 0:11:06 lr: 0.000121 grad: 0.0747 (0.0798) loss: 0.8683 (0.8748) time: 0.1448 data: 0.0571 max mem: 8452 +Train: [16] [2600/6250] eta: 0:10:46 lr: 0.000121 grad: 0.0768 (0.0800) loss: 0.8731 (0.8746) time: 0.1866 data: 0.1107 max mem: 8452 +Train: [16] [2700/6250] eta: 0:10:26 lr: 0.000121 grad: 0.0766 (0.0799) loss: 0.8730 (0.8745) time: 0.1557 data: 0.0789 max mem: 8452 +Train: [16] [2800/6250] eta: 0:10:07 lr: 0.000121 grad: 0.0756 (0.0799) loss: 0.8734 (0.8744) time: 0.1447 data: 0.0743 max mem: 8452 +Train: [16] [2900/6250] eta: 0:09:50 lr: 0.000121 grad: 0.0739 (0.0798) loss: 0.8732 (0.8742) time: 0.1646 data: 0.0785 max mem: 8452 +Train: [16] [3000/6250] eta: 0:09:32 lr: 0.000121 grad: 0.0765 (0.0798) loss: 0.8707 (0.8741) time: 0.1478 data: 0.0719 max mem: 8452 +Train: [16] [3100/6250] eta: 0:09:14 lr: 0.000121 grad: 0.0765 (0.0797) loss: 0.8673 (0.8740) time: 0.1817 data: 0.0845 max mem: 8452 +Train: [16] [3200/6250] eta: 0:08:57 lr: 0.000121 grad: 0.0755 (0.0796) loss: 0.8689 (0.8739) time: 0.1575 data: 0.0662 max mem: 8452 +Train: [16] [3300/6250] eta: 0:08:39 lr: 0.000121 grad: 0.0969 (0.0800) loss: 0.8687 (0.8738) time: 0.1930 data: 0.0625 max mem: 8452 +Train: [16] [3400/6250] eta: 0:08:22 lr: 0.000121 grad: 0.0804 (0.0802) loss: 0.8696 (0.8736) time: 0.1719 data: 0.0873 max mem: 8452 +Train: [16] [3500/6250] eta: 0:08:05 lr: 0.000120 grad: 0.0835 (0.0803) loss: 0.8649 (0.8734) time: 0.1148 data: 0.0003 max mem: 8452 +Train: [16] [3600/6250] eta: 0:07:46 lr: 0.000120 grad: 0.0835 (0.0804) loss: 0.8660 (0.8733) time: 0.1690 data: 0.0804 max mem: 8452 +Train: [16] [3700/6250] eta: 0:07:29 lr: 0.000120 grad: 0.0818 (0.0806) loss: 0.8615 (0.8731) time: 0.2117 data: 0.1193 max mem: 8452 +Train: [16] [3800/6250] eta: 0:07:12 lr: 0.000120 grad: 0.0769 (0.0808) loss: 0.8663 (0.8730) time: 0.1563 data: 0.0533 max mem: 8452 +Train: [16] [3900/6250] eta: 0:06:54 lr: 0.000120 grad: 0.0800 (0.0809) loss: 0.8698 (0.8728) time: 0.1851 data: 0.0974 max mem: 8452 +Train: [16] [4000/6250] eta: 0:06:38 lr: 0.000120 grad: 0.0724 (0.0811) loss: 0.8729 (0.8727) time: 0.1003 data: 0.0141 max mem: 8452 +Train: [16] [4100/6250] eta: 0:06:19 lr: 0.000120 grad: 0.0732 (0.0811) loss: 0.8726 (0.8725) time: 0.1696 data: 0.0904 max mem: 8452 +Train: [16] [4200/6250] eta: 0:06:01 lr: 0.000120 grad: 0.0811 (0.0811) loss: 0.8706 (0.8725) time: 0.1435 data: 0.0620 max mem: 8452 +Train: [16] [4300/6250] eta: 0:05:42 lr: 0.000120 grad: 0.0860 (0.0812) loss: 0.8649 (0.8723) time: 0.1469 data: 0.0660 max mem: 8452 +Train: [16] [4400/6250] eta: 0:05:24 lr: 0.000120 grad: 0.0740 (0.0812) loss: 0.8732 (0.8723) time: 0.1567 data: 0.0722 max mem: 8452 +Train: [16] [4500/6250] eta: 0:05:06 lr: 0.000120 grad: 0.0820 (0.0812) loss: 0.8744 (0.8722) time: 0.1676 data: 0.0876 max mem: 8452 +Train: [16] [4600/6250] eta: 0:04:48 lr: 0.000120 grad: 0.0781 (0.0812) loss: 0.8700 (0.8722) time: 0.1503 data: 0.0757 max mem: 8452 +Train: [16] [4700/6250] eta: 0:04:30 lr: 0.000120 grad: 0.0753 (0.0812) loss: 0.8733 (0.8722) time: 0.1329 data: 0.0417 max mem: 8452 +Train: [16] [4800/6250] eta: 0:04:12 lr: 0.000120 grad: 0.0764 (0.0812) loss: 0.8746 (0.8722) time: 0.1562 data: 0.0801 max mem: 8452 +Train: [16] [4900/6250] eta: 0:03:54 lr: 0.000120 grad: 0.0716 (0.0811) loss: 0.8730 (0.8722) time: 0.1382 data: 0.0555 max mem: 8452 +Train: [16] [5000/6250] eta: 0:03:37 lr: 0.000120 grad: 0.0766 (0.0811) loss: 0.8740 (0.8722) time: 0.1337 data: 0.0291 max mem: 8452 +Train: [16] [5100/6250] eta: 0:03:20 lr: 0.000120 grad: 0.0763 (0.0811) loss: 0.8751 (0.8722) time: 0.2207 data: 0.1521 max mem: 8452 +Train: [16] [5200/6250] eta: 0:03:03 lr: 0.000120 grad: 0.0808 (0.0811) loss: 0.8708 (0.8722) time: 0.1743 data: 0.1021 max mem: 8452 +Train: [16] [5300/6250] eta: 0:02:46 lr: 0.000120 grad: 0.0785 (0.0811) loss: 0.8735 (0.8721) time: 0.1810 data: 0.1114 max mem: 8452 +Train: [16] [5400/6250] eta: 0:02:28 lr: 0.000120 grad: 0.0724 (0.0810) loss: 0.8762 (0.8721) time: 0.1681 data: 0.0811 max mem: 8452 +Train: [16] [5500/6250] eta: 0:02:11 lr: 0.000120 grad: 0.0735 (0.0811) loss: 0.8777 (0.8721) time: 0.1516 data: 0.0610 max mem: 8452 +Train: [16] [5600/6250] eta: 0:01:53 lr: 0.000120 grad: 0.0778 (0.0810) loss: 0.8714 (0.8721) time: 0.1506 data: 0.0621 max mem: 8452 +Train: [16] [5700/6250] eta: 0:01:36 lr: 0.000120 grad: 0.0804 (0.0810) loss: 0.8672 (0.8721) time: 0.1804 data: 0.1044 max mem: 8452 +Train: [16] [5800/6250] eta: 0:01:18 lr: 0.000120 grad: 0.0800 (0.0810) loss: 0.8757 (0.8722) time: 0.1731 data: 0.0883 max mem: 8452 +Train: [16] [5900/6250] eta: 0:01:00 lr: 0.000120 grad: 0.0728 (0.0809) loss: 0.8749 (0.8722) time: 0.1396 data: 0.0438 max mem: 8452 +Train: [16] [6000/6250] eta: 0:00:43 lr: 0.000120 grad: 0.0783 (0.0809) loss: 0.8698 (0.8722) time: 0.1544 data: 0.0717 max mem: 8452 +Train: [16] [6100/6250] eta: 0:00:26 lr: 0.000120 grad: 0.0773 (0.0809) loss: 0.8703 (0.8722) time: 0.1309 data: 0.0390 max mem: 8452 +Train: [16] [6200/6250] eta: 0:00:08 lr: 0.000120 grad: 0.0762 (0.0809) loss: 0.8764 (0.8722) time: 0.2951 data: 0.1883 max mem: 8452 +Train: [16] [6249/6250] eta: 0:00:00 lr: 0.000120 grad: 0.0793 (0.0809) loss: 0.8734 (0.8722) time: 0.1607 data: 0.0731 max mem: 8452 +Train: [16] Total time: 0:18:15 (0.1753 s / it) +Averaged stats: lr: 0.000120 grad: 0.0793 (0.0809) loss: 0.8734 (0.8722) +Eval (hcp-train-subset): [16] [ 0/62] eta: 0:04:32 loss: 0.9005 (0.9005) time: 4.3970 data: 4.3179 max mem: 8452 +Eval (hcp-train-subset): [16] [61/62] eta: 0:00:00 loss: 0.8851 (0.8869) time: 0.1340 data: 0.1129 max mem: 8452 +Eval (hcp-train-subset): [16] Total time: 0:00:14 (0.2335 s / it) +Averaged stats (hcp-train-subset): loss: 0.8851 (0.8869) +Eval (hcp-val): [16] [ 0/62] eta: 0:05:28 loss: 0.8822 (0.8822) time: 5.2992 data: 5.2731 max mem: 8452 +Eval (hcp-val): [16] [61/62] eta: 0:00:00 loss: 0.8828 (0.8839) time: 0.1471 data: 0.1205 max mem: 8452 +Eval (hcp-val): [16] Total time: 0:00:14 (0.2301 s / it) +Averaged stats (hcp-val): loss: 0.8828 (0.8839) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [17] [ 0/6250] eta: 8:19:24 lr: 0.000120 grad: 0.0565 (0.0565) loss: 0.9129 (0.9129) time: 4.7943 data: 4.5470 max mem: 8452 +Train: [17] [ 100/6250] eta: 0:23:45 lr: 0.000120 grad: 0.0971 (0.1124) loss: 0.8733 (0.8809) time: 0.2100 data: 0.1200 max mem: 8452 +Train: [17] [ 200/6250] eta: 0:20:25 lr: 0.000120 grad: 0.0854 (0.0994) loss: 0.8700 (0.8764) time: 0.1717 data: 0.0923 max mem: 8452 +Train: [17] [ 300/6250] eta: 0:18:55 lr: 0.000120 grad: 0.0842 (0.0943) loss: 0.8635 (0.8740) time: 0.1657 data: 0.0736 max mem: 8452 +Train: [17] [ 400/6250] eta: 0:17:57 lr: 0.000120 grad: 0.0910 (0.0933) loss: 0.8678 (0.8724) time: 0.1933 data: 0.1052 max mem: 8452 +Train: [17] [ 500/6250] eta: 0:17:19 lr: 0.000120 grad: 0.0747 (0.0908) loss: 0.8635 (0.8715) time: 0.1511 data: 0.0701 max mem: 8452 +Train: [17] [ 600/6250] eta: 0:16:46 lr: 0.000120 grad: 0.0764 (0.0906) loss: 0.8678 (0.8716) time: 0.1765 data: 0.0840 max mem: 8452 +Train: [17] [ 700/6250] eta: 0:16:11 lr: 0.000120 grad: 0.0768 (0.0887) loss: 0.8705 (0.8710) time: 0.1454 data: 0.0596 max mem: 8452 +Train: [17] [ 800/6250] eta: 0:15:54 lr: 0.000120 grad: 0.0761 (0.0875) loss: 0.8720 (0.8711) time: 0.2198 data: 0.1288 max mem: 8452 +Train: [17] [ 900/6250] eta: 0:15:35 lr: 0.000120 grad: 0.0764 (0.0866) loss: 0.8733 (0.8709) time: 0.1520 data: 0.0657 max mem: 8452 +Train: [17] [1000/6250] eta: 0:15:16 lr: 0.000120 grad: 0.0735 (0.0861) loss: 0.8759 (0.8710) time: 0.1757 data: 0.0924 max mem: 8452 +Train: [17] [1100/6250] eta: 0:15:04 lr: 0.000120 grad: 0.0734 (0.0854) loss: 0.8687 (0.8708) time: 0.1252 data: 0.0227 max mem: 8452 +Train: [17] [1200/6250] eta: 0:14:47 lr: 0.000120 grad: 0.0748 (0.0851) loss: 0.8618 (0.8704) time: 0.1881 data: 0.0808 max mem: 8452 +Train: [17] [1300/6250] eta: 0:14:38 lr: 0.000120 grad: 0.0747 (0.0846) loss: 0.8694 (0.8702) time: 0.1381 data: 0.0385 max mem: 8452 +Train: [17] [1400/6250] eta: 0:14:26 lr: 0.000120 grad: 0.0796 (0.0843) loss: 0.8668 (0.8698) time: 0.2602 data: 0.1782 max mem: 8452 +Train: [17] [1500/6250] eta: 0:13:58 lr: 0.000120 grad: 0.0762 (0.0842) loss: 0.8680 (0.8694) time: 0.1434 data: 0.0694 max mem: 8452 +Train: [17] [1600/6250] eta: 0:13:37 lr: 0.000120 grad: 0.0772 (0.0839) loss: 0.8710 (0.8692) time: 0.1799 data: 0.1042 max mem: 8452 +Train: [17] [1700/6250] eta: 0:13:16 lr: 0.000120 grad: 0.0779 (0.0838) loss: 0.8669 (0.8689) time: 0.1598 data: 0.0800 max mem: 8452 +Train: [17] [1800/6250] eta: 0:12:56 lr: 0.000120 grad: 0.0799 (0.0836) loss: 0.8683 (0.8688) time: 0.1751 data: 0.0867 max mem: 8452 +Train: [17] [1900/6250] eta: 0:12:39 lr: 0.000120 grad: 0.0843 (0.0835) loss: 0.8677 (0.8686) time: 0.1694 data: 0.0838 max mem: 8452 +Train: [17] [2000/6250] eta: 0:12:19 lr: 0.000120 grad: 0.0766 (0.0833) loss: 0.8651 (0.8683) time: 0.1797 data: 0.1039 max mem: 8452 +Train: [17] [2100/6250] eta: 0:11:59 lr: 0.000120 grad: 0.0821 (0.0834) loss: 0.8635 (0.8681) time: 0.1152 data: 0.0173 max mem: 8452 +Train: [17] [2200/6250] eta: 0:11:43 lr: 0.000120 grad: 0.0774 (0.0833) loss: 0.8608 (0.8679) time: 0.1383 data: 0.0344 max mem: 8452 +Train: [17] [2300/6250] eta: 0:11:21 lr: 0.000120 grad: 0.0842 (0.0835) loss: 0.8694 (0.8676) time: 0.1499 data: 0.0723 max mem: 8452 +Train: [17] [2400/6250] eta: 0:11:04 lr: 0.000120 grad: 0.0800 (0.0835) loss: 0.8663 (0.8675) time: 0.1867 data: 0.1136 max mem: 8452 +Train: [17] [2500/6250] eta: 0:10:50 lr: 0.000120 grad: 0.0756 (0.0835) loss: 0.8604 (0.8673) time: 0.3125 data: 0.2233 max mem: 8452 +Train: [17] [2600/6250] eta: 0:10:30 lr: 0.000120 grad: 0.0796 (0.0836) loss: 0.8620 (0.8671) time: 0.1385 data: 0.0678 max mem: 8452 +Train: [17] [2700/6250] eta: 0:10:11 lr: 0.000120 grad: 0.0814 (0.0838) loss: 0.8632 (0.8668) time: 0.1564 data: 0.0774 max mem: 8452 +Train: [17] [2800/6250] eta: 0:09:53 lr: 0.000120 grad: 0.0816 (0.0838) loss: 0.8596 (0.8666) time: 0.1153 data: 0.0214 max mem: 8452 +Train: [17] [2900/6250] eta: 0:09:36 lr: 0.000120 grad: 0.0758 (0.0838) loss: 0.8629 (0.8664) time: 0.1755 data: 0.0822 max mem: 8452 +Train: [17] [3000/6250] eta: 0:09:18 lr: 0.000120 grad: 0.0772 (0.0838) loss: 0.8649 (0.8664) time: 0.1663 data: 0.0787 max mem: 8452 +Train: [17] [3100/6250] eta: 0:09:05 lr: 0.000120 grad: 0.0757 (0.0838) loss: 0.8670 (0.8663) time: 0.3041 data: 0.2034 max mem: 8452 +Train: [17] [3200/6250] eta: 0:08:45 lr: 0.000120 grad: 0.0816 (0.0838) loss: 0.8590 (0.8662) time: 0.1385 data: 0.0493 max mem: 8452 +Train: [17] [3300/6250] eta: 0:08:28 lr: 0.000120 grad: 0.0822 (0.0838) loss: 0.8680 (0.8661) time: 0.1663 data: 0.0804 max mem: 8452 +Train: [17] [3400/6250] eta: 0:08:12 lr: 0.000120 grad: 0.0779 (0.0839) loss: 0.8635 (0.8659) time: 0.1073 data: 0.0002 max mem: 8452 +Train: [17] [3500/6250] eta: 0:07:54 lr: 0.000120 grad: 0.0808 (0.0839) loss: 0.8573 (0.8658) time: 0.1106 data: 0.0250 max mem: 8452 +Train: [17] [3600/6250] eta: 0:07:37 lr: 0.000120 grad: 0.0854 (0.0840) loss: 0.8635 (0.8656) time: 0.1574 data: 0.0603 max mem: 8452 +Train: [17] [3700/6250] eta: 0:07:21 lr: 0.000120 grad: 0.0818 (0.0840) loss: 0.8627 (0.8655) time: 0.1025 data: 0.0003 max mem: 8452 +Train: [17] [3800/6250] eta: 0:07:03 lr: 0.000120 grad: 0.0767 (0.0840) loss: 0.8595 (0.8654) time: 0.1616 data: 0.0885 max mem: 8452 +Train: [17] [3900/6250] eta: 0:06:47 lr: 0.000120 grad: 0.0793 (0.0841) loss: 0.8725 (0.8654) time: 0.0886 data: 0.0002 max mem: 8452 +Train: [17] [4000/6250] eta: 0:06:29 lr: 0.000120 grad: 0.0813 (0.0841) loss: 0.8672 (0.8654) time: 0.2212 data: 0.1360 max mem: 8452 +Train: [17] [4100/6250] eta: 0:06:11 lr: 0.000120 grad: 0.0795 (0.0841) loss: 0.8654 (0.8654) time: 0.1591 data: 0.0766 max mem: 8452 +Train: [17] [4200/6250] eta: 0:05:53 lr: 0.000120 grad: 0.0770 (0.0842) loss: 0.8660 (0.8653) time: 0.1981 data: 0.1153 max mem: 8452 +Train: [17] [4300/6250] eta: 0:05:35 lr: 0.000120 grad: 0.0772 (0.0842) loss: 0.8636 (0.8653) time: 0.1468 data: 0.0601 max mem: 8452 +Train: [17] [4400/6250] eta: 0:05:20 lr: 0.000120 grad: 0.0744 (0.0841) loss: 0.8643 (0.8653) time: 0.1806 data: 0.0889 max mem: 8452 +Train: [17] [4500/6250] eta: 0:05:01 lr: 0.000120 grad: 0.0807 (0.0841) loss: 0.8610 (0.8653) time: 0.1263 data: 0.0617 max mem: 8452 +Train: [17] [4600/6250] eta: 0:04:44 lr: 0.000120 grad: 0.0814 (0.0841) loss: 0.8656 (0.8653) time: 0.1819 data: 0.1048 max mem: 8452 +Train: [17] [4700/6250] eta: 0:04:27 lr: 0.000120 grad: 0.0798 (0.0841) loss: 0.8617 (0.8653) time: 0.1834 data: 0.1085 max mem: 8452 +Train: [17] [4800/6250] eta: 0:04:10 lr: 0.000120 grad: 0.0744 (0.0840) loss: 0.8741 (0.8654) time: 0.1750 data: 0.0965 max mem: 8452 +Train: [17] [4900/6250] eta: 0:03:53 lr: 0.000119 grad: 0.0830 (0.0841) loss: 0.8676 (0.8654) time: 0.2030 data: 0.1237 max mem: 8452 +Train: [17] [5000/6250] eta: 0:03:36 lr: 0.000119 grad: 0.0732 (0.0841) loss: 0.8679 (0.8655) time: 0.2588 data: 0.1980 max mem: 8452 +Train: [17] [5100/6250] eta: 0:03:19 lr: 0.000119 grad: 0.0761 (0.0841) loss: 0.8709 (0.8655) time: 0.1905 data: 0.1144 max mem: 8452 +Train: [17] [5200/6250] eta: 0:03:01 lr: 0.000119 grad: 0.0783 (0.0841) loss: 0.8658 (0.8656) time: 0.1822 data: 0.1043 max mem: 8452 +Train: [17] [5300/6250] eta: 0:02:44 lr: 0.000119 grad: 0.0743 (0.0840) loss: 0.8687 (0.8656) time: 0.1671 data: 0.0755 max mem: 8452 +Train: [17] [5400/6250] eta: 0:02:27 lr: 0.000119 grad: 0.0751 (0.0840) loss: 0.8721 (0.8656) time: 0.1975 data: 0.1134 max mem: 8452 +Train: [17] [5500/6250] eta: 0:02:10 lr: 0.000119 grad: 0.0777 (0.0840) loss: 0.8682 (0.8657) time: 0.1916 data: 0.1050 max mem: 8452 +Train: [17] [5600/6250] eta: 0:01:53 lr: 0.000119 grad: 0.0784 (0.0840) loss: 0.8664 (0.8657) time: 0.1849 data: 0.0932 max mem: 8452 +Train: [17] [5700/6250] eta: 0:01:35 lr: 0.000119 grad: 0.0800 (0.0839) loss: 0.8692 (0.8658) time: 0.1829 data: 0.1003 max mem: 8452 +Train: [17] [5800/6250] eta: 0:01:18 lr: 0.000119 grad: 0.0778 (0.0840) loss: 0.8713 (0.8659) time: 0.1978 data: 0.0942 max mem: 8452 +Train: [17] [5900/6250] eta: 0:01:01 lr: 0.000119 grad: 0.0896 (0.0840) loss: 0.8674 (0.8659) time: 0.1611 data: 0.0535 max mem: 8452 +Train: [17] [6000/6250] eta: 0:00:43 lr: 0.000119 grad: 0.0852 (0.0841) loss: 0.8615 (0.8659) time: 0.1124 data: 0.0003 max mem: 8452 +Train: [17] [6100/6250] eta: 0:00:26 lr: 0.000119 grad: 0.0799 (0.0841) loss: 0.8668 (0.8660) time: 0.2073 data: 0.1303 max mem: 8452 +Train: [17] [6200/6250] eta: 0:00:08 lr: 0.000119 grad: 0.0853 (0.0842) loss: 0.8674 (0.8659) time: 0.1781 data: 0.0900 max mem: 8452 +Train: [17] [6249/6250] eta: 0:00:00 lr: 0.000119 grad: 0.0727 (0.0842) loss: 0.8651 (0.8659) time: 0.1353 data: 0.0211 max mem: 8452 +Train: [17] Total time: 0:18:23 (0.1765 s / it) +Averaged stats: lr: 0.000119 grad: 0.0727 (0.0842) loss: 0.8651 (0.8659) +Eval (hcp-train-subset): [17] [ 0/62] eta: 0:06:10 loss: 0.8987 (0.8987) time: 5.9721 data: 5.9445 max mem: 8452 +Eval (hcp-train-subset): [17] [61/62] eta: 0:00:00 loss: 0.8858 (0.8872) time: 0.1541 data: 0.1325 max mem: 8452 +Eval (hcp-train-subset): [17] Total time: 0:00:15 (0.2543 s / it) +Averaged stats (hcp-train-subset): loss: 0.8858 (0.8872) +Eval (hcp-val): [17] [ 0/62] eta: 0:03:28 loss: 0.8844 (0.8844) time: 3.3614 data: 3.2651 max mem: 8452 +Eval (hcp-val): [17] [61/62] eta: 0:00:00 loss: 0.8830 (0.8842) time: 0.1514 data: 0.1295 max mem: 8452 +Eval (hcp-val): [17] Total time: 0:00:14 (0.2369 s / it) +Averaged stats (hcp-val): loss: 0.8830 (0.8842) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [18] [ 0/6250] eta: 8:36:48 lr: 0.000119 grad: 0.0793 (0.0793) loss: 0.9132 (0.9132) time: 4.9613 data: 4.7272 max mem: 8452 +Train: [18] [ 100/6250] eta: 0:22:48 lr: 0.000119 grad: 0.0856 (0.0974) loss: 0.8758 (0.8806) time: 0.1643 data: 0.0698 max mem: 8452 +Train: [18] [ 200/6250] eta: 0:20:00 lr: 0.000119 grad: 0.0886 (0.0995) loss: 0.8645 (0.8755) time: 0.1742 data: 0.0822 max mem: 8452 +Train: [18] [ 300/6250] eta: 0:18:31 lr: 0.000119 grad: 0.0913 (0.0989) loss: 0.8651 (0.8730) time: 0.1178 data: 0.0368 max mem: 8452 +Train: [18] [ 400/6250] eta: 0:17:39 lr: 0.000119 grad: 0.0668 (0.0954) loss: 0.8743 (0.8726) time: 0.1696 data: 0.0921 max mem: 8452 +Train: [18] [ 500/6250] eta: 0:17:03 lr: 0.000119 grad: 0.0820 (0.0918) loss: 0.8764 (0.8730) time: 0.1850 data: 0.0981 max mem: 8452 +Train: [18] [ 600/6250] eta: 0:16:33 lr: 0.000119 grad: 0.0757 (0.0884) loss: 0.8691 (0.8734) time: 0.1528 data: 0.0646 max mem: 8452 +Train: [18] [ 700/6250] eta: 0:16:04 lr: 0.000119 grad: 0.0737 (0.0864) loss: 0.8743 (0.8735) time: 0.1475 data: 0.0640 max mem: 8452 +Train: [18] [ 800/6250] eta: 0:15:29 lr: 0.000119 grad: 0.0732 (0.0851) loss: 0.8713 (0.8733) time: 0.1364 data: 0.0349 max mem: 8452 +Train: [18] [ 900/6250] eta: 0:15:02 lr: 0.000119 grad: 0.0662 (0.0837) loss: 0.8775 (0.8735) time: 0.1483 data: 0.0530 max mem: 8452 +Train: [18] [1000/6250] eta: 0:14:45 lr: 0.000119 grad: 0.0694 (0.0826) loss: 0.8774 (0.8735) time: 0.1893 data: 0.0970 max mem: 8452 +Train: [18] [1100/6250] eta: 0:14:34 lr: 0.000119 grad: 0.0667 (0.0817) loss: 0.8776 (0.8733) time: 0.1462 data: 0.0337 max mem: 8452 +Train: [18] [1200/6250] eta: 0:14:25 lr: 0.000119 grad: 0.0698 (0.0811) loss: 0.8681 (0.8733) time: 0.1501 data: 0.0407 max mem: 8452 +Train: [18] [1300/6250] eta: 0:14:08 lr: 0.000119 grad: 0.0685 (0.0805) loss: 0.8718 (0.8733) time: 0.1799 data: 0.0987 max mem: 8452 +Train: [18] [1400/6250] eta: 0:13:56 lr: 0.000119 grad: 0.0711 (0.0802) loss: 0.8706 (0.8732) time: 0.1122 data: 0.0003 max mem: 8452 +Train: [18] [1500/6250] eta: 0:13:39 lr: 0.000119 grad: 0.0739 (0.0798) loss: 0.8725 (0.8730) time: 0.1798 data: 0.0949 max mem: 8452 +Train: [18] [1600/6250] eta: 0:13:25 lr: 0.000119 grad: 0.0761 (0.0795) loss: 0.8673 (0.8728) time: 0.1393 data: 0.0333 max mem: 8452 +Train: [18] [1700/6250] eta: 0:13:05 lr: 0.000119 grad: 0.0775 (0.0793) loss: 0.8688 (0.8726) time: 0.1615 data: 0.0743 max mem: 8452 +Train: [18] [1800/6250] eta: 0:12:48 lr: 0.000119 grad: 0.0782 (0.0793) loss: 0.8667 (0.8725) time: 0.1711 data: 0.0809 max mem: 8452 +Train: [18] [1900/6250] eta: 0:12:32 lr: 0.000119 grad: 0.0736 (0.0793) loss: 0.8693 (0.8723) time: 0.1922 data: 0.1082 max mem: 8452 +Train: [18] [2000/6250] eta: 0:12:14 lr: 0.000119 grad: 0.0767 (0.0792) loss: 0.8653 (0.8720) time: 0.1910 data: 0.0998 max mem: 8452 +Train: [18] [2100/6250] eta: 0:12:05 lr: 0.000119 grad: 0.0764 (0.0793) loss: 0.8694 (0.8718) time: 0.1198 data: 0.0003 max mem: 8452 +Train: [18] [2200/6250] eta: 0:11:47 lr: 0.000119 grad: 0.0796 (0.0793) loss: 0.8646 (0.8716) time: 0.1770 data: 0.0898 max mem: 8452 +Train: [18] [2300/6250] eta: 0:11:27 lr: 0.000119 grad: 0.0801 (0.0794) loss: 0.8707 (0.8714) time: 0.1574 data: 0.0681 max mem: 8452 +Train: [18] [2400/6250] eta: 0:11:07 lr: 0.000119 grad: 0.0774 (0.0794) loss: 0.8652 (0.8712) time: 0.1558 data: 0.0802 max mem: 8452 +Train: [18] [2500/6250] eta: 0:10:49 lr: 0.000119 grad: 0.0727 (0.0794) loss: 0.8679 (0.8711) time: 0.1206 data: 0.0214 max mem: 8452 +Train: [18] [2600/6250] eta: 0:10:31 lr: 0.000119 grad: 0.0782 (0.0794) loss: 0.8763 (0.8710) time: 0.1467 data: 0.0674 max mem: 8452 +Train: [18] [2700/6250] eta: 0:10:13 lr: 0.000119 grad: 0.0855 (0.0796) loss: 0.8731 (0.8709) time: 0.1684 data: 0.0887 max mem: 8452 +Train: [18] [2800/6250] eta: 0:09:59 lr: 0.000119 grad: 0.0793 (0.0797) loss: 0.8680 (0.8707) time: 0.1703 data: 0.0778 max mem: 8452 +Train: [18] [2900/6250] eta: 0:09:41 lr: 0.000119 grad: 0.0750 (0.0796) loss: 0.8710 (0.8706) time: 0.1728 data: 0.0935 max mem: 8452 +Train: [18] [3000/6250] eta: 0:09:23 lr: 0.000119 grad: 0.0768 (0.0797) loss: 0.8761 (0.8704) time: 0.1356 data: 0.0496 max mem: 8452 +Train: [18] [3100/6250] eta: 0:09:05 lr: 0.000119 grad: 0.0846 (0.0799) loss: 0.8656 (0.8703) time: 0.1366 data: 0.0471 max mem: 8452 +Train: [18] [3200/6250] eta: 0:08:47 lr: 0.000119 grad: 0.0752 (0.0800) loss: 0.8693 (0.8703) time: 0.1649 data: 0.0874 max mem: 8452 +Train: [18] [3300/6250] eta: 0:08:30 lr: 0.000119 grad: 0.0760 (0.0800) loss: 0.8676 (0.8702) time: 0.1623 data: 0.0753 max mem: 8452 +Train: [18] [3400/6250] eta: 0:08:12 lr: 0.000119 grad: 0.0794 (0.0801) loss: 0.8630 (0.8701) time: 0.1556 data: 0.0842 max mem: 8452 +Train: [18] [3500/6250] eta: 0:07:54 lr: 0.000119 grad: 0.0794 (0.0802) loss: 0.8707 (0.8700) time: 0.1643 data: 0.0868 max mem: 8452 +Train: [18] [3600/6250] eta: 0:07:37 lr: 0.000119 grad: 0.0768 (0.0803) loss: 0.8705 (0.8699) time: 0.2741 data: 0.1955 max mem: 8452 +Train: [18] [3700/6250] eta: 0:07:23 lr: 0.000119 grad: 0.0847 (0.0804) loss: 0.8645 (0.8698) time: 0.4170 data: 0.3305 max mem: 8452 +Train: [18] [3800/6250] eta: 0:07:05 lr: 0.000119 grad: 0.0757 (0.0804) loss: 0.8707 (0.8697) time: 0.1738 data: 0.0422 max mem: 8452 +Train: [18] [3900/6250] eta: 0:06:47 lr: 0.000119 grad: 0.0812 (0.0806) loss: 0.8753 (0.8696) time: 0.1266 data: 0.0513 max mem: 8452 +Train: [18] [4000/6250] eta: 0:06:29 lr: 0.000119 grad: 0.0771 (0.0807) loss: 0.8669 (0.8694) time: 0.1375 data: 0.0471 max mem: 8452 +Train: [18] [4100/6250] eta: 0:06:11 lr: 0.000119 grad: 0.0784 (0.0807) loss: 0.8661 (0.8693) time: 0.1522 data: 0.0788 max mem: 8452 +Train: [18] [4200/6250] eta: 0:05:54 lr: 0.000119 grad: 0.0809 (0.0808) loss: 0.8661 (0.8693) time: 0.1647 data: 0.0784 max mem: 8452 +Train: [18] [4300/6250] eta: 0:05:37 lr: 0.000119 grad: 0.0808 (0.0808) loss: 0.8692 (0.8692) time: 0.1789 data: 0.1013 max mem: 8452 +Train: [18] [4400/6250] eta: 0:05:20 lr: 0.000119 grad: 0.0899 (0.0810) loss: 0.8631 (0.8691) time: 0.1757 data: 0.0802 max mem: 8452 +Train: [18] [4500/6250] eta: 0:05:02 lr: 0.000119 grad: 0.0854 (0.0811) loss: 0.8605 (0.8690) time: 0.1628 data: 0.0952 max mem: 8452 +Train: [18] [4600/6250] eta: 0:04:44 lr: 0.000119 grad: 0.0893 (0.0812) loss: 0.8594 (0.8689) time: 0.1614 data: 0.0805 max mem: 8452 +Train: [18] [4700/6250] eta: 0:04:26 lr: 0.000119 grad: 0.0795 (0.0813) loss: 0.8716 (0.8688) time: 0.1698 data: 0.0975 max mem: 8452 +Train: [18] [4800/6250] eta: 0:04:09 lr: 0.000119 grad: 0.0880 (0.0814) loss: 0.8627 (0.8688) time: 0.1674 data: 0.0918 max mem: 8452 +Train: [18] [4900/6250] eta: 0:03:52 lr: 0.000119 grad: 0.0782 (0.0814) loss: 0.8641 (0.8687) time: 0.1741 data: 0.0890 max mem: 8452 +Train: [18] [5000/6250] eta: 0:03:35 lr: 0.000119 grad: 0.0830 (0.0815) loss: 0.8655 (0.8687) time: 0.1844 data: 0.1066 max mem: 8452 +Train: [18] [5100/6250] eta: 0:03:18 lr: 0.000119 grad: 0.0801 (0.0815) loss: 0.8635 (0.8686) time: 0.1789 data: 0.1042 max mem: 8452 +Train: [18] [5200/6250] eta: 0:03:00 lr: 0.000119 grad: 0.0735 (0.0816) loss: 0.8650 (0.8686) time: 0.1814 data: 0.1051 max mem: 8452 +Train: [18] [5300/6250] eta: 0:02:43 lr: 0.000119 grad: 0.0744 (0.0816) loss: 0.8634 (0.8686) time: 0.1594 data: 0.0785 max mem: 8452 +Train: [18] [5400/6250] eta: 0:02:26 lr: 0.000119 grad: 0.0838 (0.0817) loss: 0.8675 (0.8686) time: 0.1728 data: 0.0838 max mem: 8452 +Train: [18] [5500/6250] eta: 0:02:08 lr: 0.000119 grad: 0.0863 (0.0817) loss: 0.8709 (0.8685) time: 0.1274 data: 0.0349 max mem: 8452 +Train: [18] [5600/6250] eta: 0:01:51 lr: 0.000119 grad: 0.0851 (0.0818) loss: 0.8588 (0.8685) time: 0.1538 data: 0.0729 max mem: 8452 +Train: [18] [5700/6250] eta: 0:01:34 lr: 0.000119 grad: 0.0818 (0.0818) loss: 0.8688 (0.8685) time: 0.1428 data: 0.0555 max mem: 8452 +Train: [18] [5800/6250] eta: 0:01:16 lr: 0.000118 grad: 0.0777 (0.0818) loss: 0.8650 (0.8685) time: 0.1474 data: 0.0581 max mem: 8452 +Train: [18] [5900/6250] eta: 0:00:59 lr: 0.000118 grad: 0.0856 (0.0818) loss: 0.8681 (0.8685) time: 0.1729 data: 0.0998 max mem: 8452 +Train: [18] [6000/6250] eta: 0:00:42 lr: 0.000118 grad: 0.0741 (0.0818) loss: 0.8614 (0.8684) time: 0.1415 data: 0.0691 max mem: 8452 +Train: [18] [6100/6250] eta: 0:00:25 lr: 0.000118 grad: 0.0827 (0.0818) loss: 0.8655 (0.8683) time: 0.1745 data: 0.0683 max mem: 8452 +Train: [18] [6200/6250] eta: 0:00:08 lr: 0.000118 grad: 0.0826 (0.0818) loss: 0.8646 (0.8683) time: 0.1722 data: 0.0781 max mem: 8452 +Train: [18] [6249/6250] eta: 0:00:00 lr: 0.000118 grad: 0.0807 (0.0818) loss: 0.8646 (0.8683) time: 0.1763 data: 0.0833 max mem: 8452 +Train: [18] Total time: 0:17:56 (0.1723 s / it) +Averaged stats: lr: 0.000118 grad: 0.0807 (0.0818) loss: 0.8646 (0.8683) +Eval (hcp-train-subset): [18] [ 0/62] eta: 0:05:29 loss: 0.8958 (0.8958) time: 5.3161 data: 5.2105 max mem: 8452 +Eval (hcp-train-subset): [18] [61/62] eta: 0:00:00 loss: 0.8844 (0.8854) time: 0.1610 data: 0.1397 max mem: 8452 +Eval (hcp-train-subset): [18] Total time: 0:00:16 (0.2598 s / it) +Averaged stats (hcp-train-subset): loss: 0.8844 (0.8854) +Eval (hcp-val): [18] [ 0/62] eta: 0:04:25 loss: 0.8801 (0.8801) time: 4.2784 data: 4.2036 max mem: 8452 +Eval (hcp-val): [18] [61/62] eta: 0:00:00 loss: 0.8810 (0.8834) time: 0.1325 data: 0.1098 max mem: 8452 +Eval (hcp-val): [18] Total time: 0:00:14 (0.2275 s / it) +Averaged stats (hcp-val): loss: 0.8810 (0.8834) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [19] [ 0/6250] eta: 7:48:45 lr: 0.000118 grad: 0.0622 (0.0622) loss: 0.8955 (0.8955) time: 4.5000 data: 4.2791 max mem: 8452 +Train: [19] [ 100/6250] eta: 0:22:54 lr: 0.000118 grad: 0.0895 (0.0935) loss: 0.8803 (0.8815) time: 0.1586 data: 0.0615 max mem: 8452 +Train: [19] [ 200/6250] eta: 0:20:06 lr: 0.000118 grad: 0.0914 (0.0929) loss: 0.8640 (0.8778) time: 0.1873 data: 0.0949 max mem: 8452 +Train: [19] [ 300/6250] eta: 0:19:01 lr: 0.000118 grad: 0.1069 (0.0926) loss: 0.8700 (0.8756) time: 0.1714 data: 0.0869 max mem: 8452 +Train: [19] [ 400/6250] eta: 0:18:08 lr: 0.000118 grad: 0.0724 (0.0921) loss: 0.8607 (0.8737) time: 0.1891 data: 0.1138 max mem: 8452 +Train: [19] [ 500/6250] eta: 0:17:13 lr: 0.000118 grad: 0.0769 (0.0907) loss: 0.8764 (0.8734) time: 0.1426 data: 0.0478 max mem: 8452 +Train: [19] [ 600/6250] eta: 0:16:46 lr: 0.000118 grad: 0.0736 (0.0881) loss: 0.8711 (0.8734) time: 0.1768 data: 0.0938 max mem: 8452 +Train: [19] [ 700/6250] eta: 0:16:20 lr: 0.000118 grad: 0.0713 (0.0865) loss: 0.8719 (0.8732) time: 0.1709 data: 0.0878 max mem: 8452 +Train: [19] [ 800/6250] eta: 0:15:47 lr: 0.000118 grad: 0.0759 (0.0854) loss: 0.8726 (0.8728) time: 0.1469 data: 0.0607 max mem: 8452 +Train: [19] [ 900/6250] eta: 0:15:18 lr: 0.000118 grad: 0.0710 (0.0845) loss: 0.8690 (0.8724) time: 0.1558 data: 0.0673 max mem: 8452 +Train: [19] [1000/6250] eta: 0:14:59 lr: 0.000118 grad: 0.0710 (0.0835) loss: 0.8661 (0.8721) time: 0.1604 data: 0.0839 max mem: 8452 +Train: [19] [1100/6250] eta: 0:14:45 lr: 0.000118 grad: 0.0720 (0.0826) loss: 0.8662 (0.8718) time: 0.1922 data: 0.1142 max mem: 8452 +Train: [19] [1200/6250] eta: 0:14:28 lr: 0.000118 grad: 0.0750 (0.0820) loss: 0.8636 (0.8715) time: 0.1984 data: 0.1108 max mem: 8452 +Train: [19] [1300/6250] eta: 0:14:11 lr: 0.000118 grad: 0.0744 (0.0814) loss: 0.8708 (0.8715) time: 0.1717 data: 0.0898 max mem: 8452 +Train: [19] [1400/6250] eta: 0:13:58 lr: 0.000118 grad: 0.0783 (0.0810) loss: 0.8684 (0.8713) time: 0.2402 data: 0.1446 max mem: 8452 +Train: [19] [1500/6250] eta: 0:13:47 lr: 0.000118 grad: 0.0727 (0.0807) loss: 0.8709 (0.8712) time: 0.2319 data: 0.1521 max mem: 8452 +Train: [19] [1600/6250] eta: 0:13:28 lr: 0.000118 grad: 0.0733 (0.0805) loss: 0.8723 (0.8712) time: 0.1772 data: 0.0871 max mem: 8452 +Train: [19] [1700/6250] eta: 0:13:17 lr: 0.000118 grad: 0.0749 (0.0802) loss: 0.8699 (0.8711) time: 0.2404 data: 0.1447 max mem: 8452 +Train: [19] [1800/6250] eta: 0:12:59 lr: 0.000118 grad: 0.0724 (0.0800) loss: 0.8671 (0.8709) time: 0.1432 data: 0.0637 max mem: 8452 +Train: [19] [1900/6250] eta: 0:12:46 lr: 0.000118 grad: 0.0742 (0.0798) loss: 0.8692 (0.8707) time: 0.1668 data: 0.0937 max mem: 8452 +Train: [19] [2000/6250] eta: 0:12:28 lr: 0.000118 grad: 0.0767 (0.0798) loss: 0.8684 (0.8705) time: 0.1626 data: 0.0875 max mem: 8452 +Train: [19] [2100/6250] eta: 0:12:08 lr: 0.000118 grad: 0.0845 (0.0798) loss: 0.8637 (0.8703) time: 0.1474 data: 0.0601 max mem: 8452 +Train: [19] [2200/6250] eta: 0:11:52 lr: 0.000118 grad: 0.0757 (0.0798) loss: 0.8695 (0.8701) time: 0.1358 data: 0.0370 max mem: 8452 +Train: [19] [2300/6250] eta: 0:11:32 lr: 0.000118 grad: 0.0695 (0.0797) loss: 0.8696 (0.8700) time: 0.1657 data: 0.0916 max mem: 8452 +Train: [19] [2400/6250] eta: 0:11:13 lr: 0.000118 grad: 0.0841 (0.0799) loss: 0.8702 (0.8698) time: 0.1667 data: 0.0714 max mem: 8452 +Train: [19] [2500/6250] eta: 0:10:54 lr: 0.000118 grad: 0.0775 (0.0800) loss: 0.8646 (0.8697) time: 0.1823 data: 0.1068 max mem: 8452 +Train: [19] [2600/6250] eta: 0:10:37 lr: 0.000118 grad: 0.0815 (0.0802) loss: 0.8663 (0.8696) time: 0.1454 data: 0.0589 max mem: 8452 +Train: [19] [2700/6250] eta: 0:10:19 lr: 0.000118 grad: 0.0721 (0.0801) loss: 0.8717 (0.8695) time: 0.1658 data: 0.0873 max mem: 8452 +Train: [19] [2800/6250] eta: 0:10:03 lr: 0.000118 grad: 0.0742 (0.0801) loss: 0.8659 (0.8694) time: 0.1195 data: 0.0004 max mem: 8452 +Train: [19] [2900/6250] eta: 0:09:47 lr: 0.000118 grad: 0.0742 (0.0799) loss: 0.8659 (0.8694) time: 0.1518 data: 0.0695 max mem: 8452 +Train: [19] [3000/6250] eta: 0:09:33 lr: 0.000118 grad: 0.0767 (0.0800) loss: 0.8664 (0.8693) time: 0.2822 data: 0.1759 max mem: 8452 +Train: [19] [3100/6250] eta: 0:09:14 lr: 0.000118 grad: 0.0691 (0.0798) loss: 0.8720 (0.8693) time: 0.1979 data: 0.1208 max mem: 8452 +Train: [19] [3200/6250] eta: 0:08:54 lr: 0.000118 grad: 0.0749 (0.0798) loss: 0.8700 (0.8692) time: 0.1697 data: 0.0917 max mem: 8452 +Train: [19] [3300/6250] eta: 0:08:36 lr: 0.000118 grad: 0.0831 (0.0797) loss: 0.8672 (0.8691) time: 0.1482 data: 0.0666 max mem: 8452 +Train: [19] [3400/6250] eta: 0:08:18 lr: 0.000118 grad: 0.0769 (0.0797) loss: 0.8642 (0.8691) time: 0.1988 data: 0.1197 max mem: 8452 +Train: [19] [3500/6250] eta: 0:08:00 lr: 0.000118 grad: 0.0728 (0.0797) loss: 0.8713 (0.8690) time: 0.1682 data: 0.0770 max mem: 8452 +Train: [19] [3600/6250] eta: 0:07:42 lr: 0.000118 grad: 0.0794 (0.0798) loss: 0.8692 (0.8690) time: 0.1524 data: 0.0786 max mem: 8452 +Train: [19] [3700/6250] eta: 0:07:23 lr: 0.000118 grad: 0.0758 (0.0798) loss: 0.8601 (0.8689) time: 0.1432 data: 0.0628 max mem: 8452 +Train: [19] [3800/6250] eta: 0:07:04 lr: 0.000118 grad: 0.0881 (0.0799) loss: 0.8629 (0.8688) time: 0.1440 data: 0.0600 max mem: 8452 +Train: [19] [3900/6250] eta: 0:06:46 lr: 0.000118 grad: 0.0824 (0.0800) loss: 0.8663 (0.8687) time: 0.1515 data: 0.0751 max mem: 8452 +Train: [19] [4000/6250] eta: 0:06:28 lr: 0.000118 grad: 0.0869 (0.0803) loss: 0.8646 (0.8686) time: 0.1736 data: 0.0708 max mem: 8452 +Train: [19] [4100/6250] eta: 0:06:12 lr: 0.000118 grad: 0.0754 (0.0803) loss: 0.8698 (0.8686) time: 0.1745 data: 0.0821 max mem: 8452 +Train: [19] [4200/6250] eta: 0:05:54 lr: 0.000118 grad: 0.0749 (0.0804) loss: 0.8704 (0.8685) time: 0.1918 data: 0.1021 max mem: 8452 +Train: [19] [4300/6250] eta: 0:05:36 lr: 0.000118 grad: 0.0769 (0.0804) loss: 0.8587 (0.8684) time: 0.1735 data: 0.0925 max mem: 8452 +Train: [19] [4400/6250] eta: 0:05:18 lr: 0.000118 grad: 0.0813 (0.0805) loss: 0.8703 (0.8684) time: 0.1604 data: 0.0850 max mem: 8452 +Train: [19] [4500/6250] eta: 0:05:01 lr: 0.000118 grad: 0.0785 (0.0805) loss: 0.8602 (0.8683) time: 0.1549 data: 0.0681 max mem: 8452 +Train: [19] [4600/6250] eta: 0:04:43 lr: 0.000118 grad: 0.0814 (0.0805) loss: 0.8667 (0.8683) time: 0.1557 data: 0.0718 max mem: 8452 +Train: [19] [4700/6250] eta: 0:04:26 lr: 0.000118 grad: 0.0733 (0.0805) loss: 0.8683 (0.8682) time: 0.1527 data: 0.0592 max mem: 8452 +Train: [19] [4800/6250] eta: 0:04:08 lr: 0.000118 grad: 0.0730 (0.0805) loss: 0.8676 (0.8681) time: 0.1535 data: 0.0684 max mem: 8452 +Train: [19] [4900/6250] eta: 0:03:51 lr: 0.000118 grad: 0.0730 (0.0805) loss: 0.8686 (0.8681) time: 0.1860 data: 0.1232 max mem: 8452 +Train: [19] [5000/6250] eta: 0:03:34 lr: 0.000118 grad: 0.0809 (0.0805) loss: 0.8667 (0.8680) time: 0.1567 data: 0.0834 max mem: 8452 +Train: [19] [5100/6250] eta: 0:03:17 lr: 0.000118 grad: 0.0749 (0.0805) loss: 0.8595 (0.8680) time: 0.1444 data: 0.0718 max mem: 8452 +Train: [19] [5200/6250] eta: 0:02:59 lr: 0.000118 grad: 0.0818 (0.0806) loss: 0.8597 (0.8679) time: 0.1484 data: 0.0699 max mem: 8452 +Train: [19] [5300/6250] eta: 0:02:42 lr: 0.000118 grad: 0.0774 (0.0806) loss: 0.8697 (0.8678) time: 0.1716 data: 0.0919 max mem: 8452 +Train: [19] [5400/6250] eta: 0:02:24 lr: 0.000118 grad: 0.0827 (0.0806) loss: 0.8698 (0.8677) time: 0.1398 data: 0.0479 max mem: 8452 +Train: [19] [5500/6250] eta: 0:02:07 lr: 0.000118 grad: 0.0845 (0.0807) loss: 0.8673 (0.8677) time: 0.1432 data: 0.0514 max mem: 8452 +Train: [19] [5600/6250] eta: 0:01:50 lr: 0.000118 grad: 0.0869 (0.0808) loss: 0.8648 (0.8676) time: 0.1309 data: 0.0444 max mem: 8452 +Train: [19] [5700/6250] eta: 0:01:33 lr: 0.000118 grad: 0.0775 (0.0809) loss: 0.8667 (0.8676) time: 0.1415 data: 0.0560 max mem: 8452 +Train: [19] [5800/6250] eta: 0:01:16 lr: 0.000118 grad: 0.0790 (0.0810) loss: 0.8656 (0.8675) time: 0.1917 data: 0.0965 max mem: 8452 +Train: [19] [5900/6250] eta: 0:00:59 lr: 0.000118 grad: 0.0872 (0.0810) loss: 0.8678 (0.8675) time: 0.1585 data: 0.0637 max mem: 8452 +Train: [19] [6000/6250] eta: 0:00:42 lr: 0.000118 grad: 0.0821 (0.0810) loss: 0.8673 (0.8674) time: 0.1618 data: 0.0914 max mem: 8452 +Train: [19] [6100/6250] eta: 0:00:25 lr: 0.000117 grad: 0.0753 (0.0811) loss: 0.8582 (0.8674) time: 0.1261 data: 0.0290 max mem: 8452 +Train: [19] [6200/6250] eta: 0:00:08 lr: 0.000117 grad: 0.0824 (0.0811) loss: 0.8606 (0.8673) time: 0.1720 data: 0.0913 max mem: 8452 +Train: [19] [6249/6250] eta: 0:00:00 lr: 0.000117 grad: 0.0751 (0.0811) loss: 0.8725 (0.8673) time: 0.1316 data: 0.0465 max mem: 8452 +Train: [19] Total time: 0:17:47 (0.1707 s / it) +Averaged stats: lr: 0.000117 grad: 0.0751 (0.0811) loss: 0.8725 (0.8673) +Eval (hcp-train-subset): [19] [ 0/62] eta: 0:03:30 loss: 0.8890 (0.8890) time: 3.3892 data: 3.3119 max mem: 8452 +Eval (hcp-train-subset): [19] [61/62] eta: 0:00:00 loss: 0.8864 (0.8862) time: 0.1242 data: 0.1030 max mem: 8452 +Eval (hcp-train-subset): [19] Total time: 0:00:15 (0.2449 s / it) +Averaged stats (hcp-train-subset): loss: 0.8864 (0.8862) +Making plots (hcp-train-subset): example=6 +Eval (hcp-val): [19] [ 0/62] eta: 0:06:19 loss: 0.8810 (0.8810) time: 6.1274 data: 6.0983 max mem: 8452 +Eval (hcp-val): [19] [61/62] eta: 0:00:00 loss: 0.8832 (0.8843) time: 0.1440 data: 0.1215 max mem: 8452 +Eval (hcp-val): [19] Total time: 0:00:15 (0.2455 s / it) +Averaged stats (hcp-val): loss: 0.8832 (0.8843) +Making plots (hcp-val): example=51 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-00019.pth +Train: [20] [ 0/6250] eta: 8:20:13 lr: 0.000117 grad: 0.0637 (0.0637) loss: 0.8977 (0.8977) time: 4.8021 data: 4.6153 max mem: 8452 +Train: [20] [ 100/6250] eta: 0:22:08 lr: 0.000117 grad: 0.0972 (0.1095) loss: 0.8735 (0.8833) time: 0.1505 data: 0.0555 max mem: 8452 +Train: [20] [ 200/6250] eta: 0:19:28 lr: 0.000117 grad: 0.0930 (0.1051) loss: 0.8667 (0.8764) time: 0.1489 data: 0.0615 max mem: 8452 +Train: [20] [ 300/6250] eta: 0:18:27 lr: 0.000117 grad: 0.0798 (0.1005) loss: 0.8682 (0.8726) time: 0.1620 data: 0.0518 max mem: 8452 +Train: [20] [ 400/6250] eta: 0:18:05 lr: 0.000117 grad: 0.0790 (0.0956) loss: 0.8695 (0.8705) time: 0.1581 data: 0.0796 max mem: 8452 +Train: [20] [ 500/6250] eta: 0:17:33 lr: 0.000117 grad: 0.0820 (0.0939) loss: 0.8671 (0.8695) time: 0.1511 data: 0.0738 max mem: 8452 +Train: [20] [ 600/6250] eta: 0:16:47 lr: 0.000117 grad: 0.0741 (0.0923) loss: 0.8646 (0.8688) time: 0.1402 data: 0.0513 max mem: 8452 +Train: [20] [ 700/6250] eta: 0:16:27 lr: 0.000117 grad: 0.0837 (0.0917) loss: 0.8724 (0.8680) time: 0.2066 data: 0.1298 max mem: 8452 +Train: [20] [ 800/6250] eta: 0:15:59 lr: 0.000117 grad: 0.0877 (0.0914) loss: 0.8560 (0.8669) time: 0.1776 data: 0.0900 max mem: 8452 +Train: [20] [ 900/6250] eta: 0:15:32 lr: 0.000117 grad: 0.0799 (0.0906) loss: 0.8652 (0.8661) time: 0.1741 data: 0.0897 max mem: 8452 +Train: [20] [1000/6250] eta: 0:15:02 lr: 0.000117 grad: 0.0720 (0.0898) loss: 0.8677 (0.8657) time: 0.1300 data: 0.0331 max mem: 8452 +Train: [20] [1100/6250] eta: 0:14:33 lr: 0.000117 grad: 0.0748 (0.0891) loss: 0.8633 (0.8654) time: 0.1462 data: 0.0655 max mem: 8452 +Train: [20] [1200/6250] eta: 0:14:09 lr: 0.000117 grad: 0.0749 (0.0883) loss: 0.8676 (0.8652) time: 0.1820 data: 0.1048 max mem: 8452 +Train: [20] [1300/6250] eta: 0:13:42 lr: 0.000117 grad: 0.0709 (0.0879) loss: 0.8639 (0.8650) time: 0.1416 data: 0.0477 max mem: 8452 +Train: [20] [1400/6250] eta: 0:13:20 lr: 0.000117 grad: 0.0854 (0.0877) loss: 0.8575 (0.8649) time: 0.1453 data: 0.0589 max mem: 8452 +Train: [20] [1500/6250] eta: 0:13:05 lr: 0.000117 grad: 0.0831 (0.0875) loss: 0.8563 (0.8645) time: 0.1571 data: 0.0501 max mem: 8452 +Train: [20] [1600/6250] eta: 0:12:49 lr: 0.000117 grad: 0.0793 (0.0876) loss: 0.8596 (0.8641) time: 0.1589 data: 0.0698 max mem: 8452 +Train: [20] [1700/6250] eta: 0:12:39 lr: 0.000117 grad: 0.0847 (0.0877) loss: 0.8649 (0.8637) time: 0.1815 data: 0.1131 max mem: 8452 +Train: [20] [1800/6250] eta: 0:12:23 lr: 0.000117 grad: 0.0865 (0.0877) loss: 0.8554 (0.8635) time: 0.1176 data: 0.0353 max mem: 8452 +Train: [20] [1900/6250] eta: 0:12:10 lr: 0.000117 grad: 0.0796 (0.0875) loss: 0.8683 (0.8634) time: 0.1925 data: 0.1083 max mem: 8452 +Train: [20] [2000/6250] eta: 0:11:56 lr: 0.000117 grad: 0.0786 (0.0872) loss: 0.8617 (0.8633) time: 0.1586 data: 0.0689 max mem: 8452 +Train: [20] [2100/6250] eta: 0:11:37 lr: 0.000117 grad: 0.0824 (0.0871) loss: 0.8546 (0.8632) time: 0.1647 data: 0.0919 max mem: 8452 +Train: [20] [2200/6250] eta: 0:11:18 lr: 0.000117 grad: 0.0806 (0.0869) loss: 0.8620 (0.8631) time: 0.1620 data: 0.0755 max mem: 8452 +Train: [20] [2300/6250] eta: 0:11:00 lr: 0.000117 grad: 0.0869 (0.0868) loss: 0.8655 (0.8631) time: 0.1649 data: 0.0875 max mem: 8452 +Train: [20] [2400/6250] eta: 0:10:43 lr: 0.000117 grad: 0.0793 (0.0866) loss: 0.8615 (0.8630) time: 0.1587 data: 0.0775 max mem: 8452 +Train: [20] [2500/6250] eta: 0:10:26 lr: 0.000117 grad: 0.0790 (0.0864) loss: 0.8707 (0.8631) time: 0.1819 data: 0.1047 max mem: 8452 +Train: [20] [2600/6250] eta: 0:10:10 lr: 0.000117 grad: 0.0762 (0.0862) loss: 0.8666 (0.8632) time: 0.1826 data: 0.0982 max mem: 8452 +Train: [20] [2700/6250] eta: 0:09:56 lr: 0.000117 grad: 0.0821 (0.0861) loss: 0.8627 (0.8632) time: 0.1459 data: 0.0347 max mem: 8452 +Train: [20] [2800/6250] eta: 0:09:41 lr: 0.000117 grad: 0.0794 (0.0861) loss: 0.8648 (0.8632) time: 0.2025 data: 0.1087 max mem: 8452 +Train: [20] [2900/6250] eta: 0:09:25 lr: 0.000117 grad: 0.0840 (0.0859) loss: 0.8637 (0.8633) time: 0.1795 data: 0.0981 max mem: 8452 +Train: [20] [3000/6250] eta: 0:09:12 lr: 0.000117 grad: 0.0769 (0.0857) loss: 0.8671 (0.8634) time: 0.1179 data: 0.0280 max mem: 8452 +Train: [20] [3100/6250] eta: 0:08:56 lr: 0.000117 grad: 0.0781 (0.0855) loss: 0.8691 (0.8635) time: 0.2220 data: 0.1505 max mem: 8452 +Train: [20] [3200/6250] eta: 0:08:42 lr: 0.000117 grad: 0.0896 (0.0855) loss: 0.8633 (0.8636) time: 0.1157 data: 0.0003 max mem: 8452 +Train: [20] [3300/6250] eta: 0:08:25 lr: 0.000117 grad: 0.0756 (0.0854) loss: 0.8673 (0.8637) time: 0.1759 data: 0.0962 max mem: 8452 +Train: [20] [3400/6250] eta: 0:08:07 lr: 0.000117 grad: 0.0773 (0.0852) loss: 0.8639 (0.8637) time: 0.1752 data: 0.1020 max mem: 8452 +Train: [20] [3500/6250] eta: 0:07:49 lr: 0.000117 grad: 0.0758 (0.0852) loss: 0.8672 (0.8637) time: 0.1647 data: 0.0875 max mem: 8452 +Train: [20] [3600/6250] eta: 0:07:31 lr: 0.000117 grad: 0.0792 (0.0851) loss: 0.8667 (0.8637) time: 0.1868 data: 0.0964 max mem: 8452 +Train: [20] [3700/6250] eta: 0:07:13 lr: 0.000117 grad: 0.0774 (0.0851) loss: 0.8729 (0.8637) time: 0.1539 data: 0.0809 max mem: 8452 +Train: [20] [3800/6250] eta: 0:06:56 lr: 0.000117 grad: 0.0793 (0.0850) loss: 0.8672 (0.8638) time: 0.1761 data: 0.0884 max mem: 8452 +Train: [20] [3900/6250] eta: 0:06:38 lr: 0.000117 grad: 0.0790 (0.0849) loss: 0.8646 (0.8638) time: 0.1601 data: 0.0734 max mem: 8452 +Train: [20] [4000/6250] eta: 0:06:20 lr: 0.000117 grad: 0.0739 (0.0847) loss: 0.8649 (0.8639) time: 0.1538 data: 0.0796 max mem: 8452 +Train: [20] [4100/6250] eta: 0:06:03 lr: 0.000117 grad: 0.0820 (0.0846) loss: 0.8641 (0.8639) time: 0.1507 data: 0.0659 max mem: 8452 +Train: [20] [4200/6250] eta: 0:05:47 lr: 0.000117 grad: 0.0763 (0.0845) loss: 0.8693 (0.8640) time: 0.1304 data: 0.0320 max mem: 8452 +Train: [20] [4300/6250] eta: 0:05:30 lr: 0.000117 grad: 0.0761 (0.0845) loss: 0.8654 (0.8640) time: 0.1368 data: 0.0649 max mem: 8452 +Train: [20] [4400/6250] eta: 0:05:13 lr: 0.000117 grad: 0.0803 (0.0844) loss: 0.8683 (0.8641) time: 0.1757 data: 0.0940 max mem: 8452 +Train: [20] [4500/6250] eta: 0:04:57 lr: 0.000117 grad: 0.0771 (0.0842) loss: 0.8683 (0.8642) time: 0.1475 data: 0.0622 max mem: 8452 +Train: [20] [4600/6250] eta: 0:04:40 lr: 0.000117 grad: 0.0814 (0.0842) loss: 0.8605 (0.8643) time: 0.1353 data: 0.0514 max mem: 8452 +Train: [20] [4700/6250] eta: 0:04:24 lr: 0.000117 grad: 0.0788 (0.0841) loss: 0.8643 (0.8643) time: 0.1696 data: 0.0956 max mem: 8452 +Train: [20] [4800/6250] eta: 0:04:06 lr: 0.000117 grad: 0.0722 (0.0840) loss: 0.8656 (0.8644) time: 0.1470 data: 0.0599 max mem: 8452 +Train: [20] [4900/6250] eta: 0:03:49 lr: 0.000117 grad: 0.0762 (0.0840) loss: 0.8639 (0.8644) time: 0.1802 data: 0.1100 max mem: 8452 +Train: [20] [5000/6250] eta: 0:03:32 lr: 0.000117 grad: 0.0728 (0.0839) loss: 0.8701 (0.8645) time: 0.1444 data: 0.0663 max mem: 8452 +Train: [20] [5100/6250] eta: 0:03:15 lr: 0.000117 grad: 0.0811 (0.0839) loss: 0.8679 (0.8645) time: 0.1428 data: 0.0672 max mem: 8452 +Train: [20] [5200/6250] eta: 0:02:57 lr: 0.000117 grad: 0.0785 (0.0840) loss: 0.8591 (0.8645) time: 0.1546 data: 0.0658 max mem: 8452 +Train: [20] [5300/6250] eta: 0:02:40 lr: 0.000117 grad: 0.0798 (0.0839) loss: 0.8645 (0.8645) time: 0.1462 data: 0.0583 max mem: 8452 +Train: [20] [5400/6250] eta: 0:02:23 lr: 0.000117 grad: 0.0815 (0.0839) loss: 0.8542 (0.8645) time: 0.1363 data: 0.0423 max mem: 8452 +Train: [20] [5500/6250] eta: 0:02:06 lr: 0.000117 grad: 0.0765 (0.0839) loss: 0.8579 (0.8645) time: 0.1602 data: 0.0705 max mem: 8452 +Train: [20] [5600/6250] eta: 0:01:49 lr: 0.000117 grad: 0.0799 (0.0839) loss: 0.8597 (0.8644) time: 0.0964 data: 0.0004 max mem: 8452 +Train: [20] [5700/6250] eta: 0:01:32 lr: 0.000117 grad: 0.0833 (0.0839) loss: 0.8678 (0.8644) time: 0.1663 data: 0.0834 max mem: 8452 +Train: [20] [5800/6250] eta: 0:01:15 lr: 0.000117 grad: 0.0795 (0.0838) loss: 0.8601 (0.8644) time: 0.1467 data: 0.0701 max mem: 8452 +Train: [20] [5900/6250] eta: 0:00:58 lr: 0.000117 grad: 0.0816 (0.0838) loss: 0.8649 (0.8645) time: 0.1509 data: 0.0814 max mem: 8452 +Train: [20] [6000/6250] eta: 0:00:41 lr: 0.000116 grad: 0.0816 (0.0838) loss: 0.8619 (0.8644) time: 0.1583 data: 0.0450 max mem: 8452 +Train: [20] [6100/6250] eta: 0:00:25 lr: 0.000116 grad: 0.0837 (0.0839) loss: 0.8668 (0.8644) time: 0.2585 data: 0.1627 max mem: 8452 +Train: [20] [6200/6250] eta: 0:00:08 lr: 0.000116 grad: 0.0862 (0.0840) loss: 0.8600 (0.8643) time: 0.1132 data: 0.0129 max mem: 8452 +Train: [20] [6249/6250] eta: 0:00:00 lr: 0.000116 grad: 0.0799 (0.0840) loss: 0.8714 (0.8643) time: 0.1810 data: 0.1031 max mem: 8452 +Train: [20] Total time: 0:17:39 (0.1695 s / it) +Averaged stats: lr: 0.000116 grad: 0.0799 (0.0840) loss: 0.8714 (0.8643) +Eval (hcp-train-subset): [20] [ 0/62] eta: 0:05:06 loss: 0.8950 (0.8950) time: 4.9362 data: 4.9035 max mem: 8452 +Eval (hcp-train-subset): [20] [61/62] eta: 0:00:00 loss: 0.8856 (0.8839) time: 0.1486 data: 0.1273 max mem: 8452 +Eval (hcp-train-subset): [20] Total time: 0:00:14 (0.2323 s / it) +Averaged stats (hcp-train-subset): loss: 0.8856 (0.8839) +Eval (hcp-val): [20] [ 0/62] eta: 0:04:15 loss: 0.8775 (0.8775) time: 4.1232 data: 4.0554 max mem: 8452 +Eval (hcp-val): [20] [61/62] eta: 0:00:00 loss: 0.8802 (0.8816) time: 0.1553 data: 0.1341 max mem: 8452 +Eval (hcp-val): [20] Total time: 0:00:14 (0.2397 s / it) +Averaged stats (hcp-val): loss: 0.8802 (0.8816) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [21] [ 0/6250] eta: 12:24:05 lr: 0.000116 grad: 0.1108 (0.1108) loss: 0.8189 (0.8189) time: 7.1433 data: 7.0445 max mem: 8452 +Train: [21] [ 100/6250] eta: 0:23:43 lr: 0.000116 grad: 0.0821 (0.1064) loss: 0.8702 (0.8733) time: 0.2039 data: 0.1128 max mem: 8452 +Train: [21] [ 200/6250] eta: 0:20:33 lr: 0.000116 grad: 0.0793 (0.0965) loss: 0.8756 (0.8702) time: 0.2024 data: 0.1128 max mem: 8452 +Train: [21] [ 300/6250] eta: 0:19:13 lr: 0.000116 grad: 0.0757 (0.0926) loss: 0.8615 (0.8691) time: 0.1705 data: 0.0744 max mem: 8452 +Train: [21] [ 400/6250] eta: 0:18:00 lr: 0.000116 grad: 0.0742 (0.0896) loss: 0.8732 (0.8681) time: 0.1540 data: 0.0670 max mem: 8452 +Train: [21] [ 500/6250] eta: 0:17:32 lr: 0.000116 grad: 0.0739 (0.0878) loss: 0.8724 (0.8682) time: 0.2206 data: 0.1477 max mem: 8452 +Train: [21] [ 600/6250] eta: 0:16:58 lr: 0.000116 grad: 0.0815 (0.0869) loss: 0.8621 (0.8682) time: 0.1522 data: 0.0664 max mem: 8452 +Train: [21] [ 700/6250] eta: 0:16:27 lr: 0.000116 grad: 0.0764 (0.0858) loss: 0.8679 (0.8681) time: 0.1513 data: 0.0745 max mem: 8452 +Train: [21] [ 800/6250] eta: 0:16:07 lr: 0.000116 grad: 0.0727 (0.0850) loss: 0.8776 (0.8683) time: 0.1712 data: 0.0782 max mem: 8452 +Train: [21] [ 900/6250] eta: 0:15:38 lr: 0.000116 grad: 0.0781 (0.0841) loss: 0.8675 (0.8682) time: 0.1577 data: 0.0717 max mem: 8452 +Train: [21] [1000/6250] eta: 0:15:08 lr: 0.000116 grad: 0.0758 (0.0835) loss: 0.8658 (0.8681) time: 0.1413 data: 0.0544 max mem: 8452 +Train: [21] [1100/6250] eta: 0:14:47 lr: 0.000116 grad: 0.0752 (0.0833) loss: 0.8701 (0.8680) time: 0.1012 data: 0.0049 max mem: 8452 +Train: [21] [1200/6250] eta: 0:14:32 lr: 0.000116 grad: 0.0764 (0.0831) loss: 0.8703 (0.8679) time: 0.2081 data: 0.1388 max mem: 8452 +Train: [21] [1300/6250] eta: 0:14:17 lr: 0.000116 grad: 0.0771 (0.0830) loss: 0.8666 (0.8677) time: 0.1724 data: 0.0987 max mem: 8452 +Train: [21] [1400/6250] eta: 0:14:08 lr: 0.000116 grad: 0.0791 (0.0830) loss: 0.8700 (0.8675) time: 0.2442 data: 0.1786 max mem: 8452 +Train: [21] [1500/6250] eta: 0:13:58 lr: 0.000116 grad: 0.0738 (0.0828) loss: 0.8685 (0.8675) time: 0.1948 data: 0.1197 max mem: 8452 +Train: [21] [1600/6250] eta: 0:13:56 lr: 0.000116 grad: 0.0782 (0.0828) loss: 0.8675 (0.8673) time: 0.2456 data: 0.1791 max mem: 8452 +Train: [21] [1700/6250] eta: 0:13:39 lr: 0.000116 grad: 0.0797 (0.0829) loss: 0.8674 (0.8671) time: 0.2055 data: 0.1327 max mem: 8452 +Train: [21] [1800/6250] eta: 0:13:24 lr: 0.000116 grad: 0.0819 (0.0829) loss: 0.8647 (0.8668) time: 0.2127 data: 0.1349 max mem: 8452 +Train: [21] [1900/6250] eta: 0:13:08 lr: 0.000116 grad: 0.0768 (0.0830) loss: 0.8714 (0.8666) time: 0.1971 data: 0.1206 max mem: 8452 +Train: [21] [2000/6250] eta: 0:12:53 lr: 0.000116 grad: 0.0846 (0.0833) loss: 0.8644 (0.8665) time: 0.1383 data: 0.0591 max mem: 8452 +Train: [21] [2100/6250] eta: 0:12:36 lr: 0.000116 grad: 0.0829 (0.0838) loss: 0.8679 (0.8663) time: 0.2302 data: 0.1512 max mem: 8452 +Train: [21] [2200/6250] eta: 0:12:18 lr: 0.000116 grad: 0.0765 (0.0839) loss: 0.8661 (0.8662) time: 0.2024 data: 0.1237 max mem: 8452 +Train: [21] [2300/6250] eta: 0:11:58 lr: 0.000116 grad: 0.0806 (0.0839) loss: 0.8646 (0.8659) time: 0.2001 data: 0.1272 max mem: 8452 +Train: [21] [2400/6250] eta: 0:11:38 lr: 0.000116 grad: 0.0831 (0.0840) loss: 0.8617 (0.8657) time: 0.1480 data: 0.0585 max mem: 8452 +Train: [21] [2500/6250] eta: 0:11:20 lr: 0.000116 grad: 0.0822 (0.0840) loss: 0.8646 (0.8657) time: 0.1418 data: 0.0475 max mem: 8452 +Train: [21] [2600/6250] eta: 0:11:06 lr: 0.000116 grad: 0.0765 (0.0840) loss: 0.8687 (0.8655) time: 0.1340 data: 0.0138 max mem: 8452 +Train: [21] [2700/6250] eta: 0:10:44 lr: 0.000116 grad: 0.0755 (0.0839) loss: 0.8645 (0.8656) time: 0.1502 data: 0.0707 max mem: 8452 +Train: [21] [2800/6250] eta: 0:10:25 lr: 0.000116 grad: 0.0800 (0.0840) loss: 0.8602 (0.8654) time: 0.1359 data: 0.0258 max mem: 8452 +Train: [21] [2900/6250] eta: 0:10:06 lr: 0.000116 grad: 0.0826 (0.0841) loss: 0.8616 (0.8653) time: 0.1831 data: 0.0443 max mem: 8452 +Train: [21] [3000/6250] eta: 0:09:49 lr: 0.000116 grad: 0.0886 (0.0840) loss: 0.8607 (0.8652) time: 0.1677 data: 0.0816 max mem: 8452 +Train: [21] [3100/6250] eta: 0:09:28 lr: 0.000116 grad: 0.0845 (0.0841) loss: 0.8603 (0.8650) time: 0.1789 data: 0.0872 max mem: 8452 +Train: [21] [3200/6250] eta: 0:09:09 lr: 0.000116 grad: 0.0793 (0.0842) loss: 0.8592 (0.8649) time: 0.1240 data: 0.0359 max mem: 8452 +Train: [21] [3300/6250] eta: 0:08:51 lr: 0.000116 grad: 0.0869 (0.0842) loss: 0.8630 (0.8648) time: 0.1794 data: 0.0758 max mem: 8452 +Train: [21] [3400/6250] eta: 0:08:32 lr: 0.000116 grad: 0.0815 (0.0843) loss: 0.8562 (0.8646) time: 0.1697 data: 0.0928 max mem: 8452 +Train: [21] [3500/6250] eta: 0:08:15 lr: 0.000116 grad: 0.0811 (0.0843) loss: 0.8554 (0.8645) time: 0.1121 data: 0.0002 max mem: 8452 +Train: [21] [3600/6250] eta: 0:07:54 lr: 0.000116 grad: 0.0833 (0.0844) loss: 0.8563 (0.8644) time: 0.1583 data: 0.0837 max mem: 8452 +Train: [21] [3700/6250] eta: 0:07:35 lr: 0.000116 grad: 0.0847 (0.0846) loss: 0.8541 (0.8642) time: 0.1604 data: 0.0903 max mem: 8452 +Train: [21] [3800/6250] eta: 0:07:17 lr: 0.000116 grad: 0.0837 (0.0848) loss: 0.8580 (0.8640) time: 0.1235 data: 0.0509 max mem: 8452 +Train: [21] [3900/6250] eta: 0:06:58 lr: 0.000116 grad: 0.0870 (0.0850) loss: 0.8552 (0.8639) time: 0.1678 data: 0.0932 max mem: 8452 +Train: [21] [4000/6250] eta: 0:06:40 lr: 0.000116 grad: 0.0809 (0.0851) loss: 0.8598 (0.8637) time: 0.2204 data: 0.1445 max mem: 8452 +Train: [21] [4100/6250] eta: 0:06:22 lr: 0.000116 grad: 0.0801 (0.0850) loss: 0.8689 (0.8637) time: 0.1832 data: 0.1008 max mem: 8452 +Train: [21] [4200/6250] eta: 0:06:05 lr: 0.000116 grad: 0.0774 (0.0850) loss: 0.8617 (0.8637) time: 0.1715 data: 0.1018 max mem: 8452 +Train: [21] [4300/6250] eta: 0:05:47 lr: 0.000116 grad: 0.0806 (0.0850) loss: 0.8668 (0.8637) time: 0.2139 data: 0.1364 max mem: 8452 +Train: [21] [4400/6250] eta: 0:05:30 lr: 0.000116 grad: 0.0764 (0.0850) loss: 0.8626 (0.8636) time: 0.1525 data: 0.0711 max mem: 8452 +Train: [21] [4500/6250] eta: 0:05:12 lr: 0.000116 grad: 0.0784 (0.0849) loss: 0.8630 (0.8636) time: 0.2008 data: 0.1223 max mem: 8452 +Train: [21] [4600/6250] eta: 0:04:55 lr: 0.000116 grad: 0.0786 (0.0848) loss: 0.8609 (0.8635) time: 0.2531 data: 0.1829 max mem: 8452 +Train: [21] [4700/6250] eta: 0:04:37 lr: 0.000116 grad: 0.0822 (0.0849) loss: 0.8656 (0.8635) time: 0.1857 data: 0.1104 max mem: 8452 +Train: [21] [4800/6250] eta: 0:04:19 lr: 0.000116 grad: 0.0915 (0.0850) loss: 0.8543 (0.8634) time: 0.1795 data: 0.1019 max mem: 8452 +Train: [21] [4900/6250] eta: 0:04:01 lr: 0.000116 grad: 0.0792 (0.0849) loss: 0.8627 (0.8633) time: 0.1614 data: 0.0831 max mem: 8452 +Train: [21] [5000/6250] eta: 0:03:43 lr: 0.000116 grad: 0.0845 (0.0850) loss: 0.8602 (0.8632) time: 0.1845 data: 0.1023 max mem: 8452 +Train: [21] [5100/6250] eta: 0:03:25 lr: 0.000116 grad: 0.0807 (0.0850) loss: 0.8614 (0.8631) time: 0.1593 data: 0.0759 max mem: 8452 +Train: [21] [5200/6250] eta: 0:03:07 lr: 0.000116 grad: 0.0845 (0.0851) loss: 0.8583 (0.8630) time: 0.1591 data: 0.0713 max mem: 8452 +Train: [21] [5300/6250] eta: 0:02:49 lr: 0.000116 grad: 0.0790 (0.0851) loss: 0.8588 (0.8629) time: 0.1615 data: 0.0785 max mem: 8452 +Train: [21] [5400/6250] eta: 0:02:30 lr: 0.000116 grad: 0.0809 (0.0851) loss: 0.8561 (0.8628) time: 0.1553 data: 0.0676 max mem: 8452 +Train: [21] [5500/6250] eta: 0:02:12 lr: 0.000116 grad: 0.0850 (0.0852) loss: 0.8678 (0.8627) time: 0.1588 data: 0.0682 max mem: 8452 +Train: [21] [5600/6250] eta: 0:01:54 lr: 0.000115 grad: 0.0850 (0.0852) loss: 0.8545 (0.8626) time: 0.1548 data: 0.0730 max mem: 8452 +Train: [21] [5700/6250] eta: 0:01:37 lr: 0.000115 grad: 0.0798 (0.0852) loss: 0.8577 (0.8625) time: 0.1645 data: 0.0918 max mem: 8452 +Train: [21] [5800/6250] eta: 0:01:19 lr: 0.000115 grad: 0.0796 (0.0853) loss: 0.8632 (0.8624) time: 0.2428 data: 0.1744 max mem: 8452 +Train: [21] [5900/6250] eta: 0:01:01 lr: 0.000115 grad: 0.0865 (0.0852) loss: 0.8605 (0.8624) time: 0.2639 data: 0.1783 max mem: 8452 +Train: [21] [6000/6250] eta: 0:00:44 lr: 0.000115 grad: 0.0772 (0.0853) loss: 0.8554 (0.8623) time: 0.2633 data: 0.1826 max mem: 8452 +Train: [21] [6100/6250] eta: 0:00:26 lr: 0.000115 grad: 0.0834 (0.0852) loss: 0.8608 (0.8622) time: 0.1867 data: 0.1160 max mem: 8452 +Train: [21] [6200/6250] eta: 0:00:08 lr: 0.000115 grad: 0.0793 (0.0852) loss: 0.8597 (0.8622) time: 0.1554 data: 0.0804 max mem: 8452 +Train: [21] [6249/6250] eta: 0:00:00 lr: 0.000115 grad: 0.0933 (0.0853) loss: 0.8587 (0.8621) time: 0.1751 data: 0.1044 max mem: 8452 +Train: [21] Total time: 0:18:30 (0.1776 s / it) +Averaged stats: lr: 0.000115 grad: 0.0933 (0.0853) loss: 0.8587 (0.8621) +Eval (hcp-train-subset): [21] [ 0/62] eta: 0:03:33 loss: 0.8975 (0.8975) time: 3.4430 data: 3.3640 max mem: 8452 +Eval (hcp-train-subset): [21] [61/62] eta: 0:00:00 loss: 0.8836 (0.8843) time: 0.1763 data: 0.1538 max mem: 8452 +Eval (hcp-train-subset): [21] Total time: 0:00:15 (0.2552 s / it) +Averaged stats (hcp-train-subset): loss: 0.8836 (0.8843) +Eval (hcp-val): [21] [ 0/62] eta: 0:06:13 loss: 0.8805 (0.8805) time: 6.0191 data: 5.9896 max mem: 8452 +Eval (hcp-val): [21] [61/62] eta: 0:00:00 loss: 0.8818 (0.8837) time: 0.1609 data: 0.1394 max mem: 8452 +Eval (hcp-val): [21] Total time: 0:00:17 (0.2835 s / it) +Averaged stats (hcp-val): loss: 0.8818 (0.8837) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [22] [ 0/6250] eta: 11:10:19 lr: 0.000115 grad: 0.3259 (0.3259) loss: 0.9273 (0.9273) time: 6.4351 data: 6.2476 max mem: 8452 +Train: [22] [ 100/6250] eta: 0:24:32 lr: 0.000115 grad: 0.1215 (0.1134) loss: 0.8735 (0.8819) time: 0.1787 data: 0.0689 max mem: 8452 +Train: [22] [ 200/6250] eta: 0:21:35 lr: 0.000115 grad: 0.0832 (0.1067) loss: 0.8674 (0.8772) time: 0.1858 data: 0.0888 max mem: 8452 +Train: [22] [ 300/6250] eta: 0:20:13 lr: 0.000115 grad: 0.0820 (0.1014) loss: 0.8591 (0.8728) time: 0.1992 data: 0.1050 max mem: 8452 +Train: [22] [ 400/6250] eta: 0:18:57 lr: 0.000115 grad: 0.0784 (0.0967) loss: 0.8708 (0.8710) time: 0.1678 data: 0.0753 max mem: 8452 +Train: [22] [ 500/6250] eta: 0:18:14 lr: 0.000115 grad: 0.0892 (0.0950) loss: 0.8624 (0.8695) time: 0.1811 data: 0.0911 max mem: 8452 +Train: [22] [ 600/6250] eta: 0:17:56 lr: 0.000115 grad: 0.0784 (0.0934) loss: 0.8588 (0.8682) time: 0.2227 data: 0.1483 max mem: 8452 +Train: [22] [ 700/6250] eta: 0:17:25 lr: 0.000115 grad: 0.0775 (0.0920) loss: 0.8687 (0.8675) time: 0.1916 data: 0.1088 max mem: 8452 +Train: [22] [ 800/6250] eta: 0:16:58 lr: 0.000115 grad: 0.0756 (0.0904) loss: 0.8661 (0.8670) time: 0.1561 data: 0.0749 max mem: 8452 +Train: [22] [ 900/6250] eta: 0:16:34 lr: 0.000115 grad: 0.0843 (0.0895) loss: 0.8594 (0.8664) time: 0.1286 data: 0.0366 max mem: 8452 +Train: [22] [1000/6250] eta: 0:16:07 lr: 0.000115 grad: 0.0772 (0.0887) loss: 0.8656 (0.8664) time: 0.1696 data: 0.0967 max mem: 8452 +Train: [22] [1100/6250] eta: 0:15:34 lr: 0.000115 grad: 0.0766 (0.0878) loss: 0.8666 (0.8662) time: 0.1416 data: 0.0509 max mem: 8452 +Train: [22] [1200/6250] eta: 0:15:05 lr: 0.000115 grad: 0.0812 (0.0872) loss: 0.8593 (0.8658) time: 0.1492 data: 0.0636 max mem: 8452 +Train: [22] [1300/6250] eta: 0:14:43 lr: 0.000115 grad: 0.0803 (0.0867) loss: 0.8574 (0.8654) time: 0.1824 data: 0.1040 max mem: 8452 +Train: [22] [1400/6250] eta: 0:14:35 lr: 0.000115 grad: 0.0747 (0.0862) loss: 0.8634 (0.8652) time: 0.0969 data: 0.0004 max mem: 8452 +Train: [22] [1500/6250] eta: 0:14:12 lr: 0.000115 grad: 0.0740 (0.0858) loss: 0.8650 (0.8652) time: 0.1507 data: 0.0623 max mem: 8452 +Train: [22] [1600/6250] eta: 0:13:51 lr: 0.000115 grad: 0.0781 (0.0857) loss: 0.8599 (0.8651) time: 0.1889 data: 0.1028 max mem: 8452 +Train: [22] [1700/6250] eta: 0:13:28 lr: 0.000115 grad: 0.0816 (0.0854) loss: 0.8593 (0.8651) time: 0.1443 data: 0.0571 max mem: 8452 +Train: [22] [1800/6250] eta: 0:13:11 lr: 0.000115 grad: 0.0761 (0.0850) loss: 0.8632 (0.8650) time: 0.1827 data: 0.1045 max mem: 8452 +Train: [22] [1900/6250] eta: 0:12:54 lr: 0.000115 grad: 0.0801 (0.0850) loss: 0.8617 (0.8648) time: 0.2001 data: 0.1268 max mem: 8452 +Train: [22] [2000/6250] eta: 0:12:38 lr: 0.000115 grad: 0.0738 (0.0846) loss: 0.8643 (0.8648) time: 0.1873 data: 0.1209 max mem: 8452 +Train: [22] [2100/6250] eta: 0:12:24 lr: 0.000115 grad: 0.0767 (0.0844) loss: 0.8691 (0.8649) time: 0.1495 data: 0.0705 max mem: 8452 +Train: [22] [2200/6250] eta: 0:12:05 lr: 0.000115 grad: 0.0759 (0.0842) loss: 0.8692 (0.8650) time: 0.1837 data: 0.0883 max mem: 8452 +Train: [22] [2300/6250] eta: 0:11:50 lr: 0.000115 grad: 0.0812 (0.0841) loss: 0.8604 (0.8650) time: 0.1103 data: 0.0149 max mem: 8452 +Train: [22] [2400/6250] eta: 0:11:30 lr: 0.000115 grad: 0.0760 (0.0840) loss: 0.8673 (0.8651) time: 0.1656 data: 0.0805 max mem: 8452 +Train: [22] [2500/6250] eta: 0:11:12 lr: 0.000115 grad: 0.0787 (0.0839) loss: 0.8657 (0.8652) time: 0.1797 data: 0.0955 max mem: 8452 +Train: [22] [2600/6250] eta: 0:10:54 lr: 0.000115 grad: 0.0821 (0.0838) loss: 0.8664 (0.8652) time: 0.1237 data: 0.0114 max mem: 8452 +Train: [22] [2700/6250] eta: 0:10:35 lr: 0.000115 grad: 0.0810 (0.0838) loss: 0.8626 (0.8651) time: 0.1847 data: 0.0942 max mem: 8452 +Train: [22] [2800/6250] eta: 0:10:18 lr: 0.000115 grad: 0.0786 (0.0838) loss: 0.8649 (0.8651) time: 0.1088 data: 0.0007 max mem: 8452 +Train: [22] [2900/6250] eta: 0:10:00 lr: 0.000115 grad: 0.0749 (0.0837) loss: 0.8687 (0.8651) time: 0.1894 data: 0.1139 max mem: 8452 +Train: [22] [3000/6250] eta: 0:09:44 lr: 0.000115 grad: 0.0860 (0.0837) loss: 0.8584 (0.8650) time: 0.1127 data: 0.0003 max mem: 8452 +Train: [22] [3100/6250] eta: 0:09:26 lr: 0.000115 grad: 0.0748 (0.0837) loss: 0.8589 (0.8650) time: 0.1419 data: 0.0410 max mem: 8452 +Train: [22] [3200/6250] eta: 0:09:06 lr: 0.000115 grad: 0.0828 (0.0836) loss: 0.8599 (0.8650) time: 0.1163 data: 0.0268 max mem: 8452 +Train: [22] [3300/6250] eta: 0:08:47 lr: 0.000115 grad: 0.0808 (0.0835) loss: 0.8629 (0.8649) time: 0.1339 data: 0.0468 max mem: 8452 +Train: [22] [3400/6250] eta: 0:08:27 lr: 0.000115 grad: 0.0776 (0.0835) loss: 0.8701 (0.8649) time: 0.1520 data: 0.0565 max mem: 8452 +Train: [22] [3500/6250] eta: 0:08:08 lr: 0.000115 grad: 0.0813 (0.0835) loss: 0.8638 (0.8649) time: 0.1714 data: 0.0969 max mem: 8452 +Train: [22] [3600/6250] eta: 0:07:49 lr: 0.000115 grad: 0.0781 (0.0835) loss: 0.8620 (0.8649) time: 0.1436 data: 0.0623 max mem: 8452 +Train: [22] [3700/6250] eta: 0:07:33 lr: 0.000115 grad: 0.0834 (0.0836) loss: 0.8655 (0.8648) time: 0.3676 data: 0.2781 max mem: 8452 +Train: [22] [3800/6250] eta: 0:07:14 lr: 0.000115 grad: 0.0819 (0.0836) loss: 0.8613 (0.8648) time: 0.1458 data: 0.0648 max mem: 8452 +Train: [22] [3900/6250] eta: 0:06:55 lr: 0.000115 grad: 0.0777 (0.0836) loss: 0.8660 (0.8647) time: 0.1708 data: 0.0887 max mem: 8452 +Train: [22] [4000/6250] eta: 0:06:39 lr: 0.000115 grad: 0.0772 (0.0835) loss: 0.8700 (0.8648) time: 0.1318 data: 0.0005 max mem: 8452 +Train: [22] [4100/6250] eta: 0:06:22 lr: 0.000115 grad: 0.0817 (0.0835) loss: 0.8631 (0.8647) time: 0.1040 data: 0.0003 max mem: 8452 +Train: [22] [4200/6250] eta: 0:06:04 lr: 0.000115 grad: 0.0809 (0.0834) loss: 0.8635 (0.8647) time: 0.2112 data: 0.0912 max mem: 8452 +Train: [22] [4300/6250] eta: 0:05:47 lr: 0.000115 grad: 0.0838 (0.0835) loss: 0.8584 (0.8647) time: 0.1691 data: 0.0948 max mem: 8452 +Train: [22] [4400/6250] eta: 0:05:29 lr: 0.000115 grad: 0.0776 (0.0836) loss: 0.8651 (0.8646) time: 0.1841 data: 0.0880 max mem: 8452 +Train: [22] [4500/6250] eta: 0:05:12 lr: 0.000115 grad: 0.0834 (0.0836) loss: 0.8555 (0.8645) time: 0.1778 data: 0.0999 max mem: 8452 +Train: [22] [4600/6250] eta: 0:04:54 lr: 0.000115 grad: 0.0817 (0.0836) loss: 0.8561 (0.8645) time: 0.1630 data: 0.0931 max mem: 8452 +Train: [22] [4700/6250] eta: 0:04:36 lr: 0.000115 grad: 0.0820 (0.0837) loss: 0.8667 (0.8645) time: 0.1520 data: 0.0744 max mem: 8452 +Train: [22] [4800/6250] eta: 0:04:19 lr: 0.000115 grad: 0.0788 (0.0837) loss: 0.8655 (0.8645) time: 0.1926 data: 0.1205 max mem: 8452 +Train: [22] [4900/6250] eta: 0:04:01 lr: 0.000114 grad: 0.0900 (0.0837) loss: 0.8606 (0.8644) time: 0.1664 data: 0.0947 max mem: 8452 +Train: [22] [5000/6250] eta: 0:03:43 lr: 0.000114 grad: 0.0791 (0.0838) loss: 0.8573 (0.8644) time: 0.1688 data: 0.0906 max mem: 8452 +Train: [22] [5100/6250] eta: 0:03:24 lr: 0.000114 grad: 0.0816 (0.0839) loss: 0.8640 (0.8643) time: 0.1565 data: 0.0715 max mem: 8452 +Train: [22] [5200/6250] eta: 0:03:06 lr: 0.000114 grad: 0.0804 (0.0840) loss: 0.8654 (0.8643) time: 0.1463 data: 0.0717 max mem: 8452 +Train: [22] [5300/6250] eta: 0:02:48 lr: 0.000114 grad: 0.0870 (0.0840) loss: 0.8542 (0.8643) time: 0.1733 data: 0.0891 max mem: 8452 +Train: [22] [5400/6250] eta: 0:02:30 lr: 0.000114 grad: 0.0796 (0.0840) loss: 0.8656 (0.8643) time: 0.1317 data: 0.0378 max mem: 8452 +Train: [22] [5500/6250] eta: 0:02:12 lr: 0.000114 grad: 0.0765 (0.0840) loss: 0.8681 (0.8642) time: 0.1550 data: 0.0504 max mem: 8452 +Train: [22] [5600/6250] eta: 0:01:54 lr: 0.000114 grad: 0.0799 (0.0841) loss: 0.8587 (0.8642) time: 0.1447 data: 0.0520 max mem: 8452 +Train: [22] [5700/6250] eta: 0:01:36 lr: 0.000114 grad: 0.0888 (0.0841) loss: 0.8560 (0.8641) time: 0.1366 data: 0.0656 max mem: 8452 +Train: [22] [5800/6250] eta: 0:01:19 lr: 0.000114 grad: 0.0864 (0.0841) loss: 0.8578 (0.8641) time: 0.2066 data: 0.1358 max mem: 8452 +Train: [22] [5900/6250] eta: 0:01:01 lr: 0.000114 grad: 0.0805 (0.0842) loss: 0.8682 (0.8641) time: 0.1714 data: 0.0954 max mem: 8452 +Train: [22] [6000/6250] eta: 0:00:44 lr: 0.000114 grad: 0.0823 (0.0843) loss: 0.8612 (0.8640) time: 0.1173 data: 0.0364 max mem: 8452 +Train: [22] [6100/6250] eta: 0:00:26 lr: 0.000114 grad: 0.0800 (0.0843) loss: 0.8675 (0.8640) time: 0.1395 data: 0.0615 max mem: 8452 +Train: [22] [6200/6250] eta: 0:00:08 lr: 0.000114 grad: 0.0816 (0.0842) loss: 0.8625 (0.8640) time: 0.1771 data: 0.1062 max mem: 8452 +Train: [22] [6249/6250] eta: 0:00:00 lr: 0.000114 grad: 0.0807 (0.0842) loss: 0.8611 (0.8640) time: 0.1216 data: 0.0168 max mem: 8452 +Train: [22] Total time: 0:18:32 (0.1780 s / it) +Averaged stats: lr: 0.000114 grad: 0.0807 (0.0842) loss: 0.8611 (0.8640) +Eval (hcp-train-subset): [22] [ 0/62] eta: 0:06:06 loss: 0.8970 (0.8970) time: 5.9131 data: 5.8845 max mem: 8452 +Eval (hcp-train-subset): [22] [61/62] eta: 0:00:00 loss: 0.8830 (0.8834) time: 0.1901 data: 0.1686 max mem: 8452 +Eval (hcp-train-subset): [22] Total time: 0:00:16 (0.2630 s / it) +Averaged stats (hcp-train-subset): loss: 0.8830 (0.8834) +Eval (hcp-val): [22] [ 0/62] eta: 0:03:56 loss: 0.8767 (0.8767) time: 3.8120 data: 3.7741 max mem: 8452 +Eval (hcp-val): [22] [61/62] eta: 0:00:00 loss: 0.8808 (0.8821) time: 0.1902 data: 0.1683 max mem: 8452 +Eval (hcp-val): [22] Total time: 0:00:16 (0.2690 s / it) +Averaged stats (hcp-val): loss: 0.8808 (0.8821) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [23] [ 0/6250] eta: 9:14:42 lr: 0.000114 grad: 0.1468 (0.1468) loss: 0.8685 (0.8685) time: 5.3253 data: 5.1073 max mem: 8452 +Train: [23] [ 100/6250] eta: 0:26:35 lr: 0.000114 grad: 0.0944 (0.1000) loss: 0.8656 (0.8814) time: 0.2157 data: 0.1177 max mem: 8452 +Train: [23] [ 200/6250] eta: 0:22:32 lr: 0.000114 grad: 0.0829 (0.0958) loss: 0.8771 (0.8761) time: 0.1726 data: 0.0833 max mem: 8452 +Train: [23] [ 300/6250] eta: 0:20:33 lr: 0.000114 grad: 0.0782 (0.0938) loss: 0.8725 (0.8736) time: 0.1773 data: 0.0845 max mem: 8452 +Train: [23] [ 400/6250] eta: 0:19:41 lr: 0.000114 grad: 0.0950 (0.0931) loss: 0.8501 (0.8706) time: 0.1951 data: 0.1108 max mem: 8452 +Train: [23] [ 500/6250] eta: 0:19:19 lr: 0.000114 grad: 0.0796 (0.0925) loss: 0.8682 (0.8695) time: 0.1199 data: 0.0005 max mem: 8452 +Train: [23] [ 600/6250] eta: 0:18:56 lr: 0.000114 grad: 0.0787 (0.0913) loss: 0.8635 (0.8685) time: 0.2122 data: 0.1054 max mem: 8452 +Train: [23] [ 700/6250] eta: 0:18:27 lr: 0.000114 grad: 0.0715 (0.0894) loss: 0.8698 (0.8682) time: 0.1620 data: 0.0646 max mem: 8452 +Train: [23] [ 800/6250] eta: 0:17:53 lr: 0.000114 grad: 0.0703 (0.0880) loss: 0.8687 (0.8678) time: 0.1895 data: 0.1063 max mem: 8452 +Train: [23] [ 900/6250] eta: 0:17:11 lr: 0.000114 grad: 0.0776 (0.0870) loss: 0.8675 (0.8674) time: 0.1455 data: 0.0604 max mem: 8452 +Train: [23] [1000/6250] eta: 0:16:39 lr: 0.000114 grad: 0.0727 (0.0858) loss: 0.8667 (0.8675) time: 0.1731 data: 0.0786 max mem: 8452 +Train: [23] [1100/6250] eta: 0:16:10 lr: 0.000114 grad: 0.0732 (0.0849) loss: 0.8679 (0.8676) time: 0.1805 data: 0.0994 max mem: 8452 +Train: [23] [1200/6250] eta: 0:15:35 lr: 0.000114 grad: 0.0728 (0.0841) loss: 0.8647 (0.8675) time: 0.1547 data: 0.0766 max mem: 8452 +Train: [23] [1300/6250] eta: 0:15:15 lr: 0.000114 grad: 0.0693 (0.0838) loss: 0.8676 (0.8673) time: 0.2016 data: 0.1203 max mem: 8452 +Train: [23] [1400/6250] eta: 0:14:52 lr: 0.000114 grad: 0.0752 (0.0835) loss: 0.8626 (0.8671) time: 0.1796 data: 0.1029 max mem: 8452 +Train: [23] [1500/6250] eta: 0:14:29 lr: 0.000114 grad: 0.0759 (0.0832) loss: 0.8606 (0.8668) time: 0.1885 data: 0.1061 max mem: 8452 +Train: [23] [1600/6250] eta: 0:14:12 lr: 0.000114 grad: 0.0764 (0.0829) loss: 0.8620 (0.8665) time: 0.1317 data: 0.0354 max mem: 8452 +Train: [23] [1700/6250] eta: 0:13:54 lr: 0.000114 grad: 0.0745 (0.0827) loss: 0.8617 (0.8663) time: 0.2109 data: 0.1196 max mem: 8452 +Train: [23] [1800/6250] eta: 0:13:34 lr: 0.000114 grad: 0.0782 (0.0826) loss: 0.8670 (0.8661) time: 0.1701 data: 0.0519 max mem: 8452 +Train: [23] [1900/6250] eta: 0:13:14 lr: 0.000114 grad: 0.0783 (0.0825) loss: 0.8611 (0.8659) time: 0.1634 data: 0.0670 max mem: 8452 +Train: [23] [2000/6250] eta: 0:12:55 lr: 0.000114 grad: 0.0816 (0.0826) loss: 0.8585 (0.8657) time: 0.2247 data: 0.1475 max mem: 8452 +Train: [23] [2100/6250] eta: 0:12:31 lr: 0.000114 grad: 0.0918 (0.0827) loss: 0.8584 (0.8654) time: 0.1683 data: 0.0888 max mem: 8452 +Train: [23] [2200/6250] eta: 0:12:12 lr: 0.000114 grad: 0.0849 (0.0829) loss: 0.8615 (0.8651) time: 0.1721 data: 0.0984 max mem: 8452 +Train: [23] [2300/6250] eta: 0:11:50 lr: 0.000114 grad: 0.0831 (0.0829) loss: 0.8631 (0.8651) time: 0.1447 data: 0.0591 max mem: 8452 +Train: [23] [2400/6250] eta: 0:11:28 lr: 0.000114 grad: 0.0925 (0.0832) loss: 0.8553 (0.8647) time: 0.1474 data: 0.0672 max mem: 8452 +Train: [23] [2500/6250] eta: 0:11:11 lr: 0.000114 grad: 0.0813 (0.0836) loss: 0.8570 (0.8644) time: 0.1816 data: 0.1164 max mem: 8452 +Train: [23] [2600/6250] eta: 0:10:52 lr: 0.000114 grad: 0.0842 (0.0839) loss: 0.8603 (0.8640) time: 0.1652 data: 0.0911 max mem: 8452 +Train: [23] [2700/6250] eta: 0:10:33 lr: 0.000114 grad: 0.0819 (0.0840) loss: 0.8563 (0.8638) time: 0.1711 data: 0.0949 max mem: 8452 +Train: [23] [2800/6250] eta: 0:10:14 lr: 0.000114 grad: 0.0770 (0.0842) loss: 0.8582 (0.8636) time: 0.2052 data: 0.1318 max mem: 8452 +Train: [23] [2900/6250] eta: 0:09:56 lr: 0.000114 grad: 0.0830 (0.0844) loss: 0.8526 (0.8634) time: 0.1193 data: 0.0042 max mem: 8452 +Train: [23] [3000/6250] eta: 0:09:36 lr: 0.000114 grad: 0.0814 (0.0846) loss: 0.8625 (0.8632) time: 0.1518 data: 0.0791 max mem: 8452 +Train: [23] [3100/6250] eta: 0:09:19 lr: 0.000114 grad: 0.0812 (0.0846) loss: 0.8591 (0.8631) time: 0.1954 data: 0.1228 max mem: 8452 +Train: [23] [3200/6250] eta: 0:09:05 lr: 0.000114 grad: 0.0875 (0.0847) loss: 0.8556 (0.8629) time: 0.2052 data: 0.0974 max mem: 8452 +Train: [23] [3300/6250] eta: 0:08:46 lr: 0.000114 grad: 0.0814 (0.0848) loss: 0.8558 (0.8629) time: 0.1581 data: 0.0736 max mem: 8452 +Train: [23] [3400/6250] eta: 0:08:28 lr: 0.000114 grad: 0.0830 (0.0847) loss: 0.8612 (0.8629) time: 0.1740 data: 0.0712 max mem: 8452 +Train: [23] [3500/6250] eta: 0:08:11 lr: 0.000114 grad: 0.0837 (0.0848) loss: 0.8633 (0.8628) time: 0.1176 data: 0.0189 max mem: 8452 +Train: [23] [3600/6250] eta: 0:07:53 lr: 0.000114 grad: 0.0800 (0.0848) loss: 0.8576 (0.8627) time: 0.1135 data: 0.0174 max mem: 8452 +Train: [23] [3700/6250] eta: 0:07:37 lr: 0.000114 grad: 0.0820 (0.0849) loss: 0.8539 (0.8625) time: 0.2969 data: 0.1989 max mem: 8452 +Train: [23] [3800/6250] eta: 0:07:17 lr: 0.000114 grad: 0.0815 (0.0850) loss: 0.8590 (0.8624) time: 0.1466 data: 0.0597 max mem: 8452 +Train: [23] [3900/6250] eta: 0:07:00 lr: 0.000114 grad: 0.0838 (0.0851) loss: 0.8572 (0.8623) time: 0.1397 data: 0.0289 max mem: 8452 +Train: [23] [4000/6250] eta: 0:06:46 lr: 0.000113 grad: 0.0861 (0.0853) loss: 0.8595 (0.8621) time: 0.4548 data: 0.3500 max mem: 8452 +Train: [23] [4100/6250] eta: 0:06:27 lr: 0.000113 grad: 0.0797 (0.0853) loss: 0.8522 (0.8619) time: 0.1412 data: 0.0647 max mem: 8452 +Train: [23] [4200/6250] eta: 0:06:08 lr: 0.000113 grad: 0.0825 (0.0854) loss: 0.8622 (0.8618) time: 0.1662 data: 0.0880 max mem: 8452 +Train: [23] [4300/6250] eta: 0:05:50 lr: 0.000113 grad: 0.0791 (0.0854) loss: 0.8665 (0.8617) time: 0.1970 data: 0.0613 max mem: 8452 +Train: [23] [4400/6250] eta: 0:05:32 lr: 0.000113 grad: 0.0864 (0.0856) loss: 0.8590 (0.8615) time: 0.2285 data: 0.1671 max mem: 8452 +Train: [23] [4500/6250] eta: 0:05:14 lr: 0.000113 grad: 0.0889 (0.0856) loss: 0.8516 (0.8614) time: 0.1534 data: 0.0807 max mem: 8452 +Train: [23] [4600/6250] eta: 0:04:56 lr: 0.000113 grad: 0.0808 (0.0856) loss: 0.8535 (0.8612) time: 0.1694 data: 0.1036 max mem: 8452 +Train: [23] [4700/6250] eta: 0:04:38 lr: 0.000113 grad: 0.0835 (0.0856) loss: 0.8537 (0.8611) time: 0.1748 data: 0.0971 max mem: 8452 +Train: [23] [4800/6250] eta: 0:04:20 lr: 0.000113 grad: 0.0806 (0.0856) loss: 0.8620 (0.8610) time: 0.1750 data: 0.1056 max mem: 8452 +Train: [23] [4900/6250] eta: 0:04:02 lr: 0.000113 grad: 0.0832 (0.0856) loss: 0.8537 (0.8609) time: 0.1680 data: 0.0772 max mem: 8452 +Train: [23] [5000/6250] eta: 0:03:43 lr: 0.000113 grad: 0.0808 (0.0856) loss: 0.8561 (0.8608) time: 0.1698 data: 0.1033 max mem: 8452 +Train: [23] [5100/6250] eta: 0:03:25 lr: 0.000113 grad: 0.0790 (0.0855) loss: 0.8558 (0.8608) time: 0.1844 data: 0.1069 max mem: 8452 +Train: [23] [5200/6250] eta: 0:03:07 lr: 0.000113 grad: 0.0857 (0.0856) loss: 0.8556 (0.8607) time: 0.1781 data: 0.1014 max mem: 8452 +Train: [23] [5300/6250] eta: 0:02:49 lr: 0.000113 grad: 0.0819 (0.0855) loss: 0.8590 (0.8607) time: 0.1692 data: 0.0862 max mem: 8452 +Train: [23] [5400/6250] eta: 0:02:30 lr: 0.000113 grad: 0.0878 (0.0856) loss: 0.8624 (0.8607) time: 0.1772 data: 0.0940 max mem: 8452 +Train: [23] [5500/6250] eta: 0:02:12 lr: 0.000113 grad: 0.0825 (0.0856) loss: 0.8587 (0.8607) time: 0.1895 data: 0.1074 max mem: 8452 +Train: [23] [5600/6250] eta: 0:01:54 lr: 0.000113 grad: 0.0854 (0.0856) loss: 0.8556 (0.8607) time: 0.1831 data: 0.1115 max mem: 8452 +Train: [23] [5700/6250] eta: 0:01:37 lr: 0.000113 grad: 0.0843 (0.0856) loss: 0.8574 (0.8607) time: 0.1673 data: 0.0750 max mem: 8452 +Train: [23] [5800/6250] eta: 0:01:19 lr: 0.000113 grad: 0.0790 (0.0855) loss: 0.8595 (0.8607) time: 0.1845 data: 0.1106 max mem: 8452 +Train: [23] [5900/6250] eta: 0:01:01 lr: 0.000113 grad: 0.0818 (0.0855) loss: 0.8587 (0.8607) time: 0.1091 data: 0.0143 max mem: 8452 +Train: [23] [6000/6250] eta: 0:00:44 lr: 0.000113 grad: 0.0817 (0.0857) loss: 0.8568 (0.8607) time: 0.1525 data: 0.0726 max mem: 8452 +Train: [23] [6100/6250] eta: 0:00:26 lr: 0.000113 grad: 0.0760 (0.0856) loss: 0.8572 (0.8606) time: 0.1663 data: 0.0840 max mem: 8452 +Train: [23] [6200/6250] eta: 0:00:08 lr: 0.000113 grad: 0.0842 (0.0857) loss: 0.8670 (0.8606) time: 0.1455 data: 0.0652 max mem: 8452 +Train: [23] [6249/6250] eta: 0:00:00 lr: 0.000113 grad: 0.0777 (0.0856) loss: 0.8660 (0.8606) time: 0.1523 data: 0.0643 max mem: 8452 +Train: [23] Total time: 0:18:28 (0.1774 s / it) +Averaged stats: lr: 0.000113 grad: 0.0777 (0.0856) loss: 0.8660 (0.8606) +Eval (hcp-train-subset): [23] [ 0/62] eta: 0:04:27 loss: 0.8971 (0.8971) time: 4.3148 data: 4.2053 max mem: 8452 +Eval (hcp-train-subset): [23] [61/62] eta: 0:00:00 loss: 0.8827 (0.8841) time: 0.1462 data: 0.1249 max mem: 8452 +Eval (hcp-train-subset): [23] Total time: 0:00:14 (0.2301 s / it) +Averaged stats (hcp-train-subset): loss: 0.8827 (0.8841) +Eval (hcp-val): [23] [ 0/62] eta: 0:04:23 loss: 0.8783 (0.8783) time: 4.2441 data: 4.1706 max mem: 8452 +Eval (hcp-val): [23] [61/62] eta: 0:00:00 loss: 0.8806 (0.8819) time: 0.1408 data: 0.1192 max mem: 8452 +Eval (hcp-val): [23] Total time: 0:00:14 (0.2307 s / it) +Averaged stats (hcp-val): loss: 0.8806 (0.8819) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [24] [ 0/6250] eta: 8:12:07 lr: 0.000113 grad: 0.1693 (0.1693) loss: 0.8788 (0.8788) time: 4.7244 data: 4.4129 max mem: 8452 +Train: [24] [ 100/6250] eta: 0:22:50 lr: 0.000113 grad: 0.1061 (0.1158) loss: 0.8675 (0.8734) time: 0.1745 data: 0.0921 max mem: 8452 +Train: [24] [ 200/6250] eta: 0:19:46 lr: 0.000113 grad: 0.0806 (0.1055) loss: 0.8729 (0.8711) time: 0.1806 data: 0.0993 max mem: 8452 +Train: [24] [ 300/6250] eta: 0:18:31 lr: 0.000113 grad: 0.0867 (0.0979) loss: 0.8681 (0.8708) time: 0.1524 data: 0.0703 max mem: 8452 +Train: [24] [ 400/6250] eta: 0:17:38 lr: 0.000113 grad: 0.0799 (0.0964) loss: 0.8608 (0.8699) time: 0.1696 data: 0.0951 max mem: 8452 +Train: [24] [ 500/6250] eta: 0:17:28 lr: 0.000113 grad: 0.0771 (0.0939) loss: 0.8632 (0.8684) time: 0.1908 data: 0.1055 max mem: 8452 +Train: [24] [ 600/6250] eta: 0:17:28 lr: 0.000113 grad: 0.0810 (0.0923) loss: 0.8597 (0.8668) time: 0.2308 data: 0.1356 max mem: 8452 +Train: [24] [ 700/6250] eta: 0:17:29 lr: 0.000113 grad: 0.0826 (0.0910) loss: 0.8672 (0.8659) time: 0.2603 data: 0.1783 max mem: 8452 +Train: [24] [ 800/6250] eta: 0:17:00 lr: 0.000113 grad: 0.0791 (0.0902) loss: 0.8580 (0.8655) time: 0.1696 data: 0.0849 max mem: 8452 +Train: [24] [ 900/6250] eta: 0:16:37 lr: 0.000113 grad: 0.0904 (0.0896) loss: 0.8587 (0.8647) time: 0.1837 data: 0.1046 max mem: 8452 +Train: [24] [1000/6250] eta: 0:16:10 lr: 0.000113 grad: 0.0774 (0.0890) loss: 0.8579 (0.8639) time: 0.2039 data: 0.1259 max mem: 8452 +Train: [24] [1100/6250] eta: 0:15:44 lr: 0.000113 grad: 0.0818 (0.0885) loss: 0.8551 (0.8633) time: 0.1686 data: 0.0856 max mem: 8452 +Train: [24] [1200/6250] eta: 0:15:19 lr: 0.000113 grad: 0.0822 (0.0883) loss: 0.8537 (0.8627) time: 0.1656 data: 0.0868 max mem: 8452 +Train: [24] [1300/6250] eta: 0:14:55 lr: 0.000113 grad: 0.0802 (0.0878) loss: 0.8563 (0.8624) time: 0.1654 data: 0.0810 max mem: 8452 +Train: [24] [1400/6250] eta: 0:14:28 lr: 0.000113 grad: 0.0861 (0.0879) loss: 0.8582 (0.8620) time: 0.1399 data: 0.0518 max mem: 8452 +Train: [24] [1500/6250] eta: 0:14:09 lr: 0.000113 grad: 0.0759 (0.0876) loss: 0.8593 (0.8618) time: 0.1828 data: 0.1087 max mem: 8452 +Train: [24] [1600/6250] eta: 0:13:48 lr: 0.000113 grad: 0.0763 (0.0873) loss: 0.8525 (0.8616) time: 0.1911 data: 0.1177 max mem: 8452 +Train: [24] [1700/6250] eta: 0:13:33 lr: 0.000113 grad: 0.0772 (0.0869) loss: 0.8573 (0.8615) time: 0.1913 data: 0.0707 max mem: 8452 +Train: [24] [1800/6250] eta: 0:13:17 lr: 0.000113 grad: 0.0847 (0.0865) loss: 0.8530 (0.8614) time: 0.1978 data: 0.0840 max mem: 8452 +Train: [24] [1900/6250] eta: 0:13:04 lr: 0.000113 grad: 0.0781 (0.0863) loss: 0.8624 (0.8614) time: 0.2186 data: 0.1122 max mem: 8452 +Train: [24] [2000/6250] eta: 0:12:48 lr: 0.000113 grad: 0.0803 (0.0862) loss: 0.8655 (0.8614) time: 0.1190 data: 0.0004 max mem: 8452 +Train: [24] [2100/6250] eta: 0:12:29 lr: 0.000113 grad: 0.0896 (0.0860) loss: 0.8571 (0.8613) time: 0.1458 data: 0.0654 max mem: 8452 +Train: [24] [2200/6250] eta: 0:12:09 lr: 0.000113 grad: 0.0827 (0.0861) loss: 0.8562 (0.8612) time: 0.1566 data: 0.0422 max mem: 8452 +Train: [24] [2300/6250] eta: 0:11:53 lr: 0.000113 grad: 0.0779 (0.0859) loss: 0.8617 (0.8612) time: 0.2116 data: 0.1398 max mem: 8452 +Train: [24] [2400/6250] eta: 0:11:31 lr: 0.000113 grad: 0.0760 (0.0856) loss: 0.8611 (0.8612) time: 0.1648 data: 0.0798 max mem: 8452 +Train: [24] [2500/6250] eta: 0:11:11 lr: 0.000113 grad: 0.0797 (0.0855) loss: 0.8601 (0.8611) time: 0.1714 data: 0.1002 max mem: 8452 +Train: [24] [2600/6250] eta: 0:10:49 lr: 0.000113 grad: 0.0797 (0.0854) loss: 0.8593 (0.8610) time: 0.1645 data: 0.0854 max mem: 8452 +Train: [24] [2700/6250] eta: 0:10:29 lr: 0.000113 grad: 0.0706 (0.0851) loss: 0.8672 (0.8611) time: 0.1624 data: 0.0859 max mem: 8452 +Train: [24] [2800/6250] eta: 0:10:12 lr: 0.000113 grad: 0.0828 (0.0850) loss: 0.8624 (0.8610) time: 0.1614 data: 0.0908 max mem: 8452 +Train: [24] [2900/6250] eta: 0:09:53 lr: 0.000112 grad: 0.0806 (0.0848) loss: 0.8644 (0.8610) time: 0.1693 data: 0.0834 max mem: 8452 +Train: [24] [3000/6250] eta: 0:09:36 lr: 0.000112 grad: 0.0798 (0.0848) loss: 0.8592 (0.8610) time: 0.2141 data: 0.1349 max mem: 8452 +Train: [24] [3100/6250] eta: 0:09:19 lr: 0.000112 grad: 0.0790 (0.0847) loss: 0.8607 (0.8609) time: 0.1495 data: 0.0750 max mem: 8452 +Train: [24] [3200/6250] eta: 0:09:00 lr: 0.000112 grad: 0.0785 (0.0846) loss: 0.8565 (0.8609) time: 0.1471 data: 0.0643 max mem: 8452 +Train: [24] [3300/6250] eta: 0:08:42 lr: 0.000112 grad: 0.0863 (0.0847) loss: 0.8566 (0.8608) time: 0.1841 data: 0.1087 max mem: 8452 +Train: [24] [3400/6250] eta: 0:08:25 lr: 0.000112 grad: 0.0762 (0.0847) loss: 0.8594 (0.8608) time: 0.2075 data: 0.1312 max mem: 8452 +Train: [24] [3500/6250] eta: 0:08:07 lr: 0.000112 grad: 0.0798 (0.0846) loss: 0.8743 (0.8607) time: 0.1775 data: 0.0893 max mem: 8452 +Train: [24] [3600/6250] eta: 0:07:49 lr: 0.000112 grad: 0.0813 (0.0847) loss: 0.8584 (0.8607) time: 0.1896 data: 0.1166 max mem: 8452 +Train: [24] [3700/6250] eta: 0:07:31 lr: 0.000112 grad: 0.0759 (0.0847) loss: 0.8599 (0.8607) time: 0.1717 data: 0.0899 max mem: 8452 +Train: [24] [3800/6250] eta: 0:07:13 lr: 0.000112 grad: 0.0747 (0.0847) loss: 0.8563 (0.8607) time: 0.1818 data: 0.0816 max mem: 8452 +Train: [24] [3900/6250] eta: 0:06:56 lr: 0.000112 grad: 0.0796 (0.0847) loss: 0.8578 (0.8606) time: 0.2295 data: 0.1553 max mem: 8452 +Train: [24] [4000/6250] eta: 0:06:37 lr: 0.000112 grad: 0.0853 (0.0847) loss: 0.8523 (0.8606) time: 0.1620 data: 0.0713 max mem: 8452 +Train: [24] [4100/6250] eta: 0:06:19 lr: 0.000112 grad: 0.0791 (0.0848) loss: 0.8592 (0.8605) time: 0.1469 data: 0.0669 max mem: 8452 +Train: [24] [4200/6250] eta: 0:06:02 lr: 0.000112 grad: 0.0821 (0.0848) loss: 0.8589 (0.8604) time: 0.1828 data: 0.1090 max mem: 8452 +Train: [24] [4300/6250] eta: 0:05:44 lr: 0.000112 grad: 0.0789 (0.0848) loss: 0.8603 (0.8604) time: 0.1642 data: 0.0866 max mem: 8452 +Train: [24] [4400/6250] eta: 0:05:26 lr: 0.000112 grad: 0.0779 (0.0848) loss: 0.8613 (0.8604) time: 0.1867 data: 0.1076 max mem: 8452 +Train: [24] [4500/6250] eta: 0:05:08 lr: 0.000112 grad: 0.0844 (0.0849) loss: 0.8612 (0.8603) time: 0.1344 data: 0.0663 max mem: 8452 +Train: [24] [4600/6250] eta: 0:04:51 lr: 0.000112 grad: 0.0808 (0.0849) loss: 0.8545 (0.8602) time: 0.1812 data: 0.1071 max mem: 8452 +Train: [24] [4700/6250] eta: 0:04:33 lr: 0.000112 grad: 0.0850 (0.0850) loss: 0.8578 (0.8602) time: 0.2588 data: 0.1853 max mem: 8452 +Train: [24] [4800/6250] eta: 0:04:15 lr: 0.000112 grad: 0.0877 (0.0850) loss: 0.8538 (0.8601) time: 0.1632 data: 0.0863 max mem: 8452 +Train: [24] [4900/6250] eta: 0:03:57 lr: 0.000112 grad: 0.0793 (0.0849) loss: 0.8562 (0.8601) time: 0.1614 data: 0.0867 max mem: 8452 +Train: [24] [5000/6250] eta: 0:03:39 lr: 0.000112 grad: 0.0791 (0.0848) loss: 0.8559 (0.8601) time: 0.1421 data: 0.0588 max mem: 8452 +Train: [24] [5100/6250] eta: 0:03:22 lr: 0.000112 grad: 0.0860 (0.0849) loss: 0.8648 (0.8601) time: 0.1560 data: 0.0667 max mem: 8452 +Train: [24] [5200/6250] eta: 0:03:04 lr: 0.000112 grad: 0.0822 (0.0849) loss: 0.8529 (0.8600) time: 0.1614 data: 0.0735 max mem: 8452 +Train: [24] [5300/6250] eta: 0:02:46 lr: 0.000112 grad: 0.0816 (0.0849) loss: 0.8561 (0.8600) time: 0.1774 data: 0.0910 max mem: 8452 +Train: [24] [5400/6250] eta: 0:02:28 lr: 0.000112 grad: 0.0777 (0.0849) loss: 0.8639 (0.8599) time: 0.1659 data: 0.0730 max mem: 8452 +Train: [24] [5500/6250] eta: 0:02:11 lr: 0.000112 grad: 0.0808 (0.0849) loss: 0.8585 (0.8599) time: 0.1345 data: 0.0426 max mem: 8452 +Train: [24] [5600/6250] eta: 0:01:53 lr: 0.000112 grad: 0.0783 (0.0848) loss: 0.8584 (0.8598) time: 0.1713 data: 0.0846 max mem: 8452 +Train: [24] [5700/6250] eta: 0:01:35 lr: 0.000112 grad: 0.0810 (0.0848) loss: 0.8567 (0.8597) time: 0.1364 data: 0.0574 max mem: 8452 +Train: [24] [5800/6250] eta: 0:01:18 lr: 0.000112 grad: 0.0777 (0.0849) loss: 0.8631 (0.8597) time: 0.1355 data: 0.0539 max mem: 8452 +Train: [24] [5900/6250] eta: 0:01:00 lr: 0.000112 grad: 0.0764 (0.0849) loss: 0.8603 (0.8597) time: 0.1591 data: 0.0653 max mem: 8452 +Train: [24] [6000/6250] eta: 0:00:43 lr: 0.000112 grad: 0.0860 (0.0849) loss: 0.8532 (0.8597) time: 0.1568 data: 0.0760 max mem: 8452 +Train: [24] [6100/6250] eta: 0:00:26 lr: 0.000112 grad: 0.0890 (0.0849) loss: 0.8617 (0.8597) time: 0.1677 data: 0.0683 max mem: 8452 +Train: [24] [6200/6250] eta: 0:00:08 lr: 0.000112 grad: 0.0801 (0.0850) loss: 0.8584 (0.8596) time: 0.1419 data: 0.0577 max mem: 8452 +Train: [24] [6249/6250] eta: 0:00:00 lr: 0.000112 grad: 0.0928 (0.0850) loss: 0.8602 (0.8596) time: 0.1611 data: 0.0844 max mem: 8452 +Train: [24] Total time: 0:18:12 (0.1748 s / it) +Averaged stats: lr: 0.000112 grad: 0.0928 (0.0850) loss: 0.8602 (0.8596) +Eval (hcp-train-subset): [24] [ 0/62] eta: 0:03:23 loss: 0.8870 (0.8870) time: 3.2815 data: 3.2021 max mem: 8452 +Eval (hcp-train-subset): [24] [61/62] eta: 0:00:00 loss: 0.8826 (0.8835) time: 0.1441 data: 0.1230 max mem: 8452 +Eval (hcp-train-subset): [24] Total time: 0:00:14 (0.2396 s / it) +Averaged stats (hcp-train-subset): loss: 0.8826 (0.8835) +Making plots (hcp-train-subset): example=34 +Eval (hcp-val): [24] [ 0/62] eta: 0:07:57 loss: 0.8791 (0.8791) time: 7.7005 data: 7.6234 max mem: 8452 +Eval (hcp-val): [24] [61/62] eta: 0:00:00 loss: 0.8787 (0.8809) time: 0.1420 data: 0.1207 max mem: 8452 +Eval (hcp-val): [24] Total time: 0:00:17 (0.2854 s / it) +Averaged stats (hcp-val): loss: 0.8787 (0.8809) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [25] [ 0/6250] eta: 10:25:59 lr: 0.000112 grad: 0.0907 (0.0907) loss: 0.9011 (0.9011) time: 6.0095 data: 5.8827 max mem: 8452 +Train: [25] [ 100/6250] eta: 0:22:36 lr: 0.000112 grad: 0.0890 (0.1021) loss: 0.8741 (0.8771) time: 0.1791 data: 0.0823 max mem: 8452 +Train: [25] [ 200/6250] eta: 0:19:45 lr: 0.000112 grad: 0.0896 (0.0989) loss: 0.8556 (0.8701) time: 0.1641 data: 0.0780 max mem: 8452 +Train: [25] [ 300/6250] eta: 0:18:32 lr: 0.000112 grad: 0.0787 (0.0963) loss: 0.8634 (0.8667) time: 0.1718 data: 0.0823 max mem: 8452 +Train: [25] [ 400/6250] eta: 0:17:30 lr: 0.000112 grad: 0.0766 (0.0942) loss: 0.8641 (0.8649) time: 0.1205 data: 0.0296 max mem: 8452 +Train: [25] [ 500/6250] eta: 0:16:47 lr: 0.000112 grad: 0.0807 (0.0922) loss: 0.8587 (0.8643) time: 0.1495 data: 0.0547 max mem: 8452 +Train: [25] [ 600/6250] eta: 0:16:11 lr: 0.000112 grad: 0.0821 (0.0912) loss: 0.8611 (0.8638) time: 0.1429 data: 0.0549 max mem: 8452 +Train: [25] [ 700/6250] eta: 0:16:06 lr: 0.000112 grad: 0.0817 (0.0904) loss: 0.8637 (0.8632) time: 0.2078 data: 0.1243 max mem: 8452 +Train: [25] [ 800/6250] eta: 0:15:59 lr: 0.000112 grad: 0.0847 (0.0900) loss: 0.8576 (0.8629) time: 0.1818 data: 0.1014 max mem: 8452 +Train: [25] [ 900/6250] eta: 0:15:38 lr: 0.000112 grad: 0.0771 (0.0889) loss: 0.8704 (0.8629) time: 0.1575 data: 0.0672 max mem: 8452 +Train: [25] [1000/6250] eta: 0:15:13 lr: 0.000112 grad: 0.0845 (0.0886) loss: 0.8592 (0.8630) time: 0.1663 data: 0.0840 max mem: 8452 +Train: [25] [1100/6250] eta: 0:14:54 lr: 0.000112 grad: 0.0838 (0.0884) loss: 0.8550 (0.8627) time: 0.1777 data: 0.1084 max mem: 8452 +Train: [25] [1200/6250] eta: 0:14:33 lr: 0.000112 grad: 0.0780 (0.0883) loss: 0.8590 (0.8623) time: 0.1683 data: 0.0827 max mem: 8452 +Train: [25] [1300/6250] eta: 0:14:12 lr: 0.000112 grad: 0.0862 (0.0881) loss: 0.8545 (0.8619) time: 0.1580 data: 0.0681 max mem: 8452 +Train: [25] [1400/6250] eta: 0:13:50 lr: 0.000112 grad: 0.0876 (0.0885) loss: 0.8505 (0.8614) time: 0.1693 data: 0.0788 max mem: 8452 +Train: [25] [1500/6250] eta: 0:13:27 lr: 0.000112 grad: 0.0849 (0.0885) loss: 0.8543 (0.8610) time: 0.1589 data: 0.0748 max mem: 8452 +Train: [25] [1600/6250] eta: 0:13:07 lr: 0.000111 grad: 0.0820 (0.0884) loss: 0.8540 (0.8605) time: 0.1724 data: 0.0850 max mem: 8452 +Train: [25] [1700/6250] eta: 0:12:51 lr: 0.000111 grad: 0.0829 (0.0883) loss: 0.8587 (0.8601) time: 0.1240 data: 0.0471 max mem: 8452 +Train: [25] [1800/6250] eta: 0:12:41 lr: 0.000111 grad: 0.0859 (0.0882) loss: 0.8545 (0.8597) time: 0.2581 data: 0.1229 max mem: 8452 +Train: [25] [1900/6250] eta: 0:12:29 lr: 0.000111 grad: 0.0887 (0.0882) loss: 0.8642 (0.8594) time: 0.1797 data: 0.0658 max mem: 8452 +Train: [25] [2000/6250] eta: 0:12:12 lr: 0.000111 grad: 0.0920 (0.0884) loss: 0.8604 (0.8591) time: 0.1828 data: 0.0990 max mem: 8452 +Train: [25] [2100/6250] eta: 0:11:52 lr: 0.000111 grad: 0.0898 (0.0886) loss: 0.8590 (0.8588) time: 0.1658 data: 0.0617 max mem: 8452 +Train: [25] [2200/6250] eta: 0:11:39 lr: 0.000111 grad: 0.0850 (0.0887) loss: 0.8562 (0.8586) time: 0.1626 data: 0.0578 max mem: 8452 +Train: [25] [2300/6250] eta: 0:11:20 lr: 0.000111 grad: 0.0856 (0.0888) loss: 0.8560 (0.8584) time: 0.1024 data: 0.0008 max mem: 8452 +Train: [25] [2400/6250] eta: 0:11:07 lr: 0.000111 grad: 0.0798 (0.0889) loss: 0.8506 (0.8583) time: 0.1307 data: 0.0379 max mem: 8452 +Train: [25] [2500/6250] eta: 0:10:48 lr: 0.000111 grad: 0.0802 (0.0889) loss: 0.8521 (0.8582) time: 0.1760 data: 0.0645 max mem: 8452 +Train: [25] [2600/6250] eta: 0:10:33 lr: 0.000111 grad: 0.0931 (0.0891) loss: 0.8553 (0.8580) time: 0.1535 data: 0.0393 max mem: 8452 +Train: [25] [2700/6250] eta: 0:10:14 lr: 0.000111 grad: 0.0932 (0.0893) loss: 0.8495 (0.8578) time: 0.1643 data: 0.0714 max mem: 8452 +Train: [25] [2800/6250] eta: 0:09:55 lr: 0.000111 grad: 0.0826 (0.0893) loss: 0.8595 (0.8576) time: 0.1465 data: 0.0668 max mem: 8452 +Train: [25] [2900/6250] eta: 0:09:36 lr: 0.000111 grad: 0.0858 (0.0894) loss: 0.8592 (0.8575) time: 0.1681 data: 0.0900 max mem: 8452 +Train: [25] [3000/6250] eta: 0:09:19 lr: 0.000111 grad: 0.0837 (0.0894) loss: 0.8532 (0.8574) time: 0.1916 data: 0.1160 max mem: 8452 +Train: [25] [3100/6250] eta: 0:09:03 lr: 0.000111 grad: 0.0840 (0.0893) loss: 0.8553 (0.8574) time: 0.1718 data: 0.0963 max mem: 8452 +Train: [25] [3200/6250] eta: 0:08:47 lr: 0.000111 grad: 0.0856 (0.0893) loss: 0.8570 (0.8574) time: 0.1698 data: 0.0772 max mem: 8452 +Train: [25] [3300/6250] eta: 0:08:30 lr: 0.000111 grad: 0.0793 (0.0893) loss: 0.8629 (0.8574) time: 0.1684 data: 0.0899 max mem: 8452 +Train: [25] [3400/6250] eta: 0:08:15 lr: 0.000111 grad: 0.0857 (0.0892) loss: 0.8523 (0.8574) time: 0.2249 data: 0.1398 max mem: 8452 +Train: [25] [3500/6250] eta: 0:07:56 lr: 0.000111 grad: 0.0873 (0.0892) loss: 0.8540 (0.8574) time: 0.1791 data: 0.1006 max mem: 8452 +Train: [25] [3600/6250] eta: 0:07:38 lr: 0.000111 grad: 0.0868 (0.0891) loss: 0.8585 (0.8573) time: 0.1664 data: 0.0869 max mem: 8452 +Train: [25] [3700/6250] eta: 0:07:23 lr: 0.000111 grad: 0.0795 (0.0891) loss: 0.8610 (0.8573) time: 0.2684 data: 0.1735 max mem: 8452 +Train: [25] [3800/6250] eta: 0:07:04 lr: 0.000111 grad: 0.0930 (0.0892) loss: 0.8576 (0.8573) time: 0.1634 data: 0.0801 max mem: 8452 +Train: [25] [3900/6250] eta: 0:06:49 lr: 0.000111 grad: 0.0755 (0.0892) loss: 0.8584 (0.8572) time: 0.2591 data: 0.1760 max mem: 8452 +Train: [25] [4000/6250] eta: 0:06:31 lr: 0.000111 grad: 0.0830 (0.0891) loss: 0.8575 (0.8572) time: 0.1782 data: 0.0824 max mem: 8452 +Train: [25] [4100/6250] eta: 0:06:15 lr: 0.000111 grad: 0.0821 (0.0890) loss: 0.8567 (0.8572) time: 0.2717 data: 0.1933 max mem: 8452 +Train: [25] [4200/6250] eta: 0:05:58 lr: 0.000111 grad: 0.0825 (0.0890) loss: 0.8558 (0.8572) time: 0.1955 data: 0.1118 max mem: 8452 +Train: [25] [4300/6250] eta: 0:05:40 lr: 0.000111 grad: 0.0819 (0.0889) loss: 0.8520 (0.8571) time: 0.1644 data: 0.0931 max mem: 8452 +Train: [25] [4400/6250] eta: 0:05:23 lr: 0.000111 grad: 0.0810 (0.0889) loss: 0.8532 (0.8571) time: 0.1775 data: 0.0980 max mem: 8452 +Train: [25] [4500/6250] eta: 0:05:06 lr: 0.000111 grad: 0.0840 (0.0888) loss: 0.8520 (0.8571) time: 0.1767 data: 0.0896 max mem: 8452 +Train: [25] [4600/6250] eta: 0:04:48 lr: 0.000111 grad: 0.0813 (0.0887) loss: 0.8585 (0.8572) time: 0.1968 data: 0.1178 max mem: 8452 +Train: [25] [4700/6250] eta: 0:04:30 lr: 0.000111 grad: 0.0799 (0.0887) loss: 0.8588 (0.8572) time: 0.1780 data: 0.0998 max mem: 8452 +Train: [25] [4800/6250] eta: 0:04:12 lr: 0.000111 grad: 0.0808 (0.0886) loss: 0.8567 (0.8572) time: 0.1601 data: 0.0765 max mem: 8452 +Train: [25] [4900/6250] eta: 0:03:54 lr: 0.000111 grad: 0.0808 (0.0886) loss: 0.8578 (0.8572) time: 0.1575 data: 0.0793 max mem: 8452 +Train: [25] [5000/6250] eta: 0:03:37 lr: 0.000111 grad: 0.0784 (0.0885) loss: 0.8619 (0.8572) time: 0.1375 data: 0.0487 max mem: 8452 +Train: [25] [5100/6250] eta: 0:03:19 lr: 0.000111 grad: 0.0783 (0.0886) loss: 0.8655 (0.8573) time: 0.1570 data: 0.0792 max mem: 8452 +Train: [25] [5200/6250] eta: 0:03:02 lr: 0.000111 grad: 0.0800 (0.0886) loss: 0.8637 (0.8574) time: 0.1693 data: 0.0834 max mem: 8452 +Train: [25] [5300/6250] eta: 0:02:44 lr: 0.000111 grad: 0.0821 (0.0885) loss: 0.8600 (0.8574) time: 0.1894 data: 0.0795 max mem: 8452 +Train: [25] [5400/6250] eta: 0:02:27 lr: 0.000111 grad: 0.0778 (0.0884) loss: 0.8598 (0.8575) time: 0.2133 data: 0.1286 max mem: 8452 +Train: [25] [5500/6250] eta: 0:02:10 lr: 0.000111 grad: 0.0748 (0.0884) loss: 0.8634 (0.8575) time: 0.2698 data: 0.1519 max mem: 8452 +Train: [25] [5600/6250] eta: 0:01:53 lr: 0.000111 grad: 0.0855 (0.0883) loss: 0.8578 (0.8575) time: 0.1787 data: 0.1038 max mem: 8452 +Train: [25] [5700/6250] eta: 0:01:35 lr: 0.000111 grad: 0.0845 (0.0883) loss: 0.8612 (0.8575) time: 0.1611 data: 0.0615 max mem: 8452 +Train: [25] [5800/6250] eta: 0:01:18 lr: 0.000111 grad: 0.0813 (0.0882) loss: 0.8500 (0.8575) time: 0.1064 data: 0.0003 max mem: 8452 +Train: [25] [5900/6250] eta: 0:01:01 lr: 0.000111 grad: 0.0808 (0.0882) loss: 0.8633 (0.8574) time: 0.1588 data: 0.0768 max mem: 8452 +Train: [25] [6000/6250] eta: 0:00:43 lr: 0.000111 grad: 0.0869 (0.0882) loss: 0.8489 (0.8574) time: 0.1802 data: 0.0822 max mem: 8452 +Train: [25] [6100/6250] eta: 0:00:26 lr: 0.000111 grad: 0.0859 (0.0882) loss: 0.8515 (0.8573) time: 0.1678 data: 0.0897 max mem: 8452 +Train: [25] [6200/6250] eta: 0:00:08 lr: 0.000111 grad: 0.0832 (0.0882) loss: 0.8533 (0.8574) time: 0.1427 data: 0.0600 max mem: 8452 +Train: [25] [6249/6250] eta: 0:00:00 lr: 0.000111 grad: 0.0844 (0.0881) loss: 0.8551 (0.8574) time: 0.1633 data: 0.0823 max mem: 8452 +Train: [25] Total time: 0:18:15 (0.1753 s / it) +Averaged stats: lr: 0.000111 grad: 0.0844 (0.0881) loss: 0.8551 (0.8574) +Eval (hcp-train-subset): [25] [ 0/62] eta: 0:05:51 loss: 0.8962 (0.8962) time: 5.6721 data: 5.6438 max mem: 8452 +Eval (hcp-train-subset): [25] [61/62] eta: 0:00:00 loss: 0.8828 (0.8825) time: 0.1265 data: 0.1040 max mem: 8452 +Eval (hcp-train-subset): [25] Total time: 0:00:14 (0.2367 s / it) +Averaged stats (hcp-train-subset): loss: 0.8828 (0.8825) +Eval (hcp-val): [25] [ 0/62] eta: 0:04:42 loss: 0.8756 (0.8756) time: 4.5513 data: 4.4886 max mem: 8452 +Eval (hcp-val): [25] [61/62] eta: 0:00:00 loss: 0.8791 (0.8803) time: 0.1147 data: 0.0935 max mem: 8452 +Eval (hcp-val): [25] Total time: 0:00:14 (0.2385 s / it) +Averaged stats (hcp-val): loss: 0.8791 (0.8803) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [26] [ 0/6250] eta: 10:59:42 lr: 0.000111 grad: 0.0918 (0.0918) loss: 0.8977 (0.8977) time: 6.3333 data: 6.2313 max mem: 8452 +Train: [26] [ 100/6250] eta: 0:22:07 lr: 0.000111 grad: 0.0976 (0.1113) loss: 0.8625 (0.8683) time: 0.1626 data: 0.0587 max mem: 8452 +Train: [26] [ 200/6250] eta: 0:19:29 lr: 0.000110 grad: 0.0951 (0.1107) loss: 0.8637 (0.8616) time: 0.1599 data: 0.0661 max mem: 8452 +Train: [26] [ 300/6250] eta: 0:18:06 lr: 0.000110 grad: 0.0984 (0.1068) loss: 0.8482 (0.8579) time: 0.1591 data: 0.0738 max mem: 8452 +Train: [26] [ 400/6250] eta: 0:17:15 lr: 0.000110 grad: 0.0899 (0.1042) loss: 0.8503 (0.8571) time: 0.1585 data: 0.0731 max mem: 8452 +Train: [26] [ 500/6250] eta: 0:16:51 lr: 0.000110 grad: 0.0916 (0.1027) loss: 0.8561 (0.8561) time: 0.1540 data: 0.0668 max mem: 8452 +Train: [26] [ 600/6250] eta: 0:17:35 lr: 0.000110 grad: 0.0812 (0.1002) loss: 0.8534 (0.8559) time: 0.4405 data: 0.3313 max mem: 8452 +Train: [26] [ 700/6250] eta: 0:17:26 lr: 0.000110 grad: 0.0839 (0.0981) loss: 0.8514 (0.8559) time: 0.1438 data: 0.0454 max mem: 8452 +Train: [26] [ 800/6250] eta: 0:17:04 lr: 0.000110 grad: 0.0754 (0.0958) loss: 0.8608 (0.8562) time: 0.2043 data: 0.1332 max mem: 8452 +Train: [26] [ 900/6250] eta: 0:16:38 lr: 0.000110 grad: 0.0743 (0.0939) loss: 0.8633 (0.8567) time: 0.1822 data: 0.1008 max mem: 8452 +Train: [26] [1000/6250] eta: 0:16:17 lr: 0.000110 grad: 0.0788 (0.0926) loss: 0.8559 (0.8567) time: 0.2010 data: 0.1229 max mem: 8452 +Train: [26] [1100/6250] eta: 0:15:49 lr: 0.000110 grad: 0.0783 (0.0915) loss: 0.8582 (0.8569) time: 0.1665 data: 0.0911 max mem: 8452 +Train: [26] [1200/6250] eta: 0:15:21 lr: 0.000110 grad: 0.0775 (0.0904) loss: 0.8575 (0.8569) time: 0.1625 data: 0.0741 max mem: 8452 +Train: [26] [1300/6250] eta: 0:14:52 lr: 0.000110 grad: 0.0840 (0.0899) loss: 0.8557 (0.8568) time: 0.1509 data: 0.0552 max mem: 8452 +Train: [26] [1400/6250] eta: 0:14:23 lr: 0.000110 grad: 0.0738 (0.0893) loss: 0.8624 (0.8570) time: 0.1451 data: 0.0548 max mem: 8452 +Train: [26] [1500/6250] eta: 0:13:59 lr: 0.000110 grad: 0.0867 (0.0892) loss: 0.8596 (0.8570) time: 0.1574 data: 0.0776 max mem: 8452 +Train: [26] [1600/6250] eta: 0:13:41 lr: 0.000110 grad: 0.0840 (0.0891) loss: 0.8610 (0.8571) time: 0.1470 data: 0.0701 max mem: 8452 +Train: [26] [1700/6250] eta: 0:13:40 lr: 0.000110 grad: 0.0787 (0.0887) loss: 0.8539 (0.8571) time: 0.3407 data: 0.2508 max mem: 8452 +Train: [26] [1800/6250] eta: 0:13:21 lr: 0.000110 grad: 0.0840 (0.0883) loss: 0.8563 (0.8570) time: 0.2325 data: 0.1099 max mem: 8452 +Train: [26] [1900/6250] eta: 0:13:05 lr: 0.000110 grad: 0.0781 (0.0880) loss: 0.8533 (0.8571) time: 0.2672 data: 0.1434 max mem: 8452 +Train: [26] [2000/6250] eta: 0:12:49 lr: 0.000110 grad: 0.0832 (0.0881) loss: 0.8529 (0.8570) time: 0.1644 data: 0.0627 max mem: 8452 +Train: [26] [2100/6250] eta: 0:12:29 lr: 0.000110 grad: 0.0815 (0.0880) loss: 0.8565 (0.8570) time: 0.1609 data: 0.0730 max mem: 8452 +Train: [26] [2200/6250] eta: 0:12:06 lr: 0.000110 grad: 0.0869 (0.0880) loss: 0.8589 (0.8569) time: 0.1522 data: 0.0623 max mem: 8452 +Train: [26] [2300/6250] eta: 0:11:49 lr: 0.000110 grad: 0.0844 (0.0879) loss: 0.8578 (0.8569) time: 0.0867 data: 0.0063 max mem: 8452 +Train: [26] [2400/6250] eta: 0:11:36 lr: 0.000110 grad: 0.0747 (0.0879) loss: 0.8588 (0.8570) time: 0.1898 data: 0.1016 max mem: 8452 +Train: [26] [2500/6250] eta: 0:11:13 lr: 0.000110 grad: 0.0840 (0.0879) loss: 0.8583 (0.8570) time: 0.1325 data: 0.0525 max mem: 8452 +Train: [26] [2600/6250] eta: 0:10:54 lr: 0.000110 grad: 0.0759 (0.0876) loss: 0.8559 (0.8570) time: 0.1627 data: 0.0932 max mem: 8452 +Train: [26] [2700/6250] eta: 0:10:34 lr: 0.000110 grad: 0.0807 (0.0875) loss: 0.8602 (0.8570) time: 0.1640 data: 0.0847 max mem: 8452 +Train: [26] [2800/6250] eta: 0:10:16 lr: 0.000110 grad: 0.0790 (0.0873) loss: 0.8535 (0.8570) time: 0.2289 data: 0.1529 max mem: 8452 +Train: [26] [2900/6250] eta: 0:09:58 lr: 0.000110 grad: 0.0778 (0.0872) loss: 0.8566 (0.8568) time: 0.2652 data: 0.1709 max mem: 8452 +Train: [26] [3000/6250] eta: 0:09:42 lr: 0.000110 grad: 0.0849 (0.0871) loss: 0.8565 (0.8568) time: 0.1076 data: 0.0204 max mem: 8452 +Train: [26] [3100/6250] eta: 0:09:21 lr: 0.000110 grad: 0.0828 (0.0872) loss: 0.8531 (0.8567) time: 0.1643 data: 0.0884 max mem: 8452 +Train: [26] [3200/6250] eta: 0:09:01 lr: 0.000110 grad: 0.0819 (0.0871) loss: 0.8549 (0.8566) time: 0.1881 data: 0.1103 max mem: 8452 +Train: [26] [3300/6250] eta: 0:08:41 lr: 0.000110 grad: 0.0848 (0.0871) loss: 0.8611 (0.8565) time: 0.1607 data: 0.0829 max mem: 8452 +Train: [26] [3400/6250] eta: 0:08:22 lr: 0.000110 grad: 0.0792 (0.0870) loss: 0.8553 (0.8564) time: 0.1741 data: 0.0984 max mem: 8452 +Train: [26] [3500/6250] eta: 0:08:03 lr: 0.000110 grad: 0.0803 (0.0869) loss: 0.8575 (0.8564) time: 0.1616 data: 0.0782 max mem: 8452 +Train: [26] [3600/6250] eta: 0:07:45 lr: 0.000110 grad: 0.0877 (0.0869) loss: 0.8523 (0.8563) time: 0.1807 data: 0.0993 max mem: 8452 +Train: [26] [3700/6250] eta: 0:07:28 lr: 0.000110 grad: 0.0849 (0.0870) loss: 0.8519 (0.8562) time: 0.1210 data: 0.0006 max mem: 8452 +Train: [26] [3800/6250] eta: 0:07:10 lr: 0.000110 grad: 0.0914 (0.0871) loss: 0.8549 (0.8562) time: 0.1611 data: 0.0898 max mem: 8452 +Train: [26] [3900/6250] eta: 0:06:52 lr: 0.000110 grad: 0.0886 (0.0871) loss: 0.8525 (0.8561) time: 0.1659 data: 0.0939 max mem: 8452 +Train: [26] [4000/6250] eta: 0:06:36 lr: 0.000110 grad: 0.0927 (0.0872) loss: 0.8491 (0.8561) time: 0.3522 data: 0.2617 max mem: 8452 +Train: [26] [4100/6250] eta: 0:06:19 lr: 0.000110 grad: 0.0824 (0.0872) loss: 0.8542 (0.8561) time: 0.2112 data: 0.1455 max mem: 8452 +Train: [26] [4200/6250] eta: 0:06:01 lr: 0.000110 grad: 0.0923 (0.0872) loss: 0.8543 (0.8561) time: 0.1420 data: 0.0645 max mem: 8452 +Train: [26] [4300/6250] eta: 0:05:44 lr: 0.000110 grad: 0.0843 (0.0873) loss: 0.8584 (0.8560) time: 0.2141 data: 0.1274 max mem: 8452 +Train: [26] [4400/6250] eta: 0:05:27 lr: 0.000110 grad: 0.0776 (0.0873) loss: 0.8619 (0.8560) time: 0.1529 data: 0.0699 max mem: 8452 +Train: [26] [4500/6250] eta: 0:05:09 lr: 0.000110 grad: 0.0927 (0.0873) loss: 0.8556 (0.8560) time: 0.1866 data: 0.1105 max mem: 8452 +Train: [26] [4600/6250] eta: 0:04:51 lr: 0.000110 grad: 0.0900 (0.0874) loss: 0.8565 (0.8560) time: 0.1691 data: 0.0821 max mem: 8452 +Train: [26] [4700/6250] eta: 0:04:34 lr: 0.000110 grad: 0.0875 (0.0874) loss: 0.8553 (0.8560) time: 0.1765 data: 0.1038 max mem: 8452 +Train: [26] [4800/6250] eta: 0:04:17 lr: 0.000109 grad: 0.0808 (0.0874) loss: 0.8567 (0.8560) time: 0.1395 data: 0.0495 max mem: 8452 +Train: [26] [4900/6250] eta: 0:03:59 lr: 0.000109 grad: 0.0879 (0.0874) loss: 0.8612 (0.8560) time: 0.1739 data: 0.0895 max mem: 8452 +Train: [26] [5000/6250] eta: 0:03:41 lr: 0.000109 grad: 0.0822 (0.0874) loss: 0.8642 (0.8560) time: 0.1542 data: 0.0701 max mem: 8452 +Train: [26] [5100/6250] eta: 0:03:24 lr: 0.000109 grad: 0.0778 (0.0873) loss: 0.8596 (0.8559) time: 0.1752 data: 0.0875 max mem: 8452 +Train: [26] [5200/6250] eta: 0:03:06 lr: 0.000109 grad: 0.0812 (0.0873) loss: 0.8613 (0.8559) time: 0.1603 data: 0.0807 max mem: 8452 +Train: [26] [5300/6250] eta: 0:02:48 lr: 0.000109 grad: 0.0773 (0.0873) loss: 0.8590 (0.8560) time: 0.1310 data: 0.0463 max mem: 8452 +Train: [26] [5400/6250] eta: 0:02:31 lr: 0.000109 grad: 0.0886 (0.0873) loss: 0.8588 (0.8560) time: 0.1954 data: 0.1078 max mem: 8452 +Train: [26] [5500/6250] eta: 0:02:13 lr: 0.000109 grad: 0.0842 (0.0873) loss: 0.8597 (0.8560) time: 0.1452 data: 0.0623 max mem: 8452 +Train: [26] [5600/6250] eta: 0:01:55 lr: 0.000109 grad: 0.0840 (0.0874) loss: 0.8592 (0.8560) time: 0.2530 data: 0.1671 max mem: 8452 +Train: [26] [5700/6250] eta: 0:01:38 lr: 0.000109 grad: 0.0863 (0.0873) loss: 0.8562 (0.8560) time: 0.2506 data: 0.1493 max mem: 8452 +Train: [26] [5800/6250] eta: 0:01:20 lr: 0.000109 grad: 0.0863 (0.0873) loss: 0.8496 (0.8560) time: 0.1883 data: 0.1055 max mem: 8452 +Train: [26] [5900/6250] eta: 0:01:02 lr: 0.000109 grad: 0.0875 (0.0873) loss: 0.8550 (0.8561) time: 0.1202 data: 0.0255 max mem: 8452 +Train: [26] [6000/6250] eta: 0:00:44 lr: 0.000109 grad: 0.0842 (0.0873) loss: 0.8667 (0.8562) time: 0.0781 data: 0.0002 max mem: 8452 +Train: [26] [6100/6250] eta: 0:00:26 lr: 0.000109 grad: 0.0849 (0.0872) loss: 0.8569 (0.8562) time: 0.1507 data: 0.0708 max mem: 8452 +Train: [26] [6200/6250] eta: 0:00:08 lr: 0.000109 grad: 0.0798 (0.0872) loss: 0.8583 (0.8562) time: 0.3006 data: 0.2047 max mem: 8452 +Train: [26] [6249/6250] eta: 0:00:00 lr: 0.000109 grad: 0.0814 (0.0872) loss: 0.8624 (0.8563) time: 0.2298 data: 0.1542 max mem: 8452 +Train: [26] Total time: 0:18:47 (0.1803 s / it) +Averaged stats: lr: 0.000109 grad: 0.0814 (0.0872) loss: 0.8624 (0.8563) +Eval (hcp-train-subset): [26] [ 0/62] eta: 0:03:37 loss: 0.8814 (0.8814) time: 3.5027 data: 3.3795 max mem: 8452 +Eval (hcp-train-subset): [26] [61/62] eta: 0:00:00 loss: 0.8778 (0.8800) time: 0.1426 data: 0.1200 max mem: 8452 +Eval (hcp-train-subset): [26] Total time: 0:00:14 (0.2408 s / it) +Averaged stats (hcp-train-subset): loss: 0.8778 (0.8800) +Eval (hcp-val): [26] [ 0/62] eta: 0:05:47 loss: 0.8710 (0.8710) time: 5.6072 data: 5.5809 max mem: 8452 +Eval (hcp-val): [26] [61/62] eta: 0:00:00 loss: 0.8802 (0.8808) time: 0.1361 data: 0.1138 max mem: 8452 +Eval (hcp-val): [26] Total time: 0:00:14 (0.2286 s / it) +Averaged stats (hcp-val): loss: 0.8802 (0.8808) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [27] [ 0/6250] eta: 10:40:39 lr: 0.000109 grad: 0.1671 (0.1671) loss: 0.8752 (0.8752) time: 6.1503 data: 6.0227 max mem: 8452 +Train: [27] [ 100/6250] eta: 0:23:06 lr: 0.000109 grad: 0.0795 (0.1151) loss: 0.8831 (0.8770) time: 0.1547 data: 0.0547 max mem: 8452 +Train: [27] [ 200/6250] eta: 0:20:32 lr: 0.000109 grad: 0.0805 (0.1001) loss: 0.8722 (0.8749) time: 0.2039 data: 0.1157 max mem: 8452 +Train: [27] [ 300/6250] eta: 0:19:04 lr: 0.000109 grad: 0.0781 (0.0942) loss: 0.8608 (0.8715) time: 0.1572 data: 0.0647 max mem: 8452 +Train: [27] [ 400/6250] eta: 0:18:01 lr: 0.000109 grad: 0.0746 (0.0907) loss: 0.8587 (0.8692) time: 0.1648 data: 0.0796 max mem: 8452 +Train: [27] [ 500/6250] eta: 0:17:13 lr: 0.000109 grad: 0.0818 (0.0892) loss: 0.8601 (0.8676) time: 0.1710 data: 0.0763 max mem: 8452 +Train: [27] [ 600/6250] eta: 0:16:35 lr: 0.000109 grad: 0.0816 (0.0896) loss: 0.8563 (0.8658) time: 0.1653 data: 0.0827 max mem: 8452 +Train: [27] [ 700/6250] eta: 0:16:26 lr: 0.000109 grad: 0.0807 (0.0904) loss: 0.8597 (0.8645) time: 0.2276 data: 0.1219 max mem: 8452 +Train: [27] [ 800/6250] eta: 0:16:18 lr: 0.000109 grad: 0.0769 (0.0893) loss: 0.8598 (0.8637) time: 0.1519 data: 0.0581 max mem: 8452 +Train: [27] [ 900/6250] eta: 0:16:09 lr: 0.000109 grad: 0.0810 (0.0885) loss: 0.8571 (0.8629) time: 0.1750 data: 0.0987 max mem: 8452 +Train: [27] [1000/6250] eta: 0:15:45 lr: 0.000109 grad: 0.0762 (0.0883) loss: 0.8583 (0.8624) time: 0.1673 data: 0.0910 max mem: 8452 +Train: [27] [1100/6250] eta: 0:15:22 lr: 0.000109 grad: 0.0844 (0.0879) loss: 0.8618 (0.8620) time: 0.2036 data: 0.1315 max mem: 8452 +Train: [27] [1200/6250] eta: 0:14:56 lr: 0.000109 grad: 0.0794 (0.0874) loss: 0.8601 (0.8616) time: 0.1395 data: 0.0595 max mem: 8452 +Train: [27] [1300/6250] eta: 0:14:38 lr: 0.000109 grad: 0.0800 (0.0873) loss: 0.8605 (0.8610) time: 0.1571 data: 0.0754 max mem: 8452 +Train: [27] [1400/6250] eta: 0:14:20 lr: 0.000109 grad: 0.0823 (0.0871) loss: 0.8563 (0.8607) time: 0.2047 data: 0.1257 max mem: 8452 +Train: [27] [1500/6250] eta: 0:13:57 lr: 0.000109 grad: 0.0827 (0.0868) loss: 0.8531 (0.8604) time: 0.1608 data: 0.0760 max mem: 8452 +Train: [27] [1600/6250] eta: 0:13:37 lr: 0.000109 grad: 0.0850 (0.0867) loss: 0.8514 (0.8601) time: 0.1989 data: 0.1145 max mem: 8452 +Train: [27] [1700/6250] eta: 0:13:17 lr: 0.000109 grad: 0.0858 (0.0866) loss: 0.8592 (0.8599) time: 0.1827 data: 0.0986 max mem: 8452 +Train: [27] [1800/6250] eta: 0:12:58 lr: 0.000109 grad: 0.0799 (0.0866) loss: 0.8539 (0.8595) time: 0.1265 data: 0.0389 max mem: 8452 +Train: [27] [1900/6250] eta: 0:12:40 lr: 0.000109 grad: 0.0769 (0.0865) loss: 0.8603 (0.8594) time: 0.2153 data: 0.1048 max mem: 8452 +Train: [27] [2000/6250] eta: 0:12:33 lr: 0.000109 grad: 0.0790 (0.0863) loss: 0.8571 (0.8593) time: 0.3177 data: 0.2182 max mem: 8452 +Train: [27] [2100/6250] eta: 0:12:12 lr: 0.000109 grad: 0.0834 (0.0860) loss: 0.8547 (0.8592) time: 0.1897 data: 0.0888 max mem: 8452 +Train: [27] [2200/6250] eta: 0:11:55 lr: 0.000109 grad: 0.0820 (0.0859) loss: 0.8564 (0.8592) time: 0.1833 data: 0.1031 max mem: 8452 +Train: [27] [2300/6250] eta: 0:11:39 lr: 0.000109 grad: 0.0802 (0.0859) loss: 0.8625 (0.8592) time: 0.1625 data: 0.0480 max mem: 8452 +Train: [27] [2400/6250] eta: 0:11:23 lr: 0.000109 grad: 0.0832 (0.0860) loss: 0.8550 (0.8590) time: 0.2802 data: 0.2118 max mem: 8452 +Train: [27] [2500/6250] eta: 0:11:01 lr: 0.000109 grad: 0.0860 (0.0860) loss: 0.8512 (0.8589) time: 0.1446 data: 0.0578 max mem: 8452 +Train: [27] [2600/6250] eta: 0:10:42 lr: 0.000109 grad: 0.0842 (0.0861) loss: 0.8529 (0.8588) time: 0.1307 data: 0.0311 max mem: 8452 +Train: [27] [2700/6250] eta: 0:10:21 lr: 0.000109 grad: 0.0864 (0.0861) loss: 0.8574 (0.8587) time: 0.1535 data: 0.0667 max mem: 8452 +Train: [27] [2800/6250] eta: 0:10:02 lr: 0.000109 grad: 0.0855 (0.0860) loss: 0.8495 (0.8586) time: 0.1395 data: 0.0574 max mem: 8452 +Train: [27] [2900/6250] eta: 0:09:43 lr: 0.000109 grad: 0.0849 (0.0860) loss: 0.8638 (0.8586) time: 0.1653 data: 0.0890 max mem: 8452 +Train: [27] [3000/6250] eta: 0:09:24 lr: 0.000109 grad: 0.0816 (0.0860) loss: 0.8558 (0.8585) time: 0.1624 data: 0.0913 max mem: 8452 +Train: [27] [3100/6250] eta: 0:09:05 lr: 0.000108 grad: 0.0798 (0.0860) loss: 0.8595 (0.8584) time: 0.1409 data: 0.0603 max mem: 8452 +Train: [27] [3200/6250] eta: 0:08:48 lr: 0.000108 grad: 0.0809 (0.0859) loss: 0.8569 (0.8585) time: 0.1684 data: 0.0893 max mem: 8452 +Train: [27] [3300/6250] eta: 0:08:30 lr: 0.000108 grad: 0.0789 (0.0859) loss: 0.8657 (0.8586) time: 0.1879 data: 0.1089 max mem: 8452 +Train: [27] [3400/6250] eta: 0:08:13 lr: 0.000108 grad: 0.0832 (0.0859) loss: 0.8557 (0.8587) time: 0.1757 data: 0.1058 max mem: 8452 +Train: [27] [3500/6250] eta: 0:07:57 lr: 0.000108 grad: 0.0848 (0.0858) loss: 0.8594 (0.8587) time: 0.2335 data: 0.1627 max mem: 8452 +Train: [27] [3600/6250] eta: 0:07:38 lr: 0.000108 grad: 0.0798 (0.0859) loss: 0.8628 (0.8587) time: 0.1700 data: 0.0988 max mem: 8452 +Train: [27] [3700/6250] eta: 0:07:21 lr: 0.000108 grad: 0.0836 (0.0860) loss: 0.8570 (0.8587) time: 0.1832 data: 0.1064 max mem: 8452 +Train: [27] [3800/6250] eta: 0:07:03 lr: 0.000108 grad: 0.0928 (0.0860) loss: 0.8472 (0.8586) time: 0.1480 data: 0.0710 max mem: 8452 +Train: [27] [3900/6250] eta: 0:06:45 lr: 0.000108 grad: 0.0900 (0.0860) loss: 0.8504 (0.8586) time: 0.1241 data: 0.0474 max mem: 8452 +Train: [27] [4000/6250] eta: 0:06:27 lr: 0.000108 grad: 0.0786 (0.0860) loss: 0.8520 (0.8586) time: 0.1533 data: 0.0675 max mem: 8452 +Train: [27] [4100/6250] eta: 0:06:09 lr: 0.000108 grad: 0.0805 (0.0860) loss: 0.8566 (0.8586) time: 0.1566 data: 0.0705 max mem: 8452 +Train: [27] [4200/6250] eta: 0:05:52 lr: 0.000108 grad: 0.0785 (0.0860) loss: 0.8587 (0.8585) time: 0.1655 data: 0.0909 max mem: 8452 +Train: [27] [4300/6250] eta: 0:05:34 lr: 0.000108 grad: 0.0899 (0.0861) loss: 0.8523 (0.8584) time: 0.1714 data: 0.0860 max mem: 8452 +Train: [27] [4400/6250] eta: 0:05:17 lr: 0.000108 grad: 0.0807 (0.0861) loss: 0.8592 (0.8584) time: 0.1653 data: 0.0719 max mem: 8452 +Train: [27] [4500/6250] eta: 0:04:59 lr: 0.000108 grad: 0.0802 (0.0861) loss: 0.8607 (0.8584) time: 0.1747 data: 0.0901 max mem: 8452 +Train: [27] [4600/6250] eta: 0:04:42 lr: 0.000108 grad: 0.0830 (0.0861) loss: 0.8550 (0.8583) time: 0.1568 data: 0.0760 max mem: 8452 +Train: [27] [4700/6250] eta: 0:04:24 lr: 0.000108 grad: 0.0898 (0.0862) loss: 0.8505 (0.8582) time: 0.1778 data: 0.0832 max mem: 8452 +Train: [27] [4800/6250] eta: 0:04:07 lr: 0.000108 grad: 0.0865 (0.0862) loss: 0.8537 (0.8581) time: 0.1502 data: 0.0739 max mem: 8452 +Train: [27] [4900/6250] eta: 0:03:50 lr: 0.000108 grad: 0.0835 (0.0863) loss: 0.8540 (0.8581) time: 0.1640 data: 0.0854 max mem: 8452 +Train: [27] [5000/6250] eta: 0:03:33 lr: 0.000108 grad: 0.0844 (0.0864) loss: 0.8501 (0.8580) time: 0.1760 data: 0.0871 max mem: 8452 +Train: [27] [5100/6250] eta: 0:03:15 lr: 0.000108 grad: 0.0851 (0.0864) loss: 0.8566 (0.8580) time: 0.1733 data: 0.0930 max mem: 8452 +Train: [27] [5200/6250] eta: 0:02:58 lr: 0.000108 grad: 0.0840 (0.0863) loss: 0.8558 (0.8580) time: 0.1608 data: 0.0831 max mem: 8452 +Train: [27] [5300/6250] eta: 0:02:40 lr: 0.000108 grad: 0.0838 (0.0864) loss: 0.8556 (0.8579) time: 0.1373 data: 0.0503 max mem: 8452 +Train: [27] [5400/6250] eta: 0:02:23 lr: 0.000108 grad: 0.0797 (0.0863) loss: 0.8603 (0.8579) time: 0.1748 data: 0.0904 max mem: 8452 +Train: [27] [5500/6250] eta: 0:02:06 lr: 0.000108 grad: 0.0822 (0.0864) loss: 0.8521 (0.8579) time: 0.2053 data: 0.1205 max mem: 8452 +Train: [27] [5600/6250] eta: 0:01:49 lr: 0.000108 grad: 0.0852 (0.0864) loss: 0.8559 (0.8579) time: 0.1361 data: 0.0618 max mem: 8452 +Train: [27] [5700/6250] eta: 0:01:32 lr: 0.000108 grad: 0.0815 (0.0864) loss: 0.8609 (0.8579) time: 0.1759 data: 0.0849 max mem: 8452 +Train: [27] [5800/6250] eta: 0:01:16 lr: 0.000108 grad: 0.0852 (0.0865) loss: 0.8540 (0.8578) time: 0.1750 data: 0.0535 max mem: 8452 +Train: [27] [5900/6250] eta: 0:00:59 lr: 0.000108 grad: 0.0847 (0.0865) loss: 0.8571 (0.8578) time: 0.1466 data: 0.0381 max mem: 8452 +Train: [27] [6000/6250] eta: 0:00:42 lr: 0.000108 grad: 0.0854 (0.0865) loss: 0.8568 (0.8578) time: 0.1764 data: 0.1041 max mem: 8452 +Train: [27] [6100/6250] eta: 0:00:25 lr: 0.000108 grad: 0.0869 (0.0864) loss: 0.8583 (0.8578) time: 0.1772 data: 0.1029 max mem: 8452 +Train: [27] [6200/6250] eta: 0:00:08 lr: 0.000108 grad: 0.0776 (0.0864) loss: 0.8626 (0.8578) time: 0.1535 data: 0.0823 max mem: 8452 +Train: [27] [6249/6250] eta: 0:00:00 lr: 0.000108 grad: 0.0791 (0.0864) loss: 0.8542 (0.8578) time: 0.1677 data: 0.0898 max mem: 8452 +Train: [27] Total time: 0:17:45 (0.1704 s / it) +Averaged stats: lr: 0.000108 grad: 0.0791 (0.0864) loss: 0.8542 (0.8578) +Eval (hcp-train-subset): [27] [ 0/62] eta: 0:05:07 loss: 0.8912 (0.8912) time: 4.9658 data: 4.9340 max mem: 8452 +Eval (hcp-train-subset): [27] [61/62] eta: 0:00:00 loss: 0.8830 (0.8826) time: 0.1329 data: 0.1118 max mem: 8452 +Eval (hcp-train-subset): [27] Total time: 0:00:14 (0.2319 s / it) +Averaged stats (hcp-train-subset): loss: 0.8830 (0.8826) +Eval (hcp-val): [27] [ 0/62] eta: 0:03:23 loss: 0.8794 (0.8794) time: 3.2791 data: 3.1982 max mem: 8452 +Eval (hcp-val): [27] [61/62] eta: 0:00:00 loss: 0.8793 (0.8805) time: 0.1331 data: 0.1085 max mem: 8452 +Eval (hcp-val): [27] Total time: 0:00:14 (0.2301 s / it) +Averaged stats (hcp-val): loss: 0.8793 (0.8805) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [28] [ 0/6250] eta: 10:09:48 lr: 0.000108 grad: 0.2600 (0.2600) loss: 0.9076 (0.9076) time: 5.8541 data: 5.7002 max mem: 8452 +Train: [28] [ 100/6250] eta: 0:22:17 lr: 0.000108 grad: 0.0802 (0.1106) loss: 0.8809 (0.8809) time: 0.1775 data: 0.0788 max mem: 8452 +Train: [28] [ 200/6250] eta: 0:19:05 lr: 0.000108 grad: 0.0801 (0.0977) loss: 0.8724 (0.8745) time: 0.1575 data: 0.0702 max mem: 8452 +Train: [28] [ 300/6250] eta: 0:18:03 lr: 0.000108 grad: 0.0746 (0.0926) loss: 0.8649 (0.8724) time: 0.1812 data: 0.0903 max mem: 8452 +Train: [28] [ 400/6250] eta: 0:17:19 lr: 0.000108 grad: 0.0872 (0.0904) loss: 0.8638 (0.8699) time: 0.1676 data: 0.0822 max mem: 8452 +Train: [28] [ 500/6250] eta: 0:16:39 lr: 0.000108 grad: 0.0747 (0.0891) loss: 0.8631 (0.8685) time: 0.1661 data: 0.0882 max mem: 8452 +Train: [28] [ 600/6250] eta: 0:16:17 lr: 0.000108 grad: 0.0771 (0.0876) loss: 0.8581 (0.8679) time: 0.1739 data: 0.0850 max mem: 8452 +Train: [28] [ 700/6250] eta: 0:16:06 lr: 0.000108 grad: 0.0810 (0.0864) loss: 0.8618 (0.8672) time: 0.1893 data: 0.1004 max mem: 8452 +Train: [28] [ 800/6250] eta: 0:15:38 lr: 0.000108 grad: 0.0792 (0.0859) loss: 0.8570 (0.8664) time: 0.1565 data: 0.0721 max mem: 8452 +Train: [28] [ 900/6250] eta: 0:15:50 lr: 0.000108 grad: 0.0771 (0.0852) loss: 0.8625 (0.8659) time: 0.4471 data: 0.3447 max mem: 8452 +Train: [28] [1000/6250] eta: 0:15:17 lr: 0.000108 grad: 0.0725 (0.0846) loss: 0.8539 (0.8654) time: 0.1667 data: 0.0855 max mem: 8452 +Train: [28] [1100/6250] eta: 0:14:55 lr: 0.000108 grad: 0.0813 (0.0842) loss: 0.8564 (0.8646) time: 0.1612 data: 0.0855 max mem: 8452 +Train: [28] [1200/6250] eta: 0:14:35 lr: 0.000108 grad: 0.0760 (0.0841) loss: 0.8560 (0.8642) time: 0.1947 data: 0.1257 max mem: 8452 +Train: [28] [1300/6250] eta: 0:14:14 lr: 0.000107 grad: 0.0781 (0.0838) loss: 0.8616 (0.8638) time: 0.1700 data: 0.0962 max mem: 8452 +Train: [28] [1400/6250] eta: 0:13:55 lr: 0.000107 grad: 0.0818 (0.0838) loss: 0.8580 (0.8634) time: 0.1617 data: 0.0805 max mem: 8452 +Train: [28] [1500/6250] eta: 0:13:35 lr: 0.000107 grad: 0.0767 (0.0836) loss: 0.8609 (0.8630) time: 0.1728 data: 0.0848 max mem: 8452 +Train: [28] [1600/6250] eta: 0:13:12 lr: 0.000107 grad: 0.0760 (0.0834) loss: 0.8553 (0.8626) time: 0.1468 data: 0.0641 max mem: 8452 +Train: [28] [1700/6250] eta: 0:12:50 lr: 0.000107 grad: 0.0759 (0.0831) loss: 0.8557 (0.8624) time: 0.1513 data: 0.0632 max mem: 8452 +Train: [28] [1800/6250] eta: 0:12:30 lr: 0.000107 grad: 0.0773 (0.0829) loss: 0.8649 (0.8623) time: 0.1405 data: 0.0656 max mem: 8452 +Train: [28] [1900/6250] eta: 0:12:15 lr: 0.000107 grad: 0.0846 (0.0828) loss: 0.8601 (0.8622) time: 0.1275 data: 0.0534 max mem: 8452 +Train: [28] [2000/6250] eta: 0:12:01 lr: 0.000107 grad: 0.0862 (0.0828) loss: 0.8575 (0.8619) time: 0.1341 data: 0.0389 max mem: 8452 +Train: [28] [2100/6250] eta: 0:11:46 lr: 0.000107 grad: 0.0836 (0.0830) loss: 0.8605 (0.8616) time: 0.1269 data: 0.0004 max mem: 8452 +Train: [28] [2200/6250] eta: 0:11:27 lr: 0.000107 grad: 0.0838 (0.0830) loss: 0.8620 (0.8614) time: 0.1711 data: 0.0913 max mem: 8452 +Train: [28] [2300/6250] eta: 0:11:08 lr: 0.000107 grad: 0.0772 (0.0831) loss: 0.8635 (0.8613) time: 0.1780 data: 0.0881 max mem: 8452 +Train: [28] [2400/6250] eta: 0:10:50 lr: 0.000107 grad: 0.0836 (0.0831) loss: 0.8629 (0.8610) time: 0.1651 data: 0.0836 max mem: 8452 +Train: [28] [2500/6250] eta: 0:10:33 lr: 0.000107 grad: 0.0756 (0.0831) loss: 0.8579 (0.8609) time: 0.1822 data: 0.1011 max mem: 8452 +Train: [28] [2600/6250] eta: 0:10:14 lr: 0.000107 grad: 0.0797 (0.0831) loss: 0.8603 (0.8609) time: 0.1457 data: 0.0618 max mem: 8452 +Train: [28] [2700/6250] eta: 0:09:56 lr: 0.000107 grad: 0.0764 (0.0830) loss: 0.8641 (0.8608) time: 0.1539 data: 0.0809 max mem: 8452 +Train: [28] [2800/6250] eta: 0:09:38 lr: 0.000107 grad: 0.0812 (0.0830) loss: 0.8603 (0.8609) time: 0.1576 data: 0.0833 max mem: 8452 +Train: [28] [2900/6250] eta: 0:09:21 lr: 0.000107 grad: 0.0903 (0.0831) loss: 0.8523 (0.8607) time: 0.1624 data: 0.0915 max mem: 8452 +Train: [28] [3000/6250] eta: 0:09:03 lr: 0.000107 grad: 0.0779 (0.0830) loss: 0.8580 (0.8607) time: 0.1461 data: 0.0655 max mem: 8452 +Train: [28] [3100/6250] eta: 0:08:46 lr: 0.000107 grad: 0.0853 (0.0831) loss: 0.8593 (0.8606) time: 0.1705 data: 0.1031 max mem: 8452 +Train: [28] [3200/6250] eta: 0:08:28 lr: 0.000107 grad: 0.0789 (0.0831) loss: 0.8550 (0.8605) time: 0.1473 data: 0.0713 max mem: 8452 +Train: [28] [3300/6250] eta: 0:08:11 lr: 0.000107 grad: 0.0841 (0.0832) loss: 0.8457 (0.8603) time: 0.1529 data: 0.0782 max mem: 8452 +Train: [28] [3400/6250] eta: 0:07:54 lr: 0.000107 grad: 0.0814 (0.0833) loss: 0.8604 (0.8601) time: 0.1751 data: 0.0942 max mem: 8452 +Train: [28] [3500/6250] eta: 0:07:36 lr: 0.000107 grad: 0.0874 (0.0834) loss: 0.8453 (0.8599) time: 0.1359 data: 0.0550 max mem: 8452 +Train: [28] [3600/6250] eta: 0:07:19 lr: 0.000107 grad: 0.0854 (0.0836) loss: 0.8553 (0.8598) time: 0.1384 data: 0.0381 max mem: 8452 +Train: [28] [3700/6250] eta: 0:07:02 lr: 0.000107 grad: 0.0824 (0.0837) loss: 0.8615 (0.8597) time: 0.1643 data: 0.0767 max mem: 8452 +Train: [28] [3800/6250] eta: 0:06:45 lr: 0.000107 grad: 0.0825 (0.0837) loss: 0.8487 (0.8596) time: 0.1576 data: 0.0813 max mem: 8452 +Train: [28] [3900/6250] eta: 0:06:29 lr: 0.000107 grad: 0.0933 (0.0839) loss: 0.8471 (0.8593) time: 0.1435 data: 0.0666 max mem: 8452 +Train: [28] [4000/6250] eta: 0:06:13 lr: 0.000107 grad: 0.0842 (0.0839) loss: 0.8554 (0.8592) time: 0.1641 data: 0.0795 max mem: 8452 +Train: [28] [4100/6250] eta: 0:05:56 lr: 0.000107 grad: 0.0772 (0.0840) loss: 0.8608 (0.8591) time: 0.1801 data: 0.1082 max mem: 8452 +Train: [28] [4200/6250] eta: 0:05:40 lr: 0.000107 grad: 0.0775 (0.0840) loss: 0.8538 (0.8590) time: 0.1535 data: 0.0667 max mem: 8452 +Train: [28] [4300/6250] eta: 0:05:23 lr: 0.000107 grad: 0.0932 (0.0842) loss: 0.8555 (0.8588) time: 0.1735 data: 0.0964 max mem: 8452 +Train: [28] [4400/6250] eta: 0:05:06 lr: 0.000107 grad: 0.0815 (0.0842) loss: 0.8567 (0.8587) time: 0.1752 data: 0.0817 max mem: 8452 +Train: [28] [4500/6250] eta: 0:04:50 lr: 0.000107 grad: 0.0790 (0.0843) loss: 0.8601 (0.8586) time: 0.1517 data: 0.0672 max mem: 8452 +Train: [28] [4600/6250] eta: 0:04:34 lr: 0.000107 grad: 0.0783 (0.0844) loss: 0.8572 (0.8585) time: 0.1789 data: 0.1110 max mem: 8452 +Train: [28] [4700/6250] eta: 0:04:17 lr: 0.000107 grad: 0.0801 (0.0844) loss: 0.8576 (0.8584) time: 0.1653 data: 0.0826 max mem: 8452 +Train: [28] [4800/6250] eta: 0:04:01 lr: 0.000107 grad: 0.0800 (0.0844) loss: 0.8634 (0.8584) time: 0.2128 data: 0.1207 max mem: 8452 +Train: [28] [4900/6250] eta: 0:03:44 lr: 0.000107 grad: 0.0817 (0.0844) loss: 0.8548 (0.8583) time: 0.1758 data: 0.0920 max mem: 8452 +Train: [28] [5000/6250] eta: 0:03:28 lr: 0.000107 grad: 0.0892 (0.0844) loss: 0.8540 (0.8583) time: 0.1700 data: 0.0864 max mem: 8452 +Train: [28] [5100/6250] eta: 0:03:11 lr: 0.000107 grad: 0.0831 (0.0845) loss: 0.8537 (0.8582) time: 0.1622 data: 0.0834 max mem: 8452 +Train: [28] [5200/6250] eta: 0:02:54 lr: 0.000107 grad: 0.0819 (0.0846) loss: 0.8545 (0.8582) time: 0.1636 data: 0.0923 max mem: 8452 +Train: [28] [5300/6250] eta: 0:02:38 lr: 0.000107 grad: 0.0766 (0.0847) loss: 0.8578 (0.8581) time: 0.1351 data: 0.0593 max mem: 8452 +Train: [28] [5400/6250] eta: 0:02:21 lr: 0.000107 grad: 0.0879 (0.0847) loss: 0.8534 (0.8581) time: 0.1958 data: 0.1314 max mem: 8452 +Train: [28] [5500/6250] eta: 0:02:05 lr: 0.000107 grad: 0.0823 (0.0849) loss: 0.8516 (0.8580) time: 0.1880 data: 0.1268 max mem: 8452 +Train: [28] [5600/6250] eta: 0:01:48 lr: 0.000106 grad: 0.0854 (0.0849) loss: 0.8518 (0.8579) time: 0.1829 data: 0.1145 max mem: 8452 +Train: [28] [5700/6250] eta: 0:01:32 lr: 0.000106 grad: 0.0805 (0.0849) loss: 0.8664 (0.8579) time: 0.1678 data: 0.0891 max mem: 8452 +Train: [28] [5800/6250] eta: 0:01:15 lr: 0.000106 grad: 0.0811 (0.0849) loss: 0.8535 (0.8578) time: 0.1565 data: 0.0924 max mem: 8452 +Train: [28] [5900/6250] eta: 0:00:58 lr: 0.000106 grad: 0.0857 (0.0850) loss: 0.8570 (0.8578) time: 0.1705 data: 0.0885 max mem: 8452 +Train: [28] [6000/6250] eta: 0:00:41 lr: 0.000106 grad: 0.0880 (0.0850) loss: 0.8497 (0.8578) time: 0.1656 data: 0.0642 max mem: 8452 +Train: [28] [6100/6250] eta: 0:00:25 lr: 0.000106 grad: 0.0808 (0.0850) loss: 0.8556 (0.8578) time: 0.1905 data: 0.1124 max mem: 8452 +Train: [28] [6200/6250] eta: 0:00:08 lr: 0.000106 grad: 0.0896 (0.0851) loss: 0.8514 (0.8577) time: 0.2073 data: 0.1268 max mem: 8452 +Train: [28] [6249/6250] eta: 0:00:00 lr: 0.000106 grad: 0.0856 (0.0851) loss: 0.8535 (0.8577) time: 0.1389 data: 0.0613 max mem: 8452 +Train: [28] Total time: 0:17:36 (0.1691 s / it) +Averaged stats: lr: 0.000106 grad: 0.0856 (0.0851) loss: 0.8535 (0.8577) +Eval (hcp-train-subset): [28] [ 0/62] eta: 0:05:17 loss: 0.8944 (0.8944) time: 5.1218 data: 5.0956 max mem: 8452 +Eval (hcp-train-subset): [28] [61/62] eta: 0:00:00 loss: 0.8819 (0.8834) time: 0.1314 data: 0.1104 max mem: 8452 +Eval (hcp-train-subset): [28] Total time: 0:00:14 (0.2387 s / it) +Averaged stats (hcp-train-subset): loss: 0.8819 (0.8834) +Eval (hcp-val): [28] [ 0/62] eta: 0:03:28 loss: 0.8776 (0.8776) time: 3.3608 data: 3.2785 max mem: 8452 +Eval (hcp-val): [28] [61/62] eta: 0:00:00 loss: 0.8792 (0.8801) time: 0.1443 data: 0.1228 max mem: 8452 +Eval (hcp-val): [28] Total time: 0:00:15 (0.2471 s / it) +Averaged stats (hcp-val): loss: 0.8792 (0.8801) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [29] [ 0/6250] eta: 7:48:22 lr: 0.000106 grad: 0.0987 (0.0987) loss: 0.9206 (0.9206) time: 4.4964 data: 4.2741 max mem: 8452 +Train: [29] [ 100/6250] eta: 0:23:43 lr: 0.000106 grad: 0.0925 (0.1069) loss: 0.8716 (0.8834) time: 0.1772 data: 0.0774 max mem: 8452 +Train: [29] [ 200/6250] eta: 0:21:04 lr: 0.000106 grad: 0.0878 (0.1001) loss: 0.8682 (0.8754) time: 0.1601 data: 0.0775 max mem: 8452 +Train: [29] [ 300/6250] eta: 0:19:31 lr: 0.000106 grad: 0.0800 (0.0963) loss: 0.8661 (0.8722) time: 0.1746 data: 0.0770 max mem: 8452 +Train: [29] [ 400/6250] eta: 0:18:38 lr: 0.000106 grad: 0.0875 (0.0949) loss: 0.8493 (0.8693) time: 0.1954 data: 0.1288 max mem: 8452 +Train: [29] [ 500/6250] eta: 0:17:41 lr: 0.000106 grad: 0.0842 (0.0929) loss: 0.8559 (0.8675) time: 0.1692 data: 0.0820 max mem: 8452 +Train: [29] [ 600/6250] eta: 0:17:39 lr: 0.000106 grad: 0.0798 (0.0915) loss: 0.8545 (0.8659) time: 0.2619 data: 0.1692 max mem: 8452 +Train: [29] [ 700/6250] eta: 0:17:04 lr: 0.000106 grad: 0.0744 (0.0900) loss: 0.8625 (0.8650) time: 0.1883 data: 0.0879 max mem: 8452 +Train: [29] [ 800/6250] eta: 0:17:06 lr: 0.000106 grad: 0.0759 (0.0886) loss: 0.8592 (0.8644) time: 0.3206 data: 0.2153 max mem: 8452 +Train: [29] [ 900/6250] eta: 0:16:28 lr: 0.000106 grad: 0.0783 (0.0879) loss: 0.8643 (0.8636) time: 0.1814 data: 0.0983 max mem: 8452 +Train: [29] [1000/6250] eta: 0:16:07 lr: 0.000106 grad: 0.0813 (0.0871) loss: 0.8662 (0.8635) time: 0.1895 data: 0.1164 max mem: 8452 +Train: [29] [1100/6250] eta: 0:15:41 lr: 0.000106 grad: 0.0739 (0.0865) loss: 0.8606 (0.8631) time: 0.1753 data: 0.1026 max mem: 8452 +Train: [29] [1200/6250] eta: 0:15:12 lr: 0.000106 grad: 0.0746 (0.0859) loss: 0.8629 (0.8628) time: 0.1576 data: 0.0749 max mem: 8452 +Train: [29] [1300/6250] eta: 0:14:48 lr: 0.000106 grad: 0.0755 (0.0856) loss: 0.8594 (0.8626) time: 0.1463 data: 0.0571 max mem: 8452 +Train: [29] [1400/6250] eta: 0:14:26 lr: 0.000106 grad: 0.0742 (0.0855) loss: 0.8583 (0.8620) time: 0.1906 data: 0.1177 max mem: 8452 +Train: [29] [1500/6250] eta: 0:14:04 lr: 0.000106 grad: 0.0827 (0.0852) loss: 0.8539 (0.8615) time: 0.1554 data: 0.0755 max mem: 8452 +Train: [29] [1600/6250] eta: 0:13:40 lr: 0.000106 grad: 0.0762 (0.0850) loss: 0.8584 (0.8612) time: 0.1583 data: 0.0700 max mem: 8452 +Train: [29] [1700/6250] eta: 0:13:17 lr: 0.000106 grad: 0.0835 (0.0850) loss: 0.8617 (0.8609) time: 0.1557 data: 0.0667 max mem: 8452 +Train: [29] [1800/6250] eta: 0:12:56 lr: 0.000106 grad: 0.0785 (0.0850) loss: 0.8555 (0.8607) time: 0.1887 data: 0.1093 max mem: 8452 +Train: [29] [1900/6250] eta: 0:12:34 lr: 0.000106 grad: 0.0819 (0.0848) loss: 0.8544 (0.8605) time: 0.1549 data: 0.0685 max mem: 8452 +Train: [29] [2000/6250] eta: 0:12:17 lr: 0.000106 grad: 0.0837 (0.0847) loss: 0.8599 (0.8604) time: 0.1966 data: 0.1024 max mem: 8452 +Train: [29] [2100/6250] eta: 0:12:05 lr: 0.000106 grad: 0.0849 (0.0846) loss: 0.8590 (0.8602) time: 0.1143 data: 0.0003 max mem: 8452 +Train: [29] [2200/6250] eta: 0:11:45 lr: 0.000106 grad: 0.0806 (0.0846) loss: 0.8555 (0.8601) time: 0.1732 data: 0.0965 max mem: 8452 +Train: [29] [2300/6250] eta: 0:11:25 lr: 0.000106 grad: 0.0817 (0.0845) loss: 0.8625 (0.8600) time: 0.0977 data: 0.0199 max mem: 8452 +Train: [29] [2400/6250] eta: 0:11:07 lr: 0.000106 grad: 0.0748 (0.0846) loss: 0.8560 (0.8598) time: 0.1553 data: 0.0742 max mem: 8452 +Train: [29] [2500/6250] eta: 0:10:49 lr: 0.000106 grad: 0.0749 (0.0845) loss: 0.8615 (0.8597) time: 0.1923 data: 0.1125 max mem: 8452 +Train: [29] [2600/6250] eta: 0:10:31 lr: 0.000106 grad: 0.0789 (0.0845) loss: 0.8572 (0.8596) time: 0.1504 data: 0.0656 max mem: 8452 +Train: [29] [2700/6250] eta: 0:10:12 lr: 0.000106 grad: 0.0834 (0.0845) loss: 0.8596 (0.8594) time: 0.1495 data: 0.0565 max mem: 8452 +Train: [29] [2800/6250] eta: 0:09:54 lr: 0.000106 grad: 0.0841 (0.0844) loss: 0.8610 (0.8594) time: 0.1697 data: 0.0936 max mem: 8452 +Train: [29] [2900/6250] eta: 0:09:34 lr: 0.000106 grad: 0.0820 (0.0844) loss: 0.8522 (0.8593) time: 0.1639 data: 0.0882 max mem: 8452 +Train: [29] [3000/6250] eta: 0:09:17 lr: 0.000106 grad: 0.0853 (0.0845) loss: 0.8541 (0.8592) time: 0.2200 data: 0.1142 max mem: 8452 +Train: [29] [3100/6250] eta: 0:09:00 lr: 0.000106 grad: 0.0859 (0.0846) loss: 0.8510 (0.8590) time: 0.1754 data: 0.0957 max mem: 8452 +Train: [29] [3200/6250] eta: 0:08:43 lr: 0.000106 grad: 0.0816 (0.0847) loss: 0.8514 (0.8589) time: 0.1857 data: 0.0873 max mem: 8452 +Train: [29] [3300/6250] eta: 0:08:30 lr: 0.000106 grad: 0.0859 (0.0847) loss: 0.8580 (0.8589) time: 0.0905 data: 0.0002 max mem: 8452 +Train: [29] [3400/6250] eta: 0:08:11 lr: 0.000106 grad: 0.0926 (0.0848) loss: 0.8559 (0.8588) time: 0.1525 data: 0.0650 max mem: 8452 +Train: [29] [3500/6250] eta: 0:07:55 lr: 0.000105 grad: 0.0873 (0.0848) loss: 0.8574 (0.8588) time: 0.2553 data: 0.1720 max mem: 8452 +Train: [29] [3600/6250] eta: 0:07:37 lr: 0.000105 grad: 0.0856 (0.0850) loss: 0.8616 (0.8587) time: 0.1258 data: 0.0274 max mem: 8452 +Train: [29] [3700/6250] eta: 0:07:21 lr: 0.000105 grad: 0.0763 (0.0851) loss: 0.8553 (0.8586) time: 0.1087 data: 0.0200 max mem: 8452 +Train: [29] [3800/6250] eta: 0:07:04 lr: 0.000105 grad: 0.0812 (0.0851) loss: 0.8625 (0.8586) time: 0.1832 data: 0.1052 max mem: 8452 +Train: [29] [3900/6250] eta: 0:06:47 lr: 0.000105 grad: 0.0820 (0.0851) loss: 0.8589 (0.8586) time: 0.1828 data: 0.1147 max mem: 8452 +Train: [29] [4000/6250] eta: 0:06:29 lr: 0.000105 grad: 0.0820 (0.0851) loss: 0.8556 (0.8585) time: 0.1562 data: 0.0816 max mem: 8452 +Train: [29] [4100/6250] eta: 0:06:11 lr: 0.000105 grad: 0.0873 (0.0851) loss: 0.8472 (0.8585) time: 0.1788 data: 0.1014 max mem: 8452 +Train: [29] [4200/6250] eta: 0:05:53 lr: 0.000105 grad: 0.0800 (0.0851) loss: 0.8572 (0.8584) time: 0.1600 data: 0.0825 max mem: 8452 +Train: [29] [4300/6250] eta: 0:05:36 lr: 0.000105 grad: 0.0874 (0.0852) loss: 0.8563 (0.8583) time: 0.1640 data: 0.0811 max mem: 8452 +Train: [29] [4400/6250] eta: 0:05:18 lr: 0.000105 grad: 0.0836 (0.0853) loss: 0.8559 (0.8583) time: 0.1764 data: 0.0881 max mem: 8452 +Train: [29] [4500/6250] eta: 0:05:01 lr: 0.000105 grad: 0.0921 (0.0853) loss: 0.8591 (0.8582) time: 0.1830 data: 0.1117 max mem: 8452 +Train: [29] [4600/6250] eta: 0:04:44 lr: 0.000105 grad: 0.0850 (0.0853) loss: 0.8583 (0.8581) time: 0.1741 data: 0.1006 max mem: 8452 +Train: [29] [4700/6250] eta: 0:04:26 lr: 0.000105 grad: 0.0878 (0.0854) loss: 0.8549 (0.8581) time: 0.1488 data: 0.0842 max mem: 8452 +Train: [29] [4800/6250] eta: 0:04:08 lr: 0.000105 grad: 0.0823 (0.0854) loss: 0.8583 (0.8581) time: 0.1610 data: 0.0774 max mem: 8452 +Train: [29] [4900/6250] eta: 0:03:51 lr: 0.000105 grad: 0.0837 (0.0854) loss: 0.8579 (0.8580) time: 0.1657 data: 0.0893 max mem: 8452 +Train: [29] [5000/6250] eta: 0:03:34 lr: 0.000105 grad: 0.0852 (0.0854) loss: 0.8603 (0.8581) time: 0.1671 data: 0.0885 max mem: 8452 +Train: [29] [5100/6250] eta: 0:03:16 lr: 0.000105 grad: 0.0811 (0.0855) loss: 0.8616 (0.8581) time: 0.1391 data: 0.0554 max mem: 8452 +Train: [29] [5200/6250] eta: 0:02:59 lr: 0.000105 grad: 0.0854 (0.0855) loss: 0.8619 (0.8581) time: 0.1431 data: 0.0619 max mem: 8452 +Train: [29] [5300/6250] eta: 0:02:41 lr: 0.000105 grad: 0.0784 (0.0855) loss: 0.8589 (0.8581) time: 0.1506 data: 0.0623 max mem: 8452 +Train: [29] [5400/6250] eta: 0:02:24 lr: 0.000105 grad: 0.0793 (0.0854) loss: 0.8621 (0.8581) time: 0.1520 data: 0.0654 max mem: 8452 +Train: [29] [5500/6250] eta: 0:02:07 lr: 0.000105 grad: 0.0810 (0.0854) loss: 0.8506 (0.8581) time: 0.1646 data: 0.0830 max mem: 8452 +Train: [29] [5600/6250] eta: 0:01:50 lr: 0.000105 grad: 0.0762 (0.0853) loss: 0.8594 (0.8581) time: 0.1594 data: 0.0800 max mem: 8452 +Train: [29] [5700/6250] eta: 0:01:33 lr: 0.000105 grad: 0.0909 (0.0853) loss: 0.8602 (0.8581) time: 0.1782 data: 0.1090 max mem: 8452 +Train: [29] [5800/6250] eta: 0:01:16 lr: 0.000105 grad: 0.0864 (0.0853) loss: 0.8599 (0.8581) time: 0.1416 data: 0.0563 max mem: 8452 +Train: [29] [5900/6250] eta: 0:00:59 lr: 0.000105 grad: 0.0794 (0.0853) loss: 0.8632 (0.8581) time: 0.1461 data: 0.0592 max mem: 8452 +Train: [29] [6000/6250] eta: 0:00:42 lr: 0.000105 grad: 0.0831 (0.0854) loss: 0.8514 (0.8581) time: 0.1640 data: 0.0863 max mem: 8452 +Train: [29] [6100/6250] eta: 0:00:25 lr: 0.000105 grad: 0.0812 (0.0853) loss: 0.8593 (0.8581) time: 0.1698 data: 0.0803 max mem: 8452 +Train: [29] [6200/6250] eta: 0:00:08 lr: 0.000105 grad: 0.0853 (0.0853) loss: 0.8599 (0.8581) time: 0.1583 data: 0.0881 max mem: 8452 +Train: [29] [6249/6250] eta: 0:00:00 lr: 0.000105 grad: 0.0856 (0.0853) loss: 0.8544 (0.8581) time: 0.1618 data: 0.0768 max mem: 8452 +Train: [29] Total time: 0:17:44 (0.1703 s / it) +Averaged stats: lr: 0.000105 grad: 0.0856 (0.0853) loss: 0.8544 (0.8581) +Eval (hcp-train-subset): [29] [ 0/62] eta: 0:05:34 loss: 0.8955 (0.8955) time: 5.4031 data: 5.3771 max mem: 8452 +Eval (hcp-train-subset): [29] [61/62] eta: 0:00:00 loss: 0.8850 (0.8843) time: 0.1496 data: 0.1284 max mem: 8452 +Eval (hcp-train-subset): [29] Total time: 0:00:14 (0.2383 s / it) +Averaged stats (hcp-train-subset): loss: 0.8850 (0.8843) +Making plots (hcp-train-subset): example=10 +Eval (hcp-val): [29] [ 0/62] eta: 0:05:38 loss: 0.8798 (0.8798) time: 5.4628 data: 5.4354 max mem: 8452 +Eval (hcp-val): [29] [61/62] eta: 0:00:00 loss: 0.8792 (0.8808) time: 0.1296 data: 0.1075 max mem: 8452 +Eval (hcp-val): [29] Total time: 0:00:14 (0.2352 s / it) +Averaged stats (hcp-val): loss: 0.8792 (0.8808) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [30] [ 0/6250] eta: 9:38:12 lr: 0.000105 grad: 0.1288 (0.1288) loss: 0.8747 (0.8747) time: 5.5509 data: 5.3029 max mem: 8452 +Train: [30] [ 100/6250] eta: 0:23:17 lr: 0.000105 grad: 0.0819 (0.0966) loss: 0.8602 (0.8719) time: 0.1736 data: 0.0665 max mem: 8452 +Train: [30] [ 200/6250] eta: 0:20:32 lr: 0.000105 grad: 0.0843 (0.0920) loss: 0.8689 (0.8698) time: 0.1623 data: 0.0699 max mem: 8452 +Train: [30] [ 300/6250] eta: 0:19:26 lr: 0.000105 grad: 0.0801 (0.0906) loss: 0.8632 (0.8674) time: 0.2229 data: 0.1312 max mem: 8452 +Train: [30] [ 400/6250] eta: 0:18:14 lr: 0.000105 grad: 0.0799 (0.0899) loss: 0.8574 (0.8653) time: 0.1661 data: 0.0825 max mem: 8452 +Train: [30] [ 500/6250] eta: 0:17:39 lr: 0.000105 grad: 0.0834 (0.0886) loss: 0.8509 (0.8636) time: 0.1938 data: 0.1057 max mem: 8452 +Train: [30] [ 600/6250] eta: 0:17:07 lr: 0.000105 grad: 0.0819 (0.0878) loss: 0.8516 (0.8624) time: 0.1685 data: 0.0853 max mem: 8452 +Train: [30] [ 700/6250] eta: 0:16:38 lr: 0.000105 grad: 0.0752 (0.0867) loss: 0.8552 (0.8621) time: 0.1856 data: 0.0909 max mem: 8452 +Train: [30] [ 800/6250] eta: 0:16:14 lr: 0.000105 grad: 0.0779 (0.0860) loss: 0.8596 (0.8618) time: 0.1439 data: 0.0368 max mem: 8452 +Train: [30] [ 900/6250] eta: 0:15:58 lr: 0.000105 grad: 0.0769 (0.0855) loss: 0.8644 (0.8617) time: 0.1955 data: 0.1265 max mem: 8452 +Train: [30] [1000/6250] eta: 0:15:39 lr: 0.000105 grad: 0.0789 (0.0849) loss: 0.8612 (0.8617) time: 0.1730 data: 0.0983 max mem: 8452 +Train: [30] [1100/6250] eta: 0:15:13 lr: 0.000105 grad: 0.0814 (0.0844) loss: 0.8578 (0.8617) time: 0.1757 data: 0.0933 max mem: 8452 +Train: [30] [1200/6250] eta: 0:14:48 lr: 0.000105 grad: 0.0780 (0.0839) loss: 0.8621 (0.8615) time: 0.1548 data: 0.0775 max mem: 8452 +Train: [30] [1300/6250] eta: 0:14:27 lr: 0.000105 grad: 0.0801 (0.0838) loss: 0.8578 (0.8614) time: 0.1745 data: 0.0966 max mem: 8452 +Train: [30] [1400/6250] eta: 0:14:07 lr: 0.000104 grad: 0.0858 (0.0839) loss: 0.8592 (0.8610) time: 0.1575 data: 0.0686 max mem: 8452 +Train: [30] [1500/6250] eta: 0:13:48 lr: 0.000104 grad: 0.0737 (0.0838) loss: 0.8540 (0.8607) time: 0.1723 data: 0.0909 max mem: 8452 +Train: [30] [1600/6250] eta: 0:13:25 lr: 0.000104 grad: 0.0837 (0.0837) loss: 0.8503 (0.8602) time: 0.1617 data: 0.0680 max mem: 8452 +Train: [30] [1700/6250] eta: 0:13:05 lr: 0.000104 grad: 0.0834 (0.0838) loss: 0.8493 (0.8599) time: 0.1849 data: 0.1030 max mem: 8452 +Train: [30] [1800/6250] eta: 0:12:44 lr: 0.000104 grad: 0.0810 (0.0840) loss: 0.8582 (0.8595) time: 0.1510 data: 0.0825 max mem: 8452 +Train: [30] [1900/6250] eta: 0:12:23 lr: 0.000104 grad: 0.0850 (0.0841) loss: 0.8515 (0.8592) time: 0.1429 data: 0.0609 max mem: 8452 +Train: [30] [2000/6250] eta: 0:12:01 lr: 0.000104 grad: 0.0858 (0.0840) loss: 0.8504 (0.8589) time: 0.1545 data: 0.0825 max mem: 8452 +Train: [30] [2100/6250] eta: 0:11:41 lr: 0.000104 grad: 0.0846 (0.0839) loss: 0.8575 (0.8589) time: 0.1618 data: 0.0809 max mem: 8452 +Train: [30] [2200/6250] eta: 0:11:21 lr: 0.000104 grad: 0.0794 (0.0839) loss: 0.8493 (0.8587) time: 0.1936 data: 0.1137 max mem: 8452 +Train: [30] [2300/6250] eta: 0:11:01 lr: 0.000104 grad: 0.0872 (0.0839) loss: 0.8531 (0.8586) time: 0.1517 data: 0.0772 max mem: 8452 +Train: [30] [2400/6250] eta: 0:10:45 lr: 0.000104 grad: 0.0847 (0.0840) loss: 0.8530 (0.8584) time: 0.1661 data: 0.0804 max mem: 8452 +Train: [30] [2500/6250] eta: 0:10:28 lr: 0.000104 grad: 0.0842 (0.0840) loss: 0.8566 (0.8583) time: 0.1613 data: 0.0740 max mem: 8452 +Train: [30] [2600/6250] eta: 0:10:17 lr: 0.000104 grad: 0.0844 (0.0841) loss: 0.8538 (0.8582) time: 0.2576 data: 0.1814 max mem: 8452 +Train: [30] [2700/6250] eta: 0:09:59 lr: 0.000104 grad: 0.0752 (0.0841) loss: 0.8521 (0.8581) time: 0.1665 data: 0.0938 max mem: 8452 +Train: [30] [2800/6250] eta: 0:09:42 lr: 0.000104 grad: 0.0864 (0.0842) loss: 0.8543 (0.8579) time: 0.1653 data: 0.0862 max mem: 8452 +Train: [30] [2900/6250] eta: 0:09:25 lr: 0.000104 grad: 0.0844 (0.0841) loss: 0.8548 (0.8579) time: 0.1502 data: 0.0493 max mem: 8452 +Train: [30] [3000/6250] eta: 0:09:08 lr: 0.000104 grad: 0.0730 (0.0841) loss: 0.8539 (0.8579) time: 0.1502 data: 0.0586 max mem: 8452 +Train: [30] [3100/6250] eta: 0:08:51 lr: 0.000104 grad: 0.0769 (0.0841) loss: 0.8577 (0.8578) time: 0.1676 data: 0.0870 max mem: 8452 +Train: [30] [3200/6250] eta: 0:08:33 lr: 0.000104 grad: 0.0829 (0.0840) loss: 0.8522 (0.8578) time: 0.1607 data: 0.0845 max mem: 8452 +Train: [30] [3300/6250] eta: 0:08:16 lr: 0.000104 grad: 0.0819 (0.0840) loss: 0.8558 (0.8578) time: 0.1708 data: 0.1004 max mem: 8452 +Train: [30] [3400/6250] eta: 0:07:58 lr: 0.000104 grad: 0.0790 (0.0840) loss: 0.8503 (0.8577) time: 0.1555 data: 0.0813 max mem: 8452 +Train: [30] [3500/6250] eta: 0:07:43 lr: 0.000104 grad: 0.0879 (0.0840) loss: 0.8521 (0.8576) time: 0.1396 data: 0.0346 max mem: 8452 +Train: [30] [3600/6250] eta: 0:07:25 lr: 0.000104 grad: 0.0816 (0.0841) loss: 0.8525 (0.8575) time: 0.1827 data: 0.1119 max mem: 8452 +Train: [30] [3700/6250] eta: 0:07:09 lr: 0.000104 grad: 0.0803 (0.0842) loss: 0.8520 (0.8573) time: 0.1701 data: 0.0955 max mem: 8452 +Train: [30] [3800/6250] eta: 0:06:52 lr: 0.000104 grad: 0.0780 (0.0841) loss: 0.8478 (0.8572) time: 0.1518 data: 0.0706 max mem: 8452 +Train: [30] [3900/6250] eta: 0:06:34 lr: 0.000104 grad: 0.0863 (0.0842) loss: 0.8515 (0.8571) time: 0.1725 data: 0.0875 max mem: 8452 +Train: [30] [4000/6250] eta: 0:06:17 lr: 0.000104 grad: 0.0807 (0.0842) loss: 0.8526 (0.8570) time: 0.1722 data: 0.0913 max mem: 8452 +Train: [30] [4100/6250] eta: 0:06:00 lr: 0.000104 grad: 0.0829 (0.0843) loss: 0.8501 (0.8568) time: 0.1578 data: 0.0794 max mem: 8452 +Train: [30] [4200/6250] eta: 0:05:43 lr: 0.000104 grad: 0.0833 (0.0843) loss: 0.8477 (0.8567) time: 0.1737 data: 0.0961 max mem: 8452 +Train: [30] [4300/6250] eta: 0:05:26 lr: 0.000104 grad: 0.0839 (0.0844) loss: 0.8493 (0.8565) time: 0.1472 data: 0.0660 max mem: 8452 +Train: [30] [4400/6250] eta: 0:05:09 lr: 0.000104 grad: 0.0801 (0.0844) loss: 0.8582 (0.8564) time: 0.1481 data: 0.0670 max mem: 8452 +Train: [30] [4500/6250] eta: 0:04:52 lr: 0.000104 grad: 0.0873 (0.0844) loss: 0.8519 (0.8564) time: 0.1812 data: 0.0973 max mem: 8452 +Train: [30] [4600/6250] eta: 0:04:35 lr: 0.000104 grad: 0.0894 (0.0845) loss: 0.8458 (0.8563) time: 0.1553 data: 0.0774 max mem: 8452 +Train: [30] [4700/6250] eta: 0:04:18 lr: 0.000104 grad: 0.0876 (0.0846) loss: 0.8426 (0.8562) time: 0.1674 data: 0.0954 max mem: 8452 +Train: [30] [4800/6250] eta: 0:04:02 lr: 0.000104 grad: 0.0840 (0.0846) loss: 0.8541 (0.8562) time: 0.1931 data: 0.1170 max mem: 8452 +Train: [30] [4900/6250] eta: 0:03:45 lr: 0.000104 grad: 0.0822 (0.0846) loss: 0.8567 (0.8561) time: 0.1672 data: 0.0865 max mem: 8452 +Train: [30] [5000/6250] eta: 0:03:27 lr: 0.000104 grad: 0.0859 (0.0847) loss: 0.8521 (0.8560) time: 0.1160 data: 0.0349 max mem: 8452 +Train: [30] [5100/6250] eta: 0:03:11 lr: 0.000104 grad: 0.0853 (0.0848) loss: 0.8547 (0.8560) time: 0.1577 data: 0.0732 max mem: 8452 +Train: [30] [5200/6250] eta: 0:02:54 lr: 0.000104 grad: 0.0836 (0.0848) loss: 0.8624 (0.8560) time: 0.1376 data: 0.0502 max mem: 8452 +Train: [30] [5300/6250] eta: 0:02:37 lr: 0.000104 grad: 0.0805 (0.0848) loss: 0.8620 (0.8561) time: 0.1934 data: 0.0745 max mem: 8452 +Train: [30] [5400/6250] eta: 0:02:21 lr: 0.000103 grad: 0.0784 (0.0848) loss: 0.8604 (0.8561) time: 0.1846 data: 0.0972 max mem: 8452 +Train: [30] [5500/6250] eta: 0:02:04 lr: 0.000103 grad: 0.0773 (0.0848) loss: 0.8593 (0.8562) time: 0.1357 data: 0.0436 max mem: 8452 +Train: [30] [5600/6250] eta: 0:01:48 lr: 0.000103 grad: 0.0769 (0.0847) loss: 0.8576 (0.8562) time: 0.1291 data: 0.0251 max mem: 8452 +Train: [30] [5700/6250] eta: 0:01:31 lr: 0.000103 grad: 0.0838 (0.0847) loss: 0.8523 (0.8562) time: 0.1665 data: 0.0928 max mem: 8452 +Train: [30] [5800/6250] eta: 0:01:15 lr: 0.000103 grad: 0.0802 (0.0847) loss: 0.8519 (0.8562) time: 0.3065 data: 0.2088 max mem: 8452 +Train: [30] [5900/6250] eta: 0:00:58 lr: 0.000103 grad: 0.0785 (0.0847) loss: 0.8576 (0.8563) time: 0.1559 data: 0.0683 max mem: 8452 +Train: [30] [6000/6250] eta: 0:00:41 lr: 0.000103 grad: 0.0834 (0.0846) loss: 0.8575 (0.8564) time: 0.1034 data: 0.0002 max mem: 8452 +Train: [30] [6100/6250] eta: 0:00:25 lr: 0.000103 grad: 0.0857 (0.0846) loss: 0.8614 (0.8565) time: 0.1721 data: 0.0831 max mem: 8452 +Train: [30] [6200/6250] eta: 0:00:08 lr: 0.000103 grad: 0.0770 (0.0846) loss: 0.8632 (0.8565) time: 0.1683 data: 0.0867 max mem: 8452 +Train: [30] [6249/6250] eta: 0:00:00 lr: 0.000103 grad: 0.0838 (0.0846) loss: 0.8616 (0.8566) time: 0.1858 data: 0.1151 max mem: 8452 +Train: [30] Total time: 0:17:30 (0.1681 s / it) +Averaged stats: lr: 0.000103 grad: 0.0838 (0.0846) loss: 0.8616 (0.8566) +Eval (hcp-train-subset): [30] [ 0/62] eta: 0:05:46 loss: 0.8891 (0.8891) time: 5.5881 data: 5.5606 max mem: 8452 +Eval (hcp-train-subset): [30] [61/62] eta: 0:00:00 loss: 0.8819 (0.8820) time: 0.1466 data: 0.1241 max mem: 8452 +Eval (hcp-train-subset): [30] Total time: 0:00:14 (0.2312 s / it) +Averaged stats (hcp-train-subset): loss: 0.8819 (0.8820) +Eval (hcp-val): [30] [ 0/62] eta: 0:05:52 loss: 0.8746 (0.8746) time: 5.6856 data: 5.6590 max mem: 8452 +Eval (hcp-val): [30] [61/62] eta: 0:00:00 loss: 0.8772 (0.8794) time: 0.1432 data: 0.1222 max mem: 8452 +Eval (hcp-val): [30] Total time: 0:00:14 (0.2322 s / it) +Averaged stats (hcp-val): loss: 0.8772 (0.8794) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [31] [ 0/6250] eta: 10:03:35 lr: 0.000103 grad: 0.1717 (0.1717) loss: 0.9008 (0.9008) time: 5.7946 data: 5.6629 max mem: 8452 +Train: [31] [ 100/6250] eta: 0:21:51 lr: 0.000103 grad: 0.0915 (0.0939) loss: 0.8683 (0.8755) time: 0.1634 data: 0.0654 max mem: 8452 +Train: [31] [ 200/6250] eta: 0:19:21 lr: 0.000103 grad: 0.0810 (0.0927) loss: 0.8631 (0.8700) time: 0.1800 data: 0.0894 max mem: 8452 +Train: [31] [ 300/6250] eta: 0:18:16 lr: 0.000103 grad: 0.0721 (0.0892) loss: 0.8706 (0.8686) time: 0.1863 data: 0.0861 max mem: 8452 +Train: [31] [ 400/6250] eta: 0:17:24 lr: 0.000103 grad: 0.0837 (0.0877) loss: 0.8654 (0.8674) time: 0.1714 data: 0.0805 max mem: 8452 +Train: [31] [ 500/6250] eta: 0:16:49 lr: 0.000103 grad: 0.0787 (0.0865) loss: 0.8646 (0.8669) time: 0.1746 data: 0.0851 max mem: 8452 +Train: [31] [ 600/6250] eta: 0:16:23 lr: 0.000103 grad: 0.0758 (0.0850) loss: 0.8606 (0.8661) time: 0.1815 data: 0.1051 max mem: 8452 +Train: [31] [ 700/6250] eta: 0:16:03 lr: 0.000103 grad: 0.0823 (0.0845) loss: 0.8615 (0.8654) time: 0.1682 data: 0.0840 max mem: 8452 +Train: [31] [ 800/6250] eta: 0:15:40 lr: 0.000103 grad: 0.0780 (0.0837) loss: 0.8583 (0.8649) time: 0.1529 data: 0.0628 max mem: 8452 +Train: [31] [ 900/6250] eta: 0:15:48 lr: 0.000103 grad: 0.0772 (0.0833) loss: 0.8597 (0.8645) time: 0.2799 data: 0.1950 max mem: 8452 +Train: [31] [1000/6250] eta: 0:15:22 lr: 0.000103 grad: 0.0777 (0.0829) loss: 0.8611 (0.8643) time: 0.1734 data: 0.0877 max mem: 8452 +Train: [31] [1100/6250] eta: 0:15:08 lr: 0.000103 grad: 0.0759 (0.0825) loss: 0.8634 (0.8640) time: 0.1616 data: 0.0880 max mem: 8452 +Train: [31] [1200/6250] eta: 0:14:44 lr: 0.000103 grad: 0.0762 (0.0823) loss: 0.8610 (0.8635) time: 0.1430 data: 0.0629 max mem: 8452 +Train: [31] [1300/6250] eta: 0:14:21 lr: 0.000103 grad: 0.0815 (0.0825) loss: 0.8552 (0.8627) time: 0.1780 data: 0.0919 max mem: 8452 +Train: [31] [1400/6250] eta: 0:14:01 lr: 0.000103 grad: 0.0810 (0.0824) loss: 0.8609 (0.8623) time: 0.1664 data: 0.0761 max mem: 8452 +Train: [31] [1500/6250] eta: 0:13:41 lr: 0.000103 grad: 0.0777 (0.0824) loss: 0.8631 (0.8618) time: 0.1749 data: 0.1033 max mem: 8452 +Train: [31] [1600/6250] eta: 0:13:20 lr: 0.000103 grad: 0.0832 (0.0825) loss: 0.8517 (0.8613) time: 0.1545 data: 0.0629 max mem: 8452 +Train: [31] [1700/6250] eta: 0:12:57 lr: 0.000103 grad: 0.0796 (0.0826) loss: 0.8542 (0.8610) time: 0.1582 data: 0.0727 max mem: 8452 +Train: [31] [1800/6250] eta: 0:12:35 lr: 0.000103 grad: 0.0875 (0.0828) loss: 0.8507 (0.8606) time: 0.1536 data: 0.0612 max mem: 8452 +Train: [31] [1900/6250] eta: 0:12:15 lr: 0.000103 grad: 0.0823 (0.0828) loss: 0.8568 (0.8604) time: 0.1727 data: 0.0973 max mem: 8452 +Train: [31] [2000/6250] eta: 0:11:57 lr: 0.000103 grad: 0.0792 (0.0828) loss: 0.8607 (0.8602) time: 0.1492 data: 0.0765 max mem: 8452 +Train: [31] [2100/6250] eta: 0:11:44 lr: 0.000103 grad: 0.0807 (0.0829) loss: 0.8568 (0.8601) time: 0.2511 data: 0.1669 max mem: 8452 +Train: [31] [2200/6250] eta: 0:11:31 lr: 0.000103 grad: 0.0795 (0.0828) loss: 0.8563 (0.8600) time: 0.3197 data: 0.2160 max mem: 8452 +Train: [31] [2300/6250] eta: 0:11:15 lr: 0.000103 grad: 0.0784 (0.0828) loss: 0.8585 (0.8599) time: 0.0865 data: 0.0002 max mem: 8452 +Train: [31] [2400/6250] eta: 0:10:55 lr: 0.000103 grad: 0.0809 (0.0829) loss: 0.8548 (0.8597) time: 0.1392 data: 0.0571 max mem: 8452 +Train: [31] [2500/6250] eta: 0:10:37 lr: 0.000103 grad: 0.0725 (0.0828) loss: 0.8599 (0.8595) time: 0.1333 data: 0.0477 max mem: 8452 +Train: [31] [2600/6250] eta: 0:10:18 lr: 0.000103 grad: 0.0880 (0.0829) loss: 0.8446 (0.8592) time: 0.1740 data: 0.0995 max mem: 8452 +Train: [31] [2700/6250] eta: 0:10:00 lr: 0.000103 grad: 0.0813 (0.0829) loss: 0.8497 (0.8591) time: 0.1695 data: 0.0993 max mem: 8452 +Train: [31] [2800/6250] eta: 0:09:43 lr: 0.000103 grad: 0.0823 (0.0829) loss: 0.8536 (0.8589) time: 0.1499 data: 0.0743 max mem: 8452 +Train: [31] [2900/6250] eta: 0:09:27 lr: 0.000103 grad: 0.0788 (0.0829) loss: 0.8568 (0.8588) time: 0.1944 data: 0.1126 max mem: 8452 +Train: [31] [3000/6250] eta: 0:09:09 lr: 0.000103 grad: 0.0810 (0.0831) loss: 0.8569 (0.8586) time: 0.1706 data: 0.0937 max mem: 8452 +Train: [31] [3100/6250] eta: 0:08:52 lr: 0.000103 grad: 0.0815 (0.0831) loss: 0.8574 (0.8585) time: 0.1679 data: 0.0948 max mem: 8452 +Train: [31] [3200/6250] eta: 0:08:35 lr: 0.000102 grad: 0.0787 (0.0832) loss: 0.8525 (0.8584) time: 0.1805 data: 0.0984 max mem: 8452 +Train: [31] [3300/6250] eta: 0:08:17 lr: 0.000102 grad: 0.0730 (0.0831) loss: 0.8625 (0.8584) time: 0.1501 data: 0.0724 max mem: 8452 +Train: [31] [3400/6250] eta: 0:08:00 lr: 0.000102 grad: 0.0821 (0.0831) loss: 0.8624 (0.8584) time: 0.1692 data: 0.0924 max mem: 8452 +Train: [31] [3500/6250] eta: 0:07:42 lr: 0.000102 grad: 0.0754 (0.0831) loss: 0.8608 (0.8584) time: 0.1501 data: 0.0634 max mem: 8452 +Train: [31] [3600/6250] eta: 0:07:26 lr: 0.000102 grad: 0.0819 (0.0832) loss: 0.8585 (0.8584) time: 0.1686 data: 0.0871 max mem: 8452 +Train: [31] [3700/6250] eta: 0:07:09 lr: 0.000102 grad: 0.0775 (0.0832) loss: 0.8574 (0.8584) time: 0.1639 data: 0.0828 max mem: 8452 +Train: [31] [3800/6250] eta: 0:06:51 lr: 0.000102 grad: 0.0823 (0.0832) loss: 0.8581 (0.8585) time: 0.1635 data: 0.0783 max mem: 8452 +Train: [31] [3900/6250] eta: 0:06:34 lr: 0.000102 grad: 0.0824 (0.0832) loss: 0.8585 (0.8585) time: 0.1767 data: 0.1068 max mem: 8452 +Train: [31] [4000/6250] eta: 0:06:18 lr: 0.000102 grad: 0.0881 (0.0832) loss: 0.8495 (0.8584) time: 0.1819 data: 0.0976 max mem: 8452 +Train: [31] [4100/6250] eta: 0:06:02 lr: 0.000102 grad: 0.0770 (0.0832) loss: 0.8666 (0.8584) time: 0.1704 data: 0.0879 max mem: 8452 +Train: [31] [4200/6250] eta: 0:05:46 lr: 0.000102 grad: 0.0803 (0.0833) loss: 0.8667 (0.8585) time: 0.1711 data: 0.0947 max mem: 8452 +Train: [31] [4300/6250] eta: 0:05:29 lr: 0.000102 grad: 0.0895 (0.0833) loss: 0.8596 (0.8585) time: 0.1691 data: 0.0757 max mem: 8452 +Train: [31] [4400/6250] eta: 0:05:12 lr: 0.000102 grad: 0.0808 (0.0833) loss: 0.8572 (0.8585) time: 0.1965 data: 0.1261 max mem: 8452 +Train: [31] [4500/6250] eta: 0:04:55 lr: 0.000102 grad: 0.0860 (0.0835) loss: 0.8641 (0.8585) time: 0.1576 data: 0.0826 max mem: 8452 +Train: [31] [4600/6250] eta: 0:04:38 lr: 0.000102 grad: 0.0834 (0.0835) loss: 0.8608 (0.8585) time: 0.1596 data: 0.0818 max mem: 8452 +Train: [31] [4700/6250] eta: 0:04:21 lr: 0.000102 grad: 0.0834 (0.0836) loss: 0.8524 (0.8584) time: 0.1570 data: 0.0828 max mem: 8452 +Train: [31] [4800/6250] eta: 0:04:04 lr: 0.000102 grad: 0.0930 (0.0838) loss: 0.8511 (0.8584) time: 0.1355 data: 0.0542 max mem: 8452 +Train: [31] [4900/6250] eta: 0:03:47 lr: 0.000102 grad: 0.0795 (0.0840) loss: 0.8558 (0.8584) time: 0.1826 data: 0.1058 max mem: 8452 +Train: [31] [5000/6250] eta: 0:03:29 lr: 0.000102 grad: 0.0862 (0.0841) loss: 0.8578 (0.8583) time: 0.1438 data: 0.0556 max mem: 8452 +Train: [31] [5100/6250] eta: 0:03:12 lr: 0.000102 grad: 0.0803 (0.0841) loss: 0.8558 (0.8582) time: 0.1417 data: 0.0605 max mem: 8452 +Train: [31] [5200/6250] eta: 0:02:55 lr: 0.000102 grad: 0.0906 (0.0842) loss: 0.8509 (0.8582) time: 0.1756 data: 0.0947 max mem: 8452 +Train: [31] [5300/6250] eta: 0:02:39 lr: 0.000102 grad: 0.0840 (0.0842) loss: 0.8528 (0.8581) time: 0.1282 data: 0.0446 max mem: 8452 +Train: [31] [5400/6250] eta: 0:02:22 lr: 0.000102 grad: 0.0843 (0.0843) loss: 0.8511 (0.8580) time: 0.1672 data: 0.0776 max mem: 8452 +Train: [31] [5500/6250] eta: 0:02:05 lr: 0.000102 grad: 0.0857 (0.0844) loss: 0.8539 (0.8580) time: 0.1447 data: 0.0536 max mem: 8452 +Train: [31] [5600/6250] eta: 0:01:48 lr: 0.000102 grad: 0.0885 (0.0845) loss: 0.8523 (0.8578) time: 0.1819 data: 0.1133 max mem: 8452 +Train: [31] [5700/6250] eta: 0:01:31 lr: 0.000102 grad: 0.0824 (0.0845) loss: 0.8530 (0.8578) time: 0.1163 data: 0.0272 max mem: 8452 +Train: [31] [5800/6250] eta: 0:01:15 lr: 0.000102 grad: 0.0819 (0.0845) loss: 0.8553 (0.8577) time: 0.1542 data: 0.0740 max mem: 8452 +Train: [31] [5900/6250] eta: 0:00:58 lr: 0.000102 grad: 0.0824 (0.0846) loss: 0.8478 (0.8575) time: 0.1631 data: 0.0888 max mem: 8452 +Train: [31] [6000/6250] eta: 0:00:41 lr: 0.000102 grad: 0.0850 (0.0846) loss: 0.8512 (0.8574) time: 0.1480 data: 0.0634 max mem: 8452 +Train: [31] [6100/6250] eta: 0:00:24 lr: 0.000102 grad: 0.0862 (0.0847) loss: 0.8510 (0.8573) time: 0.1359 data: 0.0471 max mem: 8452 +Train: [31] [6200/6250] eta: 0:00:08 lr: 0.000102 grad: 0.0894 (0.0847) loss: 0.8473 (0.8572) time: 0.1283 data: 0.0444 max mem: 8452 +Train: [31] [6249/6250] eta: 0:00:00 lr: 0.000102 grad: 0.0822 (0.0847) loss: 0.8621 (0.8572) time: 0.1378 data: 0.0678 max mem: 8452 +Train: [31] Total time: 0:17:26 (0.1675 s / it) +Averaged stats: lr: 0.000102 grad: 0.0822 (0.0847) loss: 0.8621 (0.8572) +Eval (hcp-train-subset): [31] [ 0/62] eta: 0:04:58 loss: 0.8930 (0.8930) time: 4.8221 data: 4.7940 max mem: 8452 +Eval (hcp-train-subset): [31] [61/62] eta: 0:00:00 loss: 0.8818 (0.8825) time: 0.1384 data: 0.1175 max mem: 8452 +Eval (hcp-train-subset): [31] Total time: 0:00:14 (0.2267 s / it) +Averaged stats (hcp-train-subset): loss: 0.8818 (0.8825) +Eval (hcp-val): [31] [ 0/62] eta: 0:05:08 loss: 0.8753 (0.8753) time: 4.9739 data: 4.9453 max mem: 8452 +Eval (hcp-val): [31] [61/62] eta: 0:00:00 loss: 0.8780 (0.8797) time: 0.1300 data: 0.1077 max mem: 8452 +Eval (hcp-val): [31] Total time: 0:00:14 (0.2286 s / it) +Averaged stats (hcp-val): loss: 0.8780 (0.8797) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [32] [ 0/6250] eta: 10:28:51 lr: 0.000102 grad: 0.1593 (0.1593) loss: 0.9014 (0.9014) time: 6.0370 data: 5.9367 max mem: 8452 +Train: [32] [ 100/6250] eta: 0:22:02 lr: 0.000102 grad: 0.0825 (0.1129) loss: 0.8633 (0.8720) time: 0.1530 data: 0.0456 max mem: 8452 +Train: [32] [ 200/6250] eta: 0:18:56 lr: 0.000102 grad: 0.0915 (0.1096) loss: 0.8420 (0.8620) time: 0.1667 data: 0.0719 max mem: 8452 +Train: [32] [ 300/6250] eta: 0:17:27 lr: 0.000102 grad: 0.0870 (0.1041) loss: 0.8544 (0.8582) time: 0.1358 data: 0.0497 max mem: 8452 +Train: [32] [ 400/6250] eta: 0:16:37 lr: 0.000102 grad: 0.0872 (0.1030) loss: 0.8580 (0.8572) time: 0.1699 data: 0.0888 max mem: 8452 +Train: [32] [ 500/6250] eta: 0:16:02 lr: 0.000102 grad: 0.0788 (0.0997) loss: 0.8554 (0.8565) time: 0.1706 data: 0.0893 max mem: 8452 +Train: [32] [ 600/6250] eta: 0:15:44 lr: 0.000102 grad: 0.0732 (0.0968) loss: 0.8599 (0.8570) time: 0.1488 data: 0.0667 max mem: 8452 +Train: [32] [ 700/6250] eta: 0:15:34 lr: 0.000102 grad: 0.0820 (0.0942) loss: 0.8577 (0.8575) time: 0.1773 data: 0.0935 max mem: 8452 +Train: [32] [ 800/6250] eta: 0:15:24 lr: 0.000101 grad: 0.0771 (0.0923) loss: 0.8594 (0.8576) time: 0.1904 data: 0.1068 max mem: 8452 +Train: [32] [ 900/6250] eta: 0:15:12 lr: 0.000101 grad: 0.0793 (0.0910) loss: 0.8570 (0.8577) time: 0.1696 data: 0.0846 max mem: 8452 +Train: [32] [1000/6250] eta: 0:14:50 lr: 0.000101 grad: 0.0807 (0.0902) loss: 0.8637 (0.8580) time: 0.1343 data: 0.0529 max mem: 8452 +Train: [32] [1100/6250] eta: 0:14:38 lr: 0.000101 grad: 0.0795 (0.0896) loss: 0.8575 (0.8582) time: 0.2597 data: 0.1984 max mem: 8452 +Train: [32] [1200/6250] eta: 0:14:21 lr: 0.000101 grad: 0.0826 (0.0890) loss: 0.8584 (0.8581) time: 0.1779 data: 0.0980 max mem: 8452 +Train: [32] [1300/6250] eta: 0:14:04 lr: 0.000101 grad: 0.0832 (0.0889) loss: 0.8489 (0.8580) time: 0.1587 data: 0.0800 max mem: 8452 +Train: [32] [1400/6250] eta: 0:13:50 lr: 0.000101 grad: 0.0871 (0.0889) loss: 0.8549 (0.8578) time: 0.1665 data: 0.0791 max mem: 8452 +Train: [32] [1500/6250] eta: 0:13:33 lr: 0.000101 grad: 0.0852 (0.0889) loss: 0.8498 (0.8574) time: 0.1644 data: 0.0840 max mem: 8452 +Train: [32] [1600/6250] eta: 0:13:14 lr: 0.000101 grad: 0.0840 (0.0888) loss: 0.8564 (0.8572) time: 0.1727 data: 0.0924 max mem: 8452 +Train: [32] [1700/6250] eta: 0:12:57 lr: 0.000101 grad: 0.0866 (0.0887) loss: 0.8484 (0.8569) time: 0.1997 data: 0.1196 max mem: 8452 +Train: [32] [1800/6250] eta: 0:12:35 lr: 0.000101 grad: 0.0874 (0.0886) loss: 0.8519 (0.8565) time: 0.1392 data: 0.0558 max mem: 8452 +Train: [32] [1900/6250] eta: 0:12:18 lr: 0.000101 grad: 0.0844 (0.0886) loss: 0.8424 (0.8561) time: 0.1732 data: 0.0893 max mem: 8452 +Train: [32] [2000/6250] eta: 0:12:03 lr: 0.000101 grad: 0.0868 (0.0888) loss: 0.8580 (0.8558) time: 0.1157 data: 0.0300 max mem: 8452 +Train: [32] [2100/6250] eta: 0:11:43 lr: 0.000101 grad: 0.0838 (0.0889) loss: 0.8503 (0.8555) time: 0.1735 data: 0.0730 max mem: 8452 +Train: [32] [2200/6250] eta: 0:11:36 lr: 0.000101 grad: 0.0821 (0.0890) loss: 0.8489 (0.8553) time: 0.1510 data: 0.0450 max mem: 8452 +Train: [32] [2300/6250] eta: 0:11:20 lr: 0.000101 grad: 0.0852 (0.0893) loss: 0.8475 (0.8548) time: 0.1586 data: 0.0813 max mem: 8452 +Train: [32] [2400/6250] eta: 0:11:02 lr: 0.000101 grad: 0.0877 (0.0894) loss: 0.8539 (0.8545) time: 0.1573 data: 0.0762 max mem: 8452 +Train: [32] [2500/6250] eta: 0:10:43 lr: 0.000101 grad: 0.0888 (0.0895) loss: 0.8497 (0.8542) time: 0.1473 data: 0.0699 max mem: 8452 +Train: [32] [2600/6250] eta: 0:10:23 lr: 0.000101 grad: 0.0932 (0.0896) loss: 0.8522 (0.8540) time: 0.1516 data: 0.0722 max mem: 8452 +Train: [32] [2700/6250] eta: 0:10:05 lr: 0.000101 grad: 0.0854 (0.0895) loss: 0.8442 (0.8538) time: 0.1573 data: 0.0754 max mem: 8452 +Train: [32] [2800/6250] eta: 0:09:46 lr: 0.000101 grad: 0.0888 (0.0895) loss: 0.8488 (0.8537) time: 0.1727 data: 0.0924 max mem: 8452 +Train: [32] [2900/6250] eta: 0:09:27 lr: 0.000101 grad: 0.0845 (0.0894) loss: 0.8525 (0.8536) time: 0.1566 data: 0.0732 max mem: 8452 +Train: [32] [3000/6250] eta: 0:09:08 lr: 0.000101 grad: 0.0853 (0.0893) loss: 0.8493 (0.8534) time: 0.1673 data: 0.0910 max mem: 8452 +Train: [32] [3100/6250] eta: 0:08:49 lr: 0.000101 grad: 0.0850 (0.0893) loss: 0.8556 (0.8534) time: 0.1344 data: 0.0481 max mem: 8452 +Train: [32] [3200/6250] eta: 0:08:31 lr: 0.000101 grad: 0.0870 (0.0893) loss: 0.8430 (0.8533) time: 0.1522 data: 0.0670 max mem: 8452 +Train: [32] [3300/6250] eta: 0:08:14 lr: 0.000101 grad: 0.0886 (0.0893) loss: 0.8494 (0.8532) time: 0.1607 data: 0.0929 max mem: 8452 +Train: [32] [3400/6250] eta: 0:08:00 lr: 0.000101 grad: 0.0908 (0.0894) loss: 0.8410 (0.8531) time: 0.2586 data: 0.1869 max mem: 8452 +Train: [32] [3500/6250] eta: 0:07:42 lr: 0.000101 grad: 0.0853 (0.0893) loss: 0.8444 (0.8529) time: 0.1551 data: 0.0800 max mem: 8452 +Train: [32] [3600/6250] eta: 0:07:26 lr: 0.000101 grad: 0.0936 (0.0894) loss: 0.8469 (0.8528) time: 0.1574 data: 0.0771 max mem: 8452 +Train: [32] [3700/6250] eta: 0:07:09 lr: 0.000101 grad: 0.0844 (0.0895) loss: 0.8478 (0.8526) time: 0.1771 data: 0.0898 max mem: 8452 +Train: [32] [3800/6250] eta: 0:06:52 lr: 0.000101 grad: 0.0872 (0.0895) loss: 0.8432 (0.8525) time: 0.1608 data: 0.0752 max mem: 8452 +Train: [32] [3900/6250] eta: 0:06:35 lr: 0.000101 grad: 0.0831 (0.0895) loss: 0.8536 (0.8524) time: 0.1730 data: 0.0885 max mem: 8452 +Train: [32] [4000/6250] eta: 0:06:18 lr: 0.000101 grad: 0.0868 (0.0895) loss: 0.8506 (0.8524) time: 0.1741 data: 0.0869 max mem: 8452 +Train: [32] [4100/6250] eta: 0:06:01 lr: 0.000101 grad: 0.0892 (0.0896) loss: 0.8540 (0.8524) time: 0.1637 data: 0.0773 max mem: 8452 +Train: [32] [4200/6250] eta: 0:05:44 lr: 0.000101 grad: 0.0850 (0.0896) loss: 0.8480 (0.8524) time: 0.1231 data: 0.0486 max mem: 8452 +Train: [32] [4300/6250] eta: 0:05:26 lr: 0.000101 grad: 0.0912 (0.0896) loss: 0.8518 (0.8524) time: 0.1538 data: 0.0803 max mem: 8452 +Train: [32] [4400/6250] eta: 0:05:10 lr: 0.000101 grad: 0.0851 (0.0896) loss: 0.8545 (0.8524) time: 0.1791 data: 0.1013 max mem: 8452 +Train: [32] [4500/6250] eta: 0:04:53 lr: 0.000101 grad: 0.0915 (0.0896) loss: 0.8563 (0.8524) time: 0.1457 data: 0.0584 max mem: 8452 +Train: [32] [4600/6250] eta: 0:04:37 lr: 0.000101 grad: 0.0895 (0.0896) loss: 0.8517 (0.8524) time: 0.2073 data: 0.1227 max mem: 8452 +Train: [32] [4700/6250] eta: 0:04:19 lr: 0.000100 grad: 0.0907 (0.0897) loss: 0.8487 (0.8524) time: 0.1443 data: 0.0699 max mem: 8452 +Train: [32] [4800/6250] eta: 0:04:02 lr: 0.000100 grad: 0.0913 (0.0898) loss: 0.8496 (0.8524) time: 0.1652 data: 0.0868 max mem: 8452 +Train: [32] [4900/6250] eta: 0:03:45 lr: 0.000100 grad: 0.0835 (0.0898) loss: 0.8561 (0.8523) time: 0.1616 data: 0.0839 max mem: 8452 +Train: [32] [5000/6250] eta: 0:03:28 lr: 0.000100 grad: 0.0791 (0.0897) loss: 0.8577 (0.8524) time: 0.1622 data: 0.0835 max mem: 8452 +Train: [32] [5100/6250] eta: 0:03:11 lr: 0.000100 grad: 0.0827 (0.0897) loss: 0.8544 (0.8524) time: 0.1331 data: 0.0461 max mem: 8452 +Train: [32] [5200/6250] eta: 0:02:54 lr: 0.000100 grad: 0.0878 (0.0897) loss: 0.8478 (0.8524) time: 0.1356 data: 0.0450 max mem: 8452 +Train: [32] [5300/6250] eta: 0:02:37 lr: 0.000100 grad: 0.0829 (0.0897) loss: 0.8529 (0.8523) time: 0.1585 data: 0.0769 max mem: 8452 +Train: [32] [5400/6250] eta: 0:02:20 lr: 0.000100 grad: 0.0883 (0.0897) loss: 0.8535 (0.8524) time: 0.1718 data: 0.0907 max mem: 8452 +Train: [32] [5500/6250] eta: 0:02:04 lr: 0.000100 grad: 0.0814 (0.0896) loss: 0.8502 (0.8524) time: 0.1018 data: 0.0187 max mem: 8452 +Train: [32] [5600/6250] eta: 0:01:47 lr: 0.000100 grad: 0.0896 (0.0896) loss: 0.8532 (0.8524) time: 0.2216 data: 0.1201 max mem: 8452 +Train: [32] [5700/6250] eta: 0:01:31 lr: 0.000100 grad: 0.0847 (0.0896) loss: 0.8556 (0.8524) time: 0.2089 data: 0.1185 max mem: 8452 +Train: [32] [5800/6250] eta: 0:01:14 lr: 0.000100 grad: 0.0846 (0.0896) loss: 0.8533 (0.8523) time: 0.1764 data: 0.0920 max mem: 8452 +Train: [32] [5900/6250] eta: 0:00:58 lr: 0.000100 grad: 0.0798 (0.0896) loss: 0.8496 (0.8523) time: 0.1394 data: 0.0496 max mem: 8452 +Train: [32] [6000/6250] eta: 0:00:41 lr: 0.000100 grad: 0.0843 (0.0895) loss: 0.8458 (0.8522) time: 0.1112 data: 0.0186 max mem: 8452 +Train: [32] [6100/6250] eta: 0:00:24 lr: 0.000100 grad: 0.0812 (0.0895) loss: 0.8511 (0.8522) time: 0.1469 data: 0.0671 max mem: 8452 +Train: [32] [6200/6250] eta: 0:00:08 lr: 0.000100 grad: 0.0916 (0.0895) loss: 0.8464 (0.8521) time: 0.1484 data: 0.0784 max mem: 8452 +Train: [32] [6249/6250] eta: 0:00:00 lr: 0.000100 grad: 0.0843 (0.0895) loss: 0.8504 (0.8521) time: 0.1503 data: 0.0784 max mem: 8452 +Train: [32] Total time: 0:17:20 (0.1665 s / it) +Averaged stats: lr: 0.000100 grad: 0.0843 (0.0895) loss: 0.8504 (0.8521) +Eval (hcp-train-subset): [32] [ 0/62] eta: 0:03:57 loss: 0.8949 (0.8949) time: 3.8348 data: 3.7457 max mem: 8452 +Eval (hcp-train-subset): [32] [61/62] eta: 0:00:00 loss: 0.8799 (0.8782) time: 0.1420 data: 0.1207 max mem: 8452 +Eval (hcp-train-subset): [32] Total time: 0:00:14 (0.2325 s / it) +Averaged stats (hcp-train-subset): loss: 0.8799 (0.8782) +Eval (hcp-val): [32] [ 0/62] eta: 0:05:02 loss: 0.8721 (0.8721) time: 4.8763 data: 4.8222 max mem: 8452 +Eval (hcp-val): [32] [61/62] eta: 0:00:00 loss: 0.8768 (0.8778) time: 0.1250 data: 0.1036 max mem: 8452 +Eval (hcp-val): [32] Total time: 0:00:14 (0.2260 s / it) +Averaged stats (hcp-val): loss: 0.8768 (0.8778) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [33] [ 0/6250] eta: 9:48:25 lr: 0.000100 grad: 0.0950 (0.0950) loss: 0.8779 (0.8779) time: 5.6488 data: 5.5511 max mem: 8452 +Train: [33] [ 100/6250] eta: 0:21:45 lr: 0.000100 grad: 0.0780 (0.1188) loss: 0.8692 (0.8644) time: 0.1451 data: 0.0503 max mem: 8452 +Train: [33] [ 200/6250] eta: 0:19:18 lr: 0.000100 grad: 0.0823 (0.1078) loss: 0.8775 (0.8642) time: 0.1121 data: 0.0016 max mem: 8452 +Train: [33] [ 300/6250] eta: 0:18:10 lr: 0.000100 grad: 0.0759 (0.1000) loss: 0.8708 (0.8638) time: 0.1772 data: 0.0920 max mem: 8452 +Train: [33] [ 400/6250] eta: 0:17:13 lr: 0.000100 grad: 0.0816 (0.0952) loss: 0.8553 (0.8630) time: 0.1621 data: 0.0675 max mem: 8452 +Train: [33] [ 500/6250] eta: 0:16:28 lr: 0.000100 grad: 0.0845 (0.0941) loss: 0.8502 (0.8618) time: 0.1206 data: 0.0288 max mem: 8452 +Train: [33] [ 600/6250] eta: 0:15:58 lr: 0.000100 grad: 0.0863 (0.0927) loss: 0.8579 (0.8610) time: 0.1406 data: 0.0457 max mem: 8452 +Train: [33] [ 700/6250] eta: 0:15:31 lr: 0.000100 grad: 0.0844 (0.0915) loss: 0.8598 (0.8603) time: 0.1745 data: 0.0902 max mem: 8452 +Train: [33] [ 800/6250] eta: 0:15:06 lr: 0.000100 grad: 0.0780 (0.0908) loss: 0.8587 (0.8600) time: 0.1462 data: 0.0653 max mem: 8452 +Train: [33] [ 900/6250] eta: 0:14:42 lr: 0.000100 grad: 0.0771 (0.0898) loss: 0.8616 (0.8597) time: 0.1702 data: 0.0876 max mem: 8452 +Train: [33] [1000/6250] eta: 0:14:20 lr: 0.000100 grad: 0.0815 (0.0892) loss: 0.8537 (0.8595) time: 0.1519 data: 0.0814 max mem: 8452 +Train: [33] [1100/6250] eta: 0:14:00 lr: 0.000100 grad: 0.0773 (0.0886) loss: 0.8551 (0.8591) time: 0.1456 data: 0.0630 max mem: 8452 +Train: [33] [1200/6250] eta: 0:13:51 lr: 0.000100 grad: 0.0811 (0.0883) loss: 0.8565 (0.8589) time: 0.1739 data: 0.1061 max mem: 8452 +Train: [33] [1300/6250] eta: 0:13:30 lr: 0.000100 grad: 0.0797 (0.0880) loss: 0.8534 (0.8583) time: 0.1629 data: 0.0939 max mem: 8452 +Train: [33] [1400/6250] eta: 0:13:08 lr: 0.000100 grad: 0.0822 (0.0879) loss: 0.8508 (0.8578) time: 0.1599 data: 0.0826 max mem: 8452 +Train: [33] [1500/6250] eta: 0:12:52 lr: 0.000100 grad: 0.0854 (0.0875) loss: 0.8529 (0.8575) time: 0.1319 data: 0.0452 max mem: 8452 +Train: [33] [1600/6250] eta: 0:12:36 lr: 0.000100 grad: 0.0894 (0.0874) loss: 0.8555 (0.8571) time: 0.1557 data: 0.0623 max mem: 8452 +Train: [33] [1700/6250] eta: 0:12:18 lr: 0.000100 grad: 0.0815 (0.0874) loss: 0.8509 (0.8568) time: 0.1386 data: 0.0564 max mem: 8452 +Train: [33] [1800/6250] eta: 0:12:02 lr: 0.000100 grad: 0.0889 (0.0874) loss: 0.8486 (0.8565) time: 0.1654 data: 0.0901 max mem: 8452 +Train: [33] [1900/6250] eta: 0:11:43 lr: 0.000100 grad: 0.0837 (0.0875) loss: 0.8566 (0.8563) time: 0.1575 data: 0.0744 max mem: 8452 +Train: [33] [2000/6250] eta: 0:11:25 lr: 0.000100 grad: 0.0742 (0.0874) loss: 0.8519 (0.8561) time: 0.1454 data: 0.0639 max mem: 8452 +Train: [33] [2100/6250] eta: 0:11:08 lr: 0.000100 grad: 0.0819 (0.0872) loss: 0.8526 (0.8559) time: 0.1541 data: 0.0627 max mem: 8452 +Train: [33] [2200/6250] eta: 0:10:50 lr: 0.000099 grad: 0.0833 (0.0871) loss: 0.8480 (0.8556) time: 0.1557 data: 0.0824 max mem: 8452 +Train: [33] [2300/6250] eta: 0:10:34 lr: 0.000099 grad: 0.0830 (0.0872) loss: 0.8520 (0.8556) time: 0.1619 data: 0.0861 max mem: 8452 +Train: [33] [2400/6250] eta: 0:10:18 lr: 0.000099 grad: 0.0819 (0.0872) loss: 0.8559 (0.8556) time: 0.1471 data: 0.0722 max mem: 8452 +Train: [33] [2500/6250] eta: 0:10:04 lr: 0.000099 grad: 0.0816 (0.0871) loss: 0.8540 (0.8554) time: 0.1677 data: 0.0922 max mem: 8452 +Train: [33] [2600/6250] eta: 0:09:47 lr: 0.000099 grad: 0.0839 (0.0870) loss: 0.8480 (0.8553) time: 0.1738 data: 0.0949 max mem: 8452 +Train: [33] [2700/6250] eta: 0:09:31 lr: 0.000099 grad: 0.0834 (0.0869) loss: 0.8492 (0.8551) time: 0.1743 data: 0.0841 max mem: 8452 +Train: [33] [2800/6250] eta: 0:09:15 lr: 0.000099 grad: 0.0839 (0.0871) loss: 0.8431 (0.8550) time: 0.1642 data: 0.0739 max mem: 8452 +Train: [33] [2900/6250] eta: 0:09:00 lr: 0.000099 grad: 0.0817 (0.0871) loss: 0.8518 (0.8548) time: 0.1764 data: 0.0949 max mem: 8452 +Train: [33] [3000/6250] eta: 0:08:44 lr: 0.000099 grad: 0.0846 (0.0872) loss: 0.8510 (0.8546) time: 0.1755 data: 0.1098 max mem: 8452 +Train: [33] [3100/6250] eta: 0:08:27 lr: 0.000099 grad: 0.0773 (0.0872) loss: 0.8500 (0.8544) time: 0.1674 data: 0.0894 max mem: 8452 +Train: [33] [3200/6250] eta: 0:08:10 lr: 0.000099 grad: 0.0835 (0.0872) loss: 0.8438 (0.8543) time: 0.1395 data: 0.0673 max mem: 8452 +Train: [33] [3300/6250] eta: 0:07:55 lr: 0.000099 grad: 0.0844 (0.0872) loss: 0.8474 (0.8542) time: 0.2096 data: 0.1409 max mem: 8452 +Train: [33] [3400/6250] eta: 0:07:40 lr: 0.000099 grad: 0.0810 (0.0872) loss: 0.8558 (0.8541) time: 0.1886 data: 0.1137 max mem: 8452 +Train: [33] [3500/6250] eta: 0:07:26 lr: 0.000099 grad: 0.0826 (0.0873) loss: 0.8461 (0.8540) time: 0.2174 data: 0.1563 max mem: 8452 +Train: [33] [3600/6250] eta: 0:07:10 lr: 0.000099 grad: 0.0794 (0.0872) loss: 0.8461 (0.8539) time: 0.1952 data: 0.1135 max mem: 8452 +Train: [33] [3700/6250] eta: 0:06:54 lr: 0.000099 grad: 0.0865 (0.0874) loss: 0.8528 (0.8538) time: 0.1760 data: 0.0938 max mem: 8452 +Train: [33] [3800/6250] eta: 0:06:38 lr: 0.000099 grad: 0.0846 (0.0877) loss: 0.8528 (0.8537) time: 0.1293 data: 0.0410 max mem: 8452 +Train: [33] [3900/6250] eta: 0:06:23 lr: 0.000099 grad: 0.0833 (0.0877) loss: 0.8515 (0.8536) time: 0.1989 data: 0.1281 max mem: 8452 +Train: [33] [4000/6250] eta: 0:06:07 lr: 0.000099 grad: 0.0885 (0.0877) loss: 0.8474 (0.8535) time: 0.1426 data: 0.0567 max mem: 8452 +Train: [33] [4100/6250] eta: 0:05:50 lr: 0.000099 grad: 0.0843 (0.0877) loss: 0.8567 (0.8535) time: 0.1601 data: 0.0834 max mem: 8452 +Train: [33] [4200/6250] eta: 0:05:34 lr: 0.000099 grad: 0.0896 (0.0878) loss: 0.8517 (0.8535) time: 0.1367 data: 0.0583 max mem: 8452 +Train: [33] [4300/6250] eta: 0:05:17 lr: 0.000099 grad: 0.0863 (0.0878) loss: 0.8525 (0.8535) time: 0.1538 data: 0.0667 max mem: 8452 +Train: [33] [4400/6250] eta: 0:05:01 lr: 0.000099 grad: 0.0932 (0.0879) loss: 0.8585 (0.8535) time: 0.1838 data: 0.1085 max mem: 8452 +Train: [33] [4500/6250] eta: 0:04:45 lr: 0.000099 grad: 0.0879 (0.0879) loss: 0.8468 (0.8534) time: 0.1823 data: 0.1049 max mem: 8452 +Train: [33] [4600/6250] eta: 0:04:28 lr: 0.000099 grad: 0.0945 (0.0880) loss: 0.8473 (0.8534) time: 0.1929 data: 0.1108 max mem: 8452 +Train: [33] [4700/6250] eta: 0:04:12 lr: 0.000099 grad: 0.0833 (0.0880) loss: 0.8550 (0.8534) time: 0.1618 data: 0.0742 max mem: 8452 +Train: [33] [4800/6250] eta: 0:03:56 lr: 0.000099 grad: 0.0872 (0.0880) loss: 0.8486 (0.8534) time: 0.1679 data: 0.0956 max mem: 8452 +Train: [33] [4900/6250] eta: 0:03:40 lr: 0.000099 grad: 0.0854 (0.0879) loss: 0.8558 (0.8535) time: 0.1572 data: 0.0775 max mem: 8452 +Train: [33] [5000/6250] eta: 0:03:23 lr: 0.000099 grad: 0.0796 (0.0879) loss: 0.8547 (0.8535) time: 0.1521 data: 0.0717 max mem: 8452 +Train: [33] [5100/6250] eta: 0:03:07 lr: 0.000099 grad: 0.0846 (0.0879) loss: 0.8565 (0.8536) time: 0.1578 data: 0.0692 max mem: 8452 +Train: [33] [5200/6250] eta: 0:02:50 lr: 0.000099 grad: 0.0824 (0.0878) loss: 0.8556 (0.8535) time: 0.1719 data: 0.0922 max mem: 8452 +Train: [33] [5300/6250] eta: 0:02:34 lr: 0.000099 grad: 0.0801 (0.0878) loss: 0.8525 (0.8535) time: 0.1580 data: 0.0713 max mem: 8452 +Train: [33] [5400/6250] eta: 0:02:18 lr: 0.000099 grad: 0.0814 (0.0878) loss: 0.8580 (0.8536) time: 0.1551 data: 0.0834 max mem: 8452 +Train: [33] [5500/6250] eta: 0:02:01 lr: 0.000099 grad: 0.0863 (0.0877) loss: 0.8557 (0.8536) time: 0.1628 data: 0.0918 max mem: 8452 +Train: [33] [5600/6250] eta: 0:01:45 lr: 0.000099 grad: 0.0827 (0.0877) loss: 0.8502 (0.8537) time: 0.1791 data: 0.0882 max mem: 8452 +Train: [33] [5700/6250] eta: 0:01:29 lr: 0.000099 grad: 0.0819 (0.0877) loss: 0.8594 (0.8537) time: 0.1247 data: 0.0394 max mem: 8452 +Train: [33] [5800/6250] eta: 0:01:12 lr: 0.000099 grad: 0.0834 (0.0877) loss: 0.8546 (0.8537) time: 0.1452 data: 0.0577 max mem: 8452 +Train: [33] [5900/6250] eta: 0:00:56 lr: 0.000098 grad: 0.0822 (0.0876) loss: 0.8555 (0.8537) time: 0.1940 data: 0.1226 max mem: 8452 +Train: [33] [6000/6250] eta: 0:00:40 lr: 0.000098 grad: 0.0826 (0.0876) loss: 0.8540 (0.8537) time: 0.1801 data: 0.1035 max mem: 8452 +Train: [33] [6100/6250] eta: 0:00:24 lr: 0.000098 grad: 0.0830 (0.0877) loss: 0.8581 (0.8536) time: 0.1114 data: 0.0090 max mem: 8452 +Train: [33] [6200/6250] eta: 0:00:08 lr: 0.000098 grad: 0.0867 (0.0877) loss: 0.8470 (0.8536) time: 0.1900 data: 0.1118 max mem: 8452 +Train: [33] [6249/6250] eta: 0:00:00 lr: 0.000098 grad: 0.0889 (0.0877) loss: 0.8594 (0.8536) time: 0.1536 data: 0.0638 max mem: 8452 +Train: [33] Total time: 0:17:02 (0.1637 s / it) +Averaged stats: lr: 0.000098 grad: 0.0889 (0.0877) loss: 0.8594 (0.8536) +Eval (hcp-train-subset): [33] [ 0/62] eta: 0:05:59 loss: 0.8880 (0.8880) time: 5.8030 data: 5.7762 max mem: 8452 +Eval (hcp-train-subset): [33] [61/62] eta: 0:00:00 loss: 0.8763 (0.8786) time: 0.1547 data: 0.1335 max mem: 8452 +Eval (hcp-train-subset): [33] Total time: 0:00:14 (0.2354 s / it) +Averaged stats (hcp-train-subset): loss: 0.8763 (0.8786) +Eval (hcp-val): [33] [ 0/62] eta: 0:05:15 loss: 0.8776 (0.8776) time: 5.0858 data: 5.0576 max mem: 8452 +Eval (hcp-val): [33] [61/62] eta: 0:00:00 loss: 0.8759 (0.8784) time: 0.1503 data: 0.1280 max mem: 8452 +Eval (hcp-val): [33] Total time: 0:00:14 (0.2330 s / it) +Averaged stats (hcp-val): loss: 0.8759 (0.8784) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [34] [ 0/6250] eta: 11:12:06 lr: 0.000098 grad: 0.0787 (0.0787) loss: 0.8838 (0.8838) time: 6.4522 data: 6.3283 max mem: 8452 +Train: [34] [ 100/6250] eta: 0:23:13 lr: 0.000098 grad: 0.1069 (0.1266) loss: 0.8538 (0.8608) time: 0.1986 data: 0.0989 max mem: 8452 +Train: [34] [ 200/6250] eta: 0:19:44 lr: 0.000098 grad: 0.0814 (0.1127) loss: 0.8576 (0.8586) time: 0.1664 data: 0.0882 max mem: 8452 +Train: [34] [ 300/6250] eta: 0:18:11 lr: 0.000098 grad: 0.0851 (0.1063) loss: 0.8599 (0.8574) time: 0.1540 data: 0.0535 max mem: 8452 +Train: [34] [ 400/6250] eta: 0:17:17 lr: 0.000098 grad: 0.0797 (0.1001) loss: 0.8648 (0.8586) time: 0.0982 data: 0.0003 max mem: 8452 +Train: [34] [ 500/6250] eta: 0:16:33 lr: 0.000098 grad: 0.0845 (0.0966) loss: 0.8650 (0.8591) time: 0.1562 data: 0.0648 max mem: 8452 +Train: [34] [ 600/6250] eta: 0:15:55 lr: 0.000098 grad: 0.0821 (0.0945) loss: 0.8602 (0.8596) time: 0.1384 data: 0.0477 max mem: 8452 +Train: [34] [ 700/6250] eta: 0:15:23 lr: 0.000098 grad: 0.0837 (0.0931) loss: 0.8631 (0.8595) time: 0.1306 data: 0.0440 max mem: 8452 +Train: [34] [ 800/6250] eta: 0:14:53 lr: 0.000098 grad: 0.0816 (0.0920) loss: 0.8571 (0.8593) time: 0.1184 data: 0.0311 max mem: 8452 +Train: [34] [ 900/6250] eta: 0:14:40 lr: 0.000098 grad: 0.0813 (0.0911) loss: 0.8631 (0.8591) time: 0.1944 data: 0.1135 max mem: 8452 +Train: [34] [1000/6250] eta: 0:14:15 lr: 0.000098 grad: 0.0824 (0.0904) loss: 0.8593 (0.8591) time: 0.1469 data: 0.0713 max mem: 8452 +Train: [34] [1100/6250] eta: 0:14:04 lr: 0.000098 grad: 0.0825 (0.0898) loss: 0.8614 (0.8590) time: 0.2279 data: 0.0999 max mem: 8452 +Train: [34] [1200/6250] eta: 0:13:50 lr: 0.000098 grad: 0.0834 (0.0892) loss: 0.8561 (0.8589) time: 0.1645 data: 0.1002 max mem: 8452 +Train: [34] [1300/6250] eta: 0:13:41 lr: 0.000098 grad: 0.0868 (0.0889) loss: 0.8524 (0.8586) time: 0.1757 data: 0.1066 max mem: 8452 +Train: [34] [1400/6250] eta: 0:13:23 lr: 0.000098 grad: 0.0824 (0.0886) loss: 0.8585 (0.8582) time: 0.1460 data: 0.0734 max mem: 8452 +Train: [34] [1500/6250] eta: 0:13:10 lr: 0.000098 grad: 0.0871 (0.0884) loss: 0.8593 (0.8581) time: 0.2039 data: 0.1244 max mem: 8452 +Train: [34] [1600/6250] eta: 0:12:54 lr: 0.000098 grad: 0.0837 (0.0883) loss: 0.8509 (0.8579) time: 0.1558 data: 0.0627 max mem: 8452 +Train: [34] [1700/6250] eta: 0:12:38 lr: 0.000098 grad: 0.0957 (0.0883) loss: 0.8507 (0.8577) time: 0.1650 data: 0.0796 max mem: 8452 +Train: [34] [1800/6250] eta: 0:12:21 lr: 0.000098 grad: 0.0887 (0.0884) loss: 0.8462 (0.8573) time: 0.1745 data: 0.0933 max mem: 8452 +Train: [34] [1900/6250] eta: 0:12:02 lr: 0.000098 grad: 0.0863 (0.0885) loss: 0.8578 (0.8570) time: 0.1634 data: 0.0702 max mem: 8452 +Train: [34] [2000/6250] eta: 0:11:43 lr: 0.000098 grad: 0.0839 (0.0885) loss: 0.8491 (0.8566) time: 0.1429 data: 0.0451 max mem: 8452 +Train: [34] [2100/6250] eta: 0:11:26 lr: 0.000098 grad: 0.0885 (0.0886) loss: 0.8466 (0.8564) time: 0.1671 data: 0.0776 max mem: 8452 +Train: [34] [2200/6250] eta: 0:11:07 lr: 0.000098 grad: 0.0833 (0.0886) loss: 0.8565 (0.8561) time: 0.1480 data: 0.0725 max mem: 8452 +Train: [34] [2300/6250] eta: 0:10:50 lr: 0.000098 grad: 0.0823 (0.0886) loss: 0.8529 (0.8559) time: 0.1765 data: 0.0921 max mem: 8452 +Train: [34] [2400/6250] eta: 0:10:34 lr: 0.000098 grad: 0.0898 (0.0885) loss: 0.8462 (0.8557) time: 0.1606 data: 0.0809 max mem: 8452 +Train: [34] [2500/6250] eta: 0:10:17 lr: 0.000098 grad: 0.0841 (0.0886) loss: 0.8545 (0.8555) time: 0.1772 data: 0.1005 max mem: 8452 +Train: [34] [2600/6250] eta: 0:10:01 lr: 0.000098 grad: 0.0808 (0.0885) loss: 0.8493 (0.8553) time: 0.1521 data: 0.0711 max mem: 8452 +Train: [34] [2700/6250] eta: 0:09:47 lr: 0.000098 grad: 0.0892 (0.0885) loss: 0.8430 (0.8551) time: 0.1994 data: 0.1046 max mem: 8452 +Train: [34] [2800/6250] eta: 0:09:29 lr: 0.000098 grad: 0.0873 (0.0885) loss: 0.8496 (0.8550) time: 0.1662 data: 0.0970 max mem: 8452 +Train: [34] [2900/6250] eta: 0:09:12 lr: 0.000098 grad: 0.0812 (0.0884) loss: 0.8608 (0.8551) time: 0.1599 data: 0.0818 max mem: 8452 +Train: [34] [3000/6250] eta: 0:08:55 lr: 0.000098 grad: 0.0858 (0.0884) loss: 0.8513 (0.8549) time: 0.1563 data: 0.0757 max mem: 8452 +Train: [34] [3100/6250] eta: 0:08:38 lr: 0.000098 grad: 0.0908 (0.0884) loss: 0.8530 (0.8549) time: 0.1928 data: 0.1126 max mem: 8452 +Train: [34] [3200/6250] eta: 0:08:23 lr: 0.000098 grad: 0.0811 (0.0883) loss: 0.8570 (0.8549) time: 0.2729 data: 0.1962 max mem: 8452 +Train: [34] [3300/6250] eta: 0:08:05 lr: 0.000097 grad: 0.0843 (0.0882) loss: 0.8569 (0.8548) time: 0.1351 data: 0.0536 max mem: 8452 +Train: [34] [3400/6250] eta: 0:07:47 lr: 0.000097 grad: 0.0882 (0.0881) loss: 0.8550 (0.8548) time: 0.1360 data: 0.0560 max mem: 8452 +Train: [34] [3500/6250] eta: 0:07:31 lr: 0.000097 grad: 0.0842 (0.0881) loss: 0.8528 (0.8548) time: 0.1540 data: 0.0767 max mem: 8452 +Train: [34] [3600/6250] eta: 0:07:14 lr: 0.000097 grad: 0.0839 (0.0880) loss: 0.8541 (0.8548) time: 0.1558 data: 0.0743 max mem: 8452 +Train: [34] [3700/6250] eta: 0:06:59 lr: 0.000097 grad: 0.0782 (0.0879) loss: 0.8528 (0.8548) time: 0.1837 data: 0.0945 max mem: 8452 +Train: [34] [3800/6250] eta: 0:06:42 lr: 0.000097 grad: 0.0790 (0.0877) loss: 0.8576 (0.8549) time: 0.1579 data: 0.0788 max mem: 8452 +Train: [34] [3900/6250] eta: 0:06:26 lr: 0.000097 grad: 0.0851 (0.0877) loss: 0.8502 (0.8550) time: 0.1688 data: 0.0949 max mem: 8452 +Train: [34] [4000/6250] eta: 0:06:09 lr: 0.000097 grad: 0.0898 (0.0877) loss: 0.8478 (0.8549) time: 0.1706 data: 0.0854 max mem: 8452 +Train: [34] [4100/6250] eta: 0:05:52 lr: 0.000097 grad: 0.0920 (0.0878) loss: 0.8517 (0.8549) time: 0.1443 data: 0.0599 max mem: 8452 +Train: [34] [4200/6250] eta: 0:05:36 lr: 0.000097 grad: 0.0835 (0.0878) loss: 0.8533 (0.8548) time: 0.1457 data: 0.0621 max mem: 8452 +Train: [34] [4300/6250] eta: 0:05:19 lr: 0.000097 grad: 0.0848 (0.0878) loss: 0.8485 (0.8547) time: 0.1480 data: 0.0653 max mem: 8452 +Train: [34] [4400/6250] eta: 0:05:02 lr: 0.000097 grad: 0.0853 (0.0879) loss: 0.8518 (0.8546) time: 0.1928 data: 0.1219 max mem: 8452 +Train: [34] [4500/6250] eta: 0:04:46 lr: 0.000097 grad: 0.0878 (0.0879) loss: 0.8518 (0.8545) time: 0.1632 data: 0.0911 max mem: 8452 +Train: [34] [4600/6250] eta: 0:04:30 lr: 0.000097 grad: 0.0801 (0.0879) loss: 0.8476 (0.8544) time: 0.1406 data: 0.0550 max mem: 8452 +Train: [34] [4700/6250] eta: 0:04:13 lr: 0.000097 grad: 0.0854 (0.0879) loss: 0.8463 (0.8543) time: 0.1691 data: 0.0899 max mem: 8452 +Train: [34] [4800/6250] eta: 0:03:57 lr: 0.000097 grad: 0.0888 (0.0879) loss: 0.8471 (0.8542) time: 0.1507 data: 0.0637 max mem: 8452 +Train: [34] [4900/6250] eta: 0:03:40 lr: 0.000097 grad: 0.0799 (0.0879) loss: 0.8471 (0.8540) time: 0.1624 data: 0.0825 max mem: 8452 +Train: [34] [5000/6250] eta: 0:03:24 lr: 0.000097 grad: 0.0860 (0.0878) loss: 0.8537 (0.8540) time: 0.1421 data: 0.0494 max mem: 8452 +Train: [34] [5100/6250] eta: 0:03:07 lr: 0.000097 grad: 0.0855 (0.0879) loss: 0.8550 (0.8540) time: 0.1431 data: 0.0503 max mem: 8452 +Train: [34] [5200/6250] eta: 0:02:50 lr: 0.000097 grad: 0.0890 (0.0878) loss: 0.8505 (0.8539) time: 0.1449 data: 0.0694 max mem: 8452 +Train: [34] [5300/6250] eta: 0:02:34 lr: 0.000097 grad: 0.0872 (0.0878) loss: 0.8508 (0.8538) time: 0.1686 data: 0.0888 max mem: 8452 +Train: [34] [5400/6250] eta: 0:02:18 lr: 0.000097 grad: 0.0854 (0.0878) loss: 0.8508 (0.8538) time: 0.1513 data: 0.0715 max mem: 8452 +Train: [34] [5500/6250] eta: 0:02:01 lr: 0.000097 grad: 0.0863 (0.0878) loss: 0.8387 (0.8537) time: 0.1610 data: 0.0884 max mem: 8452 +Train: [34] [5600/6250] eta: 0:01:45 lr: 0.000097 grad: 0.0985 (0.0879) loss: 0.8506 (0.8536) time: 0.1601 data: 0.0748 max mem: 8452 +Train: [34] [5700/6250] eta: 0:01:29 lr: 0.000097 grad: 0.0908 (0.0879) loss: 0.8476 (0.8535) time: 0.1431 data: 0.0625 max mem: 8452 +Train: [34] [5800/6250] eta: 0:01:12 lr: 0.000097 grad: 0.0943 (0.0879) loss: 0.8563 (0.8535) time: 0.1661 data: 0.0854 max mem: 8452 +Train: [34] [5900/6250] eta: 0:00:56 lr: 0.000097 grad: 0.0891 (0.0880) loss: 0.8421 (0.8534) time: 0.1701 data: 0.0990 max mem: 8452 +Train: [34] [6000/6250] eta: 0:00:40 lr: 0.000097 grad: 0.0807 (0.0880) loss: 0.8487 (0.8533) time: 0.1658 data: 0.0908 max mem: 8452 +Train: [34] [6100/6250] eta: 0:00:24 lr: 0.000097 grad: 0.0823 (0.0880) loss: 0.8537 (0.8533) time: 0.1541 data: 0.0746 max mem: 8452 +Train: [34] [6200/6250] eta: 0:00:08 lr: 0.000097 grad: 0.0837 (0.0880) loss: 0.8548 (0.8532) time: 0.1434 data: 0.0578 max mem: 8452 +Train: [34] [6249/6250] eta: 0:00:00 lr: 0.000097 grad: 0.0868 (0.0880) loss: 0.8470 (0.8532) time: 0.1582 data: 0.0817 max mem: 8452 +Train: [34] Total time: 0:16:54 (0.1623 s / it) +Averaged stats: lr: 0.000097 grad: 0.0868 (0.0880) loss: 0.8470 (0.8532) +Eval (hcp-train-subset): [34] [ 0/62] eta: 0:05:51 loss: 0.8884 (0.8884) time: 5.6616 data: 5.6210 max mem: 8452 +Eval (hcp-train-subset): [34] [61/62] eta: 0:00:00 loss: 0.8784 (0.8801) time: 0.1438 data: 0.1226 max mem: 8452 +Eval (hcp-train-subset): [34] Total time: 0:00:14 (0.2325 s / it) +Averaged stats (hcp-train-subset): loss: 0.8784 (0.8801) +Making plots (hcp-train-subset): example=16 +Eval (hcp-val): [34] [ 0/62] eta: 0:05:55 loss: 0.8773 (0.8773) time: 5.7329 data: 5.7054 max mem: 8452 +Eval (hcp-val): [34] [61/62] eta: 0:00:00 loss: 0.8766 (0.8777) time: 0.1484 data: 0.1258 max mem: 8452 +Eval (hcp-val): [34] Total time: 0:00:15 (0.2434 s / it) +Averaged stats (hcp-val): loss: 0.8766 (0.8777) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [35] [ 0/6250] eta: 11:37:00 lr: 0.000097 grad: 0.2334 (0.2334) loss: 0.8939 (0.8939) time: 6.6912 data: 6.5724 max mem: 8452 +Train: [35] [ 100/6250] eta: 0:25:17 lr: 0.000097 grad: 0.1002 (0.1282) loss: 0.8663 (0.8626) time: 0.2257 data: 0.1296 max mem: 8452 +Train: [35] [ 200/6250] eta: 0:21:15 lr: 0.000097 grad: 0.0871 (0.1116) loss: 0.8660 (0.8614) time: 0.1926 data: 0.0918 max mem: 8452 +Train: [35] [ 300/6250] eta: 0:19:45 lr: 0.000097 grad: 0.0952 (0.1090) loss: 0.8584 (0.8611) time: 0.1699 data: 0.0635 max mem: 8452 +Train: [35] [ 400/6250] eta: 0:18:47 lr: 0.000097 grad: 0.0822 (0.1044) loss: 0.8620 (0.8612) time: 0.1767 data: 0.0853 max mem: 8452 +Train: [35] [ 500/6250] eta: 0:18:08 lr: 0.000097 grad: 0.0776 (0.1000) loss: 0.8666 (0.8616) time: 0.1720 data: 0.0838 max mem: 8452 +Train: [35] [ 600/6250] eta: 0:17:31 lr: 0.000097 grad: 0.0767 (0.0968) loss: 0.8638 (0.8619) time: 0.1735 data: 0.0814 max mem: 8452 +Train: [35] [ 700/6250] eta: 0:17:00 lr: 0.000096 grad: 0.0817 (0.0953) loss: 0.8593 (0.8617) time: 0.1218 data: 0.0307 max mem: 8452 +Train: [35] [ 800/6250] eta: 0:16:33 lr: 0.000096 grad: 0.0784 (0.0933) loss: 0.8589 (0.8616) time: 0.2033 data: 0.1107 max mem: 8452 +Train: [35] [ 900/6250] eta: 0:16:12 lr: 0.000096 grad: 0.0792 (0.0921) loss: 0.8562 (0.8614) time: 0.1907 data: 0.1086 max mem: 8452 +Train: [35] [1000/6250] eta: 0:15:39 lr: 0.000096 grad: 0.0849 (0.0912) loss: 0.8518 (0.8609) time: 0.1679 data: 0.0879 max mem: 8452 +Train: [35] [1100/6250] eta: 0:15:11 lr: 0.000096 grad: 0.0828 (0.0904) loss: 0.8581 (0.8605) time: 0.1722 data: 0.0993 max mem: 8452 +Train: [35] [1200/6250] eta: 0:14:54 lr: 0.000096 grad: 0.0793 (0.0896) loss: 0.8591 (0.8601) time: 0.1599 data: 0.0819 max mem: 8452 +Train: [35] [1300/6250] eta: 0:14:38 lr: 0.000096 grad: 0.0778 (0.0889) loss: 0.8561 (0.8600) time: 0.1572 data: 0.0791 max mem: 8452 +Train: [35] [1400/6250] eta: 0:14:14 lr: 0.000096 grad: 0.0776 (0.0887) loss: 0.8511 (0.8597) time: 0.1730 data: 0.0910 max mem: 8452 +Train: [35] [1500/6250] eta: 0:13:49 lr: 0.000096 grad: 0.0834 (0.0885) loss: 0.8483 (0.8591) time: 0.1653 data: 0.0818 max mem: 8452 +Train: [35] [1600/6250] eta: 0:13:28 lr: 0.000096 grad: 0.0856 (0.0883) loss: 0.8586 (0.8588) time: 0.1686 data: 0.0857 max mem: 8452 +Train: [35] [1700/6250] eta: 0:13:08 lr: 0.000096 grad: 0.0812 (0.0882) loss: 0.8522 (0.8583) time: 0.1651 data: 0.0811 max mem: 8452 +Train: [35] [1800/6250] eta: 0:12:49 lr: 0.000096 grad: 0.0843 (0.0881) loss: 0.8553 (0.8579) time: 0.1628 data: 0.0829 max mem: 8452 +Train: [35] [1900/6250] eta: 0:12:30 lr: 0.000096 grad: 0.0814 (0.0879) loss: 0.8574 (0.8576) time: 0.1677 data: 0.0792 max mem: 8452 +Train: [35] [2000/6250] eta: 0:12:10 lr: 0.000096 grad: 0.0894 (0.0881) loss: 0.8446 (0.8571) time: 0.1590 data: 0.0683 max mem: 8452 +Train: [35] [2100/6250] eta: 0:11:50 lr: 0.000096 grad: 0.0860 (0.0882) loss: 0.8499 (0.8568) time: 0.1603 data: 0.0817 max mem: 8452 +Train: [35] [2200/6250] eta: 0:11:30 lr: 0.000096 grad: 0.0828 (0.0883) loss: 0.8470 (0.8565) time: 0.1618 data: 0.0626 max mem: 8452 +Train: [35] [2300/6250] eta: 0:11:09 lr: 0.000096 grad: 0.0836 (0.0882) loss: 0.8475 (0.8563) time: 0.1363 data: 0.0539 max mem: 8452 +Train: [35] [2400/6250] eta: 0:10:50 lr: 0.000096 grad: 0.0866 (0.0881) loss: 0.8462 (0.8560) time: 0.1269 data: 0.0452 max mem: 8452 +Train: [35] [2500/6250] eta: 0:10:31 lr: 0.000096 grad: 0.0797 (0.0880) loss: 0.8547 (0.8558) time: 0.1732 data: 0.0888 max mem: 8452 +Train: [35] [2600/6250] eta: 0:10:12 lr: 0.000096 grad: 0.0829 (0.0880) loss: 0.8499 (0.8556) time: 0.1535 data: 0.0751 max mem: 8452 +Train: [35] [2700/6250] eta: 0:09:55 lr: 0.000096 grad: 0.0874 (0.0880) loss: 0.8478 (0.8553) time: 0.1891 data: 0.0980 max mem: 8452 +Train: [35] [2800/6250] eta: 0:09:37 lr: 0.000096 grad: 0.0822 (0.0880) loss: 0.8560 (0.8552) time: 0.1544 data: 0.0822 max mem: 8452 +Train: [35] [2900/6250] eta: 0:09:20 lr: 0.000096 grad: 0.0821 (0.0880) loss: 0.8539 (0.8550) time: 0.1758 data: 0.0787 max mem: 8452 +Train: [35] [3000/6250] eta: 0:09:03 lr: 0.000096 grad: 0.0865 (0.0880) loss: 0.8452 (0.8548) time: 0.1587 data: 0.0878 max mem: 8452 +Train: [35] [3100/6250] eta: 0:08:44 lr: 0.000096 grad: 0.0888 (0.0881) loss: 0.8504 (0.8546) time: 0.1561 data: 0.0646 max mem: 8452 +Train: [35] [3200/6250] eta: 0:08:26 lr: 0.000096 grad: 0.0785 (0.0882) loss: 0.8616 (0.8544) time: 0.1545 data: 0.0757 max mem: 8452 +Train: [35] [3300/6250] eta: 0:08:10 lr: 0.000096 grad: 0.0890 (0.0882) loss: 0.8488 (0.8543) time: 0.2094 data: 0.1430 max mem: 8452 +Train: [35] [3400/6250] eta: 0:07:54 lr: 0.000096 grad: 0.0907 (0.0883) loss: 0.8485 (0.8540) time: 0.1640 data: 0.0892 max mem: 8452 +Train: [35] [3500/6250] eta: 0:07:37 lr: 0.000096 grad: 0.0860 (0.0884) loss: 0.8533 (0.8537) time: 0.1522 data: 0.0711 max mem: 8452 +Train: [35] [3600/6250] eta: 0:07:21 lr: 0.000096 grad: 0.0861 (0.0884) loss: 0.8490 (0.8536) time: 0.1720 data: 0.0990 max mem: 8452 +Train: [35] [3700/6250] eta: 0:07:03 lr: 0.000096 grad: 0.0832 (0.0884) loss: 0.8537 (0.8534) time: 0.1581 data: 0.0805 max mem: 8452 +Train: [35] [3800/6250] eta: 0:06:46 lr: 0.000096 grad: 0.0853 (0.0884) loss: 0.8449 (0.8533) time: 0.1442 data: 0.0603 max mem: 8452 +Train: [35] [3900/6250] eta: 0:06:29 lr: 0.000096 grad: 0.0859 (0.0884) loss: 0.8548 (0.8532) time: 0.1604 data: 0.0737 max mem: 8452 +Train: [35] [4000/6250] eta: 0:06:12 lr: 0.000096 grad: 0.0867 (0.0885) loss: 0.8472 (0.8531) time: 0.1995 data: 0.1218 max mem: 8452 +Train: [35] [4100/6250] eta: 0:05:54 lr: 0.000096 grad: 0.0874 (0.0885) loss: 0.8523 (0.8529) time: 0.1381 data: 0.0500 max mem: 8452 +Train: [35] [4200/6250] eta: 0:05:37 lr: 0.000096 grad: 0.0933 (0.0886) loss: 0.8447 (0.8528) time: 0.1321 data: 0.0551 max mem: 8452 +Train: [35] [4300/6250] eta: 0:05:20 lr: 0.000095 grad: 0.0877 (0.0887) loss: 0.8445 (0.8526) time: 0.1562 data: 0.0746 max mem: 8452 +Train: [35] [4400/6250] eta: 0:05:03 lr: 0.000095 grad: 0.0892 (0.0889) loss: 0.8496 (0.8524) time: 0.1531 data: 0.0745 max mem: 8452 +Train: [35] [4500/6250] eta: 0:04:47 lr: 0.000095 grad: 0.0915 (0.0890) loss: 0.8468 (0.8522) time: 0.1634 data: 0.0871 max mem: 8452 +Train: [35] [4600/6250] eta: 0:04:30 lr: 0.000095 grad: 0.0870 (0.0892) loss: 0.8380 (0.8519) time: 0.1239 data: 0.0361 max mem: 8452 +Train: [35] [4700/6250] eta: 0:04:14 lr: 0.000095 grad: 0.0867 (0.0892) loss: 0.8377 (0.8517) time: 0.1626 data: 0.0808 max mem: 8452 +Train: [35] [4800/6250] eta: 0:03:58 lr: 0.000095 grad: 0.0902 (0.0893) loss: 0.8412 (0.8516) time: 0.1356 data: 0.0688 max mem: 8452 +Train: [35] [4900/6250] eta: 0:03:41 lr: 0.000095 grad: 0.0913 (0.0894) loss: 0.8439 (0.8514) time: 0.1483 data: 0.0695 max mem: 8452 +Train: [35] [5000/6250] eta: 0:03:24 lr: 0.000095 grad: 0.0920 (0.0895) loss: 0.8468 (0.8513) time: 0.1439 data: 0.0679 max mem: 8452 +Train: [35] [5100/6250] eta: 0:03:08 lr: 0.000095 grad: 0.0905 (0.0895) loss: 0.8403 (0.8512) time: 0.1494 data: 0.0659 max mem: 8452 +Train: [35] [5200/6250] eta: 0:02:51 lr: 0.000095 grad: 0.0798 (0.0895) loss: 0.8491 (0.8511) time: 0.1606 data: 0.0751 max mem: 8452 +Train: [35] [5300/6250] eta: 0:02:35 lr: 0.000095 grad: 0.0872 (0.0896) loss: 0.8418 (0.8510) time: 0.1645 data: 0.0811 max mem: 8452 +Train: [35] [5400/6250] eta: 0:02:19 lr: 0.000095 grad: 0.0894 (0.0896) loss: 0.8464 (0.8509) time: 0.2247 data: 0.1474 max mem: 8452 +Train: [35] [5500/6250] eta: 0:02:02 lr: 0.000095 grad: 0.0909 (0.0896) loss: 0.8514 (0.8508) time: 0.1655 data: 0.0694 max mem: 8452 +Train: [35] [5600/6250] eta: 0:01:46 lr: 0.000095 grad: 0.0878 (0.0897) loss: 0.8444 (0.8507) time: 0.1428 data: 0.0511 max mem: 8452 +Train: [35] [5700/6250] eta: 0:01:30 lr: 0.000095 grad: 0.0911 (0.0898) loss: 0.8461 (0.8507) time: 0.1247 data: 0.0230 max mem: 8452 +Train: [35] [5800/6250] eta: 0:01:13 lr: 0.000095 grad: 0.0845 (0.0898) loss: 0.8494 (0.8506) time: 0.2945 data: 0.1907 max mem: 8452 +Train: [35] [5900/6250] eta: 0:00:57 lr: 0.000095 grad: 0.0842 (0.0898) loss: 0.8455 (0.8506) time: 0.1585 data: 0.0747 max mem: 8452 +Train: [35] [6000/6250] eta: 0:00:40 lr: 0.000095 grad: 0.0911 (0.0899) loss: 0.8443 (0.8505) time: 0.1449 data: 0.0527 max mem: 8452 +Train: [35] [6100/6250] eta: 0:00:24 lr: 0.000095 grad: 0.0925 (0.0899) loss: 0.8487 (0.8505) time: 0.1667 data: 0.0852 max mem: 8452 +Train: [35] [6200/6250] eta: 0:00:08 lr: 0.000095 grad: 0.0920 (0.0900) loss: 0.8461 (0.8504) time: 0.1812 data: 0.0999 max mem: 8452 +Train: [35] [6249/6250] eta: 0:00:00 lr: 0.000095 grad: 0.0905 (0.0900) loss: 0.8441 (0.8503) time: 0.1528 data: 0.0677 max mem: 8452 +Train: [35] Total time: 0:17:08 (0.1646 s / it) +Averaged stats: lr: 0.000095 grad: 0.0905 (0.0900) loss: 0.8441 (0.8503) +Eval (hcp-train-subset): [35] [ 0/62] eta: 0:05:35 loss: 0.8897 (0.8897) time: 5.4178 data: 5.3888 max mem: 8452 +Eval (hcp-train-subset): [35] [61/62] eta: 0:00:00 loss: 0.8799 (0.8799) time: 0.1330 data: 0.1120 max mem: 8452 +Eval (hcp-train-subset): [35] Total time: 0:00:14 (0.2367 s / it) +Averaged stats (hcp-train-subset): loss: 0.8799 (0.8799) +Eval (hcp-val): [35] [ 0/62] eta: 0:03:46 loss: 0.8749 (0.8749) time: 3.6538 data: 3.5129 max mem: 8452 +Eval (hcp-val): [35] [61/62] eta: 0:00:00 loss: 0.8768 (0.8781) time: 0.1432 data: 0.1220 max mem: 8452 +Eval (hcp-val): [35] Total time: 0:00:14 (0.2335 s / it) +Averaged stats (hcp-val): loss: 0.8768 (0.8781) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [36] [ 0/6250] eta: 10:19:38 lr: 0.000095 grad: 0.1134 (0.1134) loss: 0.9019 (0.9019) time: 5.9485 data: 5.7943 max mem: 8452 +Train: [36] [ 100/6250] eta: 0:22:59 lr: 0.000095 grad: 0.1013 (0.1387) loss: 0.8575 (0.8582) time: 0.2017 data: 0.1016 max mem: 8452 +Train: [36] [ 200/6250] eta: 0:19:28 lr: 0.000095 grad: 0.0942 (0.1209) loss: 0.8552 (0.8545) time: 0.1744 data: 0.0838 max mem: 8452 +Train: [36] [ 300/6250] eta: 0:18:32 lr: 0.000095 grad: 0.0874 (0.1124) loss: 0.8479 (0.8543) time: 0.1582 data: 0.0638 max mem: 8452 +Train: [36] [ 400/6250] eta: 0:17:42 lr: 0.000095 grad: 0.0826 (0.1078) loss: 0.8600 (0.8548) time: 0.1778 data: 0.0865 max mem: 8452 +Train: [36] [ 500/6250] eta: 0:17:01 lr: 0.000095 grad: 0.0839 (0.1042) loss: 0.8606 (0.8549) time: 0.1428 data: 0.0611 max mem: 8452 +Train: [36] [ 600/6250] eta: 0:16:28 lr: 0.000095 grad: 0.0905 (0.1018) loss: 0.8473 (0.8545) time: 0.1663 data: 0.0737 max mem: 8452 +Train: [36] [ 700/6250] eta: 0:16:00 lr: 0.000095 grad: 0.0880 (0.0996) loss: 0.8552 (0.8545) time: 0.1910 data: 0.0990 max mem: 8452 +Train: [36] [ 800/6250] eta: 0:15:35 lr: 0.000095 grad: 0.0840 (0.0982) loss: 0.8585 (0.8542) time: 0.1787 data: 0.0995 max mem: 8452 +Train: [36] [ 900/6250] eta: 0:15:15 lr: 0.000095 grad: 0.0899 (0.0971) loss: 0.8498 (0.8543) time: 0.1763 data: 0.0857 max mem: 8452 +Train: [36] [1000/6250] eta: 0:14:51 lr: 0.000095 grad: 0.0857 (0.0962) loss: 0.8525 (0.8541) time: 0.1588 data: 0.0749 max mem: 8452 +Train: [36] [1100/6250] eta: 0:14:43 lr: 0.000095 grad: 0.0914 (0.0958) loss: 0.8450 (0.8532) time: 0.2933 data: 0.2046 max mem: 8452 +Train: [36] [1200/6250] eta: 0:14:16 lr: 0.000095 grad: 0.0932 (0.0955) loss: 0.8447 (0.8526) time: 0.1568 data: 0.0632 max mem: 8452 +Train: [36] [1300/6250] eta: 0:13:52 lr: 0.000095 grad: 0.0841 (0.0952) loss: 0.8382 (0.8518) time: 0.1532 data: 0.0786 max mem: 8452 +Train: [36] [1400/6250] eta: 0:13:37 lr: 0.000095 grad: 0.0882 (0.0949) loss: 0.8366 (0.8510) time: 0.1467 data: 0.0649 max mem: 8452 +Train: [36] [1500/6250] eta: 0:13:18 lr: 0.000095 grad: 0.0899 (0.0947) loss: 0.8389 (0.8503) time: 0.1601 data: 0.0774 max mem: 8452 +Train: [36] [1600/6250] eta: 0:13:00 lr: 0.000094 grad: 0.0883 (0.0946) loss: 0.8349 (0.8498) time: 0.1741 data: 0.0939 max mem: 8452 +Train: [36] [1700/6250] eta: 0:12:44 lr: 0.000094 grad: 0.0880 (0.0947) loss: 0.8391 (0.8492) time: 0.1732 data: 0.0975 max mem: 8452 +Train: [36] [1800/6250] eta: 0:12:27 lr: 0.000094 grad: 0.0810 (0.0945) loss: 0.8402 (0.8489) time: 0.1703 data: 0.0841 max mem: 8452 +Train: [36] [1900/6250] eta: 0:12:08 lr: 0.000094 grad: 0.0916 (0.0944) loss: 0.8424 (0.8485) time: 0.1587 data: 0.0760 max mem: 8452 +Train: [36] [2000/6250] eta: 0:11:51 lr: 0.000094 grad: 0.0841 (0.0942) loss: 0.8486 (0.8483) time: 0.1681 data: 0.0895 max mem: 8452 +Train: [36] [2100/6250] eta: 0:11:33 lr: 0.000094 grad: 0.0838 (0.0940) loss: 0.8521 (0.8482) time: 0.1679 data: 0.0877 max mem: 8452 +Train: [36] [2200/6250] eta: 0:11:15 lr: 0.000094 grad: 0.0821 (0.0938) loss: 0.8484 (0.8481) time: 0.1606 data: 0.0770 max mem: 8452 +Train: [36] [2300/6250] eta: 0:10:56 lr: 0.000094 grad: 0.0904 (0.0937) loss: 0.8410 (0.8481) time: 0.1572 data: 0.0695 max mem: 8452 +Train: [36] [2400/6250] eta: 0:10:40 lr: 0.000094 grad: 0.0832 (0.0937) loss: 0.8555 (0.8480) time: 0.2132 data: 0.1226 max mem: 8452 +Train: [36] [2500/6250] eta: 0:10:23 lr: 0.000094 grad: 0.0905 (0.0935) loss: 0.8427 (0.8479) time: 0.1876 data: 0.1145 max mem: 8452 +Train: [36] [2600/6250] eta: 0:10:07 lr: 0.000094 grad: 0.0904 (0.0934) loss: 0.8474 (0.8479) time: 0.2652 data: 0.1945 max mem: 8452 +Train: [36] [2700/6250] eta: 0:09:48 lr: 0.000094 grad: 0.0814 (0.0934) loss: 0.8497 (0.8478) time: 0.1419 data: 0.0729 max mem: 8452 +Train: [36] [2800/6250] eta: 0:09:30 lr: 0.000094 grad: 0.0887 (0.0932) loss: 0.8459 (0.8477) time: 0.1896 data: 0.1157 max mem: 8452 +Train: [36] [2900/6250] eta: 0:09:13 lr: 0.000094 grad: 0.0895 (0.0932) loss: 0.8490 (0.8476) time: 0.1553 data: 0.0778 max mem: 8452 +Train: [36] [3000/6250] eta: 0:08:55 lr: 0.000094 grad: 0.0923 (0.0932) loss: 0.8399 (0.8475) time: 0.1761 data: 0.1050 max mem: 8452 +Train: [36] [3100/6250] eta: 0:08:38 lr: 0.000094 grad: 0.0894 (0.0932) loss: 0.8389 (0.8474) time: 0.1633 data: 0.0861 max mem: 8452 +Train: [36] [3200/6250] eta: 0:08:21 lr: 0.000094 grad: 0.0886 (0.0931) loss: 0.8471 (0.8474) time: 0.1515 data: 0.0676 max mem: 8452 +Train: [36] [3300/6250] eta: 0:08:04 lr: 0.000094 grad: 0.0957 (0.0932) loss: 0.8385 (0.8474) time: 0.1633 data: 0.0750 max mem: 8452 +Train: [36] [3400/6250] eta: 0:07:48 lr: 0.000094 grad: 0.0940 (0.0932) loss: 0.8504 (0.8473) time: 0.1781 data: 0.1012 max mem: 8452 +Train: [36] [3500/6250] eta: 0:07:31 lr: 0.000094 grad: 0.0802 (0.0931) loss: 0.8501 (0.8473) time: 0.1739 data: 0.0927 max mem: 8452 +Train: [36] [3600/6250] eta: 0:07:14 lr: 0.000094 grad: 0.0857 (0.0930) loss: 0.8514 (0.8474) time: 0.1372 data: 0.0532 max mem: 8452 +Train: [36] [3700/6250] eta: 0:06:58 lr: 0.000094 grad: 0.0856 (0.0928) loss: 0.8479 (0.8474) time: 0.1641 data: 0.0812 max mem: 8452 +Train: [36] [3800/6250] eta: 0:06:41 lr: 0.000094 grad: 0.0850 (0.0927) loss: 0.8493 (0.8475) time: 0.1180 data: 0.0344 max mem: 8452 +Train: [36] [3900/6250] eta: 0:06:24 lr: 0.000094 grad: 0.0908 (0.0927) loss: 0.8504 (0.8475) time: 0.1687 data: 0.0657 max mem: 8452 +Train: [36] [4000/6250] eta: 0:06:07 lr: 0.000094 grad: 0.0920 (0.0926) loss: 0.8538 (0.8476) time: 0.1422 data: 0.0468 max mem: 8452 +Train: [36] [4100/6250] eta: 0:05:50 lr: 0.000094 grad: 0.0825 (0.0924) loss: 0.8473 (0.8477) time: 0.1763 data: 0.0935 max mem: 8452 +Train: [36] [4200/6250] eta: 0:05:33 lr: 0.000094 grad: 0.0796 (0.0923) loss: 0.8545 (0.8478) time: 0.1491 data: 0.0723 max mem: 8452 +Train: [36] [4300/6250] eta: 0:05:17 lr: 0.000094 grad: 0.0822 (0.0922) loss: 0.8563 (0.8479) time: 0.1623 data: 0.0841 max mem: 8452 +Train: [36] [4400/6250] eta: 0:05:01 lr: 0.000094 grad: 0.0844 (0.0921) loss: 0.8529 (0.8480) time: 0.2187 data: 0.1408 max mem: 8452 +Train: [36] [4500/6250] eta: 0:04:45 lr: 0.000094 grad: 0.0822 (0.0920) loss: 0.8550 (0.8481) time: 0.1257 data: 0.0522 max mem: 8452 +Train: [36] [4600/6250] eta: 0:04:28 lr: 0.000094 grad: 0.0897 (0.0919) loss: 0.8522 (0.8482) time: 0.1316 data: 0.0639 max mem: 8452 +Train: [36] [4700/6250] eta: 0:04:12 lr: 0.000094 grad: 0.0892 (0.0918) loss: 0.8501 (0.8483) time: 0.1991 data: 0.1132 max mem: 8452 +Train: [36] [4800/6250] eta: 0:03:56 lr: 0.000094 grad: 0.0884 (0.0918) loss: 0.8482 (0.8483) time: 0.1849 data: 0.1126 max mem: 8452 +Train: [36] [4900/6250] eta: 0:03:40 lr: 0.000094 grad: 0.0870 (0.0918) loss: 0.8435 (0.8484) time: 0.1637 data: 0.0792 max mem: 8452 +Train: [36] [5000/6250] eta: 0:03:23 lr: 0.000094 grad: 0.0856 (0.0918) loss: 0.8472 (0.8484) time: 0.1241 data: 0.0471 max mem: 8452 +Train: [36] [5100/6250] eta: 0:03:07 lr: 0.000093 grad: 0.0832 (0.0919) loss: 0.8477 (0.8485) time: 0.1554 data: 0.0604 max mem: 8452 +Train: [36] [5200/6250] eta: 0:02:50 lr: 0.000093 grad: 0.0862 (0.0918) loss: 0.8515 (0.8485) time: 0.1745 data: 0.0965 max mem: 8452 +Train: [36] [5300/6250] eta: 0:02:34 lr: 0.000093 grad: 0.0840 (0.0917) loss: 0.8520 (0.8485) time: 0.1480 data: 0.0713 max mem: 8452 +Train: [36] [5400/6250] eta: 0:02:18 lr: 0.000093 grad: 0.0799 (0.0917) loss: 0.8531 (0.8486) time: 0.1575 data: 0.0724 max mem: 8452 +Train: [36] [5500/6250] eta: 0:02:01 lr: 0.000093 grad: 0.0816 (0.0916) loss: 0.8516 (0.8487) time: 0.1845 data: 0.1069 max mem: 8452 +Train: [36] [5600/6250] eta: 0:01:45 lr: 0.000093 grad: 0.0813 (0.0914) loss: 0.8601 (0.8488) time: 0.1607 data: 0.0894 max mem: 8452 +Train: [36] [5700/6250] eta: 0:01:29 lr: 0.000093 grad: 0.0812 (0.0914) loss: 0.8554 (0.8489) time: 0.1975 data: 0.1191 max mem: 8452 +Train: [36] [5800/6250] eta: 0:01:13 lr: 0.000093 grad: 0.0861 (0.0914) loss: 0.8605 (0.8490) time: 0.1706 data: 0.0894 max mem: 8452 +Train: [36] [5900/6250] eta: 0:00:56 lr: 0.000093 grad: 0.0880 (0.0913) loss: 0.8510 (0.8491) time: 0.1287 data: 0.0267 max mem: 8452 +Train: [36] [6000/6250] eta: 0:00:40 lr: 0.000093 grad: 0.0797 (0.0913) loss: 0.8616 (0.8492) time: 0.1550 data: 0.0712 max mem: 8452 +Train: [36] [6100/6250] eta: 0:00:24 lr: 0.000093 grad: 0.0845 (0.0912) loss: 0.8579 (0.8493) time: 0.0991 data: 0.0215 max mem: 8452 +Train: [36] [6200/6250] eta: 0:00:08 lr: 0.000093 grad: 0.0768 (0.0911) loss: 0.8556 (0.8494) time: 0.1385 data: 0.0618 max mem: 8452 +Train: [36] [6249/6250] eta: 0:00:00 lr: 0.000093 grad: 0.0819 (0.0910) loss: 0.8576 (0.8494) time: 0.1458 data: 0.0647 max mem: 8452 +Train: [36] Total time: 0:16:58 (0.1630 s / it) +Averaged stats: lr: 0.000093 grad: 0.0819 (0.0910) loss: 0.8576 (0.8494) +Eval (hcp-train-subset): [36] [ 0/62] eta: 0:06:07 loss: 0.8942 (0.8942) time: 5.9276 data: 5.8962 max mem: 8452 +Eval (hcp-train-subset): [36] [61/62] eta: 0:00:00 loss: 0.8789 (0.8804) time: 0.1295 data: 0.1084 max mem: 8452 +Eval (hcp-train-subset): [36] Total time: 0:00:14 (0.2333 s / it) +Averaged stats (hcp-train-subset): loss: 0.8789 (0.8804) +Eval (hcp-val): [36] [ 0/62] eta: 0:05:24 loss: 0.8750 (0.8750) time: 5.2355 data: 5.1837 max mem: 8452 +Eval (hcp-val): [36] [61/62] eta: 0:00:00 loss: 0.8767 (0.8790) time: 0.1475 data: 0.1253 max mem: 8452 +Eval (hcp-val): [36] Total time: 0:00:14 (0.2375 s / it) +Averaged stats (hcp-val): loss: 0.8767 (0.8790) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [37] [ 0/6250] eta: 8:51:35 lr: 0.000093 grad: 0.1437 (0.1437) loss: 0.8622 (0.8622) time: 5.1032 data: 4.8989 max mem: 8452 +Train: [37] [ 100/6250] eta: 0:23:48 lr: 0.000093 grad: 0.0835 (0.1231) loss: 0.8650 (0.8625) time: 0.1944 data: 0.1038 max mem: 8452 +Train: [37] [ 200/6250] eta: 0:20:09 lr: 0.000093 grad: 0.0941 (0.1121) loss: 0.8480 (0.8567) time: 0.1685 data: 0.0746 max mem: 8452 +Train: [37] [ 300/6250] eta: 0:18:43 lr: 0.000093 grad: 0.0922 (0.1092) loss: 0.8475 (0.8532) time: 0.1694 data: 0.0912 max mem: 8452 +Train: [37] [ 400/6250] eta: 0:17:44 lr: 0.000093 grad: 0.0863 (0.1049) loss: 0.8540 (0.8519) time: 0.1576 data: 0.0582 max mem: 8452 +Train: [37] [ 500/6250] eta: 0:17:01 lr: 0.000093 grad: 0.0851 (0.1027) loss: 0.8489 (0.8513) time: 0.1703 data: 0.0860 max mem: 8452 +Train: [37] [ 600/6250] eta: 0:16:24 lr: 0.000093 grad: 0.0842 (0.1012) loss: 0.8512 (0.8510) time: 0.1462 data: 0.0624 max mem: 8452 +Train: [37] [ 700/6250] eta: 0:15:59 lr: 0.000093 grad: 0.0911 (0.0995) loss: 0.8516 (0.8511) time: 0.1742 data: 0.0916 max mem: 8452 +Train: [37] [ 800/6250] eta: 0:15:31 lr: 0.000093 grad: 0.0815 (0.0979) loss: 0.8458 (0.8511) time: 0.1448 data: 0.0675 max mem: 8452 +Train: [37] [ 900/6250] eta: 0:15:20 lr: 0.000093 grad: 0.0839 (0.0965) loss: 0.8501 (0.8513) time: 0.1663 data: 0.0399 max mem: 8452 +Train: [37] [1000/6250] eta: 0:14:56 lr: 0.000093 grad: 0.0822 (0.0952) loss: 0.8539 (0.8513) time: 0.1693 data: 0.0830 max mem: 8452 +Train: [37] [1100/6250] eta: 0:14:31 lr: 0.000093 grad: 0.0830 (0.0943) loss: 0.8582 (0.8512) time: 0.1547 data: 0.0752 max mem: 8452 +Train: [37] [1200/6250] eta: 0:14:07 lr: 0.000093 grad: 0.0828 (0.0935) loss: 0.8518 (0.8510) time: 0.1568 data: 0.0779 max mem: 8452 +Train: [37] [1300/6250] eta: 0:13:45 lr: 0.000093 grad: 0.0856 (0.0929) loss: 0.8484 (0.8508) time: 0.1555 data: 0.0764 max mem: 8452 +Train: [37] [1400/6250] eta: 0:13:31 lr: 0.000093 grad: 0.0826 (0.0926) loss: 0.8533 (0.8507) time: 0.1584 data: 0.0894 max mem: 8452 +Train: [37] [1500/6250] eta: 0:13:10 lr: 0.000093 grad: 0.0846 (0.0921) loss: 0.8468 (0.8506) time: 0.1658 data: 0.0819 max mem: 8452 +Train: [37] [1600/6250] eta: 0:12:53 lr: 0.000093 grad: 0.0768 (0.0917) loss: 0.8567 (0.8506) time: 0.1759 data: 0.1065 max mem: 8452 +Train: [37] [1700/6250] eta: 0:12:37 lr: 0.000093 grad: 0.0833 (0.0914) loss: 0.8451 (0.8505) time: 0.1581 data: 0.0681 max mem: 8452 +Train: [37] [1800/6250] eta: 0:12:19 lr: 0.000093 grad: 0.0826 (0.0910) loss: 0.8518 (0.8506) time: 0.1609 data: 0.0758 max mem: 8452 +Train: [37] [1900/6250] eta: 0:12:02 lr: 0.000093 grad: 0.0780 (0.0906) loss: 0.8577 (0.8507) time: 0.1740 data: 0.0895 max mem: 8452 +Train: [37] [2000/6250] eta: 0:11:46 lr: 0.000093 grad: 0.0767 (0.0903) loss: 0.8596 (0.8509) time: 0.1993 data: 0.1175 max mem: 8452 +Train: [37] [2100/6250] eta: 0:11:27 lr: 0.000093 grad: 0.0804 (0.0902) loss: 0.8546 (0.8511) time: 0.1643 data: 0.0850 max mem: 8452 +Train: [37] [2200/6250] eta: 0:11:07 lr: 0.000093 grad: 0.0866 (0.0900) loss: 0.8528 (0.8513) time: 0.1492 data: 0.0613 max mem: 8452 +Train: [37] [2300/6250] eta: 0:10:49 lr: 0.000092 grad: 0.0812 (0.0896) loss: 0.8569 (0.8517) time: 0.1722 data: 0.0927 max mem: 8452 +Train: [37] [2400/6250] eta: 0:10:31 lr: 0.000092 grad: 0.0803 (0.0895) loss: 0.8631 (0.8519) time: 0.1555 data: 0.0755 max mem: 8452 +Train: [37] [2500/6250] eta: 0:10:13 lr: 0.000092 grad: 0.0873 (0.0894) loss: 0.8505 (0.8519) time: 0.1607 data: 0.0910 max mem: 8452 +Train: [37] [2600/6250] eta: 0:09:56 lr: 0.000092 grad: 0.0812 (0.0893) loss: 0.8552 (0.8519) time: 0.1565 data: 0.0844 max mem: 8452 +Train: [37] [2700/6250] eta: 0:09:38 lr: 0.000092 grad: 0.0851 (0.0892) loss: 0.8550 (0.8520) time: 0.1194 data: 0.0248 max mem: 8452 +Train: [37] [2800/6250] eta: 0:09:19 lr: 0.000092 grad: 0.0843 (0.0892) loss: 0.8459 (0.8519) time: 0.1142 data: 0.0319 max mem: 8452 +Train: [37] [2900/6250] eta: 0:09:02 lr: 0.000092 grad: 0.0834 (0.0892) loss: 0.8469 (0.8518) time: 0.1580 data: 0.0825 max mem: 8452 +Train: [37] [3000/6250] eta: 0:08:49 lr: 0.000092 grad: 0.0866 (0.0891) loss: 0.8472 (0.8517) time: 0.1687 data: 0.0757 max mem: 8452 +Train: [37] [3100/6250] eta: 0:08:33 lr: 0.000092 grad: 0.0893 (0.0892) loss: 0.8510 (0.8516) time: 0.1768 data: 0.0993 max mem: 8452 +Train: [37] [3200/6250] eta: 0:08:18 lr: 0.000092 grad: 0.0855 (0.0893) loss: 0.8512 (0.8514) time: 0.1280 data: 0.0440 max mem: 8452 +Train: [37] [3300/6250] eta: 0:08:04 lr: 0.000092 grad: 0.0856 (0.0894) loss: 0.8491 (0.8512) time: 0.1795 data: 0.1121 max mem: 8452 +Train: [37] [3400/6250] eta: 0:07:49 lr: 0.000092 grad: 0.0839 (0.0894) loss: 0.8525 (0.8512) time: 0.1453 data: 0.0721 max mem: 8452 +Train: [37] [3500/6250] eta: 0:07:34 lr: 0.000092 grad: 0.0850 (0.0894) loss: 0.8420 (0.8510) time: 0.1515 data: 0.0687 max mem: 8452 +Train: [37] [3600/6250] eta: 0:07:18 lr: 0.000092 grad: 0.0859 (0.0894) loss: 0.8479 (0.8508) time: 0.1571 data: 0.0725 max mem: 8452 +Train: [37] [3700/6250] eta: 0:07:03 lr: 0.000092 grad: 0.0878 (0.0895) loss: 0.8399 (0.8507) time: 0.1988 data: 0.1197 max mem: 8452 +Train: [37] [3800/6250] eta: 0:06:46 lr: 0.000092 grad: 0.0850 (0.0895) loss: 0.8509 (0.8506) time: 0.1916 data: 0.0972 max mem: 8452 +Train: [37] [3900/6250] eta: 0:06:30 lr: 0.000092 grad: 0.0862 (0.0895) loss: 0.8553 (0.8505) time: 0.1748 data: 0.0900 max mem: 8452 +Train: [37] [4000/6250] eta: 0:06:13 lr: 0.000092 grad: 0.0844 (0.0896) loss: 0.8480 (0.8504) time: 0.1391 data: 0.0527 max mem: 8452 +Train: [37] [4100/6250] eta: 0:05:56 lr: 0.000092 grad: 0.0850 (0.0895) loss: 0.8450 (0.8504) time: 0.1508 data: 0.0653 max mem: 8452 +Train: [37] [4200/6250] eta: 0:05:39 lr: 0.000092 grad: 0.0815 (0.0896) loss: 0.8539 (0.8503) time: 0.1550 data: 0.0753 max mem: 8452 +Train: [37] [4300/6250] eta: 0:05:24 lr: 0.000092 grad: 0.0886 (0.0896) loss: 0.8499 (0.8503) time: 0.2590 data: 0.1660 max mem: 8452 +Train: [37] [4400/6250] eta: 0:05:07 lr: 0.000092 grad: 0.0932 (0.0897) loss: 0.8426 (0.8503) time: 0.2188 data: 0.1569 max mem: 8452 +Train: [37] [4500/6250] eta: 0:04:51 lr: 0.000092 grad: 0.0910 (0.0897) loss: 0.8405 (0.8502) time: 0.1664 data: 0.0921 max mem: 8452 +Train: [37] [4600/6250] eta: 0:04:34 lr: 0.000092 grad: 0.0925 (0.0897) loss: 0.8453 (0.8500) time: 0.1729 data: 0.0930 max mem: 8452 +Train: [37] [4700/6250] eta: 0:04:18 lr: 0.000092 grad: 0.0899 (0.0898) loss: 0.8443 (0.8499) time: 0.1817 data: 0.1050 max mem: 8452 +Train: [37] [4800/6250] eta: 0:04:01 lr: 0.000092 grad: 0.0892 (0.0898) loss: 0.8480 (0.8498) time: 0.1693 data: 0.0817 max mem: 8452 +Train: [37] [4900/6250] eta: 0:03:44 lr: 0.000092 grad: 0.0847 (0.0899) loss: 0.8502 (0.8498) time: 0.1761 data: 0.1005 max mem: 8452 +Train: [37] [5000/6250] eta: 0:03:28 lr: 0.000092 grad: 0.0920 (0.0899) loss: 0.8486 (0.8497) time: 0.1702 data: 0.0875 max mem: 8452 +Train: [37] [5100/6250] eta: 0:03:11 lr: 0.000092 grad: 0.0847 (0.0899) loss: 0.8522 (0.8496) time: 0.1765 data: 0.0915 max mem: 8452 +Train: [37] [5200/6250] eta: 0:02:54 lr: 0.000092 grad: 0.0941 (0.0900) loss: 0.8499 (0.8496) time: 0.1745 data: 0.0886 max mem: 8452 +Train: [37] [5300/6250] eta: 0:02:37 lr: 0.000092 grad: 0.0985 (0.0902) loss: 0.8378 (0.8495) time: 0.1628 data: 0.0752 max mem: 8452 +Train: [37] [5400/6250] eta: 0:02:21 lr: 0.000092 grad: 0.0921 (0.0902) loss: 0.8516 (0.8494) time: 0.1661 data: 0.0842 max mem: 8452 +Train: [37] [5500/6250] eta: 0:02:04 lr: 0.000092 grad: 0.0902 (0.0902) loss: 0.8491 (0.8494) time: 0.1919 data: 0.1183 max mem: 8452 +Train: [37] [5600/6250] eta: 0:01:47 lr: 0.000092 grad: 0.0847 (0.0903) loss: 0.8541 (0.8493) time: 0.1445 data: 0.0747 max mem: 8452 +Train: [37] [5700/6250] eta: 0:01:31 lr: 0.000091 grad: 0.0918 (0.0903) loss: 0.8462 (0.8493) time: 0.1418 data: 0.0486 max mem: 8452 +Train: [37] [5800/6250] eta: 0:01:14 lr: 0.000091 grad: 0.0882 (0.0903) loss: 0.8424 (0.8493) time: 0.1651 data: 0.0798 max mem: 8452 +Train: [37] [5900/6250] eta: 0:00:57 lr: 0.000091 grad: 0.0948 (0.0904) loss: 0.8445 (0.8492) time: 0.1500 data: 0.0599 max mem: 8452 +Train: [37] [6000/6250] eta: 0:00:41 lr: 0.000091 grad: 0.0842 (0.0905) loss: 0.8505 (0.8492) time: 0.1371 data: 0.0347 max mem: 8452 +Train: [37] [6100/6250] eta: 0:00:24 lr: 0.000091 grad: 0.0914 (0.0905) loss: 0.8462 (0.8491) time: 0.1708 data: 0.0914 max mem: 8452 +Train: [37] [6200/6250] eta: 0:00:08 lr: 0.000091 grad: 0.0894 (0.0906) loss: 0.8447 (0.8490) time: 0.1459 data: 0.0590 max mem: 8452 +Train: [37] [6249/6250] eta: 0:00:00 lr: 0.000091 grad: 0.0867 (0.0906) loss: 0.8493 (0.8490) time: 0.1391 data: 0.0494 max mem: 8452 +Train: [37] Total time: 0:17:19 (0.1663 s / it) +Averaged stats: lr: 0.000091 grad: 0.0867 (0.0906) loss: 0.8493 (0.8490) +Eval (hcp-train-subset): [37] [ 0/62] eta: 0:04:13 loss: 0.8943 (0.8943) time: 4.0862 data: 4.0174 max mem: 8452 +Eval (hcp-train-subset): [37] [61/62] eta: 0:00:00 loss: 0.8784 (0.8790) time: 0.1345 data: 0.1125 max mem: 8452 +Eval (hcp-train-subset): [37] Total time: 0:00:14 (0.2349 s / it) +Averaged stats (hcp-train-subset): loss: 0.8784 (0.8790) +Eval (hcp-val): [37] [ 0/62] eta: 0:06:07 loss: 0.8773 (0.8773) time: 5.9247 data: 5.8734 max mem: 8452 +Eval (hcp-val): [37] [61/62] eta: 0:00:00 loss: 0.8762 (0.8776) time: 0.1164 data: 0.0949 max mem: 8452 +Eval (hcp-val): [37] Total time: 0:00:14 (0.2383 s / it) +Averaged stats (hcp-val): loss: 0.8762 (0.8776) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [38] [ 0/6250] eta: 10:43:13 lr: 0.000091 grad: 0.0722 (0.0722) loss: 0.8900 (0.8900) time: 6.1750 data: 6.0162 max mem: 8452 +Train: [38] [ 100/6250] eta: 0:22:47 lr: 0.000091 grad: 0.0913 (0.1146) loss: 0.8690 (0.8765) time: 0.1822 data: 0.0571 max mem: 8452 +Train: [38] [ 200/6250] eta: 0:19:39 lr: 0.000091 grad: 0.0828 (0.1029) loss: 0.8575 (0.8683) time: 0.1518 data: 0.0530 max mem: 8452 +Train: [38] [ 300/6250] eta: 0:18:38 lr: 0.000091 grad: 0.0906 (0.1000) loss: 0.8504 (0.8637) time: 0.1585 data: 0.0663 max mem: 8452 +Train: [38] [ 400/6250] eta: 0:17:47 lr: 0.000091 grad: 0.0783 (0.0994) loss: 0.8604 (0.8606) time: 0.1806 data: 0.0908 max mem: 8452 +Train: [38] [ 500/6250] eta: 0:17:07 lr: 0.000091 grad: 0.0848 (0.0976) loss: 0.8536 (0.8594) time: 0.1703 data: 0.0775 max mem: 8452 +Train: [38] [ 600/6250] eta: 0:16:36 lr: 0.000091 grad: 0.0820 (0.0959) loss: 0.8666 (0.8590) time: 0.1874 data: 0.1001 max mem: 8452 +Train: [38] [ 700/6250] eta: 0:16:08 lr: 0.000091 grad: 0.0844 (0.0949) loss: 0.8565 (0.8588) time: 0.1591 data: 0.0709 max mem: 8452 +Train: [38] [ 800/6250] eta: 0:15:43 lr: 0.000091 grad: 0.0821 (0.0943) loss: 0.8558 (0.8584) time: 0.1430 data: 0.0571 max mem: 8452 +Train: [38] [ 900/6250] eta: 0:15:34 lr: 0.000091 grad: 0.0834 (0.0932) loss: 0.8546 (0.8583) time: 0.3074 data: 0.2315 max mem: 8452 +Train: [38] [1000/6250] eta: 0:15:02 lr: 0.000091 grad: 0.0789 (0.0924) loss: 0.8595 (0.8581) time: 0.1897 data: 0.1265 max mem: 8452 +Train: [38] [1100/6250] eta: 0:14:33 lr: 0.000091 grad: 0.0825 (0.0920) loss: 0.8537 (0.8578) time: 0.1508 data: 0.0676 max mem: 8452 +Train: [38] [1200/6250] eta: 0:14:14 lr: 0.000091 grad: 0.0793 (0.0916) loss: 0.8578 (0.8576) time: 0.1193 data: 0.0383 max mem: 8452 +Train: [38] [1300/6250] eta: 0:13:53 lr: 0.000091 grad: 0.0830 (0.0911) loss: 0.8514 (0.8572) time: 0.1674 data: 0.0929 max mem: 8452 +Train: [38] [1400/6250] eta: 0:13:46 lr: 0.000091 grad: 0.0868 (0.0908) loss: 0.8493 (0.8566) time: 0.1003 data: 0.0002 max mem: 8452 +Train: [38] [1500/6250] eta: 0:13:25 lr: 0.000091 grad: 0.0844 (0.0906) loss: 0.8434 (0.8560) time: 0.1513 data: 0.0691 max mem: 8452 +Train: [38] [1600/6250] eta: 0:13:05 lr: 0.000091 grad: 0.0867 (0.0903) loss: 0.8442 (0.8555) time: 0.1428 data: 0.0588 max mem: 8452 +Train: [38] [1700/6250] eta: 0:12:47 lr: 0.000091 grad: 0.0817 (0.0902) loss: 0.8465 (0.8552) time: 0.1606 data: 0.0876 max mem: 8452 +Train: [38] [1800/6250] eta: 0:12:30 lr: 0.000091 grad: 0.0863 (0.0901) loss: 0.8455 (0.8547) time: 0.1663 data: 0.0955 max mem: 8452 +Train: [38] [1900/6250] eta: 0:12:10 lr: 0.000091 grad: 0.0887 (0.0901) loss: 0.8379 (0.8543) time: 0.1572 data: 0.0679 max mem: 8452 +Train: [38] [2000/6250] eta: 0:11:54 lr: 0.000091 grad: 0.0879 (0.0901) loss: 0.8415 (0.8538) time: 0.1783 data: 0.0928 max mem: 8452 +Train: [38] [2100/6250] eta: 0:11:35 lr: 0.000091 grad: 0.0921 (0.0902) loss: 0.8445 (0.8535) time: 0.1202 data: 0.0235 max mem: 8452 +Train: [38] [2200/6250] eta: 0:11:17 lr: 0.000091 grad: 0.0874 (0.0903) loss: 0.8514 (0.8532) time: 0.1692 data: 0.1052 max mem: 8452 +Train: [38] [2300/6250] eta: 0:10:58 lr: 0.000091 grad: 0.0896 (0.0904) loss: 0.8455 (0.8528) time: 0.1463 data: 0.0564 max mem: 8452 +Train: [38] [2400/6250] eta: 0:10:39 lr: 0.000091 grad: 0.0857 (0.0905) loss: 0.8498 (0.8527) time: 0.1711 data: 0.0794 max mem: 8452 +Train: [38] [2500/6250] eta: 0:10:22 lr: 0.000091 grad: 0.0846 (0.0904) loss: 0.8503 (0.8525) time: 0.1814 data: 0.1020 max mem: 8452 +Train: [38] [2600/6250] eta: 0:10:03 lr: 0.000091 grad: 0.0871 (0.0906) loss: 0.8491 (0.8523) time: 0.1601 data: 0.0763 max mem: 8452 +Train: [38] [2700/6250] eta: 0:09:47 lr: 0.000091 grad: 0.0883 (0.0905) loss: 0.8410 (0.8521) time: 0.1962 data: 0.0641 max mem: 8452 +Train: [38] [2800/6250] eta: 0:09:32 lr: 0.000091 grad: 0.0929 (0.0907) loss: 0.8421 (0.8519) time: 0.1613 data: 0.0808 max mem: 8452 +Train: [38] [2900/6250] eta: 0:09:15 lr: 0.000090 grad: 0.0888 (0.0906) loss: 0.8486 (0.8518) time: 0.1974 data: 0.1187 max mem: 8452 +Train: [38] [3000/6250] eta: 0:08:57 lr: 0.000090 grad: 0.0901 (0.0906) loss: 0.8392 (0.8517) time: 0.1612 data: 0.0839 max mem: 8452 +Train: [38] [3100/6250] eta: 0:08:40 lr: 0.000090 grad: 0.0890 (0.0908) loss: 0.8447 (0.8515) time: 0.1771 data: 0.0996 max mem: 8452 +Train: [38] [3200/6250] eta: 0:08:23 lr: 0.000090 grad: 0.0812 (0.0908) loss: 0.8528 (0.8514) time: 0.1669 data: 0.0745 max mem: 8452 +Train: [38] [3300/6250] eta: 0:08:06 lr: 0.000090 grad: 0.0926 (0.0908) loss: 0.8423 (0.8512) time: 0.1453 data: 0.0530 max mem: 8452 +Train: [38] [3400/6250] eta: 0:07:49 lr: 0.000090 grad: 0.0870 (0.0908) loss: 0.8498 (0.8511) time: 0.1517 data: 0.0622 max mem: 8452 +Train: [38] [3500/6250] eta: 0:07:33 lr: 0.000090 grad: 0.0930 (0.0908) loss: 0.8435 (0.8511) time: 0.1503 data: 0.0625 max mem: 8452 +Train: [38] [3600/6250] eta: 0:07:17 lr: 0.000090 grad: 0.0858 (0.0906) loss: 0.8547 (0.8511) time: 0.1773 data: 0.0875 max mem: 8452 +Train: [38] [3700/6250] eta: 0:07:00 lr: 0.000090 grad: 0.0875 (0.0905) loss: 0.8511 (0.8511) time: 0.1653 data: 0.0820 max mem: 8452 +Train: [38] [3800/6250] eta: 0:06:43 lr: 0.000090 grad: 0.0871 (0.0905) loss: 0.8513 (0.8512) time: 0.1643 data: 0.0898 max mem: 8452 +Train: [38] [3900/6250] eta: 0:06:26 lr: 0.000090 grad: 0.0869 (0.0905) loss: 0.8533 (0.8512) time: 0.1435 data: 0.0579 max mem: 8452 +Train: [38] [4000/6250] eta: 0:06:10 lr: 0.000090 grad: 0.0783 (0.0904) loss: 0.8566 (0.8512) time: 0.1693 data: 0.0813 max mem: 8452 +Train: [38] [4100/6250] eta: 0:05:52 lr: 0.000090 grad: 0.0856 (0.0903) loss: 0.8517 (0.8512) time: 0.1711 data: 0.0909 max mem: 8452 +Train: [38] [4200/6250] eta: 0:05:36 lr: 0.000090 grad: 0.0897 (0.0903) loss: 0.8542 (0.8512) time: 0.1593 data: 0.0749 max mem: 8452 +Train: [38] [4300/6250] eta: 0:05:19 lr: 0.000090 grad: 0.0870 (0.0903) loss: 0.8507 (0.8512) time: 0.1496 data: 0.0536 max mem: 8452 +Train: [38] [4400/6250] eta: 0:05:02 lr: 0.000090 grad: 0.0847 (0.0902) loss: 0.8575 (0.8512) time: 0.1470 data: 0.0679 max mem: 8452 +Train: [38] [4500/6250] eta: 0:04:46 lr: 0.000090 grad: 0.0855 (0.0902) loss: 0.8534 (0.8513) time: 0.1869 data: 0.1115 max mem: 8452 +Train: [38] [4600/6250] eta: 0:04:30 lr: 0.000090 grad: 0.0822 (0.0902) loss: 0.8523 (0.8513) time: 0.1512 data: 0.0753 max mem: 8452 +Train: [38] [4700/6250] eta: 0:04:14 lr: 0.000090 grad: 0.0799 (0.0901) loss: 0.8589 (0.8514) time: 0.1876 data: 0.1001 max mem: 8452 +Train: [38] [4800/6250] eta: 0:03:57 lr: 0.000090 grad: 0.0866 (0.0901) loss: 0.8579 (0.8514) time: 0.1849 data: 0.1148 max mem: 8452 +Train: [38] [4900/6250] eta: 0:03:41 lr: 0.000090 grad: 0.0886 (0.0900) loss: 0.8531 (0.8514) time: 0.1837 data: 0.0966 max mem: 8452 +Train: [38] [5000/6250] eta: 0:03:24 lr: 0.000090 grad: 0.0856 (0.0899) loss: 0.8559 (0.8514) time: 0.1423 data: 0.0486 max mem: 8452 +Train: [38] [5100/6250] eta: 0:03:08 lr: 0.000090 grad: 0.0864 (0.0899) loss: 0.8475 (0.8514) time: 0.1640 data: 0.0822 max mem: 8452 +Train: [38] [5200/6250] eta: 0:02:51 lr: 0.000090 grad: 0.0853 (0.0898) loss: 0.8495 (0.8514) time: 0.1377 data: 0.0502 max mem: 8452 +Train: [38] [5300/6250] eta: 0:02:35 lr: 0.000090 grad: 0.0900 (0.0898) loss: 0.8551 (0.8514) time: 0.1680 data: 0.0899 max mem: 8452 +Train: [38] [5400/6250] eta: 0:02:18 lr: 0.000090 grad: 0.0913 (0.0899) loss: 0.8504 (0.8514) time: 0.1494 data: 0.0666 max mem: 8452 +Train: [38] [5500/6250] eta: 0:02:02 lr: 0.000090 grad: 0.0957 (0.0899) loss: 0.8547 (0.8514) time: 0.1538 data: 0.0612 max mem: 8452 +Train: [38] [5600/6250] eta: 0:01:46 lr: 0.000090 grad: 0.0813 (0.0899) loss: 0.8555 (0.8514) time: 0.2024 data: 0.1221 max mem: 8452 +Train: [38] [5700/6250] eta: 0:01:29 lr: 0.000090 grad: 0.0874 (0.0899) loss: 0.8512 (0.8513) time: 0.1362 data: 0.0534 max mem: 8452 +Train: [38] [5800/6250] eta: 0:01:13 lr: 0.000090 grad: 0.0966 (0.0900) loss: 0.8285 (0.8512) time: 0.1453 data: 0.0601 max mem: 8452 +Train: [38] [5900/6250] eta: 0:00:56 lr: 0.000090 grad: 0.0854 (0.0900) loss: 0.8515 (0.8511) time: 0.1854 data: 0.0823 max mem: 8452 +Train: [38] [6000/6250] eta: 0:00:40 lr: 0.000090 grad: 0.0863 (0.0900) loss: 0.8484 (0.8510) time: 0.1595 data: 0.0795 max mem: 8452 +Train: [38] [6100/6250] eta: 0:00:24 lr: 0.000090 grad: 0.0915 (0.0901) loss: 0.8450 (0.8509) time: 0.1663 data: 0.0842 max mem: 8452 +Train: [38] [6200/6250] eta: 0:00:08 lr: 0.000089 grad: 0.0862 (0.0902) loss: 0.8496 (0.8508) time: 0.1460 data: 0.0681 max mem: 8452 +Train: [38] [6249/6250] eta: 0:00:00 lr: 0.000089 grad: 0.0924 (0.0902) loss: 0.8481 (0.8508) time: 0.1431 data: 0.0781 max mem: 8452 +Train: [38] Total time: 0:17:01 (0.1634 s / it) +Averaged stats: lr: 0.000089 grad: 0.0924 (0.0902) loss: 0.8481 (0.8508) +Eval (hcp-train-subset): [38] [ 0/62] eta: 0:03:24 loss: 0.8934 (0.8934) time: 3.3001 data: 3.2256 max mem: 8452 +Eval (hcp-train-subset): [38] [61/62] eta: 0:00:00 loss: 0.8771 (0.8778) time: 0.1158 data: 0.0949 max mem: 8452 +Eval (hcp-train-subset): [38] Total time: 0:00:14 (0.2309 s / it) +Averaged stats (hcp-train-subset): loss: 0.8771 (0.8778) +Eval (hcp-val): [38] [ 0/62] eta: 0:04:31 loss: 0.8730 (0.8730) time: 4.3836 data: 4.2836 max mem: 8452 +Eval (hcp-val): [38] [61/62] eta: 0:00:00 loss: 0.8752 (0.8770) time: 0.1449 data: 0.1213 max mem: 8452 +Eval (hcp-val): [38] Total time: 0:00:14 (0.2297 s / it) +Averaged stats (hcp-val): loss: 0.8752 (0.8770) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [39] [ 0/6250] eta: 9:22:20 lr: 0.000089 grad: 0.0666 (0.0666) loss: 0.8562 (0.8562) time: 5.3985 data: 5.2072 max mem: 8452 +Train: [39] [ 100/6250] eta: 0:22:00 lr: 0.000089 grad: 0.0913 (0.1104) loss: 0.8718 (0.8699) time: 0.1715 data: 0.0774 max mem: 8452 +Train: [39] [ 200/6250] eta: 0:19:04 lr: 0.000089 grad: 0.0848 (0.1028) loss: 0.8589 (0.8639) time: 0.1440 data: 0.0487 max mem: 8452 +Train: [39] [ 300/6250] eta: 0:18:00 lr: 0.000089 grad: 0.0950 (0.1015) loss: 0.8620 (0.8630) time: 0.1728 data: 0.0755 max mem: 8452 +Train: [39] [ 400/6250] eta: 0:17:11 lr: 0.000089 grad: 0.0922 (0.1003) loss: 0.8526 (0.8614) time: 0.1483 data: 0.0614 max mem: 8452 +Train: [39] [ 500/6250] eta: 0:16:38 lr: 0.000089 grad: 0.0839 (0.0982) loss: 0.8590 (0.8602) time: 0.1579 data: 0.0685 max mem: 8452 +Train: [39] [ 600/6250] eta: 0:15:59 lr: 0.000089 grad: 0.0860 (0.0972) loss: 0.8551 (0.8592) time: 0.1688 data: 0.0894 max mem: 8452 +Train: [39] [ 700/6250] eta: 0:15:33 lr: 0.000089 grad: 0.0842 (0.0957) loss: 0.8586 (0.8584) time: 0.1774 data: 0.0920 max mem: 8452 +Train: [39] [ 800/6250] eta: 0:15:02 lr: 0.000089 grad: 0.0859 (0.0944) loss: 0.8519 (0.8579) time: 0.1445 data: 0.0474 max mem: 8452 +Train: [39] [ 900/6250] eta: 0:14:38 lr: 0.000089 grad: 0.0806 (0.0936) loss: 0.8529 (0.8575) time: 0.1505 data: 0.0559 max mem: 8452 +Train: [39] [1000/6250] eta: 0:14:16 lr: 0.000089 grad: 0.0910 (0.0929) loss: 0.8508 (0.8572) time: 0.1531 data: 0.0710 max mem: 8452 +Train: [39] [1100/6250] eta: 0:13:58 lr: 0.000089 grad: 0.0818 (0.0924) loss: 0.8593 (0.8571) time: 0.1611 data: 0.0712 max mem: 8452 +Train: [39] [1200/6250] eta: 0:13:44 lr: 0.000089 grad: 0.0842 (0.0918) loss: 0.8557 (0.8569) time: 0.1729 data: 0.0830 max mem: 8452 +Train: [39] [1300/6250] eta: 0:13:31 lr: 0.000089 grad: 0.0856 (0.0913) loss: 0.8543 (0.8568) time: 0.2115 data: 0.1270 max mem: 8452 +Train: [39] [1400/6250] eta: 0:13:19 lr: 0.000089 grad: 0.0813 (0.0908) loss: 0.8550 (0.8565) time: 0.2139 data: 0.1264 max mem: 8452 +Train: [39] [1500/6250] eta: 0:12:57 lr: 0.000089 grad: 0.0836 (0.0906) loss: 0.8455 (0.8562) time: 0.1475 data: 0.0574 max mem: 8452 +Train: [39] [1600/6250] eta: 0:12:45 lr: 0.000089 grad: 0.0844 (0.0903) loss: 0.8511 (0.8560) time: 0.1535 data: 0.0737 max mem: 8452 +Train: [39] [1700/6250] eta: 0:12:31 lr: 0.000089 grad: 0.0824 (0.0903) loss: 0.8567 (0.8558) time: 0.1950 data: 0.1172 max mem: 8452 +Train: [39] [1800/6250] eta: 0:12:15 lr: 0.000089 grad: 0.0877 (0.0903) loss: 0.8518 (0.8557) time: 0.1956 data: 0.1106 max mem: 8452 +Train: [39] [1900/6250] eta: 0:11:58 lr: 0.000089 grad: 0.0877 (0.0902) loss: 0.8413 (0.8555) time: 0.1525 data: 0.0651 max mem: 8452 +Train: [39] [2000/6250] eta: 0:11:44 lr: 0.000089 grad: 0.0867 (0.0900) loss: 0.8512 (0.8553) time: 0.1943 data: 0.1179 max mem: 8452 +Train: [39] [2100/6250] eta: 0:11:28 lr: 0.000089 grad: 0.0817 (0.0903) loss: 0.8540 (0.8551) time: 0.1764 data: 0.0980 max mem: 8452 +Train: [39] [2200/6250] eta: 0:11:14 lr: 0.000089 grad: 0.0893 (0.0902) loss: 0.8500 (0.8549) time: 0.1635 data: 0.0817 max mem: 8452 +Train: [39] [2300/6250] eta: 0:10:55 lr: 0.000089 grad: 0.0878 (0.0903) loss: 0.8592 (0.8549) time: 0.1687 data: 0.0833 max mem: 8452 +Train: [39] [2400/6250] eta: 0:10:36 lr: 0.000089 grad: 0.0839 (0.0902) loss: 0.8534 (0.8547) time: 0.1515 data: 0.0578 max mem: 8452 +Train: [39] [2500/6250] eta: 0:10:20 lr: 0.000089 grad: 0.0908 (0.0902) loss: 0.8522 (0.8546) time: 0.1852 data: 0.1146 max mem: 8452 +Train: [39] [2600/6250] eta: 0:10:01 lr: 0.000089 grad: 0.0900 (0.0902) loss: 0.8475 (0.8544) time: 0.1493 data: 0.0671 max mem: 8452 +Train: [39] [2700/6250] eta: 0:09:44 lr: 0.000089 grad: 0.0868 (0.0902) loss: 0.8540 (0.8543) time: 0.1652 data: 0.0736 max mem: 8452 +Train: [39] [2800/6250] eta: 0:09:27 lr: 0.000089 grad: 0.0923 (0.0904) loss: 0.8511 (0.8542) time: 0.1133 data: 0.0376 max mem: 8452 +Train: [39] [2900/6250] eta: 0:09:10 lr: 0.000089 grad: 0.0873 (0.0904) loss: 0.8568 (0.8541) time: 0.1331 data: 0.0514 max mem: 8452 +Train: [39] [3000/6250] eta: 0:08:52 lr: 0.000089 grad: 0.0869 (0.0904) loss: 0.8539 (0.8541) time: 0.1649 data: 0.0893 max mem: 8452 +Train: [39] [3100/6250] eta: 0:08:36 lr: 0.000089 grad: 0.0893 (0.0903) loss: 0.8519 (0.8540) time: 0.1794 data: 0.1068 max mem: 8452 +Train: [39] [3200/6250] eta: 0:08:20 lr: 0.000089 grad: 0.0840 (0.0905) loss: 0.8459 (0.8539) time: 0.1537 data: 0.0713 max mem: 8452 +Train: [39] [3300/6250] eta: 0:08:03 lr: 0.000088 grad: 0.0856 (0.0904) loss: 0.8507 (0.8538) time: 0.1815 data: 0.0960 max mem: 8452 +Train: [39] [3400/6250] eta: 0:07:46 lr: 0.000088 grad: 0.0934 (0.0905) loss: 0.8404 (0.8537) time: 0.1284 data: 0.0516 max mem: 8452 +Train: [39] [3500/6250] eta: 0:07:31 lr: 0.000088 grad: 0.0972 (0.0906) loss: 0.8471 (0.8536) time: 0.1641 data: 0.0780 max mem: 8452 +Train: [39] [3600/6250] eta: 0:07:14 lr: 0.000088 grad: 0.0931 (0.0907) loss: 0.8456 (0.8535) time: 0.1503 data: 0.0591 max mem: 8452 +Train: [39] [3700/6250] eta: 0:06:58 lr: 0.000088 grad: 0.0962 (0.0908) loss: 0.8451 (0.8534) time: 0.1625 data: 0.0780 max mem: 8452 +Train: [39] [3800/6250] eta: 0:06:42 lr: 0.000088 grad: 0.0849 (0.0908) loss: 0.8497 (0.8533) time: 0.1526 data: 0.0777 max mem: 8452 +Train: [39] [3900/6250] eta: 0:06:25 lr: 0.000088 grad: 0.0889 (0.0908) loss: 0.8565 (0.8532) time: 0.1678 data: 0.0766 max mem: 8452 +Train: [39] [4000/6250] eta: 0:06:08 lr: 0.000088 grad: 0.0885 (0.0909) loss: 0.8497 (0.8531) time: 0.1570 data: 0.0678 max mem: 8452 +Train: [39] [4100/6250] eta: 0:05:52 lr: 0.000088 grad: 0.0940 (0.0910) loss: 0.8489 (0.8530) time: 0.1736 data: 0.0936 max mem: 8452 +Train: [39] [4200/6250] eta: 0:05:35 lr: 0.000088 grad: 0.0926 (0.0910) loss: 0.8537 (0.8529) time: 0.1542 data: 0.0730 max mem: 8452 +Train: [39] [4300/6250] eta: 0:05:19 lr: 0.000088 grad: 0.0879 (0.0911) loss: 0.8500 (0.8529) time: 0.1594 data: 0.0790 max mem: 8452 +Train: [39] [4400/6250] eta: 0:05:02 lr: 0.000088 grad: 0.0893 (0.0911) loss: 0.8521 (0.8528) time: 0.2374 data: 0.1749 max mem: 8452 +Train: [39] [4500/6250] eta: 0:04:46 lr: 0.000088 grad: 0.0786 (0.0911) loss: 0.8601 (0.8528) time: 0.1450 data: 0.0630 max mem: 8452 +Train: [39] [4600/6250] eta: 0:04:30 lr: 0.000088 grad: 0.0863 (0.0911) loss: 0.8479 (0.8527) time: 0.1653 data: 0.0914 max mem: 8452 +Train: [39] [4700/6250] eta: 0:04:13 lr: 0.000088 grad: 0.0830 (0.0911) loss: 0.8521 (0.8527) time: 0.1909 data: 0.1082 max mem: 8452 +Train: [39] [4800/6250] eta: 0:03:57 lr: 0.000088 grad: 0.0891 (0.0911) loss: 0.8483 (0.8526) time: 0.1775 data: 0.0956 max mem: 8452 +Train: [39] [4900/6250] eta: 0:03:41 lr: 0.000088 grad: 0.0816 (0.0911) loss: 0.8532 (0.8525) time: 0.1716 data: 0.0878 max mem: 8452 +Train: [39] [5000/6250] eta: 0:03:24 lr: 0.000088 grad: 0.0879 (0.0911) loss: 0.8537 (0.8524) time: 0.1734 data: 0.0943 max mem: 8452 +Train: [39] [5100/6250] eta: 0:03:08 lr: 0.000088 grad: 0.0857 (0.0911) loss: 0.8532 (0.8524) time: 0.1586 data: 0.0740 max mem: 8452 +Train: [39] [5200/6250] eta: 0:02:51 lr: 0.000088 grad: 0.0881 (0.0913) loss: 0.8501 (0.8523) time: 0.1541 data: 0.0776 max mem: 8452 +Train: [39] [5300/6250] eta: 0:02:35 lr: 0.000088 grad: 0.0897 (0.0913) loss: 0.8467 (0.8522) time: 0.1436 data: 0.0547 max mem: 8452 +Train: [39] [5400/6250] eta: 0:02:18 lr: 0.000088 grad: 0.0923 (0.0913) loss: 0.8471 (0.8521) time: 0.1530 data: 0.0672 max mem: 8452 +Train: [39] [5500/6250] eta: 0:02:02 lr: 0.000088 grad: 0.0846 (0.0913) loss: 0.8524 (0.8520) time: 0.1610 data: 0.0736 max mem: 8452 +Train: [39] [5600/6250] eta: 0:01:46 lr: 0.000088 grad: 0.0914 (0.0914) loss: 0.8544 (0.8519) time: 0.1490 data: 0.0673 max mem: 8452 +Train: [39] [5700/6250] eta: 0:01:29 lr: 0.000088 grad: 0.0945 (0.0914) loss: 0.8462 (0.8518) time: 0.1807 data: 0.1089 max mem: 8452 +Train: [39] [5800/6250] eta: 0:01:13 lr: 0.000088 grad: 0.0914 (0.0914) loss: 0.8470 (0.8518) time: 0.1352 data: 0.0413 max mem: 8452 +Train: [39] [5900/6250] eta: 0:00:57 lr: 0.000088 grad: 0.0872 (0.0915) loss: 0.8473 (0.8516) time: 0.1805 data: 0.1056 max mem: 8452 +Train: [39] [6000/6250] eta: 0:00:40 lr: 0.000088 grad: 0.0940 (0.0915) loss: 0.8463 (0.8515) time: 0.1662 data: 0.0950 max mem: 8452 +Train: [39] [6100/6250] eta: 0:00:24 lr: 0.000088 grad: 0.0896 (0.0916) loss: 0.8425 (0.8514) time: 0.1448 data: 0.0695 max mem: 8452 +Train: [39] [6200/6250] eta: 0:00:08 lr: 0.000088 grad: 0.0900 (0.0916) loss: 0.8471 (0.8514) time: 0.1621 data: 0.0799 max mem: 8452 +Train: [39] [6249/6250] eta: 0:00:00 lr: 0.000088 grad: 0.0887 (0.0916) loss: 0.8517 (0.8513) time: 0.1508 data: 0.0650 max mem: 8452 +Train: [39] Total time: 0:17:01 (0.1634 s / it) +Averaged stats: lr: 0.000088 grad: 0.0887 (0.0916) loss: 0.8517 (0.8513) +Eval (hcp-train-subset): [39] [ 0/62] eta: 0:04:10 loss: 0.8886 (0.8886) time: 4.0398 data: 3.9481 max mem: 8452 +Eval (hcp-train-subset): [39] [61/62] eta: 0:00:00 loss: 0.8751 (0.8757) time: 0.1340 data: 0.1130 max mem: 8452 +Eval (hcp-train-subset): [39] Total time: 0:00:14 (0.2318 s / it) +Averaged stats (hcp-train-subset): loss: 0.8751 (0.8757) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [39] [ 0/62] eta: 0:04:53 loss: 0.8735 (0.8735) time: 4.7292 data: 4.6606 max mem: 8452 +Eval (hcp-val): [39] [61/62] eta: 0:00:00 loss: 0.8749 (0.8768) time: 0.1372 data: 0.1160 max mem: 8452 +Eval (hcp-val): [39] Total time: 0:00:14 (0.2330 s / it) +Averaged stats (hcp-val): loss: 0.8749 (0.8768) +Making plots (hcp-val): example=10 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-00039.pth +Train: [40] [ 0/6250] eta: 10:49:13 lr: 0.000088 grad: 0.1713 (0.1713) loss: 0.8697 (0.8697) time: 6.2326 data: 6.0981 max mem: 8452 +Train: [40] [ 100/6250] eta: 0:24:58 lr: 0.000088 grad: 0.0993 (0.1231) loss: 0.8609 (0.8730) time: 0.1830 data: 0.0792 max mem: 8452 +Train: [40] [ 200/6250] eta: 0:21:28 lr: 0.000088 grad: 0.0892 (0.1129) loss: 0.8639 (0.8640) time: 0.1733 data: 0.0759 max mem: 8452 +Train: [40] [ 300/6250] eta: 0:20:18 lr: 0.000088 grad: 0.0872 (0.1076) loss: 0.8493 (0.8583) time: 0.1953 data: 0.1029 max mem: 8452 +Train: [40] [ 400/6250] eta: 0:19:07 lr: 0.000087 grad: 0.0866 (0.1038) loss: 0.8529 (0.8564) time: 0.1620 data: 0.0740 max mem: 8452 +Train: [40] [ 500/6250] eta: 0:18:08 lr: 0.000087 grad: 0.0813 (0.1001) loss: 0.8551 (0.8553) time: 0.1491 data: 0.0516 max mem: 8452 +Train: [40] [ 600/6250] eta: 0:17:30 lr: 0.000087 grad: 0.0844 (0.0982) loss: 0.8575 (0.8550) time: 0.1570 data: 0.0742 max mem: 8452 +Train: [40] [ 700/6250] eta: 0:17:08 lr: 0.000087 grad: 0.0858 (0.0963) loss: 0.8569 (0.8549) time: 0.1809 data: 0.0926 max mem: 8452 +Train: [40] [ 800/6250] eta: 0:16:41 lr: 0.000087 grad: 0.0836 (0.0949) loss: 0.8476 (0.8550) time: 0.2055 data: 0.1169 max mem: 8452 +Train: [40] [ 900/6250] eta: 0:16:21 lr: 0.000087 grad: 0.0816 (0.0939) loss: 0.8539 (0.8549) time: 0.1635 data: 0.0820 max mem: 8452 +Train: [40] [1000/6250] eta: 0:15:47 lr: 0.000087 grad: 0.0852 (0.0929) loss: 0.8475 (0.8550) time: 0.1582 data: 0.0828 max mem: 8452 +Train: [40] [1100/6250] eta: 0:15:22 lr: 0.000087 grad: 0.0840 (0.0922) loss: 0.8566 (0.8551) time: 0.1952 data: 0.1116 max mem: 8452 +Train: [40] [1200/6250] eta: 0:14:58 lr: 0.000087 grad: 0.0861 (0.0917) loss: 0.8511 (0.8549) time: 0.2017 data: 0.1110 max mem: 8452 +Train: [40] [1300/6250] eta: 0:14:38 lr: 0.000087 grad: 0.0822 (0.0914) loss: 0.8535 (0.8546) time: 0.1692 data: 0.0796 max mem: 8452 +Train: [40] [1400/6250] eta: 0:14:20 lr: 0.000087 grad: 0.0865 (0.0910) loss: 0.8437 (0.8543) time: 0.1920 data: 0.1279 max mem: 8452 +Train: [40] [1500/6250] eta: 0:14:04 lr: 0.000087 grad: 0.0905 (0.0910) loss: 0.8498 (0.8541) time: 0.1848 data: 0.1185 max mem: 8452 +Train: [40] [1600/6250] eta: 0:13:43 lr: 0.000087 grad: 0.0802 (0.0906) loss: 0.8554 (0.8541) time: 0.1706 data: 0.0957 max mem: 8452 +Train: [40] [1700/6250] eta: 0:13:19 lr: 0.000087 grad: 0.0863 (0.0904) loss: 0.8508 (0.8540) time: 0.1611 data: 0.0845 max mem: 8452 +Train: [40] [1800/6250] eta: 0:12:59 lr: 0.000087 grad: 0.0835 (0.0903) loss: 0.8610 (0.8539) time: 0.1767 data: 0.0916 max mem: 8452 +Train: [40] [1900/6250] eta: 0:12:39 lr: 0.000087 grad: 0.0785 (0.0902) loss: 0.8502 (0.8537) time: 0.1543 data: 0.0734 max mem: 8452 +Train: [40] [2000/6250] eta: 0:12:23 lr: 0.000087 grad: 0.0810 (0.0901) loss: 0.8515 (0.8534) time: 0.2108 data: 0.1334 max mem: 8452 +Train: [40] [2100/6250] eta: 0:12:03 lr: 0.000087 grad: 0.0884 (0.0901) loss: 0.8513 (0.8533) time: 0.1639 data: 0.0684 max mem: 8452 +Train: [40] [2200/6250] eta: 0:11:44 lr: 0.000087 grad: 0.0809 (0.0900) loss: 0.8528 (0.8533) time: 0.1568 data: 0.0732 max mem: 8452 +Train: [40] [2300/6250] eta: 0:11:24 lr: 0.000087 grad: 0.0875 (0.0898) loss: 0.8509 (0.8532) time: 0.1763 data: 0.0946 max mem: 8452 +Train: [40] [2400/6250] eta: 0:11:04 lr: 0.000087 grad: 0.0838 (0.0899) loss: 0.8497 (0.8531) time: 0.1491 data: 0.0675 max mem: 8452 +Train: [40] [2500/6250] eta: 0:10:44 lr: 0.000087 grad: 0.0925 (0.0900) loss: 0.8407 (0.8529) time: 0.1467 data: 0.0568 max mem: 8452 +Train: [40] [2600/6250] eta: 0:10:25 lr: 0.000087 grad: 0.0861 (0.0900) loss: 0.8543 (0.8526) time: 0.1481 data: 0.0585 max mem: 8452 +Train: [40] [2700/6250] eta: 0:10:06 lr: 0.000087 grad: 0.0922 (0.0901) loss: 0.8468 (0.8524) time: 0.1655 data: 0.0920 max mem: 8452 +Train: [40] [2800/6250] eta: 0:09:50 lr: 0.000087 grad: 0.0918 (0.0903) loss: 0.8439 (0.8523) time: 0.1939 data: 0.1140 max mem: 8452 +Train: [40] [2900/6250] eta: 0:09:32 lr: 0.000087 grad: 0.0896 (0.0903) loss: 0.8410 (0.8520) time: 0.1753 data: 0.1014 max mem: 8452 +Train: [40] [3000/6250] eta: 0:09:14 lr: 0.000087 grad: 0.0898 (0.0903) loss: 0.8478 (0.8519) time: 0.1718 data: 0.1039 max mem: 8452 +Train: [40] [3100/6250] eta: 0:08:57 lr: 0.000087 grad: 0.0893 (0.0905) loss: 0.8414 (0.8516) time: 0.1952 data: 0.1193 max mem: 8452 +Train: [40] [3200/6250] eta: 0:08:39 lr: 0.000087 grad: 0.0892 (0.0905) loss: 0.8523 (0.8514) time: 0.1815 data: 0.0945 max mem: 8452 +Train: [40] [3300/6250] eta: 0:08:22 lr: 0.000087 grad: 0.0935 (0.0906) loss: 0.8430 (0.8511) time: 0.1995 data: 0.1261 max mem: 8452 +Train: [40] [3400/6250] eta: 0:08:04 lr: 0.000087 grad: 0.0903 (0.0910) loss: 0.8417 (0.8509) time: 0.1650 data: 0.0944 max mem: 8452 +Train: [40] [3500/6250] eta: 0:07:47 lr: 0.000087 grad: 0.0895 (0.0911) loss: 0.8422 (0.8508) time: 0.1417 data: 0.0535 max mem: 8452 +Train: [40] [3600/6250] eta: 0:07:29 lr: 0.000087 grad: 0.0930 (0.0913) loss: 0.8474 (0.8505) time: 0.1666 data: 0.0871 max mem: 8452 +Train: [40] [3700/6250] eta: 0:07:11 lr: 0.000086 grad: 0.0948 (0.0915) loss: 0.8442 (0.8503) time: 0.1530 data: 0.0657 max mem: 8452 +Train: [40] [3800/6250] eta: 0:06:54 lr: 0.000086 grad: 0.0885 (0.0916) loss: 0.8417 (0.8502) time: 0.1574 data: 0.0756 max mem: 8452 +Train: [40] [3900/6250] eta: 0:06:36 lr: 0.000086 grad: 0.0887 (0.0916) loss: 0.8404 (0.8500) time: 0.1656 data: 0.0816 max mem: 8452 +Train: [40] [4000/6250] eta: 0:06:18 lr: 0.000086 grad: 0.0862 (0.0918) loss: 0.8468 (0.8498) time: 0.1264 data: 0.0571 max mem: 8452 +Train: [40] [4100/6250] eta: 0:06:01 lr: 0.000086 grad: 0.0911 (0.0918) loss: 0.8432 (0.8497) time: 0.1461 data: 0.0636 max mem: 8452 +Train: [40] [4200/6250] eta: 0:05:44 lr: 0.000086 grad: 0.0970 (0.0919) loss: 0.8449 (0.8496) time: 0.1458 data: 0.0848 max mem: 8452 +Train: [40] [4300/6250] eta: 0:05:27 lr: 0.000086 grad: 0.0888 (0.0919) loss: 0.8488 (0.8494) time: 0.1438 data: 0.0666 max mem: 8452 +Train: [40] [4400/6250] eta: 0:05:11 lr: 0.000086 grad: 0.0893 (0.0920) loss: 0.8445 (0.8493) time: 0.1600 data: 0.0878 max mem: 8452 +Train: [40] [4500/6250] eta: 0:04:54 lr: 0.000086 grad: 0.0902 (0.0920) loss: 0.8362 (0.8491) time: 0.1748 data: 0.0964 max mem: 8452 +Train: [40] [4600/6250] eta: 0:04:37 lr: 0.000086 grad: 0.0969 (0.0920) loss: 0.8378 (0.8490) time: 0.1608 data: 0.0845 max mem: 8452 +Train: [40] [4700/6250] eta: 0:04:20 lr: 0.000086 grad: 0.0936 (0.0921) loss: 0.8411 (0.8488) time: 0.1231 data: 0.0435 max mem: 8452 +Train: [40] [4800/6250] eta: 0:04:03 lr: 0.000086 grad: 0.0905 (0.0921) loss: 0.8506 (0.8487) time: 0.1457 data: 0.0629 max mem: 8452 +Train: [40] [4900/6250] eta: 0:03:46 lr: 0.000086 grad: 0.0930 (0.0922) loss: 0.8422 (0.8486) time: 0.1457 data: 0.0643 max mem: 8452 +Train: [40] [5000/6250] eta: 0:03:29 lr: 0.000086 grad: 0.0902 (0.0923) loss: 0.8413 (0.8485) time: 0.1520 data: 0.0760 max mem: 8452 +Train: [40] [5100/6250] eta: 0:03:12 lr: 0.000086 grad: 0.0879 (0.0923) loss: 0.8470 (0.8485) time: 0.1443 data: 0.0528 max mem: 8452 +Train: [40] [5200/6250] eta: 0:02:55 lr: 0.000086 grad: 0.0916 (0.0923) loss: 0.8427 (0.8484) time: 0.1391 data: 0.0481 max mem: 8452 +Train: [40] [5300/6250] eta: 0:02:38 lr: 0.000086 grad: 0.0881 (0.0924) loss: 0.8427 (0.8483) time: 0.1646 data: 0.0850 max mem: 8452 +Train: [40] [5400/6250] eta: 0:02:21 lr: 0.000086 grad: 0.0963 (0.0924) loss: 0.8398 (0.8482) time: 0.1520 data: 0.0646 max mem: 8452 +Train: [40] [5500/6250] eta: 0:02:04 lr: 0.000086 grad: 0.0966 (0.0925) loss: 0.8421 (0.8480) time: 0.1330 data: 0.0426 max mem: 8452 +Train: [40] [5600/6250] eta: 0:01:47 lr: 0.000086 grad: 0.0871 (0.0925) loss: 0.8415 (0.8479) time: 0.1549 data: 0.0844 max mem: 8452 +Train: [40] [5700/6250] eta: 0:01:31 lr: 0.000086 grad: 0.0944 (0.0925) loss: 0.8428 (0.8478) time: 0.1450 data: 0.0754 max mem: 8452 +Train: [40] [5800/6250] eta: 0:01:14 lr: 0.000086 grad: 0.0905 (0.0926) loss: 0.8427 (0.8477) time: 0.1454 data: 0.0616 max mem: 8452 +Train: [40] [5900/6250] eta: 0:00:57 lr: 0.000086 grad: 0.0943 (0.0927) loss: 0.8439 (0.8476) time: 0.1674 data: 0.0912 max mem: 8452 +Train: [40] [6000/6250] eta: 0:00:41 lr: 0.000086 grad: 0.0860 (0.0927) loss: 0.8498 (0.8476) time: 0.1527 data: 0.0740 max mem: 8452 +Train: [40] [6100/6250] eta: 0:00:24 lr: 0.000086 grad: 0.0923 (0.0928) loss: 0.8482 (0.8476) time: 0.1766 data: 0.1022 max mem: 8452 +Train: [40] [6200/6250] eta: 0:00:08 lr: 0.000086 grad: 0.0930 (0.0928) loss: 0.8484 (0.8475) time: 0.1586 data: 0.0773 max mem: 8452 +Train: [40] [6249/6250] eta: 0:00:00 lr: 0.000086 grad: 0.0899 (0.0928) loss: 0.8400 (0.8475) time: 0.1687 data: 0.0892 max mem: 8452 +Train: [40] Total time: 0:17:18 (0.1661 s / it) +Averaged stats: lr: 0.000086 grad: 0.0899 (0.0928) loss: 0.8400 (0.8475) +Eval (hcp-train-subset): [40] [ 0/62] eta: 0:05:32 loss: 0.8916 (0.8916) time: 5.3668 data: 5.3358 max mem: 8452 +Eval (hcp-train-subset): [40] [61/62] eta: 0:00:00 loss: 0.8760 (0.8780) time: 0.1329 data: 0.1098 max mem: 8452 +Eval (hcp-train-subset): [40] Total time: 0:00:14 (0.2307 s / it) +Averaged stats (hcp-train-subset): loss: 0.8760 (0.8780) +Eval (hcp-val): [40] [ 0/62] eta: 0:06:42 loss: 0.8729 (0.8729) time: 6.4857 data: 6.4586 max mem: 8452 +Eval (hcp-val): [40] [61/62] eta: 0:00:00 loss: 0.8749 (0.8768) time: 0.1220 data: 0.0997 max mem: 8452 +Eval (hcp-val): [40] Total time: 0:00:15 (0.2461 s / it) +Averaged stats (hcp-val): loss: 0.8749 (0.8768) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [41] [ 0/6250] eta: 11:51:36 lr: 0.000086 grad: 0.1617 (0.1617) loss: 0.8970 (0.8970) time: 6.8315 data: 6.7331 max mem: 8452 +Train: [41] [ 100/6250] eta: 0:22:19 lr: 0.000086 grad: 0.0958 (0.1280) loss: 0.8646 (0.8747) time: 0.1475 data: 0.0564 max mem: 8452 +Train: [41] [ 200/6250] eta: 0:19:52 lr: 0.000086 grad: 0.1002 (0.1141) loss: 0.8609 (0.8671) time: 0.1922 data: 0.1052 max mem: 8452 +Train: [41] [ 300/6250] eta: 0:18:30 lr: 0.000086 grad: 0.0833 (0.1104) loss: 0.8571 (0.8636) time: 0.1548 data: 0.0462 max mem: 8452 +Train: [41] [ 400/6250] eta: 0:17:55 lr: 0.000086 grad: 0.0838 (0.1062) loss: 0.8507 (0.8626) time: 0.1610 data: 0.0740 max mem: 8452 +Train: [41] [ 500/6250] eta: 0:17:12 lr: 0.000086 grad: 0.0813 (0.1033) loss: 0.8569 (0.8610) time: 0.1858 data: 0.1032 max mem: 8452 +Train: [41] [ 600/6250] eta: 0:16:37 lr: 0.000086 grad: 0.0847 (0.1007) loss: 0.8505 (0.8598) time: 0.1716 data: 0.0877 max mem: 8452 +Train: [41] [ 700/6250] eta: 0:16:09 lr: 0.000085 grad: 0.0830 (0.0987) loss: 0.8528 (0.8585) time: 0.1805 data: 0.0975 max mem: 8452 +Train: [41] [ 800/6250] eta: 0:15:44 lr: 0.000085 grad: 0.0825 (0.0969) loss: 0.8545 (0.8577) time: 0.1640 data: 0.0738 max mem: 8452 +Train: [41] [ 900/6250] eta: 0:15:20 lr: 0.000085 grad: 0.0797 (0.0956) loss: 0.8589 (0.8575) time: 0.1511 data: 0.0588 max mem: 8452 +Train: [41] [1000/6250] eta: 0:14:57 lr: 0.000085 grad: 0.0815 (0.0946) loss: 0.8565 (0.8573) time: 0.1476 data: 0.0651 max mem: 8452 +Train: [41] [1100/6250] eta: 0:14:36 lr: 0.000085 grad: 0.0838 (0.0938) loss: 0.8548 (0.8569) time: 0.1630 data: 0.0778 max mem: 8452 +Train: [41] [1200/6250] eta: 0:14:28 lr: 0.000085 grad: 0.0826 (0.0930) loss: 0.8493 (0.8565) time: 0.2910 data: 0.1931 max mem: 8452 +Train: [41] [1300/6250] eta: 0:14:02 lr: 0.000085 grad: 0.0846 (0.0927) loss: 0.8473 (0.8558) time: 0.1739 data: 0.0927 max mem: 8452 +Train: [41] [1400/6250] eta: 0:13:40 lr: 0.000085 grad: 0.0840 (0.0923) loss: 0.8530 (0.8552) time: 0.1601 data: 0.0765 max mem: 8452 +Train: [41] [1500/6250] eta: 0:13:17 lr: 0.000085 grad: 0.0850 (0.0920) loss: 0.8506 (0.8549) time: 0.1294 data: 0.0478 max mem: 8452 +Train: [41] [1600/6250] eta: 0:13:09 lr: 0.000085 grad: 0.0856 (0.0918) loss: 0.8493 (0.8547) time: 0.1657 data: 0.0871 max mem: 8452 +Train: [41] [1700/6250] eta: 0:12:51 lr: 0.000085 grad: 0.0885 (0.0917) loss: 0.8457 (0.8543) time: 0.1814 data: 0.1027 max mem: 8452 +Train: [41] [1800/6250] eta: 0:12:32 lr: 0.000085 grad: 0.0880 (0.0915) loss: 0.8519 (0.8540) time: 0.1738 data: 0.1044 max mem: 8452 +Train: [41] [1900/6250] eta: 0:12:16 lr: 0.000085 grad: 0.0866 (0.0914) loss: 0.8410 (0.8536) time: 0.1821 data: 0.1086 max mem: 8452 +Train: [41] [2000/6250] eta: 0:11:57 lr: 0.000085 grad: 0.0798 (0.0912) loss: 0.8599 (0.8534) time: 0.1485 data: 0.0639 max mem: 8452 +Train: [41] [2100/6250] eta: 0:11:41 lr: 0.000085 grad: 0.0886 (0.0911) loss: 0.8447 (0.8531) time: 0.1171 data: 0.0252 max mem: 8452 +Train: [41] [2200/6250] eta: 0:11:22 lr: 0.000085 grad: 0.0849 (0.0910) loss: 0.8531 (0.8531) time: 0.1398 data: 0.0555 max mem: 8452 +Train: [41] [2300/6250] eta: 0:11:03 lr: 0.000085 grad: 0.0903 (0.0910) loss: 0.8485 (0.8529) time: 0.1563 data: 0.0733 max mem: 8452 +Train: [41] [2400/6250] eta: 0:10:45 lr: 0.000085 grad: 0.0828 (0.0911) loss: 0.8526 (0.8526) time: 0.1573 data: 0.0691 max mem: 8452 +Train: [41] [2500/6250] eta: 0:10:25 lr: 0.000085 grad: 0.0828 (0.0910) loss: 0.8483 (0.8524) time: 0.1461 data: 0.0590 max mem: 8452 +Train: [41] [2600/6250] eta: 0:10:07 lr: 0.000085 grad: 0.0857 (0.0910) loss: 0.8540 (0.8523) time: 0.1490 data: 0.0664 max mem: 8452 +Train: [41] [2700/6250] eta: 0:09:48 lr: 0.000085 grad: 0.0837 (0.0910) loss: 0.8424 (0.8520) time: 0.1494 data: 0.0667 max mem: 8452 +Train: [41] [2800/6250] eta: 0:09:30 lr: 0.000085 grad: 0.0895 (0.0909) loss: 0.8483 (0.8518) time: 0.1696 data: 0.0862 max mem: 8452 +Train: [41] [2900/6250] eta: 0:09:13 lr: 0.000085 grad: 0.0869 (0.0909) loss: 0.8419 (0.8516) time: 0.1605 data: 0.0836 max mem: 8452 +Train: [41] [3000/6250] eta: 0:08:55 lr: 0.000085 grad: 0.0885 (0.0909) loss: 0.8506 (0.8514) time: 0.1605 data: 0.0892 max mem: 8452 +Train: [41] [3100/6250] eta: 0:08:40 lr: 0.000085 grad: 0.0904 (0.0910) loss: 0.8410 (0.8512) time: 0.1579 data: 0.0821 max mem: 8452 +Train: [41] [3200/6250] eta: 0:08:23 lr: 0.000085 grad: 0.0838 (0.0909) loss: 0.8476 (0.8510) time: 0.1435 data: 0.0604 max mem: 8452 +Train: [41] [3300/6250] eta: 0:08:07 lr: 0.000085 grad: 0.0902 (0.0910) loss: 0.8413 (0.8507) time: 0.1893 data: 0.1100 max mem: 8452 +Train: [41] [3400/6250] eta: 0:07:49 lr: 0.000085 grad: 0.0877 (0.0910) loss: 0.8462 (0.8505) time: 0.1596 data: 0.0791 max mem: 8452 +Train: [41] [3500/6250] eta: 0:07:33 lr: 0.000085 grad: 0.0923 (0.0910) loss: 0.8492 (0.8504) time: 0.1659 data: 0.0832 max mem: 8452 +Train: [41] [3600/6250] eta: 0:07:16 lr: 0.000085 grad: 0.0868 (0.0910) loss: 0.8477 (0.8503) time: 0.1550 data: 0.0602 max mem: 8452 +Train: [41] [3700/6250] eta: 0:06:59 lr: 0.000085 grad: 0.0859 (0.0911) loss: 0.8361 (0.8502) time: 0.1521 data: 0.0595 max mem: 8452 +Train: [41] [3800/6250] eta: 0:06:41 lr: 0.000085 grad: 0.0879 (0.0911) loss: 0.8429 (0.8501) time: 0.1506 data: 0.0693 max mem: 8452 +Train: [41] [3900/6250] eta: 0:06:24 lr: 0.000084 grad: 0.0850 (0.0912) loss: 0.8467 (0.8499) time: 0.1619 data: 0.0773 max mem: 8452 +Train: [41] [4000/6250] eta: 0:06:07 lr: 0.000084 grad: 0.0888 (0.0913) loss: 0.8460 (0.8497) time: 0.1463 data: 0.0655 max mem: 8452 +Train: [41] [4100/6250] eta: 0:05:50 lr: 0.000084 grad: 0.0887 (0.0913) loss: 0.8495 (0.8496) time: 0.1373 data: 0.0467 max mem: 8452 +Train: [41] [4200/6250] eta: 0:05:32 lr: 0.000084 grad: 0.0890 (0.0913) loss: 0.8436 (0.8495) time: 0.1448 data: 0.0572 max mem: 8452 +Train: [41] [4300/6250] eta: 0:05:16 lr: 0.000084 grad: 0.0921 (0.0914) loss: 0.8474 (0.8493) time: 0.1728 data: 0.1019 max mem: 8452 +Train: [41] [4400/6250] eta: 0:05:00 lr: 0.000084 grad: 0.0911 (0.0915) loss: 0.8407 (0.8492) time: 0.1746 data: 0.1033 max mem: 8452 +Train: [41] [4500/6250] eta: 0:04:44 lr: 0.000084 grad: 0.0946 (0.0916) loss: 0.8437 (0.8491) time: 0.1738 data: 0.1003 max mem: 8452 +Train: [41] [4600/6250] eta: 0:04:29 lr: 0.000084 grad: 0.0923 (0.0917) loss: 0.8393 (0.8489) time: 0.1967 data: 0.1148 max mem: 8452 +Train: [41] [4700/6250] eta: 0:04:13 lr: 0.000084 grad: 0.0890 (0.0917) loss: 0.8463 (0.8488) time: 0.1716 data: 0.0963 max mem: 8452 +Train: [41] [4800/6250] eta: 0:03:57 lr: 0.000084 grad: 0.0861 (0.0917) loss: 0.8444 (0.8486) time: 0.1751 data: 0.0914 max mem: 8452 +Train: [41] [4900/6250] eta: 0:03:41 lr: 0.000084 grad: 0.0892 (0.0917) loss: 0.8436 (0.8485) time: 0.1724 data: 0.0886 max mem: 8452 +Train: [41] [5000/6250] eta: 0:03:24 lr: 0.000084 grad: 0.0934 (0.0918) loss: 0.8378 (0.8484) time: 0.1730 data: 0.0872 max mem: 8452 +Train: [41] [5100/6250] eta: 0:03:08 lr: 0.000084 grad: 0.0941 (0.0918) loss: 0.8494 (0.8483) time: 0.1639 data: 0.0821 max mem: 8452 +Train: [41] [5200/6250] eta: 0:02:52 lr: 0.000084 grad: 0.0905 (0.0919) loss: 0.8410 (0.8483) time: 0.1692 data: 0.0894 max mem: 8452 +Train: [41] [5300/6250] eta: 0:02:35 lr: 0.000084 grad: 0.0910 (0.0919) loss: 0.8392 (0.8482) time: 0.1662 data: 0.0714 max mem: 8452 +Train: [41] [5400/6250] eta: 0:02:19 lr: 0.000084 grad: 0.0937 (0.0920) loss: 0.8463 (0.8480) time: 0.1757 data: 0.0792 max mem: 8452 +Train: [41] [5500/6250] eta: 0:02:03 lr: 0.000084 grad: 0.0907 (0.0921) loss: 0.8453 (0.8480) time: 0.1225 data: 0.0403 max mem: 8452 +Train: [41] [5600/6250] eta: 0:01:46 lr: 0.000084 grad: 0.0886 (0.0921) loss: 0.8490 (0.8479) time: 0.1186 data: 0.0003 max mem: 8452 +Train: [41] [5700/6250] eta: 0:01:30 lr: 0.000084 grad: 0.0908 (0.0921) loss: 0.8436 (0.8478) time: 0.2102 data: 0.1074 max mem: 8452 +Train: [41] [5800/6250] eta: 0:01:14 lr: 0.000084 grad: 0.0898 (0.0922) loss: 0.8483 (0.8478) time: 0.1789 data: 0.0944 max mem: 8452 +Train: [41] [5900/6250] eta: 0:00:57 lr: 0.000084 grad: 0.0927 (0.0923) loss: 0.8401 (0.8477) time: 0.1521 data: 0.0792 max mem: 8452 +Train: [41] [6000/6250] eta: 0:00:41 lr: 0.000084 grad: 0.0900 (0.0923) loss: 0.8455 (0.8477) time: 0.1606 data: 0.0856 max mem: 8452 +Train: [41] [6100/6250] eta: 0:00:24 lr: 0.000084 grad: 0.0939 (0.0923) loss: 0.8459 (0.8477) time: 0.1757 data: 0.0700 max mem: 8452 +Train: [41] [6200/6250] eta: 0:00:08 lr: 0.000084 grad: 0.0912 (0.0923) loss: 0.8508 (0.8477) time: 0.1225 data: 0.0359 max mem: 8452 +Train: [41] [6249/6250] eta: 0:00:00 lr: 0.000084 grad: 0.0874 (0.0923) loss: 0.8549 (0.8477) time: 0.1714 data: 0.0900 max mem: 8452 +Train: [41] Total time: 0:17:16 (0.1658 s / it) +Averaged stats: lr: 0.000084 grad: 0.0874 (0.0923) loss: 0.8549 (0.8477) +Eval (hcp-train-subset): [41] [ 0/62] eta: 0:06:15 loss: 0.8854 (0.8854) time: 6.0529 data: 6.0260 max mem: 8452 +Eval (hcp-train-subset): [41] [61/62] eta: 0:00:00 loss: 0.8767 (0.8773) time: 0.1183 data: 0.0957 max mem: 8452 +Eval (hcp-train-subset): [41] Total time: 0:00:14 (0.2388 s / it) +Averaged stats (hcp-train-subset): loss: 0.8767 (0.8773) +Eval (hcp-val): [41] [ 0/62] eta: 0:05:07 loss: 0.8774 (0.8774) time: 4.9627 data: 4.9362 max mem: 8452 +Eval (hcp-val): [41] [61/62] eta: 0:00:00 loss: 0.8755 (0.8772) time: 0.1486 data: 0.1274 max mem: 8452 +Eval (hcp-val): [41] Total time: 0:00:14 (0.2342 s / it) +Averaged stats (hcp-val): loss: 0.8755 (0.8772) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [42] [ 0/6250] eta: 11:09:09 lr: 0.000084 grad: 0.1223 (0.1223) loss: 0.8951 (0.8951) time: 6.4240 data: 6.2744 max mem: 8452 +Train: [42] [ 100/6250] eta: 0:23:01 lr: 0.000084 grad: 0.1129 (0.1195) loss: 0.8604 (0.8646) time: 0.1769 data: 0.0821 max mem: 8452 +Train: [42] [ 200/6250] eta: 0:20:11 lr: 0.000084 grad: 0.0935 (0.1172) loss: 0.8576 (0.8576) time: 0.1781 data: 0.0856 max mem: 8452 +Train: [42] [ 300/6250] eta: 0:18:48 lr: 0.000084 grad: 0.0815 (0.1106) loss: 0.8634 (0.8558) time: 0.2040 data: 0.1094 max mem: 8452 +Train: [42] [ 400/6250] eta: 0:17:43 lr: 0.000084 grad: 0.0903 (0.1060) loss: 0.8624 (0.8564) time: 0.1679 data: 0.0758 max mem: 8452 +Train: [42] [ 500/6250] eta: 0:17:03 lr: 0.000084 grad: 0.0844 (0.1027) loss: 0.8576 (0.8568) time: 0.1751 data: 0.0802 max mem: 8452 +Train: [42] [ 600/6250] eta: 0:16:33 lr: 0.000084 grad: 0.0835 (0.1003) loss: 0.8547 (0.8565) time: 0.1657 data: 0.0887 max mem: 8452 +Train: [42] [ 700/6250] eta: 0:16:03 lr: 0.000084 grad: 0.0830 (0.0983) loss: 0.8596 (0.8564) time: 0.1900 data: 0.1033 max mem: 8452 +Train: [42] [ 800/6250] eta: 0:15:34 lr: 0.000084 grad: 0.0879 (0.0972) loss: 0.8520 (0.8558) time: 0.1820 data: 0.1023 max mem: 8452 +Train: [42] [ 900/6250] eta: 0:15:11 lr: 0.000083 grad: 0.0831 (0.0962) loss: 0.8541 (0.8551) time: 0.1675 data: 0.0853 max mem: 8452 +Train: [42] [1000/6250] eta: 0:14:51 lr: 0.000083 grad: 0.0926 (0.0953) loss: 0.8490 (0.8547) time: 0.1608 data: 0.0746 max mem: 8452 +Train: [42] [1100/6250] eta: 0:14:29 lr: 0.000083 grad: 0.0859 (0.0946) loss: 0.8496 (0.8539) time: 0.1575 data: 0.0806 max mem: 8452 +Train: [42] [1200/6250] eta: 0:14:06 lr: 0.000083 grad: 0.0816 (0.0941) loss: 0.8532 (0.8535) time: 0.1877 data: 0.1138 max mem: 8452 +Train: [42] [1300/6250] eta: 0:13:42 lr: 0.000083 grad: 0.0831 (0.0938) loss: 0.8469 (0.8528) time: 0.1594 data: 0.0742 max mem: 8452 +Train: [42] [1400/6250] eta: 0:13:28 lr: 0.000083 grad: 0.0874 (0.0933) loss: 0.8444 (0.8524) time: 0.1174 data: 0.0289 max mem: 8452 +Train: [42] [1500/6250] eta: 0:13:12 lr: 0.000083 grad: 0.0858 (0.0929) loss: 0.8474 (0.8519) time: 0.1791 data: 0.1040 max mem: 8452 +Train: [42] [1600/6250] eta: 0:12:54 lr: 0.000083 grad: 0.0874 (0.0927) loss: 0.8519 (0.8517) time: 0.1615 data: 0.0806 max mem: 8452 +Train: [42] [1700/6250] eta: 0:12:41 lr: 0.000083 grad: 0.0859 (0.0927) loss: 0.8487 (0.8512) time: 0.1535 data: 0.0751 max mem: 8452 +Train: [42] [1800/6250] eta: 0:12:25 lr: 0.000083 grad: 0.0845 (0.0926) loss: 0.8423 (0.8509) time: 0.1887 data: 0.1210 max mem: 8452 +Train: [42] [1900/6250] eta: 0:12:09 lr: 0.000083 grad: 0.0865 (0.0924) loss: 0.8474 (0.8507) time: 0.1790 data: 0.1071 max mem: 8452 +Train: [42] [2000/6250] eta: 0:11:55 lr: 0.000083 grad: 0.0851 (0.0925) loss: 0.8455 (0.8504) time: 0.2011 data: 0.1242 max mem: 8452 +Train: [42] [2100/6250] eta: 0:11:38 lr: 0.000083 grad: 0.0913 (0.0926) loss: 0.8442 (0.8500) time: 0.1760 data: 0.0983 max mem: 8452 +Train: [42] [2200/6250] eta: 0:11:21 lr: 0.000083 grad: 0.0932 (0.0928) loss: 0.8491 (0.8498) time: 0.1707 data: 0.0948 max mem: 8452 +Train: [42] [2300/6250] eta: 0:11:02 lr: 0.000083 grad: 0.0950 (0.0928) loss: 0.8464 (0.8495) time: 0.1681 data: 0.0740 max mem: 8452 +Train: [42] [2400/6250] eta: 0:10:43 lr: 0.000083 grad: 0.0910 (0.0928) loss: 0.8455 (0.8493) time: 0.1587 data: 0.0788 max mem: 8452 +Train: [42] [2500/6250] eta: 0:10:26 lr: 0.000083 grad: 0.0871 (0.0928) loss: 0.8504 (0.8491) time: 0.1119 data: 0.0279 max mem: 8452 +Train: [42] [2600/6250] eta: 0:10:06 lr: 0.000083 grad: 0.0927 (0.0930) loss: 0.8460 (0.8488) time: 0.1503 data: 0.0678 max mem: 8452 +Train: [42] [2700/6250] eta: 0:09:47 lr: 0.000083 grad: 0.0884 (0.0928) loss: 0.8433 (0.8487) time: 0.1541 data: 0.0588 max mem: 8452 +Train: [42] [2800/6250] eta: 0:09:30 lr: 0.000083 grad: 0.0908 (0.0928) loss: 0.8439 (0.8485) time: 0.1547 data: 0.0676 max mem: 8452 +Train: [42] [2900/6250] eta: 0:09:12 lr: 0.000083 grad: 0.0898 (0.0927) loss: 0.8451 (0.8485) time: 0.1622 data: 0.0730 max mem: 8452 +Train: [42] [3000/6250] eta: 0:08:56 lr: 0.000083 grad: 0.0865 (0.0927) loss: 0.8529 (0.8485) time: 0.2073 data: 0.1329 max mem: 8452 +Train: [42] [3100/6250] eta: 0:08:39 lr: 0.000083 grad: 0.0869 (0.0926) loss: 0.8538 (0.8485) time: 0.1409 data: 0.0682 max mem: 8452 +Train: [42] [3200/6250] eta: 0:08:23 lr: 0.000083 grad: 0.0881 (0.0925) loss: 0.8425 (0.8484) time: 0.1583 data: 0.0924 max mem: 8452 +Train: [42] [3300/6250] eta: 0:08:06 lr: 0.000083 grad: 0.0919 (0.0925) loss: 0.8439 (0.8483) time: 0.1696 data: 0.0908 max mem: 8452 +Train: [42] [3400/6250] eta: 0:07:49 lr: 0.000083 grad: 0.0951 (0.0924) loss: 0.8483 (0.8483) time: 0.1556 data: 0.0760 max mem: 8452 +Train: [42] [3500/6250] eta: 0:07:32 lr: 0.000083 grad: 0.0889 (0.0923) loss: 0.8528 (0.8483) time: 0.1617 data: 0.0757 max mem: 8452 +Train: [42] [3600/6250] eta: 0:07:16 lr: 0.000083 grad: 0.0926 (0.0923) loss: 0.8468 (0.8483) time: 0.1818 data: 0.0981 max mem: 8452 +Train: [42] [3700/6250] eta: 0:07:00 lr: 0.000083 grad: 0.0873 (0.0922) loss: 0.8453 (0.8483) time: 0.1589 data: 0.0677 max mem: 8452 +Train: [42] [3800/6250] eta: 0:06:44 lr: 0.000083 grad: 0.0851 (0.0922) loss: 0.8507 (0.8482) time: 0.1840 data: 0.0980 max mem: 8452 +Train: [42] [3900/6250] eta: 0:06:27 lr: 0.000083 grad: 0.0932 (0.0922) loss: 0.8473 (0.8482) time: 0.1512 data: 0.0667 max mem: 8452 +Train: [42] [4000/6250] eta: 0:06:10 lr: 0.000083 grad: 0.0870 (0.0923) loss: 0.8464 (0.8482) time: 0.1514 data: 0.0666 max mem: 8452 +Train: [42] [4100/6250] eta: 0:05:53 lr: 0.000082 grad: 0.0950 (0.0923) loss: 0.8482 (0.8481) time: 0.1417 data: 0.0637 max mem: 8452 +Train: [42] [4200/6250] eta: 0:05:38 lr: 0.000082 grad: 0.0898 (0.0924) loss: 0.8484 (0.8480) time: 0.1206 data: 0.0005 max mem: 8452 +Train: [42] [4300/6250] eta: 0:05:22 lr: 0.000082 grad: 0.0899 (0.0925) loss: 0.8419 (0.8479) time: 0.1708 data: 0.0913 max mem: 8452 +Train: [42] [4400/6250] eta: 0:05:05 lr: 0.000082 grad: 0.0907 (0.0925) loss: 0.8469 (0.8478) time: 0.1692 data: 0.0952 max mem: 8452 +Train: [42] [4500/6250] eta: 0:04:49 lr: 0.000082 grad: 0.0893 (0.0925) loss: 0.8398 (0.8477) time: 0.1367 data: 0.0643 max mem: 8452 +Train: [42] [4600/6250] eta: 0:04:32 lr: 0.000082 grad: 0.0922 (0.0926) loss: 0.8465 (0.8476) time: 0.1279 data: 0.0523 max mem: 8452 +Train: [42] [4700/6250] eta: 0:04:16 lr: 0.000082 grad: 0.0958 (0.0927) loss: 0.8472 (0.8476) time: 0.1710 data: 0.0936 max mem: 8452 +Train: [42] [4800/6250] eta: 0:03:59 lr: 0.000082 grad: 0.0898 (0.0927) loss: 0.8482 (0.8476) time: 0.1409 data: 0.0568 max mem: 8452 +Train: [42] [4900/6250] eta: 0:03:43 lr: 0.000082 grad: 0.0926 (0.0928) loss: 0.8512 (0.8476) time: 0.1562 data: 0.0611 max mem: 8452 +Train: [42] [5000/6250] eta: 0:03:26 lr: 0.000082 grad: 0.0986 (0.0928) loss: 0.8448 (0.8476) time: 0.1611 data: 0.0757 max mem: 8452 +Train: [42] [5100/6250] eta: 0:03:09 lr: 0.000082 grad: 0.0904 (0.0929) loss: 0.8439 (0.8475) time: 0.1463 data: 0.0697 max mem: 8452 +Train: [42] [5200/6250] eta: 0:02:53 lr: 0.000082 grad: 0.0944 (0.0929) loss: 0.8446 (0.8476) time: 0.1473 data: 0.0681 max mem: 8452 +Train: [42] [5300/6250] eta: 0:02:36 lr: 0.000082 grad: 0.0939 (0.0930) loss: 0.8447 (0.8475) time: 0.1622 data: 0.0899 max mem: 8452 +Train: [42] [5400/6250] eta: 0:02:19 lr: 0.000082 grad: 0.0914 (0.0930) loss: 0.8514 (0.8475) time: 0.1502 data: 0.0690 max mem: 8452 +Train: [42] [5500/6250] eta: 0:02:03 lr: 0.000082 grad: 0.0921 (0.0931) loss: 0.8450 (0.8474) time: 0.1480 data: 0.0689 max mem: 8452 +Train: [42] [5600/6250] eta: 0:01:47 lr: 0.000082 grad: 0.0973 (0.0931) loss: 0.8454 (0.8474) time: 0.1689 data: 0.0992 max mem: 8452 +Train: [42] [5700/6250] eta: 0:01:30 lr: 0.000082 grad: 0.0905 (0.0931) loss: 0.8516 (0.8474) time: 0.1461 data: 0.0693 max mem: 8452 +Train: [42] [5800/6250] eta: 0:01:13 lr: 0.000082 grad: 0.0954 (0.0931) loss: 0.8497 (0.8473) time: 0.1735 data: 0.0948 max mem: 8452 +Train: [42] [5900/6250] eta: 0:00:57 lr: 0.000082 grad: 0.0907 (0.0932) loss: 0.8429 (0.8472) time: 0.1650 data: 0.0693 max mem: 8452 +Train: [42] [6000/6250] eta: 0:00:41 lr: 0.000082 grad: 0.0897 (0.0932) loss: 0.8456 (0.8472) time: 0.1427 data: 0.0644 max mem: 8452 +Train: [42] [6100/6250] eta: 0:00:24 lr: 0.000082 grad: 0.0880 (0.0932) loss: 0.8497 (0.8472) time: 0.1856 data: 0.1105 max mem: 8452 +Train: [42] [6200/6250] eta: 0:00:08 lr: 0.000082 grad: 0.0958 (0.0933) loss: 0.8416 (0.8471) time: 0.1495 data: 0.0658 max mem: 8452 +Train: [42] [6249/6250] eta: 0:00:00 lr: 0.000082 grad: 0.0898 (0.0933) loss: 0.8305 (0.8471) time: 0.1910 data: 0.1027 max mem: 8452 +Train: [42] Total time: 0:17:13 (0.1654 s / it) +Averaged stats: lr: 0.000082 grad: 0.0898 (0.0933) loss: 0.8305 (0.8471) +Eval (hcp-train-subset): [42] [ 0/62] eta: 0:03:49 loss: 0.8905 (0.8905) time: 3.7025 data: 3.6143 max mem: 8452 +Eval (hcp-train-subset): [42] [61/62] eta: 0:00:00 loss: 0.8746 (0.8767) time: 0.1490 data: 0.1279 max mem: 8452 +Eval (hcp-train-subset): [42] Total time: 0:00:15 (0.2429 s / it) +Averaged stats (hcp-train-subset): loss: 0.8746 (0.8767) +Eval (hcp-val): [42] [ 0/62] eta: 0:05:22 loss: 0.8738 (0.8738) time: 5.2064 data: 5.1803 max mem: 8452 +Eval (hcp-val): [42] [61/62] eta: 0:00:00 loss: 0.8745 (0.8762) time: 0.1341 data: 0.1118 max mem: 8452 +Eval (hcp-val): [42] Total time: 0:00:14 (0.2358 s / it) +Averaged stats (hcp-val): loss: 0.8745 (0.8762) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [43] [ 0/6250] eta: 8:08:29 lr: 0.000082 grad: 0.2817 (0.2817) loss: 0.8809 (0.8809) time: 4.6895 data: 4.4146 max mem: 8452 +Train: [43] [ 100/6250] eta: 0:23:00 lr: 0.000082 grad: 0.0988 (0.1360) loss: 0.8471 (0.8604) time: 0.1802 data: 0.0916 max mem: 8452 +Train: [43] [ 200/6250] eta: 0:20:05 lr: 0.000082 grad: 0.0941 (0.1234) loss: 0.8562 (0.8540) time: 0.1772 data: 0.0789 max mem: 8452 +Train: [43] [ 300/6250] eta: 0:18:39 lr: 0.000082 grad: 0.0939 (0.1145) loss: 0.8460 (0.8509) time: 0.1413 data: 0.0585 max mem: 8452 +Train: [43] [ 400/6250] eta: 0:17:40 lr: 0.000082 grad: 0.0964 (0.1095) loss: 0.8550 (0.8502) time: 0.1514 data: 0.0669 max mem: 8452 +Train: [43] [ 500/6250] eta: 0:16:59 lr: 0.000082 grad: 0.0889 (0.1063) loss: 0.8507 (0.8502) time: 0.1470 data: 0.0537 max mem: 8452 +Train: [43] [ 600/6250] eta: 0:16:31 lr: 0.000082 grad: 0.0819 (0.1037) loss: 0.8536 (0.8500) time: 0.1610 data: 0.0860 max mem: 8452 +Train: [43] [ 700/6250] eta: 0:15:59 lr: 0.000082 grad: 0.0992 (0.1022) loss: 0.8425 (0.8499) time: 0.1694 data: 0.0841 max mem: 8452 +Train: [43] [ 800/6250] eta: 0:15:37 lr: 0.000082 grad: 0.0921 (0.1007) loss: 0.8474 (0.8501) time: 0.1595 data: 0.0775 max mem: 8452 +Train: [43] [ 900/6250] eta: 0:15:13 lr: 0.000082 grad: 0.0788 (0.0995) loss: 0.8563 (0.8507) time: 0.1483 data: 0.0582 max mem: 8452 +Train: [43] [1000/6250] eta: 0:14:49 lr: 0.000081 grad: 0.0872 (0.0981) loss: 0.8587 (0.8511) time: 0.1426 data: 0.0578 max mem: 8452 +Train: [43] [1100/6250] eta: 0:14:22 lr: 0.000081 grad: 0.0877 (0.0972) loss: 0.8500 (0.8511) time: 0.1599 data: 0.0770 max mem: 8452 +Train: [43] [1200/6250] eta: 0:14:00 lr: 0.000081 grad: 0.0936 (0.0977) loss: 0.8504 (0.8512) time: 0.1692 data: 0.0984 max mem: 8452 +Train: [43] [1300/6250] eta: 0:13:40 lr: 0.000081 grad: 0.0847 (0.0972) loss: 0.8539 (0.8512) time: 0.1548 data: 0.0782 max mem: 8452 +Train: [43] [1400/6250] eta: 0:13:18 lr: 0.000081 grad: 0.0861 (0.0965) loss: 0.8580 (0.8512) time: 0.1523 data: 0.0786 max mem: 8452 +Train: [43] [1500/6250] eta: 0:12:57 lr: 0.000081 grad: 0.0865 (0.0962) loss: 0.8507 (0.8511) time: 0.1631 data: 0.0848 max mem: 8452 +Train: [43] [1600/6250] eta: 0:12:35 lr: 0.000081 grad: 0.0860 (0.0955) loss: 0.8410 (0.8510) time: 0.1277 data: 0.0431 max mem: 8452 +Train: [43] [1700/6250] eta: 0:12:21 lr: 0.000081 grad: 0.0823 (0.0951) loss: 0.8579 (0.8509) time: 0.1740 data: 0.0868 max mem: 8452 +Train: [43] [1800/6250] eta: 0:12:07 lr: 0.000081 grad: 0.0838 (0.0945) loss: 0.8443 (0.8508) time: 0.1657 data: 0.0851 max mem: 8452 +Train: [43] [1900/6250] eta: 0:11:47 lr: 0.000081 grad: 0.0855 (0.0942) loss: 0.8493 (0.8508) time: 0.1662 data: 0.0846 max mem: 8452 +Train: [43] [2000/6250] eta: 0:11:30 lr: 0.000081 grad: 0.0810 (0.0938) loss: 0.8508 (0.8508) time: 0.1726 data: 0.0905 max mem: 8452 +Train: [43] [2100/6250] eta: 0:11:14 lr: 0.000081 grad: 0.0871 (0.0936) loss: 0.8540 (0.8507) time: 0.1580 data: 0.0718 max mem: 8452 +Train: [43] [2200/6250] eta: 0:10:57 lr: 0.000081 grad: 0.0858 (0.0935) loss: 0.8521 (0.8506) time: 0.1357 data: 0.0429 max mem: 8452 +Train: [43] [2300/6250] eta: 0:10:40 lr: 0.000081 grad: 0.0896 (0.0934) loss: 0.8456 (0.8505) time: 0.1521 data: 0.0792 max mem: 8452 +Train: [43] [2400/6250] eta: 0:10:22 lr: 0.000081 grad: 0.0847 (0.0932) loss: 0.8422 (0.8505) time: 0.1646 data: 0.0839 max mem: 8452 +Train: [43] [2500/6250] eta: 0:10:05 lr: 0.000081 grad: 0.0844 (0.0931) loss: 0.8541 (0.8504) time: 0.1437 data: 0.0526 max mem: 8452 +Train: [43] [2600/6250] eta: 0:09:48 lr: 0.000081 grad: 0.0860 (0.0929) loss: 0.8472 (0.8504) time: 0.1440 data: 0.0626 max mem: 8452 +Train: [43] [2700/6250] eta: 0:09:32 lr: 0.000081 grad: 0.0862 (0.0928) loss: 0.8542 (0.8504) time: 0.1480 data: 0.0701 max mem: 8452 +Train: [43] [2800/6250] eta: 0:09:16 lr: 0.000081 grad: 0.0916 (0.0929) loss: 0.8367 (0.8503) time: 0.1673 data: 0.0798 max mem: 8452 +Train: [43] [2900/6250] eta: 0:09:03 lr: 0.000081 grad: 0.0885 (0.0928) loss: 0.8516 (0.8502) time: 0.1594 data: 0.0821 max mem: 8452 +Train: [43] [3000/6250] eta: 0:08:46 lr: 0.000081 grad: 0.0942 (0.0928) loss: 0.8508 (0.8502) time: 0.1548 data: 0.0715 max mem: 8452 +Train: [43] [3100/6250] eta: 0:08:32 lr: 0.000081 grad: 0.0893 (0.0928) loss: 0.8411 (0.8502) time: 0.1677 data: 0.0876 max mem: 8452 +Train: [43] [3200/6250] eta: 0:08:16 lr: 0.000081 grad: 0.0883 (0.0928) loss: 0.8512 (0.8501) time: 0.1572 data: 0.0823 max mem: 8452 +Train: [43] [3300/6250] eta: 0:08:00 lr: 0.000081 grad: 0.0936 (0.0928) loss: 0.8469 (0.8499) time: 0.2043 data: 0.1144 max mem: 8452 +Train: [43] [3400/6250] eta: 0:07:44 lr: 0.000081 grad: 0.0874 (0.0927) loss: 0.8541 (0.8499) time: 0.1952 data: 0.1109 max mem: 8452 +Train: [43] [3500/6250] eta: 0:07:27 lr: 0.000081 grad: 0.0897 (0.0927) loss: 0.8456 (0.8499) time: 0.1666 data: 0.0832 max mem: 8452 +Train: [43] [3600/6250] eta: 0:07:12 lr: 0.000081 grad: 0.0920 (0.0928) loss: 0.8505 (0.8498) time: 0.1638 data: 0.0806 max mem: 8452 +Train: [43] [3700/6250] eta: 0:06:55 lr: 0.000081 grad: 0.0875 (0.0928) loss: 0.8442 (0.8497) time: 0.1481 data: 0.0621 max mem: 8452 +Train: [43] [3800/6250] eta: 0:06:38 lr: 0.000081 grad: 0.0865 (0.0929) loss: 0.8426 (0.8496) time: 0.1543 data: 0.0658 max mem: 8452 +Train: [43] [3900/6250] eta: 0:06:22 lr: 0.000081 grad: 0.0908 (0.0930) loss: 0.8481 (0.8494) time: 0.1500 data: 0.0579 max mem: 8452 +Train: [43] [4000/6250] eta: 0:06:05 lr: 0.000081 grad: 0.0942 (0.0931) loss: 0.8407 (0.8492) time: 0.1505 data: 0.0611 max mem: 8452 +Train: [43] [4100/6250] eta: 0:05:49 lr: 0.000081 grad: 0.0931 (0.0931) loss: 0.8383 (0.8490) time: 0.2030 data: 0.1333 max mem: 8452 +Train: [43] [4200/6250] eta: 0:05:32 lr: 0.000080 grad: 0.0947 (0.0932) loss: 0.8376 (0.8488) time: 0.1469 data: 0.0664 max mem: 8452 +Train: [43] [4300/6250] eta: 0:05:16 lr: 0.000080 grad: 0.0913 (0.0933) loss: 0.8438 (0.8486) time: 0.1531 data: 0.0700 max mem: 8452 +Train: [43] [4400/6250] eta: 0:05:00 lr: 0.000080 grad: 0.0956 (0.0934) loss: 0.8385 (0.8485) time: 0.1550 data: 0.0658 max mem: 8452 +Train: [43] [4500/6250] eta: 0:04:44 lr: 0.000080 grad: 0.0961 (0.0935) loss: 0.8312 (0.8482) time: 0.1809 data: 0.0945 max mem: 8452 +Train: [43] [4600/6250] eta: 0:04:28 lr: 0.000080 grad: 0.0955 (0.0936) loss: 0.8335 (0.8479) time: 0.1847 data: 0.0949 max mem: 8452 +Train: [43] [4700/6250] eta: 0:04:12 lr: 0.000080 grad: 0.0952 (0.0937) loss: 0.8441 (0.8477) time: 0.1722 data: 0.0911 max mem: 8452 +Train: [43] [4800/6250] eta: 0:03:56 lr: 0.000080 grad: 0.0910 (0.0938) loss: 0.8379 (0.8475) time: 0.1790 data: 0.1076 max mem: 8452 +Train: [43] [4900/6250] eta: 0:03:39 lr: 0.000080 grad: 0.0891 (0.0938) loss: 0.8452 (0.8474) time: 0.1433 data: 0.0625 max mem: 8452 +Train: [43] [5000/6250] eta: 0:03:23 lr: 0.000080 grad: 0.0950 (0.0940) loss: 0.8361 (0.8472) time: 0.1506 data: 0.0571 max mem: 8452 +Train: [43] [5100/6250] eta: 0:03:06 lr: 0.000080 grad: 0.1026 (0.0941) loss: 0.8439 (0.8471) time: 0.1669 data: 0.0770 max mem: 8452 +Train: [43] [5200/6250] eta: 0:02:50 lr: 0.000080 grad: 0.0953 (0.0942) loss: 0.8396 (0.8469) time: 0.1470 data: 0.0493 max mem: 8452 +Train: [43] [5300/6250] eta: 0:02:34 lr: 0.000080 grad: 0.0874 (0.0942) loss: 0.8487 (0.8469) time: 0.1407 data: 0.0635 max mem: 8452 +Train: [43] [5400/6250] eta: 0:02:17 lr: 0.000080 grad: 0.0943 (0.0942) loss: 0.8451 (0.8468) time: 0.1264 data: 0.0448 max mem: 8452 +Train: [43] [5500/6250] eta: 0:02:01 lr: 0.000080 grad: 0.0962 (0.0943) loss: 0.8429 (0.8467) time: 0.1607 data: 0.0827 max mem: 8452 +Train: [43] [5600/6250] eta: 0:01:45 lr: 0.000080 grad: 0.0908 (0.0943) loss: 0.8279 (0.8465) time: 0.1451 data: 0.0616 max mem: 8452 +Train: [43] [5700/6250] eta: 0:01:28 lr: 0.000080 grad: 0.0950 (0.0944) loss: 0.8321 (0.8463) time: 0.1842 data: 0.1034 max mem: 8452 +Train: [43] [5800/6250] eta: 0:01:12 lr: 0.000080 grad: 0.0983 (0.0945) loss: 0.8337 (0.8462) time: 0.1576 data: 0.0739 max mem: 8452 +Train: [43] [5900/6250] eta: 0:00:56 lr: 0.000080 grad: 0.0948 (0.0945) loss: 0.8392 (0.8460) time: 0.1823 data: 0.1032 max mem: 8452 +Train: [43] [6000/6250] eta: 0:00:40 lr: 0.000080 grad: 0.0931 (0.0946) loss: 0.8465 (0.8459) time: 0.1510 data: 0.0651 max mem: 8452 +Train: [43] [6100/6250] eta: 0:00:24 lr: 0.000080 grad: 0.0974 (0.0947) loss: 0.8426 (0.8458) time: 0.1488 data: 0.0719 max mem: 8452 +Train: [43] [6200/6250] eta: 0:00:08 lr: 0.000080 grad: 0.0893 (0.0948) loss: 0.8446 (0.8457) time: 0.1662 data: 0.0868 max mem: 8452 +Train: [43] [6249/6250] eta: 0:00:00 lr: 0.000080 grad: 0.0919 (0.0948) loss: 0.8446 (0.8457) time: 0.1799 data: 0.1001 max mem: 8452 +Train: [43] Total time: 0:16:54 (0.1623 s / it) +Averaged stats: lr: 0.000080 grad: 0.0919 (0.0948) loss: 0.8446 (0.8457) +Eval (hcp-train-subset): [43] [ 0/62] eta: 0:03:26 loss: 0.8923 (0.8923) time: 3.3268 data: 3.2473 max mem: 8452 +Eval (hcp-train-subset): [43] [61/62] eta: 0:00:00 loss: 0.8773 (0.8770) time: 0.1459 data: 0.1233 max mem: 8452 +Eval (hcp-train-subset): [43] Total time: 0:00:14 (0.2287 s / it) +Averaged stats (hcp-train-subset): loss: 0.8773 (0.8770) +Eval (hcp-val): [43] [ 0/62] eta: 0:06:35 loss: 0.8743 (0.8743) time: 6.3825 data: 6.3549 max mem: 8452 +Eval (hcp-val): [43] [61/62] eta: 0:00:00 loss: 0.8758 (0.8766) time: 0.1133 data: 0.0900 max mem: 8452 +Eval (hcp-val): [43] Total time: 0:00:14 (0.2341 s / it) +Averaged stats (hcp-val): loss: 0.8758 (0.8766) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [44] [ 0/6250] eta: 9:31:22 lr: 0.000080 grad: 0.2827 (0.2827) loss: 0.8578 (0.8578) time: 5.4852 data: 5.3000 max mem: 8452 +Train: [44] [ 100/6250] eta: 0:22:06 lr: 0.000080 grad: 0.1158 (0.1302) loss: 0.8458 (0.8628) time: 0.1521 data: 0.0507 max mem: 8452 +Train: [44] [ 200/6250] eta: 0:19:32 lr: 0.000080 grad: 0.0906 (0.1162) loss: 0.8644 (0.8585) time: 0.1999 data: 0.1119 max mem: 8452 +Train: [44] [ 300/6250] eta: 0:18:05 lr: 0.000080 grad: 0.0928 (0.1093) loss: 0.8572 (0.8567) time: 0.1660 data: 0.0715 max mem: 8452 +Train: [44] [ 400/6250] eta: 0:17:11 lr: 0.000080 grad: 0.0807 (0.1058) loss: 0.8586 (0.8556) time: 0.1678 data: 0.0708 max mem: 8452 +Train: [44] [ 500/6250] eta: 0:16:26 lr: 0.000080 grad: 0.0894 (0.1031) loss: 0.8558 (0.8550) time: 0.1363 data: 0.0556 max mem: 8452 +Train: [44] [ 600/6250] eta: 0:15:51 lr: 0.000080 grad: 0.0842 (0.1015) loss: 0.8555 (0.8542) time: 0.1546 data: 0.0464 max mem: 8452 +Train: [44] [ 700/6250] eta: 0:15:29 lr: 0.000080 grad: 0.0951 (0.1015) loss: 0.8476 (0.8529) time: 0.1667 data: 0.0808 max mem: 8452 +Train: [44] [ 800/6250] eta: 0:15:10 lr: 0.000080 grad: 0.0890 (0.1005) loss: 0.8550 (0.8524) time: 0.1590 data: 0.0812 max mem: 8452 +Train: [44] [ 900/6250] eta: 0:14:46 lr: 0.000080 grad: 0.0908 (0.1000) loss: 0.8437 (0.8517) time: 0.1682 data: 0.0895 max mem: 8452 +Train: [44] [1000/6250] eta: 0:14:26 lr: 0.000080 grad: 0.0837 (0.0992) loss: 0.8597 (0.8512) time: 0.1649 data: 0.0883 max mem: 8452 +Train: [44] [1100/6250] eta: 0:14:06 lr: 0.000079 grad: 0.0830 (0.0982) loss: 0.8514 (0.8510) time: 0.1352 data: 0.0530 max mem: 8452 +Train: [44] [1200/6250] eta: 0:13:47 lr: 0.000079 grad: 0.0911 (0.0978) loss: 0.8480 (0.8506) time: 0.1519 data: 0.0636 max mem: 8452 +Train: [44] [1300/6250] eta: 0:13:26 lr: 0.000079 grad: 0.0940 (0.0975) loss: 0.8405 (0.8501) time: 0.1593 data: 0.0684 max mem: 8452 +Train: [44] [1400/6250] eta: 0:13:06 lr: 0.000079 grad: 0.0919 (0.0972) loss: 0.8427 (0.8496) time: 0.1509 data: 0.0611 max mem: 8452 +Train: [44] [1500/6250] eta: 0:12:48 lr: 0.000079 grad: 0.0875 (0.0970) loss: 0.8466 (0.8492) time: 0.1791 data: 0.0919 max mem: 8452 +Train: [44] [1600/6250] eta: 0:12:32 lr: 0.000079 grad: 0.0927 (0.0968) loss: 0.8374 (0.8488) time: 0.1593 data: 0.0653 max mem: 8452 +Train: [44] [1700/6250] eta: 0:12:21 lr: 0.000079 grad: 0.0960 (0.0967) loss: 0.8332 (0.8483) time: 0.1894 data: 0.1095 max mem: 8452 +Train: [44] [1800/6250] eta: 0:12:08 lr: 0.000079 grad: 0.0912 (0.0967) loss: 0.8419 (0.8480) time: 0.1707 data: 0.0830 max mem: 8452 +Train: [44] [1900/6250] eta: 0:11:53 lr: 0.000079 grad: 0.0917 (0.0969) loss: 0.8445 (0.8476) time: 0.1593 data: 0.0795 max mem: 8452 +Train: [44] [2000/6250] eta: 0:11:41 lr: 0.000079 grad: 0.0841 (0.0968) loss: 0.8455 (0.8474) time: 0.1707 data: 0.0851 max mem: 8452 +Train: [44] [2100/6250] eta: 0:11:27 lr: 0.000079 grad: 0.0975 (0.0968) loss: 0.8449 (0.8470) time: 0.1926 data: 0.1192 max mem: 8452 +Train: [44] [2200/6250] eta: 0:11:14 lr: 0.000079 grad: 0.0946 (0.0967) loss: 0.8459 (0.8467) time: 0.1771 data: 0.1026 max mem: 8452 +Train: [44] [2300/6250] eta: 0:11:00 lr: 0.000079 grad: 0.0945 (0.0967) loss: 0.8444 (0.8465) time: 0.2077 data: 0.1209 max mem: 8452 +Train: [44] [2400/6250] eta: 0:10:42 lr: 0.000079 grad: 0.0883 (0.0966) loss: 0.8435 (0.8463) time: 0.1685 data: 0.0791 max mem: 8452 +Train: [44] [2500/6250] eta: 0:10:26 lr: 0.000079 grad: 0.0950 (0.0968) loss: 0.8401 (0.8460) time: 0.1494 data: 0.0641 max mem: 8452 +Train: [44] [2600/6250] eta: 0:10:08 lr: 0.000079 grad: 0.0984 (0.0967) loss: 0.8369 (0.8459) time: 0.1733 data: 0.0855 max mem: 8452 +Train: [44] [2700/6250] eta: 0:09:52 lr: 0.000079 grad: 0.0913 (0.0966) loss: 0.8407 (0.8457) time: 0.1845 data: 0.1074 max mem: 8452 +Train: [44] [2800/6250] eta: 0:09:38 lr: 0.000079 grad: 0.0894 (0.0965) loss: 0.8437 (0.8456) time: 0.2159 data: 0.1205 max mem: 8452 +Train: [44] [2900/6250] eta: 0:09:20 lr: 0.000079 grad: 0.0884 (0.0964) loss: 0.8431 (0.8454) time: 0.1799 data: 0.0851 max mem: 8452 +Train: [44] [3000/6250] eta: 0:09:05 lr: 0.000079 grad: 0.0931 (0.0963) loss: 0.8399 (0.8452) time: 0.1806 data: 0.1180 max mem: 8452 +Train: [44] [3100/6250] eta: 0:08:47 lr: 0.000079 grad: 0.0947 (0.0963) loss: 0.8406 (0.8451) time: 0.1671 data: 0.0916 max mem: 8452 +Train: [44] [3200/6250] eta: 0:08:30 lr: 0.000079 grad: 0.0876 (0.0961) loss: 0.8448 (0.8451) time: 0.1488 data: 0.0764 max mem: 8452 +Train: [44] [3300/6250] eta: 0:08:14 lr: 0.000079 grad: 0.0945 (0.0960) loss: 0.8417 (0.8451) time: 0.1833 data: 0.1088 max mem: 8452 +Train: [44] [3400/6250] eta: 0:07:58 lr: 0.000079 grad: 0.0993 (0.0960) loss: 0.8446 (0.8451) time: 0.1748 data: 0.0790 max mem: 8452 +Train: [44] [3500/6250] eta: 0:07:42 lr: 0.000079 grad: 0.0891 (0.0960) loss: 0.8520 (0.8449) time: 0.1298 data: 0.0417 max mem: 8452 +Train: [44] [3600/6250] eta: 0:07:25 lr: 0.000079 grad: 0.0955 (0.0959) loss: 0.8443 (0.8450) time: 0.1562 data: 0.0705 max mem: 8452 +Train: [44] [3700/6250] eta: 0:07:08 lr: 0.000079 grad: 0.0968 (0.0958) loss: 0.8443 (0.8450) time: 0.1522 data: 0.0649 max mem: 8452 +Train: [44] [3800/6250] eta: 0:06:51 lr: 0.000079 grad: 0.0942 (0.0958) loss: 0.8473 (0.8451) time: 0.1408 data: 0.0483 max mem: 8452 +Train: [44] [3900/6250] eta: 0:06:34 lr: 0.000079 grad: 0.0890 (0.0957) loss: 0.8452 (0.8452) time: 0.1596 data: 0.0823 max mem: 8452 +Train: [44] [4000/6250] eta: 0:06:16 lr: 0.000079 grad: 0.0932 (0.0956) loss: 0.8515 (0.8453) time: 0.1608 data: 0.0780 max mem: 8452 +Train: [44] [4100/6250] eta: 0:05:59 lr: 0.000079 grad: 0.0945 (0.0956) loss: 0.8428 (0.8453) time: 0.1762 data: 0.0937 max mem: 8452 +Train: [44] [4200/6250] eta: 0:05:42 lr: 0.000078 grad: 0.0898 (0.0955) loss: 0.8440 (0.8453) time: 0.1204 data: 0.0207 max mem: 8452 +Train: [44] [4300/6250] eta: 0:05:25 lr: 0.000078 grad: 0.0853 (0.0955) loss: 0.8539 (0.8454) time: 0.1824 data: 0.0934 max mem: 8452 +Train: [44] [4400/6250] eta: 0:05:09 lr: 0.000078 grad: 0.0955 (0.0955) loss: 0.8459 (0.8454) time: 0.1734 data: 0.0884 max mem: 8452 +Train: [44] [4500/6250] eta: 0:04:52 lr: 0.000078 grad: 0.0954 (0.0955) loss: 0.8461 (0.8454) time: 0.1486 data: 0.0754 max mem: 8452 +Train: [44] [4600/6250] eta: 0:04:35 lr: 0.000078 grad: 0.0892 (0.0954) loss: 0.8519 (0.8454) time: 0.1440 data: 0.0685 max mem: 8452 +Train: [44] [4700/6250] eta: 0:04:18 lr: 0.000078 grad: 0.0931 (0.0954) loss: 0.8500 (0.8455) time: 0.1664 data: 0.0792 max mem: 8452 +Train: [44] [4800/6250] eta: 0:04:02 lr: 0.000078 grad: 0.0878 (0.0953) loss: 0.8504 (0.8455) time: 0.1648 data: 0.0773 max mem: 8452 +Train: [44] [4900/6250] eta: 0:03:45 lr: 0.000078 grad: 0.0893 (0.0953) loss: 0.8492 (0.8456) time: 0.1759 data: 0.0865 max mem: 8452 +Train: [44] [5000/6250] eta: 0:03:28 lr: 0.000078 grad: 0.0861 (0.0952) loss: 0.8464 (0.8456) time: 0.2001 data: 0.1296 max mem: 8452 +Train: [44] [5100/6250] eta: 0:03:11 lr: 0.000078 grad: 0.0937 (0.0952) loss: 0.8488 (0.8457) time: 0.1548 data: 0.0622 max mem: 8452 +Train: [44] [5200/6250] eta: 0:02:54 lr: 0.000078 grad: 0.0859 (0.0952) loss: 0.8513 (0.8457) time: 0.1510 data: 0.0620 max mem: 8452 +Train: [44] [5300/6250] eta: 0:02:37 lr: 0.000078 grad: 0.0874 (0.0951) loss: 0.8478 (0.8458) time: 0.1520 data: 0.0612 max mem: 8452 +Train: [44] [5400/6250] eta: 0:02:21 lr: 0.000078 grad: 0.0893 (0.0951) loss: 0.8512 (0.8458) time: 0.1432 data: 0.0491 max mem: 8452 +Train: [44] [5500/6250] eta: 0:02:04 lr: 0.000078 grad: 0.0975 (0.0951) loss: 0.8479 (0.8459) time: 0.1549 data: 0.0652 max mem: 8452 +Train: [44] [5600/6250] eta: 0:01:47 lr: 0.000078 grad: 0.0857 (0.0952) loss: 0.8499 (0.8459) time: 0.1470 data: 0.0588 max mem: 8452 +Train: [44] [5700/6250] eta: 0:01:30 lr: 0.000078 grad: 0.0908 (0.0952) loss: 0.8461 (0.8459) time: 0.1252 data: 0.0457 max mem: 8452 +Train: [44] [5800/6250] eta: 0:01:14 lr: 0.000078 grad: 0.0909 (0.0951) loss: 0.8497 (0.8460) time: 0.1495 data: 0.0759 max mem: 8452 +Train: [44] [5900/6250] eta: 0:00:57 lr: 0.000078 grad: 0.0897 (0.0951) loss: 0.8464 (0.8460) time: 0.1474 data: 0.0688 max mem: 8452 +Train: [44] [6000/6250] eta: 0:00:41 lr: 0.000078 grad: 0.0868 (0.0951) loss: 0.8518 (0.8460) time: 0.1225 data: 0.0420 max mem: 8452 +Train: [44] [6100/6250] eta: 0:00:24 lr: 0.000078 grad: 0.0863 (0.0950) loss: 0.8477 (0.8460) time: 0.1479 data: 0.0552 max mem: 8452 +Train: [44] [6200/6250] eta: 0:00:08 lr: 0.000078 grad: 0.0915 (0.0950) loss: 0.8475 (0.8460) time: 0.1944 data: 0.1083 max mem: 8452 +Train: [44] [6249/6250] eta: 0:00:00 lr: 0.000078 grad: 0.0928 (0.0950) loss: 0.8522 (0.8460) time: 0.1704 data: 0.0945 max mem: 8452 +Train: [44] Total time: 0:17:13 (0.1654 s / it) +Averaged stats: lr: 0.000078 grad: 0.0928 (0.0950) loss: 0.8522 (0.8460) +Eval (hcp-train-subset): [44] [ 0/62] eta: 0:04:59 loss: 0.8823 (0.8823) time: 4.8350 data: 4.7971 max mem: 8452 +Eval (hcp-train-subset): [44] [61/62] eta: 0:00:00 loss: 0.8735 (0.8750) time: 0.1399 data: 0.1191 max mem: 8452 +Eval (hcp-train-subset): [44] Total time: 0:00:14 (0.2354 s / it) +Averaged stats (hcp-train-subset): loss: 0.8735 (0.8750) +Making plots (hcp-train-subset): example=14 +Eval (hcp-val): [44] [ 0/62] eta: 0:04:20 loss: 0.8749 (0.8749) time: 4.2030 data: 4.1210 max mem: 8452 +Eval (hcp-val): [44] [61/62] eta: 0:00:00 loss: 0.8749 (0.8759) time: 0.1341 data: 0.1119 max mem: 8452 +Eval (hcp-val): [44] Total time: 0:00:15 (0.2453 s / it) +Averaged stats (hcp-val): loss: 0.8749 (0.8759) +Making plots (hcp-val): example=45 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [45] [ 0/6250] eta: 8:57:46 lr: 0.000078 grad: 0.0986 (0.0986) loss: 0.8469 (0.8469) time: 5.1627 data: 4.8670 max mem: 8452 +Train: [45] [ 100/6250] eta: 0:23:40 lr: 0.000078 grad: 0.1029 (0.1146) loss: 0.8671 (0.8673) time: 0.1875 data: 0.0929 max mem: 8452 +Train: [45] [ 200/6250] eta: 0:19:41 lr: 0.000078 grad: 0.0836 (0.1095) loss: 0.8657 (0.8662) time: 0.1773 data: 0.0870 max mem: 8452 +Train: [45] [ 300/6250] eta: 0:18:13 lr: 0.000078 grad: 0.0781 (0.1016) loss: 0.8563 (0.8646) time: 0.1588 data: 0.0639 max mem: 8452 +Train: [45] [ 400/6250] eta: 0:17:26 lr: 0.000078 grad: 0.0998 (0.0995) loss: 0.8483 (0.8619) time: 0.1610 data: 0.0685 max mem: 8452 +Train: [45] [ 500/6250] eta: 0:16:42 lr: 0.000078 grad: 0.0862 (0.0990) loss: 0.8533 (0.8594) time: 0.1421 data: 0.0664 max mem: 8452 +Train: [45] [ 600/6250] eta: 0:16:08 lr: 0.000078 grad: 0.0935 (0.0985) loss: 0.8441 (0.8575) time: 0.1494 data: 0.0642 max mem: 8452 +Train: [45] [ 700/6250] eta: 0:15:42 lr: 0.000078 grad: 0.0919 (0.0980) loss: 0.8475 (0.8561) time: 0.1683 data: 0.0676 max mem: 8452 +Train: [45] [ 800/6250] eta: 0:15:19 lr: 0.000078 grad: 0.0932 (0.0989) loss: 0.8458 (0.8545) time: 0.1566 data: 0.0672 max mem: 8452 +Train: [45] [ 900/6250] eta: 0:15:00 lr: 0.000078 grad: 0.0926 (0.0987) loss: 0.8466 (0.8534) time: 0.1687 data: 0.0823 max mem: 8452 +Train: [45] [1000/6250] eta: 0:14:42 lr: 0.000078 grad: 0.0891 (0.0981) loss: 0.8443 (0.8528) time: 0.1604 data: 0.0747 max mem: 8452 +Train: [45] [1100/6250] eta: 0:14:17 lr: 0.000077 grad: 0.0918 (0.0978) loss: 0.8460 (0.8520) time: 0.1322 data: 0.0513 max mem: 8452 +Train: [45] [1200/6250] eta: 0:14:02 lr: 0.000077 grad: 0.0915 (0.0976) loss: 0.8486 (0.8514) time: 0.1472 data: 0.0635 max mem: 8452 +Train: [45] [1300/6250] eta: 0:13:42 lr: 0.000077 grad: 0.0942 (0.0973) loss: 0.8496 (0.8510) time: 0.1462 data: 0.0694 max mem: 8452 +Train: [45] [1400/6250] eta: 0:13:24 lr: 0.000077 grad: 0.0880 (0.0970) loss: 0.8417 (0.8505) time: 0.1455 data: 0.0581 max mem: 8452 +Train: [45] [1500/6250] eta: 0:13:04 lr: 0.000077 grad: 0.0938 (0.0968) loss: 0.8366 (0.8499) time: 0.1561 data: 0.0761 max mem: 8452 +Train: [45] [1600/6250] eta: 0:12:46 lr: 0.000077 grad: 0.0926 (0.0967) loss: 0.8489 (0.8495) time: 0.1579 data: 0.0668 max mem: 8452 +Train: [45] [1700/6250] eta: 0:12:33 lr: 0.000077 grad: 0.0885 (0.0966) loss: 0.8490 (0.8493) time: 0.1780 data: 0.1007 max mem: 8452 +Train: [45] [1800/6250] eta: 0:12:15 lr: 0.000077 grad: 0.0908 (0.0966) loss: 0.8468 (0.8489) time: 0.1629 data: 0.0871 max mem: 8452 +Train: [45] [1900/6250] eta: 0:11:55 lr: 0.000077 grad: 0.0931 (0.0965) loss: 0.8439 (0.8485) time: 0.1462 data: 0.0731 max mem: 8452 +Train: [45] [2000/6250] eta: 0:11:40 lr: 0.000077 grad: 0.0913 (0.0963) loss: 0.8437 (0.8481) time: 0.1788 data: 0.0846 max mem: 8452 +Train: [45] [2100/6250] eta: 0:11:25 lr: 0.000077 grad: 0.0931 (0.0962) loss: 0.8408 (0.8477) time: 0.1614 data: 0.0772 max mem: 8452 +Train: [45] [2200/6250] eta: 0:11:10 lr: 0.000077 grad: 0.1005 (0.0964) loss: 0.8383 (0.8474) time: 0.1885 data: 0.1114 max mem: 8452 +Train: [45] [2300/6250] eta: 0:10:54 lr: 0.000077 grad: 0.0938 (0.0964) loss: 0.8374 (0.8471) time: 0.1676 data: 0.0888 max mem: 8452 +Train: [45] [2400/6250] eta: 0:10:37 lr: 0.000077 grad: 0.0916 (0.0963) loss: 0.8420 (0.8470) time: 0.1541 data: 0.0724 max mem: 8452 +Train: [45] [2500/6250] eta: 0:10:21 lr: 0.000077 grad: 0.0954 (0.0963) loss: 0.8401 (0.8467) time: 0.1529 data: 0.0788 max mem: 8452 +Train: [45] [2600/6250] eta: 0:10:05 lr: 0.000077 grad: 0.0932 (0.0962) loss: 0.8394 (0.8465) time: 0.1642 data: 0.0822 max mem: 8452 +Train: [45] [2700/6250] eta: 0:09:47 lr: 0.000077 grad: 0.0926 (0.0961) loss: 0.8408 (0.8465) time: 0.1708 data: 0.0865 max mem: 8452 +Train: [45] [2800/6250] eta: 0:09:31 lr: 0.000077 grad: 0.0961 (0.0961) loss: 0.8393 (0.8464) time: 0.1821 data: 0.1008 max mem: 8452 +Train: [45] [2900/6250] eta: 0:09:14 lr: 0.000077 grad: 0.0878 (0.0961) loss: 0.8463 (0.8464) time: 0.1559 data: 0.0672 max mem: 8452 +Train: [45] [3000/6250] eta: 0:08:58 lr: 0.000077 grad: 0.0900 (0.0961) loss: 0.8517 (0.8464) time: 0.2149 data: 0.1533 max mem: 8452 +Train: [45] [3100/6250] eta: 0:08:42 lr: 0.000077 grad: 0.0874 (0.0960) loss: 0.8447 (0.8464) time: 0.2116 data: 0.1312 max mem: 8452 +Train: [45] [3200/6250] eta: 0:08:24 lr: 0.000077 grad: 0.0953 (0.0959) loss: 0.8383 (0.8463) time: 0.1453 data: 0.0636 max mem: 8452 +Train: [45] [3300/6250] eta: 0:08:08 lr: 0.000077 grad: 0.0914 (0.0959) loss: 0.8412 (0.8463) time: 0.1844 data: 0.1091 max mem: 8452 +Train: [45] [3400/6250] eta: 0:07:51 lr: 0.000077 grad: 0.0923 (0.0958) loss: 0.8470 (0.8463) time: 0.1384 data: 0.0505 max mem: 8452 +Train: [45] [3500/6250] eta: 0:07:35 lr: 0.000077 grad: 0.0914 (0.0958) loss: 0.8486 (0.8463) time: 0.1595 data: 0.0752 max mem: 8452 +Train: [45] [3600/6250] eta: 0:07:18 lr: 0.000077 grad: 0.1014 (0.0958) loss: 0.8448 (0.8463) time: 0.1557 data: 0.0725 max mem: 8452 +Train: [45] [3700/6250] eta: 0:07:02 lr: 0.000077 grad: 0.0951 (0.0958) loss: 0.8479 (0.8463) time: 0.1527 data: 0.0722 max mem: 8452 +Train: [45] [3800/6250] eta: 0:06:44 lr: 0.000077 grad: 0.0891 (0.0957) loss: 0.8506 (0.8463) time: 0.1461 data: 0.0621 max mem: 8452 +Train: [45] [3900/6250] eta: 0:06:27 lr: 0.000077 grad: 0.0880 (0.0956) loss: 0.8501 (0.8464) time: 0.1543 data: 0.0768 max mem: 8452 +Train: [45] [4000/6250] eta: 0:06:10 lr: 0.000077 grad: 0.0896 (0.0955) loss: 0.8494 (0.8464) time: 0.1557 data: 0.0636 max mem: 8452 +Train: [45] [4100/6250] eta: 0:05:53 lr: 0.000077 grad: 0.0943 (0.0955) loss: 0.8573 (0.8464) time: 0.1642 data: 0.0822 max mem: 8452 +Train: [45] [4200/6250] eta: 0:05:36 lr: 0.000076 grad: 0.0941 (0.0955) loss: 0.8427 (0.8464) time: 0.1498 data: 0.0655 max mem: 8452 +Train: [45] [4300/6250] eta: 0:05:20 lr: 0.000076 grad: 0.0924 (0.0955) loss: 0.8461 (0.8464) time: 0.1384 data: 0.0496 max mem: 8452 +Train: [45] [4400/6250] eta: 0:05:03 lr: 0.000076 grad: 0.0912 (0.0955) loss: 0.8470 (0.8463) time: 0.1577 data: 0.0947 max mem: 8452 +Train: [45] [4500/6250] eta: 0:04:46 lr: 0.000076 grad: 0.0912 (0.0954) loss: 0.8439 (0.8463) time: 0.1424 data: 0.0652 max mem: 8452 +Train: [45] [4600/6250] eta: 0:04:30 lr: 0.000076 grad: 0.0960 (0.0954) loss: 0.8404 (0.8464) time: 0.1572 data: 0.0893 max mem: 8452 +Train: [45] [4700/6250] eta: 0:04:13 lr: 0.000076 grad: 0.0882 (0.0954) loss: 0.8455 (0.8463) time: 0.1812 data: 0.0978 max mem: 8452 +Train: [45] [4800/6250] eta: 0:03:57 lr: 0.000076 grad: 0.0904 (0.0953) loss: 0.8468 (0.8463) time: 0.1320 data: 0.0588 max mem: 8452 +Train: [45] [4900/6250] eta: 0:03:40 lr: 0.000076 grad: 0.0953 (0.0953) loss: 0.8481 (0.8462) time: 0.1547 data: 0.0665 max mem: 8452 +Train: [45] [5000/6250] eta: 0:03:24 lr: 0.000076 grad: 0.0941 (0.0953) loss: 0.8428 (0.8462) time: 0.1573 data: 0.0822 max mem: 8452 +Train: [45] [5100/6250] eta: 0:03:08 lr: 0.000076 grad: 0.0939 (0.0953) loss: 0.8446 (0.8461) time: 0.1673 data: 0.0811 max mem: 8452 +Train: [45] [5200/6250] eta: 0:02:52 lr: 0.000076 grad: 0.0923 (0.0953) loss: 0.8378 (0.8461) time: 0.1819 data: 0.1009 max mem: 8452 +Train: [45] [5300/6250] eta: 0:02:36 lr: 0.000076 grad: 0.0974 (0.0953) loss: 0.8422 (0.8460) time: 0.1704 data: 0.0821 max mem: 8452 +Train: [45] [5400/6250] eta: 0:02:19 lr: 0.000076 grad: 0.0962 (0.0953) loss: 0.8489 (0.8459) time: 0.1514 data: 0.0605 max mem: 8452 +Train: [45] [5500/6250] eta: 0:02:03 lr: 0.000076 grad: 0.0859 (0.0953) loss: 0.8466 (0.8458) time: 0.1713 data: 0.0630 max mem: 8452 +Train: [45] [5600/6250] eta: 0:01:47 lr: 0.000076 grad: 0.0948 (0.0953) loss: 0.8416 (0.8457) time: 0.1191 data: 0.0389 max mem: 8452 +Train: [45] [5700/6250] eta: 0:01:30 lr: 0.000076 grad: 0.0867 (0.0952) loss: 0.8524 (0.8457) time: 0.1441 data: 0.0522 max mem: 8452 +Train: [45] [5800/6250] eta: 0:01:14 lr: 0.000076 grad: 0.0920 (0.0952) loss: 0.8411 (0.8456) time: 0.1561 data: 0.0790 max mem: 8452 +Train: [45] [5900/6250] eta: 0:00:57 lr: 0.000076 grad: 0.0895 (0.0952) loss: 0.8513 (0.8456) time: 0.1360 data: 0.0583 max mem: 8452 +Train: [45] [6000/6250] eta: 0:00:41 lr: 0.000076 grad: 0.0905 (0.0951) loss: 0.8464 (0.8456) time: 0.1405 data: 0.0559 max mem: 8452 +Train: [45] [6100/6250] eta: 0:00:24 lr: 0.000076 grad: 0.0890 (0.0951) loss: 0.8495 (0.8456) time: 0.1557 data: 0.0704 max mem: 8452 +Train: [45] [6200/6250] eta: 0:00:08 lr: 0.000076 grad: 0.0896 (0.0951) loss: 0.8519 (0.8456) time: 0.1979 data: 0.1254 max mem: 8452 +Train: [45] [6249/6250] eta: 0:00:00 lr: 0.000076 grad: 0.0866 (0.0950) loss: 0.8565 (0.8456) time: 0.1466 data: 0.0581 max mem: 8452 +Train: [45] Total time: 0:17:09 (0.1648 s / it) +Averaged stats: lr: 0.000076 grad: 0.0866 (0.0950) loss: 0.8565 (0.8456) +Eval (hcp-train-subset): [45] [ 0/62] eta: 0:05:54 loss: 0.8880 (0.8880) time: 5.7218 data: 5.6938 max mem: 8452 +Eval (hcp-train-subset): [45] [61/62] eta: 0:00:00 loss: 0.8740 (0.8753) time: 0.1400 data: 0.1183 max mem: 8452 +Eval (hcp-train-subset): [45] Total time: 0:00:14 (0.2359 s / it) +Averaged stats (hcp-train-subset): loss: 0.8740 (0.8753) +Eval (hcp-val): [45] [ 0/62] eta: 0:04:16 loss: 0.8758 (0.8758) time: 4.1291 data: 4.0396 max mem: 8452 +Eval (hcp-val): [45] [61/62] eta: 0:00:00 loss: 0.8744 (0.8760) time: 0.1386 data: 0.1160 max mem: 8452 +Eval (hcp-val): [45] Total time: 0:00:14 (0.2285 s / it) +Averaged stats (hcp-val): loss: 0.8744 (0.8760) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [46] [ 0/6250] eta: 10:13:33 lr: 0.000076 grad: 0.1433 (0.1433) loss: 0.8580 (0.8580) time: 5.8901 data: 5.7122 max mem: 8452 +Train: [46] [ 100/6250] eta: 0:23:37 lr: 0.000076 grad: 0.0950 (0.1145) loss: 0.8744 (0.8711) time: 0.1685 data: 0.0679 max mem: 8452 +Train: [46] [ 200/6250] eta: 0:20:55 lr: 0.000076 grad: 0.0945 (0.1081) loss: 0.8484 (0.8647) time: 0.1667 data: 0.0781 max mem: 8452 +Train: [46] [ 300/6250] eta: 0:19:30 lr: 0.000076 grad: 0.0917 (0.1091) loss: 0.8527 (0.8587) time: 0.1587 data: 0.0568 max mem: 8452 +Train: [46] [ 400/6250] eta: 0:18:39 lr: 0.000076 grad: 0.0968 (0.1077) loss: 0.8340 (0.8546) time: 0.1951 data: 0.1146 max mem: 8452 +Train: [46] [ 500/6250] eta: 0:17:59 lr: 0.000076 grad: 0.0975 (0.1072) loss: 0.8413 (0.8523) time: 0.1918 data: 0.0903 max mem: 8452 +Train: [46] [ 600/6250] eta: 0:17:32 lr: 0.000076 grad: 0.0985 (0.1062) loss: 0.8411 (0.8505) time: 0.1715 data: 0.0617 max mem: 8452 +Train: [46] [ 700/6250] eta: 0:17:15 lr: 0.000076 grad: 0.0935 (0.1051) loss: 0.8390 (0.8491) time: 0.1620 data: 0.0557 max mem: 8452 +Train: [46] [ 800/6250] eta: 0:16:41 lr: 0.000076 grad: 0.0929 (0.1041) loss: 0.8455 (0.8482) time: 0.1206 data: 0.0227 max mem: 8452 +Train: [46] [ 900/6250] eta: 0:16:20 lr: 0.000076 grad: 0.0953 (0.1033) loss: 0.8400 (0.8471) time: 0.1846 data: 0.0910 max mem: 8452 +Train: [46] [1000/6250] eta: 0:16:00 lr: 0.000076 grad: 0.0922 (0.1027) loss: 0.8475 (0.8469) time: 0.1780 data: 0.1033 max mem: 8452 +Train: [46] [1100/6250] eta: 0:15:29 lr: 0.000075 grad: 0.0940 (0.1021) loss: 0.8420 (0.8463) time: 0.1905 data: 0.1122 max mem: 8452 +Train: [46] [1200/6250] eta: 0:15:00 lr: 0.000075 grad: 0.0924 (0.1017) loss: 0.8449 (0.8458) time: 0.1516 data: 0.0672 max mem: 8452 +Train: [46] [1300/6250] eta: 0:14:35 lr: 0.000075 grad: 0.1000 (0.1017) loss: 0.8412 (0.8454) time: 0.1665 data: 0.0851 max mem: 8452 +Train: [46] [1400/6250] eta: 0:14:15 lr: 0.000075 grad: 0.0940 (0.1015) loss: 0.8429 (0.8450) time: 0.1666 data: 0.0847 max mem: 8452 +Train: [46] [1500/6250] eta: 0:13:54 lr: 0.000075 grad: 0.0903 (0.1012) loss: 0.8397 (0.8447) time: 0.1534 data: 0.0760 max mem: 8452 +Train: [46] [1600/6250] eta: 0:13:37 lr: 0.000075 grad: 0.0990 (0.1012) loss: 0.8337 (0.8443) time: 0.1716 data: 0.0900 max mem: 8452 +Train: [46] [1700/6250] eta: 0:13:15 lr: 0.000075 grad: 0.0953 (0.1010) loss: 0.8285 (0.8440) time: 0.1584 data: 0.0838 max mem: 8452 +Train: [46] [1800/6250] eta: 0:12:59 lr: 0.000075 grad: 0.0942 (0.1008) loss: 0.8290 (0.8436) time: 0.1630 data: 0.0814 max mem: 8452 +Train: [46] [1900/6250] eta: 0:12:39 lr: 0.000075 grad: 0.0990 (0.1006) loss: 0.8392 (0.8434) time: 0.1598 data: 0.0850 max mem: 8452 +Train: [46] [2000/6250] eta: 0:12:20 lr: 0.000075 grad: 0.0900 (0.1003) loss: 0.8415 (0.8432) time: 0.1636 data: 0.0786 max mem: 8452 +Train: [46] [2100/6250] eta: 0:12:03 lr: 0.000075 grad: 0.0918 (0.1000) loss: 0.8436 (0.8432) time: 0.1755 data: 0.0921 max mem: 8452 +Train: [46] [2200/6250] eta: 0:11:45 lr: 0.000075 grad: 0.0957 (0.0998) loss: 0.8332 (0.8431) time: 0.1757 data: 0.0927 max mem: 8452 +Train: [46] [2300/6250] eta: 0:11:25 lr: 0.000075 grad: 0.0999 (0.0998) loss: 0.8472 (0.8430) time: 0.1674 data: 0.0855 max mem: 8452 +Train: [46] [2400/6250] eta: 0:11:06 lr: 0.000075 grad: 0.0918 (0.0997) loss: 0.8440 (0.8430) time: 0.1549 data: 0.0802 max mem: 8452 +Train: [46] [2500/6250] eta: 0:10:47 lr: 0.000075 grad: 0.0923 (0.0996) loss: 0.8361 (0.8430) time: 0.1840 data: 0.1029 max mem: 8452 +Train: [46] [2600/6250] eta: 0:10:26 lr: 0.000075 grad: 0.0919 (0.0995) loss: 0.8453 (0.8431) time: 0.1556 data: 0.0726 max mem: 8452 +Train: [46] [2700/6250] eta: 0:10:07 lr: 0.000075 grad: 0.0851 (0.0993) loss: 0.8514 (0.8432) time: 0.1759 data: 0.0918 max mem: 8452 +Train: [46] [2800/6250] eta: 0:09:48 lr: 0.000075 grad: 0.0924 (0.0993) loss: 0.8446 (0.8433) time: 0.1453 data: 0.0670 max mem: 8452 +Train: [46] [2900/6250] eta: 0:09:31 lr: 0.000075 grad: 0.0930 (0.0992) loss: 0.8482 (0.8434) time: 0.2376 data: 0.1731 max mem: 8452 +Train: [46] [3000/6250] eta: 0:09:13 lr: 0.000075 grad: 0.0948 (0.0990) loss: 0.8449 (0.8435) time: 0.1669 data: 0.0989 max mem: 8452 +Train: [46] [3100/6250] eta: 0:08:55 lr: 0.000075 grad: 0.0907 (0.0988) loss: 0.8514 (0.8436) time: 0.1514 data: 0.0750 max mem: 8452 +Train: [46] [3200/6250] eta: 0:08:37 lr: 0.000075 grad: 0.0890 (0.0987) loss: 0.8490 (0.8436) time: 0.1677 data: 0.0837 max mem: 8452 +Train: [46] [3300/6250] eta: 0:08:20 lr: 0.000075 grad: 0.0973 (0.0986) loss: 0.8438 (0.8437) time: 0.1507 data: 0.0614 max mem: 8452 +Train: [46] [3400/6250] eta: 0:08:02 lr: 0.000075 grad: 0.0948 (0.0985) loss: 0.8400 (0.8438) time: 0.1795 data: 0.0936 max mem: 8452 +Train: [46] [3500/6250] eta: 0:07:45 lr: 0.000075 grad: 0.0887 (0.0983) loss: 0.8427 (0.8438) time: 0.1872 data: 0.1144 max mem: 8452 +Train: [46] [3600/6250] eta: 0:07:27 lr: 0.000075 grad: 0.0916 (0.0982) loss: 0.8406 (0.8439) time: 0.1474 data: 0.0692 max mem: 8452 +Train: [46] [3700/6250] eta: 0:07:09 lr: 0.000075 grad: 0.0952 (0.0980) loss: 0.8429 (0.8440) time: 0.1440 data: 0.0432 max mem: 8452 +Train: [46] [3800/6250] eta: 0:06:52 lr: 0.000075 grad: 0.0909 (0.0979) loss: 0.8469 (0.8440) time: 0.1811 data: 0.1085 max mem: 8452 +Train: [46] [3900/6250] eta: 0:06:34 lr: 0.000075 grad: 0.0907 (0.0978) loss: 0.8541 (0.8442) time: 0.1403 data: 0.0559 max mem: 8452 +Train: [46] [4000/6250] eta: 0:06:17 lr: 0.000075 grad: 0.0900 (0.0977) loss: 0.8488 (0.8443) time: 0.1574 data: 0.0789 max mem: 8452 +Train: [46] [4100/6250] eta: 0:05:59 lr: 0.000075 grad: 0.0887 (0.0976) loss: 0.8501 (0.8444) time: 0.1629 data: 0.0802 max mem: 8452 +Train: [46] [4200/6250] eta: 0:05:41 lr: 0.000074 grad: 0.0961 (0.0976) loss: 0.8466 (0.8445) time: 0.1708 data: 0.0913 max mem: 8452 +Train: [46] [4300/6250] eta: 0:05:24 lr: 0.000074 grad: 0.0868 (0.0975) loss: 0.8562 (0.8446) time: 0.1449 data: 0.0674 max mem: 8452 +Train: [46] [4400/6250] eta: 0:05:08 lr: 0.000074 grad: 0.0941 (0.0974) loss: 0.8518 (0.8447) time: 0.1768 data: 0.0982 max mem: 8452 +Train: [46] [4500/6250] eta: 0:04:51 lr: 0.000074 grad: 0.0899 (0.0974) loss: 0.8441 (0.8447) time: 0.1786 data: 0.0999 max mem: 8452 +Train: [46] [4600/6250] eta: 0:04:34 lr: 0.000074 grad: 0.0906 (0.0974) loss: 0.8398 (0.8448) time: 0.1410 data: 0.0676 max mem: 8452 +Train: [46] [4700/6250] eta: 0:04:17 lr: 0.000074 grad: 0.0934 (0.0974) loss: 0.8479 (0.8447) time: 0.1660 data: 0.0781 max mem: 8452 +Train: [46] [4800/6250] eta: 0:04:01 lr: 0.000074 grad: 0.0971 (0.0974) loss: 0.8415 (0.8446) time: 0.1435 data: 0.0585 max mem: 8452 +Train: [46] [4900/6250] eta: 0:03:44 lr: 0.000074 grad: 0.1007 (0.0975) loss: 0.8436 (0.8446) time: 0.1456 data: 0.0626 max mem: 8452 +Train: [46] [5000/6250] eta: 0:03:27 lr: 0.000074 grad: 0.0962 (0.0975) loss: 0.8406 (0.8445) time: 0.1567 data: 0.0843 max mem: 8452 +Train: [46] [5100/6250] eta: 0:03:10 lr: 0.000074 grad: 0.0950 (0.0975) loss: 0.8387 (0.8445) time: 0.1539 data: 0.0667 max mem: 8452 +Train: [46] [5200/6250] eta: 0:02:53 lr: 0.000074 grad: 0.0943 (0.0976) loss: 0.8383 (0.8444) time: 0.1603 data: 0.0662 max mem: 8452 +Train: [46] [5300/6250] eta: 0:02:36 lr: 0.000074 grad: 0.0932 (0.0976) loss: 0.8415 (0.8443) time: 0.1600 data: 0.0665 max mem: 8452 +Train: [46] [5400/6250] eta: 0:02:20 lr: 0.000074 grad: 0.0949 (0.0976) loss: 0.8411 (0.8443) time: 0.1563 data: 0.0672 max mem: 8452 +Train: [46] [5500/6250] eta: 0:02:03 lr: 0.000074 grad: 0.1003 (0.0977) loss: 0.8368 (0.8442) time: 0.1463 data: 0.0656 max mem: 8452 +Train: [46] [5600/6250] eta: 0:01:46 lr: 0.000074 grad: 0.0938 (0.0976) loss: 0.8440 (0.8441) time: 0.1644 data: 0.0818 max mem: 8452 +Train: [46] [5700/6250] eta: 0:01:30 lr: 0.000074 grad: 0.0948 (0.0976) loss: 0.8462 (0.8441) time: 0.1540 data: 0.0814 max mem: 8452 +Train: [46] [5800/6250] eta: 0:01:14 lr: 0.000074 grad: 0.0977 (0.0977) loss: 0.8424 (0.8441) time: 0.2106 data: 0.1095 max mem: 8452 +Train: [46] [5900/6250] eta: 0:00:57 lr: 0.000074 grad: 0.0975 (0.0977) loss: 0.8486 (0.8441) time: 0.1854 data: 0.0991 max mem: 8452 +Train: [46] [6000/6250] eta: 0:00:41 lr: 0.000074 grad: 0.0975 (0.0976) loss: 0.8426 (0.8441) time: 0.1453 data: 0.0637 max mem: 8452 +Train: [46] [6100/6250] eta: 0:00:24 lr: 0.000074 grad: 0.0908 (0.0976) loss: 0.8393 (0.8441) time: 0.1356 data: 0.0550 max mem: 8452 +Train: [46] [6200/6250] eta: 0:00:08 lr: 0.000074 grad: 0.0948 (0.0976) loss: 0.8497 (0.8441) time: 0.1575 data: 0.0622 max mem: 8452 +Train: [46] [6249/6250] eta: 0:00:00 lr: 0.000074 grad: 0.0947 (0.0976) loss: 0.8434 (0.8441) time: 0.1350 data: 0.0388 max mem: 8452 +Train: [46] Total time: 0:17:15 (0.1657 s / it) +Averaged stats: lr: 0.000074 grad: 0.0947 (0.0976) loss: 0.8434 (0.8441) +Eval (hcp-train-subset): [46] [ 0/62] eta: 0:03:39 loss: 0.8838 (0.8838) time: 3.5328 data: 3.4341 max mem: 8452 +Eval (hcp-train-subset): [46] [61/62] eta: 0:00:00 loss: 0.8727 (0.8742) time: 0.1293 data: 0.1075 max mem: 8452 +Eval (hcp-train-subset): [46] Total time: 0:00:14 (0.2343 s / it) +Averaged stats (hcp-train-subset): loss: 0.8727 (0.8742) +Eval (hcp-val): [46] [ 0/62] eta: 0:03:36 loss: 0.8709 (0.8709) time: 3.4855 data: 3.4091 max mem: 8452 +Eval (hcp-val): [46] [61/62] eta: 0:00:00 loss: 0.8739 (0.8754) time: 0.1310 data: 0.1096 max mem: 8452 +Eval (hcp-val): [46] Total time: 0:00:14 (0.2357 s / it) +Averaged stats (hcp-val): loss: 0.8739 (0.8754) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [47] [ 0/6250] eta: 10:20:35 lr: 0.000074 grad: 0.1297 (0.1297) loss: 0.8862 (0.8862) time: 5.9576 data: 5.8597 max mem: 8452 +Train: [47] [ 100/6250] eta: 0:22:49 lr: 0.000074 grad: 0.1056 (0.1184) loss: 0.8558 (0.8667) time: 0.1740 data: 0.0749 max mem: 8452 +Train: [47] [ 200/6250] eta: 0:20:22 lr: 0.000074 grad: 0.0885 (0.1104) loss: 0.8469 (0.8619) time: 0.1778 data: 0.0774 max mem: 8452 +Train: [47] [ 300/6250] eta: 0:18:51 lr: 0.000074 grad: 0.0953 (0.1076) loss: 0.8527 (0.8588) time: 0.1402 data: 0.0493 max mem: 8452 +Train: [47] [ 400/6250] eta: 0:18:07 lr: 0.000074 grad: 0.0906 (0.1056) loss: 0.8525 (0.8569) time: 0.1330 data: 0.0321 max mem: 8452 +Train: [47] [ 500/6250] eta: 0:17:27 lr: 0.000074 grad: 0.0854 (0.1040) loss: 0.8509 (0.8548) time: 0.1783 data: 0.0806 max mem: 8452 +Train: [47] [ 600/6250] eta: 0:16:48 lr: 0.000074 grad: 0.0967 (0.1025) loss: 0.8486 (0.8537) time: 0.1864 data: 0.0920 max mem: 8452 +Train: [47] [ 700/6250] eta: 0:16:21 lr: 0.000074 grad: 0.0899 (0.1008) loss: 0.8520 (0.8531) time: 0.1702 data: 0.0644 max mem: 8452 +Train: [47] [ 800/6250] eta: 0:16:16 lr: 0.000074 grad: 0.0872 (0.0995) loss: 0.8502 (0.8529) time: 0.1222 data: 0.0221 max mem: 8452 +Train: [47] [ 900/6250] eta: 0:15:47 lr: 0.000074 grad: 0.0856 (0.0982) loss: 0.8489 (0.8528) time: 0.1542 data: 0.0617 max mem: 8452 +Train: [47] [1000/6250] eta: 0:15:21 lr: 0.000073 grad: 0.0853 (0.0974) loss: 0.8478 (0.8527) time: 0.1437 data: 0.0524 max mem: 8452 +Train: [47] [1100/6250] eta: 0:14:59 lr: 0.000073 grad: 0.0895 (0.0968) loss: 0.8458 (0.8524) time: 0.1619 data: 0.0636 max mem: 8452 +Train: [47] [1200/6250] eta: 0:14:33 lr: 0.000073 grad: 0.0877 (0.0962) loss: 0.8561 (0.8521) time: 0.1554 data: 0.0682 max mem: 8452 +Train: [47] [1300/6250] eta: 0:14:12 lr: 0.000073 grad: 0.0947 (0.0961) loss: 0.8401 (0.8516) time: 0.1534 data: 0.0657 max mem: 8452 +Train: [47] [1400/6250] eta: 0:13:48 lr: 0.000073 grad: 0.0877 (0.0957) loss: 0.8493 (0.8512) time: 0.1576 data: 0.0807 max mem: 8452 +Train: [47] [1500/6250] eta: 0:13:26 lr: 0.000073 grad: 0.0944 (0.0956) loss: 0.8466 (0.8508) time: 0.1592 data: 0.0662 max mem: 8452 +Train: [47] [1600/6250] eta: 0:13:04 lr: 0.000073 grad: 0.0894 (0.0953) loss: 0.8461 (0.8507) time: 0.1548 data: 0.0780 max mem: 8452 +Train: [47] [1700/6250] eta: 0:12:42 lr: 0.000073 grad: 0.0904 (0.0951) loss: 0.8547 (0.8505) time: 0.1362 data: 0.0567 max mem: 8452 +Train: [47] [1800/6250] eta: 0:12:29 lr: 0.000073 grad: 0.0909 (0.0950) loss: 0.8425 (0.8502) time: 0.1974 data: 0.1156 max mem: 8452 +Train: [47] [1900/6250] eta: 0:12:10 lr: 0.000073 grad: 0.0945 (0.0949) loss: 0.8390 (0.8499) time: 0.1661 data: 0.0795 max mem: 8452 +Train: [47] [2000/6250] eta: 0:11:49 lr: 0.000073 grad: 0.0901 (0.0950) loss: 0.8487 (0.8496) time: 0.1474 data: 0.0778 max mem: 8452 +Train: [47] [2100/6250] eta: 0:11:32 lr: 0.000073 grad: 0.0919 (0.0948) loss: 0.8447 (0.8495) time: 0.1496 data: 0.0666 max mem: 8452 +Train: [47] [2200/6250] eta: 0:11:15 lr: 0.000073 grad: 0.0927 (0.0949) loss: 0.8478 (0.8492) time: 0.1449 data: 0.0466 max mem: 8452 +Train: [47] [2300/6250] eta: 0:10:57 lr: 0.000073 grad: 0.0926 (0.0948) loss: 0.8447 (0.8490) time: 0.1507 data: 0.0646 max mem: 8452 +Train: [47] [2400/6250] eta: 0:10:41 lr: 0.000073 grad: 0.0924 (0.0949) loss: 0.8386 (0.8487) time: 0.1672 data: 0.0746 max mem: 8452 +Train: [47] [2500/6250] eta: 0:10:22 lr: 0.000073 grad: 0.0910 (0.0950) loss: 0.8438 (0.8485) time: 0.1486 data: 0.0636 max mem: 8452 +Train: [47] [2600/6250] eta: 0:10:05 lr: 0.000073 grad: 0.0944 (0.0950) loss: 0.8452 (0.8483) time: 0.1724 data: 0.0821 max mem: 8452 +Train: [47] [2700/6250] eta: 0:09:47 lr: 0.000073 grad: 0.1011 (0.0951) loss: 0.8420 (0.8480) time: 0.1447 data: 0.0628 max mem: 8452 +Train: [47] [2800/6250] eta: 0:09:29 lr: 0.000073 grad: 0.0891 (0.0951) loss: 0.8461 (0.8478) time: 0.1508 data: 0.0687 max mem: 8452 +Train: [47] [2900/6250] eta: 0:09:13 lr: 0.000073 grad: 0.0954 (0.0951) loss: 0.8450 (0.8476) time: 0.1692 data: 0.0946 max mem: 8452 +Train: [47] [3000/6250] eta: 0:08:58 lr: 0.000073 grad: 0.0916 (0.0953) loss: 0.8381 (0.8474) time: 0.1788 data: 0.0977 max mem: 8452 +Train: [47] [3100/6250] eta: 0:08:41 lr: 0.000073 grad: 0.0934 (0.0954) loss: 0.8353 (0.8471) time: 0.2020 data: 0.1270 max mem: 8452 +Train: [47] [3200/6250] eta: 0:08:24 lr: 0.000073 grad: 0.0905 (0.0954) loss: 0.8487 (0.8471) time: 0.1586 data: 0.0705 max mem: 8452 +Train: [47] [3300/6250] eta: 0:08:07 lr: 0.000073 grad: 0.0870 (0.0954) loss: 0.8474 (0.8471) time: 0.1567 data: 0.0627 max mem: 8452 +Train: [47] [3400/6250] eta: 0:07:50 lr: 0.000073 grad: 0.0915 (0.0954) loss: 0.8496 (0.8470) time: 0.1562 data: 0.0612 max mem: 8452 +Train: [47] [3500/6250] eta: 0:07:33 lr: 0.000073 grad: 0.0903 (0.0954) loss: 0.8436 (0.8469) time: 0.1141 data: 0.0088 max mem: 8452 +Train: [47] [3600/6250] eta: 0:07:16 lr: 0.000073 grad: 0.0985 (0.0955) loss: 0.8443 (0.8468) time: 0.1459 data: 0.0626 max mem: 8452 +Train: [47] [3700/6250] eta: 0:06:58 lr: 0.000073 grad: 0.0944 (0.0956) loss: 0.8426 (0.8467) time: 0.1438 data: 0.0600 max mem: 8452 +Train: [47] [3800/6250] eta: 0:06:41 lr: 0.000073 grad: 0.0911 (0.0956) loss: 0.8530 (0.8468) time: 0.1242 data: 0.0431 max mem: 8452 +Train: [47] [3900/6250] eta: 0:06:25 lr: 0.000073 grad: 0.0964 (0.0956) loss: 0.8356 (0.8467) time: 0.1725 data: 0.0887 max mem: 8452 +Train: [47] [4000/6250] eta: 0:06:07 lr: 0.000073 grad: 0.0896 (0.0957) loss: 0.8430 (0.8467) time: 0.1500 data: 0.0787 max mem: 8452 +Train: [47] [4100/6250] eta: 0:05:51 lr: 0.000072 grad: 0.0918 (0.0956) loss: 0.8479 (0.8467) time: 0.1643 data: 0.0910 max mem: 8452 +Train: [47] [4200/6250] eta: 0:05:34 lr: 0.000072 grad: 0.0887 (0.0956) loss: 0.8520 (0.8467) time: 0.1727 data: 0.0858 max mem: 8452 +Train: [47] [4300/6250] eta: 0:05:17 lr: 0.000072 grad: 0.0971 (0.0957) loss: 0.8501 (0.8467) time: 0.1890 data: 0.1021 max mem: 8452 +Train: [47] [4400/6250] eta: 0:05:02 lr: 0.000072 grad: 0.0976 (0.0957) loss: 0.8425 (0.8466) time: 0.1706 data: 0.1096 max mem: 8452 +Train: [47] [4500/6250] eta: 0:04:46 lr: 0.000072 grad: 0.0896 (0.0959) loss: 0.8515 (0.8466) time: 0.1960 data: 0.1175 max mem: 8452 +Train: [47] [4600/6250] eta: 0:04:30 lr: 0.000072 grad: 0.0915 (0.0958) loss: 0.8546 (0.8466) time: 0.1608 data: 0.0752 max mem: 8452 +Train: [47] [4700/6250] eta: 0:04:14 lr: 0.000072 grad: 0.0888 (0.0958) loss: 0.8476 (0.8467) time: 0.1589 data: 0.0761 max mem: 8452 +Train: [47] [4800/6250] eta: 0:03:59 lr: 0.000072 grad: 0.0888 (0.0958) loss: 0.8461 (0.8467) time: 0.1935 data: 0.1095 max mem: 8452 +Train: [47] [4900/6250] eta: 0:03:42 lr: 0.000072 grad: 0.0862 (0.0958) loss: 0.8467 (0.8466) time: 0.1284 data: 0.0415 max mem: 8452 +Train: [47] [5000/6250] eta: 0:03:26 lr: 0.000072 grad: 0.0870 (0.0958) loss: 0.8543 (0.8466) time: 0.1454 data: 0.0635 max mem: 8452 +Train: [47] [5100/6250] eta: 0:03:09 lr: 0.000072 grad: 0.0983 (0.0958) loss: 0.8521 (0.8466) time: 0.1434 data: 0.0525 max mem: 8452 +Train: [47] [5200/6250] eta: 0:02:53 lr: 0.000072 grad: 0.0923 (0.0958) loss: 0.8418 (0.8465) time: 0.1364 data: 0.0538 max mem: 8452 +Train: [47] [5300/6250] eta: 0:02:36 lr: 0.000072 grad: 0.0964 (0.0959) loss: 0.8353 (0.8464) time: 0.1402 data: 0.0568 max mem: 8452 +Train: [47] [5400/6250] eta: 0:02:20 lr: 0.000072 grad: 0.0984 (0.0960) loss: 0.8326 (0.8462) time: 0.1864 data: 0.1004 max mem: 8452 +Train: [47] [5500/6250] eta: 0:02:03 lr: 0.000072 grad: 0.0948 (0.0960) loss: 0.8479 (0.8461) time: 0.1422 data: 0.0459 max mem: 8452 +Train: [47] [5600/6250] eta: 0:01:47 lr: 0.000072 grad: 0.0960 (0.0961) loss: 0.8326 (0.8460) time: 0.1549 data: 0.0673 max mem: 8452 +Train: [47] [5700/6250] eta: 0:01:30 lr: 0.000072 grad: 0.1003 (0.0961) loss: 0.8336 (0.8459) time: 0.1731 data: 0.0797 max mem: 8452 +Train: [47] [5800/6250] eta: 0:01:14 lr: 0.000072 grad: 0.1031 (0.0962) loss: 0.8394 (0.8458) time: 0.1599 data: 0.0712 max mem: 8452 +Train: [47] [5900/6250] eta: 0:00:57 lr: 0.000072 grad: 0.0946 (0.0962) loss: 0.8442 (0.8456) time: 0.1480 data: 0.0732 max mem: 8452 +Train: [47] [6000/6250] eta: 0:00:41 lr: 0.000072 grad: 0.0991 (0.0963) loss: 0.8435 (0.8455) time: 0.1811 data: 0.1043 max mem: 8452 +Train: [47] [6100/6250] eta: 0:00:24 lr: 0.000072 grad: 0.0961 (0.0963) loss: 0.8406 (0.8454) time: 0.1735 data: 0.0947 max mem: 8452 +Train: [47] [6200/6250] eta: 0:00:08 lr: 0.000072 grad: 0.1033 (0.0964) loss: 0.8397 (0.8453) time: 0.1614 data: 0.0825 max mem: 8452 +Train: [47] [6249/6250] eta: 0:00:00 lr: 0.000072 grad: 0.0945 (0.0965) loss: 0.8386 (0.8452) time: 0.1677 data: 0.0902 max mem: 8452 +Train: [47] Total time: 0:17:14 (0.1655 s / it) +Averaged stats: lr: 0.000072 grad: 0.0945 (0.0965) loss: 0.8386 (0.8452) +Eval (hcp-train-subset): [47] [ 0/62] eta: 0:03:56 loss: 0.8854 (0.8854) time: 3.8081 data: 3.7238 max mem: 8452 +Eval (hcp-train-subset): [47] [61/62] eta: 0:00:00 loss: 0.8736 (0.8742) time: 0.1892 data: 0.1680 max mem: 8452 +Eval (hcp-train-subset): [47] Total time: 0:00:14 (0.2382 s / it) +Averaged stats (hcp-train-subset): loss: 0.8736 (0.8742) +Eval (hcp-val): [47] [ 0/62] eta: 0:05:32 loss: 0.8732 (0.8732) time: 5.3694 data: 5.3415 max mem: 8452 +Eval (hcp-val): [47] [61/62] eta: 0:00:00 loss: 0.8732 (0.8759) time: 0.1466 data: 0.1239 max mem: 8452 +Eval (hcp-val): [47] Total time: 0:00:14 (0.2321 s / it) +Averaged stats (hcp-val): loss: 0.8732 (0.8759) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [48] [ 0/6250] eta: 9:30:53 lr: 0.000072 grad: 0.1925 (0.1925) loss: 0.9173 (0.9173) time: 5.4806 data: 5.3781 max mem: 8452 +Train: [48] [ 100/6250] eta: 0:22:12 lr: 0.000072 grad: 0.0956 (0.1214) loss: 0.8605 (0.8697) time: 0.1683 data: 0.0823 max mem: 8452 +Train: [48] [ 200/6250] eta: 0:19:18 lr: 0.000072 grad: 0.0950 (0.1147) loss: 0.8476 (0.8630) time: 0.1649 data: 0.0778 max mem: 8452 +Train: [48] [ 300/6250] eta: 0:18:20 lr: 0.000072 grad: 0.0946 (0.1085) loss: 0.8511 (0.8590) time: 0.1633 data: 0.0623 max mem: 8452 +Train: [48] [ 400/6250] eta: 0:17:19 lr: 0.000072 grad: 0.0925 (0.1057) loss: 0.8540 (0.8566) time: 0.1581 data: 0.0673 max mem: 8452 +Train: [48] [ 500/6250] eta: 0:16:44 lr: 0.000072 grad: 0.0961 (0.1042) loss: 0.8494 (0.8552) time: 0.1555 data: 0.0618 max mem: 8452 +Train: [48] [ 600/6250] eta: 0:16:27 lr: 0.000072 grad: 0.0886 (0.1024) loss: 0.8567 (0.8543) time: 0.1980 data: 0.1087 max mem: 8452 +Train: [48] [ 700/6250] eta: 0:15:57 lr: 0.000072 grad: 0.0860 (0.1012) loss: 0.8541 (0.8537) time: 0.1663 data: 0.0821 max mem: 8452 +Train: [48] [ 800/6250] eta: 0:15:31 lr: 0.000072 grad: 0.0831 (0.1002) loss: 0.8551 (0.8532) time: 0.1790 data: 0.0920 max mem: 8452 +Train: [48] [ 900/6250] eta: 0:15:13 lr: 0.000071 grad: 0.0921 (0.0994) loss: 0.8480 (0.8526) time: 0.1672 data: 0.0831 max mem: 8452 +Train: [48] [1000/6250] eta: 0:14:52 lr: 0.000071 grad: 0.0999 (0.0991) loss: 0.8467 (0.8522) time: 0.1533 data: 0.0697 max mem: 8452 +Train: [48] [1100/6250] eta: 0:14:31 lr: 0.000071 grad: 0.0962 (0.0988) loss: 0.8379 (0.8513) time: 0.1570 data: 0.0807 max mem: 8452 +Train: [48] [1200/6250] eta: 0:14:06 lr: 0.000071 grad: 0.0929 (0.0984) loss: 0.8426 (0.8507) time: 0.1395 data: 0.0585 max mem: 8452 +Train: [48] [1300/6250] eta: 0:13:45 lr: 0.000071 grad: 0.0960 (0.0981) loss: 0.8339 (0.8501) time: 0.1627 data: 0.0835 max mem: 8452 +Train: [48] [1400/6250] eta: 0:13:25 lr: 0.000071 grad: 0.0907 (0.0980) loss: 0.8439 (0.8493) time: 0.1576 data: 0.0749 max mem: 8452 +Train: [48] [1500/6250] eta: 0:13:07 lr: 0.000071 grad: 0.0903 (0.0978) loss: 0.8358 (0.8487) time: 0.1698 data: 0.0865 max mem: 8452 +Train: [48] [1600/6250] eta: 0:12:49 lr: 0.000071 grad: 0.0877 (0.0976) loss: 0.8429 (0.8485) time: 0.1335 data: 0.0424 max mem: 8452 +Train: [48] [1700/6250] eta: 0:12:43 lr: 0.000071 grad: 0.0933 (0.0973) loss: 0.8431 (0.8482) time: 0.1135 data: 0.0002 max mem: 8452 +Train: [48] [1800/6250] eta: 0:12:29 lr: 0.000071 grad: 0.0939 (0.0970) loss: 0.8394 (0.8480) time: 0.1770 data: 0.0946 max mem: 8452 +Train: [48] [1900/6250] eta: 0:12:18 lr: 0.000071 grad: 0.0928 (0.0968) loss: 0.8478 (0.8478) time: 0.1648 data: 0.0850 max mem: 8452 +Train: [48] [2000/6250] eta: 0:12:02 lr: 0.000071 grad: 0.0903 (0.0968) loss: 0.8411 (0.8475) time: 0.1350 data: 0.0574 max mem: 8452 +Train: [48] [2100/6250] eta: 0:11:45 lr: 0.000071 grad: 0.0976 (0.0967) loss: 0.8395 (0.8472) time: 0.1894 data: 0.1080 max mem: 8452 +Train: [48] [2200/6250] eta: 0:11:29 lr: 0.000071 grad: 0.0955 (0.0967) loss: 0.8402 (0.8470) time: 0.1792 data: 0.0891 max mem: 8452 +Train: [48] [2300/6250] eta: 0:11:13 lr: 0.000071 grad: 0.0965 (0.0970) loss: 0.8413 (0.8468) time: 0.1781 data: 0.0968 max mem: 8452 +Train: [48] [2400/6250] eta: 0:10:56 lr: 0.000071 grad: 0.0910 (0.0969) loss: 0.8511 (0.8467) time: 0.2039 data: 0.1188 max mem: 8452 +Train: [48] [2500/6250] eta: 0:10:38 lr: 0.000071 grad: 0.0917 (0.0970) loss: 0.8399 (0.8465) time: 0.1662 data: 0.0705 max mem: 8452 +Train: [48] [2600/6250] eta: 0:10:20 lr: 0.000071 grad: 0.0963 (0.0970) loss: 0.8391 (0.8463) time: 0.1774 data: 0.0924 max mem: 8452 +Train: [48] [2700/6250] eta: 0:10:02 lr: 0.000071 grad: 0.0930 (0.0969) loss: 0.8514 (0.8463) time: 0.1471 data: 0.0592 max mem: 8452 +Train: [48] [2800/6250] eta: 0:09:42 lr: 0.000071 grad: 0.0858 (0.0968) loss: 0.8535 (0.8462) time: 0.1415 data: 0.0612 max mem: 8452 +Train: [48] [2900/6250] eta: 0:09:26 lr: 0.000071 grad: 0.0966 (0.0968) loss: 0.8434 (0.8461) time: 0.1888 data: 0.1120 max mem: 8452 +Train: [48] [3000/6250] eta: 0:09:09 lr: 0.000071 grad: 0.0936 (0.0967) loss: 0.8434 (0.8460) time: 0.1587 data: 0.0752 max mem: 8452 +Train: [48] [3100/6250] eta: 0:08:50 lr: 0.000071 grad: 0.0937 (0.0967) loss: 0.8396 (0.8458) time: 0.1647 data: 0.0790 max mem: 8452 +Train: [48] [3200/6250] eta: 0:08:32 lr: 0.000071 grad: 0.0937 (0.0968) loss: 0.8421 (0.8458) time: 0.1536 data: 0.0688 max mem: 8452 +Train: [48] [3300/6250] eta: 0:08:16 lr: 0.000071 grad: 0.0975 (0.0968) loss: 0.8322 (0.8456) time: 0.1813 data: 0.1016 max mem: 8452 +Train: [48] [3400/6250] eta: 0:07:58 lr: 0.000071 grad: 0.1016 (0.0968) loss: 0.8441 (0.8455) time: 0.1467 data: 0.0655 max mem: 8452 +Train: [48] [3500/6250] eta: 0:07:40 lr: 0.000071 grad: 0.0914 (0.0968) loss: 0.8474 (0.8454) time: 0.1623 data: 0.0662 max mem: 8452 +Train: [48] [3600/6250] eta: 0:07:22 lr: 0.000071 grad: 0.0924 (0.0967) loss: 0.8414 (0.8454) time: 0.1653 data: 0.0769 max mem: 8452 +Train: [48] [3700/6250] eta: 0:07:04 lr: 0.000071 grad: 0.0922 (0.0966) loss: 0.8416 (0.8454) time: 0.1490 data: 0.0724 max mem: 8452 +Train: [48] [3800/6250] eta: 0:06:47 lr: 0.000071 grad: 0.0888 (0.0967) loss: 0.8394 (0.8454) time: 0.1265 data: 0.0455 max mem: 8452 +Train: [48] [3900/6250] eta: 0:06:30 lr: 0.000070 grad: 0.0895 (0.0966) loss: 0.8431 (0.8453) time: 0.1552 data: 0.0676 max mem: 8452 +Train: [48] [4000/6250] eta: 0:06:13 lr: 0.000070 grad: 0.0968 (0.0967) loss: 0.8401 (0.8453) time: 0.1595 data: 0.0763 max mem: 8452 +Train: [48] [4100/6250] eta: 0:05:56 lr: 0.000070 grad: 0.0985 (0.0967) loss: 0.8413 (0.8452) time: 0.1464 data: 0.0646 max mem: 8452 +Train: [48] [4200/6250] eta: 0:05:39 lr: 0.000070 grad: 0.0946 (0.0967) loss: 0.8377 (0.8450) time: 0.1696 data: 0.0945 max mem: 8452 +Train: [48] [4300/6250] eta: 0:05:22 lr: 0.000070 grad: 0.0999 (0.0967) loss: 0.8311 (0.8449) time: 0.1591 data: 0.0767 max mem: 8452 +Train: [48] [4400/6250] eta: 0:05:06 lr: 0.000070 grad: 0.1036 (0.0968) loss: 0.8362 (0.8447) time: 0.1785 data: 0.1085 max mem: 8452 +Train: [48] [4500/6250] eta: 0:04:49 lr: 0.000070 grad: 0.0960 (0.0968) loss: 0.8435 (0.8446) time: 0.1464 data: 0.0727 max mem: 8452 +Train: [48] [4600/6250] eta: 0:04:32 lr: 0.000070 grad: 0.0988 (0.0969) loss: 0.8339 (0.8444) time: 0.1341 data: 0.0632 max mem: 8452 +Train: [48] [4700/6250] eta: 0:04:16 lr: 0.000070 grad: 0.0940 (0.0970) loss: 0.8385 (0.8443) time: 0.1543 data: 0.0643 max mem: 8452 +Train: [48] [4800/6250] eta: 0:03:59 lr: 0.000070 grad: 0.0976 (0.0970) loss: 0.8365 (0.8442) time: 0.1496 data: 0.0801 max mem: 8452 +Train: [48] [4900/6250] eta: 0:03:43 lr: 0.000070 grad: 0.0960 (0.0970) loss: 0.8417 (0.8441) time: 0.1521 data: 0.0645 max mem: 8452 +Train: [48] [5000/6250] eta: 0:03:26 lr: 0.000070 grad: 0.0928 (0.0970) loss: 0.8357 (0.8440) time: 0.1623 data: 0.0769 max mem: 8452 +Train: [48] [5100/6250] eta: 0:03:09 lr: 0.000070 grad: 0.1026 (0.0971) loss: 0.8454 (0.8440) time: 0.1716 data: 0.0891 max mem: 8452 +Train: [48] [5200/6250] eta: 0:02:53 lr: 0.000070 grad: 0.0942 (0.0972) loss: 0.8322 (0.8439) time: 0.1666 data: 0.0768 max mem: 8452 +Train: [48] [5300/6250] eta: 0:02:36 lr: 0.000070 grad: 0.0984 (0.0972) loss: 0.8365 (0.8437) time: 0.1634 data: 0.0827 max mem: 8452 +Train: [48] [5400/6250] eta: 0:02:19 lr: 0.000070 grad: 0.0955 (0.0972) loss: 0.8233 (0.8436) time: 0.1337 data: 0.0550 max mem: 8452 +Train: [48] [5500/6250] eta: 0:02:03 lr: 0.000070 grad: 0.0938 (0.0973) loss: 0.8384 (0.8435) time: 0.1575 data: 0.0709 max mem: 8452 +Train: [48] [5600/6250] eta: 0:01:46 lr: 0.000070 grad: 0.0968 (0.0973) loss: 0.8441 (0.8435) time: 0.1286 data: 0.0537 max mem: 8452 +Train: [48] [5700/6250] eta: 0:01:30 lr: 0.000070 grad: 0.0996 (0.0973) loss: 0.8412 (0.8434) time: 0.1092 data: 0.0276 max mem: 8452 +Train: [48] [5800/6250] eta: 0:01:13 lr: 0.000070 grad: 0.0966 (0.0974) loss: 0.8456 (0.8433) time: 0.1426 data: 0.0556 max mem: 8452 +Train: [48] [5900/6250] eta: 0:00:57 lr: 0.000070 grad: 0.1015 (0.0975) loss: 0.8371 (0.8432) time: 0.1783 data: 0.0949 max mem: 8452 +Train: [48] [6000/6250] eta: 0:00:41 lr: 0.000070 grad: 0.0963 (0.0975) loss: 0.8398 (0.8432) time: 0.1617 data: 0.0809 max mem: 8452 +Train: [48] [6100/6250] eta: 0:00:24 lr: 0.000070 grad: 0.1013 (0.0976) loss: 0.8429 (0.8431) time: 0.1612 data: 0.0752 max mem: 8452 +Train: [48] [6200/6250] eta: 0:00:08 lr: 0.000070 grad: 0.0966 (0.0976) loss: 0.8422 (0.8430) time: 0.1582 data: 0.0802 max mem: 8452 +Train: [48] [6249/6250] eta: 0:00:00 lr: 0.000070 grad: 0.1003 (0.0976) loss: 0.8353 (0.8430) time: 0.1673 data: 0.0884 max mem: 8452 +Train: [48] Total time: 0:17:09 (0.1648 s / it) +Averaged stats: lr: 0.000070 grad: 0.1003 (0.0976) loss: 0.8353 (0.8430) +Eval (hcp-train-subset): [48] [ 0/62] eta: 0:05:06 loss: 0.8897 (0.8897) time: 4.9381 data: 4.9123 max mem: 8452 +Eval (hcp-train-subset): [48] [61/62] eta: 0:00:00 loss: 0.8733 (0.8735) time: 0.1413 data: 0.1203 max mem: 8452 +Eval (hcp-train-subset): [48] Total time: 0:00:14 (0.2355 s / it) +Averaged stats (hcp-train-subset): loss: 0.8733 (0.8735) +Eval (hcp-val): [48] [ 0/62] eta: 0:06:28 loss: 0.8727 (0.8727) time: 6.2715 data: 6.2158 max mem: 8452 +Eval (hcp-val): [48] [61/62] eta: 0:00:00 loss: 0.8733 (0.8754) time: 0.1183 data: 0.0975 max mem: 8452 +Eval (hcp-val): [48] Total time: 0:00:14 (0.2357 s / it) +Averaged stats (hcp-val): loss: 0.8733 (0.8754) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [49] [ 0/6250] eta: 11:28:29 lr: 0.000070 grad: 0.3233 (0.3233) loss: 0.8598 (0.8598) time: 6.6095 data: 6.4819 max mem: 8452 +Train: [49] [ 100/6250] eta: 0:22:18 lr: 0.000070 grad: 0.1027 (0.1430) loss: 0.8688 (0.8641) time: 0.1569 data: 0.0506 max mem: 8452 +Train: [49] [ 200/6250] eta: 0:19:09 lr: 0.000070 grad: 0.0962 (0.1269) loss: 0.8506 (0.8601) time: 0.1511 data: 0.0560 max mem: 8452 +Train: [49] [ 300/6250] eta: 0:18:12 lr: 0.000070 grad: 0.0986 (0.1202) loss: 0.8504 (0.8543) time: 0.1448 data: 0.0566 max mem: 8452 +Train: [49] [ 400/6250] eta: 0:17:12 lr: 0.000070 grad: 0.0980 (0.1153) loss: 0.8415 (0.8523) time: 0.1617 data: 0.0772 max mem: 8452 +Train: [49] [ 500/6250] eta: 0:16:37 lr: 0.000070 grad: 0.0941 (0.1130) loss: 0.8521 (0.8507) time: 0.1792 data: 0.0904 max mem: 8452 +Train: [49] [ 600/6250] eta: 0:16:06 lr: 0.000070 grad: 0.0892 (0.1108) loss: 0.8473 (0.8503) time: 0.1600 data: 0.0717 max mem: 8452 +Train: [49] [ 700/6250] eta: 0:15:45 lr: 0.000069 grad: 0.0997 (0.1095) loss: 0.8457 (0.8491) time: 0.1562 data: 0.0571 max mem: 8452 +Train: [49] [ 800/6250] eta: 0:15:22 lr: 0.000069 grad: 0.0938 (0.1082) loss: 0.8457 (0.8480) time: 0.1665 data: 0.0825 max mem: 8452 +Train: [49] [ 900/6250] eta: 0:15:04 lr: 0.000069 grad: 0.0928 (0.1073) loss: 0.8519 (0.8471) time: 0.1835 data: 0.0980 max mem: 8452 +Train: [49] [1000/6250] eta: 0:14:39 lr: 0.000069 grad: 0.0970 (0.1061) loss: 0.8467 (0.8467) time: 0.1585 data: 0.0802 max mem: 8452 +Train: [49] [1100/6250] eta: 0:14:25 lr: 0.000069 grad: 0.0900 (0.1057) loss: 0.8415 (0.8461) time: 0.1530 data: 0.0766 max mem: 8452 +Train: [49] [1200/6250] eta: 0:14:00 lr: 0.000069 grad: 0.0912 (0.1050) loss: 0.8429 (0.8457) time: 0.1469 data: 0.0733 max mem: 8452 +Train: [49] [1300/6250] eta: 0:13:39 lr: 0.000069 grad: 0.0906 (0.1043) loss: 0.8415 (0.8454) time: 0.1586 data: 0.0779 max mem: 8452 +Train: [49] [1400/6250] eta: 0:13:27 lr: 0.000069 grad: 0.0953 (0.1038) loss: 0.8471 (0.8452) time: 0.2649 data: 0.1873 max mem: 8452 +Train: [49] [1500/6250] eta: 0:13:04 lr: 0.000069 grad: 0.0950 (0.1033) loss: 0.8448 (0.8450) time: 0.1598 data: 0.0854 max mem: 8452 +Train: [49] [1600/6250] eta: 0:12:45 lr: 0.000069 grad: 0.0958 (0.1029) loss: 0.8332 (0.8448) time: 0.1575 data: 0.0756 max mem: 8452 +Train: [49] [1700/6250] eta: 0:12:26 lr: 0.000069 grad: 0.0935 (0.1025) loss: 0.8521 (0.8447) time: 0.1515 data: 0.0688 max mem: 8452 +Train: [49] [1800/6250] eta: 0:12:10 lr: 0.000069 grad: 0.0911 (0.1022) loss: 0.8379 (0.8447) time: 0.1585 data: 0.0877 max mem: 8452 +Train: [49] [1900/6250] eta: 0:11:57 lr: 0.000069 grad: 0.0938 (0.1018) loss: 0.8489 (0.8447) time: 0.1726 data: 0.0991 max mem: 8452 +Train: [49] [2000/6250] eta: 0:11:42 lr: 0.000069 grad: 0.0961 (0.1016) loss: 0.8369 (0.8447) time: 0.1966 data: 0.1257 max mem: 8452 +Train: [49] [2100/6250] eta: 0:11:25 lr: 0.000069 grad: 0.0952 (0.1014) loss: 0.8496 (0.8446) time: 0.1817 data: 0.1028 max mem: 8452 +Train: [49] [2200/6250] eta: 0:11:08 lr: 0.000069 grad: 0.0960 (0.1013) loss: 0.8391 (0.8445) time: 0.1665 data: 0.0836 max mem: 8452 +Train: [49] [2300/6250] eta: 0:10:52 lr: 0.000069 grad: 0.0936 (0.1011) loss: 0.8419 (0.8446) time: 0.1360 data: 0.0563 max mem: 8452 +Train: [49] [2400/6250] eta: 0:10:35 lr: 0.000069 grad: 0.0880 (0.1009) loss: 0.8426 (0.8447) time: 0.1372 data: 0.0470 max mem: 8452 +Train: [49] [2500/6250] eta: 0:10:17 lr: 0.000069 grad: 0.0981 (0.1008) loss: 0.8440 (0.8447) time: 0.1715 data: 0.0883 max mem: 8452 +Train: [49] [2600/6250] eta: 0:10:00 lr: 0.000069 grad: 0.0983 (0.1006) loss: 0.8429 (0.8447) time: 0.1589 data: 0.0785 max mem: 8452 +Train: [49] [2700/6250] eta: 0:09:42 lr: 0.000069 grad: 0.0986 (0.1004) loss: 0.8443 (0.8448) time: 0.1534 data: 0.0730 max mem: 8452 +Train: [49] [2800/6250] eta: 0:09:25 lr: 0.000069 grad: 0.0987 (0.1002) loss: 0.8420 (0.8448) time: 0.1756 data: 0.0937 max mem: 8452 +Train: [49] [2900/6250] eta: 0:09:10 lr: 0.000069 grad: 0.0998 (0.1002) loss: 0.8437 (0.8448) time: 0.1647 data: 0.0824 max mem: 8452 +Train: [49] [3000/6250] eta: 0:08:54 lr: 0.000069 grad: 0.0880 (0.1001) loss: 0.8476 (0.8448) time: 0.1678 data: 0.0809 max mem: 8452 +Train: [49] [3100/6250] eta: 0:08:36 lr: 0.000069 grad: 0.0890 (0.0999) loss: 0.8482 (0.8448) time: 0.1654 data: 0.0727 max mem: 8452 +Train: [49] [3200/6250] eta: 0:08:19 lr: 0.000069 grad: 0.0948 (0.0999) loss: 0.8419 (0.8447) time: 0.1576 data: 0.0653 max mem: 8452 +Train: [49] [3300/6250] eta: 0:08:03 lr: 0.000069 grad: 0.0975 (0.0998) loss: 0.8403 (0.8446) time: 0.1711 data: 0.0774 max mem: 8452 +Train: [49] [3400/6250] eta: 0:07:46 lr: 0.000069 grad: 0.0981 (0.0999) loss: 0.8337 (0.8444) time: 0.1582 data: 0.0687 max mem: 8452 +Train: [49] [3500/6250] eta: 0:07:30 lr: 0.000069 grad: 0.0939 (0.0998) loss: 0.8445 (0.8444) time: 0.1836 data: 0.1069 max mem: 8452 +Train: [49] [3600/6250] eta: 0:07:13 lr: 0.000069 grad: 0.0952 (0.0998) loss: 0.8446 (0.8443) time: 0.1560 data: 0.0830 max mem: 8452 +Train: [49] [3700/6250] eta: 0:06:56 lr: 0.000069 grad: 0.0942 (0.0997) loss: 0.8434 (0.8442) time: 0.1504 data: 0.0623 max mem: 8452 +Train: [49] [3800/6250] eta: 0:06:40 lr: 0.000068 grad: 0.0927 (0.0997) loss: 0.8405 (0.8441) time: 0.1491 data: 0.0612 max mem: 8452 +Train: [49] [3900/6250] eta: 0:06:23 lr: 0.000068 grad: 0.0961 (0.0998) loss: 0.8420 (0.8439) time: 0.1505 data: 0.0574 max mem: 8452 +Train: [49] [4000/6250] eta: 0:06:07 lr: 0.000068 grad: 0.0990 (0.0999) loss: 0.8422 (0.8437) time: 0.1457 data: 0.0687 max mem: 8452 +Train: [49] [4100/6250] eta: 0:05:50 lr: 0.000068 grad: 0.0995 (0.0999) loss: 0.8389 (0.8435) time: 0.1569 data: 0.0681 max mem: 8452 +Train: [49] [4200/6250] eta: 0:05:33 lr: 0.000068 grad: 0.1022 (0.0999) loss: 0.8359 (0.8434) time: 0.1436 data: 0.0499 max mem: 8452 +Train: [49] [4300/6250] eta: 0:05:17 lr: 0.000068 grad: 0.0974 (0.1000) loss: 0.8344 (0.8432) time: 0.1694 data: 0.0748 max mem: 8452 +Train: [49] [4400/6250] eta: 0:05:01 lr: 0.000068 grad: 0.1121 (0.1002) loss: 0.8293 (0.8431) time: 0.1563 data: 0.0680 max mem: 8452 +Train: [49] [4500/6250] eta: 0:04:45 lr: 0.000068 grad: 0.1004 (0.1004) loss: 0.8351 (0.8429) time: 0.1648 data: 0.0801 max mem: 8452 +Train: [49] [4600/6250] eta: 0:04:29 lr: 0.000068 grad: 0.0993 (0.1005) loss: 0.8393 (0.8427) time: 0.1483 data: 0.0692 max mem: 8452 +Train: [49] [4700/6250] eta: 0:04:12 lr: 0.000068 grad: 0.1039 (0.1006) loss: 0.8323 (0.8425) time: 0.1914 data: 0.1076 max mem: 8452 +Train: [49] [4800/6250] eta: 0:03:56 lr: 0.000068 grad: 0.1027 (0.1008) loss: 0.8310 (0.8423) time: 0.1717 data: 0.0974 max mem: 8452 +Train: [49] [4900/6250] eta: 0:03:40 lr: 0.000068 grad: 0.0952 (0.1009) loss: 0.8320 (0.8421) time: 0.1633 data: 0.0704 max mem: 8452 +Train: [49] [5000/6250] eta: 0:03:24 lr: 0.000068 grad: 0.0974 (0.1009) loss: 0.8366 (0.8420) time: 0.1581 data: 0.0662 max mem: 8452 +Train: [49] [5100/6250] eta: 0:03:07 lr: 0.000068 grad: 0.0999 (0.1009) loss: 0.8417 (0.8418) time: 0.1694 data: 0.0728 max mem: 8452 +Train: [49] [5200/6250] eta: 0:02:51 lr: 0.000068 grad: 0.0961 (0.1010) loss: 0.8395 (0.8416) time: 0.1377 data: 0.0409 max mem: 8452 +Train: [49] [5300/6250] eta: 0:02:34 lr: 0.000068 grad: 0.0956 (0.1010) loss: 0.8335 (0.8415) time: 0.1717 data: 0.0812 max mem: 8452 +Train: [49] [5400/6250] eta: 0:02:18 lr: 0.000068 grad: 0.1000 (0.1010) loss: 0.8354 (0.8415) time: 0.1409 data: 0.0499 max mem: 8452 +Train: [49] [5500/6250] eta: 0:02:01 lr: 0.000068 grad: 0.0943 (0.1010) loss: 0.8435 (0.8415) time: 0.1621 data: 0.0965 max mem: 8452 +Train: [49] [5600/6250] eta: 0:01:45 lr: 0.000068 grad: 0.0943 (0.1010) loss: 0.8443 (0.8414) time: 0.1643 data: 0.0751 max mem: 8452 +Train: [49] [5700/6250] eta: 0:01:29 lr: 0.000068 grad: 0.1005 (0.1010) loss: 0.8331 (0.8413) time: 0.1566 data: 0.0658 max mem: 8452 +Train: [49] [5800/6250] eta: 0:01:12 lr: 0.000068 grad: 0.1003 (0.1010) loss: 0.8316 (0.8412) time: 0.1566 data: 0.0721 max mem: 8452 +Train: [49] [5900/6250] eta: 0:00:56 lr: 0.000068 grad: 0.0990 (0.1010) loss: 0.8303 (0.8411) time: 0.1521 data: 0.0732 max mem: 8452 +Train: [49] [6000/6250] eta: 0:00:40 lr: 0.000068 grad: 0.1010 (0.1010) loss: 0.8311 (0.8410) time: 0.1298 data: 0.0341 max mem: 8452 +Train: [49] [6100/6250] eta: 0:00:24 lr: 0.000068 grad: 0.0944 (0.1010) loss: 0.8390 (0.8410) time: 0.1739 data: 0.0956 max mem: 8452 +Train: [49] [6200/6250] eta: 0:00:08 lr: 0.000068 grad: 0.0992 (0.1010) loss: 0.8373 (0.8409) time: 0.1671 data: 0.0857 max mem: 8452 +Train: [49] [6249/6250] eta: 0:00:00 lr: 0.000068 grad: 0.0945 (0.1010) loss: 0.8399 (0.8409) time: 0.1487 data: 0.0614 max mem: 8452 +Train: [49] Total time: 0:17:00 (0.1634 s / it) +Averaged stats: lr: 0.000068 grad: 0.0945 (0.1010) loss: 0.8399 (0.8409) +Eval (hcp-train-subset): [49] [ 0/62] eta: 0:03:43 loss: 0.8815 (0.8815) time: 3.6068 data: 3.5296 max mem: 8452 +Eval (hcp-train-subset): [49] [61/62] eta: 0:00:00 loss: 0.8690 (0.8703) time: 0.1254 data: 0.1042 max mem: 8452 +Eval (hcp-train-subset): [49] Total time: 0:00:14 (0.2389 s / it) +Averaged stats (hcp-train-subset): loss: 0.8690 (0.8703) +Making plots (hcp-train-subset): example=33 +Eval (hcp-val): [49] [ 0/62] eta: 0:04:47 loss: 0.8724 (0.8724) time: 4.6431 data: 4.5706 max mem: 8452 +Eval (hcp-val): [49] [61/62] eta: 0:00:00 loss: 0.8737 (0.8749) time: 0.1376 data: 0.1154 max mem: 8452 +Eval (hcp-val): [49] Total time: 0:00:14 (0.2326 s / it) +Averaged stats (hcp-val): loss: 0.8737 (0.8749) +Making plots (hcp-val): example=47 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [50] [ 0/6250] eta: 7:37:01 lr: 0.000068 grad: 0.0532 (0.0532) loss: 0.9095 (0.9095) time: 4.3875 data: 4.2050 max mem: 8452 +Train: [50] [ 100/6250] eta: 0:23:11 lr: 0.000068 grad: 0.0884 (0.1130) loss: 0.8604 (0.8671) time: 0.1542 data: 0.0489 max mem: 8452 +Train: [50] [ 200/6250] eta: 0:20:14 lr: 0.000068 grad: 0.0972 (0.1124) loss: 0.8484 (0.8582) time: 0.1700 data: 0.0695 max mem: 8452 +Train: [50] [ 300/6250] eta: 0:18:43 lr: 0.000068 grad: 0.0888 (0.1094) loss: 0.8513 (0.8535) time: 0.1471 data: 0.0507 max mem: 8452 +Train: [50] [ 400/6250] eta: 0:18:03 lr: 0.000068 grad: 0.0896 (0.1056) loss: 0.8524 (0.8530) time: 0.1910 data: 0.0925 max mem: 8452 +Train: [50] [ 500/6250] eta: 0:17:26 lr: 0.000067 grad: 0.0934 (0.1035) loss: 0.8508 (0.8527) time: 0.1682 data: 0.0745 max mem: 8452 +Train: [50] [ 600/6250] eta: 0:16:50 lr: 0.000067 grad: 0.0923 (0.1018) loss: 0.8506 (0.8524) time: 0.1349 data: 0.0526 max mem: 8452 +Train: [50] [ 700/6250] eta: 0:16:18 lr: 0.000067 grad: 0.0897 (0.1007) loss: 0.8488 (0.8523) time: 0.1820 data: 0.0942 max mem: 8452 +Train: [50] [ 800/6250] eta: 0:15:46 lr: 0.000067 grad: 0.0916 (0.0995) loss: 0.8526 (0.8520) time: 0.1601 data: 0.0749 max mem: 8452 +Train: [50] [ 900/6250] eta: 0:15:28 lr: 0.000067 grad: 0.0872 (0.0989) loss: 0.8511 (0.8516) time: 0.1654 data: 0.0703 max mem: 8452 +Train: [50] [1000/6250] eta: 0:14:59 lr: 0.000067 grad: 0.0933 (0.0984) loss: 0.8467 (0.8512) time: 0.1397 data: 0.0462 max mem: 8452 +Train: [50] [1100/6250] eta: 0:14:37 lr: 0.000067 grad: 0.0932 (0.0980) loss: 0.8545 (0.8510) time: 0.1535 data: 0.0781 max mem: 8452 +Train: [50] [1200/6250] eta: 0:14:10 lr: 0.000067 grad: 0.0918 (0.0978) loss: 0.8436 (0.8506) time: 0.1639 data: 0.0756 max mem: 8452 +Train: [50] [1300/6250] eta: 0:13:46 lr: 0.000067 grad: 0.0881 (0.0975) loss: 0.8494 (0.8501) time: 0.1488 data: 0.0688 max mem: 8452 +Train: [50] [1400/6250] eta: 0:13:27 lr: 0.000067 grad: 0.0934 (0.0973) loss: 0.8376 (0.8495) time: 0.1751 data: 0.0875 max mem: 8452 +Train: [50] [1500/6250] eta: 0:13:24 lr: 0.000067 grad: 0.0951 (0.0974) loss: 0.8430 (0.8491) time: 0.2147 data: 0.1087 max mem: 8452 +Train: [50] [1600/6250] eta: 0:13:01 lr: 0.000067 grad: 0.0920 (0.0975) loss: 0.8425 (0.8488) time: 0.1594 data: 0.0780 max mem: 8452 +Train: [50] [1700/6250] eta: 0:12:45 lr: 0.000067 grad: 0.0924 (0.0975) loss: 0.8412 (0.8484) time: 0.1713 data: 0.0890 max mem: 8452 +Train: [50] [1800/6250] eta: 0:12:33 lr: 0.000067 grad: 0.0970 (0.0975) loss: 0.8385 (0.8480) time: 0.1862 data: 0.1043 max mem: 8452 +Train: [50] [1900/6250] eta: 0:12:24 lr: 0.000067 grad: 0.0964 (0.0975) loss: 0.8403 (0.8475) time: 0.2523 data: 0.1768 max mem: 8452 +Train: [50] [2000/6250] eta: 0:12:04 lr: 0.000067 grad: 0.0970 (0.0975) loss: 0.8420 (0.8473) time: 0.1516 data: 0.0754 max mem: 8452 +Train: [50] [2100/6250] eta: 0:11:47 lr: 0.000067 grad: 0.0951 (0.0976) loss: 0.8440 (0.8470) time: 0.1713 data: 0.0985 max mem: 8452 +Train: [50] [2200/6250] eta: 0:11:28 lr: 0.000067 grad: 0.0986 (0.0977) loss: 0.8325 (0.8467) time: 0.1758 data: 0.0923 max mem: 8452 +Train: [50] [2300/6250] eta: 0:11:12 lr: 0.000067 grad: 0.0919 (0.0977) loss: 0.8346 (0.8463) time: 0.1751 data: 0.1052 max mem: 8452 +Train: [50] [2400/6250] eta: 0:10:55 lr: 0.000067 grad: 0.0956 (0.0978) loss: 0.8414 (0.8461) time: 0.1476 data: 0.0684 max mem: 8452 +Train: [50] [2500/6250] eta: 0:10:38 lr: 0.000067 grad: 0.0945 (0.0978) loss: 0.8361 (0.8458) time: 0.1808 data: 0.0995 max mem: 8452 +Train: [50] [2600/6250] eta: 0:10:21 lr: 0.000067 grad: 0.0956 (0.0979) loss: 0.8421 (0.8455) time: 0.1761 data: 0.1001 max mem: 8452 +Train: [50] [2700/6250] eta: 0:10:05 lr: 0.000067 grad: 0.0978 (0.0980) loss: 0.8377 (0.8454) time: 0.1894 data: 0.1020 max mem: 8452 +Train: [50] [2800/6250] eta: 0:09:49 lr: 0.000067 grad: 0.1064 (0.0981) loss: 0.8310 (0.8451) time: 0.1798 data: 0.0897 max mem: 8452 +Train: [50] [2900/6250] eta: 0:09:32 lr: 0.000067 grad: 0.1047 (0.0984) loss: 0.8370 (0.8448) time: 0.1890 data: 0.1029 max mem: 8452 +Train: [50] [3000/6250] eta: 0:09:14 lr: 0.000067 grad: 0.0929 (0.0985) loss: 0.8391 (0.8446) time: 0.1944 data: 0.1226 max mem: 8452 +Train: [50] [3100/6250] eta: 0:08:57 lr: 0.000067 grad: 0.0970 (0.0985) loss: 0.8440 (0.8445) time: 0.1739 data: 0.0975 max mem: 8452 +Train: [50] [3200/6250] eta: 0:08:40 lr: 0.000067 grad: 0.0974 (0.0985) loss: 0.8387 (0.8443) time: 0.1604 data: 0.0659 max mem: 8452 +Train: [50] [3300/6250] eta: 0:08:23 lr: 0.000067 grad: 0.0984 (0.0985) loss: 0.8464 (0.8442) time: 0.1749 data: 0.1005 max mem: 8452 +Train: [50] [3400/6250] eta: 0:08:05 lr: 0.000067 grad: 0.0982 (0.0988) loss: 0.8419 (0.8441) time: 0.1567 data: 0.0645 max mem: 8452 +Train: [50] [3500/6250] eta: 0:07:47 lr: 0.000067 grad: 0.0989 (0.0988) loss: 0.8363 (0.8440) time: 0.1479 data: 0.0658 max mem: 8452 +Train: [50] [3600/6250] eta: 0:07:29 lr: 0.000066 grad: 0.0984 (0.0987) loss: 0.8432 (0.8440) time: 0.1438 data: 0.0596 max mem: 8452 +Train: [50] [3700/6250] eta: 0:07:12 lr: 0.000066 grad: 0.0910 (0.0986) loss: 0.8462 (0.8439) time: 0.1747 data: 0.0865 max mem: 8452 +Train: [50] [3800/6250] eta: 0:06:54 lr: 0.000066 grad: 0.0947 (0.0985) loss: 0.8477 (0.8439) time: 0.1627 data: 0.0815 max mem: 8452 +Train: [50] [3900/6250] eta: 0:06:36 lr: 0.000066 grad: 0.0928 (0.0985) loss: 0.8479 (0.8439) time: 0.1684 data: 0.0909 max mem: 8452 +Train: [50] [4000/6250] eta: 0:06:19 lr: 0.000066 grad: 0.0954 (0.0984) loss: 0.8489 (0.8439) time: 0.1588 data: 0.0761 max mem: 8452 +Train: [50] [4100/6250] eta: 0:06:02 lr: 0.000066 grad: 0.0973 (0.0984) loss: 0.8444 (0.8439) time: 0.1330 data: 0.0500 max mem: 8452 +Train: [50] [4200/6250] eta: 0:05:44 lr: 0.000066 grad: 0.0998 (0.0984) loss: 0.8415 (0.8440) time: 0.1457 data: 0.0740 max mem: 8452 +Train: [50] [4300/6250] eta: 0:05:27 lr: 0.000066 grad: 0.0971 (0.0985) loss: 0.8485 (0.8440) time: 0.1558 data: 0.0824 max mem: 8452 +Train: [50] [4400/6250] eta: 0:05:10 lr: 0.000066 grad: 0.0945 (0.0985) loss: 0.8415 (0.8440) time: 0.1768 data: 0.1021 max mem: 8452 +Train: [50] [4500/6250] eta: 0:04:53 lr: 0.000066 grad: 0.0995 (0.0985) loss: 0.8420 (0.8440) time: 0.1582 data: 0.0723 max mem: 8452 +Train: [50] [4600/6250] eta: 0:04:36 lr: 0.000066 grad: 0.0947 (0.0985) loss: 0.8491 (0.8440) time: 0.2187 data: 0.1344 max mem: 8452 +Train: [50] [4700/6250] eta: 0:04:19 lr: 0.000066 grad: 0.0969 (0.0985) loss: 0.8419 (0.8440) time: 0.1649 data: 0.0674 max mem: 8452 +Train: [50] [4800/6250] eta: 0:04:02 lr: 0.000066 grad: 0.0976 (0.0985) loss: 0.8451 (0.8439) time: 0.1391 data: 0.0561 max mem: 8452 +Train: [50] [4900/6250] eta: 0:03:46 lr: 0.000066 grad: 0.0988 (0.0985) loss: 0.8478 (0.8439) time: 0.2403 data: 0.0818 max mem: 8452 +Train: [50] [5000/6250] eta: 0:03:29 lr: 0.000066 grad: 0.0938 (0.0986) loss: 0.8457 (0.8438) time: 0.1821 data: 0.1015 max mem: 8452 +Train: [50] [5100/6250] eta: 0:03:12 lr: 0.000066 grad: 0.0962 (0.0986) loss: 0.8316 (0.8437) time: 0.1545 data: 0.0645 max mem: 8452 +Train: [50] [5200/6250] eta: 0:02:55 lr: 0.000066 grad: 0.0968 (0.0987) loss: 0.8400 (0.8436) time: 0.1640 data: 0.0935 max mem: 8452 +Train: [50] [5300/6250] eta: 0:02:39 lr: 0.000066 grad: 0.1066 (0.0988) loss: 0.8367 (0.8435) time: 0.1712 data: 0.0866 max mem: 8452 +Train: [50] [5400/6250] eta: 0:02:22 lr: 0.000066 grad: 0.1007 (0.0989) loss: 0.8357 (0.8434) time: 0.1514 data: 0.0584 max mem: 8452 +Train: [50] [5500/6250] eta: 0:02:05 lr: 0.000066 grad: 0.0996 (0.0989) loss: 0.8406 (0.8433) time: 0.1757 data: 0.1040 max mem: 8452 +Train: [50] [5600/6250] eta: 0:01:49 lr: 0.000066 grad: 0.1021 (0.0990) loss: 0.8352 (0.8432) time: 0.2214 data: 0.1204 max mem: 8452 +Train: [50] [5700/6250] eta: 0:01:32 lr: 0.000066 grad: 0.1011 (0.0990) loss: 0.8359 (0.8430) time: 0.2570 data: 0.1622 max mem: 8452 +Train: [50] [5800/6250] eta: 0:01:15 lr: 0.000066 grad: 0.0975 (0.0991) loss: 0.8329 (0.8429) time: 0.1603 data: 0.0720 max mem: 8452 +Train: [50] [5900/6250] eta: 0:00:58 lr: 0.000066 grad: 0.1006 (0.0992) loss: 0.8359 (0.8427) time: 0.1815 data: 0.1026 max mem: 8452 +Train: [50] [6000/6250] eta: 0:00:41 lr: 0.000066 grad: 0.0967 (0.0992) loss: 0.8358 (0.8427) time: 0.1893 data: 0.1081 max mem: 8452 +Train: [50] [6100/6250] eta: 0:00:25 lr: 0.000066 grad: 0.1079 (0.0993) loss: 0.8355 (0.8426) time: 0.1698 data: 0.0903 max mem: 8452 +Train: [50] [6200/6250] eta: 0:00:08 lr: 0.000066 grad: 0.1026 (0.0994) loss: 0.8356 (0.8424) time: 0.1451 data: 0.0612 max mem: 8452 +Train: [50] [6249/6250] eta: 0:00:00 lr: 0.000066 grad: 0.0985 (0.0994) loss: 0.8368 (0.8424) time: 0.0986 data: 0.0002 max mem: 8452 +Train: [50] Total time: 0:17:37 (0.1692 s / it) +Averaged stats: lr: 0.000066 grad: 0.0985 (0.0994) loss: 0.8368 (0.8424) +Eval (hcp-train-subset): [50] [ 0/62] eta: 0:04:03 loss: 0.8793 (0.8793) time: 3.9289 data: 3.8701 max mem: 8452 +Eval (hcp-train-subset): [50] [61/62] eta: 0:00:00 loss: 0.8724 (0.8725) time: 0.1339 data: 0.1124 max mem: 8452 +Eval (hcp-train-subset): [50] Total time: 0:00:15 (0.2453 s / it) +Averaged stats (hcp-train-subset): loss: 0.8724 (0.8725) +Eval (hcp-val): [50] [ 0/62] eta: 0:05:54 loss: 0.8719 (0.8719) time: 5.7205 data: 5.6941 max mem: 8452 +Eval (hcp-val): [50] [61/62] eta: 0:00:00 loss: 0.8718 (0.8743) time: 0.1325 data: 0.1113 max mem: 8452 +Eval (hcp-val): [50] Total time: 0:00:14 (0.2308 s / it) +Averaged stats (hcp-val): loss: 0.8718 (0.8743) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [51] [ 0/6250] eta: 9:46:09 lr: 0.000066 grad: 0.0765 (0.0765) loss: 0.8732 (0.8732) time: 5.6271 data: 5.4825 max mem: 8452 +Train: [51] [ 100/6250] eta: 0:21:53 lr: 0.000066 grad: 0.1018 (0.1098) loss: 0.8642 (0.8717) time: 0.1610 data: 0.0555 max mem: 8452 +Train: [51] [ 200/6250] eta: 0:19:17 lr: 0.000066 grad: 0.0995 (0.1039) loss: 0.8639 (0.8673) time: 0.1707 data: 0.0851 max mem: 8452 +Train: [51] [ 300/6250] eta: 0:17:57 lr: 0.000065 grad: 0.0876 (0.1020) loss: 0.8594 (0.8649) time: 0.1653 data: 0.0779 max mem: 8452 +Train: [51] [ 400/6250] eta: 0:16:59 lr: 0.000065 grad: 0.0872 (0.0999) loss: 0.8574 (0.8630) time: 0.1508 data: 0.0632 max mem: 8452 +Train: [51] [ 500/6250] eta: 0:16:26 lr: 0.000065 grad: 0.0894 (0.0988) loss: 0.8621 (0.8618) time: 0.1358 data: 0.0510 max mem: 8452 +Train: [51] [ 600/6250] eta: 0:15:52 lr: 0.000065 grad: 0.0919 (0.0980) loss: 0.8553 (0.8606) time: 0.1479 data: 0.0584 max mem: 8452 +Train: [51] [ 700/6250] eta: 0:15:28 lr: 0.000065 grad: 0.0884 (0.0976) loss: 0.8570 (0.8595) time: 0.1747 data: 0.0793 max mem: 8452 +Train: [51] [ 800/6250] eta: 0:15:08 lr: 0.000065 grad: 0.0975 (0.0973) loss: 0.8467 (0.8580) time: 0.1653 data: 0.0758 max mem: 8452 +Train: [51] [ 900/6250] eta: 0:14:51 lr: 0.000065 grad: 0.0965 (0.0970) loss: 0.8432 (0.8567) time: 0.1491 data: 0.0560 max mem: 8452 +Train: [51] [1000/6250] eta: 0:14:33 lr: 0.000065 grad: 0.0941 (0.0969) loss: 0.8371 (0.8553) time: 0.1753 data: 0.0946 max mem: 8452 +Train: [51] [1100/6250] eta: 0:14:12 lr: 0.000065 grad: 0.0935 (0.0969) loss: 0.8432 (0.8543) time: 0.1677 data: 0.0907 max mem: 8452 +Train: [51] [1200/6250] eta: 0:13:51 lr: 0.000065 grad: 0.0891 (0.0967) loss: 0.8481 (0.8534) time: 0.1396 data: 0.0609 max mem: 8452 +Train: [51] [1300/6250] eta: 0:13:37 lr: 0.000065 grad: 0.0942 (0.0967) loss: 0.8462 (0.8526) time: 0.2211 data: 0.1432 max mem: 8452 +Train: [51] [1400/6250] eta: 0:13:17 lr: 0.000065 grad: 0.0936 (0.0966) loss: 0.8417 (0.8519) time: 0.1646 data: 0.0745 max mem: 8452 +Train: [51] [1500/6250] eta: 0:13:08 lr: 0.000065 grad: 0.0914 (0.0965) loss: 0.8389 (0.8512) time: 0.1169 data: 0.0003 max mem: 8452 +Train: [51] [1600/6250] eta: 0:12:48 lr: 0.000065 grad: 0.0952 (0.0966) loss: 0.8420 (0.8505) time: 0.1409 data: 0.0577 max mem: 8452 +Train: [51] [1700/6250] eta: 0:12:29 lr: 0.000065 grad: 0.0957 (0.0964) loss: 0.8391 (0.8500) time: 0.1628 data: 0.0811 max mem: 8452 +Train: [51] [1800/6250] eta: 0:12:08 lr: 0.000065 grad: 0.0966 (0.0964) loss: 0.8364 (0.8495) time: 0.1332 data: 0.0450 max mem: 8452 +Train: [51] [1900/6250] eta: 0:11:51 lr: 0.000065 grad: 0.0968 (0.0965) loss: 0.8412 (0.8491) time: 0.1553 data: 0.0768 max mem: 8452 +Train: [51] [2000/6250] eta: 0:11:38 lr: 0.000065 grad: 0.0971 (0.0966) loss: 0.8440 (0.8487) time: 0.1849 data: 0.1110 max mem: 8452 +Train: [51] [2100/6250] eta: 0:11:21 lr: 0.000065 grad: 0.1027 (0.0969) loss: 0.8327 (0.8482) time: 0.1849 data: 0.1102 max mem: 8452 +Train: [51] [2200/6250] eta: 0:11:04 lr: 0.000065 grad: 0.0985 (0.0971) loss: 0.8464 (0.8479) time: 0.1848 data: 0.1146 max mem: 8452 +Train: [51] [2300/6250] eta: 0:10:48 lr: 0.000065 grad: 0.0981 (0.0972) loss: 0.8343 (0.8475) time: 0.1524 data: 0.0774 max mem: 8452 +Train: [51] [2400/6250] eta: 0:10:32 lr: 0.000065 grad: 0.0978 (0.0973) loss: 0.8398 (0.8472) time: 0.1552 data: 0.0680 max mem: 8452 +Train: [51] [2500/6250] eta: 0:10:16 lr: 0.000065 grad: 0.0909 (0.0974) loss: 0.8437 (0.8469) time: 0.1646 data: 0.0632 max mem: 8452 +Train: [51] [2600/6250] eta: 0:10:00 lr: 0.000065 grad: 0.1009 (0.0976) loss: 0.8379 (0.8465) time: 0.1694 data: 0.0999 max mem: 8452 +Train: [51] [2700/6250] eta: 0:09:43 lr: 0.000065 grad: 0.0976 (0.0977) loss: 0.8390 (0.8462) time: 0.1799 data: 0.1101 max mem: 8452 +Train: [51] [2800/6250] eta: 0:09:27 lr: 0.000065 grad: 0.0959 (0.0979) loss: 0.8317 (0.8458) time: 0.1684 data: 0.0930 max mem: 8452 +Train: [51] [2900/6250] eta: 0:09:09 lr: 0.000065 grad: 0.0934 (0.0979) loss: 0.8382 (0.8456) time: 0.1293 data: 0.0509 max mem: 8452 +Train: [51] [3000/6250] eta: 0:08:53 lr: 0.000065 grad: 0.0963 (0.0980) loss: 0.8356 (0.8453) time: 0.1482 data: 0.0636 max mem: 8452 +Train: [51] [3100/6250] eta: 0:08:36 lr: 0.000065 grad: 0.0973 (0.0980) loss: 0.8386 (0.8451) time: 0.1481 data: 0.0566 max mem: 8452 +Train: [51] [3200/6250] eta: 0:08:18 lr: 0.000065 grad: 0.1009 (0.0981) loss: 0.8316 (0.8448) time: 0.1451 data: 0.0574 max mem: 8452 +Train: [51] [3300/6250] eta: 0:08:01 lr: 0.000065 grad: 0.0923 (0.0980) loss: 0.8437 (0.8448) time: 0.1662 data: 0.0850 max mem: 8452 +Train: [51] [3400/6250] eta: 0:07:43 lr: 0.000064 grad: 0.0953 (0.0981) loss: 0.8382 (0.8446) time: 0.1417 data: 0.0494 max mem: 8452 +Train: [51] [3500/6250] eta: 0:07:26 lr: 0.000064 grad: 0.0995 (0.0982) loss: 0.8371 (0.8445) time: 0.1665 data: 0.0935 max mem: 8452 +Train: [51] [3600/6250] eta: 0:07:09 lr: 0.000064 grad: 0.0944 (0.0982) loss: 0.8408 (0.8444) time: 0.1545 data: 0.0789 max mem: 8452 +Train: [51] [3700/6250] eta: 0:06:53 lr: 0.000064 grad: 0.0910 (0.0981) loss: 0.8434 (0.8444) time: 0.1353 data: 0.0505 max mem: 8452 +Train: [51] [3800/6250] eta: 0:06:36 lr: 0.000064 grad: 0.0892 (0.0981) loss: 0.8449 (0.8443) time: 0.1474 data: 0.0599 max mem: 8452 +Train: [51] [3900/6250] eta: 0:06:20 lr: 0.000064 grad: 0.0931 (0.0981) loss: 0.8415 (0.8442) time: 0.1532 data: 0.0792 max mem: 8452 +Train: [51] [4000/6250] eta: 0:06:04 lr: 0.000064 grad: 0.0960 (0.0981) loss: 0.8392 (0.8441) time: 0.1762 data: 0.1004 max mem: 8452 +Train: [51] [4100/6250] eta: 0:05:48 lr: 0.000064 grad: 0.0984 (0.0981) loss: 0.8367 (0.8440) time: 0.1692 data: 0.0917 max mem: 8452 +Train: [51] [4200/6250] eta: 0:05:31 lr: 0.000064 grad: 0.0936 (0.0981) loss: 0.8472 (0.8440) time: 0.1505 data: 0.0559 max mem: 8452 +Train: [51] [4300/6250] eta: 0:05:15 lr: 0.000064 grad: 0.0955 (0.0981) loss: 0.8464 (0.8439) time: 0.1803 data: 0.0924 max mem: 8452 +Train: [51] [4400/6250] eta: 0:05:00 lr: 0.000064 grad: 0.0911 (0.0981) loss: 0.8386 (0.8439) time: 0.1639 data: 0.0884 max mem: 8452 +Train: [51] [4500/6250] eta: 0:04:43 lr: 0.000064 grad: 0.1003 (0.0981) loss: 0.8426 (0.8439) time: 0.1591 data: 0.0879 max mem: 8452 +Train: [51] [4600/6250] eta: 0:04:27 lr: 0.000064 grad: 0.0972 (0.0981) loss: 0.8537 (0.8439) time: 0.1501 data: 0.0701 max mem: 8452 +Train: [51] [4700/6250] eta: 0:04:11 lr: 0.000064 grad: 0.0937 (0.0981) loss: 0.8424 (0.8438) time: 0.1737 data: 0.0987 max mem: 8452 +Train: [51] [4800/6250] eta: 0:03:55 lr: 0.000064 grad: 0.0969 (0.0981) loss: 0.8415 (0.8437) time: 0.1545 data: 0.0636 max mem: 8452 +Train: [51] [4900/6250] eta: 0:03:38 lr: 0.000064 grad: 0.0946 (0.0981) loss: 0.8409 (0.8436) time: 0.1624 data: 0.0778 max mem: 8452 +Train: [51] [5000/6250] eta: 0:03:22 lr: 0.000064 grad: 0.0997 (0.0981) loss: 0.8361 (0.8436) time: 0.1352 data: 0.0500 max mem: 8452 +Train: [51] [5100/6250] eta: 0:03:06 lr: 0.000064 grad: 0.0962 (0.0981) loss: 0.8441 (0.8436) time: 0.1677 data: 0.0820 max mem: 8452 +Train: [51] [5200/6250] eta: 0:02:49 lr: 0.000064 grad: 0.0945 (0.0981) loss: 0.8415 (0.8436) time: 0.1546 data: 0.0699 max mem: 8452 +Train: [51] [5300/6250] eta: 0:02:33 lr: 0.000064 grad: 0.1034 (0.0981) loss: 0.8335 (0.8436) time: 0.1799 data: 0.0913 max mem: 8452 +Train: [51] [5400/6250] eta: 0:02:17 lr: 0.000064 grad: 0.0946 (0.0980) loss: 0.8447 (0.8436) time: 0.1288 data: 0.0549 max mem: 8452 +Train: [51] [5500/6250] eta: 0:02:01 lr: 0.000064 grad: 0.0940 (0.0981) loss: 0.8549 (0.8436) time: 0.1566 data: 0.0806 max mem: 8452 +Train: [51] [5600/6250] eta: 0:01:44 lr: 0.000064 grad: 0.0932 (0.0981) loss: 0.8398 (0.8436) time: 0.1459 data: 0.0659 max mem: 8452 +Train: [51] [5700/6250] eta: 0:01:28 lr: 0.000064 grad: 0.0920 (0.0981) loss: 0.8372 (0.8436) time: 0.1630 data: 0.0849 max mem: 8452 +Train: [51] [5800/6250] eta: 0:01:12 lr: 0.000064 grad: 0.0921 (0.0980) loss: 0.8417 (0.8436) time: 0.2206 data: 0.1467 max mem: 8452 +Train: [51] [5900/6250] eta: 0:00:56 lr: 0.000064 grad: 0.0954 (0.0981) loss: 0.8503 (0.8437) time: 0.1664 data: 0.0937 max mem: 8452 +Train: [51] [6000/6250] eta: 0:00:40 lr: 0.000064 grad: 0.1005 (0.0981) loss: 0.8449 (0.8437) time: 0.1835 data: 0.1009 max mem: 8452 +Train: [51] [6100/6250] eta: 0:00:24 lr: 0.000064 grad: 0.0921 (0.0981) loss: 0.8495 (0.8436) time: 0.1827 data: 0.0979 max mem: 8452 +Train: [51] [6200/6250] eta: 0:00:08 lr: 0.000064 grad: 0.1000 (0.0981) loss: 0.8501 (0.8437) time: 0.1701 data: 0.0810 max mem: 8452 +Train: [51] [6249/6250] eta: 0:00:00 lr: 0.000064 grad: 0.1029 (0.0981) loss: 0.8411 (0.8437) time: 0.1910 data: 0.1112 max mem: 8452 +Train: [51] Total time: 0:16:53 (0.1621 s / it) +Averaged stats: lr: 0.000064 grad: 0.1029 (0.0981) loss: 0.8411 (0.8437) +Eval (hcp-train-subset): [51] [ 0/62] eta: 0:06:21 loss: 0.8796 (0.8796) time: 6.1453 data: 6.1188 max mem: 8452 +Eval (hcp-train-subset): [51] [61/62] eta: 0:00:00 loss: 0.8722 (0.8721) time: 0.1507 data: 0.1276 max mem: 8452 +Eval (hcp-train-subset): [51] Total time: 0:00:15 (0.2474 s / it) +Averaged stats (hcp-train-subset): loss: 0.8722 (0.8721) +Eval (hcp-val): [51] [ 0/62] eta: 0:04:16 loss: 0.8704 (0.8704) time: 4.1324 data: 4.0461 max mem: 8452 +Eval (hcp-val): [51] [61/62] eta: 0:00:00 loss: 0.8722 (0.8749) time: 0.1485 data: 0.1265 max mem: 8452 +Eval (hcp-val): [51] Total time: 0:00:15 (0.2449 s / it) +Averaged stats (hcp-val): loss: 0.8722 (0.8749) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [52] [ 0/6250] eta: 8:53:35 lr: 0.000064 grad: 0.1111 (0.1111) loss: 0.8784 (0.8784) time: 5.1225 data: 4.8952 max mem: 8452 +Train: [52] [ 100/6250] eta: 0:24:49 lr: 0.000063 grad: 0.1129 (0.1401) loss: 0.8538 (0.8681) time: 0.1895 data: 0.0913 max mem: 8452 +Train: [52] [ 200/6250] eta: 0:21:37 lr: 0.000063 grad: 0.1037 (0.1287) loss: 0.8396 (0.8590) time: 0.1841 data: 0.0833 max mem: 8452 +Train: [52] [ 300/6250] eta: 0:20:20 lr: 0.000063 grad: 0.1030 (0.1249) loss: 0.8523 (0.8537) time: 0.1785 data: 0.0769 max mem: 8452 +Train: [52] [ 400/6250] eta: 0:19:17 lr: 0.000063 grad: 0.1054 (0.1217) loss: 0.8394 (0.8507) time: 0.1908 data: 0.0888 max mem: 8452 +Train: [52] [ 500/6250] eta: 0:18:42 lr: 0.000063 grad: 0.1089 (0.1191) loss: 0.8385 (0.8487) time: 0.1845 data: 0.0891 max mem: 8452 +Train: [52] [ 600/6250] eta: 0:17:59 lr: 0.000063 grad: 0.0890 (0.1161) loss: 0.8432 (0.8474) time: 0.1721 data: 0.0747 max mem: 8452 +Train: [52] [ 700/6250] eta: 0:17:35 lr: 0.000063 grad: 0.1014 (0.1141) loss: 0.8381 (0.8463) time: 0.2403 data: 0.1425 max mem: 8452 +Train: [52] [ 800/6250] eta: 0:17:06 lr: 0.000063 grad: 0.0991 (0.1126) loss: 0.8405 (0.8456) time: 0.1406 data: 0.0297 max mem: 8452 +Train: [52] [ 900/6250] eta: 0:16:40 lr: 0.000063 grad: 0.0928 (0.1108) loss: 0.8403 (0.8454) time: 0.1961 data: 0.0849 max mem: 8452 +Train: [52] [1000/6250] eta: 0:16:21 lr: 0.000063 grad: 0.1009 (0.1096) loss: 0.8381 (0.8451) time: 0.1938 data: 0.0988 max mem: 8452 +Train: [52] [1100/6250] eta: 0:15:55 lr: 0.000063 grad: 0.0985 (0.1083) loss: 0.8410 (0.8448) time: 0.2040 data: 0.1211 max mem: 8452 +Train: [52] [1200/6250] eta: 0:15:25 lr: 0.000063 grad: 0.0914 (0.1075) loss: 0.8428 (0.8446) time: 0.1412 data: 0.0560 max mem: 8452 +Train: [52] [1300/6250] eta: 0:15:03 lr: 0.000063 grad: 0.0894 (0.1065) loss: 0.8400 (0.8443) time: 0.2011 data: 0.1265 max mem: 8452 +Train: [52] [1400/6250] eta: 0:14:34 lr: 0.000063 grad: 0.0941 (0.1059) loss: 0.8434 (0.8439) time: 0.1654 data: 0.0918 max mem: 8452 +Train: [52] [1500/6250] eta: 0:14:13 lr: 0.000063 grad: 0.0925 (0.1052) loss: 0.8356 (0.8437) time: 0.2081 data: 0.1196 max mem: 8452 +Train: [52] [1600/6250] eta: 0:13:55 lr: 0.000063 grad: 0.0888 (0.1046) loss: 0.8403 (0.8436) time: 0.1719 data: 0.0742 max mem: 8452 +Train: [52] [1700/6250] eta: 0:13:35 lr: 0.000063 grad: 0.0952 (0.1041) loss: 0.8355 (0.8435) time: 0.1421 data: 0.0638 max mem: 8452 +Train: [52] [1800/6250] eta: 0:13:10 lr: 0.000063 grad: 0.0932 (0.1036) loss: 0.8434 (0.8434) time: 0.1382 data: 0.0519 max mem: 8452 +Train: [52] [1900/6250] eta: 0:12:47 lr: 0.000063 grad: 0.0940 (0.1035) loss: 0.8421 (0.8432) time: 0.1506 data: 0.0658 max mem: 8452 +Train: [52] [2000/6250] eta: 0:12:30 lr: 0.000063 grad: 0.0951 (0.1032) loss: 0.8446 (0.8431) time: 0.2432 data: 0.1761 max mem: 8452 +Train: [52] [2100/6250] eta: 0:12:11 lr: 0.000063 grad: 0.0945 (0.1031) loss: 0.8373 (0.8429) time: 0.1806 data: 0.1117 max mem: 8452 +Train: [52] [2200/6250] eta: 0:11:49 lr: 0.000063 grad: 0.0995 (0.1028) loss: 0.8386 (0.8429) time: 0.1381 data: 0.0648 max mem: 8452 +Train: [52] [2300/6250] eta: 0:11:30 lr: 0.000063 grad: 0.0987 (0.1026) loss: 0.8382 (0.8427) time: 0.1686 data: 0.0848 max mem: 8452 +Train: [52] [2400/6250] eta: 0:11:11 lr: 0.000063 grad: 0.0932 (0.1025) loss: 0.8379 (0.8426) time: 0.1582 data: 0.0773 max mem: 8452 +Train: [52] [2500/6250] eta: 0:10:54 lr: 0.000063 grad: 0.0957 (0.1023) loss: 0.8390 (0.8425) time: 0.1735 data: 0.0973 max mem: 8452 +Train: [52] [2600/6250] eta: 0:10:38 lr: 0.000063 grad: 0.1035 (0.1023) loss: 0.8277 (0.8423) time: 0.2405 data: 0.1531 max mem: 8452 +Train: [52] [2700/6250] eta: 0:10:23 lr: 0.000063 grad: 0.1020 (0.1022) loss: 0.8339 (0.8421) time: 0.1690 data: 0.0851 max mem: 8452 +Train: [52] [2800/6250] eta: 0:10:06 lr: 0.000063 grad: 0.0986 (0.1021) loss: 0.8362 (0.8420) time: 0.1688 data: 0.0881 max mem: 8452 +Train: [52] [2900/6250] eta: 0:09:50 lr: 0.000063 grad: 0.0980 (0.1020) loss: 0.8386 (0.8419) time: 0.1962 data: 0.1158 max mem: 8452 +Train: [52] [3000/6250] eta: 0:09:32 lr: 0.000063 grad: 0.0991 (0.1020) loss: 0.8410 (0.8418) time: 0.1759 data: 0.0840 max mem: 8452 +Train: [52] [3100/6250] eta: 0:09:15 lr: 0.000063 grad: 0.0942 (0.1019) loss: 0.8408 (0.8417) time: 0.1723 data: 0.0929 max mem: 8452 +Train: [52] [3200/6250] eta: 0:08:57 lr: 0.000062 grad: 0.1026 (0.1018) loss: 0.8316 (0.8417) time: 0.1655 data: 0.0801 max mem: 8452 +Train: [52] [3300/6250] eta: 0:08:38 lr: 0.000062 grad: 0.0980 (0.1018) loss: 0.8365 (0.8416) time: 0.1720 data: 0.0836 max mem: 8452 +Train: [52] [3400/6250] eta: 0:08:19 lr: 0.000062 grad: 0.0941 (0.1019) loss: 0.8499 (0.8416) time: 0.1512 data: 0.0566 max mem: 8452 +Train: [52] [3500/6250] eta: 0:08:03 lr: 0.000062 grad: 0.0968 (0.1018) loss: 0.8310 (0.8414) time: 0.3227 data: 0.2173 max mem: 8452 +Train: [52] [3600/6250] eta: 0:07:44 lr: 0.000062 grad: 0.0958 (0.1018) loss: 0.8273 (0.8412) time: 0.1508 data: 0.0684 max mem: 8452 +Train: [52] [3700/6250] eta: 0:07:25 lr: 0.000062 grad: 0.0966 (0.1019) loss: 0.8391 (0.8411) time: 0.1488 data: 0.0678 max mem: 8452 +Train: [52] [3800/6250] eta: 0:07:07 lr: 0.000062 grad: 0.0971 (0.1019) loss: 0.8404 (0.8409) time: 0.1886 data: 0.1111 max mem: 8452 +Train: [52] [3900/6250] eta: 0:06:50 lr: 0.000062 grad: 0.0997 (0.1021) loss: 0.8273 (0.8407) time: 0.1854 data: 0.0936 max mem: 8452 +Train: [52] [4000/6250] eta: 0:06:32 lr: 0.000062 grad: 0.1026 (0.1021) loss: 0.8295 (0.8405) time: 0.1711 data: 0.0877 max mem: 8452 +Train: [52] [4100/6250] eta: 0:06:14 lr: 0.000062 grad: 0.1037 (0.1022) loss: 0.8307 (0.8404) time: 0.1918 data: 0.1074 max mem: 8452 +Train: [52] [4200/6250] eta: 0:05:58 lr: 0.000062 grad: 0.1015 (0.1022) loss: 0.8405 (0.8402) time: 0.1538 data: 0.0476 max mem: 8452 +Train: [52] [4300/6250] eta: 0:05:40 lr: 0.000062 grad: 0.0979 (0.1022) loss: 0.8285 (0.8401) time: 0.1440 data: 0.0598 max mem: 8452 +Train: [52] [4400/6250] eta: 0:05:22 lr: 0.000062 grad: 0.0972 (0.1022) loss: 0.8367 (0.8399) time: 0.1623 data: 0.0755 max mem: 8452 +Train: [52] [4500/6250] eta: 0:05:04 lr: 0.000062 grad: 0.1009 (0.1021) loss: 0.8381 (0.8399) time: 0.1524 data: 0.0730 max mem: 8452 +Train: [52] [4600/6250] eta: 0:04:46 lr: 0.000062 grad: 0.0951 (0.1021) loss: 0.8344 (0.8398) time: 0.1466 data: 0.0632 max mem: 8452 +Train: [52] [4700/6250] eta: 0:04:28 lr: 0.000062 grad: 0.1011 (0.1021) loss: 0.8365 (0.8397) time: 0.1514 data: 0.0715 max mem: 8452 +Train: [52] [4800/6250] eta: 0:04:11 lr: 0.000062 grad: 0.0983 (0.1021) loss: 0.8347 (0.8396) time: 0.1646 data: 0.0872 max mem: 8452 +Train: [52] [4900/6250] eta: 0:03:53 lr: 0.000062 grad: 0.0930 (0.1020) loss: 0.8408 (0.8395) time: 0.1781 data: 0.0828 max mem: 8452 +Train: [52] [5000/6250] eta: 0:03:35 lr: 0.000062 grad: 0.0998 (0.1022) loss: 0.8367 (0.8395) time: 0.1579 data: 0.0927 max mem: 8452 +Train: [52] [5100/6250] eta: 0:03:18 lr: 0.000062 grad: 0.0980 (0.1021) loss: 0.8348 (0.8394) time: 0.1522 data: 0.0601 max mem: 8452 +Train: [52] [5200/6250] eta: 0:03:00 lr: 0.000062 grad: 0.0927 (0.1020) loss: 0.8453 (0.8394) time: 0.1443 data: 0.0575 max mem: 8452 +Train: [52] [5300/6250] eta: 0:02:42 lr: 0.000062 grad: 0.0930 (0.1020) loss: 0.8415 (0.8394) time: 0.1577 data: 0.0669 max mem: 8452 +Train: [52] [5400/6250] eta: 0:02:25 lr: 0.000062 grad: 0.0993 (0.1019) loss: 0.8476 (0.8394) time: 0.1648 data: 0.0718 max mem: 8452 +Train: [52] [5500/6250] eta: 0:02:08 lr: 0.000062 grad: 0.0949 (0.1019) loss: 0.8394 (0.8394) time: 0.1625 data: 0.0810 max mem: 8452 +Train: [52] [5600/6250] eta: 0:01:50 lr: 0.000062 grad: 0.0972 (0.1019) loss: 0.8519 (0.8395) time: 0.1667 data: 0.0788 max mem: 8452 +Train: [52] [5700/6250] eta: 0:01:33 lr: 0.000062 grad: 0.0963 (0.1019) loss: 0.8414 (0.8396) time: 0.1778 data: 0.0947 max mem: 8452 +Train: [52] [5800/6250] eta: 0:01:16 lr: 0.000062 grad: 0.0942 (0.1019) loss: 0.8403 (0.8397) time: 0.1805 data: 0.0891 max mem: 8452 +Train: [52] [5900/6250] eta: 0:00:59 lr: 0.000062 grad: 0.0957 (0.1018) loss: 0.8454 (0.8397) time: 0.1185 data: 0.0372 max mem: 8452 +Train: [52] [6000/6250] eta: 0:00:42 lr: 0.000062 grad: 0.1009 (0.1018) loss: 0.8380 (0.8398) time: 0.1644 data: 0.0900 max mem: 8452 +Train: [52] [6100/6250] eta: 0:00:25 lr: 0.000062 grad: 0.1000 (0.1018) loss: 0.8452 (0.8398) time: 0.1859 data: 0.1203 max mem: 8452 +Train: [52] [6200/6250] eta: 0:00:08 lr: 0.000061 grad: 0.1007 (0.1018) loss: 0.8479 (0.8399) time: 0.1360 data: 0.0569 max mem: 8452 +Train: [52] [6249/6250] eta: 0:00:00 lr: 0.000061 grad: 0.0951 (0.1018) loss: 0.8430 (0.8400) time: 0.1565 data: 0.0924 max mem: 8452 +Train: [52] Total time: 0:17:46 (0.1706 s / it) +Averaged stats: lr: 0.000061 grad: 0.0951 (0.1018) loss: 0.8430 (0.8400) +Eval (hcp-train-subset): [52] [ 0/62] eta: 0:06:37 loss: 0.8792 (0.8792) time: 6.4091 data: 6.3813 max mem: 8452 +Eval (hcp-train-subset): [52] [61/62] eta: 0:00:00 loss: 0.8696 (0.8695) time: 0.1237 data: 0.1012 max mem: 8452 +Eval (hcp-train-subset): [52] Total time: 0:00:15 (0.2488 s / it) +Averaged stats (hcp-train-subset): loss: 0.8696 (0.8695) +Eval (hcp-val): [52] [ 0/62] eta: 0:03:50 loss: 0.8673 (0.8673) time: 3.7125 data: 3.6319 max mem: 8452 +Eval (hcp-val): [52] [61/62] eta: 0:00:00 loss: 0.8738 (0.8748) time: 0.1382 data: 0.1172 max mem: 8452 +Eval (hcp-val): [52] Total time: 0:00:14 (0.2328 s / it) +Averaged stats (hcp-val): loss: 0.8738 (0.8748) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [53] [ 0/6250] eta: 10:04:45 lr: 0.000061 grad: 0.1904 (0.1904) loss: 0.8473 (0.8473) time: 5.8056 data: 5.6301 max mem: 8452 +Train: [53] [ 100/6250] eta: 0:23:02 lr: 0.000061 grad: 0.1131 (0.1491) loss: 0.8578 (0.8585) time: 0.1944 data: 0.0935 max mem: 8452 +Train: [53] [ 200/6250] eta: 0:19:51 lr: 0.000061 grad: 0.0947 (0.1282) loss: 0.8524 (0.8551) time: 0.1736 data: 0.0817 max mem: 8452 +Train: [53] [ 300/6250] eta: 0:18:25 lr: 0.000061 grad: 0.0982 (0.1190) loss: 0.8514 (0.8533) time: 0.1970 data: 0.1059 max mem: 8452 +Train: [53] [ 400/6250] eta: 0:17:20 lr: 0.000061 grad: 0.1001 (0.1167) loss: 0.8454 (0.8508) time: 0.1659 data: 0.0759 max mem: 8452 +Train: [53] [ 500/6250] eta: 0:16:40 lr: 0.000061 grad: 0.0908 (0.1138) loss: 0.8525 (0.8503) time: 0.1676 data: 0.0805 max mem: 8452 +Train: [53] [ 600/6250] eta: 0:15:57 lr: 0.000061 grad: 0.0941 (0.1113) loss: 0.8494 (0.8498) time: 0.1392 data: 0.0306 max mem: 8452 +Train: [53] [ 700/6250] eta: 0:15:36 lr: 0.000061 grad: 0.0914 (0.1090) loss: 0.8496 (0.8499) time: 0.1709 data: 0.1002 max mem: 8452 +Train: [53] [ 800/6250] eta: 0:15:18 lr: 0.000061 grad: 0.0880 (0.1072) loss: 0.8543 (0.8501) time: 0.1864 data: 0.1010 max mem: 8452 +Train: [53] [ 900/6250] eta: 0:14:52 lr: 0.000061 grad: 0.0945 (0.1057) loss: 0.8515 (0.8504) time: 0.1450 data: 0.0490 max mem: 8452 +Train: [53] [1000/6250] eta: 0:14:33 lr: 0.000061 grad: 0.0937 (0.1047) loss: 0.8468 (0.8506) time: 0.1856 data: 0.1044 max mem: 8452 +Train: [53] [1100/6250] eta: 0:14:14 lr: 0.000061 grad: 0.0918 (0.1037) loss: 0.8472 (0.8504) time: 0.1776 data: 0.0976 max mem: 8452 +Train: [53] [1200/6250] eta: 0:13:50 lr: 0.000061 grad: 0.0904 (0.1031) loss: 0.8481 (0.8501) time: 0.1656 data: 0.0895 max mem: 8452 +Train: [53] [1300/6250] eta: 0:13:38 lr: 0.000061 grad: 0.0943 (0.1026) loss: 0.8391 (0.8496) time: 0.1845 data: 0.0780 max mem: 8452 +Train: [53] [1400/6250] eta: 0:13:36 lr: 0.000061 grad: 0.0967 (0.1023) loss: 0.8359 (0.8491) time: 0.1930 data: 0.0936 max mem: 8452 +Train: [53] [1500/6250] eta: 0:13:16 lr: 0.000061 grad: 0.1009 (0.1022) loss: 0.8462 (0.8487) time: 0.1826 data: 0.0962 max mem: 8452 +Train: [53] [1600/6250] eta: 0:12:56 lr: 0.000061 grad: 0.0997 (0.1021) loss: 0.8346 (0.8480) time: 0.1539 data: 0.0737 max mem: 8452 +Train: [53] [1700/6250] eta: 0:12:40 lr: 0.000061 grad: 0.0963 (0.1021) loss: 0.8326 (0.8474) time: 0.1587 data: 0.0841 max mem: 8452 +Train: [53] [1800/6250] eta: 0:12:23 lr: 0.000061 grad: 0.0980 (0.1019) loss: 0.8333 (0.8468) time: 0.1676 data: 0.0823 max mem: 8452 +Train: [53] [1900/6250] eta: 0:12:06 lr: 0.000061 grad: 0.0985 (0.1017) loss: 0.8414 (0.8464) time: 0.1454 data: 0.0685 max mem: 8452 +Train: [53] [2000/6250] eta: 0:11:47 lr: 0.000061 grad: 0.0971 (0.1017) loss: 0.8406 (0.8460) time: 0.1400 data: 0.0668 max mem: 8452 +Train: [53] [2100/6250] eta: 0:11:32 lr: 0.000061 grad: 0.0937 (0.1016) loss: 0.8399 (0.8457) time: 0.1645 data: 0.0908 max mem: 8452 +Train: [53] [2200/6250] eta: 0:11:15 lr: 0.000061 grad: 0.1001 (0.1017) loss: 0.8382 (0.8454) time: 0.1543 data: 0.0757 max mem: 8452 +Train: [53] [2300/6250] eta: 0:10:56 lr: 0.000061 grad: 0.1001 (0.1017) loss: 0.8408 (0.8450) time: 0.1411 data: 0.0494 max mem: 8452 +Train: [53] [2400/6250] eta: 0:10:40 lr: 0.000061 grad: 0.0983 (0.1016) loss: 0.8365 (0.8447) time: 0.1650 data: 0.0824 max mem: 8452 +Train: [53] [2500/6250] eta: 0:10:23 lr: 0.000061 grad: 0.0997 (0.1016) loss: 0.8389 (0.8444) time: 0.1670 data: 0.0827 max mem: 8452 +Train: [53] [2600/6250] eta: 0:10:07 lr: 0.000061 grad: 0.0945 (0.1015) loss: 0.8459 (0.8441) time: 0.1551 data: 0.0721 max mem: 8452 +Train: [53] [2700/6250] eta: 0:09:50 lr: 0.000061 grad: 0.1026 (0.1015) loss: 0.8384 (0.8439) time: 0.1561 data: 0.0690 max mem: 8452 +Train: [53] [2800/6250] eta: 0:09:32 lr: 0.000061 grad: 0.1003 (0.1015) loss: 0.8337 (0.8436) time: 0.1767 data: 0.0853 max mem: 8452 +Train: [53] [2900/6250] eta: 0:09:16 lr: 0.000061 grad: 0.0983 (0.1016) loss: 0.8422 (0.8433) time: 0.1941 data: 0.1093 max mem: 8452 +Train: [53] [3000/6250] eta: 0:08:59 lr: 0.000060 grad: 0.0996 (0.1016) loss: 0.8403 (0.8431) time: 0.1747 data: 0.1060 max mem: 8452 +Train: [53] [3100/6250] eta: 0:08:42 lr: 0.000060 grad: 0.0976 (0.1016) loss: 0.8472 (0.8430) time: 0.1606 data: 0.0649 max mem: 8452 +Train: [53] [3200/6250] eta: 0:08:24 lr: 0.000060 grad: 0.1033 (0.1017) loss: 0.8305 (0.8428) time: 0.1594 data: 0.0753 max mem: 8452 +Train: [53] [3300/6250] eta: 0:08:07 lr: 0.000060 grad: 0.1002 (0.1017) loss: 0.8442 (0.8427) time: 0.1462 data: 0.0650 max mem: 8452 +Train: [53] [3400/6250] eta: 0:07:50 lr: 0.000060 grad: 0.0996 (0.1017) loss: 0.8437 (0.8427) time: 0.1475 data: 0.0709 max mem: 8452 +Train: [53] [3500/6250] eta: 0:07:33 lr: 0.000060 grad: 0.0994 (0.1017) loss: 0.8415 (0.8427) time: 0.1573 data: 0.0740 max mem: 8452 +Train: [53] [3600/6250] eta: 0:07:16 lr: 0.000060 grad: 0.1010 (0.1017) loss: 0.8363 (0.8426) time: 0.1403 data: 0.0458 max mem: 8452 +Train: [53] [3700/6250] eta: 0:06:59 lr: 0.000060 grad: 0.0955 (0.1016) loss: 0.8397 (0.8425) time: 0.1267 data: 0.0459 max mem: 8452 +Train: [53] [3800/6250] eta: 0:06:42 lr: 0.000060 grad: 0.0958 (0.1015) loss: 0.8432 (0.8425) time: 0.1556 data: 0.0751 max mem: 8452 +Train: [53] [3900/6250] eta: 0:06:26 lr: 0.000060 grad: 0.0993 (0.1016) loss: 0.8479 (0.8425) time: 0.1470 data: 0.0642 max mem: 8452 +Train: [53] [4000/6250] eta: 0:06:09 lr: 0.000060 grad: 0.0966 (0.1015) loss: 0.8453 (0.8425) time: 0.1668 data: 0.0833 max mem: 8452 +Train: [53] [4100/6250] eta: 0:05:52 lr: 0.000060 grad: 0.1047 (0.1015) loss: 0.8345 (0.8425) time: 0.1394 data: 0.0531 max mem: 8452 +Train: [53] [4200/6250] eta: 0:05:35 lr: 0.000060 grad: 0.1057 (0.1014) loss: 0.8362 (0.8425) time: 0.1541 data: 0.0712 max mem: 8452 +Train: [53] [4300/6250] eta: 0:05:19 lr: 0.000060 grad: 0.1080 (0.1015) loss: 0.8401 (0.8425) time: 0.1505 data: 0.0816 max mem: 8452 +Train: [53] [4400/6250] eta: 0:05:03 lr: 0.000060 grad: 0.0976 (0.1016) loss: 0.8409 (0.8425) time: 0.1979 data: 0.1184 max mem: 8452 +Train: [53] [4500/6250] eta: 0:04:47 lr: 0.000060 grad: 0.1000 (0.1016) loss: 0.8403 (0.8424) time: 0.1698 data: 0.0990 max mem: 8452 +Train: [53] [4600/6250] eta: 0:04:31 lr: 0.000060 grad: 0.1004 (0.1016) loss: 0.8420 (0.8424) time: 0.1979 data: 0.1138 max mem: 8452 +Train: [53] [4700/6250] eta: 0:04:15 lr: 0.000060 grad: 0.0978 (0.1017) loss: 0.8507 (0.8424) time: 0.1799 data: 0.0943 max mem: 8452 +Train: [53] [4800/6250] eta: 0:03:59 lr: 0.000060 grad: 0.0972 (0.1017) loss: 0.8358 (0.8424) time: 0.2134 data: 0.1298 max mem: 8452 +Train: [53] [4900/6250] eta: 0:03:43 lr: 0.000060 grad: 0.0994 (0.1017) loss: 0.8425 (0.8424) time: 0.1738 data: 0.0906 max mem: 8452 +Train: [53] [5000/6250] eta: 0:03:26 lr: 0.000060 grad: 0.1060 (0.1017) loss: 0.8373 (0.8423) time: 0.1500 data: 0.0674 max mem: 8452 +Train: [53] [5100/6250] eta: 0:03:10 lr: 0.000060 grad: 0.0963 (0.1017) loss: 0.8454 (0.8422) time: 0.1648 data: 0.0813 max mem: 8452 +Train: [53] [5200/6250] eta: 0:02:53 lr: 0.000060 grad: 0.0957 (0.1017) loss: 0.8405 (0.8422) time: 0.1673 data: 0.0791 max mem: 8452 +Train: [53] [5300/6250] eta: 0:02:37 lr: 0.000060 grad: 0.1033 (0.1018) loss: 0.8382 (0.8422) time: 0.1766 data: 0.0912 max mem: 8452 +Train: [53] [5400/6250] eta: 0:02:21 lr: 0.000060 grad: 0.0975 (0.1018) loss: 0.8427 (0.8422) time: 0.2646 data: 0.1640 max mem: 8452 +Train: [53] [5500/6250] eta: 0:02:04 lr: 0.000060 grad: 0.0966 (0.1018) loss: 0.8404 (0.8422) time: 0.1433 data: 0.0651 max mem: 8452 +Train: [53] [5600/6250] eta: 0:01:47 lr: 0.000060 grad: 0.1037 (0.1019) loss: 0.8357 (0.8421) time: 0.1682 data: 0.0957 max mem: 8452 +Train: [53] [5700/6250] eta: 0:01:31 lr: 0.000060 grad: 0.1040 (0.1019) loss: 0.8393 (0.8421) time: 0.1353 data: 0.0578 max mem: 8452 +Train: [53] [5800/6250] eta: 0:01:14 lr: 0.000060 grad: 0.1035 (0.1020) loss: 0.8359 (0.8420) time: 0.1887 data: 0.1024 max mem: 8452 +Train: [53] [5900/6250] eta: 0:00:57 lr: 0.000060 grad: 0.1101 (0.1021) loss: 0.8360 (0.8419) time: 0.1419 data: 0.0611 max mem: 8452 +Train: [53] [6000/6250] eta: 0:00:41 lr: 0.000059 grad: 0.1010 (0.1022) loss: 0.8384 (0.8418) time: 0.1493 data: 0.0689 max mem: 8452 +Train: [53] [6100/6250] eta: 0:00:24 lr: 0.000059 grad: 0.0955 (0.1022) loss: 0.8424 (0.8418) time: 0.1314 data: 0.0545 max mem: 8452 +Train: [53] [6200/6250] eta: 0:00:08 lr: 0.000059 grad: 0.1084 (0.1022) loss: 0.8380 (0.8417) time: 0.1592 data: 0.0784 max mem: 8452 +Train: [53] [6249/6250] eta: 0:00:00 lr: 0.000059 grad: 0.1019 (0.1023) loss: 0.8319 (0.8417) time: 0.1514 data: 0.0741 max mem: 8452 +Train: [53] Total time: 0:17:16 (0.1659 s / it) +Averaged stats: lr: 0.000059 grad: 0.1019 (0.1023) loss: 0.8319 (0.8417) +Eval (hcp-train-subset): [53] [ 0/62] eta: 0:03:45 loss: 0.8735 (0.8735) time: 3.6424 data: 3.5782 max mem: 8452 +Eval (hcp-train-subset): [53] [61/62] eta: 0:00:00 loss: 0.8670 (0.8686) time: 0.1299 data: 0.1087 max mem: 8452 +Eval (hcp-train-subset): [53] Total time: 0:00:14 (0.2395 s / it) +Averaged stats (hcp-train-subset): loss: 0.8670 (0.8686) +Eval (hcp-val): [53] [ 0/62] eta: 0:03:38 loss: 0.8723 (0.8723) time: 3.5310 data: 3.4195 max mem: 8452 +Eval (hcp-val): [53] [61/62] eta: 0:00:00 loss: 0.8720 (0.8746) time: 0.1513 data: 0.1304 max mem: 8452 +Eval (hcp-val): [53] Total time: 0:00:14 (0.2372 s / it) +Averaged stats (hcp-val): loss: 0.8720 (0.8746) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [54] [ 0/6250] eta: 10:09:09 lr: 0.000059 grad: 0.2675 (0.2675) loss: 0.8192 (0.8192) time: 5.8479 data: 5.7206 max mem: 8452 +Train: [54] [ 100/6250] eta: 0:21:54 lr: 0.000059 grad: 0.0946 (0.1231) loss: 0.8695 (0.8688) time: 0.1524 data: 0.0545 max mem: 8452 +Train: [54] [ 200/6250] eta: 0:19:33 lr: 0.000059 grad: 0.0981 (0.1127) loss: 0.8572 (0.8643) time: 0.1866 data: 0.1020 max mem: 8452 +Train: [54] [ 300/6250] eta: 0:18:05 lr: 0.000059 grad: 0.0920 (0.1086) loss: 0.8558 (0.8603) time: 0.1735 data: 0.0844 max mem: 8452 +Train: [54] [ 400/6250] eta: 0:17:30 lr: 0.000059 grad: 0.0968 (0.1062) loss: 0.8438 (0.8580) time: 0.1818 data: 0.0831 max mem: 8452 +Train: [54] [ 500/6250] eta: 0:17:02 lr: 0.000059 grad: 0.0933 (0.1051) loss: 0.8542 (0.8566) time: 0.1801 data: 0.0968 max mem: 8452 +Train: [54] [ 600/6250] eta: 0:16:28 lr: 0.000059 grad: 0.0944 (0.1040) loss: 0.8512 (0.8558) time: 0.1663 data: 0.0688 max mem: 8452 +Train: [54] [ 700/6250] eta: 0:15:59 lr: 0.000059 grad: 0.0992 (0.1035) loss: 0.8438 (0.8543) time: 0.1651 data: 0.0746 max mem: 8452 +Train: [54] [ 800/6250] eta: 0:15:40 lr: 0.000059 grad: 0.0982 (0.1026) loss: 0.8420 (0.8534) time: 0.1737 data: 0.0817 max mem: 8452 +Train: [54] [ 900/6250] eta: 0:15:18 lr: 0.000059 grad: 0.0949 (0.1024) loss: 0.8449 (0.8526) time: 0.1712 data: 0.0953 max mem: 8452 +Train: [54] [1000/6250] eta: 0:14:55 lr: 0.000059 grad: 0.1034 (0.1021) loss: 0.8452 (0.8521) time: 0.1728 data: 0.0846 max mem: 8452 +Train: [54] [1100/6250] eta: 0:14:35 lr: 0.000059 grad: 0.0958 (0.1020) loss: 0.8449 (0.8512) time: 0.1254 data: 0.0341 max mem: 8452 +Train: [54] [1200/6250] eta: 0:14:12 lr: 0.000059 grad: 0.0955 (0.1017) loss: 0.8517 (0.8506) time: 0.1493 data: 0.0838 max mem: 8452 +Train: [54] [1300/6250] eta: 0:13:53 lr: 0.000059 grad: 0.1012 (0.1016) loss: 0.8355 (0.8500) time: 0.1924 data: 0.1086 max mem: 8452 +Train: [54] [1400/6250] eta: 0:13:32 lr: 0.000059 grad: 0.0979 (0.1018) loss: 0.8423 (0.8493) time: 0.1622 data: 0.0784 max mem: 8452 +Train: [54] [1500/6250] eta: 0:13:13 lr: 0.000059 grad: 0.1057 (0.1020) loss: 0.8394 (0.8487) time: 0.1508 data: 0.0642 max mem: 8452 +Train: [54] [1600/6250] eta: 0:12:54 lr: 0.000059 grad: 0.1047 (0.1022) loss: 0.8327 (0.8481) time: 0.1586 data: 0.0794 max mem: 8452 +Train: [54] [1700/6250] eta: 0:12:33 lr: 0.000059 grad: 0.1014 (0.1021) loss: 0.8359 (0.8478) time: 0.1526 data: 0.0698 max mem: 8452 +Train: [54] [1800/6250] eta: 0:12:20 lr: 0.000059 grad: 0.0980 (0.1021) loss: 0.8406 (0.8474) time: 0.1534 data: 0.0749 max mem: 8452 +Train: [54] [1900/6250] eta: 0:11:59 lr: 0.000059 grad: 0.1003 (0.1020) loss: 0.8416 (0.8472) time: 0.1445 data: 0.0638 max mem: 8452 +Train: [54] [2000/6250] eta: 0:11:41 lr: 0.000059 grad: 0.0978 (0.1020) loss: 0.8461 (0.8471) time: 0.1650 data: 0.0907 max mem: 8452 +Train: [54] [2100/6250] eta: 0:11:26 lr: 0.000059 grad: 0.0986 (0.1019) loss: 0.8477 (0.8470) time: 0.1404 data: 0.0618 max mem: 8452 +Train: [54] [2200/6250] eta: 0:11:08 lr: 0.000059 grad: 0.0973 (0.1019) loss: 0.8407 (0.8467) time: 0.1409 data: 0.0617 max mem: 8452 +Train: [54] [2300/6250] eta: 0:10:52 lr: 0.000059 grad: 0.0999 (0.1020) loss: 0.8383 (0.8465) time: 0.1157 data: 0.0478 max mem: 8452 +Train: [54] [2400/6250] eta: 0:10:36 lr: 0.000059 grad: 0.1016 (0.1021) loss: 0.8413 (0.8464) time: 0.1664 data: 0.0918 max mem: 8452 +Train: [54] [2500/6250] eta: 0:10:19 lr: 0.000059 grad: 0.1005 (0.1020) loss: 0.8412 (0.8463) time: 0.1566 data: 0.0752 max mem: 8452 +Train: [54] [2600/6250] eta: 0:10:05 lr: 0.000059 grad: 0.0971 (0.1021) loss: 0.8371 (0.8461) time: 0.1537 data: 0.0795 max mem: 8452 +Train: [54] [2700/6250] eta: 0:09:48 lr: 0.000059 grad: 0.0976 (0.1020) loss: 0.8467 (0.8460) time: 0.1906 data: 0.1176 max mem: 8452 +Train: [54] [2800/6250] eta: 0:09:29 lr: 0.000058 grad: 0.1039 (0.1020) loss: 0.8362 (0.8459) time: 0.1328 data: 0.0463 max mem: 8452 +Train: [54] [2900/6250] eta: 0:09:13 lr: 0.000058 grad: 0.0970 (0.1020) loss: 0.8457 (0.8457) time: 0.1622 data: 0.0757 max mem: 8452 +Train: [54] [3000/6250] eta: 0:08:55 lr: 0.000058 grad: 0.0998 (0.1020) loss: 0.8440 (0.8455) time: 0.1626 data: 0.0751 max mem: 8452 +Train: [54] [3100/6250] eta: 0:08:38 lr: 0.000058 grad: 0.0978 (0.1020) loss: 0.8409 (0.8454) time: 0.1592 data: 0.0709 max mem: 8452 +Train: [54] [3200/6250] eta: 0:08:21 lr: 0.000058 grad: 0.1004 (0.1021) loss: 0.8367 (0.8453) time: 0.1547 data: 0.0666 max mem: 8452 +Train: [54] [3300/6250] eta: 0:08:03 lr: 0.000058 grad: 0.1008 (0.1021) loss: 0.8366 (0.8451) time: 0.1447 data: 0.0607 max mem: 8452 +Train: [54] [3400/6250] eta: 0:07:45 lr: 0.000058 grad: 0.0977 (0.1021) loss: 0.8423 (0.8450) time: 0.1482 data: 0.0598 max mem: 8452 +Train: [54] [3500/6250] eta: 0:07:27 lr: 0.000058 grad: 0.0899 (0.1021) loss: 0.8478 (0.8449) time: 0.1599 data: 0.0685 max mem: 8452 +Train: [54] [3600/6250] eta: 0:07:10 lr: 0.000058 grad: 0.1022 (0.1021) loss: 0.8456 (0.8450) time: 0.1448 data: 0.0614 max mem: 8452 +Train: [54] [3700/6250] eta: 0:06:54 lr: 0.000058 grad: 0.1003 (0.1022) loss: 0.8479 (0.8449) time: 0.1827 data: 0.0969 max mem: 8452 +Train: [54] [3800/6250] eta: 0:06:37 lr: 0.000058 grad: 0.1001 (0.1021) loss: 0.8440 (0.8449) time: 0.1435 data: 0.0648 max mem: 8452 +Train: [54] [3900/6250] eta: 0:06:21 lr: 0.000058 grad: 0.0979 (0.1021) loss: 0.8391 (0.8449) time: 0.1511 data: 0.0730 max mem: 8452 +Train: [54] [4000/6250] eta: 0:06:04 lr: 0.000058 grad: 0.0977 (0.1021) loss: 0.8387 (0.8448) time: 0.1525 data: 0.0792 max mem: 8452 +Train: [54] [4100/6250] eta: 0:05:48 lr: 0.000058 grad: 0.1018 (0.1021) loss: 0.8407 (0.8447) time: 0.1635 data: 0.0811 max mem: 8452 +Train: [54] [4200/6250] eta: 0:05:31 lr: 0.000058 grad: 0.1018 (0.1021) loss: 0.8390 (0.8447) time: 0.1701 data: 0.0903 max mem: 8452 +Train: [54] [4300/6250] eta: 0:05:16 lr: 0.000058 grad: 0.1000 (0.1022) loss: 0.8447 (0.8446) time: 0.1605 data: 0.0725 max mem: 8452 +Train: [54] [4400/6250] eta: 0:05:00 lr: 0.000058 grad: 0.1037 (0.1022) loss: 0.8410 (0.8445) time: 0.1945 data: 0.1055 max mem: 8452 +Train: [54] [4500/6250] eta: 0:04:44 lr: 0.000058 grad: 0.0975 (0.1023) loss: 0.8420 (0.8444) time: 0.1574 data: 0.0823 max mem: 8452 +Train: [54] [4600/6250] eta: 0:04:27 lr: 0.000058 grad: 0.1002 (0.1023) loss: 0.8419 (0.8443) time: 0.1563 data: 0.0783 max mem: 8452 +Train: [54] [4700/6250] eta: 0:04:11 lr: 0.000058 grad: 0.1007 (0.1024) loss: 0.8356 (0.8442) time: 0.1680 data: 0.0831 max mem: 8452 +Train: [54] [4800/6250] eta: 0:03:55 lr: 0.000058 grad: 0.1025 (0.1025) loss: 0.8391 (0.8441) time: 0.1398 data: 0.0578 max mem: 8452 +Train: [54] [4900/6250] eta: 0:03:39 lr: 0.000058 grad: 0.1027 (0.1025) loss: 0.8342 (0.8439) time: 0.1601 data: 0.0736 max mem: 8452 +Train: [54] [5000/6250] eta: 0:03:22 lr: 0.000058 grad: 0.1042 (0.1026) loss: 0.8395 (0.8438) time: 0.1562 data: 0.0685 max mem: 8452 +Train: [54] [5100/6250] eta: 0:03:06 lr: 0.000058 grad: 0.0994 (0.1026) loss: 0.8405 (0.8438) time: 0.1320 data: 0.0506 max mem: 8452 +Train: [54] [5200/6250] eta: 0:02:49 lr: 0.000058 grad: 0.1042 (0.1027) loss: 0.8364 (0.8436) time: 0.1452 data: 0.0539 max mem: 8452 +Train: [54] [5300/6250] eta: 0:02:33 lr: 0.000058 grad: 0.1070 (0.1028) loss: 0.8340 (0.8436) time: 0.1697 data: 0.0822 max mem: 8452 +Train: [54] [5400/6250] eta: 0:02:17 lr: 0.000058 grad: 0.1014 (0.1028) loss: 0.8449 (0.8435) time: 0.1547 data: 0.0652 max mem: 8452 +Train: [54] [5500/6250] eta: 0:02:00 lr: 0.000058 grad: 0.0980 (0.1028) loss: 0.8401 (0.8434) time: 0.1153 data: 0.0331 max mem: 8452 +Train: [54] [5600/6250] eta: 0:01:44 lr: 0.000058 grad: 0.1103 (0.1029) loss: 0.8356 (0.8433) time: 0.1596 data: 0.0736 max mem: 8452 +Train: [54] [5700/6250] eta: 0:01:28 lr: 0.000058 grad: 0.1039 (0.1030) loss: 0.8317 (0.8432) time: 0.1575 data: 0.0751 max mem: 8452 +Train: [54] [5800/6250] eta: 0:01:12 lr: 0.000057 grad: 0.1067 (0.1031) loss: 0.8340 (0.8430) time: 0.1717 data: 0.0735 max mem: 8452 +Train: [54] [5900/6250] eta: 0:00:56 lr: 0.000057 grad: 0.1026 (0.1032) loss: 0.8380 (0.8429) time: 0.2005 data: 0.1221 max mem: 8452 +Train: [54] [6000/6250] eta: 0:00:40 lr: 0.000057 grad: 0.1020 (0.1032) loss: 0.8414 (0.8428) time: 0.1719 data: 0.0750 max mem: 8452 +Train: [54] [6100/6250] eta: 0:00:24 lr: 0.000057 grad: 0.1035 (0.1032) loss: 0.8333 (0.8427) time: 0.1363 data: 0.0467 max mem: 8452 +Train: [54] [6200/6250] eta: 0:00:08 lr: 0.000057 grad: 0.1019 (0.1032) loss: 0.8363 (0.8426) time: 0.2111 data: 0.1355 max mem: 8452 +Train: [54] [6249/6250] eta: 0:00:00 lr: 0.000057 grad: 0.1029 (0.1033) loss: 0.8424 (0.8426) time: 0.1900 data: 0.1230 max mem: 8452 +Train: [54] Total time: 0:16:55 (0.1625 s / it) +Averaged stats: lr: 0.000057 grad: 0.1029 (0.1033) loss: 0.8424 (0.8426) +Eval (hcp-train-subset): [54] [ 0/62] eta: 0:04:18 loss: 0.8830 (0.8830) time: 4.1740 data: 4.0858 max mem: 8452 +Eval (hcp-train-subset): [54] [61/62] eta: 0:00:00 loss: 0.8670 (0.8705) time: 0.1308 data: 0.1093 max mem: 8452 +Eval (hcp-train-subset): [54] Total time: 0:00:15 (0.2430 s / it) +Averaged stats (hcp-train-subset): loss: 0.8670 (0.8705) +Making plots (hcp-train-subset): example=12 +Eval (hcp-val): [54] [ 0/62] eta: 0:05:37 loss: 0.8698 (0.8698) time: 5.4411 data: 5.4106 max mem: 8452 +Eval (hcp-val): [54] [61/62] eta: 0:00:00 loss: 0.8711 (0.8739) time: 0.1566 data: 0.1355 max mem: 8452 +Eval (hcp-val): [54] Total time: 0:00:15 (0.2520 s / it) +Averaged stats (hcp-val): loss: 0.8711 (0.8739) +Making plots (hcp-val): example=36 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [55] [ 0/6250] eta: 12:34:54 lr: 0.000057 grad: 0.1719 (0.1719) loss: 0.8561 (0.8561) time: 7.2472 data: 7.1415 max mem: 8452 +Train: [55] [ 100/6250] eta: 0:23:40 lr: 0.000057 grad: 0.1235 (0.1255) loss: 0.8411 (0.8566) time: 0.1926 data: 0.0921 max mem: 8452 +Train: [55] [ 200/6250] eta: 0:20:18 lr: 0.000057 grad: 0.1063 (0.1230) loss: 0.8477 (0.8513) time: 0.1745 data: 0.0872 max mem: 8452 +Train: [55] [ 300/6250] eta: 0:19:02 lr: 0.000057 grad: 0.1014 (0.1171) loss: 0.8503 (0.8503) time: 0.1731 data: 0.0832 max mem: 8452 +Train: [55] [ 400/6250] eta: 0:18:08 lr: 0.000057 grad: 0.0985 (0.1139) loss: 0.8560 (0.8501) time: 0.1746 data: 0.0840 max mem: 8452 +Train: [55] [ 500/6250] eta: 0:17:29 lr: 0.000057 grad: 0.1082 (0.1121) loss: 0.8397 (0.8491) time: 0.1524 data: 0.0596 max mem: 8452 +Train: [55] [ 600/6250] eta: 0:16:56 lr: 0.000057 grad: 0.0994 (0.1107) loss: 0.8435 (0.8482) time: 0.1687 data: 0.0809 max mem: 8452 +Train: [55] [ 700/6250] eta: 0:16:22 lr: 0.000057 grad: 0.0975 (0.1094) loss: 0.8448 (0.8476) time: 0.1625 data: 0.0747 max mem: 8452 +Train: [55] [ 800/6250] eta: 0:15:53 lr: 0.000057 grad: 0.1019 (0.1086) loss: 0.8336 (0.8469) time: 0.1422 data: 0.0496 max mem: 8452 +Train: [55] [ 900/6250] eta: 0:15:32 lr: 0.000057 grad: 0.1050 (0.1082) loss: 0.8467 (0.8467) time: 0.2069 data: 0.1108 max mem: 8452 +Train: [55] [1000/6250] eta: 0:15:06 lr: 0.000057 grad: 0.0975 (0.1073) loss: 0.8476 (0.8467) time: 0.1362 data: 0.0531 max mem: 8452 +Train: [55] [1100/6250] eta: 0:14:41 lr: 0.000057 grad: 0.1057 (0.1066) loss: 0.8385 (0.8465) time: 0.1625 data: 0.0832 max mem: 8452 +Train: [55] [1200/6250] eta: 0:14:16 lr: 0.000057 grad: 0.1008 (0.1064) loss: 0.8394 (0.8460) time: 0.1549 data: 0.0693 max mem: 8452 +Train: [55] [1300/6250] eta: 0:13:53 lr: 0.000057 grad: 0.1024 (0.1062) loss: 0.8414 (0.8458) time: 0.1437 data: 0.0527 max mem: 8452 +Train: [55] [1400/6250] eta: 0:13:35 lr: 0.000057 grad: 0.0955 (0.1059) loss: 0.8432 (0.8455) time: 0.1280 data: 0.0456 max mem: 8452 +Train: [55] [1500/6250] eta: 0:13:18 lr: 0.000057 grad: 0.1000 (0.1056) loss: 0.8398 (0.8453) time: 0.1346 data: 0.0615 max mem: 8452 +Train: [55] [1600/6250] eta: 0:12:59 lr: 0.000057 grad: 0.0993 (0.1056) loss: 0.8454 (0.8450) time: 0.1412 data: 0.0508 max mem: 8452 +Train: [55] [1700/6250] eta: 0:12:40 lr: 0.000057 grad: 0.1019 (0.1055) loss: 0.8320 (0.8448) time: 0.1450 data: 0.0524 max mem: 8452 +Train: [55] [1800/6250] eta: 0:12:21 lr: 0.000057 grad: 0.1081 (0.1056) loss: 0.8429 (0.8446) time: 0.1571 data: 0.0726 max mem: 8452 +Train: [55] [1900/6250] eta: 0:12:01 lr: 0.000057 grad: 0.1047 (0.1056) loss: 0.8422 (0.8445) time: 0.1433 data: 0.0607 max mem: 8452 +Train: [55] [2000/6250] eta: 0:11:42 lr: 0.000057 grad: 0.0995 (0.1055) loss: 0.8420 (0.8443) time: 0.1375 data: 0.0559 max mem: 8452 +Train: [55] [2100/6250] eta: 0:11:25 lr: 0.000057 grad: 0.1045 (0.1055) loss: 0.8363 (0.8440) time: 0.1562 data: 0.0799 max mem: 8452 +Train: [55] [2200/6250] eta: 0:11:11 lr: 0.000057 grad: 0.1041 (0.1055) loss: 0.8450 (0.8439) time: 0.1745 data: 0.1004 max mem: 8452 +Train: [55] [2300/6250] eta: 0:10:54 lr: 0.000057 grad: 0.1022 (0.1055) loss: 0.8343 (0.8438) time: 0.1490 data: 0.0721 max mem: 8452 +Train: [55] [2400/6250] eta: 0:10:36 lr: 0.000057 grad: 0.1020 (0.1054) loss: 0.8384 (0.8436) time: 0.1781 data: 0.0942 max mem: 8452 +Train: [55] [2500/6250] eta: 0:10:24 lr: 0.000057 grad: 0.1008 (0.1056) loss: 0.8372 (0.8435) time: 0.1854 data: 0.1028 max mem: 8452 +Train: [55] [2600/6250] eta: 0:10:09 lr: 0.000056 grad: 0.1007 (0.1055) loss: 0.8377 (0.8434) time: 0.1895 data: 0.1077 max mem: 8452 +Train: [55] [2700/6250] eta: 0:09:53 lr: 0.000056 grad: 0.0996 (0.1054) loss: 0.8439 (0.8433) time: 0.1672 data: 0.0933 max mem: 8452 +Train: [55] [2800/6250] eta: 0:09:38 lr: 0.000056 grad: 0.0959 (0.1053) loss: 0.8411 (0.8432) time: 0.1511 data: 0.0728 max mem: 8452 +Train: [55] [2900/6250] eta: 0:09:23 lr: 0.000056 grad: 0.0996 (0.1053) loss: 0.8458 (0.8431) time: 0.1874 data: 0.1068 max mem: 8452 +Train: [55] [3000/6250] eta: 0:09:06 lr: 0.000056 grad: 0.0995 (0.1051) loss: 0.8405 (0.8431) time: 0.1692 data: 0.0724 max mem: 8452 +Train: [55] [3100/6250] eta: 0:08:49 lr: 0.000056 grad: 0.0969 (0.1050) loss: 0.8377 (0.8431) time: 0.1605 data: 0.0587 max mem: 8452 +Train: [55] [3200/6250] eta: 0:08:32 lr: 0.000056 grad: 0.0948 (0.1048) loss: 0.8404 (0.8431) time: 0.1561 data: 0.0595 max mem: 8452 +Train: [55] [3300/6250] eta: 0:08:14 lr: 0.000056 grad: 0.1009 (0.1046) loss: 0.8431 (0.8431) time: 0.1448 data: 0.0507 max mem: 8452 +Train: [55] [3400/6250] eta: 0:07:57 lr: 0.000056 grad: 0.0983 (0.1044) loss: 0.8419 (0.8432) time: 0.1614 data: 0.0670 max mem: 8452 +Train: [55] [3500/6250] eta: 0:07:41 lr: 0.000056 grad: 0.0988 (0.1044) loss: 0.8417 (0.8432) time: 0.1808 data: 0.0974 max mem: 8452 +Train: [55] [3600/6250] eta: 0:07:23 lr: 0.000056 grad: 0.0952 (0.1043) loss: 0.8374 (0.8433) time: 0.1605 data: 0.0769 max mem: 8452 +Train: [55] [3700/6250] eta: 0:07:06 lr: 0.000056 grad: 0.0958 (0.1042) loss: 0.8464 (0.8433) time: 0.1680 data: 0.0882 max mem: 8452 +Train: [55] [3800/6250] eta: 0:06:49 lr: 0.000056 grad: 0.1077 (0.1043) loss: 0.8414 (0.8432) time: 0.1479 data: 0.0671 max mem: 8452 +Train: [55] [3900/6250] eta: 0:06:32 lr: 0.000056 grad: 0.0976 (0.1043) loss: 0.8428 (0.8432) time: 0.1666 data: 0.0875 max mem: 8452 +Train: [55] [4000/6250] eta: 0:06:15 lr: 0.000056 grad: 0.1006 (0.1043) loss: 0.8463 (0.8431) time: 0.1495 data: 0.0689 max mem: 8452 +Train: [55] [4100/6250] eta: 0:05:58 lr: 0.000056 grad: 0.0994 (0.1042) loss: 0.8460 (0.8431) time: 0.1706 data: 0.0847 max mem: 8452 +Train: [55] [4200/6250] eta: 0:05:41 lr: 0.000056 grad: 0.1036 (0.1042) loss: 0.8261 (0.8430) time: 0.1870 data: 0.1095 max mem: 8452 +Train: [55] [4300/6250] eta: 0:05:24 lr: 0.000056 grad: 0.1040 (0.1042) loss: 0.8437 (0.8430) time: 0.1707 data: 0.0932 max mem: 8452 +Train: [55] [4400/6250] eta: 0:05:08 lr: 0.000056 grad: 0.1017 (0.1042) loss: 0.8416 (0.8430) time: 0.1712 data: 0.0994 max mem: 8452 +Train: [55] [4500/6250] eta: 0:04:51 lr: 0.000056 grad: 0.1023 (0.1042) loss: 0.8435 (0.8430) time: 0.1595 data: 0.0745 max mem: 8452 +Train: [55] [4600/6250] eta: 0:04:34 lr: 0.000056 grad: 0.0993 (0.1043) loss: 0.8412 (0.8429) time: 0.1531 data: 0.0646 max mem: 8452 +Train: [55] [4700/6250] eta: 0:04:17 lr: 0.000056 grad: 0.0997 (0.1043) loss: 0.8465 (0.8428) time: 0.1665 data: 0.0827 max mem: 8452 +Train: [55] [4800/6250] eta: 0:04:01 lr: 0.000056 grad: 0.1003 (0.1043) loss: 0.8424 (0.8427) time: 0.1695 data: 0.0785 max mem: 8452 +Train: [55] [4900/6250] eta: 0:03:44 lr: 0.000056 grad: 0.1037 (0.1043) loss: 0.8449 (0.8427) time: 0.1627 data: 0.0863 max mem: 8452 +Train: [55] [5000/6250] eta: 0:03:27 lr: 0.000056 grad: 0.1072 (0.1044) loss: 0.8398 (0.8426) time: 0.1530 data: 0.0668 max mem: 8452 +Train: [55] [5100/6250] eta: 0:03:10 lr: 0.000056 grad: 0.1045 (0.1044) loss: 0.8353 (0.8424) time: 0.1528 data: 0.0800 max mem: 8452 +Train: [55] [5200/6250] eta: 0:02:54 lr: 0.000056 grad: 0.1088 (0.1044) loss: 0.8402 (0.8423) time: 0.1736 data: 0.0908 max mem: 8452 +Train: [55] [5300/6250] eta: 0:02:37 lr: 0.000056 grad: 0.1084 (0.1044) loss: 0.8462 (0.8423) time: 0.1541 data: 0.0797 max mem: 8452 +Train: [55] [5400/6250] eta: 0:02:20 lr: 0.000056 grad: 0.0995 (0.1045) loss: 0.8448 (0.8422) time: 0.1274 data: 0.0526 max mem: 8452 +Train: [55] [5500/6250] eta: 0:02:03 lr: 0.000056 grad: 0.1006 (0.1045) loss: 0.8326 (0.8422) time: 0.1462 data: 0.0614 max mem: 8452 +Train: [55] [5600/6250] eta: 0:01:47 lr: 0.000055 grad: 0.1047 (0.1045) loss: 0.8401 (0.8421) time: 0.2083 data: 0.1290 max mem: 8452 +Train: [55] [5700/6250] eta: 0:01:30 lr: 0.000055 grad: 0.1076 (0.1046) loss: 0.8370 (0.8421) time: 0.2008 data: 0.1220 max mem: 8452 +Train: [55] [5800/6250] eta: 0:01:14 lr: 0.000055 grad: 0.1030 (0.1046) loss: 0.8354 (0.8420) time: 0.1067 data: 0.0003 max mem: 8452 +Train: [55] [5900/6250] eta: 0:00:57 lr: 0.000055 grad: 0.1058 (0.1046) loss: 0.8336 (0.8419) time: 0.1672 data: 0.0798 max mem: 8452 +Train: [55] [6000/6250] eta: 0:00:41 lr: 0.000055 grad: 0.1030 (0.1046) loss: 0.8296 (0.8418) time: 0.1716 data: 0.0836 max mem: 8452 +Train: [55] [6100/6250] eta: 0:00:24 lr: 0.000055 grad: 0.1073 (0.1047) loss: 0.8304 (0.8417) time: 0.1688 data: 0.1009 max mem: 8452 +Train: [55] [6200/6250] eta: 0:00:08 lr: 0.000055 grad: 0.0988 (0.1047) loss: 0.8400 (0.8416) time: 0.1408 data: 0.0325 max mem: 8452 +Train: [55] [6249/6250] eta: 0:00:00 lr: 0.000055 grad: 0.1002 (0.1046) loss: 0.8421 (0.8416) time: 0.1501 data: 0.0733 max mem: 8452 +Train: [55] Total time: 0:17:17 (0.1659 s / it) +Averaged stats: lr: 0.000055 grad: 0.1002 (0.1046) loss: 0.8421 (0.8416) +Eval (hcp-train-subset): [55] [ 0/62] eta: 0:05:41 loss: 0.8725 (0.8725) time: 5.5003 data: 5.4741 max mem: 8452 +Eval (hcp-train-subset): [55] [61/62] eta: 0:00:00 loss: 0.8682 (0.8690) time: 0.1502 data: 0.1289 max mem: 8452 +Eval (hcp-train-subset): [55] Total time: 0:00:14 (0.2379 s / it) +Averaged stats (hcp-train-subset): loss: 0.8682 (0.8690) +Eval (hcp-val): [55] [ 0/62] eta: 0:05:50 loss: 0.8722 (0.8722) time: 5.6494 data: 5.6228 max mem: 8452 +Eval (hcp-val): [55] [61/62] eta: 0:00:00 loss: 0.8701 (0.8734) time: 0.1457 data: 0.1233 max mem: 8452 +Eval (hcp-val): [55] Total time: 0:00:15 (0.2450 s / it) +Averaged stats (hcp-val): loss: 0.8701 (0.8734) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [56] [ 0/6250] eta: 9:10:41 lr: 0.000055 grad: 0.0891 (0.0891) loss: 0.8882 (0.8882) time: 5.2867 data: 5.0388 max mem: 8452 +Train: [56] [ 100/6250] eta: 0:23:32 lr: 0.000055 grad: 0.1127 (0.1371) loss: 0.8544 (0.8606) time: 0.1989 data: 0.1008 max mem: 8452 +Train: [56] [ 200/6250] eta: 0:19:41 lr: 0.000055 grad: 0.1007 (0.1254) loss: 0.8585 (0.8553) time: 0.1774 data: 0.0754 max mem: 8452 +Train: [56] [ 300/6250] eta: 0:18:37 lr: 0.000055 grad: 0.1097 (0.1194) loss: 0.8486 (0.8540) time: 0.1696 data: 0.0713 max mem: 8452 +Train: [56] [ 400/6250] eta: 0:17:47 lr: 0.000055 grad: 0.1079 (0.1181) loss: 0.8433 (0.8518) time: 0.1404 data: 0.0406 max mem: 8452 +Train: [56] [ 500/6250] eta: 0:17:09 lr: 0.000055 grad: 0.1019 (0.1149) loss: 0.8389 (0.8492) time: 0.1551 data: 0.0599 max mem: 8452 +Train: [56] [ 600/6250] eta: 0:16:40 lr: 0.000055 grad: 0.0906 (0.1123) loss: 0.8496 (0.8486) time: 0.1556 data: 0.0796 max mem: 8452 +Train: [56] [ 700/6250] eta: 0:16:08 lr: 0.000055 grad: 0.0916 (0.1103) loss: 0.8461 (0.8487) time: 0.1542 data: 0.0600 max mem: 8452 +Train: [56] [ 800/6250] eta: 0:15:47 lr: 0.000055 grad: 0.0921 (0.1087) loss: 0.8509 (0.8488) time: 0.1535 data: 0.0751 max mem: 8452 +Train: [56] [ 900/6250] eta: 0:15:24 lr: 0.000055 grad: 0.1000 (0.1077) loss: 0.8387 (0.8484) time: 0.1714 data: 0.0895 max mem: 8452 +Train: [56] [1000/6250] eta: 0:15:02 lr: 0.000055 grad: 0.0933 (0.1068) loss: 0.8458 (0.8481) time: 0.1575 data: 0.0807 max mem: 8452 +Train: [56] [1100/6250] eta: 0:14:37 lr: 0.000055 grad: 0.0958 (0.1061) loss: 0.8394 (0.8476) time: 0.1562 data: 0.0639 max mem: 8452 +Train: [56] [1200/6250] eta: 0:14:15 lr: 0.000055 grad: 0.0994 (0.1058) loss: 0.8336 (0.8471) time: 0.1554 data: 0.0767 max mem: 8452 +Train: [56] [1300/6250] eta: 0:13:52 lr: 0.000055 grad: 0.1089 (0.1056) loss: 0.8336 (0.8464) time: 0.1327 data: 0.0446 max mem: 8452 +Train: [56] [1400/6250] eta: 0:13:30 lr: 0.000055 grad: 0.1016 (0.1053) loss: 0.8381 (0.8458) time: 0.1320 data: 0.0597 max mem: 8452 +Train: [56] [1500/6250] eta: 0:13:11 lr: 0.000055 grad: 0.0982 (0.1052) loss: 0.8380 (0.8453) time: 0.1707 data: 0.1001 max mem: 8452 +Train: [56] [1600/6250] eta: 0:12:55 lr: 0.000055 grad: 0.1034 (0.1053) loss: 0.8310 (0.8447) time: 0.2120 data: 0.1272 max mem: 8452 +Train: [56] [1700/6250] eta: 0:12:38 lr: 0.000055 grad: 0.0938 (0.1052) loss: 0.8393 (0.8442) time: 0.1364 data: 0.0396 max mem: 8452 +Train: [56] [1800/6250] eta: 0:12:22 lr: 0.000055 grad: 0.0987 (0.1052) loss: 0.8386 (0.8438) time: 0.1745 data: 0.0896 max mem: 8452 +Train: [56] [1900/6250] eta: 0:12:04 lr: 0.000055 grad: 0.1031 (0.1052) loss: 0.8341 (0.8435) time: 0.1668 data: 0.0769 max mem: 8452 +Train: [56] [2000/6250] eta: 0:11:46 lr: 0.000055 grad: 0.1046 (0.1050) loss: 0.8426 (0.8432) time: 0.1436 data: 0.0725 max mem: 8452 +Train: [56] [2100/6250] eta: 0:11:30 lr: 0.000055 grad: 0.0975 (0.1049) loss: 0.8424 (0.8431) time: 0.1607 data: 0.0854 max mem: 8452 +Train: [56] [2200/6250] eta: 0:11:13 lr: 0.000055 grad: 0.1038 (0.1048) loss: 0.8357 (0.8429) time: 0.1591 data: 0.0867 max mem: 8452 +Train: [56] [2300/6250] eta: 0:10:56 lr: 0.000055 grad: 0.0977 (0.1047) loss: 0.8401 (0.8428) time: 0.1528 data: 0.0825 max mem: 8452 +Train: [56] [2400/6250] eta: 0:10:39 lr: 0.000054 grad: 0.1013 (0.1045) loss: 0.8384 (0.8427) time: 0.1595 data: 0.0791 max mem: 8452 +Train: [56] [2500/6250] eta: 0:10:26 lr: 0.000054 grad: 0.1004 (0.1045) loss: 0.8432 (0.8427) time: 0.1909 data: 0.1242 max mem: 8452 +Train: [56] [2600/6250] eta: 0:10:11 lr: 0.000054 grad: 0.1029 (0.1045) loss: 0.8411 (0.8426) time: 0.1544 data: 0.0750 max mem: 8452 +Train: [56] [2700/6250] eta: 0:09:52 lr: 0.000054 grad: 0.1028 (0.1045) loss: 0.8416 (0.8426) time: 0.1631 data: 0.0898 max mem: 8452 +Train: [56] [2800/6250] eta: 0:09:35 lr: 0.000054 grad: 0.1052 (0.1046) loss: 0.8327 (0.8425) time: 0.1451 data: 0.0587 max mem: 8452 +Train: [56] [2900/6250] eta: 0:09:17 lr: 0.000054 grad: 0.1023 (0.1046) loss: 0.8432 (0.8425) time: 0.1649 data: 0.0728 max mem: 8452 +Train: [56] [3000/6250] eta: 0:09:00 lr: 0.000054 grad: 0.1053 (0.1046) loss: 0.8421 (0.8425) time: 0.1454 data: 0.0547 max mem: 8452 +Train: [56] [3100/6250] eta: 0:08:42 lr: 0.000054 grad: 0.1026 (0.1048) loss: 0.8378 (0.8425) time: 0.1561 data: 0.0718 max mem: 8452 +Train: [56] [3200/6250] eta: 0:08:24 lr: 0.000054 grad: 0.0998 (0.1048) loss: 0.8390 (0.8424) time: 0.1633 data: 0.0716 max mem: 8452 +Train: [56] [3300/6250] eta: 0:08:06 lr: 0.000054 grad: 0.0985 (0.1047) loss: 0.8470 (0.8425) time: 0.1451 data: 0.0620 max mem: 8452 +Train: [56] [3400/6250] eta: 0:07:47 lr: 0.000054 grad: 0.0998 (0.1046) loss: 0.8440 (0.8424) time: 0.1521 data: 0.0599 max mem: 8452 +Train: [56] [3500/6250] eta: 0:07:31 lr: 0.000054 grad: 0.1004 (0.1047) loss: 0.8430 (0.8424) time: 0.1735 data: 0.0906 max mem: 8452 +Train: [56] [3600/6250] eta: 0:07:15 lr: 0.000054 grad: 0.1068 (0.1047) loss: 0.8360 (0.8424) time: 0.1745 data: 0.0868 max mem: 8452 +Train: [56] [3700/6250] eta: 0:06:58 lr: 0.000054 grad: 0.1053 (0.1048) loss: 0.8438 (0.8423) time: 0.1792 data: 0.0984 max mem: 8452 +Train: [56] [3800/6250] eta: 0:06:42 lr: 0.000054 grad: 0.1025 (0.1049) loss: 0.8418 (0.8422) time: 0.1890 data: 0.1052 max mem: 8452 +Train: [56] [3900/6250] eta: 0:06:25 lr: 0.000054 grad: 0.1084 (0.1051) loss: 0.8310 (0.8420) time: 0.1492 data: 0.0684 max mem: 8452 +Train: [56] [4000/6250] eta: 0:06:09 lr: 0.000054 grad: 0.1043 (0.1052) loss: 0.8317 (0.8418) time: 0.1512 data: 0.0706 max mem: 8452 +Train: [56] [4100/6250] eta: 0:05:53 lr: 0.000054 grad: 0.1047 (0.1053) loss: 0.8413 (0.8417) time: 0.1887 data: 0.1170 max mem: 8452 +Train: [56] [4200/6250] eta: 0:05:38 lr: 0.000054 grad: 0.1092 (0.1053) loss: 0.8411 (0.8416) time: 0.1265 data: 0.0597 max mem: 8452 +Train: [56] [4300/6250] eta: 0:05:21 lr: 0.000054 grad: 0.0990 (0.1054) loss: 0.8365 (0.8414) time: 0.1706 data: 0.0831 max mem: 8452 +Train: [56] [4400/6250] eta: 0:05:05 lr: 0.000054 grad: 0.1066 (0.1054) loss: 0.8355 (0.8413) time: 0.1572 data: 0.0809 max mem: 8452 +Train: [56] [4500/6250] eta: 0:04:49 lr: 0.000054 grad: 0.1069 (0.1055) loss: 0.8364 (0.8412) time: 0.1692 data: 0.0869 max mem: 8452 +Train: [56] [4600/6250] eta: 0:04:32 lr: 0.000054 grad: 0.0999 (0.1055) loss: 0.8358 (0.8411) time: 0.1364 data: 0.0439 max mem: 8452 +Train: [56] [4700/6250] eta: 0:04:16 lr: 0.000054 grad: 0.1021 (0.1055) loss: 0.8408 (0.8410) time: 0.1869 data: 0.1015 max mem: 8452 +Train: [56] [4800/6250] eta: 0:03:59 lr: 0.000054 grad: 0.1043 (0.1055) loss: 0.8353 (0.8408) time: 0.1685 data: 0.0713 max mem: 8452 +Train: [56] [4900/6250] eta: 0:03:42 lr: 0.000054 grad: 0.1057 (0.1055) loss: 0.8350 (0.8408) time: 0.1442 data: 0.0530 max mem: 8452 +Train: [56] [5000/6250] eta: 0:03:26 lr: 0.000054 grad: 0.1054 (0.1055) loss: 0.8356 (0.8407) time: 0.1502 data: 0.0692 max mem: 8452 +Train: [56] [5100/6250] eta: 0:03:09 lr: 0.000054 grad: 0.1162 (0.1057) loss: 0.8334 (0.8406) time: 0.1473 data: 0.0587 max mem: 8452 +Train: [56] [5200/6250] eta: 0:02:53 lr: 0.000054 grad: 0.1032 (0.1058) loss: 0.8353 (0.8405) time: 0.1792 data: 0.1101 max mem: 8452 +Train: [56] [5300/6250] eta: 0:02:36 lr: 0.000054 grad: 0.0988 (0.1058) loss: 0.8372 (0.8405) time: 0.1506 data: 0.0567 max mem: 8452 +Train: [56] [5400/6250] eta: 0:02:20 lr: 0.000054 grad: 0.1086 (0.1058) loss: 0.8366 (0.8405) time: 0.1128 data: 0.0003 max mem: 8452 +Train: [56] [5500/6250] eta: 0:02:03 lr: 0.000053 grad: 0.1038 (0.1058) loss: 0.8397 (0.8404) time: 0.1815 data: 0.0904 max mem: 8452 +Train: [56] [5600/6250] eta: 0:01:47 lr: 0.000053 grad: 0.1062 (0.1059) loss: 0.8359 (0.8403) time: 0.1546 data: 0.0828 max mem: 8452 +Train: [56] [5700/6250] eta: 0:01:30 lr: 0.000053 grad: 0.1037 (0.1060) loss: 0.8374 (0.8403) time: 0.1615 data: 0.0849 max mem: 8452 +Train: [56] [5800/6250] eta: 0:01:14 lr: 0.000053 grad: 0.1022 (0.1060) loss: 0.8326 (0.8401) time: 0.1552 data: 0.0727 max mem: 8452 +Train: [56] [5900/6250] eta: 0:00:57 lr: 0.000053 grad: 0.0980 (0.1061) loss: 0.8377 (0.8401) time: 0.1783 data: 0.0879 max mem: 8452 +Train: [56] [6000/6250] eta: 0:00:41 lr: 0.000053 grad: 0.1081 (0.1061) loss: 0.8358 (0.8401) time: 0.1593 data: 0.0749 max mem: 8452 +Train: [56] [6100/6250] eta: 0:00:24 lr: 0.000053 grad: 0.1088 (0.1062) loss: 0.8401 (0.8400) time: 0.1778 data: 0.0971 max mem: 8452 +Train: [56] [6200/6250] eta: 0:00:08 lr: 0.000053 grad: 0.1038 (0.1062) loss: 0.8334 (0.8400) time: 0.1656 data: 0.0877 max mem: 8452 +Train: [56] [6249/6250] eta: 0:00:00 lr: 0.000053 grad: 0.1022 (0.1062) loss: 0.8406 (0.8400) time: 0.1647 data: 0.0835 max mem: 8452 +Train: [56] Total time: 0:17:15 (0.1658 s / it) +Averaged stats: lr: 0.000053 grad: 0.1022 (0.1062) loss: 0.8406 (0.8400) +Eval (hcp-train-subset): [56] [ 0/62] eta: 0:04:01 loss: 0.8724 (0.8724) time: 3.8909 data: 3.7798 max mem: 8452 +Eval (hcp-train-subset): [56] [61/62] eta: 0:00:00 loss: 0.8677 (0.8683) time: 0.1403 data: 0.1193 max mem: 8452 +Eval (hcp-train-subset): [56] Total time: 0:00:14 (0.2404 s / it) +Averaged stats (hcp-train-subset): loss: 0.8677 (0.8683) +Eval (hcp-val): [56] [ 0/62] eta: 0:03:43 loss: 0.8697 (0.8697) time: 3.6006 data: 3.5056 max mem: 8452 +Eval (hcp-val): [56] [61/62] eta: 0:00:00 loss: 0.8723 (0.8742) time: 0.1473 data: 0.1258 max mem: 8452 +Eval (hcp-val): [56] Total time: 0:00:15 (0.2430 s / it) +Averaged stats (hcp-val): loss: 0.8723 (0.8742) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [57] [ 0/6250] eta: 8:19:34 lr: 0.000053 grad: 0.1987 (0.1987) loss: 0.8977 (0.8977) time: 4.7958 data: 4.4507 max mem: 8452 +Train: [57] [ 100/6250] eta: 0:22:27 lr: 0.000053 grad: 0.1247 (0.1471) loss: 0.8462 (0.8521) time: 0.1818 data: 0.0831 max mem: 8452 +Train: [57] [ 200/6250] eta: 0:19:40 lr: 0.000053 grad: 0.1148 (0.1324) loss: 0.8491 (0.8499) time: 0.1809 data: 0.0769 max mem: 8452 +Train: [57] [ 300/6250] eta: 0:18:20 lr: 0.000053 grad: 0.1041 (0.1265) loss: 0.8450 (0.8491) time: 0.1685 data: 0.0849 max mem: 8452 +Train: [57] [ 400/6250] eta: 0:17:28 lr: 0.000053 grad: 0.1093 (0.1227) loss: 0.8349 (0.8475) time: 0.1629 data: 0.0597 max mem: 8452 +Train: [57] [ 500/6250] eta: 0:16:49 lr: 0.000053 grad: 0.1178 (0.1210) loss: 0.8363 (0.8457) time: 0.1632 data: 0.0662 max mem: 8452 +Train: [57] [ 600/6250] eta: 0:16:17 lr: 0.000053 grad: 0.0987 (0.1189) loss: 0.8443 (0.8447) time: 0.1735 data: 0.0840 max mem: 8452 +Train: [57] [ 700/6250] eta: 0:15:43 lr: 0.000053 grad: 0.1059 (0.1172) loss: 0.8367 (0.8444) time: 0.1376 data: 0.0451 max mem: 8452 +Train: [57] [ 800/6250] eta: 0:15:18 lr: 0.000053 grad: 0.1092 (0.1159) loss: 0.8360 (0.8441) time: 0.1605 data: 0.0778 max mem: 8452 +Train: [57] [ 900/6250] eta: 0:14:58 lr: 0.000053 grad: 0.0970 (0.1149) loss: 0.8457 (0.8437) time: 0.1678 data: 0.0862 max mem: 8452 +Train: [57] [1000/6250] eta: 0:14:41 lr: 0.000053 grad: 0.0985 (0.1140) loss: 0.8452 (0.8435) time: 0.1795 data: 0.0956 max mem: 8452 +Train: [57] [1100/6250] eta: 0:14:25 lr: 0.000053 grad: 0.1013 (0.1134) loss: 0.8387 (0.8430) time: 0.1738 data: 0.0920 max mem: 8452 +Train: [57] [1200/6250] eta: 0:14:07 lr: 0.000053 grad: 0.1072 (0.1130) loss: 0.8345 (0.8425) time: 0.1474 data: 0.0667 max mem: 8452 +Train: [57] [1300/6250] eta: 0:13:52 lr: 0.000053 grad: 0.1059 (0.1127) loss: 0.8384 (0.8418) time: 0.1703 data: 0.0804 max mem: 8452 +Train: [57] [1400/6250] eta: 0:13:35 lr: 0.000053 grad: 0.1055 (0.1121) loss: 0.8360 (0.8415) time: 0.1545 data: 0.0770 max mem: 8452 +Train: [57] [1500/6250] eta: 0:13:19 lr: 0.000053 grad: 0.1047 (0.1120) loss: 0.8361 (0.8409) time: 0.1853 data: 0.1035 max mem: 8452 +Train: [57] [1600/6250] eta: 0:13:00 lr: 0.000053 grad: 0.1039 (0.1114) loss: 0.8401 (0.8406) time: 0.1457 data: 0.0621 max mem: 8452 +Train: [57] [1700/6250] eta: 0:12:42 lr: 0.000053 grad: 0.1018 (0.1112) loss: 0.8345 (0.8402) time: 0.1486 data: 0.0620 max mem: 8452 +Train: [57] [1800/6250] eta: 0:12:25 lr: 0.000053 grad: 0.0998 (0.1108) loss: 0.8369 (0.8398) time: 0.1906 data: 0.1041 max mem: 8452 +Train: [57] [1900/6250] eta: 0:12:06 lr: 0.000053 grad: 0.1063 (0.1107) loss: 0.8391 (0.8395) time: 0.1415 data: 0.0561 max mem: 8452 +Train: [57] [2000/6250] eta: 0:11:47 lr: 0.000053 grad: 0.1110 (0.1106) loss: 0.8391 (0.8393) time: 0.1409 data: 0.0625 max mem: 8452 +Train: [57] [2100/6250] eta: 0:11:32 lr: 0.000053 grad: 0.1039 (0.1105) loss: 0.8341 (0.8389) time: 0.2122 data: 0.1432 max mem: 8452 +Train: [57] [2200/6250] eta: 0:11:14 lr: 0.000053 grad: 0.1001 (0.1104) loss: 0.8342 (0.8387) time: 0.1158 data: 0.0346 max mem: 8452 +Train: [57] [2300/6250] eta: 0:10:57 lr: 0.000052 grad: 0.1127 (0.1103) loss: 0.8282 (0.8385) time: 0.1546 data: 0.0799 max mem: 8452 +Train: [57] [2400/6250] eta: 0:10:43 lr: 0.000052 grad: 0.1005 (0.1101) loss: 0.8365 (0.8382) time: 0.1685 data: 0.0949 max mem: 8452 +Train: [57] [2500/6250] eta: 0:10:27 lr: 0.000052 grad: 0.1053 (0.1100) loss: 0.8306 (0.8380) time: 0.1714 data: 0.0950 max mem: 8452 +Train: [57] [2600/6250] eta: 0:10:10 lr: 0.000052 grad: 0.1012 (0.1098) loss: 0.8354 (0.8378) time: 0.1994 data: 0.1145 max mem: 8452 +Train: [57] [2700/6250] eta: 0:09:57 lr: 0.000052 grad: 0.1058 (0.1097) loss: 0.8380 (0.8377) time: 0.1957 data: 0.0971 max mem: 8452 +Train: [57] [2800/6250] eta: 0:09:42 lr: 0.000052 grad: 0.1021 (0.1096) loss: 0.8373 (0.8375) time: 0.1830 data: 0.0761 max mem: 8452 +Train: [57] [2900/6250] eta: 0:09:26 lr: 0.000052 grad: 0.1067 (0.1096) loss: 0.8277 (0.8374) time: 0.1638 data: 0.0583 max mem: 8452 +Train: [57] [3000/6250] eta: 0:09:10 lr: 0.000052 grad: 0.1045 (0.1096) loss: 0.8354 (0.8373) time: 0.1913 data: 0.0884 max mem: 8452 +Train: [57] [3100/6250] eta: 0:08:54 lr: 0.000052 grad: 0.1111 (0.1096) loss: 0.8270 (0.8372) time: 0.1700 data: 0.0900 max mem: 8452 +Train: [57] [3200/6250] eta: 0:08:36 lr: 0.000052 grad: 0.1053 (0.1095) loss: 0.8369 (0.8371) time: 0.1495 data: 0.0594 max mem: 8452 +Train: [57] [3300/6250] eta: 0:08:19 lr: 0.000052 grad: 0.1040 (0.1094) loss: 0.8275 (0.8371) time: 0.1118 data: 0.0176 max mem: 8452 +Train: [57] [3400/6250] eta: 0:08:01 lr: 0.000052 grad: 0.1021 (0.1094) loss: 0.8412 (0.8370) time: 0.1656 data: 0.0856 max mem: 8452 +Train: [57] [3500/6250] eta: 0:07:44 lr: 0.000052 grad: 0.1045 (0.1094) loss: 0.8379 (0.8369) time: 0.1767 data: 0.0763 max mem: 8452 +Train: [57] [3600/6250] eta: 0:07:27 lr: 0.000052 grad: 0.1029 (0.1093) loss: 0.8282 (0.8370) time: 0.1724 data: 0.0944 max mem: 8452 +Train: [57] [3700/6250] eta: 0:07:09 lr: 0.000052 grad: 0.1042 (0.1093) loss: 0.8362 (0.8370) time: 0.1241 data: 0.0382 max mem: 8452 +Train: [57] [3800/6250] eta: 0:06:52 lr: 0.000052 grad: 0.1039 (0.1091) loss: 0.8344 (0.8370) time: 0.1613 data: 0.0817 max mem: 8452 +Train: [57] [3900/6250] eta: 0:06:35 lr: 0.000052 grad: 0.0998 (0.1090) loss: 0.8392 (0.8371) time: 0.1454 data: 0.0687 max mem: 8452 +Train: [57] [4000/6250] eta: 0:06:17 lr: 0.000052 grad: 0.1013 (0.1089) loss: 0.8383 (0.8372) time: 0.1453 data: 0.0744 max mem: 8452 +Train: [57] [4100/6250] eta: 0:06:00 lr: 0.000052 grad: 0.1000 (0.1088) loss: 0.8431 (0.8373) time: 0.1524 data: 0.0730 max mem: 8452 +Train: [57] [4200/6250] eta: 0:05:44 lr: 0.000052 grad: 0.1006 (0.1087) loss: 0.8455 (0.8374) time: 0.1620 data: 0.0906 max mem: 8452 +Train: [57] [4300/6250] eta: 0:05:27 lr: 0.000052 grad: 0.1002 (0.1086) loss: 0.8393 (0.8375) time: 0.1767 data: 0.0946 max mem: 8452 +Train: [57] [4400/6250] eta: 0:05:10 lr: 0.000052 grad: 0.0990 (0.1085) loss: 0.8426 (0.8375) time: 0.1689 data: 0.1014 max mem: 8452 +Train: [57] [4500/6250] eta: 0:04:54 lr: 0.000052 grad: 0.1068 (0.1086) loss: 0.8355 (0.8375) time: 0.1665 data: 0.0796 max mem: 8452 +Train: [57] [4600/6250] eta: 0:04:37 lr: 0.000052 grad: 0.1021 (0.1086) loss: 0.8350 (0.8376) time: 0.1812 data: 0.0996 max mem: 8452 +Train: [57] [4700/6250] eta: 0:04:20 lr: 0.000052 grad: 0.0983 (0.1086) loss: 0.8352 (0.8376) time: 0.1711 data: 0.0910 max mem: 8452 +Train: [57] [4800/6250] eta: 0:04:03 lr: 0.000052 grad: 0.1061 (0.1085) loss: 0.8397 (0.8376) time: 0.1571 data: 0.0682 max mem: 8452 +Train: [57] [4900/6250] eta: 0:03:46 lr: 0.000052 grad: 0.1073 (0.1086) loss: 0.8344 (0.8376) time: 0.1626 data: 0.0684 max mem: 8452 +Train: [57] [5000/6250] eta: 0:03:29 lr: 0.000052 grad: 0.1057 (0.1085) loss: 0.8338 (0.8376) time: 0.1324 data: 0.0428 max mem: 8452 +Train: [57] [5100/6250] eta: 0:03:12 lr: 0.000052 grad: 0.1005 (0.1085) loss: 0.8341 (0.8376) time: 0.1502 data: 0.0577 max mem: 8452 +Train: [57] [5200/6250] eta: 0:02:55 lr: 0.000052 grad: 0.1031 (0.1086) loss: 0.8491 (0.8376) time: 0.1679 data: 0.0835 max mem: 8452 +Train: [57] [5300/6250] eta: 0:02:38 lr: 0.000052 grad: 0.1013 (0.1085) loss: 0.8430 (0.8376) time: 0.1729 data: 0.0894 max mem: 8452 +Train: [57] [5400/6250] eta: 0:02:21 lr: 0.000051 grad: 0.1083 (0.1085) loss: 0.8319 (0.8376) time: 0.1435 data: 0.0612 max mem: 8452 +Train: [57] [5500/6250] eta: 0:02:05 lr: 0.000051 grad: 0.1082 (0.1086) loss: 0.8356 (0.8376) time: 0.2106 data: 0.1397 max mem: 8452 +Train: [57] [5600/6250] eta: 0:01:48 lr: 0.000051 grad: 0.1061 (0.1086) loss: 0.8354 (0.8376) time: 0.1487 data: 0.0673 max mem: 8452 +Train: [57] [5700/6250] eta: 0:01:31 lr: 0.000051 grad: 0.1015 (0.1086) loss: 0.8410 (0.8376) time: 0.2083 data: 0.1236 max mem: 8452 +Train: [57] [5800/6250] eta: 0:01:14 lr: 0.000051 grad: 0.1105 (0.1087) loss: 0.8349 (0.8376) time: 0.1307 data: 0.0379 max mem: 8452 +Train: [57] [5900/6250] eta: 0:00:58 lr: 0.000051 grad: 0.1071 (0.1087) loss: 0.8351 (0.8375) time: 0.1600 data: 0.0752 max mem: 8452 +Train: [57] [6000/6250] eta: 0:00:41 lr: 0.000051 grad: 0.1059 (0.1087) loss: 0.8306 (0.8373) time: 0.1804 data: 0.1037 max mem: 8452 +Train: [57] [6100/6250] eta: 0:00:24 lr: 0.000051 grad: 0.1045 (0.1087) loss: 0.8350 (0.8372) time: 0.1820 data: 0.1025 max mem: 8452 +Train: [57] [6200/6250] eta: 0:00:08 lr: 0.000051 grad: 0.1094 (0.1087) loss: 0.8304 (0.8372) time: 0.1730 data: 0.0891 max mem: 8452 +Train: [57] [6249/6250] eta: 0:00:00 lr: 0.000051 grad: 0.1024 (0.1087) loss: 0.8301 (0.8372) time: 0.1324 data: 0.0486 max mem: 8452 +Train: [57] Total time: 0:17:22 (0.1668 s / it) +Averaged stats: lr: 0.000051 grad: 0.1024 (0.1087) loss: 0.8301 (0.8372) +Eval (hcp-train-subset): [57] [ 0/62] eta: 0:04:30 loss: 0.8776 (0.8776) time: 4.3631 data: 4.2858 max mem: 8452 +Eval (hcp-train-subset): [57] [61/62] eta: 0:00:00 loss: 0.8678 (0.8705) time: 0.1337 data: 0.1114 max mem: 8452 +Eval (hcp-train-subset): [57] Total time: 0:00:14 (0.2376 s / it) +Averaged stats (hcp-train-subset): loss: 0.8678 (0.8705) +Eval (hcp-val): [57] [ 0/62] eta: 0:05:23 loss: 0.8728 (0.8728) time: 5.2113 data: 5.1769 max mem: 8452 +Eval (hcp-val): [57] [61/62] eta: 0:00:00 loss: 0.8727 (0.8737) time: 0.1405 data: 0.1184 max mem: 8452 +Eval (hcp-val): [57] Total time: 0:00:14 (0.2356 s / it) +Averaged stats (hcp-val): loss: 0.8727 (0.8737) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [58] [ 0/6250] eta: 11:20:46 lr: 0.000051 grad: 0.2021 (0.2021) loss: 0.8992 (0.8992) time: 6.5354 data: 6.4403 max mem: 8452 +Train: [58] [ 100/6250] eta: 0:24:36 lr: 0.000051 grad: 0.1054 (0.1273) loss: 0.8562 (0.8667) time: 0.2124 data: 0.0908 max mem: 8452 +Train: [58] [ 200/6250] eta: 0:21:29 lr: 0.000051 grad: 0.1036 (0.1259) loss: 0.8459 (0.8592) time: 0.1878 data: 0.0883 max mem: 8452 +Train: [58] [ 300/6250] eta: 0:20:21 lr: 0.000051 grad: 0.1001 (0.1221) loss: 0.8477 (0.8541) time: 0.1943 data: 0.1020 max mem: 8452 +Train: [58] [ 400/6250] eta: 0:19:16 lr: 0.000051 grad: 0.1038 (0.1198) loss: 0.8487 (0.8521) time: 0.2048 data: 0.1161 max mem: 8452 +Train: [58] [ 500/6250] eta: 0:18:18 lr: 0.000051 grad: 0.1065 (0.1180) loss: 0.8351 (0.8499) time: 0.1519 data: 0.0623 max mem: 8452 +Train: [58] [ 600/6250] eta: 0:17:38 lr: 0.000051 grad: 0.0999 (0.1161) loss: 0.8449 (0.8482) time: 0.1527 data: 0.0461 max mem: 8452 +Train: [58] [ 700/6250] eta: 0:17:01 lr: 0.000051 grad: 0.1019 (0.1148) loss: 0.8404 (0.8471) time: 0.1632 data: 0.0798 max mem: 8452 +Train: [58] [ 800/6250] eta: 0:16:31 lr: 0.000051 grad: 0.0983 (0.1134) loss: 0.8424 (0.8465) time: 0.1754 data: 0.0827 max mem: 8452 +Train: [58] [ 900/6250] eta: 0:16:06 lr: 0.000051 grad: 0.1058 (0.1126) loss: 0.8354 (0.8459) time: 0.1528 data: 0.0675 max mem: 8452 +Train: [58] [1000/6250] eta: 0:15:40 lr: 0.000051 grad: 0.1073 (0.1120) loss: 0.8334 (0.8452) time: 0.1207 data: 0.0152 max mem: 8452 +Train: [58] [1100/6250] eta: 0:15:20 lr: 0.000051 grad: 0.1008 (0.1121) loss: 0.8374 (0.8441) time: 0.2009 data: 0.1191 max mem: 8452 +Train: [58] [1200/6250] eta: 0:14:50 lr: 0.000051 grad: 0.1025 (0.1116) loss: 0.8328 (0.8432) time: 0.1653 data: 0.0841 max mem: 8452 +Train: [58] [1300/6250] eta: 0:14:29 lr: 0.000051 grad: 0.1056 (0.1113) loss: 0.8281 (0.8423) time: 0.2037 data: 0.1327 max mem: 8452 +Train: [58] [1400/6250] eta: 0:14:03 lr: 0.000051 grad: 0.1025 (0.1109) loss: 0.8244 (0.8416) time: 0.1567 data: 0.0763 max mem: 8452 +Train: [58] [1500/6250] eta: 0:13:43 lr: 0.000051 grad: 0.1079 (0.1107) loss: 0.8327 (0.8411) time: 0.1875 data: 0.1144 max mem: 8452 +Train: [58] [1600/6250] eta: 0:13:24 lr: 0.000051 grad: 0.1020 (0.1104) loss: 0.8326 (0.8406) time: 0.1762 data: 0.0968 max mem: 8452 +Train: [58] [1700/6250] eta: 0:13:02 lr: 0.000051 grad: 0.1075 (0.1103) loss: 0.8324 (0.8402) time: 0.1664 data: 0.0883 max mem: 8452 +Train: [58] [1800/6250] eta: 0:12:45 lr: 0.000051 grad: 0.1036 (0.1101) loss: 0.8307 (0.8399) time: 0.2234 data: 0.1391 max mem: 8452 +Train: [58] [1900/6250] eta: 0:12:22 lr: 0.000051 grad: 0.1059 (0.1101) loss: 0.8378 (0.8397) time: 0.1615 data: 0.0825 max mem: 8452 +Train: [58] [2000/6250] eta: 0:12:02 lr: 0.000051 grad: 0.1072 (0.1102) loss: 0.8340 (0.8394) time: 0.1355 data: 0.0564 max mem: 8452 +Train: [58] [2100/6250] eta: 0:11:45 lr: 0.000051 grad: 0.1061 (0.1102) loss: 0.8302 (0.8392) time: 0.1811 data: 0.0938 max mem: 8452 +Train: [58] [2200/6250] eta: 0:11:33 lr: 0.000050 grad: 0.1100 (0.1102) loss: 0.8328 (0.8389) time: 0.1684 data: 0.0907 max mem: 8452 +Train: [58] [2300/6250] eta: 0:11:18 lr: 0.000050 grad: 0.1078 (0.1100) loss: 0.8322 (0.8386) time: 0.1522 data: 0.0684 max mem: 8452 +Train: [58] [2400/6250] eta: 0:11:04 lr: 0.000050 grad: 0.1044 (0.1099) loss: 0.8347 (0.8385) time: 0.2033 data: 0.1347 max mem: 8452 +Train: [58] [2500/6250] eta: 0:10:51 lr: 0.000050 grad: 0.1063 (0.1099) loss: 0.8369 (0.8383) time: 0.1823 data: 0.0900 max mem: 8452 +Train: [58] [2600/6250] eta: 0:10:35 lr: 0.000050 grad: 0.1038 (0.1100) loss: 0.8314 (0.8383) time: 0.2203 data: 0.1344 max mem: 8452 +Train: [58] [2700/6250] eta: 0:10:20 lr: 0.000050 grad: 0.1068 (0.1099) loss: 0.8372 (0.8383) time: 0.2023 data: 0.1154 max mem: 8452 +Train: [58] [2800/6250] eta: 0:10:03 lr: 0.000050 grad: 0.1181 (0.1100) loss: 0.8338 (0.8382) time: 0.1568 data: 0.0673 max mem: 8452 +Train: [58] [2900/6250] eta: 0:09:47 lr: 0.000050 grad: 0.1033 (0.1100) loss: 0.8315 (0.8380) time: 0.1980 data: 0.1011 max mem: 8452 +Train: [58] [3000/6250] eta: 0:09:30 lr: 0.000050 grad: 0.1039 (0.1100) loss: 0.8356 (0.8379) time: 0.1782 data: 0.0964 max mem: 8452 +Train: [58] [3100/6250] eta: 0:09:13 lr: 0.000050 grad: 0.1144 (0.1101) loss: 0.8289 (0.8377) time: 0.1976 data: 0.0989 max mem: 8452 +Train: [58] [3200/6250] eta: 0:08:54 lr: 0.000050 grad: 0.1084 (0.1102) loss: 0.8391 (0.8375) time: 0.1718 data: 0.0830 max mem: 8452 +Train: [58] [3300/6250] eta: 0:08:35 lr: 0.000050 grad: 0.1128 (0.1102) loss: 0.8289 (0.8375) time: 0.1528 data: 0.0721 max mem: 8452 +Train: [58] [3400/6250] eta: 0:08:17 lr: 0.000050 grad: 0.1080 (0.1103) loss: 0.8321 (0.8373) time: 0.1484 data: 0.0643 max mem: 8452 +Train: [58] [3500/6250] eta: 0:07:59 lr: 0.000050 grad: 0.1041 (0.1103) loss: 0.8319 (0.8371) time: 0.1507 data: 0.0636 max mem: 8452 +Train: [58] [3600/6250] eta: 0:07:40 lr: 0.000050 grad: 0.1042 (0.1103) loss: 0.8364 (0.8370) time: 0.1555 data: 0.0797 max mem: 8452 +Train: [58] [3700/6250] eta: 0:07:25 lr: 0.000050 grad: 0.1090 (0.1104) loss: 0.8335 (0.8369) time: 0.2799 data: 0.1924 max mem: 8452 +Train: [58] [3800/6250] eta: 0:07:06 lr: 0.000050 grad: 0.1107 (0.1104) loss: 0.8307 (0.8368) time: 0.1707 data: 0.0943 max mem: 8452 +Train: [58] [3900/6250] eta: 0:06:47 lr: 0.000050 grad: 0.1125 (0.1105) loss: 0.8330 (0.8367) time: 0.1463 data: 0.0647 max mem: 8452 +Train: [58] [4000/6250] eta: 0:06:29 lr: 0.000050 grad: 0.1109 (0.1105) loss: 0.8342 (0.8366) time: 0.1678 data: 0.0963 max mem: 8452 +Train: [58] [4100/6250] eta: 0:06:11 lr: 0.000050 grad: 0.1025 (0.1105) loss: 0.8377 (0.8365) time: 0.1920 data: 0.1049 max mem: 8452 +Train: [58] [4200/6250] eta: 0:05:55 lr: 0.000050 grad: 0.1027 (0.1106) loss: 0.8367 (0.8365) time: 0.2004 data: 0.1316 max mem: 8452 +Train: [58] [4300/6250] eta: 0:05:37 lr: 0.000050 grad: 0.1050 (0.1106) loss: 0.8336 (0.8364) time: 0.1521 data: 0.0713 max mem: 8452 +Train: [58] [4400/6250] eta: 0:05:20 lr: 0.000050 grad: 0.1079 (0.1106) loss: 0.8390 (0.8364) time: 0.1673 data: 0.0934 max mem: 8452 +Train: [58] [4500/6250] eta: 0:05:02 lr: 0.000050 grad: 0.1141 (0.1107) loss: 0.8386 (0.8364) time: 0.1847 data: 0.1056 max mem: 8452 +Train: [58] [4600/6250] eta: 0:04:45 lr: 0.000050 grad: 0.1126 (0.1107) loss: 0.8361 (0.8363) time: 0.1676 data: 0.0741 max mem: 8452 +Train: [58] [4700/6250] eta: 0:04:27 lr: 0.000050 grad: 0.1043 (0.1107) loss: 0.8375 (0.8363) time: 0.1483 data: 0.0659 max mem: 8452 +Train: [58] [4800/6250] eta: 0:04:09 lr: 0.000050 grad: 0.1129 (0.1106) loss: 0.8335 (0.8363) time: 0.1460 data: 0.0599 max mem: 8452 +Train: [58] [4900/6250] eta: 0:03:52 lr: 0.000050 grad: 0.1014 (0.1105) loss: 0.8429 (0.8363) time: 0.1270 data: 0.0492 max mem: 8452 +Train: [58] [5000/6250] eta: 0:03:34 lr: 0.000050 grad: 0.1034 (0.1106) loss: 0.8350 (0.8363) time: 0.1607 data: 0.0725 max mem: 8452 +Train: [58] [5100/6250] eta: 0:03:17 lr: 0.000050 grad: 0.1038 (0.1105) loss: 0.8466 (0.8364) time: 0.1557 data: 0.0721 max mem: 8452 +Train: [58] [5200/6250] eta: 0:02:59 lr: 0.000050 grad: 0.1043 (0.1105) loss: 0.8338 (0.8365) time: 0.1753 data: 0.1058 max mem: 8452 +Train: [58] [5300/6250] eta: 0:02:42 lr: 0.000049 grad: 0.1110 (0.1105) loss: 0.8430 (0.8365) time: 0.1411 data: 0.0557 max mem: 8452 +Train: [58] [5400/6250] eta: 0:02:24 lr: 0.000049 grad: 0.1080 (0.1104) loss: 0.8350 (0.8365) time: 0.1351 data: 0.0484 max mem: 8452 +Train: [58] [5500/6250] eta: 0:02:07 lr: 0.000049 grad: 0.1043 (0.1104) loss: 0.8388 (0.8365) time: 0.1548 data: 0.0814 max mem: 8452 +Train: [58] [5600/6250] eta: 0:01:50 lr: 0.000049 grad: 0.1009 (0.1102) loss: 0.8435 (0.8366) time: 0.1632 data: 0.0762 max mem: 8452 +Train: [58] [5700/6250] eta: 0:01:33 lr: 0.000049 grad: 0.1035 (0.1101) loss: 0.8480 (0.8367) time: 0.1381 data: 0.0465 max mem: 8452 +Train: [58] [5800/6250] eta: 0:01:16 lr: 0.000049 grad: 0.1077 (0.1101) loss: 0.8346 (0.8368) time: 0.1735 data: 0.0961 max mem: 8452 +Train: [58] [5900/6250] eta: 0:00:59 lr: 0.000049 grad: 0.0997 (0.1100) loss: 0.8409 (0.8368) time: 0.1593 data: 0.0719 max mem: 8452 +Train: [58] [6000/6250] eta: 0:00:42 lr: 0.000049 grad: 0.1053 (0.1100) loss: 0.8356 (0.8368) time: 0.1500 data: 0.0745 max mem: 8452 +Train: [58] [6100/6250] eta: 0:00:25 lr: 0.000049 grad: 0.0990 (0.1100) loss: 0.8453 (0.8369) time: 0.1914 data: 0.1128 max mem: 8452 +Train: [58] [6200/6250] eta: 0:00:08 lr: 0.000049 grad: 0.1070 (0.1100) loss: 0.8344 (0.8368) time: 0.1739 data: 0.0934 max mem: 8452 +Train: [58] [6249/6250] eta: 0:00:00 lr: 0.000049 grad: 0.1043 (0.1100) loss: 0.8381 (0.8368) time: 0.1712 data: 0.0766 max mem: 8452 +Train: [58] Total time: 0:17:46 (0.1706 s / it) +Averaged stats: lr: 0.000049 grad: 0.1043 (0.1100) loss: 0.8381 (0.8368) +Eval (hcp-train-subset): [58] [ 0/62] eta: 0:05:50 loss: 0.8813 (0.8813) time: 5.6505 data: 5.6237 max mem: 8452 +Eval (hcp-train-subset): [58] [61/62] eta: 0:00:00 loss: 0.8653 (0.8674) time: 0.1875 data: 0.1661 max mem: 8452 +Eval (hcp-train-subset): [58] Total time: 0:00:17 (0.2790 s / it) +Averaged stats (hcp-train-subset): loss: 0.8653 (0.8674) +Eval (hcp-val): [58] [ 0/62] eta: 0:04:06 loss: 0.8700 (0.8700) time: 3.9705 data: 3.8593 max mem: 8452 +Eval (hcp-val): [58] [61/62] eta: 0:00:00 loss: 0.8719 (0.8732) time: 0.1724 data: 0.1506 max mem: 8452 +Eval (hcp-val): [58] Total time: 0:00:16 (0.2731 s / it) +Averaged stats (hcp-val): loss: 0.8719 (0.8732) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [59] [ 0/6250] eta: 13:34:54 lr: 0.000049 grad: 0.1656 (0.1656) loss: 0.7882 (0.7882) time: 7.8231 data: 7.6787 max mem: 8452 +Train: [59] [ 100/6250] eta: 0:27:11 lr: 0.000049 grad: 0.1043 (0.1492) loss: 0.8569 (0.8479) time: 0.2029 data: 0.1085 max mem: 8452 +Train: [59] [ 200/6250] eta: 0:22:56 lr: 0.000049 grad: 0.1100 (0.1322) loss: 0.8475 (0.8481) time: 0.1621 data: 0.0473 max mem: 8452 +Train: [59] [ 300/6250] eta: 0:21:20 lr: 0.000049 grad: 0.1100 (0.1283) loss: 0.8394 (0.8466) time: 0.1862 data: 0.0954 max mem: 8452 +Train: [59] [ 400/6250] eta: 0:19:55 lr: 0.000049 grad: 0.1098 (0.1248) loss: 0.8395 (0.8455) time: 0.1873 data: 0.0941 max mem: 8452 +Train: [59] [ 500/6250] eta: 0:19:08 lr: 0.000049 grad: 0.1048 (0.1222) loss: 0.8463 (0.8450) time: 0.1866 data: 0.0593 max mem: 8452 +Train: [59] [ 600/6250] eta: 0:18:19 lr: 0.000049 grad: 0.1140 (0.1214) loss: 0.8403 (0.8441) time: 0.1492 data: 0.0597 max mem: 8452 +Train: [59] [ 700/6250] eta: 0:17:36 lr: 0.000049 grad: 0.1051 (0.1197) loss: 0.8506 (0.8440) time: 0.1596 data: 0.0716 max mem: 8452 +Train: [59] [ 800/6250] eta: 0:17:28 lr: 0.000049 grad: 0.1027 (0.1183) loss: 0.8490 (0.8438) time: 0.2696 data: 0.1875 max mem: 8452 +Train: [59] [ 900/6250] eta: 0:17:00 lr: 0.000049 grad: 0.1038 (0.1174) loss: 0.8450 (0.8434) time: 0.2435 data: 0.1616 max mem: 8452 +Train: [59] [1000/6250] eta: 0:16:35 lr: 0.000049 grad: 0.1052 (0.1164) loss: 0.8422 (0.8433) time: 0.1543 data: 0.0730 max mem: 8452 +Train: [59] [1100/6250] eta: 0:16:04 lr: 0.000049 grad: 0.1078 (0.1157) loss: 0.8382 (0.8432) time: 0.1343 data: 0.0474 max mem: 8452 +Train: [59] [1200/6250] eta: 0:15:36 lr: 0.000049 grad: 0.1020 (0.1150) loss: 0.8417 (0.8430) time: 0.1469 data: 0.0603 max mem: 8452 +Train: [59] [1300/6250] eta: 0:15:17 lr: 0.000049 grad: 0.1088 (0.1147) loss: 0.8416 (0.8427) time: 0.1952 data: 0.1159 max mem: 8452 +Train: [59] [1400/6250] eta: 0:14:52 lr: 0.000049 grad: 0.1084 (0.1141) loss: 0.8395 (0.8427) time: 0.1734 data: 0.0898 max mem: 8452 +Train: [59] [1500/6250] eta: 0:14:30 lr: 0.000049 grad: 0.1103 (0.1138) loss: 0.8373 (0.8425) time: 0.1885 data: 0.1232 max mem: 8452 +Train: [59] [1600/6250] eta: 0:14:20 lr: 0.000049 grad: 0.1092 (0.1135) loss: 0.8358 (0.8423) time: 0.2258 data: 0.1379 max mem: 8452 +Train: [59] [1700/6250] eta: 0:14:04 lr: 0.000049 grad: 0.1022 (0.1132) loss: 0.8384 (0.8420) time: 0.1257 data: 0.0098 max mem: 8452 +Train: [59] [1800/6250] eta: 0:13:46 lr: 0.000049 grad: 0.1047 (0.1130) loss: 0.8307 (0.8416) time: 0.1830 data: 0.1006 max mem: 8452 +Train: [59] [1900/6250] eta: 0:13:24 lr: 0.000049 grad: 0.1068 (0.1129) loss: 0.8343 (0.8412) time: 0.1949 data: 0.1024 max mem: 8452 +Train: [59] [2000/6250] eta: 0:13:03 lr: 0.000049 grad: 0.1049 (0.1128) loss: 0.8325 (0.8407) time: 0.1865 data: 0.1033 max mem: 8452 +Train: [59] [2100/6250] eta: 0:12:41 lr: 0.000048 grad: 0.1076 (0.1127) loss: 0.8253 (0.8402) time: 0.1751 data: 0.0905 max mem: 8452 +Train: [59] [2200/6250] eta: 0:12:22 lr: 0.000048 grad: 0.1021 (0.1126) loss: 0.8414 (0.8398) time: 0.1830 data: 0.0967 max mem: 8452 +Train: [59] [2300/6250] eta: 0:12:04 lr: 0.000048 grad: 0.1112 (0.1126) loss: 0.8271 (0.8393) time: 0.2285 data: 0.1596 max mem: 8452 +Train: [59] [2400/6250] eta: 0:11:45 lr: 0.000048 grad: 0.1018 (0.1124) loss: 0.8332 (0.8390) time: 0.1877 data: 0.1106 max mem: 8452 +Train: [59] [2500/6250] eta: 0:11:24 lr: 0.000048 grad: 0.1065 (0.1123) loss: 0.8216 (0.8386) time: 0.1663 data: 0.0842 max mem: 8452 +Train: [59] [2600/6250] eta: 0:11:02 lr: 0.000048 grad: 0.1033 (0.1121) loss: 0.8337 (0.8385) time: 0.1626 data: 0.0883 max mem: 8452 +Train: [59] [2700/6250] eta: 0:10:43 lr: 0.000048 grad: 0.1089 (0.1120) loss: 0.8324 (0.8383) time: 0.1710 data: 0.0816 max mem: 8452 +Train: [59] [2800/6250] eta: 0:10:23 lr: 0.000048 grad: 0.1067 (0.1119) loss: 0.8331 (0.8382) time: 0.1577 data: 0.0657 max mem: 8452 +Train: [59] [2900/6250] eta: 0:10:03 lr: 0.000048 grad: 0.1141 (0.1118) loss: 0.8321 (0.8380) time: 0.1679 data: 0.0784 max mem: 8452 +Train: [59] [3000/6250] eta: 0:09:43 lr: 0.000048 grad: 0.1116 (0.1118) loss: 0.8305 (0.8378) time: 0.1469 data: 0.0582 max mem: 8452 +Train: [59] [3100/6250] eta: 0:09:23 lr: 0.000048 grad: 0.1138 (0.1117) loss: 0.8372 (0.8377) time: 0.1353 data: 0.0526 max mem: 8452 +Train: [59] [3200/6250] eta: 0:09:02 lr: 0.000048 grad: 0.1062 (0.1117) loss: 0.8366 (0.8376) time: 0.1360 data: 0.0480 max mem: 8452 +Train: [59] [3300/6250] eta: 0:08:44 lr: 0.000048 grad: 0.1149 (0.1117) loss: 0.8294 (0.8374) time: 0.1657 data: 0.0539 max mem: 8452 +Train: [59] [3400/6250] eta: 0:08:25 lr: 0.000048 grad: 0.1076 (0.1118) loss: 0.8252 (0.8373) time: 0.1729 data: 0.0880 max mem: 8452 +Train: [59] [3500/6250] eta: 0:08:07 lr: 0.000048 grad: 0.1090 (0.1119) loss: 0.8331 (0.8371) time: 0.1867 data: 0.1059 max mem: 8452 +Train: [59] [3600/6250] eta: 0:07:49 lr: 0.000048 grad: 0.1133 (0.1120) loss: 0.8255 (0.8370) time: 0.2317 data: 0.1479 max mem: 8452 +Train: [59] [3700/6250] eta: 0:07:30 lr: 0.000048 grad: 0.1122 (0.1120) loss: 0.8352 (0.8369) time: 0.1652 data: 0.0691 max mem: 8452 +Train: [59] [3800/6250] eta: 0:07:12 lr: 0.000048 grad: 0.1078 (0.1120) loss: 0.8289 (0.8367) time: 0.1262 data: 0.0407 max mem: 8452 +Train: [59] [3900/6250] eta: 0:06:53 lr: 0.000048 grad: 0.1097 (0.1120) loss: 0.8330 (0.8367) time: 0.1463 data: 0.0656 max mem: 8452 +Train: [59] [4000/6250] eta: 0:06:36 lr: 0.000048 grad: 0.1011 (0.1119) loss: 0.8333 (0.8367) time: 0.1225 data: 0.0352 max mem: 8452 +Train: [59] [4100/6250] eta: 0:06:18 lr: 0.000048 grad: 0.1099 (0.1119) loss: 0.8369 (0.8367) time: 0.1783 data: 0.0993 max mem: 8452 +Train: [59] [4200/6250] eta: 0:06:00 lr: 0.000048 grad: 0.1069 (0.1119) loss: 0.8351 (0.8367) time: 0.1519 data: 0.0843 max mem: 8452 +Train: [59] [4300/6250] eta: 0:05:42 lr: 0.000048 grad: 0.1050 (0.1120) loss: 0.8319 (0.8367) time: 0.1239 data: 0.0439 max mem: 8452 +Train: [59] [4400/6250] eta: 0:05:24 lr: 0.000048 grad: 0.1066 (0.1119) loss: 0.8385 (0.8367) time: 0.1573 data: 0.0826 max mem: 8452 +Train: [59] [4500/6250] eta: 0:05:06 lr: 0.000048 grad: 0.1116 (0.1118) loss: 0.8373 (0.8368) time: 0.1742 data: 0.0889 max mem: 8452 +Train: [59] [4600/6250] eta: 0:04:48 lr: 0.000048 grad: 0.1085 (0.1119) loss: 0.8429 (0.8367) time: 0.1909 data: 0.1087 max mem: 8452 +Train: [59] [4700/6250] eta: 0:04:31 lr: 0.000048 grad: 0.1068 (0.1118) loss: 0.8426 (0.8367) time: 0.1742 data: 0.0941 max mem: 8452 +Train: [59] [4800/6250] eta: 0:04:13 lr: 0.000048 grad: 0.1085 (0.1118) loss: 0.8396 (0.8367) time: 0.2042 data: 0.1346 max mem: 8452 +Train: [59] [4900/6250] eta: 0:03:55 lr: 0.000048 grad: 0.1118 (0.1117) loss: 0.8370 (0.8368) time: 0.1544 data: 0.0625 max mem: 8452 +Train: [59] [5000/6250] eta: 0:03:37 lr: 0.000048 grad: 0.1079 (0.1117) loss: 0.8456 (0.8367) time: 0.1783 data: 0.1000 max mem: 8452 +Train: [59] [5100/6250] eta: 0:03:19 lr: 0.000048 grad: 0.1110 (0.1117) loss: 0.8268 (0.8366) time: 0.1534 data: 0.0721 max mem: 8452 +Train: [59] [5200/6250] eta: 0:03:02 lr: 0.000047 grad: 0.1061 (0.1118) loss: 0.8299 (0.8365) time: 0.1540 data: 0.0686 max mem: 8452 +Train: [59] [5300/6250] eta: 0:02:44 lr: 0.000047 grad: 0.1079 (0.1117) loss: 0.8283 (0.8365) time: 0.1877 data: 0.1080 max mem: 8452 +Train: [59] [5400/6250] eta: 0:02:27 lr: 0.000047 grad: 0.1110 (0.1117) loss: 0.8364 (0.8365) time: 0.1529 data: 0.0758 max mem: 8452 +Train: [59] [5500/6250] eta: 0:02:09 lr: 0.000047 grad: 0.1011 (0.1117) loss: 0.8325 (0.8365) time: 0.2237 data: 0.1546 max mem: 8452 +Train: [59] [5600/6250] eta: 0:01:52 lr: 0.000047 grad: 0.1148 (0.1118) loss: 0.8317 (0.8364) time: 0.2169 data: 0.1496 max mem: 8452 +Train: [59] [5700/6250] eta: 0:01:35 lr: 0.000047 grad: 0.1088 (0.1118) loss: 0.8258 (0.8363) time: 0.1701 data: 0.1056 max mem: 8452 +Train: [59] [5800/6250] eta: 0:01:18 lr: 0.000047 grad: 0.1089 (0.1119) loss: 0.8370 (0.8362) time: 0.1569 data: 0.0685 max mem: 8452 +Train: [59] [5900/6250] eta: 0:01:00 lr: 0.000047 grad: 0.1104 (0.1119) loss: 0.8293 (0.8361) time: 0.1563 data: 0.0859 max mem: 8452 +Train: [59] [6000/6250] eta: 0:00:43 lr: 0.000047 grad: 0.1038 (0.1119) loss: 0.8361 (0.8361) time: 0.1388 data: 0.0564 max mem: 8452 +Train: [59] [6100/6250] eta: 0:00:25 lr: 0.000047 grad: 0.1126 (0.1119) loss: 0.8276 (0.8360) time: 0.1385 data: 0.0590 max mem: 8452 +Train: [59] [6200/6250] eta: 0:00:08 lr: 0.000047 grad: 0.1050 (0.1119) loss: 0.8307 (0.8360) time: 0.2523 data: 0.1673 max mem: 8452 +Train: [59] [6249/6250] eta: 0:00:00 lr: 0.000047 grad: 0.1052 (0.1118) loss: 0.8362 (0.8360) time: 0.1802 data: 0.1055 max mem: 8452 +Train: [59] Total time: 0:18:10 (0.1746 s / it) +Averaged stats: lr: 0.000047 grad: 0.1052 (0.1118) loss: 0.8362 (0.8360) +Eval (hcp-train-subset): [59] [ 0/62] eta: 0:03:58 loss: 0.8746 (0.8746) time: 3.8426 data: 3.7750 max mem: 8452 +Eval (hcp-train-subset): [59] [61/62] eta: 0:00:00 loss: 0.8675 (0.8661) time: 0.1639 data: 0.1427 max mem: 8452 +Eval (hcp-train-subset): [59] Total time: 0:00:15 (0.2556 s / it) +Averaged stats (hcp-train-subset): loss: 0.8675 (0.8661) +Making plots (hcp-train-subset): example=38 +Eval (hcp-val): [59] [ 0/62] eta: 0:06:46 loss: 0.8698 (0.8698) time: 6.5530 data: 6.5156 max mem: 8452 +Eval (hcp-val): [59] [61/62] eta: 0:00:00 loss: 0.8707 (0.8724) time: 0.1818 data: 0.1564 max mem: 8452 +Eval (hcp-val): [59] Total time: 0:00:18 (0.2913 s / it) +Averaged stats (hcp-val): loss: 0.8707 (0.8724) +Making plots (hcp-val): example=59 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-00059.pth +Train: [60] [ 0/6250] eta: 10:15:39 lr: 0.000047 grad: 0.2202 (0.2202) loss: 0.8959 (0.8959) time: 5.9103 data: 5.5714 max mem: 8452 +Train: [60] [ 100/6250] eta: 0:24:34 lr: 0.000047 grad: 0.1401 (0.1657) loss: 0.8510 (0.8582) time: 0.2070 data: 0.0954 max mem: 8452 +Train: [60] [ 200/6250] eta: 0:21:04 lr: 0.000047 grad: 0.1312 (0.1531) loss: 0.8321 (0.8508) time: 0.2041 data: 0.1027 max mem: 8452 +Train: [60] [ 300/6250] eta: 0:19:15 lr: 0.000047 grad: 0.1179 (0.1449) loss: 0.8315 (0.8460) time: 0.1676 data: 0.0643 max mem: 8452 +Train: [60] [ 400/6250] eta: 0:18:07 lr: 0.000047 grad: 0.1146 (0.1384) loss: 0.8365 (0.8436) time: 0.1669 data: 0.0758 max mem: 8452 +Train: [60] [ 500/6250] eta: 0:17:16 lr: 0.000047 grad: 0.1101 (0.1335) loss: 0.8395 (0.8430) time: 0.1254 data: 0.0325 max mem: 8452 +Train: [60] [ 600/6250] eta: 0:16:43 lr: 0.000047 grad: 0.1073 (0.1301) loss: 0.8432 (0.8432) time: 0.1406 data: 0.0420 max mem: 8452 +Train: [60] [ 700/6250] eta: 0:16:19 lr: 0.000047 grad: 0.1003 (0.1275) loss: 0.8455 (0.8432) time: 0.1858 data: 0.1068 max mem: 8452 +Train: [60] [ 800/6250] eta: 0:15:58 lr: 0.000047 grad: 0.0974 (0.1254) loss: 0.8534 (0.8435) time: 0.1793 data: 0.1020 max mem: 8452 +Train: [60] [ 900/6250] eta: 0:15:43 lr: 0.000047 grad: 0.0999 (0.1234) loss: 0.8486 (0.8437) time: 0.2020 data: 0.1228 max mem: 8452 +Train: [60] [1000/6250] eta: 0:15:14 lr: 0.000047 grad: 0.1099 (0.1217) loss: 0.8412 (0.8436) time: 0.1473 data: 0.0584 max mem: 8452 +Train: [60] [1100/6250] eta: 0:15:10 lr: 0.000047 grad: 0.1095 (0.1207) loss: 0.8419 (0.8431) time: 0.2336 data: 0.1397 max mem: 8452 +Train: [60] [1200/6250] eta: 0:14:52 lr: 0.000047 grad: 0.1016 (0.1197) loss: 0.8386 (0.8424) time: 0.1632 data: 0.0620 max mem: 8452 +Train: [60] [1300/6250] eta: 0:14:38 lr: 0.000047 grad: 0.1042 (0.1189) loss: 0.8405 (0.8419) time: 0.2734 data: 0.1845 max mem: 8452 +Train: [60] [1400/6250] eta: 0:14:24 lr: 0.000047 grad: 0.1027 (0.1183) loss: 0.8428 (0.8415) time: 0.2144 data: 0.1235 max mem: 8452 +Train: [60] [1500/6250] eta: 0:14:04 lr: 0.000047 grad: 0.1122 (0.1176) loss: 0.8297 (0.8409) time: 0.1664 data: 0.0818 max mem: 8452 +Train: [60] [1600/6250] eta: 0:13:45 lr: 0.000047 grad: 0.1042 (0.1171) loss: 0.8390 (0.8406) time: 0.1858 data: 0.1116 max mem: 8452 +Train: [60] [1700/6250] eta: 0:13:23 lr: 0.000047 grad: 0.1031 (0.1167) loss: 0.8400 (0.8402) time: 0.1715 data: 0.0904 max mem: 8452 +Train: [60] [1800/6250] eta: 0:13:00 lr: 0.000047 grad: 0.1085 (0.1166) loss: 0.8340 (0.8397) time: 0.1471 data: 0.0698 max mem: 8452 +Train: [60] [1900/6250] eta: 0:12:39 lr: 0.000047 grad: 0.1041 (0.1163) loss: 0.8344 (0.8392) time: 0.1598 data: 0.0762 max mem: 8452 +Train: [60] [2000/6250] eta: 0:12:21 lr: 0.000047 grad: 0.1095 (0.1160) loss: 0.8302 (0.8387) time: 0.2087 data: 0.1360 max mem: 8452 +Train: [60] [2100/6250] eta: 0:12:00 lr: 0.000046 grad: 0.1053 (0.1159) loss: 0.8383 (0.8385) time: 0.1733 data: 0.0981 max mem: 8452 +Train: [60] [2200/6250] eta: 0:11:48 lr: 0.000046 grad: 0.1112 (0.1157) loss: 0.8285 (0.8381) time: 0.1691 data: 0.1035 max mem: 8452 +Train: [60] [2300/6250] eta: 0:11:28 lr: 0.000046 grad: 0.1002 (0.1155) loss: 0.8302 (0.8379) time: 0.1535 data: 0.0745 max mem: 8452 +Train: [60] [2400/6250] eta: 0:11:09 lr: 0.000046 grad: 0.1076 (0.1153) loss: 0.8357 (0.8377) time: 0.1174 data: 0.0430 max mem: 8452 +Train: [60] [2500/6250] eta: 0:10:52 lr: 0.000046 grad: 0.1110 (0.1152) loss: 0.8290 (0.8375) time: 0.2105 data: 0.1339 max mem: 8452 +Train: [60] [2600/6250] eta: 0:10:33 lr: 0.000046 grad: 0.1050 (0.1152) loss: 0.8364 (0.8373) time: 0.1608 data: 0.0738 max mem: 8452 +Train: [60] [2700/6250] eta: 0:10:15 lr: 0.000046 grad: 0.1143 (0.1152) loss: 0.8246 (0.8370) time: 0.1809 data: 0.0871 max mem: 8452 +Train: [60] [2800/6250] eta: 0:09:57 lr: 0.000046 grad: 0.1105 (0.1152) loss: 0.8328 (0.8368) time: 0.1565 data: 0.0854 max mem: 8452 +Train: [60] [2900/6250] eta: 0:09:38 lr: 0.000046 grad: 0.1089 (0.1152) loss: 0.8286 (0.8367) time: 0.1538 data: 0.0714 max mem: 8452 +Train: [60] [3000/6250] eta: 0:09:20 lr: 0.000046 grad: 0.1138 (0.1152) loss: 0.8270 (0.8364) time: 0.1763 data: 0.0922 max mem: 8452 +Train: [60] [3100/6250] eta: 0:09:02 lr: 0.000046 grad: 0.1124 (0.1151) loss: 0.8274 (0.8362) time: 0.1526 data: 0.0678 max mem: 8452 +Train: [60] [3200/6250] eta: 0:08:43 lr: 0.000046 grad: 0.1135 (0.1154) loss: 0.8251 (0.8359) time: 0.1430 data: 0.0559 max mem: 8452 +Train: [60] [3300/6250] eta: 0:08:24 lr: 0.000046 grad: 0.1119 (0.1155) loss: 0.8236 (0.8358) time: 0.1683 data: 0.0871 max mem: 8452 +Train: [60] [3400/6250] eta: 0:08:07 lr: 0.000046 grad: 0.1082 (0.1154) loss: 0.8348 (0.8357) time: 0.2141 data: 0.1168 max mem: 8452 +Train: [60] [3500/6250] eta: 0:07:49 lr: 0.000046 grad: 0.1053 (0.1154) loss: 0.8405 (0.8356) time: 0.1895 data: 0.0801 max mem: 8452 +Train: [60] [3600/6250] eta: 0:07:31 lr: 0.000046 grad: 0.1053 (0.1154) loss: 0.8319 (0.8356) time: 0.1558 data: 0.0791 max mem: 8452 +Train: [60] [3700/6250] eta: 0:07:17 lr: 0.000046 grad: 0.1071 (0.1152) loss: 0.8377 (0.8355) time: 0.1533 data: 0.0352 max mem: 8452 +Train: [60] [3800/6250] eta: 0:06:58 lr: 0.000046 grad: 0.1139 (0.1152) loss: 0.8364 (0.8354) time: 0.1493 data: 0.0756 max mem: 8452 +Train: [60] [3900/6250] eta: 0:06:41 lr: 0.000046 grad: 0.1112 (0.1151) loss: 0.8277 (0.8354) time: 0.1816 data: 0.0928 max mem: 8452 +Train: [60] [4000/6250] eta: 0:06:23 lr: 0.000046 grad: 0.1083 (0.1150) loss: 0.8230 (0.8353) time: 0.1634 data: 0.0930 max mem: 8452 +Train: [60] [4100/6250] eta: 0:06:06 lr: 0.000046 grad: 0.1078 (0.1148) loss: 0.8371 (0.8353) time: 0.1978 data: 0.1283 max mem: 8452 +Train: [60] [4200/6250] eta: 0:05:50 lr: 0.000046 grad: 0.1144 (0.1148) loss: 0.8241 (0.8352) time: 0.1441 data: 0.0652 max mem: 8452 +Train: [60] [4300/6250] eta: 0:05:33 lr: 0.000046 grad: 0.1032 (0.1147) loss: 0.8388 (0.8351) time: 0.1718 data: 0.0922 max mem: 8452 +Train: [60] [4400/6250] eta: 0:05:15 lr: 0.000046 grad: 0.1123 (0.1147) loss: 0.8385 (0.8351) time: 0.1838 data: 0.0967 max mem: 8452 +Train: [60] [4500/6250] eta: 0:04:58 lr: 0.000046 grad: 0.1059 (0.1146) loss: 0.8424 (0.8351) time: 0.1788 data: 0.0989 max mem: 8452 +Train: [60] [4600/6250] eta: 0:04:41 lr: 0.000046 grad: 0.1054 (0.1145) loss: 0.8338 (0.8352) time: 0.1783 data: 0.1078 max mem: 8452 +Train: [60] [4700/6250] eta: 0:04:24 lr: 0.000046 grad: 0.1083 (0.1145) loss: 0.8351 (0.8352) time: 0.1476 data: 0.0735 max mem: 8452 +Train: [60] [4800/6250] eta: 0:04:06 lr: 0.000046 grad: 0.1047 (0.1145) loss: 0.8396 (0.8352) time: 0.1649 data: 0.0770 max mem: 8452 +Train: [60] [4900/6250] eta: 0:03:49 lr: 0.000046 grad: 0.1083 (0.1144) loss: 0.8395 (0.8353) time: 0.1522 data: 0.0568 max mem: 8452 +Train: [60] [5000/6250] eta: 0:03:31 lr: 0.000046 grad: 0.1118 (0.1143) loss: 0.8369 (0.8353) time: 0.1498 data: 0.0723 max mem: 8452 +Train: [60] [5100/6250] eta: 0:03:14 lr: 0.000046 grad: 0.1153 (0.1143) loss: 0.8249 (0.8353) time: 0.1572 data: 0.0718 max mem: 8452 +Train: [60] [5200/6250] eta: 0:02:57 lr: 0.000045 grad: 0.1064 (0.1143) loss: 0.8294 (0.8353) time: 0.1925 data: 0.1114 max mem: 8452 +Train: [60] [5300/6250] eta: 0:02:40 lr: 0.000045 grad: 0.1127 (0.1143) loss: 0.8399 (0.8352) time: 0.1585 data: 0.0815 max mem: 8452 +Train: [60] [5400/6250] eta: 0:02:23 lr: 0.000045 grad: 0.1099 (0.1143) loss: 0.8385 (0.8352) time: 0.1605 data: 0.0829 max mem: 8452 +Train: [60] [5500/6250] eta: 0:02:07 lr: 0.000045 grad: 0.1040 (0.1142) loss: 0.8314 (0.8352) time: 0.1439 data: 0.0648 max mem: 8452 +Train: [60] [5600/6250] eta: 0:01:50 lr: 0.000045 grad: 0.1154 (0.1143) loss: 0.8321 (0.8351) time: 0.1199 data: 0.0003 max mem: 8452 +Train: [60] [5700/6250] eta: 0:01:33 lr: 0.000045 grad: 0.1074 (0.1143) loss: 0.8282 (0.8350) time: 0.1700 data: 0.0858 max mem: 8452 +Train: [60] [5800/6250] eta: 0:01:16 lr: 0.000045 grad: 0.1096 (0.1143) loss: 0.8205 (0.8348) time: 0.1254 data: 0.0354 max mem: 8452 +Train: [60] [5900/6250] eta: 0:00:59 lr: 0.000045 grad: 0.1169 (0.1143) loss: 0.8209 (0.8347) time: 0.1897 data: 0.1022 max mem: 8452 +Train: [60] [6000/6250] eta: 0:00:42 lr: 0.000045 grad: 0.1153 (0.1144) loss: 0.8271 (0.8346) time: 0.1783 data: 0.1004 max mem: 8452 +Train: [60] [6100/6250] eta: 0:00:25 lr: 0.000045 grad: 0.1103 (0.1144) loss: 0.8302 (0.8346) time: 0.2220 data: 0.1455 max mem: 8452 +Train: [60] [6200/6250] eta: 0:00:08 lr: 0.000045 grad: 0.1145 (0.1144) loss: 0.8266 (0.8345) time: 0.1573 data: 0.0778 max mem: 8452 +Train: [60] [6249/6250] eta: 0:00:00 lr: 0.000045 grad: 0.1101 (0.1144) loss: 0.8301 (0.8345) time: 0.1580 data: 0.0803 max mem: 8452 +Train: [60] Total time: 0:17:53 (0.1717 s / it) +Averaged stats: lr: 0.000045 grad: 0.1101 (0.1144) loss: 0.8301 (0.8345) +Eval (hcp-train-subset): [60] [ 0/62] eta: 0:04:08 loss: 0.8684 (0.8684) time: 4.0122 data: 3.9160 max mem: 8452 +Eval (hcp-train-subset): [60] [61/62] eta: 0:00:00 loss: 0.8630 (0.8649) time: 0.1293 data: 0.1080 max mem: 8452 +Eval (hcp-train-subset): [60] Total time: 0:00:15 (0.2558 s / it) +Averaged stats (hcp-train-subset): loss: 0.8630 (0.8649) +Eval (hcp-val): [60] [ 0/62] eta: 0:07:34 loss: 0.8721 (0.8721) time: 7.3371 data: 7.2880 max mem: 8452 +Eval (hcp-val): [60] [61/62] eta: 0:00:00 loss: 0.8704 (0.8728) time: 0.1076 data: 0.0857 max mem: 8452 +Eval (hcp-val): [60] Total time: 0:00:16 (0.2618 s / it) +Averaged stats (hcp-val): loss: 0.8704 (0.8728) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [61] [ 0/6250] eta: 11:07:26 lr: 0.000045 grad: 0.0923 (0.0923) loss: 0.8536 (0.8536) time: 6.4074 data: 6.2907 max mem: 8452 +Train: [61] [ 100/6250] eta: 0:23:15 lr: 0.000045 grad: 0.1072 (0.1285) loss: 0.8561 (0.8595) time: 0.1670 data: 0.0612 max mem: 8452 +Train: [61] [ 200/6250] eta: 0:20:17 lr: 0.000045 grad: 0.1151 (0.1250) loss: 0.8355 (0.8558) time: 0.1355 data: 0.0194 max mem: 8452 +Train: [61] [ 300/6250] eta: 0:18:59 lr: 0.000045 grad: 0.0985 (0.1228) loss: 0.8378 (0.8524) time: 0.1831 data: 0.0972 max mem: 8452 +Train: [61] [ 400/6250] eta: 0:18:02 lr: 0.000045 grad: 0.1154 (0.1222) loss: 0.8328 (0.8480) time: 0.1949 data: 0.1044 max mem: 8452 +Train: [61] [ 500/6250] eta: 0:17:07 lr: 0.000045 grad: 0.1242 (0.1230) loss: 0.8297 (0.8444) time: 0.1488 data: 0.0523 max mem: 8452 +Train: [61] [ 600/6250] eta: 0:16:31 lr: 0.000045 grad: 0.1173 (0.1225) loss: 0.8381 (0.8421) time: 0.1533 data: 0.0634 max mem: 8452 +Train: [61] [ 700/6250] eta: 0:16:03 lr: 0.000045 grad: 0.1226 (0.1220) loss: 0.8370 (0.8405) time: 0.1796 data: 0.0877 max mem: 8452 +Train: [61] [ 800/6250] eta: 0:15:42 lr: 0.000045 grad: 0.1160 (0.1211) loss: 0.8452 (0.8400) time: 0.1853 data: 0.0889 max mem: 8452 +Train: [61] [ 900/6250] eta: 0:15:29 lr: 0.000045 grad: 0.1123 (0.1204) loss: 0.8328 (0.8395) time: 0.1201 data: 0.0275 max mem: 8452 +Train: [61] [1000/6250] eta: 0:15:16 lr: 0.000045 grad: 0.1065 (0.1192) loss: 0.8369 (0.8394) time: 0.2073 data: 0.1171 max mem: 8452 +Train: [61] [1100/6250] eta: 0:14:57 lr: 0.000045 grad: 0.1083 (0.1183) loss: 0.8302 (0.8389) time: 0.1698 data: 0.0613 max mem: 8452 +Train: [61] [1200/6250] eta: 0:14:40 lr: 0.000045 grad: 0.1079 (0.1176) loss: 0.8302 (0.8386) time: 0.1389 data: 0.0458 max mem: 8452 +Train: [61] [1300/6250] eta: 0:14:16 lr: 0.000045 grad: 0.1109 (0.1170) loss: 0.8346 (0.8383) time: 0.1571 data: 0.0731 max mem: 8452 +Train: [61] [1400/6250] eta: 0:13:53 lr: 0.000045 grad: 0.1063 (0.1166) loss: 0.8324 (0.8378) time: 0.1732 data: 0.0914 max mem: 8452 +Train: [61] [1500/6250] eta: 0:13:31 lr: 0.000045 grad: 0.1067 (0.1162) loss: 0.8356 (0.8375) time: 0.1768 data: 0.1058 max mem: 8452 +Train: [61] [1600/6250] eta: 0:13:10 lr: 0.000045 grad: 0.1070 (0.1158) loss: 0.8338 (0.8373) time: 0.1350 data: 0.0505 max mem: 8452 +Train: [61] [1700/6250] eta: 0:12:51 lr: 0.000045 grad: 0.1030 (0.1154) loss: 0.8402 (0.8372) time: 0.1571 data: 0.0729 max mem: 8452 +Train: [61] [1800/6250] eta: 0:12:34 lr: 0.000045 grad: 0.1121 (0.1150) loss: 0.8325 (0.8371) time: 0.1772 data: 0.1019 max mem: 8452 +Train: [61] [1900/6250] eta: 0:12:17 lr: 0.000045 grad: 0.1086 (0.1148) loss: 0.8321 (0.8370) time: 0.1681 data: 0.0929 max mem: 8452 +Train: [61] [2000/6250] eta: 0:11:59 lr: 0.000045 grad: 0.1085 (0.1146) loss: 0.8381 (0.8370) time: 0.1790 data: 0.0963 max mem: 8452 +Train: [61] [2100/6250] eta: 0:11:44 lr: 0.000044 grad: 0.1075 (0.1144) loss: 0.8349 (0.8370) time: 0.1557 data: 0.0623 max mem: 8452 +Train: [61] [2200/6250] eta: 0:11:31 lr: 0.000044 grad: 0.1109 (0.1142) loss: 0.8379 (0.8369) time: 0.1614 data: 0.0809 max mem: 8452 +Train: [61] [2300/6250] eta: 0:11:17 lr: 0.000044 grad: 0.1068 (0.1141) loss: 0.8357 (0.8369) time: 0.1450 data: 0.0681 max mem: 8452 +Train: [61] [2400/6250] eta: 0:11:00 lr: 0.000044 grad: 0.1077 (0.1140) loss: 0.8384 (0.8367) time: 0.1828 data: 0.0993 max mem: 8452 +Train: [61] [2500/6250] eta: 0:10:43 lr: 0.000044 grad: 0.1074 (0.1138) loss: 0.8407 (0.8367) time: 0.1731 data: 0.0881 max mem: 8452 +Train: [61] [2600/6250] eta: 0:10:26 lr: 0.000044 grad: 0.1117 (0.1139) loss: 0.8335 (0.8366) time: 0.1718 data: 0.0891 max mem: 8452 +Train: [61] [2700/6250] eta: 0:10:07 lr: 0.000044 grad: 0.1131 (0.1138) loss: 0.8314 (0.8365) time: 0.1465 data: 0.0523 max mem: 8452 +Train: [61] [2800/6250] eta: 0:09:48 lr: 0.000044 grad: 0.1072 (0.1136) loss: 0.8334 (0.8365) time: 0.1542 data: 0.0718 max mem: 8452 +Train: [61] [2900/6250] eta: 0:09:30 lr: 0.000044 grad: 0.1105 (0.1137) loss: 0.8318 (0.8365) time: 0.1754 data: 0.0865 max mem: 8452 +Train: [61] [3000/6250] eta: 0:09:12 lr: 0.000044 grad: 0.1106 (0.1137) loss: 0.8346 (0.8364) time: 0.1576 data: 0.0656 max mem: 8452 +Train: [61] [3100/6250] eta: 0:08:53 lr: 0.000044 grad: 0.1107 (0.1137) loss: 0.8348 (0.8363) time: 0.1565 data: 0.0713 max mem: 8452 +Train: [61] [3200/6250] eta: 0:08:36 lr: 0.000044 grad: 0.1068 (0.1137) loss: 0.8390 (0.8362) time: 0.1690 data: 0.0844 max mem: 8452 +Train: [61] [3300/6250] eta: 0:08:18 lr: 0.000044 grad: 0.1175 (0.1137) loss: 0.8285 (0.8362) time: 0.1547 data: 0.0583 max mem: 8452 +Train: [61] [3400/6250] eta: 0:08:01 lr: 0.000044 grad: 0.1152 (0.1136) loss: 0.8246 (0.8362) time: 0.1307 data: 0.0465 max mem: 8452 +Train: [61] [3500/6250] eta: 0:07:44 lr: 0.000044 grad: 0.1101 (0.1136) loss: 0.8416 (0.8362) time: 0.1714 data: 0.0902 max mem: 8452 +Train: [61] [3600/6250] eta: 0:07:27 lr: 0.000044 grad: 0.1111 (0.1135) loss: 0.8312 (0.8362) time: 0.1603 data: 0.0836 max mem: 8452 +Train: [61] [3700/6250] eta: 0:07:10 lr: 0.000044 grad: 0.1141 (0.1135) loss: 0.8319 (0.8361) time: 0.1712 data: 0.1000 max mem: 8452 +Train: [61] [3800/6250] eta: 0:06:53 lr: 0.000044 grad: 0.1081 (0.1135) loss: 0.8334 (0.8360) time: 0.1512 data: 0.0831 max mem: 8452 +Train: [61] [3900/6250] eta: 0:06:36 lr: 0.000044 grad: 0.1074 (0.1134) loss: 0.8342 (0.8360) time: 0.1319 data: 0.0544 max mem: 8452 +Train: [61] [4000/6250] eta: 0:06:18 lr: 0.000044 grad: 0.1068 (0.1135) loss: 0.8393 (0.8361) time: 0.1714 data: 0.0820 max mem: 8452 +Train: [61] [4100/6250] eta: 0:06:02 lr: 0.000044 grad: 0.1118 (0.1135) loss: 0.8384 (0.8361) time: 0.1555 data: 0.0847 max mem: 8452 +Train: [61] [4200/6250] eta: 0:05:45 lr: 0.000044 grad: 0.1000 (0.1133) loss: 0.8486 (0.8362) time: 0.1723 data: 0.0917 max mem: 8452 +Train: [61] [4300/6250] eta: 0:05:28 lr: 0.000044 grad: 0.1077 (0.1133) loss: 0.8389 (0.8363) time: 0.1564 data: 0.0775 max mem: 8452 +Train: [61] [4400/6250] eta: 0:05:11 lr: 0.000044 grad: 0.1097 (0.1132) loss: 0.8366 (0.8364) time: 0.1810 data: 0.0973 max mem: 8452 +Train: [61] [4500/6250] eta: 0:04:54 lr: 0.000044 grad: 0.1047 (0.1132) loss: 0.8440 (0.8365) time: 0.1521 data: 0.0735 max mem: 8452 +Train: [61] [4600/6250] eta: 0:04:37 lr: 0.000044 grad: 0.1051 (0.1131) loss: 0.8487 (0.8366) time: 0.1535 data: 0.0660 max mem: 8452 +Train: [61] [4700/6250] eta: 0:04:20 lr: 0.000044 grad: 0.1125 (0.1131) loss: 0.8389 (0.8367) time: 0.1885 data: 0.1043 max mem: 8452 +Train: [61] [4800/6250] eta: 0:04:03 lr: 0.000044 grad: 0.1085 (0.1130) loss: 0.8433 (0.8368) time: 0.1535 data: 0.0601 max mem: 8452 +Train: [61] [4900/6250] eta: 0:03:45 lr: 0.000044 grad: 0.1089 (0.1130) loss: 0.8362 (0.8368) time: 0.1521 data: 0.0678 max mem: 8452 +Train: [61] [5000/6250] eta: 0:03:28 lr: 0.000044 grad: 0.1055 (0.1130) loss: 0.8456 (0.8369) time: 0.1561 data: 0.0825 max mem: 8452 +Train: [61] [5100/6250] eta: 0:03:12 lr: 0.000044 grad: 0.1082 (0.1129) loss: 0.8419 (0.8370) time: 0.1104 data: 0.0303 max mem: 8452 +Train: [61] [5200/6250] eta: 0:02:55 lr: 0.000044 grad: 0.1074 (0.1129) loss: 0.8362 (0.8371) time: 0.1859 data: 0.1026 max mem: 8452 +Train: [61] [5300/6250] eta: 0:02:39 lr: 0.000043 grad: 0.1088 (0.1129) loss: 0.8298 (0.8371) time: 0.1748 data: 0.1063 max mem: 8452 +Train: [61] [5400/6250] eta: 0:02:22 lr: 0.000043 grad: 0.1099 (0.1129) loss: 0.8394 (0.8371) time: 0.1754 data: 0.1116 max mem: 8452 +Train: [61] [5500/6250] eta: 0:02:05 lr: 0.000043 grad: 0.1101 (0.1129) loss: 0.8387 (0.8371) time: 0.1499 data: 0.0694 max mem: 8452 +Train: [61] [5600/6250] eta: 0:01:48 lr: 0.000043 grad: 0.1057 (0.1129) loss: 0.8462 (0.8371) time: 0.1852 data: 0.0977 max mem: 8452 +Train: [61] [5700/6250] eta: 0:01:32 lr: 0.000043 grad: 0.1115 (0.1130) loss: 0.8354 (0.8371) time: 0.1465 data: 0.0650 max mem: 8452 +Train: [61] [5800/6250] eta: 0:01:15 lr: 0.000043 grad: 0.1053 (0.1129) loss: 0.8411 (0.8371) time: 0.1316 data: 0.0444 max mem: 8452 +Train: [61] [5900/6250] eta: 0:00:58 lr: 0.000043 grad: 0.1141 (0.1129) loss: 0.8326 (0.8371) time: 0.3183 data: 0.2331 max mem: 8452 +Train: [61] [6000/6250] eta: 0:00:41 lr: 0.000043 grad: 0.1127 (0.1129) loss: 0.8389 (0.8371) time: 0.1523 data: 0.0655 max mem: 8452 +Train: [61] [6100/6250] eta: 0:00:25 lr: 0.000043 grad: 0.1124 (0.1130) loss: 0.8261 (0.8371) time: 0.1480 data: 0.0697 max mem: 8452 +Train: [61] [6200/6250] eta: 0:00:08 lr: 0.000043 grad: 0.1101 (0.1130) loss: 0.8393 (0.8371) time: 0.1004 data: 0.0002 max mem: 8452 +Train: [61] [6249/6250] eta: 0:00:00 lr: 0.000043 grad: 0.1122 (0.1130) loss: 0.8425 (0.8371) time: 0.1648 data: 0.0803 max mem: 8452 +Train: [61] Total time: 0:17:35 (0.1688 s / it) +Averaged stats: lr: 0.000043 grad: 0.1122 (0.1130) loss: 0.8425 (0.8371) +Eval (hcp-train-subset): [61] [ 0/62] eta: 0:06:19 loss: 0.8767 (0.8767) time: 6.1276 data: 6.0956 max mem: 8452 +Eval (hcp-train-subset): [61] [61/62] eta: 0:00:00 loss: 0.8651 (0.8644) time: 0.1212 data: 0.0996 max mem: 8452 +Eval (hcp-train-subset): [61] Total time: 0:00:14 (0.2315 s / it) +Averaged stats (hcp-train-subset): loss: 0.8651 (0.8644) +Eval (hcp-val): [61] [ 0/62] eta: 0:03:39 loss: 0.8701 (0.8701) time: 3.5480 data: 3.4521 max mem: 8452 +Eval (hcp-val): [61] [61/62] eta: 0:00:00 loss: 0.8718 (0.8728) time: 0.1426 data: 0.1176 max mem: 8452 +Eval (hcp-val): [61] Total time: 0:00:14 (0.2376 s / it) +Averaged stats (hcp-val): loss: 0.8718 (0.8728) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [62] [ 0/6250] eta: 9:03:26 lr: 0.000043 grad: nan (nan) loss: 0.8780 (0.8780) time: 5.2170 data: 4.9915 max mem: 8452 +Train: [62] [ 100/6250] eta: 0:22:41 lr: 0.000043 grad: 0.1172 (0.1604) loss: 0.8735 (0.8652) time: 0.1758 data: 0.0720 max mem: 8452 +Train: [62] [ 200/6250] eta: 0:19:57 lr: 0.000043 grad: 0.1067 (0.1427) loss: 0.8626 (0.8593) time: 0.1732 data: 0.0718 max mem: 8452 +Train: [62] [ 300/6250] eta: 0:18:19 lr: 0.000043 grad: 0.1025 (0.1348) loss: 0.8455 (0.8538) time: 0.1580 data: 0.0795 max mem: 8452 +Train: [62] [ 400/6250] eta: 0:17:22 lr: 0.000043 grad: 0.1108 (0.1292) loss: 0.8489 (0.8520) time: 0.1480 data: 0.0629 max mem: 8452 +Train: [62] [ 500/6250] eta: 0:16:42 lr: 0.000043 grad: 0.1006 (0.1250) loss: 0.8482 (0.8513) time: 0.1564 data: 0.0631 max mem: 8452 +Train: [62] [ 600/6250] eta: 0:16:10 lr: 0.000043 grad: 0.1031 (0.1215) loss: 0.8533 (0.8511) time: 0.1403 data: 0.0512 max mem: 8452 +Train: [62] [ 700/6250] eta: 0:15:55 lr: 0.000043 grad: 0.1033 (0.1192) loss: 0.8420 (0.8505) time: 0.1779 data: 0.0817 max mem: 8452 +Train: [62] [ 800/6250] eta: 0:15:59 lr: 0.000043 grad: 0.1050 (0.1175) loss: 0.8401 (0.8496) time: 0.2422 data: 0.1395 max mem: 8452 +Train: [62] [ 900/6250] eta: 0:16:06 lr: 0.000043 grad: 0.0973 (0.1163) loss: 0.8501 (0.8488) time: 0.3835 data: 0.2740 max mem: 8452 +Train: [62] [1000/6250] eta: 0:15:54 lr: 0.000043 grad: 0.1005 (0.1153) loss: 0.8446 (0.8483) time: 0.2004 data: 0.1012 max mem: 8452 +Train: [62] [1100/6250] eta: 0:15:24 lr: 0.000043 grad: 0.1049 (0.1146) loss: 0.8403 (0.8478) time: 0.1456 data: 0.0543 max mem: 8452 +Train: [62] [1200/6250] eta: 0:15:03 lr: 0.000043 grad: 0.1064 (0.1137) loss: 0.8417 (0.8473) time: 0.1646 data: 0.0788 max mem: 8452 +Train: [62] [1300/6250] eta: 0:14:42 lr: 0.000043 grad: 0.0963 (0.1132) loss: 0.8472 (0.8470) time: 0.1687 data: 0.0776 max mem: 8452 +Train: [62] [1400/6250] eta: 0:14:19 lr: 0.000043 grad: 0.1062 (0.1129) loss: 0.8430 (0.8464) time: 0.1634 data: 0.0804 max mem: 8452 +Train: [62] [1500/6250] eta: 0:14:03 lr: 0.000043 grad: 0.1107 (0.1127) loss: 0.8296 (0.8459) time: 0.1111 data: 0.0003 max mem: 8452 +Train: [62] [1600/6250] eta: 0:13:41 lr: 0.000043 grad: 0.1047 (0.1125) loss: 0.8340 (0.8453) time: 0.1965 data: 0.0944 max mem: 8452 +Train: [62] [1700/6250] eta: 0:13:21 lr: 0.000043 grad: 0.1076 (0.1125) loss: 0.8238 (0.8446) time: 0.1589 data: 0.0745 max mem: 8452 +Train: [62] [1800/6250] eta: 0:13:00 lr: 0.000043 grad: 0.1081 (0.1123) loss: 0.8355 (0.8441) time: 0.1722 data: 0.0807 max mem: 8452 +Train: [62] [1900/6250] eta: 0:12:41 lr: 0.000043 grad: 0.1018 (0.1122) loss: 0.8414 (0.8439) time: 0.1479 data: 0.0698 max mem: 8452 +Train: [62] [2000/6250] eta: 0:12:21 lr: 0.000043 grad: 0.1040 (0.1120) loss: 0.8409 (0.8436) time: 0.1746 data: 0.1003 max mem: 8452 +Train: [62] [2100/6250] eta: 0:12:05 lr: 0.000043 grad: 0.1097 (0.1119) loss: 0.8360 (0.8435) time: 0.1543 data: 0.0730 max mem: 8452 +Train: [62] [2200/6250] eta: 0:11:47 lr: 0.000042 grad: 0.0986 (0.1118) loss: 0.8474 (0.8433) time: 0.1598 data: 0.0750 max mem: 8452 +Train: [62] [2300/6250] eta: 0:11:33 lr: 0.000042 grad: 0.1137 (0.1120) loss: 0.8279 (0.8431) time: 0.1543 data: 0.0820 max mem: 8452 +Train: [62] [2400/6250] eta: 0:11:15 lr: 0.000042 grad: 0.1145 (0.1120) loss: 0.8389 (0.8428) time: 0.1624 data: 0.0690 max mem: 8452 +Train: [62] [2500/6250] eta: 0:10:56 lr: 0.000042 grad: 0.1114 (0.1121) loss: 0.8365 (0.8424) time: 0.1501 data: 0.0758 max mem: 8452 +Train: [62] [2600/6250] eta: 0:10:40 lr: 0.000042 grad: 0.1081 (0.1122) loss: 0.8400 (0.8421) time: 0.2073 data: 0.1266 max mem: 8452 +Train: [62] [2700/6250] eta: 0:10:21 lr: 0.000042 grad: 0.1107 (0.1122) loss: 0.8317 (0.8420) time: 0.1560 data: 0.0707 max mem: 8452 +Train: [62] [2800/6250] eta: 0:10:02 lr: 0.000042 grad: 0.1091 (0.1122) loss: 0.8483 (0.8419) time: 0.1677 data: 0.0904 max mem: 8452 +Train: [62] [2900/6250] eta: 0:09:43 lr: 0.000042 grad: 0.1079 (0.1122) loss: 0.8394 (0.8417) time: 0.1381 data: 0.0470 max mem: 8452 +Train: [62] [3000/6250] eta: 0:09:23 lr: 0.000042 grad: 0.1078 (0.1121) loss: 0.8420 (0.8417) time: 0.1540 data: 0.0597 max mem: 8452 +Train: [62] [3100/6250] eta: 0:09:05 lr: 0.000042 grad: 0.1175 (0.1122) loss: 0.8377 (0.8416) time: 0.1519 data: 0.0603 max mem: 8452 +Train: [62] [3200/6250] eta: 0:08:46 lr: 0.000042 grad: 0.1046 (0.1120) loss: 0.8316 (0.8416) time: 0.1762 data: 0.0933 max mem: 8452 +Train: [62] [3300/6250] eta: 0:08:28 lr: 0.000042 grad: 0.1052 (0.1119) loss: 0.8434 (0.8416) time: 0.1351 data: 0.0492 max mem: 8452 +Train: [62] [3400/6250] eta: 0:08:10 lr: 0.000042 grad: 0.1088 (0.1118) loss: 0.8371 (0.8415) time: 0.1357 data: 0.0549 max mem: 8452 +Train: [62] [3500/6250] eta: 0:07:53 lr: 0.000042 grad: 0.1107 (0.1118) loss: 0.8399 (0.8414) time: 0.1699 data: 0.1029 max mem: 8452 +Train: [62] [3600/6250] eta: 0:07:35 lr: 0.000042 grad: 0.1055 (0.1118) loss: 0.8428 (0.8414) time: 0.1740 data: 0.0956 max mem: 8452 +Train: [62] [3700/6250] eta: 0:07:17 lr: 0.000042 grad: 0.1021 (0.1118) loss: 0.8362 (0.8413) time: 0.1796 data: 0.0947 max mem: 8452 +Train: [62] [3800/6250] eta: 0:06:59 lr: 0.000042 grad: 0.1062 (0.1117) loss: 0.8401 (0.8413) time: 0.1613 data: 0.0764 max mem: 8452 +Train: [62] [3900/6250] eta: 0:06:42 lr: 0.000042 grad: 0.1070 (0.1116) loss: 0.8406 (0.8413) time: 0.1734 data: 0.0994 max mem: 8452 +Train: [62] [4000/6250] eta: 0:06:25 lr: 0.000042 grad: 0.1076 (0.1115) loss: 0.8405 (0.8413) time: 0.1795 data: 0.0910 max mem: 8452 +Train: [62] [4100/6250] eta: 0:06:09 lr: 0.000042 grad: 0.1090 (0.1114) loss: 0.8470 (0.8413) time: 0.1488 data: 0.0594 max mem: 8452 +Train: [62] [4200/6250] eta: 0:05:51 lr: 0.000042 grad: 0.1057 (0.1113) loss: 0.8466 (0.8414) time: 0.1607 data: 0.0802 max mem: 8452 +Train: [62] [4300/6250] eta: 0:05:34 lr: 0.000042 grad: 0.1068 (0.1113) loss: 0.8391 (0.8414) time: 0.1937 data: 0.1143 max mem: 8452 +Train: [62] [4400/6250] eta: 0:05:16 lr: 0.000042 grad: 0.1111 (0.1113) loss: 0.8401 (0.8414) time: 0.1482 data: 0.0645 max mem: 8452 +Train: [62] [4500/6250] eta: 0:04:58 lr: 0.000042 grad: 0.1142 (0.1113) loss: 0.8412 (0.8414) time: 0.1431 data: 0.0555 max mem: 8452 +Train: [62] [4600/6250] eta: 0:04:41 lr: 0.000042 grad: 0.1106 (0.1113) loss: 0.8389 (0.8414) time: 0.1594 data: 0.0723 max mem: 8452 +Train: [62] [4700/6250] eta: 0:04:23 lr: 0.000042 grad: 0.1059 (0.1113) loss: 0.8375 (0.8415) time: 0.1036 data: 0.0130 max mem: 8452 +Train: [62] [4800/6250] eta: 0:04:06 lr: 0.000042 grad: 0.1040 (0.1113) loss: 0.8441 (0.8415) time: 0.1678 data: 0.0838 max mem: 8452 +Train: [62] [4900/6250] eta: 0:03:49 lr: 0.000042 grad: 0.1131 (0.1113) loss: 0.8440 (0.8415) time: 0.1838 data: 0.1053 max mem: 8452 +Train: [62] [5000/6250] eta: 0:03:32 lr: 0.000042 grad: 0.1134 (0.1112) loss: 0.8444 (0.8415) time: 0.1557 data: 0.0841 max mem: 8452 +Train: [62] [5100/6250] eta: 0:03:16 lr: 0.000042 grad: 0.1058 (0.1112) loss: 0.8393 (0.8415) time: 0.2758 data: 0.1997 max mem: 8452 +Train: [62] [5200/6250] eta: 0:02:59 lr: 0.000042 grad: 0.1041 (0.1112) loss: 0.8385 (0.8415) time: 0.2183 data: 0.1562 max mem: 8452 +Train: [62] [5300/6250] eta: 0:02:42 lr: 0.000042 grad: 0.1091 (0.1112) loss: 0.8389 (0.8414) time: 0.1306 data: 0.0484 max mem: 8452 +Train: [62] [5400/6250] eta: 0:02:25 lr: 0.000041 grad: 0.1148 (0.1112) loss: 0.8354 (0.8414) time: 0.1618 data: 0.0948 max mem: 8452 +Train: [62] [5500/6250] eta: 0:02:08 lr: 0.000041 grad: 0.1091 (0.1112) loss: 0.8431 (0.8414) time: 0.1559 data: 0.0793 max mem: 8452 +Train: [62] [5600/6250] eta: 0:01:51 lr: 0.000041 grad: 0.1106 (0.1112) loss: 0.8401 (0.8413) time: 0.1728 data: 0.0845 max mem: 8452 +Train: [62] [5700/6250] eta: 0:01:34 lr: 0.000041 grad: 0.1143 (0.1113) loss: 0.8398 (0.8412) time: 0.1157 data: 0.0388 max mem: 8452 +Train: [62] [5800/6250] eta: 0:01:17 lr: 0.000041 grad: 0.1120 (0.1114) loss: 0.8394 (0.8411) time: 0.1401 data: 0.0423 max mem: 8452 +Train: [62] [5900/6250] eta: 0:01:00 lr: 0.000041 grad: 0.1097 (0.1115) loss: 0.8360 (0.8410) time: 0.2614 data: 0.1693 max mem: 8452 +Train: [62] [6000/6250] eta: 0:00:43 lr: 0.000041 grad: 0.1177 (0.1116) loss: 0.8298 (0.8408) time: 0.1276 data: 0.0281 max mem: 8452 +Train: [62] [6100/6250] eta: 0:00:25 lr: 0.000041 grad: 0.1102 (0.1116) loss: 0.8391 (0.8407) time: 0.1492 data: 0.0765 max mem: 8452 +Train: [62] [6200/6250] eta: 0:00:08 lr: 0.000041 grad: 0.1165 (0.1117) loss: 0.8250 (0.8406) time: 0.1486 data: 0.0726 max mem: 8452 +Train: [62] [6249/6250] eta: 0:00:00 lr: 0.000041 grad: 0.1095 (0.1117) loss: 0.8282 (0.8405) time: 0.1309 data: 0.0528 max mem: 8452 +Train: [62] Total time: 0:18:00 (0.1729 s / it) +Averaged stats: lr: 0.000041 grad: 0.1095 (0.1117) loss: 0.8282 (0.8405) +Eval (hcp-train-subset): [62] [ 0/62] eta: 0:05:16 loss: 0.8756 (0.8756) time: 5.1006 data: 5.0674 max mem: 8452 +Eval (hcp-train-subset): [62] [61/62] eta: 0:00:00 loss: 0.8622 (0.8630) time: 0.1456 data: 0.1245 max mem: 8452 +Eval (hcp-train-subset): [62] Total time: 0:00:15 (0.2456 s / it) +Averaged stats (hcp-train-subset): loss: 0.8622 (0.8630) +Eval (hcp-val): [62] [ 0/62] eta: 0:06:17 loss: 0.8688 (0.8688) time: 6.0908 data: 6.0474 max mem: 8452 +Eval (hcp-val): [62] [61/62] eta: 0:00:00 loss: 0.8713 (0.8726) time: 0.1294 data: 0.1071 max mem: 8452 +Eval (hcp-val): [62] Total time: 0:00:14 (0.2404 s / it) +Averaged stats (hcp-val): loss: 0.8713 (0.8726) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [63] [ 0/6250] eta: 12:00:12 lr: 0.000041 grad: 0.2369 (0.2369) loss: 0.8515 (0.8515) time: 6.9140 data: 6.8200 max mem: 8452 +Train: [63] [ 100/6250] eta: 0:22:21 lr: 0.000041 grad: 0.1097 (0.1189) loss: 0.8589 (0.8686) time: 0.1650 data: 0.0604 max mem: 8452 +Train: [63] [ 200/6250] eta: 0:19:26 lr: 0.000041 grad: 0.1099 (0.1223) loss: 0.8508 (0.8617) time: 0.1101 data: 0.0002 max mem: 8452 +Train: [63] [ 300/6250] eta: 0:18:15 lr: 0.000041 grad: 0.1075 (0.1236) loss: 0.8498 (0.8563) time: 0.1872 data: 0.0926 max mem: 8452 +Train: [63] [ 400/6250] eta: 0:17:13 lr: 0.000041 grad: 0.1109 (0.1235) loss: 0.8397 (0.8525) time: 0.1489 data: 0.0589 max mem: 8452 +Train: [63] [ 500/6250] eta: 0:16:50 lr: 0.000041 grad: 0.1111 (0.1218) loss: 0.8388 (0.8503) time: 0.1868 data: 0.0809 max mem: 8452 +Train: [63] [ 600/6250] eta: 0:16:32 lr: 0.000041 grad: 0.1072 (0.1207) loss: 0.8432 (0.8488) time: 0.1852 data: 0.1062 max mem: 8452 +Train: [63] [ 700/6250] eta: 0:16:34 lr: 0.000041 grad: 0.1151 (0.1197) loss: 0.8378 (0.8477) time: 0.2281 data: 0.1347 max mem: 8452 +Train: [63] [ 800/6250] eta: 0:16:14 lr: 0.000041 grad: 0.1073 (0.1190) loss: 0.8441 (0.8471) time: 0.2393 data: 0.1513 max mem: 8452 +Train: [63] [ 900/6250] eta: 0:16:08 lr: 0.000041 grad: 0.1125 (0.1185) loss: 0.8409 (0.8466) time: 0.2851 data: 0.1735 max mem: 8452 +Train: [63] [1000/6250] eta: 0:15:46 lr: 0.000041 grad: 0.1087 (0.1177) loss: 0.8460 (0.8462) time: 0.1619 data: 0.0627 max mem: 8452 +Train: [63] [1100/6250] eta: 0:15:35 lr: 0.000041 grad: 0.1084 (0.1169) loss: 0.8431 (0.8461) time: 0.1580 data: 0.0546 max mem: 8452 +Train: [63] [1200/6250] eta: 0:15:06 lr: 0.000041 grad: 0.1085 (0.1163) loss: 0.8450 (0.8458) time: 0.1550 data: 0.0575 max mem: 8452 +Train: [63] [1300/6250] eta: 0:14:46 lr: 0.000041 grad: 0.1129 (0.1159) loss: 0.8339 (0.8452) time: 0.1444 data: 0.0598 max mem: 8452 +Train: [63] [1400/6250] eta: 0:14:22 lr: 0.000041 grad: 0.1126 (0.1157) loss: 0.8305 (0.8445) time: 0.1676 data: 0.0815 max mem: 8452 +Train: [63] [1500/6250] eta: 0:13:58 lr: 0.000041 grad: 0.1125 (0.1156) loss: 0.8277 (0.8438) time: 0.1479 data: 0.0624 max mem: 8452 +Train: [63] [1600/6250] eta: 0:13:37 lr: 0.000041 grad: 0.1108 (0.1155) loss: 0.8295 (0.8431) time: 0.1590 data: 0.0839 max mem: 8452 +Train: [63] [1700/6250] eta: 0:13:24 lr: 0.000041 grad: 0.1163 (0.1154) loss: 0.8339 (0.8424) time: 0.1662 data: 0.0530 max mem: 8452 +Train: [63] [1800/6250] eta: 0:13:03 lr: 0.000041 grad: 0.1100 (0.1152) loss: 0.8355 (0.8420) time: 0.1364 data: 0.0346 max mem: 8452 +Train: [63] [1900/6250] eta: 0:12:41 lr: 0.000041 grad: 0.1097 (0.1150) loss: 0.8381 (0.8415) time: 0.1698 data: 0.0898 max mem: 8452 +Train: [63] [2000/6250] eta: 0:12:19 lr: 0.000041 grad: 0.1079 (0.1148) loss: 0.8377 (0.8412) time: 0.1489 data: 0.0703 max mem: 8452 +Train: [63] [2100/6250] eta: 0:12:03 lr: 0.000041 grad: 0.1122 (0.1147) loss: 0.8452 (0.8409) time: 0.1602 data: 0.0715 max mem: 8452 +Train: [63] [2200/6250] eta: 0:11:43 lr: 0.000041 grad: 0.1156 (0.1145) loss: 0.8310 (0.8407) time: 0.1803 data: 0.1042 max mem: 8452 +Train: [63] [2300/6250] eta: 0:11:23 lr: 0.000041 grad: 0.1101 (0.1143) loss: 0.8265 (0.8405) time: 0.1790 data: 0.1043 max mem: 8452 +Train: [63] [2400/6250] eta: 0:11:09 lr: 0.000040 grad: 0.1068 (0.1142) loss: 0.8463 (0.8403) time: 0.1808 data: 0.1143 max mem: 8452 +Train: [63] [2500/6250] eta: 0:10:51 lr: 0.000040 grad: 0.1100 (0.1141) loss: 0.8342 (0.8401) time: 0.1805 data: 0.0976 max mem: 8452 +Train: [63] [2600/6250] eta: 0:10:32 lr: 0.000040 grad: 0.1141 (0.1141) loss: 0.8353 (0.8399) time: 0.1721 data: 0.1048 max mem: 8452 +Train: [63] [2700/6250] eta: 0:10:14 lr: 0.000040 grad: 0.1044 (0.1140) loss: 0.8356 (0.8398) time: 0.1677 data: 0.0781 max mem: 8452 +Train: [63] [2800/6250] eta: 0:09:56 lr: 0.000040 grad: 0.1135 (0.1139) loss: 0.8391 (0.8396) time: 0.1620 data: 0.0689 max mem: 8452 +Train: [63] [2900/6250] eta: 0:09:38 lr: 0.000040 grad: 0.1093 (0.1139) loss: 0.8382 (0.8395) time: 0.1417 data: 0.0607 max mem: 8452 +Train: [63] [3000/6250] eta: 0:09:19 lr: 0.000040 grad: 0.1085 (0.1138) loss: 0.8316 (0.8393) time: 0.1480 data: 0.0592 max mem: 8452 +Train: [63] [3100/6250] eta: 0:09:00 lr: 0.000040 grad: 0.1089 (0.1138) loss: 0.8353 (0.8392) time: 0.1604 data: 0.0755 max mem: 8452 +Train: [63] [3200/6250] eta: 0:08:42 lr: 0.000040 grad: 0.1076 (0.1138) loss: 0.8420 (0.8391) time: 0.1584 data: 0.0928 max mem: 8452 +Train: [63] [3300/6250] eta: 0:08:28 lr: 0.000040 grad: 0.1067 (0.1138) loss: 0.8441 (0.8390) time: 0.1387 data: 0.0003 max mem: 8452 +Train: [63] [3400/6250] eta: 0:08:12 lr: 0.000040 grad: 0.1113 (0.1138) loss: 0.8341 (0.8389) time: 0.1519 data: 0.0547 max mem: 8452 +Train: [63] [3500/6250] eta: 0:07:54 lr: 0.000040 grad: 0.1103 (0.1138) loss: 0.8291 (0.8388) time: 0.1326 data: 0.0307 max mem: 8452 +Train: [63] [3600/6250] eta: 0:07:37 lr: 0.000040 grad: 0.1190 (0.1138) loss: 0.8357 (0.8388) time: 0.1904 data: 0.1267 max mem: 8452 +Train: [63] [3700/6250] eta: 0:07:21 lr: 0.000040 grad: 0.1126 (0.1139) loss: 0.8404 (0.8387) time: 0.2166 data: 0.1362 max mem: 8452 +Train: [63] [3800/6250] eta: 0:07:03 lr: 0.000040 grad: 0.1176 (0.1139) loss: 0.8267 (0.8386) time: 0.1327 data: 0.0168 max mem: 8452 +Train: [63] [3900/6250] eta: 0:06:45 lr: 0.000040 grad: 0.1089 (0.1140) loss: 0.8395 (0.8385) time: 0.1751 data: 0.0909 max mem: 8452 +Train: [63] [4000/6250] eta: 0:06:29 lr: 0.000040 grad: 0.1141 (0.1141) loss: 0.8375 (0.8384) time: 0.1946 data: 0.1185 max mem: 8452 +Train: [63] [4100/6250] eta: 0:06:12 lr: 0.000040 grad: 0.1077 (0.1141) loss: 0.8316 (0.8383) time: 0.1944 data: 0.1193 max mem: 8452 +Train: [63] [4200/6250] eta: 0:05:54 lr: 0.000040 grad: 0.1122 (0.1141) loss: 0.8365 (0.8383) time: 0.1531 data: 0.0749 max mem: 8452 +Train: [63] [4300/6250] eta: 0:05:37 lr: 0.000040 grad: 0.1086 (0.1141) loss: 0.8304 (0.8383) time: 0.1874 data: 0.1219 max mem: 8452 +Train: [63] [4400/6250] eta: 0:05:19 lr: 0.000040 grad: 0.1057 (0.1140) loss: 0.8414 (0.8382) time: 0.1735 data: 0.0860 max mem: 8452 +Train: [63] [4500/6250] eta: 0:05:01 lr: 0.000040 grad: 0.1189 (0.1140) loss: 0.8342 (0.8382) time: 0.1626 data: 0.0772 max mem: 8452 +Train: [63] [4600/6250] eta: 0:04:44 lr: 0.000040 grad: 0.1084 (0.1140) loss: 0.8396 (0.8382) time: 0.1417 data: 0.0417 max mem: 8452 +Train: [63] [4700/6250] eta: 0:04:26 lr: 0.000040 grad: 0.1074 (0.1139) loss: 0.8320 (0.8382) time: 0.1470 data: 0.0626 max mem: 8452 +Train: [63] [4800/6250] eta: 0:04:09 lr: 0.000040 grad: 0.0996 (0.1140) loss: 0.8470 (0.8382) time: 0.1727 data: 0.0936 max mem: 8452 +Train: [63] [4900/6250] eta: 0:03:51 lr: 0.000040 grad: 0.1031 (0.1139) loss: 0.8434 (0.8382) time: 0.2048 data: 0.1314 max mem: 8452 +Train: [63] [5000/6250] eta: 0:03:35 lr: 0.000040 grad: 0.1118 (0.1140) loss: 0.8366 (0.8382) time: 0.1401 data: 0.0710 max mem: 8452 +Train: [63] [5100/6250] eta: 0:03:17 lr: 0.000040 grad: 0.1114 (0.1139) loss: 0.8364 (0.8382) time: 0.1562 data: 0.0816 max mem: 8452 +Train: [63] [5200/6250] eta: 0:03:00 lr: 0.000040 grad: 0.1152 (0.1140) loss: 0.8358 (0.8382) time: 0.1681 data: 0.0909 max mem: 8452 +Train: [63] [5300/6250] eta: 0:02:43 lr: 0.000040 grad: 0.1100 (0.1141) loss: 0.8430 (0.8381) time: 0.1053 data: 0.0121 max mem: 8452 +Train: [63] [5400/6250] eta: 0:02:26 lr: 0.000040 grad: 0.1127 (0.1142) loss: 0.8383 (0.8380) time: 0.1846 data: 0.1109 max mem: 8452 +Train: [63] [5500/6250] eta: 0:02:09 lr: 0.000040 grad: 0.1163 (0.1142) loss: 0.8333 (0.8380) time: 0.2217 data: 0.1181 max mem: 8452 +Train: [63] [5600/6250] eta: 0:01:52 lr: 0.000039 grad: 0.1107 (0.1142) loss: 0.8389 (0.8380) time: 0.1556 data: 0.0552 max mem: 8452 +Train: [63] [5700/6250] eta: 0:01:34 lr: 0.000039 grad: 0.1085 (0.1142) loss: 0.8342 (0.8380) time: 0.1971 data: 0.1235 max mem: 8452 +Train: [63] [5800/6250] eta: 0:01:17 lr: 0.000039 grad: 0.1104 (0.1142) loss: 0.8347 (0.8380) time: 0.1634 data: 0.0854 max mem: 8452 +Train: [63] [5900/6250] eta: 0:01:00 lr: 0.000039 grad: 0.1122 (0.1143) loss: 0.8402 (0.8379) time: 0.1549 data: 0.0731 max mem: 8452 +Train: [63] [6000/6250] eta: 0:00:43 lr: 0.000039 grad: 0.1120 (0.1144) loss: 0.8341 (0.8379) time: 0.1882 data: 0.1124 max mem: 8452 +Train: [63] [6100/6250] eta: 0:00:25 lr: 0.000039 grad: 0.1197 (0.1144) loss: 0.8392 (0.8379) time: 0.1978 data: 0.0749 max mem: 8452 +Train: [63] [6200/6250] eta: 0:00:08 lr: 0.000039 grad: 0.1098 (0.1145) loss: 0.8384 (0.8379) time: 0.2088 data: 0.1373 max mem: 8452 +Train: [63] [6249/6250] eta: 0:00:00 lr: 0.000039 grad: 0.1091 (0.1144) loss: 0.8410 (0.8379) time: 0.1857 data: 0.0907 max mem: 8452 +Train: [63] Total time: 0:18:04 (0.1735 s / it) +Averaged stats: lr: 0.000039 grad: 0.1091 (0.1144) loss: 0.8410 (0.8379) +Eval (hcp-train-subset): [63] [ 0/62] eta: 0:05:15 loss: 0.8744 (0.8744) time: 5.0915 data: 5.0083 max mem: 8452 +Eval (hcp-train-subset): [63] [61/62] eta: 0:00:00 loss: 0.8637 (0.8633) time: 0.1550 data: 0.1340 max mem: 8452 +Eval (hcp-train-subset): [63] Total time: 0:00:15 (0.2532 s / it) +Averaged stats (hcp-train-subset): loss: 0.8637 (0.8633) +Eval (hcp-val): [63] [ 0/62] eta: 0:03:57 loss: 0.8697 (0.8697) time: 3.8282 data: 3.7351 max mem: 8452 +Eval (hcp-val): [63] [61/62] eta: 0:00:00 loss: 0.8703 (0.8719) time: 0.0959 data: 0.0739 max mem: 8452 +Eval (hcp-val): [63] Total time: 0:00:15 (0.2430 s / it) +Averaged stats (hcp-val): loss: 0.8703 (0.8719) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [64] [ 0/6250] eta: 11:10:06 lr: 0.000039 grad: 0.1129 (0.1129) loss: 0.9008 (0.9008) time: 6.4331 data: 6.2140 max mem: 8452 +Train: [64] [ 100/6250] eta: 0:25:25 lr: 0.000039 grad: 0.1178 (0.1520) loss: 0.8480 (0.8541) time: 0.2056 data: 0.1028 max mem: 8452 +Train: [64] [ 200/6250] eta: 0:22:21 lr: 0.000039 grad: 0.1148 (0.1361) loss: 0.8550 (0.8538) time: 0.2314 data: 0.0917 max mem: 8452 +Train: [64] [ 300/6250] eta: 0:21:40 lr: 0.000039 grad: 0.1149 (0.1317) loss: 0.8564 (0.8532) time: 0.1287 data: 0.0004 max mem: 8452 +Train: [64] [ 400/6250] eta: 0:21:17 lr: 0.000039 grad: 0.1183 (0.1281) loss: 0.8405 (0.8504) time: 0.1745 data: 0.0643 max mem: 8452 +Train: [64] [ 500/6250] eta: 0:20:09 lr: 0.000039 grad: 0.1220 (0.1255) loss: 0.8282 (0.8479) time: 0.1998 data: 0.1156 max mem: 8452 +Train: [64] [ 600/6250] eta: 0:19:13 lr: 0.000039 grad: 0.1165 (0.1242) loss: 0.8338 (0.8458) time: 0.1691 data: 0.0805 max mem: 8452 +Train: [64] [ 700/6250] eta: 0:18:34 lr: 0.000039 grad: 0.1089 (0.1228) loss: 0.8485 (0.8444) time: 0.2001 data: 0.0643 max mem: 8452 +Train: [64] [ 800/6250] eta: 0:18:22 lr: 0.000039 grad: 0.1137 (0.1215) loss: 0.8419 (0.8435) time: 0.1605 data: 0.0373 max mem: 8452 +Train: [64] [ 900/6250] eta: 0:18:20 lr: 0.000039 grad: 0.1105 (0.1206) loss: 0.8409 (0.8429) time: 0.1661 data: 0.0154 max mem: 8452 +Train: [64] [1000/6250] eta: 0:17:52 lr: 0.000039 grad: 0.1036 (0.1200) loss: 0.8387 (0.8421) time: 0.1534 data: 0.0491 max mem: 8452 +Train: [64] [1100/6250] eta: 0:17:20 lr: 0.000039 grad: 0.1113 (0.1197) loss: 0.8287 (0.8413) time: 0.1425 data: 0.0528 max mem: 8452 +Train: [64] [1200/6250] eta: 0:16:51 lr: 0.000039 grad: 0.1074 (0.1190) loss: 0.8308 (0.8404) time: 0.2008 data: 0.1027 max mem: 8452 +Train: [64] [1300/6250] eta: 0:16:37 lr: 0.000039 grad: 0.1095 (0.1186) loss: 0.8395 (0.8397) time: 0.3528 data: 0.2253 max mem: 8452 +Train: [64] [1400/6250] eta: 0:16:01 lr: 0.000039 grad: 0.1106 (0.1182) loss: 0.8384 (0.8389) time: 0.1669 data: 0.0874 max mem: 8452 +Train: [64] [1500/6250] eta: 0:15:33 lr: 0.000039 grad: 0.1111 (0.1178) loss: 0.8385 (0.8385) time: 0.1925 data: 0.1076 max mem: 8452 +Train: [64] [1600/6250] eta: 0:15:04 lr: 0.000039 grad: 0.1141 (0.1175) loss: 0.8240 (0.8383) time: 0.1824 data: 0.1090 max mem: 8452 +Train: [64] [1700/6250] eta: 0:14:34 lr: 0.000039 grad: 0.1172 (0.1172) loss: 0.8279 (0.8379) time: 0.1750 data: 0.0982 max mem: 8452 +Train: [64] [1800/6250] eta: 0:14:05 lr: 0.000039 grad: 0.1076 (0.1169) loss: 0.8335 (0.8376) time: 0.1155 data: 0.0416 max mem: 8452 +Train: [64] [1900/6250] eta: 0:13:48 lr: 0.000039 grad: 0.1076 (0.1168) loss: 0.8320 (0.8373) time: 0.3237 data: 0.2500 max mem: 8452 +Train: [64] [2000/6250] eta: 0:13:22 lr: 0.000039 grad: 0.1168 (0.1169) loss: 0.8280 (0.8370) time: 0.1742 data: 0.0986 max mem: 8452 +Train: [64] [2100/6250] eta: 0:12:59 lr: 0.000039 grad: 0.1095 (0.1168) loss: 0.8269 (0.8367) time: 0.1848 data: 0.1068 max mem: 8452 +Train: [64] [2200/6250] eta: 0:12:35 lr: 0.000039 grad: 0.1163 (0.1167) loss: 0.8305 (0.8365) time: 0.1673 data: 0.0889 max mem: 8452 +Train: [64] [2300/6250] eta: 0:12:15 lr: 0.000039 grad: 0.1147 (0.1167) loss: 0.8314 (0.8362) time: 0.1787 data: 0.0987 max mem: 8452 +Train: [64] [2400/6250] eta: 0:11:55 lr: 0.000039 grad: 0.1129 (0.1167) loss: 0.8307 (0.8359) time: 0.1975 data: 0.1225 max mem: 8452 +Train: [64] [2500/6250] eta: 0:11:37 lr: 0.000039 grad: 0.1108 (0.1167) loss: 0.8358 (0.8358) time: 0.1976 data: 0.1214 max mem: 8452 +Train: [64] [2600/6250] eta: 0:11:16 lr: 0.000039 grad: 0.1105 (0.1166) loss: 0.8377 (0.8356) time: 0.1823 data: 0.0996 max mem: 8452 +Train: [64] [2700/6250] eta: 0:10:55 lr: 0.000038 grad: 0.1131 (0.1167) loss: 0.8280 (0.8355) time: 0.1869 data: 0.0928 max mem: 8452 +Train: [64] [2800/6250] eta: 0:10:35 lr: 0.000038 grad: 0.1199 (0.1168) loss: 0.8335 (0.8354) time: 0.1406 data: 0.0434 max mem: 8452 +Train: [64] [2900/6250] eta: 0:10:15 lr: 0.000038 grad: 0.1180 (0.1169) loss: 0.8293 (0.8353) time: 0.1624 data: 0.0551 max mem: 8452 +Train: [64] [3000/6250] eta: 0:09:55 lr: 0.000038 grad: 0.1112 (0.1169) loss: 0.8380 (0.8352) time: 0.1578 data: 0.0818 max mem: 8452 +Train: [64] [3100/6250] eta: 0:09:35 lr: 0.000038 grad: 0.1120 (0.1170) loss: 0.8318 (0.8351) time: 0.1616 data: 0.0680 max mem: 8452 +Train: [64] [3200/6250] eta: 0:09:16 lr: 0.000038 grad: 0.1162 (0.1171) loss: 0.8256 (0.8351) time: 0.1589 data: 0.0507 max mem: 8452 +Train: [64] [3300/6250] eta: 0:09:06 lr: 0.000038 grad: 0.1132 (0.1171) loss: 0.8359 (0.8350) time: 0.1347 data: 0.0243 max mem: 8452 +Train: [64] [3400/6250] eta: 0:08:45 lr: 0.000038 grad: 0.1165 (0.1173) loss: 0.8396 (0.8349) time: 0.1827 data: 0.0899 max mem: 8452 +Train: [64] [3500/6250] eta: 0:08:27 lr: 0.000038 grad: 0.1131 (0.1174) loss: 0.8298 (0.8349) time: 0.1239 data: 0.0184 max mem: 8452 +Train: [64] [3600/6250] eta: 0:08:08 lr: 0.000038 grad: 0.1116 (0.1173) loss: 0.8351 (0.8348) time: 0.1472 data: 0.0600 max mem: 8452 +Train: [64] [3700/6250] eta: 0:07:49 lr: 0.000038 grad: 0.1138 (0.1174) loss: 0.8367 (0.8347) time: 0.1825 data: 0.0818 max mem: 8452 +Train: [64] [3800/6250] eta: 0:07:30 lr: 0.000038 grad: 0.1205 (0.1175) loss: 0.8313 (0.8346) time: 0.1401 data: 0.0652 max mem: 8452 +Train: [64] [3900/6250] eta: 0:07:13 lr: 0.000038 grad: 0.1156 (0.1175) loss: 0.8301 (0.8346) time: 0.2932 data: 0.1845 max mem: 8452 +Train: [64] [4000/6250] eta: 0:06:54 lr: 0.000038 grad: 0.1151 (0.1176) loss: 0.8398 (0.8345) time: 0.1694 data: 0.0863 max mem: 8452 +Train: [64] [4100/6250] eta: 0:06:35 lr: 0.000038 grad: 0.1158 (0.1176) loss: 0.8346 (0.8344) time: 0.1685 data: 0.0798 max mem: 8452 +Train: [64] [4200/6250] eta: 0:06:16 lr: 0.000038 grad: 0.1099 (0.1176) loss: 0.8355 (0.8343) time: 0.1295 data: 0.0514 max mem: 8452 +Train: [64] [4300/6250] eta: 0:05:57 lr: 0.000038 grad: 0.1124 (0.1176) loss: 0.8340 (0.8343) time: 0.1802 data: 0.0991 max mem: 8452 +Train: [64] [4400/6250] eta: 0:05:38 lr: 0.000038 grad: 0.1122 (0.1176) loss: 0.8427 (0.8344) time: 0.1646 data: 0.0729 max mem: 8452 +Train: [64] [4500/6250] eta: 0:05:19 lr: 0.000038 grad: 0.1147 (0.1177) loss: 0.8365 (0.8343) time: 0.1951 data: 0.1189 max mem: 8452 +Train: [64] [4600/6250] eta: 0:05:00 lr: 0.000038 grad: 0.1178 (0.1177) loss: 0.8298 (0.8342) time: 0.1371 data: 0.0489 max mem: 8452 +Train: [64] [4700/6250] eta: 0:04:41 lr: 0.000038 grad: 0.1199 (0.1179) loss: 0.8304 (0.8341) time: 0.1683 data: 0.0770 max mem: 8452 +Train: [64] [4800/6250] eta: 0:04:23 lr: 0.000038 grad: 0.1207 (0.1180) loss: 0.8248 (0.8340) time: 0.1445 data: 0.0529 max mem: 8452 +Train: [64] [4900/6250] eta: 0:04:04 lr: 0.000038 grad: 0.1128 (0.1180) loss: 0.8385 (0.8340) time: 0.1783 data: 0.1020 max mem: 8452 +Train: [64] [5000/6250] eta: 0:03:46 lr: 0.000038 grad: 0.1174 (0.1180) loss: 0.8356 (0.8339) time: 0.2003 data: 0.1253 max mem: 8452 +Train: [64] [5100/6250] eta: 0:03:27 lr: 0.000038 grad: 0.1123 (0.1180) loss: 0.8372 (0.8339) time: 0.1781 data: 0.1026 max mem: 8452 +Train: [64] [5200/6250] eta: 0:03:09 lr: 0.000038 grad: 0.1141 (0.1180) loss: 0.8379 (0.8338) time: 0.1378 data: 0.0635 max mem: 8452 +Train: [64] [5300/6250] eta: 0:02:51 lr: 0.000038 grad: 0.1162 (0.1180) loss: 0.8247 (0.8339) time: 0.1618 data: 0.0939 max mem: 8452 +Train: [64] [5400/6250] eta: 0:02:33 lr: 0.000038 grad: 0.1100 (0.1179) loss: 0.8402 (0.8339) time: 0.3812 data: 0.2983 max mem: 8452 +Train: [64] [5500/6250] eta: 0:02:15 lr: 0.000038 grad: 0.1130 (0.1179) loss: 0.8378 (0.8339) time: 0.1207 data: 0.0119 max mem: 8452 +Train: [64] [5600/6250] eta: 0:01:57 lr: 0.000038 grad: 0.1174 (0.1179) loss: 0.8352 (0.8340) time: 0.1303 data: 0.0464 max mem: 8452 +Train: [64] [5700/6250] eta: 0:01:38 lr: 0.000038 grad: 0.1138 (0.1180) loss: 0.8259 (0.8340) time: 0.1944 data: 0.1265 max mem: 8452 +Train: [64] [5800/6250] eta: 0:01:20 lr: 0.000038 grad: 0.1138 (0.1180) loss: 0.8399 (0.8340) time: 0.1627 data: 0.0834 max mem: 8452 +Train: [64] [5900/6250] eta: 0:01:02 lr: 0.000037 grad: 0.1107 (0.1180) loss: 0.8299 (0.8340) time: 0.1825 data: 0.0918 max mem: 8452 +Train: [64] [6000/6250] eta: 0:00:44 lr: 0.000037 grad: 0.1136 (0.1180) loss: 0.8374 (0.8340) time: 0.1699 data: 0.0832 max mem: 8452 +Train: [64] [6100/6250] eta: 0:00:26 lr: 0.000037 grad: 0.1118 (0.1180) loss: 0.8402 (0.8340) time: 0.1728 data: 0.0792 max mem: 8452 +Train: [64] [6200/6250] eta: 0:00:08 lr: 0.000037 grad: 0.1123 (0.1180) loss: 0.8419 (0.8340) time: 0.1838 data: 0.0745 max mem: 8452 +Train: [64] [6249/6250] eta: 0:00:00 lr: 0.000037 grad: 0.1207 (0.1181) loss: 0.8437 (0.8341) time: 0.1936 data: 0.1039 max mem: 8452 +Train: [64] Total time: 0:18:47 (0.1804 s / it) +Averaged stats: lr: 0.000037 grad: 0.1207 (0.1181) loss: 0.8437 (0.8341) +Eval (hcp-train-subset): [64] [ 0/62] eta: 0:04:43 loss: 0.8768 (0.8768) time: 4.5728 data: 4.4957 max mem: 8452 +Eval (hcp-train-subset): [64] [61/62] eta: 0:00:00 loss: 0.8600 (0.8626) time: 0.1684 data: 0.1470 max mem: 8452 +Eval (hcp-train-subset): [64] Total time: 0:00:16 (0.2603 s / it) +Averaged stats (hcp-train-subset): loss: 0.8600 (0.8626) +Making plots (hcp-train-subset): example=28 +Eval (hcp-val): [64] [ 0/62] eta: 0:06:32 loss: 0.8725 (0.8725) time: 6.3226 data: 6.2924 max mem: 8452 +Eval (hcp-val): [64] [61/62] eta: 0:00:00 loss: 0.8704 (0.8726) time: 0.1494 data: 0.1268 max mem: 8452 +Eval (hcp-val): [64] Total time: 0:00:15 (0.2550 s / it) +Averaged stats (hcp-val): loss: 0.8704 (0.8726) +Making plots (hcp-val): example=43 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [65] [ 0/6250] eta: 8:47:15 lr: 0.000037 grad: 0.0687 (0.0687) loss: 0.8851 (0.8851) time: 5.0617 data: 4.6991 max mem: 8452 +Train: [65] [ 100/6250] eta: 0:24:41 lr: 0.000037 grad: 0.1297 (0.1639) loss: 0.8388 (0.8455) time: 0.1711 data: 0.0636 max mem: 8452 +Train: [65] [ 200/6250] eta: 0:21:52 lr: 0.000037 grad: 0.1106 (0.1485) loss: 0.8489 (0.8457) time: 0.1971 data: 0.1064 max mem: 8452 +Train: [65] [ 300/6250] eta: 0:19:53 lr: 0.000037 grad: 0.1093 (0.1368) loss: 0.8407 (0.8467) time: 0.1653 data: 0.0680 max mem: 8452 +Train: [65] [ 400/6250] eta: 0:18:38 lr: 0.000037 grad: 0.1008 (0.1314) loss: 0.8529 (0.8465) time: 0.1051 data: 0.0003 max mem: 8452 +Train: [65] [ 500/6250] eta: 0:17:48 lr: 0.000037 grad: 0.1034 (0.1279) loss: 0.8425 (0.8463) time: 0.1692 data: 0.0813 max mem: 8452 +Train: [65] [ 600/6250] eta: 0:17:23 lr: 0.000037 grad: 0.1160 (0.1255) loss: 0.8374 (0.8453) time: 0.2300 data: 0.1471 max mem: 8452 +Train: [65] [ 700/6250] eta: 0:17:19 lr: 0.000037 grad: 0.1142 (0.1241) loss: 0.8351 (0.8444) time: 0.2018 data: 0.0972 max mem: 8452 +Train: [65] [ 800/6250] eta: 0:17:02 lr: 0.000037 grad: 0.1140 (0.1226) loss: 0.8433 (0.8436) time: 0.1302 data: 0.0003 max mem: 8452 +Train: [65] [ 900/6250] eta: 0:16:45 lr: 0.000037 grad: 0.1124 (0.1215) loss: 0.8343 (0.8429) time: 0.1734 data: 0.0802 max mem: 8452 +Train: [65] [1000/6250] eta: 0:17:01 lr: 0.000037 grad: 0.1091 (0.1208) loss: 0.8419 (0.8425) time: 0.2005 data: 0.0980 max mem: 8452 +Train: [65] [1100/6250] eta: 0:16:23 lr: 0.000037 grad: 0.1100 (0.1201) loss: 0.8363 (0.8420) time: 0.1752 data: 0.0859 max mem: 8452 +Train: [65] [1200/6250] eta: 0:15:52 lr: 0.000037 grad: 0.1104 (0.1195) loss: 0.8360 (0.8415) time: 0.1810 data: 0.0648 max mem: 8452 +Train: [65] [1300/6250] eta: 0:15:32 lr: 0.000037 grad: 0.1089 (0.1188) loss: 0.8367 (0.8411) time: 0.1490 data: 0.0601 max mem: 8452 +Train: [65] [1400/6250] eta: 0:15:06 lr: 0.000037 grad: 0.1133 (0.1187) loss: 0.8279 (0.8404) time: 0.1801 data: 0.1044 max mem: 8452 +Train: [65] [1500/6250] eta: 0:14:37 lr: 0.000037 grad: 0.1188 (0.1186) loss: 0.8328 (0.8400) time: 0.1584 data: 0.0773 max mem: 8452 +Train: [65] [1600/6250] eta: 0:14:19 lr: 0.000037 grad: 0.1104 (0.1183) loss: 0.8299 (0.8395) time: 0.1039 data: 0.0211 max mem: 8452 +Train: [65] [1700/6250] eta: 0:13:56 lr: 0.000037 grad: 0.1096 (0.1180) loss: 0.8348 (0.8393) time: 0.1933 data: 0.1207 max mem: 8452 +Train: [65] [1800/6250] eta: 0:13:36 lr: 0.000037 grad: 0.1077 (0.1177) loss: 0.8338 (0.8390) time: 0.1897 data: 0.1172 max mem: 8452 +Train: [65] [1900/6250] eta: 0:13:13 lr: 0.000037 grad: 0.1113 (0.1177) loss: 0.8308 (0.8389) time: 0.1754 data: 0.0926 max mem: 8452 +Train: [65] [2000/6250] eta: 0:12:51 lr: 0.000037 grad: 0.1116 (0.1175) loss: 0.8390 (0.8389) time: 0.1585 data: 0.0883 max mem: 8452 +Train: [65] [2100/6250] eta: 0:12:30 lr: 0.000037 grad: 0.1084 (0.1173) loss: 0.8344 (0.8386) time: 0.1526 data: 0.0684 max mem: 8452 +Train: [65] [2200/6250] eta: 0:12:10 lr: 0.000037 grad: 0.1119 (0.1171) loss: 0.8384 (0.8386) time: 0.1647 data: 0.0868 max mem: 8452 +Train: [65] [2300/6250] eta: 0:11:49 lr: 0.000037 grad: 0.1098 (0.1171) loss: 0.8334 (0.8384) time: 0.1563 data: 0.0789 max mem: 8452 +Train: [65] [2400/6250] eta: 0:11:27 lr: 0.000037 grad: 0.1165 (0.1171) loss: 0.8419 (0.8385) time: 0.1617 data: 0.0761 max mem: 8452 +Train: [65] [2500/6250] eta: 0:11:08 lr: 0.000037 grad: 0.1100 (0.1169) loss: 0.8384 (0.8385) time: 0.1748 data: 0.0912 max mem: 8452 +Train: [65] [2600/6250] eta: 0:10:48 lr: 0.000037 grad: 0.1084 (0.1168) loss: 0.8371 (0.8383) time: 0.1984 data: 0.1234 max mem: 8452 +Train: [65] [2700/6250] eta: 0:10:28 lr: 0.000037 grad: 0.1105 (0.1167) loss: 0.8359 (0.8382) time: 0.1329 data: 0.0543 max mem: 8452 +Train: [65] [2800/6250] eta: 0:10:07 lr: 0.000037 grad: 0.1073 (0.1166) loss: 0.8367 (0.8382) time: 0.1545 data: 0.0785 max mem: 8452 +Train: [65] [2900/6250] eta: 0:09:48 lr: 0.000037 grad: 0.1100 (0.1166) loss: 0.8352 (0.8381) time: 0.1601 data: 0.0797 max mem: 8452 +Train: [65] [3000/6250] eta: 0:09:28 lr: 0.000036 grad: 0.1101 (0.1166) loss: 0.8409 (0.8381) time: 0.1570 data: 0.0686 max mem: 8452 +Train: [65] [3100/6250] eta: 0:09:08 lr: 0.000036 grad: 0.1080 (0.1164) loss: 0.8465 (0.8381) time: 0.1595 data: 0.0838 max mem: 8452 +Train: [65] [3200/6250] eta: 0:08:50 lr: 0.000036 grad: 0.1125 (0.1164) loss: 0.8392 (0.8380) time: 0.1512 data: 0.0629 max mem: 8452 +Train: [65] [3300/6250] eta: 0:08:33 lr: 0.000036 grad: 0.1089 (0.1164) loss: 0.8419 (0.8381) time: 0.1026 data: 0.0003 max mem: 8452 +Train: [65] [3400/6250] eta: 0:08:15 lr: 0.000036 grad: 0.1101 (0.1164) loss: 0.8408 (0.8381) time: 0.1795 data: 0.0789 max mem: 8452 +Train: [65] [3500/6250] eta: 0:07:56 lr: 0.000036 grad: 0.1124 (0.1164) loss: 0.8377 (0.8380) time: 0.1422 data: 0.0582 max mem: 8452 +Train: [65] [3600/6250] eta: 0:07:39 lr: 0.000036 grad: 0.1148 (0.1164) loss: 0.8395 (0.8380) time: 0.1697 data: 0.0778 max mem: 8452 +Train: [65] [3700/6250] eta: 0:07:22 lr: 0.000036 grad: 0.1095 (0.1163) loss: 0.8361 (0.8381) time: 0.1501 data: 0.0739 max mem: 8452 +Train: [65] [3800/6250] eta: 0:07:05 lr: 0.000036 grad: 0.1098 (0.1163) loss: 0.8438 (0.8380) time: 0.1622 data: 0.0818 max mem: 8452 +Train: [65] [3900/6250] eta: 0:06:47 lr: 0.000036 grad: 0.1079 (0.1162) loss: 0.8419 (0.8379) time: 0.1754 data: 0.0991 max mem: 8452 +Train: [65] [4000/6250] eta: 0:06:29 lr: 0.000036 grad: 0.1103 (0.1162) loss: 0.8367 (0.8379) time: 0.1519 data: 0.0877 max mem: 8452 +Train: [65] [4100/6250] eta: 0:06:11 lr: 0.000036 grad: 0.1138 (0.1163) loss: 0.8273 (0.8378) time: 0.1675 data: 0.0950 max mem: 8452 +Train: [65] [4200/6250] eta: 0:05:54 lr: 0.000036 grad: 0.1199 (0.1163) loss: 0.8282 (0.8377) time: 0.1714 data: 0.0800 max mem: 8452 +Train: [65] [4300/6250] eta: 0:05:36 lr: 0.000036 grad: 0.1097 (0.1163) loss: 0.8301 (0.8377) time: 0.1576 data: 0.0751 max mem: 8452 +Train: [65] [4400/6250] eta: 0:05:18 lr: 0.000036 grad: 0.1119 (0.1163) loss: 0.8360 (0.8377) time: 0.1609 data: 0.0861 max mem: 8452 +Train: [65] [4500/6250] eta: 0:05:01 lr: 0.000036 grad: 0.1079 (0.1164) loss: 0.8387 (0.8378) time: 0.1389 data: 0.0560 max mem: 8452 +Train: [65] [4600/6250] eta: 0:04:43 lr: 0.000036 grad: 0.1075 (0.1163) loss: 0.8382 (0.8378) time: 0.1226 data: 0.0325 max mem: 8452 +Train: [65] [4700/6250] eta: 0:04:25 lr: 0.000036 grad: 0.1117 (0.1162) loss: 0.8425 (0.8379) time: 0.1428 data: 0.0563 max mem: 8452 +Train: [65] [4800/6250] eta: 0:04:08 lr: 0.000036 grad: 0.1165 (0.1162) loss: 0.8373 (0.8380) time: 0.1600 data: 0.0819 max mem: 8452 +Train: [65] [4900/6250] eta: 0:03:51 lr: 0.000036 grad: 0.1100 (0.1162) loss: 0.8395 (0.8380) time: 0.1471 data: 0.0694 max mem: 8452 +Train: [65] [5000/6250] eta: 0:03:34 lr: 0.000036 grad: 0.1166 (0.1162) loss: 0.8356 (0.8380) time: 0.1221 data: 0.0522 max mem: 8452 +Train: [65] [5100/6250] eta: 0:03:17 lr: 0.000036 grad: 0.1176 (0.1162) loss: 0.8361 (0.8381) time: 0.1735 data: 0.0948 max mem: 8452 +Train: [65] [5200/6250] eta: 0:02:59 lr: 0.000036 grad: 0.1075 (0.1161) loss: 0.8441 (0.8381) time: 0.1530 data: 0.0764 max mem: 8452 +Train: [65] [5300/6250] eta: 0:02:42 lr: 0.000036 grad: 0.1146 (0.1161) loss: 0.8388 (0.8382) time: 0.1530 data: 0.0691 max mem: 8452 +Train: [65] [5400/6250] eta: 0:02:25 lr: 0.000036 grad: 0.1083 (0.1161) loss: 0.8479 (0.8383) time: 0.1488 data: 0.0546 max mem: 8452 +Train: [65] [5500/6250] eta: 0:02:08 lr: 0.000036 grad: 0.1180 (0.1161) loss: 0.8360 (0.8383) time: 0.1090 data: 0.0003 max mem: 8452 +Train: [65] [5600/6250] eta: 0:01:51 lr: 0.000036 grad: 0.1101 (0.1161) loss: 0.8461 (0.8383) time: 0.1300 data: 0.0367 max mem: 8452 +Train: [65] [5700/6250] eta: 0:01:34 lr: 0.000036 grad: 0.1158 (0.1161) loss: 0.8369 (0.8383) time: 0.1462 data: 0.0717 max mem: 8452 +Train: [65] [5800/6250] eta: 0:01:17 lr: 0.000036 grad: 0.1094 (0.1160) loss: 0.8394 (0.8383) time: 0.1068 data: 0.0002 max mem: 8452 +Train: [65] [5900/6250] eta: 0:01:00 lr: 0.000036 grad: 0.1146 (0.1160) loss: 0.8364 (0.8383) time: 0.1715 data: 0.0856 max mem: 8452 +Train: [65] [6000/6250] eta: 0:00:42 lr: 0.000036 grad: 0.1135 (0.1160) loss: 0.8373 (0.8383) time: 0.1649 data: 0.0847 max mem: 8452 +Train: [65] [6100/6250] eta: 0:00:25 lr: 0.000036 grad: 0.1096 (0.1160) loss: 0.8462 (0.8383) time: 0.1622 data: 0.0837 max mem: 8452 +Train: [65] [6200/6250] eta: 0:00:08 lr: 0.000036 grad: 0.1112 (0.1160) loss: 0.8378 (0.8383) time: 0.1538 data: 0.0783 max mem: 8452 +Train: [65] [6249/6250] eta: 0:00:00 lr: 0.000036 grad: 0.1105 (0.1160) loss: 0.8404 (0.8383) time: 0.1407 data: 0.0670 max mem: 8452 +Train: [65] Total time: 0:17:57 (0.1724 s / it) +Averaged stats: lr: 0.000036 grad: 0.1105 (0.1160) loss: 0.8404 (0.8383) +Eval (hcp-train-subset): [65] [ 0/62] eta: 0:04:22 loss: 0.8778 (0.8778) time: 4.2284 data: 4.1326 max mem: 8452 +Eval (hcp-train-subset): [65] [61/62] eta: 0:00:00 loss: 0.8603 (0.8622) time: 0.1494 data: 0.1239 max mem: 8452 +Eval (hcp-train-subset): [65] Total time: 0:00:14 (0.2411 s / it) +Averaged stats (hcp-train-subset): loss: 0.8603 (0.8622) +Eval (hcp-val): [65] [ 0/62] eta: 0:05:27 loss: 0.8689 (0.8689) time: 5.2814 data: 5.2547 max mem: 8452 +Eval (hcp-val): [65] [61/62] eta: 0:00:00 loss: 0.8704 (0.8720) time: 0.1242 data: 0.1030 max mem: 8452 +Eval (hcp-val): [65] Total time: 0:00:15 (0.2470 s / it) +Averaged stats (hcp-val): loss: 0.8704 (0.8720) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [66] [ 0/6250] eta: 11:31:36 lr: 0.000036 grad: 0.1445 (0.1445) loss: 0.8271 (0.8271) time: 6.6395 data: 6.5268 max mem: 8452 +Train: [66] [ 100/6250] eta: 0:23:39 lr: 0.000035 grad: 0.1754 (0.1844) loss: 0.8455 (0.8472) time: 0.1754 data: 0.0790 max mem: 8452 +Train: [66] [ 200/6250] eta: 0:20:15 lr: 0.000035 grad: 0.1242 (0.1659) loss: 0.8501 (0.8466) time: 0.1547 data: 0.0528 max mem: 8452 +Train: [66] [ 300/6250] eta: 0:18:44 lr: 0.000035 grad: 0.1097 (0.1511) loss: 0.8564 (0.8464) time: 0.1509 data: 0.0466 max mem: 8452 +Train: [66] [ 400/6250] eta: 0:17:53 lr: 0.000035 grad: 0.1137 (0.1434) loss: 0.8379 (0.8446) time: 0.1566 data: 0.0648 max mem: 8452 +Train: [66] [ 500/6250] eta: 0:17:14 lr: 0.000035 grad: 0.1149 (0.1385) loss: 0.8239 (0.8424) time: 0.1585 data: 0.0806 max mem: 8452 +Train: [66] [ 600/6250] eta: 0:16:36 lr: 0.000035 grad: 0.1218 (0.1355) loss: 0.8422 (0.8416) time: 0.1273 data: 0.0466 max mem: 8452 +Train: [66] [ 700/6250] eta: 0:16:12 lr: 0.000035 grad: 0.1135 (0.1326) loss: 0.8495 (0.8419) time: 0.1632 data: 0.0826 max mem: 8452 +Train: [66] [ 800/6250] eta: 0:16:05 lr: 0.000035 grad: 0.1107 (0.1304) loss: 0.8486 (0.8418) time: 0.2520 data: 0.1490 max mem: 8452 +Train: [66] [ 900/6250] eta: 0:15:47 lr: 0.000035 grad: 0.1196 (0.1287) loss: 0.8419 (0.8418) time: 0.1557 data: 0.0698 max mem: 8452 +Train: [66] [1000/6250] eta: 0:15:22 lr: 0.000035 grad: 0.1125 (0.1273) loss: 0.8470 (0.8417) time: 0.1615 data: 0.0634 max mem: 8452 +Train: [66] [1100/6250] eta: 0:14:56 lr: 0.000035 grad: 0.1168 (0.1259) loss: 0.8339 (0.8416) time: 0.1643 data: 0.0772 max mem: 8452 +Train: [66] [1200/6250] eta: 0:14:40 lr: 0.000035 grad: 0.1118 (0.1249) loss: 0.8336 (0.8415) time: 0.1835 data: 0.0647 max mem: 8452 +Train: [66] [1300/6250] eta: 0:14:20 lr: 0.000035 grad: 0.1149 (0.1241) loss: 0.8398 (0.8414) time: 0.1296 data: 0.0350 max mem: 8452 +Train: [66] [1400/6250] eta: 0:13:55 lr: 0.000035 grad: 0.1126 (0.1234) loss: 0.8351 (0.8409) time: 0.1513 data: 0.0830 max mem: 8452 +Train: [66] [1500/6250] eta: 0:13:32 lr: 0.000035 grad: 0.1086 (0.1228) loss: 0.8340 (0.8406) time: 0.1594 data: 0.0758 max mem: 8452 +Train: [66] [1600/6250] eta: 0:13:11 lr: 0.000035 grad: 0.1089 (0.1222) loss: 0.8369 (0.8404) time: 0.1692 data: 0.0975 max mem: 8452 +Train: [66] [1700/6250] eta: 0:13:03 lr: 0.000035 grad: 0.1149 (0.1218) loss: 0.8383 (0.8402) time: 0.3574 data: 0.2652 max mem: 8452 +Train: [66] [1800/6250] eta: 0:12:41 lr: 0.000035 grad: 0.1138 (0.1215) loss: 0.8299 (0.8400) time: 0.1707 data: 0.1071 max mem: 8452 +Train: [66] [1900/6250] eta: 0:12:22 lr: 0.000035 grad: 0.1117 (0.1211) loss: 0.8402 (0.8399) time: 0.1601 data: 0.0873 max mem: 8452 +Train: [66] [2000/6250] eta: 0:12:04 lr: 0.000035 grad: 0.1183 (0.1210) loss: 0.8379 (0.8399) time: 0.1494 data: 0.0682 max mem: 8452 +Train: [66] [2100/6250] eta: 0:11:46 lr: 0.000035 grad: 0.1257 (0.1209) loss: 0.8332 (0.8397) time: 0.1669 data: 0.0869 max mem: 8452 +Train: [66] [2200/6250] eta: 0:11:30 lr: 0.000035 grad: 0.1139 (0.1209) loss: 0.8355 (0.8395) time: 0.1808 data: 0.1094 max mem: 8452 +Train: [66] [2300/6250] eta: 0:11:12 lr: 0.000035 grad: 0.1257 (0.1211) loss: 0.8366 (0.8394) time: 0.1590 data: 0.0650 max mem: 8452 +Train: [66] [2400/6250] eta: 0:10:54 lr: 0.000035 grad: 0.1212 (0.1212) loss: 0.8309 (0.8391) time: 0.1232 data: 0.0364 max mem: 8452 +Train: [66] [2500/6250] eta: 0:10:35 lr: 0.000035 grad: 0.1258 (0.1212) loss: 0.8289 (0.8389) time: 0.1710 data: 0.0906 max mem: 8452 +Train: [66] [2600/6250] eta: 0:10:19 lr: 0.000035 grad: 0.1174 (0.1214) loss: 0.8329 (0.8387) time: 0.1677 data: 0.0932 max mem: 8452 +Train: [66] [2700/6250] eta: 0:10:01 lr: 0.000035 grad: 0.1211 (0.1213) loss: 0.8213 (0.8385) time: 0.1513 data: 0.0743 max mem: 8452 +Train: [66] [2800/6250] eta: 0:09:43 lr: 0.000035 grad: 0.1208 (0.1212) loss: 0.8338 (0.8383) time: 0.1471 data: 0.0611 max mem: 8452 +Train: [66] [2900/6250] eta: 0:09:27 lr: 0.000035 grad: 0.1227 (0.1213) loss: 0.8330 (0.8381) time: 0.1410 data: 0.0526 max mem: 8452 +Train: [66] [3000/6250] eta: 0:09:09 lr: 0.000035 grad: 0.1227 (0.1213) loss: 0.8253 (0.8378) time: 0.1818 data: 0.1019 max mem: 8452 +Train: [66] [3100/6250] eta: 0:08:52 lr: 0.000035 grad: 0.1107 (0.1214) loss: 0.8312 (0.8375) time: 0.1658 data: 0.0572 max mem: 8452 +Train: [66] [3200/6250] eta: 0:08:35 lr: 0.000035 grad: 0.1220 (0.1215) loss: 0.8300 (0.8373) time: 0.1737 data: 0.0837 max mem: 8452 +Train: [66] [3300/6250] eta: 0:08:19 lr: 0.000035 grad: 0.1203 (0.1215) loss: 0.8264 (0.8370) time: 0.1868 data: 0.0996 max mem: 8452 +Train: [66] [3400/6250] eta: 0:08:02 lr: 0.000035 grad: 0.1147 (0.1214) loss: 0.8263 (0.8368) time: 0.1463 data: 0.0536 max mem: 8452 +Train: [66] [3500/6250] eta: 0:07:45 lr: 0.000034 grad: 0.1164 (0.1214) loss: 0.8272 (0.8366) time: 0.1593 data: 0.0829 max mem: 8452 +Train: [66] [3600/6250] eta: 0:07:28 lr: 0.000034 grad: 0.1107 (0.1214) loss: 0.8283 (0.8363) time: 0.1320 data: 0.0422 max mem: 8452 +Train: [66] [3700/6250] eta: 0:07:10 lr: 0.000034 grad: 0.1225 (0.1214) loss: 0.8248 (0.8360) time: 0.1814 data: 0.1064 max mem: 8452 +Train: [66] [3800/6250] eta: 0:06:53 lr: 0.000034 grad: 0.1157 (0.1215) loss: 0.8303 (0.8359) time: 0.1644 data: 0.0931 max mem: 8452 +Train: [66] [3900/6250] eta: 0:06:37 lr: 0.000034 grad: 0.1199 (0.1215) loss: 0.8212 (0.8357) time: 0.2171 data: 0.1508 max mem: 8452 +Train: [66] [4000/6250] eta: 0:06:20 lr: 0.000034 grad: 0.1232 (0.1215) loss: 0.8298 (0.8355) time: 0.1703 data: 0.0938 max mem: 8452 +Train: [66] [4100/6250] eta: 0:06:03 lr: 0.000034 grad: 0.1186 (0.1215) loss: 0.8228 (0.8353) time: 0.1899 data: 0.1233 max mem: 8452 +Train: [66] [4200/6250] eta: 0:05:45 lr: 0.000034 grad: 0.1161 (0.1215) loss: 0.8271 (0.8351) time: 0.1648 data: 0.0863 max mem: 8452 +Train: [66] [4300/6250] eta: 0:05:29 lr: 0.000034 grad: 0.1194 (0.1215) loss: 0.8306 (0.8350) time: 0.2113 data: 0.1301 max mem: 8452 +Train: [66] [4400/6250] eta: 0:05:11 lr: 0.000034 grad: 0.1227 (0.1214) loss: 0.8300 (0.8348) time: 0.1741 data: 0.0882 max mem: 8452 +Train: [66] [4500/6250] eta: 0:04:54 lr: 0.000034 grad: 0.1177 (0.1214) loss: 0.8275 (0.8347) time: 0.1505 data: 0.0582 max mem: 8452 +Train: [66] [4600/6250] eta: 0:04:36 lr: 0.000034 grad: 0.1178 (0.1213) loss: 0.8358 (0.8347) time: 0.1472 data: 0.0574 max mem: 8452 +Train: [66] [4700/6250] eta: 0:04:19 lr: 0.000034 grad: 0.1206 (0.1214) loss: 0.8360 (0.8346) time: 0.1670 data: 0.0871 max mem: 8452 +Train: [66] [4800/6250] eta: 0:04:02 lr: 0.000034 grad: 0.1247 (0.1214) loss: 0.8276 (0.8345) time: 0.1674 data: 0.0873 max mem: 8452 +Train: [66] [4900/6250] eta: 0:03:45 lr: 0.000034 grad: 0.1194 (0.1215) loss: 0.8280 (0.8344) time: 0.1810 data: 0.0959 max mem: 8452 +Train: [66] [5000/6250] eta: 0:03:28 lr: 0.000034 grad: 0.1157 (0.1215) loss: 0.8334 (0.8344) time: 0.1560 data: 0.0692 max mem: 8452 +Train: [66] [5100/6250] eta: 0:03:12 lr: 0.000034 grad: 0.1211 (0.1215) loss: 0.8317 (0.8343) time: 0.1095 data: 0.0003 max mem: 8452 +Train: [66] [5200/6250] eta: 0:02:55 lr: 0.000034 grad: 0.1201 (0.1215) loss: 0.8321 (0.8343) time: 0.1140 data: 0.0299 max mem: 8452 +Train: [66] [5300/6250] eta: 0:02:39 lr: 0.000034 grad: 0.1255 (0.1216) loss: 0.8295 (0.8342) time: 0.1381 data: 0.0508 max mem: 8452 +Train: [66] [5400/6250] eta: 0:02:22 lr: 0.000034 grad: 0.1267 (0.1216) loss: 0.8355 (0.8342) time: 0.1841 data: 0.1043 max mem: 8452 +Train: [66] [5500/6250] eta: 0:02:05 lr: 0.000034 grad: 0.1235 (0.1217) loss: 0.8294 (0.8341) time: 0.1534 data: 0.0679 max mem: 8452 +Train: [66] [5600/6250] eta: 0:01:48 lr: 0.000034 grad: 0.1221 (0.1217) loss: 0.8417 (0.8341) time: 0.1802 data: 0.0972 max mem: 8452 +Train: [66] [5700/6250] eta: 0:01:31 lr: 0.000034 grad: 0.1125 (0.1216) loss: 0.8359 (0.8341) time: 0.1432 data: 0.0573 max mem: 8452 +Train: [66] [5800/6250] eta: 0:01:14 lr: 0.000034 grad: 0.1153 (0.1216) loss: 0.8347 (0.8341) time: 0.1304 data: 0.0423 max mem: 8452 +Train: [66] [5900/6250] eta: 0:00:58 lr: 0.000034 grad: 0.1127 (0.1216) loss: 0.8342 (0.8341) time: 0.1669 data: 0.0870 max mem: 8452 +Train: [66] [6000/6250] eta: 0:00:41 lr: 0.000034 grad: 0.1124 (0.1216) loss: 0.8331 (0.8340) time: 0.2094 data: 0.1188 max mem: 8452 +Train: [66] [6100/6250] eta: 0:00:25 lr: 0.000034 grad: 0.1211 (0.1216) loss: 0.8241 (0.8340) time: 0.1569 data: 0.0697 max mem: 8452 +Train: [66] [6200/6250] eta: 0:00:08 lr: 0.000034 grad: 0.1202 (0.1216) loss: 0.8198 (0.8339) time: 0.1608 data: 0.0816 max mem: 8452 +Train: [66] [6249/6250] eta: 0:00:00 lr: 0.000034 grad: 0.1199 (0.1216) loss: 0.8361 (0.8339) time: 0.1796 data: 0.0994 max mem: 8452 +Train: [66] Total time: 0:17:28 (0.1678 s / it) +Averaged stats: lr: 0.000034 grad: 0.1199 (0.1216) loss: 0.8361 (0.8339) +Eval (hcp-train-subset): [66] [ 0/62] eta: 0:05:19 loss: 0.8698 (0.8698) time: 5.1551 data: 5.1278 max mem: 8452 +Eval (hcp-train-subset): [66] [61/62] eta: 0:00:00 loss: 0.8584 (0.8616) time: 0.1429 data: 0.1214 max mem: 8452 +Eval (hcp-train-subset): [66] Total time: 0:00:15 (0.2442 s / it) +Averaged stats (hcp-train-subset): loss: 0.8584 (0.8616) +Eval (hcp-val): [66] [ 0/62] eta: 0:05:09 loss: 0.8692 (0.8692) time: 4.9952 data: 4.9580 max mem: 8452 +Eval (hcp-val): [66] [61/62] eta: 0:00:00 loss: 0.8684 (0.8707) time: 0.1295 data: 0.1083 max mem: 8452 +Eval (hcp-val): [66] Total time: 0:00:15 (0.2422 s / it) +Averaged stats (hcp-val): loss: 0.8684 (0.8707) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [67] [ 0/6250] eta: 13:42:57 lr: 0.000034 grad: 0.0910 (0.0910) loss: 0.8985 (0.8985) time: 7.9004 data: 7.7949 max mem: 8452 +Train: [67] [ 100/6250] eta: 0:23:53 lr: 0.000034 grad: 0.1236 (0.1527) loss: 0.8417 (0.8540) time: 0.1722 data: 0.0672 max mem: 8452 +Train: [67] [ 200/6250] eta: 0:20:07 lr: 0.000034 grad: 0.1258 (0.1441) loss: 0.8395 (0.8476) time: 0.1587 data: 0.0450 max mem: 8452 +Train: [67] [ 300/6250] eta: 0:19:24 lr: 0.000034 grad: 0.1209 (0.1412) loss: 0.8413 (0.8437) time: 0.2160 data: 0.1138 max mem: 8452 +Train: [67] [ 400/6250] eta: 0:18:21 lr: 0.000034 grad: 0.1167 (0.1364) loss: 0.8427 (0.8424) time: 0.1743 data: 0.0720 max mem: 8452 +Train: [67] [ 500/6250] eta: 0:17:37 lr: 0.000034 grad: 0.1116 (0.1322) loss: 0.8462 (0.8426) time: 0.1567 data: 0.0615 max mem: 8452 +Train: [67] [ 600/6250] eta: 0:17:37 lr: 0.000033 grad: 0.1101 (0.1293) loss: 0.8424 (0.8426) time: 0.3251 data: 0.2351 max mem: 8452 +Train: [67] [ 700/6250] eta: 0:16:46 lr: 0.000033 grad: 0.1171 (0.1281) loss: 0.8456 (0.8424) time: 0.1094 data: 0.0096 max mem: 8452 +Train: [67] [ 800/6250] eta: 0:16:14 lr: 0.000033 grad: 0.1089 (0.1269) loss: 0.8480 (0.8423) time: 0.1477 data: 0.0581 max mem: 8452 +Train: [67] [ 900/6250] eta: 0:16:01 lr: 0.000033 grad: 0.1128 (0.1252) loss: 0.8500 (0.8422) time: 0.1149 data: 0.0003 max mem: 8452 +Train: [67] [1000/6250] eta: 0:15:52 lr: 0.000033 grad: 0.1105 (0.1240) loss: 0.8329 (0.8421) time: 0.3367 data: 0.2434 max mem: 8452 +Train: [67] [1100/6250] eta: 0:15:33 lr: 0.000033 grad: 0.1158 (0.1235) loss: 0.8427 (0.8417) time: 0.1241 data: 0.0187 max mem: 8452 +Train: [67] [1200/6250] eta: 0:15:11 lr: 0.000033 grad: 0.1122 (0.1228) loss: 0.8411 (0.8411) time: 0.1617 data: 0.0869 max mem: 8452 +Train: [67] [1300/6250] eta: 0:14:47 lr: 0.000033 grad: 0.1122 (0.1223) loss: 0.8346 (0.8407) time: 0.1486 data: 0.0589 max mem: 8452 +Train: [67] [1400/6250] eta: 0:14:21 lr: 0.000033 grad: 0.1104 (0.1218) loss: 0.8317 (0.8400) time: 0.1571 data: 0.0773 max mem: 8452 +Train: [67] [1500/6250] eta: 0:13:57 lr: 0.000033 grad: 0.1098 (0.1212) loss: 0.8337 (0.8396) time: 0.1804 data: 0.1114 max mem: 8452 +Train: [67] [1600/6250] eta: 0:13:41 lr: 0.000033 grad: 0.1151 (0.1210) loss: 0.8246 (0.8393) time: 0.2290 data: 0.1666 max mem: 8452 +Train: [67] [1700/6250] eta: 0:13:20 lr: 0.000033 grad: 0.1085 (0.1207) loss: 0.8301 (0.8388) time: 0.1707 data: 0.0856 max mem: 8452 +Train: [67] [1800/6250] eta: 0:12:59 lr: 0.000033 grad: 0.1146 (0.1204) loss: 0.8334 (0.8386) time: 0.1551 data: 0.0776 max mem: 8452 +Train: [67] [1900/6250] eta: 0:12:42 lr: 0.000033 grad: 0.1077 (0.1201) loss: 0.8413 (0.8384) time: 0.1805 data: 0.1059 max mem: 8452 +Train: [67] [2000/6250] eta: 0:12:23 lr: 0.000033 grad: 0.1106 (0.1199) loss: 0.8454 (0.8381) time: 0.1236 data: 0.0299 max mem: 8452 +Train: [67] [2100/6250] eta: 0:12:03 lr: 0.000033 grad: 0.1180 (0.1198) loss: 0.8307 (0.8378) time: 0.1640 data: 0.0836 max mem: 8452 +Train: [67] [2200/6250] eta: 0:11:43 lr: 0.000033 grad: 0.1163 (0.1196) loss: 0.8371 (0.8377) time: 0.1426 data: 0.0567 max mem: 8452 +Train: [67] [2300/6250] eta: 0:11:24 lr: 0.000033 grad: 0.1128 (0.1197) loss: 0.8328 (0.8375) time: 0.1362 data: 0.0594 max mem: 8452 +Train: [67] [2400/6250] eta: 0:11:04 lr: 0.000033 grad: 0.1062 (0.1194) loss: 0.8391 (0.8374) time: 0.1655 data: 0.0796 max mem: 8452 +Train: [67] [2500/6250] eta: 0:10:47 lr: 0.000033 grad: 0.1095 (0.1192) loss: 0.8350 (0.8374) time: 0.1889 data: 0.1102 max mem: 8452 +Train: [67] [2600/6250] eta: 0:10:32 lr: 0.000033 grad: 0.1190 (0.1192) loss: 0.8370 (0.8373) time: 0.2426 data: 0.1553 max mem: 8452 +Train: [67] [2700/6250] eta: 0:10:15 lr: 0.000033 grad: 0.1103 (0.1192) loss: 0.8388 (0.8373) time: 0.1535 data: 0.0680 max mem: 8452 +Train: [67] [2800/6250] eta: 0:09:58 lr: 0.000033 grad: 0.1097 (0.1190) loss: 0.8382 (0.8372) time: 0.1673 data: 0.0878 max mem: 8452 +Train: [67] [2900/6250] eta: 0:09:39 lr: 0.000033 grad: 0.1118 (0.1189) loss: 0.8345 (0.8373) time: 0.1642 data: 0.0770 max mem: 8452 +Train: [67] [3000/6250] eta: 0:09:20 lr: 0.000033 grad: 0.1221 (0.1190) loss: 0.8302 (0.8371) time: 0.1581 data: 0.0753 max mem: 8452 +Train: [67] [3100/6250] eta: 0:09:02 lr: 0.000033 grad: 0.1210 (0.1190) loss: 0.8297 (0.8369) time: 0.1148 data: 0.0117 max mem: 8452 +Train: [67] [3200/6250] eta: 0:08:43 lr: 0.000033 grad: 0.1198 (0.1190) loss: 0.8357 (0.8368) time: 0.1577 data: 0.0793 max mem: 8452 +Train: [67] [3300/6250] eta: 0:08:24 lr: 0.000033 grad: 0.1181 (0.1191) loss: 0.8263 (0.8368) time: 0.1408 data: 0.0477 max mem: 8452 +Train: [67] [3400/6250] eta: 0:08:04 lr: 0.000033 grad: 0.1113 (0.1191) loss: 0.8360 (0.8367) time: 0.1588 data: 0.0742 max mem: 8452 +Train: [67] [3500/6250] eta: 0:07:46 lr: 0.000033 grad: 0.1234 (0.1192) loss: 0.8380 (0.8366) time: 0.1364 data: 0.0503 max mem: 8452 +Train: [67] [3600/6250] eta: 0:07:28 lr: 0.000033 grad: 0.1185 (0.1192) loss: 0.8295 (0.8365) time: 0.1615 data: 0.0803 max mem: 8452 +Train: [67] [3700/6250] eta: 0:07:11 lr: 0.000033 grad: 0.1143 (0.1192) loss: 0.8240 (0.8363) time: 0.2296 data: 0.1557 max mem: 8452 +Train: [67] [3800/6250] eta: 0:06:56 lr: 0.000033 grad: 0.1181 (0.1191) loss: 0.8341 (0.8362) time: 0.1506 data: 0.0512 max mem: 8452 +Train: [67] [3900/6250] eta: 0:06:40 lr: 0.000033 grad: 0.1188 (0.1191) loss: 0.8398 (0.8361) time: 0.2376 data: 0.1638 max mem: 8452 +Train: [67] [4000/6250] eta: 0:06:24 lr: 0.000032 grad: 0.1166 (0.1191) loss: 0.8366 (0.8361) time: 0.1767 data: 0.0982 max mem: 8452 +Train: [67] [4100/6250] eta: 0:06:06 lr: 0.000032 grad: 0.1193 (0.1191) loss: 0.8342 (0.8360) time: 0.1559 data: 0.0829 max mem: 8452 +Train: [67] [4200/6250] eta: 0:05:50 lr: 0.000032 grad: 0.1144 (0.1191) loss: 0.8311 (0.8360) time: 0.2127 data: 0.1352 max mem: 8452 +Train: [67] [4300/6250] eta: 0:05:32 lr: 0.000032 grad: 0.1170 (0.1191) loss: 0.8323 (0.8360) time: 0.1520 data: 0.0654 max mem: 8452 +Train: [67] [4400/6250] eta: 0:05:15 lr: 0.000032 grad: 0.1167 (0.1192) loss: 0.8303 (0.8359) time: 0.1489 data: 0.0526 max mem: 8452 +Train: [67] [4500/6250] eta: 0:04:58 lr: 0.000032 grad: 0.1178 (0.1193) loss: 0.8248 (0.8357) time: 0.1676 data: 0.0891 max mem: 8452 +Train: [67] [4600/6250] eta: 0:04:41 lr: 0.000032 grad: 0.1173 (0.1192) loss: 0.8269 (0.8357) time: 0.1927 data: 0.0960 max mem: 8452 +Train: [67] [4700/6250] eta: 0:04:24 lr: 0.000032 grad: 0.1181 (0.1193) loss: 0.8251 (0.8355) time: 0.1582 data: 0.0745 max mem: 8452 +Train: [67] [4800/6250] eta: 0:04:07 lr: 0.000032 grad: 0.1184 (0.1193) loss: 0.8363 (0.8354) time: 0.1672 data: 0.0932 max mem: 8452 +Train: [67] [4900/6250] eta: 0:03:50 lr: 0.000032 grad: 0.1124 (0.1193) loss: 0.8276 (0.8353) time: 0.1122 data: 0.0003 max mem: 8452 +Train: [67] [5000/6250] eta: 0:03:33 lr: 0.000032 grad: 0.1144 (0.1193) loss: 0.8367 (0.8352) time: 0.1703 data: 0.0615 max mem: 8452 +Train: [67] [5100/6250] eta: 0:03:16 lr: 0.000032 grad: 0.1164 (0.1195) loss: 0.8252 (0.8351) time: 0.1921 data: 0.1055 max mem: 8452 +Train: [67] [5200/6250] eta: 0:02:59 lr: 0.000032 grad: 0.1187 (0.1195) loss: 0.8353 (0.8350) time: 0.1269 data: 0.0368 max mem: 8452 +Train: [67] [5300/6250] eta: 0:02:42 lr: 0.000032 grad: 0.1169 (0.1195) loss: 0.8249 (0.8349) time: 0.2087 data: 0.1423 max mem: 8452 +Train: [67] [5400/6250] eta: 0:02:24 lr: 0.000032 grad: 0.1202 (0.1196) loss: 0.8281 (0.8348) time: 0.1672 data: 0.0732 max mem: 8452 +Train: [67] [5500/6250] eta: 0:02:07 lr: 0.000032 grad: 0.1247 (0.1197) loss: 0.8274 (0.8347) time: 0.1114 data: 0.0325 max mem: 8452 +Train: [67] [5600/6250] eta: 0:01:50 lr: 0.000032 grad: 0.1149 (0.1197) loss: 0.8334 (0.8347) time: 0.1508 data: 0.0740 max mem: 8452 +Train: [67] [5700/6250] eta: 0:01:33 lr: 0.000032 grad: 0.1242 (0.1198) loss: 0.8300 (0.8346) time: 0.1759 data: 0.1003 max mem: 8452 +Train: [67] [5800/6250] eta: 0:01:16 lr: 0.000032 grad: 0.1176 (0.1198) loss: 0.8283 (0.8346) time: 0.1402 data: 0.0248 max mem: 8452 +Train: [67] [5900/6250] eta: 0:00:59 lr: 0.000032 grad: 0.1204 (0.1199) loss: 0.8347 (0.8345) time: 0.1400 data: 0.0494 max mem: 8452 +Train: [67] [6000/6250] eta: 0:00:42 lr: 0.000032 grad: 0.1129 (0.1199) loss: 0.8364 (0.8345) time: 0.3018 data: 0.2217 max mem: 8452 +Train: [67] [6100/6250] eta: 0:00:25 lr: 0.000032 grad: 0.1145 (0.1199) loss: 0.8365 (0.8344) time: 0.1398 data: 0.0477 max mem: 8452 +Train: [67] [6200/6250] eta: 0:00:08 lr: 0.000032 grad: 0.1211 (0.1200) loss: 0.8326 (0.8343) time: 0.1783 data: 0.0919 max mem: 8452 +Train: [67] [6249/6250] eta: 0:00:00 lr: 0.000032 grad: 0.1196 (0.1200) loss: 0.8313 (0.8343) time: 0.1633 data: 0.0857 max mem: 8452 +Train: [67] Total time: 0:17:51 (0.1714 s / it) +Averaged stats: lr: 0.000032 grad: 0.1196 (0.1200) loss: 0.8313 (0.8343) +Eval (hcp-train-subset): [67] [ 0/62] eta: 0:04:34 loss: 0.8715 (0.8715) time: 4.4263 data: 4.3414 max mem: 8452 +Eval (hcp-train-subset): [67] [61/62] eta: 0:00:00 loss: 0.8577 (0.8612) time: 0.1536 data: 0.1324 max mem: 8452 +Eval (hcp-train-subset): [67] Total time: 0:00:14 (0.2408 s / it) +Averaged stats (hcp-train-subset): loss: 0.8577 (0.8612) +Eval (hcp-val): [67] [ 0/62] eta: 0:05:08 loss: 0.8678 (0.8678) time: 4.9742 data: 4.8910 max mem: 8452 +Eval (hcp-val): [67] [61/62] eta: 0:00:00 loss: 0.8694 (0.8716) time: 0.1471 data: 0.1256 max mem: 8452 +Eval (hcp-val): [67] Total time: 0:00:15 (0.2483 s / it) +Averaged stats (hcp-val): loss: 0.8694 (0.8716) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [68] [ 0/6250] eta: 9:34:57 lr: 0.000032 grad: 0.4236 (0.4236) loss: 0.8926 (0.8926) time: 5.5195 data: 5.2760 max mem: 8452 +Train: [68] [ 100/6250] eta: 0:23:43 lr: 0.000032 grad: 0.1126 (0.1450) loss: 0.8545 (0.8548) time: 0.1813 data: 0.0628 max mem: 8452 +Train: [68] [ 200/6250] eta: 0:20:52 lr: 0.000032 grad: 0.1210 (0.1339) loss: 0.8533 (0.8517) time: 0.2030 data: 0.1062 max mem: 8452 +Train: [68] [ 300/6250] eta: 0:19:26 lr: 0.000032 grad: 0.1218 (0.1315) loss: 0.8412 (0.8502) time: 0.2052 data: 0.1091 max mem: 8452 +Train: [68] [ 400/6250] eta: 0:18:09 lr: 0.000032 grad: 0.1137 (0.1296) loss: 0.8438 (0.8490) time: 0.1505 data: 0.0531 max mem: 8452 +Train: [68] [ 500/6250] eta: 0:17:29 lr: 0.000032 grad: 0.1169 (0.1279) loss: 0.8502 (0.8480) time: 0.1481 data: 0.0550 max mem: 8452 +Train: [68] [ 600/6250] eta: 0:17:21 lr: 0.000032 grad: 0.1194 (0.1270) loss: 0.8453 (0.8469) time: 0.2358 data: 0.1239 max mem: 8452 +Train: [68] [ 700/6250] eta: 0:16:52 lr: 0.000032 grad: 0.1318 (0.1270) loss: 0.8260 (0.8455) time: 0.1738 data: 0.0621 max mem: 8452 +Train: [68] [ 800/6250] eta: 0:16:33 lr: 0.000032 grad: 0.1200 (0.1266) loss: 0.8377 (0.8439) time: 0.2399 data: 0.1482 max mem: 8452 +Train: [68] [ 900/6250] eta: 0:16:02 lr: 0.000032 grad: 0.1133 (0.1260) loss: 0.8296 (0.8429) time: 0.1491 data: 0.0687 max mem: 8452 +Train: [68] [1000/6250] eta: 0:15:40 lr: 0.000032 grad: 0.1198 (0.1255) loss: 0.8328 (0.8423) time: 0.2093 data: 0.1475 max mem: 8452 +Train: [68] [1100/6250] eta: 0:15:10 lr: 0.000032 grad: 0.1179 (0.1249) loss: 0.8470 (0.8416) time: 0.1163 data: 0.0145 max mem: 8452 +Train: [68] [1200/6250] eta: 0:14:45 lr: 0.000032 grad: 0.1171 (0.1248) loss: 0.8299 (0.8408) time: 0.1437 data: 0.0566 max mem: 8452 +Train: [68] [1300/6250] eta: 0:14:25 lr: 0.000031 grad: 0.1178 (0.1245) loss: 0.8204 (0.8402) time: 0.1837 data: 0.0961 max mem: 8452 +Train: [68] [1400/6250] eta: 0:14:01 lr: 0.000031 grad: 0.1199 (0.1245) loss: 0.8373 (0.8394) time: 0.1712 data: 0.0975 max mem: 8452 +Train: [68] [1500/6250] eta: 0:13:42 lr: 0.000031 grad: 0.1206 (0.1242) loss: 0.8232 (0.8389) time: 0.1778 data: 0.1158 max mem: 8452 +Train: [68] [1600/6250] eta: 0:13:23 lr: 0.000031 grad: 0.1265 (0.1240) loss: 0.8265 (0.8383) time: 0.1545 data: 0.0803 max mem: 8452 +Train: [68] [1700/6250] eta: 0:13:02 lr: 0.000031 grad: 0.1188 (0.1240) loss: 0.8281 (0.8375) time: 0.1409 data: 0.0609 max mem: 8452 +Train: [68] [1800/6250] eta: 0:12:42 lr: 0.000031 grad: 0.1086 (0.1237) loss: 0.8341 (0.8371) time: 0.1770 data: 0.1015 max mem: 8452 +Train: [68] [1900/6250] eta: 0:12:24 lr: 0.000031 grad: 0.1229 (0.1236) loss: 0.8277 (0.8367) time: 0.1728 data: 0.0982 max mem: 8452 +Train: [68] [2000/6250] eta: 0:12:05 lr: 0.000031 grad: 0.1198 (0.1237) loss: 0.8294 (0.8363) time: 0.1664 data: 0.0925 max mem: 8452 +Train: [68] [2100/6250] eta: 0:11:44 lr: 0.000031 grad: 0.1203 (0.1236) loss: 0.8275 (0.8360) time: 0.1421 data: 0.0646 max mem: 8452 +Train: [68] [2200/6250] eta: 0:11:25 lr: 0.000031 grad: 0.1192 (0.1235) loss: 0.8328 (0.8356) time: 0.1506 data: 0.0587 max mem: 8452 +Train: [68] [2300/6250] eta: 0:11:06 lr: 0.000031 grad: 0.1201 (0.1235) loss: 0.8269 (0.8354) time: 0.1597 data: 0.0574 max mem: 8452 +Train: [68] [2400/6250] eta: 0:10:47 lr: 0.000031 grad: 0.1207 (0.1235) loss: 0.8245 (0.8351) time: 0.1595 data: 0.0782 max mem: 8452 +Train: [68] [2500/6250] eta: 0:10:26 lr: 0.000031 grad: 0.1171 (0.1235) loss: 0.8229 (0.8349) time: 0.1515 data: 0.0593 max mem: 8452 +Train: [68] [2600/6250] eta: 0:10:08 lr: 0.000031 grad: 0.1256 (0.1235) loss: 0.8321 (0.8346) time: 0.1371 data: 0.0598 max mem: 8452 +Train: [68] [2700/6250] eta: 0:09:50 lr: 0.000031 grad: 0.1241 (0.1235) loss: 0.8255 (0.8344) time: 0.1483 data: 0.0715 max mem: 8452 +Train: [68] [2800/6250] eta: 0:09:34 lr: 0.000031 grad: 0.1257 (0.1235) loss: 0.8135 (0.8341) time: 0.1782 data: 0.1035 max mem: 8452 +Train: [68] [2900/6250] eta: 0:09:17 lr: 0.000031 grad: 0.1240 (0.1235) loss: 0.8257 (0.8339) time: 0.1471 data: 0.0756 max mem: 8452 +Train: [68] [3000/6250] eta: 0:09:00 lr: 0.000031 grad: 0.1152 (0.1235) loss: 0.8292 (0.8337) time: 0.1839 data: 0.1033 max mem: 8452 +Train: [68] [3100/6250] eta: 0:08:43 lr: 0.000031 grad: 0.1264 (0.1236) loss: 0.8296 (0.8336) time: 0.1969 data: 0.1203 max mem: 8452 +Train: [68] [3200/6250] eta: 0:08:25 lr: 0.000031 grad: 0.1241 (0.1236) loss: 0.8307 (0.8335) time: 0.1601 data: 0.0781 max mem: 8452 +Train: [68] [3300/6250] eta: 0:08:08 lr: 0.000031 grad: 0.1277 (0.1236) loss: 0.8297 (0.8335) time: 0.1527 data: 0.0711 max mem: 8452 +Train: [68] [3400/6250] eta: 0:07:50 lr: 0.000031 grad: 0.1145 (0.1236) loss: 0.8328 (0.8336) time: 0.1410 data: 0.0686 max mem: 8452 +Train: [68] [3500/6250] eta: 0:07:32 lr: 0.000031 grad: 0.1192 (0.1235) loss: 0.8386 (0.8336) time: 0.1388 data: 0.0550 max mem: 8452 +Train: [68] [3600/6250] eta: 0:07:14 lr: 0.000031 grad: 0.1305 (0.1235) loss: 0.8443 (0.8336) time: 0.1589 data: 0.0716 max mem: 8452 +Train: [68] [3700/6250] eta: 0:06:56 lr: 0.000031 grad: 0.1274 (0.1234) loss: 0.8391 (0.8336) time: 0.1447 data: 0.0558 max mem: 8452 +Train: [68] [3800/6250] eta: 0:06:38 lr: 0.000031 grad: 0.1205 (0.1235) loss: 0.8384 (0.8337) time: 0.1405 data: 0.0473 max mem: 8452 +Train: [68] [3900/6250] eta: 0:06:21 lr: 0.000031 grad: 0.1227 (0.1235) loss: 0.8385 (0.8337) time: 0.1671 data: 0.0969 max mem: 8452 +Train: [68] [4000/6250] eta: 0:06:05 lr: 0.000031 grad: 0.1161 (0.1234) loss: 0.8349 (0.8338) time: 0.1536 data: 0.0751 max mem: 8452 +Train: [68] [4100/6250] eta: 0:05:49 lr: 0.000031 grad: 0.1191 (0.1234) loss: 0.8325 (0.8338) time: 0.1503 data: 0.0719 max mem: 8452 +Train: [68] [4200/6250] eta: 0:05:33 lr: 0.000031 grad: 0.1230 (0.1234) loss: 0.8406 (0.8338) time: 0.1274 data: 0.0325 max mem: 8452 +Train: [68] [4300/6250] eta: 0:05:17 lr: 0.000031 grad: 0.1130 (0.1233) loss: 0.8395 (0.8339) time: 0.1732 data: 0.0940 max mem: 8452 +Train: [68] [4400/6250] eta: 0:05:00 lr: 0.000031 grad: 0.1194 (0.1232) loss: 0.8309 (0.8340) time: 0.1521 data: 0.0713 max mem: 8452 +Train: [68] [4500/6250] eta: 0:04:43 lr: 0.000031 grad: 0.1155 (0.1232) loss: 0.8413 (0.8340) time: 0.1650 data: 0.0802 max mem: 8452 +Train: [68] [4600/6250] eta: 0:04:27 lr: 0.000031 grad: 0.1224 (0.1231) loss: 0.8329 (0.8341) time: 0.1693 data: 0.0949 max mem: 8452 +Train: [68] [4700/6250] eta: 0:04:10 lr: 0.000031 grad: 0.1208 (0.1231) loss: 0.8378 (0.8341) time: 0.1095 data: 0.0242 max mem: 8452 +Train: [68] [4800/6250] eta: 0:03:54 lr: 0.000030 grad: 0.1220 (0.1232) loss: 0.8373 (0.8341) time: 0.1528 data: 0.0653 max mem: 8452 +Train: [68] [4900/6250] eta: 0:03:37 lr: 0.000030 grad: 0.1210 (0.1232) loss: 0.8369 (0.8341) time: 0.1530 data: 0.0677 max mem: 8452 +Train: [68] [5000/6250] eta: 0:03:21 lr: 0.000030 grad: 0.1196 (0.1232) loss: 0.8367 (0.8341) time: 0.1796 data: 0.1027 max mem: 8452 +Train: [68] [5100/6250] eta: 0:03:05 lr: 0.000030 grad: 0.1251 (0.1233) loss: 0.8302 (0.8340) time: 0.1468 data: 0.0757 max mem: 8452 +Train: [68] [5200/6250] eta: 0:02:49 lr: 0.000030 grad: 0.1161 (0.1233) loss: 0.8358 (0.8341) time: 0.1850 data: 0.1130 max mem: 8452 +Train: [68] [5300/6250] eta: 0:02:32 lr: 0.000030 grad: 0.1127 (0.1232) loss: 0.8374 (0.8341) time: 0.1722 data: 0.0920 max mem: 8452 +Train: [68] [5400/6250] eta: 0:02:16 lr: 0.000030 grad: 0.1202 (0.1232) loss: 0.8326 (0.8342) time: 0.1316 data: 0.0542 max mem: 8452 +Train: [68] [5500/6250] eta: 0:02:00 lr: 0.000030 grad: 0.1209 (0.1233) loss: 0.8422 (0.8342) time: 0.1695 data: 0.0448 max mem: 8452 +Train: [68] [5600/6250] eta: 0:01:44 lr: 0.000030 grad: 0.1126 (0.1232) loss: 0.8360 (0.8343) time: 0.1743 data: 0.0881 max mem: 8452 +Train: [68] [5700/6250] eta: 0:01:28 lr: 0.000030 grad: 0.1214 (0.1232) loss: 0.8306 (0.8342) time: 0.1754 data: 0.0985 max mem: 8452 +Train: [68] [5800/6250] eta: 0:01:12 lr: 0.000030 grad: 0.1291 (0.1232) loss: 0.8267 (0.8342) time: 0.1386 data: 0.0542 max mem: 8452 +Train: [68] [5900/6250] eta: 0:00:56 lr: 0.000030 grad: 0.1194 (0.1232) loss: 0.8385 (0.8342) time: 0.1760 data: 0.0887 max mem: 8452 +Train: [68] [6000/6250] eta: 0:00:40 lr: 0.000030 grad: 0.1195 (0.1232) loss: 0.8441 (0.8342) time: 0.1411 data: 0.0578 max mem: 8452 +Train: [68] [6100/6250] eta: 0:00:24 lr: 0.000030 grad: 0.1196 (0.1233) loss: 0.8286 (0.8342) time: 0.1187 data: 0.0398 max mem: 8452 +Train: [68] [6200/6250] eta: 0:00:08 lr: 0.000030 grad: 0.1233 (0.1233) loss: 0.8316 (0.8342) time: 0.2388 data: 0.1390 max mem: 8452 +Train: [68] [6249/6250] eta: 0:00:00 lr: 0.000030 grad: 0.1211 (0.1233) loss: 0.8352 (0.8342) time: 0.1167 data: 0.0003 max mem: 8452 +Train: [68] Total time: 0:16:59 (0.1631 s / it) +Averaged stats: lr: 0.000030 grad: 0.1211 (0.1233) loss: 0.8352 (0.8342) +Eval (hcp-train-subset): [68] [ 0/62] eta: 0:05:56 loss: 0.8631 (0.8631) time: 5.7450 data: 5.7191 max mem: 8452 +Eval (hcp-train-subset): [68] [61/62] eta: 0:00:00 loss: 0.8565 (0.8580) time: 0.1084 data: 0.0876 max mem: 8452 +Eval (hcp-train-subset): [68] Total time: 0:00:14 (0.2369 s / it) +Averaged stats (hcp-train-subset): loss: 0.8565 (0.8580) +Eval (hcp-val): [68] [ 0/62] eta: 0:06:27 loss: 0.8666 (0.8666) time: 6.2463 data: 6.2186 max mem: 8452 +Eval (hcp-val): [68] [61/62] eta: 0:00:00 loss: 0.8707 (0.8715) time: 0.1322 data: 0.1111 max mem: 8452 +Eval (hcp-val): [68] Total time: 0:00:15 (0.2421 s / it) +Averaged stats (hcp-val): loss: 0.8707 (0.8715) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [69] [ 0/6250] eta: 8:36:42 lr: 0.000030 grad: 0.0836 (0.0836) loss: 0.8980 (0.8980) time: 4.9604 data: 4.7880 max mem: 8452 +Train: [69] [ 100/6250] eta: 0:22:58 lr: 0.000030 grad: 0.1602 (0.1731) loss: 0.8447 (0.8609) time: 0.1464 data: 0.0398 max mem: 8452 +Train: [69] [ 200/6250] eta: 0:20:08 lr: 0.000030 grad: 0.1477 (0.1664) loss: 0.8318 (0.8470) time: 0.1839 data: 0.0705 max mem: 8452 +Train: [69] [ 300/6250] eta: 0:18:43 lr: 0.000030 grad: 0.1302 (0.1621) loss: 0.8340 (0.8408) time: 0.1680 data: 0.0768 max mem: 8452 +Train: [69] [ 400/6250] eta: 0:17:42 lr: 0.000030 grad: 0.1337 (0.1555) loss: 0.8305 (0.8388) time: 0.1456 data: 0.0488 max mem: 8452 +Train: [69] [ 500/6250] eta: 0:17:20 lr: 0.000030 grad: 0.1273 (0.1509) loss: 0.8270 (0.8372) time: 0.1440 data: 0.0004 max mem: 8452 +Train: [69] [ 600/6250] eta: 0:16:33 lr: 0.000030 grad: 0.1305 (0.1479) loss: 0.8273 (0.8355) time: 0.1431 data: 0.0610 max mem: 8452 +Train: [69] [ 700/6250] eta: 0:16:07 lr: 0.000030 grad: 0.1360 (0.1454) loss: 0.8365 (0.8346) time: 0.1662 data: 0.0785 max mem: 8452 +Train: [69] [ 800/6250] eta: 0:16:05 lr: 0.000030 grad: 0.1236 (0.1431) loss: 0.8365 (0.8340) time: 0.2160 data: 0.1324 max mem: 8452 +Train: [69] [ 900/6250] eta: 0:15:47 lr: 0.000030 grad: 0.1165 (0.1410) loss: 0.8417 (0.8336) time: 0.1364 data: 0.0494 max mem: 8452 +Train: [69] [1000/6250] eta: 0:15:30 lr: 0.000030 grad: 0.1148 (0.1391) loss: 0.8390 (0.8338) time: 0.1919 data: 0.1112 max mem: 8452 +Train: [69] [1100/6250] eta: 0:15:03 lr: 0.000030 grad: 0.1205 (0.1375) loss: 0.8372 (0.8333) time: 0.1461 data: 0.0625 max mem: 8452 +Train: [69] [1200/6250] eta: 0:14:44 lr: 0.000030 grad: 0.1186 (0.1362) loss: 0.8409 (0.8332) time: 0.1812 data: 0.1056 max mem: 8452 +Train: [69] [1300/6250] eta: 0:14:17 lr: 0.000030 grad: 0.1208 (0.1351) loss: 0.8292 (0.8330) time: 0.1381 data: 0.0603 max mem: 8452 +Train: [69] [1400/6250] eta: 0:13:59 lr: 0.000030 grad: 0.1175 (0.1345) loss: 0.8361 (0.8327) time: 0.1851 data: 0.1006 max mem: 8452 +Train: [69] [1500/6250] eta: 0:13:41 lr: 0.000030 grad: 0.1262 (0.1338) loss: 0.8261 (0.8325) time: 0.1785 data: 0.1077 max mem: 8452 +Train: [69] [1600/6250] eta: 0:13:28 lr: 0.000030 grad: 0.1148 (0.1330) loss: 0.8310 (0.8324) time: 0.1815 data: 0.1106 max mem: 8452 +Train: [69] [1700/6250] eta: 0:13:12 lr: 0.000030 grad: 0.1233 (0.1325) loss: 0.8292 (0.8321) time: 0.1619 data: 0.0910 max mem: 8452 +Train: [69] [1800/6250] eta: 0:12:58 lr: 0.000030 grad: 0.1234 (0.1320) loss: 0.8294 (0.8319) time: 0.1796 data: 0.0827 max mem: 8452 +Train: [69] [1900/6250] eta: 0:12:43 lr: 0.000030 grad: 0.1202 (0.1316) loss: 0.8325 (0.8317) time: 0.1704 data: 0.0848 max mem: 8452 +Train: [69] [2000/6250] eta: 0:12:25 lr: 0.000030 grad: 0.1187 (0.1312) loss: 0.8281 (0.8316) time: 0.1703 data: 0.0851 max mem: 8452 +Train: [69] [2100/6250] eta: 0:12:15 lr: 0.000029 grad: 0.1231 (0.1309) loss: 0.8234 (0.8315) time: 0.1403 data: 0.0458 max mem: 8452 +Train: [69] [2200/6250] eta: 0:11:56 lr: 0.000029 grad: 0.1193 (0.1305) loss: 0.8250 (0.8314) time: 0.1979 data: 0.1234 max mem: 8452 +Train: [69] [2300/6250] eta: 0:11:41 lr: 0.000029 grad: 0.1228 (0.1302) loss: 0.8299 (0.8312) time: 0.2499 data: 0.1527 max mem: 8452 +Train: [69] [2400/6250] eta: 0:11:22 lr: 0.000029 grad: 0.1218 (0.1300) loss: 0.8279 (0.8311) time: 0.1701 data: 0.0933 max mem: 8452 +Train: [69] [2500/6250] eta: 0:11:06 lr: 0.000029 grad: 0.1226 (0.1297) loss: 0.8262 (0.8309) time: 0.1981 data: 0.1094 max mem: 8452 +Train: [69] [2600/6250] eta: 0:10:48 lr: 0.000029 grad: 0.1181 (0.1296) loss: 0.8297 (0.8307) time: 0.2077 data: 0.1046 max mem: 8452 +Train: [69] [2700/6250] eta: 0:10:34 lr: 0.000029 grad: 0.1198 (0.1294) loss: 0.8284 (0.8307) time: 0.3383 data: 0.2651 max mem: 8452 +Train: [69] [2800/6250] eta: 0:10:13 lr: 0.000029 grad: 0.1183 (0.1292) loss: 0.8334 (0.8307) time: 0.1686 data: 0.0786 max mem: 8452 +Train: [69] [2900/6250] eta: 0:09:54 lr: 0.000029 grad: 0.1232 (0.1291) loss: 0.8274 (0.8306) time: 0.1650 data: 0.0920 max mem: 8452 +Train: [69] [3000/6250] eta: 0:09:34 lr: 0.000029 grad: 0.1174 (0.1289) loss: 0.8356 (0.8306) time: 0.1870 data: 0.1053 max mem: 8452 +Train: [69] [3100/6250] eta: 0:09:16 lr: 0.000029 grad: 0.1219 (0.1288) loss: 0.8327 (0.8306) time: 0.1759 data: 0.0870 max mem: 8452 +Train: [69] [3200/6250] eta: 0:08:57 lr: 0.000029 grad: 0.1180 (0.1287) loss: 0.8304 (0.8306) time: 0.1395 data: 0.0554 max mem: 8452 +Train: [69] [3300/6250] eta: 0:08:39 lr: 0.000029 grad: 0.1235 (0.1286) loss: 0.8305 (0.8306) time: 0.1646 data: 0.0967 max mem: 8452 +Train: [69] [3400/6250] eta: 0:08:21 lr: 0.000029 grad: 0.1225 (0.1285) loss: 0.8214 (0.8306) time: 0.1616 data: 0.0794 max mem: 8452 +Train: [69] [3500/6250] eta: 0:08:02 lr: 0.000029 grad: 0.1235 (0.1285) loss: 0.8293 (0.8306) time: 0.1676 data: 0.0880 max mem: 8452 +Train: [69] [3600/6250] eta: 0:07:44 lr: 0.000029 grad: 0.1223 (0.1284) loss: 0.8287 (0.8305) time: 0.1669 data: 0.0871 max mem: 8452 +Train: [69] [3700/6250] eta: 0:07:28 lr: 0.000029 grad: 0.1268 (0.1284) loss: 0.8287 (0.8305) time: 0.1188 data: 0.0246 max mem: 8452 +Train: [69] [3800/6250] eta: 0:07:10 lr: 0.000029 grad: 0.1299 (0.1283) loss: 0.8184 (0.8305) time: 0.2428 data: 0.1810 max mem: 8452 +Train: [69] [3900/6250] eta: 0:06:52 lr: 0.000029 grad: 0.1261 (0.1283) loss: 0.8258 (0.8304) time: 0.1480 data: 0.0737 max mem: 8452 +Train: [69] [4000/6250] eta: 0:06:35 lr: 0.000029 grad: 0.1246 (0.1282) loss: 0.8247 (0.8303) time: 0.1774 data: 0.0576 max mem: 8452 +Train: [69] [4100/6250] eta: 0:06:16 lr: 0.000029 grad: 0.1165 (0.1281) loss: 0.8321 (0.8303) time: 0.1758 data: 0.1033 max mem: 8452 +Train: [69] [4200/6250] eta: 0:05:59 lr: 0.000029 grad: 0.1259 (0.1280) loss: 0.8293 (0.8303) time: 0.1603 data: 0.0709 max mem: 8452 +Train: [69] [4300/6250] eta: 0:05:41 lr: 0.000029 grad: 0.1265 (0.1280) loss: 0.8257 (0.8304) time: 0.1796 data: 0.0967 max mem: 8452 +Train: [69] [4400/6250] eta: 0:05:23 lr: 0.000029 grad: 0.1214 (0.1279) loss: 0.8343 (0.8305) time: 0.1687 data: 0.0872 max mem: 8452 +Train: [69] [4500/6250] eta: 0:05:05 lr: 0.000029 grad: 0.1227 (0.1278) loss: 0.8383 (0.8305) time: 0.1545 data: 0.0659 max mem: 8452 +Train: [69] [4600/6250] eta: 0:04:47 lr: 0.000029 grad: 0.1164 (0.1278) loss: 0.8333 (0.8306) time: 0.1587 data: 0.0636 max mem: 8452 +Train: [69] [4700/6250] eta: 0:04:29 lr: 0.000029 grad: 0.1153 (0.1276) loss: 0.8400 (0.8307) time: 0.1795 data: 0.0947 max mem: 8452 +Train: [69] [4800/6250] eta: 0:04:11 lr: 0.000029 grad: 0.1254 (0.1275) loss: 0.8298 (0.8307) time: 0.1518 data: 0.0585 max mem: 8452 +Train: [69] [4900/6250] eta: 0:03:53 lr: 0.000029 grad: 0.1197 (0.1274) loss: 0.8332 (0.8308) time: 0.1504 data: 0.0652 max mem: 8452 +Train: [69] [5000/6250] eta: 0:03:36 lr: 0.000029 grad: 0.1159 (0.1274) loss: 0.8352 (0.8307) time: 0.1556 data: 0.0820 max mem: 8452 +Train: [69] [5100/6250] eta: 0:03:18 lr: 0.000029 grad: 0.1203 (0.1273) loss: 0.8396 (0.8308) time: 0.1534 data: 0.0784 max mem: 8452 +Train: [69] [5200/6250] eta: 0:03:01 lr: 0.000029 grad: 0.1223 (0.1272) loss: 0.8225 (0.8309) time: 0.1421 data: 0.0580 max mem: 8452 +Train: [69] [5300/6250] eta: 0:02:43 lr: 0.000029 grad: 0.1270 (0.1272) loss: 0.8314 (0.8309) time: 0.1731 data: 0.0797 max mem: 8452 +Train: [69] [5400/6250] eta: 0:02:26 lr: 0.000029 grad: 0.1207 (0.1272) loss: 0.8313 (0.8310) time: 0.1522 data: 0.0671 max mem: 8452 +Train: [69] [5500/6250] eta: 0:02:08 lr: 0.000029 grad: 0.1343 (0.1271) loss: 0.8317 (0.8310) time: 0.1349 data: 0.0473 max mem: 8452 +Train: [69] [5600/6250] eta: 0:01:51 lr: 0.000028 grad: 0.1196 (0.1271) loss: 0.8307 (0.8311) time: 0.1972 data: 0.0841 max mem: 8452 +Train: [69] [5700/6250] eta: 0:01:34 lr: 0.000028 grad: 0.1253 (0.1271) loss: 0.8278 (0.8311) time: 0.1436 data: 0.0573 max mem: 8452 +Train: [69] [5800/6250] eta: 0:01:17 lr: 0.000028 grad: 0.1278 (0.1270) loss: 0.8152 (0.8310) time: 0.2626 data: 0.1564 max mem: 8452 +Train: [69] [5900/6250] eta: 0:01:00 lr: 0.000028 grad: 0.1262 (0.1270) loss: 0.8242 (0.8310) time: 0.1561 data: 0.0799 max mem: 8452 +Train: [69] [6000/6250] eta: 0:00:42 lr: 0.000028 grad: 0.1186 (0.1270) loss: 0.8262 (0.8309) time: 0.1751 data: 0.0942 max mem: 8452 +Train: [69] [6100/6250] eta: 0:00:25 lr: 0.000028 grad: 0.1143 (0.1269) loss: 0.8276 (0.8309) time: 0.1927 data: 0.1114 max mem: 8452 +Train: [69] [6200/6250] eta: 0:00:08 lr: 0.000028 grad: 0.1182 (0.1268) loss: 0.8357 (0.8309) time: 0.1731 data: 0.1020 max mem: 8452 +Train: [69] [6249/6250] eta: 0:00:00 lr: 0.000028 grad: 0.1120 (0.1268) loss: 0.8230 (0.8309) time: 0.1835 data: 0.1013 max mem: 8452 +Train: [69] Total time: 0:17:55 (0.1721 s / it) +Averaged stats: lr: 0.000028 grad: 0.1120 (0.1268) loss: 0.8230 (0.8309) +Eval (hcp-train-subset): [69] [ 0/62] eta: 0:06:27 loss: 0.8708 (0.8708) time: 6.2564 data: 6.2291 max mem: 8452 +Eval (hcp-train-subset): [69] [61/62] eta: 0:00:00 loss: 0.8597 (0.8596) time: 0.1491 data: 0.1267 max mem: 8452 +Eval (hcp-train-subset): [69] Total time: 0:00:14 (0.2393 s / it) +Averaged stats (hcp-train-subset): loss: 0.8597 (0.8596) +Making plots (hcp-train-subset): example=47 +Eval (hcp-val): [69] [ 0/62] eta: 0:05:53 loss: 0.8670 (0.8670) time: 5.6960 data: 5.6659 max mem: 8452 +Eval (hcp-val): [69] [61/62] eta: 0:00:00 loss: 0.8703 (0.8707) time: 0.1318 data: 0.1087 max mem: 8452 +Eval (hcp-val): [69] Total time: 0:00:15 (0.2491 s / it) +Averaged stats (hcp-val): loss: 0.8703 (0.8707) +Making plots (hcp-val): example=54 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [70] [ 0/6250] eta: 11:24:20 lr: 0.000028 grad: 0.1701 (0.1701) loss: 0.8745 (0.8745) time: 6.5697 data: 6.4402 max mem: 8452 +Train: [70] [ 100/6250] eta: 0:23:42 lr: 0.000028 grad: 0.1220 (0.1545) loss: 0.8486 (0.8581) time: 0.1524 data: 0.0577 max mem: 8452 +Train: [70] [ 200/6250] eta: 0:20:17 lr: 0.000028 grad: 0.1283 (0.1463) loss: 0.8473 (0.8523) time: 0.1743 data: 0.0768 max mem: 8452 +Train: [70] [ 300/6250] eta: 0:18:41 lr: 0.000028 grad: 0.1233 (0.1436) loss: 0.8440 (0.8494) time: 0.1711 data: 0.0696 max mem: 8452 +Train: [70] [ 400/6250] eta: 0:18:13 lr: 0.000028 grad: 0.1237 (0.1402) loss: 0.8360 (0.8471) time: 0.2075 data: 0.1153 max mem: 8452 +Train: [70] [ 500/6250] eta: 0:17:41 lr: 0.000028 grad: 0.1234 (0.1383) loss: 0.8319 (0.8451) time: 0.1749 data: 0.0780 max mem: 8452 +Train: [70] [ 600/6250] eta: 0:17:18 lr: 0.000028 grad: 0.1242 (0.1366) loss: 0.8311 (0.8434) time: 0.1952 data: 0.1019 max mem: 8452 +Train: [70] [ 700/6250] eta: 0:16:43 lr: 0.000028 grad: 0.1217 (0.1354) loss: 0.8417 (0.8418) time: 0.1525 data: 0.0494 max mem: 8452 +Train: [70] [ 800/6250] eta: 0:16:28 lr: 0.000028 grad: 0.1213 (0.1347) loss: 0.8364 (0.8410) time: 0.1675 data: 0.0696 max mem: 8452 +Train: [70] [ 900/6250] eta: 0:16:15 lr: 0.000028 grad: 0.1192 (0.1336) loss: 0.8388 (0.8405) time: 0.1897 data: 0.1106 max mem: 8452 +Train: [70] [1000/6250] eta: 0:15:53 lr: 0.000028 grad: 0.1246 (0.1323) loss: 0.8342 (0.8402) time: 0.1862 data: 0.0981 max mem: 8452 +Train: [70] [1100/6250] eta: 0:15:45 lr: 0.000028 grad: 0.1157 (0.1315) loss: 0.8300 (0.8395) time: 0.3044 data: 0.2238 max mem: 8452 +Train: [70] [1200/6250] eta: 0:15:16 lr: 0.000028 grad: 0.1185 (0.1308) loss: 0.8346 (0.8391) time: 0.1480 data: 0.0680 max mem: 8452 +Train: [70] [1300/6250] eta: 0:14:58 lr: 0.000028 grad: 0.1236 (0.1304) loss: 0.8319 (0.8387) time: 0.1991 data: 0.1098 max mem: 8452 +Train: [70] [1400/6250] eta: 0:14:40 lr: 0.000028 grad: 0.1128 (0.1300) loss: 0.8423 (0.8383) time: 0.1841 data: 0.1057 max mem: 8452 +Train: [70] [1500/6250] eta: 0:14:19 lr: 0.000028 grad: 0.1174 (0.1293) loss: 0.8360 (0.8379) time: 0.1734 data: 0.0875 max mem: 8452 +Train: [70] [1600/6250] eta: 0:13:59 lr: 0.000028 grad: 0.1112 (0.1288) loss: 0.8387 (0.8376) time: 0.1832 data: 0.1048 max mem: 8452 +Train: [70] [1700/6250] eta: 0:13:41 lr: 0.000028 grad: 0.1208 (0.1284) loss: 0.8324 (0.8374) time: 0.1781 data: 0.0972 max mem: 8452 +Train: [70] [1800/6250] eta: 0:13:19 lr: 0.000028 grad: 0.1175 (0.1281) loss: 0.8254 (0.8371) time: 0.1262 data: 0.0337 max mem: 8452 +Train: [70] [1900/6250] eta: 0:13:00 lr: 0.000028 grad: 0.1166 (0.1278) loss: 0.8334 (0.8369) time: 0.1771 data: 0.0975 max mem: 8452 +Train: [70] [2000/6250] eta: 0:12:40 lr: 0.000028 grad: 0.1200 (0.1276) loss: 0.8267 (0.8367) time: 0.1677 data: 0.0917 max mem: 8452 +Train: [70] [2100/6250] eta: 0:12:17 lr: 0.000028 grad: 0.1149 (0.1273) loss: 0.8401 (0.8365) time: 0.1574 data: 0.0920 max mem: 8452 +Train: [70] [2200/6250] eta: 0:11:58 lr: 0.000028 grad: 0.1192 (0.1271) loss: 0.8394 (0.8364) time: 0.1706 data: 0.0951 max mem: 8452 +Train: [70] [2300/6250] eta: 0:11:38 lr: 0.000028 grad: 0.1264 (0.1270) loss: 0.8311 (0.8362) time: 0.1632 data: 0.0843 max mem: 8452 +Train: [70] [2400/6250] eta: 0:11:19 lr: 0.000028 grad: 0.1205 (0.1269) loss: 0.8256 (0.8361) time: 0.1671 data: 0.0842 max mem: 8452 +Train: [70] [2500/6250] eta: 0:10:59 lr: 0.000028 grad: 0.1201 (0.1267) loss: 0.8344 (0.8359) time: 0.1300 data: 0.0485 max mem: 8452 +Train: [70] [2600/6250] eta: 0:10:40 lr: 0.000028 grad: 0.1194 (0.1267) loss: 0.8315 (0.8358) time: 0.1848 data: 0.1026 max mem: 8452 +Train: [70] [2700/6250] eta: 0:10:22 lr: 0.000028 grad: 0.1264 (0.1266) loss: 0.8275 (0.8356) time: 0.1676 data: 0.0876 max mem: 8452 +Train: [70] [2800/6250] eta: 0:10:02 lr: 0.000028 grad: 0.1250 (0.1265) loss: 0.8288 (0.8355) time: 0.1408 data: 0.0621 max mem: 8452 +Train: [70] [2900/6250] eta: 0:09:44 lr: 0.000028 grad: 0.1185 (0.1264) loss: 0.8362 (0.8354) time: 0.1515 data: 0.0747 max mem: 8452 +Train: [70] [3000/6250] eta: 0:09:25 lr: 0.000027 grad: 0.1190 (0.1262) loss: 0.8358 (0.8354) time: 0.1824 data: 0.1098 max mem: 8452 +Train: [70] [3100/6250] eta: 0:09:07 lr: 0.000027 grad: 0.1206 (0.1260) loss: 0.8347 (0.8354) time: 0.1394 data: 0.0688 max mem: 8452 +Train: [70] [3200/6250] eta: 0:08:49 lr: 0.000027 grad: 0.1244 (0.1259) loss: 0.8244 (0.8352) time: 0.1505 data: 0.0781 max mem: 8452 +Train: [70] [3300/6250] eta: 0:08:31 lr: 0.000027 grad: 0.1162 (0.1258) loss: 0.8362 (0.8352) time: 0.1543 data: 0.0782 max mem: 8452 +Train: [70] [3400/6250] eta: 0:08:12 lr: 0.000027 grad: 0.1173 (0.1257) loss: 0.8292 (0.8351) time: 0.1467 data: 0.0625 max mem: 8452 +Train: [70] [3500/6250] eta: 0:07:53 lr: 0.000027 grad: 0.1223 (0.1257) loss: 0.8350 (0.8351) time: 0.1749 data: 0.0922 max mem: 8452 +Train: [70] [3600/6250] eta: 0:07:35 lr: 0.000027 grad: 0.1253 (0.1257) loss: 0.8314 (0.8350) time: 0.1505 data: 0.0566 max mem: 8452 +Train: [70] [3700/6250] eta: 0:07:17 lr: 0.000027 grad: 0.1219 (0.1256) loss: 0.8328 (0.8349) time: 0.1594 data: 0.0751 max mem: 8452 +Train: [70] [3800/6250] eta: 0:07:00 lr: 0.000027 grad: 0.1171 (0.1255) loss: 0.8277 (0.8349) time: 0.1459 data: 0.0592 max mem: 8452 +Train: [70] [3900/6250] eta: 0:06:42 lr: 0.000027 grad: 0.1179 (0.1255) loss: 0.8329 (0.8349) time: 0.1782 data: 0.1006 max mem: 8452 +Train: [70] [4000/6250] eta: 0:06:24 lr: 0.000027 grad: 0.1128 (0.1254) loss: 0.8363 (0.8349) time: 0.1465 data: 0.0731 max mem: 8452 +Train: [70] [4100/6250] eta: 0:06:07 lr: 0.000027 grad: 0.1167 (0.1253) loss: 0.8406 (0.8349) time: 0.1758 data: 0.1011 max mem: 8452 +Train: [70] [4200/6250] eta: 0:05:50 lr: 0.000027 grad: 0.1245 (0.1254) loss: 0.8368 (0.8349) time: 0.1741 data: 0.0949 max mem: 8452 +Train: [70] [4300/6250] eta: 0:05:32 lr: 0.000027 grad: 0.1210 (0.1254) loss: 0.8316 (0.8349) time: 0.1710 data: 0.0897 max mem: 8452 +Train: [70] [4400/6250] eta: 0:05:14 lr: 0.000027 grad: 0.1194 (0.1255) loss: 0.8381 (0.8349) time: 0.1471 data: 0.0684 max mem: 8452 +Train: [70] [4500/6250] eta: 0:04:56 lr: 0.000027 grad: 0.1184 (0.1254) loss: 0.8315 (0.8349) time: 0.1438 data: 0.0561 max mem: 8452 +Train: [70] [4600/6250] eta: 0:04:40 lr: 0.000027 grad: 0.1214 (0.1255) loss: 0.8406 (0.8348) time: 0.1358 data: 0.0490 max mem: 8452 +Train: [70] [4700/6250] eta: 0:04:23 lr: 0.000027 grad: 0.1234 (0.1255) loss: 0.8318 (0.8348) time: 0.1956 data: 0.0664 max mem: 8452 +Train: [70] [4800/6250] eta: 0:04:07 lr: 0.000027 grad: 0.1265 (0.1255) loss: 0.8352 (0.8347) time: 0.1841 data: 0.1145 max mem: 8452 +Train: [70] [4900/6250] eta: 0:03:49 lr: 0.000027 grad: 0.1213 (0.1256) loss: 0.8348 (0.8346) time: 0.1149 data: 0.0126 max mem: 8452 +Train: [70] [5000/6250] eta: 0:03:33 lr: 0.000027 grad: 0.1234 (0.1255) loss: 0.8366 (0.8346) time: 0.1481 data: 0.0481 max mem: 8452 +Train: [70] [5100/6250] eta: 0:03:16 lr: 0.000027 grad: 0.1291 (0.1255) loss: 0.8325 (0.8346) time: 0.1642 data: 0.0748 max mem: 8452 +Train: [70] [5200/6250] eta: 0:02:59 lr: 0.000027 grad: 0.1222 (0.1254) loss: 0.8319 (0.8346) time: 0.2252 data: 0.1587 max mem: 8452 +Train: [70] [5300/6250] eta: 0:02:41 lr: 0.000027 grad: 0.1195 (0.1254) loss: 0.8365 (0.8346) time: 0.1727 data: 0.1049 max mem: 8452 +Train: [70] [5400/6250] eta: 0:02:24 lr: 0.000027 grad: 0.1276 (0.1254) loss: 0.8357 (0.8346) time: 0.1378 data: 0.0524 max mem: 8452 +Train: [70] [5500/6250] eta: 0:02:08 lr: 0.000027 grad: 0.1310 (0.1255) loss: 0.8322 (0.8346) time: 0.1769 data: 0.1060 max mem: 8452 +Train: [70] [5600/6250] eta: 0:01:51 lr: 0.000027 grad: 0.1333 (0.1255) loss: 0.8284 (0.8346) time: 0.1282 data: 0.0457 max mem: 8452 +Train: [70] [5700/6250] eta: 0:01:33 lr: 0.000027 grad: 0.1242 (0.1255) loss: 0.8360 (0.8346) time: 0.1922 data: 0.1087 max mem: 8452 +Train: [70] [5800/6250] eta: 0:01:16 lr: 0.000027 grad: 0.1215 (0.1256) loss: 0.8396 (0.8346) time: 0.1590 data: 0.0826 max mem: 8452 +Train: [70] [5900/6250] eta: 0:00:59 lr: 0.000027 grad: 0.1278 (0.1256) loss: 0.8315 (0.8346) time: 0.1507 data: 0.0736 max mem: 8452 +Train: [70] [6000/6250] eta: 0:00:42 lr: 0.000027 grad: 0.1209 (0.1257) loss: 0.8425 (0.8346) time: 0.1702 data: 0.1045 max mem: 8452 +Train: [70] [6100/6250] eta: 0:00:25 lr: 0.000027 grad: 0.1258 (0.1256) loss: 0.8376 (0.8346) time: 0.1571 data: 0.0891 max mem: 8452 +Train: [70] [6200/6250] eta: 0:00:08 lr: 0.000027 grad: 0.1216 (0.1256) loss: 0.8351 (0.8346) time: 0.1091 data: 0.0213 max mem: 8452 +Train: [70] [6249/6250] eta: 0:00:00 lr: 0.000027 grad: 0.1259 (0.1256) loss: 0.8353 (0.8346) time: 0.1642 data: 0.0933 max mem: 8452 +Train: [70] Total time: 0:17:51 (0.1715 s / it) +Averaged stats: lr: 0.000027 grad: 0.1259 (0.1256) loss: 0.8353 (0.8346) +Eval (hcp-train-subset): [70] [ 0/62] eta: 0:05:56 loss: 0.8653 (0.8653) time: 5.7499 data: 5.7049 max mem: 8452 +Eval (hcp-train-subset): [70] [61/62] eta: 0:00:00 loss: 0.8564 (0.8569) time: 0.1314 data: 0.1104 max mem: 8452 +Eval (hcp-train-subset): [70] Total time: 0:00:14 (0.2392 s / it) +Averaged stats (hcp-train-subset): loss: 0.8564 (0.8569) +Eval (hcp-val): [70] [ 0/62] eta: 0:06:37 loss: 0.8665 (0.8665) time: 6.4134 data: 6.3799 max mem: 8452 +Eval (hcp-val): [70] [61/62] eta: 0:00:00 loss: 0.8668 (0.8701) time: 0.1491 data: 0.1268 max mem: 8452 +Eval (hcp-val): [70] Total time: 0:00:15 (0.2448 s / it) +Averaged stats (hcp-val): loss: 0.8668 (0.8701) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [71] [ 0/6250] eta: 10:56:47 lr: 0.000027 grad: 0.1268 (0.1268) loss: 0.8995 (0.8995) time: 6.3051 data: 6.2085 max mem: 8452 +Train: [71] [ 100/6250] eta: 0:23:29 lr: 0.000027 grad: 0.1364 (0.1839) loss: 0.8344 (0.8420) time: 0.1824 data: 0.0850 max mem: 8452 +Train: [71] [ 200/6250] eta: 0:20:43 lr: 0.000027 grad: 0.1342 (0.1653) loss: 0.8453 (0.8424) time: 0.1780 data: 0.0777 max mem: 8452 +Train: [71] [ 300/6250] eta: 0:19:38 lr: 0.000027 grad: 0.1192 (0.1547) loss: 0.8477 (0.8433) time: 0.1901 data: 0.0984 max mem: 8452 +Train: [71] [ 400/6250] eta: 0:18:37 lr: 0.000026 grad: 0.1266 (0.1492) loss: 0.8434 (0.8430) time: 0.1741 data: 0.0789 max mem: 8452 +Train: [71] [ 500/6250] eta: 0:18:06 lr: 0.000026 grad: 0.1285 (0.1447) loss: 0.8388 (0.8420) time: 0.1735 data: 0.0845 max mem: 8452 +Train: [71] [ 600/6250] eta: 0:18:17 lr: 0.000026 grad: 0.1250 (0.1425) loss: 0.8253 (0.8411) time: 0.2702 data: 0.1908 max mem: 8452 +Train: [71] [ 700/6250] eta: 0:17:48 lr: 0.000026 grad: 0.1306 (0.1406) loss: 0.8333 (0.8405) time: 0.1377 data: 0.0627 max mem: 8452 +Train: [71] [ 800/6250] eta: 0:17:10 lr: 0.000026 grad: 0.1156 (0.1389) loss: 0.8414 (0.8402) time: 0.1689 data: 0.0746 max mem: 8452 +Train: [71] [ 900/6250] eta: 0:16:52 lr: 0.000026 grad: 0.1225 (0.1379) loss: 0.8382 (0.8395) time: 0.2152 data: 0.1013 max mem: 8452 +Train: [71] [1000/6250] eta: 0:16:20 lr: 0.000026 grad: 0.1176 (0.1367) loss: 0.8382 (0.8393) time: 0.1841 data: 0.1008 max mem: 8452 +Train: [71] [1100/6250] eta: 0:15:49 lr: 0.000026 grad: 0.1209 (0.1357) loss: 0.8399 (0.8391) time: 0.1686 data: 0.0776 max mem: 8452 +Train: [71] [1200/6250] eta: 0:15:31 lr: 0.000026 grad: 0.1280 (0.1350) loss: 0.8344 (0.8385) time: 0.1877 data: 0.1042 max mem: 8452 +Train: [71] [1300/6250] eta: 0:15:06 lr: 0.000026 grad: 0.1227 (0.1344) loss: 0.8326 (0.8380) time: 0.1676 data: 0.0802 max mem: 8452 +Train: [71] [1400/6250] eta: 0:14:39 lr: 0.000026 grad: 0.1250 (0.1339) loss: 0.8229 (0.8375) time: 0.1631 data: 0.0799 max mem: 8452 +Train: [71] [1500/6250] eta: 0:14:18 lr: 0.000026 grad: 0.1289 (0.1335) loss: 0.8328 (0.8371) time: 0.1741 data: 0.0938 max mem: 8452 +Train: [71] [1600/6250] eta: 0:13:58 lr: 0.000026 grad: 0.1299 (0.1331) loss: 0.8253 (0.8367) time: 0.1807 data: 0.1001 max mem: 8452 +Train: [71] [1700/6250] eta: 0:13:36 lr: 0.000026 grad: 0.1273 (0.1328) loss: 0.8350 (0.8365) time: 0.1626 data: 0.0790 max mem: 8452 +Train: [71] [1800/6250] eta: 0:13:16 lr: 0.000026 grad: 0.1217 (0.1323) loss: 0.8309 (0.8362) time: 0.1612 data: 0.0769 max mem: 8452 +Train: [71] [1900/6250] eta: 0:12:55 lr: 0.000026 grad: 0.1238 (0.1320) loss: 0.8286 (0.8359) time: 0.1680 data: 0.0857 max mem: 8452 +Train: [71] [2000/6250] eta: 0:12:33 lr: 0.000026 grad: 0.1300 (0.1319) loss: 0.8338 (0.8355) time: 0.1663 data: 0.0754 max mem: 8452 +Train: [71] [2100/6250] eta: 0:12:18 lr: 0.000026 grad: 0.1265 (0.1316) loss: 0.8256 (0.8354) time: 0.2488 data: 0.1451 max mem: 8452 +Train: [71] [2200/6250] eta: 0:11:56 lr: 0.000026 grad: 0.1243 (0.1313) loss: 0.8254 (0.8352) time: 0.1716 data: 0.0635 max mem: 8452 +Train: [71] [2300/6250] eta: 0:11:37 lr: 0.000026 grad: 0.1202 (0.1311) loss: 0.8397 (0.8352) time: 0.1941 data: 0.1098 max mem: 8452 +Train: [71] [2400/6250] eta: 0:11:19 lr: 0.000026 grad: 0.1220 (0.1307) loss: 0.8355 (0.8352) time: 0.1078 data: 0.0005 max mem: 8452 +Train: [71] [2500/6250] eta: 0:11:00 lr: 0.000026 grad: 0.1171 (0.1306) loss: 0.8328 (0.8351) time: 0.2007 data: 0.1157 max mem: 8452 +Train: [71] [2600/6250] eta: 0:10:42 lr: 0.000026 grad: 0.1191 (0.1304) loss: 0.8390 (0.8350) time: 0.1252 data: 0.0354 max mem: 8452 +Train: [71] [2700/6250] eta: 0:10:23 lr: 0.000026 grad: 0.1206 (0.1301) loss: 0.8301 (0.8351) time: 0.1683 data: 0.0854 max mem: 8452 +Train: [71] [2800/6250] eta: 0:10:06 lr: 0.000026 grad: 0.1249 (0.1299) loss: 0.8367 (0.8351) time: 0.1703 data: 0.0972 max mem: 8452 +Train: [71] [2900/6250] eta: 0:09:45 lr: 0.000026 grad: 0.1168 (0.1297) loss: 0.8437 (0.8351) time: 0.1349 data: 0.0450 max mem: 8452 +Train: [71] [3000/6250] eta: 0:09:27 lr: 0.000026 grad: 0.1201 (0.1296) loss: 0.8323 (0.8350) time: 0.1602 data: 0.0830 max mem: 8452 +Train: [71] [3100/6250] eta: 0:09:09 lr: 0.000026 grad: 0.1312 (0.1296) loss: 0.8320 (0.8349) time: 0.1440 data: 0.0640 max mem: 8452 +Train: [71] [3200/6250] eta: 0:08:51 lr: 0.000026 grad: 0.1333 (0.1295) loss: 0.8339 (0.8349) time: 0.1783 data: 0.0983 max mem: 8452 +Train: [71] [3300/6250] eta: 0:08:33 lr: 0.000026 grad: 0.1255 (0.1295) loss: 0.8273 (0.8348) time: 0.1627 data: 0.0744 max mem: 8452 +Train: [71] [3400/6250] eta: 0:08:16 lr: 0.000026 grad: 0.1178 (0.1293) loss: 0.8272 (0.8348) time: 0.1832 data: 0.1030 max mem: 8452 +Train: [71] [3500/6250] eta: 0:07:58 lr: 0.000026 grad: 0.1254 (0.1294) loss: 0.8293 (0.8346) time: 0.1581 data: 0.0817 max mem: 8452 +Train: [71] [3600/6250] eta: 0:07:40 lr: 0.000026 grad: 0.1298 (0.1293) loss: 0.8302 (0.8345) time: 0.1609 data: 0.0793 max mem: 8452 +Train: [71] [3700/6250] eta: 0:07:23 lr: 0.000026 grad: 0.1171 (0.1293) loss: 0.8395 (0.8345) time: 0.2409 data: 0.1706 max mem: 8452 +Train: [71] [3800/6250] eta: 0:07:06 lr: 0.000026 grad: 0.1336 (0.1293) loss: 0.8241 (0.8344) time: 0.1663 data: 0.0959 max mem: 8452 +Train: [71] [3900/6250] eta: 0:06:48 lr: 0.000026 grad: 0.1310 (0.1293) loss: 0.8205 (0.8342) time: 0.1505 data: 0.0859 max mem: 8452 +Train: [71] [4000/6250] eta: 0:06:31 lr: 0.000026 grad: 0.1281 (0.1294) loss: 0.8195 (0.8340) time: 0.1799 data: 0.1022 max mem: 8452 +Train: [71] [4100/6250] eta: 0:06:13 lr: 0.000026 grad: 0.1296 (0.1295) loss: 0.8252 (0.8338) time: 0.2381 data: 0.1548 max mem: 8452 +Train: [71] [4200/6250] eta: 0:05:55 lr: 0.000025 grad: 0.1219 (0.1297) loss: 0.8297 (0.8336) time: 0.1712 data: 0.0775 max mem: 8452 +Train: [71] [4300/6250] eta: 0:05:37 lr: 0.000025 grad: 0.1263 (0.1297) loss: 0.8273 (0.8334) time: 0.1455 data: 0.0640 max mem: 8452 +Train: [71] [4400/6250] eta: 0:05:20 lr: 0.000025 grad: 0.1309 (0.1297) loss: 0.8265 (0.8333) time: 0.1618 data: 0.0767 max mem: 8452 +Train: [71] [4500/6250] eta: 0:05:01 lr: 0.000025 grad: 0.1175 (0.1296) loss: 0.8313 (0.8333) time: 0.1728 data: 0.0916 max mem: 8452 +Train: [71] [4600/6250] eta: 0:04:44 lr: 0.000025 grad: 0.1293 (0.1296) loss: 0.8175 (0.8332) time: 0.1697 data: 0.0867 max mem: 8452 +Train: [71] [4700/6250] eta: 0:04:27 lr: 0.000025 grad: 0.1327 (0.1297) loss: 0.8244 (0.8330) time: 0.1910 data: 0.1104 max mem: 8452 +Train: [71] [4800/6250] eta: 0:04:10 lr: 0.000025 grad: 0.1236 (0.1296) loss: 0.8351 (0.8330) time: 0.1645 data: 0.0856 max mem: 8452 +Train: [71] [4900/6250] eta: 0:03:53 lr: 0.000025 grad: 0.1229 (0.1296) loss: 0.8318 (0.8330) time: 0.1325 data: 0.0382 max mem: 8452 +Train: [71] [5000/6250] eta: 0:03:36 lr: 0.000025 grad: 0.1340 (0.1295) loss: 0.8270 (0.8330) time: 0.1699 data: 0.0716 max mem: 8452 +Train: [71] [5100/6250] eta: 0:03:19 lr: 0.000025 grad: 0.1197 (0.1295) loss: 0.8378 (0.8330) time: 0.1055 data: 0.0003 max mem: 8452 +Train: [71] [5200/6250] eta: 0:03:02 lr: 0.000025 grad: 0.1339 (0.1295) loss: 0.8245 (0.8330) time: 0.1544 data: 0.0589 max mem: 8452 +Train: [71] [5300/6250] eta: 0:02:44 lr: 0.000025 grad: 0.1250 (0.1295) loss: 0.8308 (0.8330) time: 0.1429 data: 0.0639 max mem: 8452 +Train: [71] [5400/6250] eta: 0:02:27 lr: 0.000025 grad: 0.1197 (0.1294) loss: 0.8338 (0.8330) time: 0.1398 data: 0.0514 max mem: 8452 +Train: [71] [5500/6250] eta: 0:02:10 lr: 0.000025 grad: 0.1289 (0.1294) loss: 0.8285 (0.8330) time: 0.1967 data: 0.1238 max mem: 8452 +Train: [71] [5600/6250] eta: 0:01:52 lr: 0.000025 grad: 0.1187 (0.1293) loss: 0.8382 (0.8330) time: 0.1658 data: 0.0891 max mem: 8452 +Train: [71] [5700/6250] eta: 0:01:35 lr: 0.000025 grad: 0.1263 (0.1293) loss: 0.8320 (0.8331) time: 0.1579 data: 0.0775 max mem: 8452 +Train: [71] [5800/6250] eta: 0:01:17 lr: 0.000025 grad: 0.1250 (0.1292) loss: 0.8311 (0.8331) time: 0.1495 data: 0.0675 max mem: 8452 +Train: [71] [5900/6250] eta: 0:01:00 lr: 0.000025 grad: 0.1206 (0.1292) loss: 0.8322 (0.8331) time: 0.1601 data: 0.0835 max mem: 8452 +Train: [71] [6000/6250] eta: 0:00:43 lr: 0.000025 grad: 0.1224 (0.1292) loss: 0.8388 (0.8331) time: 0.1524 data: 0.0796 max mem: 8452 +Train: [71] [6100/6250] eta: 0:00:25 lr: 0.000025 grad: 0.1253 (0.1291) loss: 0.8276 (0.8331) time: 0.1562 data: 0.0716 max mem: 8452 +Train: [71] [6200/6250] eta: 0:00:08 lr: 0.000025 grad: 0.1248 (0.1291) loss: 0.8272 (0.8331) time: 0.1598 data: 0.0890 max mem: 8452 +Train: [71] [6249/6250] eta: 0:00:00 lr: 0.000025 grad: 0.1224 (0.1291) loss: 0.8331 (0.8331) time: 0.1748 data: 0.0899 max mem: 8452 +Train: [71] Total time: 0:18:00 (0.1729 s / it) +Averaged stats: lr: 0.000025 grad: 0.1224 (0.1291) loss: 0.8331 (0.8331) +Eval (hcp-train-subset): [71] [ 0/62] eta: 0:05:27 loss: 0.8683 (0.8683) time: 5.2800 data: 5.2486 max mem: 8452 +Eval (hcp-train-subset): [71] [61/62] eta: 0:00:00 loss: 0.8536 (0.8565) time: 0.1414 data: 0.1186 max mem: 8452 +Eval (hcp-train-subset): [71] Total time: 0:00:15 (0.2552 s / it) +Averaged stats (hcp-train-subset): loss: 0.8536 (0.8565) +Eval (hcp-val): [71] [ 0/62] eta: 0:04:40 loss: 0.8666 (0.8666) time: 4.5278 data: 4.4540 max mem: 8452 +Eval (hcp-val): [71] [61/62] eta: 0:00:00 loss: 0.8687 (0.8704) time: 0.1750 data: 0.1538 max mem: 8452 +Eval (hcp-val): [71] Total time: 0:00:16 (0.2627 s / it) +Averaged stats (hcp-val): loss: 0.8687 (0.8704) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [72] [ 0/6250] eta: 10:37:35 lr: 0.000025 grad: 0.0979 (0.0979) loss: 0.8854 (0.8854) time: 6.1209 data: 5.8755 max mem: 8452 +Train: [72] [ 100/6250] eta: 0:26:54 lr: 0.000025 grad: 0.1190 (0.1712) loss: 0.8462 (0.8502) time: 0.1470 data: 0.0200 max mem: 8452 +Train: [72] [ 200/6250] eta: 0:22:32 lr: 0.000025 grad: 0.1265 (0.1587) loss: 0.8505 (0.8445) time: 0.2012 data: 0.0963 max mem: 8452 +Train: [72] [ 300/6250] eta: 0:20:27 lr: 0.000025 grad: 0.1360 (0.1543) loss: 0.8271 (0.8408) time: 0.1717 data: 0.0821 max mem: 8452 +Train: [72] [ 400/6250] eta: 0:19:39 lr: 0.000025 grad: 0.1213 (0.1485) loss: 0.8323 (0.8391) time: 0.1774 data: 0.0820 max mem: 8452 +Train: [72] [ 500/6250] eta: 0:18:37 lr: 0.000025 grad: 0.1309 (0.1457) loss: 0.8295 (0.8377) time: 0.1871 data: 0.0791 max mem: 8452 +Train: [72] [ 600/6250] eta: 0:18:11 lr: 0.000025 grad: 0.1339 (0.1436) loss: 0.8332 (0.8369) time: 0.1665 data: 0.0548 max mem: 8452 +Train: [72] [ 700/6250] eta: 0:17:48 lr: 0.000025 grad: 0.1329 (0.1416) loss: 0.8361 (0.8365) time: 0.1883 data: 0.0915 max mem: 8452 +Train: [72] [ 800/6250] eta: 0:17:24 lr: 0.000025 grad: 0.1244 (0.1402) loss: 0.8375 (0.8363) time: 0.1354 data: 0.0138 max mem: 8452 +Train: [72] [ 900/6250] eta: 0:17:03 lr: 0.000025 grad: 0.1297 (0.1390) loss: 0.8313 (0.8361) time: 0.1151 data: 0.0142 max mem: 8452 +Train: [72] [1000/6250] eta: 0:16:56 lr: 0.000025 grad: 0.1237 (0.1378) loss: 0.8266 (0.8357) time: 0.0881 data: 0.0002 max mem: 8452 +Train: [72] [1100/6250] eta: 0:16:24 lr: 0.000025 grad: 0.1216 (0.1369) loss: 0.8354 (0.8357) time: 0.1625 data: 0.0772 max mem: 8452 +Train: [72] [1200/6250] eta: 0:15:56 lr: 0.000025 grad: 0.1254 (0.1358) loss: 0.8259 (0.8356) time: 0.1573 data: 0.0825 max mem: 8452 +Train: [72] [1300/6250] eta: 0:15:39 lr: 0.000025 grad: 0.1193 (0.1348) loss: 0.8371 (0.8356) time: 0.1872 data: 0.1062 max mem: 8452 +Train: [72] [1400/6250] eta: 0:15:15 lr: 0.000025 grad: 0.1255 (0.1342) loss: 0.8295 (0.8355) time: 0.1445 data: 0.0614 max mem: 8452 +Train: [72] [1500/6250] eta: 0:14:52 lr: 0.000025 grad: 0.1156 (0.1338) loss: 0.8365 (0.8355) time: 0.1965 data: 0.1207 max mem: 8452 +Train: [72] [1600/6250] eta: 0:14:29 lr: 0.000025 grad: 0.1231 (0.1333) loss: 0.8323 (0.8354) time: 0.2116 data: 0.0895 max mem: 8452 +Train: [72] [1700/6250] eta: 0:14:04 lr: 0.000024 grad: 0.1359 (0.1329) loss: 0.8232 (0.8352) time: 0.1567 data: 0.0661 max mem: 8452 +Train: [72] [1800/6250] eta: 0:13:42 lr: 0.000024 grad: 0.1210 (0.1325) loss: 0.8335 (0.8353) time: 0.1188 data: 0.0315 max mem: 8452 +Train: [72] [1900/6250] eta: 0:13:17 lr: 0.000024 grad: 0.1224 (0.1321) loss: 0.8410 (0.8352) time: 0.1741 data: 0.0973 max mem: 8452 +Train: [72] [2000/6250] eta: 0:13:02 lr: 0.000024 grad: 0.1176 (0.1317) loss: 0.8371 (0.8350) time: 0.1816 data: 0.0927 max mem: 8452 +Train: [72] [2100/6250] eta: 0:12:38 lr: 0.000024 grad: 0.1236 (0.1314) loss: 0.8387 (0.8349) time: 0.1586 data: 0.0795 max mem: 8452 +Train: [72] [2200/6250] eta: 0:12:20 lr: 0.000024 grad: 0.1281 (0.1311) loss: 0.8402 (0.8348) time: 0.2350 data: 0.1304 max mem: 8452 +Train: [72] [2300/6250] eta: 0:12:00 lr: 0.000024 grad: 0.1272 (0.1307) loss: 0.8304 (0.8349) time: 0.1960 data: 0.1200 max mem: 8452 +Train: [72] [2400/6250] eta: 0:11:44 lr: 0.000024 grad: 0.1257 (0.1305) loss: 0.8333 (0.8347) time: 0.1301 data: 0.0418 max mem: 8452 +Train: [72] [2500/6250] eta: 0:11:24 lr: 0.000024 grad: 0.1268 (0.1306) loss: 0.8294 (0.8345) time: 0.1519 data: 0.0536 max mem: 8452 +Train: [72] [2600/6250] eta: 0:11:05 lr: 0.000024 grad: 0.1268 (0.1305) loss: 0.8285 (0.8343) time: 0.1399 data: 0.0360 max mem: 8452 +Train: [72] [2700/6250] eta: 0:10:45 lr: 0.000024 grad: 0.1259 (0.1305) loss: 0.8298 (0.8342) time: 0.1818 data: 0.0832 max mem: 8452 +Train: [72] [2800/6250] eta: 0:10:26 lr: 0.000024 grad: 0.1237 (0.1304) loss: 0.8369 (0.8341) time: 0.1780 data: 0.0966 max mem: 8452 +Train: [72] [2900/6250] eta: 0:10:07 lr: 0.000024 grad: 0.1336 (0.1304) loss: 0.8261 (0.8339) time: 0.1755 data: 0.0910 max mem: 8452 +Train: [72] [3000/6250] eta: 0:09:48 lr: 0.000024 grad: 0.1255 (0.1304) loss: 0.8287 (0.8337) time: 0.1835 data: 0.1086 max mem: 8452 +Train: [72] [3100/6250] eta: 0:09:28 lr: 0.000024 grad: 0.1267 (0.1305) loss: 0.8319 (0.8336) time: 0.1423 data: 0.0633 max mem: 8452 +Train: [72] [3200/6250] eta: 0:09:10 lr: 0.000024 grad: 0.1213 (0.1304) loss: 0.8355 (0.8335) time: 0.1695 data: 0.0965 max mem: 8452 +Train: [72] [3300/6250] eta: 0:08:52 lr: 0.000024 grad: 0.1263 (0.1305) loss: 0.8325 (0.8335) time: 0.1709 data: 0.1005 max mem: 8452 +Train: [72] [3400/6250] eta: 0:08:33 lr: 0.000024 grad: 0.1263 (0.1304) loss: 0.8344 (0.8335) time: 0.1282 data: 0.0423 max mem: 8452 +Train: [72] [3500/6250] eta: 0:08:14 lr: 0.000024 grad: 0.1220 (0.1302) loss: 0.8411 (0.8336) time: 0.2092 data: 0.1424 max mem: 8452 +Train: [72] [3600/6250] eta: 0:07:56 lr: 0.000024 grad: 0.1257 (0.1301) loss: 0.8353 (0.8337) time: 0.1309 data: 0.0010 max mem: 8452 +Train: [72] [3700/6250] eta: 0:07:38 lr: 0.000024 grad: 0.1199 (0.1300) loss: 0.8280 (0.8337) time: 0.1473 data: 0.0628 max mem: 8452 +Train: [72] [3800/6250] eta: 0:07:19 lr: 0.000024 grad: 0.1272 (0.1299) loss: 0.8296 (0.8337) time: 0.1488 data: 0.0755 max mem: 8452 +Train: [72] [3900/6250] eta: 0:07:00 lr: 0.000024 grad: 0.1233 (0.1299) loss: 0.8354 (0.8337) time: 0.1532 data: 0.0807 max mem: 8452 +Train: [72] [4000/6250] eta: 0:06:41 lr: 0.000024 grad: 0.1264 (0.1298) loss: 0.8303 (0.8337) time: 0.1640 data: 0.0759 max mem: 8452 +Train: [72] [4100/6250] eta: 0:06:23 lr: 0.000024 grad: 0.1212 (0.1297) loss: 0.8386 (0.8338) time: 0.1662 data: 0.0693 max mem: 8452 +Train: [72] [4200/6250] eta: 0:06:03 lr: 0.000024 grad: 0.1266 (0.1296) loss: 0.8322 (0.8338) time: 0.1530 data: 0.0721 max mem: 8452 +Train: [72] [4300/6250] eta: 0:05:45 lr: 0.000024 grad: 0.1268 (0.1296) loss: 0.8356 (0.8338) time: 0.1559 data: 0.0750 max mem: 8452 +Train: [72] [4400/6250] eta: 0:05:26 lr: 0.000024 grad: 0.1201 (0.1295) loss: 0.8368 (0.8338) time: 0.1591 data: 0.0799 max mem: 8452 +Train: [72] [4500/6250] eta: 0:05:08 lr: 0.000024 grad: 0.1244 (0.1294) loss: 0.8318 (0.8338) time: 0.1603 data: 0.0855 max mem: 8452 +Train: [72] [4600/6250] eta: 0:04:50 lr: 0.000024 grad: 0.1220 (0.1293) loss: 0.8291 (0.8338) time: 0.1460 data: 0.0586 max mem: 8452 +Train: [72] [4700/6250] eta: 0:04:32 lr: 0.000024 grad: 0.1210 (0.1293) loss: 0.8335 (0.8337) time: 0.2019 data: 0.1088 max mem: 8452 +Train: [72] [4800/6250] eta: 0:04:17 lr: 0.000024 grad: 0.1223 (0.1292) loss: 0.8345 (0.8337) time: 0.2589 data: 0.1508 max mem: 8452 +Train: [72] [4900/6250] eta: 0:04:00 lr: 0.000024 grad: 0.1278 (0.1292) loss: 0.8348 (0.8337) time: 0.1591 data: 0.0486 max mem: 8452 +Train: [72] [5000/6250] eta: 0:03:42 lr: 0.000024 grad: 0.1235 (0.1291) loss: 0.8380 (0.8337) time: 0.1450 data: 0.0712 max mem: 8452 +Train: [72] [5100/6250] eta: 0:03:24 lr: 0.000024 grad: 0.1187 (0.1290) loss: 0.8418 (0.8337) time: 0.1755 data: 0.0953 max mem: 8452 +Train: [72] [5200/6250] eta: 0:03:06 lr: 0.000024 grad: 0.1218 (0.1291) loss: 0.8344 (0.8336) time: 0.1641 data: 0.0825 max mem: 8452 +Train: [72] [5300/6250] eta: 0:02:48 lr: 0.000024 grad: 0.1209 (0.1290) loss: 0.8433 (0.8336) time: 0.1324 data: 0.0317 max mem: 8452 +Train: [72] [5400/6250] eta: 0:02:30 lr: 0.000024 grad: 0.1290 (0.1290) loss: 0.8362 (0.8335) time: 0.1789 data: 0.0912 max mem: 8452 +Train: [72] [5500/6250] eta: 0:02:12 lr: 0.000023 grad: 0.1243 (0.1289) loss: 0.8362 (0.8336) time: 0.1746 data: 0.0927 max mem: 8452 +Train: [72] [5600/6250] eta: 0:01:54 lr: 0.000023 grad: 0.1300 (0.1289) loss: 0.8306 (0.8335) time: 0.1638 data: 0.0819 max mem: 8452 +Train: [72] [5700/6250] eta: 0:01:37 lr: 0.000023 grad: 0.1249 (0.1289) loss: 0.8390 (0.8336) time: 0.1653 data: 0.0755 max mem: 8452 +Train: [72] [5800/6250] eta: 0:01:19 lr: 0.000023 grad: 0.1237 (0.1289) loss: 0.8341 (0.8335) time: 0.1567 data: 0.0802 max mem: 8452 +Train: [72] [5900/6250] eta: 0:01:01 lr: 0.000023 grad: 0.1332 (0.1289) loss: 0.8331 (0.8334) time: 0.1051 data: 0.0002 max mem: 8452 +Train: [72] [6000/6250] eta: 0:00:44 lr: 0.000023 grad: 0.1199 (0.1289) loss: 0.8301 (0.8334) time: 0.1818 data: 0.0999 max mem: 8452 +Train: [72] [6100/6250] eta: 0:00:26 lr: 0.000023 grad: 0.1234 (0.1289) loss: 0.8430 (0.8334) time: 0.1400 data: 0.0318 max mem: 8452 +Train: [72] [6200/6250] eta: 0:00:08 lr: 0.000023 grad: 0.1266 (0.1289) loss: 0.8298 (0.8334) time: 0.2154 data: 0.1200 max mem: 8452 +Train: [72] [6249/6250] eta: 0:00:00 lr: 0.000023 grad: 0.1206 (0.1290) loss: 0.8292 (0.8334) time: 0.2886 data: 0.2118 max mem: 8452 +Train: [72] Total time: 0:18:36 (0.1786 s / it) +Averaged stats: lr: 0.000023 grad: 0.1206 (0.1290) loss: 0.8292 (0.8334) +Eval (hcp-train-subset): [72] [ 0/62] eta: 0:06:39 loss: 0.8614 (0.8614) time: 6.4380 data: 6.4109 max mem: 8452 +Eval (hcp-train-subset): [72] [61/62] eta: 0:00:00 loss: 0.8555 (0.8566) time: 0.1390 data: 0.1174 max mem: 8452 +Eval (hcp-train-subset): [72] Total time: 0:00:16 (0.2737 s / it) +Averaged stats (hcp-train-subset): loss: 0.8555 (0.8566) +Eval (hcp-val): [72] [ 0/62] eta: 0:07:39 loss: 0.8657 (0.8657) time: 7.4161 data: 7.3820 max mem: 8452 +Eval (hcp-val): [72] [61/62] eta: 0:00:00 loss: 0.8687 (0.8702) time: 0.1242 data: 0.1020 max mem: 8452 +Eval (hcp-val): [72] Total time: 0:00:16 (0.2709 s / it) +Averaged stats (hcp-val): loss: 0.8687 (0.8702) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [73] [ 0/6250] eta: 10:21:28 lr: 0.000023 grad: 0.0885 (0.0885) loss: 0.8918 (0.8918) time: 5.9662 data: 5.7980 max mem: 8452 +Train: [73] [ 100/6250] eta: 0:24:51 lr: 0.000023 grad: 0.1670 (0.1565) loss: 0.8429 (0.8642) time: 0.1919 data: 0.0854 max mem: 8452 +Train: [73] [ 200/6250] eta: 0:21:23 lr: 0.000023 grad: 0.1346 (0.1522) loss: 0.8404 (0.8520) time: 0.1740 data: 0.0610 max mem: 8452 +Train: [73] [ 300/6250] eta: 0:19:52 lr: 0.000023 grad: 0.1380 (0.1487) loss: 0.8420 (0.8480) time: 0.1563 data: 0.0685 max mem: 8452 +Train: [73] [ 400/6250] eta: 0:18:59 lr: 0.000023 grad: 0.1182 (0.1451) loss: 0.8519 (0.8464) time: 0.1770 data: 0.0875 max mem: 8452 +Train: [73] [ 500/6250] eta: 0:18:13 lr: 0.000023 grad: 0.1208 (0.1419) loss: 0.8455 (0.8462) time: 0.1885 data: 0.0890 max mem: 8452 +Train: [73] [ 600/6250] eta: 0:18:23 lr: 0.000023 grad: 0.1238 (0.1399) loss: 0.8443 (0.8456) time: 0.1876 data: 0.0699 max mem: 8452 +Train: [73] [ 700/6250] eta: 0:17:45 lr: 0.000023 grad: 0.1255 (0.1385) loss: 0.8484 (0.8454) time: 0.1843 data: 0.0891 max mem: 8452 +Train: [73] [ 800/6250] eta: 0:17:27 lr: 0.000023 grad: 0.1218 (0.1370) loss: 0.8426 (0.8450) time: 0.1569 data: 0.0574 max mem: 8452 +Train: [73] [ 900/6250] eta: 0:16:54 lr: 0.000023 grad: 0.1267 (0.1360) loss: 0.8414 (0.8443) time: 0.2038 data: 0.1186 max mem: 8452 +Train: [73] [1000/6250] eta: 0:16:25 lr: 0.000023 grad: 0.1246 (0.1351) loss: 0.8449 (0.8436) time: 0.1485 data: 0.0659 max mem: 8452 +Train: [73] [1100/6250] eta: 0:15:59 lr: 0.000023 grad: 0.1215 (0.1342) loss: 0.8309 (0.8428) time: 0.1571 data: 0.0783 max mem: 8452 +Train: [73] [1200/6250] eta: 0:15:36 lr: 0.000023 grad: 0.1190 (0.1333) loss: 0.8450 (0.8422) time: 0.2004 data: 0.1227 max mem: 8452 +Train: [73] [1300/6250] eta: 0:15:12 lr: 0.000023 grad: 0.1189 (0.1326) loss: 0.8336 (0.8416) time: 0.1647 data: 0.0753 max mem: 8452 +Train: [73] [1400/6250] eta: 0:14:48 lr: 0.000023 grad: 0.1223 (0.1319) loss: 0.8376 (0.8411) time: 0.1612 data: 0.0829 max mem: 8452 +Train: [73] [1500/6250] eta: 0:14:26 lr: 0.000023 grad: 0.1142 (0.1314) loss: 0.8384 (0.8407) time: 0.1931 data: 0.1141 max mem: 8452 +Train: [73] [1600/6250] eta: 0:14:03 lr: 0.000023 grad: 0.1170 (0.1310) loss: 0.8399 (0.8403) time: 0.1535 data: 0.0648 max mem: 8452 +Train: [73] [1700/6250] eta: 0:13:40 lr: 0.000023 grad: 0.1197 (0.1306) loss: 0.8429 (0.8401) time: 0.1743 data: 0.0718 max mem: 8452 +Train: [73] [1800/6250] eta: 0:13:16 lr: 0.000023 grad: 0.1231 (0.1304) loss: 0.8317 (0.8397) time: 0.1476 data: 0.0565 max mem: 8452 +Train: [73] [1900/6250] eta: 0:13:06 lr: 0.000023 grad: 0.1231 (0.1302) loss: 0.8359 (0.8394) time: 0.2037 data: 0.1191 max mem: 8452 +Train: [73] [2000/6250] eta: 0:12:45 lr: 0.000023 grad: 0.1226 (0.1300) loss: 0.8356 (0.8391) time: 0.1868 data: 0.1009 max mem: 8452 +Train: [73] [2100/6250] eta: 0:12:31 lr: 0.000023 grad: 0.1197 (0.1299) loss: 0.8344 (0.8388) time: 0.1246 data: 0.0382 max mem: 8452 +Train: [73] [2200/6250] eta: 0:12:12 lr: 0.000023 grad: 0.1260 (0.1298) loss: 0.8312 (0.8386) time: 0.2340 data: 0.1411 max mem: 8452 +Train: [73] [2300/6250] eta: 0:11:53 lr: 0.000023 grad: 0.1272 (0.1297) loss: 0.8254 (0.8383) time: 0.1681 data: 0.0929 max mem: 8452 +Train: [73] [2400/6250] eta: 0:11:31 lr: 0.000023 grad: 0.1229 (0.1296) loss: 0.8354 (0.8381) time: 0.1403 data: 0.0642 max mem: 8452 +Train: [73] [2500/6250] eta: 0:11:10 lr: 0.000023 grad: 0.1248 (0.1296) loss: 0.8336 (0.8378) time: 0.1780 data: 0.0999 max mem: 8452 +Train: [73] [2600/6250] eta: 0:10:50 lr: 0.000023 grad: 0.1284 (0.1295) loss: 0.8341 (0.8377) time: 0.1579 data: 0.0833 max mem: 8452 +Train: [73] [2700/6250] eta: 0:10:33 lr: 0.000023 grad: 0.1226 (0.1296) loss: 0.8406 (0.8375) time: 0.1881 data: 0.1248 max mem: 8452 +Train: [73] [2800/6250] eta: 0:10:14 lr: 0.000023 grad: 0.1290 (0.1297) loss: 0.8266 (0.8372) time: 0.1417 data: 0.0712 max mem: 8452 +Train: [73] [2900/6250] eta: 0:10:01 lr: 0.000023 grad: 0.1188 (0.1298) loss: 0.8348 (0.8370) time: 0.2291 data: 0.1510 max mem: 8452 +Train: [73] [3000/6250] eta: 0:09:41 lr: 0.000023 grad: 0.1400 (0.1300) loss: 0.8251 (0.8367) time: 0.1352 data: 0.0568 max mem: 8452 +Train: [73] [3100/6250] eta: 0:09:22 lr: 0.000023 grad: 0.1376 (0.1302) loss: 0.8327 (0.8365) time: 0.1567 data: 0.0814 max mem: 8452 +Train: [73] [3200/6250] eta: 0:09:03 lr: 0.000022 grad: 0.1297 (0.1304) loss: 0.8264 (0.8363) time: 0.1724 data: 0.0961 max mem: 8452 +Train: [73] [3300/6250] eta: 0:08:44 lr: 0.000022 grad: 0.1335 (0.1305) loss: 0.8257 (0.8360) time: 0.1562 data: 0.0780 max mem: 8452 +Train: [73] [3400/6250] eta: 0:08:25 lr: 0.000022 grad: 0.1248 (0.1307) loss: 0.8314 (0.8359) time: 0.1501 data: 0.0667 max mem: 8452 +Train: [73] [3500/6250] eta: 0:08:06 lr: 0.000022 grad: 0.1271 (0.1308) loss: 0.8321 (0.8358) time: 0.1599 data: 0.0809 max mem: 8452 +Train: [73] [3600/6250] eta: 0:07:47 lr: 0.000022 grad: 0.1399 (0.1309) loss: 0.8220 (0.8356) time: 0.1557 data: 0.0763 max mem: 8452 +Train: [73] [3700/6250] eta: 0:07:29 lr: 0.000022 grad: 0.1346 (0.1312) loss: 0.8203 (0.8354) time: 0.1586 data: 0.0830 max mem: 8452 +Train: [73] [3800/6250] eta: 0:07:10 lr: 0.000022 grad: 0.1285 (0.1312) loss: 0.8260 (0.8351) time: 0.1514 data: 0.0742 max mem: 8452 +Train: [73] [3900/6250] eta: 0:06:52 lr: 0.000022 grad: 0.1288 (0.1313) loss: 0.8302 (0.8349) time: 0.1624 data: 0.0746 max mem: 8452 +Train: [73] [4000/6250] eta: 0:06:33 lr: 0.000022 grad: 0.1308 (0.1313) loss: 0.8256 (0.8347) time: 0.1825 data: 0.0859 max mem: 8452 +Train: [73] [4100/6250] eta: 0:06:15 lr: 0.000022 grad: 0.1294 (0.1313) loss: 0.8285 (0.8346) time: 0.1644 data: 0.0757 max mem: 8452 +Train: [73] [4200/6250] eta: 0:05:56 lr: 0.000022 grad: 0.1295 (0.1313) loss: 0.8361 (0.8345) time: 0.1515 data: 0.0600 max mem: 8452 +Train: [73] [4300/6250] eta: 0:05:38 lr: 0.000022 grad: 0.1342 (0.1315) loss: 0.8208 (0.8343) time: 0.1465 data: 0.0720 max mem: 8452 +Train: [73] [4400/6250] eta: 0:05:20 lr: 0.000022 grad: 0.1224 (0.1315) loss: 0.8311 (0.8342) time: 0.1546 data: 0.0721 max mem: 8452 +Train: [73] [4500/6250] eta: 0:05:03 lr: 0.000022 grad: 0.1315 (0.1316) loss: 0.8275 (0.8341) time: 0.1413 data: 0.0600 max mem: 8452 +Train: [73] [4600/6250] eta: 0:04:45 lr: 0.000022 grad: 0.1311 (0.1316) loss: 0.8332 (0.8340) time: 0.2004 data: 0.1194 max mem: 8452 +Train: [73] [4700/6250] eta: 0:04:28 lr: 0.000022 grad: 0.1361 (0.1317) loss: 0.8227 (0.8338) time: 0.1032 data: 0.0003 max mem: 8452 +Train: [73] [4800/6250] eta: 0:04:11 lr: 0.000022 grad: 0.1324 (0.1317) loss: 0.8226 (0.8337) time: 0.1443 data: 0.0603 max mem: 8452 +Train: [73] [4900/6250] eta: 0:03:54 lr: 0.000022 grad: 0.1300 (0.1317) loss: 0.8317 (0.8336) time: 0.1878 data: 0.1077 max mem: 8452 +Train: [73] [5000/6250] eta: 0:03:37 lr: 0.000022 grad: 0.1266 (0.1317) loss: 0.8220 (0.8335) time: 0.1801 data: 0.1059 max mem: 8452 +Train: [73] [5100/6250] eta: 0:03:19 lr: 0.000022 grad: 0.1279 (0.1318) loss: 0.8219 (0.8334) time: 0.1700 data: 0.0864 max mem: 8452 +Train: [73] [5200/6250] eta: 0:03:02 lr: 0.000022 grad: 0.1411 (0.1318) loss: 0.8281 (0.8332) time: 0.1693 data: 0.0864 max mem: 8452 +Train: [73] [5300/6250] eta: 0:02:45 lr: 0.000022 grad: 0.1296 (0.1319) loss: 0.8298 (0.8331) time: 0.1201 data: 0.0084 max mem: 8452 +Train: [73] [5400/6250] eta: 0:02:28 lr: 0.000022 grad: 0.1318 (0.1319) loss: 0.8282 (0.8330) time: 0.2835 data: 0.2121 max mem: 8452 +Train: [73] [5500/6250] eta: 0:02:10 lr: 0.000022 grad: 0.1252 (0.1319) loss: 0.8351 (0.8329) time: 0.1931 data: 0.1151 max mem: 8452 +Train: [73] [5600/6250] eta: 0:01:53 lr: 0.000022 grad: 0.1317 (0.1319) loss: 0.8293 (0.8328) time: 0.3868 data: 0.2873 max mem: 8452 +Train: [73] [5700/6250] eta: 0:01:36 lr: 0.000022 grad: 0.1316 (0.1319) loss: 0.8283 (0.8328) time: 0.2022 data: 0.1123 max mem: 8452 +Train: [73] [5800/6250] eta: 0:01:19 lr: 0.000022 grad: 0.1273 (0.1320) loss: 0.8314 (0.8327) time: 0.2486 data: 0.1553 max mem: 8452 +Train: [73] [5900/6250] eta: 0:01:01 lr: 0.000022 grad: 0.1232 (0.1321) loss: 0.8210 (0.8326) time: 0.1830 data: 0.0960 max mem: 8452 +Train: [73] [6000/6250] eta: 0:00:44 lr: 0.000022 grad: 0.1317 (0.1321) loss: 0.8228 (0.8325) time: 0.1654 data: 0.0860 max mem: 8452 +Train: [73] [6100/6250] eta: 0:00:26 lr: 0.000022 grad: 0.1276 (0.1321) loss: 0.8313 (0.8324) time: 0.1465 data: 0.0621 max mem: 8452 +Train: [73] [6200/6250] eta: 0:00:08 lr: 0.000022 grad: 0.1240 (0.1322) loss: 0.8268 (0.8324) time: 0.1542 data: 0.0620 max mem: 8452 +Train: [73] [6249/6250] eta: 0:00:00 lr: 0.000022 grad: 0.1371 (0.1322) loss: 0.8247 (0.8324) time: 0.2025 data: 0.1347 max mem: 8452 +Train: [73] Total time: 0:18:23 (0.1766 s / it) +Averaged stats: lr: 0.000022 grad: 0.1371 (0.1322) loss: 0.8247 (0.8324) +Eval (hcp-train-subset): [73] [ 0/62] eta: 0:06:23 loss: 0.8693 (0.8693) time: 6.1802 data: 6.1532 max mem: 8452 +Eval (hcp-train-subset): [73] [61/62] eta: 0:00:00 loss: 0.8541 (0.8565) time: 0.1480 data: 0.1266 max mem: 8452 +Eval (hcp-train-subset): [73] Total time: 0:00:16 (0.2595 s / it) +Averaged stats (hcp-train-subset): loss: 0.8541 (0.8565) +Eval (hcp-val): [73] [ 0/62] eta: 0:04:20 loss: 0.8625 (0.8625) time: 4.2023 data: 4.1362 max mem: 8452 +Eval (hcp-val): [73] [61/62] eta: 0:00:00 loss: 0.8688 (0.8693) time: 0.1295 data: 0.1084 max mem: 8452 +Eval (hcp-val): [73] Total time: 0:00:15 (0.2570 s / it) +Averaged stats (hcp-val): loss: 0.8688 (0.8693) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [74] [ 0/6250] eta: 12:07:17 lr: 0.000022 grad: 0.2980 (0.2980) loss: 0.8168 (0.8168) time: 6.9820 data: 6.8331 max mem: 8452 +Train: [74] [ 100/6250] eta: 0:24:31 lr: 0.000022 grad: 0.1234 (0.1581) loss: 0.8606 (0.8528) time: 0.1951 data: 0.0849 max mem: 8452 +Train: [74] [ 200/6250] eta: 0:21:08 lr: 0.000022 grad: 0.1233 (0.1457) loss: 0.8445 (0.8508) time: 0.1771 data: 0.0645 max mem: 8452 +Train: [74] [ 300/6250] eta: 0:19:44 lr: 0.000022 grad: 0.1301 (0.1404) loss: 0.8486 (0.8510) time: 0.1893 data: 0.1020 max mem: 8452 +Train: [74] [ 400/6250] eta: 0:18:23 lr: 0.000022 grad: 0.1220 (0.1372) loss: 0.8341 (0.8500) time: 0.1446 data: 0.0403 max mem: 8452 +Train: [74] [ 500/6250] eta: 0:17:27 lr: 0.000022 grad: 0.1262 (0.1348) loss: 0.8390 (0.8488) time: 0.1544 data: 0.0568 max mem: 8452 +Train: [74] [ 600/6250] eta: 0:16:56 lr: 0.000022 grad: 0.1237 (0.1337) loss: 0.8464 (0.8477) time: 0.1783 data: 0.0953 max mem: 8452 +Train: [74] [ 700/6250] eta: 0:16:53 lr: 0.000022 grad: 0.1155 (0.1324) loss: 0.8428 (0.8468) time: 0.2162 data: 0.1194 max mem: 8452 +Train: [74] [ 800/6250] eta: 0:16:33 lr: 0.000022 grad: 0.1175 (0.1311) loss: 0.8478 (0.8463) time: 0.2230 data: 0.1012 max mem: 8452 +Train: [74] [ 900/6250] eta: 0:16:18 lr: 0.000021 grad: 0.1226 (0.1300) loss: 0.8355 (0.8459) time: 0.2048 data: 0.1228 max mem: 8452 +Train: [74] [1000/6250] eta: 0:15:46 lr: 0.000021 grad: 0.1158 (0.1292) loss: 0.8477 (0.8458) time: 0.1296 data: 0.0472 max mem: 8452 +Train: [74] [1100/6250] eta: 0:15:21 lr: 0.000021 grad: 0.1146 (0.1286) loss: 0.8526 (0.8456) time: 0.1537 data: 0.0745 max mem: 8452 +Train: [74] [1200/6250] eta: 0:14:57 lr: 0.000021 grad: 0.1229 (0.1280) loss: 0.8349 (0.8450) time: 0.1760 data: 0.0900 max mem: 8452 +Train: [74] [1300/6250] eta: 0:14:37 lr: 0.000021 grad: 0.1206 (0.1276) loss: 0.8398 (0.8445) time: 0.1748 data: 0.0919 max mem: 8452 +Train: [74] [1400/6250] eta: 0:14:25 lr: 0.000021 grad: 0.1211 (0.1275) loss: 0.8359 (0.8441) time: 0.1949 data: 0.1027 max mem: 8452 +Train: [74] [1500/6250] eta: 0:14:10 lr: 0.000021 grad: 0.1209 (0.1273) loss: 0.8357 (0.8434) time: 0.1757 data: 0.0866 max mem: 8452 +Train: [74] [1600/6250] eta: 0:13:51 lr: 0.000021 grad: 0.1237 (0.1273) loss: 0.8292 (0.8429) time: 0.2092 data: 0.1236 max mem: 8452 +Train: [74] [1700/6250] eta: 0:13:34 lr: 0.000021 grad: 0.1233 (0.1272) loss: 0.8365 (0.8426) time: 0.1778 data: 0.0993 max mem: 8452 +Train: [74] [1800/6250] eta: 0:13:12 lr: 0.000021 grad: 0.1176 (0.1268) loss: 0.8400 (0.8424) time: 0.1827 data: 0.0978 max mem: 8452 +Train: [74] [1900/6250] eta: 0:13:05 lr: 0.000021 grad: 0.1140 (0.1267) loss: 0.8352 (0.8421) time: 0.2603 data: 0.1705 max mem: 8452 +Train: [74] [2000/6250] eta: 0:12:42 lr: 0.000021 grad: 0.1228 (0.1266) loss: 0.8278 (0.8416) time: 0.1783 data: 0.0958 max mem: 8452 +Train: [74] [2100/6250] eta: 0:12:23 lr: 0.000021 grad: 0.1171 (0.1264) loss: 0.8441 (0.8415) time: 0.1890 data: 0.1052 max mem: 8452 +Train: [74] [2200/6250] eta: 0:12:06 lr: 0.000021 grad: 0.1220 (0.1264) loss: 0.8346 (0.8412) time: 0.1143 data: 0.0172 max mem: 8452 +Train: [74] [2300/6250] eta: 0:11:45 lr: 0.000021 grad: 0.1225 (0.1265) loss: 0.8320 (0.8409) time: 0.1545 data: 0.0710 max mem: 8452 +Train: [74] [2400/6250] eta: 0:11:24 lr: 0.000021 grad: 0.1202 (0.1265) loss: 0.8442 (0.8407) time: 0.1662 data: 0.0853 max mem: 8452 +Train: [74] [2500/6250] eta: 0:11:04 lr: 0.000021 grad: 0.1207 (0.1264) loss: 0.8462 (0.8405) time: 0.1742 data: 0.0921 max mem: 8452 +Train: [74] [2600/6250] eta: 0:10:43 lr: 0.000021 grad: 0.1171 (0.1263) loss: 0.8384 (0.8403) time: 0.1553 data: 0.0632 max mem: 8452 +Train: [74] [2700/6250] eta: 0:10:25 lr: 0.000021 grad: 0.1182 (0.1263) loss: 0.8369 (0.8401) time: 0.1704 data: 0.0789 max mem: 8452 +Train: [74] [2800/6250] eta: 0:10:05 lr: 0.000021 grad: 0.1248 (0.1263) loss: 0.8371 (0.8400) time: 0.1594 data: 0.0743 max mem: 8452 +Train: [74] [2900/6250] eta: 0:09:47 lr: 0.000021 grad: 0.1200 (0.1263) loss: 0.8443 (0.8398) time: 0.1691 data: 0.0812 max mem: 8452 +Train: [74] [3000/6250] eta: 0:09:30 lr: 0.000021 grad: 0.1266 (0.1264) loss: 0.8277 (0.8395) time: 0.2566 data: 0.1888 max mem: 8452 +Train: [74] [3100/6250] eta: 0:09:12 lr: 0.000021 grad: 0.1381 (0.1265) loss: 0.8263 (0.8392) time: 0.1605 data: 0.0843 max mem: 8452 +Train: [74] [3200/6250] eta: 0:08:55 lr: 0.000021 grad: 0.1287 (0.1267) loss: 0.8239 (0.8388) time: 0.1595 data: 0.0819 max mem: 8452 +Train: [74] [3300/6250] eta: 0:08:38 lr: 0.000021 grad: 0.1231 (0.1268) loss: 0.8325 (0.8385) time: 0.1747 data: 0.0866 max mem: 8452 +Train: [74] [3400/6250] eta: 0:08:21 lr: 0.000021 grad: 0.1295 (0.1269) loss: 0.8296 (0.8381) time: 0.1939 data: 0.1031 max mem: 8452 +Train: [74] [3500/6250] eta: 0:08:03 lr: 0.000021 grad: 0.1227 (0.1270) loss: 0.8258 (0.8379) time: 0.1719 data: 0.1004 max mem: 8452 +Train: [74] [3600/6250] eta: 0:07:47 lr: 0.000021 grad: 0.1303 (0.1271) loss: 0.8306 (0.8376) time: 0.2530 data: 0.1852 max mem: 8452 +Train: [74] [3700/6250] eta: 0:07:29 lr: 0.000021 grad: 0.1254 (0.1272) loss: 0.8351 (0.8374) time: 0.1633 data: 0.0849 max mem: 8452 +Train: [74] [3800/6250] eta: 0:07:11 lr: 0.000021 grad: 0.1309 (0.1274) loss: 0.8254 (0.8371) time: 0.1681 data: 0.0936 max mem: 8452 +Train: [74] [3900/6250] eta: 0:06:53 lr: 0.000021 grad: 0.1274 (0.1275) loss: 0.8251 (0.8369) time: 0.1766 data: 0.0938 max mem: 8452 +Train: [74] [4000/6250] eta: 0:06:35 lr: 0.000021 grad: 0.1343 (0.1277) loss: 0.8239 (0.8367) time: 0.1931 data: 0.1078 max mem: 8452 +Train: [74] [4100/6250] eta: 0:06:16 lr: 0.000021 grad: 0.1284 (0.1278) loss: 0.8327 (0.8365) time: 0.1672 data: 0.0950 max mem: 8452 +Train: [74] [4200/6250] eta: 0:05:58 lr: 0.000021 grad: 0.1278 (0.1280) loss: 0.8310 (0.8363) time: 0.1732 data: 0.0923 max mem: 8452 +Train: [74] [4300/6250] eta: 0:05:40 lr: 0.000021 grad: 0.1303 (0.1281) loss: 0.8350 (0.8362) time: 0.1499 data: 0.0608 max mem: 8452 +Train: [74] [4400/6250] eta: 0:05:22 lr: 0.000021 grad: 0.1257 (0.1281) loss: 0.8309 (0.8361) time: 0.1809 data: 0.0980 max mem: 8452 +Train: [74] [4500/6250] eta: 0:05:04 lr: 0.000021 grad: 0.1281 (0.1283) loss: 0.8324 (0.8360) time: 0.1201 data: 0.0277 max mem: 8452 +Train: [74] [4600/6250] eta: 0:04:46 lr: 0.000021 grad: 0.1364 (0.1283) loss: 0.8222 (0.8360) time: 0.1340 data: 0.0195 max mem: 8452 +Train: [74] [4700/6250] eta: 0:04:29 lr: 0.000021 grad: 0.1258 (0.1285) loss: 0.8367 (0.8359) time: 0.1533 data: 0.0653 max mem: 8452 +Train: [74] [4800/6250] eta: 0:04:14 lr: 0.000021 grad: 0.1267 (0.1285) loss: 0.8272 (0.8357) time: 0.2623 data: 0.1199 max mem: 8452 +Train: [74] [4900/6250] eta: 0:03:58 lr: 0.000020 grad: 0.1301 (0.1287) loss: 0.8269 (0.8356) time: 0.5063 data: 0.3955 max mem: 8452 +Train: [74] [5000/6250] eta: 0:03:40 lr: 0.000020 grad: 0.1291 (0.1289) loss: 0.8391 (0.8355) time: 0.1471 data: 0.0597 max mem: 8452 +Train: [74] [5100/6250] eta: 0:03:23 lr: 0.000020 grad: 0.1371 (0.1291) loss: 0.8222 (0.8353) time: 0.2900 data: 0.1819 max mem: 8452 +Train: [74] [5200/6250] eta: 0:03:05 lr: 0.000020 grad: 0.1308 (0.1291) loss: 0.8256 (0.8352) time: 0.1551 data: 0.0514 max mem: 8452 +Train: [74] [5300/6250] eta: 0:02:48 lr: 0.000020 grad: 0.1286 (0.1292) loss: 0.8285 (0.8351) time: 0.3733 data: 0.2614 max mem: 8452 +Train: [74] [5400/6250] eta: 0:02:30 lr: 0.000020 grad: 0.1321 (0.1294) loss: 0.8255 (0.8349) time: 0.1509 data: 0.0248 max mem: 8452 +Train: [74] [5500/6250] eta: 0:02:13 lr: 0.000020 grad: 0.1282 (0.1295) loss: 0.8259 (0.8347) time: 0.3623 data: 0.2239 max mem: 8452 +Train: [74] [5600/6250] eta: 0:01:55 lr: 0.000020 grad: 0.1317 (0.1296) loss: 0.8263 (0.8346) time: 0.1737 data: 0.0892 max mem: 8452 +Train: [74] [5700/6250] eta: 0:01:37 lr: 0.000020 grad: 0.1335 (0.1297) loss: 0.8246 (0.8344) time: 0.1529 data: 0.0688 max mem: 8452 +Train: [74] [5800/6250] eta: 0:01:19 lr: 0.000020 grad: 0.1409 (0.1298) loss: 0.8260 (0.8343) time: 0.1671 data: 0.0701 max mem: 8452 +Train: [74] [5900/6250] eta: 0:01:01 lr: 0.000020 grad: 0.1297 (0.1299) loss: 0.8229 (0.8342) time: 0.1711 data: 0.0949 max mem: 8452 +Train: [74] [6000/6250] eta: 0:00:44 lr: 0.000020 grad: 0.1298 (0.1299) loss: 0.8281 (0.8341) time: 0.1634 data: 0.0455 max mem: 8452 +Train: [74] [6100/6250] eta: 0:00:26 lr: 0.000020 grad: 0.1267 (0.1299) loss: 0.8251 (0.8340) time: 0.1864 data: 0.1041 max mem: 8452 +Train: [74] [6200/6250] eta: 0:00:08 lr: 0.000020 grad: 0.1260 (0.1299) loss: 0.8236 (0.8339) time: 0.1425 data: 0.0056 max mem: 8452 +Train: [74] [6249/6250] eta: 0:00:00 lr: 0.000020 grad: 0.1289 (0.1299) loss: 0.8177 (0.8338) time: 0.1499 data: 0.0671 max mem: 8452 +Train: [74] Total time: 0:18:35 (0.1785 s / it) +Averaged stats: lr: 0.000020 grad: 0.1289 (0.1299) loss: 0.8177 (0.8338) +Eval (hcp-train-subset): [74] [ 0/62] eta: 0:04:39 loss: 0.8636 (0.8636) time: 4.5121 data: 4.4258 max mem: 8452 +Eval (hcp-train-subset): [74] [61/62] eta: 0:00:00 loss: 0.8523 (0.8564) time: 0.1522 data: 0.1242 max mem: 8452 +Eval (hcp-train-subset): [74] Total time: 0:00:15 (0.2488 s / it) +Averaged stats (hcp-train-subset): loss: 0.8523 (0.8564) +Making plots (hcp-train-subset): example=30 +Eval (hcp-val): [74] [ 0/62] eta: 0:06:28 loss: 0.8666 (0.8666) time: 6.2711 data: 6.2431 max mem: 8452 +Eval (hcp-val): [74] [61/62] eta: 0:00:00 loss: 0.8688 (0.8703) time: 0.1389 data: 0.1165 max mem: 8452 +Eval (hcp-val): [74] Total time: 0:00:15 (0.2475 s / it) +Averaged stats (hcp-val): loss: 0.8688 (0.8703) +Making plots (hcp-val): example=48 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [75] [ 0/6250] eta: 12:38:51 lr: 0.000020 grad: 0.4034 (0.4034) loss: 0.8487 (0.8487) time: 7.2850 data: 7.1559 max mem: 8452 +Train: [75] [ 100/6250] eta: 0:24:10 lr: 0.000020 grad: 0.1687 (0.1957) loss: 0.8355 (0.8507) time: 0.1814 data: 0.0734 max mem: 8452 +Train: [75] [ 200/6250] eta: 0:20:22 lr: 0.000020 grad: 0.1458 (0.1796) loss: 0.8377 (0.8430) time: 0.1797 data: 0.0870 max mem: 8452 +Train: [75] [ 300/6250] eta: 0:19:15 lr: 0.000020 grad: 0.1327 (0.1708) loss: 0.8468 (0.8394) time: 0.1443 data: 0.0513 max mem: 8452 +Train: [75] [ 400/6250] eta: 0:18:29 lr: 0.000020 grad: 0.1335 (0.1624) loss: 0.8392 (0.8391) time: 0.1918 data: 0.0998 max mem: 8452 +Train: [75] [ 500/6250] eta: 0:17:29 lr: 0.000020 grad: 0.1237 (0.1566) loss: 0.8453 (0.8389) time: 0.1657 data: 0.0742 max mem: 8452 +Train: [75] [ 600/6250] eta: 0:16:46 lr: 0.000020 grad: 0.1302 (0.1524) loss: 0.8406 (0.8394) time: 0.1534 data: 0.0596 max mem: 8452 +Train: [75] [ 700/6250] eta: 0:16:42 lr: 0.000020 grad: 0.1332 (0.1493) loss: 0.8379 (0.8395) time: 0.2959 data: 0.2004 max mem: 8452 +Train: [75] [ 800/6250] eta: 0:16:19 lr: 0.000020 grad: 0.1300 (0.1466) loss: 0.8420 (0.8394) time: 0.2287 data: 0.1392 max mem: 8452 +Train: [75] [ 900/6250] eta: 0:16:01 lr: 0.000020 grad: 0.1274 (0.1446) loss: 0.8345 (0.8393) time: 0.1587 data: 0.0756 max mem: 8452 +Train: [75] [1000/6250] eta: 0:15:38 lr: 0.000020 grad: 0.1266 (0.1432) loss: 0.8408 (0.8390) time: 0.1598 data: 0.0681 max mem: 8452 +Train: [75] [1100/6250] eta: 0:15:16 lr: 0.000020 grad: 0.1326 (0.1422) loss: 0.8373 (0.8387) time: 0.1683 data: 0.0848 max mem: 8452 +Train: [75] [1200/6250] eta: 0:14:57 lr: 0.000020 grad: 0.1317 (0.1415) loss: 0.8318 (0.8382) time: 0.1584 data: 0.0715 max mem: 8452 +Train: [75] [1300/6250] eta: 0:14:37 lr: 0.000020 grad: 0.1262 (0.1407) loss: 0.8304 (0.8376) time: 0.1979 data: 0.1178 max mem: 8452 +Train: [75] [1400/6250] eta: 0:14:13 lr: 0.000020 grad: 0.1233 (0.1402) loss: 0.8394 (0.8373) time: 0.1745 data: 0.0855 max mem: 8452 +Train: [75] [1500/6250] eta: 0:13:49 lr: 0.000020 grad: 0.1330 (0.1396) loss: 0.8282 (0.8369) time: 0.1651 data: 0.0809 max mem: 8452 +Train: [75] [1600/6250] eta: 0:13:37 lr: 0.000020 grad: 0.1218 (0.1389) loss: 0.8387 (0.8367) time: 0.2969 data: 0.2123 max mem: 8452 +Train: [75] [1700/6250] eta: 0:13:16 lr: 0.000020 grad: 0.1366 (0.1386) loss: 0.8216 (0.8363) time: 0.2111 data: 0.1367 max mem: 8452 +Train: [75] [1800/6250] eta: 0:12:54 lr: 0.000020 grad: 0.1269 (0.1383) loss: 0.8304 (0.8360) time: 0.1767 data: 0.1000 max mem: 8452 +Train: [75] [1900/6250] eta: 0:12:40 lr: 0.000020 grad: 0.1259 (0.1380) loss: 0.8277 (0.8357) time: 0.2621 data: 0.1885 max mem: 8452 +Train: [75] [2000/6250] eta: 0:12:18 lr: 0.000020 grad: 0.1381 (0.1379) loss: 0.8248 (0.8354) time: 0.1468 data: 0.0807 max mem: 8452 +Train: [75] [2100/6250] eta: 0:12:01 lr: 0.000020 grad: 0.1274 (0.1377) loss: 0.8339 (0.8351) time: 0.1694 data: 0.0985 max mem: 8452 +Train: [75] [2200/6250] eta: 0:11:41 lr: 0.000020 grad: 0.1215 (0.1374) loss: 0.8277 (0.8350) time: 0.1333 data: 0.0545 max mem: 8452 +Train: [75] [2300/6250] eta: 0:11:22 lr: 0.000020 grad: 0.1298 (0.1373) loss: 0.8293 (0.8348) time: 0.1726 data: 0.0856 max mem: 8452 +Train: [75] [2400/6250] eta: 0:11:05 lr: 0.000020 grad: 0.1312 (0.1371) loss: 0.8266 (0.8346) time: 0.1750 data: 0.0596 max mem: 8452 +Train: [75] [2500/6250] eta: 0:10:51 lr: 0.000020 grad: 0.1290 (0.1371) loss: 0.8294 (0.8343) time: 0.2598 data: 0.1780 max mem: 8452 +Train: [75] [2600/6250] eta: 0:10:44 lr: 0.000020 grad: 0.1296 (0.1370) loss: 0.8286 (0.8341) time: 0.5273 data: 0.4129 max mem: 8452 +Train: [75] [2700/6250] eta: 0:10:22 lr: 0.000020 grad: 0.1355 (0.1369) loss: 0.8263 (0.8338) time: 0.1547 data: 0.0723 max mem: 8452 +Train: [75] [2800/6250] eta: 0:10:10 lr: 0.000019 grad: 0.1306 (0.1368) loss: 0.8315 (0.8337) time: 0.1409 data: 0.0489 max mem: 8452 +Train: [75] [2900/6250] eta: 0:09:50 lr: 0.000019 grad: 0.1267 (0.1367) loss: 0.8335 (0.8336) time: 0.1719 data: 0.0996 max mem: 8452 +Train: [75] [3000/6250] eta: 0:09:30 lr: 0.000019 grad: 0.1295 (0.1366) loss: 0.8286 (0.8335) time: 0.1319 data: 0.0398 max mem: 8452 +Train: [75] [3100/6250] eta: 0:09:14 lr: 0.000019 grad: 0.1309 (0.1365) loss: 0.8336 (0.8333) time: 0.1561 data: 0.0677 max mem: 8452 +Train: [75] [3200/6250] eta: 0:08:56 lr: 0.000019 grad: 0.1331 (0.1366) loss: 0.8306 (0.8330) time: 0.2097 data: 0.1408 max mem: 8452 +Train: [75] [3300/6250] eta: 0:08:37 lr: 0.000019 grad: 0.1265 (0.1365) loss: 0.8321 (0.8330) time: 0.1609 data: 0.0875 max mem: 8452 +Train: [75] [3400/6250] eta: 0:08:21 lr: 0.000019 grad: 0.1343 (0.1364) loss: 0.8227 (0.8328) time: 0.2101 data: 0.1294 max mem: 8452 +Train: [75] [3500/6250] eta: 0:08:02 lr: 0.000019 grad: 0.1271 (0.1363) loss: 0.8271 (0.8327) time: 0.1528 data: 0.0717 max mem: 8452 +Train: [75] [3600/6250] eta: 0:07:45 lr: 0.000019 grad: 0.1302 (0.1362) loss: 0.8200 (0.8325) time: 0.2250 data: 0.1512 max mem: 8452 +Train: [75] [3700/6250] eta: 0:07:27 lr: 0.000019 grad: 0.1272 (0.1361) loss: 0.8320 (0.8323) time: 0.1615 data: 0.0838 max mem: 8452 +Train: [75] [3800/6250] eta: 0:07:09 lr: 0.000019 grad: 0.1276 (0.1360) loss: 0.8299 (0.8322) time: 0.1651 data: 0.0762 max mem: 8452 +Train: [75] [3900/6250] eta: 0:06:50 lr: 0.000019 grad: 0.1315 (0.1360) loss: 0.8266 (0.8321) time: 0.1641 data: 0.0786 max mem: 8452 +Train: [75] [4000/6250] eta: 0:06:32 lr: 0.000019 grad: 0.1290 (0.1360) loss: 0.8288 (0.8320) time: 0.1596 data: 0.0660 max mem: 8452 +Train: [75] [4100/6250] eta: 0:06:14 lr: 0.000019 grad: 0.1283 (0.1360) loss: 0.8263 (0.8319) time: 0.1663 data: 0.0794 max mem: 8452 +Train: [75] [4200/6250] eta: 0:05:56 lr: 0.000019 grad: 0.1328 (0.1360) loss: 0.8313 (0.8318) time: 0.1491 data: 0.0496 max mem: 8452 +Train: [75] [4300/6250] eta: 0:05:37 lr: 0.000019 grad: 0.1242 (0.1360) loss: 0.8279 (0.8318) time: 0.1422 data: 0.0673 max mem: 8452 +Train: [75] [4400/6250] eta: 0:05:19 lr: 0.000019 grad: 0.1324 (0.1360) loss: 0.8245 (0.8316) time: 0.1791 data: 0.1019 max mem: 8452 +Train: [75] [4500/6250] eta: 0:05:01 lr: 0.000019 grad: 0.1285 (0.1360) loss: 0.8288 (0.8315) time: 0.1591 data: 0.0725 max mem: 8452 +Train: [75] [4600/6250] eta: 0:04:44 lr: 0.000019 grad: 0.1344 (0.1360) loss: 0.8263 (0.8314) time: 0.1874 data: 0.1163 max mem: 8452 +Train: [75] [4700/6250] eta: 0:04:27 lr: 0.000019 grad: 0.1315 (0.1359) loss: 0.8298 (0.8314) time: 0.2332 data: 0.1303 max mem: 8452 +Train: [75] [4800/6250] eta: 0:04:10 lr: 0.000019 grad: 0.1302 (0.1358) loss: 0.8333 (0.8314) time: 0.1885 data: 0.0913 max mem: 8452 +Train: [75] [4900/6250] eta: 0:03:53 lr: 0.000019 grad: 0.1297 (0.1358) loss: 0.8336 (0.8314) time: 0.1686 data: 0.0726 max mem: 8452 +Train: [75] [5000/6250] eta: 0:03:36 lr: 0.000019 grad: 0.1346 (0.1358) loss: 0.8301 (0.8314) time: 0.1106 data: 0.0113 max mem: 8452 +Train: [75] [5100/6250] eta: 0:03:18 lr: 0.000019 grad: 0.1259 (0.1358) loss: 0.8336 (0.8315) time: 0.2314 data: 0.1520 max mem: 8452 +Train: [75] [5200/6250] eta: 0:03:01 lr: 0.000019 grad: 0.1262 (0.1356) loss: 0.8418 (0.8315) time: 0.1919 data: 0.1013 max mem: 8452 +Train: [75] [5300/6250] eta: 0:02:43 lr: 0.000019 grad: 0.1299 (0.1356) loss: 0.8274 (0.8316) time: 0.1773 data: 0.0872 max mem: 8452 +Train: [75] [5400/6250] eta: 0:02:26 lr: 0.000019 grad: 0.1227 (0.1354) loss: 0.8393 (0.8316) time: 0.1713 data: 0.0965 max mem: 8452 +Train: [75] [5500/6250] eta: 0:02:09 lr: 0.000019 grad: 0.1233 (0.1354) loss: 0.8400 (0.8317) time: 0.3502 data: 0.2385 max mem: 8452 +Train: [75] [5600/6250] eta: 0:01:52 lr: 0.000019 grad: 0.1270 (0.1354) loss: 0.8419 (0.8317) time: 0.1633 data: 0.0698 max mem: 8452 +Train: [75] [5700/6250] eta: 0:01:34 lr: 0.000019 grad: 0.1331 (0.1354) loss: 0.8257 (0.8317) time: 0.1705 data: 0.0909 max mem: 8452 +Train: [75] [5800/6250] eta: 0:01:17 lr: 0.000019 grad: 0.1319 (0.1353) loss: 0.8325 (0.8317) time: 0.1653 data: 0.0826 max mem: 8452 +Train: [75] [5900/6250] eta: 0:01:00 lr: 0.000019 grad: 0.1277 (0.1353) loss: 0.8355 (0.8317) time: 0.2688 data: 0.1873 max mem: 8452 +Train: [75] [6000/6250] eta: 0:00:43 lr: 0.000019 grad: 0.1399 (0.1353) loss: 0.8280 (0.8316) time: 0.1480 data: 0.0518 max mem: 8452 +Train: [75] [6100/6250] eta: 0:00:25 lr: 0.000019 grad: 0.1351 (0.1354) loss: 0.8346 (0.8316) time: 0.2011 data: 0.1226 max mem: 8452 +Train: [75] [6200/6250] eta: 0:00:08 lr: 0.000019 grad: 0.1344 (0.1354) loss: 0.8297 (0.8316) time: 0.2002 data: 0.1280 max mem: 8452 +Train: [75] [6249/6250] eta: 0:00:00 lr: 0.000019 grad: 0.1420 (0.1354) loss: 0.8299 (0.8315) time: 0.2120 data: 0.1438 max mem: 8452 +Train: [75] Total time: 0:18:06 (0.1738 s / it) +Averaged stats: lr: 0.000019 grad: 0.1420 (0.1354) loss: 0.8299 (0.8315) +Eval (hcp-train-subset): [75] [ 0/62] eta: 0:06:36 loss: 0.8648 (0.8648) time: 6.3928 data: 6.3652 max mem: 8452 +Eval (hcp-train-subset): [75] [61/62] eta: 0:00:00 loss: 0.8537 (0.8558) time: 0.1504 data: 0.1281 max mem: 8452 +Eval (hcp-train-subset): [75] Total time: 0:00:15 (0.2461 s / it) +Averaged stats (hcp-train-subset): loss: 0.8537 (0.8558) +Eval (hcp-val): [75] [ 0/62] eta: 0:05:22 loss: 0.8640 (0.8640) time: 5.1973 data: 5.1612 max mem: 8452 +Eval (hcp-val): [75] [61/62] eta: 0:00:00 loss: 0.8689 (0.8694) time: 0.1513 data: 0.1277 max mem: 8452 +Eval (hcp-val): [75] Total time: 0:00:15 (0.2444 s / it) +Averaged stats (hcp-val): loss: 0.8689 (0.8694) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [76] [ 0/6250] eta: 10:36:17 lr: 0.000019 grad: 0.1884 (0.1884) loss: 0.8753 (0.8753) time: 6.1084 data: 5.9081 max mem: 8452 +Train: [76] [ 100/6250] eta: 0:23:58 lr: 0.000019 grad: 0.1393 (0.1846) loss: 0.8486 (0.8534) time: 0.1788 data: 0.0751 max mem: 8452 +Train: [76] [ 200/6250] eta: 0:20:50 lr: 0.000019 grad: 0.1312 (0.1621) loss: 0.8559 (0.8499) time: 0.1366 data: 0.0270 max mem: 8452 +Train: [76] [ 300/6250] eta: 0:19:35 lr: 0.000019 grad: 0.1307 (0.1551) loss: 0.8390 (0.8467) time: 0.1868 data: 0.0932 max mem: 8452 +Train: [76] [ 400/6250] eta: 0:18:41 lr: 0.000019 grad: 0.1358 (0.1513) loss: 0.8359 (0.8434) time: 0.1982 data: 0.1088 max mem: 8452 +Train: [76] [ 500/6250] eta: 0:18:25 lr: 0.000019 grad: 0.1244 (0.1480) loss: 0.8436 (0.8423) time: 0.1545 data: 0.0520 max mem: 8452 +Train: [76] [ 600/6250] eta: 0:17:34 lr: 0.000019 grad: 0.1325 (0.1456) loss: 0.8306 (0.8411) time: 0.1388 data: 0.0465 max mem: 8452 +Train: [76] [ 700/6250] eta: 0:17:31 lr: 0.000019 grad: 0.1252 (0.1429) loss: 0.8352 (0.8407) time: 0.3130 data: 0.2083 max mem: 8452 +Train: [76] [ 800/6250] eta: 0:16:45 lr: 0.000018 grad: 0.1266 (0.1411) loss: 0.8366 (0.8403) time: 0.1382 data: 0.0545 max mem: 8452 +Train: [76] [ 900/6250] eta: 0:16:19 lr: 0.000018 grad: 0.1267 (0.1405) loss: 0.8323 (0.8396) time: 0.1394 data: 0.0632 max mem: 8452 +Train: [76] [1000/6250] eta: 0:15:54 lr: 0.000018 grad: 0.1343 (0.1398) loss: 0.8385 (0.8393) time: 0.1828 data: 0.1042 max mem: 8452 +Train: [76] [1100/6250] eta: 0:15:31 lr: 0.000018 grad: 0.1338 (0.1394) loss: 0.8383 (0.8384) time: 0.1796 data: 0.0897 max mem: 8452 +Train: [76] [1200/6250] eta: 0:15:05 lr: 0.000018 grad: 0.1357 (0.1393) loss: 0.8180 (0.8374) time: 0.1388 data: 0.0511 max mem: 8452 +Train: [76] [1300/6250] eta: 0:14:41 lr: 0.000018 grad: 0.1301 (0.1389) loss: 0.8260 (0.8366) time: 0.1424 data: 0.0417 max mem: 8452 +Train: [76] [1400/6250] eta: 0:14:16 lr: 0.000018 grad: 0.1284 (0.1385) loss: 0.8220 (0.8360) time: 0.1693 data: 0.0902 max mem: 8452 +Train: [76] [1500/6250] eta: 0:13:58 lr: 0.000018 grad: 0.1303 (0.1379) loss: 0.8372 (0.8357) time: 0.1681 data: 0.0882 max mem: 8452 +Train: [76] [1600/6250] eta: 0:13:37 lr: 0.000018 grad: 0.1389 (0.1376) loss: 0.8209 (0.8352) time: 0.1584 data: 0.0745 max mem: 8452 +Train: [76] [1700/6250] eta: 0:13:19 lr: 0.000018 grad: 0.1312 (0.1375) loss: 0.8187 (0.8347) time: 0.1154 data: 0.0421 max mem: 8452 +Train: [76] [1800/6250] eta: 0:13:01 lr: 0.000018 grad: 0.1280 (0.1376) loss: 0.8326 (0.8341) time: 0.1642 data: 0.0892 max mem: 8452 +Train: [76] [1900/6250] eta: 0:12:47 lr: 0.000018 grad: 0.1279 (0.1375) loss: 0.8226 (0.8338) time: 0.2219 data: 0.1379 max mem: 8452 +Train: [76] [2000/6250] eta: 0:12:25 lr: 0.000018 grad: 0.1363 (0.1374) loss: 0.8276 (0.8334) time: 0.1368 data: 0.0573 max mem: 8452 +Train: [76] [2100/6250] eta: 0:12:13 lr: 0.000018 grad: 0.1297 (0.1371) loss: 0.8343 (0.8333) time: 0.0919 data: 0.0002 max mem: 8452 +Train: [76] [2200/6250] eta: 0:11:54 lr: 0.000018 grad: 0.1344 (0.1369) loss: 0.8258 (0.8333) time: 0.1515 data: 0.0672 max mem: 8452 +Train: [76] [2300/6250] eta: 0:11:36 lr: 0.000018 grad: 0.1258 (0.1368) loss: 0.8297 (0.8331) time: 0.1184 data: 0.0287 max mem: 8452 +Train: [76] [2400/6250] eta: 0:11:18 lr: 0.000018 grad: 0.1364 (0.1367) loss: 0.8242 (0.8331) time: 0.1913 data: 0.1187 max mem: 8452 +Train: [76] [2500/6250] eta: 0:11:00 lr: 0.000018 grad: 0.1377 (0.1366) loss: 0.8297 (0.8330) time: 0.1812 data: 0.1007 max mem: 8452 +Train: [76] [2600/6250] eta: 0:10:42 lr: 0.000018 grad: 0.1322 (0.1365) loss: 0.8300 (0.8329) time: 0.1904 data: 0.1164 max mem: 8452 +Train: [76] [2700/6250] eta: 0:10:25 lr: 0.000018 grad: 0.1330 (0.1363) loss: 0.8224 (0.8328) time: 0.1577 data: 0.0683 max mem: 8452 +Train: [76] [2800/6250] eta: 0:10:07 lr: 0.000018 grad: 0.1245 (0.1361) loss: 0.8336 (0.8328) time: 0.1440 data: 0.0538 max mem: 8452 +Train: [76] [2900/6250] eta: 0:09:49 lr: 0.000018 grad: 0.1294 (0.1359) loss: 0.8282 (0.8327) time: 0.1746 data: 0.0961 max mem: 8452 +Train: [76] [3000/6250] eta: 0:09:29 lr: 0.000018 grad: 0.1195 (0.1358) loss: 0.8397 (0.8327) time: 0.1698 data: 0.0727 max mem: 8452 +Train: [76] [3100/6250] eta: 0:09:11 lr: 0.000018 grad: 0.1358 (0.1357) loss: 0.8360 (0.8326) time: 0.1897 data: 0.1161 max mem: 8452 +Train: [76] [3200/6250] eta: 0:08:53 lr: 0.000018 grad: 0.1284 (0.1356) loss: 0.8284 (0.8326) time: 0.1717 data: 0.0906 max mem: 8452 +Train: [76] [3300/6250] eta: 0:08:36 lr: 0.000018 grad: 0.1272 (0.1355) loss: 0.8329 (0.8325) time: 0.1469 data: 0.0658 max mem: 8452 +Train: [76] [3400/6250] eta: 0:08:18 lr: 0.000018 grad: 0.1282 (0.1354) loss: 0.8362 (0.8325) time: 0.1846 data: 0.1159 max mem: 8452 +Train: [76] [3500/6250] eta: 0:08:00 lr: 0.000018 grad: 0.1308 (0.1352) loss: 0.8373 (0.8325) time: 0.2130 data: 0.1302 max mem: 8452 +Train: [76] [3600/6250] eta: 0:07:43 lr: 0.000018 grad: 0.1243 (0.1351) loss: 0.8302 (0.8325) time: 0.1856 data: 0.1233 max mem: 8452 +Train: [76] [3700/6250] eta: 0:07:25 lr: 0.000018 grad: 0.1252 (0.1352) loss: 0.8356 (0.8325) time: 0.1465 data: 0.0664 max mem: 8452 +Train: [76] [3800/6250] eta: 0:07:06 lr: 0.000018 grad: 0.1373 (0.1351) loss: 0.8296 (0.8324) time: 0.1596 data: 0.0745 max mem: 8452 +Train: [76] [3900/6250] eta: 0:06:48 lr: 0.000018 grad: 0.1299 (0.1351) loss: 0.8372 (0.8323) time: 0.1642 data: 0.0911 max mem: 8452 +Train: [76] [4000/6250] eta: 0:06:30 lr: 0.000018 grad: 0.1276 (0.1352) loss: 0.8244 (0.8323) time: 0.1479 data: 0.0683 max mem: 8452 +Train: [76] [4100/6250] eta: 0:06:11 lr: 0.000018 grad: 0.1353 (0.1351) loss: 0.8284 (0.8322) time: 0.1436 data: 0.0395 max mem: 8452 +Train: [76] [4200/6250] eta: 0:05:53 lr: 0.000018 grad: 0.1304 (0.1351) loss: 0.8360 (0.8322) time: 0.1231 data: 0.0436 max mem: 8452 +Train: [76] [4300/6250] eta: 0:05:35 lr: 0.000018 grad: 0.1379 (0.1351) loss: 0.8291 (0.8322) time: 0.1381 data: 0.0627 max mem: 8452 +Train: [76] [4400/6250] eta: 0:05:17 lr: 0.000018 grad: 0.1270 (0.1351) loss: 0.8306 (0.8322) time: 0.1656 data: 0.0975 max mem: 8452 +Train: [76] [4500/6250] eta: 0:05:00 lr: 0.000018 grad: 0.1288 (0.1352) loss: 0.8376 (0.8321) time: 0.1472 data: 0.0700 max mem: 8452 +Train: [76] [4600/6250] eta: 0:04:43 lr: 0.000018 grad: 0.1344 (0.1351) loss: 0.8231 (0.8322) time: 0.1742 data: 0.0887 max mem: 8452 +Train: [76] [4700/6250] eta: 0:04:25 lr: 0.000018 grad: 0.1254 (0.1351) loss: 0.8332 (0.8321) time: 0.1904 data: 0.1037 max mem: 8452 +Train: [76] [4800/6250] eta: 0:04:08 lr: 0.000018 grad: 0.1354 (0.1352) loss: 0.8376 (0.8321) time: 0.2657 data: 0.1742 max mem: 8452 +Train: [76] [4900/6250] eta: 0:03:51 lr: 0.000018 grad: 0.1279 (0.1352) loss: 0.8321 (0.8321) time: 0.1474 data: 0.0529 max mem: 8452 +Train: [76] [5000/6250] eta: 0:03:34 lr: 0.000018 grad: 0.1261 (0.1352) loss: 0.8323 (0.8320) time: 0.1807 data: 0.1106 max mem: 8452 +Train: [76] [5100/6250] eta: 0:03:17 lr: 0.000017 grad: 0.1297 (0.1351) loss: 0.8293 (0.8320) time: 0.2917 data: 0.1965 max mem: 8452 +Train: [76] [5200/6250] eta: 0:03:00 lr: 0.000017 grad: 0.1344 (0.1351) loss: 0.8294 (0.8320) time: 0.1606 data: 0.0834 max mem: 8452 +Train: [76] [5300/6250] eta: 0:02:42 lr: 0.000017 grad: 0.1372 (0.1352) loss: 0.8283 (0.8319) time: 0.1469 data: 0.0723 max mem: 8452 +Train: [76] [5400/6250] eta: 0:02:25 lr: 0.000017 grad: 0.1333 (0.1352) loss: 0.8164 (0.8319) time: 0.1587 data: 0.0930 max mem: 8452 +Train: [76] [5500/6250] eta: 0:02:08 lr: 0.000017 grad: 0.1293 (0.1352) loss: 0.8448 (0.8319) time: 0.1467 data: 0.0621 max mem: 8452 +Train: [76] [5600/6250] eta: 0:01:50 lr: 0.000017 grad: 0.1304 (0.1353) loss: 0.8336 (0.8319) time: 0.1596 data: 0.0772 max mem: 8452 +Train: [76] [5700/6250] eta: 0:01:33 lr: 0.000017 grad: 0.1349 (0.1352) loss: 0.8252 (0.8320) time: 0.1396 data: 0.0632 max mem: 8452 +Train: [76] [5800/6250] eta: 0:01:16 lr: 0.000017 grad: 0.1346 (0.1352) loss: 0.8309 (0.8320) time: 0.1421 data: 0.0605 max mem: 8452 +Train: [76] [5900/6250] eta: 0:00:59 lr: 0.000017 grad: 0.1250 (0.1352) loss: 0.8347 (0.8320) time: 0.2114 data: 0.1238 max mem: 8452 +Train: [76] [6000/6250] eta: 0:00:42 lr: 0.000017 grad: 0.1353 (0.1353) loss: 0.8196 (0.8319) time: 0.1580 data: 0.0691 max mem: 8452 +Train: [76] [6100/6250] eta: 0:00:25 lr: 0.000017 grad: 0.1486 (0.1353) loss: 0.8306 (0.8319) time: 0.1729 data: 0.0840 max mem: 8452 +Train: [76] [6200/6250] eta: 0:00:08 lr: 0.000017 grad: 0.1353 (0.1354) loss: 0.8254 (0.8319) time: 0.1540 data: 0.0712 max mem: 8452 +Train: [76] [6249/6250] eta: 0:00:00 lr: 0.000017 grad: 0.1356 (0.1354) loss: 0.8295 (0.8319) time: 0.1466 data: 0.0566 max mem: 8452 +Train: [76] Total time: 0:17:47 (0.1708 s / it) +Averaged stats: lr: 0.000017 grad: 0.1356 (0.1354) loss: 0.8295 (0.8319) +Eval (hcp-train-subset): [76] [ 0/62] eta: 0:07:01 loss: 0.8655 (0.8655) time: 6.7951 data: 6.7679 max mem: 8452 +Eval (hcp-train-subset): [76] [61/62] eta: 0:00:00 loss: 0.8530 (0.8543) time: 0.1457 data: 0.1246 max mem: 8452 +Eval (hcp-train-subset): [76] Total time: 0:00:15 (0.2477 s / it) +Averaged stats (hcp-train-subset): loss: 0.8530 (0.8543) +Eval (hcp-val): [76] [ 0/62] eta: 0:06:26 loss: 0.8666 (0.8666) time: 6.2277 data: 6.1985 max mem: 8452 +Eval (hcp-val): [76] [61/62] eta: 0:00:00 loss: 0.8684 (0.8689) time: 0.1497 data: 0.1280 max mem: 8452 +Eval (hcp-val): [76] Total time: 0:00:15 (0.2480 s / it) +Averaged stats (hcp-val): loss: 0.8684 (0.8689) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [77] [ 0/6250] eta: 12:32:09 lr: 0.000017 grad: 0.4255 (0.4255) loss: 0.8052 (0.8052) time: 7.2208 data: 7.1041 max mem: 8452 +Train: [77] [ 100/6250] eta: 0:22:59 lr: 0.000017 grad: 0.1562 (0.2072) loss: 0.8369 (0.8430) time: 0.1590 data: 0.0703 max mem: 8452 +Train: [77] [ 200/6250] eta: 0:20:05 lr: 0.000017 grad: 0.1493 (0.1866) loss: 0.8294 (0.8351) time: 0.1547 data: 0.0602 max mem: 8452 +Train: [77] [ 300/6250] eta: 0:18:42 lr: 0.000017 grad: 0.1479 (0.1731) loss: 0.8336 (0.8347) time: 0.1537 data: 0.0498 max mem: 8452 +Train: [77] [ 400/6250] eta: 0:17:41 lr: 0.000017 grad: 0.1306 (0.1645) loss: 0.8410 (0.8354) time: 0.1397 data: 0.0493 max mem: 8452 +Train: [77] [ 500/6250] eta: 0:16:49 lr: 0.000017 grad: 0.1382 (0.1590) loss: 0.8403 (0.8360) time: 0.1371 data: 0.0457 max mem: 8452 +Train: [77] [ 600/6250] eta: 0:16:55 lr: 0.000017 grad: 0.1348 (0.1548) loss: 0.8303 (0.8367) time: 0.1264 data: 0.0003 max mem: 8452 +Train: [77] [ 700/6250] eta: 0:16:41 lr: 0.000017 grad: 0.1283 (0.1517) loss: 0.8479 (0.8372) time: 0.1863 data: 0.1028 max mem: 8452 +Train: [77] [ 800/6250] eta: 0:16:18 lr: 0.000017 grad: 0.1340 (0.1493) loss: 0.8409 (0.8380) time: 0.1647 data: 0.0700 max mem: 8452 +Train: [77] [ 900/6250] eta: 0:15:51 lr: 0.000017 grad: 0.1292 (0.1476) loss: 0.8350 (0.8383) time: 0.1868 data: 0.0940 max mem: 8452 +Train: [77] [1000/6250] eta: 0:15:25 lr: 0.000017 grad: 0.1245 (0.1458) loss: 0.8413 (0.8385) time: 0.1340 data: 0.0295 max mem: 8452 +Train: [77] [1100/6250] eta: 0:14:56 lr: 0.000017 grad: 0.1149 (0.1442) loss: 0.8459 (0.8386) time: 0.1448 data: 0.0644 max mem: 8452 +Train: [77] [1200/6250] eta: 0:14:29 lr: 0.000017 grad: 0.1275 (0.1428) loss: 0.8411 (0.8388) time: 0.1565 data: 0.0715 max mem: 8452 +Train: [77] [1300/6250] eta: 0:14:08 lr: 0.000017 grad: 0.1190 (0.1417) loss: 0.8413 (0.8388) time: 0.1532 data: 0.0691 max mem: 8452 +Train: [77] [1400/6250] eta: 0:13:46 lr: 0.000017 grad: 0.1184 (0.1410) loss: 0.8421 (0.8391) time: 0.1203 data: 0.0363 max mem: 8452 +Train: [77] [1500/6250] eta: 0:13:33 lr: 0.000017 grad: 0.1275 (0.1405) loss: 0.8438 (0.8391) time: 0.2367 data: 0.1528 max mem: 8452 +Train: [77] [1600/6250] eta: 0:13:14 lr: 0.000017 grad: 0.1330 (0.1399) loss: 0.8303 (0.8389) time: 0.1877 data: 0.1011 max mem: 8452 +Train: [77] [1700/6250] eta: 0:12:57 lr: 0.000017 grad: 0.1289 (0.1393) loss: 0.8355 (0.8387) time: 0.1629 data: 0.0790 max mem: 8452 +Train: [77] [1800/6250] eta: 0:12:53 lr: 0.000017 grad: 0.1326 (0.1391) loss: 0.8248 (0.8384) time: 0.1540 data: 0.0003 max mem: 8452 +Train: [77] [1900/6250] eta: 0:12:51 lr: 0.000017 grad: 0.1330 (0.1389) loss: 0.8313 (0.8382) time: 0.2925 data: 0.1932 max mem: 8452 +Train: [77] [2000/6250] eta: 0:12:47 lr: 0.000017 grad: 0.1347 (0.1387) loss: 0.8284 (0.8379) time: 0.3719 data: 0.2727 max mem: 8452 +Train: [77] [2100/6250] eta: 0:12:22 lr: 0.000017 grad: 0.1379 (0.1384) loss: 0.8281 (0.8376) time: 0.1740 data: 0.0802 max mem: 8452 +Train: [77] [2200/6250] eta: 0:12:05 lr: 0.000017 grad: 0.1283 (0.1382) loss: 0.8341 (0.8375) time: 0.2049 data: 0.1248 max mem: 8452 +Train: [77] [2300/6250] eta: 0:11:47 lr: 0.000017 grad: 0.1327 (0.1380) loss: 0.8349 (0.8374) time: 0.1760 data: 0.0889 max mem: 8452 +Train: [77] [2400/6250] eta: 0:11:26 lr: 0.000017 grad: 0.1381 (0.1379) loss: 0.8350 (0.8372) time: 0.1787 data: 0.0950 max mem: 8452 +Train: [77] [2500/6250] eta: 0:11:08 lr: 0.000017 grad: 0.1297 (0.1377) loss: 0.8363 (0.8371) time: 0.1605 data: 0.0621 max mem: 8452 +Train: [77] [2600/6250] eta: 0:10:48 lr: 0.000017 grad: 0.1308 (0.1376) loss: 0.8293 (0.8370) time: 0.1576 data: 0.0763 max mem: 8452 +Train: [77] [2700/6250] eta: 0:10:29 lr: 0.000017 grad: 0.1337 (0.1375) loss: 0.8324 (0.8369) time: 0.1525 data: 0.0605 max mem: 8452 +Train: [77] [2800/6250] eta: 0:10:07 lr: 0.000017 grad: 0.1302 (0.1374) loss: 0.8335 (0.8368) time: 0.1306 data: 0.0486 max mem: 8452 +Train: [77] [2900/6250] eta: 0:09:48 lr: 0.000017 grad: 0.1221 (0.1372) loss: 0.8413 (0.8367) time: 0.1629 data: 0.0870 max mem: 8452 +Train: [77] [3000/6250] eta: 0:09:30 lr: 0.000017 grad: 0.1309 (0.1370) loss: 0.8349 (0.8368) time: 0.1574 data: 0.0761 max mem: 8452 +Train: [77] [3100/6250] eta: 0:09:13 lr: 0.000017 grad: 0.1332 (0.1369) loss: 0.8394 (0.8369) time: 0.1641 data: 0.0899 max mem: 8452 +Train: [77] [3200/6250] eta: 0:08:55 lr: 0.000017 grad: 0.1272 (0.1367) loss: 0.8361 (0.8369) time: 0.1672 data: 0.0832 max mem: 8452 +Train: [77] [3300/6250] eta: 0:08:37 lr: 0.000016 grad: 0.1319 (0.1366) loss: 0.8397 (0.8369) time: 0.1965 data: 0.1212 max mem: 8452 +Train: [77] [3400/6250] eta: 0:08:18 lr: 0.000016 grad: 0.1282 (0.1364) loss: 0.8371 (0.8369) time: 0.1578 data: 0.0890 max mem: 8452 +Train: [77] [3500/6250] eta: 0:08:00 lr: 0.000016 grad: 0.1366 (0.1364) loss: 0.8408 (0.8369) time: 0.1574 data: 0.0811 max mem: 8452 +Train: [77] [3600/6250] eta: 0:07:43 lr: 0.000016 grad: 0.1313 (0.1363) loss: 0.8383 (0.8369) time: 0.1631 data: 0.0832 max mem: 8452 +Train: [77] [3700/6250] eta: 0:07:24 lr: 0.000016 grad: 0.1261 (0.1362) loss: 0.8407 (0.8370) time: 0.1662 data: 0.0926 max mem: 8452 +Train: [77] [3800/6250] eta: 0:07:06 lr: 0.000016 grad: 0.1238 (0.1361) loss: 0.8392 (0.8370) time: 0.1782 data: 0.0930 max mem: 8452 +Train: [77] [3900/6250] eta: 0:06:49 lr: 0.000016 grad: 0.1328 (0.1361) loss: 0.8333 (0.8369) time: 0.1907 data: 0.1059 max mem: 8452 +Train: [77] [4000/6250] eta: 0:06:32 lr: 0.000016 grad: 0.1314 (0.1361) loss: 0.8338 (0.8369) time: 0.2097 data: 0.1242 max mem: 8452 +Train: [77] [4100/6250] eta: 0:06:14 lr: 0.000016 grad: 0.1286 (0.1360) loss: 0.8350 (0.8369) time: 0.2193 data: 0.1255 max mem: 8452 +Train: [77] [4200/6250] eta: 0:05:56 lr: 0.000016 grad: 0.1353 (0.1359) loss: 0.8333 (0.8369) time: 0.1587 data: 0.0729 max mem: 8452 +Train: [77] [4300/6250] eta: 0:05:40 lr: 0.000016 grad: 0.1323 (0.1359) loss: 0.8350 (0.8368) time: 0.1100 data: 0.0002 max mem: 8452 +Train: [77] [4400/6250] eta: 0:05:23 lr: 0.000016 grad: 0.1311 (0.1359) loss: 0.8340 (0.8367) time: 0.1727 data: 0.0885 max mem: 8452 +Train: [77] [4500/6250] eta: 0:05:07 lr: 0.000016 grad: 0.1363 (0.1359) loss: 0.8387 (0.8367) time: 0.1335 data: 0.0044 max mem: 8452 +Train: [77] [4600/6250] eta: 0:04:49 lr: 0.000016 grad: 0.1346 (0.1359) loss: 0.8361 (0.8367) time: 0.1982 data: 0.1027 max mem: 8452 +Train: [77] [4700/6250] eta: 0:04:32 lr: 0.000016 grad: 0.1309 (0.1359) loss: 0.8366 (0.8366) time: 0.1931 data: 0.1048 max mem: 8452 +Train: [77] [4800/6250] eta: 0:04:14 lr: 0.000016 grad: 0.1361 (0.1358) loss: 0.8256 (0.8366) time: 0.1560 data: 0.0688 max mem: 8452 +Train: [77] [4900/6250] eta: 0:03:56 lr: 0.000016 grad: 0.1269 (0.1358) loss: 0.8367 (0.8365) time: 0.1383 data: 0.0622 max mem: 8452 +Train: [77] [5000/6250] eta: 0:03:38 lr: 0.000016 grad: 0.1358 (0.1358) loss: 0.8328 (0.8364) time: 0.1640 data: 0.0910 max mem: 8452 +Train: [77] [5100/6250] eta: 0:03:21 lr: 0.000016 grad: 0.1255 (0.1358) loss: 0.8337 (0.8363) time: 0.1799 data: 0.0858 max mem: 8452 +Train: [77] [5200/6250] eta: 0:03:03 lr: 0.000016 grad: 0.1316 (0.1359) loss: 0.8311 (0.8362) time: 0.1235 data: 0.0153 max mem: 8452 +Train: [77] [5300/6250] eta: 0:02:45 lr: 0.000016 grad: 0.1333 (0.1360) loss: 0.8237 (0.8361) time: 0.1551 data: 0.0687 max mem: 8452 +Train: [77] [5400/6250] eta: 0:02:28 lr: 0.000016 grad: 0.1318 (0.1360) loss: 0.8259 (0.8359) time: 0.1117 data: 0.0003 max mem: 8452 +Train: [77] [5500/6250] eta: 0:02:10 lr: 0.000016 grad: 0.1379 (0.1361) loss: 0.8247 (0.8357) time: 0.1651 data: 0.0836 max mem: 8452 +Train: [77] [5600/6250] eta: 0:01:53 lr: 0.000016 grad: 0.1356 (0.1361) loss: 0.8319 (0.8356) time: 0.2156 data: 0.1314 max mem: 8452 +Train: [77] [5700/6250] eta: 0:01:35 lr: 0.000016 grad: 0.1303 (0.1361) loss: 0.8336 (0.8355) time: 0.1660 data: 0.0858 max mem: 8452 +Train: [77] [5800/6250] eta: 0:01:18 lr: 0.000016 grad: 0.1318 (0.1362) loss: 0.8383 (0.8354) time: 0.1978 data: 0.1295 max mem: 8452 +Train: [77] [5900/6250] eta: 0:01:00 lr: 0.000016 grad: 0.1287 (0.1362) loss: 0.8400 (0.8354) time: 0.1715 data: 0.0833 max mem: 8452 +Train: [77] [6000/6250] eta: 0:00:43 lr: 0.000016 grad: 0.1358 (0.1363) loss: 0.8329 (0.8353) time: 0.2634 data: 0.1667 max mem: 8452 +Train: [77] [6100/6250] eta: 0:00:26 lr: 0.000016 grad: 0.1335 (0.1363) loss: 0.8328 (0.8352) time: 0.1399 data: 0.0576 max mem: 8452 +Train: [77] [6200/6250] eta: 0:00:08 lr: 0.000016 grad: 0.1330 (0.1364) loss: 0.8297 (0.8352) time: 0.1734 data: 0.0781 max mem: 8452 +Train: [77] [6249/6250] eta: 0:00:00 lr: 0.000016 grad: 0.1300 (0.1364) loss: 0.8421 (0.8352) time: 0.1922 data: 0.1181 max mem: 8452 +Train: [77] Total time: 0:18:15 (0.1753 s / it) +Averaged stats: lr: 0.000016 grad: 0.1300 (0.1364) loss: 0.8421 (0.8352) +Eval (hcp-train-subset): [77] [ 0/62] eta: 0:07:08 loss: 0.8685 (0.8685) time: 6.9107 data: 6.8836 max mem: 8452 +Eval (hcp-train-subset): [77] [61/62] eta: 0:00:00 loss: 0.8533 (0.8532) time: 0.1446 data: 0.1235 max mem: 8452 +Eval (hcp-train-subset): [77] Total time: 0:00:16 (0.2600 s / it) +Averaged stats (hcp-train-subset): loss: 0.8533 (0.8532) +Eval (hcp-val): [77] [ 0/62] eta: 0:05:47 loss: 0.8674 (0.8674) time: 5.6029 data: 5.5760 max mem: 8452 +Eval (hcp-val): [77] [61/62] eta: 0:00:00 loss: 0.8673 (0.8696) time: 0.1395 data: 0.1169 max mem: 8452 +Eval (hcp-val): [77] Total time: 0:00:15 (0.2499 s / it) +Averaged stats (hcp-val): loss: 0.8673 (0.8696) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [78] [ 0/6250] eta: 12:17:45 lr: 0.000016 grad: 0.1852 (0.1852) loss: 0.8756 (0.8756) time: 7.0824 data: 6.9509 max mem: 8452 +Train: [78] [ 100/6250] eta: 0:23:20 lr: 0.000016 grad: 0.1721 (0.2052) loss: 0.8470 (0.8431) time: 0.1695 data: 0.0625 max mem: 8452 +Train: [78] [ 200/6250] eta: 0:20:02 lr: 0.000016 grad: 0.1462 (0.1829) loss: 0.8434 (0.8418) time: 0.1587 data: 0.0558 max mem: 8452 +Train: [78] [ 300/6250] eta: 0:18:54 lr: 0.000016 grad: 0.1442 (0.1713) loss: 0.8327 (0.8402) time: 0.1706 data: 0.0880 max mem: 8452 +Train: [78] [ 400/6250] eta: 0:17:45 lr: 0.000016 grad: 0.1343 (0.1648) loss: 0.8373 (0.8396) time: 0.1618 data: 0.0762 max mem: 8452 +Train: [78] [ 500/6250] eta: 0:17:00 lr: 0.000016 grad: 0.1306 (0.1600) loss: 0.8374 (0.8392) time: 0.1818 data: 0.0893 max mem: 8452 +Train: [78] [ 600/6250] eta: 0:16:22 lr: 0.000016 grad: 0.1257 (0.1552) loss: 0.8500 (0.8398) time: 0.1567 data: 0.0744 max mem: 8452 +Train: [78] [ 700/6250] eta: 0:16:11 lr: 0.000016 grad: 0.1210 (0.1518) loss: 0.8429 (0.8399) time: 0.1888 data: 0.0958 max mem: 8452 +Train: [78] [ 800/6250] eta: 0:15:50 lr: 0.000016 grad: 0.1292 (0.1496) loss: 0.8397 (0.8398) time: 0.1659 data: 0.0931 max mem: 8452 +Train: [78] [ 900/6250] eta: 0:15:23 lr: 0.000016 grad: 0.1321 (0.1487) loss: 0.8332 (0.8395) time: 0.1587 data: 0.0682 max mem: 8452 +Train: [78] [1000/6250] eta: 0:15:01 lr: 0.000016 grad: 0.1356 (0.1481) loss: 0.8410 (0.8390) time: 0.1453 data: 0.0597 max mem: 8452 +Train: [78] [1100/6250] eta: 0:14:43 lr: 0.000016 grad: 0.1358 (0.1472) loss: 0.8318 (0.8384) time: 0.1788 data: 0.0915 max mem: 8452 +Train: [78] [1200/6250] eta: 0:14:22 lr: 0.000016 grad: 0.1310 (0.1462) loss: 0.8288 (0.8378) time: 0.1607 data: 0.0677 max mem: 8452 +Train: [78] [1300/6250] eta: 0:14:02 lr: 0.000016 grad: 0.1389 (0.1454) loss: 0.8273 (0.8372) time: 0.1536 data: 0.0693 max mem: 8452 +Train: [78] [1400/6250] eta: 0:13:43 lr: 0.000016 grad: 0.1336 (0.1448) loss: 0.8167 (0.8367) time: 0.1551 data: 0.0804 max mem: 8452 +Train: [78] [1500/6250] eta: 0:13:27 lr: 0.000015 grad: 0.1319 (0.1442) loss: 0.8302 (0.8365) time: 0.1270 data: 0.0275 max mem: 8452 +Train: [78] [1600/6250] eta: 0:13:11 lr: 0.000015 grad: 0.1345 (0.1438) loss: 0.8352 (0.8362) time: 0.1846 data: 0.1115 max mem: 8452 +Train: [78] [1700/6250] eta: 0:12:53 lr: 0.000015 grad: 0.1285 (0.1434) loss: 0.8378 (0.8360) time: 0.1477 data: 0.0463 max mem: 8452 +Train: [78] [1800/6250] eta: 0:12:39 lr: 0.000015 grad: 0.1361 (0.1430) loss: 0.8354 (0.8357) time: 0.1410 data: 0.0535 max mem: 8452 +Train: [78] [1900/6250] eta: 0:12:37 lr: 0.000015 grad: 0.1331 (0.1426) loss: 0.8267 (0.8354) time: 0.2090 data: 0.1190 max mem: 8452 +Train: [78] [2000/6250] eta: 0:12:19 lr: 0.000015 grad: 0.1379 (0.1425) loss: 0.8325 (0.8351) time: 0.1765 data: 0.0894 max mem: 8452 +Train: [78] [2100/6250] eta: 0:12:02 lr: 0.000015 grad: 0.1302 (0.1422) loss: 0.8358 (0.8350) time: 0.1458 data: 0.0597 max mem: 8452 +Train: [78] [2200/6250] eta: 0:11:44 lr: 0.000015 grad: 0.1351 (0.1420) loss: 0.8313 (0.8347) time: 0.1288 data: 0.0011 max mem: 8452 +Train: [78] [2300/6250] eta: 0:11:27 lr: 0.000015 grad: 0.1328 (0.1418) loss: 0.8364 (0.8345) time: 0.1987 data: 0.1104 max mem: 8452 +Train: [78] [2400/6250] eta: 0:11:11 lr: 0.000015 grad: 0.1377 (0.1416) loss: 0.8274 (0.8343) time: 0.1712 data: 0.1012 max mem: 8452 +Train: [78] [2500/6250] eta: 0:10:51 lr: 0.000015 grad: 0.1341 (0.1412) loss: 0.8266 (0.8342) time: 0.1607 data: 0.0697 max mem: 8452 +Train: [78] [2600/6250] eta: 0:10:37 lr: 0.000015 grad: 0.1377 (0.1412) loss: 0.8274 (0.8340) time: 0.1919 data: 0.1099 max mem: 8452 +Train: [78] [2700/6250] eta: 0:10:17 lr: 0.000015 grad: 0.1300 (0.1411) loss: 0.8254 (0.8337) time: 0.1683 data: 0.0830 max mem: 8452 +Train: [78] [2800/6250] eta: 0:09:57 lr: 0.000015 grad: 0.1252 (0.1408) loss: 0.8400 (0.8336) time: 0.1684 data: 0.0877 max mem: 8452 +Train: [78] [2900/6250] eta: 0:09:38 lr: 0.000015 grad: 0.1219 (0.1405) loss: 0.8384 (0.8337) time: 0.1338 data: 0.0459 max mem: 8452 +Train: [78] [3000/6250] eta: 0:09:19 lr: 0.000015 grad: 0.1281 (0.1403) loss: 0.8329 (0.8336) time: 0.1498 data: 0.0713 max mem: 8452 +Train: [78] [3100/6250] eta: 0:09:01 lr: 0.000015 grad: 0.1312 (0.1401) loss: 0.8293 (0.8335) time: 0.1682 data: 0.0881 max mem: 8452 +Train: [78] [3200/6250] eta: 0:08:44 lr: 0.000015 grad: 0.1349 (0.1399) loss: 0.8386 (0.8335) time: 0.1739 data: 0.0971 max mem: 8452 +Train: [78] [3300/6250] eta: 0:08:28 lr: 0.000015 grad: 0.1358 (0.1400) loss: 0.8332 (0.8335) time: 0.1722 data: 0.0896 max mem: 8452 +Train: [78] [3400/6250] eta: 0:08:10 lr: 0.000015 grad: 0.1445 (0.1400) loss: 0.8353 (0.8334) time: 0.1600 data: 0.0688 max mem: 8452 +Train: [78] [3500/6250] eta: 0:07:54 lr: 0.000015 grad: 0.1375 (0.1400) loss: 0.8271 (0.8333) time: 0.2042 data: 0.1341 max mem: 8452 +Train: [78] [3600/6250] eta: 0:07:37 lr: 0.000015 grad: 0.1322 (0.1400) loss: 0.8301 (0.8332) time: 0.1850 data: 0.1075 max mem: 8452 +Train: [78] [3700/6250] eta: 0:07:20 lr: 0.000015 grad: 0.1339 (0.1399) loss: 0.8323 (0.8333) time: 0.2022 data: 0.1162 max mem: 8452 +Train: [78] [3800/6250] eta: 0:07:03 lr: 0.000015 grad: 0.1287 (0.1398) loss: 0.8356 (0.8334) time: 0.1582 data: 0.0708 max mem: 8452 +Train: [78] [3900/6250] eta: 0:06:45 lr: 0.000015 grad: 0.1428 (0.1398) loss: 0.8301 (0.8334) time: 0.1744 data: 0.0809 max mem: 8452 +Train: [78] [4000/6250] eta: 0:06:28 lr: 0.000015 grad: 0.1379 (0.1399) loss: 0.8348 (0.8333) time: 0.1600 data: 0.0735 max mem: 8452 +Train: [78] [4100/6250] eta: 0:06:11 lr: 0.000015 grad: 0.1359 (0.1399) loss: 0.8430 (0.8333) time: 0.1679 data: 0.0837 max mem: 8452 +Train: [78] [4200/6250] eta: 0:05:53 lr: 0.000015 grad: 0.1372 (0.1399) loss: 0.8246 (0.8334) time: 0.1535 data: 0.0585 max mem: 8452 +Train: [78] [4300/6250] eta: 0:05:36 lr: 0.000015 grad: 0.1367 (0.1398) loss: 0.8428 (0.8334) time: 0.1419 data: 0.0402 max mem: 8452 +Train: [78] [4400/6250] eta: 0:05:20 lr: 0.000015 grad: 0.1395 (0.1398) loss: 0.8369 (0.8333) time: 0.1952 data: 0.0836 max mem: 8452 +Train: [78] [4500/6250] eta: 0:05:05 lr: 0.000015 grad: 0.1351 (0.1398) loss: 0.8283 (0.8333) time: 0.2110 data: 0.1103 max mem: 8452 +Train: [78] [4600/6250] eta: 0:04:48 lr: 0.000015 grad: 0.1303 (0.1399) loss: 0.8411 (0.8333) time: 0.1895 data: 0.1050 max mem: 8452 +Train: [78] [4700/6250] eta: 0:04:31 lr: 0.000015 grad: 0.1372 (0.1399) loss: 0.8324 (0.8334) time: 0.1885 data: 0.1029 max mem: 8452 +Train: [78] [4800/6250] eta: 0:04:14 lr: 0.000015 grad: 0.1301 (0.1399) loss: 0.8326 (0.8333) time: 0.2286 data: 0.1062 max mem: 8452 +Train: [78] [4900/6250] eta: 0:03:57 lr: 0.000015 grad: 0.1329 (0.1398) loss: 0.8322 (0.8334) time: 0.1406 data: 0.0584 max mem: 8452 +Train: [78] [5000/6250] eta: 0:03:39 lr: 0.000015 grad: 0.1310 (0.1398) loss: 0.8402 (0.8334) time: 0.1801 data: 0.0954 max mem: 8452 +Train: [78] [5100/6250] eta: 0:03:21 lr: 0.000015 grad: 0.1348 (0.1398) loss: 0.8372 (0.8334) time: 0.1575 data: 0.0803 max mem: 8452 +Train: [78] [5200/6250] eta: 0:03:04 lr: 0.000015 grad: 0.1287 (0.1397) loss: 0.8441 (0.8335) time: 0.1549 data: 0.0726 max mem: 8452 +Train: [78] [5300/6250] eta: 0:02:46 lr: 0.000015 grad: 0.1335 (0.1397) loss: 0.8382 (0.8335) time: 0.1991 data: 0.1177 max mem: 8452 +Train: [78] [5400/6250] eta: 0:02:28 lr: 0.000015 grad: 0.1335 (0.1396) loss: 0.8361 (0.8335) time: 0.1332 data: 0.0583 max mem: 8452 +Train: [78] [5500/6250] eta: 0:02:11 lr: 0.000015 grad: 0.1290 (0.1396) loss: 0.8379 (0.8336) time: 0.2427 data: 0.1610 max mem: 8452 +Train: [78] [5600/6250] eta: 0:01:53 lr: 0.000015 grad: 0.1278 (0.1395) loss: 0.8359 (0.8337) time: 0.1551 data: 0.0699 max mem: 8452 +Train: [78] [5700/6250] eta: 0:01:36 lr: 0.000015 grad: 0.1379 (0.1394) loss: 0.8384 (0.8338) time: 0.2321 data: 0.1194 max mem: 8452 +Train: [78] [5800/6250] eta: 0:01:18 lr: 0.000015 grad: 0.1299 (0.1394) loss: 0.8371 (0.8338) time: 0.1803 data: 0.0933 max mem: 8452 +Train: [78] [5900/6250] eta: 0:01:01 lr: 0.000015 grad: 0.1282 (0.1393) loss: 0.8354 (0.8339) time: 0.3165 data: 0.2243 max mem: 8452 +Train: [78] [6000/6250] eta: 0:00:43 lr: 0.000015 grad: 0.1296 (0.1392) loss: 0.8395 (0.8340) time: 0.1559 data: 0.0745 max mem: 8452 +Train: [78] [6100/6250] eta: 0:00:26 lr: 0.000015 grad: 0.1293 (0.1391) loss: 0.8331 (0.8340) time: 0.1226 data: 0.0024 max mem: 8452 +Train: [78] [6200/6250] eta: 0:00:08 lr: 0.000014 grad: 0.1254 (0.1391) loss: 0.8333 (0.8340) time: 0.1546 data: 0.0648 max mem: 8452 +Train: [78] [6249/6250] eta: 0:00:00 lr: 0.000014 grad: 0.1336 (0.1391) loss: 0.8308 (0.8340) time: 0.1843 data: 0.1054 max mem: 8452 +Train: [78] Total time: 0:18:21 (0.1763 s / it) +Averaged stats: lr: 0.000014 grad: 0.1336 (0.1391) loss: 0.8308 (0.8340) +Eval (hcp-train-subset): [78] [ 0/62] eta: 0:06:51 loss: 0.8622 (0.8622) time: 6.6449 data: 6.6179 max mem: 8452 +Eval (hcp-train-subset): [78] [61/62] eta: 0:00:00 loss: 0.8497 (0.8512) time: 0.1093 data: 0.0881 max mem: 8452 +Eval (hcp-train-subset): [78] Total time: 0:00:15 (0.2475 s / it) +Averaged stats (hcp-train-subset): loss: 0.8497 (0.8512) +Eval (hcp-val): [78] [ 0/62] eta: 0:05:04 loss: 0.8651 (0.8651) time: 4.9151 data: 4.8074 max mem: 8452 +Eval (hcp-val): [78] [61/62] eta: 0:00:00 loss: 0.8680 (0.8691) time: 0.1313 data: 0.1101 max mem: 8452 +Eval (hcp-val): [78] Total time: 0:00:15 (0.2491 s / it) +Averaged stats (hcp-val): loss: 0.8680 (0.8691) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [79] [ 0/6250] eta: 13:05:19 lr: 0.000014 grad: 0.6333 (0.6333) loss: 0.8262 (0.8262) time: 7.5391 data: 7.4421 max mem: 8452 +Train: [79] [ 100/6250] eta: 0:23:44 lr: 0.000014 grad: 0.1541 (0.1789) loss: 0.8459 (0.8471) time: 0.1820 data: 0.0840 max mem: 8452 +Train: [79] [ 200/6250] eta: 0:20:30 lr: 0.000014 grad: 0.1428 (0.1665) loss: 0.8423 (0.8453) time: 0.1695 data: 0.0756 max mem: 8452 +Train: [79] [ 300/6250] eta: 0:18:57 lr: 0.000014 grad: 0.1495 (0.1634) loss: 0.8364 (0.8413) time: 0.1738 data: 0.0722 max mem: 8452 +Train: [79] [ 400/6250] eta: 0:18:03 lr: 0.000014 grad: 0.1342 (0.1587) loss: 0.8381 (0.8400) time: 0.1948 data: 0.1021 max mem: 8452 +Train: [79] [ 500/6250] eta: 0:17:20 lr: 0.000014 grad: 0.1438 (0.1566) loss: 0.8323 (0.8390) time: 0.1484 data: 0.0503 max mem: 8452 +Train: [79] [ 600/6250] eta: 0:17:09 lr: 0.000014 grad: 0.1272 (0.1541) loss: 0.8399 (0.8390) time: 0.1794 data: 0.0927 max mem: 8452 +Train: [79] [ 700/6250] eta: 0:16:50 lr: 0.000014 grad: 0.1434 (0.1518) loss: 0.8369 (0.8391) time: 0.1731 data: 0.0715 max mem: 8452 +Train: [79] [ 800/6250] eta: 0:16:19 lr: 0.000014 grad: 0.1308 (0.1498) loss: 0.8354 (0.8390) time: 0.1733 data: 0.0917 max mem: 8452 +Train: [79] [ 900/6250] eta: 0:15:58 lr: 0.000014 grad: 0.1334 (0.1482) loss: 0.8381 (0.8389) time: 0.2209 data: 0.1220 max mem: 8452 +Train: [79] [1000/6250] eta: 0:15:32 lr: 0.000014 grad: 0.1247 (0.1475) loss: 0.8349 (0.8392) time: 0.1839 data: 0.0887 max mem: 8452 +Train: [79] [1100/6250] eta: 0:15:12 lr: 0.000014 grad: 0.1318 (0.1465) loss: 0.8315 (0.8393) time: 0.1646 data: 0.0599 max mem: 8452 +Train: [79] [1200/6250] eta: 0:14:49 lr: 0.000014 grad: 0.1363 (0.1455) loss: 0.8221 (0.8389) time: 0.1324 data: 0.0405 max mem: 8452 +Train: [79] [1300/6250] eta: 0:14:32 lr: 0.000014 grad: 0.1294 (0.1451) loss: 0.8399 (0.8385) time: 0.2122 data: 0.1394 max mem: 8452 +Train: [79] [1400/6250] eta: 0:14:13 lr: 0.000014 grad: 0.1327 (0.1445) loss: 0.8366 (0.8381) time: 0.1890 data: 0.0950 max mem: 8452 +Train: [79] [1500/6250] eta: 0:13:54 lr: 0.000014 grad: 0.1378 (0.1442) loss: 0.8272 (0.8377) time: 0.1348 data: 0.0312 max mem: 8452 +Train: [79] [1600/6250] eta: 0:13:41 lr: 0.000014 grad: 0.1422 (0.1439) loss: 0.8281 (0.8372) time: 0.2547 data: 0.1641 max mem: 8452 +Train: [79] [1700/6250] eta: 0:13:27 lr: 0.000014 grad: 0.1297 (0.1434) loss: 0.8263 (0.8368) time: 0.1047 data: 0.0142 max mem: 8452 +Train: [79] [1800/6250] eta: 0:13:12 lr: 0.000014 grad: 0.1368 (0.1435) loss: 0.8373 (0.8366) time: 0.1496 data: 0.0457 max mem: 8452 +Train: [79] [1900/6250] eta: 0:13:02 lr: 0.000014 grad: 0.1396 (0.1433) loss: 0.8299 (0.8362) time: 0.3676 data: 0.2437 max mem: 8452 +Train: [79] [2000/6250] eta: 0:12:43 lr: 0.000014 grad: 0.1367 (0.1431) loss: 0.8207 (0.8360) time: 0.1767 data: 0.0754 max mem: 8452 +Train: [79] [2100/6250] eta: 0:12:22 lr: 0.000014 grad: 0.1372 (0.1428) loss: 0.8238 (0.8357) time: 0.1277 data: 0.0340 max mem: 8452 +Train: [79] [2200/6250] eta: 0:12:03 lr: 0.000014 grad: 0.1347 (0.1426) loss: 0.8318 (0.8354) time: 0.1711 data: 0.0876 max mem: 8452 +Train: [79] [2300/6250] eta: 0:11:44 lr: 0.000014 grad: 0.1357 (0.1423) loss: 0.8338 (0.8352) time: 0.1153 data: 0.0193 max mem: 8452 +Train: [79] [2400/6250] eta: 0:11:25 lr: 0.000014 grad: 0.1286 (0.1420) loss: 0.8286 (0.8349) time: 0.1587 data: 0.0651 max mem: 8452 +Train: [79] [2500/6250] eta: 0:11:06 lr: 0.000014 grad: 0.1343 (0.1418) loss: 0.8213 (0.8345) time: 0.2076 data: 0.1333 max mem: 8452 +Train: [79] [2600/6250] eta: 0:10:47 lr: 0.000014 grad: 0.1352 (0.1416) loss: 0.8279 (0.8344) time: 0.1777 data: 0.0905 max mem: 8452 +Train: [79] [2700/6250] eta: 0:10:27 lr: 0.000014 grad: 0.1283 (0.1416) loss: 0.8316 (0.8341) time: 0.1820 data: 0.0958 max mem: 8452 +Train: [79] [2800/6250] eta: 0:10:08 lr: 0.000014 grad: 0.1418 (0.1415) loss: 0.8281 (0.8338) time: 0.1604 data: 0.0871 max mem: 8452 +Train: [79] [2900/6250] eta: 0:09:47 lr: 0.000014 grad: 0.1299 (0.1415) loss: 0.8317 (0.8337) time: 0.1453 data: 0.0524 max mem: 8452 +Train: [79] [3000/6250] eta: 0:09:28 lr: 0.000014 grad: 0.1248 (0.1412) loss: 0.8364 (0.8335) time: 0.1706 data: 0.0871 max mem: 8452 +Train: [79] [3100/6250] eta: 0:09:11 lr: 0.000014 grad: 0.1293 (0.1410) loss: 0.8344 (0.8335) time: 0.2502 data: 0.1714 max mem: 8452 +Train: [79] [3200/6250] eta: 0:08:51 lr: 0.000014 grad: 0.1440 (0.1410) loss: 0.8302 (0.8334) time: 0.1619 data: 0.0760 max mem: 8452 +Train: [79] [3300/6250] eta: 0:08:34 lr: 0.000014 grad: 0.1391 (0.1409) loss: 0.8261 (0.8333) time: 0.2017 data: 0.1345 max mem: 8452 +Train: [79] [3400/6250] eta: 0:08:17 lr: 0.000014 grad: 0.1292 (0.1408) loss: 0.8316 (0.8332) time: 0.1646 data: 0.0773 max mem: 8452 +Train: [79] [3500/6250] eta: 0:08:00 lr: 0.000014 grad: 0.1366 (0.1407) loss: 0.8386 (0.8332) time: 0.2186 data: 0.1550 max mem: 8452 +Train: [79] [3600/6250] eta: 0:07:41 lr: 0.000014 grad: 0.1394 (0.1406) loss: 0.8224 (0.8332) time: 0.1512 data: 0.0783 max mem: 8452 +Train: [79] [3700/6250] eta: 0:07:24 lr: 0.000014 grad: 0.1332 (0.1405) loss: 0.8302 (0.8332) time: 0.1801 data: 0.0942 max mem: 8452 +Train: [79] [3800/6250] eta: 0:07:07 lr: 0.000014 grad: 0.1323 (0.1404) loss: 0.8402 (0.8332) time: 0.1592 data: 0.0747 max mem: 8452 +Train: [79] [3900/6250] eta: 0:06:49 lr: 0.000014 grad: 0.1436 (0.1404) loss: 0.8321 (0.8332) time: 0.1718 data: 0.0801 max mem: 8452 +Train: [79] [4000/6250] eta: 0:06:32 lr: 0.000014 grad: 0.1494 (0.1404) loss: 0.8295 (0.8331) time: 0.1393 data: 0.0490 max mem: 8452 +Train: [79] [4100/6250] eta: 0:06:14 lr: 0.000014 grad: 0.1428 (0.1404) loss: 0.8251 (0.8331) time: 0.1567 data: 0.0605 max mem: 8452 +Train: [79] [4200/6250] eta: 0:05:57 lr: 0.000014 grad: 0.1379 (0.1404) loss: 0.8345 (0.8331) time: 0.2338 data: 0.1443 max mem: 8452 +Train: [79] [4300/6250] eta: 0:05:39 lr: 0.000014 grad: 0.1307 (0.1404) loss: 0.8319 (0.8330) time: 0.1695 data: 0.0894 max mem: 8452 +Train: [79] [4400/6250] eta: 0:05:22 lr: 0.000014 grad: 0.1364 (0.1404) loss: 0.8315 (0.8330) time: 0.2212 data: 0.1413 max mem: 8452 +Train: [79] [4500/6250] eta: 0:05:06 lr: 0.000014 grad: 0.1347 (0.1403) loss: 0.8382 (0.8330) time: 0.1847 data: 0.0636 max mem: 8452 +Train: [79] [4600/6250] eta: 0:04:50 lr: 0.000014 grad: 0.1412 (0.1403) loss: 0.8304 (0.8330) time: 0.3906 data: 0.2874 max mem: 8452 +Train: [79] [4700/6250] eta: 0:04:32 lr: 0.000013 grad: 0.1367 (0.1402) loss: 0.8249 (0.8329) time: 0.1206 data: 0.0157 max mem: 8452 +Train: [79] [4800/6250] eta: 0:04:15 lr: 0.000013 grad: 0.1313 (0.1403) loss: 0.8298 (0.8329) time: 0.2824 data: 0.1850 max mem: 8452 +Train: [79] [4900/6250] eta: 0:03:58 lr: 0.000013 grad: 0.1391 (0.1403) loss: 0.8231 (0.8328) time: 0.3223 data: 0.2279 max mem: 8452 +Train: [79] [5000/6250] eta: 0:03:42 lr: 0.000013 grad: 0.1294 (0.1402) loss: 0.8318 (0.8328) time: 0.1488 data: 0.0498 max mem: 8452 +Train: [79] [5100/6250] eta: 0:03:25 lr: 0.000013 grad: 0.1455 (0.1402) loss: 0.8200 (0.8328) time: 0.1654 data: 0.0004 max mem: 8452 +Train: [79] [5200/6250] eta: 0:03:07 lr: 0.000013 grad: 0.1318 (0.1401) loss: 0.8404 (0.8328) time: 0.1588 data: 0.0937 max mem: 8452 +Train: [79] [5300/6250] eta: 0:02:49 lr: 0.000013 grad: 0.1380 (0.1400) loss: 0.8281 (0.8328) time: 0.2001 data: 0.1190 max mem: 8452 +Train: [79] [5400/6250] eta: 0:02:30 lr: 0.000013 grad: 0.1232 (0.1399) loss: 0.8482 (0.8328) time: 0.1657 data: 0.0829 max mem: 8452 +Train: [79] [5500/6250] eta: 0:02:12 lr: 0.000013 grad: 0.1246 (0.1398) loss: 0.8335 (0.8328) time: 0.1856 data: 0.1031 max mem: 8452 +Train: [79] [5600/6250] eta: 0:01:55 lr: 0.000013 grad: 0.1350 (0.1397) loss: 0.8384 (0.8329) time: 0.1725 data: 0.0851 max mem: 8452 +Train: [79] [5700/6250] eta: 0:01:37 lr: 0.000013 grad: 0.1253 (0.1396) loss: 0.8471 (0.8330) time: 0.1188 data: 0.0005 max mem: 8452 +Train: [79] [5800/6250] eta: 0:01:19 lr: 0.000013 grad: 0.1331 (0.1395) loss: 0.8399 (0.8331) time: 0.1569 data: 0.0683 max mem: 8452 +Train: [79] [5900/6250] eta: 0:01:01 lr: 0.000013 grad: 0.1336 (0.1395) loss: 0.8329 (0.8331) time: 0.1558 data: 0.0789 max mem: 8452 +Train: [79] [6000/6250] eta: 0:00:44 lr: 0.000013 grad: 0.1309 (0.1395) loss: 0.8339 (0.8331) time: 0.1605 data: 0.0805 max mem: 8452 +Train: [79] [6100/6250] eta: 0:00:26 lr: 0.000013 grad: 0.1331 (0.1395) loss: 0.8395 (0.8331) time: 0.1789 data: 0.1027 max mem: 8452 +Train: [79] [6200/6250] eta: 0:00:08 lr: 0.000013 grad: 0.1319 (0.1394) loss: 0.8333 (0.8331) time: 0.1614 data: 0.0852 max mem: 8452 +Train: [79] [6249/6250] eta: 0:00:00 lr: 0.000013 grad: 0.1418 (0.1394) loss: 0.8281 (0.8331) time: 0.2034 data: 0.1181 max mem: 8452 +Train: [79] Total time: 0:18:23 (0.1766 s / it) +Averaged stats: lr: 0.000013 grad: 0.1418 (0.1394) loss: 0.8281 (0.8331) +Eval (hcp-train-subset): [79] [ 0/62] eta: 0:06:45 loss: 0.8611 (0.8611) time: 6.5480 data: 6.5207 max mem: 8452 +Eval (hcp-train-subset): [79] [61/62] eta: 0:00:00 loss: 0.8497 (0.8517) time: 0.1154 data: 0.0944 max mem: 8452 +Eval (hcp-train-subset): [79] Total time: 0:00:15 (0.2482 s / it) +Averaged stats (hcp-train-subset): loss: 0.8497 (0.8517) +Making plots (hcp-train-subset): example=26 +Eval (hcp-val): [79] [ 0/62] eta: 0:05:31 loss: 0.8630 (0.8630) time: 5.3512 data: 5.2891 max mem: 8452 +Eval (hcp-val): [79] [61/62] eta: 0:00:00 loss: 0.8667 (0.8685) time: 0.1508 data: 0.1294 max mem: 8452 +Eval (hcp-val): [79] Total time: 0:00:15 (0.2431 s / it) +Averaged stats (hcp-val): loss: 0.8667 (0.8685) +Making plots (hcp-val): example=1 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-00079.pth +Train: [80] [ 0/6250] eta: 8:39:58 lr: 0.000013 grad: 0.0807 (0.0807) loss: 0.8766 (0.8766) time: 4.9917 data: 4.7164 max mem: 8452 +Train: [80] [ 100/6250] eta: 0:23:58 lr: 0.000013 grad: 0.1612 (0.1835) loss: 0.8494 (0.8523) time: 0.1864 data: 0.0774 max mem: 8452 +Train: [80] [ 200/6250] eta: 0:21:11 lr: 0.000013 grad: 0.1573 (0.1757) loss: 0.8419 (0.8447) time: 0.1864 data: 0.0810 max mem: 8452 +Train: [80] [ 300/6250] eta: 0:19:39 lr: 0.000013 grad: 0.1484 (0.1680) loss: 0.8324 (0.8417) time: 0.1798 data: 0.0896 max mem: 8452 +Train: [80] [ 400/6250] eta: 0:18:57 lr: 0.000013 grad: 0.1391 (0.1620) loss: 0.8324 (0.8407) time: 0.1887 data: 0.1085 max mem: 8452 +Train: [80] [ 500/6250] eta: 0:18:43 lr: 0.000013 grad: 0.1443 (0.1593) loss: 0.8320 (0.8395) time: 0.2325 data: 0.1545 max mem: 8452 +Train: [80] [ 600/6250] eta: 0:17:56 lr: 0.000013 grad: 0.1421 (0.1570) loss: 0.8312 (0.8387) time: 0.1673 data: 0.0760 max mem: 8452 +Train: [80] [ 700/6250] eta: 0:17:21 lr: 0.000013 grad: 0.1468 (0.1559) loss: 0.8213 (0.8371) time: 0.1616 data: 0.0752 max mem: 8452 +Train: [80] [ 800/6250] eta: 0:16:52 lr: 0.000013 grad: 0.1419 (0.1547) loss: 0.8193 (0.8361) time: 0.1641 data: 0.0773 max mem: 8452 +Train: [80] [ 900/6250] eta: 0:16:24 lr: 0.000013 grad: 0.1459 (0.1539) loss: 0.8232 (0.8353) time: 0.1667 data: 0.0783 max mem: 8452 +Train: [80] [1000/6250] eta: 0:15:54 lr: 0.000013 grad: 0.1335 (0.1528) loss: 0.8291 (0.8348) time: 0.1441 data: 0.0589 max mem: 8452 +Train: [80] [1100/6250] eta: 0:15:31 lr: 0.000013 grad: 0.1351 (0.1517) loss: 0.8260 (0.8345) time: 0.2176 data: 0.1330 max mem: 8452 +Train: [80] [1200/6250] eta: 0:14:59 lr: 0.000013 grad: 0.1440 (0.1505) loss: 0.8209 (0.8343) time: 0.1696 data: 0.0922 max mem: 8452 +Train: [80] [1300/6250] eta: 0:14:52 lr: 0.000013 grad: 0.1424 (0.1500) loss: 0.8275 (0.8340) time: 0.2035 data: 0.1095 max mem: 8452 +Train: [80] [1400/6250] eta: 0:14:35 lr: 0.000013 grad: 0.1366 (0.1493) loss: 0.8341 (0.8338) time: 0.3155 data: 0.2031 max mem: 8452 +Train: [80] [1500/6250] eta: 0:14:12 lr: 0.000013 grad: 0.1435 (0.1487) loss: 0.8268 (0.8334) time: 0.2031 data: 0.1193 max mem: 8452 +Train: [80] [1600/6250] eta: 0:13:52 lr: 0.000013 grad: 0.1370 (0.1481) loss: 0.8333 (0.8332) time: 0.1997 data: 0.1073 max mem: 8452 +Train: [80] [1700/6250] eta: 0:13:36 lr: 0.000013 grad: 0.1342 (0.1476) loss: 0.8321 (0.8331) time: 0.1594 data: 0.0749 max mem: 8452 +Train: [80] [1800/6250] eta: 0:13:16 lr: 0.000013 grad: 0.1337 (0.1471) loss: 0.8280 (0.8331) time: 0.1677 data: 0.0860 max mem: 8452 +Train: [80] [1900/6250] eta: 0:12:58 lr: 0.000013 grad: 0.1389 (0.1468) loss: 0.8272 (0.8330) time: 0.1482 data: 0.0300 max mem: 8452 +Train: [80] [2000/6250] eta: 0:12:41 lr: 0.000013 grad: 0.1320 (0.1465) loss: 0.8351 (0.8330) time: 0.1712 data: 0.0905 max mem: 8452 +Train: [80] [2100/6250] eta: 0:12:20 lr: 0.000013 grad: 0.1404 (0.1463) loss: 0.8378 (0.8331) time: 0.2043 data: 0.1285 max mem: 8452 +Train: [80] [2200/6250] eta: 0:11:58 lr: 0.000013 grad: 0.1424 (0.1461) loss: 0.8242 (0.8330) time: 0.1774 data: 0.0885 max mem: 8452 +Train: [80] [2300/6250] eta: 0:11:38 lr: 0.000013 grad: 0.1443 (0.1460) loss: 0.8353 (0.8330) time: 0.1743 data: 0.1027 max mem: 8452 +Train: [80] [2400/6250] eta: 0:11:19 lr: 0.000013 grad: 0.1394 (0.1459) loss: 0.8356 (0.8330) time: 0.1522 data: 0.0692 max mem: 8452 +Train: [80] [2500/6250] eta: 0:10:59 lr: 0.000013 grad: 0.1445 (0.1459) loss: 0.8280 (0.8328) time: 0.1700 data: 0.0920 max mem: 8452 +Train: [80] [2600/6250] eta: 0:10:40 lr: 0.000013 grad: 0.1430 (0.1458) loss: 0.8247 (0.8327) time: 0.1732 data: 0.0969 max mem: 8452 +Train: [80] [2700/6250] eta: 0:10:19 lr: 0.000013 grad: 0.1397 (0.1456) loss: 0.8336 (0.8326) time: 0.1603 data: 0.0833 max mem: 8452 +Train: [80] [2800/6250] eta: 0:10:00 lr: 0.000013 grad: 0.1374 (0.1454) loss: 0.8361 (0.8326) time: 0.1527 data: 0.0764 max mem: 8452 +Train: [80] [2900/6250] eta: 0:09:42 lr: 0.000013 grad: 0.1431 (0.1452) loss: 0.8312 (0.8326) time: 0.1820 data: 0.0967 max mem: 8452 +Train: [80] [3000/6250] eta: 0:09:25 lr: 0.000013 grad: 0.1434 (0.1452) loss: 0.8334 (0.8326) time: 0.1411 data: 0.0449 max mem: 8452 +Train: [80] [3100/6250] eta: 0:09:09 lr: 0.000013 grad: 0.1428 (0.1450) loss: 0.8366 (0.8325) time: 0.2643 data: 0.1639 max mem: 8452 +Train: [80] [3200/6250] eta: 0:08:52 lr: 0.000013 grad: 0.1424 (0.1451) loss: 0.8349 (0.8325) time: 0.1559 data: 0.0707 max mem: 8452 +Train: [80] [3300/6250] eta: 0:08:33 lr: 0.000013 grad: 0.1385 (0.1449) loss: 0.8296 (0.8326) time: 0.1571 data: 0.0788 max mem: 8452 +Train: [80] [3400/6250] eta: 0:08:19 lr: 0.000012 grad: 0.1437 (0.1448) loss: 0.8367 (0.8326) time: 0.1737 data: 0.0842 max mem: 8452 +Train: [80] [3500/6250] eta: 0:08:00 lr: 0.000012 grad: 0.1323 (0.1447) loss: 0.8317 (0.8326) time: 0.1624 data: 0.0733 max mem: 8452 +Train: [80] [3600/6250] eta: 0:07:42 lr: 0.000012 grad: 0.1480 (0.1447) loss: 0.8333 (0.8325) time: 0.1817 data: 0.1135 max mem: 8452 +Train: [80] [3700/6250] eta: 0:07:24 lr: 0.000012 grad: 0.1434 (0.1446) loss: 0.8203 (0.8325) time: 0.1479 data: 0.0695 max mem: 8452 +Train: [80] [3800/6250] eta: 0:07:06 lr: 0.000012 grad: 0.1368 (0.1445) loss: 0.8313 (0.8324) time: 0.1556 data: 0.0728 max mem: 8452 +Train: [80] [3900/6250] eta: 0:06:48 lr: 0.000012 grad: 0.1380 (0.1445) loss: 0.8326 (0.8325) time: 0.1622 data: 0.0731 max mem: 8452 +Train: [80] [4000/6250] eta: 0:06:30 lr: 0.000012 grad: 0.1371 (0.1444) loss: 0.8262 (0.8324) time: 0.1534 data: 0.0613 max mem: 8452 +Train: [80] [4100/6250] eta: 0:06:11 lr: 0.000012 grad: 0.1347 (0.1443) loss: 0.8325 (0.8324) time: 0.1655 data: 0.0858 max mem: 8452 +Train: [80] [4200/6250] eta: 0:05:53 lr: 0.000012 grad: 0.1325 (0.1441) loss: 0.8247 (0.8324) time: 0.1617 data: 0.0758 max mem: 8452 +Train: [80] [4300/6250] eta: 0:05:34 lr: 0.000012 grad: 0.1330 (0.1439) loss: 0.8300 (0.8324) time: 0.1358 data: 0.0401 max mem: 8452 +Train: [80] [4400/6250] eta: 0:05:16 lr: 0.000012 grad: 0.1354 (0.1438) loss: 0.8349 (0.8324) time: 0.1583 data: 0.0771 max mem: 8452 +Train: [80] [4500/6250] eta: 0:04:58 lr: 0.000012 grad: 0.1412 (0.1437) loss: 0.8315 (0.8324) time: 0.1485 data: 0.0563 max mem: 8452 +Train: [80] [4600/6250] eta: 0:04:41 lr: 0.000012 grad: 0.1389 (0.1436) loss: 0.8267 (0.8325) time: 0.1553 data: 0.0775 max mem: 8452 +Train: [80] [4700/6250] eta: 0:04:25 lr: 0.000012 grad: 0.1436 (0.1435) loss: 0.8277 (0.8325) time: 0.1141 data: 0.0003 max mem: 8452 +Train: [80] [4800/6250] eta: 0:04:07 lr: 0.000012 grad: 0.1435 (0.1435) loss: 0.8291 (0.8325) time: 0.1548 data: 0.0850 max mem: 8452 +Train: [80] [4900/6250] eta: 0:03:51 lr: 0.000012 grad: 0.1269 (0.1434) loss: 0.8328 (0.8325) time: 0.2557 data: 0.1723 max mem: 8452 +Train: [80] [5000/6250] eta: 0:03:33 lr: 0.000012 grad: 0.1325 (0.1433) loss: 0.8351 (0.8326) time: 0.1633 data: 0.0801 max mem: 8452 +Train: [80] [5100/6250] eta: 0:03:16 lr: 0.000012 grad: 0.1412 (0.1432) loss: 0.8325 (0.8327) time: 0.1644 data: 0.0828 max mem: 8452 +Train: [80] [5200/6250] eta: 0:02:59 lr: 0.000012 grad: 0.1338 (0.1431) loss: 0.8353 (0.8327) time: 0.1723 data: 0.0901 max mem: 8452 +Train: [80] [5300/6250] eta: 0:02:42 lr: 0.000012 grad: 0.1311 (0.1430) loss: 0.8348 (0.8327) time: 0.1529 data: 0.0818 max mem: 8452 +Train: [80] [5400/6250] eta: 0:02:24 lr: 0.000012 grad: 0.1306 (0.1430) loss: 0.8341 (0.8327) time: 0.1833 data: 0.1117 max mem: 8452 +Train: [80] [5500/6250] eta: 0:02:07 lr: 0.000012 grad: 0.1340 (0.1429) loss: 0.8330 (0.8327) time: 0.1482 data: 0.0691 max mem: 8452 +Train: [80] [5600/6250] eta: 0:01:50 lr: 0.000012 grad: 0.1386 (0.1428) loss: 0.8260 (0.8326) time: 0.1609 data: 0.0825 max mem: 8452 +Train: [80] [5700/6250] eta: 0:01:33 lr: 0.000012 grad: 0.1399 (0.1428) loss: 0.8272 (0.8325) time: 0.1696 data: 0.0925 max mem: 8452 +Train: [80] [5800/6250] eta: 0:01:16 lr: 0.000012 grad: 0.1398 (0.1428) loss: 0.8328 (0.8325) time: 0.2425 data: 0.1552 max mem: 8452 +Train: [80] [5900/6250] eta: 0:00:59 lr: 0.000012 grad: 0.1495 (0.1429) loss: 0.8169 (0.8323) time: 0.1645 data: 0.0843 max mem: 8452 +Train: [80] [6000/6250] eta: 0:00:42 lr: 0.000012 grad: 0.1409 (0.1430) loss: 0.8276 (0.8323) time: 0.1837 data: 0.0954 max mem: 8452 +Train: [80] [6100/6250] eta: 0:00:25 lr: 0.000012 grad: 0.1432 (0.1430) loss: 0.8281 (0.8322) time: 0.1443 data: 0.0547 max mem: 8452 +Train: [80] [6200/6250] eta: 0:00:08 lr: 0.000012 grad: 0.1451 (0.1430) loss: 0.8230 (0.8322) time: 0.1639 data: 0.0851 max mem: 8452 +Train: [80] [6249/6250] eta: 0:00:00 lr: 0.000012 grad: 0.1368 (0.1431) loss: 0.8333 (0.8322) time: 0.1617 data: 0.0746 max mem: 8452 +Train: [80] Total time: 0:17:48 (0.1710 s / it) +Averaged stats: lr: 0.000012 grad: 0.1368 (0.1431) loss: 0.8333 (0.8322) +Eval (hcp-train-subset): [80] [ 0/62] eta: 0:06:12 loss: 0.8577 (0.8577) time: 6.0155 data: 5.9873 max mem: 8452 +Eval (hcp-train-subset): [80] [61/62] eta: 0:00:00 loss: 0.8469 (0.8494) time: 0.1318 data: 0.1095 max mem: 8452 +Eval (hcp-train-subset): [80] Total time: 0:00:15 (0.2491 s / it) +Averaged stats (hcp-train-subset): loss: 0.8469 (0.8494) +Eval (hcp-val): [80] [ 0/62] eta: 0:06:04 loss: 0.8659 (0.8659) time: 5.8785 data: 5.8494 max mem: 8452 +Eval (hcp-val): [80] [61/62] eta: 0:00:00 loss: 0.8675 (0.8680) time: 0.1382 data: 0.1157 max mem: 8452 +Eval (hcp-val): [80] Total time: 0:00:15 (0.2493 s / it) +Averaged stats (hcp-val): loss: 0.8675 (0.8680) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [81] [ 0/6250] eta: 11:42:19 lr: 0.000012 grad: 0.4531 (0.4531) loss: 0.8571 (0.8571) time: 6.7422 data: 6.5952 max mem: 8452 +Train: [81] [ 100/6250] eta: 0:23:23 lr: 0.000012 grad: 0.1432 (0.2040) loss: 0.8555 (0.8380) time: 0.1935 data: 0.0896 max mem: 8452 +Train: [81] [ 200/6250] eta: 0:20:14 lr: 0.000012 grad: 0.1289 (0.1784) loss: 0.8390 (0.8389) time: 0.1631 data: 0.0595 max mem: 8452 +Train: [81] [ 300/6250] eta: 0:18:50 lr: 0.000012 grad: 0.1611 (0.1678) loss: 0.8351 (0.8386) time: 0.1561 data: 0.0553 max mem: 8452 +Train: [81] [ 400/6250] eta: 0:18:06 lr: 0.000012 grad: 0.1489 (0.1643) loss: 0.8199 (0.8364) time: 0.1973 data: 0.0995 max mem: 8452 +Train: [81] [ 500/6250] eta: 0:17:37 lr: 0.000012 grad: 0.1580 (0.1617) loss: 0.8219 (0.8346) time: 0.1124 data: 0.0227 max mem: 8452 +Train: [81] [ 600/6250] eta: 0:16:59 lr: 0.000012 grad: 0.1427 (0.1599) loss: 0.8330 (0.8337) time: 0.1522 data: 0.0772 max mem: 8452 +Train: [81] [ 700/6250] eta: 0:16:41 lr: 0.000012 grad: 0.1477 (0.1583) loss: 0.8206 (0.8330) time: 0.1985 data: 0.1158 max mem: 8452 +Train: [81] [ 800/6250] eta: 0:16:22 lr: 0.000012 grad: 0.1382 (0.1570) loss: 0.8338 (0.8327) time: 0.1892 data: 0.0939 max mem: 8452 +Train: [81] [ 900/6250] eta: 0:16:02 lr: 0.000012 grad: 0.1395 (0.1561) loss: 0.8192 (0.8320) time: 0.1761 data: 0.0886 max mem: 8452 +Train: [81] [1000/6250] eta: 0:15:36 lr: 0.000012 grad: 0.1397 (0.1553) loss: 0.8288 (0.8316) time: 0.1745 data: 0.0771 max mem: 8452 +Train: [81] [1100/6250] eta: 0:15:06 lr: 0.000012 grad: 0.1398 (0.1541) loss: 0.8279 (0.8311) time: 0.1580 data: 0.0731 max mem: 8452 +Train: [81] [1200/6250] eta: 0:14:44 lr: 0.000012 grad: 0.1376 (0.1532) loss: 0.8248 (0.8310) time: 0.1487 data: 0.0707 max mem: 8452 +Train: [81] [1300/6250] eta: 0:14:19 lr: 0.000012 grad: 0.1410 (0.1527) loss: 0.8264 (0.8306) time: 0.1541 data: 0.0776 max mem: 8452 +Train: [81] [1400/6250] eta: 0:13:57 lr: 0.000012 grad: 0.1432 (0.1523) loss: 0.8290 (0.8303) time: 0.1713 data: 0.0933 max mem: 8452 +Train: [81] [1500/6250] eta: 0:13:42 lr: 0.000012 grad: 0.1471 (0.1518) loss: 0.8224 (0.8300) time: 0.1702 data: 0.0931 max mem: 8452 +Train: [81] [1600/6250] eta: 0:13:24 lr: 0.000012 grad: 0.1422 (0.1513) loss: 0.8211 (0.8299) time: 0.1574 data: 0.0795 max mem: 8452 +Train: [81] [1700/6250] eta: 0:13:02 lr: 0.000012 grad: 0.1402 (0.1510) loss: 0.8293 (0.8297) time: 0.1550 data: 0.0760 max mem: 8452 +Train: [81] [1800/6250] eta: 0:12:44 lr: 0.000012 grad: 0.1459 (0.1507) loss: 0.8259 (0.8295) time: 0.1746 data: 0.1055 max mem: 8452 +Train: [81] [1900/6250] eta: 0:12:27 lr: 0.000012 grad: 0.1371 (0.1503) loss: 0.8368 (0.8294) time: 0.1740 data: 0.0920 max mem: 8452 +Train: [81] [2000/6250] eta: 0:12:18 lr: 0.000012 grad: 0.1455 (0.1501) loss: 0.8132 (0.8294) time: 0.3311 data: 0.2386 max mem: 8452 +Train: [81] [2100/6250] eta: 0:11:58 lr: 0.000012 grad: 0.1365 (0.1498) loss: 0.8278 (0.8293) time: 0.1705 data: 0.0836 max mem: 8452 +Train: [81] [2200/6250] eta: 0:11:43 lr: 0.000012 grad: 0.1396 (0.1495) loss: 0.8309 (0.8294) time: 0.1166 data: 0.0004 max mem: 8452 +Train: [81] [2300/6250] eta: 0:11:28 lr: 0.000011 grad: 0.1392 (0.1491) loss: 0.8305 (0.8294) time: 0.1147 data: 0.0003 max mem: 8452 +Train: [81] [2400/6250] eta: 0:11:11 lr: 0.000011 grad: 0.1429 (0.1489) loss: 0.8348 (0.8294) time: 0.1813 data: 0.0959 max mem: 8452 +Train: [81] [2500/6250] eta: 0:11:04 lr: 0.000011 grad: 0.1456 (0.1487) loss: 0.8294 (0.8295) time: 0.5364 data: 0.4412 max mem: 8452 +Train: [81] [2600/6250] eta: 0:10:42 lr: 0.000011 grad: 0.1369 (0.1485) loss: 0.8281 (0.8294) time: 0.1623 data: 0.0805 max mem: 8452 +Train: [81] [2700/6250] eta: 0:10:22 lr: 0.000011 grad: 0.1423 (0.1482) loss: 0.8348 (0.8296) time: 0.1414 data: 0.0700 max mem: 8452 +Train: [81] [2800/6250] eta: 0:10:02 lr: 0.000011 grad: 0.1385 (0.1479) loss: 0.8322 (0.8297) time: 0.1469 data: 0.0642 max mem: 8452 +Train: [81] [2900/6250] eta: 0:09:43 lr: 0.000011 grad: 0.1369 (0.1476) loss: 0.8321 (0.8298) time: 0.1568 data: 0.0842 max mem: 8452 +Train: [81] [3000/6250] eta: 0:09:24 lr: 0.000011 grad: 0.1327 (0.1473) loss: 0.8373 (0.8299) time: 0.1622 data: 0.0844 max mem: 8452 +Train: [81] [3100/6250] eta: 0:09:05 lr: 0.000011 grad: 0.1410 (0.1472) loss: 0.8353 (0.8301) time: 0.1605 data: 0.0755 max mem: 8452 +Train: [81] [3200/6250] eta: 0:08:46 lr: 0.000011 grad: 0.1326 (0.1470) loss: 0.8358 (0.8304) time: 0.1665 data: 0.0865 max mem: 8452 +Train: [81] [3300/6250] eta: 0:08:27 lr: 0.000011 grad: 0.1433 (0.1470) loss: 0.8260 (0.8305) time: 0.1795 data: 0.0911 max mem: 8452 +Train: [81] [3400/6250] eta: 0:08:10 lr: 0.000011 grad: 0.1356 (0.1468) loss: 0.8386 (0.8306) time: 0.1605 data: 0.0777 max mem: 8452 +Train: [81] [3500/6250] eta: 0:07:52 lr: 0.000011 grad: 0.1350 (0.1466) loss: 0.8312 (0.8308) time: 0.1783 data: 0.0971 max mem: 8452 +Train: [81] [3600/6250] eta: 0:07:35 lr: 0.000011 grad: 0.1345 (0.1464) loss: 0.8341 (0.8309) time: 0.1553 data: 0.0843 max mem: 8452 +Train: [81] [3700/6250] eta: 0:07:17 lr: 0.000011 grad: 0.1400 (0.1463) loss: 0.8334 (0.8309) time: 0.1495 data: 0.0727 max mem: 8452 +Train: [81] [3800/6250] eta: 0:07:00 lr: 0.000011 grad: 0.1423 (0.1461) loss: 0.8305 (0.8310) time: 0.1681 data: 0.0931 max mem: 8452 +Train: [81] [3900/6250] eta: 0:06:43 lr: 0.000011 grad: 0.1397 (0.1461) loss: 0.8307 (0.8311) time: 0.1891 data: 0.0950 max mem: 8452 +Train: [81] [4000/6250] eta: 0:06:25 lr: 0.000011 grad: 0.1418 (0.1461) loss: 0.8357 (0.8311) time: 0.1629 data: 0.0804 max mem: 8452 +Train: [81] [4100/6250] eta: 0:06:08 lr: 0.000011 grad: 0.1345 (0.1460) loss: 0.8340 (0.8311) time: 0.1835 data: 0.1079 max mem: 8452 +Train: [81] [4200/6250] eta: 0:05:50 lr: 0.000011 grad: 0.1476 (0.1460) loss: 0.8253 (0.8311) time: 0.1504 data: 0.0637 max mem: 8452 +Train: [81] [4300/6250] eta: 0:05:32 lr: 0.000011 grad: 0.1362 (0.1459) loss: 0.8358 (0.8311) time: 0.1639 data: 0.0715 max mem: 8452 +Train: [81] [4400/6250] eta: 0:05:14 lr: 0.000011 grad: 0.1396 (0.1459) loss: 0.8307 (0.8311) time: 0.1449 data: 0.0577 max mem: 8452 +Train: [81] [4500/6250] eta: 0:04:56 lr: 0.000011 grad: 0.1343 (0.1458) loss: 0.8366 (0.8311) time: 0.1311 data: 0.0526 max mem: 8452 +Train: [81] [4600/6250] eta: 0:04:39 lr: 0.000011 grad: 0.1399 (0.1458) loss: 0.8236 (0.8310) time: 0.1784 data: 0.1009 max mem: 8452 +Train: [81] [4700/6250] eta: 0:04:21 lr: 0.000011 grad: 0.1364 (0.1458) loss: 0.8359 (0.8310) time: 0.1720 data: 0.0956 max mem: 8452 +Train: [81] [4800/6250] eta: 0:04:05 lr: 0.000011 grad: 0.1371 (0.1458) loss: 0.8358 (0.8309) time: 0.1618 data: 0.0868 max mem: 8452 +Train: [81] [4900/6250] eta: 0:03:48 lr: 0.000011 grad: 0.1451 (0.1457) loss: 0.8222 (0.8309) time: 0.1719 data: 0.0888 max mem: 8452 +Train: [81] [5000/6250] eta: 0:03:33 lr: 0.000011 grad: 0.1391 (0.1455) loss: 0.8321 (0.8310) time: 0.4192 data: 0.2880 max mem: 8452 +Train: [81] [5100/6250] eta: 0:03:17 lr: 0.000011 grad: 0.1320 (0.1454) loss: 0.8321 (0.8310) time: 0.2026 data: 0.0840 max mem: 8452 +Train: [81] [5200/6250] eta: 0:03:00 lr: 0.000011 grad: 0.1372 (0.1454) loss: 0.8336 (0.8310) time: 0.1591 data: 0.0518 max mem: 8452 +Train: [81] [5300/6250] eta: 0:02:42 lr: 0.000011 grad: 0.1338 (0.1454) loss: 0.8386 (0.8310) time: 0.1916 data: 0.1062 max mem: 8452 +Train: [81] [5400/6250] eta: 0:02:25 lr: 0.000011 grad: 0.1321 (0.1452) loss: 0.8307 (0.8310) time: 0.1471 data: 0.0703 max mem: 8452 +Train: [81] [5500/6250] eta: 0:02:08 lr: 0.000011 grad: 0.1332 (0.1452) loss: 0.8390 (0.8310) time: 0.2054 data: 0.1251 max mem: 8452 +Train: [81] [5600/6250] eta: 0:01:51 lr: 0.000011 grad: 0.1300 (0.1450) loss: 0.8349 (0.8311) time: 0.1799 data: 0.0924 max mem: 8452 +Train: [81] [5700/6250] eta: 0:01:34 lr: 0.000011 grad: 0.1485 (0.1451) loss: 0.8319 (0.8311) time: 0.1925 data: 0.0885 max mem: 8452 +Train: [81] [5800/6250] eta: 0:01:17 lr: 0.000011 grad: 0.1375 (0.1450) loss: 0.8404 (0.8311) time: 0.1864 data: 0.1019 max mem: 8452 +Train: [81] [5900/6250] eta: 0:01:00 lr: 0.000011 grad: 0.1358 (0.1450) loss: 0.8317 (0.8311) time: 0.1893 data: 0.1045 max mem: 8452 +Train: [81] [6000/6250] eta: 0:00:42 lr: 0.000011 grad: 0.1376 (0.1449) loss: 0.8369 (0.8312) time: 0.1519 data: 0.0649 max mem: 8452 +Train: [81] [6100/6250] eta: 0:00:25 lr: 0.000011 grad: 0.1446 (0.1449) loss: 0.8380 (0.8313) time: 0.1032 data: 0.0003 max mem: 8452 +Train: [81] [6200/6250] eta: 0:00:08 lr: 0.000011 grad: 0.1428 (0.1448) loss: 0.8296 (0.8313) time: 0.1572 data: 0.0673 max mem: 8452 +Train: [81] [6249/6250] eta: 0:00:00 lr: 0.000011 grad: 0.1518 (0.1449) loss: 0.8267 (0.8313) time: 0.1906 data: 0.1052 max mem: 8452 +Train: [81] Total time: 0:18:02 (0.1732 s / it) +Averaged stats: lr: 0.000011 grad: 0.1518 (0.1449) loss: 0.8267 (0.8313) +Eval (hcp-train-subset): [81] [ 0/62] eta: 0:04:19 loss: 0.8578 (0.8578) time: 4.1875 data: 4.0907 max mem: 8452 +Eval (hcp-train-subset): [81] [61/62] eta: 0:00:00 loss: 0.8478 (0.8486) time: 0.1458 data: 0.1246 max mem: 8452 +Eval (hcp-train-subset): [81] Total time: 0:00:15 (0.2467 s / it) +Averaged stats (hcp-train-subset): loss: 0.8478 (0.8486) +Eval (hcp-val): [81] [ 0/62] eta: 0:05:09 loss: 0.8639 (0.8639) time: 4.9949 data: 4.9293 max mem: 8452 +Eval (hcp-val): [81] [61/62] eta: 0:00:00 loss: 0.8674 (0.8682) time: 0.1621 data: 0.1409 max mem: 8452 +Eval (hcp-val): [81] Total time: 0:00:15 (0.2562 s / it) +Averaged stats (hcp-val): loss: 0.8674 (0.8682) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [82] [ 0/6250] eta: 9:28:20 lr: 0.000011 grad: 0.1012 (0.1012) loss: 0.8880 (0.8880) time: 5.4562 data: 5.0550 max mem: 8452 +Train: [82] [ 100/6250] eta: 0:25:12 lr: 0.000011 grad: 0.1753 (0.1997) loss: 0.8413 (0.8482) time: 0.1774 data: 0.0703 max mem: 8452 +Train: [82] [ 200/6250] eta: 0:21:21 lr: 0.000011 grad: 0.1510 (0.1832) loss: 0.8310 (0.8420) time: 0.1626 data: 0.0589 max mem: 8452 +Train: [82] [ 300/6250] eta: 0:19:46 lr: 0.000011 grad: 0.1545 (0.1754) loss: 0.8230 (0.8400) time: 0.2039 data: 0.0978 max mem: 8452 +Train: [82] [ 400/6250] eta: 0:19:04 lr: 0.000011 grad: 0.1499 (0.1707) loss: 0.8391 (0.8379) time: 0.1775 data: 0.0826 max mem: 8452 +Train: [82] [ 500/6250] eta: 0:18:24 lr: 0.000011 grad: 0.1457 (0.1681) loss: 0.8423 (0.8367) time: 0.1629 data: 0.0799 max mem: 8452 +Train: [82] [ 600/6250] eta: 0:17:41 lr: 0.000011 grad: 0.1460 (0.1651) loss: 0.8383 (0.8371) time: 0.1660 data: 0.0803 max mem: 8452 +Train: [82] [ 700/6250] eta: 0:17:00 lr: 0.000011 grad: 0.1389 (0.1624) loss: 0.8344 (0.8372) time: 0.1614 data: 0.0663 max mem: 8452 +Train: [82] [ 800/6250] eta: 0:16:34 lr: 0.000011 grad: 0.1412 (0.1602) loss: 0.8392 (0.8372) time: 0.1225 data: 0.0221 max mem: 8452 +Train: [82] [ 900/6250] eta: 0:16:06 lr: 0.000011 grad: 0.1368 (0.1586) loss: 0.8388 (0.8369) time: 0.1684 data: 0.0739 max mem: 8452 +Train: [82] [1000/6250] eta: 0:15:37 lr: 0.000011 grad: 0.1448 (0.1577) loss: 0.8257 (0.8361) time: 0.1483 data: 0.0550 max mem: 8452 +Train: [82] [1100/6250] eta: 0:15:05 lr: 0.000011 grad: 0.1438 (0.1569) loss: 0.8275 (0.8352) time: 0.1301 data: 0.0345 max mem: 8452 +Train: [82] [1200/6250] eta: 0:14:35 lr: 0.000011 grad: 0.1420 (0.1562) loss: 0.8273 (0.8344) time: 0.1492 data: 0.0664 max mem: 8452 +Train: [82] [1300/6250] eta: 0:14:10 lr: 0.000011 grad: 0.1404 (0.1553) loss: 0.8292 (0.8339) time: 0.1543 data: 0.0716 max mem: 8452 +Train: [82] [1400/6250] eta: 0:13:58 lr: 0.000010 grad: 0.1507 (0.1549) loss: 0.8306 (0.8336) time: 0.2040 data: 0.1175 max mem: 8452 +Train: [82] [1500/6250] eta: 0:13:39 lr: 0.000010 grad: 0.1404 (0.1544) loss: 0.8256 (0.8332) time: 0.1816 data: 0.0937 max mem: 8452 +Train: [82] [1600/6250] eta: 0:13:29 lr: 0.000010 grad: 0.1352 (0.1537) loss: 0.8328 (0.8331) time: 0.1231 data: 0.0078 max mem: 8452 +Train: [82] [1700/6250] eta: 0:13:28 lr: 0.000010 grad: 0.1386 (0.1529) loss: 0.8322 (0.8330) time: 0.3508 data: 0.2319 max mem: 8452 +Train: [82] [1800/6250] eta: 0:13:03 lr: 0.000010 grad: 0.1332 (0.1521) loss: 0.8397 (0.8332) time: 0.1590 data: 0.0922 max mem: 8452 +Train: [82] [1900/6250] eta: 0:12:48 lr: 0.000010 grad: 0.1302 (0.1514) loss: 0.8340 (0.8333) time: 0.1971 data: 0.1025 max mem: 8452 +Train: [82] [2000/6250] eta: 0:12:33 lr: 0.000010 grad: 0.1446 (0.1509) loss: 0.8280 (0.8334) time: 0.1758 data: 0.0974 max mem: 8452 +Train: [82] [2100/6250] eta: 0:12:18 lr: 0.000010 grad: 0.1450 (0.1505) loss: 0.8319 (0.8332) time: 0.1331 data: 0.0005 max mem: 8452 +Train: [82] [2200/6250] eta: 0:11:58 lr: 0.000010 grad: 0.1380 (0.1503) loss: 0.8250 (0.8331) time: 0.1547 data: 0.0722 max mem: 8452 +Train: [82] [2300/6250] eta: 0:11:37 lr: 0.000010 grad: 0.1397 (0.1500) loss: 0.8240 (0.8329) time: 0.1469 data: 0.0594 max mem: 8452 +Train: [82] [2400/6250] eta: 0:11:17 lr: 0.000010 grad: 0.1436 (0.1497) loss: 0.8333 (0.8328) time: 0.1562 data: 0.0874 max mem: 8452 +Train: [82] [2500/6250] eta: 0:11:00 lr: 0.000010 grad: 0.1426 (0.1497) loss: 0.8190 (0.8326) time: 0.2200 data: 0.1436 max mem: 8452 +Train: [82] [2600/6250] eta: 0:10:41 lr: 0.000010 grad: 0.1403 (0.1494) loss: 0.8249 (0.8324) time: 0.1943 data: 0.1048 max mem: 8452 +Train: [82] [2700/6250] eta: 0:10:21 lr: 0.000010 grad: 0.1423 (0.1493) loss: 0.8354 (0.8321) time: 0.1433 data: 0.0581 max mem: 8452 +Train: [82] [2800/6250] eta: 0:10:02 lr: 0.000010 grad: 0.1374 (0.1492) loss: 0.8304 (0.8320) time: 0.1577 data: 0.0761 max mem: 8452 +Train: [82] [2900/6250] eta: 0:09:43 lr: 0.000010 grad: 0.1458 (0.1493) loss: 0.8231 (0.8319) time: 0.1496 data: 0.0609 max mem: 8452 +Train: [82] [3000/6250] eta: 0:09:24 lr: 0.000010 grad: 0.1407 (0.1491) loss: 0.8296 (0.8319) time: 0.1287 data: 0.0498 max mem: 8452 +Train: [82] [3100/6250] eta: 0:09:06 lr: 0.000010 grad: 0.1457 (0.1490) loss: 0.8311 (0.8319) time: 0.1688 data: 0.0860 max mem: 8452 +Train: [82] [3200/6250] eta: 0:08:46 lr: 0.000010 grad: 0.1430 (0.1490) loss: 0.8320 (0.8319) time: 0.1424 data: 0.0645 max mem: 8452 +Train: [82] [3300/6250] eta: 0:08:28 lr: 0.000010 grad: 0.1444 (0.1487) loss: 0.8324 (0.8319) time: 0.1612 data: 0.0843 max mem: 8452 +Train: [82] [3400/6250] eta: 0:08:11 lr: 0.000010 grad: 0.1439 (0.1486) loss: 0.8242 (0.8319) time: 0.1549 data: 0.0801 max mem: 8452 +Train: [82] [3500/6250] eta: 0:07:53 lr: 0.000010 grad: 0.1378 (0.1485) loss: 0.8286 (0.8318) time: 0.1559 data: 0.0740 max mem: 8452 +Train: [82] [3600/6250] eta: 0:07:35 lr: 0.000010 grad: 0.1340 (0.1483) loss: 0.8319 (0.8318) time: 0.1629 data: 0.0903 max mem: 8452 +Train: [82] [3700/6250] eta: 0:07:18 lr: 0.000010 grad: 0.1370 (0.1481) loss: 0.8329 (0.8318) time: 0.1807 data: 0.0896 max mem: 8452 +Train: [82] [3800/6250] eta: 0:07:02 lr: 0.000010 grad: 0.1342 (0.1480) loss: 0.8328 (0.8318) time: 0.2911 data: 0.1624 max mem: 8452 +Train: [82] [3900/6250] eta: 0:06:45 lr: 0.000010 grad: 0.1405 (0.1478) loss: 0.8242 (0.8318) time: 0.1773 data: 0.0843 max mem: 8452 +Train: [82] [4000/6250] eta: 0:06:28 lr: 0.000010 grad: 0.1386 (0.1477) loss: 0.8312 (0.8318) time: 0.1680 data: 0.0839 max mem: 8452 +Train: [82] [4100/6250] eta: 0:06:11 lr: 0.000010 grad: 0.1444 (0.1476) loss: 0.8311 (0.8318) time: 0.1985 data: 0.1232 max mem: 8452 +Train: [82] [4200/6250] eta: 0:05:54 lr: 0.000010 grad: 0.1367 (0.1475) loss: 0.8348 (0.8318) time: 0.1598 data: 0.0749 max mem: 8452 +Train: [82] [4300/6250] eta: 0:05:36 lr: 0.000010 grad: 0.1381 (0.1473) loss: 0.8339 (0.8318) time: 0.1374 data: 0.0181 max mem: 8452 +Train: [82] [4400/6250] eta: 0:05:19 lr: 0.000010 grad: 0.1377 (0.1471) loss: 0.8304 (0.8319) time: 0.1817 data: 0.0836 max mem: 8452 +Train: [82] [4500/6250] eta: 0:05:01 lr: 0.000010 grad: 0.1322 (0.1469) loss: 0.8356 (0.8319) time: 0.1536 data: 0.0650 max mem: 8452 +Train: [82] [4600/6250] eta: 0:04:45 lr: 0.000010 grad: 0.1505 (0.1467) loss: 0.8302 (0.8320) time: 0.1709 data: 0.0150 max mem: 8452 +Train: [82] [4700/6250] eta: 0:04:28 lr: 0.000010 grad: 0.1405 (0.1466) loss: 0.8290 (0.8320) time: 0.1823 data: 0.0892 max mem: 8452 +Train: [82] [4800/6250] eta: 0:04:11 lr: 0.000010 grad: 0.1380 (0.1465) loss: 0.8246 (0.8319) time: 0.1678 data: 0.0926 max mem: 8452 +Train: [82] [4900/6250] eta: 0:03:53 lr: 0.000010 grad: 0.1449 (0.1464) loss: 0.8300 (0.8320) time: 0.1199 data: 0.0003 max mem: 8452 +Train: [82] [5000/6250] eta: 0:03:36 lr: 0.000010 grad: 0.1358 (0.1464) loss: 0.8297 (0.8320) time: 0.1913 data: 0.0986 max mem: 8452 +Train: [82] [5100/6250] eta: 0:03:18 lr: 0.000010 grad: 0.1388 (0.1462) loss: 0.8260 (0.8320) time: 0.1666 data: 0.0929 max mem: 8452 +Train: [82] [5200/6250] eta: 0:03:01 lr: 0.000010 grad: 0.1416 (0.1462) loss: 0.8342 (0.8320) time: 0.2079 data: 0.1254 max mem: 8452 +Train: [82] [5300/6250] eta: 0:02:43 lr: 0.000010 grad: 0.1439 (0.1462) loss: 0.8363 (0.8320) time: 0.1884 data: 0.1115 max mem: 8452 +Train: [82] [5400/6250] eta: 0:02:26 lr: 0.000010 grad: 0.1447 (0.1461) loss: 0.8304 (0.8320) time: 0.1678 data: 0.0756 max mem: 8452 +Train: [82] [5500/6250] eta: 0:02:09 lr: 0.000010 grad: 0.1354 (0.1460) loss: 0.8336 (0.8319) time: 0.1640 data: 0.0528 max mem: 8452 +Train: [82] [5600/6250] eta: 0:01:52 lr: 0.000010 grad: 0.1376 (0.1460) loss: 0.8292 (0.8319) time: 0.1555 data: 0.0685 max mem: 8452 +Train: [82] [5700/6250] eta: 0:01:34 lr: 0.000010 grad: 0.1447 (0.1460) loss: 0.8288 (0.8319) time: 0.1642 data: 0.0690 max mem: 8452 +Train: [82] [5800/6250] eta: 0:01:17 lr: 0.000010 grad: 0.1449 (0.1460) loss: 0.8240 (0.8318) time: 0.1637 data: 0.0616 max mem: 8452 +Train: [82] [5900/6250] eta: 0:01:00 lr: 0.000010 grad: 0.1493 (0.1460) loss: 0.8263 (0.8318) time: 0.1677 data: 0.0799 max mem: 8452 +Train: [82] [6000/6250] eta: 0:00:43 lr: 0.000010 grad: 0.1444 (0.1460) loss: 0.8296 (0.8318) time: 0.2040 data: 0.1239 max mem: 8452 +Train: [82] [6100/6250] eta: 0:00:25 lr: 0.000010 grad: 0.1382 (0.1461) loss: 0.8261 (0.8317) time: 0.1818 data: 0.0960 max mem: 8452 +Train: [82] [6200/6250] eta: 0:00:08 lr: 0.000010 grad: 0.1397 (0.1461) loss: 0.8332 (0.8317) time: 0.2377 data: 0.1510 max mem: 8452 +Train: [82] [6249/6250] eta: 0:00:00 lr: 0.000010 grad: 0.1426 (0.1461) loss: 0.8268 (0.8317) time: 0.1695 data: 0.0867 max mem: 8452 +Train: [82] Total time: 0:18:03 (0.1734 s / it) +Averaged stats: lr: 0.000010 grad: 0.1426 (0.1461) loss: 0.8268 (0.8317) +Eval (hcp-train-subset): [82] [ 0/62] eta: 0:06:34 loss: 0.8587 (0.8587) time: 6.3584 data: 6.3316 max mem: 8452 +Eval (hcp-train-subset): [82] [61/62] eta: 0:00:00 loss: 0.8449 (0.8473) time: 0.1363 data: 0.1140 max mem: 8452 +Eval (hcp-train-subset): [82] Total time: 0:00:15 (0.2448 s / it) +Averaged stats (hcp-train-subset): loss: 0.8449 (0.8473) +Eval (hcp-val): [82] [ 0/62] eta: 0:03:52 loss: 0.8657 (0.8657) time: 3.7486 data: 3.6671 max mem: 8452 +Eval (hcp-val): [82] [61/62] eta: 0:00:00 loss: 0.8655 (0.8680) time: 0.1135 data: 0.0924 max mem: 8452 +Eval (hcp-val): [82] Total time: 0:00:14 (0.2398 s / it) +Averaged stats (hcp-val): loss: 0.8655 (0.8680) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [83] [ 0/6250] eta: 10:19:33 lr: 0.000010 grad: 0.7597 (0.7597) loss: 0.8914 (0.8914) time: 5.9477 data: 5.7833 max mem: 8452 +Train: [83] [ 100/6250] eta: 0:22:45 lr: 0.000010 grad: 0.1566 (0.1805) loss: 0.8490 (0.8556) time: 0.1709 data: 0.0597 max mem: 8452 +Train: [83] [ 200/6250] eta: 0:19:37 lr: 0.000010 grad: 0.1373 (0.1692) loss: 0.8505 (0.8490) time: 0.1461 data: 0.0438 max mem: 8452 +Train: [83] [ 300/6250] eta: 0:18:15 lr: 0.000010 grad: 0.1375 (0.1635) loss: 0.8403 (0.8451) time: 0.1604 data: 0.0724 max mem: 8452 +Train: [83] [ 400/6250] eta: 0:17:29 lr: 0.000010 grad: 0.1399 (0.1596) loss: 0.8434 (0.8437) time: 0.1790 data: 0.0835 max mem: 8452 +Train: [83] [ 500/6250] eta: 0:17:01 lr: 0.000010 grad: 0.1379 (0.1569) loss: 0.8403 (0.8436) time: 0.1681 data: 0.0697 max mem: 8452 +Train: [83] [ 600/6250] eta: 0:16:48 lr: 0.000010 grad: 0.1401 (0.1552) loss: 0.8383 (0.8432) time: 0.1680 data: 0.0734 max mem: 8452 +Train: [83] [ 700/6250] eta: 0:16:35 lr: 0.000009 grad: 0.1521 (0.1542) loss: 0.8271 (0.8418) time: 0.2062 data: 0.1011 max mem: 8452 +Train: [83] [ 800/6250] eta: 0:16:20 lr: 0.000009 grad: 0.1545 (0.1533) loss: 0.8299 (0.8406) time: 0.1532 data: 0.0578 max mem: 8452 +Train: [83] [ 900/6250] eta: 0:16:04 lr: 0.000009 grad: 0.1336 (0.1521) loss: 0.8319 (0.8397) time: 0.1858 data: 0.0943 max mem: 8452 +Train: [83] [1000/6250] eta: 0:15:35 lr: 0.000009 grad: 0.1417 (0.1513) loss: 0.8312 (0.8391) time: 0.1795 data: 0.0988 max mem: 8452 +Train: [83] [1100/6250] eta: 0:15:09 lr: 0.000009 grad: 0.1417 (0.1505) loss: 0.8270 (0.8387) time: 0.1246 data: 0.0379 max mem: 8452 +Train: [83] [1200/6250] eta: 0:14:50 lr: 0.000009 grad: 0.1409 (0.1504) loss: 0.8313 (0.8379) time: 0.1683 data: 0.0724 max mem: 8452 +Train: [83] [1300/6250] eta: 0:14:30 lr: 0.000009 grad: 0.1362 (0.1500) loss: 0.8331 (0.8372) time: 0.1966 data: 0.1162 max mem: 8452 +Train: [83] [1400/6250] eta: 0:14:08 lr: 0.000009 grad: 0.1395 (0.1497) loss: 0.8324 (0.8366) time: 0.1541 data: 0.0656 max mem: 8452 +Train: [83] [1500/6250] eta: 0:13:48 lr: 0.000009 grad: 0.1436 (0.1494) loss: 0.8225 (0.8361) time: 0.1630 data: 0.0615 max mem: 8452 +Train: [83] [1600/6250] eta: 0:13:33 lr: 0.000009 grad: 0.1407 (0.1491) loss: 0.8342 (0.8359) time: 0.1781 data: 0.0758 max mem: 8452 +Train: [83] [1700/6250] eta: 0:13:21 lr: 0.000009 grad: 0.1399 (0.1490) loss: 0.8334 (0.8356) time: 0.1038 data: 0.0002 max mem: 8452 +Train: [83] [1800/6250] eta: 0:13:01 lr: 0.000009 grad: 0.1378 (0.1484) loss: 0.8265 (0.8354) time: 0.1673 data: 0.0834 max mem: 8452 +Train: [83] [1900/6250] eta: 0:12:39 lr: 0.000009 grad: 0.1367 (0.1480) loss: 0.8353 (0.8353) time: 0.1661 data: 0.0786 max mem: 8452 +Train: [83] [2000/6250] eta: 0:12:20 lr: 0.000009 grad: 0.1367 (0.1477) loss: 0.8352 (0.8353) time: 0.1866 data: 0.1111 max mem: 8452 +Train: [83] [2100/6250] eta: 0:12:01 lr: 0.000009 grad: 0.1435 (0.1475) loss: 0.8283 (0.8353) time: 0.1499 data: 0.0687 max mem: 8452 +Train: [83] [2200/6250] eta: 0:11:41 lr: 0.000009 grad: 0.1333 (0.1475) loss: 0.8329 (0.8352) time: 0.1598 data: 0.0751 max mem: 8452 +Train: [83] [2300/6250] eta: 0:11:21 lr: 0.000009 grad: 0.1420 (0.1474) loss: 0.8284 (0.8351) time: 0.1354 data: 0.0562 max mem: 8452 +Train: [83] [2400/6250] eta: 0:11:01 lr: 0.000009 grad: 0.1284 (0.1473) loss: 0.8357 (0.8350) time: 0.1776 data: 0.0932 max mem: 8452 +Train: [83] [2500/6250] eta: 0:10:43 lr: 0.000009 grad: 0.1471 (0.1471) loss: 0.8156 (0.8348) time: 0.1719 data: 0.0929 max mem: 8452 +Train: [83] [2600/6250] eta: 0:10:25 lr: 0.000009 grad: 0.1414 (0.1471) loss: 0.8385 (0.8346) time: 0.1949 data: 0.1176 max mem: 8452 +Train: [83] [2700/6250] eta: 0:10:11 lr: 0.000009 grad: 0.1492 (0.1472) loss: 0.8267 (0.8344) time: 0.1195 data: 0.0006 max mem: 8452 +Train: [83] [2800/6250] eta: 0:10:04 lr: 0.000009 grad: 0.1432 (0.1471) loss: 0.8318 (0.8344) time: 0.4490 data: 0.3094 max mem: 8452 +Train: [83] [2900/6250] eta: 0:09:46 lr: 0.000009 grad: 0.1422 (0.1471) loss: 0.8309 (0.8344) time: 0.2153 data: 0.1284 max mem: 8452 +Train: [83] [3000/6250] eta: 0:09:27 lr: 0.000009 grad: 0.1382 (0.1469) loss: 0.8348 (0.8345) time: 0.1719 data: 0.0909 max mem: 8452 +Train: [83] [3100/6250] eta: 0:09:11 lr: 0.000009 grad: 0.1402 (0.1467) loss: 0.8303 (0.8345) time: 0.2423 data: 0.1546 max mem: 8452 +Train: [83] [3200/6250] eta: 0:08:54 lr: 0.000009 grad: 0.1344 (0.1466) loss: 0.8415 (0.8346) time: 0.1206 data: 0.0295 max mem: 8452 +Train: [83] [3300/6250] eta: 0:08:36 lr: 0.000009 grad: 0.1416 (0.1464) loss: 0.8367 (0.8346) time: 0.1839 data: 0.1142 max mem: 8452 +Train: [83] [3400/6250] eta: 0:08:18 lr: 0.000009 grad: 0.1473 (0.1464) loss: 0.8342 (0.8347) time: 0.1699 data: 0.1003 max mem: 8452 +Train: [83] [3500/6250] eta: 0:08:00 lr: 0.000009 grad: 0.1473 (0.1463) loss: 0.8412 (0.8347) time: 0.1470 data: 0.0778 max mem: 8452 +Train: [83] [3600/6250] eta: 0:07:42 lr: 0.000009 grad: 0.1505 (0.1463) loss: 0.8423 (0.8348) time: 0.1627 data: 0.0822 max mem: 8452 +Train: [83] [3700/6250] eta: 0:07:25 lr: 0.000009 grad: 0.1536 (0.1464) loss: 0.8324 (0.8348) time: 0.1846 data: 0.1128 max mem: 8452 +Train: [83] [3800/6250] eta: 0:07:08 lr: 0.000009 grad: 0.1392 (0.1465) loss: 0.8277 (0.8347) time: 0.1575 data: 0.0742 max mem: 8452 +Train: [83] [3900/6250] eta: 0:06:51 lr: 0.000009 grad: 0.1486 (0.1466) loss: 0.8365 (0.8347) time: 0.1854 data: 0.1088 max mem: 8452 +Train: [83] [4000/6250] eta: 0:06:32 lr: 0.000009 grad: 0.1476 (0.1466) loss: 0.8235 (0.8346) time: 0.1729 data: 0.0916 max mem: 8452 +Train: [83] [4100/6250] eta: 0:06:15 lr: 0.000009 grad: 0.1485 (0.1467) loss: 0.8317 (0.8345) time: 0.1715 data: 0.0823 max mem: 8452 +Train: [83] [4200/6250] eta: 0:05:58 lr: 0.000009 grad: 0.1418 (0.1467) loss: 0.8387 (0.8344) time: 0.1697 data: 0.0739 max mem: 8452 +Train: [83] [4300/6250] eta: 0:05:40 lr: 0.000009 grad: 0.1400 (0.1467) loss: 0.8276 (0.8343) time: 0.1781 data: 0.0876 max mem: 8452 +Train: [83] [4400/6250] eta: 0:05:22 lr: 0.000009 grad: 0.1452 (0.1467) loss: 0.8330 (0.8343) time: 0.1754 data: 0.0856 max mem: 8452 +Train: [83] [4500/6250] eta: 0:05:04 lr: 0.000009 grad: 0.1484 (0.1466) loss: 0.8302 (0.8343) time: 0.1702 data: 0.0927 max mem: 8452 +Train: [83] [4600/6250] eta: 0:04:46 lr: 0.000009 grad: 0.1444 (0.1467) loss: 0.8307 (0.8342) time: 0.1698 data: 0.0775 max mem: 8452 +Train: [83] [4700/6250] eta: 0:04:28 lr: 0.000009 grad: 0.1424 (0.1466) loss: 0.8378 (0.8342) time: 0.1430 data: 0.0567 max mem: 8452 +Train: [83] [4800/6250] eta: 0:04:10 lr: 0.000009 grad: 0.1436 (0.1466) loss: 0.8378 (0.8342) time: 0.1452 data: 0.0600 max mem: 8452 +Train: [83] [4900/6250] eta: 0:03:53 lr: 0.000009 grad: 0.1368 (0.1465) loss: 0.8368 (0.8342) time: 0.1288 data: 0.0377 max mem: 8452 +Train: [83] [5000/6250] eta: 0:03:36 lr: 0.000009 grad: 0.1385 (0.1463) loss: 0.8432 (0.8344) time: 0.2489 data: 0.1715 max mem: 8452 +Train: [83] [5100/6250] eta: 0:03:18 lr: 0.000009 grad: 0.1398 (0.1463) loss: 0.8427 (0.8345) time: 0.1679 data: 0.0792 max mem: 8452 +Train: [83] [5200/6250] eta: 0:03:02 lr: 0.000009 grad: 0.1369 (0.1462) loss: 0.8441 (0.8346) time: 0.1170 data: 0.0338 max mem: 8452 +Train: [83] [5300/6250] eta: 0:02:44 lr: 0.000009 grad: 0.1455 (0.1461) loss: 0.8393 (0.8346) time: 0.1649 data: 0.0848 max mem: 8452 +Train: [83] [5400/6250] eta: 0:02:26 lr: 0.000009 grad: 0.1423 (0.1461) loss: 0.8343 (0.8347) time: 0.1831 data: 0.1059 max mem: 8452 +Train: [83] [5500/6250] eta: 0:02:09 lr: 0.000009 grad: 0.1398 (0.1461) loss: 0.8403 (0.8347) time: 0.1408 data: 0.0557 max mem: 8452 +Train: [83] [5600/6250] eta: 0:01:51 lr: 0.000009 grad: 0.1391 (0.1462) loss: 0.8308 (0.8348) time: 0.1567 data: 0.0697 max mem: 8452 +Train: [83] [5700/6250] eta: 0:01:34 lr: 0.000009 grad: 0.1399 (0.1462) loss: 0.8352 (0.8347) time: 0.1308 data: 0.0466 max mem: 8452 +Train: [83] [5800/6250] eta: 0:01:17 lr: 0.000009 grad: 0.1468 (0.1461) loss: 0.8333 (0.8347) time: 0.1293 data: 0.0475 max mem: 8452 +Train: [83] [5900/6250] eta: 0:00:59 lr: 0.000009 grad: 0.1409 (0.1461) loss: 0.8290 (0.8346) time: 0.1647 data: 0.0803 max mem: 8452 +Train: [83] [6000/6250] eta: 0:00:42 lr: 0.000009 grad: 0.1453 (0.1461) loss: 0.8363 (0.8346) time: 0.1667 data: 0.0859 max mem: 8452 +Train: [83] [6100/6250] eta: 0:00:25 lr: 0.000009 grad: 0.1341 (0.1461) loss: 0.8334 (0.8346) time: 0.1352 data: 0.0459 max mem: 8452 +Train: [83] [6200/6250] eta: 0:00:08 lr: 0.000009 grad: 0.1480 (0.1461) loss: 0.8281 (0.8346) time: 0.1681 data: 0.0873 max mem: 8452 +Train: [83] [6249/6250] eta: 0:00:00 lr: 0.000009 grad: 0.1389 (0.1461) loss: 0.8371 (0.8346) time: 0.3023 data: 0.2181 max mem: 8452 +Train: [83] Total time: 0:17:56 (0.1722 s / it) +Averaged stats: lr: 0.000009 grad: 0.1389 (0.1461) loss: 0.8371 (0.8346) +Eval (hcp-train-subset): [83] [ 0/62] eta: 0:05:46 loss: 0.8561 (0.8561) time: 5.5944 data: 5.5203 max mem: 8452 +Eval (hcp-train-subset): [83] [61/62] eta: 0:00:00 loss: 0.8472 (0.8481) time: 0.1276 data: 0.1055 max mem: 8452 +Eval (hcp-train-subset): [83] Total time: 0:00:17 (0.2762 s / it) +Averaged stats (hcp-train-subset): loss: 0.8472 (0.8481) +Eval (hcp-val): [83] [ 0/62] eta: 0:05:35 loss: 0.8637 (0.8637) time: 5.4134 data: 5.3864 max mem: 8452 +Eval (hcp-val): [83] [61/62] eta: 0:00:00 loss: 0.8649 (0.8680) time: 0.1427 data: 0.1197 max mem: 8452 +Eval (hcp-val): [83] Total time: 0:00:15 (0.2580 s / it) +Averaged stats (hcp-val): loss: 0.8649 (0.8680) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [84] [ 0/6250] eta: 11:07:37 lr: 0.000009 grad: 0.2753 (0.2753) loss: 0.8594 (0.8594) time: 6.4092 data: 6.2763 max mem: 8452 +Train: [84] [ 100/6250] eta: 0:24:12 lr: 0.000009 grad: 0.1606 (0.1883) loss: 0.8341 (0.8471) time: 0.2000 data: 0.0862 max mem: 8452 +Train: [84] [ 200/6250] eta: 0:21:06 lr: 0.000009 grad: 0.1647 (0.1800) loss: 0.8316 (0.8398) time: 0.1664 data: 0.0443 max mem: 8452 +Train: [84] [ 300/6250] eta: 0:20:05 lr: 0.000008 grad: 0.1550 (0.1749) loss: 0.8340 (0.8362) time: 0.2174 data: 0.0867 max mem: 8452 +Train: [84] [ 400/6250] eta: 0:19:24 lr: 0.000008 grad: 0.1439 (0.1698) loss: 0.8337 (0.8343) time: 0.1630 data: 0.0675 max mem: 8452 +Train: [84] [ 500/6250] eta: 0:18:42 lr: 0.000008 grad: 0.1446 (0.1663) loss: 0.8347 (0.8335) time: 0.1891 data: 0.0919 max mem: 8452 +Train: [84] [ 600/6250] eta: 0:17:56 lr: 0.000008 grad: 0.1408 (0.1635) loss: 0.8410 (0.8334) time: 0.1843 data: 0.0687 max mem: 8452 +Train: [84] [ 700/6250] eta: 0:17:35 lr: 0.000008 grad: 0.1415 (0.1616) loss: 0.8386 (0.8334) time: 0.2036 data: 0.1058 max mem: 8452 +Train: [84] [ 800/6250] eta: 0:17:06 lr: 0.000008 grad: 0.1380 (0.1601) loss: 0.8392 (0.8333) time: 0.1712 data: 0.0834 max mem: 8452 +Train: [84] [ 900/6250] eta: 0:16:35 lr: 0.000008 grad: 0.1547 (0.1587) loss: 0.8346 (0.8331) time: 0.1689 data: 0.0697 max mem: 8452 +Train: [84] [1000/6250] eta: 0:15:57 lr: 0.000008 grad: 0.1389 (0.1574) loss: 0.8411 (0.8333) time: 0.1281 data: 0.0219 max mem: 8452 +Train: [84] [1100/6250] eta: 0:15:27 lr: 0.000008 grad: 0.1369 (0.1563) loss: 0.8433 (0.8336) time: 0.1545 data: 0.0688 max mem: 8452 +Train: [84] [1200/6250] eta: 0:15:01 lr: 0.000008 grad: 0.1511 (0.1557) loss: 0.8300 (0.8336) time: 0.1565 data: 0.0692 max mem: 8452 +Train: [84] [1300/6250] eta: 0:14:33 lr: 0.000008 grad: 0.1467 (0.1551) loss: 0.8355 (0.8336) time: 0.1340 data: 0.0456 max mem: 8452 +Train: [84] [1400/6250] eta: 0:14:07 lr: 0.000008 grad: 0.1404 (0.1543) loss: 0.8361 (0.8334) time: 0.1588 data: 0.0692 max mem: 8452 +Train: [84] [1500/6250] eta: 0:13:47 lr: 0.000008 grad: 0.1478 (0.1537) loss: 0.8315 (0.8333) time: 0.1608 data: 0.0799 max mem: 8452 +Train: [84] [1600/6250] eta: 0:13:34 lr: 0.000008 grad: 0.1332 (0.1531) loss: 0.8330 (0.8334) time: 0.1737 data: 0.0987 max mem: 8452 +Train: [84] [1700/6250] eta: 0:13:14 lr: 0.000008 grad: 0.1413 (0.1526) loss: 0.8402 (0.8334) time: 0.1400 data: 0.0642 max mem: 8452 +Train: [84] [1800/6250] eta: 0:13:00 lr: 0.000008 grad: 0.1404 (0.1523) loss: 0.8292 (0.8332) time: 0.1692 data: 0.0809 max mem: 8452 +Train: [84] [1900/6250] eta: 0:12:40 lr: 0.000008 grad: 0.1371 (0.1520) loss: 0.8293 (0.8330) time: 0.1665 data: 0.0855 max mem: 8452 +Train: [84] [2000/6250] eta: 0:12:21 lr: 0.000008 grad: 0.1346 (0.1516) loss: 0.8321 (0.8330) time: 0.1865 data: 0.1076 max mem: 8452 +Train: [84] [2100/6250] eta: 0:12:02 lr: 0.000008 grad: 0.1459 (0.1512) loss: 0.8346 (0.8330) time: 0.1583 data: 0.0857 max mem: 8452 +Train: [84] [2200/6250] eta: 0:11:42 lr: 0.000008 grad: 0.1474 (0.1509) loss: 0.8332 (0.8330) time: 0.1620 data: 0.0897 max mem: 8452 +Train: [84] [2300/6250] eta: 0:11:21 lr: 0.000008 grad: 0.1482 (0.1508) loss: 0.8370 (0.8332) time: 0.1411 data: 0.0533 max mem: 8452 +Train: [84] [2400/6250] eta: 0:11:03 lr: 0.000008 grad: 0.1403 (0.1507) loss: 0.8275 (0.8332) time: 0.1794 data: 0.0933 max mem: 8452 +Train: [84] [2500/6250] eta: 0:10:44 lr: 0.000008 grad: 0.1464 (0.1505) loss: 0.8426 (0.8332) time: 0.1782 data: 0.0985 max mem: 8452 +Train: [84] [2600/6250] eta: 0:10:25 lr: 0.000008 grad: 0.1387 (0.1503) loss: 0.8313 (0.8331) time: 0.1842 data: 0.0951 max mem: 8452 +Train: [84] [2700/6250] eta: 0:10:06 lr: 0.000008 grad: 0.1483 (0.1501) loss: 0.8237 (0.8330) time: 0.1393 data: 0.0536 max mem: 8452 +Train: [84] [2800/6250] eta: 0:09:48 lr: 0.000008 grad: 0.1390 (0.1498) loss: 0.8401 (0.8331) time: 0.1556 data: 0.0734 max mem: 8452 +Train: [84] [2900/6250] eta: 0:09:29 lr: 0.000008 grad: 0.1359 (0.1495) loss: 0.8314 (0.8332) time: 0.1513 data: 0.0626 max mem: 8452 +Train: [84] [3000/6250] eta: 0:09:11 lr: 0.000008 grad: 0.1467 (0.1493) loss: 0.8279 (0.8332) time: 0.1585 data: 0.0696 max mem: 8452 +Train: [84] [3100/6250] eta: 0:08:59 lr: 0.000008 grad: 0.1408 (0.1491) loss: 0.8232 (0.8332) time: 0.1629 data: 0.0494 max mem: 8452 +Train: [84] [3200/6250] eta: 0:08:40 lr: 0.000008 grad: 0.1473 (0.1490) loss: 0.8300 (0.8332) time: 0.1552 data: 0.0692 max mem: 8452 +Train: [84] [3300/6250] eta: 0:08:23 lr: 0.000008 grad: 0.1395 (0.1488) loss: 0.8338 (0.8332) time: 0.1514 data: 0.0743 max mem: 8452 +Train: [84] [3400/6250] eta: 0:08:05 lr: 0.000008 grad: 0.1426 (0.1488) loss: 0.8263 (0.8331) time: 0.1375 data: 0.0526 max mem: 8452 +Train: [84] [3500/6250] eta: 0:07:47 lr: 0.000008 grad: 0.1404 (0.1487) loss: 0.8242 (0.8331) time: 0.1489 data: 0.0752 max mem: 8452 +Train: [84] [3600/6250] eta: 0:07:30 lr: 0.000008 grad: 0.1580 (0.1487) loss: 0.8283 (0.8330) time: 0.1695 data: 0.0859 max mem: 8452 +Train: [84] [3700/6250] eta: 0:07:13 lr: 0.000008 grad: 0.1368 (0.1486) loss: 0.8208 (0.8329) time: 0.1831 data: 0.1060 max mem: 8452 +Train: [84] [3800/6250] eta: 0:06:56 lr: 0.000008 grad: 0.1500 (0.1486) loss: 0.8322 (0.8329) time: 0.1498 data: 0.0666 max mem: 8452 +Train: [84] [3900/6250] eta: 0:06:40 lr: 0.000008 grad: 0.1433 (0.1487) loss: 0.8241 (0.8328) time: 0.1760 data: 0.0830 max mem: 8452 +Train: [84] [4000/6250] eta: 0:06:23 lr: 0.000008 grad: 0.1442 (0.1487) loss: 0.8346 (0.8328) time: 0.1545 data: 0.0683 max mem: 8452 +Train: [84] [4100/6250] eta: 0:06:06 lr: 0.000008 grad: 0.1412 (0.1487) loss: 0.8298 (0.8327) time: 0.1542 data: 0.0759 max mem: 8452 +Train: [84] [4200/6250] eta: 0:05:48 lr: 0.000008 grad: 0.1547 (0.1489) loss: 0.8273 (0.8326) time: 0.1747 data: 0.0919 max mem: 8452 +Train: [84] [4300/6250] eta: 0:05:31 lr: 0.000008 grad: 0.1502 (0.1489) loss: 0.8340 (0.8326) time: 0.1806 data: 0.0858 max mem: 8452 +Train: [84] [4400/6250] eta: 0:05:14 lr: 0.000008 grad: 0.1486 (0.1489) loss: 0.8305 (0.8326) time: 0.1575 data: 0.0628 max mem: 8452 +Train: [84] [4500/6250] eta: 0:04:57 lr: 0.000008 grad: 0.1380 (0.1489) loss: 0.8360 (0.8326) time: 0.1702 data: 0.0909 max mem: 8452 +Train: [84] [4600/6250] eta: 0:04:40 lr: 0.000008 grad: 0.1499 (0.1488) loss: 0.8308 (0.8326) time: 0.1634 data: 0.0899 max mem: 8452 +Train: [84] [4700/6250] eta: 0:04:22 lr: 0.000008 grad: 0.1500 (0.1488) loss: 0.8322 (0.8325) time: 0.1854 data: 0.1045 max mem: 8452 +Train: [84] [4800/6250] eta: 0:04:05 lr: 0.000008 grad: 0.1393 (0.1487) loss: 0.8385 (0.8325) time: 0.1655 data: 0.0933 max mem: 8452 +Train: [84] [4900/6250] eta: 0:03:48 lr: 0.000008 grad: 0.1439 (0.1487) loss: 0.8273 (0.8325) time: 0.1856 data: 0.1002 max mem: 8452 +Train: [84] [5000/6250] eta: 0:03:31 lr: 0.000008 grad: 0.1491 (0.1487) loss: 0.8325 (0.8326) time: 0.1688 data: 0.0919 max mem: 8452 +Train: [84] [5100/6250] eta: 0:03:14 lr: 0.000008 grad: 0.1514 (0.1487) loss: 0.8309 (0.8326) time: 0.1578 data: 0.0816 max mem: 8452 +Train: [84] [5200/6250] eta: 0:02:58 lr: 0.000008 grad: 0.1410 (0.1488) loss: 0.8408 (0.8326) time: 0.0964 data: 0.0002 max mem: 8452 +Train: [84] [5300/6250] eta: 0:02:40 lr: 0.000008 grad: 0.1404 (0.1488) loss: 0.8331 (0.8327) time: 0.1647 data: 0.0800 max mem: 8452 +Train: [84] [5400/6250] eta: 0:02:24 lr: 0.000008 grad: 0.1463 (0.1488) loss: 0.8341 (0.8328) time: 0.1312 data: 0.0338 max mem: 8452 +Train: [84] [5500/6250] eta: 0:02:07 lr: 0.000008 grad: 0.1448 (0.1489) loss: 0.8336 (0.8327) time: 0.2534 data: 0.1604 max mem: 8452 +Train: [84] [5600/6250] eta: 0:01:50 lr: 0.000008 grad: 0.1427 (0.1489) loss: 0.8360 (0.8327) time: 0.2085 data: 0.1236 max mem: 8452 +Train: [84] [5700/6250] eta: 0:01:33 lr: 0.000008 grad: 0.1433 (0.1489) loss: 0.8372 (0.8327) time: 0.2606 data: 0.1445 max mem: 8452 +Train: [84] [5800/6250] eta: 0:01:16 lr: 0.000008 grad: 0.1387 (0.1489) loss: 0.8313 (0.8327) time: 0.1657 data: 0.0825 max mem: 8452 +Train: [84] [5900/6250] eta: 0:00:59 lr: 0.000008 grad: 0.1424 (0.1489) loss: 0.8260 (0.8327) time: 0.1851 data: 0.0837 max mem: 8452 +Train: [84] [6000/6250] eta: 0:00:42 lr: 0.000008 grad: 0.1400 (0.1488) loss: 0.8326 (0.8327) time: 0.1222 data: 0.0366 max mem: 8452 +Train: [84] [6100/6250] eta: 0:00:25 lr: 0.000008 grad: 0.1484 (0.1488) loss: 0.8252 (0.8326) time: 0.1283 data: 0.0441 max mem: 8452 +Train: [84] [6200/6250] eta: 0:00:08 lr: 0.000008 grad: 0.1458 (0.1488) loss: 0.8273 (0.8325) time: 0.1621 data: 0.0817 max mem: 8452 +Train: [84] [6249/6250] eta: 0:00:00 lr: 0.000008 grad: 0.1466 (0.1488) loss: 0.8315 (0.8325) time: 0.1653 data: 0.0910 max mem: 8452 +Train: [84] Total time: 0:17:49 (0.1712 s / it) +Averaged stats: lr: 0.000008 grad: 0.1466 (0.1488) loss: 0.8315 (0.8325) +Eval (hcp-train-subset): [84] [ 0/62] eta: 0:05:55 loss: 0.8580 (0.8580) time: 5.7350 data: 5.7070 max mem: 8452 +Eval (hcp-train-subset): [84] [61/62] eta: 0:00:00 loss: 0.8428 (0.8467) time: 0.1302 data: 0.1088 max mem: 8452 +Eval (hcp-train-subset): [84] Total time: 0:00:14 (0.2400 s / it) +Averaged stats (hcp-train-subset): loss: 0.8428 (0.8467) +Making plots (hcp-train-subset): example=9 +Eval (hcp-val): [84] [ 0/62] eta: 0:05:01 loss: 0.8656 (0.8656) time: 4.8549 data: 4.8031 max mem: 8452 +Eval (hcp-val): [84] [61/62] eta: 0:00:00 loss: 0.8674 (0.8684) time: 0.1243 data: 0.1034 max mem: 8452 +Eval (hcp-val): [84] Total time: 0:00:15 (0.2458 s / it) +Averaged stats (hcp-val): loss: 0.8674 (0.8684) +Making plots (hcp-val): example=39 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [85] [ 0/6250] eta: 9:25:58 lr: 0.000008 grad: 0.1253 (0.1253) loss: 0.8699 (0.8699) time: 5.4333 data: 5.1605 max mem: 8452 +Train: [85] [ 100/6250] eta: 0:23:28 lr: 0.000008 grad: 0.1463 (0.1666) loss: 0.8507 (0.8487) time: 0.1428 data: 0.0382 max mem: 8452 +Train: [85] [ 200/6250] eta: 0:20:14 lr: 0.000008 grad: 0.1479 (0.1687) loss: 0.8336 (0.8369) time: 0.1640 data: 0.0687 max mem: 8452 +Train: [85] [ 300/6250] eta: 0:19:08 lr: 0.000007 grad: 0.1575 (0.1683) loss: 0.8142 (0.8321) time: 0.1868 data: 0.0955 max mem: 8452 +Train: [85] [ 400/6250] eta: 0:17:58 lr: 0.000007 grad: 0.1428 (0.1652) loss: 0.8307 (0.8314) time: 0.1573 data: 0.0780 max mem: 8452 +Train: [85] [ 500/6250] eta: 0:17:11 lr: 0.000007 grad: 0.1381 (0.1622) loss: 0.8357 (0.8319) time: 0.1668 data: 0.0784 max mem: 8452 +Train: [85] [ 600/6250] eta: 0:16:48 lr: 0.000007 grad: 0.1537 (0.1605) loss: 0.8310 (0.8324) time: 0.1449 data: 0.0608 max mem: 8452 +Train: [85] [ 700/6250] eta: 0:16:29 lr: 0.000007 grad: 0.1405 (0.1597) loss: 0.8339 (0.8321) time: 0.1778 data: 0.0885 max mem: 8452 +Train: [85] [ 800/6250] eta: 0:16:07 lr: 0.000007 grad: 0.1465 (0.1588) loss: 0.8291 (0.8324) time: 0.1822 data: 0.0904 max mem: 8452 +Train: [85] [ 900/6250] eta: 0:15:44 lr: 0.000007 grad: 0.1350 (0.1575) loss: 0.8374 (0.8327) time: 0.1794 data: 0.0816 max mem: 8452 +Train: [85] [1000/6250] eta: 0:15:21 lr: 0.000007 grad: 0.1420 (0.1567) loss: 0.8358 (0.8330) time: 0.1540 data: 0.0731 max mem: 8452 +Train: [85] [1100/6250] eta: 0:14:58 lr: 0.000007 grad: 0.1499 (0.1563) loss: 0.8359 (0.8331) time: 0.1908 data: 0.1165 max mem: 8452 +Train: [85] [1200/6250] eta: 0:14:41 lr: 0.000007 grad: 0.1394 (0.1559) loss: 0.8365 (0.8332) time: 0.1760 data: 0.0900 max mem: 8452 +Train: [85] [1300/6250] eta: 0:14:21 lr: 0.000007 grad: 0.1407 (0.1554) loss: 0.8330 (0.8330) time: 0.1646 data: 0.0831 max mem: 8452 +Train: [85] [1400/6250] eta: 0:14:13 lr: 0.000007 grad: 0.1505 (0.1549) loss: 0.8376 (0.8331) time: 0.2528 data: 0.1504 max mem: 8452 +Train: [85] [1500/6250] eta: 0:13:49 lr: 0.000007 grad: 0.1494 (0.1546) loss: 0.8351 (0.8329) time: 0.1568 data: 0.0613 max mem: 8452 +Train: [85] [1600/6250] eta: 0:13:26 lr: 0.000007 grad: 0.1397 (0.1542) loss: 0.8362 (0.8330) time: 0.1472 data: 0.0605 max mem: 8452 +Train: [85] [1700/6250] eta: 0:13:05 lr: 0.000007 grad: 0.1613 (0.1544) loss: 0.8222 (0.8326) time: 0.1543 data: 0.0661 max mem: 8452 +Train: [85] [1800/6250] eta: 0:12:43 lr: 0.000007 grad: 0.1529 (0.1541) loss: 0.8281 (0.8325) time: 0.1471 data: 0.0528 max mem: 8452 +Train: [85] [1900/6250] eta: 0:12:25 lr: 0.000007 grad: 0.1464 (0.1538) loss: 0.8374 (0.8325) time: 0.1799 data: 0.1000 max mem: 8452 +Train: [85] [2000/6250] eta: 0:12:05 lr: 0.000007 grad: 0.1543 (0.1536) loss: 0.8327 (0.8323) time: 0.1432 data: 0.0632 max mem: 8452 +Train: [85] [2100/6250] eta: 0:11:46 lr: 0.000007 grad: 0.1453 (0.1534) loss: 0.8244 (0.8321) time: 0.1839 data: 0.0945 max mem: 8452 +Train: [85] [2200/6250] eta: 0:11:30 lr: 0.000007 grad: 0.1466 (0.1532) loss: 0.8314 (0.8320) time: 0.1639 data: 0.0711 max mem: 8452 +Train: [85] [2300/6250] eta: 0:11:10 lr: 0.000007 grad: 0.1498 (0.1533) loss: 0.8259 (0.8319) time: 0.1311 data: 0.0528 max mem: 8452 +Train: [85] [2400/6250] eta: 0:10:51 lr: 0.000007 grad: 0.1414 (0.1532) loss: 0.8327 (0.8319) time: 0.1534 data: 0.0621 max mem: 8452 +Train: [85] [2500/6250] eta: 0:10:33 lr: 0.000007 grad: 0.1407 (0.1530) loss: 0.8327 (0.8318) time: 0.1622 data: 0.0792 max mem: 8452 +Train: [85] [2600/6250] eta: 0:10:15 lr: 0.000007 grad: 0.1472 (0.1529) loss: 0.8297 (0.8318) time: 0.1538 data: 0.0588 max mem: 8452 +Train: [85] [2700/6250] eta: 0:09:58 lr: 0.000007 grad: 0.1484 (0.1527) loss: 0.8291 (0.8319) time: 0.1966 data: 0.1051 max mem: 8452 +Train: [85] [2800/6250] eta: 0:09:42 lr: 0.000007 grad: 0.1458 (0.1526) loss: 0.8390 (0.8321) time: 0.1646 data: 0.0907 max mem: 8452 +Train: [85] [2900/6250] eta: 0:09:25 lr: 0.000007 grad: 0.1445 (0.1524) loss: 0.8390 (0.8322) time: 0.1488 data: 0.0524 max mem: 8452 +Train: [85] [3000/6250] eta: 0:09:07 lr: 0.000007 grad: 0.1327 (0.1521) loss: 0.8408 (0.8324) time: 0.1810 data: 0.0983 max mem: 8452 +Train: [85] [3100/6250] eta: 0:08:49 lr: 0.000007 grad: 0.1369 (0.1519) loss: 0.8395 (0.8326) time: 0.1405 data: 0.0692 max mem: 8452 +Train: [85] [3200/6250] eta: 0:08:33 lr: 0.000007 grad: 0.1345 (0.1516) loss: 0.8416 (0.8328) time: 0.1923 data: 0.1290 max mem: 8452 +Train: [85] [3300/6250] eta: 0:08:15 lr: 0.000007 grad: 0.1367 (0.1513) loss: 0.8462 (0.8330) time: 0.1593 data: 0.0864 max mem: 8452 +Train: [85] [3400/6250] eta: 0:07:59 lr: 0.000007 grad: 0.1445 (0.1510) loss: 0.8362 (0.8332) time: 0.1680 data: 0.0888 max mem: 8452 +Train: [85] [3500/6250] eta: 0:07:42 lr: 0.000007 grad: 0.1348 (0.1507) loss: 0.8383 (0.8334) time: 0.1906 data: 0.1141 max mem: 8452 +Train: [85] [3600/6250] eta: 0:07:25 lr: 0.000007 grad: 0.1413 (0.1505) loss: 0.8298 (0.8336) time: 0.1711 data: 0.0938 max mem: 8452 +Train: [85] [3700/6250] eta: 0:07:07 lr: 0.000007 grad: 0.1384 (0.1503) loss: 0.8426 (0.8337) time: 0.1609 data: 0.0822 max mem: 8452 +Train: [85] [3800/6250] eta: 0:06:50 lr: 0.000007 grad: 0.1333 (0.1501) loss: 0.8345 (0.8338) time: 0.1707 data: 0.0861 max mem: 8452 +Train: [85] [3900/6250] eta: 0:06:34 lr: 0.000007 grad: 0.1330 (0.1498) loss: 0.8364 (0.8339) time: 0.1897 data: 0.1078 max mem: 8452 +Train: [85] [4000/6250] eta: 0:06:17 lr: 0.000007 grad: 0.1357 (0.1496) loss: 0.8433 (0.8340) time: 0.1732 data: 0.1030 max mem: 8452 +Train: [85] [4100/6250] eta: 0:05:59 lr: 0.000007 grad: 0.1391 (0.1495) loss: 0.8314 (0.8341) time: 0.1282 data: 0.0415 max mem: 8452 +Train: [85] [4200/6250] eta: 0:05:42 lr: 0.000007 grad: 0.1388 (0.1494) loss: 0.8350 (0.8341) time: 0.1643 data: 0.0909 max mem: 8452 +Train: [85] [4300/6250] eta: 0:05:25 lr: 0.000007 grad: 0.1364 (0.1493) loss: 0.8387 (0.8342) time: 0.1721 data: 0.0905 max mem: 8452 +Train: [85] [4400/6250] eta: 0:05:08 lr: 0.000007 grad: 0.1417 (0.1493) loss: 0.8348 (0.8342) time: 0.1810 data: 0.0996 max mem: 8452 +Train: [85] [4500/6250] eta: 0:04:51 lr: 0.000007 grad: 0.1420 (0.1493) loss: 0.8347 (0.8342) time: 0.1637 data: 0.0798 max mem: 8452 +Train: [85] [4600/6250] eta: 0:04:34 lr: 0.000007 grad: 0.1379 (0.1493) loss: 0.8279 (0.8341) time: 0.1693 data: 0.0888 max mem: 8452 +Train: [85] [4700/6250] eta: 0:04:17 lr: 0.000007 grad: 0.1477 (0.1493) loss: 0.8281 (0.8341) time: 0.1681 data: 0.0749 max mem: 8452 +Train: [85] [4800/6250] eta: 0:04:01 lr: 0.000007 grad: 0.1446 (0.1492) loss: 0.8396 (0.8341) time: 0.1517 data: 0.0646 max mem: 8452 +Train: [85] [4900/6250] eta: 0:03:44 lr: 0.000007 grad: 0.1524 (0.1493) loss: 0.8238 (0.8340) time: 0.1084 data: 0.0298 max mem: 8452 +Train: [85] [5000/6250] eta: 0:03:28 lr: 0.000007 grad: 0.1468 (0.1493) loss: 0.8304 (0.8340) time: 0.1775 data: 0.0923 max mem: 8452 +Train: [85] [5100/6250] eta: 0:03:11 lr: 0.000007 grad: 0.1430 (0.1492) loss: 0.8353 (0.8340) time: 0.1380 data: 0.0541 max mem: 8452 +Train: [85] [5200/6250] eta: 0:02:55 lr: 0.000007 grad: 0.1451 (0.1493) loss: 0.8343 (0.8340) time: 0.1570 data: 0.0793 max mem: 8452 +Train: [85] [5300/6250] eta: 0:02:38 lr: 0.000007 grad: 0.1471 (0.1492) loss: 0.8358 (0.8340) time: 0.1472 data: 0.0693 max mem: 8452 +Train: [85] [5400/6250] eta: 0:02:21 lr: 0.000007 grad: 0.1423 (0.1493) loss: 0.8305 (0.8340) time: 0.1484 data: 0.0596 max mem: 8452 +Train: [85] [5500/6250] eta: 0:02:04 lr: 0.000007 grad: 0.1446 (0.1492) loss: 0.8344 (0.8341) time: 0.1453 data: 0.0787 max mem: 8452 +Train: [85] [5600/6250] eta: 0:01:47 lr: 0.000007 grad: 0.1383 (0.1492) loss: 0.8310 (0.8341) time: 0.1125 data: 0.0213 max mem: 8452 +Train: [85] [5700/6250] eta: 0:01:31 lr: 0.000007 grad: 0.1294 (0.1492) loss: 0.8337 (0.8341) time: 0.1699 data: 0.0963 max mem: 8452 +Train: [85] [5800/6250] eta: 0:01:14 lr: 0.000007 grad: 0.1454 (0.1490) loss: 0.8380 (0.8342) time: 0.1465 data: 0.0651 max mem: 8452 +Train: [85] [5900/6250] eta: 0:00:57 lr: 0.000007 grad: 0.1451 (0.1490) loss: 0.8356 (0.8342) time: 0.1481 data: 0.0565 max mem: 8452 +Train: [85] [6000/6250] eta: 0:00:41 lr: 0.000007 grad: 0.1398 (0.1490) loss: 0.8346 (0.8343) time: 0.1367 data: 0.0485 max mem: 8452 +Train: [85] [6100/6250] eta: 0:00:24 lr: 0.000007 grad: 0.1418 (0.1490) loss: 0.8390 (0.8343) time: 0.1219 data: 0.0403 max mem: 8452 +Train: [85] [6200/6250] eta: 0:00:08 lr: 0.000007 grad: 0.1365 (0.1489) loss: 0.8388 (0.8344) time: 0.1791 data: 0.1045 max mem: 8452 +Train: [85] [6249/6250] eta: 0:00:00 lr: 0.000007 grad: 0.1326 (0.1488) loss: 0.8382 (0.8344) time: 0.1480 data: 0.0599 max mem: 8452 +Train: [85] Total time: 0:17:25 (0.1672 s / it) +Averaged stats: lr: 0.000007 grad: 0.1326 (0.1488) loss: 0.8382 (0.8344) +Eval (hcp-train-subset): [85] [ 0/62] eta: 0:04:32 loss: 0.8512 (0.8512) time: 4.3882 data: 4.3187 max mem: 8452 +Eval (hcp-train-subset): [85] [61/62] eta: 0:00:00 loss: 0.8447 (0.8468) time: 0.1685 data: 0.1469 max mem: 8452 +Eval (hcp-train-subset): [85] Total time: 0:00:16 (0.2581 s / it) +Averaged stats (hcp-train-subset): loss: 0.8447 (0.8468) +Eval (hcp-val): [85] [ 0/62] eta: 0:06:33 loss: 0.8652 (0.8652) time: 6.3462 data: 6.3146 max mem: 8452 +Eval (hcp-val): [85] [61/62] eta: 0:00:00 loss: 0.8655 (0.8675) time: 0.1377 data: 0.1149 max mem: 8452 +Eval (hcp-val): [85] Total time: 0:00:15 (0.2554 s / it) +Averaged stats (hcp-val): loss: 0.8655 (0.8675) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [86] [ 0/6250] eta: 13:54:26 lr: 0.000007 grad: 0.7936 (0.7936) loss: 0.7560 (0.7560) time: 8.0106 data: 7.8970 max mem: 8452 +Train: [86] [ 100/6250] eta: 0:25:20 lr: 0.000007 grad: 0.1639 (0.2127) loss: 0.8198 (0.8293) time: 0.1990 data: 0.0861 max mem: 8452 +Train: [86] [ 200/6250] eta: 0:21:26 lr: 0.000007 grad: 0.1428 (0.1923) loss: 0.8366 (0.8280) time: 0.1870 data: 0.0957 max mem: 8452 +Train: [86] [ 300/6250] eta: 0:20:26 lr: 0.000007 grad: 0.1562 (0.1814) loss: 0.8317 (0.8295) time: 0.1743 data: 0.0870 max mem: 8452 +Train: [86] [ 400/6250] eta: 0:19:18 lr: 0.000007 grad: 0.1429 (0.1749) loss: 0.8361 (0.8306) time: 0.1761 data: 0.0793 max mem: 8452 +Train: [86] [ 500/6250] eta: 0:18:31 lr: 0.000007 grad: 0.1416 (0.1697) loss: 0.8463 (0.8318) time: 0.1929 data: 0.0946 max mem: 8452 +Train: [86] [ 600/6250] eta: 0:17:52 lr: 0.000006 grad: 0.1419 (0.1661) loss: 0.8428 (0.8327) time: 0.1644 data: 0.0649 max mem: 8452 +Train: [86] [ 700/6250] eta: 0:17:22 lr: 0.000006 grad: 0.1396 (0.1642) loss: 0.8370 (0.8336) time: 0.1754 data: 0.0732 max mem: 8452 +Train: [86] [ 800/6250] eta: 0:16:50 lr: 0.000006 grad: 0.1412 (0.1623) loss: 0.8426 (0.8341) time: 0.1504 data: 0.0512 max mem: 8452 +Train: [86] [ 900/6250] eta: 0:16:20 lr: 0.000006 grad: 0.1475 (0.1615) loss: 0.8419 (0.8345) time: 0.1336 data: 0.0445 max mem: 8452 +Train: [86] [1000/6250] eta: 0:15:52 lr: 0.000006 grad: 0.1430 (0.1602) loss: 0.8350 (0.8348) time: 0.1595 data: 0.0804 max mem: 8452 +Train: [86] [1100/6250] eta: 0:15:25 lr: 0.000006 grad: 0.1467 (0.1587) loss: 0.8419 (0.8352) time: 0.1360 data: 0.0420 max mem: 8452 +Train: [86] [1200/6250] eta: 0:15:02 lr: 0.000006 grad: 0.1550 (0.1583) loss: 0.8409 (0.8352) time: 0.1498 data: 0.0753 max mem: 8452 +Train: [86] [1300/6250] eta: 0:14:38 lr: 0.000006 grad: 0.1463 (0.1579) loss: 0.8319 (0.8351) time: 0.1854 data: 0.0842 max mem: 8452 +Train: [86] [1400/6250] eta: 0:14:26 lr: 0.000006 grad: 0.1491 (0.1574) loss: 0.8309 (0.8348) time: 0.1714 data: 0.0393 max mem: 8452 +Train: [86] [1500/6250] eta: 0:14:02 lr: 0.000006 grad: 0.1492 (0.1571) loss: 0.8298 (0.8345) time: 0.1770 data: 0.0974 max mem: 8452 +Train: [86] [1600/6250] eta: 0:13:39 lr: 0.000006 grad: 0.1487 (0.1570) loss: 0.8215 (0.8341) time: 0.1600 data: 0.0592 max mem: 8452 +Train: [86] [1700/6250] eta: 0:13:18 lr: 0.000006 grad: 0.1419 (0.1567) loss: 0.8420 (0.8340) time: 0.1713 data: 0.0877 max mem: 8452 +Train: [86] [1800/6250] eta: 0:13:03 lr: 0.000006 grad: 0.1421 (0.1562) loss: 0.8358 (0.8339) time: 0.1761 data: 0.0912 max mem: 8452 +Train: [86] [1900/6250] eta: 0:12:41 lr: 0.000006 grad: 0.1538 (0.1560) loss: 0.8252 (0.8338) time: 0.1649 data: 0.0881 max mem: 8452 +Train: [86] [2000/6250] eta: 0:12:19 lr: 0.000006 grad: 0.1495 (0.1558) loss: 0.8309 (0.8336) time: 0.1511 data: 0.0631 max mem: 8452 +Train: [86] [2100/6250] eta: 0:12:01 lr: 0.000006 grad: 0.1549 (0.1557) loss: 0.8388 (0.8335) time: 0.2007 data: 0.1171 max mem: 8452 +Train: [86] [2200/6250] eta: 0:11:40 lr: 0.000006 grad: 0.1571 (0.1558) loss: 0.8245 (0.8334) time: 0.1625 data: 0.0885 max mem: 8452 +Train: [86] [2300/6250] eta: 0:11:27 lr: 0.000006 grad: 0.1449 (0.1557) loss: 0.8356 (0.8333) time: 0.2380 data: 0.1400 max mem: 8452 +Train: [86] [2400/6250] eta: 0:11:05 lr: 0.000006 grad: 0.1458 (0.1555) loss: 0.8324 (0.8334) time: 0.1473 data: 0.0636 max mem: 8452 +Train: [86] [2500/6250] eta: 0:10:45 lr: 0.000006 grad: 0.1439 (0.1553) loss: 0.8384 (0.8333) time: 0.1605 data: 0.0853 max mem: 8452 +Train: [86] [2600/6250] eta: 0:10:26 lr: 0.000006 grad: 0.1510 (0.1552) loss: 0.8319 (0.8332) time: 0.1628 data: 0.0820 max mem: 8452 +Train: [86] [2700/6250] eta: 0:10:07 lr: 0.000006 grad: 0.1481 (0.1551) loss: 0.8367 (0.8332) time: 0.1571 data: 0.0795 max mem: 8452 +Train: [86] [2800/6250] eta: 0:09:48 lr: 0.000006 grad: 0.1495 (0.1550) loss: 0.8301 (0.8332) time: 0.1483 data: 0.0602 max mem: 8452 +Train: [86] [2900/6250] eta: 0:09:28 lr: 0.000006 grad: 0.1547 (0.1551) loss: 0.8316 (0.8331) time: 0.1508 data: 0.0729 max mem: 8452 +Train: [86] [3000/6250] eta: 0:09:10 lr: 0.000006 grad: 0.1494 (0.1549) loss: 0.8348 (0.8331) time: 0.1671 data: 0.0925 max mem: 8452 +Train: [86] [3100/6250] eta: 0:08:52 lr: 0.000006 grad: 0.1488 (0.1548) loss: 0.8338 (0.8331) time: 0.1512 data: 0.0778 max mem: 8452 +Train: [86] [3200/6250] eta: 0:08:36 lr: 0.000006 grad: 0.1424 (0.1546) loss: 0.8297 (0.8331) time: 0.1736 data: 0.1004 max mem: 8452 +Train: [86] [3300/6250] eta: 0:08:18 lr: 0.000006 grad: 0.1376 (0.1544) loss: 0.8294 (0.8330) time: 0.1741 data: 0.0989 max mem: 8452 +Train: [86] [3400/6250] eta: 0:08:01 lr: 0.000006 grad: 0.1477 (0.1542) loss: 0.8282 (0.8330) time: 0.1533 data: 0.0770 max mem: 8452 +Train: [86] [3500/6250] eta: 0:07:44 lr: 0.000006 grad: 0.1408 (0.1539) loss: 0.8343 (0.8330) time: 0.2346 data: 0.1438 max mem: 8452 +Train: [86] [3600/6250] eta: 0:07:26 lr: 0.000006 grad: 0.1501 (0.1538) loss: 0.8318 (0.8330) time: 0.1724 data: 0.1007 max mem: 8452 +Train: [86] [3700/6250] eta: 0:07:09 lr: 0.000006 grad: 0.1412 (0.1536) loss: 0.8365 (0.8331) time: 0.1560 data: 0.0828 max mem: 8452 +Train: [86] [3800/6250] eta: 0:06:51 lr: 0.000006 grad: 0.1458 (0.1535) loss: 0.8307 (0.8331) time: 0.1434 data: 0.0627 max mem: 8452 +Train: [86] [3900/6250] eta: 0:06:33 lr: 0.000006 grad: 0.1478 (0.1534) loss: 0.8406 (0.8332) time: 0.1449 data: 0.0569 max mem: 8452 +Train: [86] [4000/6250] eta: 0:06:16 lr: 0.000006 grad: 0.1478 (0.1532) loss: 0.8331 (0.8332) time: 0.1500 data: 0.0695 max mem: 8452 +Train: [86] [4100/6250] eta: 0:06:00 lr: 0.000006 grad: 0.1422 (0.1530) loss: 0.8349 (0.8333) time: 0.1802 data: 0.0950 max mem: 8452 +Train: [86] [4200/6250] eta: 0:05:43 lr: 0.000006 grad: 0.1406 (0.1528) loss: 0.8340 (0.8333) time: 0.1425 data: 0.0534 max mem: 8452 +Train: [86] [4300/6250] eta: 0:05:26 lr: 0.000006 grad: 0.1501 (0.1527) loss: 0.8401 (0.8333) time: 0.1346 data: 0.0540 max mem: 8452 +Train: [86] [4400/6250] eta: 0:05:09 lr: 0.000006 grad: 0.1403 (0.1526) loss: 0.8288 (0.8333) time: 0.1933 data: 0.1132 max mem: 8452 +Train: [86] [4500/6250] eta: 0:04:52 lr: 0.000006 grad: 0.1456 (0.1525) loss: 0.8338 (0.8333) time: 0.1487 data: 0.0743 max mem: 8452 +Train: [86] [4600/6250] eta: 0:04:35 lr: 0.000006 grad: 0.1495 (0.1524) loss: 0.8285 (0.8333) time: 0.1884 data: 0.1149 max mem: 8452 +Train: [86] [4700/6250] eta: 0:04:18 lr: 0.000006 grad: 0.1430 (0.1523) loss: 0.8315 (0.8332) time: 0.1630 data: 0.0865 max mem: 8452 +Train: [86] [4800/6250] eta: 0:04:00 lr: 0.000006 grad: 0.1474 (0.1522) loss: 0.8326 (0.8331) time: 0.1704 data: 0.0894 max mem: 8452 +Train: [86] [4900/6250] eta: 0:03:44 lr: 0.000006 grad: 0.1493 (0.1521) loss: 0.8286 (0.8331) time: 0.1886 data: 0.0959 max mem: 8452 +Train: [86] [5000/6250] eta: 0:03:28 lr: 0.000006 grad: 0.1523 (0.1521) loss: 0.8311 (0.8330) time: 0.1534 data: 0.0327 max mem: 8452 +Train: [86] [5100/6250] eta: 0:03:11 lr: 0.000006 grad: 0.1506 (0.1520) loss: 0.8245 (0.8330) time: 0.2375 data: 0.1213 max mem: 8452 +Train: [86] [5200/6250] eta: 0:02:55 lr: 0.000006 grad: 0.1380 (0.1519) loss: 0.8360 (0.8329) time: 0.1517 data: 0.0446 max mem: 8452 +Train: [86] [5300/6250] eta: 0:02:38 lr: 0.000006 grad: 0.1450 (0.1518) loss: 0.8277 (0.8329) time: 0.1470 data: 0.0607 max mem: 8452 +Train: [86] [5400/6250] eta: 0:02:22 lr: 0.000006 grad: 0.1446 (0.1518) loss: 0.8265 (0.8329) time: 0.1951 data: 0.1056 max mem: 8452 +Train: [86] [5500/6250] eta: 0:02:05 lr: 0.000006 grad: 0.1449 (0.1517) loss: 0.8314 (0.8328) time: 0.1740 data: 0.1018 max mem: 8452 +Train: [86] [5600/6250] eta: 0:01:48 lr: 0.000006 grad: 0.1460 (0.1517) loss: 0.8296 (0.8328) time: 0.1731 data: 0.0975 max mem: 8452 +Train: [86] [5700/6250] eta: 0:01:31 lr: 0.000006 grad: 0.1511 (0.1517) loss: 0.8302 (0.8327) time: 0.1822 data: 0.0933 max mem: 8452 +Train: [86] [5800/6250] eta: 0:01:15 lr: 0.000006 grad: 0.1549 (0.1517) loss: 0.8335 (0.8326) time: 0.1656 data: 0.0877 max mem: 8452 +Train: [86] [5900/6250] eta: 0:00:58 lr: 0.000006 grad: 0.1463 (0.1516) loss: 0.8357 (0.8326) time: 0.1799 data: 0.0901 max mem: 8452 +Train: [86] [6000/6250] eta: 0:00:41 lr: 0.000006 grad: 0.1444 (0.1517) loss: 0.8276 (0.8326) time: 0.1887 data: 0.1135 max mem: 8452 +Train: [86] [6100/6250] eta: 0:00:25 lr: 0.000006 grad: 0.1485 (0.1518) loss: 0.8303 (0.8326) time: 0.1501 data: 0.0522 max mem: 8452 +Train: [86] [6200/6250] eta: 0:00:08 lr: 0.000006 grad: 0.1520 (0.1519) loss: 0.8294 (0.8325) time: 0.1830 data: 0.0906 max mem: 8452 +Train: [86] [6249/6250] eta: 0:00:00 lr: 0.000006 grad: 0.1543 (0.1519) loss: 0.8288 (0.8325) time: 0.1643 data: 0.0748 max mem: 8452 +Train: [86] Total time: 0:17:29 (0.1679 s / it) +Averaged stats: lr: 0.000006 grad: 0.1543 (0.1519) loss: 0.8288 (0.8325) +Eval (hcp-train-subset): [86] [ 0/62] eta: 0:06:23 loss: 0.8536 (0.8536) time: 6.1836 data: 6.1565 max mem: 8452 +Eval (hcp-train-subset): [86] [61/62] eta: 0:00:00 loss: 0.8421 (0.8457) time: 0.1451 data: 0.1237 max mem: 8452 +Eval (hcp-train-subset): [86] Total time: 0:00:15 (0.2498 s / it) +Averaged stats (hcp-train-subset): loss: 0.8421 (0.8457) +Eval (hcp-val): [86] [ 0/62] eta: 0:05:03 loss: 0.8632 (0.8632) time: 4.8985 data: 4.8036 max mem: 8452 +Eval (hcp-val): [86] [61/62] eta: 0:00:00 loss: 0.8659 (0.8670) time: 0.1368 data: 0.1159 max mem: 8452 +Eval (hcp-val): [86] Total time: 0:00:15 (0.2484 s / it) +Averaged stats (hcp-val): loss: 0.8659 (0.8670) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [87] [ 0/6250] eta: 10:47:00 lr: 0.000006 grad: 0.1573 (0.1573) loss: 0.8617 (0.8617) time: 6.2113 data: 6.0473 max mem: 8452 +Train: [87] [ 100/6250] eta: 0:23:35 lr: 0.000006 grad: 0.1605 (0.1816) loss: 0.8474 (0.8526) time: 0.1875 data: 0.0919 max mem: 8452 +Train: [87] [ 200/6250] eta: 0:20:40 lr: 0.000006 grad: 0.1370 (0.1721) loss: 0.8559 (0.8474) time: 0.1953 data: 0.0852 max mem: 8452 +Train: [87] [ 300/6250] eta: 0:20:01 lr: 0.000006 grad: 0.1598 (0.1693) loss: 0.8294 (0.8432) time: 0.1891 data: 0.0893 max mem: 8452 +Train: [87] [ 400/6250] eta: 0:18:56 lr: 0.000006 grad: 0.1445 (0.1658) loss: 0.8418 (0.8418) time: 0.1798 data: 0.0898 max mem: 8452 +Train: [87] [ 500/6250] eta: 0:18:06 lr: 0.000006 grad: 0.1562 (0.1642) loss: 0.8282 (0.8409) time: 0.1598 data: 0.0765 max mem: 8452 +Train: [87] [ 600/6250] eta: 0:17:40 lr: 0.000006 grad: 0.1389 (0.1607) loss: 0.8278 (0.8404) time: 0.1728 data: 0.0849 max mem: 8452 +Train: [87] [ 700/6250] eta: 0:17:09 lr: 0.000006 grad: 0.1434 (0.1589) loss: 0.8356 (0.8395) time: 0.1771 data: 0.0916 max mem: 8452 +Train: [87] [ 800/6250] eta: 0:16:38 lr: 0.000006 grad: 0.1513 (0.1581) loss: 0.8325 (0.8390) time: 0.1697 data: 0.0715 max mem: 8452 +Train: [87] [ 900/6250] eta: 0:16:13 lr: 0.000006 grad: 0.1459 (0.1574) loss: 0.8349 (0.8384) time: 0.1599 data: 0.0648 max mem: 8452 +Train: [87] [1000/6250] eta: 0:15:42 lr: 0.000006 grad: 0.1357 (0.1567) loss: 0.8388 (0.8379) time: 0.1455 data: 0.0615 max mem: 8452 +Train: [87] [1100/6250] eta: 0:15:17 lr: 0.000006 grad: 0.1443 (0.1560) loss: 0.8357 (0.8376) time: 0.1896 data: 0.0985 max mem: 8452 +Train: [87] [1200/6250] eta: 0:15:05 lr: 0.000006 grad: 0.1472 (0.1551) loss: 0.8334 (0.8376) time: 0.1656 data: 0.0738 max mem: 8452 +Train: [87] [1300/6250] eta: 0:14:38 lr: 0.000006 grad: 0.1359 (0.1542) loss: 0.8386 (0.8374) time: 0.1519 data: 0.0531 max mem: 8452 +Train: [87] [1400/6250] eta: 0:14:16 lr: 0.000005 grad: 0.1419 (0.1535) loss: 0.8395 (0.8373) time: 0.1849 data: 0.1072 max mem: 8452 +Train: [87] [1500/6250] eta: 0:13:51 lr: 0.000005 grad: 0.1424 (0.1532) loss: 0.8291 (0.8370) time: 0.1565 data: 0.0657 max mem: 8452 +Train: [87] [1600/6250] eta: 0:13:42 lr: 0.000005 grad: 0.1449 (0.1528) loss: 0.8337 (0.8369) time: 0.3445 data: 0.2507 max mem: 8452 +Train: [87] [1700/6250] eta: 0:13:21 lr: 0.000005 grad: 0.1519 (0.1526) loss: 0.8314 (0.8368) time: 0.2471 data: 0.1721 max mem: 8452 +Train: [87] [1800/6250] eta: 0:13:02 lr: 0.000005 grad: 0.1477 (0.1524) loss: 0.8284 (0.8366) time: 0.1260 data: 0.0075 max mem: 8452 +Train: [87] [1900/6250] eta: 0:12:39 lr: 0.000005 grad: 0.1491 (0.1523) loss: 0.8310 (0.8364) time: 0.1565 data: 0.0725 max mem: 8452 +Train: [87] [2000/6250] eta: 0:12:17 lr: 0.000005 grad: 0.1452 (0.1523) loss: 0.8305 (0.8361) time: 0.1443 data: 0.0623 max mem: 8452 +Train: [87] [2100/6250] eta: 0:11:56 lr: 0.000005 grad: 0.1519 (0.1521) loss: 0.8287 (0.8360) time: 0.1448 data: 0.0506 max mem: 8452 +Train: [87] [2200/6250] eta: 0:11:38 lr: 0.000005 grad: 0.1400 (0.1520) loss: 0.8368 (0.8359) time: 0.1670 data: 0.0838 max mem: 8452 +Train: [87] [2300/6250] eta: 0:11:19 lr: 0.000005 grad: 0.1431 (0.1520) loss: 0.8312 (0.8358) time: 0.1559 data: 0.0793 max mem: 8452 +Train: [87] [2400/6250] eta: 0:10:59 lr: 0.000005 grad: 0.1402 (0.1518) loss: 0.8344 (0.8358) time: 0.1708 data: 0.0835 max mem: 8452 +Train: [87] [2500/6250] eta: 0:10:40 lr: 0.000005 grad: 0.1478 (0.1520) loss: 0.8326 (0.8355) time: 0.1588 data: 0.0786 max mem: 8452 +Train: [87] [2600/6250] eta: 0:10:22 lr: 0.000005 grad: 0.1507 (0.1521) loss: 0.8323 (0.8354) time: 0.1800 data: 0.1000 max mem: 8452 +Train: [87] [2700/6250] eta: 0:10:03 lr: 0.000005 grad: 0.1453 (0.1521) loss: 0.8354 (0.8353) time: 0.1487 data: 0.0687 max mem: 8452 +Train: [87] [2800/6250] eta: 0:09:44 lr: 0.000005 grad: 0.1405 (0.1521) loss: 0.8327 (0.8353) time: 0.1649 data: 0.0702 max mem: 8452 +Train: [87] [2900/6250] eta: 0:09:25 lr: 0.000005 grad: 0.1409 (0.1519) loss: 0.8341 (0.8354) time: 0.1305 data: 0.0340 max mem: 8452 +Train: [87] [3000/6250] eta: 0:09:06 lr: 0.000005 grad: 0.1445 (0.1518) loss: 0.8390 (0.8354) time: 0.1454 data: 0.0529 max mem: 8452 +Train: [87] [3100/6250] eta: 0:08:49 lr: 0.000005 grad: 0.1449 (0.1518) loss: 0.8307 (0.8353) time: 0.1770 data: 0.0869 max mem: 8452 +Train: [87] [3200/6250] eta: 0:08:36 lr: 0.000005 grad: 0.1425 (0.1518) loss: 0.8340 (0.8353) time: 0.2013 data: 0.1202 max mem: 8452 +Train: [87] [3300/6250] eta: 0:08:21 lr: 0.000005 grad: 0.1468 (0.1519) loss: 0.8367 (0.8353) time: 0.1947 data: 0.1028 max mem: 8452 +Train: [87] [3400/6250] eta: 0:08:03 lr: 0.000005 grad: 0.1453 (0.1520) loss: 0.8314 (0.8352) time: 0.1357 data: 0.0574 max mem: 8452 +Train: [87] [3500/6250] eta: 0:07:46 lr: 0.000005 grad: 0.1487 (0.1520) loss: 0.8347 (0.8352) time: 0.1619 data: 0.0818 max mem: 8452 +Train: [87] [3600/6250] eta: 0:07:28 lr: 0.000005 grad: 0.1386 (0.1520) loss: 0.8379 (0.8352) time: 0.1488 data: 0.0589 max mem: 8452 +Train: [87] [3700/6250] eta: 0:07:10 lr: 0.000005 grad: 0.1476 (0.1520) loss: 0.8267 (0.8352) time: 0.1583 data: 0.0735 max mem: 8452 +Train: [87] [3800/6250] eta: 0:06:53 lr: 0.000005 grad: 0.1596 (0.1520) loss: 0.8355 (0.8352) time: 0.1463 data: 0.0565 max mem: 8452 +Train: [87] [3900/6250] eta: 0:06:36 lr: 0.000005 grad: 0.1506 (0.1520) loss: 0.8300 (0.8352) time: 0.1780 data: 0.0824 max mem: 8452 +Train: [87] [4000/6250] eta: 0:06:18 lr: 0.000005 grad: 0.1485 (0.1520) loss: 0.8375 (0.8352) time: 0.1429 data: 0.0596 max mem: 8452 +Train: [87] [4100/6250] eta: 0:06:01 lr: 0.000005 grad: 0.1347 (0.1519) loss: 0.8405 (0.8353) time: 0.1969 data: 0.1286 max mem: 8452 +Train: [87] [4200/6250] eta: 0:05:44 lr: 0.000005 grad: 0.1485 (0.1519) loss: 0.8339 (0.8354) time: 0.1394 data: 0.0526 max mem: 8452 +Train: [87] [4300/6250] eta: 0:05:28 lr: 0.000005 grad: 0.1554 (0.1520) loss: 0.8310 (0.8354) time: 0.1631 data: 0.0925 max mem: 8452 +Train: [87] [4400/6250] eta: 0:05:12 lr: 0.000005 grad: 0.1531 (0.1520) loss: 0.8335 (0.8354) time: 0.1742 data: 0.0839 max mem: 8452 +Train: [87] [4500/6250] eta: 0:04:55 lr: 0.000005 grad: 0.1436 (0.1520) loss: 0.8381 (0.8355) time: 0.1923 data: 0.1030 max mem: 8452 +Train: [87] [4600/6250] eta: 0:04:38 lr: 0.000005 grad: 0.1501 (0.1520) loss: 0.8322 (0.8355) time: 0.1419 data: 0.0442 max mem: 8452 +Train: [87] [4700/6250] eta: 0:04:21 lr: 0.000005 grad: 0.1573 (0.1521) loss: 0.8388 (0.8356) time: 0.1554 data: 0.0699 max mem: 8452 +Train: [87] [4800/6250] eta: 0:04:04 lr: 0.000005 grad: 0.1448 (0.1521) loss: 0.8412 (0.8357) time: 0.1840 data: 0.1101 max mem: 8452 +Train: [87] [4900/6250] eta: 0:03:48 lr: 0.000005 grad: 0.1490 (0.1520) loss: 0.8425 (0.8357) time: 0.3339 data: 0.2341 max mem: 8452 +Train: [87] [5000/6250] eta: 0:03:31 lr: 0.000005 grad: 0.1459 (0.1519) loss: 0.8437 (0.8358) time: 0.1608 data: 0.0821 max mem: 8452 +Train: [87] [5100/6250] eta: 0:03:14 lr: 0.000005 grad: 0.1499 (0.1519) loss: 0.8356 (0.8359) time: 0.0997 data: 0.0013 max mem: 8452 +Train: [87] [5200/6250] eta: 0:02:57 lr: 0.000005 grad: 0.1500 (0.1519) loss: 0.8352 (0.8360) time: 0.1542 data: 0.0686 max mem: 8452 +Train: [87] [5300/6250] eta: 0:02:40 lr: 0.000005 grad: 0.1444 (0.1519) loss: 0.8455 (0.8360) time: 0.1727 data: 0.0928 max mem: 8452 +Train: [87] [5400/6250] eta: 0:02:23 lr: 0.000005 grad: 0.1421 (0.1519) loss: 0.8370 (0.8360) time: 0.1256 data: 0.0364 max mem: 8452 +Train: [87] [5500/6250] eta: 0:02:06 lr: 0.000005 grad: 0.1491 (0.1519) loss: 0.8324 (0.8361) time: 0.1487 data: 0.0694 max mem: 8452 +Train: [87] [5600/6250] eta: 0:01:49 lr: 0.000005 grad: 0.1349 (0.1518) loss: 0.8406 (0.8361) time: 0.1684 data: 0.0725 max mem: 8452 +Train: [87] [5700/6250] eta: 0:01:33 lr: 0.000005 grad: 0.1403 (0.1518) loss: 0.8369 (0.8361) time: 0.1135 data: 0.0006 max mem: 8452 +Train: [87] [5800/6250] eta: 0:01:16 lr: 0.000005 grad: 0.1399 (0.1517) loss: 0.8399 (0.8362) time: 0.1174 data: 0.0005 max mem: 8452 +Train: [87] [5900/6250] eta: 0:00:59 lr: 0.000005 grad: 0.1456 (0.1517) loss: 0.8417 (0.8363) time: 0.1755 data: 0.0954 max mem: 8452 +Train: [87] [6000/6250] eta: 0:00:42 lr: 0.000005 grad: 0.1456 (0.1517) loss: 0.8358 (0.8363) time: 0.1254 data: 0.0438 max mem: 8452 +Train: [87] [6100/6250] eta: 0:00:25 lr: 0.000005 grad: 0.1403 (0.1516) loss: 0.8349 (0.8363) time: 0.2043 data: 0.1069 max mem: 8452 +Train: [87] [6200/6250] eta: 0:00:08 lr: 0.000005 grad: 0.1507 (0.1516) loss: 0.8317 (0.8363) time: 0.1481 data: 0.0763 max mem: 8452 +Train: [87] [6249/6250] eta: 0:00:00 lr: 0.000005 grad: 0.1523 (0.1516) loss: 0.8341 (0.8363) time: 0.1696 data: 0.0888 max mem: 8452 +Train: [87] Total time: 0:17:43 (0.1701 s / it) +Averaged stats: lr: 0.000005 grad: 0.1523 (0.1516) loss: 0.8341 (0.8363) +Eval (hcp-train-subset): [87] [ 0/62] eta: 0:04:51 loss: 0.8580 (0.8580) time: 4.7079 data: 4.6580 max mem: 8452 +Eval (hcp-train-subset): [87] [61/62] eta: 0:00:00 loss: 0.8406 (0.8456) time: 0.1260 data: 0.1049 max mem: 8452 +Eval (hcp-train-subset): [87] Total time: 0:00:14 (0.2363 s / it) +Averaged stats (hcp-train-subset): loss: 0.8406 (0.8456) +Eval (hcp-val): [87] [ 0/62] eta: 0:06:29 loss: 0.8635 (0.8635) time: 6.2861 data: 6.2600 max mem: 8452 +Eval (hcp-val): [87] [61/62] eta: 0:00:00 loss: 0.8664 (0.8676) time: 0.1462 data: 0.1250 max mem: 8452 +Eval (hcp-val): [87] Total time: 0:00:15 (0.2466 s / it) +Averaged stats (hcp-val): loss: 0.8664 (0.8676) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [88] [ 0/6250] eta: 15:49:41 lr: 0.000005 grad: 0.1173 (0.1173) loss: 0.8807 (0.8807) time: 9.1171 data: 9.0031 max mem: 8452 +Train: [88] [ 100/6250] eta: 0:24:35 lr: 0.000005 grad: 0.1778 (0.2070) loss: 0.8384 (0.8465) time: 0.1729 data: 0.0613 max mem: 8452 +Train: [88] [ 200/6250] eta: 0:20:50 lr: 0.000005 grad: 0.1811 (0.2023) loss: 0.8368 (0.8389) time: 0.1968 data: 0.0782 max mem: 8452 +Train: [88] [ 300/6250] eta: 0:19:44 lr: 0.000005 grad: 0.1761 (0.1971) loss: 0.8292 (0.8353) time: 0.1663 data: 0.0717 max mem: 8452 +Train: [88] [ 400/6250] eta: 0:18:37 lr: 0.000005 grad: 0.1573 (0.1902) loss: 0.8317 (0.8336) time: 0.1707 data: 0.0801 max mem: 8452 +Train: [88] [ 500/6250] eta: 0:17:47 lr: 0.000005 grad: 0.1666 (0.1856) loss: 0.8296 (0.8335) time: 0.1678 data: 0.0650 max mem: 8452 +Train: [88] [ 600/6250] eta: 0:17:12 lr: 0.000005 grad: 0.1464 (0.1813) loss: 0.8465 (0.8344) time: 0.1482 data: 0.0469 max mem: 8452 +Train: [88] [ 700/6250] eta: 0:16:45 lr: 0.000005 grad: 0.1352 (0.1776) loss: 0.8432 (0.8357) time: 0.1699 data: 0.0833 max mem: 8452 +Train: [88] [ 800/6250] eta: 0:16:20 lr: 0.000005 grad: 0.1502 (0.1752) loss: 0.8465 (0.8363) time: 0.1809 data: 0.1036 max mem: 8452 +Train: [88] [ 900/6250] eta: 0:15:50 lr: 0.000005 grad: 0.1451 (0.1724) loss: 0.8454 (0.8370) time: 0.1522 data: 0.0535 max mem: 8452 +Train: [88] [1000/6250] eta: 0:15:23 lr: 0.000005 grad: 0.1486 (0.1702) loss: 0.8383 (0.8375) time: 0.1620 data: 0.0845 max mem: 8452 +Train: [88] [1100/6250] eta: 0:14:57 lr: 0.000005 grad: 0.1511 (0.1689) loss: 0.8399 (0.8374) time: 0.1546 data: 0.0670 max mem: 8452 +Train: [88] [1200/6250] eta: 0:14:38 lr: 0.000005 grad: 0.1492 (0.1677) loss: 0.8414 (0.8375) time: 0.1393 data: 0.0591 max mem: 8452 +Train: [88] [1300/6250] eta: 0:14:14 lr: 0.000005 grad: 0.1509 (0.1667) loss: 0.8325 (0.8374) time: 0.1646 data: 0.0833 max mem: 8452 +Train: [88] [1400/6250] eta: 0:13:54 lr: 0.000005 grad: 0.1442 (0.1657) loss: 0.8308 (0.8375) time: 0.1577 data: 0.0731 max mem: 8452 +Train: [88] [1500/6250] eta: 0:13:33 lr: 0.000005 grad: 0.1528 (0.1647) loss: 0.8347 (0.8374) time: 0.1259 data: 0.0454 max mem: 8452 +Train: [88] [1600/6250] eta: 0:13:15 lr: 0.000005 grad: 0.1431 (0.1637) loss: 0.8437 (0.8375) time: 0.1740 data: 0.0906 max mem: 8452 +Train: [88] [1700/6250] eta: 0:12:56 lr: 0.000005 grad: 0.1387 (0.1629) loss: 0.8376 (0.8373) time: 0.1842 data: 0.1153 max mem: 8452 +Train: [88] [1800/6250] eta: 0:12:36 lr: 0.000005 grad: 0.1549 (0.1623) loss: 0.8403 (0.8370) time: 0.1163 data: 0.0305 max mem: 8452 +Train: [88] [1900/6250] eta: 0:12:16 lr: 0.000005 grad: 0.1526 (0.1617) loss: 0.8311 (0.8369) time: 0.1791 data: 0.1003 max mem: 8452 +Train: [88] [2000/6250] eta: 0:11:56 lr: 0.000005 grad: 0.1515 (0.1612) loss: 0.8300 (0.8367) time: 0.1706 data: 0.0915 max mem: 8452 +Train: [88] [2100/6250] eta: 0:11:38 lr: 0.000005 grad: 0.1471 (0.1606) loss: 0.8294 (0.8366) time: 0.1743 data: 0.0898 max mem: 8452 +Train: [88] [2200/6250] eta: 0:11:23 lr: 0.000005 grad: 0.1505 (0.1601) loss: 0.8366 (0.8365) time: 0.1901 data: 0.1163 max mem: 8452 +Train: [88] [2300/6250] eta: 0:11:06 lr: 0.000005 grad: 0.1469 (0.1595) loss: 0.8429 (0.8363) time: 0.1726 data: 0.0911 max mem: 8452 +Train: [88] [2400/6250] eta: 0:10:48 lr: 0.000005 grad: 0.1423 (0.1590) loss: 0.8411 (0.8362) time: 0.1807 data: 0.0956 max mem: 8452 +Train: [88] [2500/6250] eta: 0:10:30 lr: 0.000005 grad: 0.1474 (0.1585) loss: 0.8342 (0.8360) time: 0.1677 data: 0.0835 max mem: 8452 +Train: [88] [2600/6250] eta: 0:10:11 lr: 0.000005 grad: 0.1494 (0.1581) loss: 0.8297 (0.8360) time: 0.1482 data: 0.0787 max mem: 8452 +Train: [88] [2700/6250] eta: 0:09:54 lr: 0.000005 grad: 0.1428 (0.1578) loss: 0.8360 (0.8361) time: 0.1619 data: 0.0719 max mem: 8452 +Train: [88] [2800/6250] eta: 0:09:35 lr: 0.000005 grad: 0.1464 (0.1575) loss: 0.8372 (0.8360) time: 0.1418 data: 0.0619 max mem: 8452 +Train: [88] [2900/6250] eta: 0:09:16 lr: 0.000004 grad: 0.1466 (0.1572) loss: 0.8310 (0.8359) time: 0.1528 data: 0.0654 max mem: 8452 +Train: [88] [3000/6250] eta: 0:08:59 lr: 0.000004 grad: 0.1425 (0.1569) loss: 0.8308 (0.8358) time: 0.1723 data: 0.0813 max mem: 8452 +Train: [88] [3100/6250] eta: 0:08:45 lr: 0.000004 grad: 0.1462 (0.1567) loss: 0.8330 (0.8356) time: 0.1770 data: 0.0930 max mem: 8452 +Train: [88] [3200/6250] eta: 0:08:29 lr: 0.000004 grad: 0.1524 (0.1566) loss: 0.8307 (0.8355) time: 0.1712 data: 0.0827 max mem: 8452 +Train: [88] [3300/6250] eta: 0:08:15 lr: 0.000004 grad: 0.1532 (0.1564) loss: 0.8297 (0.8353) time: 0.1981 data: 0.1194 max mem: 8452 +Train: [88] [3400/6250] eta: 0:07:59 lr: 0.000004 grad: 0.1463 (0.1564) loss: 0.8310 (0.8353) time: 0.1781 data: 0.0947 max mem: 8452 +Train: [88] [3500/6250] eta: 0:07:44 lr: 0.000004 grad: 0.1553 (0.1563) loss: 0.8264 (0.8351) time: 0.1788 data: 0.1015 max mem: 8452 +Train: [88] [3600/6250] eta: 0:07:28 lr: 0.000004 grad: 0.1419 (0.1562) loss: 0.8332 (0.8350) time: 0.1380 data: 0.0520 max mem: 8452 +Train: [88] [3700/6250] eta: 0:07:12 lr: 0.000004 grad: 0.1587 (0.1561) loss: 0.8328 (0.8350) time: 0.1962 data: 0.1146 max mem: 8452 +Train: [88] [3800/6250] eta: 0:06:55 lr: 0.000004 grad: 0.1518 (0.1559) loss: 0.8228 (0.8349) time: 0.1682 data: 0.0894 max mem: 8452 +Train: [88] [3900/6250] eta: 0:06:38 lr: 0.000004 grad: 0.1426 (0.1558) loss: 0.8326 (0.8349) time: 0.1725 data: 0.0906 max mem: 8452 +Train: [88] [4000/6250] eta: 0:06:20 lr: 0.000004 grad: 0.1487 (0.1558) loss: 0.8313 (0.8347) time: 0.1559 data: 0.0850 max mem: 8452 +Train: [88] [4100/6250] eta: 0:06:03 lr: 0.000004 grad: 0.1434 (0.1556) loss: 0.8359 (0.8347) time: 0.1527 data: 0.0580 max mem: 8452 +Train: [88] [4200/6250] eta: 0:05:46 lr: 0.000004 grad: 0.1490 (0.1556) loss: 0.8298 (0.8346) time: 0.1708 data: 0.0871 max mem: 8452 +Train: [88] [4300/6250] eta: 0:05:29 lr: 0.000004 grad: 0.1525 (0.1556) loss: 0.8406 (0.8345) time: 0.1324 data: 0.0492 max mem: 8452 +Train: [88] [4400/6250] eta: 0:05:13 lr: 0.000004 grad: 0.1511 (0.1554) loss: 0.8349 (0.8345) time: 0.2026 data: 0.1136 max mem: 8452 +Train: [88] [4500/6250] eta: 0:04:56 lr: 0.000004 grad: 0.1515 (0.1554) loss: 0.8321 (0.8344) time: 0.1889 data: 0.1039 max mem: 8452 +Train: [88] [4600/6250] eta: 0:04:39 lr: 0.000004 grad: 0.1431 (0.1553) loss: 0.8294 (0.8344) time: 0.2006 data: 0.1146 max mem: 8452 +Train: [88] [4700/6250] eta: 0:04:21 lr: 0.000004 grad: 0.1468 (0.1552) loss: 0.8340 (0.8343) time: 0.1537 data: 0.0665 max mem: 8452 +Train: [88] [4800/6250] eta: 0:04:04 lr: 0.000004 grad: 0.1506 (0.1551) loss: 0.8289 (0.8343) time: 0.1568 data: 0.0666 max mem: 8452 +Train: [88] [4900/6250] eta: 0:03:47 lr: 0.000004 grad: 0.1486 (0.1550) loss: 0.8331 (0.8343) time: 0.1571 data: 0.0660 max mem: 8452 +Train: [88] [5000/6250] eta: 0:03:30 lr: 0.000004 grad: 0.1453 (0.1549) loss: 0.8327 (0.8342) time: 0.1430 data: 0.0707 max mem: 8452 +Train: [88] [5100/6250] eta: 0:03:14 lr: 0.000004 grad: 0.1472 (0.1549) loss: 0.8324 (0.8342) time: 0.1639 data: 0.0676 max mem: 8452 +Train: [88] [5200/6250] eta: 0:02:57 lr: 0.000004 grad: 0.1452 (0.1547) loss: 0.8295 (0.8342) time: 0.1940 data: 0.1105 max mem: 8452 +Train: [88] [5300/6250] eta: 0:02:40 lr: 0.000004 grad: 0.1473 (0.1546) loss: 0.8243 (0.8342) time: 0.1122 data: 0.0003 max mem: 8452 +Train: [88] [5400/6250] eta: 0:02:23 lr: 0.000004 grad: 0.1430 (0.1545) loss: 0.8206 (0.8342) time: 0.1378 data: 0.0547 max mem: 8452 +Train: [88] [5500/6250] eta: 0:02:06 lr: 0.000004 grad: 0.1528 (0.1543) loss: 0.8332 (0.8342) time: 0.1775 data: 0.0918 max mem: 8452 +Train: [88] [5600/6250] eta: 0:01:49 lr: 0.000004 grad: 0.1410 (0.1542) loss: 0.8391 (0.8343) time: 0.1706 data: 0.0955 max mem: 8452 +Train: [88] [5700/6250] eta: 0:01:32 lr: 0.000004 grad: 0.1445 (0.1540) loss: 0.8404 (0.8344) time: 0.1603 data: 0.0737 max mem: 8452 +Train: [88] [5800/6250] eta: 0:01:15 lr: 0.000004 grad: 0.1440 (0.1539) loss: 0.8379 (0.8344) time: 0.1877 data: 0.0966 max mem: 8452 +Train: [88] [5900/6250] eta: 0:00:59 lr: 0.000004 grad: 0.1456 (0.1538) loss: 0.8346 (0.8345) time: 0.1410 data: 0.0602 max mem: 8452 +Train: [88] [6000/6250] eta: 0:00:42 lr: 0.000004 grad: 0.1437 (0.1536) loss: 0.8359 (0.8346) time: 0.1912 data: 0.0999 max mem: 8452 +Train: [88] [6100/6250] eta: 0:00:25 lr: 0.000004 grad: 0.1462 (0.1535) loss: 0.8359 (0.8347) time: 0.1292 data: 0.0353 max mem: 8452 +Train: [88] [6200/6250] eta: 0:00:08 lr: 0.000004 grad: 0.1543 (0.1535) loss: 0.8356 (0.8347) time: 0.1596 data: 0.0754 max mem: 8452 +Train: [88] [6249/6250] eta: 0:00:00 lr: 0.000004 grad: 0.1452 (0.1535) loss: 0.8274 (0.8348) time: 0.1476 data: 0.0709 max mem: 8452 +Train: [88] Total time: 0:17:42 (0.1700 s / it) +Averaged stats: lr: 0.000004 grad: 0.1452 (0.1535) loss: 0.8274 (0.8348) +Eval (hcp-train-subset): [88] [ 0/62] eta: 0:05:39 loss: 0.8514 (0.8514) time: 5.4810 data: 5.4541 max mem: 8452 +Eval (hcp-train-subset): [88] [61/62] eta: 0:00:00 loss: 0.8435 (0.8445) time: 0.1218 data: 0.0995 max mem: 8452 +Eval (hcp-train-subset): [88] Total time: 0:00:15 (0.2472 s / it) +Averaged stats (hcp-train-subset): loss: 0.8435 (0.8445) +Eval (hcp-val): [88] [ 0/62] eta: 0:05:33 loss: 0.8655 (0.8655) time: 5.3835 data: 5.3555 max mem: 8452 +Eval (hcp-val): [88] [61/62] eta: 0:00:00 loss: 0.8643 (0.8673) time: 0.1454 data: 0.1243 max mem: 8452 +Eval (hcp-val): [88] Total time: 0:00:15 (0.2509 s / it) +Averaged stats (hcp-val): loss: 0.8643 (0.8673) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [89] [ 0/6250] eta: 12:20:15 lr: 0.000004 grad: 0.6109 (0.6109) loss: 0.7644 (0.7644) time: 7.1064 data: 6.9972 max mem: 8452 +Train: [89] [ 100/6250] eta: 0:22:58 lr: 0.000004 grad: 0.1556 (0.2004) loss: 0.8343 (0.8374) time: 0.1621 data: 0.0625 max mem: 8452 +Train: [89] [ 200/6250] eta: 0:20:34 lr: 0.000004 grad: 0.1596 (0.1855) loss: 0.8345 (0.8390) time: 0.1655 data: 0.0641 max mem: 8452 +Train: [89] [ 300/6250] eta: 0:19:18 lr: 0.000004 grad: 0.1631 (0.1793) loss: 0.8342 (0.8386) time: 0.2135 data: 0.1204 max mem: 8452 +Train: [89] [ 400/6250] eta: 0:18:12 lr: 0.000004 grad: 0.1595 (0.1753) loss: 0.8357 (0.8384) time: 0.1508 data: 0.0585 max mem: 8452 +Train: [89] [ 500/6250] eta: 0:17:46 lr: 0.000004 grad: 0.1640 (0.1741) loss: 0.8391 (0.8381) time: 0.1845 data: 0.0811 max mem: 8452 +Train: [89] [ 600/6250] eta: 0:17:12 lr: 0.000004 grad: 0.1644 (0.1721) loss: 0.8305 (0.8380) time: 0.1533 data: 0.0572 max mem: 8452 +Train: [89] [ 700/6250] eta: 0:16:38 lr: 0.000004 grad: 0.1524 (0.1706) loss: 0.8307 (0.8371) time: 0.1827 data: 0.0748 max mem: 8452 +Train: [89] [ 800/6250] eta: 0:15:57 lr: 0.000004 grad: 0.1519 (0.1697) loss: 0.8306 (0.8368) time: 0.1418 data: 0.0353 max mem: 8452 +Train: [89] [ 900/6250] eta: 0:15:30 lr: 0.000004 grad: 0.1495 (0.1684) loss: 0.8307 (0.8366) time: 0.1507 data: 0.0556 max mem: 8452 +Train: [89] [1000/6250] eta: 0:15:02 lr: 0.000004 grad: 0.1583 (0.1671) loss: 0.8399 (0.8368) time: 0.1467 data: 0.0538 max mem: 8452 +Train: [89] [1100/6250] eta: 0:14:35 lr: 0.000004 grad: 0.1397 (0.1658) loss: 0.8334 (0.8365) time: 0.1263 data: 0.0452 max mem: 8452 +Train: [89] [1200/6250] eta: 0:14:08 lr: 0.000004 grad: 0.1484 (0.1649) loss: 0.8325 (0.8363) time: 0.1601 data: 0.0818 max mem: 8452 +Train: [89] [1300/6250] eta: 0:13:52 lr: 0.000004 grad: 0.1495 (0.1641) loss: 0.8363 (0.8361) time: 0.0997 data: 0.0018 max mem: 8452 +Train: [89] [1400/6250] eta: 0:13:33 lr: 0.000004 grad: 0.1497 (0.1635) loss: 0.8358 (0.8360) time: 0.1279 data: 0.0407 max mem: 8452 +Train: [89] [1500/6250] eta: 0:13:15 lr: 0.000004 grad: 0.1548 (0.1630) loss: 0.8369 (0.8359) time: 0.1900 data: 0.1122 max mem: 8452 +Train: [89] [1600/6250] eta: 0:12:58 lr: 0.000004 grad: 0.1544 (0.1624) loss: 0.8326 (0.8358) time: 0.2005 data: 0.1217 max mem: 8452 +Train: [89] [1700/6250] eta: 0:12:39 lr: 0.000004 grad: 0.1564 (0.1619) loss: 0.8330 (0.8356) time: 0.1852 data: 0.1075 max mem: 8452 +Train: [89] [1800/6250] eta: 0:12:20 lr: 0.000004 grad: 0.1612 (0.1618) loss: 0.8307 (0.8355) time: 0.2010 data: 0.1115 max mem: 8452 +Train: [89] [1900/6250] eta: 0:12:02 lr: 0.000004 grad: 0.1641 (0.1616) loss: 0.8314 (0.8353) time: 0.1913 data: 0.1060 max mem: 8452 +Train: [89] [2000/6250] eta: 0:11:48 lr: 0.000004 grad: 0.1526 (0.1615) loss: 0.8314 (0.8352) time: 0.2027 data: 0.1293 max mem: 8452 +Train: [89] [2100/6250] eta: 0:11:33 lr: 0.000004 grad: 0.1693 (0.1614) loss: 0.8258 (0.8351) time: 0.1106 data: 0.0051 max mem: 8452 +Train: [89] [2200/6250] eta: 0:11:18 lr: 0.000004 grad: 0.1613 (0.1615) loss: 0.8278 (0.8349) time: 0.1636 data: 0.0622 max mem: 8452 +Train: [89] [2300/6250] eta: 0:11:00 lr: 0.000004 grad: 0.1504 (0.1614) loss: 0.8307 (0.8348) time: 0.1425 data: 0.0473 max mem: 8452 +Train: [89] [2400/6250] eta: 0:10:48 lr: 0.000004 grad: 0.1583 (0.1612) loss: 0.8301 (0.8346) time: 0.1352 data: 0.0003 max mem: 8452 +Train: [89] [2500/6250] eta: 0:10:30 lr: 0.000004 grad: 0.1667 (0.1613) loss: 0.8249 (0.8344) time: 0.1579 data: 0.0689 max mem: 8452 +Train: [89] [2600/6250] eta: 0:10:12 lr: 0.000004 grad: 0.1541 (0.1613) loss: 0.8274 (0.8342) time: 0.1518 data: 0.0549 max mem: 8452 +Train: [89] [2700/6250] eta: 0:09:56 lr: 0.000004 grad: 0.1588 (0.1614) loss: 0.8297 (0.8340) time: 0.2137 data: 0.1310 max mem: 8452 +Train: [89] [2800/6250] eta: 0:09:42 lr: 0.000004 grad: 0.1558 (0.1614) loss: 0.8334 (0.8337) time: 0.2847 data: 0.1999 max mem: 8452 +Train: [89] [2900/6250] eta: 0:09:22 lr: 0.000004 grad: 0.1539 (0.1614) loss: 0.8385 (0.8336) time: 0.1464 data: 0.0571 max mem: 8452 +Train: [89] [3000/6250] eta: 0:09:05 lr: 0.000004 grad: 0.1629 (0.1614) loss: 0.8182 (0.8334) time: 0.1829 data: 0.0954 max mem: 8452 +Train: [89] [3100/6250] eta: 0:08:49 lr: 0.000004 grad: 0.1638 (0.1615) loss: 0.8262 (0.8332) time: 0.2280 data: 0.1562 max mem: 8452 +Train: [89] [3200/6250] eta: 0:08:32 lr: 0.000004 grad: 0.1592 (0.1615) loss: 0.8263 (0.8332) time: 0.1603 data: 0.0915 max mem: 8452 +Train: [89] [3300/6250] eta: 0:08:15 lr: 0.000004 grad: 0.1510 (0.1614) loss: 0.8274 (0.8331) time: 0.1547 data: 0.0751 max mem: 8452 +Train: [89] [3400/6250] eta: 0:07:58 lr: 0.000004 grad: 0.1564 (0.1614) loss: 0.8268 (0.8329) time: 0.1969 data: 0.1114 max mem: 8452 +Train: [89] [3500/6250] eta: 0:07:42 lr: 0.000004 grad: 0.1561 (0.1613) loss: 0.8335 (0.8328) time: 0.1662 data: 0.0907 max mem: 8452 +Train: [89] [3600/6250] eta: 0:07:25 lr: 0.000004 grad: 0.1538 (0.1613) loss: 0.8211 (0.8327) time: 0.1617 data: 0.0809 max mem: 8452 +Train: [89] [3700/6250] eta: 0:07:08 lr: 0.000004 grad: 0.1453 (0.1614) loss: 0.8291 (0.8325) time: 0.1579 data: 0.0738 max mem: 8452 +Train: [89] [3800/6250] eta: 0:06:51 lr: 0.000004 grad: 0.1583 (0.1615) loss: 0.8268 (0.8323) time: 0.1618 data: 0.0743 max mem: 8452 +Train: [89] [3900/6250] eta: 0:06:34 lr: 0.000004 grad: 0.1591 (0.1615) loss: 0.8239 (0.8321) time: 0.1802 data: 0.0954 max mem: 8452 +Train: [89] [4000/6250] eta: 0:06:16 lr: 0.000004 grad: 0.1501 (0.1615) loss: 0.8257 (0.8320) time: 0.1503 data: 0.0676 max mem: 8452 +Train: [89] [4100/6250] eta: 0:05:59 lr: 0.000004 grad: 0.1533 (0.1614) loss: 0.8210 (0.8319) time: 0.1675 data: 0.0956 max mem: 8452 +Train: [89] [4200/6250] eta: 0:05:43 lr: 0.000004 grad: 0.1527 (0.1612) loss: 0.8392 (0.8319) time: 0.1916 data: 0.1204 max mem: 8452 +Train: [89] [4300/6250] eta: 0:05:27 lr: 0.000004 grad: 0.1501 (0.1611) loss: 0.8238 (0.8319) time: 0.1627 data: 0.0837 max mem: 8452 +Train: [89] [4400/6250] eta: 0:05:10 lr: 0.000004 grad: 0.1588 (0.1611) loss: 0.8262 (0.8318) time: 0.1508 data: 0.0862 max mem: 8452 +Train: [89] [4500/6250] eta: 0:04:53 lr: 0.000004 grad: 0.1483 (0.1609) loss: 0.8330 (0.8318) time: 0.1833 data: 0.1021 max mem: 8452 +Train: [89] [4600/6250] eta: 0:04:37 lr: 0.000004 grad: 0.1607 (0.1609) loss: 0.8314 (0.8318) time: 0.1886 data: 0.1089 max mem: 8452 +Train: [89] [4700/6250] eta: 0:04:20 lr: 0.000004 grad: 0.1550 (0.1607) loss: 0.8288 (0.8318) time: 0.1667 data: 0.0670 max mem: 8452 +Train: [89] [4800/6250] eta: 0:04:03 lr: 0.000004 grad: 0.1465 (0.1606) loss: 0.8363 (0.8318) time: 0.1559 data: 0.0826 max mem: 8452 +Train: [89] [4900/6250] eta: 0:03:45 lr: 0.000004 grad: 0.1536 (0.1606) loss: 0.8327 (0.8317) time: 0.1476 data: 0.0588 max mem: 8452 +Train: [89] [5000/6250] eta: 0:03:29 lr: 0.000004 grad: 0.1614 (0.1605) loss: 0.8347 (0.8317) time: 0.1983 data: 0.1137 max mem: 8452 +Train: [89] [5100/6250] eta: 0:03:12 lr: 0.000004 grad: 0.1617 (0.1604) loss: 0.8204 (0.8317) time: 0.2120 data: 0.1005 max mem: 8452 +Train: [89] [5200/6250] eta: 0:02:55 lr: 0.000003 grad: 0.1548 (0.1603) loss: 0.8277 (0.8317) time: 0.1296 data: 0.0456 max mem: 8452 +Train: [89] [5300/6250] eta: 0:02:38 lr: 0.000003 grad: 0.1519 (0.1603) loss: 0.8262 (0.8316) time: 0.1555 data: 0.0678 max mem: 8452 +Train: [89] [5400/6250] eta: 0:02:21 lr: 0.000003 grad: 0.1482 (0.1602) loss: 0.8301 (0.8315) time: 0.1790 data: 0.1003 max mem: 8452 +Train: [89] [5500/6250] eta: 0:02:05 lr: 0.000003 grad: 0.1670 (0.1601) loss: 0.8292 (0.8315) time: 0.1658 data: 0.0610 max mem: 8452 +Train: [89] [5600/6250] eta: 0:01:48 lr: 0.000003 grad: 0.1526 (0.1602) loss: 0.8333 (0.8315) time: 0.1557 data: 0.0691 max mem: 8452 +Train: [89] [5700/6250] eta: 0:01:31 lr: 0.000003 grad: 0.1443 (0.1601) loss: 0.8374 (0.8315) time: 0.1475 data: 0.0580 max mem: 8452 +Train: [89] [5800/6250] eta: 0:01:15 lr: 0.000003 grad: 0.1471 (0.1600) loss: 0.8354 (0.8316) time: 0.1865 data: 0.1093 max mem: 8452 +Train: [89] [5900/6250] eta: 0:00:58 lr: 0.000003 grad: 0.1511 (0.1599) loss: 0.8323 (0.8316) time: 0.1359 data: 0.0486 max mem: 8452 +Train: [89] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1569 (0.1598) loss: 0.8312 (0.8316) time: 0.1306 data: 0.0541 max mem: 8452 +Train: [89] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1484 (0.1597) loss: 0.8314 (0.8316) time: 0.1597 data: 0.0764 max mem: 8452 +Train: [89] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1569 (0.1597) loss: 0.8272 (0.8316) time: 0.1463 data: 0.0745 max mem: 8452 +Train: [89] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1492 (0.1597) loss: 0.8280 (0.8316) time: 0.1331 data: 0.0577 max mem: 8452 +Train: [89] Total time: 0:17:27 (0.1675 s / it) +Averaged stats: lr: 0.000003 grad: 0.1492 (0.1597) loss: 0.8280 (0.8316) +Eval (hcp-train-subset): [89] [ 0/62] eta: 0:06:10 loss: 0.8549 (0.8549) time: 5.9810 data: 5.9542 max mem: 8452 +Eval (hcp-train-subset): [89] [61/62] eta: 0:00:00 loss: 0.8409 (0.8435) time: 0.1369 data: 0.1146 max mem: 8452 +Eval (hcp-train-subset): [89] Total time: 0:00:14 (0.2415 s / it) +Averaged stats (hcp-train-subset): loss: 0.8409 (0.8435) +Making plots (hcp-train-subset): example=55 +Eval (hcp-val): [89] [ 0/62] eta: 0:05:40 loss: 0.8643 (0.8643) time: 5.4907 data: 5.4642 max mem: 8452 +Eval (hcp-val): [89] [61/62] eta: 0:00:00 loss: 0.8643 (0.8669) time: 0.1384 data: 0.1170 max mem: 8452 +Eval (hcp-val): [89] Total time: 0:00:15 (0.2449 s / it) +Averaged stats (hcp-val): loss: 0.8643 (0.8669) +Making plots (hcp-val): example=15 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [90] [ 0/6250] eta: 11:31:25 lr: 0.000003 grad: 0.3646 (0.3646) loss: 0.8162 (0.8162) time: 6.6377 data: 6.4646 max mem: 8452 +Train: [90] [ 100/6250] eta: 0:22:41 lr: 0.000003 grad: 0.1882 (0.2081) loss: 0.8546 (0.8511) time: 0.1459 data: 0.0405 max mem: 8452 +Train: [90] [ 200/6250] eta: 0:19:45 lr: 0.000003 grad: 0.1587 (0.1873) loss: 0.8547 (0.8494) time: 0.1622 data: 0.0688 max mem: 8452 +Train: [90] [ 300/6250] eta: 0:18:31 lr: 0.000003 grad: 0.1596 (0.1785) loss: 0.8435 (0.8479) time: 0.1502 data: 0.0643 max mem: 8452 +Train: [90] [ 400/6250] eta: 0:17:45 lr: 0.000003 grad: 0.1516 (0.1739) loss: 0.8401 (0.8462) time: 0.1693 data: 0.0584 max mem: 8452 +Train: [90] [ 500/6250] eta: 0:17:05 lr: 0.000003 grad: 0.1604 (0.1716) loss: 0.8414 (0.8447) time: 0.1651 data: 0.0743 max mem: 8452 +Train: [90] [ 600/6250] eta: 0:16:34 lr: 0.000003 grad: 0.1543 (0.1696) loss: 0.8470 (0.8450) time: 0.1647 data: 0.0657 max mem: 8452 +Train: [90] [ 700/6250] eta: 0:16:04 lr: 0.000003 grad: 0.1611 (0.1678) loss: 0.8423 (0.8448) time: 0.1556 data: 0.0640 max mem: 8452 +Train: [90] [ 800/6250] eta: 0:15:34 lr: 0.000003 grad: 0.1494 (0.1664) loss: 0.8482 (0.8449) time: 0.1654 data: 0.0657 max mem: 8452 +Train: [90] [ 900/6250] eta: 0:15:08 lr: 0.000003 grad: 0.1471 (0.1654) loss: 0.8444 (0.8449) time: 0.1597 data: 0.0782 max mem: 8452 +Train: [90] [1000/6250] eta: 0:14:48 lr: 0.000003 grad: 0.1358 (0.1637) loss: 0.8478 (0.8448) time: 0.1435 data: 0.0542 max mem: 8452 +Train: [90] [1100/6250] eta: 0:14:34 lr: 0.000003 grad: 0.1402 (0.1620) loss: 0.8477 (0.8450) time: 0.2055 data: 0.1160 max mem: 8452 +Train: [90] [1200/6250] eta: 0:14:16 lr: 0.000003 grad: 0.1527 (0.1607) loss: 0.8371 (0.8449) time: 0.1582 data: 0.0827 max mem: 8452 +Train: [90] [1300/6250] eta: 0:14:02 lr: 0.000003 grad: 0.1442 (0.1593) loss: 0.8342 (0.8447) time: 0.2077 data: 0.1065 max mem: 8452 +Train: [90] [1400/6250] eta: 0:13:49 lr: 0.000003 grad: 0.1502 (0.1586) loss: 0.8399 (0.8446) time: 0.1247 data: 0.0308 max mem: 8452 +Train: [90] [1500/6250] eta: 0:13:29 lr: 0.000003 grad: 0.1480 (0.1579) loss: 0.8486 (0.8445) time: 0.1713 data: 0.0932 max mem: 8452 +Train: [90] [1600/6250] eta: 0:13:10 lr: 0.000003 grad: 0.1447 (0.1574) loss: 0.8476 (0.8444) time: 0.1618 data: 0.0717 max mem: 8452 +Train: [90] [1700/6250] eta: 0:12:49 lr: 0.000003 grad: 0.1514 (0.1569) loss: 0.8382 (0.8440) time: 0.1650 data: 0.0901 max mem: 8452 +Train: [90] [1800/6250] eta: 0:12:32 lr: 0.000003 grad: 0.1504 (0.1566) loss: 0.8381 (0.8438) time: 0.1721 data: 0.0864 max mem: 8452 +Train: [90] [1900/6250] eta: 0:12:16 lr: 0.000003 grad: 0.1462 (0.1562) loss: 0.8416 (0.8435) time: 0.1835 data: 0.0878 max mem: 8452 +Train: [90] [2000/6250] eta: 0:11:57 lr: 0.000003 grad: 0.1411 (0.1557) loss: 0.8382 (0.8433) time: 0.1481 data: 0.0714 max mem: 8452 +Train: [90] [2100/6250] eta: 0:11:39 lr: 0.000003 grad: 0.1532 (0.1555) loss: 0.8392 (0.8429) time: 0.1528 data: 0.0804 max mem: 8452 +Train: [90] [2200/6250] eta: 0:11:21 lr: 0.000003 grad: 0.1476 (0.1553) loss: 0.8451 (0.8427) time: 0.1679 data: 0.0827 max mem: 8452 +Train: [90] [2300/6250] eta: 0:11:03 lr: 0.000003 grad: 0.1581 (0.1553) loss: 0.8344 (0.8423) time: 0.1832 data: 0.1070 max mem: 8452 +Train: [90] [2400/6250] eta: 0:10:45 lr: 0.000003 grad: 0.1465 (0.1551) loss: 0.8395 (0.8420) time: 0.1788 data: 0.0921 max mem: 8452 +Train: [90] [2500/6250] eta: 0:10:27 lr: 0.000003 grad: 0.1484 (0.1548) loss: 0.8344 (0.8418) time: 0.1540 data: 0.0753 max mem: 8452 +Train: [90] [2600/6250] eta: 0:10:10 lr: 0.000003 grad: 0.1481 (0.1546) loss: 0.8355 (0.8415) time: 0.1837 data: 0.1192 max mem: 8452 +Train: [90] [2700/6250] eta: 0:09:52 lr: 0.000003 grad: 0.1500 (0.1544) loss: 0.8352 (0.8414) time: 0.1536 data: 0.0632 max mem: 8452 +Train: [90] [2800/6250] eta: 0:09:35 lr: 0.000003 grad: 0.1525 (0.1544) loss: 0.8377 (0.8412) time: 0.1845 data: 0.1040 max mem: 8452 +Train: [90] [2900/6250] eta: 0:09:16 lr: 0.000003 grad: 0.1496 (0.1545) loss: 0.8456 (0.8410) time: 0.1516 data: 0.0713 max mem: 8452 +Train: [90] [3000/6250] eta: 0:08:59 lr: 0.000003 grad: 0.1522 (0.1544) loss: 0.8333 (0.8408) time: 0.1761 data: 0.1051 max mem: 8452 +Train: [90] [3100/6250] eta: 0:08:43 lr: 0.000003 grad: 0.1474 (0.1544) loss: 0.8391 (0.8407) time: 0.1797 data: 0.0985 max mem: 8452 +Train: [90] [3200/6250] eta: 0:08:27 lr: 0.000003 grad: 0.1392 (0.1544) loss: 0.8373 (0.8405) time: 0.2023 data: 0.1186 max mem: 8452 +Train: [90] [3300/6250] eta: 0:08:10 lr: 0.000003 grad: 0.1561 (0.1543) loss: 0.8367 (0.8403) time: 0.1701 data: 0.0910 max mem: 8452 +Train: [90] [3400/6250] eta: 0:07:54 lr: 0.000003 grad: 0.1487 (0.1543) loss: 0.8346 (0.8402) time: 0.1770 data: 0.1079 max mem: 8452 +Train: [90] [3500/6250] eta: 0:07:39 lr: 0.000003 grad: 0.1503 (0.1543) loss: 0.8320 (0.8399) time: 0.1680 data: 0.0764 max mem: 8452 +Train: [90] [3600/6250] eta: 0:07:22 lr: 0.000003 grad: 0.1580 (0.1543) loss: 0.8289 (0.8398) time: 0.1785 data: 0.0961 max mem: 8452 +Train: [90] [3700/6250] eta: 0:07:05 lr: 0.000003 grad: 0.1570 (0.1544) loss: 0.8293 (0.8396) time: 0.1641 data: 0.0709 max mem: 8452 +Train: [90] [3800/6250] eta: 0:06:48 lr: 0.000003 grad: 0.1530 (0.1546) loss: 0.8369 (0.8394) time: 0.1498 data: 0.0678 max mem: 8452 +Train: [90] [3900/6250] eta: 0:06:31 lr: 0.000003 grad: 0.1502 (0.1546) loss: 0.8364 (0.8392) time: 0.1544 data: 0.0760 max mem: 8452 +Train: [90] [4000/6250] eta: 0:06:14 lr: 0.000003 grad: 0.1553 (0.1548) loss: 0.8352 (0.8390) time: 0.1345 data: 0.0525 max mem: 8452 +Train: [90] [4100/6250] eta: 0:05:57 lr: 0.000003 grad: 0.1526 (0.1548) loss: 0.8335 (0.8390) time: 0.1905 data: 0.1071 max mem: 8452 +Train: [90] [4200/6250] eta: 0:05:40 lr: 0.000003 grad: 0.1530 (0.1548) loss: 0.8277 (0.8388) time: 0.1703 data: 0.0952 max mem: 8452 +Train: [90] [4300/6250] eta: 0:05:25 lr: 0.000003 grad: 0.1445 (0.1547) loss: 0.8381 (0.8387) time: 0.1610 data: 0.0836 max mem: 8452 +Train: [90] [4400/6250] eta: 0:05:08 lr: 0.000003 grad: 0.1523 (0.1547) loss: 0.8395 (0.8386) time: 0.1819 data: 0.1054 max mem: 8452 +Train: [90] [4500/6250] eta: 0:04:51 lr: 0.000003 grad: 0.1447 (0.1548) loss: 0.8399 (0.8384) time: 0.1768 data: 0.1023 max mem: 8452 +Train: [90] [4600/6250] eta: 0:04:34 lr: 0.000003 grad: 0.1450 (0.1547) loss: 0.8321 (0.8384) time: 0.1759 data: 0.0929 max mem: 8452 +Train: [90] [4700/6250] eta: 0:04:18 lr: 0.000003 grad: 0.1597 (0.1548) loss: 0.8314 (0.8382) time: 0.1728 data: 0.0800 max mem: 8452 +Train: [90] [4800/6250] eta: 0:04:01 lr: 0.000003 grad: 0.1529 (0.1548) loss: 0.8295 (0.8381) time: 0.1514 data: 0.0729 max mem: 8452 +Train: [90] [4900/6250] eta: 0:03:44 lr: 0.000003 grad: 0.1521 (0.1549) loss: 0.8363 (0.8380) time: 0.1726 data: 0.0846 max mem: 8452 +Train: [90] [5000/6250] eta: 0:03:27 lr: 0.000003 grad: 0.1565 (0.1548) loss: 0.8325 (0.8379) time: 0.1625 data: 0.0786 max mem: 8452 +Train: [90] [5100/6250] eta: 0:03:11 lr: 0.000003 grad: 0.1427 (0.1547) loss: 0.8354 (0.8378) time: 0.1701 data: 0.0877 max mem: 8452 +Train: [90] [5200/6250] eta: 0:02:54 lr: 0.000003 grad: 0.1427 (0.1546) loss: 0.8337 (0.8377) time: 0.1429 data: 0.0608 max mem: 8452 +Train: [90] [5300/6250] eta: 0:02:37 lr: 0.000003 grad: 0.1488 (0.1546) loss: 0.8397 (0.8377) time: 0.2338 data: 0.1468 max mem: 8452 +Train: [90] [5400/6250] eta: 0:02:21 lr: 0.000003 grad: 0.1508 (0.1545) loss: 0.8334 (0.8376) time: 0.1528 data: 0.0729 max mem: 8452 +Train: [90] [5500/6250] eta: 0:02:04 lr: 0.000003 grad: 0.1534 (0.1544) loss: 0.8297 (0.8375) time: 0.1408 data: 0.0614 max mem: 8452 +Train: [90] [5600/6250] eta: 0:01:47 lr: 0.000003 grad: 0.1535 (0.1545) loss: 0.8380 (0.8375) time: 0.1816 data: 0.1069 max mem: 8452 +Train: [90] [5700/6250] eta: 0:01:31 lr: 0.000003 grad: 0.1541 (0.1544) loss: 0.8276 (0.8374) time: 0.1811 data: 0.1064 max mem: 8452 +Train: [90] [5800/6250] eta: 0:01:14 lr: 0.000003 grad: 0.1533 (0.1544) loss: 0.8242 (0.8374) time: 0.1494 data: 0.0732 max mem: 8452 +Train: [90] [5900/6250] eta: 0:00:58 lr: 0.000003 grad: 0.1476 (0.1545) loss: 0.8301 (0.8372) time: 0.1934 data: 0.1063 max mem: 8452 +Train: [90] [6000/6250] eta: 0:00:41 lr: 0.000003 grad: 0.1432 (0.1545) loss: 0.8351 (0.8371) time: 0.1640 data: 0.0907 max mem: 8452 +Train: [90] [6100/6250] eta: 0:00:24 lr: 0.000003 grad: 0.1574 (0.1545) loss: 0.8265 (0.8369) time: 0.1507 data: 0.0780 max mem: 8452 +Train: [90] [6200/6250] eta: 0:00:08 lr: 0.000003 grad: 0.1441 (0.1545) loss: 0.8356 (0.8369) time: 0.1605 data: 0.0971 max mem: 8452 +Train: [90] [6249/6250] eta: 0:00:00 lr: 0.000003 grad: 0.1459 (0.1545) loss: 0.8413 (0.8368) time: 0.1464 data: 0.0743 max mem: 8452 +Train: [90] Total time: 0:17:22 (0.1669 s / it) +Averaged stats: lr: 0.000003 grad: 0.1459 (0.1545) loss: 0.8413 (0.8368) +Eval (hcp-train-subset): [90] [ 0/62] eta: 0:06:14 loss: 0.8518 (0.8518) time: 6.0484 data: 6.0161 max mem: 8452 +Eval (hcp-train-subset): [90] [61/62] eta: 0:00:00 loss: 0.8397 (0.8431) time: 0.1418 data: 0.1208 max mem: 8452 +Eval (hcp-train-subset): [90] Total time: 0:00:14 (0.2416 s / it) +Averaged stats (hcp-train-subset): loss: 0.8397 (0.8431) +Eval (hcp-val): [90] [ 0/62] eta: 0:06:13 loss: 0.8618 (0.8618) time: 6.0166 data: 5.9881 max mem: 8452 +Eval (hcp-val): [90] [61/62] eta: 0:00:00 loss: 0.8652 (0.8668) time: 0.1371 data: 0.1156 max mem: 8452 +Eval (hcp-val): [90] Total time: 0:00:14 (0.2411 s / it) +Averaged stats (hcp-val): loss: 0.8652 (0.8668) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [91] [ 0/6250] eta: 12:57:12 lr: 0.000003 grad: 0.2555 (0.2555) loss: 0.8397 (0.8397) time: 7.4612 data: 7.3395 max mem: 8452 +Train: [91] [ 100/6250] eta: 0:22:55 lr: 0.000003 grad: 0.1926 (0.2119) loss: 0.8335 (0.8491) time: 0.1915 data: 0.0978 max mem: 8452 +Train: [91] [ 200/6250] eta: 0:18:51 lr: 0.000003 grad: 0.1638 (0.2044) loss: 0.8466 (0.8411) time: 0.1419 data: 0.0221 max mem: 8452 +Train: [91] [ 300/6250] eta: 0:17:46 lr: 0.000003 grad: 0.1687 (0.1951) loss: 0.8373 (0.8399) time: 0.1497 data: 0.0447 max mem: 8452 +Train: [91] [ 400/6250] eta: 0:17:00 lr: 0.000003 grad: 0.1702 (0.1937) loss: 0.8327 (0.8378) time: 0.1426 data: 0.0458 max mem: 8452 +Train: [91] [ 500/6250] eta: 0:16:23 lr: 0.000003 grad: 0.1699 (0.1900) loss: 0.8369 (0.8367) time: 0.1357 data: 0.0353 max mem: 8452 +Train: [91] [ 600/6250] eta: 0:15:42 lr: 0.000003 grad: 0.1490 (0.1854) loss: 0.8355 (0.8366) time: 0.1419 data: 0.0373 max mem: 8452 +Train: [91] [ 700/6250] eta: 0:15:11 lr: 0.000003 grad: 0.1534 (0.1821) loss: 0.8351 (0.8362) time: 0.1245 data: 0.0313 max mem: 8452 +Train: [91] [ 800/6250] eta: 0:14:50 lr: 0.000003 grad: 0.1629 (0.1792) loss: 0.8419 (0.8361) time: 0.1563 data: 0.0681 max mem: 8452 +Train: [91] [ 900/6250] eta: 0:14:24 lr: 0.000003 grad: 0.1503 (0.1768) loss: 0.8349 (0.8361) time: 0.1573 data: 0.0703 max mem: 8452 +Train: [91] [1000/6250] eta: 0:13:55 lr: 0.000003 grad: 0.1621 (0.1747) loss: 0.8406 (0.8362) time: 0.1374 data: 0.0552 max mem: 8452 +Train: [91] [1100/6250] eta: 0:13:33 lr: 0.000003 grad: 0.1453 (0.1725) loss: 0.8388 (0.8367) time: 0.1416 data: 0.0466 max mem: 8452 +Train: [91] [1200/6250] eta: 0:13:16 lr: 0.000003 grad: 0.1494 (0.1707) loss: 0.8376 (0.8371) time: 0.1467 data: 0.0388 max mem: 8452 +Train: [91] [1300/6250] eta: 0:12:57 lr: 0.000003 grad: 0.1431 (0.1690) loss: 0.8363 (0.8373) time: 0.1771 data: 0.0958 max mem: 8452 +Train: [91] [1400/6250] eta: 0:12:40 lr: 0.000003 grad: 0.1448 (0.1678) loss: 0.8397 (0.8376) time: 0.1624 data: 0.0721 max mem: 8452 +Train: [91] [1500/6250] eta: 0:12:20 lr: 0.000003 grad: 0.1499 (0.1672) loss: 0.8375 (0.8376) time: 0.1365 data: 0.0502 max mem: 8452 +Train: [91] [1600/6250] eta: 0:12:01 lr: 0.000003 grad: 0.1568 (0.1664) loss: 0.8364 (0.8377) time: 0.1380 data: 0.0469 max mem: 8452 +Train: [91] [1700/6250] eta: 0:11:43 lr: 0.000003 grad: 0.1571 (0.1660) loss: 0.8398 (0.8376) time: 0.1333 data: 0.0588 max mem: 8452 +Train: [91] [1800/6250] eta: 0:11:28 lr: 0.000003 grad: 0.1616 (0.1655) loss: 0.8325 (0.8376) time: 0.1440 data: 0.0464 max mem: 8452 +Train: [91] [1900/6250] eta: 0:11:13 lr: 0.000003 grad: 0.1710 (0.1654) loss: 0.8348 (0.8375) time: 0.1537 data: 0.0698 max mem: 8452 +Train: [91] [2000/6250] eta: 0:10:58 lr: 0.000003 grad: 0.1504 (0.1652) loss: 0.8406 (0.8372) time: 0.1664 data: 0.0871 max mem: 8452 +Train: [91] [2100/6250] eta: 0:10:41 lr: 0.000003 grad: 0.1496 (0.1648) loss: 0.8314 (0.8370) time: 0.1379 data: 0.0543 max mem: 8452 +Train: [91] [2200/6250] eta: 0:10:25 lr: 0.000003 grad: 0.1604 (0.1646) loss: 0.8298 (0.8367) time: 0.1620 data: 0.0760 max mem: 8452 +Train: [91] [2300/6250] eta: 0:10:10 lr: 0.000003 grad: 0.1576 (0.1643) loss: 0.8331 (0.8365) time: 0.1735 data: 0.0884 max mem: 8452 +Train: [91] [2400/6250] eta: 0:09:54 lr: 0.000003 grad: 0.1751 (0.1642) loss: 0.8225 (0.8362) time: 0.1646 data: 0.0862 max mem: 8452 +Train: [91] [2500/6250] eta: 0:09:43 lr: 0.000003 grad: 0.1595 (0.1639) loss: 0.8252 (0.8359) time: 0.3060 data: 0.2056 max mem: 8452 +Train: [91] [2600/6250] eta: 0:09:24 lr: 0.000003 grad: 0.1509 (0.1636) loss: 0.8283 (0.8357) time: 0.1654 data: 0.0874 max mem: 8452 +Train: [91] [2700/6250] eta: 0:09:11 lr: 0.000002 grad: 0.1430 (0.1632) loss: 0.8383 (0.8356) time: 0.1325 data: 0.0445 max mem: 8452 +Train: [91] [2800/6250] eta: 0:08:55 lr: 0.000002 grad: 0.1505 (0.1629) loss: 0.8313 (0.8354) time: 0.1528 data: 0.0698 max mem: 8452 +Train: [91] [2900/6250] eta: 0:08:38 lr: 0.000002 grad: 0.1473 (0.1625) loss: 0.8342 (0.8353) time: 0.1670 data: 0.0880 max mem: 8452 +Train: [91] [3000/6250] eta: 0:08:26 lr: 0.000002 grad: 0.1601 (0.1623) loss: 0.8359 (0.8353) time: 0.2792 data: 0.2001 max mem: 8452 +Train: [91] [3100/6250] eta: 0:08:09 lr: 0.000002 grad: 0.1480 (0.1620) loss: 0.8349 (0.8353) time: 0.1489 data: 0.0763 max mem: 8452 +Train: [91] [3200/6250] eta: 0:07:53 lr: 0.000002 grad: 0.1507 (0.1617) loss: 0.8399 (0.8353) time: 0.1471 data: 0.0685 max mem: 8452 +Train: [91] [3300/6250] eta: 0:07:38 lr: 0.000002 grad: 0.1548 (0.1615) loss: 0.8396 (0.8353) time: 0.1444 data: 0.0570 max mem: 8452 +Train: [91] [3400/6250] eta: 0:07:23 lr: 0.000002 grad: 0.1517 (0.1612) loss: 0.8355 (0.8354) time: 0.1410 data: 0.0531 max mem: 8452 +Train: [91] [3500/6250] eta: 0:07:08 lr: 0.000002 grad: 0.1570 (0.1610) loss: 0.8364 (0.8354) time: 0.1583 data: 0.0723 max mem: 8452 +Train: [91] [3600/6250] eta: 0:06:53 lr: 0.000002 grad: 0.1583 (0.1608) loss: 0.8349 (0.8354) time: 0.1581 data: 0.0753 max mem: 8452 +Train: [91] [3700/6250] eta: 0:06:38 lr: 0.000002 grad: 0.1565 (0.1607) loss: 0.8332 (0.8354) time: 0.1803 data: 0.0991 max mem: 8452 +Train: [91] [3800/6250] eta: 0:06:21 lr: 0.000002 grad: 0.1527 (0.1605) loss: 0.8424 (0.8354) time: 0.1499 data: 0.0644 max mem: 8452 +Train: [91] [3900/6250] eta: 0:06:05 lr: 0.000002 grad: 0.1513 (0.1602) loss: 0.8412 (0.8355) time: 0.1200 data: 0.0312 max mem: 8452 +Train: [91] [4000/6250] eta: 0:05:49 lr: 0.000002 grad: 0.1475 (0.1600) loss: 0.8417 (0.8356) time: 0.1355 data: 0.0448 max mem: 8452 +Train: [91] [4100/6250] eta: 0:05:33 lr: 0.000002 grad: 0.1560 (0.1598) loss: 0.8386 (0.8357) time: 0.1863 data: 0.1046 max mem: 8452 +Train: [91] [4200/6250] eta: 0:05:18 lr: 0.000002 grad: 0.1490 (0.1597) loss: 0.8353 (0.8358) time: 0.1699 data: 0.0889 max mem: 8452 +Train: [91] [4300/6250] eta: 0:05:02 lr: 0.000002 grad: 0.1494 (0.1596) loss: 0.8409 (0.8359) time: 0.1543 data: 0.0834 max mem: 8452 +Train: [91] [4400/6250] eta: 0:04:47 lr: 0.000002 grad: 0.1633 (0.1596) loss: 0.8283 (0.8359) time: 0.1779 data: 0.0953 max mem: 8452 +Train: [91] [4500/6250] eta: 0:04:32 lr: 0.000002 grad: 0.1471 (0.1595) loss: 0.8337 (0.8359) time: 0.1423 data: 0.0614 max mem: 8452 +Train: [91] [4600/6250] eta: 0:04:16 lr: 0.000002 grad: 0.1481 (0.1595) loss: 0.8420 (0.8360) time: 0.1768 data: 0.1040 max mem: 8452 +Train: [91] [4700/6250] eta: 0:04:01 lr: 0.000002 grad: 0.1582 (0.1593) loss: 0.8270 (0.8360) time: 0.1439 data: 0.0671 max mem: 8452 +Train: [91] [4800/6250] eta: 0:03:45 lr: 0.000002 grad: 0.1452 (0.1593) loss: 0.8354 (0.8359) time: 0.1415 data: 0.0654 max mem: 8452 +Train: [91] [4900/6250] eta: 0:03:29 lr: 0.000002 grad: 0.1517 (0.1592) loss: 0.8381 (0.8359) time: 0.1435 data: 0.0535 max mem: 8452 +Train: [91] [5000/6250] eta: 0:03:13 lr: 0.000002 grad: 0.1559 (0.1591) loss: 0.8298 (0.8359) time: 0.1504 data: 0.0786 max mem: 8452 +Train: [91] [5100/6250] eta: 0:02:58 lr: 0.000002 grad: 0.1493 (0.1590) loss: 0.8367 (0.8359) time: 0.1557 data: 0.0684 max mem: 8452 +Train: [91] [5200/6250] eta: 0:02:42 lr: 0.000002 grad: 0.1536 (0.1589) loss: 0.8388 (0.8359) time: 0.1608 data: 0.0746 max mem: 8452 +Train: [91] [5300/6250] eta: 0:02:28 lr: 0.000002 grad: 0.1511 (0.1589) loss: 0.8389 (0.8359) time: 0.1594 data: 0.0637 max mem: 8452 +Train: [91] [5400/6250] eta: 0:02:12 lr: 0.000002 grad: 0.1641 (0.1590) loss: 0.8304 (0.8358) time: 0.1222 data: 0.0456 max mem: 8452 +Train: [91] [5500/6250] eta: 0:01:57 lr: 0.000002 grad: 0.1595 (0.1590) loss: 0.8328 (0.8357) time: 0.1180 data: 0.0003 max mem: 8452 +Train: [91] [5600/6250] eta: 0:01:41 lr: 0.000002 grad: 0.1556 (0.1591) loss: 0.8329 (0.8357) time: 0.1587 data: 0.0608 max mem: 8452 +Train: [91] [5700/6250] eta: 0:01:25 lr: 0.000002 grad: 0.1516 (0.1591) loss: 0.8270 (0.8356) time: 0.1609 data: 0.0755 max mem: 8452 +Train: [91] [5800/6250] eta: 0:01:10 lr: 0.000002 grad: 0.1536 (0.1591) loss: 0.8305 (0.8355) time: 0.1332 data: 0.0548 max mem: 8452 +Train: [91] [5900/6250] eta: 0:00:54 lr: 0.000002 grad: 0.1526 (0.1590) loss: 0.8324 (0.8355) time: 0.1900 data: 0.1132 max mem: 8452 +Train: [91] [6000/6250] eta: 0:00:39 lr: 0.000002 grad: 0.1512 (0.1590) loss: 0.8336 (0.8354) time: 0.1308 data: 0.0565 max mem: 8452 +Train: [91] [6100/6250] eta: 0:00:23 lr: 0.000002 grad: 0.1526 (0.1590) loss: 0.8306 (0.8354) time: 0.1621 data: 0.0764 max mem: 8452 +Train: [91] [6200/6250] eta: 0:00:07 lr: 0.000002 grad: 0.1476 (0.1590) loss: 0.8351 (0.8353) time: 0.1478 data: 0.0672 max mem: 8452 +Train: [91] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1552 (0.1590) loss: 0.8306 (0.8353) time: 0.1505 data: 0.0702 max mem: 8452 +Train: [91] Total time: 0:16:21 (0.1570 s / it) +Averaged stats: lr: 0.000002 grad: 0.1552 (0.1590) loss: 0.8306 (0.8353) +Eval (hcp-train-subset): [91] [ 0/62] eta: 0:06:47 loss: 0.8496 (0.8496) time: 6.5734 data: 6.5355 max mem: 8452 +Eval (hcp-train-subset): [91] [61/62] eta: 0:00:00 loss: 0.8380 (0.8410) time: 0.1126 data: 0.0911 max mem: 8452 +Eval (hcp-train-subset): [91] Total time: 0:00:15 (0.2425 s / it) +Averaged stats (hcp-train-subset): loss: 0.8380 (0.8410) +Eval (hcp-val): [91] [ 0/62] eta: 0:04:53 loss: 0.8638 (0.8638) time: 4.7409 data: 4.6724 max mem: 8452 +Eval (hcp-val): [91] [61/62] eta: 0:00:00 loss: 0.8661 (0.8666) time: 0.1790 data: 0.1572 max mem: 8452 +Eval (hcp-val): [91] Total time: 0:00:17 (0.2746 s / it) +Averaged stats (hcp-val): loss: 0.8661 (0.8666) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [92] [ 0/6250] eta: 12:23:10 lr: 0.000002 grad: 0.2785 (0.2785) loss: 0.8236 (0.8236) time: 7.1345 data: 7.0441 max mem: 8452 +Train: [92] [ 100/6250] eta: 0:22:44 lr: 0.000002 grad: 0.1770 (0.1905) loss: 0.8350 (0.8485) time: 0.1758 data: 0.0763 max mem: 8452 +Train: [92] [ 200/6250] eta: 0:19:27 lr: 0.000002 grad: 0.1512 (0.1767) loss: 0.8418 (0.8473) time: 0.1761 data: 0.0738 max mem: 8452 +Train: [92] [ 300/6250] eta: 0:18:11 lr: 0.000002 grad: 0.1606 (0.1731) loss: 0.8292 (0.8438) time: 0.1776 data: 0.0691 max mem: 8452 +Train: [92] [ 400/6250] eta: 0:17:20 lr: 0.000002 grad: 0.1635 (0.1735) loss: 0.8289 (0.8409) time: 0.1750 data: 0.0828 max mem: 8452 +Train: [92] [ 500/6250] eta: 0:16:44 lr: 0.000002 grad: 0.1621 (0.1713) loss: 0.8411 (0.8396) time: 0.1370 data: 0.0394 max mem: 8452 +Train: [92] [ 600/6250] eta: 0:16:18 lr: 0.000002 grad: 0.1565 (0.1687) loss: 0.8429 (0.8397) time: 0.2107 data: 0.1113 max mem: 8452 +Train: [92] [ 700/6250] eta: 0:15:40 lr: 0.000002 grad: 0.1461 (0.1665) loss: 0.8420 (0.8402) time: 0.1460 data: 0.0517 max mem: 8452 +Train: [92] [ 800/6250] eta: 0:15:15 lr: 0.000002 grad: 0.1490 (0.1650) loss: 0.8441 (0.8408) time: 0.1486 data: 0.0498 max mem: 8452 +Train: [92] [ 900/6250] eta: 0:14:46 lr: 0.000002 grad: 0.1500 (0.1644) loss: 0.8426 (0.8409) time: 0.1412 data: 0.0473 max mem: 8452 +Train: [92] [1000/6250] eta: 0:14:27 lr: 0.000002 grad: 0.1457 (0.1635) loss: 0.8397 (0.8410) time: 0.1712 data: 0.0862 max mem: 8452 +Train: [92] [1100/6250] eta: 0:14:00 lr: 0.000002 grad: 0.1554 (0.1625) loss: 0.8368 (0.8409) time: 0.1396 data: 0.0506 max mem: 8452 +Train: [92] [1200/6250] eta: 0:13:40 lr: 0.000002 grad: 0.1565 (0.1624) loss: 0.8392 (0.8408) time: 0.1457 data: 0.0628 max mem: 8452 +Train: [92] [1300/6250] eta: 0:13:19 lr: 0.000002 grad: 0.1540 (0.1621) loss: 0.8387 (0.8404) time: 0.1492 data: 0.0570 max mem: 8452 +Train: [92] [1400/6250] eta: 0:13:04 lr: 0.000002 grad: 0.1510 (0.1617) loss: 0.8400 (0.8403) time: 0.1779 data: 0.0927 max mem: 8452 +Train: [92] [1500/6250] eta: 0:12:43 lr: 0.000002 grad: 0.1533 (0.1615) loss: 0.8331 (0.8399) time: 0.1582 data: 0.0578 max mem: 8452 +Train: [92] [1600/6250] eta: 0:12:26 lr: 0.000002 grad: 0.1503 (0.1610) loss: 0.8391 (0.8397) time: 0.1459 data: 0.0500 max mem: 8452 +Train: [92] [1700/6250] eta: 0:12:13 lr: 0.000002 grad: 0.1521 (0.1606) loss: 0.8390 (0.8397) time: 0.1578 data: 0.0382 max mem: 8452 +Train: [92] [1800/6250] eta: 0:11:54 lr: 0.000002 grad: 0.1413 (0.1604) loss: 0.8400 (0.8396) time: 0.1600 data: 0.0839 max mem: 8452 +Train: [92] [1900/6250] eta: 0:11:39 lr: 0.000002 grad: 0.1547 (0.1600) loss: 0.8299 (0.8394) time: 0.1770 data: 0.0923 max mem: 8452 +Train: [92] [2000/6250] eta: 0:11:20 lr: 0.000002 grad: 0.1436 (0.1599) loss: 0.8396 (0.8393) time: 0.1540 data: 0.0757 max mem: 8452 +Train: [92] [2100/6250] eta: 0:11:04 lr: 0.000002 grad: 0.1540 (0.1595) loss: 0.8376 (0.8392) time: 0.1603 data: 0.0721 max mem: 8452 +Train: [92] [2200/6250] eta: 0:10:54 lr: 0.000002 grad: 0.1533 (0.1595) loss: 0.8330 (0.8391) time: 0.1405 data: 0.0494 max mem: 8452 +Train: [92] [2300/6250] eta: 0:10:35 lr: 0.000002 grad: 0.1523 (0.1593) loss: 0.8389 (0.8389) time: 0.1375 data: 0.0565 max mem: 8452 +Train: [92] [2400/6250] eta: 0:10:20 lr: 0.000002 grad: 0.1523 (0.1592) loss: 0.8387 (0.8389) time: 0.1684 data: 0.0719 max mem: 8452 +Train: [92] [2500/6250] eta: 0:10:02 lr: 0.000002 grad: 0.1501 (0.1591) loss: 0.8297 (0.8387) time: 0.1459 data: 0.0608 max mem: 8452 +Train: [92] [2600/6250] eta: 0:09:46 lr: 0.000002 grad: 0.1580 (0.1590) loss: 0.8241 (0.8385) time: 0.1684 data: 0.0713 max mem: 8452 +Train: [92] [2700/6250] eta: 0:09:31 lr: 0.000002 grad: 0.1525 (0.1591) loss: 0.8296 (0.8382) time: 0.1625 data: 0.0866 max mem: 8452 +Train: [92] [2800/6250] eta: 0:09:14 lr: 0.000002 grad: 0.1505 (0.1590) loss: 0.8274 (0.8380) time: 0.1834 data: 0.1075 max mem: 8452 +Train: [92] [2900/6250] eta: 0:08:57 lr: 0.000002 grad: 0.1658 (0.1591) loss: 0.8279 (0.8377) time: 0.1614 data: 0.0872 max mem: 8452 +Train: [92] [3000/6250] eta: 0:08:41 lr: 0.000002 grad: 0.1561 (0.1591) loss: 0.8293 (0.8376) time: 0.1504 data: 0.0748 max mem: 8452 +Train: [92] [3100/6250] eta: 0:08:27 lr: 0.000002 grad: 0.1550 (0.1592) loss: 0.8264 (0.8374) time: 0.1779 data: 0.0972 max mem: 8452 +Train: [92] [3200/6250] eta: 0:08:11 lr: 0.000002 grad: 0.1604 (0.1591) loss: 0.8365 (0.8373) time: 0.1580 data: 0.0813 max mem: 8452 +Train: [92] [3300/6250] eta: 0:07:55 lr: 0.000002 grad: 0.1489 (0.1590) loss: 0.8335 (0.8372) time: 0.1597 data: 0.0775 max mem: 8452 +Train: [92] [3400/6250] eta: 0:07:39 lr: 0.000002 grad: 0.1525 (0.1591) loss: 0.8310 (0.8370) time: 0.1635 data: 0.0793 max mem: 8452 +Train: [92] [3500/6250] eta: 0:07:23 lr: 0.000002 grad: 0.1598 (0.1590) loss: 0.8297 (0.8369) time: 0.1555 data: 0.0749 max mem: 8452 +Train: [92] [3600/6250] eta: 0:07:06 lr: 0.000002 grad: 0.1587 (0.1590) loss: 0.8281 (0.8368) time: 0.1649 data: 0.0883 max mem: 8452 +Train: [92] [3700/6250] eta: 0:06:49 lr: 0.000002 grad: 0.1523 (0.1589) loss: 0.8291 (0.8368) time: 0.1428 data: 0.0554 max mem: 8452 +Train: [92] [3800/6250] eta: 0:06:32 lr: 0.000002 grad: 0.1450 (0.1588) loss: 0.8397 (0.8367) time: 0.1521 data: 0.0690 max mem: 8452 +Train: [92] [3900/6250] eta: 0:06:16 lr: 0.000002 grad: 0.1612 (0.1588) loss: 0.8315 (0.8367) time: 0.1447 data: 0.0654 max mem: 8452 +Train: [92] [4000/6250] eta: 0:05:59 lr: 0.000002 grad: 0.1581 (0.1587) loss: 0.8385 (0.8367) time: 0.1565 data: 0.0829 max mem: 8452 +Train: [92] [4100/6250] eta: 0:05:43 lr: 0.000002 grad: 0.1492 (0.1586) loss: 0.8393 (0.8367) time: 0.1159 data: 0.0273 max mem: 8452 +Train: [92] [4200/6250] eta: 0:05:27 lr: 0.000002 grad: 0.1573 (0.1585) loss: 0.8437 (0.8368) time: 0.1669 data: 0.1037 max mem: 8452 +Train: [92] [4300/6250] eta: 0:05:10 lr: 0.000002 grad: 0.1399 (0.1583) loss: 0.8373 (0.8368) time: 0.1289 data: 0.0379 max mem: 8452 +Train: [92] [4400/6250] eta: 0:04:55 lr: 0.000002 grad: 0.1492 (0.1583) loss: 0.8311 (0.8367) time: 0.1468 data: 0.0667 max mem: 8452 +Train: [92] [4500/6250] eta: 0:04:39 lr: 0.000002 grad: 0.1463 (0.1582) loss: 0.8435 (0.8368) time: 0.1622 data: 0.0780 max mem: 8452 +Train: [92] [4600/6250] eta: 0:04:23 lr: 0.000002 grad: 0.1533 (0.1580) loss: 0.8352 (0.8369) time: 0.1702 data: 0.0868 max mem: 8452 +Train: [92] [4700/6250] eta: 0:04:07 lr: 0.000002 grad: 0.1492 (0.1579) loss: 0.8367 (0.8369) time: 0.1932 data: 0.1143 max mem: 8452 +Train: [92] [4800/6250] eta: 0:03:51 lr: 0.000002 grad: 0.1432 (0.1578) loss: 0.8386 (0.8369) time: 0.1740 data: 0.0916 max mem: 8452 +Train: [92] [4900/6250] eta: 0:03:36 lr: 0.000002 grad: 0.1555 (0.1577) loss: 0.8410 (0.8370) time: 0.1735 data: 0.0888 max mem: 8452 +Train: [92] [5000/6250] eta: 0:03:19 lr: 0.000002 grad: 0.1571 (0.1577) loss: 0.8357 (0.8370) time: 0.1562 data: 0.0699 max mem: 8452 +Train: [92] [5100/6250] eta: 0:03:03 lr: 0.000002 grad: 0.1592 (0.1577) loss: 0.8302 (0.8370) time: 0.1493 data: 0.0617 max mem: 8452 +Train: [92] [5200/6250] eta: 0:02:47 lr: 0.000002 grad: 0.1507 (0.1577) loss: 0.8408 (0.8370) time: 0.1612 data: 0.0807 max mem: 8452 +Train: [92] [5300/6250] eta: 0:02:31 lr: 0.000002 grad: 0.1451 (0.1577) loss: 0.8375 (0.8370) time: 0.1509 data: 0.0638 max mem: 8452 +Train: [92] [5400/6250] eta: 0:02:15 lr: 0.000002 grad: 0.1593 (0.1577) loss: 0.8309 (0.8370) time: 0.1942 data: 0.1069 max mem: 8452 +Train: [92] [5500/6250] eta: 0:01:59 lr: 0.000002 grad: 0.1520 (0.1576) loss: 0.8372 (0.8370) time: 0.1587 data: 0.0732 max mem: 8452 +Train: [92] [5600/6250] eta: 0:01:43 lr: 0.000002 grad: 0.1475 (0.1576) loss: 0.8380 (0.8371) time: 0.1636 data: 0.0749 max mem: 8452 +Train: [92] [5700/6250] eta: 0:01:27 lr: 0.000002 grad: 0.1496 (0.1575) loss: 0.8380 (0.8371) time: 0.1708 data: 0.0890 max mem: 8452 +Train: [92] [5800/6250] eta: 0:01:11 lr: 0.000002 grad: 0.1492 (0.1573) loss: 0.8370 (0.8372) time: 0.1513 data: 0.0634 max mem: 8452 +Train: [92] [5900/6250] eta: 0:00:55 lr: 0.000002 grad: 0.1436 (0.1573) loss: 0.8389 (0.8372) time: 0.1514 data: 0.0462 max mem: 8452 +Train: [92] [6000/6250] eta: 0:00:39 lr: 0.000002 grad: 0.1514 (0.1572) loss: 0.8341 (0.8372) time: 0.1505 data: 0.0676 max mem: 8452 +Train: [92] [6100/6250] eta: 0:00:23 lr: 0.000002 grad: 0.1444 (0.1571) loss: 0.8360 (0.8372) time: 0.1620 data: 0.0658 max mem: 8452 +Train: [92] [6200/6250] eta: 0:00:07 lr: 0.000002 grad: 0.1418 (0.1570) loss: 0.8369 (0.8372) time: 0.1589 data: 0.0756 max mem: 8452 +Train: [92] [6249/6250] eta: 0:00:00 lr: 0.000002 grad: 0.1572 (0.1571) loss: 0.8304 (0.8372) time: 0.1828 data: 0.0994 max mem: 8452 +Train: [92] Total time: 0:16:41 (0.1602 s / it) +Averaged stats: lr: 0.000002 grad: 0.1572 (0.1571) loss: 0.8304 (0.8372) +Eval (hcp-train-subset): [92] [ 0/62] eta: 0:05:27 loss: 0.8505 (0.8505) time: 5.2839 data: 5.2569 max mem: 8452 +Eval (hcp-train-subset): [92] [61/62] eta: 0:00:00 loss: 0.8378 (0.8406) time: 0.1421 data: 0.1211 max mem: 8452 +Eval (hcp-train-subset): [92] Total time: 0:00:15 (0.2502 s / it) +Averaged stats (hcp-train-subset): loss: 0.8378 (0.8406) +Eval (hcp-val): [92] [ 0/62] eta: 0:05:46 loss: 0.8625 (0.8625) time: 5.5830 data: 5.5577 max mem: 8452 +Eval (hcp-val): [92] [61/62] eta: 0:00:00 loss: 0.8641 (0.8661) time: 0.1230 data: 0.1020 max mem: 8452 +Eval (hcp-val): [92] Total time: 0:00:15 (0.2508 s / it) +Averaged stats (hcp-val): loss: 0.8641 (0.8661) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [93] [ 0/6250] eta: 9:07:00 lr: 0.000002 grad: 0.4581 (0.4581) loss: 0.8470 (0.8470) time: 5.2512 data: 4.9715 max mem: 8452 +Train: [93] [ 100/6250] eta: 0:22:17 lr: 0.000002 grad: 0.1772 (0.2031) loss: 0.8565 (0.8471) time: 0.1432 data: 0.0469 max mem: 8452 +Train: [93] [ 200/6250] eta: 0:19:28 lr: 0.000002 grad: 0.1649 (0.1900) loss: 0.8506 (0.8478) time: 0.1688 data: 0.0719 max mem: 8452 +Train: [93] [ 300/6250] eta: 0:18:08 lr: 0.000002 grad: 0.1756 (0.1854) loss: 0.8415 (0.8466) time: 0.1552 data: 0.0513 max mem: 8452 +Train: [93] [ 400/6250] eta: 0:17:16 lr: 0.000002 grad: 0.1545 (0.1800) loss: 0.8450 (0.8460) time: 0.1545 data: 0.0671 max mem: 8452 +Train: [93] [ 500/6250] eta: 0:16:39 lr: 0.000002 grad: 0.1541 (0.1754) loss: 0.8416 (0.8463) time: 0.1512 data: 0.0389 max mem: 8452 +Train: [93] [ 600/6250] eta: 0:16:01 lr: 0.000002 grad: 0.1553 (0.1730) loss: 0.8415 (0.8462) time: 0.1537 data: 0.0599 max mem: 8452 +Train: [93] [ 700/6250] eta: 0:15:31 lr: 0.000002 grad: 0.1578 (0.1712) loss: 0.8372 (0.8460) time: 0.1584 data: 0.0766 max mem: 8452 +Train: [93] [ 800/6250] eta: 0:15:06 lr: 0.000002 grad: 0.1562 (0.1695) loss: 0.8428 (0.8458) time: 0.1695 data: 0.0823 max mem: 8452 +Train: [93] [ 900/6250] eta: 0:14:43 lr: 0.000002 grad: 0.1570 (0.1692) loss: 0.8510 (0.8455) time: 0.1672 data: 0.0852 max mem: 8452 +Train: [93] [1000/6250] eta: 0:14:20 lr: 0.000002 grad: 0.1466 (0.1681) loss: 0.8465 (0.8454) time: 0.1666 data: 0.0670 max mem: 8452 +Train: [93] [1100/6250] eta: 0:14:01 lr: 0.000002 grad: 0.1471 (0.1671) loss: 0.8338 (0.8450) time: 0.1434 data: 0.0558 max mem: 8452 +Train: [93] [1200/6250] eta: 0:13:49 lr: 0.000002 grad: 0.1518 (0.1662) loss: 0.8456 (0.8448) time: 0.1195 data: 0.0006 max mem: 8452 +Train: [93] [1300/6250] eta: 0:13:31 lr: 0.000002 grad: 0.1511 (0.1657) loss: 0.8433 (0.8445) time: 0.1798 data: 0.1017 max mem: 8452 +Train: [93] [1400/6250] eta: 0:13:09 lr: 0.000002 grad: 0.1517 (0.1653) loss: 0.8396 (0.8442) time: 0.1586 data: 0.0573 max mem: 8452 +Train: [93] [1500/6250] eta: 0:12:54 lr: 0.000002 grad: 0.1476 (0.1649) loss: 0.8398 (0.8438) time: 0.2180 data: 0.1346 max mem: 8452 +Train: [93] [1600/6250] eta: 0:12:35 lr: 0.000002 grad: 0.1630 (0.1646) loss: 0.8397 (0.8435) time: 0.1657 data: 0.0765 max mem: 8452 +Train: [93] [1700/6250] eta: 0:12:19 lr: 0.000002 grad: 0.1575 (0.1645) loss: 0.8403 (0.8432) time: 0.1653 data: 0.0903 max mem: 8452 +Train: [93] [1800/6250] eta: 0:12:00 lr: 0.000002 grad: 0.1499 (0.1645) loss: 0.8428 (0.8427) time: 0.1444 data: 0.0560 max mem: 8452 +Train: [93] [1900/6250] eta: 0:11:43 lr: 0.000002 grad: 0.1499 (0.1643) loss: 0.8420 (0.8424) time: 0.1429 data: 0.0641 max mem: 8452 +Train: [93] [2000/6250] eta: 0:11:25 lr: 0.000002 grad: 0.1595 (0.1644) loss: 0.8387 (0.8420) time: 0.1615 data: 0.0874 max mem: 8452 +Train: [93] [2100/6250] eta: 0:11:08 lr: 0.000002 grad: 0.1574 (0.1642) loss: 0.8337 (0.8416) time: 0.1672 data: 0.0928 max mem: 8452 +Train: [93] [2200/6250] eta: 0:10:52 lr: 0.000002 grad: 0.1620 (0.1641) loss: 0.8344 (0.8412) time: 0.1858 data: 0.1113 max mem: 8452 +Train: [93] [2300/6250] eta: 0:10:34 lr: 0.000001 grad: 0.1520 (0.1639) loss: 0.8374 (0.8410) time: 0.1655 data: 0.0873 max mem: 8452 +Train: [93] [2400/6250] eta: 0:10:16 lr: 0.000001 grad: 0.1697 (0.1639) loss: 0.8310 (0.8407) time: 0.1579 data: 0.0810 max mem: 8452 +Train: [93] [2500/6250] eta: 0:09:59 lr: 0.000001 grad: 0.1695 (0.1640) loss: 0.8345 (0.8404) time: 0.1444 data: 0.0678 max mem: 8452 +Train: [93] [2600/6250] eta: 0:09:43 lr: 0.000001 grad: 0.1653 (0.1641) loss: 0.8280 (0.8401) time: 0.1533 data: 0.0691 max mem: 8452 +Train: [93] [2700/6250] eta: 0:09:27 lr: 0.000001 grad: 0.1563 (0.1642) loss: 0.8290 (0.8399) time: 0.1524 data: 0.0677 max mem: 8452 +Train: [93] [2800/6250] eta: 0:09:10 lr: 0.000001 grad: 0.1723 (0.1642) loss: 0.8276 (0.8395) time: 0.1639 data: 0.0935 max mem: 8452 +Train: [93] [2900/6250] eta: 0:08:56 lr: 0.000001 grad: 0.1586 (0.1641) loss: 0.8374 (0.8393) time: 0.1984 data: 0.1358 max mem: 8452 +Train: [93] [3000/6250] eta: 0:08:40 lr: 0.000001 grad: 0.1571 (0.1640) loss: 0.8276 (0.8391) time: 0.1741 data: 0.1025 max mem: 8452 +Train: [93] [3100/6250] eta: 0:08:24 lr: 0.000001 grad: 0.1662 (0.1639) loss: 0.8333 (0.8389) time: 0.1570 data: 0.0746 max mem: 8452 +Train: [93] [3200/6250] eta: 0:08:08 lr: 0.000001 grad: 0.1570 (0.1637) loss: 0.8377 (0.8388) time: 0.1444 data: 0.0566 max mem: 8452 +Train: [93] [3300/6250] eta: 0:07:52 lr: 0.000001 grad: 0.1549 (0.1636) loss: 0.8426 (0.8387) time: 0.1573 data: 0.0847 max mem: 8452 +Train: [93] [3400/6250] eta: 0:07:36 lr: 0.000001 grad: 0.1529 (0.1636) loss: 0.8352 (0.8385) time: 0.1644 data: 0.0806 max mem: 8452 +Train: [93] [3500/6250] eta: 0:07:20 lr: 0.000001 grad: 0.1602 (0.1638) loss: 0.8195 (0.8381) time: 0.1682 data: 0.0808 max mem: 8452 +Train: [93] [3600/6250] eta: 0:07:03 lr: 0.000001 grad: 0.1640 (0.1638) loss: 0.8344 (0.8379) time: 0.1461 data: 0.0511 max mem: 8452 +Train: [93] [3700/6250] eta: 0:06:46 lr: 0.000001 grad: 0.1519 (0.1636) loss: 0.8355 (0.8378) time: 0.1450 data: 0.0502 max mem: 8452 +Train: [93] [3800/6250] eta: 0:06:29 lr: 0.000001 grad: 0.1607 (0.1636) loss: 0.8344 (0.8376) time: 0.1570 data: 0.0761 max mem: 8452 +Train: [93] [3900/6250] eta: 0:06:13 lr: 0.000001 grad: 0.1694 (0.1636) loss: 0.8277 (0.8374) time: 0.1370 data: 0.0511 max mem: 8452 +Train: [93] [4000/6250] eta: 0:05:56 lr: 0.000001 grad: 0.1641 (0.1636) loss: 0.8354 (0.8372) time: 0.1597 data: 0.0821 max mem: 8452 +Train: [93] [4100/6250] eta: 0:05:40 lr: 0.000001 grad: 0.1595 (0.1636) loss: 0.8349 (0.8371) time: 0.1350 data: 0.0553 max mem: 8452 +Train: [93] [4200/6250] eta: 0:05:23 lr: 0.000001 grad: 0.1522 (0.1634) loss: 0.8327 (0.8369) time: 0.1418 data: 0.0638 max mem: 8452 +Train: [93] [4300/6250] eta: 0:05:06 lr: 0.000001 grad: 0.1563 (0.1632) loss: 0.8318 (0.8368) time: 0.1270 data: 0.0264 max mem: 8452 +Train: [93] [4400/6250] eta: 0:04:50 lr: 0.000001 grad: 0.1565 (0.1631) loss: 0.8364 (0.8366) time: 0.1424 data: 0.0692 max mem: 8452 +Train: [93] [4500/6250] eta: 0:04:34 lr: 0.000001 grad: 0.1461 (0.1630) loss: 0.8326 (0.8365) time: 0.1546 data: 0.0818 max mem: 8452 +Train: [93] [4600/6250] eta: 0:04:18 lr: 0.000001 grad: 0.1600 (0.1628) loss: 0.8301 (0.8364) time: 0.1499 data: 0.0702 max mem: 8452 +Train: [93] [4700/6250] eta: 0:04:03 lr: 0.000001 grad: 0.1559 (0.1627) loss: 0.8284 (0.8364) time: 0.1741 data: 0.0963 max mem: 8452 +Train: [93] [4800/6250] eta: 0:03:47 lr: 0.000001 grad: 0.1478 (0.1625) loss: 0.8442 (0.8364) time: 0.1200 data: 0.0421 max mem: 8452 +Train: [93] [4900/6250] eta: 0:03:31 lr: 0.000001 grad: 0.1477 (0.1623) loss: 0.8446 (0.8364) time: 0.1456 data: 0.0667 max mem: 8452 +Train: [93] [5000/6250] eta: 0:03:15 lr: 0.000001 grad: 0.1448 (0.1621) loss: 0.8444 (0.8365) time: 0.1504 data: 0.0656 max mem: 8452 +Train: [93] [5100/6250] eta: 0:02:59 lr: 0.000001 grad: 0.1511 (0.1620) loss: 0.8347 (0.8365) time: 0.1385 data: 0.0577 max mem: 8452 +Train: [93] [5200/6250] eta: 0:02:44 lr: 0.000001 grad: 0.1593 (0.1618) loss: 0.8413 (0.8366) time: 0.1624 data: 0.0885 max mem: 8452 +Train: [93] [5300/6250] eta: 0:02:28 lr: 0.000001 grad: 0.1554 (0.1617) loss: 0.8432 (0.8367) time: 0.1574 data: 0.0839 max mem: 8452 +Train: [93] [5400/6250] eta: 0:02:12 lr: 0.000001 grad: 0.1521 (0.1616) loss: 0.8368 (0.8367) time: 0.1415 data: 0.0582 max mem: 8452 +Train: [93] [5500/6250] eta: 0:01:56 lr: 0.000001 grad: 0.1549 (0.1616) loss: 0.8348 (0.8367) time: 0.1203 data: 0.0445 max mem: 8452 +Train: [93] [5600/6250] eta: 0:01:40 lr: 0.000001 grad: 0.1543 (0.1615) loss: 0.8361 (0.8367) time: 0.1412 data: 0.0595 max mem: 8452 +Train: [93] [5700/6250] eta: 0:01:25 lr: 0.000001 grad: 0.1503 (0.1615) loss: 0.8401 (0.8368) time: 0.1388 data: 0.0569 max mem: 8452 +Train: [93] [5800/6250] eta: 0:01:09 lr: 0.000001 grad: 0.1606 (0.1614) loss: 0.8409 (0.8368) time: 0.1217 data: 0.0366 max mem: 8452 +Train: [93] [5900/6250] eta: 0:00:53 lr: 0.000001 grad: 0.1557 (0.1613) loss: 0.8297 (0.8367) time: 0.1322 data: 0.0399 max mem: 8452 +Train: [93] [6000/6250] eta: 0:00:38 lr: 0.000001 grad: 0.1458 (0.1612) loss: 0.8409 (0.8368) time: 0.1519 data: 0.0719 max mem: 8452 +Train: [93] [6100/6250] eta: 0:00:22 lr: 0.000001 grad: 0.1521 (0.1611) loss: 0.8387 (0.8368) time: 0.1250 data: 0.0466 max mem: 8452 +Train: [93] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1500 (0.1610) loss: 0.8427 (0.8369) time: 0.1335 data: 0.0380 max mem: 8452 +Train: [93] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1583 (0.1610) loss: 0.8378 (0.8369) time: 0.1589 data: 0.0728 max mem: 8452 +Train: [93] Total time: 0:16:01 (0.1538 s / it) +Averaged stats: lr: 0.000001 grad: 0.1583 (0.1610) loss: 0.8378 (0.8369) +Eval (hcp-train-subset): [93] [ 0/62] eta: 0:04:04 loss: 0.8492 (0.8492) time: 3.9401 data: 3.8492 max mem: 8452 +Eval (hcp-train-subset): [93] [61/62] eta: 0:00:00 loss: 0.8359 (0.8397) time: 0.1361 data: 0.1154 max mem: 8452 +Eval (hcp-train-subset): [93] Total time: 0:00:15 (0.2422 s / it) +Averaged stats (hcp-train-subset): loss: 0.8359 (0.8397) +Eval (hcp-val): [93] [ 0/62] eta: 0:06:28 loss: 0.8611 (0.8611) time: 6.2673 data: 6.2407 max mem: 8452 +Eval (hcp-val): [93] [61/62] eta: 0:00:00 loss: 0.8654 (0.8662) time: 0.1397 data: 0.1186 max mem: 8452 +Eval (hcp-val): [93] Total time: 0:00:15 (0.2447 s / it) +Averaged stats (hcp-val): loss: 0.8654 (0.8662) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [94] [ 0/6250] eta: 7:52:26 lr: 0.000001 grad: 0.1429 (0.1429) loss: 0.8718 (0.8718) time: 4.5355 data: 4.3516 max mem: 8452 +Train: [94] [ 100/6250] eta: 0:21:08 lr: 0.000001 grad: 0.2115 (0.1977) loss: 0.8224 (0.8493) time: 0.1654 data: 0.0685 max mem: 8452 +Train: [94] [ 200/6250] eta: 0:18:26 lr: 0.000001 grad: 0.1869 (0.1939) loss: 0.8425 (0.8416) time: 0.1357 data: 0.0323 max mem: 8452 +Train: [94] [ 300/6250] eta: 0:17:30 lr: 0.000001 grad: 0.1667 (0.1870) loss: 0.8447 (0.8412) time: 0.1671 data: 0.0671 max mem: 8452 +Train: [94] [ 400/6250] eta: 0:16:51 lr: 0.000001 grad: 0.1592 (0.1822) loss: 0.8242 (0.8391) time: 0.1529 data: 0.0507 max mem: 8452 +Train: [94] [ 500/6250] eta: 0:16:04 lr: 0.000001 grad: 0.1504 (0.1806) loss: 0.8281 (0.8369) time: 0.1358 data: 0.0279 max mem: 8452 +Train: [94] [ 600/6250] eta: 0:15:37 lr: 0.000001 grad: 0.1640 (0.1792) loss: 0.8305 (0.8364) time: 0.1555 data: 0.0605 max mem: 8452 +Train: [94] [ 700/6250] eta: 0:15:12 lr: 0.000001 grad: 0.1593 (0.1785) loss: 0.8325 (0.8358) time: 0.1700 data: 0.0767 max mem: 8452 +Train: [94] [ 800/6250] eta: 0:14:45 lr: 0.000001 grad: 0.1627 (0.1777) loss: 0.8343 (0.8356) time: 0.1442 data: 0.0498 max mem: 8452 +Train: [94] [ 900/6250] eta: 0:14:18 lr: 0.000001 grad: 0.1630 (0.1768) loss: 0.8404 (0.8359) time: 0.1310 data: 0.0443 max mem: 8452 +Train: [94] [1000/6250] eta: 0:13:53 lr: 0.000001 grad: 0.1557 (0.1758) loss: 0.8433 (0.8362) time: 0.1456 data: 0.0471 max mem: 8452 +Train: [94] [1100/6250] eta: 0:13:31 lr: 0.000001 grad: 0.1626 (0.1748) loss: 0.8349 (0.8359) time: 0.1455 data: 0.0547 max mem: 8452 +Train: [94] [1200/6250] eta: 0:13:13 lr: 0.000001 grad: 0.1555 (0.1740) loss: 0.8374 (0.8359) time: 0.1683 data: 0.0784 max mem: 8452 +Train: [94] [1300/6250] eta: 0:12:52 lr: 0.000001 grad: 0.1574 (0.1733) loss: 0.8269 (0.8357) time: 0.1532 data: 0.0619 max mem: 8452 +Train: [94] [1400/6250] eta: 0:12:33 lr: 0.000001 grad: 0.1548 (0.1724) loss: 0.8339 (0.8359) time: 0.1054 data: 0.0167 max mem: 8452 +Train: [94] [1500/6250] eta: 0:12:17 lr: 0.000001 grad: 0.1483 (0.1716) loss: 0.8347 (0.8358) time: 0.1638 data: 0.0791 max mem: 8452 +Train: [94] [1600/6250] eta: 0:11:58 lr: 0.000001 grad: 0.1518 (0.1708) loss: 0.8352 (0.8359) time: 0.1576 data: 0.0650 max mem: 8452 +Train: [94] [1700/6250] eta: 0:11:42 lr: 0.000001 grad: 0.1547 (0.1698) loss: 0.8386 (0.8361) time: 0.1815 data: 0.1011 max mem: 8452 +Train: [94] [1800/6250] eta: 0:11:24 lr: 0.000001 grad: 0.1574 (0.1692) loss: 0.8408 (0.8362) time: 0.1529 data: 0.0732 max mem: 8452 +Train: [94] [1900/6250] eta: 0:11:07 lr: 0.000001 grad: 0.1449 (0.1688) loss: 0.8378 (0.8364) time: 0.1530 data: 0.0739 max mem: 8452 +Train: [94] [2000/6250] eta: 0:10:50 lr: 0.000001 grad: 0.1565 (0.1685) loss: 0.8321 (0.8364) time: 0.1213 data: 0.0398 max mem: 8452 +Train: [94] [2100/6250] eta: 0:10:34 lr: 0.000001 grad: 0.1548 (0.1682) loss: 0.8397 (0.8364) time: 0.1592 data: 0.0884 max mem: 8452 +Train: [94] [2200/6250] eta: 0:10:16 lr: 0.000001 grad: 0.1529 (0.1677) loss: 0.8416 (0.8366) time: 0.1248 data: 0.0417 max mem: 8452 +Train: [94] [2300/6250] eta: 0:10:00 lr: 0.000001 grad: 0.1592 (0.1672) loss: 0.8383 (0.8366) time: 0.1345 data: 0.0539 max mem: 8452 +Train: [94] [2400/6250] eta: 0:09:44 lr: 0.000001 grad: 0.1571 (0.1667) loss: 0.8432 (0.8369) time: 0.1416 data: 0.0613 max mem: 8452 +Train: [94] [2500/6250] eta: 0:09:28 lr: 0.000001 grad: 0.1578 (0.1665) loss: 0.8400 (0.8369) time: 0.1573 data: 0.0713 max mem: 8452 +Train: [94] [2600/6250] eta: 0:09:14 lr: 0.000001 grad: 0.1524 (0.1662) loss: 0.8438 (0.8370) time: 0.1896 data: 0.1152 max mem: 8452 +Train: [94] [2700/6250] eta: 0:08:58 lr: 0.000001 grad: 0.1517 (0.1658) loss: 0.8358 (0.8371) time: 0.1195 data: 0.0308 max mem: 8452 +Train: [94] [2800/6250] eta: 0:08:42 lr: 0.000001 grad: 0.1566 (0.1655) loss: 0.8262 (0.8371) time: 0.1377 data: 0.0629 max mem: 8452 +Train: [94] [2900/6250] eta: 0:08:27 lr: 0.000001 grad: 0.1551 (0.1652) loss: 0.8391 (0.8371) time: 0.1588 data: 0.0849 max mem: 8452 +Train: [94] [3000/6250] eta: 0:08:14 lr: 0.000001 grad: 0.1563 (0.1650) loss: 0.8386 (0.8371) time: 0.1551 data: 0.0805 max mem: 8452 +Train: [94] [3100/6250] eta: 0:07:58 lr: 0.000001 grad: 0.1551 (0.1649) loss: 0.8360 (0.8371) time: 0.1538 data: 0.0827 max mem: 8452 +Train: [94] [3200/6250] eta: 0:07:43 lr: 0.000001 grad: 0.1606 (0.1648) loss: 0.8355 (0.8371) time: 0.1400 data: 0.0629 max mem: 8452 +Train: [94] [3300/6250] eta: 0:07:28 lr: 0.000001 grad: 0.1624 (0.1647) loss: 0.8317 (0.8370) time: 0.1676 data: 0.0894 max mem: 8452 +Train: [94] [3400/6250] eta: 0:07:14 lr: 0.000001 grad: 0.1644 (0.1647) loss: 0.8277 (0.8370) time: 0.1754 data: 0.1054 max mem: 8452 +Train: [94] [3500/6250] eta: 0:06:58 lr: 0.000001 grad: 0.1535 (0.1647) loss: 0.8370 (0.8369) time: 0.1591 data: 0.0650 max mem: 8452 +Train: [94] [3600/6250] eta: 0:06:43 lr: 0.000001 grad: 0.1575 (0.1648) loss: 0.8333 (0.8367) time: 0.1324 data: 0.0568 max mem: 8452 +Train: [94] [3700/6250] eta: 0:06:28 lr: 0.000001 grad: 0.1600 (0.1649) loss: 0.8290 (0.8366) time: 0.1554 data: 0.0731 max mem: 8452 +Train: [94] [3800/6250] eta: 0:06:12 lr: 0.000001 grad: 0.1562 (0.1648) loss: 0.8374 (0.8365) time: 0.1706 data: 0.0947 max mem: 8452 +Train: [94] [3900/6250] eta: 0:05:56 lr: 0.000001 grad: 0.1627 (0.1648) loss: 0.8376 (0.8364) time: 0.1530 data: 0.0681 max mem: 8452 +Train: [94] [4000/6250] eta: 0:05:41 lr: 0.000001 grad: 0.1571 (0.1647) loss: 0.8385 (0.8364) time: 0.1327 data: 0.0397 max mem: 8452 +Train: [94] [4100/6250] eta: 0:05:25 lr: 0.000001 grad: 0.1665 (0.1647) loss: 0.8268 (0.8364) time: 0.1611 data: 0.0866 max mem: 8452 +Train: [94] [4200/6250] eta: 0:05:10 lr: 0.000001 grad: 0.1617 (0.1646) loss: 0.8374 (0.8363) time: 0.1348 data: 0.0499 max mem: 8452 +Train: [94] [4300/6250] eta: 0:04:54 lr: 0.000001 grad: 0.1621 (0.1648) loss: 0.8338 (0.8362) time: 0.1315 data: 0.0399 max mem: 8452 +Train: [94] [4400/6250] eta: 0:04:39 lr: 0.000001 grad: 0.1662 (0.1648) loss: 0.8335 (0.8361) time: 0.1611 data: 0.0786 max mem: 8452 +Train: [94] [4500/6250] eta: 0:04:24 lr: 0.000001 grad: 0.1608 (0.1649) loss: 0.8395 (0.8360) time: 0.1826 data: 0.1009 max mem: 8452 +Train: [94] [4600/6250] eta: 0:04:10 lr: 0.000001 grad: 0.1569 (0.1649) loss: 0.8337 (0.8359) time: 0.1478 data: 0.0719 max mem: 8452 +Train: [94] [4700/6250] eta: 0:03:55 lr: 0.000001 grad: 0.1551 (0.1648) loss: 0.8433 (0.8358) time: 0.1431 data: 0.0709 max mem: 8452 +Train: [94] [4800/6250] eta: 0:03:40 lr: 0.000001 grad: 0.1556 (0.1647) loss: 0.8356 (0.8358) time: 0.1703 data: 0.0902 max mem: 8452 +Train: [94] [4900/6250] eta: 0:03:25 lr: 0.000001 grad: 0.1568 (0.1646) loss: 0.8277 (0.8358) time: 0.1520 data: 0.0706 max mem: 8452 +Train: [94] [5000/6250] eta: 0:03:09 lr: 0.000001 grad: 0.1585 (0.1646) loss: 0.8330 (0.8358) time: 0.1481 data: 0.0537 max mem: 8452 +Train: [94] [5100/6250] eta: 0:02:54 lr: 0.000001 grad: 0.1534 (0.1646) loss: 0.8378 (0.8358) time: 0.1367 data: 0.0484 max mem: 8452 +Train: [94] [5200/6250] eta: 0:02:39 lr: 0.000001 grad: 0.1533 (0.1645) loss: 0.8364 (0.8357) time: 0.1640 data: 0.0865 max mem: 8452 +Train: [94] [5300/6250] eta: 0:02:24 lr: 0.000001 grad: 0.1563 (0.1644) loss: 0.8351 (0.8358) time: 0.1471 data: 0.0723 max mem: 8452 +Train: [94] [5400/6250] eta: 0:02:08 lr: 0.000001 grad: 0.1515 (0.1643) loss: 0.8394 (0.8358) time: 0.1579 data: 0.0757 max mem: 8452 +Train: [94] [5500/6250] eta: 0:01:53 lr: 0.000001 grad: 0.1473 (0.1642) loss: 0.8455 (0.8359) time: 0.1323 data: 0.0435 max mem: 8452 +Train: [94] [5600/6250] eta: 0:01:38 lr: 0.000001 grad: 0.1588 (0.1641) loss: 0.8379 (0.8360) time: 0.1203 data: 0.0379 max mem: 8452 +Train: [94] [5700/6250] eta: 0:01:23 lr: 0.000001 grad: 0.1492 (0.1639) loss: 0.8447 (0.8361) time: 0.1166 data: 0.0295 max mem: 8452 +Train: [94] [5800/6250] eta: 0:01:07 lr: 0.000001 grad: 0.1549 (0.1638) loss: 0.8390 (0.8361) time: 0.1636 data: 0.0817 max mem: 8452 +Train: [94] [5900/6250] eta: 0:00:52 lr: 0.000001 grad: 0.1540 (0.1636) loss: 0.8471 (0.8362) time: 0.1302 data: 0.0465 max mem: 8452 +Train: [94] [6000/6250] eta: 0:00:37 lr: 0.000001 grad: 0.1555 (0.1635) loss: 0.8367 (0.8362) time: 0.1566 data: 0.0715 max mem: 8452 +Train: [94] [6100/6250] eta: 0:00:22 lr: 0.000001 grad: 0.1485 (0.1634) loss: 0.8426 (0.8363) time: 0.1396 data: 0.0605 max mem: 8452 +Train: [94] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1626 (0.1633) loss: 0.8347 (0.8363) time: 0.1124 data: 0.0258 max mem: 8452 +Train: [94] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1475 (0.1633) loss: 0.8425 (0.8363) time: 0.1409 data: 0.0533 max mem: 8452 +Train: [94] Total time: 0:15:46 (0.1515 s / it) +Averaged stats: lr: 0.000001 grad: 0.1475 (0.1633) loss: 0.8425 (0.8363) +Eval (hcp-train-subset): [94] [ 0/62] eta: 0:06:25 loss: 0.8505 (0.8505) time: 6.2241 data: 6.1979 max mem: 8452 +Eval (hcp-train-subset): [94] [61/62] eta: 0:00:00 loss: 0.8370 (0.8396) time: 0.1016 data: 0.0805 max mem: 8452 +Eval (hcp-train-subset): [94] Total time: 0:00:15 (0.2420 s / it) +Averaged stats (hcp-train-subset): loss: 0.8370 (0.8396) +Making plots (hcp-train-subset): example=2 +Eval (hcp-val): [94] [ 0/62] eta: 0:05:15 loss: 0.8636 (0.8636) time: 5.0871 data: 5.0580 max mem: 8452 +Eval (hcp-val): [94] [61/62] eta: 0:00:00 loss: 0.8646 (0.8659) time: 0.1419 data: 0.1193 max mem: 8452 +Eval (hcp-val): [94] Total time: 0:00:14 (0.2320 s / it) +Averaged stats (hcp-val): loss: 0.8646 (0.8659) +Making plots (hcp-val): example=53 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [95] [ 0/6250] eta: 8:08:54 lr: 0.000001 grad: 0.1745 (0.1745) loss: 0.8282 (0.8282) time: 4.6935 data: 4.3969 max mem: 8452 +Train: [95] [ 100/6250] eta: 0:21:43 lr: 0.000001 grad: 0.1886 (0.2527) loss: 0.8480 (0.8350) time: 0.1902 data: 0.0814 max mem: 8452 +Train: [95] [ 200/6250] eta: 0:19:03 lr: 0.000001 grad: 0.1850 (0.2186) loss: 0.8511 (0.8418) time: 0.1668 data: 0.0605 max mem: 8452 +Train: [95] [ 300/6250] eta: 0:17:55 lr: 0.000001 grad: 0.1485 (0.2093) loss: 0.8435 (0.8408) time: 0.1694 data: 0.0591 max mem: 8452 +Train: [95] [ 400/6250] eta: 0:17:08 lr: 0.000001 grad: 0.1951 (0.2043) loss: 0.8328 (0.8393) time: 0.1655 data: 0.0631 max mem: 8452 +Train: [95] [ 500/6250] eta: 0:16:26 lr: 0.000001 grad: 0.1445 (0.1981) loss: 0.8483 (0.8400) time: 0.1512 data: 0.0542 max mem: 8452 +Train: [95] [ 600/6250] eta: 0:15:48 lr: 0.000001 grad: 0.1517 (0.1927) loss: 0.8374 (0.8398) time: 0.1542 data: 0.0519 max mem: 8452 +Train: [95] [ 700/6250] eta: 0:15:19 lr: 0.000001 grad: 0.1690 (0.1895) loss: 0.8286 (0.8390) time: 0.1538 data: 0.0537 max mem: 8452 +Train: [95] [ 800/6250] eta: 0:14:46 lr: 0.000001 grad: 0.1660 (0.1864) loss: 0.8274 (0.8384) time: 0.1468 data: 0.0596 max mem: 8452 +Train: [95] [ 900/6250] eta: 0:14:27 lr: 0.000001 grad: 0.1676 (0.1841) loss: 0.8277 (0.8378) time: 0.1594 data: 0.0718 max mem: 8452 +Train: [95] [1000/6250] eta: 0:14:03 lr: 0.000001 grad: 0.1736 (0.1822) loss: 0.8328 (0.8375) time: 0.1521 data: 0.0716 max mem: 8452 +Train: [95] [1100/6250] eta: 0:13:43 lr: 0.000001 grad: 0.1571 (0.1809) loss: 0.8346 (0.8374) time: 0.1614 data: 0.0759 max mem: 8452 +Train: [95] [1200/6250] eta: 0:13:25 lr: 0.000001 grad: 0.1677 (0.1798) loss: 0.8389 (0.8371) time: 0.1299 data: 0.0452 max mem: 8452 +Train: [95] [1300/6250] eta: 0:13:05 lr: 0.000001 grad: 0.1547 (0.1790) loss: 0.8359 (0.8369) time: 0.1564 data: 0.0707 max mem: 8452 +Train: [95] [1400/6250] eta: 0:12:46 lr: 0.000001 grad: 0.1583 (0.1780) loss: 0.8366 (0.8369) time: 0.1403 data: 0.0583 max mem: 8452 +Train: [95] [1500/6250] eta: 0:12:29 lr: 0.000001 grad: 0.1512 (0.1768) loss: 0.8383 (0.8371) time: 0.1380 data: 0.0636 max mem: 8452 +Train: [95] [1600/6250] eta: 0:12:10 lr: 0.000001 grad: 0.1601 (0.1756) loss: 0.8385 (0.8374) time: 0.1507 data: 0.0655 max mem: 8452 +Train: [95] [1700/6250] eta: 0:11:55 lr: 0.000001 grad: 0.1619 (0.1748) loss: 0.8361 (0.8373) time: 0.1859 data: 0.0975 max mem: 8452 +Train: [95] [1800/6250] eta: 0:11:41 lr: 0.000001 grad: 0.1553 (0.1741) loss: 0.8414 (0.8373) time: 0.1614 data: 0.0747 max mem: 8452 +Train: [95] [1900/6250] eta: 0:11:22 lr: 0.000001 grad: 0.1654 (0.1735) loss: 0.8354 (0.8373) time: 0.1414 data: 0.0538 max mem: 8452 +Train: [95] [2000/6250] eta: 0:11:06 lr: 0.000001 grad: 0.1625 (0.1729) loss: 0.8360 (0.8371) time: 0.1533 data: 0.0694 max mem: 8452 +Train: [95] [2100/6250] eta: 0:10:49 lr: 0.000001 grad: 0.1585 (0.1724) loss: 0.8367 (0.8371) time: 0.1783 data: 0.1001 max mem: 8452 +Train: [95] [2200/6250] eta: 0:10:32 lr: 0.000001 grad: 0.1575 (0.1719) loss: 0.8366 (0.8370) time: 0.1418 data: 0.0709 max mem: 8452 +Train: [95] [2300/6250] eta: 0:10:16 lr: 0.000001 grad: 0.1635 (0.1715) loss: 0.8315 (0.8369) time: 0.1758 data: 0.1007 max mem: 8452 +Train: [95] [2400/6250] eta: 0:09:59 lr: 0.000001 grad: 0.1539 (0.1710) loss: 0.8343 (0.8369) time: 0.1422 data: 0.0629 max mem: 8452 +Train: [95] [2500/6250] eta: 0:09:42 lr: 0.000001 grad: 0.1606 (0.1707) loss: 0.8372 (0.8368) time: 0.1381 data: 0.0675 max mem: 8452 +Train: [95] [2600/6250] eta: 0:09:26 lr: 0.000001 grad: 0.1597 (0.1702) loss: 0.8414 (0.8369) time: 0.1434 data: 0.0603 max mem: 8452 +Train: [95] [2700/6250] eta: 0:09:11 lr: 0.000001 grad: 0.1514 (0.1702) loss: 0.8406 (0.8369) time: 0.1209 data: 0.0422 max mem: 8452 +Train: [95] [2800/6250] eta: 0:08:55 lr: 0.000001 grad: 0.1551 (0.1702) loss: 0.8367 (0.8368) time: 0.1437 data: 0.0739 max mem: 8452 +Train: [95] [2900/6250] eta: 0:08:38 lr: 0.000001 grad: 0.1592 (0.1700) loss: 0.8410 (0.8369) time: 0.1489 data: 0.0688 max mem: 8452 +Train: [95] [3000/6250] eta: 0:08:24 lr: 0.000001 grad: 0.1593 (0.1700) loss: 0.8221 (0.8367) time: 0.1720 data: 0.0879 max mem: 8452 +Train: [95] [3100/6250] eta: 0:08:09 lr: 0.000001 grad: 0.1481 (0.1699) loss: 0.8398 (0.8367) time: 0.1762 data: 0.0936 max mem: 8452 +Train: [95] [3200/6250] eta: 0:07:53 lr: 0.000001 grad: 0.1697 (0.1698) loss: 0.8333 (0.8367) time: 0.1696 data: 0.0851 max mem: 8452 +Train: [95] [3300/6250] eta: 0:07:38 lr: 0.000001 grad: 0.1556 (0.1697) loss: 0.8384 (0.8367) time: 0.1756 data: 0.0982 max mem: 8452 +Train: [95] [3400/6250] eta: 0:07:23 lr: 0.000001 grad: 0.1618 (0.1695) loss: 0.8337 (0.8367) time: 0.1519 data: 0.0686 max mem: 8452 +Train: [95] [3500/6250] eta: 0:07:07 lr: 0.000001 grad: 0.1633 (0.1696) loss: 0.8387 (0.8367) time: 0.1512 data: 0.0692 max mem: 8452 +Train: [95] [3600/6250] eta: 0:06:51 lr: 0.000001 grad: 0.1648 (0.1694) loss: 0.8345 (0.8367) time: 0.1601 data: 0.0696 max mem: 8452 +Train: [95] [3700/6250] eta: 0:06:35 lr: 0.000001 grad: 0.1607 (0.1691) loss: 0.8361 (0.8367) time: 0.1503 data: 0.0618 max mem: 8452 +Train: [95] [3800/6250] eta: 0:06:19 lr: 0.000001 grad: 0.1621 (0.1689) loss: 0.8388 (0.8368) time: 0.1625 data: 0.0815 max mem: 8452 +Train: [95] [3900/6250] eta: 0:06:02 lr: 0.000001 grad: 0.1484 (0.1686) loss: 0.8384 (0.8368) time: 0.1300 data: 0.0532 max mem: 8452 +Train: [95] [4000/6250] eta: 0:05:47 lr: 0.000001 grad: 0.1578 (0.1683) loss: 0.8377 (0.8368) time: 0.1646 data: 0.0871 max mem: 8452 +Train: [95] [4100/6250] eta: 0:05:31 lr: 0.000001 grad: 0.1558 (0.1681) loss: 0.8376 (0.8368) time: 0.1548 data: 0.0690 max mem: 8452 +Train: [95] [4200/6250] eta: 0:05:15 lr: 0.000001 grad: 0.1654 (0.1680) loss: 0.8257 (0.8368) time: 0.1363 data: 0.0503 max mem: 8452 +Train: [95] [4300/6250] eta: 0:04:59 lr: 0.000001 grad: 0.1619 (0.1679) loss: 0.8346 (0.8367) time: 0.1430 data: 0.0640 max mem: 8452 +Train: [95] [4400/6250] eta: 0:04:44 lr: 0.000001 grad: 0.1532 (0.1678) loss: 0.8370 (0.8367) time: 0.1457 data: 0.0622 max mem: 8452 +Train: [95] [4500/6250] eta: 0:04:28 lr: 0.000001 grad: 0.1513 (0.1676) loss: 0.8378 (0.8366) time: 0.1515 data: 0.0724 max mem: 8452 +Train: [95] [4600/6250] eta: 0:04:13 lr: 0.000001 grad: 0.1577 (0.1674) loss: 0.8363 (0.8366) time: 0.1579 data: 0.0772 max mem: 8452 +Train: [95] [4700/6250] eta: 0:03:58 lr: 0.000001 grad: 0.1540 (0.1673) loss: 0.8422 (0.8367) time: 0.1412 data: 0.0513 max mem: 8452 +Train: [95] [4800/6250] eta: 0:03:42 lr: 0.000001 grad: 0.1555 (0.1672) loss: 0.8345 (0.8367) time: 0.1366 data: 0.0575 max mem: 8452 +Train: [95] [4900/6250] eta: 0:03:27 lr: 0.000001 grad: 0.1585 (0.1670) loss: 0.8297 (0.8367) time: 0.1326 data: 0.0564 max mem: 8452 +Train: [95] [5000/6250] eta: 0:03:12 lr: 0.000001 grad: 0.1575 (0.1670) loss: 0.8402 (0.8367) time: 0.1587 data: 0.0825 max mem: 8452 +Train: [95] [5100/6250] eta: 0:02:56 lr: 0.000001 grad: 0.1586 (0.1669) loss: 0.8365 (0.8367) time: 0.1507 data: 0.0664 max mem: 8452 +Train: [95] [5200/6250] eta: 0:02:41 lr: 0.000001 grad: 0.1514 (0.1669) loss: 0.8344 (0.8367) time: 0.1512 data: 0.0684 max mem: 8452 +Train: [95] [5300/6250] eta: 0:02:25 lr: 0.000001 grad: 0.1516 (0.1668) loss: 0.8397 (0.8367) time: 0.1587 data: 0.0743 max mem: 8452 +Train: [95] [5400/6250] eta: 0:02:10 lr: 0.000001 grad: 0.1632 (0.1668) loss: 0.8381 (0.8367) time: 0.1582 data: 0.0748 max mem: 8452 +Train: [95] [5500/6250] eta: 0:01:55 lr: 0.000001 grad: 0.1547 (0.1668) loss: 0.8436 (0.8367) time: 0.1810 data: 0.1060 max mem: 8452 +Train: [95] [5600/6250] eta: 0:01:39 lr: 0.000001 grad: 0.1663 (0.1667) loss: 0.8368 (0.8367) time: 0.1428 data: 0.0603 max mem: 8452 +Train: [95] [5700/6250] eta: 0:01:24 lr: 0.000001 grad: 0.1535 (0.1667) loss: 0.8361 (0.8367) time: 0.1504 data: 0.0551 max mem: 8452 +Train: [95] [5800/6250] eta: 0:01:08 lr: 0.000001 grad: 0.1646 (0.1667) loss: 0.8327 (0.8366) time: 0.1413 data: 0.0638 max mem: 8452 +Train: [95] [5900/6250] eta: 0:00:53 lr: 0.000001 grad: 0.1658 (0.1666) loss: 0.8377 (0.8366) time: 0.1853 data: 0.1031 max mem: 8452 +Train: [95] [6000/6250] eta: 0:00:38 lr: 0.000001 grad: 0.1555 (0.1666) loss: 0.8284 (0.8365) time: 0.1687 data: 0.0891 max mem: 8452 +Train: [95] [6100/6250] eta: 0:00:22 lr: 0.000001 grad: 0.1536 (0.1665) loss: 0.8350 (0.8365) time: 0.1857 data: 0.1074 max mem: 8452 +Train: [95] [6200/6250] eta: 0:00:07 lr: 0.000001 grad: 0.1699 (0.1665) loss: 0.8346 (0.8365) time: 0.1440 data: 0.0463 max mem: 8452 +Train: [95] [6249/6250] eta: 0:00:00 lr: 0.000001 grad: 0.1597 (0.1664) loss: 0.8344 (0.8364) time: 0.1628 data: 0.0889 max mem: 8452 +Train: [95] Total time: 0:16:01 (0.1538 s / it) +Averaged stats: lr: 0.000001 grad: 0.1597 (0.1664) loss: 0.8344 (0.8364) +Eval (hcp-train-subset): [95] [ 0/62] eta: 0:06:40 loss: 0.8480 (0.8480) time: 6.4674 data: 6.4393 max mem: 8452 +Eval (hcp-train-subset): [95] [61/62] eta: 0:00:00 loss: 0.8369 (0.8393) time: 0.1189 data: 0.0980 max mem: 8452 +Eval (hcp-train-subset): [95] Total time: 0:00:15 (0.2513 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8393) +Eval (hcp-val): [95] [ 0/62] eta: 0:05:31 loss: 0.8588 (0.8588) time: 5.3433 data: 5.3147 max mem: 8452 +Eval (hcp-val): [95] [61/62] eta: 0:00:00 loss: 0.8642 (0.8656) time: 0.1282 data: 0.1073 max mem: 8452 +Eval (hcp-val): [95] Total time: 0:00:14 (0.2407 s / it) +Averaged stats (hcp-val): loss: 0.8642 (0.8656) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [96] [ 0/6250] eta: 10:55:52 lr: 0.000001 grad: 0.0994 (0.0994) loss: 0.8709 (0.8709) time: 6.2964 data: 6.2065 max mem: 8452 +Train: [96] [ 100/6250] eta: 0:21:34 lr: 0.000001 grad: 0.1776 (0.1967) loss: 0.8345 (0.8399) time: 0.1730 data: 0.0627 max mem: 8452 +Train: [96] [ 200/6250] eta: 0:18:28 lr: 0.000001 grad: 0.1688 (0.1908) loss: 0.8315 (0.8339) time: 0.1596 data: 0.0505 max mem: 8452 +Train: [96] [ 300/6250] eta: 0:17:23 lr: 0.000001 grad: 0.1593 (0.1875) loss: 0.8321 (0.8323) time: 0.1663 data: 0.0571 max mem: 8452 +Train: [96] [ 400/6250] eta: 0:16:32 lr: 0.000001 grad: 0.1789 (0.1859) loss: 0.8276 (0.8316) time: 0.1451 data: 0.0470 max mem: 8452 +Train: [96] [ 500/6250] eta: 0:15:57 lr: 0.000001 grad: 0.1645 (0.1846) loss: 0.8350 (0.8322) time: 0.1381 data: 0.0296 max mem: 8452 +Train: [96] [ 600/6250] eta: 0:15:24 lr: 0.000001 grad: 0.1606 (0.1831) loss: 0.8361 (0.8331) time: 0.1519 data: 0.0528 max mem: 8452 +Train: [96] [ 700/6250] eta: 0:14:56 lr: 0.000001 grad: 0.1717 (0.1822) loss: 0.8335 (0.8331) time: 0.1648 data: 0.0784 max mem: 8452 +Train: [96] [ 800/6250] eta: 0:14:31 lr: 0.000001 grad: 0.1615 (0.1811) loss: 0.8361 (0.8330) time: 0.1753 data: 0.0907 max mem: 8452 +Train: [96] [ 900/6250] eta: 0:14:13 lr: 0.000001 grad: 0.1535 (0.1801) loss: 0.8354 (0.8328) time: 0.1619 data: 0.0730 max mem: 8452 +Train: [96] [1000/6250] eta: 0:13:52 lr: 0.000001 grad: 0.1694 (0.1793) loss: 0.8320 (0.8328) time: 0.1455 data: 0.0550 max mem: 8452 +Train: [96] [1100/6250] eta: 0:13:34 lr: 0.000000 grad: 0.1567 (0.1784) loss: 0.8381 (0.8329) time: 0.1576 data: 0.0680 max mem: 8452 +Train: [96] [1200/6250] eta: 0:13:13 lr: 0.000000 grad: 0.1745 (0.1776) loss: 0.8257 (0.8327) time: 0.1186 data: 0.0482 max mem: 8452 +Train: [96] [1300/6250] eta: 0:12:57 lr: 0.000000 grad: 0.1510 (0.1766) loss: 0.8336 (0.8327) time: 0.1645 data: 0.0879 max mem: 8452 +Train: [96] [1400/6250] eta: 0:12:38 lr: 0.000000 grad: 0.1591 (0.1756) loss: 0.8303 (0.8327) time: 0.1696 data: 0.0898 max mem: 8452 +Train: [96] [1500/6250] eta: 0:12:21 lr: 0.000000 grad: 0.1748 (0.1752) loss: 0.8288 (0.8325) time: 0.1522 data: 0.0653 max mem: 8452 +Train: [96] [1600/6250] eta: 0:12:02 lr: 0.000000 grad: 0.1618 (0.1746) loss: 0.8303 (0.8325) time: 0.1417 data: 0.0575 max mem: 8452 +Train: [96] [1700/6250] eta: 0:11:47 lr: 0.000000 grad: 0.1569 (0.1740) loss: 0.8318 (0.8324) time: 0.1486 data: 0.0832 max mem: 8452 +Train: [96] [1800/6250] eta: 0:11:31 lr: 0.000000 grad: 0.1580 (0.1735) loss: 0.8258 (0.8323) time: 0.1543 data: 0.0751 max mem: 8452 +Train: [96] [1900/6250] eta: 0:11:13 lr: 0.000000 grad: 0.1600 (0.1730) loss: 0.8389 (0.8324) time: 0.1566 data: 0.0805 max mem: 8452 +Train: [96] [2000/6250] eta: 0:10:59 lr: 0.000000 grad: 0.1574 (0.1722) loss: 0.8295 (0.8325) time: 0.1704 data: 0.0989 max mem: 8452 +Train: [96] [2100/6250] eta: 0:10:41 lr: 0.000000 grad: 0.1552 (0.1719) loss: 0.8294 (0.8325) time: 0.1600 data: 0.0675 max mem: 8452 +Train: [96] [2200/6250] eta: 0:10:24 lr: 0.000000 grad: 0.1600 (0.1716) loss: 0.8317 (0.8325) time: 0.1410 data: 0.0620 max mem: 8452 +Train: [96] [2300/6250] eta: 0:10:08 lr: 0.000000 grad: 0.1584 (0.1713) loss: 0.8311 (0.8326) time: 0.1318 data: 0.0478 max mem: 8452 +Train: [96] [2400/6250] eta: 0:09:52 lr: 0.000000 grad: 0.1570 (0.1710) loss: 0.8341 (0.8327) time: 0.1361 data: 0.0621 max mem: 8452 +Train: [96] [2500/6250] eta: 0:09:37 lr: 0.000000 grad: 0.1573 (0.1707) loss: 0.8271 (0.8328) time: 0.1155 data: 0.0466 max mem: 8452 +Train: [96] [2600/6250] eta: 0:09:22 lr: 0.000000 grad: 0.1583 (0.1702) loss: 0.8373 (0.8330) time: 0.1225 data: 0.0456 max mem: 8452 +Train: [96] [2700/6250] eta: 0:09:06 lr: 0.000000 grad: 0.1557 (0.1697) loss: 0.8387 (0.8332) time: 0.1461 data: 0.0619 max mem: 8452 +Train: [96] [2800/6250] eta: 0:08:50 lr: 0.000000 grad: 0.1539 (0.1694) loss: 0.8380 (0.8334) time: 0.1389 data: 0.0581 max mem: 8452 +Train: [96] [2900/6250] eta: 0:08:35 lr: 0.000000 grad: 0.1486 (0.1689) loss: 0.8394 (0.8336) time: 0.1443 data: 0.0635 max mem: 8452 +Train: [96] [3000/6250] eta: 0:08:20 lr: 0.000000 grad: 0.1501 (0.1685) loss: 0.8319 (0.8338) time: 0.1199 data: 0.0462 max mem: 8452 +Train: [96] [3100/6250] eta: 0:08:06 lr: 0.000000 grad: 0.1529 (0.1682) loss: 0.8384 (0.8339) time: 0.1926 data: 0.1135 max mem: 8452 +Train: [96] [3200/6250] eta: 0:07:50 lr: 0.000000 grad: 0.1476 (0.1677) loss: 0.8450 (0.8341) time: 0.1678 data: 0.0858 max mem: 8452 +Train: [96] [3300/6250] eta: 0:07:35 lr: 0.000000 grad: 0.1552 (0.1674) loss: 0.8370 (0.8344) time: 0.1613 data: 0.0782 max mem: 8452 +Train: [96] [3400/6250] eta: 0:07:20 lr: 0.000000 grad: 0.1579 (0.1670) loss: 0.8455 (0.8346) time: 0.1491 data: 0.0553 max mem: 8452 +Train: [96] [3500/6250] eta: 0:07:04 lr: 0.000000 grad: 0.1604 (0.1668) loss: 0.8416 (0.8347) time: 0.1366 data: 0.0479 max mem: 8452 +Train: [96] [3600/6250] eta: 0:06:49 lr: 0.000000 grad: 0.1597 (0.1666) loss: 0.8381 (0.8349) time: 0.1507 data: 0.0650 max mem: 8452 +Train: [96] [3700/6250] eta: 0:06:33 lr: 0.000000 grad: 0.1568 (0.1666) loss: 0.8401 (0.8350) time: 0.1534 data: 0.0727 max mem: 8452 +Train: [96] [3800/6250] eta: 0:06:17 lr: 0.000000 grad: 0.1538 (0.1663) loss: 0.8397 (0.8352) time: 0.1449 data: 0.0606 max mem: 8452 +Train: [96] [3900/6250] eta: 0:06:02 lr: 0.000000 grad: 0.1523 (0.1661) loss: 0.8486 (0.8355) time: 0.1763 data: 0.0943 max mem: 8452 +Train: [96] [4000/6250] eta: 0:05:45 lr: 0.000000 grad: 0.1527 (0.1657) loss: 0.8424 (0.8357) time: 0.1413 data: 0.0637 max mem: 8452 +Train: [96] [4100/6250] eta: 0:05:30 lr: 0.000000 grad: 0.1511 (0.1655) loss: 0.8387 (0.8358) time: 0.1442 data: 0.0620 max mem: 8452 +Train: [96] [4200/6250] eta: 0:05:15 lr: 0.000000 grad: 0.1568 (0.1653) loss: 0.8399 (0.8360) time: 0.1613 data: 0.0867 max mem: 8452 +Train: [96] [4300/6250] eta: 0:04:59 lr: 0.000000 grad: 0.1568 (0.1650) loss: 0.8441 (0.8361) time: 0.1411 data: 0.0609 max mem: 8452 +Train: [96] [4400/6250] eta: 0:04:44 lr: 0.000000 grad: 0.1441 (0.1647) loss: 0.8445 (0.8363) time: 0.1450 data: 0.0650 max mem: 8452 +Train: [96] [4500/6250] eta: 0:04:28 lr: 0.000000 grad: 0.1481 (0.1644) loss: 0.8442 (0.8364) time: 0.1524 data: 0.0671 max mem: 8452 +Train: [96] [4600/6250] eta: 0:04:13 lr: 0.000000 grad: 0.1465 (0.1642) loss: 0.8425 (0.8366) time: 0.1360 data: 0.0501 max mem: 8452 +Train: [96] [4700/6250] eta: 0:03:58 lr: 0.000000 grad: 0.1478 (0.1640) loss: 0.8456 (0.8367) time: 0.1868 data: 0.1150 max mem: 8452 +Train: [96] [4800/6250] eta: 0:03:43 lr: 0.000000 grad: 0.1455 (0.1638) loss: 0.8455 (0.8369) time: 0.1549 data: 0.0797 max mem: 8452 +Train: [96] [4900/6250] eta: 0:03:27 lr: 0.000000 grad: 0.1539 (0.1636) loss: 0.8421 (0.8370) time: 0.1408 data: 0.0635 max mem: 8452 +Train: [96] [5000/6250] eta: 0:03:12 lr: 0.000000 grad: 0.1526 (0.1634) loss: 0.8462 (0.8372) time: 0.1910 data: 0.1036 max mem: 8452 +Train: [96] [5100/6250] eta: 0:02:57 lr: 0.000000 grad: 0.1717 (0.1634) loss: 0.8424 (0.8373) time: 0.1451 data: 0.0518 max mem: 8452 +Train: [96] [5200/6250] eta: 0:02:41 lr: 0.000000 grad: 0.1566 (0.1633) loss: 0.8390 (0.8374) time: 0.1543 data: 0.0638 max mem: 8452 +Train: [96] [5300/6250] eta: 0:02:26 lr: 0.000000 grad: 0.1520 (0.1633) loss: 0.8436 (0.8375) time: 0.1894 data: 0.1212 max mem: 8452 +Train: [96] [5400/6250] eta: 0:02:10 lr: 0.000000 grad: 0.1529 (0.1632) loss: 0.8374 (0.8376) time: 0.1379 data: 0.0533 max mem: 8452 +Train: [96] [5500/6250] eta: 0:01:55 lr: 0.000000 grad: 0.1496 (0.1632) loss: 0.8394 (0.8376) time: 0.1419 data: 0.0542 max mem: 8452 +Train: [96] [5600/6250] eta: 0:01:39 lr: 0.000000 grad: 0.1630 (0.1631) loss: 0.8437 (0.8377) time: 0.1712 data: 0.0979 max mem: 8452 +Train: [96] [5700/6250] eta: 0:01:24 lr: 0.000000 grad: 0.1621 (0.1632) loss: 0.8414 (0.8377) time: 0.1413 data: 0.0587 max mem: 8452 +Train: [96] [5800/6250] eta: 0:01:09 lr: 0.000000 grad: 0.1696 (0.1633) loss: 0.8341 (0.8377) time: 0.1459 data: 0.0719 max mem: 8452 +Train: [96] [5900/6250] eta: 0:00:53 lr: 0.000000 grad: 0.1576 (0.1633) loss: 0.8384 (0.8377) time: 0.1673 data: 0.0850 max mem: 8452 +Train: [96] [6000/6250] eta: 0:00:38 lr: 0.000000 grad: 0.1644 (0.1633) loss: 0.8393 (0.8378) time: 0.1740 data: 0.0899 max mem: 8452 +Train: [96] [6100/6250] eta: 0:00:23 lr: 0.000000 grad: 0.1582 (0.1633) loss: 0.8404 (0.8378) time: 0.1697 data: 0.0904 max mem: 8452 +Train: [96] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1595 (0.1633) loss: 0.8340 (0.8378) time: 0.1551 data: 0.0801 max mem: 8452 +Train: [96] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1573 (0.1633) loss: 0.8357 (0.8377) time: 0.1536 data: 0.0754 max mem: 8452 +Train: [96] Total time: 0:16:08 (0.1550 s / it) +Averaged stats: lr: 0.000000 grad: 0.1573 (0.1633) loss: 0.8357 (0.8377) +Eval (hcp-train-subset): [96] [ 0/62] eta: 0:05:33 loss: 0.8471 (0.8471) time: 5.3820 data: 5.3558 max mem: 8452 +Eval (hcp-train-subset): [96] [61/62] eta: 0:00:00 loss: 0.8351 (0.8389) time: 0.1427 data: 0.1193 max mem: 8452 +Eval (hcp-train-subset): [96] Total time: 0:00:14 (0.2351 s / it) +Averaged stats (hcp-train-subset): loss: 0.8351 (0.8389) +Eval (hcp-val): [96] [ 0/62] eta: 0:03:56 loss: 0.8614 (0.8614) time: 3.8196 data: 3.7572 max mem: 8452 +Eval (hcp-val): [96] [61/62] eta: 0:00:00 loss: 0.8643 (0.8653) time: 0.1017 data: 0.0807 max mem: 8452 +Eval (hcp-val): [96] Total time: 0:00:14 (0.2348 s / it) +Averaged stats (hcp-val): loss: 0.8643 (0.8653) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [97] [ 0/6250] eta: 9:04:31 lr: 0.000000 grad: 0.1673 (0.1673) loss: 0.8696 (0.8696) time: 5.2275 data: 4.9037 max mem: 8452 +Train: [97] [ 100/6250] eta: 0:22:07 lr: 0.000000 grad: 0.1911 (0.1994) loss: 0.8480 (0.8377) time: 0.1392 data: 0.0245 max mem: 8452 +Train: [97] [ 200/6250] eta: 0:18:56 lr: 0.000000 grad: 0.1605 (0.1910) loss: 0.8550 (0.8358) time: 0.1596 data: 0.0588 max mem: 8452 +Train: [97] [ 300/6250] eta: 0:17:55 lr: 0.000000 grad: 0.1706 (0.1884) loss: 0.8477 (0.8349) time: 0.1630 data: 0.0561 max mem: 8452 +Train: [97] [ 400/6250] eta: 0:17:01 lr: 0.000000 grad: 0.1624 (0.1855) loss: 0.8356 (0.8346) time: 0.1565 data: 0.0636 max mem: 8452 +Train: [97] [ 500/6250] eta: 0:16:22 lr: 0.000000 grad: 0.1694 (0.1842) loss: 0.8354 (0.8352) time: 0.1480 data: 0.0534 max mem: 8452 +Train: [97] [ 600/6250] eta: 0:15:43 lr: 0.000000 grad: 0.1711 (0.1824) loss: 0.8409 (0.8352) time: 0.1412 data: 0.0560 max mem: 8452 +Train: [97] [ 700/6250] eta: 0:15:14 lr: 0.000000 grad: 0.1678 (0.1805) loss: 0.8367 (0.8353) time: 0.1315 data: 0.0413 max mem: 8452 +Train: [97] [ 800/6250] eta: 0:14:48 lr: 0.000000 grad: 0.1438 (0.1786) loss: 0.8411 (0.8355) time: 0.1331 data: 0.0370 max mem: 8452 +Train: [97] [ 900/6250] eta: 0:14:27 lr: 0.000000 grad: 0.1684 (0.1772) loss: 0.8382 (0.8357) time: 0.1592 data: 0.0683 max mem: 8452 +Train: [97] [1000/6250] eta: 0:14:03 lr: 0.000000 grad: 0.1587 (0.1767) loss: 0.8341 (0.8355) time: 0.1494 data: 0.0757 max mem: 8452 +Train: [97] [1100/6250] eta: 0:13:40 lr: 0.000000 grad: 0.1701 (0.1755) loss: 0.8379 (0.8356) time: 0.1192 data: 0.0398 max mem: 8452 +Train: [97] [1200/6250] eta: 0:13:18 lr: 0.000000 grad: 0.1673 (0.1749) loss: 0.8387 (0.8355) time: 0.1409 data: 0.0548 max mem: 8452 +Train: [97] [1300/6250] eta: 0:13:01 lr: 0.000000 grad: 0.1599 (0.1741) loss: 0.8372 (0.8356) time: 0.1503 data: 0.0695 max mem: 8452 +Train: [97] [1400/6250] eta: 0:12:44 lr: 0.000000 grad: 0.1584 (0.1736) loss: 0.8391 (0.8357) time: 0.1464 data: 0.0324 max mem: 8452 +Train: [97] [1500/6250] eta: 0:12:25 lr: 0.000000 grad: 0.1629 (0.1730) loss: 0.8355 (0.8359) time: 0.1525 data: 0.0754 max mem: 8452 +Train: [97] [1600/6250] eta: 0:12:07 lr: 0.000000 grad: 0.1608 (0.1723) loss: 0.8339 (0.8361) time: 0.1094 data: 0.0192 max mem: 8452 +Train: [97] [1700/6250] eta: 0:11:50 lr: 0.000000 grad: 0.1584 (0.1718) loss: 0.8380 (0.8362) time: 0.1519 data: 0.0812 max mem: 8452 +Train: [97] [1800/6250] eta: 0:11:31 lr: 0.000000 grad: 0.1478 (0.1713) loss: 0.8414 (0.8365) time: 0.1351 data: 0.0618 max mem: 8452 +Train: [97] [1900/6250] eta: 0:11:14 lr: 0.000000 grad: 0.1525 (0.1706) loss: 0.8382 (0.8368) time: 0.1474 data: 0.0658 max mem: 8452 +Train: [97] [2000/6250] eta: 0:11:00 lr: 0.000000 grad: 0.1536 (0.1701) loss: 0.8385 (0.8369) time: 0.1506 data: 0.0750 max mem: 8452 +Train: [97] [2100/6250] eta: 0:10:46 lr: 0.000000 grad: 0.1632 (0.1696) loss: 0.8400 (0.8370) time: 0.1319 data: 0.0491 max mem: 8452 +Train: [97] [2200/6250] eta: 0:10:29 lr: 0.000000 grad: 0.1611 (0.1691) loss: 0.8415 (0.8372) time: 0.1519 data: 0.0732 max mem: 8452 +Train: [97] [2300/6250] eta: 0:10:11 lr: 0.000000 grad: 0.1767 (0.1688) loss: 0.8336 (0.8373) time: 0.1321 data: 0.0518 max mem: 8452 +Train: [97] [2400/6250] eta: 0:09:56 lr: 0.000000 grad: 0.1544 (0.1684) loss: 0.8458 (0.8375) time: 0.1395 data: 0.0533 max mem: 8452 +Train: [97] [2500/6250] eta: 0:09:40 lr: 0.000000 grad: 0.1508 (0.1679) loss: 0.8437 (0.8377) time: 0.1664 data: 0.0958 max mem: 8452 +Train: [97] [2600/6250] eta: 0:09:25 lr: 0.000000 grad: 0.1528 (0.1677) loss: 0.8464 (0.8378) time: 0.1746 data: 0.0930 max mem: 8452 +Train: [97] [2700/6250] eta: 0:09:10 lr: 0.000000 grad: 0.1519 (0.1674) loss: 0.8410 (0.8379) time: 0.1642 data: 0.0744 max mem: 8452 +Train: [97] [2800/6250] eta: 0:08:53 lr: 0.000000 grad: 0.1613 (0.1671) loss: 0.8499 (0.8380) time: 0.1530 data: 0.0734 max mem: 8452 +Train: [97] [2900/6250] eta: 0:08:39 lr: 0.000000 grad: 0.1589 (0.1669) loss: 0.8435 (0.8381) time: 0.1672 data: 0.0987 max mem: 8452 +Train: [97] [3000/6250] eta: 0:08:24 lr: 0.000000 grad: 0.1508 (0.1665) loss: 0.8390 (0.8383) time: 0.1765 data: 0.1014 max mem: 8452 +Train: [97] [3100/6250] eta: 0:08:08 lr: 0.000000 grad: 0.1520 (0.1661) loss: 0.8448 (0.8384) time: 0.1413 data: 0.0564 max mem: 8452 +Train: [97] [3200/6250] eta: 0:07:53 lr: 0.000000 grad: 0.1651 (0.1658) loss: 0.8451 (0.8385) time: 0.1511 data: 0.0697 max mem: 8452 +Train: [97] [3300/6250] eta: 0:07:38 lr: 0.000000 grad: 0.1536 (0.1655) loss: 0.8439 (0.8386) time: 0.1531 data: 0.0624 max mem: 8452 +Train: [97] [3400/6250] eta: 0:07:23 lr: 0.000000 grad: 0.1599 (0.1653) loss: 0.8446 (0.8388) time: 0.1503 data: 0.0711 max mem: 8452 +Train: [97] [3500/6250] eta: 0:07:07 lr: 0.000000 grad: 0.1436 (0.1650) loss: 0.8501 (0.8389) time: 0.1410 data: 0.0538 max mem: 8452 +Train: [97] [3600/6250] eta: 0:06:51 lr: 0.000000 grad: 0.1565 (0.1647) loss: 0.8425 (0.8390) time: 0.1284 data: 0.0476 max mem: 8452 +Train: [97] [3700/6250] eta: 0:06:35 lr: 0.000000 grad: 0.1586 (0.1647) loss: 0.8466 (0.8392) time: 0.1464 data: 0.0616 max mem: 8452 +Train: [97] [3800/6250] eta: 0:06:19 lr: 0.000000 grad: 0.1517 (0.1646) loss: 0.8425 (0.8392) time: 0.1445 data: 0.0586 max mem: 8452 +Train: [97] [3900/6250] eta: 0:06:03 lr: 0.000000 grad: 0.1591 (0.1644) loss: 0.8413 (0.8393) time: 0.1344 data: 0.0442 max mem: 8452 +Train: [97] [4000/6250] eta: 0:05:47 lr: 0.000000 grad: 0.1535 (0.1644) loss: 0.8489 (0.8395) time: 0.1305 data: 0.0502 max mem: 8452 +Train: [97] [4100/6250] eta: 0:05:32 lr: 0.000000 grad: 0.1777 (0.1644) loss: 0.8377 (0.8394) time: 0.1268 data: 0.0387 max mem: 8452 +Train: [97] [4200/6250] eta: 0:05:16 lr: 0.000000 grad: 0.1646 (0.1644) loss: 0.8421 (0.8395) time: 0.1625 data: 0.0847 max mem: 8452 +Train: [97] [4300/6250] eta: 0:05:01 lr: 0.000000 grad: 0.1579 (0.1645) loss: 0.8358 (0.8395) time: 0.1540 data: 0.0732 max mem: 8452 +Train: [97] [4400/6250] eta: 0:04:45 lr: 0.000000 grad: 0.1585 (0.1646) loss: 0.8425 (0.8394) time: 0.1449 data: 0.0619 max mem: 8452 +Train: [97] [4500/6250] eta: 0:04:29 lr: 0.000000 grad: 0.1642 (0.1647) loss: 0.8335 (0.8394) time: 0.1335 data: 0.0588 max mem: 8452 +Train: [97] [4600/6250] eta: 0:04:14 lr: 0.000000 grad: 0.1558 (0.1646) loss: 0.8381 (0.8393) time: 0.2327 data: 0.1657 max mem: 8452 +Train: [97] [4700/6250] eta: 0:03:59 lr: 0.000000 grad: 0.1598 (0.1646) loss: 0.8418 (0.8393) time: 0.1498 data: 0.0691 max mem: 8452 +Train: [97] [4800/6250] eta: 0:03:44 lr: 0.000000 grad: 0.1614 (0.1646) loss: 0.8410 (0.8392) time: 0.1274 data: 0.0418 max mem: 8452 +Train: [97] [4900/6250] eta: 0:03:28 lr: 0.000000 grad: 0.1548 (0.1646) loss: 0.8373 (0.8392) time: 0.1683 data: 0.0811 max mem: 8452 +Train: [97] [5000/6250] eta: 0:03:13 lr: 0.000000 grad: 0.1677 (0.1646) loss: 0.8306 (0.8391) time: 0.1553 data: 0.0720 max mem: 8452 +Train: [97] [5100/6250] eta: 0:02:57 lr: 0.000000 grad: 0.1651 (0.1647) loss: 0.8359 (0.8389) time: 0.1514 data: 0.0623 max mem: 8452 +Train: [97] [5200/6250] eta: 0:02:42 lr: 0.000000 grad: 0.1447 (0.1647) loss: 0.8414 (0.8389) time: 0.1320 data: 0.0444 max mem: 8452 +Train: [97] [5300/6250] eta: 0:02:26 lr: 0.000000 grad: 0.1650 (0.1647) loss: 0.8345 (0.8388) time: 0.1297 data: 0.0442 max mem: 8452 +Train: [97] [5400/6250] eta: 0:02:11 lr: 0.000000 grad: 0.1709 (0.1646) loss: 0.8356 (0.8387) time: 0.1517 data: 0.0653 max mem: 8452 +Train: [97] [5500/6250] eta: 0:01:55 lr: 0.000000 grad: 0.1483 (0.1646) loss: 0.8441 (0.8387) time: 0.1375 data: 0.0456 max mem: 8452 +Train: [97] [5600/6250] eta: 0:01:40 lr: 0.000000 grad: 0.1565 (0.1646) loss: 0.8410 (0.8387) time: 0.1397 data: 0.0534 max mem: 8452 +Train: [97] [5700/6250] eta: 0:01:24 lr: 0.000000 grad: 0.1634 (0.1646) loss: 0.8375 (0.8386) time: 0.1350 data: 0.0616 max mem: 8452 +Train: [97] [5800/6250] eta: 0:01:09 lr: 0.000000 grad: 0.1604 (0.1647) loss: 0.8378 (0.8386) time: 0.1257 data: 0.0379 max mem: 8452 +Train: [97] [5900/6250] eta: 0:00:53 lr: 0.000000 grad: 0.1579 (0.1648) loss: 0.8401 (0.8386) time: 0.1440 data: 0.0586 max mem: 8452 +Train: [97] [6000/6250] eta: 0:00:38 lr: 0.000000 grad: 0.1685 (0.1649) loss: 0.8451 (0.8387) time: 0.1199 data: 0.0327 max mem: 8452 +Train: [97] [6100/6250] eta: 0:00:23 lr: 0.000000 grad: 0.1660 (0.1649) loss: 0.8364 (0.8387) time: 0.1602 data: 0.0733 max mem: 8452 +Train: [97] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1702 (0.1649) loss: 0.8355 (0.8387) time: 0.1488 data: 0.0706 max mem: 8452 +Train: [97] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1615 (0.1649) loss: 0.8416 (0.8387) time: 0.1366 data: 0.0501 max mem: 8452 +Train: [97] Total time: 0:16:07 (0.1548 s / it) +Averaged stats: lr: 0.000000 grad: 0.1615 (0.1649) loss: 0.8416 (0.8387) +Eval (hcp-train-subset): [97] [ 0/62] eta: 0:05:55 loss: 0.8482 (0.8482) time: 5.7323 data: 5.7063 max mem: 8452 +Eval (hcp-train-subset): [97] [61/62] eta: 0:00:00 loss: 0.8365 (0.8385) time: 0.1295 data: 0.1086 max mem: 8452 +Eval (hcp-train-subset): [97] Total time: 0:00:14 (0.2330 s / it) +Averaged stats (hcp-train-subset): loss: 0.8365 (0.8385) +Eval (hcp-val): [97] [ 0/62] eta: 0:04:39 loss: 0.8617 (0.8617) time: 4.5116 data: 4.3611 max mem: 8452 +Eval (hcp-val): [97] [61/62] eta: 0:00:00 loss: 0.8642 (0.8656) time: 0.1187 data: 0.0977 max mem: 8452 +Eval (hcp-val): [97] Total time: 0:00:14 (0.2386 s / it) +Averaged stats (hcp-val): loss: 0.8642 (0.8656) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [98] [ 0/6250] eta: 9:59:43 lr: 0.000000 grad: 0.2679 (0.2679) loss: 0.8269 (0.8269) time: 5.7574 data: 5.5747 max mem: 8452 +Train: [98] [ 100/6250] eta: 0:22:37 lr: 0.000000 grad: 0.1548 (0.1686) loss: 0.8594 (0.8606) time: 0.1730 data: 0.0649 max mem: 8452 +Train: [98] [ 200/6250] eta: 0:19:30 lr: 0.000000 grad: 0.1708 (0.1721) loss: 0.8456 (0.8531) time: 0.1792 data: 0.0807 max mem: 8452 +Train: [98] [ 300/6250] eta: 0:18:04 lr: 0.000000 grad: 0.1700 (0.1730) loss: 0.8464 (0.8508) time: 0.1698 data: 0.0766 max mem: 8452 +Train: [98] [ 400/6250] eta: 0:17:15 lr: 0.000000 grad: 0.1606 (0.1726) loss: 0.8422 (0.8488) time: 0.1582 data: 0.0598 max mem: 8452 +Train: [98] [ 500/6250] eta: 0:16:28 lr: 0.000000 grad: 0.1690 (0.1713) loss: 0.8358 (0.8471) time: 0.1658 data: 0.0689 max mem: 8452 +Train: [98] [ 600/6250] eta: 0:15:52 lr: 0.000000 grad: 0.1600 (0.1713) loss: 0.8385 (0.8455) time: 0.1617 data: 0.0636 max mem: 8452 +Train: [98] [ 700/6250] eta: 0:15:21 lr: 0.000000 grad: 0.1718 (0.1711) loss: 0.8390 (0.8441) time: 0.1395 data: 0.0342 max mem: 8452 +Train: [98] [ 800/6250] eta: 0:14:55 lr: 0.000000 grad: 0.1659 (0.1721) loss: 0.8391 (0.8428) time: 0.1696 data: 0.0817 max mem: 8452 +Train: [98] [ 900/6250] eta: 0:14:31 lr: 0.000000 grad: 0.1698 (0.1722) loss: 0.8363 (0.8419) time: 0.1347 data: 0.0368 max mem: 8452 +Train: [98] [1000/6250] eta: 0:14:08 lr: 0.000000 grad: 0.1506 (0.1722) loss: 0.8351 (0.8413) time: 0.1609 data: 0.0802 max mem: 8452 +Train: [98] [1100/6250] eta: 0:13:43 lr: 0.000000 grad: 0.1582 (0.1721) loss: 0.8388 (0.8408) time: 0.1507 data: 0.0732 max mem: 8452 +Train: [98] [1200/6250] eta: 0:13:23 lr: 0.000000 grad: 0.1660 (0.1718) loss: 0.8394 (0.8406) time: 0.1631 data: 0.0805 max mem: 8452 +Train: [98] [1300/6250] eta: 0:13:03 lr: 0.000000 grad: 0.1614 (0.1715) loss: 0.8340 (0.8402) time: 0.1467 data: 0.0600 max mem: 8452 +Train: [98] [1400/6250] eta: 0:12:43 lr: 0.000000 grad: 0.1638 (0.1708) loss: 0.8391 (0.8399) time: 0.1624 data: 0.0810 max mem: 8452 +Train: [98] [1500/6250] eta: 0:12:25 lr: 0.000000 grad: 0.1639 (0.1705) loss: 0.8370 (0.8396) time: 0.1312 data: 0.0507 max mem: 8452 +Train: [98] [1600/6250] eta: 0:12:06 lr: 0.000000 grad: 0.1665 (0.1703) loss: 0.8361 (0.8394) time: 0.1289 data: 0.0502 max mem: 8452 +Train: [98] [1700/6250] eta: 0:11:49 lr: 0.000000 grad: 0.1645 (0.1702) loss: 0.8354 (0.8393) time: 0.1752 data: 0.0976 max mem: 8452 +Train: [98] [1800/6250] eta: 0:11:31 lr: 0.000000 grad: 0.1536 (0.1699) loss: 0.8423 (0.8393) time: 0.1606 data: 0.0822 max mem: 8452 +Train: [98] [1900/6250] eta: 0:11:15 lr: 0.000000 grad: 0.1640 (0.1700) loss: 0.8390 (0.8391) time: 0.1446 data: 0.0690 max mem: 8452 +Train: [98] [2000/6250] eta: 0:10:58 lr: 0.000000 grad: 0.1618 (0.1699) loss: 0.8436 (0.8391) time: 0.1568 data: 0.0777 max mem: 8452 +Train: [98] [2100/6250] eta: 0:10:41 lr: 0.000000 grad: 0.1652 (0.1696) loss: 0.8370 (0.8391) time: 0.1112 data: 0.0275 max mem: 8452 +Train: [98] [2200/6250] eta: 0:10:25 lr: 0.000000 grad: 0.1642 (0.1693) loss: 0.8334 (0.8390) time: 0.1512 data: 0.0682 max mem: 8452 +Train: [98] [2300/6250] eta: 0:10:11 lr: 0.000000 grad: 0.1614 (0.1694) loss: 0.8271 (0.8388) time: 0.1837 data: 0.0922 max mem: 8452 +Train: [98] [2400/6250] eta: 0:09:55 lr: 0.000000 grad: 0.1608 (0.1692) loss: 0.8348 (0.8386) time: 0.1493 data: 0.0683 max mem: 8452 +Train: [98] [2500/6250] eta: 0:09:39 lr: 0.000000 grad: 0.1602 (0.1689) loss: 0.8442 (0.8385) time: 0.1451 data: 0.0707 max mem: 8452 +Train: [98] [2600/6250] eta: 0:09:23 lr: 0.000000 grad: 0.1601 (0.1689) loss: 0.8339 (0.8384) time: 0.1387 data: 0.0542 max mem: 8452 +Train: [98] [2700/6250] eta: 0:09:07 lr: 0.000000 grad: 0.1684 (0.1688) loss: 0.8290 (0.8382) time: 0.1475 data: 0.0767 max mem: 8452 +Train: [98] [2800/6250] eta: 0:08:52 lr: 0.000000 grad: 0.1557 (0.1687) loss: 0.8363 (0.8382) time: 0.1623 data: 0.0804 max mem: 8452 +Train: [98] [2900/6250] eta: 0:08:39 lr: 0.000000 grad: 0.1604 (0.1686) loss: 0.8353 (0.8381) time: 0.1898 data: 0.1143 max mem: 8452 +Train: [98] [3000/6250] eta: 0:08:24 lr: 0.000000 grad: 0.1672 (0.1686) loss: 0.8363 (0.8381) time: 0.1708 data: 0.0974 max mem: 8452 +Train: [98] [3100/6250] eta: 0:08:08 lr: 0.000000 grad: 0.1771 (0.1686) loss: 0.8361 (0.8380) time: 0.1436 data: 0.0703 max mem: 8452 +Train: [98] [3200/6250] eta: 0:07:53 lr: 0.000000 grad: 0.1633 (0.1687) loss: 0.8400 (0.8379) time: 0.1598 data: 0.0867 max mem: 8452 +Train: [98] [3300/6250] eta: 0:07:38 lr: 0.000000 grad: 0.1757 (0.1689) loss: 0.8400 (0.8380) time: 0.1369 data: 0.0618 max mem: 8452 +Train: [98] [3400/6250] eta: 0:07:22 lr: 0.000000 grad: 0.1634 (0.1689) loss: 0.8422 (0.8380) time: 0.1518 data: 0.0768 max mem: 8452 +Train: [98] [3500/6250] eta: 0:07:07 lr: 0.000000 grad: 0.1592 (0.1688) loss: 0.8315 (0.8379) time: 0.1578 data: 0.0771 max mem: 8452 +Train: [98] [3600/6250] eta: 0:06:51 lr: 0.000000 grad: 0.1647 (0.1688) loss: 0.8393 (0.8380) time: 0.1367 data: 0.0545 max mem: 8452 +Train: [98] [3700/6250] eta: 0:06:34 lr: 0.000000 grad: 0.1637 (0.1687) loss: 0.8388 (0.8380) time: 0.1454 data: 0.0649 max mem: 8452 +Train: [98] [3800/6250] eta: 0:06:18 lr: 0.000000 grad: 0.1553 (0.1687) loss: 0.8348 (0.8379) time: 0.1508 data: 0.0703 max mem: 8452 +Train: [98] [3900/6250] eta: 0:06:02 lr: 0.000000 grad: 0.1647 (0.1688) loss: 0.8379 (0.8379) time: 0.1755 data: 0.0953 max mem: 8452 +Train: [98] [4000/6250] eta: 0:05:46 lr: 0.000000 grad: 0.1730 (0.1686) loss: 0.8387 (0.8379) time: 0.1556 data: 0.0661 max mem: 8452 +Train: [98] [4100/6250] eta: 0:05:31 lr: 0.000000 grad: 0.1595 (0.1686) loss: 0.8349 (0.8379) time: 0.1574 data: 0.0745 max mem: 8452 +Train: [98] [4200/6250] eta: 0:05:15 lr: 0.000000 grad: 0.1746 (0.1684) loss: 0.8338 (0.8379) time: 0.1775 data: 0.0958 max mem: 8452 +Train: [98] [4300/6250] eta: 0:05:00 lr: 0.000000 grad: 0.1555 (0.1684) loss: 0.8461 (0.8378) time: 0.1361 data: 0.0545 max mem: 8452 +Train: [98] [4400/6250] eta: 0:04:44 lr: 0.000000 grad: 0.1495 (0.1684) loss: 0.8428 (0.8379) time: 0.1660 data: 0.0899 max mem: 8452 +Train: [98] [4500/6250] eta: 0:04:29 lr: 0.000000 grad: 0.1702 (0.1684) loss: 0.8391 (0.8379) time: 0.1611 data: 0.0833 max mem: 8452 +Train: [98] [4600/6250] eta: 0:04:13 lr: 0.000000 grad: 0.1623 (0.1684) loss: 0.8362 (0.8378) time: 0.1366 data: 0.0425 max mem: 8452 +Train: [98] [4700/6250] eta: 0:03:58 lr: 0.000000 grad: 0.1622 (0.1683) loss: 0.8408 (0.8377) time: 0.1657 data: 0.0782 max mem: 8452 +Train: [98] [4800/6250] eta: 0:03:43 lr: 0.000000 grad: 0.1616 (0.1683) loss: 0.8378 (0.8377) time: 0.1695 data: 0.0856 max mem: 8452 +Train: [98] [4900/6250] eta: 0:03:27 lr: 0.000000 grad: 0.1603 (0.1682) loss: 0.8438 (0.8378) time: 0.1534 data: 0.0733 max mem: 8452 +Train: [98] [5000/6250] eta: 0:03:12 lr: 0.000000 grad: 0.1652 (0.1683) loss: 0.8408 (0.8378) time: 0.1528 data: 0.0706 max mem: 8452 +Train: [98] [5100/6250] eta: 0:02:57 lr: 0.000000 grad: 0.1602 (0.1680) loss: 0.8384 (0.8378) time: 0.1497 data: 0.0722 max mem: 8452 +Train: [98] [5200/6250] eta: 0:02:41 lr: 0.000000 grad: 0.1547 (0.1679) loss: 0.8398 (0.8378) time: 0.1526 data: 0.0689 max mem: 8452 +Train: [98] [5300/6250] eta: 0:02:26 lr: 0.000000 grad: 0.1565 (0.1678) loss: 0.8341 (0.8378) time: 0.1350 data: 0.0579 max mem: 8452 +Train: [98] [5400/6250] eta: 0:02:10 lr: 0.000000 grad: 0.1612 (0.1678) loss: 0.8399 (0.8378) time: 0.1466 data: 0.0710 max mem: 8452 +Train: [98] [5500/6250] eta: 0:01:55 lr: 0.000000 grad: 0.1679 (0.1678) loss: 0.8460 (0.8379) time: 0.1447 data: 0.0636 max mem: 8452 +Train: [98] [5600/6250] eta: 0:01:39 lr: 0.000000 grad: 0.1647 (0.1678) loss: 0.8412 (0.8379) time: 0.1433 data: 0.0581 max mem: 8452 +Train: [98] [5700/6250] eta: 0:01:24 lr: 0.000000 grad: 0.1630 (0.1678) loss: 0.8400 (0.8378) time: 0.1599 data: 0.0722 max mem: 8452 +Train: [98] [5800/6250] eta: 0:01:08 lr: 0.000000 grad: 0.1590 (0.1677) loss: 0.8378 (0.8379) time: 0.1472 data: 0.0585 max mem: 8452 +Train: [98] [5900/6250] eta: 0:00:53 lr: 0.000000 grad: 0.1589 (0.1678) loss: 0.8385 (0.8379) time: 0.1410 data: 0.0539 max mem: 8452 +Train: [98] [6000/6250] eta: 0:00:38 lr: 0.000000 grad: 0.1515 (0.1677) loss: 0.8388 (0.8380) time: 0.1490 data: 0.0612 max mem: 8452 +Train: [98] [6100/6250] eta: 0:00:22 lr: 0.000000 grad: 0.1562 (0.1677) loss: 0.8421 (0.8380) time: 0.1908 data: 0.1163 max mem: 8452 +Train: [98] [6200/6250] eta: 0:00:07 lr: 0.000000 grad: 0.1650 (0.1676) loss: 0.8389 (0.8380) time: 0.1482 data: 0.0626 max mem: 8452 +Train: [98] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1703 (0.1676) loss: 0.8245 (0.8380) time: 0.1442 data: 0.0561 max mem: 8452 +Train: [98] Total time: 0:16:04 (0.1543 s / it) +Averaged stats: lr: 0.000000 grad: 0.1703 (0.1676) loss: 0.8245 (0.8380) +Eval (hcp-train-subset): [98] [ 0/62] eta: 0:06:36 loss: 0.8485 (0.8485) time: 6.3881 data: 6.3622 max mem: 8452 +Eval (hcp-train-subset): [98] [61/62] eta: 0:00:00 loss: 0.8368 (0.8385) time: 0.1191 data: 0.0984 max mem: 8452 +Eval (hcp-train-subset): [98] Total time: 0:00:14 (0.2383 s / it) +Averaged stats (hcp-train-subset): loss: 0.8368 (0.8385) +Eval (hcp-val): [98] [ 0/62] eta: 0:06:32 loss: 0.8623 (0.8623) time: 6.3351 data: 6.3089 max mem: 8452 +Eval (hcp-val): [98] [61/62] eta: 0:00:00 loss: 0.8633 (0.8658) time: 0.1334 data: 0.1124 max mem: 8452 +Eval (hcp-val): [98] Total time: 0:00:14 (0.2349 s / it) +Averaged stats (hcp-val): loss: 0.8633 (0.8658) +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +Train: [99] [ 0/6250] eta: 8:09:12 lr: 0.000000 grad: 0.1711 (0.1711) loss: 0.8976 (0.8976) time: 4.6964 data: 4.3879 max mem: 8452 +Train: [99] [ 100/6250] eta: 0:20:26 lr: 0.000000 grad: 0.1783 (0.2110) loss: 0.8468 (0.8486) time: 0.1536 data: 0.0641 max mem: 8452 +Train: [99] [ 200/6250] eta: 0:17:36 lr: 0.000000 grad: 0.1534 (0.1927) loss: 0.8496 (0.8475) time: 0.1508 data: 0.0616 max mem: 8452 +Train: [99] [ 300/6250] eta: 0:16:14 lr: 0.000000 grad: 0.1732 (0.1850) loss: 0.8462 (0.8470) time: 0.1329 data: 0.0450 max mem: 8452 +Train: [99] [ 400/6250] eta: 0:15:35 lr: 0.000000 grad: 0.1665 (0.1832) loss: 0.8352 (0.8448) time: 0.1575 data: 0.0708 max mem: 8452 +Train: [99] [ 500/6250] eta: 0:14:57 lr: 0.000000 grad: 0.1755 (0.1817) loss: 0.8435 (0.8438) time: 0.1218 data: 0.0395 max mem: 8452 +Train: [99] [ 600/6250] eta: 0:14:26 lr: 0.000000 grad: 0.1708 (0.1816) loss: 0.8436 (0.8431) time: 0.1258 data: 0.0479 max mem: 8452 +Train: [99] [ 700/6250] eta: 0:13:58 lr: 0.000000 grad: 0.1770 (0.1812) loss: 0.8465 (0.8428) time: 0.1364 data: 0.0548 max mem: 8452 +Train: [99] [ 800/6250] eta: 0:13:30 lr: 0.000000 grad: 0.1675 (0.1809) loss: 0.8488 (0.8425) time: 0.1251 data: 0.0509 max mem: 8452 +Train: [99] [ 900/6250] eta: 0:13:07 lr: 0.000000 grad: 0.1560 (0.1804) loss: 0.8356 (0.8424) time: 0.1523 data: 0.0726 max mem: 8452 +Train: [99] [1000/6250] eta: 0:12:39 lr: 0.000000 grad: 0.1763 (0.1804) loss: 0.8418 (0.8419) time: 0.1225 data: 0.0346 max mem: 8452 +Train: [99] [1100/6250] eta: 0:12:16 lr: 0.000000 grad: 0.1753 (0.1801) loss: 0.8319 (0.8416) time: 0.1330 data: 0.0595 max mem: 8452 +Train: [99] [1200/6250] eta: 0:11:55 lr: 0.000000 grad: 0.1588 (0.1798) loss: 0.8488 (0.8415) time: 0.1225 data: 0.0380 max mem: 8452 +Train: [99] [1300/6250] eta: 0:11:34 lr: 0.000000 grad: 0.1569 (0.1797) loss: 0.8379 (0.8412) time: 0.1027 data: 0.0279 max mem: 8452 +Train: [99] [1400/6250] eta: 0:11:14 lr: 0.000000 grad: 0.1597 (0.1793) loss: 0.8392 (0.8410) time: 0.1134 data: 0.0335 max mem: 8452 +Train: [99] [1500/6250] eta: 0:10:56 lr: 0.000000 grad: 0.1664 (0.1786) loss: 0.8313 (0.8410) time: 0.1153 data: 0.0375 max mem: 8452 +Train: [99] [1600/6250] eta: 0:10:39 lr: 0.000000 grad: 0.1607 (0.1782) loss: 0.8391 (0.8408) time: 0.1269 data: 0.0519 max mem: 8452 +Train: [99] [1700/6250] eta: 0:10:20 lr: 0.000000 grad: 0.1679 (0.1777) loss: 0.8353 (0.8407) time: 0.1033 data: 0.0176 max mem: 8452 +Train: [99] [1800/6250] eta: 0:10:05 lr: 0.000000 grad: 0.1691 (0.1772) loss: 0.8454 (0.8407) time: 0.1170 data: 0.0288 max mem: 8452 +Train: [99] [1900/6250] eta: 0:09:49 lr: 0.000000 grad: 0.1623 (0.1768) loss: 0.8354 (0.8405) time: 0.1274 data: 0.0571 max mem: 8452 +Train: [99] [2000/6250] eta: 0:09:34 lr: 0.000000 grad: 0.1600 (0.1766) loss: 0.8407 (0.8404) time: 0.0959 data: 0.0118 max mem: 8452 +Train: [99] [2100/6250] eta: 0:09:18 lr: 0.000000 grad: 0.1518 (0.1760) loss: 0.8333 (0.8404) time: 0.1277 data: 0.0553 max mem: 8452 +Train: [99] [2200/6250] eta: 0:09:02 lr: 0.000000 grad: 0.1639 (0.1756) loss: 0.8264 (0.8401) time: 0.1184 data: 0.0357 max mem: 8452 +Train: [99] [2300/6250] eta: 0:08:47 lr: 0.000000 grad: 0.1510 (0.1751) loss: 0.8296 (0.8398) time: 0.1236 data: 0.0502 max mem: 8452 +Train: [99] [2400/6250] eta: 0:08:32 lr: 0.000000 grad: 0.1576 (0.1746) loss: 0.8322 (0.8397) time: 0.1172 data: 0.0467 max mem: 8452 +Train: [99] [2500/6250] eta: 0:08:17 lr: 0.000000 grad: 0.1477 (0.1742) loss: 0.8358 (0.8396) time: 0.1151 data: 0.0328 max mem: 8452 +Train: [99] [2600/6250] eta: 0:08:03 lr: 0.000000 grad: 0.1551 (0.1739) loss: 0.8410 (0.8395) time: 0.1188 data: 0.0417 max mem: 8452 +Train: [99] [2700/6250] eta: 0:07:49 lr: 0.000000 grad: 0.1696 (0.1736) loss: 0.8330 (0.8394) time: 0.1167 data: 0.0376 max mem: 8452 +Train: [99] [2800/6250] eta: 0:07:35 lr: 0.000000 grad: 0.1596 (0.1731) loss: 0.8335 (0.8394) time: 0.1237 data: 0.0485 max mem: 8452 +Train: [99] [2900/6250] eta: 0:07:22 lr: 0.000000 grad: 0.1553 (0.1728) loss: 0.8412 (0.8393) time: 0.1690 data: 0.1045 max mem: 8452 +Train: [99] [3000/6250] eta: 0:07:10 lr: 0.000000 grad: 0.1632 (0.1726) loss: 0.8348 (0.8393) time: 0.1394 data: 0.0619 max mem: 8452 +Train: [99] [3100/6250] eta: 0:06:58 lr: 0.000000 grad: 0.1463 (0.1722) loss: 0.8447 (0.8393) time: 0.1465 data: 0.0712 max mem: 8452 +Train: [99] [3200/6250] eta: 0:06:45 lr: 0.000000 grad: 0.1677 (0.1720) loss: 0.8254 (0.8393) time: 0.1333 data: 0.0663 max mem: 8452 +Train: [99] [3300/6250] eta: 0:06:31 lr: 0.000000 grad: 0.1594 (0.1717) loss: 0.8360 (0.8393) time: 0.1324 data: 0.0725 max mem: 8452 +Train: [99] [3400/6250] eta: 0:06:18 lr: 0.000000 grad: 0.1619 (0.1715) loss: 0.8415 (0.8394) time: 0.1234 data: 0.0609 max mem: 8452 +Train: [99] [3500/6250] eta: 0:06:04 lr: 0.000000 grad: 0.1816 (0.1715) loss: 0.8306 (0.8394) time: 0.1325 data: 0.0627 max mem: 8452 +Train: [99] [3600/6250] eta: 0:05:50 lr: 0.000000 grad: 0.1643 (0.1715) loss: 0.8348 (0.8394) time: 0.1157 data: 0.0488 max mem: 8452 +Train: [99] [3700/6250] eta: 0:05:37 lr: 0.000000 grad: 0.1662 (0.1715) loss: 0.8439 (0.8395) time: 0.1741 data: 0.1042 max mem: 8452 +Train: [99] [3800/6250] eta: 0:05:23 lr: 0.000000 grad: 0.1725 (0.1715) loss: 0.8430 (0.8395) time: 0.1299 data: 0.0591 max mem: 8452 +Train: [99] [3900/6250] eta: 0:05:10 lr: 0.000000 grad: 0.1663 (0.1716) loss: 0.8392 (0.8396) time: 0.1195 data: 0.0548 max mem: 8452 +Train: [99] [4000/6250] eta: 0:04:56 lr: 0.000000 grad: 0.1622 (0.1716) loss: 0.8478 (0.8396) time: 0.1328 data: 0.0644 max mem: 8452 +Train: [99] [4100/6250] eta: 0:04:43 lr: 0.000000 grad: 0.1696 (0.1717) loss: 0.8408 (0.8397) time: 0.1300 data: 0.0662 max mem: 8452 +Train: [99] [4200/6250] eta: 0:04:29 lr: 0.000000 grad: 0.1728 (0.1718) loss: 0.8408 (0.8398) time: 0.1445 data: 0.0786 max mem: 8452 +Train: [99] [4300/6250] eta: 0:04:16 lr: 0.000000 grad: 0.1727 (0.1718) loss: 0.8389 (0.8398) time: 0.1289 data: 0.0608 max mem: 8452 +Train: [99] [4400/6250] eta: 0:04:03 lr: 0.000000 grad: 0.1750 (0.1719) loss: 0.8390 (0.8398) time: 0.1395 data: 0.0748 max mem: 8452 +Train: [99] [4500/6250] eta: 0:03:49 lr: 0.000000 grad: 0.1652 (0.1719) loss: 0.8382 (0.8399) time: 0.1159 data: 0.0464 max mem: 8452 +Train: [99] [4600/6250] eta: 0:03:36 lr: 0.000000 grad: 0.1637 (0.1720) loss: 0.8432 (0.8399) time: 0.1192 data: 0.0540 max mem: 8452 +Train: [99] [4700/6250] eta: 0:03:23 lr: 0.000000 grad: 0.1605 (0.1720) loss: 0.8443 (0.8400) time: 0.1360 data: 0.0711 max mem: 8452 +Train: [99] [4800/6250] eta: 0:03:10 lr: 0.000000 grad: 0.1614 (0.1720) loss: 0.8469 (0.8400) time: 0.1444 data: 0.0766 max mem: 8452 +Train: [99] [4900/6250] eta: 0:02:56 lr: 0.000000 grad: 0.1571 (0.1718) loss: 0.8446 (0.8401) time: 0.1147 data: 0.0522 max mem: 8452 +Train: [99] [5000/6250] eta: 0:02:43 lr: 0.000000 grad: 0.1588 (0.1717) loss: 0.8389 (0.8401) time: 0.1350 data: 0.0720 max mem: 8452 +Train: [99] [5100/6250] eta: 0:02:30 lr: 0.000000 grad: 0.1563 (0.1716) loss: 0.8369 (0.8401) time: 0.1228 data: 0.0516 max mem: 8452 +Train: [99] [5200/6250] eta: 0:02:17 lr: 0.000000 grad: 0.1554 (0.1715) loss: 0.8375 (0.8401) time: 0.1014 data: 0.0318 max mem: 8452 +Train: [99] [5300/6250] eta: 0:02:03 lr: 0.000000 grad: 0.1618 (0.1714) loss: 0.8392 (0.8401) time: 0.1233 data: 0.0562 max mem: 8452 +Train: [99] [5400/6250] eta: 0:01:50 lr: 0.000000 grad: 0.1721 (0.1714) loss: 0.8457 (0.8401) time: 0.1251 data: 0.0577 max mem: 8452 +Train: [99] [5500/6250] eta: 0:01:37 lr: 0.000000 grad: 0.1634 (0.1713) loss: 0.8405 (0.8400) time: 0.1121 data: 0.0509 max mem: 8452 +Train: [99] [5600/6250] eta: 0:01:24 lr: 0.000000 grad: 0.1505 (0.1711) loss: 0.8417 (0.8400) time: 0.1132 data: 0.0474 max mem: 8452 +Train: [99] [5700/6250] eta: 0:01:11 lr: 0.000000 grad: 0.1643 (0.1710) loss: 0.8392 (0.8400) time: 0.1136 data: 0.0423 max mem: 8452 +Train: [99] [5800/6250] eta: 0:00:58 lr: 0.000000 grad: 0.1591 (0.1709) loss: 0.8363 (0.8400) time: 0.1085 data: 0.0363 max mem: 8452 +Train: [99] [5900/6250] eta: 0:00:45 lr: 0.000000 grad: 0.1530 (0.1707) loss: 0.8457 (0.8400) time: 0.1066 data: 0.0404 max mem: 8452 +Train: [99] [6000/6250] eta: 0:00:32 lr: 0.000000 grad: 0.1714 (0.1706) loss: 0.8368 (0.8399) time: 0.1096 data: 0.0407 max mem: 8452 +Train: [99] [6100/6250] eta: 0:00:19 lr: 0.000000 grad: 0.1582 (0.1705) loss: 0.8457 (0.8399) time: 0.1230 data: 0.0565 max mem: 8452 +Train: [99] [6200/6250] eta: 0:00:06 lr: 0.000000 grad: 0.1621 (0.1704) loss: 0.8384 (0.8398) time: 0.0971 data: 0.0241 max mem: 8452 +Train: [99] [6249/6250] eta: 0:00:00 lr: 0.000000 grad: 0.1563 (0.1704) loss: 0.8393 (0.8398) time: 0.1124 data: 0.0452 max mem: 8452 +Train: [99] Total time: 0:13:25 (0.1289 s / it) +Averaged stats: lr: 0.000000 grad: 0.1563 (0.1704) loss: 0.8393 (0.8398) +Eval (hcp-train-subset): [99] [ 0/62] eta: 0:03:23 loss: 0.8463 (0.8463) time: 3.2840 data: 3.2255 max mem: 8452 +Eval (hcp-train-subset): [99] [61/62] eta: 0:00:00 loss: 0.8369 (0.8383) time: 0.1046 data: 0.0829 max mem: 8452 +Eval (hcp-train-subset): [99] Total time: 0:00:11 (0.1855 s / it) +Averaged stats (hcp-train-subset): loss: 0.8369 (0.8383) +Making plots (hcp-train-subset): example=56 +Eval (hcp-val): [99] [ 0/62] eta: 0:04:03 loss: 0.8620 (0.8620) time: 3.9221 data: 3.8644 max mem: 8452 +Eval (hcp-val): [99] [61/62] eta: 0:00:00 loss: 0.8632 (0.8655) time: 0.1173 data: 0.0956 max mem: 8452 +Eval (hcp-val): [99] Total time: 0:00:11 (0.1883 s / it) +Averaged stats (hcp-val): loss: 0.8632 (0.8655) +Making plots (hcp-val): example=50 +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-last.pth +saving checkpoint experiments/decoders/output/decoders/crossreg_reg16/pretrain/checkpoint-00099.pth +done! training time: 1 day, 6:16:34 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f74cce4c7ad628277b92a20b64f32ee5cc9f0309 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..58073b339cf8b53b0cbd9c85bd6de9bda2a0dd1e --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,train,0.6909448818897638,0.020763181950737924,0.6907714693832445,0.020899903319859962,0.6925549586312407,0.020679987336976687 +flat_mae,patch,logistic,aabc_age,,0.005994842503189409,test,0.4230769230769231,0.06590602059217245,0.40371456500488756,0.06808393227500256,0.4141483516483516,0.06559979351340875 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,train,0.6791338582677166,0.020777861089126153,0.6773560548957107,0.02114130571680033,0.6805879343446064,0.02079693526867027 +flat_mae,patch,logistic,aabc_age,1,0.005994842503189409,test,0.4423076923076923,0.05639950218001792,0.41239316239316237,0.05436409633709529,0.4384157509157509,0.05567966292079005 +flat_mae,patch,logistic,aabc_age,2,9.999999999999999e-05,train,0.4763779527559055,0.02025906175910342,0.45125754758827974,0.020708422841936115,0.4750462226859408,0.02011398700358501 +flat_mae,patch,logistic,aabc_age,2,9.999999999999999e-05,test,0.5384615384615384,0.05775661800241529,0.48668981481481477,0.05814183411080539,0.5290750915750916,0.05668041956763944 +flat_mae,patch,logistic,aabc_age,3,0.005994842503189409,train,0.6889763779527559,0.01973508402432284,0.6874103586560196,0.020001743866494767,0.6894131588890445,0.019793685565074364 +flat_mae,patch,logistic,aabc_age,3,0.005994842503189409,test,0.5384615384615384,0.061622346672838224,0.5105596872616323,0.06704800119865006,0.5364010989010989,0.06150449099442846 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,train,0.9980314960629921,0.001954739277246782,0.99795904766665,0.002026591296432331,0.997983870967742,0.002002031356535018 +flat_mae,patch,logistic,aabc_age,4,0.3593813663804626,test,0.5,0.0684247524333273,0.5040692640692641,0.06926628446379131,0.5059523809523809,0.06836869825039218 +flat_mae,patch,logistic,aabc_age,5,0.046415888336127774,train,0.8523622047244095,0.015209318760113963,0.8525323658599772,0.015323600985181825,0.8539500977197447,0.01504255220852414 +flat_mae,patch,logistic,aabc_age,5,0.046415888336127774,test,0.4807692307692308,0.06756636010435577,0.4786324786324786,0.0661093383225889,0.4816849816849817,0.06786103385897078 +flat_mae,patch,logistic,aabc_age,6,0.046415888336127774,train,0.844488188976378,0.016278123124444828,0.8443733011174872,0.01636457889917709,0.8454680670286485,0.016212092090831107 +flat_mae,patch,logistic,aabc_age,6,0.046415888336127774,test,0.4807692307692308,0.0689482590500696,0.4864021164021164,0.06794342502268319,0.4835164835164835,0.06905267364370371 +flat_mae,patch,logistic,aabc_age,7,0.000774263682681127,train,0.562992125984252,0.020424341967551597,0.5553293142541823,0.021151957160022043,0.564402849887512,0.02044211858504042 +flat_mae,patch,logistic,aabc_age,7,0.000774263682681127,test,0.5384615384615384,0.06227372055842937,0.506237322515213,0.06520498816089634,0.532051282051282,0.06195571716329027 +flat_mae,patch,logistic,aabc_age,8,0.005994842503189409,train,0.6889763779527559,0.020405326087927757,0.687049600671336,0.020761185094706567,0.6886604819050651,0.02043039854223848 +flat_mae,patch,logistic,aabc_age,8,0.005994842503189409,test,0.5961538461538461,0.0544544758567044,0.56426267281106,0.05689714846677295,0.6062271062271063,0.0552631218048549 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,train,0.6830708661417323,0.020401299772957227,0.6819329854201993,0.020749969086261283,0.6849377336307441,0.020399140001151967 +flat_mae,patch,logistic,aabc_age,9,0.005994842503189409,test,0.5769230769230769,0.06299313149371617,0.5644450883801797,0.06934074177484975,0.575091575091575,0.06334943604915923 +flat_mae,patch,logistic,aabc_age,10,0.005994842503189409,train,0.6811023622047244,0.020122410437688705,0.6803625759437936,0.020448172602646097,0.68333911916055,0.020057397316801184 +flat_mae,patch,logistic,aabc_age,10,0.005994842503189409,test,0.4807692307692308,0.062125517154039085,0.4709891557717645,0.0647405205774203,0.48031135531135527,0.06203143684892928 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,train,0.860236220472441,0.016250936055681387,0.860712069420382,0.016275459824429774,0.8609267744428823,0.016243121538830986 +flat_mae,patch,logistic,aabc_age,11,0.046415888336127774,test,0.5769230769230769,0.06764570073849754,0.5788461538461538,0.06804346814862999,0.5755494505494505,0.06789688615317782 +flat_mae,patch,logistic,aabc_age,12,0.046415888336127774,train,0.8641732283464567,0.014945132877093908,0.863863319719171,0.015049314576448392,0.8642063555234192,0.014886540799393342 +flat_mae,patch,logistic,aabc_age,12,0.046415888336127774,test,0.4807692307692308,0.06436623209664775,0.486043956043956,0.0631173860656559,0.48649267399267404,0.0649968654708216 +flat_mae,patch,logistic,aabc_age,13,0.046415888336127774,train,0.8622047244094488,0.014876785359663061,0.8626642501433204,0.014864213197375497,0.8625077677127826,0.014899140166468951 +flat_mae,patch,logistic,aabc_age,13,0.046415888336127774,test,0.46153846153846156,0.0668999075719548,0.46705508662030404,0.06417401843311422,0.46543040293040294,0.06742120304890836 +flat_mae,patch,logistic,aabc_age,14,0.005994842503189409,train,0.6791338582677166,0.020005463014814248,0.6766086567492655,0.020477820100177,0.6803203797932063,0.01993470942029186 +flat_mae,patch,logistic,aabc_age,14,0.005994842503189409,test,0.5961538461538461,0.06498743620043282,0.5892180824269109,0.06880636437949011,0.5959249084249084,0.06511275234173927 +flat_mae,patch,logistic,aabc_age,15,0.3593813663804626,train,0.9940944881889764,0.003452322672790542,0.9941191941141836,0.0034344744225282076,0.9941191941141836,0.0034387967891773624 +flat_mae,patch,logistic,aabc_age,15,0.3593813663804626,test,0.46153846153846156,0.06315829647956936,0.4678713527851459,0.06194251533017741,0.4597069597069597,0.06329806029961517 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,train,0.6751968503937008,0.02008170851919811,0.670150388403345,0.02071235768361279,0.6749003623014678,0.020066184602780035 +flat_mae,patch,logistic,aabc_age,16,0.005994842503189409,test,0.4230769230769231,0.06712140153765189,0.4226190476190476,0.06939709107622663,0.41964285714285715,0.06700304467369642 +flat_mae,patch,logistic,aabc_age,17,0.046415888336127774,train,0.8503937007874016,0.015934612713328335,0.8507753695682757,0.016026973672029435,0.851131305033286,0.01587008112464326 +flat_mae,patch,logistic,aabc_age,17,0.046415888336127774,test,0.5384615384615384,0.06529055451499657,0.5335724994645534,0.06670212663077621,0.5382326007326007,0.06512887868192521 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,train,0.8582677165354331,0.015054216195433442,0.8582551864136222,0.015207560589986062,0.8592957945027608,0.015036312193842235 +flat_mae,patch,logistic,aabc_age,18,0.046415888336127774,test,0.5,0.06636455709088868,0.49119584438549957,0.06799515855244659,0.502518315018315,0.0664501772174689 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,train,0.8582677165354331,0.015063600775516349,0.8582233944137753,0.015239871313684166,0.85978091693534,0.014933732717254412 +flat_mae,patch,logistic,aabc_age,19,0.046415888336127774,test,0.5769230769230769,0.06723120929269813,0.5755494505494505,0.06780044458458498,0.5771520146520146,0.06709150664989616 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,train,0.6771653543307087,0.021797373425506486,0.6748368898935773,0.022303699170135003,0.678036696209548,0.02172760134747154 +flat_mae,patch,logistic,aabc_age,20,0.005994842503189409,test,0.5384615384615384,0.06257535102748539,0.5354417293233082,0.06489870391041111,0.5366300366300366,0.0627358407390661 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,train,0.8641732283464567,0.01475971807652691,0.8649613587456145,0.014732681680215597,0.8650090191776199,0.01467872634219246 +flat_mae,patch,logistic,aabc_age,21,0.046415888336127774,test,0.36538461538461536,0.058200060493268556,0.3547427035330261,0.0576444117850116,0.36881868131868134,0.0590071627331715 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,train,0.8484251968503937,0.01567115636034188,0.8493403883292446,0.015644370885393364,0.8499178396552286,0.01563074486926483 +flat_mae,patch,logistic,aabc_age,22,0.046415888336127774,test,0.4423076923076923,0.06676616219464156,0.4439153439153439,0.06715179872228669,0.4439102564102565,0.06687174144178824 +flat_mae,patch,logistic,aabc_age,23,0.046415888336127774,train,0.8622047244094488,0.014884749027494789,0.8627583070592184,0.014922837405432448,0.8629928901453617,0.014891218224479134 +flat_mae,patch,logistic,aabc_age,23,0.046415888336127774,test,0.5192307692307693,0.06450659339723325,0.5026540616246498,0.06523204647569442,0.5171703296703296,0.06425776429879188 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,train,0.8681102362204725,0.01467381724848122,0.8681489538071451,0.014747472936497958,0.8685061681393355,0.014555548421831889 +flat_mae,patch,logistic,aabc_age,24,0.046415888336127774,test,0.38461538461538464,0.06178483134730874,0.38470187982931614,0.06086732862010043,0.3825549450549451,0.06161444609250516 +flat_mae,patch,logistic,aabc_age,25,0.046415888336127774,train,0.8543307086614174,0.016135717623420618,0.8544610839106795,0.01624793665421405,0.8562337813034031,0.015966829055632445 +flat_mae,patch,logistic,aabc_age,25,0.046415888336127774,test,0.5192307692307693,0.0645184598142635,0.5143870372506055,0.06604555179013286,0.521978021978022,0.06459518165432901 +flat_mae,patch,logistic,aabc_age,26,0.046415888336127774,train,0.8562992125984252,0.01482453431085224,0.8563778539123184,0.01494902624558214,0.8572796654705029,0.014836994384072223 +flat_mae,patch,logistic,aabc_age,26,0.046415888336127774,test,0.46153846153846156,0.06586577484443638,0.46314102564102566,0.06626812904535904,0.46726190476190477,0.06597669329456253 +flat_mae,patch,logistic,aabc_age,27,0.005994842503189409,train,0.6692913385826772,0.020184766764806048,0.6672304346812847,0.02053235529783431,0.6696546388588942,0.020153753016745383 +flat_mae,patch,logistic,aabc_age,27,0.005994842503189409,test,0.40384615384615385,0.06264339762714176,0.38983627933932197,0.06324771084643517,0.40041208791208793,0.062080165128487554 +flat_mae,patch,logistic,aabc_age,28,0.3593813663804626,train,0.9960629921259843,0.002685890714086824,0.9959177224842757,0.0027852893204049827,0.9959177552652626,0.0027851532983297397 +flat_mae,patch,logistic,aabc_age,28,0.3593813663804626,test,0.5,0.0695210155106579,0.4998357963875205,0.07005433430211298,0.4981684981684982,0.06953988285019243 +flat_mae,patch,logistic,aabc_age,29,0.005994842503189409,train,0.6692913385826772,0.021336323136317795,0.6676283205873957,0.02170670346291994,0.6701897479616946,0.02123995766004647 +flat_mae,patch,logistic,aabc_age,29,0.005994842503189409,test,0.46153846153846156,0.05963670834518385,0.462280701754386,0.05804526330960632,0.46222527472527475,0.05997957851486729 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,train,0.6751968503937008,0.020971395509094264,0.6739846799175877,0.02127438047892122,0.6760705538475111,0.02094881161537496 +flat_mae,patch,logistic,aabc_age,30,0.005994842503189409,test,0.5576923076923077,0.06547929796155774,0.551237098572302,0.06698177378652825,0.5618131868131868,0.06578500412653013 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,train,0.468503937007874,0.020051980006069333,0.43563257517033016,0.020265153706970733,0.46721689563838137,0.019888640858174607 +flat_mae,patch,logistic,aabc_age,31,9.999999999999999e-05,test,0.5192307692307693,0.05624885271676803,0.45166666666666666,0.047708411402223476,0.5068681318681318,0.054819871130277656 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,train,0.6948818897637795,0.019977736926888017,0.6945601667431633,0.02024689769235351,0.696414169650683,0.019899644495376057 +flat_mae,patch,logistic,aabc_age,32,0.005994842503189409,test,0.5384615384615384,0.06019991350325028,0.5159855009001119,0.06525244000614479,0.5350274725274725,0.059794208237818364 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,train,0.6771653543307087,0.02023253742641148,0.6764712330137655,0.020554894237297158,0.6782366428904331,0.020181690330349045 +flat_mae,patch,logistic,aabc_age,33,0.005994842503189409,test,0.46153846153846156,0.06433795754502228,0.4433243727598566,0.06491286309222595,0.4565018315018315,0.06414462156419289 +flat_mae,patch,logistic,aabc_age,34,0.046415888336127774,train,0.8464566929133859,0.015365711510053184,0.8471793099075432,0.01542855353844026,0.8471990203092125,0.01536527513301707 +flat_mae,patch,logistic,aabc_age,34,0.046415888336127774,test,0.4807692307692308,0.0659747127458202,0.48653351895480834,0.06627739801619369,0.48489010989010983,0.06623381931324622 +flat_mae,patch,logistic,aabc_age,35,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,35,166.81005372000556,test,0.36538461538461536,0.0660398279505606,0.3735805257544388,0.06611384373746047,0.36469780219780223,0.06607662203149998 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,train,0.860236220472441,0.015183390779753747,0.8606736037523514,0.015151539864199535,0.8612943023347251,0.015112706997879291 +flat_mae,patch,logistic,aabc_age,36,0.046415888336127774,test,0.5192307692307693,0.06480890206586011,0.5082915360501568,0.06649929290163327,0.5217490842490843,0.06497987709697729 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,train,0.8484251968503937,0.0163257472588561,0.8492957075305123,0.016298527340867404,0.8490651893308068,0.016396810866168256 +flat_mae,patch,logistic,aabc_age,37,0.046415888336127774,test,0.5961538461538461,0.06616082253017885,0.5881410256410257,0.06813175108343256,0.5904304029304029,0.06669280121839809 +flat_mae,patch,logistic,aabc_age,38,0.046415888336127774,train,0.8641732283464567,0.01547554616112329,0.8642822641729047,0.015523152566202333,0.8645238967450406,0.015437285862135393 +flat_mae,patch,logistic,aabc_age,38,0.046415888336127774,test,0.5769230769230769,0.06892422517930867,0.585389998293224,0.06876876263623657,0.5769230769230769,0.06900252565059893 +flat_mae,patch,logistic,aabc_age,39,0.3593813663804626,train,0.9940944881889764,0.003536868603564316,0.9940901067702771,0.003552023700451002,0.9938516395627832,0.0036788374521238773 +flat_mae,patch,logistic,aabc_age,39,0.3593813663804626,test,0.4230769230769231,0.06889787485665515,0.4260869565217391,0.07019440276677814,0.4198717948717948,0.06895793071155557 +flat_mae,patch,logistic,aabc_age,40,0.046415888336127774,train,0.8582677165354331,0.015133470604718044,0.8582852720453575,0.015190355975315022,0.8589106454106243,0.015079306448759528 +flat_mae,patch,logistic,aabc_age,40,0.046415888336127774,test,0.5,0.06381259544383151,0.4883478590375142,0.06376568099077827,0.4993131868131868,0.06387822137423214 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,train,0.8582677165354331,0.01562104857345745,0.857866831851114,0.01575518250585895,0.8590282399513607,0.015610235059018136 +flat_mae,patch,logistic,aabc_age,41,0.046415888336127774,test,0.5769230769230769,0.06294385588826633,0.5712365591397849,0.06456814309425729,0.5737179487179487,0.0628581221369872 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,train,0.6988188976377953,0.019054778092886207,0.6969779715045316,0.019468421592421202,0.7003464543747567,0.01910523027423715 +flat_mae,patch,logistic,aabc_age,42,0.005994842503189409,test,0.4807692307692308,0.058135871764331666,0.455974025974026,0.06480297641189475,0.4816849816849817,0.05836362091152569 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,train,0.6909448818897638,0.020238801192712656,0.6890889798530486,0.02056436854673798,0.6923995327864608,0.02018680647044399 +flat_mae,patch,logistic,aabc_age,43,0.005994842503189409,test,0.5,0.06566527997414492,0.48374384236453205,0.07066486877196798,0.49404761904761907,0.06587970403446247 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,train,0.6830708661417323,0.020257118716681233,0.6824218064153075,0.02016260516352572,0.6840674621060283,0.02023752902747347 +flat_mae,patch,logistic,aabc_age,44,0.005994842503189409,test,0.4807692307692308,0.07068426128141547,0.47858293075684377,0.071275607735733,0.4775641025641026,0.07096995889963467 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,train,0.6535433070866141,0.019132106381028448,0.6513305733166198,0.01969115314214864,0.6546134460067243,0.019138536295434445 +flat_mae,patch,logistic,aabc_age,45,0.005994842503189409,test,0.5192307692307693,0.06504185043256616,0.5263090371786023,0.06427446885691739,0.5249542124542124,0.0651905290656538 +flat_mae,patch,logistic,aabc_age,46,0.005994842503189409,train,0.6811023622047244,0.019608218607626588,0.6802222922375166,0.019849536250151137,0.6818337651925913,0.019543796964727883 +flat_mae,patch,logistic,aabc_age,46,0.005994842503189409,test,0.5576923076923077,0.06708869868408733,0.5583501683501684,0.06842010574827573,0.5620421245421245,0.06711164475137846 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,train,0.687007874015748,0.019774920394149575,0.6855655336585478,0.02002251905644776,0.6888523971545237,0.01969547172507269 +flat_mae,patch,logistic,aabc_age,47,0.005994842503189409,test,0.4423076923076923,0.06598452167434204,0.4371223479169506,0.06737023054887963,0.44024725274725274,0.06577044354148308 +flat_mae,patch,logistic,aabc_age,48,0.046415888336127774,train,0.8720472440944882,0.015442295973365145,0.8718789884959492,0.015552659835425323,0.8715005734681782,0.015488575275649496 +flat_mae,patch,logistic,aabc_age,48,0.046415888336127774,test,0.4230769230769231,0.06053147257086708,0.4285667293233083,0.0617109825466733,0.4253663003663004,0.06103043258939648 +flat_mae,patch,logistic,aabc_age,49,0.005994842503189409,train,0.6929133858267716,0.019392539870816426,0.6908801886044706,0.019899234428032576,0.6934454169535607,0.019379636450563217 +flat_mae,patch,logistic,aabc_age,49,0.005994842503189409,test,0.40384615384615385,0.05927191378143285,0.40440476190476193,0.05949890383364228,0.40773809523809523,0.05996839378928168 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,train,0.8720472440944882,0.014218473277042237,0.8722755709470685,0.014250247012995893,0.8727883595549579,0.014158842484140184 +flat_mae,patch,logistic,aabc_age,50,0.046415888336127774,test,0.4230769230769231,0.07197895813500765,0.4281343656343657,0.07205928416462981,0.4228479853479854,0.07178629787303666 +flat_mae,patch,logistic,aabc_age,51,0.046415888336127774,train,0.8503937007874016,0.016338950285210898,0.8502731145834593,0.01646593271614384,0.8515164541254228,0.016204273343789752 +flat_mae,patch,logistic,aabc_age,51,0.046415888336127774,test,0.5,0.06554757971962498,0.49702380952380953,0.06671357069508094,0.5011446886446886,0.06578705163679525 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,train,0.8720472440944882,0.014842571899906055,0.8724812323485371,0.014845414245963586,0.8727383728847368,0.014765889012996962 +flat_mae,patch,logistic,aabc_age,52,0.046415888336127774,test,0.4230769230769231,0.06830200729981097,0.43774323786600927,0.06773483543808248,0.42582417582417587,0.06846260703750402 +flat_mae,patch,logistic,aabc_age,53,0.005994842503189409,train,0.6889763779527559,0.019293096497118974,0.6880067325989833,0.019530999800025987,0.6906009716353816,0.019277649167917753 +flat_mae,patch,logistic,aabc_age,53,0.005994842503189409,test,0.5384615384615384,0.0659367973335341,0.5301383801383801,0.06772021048739683,0.538003663003663,0.06604214926979456 +flat_mae,patch,logistic,aabc_age,54,0.005994842503189409,train,0.6850393700787402,0.020341502453197595,0.6829945917852012,0.020802954974879703,0.6864187535602017,0.02030795356266952 +flat_mae,patch,logistic,aabc_age,54,0.005994842503189409,test,0.4423076923076923,0.06348455293643063,0.428125339415662,0.06600058492062282,0.44184981684981683,0.06375715168881134 +flat_mae,patch,logistic,aabc_age,55,0.046415888336127774,train,0.8622047244094488,0.015142156074013402,0.8620043639333924,0.015228447845520594,0.8631604713563193,0.01508597231713336 +flat_mae,patch,logistic,aabc_age,55,0.046415888336127774,test,0.5961538461538461,0.06521584553523584,0.5821548821548821,0.06879524307566008,0.5972985347985348,0.06541360153577697 +flat_mae,patch,logistic,aabc_age,56,0.005994842503189409,train,0.6811023622047244,0.020320879013375565,0.6800055628751281,0.020469339971706135,0.6828040100577496,0.02029840381680249 +flat_mae,patch,logistic,aabc_age,56,0.005994842503189409,test,0.5192307692307693,0.06050228613216971,0.5042058516196447,0.06270173279740318,0.5157967032967032,0.060250288434124215 +flat_mae,patch,logistic,aabc_age,57,0.3593813663804626,train,0.9980314960629921,0.0019756523748890135,0.99795904766665,0.002048256277794706,0.997983870967742,0.00202345041621698 +flat_mae,patch,logistic,aabc_age,57,0.3593813663804626,test,0.4807692307692308,0.06626344900890847,0.48270655270655266,0.06383094540649432,0.48626373626373626,0.06705277500600391 +flat_mae,patch,logistic,aabc_age,58,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,58,0.3593813663804626,test,0.4423076923076923,0.05529719329042675,0.42794612794612796,0.057457578607542796,0.4475732600732601,0.056224622637874394 +flat_mae,patch,logistic,aabc_age,59,0.005994842503189409,train,0.7066929133858267,0.01940528576522983,0.7039085308539799,0.019871763357471428,0.7078758614009886,0.01930618565465022 +flat_mae,patch,logistic,aabc_age,59,0.005994842503189409,test,0.5192307692307693,0.06851634582324435,0.5198362357282897,0.06825223595985025,0.5190018315018315,0.06846604697768587 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,train,0.6811023622047244,0.020794515306294913,0.6778129567780221,0.02108507945326142,0.68320678035018,0.020647193119707186 +flat_mae,patch,logistic,aabc_age,60,0.005994842503189409,test,0.4230769230769231,0.05916574852747634,0.4150574712643678,0.06292739651861656,0.4253663003663004,0.05974491000733991 +flat_mae,patch,logistic,aabc_age,61,0.005994842503189409,train,0.6850393700787402,0.01997295586131235,0.6846474916233403,0.020237788793165155,0.6872037960141084,0.01995403865692548 +flat_mae,patch,logistic,aabc_age,61,0.005994842503189409,test,0.4230769230769231,0.06828408289148621,0.4297727272727273,0.06719724710562539,0.42101648351648346,0.06828875333972878 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,train,0.6594488188976378,0.02013713293913129,0.6557035798767992,0.020716212527444895,0.6605118730928347,0.02009979021124881 +flat_mae,patch,logistic,aabc_age,62,0.005994842503189409,test,0.46153846153846156,0.06719458628517258,0.4605519480519481,0.06800512714172513,0.45970695970695963,0.06728733382243106 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,train,0.7047244094488189,0.018952892890645952,0.7023112049805594,0.019447872006563543,0.7051570420549723,0.018986316408031074 +flat_mae,patch,logistic,aabc_age,63,0.005994842503189409,test,0.4423076923076923,0.054880181482267594,0.4065199506375977,0.057385444575812135,0.44276556776556775,0.055156601173926116 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,train,0.860236220472441,0.014941809027534586,0.8604135643624837,0.01496995605788504,0.8604416520103033,0.014960542836090853 +flat_mae,patch,logistic,aabc_age,64,0.046415888336127774,test,0.36538461538461536,0.06747250152127503,0.3734739772970658,0.06629045237532968,0.36332417582417587,0.06735908627399896 +flat_mae,patch,logistic,aabc_age,65,0.005994842503189409,train,0.687007874015748,0.01891448191241969,0.6848057787019648,0.019188112758283204,0.6875146243975228,0.01884246501696604 +flat_mae,patch,logistic,aabc_age,65,0.005994842503189409,test,0.5576923076923077,0.06276747499429751,0.5396198830409357,0.06772983371905472,0.5473901098901099,0.06286918503388973 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,train,0.8661417322834646,0.014131952144843347,0.8665105839572754,0.014156164201503708,0.8668575669989202,0.014086665784475424 +flat_mae,patch,logistic,aabc_age,66,0.046415888336127774,test,0.40384615384615385,0.0661057069929777,0.4064916564916565,0.06632904046272096,0.4033882783882784,0.0662533216814986 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,train,0.8681102362204725,0.014805086047745393,0.8677386595990809,0.014934413328335767,0.8685061681393356,0.014777323768210652 +flat_mae,patch,logistic,aabc_age,67,0.046415888336127774,test,0.6153846153846154,0.062008720039577865,0.6123876123876124,0.0632402360423215,0.6197344322344323,0.061800994719126416 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,train,0.8661417322834646,0.014497555599418697,0.8661973623522775,0.014573619054218766,0.8672427160910567,0.014430241579265623 +flat_mae,patch,logistic,aabc_age,68,0.046415888336127774,test,0.5192307692307693,0.061565799216253936,0.516559829059829,0.06240185046260703,0.5217490842490843,0.06195351774406811 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,train,0.8661417322834646,0.015047717928896375,0.8653893445729334,0.015333136258828943,0.8661225112152348,0.01512791524657173 +flat_mae,patch,logistic,aabc_age,69,0.046415888336127774,test,0.4807692307692308,0.07050343061022385,0.4842857142857142,0.07085186182702514,0.47619047619047616,0.0704721458967132 +flat_mae,patch,logistic,aabc_age,70,0.005994842503189409,train,0.6830708661417323,0.02001145550470286,0.6803267413481353,0.02044976351893998,0.6845702057389013,0.019917477260692484 +flat_mae,patch,logistic,aabc_age,70,0.005994842503189409,test,0.46153846153846156,0.06820392325906915,0.46166666666666667,0.06900382103124536,0.46153846153846156,0.06855971635919461 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,train,0.6929133858267716,0.02070298116762072,0.6921291883657881,0.02079306387766873,0.69419809393754,0.020613159987941398 +flat_mae,patch,logistic,aabc_age,71,0.005994842503189409,test,0.46153846153846156,0.06871038395981591,0.45980861244019133,0.07178409201756873,0.4597069597069597,0.06889318186234422 +flat_mae,patch,logistic,aabc_age,72,0.005994842503189409,train,0.687007874015748,0.020515126230194348,0.6864538448491914,0.020705843002749674,0.6888024104843025,0.02044194713581786 +flat_mae,patch,logistic,aabc_age,72,0.005994842503189409,test,0.6346153846153846,0.06418043859483084,0.6316049087788218,0.06513472506821406,0.6332417582417582,0.06438767097205852 +flat_mae,patch,logistic,aabc_age,73,0.005994842503189409,train,0.6988188976377953,0.02027620211599658,0.6971942043720148,0.02070890928144876,0.7001288864935777,0.02025139339037098 +flat_mae,patch,logistic,aabc_age,73,0.005994842503189409,test,0.5384615384615384,0.06062299835041222,0.5331798386521025,0.061233260736975714,0.5366300366300366,0.06071819736921237 +flat_mae,patch,logistic,aabc_age,74,0.000774263682681127,train,0.5374015748031497,0.021365991926686256,0.5283627713248544,0.021845955893075766,0.5387635239715451,0.021340873353670638 +flat_mae,patch,logistic,aabc_age,74,0.000774263682681127,test,0.5384615384615384,0.06263299459417791,0.5030922326855005,0.0692137329608067,0.5293040293040293,0.062294166898528895 +flat_mae,patch,logistic,aabc_age,75,0.000774263682681127,train,0.5610236220472441,0.01938063016822856,0.5511206647512998,0.02012209405804377,0.5619692062931899,0.0194147276677089 +flat_mae,patch,logistic,aabc_age,75,0.000774263682681127,test,0.5,0.0660326595721959,0.48729283380018673,0.06980579435256785,0.4965659340659341,0.06571696585174513 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,train,0.84251968503937,0.016060098936605472,0.8423433092696717,0.016180770895387987,0.8443721961913274,0.015973014122325054 +flat_mae,patch,logistic,aabc_age,76,0.046415888336127774,test,0.5384615384615384,0.0638023366788433,0.5318588416414504,0.06469857359975405,0.5366300366300366,0.0637735392448262 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,train,0.8503937007874016,0.016245132141925994,0.8503656322054065,0.016452633596631492,0.8514488462549077,0.016243273552787128 +flat_mae,patch,logistic,aabc_age,77,0.046415888336127774,test,0.38461538461538464,0.06618402710463442,0.390937019969278,0.0642480122873931,0.38827838827838823,0.06678068012009104 +flat_mae,patch,logistic,aabc_age,78,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,78,21.54434690031882,test,0.5576923076923077,0.06742139846083142,0.5645398351648352,0.0671393435276521,0.5576923076923077,0.06752191446435851 +flat_mae,patch,logistic,aabc_age,79,0.005994842503189409,train,0.6850393700787402,0.021024319122006987,0.6833113275433578,0.02143535897384695,0.6865187269006442,0.020962750694176177 +flat_mae,patch,logistic,aabc_age,79,0.005994842503189409,test,0.5,0.06715428671985185,0.49440993788819876,0.06922768334147779,0.49977106227106227,0.06719374569066505 +flat_mae,patch,logistic,aabc_age,80,0.046415888336127774,train,0.8622047244094488,0.015335883831024077,0.8623008712294945,0.015437812320046176,0.8633780392374983,0.015256408190066092 +flat_mae,patch,logistic,aabc_age,80,0.046415888336127774,test,0.46153846153846156,0.0538200348740704,0.43299396681749625,0.05380161895283701,0.4665750915750916,0.054762445182443734 +flat_mae,patch,logistic,aabc_age,81,0.3593813663804626,train,0.9960629921259843,0.0027859554057979856,0.9959182993469279,0.0028885203596981835,0.9959677419354839,0.0028533575527124695 +flat_mae,patch,logistic,aabc_age,81,0.3593813663804626,test,0.4807692307692308,0.06740299845840267,0.48543362008835156,0.06774184513187578,0.47779304029304026,0.0674313034467835 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,train,0.6909448818897638,0.01986758041235778,0.6879495414814659,0.020323390246426102,0.6921495994353544,0.019746748377291037 +flat_mae,patch,logistic,aabc_age,82,0.005994842503189409,test,0.5384615384615384,0.06717163170944171,0.5299137807027008,0.06997967761028621,0.5396062271062271,0.06738857930314839 +flat_mae,patch,logistic,aabc_age,83,0.3593813663804626,train,0.9960629921259843,0.002752911759763884,0.9960256812008625,0.00278294517388241,0.9959177552652626,0.0028539588597345884 +flat_mae,patch,logistic,aabc_age,83,0.3593813663804626,test,0.5,0.06655890081804618,0.5045787545787546,0.06538493333500774,0.5041208791208791,0.06664849561662124 +flat_mae,patch,logistic,aabc_age,84,0.046415888336127774,train,0.8562992125984252,0.015574548376537743,0.8569671673418803,0.01552824333898337,0.857262044270209,0.015421800114352706 +flat_mae,patch,logistic,aabc_age,84,0.046415888336127774,test,0.5384615384615384,0.060135497890255095,0.5240777541424093,0.06227517261195627,0.5309065934065934,0.060196429981947845 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,train,0.8641732283464567,0.01530745671679205,0.8642982338745914,0.015435772584766866,0.8649090458371773,0.015261484343959688 +flat_mae,patch,logistic,aabc_age,85,0.046415888336127774,test,0.5,0.062356237024518944,0.4860837438423645,0.0639203116637364,0.4965659340659341,0.06204328977184569 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,train,0.860236220472441,0.015086034706870003,0.8604357759615218,0.015151632787392252,0.8607591932319247,0.015101629473131541 +flat_mae,patch,logistic,aabc_age,86,0.046415888336127774,test,0.5576923076923077,0.06467281101983352,0.548015873015873,0.06951547090264605,0.5558608058608059,0.06460518916951155 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,train,0.6791338582677166,0.0189888301680578,0.6767677216349324,0.019337903829513503,0.679350134928048,0.018874946548941868 +flat_mae,patch,logistic,aabc_age,87,0.005994842503189409,test,0.6153846153846154,0.06528103786954864,0.623076923076923,0.06445946964668103,0.6169871794871795,0.06563280171808179 +flat_mae,patch,logistic,aabc_age,88,0.046415888336127774,train,0.8464566929133859,0.014932318840297122,0.8462132621274885,0.014995824447776938,0.8463963566550119,0.014907787873885664 +flat_mae,patch,logistic,aabc_age,88,0.046415888336127774,test,0.5384615384615384,0.0634508032878215,0.5384392419175028,0.06401219097548588,0.5368589743589743,0.06369213432322278 +flat_mae,patch,logistic,aabc_age,89,0.046415888336127774,train,0.8523622047244095,0.01548363632955735,0.8529284509581991,0.01552369816791747,0.8537825165087871,0.015368827954671925 +flat_mae,patch,logistic,aabc_age,89,0.046415888336127774,test,0.46153846153846156,0.06886123599301139,0.4629895064677673,0.06896651041256796,0.4640567765567766,0.0690575949048827 +flat_mae,patch,logistic,aabc_age,90,0.046415888336127774,train,0.8582677165354331,0.01483817424223175,0.8577884212771327,0.014963233604303126,0.8588106720701818,0.01483266779961466 +flat_mae,patch,logistic,aabc_age,90,0.046415888336127774,test,0.5192307692307693,0.05642038953277073,0.4972691585594812,0.058799261639715196,0.5185439560439561,0.056435595632769384 +flat_mae,patch,logistic,aabc_age,91,0.3593813663804626,train,0.9921259842519685,0.003905136745388815,0.9920867443145884,0.00391702296415853,0.9921030650819254,0.003913474136034504 +flat_mae,patch,logistic,aabc_age,91,0.3593813663804626,test,0.4807692307692308,0.06235662845621174,0.4751835193514354,0.0638647399594111,0.48489010989010994,0.06254024488035001 +flat_mae,patch,logistic,aabc_age,92,0.005994842503189409,train,0.7007874015748031,0.019616802597209573,0.6991040363433145,0.019992775141362967,0.702412570077236,0.01954732810865538 +flat_mae,patch,logistic,aabc_age,92,0.005994842503189409,test,0.5576923076923077,0.06199403483424502,0.546875,0.06601499700457646,0.5588369963369964,0.06215811292066658 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,train,0.8740157480314961,0.01527715056162824,0.8748864497541222,0.015237276515469628,0.8750220564683949,0.015203300009910487 +flat_mae,patch,logistic,aabc_age,93,0.046415888336127774,test,0.46153846153846156,0.06395454191808947,0.44726081403742574,0.06425092641923034,0.4608516483516484,0.06390318564525278 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,train,0.562992125984252,0.020464593817107635,0.5543031715085309,0.021070718821512895,0.5629474825897747,0.020328120600102313 +flat_mae,patch,logistic,aabc_age,94,0.000774263682681127,test,0.5384615384615384,0.06453635276650181,0.5289045923688279,0.0662834468966552,0.5425824175824175,0.06487913607959161 +flat_mae,patch,logistic,aabc_age,95,0.005994842503189409,train,0.6968503937007874,0.020491917976055936,0.6960027333606669,0.020898288848247175,0.6996680980994997,0.020370503910451383 +flat_mae,patch,logistic,aabc_age,95,0.005994842503189409,test,0.4807692307692308,0.06113535037184916,0.44457257372445,0.05889394588366362,0.47275641025641024,0.06016005777303756 +flat_mae,patch,logistic,aabc_age,96,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,96,166.81005372000556,test,0.4807692307692308,0.07083437637009057,0.4829032258064516,0.06991098298687316,0.4775641025641026,0.07081038833995275 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,train,0.6791338582677166,0.020135434471881715,0.6769136243522962,0.020605754227487737,0.6797852706904058,0.020267551049499778 +flat_mae,patch,logistic,aabc_age,97,0.005994842503189409,test,0.4230769230769231,0.061328294964996456,0.420455681250284,0.06120184324781853,0.4223901098901099,0.06127065101631762 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,train,0.8562992125984252,0.0158621182448496,0.857149067294025,0.015849156822607055,0.8579147479137458,0.015688028160802007 +flat_mae,patch,logistic,aabc_age,98,0.046415888336127774,test,0.5192307692307693,0.06583863858982009,0.5123677248677249,0.06759852492998088,0.5203754578754579,0.06630547663069584 +flat_mae,patch,logistic,aabc_age,99,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_age,99,2.782559402207126,test,0.38461538461538464,0.06448127107561255,0.38255693581780537,0.06315006323450753,0.3853021978021979,0.06476403382188932 +flat_mae,patch,logistic,aabc_age,100,0.046415888336127774,train,0.8641732283464567,0.015538417467195123,0.8644080233903848,0.015630745867176287,0.8644739100748193,0.015532348242812508 +flat_mae,patch,logistic,aabc_age,100,0.046415888336127774,test,0.4423076923076923,0.06247276329606491,0.4409460654288241,0.06204145251566039,0.4432234432234432,0.06279700640292792 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7a10c3f183b64d7bcb11334a2048076900d94189 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:48:57 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_age patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_age__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:22:19 time: 5.8772 data: 4.8325 max mem: 3207 +extract (train) [ 20/228] eta: 0:01:53 time: 0.2766 data: 0.1036 max mem: 3395 +extract (train) [ 40/228] eta: 0:01:13 time: 0.2324 data: 0.0809 max mem: 3395 +extract (train) [ 60/228] eta: 0:00:57 time: 0.2327 data: 0.0814 max mem: 3395 +extract (train) [ 80/228] eta: 0:00:46 time: 0.2417 data: 0.0855 max mem: 3395 +extract (train) [100/228] eta: 0:00:38 time: 0.2405 data: 0.0854 max mem: 3395 +extract (train) [120/228] eta: 0:00:31 time: 0.2408 data: 0.0855 max mem: 3395 +extract (train) [140/228] eta: 0:00:24 time: 0.2334 data: 0.0805 max mem: 3395 +extract (train) [160/228] eta: 0:00:18 time: 0.2406 data: 0.0846 max mem: 3395 +extract (train) [180/228] eta: 0:00:13 time: 0.2559 data: 0.0972 max mem: 3395 +extract (train) [200/228] eta: 0:00:07 time: 0.2544 data: 0.0943 max mem: 3395 +extract (train) [220/228] eta: 0:00:02 time: 0.1977 data: 0.0632 max mem: 3395 +extract (train) [227/228] eta: 0:00:00 time: 0.1927 data: 0.0625 max mem: 3395 +extract (train) Total time: 0:01:00 (0.2663 s / it) +extract (validation) [ 0/27] eta: 0:02:22 time: 5.2676 data: 5.0934 max mem: 3395 +extract (validation) [20/27] eta: 0:00:03 time: 0.2411 data: 0.0855 max mem: 3395 +extract (validation) [26/27] eta: 0:00:00 time: 0.2019 data: 0.0666 max mem: 3395 +extract (validation) Total time: 0:00:11 (0.4323 s / it) +extract (test) [ 0/26] eta: 0:02:09 time: 4.9658 data: 4.8259 max mem: 3395 +extract (test) [20/26] eta: 0:00:02 time: 0.1993 data: 0.0664 max mem: 3395 +extract (test) [25/26] eta: 0:00:00 time: 0.2028 data: 0.0693 max mem: 3395 +extract (test) Total time: 0:00:10 (0.3962 s / it) +feature extraction time: 0:01:22 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | train | 0.69094 | 0.020763 | 0.69077 | 0.0209 | 0.69255 | 0.02068 | +| flat_mae | patch | logistic | aabc_age | | 0.0059948 | test | 0.42308 | 0.065906 | 0.40371 | 0.068084 | 0.41415 | 0.0656 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05639950218001792, "f1": 0.41239316239316237, "f1_std": 0.05436409633709529, "bacc": 0.4384157509157509, "bacc_std": 0.05567966292079005} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.05775661800241529, "f1": 0.48668981481481477, "f1_std": 0.05814183411080539, "bacc": 0.5290750915750916, "bacc_std": 0.05668041956763944} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.061622346672838224, "f1": 0.5105596872616323, "f1_std": 0.06704800119865006, "bacc": 0.5364010989010989, "bacc_std": 0.06150449099442846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.0684247524333273, "f1": 0.5040692640692641, "f1_std": 0.06926628446379131, "bacc": 0.5059523809523809, "bacc_std": 0.06836869825039218} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06756636010435577, "f1": 0.4786324786324786, "f1_std": 0.0661093383225889, "bacc": 0.4816849816849817, "bacc_std": 0.06786103385897078} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0689482590500696, "f1": 0.4864021164021164, "f1_std": 0.06794342502268319, "bacc": 0.4835164835164835, "bacc_std": 0.06905267364370371} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06227372055842937, "f1": 0.506237322515213, "f1_std": 0.06520498816089634, "bacc": 0.532051282051282, "bacc_std": 0.06195571716329027} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 0.005994842503189409, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.0544544758567044, "f1": 0.56426267281106, "f1_std": 0.05689714846677295, "bacc": 0.6062271062271063, "bacc_std": 0.0552631218048549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06299313149371617, "f1": 0.5644450883801797, "f1_std": 0.06934074177484975, "bacc": 0.575091575091575, "bacc_std": 0.06334943604915923} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.062125517154039085, "f1": 0.4709891557717645, "f1_std": 0.0647405205774203, "bacc": 0.48031135531135527, "bacc_std": 0.06203143684892928} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06764570073849754, "f1": 0.5788461538461538, "f1_std": 0.06804346814862999, "bacc": 0.5755494505494505, "bacc_std": 0.06789688615317782} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06436623209664775, "f1": 0.486043956043956, "f1_std": 0.0631173860656559, "bacc": 0.48649267399267404, "bacc_std": 0.0649968654708216} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0668999075719548, "f1": 0.46705508662030404, "f1_std": 0.06417401843311422, "bacc": 0.46543040293040294, "bacc_std": 0.06742120304890836} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.005994842503189409, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06498743620043282, "f1": 0.5892180824269109, "f1_std": 0.06880636437949011, "bacc": 0.5959249084249084, "bacc_std": 0.06511275234173927} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06315829647956936, "f1": 0.4678713527851459, "f1_std": 0.06194251533017741, "bacc": 0.4597069597069597, "bacc_std": 0.06329806029961517} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06712140153765189, "f1": 0.4226190476190476, "f1_std": 0.06939709107622663, "bacc": 0.41964285714285715, "bacc_std": 0.06700304467369642} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06529055451499657, "f1": 0.5335724994645534, "f1_std": 0.06670212663077621, "bacc": 0.5382326007326007, "bacc_std": 0.06512887868192521} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06636455709088868, "f1": 0.49119584438549957, "f1_std": 0.06799515855244659, "bacc": 0.502518315018315, "bacc_std": 0.0664501772174689} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06723120929269813, "f1": 0.5755494505494505, "f1_std": 0.06780044458458498, "bacc": 0.5771520146520146, "bacc_std": 0.06709150664989616} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06257535102748539, "f1": 0.5354417293233082, "f1_std": 0.06489870391041111, "bacc": 0.5366300366300366, "bacc_std": 0.0627358407390661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.058200060493268556, "f1": 0.3547427035330261, "f1_std": 0.0576444117850116, "bacc": 0.36881868131868134, "bacc_std": 0.0590071627331715} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06676616219464156, "f1": 0.4439153439153439, "f1_std": 0.06715179872228669, "bacc": 0.4439102564102565, "bacc_std": 0.06687174144178824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06450659339723325, "f1": 0.5026540616246498, "f1_std": 0.06523204647569442, "bacc": 0.5171703296703296, "bacc_std": 0.06425776429879188} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06178483134730874, "f1": 0.38470187982931614, "f1_std": 0.06086732862010043, "bacc": 0.3825549450549451, "bacc_std": 0.06161444609250516} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.0645184598142635, "f1": 0.5143870372506055, "f1_std": 0.06604555179013286, "bacc": 0.521978021978022, "bacc_std": 0.06459518165432901} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06586577484443638, "f1": 0.46314102564102566, "f1_std": 0.06626812904535904, "bacc": 0.46726190476190477, "bacc_std": 0.06597669329456253} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06264339762714176, "f1": 0.38983627933932197, "f1_std": 0.06324771084643517, "bacc": 0.40041208791208793, "bacc_std": 0.062080165128487554} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.0695210155106579, "f1": 0.4998357963875205, "f1_std": 0.07005433430211298, "bacc": 0.4981684981684982, "bacc_std": 0.06953988285019243} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05963670834518385, "f1": 0.462280701754386, "f1_std": 0.05804526330960632, "bacc": 0.46222527472527475, "bacc_std": 0.05997957851486729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06547929796155774, "f1": 0.551237098572302, "f1_std": 0.06698177378652825, "bacc": 0.5618131868131868, "bacc_std": 0.06578500412653013} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05624885271676803, "f1": 0.45166666666666666, "f1_std": 0.047708411402223476, "bacc": 0.5068681318681318, "bacc_std": 0.054819871130277656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06019991350325028, "f1": 0.5159855009001119, "f1_std": 0.06525244000614479, "bacc": 0.5350274725274725, "bacc_std": 0.059794208237818364} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06433795754502228, "f1": 0.4433243727598566, "f1_std": 0.06491286309222595, "bacc": 0.4565018315018315, "bacc_std": 0.06414462156419289} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0659747127458202, "f1": 0.48653351895480834, "f1_std": 0.06627739801619369, "bacc": 0.48489010989010983, "bacc_std": 0.06623381931324622} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 166.81005372000556, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.0660398279505606, "f1": 0.3735805257544388, "f1_std": 0.06611384373746047, "bacc": 0.36469780219780223, "bacc_std": 0.06607662203149998} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06480890206586011, "f1": 0.5082915360501568, "f1_std": 0.06649929290163327, "bacc": 0.5217490842490843, "bacc_std": 0.06497987709697729} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06616082253017885, "f1": 0.5881410256410257, "f1_std": 0.06813175108343256, "bacc": 0.5904304029304029, "bacc_std": 0.06669280121839809} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06892422517930867, "f1": 0.585389998293224, "f1_std": 0.06876876263623657, "bacc": 0.5769230769230769, "bacc_std": 0.06900252565059893} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06889787485665515, "f1": 0.4260869565217391, "f1_std": 0.07019440276677814, "bacc": 0.4198717948717948, "bacc_std": 0.06895793071155557} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06381259544383151, "f1": 0.4883478590375142, "f1_std": 0.06376568099077827, "bacc": 0.4993131868131868, "bacc_std": 0.06387822137423214} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06294385588826633, "f1": 0.5712365591397849, "f1_std": 0.06456814309425729, "bacc": 0.5737179487179487, "bacc_std": 0.0628581221369872} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.058135871764331666, "f1": 0.455974025974026, "f1_std": 0.06480297641189475, "bacc": 0.4816849816849817, "bacc_std": 0.05836362091152569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06566527997414492, "f1": 0.48374384236453205, "f1_std": 0.07066486877196798, "bacc": 0.49404761904761907, "bacc_std": 0.06587970403446247} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07068426128141547, "f1": 0.47858293075684377, "f1_std": 0.071275607735733, "bacc": 0.4775641025641026, "bacc_std": 0.07096995889963467} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06504185043256616, "f1": 0.5263090371786023, "f1_std": 0.06427446885691739, "bacc": 0.5249542124542124, "bacc_std": 0.0651905290656538} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06708869868408733, "f1": 0.5583501683501684, "f1_std": 0.06842010574827573, "bacc": 0.5620421245421245, "bacc_std": 0.06711164475137846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06598452167434204, "f1": 0.4371223479169506, "f1_std": 0.06737023054887963, "bacc": 0.44024725274725274, "bacc_std": 0.06577044354148308} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06053147257086708, "f1": 0.4285667293233083, "f1_std": 0.0617109825466733, "bacc": 0.4253663003663004, "bacc_std": 0.06103043258939648} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.05927191378143285, "f1": 0.40440476190476193, "f1_std": 0.05949890383364228, "bacc": 0.40773809523809523, "bacc_std": 0.05996839378928168} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.07197895813500765, "f1": 0.4281343656343657, "f1_std": 0.07205928416462981, "bacc": 0.4228479853479854, "bacc_std": 0.07178629787303666} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06554757971962498, "f1": 0.49702380952380953, "f1_std": 0.06671357069508094, "bacc": 0.5011446886446886, "bacc_std": 0.06578705163679525} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06830200729981097, "f1": 0.43774323786600927, "f1_std": 0.06773483543808248, "bacc": 0.42582417582417587, "bacc_std": 0.06846260703750402} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0659367973335341, "f1": 0.5301383801383801, "f1_std": 0.06772021048739683, "bacc": 0.538003663003663, "bacc_std": 0.06604214926979456} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06348455293643063, "f1": 0.428125339415662, "f1_std": 0.06600058492062282, "bacc": 0.44184981684981683, "bacc_std": 0.06375715168881134} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06521584553523584, "f1": 0.5821548821548821, "f1_std": 0.06879524307566008, "bacc": 0.5972985347985348, "bacc_std": 0.06541360153577697} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06050228613216971, "f1": 0.5042058516196447, "f1_std": 0.06270173279740318, "bacc": 0.5157967032967032, "bacc_std": 0.060250288434124215} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06626344900890847, "f1": 0.48270655270655266, "f1_std": 0.06383094540649432, "bacc": 0.48626373626373626, "bacc_std": 0.06705277500600391} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.05529719329042675, "f1": 0.42794612794612796, "f1_std": 0.057457578607542796, "bacc": 0.4475732600732601, "bacc_std": 0.056224622637874394} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06851634582324435, "f1": 0.5198362357282897, "f1_std": 0.06825223595985025, "bacc": 0.5190018315018315, "bacc_std": 0.06846604697768587} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05916574852747634, "f1": 0.4150574712643678, "f1_std": 0.06292739651861656, "bacc": 0.4253663003663004, "bacc_std": 0.05974491000733991} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06828408289148621, "f1": 0.4297727272727273, "f1_std": 0.06719724710562539, "bacc": 0.42101648351648346, "bacc_std": 0.06828875333972878} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06719458628517258, "f1": 0.4605519480519481, "f1_std": 0.06800512714172513, "bacc": 0.45970695970695963, "bacc_std": 0.06728733382243106} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.054880181482267594, "f1": 0.4065199506375977, "f1_std": 0.057385444575812135, "bacc": 0.44276556776556775, "bacc_std": 0.055156601173926116} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.06747250152127503, "f1": 0.3734739772970658, "f1_std": 0.06629045237532968, "bacc": 0.36332417582417587, "bacc_std": 0.06735908627399896} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06276747499429751, "f1": 0.5396198830409357, "f1_std": 0.06772983371905472, "bacc": 0.5473901098901099, "bacc_std": 0.06286918503388973} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0661057069929777, "f1": 0.4064916564916565, "f1_std": 0.06632904046272096, "bacc": 0.4033882783882784, "bacc_std": 0.0662533216814986} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.062008720039577865, "f1": 0.6123876123876124, "f1_std": 0.0632402360423215, "bacc": 0.6197344322344323, "bacc_std": 0.061800994719126416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.061565799216253936, "f1": 0.516559829059829, "f1_std": 0.06240185046260703, "bacc": 0.5217490842490843, "bacc_std": 0.06195351774406811} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07050343061022385, "f1": 0.4842857142857142, "f1_std": 0.07085186182702514, "bacc": 0.47619047619047616, "bacc_std": 0.0704721458967132} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06820392325906915, "f1": 0.46166666666666667, "f1_std": 0.06900382103124536, "bacc": 0.46153846153846156, "bacc_std": 0.06855971635919461} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06871038395981591, "f1": 0.45980861244019133, "f1_std": 0.07178409201756873, "bacc": 0.4597069597069597, "bacc_std": 0.06889318186234422} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.6346153846153846, "acc_std": 0.06418043859483084, "f1": 0.6316049087788218, "f1_std": 0.06513472506821406, "bacc": 0.6332417582417582, "bacc_std": 0.06438767097205852} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06062299835041222, "f1": 0.5331798386521025, "f1_std": 0.061233260736975714, "bacc": 0.5366300366300366, "bacc_std": 0.06071819736921237} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06263299459417791, "f1": 0.5030922326855005, "f1_std": 0.0692137329608067, "bacc": 0.5293040293040293, "bacc_std": 0.062294166898528895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.0660326595721959, "f1": 0.48729283380018673, "f1_std": 0.06980579435256785, "bacc": 0.4965659340659341, "bacc_std": 0.06571696585174513} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0638023366788433, "f1": 0.5318588416414504, "f1_std": 0.06469857359975405, "bacc": 0.5366300366300366, "bacc_std": 0.0637735392448262} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06618402710463442, "f1": 0.390937019969278, "f1_std": 0.0642480122873931, "bacc": 0.38827838827838823, "bacc_std": 0.06678068012009104} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 21.54434690031882, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06742139846083142, "f1": 0.5645398351648352, "f1_std": 0.0671393435276521, "bacc": 0.5576923076923077, "bacc_std": 0.06752191446435851} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06715428671985185, "f1": 0.49440993788819876, "f1_std": 0.06922768334147779, "bacc": 0.49977106227106227, "bacc_std": 0.06719374569066505} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.0538200348740704, "f1": 0.43299396681749625, "f1_std": 0.05380161895283701, "bacc": 0.4665750915750916, "bacc_std": 0.054762445182443734} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06740299845840267, "f1": 0.48543362008835156, "f1_std": 0.06774184513187578, "bacc": 0.47779304029304026, "bacc_std": 0.0674313034467835} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06717163170944171, "f1": 0.5299137807027008, "f1_std": 0.06997967761028621, "bacc": 0.5396062271062271, "bacc_std": 0.06738857930314839} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.06655890081804618, "f1": 0.5045787545787546, "f1_std": 0.06538493333500774, "bacc": 0.5041208791208791, "bacc_std": 0.06664849561662124} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.060135497890255095, "f1": 0.5240777541424093, "f1_std": 0.06227517261195627, "bacc": 0.5309065934065934, "bacc_std": 0.060196429981947845} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.062356237024518944, "f1": 0.4860837438423645, "f1_std": 0.0639203116637364, "bacc": 0.4965659340659341, "bacc_std": 0.06204328977184569} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06467281101983352, "f1": 0.548015873015873, "f1_std": 0.06951547090264605, "bacc": 0.5558608058608059, "bacc_std": 0.06460518916951155} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.005994842503189409, "split": "test", "acc": 0.6153846153846154, "acc_std": 0.06528103786954864, "f1": 0.623076923076923, "f1_std": 0.06445946964668103, "bacc": 0.6169871794871795, "bacc_std": 0.06563280171808179} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.0634508032878215, "f1": 0.5384392419175028, "f1_std": 0.06401219097548588, "bacc": 0.5368589743589743, "bacc_std": 0.06369213432322278} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06886123599301139, "f1": 0.4629895064677673, "f1_std": 0.06896651041256796, "bacc": 0.4640567765567766, "bacc_std": 0.0690575949048827} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05642038953277073, "f1": 0.4972691585594812, "f1_std": 0.058799261639715196, "bacc": 0.5185439560439561, "bacc_std": 0.056435595632769384} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06235662845621174, "f1": 0.4751835193514354, "f1_std": 0.0638647399594111, "bacc": 0.48489010989010994, "bacc_std": 0.06254024488035001} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06199403483424502, "f1": 0.546875, "f1_std": 0.06601499700457646, "bacc": 0.5588369963369964, "bacc_std": 0.06215811292066658} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06395454191808947, "f1": 0.44726081403742574, "f1_std": 0.06425092641923034, "bacc": 0.4608516483516484, "bacc_std": 0.06390318564525278} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.000774263682681127, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06453635276650181, "f1": 0.5289045923688279, "f1_std": 0.0662834468966552, "bacc": 0.5425824175824175, "bacc_std": 0.06487913607959161} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06113535037184916, "f1": 0.44457257372445, "f1_std": 0.05889394588366362, "bacc": 0.47275641025641024, "bacc_std": 0.06016005777303756} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 166.81005372000556, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07083437637009057, "f1": 0.4829032258064516, "f1_std": 0.06991098298687316, "bacc": 0.4775641025641026, "bacc_std": 0.07081038833995275} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.061328294964996456, "f1": 0.420455681250284, "f1_std": 0.06120184324781853, "bacc": 0.4223901098901099, "bacc_std": 0.06127065101631762} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06583863858982009, "f1": 0.5123677248677249, "f1_std": 0.06759852492998088, "bacc": 0.5203754578754579, "bacc_std": 0.06630547663069584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 2.782559402207126, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06448127107561255, "f1": 0.38255693581780537, "f1_std": 0.06315006323450753, "bacc": 0.3853021978021979, "bacc_std": 0.06476403382188932} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06247276329606491, "f1": 0.4409460654288241, "f1_std": 0.06204145251566039, "bacc": 0.4432234432234432, "bacc_std": 0.06279700640292792} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_age | train | 100 | 3.6337 | 23.528 | 0.78915 | 0.12795 | 0.78759 | 0.13072 | 0.78996 | 0.12774 | +| flat_mae | patch | logistic | aabc_age | test | 100 | 3.6337 | 23.528 | 0.49481 | 0.060866 | 0.48766 | 0.059456 | 0.49446 | 0.060655 | + + +done! total time: 0:06:14 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cb8d40da1623ca3d01ffd6c2ef874283b4d14d94 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_age reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..afe6eb2af30add60730b8e6d7bec9a8099b2f2e0 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,aabc_age,,0.005994842503189409,train,0.6830708661417323,0.01923070134289823,0.6798714795501035,0.019534890883764682,0.6829065056132148,0.019241365681448568 +flat_mae,reg,logistic,aabc_age,,0.005994842503189409,test,0.4230769230769231,0.05321469021273985,0.3777949776401789,0.056719001184573334,0.41117216117216115,0.05311649893940199 +flat_mae,reg,logistic,aabc_age,1,0.005994842503189409,train,0.6889763779527559,0.0192698140403966,0.6859033376238425,0.01979541840593549,0.6893631722188232,0.019336924056377703 +flat_mae,reg,logistic,aabc_age,1,0.005994842503189409,test,0.4807692307692308,0.06392649023563043,0.4727106227106227,0.06461674271306289,0.4773351648351648,0.06370365856335485 +flat_mae,reg,logistic,aabc_age,2,0.000774263682681127,train,0.562992125984252,0.020095118763709657,0.556633674493453,0.020671899311577847,0.5633649971518386,0.02010115577682658 +flat_mae,reg,logistic,aabc_age,2,0.000774263682681127,test,0.4807692307692308,0.06499288764001014,0.46895604395604396,0.06549929458359877,0.4773351648351648,0.06447628157746148 +flat_mae,reg,logistic,aabc_age,3,0.005994842503189409,train,0.6889763779527559,0.018417642640118748,0.6873761918976704,0.018812148749626806,0.6894631455592657,0.0184854118780836 +flat_mae,reg,logistic,aabc_age,3,0.005994842503189409,test,0.40384615384615385,0.06431132672836201,0.4075757575757576,0.06411101830677048,0.40476190476190477,0.06454332680481649 +flat_mae,reg,logistic,aabc_age,4,0.046415888336127774,train,0.8759842519685039,0.01501251415490297,0.8766786185334745,0.014997018277373585,0.8766030497382952,0.015008831584227179 +flat_mae,reg,logistic,aabc_age,4,0.046415888336127774,test,0.5,0.06404476753428581,0.49809116809116816,0.06389822185898075,0.49954212454212454,0.0641330857544142 +flat_mae,reg,logistic,aabc_age,5,0.000774263682681127,train,0.5590551181102362,0.021951590517423836,0.5516078336856411,0.022339379204687707,0.557392249357006,0.02191960699186777 +flat_mae,reg,logistic,aabc_age,5,0.000774263682681127,test,0.4807692307692308,0.06344783068738372,0.46785714285714286,0.06437307540771604,0.4787087912087912,0.06313697931343294 +flat_mae,reg,logistic,aabc_age,6,0.046415888336127774,train,0.8818897637795275,0.014198110267661327,0.8826220092053709,0.01409355640304344,0.8828013968457332,0.014157598836709563 +flat_mae,reg,logistic,aabc_age,6,0.046415888336127774,test,0.5769230769230769,0.06557550190203765,0.575724084344774,0.06620175191242723,0.5782967032967032,0.06567597854213691 +flat_mae,reg,logistic,aabc_age,7,0.000774263682681127,train,0.562992125984252,0.02089889866782292,0.559964930576011,0.021200324000270117,0.5635649438327237,0.020878384963908998 +flat_mae,reg,logistic,aabc_age,7,0.000774263682681127,test,0.5,0.06245484759540832,0.4860426929392446,0.06398583009981376,0.49793956043956045,0.062365463047425254 +flat_mae,reg,logistic,aabc_age,8,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,8,2.782559402207126,test,0.5576923076923077,0.06387510928208902,0.5540343915343916,0.06459370229866367,0.5620421245421245,0.06411207140381107 +flat_mae,reg,logistic,aabc_age,9,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,9,2.782559402207126,test,0.40384615384615385,0.06568234251565025,0.37619406737053795,0.06207605024606054,0.3944597069597069,0.06450187680279233 +flat_mae,reg,logistic,aabc_age,10,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,10,2.782559402207126,test,0.4807692307692308,0.06844264000178692,0.48204022988505746,0.0679189135915089,0.4819139194139194,0.06851931010782819 +flat_mae,reg,logistic,aabc_age,11,9.999999999999999e-05,train,0.484251968503937,0.020972022259463565,0.4601933443914576,0.020777827896331657,0.48316072548519434,0.02082475515882011 +flat_mae,reg,logistic,aabc_age,11,9.999999999999999e-05,test,0.4807692307692308,0.0638063360545805,0.43797672915319974,0.06620800713039032,0.4713827838827839,0.0630988157688371 +flat_mae,reg,logistic,aabc_age,12,0.005994842503189409,train,0.6889763779527559,0.020675235740632934,0.6853598583934409,0.021036625144465707,0.6886104952348439,0.020760226164115023 +flat_mae,reg,logistic,aabc_age,12,0.005994842503189409,test,0.5,0.06442164177505942,0.498015873015873,0.06589170968563947,0.5027472527472527,0.06465867122669075 +flat_mae,reg,logistic,aabc_age,13,0.005994842503189409,train,0.6988188976377953,0.019342376243756534,0.6964198572056423,0.01959274200914495,0.6987235058660617,0.019278970189732177 +flat_mae,reg,logistic,aabc_age,13,0.005994842503189409,test,0.4807692307692308,0.0653150195219134,0.47664021164021164,0.06541059903231335,0.48031135531135527,0.0654556296709045 +flat_mae,reg,logistic,aabc_age,14,0.046415888336127774,train,0.8779527559055118,0.01367774784683399,0.8783408009073621,0.013694697657042204,0.8793718557545326,0.013552944900066486 +flat_mae,reg,logistic,aabc_age,14,0.046415888336127774,test,0.5576923076923077,0.06324989183048495,0.5470764652014652,0.06697596119904248,0.5588369963369964,0.06334580658127892 +flat_mae,reg,logistic,aabc_age,15,0.005994842503189409,train,0.6791338582677166,0.0210140663647465,0.6760743521880963,0.021505158574007997,0.6796176894794481,0.020973828793038943 +flat_mae,reg,logistic,aabc_age,15,0.005994842503189409,test,0.5384615384615384,0.06790720914052083,0.5455128205128206,0.06714061488273218,0.5382326007326008,0.06788501768596923 +flat_mae,reg,logistic,aabc_age,16,0.000774263682681127,train,0.5669291338582677,0.020650291604940748,0.562188226491031,0.020983670164582132,0.5668445249132605,0.020578088208126573 +flat_mae,reg,logistic,aabc_age,16,0.000774263682681127,test,0.40384615384615385,0.06034030711491195,0.40339972527472523,0.06064234580491178,0.4017857142857143,0.060289564016466755 +flat_mae,reg,logistic,aabc_age,17,0.000774263682681127,train,0.5728346456692913,0.02163543229713382,0.5708453611707841,0.022331057907550772,0.5735279944532776,0.02158519733910513 +flat_mae,reg,logistic,aabc_age,17,0.000774263682681127,test,0.40384615384615385,0.059532933056781236,0.3705999775078722,0.05752857458702979,0.3999542124542125,0.05853471994664114 +flat_mae,reg,logistic,aabc_age,18,9.999999999999999e-05,train,0.49015748031496065,0.020610579906737415,0.4724424692239444,0.021276612915928972,0.48897392350049573,0.02051787825875249 +flat_mae,reg,logistic,aabc_age,18,9.999999999999999e-05,test,0.4807692307692308,0.05648720858502224,0.4219473055679952,0.0487320042704272,0.47115384615384615,0.054939450263597214 +flat_mae,reg,logistic,aabc_age,19,0.046415888336127774,train,0.8799212598425197,0.014013589146302281,0.8806703735180286,0.013980137345904356,0.8813203769162755,0.013922403750733555 +flat_mae,reg,logistic,aabc_age,19,0.046415888336127774,test,0.5384615384615384,0.06988886994373163,0.5381481481481482,0.0713690162966848,0.5384615384615384,0.07021150269999357 +flat_mae,reg,logistic,aabc_age,20,9.999999999999999e-05,train,0.49803149606299213,0.020590851912108077,0.4736691034166579,0.02106712655244585,0.49558307233179066,0.020489372024776895 +flat_mae,reg,logistic,aabc_age,20,9.999999999999999e-05,test,0.46153846153846156,0.05265135972103069,0.42399710504549215,0.055004551818534544,0.4576465201465202,0.051967655631323245 +flat_mae,reg,logistic,aabc_age,21,0.046415888336127774,train,0.889763779527559,0.014431835799917109,0.8900467041301704,0.014451192559254021,0.8903807905421863,0.01436598618956096 +flat_mae,reg,logistic,aabc_age,21,0.046415888336127774,test,0.4230769230769231,0.06637708309170653,0.4186253561253561,0.06455460536362269,0.4237637362637363,0.06650543523302856 +flat_mae,reg,logistic,aabc_age,22,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,22,21.54434690031882,test,0.4423076923076923,0.06520332332620067,0.44601191235132326,0.06362027676859443,0.44368131868131866,0.06540399950325476 +flat_mae,reg,logistic,aabc_age,23,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,23,2.782559402207126,test,0.5,0.06540610506582438,0.4963516687654619,0.06553807141083202,0.4981684981684982,0.06540147135900841 +flat_mae,reg,logistic,aabc_age,24,0.046415888336127774,train,0.8877952755905512,0.014516906556878838,0.888456162094335,0.014451800832808157,0.8883646615099282,0.014445253491761897 +flat_mae,reg,logistic,aabc_age,24,0.046415888336127774,test,0.38461538461538464,0.06368230830091309,0.37456668491151246,0.06273174694591384,0.38095238095238093,0.06310289381847908 +flat_mae,reg,logistic,aabc_age,25,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,25,0.3593813663804626,test,0.5,0.06741073431280598,0.5024242424242424,0.0653877209785972,0.49519230769230765,0.06735275885296506 +flat_mae,reg,logistic,aabc_age,26,0.000774263682681127,train,0.5767716535433071,0.021572223464947936,0.571936025493609,0.02200246104271347,0.5754021949062984,0.0215492388745687 +flat_mae,reg,logistic,aabc_age,26,0.000774263682681127,test,0.40384615384615385,0.061653870147315264,0.3955128205128205,0.05961138743002379,0.4015567765567766,0.06133448230448211 +flat_mae,reg,logistic,aabc_age,27,0.046415888336127774,train,0.8779527559055118,0.014379953461890013,0.8790338256454406,0.01431668371265711,0.8791542878733537,0.014300855988585841 +flat_mae,reg,logistic,aabc_age,27,0.046415888336127774,test,0.46153846153846156,0.06474364559530468,0.44010263929618765,0.0663742606413684,0.45535714285714285,0.06426304577997372 +flat_mae,reg,logistic,aabc_age,28,0.005994842503189409,train,0.6811023622047244,0.019979480995744644,0.6779496990979299,0.020381535215961245,0.6807135603167692,0.01989156403205067 +flat_mae,reg,logistic,aabc_age,28,0.005994842503189409,test,0.5,0.06448104166131166,0.49201581027667984,0.06705186146570921,0.502518315018315,0.06483815948329971 +flat_mae,reg,logistic,aabc_age,29,9.999999999999999e-05,train,0.5019685039370079,0.019261934846849314,0.47560087054765765,0.019664492591450325,0.5000004794884434,0.019129231858690327 +flat_mae,reg,logistic,aabc_age,29,9.999999999999999e-05,test,0.34615384615384615,0.06450919617025579,0.34449112978524743,0.05991937573416582,0.34226190476190477,0.06362295727993145 +flat_mae,reg,logistic,aabc_age,30,0.046415888336127774,train,0.8818897637795275,0.014885573743077923,0.8825261008720511,0.01484085276206316,0.8825838289645543,0.014905387670293658 +flat_mae,reg,logistic,aabc_age,30,0.046415888336127774,test,0.5576923076923077,0.06555474472693046,0.5524160035366932,0.06626494322115675,0.55746336996337,0.0657478067859569 +flat_mae,reg,logistic,aabc_age,31,9.999999999999999e-05,train,0.45866141732283466,0.020509120306537565,0.43271733418520986,0.020690268860898857,0.45767135957989136,0.02036589757145483 +flat_mae,reg,logistic,aabc_age,31,9.999999999999999e-05,test,0.5961538461538461,0.06027475307280956,0.5589755077658303,0.06368020402872923,0.586996336996337,0.059838645162049446 +flat_mae,reg,logistic,aabc_age,32,0.046415888336127774,train,0.8858267716535433,0.014244733775149341,0.8865078733235808,0.014185237170763643,0.8867836682400281,0.014149241208137318 +flat_mae,reg,logistic,aabc_age,32,0.046415888336127774,test,0.46153846153846156,0.06245588975973742,0.4513774858602444,0.06227338134847076,0.45947802197802196,0.06225459913542822 +flat_mae,reg,logistic,aabc_age,33,0.046415888336127774,train,0.8877952755905512,0.014673160211871912,0.8884997535344249,0.014624342160955156,0.8883646615099283,0.014603204295168587 +flat_mae,reg,logistic,aabc_age,33,0.046415888336127774,test,0.5961538461538461,0.06697142373903317,0.5995879120879122,0.06669933972403849,0.6007326007326007,0.06702602801536572 +flat_mae,reg,logistic,aabc_age,34,0.005994842503189409,train,0.6929133858267716,0.02014233059819453,0.6885866471657839,0.02076125641672099,0.6930778890617179,0.02005970987829225 +flat_mae,reg,logistic,aabc_age,34,0.005994842503189409,test,0.40384615384615385,0.06515674092197955,0.41493506493506493,0.0672134572814512,0.40201465201465203,0.06537233411884795 +flat_mae,reg,logistic,aabc_age,35,0.000774263682681127,train,0.5669291338582677,0.019784997786006307,0.5608086489917841,0.020220443418865513,0.5666945649025967,0.01979916449514612 +flat_mae,reg,logistic,aabc_age,35,0.000774263682681127,test,0.4230769230769231,0.05737419992094049,0.40560344827586203,0.05743243534266446,0.42216117216117216,0.057226159612763464 +flat_mae,reg,logistic,aabc_age,36,0.046415888336127774,train,0.8818897637795275,0.014676770380951566,0.8824484538957474,0.014613541038115066,0.8822662877429328,0.014669029150754532 +flat_mae,reg,logistic,aabc_age,36,0.046415888336127774,test,0.46153846153846156,0.06574123335710708,0.45002901519030547,0.06598791952631954,0.4624542124542124,0.06589201283273009 +flat_mae,reg,logistic,aabc_age,37,0.005994842503189409,train,0.687007874015748,0.02071464241045015,0.6848913699303126,0.021091700707254406,0.6885848426031236,0.020682687269679062 +flat_mae,reg,logistic,aabc_age,37,0.005994842503189409,test,0.4230769230769231,0.06315299118694212,0.4040749340671941,0.06387881387881181,0.41529304029304026,0.06261497779724998 +flat_mae,reg,logistic,aabc_age,38,0.046415888336127774,train,0.8877952755905512,0.014080225815146497,0.8882201730034892,0.01404513363025088,0.888314674839707,0.014077364708617715 +flat_mae,reg,logistic,aabc_age,38,0.046415888336127774,test,0.5192307692307693,0.06934750841289775,0.5229411764705882,0.07055935321047917,0.516025641025641,0.06968061124895286 +flat_mae,reg,logistic,aabc_age,39,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,39,0.3593813663804626,test,0.5384615384615384,0.06496083253248537,0.5316017316017316,0.0663491962906908,0.5325091575091575,0.06515406312594502 +flat_mae,reg,logistic,aabc_age,40,0.005994842503189409,train,0.6988188976377953,0.019265994922586287,0.6961963245589418,0.019493493979544668,0.6992762361691559,0.019201425972128882 +flat_mae,reg,logistic,aabc_age,40,0.005994842503189409,test,0.5,0.06165223857014487,0.49750536819502333,0.062422058724623135,0.502518315018315,0.06211489162777248 +flat_mae,reg,logistic,aabc_age,41,0.005994842503189409,train,0.6830708661417323,0.020215706996036975,0.6809865117477092,0.02046468558013527,0.6836323263436705,0.0203165877317468 +flat_mae,reg,logistic,aabc_age,41,0.005994842503189409,test,0.46153846153846156,0.06269984617253196,0.4471590909090909,0.06462980002215843,0.46382783882783885,0.06315461011652489 +flat_mae,reg,logistic,aabc_age,42,0.000774263682681127,train,0.5688976377952756,0.02064940888490938,0.5633677451262449,0.020908029711946528,0.5688106672752973,0.02067572884315996 +flat_mae,reg,logistic,aabc_age,42,0.000774263682681127,test,0.4807692307692308,0.06251007019464659,0.4637140033879164,0.06754746767707688,0.4846611721611722,0.06323007138428309 +flat_mae,reg,logistic,aabc_age,43,0.005994842503189409,train,0.6811023622047244,0.019704477017490944,0.6787334239064748,0.020002319307510362,0.6810311015383907,0.019659935226709637 +flat_mae,reg,logistic,aabc_age,43,0.005994842503189409,test,0.5,0.06982940963307753,0.49797903246179104,0.07105596729203731,0.5,0.07004852764544628 +flat_mae,reg,logistic,aabc_age,44,0.046415888336127774,train,0.8956692913385826,0.013315691086656312,0.8966775268865861,0.01318786989841502,0.8971642334226461,0.013178070816013488 +flat_mae,reg,logistic,aabc_age,44,0.046415888336127774,test,0.5,0.0670707477750218,0.49785821375026773,0.06829259187461195,0.49977106227106227,0.06734707878502307 +flat_mae,reg,logistic,aabc_age,45,0.005994842503189409,train,0.6811023622047244,0.019651440223510473,0.6789865603607418,0.02005576956348468,0.6812986560897909,0.019655443527758033 +flat_mae,reg,logistic,aabc_age,45,0.005994842503189409,test,0.46153846153846156,0.06691064208082775,0.4614285714285714,0.06628546680986722,0.4624542124542124,0.06700802045578522 +flat_mae,reg,logistic,aabc_age,46,0.000774263682681127,train,0.5728346456692913,0.021594595496399308,0.5674046914718556,0.022209502588471323,0.5721902216962766,0.021632207309020383 +flat_mae,reg,logistic,aabc_age,46,0.000774263682681127,test,0.5192307692307693,0.05813069339680113,0.5008313002620404,0.06389218518153582,0.5144230769230769,0.057606607394683165 +flat_mae,reg,logistic,aabc_age,47,0.000774263682681127,train,0.5728346456692913,0.019916145744237824,0.5668923570616491,0.020232247340160596,0.5720902483558341,0.01986800109114692 +flat_mae,reg,logistic,aabc_age,47,0.000774263682681127,test,0.40384615384615385,0.06372113570939139,0.39374999999999993,0.06387832317208787,0.39880952380952384,0.06306300428607248 +flat_mae,reg,logistic,aabc_age,48,0.046415888336127774,train,0.889763779527559,0.013792724276896345,0.8899514725568942,0.01382697599264229,0.8898956681096072,0.013863565367651478 +flat_mae,reg,logistic,aabc_age,48,0.046415888336127774,test,0.36538461538461536,0.0618072375647433,0.3483529612561871,0.061075396886352884,0.3658424908424909,0.06215204716271532 +flat_mae,reg,logistic,aabc_age,49,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,49,166.81005372000556,test,0.4230769230769231,0.06295178722477146,0.4152923538230885,0.06336822942101028,0.4210164835164835,0.06293127180838252 +flat_mae,reg,logistic,aabc_age,50,0.000774263682681127,train,0.5669291338582677,0.020695767070334672,0.5603793585287771,0.021153162073629505,0.5652891842750807,0.020672623872916757 +flat_mae,reg,logistic,aabc_age,50,0.000774263682681127,test,0.38461538461538464,0.06444229334526848,0.3927631578947368,0.06591219154022745,0.3855311355311355,0.06493610203636144 +flat_mae,reg,logistic,aabc_age,51,0.005994842503189409,train,0.6850393700787402,0.02055322454920586,0.6820660706052081,0.020954520689016133,0.6855984687057073,0.020515302882699087 +flat_mae,reg,logistic,aabc_age,51,0.005994842503189409,test,0.4807692307692308,0.07097795307336784,0.4800010708931248,0.0714630613118987,0.48054029304029305,0.07104318529455834 +flat_mae,reg,logistic,aabc_age,52,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,52,2.782559402207126,test,0.38461538461538464,0.07229757498777138,0.39176136363636366,0.07213397036348435,0.3841575091575091,0.07249398858109236 +flat_mae,reg,logistic,aabc_age,53,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,53,21.54434690031882,test,0.5769230769230769,0.06790238381537611,0.5809643255295429,0.06740518892365956,0.5769230769230769,0.06811940186129864 +flat_mae,reg,logistic,aabc_age,54,0.005994842503189409,train,0.6948818897637795,0.020169968372688345,0.69440694044822,0.020415980541773168,0.696414169650683,0.020146016642248365 +flat_mae,reg,logistic,aabc_age,54,0.005994842503189409,test,0.4423076923076923,0.06281578213480352,0.4216616716616717,0.06600847265441218,0.44459706959706957,0.06335999149372863 +flat_mae,reg,logistic,aabc_age,55,0.000774263682681127,train,0.5787401574803149,0.021305426124402314,0.5704341703183987,0.02174401368430274,0.5776535130200292,0.021222515464716592 +flat_mae,reg,logistic,aabc_age,55,0.000774263682681127,test,0.5192307692307693,0.06733378615076127,0.5319272125723739,0.06625803821352118,0.5219780219780219,0.06767559599978307 +flat_mae,reg,logistic,aabc_age,56,0.000774263682681127,train,0.5826771653543307,0.021727137285822755,0.5800974081086374,0.02192747434844728,0.5830559093114738,0.021698153946426872 +flat_mae,reg,logistic,aabc_age,56,0.000774263682681127,test,0.40384615384615385,0.06454831684173175,0.3952861952861953,0.06470480387384425,0.40315934065934067,0.06448685433594097 +flat_mae,reg,logistic,aabc_age,57,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,57,2.782559402207126,test,0.5576923076923077,0.0698287317309138,0.5565527950310558,0.07030071315273738,0.5560897435897436,0.06999355155833688 +flat_mae,reg,logistic,aabc_age,58,0.046415888336127774,train,0.8937007874015748,0.013323604224715593,0.8940168338866371,0.013327490503081244,0.8933252092008078,0.013410005147766019 +flat_mae,reg,logistic,aabc_age,58,0.046415888336127774,test,0.36538461538461536,0.05455489608083341,0.326384872080089,0.04912865000108022,0.3598901098901099,0.053155097581748925 +flat_mae,reg,logistic,aabc_age,59,0.000774263682681127,train,0.5708661417322834,0.020811328987424813,0.569379487097297,0.021159280266823805,0.571126716328883,0.02075969907574453 +flat_mae,reg,logistic,aabc_age,59,0.000774263682681127,test,0.5192307692307693,0.06763261135238824,0.5111111111111111,0.06891196181937025,0.5146520146520146,0.06731415324170952 +flat_mae,reg,logistic,aabc_age,60,0.000774263682681127,train,0.5708661417322834,0.02226122398081889,0.5659027084401392,0.02238168450327363,0.5708767829777768,0.02217148512486424 +flat_mae,reg,logistic,aabc_age,60,0.000774263682681127,test,0.34615384615384615,0.057909578057254316,0.33173444202855973,0.05615443403013839,0.34363553113553114,0.05743505971918894 +flat_mae,reg,logistic,aabc_age,61,0.005994842503189409,train,0.7165354330708661,0.01942633586822412,0.7161636688624861,0.01955930996231553,0.7174861283993332,0.019374707066805084 +flat_mae,reg,logistic,aabc_age,61,0.005994842503189409,test,0.34615384615384615,0.06472494146260217,0.3451075268817204,0.06330225620794061,0.3411172161172161,0.06419883097896827 +flat_mae,reg,logistic,aabc_age,62,0.046415888336127774,train,0.8740157480314961,0.014576394030847454,0.8751922844127773,0.014457693832380523,0.8748368540571435,0.01453434574432885 +flat_mae,reg,logistic,aabc_age,62,0.046415888336127774,test,0.5961538461538461,0.06750650856195166,0.598091168091168,0.06754244914274019,0.5977564102564104,0.06748670187744835 +flat_mae,reg,logistic,aabc_age,63,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,63,0.3593813663804626,test,0.5576923076923077,0.06389196688123369,0.5503402145081306,0.06585495737193393,0.55746336996337,0.06388187573260423 +flat_mae,reg,logistic,aabc_age,64,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,64,0.3593813663804626,test,0.4423076923076923,0.06570018868237297,0.44512422360248444,0.0653039370595607,0.43910256410256404,0.06552693169520964 +flat_mae,reg,logistic,aabc_age,65,0.046415888336127774,train,0.8956692913385826,0.013422055535690121,0.8965901242853688,0.013341811334757564,0.896044028546824,0.013389530732611987 +flat_mae,reg,logistic,aabc_age,65,0.046415888336127774,test,0.46153846153846156,0.06830686936441213,0.4687548698768895,0.06812309083838386,0.46130952380952384,0.06809553890785063 +flat_mae,reg,logistic,aabc_age,66,0.000774263682681127,train,0.5590551181102362,0.019712696712546027,0.5561399838507203,0.01984878047567006,0.5602353760819656,0.01970423017220102 +flat_mae,reg,logistic,aabc_age,66,0.000774263682681127,test,0.4807692307692308,0.06086500485967324,0.4729411764705882,0.06278749487425804,0.4759615384615385,0.060776278335856374 +flat_mae,reg,logistic,aabc_age,67,0.046415888336127774,train,0.8818897637795275,0.013979579870557852,0.8823946971610163,0.013951972865221063,0.8823162744131542,0.013973674510944934 +flat_mae,reg,logistic,aabc_age,67,0.046415888336127774,test,0.46153846153846156,0.06123109537988128,0.44439814814814815,0.06222045876094415,0.4652014652014652,0.06188568454248891 +flat_mae,reg,logistic,aabc_age,68,0.046415888336127774,train,0.8799212598425197,0.014234156006676124,0.8804661747720195,0.014199981733710417,0.8800325908294958,0.014231342549958977 +flat_mae,reg,logistic,aabc_age,68,0.046415888336127774,test,0.5,0.06074142499200337,0.46757723112128147,0.0643749747928856,0.49633699633699635,0.06021839359003046 +flat_mae,reg,logistic,aabc_age,69,0.046415888336127774,train,0.8858267716535433,0.013997654316657936,0.8862919913351954,0.013979992214210408,0.8862309379369339,0.014039228153806997 +flat_mae,reg,logistic,aabc_age,69,0.046415888336127774,test,0.46153846153846156,0.06949675400022685,0.4735023041474654,0.06948234676499879,0.4642857142857143,0.06996559195902667 +flat_mae,reg,logistic,aabc_age,70,0.3593813663804626,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,70,0.3593813663804626,test,0.38461538461538464,0.06402305196905216,0.3711755485893417,0.060239789992814693,0.3928571428571428,0.06529850877149543 +flat_mae,reg,logistic,aabc_age,71,0.000774263682681127,train,0.5826771653543307,0.02102937600047396,0.5779409916510969,0.021426903448425183,0.5822032589870518,0.020921044591236847 +flat_mae,reg,logistic,aabc_age,71,0.000774263682681127,test,0.4807692307692308,0.0647420347617277,0.47474913336982305,0.06580341558786117,0.4816849816849817,0.06503710758054057 +flat_mae,reg,logistic,aabc_age,72,0.046415888336127774,train,0.8858267716535433,0.014810529133138564,0.8871495949198197,0.014695165353511229,0.8873011561425347,0.014681515658421141 +flat_mae,reg,logistic,aabc_age,72,0.046415888336127774,test,0.5,0.06540298384521909,0.48957938613111024,0.06573613538224057,0.4965659340659341,0.0651702601631819 +flat_mae,reg,logistic,aabc_age,73,0.000774263682681127,train,0.5866141732283464,0.021660074533982054,0.5821735596848041,0.022127122141425933,0.5867206394841471,0.02168000959585534 +flat_mae,reg,logistic,aabc_age,73,0.000774263682681127,test,0.5192307692307693,0.06268423732859366,0.5149572649572649,0.06260467595753764,0.5173992673992673,0.06265035032563458 +flat_mae,reg,logistic,aabc_age,74,0.005994842503189409,train,0.7047244094488189,0.019914991933561194,0.7029816021524818,0.020255134124282318,0.705959705709173,0.019826926264628907 +flat_mae,reg,logistic,aabc_age,74,0.005994842503189409,test,0.5192307692307693,0.07041378126273277,0.5204123833156091,0.07159149988377018,0.5176282051282051,0.07046676119258215 +flat_mae,reg,logistic,aabc_age,75,0.000774263682681127,train,0.5669291338582677,0.02040365640316433,0.5615568309976203,0.020674192184642386,0.5671796873351758,0.020384630750251383 +flat_mae,reg,logistic,aabc_age,75,0.000774263682681127,test,0.5192307692307693,0.06909468462759621,0.5144562334217506,0.0705216389655756,0.516025641025641,0.06903198235439796 +flat_mae,reg,logistic,aabc_age,76,0.005994842503189409,train,0.6889763779527559,0.019513257955412564,0.685651483203328,0.019885632675019943,0.6893631722188232,0.019532670015661804 +flat_mae,reg,logistic,aabc_age,76,0.005994842503189409,test,0.5,0.06759970720499596,0.5083083458270864,0.06720281658617179,0.5027472527472527,0.06816647412932798 +flat_mae,reg,logistic,aabc_age,77,0.3593813663804626,train,0.9980314960629921,0.0020490754982237184,0.9980934568599307,0.0019830484371248895,0.9982014388489209,0.0018721768940605115 +flat_mae,reg,logistic,aabc_age,77,0.3593813663804626,test,0.38461538461538464,0.06847029978510918,0.38820921429617083,0.06865216422406259,0.3839285714285714,0.06870318842742007 +flat_mae,reg,logistic,aabc_age,78,0.005994842503189409,train,0.6889763779527559,0.02023616647255272,0.6869199911683572,0.020574708547390783,0.6899982546620661,0.020208310447527692 +flat_mae,reg,logistic,aabc_age,78,0.005994842503189409,test,0.5384615384615384,0.06741858995996096,0.540984940984941,0.06810286677314144,0.5382326007326007,0.06754999106677068 +flat_mae,reg,logistic,aabc_age,79,0.005994842503189409,train,0.7125984251968503,0.02017712924905547,0.7113073888091822,0.0204688279390747,0.7135214782053323,0.020146279497571754 +flat_mae,reg,logistic,aabc_age,79,0.005994842503189409,test,0.46153846153846156,0.065723769713289,0.44365530303030304,0.06572021130610678,0.4551282051282051,0.06511866138247166 +flat_mae,reg,logistic,aabc_age,80,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,80,166.81005372000556,test,0.40384615384615385,0.058525066697549886,0.3709821428571428,0.05559029878357505,0.40132783882783885,0.058001091808630965 +flat_mae,reg,logistic,aabc_age,81,0.3593813663804626,train,0.9980314960629921,0.001924306993677152,0.9979838381867551,0.0019711855933106284,0.997983870967742,0.0019708628080403164 +flat_mae,reg,logistic,aabc_age,81,0.3593813663804626,test,0.5,0.06401881195417226,0.5049919484702093,0.06391354379750719,0.5029761904761905,0.0641028446144438 +flat_mae,reg,logistic,aabc_age,82,0.005994842503189409,train,0.7047244094488189,0.01941112417103871,0.7019747774222612,0.01978648201195585,0.7048894875035722,0.019389242585195268 +flat_mae,reg,logistic,aabc_age,82,0.005994842503189409,test,0.5384615384615384,0.06583918906371833,0.5192673992673993,0.07044439651952257,0.5350274725274725,0.06569818328729189 +flat_mae,reg,logistic,aabc_age,83,0.046415888336127774,train,0.8799212598425197,0.014836229582593279,0.8809197204915469,0.01473859234728626,0.8802501587106747,0.014835296755588213 +flat_mae,reg,logistic,aabc_age,83,0.046415888336127774,test,0.4230769230769231,0.060348788980069415,0.41436688311688313,0.062382876443557715,0.4269688644688645,0.06101494230595718 +flat_mae,reg,logistic,aabc_age,84,0.046415888336127774,train,0.8976377952755905,0.013359408854721465,0.8980096938253757,0.013314866238954826,0.8980601575790821,0.013276939603071441 +flat_mae,reg,logistic,aabc_age,84,0.046415888336127774,test,0.5,0.05802084659028386,0.4677551533433887,0.06192472378815546,0.49633699633699635,0.05758027878626256 +flat_mae,reg,logistic,aabc_age,85,0.046415888336127774,train,0.8838582677165354,0.014382584893456951,0.884560820298844,0.014318336050023733,0.8837473076723904,0.014359333259151636 +flat_mae,reg,logistic,aabc_age,85,0.046415888336127774,test,0.4230769230769231,0.05897210001247757,0.40600748013090227,0.0597602158786027,0.4194139194139194,0.0586917136967691 +flat_mae,reg,logistic,aabc_age,86,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,86,2.782559402207126,test,0.5,0.06639904246475761,0.4874478969306555,0.06638835257789928,0.49519230769230765,0.06605158352166625 +flat_mae,reg,logistic,aabc_age,87,0.000774263682681127,train,0.5688976377952756,0.021377857049422508,0.5620650945445305,0.021759894531106223,0.568275558172497,0.021252294664189278 +flat_mae,reg,logistic,aabc_age,87,0.000774263682681127,test,0.4807692307692308,0.06118672314119621,0.4655677655677656,0.06338211564047945,0.4787087912087912,0.06104466523850354 +flat_mae,reg,logistic,aabc_age,88,0.000774263682681127,train,0.5669291338582677,0.019922558779351018,0.56085652833058,0.020726179982729555,0.5673972552163548,0.01994821177769374 +flat_mae,reg,logistic,aabc_age,88,0.000774263682681127,test,0.4807692307692308,0.06366861320691937,0.4831418581418581,0.06507061271602911,0.4819139194139194,0.06390754671126389 +flat_mae,reg,logistic,aabc_age,89,9.999999999999999e-05,train,0.4940944881889764,0.020277180199132067,0.47814209495405224,0.020859045729138683,0.49288858702427557,0.02019112823462845 +flat_mae,reg,logistic,aabc_age,89,9.999999999999999e-05,test,0.34615384615384615,0.0626234166082649,0.3208773637374861,0.0596135016602588,0.34363553113553114,0.06206860447575715 +flat_mae,reg,logistic,aabc_age,90,0.000774263682681127,train,0.5492125984251969,0.021069819704368727,0.5436478978133253,0.02122109381961649,0.5485494036122742,0.021085816275684403 +flat_mae,reg,logistic,aabc_age,90,0.000774263682681127,test,0.5769230769230769,0.061525238964069036,0.5651216901670622,0.06486315785945077,0.575091575091575,0.06141110803495058 +flat_mae,reg,logistic,aabc_age,91,0.000774263682681127,train,0.5708661417322834,0.02213496994381941,0.5639376947603875,0.022338606301287957,0.5700241326533548,0.022009939287939848 +flat_mae,reg,logistic,aabc_age,91,0.000774263682681127,test,0.5,0.06515674092197955,0.4923563218390804,0.06821044966689592,0.502518315018315,0.06532839741033897 +flat_mae,reg,logistic,aabc_age,92,0.046415888336127774,train,0.8877952755905512,0.013941442419191543,0.8886586289191936,0.013882508137722585,0.8886822027315497,0.013942346536576899 +flat_mae,reg,logistic,aabc_age,92,0.046415888336127774,test,0.5,0.05702531100024406,0.4719971264367816,0.06062268904018997,0.5006868131868132,0.057241693488105316 +flat_mae,reg,logistic,aabc_age,93,0.005994842503189409,train,0.702755905511811,0.02025490267866437,0.702062446337962,0.020647357295559124,0.7036084142549996,0.020304862942925262 +flat_mae,reg,logistic,aabc_age,93,0.005994842503189409,test,0.38461538461538464,0.06142831488672374,0.3729707792207792,0.06167657212603863,0.37957875457875456,0.061093329771185007 +flat_mae,reg,logistic,aabc_age,94,0.005994842503189409,train,0.702755905511811,0.0199240746820901,0.7013387589545851,0.020294128174418134,0.7029057239412416,0.019972620598178323 +flat_mae,reg,logistic,aabc_age,94,0.005994842503189409,test,0.4230769230769231,0.06282382382692642,0.41265398550724636,0.06580454519168219,0.4255952380952381,0.06311264277058883 +flat_mae,reg,logistic,aabc_age,95,0.046415888336127774,train,0.9015748031496063,0.012802277914365084,0.9019934418273707,0.012828158449084992,0.9026099035461048,0.012716971361564014 +flat_mae,reg,logistic,aabc_age,95,0.046415888336127774,test,0.5192307692307693,0.06396072898326757,0.5068390804597701,0.06378384137995073,0.5144230769230769,0.06346802664631261 +flat_mae,reg,logistic,aabc_age,96,0.046415888336127774,train,0.8759842519685039,0.014800101776204942,0.8767430543592192,0.014719629614117175,0.8768529830894016,0.014754521936209306 +flat_mae,reg,logistic,aabc_age,96,0.046415888336127774,test,0.5769230769230769,0.06777611726121464,0.5774844720496894,0.06777940729971099,0.5753205128205129,0.0680244208681978 +flat_mae,reg,logistic,aabc_age,97,0.005994842503189409,train,0.687007874015748,0.02081715353279026,0.6853541431065302,0.021116539643000535,0.6867943128834709,0.020797908768239864 +flat_mae,reg,logistic,aabc_age,97,0.005994842503189409,test,0.40384615384615385,0.0660385847407121,0.40186335403726703,0.06627994659758296,0.40315934065934067,0.06582862099472016 +flat_mae,reg,logistic,aabc_age,98,0.005994842503189409,train,0.7007874015748031,0.019946942378746182,0.6996748661513315,0.020226491653690594,0.701492311882299,0.019956037934423264 +flat_mae,reg,logistic,aabc_age,98,0.005994842503189409,test,0.5,0.05464867620218158,0.45105859665044135,0.05759855775642732,0.4919871794871795,0.05344432023041848 +flat_mae,reg,logistic,aabc_age,99,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_age,99,21.54434690031882,test,0.46153846153846156,0.06620972595209021,0.4539317642765918,0.06513115046609158,0.459478021978022,0.06576670418151946 +flat_mae,reg,logistic,aabc_age,100,0.046415888336127774,train,0.8956692913385826,0.01389261748230481,0.896509657317368,0.013811785177737847,0.895826460665645,0.01391525209042634 +flat_mae,reg,logistic,aabc_age,100,0.046415888336127774,test,0.46153846153846156,0.07202213458251905,0.4573268921095008,0.07246823095831337,0.46108058608058605,0.07209379065617269 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a575f698a1fe0eee6bd6fdde08701a6565e0f457 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:19:48 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_age reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_age +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_age__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_age (flat) +train (n=455): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1 2 3], + counts=[110 127 109 109] +) + +validation (n=53): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1 2 3], + counts=[14 13 12 14] +) + +test (n=52): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1 2 3], + counts=[13 13 12 14] +) + +extracting features for all splits +extract (train) [ 0/228] eta: 0:21:48 time: 5.7411 data: 4.7595 max mem: 3207 +extract (train) [ 20/228] eta: 0:01:48 time: 0.2603 data: 0.0941 max mem: 3395 +extract (train) [ 40/228] eta: 0:01:09 time: 0.2124 data: 0.0732 max mem: 3395 +extract (train) [ 60/228] eta: 0:00:53 time: 0.2099 data: 0.0709 max mem: 3395 +extract (train) [ 80/228] eta: 0:00:43 time: 0.2160 data: 0.0746 max mem: 3395 +extract (train) [100/228] eta: 0:00:35 time: 0.2181 data: 0.0742 max mem: 3395 +extract (train) [120/228] eta: 0:00:29 time: 0.2217 data: 0.0766 max mem: 3395 +extract (train) [140/228] eta: 0:00:23 time: 0.2195 data: 0.0760 max mem: 3395 +extract (train) [160/228] eta: 0:00:17 time: 0.2328 data: 0.0825 max mem: 3395 +extract (train) [180/228] eta: 0:00:12 time: 0.2222 data: 0.0750 max mem: 3395 +extract (train) [200/228] eta: 0:00:07 time: 0.2305 data: 0.0802 max mem: 3395 +extract (train) [220/228] eta: 0:00:01 time: 0.1931 data: 0.0589 max mem: 3395 +extract (train) [227/228] eta: 0:00:00 time: 0.2047 data: 0.0671 max mem: 3395 +extract (train) Total time: 0:00:56 (0.2478 s / it) +extract (validation) [ 0/27] eta: 0:02:16 time: 5.0416 data: 4.9019 max mem: 3395 +extract (validation) [20/27] eta: 0:00:03 time: 0.2020 data: 0.0610 max mem: 3395 +extract (validation) [26/27] eta: 0:00:00 time: 0.1865 data: 0.0557 max mem: 3395 +extract (validation) Total time: 0:00:10 (0.3920 s / it) +extract (test) [ 0/26] eta: 0:02:08 time: 4.9397 data: 4.7402 max mem: 3395 +extract (test) [20/26] eta: 0:00:02 time: 0.2428 data: 0.0836 max mem: 3395 +extract (test) [25/26] eta: 0:00:00 time: 0.2152 data: 0.0692 max mem: 3395 +extract (test) Total time: 0:00:11 (0.4296 s / it) +feature extraction time: 0:01:18 +train features: (455, 768) +validation features: (53, 768) +test features: (52, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_age | | 0.0059948 | train | 0.68307 | 0.019231 | 0.67987 | 0.019535 | 0.68291 | 0.019241 | +| flat_mae | reg | logistic | aabc_age | | 0.0059948 | test | 0.42308 | 0.053215 | 0.37779 | 0.056719 | 0.41117 | 0.053116 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06392649023563043, "f1": 0.4727106227106227, "f1_std": 0.06461674271306289, "bacc": 0.4773351648351648, "bacc_std": 0.06370365856335485} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 2, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06499288764001014, "f1": 0.46895604395604396, "f1_std": 0.06549929458359877, "bacc": 0.4773351648351648, "bacc_std": 0.06447628157746148} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 3, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06431132672836201, "f1": 0.4075757575757576, "f1_std": 0.06411101830677048, "bacc": 0.40476190476190477, "bacc_std": 0.06454332680481649} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06404476753428581, "f1": 0.49809116809116816, "f1_std": 0.06389822185898075, "bacc": 0.49954212454212454, "bacc_std": 0.0641330857544142} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 5, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06344783068738372, "f1": 0.46785714285714286, "f1_std": 0.06437307540771604, "bacc": 0.4787087912087912, "bacc_std": 0.06313697931343294} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06557550190203765, "f1": 0.575724084344774, "f1_std": 0.06620175191242723, "bacc": 0.5782967032967032, "bacc_std": 0.06567597854213691} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 7, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06245484759540832, "f1": 0.4860426929392446, "f1_std": 0.06398583009981376, "bacc": 0.49793956043956045, "bacc_std": 0.062365463047425254} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06387510928208902, "f1": 0.5540343915343916, "f1_std": 0.06459370229866367, "bacc": 0.5620421245421245, "bacc_std": 0.06411207140381107} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 9, "C": 2.782559402207126, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06568234251565025, "f1": 0.37619406737053795, "f1_std": 0.06207605024606054, "bacc": 0.3944597069597069, "bacc_std": 0.06450187680279233} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 10, "C": 2.782559402207126, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06844264000178692, "f1": 0.48204022988505746, "f1_std": 0.0679189135915089, "bacc": 0.4819139194139194, "bacc_std": 0.06851931010782819} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 11, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0638063360545805, "f1": 0.43797672915319974, "f1_std": 0.06620800713039032, "bacc": 0.4713827838827839, "bacc_std": 0.0630988157688371} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06442164177505942, "f1": 0.498015873015873, "f1_std": 0.06589170968563947, "bacc": 0.5027472527472527, "bacc_std": 0.06465867122669075} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 13, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0653150195219134, "f1": 0.47664021164021164, "f1_std": 0.06541059903231335, "bacc": 0.48031135531135527, "bacc_std": 0.0654556296709045} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06324989183048495, "f1": 0.5470764652014652, "f1_std": 0.06697596119904248, "bacc": 0.5588369963369964, "bacc_std": 0.06334580658127892} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 15, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06790720914052083, "f1": 0.5455128205128206, "f1_std": 0.06714061488273218, "bacc": 0.5382326007326008, "bacc_std": 0.06788501768596923} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 16, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06034030711491195, "f1": 0.40339972527472523, "f1_std": 0.06064234580491178, "bacc": 0.4017857142857143, "bacc_std": 0.060289564016466755} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 17, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.059532933056781236, "f1": 0.3705999775078722, "f1_std": 0.05752857458702979, "bacc": 0.3999542124542125, "bacc_std": 0.05853471994664114} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 18, "C": 9.999999999999999e-05, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.05648720858502224, "f1": 0.4219473055679952, "f1_std": 0.0487320042704272, "bacc": 0.47115384615384615, "bacc_std": 0.054939450263597214} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06988886994373163, "f1": 0.5381481481481482, "f1_std": 0.0713690162966848, "bacc": 0.5384615384615384, "bacc_std": 0.07021150269999357} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 20, "C": 9.999999999999999e-05, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.05265135972103069, "f1": 0.42399710504549215, "f1_std": 0.055004551818534544, "bacc": 0.4576465201465202, "bacc_std": 0.051967655631323245} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06637708309170653, "f1": 0.4186253561253561, "f1_std": 0.06455460536362269, "bacc": 0.4237637362637363, "bacc_std": 0.06650543523302856} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 22, "C": 21.54434690031882, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06520332332620067, "f1": 0.44601191235132326, "f1_std": 0.06362027676859443, "bacc": 0.44368131868131866, "bacc_std": 0.06540399950325476} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 23, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.06540610506582438, "f1": 0.4963516687654619, "f1_std": 0.06553807141083202, "bacc": 0.4981684981684982, "bacc_std": 0.06540147135900841} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06368230830091309, "f1": 0.37456668491151246, "f1_std": 0.06273174694591384, "bacc": 0.38095238095238093, "bacc_std": 0.06310289381847908} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 25, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.06741073431280598, "f1": 0.5024242424242424, "f1_std": 0.0653877209785972, "bacc": 0.49519230769230765, "bacc_std": 0.06735275885296506} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 26, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.061653870147315264, "f1": 0.3955128205128205, "f1_std": 0.05961138743002379, "bacc": 0.4015567765567766, "bacc_std": 0.06133448230448211} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 27, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06474364559530468, "f1": 0.44010263929618765, "f1_std": 0.0663742606413684, "bacc": 0.45535714285714285, "bacc_std": 0.06426304577997372} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06448104166131166, "f1": 0.49201581027667984, "f1_std": 0.06705186146570921, "bacc": 0.502518315018315, "bacc_std": 0.06483815948329971} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 29, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06450919617025579, "f1": 0.34449112978524743, "f1_std": 0.05991937573416582, "bacc": 0.34226190476190477, "bacc_std": 0.06362295727993145} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06555474472693046, "f1": 0.5524160035366932, "f1_std": 0.06626494322115675, "bacc": 0.55746336996337, "bacc_std": 0.0657478067859569} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 31, "C": 9.999999999999999e-05, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06027475307280956, "f1": 0.5589755077658303, "f1_std": 0.06368020402872923, "bacc": 0.586996336996337, "bacc_std": 0.059838645162049446} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06245588975973742, "f1": 0.4513774858602444, "f1_std": 0.06227338134847076, "bacc": 0.45947802197802196, "bacc_std": 0.06225459913542822} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06697142373903317, "f1": 0.5995879120879122, "f1_std": 0.06669933972403849, "bacc": 0.6007326007326007, "bacc_std": 0.06702602801536572} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06515674092197955, "f1": 0.41493506493506493, "f1_std": 0.0672134572814512, "bacc": 0.40201465201465203, "bacc_std": 0.06537233411884795} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 35, "C": 0.000774263682681127, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05737419992094049, "f1": 0.40560344827586203, "f1_std": 0.05743243534266446, "bacc": 0.42216117216117216, "bacc_std": 0.057226159612763464} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06574123335710708, "f1": 0.45002901519030547, "f1_std": 0.06598791952631954, "bacc": 0.4624542124542124, "bacc_std": 0.06589201283273009} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06315299118694212, "f1": 0.4040749340671941, "f1_std": 0.06387881387881181, "bacc": 0.41529304029304026, "bacc_std": 0.06261497779724998} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06934750841289775, "f1": 0.5229411764705882, "f1_std": 0.07055935321047917, "bacc": 0.516025641025641, "bacc_std": 0.06968061124895286} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06496083253248537, "f1": 0.5316017316017316, "f1_std": 0.0663491962906908, "bacc": 0.5325091575091575, "bacc_std": 0.06515406312594502} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06165223857014487, "f1": 0.49750536819502333, "f1_std": 0.062422058724623135, "bacc": 0.502518315018315, "bacc_std": 0.06211489162777248} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06269984617253196, "f1": 0.4471590909090909, "f1_std": 0.06462980002215843, "bacc": 0.46382783882783885, "bacc_std": 0.06315461011652489} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 42, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06251007019464659, "f1": 0.4637140033879164, "f1_std": 0.06754746767707688, "bacc": 0.4846611721611722, "bacc_std": 0.06323007138428309} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 43, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06982940963307753, "f1": 0.49797903246179104, "f1_std": 0.07105596729203731, "bacc": 0.5, "bacc_std": 0.07004852764544628} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.0670707477750218, "f1": 0.49785821375026773, "f1_std": 0.06829259187461195, "bacc": 0.49977106227106227, "bacc_std": 0.06734707878502307} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06691064208082775, "f1": 0.4614285714285714, "f1_std": 0.06628546680986722, "bacc": 0.4624542124542124, "bacc_std": 0.06700802045578522} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 46, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.05813069339680113, "f1": 0.5008313002620404, "f1_std": 0.06389218518153582, "bacc": 0.5144230769230769, "bacc_std": 0.057606607394683165} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 47, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06372113570939139, "f1": 0.39374999999999993, "f1_std": 0.06387832317208787, "bacc": 0.39880952380952384, "bacc_std": 0.06306300428607248} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.0618072375647433, "f1": 0.3483529612561871, "f1_std": 0.061075396886352884, "bacc": 0.3658424908424909, "bacc_std": 0.06215204716271532} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 49, "C": 166.81005372000556, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06295178722477146, "f1": 0.4152923538230885, "f1_std": 0.06336822942101028, "bacc": 0.4210164835164835, "bacc_std": 0.06293127180838252} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 50, "C": 0.000774263682681127, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06444229334526848, "f1": 0.3927631578947368, "f1_std": 0.06591219154022745, "bacc": 0.3855311355311355, "bacc_std": 0.06493610203636144} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.07097795307336784, "f1": 0.4800010708931248, "f1_std": 0.0714630613118987, "bacc": 0.48054029304029305, "bacc_std": 0.07104318529455834} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 52, "C": 2.782559402207126, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.07229757498777138, "f1": 0.39176136363636366, "f1_std": 0.07213397036348435, "bacc": 0.3841575091575091, "bacc_std": 0.07249398858109236} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 53, "C": 21.54434690031882, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06790238381537611, "f1": 0.5809643255295429, "f1_std": 0.06740518892365956, "bacc": 0.5769230769230769, "bacc_std": 0.06811940186129864} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06281578213480352, "f1": 0.4216616716616717, "f1_std": 0.06600847265441218, "bacc": 0.44459706959706957, "bacc_std": 0.06335999149372863} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 55, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06733378615076127, "f1": 0.5319272125723739, "f1_std": 0.06625803821352118, "bacc": 0.5219780219780219, "bacc_std": 0.06767559599978307} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 56, "C": 0.000774263682681127, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.06454831684173175, "f1": 0.3952861952861953, "f1_std": 0.06470480387384425, "bacc": 0.40315934065934067, "bacc_std": 0.06448685433594097} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 57, "C": 2.782559402207126, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.0698287317309138, "f1": 0.5565527950310558, "f1_std": 0.07030071315273738, "bacc": 0.5560897435897436, "bacc_std": 0.06999355155833688} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.36538461538461536, "acc_std": 0.05455489608083341, "f1": 0.326384872080089, "f1_std": 0.04912865000108022, "bacc": 0.3598901098901099, "bacc_std": 0.053155097581748925} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 59, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06763261135238824, "f1": 0.5111111111111111, "f1_std": 0.06891196181937025, "bacc": 0.5146520146520146, "bacc_std": 0.06731415324170952} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 60, "C": 0.000774263682681127, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.057909578057254316, "f1": 0.33173444202855973, "f1_std": 0.05615443403013839, "bacc": 0.34363553113553114, "bacc_std": 0.05743505971918894} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 61, "C": 0.005994842503189409, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.06472494146260217, "f1": 0.3451075268817204, "f1_std": 0.06330225620794061, "bacc": 0.3411172161172161, "bacc_std": 0.06419883097896827} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 62, "C": 0.046415888336127774, "split": "test", "acc": 0.5961538461538461, "acc_std": 0.06750650856195166, "f1": 0.598091168091168, "f1_std": 0.06754244914274019, "bacc": 0.5977564102564104, "bacc_std": 0.06748670187744835} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 63, "C": 0.3593813663804626, "split": "test", "acc": 0.5576923076923077, "acc_std": 0.06389196688123369, "f1": 0.5503402145081306, "f1_std": 0.06585495737193393, "bacc": 0.55746336996337, "bacc_std": 0.06388187573260423} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 64, "C": 0.3593813663804626, "split": "test", "acc": 0.4423076923076923, "acc_std": 0.06570018868237297, "f1": 0.44512422360248444, "f1_std": 0.0653039370595607, "bacc": 0.43910256410256404, "bacc_std": 0.06552693169520964} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06830686936441213, "f1": 0.4687548698768895, "f1_std": 0.06812309083838386, "bacc": 0.46130952380952384, "bacc_std": 0.06809553890785063} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 66, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06086500485967324, "f1": 0.4729411764705882, "f1_std": 0.06278749487425804, "bacc": 0.4759615384615385, "bacc_std": 0.060776278335856374} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 67, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06123109537988128, "f1": 0.44439814814814815, "f1_std": 0.06222045876094415, "bacc": 0.4652014652014652, "bacc_std": 0.06188568454248891} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 68, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06074142499200337, "f1": 0.46757723112128147, "f1_std": 0.0643749747928856, "bacc": 0.49633699633699635, "bacc_std": 0.06021839359003046} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 69, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06949675400022685, "f1": 0.4735023041474654, "f1_std": 0.06948234676499879, "bacc": 0.4642857142857143, "bacc_std": 0.06996559195902667} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 70, "C": 0.3593813663804626, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06402305196905216, "f1": 0.3711755485893417, "f1_std": 0.060239789992814693, "bacc": 0.3928571428571428, "bacc_std": 0.06529850877149543} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 71, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.0647420347617277, "f1": 0.47474913336982305, "f1_std": 0.06580341558786117, "bacc": 0.4816849816849817, "bacc_std": 0.06503710758054057} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.06540298384521909, "f1": 0.48957938613111024, "f1_std": 0.06573613538224057, "bacc": 0.4965659340659341, "bacc_std": 0.0651702601631819} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 73, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06268423732859366, "f1": 0.5149572649572649, "f1_std": 0.06260467595753764, "bacc": 0.5173992673992673, "bacc_std": 0.06265035032563458} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.07041378126273277, "f1": 0.5204123833156091, "f1_std": 0.07159149988377018, "bacc": 0.5176282051282051, "bacc_std": 0.07046676119258215} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 75, "C": 0.000774263682681127, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06909468462759621, "f1": 0.5144562334217506, "f1_std": 0.0705216389655756, "bacc": 0.516025641025641, "bacc_std": 0.06903198235439796} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.06759970720499596, "f1": 0.5083083458270864, "f1_std": 0.06720281658617179, "bacc": 0.5027472527472527, "bacc_std": 0.06816647412932798} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06847029978510918, "f1": 0.38820921429617083, "f1_std": 0.06865216422406259, "bacc": 0.3839285714285714, "bacc_std": 0.06870318842742007} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06741858995996096, "f1": 0.540984940984941, "f1_std": 0.06810286677314144, "bacc": 0.5382326007326007, "bacc_std": 0.06754999106677068} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 79, "C": 0.005994842503189409, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.065723769713289, "f1": 0.44365530303030304, "f1_std": 0.06572021130610678, "bacc": 0.4551282051282051, "bacc_std": 0.06511866138247166} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 80, "C": 166.81005372000556, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.058525066697549886, "f1": 0.3709821428571428, "f1_std": 0.05559029878357505, "bacc": 0.40132783882783885, "bacc_std": 0.058001091808630965} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.5, "acc_std": 0.06401881195417226, "f1": 0.5049919484702093, "f1_std": 0.06391354379750719, "bacc": 0.5029761904761905, "bacc_std": 0.0641028446144438} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.5384615384615384, "acc_std": 0.06583918906371833, "f1": 0.5192673992673993, "f1_std": 0.07044439651952257, "bacc": 0.5350274725274725, "bacc_std": 0.06569818328729189} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.060348788980069415, "f1": 0.41436688311688313, "f1_std": 0.062382876443557715, "bacc": 0.4269688644688645, "bacc_std": 0.06101494230595718} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.05802084659028386, "f1": 0.4677551533433887, "f1_std": 0.06192472378815546, "bacc": 0.49633699633699635, "bacc_std": 0.05758027878626256} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.05897210001247757, "f1": 0.40600748013090227, "f1_std": 0.0597602158786027, "bacc": 0.4194139194139194, "bacc_std": 0.0586917136967691} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 86, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.06639904246475761, "f1": 0.4874478969306555, "f1_std": 0.06638835257789928, "bacc": 0.49519230769230765, "bacc_std": 0.06605158352166625} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 87, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06118672314119621, "f1": 0.4655677655677656, "f1_std": 0.06338211564047945, "bacc": 0.4787087912087912, "bacc_std": 0.06104466523850354} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 88, "C": 0.000774263682681127, "split": "test", "acc": 0.4807692307692308, "acc_std": 0.06366861320691937, "f1": 0.4831418581418581, "f1_std": 0.06507061271602911, "bacc": 0.4819139194139194, "bacc_std": 0.06390754671126389} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 89, "C": 9.999999999999999e-05, "split": "test", "acc": 0.34615384615384615, "acc_std": 0.0626234166082649, "f1": 0.3208773637374861, "f1_std": 0.0596135016602588, "bacc": 0.34363553113553114, "bacc_std": 0.06206860447575715} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 90, "C": 0.000774263682681127, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.061525238964069036, "f1": 0.5651216901670622, "f1_std": 0.06486315785945077, "bacc": 0.575091575091575, "bacc_std": 0.06141110803495058} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 91, "C": 0.000774263682681127, "split": "test", "acc": 0.5, "acc_std": 0.06515674092197955, "f1": 0.4923563218390804, "f1_std": 0.06821044966689592, "bacc": 0.502518315018315, "bacc_std": 0.06532839741033897} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.5, "acc_std": 0.05702531100024406, "f1": 0.4719971264367816, "f1_std": 0.06062268904018997, "bacc": 0.5006868131868132, "bacc_std": 0.057241693488105316} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.38461538461538464, "acc_std": 0.06142831488672374, "f1": 0.3729707792207792, "f1_std": 0.06167657212603863, "bacc": 0.37957875457875456, "bacc_std": 0.061093329771185007} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.4230769230769231, "acc_std": 0.06282382382692642, "f1": 0.41265398550724636, "f1_std": 0.06580454519168219, "bacc": 0.4255952380952381, "bacc_std": 0.06311264277058883} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.5192307692307693, "acc_std": 0.06396072898326757, "f1": 0.5068390804597701, "f1_std": 0.06378384137995073, "bacc": 0.5144230769230769, "bacc_std": 0.06346802664631261} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.5769230769230769, "acc_std": 0.06777611726121464, "f1": 0.5774844720496894, "f1_std": 0.06777940729971099, "bacc": 0.5753205128205129, "bacc_std": 0.0680244208681978} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.40384615384615385, "acc_std": 0.0660385847407121, "f1": 0.40186335403726703, "f1_std": 0.06627994659758296, "bacc": 0.40315934065934067, "bacc_std": 0.06582862099472016} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.5, "acc_std": 0.05464867620218158, "f1": 0.45105859665044135, "f1_std": 0.05759855775642732, "bacc": 0.4919871794871795, "bacc_std": 0.05344432023041848} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 99, "C": 21.54434690031882, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.06620972595209021, "f1": 0.4539317642765918, "f1_std": 0.06513115046609158, "bacc": 0.459478021978022, "bacc_std": 0.06576670418151946} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_age", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.46153846153846156, "acc_std": 0.07202213458251905, "f1": 0.4573268921095008, "f1_std": 0.07246823095831337, "bacc": 0.46108058608058605, "bacc_std": 0.07209379065617269} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_age | train | 100 | 4.2171 | 23.639 | 0.76469 | 0.17184 | 0.76183 | 0.17579 | 0.76484 | 0.17213 | +| flat_mae | reg | logistic | aabc_age | test | 100 | 4.2171 | 23.639 | 0.47269 | 0.06204 | 0.46335 | 0.065035 | 0.47127 | 0.062477 | + + +done! total time: 0:05:50 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1d6bf8e275f5a06cf7bf22d6adf34785a6456a22 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..79ab3e6800bb799430a7a5469e96a6577448a38b --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,train,0.9017013232514177,0.012736280551738314,0.898703785535425,0.013215530381550355,0.8963773419203747,0.013510913226155013 +flat_mae,patch,logistic,aabc_sex,,0.005994842503189409,test,0.9090909090909091,0.03827643687485436,0.9071259709557582,0.038641987643678516,0.9166666666666667,0.035932708637756695 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,train,0.941398865784499,0.010857903829208393,0.9400272819365054,0.011112035228543085,0.9408320876930742,0.011207419318927686 +flat_mae,patch,logistic,aabc_sex,1,0.046415888336127774,test,0.8181818181818182,0.05348713910452469,0.8131793478260869,0.054979212146414026,0.8131793478260869,0.054957623048201634 +flat_mae,patch,logistic,aabc_sex,2,0.046415888336127774,train,0.9357277882797732,0.010822021442336197,0.9339410589410589,0.011146879758396133,0.9328892992174448,0.011367768071767531 +flat_mae,patch,logistic,aabc_sex,2,0.046415888336127774,test,0.8909090909090909,0.0412584837256393,0.8879076086956521,0.042341836210017005,0.8879076086956521,0.04225670370228804 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,train,0.941398865784499,0.010551743076354382,0.9398830580860384,0.010826123291461083,0.939615756616548,0.010938151016758806 +flat_mae,patch,logistic,aabc_sex,3,0.046415888336127774,test,0.7818181818181819,0.05210369825550606,0.76890756302521,0.05680169055069752,0.7635869565217391,0.05592744453386241 +flat_mae,patch,logistic,aabc_sex,4,0.046415888336127774,train,0.943289224952741,0.009760959579726414,0.9416372462488967,0.010101103721930413,0.9400334124681262,0.010524769456495539 +flat_mae,patch,logistic,aabc_sex,4,0.046415888336127774,test,0.8181818181818182,0.05247810720231044,0.8166666666666667,0.052501969623929716,0.8254076086956521,0.05071315102699185 +flat_mae,patch,logistic,aabc_sex,5,0.3593813663804626,train,0.9924385633270322,0.0038033556690961995,0.9922570257611241,0.0038886648085650665,0.9928558867493186,0.003619551937435811 +flat_mae,patch,logistic,aabc_sex,5,0.3593813663804626,test,0.8181818181818182,0.05208099223388619,0.8131793478260869,0.05383167560013537,0.8131793478260869,0.053847858227065365 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,train,0.994328922495274,0.0031986843397265393,0.9941893034853195,0.003275884316451405,0.9944898736774231,0.0031679022448772654 +flat_mae,patch,logistic,aabc_sex,6,0.3593813663804626,test,0.9090909090909091,0.03719932461841365,0.905982905982906,0.038818152031709165,0.9035326086956521,0.03987086821319644 +flat_mae,patch,logistic,aabc_sex,7,0.046415888336127774,train,0.9357277882797732,0.010374618340692393,0.9341056302939711,0.010624612182243405,0.9341056302939711,0.010667060890048166 +flat_mae,patch,logistic,aabc_sex,7,0.046415888336127774,test,0.8727272727272727,0.0440026295232305,0.8683760683760684,0.04617714443188985,0.8661684782608696,0.046897032550463416 +flat_mae,patch,logistic,aabc_sex,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,8,166.81005372000556,test,0.8181818181818182,0.04811857255565034,0.8166666666666667,0.0483682911523126,0.8254076086956521,0.04795113367465533 +flat_mae,patch,logistic,aabc_sex,9,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,9,166.81005372000556,test,0.8545454545454545,0.04570410040016571,0.8484848484848485,0.048505118311174523,0.8444293478260869,0.04918904563182276 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,train,0.9319470699432892,0.010805101851496121,0.9301434985474073,0.011101021599693534,0.9296213253612357,0.01124940764633952 +flat_mae,patch,logistic,aabc_sex,10,0.046415888336127774,test,0.8909090909090909,0.042331333763322626,0.8891129032258065,0.0426952658338831,0.8940217391304348,0.04145416230090705 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,train,0.9300567107750473,0.010860983873207471,0.9282475209414007,0.011146791644726275,0.9279873384331311,0.011256998605877309 +flat_mae,patch,logistic,aabc_sex,11,0.046415888336127774,test,0.9454545454545454,0.029653558871053046,0.9435897435897436,0.03095474923509793,0.9408967391304348,0.03215051798878318 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,train,0.996219281663516,0.002536137873149522,0.9961238606055277,0.002600608382737361,0.9961238606055277,0.002652418738548024 +flat_mae,patch,logistic,aabc_sex,12,0.3593813663804626,test,0.8363636363636363,0.04862778174073737,0.8307692307692308,0.05108891059257972,0.8288043478260869,0.05152825764450441 +flat_mae,patch,logistic,aabc_sex,13,0.046415888336127774,train,0.9395085066162571,0.00983353937533734,0.9379817696884434,0.010088684725499142,0.9379817696884434,0.010224041700548553 +flat_mae,patch,logistic,aabc_sex,13,0.046415888336127774,test,0.8909090909090909,0.04000692502038587,0.8863636363636364,0.042140842076823906,0.8817934782608696,0.042894589293149245 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,train,0.9300567107750473,0.011404523545194308,0.9282475209414007,0.011706476349237152,0.9279873384331311,0.011834992300765132 +flat_mae,patch,logistic,aabc_sex,14,0.046415888336127774,test,0.9090909090909091,0.03980507879053453,0.905982905982906,0.04162782937675307,0.9035326086956521,0.04261664455839096 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,train,0.994328922495274,0.003342668189736639,0.9941822314276811,0.003432473935009233,0.99388170813916,0.0036809079935505606 +flat_mae,patch,logistic,aabc_sex,15,0.3593813663804626,test,0.8181818181818182,0.052728163001888435,0.8131793478260869,0.054402197084756125,0.8131793478260869,0.0544089271173042 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,train,0.9319470699432892,0.010840665781725371,0.9302294908994988,0.011112567636942357,0.9302294908994988,0.011240839133363146 +flat_mae,patch,logistic,aabc_sex,16,0.046415888336127774,test,0.8909090909090909,0.04436475408428043,0.8879076086956521,0.04578575195712156,0.8879076086956521,0.04599213008069578 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,train,0.9395085066162571,0.010462866648462426,0.9379817696884434,0.010743366386172851,0.9379817696884434,0.010940705422756533 +flat_mae,patch,logistic,aabc_sex,17,0.046415888336127774,test,0.9272727272727272,0.03463910750286505,0.9242424242424243,0.03688055219883087,0.9191576086956521,0.03837289279491788 +flat_mae,patch,logistic,aabc_sex,18,0.046415888336127774,train,0.9338374291115312,0.01028940120647262,0.9322888667025062,0.010521995511339347,0.9330798089041297,0.010623739386174207 +flat_mae,patch,logistic,aabc_sex,18,0.046415888336127774,test,0.9090909090909091,0.038108587782938345,0.9071259709557582,0.038897029534429535,0.9096467391304348,0.03852450096659667 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,train,0.947069943289225,0.00941492695804502,0.945734048477388,0.009676570476580498,0.945734048477388,0.00993040696806876 +flat_mae,patch,logistic,aabc_sex,19,0.046415888336127774,test,0.8363636363636363,0.04679494215799657,0.8307692307692308,0.0488763400887655,0.8288043478260869,0.04913731440732054 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,train,0.941398865784499,0.010154235261791456,0.939956136014968,0.010394974674407547,0.9402239221548111,0.010467010963599501 +flat_mae,patch,logistic,aabc_sex,20,0.046415888336127774,test,0.8363636363636363,0.0478800705620281,0.8250265111346766,0.05352598067489189,0.8165760869565217,0.052746288933709404 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,train,0.941398865784499,0.009951023033309204,0.9398830580860384,0.010209418087499467,0.939615756616548,0.010318622123939433 +flat_mae,patch,logistic,aabc_sex,21,0.046415888336127774,test,0.8,0.055858842164279436,0.795677136102668,0.05714775522539658,0.7975543478260869,0.05715501169926794 +flat_mae,patch,logistic,aabc_sex,22,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,22,2.782559402207126,test,0.8909090909090909,0.041266222955642466,0.8879076086956521,0.04271100178154569,0.8879076086956521,0.043320171041105096 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,train,0.9924385633270322,0.0038716678669347424,0.9922570257611241,0.003958529125836061,0.9928558867493186,0.003684615396613088 +flat_mae,patch,logistic,aabc_sex,23,0.3593813663804626,test,0.8727272727272727,0.046382940722669186,0.8699763593380614,0.047326346775203074,0.8722826086956521,0.04707285219839602 +flat_mae,patch,logistic,aabc_sex,24,0.005994842503189409,train,0.9073724007561437,0.013061568781306697,0.9044834307992202,0.013544734120470909,0.9022978399132449,0.013842617775925863 +flat_mae,patch,logistic,aabc_sex,24,0.005994842503189409,test,0.8727272727272727,0.04437941597163565,0.8663658451926415,0.04788913918531563,0.8600543478260869,0.04862966265227339 +flat_mae,patch,logistic,aabc_sex,25,0.005994842503189409,train,0.9017013232514177,0.012631005392805109,0.8984254992319508,0.013153502267413297,0.8955713825141417,0.013468375583154385 +flat_mae,patch,logistic,aabc_sex,25,0.005994842503189409,test,0.9090909090909091,0.03594272762912531,0.9071259709557582,0.036687381133304796,0.9096467391304348,0.036402232410138714 +flat_mae,patch,logistic,aabc_sex,26,0.005994842503189409,train,0.9168241965973535,0.011402146950693507,0.914287818529975,0.011790413348210177,0.912292271168557,0.012022888426837021 +flat_mae,patch,logistic,aabc_sex,26,0.005994842503189409,test,0.8,0.04932115701122205,0.790003471017008,0.05312854744297095,0.7853260869565217,0.052592327630807345 +flat_mae,patch,logistic,aabc_sex,27,0.3593813663804626,train,0.994328922495274,0.003298069502824345,0.9941961885745005,0.003367000163889806,0.9950980392156863,0.0028507822990099323 +flat_mae,patch,logistic,aabc_sex,27,0.3593813663804626,test,0.8727272727272727,0.045270901752169065,0.8683760683760684,0.04748620593779692,0.8661684782608696,0.04820920863042269 +flat_mae,patch,logistic,aabc_sex,28,0.3593813663804626,train,0.994328922495274,0.0032022907492141664,0.9941893034853195,0.003278383920417173,0.9944898736774231,0.0031393921305393506 +flat_mae,patch,logistic,aabc_sex,28,0.3593813663804626,test,0.8363636363636363,0.048841913987716215,0.8281846581048247,0.05256912890279168,0.8226902173913043,0.05248386976246496 +flat_mae,patch,logistic,aabc_sex,29,0.3593813663804626,train,0.9905482041587902,0.004099405887029602,0.9903155058088658,0.004197381540231969,0.9906137342829509,0.004141407038678547 +flat_mae,patch,logistic,aabc_sex,29,0.3593813663804626,test,0.8909090909090909,0.04198896352437435,0.8891129032258065,0.04250001062274569,0.8940217391304348,0.041827137809489226 +flat_mae,patch,logistic,aabc_sex,30,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,30,21.54434690031882,test,0.8,0.056256790223767554,0.795677136102668,0.05750812365464856,0.7975543478260869,0.05733721169516163 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,train,0.9111531190926276,0.012319120730009528,0.9085047894870484,0.012730577313877266,0.9067821448459803,0.01296248559908238 +flat_mae,patch,logistic,aabc_sex,31,0.005994842503189409,test,0.8181818181818182,0.04979858937893953,0.8131793478260869,0.05103455820686764,0.8131793478260869,0.0506737469949763 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,train,0.9395085066162571,0.01021312687632478,0.9378268790033496,0.010525747756997432,0.9367654386119171,0.010773582539186291 +flat_mae,patch,logistic,aabc_sex,32,0.046415888336127774,test,0.8909090909090909,0.03954242412631178,0.8863636363636364,0.04209096636723131,0.8817934782608696,0.04296268390331083 +flat_mae,patch,logistic,aabc_sex,33,0.046415888336127774,train,0.9376181474480151,0.010349125843089503,0.9360823383385143,0.0105847702486143,0.9363477827603388,0.01055517935621188 +flat_mae,patch,logistic,aabc_sex,33,0.046415888336127774,test,0.8727272727272727,0.04666488937977293,0.8699763593380614,0.04750261277686299,0.8722826086956521,0.047004524479911346 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,train,0.9357277882797732,0.011062461963176767,0.9341847189695551,0.011314808580381966,0.9347137958322342,0.011319475063581911 +flat_mae,patch,logistic,aabc_sex,34,0.046415888336127774,test,0.8727272727272727,0.04569536208087729,0.8711943793911007,0.0458706476101865,0.8783967391304348,0.0441757392544989 +flat_mae,patch,logistic,aabc_sex,35,0.046415888336127774,train,0.9376181474480151,0.010545401447546884,0.9360045457044925,0.010833178775114673,0.9357396172220757,0.011000829083770968 +flat_mae,patch,logistic,aabc_sex,35,0.046415888336127774,test,0.9090909090909091,0.03970967365539765,0.9071259709557582,0.04031317116258569,0.9096467391304348,0.03948485852143157 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,train,0.9338374291115312,0.010006415157777762,0.9319544133158395,0.010313195219308898,0.9306471467510771,0.010508557328176477 +flat_mae,patch,logistic,aabc_sex,36,0.046415888336127774,test,0.9272727272727272,0.034722436598052644,0.9266666666666667,0.034603337730122016,0.9375,0.02983959395145148 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,train,0.941398865784499,0.010653505467923631,0.9398830580860384,0.010934803065751494,0.939615756616548,0.011051509154167938 +flat_mae,patch,logistic,aabc_sex,37,0.046415888336127774,test,0.8,0.052858319907759764,0.7931623931623932,0.05518175834953696,0.7914402173913043,0.054906864924772404 +flat_mae,patch,logistic,aabc_sex,38,0.046415888336127774,train,0.941398865784499,0.01007078552310155,0.9400272819365054,0.010291129864365329,0.9408320876930742,0.010295766853827465 +flat_mae,patch,logistic,aabc_sex,38,0.046415888336127774,test,0.8363636363636363,0.04548756618776111,0.8250265111346766,0.0512178589464446,0.8165760869565217,0.050683700036778336 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,train,0.9017013232514177,0.012696460532861106,0.8984254992319508,0.0132383157233643,0.8955713825141417,0.013569971050411423 +flat_mae,patch,logistic,aabc_sex,39,0.005994842503189409,test,0.9090909090909091,0.03634428576046057,0.905982905982906,0.0379298923903708,0.9035326086956521,0.038649464522213656 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,40,166.81005372000556,test,0.8545454545454545,0.046094677988277266,0.8533333333333333,0.04614379258788152,0.8627717391304348,0.04433271990944559 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,train,0.941398865784499,0.01043909598255936,0.9398830580860384,0.010702787950364523,0.939615756616548,0.010768434835047134 +flat_mae,patch,logistic,aabc_sex,41,0.046415888336127774,test,0.9090909090909091,0.03742895860358342,0.905982905982906,0.03902941314874531,0.9035326086956521,0.039631859598692476 +flat_mae,patch,logistic,aabc_sex,42,0.046415888336127774,train,0.943289224952741,0.010140064194534257,0.9417862487895061,0.010426741633006345,0.9412497435446525,0.010649535435037728 +flat_mae,patch,logistic,aabc_sex,42,0.046415888336127774,test,0.8181818181818182,0.05221549752533417,0.8176392572944298,0.0521501545233459,0.8315217391304348,0.04946974291745886 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,train,0.9395085066162571,0.01025561853956667,0.9379817696884434,0.01051421958023947,0.9379817696884434,0.010639791603076995 +flat_mae,patch,logistic,aabc_sex,43,0.046415888336127774,test,0.9272727272727272,0.03514832796418183,0.9252717391304348,0.03614303941971562,0.9252717391304348,0.036088564719109435 +flat_mae,patch,logistic,aabc_sex,44,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,44,2.782559402207126,test,0.8181818181818182,0.05037342865092254,0.8131793478260869,0.05195028169840239,0.8131793478260869,0.05188559240308793 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,train,0.9357277882797732,0.011081584053754184,0.9340244152947736,0.011387230440626991,0.9334974647557079,0.011516241414089582 +flat_mae,patch,logistic,aabc_sex,45,0.046415888336127774,test,0.9636363636363636,0.02440745042735182,0.9630376344086022,0.024547986237309635,0.96875,0.02097515271100547 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,train,0.9243856332703214,0.01177773500108804,0.9224772121105542,0.012073446264526043,0.9224772121105542,0.012158263396964868 +flat_mae,patch,logistic,aabc_sex,46,0.046415888336127774,test,0.8909090909090909,0.042569130941222055,0.8863636363636364,0.045142484136029004,0.8817934782608696,0.04606440104057794 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,train,0.9319470699432892,0.01119356927355103,0.9300552388787683,0.011542683297994046,0.9290131598229725,0.011792123481695733 +flat_mae,patch,logistic,aabc_sex,47,0.046415888336127774,test,0.9090909090909091,0.0362897248850333,0.905982905982906,0.037843405964720925,0.9035326086956521,0.03855999658591088 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,train,0.9376181474480151,0.010869091137849155,0.9360045457044925,0.011154030384100799,0.9357396172220757,0.011234062939857462 +flat_mae,patch,logistic,aabc_sex,48,0.046415888336127774,test,0.8909090909090909,0.04070817734165138,0.8891129032258065,0.041109118157654716,0.8940217391304348,0.03999867137296038 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,train,0.9035916824196597,0.012809044152239093,0.9004483312116013,0.013340541062934067,0.8978135349805094,0.013721744351702404 +flat_mae,patch,logistic,aabc_sex,49,0.005994842503189409,test,0.8909090909090909,0.0403326826439328,0.8891129032258065,0.040762237509092684,0.8940217391304348,0.039739083678492326 +flat_mae,patch,logistic,aabc_sex,50,0.005994842503189409,train,0.9092627599243857,0.011575668042803546,0.9063689194371516,0.012048210437358561,0.9039318268413494,0.012452967709837387 +flat_mae,patch,logistic,aabc_sex,50,0.005994842503189409,test,0.8909090909090909,0.04323965122450144,0.8879076086956521,0.04435367947873587,0.8879076086956521,0.044255169712690424 +flat_mae,patch,logistic,aabc_sex,51,0.005994842503189409,train,0.9035916824196597,0.01214364140142771,0.9008478594030804,0.012537695445377374,0.8996380315952988,0.01280485869928962 +flat_mae,patch,logistic,aabc_sex,51,0.005994842503189409,test,0.8909090909090909,0.03960484151053227,0.884453781512605,0.044044408183337456,0.8756793478260869,0.04552610818735284 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,train,0.9376181474480151,0.01076572475031532,0.9360045457044925,0.011057165351274663,0.9357396172220757,0.011246314913452318 +flat_mae,patch,logistic,aabc_sex,52,0.046415888336127774,test,0.8363636363636363,0.04984258194763398,0.8343927735028438,0.05008615117849434,0.8410326086956521,0.048906320945037544 +flat_mae,patch,logistic,aabc_sex,53,0.005994842503189409,train,0.8979206049149339,0.013906410743315228,0.8948077772867875,0.01435147840678079,0.8929115741961957,0.014439199163655684 +flat_mae,patch,logistic,aabc_sex,53,0.005994842503189409,test,0.8909090909090909,0.04114414893682378,0.8863636363636364,0.043654625187665996,0.8817934782608696,0.044559926842482014 +flat_mae,patch,logistic,aabc_sex,54,0.005994842503189409,train,0.9092627599243857,0.012368797284794812,0.9062389223679547,0.0129048700138671,0.9033236613030862,0.013303088215280033 +flat_mae,patch,logistic,aabc_sex,54,0.005994842503189409,test,0.8545454545454545,0.047307106380010025,0.8521505376344086,0.04786339862693188,0.8566576086956521,0.04702470759122328 +flat_mae,patch,logistic,aabc_sex,55,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,55,2.782559402207126,test,0.9090909090909091,0.03812525680715568,0.9079959852793577,0.038219740057464736,0.9157608695652174,0.03593299981583788 +flat_mae,patch,logistic,aabc_sex,56,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,56,21.54434690031882,test,0.7636363636363637,0.05350388570117096,0.7585275244849713,0.05496919596286845,0.7601902173913043,0.05485943260568396 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,train,0.9395085066162571,0.009588351918251943,0.9379817696884434,0.009834771679743363,0.9379817696884434,0.009960089599586849 +flat_mae,patch,logistic,aabc_sex,57,0.046415888336127774,test,0.8545454545454545,0.046975907311818825,0.8521505376344086,0.04765925698712997,0.8566576086956521,0.04721661379733962 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,train,0.9508506616257089,0.009028820049281412,0.9496706674473068,0.009229265120949164,0.9502183534101234,0.0092261108618172 +flat_mae,patch,logistic,aabc_sex,58,0.046415888336127774,test,0.8181818181818182,0.051609147757266854,0.8151881720430108,0.052246682630695165,0.8192934782608696,0.051672217432648465 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,train,0.9092627599243857,0.012773893634649612,0.9064958020327,0.013233961211174835,0.9045399923796125,0.013501883125809725 +flat_mae,patch,logistic,aabc_sex,59,0.005994842503189409,test,0.8727272727272727,0.04256520132263399,0.8711943793911007,0.04277798936421392,0.8783967391304348,0.04139231675637766 +flat_mae,patch,logistic,aabc_sex,60,0.005994842503189409,train,0.9092627599243857,0.011928666043056762,0.9064958020327,0.012359095444912711,0.9045399923796125,0.012648897339608332 +flat_mae,patch,logistic,aabc_sex,60,0.005994842503189409,test,0.8181818181818182,0.050476132973911514,0.8106060606060606,0.053976134904533,0.8070652173913043,0.054044860217992936 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,train,0.9338374291115312,0.01090329016465245,0.9322888667025062,0.01113982288903905,0.9330798089041297,0.011111655835811597 +flat_mae,patch,logistic,aabc_sex,61,0.046415888336127774,test,0.9454545454545454,0.030362634714017494,0.9442755825734549,0.0309028386283272,0.9470108695652174,0.029820141915815414 +flat_mae,patch,logistic,aabc_sex,62,0.3593813663804626,train,0.9886578449905482,0.004794527763107694,0.9883715818165831,0.004917707790313068,0.9883715818165831,0.00501332980669672 +flat_mae,patch,logistic,aabc_sex,62,0.3593813663804626,test,0.9272727272727272,0.03247325663825874,0.9242424242424243,0.03456102242110411,0.9191576086956521,0.036403069894655846 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,train,0.9035916824196597,0.013071803440883514,0.900308545034642,0.013685529443046707,0.8972053694422463,0.014154644988109819 +flat_mae,patch,logistic,aabc_sex,63,0.005994842503189409,test,0.9090909090909091,0.03740436179099619,0.905982905982906,0.03918052192591314,0.9035326086956521,0.04020592374697821 +flat_mae,patch,logistic,aabc_sex,64,0.046415888336127774,train,0.9357277882797732,0.01124707405939567,0.9337678597731625,0.011643260861567948,0.9316729681409186,0.011976204213652551 +flat_mae,patch,logistic,aabc_sex,64,0.046415888336127774,test,0.8727272727272727,0.043067366027294086,0.8711943793911007,0.043253468635092135,0.8783967391304348,0.04168359260372007 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,train,0.9035916824196597,0.012571410936169989,0.900974508616418,0.012992145315596596,0.9002461971335619,0.013338580785946892 +flat_mae,patch,logistic,aabc_sex,65,0.005994842503189409,test,0.8727272727272727,0.0450683081188346,0.8663658451926415,0.04847370714574701,0.8600543478260869,0.049097999420360895 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,train,0.941398865784499,0.010126027865642187,0.939956136014968,0.010359116094821649,0.9402239221548111,0.010367359576338303 +flat_mae,patch,logistic,aabc_sex,66,0.046415888336127774,test,0.8545454545454545,0.04570796266778544,0.8484848484848485,0.04839397937338596,0.8444293478260869,0.048718197568502125 +flat_mae,patch,logistic,aabc_sex,67,0.005994842503189409,train,0.9017013232514177,0.012764303106427743,0.8985663293902475,0.013269010350432623,0.8961795480524049,0.013576274168806869 +flat_mae,patch,logistic,aabc_sex,67,0.005994842503189409,test,0.9090909090909091,0.03910915430450041,0.9071259709557582,0.03983721099297673,0.9096467391304348,0.0393662235498639 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,68,21.54434690031882,test,0.8909090909090909,0.042623331987915555,0.8879076086956521,0.043848693303891344,0.8879076086956521,0.04404511613852675 +flat_mae,patch,logistic,aabc_sex,69,0.3593813663804626,train,0.9905482041587902,0.004302003956151526,0.9903155058088658,0.004406041620427161,0.9906137342829509,0.0043639358203652655 +flat_mae,patch,logistic,aabc_sex,69,0.3593813663804626,test,0.9636363636363636,0.024582356099547478,0.9621212121212122,0.026176919893290854,0.9565217391304348,0.029391947510328503 +flat_mae,patch,logistic,aabc_sex,70,0.046415888336127774,train,0.9281663516068053,0.010576162715483568,0.9260738452486026,0.010921323338928821,0.9245288548902371,0.011184477821342461 +flat_mae,patch,logistic,aabc_sex,70,0.046415888336127774,test,0.9090909090909091,0.03879117220866514,0.9071259709557582,0.03954961183733501,0.9096467391304348,0.039159010361722014 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,train,0.9035916824196597,0.012281472500146124,0.9007179630604141,0.01269323783608969,0.8990298660570357,0.01291757168194687 +flat_mae,patch,logistic,aabc_sex,71,0.005994842503189409,test,0.8727272727272727,0.04018305222292618,0.8663658451926415,0.04334822900416504,0.8600543478260869,0.04369894171166661 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,train,0.9073724007561437,0.012240965875470999,0.9046113762737312,0.012675414165854881,0.9029060054515079,0.012973368541739255 +flat_mae,patch,logistic,aabc_sex,72,0.005994842503189409,test,0.8909090909090909,0.043044639523819185,0.8879076086956521,0.044321635917092254,0.8879076086956521,0.04440219312103784 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,train,0.9357277882797732,0.010426338327321342,0.9341847189695551,0.010672808565927618,0.9347137958322342,0.010770578381644327 +flat_mae,patch,logistic,aabc_sex,73,0.046415888336127774,test,0.9818181818181818,0.01793059161607557,0.9814251941911516,0.01815942922178831,0.984375,0.015409102170064937 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,train,0.9376181474480151,0.010055187001691609,0.9358427325549344,0.010391222964911719,0.9345232861455495,0.010779585938433714 +flat_mae,patch,logistic,aabc_sex,74,0.046415888336127774,test,0.8545454545454545,0.047153682274729235,0.8505434782608696,0.048576365485099963,0.8505434782608696,0.04884489657615549 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,train,0.9338374291115312,0.0110304127514518,0.9322888667025062,0.011275049061486074,0.9330798089041297,0.011293368307295685 +flat_mae,patch,logistic,aabc_sex,75,0.046415888336127774,test,0.8727272727272727,0.04416795891867,0.8683760683760684,0.046163579405408335,0.8661684782608696,0.046767530710494956 +flat_mae,patch,logistic,aabc_sex,76,0.005994842503189409,train,0.9111531190926276,0.011962935434685951,0.9083820662768032,0.012443025104447059,0.906173979307717,0.01288283206924853 +flat_mae,patch,logistic,aabc_sex,76,0.005994842503189409,test,0.8363636363636363,0.051020086791364286,0.8307692307692308,0.0531809733567457,0.8288043478260869,0.053033020354609446 +flat_mae,patch,logistic,aabc_sex,77,0.046415888336127774,train,0.9395085066162571,0.010731068675604687,0.9379817696884434,0.011003156737524904,0.9379817696884434,0.01112110798799719 +flat_mae,patch,logistic,aabc_sex,77,0.046415888336127774,test,0.9090909090909091,0.035850857269278086,0.9027925061859314,0.04062160310552108,0.8913043478260869,0.04286515543065857 +flat_mae,patch,logistic,aabc_sex,78,0.046415888336127774,train,0.9262759924385633,0.010559553082000708,0.9243690085598548,0.010861717871011688,0.9241111990386588,0.011100718672687812 +flat_mae,patch,logistic,aabc_sex,78,0.046415888336127774,test,0.9818181818181818,0.016437449682542477,0.9811965811965813,0.017197400283794628,0.9782608695652174,0.01965347244651818 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,train,0.9319470699432892,0.010660024146021336,0.9301434985474073,0.010965607201998944,0.9296213253612357,0.011121650242493807 +flat_mae,patch,logistic,aabc_sex,79,0.046415888336127774,test,0.9454545454545454,0.030597358498854744,0.9435897435897436,0.03195122551388159,0.9408967391304348,0.03317717016943012 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,train,0.9338374291115312,0.010669867036919425,0.9321260333229466,0.010961914178000015,0.9318634778276034,0.011124011187302055 +flat_mae,patch,logistic,aabc_sex,80,0.046415888336127774,test,0.8363636363636363,0.04922377978038426,0.8281846581048247,0.05332793318649528,0.8226902173913043,0.05346627214339547 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,train,0.9262759924385633,0.01122154142641439,0.9244609453091532,0.011480131483197872,0.9247193645769219,0.01148960903956374 +flat_mae,patch,logistic,aabc_sex,81,0.046415888336127774,test,0.9454545454545454,0.030537141725993103,0.9435897435897436,0.031940337009833564,0.9408967391304348,0.03332690663410102 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,train,0.9319470699432892,0.010321687192338025,0.930313231850117,0.010575843162753435,0.930837656437762,0.010717000936821522 +flat_mae,patch,logistic,aabc_sex,82,0.046415888336127774,test,0.9272727272727272,0.031694742374956716,0.9229691876750701,0.03495757395155499,0.9130434782608696,0.037895887622230846 +flat_mae,patch,logistic,aabc_sex,83,0.046415888336127774,train,0.9376181474480151,0.010418606129220803,0.9360823383385143,0.010677341848611502,0.9363477827603388,0.010763357600007264 +flat_mae,patch,logistic,aabc_sex,83,0.046415888336127774,test,0.9090909090909091,0.037805924587084205,0.9045470322804582,0.04081315496066223,0.8974184782608696,0.04248443043996943 +flat_mae,patch,logistic,aabc_sex,84,0.3593813663804626,train,0.994328922495274,0.003529002369842171,0.9941822314276811,0.003623236306305636,0.99388170813916,0.003806163226005856 +flat_mae,patch,logistic,aabc_sex,84,0.3593813663804626,test,0.8545454545454545,0.04749463997596232,0.8505434782608696,0.04891918060707567,0.8505434782608696,0.048979290434044635 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,train,0.943289224952741,0.010161858462516046,0.9419276932084308,0.010415249379670916,0.9424660746211788,0.010575216093054248 +flat_mae,patch,logistic,aabc_sex,85,0.046415888336127774,test,0.9090909090909091,0.04001817768782764,0.905982905982906,0.0417243088389765,0.9035326086956521,0.04260591396130107 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,train,0.9300567107750473,0.011648934950088473,0.9283347429856068,0.011924782605754778,0.9285955039713942,0.011991143546546193 +flat_mae,patch,logistic,aabc_sex,86,0.046415888336127774,test,0.9090909090909091,0.039569184103017754,0.905982905982906,0.04134714715820922,0.9035326086956521,0.04204180872780416 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,train,0.941398865784499,0.010169173748403502,0.939956136014968,0.01041088804379122,0.9402239221548111,0.010478444479591948 +flat_mae,patch,logistic,aabc_sex,87,0.046415888336127774,test,0.8909090909090909,0.04308524703882634,0.8863636363636364,0.04553691726746336,0.8817934782608696,0.046210066065718695 +flat_mae,patch,logistic,aabc_sex,88,0.046415888336127774,train,0.9357277882797732,0.010856587962886398,0.9341847189695551,0.011089995583264033,0.9347137958322342,0.011034791753333108 +flat_mae,patch,logistic,aabc_sex,88,0.046415888336127774,test,0.9272727272727272,0.033914700973895685,0.9229691876750701,0.03753662222269876,0.9130434782608696,0.040550185947049185 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,train,0.9357277882797732,0.010970971696933427,0.9341056302939711,0.011245992749244572,0.9341056302939711,0.011348188764871864 +flat_mae,patch,logistic,aabc_sex,89,0.046415888336127774,test,0.9090909090909091,0.035995867531410375,0.9045470322804582,0.03899476999428076,0.8974184782608696,0.04099145377092954 +flat_mae,patch,logistic,aabc_sex,90,0.3593813663804626,train,0.9924385633270322,0.0038365834783944818,0.9922477212110554,0.003933727922664302,0.9922477212110554,0.00398237402230944 +flat_mae,patch,logistic,aabc_sex,90,0.3593813663804626,test,0.7818181818181819,0.054460770626112896,0.76890756302521,0.060433565984610214,0.7635869565217391,0.05920365428744346 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,train,0.9357277882797732,0.011007521668612448,0.9339410589410589,0.011341597763121148,0.9328892992174448,0.011580199925810985 +flat_mae,patch,logistic,aabc_sex,91,0.046415888336127774,test,0.8363636363636363,0.05041677537952441,0.8343927735028438,0.050643544090660596,0.8410326086956521,0.0496379164925528 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,train,0.8998109640831758,0.013252924577720326,0.8966861598440545,0.013737051276212936,0.8945455611243003,0.013981648336321805 +flat_mae,patch,logistic,aabc_sex,92,0.005994842503189409,test,0.9090909090909091,0.038584457111361735,0.905982905982906,0.04045763051581,0.9035326086956521,0.04149772317483288 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,train,0.9300567107750473,0.011298798038334602,0.9282475209414007,0.011604287911305987,0.9279873384331311,0.011758492417544513 +flat_mae,patch,logistic,aabc_sex,93,0.046415888336127774,test,0.8727272727272727,0.0460062374499102,0.8663658451926415,0.049532741904646585,0.8600543478260869,0.05028972597948847 +flat_mae,patch,logistic,aabc_sex,94,0.005994842503189409,train,0.9035916824196597,0.012988982896862263,0.9004483312116013,0.013528553169459534,0.8978135349805094,0.013882974922399666 +flat_mae,patch,logistic,aabc_sex,94,0.005994842503189409,test,0.9272727272727272,0.03310688924834951,0.9252717391304348,0.03424716454738234,0.9252717391304348,0.03467743620934805 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,train,0.9300567107750473,0.011004082567631709,0.9281579768393621,0.011331102015672733,0.9273791728948679,0.01157540021927881 +flat_mae,patch,logistic,aabc_sex,95,0.046415888336127774,test,0.9272727272727272,0.03445891553000664,0.9260752688172043,0.0347387757227433,0.9313858695652174,0.03281576577050908 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,train,0.8998109640831758,0.012785812008573948,0.8966861598440545,0.013256361433048149,0.8945455611243003,0.013505606222781387 +flat_mae,patch,logistic,aabc_sex,96,0.005994842503189409,test,0.9454545454545454,0.030538419103193843,0.9435897435897436,0.0318544159850085,0.9408967391304348,0.0330751371005418 +flat_mae,patch,logistic,aabc_sex,97,0.046415888336127774,train,0.9357277882797732,0.011447373331691645,0.9341847189695551,0.011712766283621891,0.9347137958322342,0.011764488738251838 +flat_mae,patch,logistic,aabc_sex,97,0.046415888336127774,test,0.8545454545454545,0.04834141663194687,0.8484848484848485,0.05100471362995338,0.8444293478260869,0.05114326034123909 +flat_mae,patch,logistic,aabc_sex,98,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,aabc_sex,98,2.782559402207126,test,0.8727272727272727,0.04234207801050786,0.8639095086603039,0.047535770918714505,0.8539402173913043,0.048212994543474746 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,train,0.9224952741020794,0.012435825739734323,0.9204904961783089,0.012746858553547532,0.9202350596441865,0.012780711473807887 +flat_mae,patch,logistic,aabc_sex,99,0.046415888336127774,test,0.9272727272727272,0.0348585998495504,0.9229691876750701,0.038754339375731035,0.9130434782608696,0.041678760689679815 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,train,0.9376181474480151,0.010515155795279913,0.9360045457044925,0.010797352320460273,0.9357396172220757,0.01094112891452016 +flat_mae,patch,logistic,aabc_sex,100,0.046415888336127774,test,0.9272727272727272,0.03316417463678003,0.9260752688172043,0.033476922223307115,0.9313858695652174,0.031864322199624665 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d6a183d790d502da3a2d8f17bf1b3807f66f67ea --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:49:01 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_sex patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic +model: flat_mae +representation: patch +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_sex__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:19:56 time: 5.0689 data: 4.1230 max mem: 3207 +extract (train) [ 20/236] eta: 0:01:40 time: 0.2355 data: 0.0827 max mem: 3395 +extract (train) [ 40/236] eta: 0:01:05 time: 0.1977 data: 0.0623 max mem: 3395 +extract (train) [ 60/236] eta: 0:00:50 time: 0.1966 data: 0.0633 max mem: 3395 +extract (train) [ 80/236] eta: 0:00:42 time: 0.2218 data: 0.0761 max mem: 3395 +extract (train) [100/236] eta: 0:00:35 time: 0.2100 data: 0.0693 max mem: 3395 +extract (train) [120/236] eta: 0:00:29 time: 0.2229 data: 0.0774 max mem: 3395 +extract (train) [140/236] eta: 0:00:23 time: 0.1882 data: 0.0593 max mem: 3395 +extract (train) [160/236] eta: 0:00:18 time: 0.2075 data: 0.0668 max mem: 3395 +extract (train) [180/236] eta: 0:00:13 time: 0.2161 data: 0.0753 max mem: 3395 +extract (train) [200/236] eta: 0:00:08 time: 0.2257 data: 0.0779 max mem: 3395 +extract (train) [220/236] eta: 0:00:03 time: 0.2010 data: 0.0635 max mem: 3395 +extract (train) [235/236] eta: 0:00:00 time: 0.1807 data: 0.0563 max mem: 3395 +extract (train) Total time: 0:00:54 (0.2320 s / it) +extract (validation) [ 0/29] eta: 0:02:06 time: 4.3502 data: 4.1801 max mem: 3395 +extract (validation) [20/29] eta: 0:00:03 time: 0.1979 data: 0.0641 max mem: 3395 +extract (validation) [28/29] eta: 0:00:00 time: 0.1660 data: 0.0457 max mem: 3395 +extract (validation) Total time: 0:00:09 (0.3431 s / it) +extract (test) [ 0/28] eta: 0:01:59 time: 4.2602 data: 4.0910 max mem: 3395 +extract (test) [20/28] eta: 0:00:03 time: 0.1941 data: 0.0605 max mem: 3395 +extract (test) [27/28] eta: 0:00:00 time: 0.1676 data: 0.0487 max mem: 3395 +extract (test) Total time: 0:00:09 (0.3431 s / it) +feature extraction time: 0:01:14 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | train | 0.9017 | 0.012736 | 0.8987 | 0.013216 | 0.89638 | 0.013511 | +| flat_mae | patch | logistic | aabc_sex | | 0.0059948 | test | 0.90909 | 0.038276 | 0.90713 | 0.038642 | 0.91667 | 0.035933 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05348713910452469, "f1": 0.8131793478260869, "f1_std": 0.054979212146414026, "bacc": 0.8131793478260869, "bacc_std": 0.054957623048201634} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0412584837256393, "f1": 0.8879076086956521, "f1_std": 0.042341836210017005, "bacc": 0.8879076086956521, "bacc_std": 0.04225670370228804} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05210369825550606, "f1": 0.76890756302521, "f1_std": 0.05680169055069752, "bacc": 0.7635869565217391, "bacc_std": 0.05592744453386241} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05247810720231044, "f1": 0.8166666666666667, "f1_std": 0.052501969623929716, "bacc": 0.8254076086956521, "bacc_std": 0.05071315102699185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05208099223388619, "f1": 0.8131793478260869, "f1_std": 0.05383167560013537, "bacc": 0.8131793478260869, "bacc_std": 0.053847858227065365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03719932461841365, "f1": 0.905982905982906, "f1_std": 0.038818152031709165, "bacc": 0.9035326086956521, "bacc_std": 0.03987086821319644} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0440026295232305, "f1": 0.8683760683760684, "f1_std": 0.04617714443188985, "bacc": 0.8661684782608696, "bacc_std": 0.046897032550463416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04811857255565034, "f1": 0.8166666666666667, "f1_std": 0.0483682911523126, "bacc": 0.8254076086956521, "bacc_std": 0.04795113367465533} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04570410040016571, "f1": 0.8484848484848485, "f1_std": 0.048505118311174523, "bacc": 0.8444293478260869, "bacc_std": 0.04918904563182276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042331333763322626, "f1": 0.8891129032258065, "f1_std": 0.0426952658338831, "bacc": 0.8940217391304348, "bacc_std": 0.04145416230090705} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029653558871053046, "f1": 0.9435897435897436, "f1_std": 0.03095474923509793, "bacc": 0.9408967391304348, "bacc_std": 0.03215051798878318} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04862778174073737, "f1": 0.8307692307692308, "f1_std": 0.05108891059257972, "bacc": 0.8288043478260869, "bacc_std": 0.05152825764450441} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04000692502038587, "f1": 0.8863636363636364, "f1_std": 0.042140842076823906, "bacc": 0.8817934782608696, "bacc_std": 0.042894589293149245} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03980507879053453, "f1": 0.905982905982906, "f1_std": 0.04162782937675307, "bacc": 0.9035326086956521, "bacc_std": 0.04261664455839096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.052728163001888435, "f1": 0.8131793478260869, "f1_std": 0.054402197084756125, "bacc": 0.8131793478260869, "bacc_std": 0.0544089271173042} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04436475408428043, "f1": 0.8879076086956521, "f1_std": 0.04578575195712156, "bacc": 0.8879076086956521, "bacc_std": 0.04599213008069578} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03463910750286505, "f1": 0.9242424242424243, "f1_std": 0.03688055219883087, "bacc": 0.9191576086956521, "bacc_std": 0.03837289279491788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038108587782938345, "f1": 0.9071259709557582, "f1_std": 0.038897029534429535, "bacc": 0.9096467391304348, "bacc_std": 0.03852450096659667} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04679494215799657, "f1": 0.8307692307692308, "f1_std": 0.0488763400887655, "bacc": 0.8288043478260869, "bacc_std": 0.04913731440732054} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.0478800705620281, "f1": 0.8250265111346766, "f1_std": 0.05352598067489189, "bacc": 0.8165760869565217, "bacc_std": 0.052746288933709404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.055858842164279436, "f1": 0.795677136102668, "f1_std": 0.05714775522539658, "bacc": 0.7975543478260869, "bacc_std": 0.05715501169926794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041266222955642466, "f1": 0.8879076086956521, "f1_std": 0.04271100178154569, "bacc": 0.8879076086956521, "bacc_std": 0.043320171041105096} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046382940722669186, "f1": 0.8699763593380614, "f1_std": 0.047326346775203074, "bacc": 0.8722826086956521, "bacc_std": 0.04707285219839602} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04437941597163565, "f1": 0.8663658451926415, "f1_std": 0.04788913918531563, "bacc": 0.8600543478260869, "bacc_std": 0.04862966265227339} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03594272762912531, "f1": 0.9071259709557582, "f1_std": 0.036687381133304796, "bacc": 0.9096467391304348, "bacc_std": 0.036402232410138714} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.04932115701122205, "f1": 0.790003471017008, "f1_std": 0.05312854744297095, "bacc": 0.7853260869565217, "bacc_std": 0.052592327630807345} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045270901752169065, "f1": 0.8683760683760684, "f1_std": 0.04748620593779692, "bacc": 0.8661684782608696, "bacc_std": 0.04820920863042269} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048841913987716215, "f1": 0.8281846581048247, "f1_std": 0.05256912890279168, "bacc": 0.8226902173913043, "bacc_std": 0.05248386976246496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04198896352437435, "f1": 0.8891129032258065, "f1_std": 0.04250001062274569, "bacc": 0.8940217391304348, "bacc_std": 0.041827137809489226} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 21.54434690031882, "split": "test", "acc": 0.8, "acc_std": 0.056256790223767554, "f1": 0.795677136102668, "f1_std": 0.05750812365464856, "bacc": 0.7975543478260869, "bacc_std": 0.05733721169516163} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.04979858937893953, "f1": 0.8131793478260869, "f1_std": 0.05103455820686764, "bacc": 0.8131793478260869, "bacc_std": 0.0506737469949763} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03954242412631178, "f1": 0.8863636363636364, "f1_std": 0.04209096636723131, "bacc": 0.8817934782608696, "bacc_std": 0.04296268390331083} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04666488937977293, "f1": 0.8699763593380614, "f1_std": 0.04750261277686299, "bacc": 0.8722826086956521, "bacc_std": 0.047004524479911346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04569536208087729, "f1": 0.8711943793911007, "f1_std": 0.0458706476101865, "bacc": 0.8783967391304348, "bacc_std": 0.0441757392544989} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03970967365539765, "f1": 0.9071259709557582, "f1_std": 0.04031317116258569, "bacc": 0.9096467391304348, "bacc_std": 0.03948485852143157} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034722436598052644, "f1": 0.9266666666666667, "f1_std": 0.034603337730122016, "bacc": 0.9375, "bacc_std": 0.02983959395145148} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.052858319907759764, "f1": 0.7931623931623932, "f1_std": 0.05518175834953696, "bacc": 0.7914402173913043, "bacc_std": 0.054906864924772404} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04548756618776111, "f1": 0.8250265111346766, "f1_std": 0.0512178589464446, "bacc": 0.8165760869565217, "bacc_std": 0.050683700036778336} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03634428576046057, "f1": 0.905982905982906, "f1_std": 0.0379298923903708, "bacc": 0.9035326086956521, "bacc_std": 0.038649464522213656} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046094677988277266, "f1": 0.8533333333333333, "f1_std": 0.04614379258788152, "bacc": 0.8627717391304348, "bacc_std": 0.04433271990944559} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03742895860358342, "f1": 0.905982905982906, "f1_std": 0.03902941314874531, "bacc": 0.9035326086956521, "bacc_std": 0.039631859598692476} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05221549752533417, "f1": 0.8176392572944298, "f1_std": 0.0521501545233459, "bacc": 0.8315217391304348, "bacc_std": 0.04946974291745886} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03514832796418183, "f1": 0.9252717391304348, "f1_std": 0.03614303941971562, "bacc": 0.9252717391304348, "bacc_std": 0.036088564719109435} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 2.782559402207126, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05037342865092254, "f1": 0.8131793478260869, "f1_std": 0.05195028169840239, "bacc": 0.8131793478260869, "bacc_std": 0.05188559240308793} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.02440745042735182, "f1": 0.9630376344086022, "f1_std": 0.024547986237309635, "bacc": 0.96875, "bacc_std": 0.02097515271100547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042569130941222055, "f1": 0.8863636363636364, "f1_std": 0.045142484136029004, "bacc": 0.8817934782608696, "bacc_std": 0.04606440104057794} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0362897248850333, "f1": 0.905982905982906, "f1_std": 0.037843405964720925, "bacc": 0.9035326086956521, "bacc_std": 0.03855999658591088} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04070817734165138, "f1": 0.8891129032258065, "f1_std": 0.041109118157654716, "bacc": 0.8940217391304348, "bacc_std": 0.03999867137296038} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0403326826439328, "f1": 0.8891129032258065, "f1_std": 0.040762237509092684, "bacc": 0.8940217391304348, "bacc_std": 0.039739083678492326} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04323965122450144, "f1": 0.8879076086956521, "f1_std": 0.04435367947873587, "bacc": 0.8879076086956521, "bacc_std": 0.044255169712690424} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03960484151053227, "f1": 0.884453781512605, "f1_std": 0.044044408183337456, "bacc": 0.8756793478260869, "bacc_std": 0.04552610818735284} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04984258194763398, "f1": 0.8343927735028438, "f1_std": 0.05008615117849434, "bacc": 0.8410326086956521, "bacc_std": 0.048906320945037544} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04114414893682378, "f1": 0.8863636363636364, "f1_std": 0.043654625187665996, "bacc": 0.8817934782608696, "bacc_std": 0.044559926842482014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047307106380010025, "f1": 0.8521505376344086, "f1_std": 0.04786339862693188, "bacc": 0.8566576086956521, "bacc_std": 0.04702470759122328} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03812525680715568, "f1": 0.9079959852793577, "f1_std": 0.038219740057464736, "bacc": 0.9157608695652174, "bacc_std": 0.03593299981583788} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 21.54434690031882, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05350388570117096, "f1": 0.7585275244849713, "f1_std": 0.05496919596286845, "bacc": 0.7601902173913043, "bacc_std": 0.05485943260568396} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.046975907311818825, "f1": 0.8521505376344086, "f1_std": 0.04765925698712997, "bacc": 0.8566576086956521, "bacc_std": 0.04721661379733962} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.051609147757266854, "f1": 0.8151881720430108, "f1_std": 0.052246682630695165, "bacc": 0.8192934782608696, "bacc_std": 0.051672217432648465} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04256520132263399, "f1": 0.8711943793911007, "f1_std": 0.04277798936421392, "bacc": 0.8783967391304348, "bacc_std": 0.04139231675637766} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.050476132973911514, "f1": 0.8106060606060606, "f1_std": 0.053976134904533, "bacc": 0.8070652173913043, "bacc_std": 0.054044860217992936} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030362634714017494, "f1": 0.9442755825734549, "f1_std": 0.0309028386283272, "bacc": 0.9470108695652174, "bacc_std": 0.029820141915815414} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03247325663825874, "f1": 0.9242424242424243, "f1_std": 0.03456102242110411, "bacc": 0.9191576086956521, "bacc_std": 0.036403069894655846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03740436179099619, "f1": 0.905982905982906, "f1_std": 0.03918052192591314, "bacc": 0.9035326086956521, "bacc_std": 0.04020592374697821} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.043067366027294086, "f1": 0.8711943793911007, "f1_std": 0.043253468635092135, "bacc": 0.8783967391304348, "bacc_std": 0.04168359260372007} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0450683081188346, "f1": 0.8663658451926415, "f1_std": 0.04847370714574701, "bacc": 0.8600543478260869, "bacc_std": 0.049097999420360895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04570796266778544, "f1": 0.8484848484848485, "f1_std": 0.04839397937338596, "bacc": 0.8444293478260869, "bacc_std": 0.048718197568502125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03910915430450041, "f1": 0.9071259709557582, "f1_std": 0.03983721099297673, "bacc": 0.9096467391304348, "bacc_std": 0.0393662235498639} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.042623331987915555, "f1": 0.8879076086956521, "f1_std": 0.043848693303891344, "bacc": 0.8879076086956521, "bacc_std": 0.04404511613852675} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.024582356099547478, "f1": 0.9621212121212122, "f1_std": 0.026176919893290854, "bacc": 0.9565217391304348, "bacc_std": 0.029391947510328503} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03879117220866514, "f1": 0.9071259709557582, "f1_std": 0.03954961183733501, "bacc": 0.9096467391304348, "bacc_std": 0.039159010361722014} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04018305222292618, "f1": 0.8663658451926415, "f1_std": 0.04334822900416504, "bacc": 0.8600543478260869, "bacc_std": 0.04369894171166661} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.043044639523819185, "f1": 0.8879076086956521, "f1_std": 0.044321635917092254, "bacc": 0.8879076086956521, "bacc_std": 0.04440219312103784} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.01793059161607557, "f1": 0.9814251941911516, "f1_std": 0.01815942922178831, "bacc": 0.984375, "bacc_std": 0.015409102170064937} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047153682274729235, "f1": 0.8505434782608696, "f1_std": 0.048576365485099963, "bacc": 0.8505434782608696, "bacc_std": 0.04884489657615549} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04416795891867, "f1": 0.8683760683760684, "f1_std": 0.046163579405408335, "bacc": 0.8661684782608696, "bacc_std": 0.046767530710494956} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.051020086791364286, "f1": 0.8307692307692308, "f1_std": 0.0531809733567457, "bacc": 0.8288043478260869, "bacc_std": 0.053033020354609446} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.035850857269278086, "f1": 0.9027925061859314, "f1_std": 0.04062160310552108, "bacc": 0.8913043478260869, "bacc_std": 0.04286515543065857} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.046415888336127774, "split": "test", "acc": 0.9818181818181818, "acc_std": 0.016437449682542477, "f1": 0.9811965811965813, "f1_std": 0.017197400283794628, "bacc": 0.9782608695652174, "bacc_std": 0.01965347244651818} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030597358498854744, "f1": 0.9435897435897436, "f1_std": 0.03195122551388159, "bacc": 0.9408967391304348, "bacc_std": 0.03317717016943012} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04922377978038426, "f1": 0.8281846581048247, "f1_std": 0.05332793318649528, "bacc": 0.8226902173913043, "bacc_std": 0.05346627214339547} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030537141725993103, "f1": 0.9435897435897436, "f1_std": 0.031940337009833564, "bacc": 0.9408967391304348, "bacc_std": 0.03332690663410102} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.031694742374956716, "f1": 0.9229691876750701, "f1_std": 0.03495757395155499, "bacc": 0.9130434782608696, "bacc_std": 0.037895887622230846} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.037805924587084205, "f1": 0.9045470322804582, "f1_std": 0.04081315496066223, "bacc": 0.8974184782608696, "bacc_std": 0.04248443043996943} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04749463997596232, "f1": 0.8505434782608696, "f1_std": 0.04891918060707567, "bacc": 0.8505434782608696, "bacc_std": 0.048979290434044635} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.04001817768782764, "f1": 0.905982905982906, "f1_std": 0.0417243088389765, "bacc": 0.9035326086956521, "bacc_std": 0.04260591396130107} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039569184103017754, "f1": 0.905982905982906, "f1_std": 0.04134714715820922, "bacc": 0.9035326086956521, "bacc_std": 0.04204180872780416} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04308524703882634, "f1": 0.8863636363636364, "f1_std": 0.04553691726746336, "bacc": 0.8817934782608696, "bacc_std": 0.046210066065718695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.033914700973895685, "f1": 0.9229691876750701, "f1_std": 0.03753662222269876, "bacc": 0.9130434782608696, "bacc_std": 0.040550185947049185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.035995867531410375, "f1": 0.9045470322804582, "f1_std": 0.03899476999428076, "bacc": 0.8974184782608696, "bacc_std": 0.04099145377092954} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.054460770626112896, "f1": 0.76890756302521, "f1_std": 0.060433565984610214, "bacc": 0.7635869565217391, "bacc_std": 0.05920365428744346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05041677537952441, "f1": 0.8343927735028438, "f1_std": 0.050643544090660596, "bacc": 0.8410326086956521, "bacc_std": 0.0496379164925528} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038584457111361735, "f1": 0.905982905982906, "f1_std": 0.04045763051581, "bacc": 0.9035326086956521, "bacc_std": 0.04149772317483288} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.0460062374499102, "f1": 0.8663658451926415, "f1_std": 0.049532741904646585, "bacc": 0.8600543478260869, "bacc_std": 0.05028972597948847} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03310688924834951, "f1": 0.9252717391304348, "f1_std": 0.03424716454738234, "bacc": 0.9252717391304348, "bacc_std": 0.03467743620934805} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03445891553000664, "f1": 0.9260752688172043, "f1_std": 0.0347387757227433, "bacc": 0.9313858695652174, "bacc_std": 0.03281576577050908} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.005994842503189409, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030538419103193843, "f1": 0.9435897435897436, "f1_std": 0.0318544159850085, "bacc": 0.9408967391304348, "bacc_std": 0.0330751371005418} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 0.046415888336127774, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04834141663194687, "f1": 0.8484848484848485, "f1_std": 0.05100471362995338, "bacc": 0.8444293478260869, "bacc_std": 0.05114326034123909} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04234207801050786, "f1": 0.8639095086603039, "f1_std": 0.047535770918714505, "bacc": 0.8539402173913043, "bacc_std": 0.048212994543474746} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.0348585998495504, "f1": 0.9229691876750701, "f1_std": 0.038754339375731035, "bacc": 0.9130434782608696, "bacc_std": 0.041678760689679815} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03316417463678003, "f1": 0.9260752688172043, "f1_std": 0.033476922223307115, "bacc": 0.9313858695652174, "bacc_std": 0.031864322199624665} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | aabc_sex | train | 100 | 5.8328 | 28.692 | 0.94295 | 0.031263 | 0.94138 | 0.032202 | 0.94086 | 0.03284 | +| flat_mae | patch | logistic | aabc_sex | test | 100 | 5.8328 | 28.692 | 0.87927 | 0.046626 | 0.87536 | 0.048169 | 0.87461 | 0.048118 | + + +done! total time: 0:05:05 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3ab2db0421df29636d048ced1b4d031ca102d544 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_sex reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..b5ea09d8164f7e09ad730de288e95c2ebc80caed --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,aabc_sex,,0.3593813663804626,train,0.996219281663516,0.002634984385757066,0.9961285128805621,0.002698474195501166,0.9961285128805621,0.002737409940367591 +flat_mae,reg,logistic,aabc_sex,,0.3593813663804626,test,0.9272727272727272,0.0361240104671589,0.9242424242424243,0.03779704010033197,0.9242424242424243,0.03823911946052917 +flat_mae,reg,logistic,aabc_sex,1,0.3593813663804626,train,0.996219281663516,0.002830745791657445,0.9961285128805621,0.002893068989786162,0.9967320261437909,0.00244683745716795 +flat_mae,reg,logistic,aabc_sex,1,0.3593813663804626,test,0.8363636363636363,0.04878905174573422,0.8307692307692308,0.050793873140110773,0.8288043478260869,0.05092548014139616 +flat_mae,reg,logistic,aabc_sex,2,0.3593813663804626,train,0.994328922495274,0.0033536037219096915,0.9941893034853195,0.0034334774756359476,0.9944898736774231,0.0032923108718440545 +flat_mae,reg,logistic,aabc_sex,2,0.3593813663804626,test,0.8909090909090909,0.043970298013977754,0.8879076086956521,0.04530922378960111,0.8879076086956521,0.045544170797208176 +flat_mae,reg,logistic,aabc_sex,3,0.3593813663804626,train,0.994328922495274,0.0032466311977886945,0.9941961885745005,0.0033146996411066785,0.9950980392156863,0.0028063201039709457 +flat_mae,reg,logistic,aabc_sex,3,0.3593813663804626,test,0.8363636363636363,0.04937057041538505,0.8281846581048247,0.0531771399884078,0.8226902173913043,0.05331152750812794 +flat_mae,reg,logistic,aabc_sex,4,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,4,166.81005372000556,test,0.8545454545454545,0.047300285673486014,0.8521505376344086,0.04783804078913595,0.8566576086956521,0.04713266054990701 +flat_mae,reg,logistic,aabc_sex,5,0.046415888336127774,train,0.9489603024574669,0.009764835777059347,0.947507690272219,0.010057304516163297,0.9461517043289662,0.010280739290898898 +flat_mae,reg,logistic,aabc_sex,5,0.046415888336127774,test,0.8181818181818182,0.051122927527756684,0.8131793478260869,0.05280821772163583,0.8131793478260869,0.0528974447875508 +flat_mae,reg,logistic,aabc_sex,6,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,6,166.81005372000556,test,0.9454545454545454,0.030464720145665536,0.9435897435897436,0.031856996515590215,0.9408967391304348,0.03345344386828878 +flat_mae,reg,logistic,aabc_sex,7,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,7,2.782559402207126,test,0.8727272727272727,0.04538473184119875,0.8711943793911007,0.04562365132356,0.8783967391304348,0.044191769792042805 +flat_mae,reg,logistic,aabc_sex,8,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,8,21.54434690031882,test,0.8363636363636363,0.04784906019958457,0.8328267477203647,0.04890049102750025,0.8349184782608696,0.0489350795018083 +flat_mae,reg,logistic,aabc_sex,9,0.3593813663804626,train,0.996219281663516,0.002690841118844736,0.9961238606055277,0.002758816201291458,0.9961238606055277,0.0027982263363807844 +flat_mae,reg,logistic,aabc_sex,9,0.3593813663804626,test,0.8909090909090909,0.039875425850727404,0.8863636363636364,0.04237492638234629,0.8817934782608696,0.04359885144805758 +flat_mae,reg,logistic,aabc_sex,10,0.046415888336127774,train,0.947069943289225,0.009772775895430059,0.945455884519075,0.010123479397982117,0.9433013863243354,0.010488020649491477 +flat_mae,reg,logistic,aabc_sex,10,0.046415888336127774,test,0.8909090909090909,0.04245329567948273,0.8891129032258065,0.042948231050356,0.8940217391304348,0.04190508088782208 +flat_mae,reg,logistic,aabc_sex,11,0.005994842503189409,train,0.888468809073724,0.013394597928340395,0.8851443102071458,0.01384947558008839,0.8835253084791466,0.014030159787920833 +flat_mae,reg,logistic,aabc_sex,11,0.005994842503189409,test,0.8909090909090909,0.041339937266802185,0.884453781512605,0.045845344408521095,0.8756793478260869,0.04692616111634535 +flat_mae,reg,logistic,aabc_sex,12,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,12,21.54434690031882,test,0.8545454545454545,0.04838242970472059,0.8484848484848485,0.05113010272550589,0.8444293478260869,0.05144952348912853 +flat_mae,reg,logistic,aabc_sex,13,0.3593813663804626,train,0.994328922495274,0.003184062983312339,0.9941893034853195,0.0032600585039322698,0.9944898736774231,0.0031370398503740185 +flat_mae,reg,logistic,aabc_sex,13,0.3593813663804626,test,0.8727272727272727,0.046665682791674885,0.8711943793911007,0.04684649393083506,0.8783967391304348,0.04540061546856371 +flat_mae,reg,logistic,aabc_sex,14,0.3593813663804626,train,0.994328922495274,0.0031768361809753746,0.9941961885745005,0.0032442776511340714,0.9950980392156863,0.0027459907512025717 +flat_mae,reg,logistic,aabc_sex,14,0.3593813663804626,test,0.9272727272727272,0.03398589887459283,0.9260752688172043,0.034311913578061945,0.9313858695652174,0.03267465845875645 +flat_mae,reg,logistic,aabc_sex,15,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,15,2.782559402207126,test,0.8363636363636363,0.04882411001757494,0.8281846581048247,0.05219634790059309,0.8226902173913043,0.05202307742205047 +flat_mae,reg,logistic,aabc_sex,16,0.3593813663804626,train,0.9924385633270322,0.0036206177012126257,0.9922570257611241,0.00370236483411091,0.9928558867493186,0.003461005263775228 +flat_mae,reg,logistic,aabc_sex,16,0.3593813663804626,test,0.8363636363636363,0.049857966860915315,0.8281846581048247,0.05424034522368572,0.8226902173913043,0.05424584222108683 +flat_mae,reg,logistic,aabc_sex,17,0.3593813663804626,train,0.998109640831758,0.0018562480008703908,0.9980631011617731,0.0018999510405251546,0.9983660130718954,0.0016045019484647492 +flat_mae,reg,logistic,aabc_sex,17,0.3593813663804626,test,0.8,0.049709290416571086,0.7861435136090491,0.05529395035443376,0.7792119565217391,0.0539233307128535 +flat_mae,reg,logistic,aabc_sex,18,0.005994842503189409,train,0.8941398865784499,0.012635847910909204,0.89091176903815,0.013119517391792946,0.8890354348017233,0.013469824735542799 +flat_mae,reg,logistic,aabc_sex,18,0.005994842503189409,test,0.8181818181818182,0.053335166635157305,0.8166666666666667,0.05345539508349983,0.8254076086956521,0.05211146830666055 +flat_mae,reg,logistic,aabc_sex,19,0.046415888336127774,train,0.9546313799621928,0.008676407569561796,0.9533097969991173,0.008966563310520155,0.9516618306515432,0.009321472361776814 +flat_mae,reg,logistic,aabc_sex,19,0.046415888336127774,test,0.8363636363636363,0.049113408985212555,0.8343927735028438,0.049324040007927034,0.8410326086956521,0.048334336523767625 +flat_mae,reg,logistic,aabc_sex,20,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,20,2.782559402207126,test,0.9272727272727272,0.03356377425363186,0.9229691876750701,0.03715940739966153,0.9130434782608696,0.04013059965108157 +flat_mae,reg,logistic,aabc_sex,21,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,21,166.81005372000556,test,0.7818181818181819,0.05289383097651274,0.7727272727272727,0.056070360552661465,0.7697010869565217,0.05540534069699311 +flat_mae,reg,logistic,aabc_sex,22,0.3593813663804626,train,0.998109640831758,0.0018165397550330869,0.9980631011617731,0.0018592433943678782,0.9983660130718954,0.0015701789712622457 +flat_mae,reg,logistic,aabc_sex,22,0.3593813663804626,test,0.8545454545454545,0.04588847421864994,0.8484848484848485,0.04869388556736162,0.8444293478260869,0.04908840214540535 +flat_mae,reg,logistic,aabc_sex,23,0.046415888336127774,train,0.9489603024574669,0.009586263896180985,0.9474389216202193,0.009931806006473176,0.9455435387907032,0.010407368573797019 +flat_mae,reg,logistic,aabc_sex,23,0.046415888336127774,test,0.8363636363636363,0.04985892163009244,0.8354935194416749,0.04981141581980006,0.8471467391304348,0.047427565059179444 +flat_mae,reg,logistic,aabc_sex,24,0.046415888336127774,train,0.9565217391304348,0.009186629000546426,0.9553414450623061,0.009452707749959268,0.9545121486561741,0.009642754044532836 +flat_mae,reg,logistic,aabc_sex,24,0.046415888336127774,test,0.7818181818181819,0.05895139894876565,0.7758152173913043,0.06088381162785889,0.7758152173913043,0.060935323685145225 +flat_mae,reg,logistic,aabc_sex,25,0.046415888336127774,train,0.9489603024574669,0.008841340581774668,0.9474389216202193,0.009150474136468335,0.9455435387907032,0.009519950944079167 +flat_mae,reg,logistic,aabc_sex,25,0.046415888336127774,test,0.9454545454545454,0.030121099932722,0.9442755825734549,0.03061548458588365,0.9470108695652174,0.029236769163787205 +flat_mae,reg,logistic,aabc_sex,26,0.005994842503189409,train,0.9017013232514177,0.012826557099872175,0.8988378934980876,0.013218529779239166,0.8973958791289312,0.013353453041046504 +flat_mae,reg,logistic,aabc_sex,26,0.005994842503189409,test,0.8,0.04932115701122205,0.790003471017008,0.05312854744297095,0.7853260869565217,0.052592327630807345 +flat_mae,reg,logistic,aabc_sex,27,0.3593813663804626,train,0.994328922495274,0.0032991506584572317,0.9941893034853195,0.0033769854842508576,0.9944898736774231,0.003226562357402419 +flat_mae,reg,logistic,aabc_sex,27,0.3593813663804626,test,0.8545454545454545,0.045531149994643326,0.84593837535014,0.049674929326242574,0.8383152173913043,0.049667072639924786 +flat_mae,reg,logistic,aabc_sex,28,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,28,2.782559402207126,test,0.8545454545454545,0.04906633728479692,0.8521505376344086,0.04955629598032052,0.8566576086956521,0.04875061078439902 +flat_mae,reg,logistic,aabc_sex,29,0.046415888336127774,train,0.947069943289225,0.009727672197950128,0.9455280964989703,0.010047941146477056,0.9439095518625986,0.010383162030127773 +flat_mae,reg,logistic,aabc_sex,29,0.046415888336127774,test,0.8727272727272727,0.044815507941627905,0.8699763593380614,0.045706183777371255,0.8722826086956521,0.045414490362016426 +flat_mae,reg,logistic,aabc_sex,30,0.3593813663804626,train,0.9924385633270322,0.0037759421627188224,0.9922570257611241,0.0038613567734661395,0.9928558867493186,0.0036246968274919124 +flat_mae,reg,logistic,aabc_sex,30,0.3593813663804626,test,0.9090909090909091,0.04010768974722309,0.9079959852793577,0.04022769330940008,0.9157608695652174,0.03771101025441605 +flat_mae,reg,logistic,aabc_sex,31,0.046415888336127774,train,0.9527410207939508,0.00895966354114621,0.951396009511314,0.009237054325549608,0.9500278437234386,0.009461791272900866 +flat_mae,reg,logistic,aabc_sex,31,0.046415888336127774,test,0.8,0.05281752776938182,0.7975911676145868,0.05301377698028716,0.8036684782608696,0.05197778074587208 +flat_mae,reg,logistic,aabc_sex,32,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,32,166.81005372000556,test,0.8545454545454545,0.045053708995096885,0.84593837535014,0.049635685608247763,0.8383152173913043,0.049732194917444676 +flat_mae,reg,logistic,aabc_sex,33,0.046415888336127774,train,0.947069943289225,0.00932217815938651,0.9456671655368724,0.009575748073912023,0.9451258829391249,0.009727073305684017 +flat_mae,reg,logistic,aabc_sex,33,0.046415888336127774,test,0.8727272727272727,0.04238976954388252,0.8683760683760684,0.04454514293155388,0.8661684782608696,0.04527064341394798 +flat_mae,reg,logistic,aabc_sex,34,0.046415888336127774,train,0.945179584120983,0.009695899660748863,0.9436193710331242,0.009997573101217181,0.942275564934494,0.01025017670689886 +flat_mae,reg,logistic,aabc_sex,34,0.046415888336127774,test,0.8909090909090909,0.04271258548341093,0.8879076086956521,0.04398485895302395,0.8879076086956521,0.0441251714264263 +flat_mae,reg,logistic,aabc_sex,35,0.3593813663804626,train,0.9924385633270322,0.0036170134498649583,0.9922570257611241,0.0036995103785970014,0.9928558867493186,0.0034690267628301958 +flat_mae,reg,logistic,aabc_sex,35,0.3593813663804626,test,0.9090909090909091,0.03837871310811126,0.9071259709557582,0.039029830616125395,0.9096467391304348,0.03833939346255904 +flat_mae,reg,logistic,aabc_sex,36,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,36,21.54434690031882,test,0.8909090909090909,0.041122674769101406,0.8879076086956521,0.042293800769416245,0.8879076086956521,0.04219653564933697 +flat_mae,reg,logistic,aabc_sex,37,0.005994842503189409,train,0.9092627599243857,0.012561954270807606,0.9066195939982348,0.01295156747484109,0.9051481579178757,0.013098832736790042 +flat_mae,reg,logistic,aabc_sex,37,0.005994842503189409,test,0.7636363636363637,0.058827103440281275,0.7555555555555555,0.061475708189840605,0.7540760869565217,0.061145286992873034 +flat_mae,reg,logistic,aabc_sex,38,0.005994842503189409,train,0.9017013232514177,0.012818169103715948,0.8989686783804431,0.013203164355997124,0.8980040446671942,0.013362599850149311 +flat_mae,reg,logistic,aabc_sex,38,0.005994842503189409,test,0.8363636363636363,0.04876008393270016,0.8250265111346766,0.054205102480322453,0.8165760869565217,0.05348034752786048 +flat_mae,reg,logistic,aabc_sex,39,0.3593813663804626,train,0.9924385633270322,0.003780907367675085,0.9922570257611241,0.0038671450257261974,0.9928558867493186,0.0036207264576137853 +flat_mae,reg,logistic,aabc_sex,39,0.3593813663804626,test,0.9090909090909091,0.036207282040043726,0.905982905982906,0.03784871836901494,0.9035326086956521,0.0386617676507787 +flat_mae,reg,logistic,aabc_sex,40,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,40,21.54434690031882,test,0.8363636363636363,0.04943682837723308,0.8328267477203647,0.050379989773158045,0.8349184782608696,0.05011797105985936 +flat_mae,reg,logistic,aabc_sex,41,0.005994842503189409,train,0.8922495274102079,0.013327524961057689,0.8888888888888888,0.013790253135660986,0.8867932823353557,0.013955327630391905 +flat_mae,reg,logistic,aabc_sex,41,0.005994842503189409,test,0.9090909090909091,0.038480287966483194,0.905982905982906,0.040362495966507414,0.9035326086956521,0.04107032746648314 +flat_mae,reg,logistic,aabc_sex,42,0.046415888336127774,train,0.947069943289225,0.009814304241818308,0.9455280964989703,0.010137911184555879,0.9439095518625986,0.010480930803566536 +flat_mae,reg,logistic,aabc_sex,42,0.046415888336127774,test,0.7636363636363637,0.05695677351805294,0.7607895617263298,0.0573077708763622,0.7663043478260869,0.056655096177086736 +flat_mae,reg,logistic,aabc_sex,43,0.3593813663804626,train,0.9924385633270322,0.0038081349957554103,0.9922570257611241,0.003893524235636497,0.9928558867493186,0.0036173400607797442 +flat_mae,reg,logistic,aabc_sex,43,0.3593813663804626,test,0.9090909090909091,0.0370304498335631,0.9079959852793577,0.03715171793773863,0.9157608695652174,0.03461531769981152 +flat_mae,reg,logistic,aabc_sex,44,0.005994842503189409,train,0.9035916824196597,0.012296860637732103,0.9007179630604141,0.01274877808341945,0.8990298660570357,0.013098184199385816 +flat_mae,reg,logistic,aabc_sex,44,0.005994842503189409,test,0.8,0.049848908904892415,0.790003471017008,0.0535331196612943,0.7853260869565217,0.05279558305024048 +flat_mae,reg,logistic,aabc_sex,45,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,45,21.54434690031882,test,0.9272727272727272,0.034420520498751314,0.9252717391304348,0.035543324911137035,0.9252717391304348,0.03607356402960767 +flat_mae,reg,logistic,aabc_sex,46,0.046415888336127774,train,0.943289224952741,0.01077968924650493,0.9416372462488967,0.011139307778772665,0.9400334124681262,0.011462646582932024 +flat_mae,reg,logistic,aabc_sex,46,0.046415888336127774,test,0.8727272727272727,0.04606678586932865,0.8683760683760684,0.04810424020671304,0.8661684782608696,0.0485527380172785 +flat_mae,reg,logistic,aabc_sex,47,0.046415888336127774,train,0.9565217391304348,0.008501997485851412,0.9552257480468535,0.008809170598388635,0.9532958175796478,0.009302815709868281 +flat_mae,reg,logistic,aabc_sex,47,0.046415888336127774,test,0.8363636363636363,0.04627722428585473,0.8250265111346766,0.05193517159002764,0.8165760869565217,0.051473059834153394 +flat_mae,reg,logistic,aabc_sex,48,0.046415888336127774,train,0.9508506616257089,0.009414121513475572,0.9493518927677125,0.009752798680890806,0.9471775257188078,0.010192231213384115 +flat_mae,reg,logistic,aabc_sex,48,0.046415888336127774,test,0.8909090909090909,0.04178906496217907,0.8879076086956521,0.04306436179205185,0.8879076086956521,0.04326713931636038 +flat_mae,reg,logistic,aabc_sex,49,0.046415888336127774,train,0.9546313799621928,0.009449508986108461,0.9534289990316049,0.009715182884704321,0.9528781617280695,0.00989865344580095 +flat_mae,reg,logistic,aabc_sex,49,0.046415888336127774,test,0.8181818181818182,0.051444085027314054,0.8166666666666667,0.0516295507315779,0.8254076086956521,0.05051938021250624 +flat_mae,reg,logistic,aabc_sex,50,0.046415888336127774,train,0.9527410207939508,0.009104111059074584,0.951396009511314,0.009396482100355626,0.9500278437234386,0.009722636537583445 +flat_mae,reg,logistic,aabc_sex,50,0.046415888336127774,test,0.8363636363636363,0.05264242703340091,0.8328267477203647,0.053484885818128866,0.8349184782608696,0.053023739725385106 +flat_mae,reg,logistic,aabc_sex,51,0.046415888336127774,train,0.945179584120983,0.00935826387274355,0.9437615704675844,0.009614080445610228,0.9434918960110203,0.009811686481482692 +flat_mae,reg,logistic,aabc_sex,51,0.046415888336127774,test,0.8727272727272727,0.042230003825958796,0.8639095086603039,0.04792332333618021,0.8539402173913043,0.048416049506693475 +flat_mae,reg,logistic,aabc_sex,52,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,52,21.54434690031882,test,0.8181818181818182,0.05155948181750136,0.8106060606060606,0.054806682213843536,0.8070652173913043,0.05475552581177027 +flat_mae,reg,logistic,aabc_sex,53,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,53,10000.0,test,0.8545454545454545,0.04718395861321113,0.8521505376344086,0.047962697984512005,0.8566576086956521,0.04773131425935898 +flat_mae,reg,logistic,aabc_sex,54,0.3593813663804626,train,0.994328922495274,0.0034220722533401795,0.9941893034853195,0.0035044826248548265,0.9944898736774231,0.003395228774605986 +flat_mae,reg,logistic,aabc_sex,54,0.3593813663804626,test,0.8727272727272727,0.04646646707017298,0.8699763593380614,0.04727874773091675,0.8722826086956521,0.04677853172076245 +flat_mae,reg,logistic,aabc_sex,55,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,55,2.782559402207126,test,0.8363636363636363,0.05046522081985465,0.8328267477203647,0.051509408070540004,0.8349184782608696,0.051246225104043946 +flat_mae,reg,logistic,aabc_sex,56,0.3593813663804626,train,0.994328922495274,0.003298589541748651,0.9941893034853195,0.0033779163009851907,0.9944898736774231,0.0032766469102747846 +flat_mae,reg,logistic,aabc_sex,56,0.3593813663804626,test,0.8181818181818182,0.049089562271087114,0.8131793478260869,0.050759399628519206,0.8131793478260869,0.05085090556831021 +flat_mae,reg,logistic,aabc_sex,57,0.046415888336127774,train,0.941398865784499,0.009930345856306765,0.9397310517940294,0.010249141471454273,0.9383994255400216,0.010539362253073427 +flat_mae,reg,logistic,aabc_sex,57,0.046415888336127774,test,0.8909090909090909,0.04239224940855764,0.8879076086956521,0.04379206517870961,0.8879076086956521,0.04387796189609727 +flat_mae,reg,logistic,aabc_sex,58,0.3593813663804626,train,0.9924385633270322,0.003719079771520455,0.9922570257611241,0.0038027638008959266,0.9928558867493186,0.003515547062544777 +flat_mae,reg,logistic,aabc_sex,58,0.3593813663804626,test,0.7636363636363637,0.056758161753353444,0.7607895617263298,0.05701274578796561,0.7663043478260869,0.05669679652677279 +flat_mae,reg,logistic,aabc_sex,59,0.005994842503189409,train,0.9017013232514177,0.01302504985675673,0.898703785535425,0.013487196339756109,0.8967877135906679,0.013730501170442853 +flat_mae,reg,logistic,aabc_sex,59,0.005994842503189409,test,0.8363636363636363,0.048037175686481415,0.8354935194416749,0.04794510729278932,0.8471467391304348,0.04554013528884234 +flat_mae,reg,logistic,aabc_sex,60,0.3593813663804626,train,0.994328922495274,0.0032580053720696325,0.9941893034853195,0.003335514169169169,0.9944898736774231,0.0031878391916870664 +flat_mae,reg,logistic,aabc_sex,60,0.3593813663804626,test,0.8545454545454545,0.047780143875467015,0.8484848484848485,0.050624116585314564,0.8444293478260869,0.05112141419669558 +flat_mae,reg,logistic,aabc_sex,61,0.046415888336127774,train,0.9489603024574669,0.009205219217082517,0.9475747398557507,0.009484563678306338,0.9467598698672295,0.009769371607695759 +flat_mae,reg,logistic,aabc_sex,61,0.046415888336127774,test,0.8909090909090909,0.041437380816427324,0.8891129032258065,0.04176354832299889,0.8940217391304348,0.04049168659406426 +flat_mae,reg,logistic,aabc_sex,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,62,21.54434690031882,test,0.8909090909090909,0.04099927030191216,0.8891129032258065,0.04136552721701025,0.8940217391304348,0.040061971904152775 +flat_mae,reg,logistic,aabc_sex,63,0.046415888336127774,train,0.943289224952741,0.010227716611483173,0.9416372462488967,0.01057531262045935,0.9400334124681262,0.010954360181287813 +flat_mae,reg,logistic,aabc_sex,63,0.046415888336127774,test,0.9454545454545454,0.029934230937476623,0.9435897435897436,0.03138985009877738,0.9408967391304348,0.032919090083216154 +flat_mae,reg,logistic,aabc_sex,64,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,64,21.54434690031882,test,0.8545454545454545,0.04716850048513867,0.8521505376344086,0.04774354321752257,0.8566576086956521,0.047267771812429304 +flat_mae,reg,logistic,aabc_sex,65,0.046415888336127774,train,0.9508506616257089,0.009713043618064004,0.9494843391902215,0.010019674036298725,0.9483938567953341,0.010329694467065716 +flat_mae,reg,logistic,aabc_sex,65,0.046415888336127774,test,0.8727272727272727,0.045190505841181026,0.8683760683760684,0.04717683417932218,0.8661684782608696,0.04754874920459581 +flat_mae,reg,logistic,aabc_sex,66,0.3593813663804626,train,0.9924385633270322,0.0037437054015904327,0.9922570257611241,0.003827233472356847,0.9928558867493186,0.0035620164215559758 +flat_mae,reg,logistic,aabc_sex,66,0.3593813663804626,test,0.8363636363636363,0.05096391852806782,0.8307692307692308,0.05321866936233793,0.8288043478260869,0.05338121068044289 +flat_mae,reg,logistic,aabc_sex,67,0.3593813663804626,train,0.9924385633270322,0.0038506277531447533,0.9922570257611241,0.0039370809009300605,0.9928558867493186,0.0036717435099821276 +flat_mae,reg,logistic,aabc_sex,67,0.3593813663804626,test,0.8727272727272727,0.04490571941705906,0.8699763593380614,0.04587421889846148,0.8722826086956521,0.04573827284697767 +flat_mae,reg,logistic,aabc_sex,68,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,68,2.782559402207126,test,0.8909090909090909,0.0408511751654306,0.884453781512605,0.04498039033598734,0.8756793478260869,0.04620734528721433 +flat_mae,reg,logistic,aabc_sex,69,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,69,2.782559402207126,test,0.9454545454545454,0.028858251466191625,0.9427282193682749,0.03126170377286141,0.9347826086956521,0.034504431100881285 +flat_mae,reg,logistic,aabc_sex,70,0.046415888336127774,train,0.947069943289225,0.00971540453252162,0.9455985191279309,0.010017310422999371,0.9445177174008617,0.010300518140653771 +flat_mae,reg,logistic,aabc_sex,70,0.046415888336127774,test,0.9090909090909091,0.039024061236266804,0.9071259709557582,0.03976427620716095,0.9096467391304348,0.03932100736277034 +flat_mae,reg,logistic,aabc_sex,71,0.005994842503189409,train,0.888468809073724,0.01297148703567487,0.8851443102071458,0.013399088636730744,0.8835253084791466,0.013590403505135169 +flat_mae,reg,logistic,aabc_sex,71,0.005994842503189409,test,0.8181818181818182,0.046335834801769324,0.8074229691876751,0.050612761424560185,0.8009510869565217,0.04989871703229617 +flat_mae,reg,logistic,aabc_sex,72,0.046415888336127774,train,0.9395085066162571,0.010398490351909984,0.9377463959988231,0.010774034156868348,0.936157273073654,0.011233642861728146 +flat_mae,reg,logistic,aabc_sex,72,0.046415888336127774,test,0.9272727272727272,0.03477808752506134,0.9252717391304348,0.035761751674160236,0.9252717391304348,0.035871101411233335 +flat_mae,reg,logistic,aabc_sex,73,0.3593813663804626,train,0.994328922495274,0.0032157248688185467,0.9941893034853195,0.0032925424834571865,0.9944898736774231,0.0031898874962650817 +flat_mae,reg,logistic,aabc_sex,73,0.3593813663804626,test,0.9454545454545454,0.027465957892911858,0.9427282193682749,0.029833805294656204,0.9347826086956521,0.03283973226326418 +flat_mae,reg,logistic,aabc_sex,74,0.046415888336127774,train,0.9527410207939508,0.008951125128785747,0.9513323348335363,0.009265455377553942,0.9494196781851754,0.009716715196011276 +flat_mae,reg,logistic,aabc_sex,74,0.046415888336127774,test,0.8727272727272727,0.04392828114435528,0.8663658451926415,0.04722950787830501,0.8600543478260869,0.048088630906850255 +flat_mae,reg,logistic,aabc_sex,75,0.3593813663804626,train,0.998109640831758,0.001805173245960891,0.9980631011617731,0.0018475137904941231,0.9983660130718954,0.0015603539985511459 +flat_mae,reg,logistic,aabc_sex,75,0.3593813663804626,test,0.7818181818181819,0.05191428408985317,0.7758152173913043,0.05393519564517808,0.7758152173913043,0.05433261014918414 +flat_mae,reg,logistic,aabc_sex,76,0.046415888336127774,train,0.9527410207939508,0.009292783408940467,0.951396009511314,0.009601040561297463,0.9500278437234386,0.010019032750985219 +flat_mae,reg,logistic,aabc_sex,76,0.046415888336127774,test,0.8181818181818182,0.05152216565439583,0.8106060606060606,0.054703395687990576,0.8070652173913043,0.05450938222698876 +flat_mae,reg,logistic,aabc_sex,77,0.046415888336127774,train,0.9489603024574669,0.009537554985398662,0.947507690272219,0.009823973074702697,0.9461517043289662,0.010046784362840318 +flat_mae,reg,logistic,aabc_sex,77,0.046415888336127774,test,0.8363636363636363,0.04860058156982915,0.8250265111346766,0.05473858143502813,0.8165760869565217,0.0541095486343354 +flat_mae,reg,logistic,aabc_sex,78,0.3593813663804626,train,0.9924385633270322,0.003875594063433446,0.9922570257611241,0.0039633552517171315,0.9928558867493186,0.0037330251104144133 +flat_mae,reg,logistic,aabc_sex,78,0.3593813663804626,test,0.9636363636363636,0.025061141762622894,0.9630376344086022,0.02518974230140629,0.96875,0.021536918702254042 +flat_mae,reg,logistic,aabc_sex,79,0.046415888336127774,train,0.947069943289225,0.009696598413012184,0.9455985191279309,0.010008079070269467,0.9445177174008617,0.01032785991946748 +flat_mae,reg,logistic,aabc_sex,79,0.046415888336127774,test,0.8363636363636363,0.05011688816495733,0.8281846581048247,0.054043961566229454,0.8226902173913043,0.053893677148751824 +flat_mae,reg,logistic,aabc_sex,80,0.3593813663804626,train,0.994328922495274,0.0033267636083419813,0.9941893034853195,0.003406445565543251,0.9944898736774231,0.0033059851064630376 +flat_mae,reg,logistic,aabc_sex,80,0.3593813663804626,test,0.8545454545454545,0.0470691420384035,0.84593837535014,0.05192120391269799,0.8383152173913043,0.052042503640169456 +flat_mae,reg,logistic,aabc_sex,81,0.3593813663804626,train,0.996219281663516,0.0026075337814240817,0.9961285128805621,0.0026653780677915856,0.9967320261437909,0.00225389766400872 +flat_mae,reg,logistic,aabc_sex,81,0.3593813663804626,test,0.8545454545454545,0.04561942459990529,0.8484848484848485,0.04833941315529502,0.8444293478260869,0.04891893752229796 +flat_mae,reg,logistic,aabc_sex,82,0.3593813663804626,train,0.994328922495274,0.0032565550482144723,0.9941961885745005,0.0033261802076505246,0.9950980392156863,0.002814898072721333 +flat_mae,reg,logistic,aabc_sex,82,0.3593813663804626,test,0.8363636363636363,0.04603497053758905,0.8281846581048247,0.04967580339768975,0.8226902173913043,0.04983712800676367 +flat_mae,reg,logistic,aabc_sex,83,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,83,166.81005372000556,test,0.8727272727272727,0.040373315792725926,0.8609606356085229,0.04853180712733903,0.8478260869565217,0.04827244279565058 +flat_mae,reg,logistic,aabc_sex,84,0.046415888336127774,train,0.947069943289225,0.010444281449568577,0.9455280964989703,0.010798567610199247,0.9439095518625986,0.011155885892157014 +flat_mae,reg,logistic,aabc_sex,84,0.046415888336127774,test,0.7636363636363637,0.058607262687054594,0.7555555555555555,0.06058215084947754,0.7540760869565217,0.06008471558761189 +flat_mae,reg,logistic,aabc_sex,85,0.3593813663804626,train,0.994328922495274,0.003298112842533262,0.9941893034853195,0.0033766894129572847,0.9944898736774231,0.0032391712232232614 +flat_mae,reg,logistic,aabc_sex,85,0.3593813663804626,test,0.8545454545454545,0.04534450680645517,0.8521505376344086,0.04610360165495689,0.8566576086956521,0.04608245664413496 +flat_mae,reg,logistic,aabc_sex,86,0.005994842503189409,train,0.8941398865784499,0.013698224464611119,0.89091176903815,0.014185651696689753,0.8890354348017233,0.0145015951954965 +flat_mae,reg,logistic,aabc_sex,86,0.005994842503189409,test,0.8727272727272727,0.04724525075611582,0.8699763593380614,0.04803777289748641,0.8722826086956521,0.04755470921834729 +flat_mae,reg,logistic,aabc_sex,87,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,87,21.54434690031882,test,0.8,0.05266492865981876,0.790003471017008,0.056646254632873254,0.7853260869565217,0.05591788830996608 +flat_mae,reg,logistic,aabc_sex,88,0.046415888336127774,train,0.947069943289225,0.009745511975406636,0.9455985191279309,0.010037849658873192,0.9445177174008617,0.010280696621434613 +flat_mae,reg,logistic,aabc_sex,88,0.046415888336127774,test,0.8727272727272727,0.048034422918610827,0.8683760683760684,0.05000010522611678,0.8661684782608696,0.050509540090193594 +flat_mae,reg,logistic,aabc_sex,89,0.3593813663804626,train,0.998109640831758,0.0018423972291365875,0.9980631011617731,0.001885598651661491,0.9983660130718954,0.0015925296310673957 +flat_mae,reg,logistic,aabc_sex,89,0.3593813663804626,test,0.8363636363636363,0.04836369104576537,0.8281846581048247,0.0522476145570863,0.8226902173913043,0.05212117003680967 +flat_mae,reg,logistic,aabc_sex,90,0.046415888336127774,train,0.9489603024574669,0.009533765546165897,0.9473684210526316,0.009883008620637375,0.9449353732524399,0.010303907940644093 +flat_mae,reg,logistic,aabc_sex,90,0.046415888336127774,test,0.8363636363636363,0.05043357139809691,0.8281846581048247,0.054618886000415194,0.8226902173913043,0.054659761649513625 +flat_mae,reg,logistic,aabc_sex,91,0.3593813663804626,train,0.9924385633270322,0.003603078131141591,0.9922570257611241,0.0036857427539549615,0.9928558867493186,0.0034873481943158693 +flat_mae,reg,logistic,aabc_sex,91,0.3593813663804626,test,0.8545454545454545,0.0481018753607709,0.8521505376344086,0.048586201340465214,0.8566576086956521,0.047759252859324385 +flat_mae,reg,logistic,aabc_sex,92,0.046415888336127774,train,0.9527410207939508,0.009371606908932201,0.951396009511314,0.009680456400036978,0.9500278437234386,0.010086597822755472 +flat_mae,reg,logistic,aabc_sex,92,0.046415888336127774,test,0.9090909090909091,0.03737502591281338,0.905982905982906,0.039091733600425914,0.9035326086956521,0.040039982989153976 +flat_mae,reg,logistic,aabc_sex,93,0.046415888336127774,train,0.9508506616257089,0.009159225391092343,0.9494843391902215,0.009442918603219275,0.9483938567953341,0.00972055555585367 +flat_mae,reg,logistic,aabc_sex,93,0.046415888336127774,test,0.8727272727272727,0.04484641928085283,0.8639095086603039,0.050315887270863474,0.8539402173913043,0.05101077945347751 +flat_mae,reg,logistic,aabc_sex,94,0.005994842503189409,train,0.8922495274102079,0.013604365308095877,0.8888888888888888,0.014135256187297537,0.8867932823353557,0.014475765550008277 +flat_mae,reg,logistic,aabc_sex,94,0.005994842503189409,test,0.8909090909090909,0.03886078564770693,0.8863636363636364,0.04134002386122689,0.8817934782608696,0.04234252218607174 +flat_mae,reg,logistic,aabc_sex,95,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,95,2.782559402207126,test,0.8727272727272727,0.045928525139477344,0.8699763593380614,0.04692464121740007,0.8722826086956521,0.04679734925900763 +flat_mae,reg,logistic,aabc_sex,96,0.046415888336127774,train,0.947069943289225,0.009276051572292167,0.945455884519075,0.009617757652056292,0.9433013863243354,0.010050760156760546 +flat_mae,reg,logistic,aabc_sex,96,0.046415888336127774,test,0.9272727272727272,0.03486836639716022,0.9252717391304348,0.03582425508042928,0.9252717391304348,0.035893155816074857 +flat_mae,reg,logistic,aabc_sex,97,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,97,21.54434690031882,test,0.8545454545454545,0.047924720583172986,0.8521505376344086,0.048493295063604974,0.8566576086956521,0.04777858165926426 +flat_mae,reg,logistic,aabc_sex,98,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,aabc_sex,98,21.54434690031882,test,0.7818181818181819,0.05593832495120949,0.7758152173913043,0.05780587677586161,0.7758152173913043,0.058084546766919876 +flat_mae,reg,logistic,aabc_sex,99,0.3593813663804626,train,0.9924385633270322,0.003633384409925424,0.9922570257611241,0.0037147065273204507,0.9928558867493186,0.0034362356321566137 +flat_mae,reg,logistic,aabc_sex,99,0.3593813663804626,test,0.8545454545454545,0.05012771787318421,0.8484848484848485,0.05366999047934252,0.8444293478260869,0.05436362900341514 +flat_mae,reg,logistic,aabc_sex,100,0.3593813663804626,train,0.9924385633270322,0.003657539687243723,0.9922570257611241,0.0037406243815651364,0.9928558867493186,0.0035011796081647387 +flat_mae,reg,logistic,aabc_sex,100,0.3593813663804626,test,0.9272727272727272,0.03417909080028146,0.9252717391304348,0.03528196673215015,0.9252717391304348,0.03556974734271991 diff --git a/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..82e1504c9952043f3081c7bc1f2378aa72eb592c --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic/log.txt @@ -0,0 +1,245 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:20:27 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (aabc_sex reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic +model: flat_mae +representation: reg +dataset: aabc_sex +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/aabc_sex__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: aabc_sex (flat) +train (n=471): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 471 +}), + labels=[0 1], + counts=[269 202] +) + +validation (n=58): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 58 +}), + labels=[0 1], + counts=[36 22] +) + +test (n=55): +HFDataset( + dataset=Dataset({ + features: ['sub', 'visit', 'mod', 'task', 'path', 'start', 'end', 'tr', 'segment', 'bold', 'mean', 'std'], + num_rows: 55 +}), + labels=[0 1], + counts=[33 22] +) + +extracting features for all splits +extract (train) [ 0/236] eta: 0:21:51 time: 5.5551 data: 4.5692 max mem: 3207 +extract (train) [ 20/236] eta: 0:01:48 time: 0.2499 data: 0.0903 max mem: 3395 +extract (train) [ 40/236] eta: 0:01:11 time: 0.2158 data: 0.0694 max mem: 3395 +extract (train) [ 60/236] eta: 0:00:55 time: 0.2113 data: 0.0687 max mem: 3395 +extract (train) [ 80/236] eta: 0:00:44 time: 0.1966 data: 0.0656 max mem: 3395 +extract (train) [100/236] eta: 0:00:37 time: 0.2280 data: 0.0789 max mem: 3395 +extract (train) [120/236] eta: 0:00:30 time: 0.2193 data: 0.0736 max mem: 3395 +extract (train) [140/236] eta: 0:00:25 time: 0.2396 data: 0.0868 max mem: 3395 +extract (train) [160/236] eta: 0:00:19 time: 0.1965 data: 0.0620 max mem: 3395 +extract (train) [180/236] eta: 0:00:14 time: 0.2413 data: 0.0872 max mem: 3395 +extract (train) [200/236] eta: 0:00:08 time: 0.2043 data: 0.0686 max mem: 3395 +extract (train) [220/236] eta: 0:00:03 time: 0.1933 data: 0.0609 max mem: 3395 +extract (train) [235/236] eta: 0:00:00 time: 0.1892 data: 0.0611 max mem: 3395 +extract (train) Total time: 0:00:56 (0.2408 s / it) +extract (validation) [ 0/29] eta: 0:02:03 time: 4.2541 data: 4.1053 max mem: 3395 +extract (validation) [20/29] eta: 0:00:03 time: 0.2051 data: 0.0662 max mem: 3395 +extract (validation) [28/29] eta: 0:00:00 time: 0.1755 data: 0.0510 max mem: 3395 +extract (validation) Total time: 0:00:10 (0.3496 s / it) +extract (test) [ 0/28] eta: 0:02:01 time: 4.3254 data: 4.1810 max mem: 3395 +extract (test) [20/28] eta: 0:00:03 time: 0.2022 data: 0.0643 max mem: 3395 +extract (test) [27/28] eta: 0:00:00 time: 0.1752 data: 0.0518 max mem: 3395 +extract (test) Total time: 0:00:10 (0.3572 s / it) +feature extraction time: 0:01:17 +train features: (471, 768) +validation features: (58, 768) +test features: (55, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|--------:|:--------|--------:|----------:|--------:|----------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_sex | | 0.35938 | train | 0.99622 | 0.002635 | 0.99613 | 0.0026985 | 0.99613 | 0.0027374 | +| flat_mae | reg | logistic | aabc_sex | | 0.35938 | test | 0.92727 | 0.036124 | 0.92424 | 0.037797 | 0.92424 | 0.038239 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 1, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04878905174573422, "f1": 0.8307692307692308, "f1_std": 0.050793873140110773, "bacc": 0.8288043478260869, "bacc_std": 0.05092548014139616} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 2, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.043970298013977754, "f1": 0.8879076086956521, "f1_std": 0.04530922378960111, "bacc": 0.8879076086956521, "bacc_std": 0.045544170797208176} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 3, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04937057041538505, "f1": 0.8281846581048247, "f1_std": 0.0531771399884078, "bacc": 0.8226902173913043, "bacc_std": 0.05331152750812794} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 4, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047300285673486014, "f1": 0.8521505376344086, "f1_std": 0.04783804078913595, "bacc": 0.8566576086956521, "bacc_std": 0.04713266054990701} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.051122927527756684, "f1": 0.8131793478260869, "f1_std": 0.05280821772163583, "bacc": 0.8131793478260869, "bacc_std": 0.0528974447875508} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 6, "C": 166.81005372000556, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030464720145665536, "f1": 0.9435897435897436, "f1_std": 0.031856996515590215, "bacc": 0.9408967391304348, "bacc_std": 0.03345344386828878} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 7, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04538473184119875, "f1": 0.8711943793911007, "f1_std": 0.04562365132356, "bacc": 0.8783967391304348, "bacc_std": 0.044191769792042805} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 8, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04784906019958457, "f1": 0.8328267477203647, "f1_std": 0.04890049102750025, "bacc": 0.8349184782608696, "bacc_std": 0.0489350795018083} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.039875425850727404, "f1": 0.8863636363636364, "f1_std": 0.04237492638234629, "bacc": 0.8817934782608696, "bacc_std": 0.04359885144805758} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04245329567948273, "f1": 0.8891129032258065, "f1_std": 0.042948231050356, "bacc": 0.8940217391304348, "bacc_std": 0.04190508088782208} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 11, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041339937266802185, "f1": 0.884453781512605, "f1_std": 0.045845344408521095, "bacc": 0.8756793478260869, "bacc_std": 0.04692616111634535} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 12, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04838242970472059, "f1": 0.8484848484848485, "f1_std": 0.05113010272550589, "bacc": 0.8444293478260869, "bacc_std": 0.05144952348912853} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 13, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.046665682791674885, "f1": 0.8711943793911007, "f1_std": 0.04684649393083506, "bacc": 0.8783967391304348, "bacc_std": 0.04540061546856371} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 14, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03398589887459283, "f1": 0.9260752688172043, "f1_std": 0.034311913578061945, "bacc": 0.9313858695652174, "bacc_std": 0.03267465845875645} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 15, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04882411001757494, "f1": 0.8281846581048247, "f1_std": 0.05219634790059309, "bacc": 0.8226902173913043, "bacc_std": 0.05202307742205047} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 16, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.049857966860915315, "f1": 0.8281846581048247, "f1_std": 0.05424034522368572, "bacc": 0.8226902173913043, "bacc_std": 0.05424584222108683} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.8, "acc_std": 0.049709290416571086, "f1": 0.7861435136090491, "f1_std": 0.05529395035443376, "bacc": 0.7792119565217391, "bacc_std": 0.0539233307128535} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 18, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.053335166635157305, "f1": 0.8166666666666667, "f1_std": 0.05345539508349983, "bacc": 0.8254076086956521, "bacc_std": 0.05211146830666055} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.049113408985212555, "f1": 0.8343927735028438, "f1_std": 0.049324040007927034, "bacc": 0.8410326086956521, "bacc_std": 0.048334336523767625} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 20, "C": 2.782559402207126, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03356377425363186, "f1": 0.9229691876750701, "f1_std": 0.03715940739966153, "bacc": 0.9130434782608696, "bacc_std": 0.04013059965108157} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 21, "C": 166.81005372000556, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05289383097651274, "f1": 0.7727272727272727, "f1_std": 0.056070360552661465, "bacc": 0.7697010869565217, "bacc_std": 0.05540534069699311} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 22, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04588847421864994, "f1": 0.8484848484848485, "f1_std": 0.04869388556736162, "bacc": 0.8444293478260869, "bacc_std": 0.04908840214540535} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04985892163009244, "f1": 0.8354935194416749, "f1_std": 0.04981141581980006, "bacc": 0.8471467391304348, "bacc_std": 0.047427565059179444} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05895139894876565, "f1": 0.7758152173913043, "f1_std": 0.06088381162785889, "bacc": 0.7758152173913043, "bacc_std": 0.060935323685145225} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.030121099932722, "f1": 0.9442755825734549, "f1_std": 0.03061548458588365, "bacc": 0.9470108695652174, "bacc_std": 0.029236769163787205} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.04932115701122205, "f1": 0.790003471017008, "f1_std": 0.05312854744297095, "bacc": 0.7853260869565217, "bacc_std": 0.052592327630807345} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.045531149994643326, "f1": 0.84593837535014, "f1_std": 0.049674929326242574, "bacc": 0.8383152173913043, "bacc_std": 0.049667072639924786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 28, "C": 2.782559402207126, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04906633728479692, "f1": 0.8521505376344086, "f1_std": 0.04955629598032052, "bacc": 0.8566576086956521, "bacc_std": 0.04875061078439902} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.044815507941627905, "f1": 0.8699763593380614, "f1_std": 0.045706183777371255, "bacc": 0.8722826086956521, "bacc_std": 0.045414490362016426} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 30, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.04010768974722309, "f1": 0.9079959852793577, "f1_std": 0.04022769330940008, "bacc": 0.9157608695652174, "bacc_std": 0.03771101025441605} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 31, "C": 0.046415888336127774, "split": "test", "acc": 0.8, "acc_std": 0.05281752776938182, "f1": 0.7975911676145868, "f1_std": 0.05301377698028716, "bacc": 0.8036684782608696, "bacc_std": 0.05197778074587208} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 32, "C": 166.81005372000556, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.045053708995096885, "f1": 0.84593837535014, "f1_std": 0.049635685608247763, "bacc": 0.8383152173913043, "bacc_std": 0.049732194917444676} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04238976954388252, "f1": 0.8683760683760684, "f1_std": 0.04454514293155388, "bacc": 0.8661684782608696, "bacc_std": 0.04527064341394798} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 34, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04271258548341093, "f1": 0.8879076086956521, "f1_std": 0.04398485895302395, "bacc": 0.8879076086956521, "bacc_std": 0.0441251714264263} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03837871310811126, "f1": 0.9071259709557582, "f1_std": 0.039029830616125395, "bacc": 0.9096467391304348, "bacc_std": 0.03833939346255904} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 36, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041122674769101406, "f1": 0.8879076086956521, "f1_std": 0.042293800769416245, "bacc": 0.8879076086956521, "bacc_std": 0.04219653564933697} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.058827103440281275, "f1": 0.7555555555555555, "f1_std": 0.061475708189840605, "bacc": 0.7540760869565217, "bacc_std": 0.061145286992873034} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 38, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04876008393270016, "f1": 0.8250265111346766, "f1_std": 0.054205102480322453, "bacc": 0.8165760869565217, "bacc_std": 0.05348034752786048} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.036207282040043726, "f1": 0.905982905982906, "f1_std": 0.03784871836901494, "bacc": 0.9035326086956521, "bacc_std": 0.0386617676507787} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 40, "C": 21.54434690031882, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04943682837723308, "f1": 0.8328267477203647, "f1_std": 0.050379989773158045, "bacc": 0.8349184782608696, "bacc_std": 0.05011797105985936} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.038480287966483194, "f1": 0.905982905982906, "f1_std": 0.040362495966507414, "bacc": 0.9035326086956521, "bacc_std": 0.04107032746648314} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.05695677351805294, "f1": 0.7607895617263298, "f1_std": 0.0573077708763622, "bacc": 0.7663043478260869, "bacc_std": 0.056655096177086736} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.0370304498335631, "f1": 0.9079959852793577, "f1_std": 0.03715171793773863, "bacc": 0.9157608695652174, "bacc_std": 0.03461531769981152} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.8, "acc_std": 0.049848908904892415, "f1": 0.790003471017008, "f1_std": 0.0535331196612943, "bacc": 0.7853260869565217, "bacc_std": 0.05279558305024048} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 45, "C": 21.54434690031882, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.034420520498751314, "f1": 0.9252717391304348, "f1_std": 0.035543324911137035, "bacc": 0.9252717391304348, "bacc_std": 0.03607356402960767} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04606678586932865, "f1": 0.8683760683760684, "f1_std": 0.04810424020671304, "bacc": 0.8661684782608696, "bacc_std": 0.0485527380172785} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04627722428585473, "f1": 0.8250265111346766, "f1_std": 0.05193517159002764, "bacc": 0.8165760869565217, "bacc_std": 0.051473059834153394} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04178906496217907, "f1": 0.8879076086956521, "f1_std": 0.04306436179205185, "bacc": 0.8879076086956521, "bacc_std": 0.04326713931636038} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.051444085027314054, "f1": 0.8166666666666667, "f1_std": 0.0516295507315779, "bacc": 0.8254076086956521, "bacc_std": 0.05051938021250624} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 50, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05264242703340091, "f1": 0.8328267477203647, "f1_std": 0.053484885818128866, "bacc": 0.8349184782608696, "bacc_std": 0.053023739725385106} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 51, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.042230003825958796, "f1": 0.8639095086603039, "f1_std": 0.04792332333618021, "bacc": 0.8539402173913043, "bacc_std": 0.048416049506693475} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 52, "C": 21.54434690031882, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05155948181750136, "f1": 0.8106060606060606, "f1_std": 0.054806682213843536, "bacc": 0.8070652173913043, "bacc_std": 0.05475552581177027} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 53, "C": 10000.0, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04718395861321113, "f1": 0.8521505376344086, "f1_std": 0.047962697984512005, "bacc": 0.8566576086956521, "bacc_std": 0.04773131425935898} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 54, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04646646707017298, "f1": 0.8699763593380614, "f1_std": 0.04727874773091675, "bacc": 0.8722826086956521, "bacc_std": 0.04677853172076245} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 55, "C": 2.782559402207126, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05046522081985465, "f1": 0.8328267477203647, "f1_std": 0.051509408070540004, "bacc": 0.8349184782608696, "bacc_std": 0.051246225104043946} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 56, "C": 0.3593813663804626, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.049089562271087114, "f1": 0.8131793478260869, "f1_std": 0.050759399628519206, "bacc": 0.8131793478260869, "bacc_std": 0.05085090556831021} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 57, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04239224940855764, "f1": 0.8879076086956521, "f1_std": 0.04379206517870961, "bacc": 0.8879076086956521, "bacc_std": 0.04387796189609727} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.056758161753353444, "f1": 0.7607895617263298, "f1_std": 0.05701274578796561, "bacc": 0.7663043478260869, "bacc_std": 0.05669679652677279} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.048037175686481415, "f1": 0.8354935194416749, "f1_std": 0.04794510729278932, "bacc": 0.8471467391304348, "bacc_std": 0.04554013528884234} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047780143875467015, "f1": 0.8484848484848485, "f1_std": 0.050624116585314564, "bacc": 0.8444293478260869, "bacc_std": 0.05112141419669558} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.041437380816427324, "f1": 0.8891129032258065, "f1_std": 0.04176354832299889, "bacc": 0.8940217391304348, "bacc_std": 0.04049168659406426} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.04099927030191216, "f1": 0.8891129032258065, "f1_std": 0.04136552721701025, "bacc": 0.8940217391304348, "bacc_std": 0.040061971904152775} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.029934230937476623, "f1": 0.9435897435897436, "f1_std": 0.03138985009877738, "bacc": 0.9408967391304348, "bacc_std": 0.032919090083216154} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 64, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04716850048513867, "f1": 0.8521505376344086, "f1_std": 0.04774354321752257, "bacc": 0.8566576086956521, "bacc_std": 0.047267771812429304} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 65, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045190505841181026, "f1": 0.8683760683760684, "f1_std": 0.04717683417932218, "bacc": 0.8661684782608696, "bacc_std": 0.04754874920459581} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05096391852806782, "f1": 0.8307692307692308, "f1_std": 0.05321866936233793, "bacc": 0.8288043478260869, "bacc_std": 0.05338121068044289} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04490571941705906, "f1": 0.8699763593380614, "f1_std": 0.04587421889846148, "bacc": 0.8722826086956521, "bacc_std": 0.04573827284697767} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 68, "C": 2.782559402207126, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.0408511751654306, "f1": 0.884453781512605, "f1_std": 0.04498039033598734, "bacc": 0.8756793478260869, "bacc_std": 0.04620734528721433} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 69, "C": 2.782559402207126, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.028858251466191625, "f1": 0.9427282193682749, "f1_std": 0.03126170377286141, "bacc": 0.9347826086956521, "bacc_std": 0.034504431100881285} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 70, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.039024061236266804, "f1": 0.9071259709557582, "f1_std": 0.03976427620716095, "bacc": 0.9096467391304348, "bacc_std": 0.03932100736277034} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 71, "C": 0.005994842503189409, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.046335834801769324, "f1": 0.8074229691876751, "f1_std": 0.050612761424560185, "bacc": 0.8009510869565217, "bacc_std": 0.04989871703229617} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 72, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03477808752506134, "f1": 0.9252717391304348, "f1_std": 0.035761751674160236, "bacc": 0.9252717391304348, "bacc_std": 0.035871101411233335} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.9454545454545454, "acc_std": 0.027465957892911858, "f1": 0.9427282193682749, "f1_std": 0.029833805294656204, "bacc": 0.9347826086956521, "bacc_std": 0.03283973226326418} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04392828114435528, "f1": 0.8663658451926415, "f1_std": 0.04722950787830501, "bacc": 0.8600543478260869, "bacc_std": 0.048088630906850255} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 75, "C": 0.3593813663804626, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05191428408985317, "f1": 0.7758152173913043, "f1_std": 0.05393519564517808, "bacc": 0.7758152173913043, "bacc_std": 0.05433261014918414} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 76, "C": 0.046415888336127774, "split": "test", "acc": 0.8181818181818182, "acc_std": 0.05152216565439583, "f1": 0.8106060606060606, "f1_std": 0.054703395687990576, "bacc": 0.8070652173913043, "bacc_std": 0.05450938222698876} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04860058156982915, "f1": 0.8250265111346766, "f1_std": 0.05473858143502813, "bacc": 0.8165760869565217, "bacc_std": 0.0541095486343354} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.9636363636363636, "acc_std": 0.025061141762622894, "f1": 0.9630376344086022, "f1_std": 0.02518974230140629, "bacc": 0.96875, "bacc_std": 0.021536918702254042} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 79, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05011688816495733, "f1": 0.8281846581048247, "f1_std": 0.054043961566229454, "bacc": 0.8226902173913043, "bacc_std": 0.053893677148751824} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 80, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0470691420384035, "f1": 0.84593837535014, "f1_std": 0.05192120391269799, "bacc": 0.8383152173913043, "bacc_std": 0.052042503640169456} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04561942459990529, "f1": 0.8484848484848485, "f1_std": 0.04833941315529502, "bacc": 0.8444293478260869, "bacc_std": 0.04891893752229796} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04603497053758905, "f1": 0.8281846581048247, "f1_std": 0.04967580339768975, "bacc": 0.8226902173913043, "bacc_std": 0.04983712800676367} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 83, "C": 166.81005372000556, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.040373315792725926, "f1": 0.8609606356085229, "f1_std": 0.04853180712733903, "bacc": 0.8478260869565217, "bacc_std": 0.04827244279565058} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.7636363636363637, "acc_std": 0.058607262687054594, "f1": 0.7555555555555555, "f1_std": 0.06058215084947754, "bacc": 0.7540760869565217, "bacc_std": 0.06008471558761189} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.04534450680645517, "f1": 0.8521505376344086, "f1_std": 0.04610360165495689, "bacc": 0.8566576086956521, "bacc_std": 0.04608245664413496} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 86, "C": 0.005994842503189409, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04724525075611582, "f1": 0.8699763593380614, "f1_std": 0.04803777289748641, "bacc": 0.8722826086956521, "bacc_std": 0.04755470921834729} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 87, "C": 21.54434690031882, "split": "test", "acc": 0.8, "acc_std": 0.05266492865981876, "f1": 0.790003471017008, "f1_std": 0.056646254632873254, "bacc": 0.7853260869565217, "bacc_std": 0.05591788830996608} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 88, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.048034422918610827, "f1": 0.8683760683760684, "f1_std": 0.05000010522611678, "bacc": 0.8661684782608696, "bacc_std": 0.050509540090193594} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.04836369104576537, "f1": 0.8281846581048247, "f1_std": 0.0522476145570863, "bacc": 0.8226902173913043, "bacc_std": 0.05212117003680967} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.8363636363636363, "acc_std": 0.05043357139809691, "f1": 0.8281846581048247, "f1_std": 0.054618886000415194, "bacc": 0.8226902173913043, "bacc_std": 0.054659761649513625} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 91, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.0481018753607709, "f1": 0.8521505376344086, "f1_std": 0.048586201340465214, "bacc": 0.8566576086956521, "bacc_std": 0.047759252859324385} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 92, "C": 0.046415888336127774, "split": "test", "acc": 0.9090909090909091, "acc_std": 0.03737502591281338, "f1": 0.905982905982906, "f1_std": 0.039091733600425914, "bacc": 0.9035326086956521, "bacc_std": 0.040039982989153976} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.04484641928085283, "f1": 0.8639095086603039, "f1_std": 0.050315887270863474, "bacc": 0.8539402173913043, "bacc_std": 0.05101077945347751} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 94, "C": 0.005994842503189409, "split": "test", "acc": 0.8909090909090909, "acc_std": 0.03886078564770693, "f1": 0.8863636363636364, "f1_std": 0.04134002386122689, "bacc": 0.8817934782608696, "bacc_std": 0.04234252218607174} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 95, "C": 2.782559402207126, "split": "test", "acc": 0.8727272727272727, "acc_std": 0.045928525139477344, "f1": 0.8699763593380614, "f1_std": 0.04692464121740007, "bacc": 0.8722826086956521, "bacc_std": 0.04679734925900763} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03486836639716022, "f1": 0.9252717391304348, "f1_std": 0.03582425508042928, "bacc": 0.9252717391304348, "bacc_std": 0.035893155816074857} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 97, "C": 21.54434690031882, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.047924720583172986, "f1": 0.8521505376344086, "f1_std": 0.048493295063604974, "bacc": 0.8566576086956521, "bacc_std": 0.04777858165926426} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 98, "C": 21.54434690031882, "split": "test", "acc": 0.7818181818181819, "acc_std": 0.05593832495120949, "f1": 0.7758152173913043, "f1_std": 0.05780587677586161, "bacc": 0.7758152173913043, "bacc_std": 0.058084546766919876} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 99, "C": 0.3593813663804626, "split": "test", "acc": 0.8545454545454545, "acc_std": 0.05012771787318421, "f1": 0.8484848484848485, "f1_std": 0.05366999047934252, "bacc": 0.8444293478260869, "bacc_std": 0.05436362900341514} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "aabc_sex", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.9272727272727272, "acc_std": 0.03417909080028146, "f1": 0.9252717391304348, "f1_std": 0.03528196673215015, "bacc": 0.9252717391304348, "bacc_std": 0.03556974734271991} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | aabc_sex | train | 100 | 111.06 | 999.55 | 0.97004 | 0.034094 | 0.96917 | 0.03511 | 0.96866 | 0.035922 | +| flat_mae | reg | logistic | aabc_sex | test | 100 | 111.06 | 999.55 | 0.86018 | 0.045844 | 0.85539 | 0.047494 | 0.85453 | 0.047994 | + + +done! total time: 0:05:15 diff --git a/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ff7678fdf3eb69a03a1f698de42588b2773482c0 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..d5da4074b6074b68c10cb45e42a8bfc1fa84f013 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,train,0.8048433048433048,0.013719501824729186,0.8007181886561003,0.01410177746194876,0.7985504629325628,0.014071714903408103 +flat_mae,patch,logistic,abide_dx,,0.046415888336127774,test,0.6370967741935484,0.041930880640653465,0.6301451580831179,0.043253016133668935,0.6301387797852841,0.04236249519201268 +flat_mae,patch,logistic,abide_dx,1,0.005994842503189409,train,0.7136752136752137,0.0171057651937472,0.7046066886481395,0.01799207407451506,0.7031007751937984,0.017602332555306174 +flat_mae,patch,logistic,abide_dx,1,0.005994842503189409,test,0.6370967741935484,0.0413540681071578,0.6217205613178767,0.0445126440094066,0.6234243697478992,0.042419518767649766 +flat_mae,patch,logistic,abide_dx,2,0.046415888336127774,train,0.7763532763532763,0.015789840016130697,0.7706183153202091,0.01641474658430577,0.7682170542635659,0.016263535578705923 +flat_mae,patch,logistic,abide_dx,2,0.046415888336127774,test,0.6209677419354839,0.04108504922123041,0.6137071651090342,0.04255898861007961,0.6134453781512605,0.04193651270931691 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,train,0.99002849002849,0.0036976709579445177,0.9899254350986032,0.003734234677147886,0.9900701365817646,0.0036889128659866118 +flat_mae,patch,logistic,abide_dx,3,2.782559402207126,test,0.6290322580645161,0.04313506062050511,0.6274817136886102,0.043307083691054085,0.6286764705882353,0.04350144010596647 +flat_mae,patch,logistic,abide_dx,4,0.005994842503189409,train,0.7150997150997151,0.01645814943630765,0.7059242440744993,0.01730640395327445,0.7043927648578812,0.016940951389988773 +flat_mae,patch,logistic,abide_dx,4,0.005994842503189409,test,0.6370967741935484,0.0413364032181002,0.6217205613178767,0.04428477850654438,0.6234243697478992,0.04227903888347496 +flat_mae,patch,logistic,abide_dx,5,0.046415888336127774,train,0.7948717948717948,0.015686050587002297,0.7904477611940299,0.016205437856568927,0.7882613510520486,0.016150168535988833 +flat_mae,patch,logistic,abide_dx,5,0.046415888336127774,test,0.6290322580645161,0.04249135310212574,0.6242424242424243,0.043032535395791986,0.6239495798319328,0.04285442692003955 +flat_mae,patch,logistic,abide_dx,6,0.046415888336127774,train,0.7962962962962963,0.014671060158311025,0.7928147889780258,0.01499599752663489,0.7913252122554448,0.014995310539022566 +flat_mae,patch,logistic,abide_dx,6,0.046415888336127774,test,0.5564516129032258,0.047866000524834924,0.5557292684515667,0.047736350856069316,0.5577731092436975,0.04768685760723221 +flat_mae,patch,logistic,abide_dx,7,0.005994842503189409,train,0.7008547008547008,0.01736009699719115,0.6908967391304348,0.018428802839526366,0.6897009966777409,0.0179993278108003 +flat_mae,patch,logistic,abide_dx,7,0.005994842503189409,test,0.6048387096774194,0.04074862343901715,0.5907590759075907,0.0425868877379737,0.592436974789916,0.04119028767278138 +flat_mae,patch,logistic,abide_dx,8,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,8,166.81005372000556,test,0.6129032258064516,0.04215123161596794,0.6063492063492064,0.042936350434970946,0.60609243697479,0.042606560890562285 +flat_mae,patch,logistic,abide_dx,9,0.005994842503189409,train,0.7022792022792023,0.016021398868727495,0.6918744211541006,0.016925456134205544,0.6906976744186046,0.016487651875564217 +flat_mae,patch,logistic,abide_dx,9,0.005994842503189409,test,0.6693548387096774,0.03976385811350252,0.6473118279569892,0.0442451588394283,0.6512605042016807,0.04101981158689187 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,train,0.8034188034188035,0.015014422332540356,0.79934714708246,0.015555015349776782,0.7971945367294204,0.015611362803438486 +flat_mae,patch,logistic,abide_dx,10,0.046415888336127774,test,0.6129032258064516,0.045363427237116796,0.6092436974789917,0.04601668820063395,0.6092436974789917,0.045958795153788076 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,train,0.896011396011396,0.012079520437630508,0.8944641345692461,0.012312858314999826,0.8929863418235511,0.01246821035504638 +flat_mae,patch,logistic,abide_dx,11,0.3593813663804626,test,0.5725806451612904,0.04532365685784569,0.5623043623043623,0.04650999812493861,0.5630252100840336,0.04571640552502948 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,train,0.792022792022792,0.015244006598576967,0.7878890728476822,0.01570240106573816,0.7859726836471022,0.015668020646655925 +flat_mae,patch,logistic,abide_dx,12,0.046415888336127774,test,0.5806451612903226,0.04278269511193261,0.5778999738151349,0.043087795982312355,0.5782563025210083,0.04315770624781674 +flat_mae,patch,logistic,abide_dx,13,2.782559402207126,train,0.9957264957264957,0.002398921303136288,0.9956823293279728,0.0024229374928977708,0.995828719084533,0.0023550591069073693 +flat_mae,patch,logistic,abide_dx,13,2.782559402207126,test,0.6693548387096774,0.04299145366755504,0.6630211440312852,0.04405255706561303,0.6622899159663866,0.04351216939338733 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,train,0.9928774928774928,0.0031530160505481896,0.992790757381258,0.0031977034784330316,0.9920634920634921,0.0035133607420393966 +flat_mae,patch,logistic,abide_dx,14,2.782559402207126,test,0.5806451612903226,0.042709174906896616,0.5643243243243243,0.04513708565871105,0.5672268907563025,0.04322054994163373 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,train,0.8917378917378918,0.01162925796910558,0.8902402896642527,0.011856554484565473,0.889110372831303,0.012051244575014134 +flat_mae,patch,logistic,abide_dx,15,0.3593813663804626,test,0.6048387096774194,0.044774844282711945,0.6004471624909581,0.04550340991937661,0.6003151260504203,0.045195574619394406 +flat_mae,patch,logistic,abide_dx,16,0.005994842503189409,train,0.7065527065527065,0.01675195723492395,0.6967844202898551,0.0175899962584629,0.6954595791805094,0.017180109796192212 +flat_mae,patch,logistic,abide_dx,16,0.005994842503189409,test,0.6290322580645161,0.04360293775723596,0.6169755573462261,0.04563422766744549,0.6176470588235294,0.044284053352422185 +flat_mae,patch,logistic,abide_dx,17,2.782559402207126,train,0.9886039886039886,0.0037293381999207176,0.9884615384615385,0.0037836261381679038,0.9875968992248062,0.004056603059752365 +flat_mae,patch,logistic,abide_dx,17,2.782559402207126,test,0.6290322580645161,0.04436590770974339,0.6255252100840336,0.04503818082502933,0.6255252100840336,0.04504039081857175 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,train,0.8774928774928775,0.012248831764504448,0.8753520254366767,0.012525957486008094,0.8732373569582872,0.012614556474199384 +flat_mae,patch,logistic,abide_dx,18,0.3593813663804626,test,0.6612903225806451,0.04337462046303316,0.6590730557737627,0.04357431449332335,0.6596638655462186,0.04363076014911423 +flat_mae,patch,logistic,abide_dx,19,0.046415888336127774,train,0.7977207977207977,0.014496116212575573,0.7924374297255653,0.015039236933139194,0.7896640826873385,0.014929628004878423 +flat_mae,patch,logistic,abide_dx,19,0.046415888336127774,test,0.5967741935483871,0.04292130349190631,0.5836690840719849,0.04522622381151135,0.5850840336134454,0.04367885899094509 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,train,0.8988603988603988,0.011401640703657628,0.8973555281426915,0.011623533795279594,0.8958656330749355,0.011761567911213055 +flat_mae,patch,logistic,abide_dx,20,0.3593813663804626,test,0.5725806451612904,0.043190798895843395,0.5643931861867832,0.044062420718036927,0.5646008403361344,0.04351088426791385 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,train,0.7806267806267806,0.015568496959577596,0.7760830481934697,0.01607806212594092,0.7741602067183463,0.016052965372511257 +flat_mae,patch,logistic,abide_dx,21,0.046415888336127774,test,0.5806451612903226,0.04426216418047864,0.5716183895827798,0.04518063219735387,0.571953781512605,0.044498790031625046 +flat_mae,patch,logistic,abide_dx,22,0.005994842503189409,train,0.7094017094017094,0.01640367666445383,0.6987504733055661,0.01732937029919764,0.697452934662237,0.01683669332987146 +flat_mae,patch,logistic,abide_dx,22,0.005994842503189409,test,0.6290322580645161,0.038247030313261675,0.5988748241912799,0.04404624830365543,0.6081932773109243,0.03938817822095583 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,train,0.801994301994302,0.014673612371921095,0.7976378850879831,0.015146413330033899,0.7953119232188999,0.01511970142885264 +flat_mae,patch,logistic,abide_dx,23,0.046415888336127774,test,0.5806451612903226,0.04264475867263947,0.5643243243243243,0.045159713197064036,0.5672268907563025,0.043278027486011166 +flat_mae,patch,logistic,abide_dx,24,0.046415888336127774,train,0.792022792022792,0.015294469195778489,0.7877150976379649,0.0157694213239284,0.7856773717238834,0.01573619663781415 +flat_mae,patch,logistic,abide_dx,24,0.046415888336127774,test,0.6129032258064516,0.0424024742568277,0.6092436974789917,0.04295759391042048,0.6092436974789917,0.04296153729402433 +flat_mae,patch,logistic,abide_dx,25,0.046415888336127774,train,0.7891737891737892,0.015475200237405826,0.7844427662099471,0.015991922847636217,0.7822074566260613,0.015925597322405262 +flat_mae,patch,logistic,abide_dx,25,0.046415888336127774,test,0.6370967741935484,0.04137057473246012,0.6342182890855457,0.041843884689032294,0.634453781512605,0.04173519074636086 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,train,0.9031339031339032,0.010913938680227548,0.9016579866833674,0.011138460571374865,0.9000369139904023,0.01130439242131605 +flat_mae,patch,logistic,abide_dx,26,0.3593813663804626,test,0.6129032258064516,0.041550653614797164,0.6045708211533352,0.042960853995053915,0.6045168067226891,0.04217036711700941 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,train,0.8874643874643875,0.011961177707940817,0.8862341658546592,0.01209962484762592,0.8861203396087117,0.01216002523556953 +flat_mae,patch,logistic,abide_dx,27,0.3593813663804626,test,0.6048387096774194,0.04494434933271018,0.6017043592264831,0.04513042682401252,0.601890756302521,0.04502010771910276 +flat_mae,patch,logistic,abide_dx,28,2.782559402207126,train,0.9914529914529915,0.0034260831801664095,0.9913569505548625,0.003467609937489287,0.9910668143226282,0.003603875122604634 +flat_mae,patch,logistic,abide_dx,28,2.782559402207126,test,0.6048387096774194,0.042046738277681926,0.6004471624909581,0.04274295112115591,0.6003151260504203,0.0424989894972854 +flat_mae,patch,logistic,abide_dx,29,0.046415888336127774,train,0.7891737891737892,0.015157739130338018,0.7840628507295174,0.015685301483139808,0.7816168327796236,0.01557055541446876 +flat_mae,patch,logistic,abide_dx,29,0.046415888336127774,test,0.6612903225806451,0.0391307042963769,0.643092105263158,0.04279666290864247,0.645483193277311,0.0401455358090731 +flat_mae,patch,logistic,abide_dx,30,0.005994842503189409,train,0.7165242165242165,0.017137574846504643,0.7078443961577956,0.01797341281256036,0.7062753783684016,0.017628254759006652 +flat_mae,patch,logistic,abide_dx,30,0.005994842503189409,test,0.5887096774193549,0.041628138621346546,0.5765651155005022,0.04347266402869212,0.5777310924369747,0.04219842861335323 +flat_mae,patch,logistic,abide_dx,31,0.000774263682681127,train,0.6495726495726496,0.0164933740554273,0.6205972300337458,0.018650567232868648,0.6278331487633814,0.016972609654537594 +flat_mae,patch,logistic,abide_dx,31,0.000774263682681127,test,0.5725806451612904,0.040118123582120094,0.5400013998740113,0.044923966082496755,0.5519957983193278,0.040784098260129346 +flat_mae,patch,logistic,abide_dx,32,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,32,166.81005372000556,test,0.5967741935483871,0.04263601910204478,0.5941345902068604,0.04267443184443654,0.5945378151260504,0.04262416152457401 +flat_mae,patch,logistic,abide_dx,33,0.005994842503189409,train,0.717948717948718,0.01611371530740029,0.7082490239704462,0.01685000576933199,0.7066814322628276,0.016452027167243647 +flat_mae,patch,logistic,abide_dx,33,0.005994842503189409,test,0.5645161290322581,0.042961020979734976,0.5571428571428572,0.043827388923552583,0.5572478991596639,0.04332709357275242 +flat_mae,patch,logistic,abide_dx,34,0.005994842503189409,train,0.7222222222222222,0.016384683253261173,0.71220011647391,0.017332123454611093,0.7105574012550757,0.01686954980524529 +flat_mae,patch,logistic,abide_dx,34,0.005994842503189409,test,0.5887096774193549,0.04262076250446511,0.5765651155005022,0.04433040395864553,0.5777310924369747,0.04315559466330222 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,train,0.886039886039886,0.012072621923003245,0.884048395755048,0.012363323953729894,0.88187523071244,0.012495801885444363 +flat_mae,patch,logistic,abide_dx,35,0.3593813663804626,test,0.6774193548387096,0.043843041396282846,0.6753076721654884,0.04401292470378633,0.6759453781512605,0.04381282463251082 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,train,0.896011396011396,0.011655728534170464,0.8947450577663671,0.011841983846363266,0.8941675895164267,0.01198997982862024 +flat_mae,patch,logistic,abide_dx,36,0.3593813663804626,test,0.6693548387096774,0.040733707314096375,0.6575739206573719,0.043434569062111135,0.657563025210084,0.041833717096222606 +flat_mae,patch,logistic,abide_dx,37,0.005994842503189409,train,0.7094017094017094,0.016614472782439615,0.6987504733055661,0.017730912707985696,0.697452934662237,0.017242699880151428 +flat_mae,patch,logistic,abide_dx,37,0.005994842503189409,test,0.6532258064516129,0.040163505574349605,0.63853298081486,0.043007748866683265,0.6397058823529411,0.0411267143859546 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,train,0.886039886039886,0.011447843310072725,0.8843844956644186,0.011631703203711416,0.8830564784053156,0.01167573316616074 +flat_mae,patch,logistic,abide_dx,38,0.3593813663804626,test,0.6290322580645161,0.045235756578806366,0.6242424242424243,0.04614449429322273,0.6239495798319328,0.04601927920070753 +flat_mae,patch,logistic,abide_dx,39,0.046415888336127774,train,0.8034188034188035,0.01454010703340652,0.799179104477612,0.015010492581539426,0.7968992248062015,0.014979179368114595 +flat_mae,patch,logistic,abide_dx,39,0.046415888336127774,test,0.5483870967741935,0.04448014850269793,0.5441176470588236,0.045044664670335646,0.5441176470588236,0.044904531797821584 +flat_mae,patch,logistic,abide_dx,40,0.005994842503189409,train,0.7165242165242165,0.016421742132374954,0.7069323962867782,0.017169347697332072,0.7053894425987449,0.016783711651821853 +flat_mae,patch,logistic,abide_dx,40,0.005994842503189409,test,0.6451612903225806,0.039635973632891404,0.6288435374149659,0.043169562491677096,0.6307773109243697,0.040832271782975285 +flat_mae,patch,logistic,abide_dx,41,0.005994842503189409,train,0.7008547008547008,0.017164154308188788,0.6918504025886071,0.018109118806555326,0.6905869324473976,0.017759749098782578 +flat_mae,patch,logistic,abide_dx,41,0.005994842503189409,test,0.5887096774193549,0.03969714628933886,0.5649122807017544,0.043053121532163945,0.5714285714285714,0.04030853138760041 +flat_mae,patch,logistic,abide_dx,42,0.046415888336127774,train,0.7891737891737892,0.015464758019272015,0.7851559592049431,0.015892925683313196,0.7833887043189369,0.015861425610429723 +flat_mae,patch,logistic,abide_dx,42,0.046415888336127774,test,0.6209677419354839,0.04290447184705232,0.6137071651090342,0.043895819809497805,0.6134453781512605,0.043200473456294824 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,train,0.7891737891737892,0.014694651841854083,0.7849834437086092,0.015106600355826024,0.783093392395718,0.015072031804354591 +flat_mae,patch,logistic,abide_dx,43,0.046415888336127774,test,0.6774193548387096,0.039779997875934656,0.6669352672575879,0.041456608752838416,0.6664915966386555,0.04046611372366884 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,train,0.7236467236467237,0.016670815223816186,0.714447463768116,0.01764954589626934,0.712735326688815,0.017254554992663085 +flat_mae,patch,logistic,abide_dx,44,0.005994842503189409,test,0.6129032258064516,0.04080627310938899,0.588836695219674,0.04513230696424951,0.595063025210084,0.04176882254188167 +flat_mae,patch,logistic,abide_dx,45,0.046415888336127774,train,0.7849002849002849,0.015396094430196947,0.7807134951747536,0.01578689121577714,0.778922111480251,0.015742690000118895 +flat_mae,patch,logistic,abide_dx,45,0.046415888336127774,test,0.6048387096774194,0.04264866268384136,0.5931704050887178,0.04415897100605938,0.5940126050420168,0.04302443840552972 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,train,0.7207977207977208,0.01622178766090919,0.7135051846916254,0.016873591465846677,0.7119232188999631,0.01663464590078625 +flat_mae,patch,logistic,abide_dx,46,0.005994842503189409,test,0.5403225806451613,0.0425988353130836,0.5267492467358554,0.04436572763838384,0.5288865546218487,0.04305844212516156 +flat_mae,patch,logistic,abide_dx,47,0.046415888336127774,train,0.801994301994302,0.015273691070440984,0.798610179496123,0.015606766307833331,0.7970837947582133,0.015614951715900263 +flat_mae,patch,logistic,abide_dx,47,0.046415888336127774,test,0.6290322580645161,0.04038287105585534,0.6191239316239316,0.04187322781651601,0.6192226890756303,0.041016639224877895 +flat_mae,patch,logistic,abide_dx,48,2.782559402207126,train,0.9886039886039886,0.0040445566690351775,0.9884759340731499,0.004093991774347092,0.988187523071244,0.004232842106961258 +flat_mae,patch,logistic,abide_dx,48,2.782559402207126,test,0.5887096774193549,0.04328383202148465,0.5873947935016637,0.04331566816011826,0.5887605042016807,0.043354773773776695 +flat_mae,patch,logistic,abide_dx,49,0.005994842503189409,train,0.7094017094017094,0.017168444571295745,0.7003515232674924,0.017996165568886772,0.6989294942783315,0.017627631901596722 +flat_mae,patch,logistic,abide_dx,49,0.005994842503189409,test,0.5564516129032258,0.042674944458022654,0.5343756400628115,0.045136759158338466,0.5404411764705883,0.0429333075038373 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,train,0.896011396011396,0.011765884732505573,0.8944641345692461,0.011965835855950572,0.8929863418235511,0.012030173375080624 +flat_mae,patch,logistic,abide_dx,50,0.3593813663804626,test,0.5967741935483871,0.04394383180604676,0.5836690840719849,0.04588776957493644,0.5850840336134454,0.044418573331478105 +flat_mae,patch,logistic,abide_dx,51,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,51,1291.5496650148827,test,0.5483870967741935,0.04480261949752214,0.5407407407407407,0.045561320243139476,0.5409663865546219,0.04494279253299461 +flat_mae,patch,logistic,abide_dx,52,0.005994842503189409,train,0.7336182336182336,0.01621542577160026,0.7246048146011433,0.017149419849785637,0.7226651901070507,0.0167669004579093 +flat_mae,patch,logistic,abide_dx,52,0.005994842503189409,test,0.6129032258064516,0.04234237772129254,0.6003223207091055,0.04388798465189365,0.6013655462184874,0.04276781425143125 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,train,0.7948717948717948,0.014701755753211669,0.7900857199813941,0.015201555498335809,0.7876707272056109,0.015135039775108626 +flat_mae,patch,logistic,abide_dx,53,0.046415888336127774,test,0.6451612903225806,0.04308840403072121,0.6405797101449275,0.04367729059226176,0.6402310924369747,0.043482548787641545 +flat_mae,patch,logistic,abide_dx,54,0.005994842503189409,train,0.6994301994301995,0.016743596288005425,0.6895881838890647,0.01748789671246061,0.6884090070136581,0.017098231186156974 +flat_mae,patch,logistic,abide_dx,54,0.005994842503189409,test,0.6774193548387096,0.04308456401784404,0.6688034188034189,0.04463608086920211,0.6680672268907563,0.04370904905003232 +flat_mae,patch,logistic,abide_dx,55,0.046415888336127774,train,0.7977207977207977,0.015257833627383584,0.7918392916805881,0.015948015619107674,0.7887781469176818,0.015792968265492015 +flat_mae,patch,logistic,abide_dx,55,0.046415888336127774,test,0.5887096774193549,0.042624842653531204,0.5740553647201454,0.04447022416090202,0.576155462184874,0.04305052293145385 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,train,0.7094017094017094,0.016455402445418,0.6997282608695652,0.017214296175225824,0.6983388704318937,0.016795087092320825 +flat_mae,patch,logistic,abide_dx,56,0.005994842503189409,test,0.6612903225806451,0.0405704510504767,0.643092105263158,0.04392561804230355,0.645483193277311,0.04149815301618894 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,train,0.896011396011396,0.01138197140828498,0.8946775648785461,0.011528765737189786,0.8938722775932078,0.011551536265412261 +flat_mae,patch,logistic,abide_dx,57,0.3593813663804626,test,0.6612903225806451,0.03995656786182424,0.6580882352941176,0.04035410411973056,0.6580882352941176,0.04021099201390925 +flat_mae,patch,logistic,abide_dx,58,0.046415888336127774,train,0.7877492877492878,0.015047961623311235,0.7823065540300074,0.015618345616013614,0.779734219269103,0.015506962202975247 +flat_mae,patch,logistic,abide_dx,58,0.046415888336127774,test,0.5645161290322581,0.04368043004347049,0.555142173797502,0.04442032890884715,0.555672268907563,0.043815688325809114 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,train,0.8091168091168092,0.014449721160062521,0.8046631005382417,0.015059064178231005,0.8020671834625323,0.015108344726018711 +flat_mae,patch,logistic,abide_dx,59,0.046415888336127774,test,0.6290322580645161,0.042952506259409585,0.6266038229903116,0.043258917508129435,0.6271008403361344,0.04331637371844942 +flat_mae,patch,logistic,abide_dx,60,0.046415888336127774,train,0.801994301994302,0.014247708861949407,0.7974631521921877,0.014709048865617282,0.7950166112956811,0.014653312921695427 +flat_mae,patch,logistic,abide_dx,60,0.046415888336127774,test,0.6209677419354839,0.041998943919134196,0.6118548118548119,0.04360736611255973,0.6118697478991597,0.042744325268996665 +flat_mae,patch,logistic,abide_dx,61,2.782559402207126,train,0.9928774928774928,0.003208734912769237,0.9927996307502949,0.0032437693966492756,0.9926541159099298,0.0032640934838195604 +flat_mae,patch,logistic,abide_dx,61,2.782559402207126,test,0.5,0.04480751699887618,0.4952731092436975,0.0449423818137944,0.4952731092436975,0.04484025526374081 +flat_mae,patch,logistic,abide_dx,62,0.000774263682681127,train,0.6524216524216524,0.01688547627686341,0.6296699875466998,0.018867695190620714,0.6336655592469546,0.017460444903492182 +flat_mae,patch,logistic,abide_dx,62,0.000774263682681127,test,0.49193548387096775,0.03757549113210549,0.44227886056971516,0.040957788434021064,0.46743697478991597,0.03738294141446133 +flat_mae,patch,logistic,abide_dx,63,0.005994842503189409,train,0.717948717948718,0.016609927038375594,0.7069499144016125,0.017609341096731065,0.705500184569952,0.017062897895619798 +flat_mae,patch,logistic,abide_dx,63,0.005994842503189409,test,0.6209677419354839,0.044687826317910906,0.6167554415729598,0.045269810287524095,0.6165966386554622,0.04517071727373528 +flat_mae,patch,logistic,abide_dx,64,0.046415888336127774,train,0.782051282051282,0.015762463514470058,0.7772560893414491,0.0163106376033539,0.77515688445921,0.0162695286614955 +flat_mae,patch,logistic,abide_dx,64,0.046415888336127774,test,0.6693548387096774,0.04157218250176983,0.6553454003118433,0.04469494207524602,0.6559873949579832,0.04266080100807519 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,train,0.8974358974358975,0.01184169244602999,0.8959460460979767,0.012086340589663853,0.8945736434108527,0.012280377999528374 +flat_mae,patch,logistic,abide_dx,65,0.3593813663804626,test,0.6370967741935484,0.0414503545685747,0.6241664982824813,0.04381025120786185,0.625,0.042239211589379766 +flat_mae,patch,logistic,abide_dx,66,0.3593813663804626,train,0.9002849002849003,0.0108420857518795,0.8988364337063663,0.011053433947899786,0.8974529346622371,0.011206485905957226 +flat_mae,patch,logistic,abide_dx,66,0.3593813663804626,test,0.5806451612903226,0.04354066837210107,0.5788923719958203,0.04377482800076446,0.5798319327731092,0.04369784052654255 +flat_mae,patch,logistic,abide_dx,67,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,67,21.54434690031882,test,0.5725806451612904,0.04073715587625844,0.5678306043269548,0.04119891535053769,0.5677521008403361,0.0411335854723978 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,train,0.8846153846153846,0.012183438155580968,0.8826433420085321,0.012455825458291016,0.8805832410483574,0.012557178856785612 +flat_mae,patch,logistic,abide_dx,68,0.3593813663804626,test,0.6129032258064516,0.04169566663365599,0.610369206598586,0.04176827217228901,0.6108193277310925,0.04174429054982945 +flat_mae,patch,logistic,abide_dx,69,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,69,10000.0,test,0.6048387096774194,0.04399135226247737,0.6046072753302532,0.04406297832447376,0.6081932773109244,0.04416637338939243 +flat_mae,patch,logistic,abide_dx,70,0.005994842503189409,train,0.7108262108262108,0.017133084274724122,0.7013573522724177,0.018216180847185556,0.6999261720191953,0.01777914192104647 +flat_mae,patch,logistic,abide_dx,70,0.005994842503189409,test,0.6209677419354839,0.04070968700475322,0.6097756946769334,0.04193263456038377,0.6102941176470589,0.04094494111161957 +flat_mae,patch,logistic,abide_dx,71,0.3593813663804626,train,0.8974358974358975,0.011789771045666775,0.8959460460979767,0.011988943059998987,0.8945736434108527,0.012051053084187914 +flat_mae,patch,logistic,abide_dx,71,0.3593813663804626,test,0.6129032258064516,0.04012958976897239,0.6003223207091055,0.04192472738566776,0.6013655462184874,0.040596885930704985 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,train,0.8917378917378918,0.0116475362253543,0.8904539369399707,0.011823078135028985,0.8899963086009597,0.011952254179587143 +flat_mae,patch,logistic,abide_dx,72,0.3593813663804626,test,0.6693548387096774,0.041345914567279644,0.665680278818965,0.04210229323894063,0.6654411764705883,0.04198157351540627 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,train,0.8931623931623932,0.011508381529626549,0.8919288392972604,0.011649820993383565,0.8915836101882613,0.011715936632763994 +flat_mae,patch,logistic,abide_dx,73,0.3593813663804626,test,0.5725806451612904,0.04335695979354436,0.5623043623043623,0.04480704743301905,0.5630252100840336,0.044018198675353684 +flat_mae,patch,logistic,abide_dx,74,0.005994842503189409,train,0.7165242165242165,0.016861253587729944,0.7084249084249084,0.0176745587232477,0.7068660022148394,0.0173896570682708 +flat_mae,patch,logistic,abide_dx,74,0.005994842503189409,test,0.5967741935483871,0.043074651459240706,0.5860042735042735,0.044687270103453455,0.5866596638655462,0.04362876863784573 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,train,0.99002849002849,0.003971007174474026,0.989913358334411,0.004021415845040941,0.9894795127353266,0.0042148129939262625 +flat_mae,patch,logistic,abide_dx,75,2.782559402207126,test,0.5887096774193549,0.04244870504306941,0.5854473942969518,0.04277510884061642,0.585609243697479,0.04280705844485323 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,train,0.8931623931623932,0.011825970261128914,0.8914958731336362,0.01209174384857023,0.8898117386489479,0.012270972430327662 +flat_mae,patch,logistic,abide_dx,76,0.3593813663804626,test,0.5967741935483871,0.04557067900085948,0.58994708994709,0.04643368145260979,0.5898109243697479,0.045895271723382314 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,train,0.896011396011396,0.01150340282508601,0.8944641345692461,0.01174352673395503,0.8929863418235511,0.011916792903374905 +flat_mae,patch,logistic,abide_dx,77,0.3593813663804626,test,0.5403225806451613,0.04490103581978825,0.5388530045018595,0.04506993946207348,0.5399159663865546,0.04521782898647137 +flat_mae,patch,logistic,abide_dx,78,0.3593813663804626,train,0.905982905982906,0.010296589154488462,0.904867892605764,0.010432642625652319,0.9043927648578811,0.010516917596618394 +flat_mae,patch,logistic,abide_dx,78,0.3593813663804626,test,0.5564516129032258,0.043312608440822076,0.5541026479241582,0.04375910087160651,0.5546218487394958,0.043903278345784724 +flat_mae,patch,logistic,abide_dx,79,2.782559402207126,train,0.9857549857549858,0.004455057093358465,0.9855860443342066,0.00451562195229425,0.9850129198966409,0.004739067120698339 +flat_mae,patch,logistic,abide_dx,79,2.782559402207126,test,0.6129032258064516,0.043516105119675866,0.6045708211533352,0.04487606551140039,0.6045168067226891,0.04418388648515332 +flat_mae,patch,logistic,abide_dx,80,2.782559402207126,train,0.9914529914529915,0.0036076465339177823,0.991351626600524,0.0036550895259955677,0.9907715023994094,0.0038796660945131945 +flat_mae,patch,logistic,abide_dx,80,2.782559402207126,test,0.6532258064516129,0.04358989658495648,0.6480760345851759,0.0442043492689369,0.6475840336134454,0.043980583142059874 +flat_mae,patch,logistic,abide_dx,81,2.782559402207126,train,0.9928774928774928,0.00311816170904111,0.9927952559531508,0.0031575056354073766,0.9923588039867111,0.0033544900533854227 +flat_mae,patch,logistic,abide_dx,81,2.782559402207126,test,0.6612903225806451,0.04515956217891696,0.6580882352941176,0.04594365845742023,0.6580882352941176,0.0458000828432345 +flat_mae,patch,logistic,abide_dx,82,0.005994842503189409,train,0.698005698005698,0.015703166146795736,0.6879528985507246,0.016610677097395804,0.6868217054263566,0.016204561074993785 +flat_mae,patch,logistic,abide_dx,82,0.005994842503189409,test,0.6370967741935484,0.04032088706120817,0.6190346145968457,0.04353036747671587,0.6218487394957983,0.04116091461162507 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,train,0.8888888888888888,0.011732157410464471,0.8873518762343646,0.011964111975785766,0.8862310815799188,0.01213916079441141 +flat_mae,patch,logistic,abide_dx,83,0.3593813663804626,test,0.6612903225806451,0.04704115971780727,0.6569169960474308,0.048004148104000194,0.6565126050420168,0.047684507981011454 +flat_mae,patch,logistic,abide_dx,84,0.046415888336127774,train,0.7977207977207977,0.014112101008533122,0.7933582089552238,0.014480848692680733,0.7911406423034331,0.014416041874040013 +flat_mae,patch,logistic,abide_dx,84,0.046415888336127774,test,0.6290322580645161,0.0433552347332143,0.6191239316239316,0.044919338641026076,0.6192226890756303,0.04390636728901356 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,train,0.792022792022792,0.014846120769035371,0.7878890728476822,0.015345442161177175,0.7859726836471022,0.015367257339060919 +flat_mae,patch,logistic,abide_dx,85,0.046415888336127774,test,0.6693548387096774,0.040122377183867054,0.6528982044104594,0.04396759538050346,0.6544117647058824,0.04128964065373109 +flat_mae,patch,logistic,abide_dx,86,0.046415888336127774,train,0.801994301994302,0.014179288829800261,0.7972847482627168,0.014712381234934414,0.7947212993724622,0.014670767571774348 +flat_mae,patch,logistic,abide_dx,86,0.046415888336127774,test,0.6129032258064516,0.04414849068732454,0.6063492063492064,0.04530152771990273,0.60609243697479,0.04484168034108939 +flat_mae,patch,logistic,abide_dx,87,2.782559402207126,train,0.9943019943019943,0.00276330365896161,0.9942447694628451,0.0027893959489608644,0.9945367294204503,0.002673826569150239 +flat_mae,patch,logistic,abide_dx,87,2.782559402207126,test,0.6451612903225806,0.043857576229380496,0.6451612903225806,0.043981823989672944,0.6512605042016807,0.043678371951350575 +flat_mae,patch,logistic,abide_dx,88,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,patch,logistic,abide_dx,88,1291.5496650148827,test,0.4838709677419355,0.04374165893432418,0.4700854700854701,0.04513550799502679,0.4726890756302521,0.04406401031229365 +flat_mae,patch,logistic,abide_dx,89,2.782559402207126,train,0.9914529914529915,0.003455670169116937,0.9913621262458472,0.0034922643761058155,0.9913621262458472,0.003497870732941329 +flat_mae,patch,logistic,abide_dx,89,2.782559402207126,test,0.5725806451612904,0.04501060980254641,0.5691904293674206,0.045419041245601546,0.569327731092437,0.045448733282695844 +flat_mae,patch,logistic,abide_dx,90,0.005994842503189409,train,0.698005698005698,0.016487407671676217,0.6882796987189692,0.017303635666999558,0.6871170173495755,0.016901177087125508 +flat_mae,patch,logistic,abide_dx,90,0.005994842503189409,test,0.5967741935483871,0.041084830770722384,0.5782312925170068,0.043923761763414615,0.5819327731092437,0.0417845551106481 +flat_mae,patch,logistic,abide_dx,91,0.005994842503189409,train,0.7136752136752137,0.01646742968567329,0.7046066886481395,0.017354239026497617,0.7031007751937984,0.01700038876088011 +flat_mae,patch,logistic,abide_dx,91,0.005994842503189409,test,0.6370967741935484,0.04077958761278596,0.6301451580831179,0.04169847938257321,0.6297268907563025,0.04120819183088193 +flat_mae,patch,logistic,abide_dx,92,0.3593813663804626,train,0.886039886039886,0.012175104591282588,0.8841354723707665,0.012431670036250975,0.882170542635659,0.012540716869198115 +flat_mae,patch,logistic,abide_dx,92,0.3593813663804626,test,0.5725806451612904,0.043692711860435524,0.5703170970905524,0.04384860554893189,0.5709033613445378,0.04371098251832914 +flat_mae,patch,logistic,abide_dx,93,0.005994842503189409,train,0.7094017094017094,0.016497633347610532,0.7000427289559892,0.01724760452669834,0.6986341823551125,0.016869906837272124 +flat_mae,patch,logistic,abide_dx,93,0.005994842503189409,test,0.5887096774193549,0.041577016283500925,0.5740553647201454,0.04377127055409218,0.576155462184874,0.042134492368304806 +flat_mae,patch,logistic,abide_dx,94,2.782559402207126,train,0.9886039886039886,0.004023182430229649,0.9884688354673653,0.004075924434876133,0.9878922111480251,0.004259072066004876 +flat_mae,patch,logistic,abide_dx,94,2.782559402207126,test,0.5887096774193549,0.042764446293684324,0.5808311791608669,0.043784163672292875,0.5808823529411764,0.04326289323966562 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,train,0.8974358974358975,0.011446992447390543,0.8959460460979767,0.011652619099319143,0.8945736434108527,0.011764459732383548 +flat_mae,patch,logistic,abide_dx,95,0.3593813663804626,test,0.5967741935483871,0.0445041475226991,0.5929621848739496,0.04512306945834566,0.5929621848739496,0.04501057822130937 +flat_mae,patch,logistic,abide_dx,96,0.046415888336127774,train,0.7991452991452992,0.015426108443613041,0.7943679820506695,0.016038269885567048,0.791842008121078,0.01600514787909484 +flat_mae,patch,logistic,abide_dx,96,0.046415888336127774,test,0.5887096774193549,0.04405069919871808,0.5826018084614877,0.044867150113164445,0.5824579831932774,0.04435502738963009 +flat_mae,patch,logistic,abide_dx,97,0.005994842503189409,train,0.7037037037037037,0.017184333816676785,0.6921494050279565,0.018273851879471604,0.6911037283130306,0.017674503332541232 +flat_mae,patch,logistic,abide_dx,97,0.005994842503189409,test,0.6935483870967742,0.03828414970489003,0.6835885038947085,0.040641394620409645,0.6827731092436975,0.0394055630434495 +flat_mae,patch,logistic,abide_dx,98,0.005994842503189409,train,0.7193732193732194,0.015841227255806983,0.7075760747521267,0.016952431852061602,0.7062015503875969,0.016361535253222283 +flat_mae,patch,logistic,abide_dx,98,0.005994842503189409,test,0.6370967741935484,0.04316731719337277,0.626380984265149,0.04441021684002011,0.6265756302521008,0.04346055146985166 +flat_mae,patch,logistic,abide_dx,99,0.046415888336127774,train,0.801994301994302,0.014990059286734865,0.7979764100844094,0.01544807285577632,0.7959025470653378,0.015439297839843824 +flat_mae,patch,logistic,abide_dx,99,0.046415888336127774,test,0.5967741935483871,0.04320956603918263,0.5915678524374176,0.04366914263639579,0.5913865546218487,0.043442450082562166 +flat_mae,patch,logistic,abide_dx,100,0.3593813663804626,train,0.8789173789173789,0.012569236180772256,0.8769393853775034,0.012842185347244192,0.8751199704688077,0.01293917095778721 +flat_mae,patch,logistic,abide_dx,100,0.3593813663804626,test,0.5806451612903226,0.04319412355973499,0.5643243243243243,0.04562847445640748,0.5672268907563025,0.04383054182789003 diff --git a/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a7bb560b605eabacdc6ab48a546a87b5d64040a1 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:45:54 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (abide_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic +model: flat_mae +representation: patch +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/abide_dx__patch__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:19:36 time: 4.0717 data: 3.3442 max mem: 2698 +extract (train) [ 20/289] eta: 0:01:44 time: 0.2027 data: 0.0700 max mem: 2852 +extract (train) [ 40/289] eta: 0:01:10 time: 0.1779 data: 0.0572 max mem: 2852 +extract (train) [ 60/289] eta: 0:00:56 time: 0.1677 data: 0.0531 max mem: 2852 +extract (train) [ 80/289] eta: 0:00:47 time: 0.1660 data: 0.0534 max mem: 2852 +extract (train) [100/289] eta: 0:00:40 time: 0.1576 data: 0.0483 max mem: 2852 +extract (train) [120/289] eta: 0:00:34 time: 0.1626 data: 0.0494 max mem: 2852 +extract (train) [140/289] eta: 0:00:29 time: 0.1576 data: 0.0479 max mem: 2852 +extract (train) [160/289] eta: 0:00:24 time: 0.1617 data: 0.0506 max mem: 2852 +extract (train) [180/289] eta: 0:00:20 time: 0.1604 data: 0.0494 max mem: 2852 +extract (train) [200/289] eta: 0:00:16 time: 0.1606 data: 0.0494 max mem: 2852 +extract (train) [220/289] eta: 0:00:12 time: 0.1642 data: 0.0512 max mem: 2852 +extract (train) [240/289] eta: 0:00:08 time: 0.1698 data: 0.0543 max mem: 2852 +extract (train) [260/289] eta: 0:00:05 time: 0.1718 data: 0.0553 max mem: 2852 +extract (train) [280/289] eta: 0:00:01 time: 0.1581 data: 0.0476 max mem: 2852 +extract (train) [288/289] eta: 0:00:00 time: 0.1566 data: 0.0484 max mem: 2852 +extract (train) Total time: 0:00:52 (0.1816 s / it) +extract (validation) [ 0/62] eta: 0:03:40 time: 3.5524 data: 3.3639 max mem: 2852 +extract (validation) [20/62] eta: 0:00:14 time: 0.1950 data: 0.0626 max mem: 2852 +extract (validation) [40/62] eta: 0:00:05 time: 0.1504 data: 0.0413 max mem: 2852 +extract (validation) [60/62] eta: 0:00:00 time: 0.1482 data: 0.0422 max mem: 2852 +extract (validation) [61/62] eta: 0:00:00 time: 0.1485 data: 0.0425 max mem: 2852 +extract (validation) Total time: 0:00:13 (0.2241 s / it) +extract (test) [ 0/62] eta: 0:03:35 time: 3.4692 data: 3.3123 max mem: 2852 +extract (test) [20/62] eta: 0:00:14 time: 0.1977 data: 0.0695 max mem: 2852 +extract (test) [40/62] eta: 0:00:05 time: 0.1488 data: 0.0426 max mem: 2852 +extract (test) [60/62] eta: 0:00:00 time: 0.1420 data: 0.0398 max mem: 2852 +extract (test) [61/62] eta: 0:00:00 time: 0.1417 data: 0.0398 max mem: 2852 +extract (test) Total time: 0:00:13 (0.2201 s / it) +feature extraction time: 0:01:20 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|---------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | | 0.046416 | train | 0.80484 | 0.01372 | 0.80072 | 0.014102 | 0.79855 | 0.014072 | +| flat_mae | patch | logistic | abide_dx | | 0.046416 | test | 0.6371 | 0.041931 | 0.63015 | 0.043253 | 0.63014 | 0.042362 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.0413540681071578, "f1": 0.6217205613178767, "f1_std": 0.0445126440094066, "bacc": 0.6234243697478992, "bacc_std": 0.042419518767649766} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04108504922123041, "f1": 0.6137071651090342, "f1_std": 0.04255898861007961, "bacc": 0.6134453781512605, "bacc_std": 0.04193651270931691} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04313506062050511, "f1": 0.6274817136886102, "f1_std": 0.043307083691054085, "bacc": 0.6286764705882353, "bacc_std": 0.04350144010596647} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.0413364032181002, "f1": 0.6217205613178767, "f1_std": 0.04428477850654438, "bacc": 0.6234243697478992, "bacc_std": 0.04227903888347496} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04249135310212574, "f1": 0.6242424242424243, "f1_std": 0.043032535395791986, "bacc": 0.6239495798319328, "bacc_std": 0.04285442692003955} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.047866000524834924, "f1": 0.5557292684515667, "f1_std": 0.047736350856069316, "bacc": 0.5577731092436975, "bacc_std": 0.04768685760723221} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04074862343901715, "f1": 0.5907590759075907, "f1_std": 0.0425868877379737, "bacc": 0.592436974789916, "bacc_std": 0.04119028767278138} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 166.81005372000556, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04215123161596794, "f1": 0.6063492063492064, "f1_std": 0.042936350434970946, "bacc": 0.60609243697479, "bacc_std": 0.042606560890562285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.005994842503189409, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.03976385811350252, "f1": 0.6473118279569892, "f1_std": 0.0442451588394283, "bacc": 0.6512605042016807, "bacc_std": 0.04101981158689187} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.045363427237116796, "f1": 0.6092436974789917, "f1_std": 0.04601668820063395, "bacc": 0.6092436974789917, "bacc_std": 0.045958795153788076} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04532365685784569, "f1": 0.5623043623043623, "f1_std": 0.04650999812493861, "bacc": 0.5630252100840336, "bacc_std": 0.04571640552502948} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04278269511193261, "f1": 0.5778999738151349, "f1_std": 0.043087795982312355, "bacc": 0.5782563025210083, "bacc_std": 0.04315770624781674} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 2.782559402207126, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04299145366755504, "f1": 0.6630211440312852, "f1_std": 0.04405255706561303, "bacc": 0.6622899159663866, "bacc_std": 0.04351216939338733} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042709174906896616, "f1": 0.5643243243243243, "f1_std": 0.04513708565871105, "bacc": 0.5672268907563025, "bacc_std": 0.04322054994163373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044774844282711945, "f1": 0.6004471624909581, "f1_std": 0.04550340991937661, "bacc": 0.6003151260504203, "bacc_std": 0.045195574619394406} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04360293775723596, "f1": 0.6169755573462261, "f1_std": 0.04563422766744549, "bacc": 0.6176470588235294, "bacc_std": 0.044284053352422185} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 2.782559402207126, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04436590770974339, "f1": 0.6255252100840336, "f1_std": 0.04503818082502933, "bacc": 0.6255252100840336, "bacc_std": 0.04504039081857175} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04337462046303316, "f1": 0.6590730557737627, "f1_std": 0.04357431449332335, "bacc": 0.6596638655462186, "bacc_std": 0.04363076014911423} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04292130349190631, "f1": 0.5836690840719849, "f1_std": 0.04522622381151135, "bacc": 0.5850840336134454, "bacc_std": 0.04367885899094509} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.043190798895843395, "f1": 0.5643931861867832, "f1_std": 0.044062420718036927, "bacc": 0.5646008403361344, "bacc_std": 0.04351088426791385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04426216418047864, "f1": 0.5716183895827798, "f1_std": 0.04518063219735387, "bacc": 0.571953781512605, "bacc_std": 0.044498790031625046} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.005994842503189409, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.038247030313261675, "f1": 0.5988748241912799, "f1_std": 0.04404624830365543, "bacc": 0.6081932773109243, "bacc_std": 0.03938817822095583} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04264475867263947, "f1": 0.5643243243243243, "f1_std": 0.045159713197064036, "bacc": 0.5672268907563025, "bacc_std": 0.043278027486011166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.0424024742568277, "f1": 0.6092436974789917, "f1_std": 0.04295759391042048, "bacc": 0.6092436974789917, "bacc_std": 0.04296153729402433} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04137057473246012, "f1": 0.6342182890855457, "f1_std": 0.041843884689032294, "bacc": 0.634453781512605, "bacc_std": 0.04173519074636086} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.041550653614797164, "f1": 0.6045708211533352, "f1_std": 0.042960853995053915, "bacc": 0.6045168067226891, "bacc_std": 0.04217036711700941} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04494434933271018, "f1": 0.6017043592264831, "f1_std": 0.04513042682401252, "bacc": 0.601890756302521, "bacc_std": 0.04502010771910276} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 2.782559402207126, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.042046738277681926, "f1": 0.6004471624909581, "f1_std": 0.04274295112115591, "bacc": 0.6003151260504203, "bacc_std": 0.0424989894972854} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.0391307042963769, "f1": 0.643092105263158, "f1_std": 0.04279666290864247, "bacc": 0.645483193277311, "bacc_std": 0.0401455358090731} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.041628138621346546, "f1": 0.5765651155005022, "f1_std": 0.04347266402869212, "bacc": 0.5777310924369747, "bacc_std": 0.04219842861335323} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.000774263682681127, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.040118123582120094, "f1": 0.5400013998740113, "f1_std": 0.044923966082496755, "bacc": 0.5519957983193278, "bacc_std": 0.040784098260129346} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 166.81005372000556, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04263601910204478, "f1": 0.5941345902068604, "f1_std": 0.04267443184443654, "bacc": 0.5945378151260504, "bacc_std": 0.04262416152457401} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.042961020979734976, "f1": 0.5571428571428572, "f1_std": 0.043827388923552583, "bacc": 0.5572478991596639, "bacc_std": 0.04332709357275242} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04262076250446511, "f1": 0.5765651155005022, "f1_std": 0.04433040395864553, "bacc": 0.5777310924369747, "bacc_std": 0.04315559466330222} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.3593813663804626, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.043843041396282846, "f1": 0.6753076721654884, "f1_std": 0.04401292470378633, "bacc": 0.6759453781512605, "bacc_std": 0.04381282463251082} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.040733707314096375, "f1": 0.6575739206573719, "f1_std": 0.043434569062111135, "bacc": 0.657563025210084, "bacc_std": 0.041833717096222606} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.005994842503189409, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.040163505574349605, "f1": 0.63853298081486, "f1_std": 0.043007748866683265, "bacc": 0.6397058823529411, "bacc_std": 0.0411267143859546} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.045235756578806366, "f1": 0.6242424242424243, "f1_std": 0.04614449429322273, "bacc": 0.6239495798319328, "bacc_std": 0.04601927920070753} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.046415888336127774, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04448014850269793, "f1": 0.5441176470588236, "f1_std": 0.045044664670335646, "bacc": 0.5441176470588236, "bacc_std": 0.044904531797821584} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.005994842503189409, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.039635973632891404, "f1": 0.6288435374149659, "f1_std": 0.043169562491677096, "bacc": 0.6307773109243697, "bacc_std": 0.040832271782975285} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.03969714628933886, "f1": 0.5649122807017544, "f1_std": 0.043053121532163945, "bacc": 0.5714285714285714, "bacc_std": 0.04030853138760041} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04290447184705232, "f1": 0.6137071651090342, "f1_std": 0.043895819809497805, "bacc": 0.6134453781512605, "bacc_std": 0.043200473456294824} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.046415888336127774, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.039779997875934656, "f1": 0.6669352672575879, "f1_std": 0.041456608752838416, "bacc": 0.6664915966386555, "bacc_std": 0.04046611372366884} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04080627310938899, "f1": 0.588836695219674, "f1_std": 0.04513230696424951, "bacc": 0.595063025210084, "bacc_std": 0.04176882254188167} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04264866268384136, "f1": 0.5931704050887178, "f1_std": 0.04415897100605938, "bacc": 0.5940126050420168, "bacc_std": 0.04302443840552972} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.005994842503189409, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.0425988353130836, "f1": 0.5267492467358554, "f1_std": 0.04436572763838384, "bacc": 0.5288865546218487, "bacc_std": 0.04305844212516156} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04038287105585534, "f1": 0.6191239316239316, "f1_std": 0.04187322781651601, "bacc": 0.6192226890756303, "bacc_std": 0.041016639224877895} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04328383202148465, "f1": 0.5873947935016637, "f1_std": 0.04331566816011826, "bacc": 0.5887605042016807, "bacc_std": 0.043354773773776695} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.005994842503189409, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042674944458022654, "f1": 0.5343756400628115, "f1_std": 0.045136759158338466, "bacc": 0.5404411764705883, "bacc_std": 0.0429333075038373} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04394383180604676, "f1": 0.5836690840719849, "f1_std": 0.04588776957493644, "bacc": 0.5850840336134454, "bacc_std": 0.044418573331478105} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 1291.5496650148827, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04480261949752214, "f1": 0.5407407407407407, "f1_std": 0.045561320243139476, "bacc": 0.5409663865546219, "bacc_std": 0.04494279253299461} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04234237772129254, "f1": 0.6003223207091055, "f1_std": 0.04388798465189365, "bacc": 0.6013655462184874, "bacc_std": 0.04276781425143125} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04308840403072121, "f1": 0.6405797101449275, "f1_std": 0.04367729059226176, "bacc": 0.6402310924369747, "bacc_std": 0.043482548787641545} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.005994842503189409, "split": "test", "acc": 0.6774193548387096, "acc_std": 0.04308456401784404, "f1": 0.6688034188034189, "f1_std": 0.04463608086920211, "bacc": 0.6680672268907563, "bacc_std": 0.04370904905003232} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.042624842653531204, "f1": 0.5740553647201454, "f1_std": 0.04447022416090202, "bacc": 0.576155462184874, "bacc_std": 0.04305052293145385} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.005994842503189409, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.0405704510504767, "f1": 0.643092105263158, "f1_std": 0.04392561804230355, "bacc": 0.645483193277311, "bacc_std": 0.04149815301618894} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.03995656786182424, "f1": 0.6580882352941176, "f1_std": 0.04035410411973056, "bacc": 0.6580882352941176, "bacc_std": 0.04021099201390925} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04368043004347049, "f1": 0.555142173797502, "f1_std": 0.04442032890884715, "bacc": 0.555672268907563, "bacc_std": 0.043815688325809114} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.042952506259409585, "f1": 0.6266038229903116, "f1_std": 0.043258917508129435, "bacc": 0.6271008403361344, "bacc_std": 0.04331637371844942} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.041998943919134196, "f1": 0.6118548118548119, "f1_std": 0.04360736611255973, "bacc": 0.6118697478991597, "bacc_std": 0.042744325268996665} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 2.782559402207126, "split": "test", "acc": 0.5, "acc_std": 0.04480751699887618, "f1": 0.4952731092436975, "f1_std": 0.0449423818137944, "bacc": 0.4952731092436975, "bacc_std": 0.04484025526374081} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 0.000774263682681127, "split": "test", "acc": 0.49193548387096775, "acc_std": 0.03757549113210549, "f1": 0.44227886056971516, "f1_std": 0.040957788434021064, "bacc": 0.46743697478991597, "bacc_std": 0.03738294141446133} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.044687826317910906, "f1": 0.6167554415729598, "f1_std": 0.045269810287524095, "bacc": 0.6165966386554622, "bacc_std": 0.04517071727373528} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.04157218250176983, "f1": 0.6553454003118433, "f1_std": 0.04469494207524602, "bacc": 0.6559873949579832, "bacc_std": 0.04266080100807519} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.0414503545685747, "f1": 0.6241664982824813, "f1_std": 0.04381025120786185, "bacc": 0.625, "bacc_std": 0.042239211589379766} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04354066837210107, "f1": 0.5788923719958203, "f1_std": 0.04377482800076446, "bacc": 0.5798319327731092, "bacc_std": 0.04369784052654255} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 21.54434690031882, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04073715587625844, "f1": 0.5678306043269548, "f1_std": 0.04119891535053769, "bacc": 0.5677521008403361, "bacc_std": 0.0411335854723978} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04169566663365599, "f1": 0.610369206598586, "f1_std": 0.04176827217228901, "bacc": 0.6108193277310925, "bacc_std": 0.04174429054982945} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 10000.0, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04399135226247737, "f1": 0.6046072753302532, "f1_std": 0.04406297832447376, "bacc": 0.6081932773109244, "bacc_std": 0.04416637338939243} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 0.005994842503189409, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04070968700475322, "f1": 0.6097756946769334, "f1_std": 0.04193263456038377, "bacc": 0.6102941176470589, "bacc_std": 0.04094494111161957} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04012958976897239, "f1": 0.6003223207091055, "f1_std": 0.04192472738566776, "bacc": 0.6013655462184874, "bacc_std": 0.040596885930704985} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.041345914567279644, "f1": 0.665680278818965, "f1_std": 0.04210229323894063, "bacc": 0.6654411764705883, "bacc_std": 0.04198157351540627} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04335695979354436, "f1": 0.5623043623043623, "f1_std": 0.04480704743301905, "bacc": 0.5630252100840336, "bacc_std": 0.044018198675353684} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.043074651459240706, "f1": 0.5860042735042735, "f1_std": 0.044687270103453455, "bacc": 0.5866596638655462, "bacc_std": 0.04362876863784573} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04244870504306941, "f1": 0.5854473942969518, "f1_std": 0.04277510884061642, "bacc": 0.585609243697479, "bacc_std": 0.04280705844485323} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04557067900085948, "f1": 0.58994708994709, "f1_std": 0.04643368145260979, "bacc": 0.5898109243697479, "bacc_std": 0.045895271723382314} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04490103581978825, "f1": 0.5388530045018595, "f1_std": 0.04506993946207348, "bacc": 0.5399159663865546, "bacc_std": 0.04521782898647137} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.3593813663804626, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.043312608440822076, "f1": 0.5541026479241582, "f1_std": 0.04375910087160651, "bacc": 0.5546218487394958, "bacc_std": 0.043903278345784724} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043516105119675866, "f1": 0.6045708211533352, "f1_std": 0.04487606551140039, "bacc": 0.6045168067226891, "bacc_std": 0.04418388648515332} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 2.782559402207126, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04358989658495648, "f1": 0.6480760345851759, "f1_std": 0.0442043492689369, "bacc": 0.6475840336134454, "bacc_std": 0.043980583142059874} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 2.782559402207126, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04515956217891696, "f1": 0.6580882352941176, "f1_std": 0.04594365845742023, "bacc": 0.6580882352941176, "bacc_std": 0.0458000828432345} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04032088706120817, "f1": 0.6190346145968457, "f1_std": 0.04353036747671587, "bacc": 0.6218487394957983, "bacc_std": 0.04116091461162507} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 0.3593813663804626, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04704115971780727, "f1": 0.6569169960474308, "f1_std": 0.048004148104000194, "bacc": 0.6565126050420168, "bacc_std": 0.047684507981011454} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.0433552347332143, "f1": 0.6191239316239316, "f1_std": 0.044919338641026076, "bacc": 0.6192226890756303, "bacc_std": 0.04390636728901356} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.046415888336127774, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.040122377183867054, "f1": 0.6528982044104594, "f1_std": 0.04396759538050346, "bacc": 0.6544117647058824, "bacc_std": 0.04128964065373109} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04414849068732454, "f1": 0.6063492063492064, "f1_std": 0.04530152771990273, "bacc": 0.60609243697479, "bacc_std": 0.04484168034108939} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 2.782559402207126, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.043857576229380496, "f1": 0.6451612903225806, "f1_std": 0.043981823989672944, "bacc": 0.6512605042016807, "bacc_std": 0.043678371951350575} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 1291.5496650148827, "split": "test", "acc": 0.4838709677419355, "acc_std": 0.04374165893432418, "f1": 0.4700854700854701, "f1_std": 0.04513550799502679, "bacc": 0.4726890756302521, "bacc_std": 0.04406401031229365} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04501060980254641, "f1": 0.5691904293674206, "f1_std": 0.045419041245601546, "bacc": 0.569327731092437, "bacc_std": 0.045448733282695844} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.041084830770722384, "f1": 0.5782312925170068, "f1_std": 0.043923761763414615, "bacc": 0.5819327731092437, "bacc_std": 0.0417845551106481} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04077958761278596, "f1": 0.6301451580831179, "f1_std": 0.04169847938257321, "bacc": 0.6297268907563025, "bacc_std": 0.04120819183088193} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.043692711860435524, "f1": 0.5703170970905524, "f1_std": 0.04384860554893189, "bacc": 0.5709033613445378, "bacc_std": 0.04371098251832914} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.041577016283500925, "f1": 0.5740553647201454, "f1_std": 0.04377127055409218, "bacc": 0.576155462184874, "bacc_std": 0.042134492368304806} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.042764446293684324, "f1": 0.5808311791608669, "f1_std": 0.043784163672292875, "bacc": 0.5808823529411764, "bacc_std": 0.04326289323966562} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0445041475226991, "f1": 0.5929621848739496, "f1_std": 0.04512306945834566, "bacc": 0.5929621848739496, "bacc_std": 0.04501057822130937} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04405069919871808, "f1": 0.5826018084614877, "f1_std": 0.044867150113164445, "bacc": 0.5824579831932774, "bacc_std": 0.04435502738963009} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.6935483870967742, "acc_std": 0.03828414970489003, "f1": 0.6835885038947085, "f1_std": 0.040641394620409645, "bacc": 0.6827731092436975, "bacc_std": 0.0394055630434495} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.005994842503189409, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04316731719337277, "f1": 0.626380984265149, "f1_std": 0.04441021684002011, "bacc": 0.6265756302521008, "bacc_std": 0.04346055146985166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04320956603918263, "f1": 0.5915678524374176, "f1_std": 0.04366914263639579, "bacc": 0.5913865546218487, "bacc_std": 0.043442450082562166} +{"model": "flat_mae", "repr": "patch", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04319412355973499, "f1": 0.5643243243243243, "f1_std": 0.04562847445640748, "bacc": 0.5672268907563025, "bacc_std": 0.04383054182789003} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | patch | logistic | abide_dx | train | 100 | 129.87 | 1013.6 | 0.83266 | 0.10596 | 0.82793 | 0.11012 | 0.82671 | 0.11032 | +| flat_mae | patch | logistic | abide_dx | test | 100 | 129.87 | 1013.6 | 0.60952 | 0.041028 | 0.59988 | 0.042713 | 0.60124 | 0.041401 | + + +done! total time: 0:05:56 diff --git a/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8e0712bba919ef1da551d5f8c8c5e1e53cbade6c --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (abide_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic +model: flat_mae +representation: reg +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic +remote_dir: null diff --git a/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/eval_table.csv b/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/eval_table.csv new file mode 100644 index 0000000000000000000000000000000000000000..e7f46627829b8d83f8e5c1c60fcf4204a2e35717 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/eval_table.csv @@ -0,0 +1,203 @@ +model,repr,clf,dataset,trial,C,split,acc,acc_std,f1,f1_std,bacc,bacc_std +flat_mae,reg,logistic,abide_dx,,0.005994842503189409,train,0.7222222222222222,0.016673629198043306,0.7098429561298829,0.017891834943761297,0.7083196532930593,0.01721875394332068 +flat_mae,reg,logistic,abide_dx,,0.005994842503189409,test,0.5241935483870968,0.03905716014490567,0.4879260866522013,0.0444112391352283,0.5060225189840273,0.03964323282840198 +flat_mae,reg,logistic,abide_dx,1,0.046415888336127774,train,0.8347578347578347,0.013454839678474493,0.8310497356780666,0.013929098060691,0.8282761166482097,0.013964710180484804 +flat_mae,reg,logistic,abide_dx,1,0.046415888336127774,test,0.6129032258064516,0.04395057708160896,0.6112852664576802,0.0442632628771069,0.6123949579831933,0.04437056866909796 +flat_mae,reg,logistic,abide_dx,2,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,2,21.54434690031882,test,0.5564516129032258,0.04387096774193549,0.5457875457875458,0.04437906915752659,0.5467436974789917,0.043705727546464596 +flat_mae,reg,logistic,abide_dx,3,0.046415888336127774,train,0.8148148148148148,0.01395000826155015,0.8108208955223881,0.014389827929782495,0.8084163898117387,0.01438405714762052 +flat_mae,reg,logistic,abide_dx,3,0.046415888336127774,test,0.6451612903225806,0.0410885284430458,0.6260964912280702,0.04523703162189061,0.6292016806722689,0.04246050489343041 +flat_mae,reg,logistic,abide_dx,4,0.3593813663804626,train,0.9230769230769231,0.00999530575447847,0.9219048717779682,0.010199800741302773,0.9201919527500924,0.010405434989598018 +flat_mae,reg,logistic,abide_dx,4,0.3593813663804626,test,0.6451612903225806,0.04242911699272703,0.6405797101449275,0.04323085992949722,0.6402310924369747,0.043012070888706226 +flat_mae,reg,logistic,abide_dx,5,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,5,1291.5496650148827,test,0.5645161290322581,0.04151114088889901,0.5588932806324111,0.04194960983601311,0.5588235294117647,0.04182645664059639 +flat_mae,reg,logistic,abide_dx,6,0.005994842503189409,train,0.7122507122507122,0.01612728764367488,0.7020323426573427,0.01712075688938658,0.7006275378368402,0.01666518745113348 +flat_mae,reg,logistic,abide_dx,6,0.005994842503189409,test,0.5806451612903226,0.04464624509219635,0.5670158474348643,0.046734543154942645,0.5688025210084033,0.04528410178700407 +flat_mae,reg,logistic,abide_dx,7,0.046415888336127774,train,0.8219373219373219,0.014066512380896954,0.818173529795712,0.014491840621226021,0.8157622739018088,0.014487626622664939 +flat_mae,reg,logistic,abide_dx,7,0.046415888336127774,test,0.5887096774193549,0.04295151296731073,0.5740553647201454,0.04532577730086134,0.576155462184874,0.04360534964925386 +flat_mae,reg,logistic,abide_dx,8,2.782559402207126,train,0.9985754985754985,0.0014201500491586375,0.998559926150059,0.0014365735228125326,0.9984126984126984,0.0015824529119196295 +flat_mae,reg,logistic,abide_dx,8,2.782559402207126,test,0.6129032258064516,0.04266482392829561,0.6045708211533352,0.044285384319347344,0.6045168067226891,0.0433675900675257 +flat_mae,reg,logistic,abide_dx,9,0.3593813663804626,train,0.9273504273504274,0.009802588326552062,0.9263204469917579,0.009983590627467695,0.9249538575119971,0.010188393154277157 +flat_mae,reg,logistic,abide_dx,9,0.3593813663804626,test,0.6209677419354839,0.044660192323319414,0.6153389215233318,0.04545621416013453,0.6150210084033614,0.044908791021144874 +flat_mae,reg,logistic,abide_dx,10,0.046415888336127774,train,0.8091168091168092,0.015244120544499577,0.8043120090533884,0.015849741434130447,0.8014765596160944,0.015800763082693726 +flat_mae,reg,logistic,abide_dx,10,0.046415888336127774,test,0.5967741935483871,0.044464427667333786,0.58994708994709,0.045783405871545606,0.5898109243697479,0.045122527793024225 +flat_mae,reg,logistic,abide_dx,11,0.3593813663804626,train,0.9330484330484331,0.009331730849076455,0.9320522510240352,0.009519838968951958,0.9304171280915468,0.009754648856604577 +flat_mae,reg,logistic,abide_dx,11,0.3593813663804626,test,0.5080645161290323,0.041267634895961115,0.4962370962370962,0.042236472808414804,0.49789915966386555,0.04140294053207701 +flat_mae,reg,logistic,abide_dx,12,0.005994842503189409,train,0.7336182336182336,0.015634582921056663,0.7230710812492749,0.016608595721814893,0.721188630490956,0.016145702834668974 +flat_mae,reg,logistic,abide_dx,12,0.005994842503189409,test,0.5483870967741935,0.045068369267466525,0.5454307410316837,0.045101189052741054,0.5456932773109244,0.045011145921707296 +flat_mae,reg,logistic,abide_dx,13,0.046415888336127774,train,0.8162393162393162,0.013817741357317611,0.8128112216528621,0.014184603214825356,0.810889627168697,0.014214294139557734 +flat_mae,reg,logistic,abide_dx,13,0.046415888336127774,test,0.6209677419354839,0.043491013580127635,0.6167554415729598,0.04421712747958401,0.6165966386554622,0.044030963510375304 +flat_mae,reg,logistic,abide_dx,14,2.782559402207126,train,0.9985754985754985,0.0013134984598052104,0.998559926150059,0.0013285583977231234,0.9984126984126984,0.0014636125694972388 +flat_mae,reg,logistic,abide_dx,14,2.782559402207126,test,0.6129032258064516,0.04294769402979147,0.6063492063492064,0.043820608630348507,0.60609243697479,0.043368887097137696 +flat_mae,reg,logistic,abide_dx,15,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,15,1291.5496650148827,test,0.5403225806451613,0.04493973302745094,0.5395739691225327,0.0449998443453219,0.5414915966386555,0.04535487070102569 +flat_mae,reg,logistic,abide_dx,16,0.046415888336127774,train,0.8304843304843305,0.014754342941248099,0.8270445525183073,0.01521256425004095,0.8246954595791806,0.01524746442359881 +flat_mae,reg,logistic,abide_dx,16,0.046415888336127774,test,0.5887096774193549,0.04427793626580146,0.5740553647201454,0.04591097260561043,0.576155462184874,0.044624919579721894 +flat_mae,reg,logistic,abide_dx,17,0.3593813663804626,train,0.9273504273504274,0.009828100205023692,0.9263204469917579,0.01000756284498476,0.9249538575119971,0.01017370280973181 +flat_mae,reg,logistic,abide_dx,17,0.3593813663804626,test,0.5725806451612904,0.04314043989843629,0.5599598259122867,0.04444114144964044,0.5614495798319328,0.04342960134591508 +flat_mae,reg,logistic,abide_dx,18,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,18,21.54434690031882,test,0.5483870967741935,0.04363316419525298,0.5407407407407407,0.04449217039796976,0.5409663865546219,0.04398735104831126 +flat_mae,reg,logistic,abide_dx,19,0.3593813663804626,train,0.9259259259259259,0.00977672013618543,0.924951275071751,0.009921757315400789,0.9239571797711332,0.010010063564097667 +flat_mae,reg,logistic,abide_dx,19,0.3593813663804626,test,0.5645161290322581,0.04501784534585998,0.5588932806324111,0.04544390340246913,0.5588235294117647,0.045221335833034004 +flat_mae,reg,logistic,abide_dx,20,0.3593813663804626,train,0.9373219373219374,0.00914058287385996,0.9366176374023245,0.00925090382378732,0.9363602805463271,0.009314356654406036 +flat_mae,reg,logistic,abide_dx,20,0.3593813663804626,test,0.6451612903225806,0.041592905922776494,0.6356837606837606,0.043485261235150396,0.6355042016806722,0.042304301340790634 +flat_mae,reg,logistic,abide_dx,21,0.046415888336127774,train,0.8276353276353277,0.013763662209441405,0.8238430510478126,0.01427305324266069,0.8212255444813584,0.014340400724982542 +flat_mae,reg,logistic,abide_dx,21,0.046415888336127774,test,0.5645161290322581,0.04513961173234119,0.5503626107977437,0.047117613674215686,0.5525210084033614,0.04568836372450983 +flat_mae,reg,logistic,abide_dx,22,0.046415888336127774,train,0.8076923076923077,0.014524041883427399,0.8031182806868111,0.01501731186648699,0.8004798818752307,0.014929723284786976 +flat_mae,reg,logistic,abide_dx,22,0.046415888336127774,test,0.5887096774193549,0.042625330902496775,0.5712833028269271,0.04548412365096064,0.5745798319327731,0.0434509485131368 +flat_mae,reg,logistic,abide_dx,23,0.046415888336127774,train,0.8247863247863247,0.013672042604798562,0.8207767461844538,0.014181267712221498,0.8180509413067553,0.01422909297953083 +flat_mae,reg,logistic,abide_dx,23,0.046415888336127774,test,0.5967741935483871,0.04480381561720566,0.5880946053680574,0.046350769014264354,0.5882352941176471,0.045510625606194725 +flat_mae,reg,logistic,abide_dx,24,0.046415888336127774,train,0.8133903133903134,0.014613562639471306,0.809284625514574,0.015123654844692263,0.8068290882244371,0.015141050112035795 +flat_mae,reg,logistic,abide_dx,24,0.046415888336127774,test,0.6048387096774194,0.04372693386297777,0.5972691721349506,0.04457894828089179,0.5971638655462186,0.04409887485772457 +flat_mae,reg,logistic,abide_dx,25,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,25,21.54434690031882,test,0.5564516129032258,0.04425849948060502,0.5529334644378892,0.044753295700216966,0.553046218487395,0.04467618305047169 +flat_mae,reg,logistic,abide_dx,26,0.005994842503189409,train,0.7065527065527065,0.016644340611713847,0.6932859372879054,0.0177805901292291,0.6925064599483204,0.017111451027819254 +flat_mae,reg,logistic,abide_dx,26,0.005994842503189409,test,0.5725806451612904,0.04495368179319451,0.5513074349696183,0.04818714162877323,0.5567226890756303,0.045558894187865684 +flat_mae,reg,logistic,abide_dx,27,0.3593813663804626,train,0.9216524216524217,0.010257554146404491,0.9206474803879456,0.010414657429975039,0.9197858988556663,0.010550509226253097 +flat_mae,reg,logistic,abide_dx,27,0.3593813663804626,test,0.6290322580645161,0.043199977237246855,0.6210470369386127,0.044393904059419086,0.6207983193277311,0.04378581149306724 +flat_mae,reg,logistic,abide_dx,28,0.005994842503189409,train,0.7022792022792023,0.01683426483288467,0.6893903949360121,0.017971934351256613,0.6886304909560723,0.017306025404779046 +flat_mae,reg,logistic,abide_dx,28,0.005994842503189409,test,0.6048387096774194,0.04444265500357634,0.5907590759075907,0.047118978016673835,0.592436974789916,0.045402049065869636 +flat_mae,reg,logistic,abide_dx,29,0.046415888336127774,train,0.8347578347578347,0.014101880325303524,0.8311940298507463,0.014618494912851073,0.8285714285714285,0.014699921031724203 +flat_mae,reg,logistic,abide_dx,29,0.046415888336127774,test,0.6370967741935484,0.042445606987642756,0.6241664982824813,0.0451739021056403,0.625,0.04357202583553351 +flat_mae,reg,logistic,abide_dx,30,0.046415888336127774,train,0.8233618233618234,0.013989216423773264,0.8202750134203245,0.01431323105120411,0.818530823181986,0.014327601283562835 +flat_mae,reg,logistic,abide_dx,30,0.046415888336127774,test,0.5967741935483871,0.044275327560540215,0.5929621848739496,0.04485207230090352,0.5929621848739496,0.044765000973135814 +flat_mae,reg,logistic,abide_dx,31,0.3593813663804626,train,0.9301994301994302,0.009082735470973753,0.9293935083408768,0.009207941329696566,0.9290143964562569,0.009351377916701473 +flat_mae,reg,logistic,abide_dx,31,0.3593813663804626,test,0.5967741935483871,0.04453675013270428,0.5915678524374176,0.045327509955712025,0.5913865546218487,0.04508493223747495 +flat_mae,reg,logistic,abide_dx,32,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,32,166.81005372000556,test,0.5887096774193549,0.04331443730060514,0.5854473942969518,0.04346322866331395,0.585609243697479,0.04339784369493768 +flat_mae,reg,logistic,abide_dx,33,0.046415888336127774,train,0.8190883190883191,0.014069603486189141,0.8151079957278694,0.014498226881783363,0.8125876707272056,0.01445683867291224 +flat_mae,reg,logistic,abide_dx,33,0.046415888336127774,test,0.6290322580645161,0.04275135623506656,0.6227513227513227,0.043466992184883556,0.6223739495798319,0.04304501849763443 +flat_mae,reg,logistic,abide_dx,34,0.3593813663804626,train,0.9188034188034188,0.01000258690089041,0.9176522642849059,0.010173848547408215,0.9163159837578443,0.010282489420741829 +flat_mae,reg,logistic,abide_dx,34,0.3593813663804626,test,0.6129032258064516,0.04234063282882618,0.607905138339921,0.043092112081540374,0.6076680672268908,0.042796816889084925 +flat_mae,reg,logistic,abide_dx,35,0.046415888336127774,train,0.8361823361823362,0.013519787150882123,0.8329937214907064,0.013939722842176675,0.830749354005168,0.014029130332672295 +flat_mae,reg,logistic,abide_dx,35,0.046415888336127774,test,0.6048387096774194,0.044814381889539866,0.6004471624909581,0.045479088978431205,0.6003151260504203,0.045245013740791595 +flat_mae,reg,logistic,abide_dx,36,0.3593813663804626,train,0.9259259259259259,0.009822287604620172,0.924951275071751,0.009972645761120806,0.9239571797711332,0.01007420480107739 +flat_mae,reg,logistic,abide_dx,36,0.3593813663804626,test,0.6370967741935484,0.03873528722737044,0.6241664982824813,0.04080478980858926,0.625,0.039376347841006715 +flat_mae,reg,logistic,abide_dx,37,0.046415888336127774,train,0.811965811965812,0.01427750823847296,0.8068727490996399,0.014897432348334481,0.8037652270210409,0.014827794333911654 +flat_mae,reg,logistic,abide_dx,37,0.046415888336127774,test,0.6370967741935484,0.04199832450451165,0.6283716283716283,0.043426608510119674,0.6281512605042017,0.042631690567772065 +flat_mae,reg,logistic,abide_dx,38,0.3593813663804626,train,0.9387464387464387,0.009005857534023826,0.9381488926180686,0.009086451141603695,0.9385382059800664,0.009091879671709794 +flat_mae,reg,logistic,abide_dx,38,0.3593813663804626,test,0.5725806451612904,0.044967903919734174,0.5662332519305657,0.0457125214025606,0.5661764705882353,0.04546098036972832 +flat_mae,reg,logistic,abide_dx,39,0.3593813663804626,train,0.9316239316239316,0.009226918756552389,0.9307242539123857,0.009372748656384202,0.9297157622739018,0.009506970615358594 +flat_mae,reg,logistic,abide_dx,39,0.3593813663804626,test,0.5725806451612904,0.04447214985114768,0.5712141971683957,0.04466205371513864,0.5724789915966386,0.04486280246770522 +flat_mae,reg,logistic,abide_dx,40,0.3593813663804626,train,0.9373219373219374,0.009546869964246713,0.9364972327530201,0.009704182836587581,0.9354743447766704,0.009883010222060822 +flat_mae,reg,logistic,abide_dx,40,0.3593813663804626,test,0.5887096774193549,0.04289743776140058,0.5788211788211788,0.04458060530385843,0.5793067226890757,0.0435962625004627 +flat_mae,reg,logistic,abide_dx,41,0.3593813663804626,train,0.9316239316239316,0.00992745661540211,0.9308556044388995,0.010047823956099705,0.9306016980435585,0.010119372534444258 +flat_mae,reg,logistic,abide_dx,41,0.3593813663804626,test,0.5806451612903226,0.04158483674661302,0.5670158474348643,0.043504956269000895,0.5688025210084033,0.04215859772898527 +flat_mae,reg,logistic,abide_dx,42,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,42,1291.5496650148827,test,0.5725806451612904,0.04736247136783172,0.5712141971683957,0.04741980959511276,0.5724789915966386,0.04755060054771044 +flat_mae,reg,logistic,abide_dx,43,0.3593813663804626,train,0.9415954415954416,0.008505748463101728,0.9408073740907325,0.00865197204138749,0.9396456256921373,0.008842468470152166 +flat_mae,reg,logistic,abide_dx,43,0.3593813663804626,test,0.5725806451612904,0.04315357469973079,0.5662332519305657,0.04408606535703067,0.5661764705882353,0.04362160414328353 +flat_mae,reg,logistic,abide_dx,44,0.046415888336127774,train,0.8347578347578347,0.014074506608345973,0.8314735099337749,0.014453688867707096,0.8291620524178664,0.014460855938839315 +flat_mae,reg,logistic,abide_dx,44,0.046415888336127774,test,0.5564516129032258,0.042101566282678075,0.5343756400628115,0.04464840601889255,0.5404411764705883,0.04245107335071661 +flat_mae,reg,logistic,abide_dx,45,0.005994842503189409,train,0.7165242165242165,0.015684688587666546,0.7046073039374274,0.01685837807294446,0.7033222591362126,0.016262635796370196 +flat_mae,reg,logistic,abide_dx,45,0.005994842503189409,test,0.5806451612903226,0.042284847459365525,0.5581140350877193,0.045202461679594005,0.5640756302521008,0.04272463526059535 +flat_mae,reg,logistic,abide_dx,46,0.046415888336127774,train,0.8276353276353277,0.013817837400149162,0.824419828061987,0.014191638254584278,0.8224067921742341,0.014260594137696045 +flat_mae,reg,logistic,abide_dx,46,0.046415888336127774,test,0.5645161290322581,0.04251046268961711,0.555142173797502,0.04372519520856913,0.555672268907563,0.04308578626285256 +flat_mae,reg,logistic,abide_dx,47,0.046415888336127774,train,0.8034188034188035,0.014536420810204544,0.7996724484478523,0.014920718855468515,0.7977851605758582,0.014918953434903678 +flat_mae,reg,logistic,abide_dx,47,0.046415888336127774,test,0.6451612903225806,0.03905281716619205,0.6356837606837606,0.040608572484898735,0.6355042016806722,0.0395745947622551 +flat_mae,reg,logistic,abide_dx,48,0.046415888336127774,train,0.811965811965812,0.014312631542121753,0.807910447761194,0.014742183727397851,0.8055370985603544,0.014700388263081827 +flat_mae,reg,logistic,abide_dx,48,0.046415888336127774,test,0.5967741935483871,0.043044211112549954,0.5836690840719849,0.045261871721320075,0.5850840336134454,0.04369736954323317 +flat_mae,reg,logistic,abide_dx,49,0.046415888336127774,train,0.8276353276353277,0.013760987827918228,0.8236909454334871,0.014174794260659757,0.8209302325581396,0.014136696625947822 +flat_mae,reg,logistic,abide_dx,49,0.046415888336127774,test,0.5887096774193549,0.04145938172460453,0.5740553647201454,0.04367366725998392,0.576155462184874,0.04207204377294009 +flat_mae,reg,logistic,abide_dx,50,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,50,2.782559402207126,test,0.5483870967741935,0.044560435524711,0.5386659580122243,0.04540312402538256,0.539390756302521,0.04477826050122978 +flat_mae,reg,logistic,abide_dx,51,0.3593813663804626,train,0.9344729344729344,0.009416486272267257,0.9336538461538462,0.00954497647821566,0.932890365448505,0.009621973087443536 +flat_mae,reg,logistic,abide_dx,51,0.3593813663804626,test,0.6451612903225806,0.04196114289443608,0.6336287939833467,0.0444301022152979,0.6339285714285714,0.04295668951519584 +flat_mae,reg,logistic,abide_dx,52,0.046415888336127774,train,0.8233618233618234,0.014801671794429195,0.8197032336103263,0.015260429410708215,0.8173495754891104,0.015246260241620672 +flat_mae,reg,logistic,abide_dx,52,0.046415888336127774,test,0.5725806451612904,0.043267538232770374,0.5643931861867832,0.04439007222378754,0.5646008403361344,0.04377323295877954 +flat_mae,reg,logistic,abide_dx,53,0.3593813663804626,train,0.9259259259259259,0.010083932391991842,0.9247433307219726,0.010296625127979511,0.9227759320782577,0.010487087960483402 +flat_mae,reg,logistic,abide_dx,53,0.3593813663804626,test,0.5887096774193549,0.04555380976128023,0.5841388834089565,0.04628499679920593,0.5840336134453781,0.04618248372075831 +flat_mae,reg,logistic,abide_dx,54,0.046415888336127774,train,0.8176638176638177,0.013843849538011004,0.8135721221275218,0.014348031629113437,0.811000369139904,0.014363638671879198 +flat_mae,reg,logistic,abide_dx,54,0.046415888336127774,test,0.6129032258064516,0.04404919915151349,0.607905138339921,0.04486856407534647,0.6076680672268908,0.04460279530927995 +flat_mae,reg,logistic,abide_dx,55,0.005994842503189409,train,0.7165242165242165,0.017310330072290065,0.7062965291195287,0.018277479725699357,0.7047988187523071,0.017790399741439655 +flat_mae,reg,logistic,abide_dx,55,0.005994842503189409,test,0.5403225806451613,0.03951604674119148,0.5096774193548387,0.042994210298022154,0.5210084033613446,0.03988599886791966 +flat_mae,reg,logistic,abide_dx,56,0.046415888336127774,train,0.8034188034188035,0.014889176457677587,0.7996724484478523,0.01531019696349788,0.7977851605758582,0.015302581560244199 +flat_mae,reg,logistic,abide_dx,56,0.046415888336127774,test,0.6290322580645161,0.04095775849908671,0.6191239316239316,0.04268570493385553,0.6192226890756303,0.04166668433696633 +flat_mae,reg,logistic,abide_dx,57,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,57,10000.0,test,0.6290322580645161,0.04074809035827315,0.628161668839635,0.040822686318211086,0.6302521008403361,0.040860401187507715 +flat_mae,reg,logistic,abide_dx,58,0.3593813663804626,train,0.9088319088319088,0.011220393257822469,0.9075707702435813,0.011407773612895918,0.9063861203396086,0.011533125991521963 +flat_mae,reg,logistic,abide_dx,58,0.3593813663804626,test,0.5967741935483871,0.0450012689149341,0.58994708994709,0.04626751618773533,0.5898109243697479,0.04577113065972449 +flat_mae,reg,logistic,abide_dx,59,0.005994842503189409,train,0.7222222222222222,0.015984114351180887,0.7098429561298829,0.01716313794543137,0.7084902177925434,0.016529487306629002 +flat_mae,reg,logistic,abide_dx,59,0.005994842503189409,test,0.6048387096774194,0.042242089445333975,0.5931704050887178,0.044193292676184756,0.5940126050420168,0.042983082947113546 +flat_mae,reg,logistic,abide_dx,60,0.3593813663804626,train,0.9358974358974359,0.009007130054295955,0.9349436445974806,0.009175751394726135,0.933296419342931,0.009352851707702527 +flat_mae,reg,logistic,abide_dx,60,0.3593813663804626,test,0.5887096774193549,0.04409967366638658,0.5765651155005022,0.04635204942741195,0.5777310924369747,0.04487031530345105 +flat_mae,reg,logistic,abide_dx,61,0.046415888336127774,train,0.8290598290598291,0.013281946170419142,0.825802129085089,0.013635332002089582,0.8236987818383168,0.013668614704927248 +flat_mae,reg,logistic,abide_dx,61,0.046415888336127774,test,0.5806451612903226,0.04373535431983821,0.5752305665349143,0.04431464568516978,0.5751050420168067,0.0440792809743897 +flat_mae,reg,logistic,abide_dx,62,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,62,21.54434690031882,test,0.5564516129032258,0.044720196128006505,0.5550336008351275,0.04490882050676395,0.5561974789915967,0.04510092478850601 +flat_mae,reg,logistic,abide_dx,63,0.046415888336127774,train,0.8190883190883191,0.01438937224663829,0.8154172955447481,0.014827211340388334,0.8131782945736434,0.01483184995561313 +flat_mae,reg,logistic,abide_dx,63,0.046415888336127774,test,0.6290322580645161,0.046584275169074964,0.6255252100840336,0.04701167377296699,0.6255252100840336,0.04681276423064385 +flat_mae,reg,logistic,abide_dx,64,0.046415888336127774,train,0.8062678062678063,0.01492497831282071,0.8025757462964341,0.015360419551484062,0.8006644518272426,0.015396462961071947 +flat_mae,reg,logistic,abide_dx,64,0.046415888336127774,test,0.6612903225806451,0.04028065885294668,0.6481081081081081,0.0429401579018039,0.6486344537815126,0.04125255943370762 +flat_mae,reg,logistic,abide_dx,65,0.3593813663804626,train,0.9373219373219374,0.008883388246173336,0.9363669325598261,0.00907680295274996,0.9345884090070137,0.009344519331608214 +flat_mae,reg,logistic,abide_dx,65,0.3593813663804626,test,0.6209677419354839,0.0455018810145084,0.6153389215233318,0.046070126888814976,0.6150210084033614,0.04572263399417745 +flat_mae,reg,logistic,abide_dx,66,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,66,166.81005372000556,test,0.532258064516129,0.04339142561448564,0.5317708333333333,0.04351924292290055,0.5341386554621849,0.04374376971991171 +flat_mae,reg,logistic,abide_dx,67,0.3593813663804626,train,0.9287749287749287,0.009840779173046849,0.9276378180018967,0.01005779329227266,0.925655223329642,0.010296893161666648 +flat_mae,reg,logistic,abide_dx,67,0.3593813663804626,test,0.5887096774193549,0.043452295418161514,0.5854473942969518,0.04401327540223378,0.585609243697479,0.04395864580039378 +flat_mae,reg,logistic,abide_dx,68,21.54434690031882,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,68,21.54434690031882,test,0.6048387096774194,0.04151236604747459,0.6035753898349319,0.04165215581397049,0.6050420168067226,0.041813622839103476 +flat_mae,reg,logistic,abide_dx,69,0.005994842503189409,train,0.7207977207977208,0.01616780475918868,0.7078105754937354,0.017303864432597814,0.7066076042820228,0.016623055695974148 +flat_mae,reg,logistic,abide_dx,69,0.005994842503189409,test,0.6532258064516129,0.040085999512546454,0.626793588577028,0.04602630390396756,0.6334033613445378,0.041587835136550344 +flat_mae,reg,logistic,abide_dx,70,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,70,1291.5496650148827,test,0.5806451612903226,0.04435047192580507,0.5735449735449736,0.04545865206707871,0.5735294117647058,0.044977516715817206 +flat_mae,reg,logistic,abide_dx,71,2.782559402207126,train,0.9985754985754985,0.001537033736520454,0.998559926150059,0.0015548492569231833,0.9984126984126984,0.001712694734979937 +flat_mae,reg,logistic,abide_dx,71,2.782559402207126,test,0.5806451612903226,0.04378151161878026,0.5716183895827798,0.04484709926495693,0.571953781512605,0.04411660226603999 +flat_mae,reg,logistic,abide_dx,72,0.3593813663804626,train,0.9330484330484331,0.00888643037079718,0.93218966505879,0.009036982563995597,0.9313030638612034,0.009235239077410293 +flat_mae,reg,logistic,abide_dx,72,0.3593813663804626,test,0.6129032258064516,0.04196739170714987,0.6063492063492064,0.04283758856127532,0.60609243697479,0.042416460637840256 +flat_mae,reg,logistic,abide_dx,73,0.046415888336127774,train,0.8162393162393162,0.014341920807398092,0.811868579322953,0.014924035448634833,0.8091177556293836,0.014940116196250994 +flat_mae,reg,logistic,abide_dx,73,0.046415888336127774,test,0.6048387096774194,0.04196055082076618,0.5972691721349506,0.043283482309888516,0.5971638655462186,0.042798979315679365 +flat_mae,reg,logistic,abide_dx,74,0.046415888336127774,train,0.8176638176638177,0.013824539658531799,0.8141889376907616,0.014195368899632197,0.8121816168327796,0.014221800126399883 +flat_mae,reg,logistic,abide_dx,74,0.046415888336127774,test,0.6370967741935484,0.04351724991980451,0.626380984265149,0.04532001770371712,0.6265756302521008,0.044117100474305185 +flat_mae,reg,logistic,abide_dx,75,2.782559402207126,train,0.9985754985754985,0.0013413297846496782,0.9985607764426576,0.0013545797469480289,0.9987080103359174,0.0012165549209613624 +flat_mae,reg,logistic,abide_dx,75,2.782559402207126,test,0.6209677419354839,0.04411356961223385,0.6167554415729598,0.04467528520637346,0.6165966386554622,0.04444876834044117 +flat_mae,reg,logistic,abide_dx,76,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,76,2.782559402207126,test,0.5725806451612904,0.045654595514266476,0.5712141971683957,0.04591922360045486,0.5724789915966386,0.04608898179359832 +flat_mae,reg,logistic,abide_dx,77,0.046415888336127774,train,0.8233618233618234,0.01482743818977934,0.8197032336103263,0.015291438734954992,0.8173495754891104,0.015306072906845011 +flat_mae,reg,logistic,abide_dx,77,0.046415888336127774,test,0.5725806451612904,0.04343502569143729,0.5623043623043623,0.044781493397984096,0.5630252100840336,0.043965999320902206 +flat_mae,reg,logistic,abide_dx,78,0.005994842503189409,train,0.7321937321937322,0.015727966610268474,0.7235687894300292,0.016455144146042367,0.7216685123661868,0.016127411683474223 +flat_mae,reg,logistic,abide_dx,78,0.005994842503189409,test,0.5967741935483871,0.04359630279124087,0.5782312925170068,0.04609870381151599,0.5819327731092437,0.0441266763844312 +flat_mae,reg,logistic,abide_dx,79,0.3593813663804626,train,0.9344729344729344,0.009622409589531877,0.9336107433327028,0.009774904898626993,0.932595053525286,0.00991333616485953 +flat_mae,reg,logistic,abide_dx,79,0.3593813663804626,test,0.5403225806451613,0.04351294555418249,0.5366764995083579,0.043958891892718385,0.5367647058823529,0.04401771358561786 +flat_mae,reg,logistic,abide_dx,80,0.005994842503189409,train,0.7150997150997151,0.016672990496771158,0.7029451591062965,0.018130936655806486,0.701734957548911,0.017427041351015228 +flat_mae,reg,logistic,abide_dx,80,0.005994842503189409,test,0.6129032258064516,0.04279741986057295,0.607905138339921,0.043302167480701995,0.6076680672268908,0.04296470678427449 +flat_mae,reg,logistic,abide_dx,81,0.3593813663804626,train,0.9245014245014245,0.010457855135554793,0.9235820282413351,0.01060555091728331,0.9229605020302695,0.01073358754409635 +flat_mae,reg,logistic,abide_dx,81,0.3593813663804626,test,0.6532258064516129,0.04266466234615413,0.6480760345851759,0.04321881873010316,0.6475840336134454,0.042898516701080525 +flat_mae,reg,logistic,abide_dx,82,0.3593813663804626,train,0.9245014245014245,0.010028682253402485,0.9236760859531259,0.010147919122871576,0.9235511258767073,0.010235128633471998 +flat_mae,reg,logistic,abide_dx,82,0.3593813663804626,test,0.5967741935483871,0.04119887807490142,0.5836690840719849,0.043293272164033926,0.5850840336134454,0.041919368781666855 +flat_mae,reg,logistic,abide_dx,83,2.782559402207126,train,0.9985754985754985,0.0014136653380161619,0.9985607764426576,0.0014274782426942384,0.9987080103359174,0.001282161585642588 +flat_mae,reg,logistic,abide_dx,83,2.782559402207126,test,0.5483870967741935,0.04510785721488232,0.5454307410316837,0.045376275643544295,0.5456932773109244,0.045404438143670865 +flat_mae,reg,logistic,abide_dx,84,0.3593813663804626,train,0.9387464387464387,0.009002926087880884,0.9379199289244267,0.009149253612803778,0.9367663344407531,0.009306355796671885 +flat_mae,reg,logistic,abide_dx,84,0.3593813663804626,test,0.6129032258064516,0.043532550884050246,0.6119947848761408,0.0436963453355689,0.6139705882352942,0.043841582697882436 +flat_mae,reg,logistic,abide_dx,85,0.3593813663804626,train,0.9373219373219374,0.00913712302373317,0.9366176374023245,0.009245443085469861,0.9363602805463271,0.009284449981391649 +flat_mae,reg,logistic,abide_dx,85,0.3593813663804626,test,0.6129032258064516,0.04278218129572632,0.607905138339921,0.04341605981491767,0.6076680672268908,0.04300998618436581 +flat_mae,reg,logistic,abide_dx,86,0.3593813663804626,train,0.9330484330484331,0.00909078193638841,0.932316529052772,0.0091872121481258,0.9321889996308601,0.009214267293799379 +flat_mae,reg,logistic,abide_dx,86,0.3593813663804626,test,0.5887096774193549,0.04639236813334464,0.5841388834089565,0.04695397287428437,0.5840336134453781,0.04677696931012307 +flat_mae,reg,logistic,abide_dx,87,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,87,166.81005372000556,test,0.6129032258064516,0.04405607296430788,0.607905138339921,0.04444903753352666,0.6076680672268908,0.044191989920764035 +flat_mae,reg,logistic,abide_dx,88,0.3593813663804626,train,0.9401709401709402,0.008962184117156038,0.9392157671215933,0.009156453575647054,0.937172388335179,0.009416670797553237 +flat_mae,reg,logistic,abide_dx,88,0.3593813663804626,test,0.6048387096774194,0.04394622340439329,0.6035753898349319,0.04395717376797717,0.6050420168067226,0.04417283587902601 +flat_mae,reg,logistic,abide_dx,89,0.3593813663804626,train,0.9259259259259259,0.009675070636763592,0.9250474305378746,0.009810457197395761,0.924547803617571,0.009940635881329832 +flat_mae,reg,logistic,abide_dx,89,0.3593813663804626,test,0.6048387096774194,0.04450310702478559,0.6035753898349319,0.04480218043878436,0.6050420168067226,0.045173419704359036 +flat_mae,reg,logistic,abide_dx,90,0.046415888336127774,train,0.8276353276353277,0.013906007129198487,0.8241377382749175,0.014340983481063718,0.8218161683277962,0.014408152537158351 +flat_mae,reg,logistic,abide_dx,90,0.046415888336127774,test,0.5564516129032258,0.04441490361186431,0.5376584638329605,0.04685996764646505,0.542016806722689,0.044907295603635655 +flat_mae,reg,logistic,abide_dx,91,0.005994842503189409,train,0.7250712250712251,0.016476321934927485,0.7154629822140737,0.017418034255722633,0.7137320044296789,0.01698932357612601 +flat_mae,reg,logistic,abide_dx,91,0.005994842503189409,test,0.5887096774193549,0.04169275596676308,0.5740553647201454,0.04316167186424532,0.576155462184874,0.04195330516513154 +flat_mae,reg,logistic,abide_dx,92,1291.5496650148827,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,92,1291.5496650148827,test,0.5241935483870968,0.04525939804441009,0.5241626016260164,0.04539458882673062,0.5283613445378151,0.0452572721817495 +flat_mae,reg,logistic,abide_dx,93,0.046415888336127774,train,0.811965811965812,0.01454376190610288,0.8092344178462907,0.014806401634394397,0.8081949058693245,0.014844955525547788 +flat_mae,reg,logistic,abide_dx,93,0.046415888336127774,test,0.5725806451612904,0.04358456084221262,0.5573516535327002,0.04543067671030717,0.5598739495798319,0.044003292809102035 +flat_mae,reg,logistic,abide_dx,94,2.782559402207126,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,94,2.782559402207126,test,0.5725806451612904,0.04350924166544126,0.5599598259122867,0.04474369651620298,0.5614495798319328,0.04371385251730714 +flat_mae,reg,logistic,abide_dx,95,0.3593813663804626,train,0.9273504273504274,0.0098096240393211,0.9263701482592037,0.009972502948691196,0.925249169435216,0.010105488377285627 +flat_mae,reg,logistic,abide_dx,95,0.3593813663804626,test,0.6370967741935484,0.042395967427460615,0.626380984265149,0.0442934326800233,0.6265756302521008,0.0431109933896401 +flat_mae,reg,logistic,abide_dx,96,10000.0,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,96,10000.0,test,0.5806451612903226,0.043739128276083845,0.5716183895827798,0.044999281224043924,0.571953781512605,0.0441973978433437 +flat_mae,reg,logistic,abide_dx,97,0.005994842503189409,train,0.7222222222222222,0.016951639732659965,0.7091178764266272,0.018347139772812923,0.7078995939461056,0.017567795329182144 +flat_mae,reg,logistic,abide_dx,97,0.005994842503189409,test,0.6693548387096774,0.039253104227146444,0.6575739206573719,0.04134893750265247,0.657563025210084,0.040025966630817346 +flat_mae,reg,logistic,abide_dx,98,0.046415888336127774,train,0.8176638176638177,0.014133068967655017,0.8129013451047349,0.014666520860196423,0.8098191214470284,0.01457330197750005 +flat_mae,reg,logistic,abide_dx,98,0.046415888336127774,test,0.6451612903225806,0.0425206658453675,0.6336287939833467,0.04452801183371108,0.6339285714285714,0.04319013594992082 +flat_mae,reg,logistic,abide_dx,99,166.81005372000556,train,1.0,0.0,1.0,0.0,1.0,0.0 +flat_mae,reg,logistic,abide_dx,99,166.81005372000556,test,0.5806451612903226,0.04630065075293955,0.5752305665349143,0.04717865573291078,0.5751050420168067,0.04681552931311242 +flat_mae,reg,logistic,abide_dx,100,0.005994842503189409,train,0.7193732193732194,0.01611973667097688,0.7075760747521267,0.017293867162878097,0.7062015503875969,0.016687744267718952 +flat_mae,reg,logistic,abide_dx,100,0.005994842503189409,test,0.5645161290322581,0.04289129108801309,0.5374412821221332,0.04703033317132357,0.546218487394958,0.043783554866055806 diff --git a/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/log.txt b/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..ecea0f319b9329f0e390fc2c7bda39d339ce310d --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic/log.txt @@ -0,0 +1,252 @@ +fMRI foundation model logistic probe eval +version: 0.1.dev66+g7ddd3aa04 +sha: aef99c83a386cf95c3d8ca503ecc968d8d5694af, status: has uncommitted changes, branch: dev/clane9 +cwd: /data/connor/fmri-fm +start: 2026-03-07 21:19:16 +config: +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (abide_dx reg logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic +model: flat_mae +representation: reg +dataset: abide_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/abide_dx__reg__logistic +remote_dir: null + +creating frozen backbone model: flat_mae +backbone: +MaskedEncoderWrapper( + (model): MaskedEncoder( + class_token=False, reg_tokens=4, no_embed_class=True, mask_drop_scale=False + (patchify): Patchify3D((16, 224, 560), (4, 16, 16), in_chans=1) + (patch_embed): Linear(in_features=1024, out_features=768, bias=True) + (pos_embed): SeparablePosEmbed(768, (4, 14, 35)) + (blocks): ModuleList( + (0-11): 12 x Block( + (norm1): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (attn): Attention( + num_heads=12 + (q): Linear(in_features=768, out_features=768, bias=True) + (k): Linear(in_features=768, out_features=768, bias=True) + (v): Linear(in_features=768, out_features=768, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (drop_path1): Identity() + (norm2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (mlp): Mlp( + (fc1): Linear(in_features=768, out_features=3072, bias=True) + (act): GELU(approximate='none') + (fc2): Linear(in_features=3072, out_features=768, bias=True) + ) + (drop_path2): Identity() + ) + ) + (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + ) +) +creating dataset: abide_dx (flat) +train (n=578): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 578 +}), + labels=['Autism' 'Control'], + counts=[260 318] +) + +validation (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[54 70] +) + +test (n=124): +HFDataset( + dataset=Dataset({ + features: ['sub', 'site', 'dataset', 'path', 'n_frames', 'tr', 'bold', 'mean', 'std'], + num_rows: 124 +}), + labels=['Autism' 'Control'], + counts=[57 67] +) + +extracting features for all splits +extract (train) [ 0/289] eta: 0:22:30 time: 4.6723 data: 3.7127 max mem: 2698 +extract (train) [ 20/289] eta: 0:01:52 time: 0.2071 data: 0.0661 max mem: 2852 +extract (train) [ 40/289] eta: 0:01:14 time: 0.1747 data: 0.0546 max mem: 2852 +extract (train) [ 60/289] eta: 0:00:58 time: 0.1643 data: 0.0514 max mem: 2852 +extract (train) [ 80/289] eta: 0:00:50 time: 0.1899 data: 0.0616 max mem: 2852 +extract (train) [100/289] eta: 0:00:43 time: 0.1848 data: 0.0601 max mem: 2852 +extract (train) [120/289] eta: 0:00:36 time: 0.1678 data: 0.0520 max mem: 2852 +extract (train) [140/289] eta: 0:00:31 time: 0.1660 data: 0.0524 max mem: 2852 +extract (train) [160/289] eta: 0:00:26 time: 0.1758 data: 0.0569 max mem: 2852 +extract (train) [180/289] eta: 0:00:22 time: 0.1939 data: 0.0678 max mem: 2852 +extract (train) [200/289] eta: 0:00:18 time: 0.1956 data: 0.0668 max mem: 2852 +extract (train) [220/289] eta: 0:00:14 time: 0.2145 data: 0.0797 max mem: 2852 +extract (train) [240/289] eta: 0:00:09 time: 0.1912 data: 0.0651 max mem: 2852 +extract (train) [260/289] eta: 0:00:05 time: 0.1958 data: 0.0686 max mem: 2852 +extract (train) [280/289] eta: 0:00:01 time: 0.1609 data: 0.0509 max mem: 2852 +extract (train) [288/289] eta: 0:00:00 time: 0.1574 data: 0.0488 max mem: 2852 +extract (train) Total time: 0:00:57 (0.2004 s / it) +extract (validation) [ 0/62] eta: 0:03:40 time: 3.5505 data: 3.3305 max mem: 2852 +extract (validation) [20/62] eta: 0:00:15 time: 0.2120 data: 0.0714 max mem: 2852 +extract (validation) [40/62] eta: 0:00:05 time: 0.1579 data: 0.0465 max mem: 2852 +extract (validation) [60/62] eta: 0:00:00 time: 0.1632 data: 0.0518 max mem: 2852 +extract (validation) [61/62] eta: 0:00:00 time: 0.1636 data: 0.0520 max mem: 2852 +extract (validation) Total time: 0:00:14 (0.2368 s / it) +extract (test) [ 0/62] eta: 0:03:30 time: 3.3999 data: 3.2086 max mem: 2852 +extract (test) [20/62] eta: 0:00:15 time: 0.2178 data: 0.0782 max mem: 2852 +extract (test) [40/62] eta: 0:00:05 time: 0.1667 data: 0.0540 max mem: 2852 +extract (test) [60/62] eta: 0:00:00 time: 0.1535 data: 0.0457 max mem: 2852 +extract (test) [61/62] eta: 0:00:00 time: 0.1538 data: 0.0460 max mem: 2852 +extract (test) Total time: 0:00:14 (0.2358 s / it) +feature extraction time: 0:01:27 +train features: (578, 768) +validation features: (124, 768) +test features: (124, 768) +evaluating fixed splits +eval results (fixed splits): + +| model | repr | clf | dataset | trial | C | split | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|----------:|:--------|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | abide_dx | | 0.0059948 | train | 0.72222 | 0.016674 | 0.70984 | 0.017892 | 0.70832 | 0.017219 | +| flat_mae | reg | logistic | abide_dx | | 0.0059948 | test | 0.52419 | 0.039057 | 0.48793 | 0.044411 | 0.50602 | 0.039643 | + + +evaluating random splits (n=100) +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 1, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04395057708160896, "f1": 0.6112852664576802, "f1_std": 0.0442632628771069, "bacc": 0.6123949579831933, "bacc_std": 0.04437056866909796} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 2, "C": 21.54434690031882, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04387096774193549, "f1": 0.5457875457875458, "f1_std": 0.04437906915752659, "bacc": 0.5467436974789917, "bacc_std": 0.043705727546464596} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 3, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.0410885284430458, "f1": 0.6260964912280702, "f1_std": 0.04523703162189061, "bacc": 0.6292016806722689, "bacc_std": 0.04246050489343041} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 4, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04242911699272703, "f1": 0.6405797101449275, "f1_std": 0.04323085992949722, "bacc": 0.6402310924369747, "bacc_std": 0.043012070888706226} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 5, "C": 1291.5496650148827, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04151114088889901, "f1": 0.5588932806324111, "f1_std": 0.04194960983601311, "bacc": 0.5588235294117647, "bacc_std": 0.04182645664059639} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 6, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04464624509219635, "f1": 0.5670158474348643, "f1_std": 0.046734543154942645, "bacc": 0.5688025210084033, "bacc_std": 0.04528410178700407} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 7, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04295151296731073, "f1": 0.5740553647201454, "f1_std": 0.04532577730086134, "bacc": 0.576155462184874, "bacc_std": 0.04360534964925386} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 8, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04266482392829561, "f1": 0.6045708211533352, "f1_std": 0.044285384319347344, "bacc": 0.6045168067226891, "bacc_std": 0.0433675900675257} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 9, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.044660192323319414, "f1": 0.6153389215233318, "f1_std": 0.04545621416013453, "bacc": 0.6150210084033614, "bacc_std": 0.044908791021144874} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 10, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044464427667333786, "f1": 0.58994708994709, "f1_std": 0.045783405871545606, "bacc": 0.5898109243697479, "bacc_std": 0.045122527793024225} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 11, "C": 0.3593813663804626, "split": "test", "acc": 0.5080645161290323, "acc_std": 0.041267634895961115, "f1": 0.4962370962370962, "f1_std": 0.042236472808414804, "bacc": 0.49789915966386555, "bacc_std": 0.04140294053207701} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 12, "C": 0.005994842503189409, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.045068369267466525, "f1": 0.5454307410316837, "f1_std": 0.045101189052741054, "bacc": 0.5456932773109244, "bacc_std": 0.045011145921707296} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 13, "C": 0.046415888336127774, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.043491013580127635, "f1": 0.6167554415729598, "f1_std": 0.04421712747958401, "bacc": 0.6165966386554622, "bacc_std": 0.044030963510375304} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 14, "C": 2.782559402207126, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04294769402979147, "f1": 0.6063492063492064, "f1_std": 0.043820608630348507, "bacc": 0.60609243697479, "bacc_std": 0.043368887097137696} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 15, "C": 1291.5496650148827, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04493973302745094, "f1": 0.5395739691225327, "f1_std": 0.0449998443453219, "bacc": 0.5414915966386555, "bacc_std": 0.04535487070102569} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 16, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04427793626580146, "f1": 0.5740553647201454, "f1_std": 0.04591097260561043, "bacc": 0.576155462184874, "bacc_std": 0.044624919579721894} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 17, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04314043989843629, "f1": 0.5599598259122867, "f1_std": 0.04444114144964044, "bacc": 0.5614495798319328, "bacc_std": 0.04342960134591508} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 18, "C": 21.54434690031882, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04363316419525298, "f1": 0.5407407407407407, "f1_std": 0.04449217039796976, "bacc": 0.5409663865546219, "bacc_std": 0.04398735104831126} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 19, "C": 0.3593813663804626, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04501784534585998, "f1": 0.5588932806324111, "f1_std": 0.04544390340246913, "bacc": 0.5588235294117647, "bacc_std": 0.045221335833034004} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 20, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.041592905922776494, "f1": 0.6356837606837606, "f1_std": 0.043485261235150396, "bacc": 0.6355042016806722, "bacc_std": 0.042304301340790634} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 21, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04513961173234119, "f1": 0.5503626107977437, "f1_std": 0.047117613674215686, "bacc": 0.5525210084033614, "bacc_std": 0.04568836372450983} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 22, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.042625330902496775, "f1": 0.5712833028269271, "f1_std": 0.04548412365096064, "bacc": 0.5745798319327731, "bacc_std": 0.0434509485131368} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 23, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04480381561720566, "f1": 0.5880946053680574, "f1_std": 0.046350769014264354, "bacc": 0.5882352941176471, "bacc_std": 0.045510625606194725} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 24, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04372693386297777, "f1": 0.5972691721349506, "f1_std": 0.04457894828089179, "bacc": 0.5971638655462186, "bacc_std": 0.04409887485772457} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 25, "C": 21.54434690031882, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04425849948060502, "f1": 0.5529334644378892, "f1_std": 0.044753295700216966, "bacc": 0.553046218487395, "bacc_std": 0.04467618305047169} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 26, "C": 0.005994842503189409, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04495368179319451, "f1": 0.5513074349696183, "f1_std": 0.04818714162877323, "bacc": 0.5567226890756303, "bacc_std": 0.045558894187865684} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 27, "C": 0.3593813663804626, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.043199977237246855, "f1": 0.6210470369386127, "f1_std": 0.044393904059419086, "bacc": 0.6207983193277311, "bacc_std": 0.04378581149306724} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 28, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04444265500357634, "f1": 0.5907590759075907, "f1_std": 0.047118978016673835, "bacc": 0.592436974789916, "bacc_std": 0.045402049065869636} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 29, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042445606987642756, "f1": 0.6241664982824813, "f1_std": 0.0451739021056403, "bacc": 0.625, "bacc_std": 0.04357202583553351} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 30, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.044275327560540215, "f1": 0.5929621848739496, "f1_std": 0.04485207230090352, "bacc": 0.5929621848739496, "bacc_std": 0.044765000973135814} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 31, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04453675013270428, "f1": 0.5915678524374176, "f1_std": 0.045327509955712025, "bacc": 0.5913865546218487, "bacc_std": 0.04508493223747495} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 32, "C": 166.81005372000556, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04331443730060514, "f1": 0.5854473942969518, "f1_std": 0.04346322866331395, "bacc": 0.585609243697479, "bacc_std": 0.04339784369493768} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 33, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04275135623506656, "f1": 0.6227513227513227, "f1_std": 0.043466992184883556, "bacc": 0.6223739495798319, "bacc_std": 0.04304501849763443} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 34, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04234063282882618, "f1": 0.607905138339921, "f1_std": 0.043092112081540374, "bacc": 0.6076680672268908, "bacc_std": 0.042796816889084925} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 35, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.044814381889539866, "f1": 0.6004471624909581, "f1_std": 0.045479088978431205, "bacc": 0.6003151260504203, "bacc_std": 0.045245013740791595} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 36, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.03873528722737044, "f1": 0.6241664982824813, "f1_std": 0.04080478980858926, "bacc": 0.625, "bacc_std": 0.039376347841006715} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 37, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04199832450451165, "f1": 0.6283716283716283, "f1_std": 0.043426608510119674, "bacc": 0.6281512605042017, "bacc_std": 0.042631690567772065} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 38, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.044967903919734174, "f1": 0.5662332519305657, "f1_std": 0.0457125214025606, "bacc": 0.5661764705882353, "bacc_std": 0.04546098036972832} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 39, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04447214985114768, "f1": 0.5712141971683957, "f1_std": 0.04466205371513864, "bacc": 0.5724789915966386, "bacc_std": 0.04486280246770522} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 40, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04289743776140058, "f1": 0.5788211788211788, "f1_std": 0.04458060530385843, "bacc": 0.5793067226890757, "bacc_std": 0.0435962625004627} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 41, "C": 0.3593813663804626, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04158483674661302, "f1": 0.5670158474348643, "f1_std": 0.043504956269000895, "bacc": 0.5688025210084033, "bacc_std": 0.04215859772898527} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 42, "C": 1291.5496650148827, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04736247136783172, "f1": 0.5712141971683957, "f1_std": 0.04741980959511276, "bacc": 0.5724789915966386, "bacc_std": 0.04755060054771044} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 43, "C": 0.3593813663804626, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04315357469973079, "f1": 0.5662332519305657, "f1_std": 0.04408606535703067, "bacc": 0.5661764705882353, "bacc_std": 0.04362160414328353} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 44, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.042101566282678075, "f1": 0.5343756400628115, "f1_std": 0.04464840601889255, "bacc": 0.5404411764705883, "bacc_std": 0.04245107335071661} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 45, "C": 0.005994842503189409, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.042284847459365525, "f1": 0.5581140350877193, "f1_std": 0.045202461679594005, "bacc": 0.5640756302521008, "bacc_std": 0.04272463526059535} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 46, "C": 0.046415888336127774, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04251046268961711, "f1": 0.555142173797502, "f1_std": 0.04372519520856913, "bacc": 0.555672268907563, "bacc_std": 0.04308578626285256} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 47, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.03905281716619205, "f1": 0.6356837606837606, "f1_std": 0.040608572484898735, "bacc": 0.6355042016806722, "bacc_std": 0.0395745947622551} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 48, "C": 0.046415888336127774, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.043044211112549954, "f1": 0.5836690840719849, "f1_std": 0.045261871721320075, "bacc": 0.5850840336134454, "bacc_std": 0.04369736954323317} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 49, "C": 0.046415888336127774, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04145938172460453, "f1": 0.5740553647201454, "f1_std": 0.04367366725998392, "bacc": 0.576155462184874, "bacc_std": 0.04207204377294009} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 50, "C": 2.782559402207126, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.044560435524711, "f1": 0.5386659580122243, "f1_std": 0.04540312402538256, "bacc": 0.539390756302521, "bacc_std": 0.04477826050122978} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 51, "C": 0.3593813663804626, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.04196114289443608, "f1": 0.6336287939833467, "f1_std": 0.0444301022152979, "bacc": 0.6339285714285714, "bacc_std": 0.04295668951519584} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 52, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.043267538232770374, "f1": 0.5643931861867832, "f1_std": 0.04439007222378754, "bacc": 0.5646008403361344, "bacc_std": 0.04377323295877954} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 53, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04555380976128023, "f1": 0.5841388834089565, "f1_std": 0.04628499679920593, "bacc": 0.5840336134453781, "bacc_std": 0.04618248372075831} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 54, "C": 0.046415888336127774, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04404919915151349, "f1": 0.607905138339921, "f1_std": 0.04486856407534647, "bacc": 0.6076680672268908, "bacc_std": 0.04460279530927995} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 55, "C": 0.005994842503189409, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.03951604674119148, "f1": 0.5096774193548387, "f1_std": 0.042994210298022154, "bacc": 0.5210084033613446, "bacc_std": 0.03988599886791966} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 56, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04095775849908671, "f1": 0.6191239316239316, "f1_std": 0.04268570493385553, "bacc": 0.6192226890756303, "bacc_std": 0.04166668433696633} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 57, "C": 10000.0, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.04074809035827315, "f1": 0.628161668839635, "f1_std": 0.040822686318211086, "bacc": 0.6302521008403361, "bacc_std": 0.040860401187507715} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 58, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.0450012689149341, "f1": 0.58994708994709, "f1_std": 0.04626751618773533, "bacc": 0.5898109243697479, "bacc_std": 0.04577113065972449} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 59, "C": 0.005994842503189409, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.042242089445333975, "f1": 0.5931704050887178, "f1_std": 0.044193292676184756, "bacc": 0.5940126050420168, "bacc_std": 0.042983082947113546} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 60, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04409967366638658, "f1": 0.5765651155005022, "f1_std": 0.04635204942741195, "bacc": 0.5777310924369747, "bacc_std": 0.04487031530345105} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 61, "C": 0.046415888336127774, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04373535431983821, "f1": 0.5752305665349143, "f1_std": 0.04431464568516978, "bacc": 0.5751050420168067, "bacc_std": 0.0440792809743897} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 62, "C": 21.54434690031882, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.044720196128006505, "f1": 0.5550336008351275, "f1_std": 0.04490882050676395, "bacc": 0.5561974789915967, "bacc_std": 0.04510092478850601} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 63, "C": 0.046415888336127774, "split": "test", "acc": 0.6290322580645161, "acc_std": 0.046584275169074964, "f1": 0.6255252100840336, "f1_std": 0.04701167377296699, "bacc": 0.6255252100840336, "bacc_std": 0.04681276423064385} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 64, "C": 0.046415888336127774, "split": "test", "acc": 0.6612903225806451, "acc_std": 0.04028065885294668, "f1": 0.6481081081081081, "f1_std": 0.0429401579018039, "bacc": 0.6486344537815126, "bacc_std": 0.04125255943370762} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 65, "C": 0.3593813663804626, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.0455018810145084, "f1": 0.6153389215233318, "f1_std": 0.046070126888814976, "bacc": 0.6150210084033614, "bacc_std": 0.04572263399417745} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 66, "C": 166.81005372000556, "split": "test", "acc": 0.532258064516129, "acc_std": 0.04339142561448564, "f1": 0.5317708333333333, "f1_std": 0.04351924292290055, "bacc": 0.5341386554621849, "bacc_std": 0.04374376971991171} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 67, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.043452295418161514, "f1": 0.5854473942969518, "f1_std": 0.04401327540223378, "bacc": 0.585609243697479, "bacc_std": 0.04395864580039378} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 68, "C": 21.54434690031882, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04151236604747459, "f1": 0.6035753898349319, "f1_std": 0.04165215581397049, "bacc": 0.6050420168067226, "bacc_std": 0.041813622839103476} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 69, "C": 0.005994842503189409, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.040085999512546454, "f1": 0.626793588577028, "f1_std": 0.04602630390396756, "bacc": 0.6334033613445378, "bacc_std": 0.041587835136550344} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 70, "C": 1291.5496650148827, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04435047192580507, "f1": 0.5735449735449736, "f1_std": 0.04545865206707871, "bacc": 0.5735294117647058, "bacc_std": 0.044977516715817206} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 71, "C": 2.782559402207126, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04378151161878026, "f1": 0.5716183895827798, "f1_std": 0.04484709926495693, "bacc": 0.571953781512605, "bacc_std": 0.04411660226603999} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 72, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04196739170714987, "f1": 0.6063492063492064, "f1_std": 0.04283758856127532, "bacc": 0.60609243697479, "bacc_std": 0.042416460637840256} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 73, "C": 0.046415888336127774, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04196055082076618, "f1": 0.5972691721349506, "f1_std": 0.043283482309888516, "bacc": 0.5971638655462186, "bacc_std": 0.042798979315679365} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 74, "C": 0.046415888336127774, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.04351724991980451, "f1": 0.626380984265149, "f1_std": 0.04532001770371712, "bacc": 0.6265756302521008, "bacc_std": 0.044117100474305185} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 75, "C": 2.782559402207126, "split": "test", "acc": 0.6209677419354839, "acc_std": 0.04411356961223385, "f1": 0.6167554415729598, "f1_std": 0.04467528520637346, "bacc": 0.6165966386554622, "bacc_std": 0.04444876834044117} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 76, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.045654595514266476, "f1": 0.5712141971683957, "f1_std": 0.04591922360045486, "bacc": 0.5724789915966386, "bacc_std": 0.04608898179359832} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 77, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04343502569143729, "f1": 0.5623043623043623, "f1_std": 0.044781493397984096, "bacc": 0.5630252100840336, "bacc_std": 0.043965999320902206} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 78, "C": 0.005994842503189409, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04359630279124087, "f1": 0.5782312925170068, "f1_std": 0.04609870381151599, "bacc": 0.5819327731092437, "bacc_std": 0.0441266763844312} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 79, "C": 0.3593813663804626, "split": "test", "acc": 0.5403225806451613, "acc_std": 0.04351294555418249, "f1": 0.5366764995083579, "f1_std": 0.043958891892718385, "bacc": 0.5367647058823529, "bacc_std": 0.04401771358561786} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 80, "C": 0.005994842503189409, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04279741986057295, "f1": 0.607905138339921, "f1_std": 0.043302167480701995, "bacc": 0.6076680672268908, "bacc_std": 0.04296470678427449} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 81, "C": 0.3593813663804626, "split": "test", "acc": 0.6532258064516129, "acc_std": 0.04266466234615413, "f1": 0.6480760345851759, "f1_std": 0.04321881873010316, "bacc": 0.6475840336134454, "bacc_std": 0.042898516701080525} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 82, "C": 0.3593813663804626, "split": "test", "acc": 0.5967741935483871, "acc_std": 0.04119887807490142, "f1": 0.5836690840719849, "f1_std": 0.043293272164033926, "bacc": 0.5850840336134454, "bacc_std": 0.041919368781666855} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 83, "C": 2.782559402207126, "split": "test", "acc": 0.5483870967741935, "acc_std": 0.04510785721488232, "f1": 0.5454307410316837, "f1_std": 0.045376275643544295, "bacc": 0.5456932773109244, "bacc_std": 0.045404438143670865} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 84, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.043532550884050246, "f1": 0.6119947848761408, "f1_std": 0.0436963453355689, "bacc": 0.6139705882352942, "bacc_std": 0.043841582697882436} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 85, "C": 0.3593813663804626, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04278218129572632, "f1": 0.607905138339921, "f1_std": 0.04341605981491767, "bacc": 0.6076680672268908, "bacc_std": 0.04300998618436581} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 86, "C": 0.3593813663804626, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04639236813334464, "f1": 0.5841388834089565, "f1_std": 0.04695397287428437, "bacc": 0.5840336134453781, "bacc_std": 0.04677696931012307} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 87, "C": 166.81005372000556, "split": "test", "acc": 0.6129032258064516, "acc_std": 0.04405607296430788, "f1": 0.607905138339921, "f1_std": 0.04444903753352666, "bacc": 0.6076680672268908, "bacc_std": 0.044191989920764035} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 88, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04394622340439329, "f1": 0.6035753898349319, "f1_std": 0.04395717376797717, "bacc": 0.6050420168067226, "bacc_std": 0.04417283587902601} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 89, "C": 0.3593813663804626, "split": "test", "acc": 0.6048387096774194, "acc_std": 0.04450310702478559, "f1": 0.6035753898349319, "f1_std": 0.04480218043878436, "bacc": 0.6050420168067226, "bacc_std": 0.045173419704359036} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 90, "C": 0.046415888336127774, "split": "test", "acc": 0.5564516129032258, "acc_std": 0.04441490361186431, "f1": 0.5376584638329605, "f1_std": 0.04685996764646505, "bacc": 0.542016806722689, "bacc_std": 0.044907295603635655} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 91, "C": 0.005994842503189409, "split": "test", "acc": 0.5887096774193549, "acc_std": 0.04169275596676308, "f1": 0.5740553647201454, "f1_std": 0.04316167186424532, "bacc": 0.576155462184874, "bacc_std": 0.04195330516513154} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 92, "C": 1291.5496650148827, "split": "test", "acc": 0.5241935483870968, "acc_std": 0.04525939804441009, "f1": 0.5241626016260164, "f1_std": 0.04539458882673062, "bacc": 0.5283613445378151, "bacc_std": 0.0452572721817495} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 93, "C": 0.046415888336127774, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04358456084221262, "f1": 0.5573516535327002, "f1_std": 0.04543067671030717, "bacc": 0.5598739495798319, "bacc_std": 0.044003292809102035} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 94, "C": 2.782559402207126, "split": "test", "acc": 0.5725806451612904, "acc_std": 0.04350924166544126, "f1": 0.5599598259122867, "f1_std": 0.04474369651620298, "bacc": 0.5614495798319328, "bacc_std": 0.04371385251730714} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 95, "C": 0.3593813663804626, "split": "test", "acc": 0.6370967741935484, "acc_std": 0.042395967427460615, "f1": 0.626380984265149, "f1_std": 0.0442934326800233, "bacc": 0.6265756302521008, "bacc_std": 0.0431109933896401} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 96, "C": 10000.0, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.043739128276083845, "f1": 0.5716183895827798, "f1_std": 0.044999281224043924, "bacc": 0.571953781512605, "bacc_std": 0.0441973978433437} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 97, "C": 0.005994842503189409, "split": "test", "acc": 0.6693548387096774, "acc_std": 0.039253104227146444, "f1": 0.6575739206573719, "f1_std": 0.04134893750265247, "bacc": 0.657563025210084, "bacc_std": 0.040025966630817346} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 98, "C": 0.046415888336127774, "split": "test", "acc": 0.6451612903225806, "acc_std": 0.0425206658453675, "f1": 0.6336287939833467, "f1_std": 0.04452801183371108, "bacc": 0.6339285714285714, "bacc_std": 0.04319013594992082} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 99, "C": 166.81005372000556, "split": "test", "acc": 0.5806451612903226, "acc_std": 0.04630065075293955, "f1": 0.5752305665349143, "f1_std": 0.04717865573291078, "bacc": 0.5751050420168067, "bacc_std": 0.04681552931311242} +{"model": "flat_mae", "repr": "reg", "clf": "logistic", "dataset": "abide_dx", "trial": 100, "C": 0.005994842503189409, "split": "test", "acc": 0.5645161290322581, "acc_std": 0.04289129108801309, "f1": 0.5374412821221332, "f1_std": 0.04703033317132357, "bacc": 0.546218487394958, "bacc_std": 0.043783554866055806} +eval results (random splits): + +| model | repr | clf | dataset | split | n_trials | C | C_std | acc | acc_std | f1 | f1_std | bacc | bacc_std | +|:---------|:-------|:---------|:----------|:--------|-----------:|-------:|--------:|--------:|----------:|--------:|---------:|--------:|-----------:| +| flat_mae | reg | logistic | abide_dx | train | 100 | 272.68 | 1425 | 0.88425 | 0.094191 | 0.88125 | 0.09757 | 0.88001 | 0.098234 | +| flat_mae | reg | logistic | abide_dx | test | 100 | 272.68 | 1425 | 0.59468 | 0.032876 | 0.58582 | 0.03338 | 0.58694 | 0.032555 | + + +done! total time: 0:05:56 diff --git a/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/config.yaml b/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4bc41d502053c0b6b4baee6bcf80a16493f27806 --- /dev/null +++ b/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic/config.yaml @@ -0,0 +1,30 @@ +output_root: experiments/decoders/output +name_prefix: eval_logistic +remote_root: null +notes: decoder ablations crossreg_reg4; eval v2 (adhd200_dx patch logistic) +model_kwargs: + ckpt_path: experiments/decoders/output/decoders/crossreg_reg4/pretrain/checkpoint-last.pth +dataset_kwargs: {} +num_workers: 16 +batch_size: 2 +cv_folds: 5 +max_iter: 1000 +Cs: 10 +balanced_sampling: false +metrics: +- acc +- f1 +- bacc +cv_metric: bacc +n_trials: 100 +amp: true +device: cuda +seed: 4466 +debug: false +name: decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic +model: flat_mae +representation: patch +dataset: adhd200_dx +distributed: false +output_dir: experiments/decoders/output/decoders/crossreg_reg4/eval_v2/adhd200_dx__patch__logistic +remote_dir: null